diff --git a/.gitignore b/.gitignore
index bafc09d3..84bc623d 100644
--- a/.gitignore
+++ b/.gitignore
@@ -15,4 +15,6 @@ community_list
 oaidata_old/*
 results*.txt
 *.crt
-__pycache__/
\ No newline at end of file
+__pycache__/
+#ignore generated json-output
+oaitestdata/*/*/json
\ No newline at end of file
diff --git a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/e244cf61-aee1-5066-8173-f2c857c34762.json b/oaitestdata/aleph-marcxml/dataset:aleph_1/json/e244cf61-aee1-5066-8173-f2c857c34762.json
deleted file mode 100644
index ac4b41ee..00000000
--- a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/e244cf61-aee1-5066-8173-f2c857c34762.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Checksum": null,
-    "Contact": [
-        "N/A"
-    ],
-    "Discipline": "Physics",
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": "N/A",
-    "PublicationTimestamp": "2000-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "author": [
-        "Marcello Maggi"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:www.openaccessrepository.it:7151",
-        "2016-06-29T14:35:13Z",
-        "dataset:aleph",
-        "openaire",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4000.86.AL,11100/1c5c1fb2-cbe6-11e3-a0f1-e41f13eb41b2eng",
-        "00000coc  2200000uu 4500",
-        "7151",
-        "20160629143513.0",
-        "Handle",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4000.86.AL,11100/1c5c1fb2-cbe6-11e3-a0f1-e41f13eb41b2",
-        "HEP CERN LEP ALEPH MINI RealData 2000",
-        "DATASETREALDATA",
-        "Marcello Maggi",
-        "1821152968",
-        "324340920",
-        "Search for neutral Higgs bosons decaying into four taus at LEP2",
-        "10.1007/JHEP05(2010)049",
-        "2010",
-        "[1]",
-        "PUBLICATIONINFN-2014-001",
-        "[1]",
-        "10.5072/oar.it/1411041136.04 ",
-        "ALEPH SCL5 Virtual Machine for Research Environment",
-        "SOFTWAREALEPH-2014-001",
-        "[2]",
-        "ALEPH Collaboration",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4000.86.AL",
-        "ALEPH",
-        "oai:www.openaccessrepository.it:7151",
-        "openaire",
-        "dataset:aleph",
-        "ALEPH",
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4000.86.AL",
-        "2014-09-01",
-        "ALEPH",
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>55043</td><td>3665</td><td>7.737</td><td>207.929</td><td>1</td></tr> <tr> <td>55045</td><td>7248</td><td>17.418</td><td>205.123</td><td>13</td></tr> <tr> <td>55046</td><td>299</td><td>0.724</td><td>205.200</td><td>-1</td></tr> <tr> <td>55047</td><td>965</td><td>2.219</td><td>206.563</td><td>1</td></tr> <tr> <td>55049</td><td>12486</td><td>30.972</td><td>205.101</td><td>11</td></tr> <tr> <td>55050</td><td>12020</td><td>27.715</td><td>206.566</td><td>12</td></tr> <tr> <td>55053</td><td>7961</td><td>20.144</td><td>205.095</td><td>6</td></tr> <tr> <td>55054</td><td>3733</td><td>7.607</td><td>206.570</td><td>2</td></tr> <tr> <td>55056</td><td>3661</td><td>9.140</td><td>205.110</td><td>5</td></tr> <tr> <td>55057</td><td>999</td><td>2.071</td><td>205.296</td><td>3</td></tr> <tr> <td>55059</td><td>8870</td><td>21.888</td><td>205.116</td><td>13</td></tr> <tr> <td>55060</td><td>1976</td><td>4.739</td><td>206.471</td><td>4</td></tr> <tr> <td>55063</td><td>1593</td><td>3.958</td><td>205.115</td><td>2</td></tr> <tr> <td>55068</td><td>5158</td><td>12.658</td><td>205.099</td><td>3</td></tr> <tr> <td>55069</td><td>6757</td><td>16.155</td><td>206.574</td><td>7</td></tr> <tr> <td>55071</td><td>7256</td><td>18.409</td><td>205.054</td><td>8</td></tr> <tr> <td>55072</td><td>14082</td><td>34.227</td><td>206.551</td><td>20</td></tr> <tr> <td>55074</td><td>6511</td><td>16.462</td><td>205.057</td><td>7</td></tr> <tr> <td>55075</td><td>9530</td><td>22.657</td><td>206.607</td><td>16</td></tr> <tr> <td>55077</td><td>3481</td><td>8.667</td><td>205.093</td><td>6</td></tr> <tr> <td>55082</td><td>14786</td><td>36.954</td><td>205.086</td><td>17</td></tr> <tr></table> Total file length :   305.594 Mbytes",
-        "ALEPH - INFN",
-        "High Energy Physics",
-        "2000",
-        "eng",
-        "Researchers",
-        "info:eu-repo/semantics/other",
-        "Marcello Maggi"
-    ],
-    "notes": [
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>55043</td><td>3665</td><td>7.737</td><td>207.929</td><td>1</td></tr> <tr> <td>55045</td><td>7248</td><td>17.418</td><td>205.123</td><td>13</td></tr> <tr> <td>55046</td><td>299</td><td>0.724</td><td>205.200</td><td>-1</td></tr> <tr> <td>55047</td><td>965</td><td>2.219</td><td>206.563</td><td>1</td></tr> <tr> <td>55049</td><td>12486</td><td>30.972</td><td>205.101</td><td>11</td></tr> <tr> <td>55050</td><td>12020</td><td>27.715</td><td>206.566</td><td>12</td></tr> <tr> <td>55053</td><td>7961</td><td>20.144</td><td>205.095</td><td>6</td></tr> <tr> <td>55054</td><td>3733</td><td>7.607</td><td>206.570</td><td>2</td></tr> <tr> <td>55056</td><td>3661</td><td>9.140</td><td>205.110</td><td>5</td></tr> <tr> <td>55057</td><td>999</td><td>2.071</td><td>205.296</td><td>3</td></tr> <tr> <td>55059</td><td>8870</td><td>21.888</td><td>205.116</td><td>13</td></tr> <tr> <td>55060</td><td>1976</td><td>4.739</td><td>206.471</td><td>4</td></tr> <tr> <td>55063</td><td>1593</td><td>3.958</td><td>205.115</td><td>2</td></tr> <tr> <td>55068</td><td>5158</td><td>12.658</td><td>205.099</td><td>3</td></tr> <tr> <td>55069</td><td>6757</td><td>16.155</td><td>206.574</td><td>7</td></tr> <tr> <td>55071</td><td>7256</td><td>18.409</td><td>205.054</td><td>8</td></tr> <tr> <td>55072</td><td>14082</td><td>34.227</td><td>206.551</td><td>20</td></tr> <tr> <td>55074</td><td>6511</td><td>16.462</td><td>205.057</td><td>7</td></tr> <tr> <td>55075</td><td>9530</td><td>22.657</td><td>206.607</td><td>16</td></tr> <tr> <td>55077</td><td>3481</td><td>8.667</td><td>205.093</td><td>6</td></tr> <tr> <td>55082</td><td>14786</td><td>36.954</td><td>205.086</td><td>17</td></tr> <tr></table> Total file length :   305.594 Mbytes"
-    ],
-    "oai_identifier": [
-        "oai:www.openaccessrepository.it:7151"
-    ],
-    "oai_set": [
-        "dataset:aleph",
-        "openaire"
-    ],
-    "tags": [
-        {
-            "name": "HEP CERN LEP ALEPH MINI RealData"
-        }
-    ],
-    "title": [
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4000.86.AL"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/e339384a-3d79-5e54-94ca-d1986c9ee9c8.json b/oaitestdata/aleph-marcxml/dataset:aleph_1/json/e339384a-3d79-5e54-94ca-d1986c9ee9c8.json
deleted file mode 100644
index 774c5038..00000000
--- a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/e339384a-3d79-5e54-94ca-d1986c9ee9c8.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Checksum": null,
-    "Contact": [
-        "N/A"
-    ],
-    "Discipline": "Physics",
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": "N/A",
-    "PublicationTimestamp": "2000-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "author": [
-        "Marcello Maggi"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:www.openaccessrepository.it:7277",
-        "2016-06-29T14:35:14Z",
-        "dataset:aleph",
-        "openaire",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.9.AL,11100/e27f4e8c-cbe9-11e3-a29c-e41f13eb41b2eng",
-        "00000coc  2200000uu 4500",
-        "7277",
-        "20160629143514.0",
-        "Handle",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.9.AL,11100/e27f4e8c-cbe9-11e3-a29c-e41f13eb41b2",
-        "HEP CERN LEP ALEPH MINI RealData 2000",
-        "DATASETREALDATA",
-        "Marcello Maggi",
-        "544400955",
-        "310595760",
-        "Search for neutral Higgs bosons decaying into four taus at LEP2",
-        "10.1007/JHEP05(2010)049",
-        "2010",
-        "[1]",
-        "PUBLICATIONINFN-2014-001",
-        "[1]",
-        "10.5072/oar.it/1411041136.04 ",
-        "ALEPH SCL5 Virtual Machine for Research Environment",
-        "SOFTWAREALEPH-2014-001",
-        "[2]",
-        "ALEPH Collaboration",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.9.AL",
-        "ALEPH",
-        "oai:www.openaccessrepository.it:7277",
-        "openaire",
-        "dataset:aleph",
-        "ALEPH",
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4001.9.AL",
-        "2014-09-01",
-        "ALEPH",
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>55749</td><td>282</td><td>0.756</td><td>205.939</td><td>-1</td></tr> <tr> <td>55750</td><td>275</td><td>0.499</td><td>208.456</td><td>-1</td></tr> <tr> <td>55752</td><td>2604</td><td>6.244</td><td>205.282</td><td>5</td></tr> <tr> <td>55753</td><td>6227</td><td>10.565</td><td>207.846</td><td>6</td></tr> <tr> <td>55755</td><td>1323</td><td>2.987</td><td>205.169</td><td>-1</td></tr> <tr> <td>55757</td><td>2081</td><td>5.066</td><td>205.248</td><td>3</td></tr> <tr> <td>55758</td><td>6572</td><td>12.945</td><td>207.835</td><td>5</td></tr> <tr> <td>55761</td><td>542</td><td>1.141</td><td>205.325</td><td>-1</td></tr> <tr> <td>55762</td><td>69</td><td>0.187</td><td>205.325</td><td>-1</td></tr> <tr> <td>55765</td><td>2719</td><td>6.388</td><td>205.102</td><td>3</td></tr> <tr> <td>55766</td><td>2221</td><td>4.080</td><td>206.938</td><td>1</td></tr> <tr> <td>55772</td><td>4878</td><td>10.377</td><td>205.151</td><td>2</td></tr> <tr> <td>55773</td><td>6128</td><td>12.630</td><td>208.022</td><td>4</td></tr> <tr> <td>55776</td><td>4536</td><td>11.095</td><td>205.126</td><td>5</td></tr> <tr> <td>55777</td><td>6745</td><td>14.753</td><td>208.036</td><td>5</td></tr> <tr> <td>55779</td><td>1910</td><td>4.551</td><td>205.085</td><td>-1</td></tr> <tr> <td>55781</td><td>2892</td><td>7.260</td><td>205.116</td><td>6</td></tr> <tr> <td>55782</td><td>6141</td><td>13.095</td><td>207.557</td><td>3</td></tr> <tr> <td>55784</td><td>3880</td><td>9.532</td><td>205.143</td><td>7</td></tr> <tr> <td>55785</td><td>3816</td><td>8.313</td><td>208.016</td><td>4</td></tr> <tr> <td>55787</td><td>596</td><td>1.452</td><td>205.097</td><td>1</td></tr> <tr> <td>55790</td><td>3721</td><td>7.512</td><td>208.036</td><td>7</td></tr> <tr> <td>55793</td><td>3719</td><td>9.192</td><td>205.135</td><td>3</td></tr> <tr> <td>55794</td><td>8870</td><td>20.263</td><td>207.691</td><td>9</td></tr> <tr> <td>55796</td><td>4477</td><td>11.074</td><td>205.146</td><td>4</td></tr> <tr> <td>55797</td><td>8835</td><td>19.166</td><td>208.043</td><td>9</td></tr> <tr> <td>55799</td><td>4194</td><td>10.210</td><td>205.142</td><td>3</td></tr> <tr> <td>55800</td><td>2464</td><td>5.056</td><td>206.871</td><td>3</td></tr> <tr> <td>55802</td><td>4726</td><td>11.568</td><td>205.175</td><td>5</td></tr> <tr> <td>55803</td><td>3716</td><td>7.440</td><td>207.223</td><td>1</td></tr> <tr> <td>55806</td><td>8154</td><td>20.107</td><td>205.158</td><td>10</td></tr> <tr> <td>55807</td><td>2683</td><td>5.596</td><td>208.004</td><td>4</td></tr> <tr> <td>55809</td><td>5861</td><td>13.639</td><td>205.120</td><td>7</td></tr> <tr> <td>55810</td><td>5209</td><td>11.147</td><td>207.654</td><td>4</td></tr> <tr> <td>55812</td><td>5281</td><td>12.619</td><td>205.118</td><td>8</td></tr> <tr></table> Total file length :   305.594 Mbytes",
-        "ALEPH - INFN",
-        "High Energy Physics",
-        "2000",
-        "eng",
-        "Researchers",
-        "info:eu-repo/semantics/other",
-        "Marcello Maggi"
-    ],
-    "notes": [
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>55749</td><td>282</td><td>0.756</td><td>205.939</td><td>-1</td></tr> <tr> <td>55750</td><td>275</td><td>0.499</td><td>208.456</td><td>-1</td></tr> <tr> <td>55752</td><td>2604</td><td>6.244</td><td>205.282</td><td>5</td></tr> <tr> <td>55753</td><td>6227</td><td>10.565</td><td>207.846</td><td>6</td></tr> <tr> <td>55755</td><td>1323</td><td>2.987</td><td>205.169</td><td>-1</td></tr> <tr> <td>55757</td><td>2081</td><td>5.066</td><td>205.248</td><td>3</td></tr> <tr> <td>55758</td><td>6572</td><td>12.945</td><td>207.835</td><td>5</td></tr> <tr> <td>55761</td><td>542</td><td>1.141</td><td>205.325</td><td>-1</td></tr> <tr> <td>55762</td><td>69</td><td>0.187</td><td>205.325</td><td>-1</td></tr> <tr> <td>55765</td><td>2719</td><td>6.388</td><td>205.102</td><td>3</td></tr> <tr> <td>55766</td><td>2221</td><td>4.080</td><td>206.938</td><td>1</td></tr> <tr> <td>55772</td><td>4878</td><td>10.377</td><td>205.151</td><td>2</td></tr> <tr> <td>55773</td><td>6128</td><td>12.630</td><td>208.022</td><td>4</td></tr> <tr> <td>55776</td><td>4536</td><td>11.095</td><td>205.126</td><td>5</td></tr> <tr> <td>55777</td><td>6745</td><td>14.753</td><td>208.036</td><td>5</td></tr> <tr> <td>55779</td><td>1910</td><td>4.551</td><td>205.085</td><td>-1</td></tr> <tr> <td>55781</td><td>2892</td><td>7.260</td><td>205.116</td><td>6</td></tr> <tr> <td>55782</td><td>6141</td><td>13.095</td><td>207.557</td><td>3</td></tr> <tr> <td>55784</td><td>3880</td><td>9.532</td><td>205.143</td><td>7</td></tr> <tr> <td>55785</td><td>3816</td><td>8.313</td><td>208.016</td><td>4</td></tr> <tr> <td>55787</td><td>596</td><td>1.452</td><td>205.097</td><td>1</td></tr> <tr> <td>55790</td><td>3721</td><td>7.512</td><td>208.036</td><td>7</td></tr> <tr> <td>55793</td><td>3719</td><td>9.192</td><td>205.135</td><td>3</td></tr> <tr> <td>55794</td><td>8870</td><td>20.263</td><td>207.691</td><td>9</td></tr> <tr> <td>55796</td><td>4477</td><td>11.074</td><td>205.146</td><td>4</td></tr> <tr> <td>55797</td><td>8835</td><td>19.166</td><td>208.043</td><td>9</td></tr> <tr> <td>55799</td><td>4194</td><td>10.210</td><td>205.142</td><td>3</td></tr> <tr> <td>55800</td><td>2464</td><td>5.056</td><td>206.871</td><td>3</td></tr> <tr> <td>55802</td><td>4726</td><td>11.568</td><td>205.175</td><td>5</td></tr> <tr> <td>55803</td><td>3716</td><td>7.440</td><td>207.223</td><td>1</td></tr> <tr> <td>55806</td><td>8154</td><td>20.107</td><td>205.158</td><td>10</td></tr> <tr> <td>55807</td><td>2683</td><td>5.596</td><td>208.004</td><td>4</td></tr> <tr> <td>55809</td><td>5861</td><td>13.639</td><td>205.120</td><td>7</td></tr> <tr> <td>55810</td><td>5209</td><td>11.147</td><td>207.654</td><td>4</td></tr> <tr> <td>55812</td><td>5281</td><td>12.619</td><td>205.118</td><td>8</td></tr> <tr></table> Total file length :   305.594 Mbytes"
-    ],
-    "oai_identifier": [
-        "oai:www.openaccessrepository.it:7277"
-    ],
-    "oai_set": [
-        "dataset:aleph",
-        "openaire"
-    ],
-    "tags": [
-        {
-            "name": "HEP CERN LEP ALEPH MINI RealData"
-        }
-    ],
-    "title": [
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4001.9.AL"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/e52092e4-0de6-5dbb-b863-298a57beac39.json b/oaitestdata/aleph-marcxml/dataset:aleph_1/json/e52092e4-0de6-5dbb-b863-298a57beac39.json
deleted file mode 100644
index e48b01ca..00000000
--- a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/e52092e4-0de6-5dbb-b863-298a57beac39.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Checksum": null,
-    "Contact": [
-        "N/A"
-    ],
-    "Discipline": "Physics",
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": "N/A",
-    "PublicationTimestamp": "2000-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "author": [
-        "Marcello Maggi"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:www.openaccessrepository.it:7190",
-        "2016-06-29T14:35:13Z",
-        "dataset:aleph",
-        "openaire",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4000.72.AL,11100/913aae58-cbe5-11e3-be28-e41f13eb41b2\neng",
-        "00000coc  2200000uu 4500",
-        "7190",
-        "20160629143513.0",
-        "Handle",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4000.72.AL,11100/913aae58-cbe5-11e3-be28-e41f13eb41b2\n",
-        "ALEPH",
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4000.72.AL",
-        "2014-09-01",
-        "ALEPH",
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>54641</td><td>3697</td><td>8.555</td><td>206.544</td><td>7</td></tr> <tr> <td>54643</td><td>7990</td><td>19.732</td><td>205.092</td><td>8</td></tr> <tr> <td>54644</td><td>3299</td><td>7.753</td><td>206.468</td><td>5</td></tr> <tr> <td>54646</td><td>8535</td><td>20.197</td><td>205.093</td><td>5</td></tr> <tr> <td>54647</td><td>473</td><td>1.014</td><td>206.581</td><td>-1</td></tr> <tr> <td>54649</td><td>8011</td><td>19.550</td><td>205.102</td><td>11</td></tr> <tr> <td>54650</td><td>404</td><td>0.956</td><td>205.876</td><td>-1</td></tr> <tr> <td>54651</td><td>1335</td><td>3.078</td><td>206.576</td><td>2</td></tr> <tr> <td>54653</td><td>7504</td><td>18.028</td><td>205.102</td><td>8</td></tr> <tr> <td>54654</td><td>1258</td><td>2.268</td><td>206.472</td><td>-1</td></tr> <tr> <td>54656</td><td>5478</td><td>13.893</td><td>205.100</td><td>7</td></tr> <tr> <td>54657</td><td>19543</td><td>44.210</td><td>206.603</td><td>18</td></tr> <tr> <td>54658</td><td>3443</td><td>6.092</td><td>206.633</td><td>3</td></tr> <tr> <td>54659</td><td>4209</td><td>6.368</td><td>207.830</td><td>1</td></tr> <tr> <td>54661</td><td>6351</td><td>15.960</td><td>205.130</td><td>10</td></tr> <tr> <td>54662</td><td>11827</td><td>27.274</td><td>206.604</td><td>17</td></tr> <tr> <td>54664</td><td>17907</td><td>43.151</td><td>205.125</td><td>20</td></tr> <tr> <td>54665</td><td>6180</td><td>13.097</td><td>206.651</td><td>7</td></tr> <tr> <td>54666</td><td>2592</td><td>4.492</td><td>207.892</td><td>4</td></tr> <tr> <td>54668</td><td>5329</td><td>12.884</td><td>205.140</td><td>2</td></tr> <tr> <td>54669</td><td>3335</td><td>6.785</td><td>206.632</td><td>4</td></tr> <tr> <td>54671</td><td>7891</td><td>19.378</td><td>205.133</td><td>7</td></tr> <tr></table> Total file length :   305.594 Mbytes",
-        "HEP CERN LEP ALEPH MINI RealData 2000",
-        "ALEPH Collaboration",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4000.72.AL",
-        "ALEPH",
-        "oai:www.openaccessrepository.it:7190",
-        "openaire",
-        "dataset:aleph",
-        "High Energy Physics",
-        "2000",
-        "ALEPH - INFN",
-        "DATASETREALDATA",
-        "Marcello Maggi",
-        "3391633296",
-        "316651320",
-        "Search for neutral Higgs bosons decaying into four taus at LEP2",
-        "10.1007/JHEP05(2010)049",
-        "2010",
-        "[1]",
-        "PUBLICATIONINFN-2014-001",
-        "[1]",
-        "10.5072/oar.it/1411041136.04 ",
-        "ALEPH SCL5 Virtual Machine for Research Environment",
-        "SOFTWAREALEPH-2014-001",
-        "[2]",
-        "eng",
-        "Researchers",
-        "info:eu-repo/semantics/other",
-        "Marcello Maggi"
-    ],
-    "notes": [
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>54641</td><td>3697</td><td>8.555</td><td>206.544</td><td>7</td></tr> <tr> <td>54643</td><td>7990</td><td>19.732</td><td>205.092</td><td>8</td></tr> <tr> <td>54644</td><td>3299</td><td>7.753</td><td>206.468</td><td>5</td></tr> <tr> <td>54646</td><td>8535</td><td>20.197</td><td>205.093</td><td>5</td></tr> <tr> <td>54647</td><td>473</td><td>1.014</td><td>206.581</td><td>-1</td></tr> <tr> <td>54649</td><td>8011</td><td>19.550</td><td>205.102</td><td>11</td></tr> <tr> <td>54650</td><td>404</td><td>0.956</td><td>205.876</td><td>-1</td></tr> <tr> <td>54651</td><td>1335</td><td>3.078</td><td>206.576</td><td>2</td></tr> <tr> <td>54653</td><td>7504</td><td>18.028</td><td>205.102</td><td>8</td></tr> <tr> <td>54654</td><td>1258</td><td>2.268</td><td>206.472</td><td>-1</td></tr> <tr> <td>54656</td><td>5478</td><td>13.893</td><td>205.100</td><td>7</td></tr> <tr> <td>54657</td><td>19543</td><td>44.210</td><td>206.603</td><td>18</td></tr> <tr> <td>54658</td><td>3443</td><td>6.092</td><td>206.633</td><td>3</td></tr> <tr> <td>54659</td><td>4209</td><td>6.368</td><td>207.830</td><td>1</td></tr> <tr> <td>54661</td><td>6351</td><td>15.960</td><td>205.130</td><td>10</td></tr> <tr> <td>54662</td><td>11827</td><td>27.274</td><td>206.604</td><td>17</td></tr> <tr> <td>54664</td><td>17907</td><td>43.151</td><td>205.125</td><td>20</td></tr> <tr> <td>54665</td><td>6180</td><td>13.097</td><td>206.651</td><td>7</td></tr> <tr> <td>54666</td><td>2592</td><td>4.492</td><td>207.892</td><td>4</td></tr> <tr> <td>54668</td><td>5329</td><td>12.884</td><td>205.140</td><td>2</td></tr> <tr> <td>54669</td><td>3335</td><td>6.785</td><td>206.632</td><td>4</td></tr> <tr> <td>54671</td><td>7891</td><td>19.378</td><td>205.133</td><td>7</td></tr> <tr></table> Total file length :   305.594 Mbytes"
-    ],
-    "oai_identifier": [
-        "oai:www.openaccessrepository.it:7190"
-    ],
-    "oai_set": [
-        "dataset:aleph",
-        "openaire"
-    ],
-    "tags": [
-        {
-            "name": "HEP CERN LEP ALEPH MINI RealData"
-        }
-    ],
-    "title": [
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4000.72.AL"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/e55895a9-9c37-5ffe-9dab-da2cd1a93951.json b/oaitestdata/aleph-marcxml/dataset:aleph_1/json/e55895a9-9c37-5ffe-9dab-da2cd1a93951.json
deleted file mode 100644
index 40e334f4..00000000
--- a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/e55895a9-9c37-5ffe-9dab-da2cd1a93951.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Checksum": null,
-    "Contact": [
-        "N/A"
-    ],
-    "Discipline": "Physics",
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": "N/A",
-    "PublicationTimestamp": "2000-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "author": [
-        "Marcello Maggi"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:www.openaccessrepository.it:7243",
-        "2016-06-29T14:35:15Z",
-        "dataset:aleph",
-        "openaire",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.72.AL,11100/310e6fac-cbe9-11e3-856a-e41f13eb41b2eng",
-        "00000coc  2200000uu 4500",
-        "7243",
-        "20160629143515.0",
-        "Handle",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.72.AL,11100/310e6fac-cbe9-11e3-856a-e41f13eb41b2",
-        "HEP CERN LEP ALEPH MINI RealData 2000",
-        "DATASETREALDATA",
-        "Marcello Maggi",
-        "3075523334",
-        "305245080",
-        "Search for neutral Higgs bosons decaying into four taus at LEP2",
-        "10.1007/JHEP05(2010)049",
-        "2010",
-        "[1]",
-        "PUBLICATIONINFN-2014-001",
-        "[1]",
-        "10.5072/oar.it/1411041136.04 ",
-        "ALEPH SCL5 Virtual Machine for Research Environment",
-        "SOFTWAREALEPH-2014-001",
-        "[2]",
-        "ALEPH Collaboration",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.72.AL",
-        "ALEPH",
-        "oai:www.openaccessrepository.it:7243",
-        "openaire",
-        "dataset:aleph",
-        "ALEPH",
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4001.72.AL",
-        "2014-09-01",
-        "ALEPH",
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>57882</td><td>17682</td><td>50.865</td><td>206.150</td><td>21</td></tr> <tr> <td>57883</td><td>4340</td><td>12.202</td><td>206.153</td><td>6</td></tr> <tr> <td>57884</td><td>679</td><td>1.502</td><td>207.717</td><td>-1</td></tr> <tr> <td>57886</td><td>7500</td><td>20.724</td><td>206.147</td><td>12</td></tr> <tr> <td>57888</td><td>15011</td><td>43.615</td><td>206.146</td><td>13</td></tr> <tr> <td>57908</td><td>7191</td><td>17.234</td><td>205.524</td><td>4</td></tr> <tr> <td>58008</td><td>1160</td><td>2.907</td><td>206.429</td><td>1</td></tr> <tr> <td>58009</td><td>314</td><td>0.686</td><td>207.790</td><td>-1</td></tr> <tr> <td>58011</td><td>16692</td><td>47.240</td><td>206.391</td><td>25</td></tr> <tr> <td>58012</td><td>7394</td><td>20.457</td><td>206.396</td><td>13</td></tr> <tr> <td>58172</td><td>1210</td><td>2.757</td><td>207.393</td><td>-1</td></tr> <tr> <td>58174</td><td>932</td><td>2.449</td><td>206.372</td><td>1</td></tr> <tr> <td>58177</td><td>17147</td><td>49.112</td><td>206.365</td><td>24</td></tr> <tr> <td>58178</td><td>4139</td><td>11.252</td><td>206.372</td><td>5</td></tr> <tr> <td>58179</td><td>2160</td><td>5.440</td><td>207.704</td><td>2</td></tr> <tr> <td>58181</td><td>5362</td><td>15.344</td><td>206.382</td><td>5</td></tr> <tr></table> Total file length :   305.594 Mbytes",
-        "ALEPH - INFN",
-        "High Energy Physics",
-        "2000",
-        "eng",
-        "Researchers",
-        "info:eu-repo/semantics/other",
-        "Marcello Maggi"
-    ],
-    "notes": [
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>57882</td><td>17682</td><td>50.865</td><td>206.150</td><td>21</td></tr> <tr> <td>57883</td><td>4340</td><td>12.202</td><td>206.153</td><td>6</td></tr> <tr> <td>57884</td><td>679</td><td>1.502</td><td>207.717</td><td>-1</td></tr> <tr> <td>57886</td><td>7500</td><td>20.724</td><td>206.147</td><td>12</td></tr> <tr> <td>57888</td><td>15011</td><td>43.615</td><td>206.146</td><td>13</td></tr> <tr> <td>57908</td><td>7191</td><td>17.234</td><td>205.524</td><td>4</td></tr> <tr> <td>58008</td><td>1160</td><td>2.907</td><td>206.429</td><td>1</td></tr> <tr> <td>58009</td><td>314</td><td>0.686</td><td>207.790</td><td>-1</td></tr> <tr> <td>58011</td><td>16692</td><td>47.240</td><td>206.391</td><td>25</td></tr> <tr> <td>58012</td><td>7394</td><td>20.457</td><td>206.396</td><td>13</td></tr> <tr> <td>58172</td><td>1210</td><td>2.757</td><td>207.393</td><td>-1</td></tr> <tr> <td>58174</td><td>932</td><td>2.449</td><td>206.372</td><td>1</td></tr> <tr> <td>58177</td><td>17147</td><td>49.112</td><td>206.365</td><td>24</td></tr> <tr> <td>58178</td><td>4139</td><td>11.252</td><td>206.372</td><td>5</td></tr> <tr> <td>58179</td><td>2160</td><td>5.440</td><td>207.704</td><td>2</td></tr> <tr> <td>58181</td><td>5362</td><td>15.344</td><td>206.382</td><td>5</td></tr> <tr></table> Total file length :   305.594 Mbytes"
-    ],
-    "oai_identifier": [
-        "oai:www.openaccessrepository.it:7243"
-    ],
-    "oai_set": [
-        "dataset:aleph",
-        "openaire"
-    ],
-    "tags": [
-        {
-            "name": "HEP CERN LEP ALEPH MINI RealData"
-        }
-    ],
-    "title": [
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4001.72.AL"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/e8e7c864-7595-553f-ba4a-a2a66963288e.json b/oaitestdata/aleph-marcxml/dataset:aleph_1/json/e8e7c864-7595-553f-ba4a-a2a66963288e.json
deleted file mode 100644
index 125189b7..00000000
--- a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/e8e7c864-7595-553f-ba4a-a2a66963288e.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Checksum": null,
-    "Contact": [
-        "N/A"
-    ],
-    "Discipline": "Physics",
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": "N/A",
-    "PublicationTimestamp": "2000-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "author": [
-        "Marcello Maggi"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:www.openaccessrepository.it:7189",
-        "2016-06-29T14:35:13Z",
-        "dataset:aleph",
-        "openaire",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.23.AL,11100/2bf30d5e-cbe7-11e3-83a8-e41f13eb41b2\neng",
-        "00000coc  2200000uu 4500",
-        "7189",
-        "20160629143513.0",
-        "Handle",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.23.AL,11100/2bf30d5e-cbe7-11e3-83a8-e41f13eb41b2\n",
-        "ALEPH",
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4001.23.AL",
-        "2014-09-01",
-        "ALEPH",
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>56321</td><td>2784</td><td>5.681</td><td>207.803</td><td>-1</td></tr> <tr> <td>56323</td><td>4656</td><td>10.939</td><td>205.195</td><td>5</td></tr> <tr> <td>56324</td><td>718</td><td>1.493</td><td>207.767</td><td>2</td></tr> <tr> <td>56327</td><td>2406</td><td>6.421</td><td>205.189</td><td>5</td></tr> <tr> <td>56328</td><td>258</td><td>0.644</td><td>206.314</td><td>-1</td></tr> <tr> <td>56329</td><td>4782</td><td>12.645</td><td>206.371</td><td>8</td></tr> <tr> <td>56331</td><td>4680</td><td>11.271</td><td>205.180</td><td>11</td></tr> <tr> <td>56332</td><td>16725</td><td>39.637</td><td>206.336</td><td>20</td></tr> <tr> <td>56334</td><td>21275</td><td>53.597</td><td>205.187</td><td>34</td></tr> <tr> <td>56335</td><td>8419</td><td>20.278</td><td>206.579</td><td>6</td></tr> <tr> <td>56338</td><td>3474</td><td>9.469</td><td>205.183</td><td>2</td></tr> <tr> <td>56339</td><td>12033</td><td>29.312</td><td>206.588</td><td>13</td></tr> <tr> <td>56341</td><td>4802</td><td>10.716</td><td>205.202</td><td>4</td></tr> <tr> <td>56342</td><td>8971</td><td>23.839</td><td>206.378</td><td>14</td></tr> <tr> <td>56343</td><td>761</td><td>1.417</td><td>207.701</td><td>-1</td></tr> <tr> <td>56345</td><td>1831</td><td>4.602</td><td>205.170</td><td>1</td></tr> <tr> <td>56346</td><td>3661</td><td>4.705</td><td>206.355</td><td>3</td></tr> <tr> <td>56349</td><td>3009</td><td>7.562</td><td>205.180</td><td>3</td></tr> <tr> <td>56350</td><td>13026</td><td>33.436</td><td>206.374</td><td>14</td></tr> <tr> <td>56351</td><td>5621</td><td>12.616</td><td>207.825</td><td>3</td></tr> <tr> <td>56355</td><td>4688</td><td>11.885</td><td>205.181</td><td>6</td></tr> <tr></table> Total file length :   305.594 Mbytes",
-        "HEP CERN LEP ALEPH MINI RealData 2000",
-        "ALEPH Collaboration",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.23.AL",
-        "ALEPH",
-        "oai:www.openaccessrepository.it:7189",
-        "openaire",
-        "dataset:aleph",
-        "High Energy Physics",
-        "2000",
-        "ALEPH - INFN",
-        "DATASETREALDATA",
-        "Marcello Maggi",
-        "1515644344",
-        "313959960",
-        "Search for neutral Higgs bosons decaying into four taus at LEP2",
-        "10.1007/JHEP05(2010)049",
-        "2010",
-        "[1]",
-        "PUBLICATIONINFN-2014-001",
-        "[1]",
-        "10.5072/oar.it/1411041136.04 ",
-        "ALEPH SCL5 Virtual Machine for Research Environment",
-        "SOFTWAREALEPH-2014-001",
-        "[2]",
-        "eng",
-        "Researchers",
-        "info:eu-repo/semantics/other",
-        "Marcello Maggi"
-    ],
-    "notes": [
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>56321</td><td>2784</td><td>5.681</td><td>207.803</td><td>-1</td></tr> <tr> <td>56323</td><td>4656</td><td>10.939</td><td>205.195</td><td>5</td></tr> <tr> <td>56324</td><td>718</td><td>1.493</td><td>207.767</td><td>2</td></tr> <tr> <td>56327</td><td>2406</td><td>6.421</td><td>205.189</td><td>5</td></tr> <tr> <td>56328</td><td>258</td><td>0.644</td><td>206.314</td><td>-1</td></tr> <tr> <td>56329</td><td>4782</td><td>12.645</td><td>206.371</td><td>8</td></tr> <tr> <td>56331</td><td>4680</td><td>11.271</td><td>205.180</td><td>11</td></tr> <tr> <td>56332</td><td>16725</td><td>39.637</td><td>206.336</td><td>20</td></tr> <tr> <td>56334</td><td>21275</td><td>53.597</td><td>205.187</td><td>34</td></tr> <tr> <td>56335</td><td>8419</td><td>20.278</td><td>206.579</td><td>6</td></tr> <tr> <td>56338</td><td>3474</td><td>9.469</td><td>205.183</td><td>2</td></tr> <tr> <td>56339</td><td>12033</td><td>29.312</td><td>206.588</td><td>13</td></tr> <tr> <td>56341</td><td>4802</td><td>10.716</td><td>205.202</td><td>4</td></tr> <tr> <td>56342</td><td>8971</td><td>23.839</td><td>206.378</td><td>14</td></tr> <tr> <td>56343</td><td>761</td><td>1.417</td><td>207.701</td><td>-1</td></tr> <tr> <td>56345</td><td>1831</td><td>4.602</td><td>205.170</td><td>1</td></tr> <tr> <td>56346</td><td>3661</td><td>4.705</td><td>206.355</td><td>3</td></tr> <tr> <td>56349</td><td>3009</td><td>7.562</td><td>205.180</td><td>3</td></tr> <tr> <td>56350</td><td>13026</td><td>33.436</td><td>206.374</td><td>14</td></tr> <tr> <td>56351</td><td>5621</td><td>12.616</td><td>207.825</td><td>3</td></tr> <tr> <td>56355</td><td>4688</td><td>11.885</td><td>205.181</td><td>6</td></tr> <tr></table> Total file length :   305.594 Mbytes"
-    ],
-    "oai_identifier": [
-        "oai:www.openaccessrepository.it:7189"
-    ],
-    "oai_set": [
-        "dataset:aleph",
-        "openaire"
-    ],
-    "tags": [
-        {
-            "name": "HEP CERN LEP ALEPH MINI RealData"
-        }
-    ],
-    "title": [
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4001.23.AL"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/e8f3a28c-cf27-5838-a479-b0d049d2a185.json b/oaitestdata/aleph-marcxml/dataset:aleph_1/json/e8f3a28c-cf27-5838-a479-b0d049d2a185.json
deleted file mode 100644
index 7069dc7c..00000000
--- a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/e8f3a28c-cf27-5838-a479-b0d049d2a185.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Checksum": null,
-    "Contact": [
-        "N/A"
-    ],
-    "Discipline": "Physics",
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": "N/A",
-    "PublicationTimestamp": "2000-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "author": [
-        "Marcello Maggi"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:www.openaccessrepository.it:7185",
-        "2016-06-29T14:35:13Z",
-        "dataset:aleph",
-        "openaire",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4000.56.AL,11100/f5fd9eb4-cbe4-11e3-9623-e41f13eb41b2\neng",
-        "00000coc  2200000uu 4500",
-        "7185",
-        "20160629143513.0",
-        "Handle",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4000.56.AL,11100/f5fd9eb4-cbe4-11e3-9623-e41f13eb41b2\n",
-        "ALEPH",
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4000.56.AL",
-        "2014-09-01",
-        "ALEPH",
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>54242</td><td>5517</td><td>11.396</td><td>206.247</td><td>2</td></tr> <tr> <td>54243</td><td>2252</td><td>3.694</td><td>207.310</td><td>1</td></tr> <tr> <td>54245</td><td>384</td><td>1.064</td><td>204.867</td><td>-1</td></tr> <tr> <td>54247</td><td>19166</td><td>45.802</td><td>204.884</td><td>16</td></tr> <tr> <td>54248</td><td>14880</td><td>32.272</td><td>206.279</td><td>17</td></tr> <tr> <td>54250</td><td>19456</td><td>46.805</td><td>204.876</td><td>13</td></tr> <tr> <td>54251</td><td>1346</td><td>2.882</td><td>205.059</td><td>-1</td></tr> <tr> <td>54252</td><td>1519</td><td>3.305</td><td>206.176</td><td>3</td></tr> <tr> <td>54255</td><td>9478</td><td>22.646</td><td>204.877</td><td>13</td></tr> <tr> <td>54257</td><td>3103</td><td>5.422</td><td>204.892</td><td>1</td></tr> <tr> <td>54260</td><td>17799</td><td>42.752</td><td>204.874</td><td>19</td></tr> <tr> <td>54261</td><td>6000</td><td>13.242</td><td>206.244</td><td>6</td></tr> <tr> <td>54264</td><td>3207</td><td>7.797</td><td>205.067</td><td>3</td></tr> <tr> <td>54267</td><td>14073</td><td>33.767</td><td>205.076</td><td>16</td></tr> <tr> <td>56572</td><td>11460</td><td>57.959</td><td>91.288</td><td>1902</td></tr> <tr></table> Total file length :   305.594 Mbytes",
-        "HEP CERN LEP ALEPH MINI RealData 2000",
-        "ALEPH Collaboration",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4000.56.AL",
-        "ALEPH",
-        "oai:www.openaccessrepository.it:7185",
-        "openaire",
-        "dataset:aleph",
-        "High Energy Physics",
-        "2000",
-        "ALEPH - INFN",
-        "DATASETREALDATA",
-        "Marcello Maggi",
-        "3941248621",
-        "332575200",
-        "Search for neutral Higgs bosons decaying into four taus at LEP2",
-        "10.1007/JHEP05(2010)049",
-        "2010",
-        "[1]",
-        "PUBLICATIONINFN-2014-001",
-        "[1]",
-        "10.5072/oar.it/1411041136.04 ",
-        "ALEPH SCL5 Virtual Machine for Research Environment",
-        "SOFTWAREALEPH-2014-001",
-        "[2]",
-        "eng",
-        "Researchers",
-        "info:eu-repo/semantics/other",
-        "Marcello Maggi"
-    ],
-    "notes": [
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>54242</td><td>5517</td><td>11.396</td><td>206.247</td><td>2</td></tr> <tr> <td>54243</td><td>2252</td><td>3.694</td><td>207.310</td><td>1</td></tr> <tr> <td>54245</td><td>384</td><td>1.064</td><td>204.867</td><td>-1</td></tr> <tr> <td>54247</td><td>19166</td><td>45.802</td><td>204.884</td><td>16</td></tr> <tr> <td>54248</td><td>14880</td><td>32.272</td><td>206.279</td><td>17</td></tr> <tr> <td>54250</td><td>19456</td><td>46.805</td><td>204.876</td><td>13</td></tr> <tr> <td>54251</td><td>1346</td><td>2.882</td><td>205.059</td><td>-1</td></tr> <tr> <td>54252</td><td>1519</td><td>3.305</td><td>206.176</td><td>3</td></tr> <tr> <td>54255</td><td>9478</td><td>22.646</td><td>204.877</td><td>13</td></tr> <tr> <td>54257</td><td>3103</td><td>5.422</td><td>204.892</td><td>1</td></tr> <tr> <td>54260</td><td>17799</td><td>42.752</td><td>204.874</td><td>19</td></tr> <tr> <td>54261</td><td>6000</td><td>13.242</td><td>206.244</td><td>6</td></tr> <tr> <td>54264</td><td>3207</td><td>7.797</td><td>205.067</td><td>3</td></tr> <tr> <td>54267</td><td>14073</td><td>33.767</td><td>205.076</td><td>16</td></tr> <tr> <td>56572</td><td>11460</td><td>57.959</td><td>91.288</td><td>1902</td></tr> <tr></table> Total file length :   305.594 Mbytes"
-    ],
-    "oai_identifier": [
-        "oai:www.openaccessrepository.it:7185"
-    ],
-    "oai_set": [
-        "dataset:aleph",
-        "openaire"
-    ],
-    "tags": [
-        {
-            "name": "HEP CERN LEP ALEPH MINI RealData"
-        }
-    ],
-    "title": [
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4000.56.AL"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/e9a84abe-1e4b-50a1-8634-a0851b203fd1.json b/oaitestdata/aleph-marcxml/dataset:aleph_1/json/e9a84abe-1e4b-50a1-8634-a0851b203fd1.json
deleted file mode 100644
index 8e5a2086..00000000
--- a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/e9a84abe-1e4b-50a1-8634-a0851b203fd1.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Checksum": null,
-    "Contact": [
-        "N/A"
-    ],
-    "Discipline": "Physics",
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": "N/A",
-    "PublicationTimestamp": "2000-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "author": [
-        "Marcello Maggi"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:www.openaccessrepository.it:7269",
-        "2016-06-29T14:35:15Z",
-        "dataset:aleph",
-        "openaire",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4000.83.AL,11100/fe5d7ede-cbe5-11e3-868f-e41f13eb41b2eng",
-        "00000coc  2200000uu 4500",
-        "7269",
-        "20160629143515.0",
-        "Handle",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4000.83.AL,11100/fe5d7ede-cbe5-11e3-868f-e41f13eb41b2",
-        "HEP CERN LEP ALEPH MINI RealData 2000",
-        "DATASETREALDATA",
-        "Marcello Maggi",
-        "2737411411",
-        "308352960",
-        "Search for neutral Higgs bosons decaying into four taus at LEP2",
-        "10.1007/JHEP05(2010)049",
-        "2010",
-        "[1]",
-        "PUBLICATIONINFN-2014-001",
-        "[1]",
-        "10.5072/oar.it/1411041136.04 ",
-        "ALEPH SCL5 Virtual Machine for Research Environment",
-        "SOFTWAREALEPH-2014-001",
-        "[2]",
-        "ALEPH Collaboration",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4000.83.AL",
-        "ALEPH",
-        "oai:www.openaccessrepository.it:7269",
-        "openaire",
-        "dataset:aleph",
-        "ALEPH",
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4000.83.AL",
-        "2014-09-01",
-        "ALEPH",
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>54956</td><td>19822</td><td>45.622</td><td>206.608</td><td>18</td></tr> <tr> <td>54957</td><td>1726</td><td>2.710</td><td>207.887</td><td>2</td></tr> <tr> <td>54960</td><td>4936</td><td>12.234</td><td>205.100</td><td>7</td></tr> <tr> <td>54961</td><td>18567</td><td>41.795</td><td>206.573</td><td>8</td></tr> <tr> <td>54962</td><td>405</td><td>0.431</td><td>207.375</td><td>1</td></tr> <tr> <td>54964</td><td>8179</td><td>20.148</td><td>205.111</td><td>8</td></tr> <tr> <td>54965</td><td>1726</td><td>4.136</td><td>206.582</td><td>2</td></tr> <tr> <td>54967</td><td>8964</td><td>21.572</td><td>205.122</td><td>12</td></tr> <tr> <td>54968</td><td>17495</td><td>38.870</td><td>206.523</td><td>22</td></tr> <tr> <td>54969</td><td>9507</td><td>19.471</td><td>208.073</td><td>7</td></tr> <tr> <td>54970</td><td>3385</td><td>5.242</td><td>208.258</td><td>1</td></tr> <tr> <td>54972</td><td>11063</td><td>25.847</td><td>205.111</td><td>10</td></tr> <tr> <td>54973</td><td>6908</td><td>15.930</td><td>206.538</td><td>9</td></tr> <tr> <td>54975</td><td>17218</td><td>41.429</td><td>205.118</td><td>25</td></tr> <tr> <td>54976</td><td>5331</td><td>11.181</td><td>206.591</td><td>4</td></tr> <tr></table> Total file length :   305.594 Mbytes",
-        "ALEPH - INFN",
-        "High Energy Physics",
-        "2000",
-        "eng",
-        "Researchers",
-        "info:eu-repo/semantics/other",
-        "Marcello Maggi"
-    ],
-    "notes": [
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>54956</td><td>19822</td><td>45.622</td><td>206.608</td><td>18</td></tr> <tr> <td>54957</td><td>1726</td><td>2.710</td><td>207.887</td><td>2</td></tr> <tr> <td>54960</td><td>4936</td><td>12.234</td><td>205.100</td><td>7</td></tr> <tr> <td>54961</td><td>18567</td><td>41.795</td><td>206.573</td><td>8</td></tr> <tr> <td>54962</td><td>405</td><td>0.431</td><td>207.375</td><td>1</td></tr> <tr> <td>54964</td><td>8179</td><td>20.148</td><td>205.111</td><td>8</td></tr> <tr> <td>54965</td><td>1726</td><td>4.136</td><td>206.582</td><td>2</td></tr> <tr> <td>54967</td><td>8964</td><td>21.572</td><td>205.122</td><td>12</td></tr> <tr> <td>54968</td><td>17495</td><td>38.870</td><td>206.523</td><td>22</td></tr> <tr> <td>54969</td><td>9507</td><td>19.471</td><td>208.073</td><td>7</td></tr> <tr> <td>54970</td><td>3385</td><td>5.242</td><td>208.258</td><td>1</td></tr> <tr> <td>54972</td><td>11063</td><td>25.847</td><td>205.111</td><td>10</td></tr> <tr> <td>54973</td><td>6908</td><td>15.930</td><td>206.538</td><td>9</td></tr> <tr> <td>54975</td><td>17218</td><td>41.429</td><td>205.118</td><td>25</td></tr> <tr> <td>54976</td><td>5331</td><td>11.181</td><td>206.591</td><td>4</td></tr> <tr></table> Total file length :   305.594 Mbytes"
-    ],
-    "oai_identifier": [
-        "oai:www.openaccessrepository.it:7269"
-    ],
-    "oai_set": [
-        "dataset:aleph",
-        "openaire"
-    ],
-    "tags": [
-        {
-            "name": "HEP CERN LEP ALEPH MINI RealData"
-        }
-    ],
-    "title": [
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4000.83.AL"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/e9f19d22-bd64-5b4d-ac41-cbc015c7c00e.json b/oaitestdata/aleph-marcxml/dataset:aleph_1/json/e9f19d22-bd64-5b4d-ac41-cbc015c7c00e.json
deleted file mode 100644
index 24ac454a..00000000
--- a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/e9f19d22-bd64-5b4d-ac41-cbc015c7c00e.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Checksum": null,
-    "Contact": [
-        "N/A"
-    ],
-    "Discipline": "Physics",
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": "N/A",
-    "PublicationTimestamp": "2000-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "author": [
-        "Marcello Maggi"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:www.openaccessrepository.it:7309",
-        "2016-06-29T14:35:14Z",
-        "dataset:aleph",
-        "openaire",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.18.AL,11100/f90a2422-cbe6-11e3-9bbe-e41f13eb41b2eng",
-        "00000coc  2200000uu 4500",
-        "7309",
-        "20160629143514.0",
-        "Handle",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.18.AL,11100/f90a2422-cbe6-11e3-9bbe-e41f13eb41b2",
-        "HEP CERN LEP ALEPH MINI RealData 2000",
-        "DATASETREALDATA",
-        "Marcello Maggi",
-        "2327254944",
-        "314632800",
-        "Search for neutral Higgs bosons decaying into four taus at LEP2",
-        "10.1007/JHEP05(2010)049",
-        "2010",
-        "[1]",
-        "PUBLICATIONINFN-2014-001",
-        "[1]",
-        "10.5072/oar.it/1411041136.04 ",
-        "ALEPH SCL5 Virtual Machine for Research Environment",
-        "SOFTWAREALEPH-2014-001",
-        "[2]",
-        "ALEPH Collaboration",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.18.AL",
-        "ALEPH",
-        "oai:www.openaccessrepository.it:7309",
-        "openaire",
-        "dataset:aleph",
-        "ALEPH",
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4001.18.AL",
-        "2014-09-01",
-        "ALEPH",
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>56167</td><td>21888</td><td>53.989</td><td>206.382</td><td>30</td></tr> <tr> <td>56168</td><td>6767</td><td>16.295</td><td>206.372</td><td>8</td></tr> <tr> <td>56169</td><td>376</td><td>0.707</td><td>208.064</td><td>-1</td></tr> <tr> <td>56173</td><td>3220</td><td>8.241</td><td>206.374</td><td>2</td></tr> <tr> <td>56176</td><td>6846</td><td>17.561</td><td>206.380</td><td>10</td></tr> <tr> <td>56178</td><td>7738</td><td>20.089</td><td>205.201</td><td>7</td></tr> <tr> <td>56179</td><td>10208</td><td>25.532</td><td>206.369</td><td>13</td></tr> <tr> <td>56181</td><td>4100</td><td>10.256</td><td>205.182</td><td>3</td></tr> <tr> <td>56182</td><td>2776</td><td>6.152</td><td>206.314</td><td>-1</td></tr> <tr> <td>56184</td><td>2249</td><td>5.586</td><td>206.366</td><td>2</td></tr> <tr> <td>56186</td><td>5024</td><td>13.096</td><td>205.177</td><td>5</td></tr> <tr> <td>56187</td><td>8261</td><td>22.337</td><td>206.369</td><td>12</td></tr> <tr> <td>56188</td><td>7798</td><td>20.968</td><td>206.550</td><td>11</td></tr> <tr> <td>56190</td><td>7770</td><td>20.551</td><td>206.385</td><td>13</td></tr> <tr> <td>56191</td><td>9915</td><td>26.131</td><td>206.574</td><td>14</td></tr> <tr> <td>56192</td><td>2307</td><td>5.658</td><td>206.825</td><td>2</td></tr> <tr> <td>56194</td><td>7175</td><td>19.481</td><td>206.375</td><td>12</td></tr> <tr> <td>56195</td><td>3090</td><td>8.754</td><td>206.609</td><td>10</td></tr> <tr> <td>56197</td><td>4371</td><td>11.578</td><td>206.397</td><td>4</td></tr> <tr></table> Total file length :   305.594 Mbytes",
-        "ALEPH - INFN",
-        "High Energy Physics",
-        "2000",
-        "eng",
-        "Researchers",
-        "info:eu-repo/semantics/other",
-        "Marcello Maggi"
-    ],
-    "notes": [
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>56167</td><td>21888</td><td>53.989</td><td>206.382</td><td>30</td></tr> <tr> <td>56168</td><td>6767</td><td>16.295</td><td>206.372</td><td>8</td></tr> <tr> <td>56169</td><td>376</td><td>0.707</td><td>208.064</td><td>-1</td></tr> <tr> <td>56173</td><td>3220</td><td>8.241</td><td>206.374</td><td>2</td></tr> <tr> <td>56176</td><td>6846</td><td>17.561</td><td>206.380</td><td>10</td></tr> <tr> <td>56178</td><td>7738</td><td>20.089</td><td>205.201</td><td>7</td></tr> <tr> <td>56179</td><td>10208</td><td>25.532</td><td>206.369</td><td>13</td></tr> <tr> <td>56181</td><td>4100</td><td>10.256</td><td>205.182</td><td>3</td></tr> <tr> <td>56182</td><td>2776</td><td>6.152</td><td>206.314</td><td>-1</td></tr> <tr> <td>56184</td><td>2249</td><td>5.586</td><td>206.366</td><td>2</td></tr> <tr> <td>56186</td><td>5024</td><td>13.096</td><td>205.177</td><td>5</td></tr> <tr> <td>56187</td><td>8261</td><td>22.337</td><td>206.369</td><td>12</td></tr> <tr> <td>56188</td><td>7798</td><td>20.968</td><td>206.550</td><td>11</td></tr> <tr> <td>56190</td><td>7770</td><td>20.551</td><td>206.385</td><td>13</td></tr> <tr> <td>56191</td><td>9915</td><td>26.131</td><td>206.574</td><td>14</td></tr> <tr> <td>56192</td><td>2307</td><td>5.658</td><td>206.825</td><td>2</td></tr> <tr> <td>56194</td><td>7175</td><td>19.481</td><td>206.375</td><td>12</td></tr> <tr> <td>56195</td><td>3090</td><td>8.754</td><td>206.609</td><td>10</td></tr> <tr> <td>56197</td><td>4371</td><td>11.578</td><td>206.397</td><td>4</td></tr> <tr></table> Total file length :   305.594 Mbytes"
-    ],
-    "oai_identifier": [
-        "oai:www.openaccessrepository.it:7309"
-    ],
-    "oai_set": [
-        "dataset:aleph",
-        "openaire"
-    ],
-    "tags": [
-        {
-            "name": "HEP CERN LEP ALEPH MINI RealData"
-        }
-    ],
-    "title": [
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4001.18.AL"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/ec5650e7-4800-531e-8048-03ce27b25d1a.json b/oaitestdata/aleph-marcxml/dataset:aleph_1/json/ec5650e7-4800-531e-8048-03ce27b25d1a.json
deleted file mode 100644
index 95d3b101..00000000
--- a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/ec5650e7-4800-531e-8048-03ce27b25d1a.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Checksum": null,
-    "Contact": [
-        "N/A"
-    ],
-    "Discipline": "Physics",
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": "N/A",
-    "PublicationTimestamp": "2000-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "author": [
-        "Marcello Maggi"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:www.openaccessrepository.it:7301",
-        "2016-06-29T14:35:14Z",
-        "dataset:aleph",
-        "openaire",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4000.99.AL,11100/9abffa40-cbe6-11e3-8ed9-e41f13eb41b2eng",
-        "00000coc  2200000uu 4500",
-        "7301",
-        "20160629143514.0",
-        "Handle",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4000.99.AL,11100/9abffa40-cbe6-11e3-8ed9-e41f13eb41b2",
-        "HEP CERN LEP ALEPH MINI RealData 2000",
-        "DATASETREALDATA",
-        "Marcello Maggi",
-        "1851280318",
-        "317612520",
-        "Search for neutral Higgs bosons decaying into four taus at LEP2",
-        "10.1007/JHEP05(2010)049",
-        "2010",
-        "[1]",
-        "PUBLICATIONINFN-2014-001",
-        "[1]",
-        "10.5072/oar.it/1411041136.04 ",
-        "ALEPH SCL5 Virtual Machine for Research Environment",
-        "SOFTWAREALEPH-2014-001",
-        "[2]",
-        "ALEPH Collaboration",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4000.99.AL",
-        "ALEPH",
-        "oai:www.openaccessrepository.it:7301",
-        "openaire",
-        "dataset:aleph",
-        "ALEPH",
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4000.99.AL",
-        "2014-09-01",
-        "ALEPH",
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>55452</td><td>4056</td><td>10.155</td><td>205.089</td><td>6</td></tr> <tr> <td>55453</td><td>2763</td><td>5.033</td><td>206.300</td><td>4</td></tr> <tr> <td>55454</td><td>3817</td><td>9.009</td><td>206.340</td><td>2</td></tr> <tr> <td>55456</td><td>21223</td><td>51.722</td><td>205.116</td><td>36</td></tr> <tr> <td>55457</td><td>10056</td><td>23.582</td><td>205.129</td><td>15</td></tr> <tr> <td>55458</td><td>2563</td><td>4.923</td><td>207.691</td><td>-1</td></tr> <tr> <td>55460</td><td>4675</td><td>11.313</td><td>205.118</td><td>10</td></tr> <tr> <td>55462</td><td>4880</td><td>11.580</td><td>205.125</td><td>8</td></tr> <tr> <td>55463</td><td>6295</td><td>15.477</td><td>205.123</td><td>7</td></tr> <tr> <td>55464</td><td>14384</td><td>33.684</td><td>206.578</td><td>18</td></tr> <tr> <td>55466</td><td>15455</td><td>37.751</td><td>205.117</td><td>24</td></tr> <tr> <td>55467</td><td>12067</td><td>28.762</td><td>206.569</td><td>16</td></tr> <tr> <td>55468</td><td>2239</td><td>3.663</td><td>207.778</td><td>4</td></tr> <tr> <td>55470</td><td>5807</td><td>14.105</td><td>205.158</td><td>8</td></tr> <tr> <td>55471</td><td>354</td><td>0.711</td><td>205.384</td><td>-1</td></tr> <tr> <td>55474</td><td>11136</td><td>27.959</td><td>205.117</td><td>16</td></tr> <tr> <td>55475</td><td>4407</td><td>10.248</td><td>206.590</td><td>7</td></tr> <tr> <td>55477</td><td>6344</td><td>16.116</td><td>205.121</td><td>5</td></tr> <tr></table> Total file length :   305.594 Mbytes",
-        "ALEPH - INFN",
-        "High Energy Physics",
-        "2000",
-        "eng",
-        "Researchers",
-        "info:eu-repo/semantics/other",
-        "Marcello Maggi"
-    ],
-    "notes": [
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>55452</td><td>4056</td><td>10.155</td><td>205.089</td><td>6</td></tr> <tr> <td>55453</td><td>2763</td><td>5.033</td><td>206.300</td><td>4</td></tr> <tr> <td>55454</td><td>3817</td><td>9.009</td><td>206.340</td><td>2</td></tr> <tr> <td>55456</td><td>21223</td><td>51.722</td><td>205.116</td><td>36</td></tr> <tr> <td>55457</td><td>10056</td><td>23.582</td><td>205.129</td><td>15</td></tr> <tr> <td>55458</td><td>2563</td><td>4.923</td><td>207.691</td><td>-1</td></tr> <tr> <td>55460</td><td>4675</td><td>11.313</td><td>205.118</td><td>10</td></tr> <tr> <td>55462</td><td>4880</td><td>11.580</td><td>205.125</td><td>8</td></tr> <tr> <td>55463</td><td>6295</td><td>15.477</td><td>205.123</td><td>7</td></tr> <tr> <td>55464</td><td>14384</td><td>33.684</td><td>206.578</td><td>18</td></tr> <tr> <td>55466</td><td>15455</td><td>37.751</td><td>205.117</td><td>24</td></tr> <tr> <td>55467</td><td>12067</td><td>28.762</td><td>206.569</td><td>16</td></tr> <tr> <td>55468</td><td>2239</td><td>3.663</td><td>207.778</td><td>4</td></tr> <tr> <td>55470</td><td>5807</td><td>14.105</td><td>205.158</td><td>8</td></tr> <tr> <td>55471</td><td>354</td><td>0.711</td><td>205.384</td><td>-1</td></tr> <tr> <td>55474</td><td>11136</td><td>27.959</td><td>205.117</td><td>16</td></tr> <tr> <td>55475</td><td>4407</td><td>10.248</td><td>206.590</td><td>7</td></tr> <tr> <td>55477</td><td>6344</td><td>16.116</td><td>205.121</td><td>5</td></tr> <tr></table> Total file length :   305.594 Mbytes"
-    ],
-    "oai_identifier": [
-        "oai:www.openaccessrepository.it:7301"
-    ],
-    "oai_set": [
-        "dataset:aleph",
-        "openaire"
-    ],
-    "tags": [
-        {
-            "name": "HEP CERN LEP ALEPH MINI RealData"
-        }
-    ],
-    "title": [
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4000.99.AL"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/ef64291b-f64e-5ebf-a58a-69513e9902b0.json b/oaitestdata/aleph-marcxml/dataset:aleph_1/json/ef64291b-f64e-5ebf-a58a-69513e9902b0.json
deleted file mode 100644
index 13c65bd9..00000000
--- a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/ef64291b-f64e-5ebf-a58a-69513e9902b0.json
+++ /dev/null
@@ -1,88 +0,0 @@
-{
-    "Checksum": null,
-    "Contact": [
-        "N/A"
-    ],
-    "Discipline": "Physics",
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": "N/A",
-    "PublicationTimestamp": "2000-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "author": [
-        "Marcello Maggi",
-        "CURATOR"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:www.openaccessrepository.it:7330",
-        "2016-06-29T14:35:14Z",
-        "dataset:aleph",
-        "openaire",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4000.27.AL,11100/b2ca90a8-cbe3-11e3-ac1a-e41f13eb41b2eng",
-        "00000coc  2200000uu 4500",
-        "7330",
-        "20160629143514.0",
-        "Handle",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4000.27.AL,11100/b2ca90a8-cbe3-11e3-ac1a-e41f13eb41b2",
-        "HEP CERN LEP ALEPH MINI RealData 2000",
-        "Researchers",
-        "info:eu-repo/semantics/other",
-        "DATASETREALDATA",
-        "Marcello Maggi",
-        "3039181162",
-        "304476120",
-        "10.1007/JHEP05(2010)049",
-        "[1]",
-        "[1]",
-        "PUBLICATIONINFN-2014-001",
-        "Search for neutral Higgs bosons decaying into four taus at LEP2",
-        "2010",
-        "10.5072/oar.it/1411041136.04",
-        "[2]",
-        "SOFTWAREALEPH-2014-001",
-        "ALEPH SCL5 Virtual Machine for Research Environment",
-        "CURATOR",
-        "10.5072/oar.it/1415804221.39",
-        "[3]",
-        "SOFTWAREALEPH-2014-185",
-        "Analysis with the CHAIN-REDS Science Gateway of LEP Data from the ALEPH Collaboration year 2000 datafile ZD4000.27.AL",
-        "ALEPH Collaboration",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4000.27.AL",
-        "ALEPH",
-        "oai:www.openaccessrepository.it:7330",
-        "openaire",
-        "dataset:aleph",
-        "ALEPH",
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4000.27.AL",
-        "2014-09-01",
-        "ALEPH",
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>53507</td><td>18537</td><td>38.825</td><td>204.899</td><td>20</td></tr> <tr> <td>53508</td><td>11124</td><td>22.029</td><td>205.902</td><td>3</td></tr> <tr> <td>53509</td><td>4120</td><td>7.461</td><td>207.042</td><td>3</td></tr> <tr> <td>53511</td><td>9701</td><td>24.063</td><td>203.554</td><td>11</td></tr> <tr> <td>53513</td><td>10057</td><td>25.534</td><td>203.546</td><td>11</td></tr> <tr> <td>53515</td><td>13197</td><td>32.412</td><td>203.569</td><td>20</td></tr> <tr> <td>53516</td><td>12116</td><td>25.408</td><td>204.907</td><td>13</td></tr> <tr> <td>53517</td><td>4315</td><td>8.417</td><td>206.611</td><td>7</td></tr> <tr> <td>53522</td><td>11770</td><td>27.740</td><td>203.769</td><td>10</td></tr> <tr> <td>53523</td><td>11679</td><td>25.291</td><td>204.908</td><td>12</td></tr> <tr> <td>53524</td><td>6120</td><td>12.298</td><td>206.613</td><td>2</td></tr> <tr> <td>53530</td><td>12897</td><td>31.621</td><td>203.553</td><td>23</td></tr> <tr> <td>53531</td><td>9853</td><td>21.622</td><td>204.845</td><td>9</td></tr> <tr></table> Total file length :   305.594 Mbytes",
-        "ALEPH - INFN",
-        "High Energy Physics",
-        "2000",
-        "Marcello Maggi",
-        "eng"
-    ],
-    "notes": [
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>53507</td><td>18537</td><td>38.825</td><td>204.899</td><td>20</td></tr> <tr> <td>53508</td><td>11124</td><td>22.029</td><td>205.902</td><td>3</td></tr> <tr> <td>53509</td><td>4120</td><td>7.461</td><td>207.042</td><td>3</td></tr> <tr> <td>53511</td><td>9701</td><td>24.063</td><td>203.554</td><td>11</td></tr> <tr> <td>53513</td><td>10057</td><td>25.534</td><td>203.546</td><td>11</td></tr> <tr> <td>53515</td><td>13197</td><td>32.412</td><td>203.569</td><td>20</td></tr> <tr> <td>53516</td><td>12116</td><td>25.408</td><td>204.907</td><td>13</td></tr> <tr> <td>53517</td><td>4315</td><td>8.417</td><td>206.611</td><td>7</td></tr> <tr> <td>53522</td><td>11770</td><td>27.740</td><td>203.769</td><td>10</td></tr> <tr> <td>53523</td><td>11679</td><td>25.291</td><td>204.908</td><td>12</td></tr> <tr> <td>53524</td><td>6120</td><td>12.298</td><td>206.613</td><td>2</td></tr> <tr> <td>53530</td><td>12897</td><td>31.621</td><td>203.553</td><td>23</td></tr> <tr> <td>53531</td><td>9853</td><td>21.622</td><td>204.845</td><td>9</td></tr> <tr></table> Total file length :   305.594 Mbytes"
-    ],
-    "oai_identifier": [
-        "oai:www.openaccessrepository.it:7330"
-    ],
-    "oai_set": [
-        "dataset:aleph",
-        "openaire"
-    ],
-    "tags": [
-        {
-            "name": "HEP CERN LEP ALEPH MINI RealData"
-        }
-    ],
-    "title": [
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4000.27.AL"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/f26fa0ed-29b5-54b3-94f7-76ab54b61338.json b/oaitestdata/aleph-marcxml/dataset:aleph_1/json/f26fa0ed-29b5-54b3-94f7-76ab54b61338.json
deleted file mode 100644
index fbda7d90..00000000
--- a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/f26fa0ed-29b5-54b3-94f7-76ab54b61338.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Checksum": null,
-    "Contact": [
-        "N/A"
-    ],
-    "Discipline": "Physics",
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": "N/A",
-    "PublicationTimestamp": "2000-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "author": [
-        "Marcello Maggi"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:www.openaccessrepository.it:7248",
-        "2016-06-29T14:35:15Z",
-        "dataset:aleph",
-        "openaire",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4000.45.AL,11100/7a26597a-cbe4-11e3-a724-e41f13eb41b2eng",
-        "00000coc  2200000uu 4500",
-        "7248",
-        "20160629143515.0",
-        "Handle",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4000.45.AL,11100/7a26597a-cbe4-11e3-a724-e41f13eb41b2",
-        "HEP CERN LEP ALEPH MINI RealData 2000",
-        "DATASETREALDATA",
-        "Marcello Maggi",
-        "1008864267",
-        "324501120",
-        "Search for neutral Higgs bosons decaying into four taus at LEP2",
-        "10.1007/JHEP05(2010)049",
-        "2010",
-        "[1]",
-        "PUBLICATIONINFN-2014-001",
-        "[1]",
-        "10.5072/oar.it/1411041136.04 ",
-        "ALEPH SCL5 Virtual Machine for Research Environment",
-        "SOFTWAREALEPH-2014-001",
-        "[2]",
-        "ALEPH Collaboration",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4000.45.AL",
-        "ALEPH",
-        "oai:www.openaccessrepository.it:7248",
-        "openaire",
-        "dataset:aleph",
-        "ALEPH",
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4000.45.AL",
-        "2014-09-01",
-        "ALEPH",
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>53987</td><td>7954</td><td>17.755</td><td>206.151</td><td>5</td></tr> <tr> <td>53988</td><td>420</td><td>0.728</td><td>206.132</td><td>-1</td></tr> <tr> <td>53990</td><td>16190</td><td>37.943</td><td>205.040</td><td>14</td></tr> <tr> <td>53991</td><td>11351</td><td>24.367</td><td>206.440</td><td>11</td></tr> <tr> <td>53997</td><td>14278</td><td>34.299</td><td>204.973</td><td>21</td></tr> <tr> <td>53998</td><td>77</td><td>0.268</td><td>206.404</td><td>-1</td></tr> <tr> <td>54000</td><td>18669</td><td>46.452</td><td>204.964</td><td>24</td></tr> <tr> <td>54001</td><td>14787</td><td>32.430</td><td>206.390</td><td>13</td></tr> <tr> <td>54002</td><td>3272</td><td>6.020</td><td>207.875</td><td>3</td></tr> <tr> <td>54004</td><td>16155</td><td>37.201</td><td>205.044</td><td>8</td></tr> <tr> <td>54009</td><td>18884</td><td>47.161</td><td>205.023</td><td>22</td></tr> <tr> <td>54010</td><td>4902</td><td>11.002</td><td>206.333</td><td>6</td></tr> <tr> <td>54011</td><td>2850</td><td>3.869</td><td>207.872</td><td>3</td></tr> <tr> <td>54014</td><td>9158</td><td>23.180</td><td>205.013</td><td>16</td></tr> <tr></table> Total file length :   305.594 Mbytes",
-        "ALEPH - INFN",
-        "High Energy Physics",
-        "2000",
-        "eng",
-        "Researchers",
-        "info:eu-repo/semantics/other",
-        "Marcello Maggi"
-    ],
-    "notes": [
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>53987</td><td>7954</td><td>17.755</td><td>206.151</td><td>5</td></tr> <tr> <td>53988</td><td>420</td><td>0.728</td><td>206.132</td><td>-1</td></tr> <tr> <td>53990</td><td>16190</td><td>37.943</td><td>205.040</td><td>14</td></tr> <tr> <td>53991</td><td>11351</td><td>24.367</td><td>206.440</td><td>11</td></tr> <tr> <td>53997</td><td>14278</td><td>34.299</td><td>204.973</td><td>21</td></tr> <tr> <td>53998</td><td>77</td><td>0.268</td><td>206.404</td><td>-1</td></tr> <tr> <td>54000</td><td>18669</td><td>46.452</td><td>204.964</td><td>24</td></tr> <tr> <td>54001</td><td>14787</td><td>32.430</td><td>206.390</td><td>13</td></tr> <tr> <td>54002</td><td>3272</td><td>6.020</td><td>207.875</td><td>3</td></tr> <tr> <td>54004</td><td>16155</td><td>37.201</td><td>205.044</td><td>8</td></tr> <tr> <td>54009</td><td>18884</td><td>47.161</td><td>205.023</td><td>22</td></tr> <tr> <td>54010</td><td>4902</td><td>11.002</td><td>206.333</td><td>6</td></tr> <tr> <td>54011</td><td>2850</td><td>3.869</td><td>207.872</td><td>3</td></tr> <tr> <td>54014</td><td>9158</td><td>23.180</td><td>205.013</td><td>16</td></tr> <tr></table> Total file length :   305.594 Mbytes"
-    ],
-    "oai_identifier": [
-        "oai:www.openaccessrepository.it:7248"
-    ],
-    "oai_set": [
-        "dataset:aleph",
-        "openaire"
-    ],
-    "tags": [
-        {
-            "name": "HEP CERN LEP ALEPH MINI RealData"
-        }
-    ],
-    "title": [
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4000.45.AL"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/f2b01afd-16e1-5ae2-a9cc-1b61aa7f28a7.json b/oaitestdata/aleph-marcxml/dataset:aleph_1/json/f2b01afd-16e1-5ae2-a9cc-1b61aa7f28a7.json
deleted file mode 100644
index ceca1cea..00000000
--- a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/f2b01afd-16e1-5ae2-a9cc-1b61aa7f28a7.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Checksum": null,
-    "Contact": [
-        "N/A"
-    ],
-    "Discipline": "Physics",
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": "N/A",
-    "PublicationTimestamp": "2000-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "author": [
-        "Marcello Maggi"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:www.openaccessrepository.it:7325",
-        "2016-06-29T14:35:14Z",
-        "dataset:aleph",
-        "openaire",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4000.94.AL,11100/71651e50-cbe6-11e3-8ace-e41f13eb41b2eng",
-        "00000coc  2200000uu 4500",
-        "7325",
-        "20160629143514.0",
-        "Handle",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4000.94.AL,11100/71651e50-cbe6-11e3-8ace-e41f13eb41b2",
-        "HEP CERN LEP ALEPH MINI RealData 2000",
-        "DATASETREALDATA",
-        "Marcello Maggi",
-        "3277972373",
-        "308961720",
-        "Search for neutral Higgs bosons decaying into four taus at LEP2",
-        "10.1007/JHEP05(2010)049",
-        "2010",
-        "[1]",
-        "PUBLICATIONINFN-2014-001",
-        "[1]",
-        "10.5072/oar.it/1411041136.04 ",
-        "ALEPH SCL5 Virtual Machine for Research Environment",
-        "SOFTWAREALEPH-2014-001",
-        "[2]",
-        "ALEPH Collaboration",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4000.94.AL",
-        "ALEPH",
-        "oai:www.openaccessrepository.it:7325",
-        "openaire",
-        "dataset:aleph",
-        "ALEPH",
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4000.94.AL",
-        "2014-09-01",
-        "ALEPH",
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>55311</td><td>12401</td><td>31.186</td><td>205.077</td><td>9</td></tr> <tr> <td>55312</td><td>11850</td><td>28.358</td><td>206.544</td><td>11</td></tr> <tr> <td>55316</td><td>12600</td><td>31.803</td><td>205.093</td><td>20</td></tr> <tr> <td>55317</td><td>12487</td><td>30.236</td><td>206.543</td><td>12</td></tr> <tr> <td>55318</td><td>5885</td><td>12.282</td><td>207.646</td><td>6</td></tr> <tr> <td>55321</td><td>12543</td><td>30.763</td><td>205.063</td><td>22</td></tr> <tr> <td>55322</td><td>13335</td><td>31.804</td><td>206.577</td><td>12</td></tr> <tr> <td>55323</td><td>1408</td><td>2.474</td><td>207.955</td><td>2</td></tr> <tr> <td>55326</td><td>10274</td><td>25.232</td><td>205.091</td><td>8</td></tr> <tr> <td>55327</td><td>8273</td><td>20.210</td><td>206.601</td><td>12</td></tr> <tr> <td>55338</td><td>18218</td><td>42.293</td><td>205.073</td><td>18</td></tr> <tr> <td>55339</td><td>209</td><td>0.504</td><td>205.072</td><td>-1</td></tr> <tr> <td>55340</td><td>188</td><td>0.405</td><td>205.072</td><td>-1</td></tr> <tr> <td>55341</td><td>397</td><td>0.805</td><td>205.072</td><td>2</td></tr> <tr> <td>55342</td><td>247</td><td>0.622</td><td>205.072</td><td>-1</td></tr> <tr> <td>55343</td><td>729</td><td>1.549</td><td>205.072</td><td>1</td></tr> <tr> <td>55344</td><td>7802</td><td>16.720</td><td>206.546</td><td>8</td></tr> <tr></table> Total file length :   305.594 Mbytes",
-        "ALEPH - INFN",
-        "High Energy Physics",
-        "2000",
-        "eng",
-        "Researchers",
-        "info:eu-repo/semantics/other",
-        "Marcello Maggi"
-    ],
-    "notes": [
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>55311</td><td>12401</td><td>31.186</td><td>205.077</td><td>9</td></tr> <tr> <td>55312</td><td>11850</td><td>28.358</td><td>206.544</td><td>11</td></tr> <tr> <td>55316</td><td>12600</td><td>31.803</td><td>205.093</td><td>20</td></tr> <tr> <td>55317</td><td>12487</td><td>30.236</td><td>206.543</td><td>12</td></tr> <tr> <td>55318</td><td>5885</td><td>12.282</td><td>207.646</td><td>6</td></tr> <tr> <td>55321</td><td>12543</td><td>30.763</td><td>205.063</td><td>22</td></tr> <tr> <td>55322</td><td>13335</td><td>31.804</td><td>206.577</td><td>12</td></tr> <tr> <td>55323</td><td>1408</td><td>2.474</td><td>207.955</td><td>2</td></tr> <tr> <td>55326</td><td>10274</td><td>25.232</td><td>205.091</td><td>8</td></tr> <tr> <td>55327</td><td>8273</td><td>20.210</td><td>206.601</td><td>12</td></tr> <tr> <td>55338</td><td>18218</td><td>42.293</td><td>205.073</td><td>18</td></tr> <tr> <td>55339</td><td>209</td><td>0.504</td><td>205.072</td><td>-1</td></tr> <tr> <td>55340</td><td>188</td><td>0.405</td><td>205.072</td><td>-1</td></tr> <tr> <td>55341</td><td>397</td><td>0.805</td><td>205.072</td><td>2</td></tr> <tr> <td>55342</td><td>247</td><td>0.622</td><td>205.072</td><td>-1</td></tr> <tr> <td>55343</td><td>729</td><td>1.549</td><td>205.072</td><td>1</td></tr> <tr> <td>55344</td><td>7802</td><td>16.720</td><td>206.546</td><td>8</td></tr> <tr></table> Total file length :   305.594 Mbytes"
-    ],
-    "oai_identifier": [
-        "oai:www.openaccessrepository.it:7325"
-    ],
-    "oai_set": [
-        "dataset:aleph",
-        "openaire"
-    ],
-    "tags": [
-        {
-            "name": "HEP CERN LEP ALEPH MINI RealData"
-        }
-    ],
-    "title": [
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4000.94.AL"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/f2de7af4-8e10-5fdc-aca8-95dbdca48bbd.json b/oaitestdata/aleph-marcxml/dataset:aleph_1/json/f2de7af4-8e10-5fdc-aca8-95dbdca48bbd.json
deleted file mode 100644
index b607fa84..00000000
--- a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/f2de7af4-8e10-5fdc-aca8-95dbdca48bbd.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Checksum": null,
-    "Contact": [
-        "N/A"
-    ],
-    "Discipline": "Physics",
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": "N/A",
-    "PublicationTimestamp": "2000-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "author": [
-        "Marcello Maggi"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:www.openaccessrepository.it:7279",
-        "2016-06-29T14:35:14Z",
-        "dataset:aleph",
-        "openaire",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.54.AL,11100/65c7a39a-cbe8-11e3-adf9-e41f13eb41b2eng",
-        "00000coc  2200000uu 4500",
-        "7279",
-        "20160629143514.0",
-        "Handle",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.54.AL,11100/65c7a39a-cbe8-11e3-adf9-e41f13eb41b2",
-        "HEP CERN LEP ALEPH MINI RealData 2000",
-        "DATASETREALDATA",
-        "Marcello Maggi",
-        "2519714616",
-        "305565480",
-        "Search for neutral Higgs bosons decaying into four taus at LEP2",
-        "10.1007/JHEP05(2010)049",
-        "2010",
-        "[1]",
-        "PUBLICATIONINFN-2014-001",
-        "[1]",
-        "10.5072/oar.it/1411041136.04 ",
-        "ALEPH SCL5 Virtual Machine for Research Environment",
-        "SOFTWAREALEPH-2014-001",
-        "[2]",
-        "ALEPH Collaboration",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.54.AL",
-        "ALEPH",
-        "oai:www.openaccessrepository.it:7279",
-        "openaire",
-        "dataset:aleph",
-        "ALEPH",
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4001.54.AL",
-        "2014-09-01",
-        "ALEPH",
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>57394</td><td>2518</td><td>7.062</td><td>206.622</td><td>6</td></tr> <tr> <td>57396</td><td>2170</td><td>5.877</td><td>206.145</td><td>5</td></tr> <tr> <td>57398</td><td>4146</td><td>13.011</td><td>205.149</td><td>13</td></tr> <tr> <td>57399</td><td>12010</td><td>35.832</td><td>206.368</td><td>8</td></tr> <tr> <td>57400</td><td>1678</td><td>4.447</td><td>206.641</td><td>4</td></tr> <tr> <td>57402</td><td>3021</td><td>9.155</td><td>206.140</td><td>4</td></tr> <tr> <td>57404</td><td>6993</td><td>21.397</td><td>205.150</td><td>14</td></tr> <tr> <td>57405</td><td>4790</td><td>14.682</td><td>206.328</td><td>5</td></tr> <tr> <td>57406</td><td>909</td><td>2.599</td><td>207.228</td><td>1</td></tr> <tr> <td>57408</td><td>3490</td><td>10.409</td><td>205.156</td><td>5</td></tr> <tr> <td>57409</td><td>17398</td><td>51.066</td><td>206.355</td><td>18</td></tr> <tr> <td>57410</td><td>6645</td><td>17.947</td><td>206.364</td><td>10</td></tr> <tr> <td>57411</td><td>164</td><td>0.449</td><td>207.986</td><td>-1</td></tr> <tr> <td>57413</td><td>247</td><td>0.607</td><td>208.445</td><td>-1</td></tr> <tr> <td>57414</td><td>873</td><td>1.744</td><td>208.464</td><td>-1</td></tr> <tr> <td>57416</td><td>17860</td><td>52.733</td><td>206.373</td><td>36</td></tr> <tr> <td>57417</td><td>6574</td><td>18.590</td><td>206.372</td><td>9</td></tr> <tr> <td>57418</td><td>122</td><td>0.320</td><td>206.520</td><td>-1</td></tr> <tr> <td>57419</td><td>216</td><td>0.579</td><td>208.154</td><td>-1</td></tr> <tr> <td>57420</td><td>687</td><td>1.676</td><td>208.270</td><td>-1</td></tr> <tr> <td>57423</td><td>11539</td><td>33.794</td><td>206.370</td><td>13</td></tr> <tr></table> Total file length :   305.594 Mbytes",
-        "ALEPH - INFN",
-        "High Energy Physics",
-        "2000",
-        "eng",
-        "Researchers",
-        "info:eu-repo/semantics/other",
-        "Marcello Maggi"
-    ],
-    "notes": [
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>57394</td><td>2518</td><td>7.062</td><td>206.622</td><td>6</td></tr> <tr> <td>57396</td><td>2170</td><td>5.877</td><td>206.145</td><td>5</td></tr> <tr> <td>57398</td><td>4146</td><td>13.011</td><td>205.149</td><td>13</td></tr> <tr> <td>57399</td><td>12010</td><td>35.832</td><td>206.368</td><td>8</td></tr> <tr> <td>57400</td><td>1678</td><td>4.447</td><td>206.641</td><td>4</td></tr> <tr> <td>57402</td><td>3021</td><td>9.155</td><td>206.140</td><td>4</td></tr> <tr> <td>57404</td><td>6993</td><td>21.397</td><td>205.150</td><td>14</td></tr> <tr> <td>57405</td><td>4790</td><td>14.682</td><td>206.328</td><td>5</td></tr> <tr> <td>57406</td><td>909</td><td>2.599</td><td>207.228</td><td>1</td></tr> <tr> <td>57408</td><td>3490</td><td>10.409</td><td>205.156</td><td>5</td></tr> <tr> <td>57409</td><td>17398</td><td>51.066</td><td>206.355</td><td>18</td></tr> <tr> <td>57410</td><td>6645</td><td>17.947</td><td>206.364</td><td>10</td></tr> <tr> <td>57411</td><td>164</td><td>0.449</td><td>207.986</td><td>-1</td></tr> <tr> <td>57413</td><td>247</td><td>0.607</td><td>208.445</td><td>-1</td></tr> <tr> <td>57414</td><td>873</td><td>1.744</td><td>208.464</td><td>-1</td></tr> <tr> <td>57416</td><td>17860</td><td>52.733</td><td>206.373</td><td>36</td></tr> <tr> <td>57417</td><td>6574</td><td>18.590</td><td>206.372</td><td>9</td></tr> <tr> <td>57418</td><td>122</td><td>0.320</td><td>206.520</td><td>-1</td></tr> <tr> <td>57419</td><td>216</td><td>0.579</td><td>208.154</td><td>-1</td></tr> <tr> <td>57420</td><td>687</td><td>1.676</td><td>208.270</td><td>-1</td></tr> <tr> <td>57423</td><td>11539</td><td>33.794</td><td>206.370</td><td>13</td></tr> <tr></table> Total file length :   305.594 Mbytes"
-    ],
-    "oai_identifier": [
-        "oai:www.openaccessrepository.it:7279"
-    ],
-    "oai_set": [
-        "dataset:aleph",
-        "openaire"
-    ],
-    "tags": [
-        {
-            "name": "HEP CERN LEP ALEPH MINI RealData"
-        }
-    ],
-    "title": [
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4001.54.AL"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/f491f095-dab8-5ea8-b6f7-2da0dfdc163d.json b/oaitestdata/aleph-marcxml/dataset:aleph_1/json/f491f095-dab8-5ea8-b6f7-2da0dfdc163d.json
deleted file mode 100644
index 03e30a63..00000000
--- a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/f491f095-dab8-5ea8-b6f7-2da0dfdc163d.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Checksum": null,
-    "Contact": [
-        "N/A"
-    ],
-    "Discipline": "Physics",
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": "N/A",
-    "PublicationTimestamp": "2000-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "author": [
-        "Marcello Maggi"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:www.openaccessrepository.it:7304",
-        "2016-06-29T14:35:14Z",
-        "dataset:aleph",
-        "openaire",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.30.AL,11100/73151c4a-cbe7-11e3-8244-e41f13eb41b2eng",
-        "00000coc  2200000uu 4500",
-        "7304",
-        "20160629143514.0",
-        "Handle",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.30.AL,11100/73151c4a-cbe7-11e3-8244-e41f13eb41b2",
-        "HEP CERN LEP ALEPH MINI RealData 2000",
-        "DATASETREALDATA",
-        "Marcello Maggi",
-        "244845634",
-        "324020520",
-        "Search for neutral Higgs bosons decaying into four taus at LEP2",
-        "10.1007/JHEP05(2010)049",
-        "2010",
-        "[1]",
-        "PUBLICATIONINFN-2014-001",
-        "[1]",
-        "10.5072/oar.it/1411041136.04 ",
-        "ALEPH SCL5 Virtual Machine for Research Environment",
-        "SOFTWAREALEPH-2014-001",
-        "[2]",
-        "ALEPH Collaboration",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.30.AL",
-        "ALEPH",
-        "oai:www.openaccessrepository.it:7304",
-        "openaire",
-        "dataset:aleph",
-        "ALEPH",
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4001.30.AL",
-        "2014-09-01",
-        "ALEPH",
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>56539</td><td>5868</td><td>13.717</td><td>206.368</td><td>5</td></tr> <tr> <td>56540</td><td>2184</td><td>4.753</td><td>207.742</td><td>2</td></tr> <tr> <td>56542</td><td>17067</td><td>43.906</td><td>206.362</td><td>28</td></tr> <tr> <td>56543</td><td>2709</td><td>4.793</td><td>207.608</td><td>2</td></tr> <tr> <td>56545</td><td>3631</td><td>9.897</td><td>206.347</td><td>8</td></tr> <tr> <td>56547</td><td>20626</td><td>51.388</td><td>206.355</td><td>27</td></tr> <tr> <td>56548</td><td>372</td><td>0.669</td><td>207.980</td><td>1</td></tr> <tr> <td>56551</td><td>14292</td><td>36.119</td><td>206.383</td><td>15</td></tr> <tr> <td>56553</td><td>16116</td><td>41.451</td><td>206.359</td><td>18</td></tr> <tr> <td>56554</td><td>244</td><td>0.676</td><td>206.398</td><td>-1</td></tr> <tr> <td>56555</td><td>624</td><td>1.673</td><td>206.398</td><td>1</td></tr> <tr> <td>56556</td><td>601</td><td>1.395</td><td>206.398</td><td>-1</td></tr> <tr> <td>56557</td><td>991</td><td>2.348</td><td>206.398</td><td>-1</td></tr> <tr> <td>56558</td><td>1486</td><td>2.742</td><td>207.978</td><td>-1</td></tr> <tr> <td>56560</td><td>1581</td><td>4.357</td><td>206.361</td><td>5</td></tr> <tr> <td>56562</td><td>18784</td><td>46.607</td><td>206.381</td><td>22</td></tr> <tr> <td>56573</td><td>10488</td><td>55.887</td><td>91.276</td><td>1863</td></tr> <tr></table> Total file length :   305.594 Mbytes",
-        "ALEPH - INFN",
-        "High Energy Physics",
-        "2000",
-        "eng",
-        "Researchers",
-        "info:eu-repo/semantics/other",
-        "Marcello Maggi"
-    ],
-    "notes": [
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>56539</td><td>5868</td><td>13.717</td><td>206.368</td><td>5</td></tr> <tr> <td>56540</td><td>2184</td><td>4.753</td><td>207.742</td><td>2</td></tr> <tr> <td>56542</td><td>17067</td><td>43.906</td><td>206.362</td><td>28</td></tr> <tr> <td>56543</td><td>2709</td><td>4.793</td><td>207.608</td><td>2</td></tr> <tr> <td>56545</td><td>3631</td><td>9.897</td><td>206.347</td><td>8</td></tr> <tr> <td>56547</td><td>20626</td><td>51.388</td><td>206.355</td><td>27</td></tr> <tr> <td>56548</td><td>372</td><td>0.669</td><td>207.980</td><td>1</td></tr> <tr> <td>56551</td><td>14292</td><td>36.119</td><td>206.383</td><td>15</td></tr> <tr> <td>56553</td><td>16116</td><td>41.451</td><td>206.359</td><td>18</td></tr> <tr> <td>56554</td><td>244</td><td>0.676</td><td>206.398</td><td>-1</td></tr> <tr> <td>56555</td><td>624</td><td>1.673</td><td>206.398</td><td>1</td></tr> <tr> <td>56556</td><td>601</td><td>1.395</td><td>206.398</td><td>-1</td></tr> <tr> <td>56557</td><td>991</td><td>2.348</td><td>206.398</td><td>-1</td></tr> <tr> <td>56558</td><td>1486</td><td>2.742</td><td>207.978</td><td>-1</td></tr> <tr> <td>56560</td><td>1581</td><td>4.357</td><td>206.361</td><td>5</td></tr> <tr> <td>56562</td><td>18784</td><td>46.607</td><td>206.381</td><td>22</td></tr> <tr> <td>56573</td><td>10488</td><td>55.887</td><td>91.276</td><td>1863</td></tr> <tr></table> Total file length :   305.594 Mbytes"
-    ],
-    "oai_identifier": [
-        "oai:www.openaccessrepository.it:7304"
-    ],
-    "oai_set": [
-        "dataset:aleph",
-        "openaire"
-    ],
-    "tags": [
-        {
-            "name": "HEP CERN LEP ALEPH MINI RealData"
-        }
-    ],
-    "title": [
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4001.30.AL"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/f59c01fc-a3dc-58d4-9b34-621776c2fea3.json b/oaitestdata/aleph-marcxml/dataset:aleph_1/json/f59c01fc-a3dc-58d4-9b34-621776c2fea3.json
deleted file mode 100644
index 671f0043..00000000
--- a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/f59c01fc-a3dc-58d4-9b34-621776c2fea3.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Checksum": null,
-    "Contact": [
-        "N/A"
-    ],
-    "Discipline": "Physics",
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": "N/A",
-    "PublicationTimestamp": "2000-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "author": [
-        "Marcello Maggi"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:www.openaccessrepository.it:7168",
-        "2016-06-29T14:35:13Z",
-        "dataset:aleph",
-        "openaire",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4000.82.AL,11100/f5c17c94-cbe5-11e3-a011-e41f13eb41b2eng",
-        "00000coc  2200000uu 4500",
-        "7168",
-        "20160629143513.0",
-        "Handle",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4000.82.AL,11100/f5c17c94-cbe5-11e3-a011-e41f13eb41b2",
-        "HEP CERN LEP ALEPH MINI RealData 2000",
-        "DATASETREALDATA",
-        "Marcello Maggi",
-        "3727683843",
-        "305020800",
-        "Search for neutral Higgs bosons decaying into four taus at LEP2",
-        "10.1007/JHEP05(2010)049",
-        "2010",
-        "[1]",
-        "PUBLICATIONINFN-2014-001",
-        "[1]",
-        "10.5072/oar.it/1411041136.04 ",
-        "ALEPH SCL5 Virtual Machine for Research Environment",
-        "SOFTWAREALEPH-2014-001",
-        "[2]",
-        "ALEPH Collaboration",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4000.82.AL",
-        "ALEPH",
-        "oai:www.openaccessrepository.it:7168",
-        "openaire",
-        "dataset:aleph",
-        "ALEPH",
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4000.82.AL",
-        "2014-09-01",
-        "ALEPH",
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>54919</td><td>20396</td><td>47.213</td><td>206.579</td><td>20</td></tr> <tr> <td>54920</td><td>571</td><td>1.460</td><td>206.591</td><td>1</td></tr> <tr> <td>54922</td><td>12176</td><td>30.622</td><td>205.123</td><td>15</td></tr> <tr> <td>54923</td><td>18764</td><td>44.922</td><td>206.531</td><td>21</td></tr> <tr> <td>54928</td><td>11604</td><td>26.286</td><td>206.580</td><td>13</td></tr> <tr> <td>54929</td><td>4279</td><td>8.291</td><td>207.986</td><td>3</td></tr> <tr> <td>54931</td><td>7960</td><td>20.254</td><td>205.119</td><td>11</td></tr> <tr> <td>54932</td><td>296</td><td>0.677</td><td>205.191</td><td>-1</td></tr> <tr> <td>54933</td><td>300</td><td>0.784</td><td>205.191</td><td>-1</td></tr> <tr> <td>54934</td><td>1012</td><td>2.232</td><td>205.191</td><td>1</td></tr> <tr> <td>54935</td><td>1322</td><td>3.160</td><td>205.191</td><td>3</td></tr> <tr> <td>54936</td><td>1562</td><td>3.600</td><td>205.219</td><td>4</td></tr> <tr> <td>54937</td><td>4913</td><td>11.800</td><td>206.548</td><td>4</td></tr> <tr> <td>54939</td><td>6500</td><td>15.923</td><td>205.122</td><td>2</td></tr> <tr> <td>54940</td><td>6166</td><td>15.004</td><td>206.639</td><td>2</td></tr> <tr> <td>54943</td><td>9260</td><td>23.892</td><td>205.121</td><td>10</td></tr> <tr> <td>54944</td><td>742</td><td>1.672</td><td>206.633</td><td>-1</td></tr> <tr> <td>54946</td><td>3097</td><td>7.455</td><td>205.114</td><td>2</td></tr> <tr> <td>54953</td><td>8582</td><td>21.256</td><td>205.059</td><td>7</td></tr> <tr> <td>54955</td><td>7120</td><td>16.789</td><td>205.140</td><td>6</td></tr> <tr></table> Total file length :   305.594 Mbytes",
-        "ALEPH - INFN",
-        "High Energy Physics",
-        "2000",
-        "eng",
-        "Researchers",
-        "info:eu-repo/semantics/other",
-        "Marcello Maggi"
-    ],
-    "notes": [
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>54919</td><td>20396</td><td>47.213</td><td>206.579</td><td>20</td></tr> <tr> <td>54920</td><td>571</td><td>1.460</td><td>206.591</td><td>1</td></tr> <tr> <td>54922</td><td>12176</td><td>30.622</td><td>205.123</td><td>15</td></tr> <tr> <td>54923</td><td>18764</td><td>44.922</td><td>206.531</td><td>21</td></tr> <tr> <td>54928</td><td>11604</td><td>26.286</td><td>206.580</td><td>13</td></tr> <tr> <td>54929</td><td>4279</td><td>8.291</td><td>207.986</td><td>3</td></tr> <tr> <td>54931</td><td>7960</td><td>20.254</td><td>205.119</td><td>11</td></tr> <tr> <td>54932</td><td>296</td><td>0.677</td><td>205.191</td><td>-1</td></tr> <tr> <td>54933</td><td>300</td><td>0.784</td><td>205.191</td><td>-1</td></tr> <tr> <td>54934</td><td>1012</td><td>2.232</td><td>205.191</td><td>1</td></tr> <tr> <td>54935</td><td>1322</td><td>3.160</td><td>205.191</td><td>3</td></tr> <tr> <td>54936</td><td>1562</td><td>3.600</td><td>205.219</td><td>4</td></tr> <tr> <td>54937</td><td>4913</td><td>11.800</td><td>206.548</td><td>4</td></tr> <tr> <td>54939</td><td>6500</td><td>15.923</td><td>205.122</td><td>2</td></tr> <tr> <td>54940</td><td>6166</td><td>15.004</td><td>206.639</td><td>2</td></tr> <tr> <td>54943</td><td>9260</td><td>23.892</td><td>205.121</td><td>10</td></tr> <tr> <td>54944</td><td>742</td><td>1.672</td><td>206.633</td><td>-1</td></tr> <tr> <td>54946</td><td>3097</td><td>7.455</td><td>205.114</td><td>2</td></tr> <tr> <td>54953</td><td>8582</td><td>21.256</td><td>205.059</td><td>7</td></tr> <tr> <td>54955</td><td>7120</td><td>16.789</td><td>205.140</td><td>6</td></tr> <tr></table> Total file length :   305.594 Mbytes"
-    ],
-    "oai_identifier": [
-        "oai:www.openaccessrepository.it:7168"
-    ],
-    "oai_set": [
-        "dataset:aleph",
-        "openaire"
-    ],
-    "tags": [
-        {
-            "name": "HEP CERN LEP ALEPH MINI RealData"
-        }
-    ],
-    "title": [
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4000.82.AL"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/f7cbbf77-ea96-5850-95e8-624da1db42ce.json b/oaitestdata/aleph-marcxml/dataset:aleph_1/json/f7cbbf77-ea96-5850-95e8-624da1db42ce.json
deleted file mode 100644
index 74f94b1d..00000000
--- a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/f7cbbf77-ea96-5850-95e8-624da1db42ce.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Checksum": null,
-    "Contact": [
-        "N/A"
-    ],
-    "Discipline": "Physics",
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": "N/A",
-    "PublicationTimestamp": "2000-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "author": [
-        "Marcello Maggi"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:www.openaccessrepository.it:7322",
-        "2016-06-29T14:35:14Z",
-        "dataset:aleph",
-        "openaire",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.83.AL,11100/a2b58078-cbe9-11e3-b259-e41f13eb41b2eng",
-        "00000coc  2200000uu 4500",
-        "7322",
-        "20160629143514.0",
-        "Handle",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.83.AL,11100/a2b58078-cbe9-11e3-b259-e41f13eb41b2",
-        "HEP CERN LEP ALEPH MINI RealData 2000",
-        "DATASETREALDATA",
-        "Marcello Maggi",
-        "1621536175",
-        "311556960",
-        "Search for neutral Higgs bosons decaying into four taus at LEP2",
-        "10.1007/JHEP05(2010)049",
-        "2010",
-        "[1]",
-        "PUBLICATIONINFN-2014-001",
-        "[1]",
-        "10.5072/oar.it/1411041136.04 ",
-        "ALEPH SCL5 Virtual Machine for Research Environment",
-        "SOFTWAREALEPH-2014-001",
-        "[2]",
-        "ALEPH Collaboration",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.83.AL",
-        "ALEPH",
-        "oai:www.openaccessrepository.it:7322",
-        "openaire",
-        "dataset:aleph",
-        "ALEPH",
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4001.83.AL",
-        "2014-09-01",
-        "ALEPH",
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>58271</td><td>6926</td><td>18.360</td><td>206.351</td><td>17</td></tr> <tr> <td>58273</td><td>17027</td><td>46.975</td><td>206.359</td><td>19</td></tr> <tr> <td>58274</td><td>1938</td><td>4.875</td><td>206.369</td><td>4</td></tr> <tr> <td>58276</td><td>16588</td><td>45.521</td><td>206.388</td><td>11</td></tr> <tr> <td>58277</td><td>7542</td><td>19.622</td><td>206.392</td><td>11</td></tr> <tr> <td>58278</td><td>1256</td><td>2.983</td><td>207.984</td><td>1</td></tr> <tr> <td>58280</td><td>1243</td><td>3.415</td><td>206.384</td><td>1</td></tr> <tr> <td>58282</td><td>9774</td><td>26.566</td><td>206.415</td><td>9</td></tr> <tr> <td>58283</td><td>2254</td><td>5.174</td><td>207.787</td><td>4</td></tr> <tr> <td>58289</td><td>3201</td><td>8.339</td><td>206.357</td><td>6</td></tr> <tr> <td>58291</td><td>3756</td><td>10.594</td><td>206.380</td><td>3</td></tr> <tr> <td>58297</td><td>16650</td><td>46.841</td><td>206.342</td><td>18</td></tr> <tr> <td>58298</td><td>3433</td><td>9.622</td><td>206.336</td><td>3</td></tr> <tr> <td>58299</td><td>4214</td><td>10.381</td><td>207.729</td><td>3</td></tr> <tr> <td>58302</td><td>15948</td><td>42.552</td><td>206.310</td><td>24</td></tr> <tr> <td>58303</td><td>3340</td><td>8.198</td><td>207.753</td><td>1</td></tr> <tr></table> Total file length :   305.594 Mbytes",
-        "ALEPH - INFN",
-        "High Energy Physics",
-        "2000",
-        "eng",
-        "Researchers",
-        "info:eu-repo/semantics/other",
-        "Marcello Maggi"
-    ],
-    "notes": [
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>58271</td><td>6926</td><td>18.360</td><td>206.351</td><td>17</td></tr> <tr> <td>58273</td><td>17027</td><td>46.975</td><td>206.359</td><td>19</td></tr> <tr> <td>58274</td><td>1938</td><td>4.875</td><td>206.369</td><td>4</td></tr> <tr> <td>58276</td><td>16588</td><td>45.521</td><td>206.388</td><td>11</td></tr> <tr> <td>58277</td><td>7542</td><td>19.622</td><td>206.392</td><td>11</td></tr> <tr> <td>58278</td><td>1256</td><td>2.983</td><td>207.984</td><td>1</td></tr> <tr> <td>58280</td><td>1243</td><td>3.415</td><td>206.384</td><td>1</td></tr> <tr> <td>58282</td><td>9774</td><td>26.566</td><td>206.415</td><td>9</td></tr> <tr> <td>58283</td><td>2254</td><td>5.174</td><td>207.787</td><td>4</td></tr> <tr> <td>58289</td><td>3201</td><td>8.339</td><td>206.357</td><td>6</td></tr> <tr> <td>58291</td><td>3756</td><td>10.594</td><td>206.380</td><td>3</td></tr> <tr> <td>58297</td><td>16650</td><td>46.841</td><td>206.342</td><td>18</td></tr> <tr> <td>58298</td><td>3433</td><td>9.622</td><td>206.336</td><td>3</td></tr> <tr> <td>58299</td><td>4214</td><td>10.381</td><td>207.729</td><td>3</td></tr> <tr> <td>58302</td><td>15948</td><td>42.552</td><td>206.310</td><td>24</td></tr> <tr> <td>58303</td><td>3340</td><td>8.198</td><td>207.753</td><td>1</td></tr> <tr></table> Total file length :   305.594 Mbytes"
-    ],
-    "oai_identifier": [
-        "oai:www.openaccessrepository.it:7322"
-    ],
-    "oai_set": [
-        "dataset:aleph",
-        "openaire"
-    ],
-    "tags": [
-        {
-            "name": "HEP CERN LEP ALEPH MINI RealData"
-        }
-    ],
-    "title": [
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4001.83.AL"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/f89dd186-843d-5ee5-b80d-769dd87aa9c8.json b/oaitestdata/aleph-marcxml/dataset:aleph_1/json/f89dd186-843d-5ee5-b80d-769dd87aa9c8.json
deleted file mode 100644
index b8423cef..00000000
--- a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/f89dd186-843d-5ee5-b80d-769dd87aa9c8.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Checksum": null,
-    "Contact": [
-        "N/A"
-    ],
-    "Discipline": "Physics",
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": "N/A",
-    "PublicationTimestamp": "2000-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "author": [
-        "Marcello Maggi"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:www.openaccessrepository.it:7235",
-        "2016-06-29T14:35:15Z",
-        "dataset:aleph",
-        "openaire",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4000.66.AL,11100/501a0f9a-cbe5-11e3-bae1-e41f13eb41b2eng",
-        "00000coc  2200000uu 4500",
-        "7235",
-        "20160629143515.0",
-        "Handle",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4000.66.AL,11100/501a0f9a-cbe5-11e3-bae1-e41f13eb41b2",
-        "HEP CERN LEP ALEPH MINI RealData 2000",
-        "DATASETREALDATA",
-        "Marcello Maggi",
-        "1223342829",
-        "322450560",
-        "Search for neutral Higgs bosons decaying into four taus at LEP2",
-        "10.1007/JHEP05(2010)049",
-        "2010",
-        "[1]",
-        "PUBLICATIONINFN-2014-001",
-        "[1]",
-        "10.5072/oar.it/1411041136.04 ",
-        "ALEPH SCL5 Virtual Machine for Research Environment",
-        "SOFTWAREALEPH-2014-001",
-        "[2]",
-        "ALEPH Collaboration",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4000.66.AL",
-        "ALEPH",
-        "oai:www.openaccessrepository.it:7235",
-        "openaire",
-        "dataset:aleph",
-        "ALEPH",
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4000.66.AL",
-        "2014-09-01",
-        "ALEPH",
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>54481</td><td>3680</td><td>7.247</td><td>208.272</td><td>1</td></tr> <tr> <td>54484</td><td>4793</td><td>11.486</td><td>205.085</td><td>3</td></tr> <tr> <td>54485</td><td>19609</td><td>47.300</td><td>206.098</td><td>21</td></tr> <tr> <td>54486</td><td>1747</td><td>3.471</td><td>206.234</td><td>1</td></tr> <tr> <td>54489</td><td>9470</td><td>22.398</td><td>206.115</td><td>12</td></tr> <tr> <td>54491</td><td>8907</td><td>22.115</td><td>205.128</td><td>4</td></tr> <tr> <td>54492</td><td>17056</td><td>40.703</td><td>206.106</td><td>19</td></tr> <tr> <td>54493</td><td>4717</td><td>9.329</td><td>208.357</td><td>3</td></tr> <tr> <td>54495</td><td>4126</td><td>9.118</td><td>205.121</td><td>7</td></tr> <tr> <td>54496</td><td>15703</td><td>36.683</td><td>206.115</td><td>15</td></tr> <tr> <td>54497</td><td>2718</td><td>5.390</td><td>208.311</td><td>3</td></tr> <tr> <td>54499</td><td>6099</td><td>13.974</td><td>205.114</td><td>8</td></tr> <tr> <td>54500</td><td>11393</td><td>25.477</td><td>206.100</td><td>6</td></tr> <tr> <td>54501</td><td>2331</td><td>4.435</td><td>207.844</td><td>4</td></tr> <tr> <td>54510</td><td>11949</td><td>29.030</td><td>205.085</td><td>7</td></tr> <tr> <td>54511</td><td>713</td><td>1.801</td><td>206.274</td><td>-1</td></tr> <tr> <td>54513</td><td>13237</td><td>30.643</td><td>205.083</td><td>13</td></tr> <tr></table> Total file length :   305.594 Mbytes",
-        "ALEPH - INFN",
-        "High Energy Physics",
-        "2000",
-        "eng",
-        "Researchers",
-        "info:eu-repo/semantics/other",
-        "Marcello Maggi"
-    ],
-    "notes": [
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>54481</td><td>3680</td><td>7.247</td><td>208.272</td><td>1</td></tr> <tr> <td>54484</td><td>4793</td><td>11.486</td><td>205.085</td><td>3</td></tr> <tr> <td>54485</td><td>19609</td><td>47.300</td><td>206.098</td><td>21</td></tr> <tr> <td>54486</td><td>1747</td><td>3.471</td><td>206.234</td><td>1</td></tr> <tr> <td>54489</td><td>9470</td><td>22.398</td><td>206.115</td><td>12</td></tr> <tr> <td>54491</td><td>8907</td><td>22.115</td><td>205.128</td><td>4</td></tr> <tr> <td>54492</td><td>17056</td><td>40.703</td><td>206.106</td><td>19</td></tr> <tr> <td>54493</td><td>4717</td><td>9.329</td><td>208.357</td><td>3</td></tr> <tr> <td>54495</td><td>4126</td><td>9.118</td><td>205.121</td><td>7</td></tr> <tr> <td>54496</td><td>15703</td><td>36.683</td><td>206.115</td><td>15</td></tr> <tr> <td>54497</td><td>2718</td><td>5.390</td><td>208.311</td><td>3</td></tr> <tr> <td>54499</td><td>6099</td><td>13.974</td><td>205.114</td><td>8</td></tr> <tr> <td>54500</td><td>11393</td><td>25.477</td><td>206.100</td><td>6</td></tr> <tr> <td>54501</td><td>2331</td><td>4.435</td><td>207.844</td><td>4</td></tr> <tr> <td>54510</td><td>11949</td><td>29.030</td><td>205.085</td><td>7</td></tr> <tr> <td>54511</td><td>713</td><td>1.801</td><td>206.274</td><td>-1</td></tr> <tr> <td>54513</td><td>13237</td><td>30.643</td><td>205.083</td><td>13</td></tr> <tr></table> Total file length :   305.594 Mbytes"
-    ],
-    "oai_identifier": [
-        "oai:www.openaccessrepository.it:7235"
-    ],
-    "oai_set": [
-        "dataset:aleph",
-        "openaire"
-    ],
-    "tags": [
-        {
-            "name": "HEP CERN LEP ALEPH MINI RealData"
-        }
-    ],
-    "title": [
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4000.66.AL"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/fafd1936-4a01-53be-8278-096333b77169.json b/oaitestdata/aleph-marcxml/dataset:aleph_1/json/fafd1936-4a01-53be-8278-096333b77169.json
deleted file mode 100644
index 31e4c506..00000000
--- a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/fafd1936-4a01-53be-8278-096333b77169.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Checksum": null,
-    "Contact": [
-        "N/A"
-    ],
-    "Discipline": "Physics",
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": "N/A",
-    "PublicationTimestamp": "2000-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "author": [
-        "Marcello Maggi"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:www.openaccessrepository.it:7313",
-        "2016-06-29T14:35:14Z",
-        "dataset:aleph",
-        "openaire",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.80.AL,11100/8a535104-cbe9-11e3-a65a-e41f13eb41b2eng",
-        "00000coc  2200000uu 4500",
-        "7313",
-        "20160629143514.0",
-        "Handle",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.80.AL,11100/8a535104-cbe9-11e3-a65a-e41f13eb41b2",
-        "HEP CERN LEP ALEPH MINI RealData 2000",
-        "DATASETREALDATA",
-        "Marcello Maggi",
-        "98239432",
-        "310403520",
-        "Search for neutral Higgs bosons decaying into four taus at LEP2",
-        "10.1007/JHEP05(2010)049",
-        "2010",
-        "[1]",
-        "PUBLICATIONINFN-2014-001",
-        "[1]",
-        "10.5072/oar.it/1411041136.04 ",
-        "ALEPH SCL5 Virtual Machine for Research Environment",
-        "SOFTWAREALEPH-2014-001",
-        "[2]",
-        "ALEPH Collaboration",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.80.AL",
-        "ALEPH",
-        "oai:www.openaccessrepository.it:7313",
-        "openaire",
-        "dataset:aleph",
-        "ALEPH",
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4001.80.AL",
-        "2014-09-01",
-        "ALEPH",
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>58183</td><td>16835</td><td>47.339</td><td>206.393</td><td>29</td></tr> <tr> <td>58184</td><td>5844</td><td>15.593</td><td>206.407</td><td>9</td></tr> <tr> <td>58185</td><td>761</td><td>1.787</td><td>207.730</td><td>2</td></tr> <tr> <td>58187</td><td>16903</td><td>47.268</td><td>206.393</td><td>25</td></tr> <tr> <td>58188</td><td>7361</td><td>20.676</td><td>206.398</td><td>9</td></tr> <tr> <td>58189</td><td>1130</td><td>2.808</td><td>208.030</td><td>-1</td></tr> <tr> <td>58201</td><td>16712</td><td>46.849</td><td>206.159</td><td>23</td></tr> <tr> <td>58202</td><td>3399</td><td>9.103</td><td>206.171</td><td>4</td></tr> <tr> <td>58203</td><td>1259</td><td>3.327</td><td>207.712</td><td>1</td></tr> <tr> <td>58205</td><td>16975</td><td>48.308</td><td>206.153</td><td>23</td></tr> <tr> <td>58206</td><td>7183</td><td>19.990</td><td>206.168</td><td>14</td></tr> <tr> <td>58207</td><td>733</td><td>1.771</td><td>207.765</td><td>-1</td></tr> <tr> <td>58209</td><td>16178</td><td>44.173</td><td>206.187</td><td>20</td></tr> <tr></table> Total file length :   305.594 Mbytes",
-        "ALEPH - INFN",
-        "High Energy Physics",
-        "2000",
-        "eng",
-        "Researchers",
-        "info:eu-repo/semantics/other",
-        "Marcello Maggi"
-    ],
-    "notes": [
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>58183</td><td>16835</td><td>47.339</td><td>206.393</td><td>29</td></tr> <tr> <td>58184</td><td>5844</td><td>15.593</td><td>206.407</td><td>9</td></tr> <tr> <td>58185</td><td>761</td><td>1.787</td><td>207.730</td><td>2</td></tr> <tr> <td>58187</td><td>16903</td><td>47.268</td><td>206.393</td><td>25</td></tr> <tr> <td>58188</td><td>7361</td><td>20.676</td><td>206.398</td><td>9</td></tr> <tr> <td>58189</td><td>1130</td><td>2.808</td><td>208.030</td><td>-1</td></tr> <tr> <td>58201</td><td>16712</td><td>46.849</td><td>206.159</td><td>23</td></tr> <tr> <td>58202</td><td>3399</td><td>9.103</td><td>206.171</td><td>4</td></tr> <tr> <td>58203</td><td>1259</td><td>3.327</td><td>207.712</td><td>1</td></tr> <tr> <td>58205</td><td>16975</td><td>48.308</td><td>206.153</td><td>23</td></tr> <tr> <td>58206</td><td>7183</td><td>19.990</td><td>206.168</td><td>14</td></tr> <tr> <td>58207</td><td>733</td><td>1.771</td><td>207.765</td><td>-1</td></tr> <tr> <td>58209</td><td>16178</td><td>44.173</td><td>206.187</td><td>20</td></tr> <tr></table> Total file length :   305.594 Mbytes"
-    ],
-    "oai_identifier": [
-        "oai:www.openaccessrepository.it:7313"
-    ],
-    "oai_set": [
-        "dataset:aleph",
-        "openaire"
-    ],
-    "tags": [
-        {
-            "name": "HEP CERN LEP ALEPH MINI RealData"
-        }
-    ],
-    "title": [
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4001.80.AL"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/fcd93d6b-c356-50e7-953e-b5849af30418.json b/oaitestdata/aleph-marcxml/dataset:aleph_1/json/fcd93d6b-c356-50e7-953e-b5849af30418.json
deleted file mode 100644
index 0f60a786..00000000
--- a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/fcd93d6b-c356-50e7-953e-b5849af30418.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Checksum": null,
-    "Contact": [
-        "N/A"
-    ],
-    "Discipline": "Physics",
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": "N/A",
-    "PublicationTimestamp": "2000-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "author": [
-        "Marcello Maggi"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:www.openaccessrepository.it:7228",
-        "2016-06-29T14:35:15Z",
-        "dataset:aleph",
-        "openaire",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.93.AL,11100/09226fb0-cbea-11e3-9a66-e41f13eb41b2eng",
-        "00000coc  2200000uu 4500",
-        "7228",
-        "20160629143515.0",
-        "Handle",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.93.AL,11100/09226fb0-cbea-11e3-9a66-e41f13eb41b2",
-        "HEP CERN LEP ALEPH MINI RealData 2000",
-        "DATASETREALDATA",
-        "Marcello Maggi",
-        "731109976",
-        "340425000",
-        "Search for neutral Higgs bosons decaying into four taus at LEP2",
-        "10.1007/JHEP05(2010)049",
-        "2010",
-        "[1]",
-        "PUBLICATIONINFN-2014-001",
-        "[1]",
-        "10.5072/oar.it/1411041136.04 ",
-        "ALEPH SCL5 Virtual Machine for Research Environment",
-        "SOFTWAREALEPH-2014-001",
-        "[2]",
-        "ALEPH Collaboration",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.93.AL",
-        "ALEPH",
-        "oai:www.openaccessrepository.it:7228",
-        "openaire",
-        "dataset:aleph",
-        "ALEPH",
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4001.93.AL",
-        "2014-09-01",
-        "ALEPH",
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>45231</td><td>8811</td><td>42.049</td><td>91.282</td><td>1193</td></tr> <tr> <td>45232</td><td>8257</td><td>38.572</td><td>91.261</td><td>1085</td></tr> <tr> <td>45233</td><td>5283</td><td>23.202</td><td>91.263</td><td>647</td></tr> <tr> <td>45236</td><td>763</td><td>3.268</td><td>91.366</td><td>90</td></tr> <tr> <td>45239</td><td>11582</td><td>49.932</td><td>91.385</td><td>1351</td></tr> <tr> <td>45240</td><td>3216</td><td>14.216</td><td>91.386</td><td>400</td></tr> <tr> <td>45242</td><td>10403</td><td>49.864</td><td>91.382</td><td>1467</td></tr> <tr> <td>45243</td><td>10179</td><td>48.533</td><td>91.382</td><td>1442</td></tr> <tr> <td>45244</td><td>8240</td><td>33.332</td><td>91.384</td><td>937</td></tr> <tr> <td>45245</td><td>8234</td><td>36.319</td><td>91.320</td><td>1047</td></tr> <tr></table> Total file length :   305.594 Mbytes",
-        "ALEPH - INFN",
-        "High Energy Physics",
-        "2000",
-        "eng",
-        "Researchers",
-        "info:eu-repo/semantics/other",
-        "Marcello Maggi"
-    ],
-    "notes": [
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>45231</td><td>8811</td><td>42.049</td><td>91.282</td><td>1193</td></tr> <tr> <td>45232</td><td>8257</td><td>38.572</td><td>91.261</td><td>1085</td></tr> <tr> <td>45233</td><td>5283</td><td>23.202</td><td>91.263</td><td>647</td></tr> <tr> <td>45236</td><td>763</td><td>3.268</td><td>91.366</td><td>90</td></tr> <tr> <td>45239</td><td>11582</td><td>49.932</td><td>91.385</td><td>1351</td></tr> <tr> <td>45240</td><td>3216</td><td>14.216</td><td>91.386</td><td>400</td></tr> <tr> <td>45242</td><td>10403</td><td>49.864</td><td>91.382</td><td>1467</td></tr> <tr> <td>45243</td><td>10179</td><td>48.533</td><td>91.382</td><td>1442</td></tr> <tr> <td>45244</td><td>8240</td><td>33.332</td><td>91.384</td><td>937</td></tr> <tr> <td>45245</td><td>8234</td><td>36.319</td><td>91.320</td><td>1047</td></tr> <tr></table> Total file length :   305.594 Mbytes"
-    ],
-    "oai_identifier": [
-        "oai:www.openaccessrepository.it:7228"
-    ],
-    "oai_set": [
-        "dataset:aleph",
-        "openaire"
-    ],
-    "tags": [
-        {
-            "name": "HEP CERN LEP ALEPH MINI RealData"
-        }
-    ],
-    "title": [
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4001.93.AL"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/fe155777-cf48-5a5f-8b57-280430c55ff0.json b/oaitestdata/aleph-marcxml/dataset:aleph_1/json/fe155777-cf48-5a5f-8b57-280430c55ff0.json
deleted file mode 100644
index 53e4ba7b..00000000
--- a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/fe155777-cf48-5a5f-8b57-280430c55ff0.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Checksum": null,
-    "Contact": [
-        "N/A"
-    ],
-    "Discipline": "Physics",
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": "N/A",
-    "PublicationTimestamp": "2000-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "author": [
-        "Marcello Maggi"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:www.openaccessrepository.it:7326",
-        "2016-06-29T14:35:14Z",
-        "dataset:aleph",
-        "openaire",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.16.AL,11100/e8841252-cbe6-11e3-8de5-e41f13eb41b2eng",
-        "00000coc  2200000uu 4500",
-        "7326",
-        "20160629143514.0",
-        "Handle",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.16.AL,11100/e8841252-cbe6-11e3-8de5-e41f13eb41b2",
-        "High Energy Physics",
-        "HEP CERN LEP ALEPH MINI RealData 2000",
-        "DATASETREALDATA",
-        "Marcello Maggi",
-        "3662296428",
-        "313479360",
-        "Search for neutral Higgs bosons decaying into four taus at LEP2",
-        "10.1007/JHEP05(2010)049",
-        "2010",
-        "[1]",
-        "PUBLICATIONINFN-2014-001",
-        "[1]",
-        "10.5072/oar.it/1411041136.04 ",
-        "ALEPH SCL5 Virtual Machine for Research Environment",
-        "SOFTWAREALEPH-2014-001",
-        "[2]",
-        "ALEPH Collaboration",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.16.AL",
-        "ALEPH",
-        "oai:www.openaccessrepository.it:7326",
-        "openaire",
-        "dataset:aleph",
-        "ALEPH",
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4001.16.AL",
-        "2014-09-01",
-        "ALEPH",
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>56100</td><td>3291</td><td>8.334</td><td>206.543</td><td>6</td></tr> <tr> <td>56101</td><td>2259</td><td>5.341</td><td>207.941</td><td>3</td></tr> <tr> <td>56103</td><td>8351</td><td>20.408</td><td>206.560</td><td>13</td></tr> <tr> <td>56106</td><td>6172</td><td>15.357</td><td>206.598</td><td>10</td></tr> <tr> <td>56107</td><td>593</td><td>0.842</td><td>207.879</td><td>1</td></tr> <tr> <td>56109</td><td>1827</td><td>3.996</td><td>206.577</td><td>-1</td></tr> <tr> <td>56115</td><td>19256</td><td>48.238</td><td>206.566</td><td>21</td></tr> <tr> <td>56117</td><td>12838</td><td>31.163</td><td>206.570</td><td>19</td></tr> <tr> <td>56118</td><td>1725</td><td>3.660</td><td>207.944</td><td>-1</td></tr> <tr> <td>56120</td><td>15353</td><td>39.233</td><td>206.592</td><td>18</td></tr> <tr> <td>56675</td><td>734</td><td>1.463</td><td>207.960</td><td>1</td></tr> <tr> <td>56677</td><td>1372</td><td>1.524</td><td>206.620</td><td>-1</td></tr> <tr> <td>56679</td><td>8676</td><td>26.834</td><td>206.378</td><td>13</td></tr> <tr> <td>56681</td><td>17181</td><td>51.980</td><td>206.374</td><td>34</td></tr> <tr> <td>56688</td><td>17345</td><td>53.535</td><td>206.392</td><td>21</td></tr> <tr></table> Total file length :   305.594 Mbytes",
-        "eng",
-        "Researchers",
-        "info:eu-repo/semantics/other",
-        "Marcello Maggi",
-        "2000",
-        "ALEPH - INFN"
-    ],
-    "notes": [
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>56100</td><td>3291</td><td>8.334</td><td>206.543</td><td>6</td></tr> <tr> <td>56101</td><td>2259</td><td>5.341</td><td>207.941</td><td>3</td></tr> <tr> <td>56103</td><td>8351</td><td>20.408</td><td>206.560</td><td>13</td></tr> <tr> <td>56106</td><td>6172</td><td>15.357</td><td>206.598</td><td>10</td></tr> <tr> <td>56107</td><td>593</td><td>0.842</td><td>207.879</td><td>1</td></tr> <tr> <td>56109</td><td>1827</td><td>3.996</td><td>206.577</td><td>-1</td></tr> <tr> <td>56115</td><td>19256</td><td>48.238</td><td>206.566</td><td>21</td></tr> <tr> <td>56117</td><td>12838</td><td>31.163</td><td>206.570</td><td>19</td></tr> <tr> <td>56118</td><td>1725</td><td>3.660</td><td>207.944</td><td>-1</td></tr> <tr> <td>56120</td><td>15353</td><td>39.233</td><td>206.592</td><td>18</td></tr> <tr> <td>56675</td><td>734</td><td>1.463</td><td>207.960</td><td>1</td></tr> <tr> <td>56677</td><td>1372</td><td>1.524</td><td>206.620</td><td>-1</td></tr> <tr> <td>56679</td><td>8676</td><td>26.834</td><td>206.378</td><td>13</td></tr> <tr> <td>56681</td><td>17181</td><td>51.980</td><td>206.374</td><td>34</td></tr> <tr> <td>56688</td><td>17345</td><td>53.535</td><td>206.392</td><td>21</td></tr> <tr></table> Total file length :   305.594 Mbytes"
-    ],
-    "oai_identifier": [
-        "oai:www.openaccessrepository.it:7326"
-    ],
-    "oai_set": [
-        "dataset:aleph",
-        "openaire"
-    ],
-    "tags": [
-        {
-            "name": "HEP CERN LEP ALEPH MINI RealData"
-        }
-    ],
-    "title": [
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4001.16.AL"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/feb3fc1a-bb40-5221-9e7a-0932f6c4a1a3.json b/oaitestdata/aleph-marcxml/dataset:aleph_1/json/feb3fc1a-bb40-5221-9e7a-0932f6c4a1a3.json
deleted file mode 100644
index 8855c59c..00000000
--- a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/feb3fc1a-bb40-5221-9e7a-0932f6c4a1a3.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Checksum": null,
-    "Contact": [
-        "N/A"
-    ],
-    "Discipline": "Physics",
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": "N/A",
-    "PublicationTimestamp": "2000-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "author": [
-        "Marcello Maggi"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:www.openaccessrepository.it:7216",
-        "2016-06-29T14:35:13Z",
-        "dataset:aleph",
-        "openaire",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.97.AL,11100/3616d790-cbea-11e3-9c8a-e41f13eb41b2\neng",
-        "00000coc  2200000uu 4500",
-        "7216",
-        "20160629143513.0",
-        "Handle",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.97.AL,11100/3616d790-cbea-11e3-9c8a-e41f13eb41b2\n",
-        "ALEPH",
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4001.97.AL",
-        "2014-09-01",
-        "ALEPH",
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>45306</td><td>10941</td><td>40.637</td><td>91.213</td><td>1230</td></tr> <tr> <td>45307</td><td>9102</td><td>34.802</td><td>91.208</td><td>1044</td></tr> <tr> <td>45308</td><td>8643</td><td>34.057</td><td>91.216</td><td>1054</td></tr> <tr> <td>45309</td><td>8423</td><td>33.057</td><td>91.225</td><td>1013</td></tr> <tr> <td>45310</td><td>8000</td><td>31.096</td><td>91.187</td><td>938</td></tr> <tr> <td>45311</td><td>1726</td><td>6.602</td><td>91.155</td><td>194</td></tr> <tr> <td>45313</td><td>10696</td><td>43.252</td><td>91.260</td><td>1321</td></tr> <tr> <td>45314</td><td>9066</td><td>35.294</td><td>91.250</td><td>1065</td></tr> <tr> <td>45315</td><td>4218</td><td>16.364</td><td>91.236</td><td>500</td></tr> <tr> <td>45319</td><td>9968</td><td>42.913</td><td>91.220</td><td>1333</td></tr> <tr></table> Total file length :   305.594 Mbytes",
-        "HEP CERN LEP ALEPH MINI RealData 2000",
-        "ALEPH Collaboration",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.97.AL",
-        "ALEPH",
-        "oai:www.openaccessrepository.it:7216",
-        "openaire",
-        "dataset:aleph",
-        "High Energy Physics",
-        "2000",
-        "ALEPH - INFN",
-        "DATASETREALDATA",
-        "Marcello Maggi",
-        "3310101719",
-        "319246560",
-        "Search for neutral Higgs bosons decaying into four taus at LEP2",
-        "10.1007/JHEP05(2010)049",
-        "2010",
-        "[1]",
-        "PUBLICATIONINFN-2014-001",
-        "[1]",
-        "10.5072/oar.it/1411041136.04 ",
-        "ALEPH SCL5 Virtual Machine for Research Environment",
-        "SOFTWAREALEPH-2014-001",
-        "[2]",
-        "eng",
-        "Researchers",
-        "info:eu-repo/semantics/other",
-        "Marcello Maggi"
-    ],
-    "notes": [
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>45306</td><td>10941</td><td>40.637</td><td>91.213</td><td>1230</td></tr> <tr> <td>45307</td><td>9102</td><td>34.802</td><td>91.208</td><td>1044</td></tr> <tr> <td>45308</td><td>8643</td><td>34.057</td><td>91.216</td><td>1054</td></tr> <tr> <td>45309</td><td>8423</td><td>33.057</td><td>91.225</td><td>1013</td></tr> <tr> <td>45310</td><td>8000</td><td>31.096</td><td>91.187</td><td>938</td></tr> <tr> <td>45311</td><td>1726</td><td>6.602</td><td>91.155</td><td>194</td></tr> <tr> <td>45313</td><td>10696</td><td>43.252</td><td>91.260</td><td>1321</td></tr> <tr> <td>45314</td><td>9066</td><td>35.294</td><td>91.250</td><td>1065</td></tr> <tr> <td>45315</td><td>4218</td><td>16.364</td><td>91.236</td><td>500</td></tr> <tr> <td>45319</td><td>9968</td><td>42.913</td><td>91.220</td><td>1333</td></tr> <tr></table> Total file length :   305.594 Mbytes"
-    ],
-    "oai_identifier": [
-        "oai:www.openaccessrepository.it:7216"
-    ],
-    "oai_set": [
-        "dataset:aleph",
-        "openaire"
-    ],
-    "tags": [
-        {
-            "name": "HEP CERN LEP ALEPH MINI RealData"
-        }
-    ],
-    "title": [
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4001.97.AL"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/ff957fab-7523-5b3d-b7fc-3d64e1a0cfa6.json b/oaitestdata/aleph-marcxml/dataset:aleph_1/json/ff957fab-7523-5b3d-b7fc-3d64e1a0cfa6.json
deleted file mode 100644
index 91872444..00000000
--- a/oaitestdata/aleph-marcxml/dataset:aleph_1/json/ff957fab-7523-5b3d-b7fc-3d64e1a0cfa6.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Checksum": null,
-    "Contact": [
-        "N/A"
-    ],
-    "Discipline": "Physics",
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": "N/A",
-    "PublicationTimestamp": "2000-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "author": [
-        "Marcello Maggi"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:www.openaccessrepository.it:7292",
-        "2016-06-29T14:35:14Z",
-        "dataset:aleph",
-        "openaire",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.22.AL,11100/21065950-cbe7-11e3-b2d0-e41f13eb41b2eng",
-        "00000coc  2200000uu 4500",
-        "7292",
-        "20160629143514.0",
-        "Handle",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.22.AL,11100/21065950-cbe7-11e3-b2d0-e41f13eb41b2",
-        "HEP CERN LEP ALEPH MINI RealData 2000",
-        "DATASETREALDATA",
-        "Marcello Maggi",
-        "3183251205",
-        "311460840",
-        "Search for neutral Higgs bosons decaying into four taus at LEP2",
-        "10.1007/JHEP05(2010)049",
-        "2010",
-        "[1]",
-        "PUBLICATIONINFN-2014-001",
-        "[1]",
-        "10.5072/oar.it/1411041136.04 ",
-        "ALEPH SCL5 Virtual Machine for Research Environment",
-        "SOFTWAREALEPH-2014-001",
-        "[2]",
-        "ALEPH Collaboration",
-        "irods://data.repo.cineca.it:1247/CINECA01/home/DRES_EUDalep/dati/ZD4001.22.AL",
-        "ALEPH",
-        "oai:www.openaccessrepository.it:7292",
-        "openaire",
-        "dataset:aleph",
-        "ALEPH",
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4001.22.AL",
-        "2014-09-01",
-        "ALEPH",
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>56294</td><td>5778</td><td>11.455</td><td>205.231</td><td>4</td></tr> <tr> <td>56295</td><td>8187</td><td>19.730</td><td>206.401</td><td>10</td></tr> <tr> <td>56296</td><td>1157</td><td>1.966</td><td>207.852</td><td>2</td></tr> <tr> <td>56298</td><td>2553</td><td>6.699</td><td>205.204</td><td>1</td></tr> <tr> <td>56299</td><td>11983</td><td>31.012</td><td>206.399</td><td>11</td></tr> <tr> <td>56301</td><td>2781</td><td>7.219</td><td>205.199</td><td>3</td></tr> <tr> <td>56302</td><td>10486</td><td>27.099</td><td>206.391</td><td>18</td></tr> <tr> <td>56304</td><td>3193</td><td>8.326</td><td>205.202</td><td>3</td></tr> <tr> <td>56305</td><td>9852</td><td>24.324</td><td>206.386</td><td>12</td></tr> <tr> <td>56307</td><td>3172</td><td>7.691</td><td>205.184</td><td>3</td></tr> <tr> <td>56308</td><td>5272</td><td>13.452</td><td>206.349</td><td>4</td></tr> <tr> <td>56310</td><td>2735</td><td>7.180</td><td>205.187</td><td>6</td></tr> <tr> <td>56311</td><td>13191</td><td>32.959</td><td>206.390</td><td>17</td></tr> <tr> <td>56312</td><td>6174</td><td>11.819</td><td>207.796</td><td>3</td></tr> <tr> <td>56314</td><td>2023</td><td>5.598</td><td>205.194</td><td>4</td></tr> <tr> <td>56315</td><td>19626</td><td>48.153</td><td>206.392</td><td>14</td></tr> <tr> <td>56316</td><td>351</td><td>0.460</td><td>207.992</td><td>-1</td></tr> <tr> <td>56319</td><td>2505</td><td>6.718</td><td>205.201</td><td>2</td></tr> <tr> <td>56320</td><td>15590</td><td>37.957</td><td>206.395</td><td>13</td></tr> <tr></table> Total file length :   305.594 Mbytes",
-        "ALEPH - INFN",
-        "High Energy Physics",
-        "2000",
-        "eng",
-        "Researchers",
-        "info:eu-repo/semantics/other",
-        "Marcello Maggi"
-    ],
-    "notes": [
-        "Run contents for this data file <table border=\"1\"> <tr> <th>Run #</th><th>Nevents</th><th>Length (Mb)</th><th>LEP energy</th><th>Nb of Z0s</th></tr> <tr> <td>56294</td><td>5778</td><td>11.455</td><td>205.231</td><td>4</td></tr> <tr> <td>56295</td><td>8187</td><td>19.730</td><td>206.401</td><td>10</td></tr> <tr> <td>56296</td><td>1157</td><td>1.966</td><td>207.852</td><td>2</td></tr> <tr> <td>56298</td><td>2553</td><td>6.699</td><td>205.204</td><td>1</td></tr> <tr> <td>56299</td><td>11983</td><td>31.012</td><td>206.399</td><td>11</td></tr> <tr> <td>56301</td><td>2781</td><td>7.219</td><td>205.199</td><td>3</td></tr> <tr> <td>56302</td><td>10486</td><td>27.099</td><td>206.391</td><td>18</td></tr> <tr> <td>56304</td><td>3193</td><td>8.326</td><td>205.202</td><td>3</td></tr> <tr> <td>56305</td><td>9852</td><td>24.324</td><td>206.386</td><td>12</td></tr> <tr> <td>56307</td><td>3172</td><td>7.691</td><td>205.184</td><td>3</td></tr> <tr> <td>56308</td><td>5272</td><td>13.452</td><td>206.349</td><td>4</td></tr> <tr> <td>56310</td><td>2735</td><td>7.180</td><td>205.187</td><td>6</td></tr> <tr> <td>56311</td><td>13191</td><td>32.959</td><td>206.390</td><td>17</td></tr> <tr> <td>56312</td><td>6174</td><td>11.819</td><td>207.796</td><td>3</td></tr> <tr> <td>56314</td><td>2023</td><td>5.598</td><td>205.194</td><td>4</td></tr> <tr> <td>56315</td><td>19626</td><td>48.153</td><td>206.392</td><td>14</td></tr> <tr> <td>56316</td><td>351</td><td>0.460</td><td>207.992</td><td>-1</td></tr> <tr> <td>56319</td><td>2505</td><td>6.718</td><td>205.201</td><td>2</td></tr> <tr> <td>56320</td><td>15590</td><td>37.957</td><td>206.395</td><td>13</td></tr> <tr></table> Total file length :   305.594 Mbytes"
-    ],
-    "oai_identifier": [
-        "oai:www.openaccessrepository.it:7292"
-    ],
-    "oai_set": [
-        "dataset:aleph",
-        "openaire"
-    ],
-    "tags": [
-        {
-            "name": "HEP CERN LEP ALEPH MINI RealData"
-        }
-    ],
-    "title": [
-        "LEP Data from The ALEPH Collaboration year 2000 datafile ZD4001.22.AL"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/anaee-iso19139/SET_1/json/28e634ad-e4f4-5b54-a635-90c0c92d0692.json b/oaitestdata/anaee-iso19139/SET_1/json/28e634ad-e4f4-5b54-a635-90c0c92d0692.json
deleted file mode 100644
index bec69105..00000000
--- a/oaitestdata/anaee-iso19139/SET_1/json/28e634ad-e4f4-5b54-a635-90c0c92d0692.json
+++ /dev/null
@@ -1,101 +0,0 @@
-{
-    "Contact": [
-        "christian.pichot@avignon.inra.fr"
-    ],
-    "Contributor": [
-        "AnaEE"
-    ],
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Format": [
-        "inapplicable"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://w3.avignon.inra.fr/geonetwork_anaee/srv/fre/csw-envriplus?verb=GetRecord&metadataPrefix=iso19139&identifier=28e634ad-e4f4-5b54-a635-90c0c92d0692",
-    "PublicationTimestamp": "2018-10-20T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "INRA"
-    ],
-    "ResourceType": "dataset",
-    "Rights": [
-        "See AnaEE-France charters"
-    ],
-    "SpatialCoverage": "(41N-51N,6 W-10E)",
-    "TempCoverageBegin": 63461015999,
-    "TempCoverageEnd": 63461015999,
-    "TemporalCoverage": " point in time : 2012-01-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2012-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2012-01-01T11:59:59Z",
-    "author": [
-        "Philippe Clastre",
-        "Christian PICHOT"
-    ],
-    "fulltext": "20b9aa10-5aa5-48e3-bb61-e5a5746796ae;Philippe Clastre;INRA;Christian PICHOT;INRA;+33 4 32 72 29 66;+33 4 90 13 59 59;INRA - Domaine Saint-Paul - Site Agroparc;Avignon Cedex 9;84914;France;christian.pichot@avignon.inra.fr;2018-10-30T11:05:49;ISO 19115:2003/19139;1.0;WGS 84 (EPSG:4326);AnaEE-France modeling platforms and data management services;Plateforme de mod\u00e9lisation et services de gestion des donn\u00e9es de AnaEE-France;2018-10-20;http://w3.avignon.inra.fr/geonetwork_anaee/80894c9d-aa65-4808-8870-a04a7bf402f4;Jean-Fran\u00e7ois LE GALLIARD;CNRS;+33 1 64 28 35 33;+33 1 64 28 02 66;78, rue du Ch\u00e2teau;Saint-Pierre-L\u00e8s-Nemours;77140;France;cereep@biologie.ens.fr;Andr\u00e9 CHANZY;INRA;+33 4 32 72 22 11;+33 4 32 72 22 12;Domaine Saint Paul - Site Agroparc CS 40509;Avignon Cedex 9;84914;France;andre.chanzy@avignon.inra.fr;AnaEE-France is the French national infrastructure devoted to the study of continental ecosystems and their biodiversity. It offers experimental facilities in controlled, semi-natural or natural environments, analysis platforms and shared instruments as well as modeling platforms and database Information Systems.\nModeling platforms are facilities specialized in developing models to support the projects run by AnaEE.  They streamline model development by providing the necessary hardware and software, as well as the access to expertise, datasets and modelling libraries. Two types of platforms are or will be provided: i) model factories which are nationally supported software platforms with advanced and well-established facilities providing users access to general and extensible modeling resources and ii) Modeling solution platforms which are implemented as self-contained software solutions that model specific aspects of ecosystem function and are centered on a well-established and supported model development team with a strong community of users.\nBoth types are used to exploit mathematical models to test and develop our understanding of the complex quantitative relationships between processes within ecosystems, the interactions with their environments, and their functioning and behaviour under various pressures.\n\nDatabase Information systems have been developed for the management of the data produced by the AnaEE-F experimental facilities. These IS rely on two main architectural models : databases for long term experiments (in natura) and databases for short to middle term experiments (mostly in ecotrons and mesocosms)\n\nBased on a distributed architecture, the overall AnaEE-F IS develops a semantic interoperability of modeling platforms and database IS and provides portals for the discovery and the exploitation of these resources.;Experimentation on continental ecosystems;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng//resources.get?uuid=20b9aa10-5aa5-48e3-bb61-e5a5746796ae&fname=AnaEE_node5.png;large_thumbnail;png;France;France;AnaEE-France Locations;2018-07-12;geonetwork.thesaurus.local.place.anaee-france_locations;Environmental monitoring facilities;Installations de suivi environnemental;GEMET - INSPIRE themes, version 1.0 INSPIRE themes;2008-06-01;geonetwork.thesaurus.external.theme.inspire-theme;modelling platform;plateforme de mod\u00e9lisation;databases;base de donn\u00e9es;information system;syst\u00e8me d'information;theme.anaeeThes.rdf;2018-07-12;geonetwork.thesaurus.external.theme.anaeeThes;theme.drivers.rdf;2018-06-25;geonetwork.thesaurus.external.theme.drivers;biodiversity;biodiversit\u00e9;imaging;imagerie;air chemical property;propri\u00e9t\u00e9 chimique de l'air;meteorology;m\u00e9t\u00e9orologie;organic amendment;amendement organique;soil biology;biologie du sol;surface flux;flux de surface;soil chemistry;chimie du sol;water chemical property;propri\u00e9t\u00e9 chimique de l'eau;vegetation;v\u00e9g\u00e9tation;water biology;biologie de l'eau;soil physics;physique du sol;mulch;paillis;ecosystem management;gestion des \u00e9cosyst\u00e8mes;water physical property;propri\u00e9t\u00e9 physique de l'eau;theme.variableAnaee.rdf;2018-08-24;geonetwork.thesaurus.external.theme.variableAnaee;See AnaEE-France charters;5000;structure;2012-01-01;France;-5.7;9.5;41.3;51;You can customize the template to suit your needs. You can add and remove fields and fill out default information (e.g. contact details). Fields you can not change in the default view may be accessible in the more comprehensive (and more complex) advanced view. You can even use the XML editor to create custom structures, but they have to be validated by the system, so know what you do :-);inapplicable;inapplicable;https://www.anaee-france.fr/en/about-us/introduction-to-anaee-france;WWW:LINK-1.0-http--link;AnaEE-France web site;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/home;WWW:LINK-1.0-http--link;AnaEE-France metadata catalogue;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/864d43f1-fbba-4652-896d-61950f3d3a22;WWW:LINK-1.0-http--link;Virtual Soil Modeling Platform;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/ee520bf5-f86b-4064-97ce-8fb308d17efb;WWW:LINK-1.0-http--link;RECORD modeling and simulating platform for agroecosystems;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/59c9d6ec-057c-4ebf-b69f-35286784b9d2;WWW:LINK-1.0-http--link;CAPSIS (Computer-Aided Projection of Strategies In Silviculture);Ecotron IleDeFrance;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/fd85ef74-988e-44c7-bb1b-c3655e6e5137;WWW:LINK-1.0-http--link;Information Systems for the \"Observation and Experimentation Systems for Environmental Research\" (SOERE);http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/c106e898-b8a4-4679-8e2b-eb8fc04e8337;WWW:LINK-1.0-http--link;UMS BBEES 3468 - AnaEE-F;Commission Regulation (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;Not evaluated",
-    "group": "anaee",
-    "groups": [
-        {
-            "name": "anaee"
-        }
-    ],
-    "name": "28e634ad-e4f4-5b54-a635-90c0c92d0692",
-    "notes": [
-        "AnaEE-France is the French national infrastructure devoted to the study of continental ecosystems and their biodiversity. It offers experimental facilities in controlled, semi-natural or natural environments, analysis platforms and shared instruments as well as modeling platforms and database Information Systems.\nModeling platforms are facilities specialized in developing models to support the projects run by AnaEE.  They streamline model development by providing the necessary hardware and software, as well as the access to expertise, datasets and modelling libraries. Two types of platforms are or will be provided: i) model factories which are nationally supported software platforms with advanced and well-established facilities providing users access to general and extensible modeling resources and ii) Modeling solution platforms which are implemented as self-contained software solutions that model specific aspects of ecosystem function and are centered on a well-established and supported model development team with a strong community of users.\nBoth types are used to exploit mathematical models to test and develop our understanding of the complex quantitative relationships between processes within ecosystems, the interactions with their environments, and their functioning and behaviour under various pressures.\n\nDatabase Information systems have been developed for the management of the data produced by the AnaEE-F experimental facilities. These IS rely on two main architectural models : databases for long term experiments (in natura) and databases for short to middle term experiments (mostly in ecotrons and mesocosms)\n\nBased on a distributed architecture, the overall AnaEE-F IS develops a semantic interoperability of modeling platforms and database IS and provides portals for the discovery and the exploitation of these resources."
-    ],
-    "oai_identifier": [
-        "28e634ad-e4f4-5b54-a635-90c0c92d0692"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-5.7,41.3],[-5.7,51],[9.5,51],[9.5,41.3],[-5.7,41.3]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "France"
-        },
-        {
-            "name": "Environmental monitoring facilities"
-        },
-        {
-            "name": "modelling platform"
-        },
-        {
-            "name": "databases"
-        },
-        {
-            "name": "information system"
-        },
-        {
-            "name": "biodiversity"
-        },
-        {
-            "name": "imaging"
-        },
-        {
-            "name": "air chemical property"
-        },
-        {
-            "name": "meteorology"
-        },
-        {
-            "name": "organic amendment"
-        },
-        {
-            "name": "soil biology"
-        },
-        {
-            "name": "surface flux"
-        }
-    ],
-    "title": [
-        "AnaEE-France modeling platforms and data management services"
-    ],
-    "url": "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/c106e898-b8a4-4679-8e2b-eb8fc04e8337"
-}
\ No newline at end of file
diff --git a/oaitestdata/anaee-iso19139/SET_1/json/30aef3e3-19f7-5f41-94ca-242a7d300d85.json b/oaitestdata/anaee-iso19139/SET_1/json/30aef3e3-19f7-5f41-94ca-242a7d300d85.json
deleted file mode 100644
index ab6ef601..00000000
--- a/oaitestdata/anaee-iso19139/SET_1/json/30aef3e3-19f7-5f41-94ca-242a7d300d85.json
+++ /dev/null
@@ -1,201 +0,0 @@
-{
-    "Contact": [
-        "christian.pichot@avignon.inra.fr"
-    ],
-    "Contributor": [
-        "AnaEE"
-    ],
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Format": [
-        "inapplicable"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://w3.avignon.inra.fr/geonetwork_anaee/srv/fre/csw-envriplus?verb=GetRecord&metadataPrefix=iso19139&identifier=30aef3e3-19f7-5f41-94ca-242a7d300d85",
-    "PublicationTimestamp": "2018-10-20T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "INRA"
-    ],
-    "ResourceType": "dataset",
-    "Rights": [
-        "See AnaEE-France charters"
-    ],
-    "SpatialCoverage": [
-        "47.22",
-        "48.16",
-        "5.7",
-        "45.250812",
-        "48.524083",
-        "43.51",
-        "42.86",
-        "48.56",
-        "48.11168",
-        "44.432843",
-        "48.7",
-        "47.48",
-        "47.2835",
-        "42.1427",
-        "47.23",
-        "47.403",
-        "46.1367",
-        "52.45",
-        "42.75",
-        "43.8452",
-        "44.38432",
-        "47.3155",
-        "44.38432",
-        "9.8",
-        "43.8",
-        "4.94",
-        "2.58",
-        "-54.6",
-        "-1.97023",
-        "2.914269",
-        "3.77",
-        "0.99",
-        "6.08",
-        "-1.71026",
-        "2.010709",
-        "2.03",
-        "5.69",
-        "1.4649",
-        "4.4045",
-        "0.9",
-        "6.0359",
-        "5.9533",
-        "5",
-        "2.6",
-        "5.5926",
-        "1.435167",
-        "4.168",
-        "1.435167",
-        "-83.6",
-        "5.5",
-        "47.42",
-        "48.36",
-        "2.1",
-        "47.250812",
-        "50.524083",
-        "43.71",
-        "43.06",
-        "48.79",
-        "48.11363",
-        "46.432843",
-        "48.9",
-        "49.48",
-        "48.2835",
-        "44.1427",
-        "49.23",
-        "49.403",
-        "46.5349",
-        "52.65",
-        "44.75",
-        "46.5207",
-        "46.38432",
-        "49.3155",
-        "46.431768",
-        "10",
-        "44",
-        "5.14",
-        "2.78",
-        "-51.6",
-        "1.07023",
-        "4.014269",
-        "3.97",
-        "1.19",
-        "6.28",
-        "-1.70489",
-        "4.010709",
-        "2.23",
-        "7.69",
-        "3.4649",
-        "6.4045",
-        "2.9",
-        "8.0359",
-        "7.0387",
-        "5.3",
-        "4.6",
-        "7.7459",
-        "3.435167",
-        "6.168",
-        "4.013044",
-        "-83.8",
-        "5.8"
-    ],
-    "TempCoverageBegin": 63461015999,
-    "TempCoverageEnd": 63461015999,
-    "TemporalCoverage": " point in time : 2012-01-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2012-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2012-01-01T11:59:59Z",
-    "author": [
-        "Philippe Clastre",
-        "Christian PICHOT"
-    ],
-    "fulltext": "08508ba3-5a7d-44eb-8dc0-06a5c92a9472;Philippe Clastre;INRA;Christian PICHOT;INRA;+33 4 32 72 29 66;+33 4 90 13 59 59;INRA - Domaine Saint-Paul - Site Agroparc;Avignon Cedex 9;84914;France;christian.pichot@avignon.inra.fr;2018-10-30T11:05:13;ISO 19115:2003/19139;1.0;WGS 84 (EPSG:4326);AnaEE-France services for experimentation on continental ecosytems;Services AnaEE-France pour l'exp\u00e9rimentation sur les ecosyst\u00e8mes continentaux;2018-10-20;http://w3.avignon.inra.fr/geonetwork_anaee/80894c9d-aa65-4808-8870-a04a7bf402f4;Jean-Fran\u00e7ois LE GALLIARD;CNRS;+33 1 64 28 35 33;+33 1 64 28 02 66;78, rue du Ch\u00e2teau;Saint-Pierre-L\u00e8s-Nemours;77140;France;cereep@biologie.ens.fr;Andr\u00e9 CHANZY;INRA;+33 4 32 72 22 11;+33 4 32 72 22 12;Domaine Saint Paul - Site Agroparc CS 40509;Avignon Cedex 9;84914;France;andre.chanzy@avignon.inra.fr;AnaEE France has brought together in an integrated network a unique collection of experimental platforms  in controlled, semi-natural or natural environments, analysis platforms and shared instruments as well as modeling platforms and Database Information Systems, all devoted to the biology of continental ecosystems.\nThe infrastructure is built around three main service offerings that provide access to a range of experimental facilities: the Tr\u00e8s Grande Infrastructure de Recherche des \u00c9cotrons - \u00c9cotrons Very Large Research Infrastructure, four experimental platforms in semi-natural environments, and some 20 natural sites in metropolitan France and French Guiana where long-term experiments are conducted in forests, pastures, lakes and crops. In the field of environmental microbiology, AnaEE France is also investing in the shared instruments and analytical resources required for a detailed characterization of the environment and microorganisms. \n\nIn a single integrated network it provides all the tools required to study, understand and model biological systems and conduct innovative biological research on gene - environment interactions, biodiversity and the functioning of ecosystems.;Experimentation on continental ecosystems;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng//resources.get?uuid=08508ba3-5a7d-44eb-8dc0-06a5c92a9472&fname=AnaEE_Nodes.png;large_thumbnail;png;Guyane;Guyane;Estrees-Mons;Estrees-Mons;Lusignan;Lusignan;Foljuif;Foljuif;Dijon;Dijon;Nancy;Nancy;Theix;Theix;Montpellier;Montpellier;Rennes;Rennes;Azerailles;Azerailles;Versailles;Versailles;Lac_Leman;Lac L\u00e9man;Font-Blanche;Font_Blanche;Fougeres;Fougeres;Laqueuille;Laqueuille;Hesse;Hesse;Lac_Peri_Alpins;Lacs_Peri_Alpins;Montiers;Montiers;Barbeau_Fontainebleau;Barbeau;O3HP;Theix-Laqueuille;Moulis;Moulis;Coffee-Flux;Puechabon;Puechabon;Paracou;Paracou;AnaEE-France Locations;2018-07-12;geonetwork.thesaurus.local.place.anaee-france_locations;Environmental monitoring facilities;Installations de suivi environnemental;GEMET - INSPIRE themes, version 1.0 INSPIRE themes;2008-06-01;geonetwork.thesaurus.external.theme.inspire-theme;mesocosm;m\u00e9socosme;long term experiment;exp\u00e9rimentation long terme;mobile laboratory;laboratoire mobile;ecotron;\u00e9cotron;analysis laboratory;Laboratoire d'analyse;theme.anaeeThes.rdf;2018-07-12;geonetwork.thesaurus.external.theme.anaeeThes;soil;sol;climate;climat;ecosystem management;gestion des \u00e9cosyst\u00e8mes;theme.drivers.rdf;2018-06-25;geonetwork.thesaurus.external.theme.drivers;biodiversity;biodiversit\u00e9;imaging;imagerie;air chemical property;propri\u00e9t\u00e9 chimique de l'air;meteorology;m\u00e9t\u00e9orologie;organic amendment;amendement organique;soil biology;biologie du sol;surface flux;flux de surface;soil chemistry;chimie du sol;water chemical property;propri\u00e9t\u00e9 chimique de l'eau;vegetation;v\u00e9g\u00e9tation;water biology;biologie de l'eau;soil physics;physique du sol;mulch;paillis;ecosystem management;gestion des \u00e9cosyst\u00e8mes;water physical property;propri\u00e9t\u00e9 physique de l'eau;theme.variableAnaee.rdf;2018-08-24;geonetwork.thesaurus.external.theme.variableAnaee;See AnaEE-France charters;5000;structure;2012-01-01;Dijon;4.94;5.14;47.22;47.42;Foljuif;2.58;2.78;48.16;48.36;Guyane;-54.6;-51.6;5.7;2.1;Lusignan;-1.97023;1.07023;45.250812;47.250812;Estrees-Mons;2.914269;4.014269;48.524083;50.524083;Montpellier;3.77;3.97;43.51;43.71;Moulis;0.99;1.19;42.86;43.06;Nancy;6.08;6.28;48.56;48.79;Rennes;-1.71026;-1.70489;48.11168;48.11363;Theix;2.010709;4.010709;44.432843;46.432843;Versailles;2.03;2.23;48.7;48.9;Azerailles;5.69;7.69;47.48;49.48;Barbeau_Fontainebleau;1.4649;3.4649;47.2835;48.2835;Font-Blanche;4.4045;6.4045;42.1427;44.1427;Fougeres;0.9;2.9;47.23;49.23;Hesse;6.0359;8.0359;47.403;49.403;Lac_Leman;5.9533;7.0387;46.1367;46.5349;Paracou;5;5.3;52.45;52.65;Puechabon;2.6;4.6;42.75;44.75;Lac_Peri_Alpins;5.5926;7.7459;43.8452;46.5207;Laqueuille;1.435167;3.435167;44.38432;46.38432;Montiers;4.168;6.168;47.3155;49.3155;Theix-Laqueuille;1.435167;4.013044;44.38432;46.431768;Coffee-Flux;-83.6;-83.8;9.8;10;O3HP;5.5;5.8;43.8;44;You can customize the template to suit your needs. You can add and remove fields and fill out default information (e.g. contact details). Fields you can not change in the default view may be accessible in the more comprehensive (and more complex) advanced view. You can even use the XML editor to create custom structures, but they have to be validated by the system, so know what you do :-);inapplicable;inapplicable;https://www.anaee-france.fr/en/about-us/introduction-to-anaee-france;WWW:LINK-1.0-http--link;AnaEE-France web site;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/home;WWW:LINK-1.0-http--link;AnaEE-France metadata catalogue;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/5934deaf-ee90-4338-b9a5-ecb6f200d0f3;WWW:LINK-1.0-http--link;Montpellier European Ecotron;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/80894c9d-aa65-4808-8870-a04a7bf402f4;WWW:LINK-1.0-http--link;Moulis Metatron;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/d16472fe-ca94-4e35-8dac-934eeced2ea4;WWW:LINK-1.0-http--link;Ecotron IleDeFrance;Ecotron IleDeFrance;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/84e7a32a-0ddd-47e8-a382-d65a7c90d5a4;WWW:LINK-1.0-http--link;SOERE OLA, Observatory on Alpine LAkes;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/cdf098e3-2ae7-4514-8957-ef3847a21ec2;WWW:LINK-1.0-http--link;Aquatic Experimental platform of Rennes and Le Rheu (PEARL);http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/546ed900-ded6-4770-be14-4e702b136309;WWW:LINK-1.0-http--link;PLANAQUA;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/a0248f18-bcdc-4bf0-93b3-7779f3797345;WWW:LINK-1.0-http--link;SOERE F-ORE-T : Hesse site;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/44a8ec47-5316-4f03-b3d4-e8247e909fcf;WWW:LINK-1.0-http--link;SOERE F-ORE-T : Font Blanche site;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/2149b09b-9ed6-492d-a346-1ce8e0e1f782;WWW:LINK-1.0-http--link;SOERE F-ORE-T : Barbeau site;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/356d6b7b-5b1b-4271-8350-d0c3acc32e64;WWW:LINK-1.0-http--link;SOERE F-ORE-T : Pu\u00e9chabon site;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/c32a4228-b3b7-4eda-b06c-97d0e59c0dfb;WWW:LINK-1.0-http--link;SOERE F-ORE-T : Azerailles/Clermont Site;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/9db01e1c-da42-4f6a-850e-81ae0b3c2a88;WWW:LINK-1.0-http--link;SOERE F-ORE-T : Rubberflux site (Thailand);http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/d90c4710-1d03-4438-ada8-c62ef24c79b6;WWW:LINK-1.0-http--link;SOERE F-ORE-T : Paracou Site (French Guiana);http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/177afe24-aa95-4f3e-a0f5-34e46ee42c55;WWW:LINK-1.0-http--link;SOERE F-ORE-T : Montiers site;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/50264564-795a-45e0-bc28-7ef8568b62fa;WWW:LINK-1.0-http--link;SOERE F-ORE-T : Breuil-Chenue Site;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/32c5ab4e-21b6-4308-8b98-7058c5793b0d;WWW:LINK-1.0-http--link;SOERE F-ORE-T : Xylosylve Pierroton site;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/d466e5e3-2ec0-47d9-b179-9bd088215ebb;WWW:LINK-1.0-http--link;SOERE F-ORE-T : Coffee-Flux site (Costa Rica);http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/4fbd2cb9-1a62-484b-8aa4-e2c94b8acf82;WWW:LINK-1.0-http--link;Itatinga;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/27aeb479-5c59-421a-bef7-cba6ab0a647d;WWW:LINK-1.0-http--link;SOERE PRO Reunion;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/0006eb99-b0d4-4754-857b-0f3c243d7f13;WWW:LINK-1.0-http--link;SOERE PRO Long term field experiment network for research on the recycling of organic residues in agriculture;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/c7179e1a-1316-49f2-a5f9-94ca06bf3259;WWW:LINK-1.0-http--link;SOERE PRO Site of QualiAgro;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/fdd9e7d7-ee67-4d3c-bc8c-5d6c389de3ad;WWW:LINK-1.0-http--link;Site EFELE of SOERE PRO;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/c8912811-b542-4bae-b4b2-3c62a2812866;WWW:LINK-1.0-http--link;SOERE PRO Site of Colmar;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/32367bcf-e2d5-4cf3-92bb-b1734fa670a2;WWW:LINK-1.0-http--link;System of Observation and Experimentation in Environmental Research (SOERE) for studying Agroecosystems, Biogeochemical Cycles and Biodiversity (ACBB);http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/f0dafd0b-3462-45b1-9062-538c2296d030;WWW:LINK-1.0-http--link;SOERE ACBB Estr\u00e9es-Mons Platform (Arable crops);http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/248a7f0c-cdbf-4002-b813-1384d3bba4b0;WWW:LINK-1.0-http--link;SOERE ACBB Lusignan Platform (Temporary Grassland);http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/3fe00c17-cae3-4ad9-9ab2-06412d30185c;WWW:LINK-1.0-http--link;SOERE ACBB Theix-Laqueuille Platform (Permanent Grassland);http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/08b1c286-760a-46fa-94f7-1c113c6e5aa4;WWW:LINK-1.0-http--link;Nouragues ecological research stations;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/49378f22-cf6e-4a22-8222-9800b8493309;WWW:LINK-1.0-http--link;Parar\u00e9 camp at the Nouragues station;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/82b98e1a-e136-4814-a938-9d571983361d;WWW:LINK-1.0-http--link;Inselberg camp at the Nouragues station;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/d1f43b85-a5ea-448e-8f48-91e23d287b84;WWW:LINK-1.0-http--link;Canopy Operating Permanent Acces System (COPAS);http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/ee19974d-36a4-4803-89a5-2637eb6d58d9;WWW:LINK-1.0-http--link;Station alpine Joseph Fourier (Lautaret);http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/d5d0cf74-4808-4e76-9537-d782b34b56f3;WWW:LINK-1.0-http--link;Greenhouse for Outreach education, plant nursery and alpine projects;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/937d57d9-b01e-4506-afd6-3e71c5bb5873;WWW:LINK-1.0-http--link;M-POETE (Mobile Platform for the Observation and the Experimentation in Terrestrial Ecosystems);http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/e0996c60-34c2-4f52-90e3-616474a4ebb5;WWW:LINK-1.0-http--link;Mobile Gas Laboratory;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/d3d29fb1-35a4-4f8b-adb8-26ed8d766f0f;WWW:LINK-1.0-http--link;Platform GenoSol : a logistical and technical tool for microbial diversity research;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/1570fce2-e646-42bb-ab5d-be3bd953f131;WWW:LINK-1.0-http--link;PTRMS;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/98d8e72e-edab-4d92-a410-c3364f437c05;WWW:LINK-1.0-http--link;BIOCHEMENV - The environmental biochemistry for Research;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/6c173c29-ec47-4324-bfb2-e1d6bc92566d;WWW:LINK-1.0-http--link;eDNA;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/bba59854-af70-4e6a-9482-e9bf1b0f3c6c;WWW:LINK-1.0-http--link;RMI for small animals;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/1ff61781-5c3b-4680-97e1-47ed1e8a6dff;WWW:LINK-1.0-http--link;Environmental and Human Genomic Platform (GEH);Commission Regulation (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;Not evaluated",
-    "group": "anaee",
-    "groups": [
-        {
-            "name": "anaee"
-        }
-    ],
-    "name": "30aef3e3-19f7-5f41-94ca-242a7d300d85",
-    "notes": [
-        "AnaEE France has brought together in an integrated network a unique collection of experimental platforms  in controlled, semi-natural or natural environments, analysis platforms and shared instruments as well as modeling platforms and Database Information Systems, all devoted to the biology of continental ecosystems.\nThe infrastructure is built around three main service offerings that provide access to a range of experimental facilities: the Tr\u00e8s Grande Infrastructure de Recherche des \u00c9cotrons - \u00c9cotrons Very Large Research Infrastructure, four experimental platforms in semi-natural environments, and some 20 natural sites in metropolitan France and French Guiana where long-term experiments are conducted in forests, pastures, lakes and crops. In the field of environmental microbiology, AnaEE France is also investing in the shared instruments and analytical resources required for a detailed characterization of the environment and microorganisms. \n\nIn a single integrated network it provides all the tools required to study, understand and model biological systems and conduct innovative biological research on gene - environment interactions, biodiversity and the functioning of ecosystems."
-    ],
-    "oai_identifier": [
-        "30aef3e3-19f7-5f41-94ca-242a7d300d85"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Guyane"
-        },
-        {
-            "name": "Estrees-Mons"
-        },
-        {
-            "name": "Lusignan"
-        },
-        {
-            "name": "Foljuif"
-        },
-        {
-            "name": "Dijon"
-        },
-        {
-            "name": "Nancy"
-        },
-        {
-            "name": "Theix"
-        },
-        {
-            "name": "Montpellier"
-        },
-        {
-            "name": "Rennes"
-        },
-        {
-            "name": "Azerailles"
-        },
-        {
-            "name": "Versailles"
-        },
-        {
-            "name": "Lac_Leman"
-        }
-    ],
-    "title": [
-        "AnaEE-France services for experimentation on continental ecosytems"
-    ],
-    "url": "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/1ff61781-5c3b-4680-97e1-47ed1e8a6dff"
-}
\ No newline at end of file
diff --git a/oaitestdata/anaee-iso19139/SET_1/json/b2f601cd-aa35-53e5-bba9-665c5349f40d.json b/oaitestdata/anaee-iso19139/SET_1/json/b2f601cd-aa35-53e5-bba9-665c5349f40d.json
deleted file mode 100644
index 5de68ff4..00000000
--- a/oaitestdata/anaee-iso19139/SET_1/json/b2f601cd-aa35-53e5-bba9-665c5349f40d.json
+++ /dev/null
@@ -1,99 +0,0 @@
-{
-    "Contact": [
-        "christian.pichot@avignon.inra.fr"
-    ],
-    "Contributor": [
-        "AnaEE"
-    ],
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Format": [
-        "inapplicable"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://w3.avignon.inra.fr/geonetwork_anaee/srv/fre/csw-envriplus?verb=GetRecord&metadataPrefix=iso19139&identifier=b2f601cd-aa35-53e5-bba9-665c5349f40d",
-    "PublicationTimestamp": "2018-10-20T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "INRA"
-    ],
-    "ResourceType": "dataset",
-    "Rights": [
-        "See AnaEE-France charters"
-    ],
-    "TempCoverageBegin": 63461015999,
-    "TempCoverageEnd": 63461015999,
-    "TemporalCoverage": " point in time : 2012-01-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2012-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2012-01-01T11:59:59Z",
-    "author": [
-        "Philippe Clastre",
-        "Christian PICHOT"
-    ],
-    "fulltext": "ec151f7d-fa3f-49b2-8603-0eda7589a3a4;Philippe Clastre;INRA;Christian PICHOT;INRA;+33 4 32 72 29 66;+33 4 90 13 59 59;INRA - Domaine Saint-Paul - Site Agroparc;Avignon Cedex 9;84914;France;christian.pichot@avignon.inra.fr;2018-10-30T11:07:05;ISO 19115:2003/19139;1.0;WGS 84 (EPSG:4326);Projects of experimentation on ecosystems using the AnaEE services;Projets d'experimentation sur les \u00e9cosyst\u00e8mes utilisant les services de AnaEE-France;2018-10-20;http://w3.avignon.inra.fr/geonetwork_anaee/80894c9d-aa65-4808-8870-a04a7bf402f4;Jean-Fran\u00e7ois LE GALLIARD;CNRS;+33 1 64 28 35 33;+33 1 64 28 02 66;78, rue du Ch\u00e2teau;Saint-Pierre-L\u00e8s-Nemours;77140;France;cereep@biologie.ens.fr;Andr\u00e9 CHANZY;INRA;+33 4 32 72 22 11;+33 4 32 72 22 12;Domaine Saint Paul - Site Agroparc CS 40509;Avignon Cedex 9;84914;France;andre.chanzy@avignon.inra.fr;AnaEE-France is the French national infrastructure devoted to the study of continental ecosystems and their biodiversity. It offers experimental facilities in controlled, semi-natural or natural environments, analysis platforms and shared instruments as well as modeling platforms and database Information Systems.\n\nThe research project that use the AnaEE-F experimental facilities will be described by general metadata (description of the experiment, type of ecosystem, studied variables, manipulated factors);Experimentation on continental ecosystems;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng//resources.get?uuid=ec151f7d-fa3f-49b2-8603-0eda7589a3a4&fname=AnaEE4projects.png;large_thumbnail;png;AnaEE-France Locations;2018-07-12;geonetwork.thesaurus.local.place.anaee-france_locations;Environmental monitoring facilities;Installations de suivi environnemental;GEMET - INSPIRE themes, version 1.0 INSPIRE themes;2008-06-01;geonetwork.thesaurus.external.theme.inspire-theme;ecosystem;\u00e9cosyst\u00e8me;experimentation;exp\u00e9rimentation;Manipulated experimental factors;facteurs exp\u00e9rimentaux manipul\u00e9s;forest ecosystem;\u00e9cosyst\u00e8me forestier;cropping system;freshwater lakes;lac d'eau douce;grassland;prairie;experimental ecology;ecologie exp\u00e9rimentale;theme.anaeeThes.rdf;2018-07-12;geonetwork.thesaurus.external.theme.anaeeThes;soil;sol;climate;climat;ecosystem management;gestion des \u00e9cosyst\u00e8mes;theme.drivers.rdf;2018-06-25;geonetwork.thesaurus.external.theme.drivers;biodiversity;biodiversit\u00e9;imaging;imagerie;air chemical property;propri\u00e9t\u00e9 chimique de l'air;meteorology;m\u00e9t\u00e9orologie;soil biology;biologie du sol;organic amendment;amendement organique;surface flux;flux de surface;soil chemistry;chimie du sol;water chemical property;propri\u00e9t\u00e9 chimique de l'eau;water biology;biologie de l'eau;vegetation;v\u00e9g\u00e9tation;mulch;paillis;soil physics;physique du sol;ecosystem management;gestion des \u00e9cosyst\u00e8mes;water physical property;propri\u00e9t\u00e9 physique de l'eau;theme.variableAnaee.rdf;2018-08-24;geonetwork.thesaurus.external.theme.variableAnaee;See AnaEE-France charters;5000;structure;2012-01-01;You can customize the template to suit your needs. You can add and remove fields and fill out default information (e.g. contact details). Fields you can not change in the default view may be accessible in the more comprehensive (and more complex) advanced view. You can even use the XML editor to create custom structures, but they have to be validated by the system, so know what you do :-);inapplicable;inapplicable;https://www.anaee-france.fr/en/about-us/introduction-to-anaee-france;WWW:LINK-1.0-http--link;AnaEE-France web site;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/home;WWW:LINK-1.0-http--link;AnaEE-France metadata catalogue;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/08508ba3-5a7d-44eb-8dc0-06a5c92a9472;WWW:LINK-1.0-http--link;AnaEE-France services for experimentation on continental ecosytems;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/20b9aa10-5aa5-48e3-bb61-e5a5746796ae;WWW:LINK-1.0-http--link;AnaEE-France modeling platforms and data management services;Commission Regulation (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;Not evaluated",
-    "group": "anaee",
-    "groups": [
-        {
-            "name": "anaee"
-        }
-    ],
-    "name": "b2f601cd-aa35-53e5-bba9-665c5349f40d",
-    "notes": [
-        "AnaEE-France is the French national infrastructure devoted to the study of continental ecosystems and their biodiversity. It offers experimental facilities in controlled, semi-natural or natural environments, analysis platforms and shared instruments as well as modeling platforms and database Information Systems.\n\nThe research project that use the AnaEE-F experimental facilities will be described by general metadata (description of the experiment, type of ecosystem, studied variables, manipulated factors)"
-    ],
-    "oai_identifier": [
-        "b2f601cd-aa35-53e5-bba9-665c5349f40d"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Environmental monitoring facilities"
-        },
-        {
-            "name": "ecosystem"
-        },
-        {
-            "name": "experimentation"
-        },
-        {
-            "name": "Manipulated experimental factors"
-        },
-        {
-            "name": "forest ecosystem"
-        },
-        {
-            "name": "cropping system"
-        },
-        {
-            "name": "freshwater lakes"
-        },
-        {
-            "name": "grassland"
-        },
-        {
-            "name": "experimental ecology"
-        },
-        {
-            "name": "soil"
-        },
-        {
-            "name": "climate"
-        },
-        {
-            "name": "ecosystem management"
-        }
-    ],
-    "title": [
-        "Projects of experimentation on ecosystems using the AnaEE services"
-    ],
-    "url": "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/20b9aa10-5aa5-48e3-bb61-e5a5746796ae"
-}
\ No newline at end of file
diff --git a/oaitestdata/anaee-iso19139/SET_1/json/bfab9352-d1fe-5e7b-8c7d-3c71eb743904.json b/oaitestdata/anaee-iso19139/SET_1/json/bfab9352-d1fe-5e7b-8c7d-3c71eb743904.json
deleted file mode 100644
index 3fbbc51f..00000000
--- a/oaitestdata/anaee-iso19139/SET_1/json/bfab9352-d1fe-5e7b-8c7d-3c71eb743904.json
+++ /dev/null
@@ -1,99 +0,0 @@
-{
-    "Contact": [
-        "christian.pichot@avignon.inra.fr"
-    ],
-    "Contributor": [
-        "AnaEE"
-    ],
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Format": [
-        "inapplicable"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://w3.avignon.inra.fr/geonetwork_anaee/srv/fre/csw-envriplus?verb=GetRecord&metadataPrefix=iso19139&identifier=bfab9352-d1fe-5e7b-8c7d-3c71eb743904",
-    "PublicationTimestamp": "2018-10-20T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "INRA"
-    ],
-    "ResourceType": "dataset",
-    "Rights": [
-        "See AnaEE-France charters"
-    ],
-    "TempCoverageBegin": 63461015999,
-    "TempCoverageEnd": 63461015999,
-    "TemporalCoverage": " point in time : 2012-01-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2012-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2012-01-01T11:59:59Z",
-    "author": [
-        "Philippe Clastre",
-        "Christian PICHOT"
-    ],
-    "fulltext": "dd9d31f9-b647-420f-9945-2f4942366534;Philippe Clastre;INRA;Christian PICHOT;INRA;+33 4 32 72 29 66;+33 4 90 13 59 59;INRA - Domaine Saint-Paul - Site Agroparc;Avignon Cedex 9;84914;France;christian.pichot@avignon.inra.fr;2018-10-30T11:06:23;ISO 19115:2003/19139;1.0;WGS 84 (EPSG:4326);Datasets from experimentations using the AnaEE services;Jeux de donn\u00e9es provenant des experimentations r\u00e9alis\u00e9es par les services de AnaEE-France;2018-10-20;http://w3.avignon.inra.fr/geonetwork_anaee/80894c9d-aa65-4808-8870-a04a7bf402f4;Jean-Fran\u00e7ois LE GALLIARD;CNRS;+33 1 64 28 35 33;+33 1 64 28 02 66;78, rue du Ch\u00e2teau;Saint-Pierre-L\u00e8s-Nemours;77140;France;cereep@biologie.ens.fr;Andr\u00e9 CHANZY;INRA;+33 4 32 72 22 11;+33 4 32 72 22 12;Domaine Saint Paul - Site Agroparc CS 40509;Avignon Cedex 9;84914;France;andre.chanzy@avignon.inra.fr;AnaEE-France is the French national infrastructure devoted to the study of continental ecosystems and their biodiversity. It offers experimental facilities in controlled, semi-natural or natural environments, analysis platforms and shared instruments as well as modeling platforms and database Information Systems.\n\nThe data generated from the AnaEE-F services are mostly produced by the platforms and, in some cases, by the user of the services. Data produced by the platforms are either core data characterizing the environment of the site (weather, soil ...) or experience-specific data collected by the platform on behalf of the user (measurement of gas in a enclosed platform cell, temperature of a basin ...).\nData are stored in dedicated database IS. According to a FAIR OpenData policy, datasets become accessible at the end of the project and when completed.;Experimentation on continental ecosystems;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng//resources.get?uuid=20b9aa10-5aa5-48e3-bb61-e5a5746796ae&fname=AnaEE_node5.png;large_thumbnail;png;AnaEE-France Locations;2018-07-12;geonetwork.thesaurus.local.place.anaee-france_locations;Environmental monitoring facilities;Installations de suivi environnemental;GEMET - INSPIRE themes, version 1.0 INSPIRE themes;2008-06-01;geonetwork.thesaurus.external.theme.inspire-theme;experimentation;exp\u00e9rimentation;ecosystem;\u00e9cosyst\u00e8me;Manipulated experimental factors;facteurs exp\u00e9rimentaux manipul\u00e9s;forest ecosystem;\u00e9cosyst\u00e8me forestier;cropping system;grassland;prairie;experimental ecology;ecologie exp\u00e9rimentale;freshwater lakes;lac d'eau douce;theme.anaeeThes.rdf;2018-07-12;geonetwork.thesaurus.external.theme.anaeeThes;climate;climat;soil;sol;ecosystem management;gestion des \u00e9cosyst\u00e8mes;theme.drivers.rdf;2018-06-25;geonetwork.thesaurus.external.theme.drivers;biodiversity;biodiversit\u00e9;air chemical property;propri\u00e9t\u00e9 chimique de l'air;imaging;imagerie;meteorology;m\u00e9t\u00e9orologie;soil biology;biologie du sol;organic amendment;amendement organique;surface flux;flux de surface;water chemical property;propri\u00e9t\u00e9 chimique de l'eau;soil chemistry;chimie du sol;vegetation;v\u00e9g\u00e9tation;water biology;biologie de l'eau;soil physics;physique du sol;ecosystem management;gestion des \u00e9cosyst\u00e8mes;mulch;paillis;water physical property;propri\u00e9t\u00e9 physique de l'eau;theme.variableAnaee.rdf;2018-08-24;geonetwork.thesaurus.external.theme.variableAnaee;See AnaEE-France charters;5000;structure;2012-01-01;You can customize the template to suit your needs. You can add and remove fields and fill out default information (e.g. contact details). Fields you can not change in the default view may be accessible in the more comprehensive (and more complex) advanced view. You can even use the XML editor to create custom structures, but they have to be validated by the system, so know what you do :-);inapplicable;inapplicable;https://www.anaee-france.fr/en/about-us/introduction-to-anaee-france;WWW:LINK-1.0-http--link;AnaEE-France web site;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/home;WWW:LINK-1.0-http--link;AnaEE-France metadata catalogue;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/20b9aa10-5aa5-48e3-bb61-e5a5746796ae;WWW:LINK-1.0-http--link;AnaEE-France modeling platforms and data management services;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/d7d7f3bb-86dc-4c10-9661-dfa293c73862;WWW:LINK-1.0-http--link;SOERE OLA : Data from the Observatory on LAkes for Lake Geneva;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/09d4c15b-fd36-482f-aae1-68fe1570dedf;WWW:LINK-1.0-http--link;SOERE OLA : Data from the Observatory on LAkes for Annecy Lake;Commission Regulation (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;Not evaluated",
-    "group": "anaee",
-    "groups": [
-        {
-            "name": "anaee"
-        }
-    ],
-    "name": "bfab9352-d1fe-5e7b-8c7d-3c71eb743904",
-    "notes": [
-        "AnaEE-France is the French national infrastructure devoted to the study of continental ecosystems and their biodiversity. It offers experimental facilities in controlled, semi-natural or natural environments, analysis platforms and shared instruments as well as modeling platforms and database Information Systems.\n\nThe data generated from the AnaEE-F services are mostly produced by the platforms and, in some cases, by the user of the services. Data produced by the platforms are either core data characterizing the environment of the site (weather, soil ...) or experience-specific data collected by the platform on behalf of the user (measurement of gas in a enclosed platform cell, temperature of a basin ...).\nData are stored in dedicated database IS. According to a FAIR OpenData policy, datasets become accessible at the end of the project and when completed."
-    ],
-    "oai_identifier": [
-        "bfab9352-d1fe-5e7b-8c7d-3c71eb743904"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Environmental monitoring facilities"
-        },
-        {
-            "name": "experimentation"
-        },
-        {
-            "name": "ecosystem"
-        },
-        {
-            "name": "Manipulated experimental factors"
-        },
-        {
-            "name": "forest ecosystem"
-        },
-        {
-            "name": "cropping system"
-        },
-        {
-            "name": "grassland"
-        },
-        {
-            "name": "experimental ecology"
-        },
-        {
-            "name": "freshwater lakes"
-        },
-        {
-            "name": "climate"
-        },
-        {
-            "name": "soil"
-        },
-        {
-            "name": "ecosystem management"
-        }
-    ],
-    "title": [
-        "Datasets from experimentations using the AnaEE services"
-    ],
-    "url": "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/09d4c15b-fd36-482f-aae1-68fe1570dedf"
-}
\ No newline at end of file
diff --git a/oaitestdata/anaee-oai_dc/SET_1/json/28e634ad-e4f4-5b54-a635-90c0c92d0692.json b/oaitestdata/anaee-oai_dc/SET_1/json/28e634ad-e4f4-5b54-a635-90c0c92d0692.json
deleted file mode 100644
index b1b2f617..00000000
--- a/oaitestdata/anaee-oai_dc/SET_1/json/28e634ad-e4f4-5b54-a635-90c0c92d0692.json
+++ /dev/null
@@ -1,101 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "inapplicable"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://w3.avignon.inra.fr/geonetwork_anaee/srv/fre/csw-envriplus?verb=GetRecord&metadataPrefix=oai_dc&identifier=28e634ad-e4f4-5b54-a635-90c0c92d0692",
-    "PublicationTimestamp": "2018-10-27T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "AnaEE"
-    ],
-    "RelatedIdentifier": [
-        "https://www.anaee-france.fr/en/about-us/introduction-to-anaee-france",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/home",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/864d43f1-fbba-4652-896d-61950f3d3a22",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/ee520bf5-f86b-4064-97ce-8fb308d17efb",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/59c9d6ec-057c-4ebf-b69f-35286784b9d2",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/fd85ef74-988e-44c7-bb1b-c3655e6e5137",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/c106e898-b8a4-4679-8e2b-eb8fc04e8337",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng//resources.get?uuid=20b9aa10-5aa5-48e3-bb61-e5a5746796ae&fname=AnaEE_node5.png"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "intellectualPropertyRights",
-        "intellectualPropertyRights"
-    ],
-    "SpatialCoverage": [
-        "9.5 41.3",
-        "-5.7 51"
-    ],
-    "fulltext": "20b9aa10-5aa5-48e3-bb61-e5a5746796ae;2018-10-27T08:49:34;Plateforme de mod\u00e9lisation et services de gestion des donn\u00e9es de AnaEE-France;dataset;France;Installations de suivi environnemental;plateforme de mod\u00e9lisation;base de donn\u00e9es;syst\u00e8me d'information;biodiversit\u00e9;imagerie;propri\u00e9t\u00e9 chimique de l'air;m\u00e9t\u00e9orologie;amendement organique;biologie du sol;flux de surface;chimie du sol;propri\u00e9t\u00e9 chimique de l'eau;v\u00e9g\u00e9tation;biologie de l'eau;physique du sol;paillis;gestion des \u00e9cosyst\u00e8mes;propri\u00e9t\u00e9 physique de l'eau;structure;inapplicable;AnaEE-France is the French national infrastructure devoted to the study of continental ecosystems and their biodiversity. It offers experimental facilities in controlled, semi-natural or natural environments, analysis platforms and shared instruments as well as modeling platforms and database Information Systems.\nModeling platforms are facilities specialized in developing models to support the projects run by AnaEE.  They streamline model development by providing the necessary hardware and software, as well as the access to expertise, datasets and modelling libraries. Two types of platforms are or will be provided: i) model factories which are nationally supported software platforms with advanced and well-established facilities providing users access to general and extensible modeling resources and ii) Modeling solution platforms which are implemented as self-contained software solutions that model specific aspects of ecosystem function and are centered on a well-established and supported model development team with a strong community of users.\nBoth types are used to exploit mathematical models to test and develop our understanding of the complex quantitative relationships between processes within ecosystems, the interactions with their environments, and their functioning and behaviour under various pressures.\n\nDatabase Information systems have been developed for the management of the data produced by the AnaEE-F experimental facilities. These IS rely on two main architectural models : databases for long term experiments (in natura) and databases for short to middle term experiments (mostly in ecotrons and mesocosms)\n\nBased on a distributed architecture, the overall AnaEE-F IS develops a semantic interoperability of modeling platforms and database IS and provides portals for the discovery and the exploitation of these resources.;AnaEE-France is the French national infrastructure devoted to the study of continental ecosystems and their biodiversity. It offers experimental facilities in controlled, semi-natural or natural environments, analysis platforms and shared instruments as well as modeling platforms and database Information Systems.\nModeling platforms are facilities specialized in developing models to support the projects run by AnaEE.  They streamline model development by providing the necessary hardware and software, as well as the access to expertise, datasets and modelling libraries. Two types of platforms are or will be provided: i) model factories which are nationally supported software platforms with advanced and well-established facilities providing users access to general and extensible modeling resources and ii) Modeling solution platforms which are implemented as self-contained software solutions that model specific aspects of ecosystem function and are centered on a well-established and supported model development team with a strong community of users.\nBoth types are used to exploit mathematical models to test and develop our understanding of the complex quantitative relationships between processes within ecosystems, the interactions with their environments, and their functioning and behaviour under various pressures.\n\nDatabase Information systems have been developed for the management of the data produced by the AnaEE-F experimental facilities. These IS rely on two main architectural models : databases for long term experiments (in natura) and databases for short to middle term experiments (mostly in ecotrons and mesocosms)\n\nBased on a distributed architecture, the overall AnaEE-F IS develops a semantic interoperability of modeling platforms and database IS and provides portals for the discovery and the exploitation of these resources.;intellectualPropertyRights;intellectualPropertyRights;eng;inapplicable;9.5 41.3;-5.7 51;https://www.anaee-france.fr/en/about-us/introduction-to-anaee-france;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/home;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/864d43f1-fbba-4652-896d-61950f3d3a22;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/ee520bf5-f86b-4064-97ce-8fb308d17efb;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/59c9d6ec-057c-4ebf-b69f-35286784b9d2;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/fd85ef74-988e-44c7-bb1b-c3655e6e5137;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/c106e898-b8a4-4679-8e2b-eb8fc04e8337;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng//resources.get?uuid=20b9aa10-5aa5-48e3-bb61-e5a5746796ae&fname=AnaEE_node5.png",
-    "group": "anaee",
-    "groups": [
-        {
-            "name": "anaee"
-        }
-    ],
-    "name": "28e634ad-e4f4-5b54-a635-90c0c92d0692",
-    "notes": [
-        "AnaEE-France is the French national infrastructure devoted to the study of continental ecosystems and their biodiversity. It offers experimental facilities in controlled, semi-natural or natural environments, analysis platforms and shared instruments as well as modeling platforms and database Information Systems.\nModeling platforms are facilities specialized in developing models to support the projects run by AnaEE.  They streamline model development by providing the necessary hardware and software, as well as the access to expertise, datasets and modelling libraries. Two types of platforms are or will be provided: i) model factories which are nationally supported software platforms with advanced and well-established facilities providing users access to general and extensible modeling resources and ii) Modeling solution platforms which are implemented as self-contained software solutions that model specific aspects of ecosystem function and are centered on a well-established and supported model development team with a strong community of users.\nBoth types are used to exploit mathematical models to test and develop our understanding of the complex quantitative relationships between processes within ecosystems, the interactions with their environments, and their functioning and behaviour under various pressures.\n\nDatabase Information systems have been developed for the management of the data produced by the AnaEE-F experimental facilities. These IS rely on two main architectural models : databases for long term experiments (in natura) and databases for short to middle term experiments (mostly in ecotrons and mesocosms)\n\nBased on a distributed architecture, the overall AnaEE-F IS develops a semantic interoperability of modeling platforms and database IS and provides portals for the discovery and the exploitation of these resources."
-    ],
-    "oai_identifier": [
-        "28e634ad-e4f4-5b54-a635-90c0c92d0692"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "France"
-        },
-        {
-            "name": "Installations de suivi environnemental"
-        },
-        {
-            "name": "Installations de suivi environnemental"
-        },
-        {
-            "name": "Installations de suivi environnemental"
-        },
-        {
-            "name": "Installations de suivi environnemental"
-        },
-        {
-            "name": "Installations de suivi environnemental"
-        },
-        {
-            "name": "imagerie"
-        },
-        {
-            "name": "imagerie"
-        },
-        {
-            "name": "imagerie"
-        },
-        {
-            "name": "amendement organique"
-        },
-        {
-            "name": "biologie du sol"
-        },
-        {
-            "name": "flux de surface"
-        }
-    ],
-    "title": [
-        "Plateforme de mod\u00e9lisation et services de gestion des donn\u00e9es de AnaEE-France"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/anaee-oai_dc/SET_1/json/30aef3e3-19f7-5f41-94ca-242a7d300d85.json b/oaitestdata/anaee-oai_dc/SET_1/json/30aef3e3-19f7-5f41-94ca-242a7d300d85.json
deleted file mode 100644
index be1eff6d..00000000
--- a/oaitestdata/anaee-oai_dc/SET_1/json/30aef3e3-19f7-5f41-94ca-242a7d300d85.json
+++ /dev/null
@@ -1,185 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "inapplicable"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://w3.avignon.inra.fr/geonetwork_anaee/srv/fre/csw-envriplus?verb=GetRecord&metadataPrefix=oai_dc&identifier=30aef3e3-19f7-5f41-94ca-242a7d300d85",
-    "PublicationTimestamp": "2018-10-27T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "AnaEE"
-    ],
-    "RelatedIdentifier": [
-        "https://www.anaee-france.fr/en/about-us/introduction-to-anaee-france",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/home",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/5934deaf-ee90-4338-b9a5-ecb6f200d0f3",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/80894c9d-aa65-4808-8870-a04a7bf402f4",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/d16472fe-ca94-4e35-8dac-934eeced2ea4",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/84e7a32a-0ddd-47e8-a382-d65a7c90d5a4",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/cdf098e3-2ae7-4514-8957-ef3847a21ec2",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/546ed900-ded6-4770-be14-4e702b136309",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/a0248f18-bcdc-4bf0-93b3-7779f3797345",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/44a8ec47-5316-4f03-b3d4-e8247e909fcf",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/2149b09b-9ed6-492d-a346-1ce8e0e1f782",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/356d6b7b-5b1b-4271-8350-d0c3acc32e64",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/c32a4228-b3b7-4eda-b06c-97d0e59c0dfb",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/9db01e1c-da42-4f6a-850e-81ae0b3c2a88",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/d90c4710-1d03-4438-ada8-c62ef24c79b6",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/177afe24-aa95-4f3e-a0f5-34e46ee42c55",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/50264564-795a-45e0-bc28-7ef8568b62fa",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/32c5ab4e-21b6-4308-8b98-7058c5793b0d",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/d466e5e3-2ec0-47d9-b179-9bd088215ebb",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/4fbd2cb9-1a62-484b-8aa4-e2c94b8acf82",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/27aeb479-5c59-421a-bef7-cba6ab0a647d",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/0006eb99-b0d4-4754-857b-0f3c243d7f13",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/c7179e1a-1316-49f2-a5f9-94ca06bf3259",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/fdd9e7d7-ee67-4d3c-bc8c-5d6c389de3ad",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/c8912811-b542-4bae-b4b2-3c62a2812866",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/32367bcf-e2d5-4cf3-92bb-b1734fa670a2",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/f0dafd0b-3462-45b1-9062-538c2296d030",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/248a7f0c-cdbf-4002-b813-1384d3bba4b0",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/3fe00c17-cae3-4ad9-9ab2-06412d30185c",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/08b1c286-760a-46fa-94f7-1c113c6e5aa4",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/49378f22-cf6e-4a22-8222-9800b8493309",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/82b98e1a-e136-4814-a938-9d571983361d",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/d1f43b85-a5ea-448e-8f48-91e23d287b84",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/ee19974d-36a4-4803-89a5-2637eb6d58d9",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/d5d0cf74-4808-4e76-9537-d782b34b56f3",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/937d57d9-b01e-4506-afd6-3e71c5bb5873",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/e0996c60-34c2-4f52-90e3-616474a4ebb5",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/d3d29fb1-35a4-4f8b-adb8-26ed8d766f0f",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/1570fce2-e646-42bb-ab5d-be3bd953f131",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/98d8e72e-edab-4d92-a410-c3364f437c05",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/6c173c29-ec47-4324-bfb2-e1d6bc92566d",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/bba59854-af70-4e6a-9482-e9bf1b0f3c6c",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/1ff61781-5c3b-4680-97e1-47ed1e8a6dff",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng//resources.get?uuid=08508ba3-5a7d-44eb-8dc0-06a5c92a9472&fname=AnaEE_Nodes.png"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "intellectualPropertyRights",
-        "intellectualPropertyRights"
-    ],
-    "SpatialCoverage": [
-        "5.14 47.22",
-        "2.78 48.16",
-        "-51.6 5.7",
-        "1.07023 45.250812",
-        "4.014269 48.524083",
-        "3.97 43.51",
-        "1.19 42.86",
-        "6.28 48.56",
-        "-1.70489 48.11168",
-        "4.010709 44.432843",
-        "2.23 48.7",
-        "7.69 47.48",
-        "3.4649 47.2835",
-        "6.4045 42.1427",
-        "2.9 47.23",
-        "8.0359 47.403",
-        "7.0387 46.1367",
-        "5.3 52.45",
-        "4.6 42.75",
-        "7.7459 43.8452",
-        "3.435167 44.38432",
-        "6.168 47.3155",
-        "4.013044 44.38432",
-        "-83.8 9.8",
-        "5.8 43.8",
-        "4.94 47.42",
-        "2.58 48.36",
-        "-54.6 2.1",
-        "-1.97023 47.250812",
-        "2.914269 50.524083",
-        "3.77 43.71",
-        "0.99 43.06",
-        "6.08 48.79",
-        "-1.71026 48.11363",
-        "2.010709 46.432843",
-        "2.03 48.9",
-        "5.69 49.48",
-        "1.4649 48.2835",
-        "4.4045 44.1427",
-        "0.9 49.23",
-        "6.0359 49.403",
-        "5.9533 46.5349",
-        "5 52.65",
-        "2.6 44.75",
-        "5.5926 46.5207",
-        "1.435167 46.38432",
-        "4.168 49.3155",
-        "1.435167 46.431768",
-        "-83.6 10",
-        "5.5 44"
-    ],
-    "fulltext": "08508ba3-5a7d-44eb-8dc0-06a5c92a9472;2018-10-27T08:44:34;Services AnaEE-France pour l'exp\u00e9rimentation sur les ecosyst\u00e8mes continentaux;dataset;Guyane;Estrees-Mons;Lusignan;Foljuif;Dijon;Nancy;Theix;Montpellier;Rennes;Azerailles;Versailles;Lac L\u00e9man;Font_Blanche;Fougeres;Laqueuille;Hesse;Lacs_Peri_Alpins;Montiers;Barbeau;O3HP;Theix-Laqueuille;Moulis;Coffee-Flux;Puechabon;Paracou;Installations de suivi environnemental;m\u00e9socosme;exp\u00e9rimentation long terme;laboratoire mobile;\u00e9cotron;Laboratoire d'analyse;sol;climat;gestion des \u00e9cosyst\u00e8mes;biodiversit\u00e9;imagerie;propri\u00e9t\u00e9 chimique de l'air;m\u00e9t\u00e9orologie;amendement organique;biologie du sol;flux de surface;chimie du sol;propri\u00e9t\u00e9 chimique de l'eau;v\u00e9g\u00e9tation;biologie de l'eau;physique du sol;paillis;gestion des \u00e9cosyst\u00e8mes;propri\u00e9t\u00e9 physique de l'eau;structure;inapplicable;AnaEE France has brought together in an integrated network a unique collection of experimental platforms  in controlled, semi-natural or natural environments, analysis platforms and shared instruments as well as modeling platforms and Database Information Systems, all devoted to the biology of continental ecosystems.\nThe infrastructure is built around three main service offerings that provide access to a range of experimental facilities: the Tr\u00e8s Grande Infrastructure de Recherche des \u00c9cotrons - \u00c9cotrons Very Large Research Infrastructure, four experimental platforms in semi-natural environments, and some 20 natural sites in metropolitan France and French Guiana where long-term experiments are conducted in forests, pastures, lakes and crops. In the field of environmental microbiology, AnaEE France is also investing in the shared instruments and analytical resources required for a detailed characterization of the environment and microorganisms. \n\nIn a single integrated network it provides all the tools required to study, understand and model biological systems and conduct innovative biological research on gene - environment interactions, biodiversity and the functioning of ecosystems.;AnaEE France has brought together in an integrated network a unique collection of experimental platforms  in controlled, semi-natural or natural environments, analysis platforms and shared instruments as well as modeling platforms and Database Information Systems, all devoted to the biology of continental ecosystems.\nThe infrastructure is built around three main service offerings that provide access to a range of experimental facilities: the Tr\u00e8s Grande Infrastructure de Recherche des \u00c9cotrons - \u00c9cotrons Very Large Research Infrastructure, four experimental platforms in semi-natural environments, and some 20 natural sites in metropolitan France and French Guiana where long-term experiments are conducted in forests, pastures, lakes and crops. In the field of environmental microbiology, AnaEE France is also investing in the shared instruments and analytical resources required for a detailed characterization of the environment and microorganisms. \n\nIn a single integrated network it provides all the tools required to study, understand and model biological systems and conduct innovative biological research on gene - environment interactions, biodiversity and the functioning of ecosystems.;intellectualPropertyRights;intellectualPropertyRights;eng;inapplicable;5.14 47.22;4.94 47.42;2.78 48.16;2.58 48.36;-51.6 5.7;-54.6 2.1;1.07023 45.250812;-1.97023 47.250812;4.014269 48.524083;2.914269 50.524083;3.97 43.51;3.77 43.71;1.19 42.86;0.99 43.06;6.28 48.56;6.08 48.79;-1.70489 48.11168;-1.71026 48.11363;4.010709 44.432843;2.010709 46.432843;2.23 48.7;2.03 48.9;7.69 47.48;5.69 49.48;3.4649 47.2835;1.4649 48.2835;6.4045 42.1427;4.4045 44.1427;2.9 47.23;0.9 49.23;8.0359 47.403;6.0359 49.403;7.0387 46.1367;5.9533 46.5349;5.3 52.45;5 52.65;4.6 42.75;2.6 44.75;7.7459 43.8452;5.5926 46.5207;3.435167 44.38432;1.435167 46.38432;6.168 47.3155;4.168 49.3155;4.013044 44.38432;1.435167 46.431768;-83.8 9.8;-83.6 10;5.8 43.8;5.5 44;https://www.anaee-france.fr/en/about-us/introduction-to-anaee-france;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/home;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/5934deaf-ee90-4338-b9a5-ecb6f200d0f3;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/80894c9d-aa65-4808-8870-a04a7bf402f4;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/d16472fe-ca94-4e35-8dac-934eeced2ea4;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/84e7a32a-0ddd-47e8-a382-d65a7c90d5a4;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/cdf098e3-2ae7-4514-8957-ef3847a21ec2;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/546ed900-ded6-4770-be14-4e702b136309;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/a0248f18-bcdc-4bf0-93b3-7779f3797345;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/44a8ec47-5316-4f03-b3d4-e8247e909fcf;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/2149b09b-9ed6-492d-a346-1ce8e0e1f782;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/356d6b7b-5b1b-4271-8350-d0c3acc32e64;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/c32a4228-b3b7-4eda-b06c-97d0e59c0dfb;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/9db01e1c-da42-4f6a-850e-81ae0b3c2a88;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/d90c4710-1d03-4438-ada8-c62ef24c79b6;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/177afe24-aa95-4f3e-a0f5-34e46ee42c55;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/50264564-795a-45e0-bc28-7ef8568b62fa;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/32c5ab4e-21b6-4308-8b98-7058c5793b0d;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/d466e5e3-2ec0-47d9-b179-9bd088215ebb;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/4fbd2cb9-1a62-484b-8aa4-e2c94b8acf82;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/27aeb479-5c59-421a-bef7-cba6ab0a647d;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/0006eb99-b0d4-4754-857b-0f3c243d7f13;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/c7179e1a-1316-49f2-a5f9-94ca06bf3259;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/fdd9e7d7-ee67-4d3c-bc8c-5d6c389de3ad;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/c8912811-b542-4bae-b4b2-3c62a2812866;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/32367bcf-e2d5-4cf3-92bb-b1734fa670a2;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/f0dafd0b-3462-45b1-9062-538c2296d030;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/248a7f0c-cdbf-4002-b813-1384d3bba4b0;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/3fe00c17-cae3-4ad9-9ab2-06412d30185c;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/08b1c286-760a-46fa-94f7-1c113c6e5aa4;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/49378f22-cf6e-4a22-8222-9800b8493309;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/82b98e1a-e136-4814-a938-9d571983361d;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/d1f43b85-a5ea-448e-8f48-91e23d287b84;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/ee19974d-36a4-4803-89a5-2637eb6d58d9;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/d5d0cf74-4808-4e76-9537-d782b34b56f3;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/937d57d9-b01e-4506-afd6-3e71c5bb5873;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/e0996c60-34c2-4f52-90e3-616474a4ebb5;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/d3d29fb1-35a4-4f8b-adb8-26ed8d766f0f;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/1570fce2-e646-42bb-ab5d-be3bd953f131;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/98d8e72e-edab-4d92-a410-c3364f437c05;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/6c173c29-ec47-4324-bfb2-e1d6bc92566d;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/bba59854-af70-4e6a-9482-e9bf1b0f3c6c;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/1ff61781-5c3b-4680-97e1-47ed1e8a6dff;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng//resources.get?uuid=08508ba3-5a7d-44eb-8dc0-06a5c92a9472&fname=AnaEE_Nodes.png",
-    "group": "anaee",
-    "groups": [
-        {
-            "name": "anaee"
-        }
-    ],
-    "name": "30aef3e3-19f7-5f41-94ca-242a7d300d85",
-    "notes": [
-        "AnaEE France has brought together in an integrated network a unique collection of experimental platforms  in controlled, semi-natural or natural environments, analysis platforms and shared instruments as well as modeling platforms and Database Information Systems, all devoted to the biology of continental ecosystems.\nThe infrastructure is built around three main service offerings that provide access to a range of experimental facilities: the Tr\u00e8s Grande Infrastructure de Recherche des \u00c9cotrons - \u00c9cotrons Very Large Research Infrastructure, four experimental platforms in semi-natural environments, and some 20 natural sites in metropolitan France and French Guiana where long-term experiments are conducted in forests, pastures, lakes and crops. In the field of environmental microbiology, AnaEE France is also investing in the shared instruments and analytical resources required for a detailed characterization of the environment and microorganisms. \n\nIn a single integrated network it provides all the tools required to study, understand and model biological systems and conduct innovative biological research on gene - environment interactions, biodiversity and the functioning of ecosystems."
-    ],
-    "oai_identifier": [
-        "30aef3e3-19f7-5f41-94ca-242a7d300d85"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Guyane"
-        },
-        {
-            "name": "Estrees-Mons"
-        },
-        {
-            "name": "Lusignan"
-        },
-        {
-            "name": "Foljuif"
-        },
-        {
-            "name": "Dijon"
-        },
-        {
-            "name": "Nancy"
-        },
-        {
-            "name": "Theix"
-        },
-        {
-            "name": "Montpellier"
-        },
-        {
-            "name": "Rennes"
-        },
-        {
-            "name": "Azerailles"
-        },
-        {
-            "name": "Versailles"
-        },
-        {
-            "name": "Versailles"
-        }
-    ],
-    "title": [
-        "Services AnaEE-France pour l'exp\u00e9rimentation sur les ecosyst\u00e8mes continentaux"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/anaee-oai_dc/SET_1/json/b2f601cd-aa35-53e5-bba9-665c5349f40d.json b/oaitestdata/anaee-oai_dc/SET_1/json/b2f601cd-aa35-53e5-bba9-665c5349f40d.json
deleted file mode 100644
index 872f40ea..00000000
--- a/oaitestdata/anaee-oai_dc/SET_1/json/b2f601cd-aa35-53e5-bba9-665c5349f40d.json
+++ /dev/null
@@ -1,94 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "inapplicable"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://w3.avignon.inra.fr/geonetwork_anaee/srv/fre/csw-envriplus?verb=GetRecord&metadataPrefix=oai_dc&identifier=b2f601cd-aa35-53e5-bba9-665c5349f40d",
-    "PublicationTimestamp": "2018-10-27T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "AnaEE"
-    ],
-    "RelatedIdentifier": [
-        "https://www.anaee-france.fr/en/about-us/introduction-to-anaee-france",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/home",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/08508ba3-5a7d-44eb-8dc0-06a5c92a9472",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/20b9aa10-5aa5-48e3-bb61-e5a5746796ae",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng//resources.get?uuid=ec151f7d-fa3f-49b2-8603-0eda7589a3a4&fname=AnaEE4projects.png"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "intellectualPropertyRights",
-        "intellectualPropertyRights"
-    ],
-    "fulltext": "ec151f7d-fa3f-49b2-8603-0eda7589a3a4;2018-10-27T08:47:30;Projets d'experimentation sur les \u00e9cosyst\u00e8mes utilisant les services de AnaEE-France;dataset;Installations de suivi environnemental;\u00e9cosyst\u00e8me;exp\u00e9rimentation;facteurs exp\u00e9rimentaux manipul\u00e9s;\u00e9cosyst\u00e8me forestier;cropping system;lac d'eau douce;prairie;ecologie exp\u00e9rimentale;sol;climat;gestion des \u00e9cosyst\u00e8mes;biodiversit\u00e9;imagerie;propri\u00e9t\u00e9 chimique de l'air;m\u00e9t\u00e9orologie;amendement organique;biologie du sol;flux de surface;chimie du sol;propri\u00e9t\u00e9 chimique de l'eau;v\u00e9g\u00e9tation;biologie de l'eau;physique du sol;paillis;gestion des \u00e9cosyst\u00e8mes;propri\u00e9t\u00e9 physique de l'eau;structure;inapplicable;AnaEE-France is the French national infrastructure devoted to the study of continental ecosystems and their biodiversity. It offers experimental facilities in controlled, semi-natural or natural environments, analysis platforms and shared instruments as well as modeling platforms and database Information Systems.\n\nThe research project that use the AnaEE-F experimental facilities will be described by general metadata (description of the experiment, type of ecosystem, studied variables, manipulated factors);AnaEE-France is the French national infrastructure devoted to the study of continental ecosystems and their biodiversity. It offers experimental facilities in controlled, semi-natural or natural environments, analysis platforms and shared instruments as well as modeling platforms and database Information Systems.\n\nThe research project that use the AnaEE-F experimental facilities will be described by general metadata (description of the experiment, type of ecosystem, studied variables, manipulated factors);intellectualPropertyRights;intellectualPropertyRights;eng;inapplicable;https://www.anaee-france.fr/en/about-us/introduction-to-anaee-france;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/home;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/08508ba3-5a7d-44eb-8dc0-06a5c92a9472;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/20b9aa10-5aa5-48e3-bb61-e5a5746796ae;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng//resources.get?uuid=ec151f7d-fa3f-49b2-8603-0eda7589a3a4&fname=AnaEE4projects.png",
-    "group": "anaee",
-    "groups": [
-        {
-            "name": "anaee"
-        }
-    ],
-    "name": "b2f601cd-aa35-53e5-bba9-665c5349f40d",
-    "notes": [
-        "AnaEE-France is the French national infrastructure devoted to the study of continental ecosystems and their biodiversity. It offers experimental facilities in controlled, semi-natural or natural environments, analysis platforms and shared instruments as well as modeling platforms and database Information Systems.\n\nThe research project that use the AnaEE-F experimental facilities will be described by general metadata (description of the experiment, type of ecosystem, studied variables, manipulated factors)"
-    ],
-    "oai_identifier": [
-        "b2f601cd-aa35-53e5-bba9-665c5349f40d"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Installations de suivi environnemental"
-        },
-        {
-            "name": "Installations de suivi environnemental"
-        },
-        {
-            "name": "Installations de suivi environnemental"
-        },
-        {
-            "name": "Installations de suivi environnemental"
-        },
-        {
-            "name": "Installations de suivi environnemental"
-        },
-        {
-            "name": "cropping system"
-        },
-        {
-            "name": "lac deau douce"
-        },
-        {
-            "name": "prairie"
-        },
-        {
-            "name": "prairie"
-        },
-        {
-            "name": "sol"
-        },
-        {
-            "name": "climat"
-        },
-        {
-            "name": "climat"
-        }
-    ],
-    "title": [
-        "Projets d'experimentation sur les \u00e9cosyst\u00e8mes utilisant les services de AnaEE-France"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/anaee-oai_dc/SET_1/json/bfab9352-d1fe-5e7b-8c7d-3c71eb743904.json b/oaitestdata/anaee-oai_dc/SET_1/json/bfab9352-d1fe-5e7b-8c7d-3c71eb743904.json
deleted file mode 100644
index 7211dcf8..00000000
--- a/oaitestdata/anaee-oai_dc/SET_1/json/bfab9352-d1fe-5e7b-8c7d-3c71eb743904.json
+++ /dev/null
@@ -1,95 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "inapplicable"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://w3.avignon.inra.fr/geonetwork_anaee/srv/fre/csw-envriplus?verb=GetRecord&metadataPrefix=oai_dc&identifier=bfab9352-d1fe-5e7b-8c7d-3c71eb743904",
-    "PublicationTimestamp": "2018-10-27T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "AnaEE"
-    ],
-    "RelatedIdentifier": [
-        "https://www.anaee-france.fr/en/about-us/introduction-to-anaee-france",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/home",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/20b9aa10-5aa5-48e3-bb61-e5a5746796ae",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/d7d7f3bb-86dc-4c10-9661-dfa293c73862",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/09d4c15b-fd36-482f-aae1-68fe1570dedf",
-        "http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng//resources.get?uuid=20b9aa10-5aa5-48e3-bb61-e5a5746796ae&fname=AnaEE_node5.png"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "intellectualPropertyRights",
-        "intellectualPropertyRights"
-    ],
-    "fulltext": "dd9d31f9-b647-420f-9945-2f4942366534;2018-10-27T08:48:29;Jeux de donn\u00e9es provenant des experimentations r\u00e9alis\u00e9es par les services de AnaEE-France;dataset;Installations de suivi environnemental;\u00e9cosyst\u00e8me;exp\u00e9rimentation;facteurs exp\u00e9rimentaux manipul\u00e9s;\u00e9cosyst\u00e8me forestier;cropping system;lac d'eau douce;prairie;ecologie exp\u00e9rimentale;sol;climat;gestion des \u00e9cosyst\u00e8mes;biodiversit\u00e9;imagerie;propri\u00e9t\u00e9 chimique de l'air;m\u00e9t\u00e9orologie;amendement organique;biologie du sol;flux de surface;chimie du sol;propri\u00e9t\u00e9 chimique de l'eau;v\u00e9g\u00e9tation;biologie de l'eau;physique du sol;paillis;gestion des \u00e9cosyst\u00e8mes;propri\u00e9t\u00e9 physique de l'eau;structure;inapplicable;AnaEE-France is the French national infrastructure devoted to the study of continental ecosystems and their biodiversity. It offers experimental facilities in controlled, semi-natural or natural environments, analysis platforms and shared instruments as well as modeling platforms and database Information Systems.\n\nThe data generated from the AnaEE-F services are mostly produced by the platforms and, in some cases, by the user of the services. Data produced by the platforms are either core data characterizing the environment of the site (weather, soil ...) or experience-specific data collected by the platform on behalf of the user (measurement of gas in a enclosed platform cell, temperature of a basin ...).\nData are stored in dedicated database IS. According to a FAIR OpenData policy, datasets become accessible at the end of the project and when completed.;AnaEE-France is the French national infrastructure devoted to the study of continental ecosystems and their biodiversity. It offers experimental facilities in controlled, semi-natural or natural environments, analysis platforms and shared instruments as well as modeling platforms and database Information Systems.\n\nThe data generated from the AnaEE-F services are mostly produced by the platforms and, in some cases, by the user of the services. Data produced by the platforms are either core data characterizing the environment of the site (weather, soil ...) or experience-specific data collected by the platform on behalf of the user (measurement of gas in a enclosed platform cell, temperature of a basin ...).\nData are stored in dedicated database IS. According to a FAIR OpenData policy, datasets become accessible at the end of the project and when completed.;intellectualPropertyRights;intellectualPropertyRights;eng;inapplicable;https://www.anaee-france.fr/en/about-us/introduction-to-anaee-france;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/home;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/20b9aa10-5aa5-48e3-bb61-e5a5746796ae;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/d7d7f3bb-86dc-4c10-9661-dfa293c73862;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng/catalog.search#/metadata/09d4c15b-fd36-482f-aae1-68fe1570dedf;http://w3.avignon.inra.fr/geonetwork_anaee/srv/eng//resources.get?uuid=20b9aa10-5aa5-48e3-bb61-e5a5746796ae&fname=AnaEE_node5.png",
-    "group": "anaee",
-    "groups": [
-        {
-            "name": "anaee"
-        }
-    ],
-    "name": "bfab9352-d1fe-5e7b-8c7d-3c71eb743904",
-    "notes": [
-        "AnaEE-France is the French national infrastructure devoted to the study of continental ecosystems and their biodiversity. It offers experimental facilities in controlled, semi-natural or natural environments, analysis platforms and shared instruments as well as modeling platforms and database Information Systems.\n\nThe data generated from the AnaEE-F services are mostly produced by the platforms and, in some cases, by the user of the services. Data produced by the platforms are either core data characterizing the environment of the site (weather, soil ...) or experience-specific data collected by the platform on behalf of the user (measurement of gas in a enclosed platform cell, temperature of a basin ...).\nData are stored in dedicated database IS. According to a FAIR OpenData policy, datasets become accessible at the end of the project and when completed."
-    ],
-    "oai_identifier": [
-        "bfab9352-d1fe-5e7b-8c7d-3c71eb743904"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Installations de suivi environnemental"
-        },
-        {
-            "name": "Installations de suivi environnemental"
-        },
-        {
-            "name": "Installations de suivi environnemental"
-        },
-        {
-            "name": "Installations de suivi environnemental"
-        },
-        {
-            "name": "Installations de suivi environnemental"
-        },
-        {
-            "name": "cropping system"
-        },
-        {
-            "name": "lac deau douce"
-        },
-        {
-            "name": "prairie"
-        },
-        {
-            "name": "prairie"
-        },
-        {
-            "name": "sol"
-        },
-        {
-            "name": "climat"
-        },
-        {
-            "name": "climat"
-        }
-    ],
-    "title": [
-        "Jeux de donn\u00e9es provenant des experimentations r\u00e9alis\u00e9es par les services de AnaEE-France"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/b2share-oai_dc/EUDAT_1/json/00cc5cb4-cfb2-5876-9e41-071cf49d04d2.json b/oaitestdata/b2share-oai_dc/EUDAT_1/json/00cc5cb4-cfb2-5876-9e41-071cf49d04d2.json
deleted file mode 100644
index c3095eec..00000000
--- a/oaitestdata/b2share-oai_dc/EUDAT_1/json/00cc5cb4-cfb2-5876-9e41-071cf49d04d2.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.23728/b2share.d8b3db5e46204709964990d656a4fedc",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://b2share.eudat.eu/api/oai2d?verb=GetRecord&metadataPrefix=marcxml&identifier=oai:b2share.eudat.eu:b2rec/d8b3db5e46204709964990d656a4fedc",
-    "PID": "http://hdl.handle.net/11304/e2d02cfb-eea1-4475-bd26-4ff9a7727075",
-    "PublicationTimestamp": "2018-01-31T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11304/e2d02cfb-eea1-4475-bd26-4ff9a7727075",
-        "10.23728/b2share.d8b3db5e46204709964990d656a4fedc",
-        "https://b2share.eudat.eu/api/records/d8b3db5e46204709964990d656a4fedc",
-        "oai:b2share.eudat.eu:b2rec/d8b3db5e46204709964990d656a4fedc"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Luca Franci"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/d8b3db5e46204709964990d656a4fedc;2018-01-31T12:05:00Z;e9b9792e-79fb-4b07-b6b4-b9c2bd06d095;Luca Franci;2018-01-31T12:05:00.092734+00:00;This is a small collection of movies from 2D and 3D high-resolution hybrid particle-in-cell  simulations of plasma turbulence performed with the hybrid code CAMELIA. The evolution of the magnetic field is shown in a large 3D grid (3D_B2_Wholegrid.avi), in a large 2D grid (2D_B2_WholeGrid.avi) and in two smaller 2D subgrids (2D_B2_SubGrid1.avi and 2D_B2_SubGrid2.avi)\nThese movie were shown by L. Franci during his talk \"Hybrid simulations of plasma turbulence \u2028in support of space missions:  toward an archive for numerical results  with EUDAT services\" at the \"EUDAT Conference - Putting the EOSC vision into practice\" in Porto (24th January 2018). \nMore details about CAMELIA can be found here: http://terezka.asu.cas.cz/helinger/camelia.html and https://arxiv.org/abs/1712.03930. The analysis and discussion of the 2D and 3D simulations shown in the movies can be found here: http://dx.doi.org/10.3847/2041-8213/aa93fb and http://dx.doi.org/10.3847/1538-4357/aaa3e8.;http://hdl.handle.net/11304/e2d02cfb-eea1-4475-bd26-4ff9a7727075;10.23728/b2share.d8b3db5e46204709964990d656a4fedc;https://b2share.eudat.eu/api/records/d8b3db5e46204709964990d656a4fedc;oai:b2share.eudat.eu:b2rec/d8b3db5e46204709964990d656a4fedc;info:eu-repo/semantics/openAccess;Turbulence;Astrophysical plasmas;Solar wind;Movies from the talk \"Hybrid simulations of plasma turbulence \u2028in support of space missions:  toward an archive for numerical results  with EUDAT services\"",
-    "group": "b2share",
-    "groups": [
-        {
-            "name": "b2share"
-        }
-    ],
-    "name": "00cc5cb4-cfb2-5876-9e41-071cf49d04d2",
-    "notes": [
-        "This is a small collection of movies from 2D and 3D high-resolution hybrid particle-in-cell  simulations of plasma turbulence performed with the hybrid code CAMELIA. The evolution of the magnetic field is shown in a large 3D grid (3D_B2_Wholegrid.avi), in a large 2D grid (2D_B2_WholeGrid.avi) and in two smaller 2D subgrids (2D_B2_SubGrid1.avi and 2D_B2_SubGrid2.avi)\nThese movie were shown by L. Franci during his talk \"Hybrid simulations of plasma turbulence \u2028in support of space missions:  toward an archive for numerical results  with EUDAT services\" at the \"EUDAT Conference - Putting the EOSC vision into practice\" in Porto (24th January 2018). \nMore details about CAMELIA can be found here: http://terezka.asu.cas.cz/helinger/camelia.html and https://arxiv.org/abs/1712.03930. The analysis and discussion of the 2D and 3D simulations shown in the movies can be found here: http://dx.doi.org/10.3847/2041-8213/aa93fb and http://dx.doi.org/10.3847/1538-4357/aaa3e8."
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/d8b3db5e46204709964990d656a4fedc"
-    ],
-    "oai_set": [
-        "e9b9792e-79fb-4b07-b6b4-b9c2bd06d095"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Turbulence"
-        },
-        {
-            "name": "Astrophysical plasmas"
-        },
-        {
-            "name": "Solar wind"
-        }
-    ],
-    "title": [
-        "Movies from the talk \"Hybrid simulations of plasma turbulence \u2028in support of space missions:  toward an archive for numerical results  with EUDAT services\""
-    ],
-    "url": "https://b2share.eudat.eu/api/records/d8b3db5e46204709964990d656a4fedc"
-}
\ No newline at end of file
diff --git a/oaitestdata/b2share-oai_dc/EUDAT_1/json/0a04573e-7cf3-5846-924a-a5e0c89063c7.json b/oaitestdata/b2share-oai_dc/EUDAT_1/json/0a04573e-7cf3-5846-924a-a5e0c89063c7.json
deleted file mode 100644
index efc65a51..00000000
--- a/oaitestdata/b2share-oai_dc/EUDAT_1/json/0a04573e-7cf3-5846-924a-a5e0c89063c7.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.23728/b2share.933d3d24060d4b528c2f6c523ac3844d",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://b2share.eudat.eu/api/oai2d?verb=GetRecord&metadataPrefix=marcxml&identifier=oai:b2share.eudat.eu:b2rec/933d3d24060d4b528c2f6c523ac3844d",
-    "PID": "http://hdl.handle.net/11304/b096f60a-7232-4bc5-97d0-5297d8d85c04",
-    "PublicationTimestamp": "2019-04-12T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11304/b096f60a-7232-4bc5-97d0-5297d8d85c04",
-        "10.23728/b2share.933d3d24060d4b528c2f6c523ac3844d",
-        "https://b2share.eudat.eu/api/records/933d3d24060d4b528c2f6c523ac3844d",
-        "oai:b2share.eudat.eu:b2rec/933d3d24060d4b528c2f6c523ac3844d"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess",
-        "Creative Commons Attribution-NonCommercial-NoDerivs (CC-BY-NC-ND)"
-    ],
-    "author": [
-        "Franco Vazza"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/933d3d24060d4b528c2f6c523ac3844d;2019-04-12T15:07:50Z;e9b9792e-79fb-4b07-b6b4-b9c2bd06d095;Franco Vazza;2019-04-12T15:07:50.961654+00:00;Initial conditions for ENZO (enzo-project.org) AMR simulations of a pair of massive clusters in an early merger stage. Nested initial conditions are needed to produce 2 sets of 256^3 nested grids, using ENZO's \"inits\" sub-program. The full AMR simulation can then run with enzo.exe -d param_amr.dat A simulation with 8 levels of AMR within the innermost 0.1^3 region, and Dedner-MHD (see param_amr.dat)  took ~80,000 core hours on 512 cores in JURECA (now dismissed) @ Julich FZ. More info can be found here http://adsabs.harvard.edu/abs/2018MNRAS.474.1672V and here https://cosmosimfrazza.myfreesites.net/amr_clusters ;http://hdl.handle.net/11304/b096f60a-7232-4bc5-97d0-5297d8d85c04;10.23728/b2share.933d3d24060d4b528c2f6c523ac3844d;https://b2share.eudat.eu/api/records/933d3d24060d4b528c2f6c523ac3844d;oai:b2share.eudat.eu:b2rec/933d3d24060d4b528c2f6c523ac3844d;info:eu-repo/semantics/openAccess;Creative Commons Attribution-NonCommercial-NoDerivs (CC-BY-NC-ND);enzo;numerical simulations;MHD;Initial conditions for pre-merger cluster simulation with ENZO",
-    "group": "b2share",
-    "groups": [
-        {
-            "name": "b2share"
-        }
-    ],
-    "name": "0a04573e-7cf3-5846-924a-a5e0c89063c7",
-    "notes": [
-        "Initial conditions for ENZO (enzo-project.org) AMR simulations of a pair of massive clusters in an early merger stage. Nested initial conditions are needed to produce 2 sets of 256^3 nested grids, using ENZO's \"inits\" sub-program. The full AMR simulation can then run with enzo.exe -d param_amr.dat A simulation with 8 levels of AMR within the innermost 0.1^3 region, and Dedner-MHD (see param_amr.dat)  took ~80,000 core hours on 512 cores in JURECA (now dismissed) @ Julich FZ. More info can be found here http://adsabs.harvard.edu/abs/2018MNRAS.474.1672V and here https://cosmosimfrazza.myfreesites.net/amr_clusters "
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/933d3d24060d4b528c2f6c523ac3844d"
-    ],
-    "oai_set": [
-        "e9b9792e-79fb-4b07-b6b4-b9c2bd06d095"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "enzo"
-        },
-        {
-            "name": "numerical simulations"
-        },
-        {
-            "name": "MHD"
-        }
-    ],
-    "title": [
-        "Initial conditions for pre-merger cluster simulation with ENZO"
-    ],
-    "url": "https://b2share.eudat.eu/api/records/933d3d24060d4b528c2f6c523ac3844d"
-}
\ No newline at end of file
diff --git a/oaitestdata/b2share-oai_dc/EUDAT_1/json/0a2437d0-108f-5f04-908a-bd31e106b6a5.json b/oaitestdata/b2share-oai_dc/EUDAT_1/json/0a2437d0-108f-5f04-908a-bd31e106b6a5.json
deleted file mode 100644
index b17e144f..00000000
--- a/oaitestdata/b2share-oai_dc/EUDAT_1/json/0a2437d0-108f-5f04-908a-bd31e106b6a5.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "https://b2share.eudat.eu"
-    ],
-    "Contributor": [
-        "Asela Rajapakse (SCLab)",
-        "Doron Goldfarb (EAA)"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.23728/b2share.cac880ea6dd54dcf8c737bfe3818adc6",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://b2share.eudat.eu/api/oai2d?verb=GetRecord&metadataPrefix=marcxml&identifier=oai:b2share.eudat.eu:b2rec/cac880ea6dd54dcf8c737bfe3818adc6",
-    "PID": "http://hdl.handle.net/11304/55972615-30a5-415b-9e58-6fb08657b6af",
-    "PublicationTimestamp": "2018-08-26T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "https://b2share.eudat.eu"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11304/55972615-30a5-415b-9e58-6fb08657b6af",
-        "10.23728/b2share.cac880ea6dd54dcf8c737bfe3818adc6",
-        "https://b2share.eudat.eu/api/records/cac880ea6dd54dcf8c737bfe3818adc6",
-        "oai:b2share.eudat.eu:b2rec/cac880ea6dd54dcf8c737bfe3818adc6"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess",
-        "Creative Commons Attribution (CC-BY)"
-    ],
-    "author": [
-        "Cortes, Toni (BSC)",
-        "Weigel, Tobias (DKRZ)",
-        "Miranda, Alberto (BSC)",
-        "Dima, Emanuel (EKUT)",
-        "Cacciari, Claudio (Cineca)",
-        "Queralt, Anna (BSC)",
-        "Fares, Massimo (INGV)"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/cac880ea6dd54dcf8c737bfe3818adc6;2018-08-26T16:28:28Z;e9b9792e-79fb-4b07-b6b4-b9c2bd06d095;Asela Rajapakse (SCLab);Doron Goldfarb (EAA);Miranda, Alberto (BSC);Weigel, Tobias (DKRZ);Dima, Emanuel (EKUT);Cacciari, Claudio (Cineca);Cortes, Toni (BSC);Queralt, Anna (BSC);Fares, Massimo (INGV);2018-08-26T16:28:28.270599+00:00;This document presents the work done by WP8 to produce a generic framework that allows the EUDAT CDI services to appropriately handle dynamic data. We propose a generic HTTP API to allow services to model the dynamic data lifecycle of research communities, present extensions to the Generic Execution Framework and discuss optimizations to data transfers and storage. We also discuss a proof-of-concept prototype for a dynamic data-enabled archival service based on the HTTP API and discuss the results obtained when using it to replicate a real use case.;http://hdl.handle.net/11304/55972615-30a5-415b-9e58-6fb08657b6af;10.23728/b2share.cac880ea6dd54dcf8c737bfe3818adc6;https://b2share.eudat.eu/api/records/cac880ea6dd54dcf8c737bfe3818adc6;oai:b2share.eudat.eu:b2rec/cac880ea6dd54dcf8c737bfe3818adc6;eng;https://b2share.eudat.eu;info:eu-repo/semantics/openAccess;Creative Commons Attribution (CC-BY);Data Life Cycle models, Dynamic Data, fingerprinting, deduplication;D8.5: Report on Dynamic Data Framework and Management Services;Text",
-    "group": "b2share",
-    "groups": [
-        {
-            "name": "b2share"
-        }
-    ],
-    "name": "0a2437d0-108f-5f04-908a-bd31e106b6a5",
-    "notes": [
-        "This document presents the work done by WP8 to produce a generic framework that allows the EUDAT CDI services to appropriately handle dynamic data. We propose a generic HTTP API to allow services to model the dynamic data lifecycle of research communities, present extensions to the Generic Execution Framework and discuss optimizations to data transfers and storage. We also discuss a proof-of-concept prototype for a dynamic data-enabled archival service based on the HTTP API and discuss the results obtained when using it to replicate a real use case."
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/cac880ea6dd54dcf8c737bfe3818adc6"
-    ],
-    "oai_set": [
-        "e9b9792e-79fb-4b07-b6b4-b9c2bd06d095"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Data Life Cycle models"
-        },
-        {
-            "name": "Dynamic Data"
-        },
-        {
-            "name": "fingerprinting"
-        },
-        {
-            "name": "deduplication"
-        }
-    ],
-    "title": [
-        "D8.5: Report on Dynamic Data Framework and Management Services"
-    ],
-    "url": "https://b2share.eudat.eu/api/records/cac880ea6dd54dcf8c737bfe3818adc6"
-}
\ No newline at end of file
diff --git a/oaitestdata/b2share-oai_dc/EUDAT_1/json/0a2724ba-e065-5ca2-b04b-cd5ea9bb3cf2.json b/oaitestdata/b2share-oai_dc/EUDAT_1/json/0a2724ba-e065-5ca2-b04b-cd5ea9bb3cf2.json
deleted file mode 100644
index cbfc3629..00000000
--- a/oaitestdata/b2share-oai_dc/EUDAT_1/json/0a2724ba-e065-5ca2-b04b-cd5ea9bb3cf2.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.23728/b2share.d2e4b65310ed43fb91251c1ab2c47d86",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://b2share.eudat.eu/api/oai2d?verb=GetRecord&metadataPrefix=marcxml&identifier=oai:b2share.eudat.eu:b2rec/d2e4b65310ed43fb91251c1ab2c47d86",
-    "PID": "http://hdl.handle.net/11304/1c2f7424-47bb-48ac-82b1-b7431fab2891",
-    "PublicationTimestamp": "2017-06-18T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11304/1c2f7424-47bb-48ac-82b1-b7431fab2891",
-        "10.23728/b2share.d2e4b65310ed43fb91251c1ab2c47d86",
-        "https://b2share.eudat.eu/api/records/d2e4b65310ed43fb91251c1ab2c47d86",
-        "oai:b2share.eudat.eu:b2rec/d2e4b65310ed43fb91251c1ab2c47d86"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess",
-        "CC-BY-SA"
-    ],
-    "author": [
-        "Kuchinke, Wolfgang",
-        "Iozzi, Francesca",
-        "Broeder, Daan"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/d2e4b65310ed43fb91251c1ab2c47d86;2018-01-11T13:50:33Z;e9b9792e-79fb-4b07-b6b4-b9c2bd06d095;Kuchinke, Wolfgang;Iozzi, Francesca;Broeder, Daan;2017-06-18T19:53:44.042408+00:00;Results of the first f2f EUDAT Sensitive Data Working Group Meeting in Krakow Sept 27, 2016;http://hdl.handle.net/11304/1c2f7424-47bb-48ac-82b1-b7431fab2891;10.23728/b2share.d2e4b65310ed43fb91251c1ab2c47d86;https://b2share.eudat.eu/api/records/d2e4b65310ed43fb91251c1ab2c47d86;oai:b2share.eudat.eu:b2rec/d2e4b65310ed43fb91251c1ab2c47d86;info:eu-repo/semantics/openAccess;CC-BY-SA;Sensitive Data, eInfrastructure, ;How can e-infrastructures deal with the sensitive data challenge? Results of the EUDAT Sensitive Data Group workshop",
-    "group": "b2share",
-    "groups": [
-        {
-            "name": "b2share"
-        }
-    ],
-    "name": "0a2724ba-e065-5ca2-b04b-cd5ea9bb3cf2",
-    "notes": [
-        "Results of the first f2f EUDAT Sensitive Data Working Group Meeting in Krakow Sept 27, 2016"
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/d2e4b65310ed43fb91251c1ab2c47d86"
-    ],
-    "oai_set": [
-        "e9b9792e-79fb-4b07-b6b4-b9c2bd06d095"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Sensitive Data"
-        },
-        {
-            "name": "eInfrastructure"
-        }
-    ],
-    "title": [
-        "How can e-infrastructures deal with the sensitive data challenge? Results of the EUDAT Sensitive Data Group workshop"
-    ],
-    "url": "https://b2share.eudat.eu/api/records/d2e4b65310ed43fb91251c1ab2c47d86"
-}
\ No newline at end of file
diff --git a/oaitestdata/b2share-oai_dc/EUDAT_1/json/0a3dfe6d-8fe7-5236-bdfd-8b7db7609d0c.json b/oaitestdata/b2share-oai_dc/EUDAT_1/json/0a3dfe6d-8fe7-5236-bdfd-8b7db7609d0c.json
deleted file mode 100644
index 214dc4ba..00000000
--- a/oaitestdata/b2share-oai_dc/EUDAT_1/json/0a3dfe6d-8fe7-5236-bdfd-8b7db7609d0c.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "http://b2share.eudat.eu"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://b2share.eudat.eu/api/oai2d?verb=GetRecord&metadataPrefix=marcxml&identifier=oai:b2share.eudat.eu:b2rec/447a906972b84c7a810a45636cbb778d",
-    "PID": "http://hdl.handle.net/11304/b79aae29-abcd-4b1b-bb38-3943649a430a",
-    "PublicationTimestamp": "2016-12-22T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "http://b2share.eudat.eu"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11304/b79aae29-abcd-4b1b-bb38-3943649a430a",
-        "https://b2share.eudat.eu/api/records/447a906972b84c7a810a45636cbb778d",
-        "oai:b2share.eudat.eu:b2rec/447a906972b84c7a810a45636cbb778d"
-    ],
-    "ResourceType": [
-        "Other"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Daniel Figat"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/447a906972b84c7a810a45636cbb778d;2018-01-11T13:49:18Z;e9b9792e-79fb-4b07-b6b4-b9c2bd06d095;Daniel Figat;2016-12-22T10:32:38.247093+00:00;pulsefile with 10 slices;http://hdl.handle.net/11304/b79aae29-abcd-4b1b-bb38-3943649a430a;https://b2share.eudat.eu/api/records/447a906972b84c7a810a45636cbb778d;oai:b2share.eudat.eu:b2rec/447a906972b84c7a810a45636cbb778d;en;http://b2share.eudat.eu;info:eu-repo/semantics/openAccess;pulsefile;fusion;euitm_10050;Other",
-    "group": "b2share",
-    "groups": [
-        {
-            "name": "b2share"
-        }
-    ],
-    "name": "0a3dfe6d-8fe7-5236-bdfd-8b7db7609d0c",
-    "notes": [
-        "pulsefile with 10 slices"
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/447a906972b84c7a810a45636cbb778d"
-    ],
-    "oai_set": [
-        "e9b9792e-79fb-4b07-b6b4-b9c2bd06d095"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "pulsefile"
-        },
-        {
-            "name": "fusion"
-        }
-    ],
-    "title": [
-        "euitm_10050"
-    ],
-    "url": "https://b2share.eudat.eu/api/records/447a906972b84c7a810a45636cbb778d"
-}
\ No newline at end of file
diff --git a/oaitestdata/b2share-oai_dc/EUDAT_1/json/0c8bb734-992d-541d-81cb-b795abd6cc23.json b/oaitestdata/b2share-oai_dc/EUDAT_1/json/0c8bb734-992d-541d-81cb-b795abd6cc23.json
deleted file mode 100644
index 386f7019..00000000
--- a/oaitestdata/b2share-oai_dc/EUDAT_1/json/0c8bb734-992d-541d-81cb-b795abd6cc23.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://b2share.eudat.eu/api/oai2d?verb=GetRecord&metadataPrefix=marcxml&identifier=oai:b2share.eudat.eu:b2rec/7fa4709bcc0c406eb43805aeb5590093",
-    "PID": "http://hdl.handle.net/11304/348c967c-b988-11e3-8cd7-14feb57d12b9",
-    "PublicationTimestamp": "2016-12-22T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11304/348c967c-b988-11e3-8cd7-14feb57d12b9",
-        "https://b2share.eudat.eu/api/records/7fa4709bcc0c406eb43805aeb5590093",
-        "oai:b2share.eudat.eu:b2rec/7fa4709bcc0c406eb43805aeb5590093"
-    ],
-    "ResourceType": [
-        "Other"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/closedAccess"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/7fa4709bcc0c406eb43805aeb5590093;2018-01-11T13:47:53Z;e9b9792e-79fb-4b07-b6b4-b9c2bd06d095;2016-12-22T10:00:22.765920+00:00;A talk on PIDs given at one of EUDAT's training days;http://hdl.handle.net/11304/348c967c-b988-11e3-8cd7-14feb57d12b9;https://b2share.eudat.eu/api/records/7fa4709bcc0c406eb43805aeb5590093;oai:b2share.eudat.eu:b2rec/7fa4709bcc0c406eb43805aeb5590093;en;info:eu-repo/semantics/closedAccess;A Talk On PIDs;Other",
-    "group": "b2share",
-    "groups": [
-        {
-            "name": "b2share"
-        }
-    ],
-    "name": "0c8bb734-992d-541d-81cb-b795abd6cc23",
-    "notes": [
-        "A talk on PIDs given at one of EUDAT's training days"
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/7fa4709bcc0c406eb43805aeb5590093"
-    ],
-    "oai_set": [
-        "e9b9792e-79fb-4b07-b6b4-b9c2bd06d095"
-    ],
-    "state": "active",
-    "title": [
-        "A Talk On PIDs"
-    ],
-    "url": "https://b2share.eudat.eu/api/records/7fa4709bcc0c406eb43805aeb5590093"
-}
\ No newline at end of file
diff --git a/oaitestdata/b2share-oai_dc/EUDAT_1/json/0ccb6d95-b88e-5570-83c4-286f0654988c.json b/oaitestdata/b2share-oai_dc/EUDAT_1/json/0ccb6d95-b88e-5570-83c4-286f0654988c.json
deleted file mode 100644
index 24750b96..00000000
--- a/oaitestdata/b2share-oai_dc/EUDAT_1/json/0ccb6d95-b88e-5570-83c4-286f0654988c.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "http://b2share.eudat.eu"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://b2share.eudat.eu/api/oai2d?verb=GetRecord&metadataPrefix=marcxml&identifier=oai:b2share.eudat.eu:b2rec/f59030f3d81a48958f5e529db6507b2c",
-    "PID": "http://hdl.handle.net/11304/01f56006-8401-4bbd-847c-1268914e7788",
-    "PublicationTimestamp": "2016-12-22T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "http://b2share.eudat.eu"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11304/01f56006-8401-4bbd-847c-1268914e7788",
-        "https://b2share.eudat.eu/api/records/f59030f3d81a48958f5e529db6507b2c",
-        "oai:b2share.eudat.eu:b2rec/f59030f3d81a48958f5e529db6507b2c"
-    ],
-    "ResourceType": [
-        "Other"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Jonas Berndt"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/f59030f3d81a48958f5e529db6507b2c;2018-01-11T13:49:14Z;e9b9792e-79fb-4b07-b6b4-b9c2bd06d095;Jonas Berndt;2016-12-22T10:28:37.103265+00:00;labelled wind data for 128 member, 4 towers, a 6h interval. Global models are featured from 0 to 16. 1 month of data (November 2014);http://hdl.handle.net/11304/01f56006-8401-4bbd-847c-1268914e7788;https://b2share.eudat.eu/api/records/f59030f3d81a48958f5e529db6507b2c;oai:b2share.eudat.eu:b2rec/f59030f3d81a48958f5e529db6507b2c;en;http://b2share.eudat.eu;info:eu-repo/semantics/openAccess;Libvsm format wind data 6h interval 1 month;Other",
-    "group": "b2share",
-    "groups": [
-        {
-            "name": "b2share"
-        }
-    ],
-    "name": "0ccb6d95-b88e-5570-83c4-286f0654988c",
-    "notes": [
-        "labelled wind data for 128 member, 4 towers, a 6h interval. Global models are featured from 0 to 16. 1 month of data (November 2014)"
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/f59030f3d81a48958f5e529db6507b2c"
-    ],
-    "oai_set": [
-        "e9b9792e-79fb-4b07-b6b4-b9c2bd06d095"
-    ],
-    "state": "active",
-    "title": [
-        "Libvsm format wind data 6h interval 1 month"
-    ],
-    "url": "https://b2share.eudat.eu/api/records/f59030f3d81a48958f5e529db6507b2c"
-}
\ No newline at end of file
diff --git a/oaitestdata/b2share-oai_dc/EUDAT_1/json/0d3411db-3eef-5086-828c-a6dd73aa32e0.json b/oaitestdata/b2share-oai_dc/EUDAT_1/json/0d3411db-3eef-5086-828c-a6dd73aa32e0.json
deleted file mode 100644
index d872b6be..00000000
--- a/oaitestdata/b2share-oai_dc/EUDAT_1/json/0d3411db-3eef-5086-828c-a6dd73aa32e0.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "http://b2share.eudat.eu"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://b2share.eudat.eu/api/oai2d?verb=GetRecord&metadataPrefix=marcxml&identifier=oai:b2share.eudat.eu:b2rec/52fc8d49a263476fbea88de813fbb2af",
-    "PID": "http://hdl.handle.net/11304/07756b90-7ed6-11e5-9bb4-2b0aad496318",
-    "PublicationTimestamp": "2016-12-22T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "http://b2share.eudat.eu"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11304/07756b90-7ed6-11e5-9bb4-2b0aad496318",
-        "https://b2share.eudat.eu/api/records/52fc8d49a263476fbea88de813fbb2af",
-        "oai:b2share.eudat.eu:b2rec/52fc8d49a263476fbea88de813fbb2af"
-    ],
-    "ResourceType": [
-        "Other"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/closedAccess"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/52fc8d49a263476fbea88de813fbb2af;2018-01-11T13:48:42Z;e9b9792e-79fb-4b07-b6b4-b9c2bd06d095;2016-12-22T10:22:39.022583+00:00;EUDAT Services Presentation;http://hdl.handle.net/11304/07756b90-7ed6-11e5-9bb4-2b0aad496318;https://b2share.eudat.eu/api/records/52fc8d49a263476fbea88de813fbb2af;oai:b2share.eudat.eu:b2rec/52fc8d49a263476fbea88de813fbb2af;en;http://b2share.eudat.eu;info:eu-repo/semantics/closedAccess;EUDAT Services Presentation;Other",
-    "group": "b2share",
-    "groups": [
-        {
-            "name": "b2share"
-        }
-    ],
-    "name": "0d3411db-3eef-5086-828c-a6dd73aa32e0",
-    "notes": [
-        "EUDAT Services Presentation"
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/52fc8d49a263476fbea88de813fbb2af"
-    ],
-    "oai_set": [
-        "e9b9792e-79fb-4b07-b6b4-b9c2bd06d095"
-    ],
-    "state": "active",
-    "title": [
-        "EUDAT Services Presentation"
-    ],
-    "url": "https://b2share.eudat.eu/api/records/52fc8d49a263476fbea88de813fbb2af"
-}
\ No newline at end of file
diff --git a/oaitestdata/b2share-oai_dc/EUDAT_1/json/0e952885-5493-5d80-a9a3-695cabc0843a.json b/oaitestdata/b2share-oai_dc/EUDAT_1/json/0e952885-5493-5d80-a9a3-695cabc0843a.json
deleted file mode 100644
index 14f48711..00000000
--- a/oaitestdata/b2share-oai_dc/EUDAT_1/json/0e952885-5493-5d80-a9a3-695cabc0843a.json
+++ /dev/null
@@ -1,45 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.23728/b2share.51405d517d1947f894ef70f965e728fc",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://b2share.eudat.eu/api/oai2d?verb=GetRecord&metadataPrefix=marcxml&identifier=oai:b2share.eudat.eu:b2rec/51405d517d1947f894ef70f965e728fc",
-    "PID": "http://hdl.handle.net/11304/c4fc6f0b-1a4e-4b3a-b55e-f71928f85a2e",
-    "PublicationTimestamp": "2017-11-24T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11304/c4fc6f0b-1a4e-4b3a-b55e-f71928f85a2e",
-        "10.23728/b2share.51405d517d1947f894ef70f965e728fc",
-        "https://b2share.eudat.eu/api/records/51405d517d1947f894ef70f965e728fc",
-        "oai:b2share.eudat.eu:b2rec/51405d517d1947f894ef70f965e728fc"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Micha\u0142 Jankowski"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/51405d517d1947f894ef70f965e728fc;2018-01-11T13:51:04Z;e9b9792e-79fb-4b07-b6b4-b9c2bd06d095;Micha\u0142 Jankowski;2017-11-24T15:21:46.357477+00:00;Presentation from AARC2 meeting.;http://hdl.handle.net/11304/c4fc6f0b-1a4e-4b3a-b55e-f71928f85a2e;10.23728/b2share.51405d517d1947f894ef70f965e728fc;https://b2share.eudat.eu/api/records/51405d517d1947f894ef70f965e728fc;oai:b2share.eudat.eu:b2rec/51405d517d1947f894ef70f965e728fc;info:eu-repo/semantics/openAccess;EUDAT-PRACE AAI integration status",
-    "group": "b2share",
-    "groups": [
-        {
-            "name": "b2share"
-        }
-    ],
-    "name": "0e952885-5493-5d80-a9a3-695cabc0843a",
-    "notes": [
-        "Presentation from AARC2 meeting."
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/51405d517d1947f894ef70f965e728fc"
-    ],
-    "oai_set": [
-        "e9b9792e-79fb-4b07-b6b4-b9c2bd06d095"
-    ],
-    "state": "active",
-    "title": [
-        "EUDAT-PRACE AAI integration status"
-    ],
-    "url": "https://b2share.eudat.eu/api/records/51405d517d1947f894ef70f965e728fc"
-}
\ No newline at end of file
diff --git a/oaitestdata/b2share-oai_dc/EUDAT_1/json/0ec59384-a7b6-5dc7-b0ab-3530042ba8a6.json b/oaitestdata/b2share-oai_dc/EUDAT_1/json/0ec59384-a7b6-5dc7-b0ab-3530042ba8a6.json
deleted file mode 100644
index 61f25309..00000000
--- a/oaitestdata/b2share-oai_dc/EUDAT_1/json/0ec59384-a7b6-5dc7-b0ab-3530042ba8a6.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "EUDAT"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.23728/b2share.398e55b3f2c44b89bacce36f4764cee2",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://b2share.eudat.eu/api/oai2d?verb=GetRecord&metadataPrefix=marcxml&identifier=oai:b2share.eudat.eu:b2rec/398e55b3f2c44b89bacce36f4764cee2",
-    "PID": "http://hdl.handle.net/11304/74c66f0b-f814-4202-9dcb-4889ba9b1047",
-    "PublicationTimestamp": "2017-09-27T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "EUDAT"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11304/74c66f0b-f814-4202-9dcb-4889ba9b1047",
-        "10.23728/b2share.398e55b3f2c44b89bacce36f4764cee2",
-        "https://b2share.eudat.eu/api/records/398e55b3f2c44b89bacce36f4764cee2",
-        "oai:b2share.eudat.eu:b2rec/398e55b3f2c44b89bacce36f4764cee2"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Kaila, Urpo ",
-        "Reetz, Johannes ",
-        "Brzezniak, Maciej",
-        "Elbers, Willem ",
-        "Thiemann, Hannes ",
-        "Massol, Marion ",
-        "van de Sanden, Mark",
-        "Rouchon, Olivier"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/398e55b3f2c44b89bacce36f4764cee2;2018-01-11T13:50:52Z;e9b9792e-79fb-4b07-b6b4-b9c2bd06d095;Rouchon, Olivier;Massol, Marion ;Kaila, Urpo ;Elbers, Willem ;Thiemann, Hannes ;Brzezniak, Maciej;van de Sanden, Mark;Reetz, Johannes ;2017-09-27T09:14:37.936844+00:00;This document describes the Terms of Use (ToU) of EUDAT resources and services. Before using any EUDAT services and resources each user must have read and agreed to understand and follow these terms. This ToU can be subject of change.;http://hdl.handle.net/11304/74c66f0b-f814-4202-9dcb-4889ba9b1047;10.23728/b2share.398e55b3f2c44b89bacce36f4764cee2;https://b2share.eudat.eu/api/records/398e55b3f2c44b89bacce36f4764cee2;oai:b2share.eudat.eu:b2rec/398e55b3f2c44b89bacce36f4764cee2;eng;EUDAT;info:eu-repo/semantics/openAccess;Terms of Use;EUDAT Services;EUDAT resources;Users rights and duties;Personal information and data privacy;Access conditions;Legal restrictions;Potential sanctions;EUDAT Services Terms of Use v1.1",
-    "group": "b2share",
-    "groups": [
-        {
-            "name": "b2share"
-        }
-    ],
-    "name": "0ec59384-a7b6-5dc7-b0ab-3530042ba8a6",
-    "notes": [
-        "This document describes the Terms of Use (ToU) of EUDAT resources and services. Before using any EUDAT services and resources each user must have read and agreed to understand and follow these terms. This ToU can be subject of change."
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/398e55b3f2c44b89bacce36f4764cee2"
-    ],
-    "oai_set": [
-        "e9b9792e-79fb-4b07-b6b4-b9c2bd06d095"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Terms Use"
-        },
-        {
-            "name": "EUDAT Services"
-        },
-        {
-            "name": "EUDAT resources"
-        },
-        {
-            "name": "Users rights duties"
-        },
-        {
-            "name": "Personal information data privacy"
-        },
-        {
-            "name": "Access conditions"
-        },
-        {
-            "name": "Legal restrictions"
-        },
-        {
-            "name": "Potential sanctions"
-        }
-    ],
-    "title": [
-        "EUDAT Services Terms of Use v1.1"
-    ],
-    "url": "https://b2share.eudat.eu/api/records/398e55b3f2c44b89bacce36f4764cee2"
-}
\ No newline at end of file
diff --git a/oaitestdata/b2share-oai_dc/EUDAT_1/json/0f2134cd-c80a-5f7b-9ea0-3f830e0730e2.json b/oaitestdata/b2share-oai_dc/EUDAT_1/json/0f2134cd-c80a-5f7b-9ea0-3f830e0730e2.json
deleted file mode 100644
index 9ffca683..00000000
--- a/oaitestdata/b2share-oai_dc/EUDAT_1/json/0f2134cd-c80a-5f7b-9ea0-3f830e0730e2.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "http://b2share.eudat.eu"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://b2share.eudat.eu/api/oai2d?verb=GetRecord&metadataPrefix=marcxml&identifier=oai:b2share.eudat.eu:b2rec/c9bd5d7b6ffc48fe940e8f220e3dbab3",
-    "PID": "http://hdl.handle.net/11304/d043f756-57eb-11e5-9bb4-2b0aad496318",
-    "PublicationTimestamp": "2016-12-22T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "http://b2share.eudat.eu"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11304/d043f756-57eb-11e5-9bb4-2b0aad496318",
-        "https://b2share.eudat.eu/api/records/c9bd5d7b6ffc48fe940e8f220e3dbab3",
-        "oai:b2share.eudat.eu:b2rec/c9bd5d7b6ffc48fe940e8f220e3dbab3"
-    ],
-    "ResourceType": [
-        "Other"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/closedAccess"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/c9bd5d7b6ffc48fe940e8f220e3dbab3;2018-01-11T13:48:35Z;e9b9792e-79fb-4b07-b6b4-b9c2bd06d095;2016-12-22T10:21:29.742408+00:00;Test Image Private;http://hdl.handle.net/11304/d043f756-57eb-11e5-9bb4-2b0aad496318;https://b2share.eudat.eu/api/records/c9bd5d7b6ffc48fe940e8f220e3dbab3;oai:b2share.eudat.eu:b2rec/c9bd5d7b6ffc48fe940e8f220e3dbab3;en;http://b2share.eudat.eu;info:eu-repo/semantics/closedAccess;Test Image Private;Other",
-    "group": "b2share",
-    "groups": [
-        {
-            "name": "b2share"
-        }
-    ],
-    "name": "0f2134cd-c80a-5f7b-9ea0-3f830e0730e2",
-    "notes": [
-        "Test Image Private"
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/c9bd5d7b6ffc48fe940e8f220e3dbab3"
-    ],
-    "oai_set": [
-        "e9b9792e-79fb-4b07-b6b4-b9c2bd06d095"
-    ],
-    "state": "active",
-    "title": [
-        "Test Image Private"
-    ],
-    "url": "https://b2share.eudat.eu/api/records/c9bd5d7b6ffc48fe940e8f220e3dbab3"
-}
\ No newline at end of file
diff --git a/oaitestdata/b2share-oai_dc/EUDAT_1/json/0f708217-ad82-57a7-8c05-f71ae166295f.json b/oaitestdata/b2share-oai_dc/EUDAT_1/json/0f708217-ad82-57a7-8c05-f71ae166295f.json
deleted file mode 100644
index f2d54768..00000000
--- a/oaitestdata/b2share-oai_dc/EUDAT_1/json/0f708217-ad82-57a7-8c05-f71ae166295f.json
+++ /dev/null
@@ -1,42 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.23728/b2share.c5dbf769a2aa4fcc84ad3ba511669a6e",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://b2share.eudat.eu/api/oai2d?verb=GetRecord&metadataPrefix=marcxml&identifier=oai:b2share.eudat.eu:b2rec/c5dbf769a2aa4fcc84ad3ba511669a6e",
-    "PID": "http://hdl.handle.net/11304/2a56b2d8-d69f-43be-ad55-8edf39335b2e",
-    "PublicationTimestamp": "2019-04-30T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11304/2a56b2d8-d69f-43be-ad55-8edf39335b2e",
-        "10.23728/b2share.c5dbf769a2aa4fcc84ad3ba511669a6e",
-        "https://b2share.eudat.eu/api/records/c5dbf769a2aa4fcc84ad3ba511669a6e",
-        "oai:b2share.eudat.eu:b2rec/c5dbf769a2aa4fcc84ad3ba511669a6e"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/c5dbf769a2aa4fcc84ad3ba511669a6e;2019-04-30T15:35:17Z;e9b9792e-79fb-4b07-b6b4-b9c2bd06d095;2019-04-30T15:32:57.431779+00:00;test 2;http://hdl.handle.net/11304/2a56b2d8-d69f-43be-ad55-8edf39335b2e;10.23728/b2share.c5dbf769a2aa4fcc84ad3ba511669a6e;https://b2share.eudat.eu/api/records/c5dbf769a2aa4fcc84ad3ba511669a6e;oai:b2share.eudat.eu:b2rec/c5dbf769a2aa4fcc84ad3ba511669a6e;info:eu-repo/semantics/openAccess;Test ec-ecarth 3.3.1",
-    "group": "b2share",
-    "groups": [
-        {
-            "name": "b2share"
-        }
-    ],
-    "name": "0f708217-ad82-57a7-8c05-f71ae166295f",
-    "notes": [
-        "test 2"
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/c5dbf769a2aa4fcc84ad3ba511669a6e"
-    ],
-    "oai_set": [
-        "e9b9792e-79fb-4b07-b6b4-b9c2bd06d095"
-    ],
-    "state": "active",
-    "title": [
-        "Test ec-ecarth 3.3.1"
-    ],
-    "url": "https://b2share.eudat.eu/api/records/c5dbf769a2aa4fcc84ad3ba511669a6e"
-}
\ No newline at end of file
diff --git a/oaitestdata/b2share-oai_dc/EUDAT_1/json/0f97c857-d0b8-5d67-850e-78290ee8ff9d.json b/oaitestdata/b2share-oai_dc/EUDAT_1/json/0f97c857-d0b8-5d67-850e-78290ee8ff9d.json
deleted file mode 100644
index c610c07a..00000000
--- a/oaitestdata/b2share-oai_dc/EUDAT_1/json/0f97c857-d0b8-5d67-850e-78290ee8ff9d.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.23728/b2share.35123c2043e9405d9a2891f368dbec4e",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://b2share.eudat.eu/api/oai2d?verb=GetRecord&metadataPrefix=marcxml&identifier=oai:b2share.eudat.eu:b2rec/35123c2043e9405d9a2891f368dbec4e",
-    "PID": "http://hdl.handle.net/11304/2b0d5f91-f16d-4591-afd4-ee1bc87f062f",
-    "PublicationTimestamp": "2018-10-11T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11304/2b0d5f91-f16d-4591-afd4-ee1bc87f062f",
-        "10.23728/b2share.35123c2043e9405d9a2891f368dbec4e",
-        "https://b2share.eudat.eu/api/records/35123c2043e9405d9a2891f368dbec4e",
-        "oai:b2share.eudat.eu:b2rec/35123c2043e9405d9a2891f368dbec4e"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess",
-        "Public Domain Dedication (CC Zero)"
-    ],
-    "author": [
-        "Modsching, Norbert"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/35123c2043e9405d9a2891f368dbec4e;2018-10-11T11:54:11Z;e9b9792e-79fb-4b07-b6b4-b9c2bd06d095;Modsching, Norbert;2018-10-11T11:54:11.132926+00:00;Data sets of the experimental results that are published in the journal Optics Express in the paper \"Carrier-envelope offset frequency stabilization of a thin-disk laser oscillator operating in the strongly self-phase modulation broadened regime,\" N. Modsching, et. al. Uploaded data sets agree in the filename with the figure number and sub-figure letter of the publication (FigXx). Corresponding filenames with the extension \"metadata\" contain further information concerning the data set.;http://hdl.handle.net/11304/2b0d5f91-f16d-4591-afd4-ee1bc87f062f;10.23728/b2share.35123c2043e9405d9a2891f368dbec4e;https://b2share.eudat.eu/api/records/35123c2043e9405d9a2891f368dbec4e;oai:b2share.eudat.eu:b2rec/35123c2043e9405d9a2891f368dbec4e;info:eu-repo/semantics/openAccess;Public Domain Dedication (CC Zero);Mode-locked lasers; Laser stabilization; Lasers, pulsed; Ultrafast lasers; Lasers, ytterbium; Ultrafast technology.;Carrier-envelope offset frequency stabilization of a thin-disk laser oscillator operating in the strongly self-phase modulation broadened regime",
-    "group": "b2share",
-    "groups": [
-        {
-            "name": "b2share"
-        }
-    ],
-    "name": "0f97c857-d0b8-5d67-850e-78290ee8ff9d",
-    "notes": [
-        "Data sets of the experimental results that are published in the journal Optics Express in the paper \"Carrier-envelope offset frequency stabilization of a thin-disk laser oscillator operating in the strongly self-phase modulation broadened regime,\" N. Modsching, et. al. Uploaded data sets agree in the filename with the figure number and sub-figure letter of the publication (FigXx). Corresponding filenames with the extension \"metadata\" contain further information concerning the data set."
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/35123c2043e9405d9a2891f368dbec4e"
-    ],
-    "oai_set": [
-        "e9b9792e-79fb-4b07-b6b4-b9c2bd06d095"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Mode-locked lasers"
-        },
-        {
-            "name": "Laser stabilization"
-        },
-        {
-            "name": "Lasers"
-        },
-        {
-            "name": "pulsed"
-        },
-        {
-            "name": "Ultrafast lasers"
-        },
-        {
-            "name": "Lasers"
-        },
-        {
-            "name": "ytterbium"
-        },
-        {
-            "name": "Ultrafast technology."
-        }
-    ],
-    "title": [
-        "Carrier-envelope offset frequency stabilization of a thin-disk laser oscillator operating in the strongly self-phase modulation broadened regime"
-    ],
-    "url": "https://b2share.eudat.eu/api/records/35123c2043e9405d9a2891f368dbec4e"
-}
\ No newline at end of file
diff --git a/oaitestdata/b2share-oai_dc/EUDAT_1/json/0f9eb981-cdf8-5e5e-b247-0c185f6b2360.json b/oaitestdata/b2share-oai_dc/EUDAT_1/json/0f9eb981-cdf8-5e5e-b247-0c185f6b2360.json
deleted file mode 100644
index dac50b7d..00000000
--- a/oaitestdata/b2share-oai_dc/EUDAT_1/json/0f9eb981-cdf8-5e5e-b247-0c185f6b2360.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "PSNC"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://b2share.eudat.eu/api/oai2d?verb=GetRecord&metadataPrefix=marcxml&identifier=oai:b2share.eudat.eu:b2rec/22eeafc802fa4358b9efd151cb9a6829",
-    "PID": "http://hdl.handle.net/11304/3cc247e6-b335-11e3-8cd7-14feb57d12b9",
-    "PublicationTimestamp": "2016-12-22T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "PSNC"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11304/3cc247e6-b335-11e3-8cd7-14feb57d12b9",
-        "https://b2share.eudat.eu/api/records/22eeafc802fa4358b9efd151cb9a6829",
-        "oai:b2share.eudat.eu:b2rec/22eeafc802fa4358b9efd151cb9a6829"
-    ],
-    "ResourceType": [
-        "Other"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess",
-        "GPL"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/22eeafc802fa4358b9efd151cb9a6829;2018-01-11T13:47:54Z;e9b9792e-79fb-4b07-b6b4-b9c2bd06d095;2016-12-22T10:01:02.758515+00:00;Draft slides for EUDAT presentation on ISGC;http://hdl.handle.net/11304/3cc247e6-b335-11e3-8cd7-14feb57d12b9;https://b2share.eudat.eu/api/records/22eeafc802fa4358b9efd151cb9a6829;oai:b2share.eudat.eu:b2rec/22eeafc802fa4358b9efd151cb9a6829;en;PSNC;info:eu-repo/semantics/openAccess;GPL;Storae;iRODS;OBject storage;cloud storagte;EUDAT presentation on ISGC;Other",
-    "group": "b2share",
-    "groups": [
-        {
-            "name": "b2share"
-        }
-    ],
-    "name": "0f9eb981-cdf8-5e5e-b247-0c185f6b2360",
-    "notes": [
-        "Draft slides for EUDAT presentation on ISGC"
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/22eeafc802fa4358b9efd151cb9a6829"
-    ],
-    "oai_set": [
-        "e9b9792e-79fb-4b07-b6b4-b9c2bd06d095"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Storae"
-        },
-        {
-            "name": "iRODS"
-        },
-        {
-            "name": "OBject storage"
-        },
-        {
-            "name": "cloud storagte"
-        }
-    ],
-    "title": [
-        "EUDAT presentation on ISGC"
-    ],
-    "url": "https://b2share.eudat.eu/api/records/22eeafc802fa4358b9efd151cb9a6829"
-}
\ No newline at end of file
diff --git a/oaitestdata/b2share-oai_dc/EUDAT_1/json/1a146ad0-a8c0-5550-8d66-f1ce2d03731f.json b/oaitestdata/b2share-oai_dc/EUDAT_1/json/1a146ad0-a8c0-5550-8d66-f1ce2d03731f.json
deleted file mode 100644
index c9c9c5b3..00000000
--- a/oaitestdata/b2share-oai_dc/EUDAT_1/json/1a146ad0-a8c0-5550-8d66-f1ce2d03731f.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contributor": [
-        "Francesco De Gasperin",
-        "Tammo-Jan Dijkema",
-        "Andr\u00e9 Ren\u00e9 Offringa"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.23728/b2share.2e31b8df6ed642ff80da31c08e992a72",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://b2share.eudat.eu/api/oai2d?verb=GetRecord&metadataPrefix=marcxml&identifier=oai:b2share.eudat.eu:b2rec/2e31b8df6ed642ff80da31c08e992a72",
-    "PID": "http://hdl.handle.net/11304/df7156ea-e36c-4515-967b-4bbe962759e9",
-    "PublicationTimestamp": "2019-09-30T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11304/df7156ea-e36c-4515-967b-4bbe962759e9",
-        "10.23728/b2share.2e31b8df6ed642ff80da31c08e992a72",
-        "https://b2share.eudat.eu/api/records/2e31b8df6ed642ff80da31c08e992a72",
-        "oai:b2share.eudat.eu:b2rec/2e31b8df6ed642ff80da31c08e992a72"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess",
-        "GNU General Public License 3 (GPL-3.0)"
-    ],
-    "author": [
-        "Mechev, Alexandar",
-        "Sweijen, Frits"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/2e31b8df6ed642ff80da31c08e992a72;2019-09-30T13:14:08Z;e9b9792e-79fb-4b07-b6b4-b9c2bd06d095;Tammo-Jan Dijkema;Andr\u00e9 Ren\u00e9 Offringa;Francesco De Gasperin;Sweijen, Frits;Mechev, Alexandar;2019-09-30T13:14:08.392218+00:00;This Singularity image contains an install of LOFAR ${LOFAR_VERSION}. In order to run your pipelines, you may need to know where the software is installed. The root directory is /opt/lofar, with all software installed as follows:\n\n    * AOFlagger: $INSTALLDIR/aoflagger\n    * Casacore: $INSTALLDIR/casacore\n    * Dysco: $INSTALLDIR/dysco\n    * LOFAR: $INSTALLDIR/lofar\n    * LoSoTo: $INSTALLDIR/losoto\n    * PyBDSF: $INSTALLDIR/pybdsf\n    * RMextract: $INSTALLDIR/RMextract\n\n    To execute a command, use\n        singularity exec -B <paths,that,need,to,be,accessible> <path to image> <command> <arguments>\n    for example:\n        #singularity exec lofar.simg genericpipeline.py -d -c pipeline.cfg pipeline.parset\n \n\nAll packages located in /opt/lofar ;http://hdl.handle.net/11304/df7156ea-e36c-4515-967b-4bbe962759e9;10.23728/b2share.2e31b8df6ed642ff80da31c08e992a72;https://b2share.eudat.eu/api/records/2e31b8df6ed642ff80da31c08e992a72;oai:b2share.eudat.eu:b2rec/2e31b8df6ed642ff80da31c08e992a72;eng;info:eu-repo/semantics/openAccess;GNU General Public License 3 (GPL-3.0);LOFAR;Radio Astronomical Software;LOFAR SKSP Software Image",
-    "group": "b2share",
-    "groups": [
-        {
-            "name": "b2share"
-        }
-    ],
-    "name": "1a146ad0-a8c0-5550-8d66-f1ce2d03731f",
-    "notes": [
-        "This Singularity image contains an install of LOFAR ${LOFAR_VERSION}. In order to run your pipelines, you may need to know where the software is installed. The root directory is /opt/lofar, with all software installed as follows:\n\n    * AOFlagger: $INSTALLDIR/aoflagger\n    * Casacore: $INSTALLDIR/casacore\n    * Dysco: $INSTALLDIR/dysco\n    * LOFAR: $INSTALLDIR/lofar\n    * LoSoTo: $INSTALLDIR/losoto\n    * PyBDSF: $INSTALLDIR/pybdsf\n    * RMextract: $INSTALLDIR/RMextract\n\n    To execute a command, use\n        singularity exec -B <paths,that,need,to,be,accessible> <path to image> <command> <arguments>\n    for example:\n        #singularity exec lofar.simg genericpipeline.py -d -c pipeline.cfg pipeline.parset\n \n\nAll packages located in /opt/lofar "
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/2e31b8df6ed642ff80da31c08e992a72"
-    ],
-    "oai_set": [
-        "e9b9792e-79fb-4b07-b6b4-b9c2bd06d095"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "LOFAR"
-        },
-        {
-            "name": "Radio Astronomical Software"
-        }
-    ],
-    "title": [
-        "LOFAR SKSP Software Image"
-    ],
-    "url": "https://b2share.eudat.eu/api/records/2e31b8df6ed642ff80da31c08e992a72"
-}
\ No newline at end of file
diff --git a/oaitestdata/b2share-oai_dc/EUDAT_1/json/1ae36cab-0e8a-5f78-bf9f-706b6a8c55ea.json b/oaitestdata/b2share-oai_dc/EUDAT_1/json/1ae36cab-0e8a-5f78-bf9f-706b6a8c55ea.json
deleted file mode 100644
index 434cf3db..00000000
--- a/oaitestdata/b2share-oai_dc/EUDAT_1/json/1ae36cab-0e8a-5f78-bf9f-706b6a8c55ea.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.23728/b2share.811d90e661534996a18f6bca9169abed",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://b2share.eudat.eu/api/oai2d?verb=GetRecord&metadataPrefix=marcxml&identifier=oai:b2share.eudat.eu:b2rec/811d90e661534996a18f6bca9169abed",
-    "PID": "http://hdl.handle.net/11304/7ea0e729-d497-4501-a50d-dda0e2b27959",
-    "PublicationTimestamp": "2019-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11304/7ea0e729-d497-4501-a50d-dda0e2b27959",
-        "10.23728/b2share.811d90e661534996a18f6bca9169abed",
-        "https://b2share.eudat.eu/api/records/811d90e661534996a18f6bca9169abed",
-        "oai:b2share.eudat.eu:b2rec/811d90e661534996a18f6bca9169abed"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Jones, Michael G."
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/811d90e661534996a18f6bca9169abed;2019-05-30T14:18:07Z;e9b9792e-79fb-4b07-b6b4-b9c2bd06d095;Jones, Michael G.;2019-05-30T14:18:07.600746+00:00;The VLA D and C array data of HCG 16 were collected by the Very Large Array (http://www.vla.nrao.edu/) in 1989 and 1999, under PI projects of Jacqueline van Gorkom and Marcus Verheijen. The project numbers are AW234 and AW500 respectively. The full original data of these projects are hosted by the VLA Archive (https://science.nrao.edu/facilities/vla/archive/index). This archive also includes a source mask to be used when CLEANing the HI line emission from the group and a separate mask identifying the region corresponding to each feature discussed in the coming paper Jones et al. (in prep.).;http://hdl.handle.net/11304/7ea0e729-d497-4501-a50d-dda0e2b27959;10.23728/b2share.811d90e661534996a18f6bca9169abed;https://b2share.eudat.eu/api/records/811d90e661534996a18f6bca9169abed;oai:b2share.eudat.eu:b2rec/811d90e661534996a18f6bca9169abed;info:eu-repo/semantics/openAccess;VLA;HCG 16;HCG16 L-band VLA C+D array data",
-    "group": "b2share",
-    "groups": [
-        {
-            "name": "b2share"
-        }
-    ],
-    "name": "1ae36cab-0e8a-5f78-bf9f-706b6a8c55ea",
-    "notes": [
-        "The VLA D and C array data of HCG 16 were collected by the Very Large Array (http://www.vla.nrao.edu/) in 1989 and 1999, under PI projects of Jacqueline van Gorkom and Marcus Verheijen. The project numbers are AW234 and AW500 respectively. The full original data of these projects are hosted by the VLA Archive (https://science.nrao.edu/facilities/vla/archive/index). This archive also includes a source mask to be used when CLEANing the HI line emission from the group and a separate mask identifying the region corresponding to each feature discussed in the coming paper Jones et al. (in prep.)."
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/811d90e661534996a18f6bca9169abed"
-    ],
-    "oai_set": [
-        "e9b9792e-79fb-4b07-b6b4-b9c2bd06d095"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "VLA"
-        },
-        {
-            "name": "HCG"
-        }
-    ],
-    "title": [
-        "HCG16 L-band VLA C+D array data"
-    ],
-    "url": "https://b2share.eudat.eu/api/records/811d90e661534996a18f6bca9169abed"
-}
\ No newline at end of file
diff --git a/oaitestdata/b2share-oai_dc/EUDAT_1/json/1af09218-a99f-5f39-8004-7e866d4a05e3.json b/oaitestdata/b2share-oai_dc/EUDAT_1/json/1af09218-a99f-5f39-8004-7e866d4a05e3.json
deleted file mode 100644
index 1a0c4b5b..00000000
--- a/oaitestdata/b2share-oai_dc/EUDAT_1/json/1af09218-a99f-5f39-8004-7e866d4a05e3.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "https://b2share.eudat.eu"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://b2share.eudat.eu/api/oai2d?verb=GetRecord&metadataPrefix=marcxml&identifier=oai:b2share.eudat.eu:b2rec/0dab599f53174f76915f3a66f057ed83",
-    "PID": "http://hdl.handle.net/11304/a8e55fd8-d52d-11e4-ac7e-860aa0063d1f",
-    "PublicationTimestamp": "2016-12-22T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "https://b2share.eudat.eu"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11304/a8e55fd8-d52d-11e4-ac7e-860aa0063d1f",
-        "https://b2share.eudat.eu/api/records/0dab599f53174f76915f3a66f057ed83",
-        "oai:b2share.eudat.eu:b2rec/0dab599f53174f76915f3a66f057ed83"
-    ],
-    "ResourceType": [
-        "Other"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/0dab599f53174f76915f3a66f057ed83;2018-01-11T13:48:15Z;e9b9792e-79fb-4b07-b6b4-b9c2bd06d095;2016-12-22T10:13:39.726381+00:00;TraIT PID workshop;http://hdl.handle.net/11304/a8e55fd8-d52d-11e4-ac7e-860aa0063d1f;https://b2share.eudat.eu/api/records/0dab599f53174f76915f3a66f057ed83;oai:b2share.eudat.eu:b2rec/0dab599f53174f76915f3a66f057ed83;en;https://b2share.eudat.eu;info:eu-repo/semantics/openAccess;TraIT PID workshop;Other",
-    "group": "b2share",
-    "groups": [
-        {
-            "name": "b2share"
-        }
-    ],
-    "name": "1af09218-a99f-5f39-8004-7e866d4a05e3",
-    "notes": [
-        "TraIT PID workshop"
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/0dab599f53174f76915f3a66f057ed83"
-    ],
-    "oai_set": [
-        "e9b9792e-79fb-4b07-b6b4-b9c2bd06d095"
-    ],
-    "state": "active",
-    "title": [
-        "TraIT PID workshop"
-    ],
-    "url": "https://b2share.eudat.eu/api/records/0dab599f53174f76915f3a66f057ed83"
-}
\ No newline at end of file
diff --git a/oaitestdata/b2share-oai_dc/EUDAT_1/json/1b8a6462-3e97-5be5-bced-22d0ecc32bb9.json b/oaitestdata/b2share-oai_dc/EUDAT_1/json/1b8a6462-3e97-5be5-bced-22d0ecc32bb9.json
deleted file mode 100644
index da942ebe..00000000
--- a/oaitestdata/b2share-oai_dc/EUDAT_1/json/1b8a6462-3e97-5be5-bced-22d0ecc32bb9.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "http://b2share.eudat.eu"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://b2share.eudat.eu/api/oai2d?verb=GetRecord&metadataPrefix=marcxml&identifier=oai:b2share.eudat.eu:b2rec/8913da0e5c934eb8b924e7b33bb4ec7f",
-    "PID": "http://hdl.handle.net/11304/1aab3df4-f3ce-11e4-ac7e-860aa0063d1f",
-    "PublicationTimestamp": "2016-12-22T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "http://b2share.eudat.eu"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11304/1aab3df4-f3ce-11e4-ac7e-860aa0063d1f",
-        "https://b2share.eudat.eu/api/records/8913da0e5c934eb8b924e7b33bb4ec7f",
-        "oai:b2share.eudat.eu:b2rec/8913da0e5c934eb8b924e7b33bb4ec7f"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess",
-        "Creative Commons Attribution (CC-BY)"
-    ],
-    "author": [
-        "Herman Stehouwer, Peter Wittenburg"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/8913da0e5c934eb8b924e7b33bb4ec7f;2018-01-11T13:48:18Z;e9b9792e-79fb-4b07-b6b4-b9c2bd06d095;Herman Stehouwer, Peter Wittenburg;2016-12-22T10:14:24.598038+00:00;Various initiatives and organisations formulated principles for how to deal with data to improve data sharing and re-use. This document compared a number of such principles and found that we all share the same core principles. ;http://hdl.handle.net/11304/1aab3df4-f3ce-11e4-ac7e-860aa0063d1f;https://b2share.eudat.eu/api/records/8913da0e5c934eb8b924e7b33bb4ec7f;oai:b2share.eudat.eu:b2rec/8913da0e5c934eb8b924e7b33bb4ec7f;en;http://b2share.eudat.eu;info:eu-repo/semantics/openAccess;Creative Commons Attribution (CC-BY);Data Principles;Data SHaring;Data Re-Use;Data Science;Principles for Data Sharing and Re-use: are they all the same?;Text",
-    "group": "b2share",
-    "groups": [
-        {
-            "name": "b2share"
-        }
-    ],
-    "name": "1b8a6462-3e97-5be5-bced-22d0ecc32bb9",
-    "notes": [
-        "Various initiatives and organisations formulated principles for how to deal with data to improve data sharing and re-use. This document compared a number of such principles and found that we all share the same core principles. "
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/8913da0e5c934eb8b924e7b33bb4ec7f"
-    ],
-    "oai_set": [
-        "e9b9792e-79fb-4b07-b6b4-b9c2bd06d095"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Data Principles"
-        },
-        {
-            "name": "Data SHaring"
-        },
-        {
-            "name": "Data Re-Use"
-        },
-        {
-            "name": "Data Science"
-        }
-    ],
-    "title": [
-        "Principles for Data Sharing and Re-use: are they all the same?"
-    ],
-    "url": "https://b2share.eudat.eu/api/records/8913da0e5c934eb8b924e7b33bb4ec7f"
-}
\ No newline at end of file
diff --git a/oaitestdata/b2share-oai_dc/EUDAT_1/json/1bb36b50-373e-5a0e-8aa3-2723527aa990.json b/oaitestdata/b2share-oai_dc/EUDAT_1/json/1bb36b50-373e-5a0e-8aa3-2723527aa990.json
deleted file mode 100644
index 345fe874..00000000
--- a/oaitestdata/b2share-oai_dc/EUDAT_1/json/1bb36b50-373e-5a0e-8aa3-2723527aa990.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "https://b2share.eudat.eu"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://b2share.eudat.eu/api/oai2d?verb=GetRecord&metadataPrefix=marcxml&identifier=oai:b2share.eudat.eu:b2rec/25b1dbfff95d411ca325e4de6a9e7867",
-    "PID": "http://hdl.handle.net/11304/135eb282-ad16-11e4-ac7e-860aa0063d1f",
-    "PublicationTimestamp": "2016-12-22T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "https://b2share.eudat.eu"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11304/135eb282-ad16-11e4-ac7e-860aa0063d1f",
-        "https://b2share.eudat.eu/api/records/25b1dbfff95d411ca325e4de6a9e7867",
-        "oai:b2share.eudat.eu:b2rec/25b1dbfff95d411ca325e4de6a9e7867"
-    ],
-    "ResourceType": [
-        "Other"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess",
-        "GNU General Public License 3 (GPL-3.0)"
-    ],
-    "author": [
-        "St\u00e9phane COUTIN"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/25b1dbfff95d411ca325e4de6a9e7867;2018-01-11T13:48:12Z;e9b9792e-79fb-4b07-b6b4-b9c2bd06d095;St\u00e9phane COUTIN;2016-12-22T10:11:18.594471+00:00;B2SAFE repository package is a set of software application and components. It provides an easy to deploy interface for a data repository to replicate its data objects into EUDAT B2SAFE.\nIn the zip file, you will find the runnable jar program and the product documentation.\nSome further information and the source files are available on github at http://eudat-b2safe.github.io/B2SAFE-repository-package/;http://hdl.handle.net/11304/135eb282-ad16-11e4-ac7e-860aa0063d1f;https://b2share.eudat.eu/api/records/25b1dbfff95d411ca325e4de6a9e7867;oai:b2share.eudat.eu:b2rec/25b1dbfff95d411ca325e4de6a9e7867;en;https://b2share.eudat.eu;info:eu-repo/semantics/openAccess;GNU General Public License 3 (GPL-3.0);B2SAFE;software;interface;repository package;B2SAFE repository package client application;Other",
-    "group": "b2share",
-    "groups": [
-        {
-            "name": "b2share"
-        }
-    ],
-    "name": "1bb36b50-373e-5a0e-8aa3-2723527aa990",
-    "notes": [
-        "B2SAFE repository package is a set of software application and components. It provides an easy to deploy interface for a data repository to replicate its data objects into EUDAT B2SAFE.\nIn the zip file, you will find the runnable jar program and the product documentation.\nSome further information and the source files are available on github at http://eudat-b2safe.github.io/B2SAFE-repository-package/"
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/25b1dbfff95d411ca325e4de6a9e7867"
-    ],
-    "oai_set": [
-        "e9b9792e-79fb-4b07-b6b4-b9c2bd06d095"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "BSAFE"
-        },
-        {
-            "name": "software"
-        },
-        {
-            "name": "interface"
-        },
-        {
-            "name": "repository package"
-        }
-    ],
-    "title": [
-        "B2SAFE repository package client application"
-    ],
-    "url": "https://b2share.eudat.eu/api/records/25b1dbfff95d411ca325e4de6a9e7867"
-}
\ No newline at end of file
diff --git a/oaitestdata/b2share-oai_dc/EUDAT_1/json/1bcf112e-4c14-5310-b10d-ca25c3e4f641.json b/oaitestdata/b2share-oai_dc/EUDAT_1/json/1bcf112e-4c14-5310-b10d-ca25c3e4f641.json
deleted file mode 100644
index cd66f457..00000000
--- a/oaitestdata/b2share-oai_dc/EUDAT_1/json/1bcf112e-4c14-5310-b10d-ca25c3e4f641.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "Contact": [
-        "http://b2share.eudat.eu"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://b2share.eudat.eu/api/oai2d?verb=GetRecord&metadataPrefix=marcxml&identifier=oai:b2share.eudat.eu:b2rec/77c14a35ef924a9aa644fcab7d7c6dc9",
-    "PID": "http://hdl.handle.net/11304/376e3386-e42a-11e5-9bb4-2b0aad496318",
-    "PublicationTimestamp": "2016-12-22T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "http://b2share.eudat.eu"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11304/376e3386-e42a-11e5-9bb4-2b0aad496318",
-        "https://b2share.eudat.eu/api/records/77c14a35ef924a9aa644fcab7d7c6dc9",
-        "oai:b2share.eudat.eu:b2rec/77c14a35ef924a9aa644fcab7d7c6dc9"
-    ],
-    "ResourceType": [
-        "Other"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/77c14a35ef924a9aa644fcab7d7c6dc9;2018-01-11T13:49:00Z;e9b9792e-79fb-4b07-b6b4-b9c2bd06d095;2016-12-22T10:25:45.254987+00:00;NETDB;http://hdl.handle.net/11304/376e3386-e42a-11e5-9bb4-2b0aad496318;https://b2share.eudat.eu/api/records/77c14a35ef924a9aa644fcab7d7c6dc9;oai:b2share.eudat.eu:b2rec/77c14a35ef924a9aa644fcab7d7c6dc9;en;http://b2share.eudat.eu;info:eu-repo/semantics/openAccess;NETDB;NETDB;Other",
-    "group": "b2share",
-    "groups": [
-        {
-            "name": "b2share"
-        }
-    ],
-    "name": "1bcf112e-4c14-5310-b10d-ca25c3e4f641",
-    "notes": [
-        "NETDB"
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/77c14a35ef924a9aa644fcab7d7c6dc9"
-    ],
-    "oai_set": [
-        "e9b9792e-79fb-4b07-b6b4-b9c2bd06d095"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "NETDB"
-        }
-    ],
-    "title": [
-        "NETDB"
-    ],
-    "url": "https://b2share.eudat.eu/api/records/77c14a35ef924a9aa644fcab7d7c6dc9"
-}
\ No newline at end of file
diff --git a/oaitestdata/b2share-oai_dc/EUDAT_1/json/1c3ae077-3c50-583b-a89a-f37fecd0c1ee.json b/oaitestdata/b2share-oai_dc/EUDAT_1/json/1c3ae077-3c50-583b-a89a-f37fecd0c1ee.json
deleted file mode 100644
index aa723d3b..00000000
--- a/oaitestdata/b2share-oai_dc/EUDAT_1/json/1c3ae077-3c50-583b-a89a-f37fecd0c1ee.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.23728/b2share.8b49a31f0faa4f479f8263db8382d531",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://b2share.eudat.eu/api/oai2d?verb=GetRecord&metadataPrefix=marcxml&identifier=oai:b2share.eudat.eu:b2rec/8b49a31f0faa4f479f8263db8382d531",
-    "PID": "http://hdl.handle.net/11304/7117c31b-ea35-437a-949a-4765c43f149d",
-    "PublicationTimestamp": "2017-02-13T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11304/7117c31b-ea35-437a-949a-4765c43f149d",
-        "10.23728/b2share.8b49a31f0faa4f479f8263db8382d531",
-        "https://b2share.eudat.eu/api/records/8b49a31f0faa4f479f8263db8382d531",
-        "oai:b2share.eudat.eu:b2rec/8b49a31f0faa4f479f8263db8382d531"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess",
-        "Creative Commons Attribution-NonCommercial-ShareAlike (CC-BY-NC-SA)"
-    ],
-    "author": [
-        "Kaliontzopoulos Panos"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/8b49a31f0faa4f479f8263db8382d531;2018-01-11T13:50:00Z;e9b9792e-79fb-4b07-b6b4-b9c2bd06d095;Kaliontzopoulos Panos;2017-02-13T08:11:12.362766+00:00;Second edition with more than 31.000 terms;http://hdl.handle.net/11304/7117c31b-ea35-437a-949a-4765c43f149d;10.23728/b2share.8b49a31f0faa4f479f8263db8382d531;https://b2share.eudat.eu/api/records/8b49a31f0faa4f479f8263db8382d531;oai:b2share.eudat.eu:b2rec/8b49a31f0faa4f479f8263db8382d531;info:eu-repo/semantics/openAccess;Creative Commons Attribution-NonCommercial-ShareAlike (CC-BY-NC-SA);Lexicon, English-Greek, Dictionary ;English-Greek Lexicon of Electronics",
-    "group": "b2share",
-    "groups": [
-        {
-            "name": "b2share"
-        }
-    ],
-    "name": "1c3ae077-3c50-583b-a89a-f37fecd0c1ee",
-    "notes": [
-        "Second edition with more than 31.000 terms"
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/8b49a31f0faa4f479f8263db8382d531"
-    ],
-    "oai_set": [
-        "e9b9792e-79fb-4b07-b6b4-b9c2bd06d095"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Lexicon"
-        },
-        {
-            "name": "English-Greek"
-        },
-        {
-            "name": "Dictionary"
-        }
-    ],
-    "title": [
-        "English-Greek Lexicon of Electronics"
-    ],
-    "url": "https://b2share.eudat.eu/api/records/8b49a31f0faa4f479f8263db8382d531"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/00061623-1f08-55b6-aa33-648131abd691.json b/oaitestdata/clarin-oai_dc/SET_1/json/00061623-1f08-55b6-aa33-648131abd691.json
deleted file mode 100644
index 58b9fe1f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/00061623-1f08-55b6-aa33-648131abd691.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Emilia"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/244",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/244"
-    ],
-    "PID": "http://hdl.handle.net/11321/244",
-    "PublicationTimestamp": "2016-01-31T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Emilia"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Ka, Emilia"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/244;2016-01-31T17:44:28Z;hdl_11321_3;hdl_11321_4;Teksty reklam TVP ABC ver.3;Ka, Emilia;reklama;kompletny korpus;2016-01-31;corpus;http://hdl.handle.net/11321/244;pol;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;text/plain; charset=utf-8;text/plain;downloadable_files_count: 1;Emilia",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "00061623-1f08-55b6-aa33-648131abd691",
-    "notes": [
-        "kompletny korpus"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/244"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "reklama"
-        }
-    ],
-    "title": [
-        "Teksty reklam TVP ABC ver.3"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/00187d97-dee9-5004-b338-8902c53ba44f.json b/oaitestdata/clarin-oai_dc/SET_1/json/00187d97-dee9-5004-b338-8902c53ba44f.json
deleted file mode 100644
index 8f97df9c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/00187d97-dee9-5004-b338-8902c53ba44f.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3983",
-    "MetadataAccess": [
-        "oai:ota:oucs:3983"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "O'Hara, Kane, 1714?-1782."
-    ],
-    "fulltext": "oai:ota:oucs:3983;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3983.xml;The golden pippin: an English burletta, in three acts. As it is performed at the Theatre-Royal, Covent-Garden. By the author of Midas.;O'Hara, Kane, 1714?-1782.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "00187d97-dee9-5004-b338-8902c53ba44f",
-    "oai_identifier": [
-        "oai:ota:oucs:3983"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The golden pippin: an English burletta, in three acts. As it is performed at the Theatre-Royal, Covent-Garden. By the author of Midas."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3983.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/003024ea-b1a5-528a-a702-9d5ba8aef809.json b/oaitestdata/clarin-oai_dc/SET_1/json/003024ea-b1a5-528a-a702-9d5ba8aef809.json
deleted file mode 100644
index 9107e138..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/003024ea-b1a5-528a-a702-9d5ba8aef809.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Craig, Hugh"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(2 files : ca. 194, 3 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2069",
-    "MetadataAccess": [
-        "oai:ota:oucs:2069"
-    ],
-    "PublicationTimestamp": "1611-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1611"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Jonson, Ben, 1573?-1637"
-    ],
-    "fulltext": "oai:ota:oucs:2069;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/2069.xml;Catiline [1611] / Ben Jonson;Jonson, Ben, 1573?-1637;1611;text_and_corpus_linguistics;English drama -- 17th century;Oxford Text Archive, University of Oxford;Craig, Hugh;text/sgml;(2 files : ca. 194, 3 KB);Text;Plays;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "003024ea-b1a5-528a-a702-9d5ba8aef809",
-    "oai_identifier": [
-        "oai:ota:oucs:2069"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- th century"
-        }
-    ],
-    "title": [
-        "Catiline [1611] / Ben Jonson"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2069.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/004f4f45-5b3f-5f8d-b24b-65b8cb3a81ae.json b/oaitestdata/clarin-oai_dc/SET_1/json/004f4f45-5b3f-5f8d-b24b-65b8cb3a81ae.json
deleted file mode 100644
index 229051d0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/004f4f45-5b3f-5f8d-b24b-65b8cb3a81ae.json
+++ /dev/null
@@ -1,49 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4498",
-    "MetadataAccess": [
-        "oai:ota:oucs:4498"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:4498;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4498.xml;A farther argument against ennobling foreigners, in answer to the two parts of the State anatomy: with a short account of the anatomizer;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "004f4f45-5b3f-5f8d-b24b-65b8cb3a81ae",
-    "oai_identifier": [
-        "oai:ota:oucs:4498"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A farther argument against ennobling foreigners, in answer to the two parts of the State anatomy: with a short account of the anatomizer"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4498.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/005dd870-0274-54c1-a48e-64087ea20432.json b/oaitestdata/clarin-oai_dc/SET_1/json/005dd870-0274-54c1-a48e-64087ea20432.json
deleted file mode 100644
index 4ed4a74f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/005dd870-0274-54c1-a48e-64087ea20432.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4805",
-    "MetadataAccess": [
-        "oai:ota:oucs:4805"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Donovan, E. (Edward), 1768-1837."
-    ],
-    "fulltext": "oai:ota:oucs:4805;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4805.xml;The natural history of British insects: explaining them in their several states, with the periods of their transformations, their food, \u00c5\u0093conomy, &c. Together with the history of such minute insects as require investigation by the microscope. The whole illustrated by coloured figures, ... By E. Donovan. [pt.5];Donovan, E. (Edward), 1768-1837.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "005dd870-0274-54c1-a48e-64087ea20432",
-    "oai_identifier": [
-        "oai:ota:oucs:4805"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The natural history of British insects: explaining them in their several states, with the periods of their transformations, their food, \u00c5\u0093conomy, &c. Together with the history of such minute insects as require investigation by the microscope. The whole illustrated by coloured figures, ... By E. Donovan. [pt.5]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4805.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0079bb6c-fbf3-5221-a41e-43c2744d5127.json b/oaitestdata/clarin-oai_dc/SET_1/json/0079bb6c-fbf3-5221-a41e-43c2744d5127.json
deleted file mode 100644
index f36f63d9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0079bb6c-fbf3-5221-a41e-43c2744d5127.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/7",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/7"
-    ],
-    "PID": "http://hdl.handle.net/10794/7",
-    "PublicationTimestamp": "2012-07-04T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/7;2017-10-27T16:36:05Z;hdl_10794_1;hdl_10794_2;8 SIDOR (2017-10-16);8 SIDOR (2017-10-16);n/a, n/a;Swedish;Corpus;News;News articles from 8 SIDOR. The material is sentence scrambled.;Nyhetsartiklar fr\u00e5n 8 SIDOR. Materialet \u00e4r meningsomkastat.;2012-07-04;corpus;http://hdl.handle.net/10794/7;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/attasidor",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0079bb6c-fbf3-5221-a41e-43c2744d5127",
-    "notes": [
-        "News articles from 8 SIDOR. The material is sentence scrambled.",
-        "Nyhetsartiklar fr\u00e5n 8 SIDOR. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/7"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Corpus"
-        },
-        {
-            "name": "News"
-        }
-    ],
-    "title": [
-        "8 SIDOR (2017-10-16)",
-        "8 SIDOR (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/007d1ca7-22b7-572f-9222-c700224ec926.json b/oaitestdata/clarin-oai_dc/SET_1/json/007d1ca7-22b7-572f-9222-c700224ec926.json
deleted file mode 100644
index 6d001fab..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/007d1ca7-22b7-572f-9222-c700224ec926.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Kaczkowski"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/104",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/104"
-    ],
-    "PID": "http://hdl.handle.net/11321/104",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Kaczkowski"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Kaczkowski, Kaczkowski"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/104;2015-04-08T14:07:02Z;hdl_11321_3;hdl_11321_4;MWE Kaczkowski, Olbrachtowi Rycerze, Tom 1;Kaczkowski, Kaczkowski;Kaczkowski;2015-04-08;corpus;http://hdl.handle.net/11321/104;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain; charset=utf-8;downloadable_files_count: 1;Kaczkowski",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "007d1ca7-22b7-572f-9222-c700224ec926",
-    "notes": [
-        "Kaczkowski"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/104"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Kaczkowski, Olbrachtowi Rycerze, Tom 1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0081e8da-9027-57ab-b893-19e95f2d4ac1.json b/oaitestdata/clarin-oai_dc/SET_1/json/0081e8da-9027-57ab-b893-19e95f2d4ac1.json
deleted file mode 100644
index b40ea798..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0081e8da-9027-57ab-b893-19e95f2d4ac1.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1468",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1468"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1468",
-    "PublicationTimestamp": "2015-02-05T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "The MIT License (MIT)",
-        "http://opensource.org/licenses/mit-license.php",
-        "PUB"
-    ],
-    "author": [
-        "Kamocki, Pawel",
-        "Sedl\u00e1k, Michal",
-        "Stra\u0148\u00e1k, Pavel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1468;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Public License Selector;Sedl\u00e1k, Michal;Stra\u0148\u00e1k, Pavel;Kamocki, Pawel;Legal;Licensing;Customizable tool that will help user select the right open license for his data or software;2015-02-05;toolService;http://hdl.handle.net/11234/1-1468;eng;The MIT License (MIT);http://opensource.org/licenses/mit-license.php;PUB;application/zip;application/zip;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://github.com/ufal/public-license-selector",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0081e8da-9027-57ab-b893-19e95f2d4ac1",
-    "notes": [
-        "Customizable tool that will help user select the right open license for his data or software"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1468"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Legal"
-        },
-        {
-            "name": "Licensing"
-        }
-    ],
-    "title": [
-        "Public License Selector"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0084548c-69fc-5990-aaa3-5b01b3c12c53.json b/oaitestdata/clarin-oai_dc/SET_1/json/0084548c-69fc-5990-aaa3-5b01b3c12c53.json
deleted file mode 100644
index a46cb4c1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0084548c-69fc-5990-aaa3-5b01b3c12c53.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Fondazione Bruno Kessler, Trento, Italy"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2133",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2133"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2133",
-    "PublicationTimestamp": "2017-04-10T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Fondazione Bruno Kessler, Trento, Italy"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "AGREEMENT ON THE USE OF DATA IN QT21 APE Task",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21",
-        "PUB"
-    ],
-    "author": [
-        "Turchi, Marco",
-        "Chatterjee, Rajen",
-        "Negri, Matteo"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2133;2017-09-04T10:30:19Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Test Data EN-DE APE Shared Task WMT17;Turchi, Marco;Chatterjee, Rajen;Negri, Matteo;machine translation;shared task;automatic post-editing;post-editing;Test data for the WMT 2017 Automatic post-editing task (the same used for the Sentence-level Quality Estimation task). They consist in 2,000 English-German pairs (source and target) belonging to the IT domain and already tokenized. All data is provided by the EU project QT21 (http://www.qt21.eu/).;2017-04-10;corpus;http://hdl.handle.net/11372/LRT-2133;eng;dne;AGREEMENT ON THE USE OF DATA IN QT21 APE Task;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Fondazione Bruno Kessler, Trento, Italy;http://www.statmt.org/wmt17/ape-task.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0084548c-69fc-5990-aaa3-5b01b3c12c53",
-    "notes": [
-        "Test data for the WMT 2017 Automatic post-editing task (the same used for the Sentence-level Quality Estimation task). They consist in 2,000 English-German pairs (source and target) belonging to the IT domain and already tokenized. All data is provided by the EU project QT21 (http://www.qt21.eu/)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2133"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "shared task"
-        },
-        {
-            "name": "automatic post-editing"
-        },
-        {
-            "name": "post-editing"
-        }
-    ],
-    "title": [
-        "Test Data EN-DE APE Shared Task WMT17"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/00902046-63df-5a85-beda-e40ec4918798.json b/oaitestdata/clarin-oai_dc/SET_1/json/00902046-63df-5a85-beda-e40ec4918798.json
deleted file mode 100644
index 39a36e94..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/00902046-63df-5a85-beda-e40ec4918798.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contributor": [
-        "McLaughlin, Jamie",
-        "Hu, Xiaoling"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/xml"
-    ],
-    "Language": [
-        "Chinese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-898",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-898"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-898",
-    "PublicationTimestamp": "2007-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2007"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-898;2016-04-06T16:39:56Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Sheffield Corpus of Chinese;Hu, Xiaoling;McLaughlin, Jamie;A diachronic corpus consisting of a wide range of fully marked-up Chinese historical texts together with an integral search and analysis tool;2007;corpus;http://hdl.handle.net/11372/LRT-898;zho;application/xml;downloadable_files_count: 0;United Kingdom;http://www.hrionline.ac.uk/scc/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "00902046-63df-5a85-beda-e40ec4918798",
-    "notes": [
-        "A diachronic corpus consisting of a wide range of fully marked-up Chinese historical texts together with an integral search and analysis tool"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-898"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Sheffield Corpus of Chinese"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0096e694-6df9-5dd7-8b6c-406ae07bf14e.json b/oaitestdata/clarin-oai_dc/SET_1/json/0096e694-6df9-5dd7-8b6c-406ae07bf14e.json
deleted file mode 100644
index 56143bb1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0096e694-6df9-5dd7-8b6c-406ae07bf14e.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=87ad7ad4bc9f11e1a404080027e73ea27860c02e583d40aeb9144efe5f25206a",
-    "MetadataAccess": [
-        "87ad7ad4bc9f11e1a404080027e73ea27860c02e583d40aeb9144efe5f25206a"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "87ad7ad4bc9f11e1a404080027e73ea27860c02e583d40aeb9144efe5f25206a;2018-11-15T16:39:25Z;toolService;toolService:tool;UIMA/U-Compare Apertium Morphological Analyser ;This tool performs tokenization of text and assigns all possible morphological analyses to each token. These analyses include the base form of the token, part-of-speech, information about number and gender. The morphological analyser is a module of Apertium machine translation system. The provided tool can currently operate on a subset of the languages that are supported by the Apertium system, namely:  English, Spanish, Calatan, Galician, Portuguese, Romanian and Basque.  The tool is provided as a UIMA  component, specifically as Java archive (jar) file, which can be incorporated within any UIMA workflow. However, it is particularly designed use in the U-Compare text mining platform (see separate META-SHARE record), since the types of annotations it produces are compliant with the U-Compare. \n;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0096e694-6df9-5dd7-8b6c-406ae07bf14e",
-    "notes": [
-        "This tool performs tokenization of text and assigns all possible morphological analyses to each token. These analyses include the base form of the token, part-of-speech, information about number and gender. The morphological analyser is a module of Apertium machine translation system. The provided tool can currently operate on a subset of the languages that are supported by the Apertium system, namely:  English, Spanish, Calatan, Galician, Portuguese, Romanian and Basque.  The tool is provided as a UIMA  component, specifically as Java archive (jar) file, which can be incorporated within any UIMA workflow. However, it is particularly designed use in the U-Compare text mining platform (see separate META-SHARE record), since the types of annotations it produces are compliant with the U-Compare. \n"
-    ],
-    "oai_identifier": [
-        "87ad7ad4bc9f11e1a404080027e73ea27860c02e583d40aeb9144efe5f25206a"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "UIMA/U-Compare Apertium Morphological Analyser "
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/00998041-31ca-50f0-ad44-bd3c4c74ff51.json b/oaitestdata/clarin-oai_dc/SET_1/json/00998041-31ca-50f0-ad44-bd3c4c74ff51.json
deleted file mode 100644
index 603b2a8c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/00998041-31ca-50f0-ad44-bd3c4c74ff51.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "UJ"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "downloadable_files_count: 10",
-        "application/vnd.oasis.opendocument.text",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/369",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/369"
-    ],
-    "PID": "http://hdl.handle.net/11321/369",
-    "PublicationTimestamp": "2017-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "UJ"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Byszuk, Joanna"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/369;2017-05-30T07:54:12Z;hdl_11321_3;hdl_11321_4;PracticeTextCorpus;Byszuk, Joanna;literature;polish literature;This is a corpus of texts.;2017-05-30;corpus;http://hdl.handle.net/11321/369;pol;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/msword;text/plain;application/vnd.oasis.opendocument.text;text/plain;application/vnd.oasis.opendocument.text;downloadable_files_count: 10;UJ",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "00998041-31ca-50f0-ad44-bd3c4c74ff51",
-    "notes": [
-        "This is a corpus of texts."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/369"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "literature"
-        },
-        {
-            "name": "polish literature"
-        }
-    ],
-    "title": [
-        "PracticeTextCorpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/00ab6597-fa7d-59b9-91db-0b6d53e040a6.json b/oaitestdata/clarin-oai_dc/SET_1/json/00ab6597-fa7d-59b9-91db-0b6d53e040a6.json
deleted file mode 100644
index ac952677..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/00ab6597-fa7d-59b9-91db-0b6d53e040a6.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4487",
-    "MetadataAccess": [
-        "oai:ota:oucs:4487"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Walton, Jacob, d. 1743."
-    ],
-    "fulltext": "oai:ota:oucs:4487;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4487.xml;The catechism of the author of The minute philosopher fully answer'd: By J. Walton.;Walton, Jacob, d. 1743.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "00ab6597-fa7d-59b9-91db-0b6d53e040a6",
-    "oai_identifier": [
-        "oai:ota:oucs:4487"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The catechism of the author of The minute philosopher fully answer'd: By J. Walton."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4487.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/00b3142b-10ed-5196-8cc6-0ac428dcefdd.json b/oaitestdata/clarin-oai_dc/SET_1/json/00b3142b-10ed-5196-8cc6-0ac428dcefdd.json
deleted file mode 100644
index b8a00d63..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/00b3142b-10ed-5196-8cc6-0ac428dcefdd.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Matteo Grella"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/x-rar-compressed"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2476",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2476"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2476",
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Matteo Grella"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11372/LRT-2630"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Grella, Matteo"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2476;2018-03-02T08:51:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Italian Content Words;Grella, Matteo;morphological dictionary;This resource is an Italian morphological dictionary for content words, encoded in a JSON Lines format text file. It contains correspondences between surface form and lexical forms of words followed by grammatical features. The surface word forms have been generated algorithmically by using stable phonological and morphological rules of the Italian language. Particular attention has been given to the generation of verbs for which rules have been extracted from the famous A.L e G. Lepschy, La lingua italiana. The dictionary with its remarkable coverage is particularly useful used together with the Italian Function Words (http://hdl.handle.net/11372/LRT-2288) for tasks such as POS-Tagging or Syntactic Parsing.;2011;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-2476;ita;http://hdl.handle.net/11372/LRT-2630;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/x-rar-compressed;text/plain; charset=utf-8;downloadable_files_count: 1;Matteo Grella",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "00b3142b-10ed-5196-8cc6-0ac428dcefdd",
-    "notes": [
-        "This resource is an Italian morphological dictionary for content words, encoded in a JSON Lines format text file. It contains correspondences between surface form and lexical forms of words followed by grammatical features. The surface word forms have been generated algorithmically by using stable phonological and morphological rules of the Italian language. Particular attention has been given to the generation of verbs for which rules have been extracted from the famous A.L e G. Lepschy, La lingua italiana. The dictionary with its remarkable coverage is particularly useful used together with the Italian Function Words (http://hdl.handle.net/11372/LRT-2288) for tasks such as POS-Tagging or Syntactic Parsing."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2476"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphological dictionary"
-        }
-    ],
-    "title": [
-        "Italian Content Words"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/00b4213e-7b46-5559-9185-071e2bd55a52.json b/oaitestdata/clarin-oai_dc/SET_1/json/00b4213e-7b46-5559-9185-071e2bd55a52.json
deleted file mode 100644
index 31669d69..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/00b4213e-7b46-5559-9185-071e2bd55a52.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "University of Silesia"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 4",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/362",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/362"
-    ],
-    "PID": "http://hdl.handle.net/11321/362",
-    "PublicationTimestamp": "2017-04-25T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "University of Silesia"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Pastuch, Magdalena"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/362;2017-04-25T14:09:46Z;hdl_11321_3;hdl_11321_4;Lilia;Pastuch, Magdalena;history receipes;sample of historical texts;2017-04-25;corpus;http://hdl.handle.net/11321/362;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;application/msword;application/msword;application/msword;application/msword;downloadable_files_count: 4;University of Silesia;http://www.us.edu.pl",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "00b4213e-7b46-5559-9185-071e2bd55a52",
-    "notes": [
-        "sample of historical texts"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/362"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "history receipes"
-        }
-    ],
-    "title": [
-        "Lilia"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/00bd4636-5c8d-5513-99eb-1d6184f42c6c.json b/oaitestdata/clarin-oai_dc/SET_1/json/00bd4636-5c8d-5513-99eb-1d6184f42c6c.json
deleted file mode 100644
index 1a38b57a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/00bd4636-5c8d-5513-99eb-1d6184f42c6c.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-985",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-985"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-985",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-985;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LAC Katang Corpus;Language and Cognition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-985;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI29300%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "00bd4636-5c8d-5513-99eb-1d6184f42c6c",
-    "notes": [
-        "Language and Cognition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-985"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LAC Katang Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/00c83f6d-811a-57f3-8b46-05892c6037cc.json b/oaitestdata/clarin-oai_dc/SET_1/json/00c83f6d-811a-57f3-8b46-05892c6037cc.json
deleted file mode 100644
index 0fa5167a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/00c83f6d-811a-57f3-8b46-05892c6037cc.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Uniwersytet Miko\u0142aja Kopernika w Toruniu"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/232",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/232"
-    ],
-    "PID": "http://hdl.handle.net/11321/232",
-    "PublicationTimestamp": "2015-07-07T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Uniwersytet Miko\u0142aja Kopernika w Toruniu"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Wieslawa, Osinska"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/232;2015-11-09T18:57:42Z;hdl_11321_3;hdl_11321_4;MEtadane artykulow naukowych;Wieslawa, Osinska;Wieslawa, Osinska;metadane;biblioteki cyfrowe;kolekcja rekord\u00f3w metadanych artyku\u0142\u00f3w naukowych z bibliotek cyfrowych w iIlo\u015bci 146 tys.;2015-07-07;corpus;http://hdl.handle.net/11321/232;pol;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;Uniwersytet Miko\u0142aja Kopernika w Toruniu;http://www.wizualizacjanauki.umk.pl",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "00c83f6d-811a-57f3-8b46-05892c6037cc",
-    "notes": [
-        "kolekcja rekord\u00f3w metadanych artyku\u0142\u00f3w naukowych z bibliotek cyfrowych w iIlo\u015bci 146 tys."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/232"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "metadane"
-        },
-        {
-            "name": "biblioteki cyfrowe"
-        }
-    ],
-    "title": [
-        "MEtadane artykulow naukowych"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/00cd211c-151a-5584-92e8-80f6a42c0984.json b/oaitestdata/clarin-oai_dc/SET_1/json/00cd211c-151a-5584-92e8-80f6a42c0984.json
deleted file mode 100644
index 6897b562..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/00cd211c-151a-5584-92e8-80f6a42c0984.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=151585066c0911e2a2aa782bcb074135f1f91526aee34f52b62e56c1164326e3",
-    "MetadataAccess": [
-        "151585066c0911e2a2aa782bcb074135f1f91526aee34f52b62e56c1164326e3"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "151585066c0911e2a2aa782bcb074135f1f91526aee34f52b62e56c1164326e3;2018-11-15T16:40:10Z;toolService;toolService:service;U-Compare Co-reference Identification service;Web service created by exporting UIMA-based workflow from the U-Compare text mining system.\nFunctionality: Identifies co-reference chains in plain text. Also identifies sentences, tokens with parts-of-speech and lemmas, and NP chunks\nTools in workflow: TTL-Tokenizer (RACAI, Romania), TTL-Tagger (RACAI, Romania), TTL-Lemmatizer (RACAI, Romania), UAIC-NPChunker (UAIC, Romania), UAIC-RARE (UAIC, Romania)  \nNOTE: The licence provided covers the web service only. Tools used to create the workflow may have their own licences\n;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "00cd211c-151a-5584-92e8-80f6a42c0984",
-    "notes": [
-        "Web service created by exporting UIMA-based workflow from the U-Compare text mining system.\nFunctionality: Identifies co-reference chains in plain text. Also identifies sentences, tokens with parts-of-speech and lemmas, and NP chunks\nTools in workflow: TTL-Tokenizer (RACAI, Romania), TTL-Tagger (RACAI, Romania), TTL-Lemmatizer (RACAI, Romania), UAIC-NPChunker (UAIC, Romania), UAIC-RARE (UAIC, Romania)  \nNOTE: The licence provided covers the web service only. Tools used to create the workflow may have their own licences\n"
-    ],
-    "oai_identifier": [
-        "151585066c0911e2a2aa782bcb074135f1f91526aee34f52b62e56c1164326e3"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:service"
-    ],
-    "state": "active",
-    "title": [
-        "U-Compare Co-reference Identification service"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/00daafe8-db46-5e06-8d13-4e00466ddc72.json b/oaitestdata/clarin-oai_dc/SET_1/json/00daafe8-db46-5e06-8d13-4e00466ddc72.json
deleted file mode 100644
index bdc7c963..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/00daafe8-db46-5e06-8d13-4e00466ddc72.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4145",
-    "MetadataAccess": [
-        "oai:ota:oucs:4145"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Carey, Henry, 1687?-1743."
-    ],
-    "fulltext": "oai:ota:oucs:4145;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4145.xml;Pudding and dumpling burnt to pot. Or, a compleat key to the dissertation on dumpling. Wherein all the mystery of that dark treatise is brought to light; in such a manner and method, that the meanest capacity may know who and who's together. Published for the general information of mankind. By J. W. author of 684 treatises;Carey, Henry, 1687?-1743.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "00daafe8-db46-5e06-8d13-4e00466ddc72",
-    "oai_identifier": [
-        "oai:ota:oucs:4145"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Pudding and dumpling burnt to pot. Or, a compleat key to the dissertation on dumpling. Wherein all the mystery of that dark treatise is brought to light; in such a manner and method, that the meanest capacity may know who and who's together. Published for the general information of mankind. By J. W. author of 684 treatises"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4145.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/00e85b52-0345-512e-b6ad-3f9159cebccc.json b/oaitestdata/clarin-oai_dc/SET_1/json/00e85b52-0345-512e-b6ad-3f9159cebccc.json
deleted file mode 100644
index 15e55a51..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/00e85b52-0345-512e-b6ad-3f9159cebccc.json
+++ /dev/null
@@ -1,49 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4775",
-    "MetadataAccess": [
-        "oai:ota:oucs:4775"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:4775;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4775.xml;A select collection of poems: with notes, biographical and historical.: [pt.1];text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "00e85b52-0345-512e-b6ad-3f9159cebccc",
-    "oai_identifier": [
-        "oai:ota:oucs:4775"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A select collection of poems: with notes, biographical and historical.: [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4775.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/00e9edee-1190-5607-bb2a-cc6a362241c9.json b/oaitestdata/clarin-oai_dc/SET_1/json/00e9edee-1190-5607-bb2a-cc6a362241c9.json
deleted file mode 100644
index afa4b722..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/00e9edee-1190-5607-bb2a-cc6a362241c9.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Johnston, Ian C."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "1 file: 328 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2524",
-    "MetadataAccess": [
-        "oai:ota:oucs:2524"
-    ],
-    "PublicationTimestamp": "1782-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1782"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Philosophical works"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Rousseau, Jean-Jacques"
-    ],
-    "fulltext": "oai:ota:oucs:2524;2018-05-17T08:02:40Z;http://ota.ox.ac.uk/headers/2524.xml;Discourse on the origin and the foundations of inequality among men;Discours sur l'origine et les fondements de l'in\u00c3\u00a9galit\u00c3\u00a9 parmi les hommes;Second Discourse;Rousseau, Jean-Jacques;1782;text_and_corpus_linguistics;Ethics;eng;Oxford Text Archive, University of Oxford;Johnston, Ian C.;1 file: 328 KB;Text;Philosophical works;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "00e9edee-1190-5607-bb2a-cc6a362241c9",
-    "oai_identifier": [
-        "oai:ota:oucs:2524"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Ethics"
-        }
-    ],
-    "title": [
-        "Discourse on the origin and the foundations of inequality among men",
-        "Discours sur l'origine et les fondements de l'in\u00c3\u00a9galit\u00c3\u00a9 parmi les hommes",
-        "Second Discourse"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2524.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/00eab22e-9d8b-5675-b539-b437c5d2e864.json b/oaitestdata/clarin-oai_dc/SET_1/json/00eab22e-9d8b-5675-b539-b437c5d2e864.json
deleted file mode 100644
index 711bdbc3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/00eab22e-9d8b-5675-b539-b437c5d2e864.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gotehenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/25",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/25"
-    ],
-    "PID": "http://hdl.handle.net/10794/25",
-    "PublicationTimestamp": "2012-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gotehenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/25;2017-10-27T15:22:51Z;hdl_10794_1;hdl_10794_2;Old Swedish morphology (2017-10-16);Fornsvensk morfologi (2017-10-16);n/a, n/a;Swedish;Morphology;Old Swedish morphology from S\u00f6derwall and Schlyter.;Fornsvensk morfologi ur S\u00f6derwall och Schlyter.;2012-05-30;lexicalConceptualResource;http://hdl.handle.net/10794/25;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gotehenburg;https://spraakbanken.gu.se/swe/resurs/fsvm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "00eab22e-9d8b-5675-b539-b437c5d2e864",
-    "notes": [
-        "Old Swedish morphology from S\u00f6derwall and Schlyter.",
-        "Fornsvensk morfologi ur S\u00f6derwall och Schlyter."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/25"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Morphology"
-        }
-    ],
-    "title": [
-        "Old Swedish morphology (2017-10-16)",
-        "Fornsvensk morfologi (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/01136a7d-cb07-5cd2-9499-e10dfb6cfb21.json b/oaitestdata/clarin-oai_dc/SET_1/json/01136a7d-cb07-5cd2-9499-e10dfb6cfb21.json
deleted file mode 100644
index 8881e732..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/01136a7d-cb07-5cd2-9499-e10dfb6cfb21.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 20.2 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2277",
-    "MetadataAccess": [
-        "oai:ota:oucs:2277"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Fielding, Henry, 1707-1754"
-    ],
-    "fulltext": "oai:ota:oucs:2277;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/2277.xml;Some papers proper to be read before the R-L Society concerning the Terrestrial Chrysipus, Golden-foot or Guinea : an insect, or vegetable, resembling the Polypus, which hath this surprising property, that being cut into several pieces, each piece becomes a perfect animal, or vegetable, as complete as that of which it was originally only a part / collected by Petrus Gualterus, but not published till after his death;Fielding, Henry, 1707-1754;default: 1976-01-01;text_and_corpus_linguistics;Addresses -- Great Britain -- 18th century;Parodies -- Great Britain -- 18th century;Satires -- Great Britain -- 18th century;eng;Oxford Text Archive, University of Oxford;(1 file : ca. 20.2 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "01136a7d-cb07-5cd2-9499-e10dfb6cfb21",
-    "oai_identifier": [
-        "oai:ota:oucs:2277"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Addresses -- Great Britain -- th century"
-        },
-        {
-            "name": "Parodies -- Great Britain -- th century"
-        },
-        {
-            "name": "Satires -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Some papers proper to be read before the R-L Society concerning the Terrestrial Chrysipus, Golden-foot or Guinea : an insect, or vegetable, resembling the Polypus, which hath this surprising property, that being cut into several pieces, each piece becomes a perfect animal, or vegetable, as complete as that of which it was originally only a part / collected by Petrus Gualterus, but not published till after his death"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2277.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/011e844e-7d78-5f94-858d-1ebd37ceba1f.json b/oaitestdata/clarin-oai_dc/SET_1/json/011e844e-7d78-5f94-858d-1ebd37ceba1f.json
deleted file mode 100644
index 4203f9e0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/011e844e-7d78-5f94-858d-1ebd37ceba1f.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 3",
-        "application/pdf"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4900-A",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4900-A"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-4900-A",
-    "PublicationTimestamp": "2009-11-02T09:37:56Z",
-    "PublicationYear": [
-        "2009"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "PDT 2.0 License",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/license-pdt2",
-        "ACA"
-    ],
-    "author": [
-        "Kolovratn\u00edk, David"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4900-A;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;MORFO;Kolovratn\u00edk, David;morphological analysis;The MORFO system for morphological analysis of Czech consists of four units: the analyzer, the generator, the dictionary editor, and the library with the shared source code for handling dictionary objects.;2009-11-02T09:37:56Z;toolService;http://hdl.handle.net/11858/00-097C-0000-0001-4900-A;ces;PDT 2.0 License;https://lindat.mff.cuni.cz/repository/xmlui/page/license-pdt2;ACA;application/x-gzip;application/pdf;application/pdf;text/plain; charset=utf-8;downloadable_files_count: 3;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/morfo",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "011e844e-7d78-5f94-858d-1ebd37ceba1f",
-    "notes": [
-        "The MORFO system for morphological analysis of Czech consists of four units: the analyzer, the generator, the dictionary editor, and the library with the shared source code for handling dictionary objects."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4900-A"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphological analysis"
-        }
-    ],
-    "title": [
-        "MORFO"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/01286a8e-5bbd-5fb4-95c3-716e18d3e189.json b/oaitestdata/clarin-oai_dc/SET_1/json/01286a8e-5bbd-5fb4-95c3-716e18d3e189.json
deleted file mode 100644
index ec4cc0eb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/01286a8e-5bbd-5fb4-95c3-716e18d3e189.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3324",
-    "MetadataAccess": [
-        "oai:ota:oucs:3324"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pope, Alexander, 1688-1744."
-    ],
-    "fulltext": "oai:ota:oucs:3324;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3324.xml;The history of the Norfolk steward continued: In two parts. Part I. Containing an account of Mr. Lyn's private character, ... Part II. Containing some farther account of Mr. Lyn's management, ...;Pope, Alexander, 1688-1744.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "01286a8e-5bbd-5fb4-95c3-716e18d3e189",
-    "oai_identifier": [
-        "oai:ota:oucs:3324"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The history of the Norfolk steward continued: In two parts. Part I. Containing an account of Mr. Lyn's private character, ... Part II. Containing some farther account of Mr. Lyn's management, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3324.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/016248ea-fcec-582d-82da-b808c691f9c1.json b/oaitestdata/clarin-oai_dc/SET_1/json/016248ea-fcec-582d-82da-b808c691f9c1.json
deleted file mode 100644
index edc0e96d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/016248ea-fcec-582d-82da-b808c691f9c1.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2628",
-    "MetadataAccess": [
-        "oai:ota:oucs:2628"
-    ],
-    "PublicationTimestamp": "1735-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1735"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2628;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2628.xml;An argument against abolishing Christianity;Swift, Jonathan, 1667-1745;1735;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "016248ea-fcec-582d-82da-b808c691f9c1",
-    "oai_identifier": [
-        "oai:ota:oucs:2628"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An argument against abolishing Christianity"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2628.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/016e31db-0e31-5266-99b9-c0e36468b441.json b/oaitestdata/clarin-oai_dc/SET_1/json/016e31db-0e31-5266-99b9-c0e36468b441.json
deleted file mode 100644
index 7aa23bd3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/016e31db-0e31-5266-99b9-c0e36468b441.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=9047a214568c11e2a2aa782bcb074135b50e3cb8f86b4a2ba5dc7d4c54eb0600",
-    "MetadataAccess": [
-        "9047a214568c11e2a2aa782bcb074135b50e3cb8f86b4a2ba5dc7d4c54eb0600"
-    ],
-    "PublicationTimestamp": "2015-12-07T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "9047a214568c11e2a2aa782bcb074135b50e3cb8f86b4a2ba5dc7d4c54eb0600;2018-11-15T16:40:00Z;toolService;toolService:tool;SenseClusters;SenseClusters is a package of (mostly) Perl programs that allows a user to cluster similar contexts together using unsupervised knowledge-lean methods.;2015-12-07",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "016e31db-0e31-5266-99b9-c0e36468b441",
-    "notes": [
-        "SenseClusters is a package of (mostly) Perl programs that allows a user to cluster similar contexts together using unsupervised knowledge-lean methods."
-    ],
-    "oai_identifier": [
-        "9047a214568c11e2a2aa782bcb074135b50e3cb8f86b4a2ba5dc7d4c54eb0600"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "SenseClusters"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/01c2d732-348c-5d5b-9a0b-d548e8f5d3e1.json b/oaitestdata/clarin-oai_dc/SET_1/json/01c2d732-348c-5d5b-9a0b-d548e8f5d3e1.json
deleted file mode 100644
index 095c489b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/01c2d732-348c-5d5b-9a0b-d548e8f5d3e1.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "IPI PAN"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/576",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/576"
-    ],
-    "PID": "http://hdl.handle.net/11321/576",
-    "PublicationTimestamp": "2018-07-26T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "IPI PAN"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "author": [
-        "Aleksander Wawer"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/576;2018-07-26T14:08:45Z;hdl_11321_3;hdl_11321_4;Polish language sentiment dependency treebank (Treebank Wydzwieku);Aleksander Wawer;sentiment;The dataset is a dependency treebank with sentiment annotations.;2018-07-26;corpus;http://hdl.handle.net/11321/576;pol;downloadable_files_count: 0;IPI PAN;http://zil.ipipan.waw.pl/TreebankWydzwieku",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "01c2d732-348c-5d5b-9a0b-d548e8f5d3e1",
-    "notes": [
-        "The dataset is a dependency treebank with sentiment annotations."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/576"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "sentiment"
-        }
-    ],
-    "title": [
-        "Polish language sentiment dependency treebank (Treebank Wydzwieku)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/01d7a274-c55a-5291-ab1a-e783018e298b.json b/oaitestdata/clarin-oai_dc/SET_1/json/01d7a274-c55a-5291-ab1a-e783018e298b.json
deleted file mode 100644
index f2f68225..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/01d7a274-c55a-5291-ab1a-e783018e298b.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4223",
-    "MetadataAccess": [
-        "oai:ota:oucs:4223"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Wollstonecraft, Mary, 1759-1797."
-    ],
-    "fulltext": "oai:ota:oucs:4223;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4223.xml;A vindication of the rights of woman: with strictures on political and moral subjects. By Mary Wollstonecraft.;Wollstonecraft, Mary, 1759-1797.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "01d7a274-c55a-5291-ab1a-e783018e298b",
-    "oai_identifier": [
-        "oai:ota:oucs:4223"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A vindication of the rights of woman: with strictures on political and moral subjects. By Mary Wollstonecraft."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4223.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/01e41c8f-b327-5aa8-9a64-073f5fae5214.json b/oaitestdata/clarin-oai_dc/SET_1/json/01e41c8f-b327-5aa8-9a64-073f5fae5214.json
deleted file mode 100644
index ea159128..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/01e41c8f-b327-5aa8-9a64-073f5fae5214.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Estonian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-249",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-249"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-249",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Estonia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-249;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Corpus of Written Estonian;4.4 mio words; TEI/SGML;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-249;est;downloadable_files_count: 0;Estonia;http://www.cl.ut.ee/korpused/baaskorpus/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "01e41c8f-b327-5aa8-9a64-073f5fae5214",
-    "notes": [
-        "4.4 mio words; TEI/SGML"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-249"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus of Written Estonian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/01e597ef-8943-52ca-b7e1-8174af75c6fe.json b/oaitestdata/clarin-oai_dc/SET_1/json/01e597ef-8943-52ca-b7e1-8174af75c6fe.json
deleted file mode 100644
index c0e0fe2b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/01e597ef-8943-52ca-b7e1-8174af75c6fe.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Trojina, Institute for Applied Slovene Studies",
-        "Faculty of Arts, University of Ljubljana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1045",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1045"
-    ],
-    "PID": "http://hdl.handle.net/11356/1045",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Trojina, Institute for Applied Slovene Studies",
-        "Faculty of Arts, University of Ljubljana"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11356/1193"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/"
-    ],
-    "author": [
-        "Dobrovoljc, Kaja"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1045;2018-08-03T18:50:22Z;hdl_11356_1023;hdl_11356_1024;KRES corpus n-grams 1.0;Dobrovoljc, Kaja;n-grams;wordlist;multiword expressions;This is a collection of n-grams extracted from the KRES corpus of written Slovene. In addition to the separate lists of n-grams for tokens and their attributes (morphosyntacic tag, lemma), an adjusted frequency list with statistical substring reduction has also been added (as described in O'Donnell 2011). Only n-grams within sentences have been counted.;2015-07-01;lexicalConceptualResource;http://hdl.handle.net/11356/1045;slv;http://hdl.handle.net/11356/1193;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);PUB;https://creativecommons.org/licenses/by-nc-sa/4.0/;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 4;Trojina, Institute for Applied Slovene Studies;Faculty of Arts, University of Ljubljana;http://eng.slovenscina.eu/korpusi/kres",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "01e597ef-8943-52ca-b7e1-8174af75c6fe",
-    "notes": [
-        "This is a collection of n-grams extracted from the KRES corpus of written Slovene. In addition to the separate lists of n-grams for tokens and their attributes (morphosyntacic tag, lemma), an adjusted frequency list with statistical substring reduction has also been added (as described in O'Donnell 2011). Only n-grams within sentences have been counted."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1045"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "n-grams"
-        },
-        {
-            "name": "wordlist"
-        },
-        {
-            "name": "multiword expressions"
-        }
-    ],
-    "title": [
-        "KRES corpus n-grams 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0209845e-4c7a-5bc0-9c10-293616c77379.json b/oaitestdata/clarin-oai_dc/SET_1/json/0209845e-4c7a-5bc0-9c10-293616c77379.json
deleted file mode 100644
index 9b4e8ac8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0209845e-4c7a-5bc0-9c10-293616c77379.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Humanities and Social Sciences, University of Zagreb"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Croatian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1072",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1072"
-    ],
-    "PID": "http://hdl.handle.net/11356/1072",
-    "PublicationTimestamp": "2016-09-19T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Faculty of Humanities and Social Sciences, University of Zagreb"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/324414",
-        "http://www.lrec-conf.org/proceedings/lrec2016/summaries/340.html",
-        "http://hdl.handle.net/11356/1067"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "GNU General Public Licence, version 3",
-        "PUB",
-        "http://opensource.org/licenses/GPL-3.0"
-    ],
-    "author": [
-        "Boras, Damir",
-        "Klubi\u010dka, Filip",
-        "Ljube\u0161i\u0107, Nikola"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1072;2018-08-13T20:19:32Z;hdl_11356_1023;hdl_11356_1024;Inflectional lexicon hrLex 1.2;Ljube\u0161i\u0107, Nikola;Klubi\u010dka, Filip;Boras, Damir;morphology;inflection;hrLex is a large inflectional lexicon of Croatian language where each entry consists of a (wordform, lemma, MSD, frequency, per-million frequency) 5-tuple. The (wordform, lemma, MSD) triple frequencies are calculated on the hrWaC v2.2 corpus. The MSD tagset follows the MULTEXT-East V5 tagset for Croatian available at http://nl.ijs.si/ME/V5/msd/html/msd-hr.html.;2016-09-19;lexicalConceptualResource;http://hdl.handle.net/11356/1072;hrv;info:eu-repo/grantAgreement/EC/FP7/324414;http://www.lrec-conf.org/proceedings/lrec2016/summaries/340.html;http://hdl.handle.net/11356/1067;GNU General Public Licence, version 3;PUB;http://opensource.org/licenses/GPL-3.0;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Faculty of Humanities and Social Sciences, University of Zagreb",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0209845e-4c7a-5bc0-9c10-293616c77379",
-    "notes": [
-        "hrLex is a large inflectional lexicon of Croatian language where each entry consists of a (wordform, lemma, MSD, frequency, per-million frequency) 5-tuple. The (wordform, lemma, MSD) triple frequencies are calculated on the hrWaC v2.2 corpus. The MSD tagset follows the MULTEXT-East V5 tagset for Croatian available at http://nl.ijs.si/ME/V5/msd/html/msd-hr.html."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1072"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "inflection"
-        }
-    ],
-    "title": [
-        "Inflectional lexicon hrLex 1.2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/02138370-7d01-5e97-8947-5fc7d985c695.json b/oaitestdata/clarin-oai_dc/SET_1/json/02138370-7d01-5e97-8947-5fc7d985c695.json
deleted file mode 100644
index 1073d152..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/02138370-7d01-5e97-8947-5fc7d985c695.json
+++ /dev/null
@@ -1,155 +0,0 @@
-{
-    "Contact": [
-        "Universal Dependencies Consortium"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 3"
-    ],
-    "Language": [
-        "Basque",
-        "Bulgarian",
-        "Croatian",
-        "Czech",
-        "Danish",
-        "English",
-        "Finnish",
-        "French",
-        "German",
-        "Modern Greek (1453-)",
-        "Hebrew",
-        "Hungarian",
-        "Indonesian",
-        "Irish",
-        "Italian",
-        "Persian",
-        "Spanish",
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/LRT-1478",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/LRT-1478"
-    ],
-    "PID": "http://hdl.handle.net/11234/LRT-1478",
-    "PublicationTimestamp": "2015-05-15T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Universal Dependencies Consortium"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-1464",
-        "http://hdl.handle.net/11234/1-1548"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Licence Universal Dependencies v1.1",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-1.1",
-        "PUB"
-    ],
-    "author": [
-        "Seraji, Mojgan",
-        "Simov, Kiril",
-        "Manning, Christopher",
-        "Bosco, Cristina",
-        "Lynn, Teresa",
-        "Plank, Barbara",
-        "Ginter, Filip",
-        "Osenova, Petya",
-        "Gojenola, Koldo",
-        "Agi\u0107, \u017deljko",
-        "Kuokkala, Juha",
-        "Kanerva, Jenna",
-        "Choi, Jinho",
-        "Aranzabe, Maria Jesus",
-        "Haji\u010d, Jan",
-        "Vincze, Veronika",
-        "Atutxa, Aitziber",
-        "Goldberg, Yoav",
-        "Nurmi, Hanna",
-        "Pyysalo, Sampo",
-        "Seeker, Wolfgang",
-        "Dozat, Timothy",
-        "Tsarfaty, Reut",
-        "Goenaga, Iakes",
-        "Simi, Maria",
-        "Piitulainen, Jussi",
-        "Nivre, Joakim",
-        "Prokopidis, Prokopis",
-        "Petrov, Slav",
-        "McDonald, Ryan",
-        "Foster, Jennifer",
-        "Lind\u00e9n, Krister",
-        "Smith, Aaron",
-        "de Marneffe, Marie-Catherine",
-        "Lenci, Alessandro",
-        "Mart\u00ednez, H\u00e9ctor Alonso",
-        "Missil\u00e4, Anna",
-        "Ljube\u0161i\u0107, Nikola",
-        "Montemagni, Simonetta",
-        "Zeman, Daniel",
-        "Silveira, Natalia",
-        "Johannsen, Anders Tr\u00e6rup",
-        "Farkas, Rich\u00e1rd",
-        "Laippala, Veronika"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/LRT-1478;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Universal Dependencies 1.1;Agi\u0107, \u017deljko;Aranzabe, Maria Jesus;Atutxa, Aitziber;Bosco, Cristina;Choi, Jinho;de Marneffe, Marie-Catherine;Dozat, Timothy;Farkas, Rich\u00e1rd;Foster, Jennifer;Ginter, Filip;Goenaga, Iakes;Gojenola, Koldo;Goldberg, Yoav;Haji\u010d, Jan;Johannsen, Anders Tr\u00e6rup;Kanerva, Jenna;Kuokkala, Juha;Laippala, Veronika;Lenci, Alessandro;Lind\u00e9n, Krister;Ljube\u0161i\u0107, Nikola;Lynn, Teresa;Manning, Christopher;Mart\u00ednez, H\u00e9ctor Alonso;McDonald, Ryan;Missil\u00e4, Anna;Montemagni, Simonetta;Nivre, Joakim;Nurmi, Hanna;Osenova, Petya;Petrov, Slav;Piitulainen, Jussi;Plank, Barbara;Prokopidis, Prokopis;Pyysalo, Sampo;Seeker, Wolfgang;Seraji, Mojgan;Silveira, Natalia;Simi, Maria;Simov, Kiril;Smith, Aaron;Tsarfaty, Reut;Vincze, Veronika;Zeman, Daniel;treebank;dependency syntax;morphology;harmonized annotation;interset;universal tagset;stanford dependencies;universal dependencies;Universal Dependencies is a project that seeks to develop cross-linguistically consistent treebank annotation for many languages, with the goal of facilitating multilingual parser development, cross-lingual learning, and parsing research from a language typology perspective. The annotation scheme is based on (universal) Stanford dependencies (de Marneffe et al., 2006, 2008, 2014), Google universal part-of-speech tags (Petrov et al., 2012), and the Interset interlingua for morphosyntactic tagsets (Zeman, 2008). This is the second release of UD Treebanks, Version 1.1.;2015-05-15;corpus;http://hdl.handle.net/11234/LRT-1478;eus;bul;hrv;ces;dan;eng;fin;fra;deu;ell;heb;hun;ind;gle;ita;fas;spa;swe;http://hdl.handle.net/11234/1-1464;http://hdl.handle.net/11234/1-1548;Licence Universal Dependencies v1.1;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-1.1;PUB;text/plain; charset=utf-8;application/x-gzip;application/x-gzip;application/x-gzip;downloadable_files_count: 3;Universal Dependencies Consortium;http://universaldependencies.github.io/docs/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "02138370-7d01-5e97-8947-5fc7d985c695",
-    "notes": [
-        "Universal Dependencies is a project that seeks to develop cross-linguistically consistent treebank annotation for many languages, with the goal of facilitating multilingual parser development, cross-lingual learning, and parsing research from a language typology perspective. The annotation scheme is based on (universal) Stanford dependencies (de Marneffe et al., 2006, 2008, 2014), Google universal part-of-speech tags (Petrov et al., 2012), and the Interset interlingua for morphosyntactic tagsets (Zeman, 2008). This is the second release of UD Treebanks, Version 1.1."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/LRT-1478"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "dependency syntax"
-        },
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "harmonized annotation"
-        },
-        {
-            "name": "interset"
-        },
-        {
-            "name": "universal tagset"
-        },
-        {
-            "name": "stanford dependencies"
-        },
-        {
-            "name": "universal dependencies"
-        }
-    ],
-    "title": [
-        "Universal Dependencies 1.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/02378880-2af9-590f-a15a-787c628b78ce.json b/oaitestdata/clarin-oai_dc/SET_1/json/02378880-2af9-590f-a15a-787c628b78ce.json
deleted file mode 100644
index 0490ffbf..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/02378880-2af9-590f-a15a-787c628b78ce.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5541",
-    "MetadataAccess": [
-        "oai:ota:oucs:5541"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Grant, Alexander, d. 1817."
-    ],
-    "fulltext": "oai:ota:oucs:5541;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5541.xml;Observations on the use of opium in removing symptoms supposed to be owing to morbid irritability: By Alexander Grant, ...;Grant, Alexander, d. 1817.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "02378880-2af9-590f-a15a-787c628b78ce",
-    "oai_identifier": [
-        "oai:ota:oucs:5541"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Observations on the use of opium in removing symptoms supposed to be owing to morbid irritability: By Alexander Grant, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5541.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/024403ec-9aaf-5782-bc1b-59a383e818e3.json b/oaitestdata/clarin-oai_dc/SET_1/json/024403ec-9aaf-5782-bc1b-59a383e818e3.json
deleted file mode 100644
index ea366f1f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/024403ec-9aaf-5782-bc1b-59a383e818e3.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Centro de Tecnolog\u00edas y Aplicaciones del Lenguaje y del Habla (TALP)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Catalan",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1084",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1084"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1084",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Centro de Tecnolog\u00edas y Aplicaciones del Lenguaje y del Habla (TALP)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1084;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LC-STAR Dialogues;oral corpus;bilingual;Bilingual oral corpus (55 hours recording). 77 Spanish speakers; 59 Catalan speakers; Environment: Local telephone. Annotation: orthographic.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1084;cat;spa;downloadable_files_count: 0;Spain;Centro de Tecnolog\u00edas y Aplicaciones del Lenguaje y del Habla (TALP);http://www.lc-star.com/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "024403ec-9aaf-5782-bc1b-59a383e818e3",
-    "notes": [
-        "Bilingual oral corpus (55 hours recording). 77 Spanish speakers; 59 Catalan speakers; Environment: Local telephone. Annotation: orthographic."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1084"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "oral corpus"
-        },
-        {
-            "name": "bilingual"
-        }
-    ],
-    "title": [
-        "LC-STAR Dialogues"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/024c41ea-dcee-5371-b006-4a3a054021d7.json b/oaitestdata/clarin-oai_dc/SET_1/json/024c41ea-dcee-5371-b006-4a3a054021d7.json
deleted file mode 100644
index 3c1fe28e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/024c41ea-dcee-5371-b006-4a3a054021d7.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Arts, Institute of the Czech National Corpus, Charles University in Prague"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-119E-8",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-119E-8"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-119E-8",
-    "PublicationTimestamp": "2005-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2005"
-    ],
-    "Publisher": [
-        "Faculty of Arts, Institute of the Czech National Corpus, Charles University in Prague"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Czech National Corpus (Shuffled Corpus Data)",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/license-cnc",
-        "ACA"
-    ],
-    "author": [
-        "Hn\u00e1tkov\u00e1, Milena",
-        "Kop\u0159ivov\u00e1, Marie",
-        "Petkevi\u010d, Vladim\u00edr",
-        "Kocek, Jan",
-        "Spoustov\u00e1, Johanka",
-        "\u010cerm\u00e1k, Franti\u0161ek",
-        "Hlav\u00e1\u010dov\u00e1, Jaroslava",
-        "Vel\u00ed\u0161ek, Zden\u011bk",
-        "Schmiedtov\u00e1, V\u011bra",
-        "K\u0159en, Michal",
-        "Jel\u00ednek, Tom\u00e1\u0161",
-        "Novotn\u00e1, Renata",
-        "Skoumalov\u00e1, Hana",
-        "\u0160ulc, Michal"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-119E-8;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;SYN2005: balanced corpus of written Czech;\u010cerm\u00e1k, Franti\u0161ek;Hlav\u00e1\u010dov\u00e1, Jaroslava;Hn\u00e1tkov\u00e1, Milena;Jel\u00ednek, Tom\u00e1\u0161;Kocek, Jan;Kop\u0159ivov\u00e1, Marie;K\u0159en, Michal;Novotn\u00e1, Renata;Petkevi\u010d, Vladim\u00edr;Schmiedtov\u00e1, V\u011bra;Skoumalov\u00e1, Hana;Spoustov\u00e1, Johanka;\u0160ulc, Michal;Vel\u00ed\u0161ek, Zden\u011bk;balanced corpus;written language;Balanced corpus of contemporary written Czech sized 100 MW. It was created as a representation of written language from 2000\u20132004 and thus it contains a wide range of text types and genres (fiction, professional literature, newspapers etc.) in balanced proportions. The corpus is lemmatized and morphologically tagged by a combination of stochastic and rule-based methods.\r\nThe corpus is provided in a (semi-XML) vertical format used as an input to the Manatee query engine. The data thus correspond to the corpus available via query interface to registered users of the CNC with one important exception: they are shuffled, i.e. divided into blocks sized max. 100 words (respecting the sentence boundaries) whose ordering was randomized within the given document.;2005;corpus;http://hdl.handle.net/11858/00-097C-0000-0023-119E-8;ces;Czech National Corpus (Shuffled Corpus Data);https://lindat.mff.cuni.cz/repository/xmlui/page/license-cnc;ACA;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Faculty of Arts, Institute of the Czech National Corpus, Charles University in Prague;https://wiki.korpus.cz/doku.php/cnk:syn2005",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "024c41ea-dcee-5371-b006-4a3a054021d7",
-    "notes": [
-        "Balanced corpus of contemporary written Czech sized 100 MW. It was created as a representation of written language from 2000\u20132004 and thus it contains a wide range of text types and genres (fiction, professional literature, newspapers etc.) in balanced proportions. The corpus is lemmatized and morphologically tagged by a combination of stochastic and rule-based methods.\r\nThe corpus is provided in a (semi-XML) vertical format used as an input to the Manatee query engine. The data thus correspond to the corpus available via query interface to registered users of the CNC with one important exception: they are shuffled, i.e. divided into blocks sized max. 100 words (respecting the sentence boundaries) whose ordering was randomized within the given document."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-119E-8"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "balanced corpus"
-        },
-        {
-            "name": "written language"
-        }
-    ],
-    "title": [
-        "SYN2005: balanced corpus of written Czech"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/024c58d5-296e-52a5-a7ed-683b368ed24e.json b/oaitestdata/clarin-oai_dc/SET_1/json/024c58d5-296e-52a5-a7ed-683b368ed24e.json
deleted file mode 100644
index a6d3db1e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/024c58d5-296e-52a5-a7ed-683b368ed24e.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/13",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/13"
-    ],
-    "PID": "http://hdl.handle.net/11321/13",
-    "PublicationTimestamp": "2010-07-19T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Marci\u0144czuk, Micha\u0142",
-        "Koco\u0144, Jan",
-        "Marcin, Ptak",
-        "Kaczmarek, Adam"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/13;2016-01-21T14:26:56Z;hdl_11321_3;hdl_11321_4;Inforex;Marci\u0144czuk, Micha\u0142;Koco\u0144, Jan;Marcin, Ptak;Kaczmarek, Adam;Inforex is a web-based system designed for managing and annotating text corpora on the semantic level including annotation of Named Entities (NE), anaphora, Word Sense Disambiguation (WSD) and relations between named entities. The system also supports manual text clean-up and automatic text pre-processing including text segmentation, morphosyntactic analysis and word selection for WSD annotation.;2010-07-19;toolService;http://hdl.handle.net/11321/13;pol;downloadable_files_count: 0;Wroc\u0142aw University of Technology;http://nlp.pwr.wroc.pl/inforex/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "024c58d5-296e-52a5-a7ed-683b368ed24e",
-    "notes": [
-        "Inforex is a web-based system designed for managing and annotating text corpora on the semantic level including annotation of Named Entities (NE), anaphora, Word Sense Disambiguation (WSD) and relations between named entities. The system also supports manual text clean-up and automatic text pre-processing including text segmentation, morphosyntactic analysis and word selection for WSD annotation."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/13"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Inforex"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/026b5eb2-3c0d-5dc2-aa58-5f314abee530.json b/oaitestdata/clarin-oai_dc/SET_1/json/026b5eb2-3c0d-5dc2-aa58-5f314abee530.json
deleted file mode 100644
index 333b1dd7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/026b5eb2-3c0d-5dc2-aa58-5f314abee530.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "text/xml",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Lule Sami"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/107",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/107"
-    ],
-    "PID": "http://hdl.handle.net/11509/107",
-    "PublicationTimestamp": "2015-10-10T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "The Divvun group at UiT The Arctic University of Norway",
-        "Giellatekno - Saami Language Technology, UiT The Arctic University of Norway"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/107;2016-09-06T13:05:44Z;hdl_11509_1;hdl_11509_2;Lule Saami lemma frequency list;Giellatekno - Saami Language Technology, UiT The Arctic University of Norway;The Divvun group at UiT The Arctic University of Norway;Lemma Frequencies;Lule Saami;The Lule Saami lemma frequency list is work done by the Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language community. In particular, Ciprian-Virgil Gerstenberger compiled the list from the entire SIKOR Lule Saami corpus version 2015-10-10. The data is in an one-lemma-per-line format with the following values: <ABS_FREQ> <LEMMA> <POS>. Since the list has been derived automatically, it may contain wrong values. In case you find any errors the creators would appreciate your feedback sent to giellatekno@uit.no and feedback@divvun.no. Please note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata).;2015-10-10;corpus;http://hdl.handle.net/11509/107;smj;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;text/xml;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Giellatekno - Saami Language Technology;http://giellatekno.uit.no/index.eng.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "026b5eb2-3c0d-5dc2-aa58-5f314abee530",
-    "notes": [
-        "The Lule Saami lemma frequency list is work done by the Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language community. In particular, Ciprian-Virgil Gerstenberger compiled the list from the entire SIKOR Lule Saami corpus version 2015-10-10. The data is in an one-lemma-per-line format with the following values: <ABS_FREQ> <LEMMA> <POS>. Since the list has been derived automatically, it may contain wrong values. In case you find any errors the creators would appreciate your feedback sent to giellatekno@uit.no and feedback@divvun.no. Please note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata)."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/107"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Lemma Frequencies"
-        },
-        {
-            "name": "Lule Saami"
-        }
-    ],
-    "title": [
-        "Lule Saami lemma frequency list"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/028d93fe-e644-58cb-bb98-72028958b651.json b/oaitestdata/clarin-oai_dc/SET_1/json/028d93fe-e644-58cb-bb98-72028958b651.json
deleted file mode 100644
index 8a871115..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/028d93fe-e644-58cb-bb98-72028958b651.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4733",
-    "MetadataAccess": [
-        "oai:ota:oucs:4733"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Berquin, M. (Arnaud), 1747-1791."
-    ],
-    "fulltext": "oai:ota:oucs:4733;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4733.xml;The children's friend: Translated from the French of M. Berquin; complete in four volumes. Ornamented with frontispieces. [pt.3];Ami des enfans. English;Berquin, M. (Arnaud), 1747-1791.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "028d93fe-e644-58cb-bb98-72028958b651",
-    "oai_identifier": [
-        "oai:ota:oucs:4733"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The children's friend: Translated from the French of M. Berquin; complete in four volumes. Ornamented with frontispieces. [pt.3]",
-        "Ami des enfans. English"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4733.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/028ee7f7-94f8-502a-a23d-cdb908832f11.json b/oaitestdata/clarin-oai_dc/SET_1/json/028ee7f7-94f8-502a-a23d-cdb908832f11.json
deleted file mode 100644
index e252c5fc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/028ee7f7-94f8-502a-a23d-cdb908832f11.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Department of Linguistics and Nordic Studies, University of Oslo"
-    ],
-    "Contributor": [
-        "Hagen, Kristin"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Norwegian",
-        "Norwegian Nynorsk"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-483",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-483"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-483",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Department of Linguistics and Nordic Studies, University of Oslo"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "GNU General Public License"
-    ],
-    "SpatialCoverage": [
-        "Norway"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-483;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Norwegian Word Bank;Hagen, Kristin;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-483;nor;nno;GNU General Public License;downloadable_files_count: 0;Norway;Department of Linguistics and Nordic Studies, University of Oslo;http://www.edd.uio.no/prosjekt/ordbanken/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "028ee7f7-94f8-502a-a23d-cdb908832f11",
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-483"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Norwegian Word Bank"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0294bfa5-b10c-57af-bb0e-02257d307bb3.json b/oaitestdata/clarin-oai_dc/SET_1/json/0294bfa5-b10c-57af-bb0e-02257d307bb3.json
deleted file mode 100644
index 39e7619a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0294bfa5-b10c-57af-bb0e-02257d307bb3.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/113",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/113"
-    ],
-    "PID": "http://hdl.handle.net/10794/113",
-    "PublicationTimestamp": "2017-10-26T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/113;2017-11-01T13:40:38Z;hdl_10794_1;hdl_10794_2;Blog mix 2016 (2017-10-26);Bloggmix 2016 (2017-10-26);n/a, n/a;n/a, n/a;Swedish;Blog;The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.;Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat.;2017-10-26;corpus;http://hdl.handle.net/10794/113;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/bloggmix2016",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0294bfa5-b10c-57af-bb0e-02257d307bb3",
-    "notes": [
-        "The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.",
-        "Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/113"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Blog"
-        }
-    ],
-    "title": [
-        "Blog mix 2016 (2017-10-26)",
-        "Bloggmix 2016 (2017-10-26)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/029c8fd3-e3fd-53d7-bcc1-7d141c429188.json b/oaitestdata/clarin-oai_dc/SET_1/json/029c8fd3-e3fd-53d7-bcc1-7d141c429188.json
deleted file mode 100644
index e34da716..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/029c8fd3-e3fd-53d7-bcc1-7d141c429188.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4791",
-    "MetadataAccess": [
-        "oai:ota:oucs:4791"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Macpherson, James, 1736-1796."
-    ],
-    "fulltext": "oai:ota:oucs:4791;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4791.xml;Original papers: containing the secret history of Great Britain, from the restoration, to the accession of the House of Hannover. ... The whole arranged and published by James Macpherson, ... [pt.2];Macpherson, James, 1736-1796.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "029c8fd3-e3fd-53d7-bcc1-7d141c429188",
-    "oai_identifier": [
-        "oai:ota:oucs:4791"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Original papers: containing the secret history of Great Britain, from the restoration, to the accession of the House of Hannover. ... The whole arranged and published by James Macpherson, ... [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4791.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/02a47aca-3f0a-5107-9a33-f05e906c5495.json b/oaitestdata/clarin-oai_dc/SET_1/json/02a47aca-3f0a-5107-9a33-f05e906c5495.json
deleted file mode 100644
index 11dbe775..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/02a47aca-3f0a-5107-9a33-f05e906c5495.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "University of Oslo"
-    ],
-    "Contributor": [
-        "Worren, Dagfinn"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Norwegian Nynorsk"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-670",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-670"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-670",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Oslo"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-670;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Nynorskordboka;Worren, Dagfinn;90 000 entries with definitions, etymology, examples;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-670;nno;downloadable_files_count: 0;University of Oslo;http://www.dokpro.uio.no/ordboksoek.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "02a47aca-3f0a-5107-9a33-f05e906c5495",
-    "notes": [
-        "90 000 entries with definitions, etymology, examples"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-670"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Nynorskordboka"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/02a94090-0d1d-593f-9bc4-1a725dc199cf.json b/oaitestdata/clarin-oai_dc/SET_1/json/02a94090-0d1d-593f-9bc4-1a725dc199cf.json
deleted file mode 100644
index 0de1523a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/02a94090-0d1d-593f-9bc4-1a725dc199cf.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/59",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/59"
-    ],
-    "PID": "http://hdl.handle.net/10794/59",
-    "PublicationTimestamp": "2015-04-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/59;2017-10-31T12:35:18Z;hdl_10794_1;hdl_10794_2;ASPAC \u2013 Swedish-Latin (2017-10-16);ASPAC \u2013 svenska-latin (2017-10-16);n/a, n/a;ASPAC;Parallel;Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.;Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat.;2015-04-16;corpus;http://hdl.handle.net/10794/59;swe;lat;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/octet-stream;application/gzip;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/aspacsvla",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "02a94090-0d1d-593f-9bc4-1a725dc199cf",
-    "notes": [
-        "Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.",
-        "Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/59"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ASPAC"
-        },
-        {
-            "name": "Parallel"
-        }
-    ],
-    "title": [
-        "ASPAC \u2013 Swedish-Latin (2017-10-16)",
-        "ASPAC \u2013 svenska-latin (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/02b35811-7a69-53d9-9c09-707ef3c2a812.json b/oaitestdata/clarin-oai_dc/SET_1/json/02b35811-7a69-53d9-9c09-707ef3c2a812.json
deleted file mode 100644
index afb4db68..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/02b35811-7a69-53d9-9c09-707ef3c2a812.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1409",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1409"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1409",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1409;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;freeling_dependency;Freeling-based dependency parser.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1409;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "02b35811-7a69-53d9-9c09-707ef3c2a812",
-    "notes": [
-        "Freeling-based dependency parser."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1409"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "freeling_dependency"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/02e11e4f-a9e7-5f26-8464-77824d43d05f.json b/oaitestdata/clarin-oai_dc/SET_1/json/02e11e4f-a9e7-5f26-8464-77824d43d05f.json
deleted file mode 100644
index aad25dee..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/02e11e4f-a9e7-5f26-8464-77824d43d05f.json
+++ /dev/null
@@ -1,182 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/x-tar",
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Belarusian",
-        "Bosnian",
-        "Bulgarian",
-        "Czech",
-        "Croatian",
-        "Upper Sorbian",
-        "Macedonian",
-        "Polish",
-        "Russian",
-        "Slovak",
-        "Slovenian",
-        "Serbian",
-        "Ukrainian",
-        "Latvian",
-        "Lithuanian",
-        "Afrikaans",
-        "Danish",
-        "German",
-        "English",
-        "Faroese",
-        "Western Frisian",
-        "Swiss German",
-        "Icelandic",
-        "Limburgan",
-        "Luxembourgish",
-        "Low German",
-        "Dutch",
-        "Norwegian Nynorsk",
-        "Norwegian",
-        "Scots",
-        "Swedish",
-        "Yiddish",
-        "Aragonese",
-        "Asturian",
-        "Catalan",
-        "French",
-        "Galician",
-        "Haitian",
-        "Italian",
-        "Latin",
-        "Neapolitan",
-        "Portuguese",
-        "Romanian",
-        "Spanish",
-        "Walloon",
-        "Breton",
-        "Welsh",
-        "Scottish Gaelic",
-        "Irish",
-        "Modern Greek (1453-)",
-        "Armenian",
-        "Albanian",
-        "Persian",
-        "Kurdish",
-        "Tajik",
-        "Bengali",
-        "Gujarati",
-        "Hindi",
-        "Marathi",
-        "Nepali (macrolanguage)",
-        "Urdu",
-        "Amharic",
-        "Arabic",
-        "Hebrew",
-        "Estonian",
-        "Finnish",
-        "Hungarian",
-        "Basque",
-        "Georgian",
-        "Chuvash",
-        "Azerbaijani",
-        "Turkish",
-        "Uzbek",
-        "Kazakh",
-        "Tatar",
-        "Yakut",
-        "Korean",
-        "Mongolian",
-        "Telugu",
-        "Kannada",
-        "Malayalam",
-        "Tamil",
-        "Newari",
-        "Vietnamese",
-        "Indonesian",
-        "Javanese",
-        "Malagasy",
-        "Maori",
-        "Malay (macrolanguage)",
-        "Pampanga",
-        "Sundanese",
-        "Tagalog",
-        "Waray (Philippines)",
-        "Swahili (macrolanguage)",
-        "Esperanto",
-        "Ido",
-        "Interlingua (International Auxiliary Language Association)",
-        "Volap\u00fck"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1662",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1662"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1662",
-    "PublicationTimestamp": "2016-03-17T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-1743"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "Yu, Zhiwei",
-        "Zeman, Daniel",
-        "Mare\u010dek, David"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1662;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Deltacorpus;Mare\u010dek, David;Yu, Zhiwei;Zeman, Daniel;\u017dabokrtsk\u00fd, Zden\u011bk;part of speech;tagging;semi-supervised;cross-language;Texts in 107 languages from the W2C corpus (http://hdl.handle.net/11858/00-097C-0000-0022-6133-9), first 1,000,000 tokens per language, tagged by the delexicalized tagger described in Yu et al. (2016, LREC, Portoro\u017e, Slovenia).;2016-03-17;corpus;http://hdl.handle.net/11234/1-1662;bel;bos;bul;ces;hbs;hrv;hsb;mkd;pol;rus;slk;slv;srp;ukr;lav;lit;afr;dan;deu;eng;fao;fry;gsw;isl;lim;ltz;nds;nld;nno;nor;sco;swe;yid;arg;ast;cat;fra;glg;hat;ita;lat;lmo;nap;pms;por;ron;spa;vec;wln;bre;cym;gla;gle;ell;hye;sqi;diq;fas;glk;kur;tgk;ben;bpy;guj;hif;hin;mar;nep;urd;amh;ara;arz;heb;est;fin;hun;eus;kat;chv;aze;tur;uzb;kaz;tat;sah;kor;mon;tel;kan;mal;tam;new;vie;ind;jav;mlg;mri;msa;pam;sun;tgl;war;swa;epo;ido;ina;vol;http://hdl.handle.net/11234/1-1743;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;PUB;application/x-tar;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/deltacorpus",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "02e11e4f-a9e7-5f26-8464-77824d43d05f",
-    "notes": [
-        "Texts in 107 languages from the W2C corpus (http://hdl.handle.net/11858/00-097C-0000-0022-6133-9), first 1,000,000 tokens per language, tagged by the delexicalized tagger described in Yu et al. (2016, LREC, Portoro\u017e, Slovenia)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1662"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "part speech"
-        },
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "semi-supervised"
-        },
-        {
-            "name": "cross-language"
-        }
-    ],
-    "title": [
-        "Deltacorpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/02f74897-7eb7-53f0-91a9-d5006053a8ec.json b/oaitestdata/clarin-oai_dc/SET_1/json/02f74897-7eb7-53f0-91a9-d5006053a8ec.json
deleted file mode 100644
index 8ef31ac3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/02f74897-7eb7-53f0-91a9-d5006053a8ec.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "IPI PAN"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 4",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/390",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/390"
-    ],
-    "PID": "http://hdl.handle.net/11321/390",
-    "PublicationTimestamp": "2017-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "IPI PAN"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Domis, Julia"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/390;2017-05-30T11:54:58Z;hdl_11321_3;hdl_11321_4;Corpus_Sienkiewicz_Novels;Domis, Julia;Corpus;Sienkiewicz;novels;Sienkiewicz Novels;2017-05-30;corpus;http://hdl.handle.net/11321/390;pol;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;text/plain; charset=utf-8;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/zip;downloadable_files_count: 4;IPI PAN",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "02f74897-7eb7-53f0-91a9-d5006053a8ec",
-    "notes": [
-        "Sienkiewicz Novels"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/390"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Corpus"
-        },
-        {
-            "name": "Sienkiewicz"
-        },
-        {
-            "name": "novels"
-        }
-    ],
-    "title": [
-        "Corpus_Sienkiewicz_Novels"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/02f8c282-227d-5efb-8bdb-2a2437631b4c.json b/oaitestdata/clarin-oai_dc/SET_1/json/02f8c282-227d-5efb-8bdb-2a2437631b4c.json
deleted file mode 100644
index cac6c1f9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/02f8c282-227d-5efb-8bdb-2a2437631b4c.json
+++ /dev/null
@@ -1,88 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1702",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1702"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1702",
-    "PublicationTimestamp": "2016-05-23T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Mozilla Public License 2.0",
-        "http://opensource.org/licenses/MPL-2.0",
-        "PUB"
-    ],
-    "author": [
-        "Straka, Milan",
-        "Strakov\u00e1, Jana"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1702;2018-07-02T22:05:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;UDPipe;Straka, Milan;Strakov\u00e1, Jana;tokenizer;POS tagger;tagger;lemmatization;parser;dependency parser;CoNLL-U;UDPipe is an trainable pipeline for tokenization, tagging, lemmatization and dependency parsing of CoNLL-U files. UDPipe is language-agnostic and can be trained given only annotated data in CoNLL-U format. Trained models are provided for nearly all UD treebanks. UDPipe is available as a binary, as a library for C++, Python, Perl, Java, C#, and as a web service.\r\n\r\nUDPipe is a free software under Mozilla Public License 2.0 (http://www.mozilla.org/MPL/2.0/) and the linguistic models are free for non-commercial use and distributed under CC BY-NC-SA (http://creativecommons.org/licenses/by-nc-sa/4.0/) license, although for some models the original data used to create the model may impose additional licensing conditions. UDPipe is versioned using Semantic Versioning (http://semver.org/).\r\n\r\nUDPipe website http://ufal.mff.cuni.cz/udpipe contains download links of both the released packages and trained models, hosts documentation and offers online demo.\r\n\r\nUDPipe development repository http://github.com/ufal/udpipe is hosted on GitHub.;2016-05-23;toolService;http://hdl.handle.net/11234/1-1702;eng;Mozilla Public License 2.0;http://opensource.org/licenses/MPL-2.0;PUB;application/zip;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/udpipe",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "02f8c282-227d-5efb-8bdb-2a2437631b4c",
-    "notes": [
-        "UDPipe is an trainable pipeline for tokenization, tagging, lemmatization and dependency parsing of CoNLL-U files. UDPipe is language-agnostic and can be trained given only annotated data in CoNLL-U format. Trained models are provided for nearly all UD treebanks. UDPipe is available as a binary, as a library for C++, Python, Perl, Java, C#, and as a web service.\r\n\r\nUDPipe is a free software under Mozilla Public License 2.0 (http://www.mozilla.org/MPL/2.0/) and the linguistic models are free for non-commercial use and distributed under CC BY-NC-SA (http://creativecommons.org/licenses/by-nc-sa/4.0/) license, although for some models the original data used to create the model may impose additional licensing conditions. UDPipe is versioned using Semantic Versioning (http://semver.org/).\r\n\r\nUDPipe website http://ufal.mff.cuni.cz/udpipe contains download links of both the released packages and trained models, hosts documentation and offers online demo.\r\n\r\nUDPipe development repository http://github.com/ufal/udpipe is hosted on GitHub."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1702"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "tokenizer"
-        },
-        {
-            "name": "POS tagger"
-        },
-        {
-            "name": "tagger"
-        },
-        {
-            "name": "lemmatization"
-        },
-        {
-            "name": "parser"
-        },
-        {
-            "name": "dependency parser"
-        },
-        {
-            "name": "CoNLL-U"
-        }
-    ],
-    "title": [
-        "UDPipe"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0307fed5-6d32-583f-a0d3-71884ea9c7ba.json b/oaitestdata/clarin-oai_dc/SET_1/json/0307fed5-6d32-583f-a0d3-71884ea9c7ba.json
deleted file mode 100644
index e09ed7e1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0307fed5-6d32-583f-a0d3-71884ea9c7ba.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 444 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2048",
-    "MetadataAccess": [
-        "oai:ota:oucs:2048"
-    ],
-    "PublicationTimestamp": "1911-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1911"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Burnett, Frances Hodgson, 1849-1924"
-    ],
-    "fulltext": "oai:ota:oucs:2048;2018-05-17T09:29:11Z;http://ota.ox.ac.uk/headers/2048.xml;The secret garden / by Frances Hodgson Burnett;Burnett, Frances Hodgson, 1849-1924;1911;text_and_corpus_linguistics;Juvenile literature -- United States -- 20th century;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 444 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0307fed5-6d32-583f-a0d3-71884ea9c7ba",
-    "oai_identifier": [
-        "oai:ota:oucs:2048"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Juvenile literature -- United States -- th century"
-        }
-    ],
-    "title": [
-        "The secret garden / by Frances Hodgson Burnett"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2048.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/031561b9-6128-5c62-98c1-bd347e50643c.json b/oaitestdata/clarin-oai_dc/SET_1/json/031561b9-6128-5c62-98c1-bd347e50643c.json
deleted file mode 100644
index ed7be277..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/031561b9-6128-5c62-98c1-bd347e50643c.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4839",
-    "MetadataAccess": [
-        "oai:ota:oucs:4839"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Donovan, E. (Edward), 1768-1837."
-    ],
-    "fulltext": "oai:ota:oucs:4839;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4839.xml;Instructions for collecting and preserving various subjects of natural history; as animals, birds, reptiles, shells, corals, plants, &c. Together with A treatise on the management of insects in their several states; selected from the best authorities. By E. Donovan,;Donovan, E. (Edward), 1768-1837.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "031561b9-6128-5c62-98c1-bd347e50643c",
-    "oai_identifier": [
-        "oai:ota:oucs:4839"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Instructions for collecting and preserving various subjects of natural history; as animals, birds, reptiles, shells, corals, plants, &c. Together with A treatise on the management of insects in their several states; selected from the best authorities. By E. Donovan,"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4839.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/031a709c-6a6c-5f32-9c0b-7605b8193cd6.json b/oaitestdata/clarin-oai_dc/SET_1/json/031a709c-6a6c-5f32-9c0b-7605b8193cd6.json
deleted file mode 100644
index 968c2864..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/031a709c-6a6c-5f32-9c0b-7605b8193cd6.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=03dac3a2615d11e2a2aa782bcb074135e14195826bfd40c6a8d67b1448380342",
-    "MetadataAccess": [
-        "03dac3a2615d11e2a2aa782bcb074135e14195826bfd40c6a8d67b1448380342"
-    ],
-    "PublicationTimestamp": "2013-02-05T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "03dac3a2615d11e2a2aa782bcb074135e14195826bfd40c6a8d67b1448380342;2018-11-15T16:40:03Z;lexicalConceptualResource;lexicalConceptualResource:lexicon;Maltese Speech Engine Lexicon;This lexicon is a speech lexicon, exported from Crimsonwing\u00e2\u0080\u0099s text-to-speech (TTS) database into a .txt file. In its original form and together with the Maltese Speech Engine Diphone repository, it was used for building Crimsonwing\u00e2\u0080\u0099s text-to-speech system.\n\nThe file is in txt format, with each line per word form containing the information of part of speech, written form, phonetic form, syllables, stress position and language (separated by commas).\n\nAfter unzipping the file, the folder contains the files:\n- lexicon_export_2012_12_19.txt\n- Maltese_Speech_Engine_Lexicon_NarrativeDescription.doc\n- Maltese TTS - Database Schema.pdf (the original documentation for the entire speech database)\nWith one entry per line and data values separated by comma, the structure of an entry follows the structure:  PartOfSpeech,WrittenForm,PhoneticForm,Syllables,StressPosition,Language\n\nFor example, the verb form niktbu \u00e2\u0080\u009cwe write\u00e2\u0080\u009d is represented as:\nVerb,niktbu,n\u00c9\u00aagdb\u00ca\u008a,n\u00c9\u00aag-db\u00ca\u008a,1,Maltese\n\nThe attributes and values in the lexicon are:\n\n\u00e2\u0080\u00a2\tPartOfSpeech (Abbreviation, Acronym, Adjective, Adverb, Article, Conjunction, Interjection, Letter, Noun, Numeral, Participle, Preposition, Pronoun, Verb, Unknown)\n\u00e2\u0080\u00a2\tWrittenForm (string: orthographical representation of the entries)\n\u00e2\u0080\u00a2\tPhoneticForm (string: representation of the entries in IPA)\n\u00e2\u0080\u00a2\tSyllables (string: representation of the entries in IPA, with syllable boundaries indicated with a hyphen)\n\u00e2\u0080\u00a2\tStressPosition (number indicating the syllable carrying word stress; values are: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9)\n\u00e2\u0080\u00a2\tLanguage (English, French, Italian, Maltese, Unknown)\n\nNB: The value \u00e2\u0080\u009c0\u00e2\u0080\u009d for stress position only applies to two entries which do not contain values for PhoneticForm and Syllables (for some unknown reason). The respective word forms are the adjective iffullata \u00e2\u0080\u009ccrowded, congested\u00e2\u0080\u009d and the participle immankat \u00e2\u0080\u009cmutilated, disabled\u00e2\u0080\u009d. ;2013-02-05",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "031a709c-6a6c-5f32-9c0b-7605b8193cd6",
-    "notes": [
-        "This lexicon is a speech lexicon, exported from Crimsonwing\u00e2\u0080\u0099s text-to-speech (TTS) database into a .txt file. In its original form and together with the Maltese Speech Engine Diphone repository, it was used for building Crimsonwing\u00e2\u0080\u0099s text-to-speech system.\n\nThe file is in txt format, with each line per word form containing the information of part of speech, written form, phonetic form, syllables, stress position and language (separated by commas).\n\nAfter unzipping the file, the folder contains the files:\n- lexicon_export_2012_12_19.txt\n- Maltese_Speech_Engine_Lexicon_NarrativeDescription.doc\n- Maltese TTS - Database Schema.pdf (the original documentation for the entire speech database)\nWith one entry per line and data values separated by comma, the structure of an entry follows the structure:  PartOfSpeech,WrittenForm,PhoneticForm,Syllables,StressPosition,Language\n\nFor example, the verb form niktbu \u00e2\u0080\u009cwe write\u00e2\u0080\u009d is represented as:\nVerb,niktbu,n\u00c9\u00aagdb\u00ca\u008a,n\u00c9\u00aag-db\u00ca\u008a,1,Maltese\n\nThe attributes and values in the lexicon are:\n\n\u00e2\u0080\u00a2\tPartOfSpeech (Abbreviation, Acronym, Adjective, Adverb, Article, Conjunction, Interjection, Letter, Noun, Numeral, Participle, Preposition, Pronoun, Verb, Unknown)\n\u00e2\u0080\u00a2\tWrittenForm (string: orthographical representation of the entries)\n\u00e2\u0080\u00a2\tPhoneticForm (string: representation of the entries in IPA)\n\u00e2\u0080\u00a2\tSyllables (string: representation of the entries in IPA, with syllable boundaries indicated with a hyphen)\n\u00e2\u0080\u00a2\tStressPosition (number indicating the syllable carrying word stress; values are: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9)\n\u00e2\u0080\u00a2\tLanguage (English, French, Italian, Maltese, Unknown)\n\nNB: The value \u00e2\u0080\u009c0\u00e2\u0080\u009d for stress position only applies to two entries which do not contain values for PhoneticForm and Syllables (for some unknown reason). The respective word forms are the adjective iffullata \u00e2\u0080\u009ccrowded, congested\u00e2\u0080\u009d and the participle immankat \u00e2\u0080\u009cmutilated, disabled\u00e2\u0080\u009d. "
-    ],
-    "oai_identifier": [
-        "03dac3a2615d11e2a2aa782bcb074135e14195826bfd40c6a8d67b1448380342"
-    ],
-    "oai_set": [
-        "lexicalConceptualResource",
-        "lexicalConceptualResource:lexicon"
-    ],
-    "state": "active",
-    "title": [
-        "Maltese Speech Engine Lexicon"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/032cd5ce-25f1-5a55-9364-fdfa1e31124a.json b/oaitestdata/clarin-oai_dc/SET_1/json/032cd5ce-25f1-5a55-9364-fdfa1e31124a.json
deleted file mode 100644
index 7f0f9351..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/032cd5ce-25f1-5a55-9364-fdfa1e31124a.json
+++ /dev/null
@@ -1,112 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 12",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Bulgarian",
-        "Czech",
-        "English",
-        "Estonian",
-        "French",
-        "Hungarian",
-        "Romanian",
-        "Slovak",
-        "Slovenian",
-        "Ukrainian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1041",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1041"
-    ],
-    "PID": "http://hdl.handle.net/11356/1041",
-    "PublicationTimestamp": "2010-05-14T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/211938",
-        "https://doi.org/10.1007/s10579-011-9174-8",
-        "http://hdl.handle.net/11372/LRT-675"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "https://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Shevchenko, Igor",
-        "Oravecz, Csaba",
-        "Kaalep, Heiki-Jaan",
-        "Petkevi\u010d, Vladim\u00edr",
-        "Dimitrova, Ludmila",
-        "Steenwijk, Han",
-        "Priest-Dorman, Greg",
-        "Tihanyi, Laszlo",
-        "Kotsyba, Natalia",
-        "Tufi\u015f, Dan",
-        "V\u00e9ronis, Jean",
-        "Garab\u00edk, Radovan",
-        "Erjavec, Toma\u017e",
-        "Sinapova, Lydia",
-        "Holozan, Peter",
-        "Derzhanski, Ivan",
-        "Bruda, \u015etefan",
-        "Simov, Kiril",
-        "Ide, Nancy"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1041;2018-05-28T11:25:35Z;hdl_11356_1023;hdl_11356_1024;MULTEXT-East free lexicons  4.0;Erjavec, Toma\u017e;Bruda, \u015etefan;Derzhanski, Ivan;Dimitrova, Ludmila;Garab\u00edk, Radovan;Holozan, Peter;Ide, Nancy;Kaalep, Heiki-Jaan;Kotsyba, Natalia;Oravecz, Csaba;Petkevi\u010d, Vladim\u00edr;Priest-Dorman, Greg;Shevchenko, Igor;Simov, Kiril;Sinapova, Lydia;Steenwijk, Han;Tihanyi, Laszlo;Tufi\u015f, Dan;V\u00e9ronis, Jean;lemmatisation;inflection;tagging;multilingual;The MULTEXT-East morphosyntactic lexicons have a simple structure, where each line is a lexical entry with three tab-separated fields: (1) the word-form, the inflected form of the word; (2) the lemma, the base-form of the word; (3) the MSD, the morphosyntactic description of the word-form, i.e., its fine-grained PoS tag, as defined in the MULTEXT-East morphosyntactic specifications.\r\n\r\nThis submission contains the freely available MULTEXT-East lexicons, while a separate submission (http://hdl.handle.net/11356/1042) gives those that are available only for non-commercial use.;2010-05-14;lexicalConceptualResource;http://hdl.handle.net/11356/1041;bul;ces;eng;est;fra;hun;ron;slk;slv;ukr;info:eu-repo/grantAgreement/EC/FP7/211938;https://doi.org/10.1007/s10579-011-9174-8;http://hdl.handle.net/11372/LRT-675;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);https://creativecommons.org/licenses/by-sa/4.0/;PUB;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;text/plain;text/plain; charset=utf-8;downloadable_files_count: 12;Jo\u017eef Stefan Institute;http://nl.ijs.si/ME/V4/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "032cd5ce-25f1-5a55-9364-fdfa1e31124a",
-    "notes": [
-        "The MULTEXT-East morphosyntactic lexicons have a simple structure, where each line is a lexical entry with three tab-separated fields: (1) the word-form, the inflected form of the word; (2) the lemma, the base-form of the word; (3) the MSD, the morphosyntactic description of the word-form, i.e., its fine-grained PoS tag, as defined in the MULTEXT-East morphosyntactic specifications.\r\n\r\nThis submission contains the freely available MULTEXT-East lexicons, while a separate submission (http://hdl.handle.net/11356/1042) gives those that are available only for non-commercial use."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1041"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "lemmatisation"
-        },
-        {
-            "name": "inflection"
-        },
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "multilingual"
-        }
-    ],
-    "title": [
-        "MULTEXT-East free lexicons  4.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0331fbf8-1cba-56bd-b8ba-41645a3d61bc.json b/oaitestdata/clarin-oai_dc/SET_1/json/0331fbf8-1cba-56bd-b8ba-41645a3d61bc.json
deleted file mode 100644
index daa041b1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0331fbf8-1cba-56bd-b8ba-41645a3d61bc.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3368",
-    "MetadataAccess": [
-        "oai:ota:oucs:3368"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Blair, Hugh, 1718-1800."
-    ],
-    "fulltext": "oai:ota:oucs:3368;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3368.xml;Lectures on rhetoric and belles lettres: By Hugh Blair, ... In three volumes. ... [pt.1];Blair, Hugh, 1718-1800.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0331fbf8-1cba-56bd-b8ba-41645a3d61bc",
-    "oai_identifier": [
-        "oai:ota:oucs:3368"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Lectures on rhetoric and belles lettres: By Hugh Blair, ... In three volumes. ... [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3368.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0332f318-f4eb-5904-a7eb-d4f54ab94c42.json b/oaitestdata/clarin-oai_dc/SET_1/json/0332f318-f4eb-5904-a7eb-d4f54ab94c42.json
deleted file mode 100644
index 42bd3d7f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0332f318-f4eb-5904-a7eb-d4f54ab94c42.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Finnish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-827",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-827"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-827",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Finland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-827;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Parole frequency list;frequency list of the Parole corpus, 1 339 787 words;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-827;fin;downloadable_files_count: 0;Finland;http://kaino.kotus.fi/sanat/taajuuslista/parole.php",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0332f318-f4eb-5904-a7eb-d4f54ab94c42",
-    "notes": [
-        "frequency list of the Parole corpus, 1 339 787 words"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-827"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Parole frequency list"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/033d2dc9-eca0-510a-8aec-0fa68a0850c5.json b/oaitestdata/clarin-oai_dc/SET_1/json/033d2dc9-eca0-510a-8aec-0fa68a0850c5.json
deleted file mode 100644
index 5c4f43af..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/033d2dc9-eca0-510a-8aec-0fa68a0850c5.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/72",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/72"
-    ],
-    "PID": "http://hdl.handle.net/10794/72",
-    "PublicationTimestamp": "2015-04-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/72;2017-10-31T15:43:48Z;hdl_10794_1;hdl_10794_2;ASPAC \u2013 Swedish-Spanish (2017-10-16);ASPAC \u2013 svenska-spanska (2017-10-16);n/a, n/a;ASPAC;Parallel;Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.;Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat.;2015-04-16;corpus;http://hdl.handle.net/10794/72;swe;spa;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/octet-stream;application/gzip;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/aspacsves",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "033d2dc9-eca0-510a-8aec-0fa68a0850c5",
-    "notes": [
-        "Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.",
-        "Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/72"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ASPAC"
-        },
-        {
-            "name": "Parallel"
-        }
-    ],
-    "title": [
-        "ASPAC \u2013 Swedish-Spanish (2017-10-16)",
-        "ASPAC \u2013 svenska-spanska (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0364b704-df99-5208-88ce-28cf002a4b24.json b/oaitestdata/clarin-oai_dc/SET_1/json/0364b704-df99-5208-88ce-28cf002a4b24.json
deleted file mode 100644
index 22cc5b47..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0364b704-df99-5208-88ce-28cf002a4b24.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 24",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/225",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/225"
-    ],
-    "PID": "http://hdl.handle.net/11321/225",
-    "PublicationTimestamp": "2015-09-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Piasecki, Maciej",
-        "M\u0142ynarczyk, Ksenia"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/225;2015-09-01T07:44:35Z;hdl_11321_3;hdl_11321_4;24 novels;M\u0142ynarczyk, Ksenia;Piasecki, Maciej;Selected novels translated into polish;2015-09-01;corpus;http://hdl.handle.net/11321/225;Polish;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain; charset=utf-8;downloadable_files_count: 24;Wroc\u0142aw University of Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0364b704-df99-5208-88ce-28cf002a4b24",
-    "notes": [
-        "Selected novels translated into polish"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/225"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "24 novels"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/036b7e64-26ec-522a-8a12-5d67b2175941.json b/oaitestdata/clarin-oai_dc/SET_1/json/036b7e64-26ec-522a-8a12-5d67b2175941.json
deleted file mode 100644
index 056b2618..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/036b7e64-26ec-522a-8a12-5d67b2175941.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "University of Zagreb, Faculty of Humanities and Social Sciences"
-    ],
-    "Contributor": [
-        "Tadi\u0107, Marko"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Croatian",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-237",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-237"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-237",
-    "PublicationTimestamp": "2010-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "University of Zagreb, Faculty of Humanities and Social Sciences"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Croatia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-237;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Croatian-English Parallel Corpus;Tadi\u0107, Marko;written; domain-specific (newspaper); synchronic; bilingual; parallel; unidirectional; XML; S-alignment;2010;corpus;http://hdl.handle.net/11372/LRT-237;hrv;eng;downloadable_files_count: 0;Croatia;University of Zagreb, Faculty of Humanities and Social Sciences;http://hnk.ffzg.hr",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "036b7e64-26ec-522a-8a12-5d67b2175941",
-    "notes": [
-        "written; domain-specific (newspaper); synchronic; bilingual; parallel; unidirectional; XML; S-alignment"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-237"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Croatian-English Parallel Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0381799e-265f-549b-8c54-b72f7b06532b.json b/oaitestdata/clarin-oai_dc/SET_1/json/0381799e-265f-549b-8c54-b72f7b06532b.json
deleted file mode 100644
index 1a8b0257..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0381799e-265f-549b-8c54-b72f7b06532b.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4652",
-    "MetadataAccess": [
-        "oai:ota:oucs:4652"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gibbon, Edward, 1737-1794."
-    ],
-    "fulltext": "oai:ota:oucs:4652;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4652.xml;Miscellaneous works: of Edward Gibbon, Esquire. With memoirs of his life and writings, composed by himself: illustrated from his letters, with occasional notes and narrative, by John Lord Sheffield. In two volumes. ... [pt.1];Gibbon, Edward, 1737-1794.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0381799e-265f-549b-8c54-b72f7b06532b",
-    "oai_identifier": [
-        "oai:ota:oucs:4652"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Miscellaneous works: of Edward Gibbon, Esquire. With memoirs of his life and writings, composed by himself: illustrated from his letters, with occasional notes and narrative, by John Lord Sheffield. In two volumes. ... [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4652.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0396f546-ea7f-5f70-9113-8ba5f073766a.json b/oaitestdata/clarin-oai_dc/SET_1/json/0396f546-ea7f-5f70-9113-8ba5f073766a.json
deleted file mode 100644
index ec41fae5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0396f546-ea7f-5f70-9113-8ba5f073766a.json
+++ /dev/null
@@ -1,49 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-684",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-684"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-684",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Code of conduct"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-684;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;People of the Center corpus;Documentation of the People of the Center project (DoBeS project);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-684;Code of conduct;downloadable_files_count: 0;http://corpus1.mpi.nl/ds/imdi_browser/?openpath=MPI360494%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0396f546-ea7f-5f70-9113-8ba5f073766a",
-    "notes": [
-        "Documentation of the People of the Center project (DoBeS project)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-684"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "People of the Center corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/039aaac3-62ab-53d0-803a-00da51ac7a66.json b/oaitestdata/clarin-oai_dc/SET_1/json/039aaac3-62ab-53d0-803a-00da51ac7a66.json
deleted file mode 100644
index 5edb1f63..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/039aaac3-62ab-53d0-803a-00da51ac7a66.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2731",
-    "MetadataAccess": [
-        "oai:ota:oucs:2731"
-    ],
-    "PublicationTimestamp": "1738-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1738"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2731;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2731.xml;The Examiner;Swift, Jonathan, 1667-1745;1738;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "039aaac3-62ab-53d0-803a-00da51ac7a66",
-    "oai_identifier": [
-        "oai:ota:oucs:2731"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The Examiner"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2731.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/03b622e4-9dbb-5aa1-828f-45abd535acca.json b/oaitestdata/clarin-oai_dc/SET_1/json/03b622e4-9dbb-5aa1-828f-45abd535acca.json
deleted file mode 100644
index 50e94a41..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/03b622e4-9dbb-5aa1-828f-45abd535acca.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contributor": [
-        "Monachini, Monica"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Bulgarian",
-        "English",
-        "Modern Greek (1453-)",
-        "Serbian",
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-474",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-474"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-474",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Italy"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-474;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;INTERA Terminological Lexicon;Monachini, Monica;17357 terms, XML;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-474;bul;eng;ell;srp;slv;downloadable_files_count: 0;Italy;http://www.ilc.cnr.it/intera_prg/papers/INTERA_D5.1.zip",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "03b622e4-9dbb-5aa1-828f-45abd535acca",
-    "notes": [
-        "17357 terms, XML"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-474"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "INTERA Terminological Lexicon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/03c22d6c-3c53-579e-be13-b7cca790759c.json b/oaitestdata/clarin-oai_dc/SET_1/json/03c22d6c-3c53-579e-be13-b7cca790759c.json
deleted file mode 100644
index 46ed1465..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/03c22d6c-3c53-579e-be13-b7cca790759c.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5601",
-    "MetadataAccess": [
-        "oai:ota:oucs:5601"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Shebbeare, John, 1709-1788."
-    ],
-    "fulltext": "oai:ota:oucs:5601;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5601.xml;A new analysis of the Bristol waters: together with the cause of the diabetes and hectic. And their cure, as it results from those waters, experimentally consider'd. ... By John Shebbeare, ...;Shebbeare, John, 1709-1788.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "03c22d6c-3c53-579e-be13-b7cca790759c",
-    "oai_identifier": [
-        "oai:ota:oucs:5601"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A new analysis of the Bristol waters: together with the cause of the diabetes and hectic. And their cure, as it results from those waters, experimentally consider'd. ... By John Shebbeare, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5601.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/03ca9b43-cb90-5657-96a4-04c798d7c574.json b/oaitestdata/clarin-oai_dc/SET_1/json/03ca9b43-cb90-5657-96a4-04c798d7c574.json
deleted file mode 100644
index cbe706ea..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/03ca9b43-cb90-5657-96a4-04c798d7c574.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1158",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1158"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1158",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1158;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Pierer's Universal-Lexikon;Germanistik;4. Aufl. 1857-1865; wortgenaue Seitenkonkordanz zu der gedruckten Ausgabe; laut dem im Untertitel angegebenen Eigenanspruch ein \"enzyklop\u00e4disches W\u00f6rterbuch\";2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1158;deu;downloadable_files_count: 0;http://www.zeno.org/Pierer-1857",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "03ca9b43-cb90-5657-96a4-04c798d7c574",
-    "notes": [
-        "4. Aufl. 1857-1865; wortgenaue Seitenkonkordanz zu der gedruckten Ausgabe; laut dem im Untertitel angegebenen Eigenanspruch ein \"enzyklop\u00e4disches W\u00f6rterbuch\""
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1158"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Pierer's Universal-Lexikon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/03d66613-8210-5d3b-83c7-ba888f8f89a3.json b/oaitestdata/clarin-oai_dc/SET_1/json/03d66613-8210-5d3b-83c7-ba888f8f89a3.json
deleted file mode 100644
index bcd450cd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/03d66613-8210-5d3b-83c7-ba888f8f89a3.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish",
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/75",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/75"
-    ],
-    "PID": "http://hdl.handle.net/10794/75",
-    "PublicationTimestamp": "2015-04-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/75;2017-10-31T15:50:37Z;hdl_10794_1;hdl_10794_2;ASPAC \u2013 Swedish-German (2017-10-16);ASPAC \u2013 svenska-tyska (2017-10-16);n/a, n/a;ASPAC;Parallel;Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.;Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat.;2015-04-16;corpus;http://hdl.handle.net/10794/75;swe;deu;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/octet-stream;application/gzip;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/aspacsvde",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "03d66613-8210-5d3b-83c7-ba888f8f89a3",
-    "notes": [
-        "Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.",
-        "Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/75"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ASPAC"
-        },
-        {
-            "name": "Parallel"
-        }
-    ],
-    "title": [
-        "ASPAC \u2013 Swedish-German (2017-10-16)",
-        "ASPAC \u2013 svenska-tyska (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/03de6f64-dc62-58d6-82f3-1e1073f8e7d2.json b/oaitestdata/clarin-oai_dc/SET_1/json/03de6f64-dc62-58d6-82f3-1e1073f8e7d2.json
deleted file mode 100644
index 16813288..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/03de6f64-dc62-58d6-82f3-1e1073f8e7d2.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia J.K.Mci i Rzeczyplitey u XX. Scholarum Piarum"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-400",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-400"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D1A-3",
-    "PublicationTimestamp": "1768-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1768"
-    ],
-    "Publisher": [
-        "Drukarnia J.K.Mci i Rzeczyplitey u XX. Scholarum Piarum"
-    ],
-    "RelatedIdentifier": [
-        "http://pbc.biaman.pl/Content/400"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-400;2019-03-01T15:27:36Z;Konstytucye Seymu Extraordynaryinego w Warszawie, Roku MDCCLXVII. Dnia pi\u0105tego pa\u017adziernika z\u0142o\u017conego y zacz\u0119tego, a z Limitacyi y prorogacyi roku MDCCLXVIII. Dnia pi\u0105tego Marca, przy rozwi\u0105zaniu Konfederacyi Generalnych Koronney y Wielkiego Xi\u0119stwa Litewskiego zako\u0144czonego [...] ustanowione.;Konstytucja 1768 r.;Drukarnia J.K.Mci i Rzeczyplitey u XX. Scholarum Piarum;1768;starodruk;application/xml;clarind-uds:poldilemma-400;hdl:11858/00-246C-0000-0023-8D1A-3;pol;lat;http://pbc.biaman.pl/Content/400;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "03de6f64-dc62-58d6-82f3-1e1073f8e7d2",
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-400"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Konstytucja r."
-        }
-    ],
-    "title": [
-        "Konstytucye Seymu Extraordynaryinego w Warszawie, Roku MDCCLXVII. Dnia pi\u0105tego pa\u017adziernika z\u0142o\u017conego y zacz\u0119tego, a z Limitacyi y prorogacyi roku MDCCLXVIII. Dnia pi\u0105tego Marca, przy rozwi\u0105zaniu Konfederacyi Generalnych Koronney y Wielkiego Xi\u0119stwa Litewskiego zako\u0144czonego [...] ustanowione."
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/03f1226a-9808-5f25-8b85-1518f885aa4e.json b/oaitestdata/clarin-oai_dc/SET_1/json/03f1226a-9808-5f25-8b85-1518f885aa4e.json
deleted file mode 100644
index 2fdd5141..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/03f1226a-9808-5f25-8b85-1518f885aa4e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4292",
-    "MetadataAccess": [
-        "oai:ota:oucs:4292"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Smollett, Tobias George, 1721-1771."
-    ],
-    "fulltext": "oai:ota:oucs:4292;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4292.xml;The history and adventures of an atom: In two volumes. ... [pt.1];Smollett, Tobias George, 1721-1771.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "03f1226a-9808-5f25-8b85-1518f885aa4e",
-    "oai_identifier": [
-        "oai:ota:oucs:4292"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The history and adventures of an atom: In two volumes. ... [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4292.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0410cf96-68fe-5f44-8049-28fd0775358a.json b/oaitestdata/clarin-oai_dc/SET_1/json/0410cf96-68fe-5f44-8049-28fd0775358a.json
deleted file mode 100644
index 4436cac2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0410cf96-68fe-5f44-8049-28fd0775358a.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "A"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1537",
-    "MetadataAccess": [
-        "oai:ota:oucs:1537"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Daniel, Samuel"
-    ],
-    "fulltext": "oai:ota:oucs:1537;2018-04-16T15:30:51Z;http://ota.ox.ac.uk/headers/1537.xml;Delia;Daniel, Samuel;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;A;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0410cf96-68fe-5f44-8049-28fd0775358a",
-    "oai_identifier": [
-        "oai:ota:oucs:1537"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Delia"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1537.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/04415663-45a1-5886-a9d9-34dd2872c3b2.json b/oaitestdata/clarin-oai_dc/SET_1/json/04415663-45a1-5886-a9d9-34dd2872c3b2.json
deleted file mode 100644
index a5aec273..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/04415663-45a1-5886-a9d9-34dd2872c3b2.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Masaryk University, NLP Centre"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-000D-F696-9",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-000D-F696-9"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-000D-F696-9",
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Masaryk University, NLP Centre"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0)",
-        "http://creativecommons.org/licenses/by-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Pomik\u00e1lek, Jan"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-000D-F696-9;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;jusText;Pomik\u00e1lek, Jan;boilerplate;web documents;text cleaning;boilerplate removal;text corpora;jusText is a heuristic based boilerplate removal tool useful for cleaning documents in large textual corpora. The tool has been implemented in Python, licensed under New BSD License and made an open source software (available for download including the source code at http://code.google.com/p/justext/). It is successfully used for cleaning large textual corpora at Natural language processing centre at Faculty of informatics, Masaryk university Brno and it's industry partners. The research leading to this piece of software was published in author's Ph.D. thesis \"Removing Boilerplate and Duplicate Content from Web Corpora\". The boilerplate removal algorithm is able to remove most of non-grammatical sentences from a web page like navigation, advertisements, tables, short notes and so on. It has been shown it overperforms or at least keeps up with it's competitors (according to comparison with participants of Cleaneval competition in author's Ph.D. thesis). The precise removal of unwanted content and scalability of the algorithm has been demonstrated while building corpora of American Spanish, Arabic, Czech, French, Japanese, Russian, Tajik, and six Turkic languages consisting --- over 20 TB of HTML pages were processed resulting in corpora of 70 billions tokens altogether.;2011;toolService;http://hdl.handle.net/11858/00-097C-0000-000D-F696-9;eng;Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0);http://creativecommons.org/licenses/by-sa/3.0/;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Masaryk University, NLP Centre;http://code.google.com/p/justext/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "04415663-45a1-5886-a9d9-34dd2872c3b2",
-    "notes": [
-        "jusText is a heuristic based boilerplate removal tool useful for cleaning documents in large textual corpora. The tool has been implemented in Python, licensed under New BSD License and made an open source software (available for download including the source code at http://code.google.com/p/justext/). It is successfully used for cleaning large textual corpora at Natural language processing centre at Faculty of informatics, Masaryk university Brno and it's industry partners. The research leading to this piece of software was published in author's Ph.D. thesis \"Removing Boilerplate and Duplicate Content from Web Corpora\". The boilerplate removal algorithm is able to remove most of non-grammatical sentences from a web page like navigation, advertisements, tables, short notes and so on. It has been shown it overperforms or at least keeps up with it's competitors (according to comparison with participants of Cleaneval competition in author's Ph.D. thesis). The precise removal of unwanted content and scalability of the algorithm has been demonstrated while building corpora of American Spanish, Arabic, Czech, French, Japanese, Russian, Tajik, and six Turkic languages consisting --- over 20 TB of HTML pages were processed resulting in corpora of 70 billions tokens altogether."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-000D-F696-9"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "boilerplate"
-        },
-        {
-            "name": "web documents"
-        },
-        {
-            "name": "text cleaning"
-        },
-        {
-            "name": "boilerplate removal"
-        },
-        {
-            "name": "text corpora"
-        }
-    ],
-    "title": [
-        "jusText"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/045e8379-74dc-5838-8118-9d488c64b254.json b/oaitestdata/clarin-oai_dc/SET_1/json/045e8379-74dc-5838-8118-9d488c64b254.json
deleted file mode 100644
index bfb2d4e3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/045e8379-74dc-5838-8118-9d488c64b254.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=3ba530bc3adc11e2a2aa782bcb074135f9b02c06dbbd4244a0d9e029f4a62129",
-    "MetadataAccess": [
-        "3ba530bc3adc11e2a2aa782bcb074135f9b02c06dbbd4244a0d9e029f4a62129"
-    ],
-    "PublicationTimestamp": "2012-11-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "fulltext": "3ba530bc3adc11e2a2aa782bcb074135f9b02c06dbbd4244a0d9e029f4a62129;2018-11-15T16:39:54Z;lexicalConceptualResource;lexicalConceptualResource:other;MALTESE AUTOMATIC COLLOCATIONS DICTIONARY;Maltese Automatic Collocations Dictionary\n===========================================\n\nLexical Computing Limited, October 2012\n\nThis is an Automatic Collocations Dictionary produced by Lexical Computing Limited, for delivery to the EU CESAR project.\nThe method is\n  \u00e2\u0080\u00a2 Take a corpus of the language in question\n  \u00e2\u0080\u00a2 Lemmatise and part-of-speech-tag it\n  \u00e2\u0080\u00a2 Load it into the Sketch Engine     \n    (http://www.sketchengine.co.uk)\n  \u00e2\u0080\u00a2 Apply a \u00e2\u0080\u0098sketch grammar\u00e2\u0080\u0099 (of regular expressions over part-of-speech tags). A sketch grammar, when applied to a corpus, identifies a set of collocations, eg <headword, grammatical relation, collocate> triples.\n  \u00e2\u0080\u00a2 For all lexical words of sufficient frequency, list all collocations they participate in\n\nIn this case,\n\u00e2\u0080\u00a2 The Maltese MLRS Corpus was developed at the University of Malta by Claudia Borg, Albert Gatt, et al. It is contains about 111 milion words and it was processed by their lemmatizator and tagger for Maltese.\n\u00e2\u0080\u00a2 The sketch grammar was also as prepared by Jan Joachimsen\n\u00e2\u0080\u00a2 The dictionary has entries for 12,553 headwords, with an average of 5.7 collocations per headword.\n\u00e2\u0080\u00a2 The entry for each collocation includes pointers to its corpus examples on the Sketch Engine website.;2012-11-30",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "045e8379-74dc-5838-8118-9d488c64b254",
-    "notes": [
-        "Maltese Automatic Collocations Dictionary\n===========================================\n\nLexical Computing Limited, October 2012\n\nThis is an Automatic Collocations Dictionary produced by Lexical Computing Limited, for delivery to the EU CESAR project.\nThe method is\n  \u00e2\u0080\u00a2 Take a corpus of the language in question\n  \u00e2\u0080\u00a2 Lemmatise and part-of-speech-tag it\n  \u00e2\u0080\u00a2 Load it into the Sketch Engine     \n    (http://www.sketchengine.co.uk)\n  \u00e2\u0080\u00a2 Apply a \u00e2\u0080\u0098sketch grammar\u00e2\u0080\u0099 (of regular expressions over part-of-speech tags). A sketch grammar, when applied to a corpus, identifies a set of collocations, eg <headword, grammatical relation, collocate> triples.\n  \u00e2\u0080\u00a2 For all lexical words of sufficient frequency, list all collocations they participate in\n\nIn this case,\n\u00e2\u0080\u00a2 The Maltese MLRS Corpus was developed at the University of Malta by Claudia Borg, Albert Gatt, et al. It is contains about 111 milion words and it was processed by their lemmatizator and tagger for Maltese.\n\u00e2\u0080\u00a2 The sketch grammar was also as prepared by Jan Joachimsen\n\u00e2\u0080\u00a2 The dictionary has entries for 12,553 headwords, with an average of 5.7 collocations per headword.\n\u00e2\u0080\u00a2 The entry for each collocation includes pointers to its corpus examples on the Sketch Engine website."
-    ],
-    "oai_identifier": [
-        "3ba530bc3adc11e2a2aa782bcb074135f9b02c06dbbd4244a0d9e029f4a62129"
-    ],
-    "oai_set": [
-        "lexicalConceptualResource",
-        "lexicalConceptualResource:other"
-    ],
-    "state": "active",
-    "title": [
-        "MALTESE AUTOMATIC COLLOCATIONS DICTIONARY"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/045f7b3d-07a9-517b-a84e-e1ca545ed853.json b/oaitestdata/clarin-oai_dc/SET_1/json/045f7b3d-07a9-517b-a84e-e1ca545ed853.json
deleted file mode 100644
index 3506a2fb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/045f7b3d-07a9-517b-a84e-e1ca545ed853.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/333",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/333"
-    ],
-    "PID": "http://hdl.handle.net/11321/333",
-    "PublicationTimestamp": "2017-01-23T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "IS PAS corpora license",
-        "http://clarin-pl.eu/en/licenses/is-pas-corpora-license/",
-        "CC"
-    ],
-    "author": [
-        "Marci\u0144czuk, Micha\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/333;2017-01-23T14:04:31Z;hdl_11321_3;hdl_11321_203;Korpus wiadomo\u015bci z Polski (pi\u0119\u0107 portali);Marci\u0144czuk, Micha\u0142;Polska;1000 wiadomo\u015bci z Polski z pi\u0119ciu portali informacyjnych;2017-01-23;corpus;http://hdl.handle.net/11321/333;pol;IS PAS corpora license;http://clarin-pl.eu/en/licenses/is-pas-corpora-license/;CC;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;Wroc\u0142aw University of Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "045f7b3d-07a9-517b-a84e-e1ca545ed853",
-    "notes": [
-        "1000 wiadomo\u015bci z Polski z pi\u0119ciu portali informacyjnych"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/333"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_203"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Polska"
-        }
-    ],
-    "title": [
-        "Korpus wiadomo\u015bci z Polski (pi\u0119\u0107 portali)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0460cb81-5860-598e-b081-3319c5231a4a.json b/oaitestdata/clarin-oai_dc/SET_1/json/0460cb81-5860-598e-b081-3319c5231a4a.json
deleted file mode 100644
index bccb5759..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0460cb81-5860-598e-b081-3319c5231a4a.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3769",
-    "MetadataAccess": [
-        "oai:ota:oucs:3769"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Macpherson, James, 1736-1796."
-    ],
-    "fulltext": "oai:ota:oucs:3769;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3769.xml;A short history of the opposition during the last session of Parliament;Macpherson, James, 1736-1796.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0460cb81-5860-598e-b081-3319c5231a4a",
-    "oai_identifier": [
-        "oai:ota:oucs:3769"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A short history of the opposition during the last session of Parliament"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3769.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0465d32a-aa56-5eb1-93f6-2f0ba5a6d8e0.json b/oaitestdata/clarin-oai_dc/SET_1/json/0465d32a-aa56-5eb1-93f6-2f0ba5a6d8e0.json
deleted file mode 100644
index 5affd3c7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0465d32a-aa56-5eb1-93f6-2f0ba5a6d8e0.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 1 MB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1799",
-    "MetadataAccess": [
-        "oai:ota:oucs:1799"
-    ],
-    "PublicationTimestamp": "1980-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1980"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dickens, Charles, 1812-1870"
-    ],
-    "fulltext": "oai:ota:oucs:1799;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/1799.xml;Great expectations / by Charles Dickens;Dickens, Charles, 1812-1870;1980-01-01;text_and_corpus_linguistics;Fiction -- Great Britain -- 19th century;Novels -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 1 MB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0465d32a-aa56-5eb1-93f6-2f0ba5a6d8e0",
-    "oai_identifier": [
-        "oai:ota:oucs:1799"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- Great Britain -- th century"
-        },
-        {
-            "name": "Novels -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Great expectations / by Charles Dickens"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1799.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/049a9ff2-27c5-57f4-91e7-1ba62cf3cccb.json b/oaitestdata/clarin-oai_dc/SET_1/json/049a9ff2-27c5-57f4-91e7-1ba62cf3cccb.json
deleted file mode 100644
index b72e71d3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/049a9ff2-27c5-57f4-91e7-1ba62cf3cccb.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "809 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1301",
-    "MetadataAccess": [
-        "oai:ota:oucs:1301"
-    ],
-    "PublicationTimestamp": "1981-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1981"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Mahf\u00c5\u00abz, Naj\u00c4\u00abb,  1912-"
-    ],
-    "fulltext": "oai:ota:oucs:1301;2018-03-07T11:07:13Z;http://ota.ox.ac.uk/headers/1301.xml;Children of Gebelawi / compiled by Philip Stewart;Mahf\u00c5\u00abz, Naj\u00c4\u00abb,  1912-;1981;text_and_corpus_linguistics;Novels -- Egypt -- 20th century;eng;Oxford Text Archive, University of Oxford;809 KB;Text;Novels;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "049a9ff2-27c5-57f4-91e7-1ba62cf3cccb",
-    "oai_identifier": [
-        "oai:ota:oucs:1301"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Novels -- Egypt -- th century"
-        }
-    ],
-    "title": [
-        "Children of Gebelawi / compiled by Philip Stewart"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1301.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/04c3560c-b758-5674-a17d-0e582befb181.json b/oaitestdata/clarin-oai_dc/SET_1/json/04c3560c-b758-5674-a17d-0e582befb181.json
deleted file mode 100644
index 2f0b70e2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/04c3560c-b758-5674-a17d-0e582befb181.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5257",
-    "MetadataAccess": [
-        "oai:ota:oucs:5257"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gray, Thomas, 1716-1771."
-    ],
-    "fulltext": "oai:ota:oucs:5257;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5257.xml;The poetical works: of Thomas Gray. With the life of the author.;Gray, Thomas, 1716-1771.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "04c3560c-b758-5674-a17d-0e582befb181",
-    "oai_identifier": [
-        "oai:ota:oucs:5257"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The poetical works: of Thomas Gray. With the life of the author."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5257.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/04d7f30e-f754-5074-9a34-59f891b89cbf.json b/oaitestdata/clarin-oai_dc/SET_1/json/04d7f30e-f754-5074-9a34-59f891b89cbf.json
deleted file mode 100644
index 73b5d4f6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/04d7f30e-f754-5074-9a34-59f891b89cbf.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/vnd.oasis.opendocument.text",
-        "downloadable_files_count: 10",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/374",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/374"
-    ],
-    "PID": "http://hdl.handle.net/11321/374",
-    "PublicationTimestamp": "2017-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Anna Granat"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/374;2017-05-30T07:54:43Z;hdl_11321_3;hdl_11321_4;Wypowiedzi dzieci przedszkolnych jako skutek odbioru medi\u00f3w (pilota\u017c);Anna Granat;j\u0119zyk;dzieci;przedszkole;testowy korpus dokument\u00f3w;2017-05-30;corpus;http://hdl.handle.net/11321/374;pol;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;text/plain;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;downloadable_files_count: 10;Institute of Computer Science, Polish Academy of Sciences",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "04d7f30e-f754-5074-9a34-59f891b89cbf",
-    "notes": [
-        "testowy korpus dokument\u00f3w"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/374"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "dzieci"
-        },
-        {
-            "name": "przedszkole"
-        }
-    ],
-    "title": [
-        "Wypowiedzi dzieci przedszkolnych jako skutek odbioru medi\u00f3w (pilota\u017c)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/04dfbf2a-07b2-5f75-882e-49fabd4da63c.json b/oaitestdata/clarin-oai_dc/SET_1/json/04dfbf2a-07b2-5f75-882e-49fabd4da63c.json
deleted file mode 100644
index 2b1471e7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/04dfbf2a-07b2-5f75-882e-49fabd4da63c.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "A"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1563",
-    "MetadataAccess": [
-        "oai:ota:oucs:1563"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "While this resource was freely available for non-commercial use provided that this header is included in its entirety with any copy distributed, it has been removed from our catalogue for one reason or another.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Faulkner, William"
-    ],
-    "fulltext": "oai:ota:oucs:1563;2018-04-16T15:30:51Z;http://ota.ox.ac.uk/headers/1563.xml;Sanctuary;Faulkner, William;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;A;Text;While this resource was freely available for non-commercial use provided that this header is included in its entirety with any copy distributed, it has been removed from our catalogue for one reason or another.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "04dfbf2a-07b2-5f75-882e-49fabd4da63c",
-    "oai_identifier": [
-        "oai:ota:oucs:1563"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Sanctuary"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1563.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/04ed2848-f1aa-58ad-8d84-629c3b486ed1.json b/oaitestdata/clarin-oai_dc/SET_1/json/04ed2848-f1aa-58ad-8d84-629c3b486ed1.json
deleted file mode 100644
index 11bb8fc9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/04ed2848-f1aa-58ad-8d84-629c3b486ed1.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Borin, Lars"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-218",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-218"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-218",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Sweden"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-218;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Talbanken/Bruksprosa;Borin, Lars;appr. 85 kW, functional (traditional) syntactic roles (in TEI/XCES XML format);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-218;swe;downloadable_files_count: 0;Sweden;http://spraakbanken.gu.se/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "04ed2848-f1aa-58ad-8d84-629c3b486ed1",
-    "notes": [
-        "appr. 85 kW, functional (traditional) syntactic roles (in TEI/XCES XML format)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-218"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Talbanken/Bruksprosa"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/04f5d9db-5bd2-5fb8-afc9-1152d498f0af.json b/oaitestdata/clarin-oai_dc/SET_1/json/04f5d9db-5bd2-5fb8-afc9-1152d498f0af.json
deleted file mode 100644
index f7c7216a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/04f5d9db-5bd2-5fb8-afc9-1152d498f0af.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English",
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-416",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-416"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-416",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Slovenia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-416;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;IJS-ELAN;parallel, mixed text; 2x0.5 mil. words; TEI / morphosyntactic tags;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-416;eng;slv;downloadable_files_count: 0;Slovenia;http://nl.ijs.si/elan/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "04f5d9db-5bd2-5fb8-afc9-1152d498f0af",
-    "notes": [
-        "parallel, mixed text; 2x0.5 mil. words; TEI / morphosyntactic tags"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-416"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "IJS-ELAN"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0508fedc-ffd6-5239-aa6e-ef54317da876.json b/oaitestdata/clarin-oai_dc/SET_1/json/0508fedc-ffd6-5239-aa6e-ef54317da876.json
deleted file mode 100644
index fc0f0094..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0508fedc-ffd6-5239-aa6e-ef54317da876.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 52.2 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2158",
-    "MetadataAccess": [
-        "oai:ota:oucs:2158"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gaskell, Elizabeth Cleghorn, 1810-1865"
-    ],
-    "fulltext": "oai:ota:oucs:2158;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/2158.xml;The heart of John Middleton / by Elizabeth Gaskell;Gaskell, Elizabeth Cleghorn, 1810-1865;text_and_corpus_linguistics;Fiction -- Great Britain -- 19th century;Short stories -- Great Britain -- 19th century;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 52.2 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0508fedc-ffd6-5239-aa6e-ef54317da876",
-    "oai_identifier": [
-        "oai:ota:oucs:2158"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- Great Britain -- th century"
-        },
-        {
-            "name": "Short stories -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "The heart of John Middleton / by Elizabeth Gaskell"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2158.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/050bb70c-5bd5-5e61-ab33-6dbb57631071.json b/oaitestdata/clarin-oai_dc/SET_1/json/050bb70c-5bd5-5e61-ab33-6dbb57631071.json
deleted file mode 100644
index 4f77fa43..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/050bb70c-5bd5-5e61-ab33-6dbb57631071.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Smith, John B."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(2 files : ca. 428, 421 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1658",
-    "MetadataAccess": [
-        "oai:ota:oucs:1658"
-    ],
-    "PublicationTimestamp": "1931-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1931"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Woolf, Virginia, 1882-1941"
-    ],
-    "fulltext": "oai:ota:oucs:1658;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/1658.xml;The waves / Virginia Woolf;Woolf, Virginia, 1882-1941;1931;text_and_corpus_linguistics;English fiction -- 20th century;eng;Oxford Text Archive, University of Oxford;Smith, John B.;text/sgml;(2 files : ca. 428, 421 KB);Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "050bb70c-5bd5-5e61-ab33-6dbb57631071",
-    "oai_identifier": [
-        "oai:ota:oucs:1658"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English fiction -- th century"
-        }
-    ],
-    "title": [
-        "The waves / Virginia Woolf"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1658.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0538e2f6-65f6-5f6e-bedd-7bb1e182f38b.json b/oaitestdata/clarin-oai_dc/SET_1/json/0538e2f6-65f6-5f6e-bedd-7bb1e182f38b.json
deleted file mode 100644
index 5587886f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0538e2f6-65f6-5f6e-bedd-7bb1e182f38b.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Palmer, Nigel F"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 19 KB)"
-    ],
-    "Language": [
-        "Middle High German (ca. 1050-1500)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1958",
-    "MetadataAccess": [
-        "oai:ota:oucs:1958"
-    ],
-    "PublicationTimestamp": "1192-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1192"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Songs"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hartmann, von Aue, 12th cent"
-    ],
-    "fulltext": "oai:ota:oucs:1958;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/1958.xml;Lieder / Hartmann von Aue;Hartmann, von Aue, 12th cent;1192-1220;text_and_corpus_linguistics;Songs, German (Middle High German) -- 12th century;gmh;Oxford Text Archive, University of Oxford;Palmer, Nigel F;(1 file : ca. 19 KB);Text;Songs;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0538e2f6-65f6-5f6e-bedd-7bb1e182f38b",
-    "oai_identifier": [
-        "oai:ota:oucs:1958"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Songs"
-        },
-        {
-            "name": "German Middle High German -- th century"
-        }
-    ],
-    "title": [
-        "Lieder / Hartmann von Aue"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1958.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/053aabe8-65c0-57df-a514-245152ccc649.json b/oaitestdata/clarin-oai_dc/SET_1/json/053aabe8-65c0-57df-a514-245152ccc649.json
deleted file mode 100644
index 3856335e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/053aabe8-65c0-57df-a514-245152ccc649.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "The National Library of Sweden"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/88",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/88"
-    ],
-    "PID": "http://hdl.handle.net/10794/88",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "The National Library of Sweden"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/88;2017-10-25T14:40:52Z;hdl_10794_1;hdl_10794_2;Blekingsposten 1850's (2015-04-08);Blekingsposten 1850-talet (2015-04-08);n/a, n/a;Swedish;News;A corpus with texts from Blekingeposten 1850\u20131859.;En korpus med texter fr\u00e5n Blekingeposten p\u00e5 1850-talet (1850\u20131859).;2015-04-08;corpus;http://hdl.handle.net/10794/88;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;The National Library of Sweden;https://spraakbanken.gu.se/swe/resurs/kubhist-blekingsposten-1850",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "053aabe8-65c0-57df-a514-245152ccc649",
-    "notes": [
-        "A corpus with texts from Blekingeposten 1850\u20131859.",
-        "En korpus med texter fr\u00e5n Blekingeposten p\u00e5 1850-talet (1850\u20131859)."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/88"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "News"
-        }
-    ],
-    "title": [
-        "Blekingsposten 1850's (2015-04-08)",
-        "Blekingsposten 1850-talet (2015-04-08)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0563579f-b309-506e-8f9b-f7411b5f82e4.json b/oaitestdata/clarin-oai_dc/SET_1/json/0563579f-b309-506e-8f9b-f7411b5f82e4.json
deleted file mode 100644
index 6c23784d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0563579f-b309-506e-8f9b-f7411b5f82e4.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "less than 512 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1314",
-    "MetadataAccess": [
-        "oai:ota:oucs:1314"
-    ],
-    "PublicationTimestamp": "1475-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1475"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Devotional material"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:1314;2018-03-07T11:46:23Z;http://ota.ox.ac.uk/headers/1314.xml;The mirour of mans saluacioune / compiled by Ivan Dixon ; revised by Avril Henry;1475;text_and_corpus_linguistics;Devotional material -- Europe -- 15th Century;eng;Oxford Text Archive, University of Oxford;less than 512 KB;Text;Devotional material;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0563579f-b309-506e-8f9b-f7411b5f82e4",
-    "oai_identifier": [
-        "oai:ota:oucs:1314"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Devotional material -- Europe -- th Century"
-        }
-    ],
-    "title": [
-        "The mirour of mans saluacioune / compiled by Ivan Dixon ; revised by Avril Henry"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1314.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/056d3093-1c23-5ad7-b291-dbc2b742dde4.json b/oaitestdata/clarin-oai_dc/SET_1/json/056d3093-1c23-5ad7-b291-dbc2b742dde4.json
deleted file mode 100644
index 5efd476e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/056d3093-1c23-5ad7-b291-dbc2b742dde4.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3847",
-    "MetadataAccess": [
-        "oai:ota:oucs:3847"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "More, Hannah, 1745-1833."
-    ],
-    "fulltext": "oai:ota:oucs:3847;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3847.xml;The apprentice turned master: or, the second part of the two shoemakers. ...;Two shoemakers.;More, Hannah, 1745-1833.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "056d3093-1c23-5ad7-b291-dbc2b742dde4",
-    "oai_identifier": [
-        "oai:ota:oucs:3847"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The apprentice turned master: or, the second part of the two shoemakers. ...",
-        "Two shoemakers."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3847.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/056e6d2d-0108-53cd-b66e-b7eadc092025.json b/oaitestdata/clarin-oai_dc/SET_1/json/056e6d2d-0108-53cd-b66e-b7eadc092025.json
deleted file mode 100644
index 128228f5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/056e6d2d-0108-53cd-b66e-b7eadc092025.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5311",
-    "MetadataAccess": [
-        "oai:ota:oucs:5311"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Warton, Thomas, 1728-1790."
-    ],
-    "fulltext": "oai:ota:oucs:5311;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5311.xml;The history of English poetry: from the close of the eleventh to the commencement of the eighteenth century. To which are prefixed, two dissertations. ... By Thomas Warton, ... [pt.4];Warton, Thomas, 1728-1790.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "056e6d2d-0108-53cd-b66e-b7eadc092025",
-    "oai_identifier": [
-        "oai:ota:oucs:5311"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The history of English poetry: from the close of the eleventh to the commencement of the eighteenth century. To which are prefixed, two dissertations. ... By Thomas Warton, ... [pt.4]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5311.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/05797735-d6f6-568f-bdc0-39836315a44c.json b/oaitestdata/clarin-oai_dc/SET_1/json/05797735-d6f6-568f-bdc0-39836315a44c.json
deleted file mode 100644
index 00e932a6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/05797735-d6f6-568f-bdc0-39836315a44c.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Jan Wieczorek"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/476",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/476"
-    ],
-    "PID": "http://hdl.handle.net/11321/476",
-    "PublicationTimestamp": "2018-06-06T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Jan Wieczorek"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Wieczorek, Jan"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/476;2018-06-13T13:01:48Z;hdl_11321_3;hdl_11321_478;Siemiradzki test;Wieczorek, Jan;Siemiradzki;historia sztuki;history of art;test;Test korpusu Siemiradzki;2018-06-06;corpus;http://hdl.handle.net/11321/476;pol;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;CC;text/plain; charset=utf-8;application/msword;application/msword;downloadable_files_count: 2;Jan Wieczorek",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "05797735-d6f6-568f-bdc0-39836315a44c",
-    "notes": [
-        "Test korpusu Siemiradzki"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/476"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_478"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Siemiradzki"
-        },
-        {
-            "name": "historia sztuki"
-        },
-        {
-            "name": "history art"
-        },
-        {
-            "name": "test"
-        }
-    ],
-    "title": [
-        "Siemiradzki test"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/058869f3-a2d0-58e5-b9b5-af8bc0f54665.json b/oaitestdata/clarin-oai_dc/SET_1/json/058869f3-a2d0-58e5-b9b5-af8bc0f54665.json
deleted file mode 100644
index af9329b9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/058869f3-a2d0-58e5-b9b5-af8bc0f54665.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=f95a45fe059211e7a2aa782bcb0741356d6e858348cb4b4ea5f631ba11e737aa",
-    "MetadataAccess": [
-        "f95a45fe059211e7a2aa782bcb0741356d6e858348cb4b4ea5f631ba11e737aa"
-    ],
-    "PublicationTimestamp": "2017-03-10T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "fulltext": "f95a45fe059211e7a2aa782bcb0741356d6e858348cb4b4ea5f631ba11e737aa;2018-11-15T16:40:29Z;toolService;toolService:tool;English to Portuguese Machine translation module;Technical Description:\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/Pilot1_technical_description.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/TechnicalDescriptionPilot2_D2.7.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2016/11/TechnicalDescriptionPilot3_D2.10.pdf;2017-03-10",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "058869f3-a2d0-58e5-b9b5-af8bc0f54665",
-    "notes": [
-        "Technical Description:\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/Pilot1_technical_description.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/TechnicalDescriptionPilot2_D2.7.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2016/11/TechnicalDescriptionPilot3_D2.10.pdf"
-    ],
-    "oai_identifier": [
-        "f95a45fe059211e7a2aa782bcb0741356d6e858348cb4b4ea5f631ba11e737aa"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "English to Portuguese Machine translation module"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/05e3932c-29e4-588b-8527-a8758bf1bcd3.json b/oaitestdata/clarin-oai_dc/SET_1/json/05e3932c-29e4-588b-8527-a8758bf1bcd3.json
deleted file mode 100644
index f43b2aa7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/05e3932c-29e4-588b-8527-a8758bf1bcd3.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3990",
-    "MetadataAccess": [
-        "oai:ota:oucs:3990"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Burgoyne, John, 1722-1792."
-    ],
-    "fulltext": "oai:ota:oucs:3990;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3990.xml;The heiress: A comedy in five acts. As performed at the Theatre-Royal Drury-Lane.;Burgoyne, John, 1722-1792.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "05e3932c-29e4-588b-8527-a8758bf1bcd3",
-    "oai_identifier": [
-        "oai:ota:oucs:3990"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The heiress: A comedy in five acts. As performed at the Theatre-Royal Drury-Lane."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3990.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/05eb5281-0998-56a9-8264-50ced0e38784.json b/oaitestdata/clarin-oai_dc/SET_1/json/05eb5281-0998-56a9-8264-50ced0e38784.json
deleted file mode 100644
index 7ce06ac5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/05eb5281-0998-56a9-8264-50ced0e38784.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=53f0dc3cbc6c11e1a404080027e73ea2a392ee1cbd3a440e854b3b1aaf6694a0",
-    "MetadataAccess": [
-        "53f0dc3cbc6c11e1a404080027e73ea2a392ee1cbd3a440e854b3b1aaf6694a0"
-    ],
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "53f0dc3cbc6c11e1a404080027e73ea2a392ee1cbd3a440e854b3b1aaf6694a0;2018-11-15T16:39:32Z;corpus;corpus:text;Local Government Documentation;This corpus is a collection of different governmental resources, containing two types of documents: minutes, which were taken during local council meetings (covering the years from 2007 till 2010) and memorandums (covering from 2008 till 2011).\nThis corpus, consisting of raw text files and comma separated values (CSV) files, is the percentage that could be extracted from the original corpus.\nSome issues arise due to Maltese characters. It is important to note that not all documents contain the right Maltese characters. Some documents may replace:\n\u00c4\u00a1 -> g ; \u00c5\u00bc -> z ; \u00c4\u00a7 -> h ; \u00c4\u008b -> c\nWith those being on the right hand side also Maltese characters, except c. Furthermore, in some of the documents, the keyboard equivalence of the character is printed, rather than the character itself (and this is also dependent on whether the user made use of the 47 or 48-key keyboard layout).\n;2015-12-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "05eb5281-0998-56a9-8264-50ced0e38784",
-    "notes": [
-        "This corpus is a collection of different governmental resources, containing two types of documents: minutes, which were taken during local council meetings (covering the years from 2007 till 2010) and memorandums (covering from 2008 till 2011).\nThis corpus, consisting of raw text files and comma separated values (CSV) files, is the percentage that could be extracted from the original corpus.\nSome issues arise due to Maltese characters. It is important to note that not all documents contain the right Maltese characters. Some documents may replace:\n\u00c4\u00a1 -> g ; \u00c5\u00bc -> z ; \u00c4\u00a7 -> h ; \u00c4\u008b -> c\nWith those being on the right hand side also Maltese characters, except c. Furthermore, in some of the documents, the keyboard equivalence of the character is printed, rather than the character itself (and this is also dependent on whether the user made use of the 47 or 48-key keyboard layout).\n"
-    ],
-    "oai_identifier": [
-        "53f0dc3cbc6c11e1a404080027e73ea2a392ee1cbd3a440e854b3b1aaf6694a0"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "Local Government Documentation"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/06036765-333f-5a39-bff8-83fdd1ea61b6.json b/oaitestdata/clarin-oai_dc/SET_1/json/06036765-333f-5a39-bff8-83fdd1ea61b6.json
deleted file mode 100644
index 1c4c372c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/06036765-333f-5a39-bff8-83fdd1ea61b6.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/31",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/31"
-    ],
-    "PID": "http://hdl.handle.net/11321/31",
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Godlewski, Grzegorz",
-        "Piasecki, Maciej",
-        "Broda, Bartosz",
-        "Wardy\u0144ski, Adam",
-        "Radziszewski, Adam"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/31;2016-01-21T14:37:02Z;hdl_11321_3;hdl_11321_4;TaKIPI;Piasecki, Maciej;Radziszewski, Adam;Godlewski, Grzegorz;Broda, Bartosz;Wardy\u0144ski, Adam;TaKIPI is a tagger of Polish language that is a tool which assigns morpho-syntactic markers to words in the text.\r\n\r\nThe tagger assumes a morpho-syntactic description of IPI PAN corpus tagset. Contextual disambiguation is carried out via a small set of hand-written rules and via a bigger number of rules automatically extracted by means of the algorithm of the induction of decision trees C4.5. During the process of tagger's learning and functioning, the context of each word's occurence in the text is represented as a feature vector of a constant length. Such vector is obtained by means of hand-written functional expressions of JOSKIPI formalism, which refer to morpho-syntactic properties of the context.;2014;toolService;http://hdl.handle.net/11321/31;pol;downloadable_files_count: 0;Wroc\u0142aw University of Technology;http://nlp.pwr.wroc.pl/takipi/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "06036765-333f-5a39-bff8-83fdd1ea61b6",
-    "notes": [
-        "TaKIPI is a tagger of Polish language that is a tool which assigns morpho-syntactic markers to words in the text.\r\n\r\nThe tagger assumes a morpho-syntactic description of IPI PAN corpus tagset. Contextual disambiguation is carried out via a small set of hand-written rules and via a bigger number of rules automatically extracted by means of the algorithm of the induction of decision trees C4.5. During the process of tagger's learning and functioning, the context of each word's occurence in the text is represented as a feature vector of a constant length. Such vector is obtained by means of hand-written functional expressions of JOSKIPI formalism, which refer to morpho-syntactic properties of the context."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/31"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "TaKIPI"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/06288e49-658c-5e86-93a8-87651e1e54f0.json b/oaitestdata/clarin-oai_dc/SET_1/json/06288e49-658c-5e86-93a8-87651e1e54f0.json
deleted file mode 100644
index 0e32ec13..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/06288e49-658c-5e86-93a8-87651e1e54f0.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5228",
-    "MetadataAccess": [
-        "oai:ota:oucs:5228"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Sharp, Granville, 1735-1813."
-    ],
-    "fulltext": "oai:ota:oucs:5228;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5228.xml;A tract on duelling: wherein the opinions of some of the most celebrated writers on crown law are examined and corrected ... in order to ascertain the due distinction between manslaughter and murder. By Granville Sharp.;Sharp, Granville, 1735-1813.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "06288e49-658c-5e86-93a8-87651e1e54f0",
-    "oai_identifier": [
-        "oai:ota:oucs:5228"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A tract on duelling: wherein the opinions of some of the most celebrated writers on crown law are examined and corrected ... in order to ascertain the due distinction between manslaughter and murder. By Granville Sharp."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5228.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0651d036-4de3-5a57-a586-87609433f512.json b/oaitestdata/clarin-oai_dc/SET_1/json/0651d036-4de3-5a57-a586-87609433f512.json
deleted file mode 100644
index c18b28c4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0651d036-4de3-5a57-a586-87609433f512.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1161",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1161"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1161",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1161;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Wikipedia-Lexikon;Germanistik;Pr\u00e4sentation der am h\u00e4ufigsten gesuchten (20.000) Stichw\u00f6rter der Wikipedia;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1161;deu;downloadable_files_count: 0;http://www.zeno.org/Glossar/M/Das+Wikipedia+Lexikon",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0651d036-4de3-5a57-a586-87609433f512",
-    "notes": [
-        "Pr\u00e4sentation der am h\u00e4ufigsten gesuchten (20.000) Stichw\u00f6rter der Wikipedia"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1161"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Wikipedia-Lexikon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0652beb4-d80f-5d47-822a-7af94ba2ae56.json b/oaitestdata/clarin-oai_dc/SET_1/json/0652beb4-d80f-5d47-822a-7af94ba2ae56.json
deleted file mode 100644
index 34f478d1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0652beb4-d80f-5d47-822a-7af94ba2ae56.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 309 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1921",
-    "MetadataAccess": [
-        "oai:ota:oucs:1921"
-    ],
-    "PublicationTimestamp": "1748-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1748"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Philosophical works"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hume, David, 1711-1776"
-    ],
-    "fulltext": "oai:ota:oucs:1921;2018-04-16T10:12:13Z;http://ota.ox.ac.uk/headers/1921.xml;An enquiry concerning human understanding / by David Hume;Hume, David, 1711-1776;1748;text_and_corpus_linguistics;Essays -- England -- 18th century;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 309 KB);Text;Philosophical works;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0652beb4-d80f-5d47-822a-7af94ba2ae56",
-    "oai_identifier": [
-        "oai:ota:oucs:1921"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Essays -- England -- th century"
-        }
-    ],
-    "title": [
-        "An enquiry concerning human understanding / by David Hume"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1921.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0657a944-a0bf-55bd-ba7e-b884728354b2.json b/oaitestdata/clarin-oai_dc/SET_1/json/0657a944-a0bf-55bd-ba7e-b884728354b2.json
deleted file mode 100644
index 7487b5e5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0657a944-a0bf-55bd-ba7e-b884728354b2.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3604",
-    "MetadataAccess": [
-        "oai:ota:oucs:3604"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Cumberland, Richard, 1732-1811."
-    ],
-    "fulltext": "oai:ota:oucs:3604;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3604.xml;Amelia: A musical entertainment of two acts. As it is performed at the Theatre Royal in Covent-Garden.;Cumberland, Richard, 1732-1811.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0657a944-a0bf-55bd-ba7e-b884728354b2",
-    "oai_identifier": [
-        "oai:ota:oucs:3604"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Amelia: A musical entertainment of two acts. As it is performed at the Theatre Royal in Covent-Garden."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3604.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0670262a-6178-5c38-93fb-3764ded1504b.json b/oaitestdata/clarin-oai_dc/SET_1/json/0670262a-6178-5c38-93fb-3764ded1504b.json
deleted file mode 100644
index cbdc2c5d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0670262a-6178-5c38-93fb-3764ded1504b.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2689",
-    "MetadataAccess": [
-        "oai:ota:oucs:2689"
-    ],
-    "PublicationTimestamp": "1711-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1711"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2689;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2689.xml;A vindication of Isaac Bickerstaff;Swift, Jonathan, 1667-1745;1711;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0670262a-6178-5c38-93fb-3764ded1504b",
-    "oai_identifier": [
-        "oai:ota:oucs:2689"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A vindication of Isaac Bickerstaff"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2689.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/068f8129-c2e2-5203-baea-6a7d4f170ca8.json b/oaitestdata/clarin-oai_dc/SET_1/json/068f8129-c2e2-5203-baea-6a7d4f170ca8.json
deleted file mode 100644
index 27439080..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/068f8129-c2e2-5203-baea-6a7d4f170ca8.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain",
-        "(1 file : ca. 119 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0039",
-    "MetadataAccess": [
-        "oai:ota:oucs:0039"
-    ],
-    "PublicationTimestamp": "1611-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1611"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dekker, Thomas, ca. 1572-1632"
-    ],
-    "fulltext": "oai:ota:oucs:0039;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0039.xml;Match mee in London;Dekker, Thomas, ca. 1572-1632;1611;text_and_corpus_linguistics;Plays -- England -- 17th century;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 119 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "068f8129-c2e2-5203-baea-6a7d4f170ca8",
-    "oai_identifier": [
-        "oai:ota:oucs:0039"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        }
-    ],
-    "title": [
-        "Match mee in London"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0039.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0694cc2a-e760-5c4f-a14a-17502a007892.json b/oaitestdata/clarin-oai_dc/SET_1/json/0694cc2a-e760-5c4f-a14a-17502a007892.json
deleted file mode 100644
index 62fc3fc5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0694cc2a-e760-5c4f-a14a-17502a007892.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4144",
-    "MetadataAccess": [
-        "oai:ota:oucs:4144"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Thomson, James, 1700-1748."
-    ],
-    "fulltext": "oai:ota:oucs:4144;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4144.xml;The prospect: being the fifth part of Liberty. A poem. By Mr. Thomson;Liberty, a poem.;Thomson, James, 1700-1748.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0694cc2a-e760-5c4f-a14a-17502a007892",
-    "oai_identifier": [
-        "oai:ota:oucs:4144"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The prospect: being the fifth part of Liberty. A poem. By Mr. Thomson",
-        "Liberty, a poem."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4144.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/06af5077-654d-51b9-be5b-6cd282cc1d9d.json b/oaitestdata/clarin-oai_dc/SET_1/json/06af5077-654d-51b9-be5b-6cd282cc1d9d.json
deleted file mode 100644
index c4fbb1d1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/06af5077-654d-51b9-be5b-6cd282cc1d9d.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/41",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/41"
-    ],
-    "PID": "http://hdl.handle.net/11321/41",
-    "PublicationTimestamp": "2012-09-23T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Ry\u015bnik, B\u0142a\u017cej"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/41;2016-01-19T13:55:50Z;hdl_11321_3;hdl_11321_4;Spartan;Ry\u015bnik, B\u0142a\u017cej;Ekstrakcja s\u0142\u00f3w kluczowych;2012-09-23;toolService;http://hdl.handle.net/11321/41;pol;downloadable_files_count: 0;Wroc\u0142aw University of Technology;http://",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "06af5077-654d-51b9-be5b-6cd282cc1d9d",
-    "notes": [
-        "Ekstrakcja s\u0142\u00f3w kluczowych"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/41"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Spartan"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/06c5fb45-ced1-5fc2-8c75-9c0152cdcc41.json b/oaitestdata/clarin-oai_dc/SET_1/json/06c5fb45-ced1-5fc2-8c75-9c0152cdcc41.json
deleted file mode 100644
index 849d49a6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/06c5fb45-ced1-5fc2-8c75-9c0152cdcc41.json
+++ /dev/null
@@ -1,88 +0,0 @@
-{
-    "Contact": [
-        "Fondazione Bruno Kessler, Trento, Italy"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "English",
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2725",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2725"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2725",
-    "PublicationTimestamp": "2018-05-04T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Fondazione Bruno Kessler, Trento, Italy"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/H2020/645452"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "AGREEMENT ON THE USE OF DATA IN QT21 APE Task",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21",
-        "PUB"
-    ],
-    "author": [
-        "Turchi, Marco",
-        "Chatterjee, Rajen",
-        "Negri, Matteo"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2725;2018-05-03T06:43:41Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Test Data EN-DE MT_PBSMT APE Shared Task WMT18;Turchi, Marco;Negri, Matteo;Chatterjee, Rajen;machine translation;shared task;automatic post-editing;post-editing;phrase-based MT;Test data for the WMT 2018 Automatic post-editing task. They consist in English-German pairs (source and target) belonging to the information technology domain and already tokenized. Test set contains 2,000 pairs. A phrase-based machine translation system has been used to generate the target segments. This test set is sampled from the same dataset used for the 2016 and 2017 APE shared task editions. All data is provided by the EU project QT21 (http://www.qt21.eu/).;2018-05-04;corpus;http://hdl.handle.net/11372/LRT-2725;eng;deu;info:eu-repo/grantAgreement/EC/H2020/645452;AGREEMENT ON THE USE OF DATA IN QT21 APE Task;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Fondazione Bruno Kessler, Trento, Italy;http://www.statmt.org/wmt18/ape-task.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "06c5fb45-ced1-5fc2-8c75-9c0152cdcc41",
-    "notes": [
-        "Test data for the WMT 2018 Automatic post-editing task. They consist in English-German pairs (source and target) belonging to the information technology domain and already tokenized. Test set contains 2,000 pairs. A phrase-based machine translation system has been used to generate the target segments. This test set is sampled from the same dataset used for the 2016 and 2017 APE shared task editions. All data is provided by the EU project QT21 (http://www.qt21.eu/)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2725"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "shared task"
-        },
-        {
-            "name": "automatic post-editing"
-        },
-        {
-            "name": "post-editing"
-        },
-        {
-            "name": "phrase-based MT"
-        }
-    ],
-    "title": [
-        "Test Data EN-DE MT_PBSMT APE Shared Task WMT18"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/06c9bec6-4a3a-53ea-8839-6818edd2f988.json b/oaitestdata/clarin-oai_dc/SET_1/json/06c9bec6-4a3a-53ea-8839-6818edd2f988.json
deleted file mode 100644
index 03f80e97..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/06c9bec6-4a3a-53ea-8839-6818edd2f988.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Department of Information Technology, Gauhati University, Assam, India"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Assamese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/618",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/618"
-    ],
-    "PID": "http://hdl.handle.net/11321/618",
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Department of Information Technology, Gauhati University, Assam, India"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "author": [
-        "Sarma, Prof. Shikhar Kr."
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/618;2019-01-08T10:54:37Z;hdl_11321_3;hdl_11321_610;Assamese Root Words;Sarma, Prof. Shikhar Kr.;Assamese NLP;RootWords;Assamese Lemas;Gauhati University;This list comprises of Assamese root words. Size of the Assamese Root Word List  is 15,750 words\r\n\r\n---\r\n\r\n1. These Assamese NLP resources including the Tools and Applications are developed\r\nduring Research and Development Projects as well as Masters and Ph.D. thesis\r\nworks.\r\n2. These are mainly developed or generated at Gauhati University Department of\r\nComputer Science and Department of Information Technology.\r\n3. These resources are used by students and researchers for further studies, researches, as\r\nwell as for design and development of tools and applications.\r\n4. Computational Linguistics in Assamese is not rich, and Natural Language Processing\r\nworks have mainly started during last two decades, and most of the resources are first\r\ngeneration resources, and with ample scope for upgrading, enriching, and purifying.\r\n5. These are very good and essential resources for all the researchers in Assamese NLP, as\r\nthe language requires more and more NLP works to make Assamese a rich media for\r\nthe digital world.\r\n6. Anyone interested, or in need of such resources may express their interest for the\r\nrequired resources, and the way of availability will be advised/informed accordingly.\r\n7. These are purely research materials and could only be used for further research only.\r\n8. Researchers may visit the NLP Lab of Department of Information Technology, Gauhati\r\nUniversity, Guwahati, India or contact us.\r\n9. Researchers interested in collaborative works, and also students for project works, are\r\nwelcome.\r\n10. Contact person is Professor Shikhar Kr. Sarma, Department of Information\r\nTechnology, Gauhati University, Guwahati 781014, Assam, India. Email-\r\nsks@gauhati.ac.in;2019-01-08;lexicalConceptualResource;http://hdl.handle.net/11321/618;asm;downloadable_files_count: 0;Department of Information Technology, Gauhati University, Assam, India",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "06c9bec6-4a3a-53ea-8839-6818edd2f988",
-    "notes": [
-        "This list comprises of Assamese root words. Size of the Assamese Root Word List  is 15,750 words\r\n\r\n---\r\n\r\n1. These Assamese NLP resources including the Tools and Applications are developed\r\nduring Research and Development Projects as well as Masters and Ph.D. thesis\r\nworks.\r\n2. These are mainly developed or generated at Gauhati University Department of\r\nComputer Science and Department of Information Technology.\r\n3. These resources are used by students and researchers for further studies, researches, as\r\nwell as for design and development of tools and applications.\r\n4. Computational Linguistics in Assamese is not rich, and Natural Language Processing\r\nworks have mainly started during last two decades, and most of the resources are first\r\ngeneration resources, and with ample scope for upgrading, enriching, and purifying.\r\n5. These are very good and essential resources for all the researchers in Assamese NLP, as\r\nthe language requires more and more NLP works to make Assamese a rich media for\r\nthe digital world.\r\n6. Anyone interested, or in need of such resources may express their interest for the\r\nrequired resources, and the way of availability will be advised/informed accordingly.\r\n7. These are purely research materials and could only be used for further research only.\r\n8. Researchers may visit the NLP Lab of Department of Information Technology, Gauhati\r\nUniversity, Guwahati, India or contact us.\r\n9. Researchers interested in collaborative works, and also students for project works, are\r\nwelcome.\r\n10. Contact person is Professor Shikhar Kr. Sarma, Department of Information\r\nTechnology, Gauhati University, Guwahati 781014, Assam, India. Email-\r\nsks@gauhati.ac.in"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/618"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_610"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Assamese NLP"
-        },
-        {
-            "name": "RootWords"
-        },
-        {
-            "name": "Assamese Lemas"
-        },
-        {
-            "name": "Gauhati University"
-        }
-    ],
-    "title": [
-        "Assamese Root Words"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/06de2527-bb78-59bd-b9a6-ad53b9c8fa4f.json b/oaitestdata/clarin-oai_dc/SET_1/json/06de2527-bb78-59bd-b9a6-ad53b9c8fa4f.json
deleted file mode 100644
index 2949f3e7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/06de2527-bb78-59bd-b9a6-ad53b9c8fa4f.json
+++ /dev/null
@@ -1,92 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 4",
-        "application/pdf",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1088",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1088"
-    ],
-    "PID": "http://hdl.handle.net/11356/1088",
-    "PublicationTimestamp": "2017-02-16T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "http://nl.ijs.si/janes/viri/rocno-oznaceni-korpusi/#Janes-Vejica",
-        "https://doi.org/10.1007/s10579-018-9425-z"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "https://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Logar, Polona",
-        "Erjavec, Toma\u017e",
-        "Popi\u010d, Damjan",
-        "Fi\u0161er, Darja",
-        "Zupan, Katja",
-        "Kav\u010di\u010d, Teja"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1088;2018-12-04T16:12:01Z;hdl_11356_1023;hdl_11356_1024;Tweet comma corpus Janes-Vejica 1.0;Popi\u010d, Damjan;Zupan, Katja;Logar, Polona;Kav\u010di\u010d, Teja;Erjavec, Toma\u017e;Fi\u0161er, Darja;computer-mediated communication;Twitter;comma placement;TEI;manual annotation;Janes-Vejica is a corpus of Slovene tweets where commas are annotated with the reason for their (in)correct use, according to the supplied typology. The corpus was sampled from the Janes-Norm corpus (http://hdl.handle.net/11356/1084), which was manually annotated for tokenisation, sentence segmentation, and word normalisation, and automatically for morphosyntactic descriptions and lemmas.\r\n\r\nThe corpus is further described in:\r\n POPI\u010c, Damjan, FI\u0160ER, Darja, ZUPAN, Katja, LOGAR, Polona. Raba vejice v uporabni\u0161kih spletnih vsebinah. Proceedings of the Conference on Language Technologies & Digital Humanities, Ljubljana, Slovenia. 2016, pp. 149-153. http://www.sdjt.si/wp/dogodki/konference/jtdh-2016/zbornik/;2017-02-16;corpus;http://hdl.handle.net/11356/1088;slv;http://nl.ijs.si/janes/viri/rocno-oznaceni-korpusi/#Janes-Vejica;https://doi.org/10.1007/s10579-018-9425-z;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);https://creativecommons.org/licenses/by-sa/4.0/;PUB;application/pdf;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 4;Jo\u017eef Stefan Institute;http://nl.ijs.si/janes/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "06de2527-bb78-59bd-b9a6-ad53b9c8fa4f",
-    "notes": [
-        "Janes-Vejica is a corpus of Slovene tweets where commas are annotated with the reason for their (in)correct use, according to the supplied typology. The corpus was sampled from the Janes-Norm corpus (http://hdl.handle.net/11356/1084), which was manually annotated for tokenisation, sentence segmentation, and word normalisation, and automatically for morphosyntactic descriptions and lemmas.\r\n\r\nThe corpus is further described in:\r\n POPI\u010c, Damjan, FI\u0160ER, Darja, ZUPAN, Katja, LOGAR, Polona. Raba vejice v uporabni\u0161kih spletnih vsebinah. Proceedings of the Conference on Language Technologies & Digital Humanities, Ljubljana, Slovenia. 2016, pp. 149-153. http://www.sdjt.si/wp/dogodki/konference/jtdh-2016/zbornik/"
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1088"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "computer-mediated communication"
-        },
-        {
-            "name": "Twitter"
-        },
-        {
-            "name": "comma placement"
-        },
-        {
-            "name": "TEI"
-        },
-        {
-            "name": "manual annotation"
-        }
-    ],
-    "title": [
-        "Tweet comma corpus Janes-Vejica 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/06e8a8ac-ad1c-58f5-9ebb-97b5710ab115.json b/oaitestdata/clarin-oai_dc/SET_1/json/06e8a8ac-ad1c-58f5-9ebb-97b5710ab115.json
deleted file mode 100644
index 1ccd6309..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/06e8a8ac-ad1c-58f5-9ebb-97b5710ab115.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3877",
-    "MetadataAccess": [
-        "oai:ota:oucs:3877"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Francklin, Thomas, 1721-1784."
-    ],
-    "fulltext": "oai:ota:oucs:3877;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3877.xml;A sermon preach'd at Queen-street chapel, and St. Paul's, Covent-Garden: on Friday the 17th of February, 1758. ... By the Rev. Thomas Francklin, ...;Francklin, Thomas, 1721-1784.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "06e8a8ac-ad1c-58f5-9ebb-97b5710ab115",
-    "oai_identifier": [
-        "oai:ota:oucs:3877"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A sermon preach'd at Queen-street chapel, and St. Paul's, Covent-Garden: on Friday the 17th of February, 1758. ... By the Rev. Thomas Francklin, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3877.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/06eacab3-3384-5096-a473-7434e4456af4.json b/oaitestdata/clarin-oai_dc/SET_1/json/06eacab3-3384-5096-a473-7434e4456af4.json
deleted file mode 100644
index 6af7e7a5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/06eacab3-3384-5096-a473-7434e4456af4.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3468",
-    "MetadataAccess": [
-        "oai:ota:oucs:3468"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hill, Aaron, 1685-1750."
-    ],
-    "fulltext": "oai:ota:oucs:3468;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3468.xml;The northern-star: A poem. Written by Mr. Hill.;Hill, Aaron, 1685-1750.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "06eacab3-3384-5096-a473-7434e4456af4",
-    "oai_identifier": [
-        "oai:ota:oucs:3468"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The northern-star: A poem. Written by Mr. Hill."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3468.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/06f19814-858d-5538-bae6-efb3a943b91c.json b/oaitestdata/clarin-oai_dc/SET_1/json/06f19814-858d-5538-bae6-efb3a943b91c.json
deleted file mode 100644
index ea62f54b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/06f19814-858d-5538-bae6-efb3a943b91c.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/62",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/62"
-    ],
-    "PID": "http://hdl.handle.net/10794/62",
-    "PublicationTimestamp": "2015-04-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/62;2017-10-31T12:41:58Z;hdl_10794_1;hdl_10794_2;ASPAC \u2013 Swedish-Molise Slavic (2017-10-16);ASPAC \u2013 svenska-moliseslaviska (2017-10-16);n/a, n/a;ASPAC;Parallel;Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.;Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat.;2015-04-16;corpus;http://hdl.handle.net/10794/62;swe;svm;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/octet-stream;application/gzip;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/aspacsvsvm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "06f19814-858d-5538-bae6-efb3a943b91c",
-    "notes": [
-        "Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.",
-        "Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/62"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ASPAC"
-        },
-        {
-            "name": "Parallel"
-        }
-    ],
-    "title": [
-        "ASPAC \u2013 Swedish-Molise Slavic (2017-10-16)",
-        "ASPAC \u2013 svenska-moliseslaviska (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/06f1d0d1-f63b-573d-9515-15bb9fa81567.json b/oaitestdata/clarin-oai_dc/SET_1/json/06f1d0d1-f63b-573d-9515-15bb9fa81567.json
deleted file mode 100644
index 39aa04e7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/06f1d0d1-f63b-573d-9515-15bb9fa81567.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5230",
-    "MetadataAccess": [
-        "oai:ota:oucs:5230"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dudley, H. Bate, Sir (Henry Bate), 1745-1824."
-    ],
-    "fulltext": "oai:ota:oucs:5230;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5230.xml;Passages selected by distinguished personages: on the great literary trial of Vortigern and Rowena; a comi-tragedy. ... Volume I. [pt.2];Dudley, H. Bate, Sir (Henry Bate), 1745-1824.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "06f1d0d1-f63b-573d-9515-15bb9fa81567",
-    "oai_identifier": [
-        "oai:ota:oucs:5230"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Passages selected by distinguished personages: on the great literary trial of Vortigern and Rowena; a comi-tragedy. ... Volume I. [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5230.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/071653d1-929d-5345-b5f3-12790b85eab4.json b/oaitestdata/clarin-oai_dc/SET_1/json/071653d1-929d-5345-b5f3-12790b85eab4.json
deleted file mode 100644
index aae75763..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/071653d1-929d-5345-b5f3-12790b85eab4.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/6",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/6"
-    ],
-    "PID": "http://hdl.handle.net/10794/6",
-    "PublicationTimestamp": "2015-04-28T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/6;2017-10-27T16:24:22Z;hdl_10794_1;hdl_10794_2;Laws of 1734 (2017-10-16);1734 \u00e5rs lag (2017-10-16);n/a, n/a;Swedish;Corpus;Laws;The Swedish Laws of 1734.;1734 \u00e5rs lag.;2015-04-28;corpus;http://hdl.handle.net/10794/6;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/lag1734",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "071653d1-929d-5345-b5f3-12790b85eab4",
-    "notes": [
-        "The Swedish Laws of 1734.",
-        "1734 \u00e5rs lag."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/6"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Corpus"
-        },
-        {
-            "name": "Laws"
-        }
-    ],
-    "title": [
-        "Laws of 1734 (2017-10-16)",
-        "1734 \u00e5rs lag (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/072e6f15-8ef3-5203-aad1-f872ec15cd2c.json b/oaitestdata/clarin-oai_dc/SET_1/json/072e6f15-8ef3-5203-aad1-f872ec15cd2c.json
deleted file mode 100644
index 81cba409..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/072e6f15-8ef3-5203-aad1-f872ec15cd2c.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "[s.n.]"
-    ],
-    "Contributor": [
-        "Naruszewicz, Adam (1733-1796)."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Latin",
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-27393",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-27393"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D12-4",
-    "PublicationTimestamp": "1766-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1766"
-    ],
-    "Publisher": [
-        "[s.n.]"
-    ],
-    "RelatedIdentifier": [
-        "http://rcin.org.pl/Content/27393",
-        "oai:rcin.org.pl:publication:45491"
-    ],
-    "ResourceType": [
-        "Text",
-        "Early printed book (1501-1800)"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-27393;2019-03-01T13:22:56Z;Wiersze Pod Czas [!] Akademii Za\u0142uskich Mowione W Warszawie Roku 1766;Stanis\u0142aw August Poniatowski (kr\u00f3l Polski ; 1732-1798);Polish poetry - 18th c.;Latin poetry - 18th c.;Tyt. nag\u0142.;Aut. wiersza Fejerwerk Zycia Ludzkiego: Adam Naruszewicz (NKor);[4] k., sygn. A4 ; 4\u00b0;Estr. XV-XVIII, 34, 240 (w odpisie tyt. data 1768);NKor, 5, 372;Fejerwerk Zycia Ludzkiego i Do Nayjasnieyszego Krola oraz druga zwrotka utworu Epigramma de Beata Virgine Maria w j\u0119z. pol.;[s.n.];Naruszewicz, Adam (1733-1796).;[ca 1766];Text;Early printed book (1501-1800);application/xml;clarind-uds:poldilemma-27393;hdl:11858/00-246C-0000-0023-8D12-4;IBL PAN, call no. XVIII.2.1262;http://katalog.pan.pl/webpac-bin/233biblitEN/wgbroker.exe?new+-access+top+search+open+NR+xx002779312;lat;pol;http://rcin.org.pl/Content/27393;oai:rcin.org.pl:publication:45491;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "072e6f15-8ef3-5203-aad1-f872ec15cd2c",
-    "notes": [
-        "Tyt. nag\u0142.",
-        "Aut. wiersza Fejerwerk Zycia Ludzkiego: Adam Naruszewicz (NKor)",
-        "[4] k., sygn. A4 ; 4\u00b0",
-        "Estr. XV-XVIII, 34, 240 (w odpisie tyt. data 1768)",
-        "NKor, 5, 372",
-        "Fejerwerk Zycia Ludzkiego i Do Nayjasnieyszego Krola oraz druga zwrotka utworu Epigramma de Beata Virgine Maria w j\u0119z. pol."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-27393"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Stanis\u0142aw August Poniatowski kr\u00f3l Polski"
-        },
-        {
-            "name": "Polish poetry - th c."
-        },
-        {
-            "name": "Latin poetry - th c."
-        }
-    ],
-    "title": [
-        "Wiersze Pod Czas [!] Akademii Za\u0142uskich Mowione W Warszawie Roku 1766"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/074018c6-27d6-5aca-b794-c97f006287dd.json b/oaitestdata/clarin-oai_dc/SET_1/json/074018c6-27d6-5aca-b794-c97f006287dd.json
deleted file mode 100644
index d557c202..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/074018c6-27d6-5aca-b794-c97f006287dd.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-677",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-677"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-677",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Code of conduct"
-    ],
-    "SpatialCoverage": [
-        "Namibia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-677;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;\u2260Akhoe Hai//om;Documentation of the \u2260Akhoe Hai//om project (DoBeS project);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-677;Code of conduct;downloadable_files_count: 0;Namibia;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser/?openpath=MPI318962%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "074018c6-27d6-5aca-b794-c97f006287dd",
-    "notes": [
-        "Documentation of the \u2260Akhoe Hai//om project (DoBeS project)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-677"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "\u2260Akhoe Hai//om"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/075c5e9d-44ec-53fb-903d-467bd1792dcc.json b/oaitestdata/clarin-oai_dc/SET_1/json/075c5e9d-44ec-53fb-903d-467bd1792dcc.json
deleted file mode 100644
index 79cae031..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/075c5e9d-44ec-53fb-903d-467bd1792dcc.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Burnard, Lou"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3038",
-    "MetadataAccess": [
-        "oai:ota:oucs:3038"
-    ],
-    "PublicationTimestamp": "1675-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1675"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Wycherley, William, 1640-1716"
-    ],
-    "fulltext": "oai:ota:oucs:3038;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3038.xml;The country\u00e2\u0080\u0093wife: [a comedy, acted at the Theatre Royal, 1675];Wycherley, William, 1640-1716;not after: 1675;text_and_corpus_linguistics;English drama (Comedy);eng;Oxford Text Archive, University of Oxford;Burnard, Lou;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "075c5e9d-44ec-53fb-903d-467bd1792dcc",
-    "oai_identifier": [
-        "oai:ota:oucs:3038"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama Comedy"
-        }
-    ],
-    "title": [
-        "The country\u00e2\u0080\u0093wife: [a comedy, acted at the Theatre Royal, 1675]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3038.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/076ac53d-1074-5707-bd2c-62e7a641a527.json b/oaitestdata/clarin-oai_dc/SET_1/json/076ac53d-1074-5707-bd2c-62e7a641a527.json
deleted file mode 100644
index cd6726a8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/076ac53d-1074-5707-bd2c-62e7a641a527.json
+++ /dev/null
@@ -1,88 +0,0 @@
-{
-    "Contact": [
-        "University of Bergen"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Wolof"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/112",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/112"
-    ],
-    "PID": "http://hdl.handle.net/11509/112",
-    "PublicationTimestamp": "2014-09-20T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Bergen"
-    ],
-    "ResourceType": [
-        "LanguageDescription"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Dione, Cheikh M. Bamba"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/112;2016-04-15T05:59:21Z;hdl_11509_1;hdl_11509_2;Wolof Morphological Analyzer;Dione, Cheikh M. Bamba;Wolof;Morphology;Analyzer;Finite-State;Fst;Tool;Finite-State Fst Tool;This README describes a finite-state based morphological analyzer of Wolof.\r\nThe analyzer was developed and tested on natural language data extracted from Wolof text books. \r\nThese include Ciss\u00e9, M. (1994). Contes wolof modernes. L\u2019harmattan;\r\nand Ba, M. (2007). Bataaxal bu gudde nii. Nouvelles Editions Africaines du S\u00e9n\u00e9gal (NEAS). \r\nAs of September 2014, the tool shows a high coverage (more than 90%) on unseen data.\r\n\r\nSee: Cheikh M. Bamba Dione: A Morphological Analyzer For Wolof Using Finite-State Techniques. In: Proceedings of the Eighth International Conference on Language Resources and Evaluation. Eds. Nicoletta Calzolari et al. European Language Resources Association 2012. ISBN 978-2-9517408-7-7.\r\n\r\nPlease make reference to the above mentioned paper when publishing research based on this analyzer.;2014-09-20;LanguageDescription;http://hdl.handle.net/11509/112;wol;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;University of Bergen",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "076ac53d-1074-5707-bd2c-62e7a641a527",
-    "notes": [
-        "This README describes a finite-state based morphological analyzer of Wolof.\r\nThe analyzer was developed and tested on natural language data extracted from Wolof text books. \r\nThese include Ciss\u00e9, M. (1994). Contes wolof modernes. L\u2019harmattan;\r\nand Ba, M. (2007). Bataaxal bu gudde nii. Nouvelles Editions Africaines du S\u00e9n\u00e9gal (NEAS). \r\nAs of September 2014, the tool shows a high coverage (more than 90%) on unseen data.\r\n\r\nSee: Cheikh M. Bamba Dione: A Morphological Analyzer For Wolof Using Finite-State Techniques. In: Proceedings of the Eighth International Conference on Language Resources and Evaluation. Eds. Nicoletta Calzolari et al. European Language Resources Association 2012. ISBN 978-2-9517408-7-7.\r\n\r\nPlease make reference to the above mentioned paper when publishing research based on this analyzer."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/112"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Wolof"
-        },
-        {
-            "name": "Morphology"
-        },
-        {
-            "name": "Analyzer"
-        },
-        {
-            "name": "Finite-State"
-        },
-        {
-            "name": "Fst"
-        },
-        {
-            "name": "Tool"
-        },
-        {
-            "name": "Finite-State Fst Tool"
-        }
-    ],
-    "title": [
-        "Wolof Morphological Analyzer"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/078ac7d8-0896-5814-81a3-8310b8f1b20f.json b/oaitestdata/clarin-oai_dc/SET_1/json/078ac7d8-0896-5814-81a3-8310b8f1b20f.json
deleted file mode 100644
index 2f6cc037..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/078ac7d8-0896-5814-81a3-8310b8f1b20f.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Politechnika Wroc\u0142awska"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 651",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/50",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/50"
-    ],
-    "PID": "http://hdl.handle.net/11321/50",
-    "PublicationTimestamp": "2015-01-22T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Politechnika Wroc\u0142awska"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Ba\u0144ka-Kowalczyk, Magdalena"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/50;2015-01-29T15:14:58Z;hdl_11321_3;hdl_11321_4;International Women's Day Corpus;Ba\u0144ka-Kowalczyk, Magdalena;International Women's Day;woman;champion of work;work competition;league of women;work;The corpus contains articles form the daily \"Trybuna Ludu\" from years 1949-1956.The articles dealt with the situation of women, they were especially concerned with the International Women's Day (arrangements and celebration). \"Trybuna Ludu\" was first published in 1948 and was the main tool of the communist propaganda. Articles in Trybuna Ludu regard the life of the government, report visits by representatives of friendly countries and point to the threat to peace on the part of the imperialist countries. Moreover, journalists explained the communist doctrine and described the lives of the workers, as well as organizations \u2013 including women organizations.;2015-01-22;corpus;http://hdl.handle.net/11321/50;pol;Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0);http://creativecommons.org/licenses/by-nc-nd/3.0/;CC;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessin",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "078ac7d8-0896-5814-81a3-8310b8f1b20f",
-    "notes": [
-        "The corpus contains articles form the daily \"Trybuna Ludu\" from years 1949-1956.The articles dealt with the situation of women, they were especially concerned with the International Women's Day (arrangements and celebration). \"Trybuna Ludu\" was first published in 1948 and was the main tool of the communist propaganda. Articles in Trybuna Ludu regard the life of the government, report visits by representatives of friendly countries and point to the threat to peace on the part of the imperialist countries. Moreover, journalists explained the communist doctrine and described the lives of the workers, as well as organizations \u2013 including women organizations."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/50"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "International Womens Day"
-        },
-        {
-            "name": "woman"
-        },
-        {
-            "name": "champion work"
-        },
-        {
-            "name": "work competition"
-        },
-        {
-            "name": "league women"
-        },
-        {
-            "name": "work"
-        }
-    ],
-    "title": [
-        "International Women's Day Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/07c2e517-7cfe-55ba-83d1-c3ca2c6d414f.json b/oaitestdata/clarin-oai_dc/SET_1/json/07c2e517-7cfe-55ba-83d1-c3ca2c6d414f.json
deleted file mode 100644
index 9b3ef0ce..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/07c2e517-7cfe-55ba-83d1-c3ca2c6d414f.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Johannes V. Jensen-centret, Aarhus Universitet"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "text/xml",
-        "downloadable_files_count: 4",
-        "application/pdf",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Danish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repository.clarin.dk:20.500.12115/20",
-    "MetadataAccess": [
-        "oai:repository.clarin.dk:20.500.12115/20"
-    ],
-    "PID": "http://hdl.handle.net/20.500.12115/20",
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Johannes V. Jensen-centret, Aarhus Universitet"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Iversen, Stefan",
-        "Johannes V. Jensen"
-    ],
-    "fulltext": "oai:repository.clarin.dk:20.500.12115/20;2018-06-28T13:26:44Z;hdl_20.500.12115_1;hdl_20.500.12115_3;Johannes V. Jensen Corpus;Iversen, Stefan;Johannes V. Jensen;literature;I regi af CLARIN-projektet og i samarbejde med rettighedshaverne, gjorde  Jensen Forum i 2011  hovedparten af Jensens udgivelser tilg\u00e6ngelige i s\u00f8gbare fuldtekstversioner, som man nu finder p\u00e5 dette websted.\r\nAlle v\u00e6rker er publiceret digitalt i XML-formatet (TEIP5DKCLARIN-format) af Johannes V. Jensen-Centret, Aarhus Universitet.\r\nDer er tale om de samme udgivelser som ligger p\u00e5 \"Jensen online\": http://johannesvjensen.dk/jensenonline/liste-over-vaerker/ (undtagen Br\u00e6en, Daduse og Kornmarken), nemlig: \r\nAandens Stadier\r\n\u00c6stetik og Udvikling\r\nChristofer Columbus\r\nCimbrernes Tog\r\nDen ny Verden\r\nDet Blivende\r\nDet tabte Land\r\nDr. Renaults Fristelser\r\nDyrenes Forvandling\r\nEvolution og Moral\r\nG\u00e6st kommer til Verden\r\nGudrun\r\nHamlet\r\nHjulet\r\nJ\u00f8rgine\r\nKvinden i Sagatiden\r\nMadame DOra\r\nMarieh\u00f8nen\r\nMindets Tavle\r\nM\u00f8llen\r\nMyter ny samling\r\nMyter og Jagter\r\nMyter\r\nNordisk Aand\r\nNordvejen\r\nNye Myter\r\nOm Sproget og Undervisningen\r\nPisangen\r\nRetninger i Tiden\r\nRudyard Kipling\r\nS\u00e6lernes \u00d8\r\nSangerinden\r\nSingaporenoveller\r\nSkibet\r\nSwift og Oehlenschl\u00e4ger\r\nTilblivelsen\r\nUdvikling og Form\r\nUngt er endnu Ordet\r\nVed Livets Bred og andre Myter\r\nVerdens Lys\r\nVor Oprindelse\r\nVor Tidsalder;2011;corpus;http://hdl.handle.net/20.500.12115/20;dan;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;PUB;application/zip;application/pdf;application/pdf;text/xml;text/plain; charset=utf-8;downloadable_files_count: 4;Johannes V. Jensen-centret, Aarhus Universitet;http://johannesvjensen.dk/jensenonline/liste-over-vaerker/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "07c2e517-7cfe-55ba-83d1-c3ca2c6d414f",
-    "notes": [
-        "I regi af CLARIN-projektet og i samarbejde med rettighedshaverne, gjorde  Jensen Forum i 2011  hovedparten af Jensens udgivelser tilg\u00e6ngelige i s\u00f8gbare fuldtekstversioner, som man nu finder p\u00e5 dette websted.\r\nAlle v\u00e6rker er publiceret digitalt i XML-formatet (TEIP5DKCLARIN-format) af Johannes V. Jensen-Centret, Aarhus Universitet.\r\nDer er tale om de samme udgivelser som ligger p\u00e5 \"Jensen online\": http://johannesvjensen.dk/jensenonline/liste-over-vaerker/ (undtagen Br\u00e6en, Daduse og Kornmarken), nemlig: \r\nAandens Stadier\r\n\u00c6stetik og Udvikling\r\nChristofer Columbus\r\nCimbrernes Tog\r\nDen ny Verden\r\nDet Blivende\r\nDet tabte Land\r\nDr. Renaults Fristelser\r\nDyrenes Forvandling\r\nEvolution og Moral\r\nG\u00e6st kommer til Verden\r\nGudrun\r\nHamlet\r\nHjulet\r\nJ\u00f8rgine\r\nKvinden i Sagatiden\r\nMadame DOra\r\nMarieh\u00f8nen\r\nMindets Tavle\r\nM\u00f8llen\r\nMyter ny samling\r\nMyter og Jagter\r\nMyter\r\nNordisk Aand\r\nNordvejen\r\nNye Myter\r\nOm Sproget og Undervisningen\r\nPisangen\r\nRetninger i Tiden\r\nRudyard Kipling\r\nS\u00e6lernes \u00d8\r\nSangerinden\r\nSingaporenoveller\r\nSkibet\r\nSwift og Oehlenschl\u00e4ger\r\nTilblivelsen\r\nUdvikling og Form\r\nUngt er endnu Ordet\r\nVed Livets Bred og andre Myter\r\nVerdens Lys\r\nVor Oprindelse\r\nVor Tidsalder"
-    ],
-    "oai_identifier": [
-        "oai:repository.clarin.dk:20.500.12115/20"
-    ],
-    "oai_set": [
-        "hdl_20.500.12115_1",
-        "hdl_20.500.12115_3"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "literature"
-        }
-    ],
-    "title": [
-        "Johannes V. Jensen Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/07cc6aa5-c09d-52f0-806c-6285879adc23.json b/oaitestdata/clarin-oai_dc/SET_1/json/07cc6aa5-c09d-52f0-806c-6285879adc23.json
deleted file mode 100644
index 8262e14c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/07cc6aa5-c09d-52f0-806c-6285879adc23.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "The National Library of Sweden"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/19",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/19"
-    ],
-    "PID": "http://hdl.handle.net/10794/19",
-    "PublicationTimestamp": "2015-04-23T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "The National Library of Sweden"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/19;2017-10-27T16:47:39Z;hdl_10794_1;hdl_10794_2;Aftonbladet 1850's (2017-10-16);Aftonbladet 1850-talet (2017-10-16);n/a, n/a;Swedish;News;A corpus with texts from Aftonbladet in the 1850's.;En korpus med texter fr\u00e5n Aftonbladet p\u00e5 1850-talet.;2015-04-23;corpus;http://hdl.handle.net/10794/19;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;The National Library of Sweden;https://spraakbanken.gu.se/swe/resurs/kubhist-aftonbladet-1850",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "07cc6aa5-c09d-52f0-806c-6285879adc23",
-    "notes": [
-        "A corpus with texts from Aftonbladet in the 1850's.",
-        "En korpus med texter fr\u00e5n Aftonbladet p\u00e5 1850-talet."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/19"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "News"
-        }
-    ],
-    "title": [
-        "Aftonbladet 1850's (2017-10-16)",
-        "Aftonbladet 1850-talet (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/080541ae-54c6-5779-a7bf-c4781c3a6225.json b/oaitestdata/clarin-oai_dc/SET_1/json/080541ae-54c6-5779-a7bf-c4781c3a6225.json
deleted file mode 100644
index ffe7b463..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/080541ae-54c6-5779-a7bf-c4781c3a6225.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contributor": [
-        "Gippert, Jost"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-459",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-459"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-459",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-459;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS;Gippert, Jost;ca. 16 Mio. entries, relational databases, linked with texts (XML-structuring in progress);2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-459;downloadable_files_count: 0;Germany;http://titus.fkidg1.uni-frankfurt.de/database/titusinx/wordwhl.htm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "080541ae-54c6-5779-a7bf-c4781c3a6225",
-    "notes": [
-        "ca. 16 Mio. entries, relational databases, linked with texts (XML-structuring in progress)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-459"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/08596e6f-dfe5-558e-9e0a-df837a96d958.json b/oaitestdata/clarin-oai_dc/SET_1/json/08596e6f-dfe5-558e-9e0a-df837a96d958.json
deleted file mode 100644
index 49d8bef4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/08596e6f-dfe5-558e-9e0a-df837a96d958.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 45.3 KB)"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0225",
-    "MetadataAccess": [
-        "oai:ota:oucs:0225"
-    ],
-    "PublicationYear": [
-        "310 BCE-230 BCE"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Academic dissertations"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Aristarchus, of Samos"
-    ],
-    "fulltext": "oai:ota:oucs:0225;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0225.xml;On the sizes and distances of the sun and moon. English;Sizes and distances / Aristarchus;Aristarchus, of Samos;310 BCE-230 BCE;text_and_corpus_linguistics;Academic dissertations -- Greece -- B.C.;grc;Oxford Text Archive, University of Oxford;(1 file : ca. 45.3 KB);Text;Academic dissertations;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "08596e6f-dfe5-558e-9e0a-df837a96d958",
-    "oai_identifier": [
-        "oai:ota:oucs:0225"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Academic dissertations -- Greece -- B.C."
-        }
-    ],
-    "title": [
-        "On the sizes and distances of the sun and moon. English",
-        "Sizes and distances / Aristarchus"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0225.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/09026752-eda2-50d9-95cb-d8a5b0ed80fa.json b/oaitestdata/clarin-oai_dc/SET_1/json/09026752-eda2-50d9-95cb-d8a5b0ed80fa.json
deleted file mode 100644
index df76640e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/09026752-eda2-50d9-95cb-d8a5b0ed80fa.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Wroclaw University of Science and Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/606",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/606"
-    ],
-    "PID": "http://hdl.handle.net/11321/606",
-    "PublicationTimestamp": "2018-09-28T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Wroclaw University of Science and Technology"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "author": [
-        "Koco\u0144, Jan"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/606;2018-10-04T13:42:47Z;hdl_11321_3;hdl_11321_4;KGR10 FastText Polish word embeddings;Koco\u0144, Jan;Polish;embeddings;word embeddings;KGR10;Fasttext;skipgram;cbow;Distributional language model (both textual and binary) for Polish (word embeddings) trained on KGR10 corpus (over 4 billion of words) using Fasttext with the following variants (all possible combinations):\r\n- dimension: 100, 300\r\n- method: skipgram, cbow\r\n- source text: plain, plain.lower, plain.lemma, plain.lemma.lower;2018-09-28;languageDescription;http://hdl.handle.net/11321/606;pol;application/zip;downloadable_files_count: 1;Wroclaw University of Science and Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "09026752-eda2-50d9-95cb-d8a5b0ed80fa",
-    "notes": [
-        "Distributional language model (both textual and binary) for Polish (word embeddings) trained on KGR10 corpus (over 4 billion of words) using Fasttext with the following variants (all possible combinations):\r\n- dimension: 100, 300\r\n- method: skipgram, cbow\r\n- source text: plain, plain.lower, plain.lemma, plain.lemma.lower"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/606"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Polish"
-        },
-        {
-            "name": "embeddings"
-        },
-        {
-            "name": "word embeddings"
-        },
-        {
-            "name": "KGR"
-        },
-        {
-            "name": "Fasttext"
-        },
-        {
-            "name": "skipgram"
-        },
-        {
-            "name": "cbow"
-        }
-    ],
-    "title": [
-        "KGR10 FastText Polish word embeddings"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/090e3711-8300-56f1-b5f9-97f1151c7232.json b/oaitestdata/clarin-oai_dc/SET_1/json/090e3711-8300-56f1-b5f9-97f1151c7232.json
deleted file mode 100644
index 33e7e56b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/090e3711-8300-56f1-b5f9-97f1151c7232.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "ZRC SAZU"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1038",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1038"
-    ],
-    "PID": "http://hdl.handle.net/11356/1038",
-    "PublicationTimestamp": "2006-08-31T11:59:59Z",
-    "PublicationYear": [
-        "2006"
-    ],
-    "Publisher": [
-        "ZRC SAZU"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)",
-        "https://creativecommons.org/licenses/by-nc/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Jakopin, Primo\u017e"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1038;2017-04-25T08:23:16Z;hdl_11356_1023;hdl_11356_1024;List of Slovenian headwords 1.1;Jakopin, Primo\u017e;headwords;A list of headwords from the collection \"Besede slovenskega jezika\" (Words of Slovenian Language).;2006-08-31;lexicalConceptualResource;http://hdl.handle.net/11356/1038;slv;Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0);https://creativecommons.org/licenses/by-nc/4.0/;PUB;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;ZRC SAZU;http://bos.zrc-sazu.si/besede_en.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "090e3711-8300-56f1-b5f9-97f1151c7232",
-    "notes": [
-        "A list of headwords from the collection \"Besede slovenskega jezika\" (Words of Slovenian Language)."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1038"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "headwords"
-        }
-    ],
-    "title": [
-        "List of Slovenian headwords 1.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/092ae80e-5e76-5f8a-86fa-926055c58b4f.json b/oaitestdata/clarin-oai_dc/SET_1/json/092ae80e-5e76-5f8a-86fa-926055c58b4f.json
deleted file mode 100644
index dc32b450..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/092ae80e-5e76-5f8a-86fa-926055c58b4f.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1029",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1029"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1029",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1029;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LAC Nqeq Corpus;Language and Cognition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1029;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI30248%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "092ae80e-5e76-5f8a-86fa-926055c58b4f",
-    "notes": [
-        "Language and Cognition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1029"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LAC Nqeq Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/09572bc5-2a50-5d3b-a503-542f117ec3c6.json b/oaitestdata/clarin-oai_dc/SET_1/json/09572bc5-2a50-5d3b-a503-542f117ec3c6.json
deleted file mode 100644
index d12798af..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/09572bc5-2a50-5d3b-a503-542f117ec3c6.json
+++ /dev/null
@@ -1,119 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech",
-        "English",
-        "French",
-        "German",
-        "Hungarian",
-        "Polish",
-        "Spanish",
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2121",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2121"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2121",
-    "PublicationTimestamp": "2017-04-03T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/257528",
-        "info:eu-repo/grantAgreement/EC/H2020/644753",
-        "http://hdl.handle.net/11858/00-097C-0000-0022-D9BF-5"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)",
-        "http://creativecommons.org/licenses/by-nc/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Haji\u010d, Jan",
-        "Ure\u0161ov\u00e1, Zde\u0148ka",
-        "Libovick\u00fd, Jind\u0159ich",
-        "Du\u0161ek, Ond\u0159ej",
-        "Pecina, Pavel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2121;2017-11-09T14:20:29Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Khresmoi Query Translation Test Data 2.0;Pecina, Pavel;Du\u0161ek, Ond\u0159ej;Haji\u010d, Jan;Libovick\u00fd, Jind\u0159ich;Ure\u0161ov\u00e1, Zde\u0148ka;corpus;test data;medical;health;machine translation;Czech;English;French;German;Hungarian;Polish;Spanish;Swedish;This package contains data sets for development and testing of machine translation of medical queries between Czech, English, French, German, Hungarian, Polish, Spanish ans Swedish. The queries come from general public and medical experts. This is version 2.0 extending the previous version by adding Hungarian, Polish, Spanish, and Swedish translations.;2017-04-03;corpus;http://hdl.handle.net/11234/1-2121;ces;eng;fra;deu;hun;pol;spa;swe;info:eu-repo/grantAgreement/EC/FP7/257528;info:eu-repo/grantAgreement/EC/H2020/644753;http://hdl.handle.net/11858/00-097C-0000-0022-D9BF-5;Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0);http://creativecommons.org/licenses/by-nc/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://khresmoi.eu http://kconnect.eu",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "09572bc5-2a50-5d3b-a503-542f117ec3c6",
-    "notes": [
-        "This package contains data sets for development and testing of machine translation of medical queries between Czech, English, French, German, Hungarian, Polish, Spanish ans Swedish. The queries come from general public and medical experts. This is version 2.0 extending the previous version by adding Hungarian, Polish, Spanish, and Swedish translations."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2121"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "test data"
-        },
-        {
-            "name": "medical"
-        },
-        {
-            "name": "health"
-        },
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "Czech"
-        },
-        {
-            "name": "English"
-        },
-        {
-            "name": "French"
-        },
-        {
-            "name": "German"
-        },
-        {
-            "name": "Hungarian"
-        },
-        {
-            "name": "Polish"
-        },
-        {
-            "name": "Spanish"
-        }
-    ],
-    "title": [
-        "Khresmoi Query Translation Test Data 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0989aa56-54a9-5b5c-bc3c-722204c90acf.json b/oaitestdata/clarin-oai_dc/SET_1/json/0989aa56-54a9-5b5c-bc3c-722204c90acf.json
deleted file mode 100644
index 813be74e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0989aa56-54a9-5b5c-bc3c-722204c90acf.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Serbian",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1059",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1059"
-    ],
-    "PID": "http://hdl.handle.net/11356/1059",
-    "PublicationTimestamp": "2016-03-09T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/324414"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN.SI User Licence for Internet Corpora",
-        "ACA",
-        "http://www.clarin.si/info/wp-content/uploads/2016/01/CLARIN.SI-WAC-2016-01.pdf"
-    ],
-    "author": [
-        "Espl\u00e0-Gomis, Miquel",
-        "Klubi\u010dka, Filip",
-        "Ortiz Rojas, Sergio",
-        "Ljube\u0161i\u0107, Nikola",
-        "Toral, Antonio"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1059;2018-10-29T12:10:36Z;hdl_11356_1023;hdl_11356_1024;Serbian-English parallel corpus srenWaC 1.0;Ljube\u0161i\u0107, Nikola;Espl\u00e0-Gomis, Miquel;Ortiz Rojas, Sergio;Klubi\u010dka, Filip;Toral, Antonio;parallel corpus;web corpus;multilingual;The srenWaC corpus consists of sentence aligned parallel Serbian-English texts crawled from the .rs top-level domain for Serbia. The corpus was built with Spidextor (https://github.com/abumatran/spidextor), a tool that glues together the output of SpiderLing used for crawling and Bitextor used for bitext extraction. The accuracy of the extracted bitext, given the evaluation results on other languages, can be estimated at 74% on the sentence level and 76% on the word level.;2016-03-09;corpus;http://hdl.handle.net/11356/1059;srp;eng;info:eu-repo/grantAgreement/EC/FP7/324414;CLARIN.SI User Licence for Internet Corpora;ACA;http://www.clarin.si/info/wp-content/uploads/2016/01/CLARIN.SI-WAC-2016-01.pdf;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;Jo\u017eef Stefan Institute",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0989aa56-54a9-5b5c-bc3c-722204c90acf",
-    "notes": [
-        "The srenWaC corpus consists of sentence aligned parallel Serbian-English texts crawled from the .rs top-level domain for Serbia. The corpus was built with Spidextor (https://github.com/abumatran/spidextor), a tool that glues together the output of SpiderLing used for crawling and Bitextor used for bitext extraction. The accuracy of the extracted bitext, given the evaluation results on other languages, can be estimated at 74% on the sentence level and 76% on the word level."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1059"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parallel corpus"
-        },
-        {
-            "name": "web corpus"
-        },
-        {
-            "name": "multilingual"
-        }
-    ],
-    "title": [
-        "Serbian-English parallel corpus srenWaC 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/09cb1014-3297-57df-97ac-6247be059d61.json b/oaitestdata/clarin-oai_dc/SET_1/json/09cb1014-3297-57df-97ac-6247be059d61.json
deleted file mode 100644
index ee76e0a8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/09cb1014-3297-57df-97ac-6247be059d61.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4418",
-    "MetadataAccess": [
-        "oai:ota:oucs:4418"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Brooke, Frances, 1724?-1789."
-    ],
-    "fulltext": "oai:ota:oucs:4418;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4418.xml;The history of Lady Julia Mandeville: In two volumes. By the translator of Lady Catesby's letters. [pt.1];Brooke, Frances, 1724?-1789.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "09cb1014-3297-57df-97ac-6247be059d61",
-    "oai_identifier": [
-        "oai:ota:oucs:4418"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The history of Lady Julia Mandeville: In two volumes. By the translator of Lady Catesby's letters. [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4418.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/09d8f598-2f52-5c15-aaca-d3341b92f93c.json b/oaitestdata/clarin-oai_dc/SET_1/json/09d8f598-2f52-5c15-aaca-d3341b92f93c.json
deleted file mode 100644
index a35a72d3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/09d8f598-2f52-5c15-aaca-d3341b92f93c.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5628",
-    "MetadataAccess": [
-        "oai:ota:oucs:5628"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Chaigneau, William, 1709-1781."
-    ],
-    "fulltext": "oai:ota:oucs:5628;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5628.xml;The history of Jack Connor.: [pt.1];Chaigneau, William, 1709-1781.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "09d8f598-2f52-5c15-aaca-d3341b92f93c",
-    "oai_identifier": [
-        "oai:ota:oucs:5628"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The history of Jack Connor.: [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5628.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0a353509-ca74-5ea2-9271-fd4c0d0f3855.json b/oaitestdata/clarin-oai_dc/SET_1/json/0a353509-ca74-5ea2-9271-fd4c0d0f3855.json
deleted file mode 100644
index 3fd5746b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0a353509-ca74-5ea2-9271-fd4c0d0f3855.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/555",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/555"
-    ],
-    "PID": "http://hdl.handle.net/11321/555",
-    "PublicationTimestamp": "2018-07-25T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Marciniak, Ma\u0142gorzata",
-        "Polak, Justyna"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/555;2018-07-25T10:16:47Z;hdl_11321_3;hdl_11321_4;Bulhakov - corpus of events, temporal expressions and temporal relations;Marciniak, Ma\u0142gorzata;Polak, Justyna;Bu\u0142hakov;TimeML;TIMEX3;temporal expressions;temporal relations;events;The corpus contains the text of the short story \"Fatalne jaja\" by Michai\u0142 Bu\u0142hakov (http:// www.wolnelektury.pl). The corpus is manually annotated with temporal expressions, events and temporal relations using TimeML gudelines adapted to Polish.;2018-07-25;corpus;http://hdl.handle.net/11321/555;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;Institute of Computer Science, Polish Academy of Sciences",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0a353509-ca74-5ea2-9271-fd4c0d0f3855",
-    "notes": [
-        "The corpus contains the text of the short story \"Fatalne jaja\" by Michai\u0142 Bu\u0142hakov (http:// www.wolnelektury.pl). The corpus is manually annotated with temporal expressions, events and temporal relations using TimeML gudelines adapted to Polish."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/555"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "TimeML"
-        },
-        {
-            "name": "TIMEX"
-        },
-        {
-            "name": "temporal expressions"
-        },
-        {
-            "name": "temporal relations"
-        },
-        {
-            "name": "events"
-        }
-    ],
-    "title": [
-        "Bulhakov - corpus of events, temporal expressions and temporal relations"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0a439ab3-1d94-5856-b51a-e7f1b6e7a33f.json b/oaitestdata/clarin-oai_dc/SET_1/json/0a439ab3-1d94-5856-b51a-e7f1b6e7a33f.json
deleted file mode 100644
index 8ff313a7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0a439ab3-1d94-5856-b51a-e7f1b6e7a33f.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "French"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4653",
-    "MetadataAccess": [
-        "oai:ota:oucs:4653"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gibbon, Edward, 1737-1794."
-    ],
-    "fulltext": "oai:ota:oucs:4653;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4653.xml;M\u00c3\u00a9moire justificatif pour servir de r\u00c3\u00a9ponse \u00c3\u00a0 l'expos\u00c3\u00a9, &c de la cour de France;Gibbon, Edward, 1737-1794.;text_and_corpus_linguistics;fra;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0a439ab3-1d94-5856-b51a-e7f1b6e7a33f",
-    "oai_identifier": [
-        "oai:ota:oucs:4653"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "M\u00c3\u00a9moire justificatif pour servir de r\u00c3\u00a9ponse \u00c3\u00a0 l'expos\u00c3\u00a9, &c de la cour de France"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4653.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0a55447b-f396-55ae-9bf0-e71e1b266d54.json b/oaitestdata/clarin-oai_dc/SET_1/json/0a55447b-f396-55ae-9bf0-e71e1b266d54.json
deleted file mode 100644
index 26aec1f8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0a55447b-f396-55ae-9bf0-e71e1b266d54.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4689",
-    "MetadataAccess": [
-        "oai:ota:oucs:4689"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dibdin, Charles, 1745-1814."
-    ],
-    "fulltext": "oai:ota:oucs:4689;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4689.xml;The cobler: or, a wife of ten thousand. A ballad opera. In two acts. As it is performed at the Theatre-Royal, Drury-Lane.;Dibdin, Charles, 1745-1814.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0a55447b-f396-55ae-9bf0-e71e1b266d54",
-    "oai_identifier": [
-        "oai:ota:oucs:4689"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The cobler: or, a wife of ten thousand. A ballad opera. In two acts. As it is performed at the Theatre-Royal, Drury-Lane."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4689.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0a5ac164-94bd-5ad6-bc5e-7f3511c5f45d.json b/oaitestdata/clarin-oai_dc/SET_1/json/0a5ac164-94bd-5ad6-bc5e-7f3511c5f45d.json
deleted file mode 100644
index d9ef14e4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0a5ac164-94bd-5ad6-bc5e-7f3511c5f45d.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contributor": [
-        "Manfred Pinkal",
-        "Simon Ostermann",
-        "Tatiana Anikina",
-        "Ashutosh Modi"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:inscript",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:inscript"
-    ],
-    "PID": "http://hdl.handle.net/21.11119/0000-0000-5DD4-9",
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "RelatedIdentifier": [
-        "Ashutosh Modi, Tatiana Anikina, Simon Ostermann and Manfred Pinkal. 2016. \"InScript: Narrative texts annotated with script information\". In Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC 16), Portoro\u017e, Slovenia. http://www.lrec-conf.org/proceedings/lrec2016/pdf/352_Paper.pdf"
-    ],
-    "ResourceType": [
-        "Collection",
-        "Dataset",
-        "Text"
-    ],
-    "Rights": [
-        "CC-BY-SA-NC-4.0"
-    ],
-    "author": [
-        "Ashutosh Modi, Fachrichtung Sprachwissenschaft und Sprachtechnologie, Universit\u00e4t des Saarlandes, Campus C7.4, 66123 Saarbr\u00fccken"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:inscript;2018-01-31T16:10:04Z;InScript: Narrative texts annotated with script information;Ashutosh Modi, Fachrichtung Sprachwissenschaft und Sprachtechnologie, Universit\u00e4t des Saarlandes, Campus C7.4, 66123 Saarbr\u00fccken;Scripts;Script Knowledge;Narrative Texts;Commonsense Knowledge;Crowdsourcing;The InScript corpus contains a total of 1000 narrative texts crowdsourced via Amazon Mechanical Turk. The texts cover 10 different scenarios describing everyday situations like taking a bath, baking a cake etc. It is annotated with script information in the form of scenario-specific events and participants labels. The texts are also annotated with coreference chains linking different mentions of the same entity within the document.;Ashutosh Modi;Tatiana Anikina;Simon Ostermann;Manfred Pinkal;2016;Collection;Dataset;Text;text/xml;clarind-uds:inscript;hdl:21.11119/0000-0000-5DD4-9;eng;Ashutosh Modi, Tatiana Anikina, Simon Ostermann and Manfred Pinkal. 2016. \"InScript: Narrative texts annotated with script information\". In Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC 16), Portoro\u017e, Slovenia. http://www.lrec-conf.org/proceedings/lrec2016/pdf/352_Paper.pdf;CC-BY-SA-NC-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0a5ac164-94bd-5ad6-bc5e-7f3511c5f45d",
-    "notes": [
-        "The InScript corpus contains a total of 1000 narrative texts crowdsourced via Amazon Mechanical Turk. The texts cover 10 different scenarios describing everyday situations like taking a bath, baking a cake etc. It is annotated with script information in the form of scenario-specific events and participants labels. The texts are also annotated with coreference chains linking different mentions of the same entity within the document."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:inscript"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Scripts"
-        },
-        {
-            "name": "Script Knowledge"
-        },
-        {
-            "name": "Narrative Texts"
-        },
-        {
-            "name": "Commonsense Knowledge"
-        },
-        {
-            "name": "Crowdsourcing"
-        }
-    ],
-    "title": [
-        "InScript: Narrative texts annotated with script information"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0a7184b0-4326-53f0-85c3-f902c1851b3a.json b/oaitestdata/clarin-oai_dc/SET_1/json/0a7184b0-4326-53f0-85c3-f902c1851b3a.json
deleted file mode 100644
index 618e99d8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0a7184b0-4326-53f0-85c3-f902c1851b3a.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "University of Augsburg"
-    ],
-    "Contributor": [
-        "Voormann, Holger",
-        "Gut, Ulrike"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-286",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-286"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-286",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Augsburg"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-286;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Platform for Annotated Corpora in XML;Gut, Ulrike;Voormann, Holger;Integrated tool for corpus linguists built on Eclipse, Vex, Subversive, etc. for creating and editing transcriptions and annotations, querying, managing version controlled data, and building a shippable corpus.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-286;downloadable_files_count: 0;Germany;University of Augsburg;http://pacx.sourceforge.net/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0a7184b0-4326-53f0-85c3-f902c1851b3a",
-    "notes": [
-        "Integrated tool for corpus linguists built on Eclipse, Vex, Subversive, etc. for creating and editing transcriptions and annotations, querying, managing version controlled data, and building a shippable corpus."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-286"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Platform for Annotated Corpora in XML"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0a770b07-018a-5dbf-931f-a916c484f443.json b/oaitestdata/clarin-oai_dc/SET_1/json/0a770b07-018a-5dbf-931f-a916c484f443.json
deleted file mode 100644
index f6fdad81..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0a770b07-018a-5dbf-931f-a916c484f443.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Tilde"
-    ],
-    "Contributor": [
-        "Vasiljeva, Anita"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Latvian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-711",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-711"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-711",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Tilde"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Latvia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-711;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Collection of Latvian literature;Vasiljeva, Anita;Masterpieces of Latvian literature from the beginning of Latvian literature until first decades of 20th century;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-711;lav;downloadable_files_count: 0;Latvia;Tilde;http://www.letonika.lv/klasiki",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0a770b07-018a-5dbf-931f-a916c484f443",
-    "notes": [
-        "Masterpieces of Latvian literature from the beginning of Latvian literature until first decades of 20th century"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-711"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Collection of Latvian literature"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0a778371-7663-55b4-8201-7f6cd953a62c.json b/oaitestdata/clarin-oai_dc/SET_1/json/0a778371-7663-55b4-8201-7f6cd953a62c.json
deleted file mode 100644
index 15b6e754..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0a778371-7663-55b4-8201-7f6cd953a62c.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "University of Sheffield"
-    ],
-    "Contributor": [
-        "Funk, Adam",
-        "Peters, Wim"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1395",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1395"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1395",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Sheffield"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1395;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;GATE-ANNIE-RDF;Funk, Adam;Peters, Wim;ANNIE-RDF developed by the GATE group at the University of Sheffield (http;//www.gate.ac.uk; Cunningham et al., 2002) is an Information Extraction (IE) web service for English. It consists of the following main language processing tools: tokeniser, sentence splitter, POS tagger, coreference resolver and named entity recogniser. \r\nThe named entity recogniser identifies and categorizes entity names (such as persons, organizations, and location names), temporal expressions (dates and times), and certain types of numerical expressions (monetary values and percentages). \r\nThe text spans and annotations are exported into an RDF-XML ontology, in which the recognized named entities are instances according to the PROTON ontology (http://proton.semanticweb.org/).\r\n\r\n\r\n\r\nH. Cunningham, D. Maynard, K. Bontcheva, and V. Tablan. 2002. GATE: A Framework and Graphical Development Environment for Robust NLP Tools and Applications. In Proceedings of the 40th Anniversary Meeting of the Association for Computational Linguistics (ACL-02).;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1395;downloadable_files_count: 0;United Kingdom;University of Sheffield",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0a778371-7663-55b4-8201-7f6cd953a62c",
-    "notes": [
-        "ANNIE-RDF developed by the GATE group at the University of Sheffield (http;//www.gate.ac.uk; Cunningham et al., 2002) is an Information Extraction (IE) web service for English. It consists of the following main language processing tools: tokeniser, sentence splitter, POS tagger, coreference resolver and named entity recogniser. \r\nThe named entity recogniser identifies and categorizes entity names (such as persons, organizations, and location names), temporal expressions (dates and times), and certain types of numerical expressions (monetary values and percentages). \r\nThe text spans and annotations are exported into an RDF-XML ontology, in which the recognized named entities are instances according to the PROTON ontology (http://proton.semanticweb.org/).\r\n\r\n\r\n\r\nH. Cunningham, D. Maynard, K. Bontcheva, and V. Tablan. 2002. GATE: A Framework and Graphical Development Environment for Robust NLP Tools and Applications. In Proceedings of the 40th Anniversary Meeting of the Association for Computational Linguistics (ACL-02)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1395"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "GATE-ANNIE-RDF"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0a84a124-9ecf-502f-b2e4-8df135ca2ffb.json b/oaitestdata/clarin-oai_dc/SET_1/json/0a84a124-9ecf-502f-b2e4-8df135ca2ffb.json
deleted file mode 100644
index 3dec9ca8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0a84a124-9ecf-502f-b2e4-8df135ca2ffb.json
+++ /dev/null
@@ -1,105 +0,0 @@
-{
-    "Contact": [
-        "Universit\u00e4t des Saarlandes"
-    ],
-    "Contributor": [
-        "Alla Mishchenko"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml"
-    ],
-    "Language": [
-        "Georgian",
-        "Ukrainian",
-        "Russian",
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:grug",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:grug"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0006-C150-9",
-    "PublicationTimestamp": "2012-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Universit\u00e4t des Saarlandes"
-    ],
-    "RelatedIdentifier": [
-        "Research report \"Building Parallel Treebanks for the Lesser-Resourced Languages\"",
-        "Slides \"A German-Georgian Treebank Project\"",
-        "XEROX Finite-State Tool: http://www.cis.upenn.edu/~cis639/docs/xfst.html",
-        "TIGER-XML format: http://www.ims.uni-stuttgart.de/projekte/TIGER/TIGERSearch/doc/html/TigerXML.html",
-        "Synpathy, tool for manual syntactical annotation: http://tla.mpi.nl/tools/tla-tools/older-tools/synpathy/",
-        "TIGERSearch tool to explore linguistically annotated texts: http://www.ims.uni-stuttgart.de/projekte/TIGER/TIGERSearch/oldindex.shtml",
-        "Stockholm Treealigner, a tool for aligning and searching parallel treebanks: http://www.ling.su.se/datorlingvistik/stockholm-treealigner-1.14019"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC BY 3.0) http://creativecommons.org/licenses/by/3.0/"
-    ],
-    "SpatialCoverage": [
-        "Georgia",
-        "Ukraine",
-        "Russia",
-        "Germany"
-    ],
-    "TemporalCoverage": [
-        "Georgia",
-        "Ukraine",
-        "Russia",
-        "Germany"
-    ],
-    "author": [
-        "Oleg Kapanadze"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:grug;2014-06-03T12:59:07Z;GRUG Parallel Treebank;Oleg Kapanadze;corpus linguistics;linguistics;computational linguistics;treebank;syntactic annotation;lesser-resourced languages;This dataset is made of two types of resources: four monolingual Treebanks (German, Georgian, Russian and Ukrainian), and four parallel Treebanks (German-Georgian, German-Russian, German-Ukrainian, Georgian-Ukrainian).\nThe parallel texts used for the outlined experiment comprises German sentences and their translations into Georgian and Russian languages compiled for the GREG NLP lexicon\nproject. The GREG itself contains valency data with the manually aligned Georgian, Russian, English and German verbs (ca. 1250) augmented with the examples of sentences considered as translation equivalents. Each subcorpus used for the study has a size of roughly 2600 sentence pairs that correspond to different syntactic subcategorization frames considered as German-Georgian translation equivalents. For the Russian and Ukrainian languages translation equivalents were provided by Dr. Alla Mishchenko.\n\nMorphological analysis\nFor the Georgian text analyses has been applied a finitestate morphological transducer using the XEROX FST tools.\nFor the rest of languages, German, Russian and Ukrainian, involved in the experiment, morphological features, including POS tags, were assigned manually drawing on the TIGER guidelines for the German language with the necessary changes relevant to the Russian and Ukrainian grammar formal description.\n\nSyntactic parsing\nThe syntactical annotation was done manually with Synpathy. The annotation followed the TIGER guidelines and the outcome follows the TIGER-XML format.\n\nAlignment of  monolingual Treebanks into parallel bilingual Treebanks\nThe alignment of the monolingual (GO, RU, UK, GE) Treebanks into the bilingual (GE-GO, GE-RU, GE-UK, GO-UK) ones was done manually with Stockholm TreeAligner. The issue was performed at sentence, phrase and word level. Two types of translations are aligned: \"exact\" and \"fuzzy\" translation equivalents.;Universit\u00e4t des Saarlandes;Alla Mishchenko;2012;Dataset;text/xml;clarind-uds:grug;hdl:11858/00-246C-0000-0006-C150-9;GREG NLP lexicon, A Georgian, Russian, English and German Valency Lexicon for Natural Language Processing: http://www2.informatik.uni-stuttgart.de/ivi/is/greg-index.html;kat;ukr;rus;deu;Research report \"Building Parallel Treebanks for the Lesser-Resourced Languages\";Slides \"A German-Georgian Treebank Project\";XEROX Finite-State Tool: http://www.cis.upenn.edu/~cis639/docs/xfst.html;TIGER-XML format: http://www.ims.uni-stuttgart.de/projekte/TIGER/TIGERSearch/doc/html/TigerXML.html;Synpathy, tool for manual syntactical annotation: http://tla.mpi.nl/tools/tla-tools/older-tools/synpathy/;TIGERSearch tool to explore linguistically annotated texts: http://www.ims.uni-stuttgart.de/projekte/TIGER/TIGERSearch/oldindex.shtml;Stockholm Treealigner, a tool for aligning and searching parallel treebanks: http://www.ling.su.se/datorlingvistik/stockholm-treealigner-1.14019;Georgia;Ukraine;Russia;Germany;Creative Commons Attribution 3.0 Unported (CC BY 3.0) http://creativecommons.org/licenses/by/3.0/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0a84a124-9ecf-502f-b2e4-8df135ca2ffb",
-    "notes": [
-        "This dataset is made of two types of resources: four monolingual Treebanks (German, Georgian, Russian and Ukrainian), and four parallel Treebanks (German-Georgian, German-Russian, German-Ukrainian, Georgian-Ukrainian).\nThe parallel texts used for the outlined experiment comprises German sentences and their translations into Georgian and Russian languages compiled for the GREG NLP lexicon\nproject. The GREG itself contains valency data with the manually aligned Georgian, Russian, English and German verbs (ca. 1250) augmented with the examples of sentences considered as translation equivalents. Each subcorpus used for the study has a size of roughly 2600 sentence pairs that correspond to different syntactic subcategorization frames considered as German-Georgian translation equivalents. For the Russian and Ukrainian languages translation equivalents were provided by Dr. Alla Mishchenko.\n\nMorphological analysis\nFor the Georgian text analyses has been applied a finitestate morphological transducer using the XEROX FST tools.\nFor the rest of languages, German, Russian and Ukrainian, involved in the experiment, morphological features, including POS tags, were assigned manually drawing on the TIGER guidelines for the German language with the necessary changes relevant to the Russian and Ukrainian grammar formal description.\n\nSyntactic parsing\nThe syntactical annotation was done manually with Synpathy. The annotation followed the TIGER guidelines and the outcome follows the TIGER-XML format.\n\nAlignment of  monolingual Treebanks into parallel bilingual Treebanks\nThe alignment of the monolingual (GO, RU, UK, GE) Treebanks into the bilingual (GE-GO, GE-RU, GE-UK, GO-UK) ones was done manually with Stockholm TreeAligner. The issue was performed at sentence, phrase and word level. Two types of translations are aligned: \"exact\" and \"fuzzy\" translation equivalents."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:grug"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus linguistics"
-        },
-        {
-            "name": "linguistics"
-        },
-        {
-            "name": "computational linguistics"
-        },
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "syntactic annotation"
-        },
-        {
-            "name": "lesser-resourced languages"
-        }
-    ],
-    "title": [
-        "GRUG Parallel Treebank"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0a8928a1-b026-5c83-8cc3-430e0b560c63.json b/oaitestdata/clarin-oai_dc/SET_1/json/0a8928a1-b026-5c83-8cc3-430e0b560c63.json
deleted file mode 100644
index b60381ab..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0a8928a1-b026-5c83-8cc3-430e0b560c63.json
+++ /dev/null
@@ -1,332 +0,0 @@
-{
-    "Contact": [
-        "Universal Dependencies Consortium"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)",
-        "Arabic",
-        "Basque",
-        "Bulgarian",
-        "Croatian",
-        "Czech",
-        "Danish",
-        "Dutch",
-        "English",
-        "Estonian",
-        "Finnish",
-        "French",
-        "German",
-        "Gothic",
-        "Modern Greek (1453-)",
-        "Hebrew",
-        "Hindi",
-        "Hungarian",
-        "Indonesian",
-        "Irish",
-        "Italian",
-        "Japanese",
-        "Latin",
-        "Norwegian",
-        "Church Slavic",
-        "Persian",
-        "Polish",
-        "Portuguese",
-        "Romanian",
-        "Slovenian",
-        "Spanish",
-        "Swedish",
-        "Tamil",
-        "Catalan",
-        "Chinese",
-        "Galician",
-        "Kazakh",
-        "Latvian",
-        "Russian",
-        "Turkish",
-        "Coptic",
-        "Sanskrit",
-        "Slovak",
-        "Ukrainian",
-        "Uighur",
-        "Vietnamese",
-        "Belarusian",
-        "Korean",
-        "Lithuanian",
-        "Urdu",
-        "Northern Sami",
-        "Upper Sorbian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2184",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2184"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2184",
-    "PublicationTimestamp": "2017-05-18T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Universal Dependencies Consortium"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Licence Universal Dependencies v2.0",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-2.0",
-        "PUB"
-    ],
-    "author": [
-        "Ion, Radu",
-        "Seraji, Mojgan",
-        "Manning, Christopher",
-        "Cebiro\u011flu Eryi\u011fit, G\u00fcl\u015fen",
-        "Ma\u0161ek, Jan",
-        "Uszkoreit, Hans",
-        "Hlav\u00e1\u010dov\u00e1, Jaroslava",
-        "Passarotti, Marco",
-        "Nguy\u1ec5n Th\u1ecb, L\u01b0\u01a1ng",
-        "Zhu, Hanzhi",
-        "Osenova, Petya",
-        "Macketanz, Vivien",
-        "Agi\u0107, \u017deljko",
-        "Simionescu, Radu",
-        "Muischnek, Kadri",
-        "Choi, Jinho",
-        "Montemagni, Simonetta",
-        "Ojala, Stina",
-        "Ure\u0161ov\u00e1, Zde\u0148ka",
-        "Moskalevskyi, Bohdan",
-        "Stella, Antonio",
-        "Rovati, Davide",
-        "Bank, Sebastian",
-        "Seeker, Wolfgang",
-        "Harris, Kim",
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "Sanguinetti, Manuela",
-        "Cinkov\u00e1, Silvie",
-        "Irimia, Elena",
-        "Goldberg, Yoav",
-        "Yu, Zhuoran",
-        "Simk\u00f3, Katalin",
-        "Simi, Maria",
-        "Badmaeva, Elena",
-        "Hladk\u00e1, Barbora",
-        "Trosterud, Trond",
-        "Krek, Simon",
-        "G\u00f6k\u0131rmak, Memduh",
-        "L\u00ea H\u1ed3ng, Ph\u01b0\u01a1ng",
-        "\u00d8vrelid, Lilja",
-        "Galbraith, Daniel",
-        "Lenci, Alessandro",
-        "Seddah, Djam\u00e9",
-        "Martins, Andr\u00e9",
-        "Ginter, Filip",
-        "Mititelu, Verginica",
-        "Erjavec, Toma\u017e",
-        "Johannsen, Anders",
-        "Bick, Eckhard",
-        "Mart\u00ednez Alonso, H\u00e9ctor",
-        "Kettnerov\u00e1, V\u00e1clava",
-        "Kayadelen, Tolga",
-        "Li, Josie",
-        "Haug, Dag",
-        "Rehm, Georg",
-        "Lynn, Teresa",
-        "Plank, Barbara",
-        "Freitas, Cl\u00e1udia",
-        "Varga, Viktor",
-        "Lyashevskaya, Olga",
-        "J\u00f8rgensen, Fredrik",
-        "M\u0103r\u0103nduc, C\u0103t\u0103lina",
-        "Ka\u015f\u0131kara, H\u00fcner",
-        "Pyysalo, Sampo",
-        "Kanerva, Jenna",
-        "Sulubacak, Umut",
-        "Sz\u00e1nt\u00f3, Zsolt",
-        "Chalub, Fabricio",
-        "Marheinecke, Katrin",
-        "Atutxa, Aitziber",
-        "Bauer, John",
-        "Matsumoto, Yuji",
-        "Dozat, Timothy",
-        "Ateyah, Luma",
-        "G\u00f3mez Guinovart, Xavier",
-        "M\u00fc\u00fcrisep, Kaili",
-        "Saul\u012bte, Baiba",
-        "Caron, Gauthier",
-        "Mandl, Michael",
-        "Nivre, Joakim",
-        "Prokopidis, Prokopis",
-        "Petrov, Slav",
-        "Reddy, Siva",
-        "Guillaume, Bruno",
-        "Gr\u016bz\u012btis, Normunds",
-        "Cetin, Savas",
-        "Haji\u010d jr., Jan",
-        "Perrier, Guy",
-        "Trukhina, Anna",
-        "Nainwani, Pinkey",
-        "de Marneffe, Marie-Catherine",
-        "Antonsen, Lene",
-        "Attia, Mohammed",
-        "Schuster, Sebastian",
-        "Missil\u00e4, Anna",
-        "Perez, Cenel-Augusto",
-        "Hohle, Petter",
-        "Makazhanov, Aibek",
-        "Tyers, Francis",
-        "McDonald, Ryan",
-        "Pretkalni\u0146a, Lauma",
-        "Farkas, Rich\u00e1rd",
-        "Moreno Romero, Laura",
-        "Sawanakunanon, Yanin",
-        "Washington, Jonathan North",
-        "Bosco, Cristina",
-        "Kirchner, Jesse",
-        "Fernandez Alcalde, Hector",
-        "Eli, Marhaba",
-        "Mori, Shunsuke",
-        "de Paiva, Valeria",
-        "Grioni, Matias",
-        "Real, Livy",
-        "Lertpradit, Saran",
-        "Asahara, Masayuki",
-        "Pitler, Emily",
-        "Suhr, Alane",
-        "Tanaka, Takaaki",
-        "Miyao, Yusuke",
-        "Vincze, Veronika",
-        "Kwak, Sookyoung",
-        "Cho, Yongseok",
-        "Bhat, Riyaz Ahmad",
-        "Mustafina, Nina",
-        "Garcia, Marcos",
-        "Loginova, Olga",
-        "Shimada, Atsuko",
-        "Nguy\u1ec5n Th\u1ecb Minh, Huy\u1ec1n",
-        "Nitisaroj, Rattima",
-        "Puolakainen, Tiina",
-        "Tsarfaty, Reut",
-        "Taji, Dima",
-        "Goenaga, Iakes",
-        "Rituma, Laura",
-        "H\u00e0 M\u1ef9, Linh",
-        "Lambertino, Lorenzo",
-        "Habash, Nizar",
-        "Droganova, Kira",
-        "Elkahky, Ali",
-        "Connor, Miriam",
-        "Mare\u010dek, David",
-        "Smith, Aaron",
-        "Banerjee, Esha",
-        "Nedoluzhko, Anna",
-        "Strnadov\u00e1, Jana",
-        "More, Amir",
-        "Mendon\u00e7a, Gustavo",
-        "\u0160imkov\u00e1, M\u00e1ria",
-        "Gajdo\u0161ov\u00e1, Katar\u00edna",
-        "Zeman, Daniel",
-        "Celano, Giuseppe G. A.",
-        "Dobrovoljc, Kaja",
-        "Popel, Martin",
-        "Laippala, Veronika",
-        "Gojenola, Koldo",
-        "Lando, Tatiana",
-        "Simov, Kiril",
-        "Ballesteros, Miguel",
-        "Nurmi, Hanna",
-        "Nikolaev, Vitaly",
-        "Rademaker, Alexandre",
-        "Ljube\u0161i\u0107, Nikola",
-        "Ahrenberg, Lars",
-        "Shakurova, Lena",
-        "Diaz de Ilarraza, Arantza",
-        "Rosa, Rudolf",
-        "Aranzabe, Maria Jesus",
-        "Li, Cheuk Ying",
-        "Candito, Marie",
-        "Shen, Mo",
-        "Saleh, Shadi",
-        "Burchardt, Aljoscha",
-        "Bengoetxea, Kepa",
-        "Shohibussirri, Muh",
-        "van Noord, Gertjan",
-        "Pascual, Elena",
-        "Rinaldi, Larissa",
-        "Bouma, Gosse",
-        "Foster, Jennifer",
-        "\u00c7\u00f6ltekin, \u00c7a\u011fr\u0131",
-        "Piitulainen, Jussi",
-        "Uematsu, Sumire",
-        "Gonz\u00e1les Saavedra, Berta",
-        "Uria, Larraitz",
-        "Manurung, Ruli",
-        "Leung, Herman",
-        "Kanayama, Hiroshi",
-        "Haji\u010d, Jan",
-        "Bowman, Sam",
-        "Kotsyba, Natalia",
-        "Silveira, Natalia"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2184;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Universal Dependencies 2.0 \u2013 CoNLL 2017 Shared Task Development and Test Data;Nivre, Joakim;Agi\u0107, \u017deljko;Ahrenberg, Lars;Antonsen, Lene;Aranzabe, Maria Jesus;Asahara, Masayuki;Ateyah, Luma;Attia, Mohammed;Atutxa, Aitziber;Badmaeva, Elena;Ballesteros, Miguel;Banerjee, Esha;Bank, Sebastian;Bauer, John;Bengoetxea, Kepa;Bhat, Riyaz Ahmad;Bick, Eckhard;Bosco, Cristina;Bouma, Gosse;Bowman, Sam;Burchardt, Aljoscha;Candito, Marie;Caron, Gauthier;Cebiro\u011flu Eryi\u011fit, G\u00fcl\u015fen;Celano, Giuseppe G. A.;Cetin, Savas;Chalub, Fabricio;Choi, Jinho;Cho, Yongseok;Cinkov\u00e1, Silvie;\u00c7\u00f6ltekin, \u00c7a\u011fr\u0131;Connor, Miriam;de Marneffe, Marie-Catherine;de Paiva, Valeria;Diaz de Ilarraza, Arantza;Dobrovoljc, Kaja;Dozat, Timothy;Droganova, Kira;Eli, Marhaba;Elkahky, Ali;Erjavec, Toma\u017e;Farkas, Rich\u00e1rd;Fernandez Alcalde, Hector;Foster, Jennifer;Freitas, Cl\u00e1udia;Gajdo\u0161ov\u00e1, Katar\u00edna;Galbraith, Daniel;Garcia, Marcos;Ginter, Filip;Goenaga, Iakes;Gojenola, Koldo;G\u00f6k\u0131rmak, Memduh;Goldberg, Yoav;G\u00f3mez Guinovart, Xavier;Gonz\u00e1les Saavedra, Berta;Grioni, Matias;Gr\u016bz\u012btis, Normunds;Guillaume, Bruno;Habash, Nizar;Haji\u010d, Jan;Haji\u010d jr., Jan;H\u00e0 M\u1ef9, Linh;Harris, Kim;Haug, Dag;Hladk\u00e1, Barbora;Hlav\u00e1\u010dov\u00e1, Jaroslava;Hohle, Petter;Ion, Radu;Irimia, Elena;Johannsen, Anders;J\u00f8rgensen, Fredrik;Ka\u015f\u0131kara, H\u00fcner;Kanayama, Hiroshi;Kanerva, Jenna;Kayadelen, Tolga;Kettnerov\u00e1, V\u00e1clava;Kirchner, Jesse;Kotsyba, Natalia;Krek, Simon;Kwak, Sookyoung;Laippala, Veronika;Lambertino, Lorenzo;Lando, Tatiana;L\u00ea H\u1ed3ng, Ph\u01b0\u01a1ng;Lenci, Alessandro;Lertpradit, Saran;Leung, Herman;Li, Cheuk Ying;Li, Josie;Ljube\u0161i\u0107, Nikola;Loginova, Olga;Lyashevskaya, Olga;Lynn, Teresa;Macketanz, Vivien;Makazhanov, Aibek;Mandl, Michael;Manning, Christopher;Manurung, Ruli;M\u0103r\u0103nduc, C\u0103t\u0103lina;Mare\u010dek, David;Marheinecke, Katrin;Mart\u00ednez Alonso, H\u00e9ctor;Martins, Andr\u00e9;Ma\u0161ek, Jan;Matsumoto, Yuji;McDonald, Ryan;Mendon\u00e7a, Gustavo;Missil\u00e4, Anna;Mititelu, Verginica;Miyao, Yusuke;Montemagni, Simonetta;More, Amir;Moreno Romero, Laura;Mori, Shunsuke;Moskalevskyi, Bohdan;Muischnek, Kadri;Mustafina, Nina;M\u00fc\u00fcrisep, Kaili;Nainwani, Pinkey;Nedoluzhko, Anna;Nguy\u1ec5n Th\u1ecb, L\u01b0\u01a1ng;Nguy\u1ec5n Th\u1ecb Minh, Huy\u1ec1n;Nikolaev, Vitaly;Nitisaroj, Rattima;Nurmi, Hanna;Ojala, Stina;Osenova, Petya;\u00d8vrelid, Lilja;Pascual, Elena;Passarotti, Marco;Perez, Cenel-Augusto;Perrier, Guy;Petrov, Slav;Piitulainen, Jussi;Pitler, Emily;Plank, Barbara;Popel, Martin;Pretkalni\u0146a, Lauma;Prokopidis, Prokopis;Puolakainen, Tiina;Pyysalo, Sampo;Rademaker, Alexandre;Real, Livy;Reddy, Siva;Rehm, Georg;Rinaldi, Larissa;Rituma, Laura;Rosa, Rudolf;Rovati, Davide;Saleh, Shadi;Sanguinetti, Manuela;Saul\u012bte, Baiba;Sawanakunanon, Yanin;Schuster, Sebastian;Seddah, Djam\u00e9;Seeker, Wolfgang;Seraji, Mojgan;Shakurova, Lena;Shen, Mo;Shimada, Atsuko;Shohibussirri, Muh;Silveira, Natalia;Simi, Maria;Simionescu, Radu;Simk\u00f3, Katalin;\u0160imkov\u00e1, M\u00e1ria;Simov, Kiril;Smith, Aaron;Stella, Antonio;Strnadov\u00e1, Jana;Suhr, Alane;Sulubacak, Umut;Sz\u00e1nt\u00f3, Zsolt;Taji, Dima;Tanaka, Takaaki;Trosterud, Trond;Trukhina, Anna;Tsarfaty, Reut;Tyers, Francis;Uematsu, Sumire;Ure\u0161ov\u00e1, Zde\u0148ka;Uria, Larraitz;Uszkoreit, Hans;van Noord, Gertjan;Varga, Viktor;Vincze, Veronika;Washington, Jonathan North;Yu, Zhuoran;\u017dabokrtsk\u00fd, Zden\u011bk;Zeman, Daniel;Zhu, Hanzhi;treebank;dependency;syntax;morphology;harmonized annotation;interset;universal tagset;stanford dependencies;Universal Dependencies is a project that seeks to develop cross-linguistically consistent treebank annotation for many languages, with the goal of facilitating multilingual parser development, cross-lingual learning, and parsing research from a language typology perspective. The annotation scheme is based on (universal) Stanford dependencies (de Marneffe et al., 2006, 2008, 2014), Google universal part-of-speech tags (Petrov et al., 2012), and the Interset interlingua for morphosyntactic tagsets (Zeman, 2008).\r\n\r\nThis release contains the test data used in the CoNLL 2017 shared task on parsing Universal Dependencies. Due to the shared task the test data was held hidden and not released together with the training and development data of UD 2.0. Therefore this release complements the UD 2.0 release (http://hdl.handle.net/11234/1-1983) to a full release of UD treebanks. In addition, the present release contains 18 new parallel test sets and 4 test sets in surprise languages. The present release also includes the development data already released with UD 2.0. Unlike regular UD releases, this one uses the folder-file structure that was visible to the systems participating in the shared task.;2017-05-18;corpus;http://hdl.handle.net/11234/1-2184;grc;ara;eus;bul;hrv;ces;dan;nld;eng;est;fin;fra;deu;got;ell;heb;hin;hun;ind;gle;ita;jpn;lat;nor;chu;fas;pol;por;ron;slv;spa;swe;tam;cat;zho;glg;kaz;lav;rus;tur;cop;san;slk;ukr;uig;vie;bel;kor;lit;urd;sme;hsb;bxr;kmr;Licence Universal Dependencies v2.0;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-2.0;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Universal Dependencies Consortium;http://universaldependencies.org/conll17/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0a8928a1-b026-5c83-8cc3-430e0b560c63",
-    "notes": [
-        "Universal Dependencies is a project that seeks to develop cross-linguistically consistent treebank annotation for many languages, with the goal of facilitating multilingual parser development, cross-lingual learning, and parsing research from a language typology perspective. The annotation scheme is based on (universal) Stanford dependencies (de Marneffe et al., 2006, 2008, 2014), Google universal part-of-speech tags (Petrov et al., 2012), and the Interset interlingua for morphosyntactic tagsets (Zeman, 2008).\r\n\r\nThis release contains the test data used in the CoNLL 2017 shared task on parsing Universal Dependencies. Due to the shared task the test data was held hidden and not released together with the training and development data of UD 2.0. Therefore this release complements the UD 2.0 release (http://hdl.handle.net/11234/1-1983) to a full release of UD treebanks. In addition, the present release contains 18 new parallel test sets and 4 test sets in surprise languages. The present release also includes the development data already released with UD 2.0. Unlike regular UD releases, this one uses the folder-file structure that was visible to the systems participating in the shared task."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2184"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "dependency"
-        },
-        {
-            "name": "syntax"
-        },
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "harmonized annotation"
-        },
-        {
-            "name": "interset"
-        },
-        {
-            "name": "universal tagset"
-        },
-        {
-            "name": "stanford dependencies"
-        }
-    ],
-    "title": [
-        "Universal Dependencies 2.0 \u2013 CoNLL 2017 Shared Task Development and Test Data"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0a8bbeda-1a3c-56f0-8d70-f9481a2e96d4.json b/oaitestdata/clarin-oai_dc/SET_1/json/0a8bbeda-1a3c-56f0-8d70-f9481a2e96d4.json
deleted file mode 100644
index a85819a3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0a8bbeda-1a3c-56f0-8d70-f9481a2e96d4.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "National University of Engineering, Peru"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2673",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2673"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2673",
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "National University of Engineering, Peru"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Coronado, Alberto",
-        "Villota, Elizabeth",
-        "Bello Medina, Kevin",
-        "Cardenas Acosta, Ronald"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2673;2018-07-02T22:05:54Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Engineering job ads corpus;Cardenas Acosta, Ronald;Bello Medina, Kevin;Coronado, Alberto;Villota, Elizabeth;job-advertisement;PoS tagging;text corpora;The corpus presented consists of job ads in Spanish related to Engineering positions in Peru.\r\nThe documents were preprocessed and annotated for POS tagging, NER, and topic modeling tasks.\r\n\r\nThe corpus is divided in two components:\r\n- POS tagging/ NER training data: Consisting of 800 job ads, each one tokenized and manually annotated with POS tag information (EAGLE format) and Entity Label in BIO format. \r\n- Topic modeling training data: containing 9000 documents stripped from stopwords. Comes in two formats:\r\n  * Whole text documents: containing all the information originally posted in the ad.\r\n  * Extracted chunks documents: containing chunks extracted by custom NER models (expected skills, tasks to perform, and preferred major), as described in Improving Topic Coherence Using Entity Extraction Denoising (to appear);2016;corpus;http://hdl.handle.net/11234/1-2673;spa;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;National University of Engineering, Peru;https://github.com/ronaldahmed/labor-market-demand-analysis",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0a8bbeda-1a3c-56f0-8d70-f9481a2e96d4",
-    "notes": [
-        "The corpus presented consists of job ads in Spanish related to Engineering positions in Peru.\r\nThe documents were preprocessed and annotated for POS tagging, NER, and topic modeling tasks.\r\n\r\nThe corpus is divided in two components:\r\n- POS tagging/ NER training data: Consisting of 800 job ads, each one tokenized and manually annotated with POS tag information (EAGLE format) and Entity Label in BIO format. \r\n- Topic modeling training data: containing 9000 documents stripped from stopwords. Comes in two formats:\r\n  * Whole text documents: containing all the information originally posted in the ad.\r\n  * Extracted chunks documents: containing chunks extracted by custom NER models (expected skills, tasks to perform, and preferred major), as described in Improving Topic Coherence Using Entity Extraction Denoising (to appear)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2673"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "job-advertisement"
-        },
-        {
-            "name": "PoS tagging"
-        },
-        {
-            "name": "text corpora"
-        }
-    ],
-    "title": [
-        "Engineering job ads corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0a9041fd-bb2b-5855-bfbc-6b73ec6a48e9.json b/oaitestdata/clarin-oai_dc/SET_1/json/0a9041fd-bb2b-5855-bfbc-6b73ec6a48e9.json
deleted file mode 100644
index 8250ce6c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0a9041fd-bb2b-5855-bfbc-6b73ec6a48e9.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3531",
-    "MetadataAccess": [
-        "oai:ota:oucs:3531"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Cowley, Mrs. (Hannah), 1743-1809."
-    ],
-    "fulltext": "oai:ota:oucs:3531;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3531.xml;Who's the dupe?: A farce: as it is acted at the Theatre-Royal in Drury-Lane. By Mrs. Cowley, ...;Cowley, Mrs. (Hannah), 1743-1809.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0a9041fd-bb2b-5855-bfbc-6b73ec6a48e9",
-    "oai_identifier": [
-        "oai:ota:oucs:3531"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Who's the dupe?: A farce: as it is acted at the Theatre-Royal in Drury-Lane. By Mrs. Cowley, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3531.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0a91f49d-056c-5390-94b5-aae34df030d5.json b/oaitestdata/clarin-oai_dc/SET_1/json/0a91f49d-056c-5390-94b5-aae34df030d5.json
deleted file mode 100644
index 9c1fe8df..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0a91f49d-056c-5390-94b5-aae34df030d5.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Gojawiczy\u0144ska"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 7",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/75",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/75"
-    ],
-    "PID": "http://hdl.handle.net/11321/75",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Gojawiczy\u0144ska"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Gojawiczy\u0144ska, Gojawiczy\u0144ska"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/75;2015-05-19T13:38:21Z;hdl_11321_3;hdl_11321_4;MWE Gojawiczy\u0144ska;Gojawiczy\u0144ska, Gojawiczy\u0144ska;Gojawiczy\u0144ska;2015-04-08;corpus;http://hdl.handle.net/11321/75;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 7;Gojawiczy\u0144ska",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0a91f49d-056c-5390-94b5-aae34df030d5",
-    "notes": [
-        "Gojawiczy\u0144ska"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/75"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Gojawiczy\u0144ska"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0aa4e26f-6d39-515b-a7f9-cc727a01f8ce.json b/oaitestdata/clarin-oai_dc/SET_1/json/0aa4e26f-6d39-515b-a7f9-cc727a01f8ce.json
deleted file mode 100644
index f9a54ee1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0aa4e26f-6d39-515b-a7f9-cc727a01f8ce.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3642",
-    "MetadataAccess": [
-        "oai:ota:oucs:3642"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Paley, William, 1743-1805."
-    ],
-    "fulltext": "oai:ota:oucs:3642;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3642.xml;Caution recommended in the use and application of Scripture language: A sermon preached July 15, 1777, in the cathedral church of Carlisle, at the visitation of the Right Reverend Edmund, Lord Bishop of Carlisle. By William Paley, ...;Paley, William, 1743-1805.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0aa4e26f-6d39-515b-a7f9-cc727a01f8ce",
-    "oai_identifier": [
-        "oai:ota:oucs:3642"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Caution recommended in the use and application of Scripture language: A sermon preached July 15, 1777, in the cathedral church of Carlisle, at the visitation of the Right Reverend Edmund, Lord Bishop of Carlisle. By William Paley, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3642.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0ab86989-f89e-55ef-93da-d8ec8e59977f.json b/oaitestdata/clarin-oai_dc/SET_1/json/0ab86989-f89e-55ef-93da-d8ec8e59977f.json
deleted file mode 100644
index 89e5a926..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0ab86989-f89e-55ef-93da-d8ec8e59977f.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "University of Bergen"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml",
-        "downloadable_files_count: 1",
-        "text/plain"
-    ],
-    "Language": [
-        "English",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/87",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/87"
-    ],
-    "PID": "http://hdl.handle.net/11509/87",
-    "PublicationTimestamp": "2004-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2004"
-    ],
-    "Publisher": [
-        "University of Bergen"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "gunns-license",
-        "www.dummy.org",
-        "RES"
-    ],
-    "author": [
-        "Ommundsen, \u00c5slaug"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/87;2017-01-13T08:40:22Z;hdl_11509_1;hdl_11509_2;The Botulph Breviary fragments;Ommundsen, \u00c5slaug;Fragment;Liturgy;13th Century;Transcription of UBB MS 1549, 1b.\n\nThe so-called Botulph Breviary fragments is a group of four fragments from the same Breviary, written in England in the late thirteenth century. One of the fragments contains the readings six to nine for the Matins of St Botulph's day (17 June, in Scotland 25 June). Nine readings constitute the highest degree of a saint's feast. St Botulph was a popular saint in Eastern England and Scotland, and the Botulph breviary was therefore perhaps written in Eastern England. The lessons six to nine, more or less extant in our fragment a, describe Botulph's discovery of Ikanho (possibly the present Iken in Suffolk, east of Ipswich), the exorcism of the area's demons, the building of the monastery (in 654), and, finally, to the great lament of his fellow brothers, Botulph's death (in 680). Apart from the readings of St Botulph's day, the fragments contain parts of the liturgy of the feast days of the Annunciation (25 March) and of the Saints Philip and Jacob (1 May).;2004;corpus;http://hdl.handle.net/11509/87;eng;lat;gunns-license;www.dummy.org;RES;text/xml;text/plain;downloadable_files_count: 1;University of Bergen;http://ub.uib.no/fragment/transcriptions/UBB%20MS%201549,%201b-transkr.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0ab86989-f89e-55ef-93da-d8ec8e59977f",
-    "notes": [
-        "Transcription of UBB MS 1549, 1b.\n\nThe so-called Botulph Breviary fragments is a group of four fragments from the same Breviary, written in England in the late thirteenth century. One of the fragments contains the readings six to nine for the Matins of St Botulph's day (17 June, in Scotland 25 June). Nine readings constitute the highest degree of a saint's feast. St Botulph was a popular saint in Eastern England and Scotland, and the Botulph breviary was therefore perhaps written in Eastern England. The lessons six to nine, more or less extant in our fragment a, describe Botulph's discovery of Ikanho (possibly the present Iken in Suffolk, east of Ipswich), the exorcism of the area's demons, the building of the monastery (in 654), and, finally, to the great lament of his fellow brothers, Botulph's death (in 680). Apart from the readings of St Botulph's day, the fragments contain parts of the liturgy of the feast days of the Annunciation (25 March) and of the Saints Philip and Jacob (1 May)."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/87"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Fragment"
-        },
-        {
-            "name": "Liturgy"
-        },
-        {
-            "name": "th Century"
-        }
-    ],
-    "title": [
-        "The Botulph Breviary fragments"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0ac9bcf4-10cb-53f1-8e0b-c7dded0e7711.json b/oaitestdata/clarin-oai_dc/SET_1/json/0ac9bcf4-10cb-53f1-8e0b-c7dded0e7711.json
deleted file mode 100644
index 77c37a11..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0ac9bcf4-10cb-53f1-8e0b-c7dded0e7711.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3161",
-    "MetadataAccess": [
-        "oai:ota:oucs:3161"
-    ],
-    "PublicationTimestamp": "1690-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1690"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Browne, Thomas, Sir, 1605-1682"
-    ],
-    "fulltext": "oai:ota:oucs:3161;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3161.xml;Letter to a friend;Browne, Thomas, Sir, 1605-1682;not after: 1690;text_and_corpus_linguistics;Letters -- England -- 17th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0ac9bcf4-10cb-53f1-8e0b-c7dded0e7711",
-    "oai_identifier": [
-        "oai:ota:oucs:3161"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Letters -- England -- th century"
-        }
-    ],
-    "title": [
-        "Letter to a friend"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3161.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0acc47b0-cf2b-50b2-9563-4d4682a4b06e.json b/oaitestdata/clarin-oai_dc/SET_1/json/0acc47b0-cf2b-50b2-9563-4d4682a4b06e.json
deleted file mode 100644
index 76cd9a16..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0acc47b0-cf2b-50b2-9563-4d4682a4b06e.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "less than 512 KB"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0219",
-    "MetadataAccess": [
-        "oai:ota:oucs:0219"
-    ],
-    "PublicationYear": [
-        "50-150"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Fiction"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Chariton"
-    ],
-    "fulltext": "oai:ota:oucs:0219;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0219.xml; Chaerea et Callirhoe  / compiled by Thesaurus Linguae Graecae;Chariton;50-150;text_and_corpus_linguistics;Fiction -- Greece -- 2nd century;grc;Oxford Text Archive, University of Oxford;less than 512 KB;Text;Fiction;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0acc47b0-cf2b-50b2-9563-4d4682a4b06e",
-    "oai_identifier": [
-        "oai:ota:oucs:0219"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- Greece -- nd century"
-        }
-    ],
-    "title": [
-        " Chaerea et Callirhoe  / compiled by Thesaurus Linguae Graecae"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0219.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0add56b0-59ae-5850-8a39-ecb6abfe6247.json b/oaitestdata/clarin-oai_dc/SET_1/json/0add56b0-59ae-5850-8a39-ecb6abfe6247.json
deleted file mode 100644
index 4e664c41..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0add56b0-59ae-5850-8a39-ecb6abfe6247.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "NHH Norwegian School of Economics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "application/octet-stream",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Norwegian Bokm\u00e5l"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/121",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/121"
-    ],
-    "PID": "http://hdl.handle.net/11509/121",
-    "PublicationTimestamp": "2017-01-10T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "NHH Norwegian School of Economics"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "CLARIN_RES-PLAN-INF",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEula?RES=1&PLAN=1&INF=1",
-        "RES"
-    ],
-    "author": [
-        "Bergen municipality"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/121;2017-01-18T09:25:04Z;hdl_11509_1;hdl_11509_2;Bergen municipality's interpreter's termbase;Bergen municipality;Interpreting;Terminology;Terminological;Termbase;The resource Tolking is a termbase consisting of terms, definitions and other conceptual information relating to a wide range of domains, developed for and by the interpreting services offered by Bergen municipality (Bergen kommune).;2017-01-10;lexicalConceptualResource;http://hdl.handle.net/11509/121;nob;CLARIN_RES-PLAN-INF;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEula?RES=1&PLAN=1&INF=1;RES;application/zip;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;NHH Norwegian School of Economics;http://www.terminologi.no",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0add56b0-59ae-5850-8a39-ecb6abfe6247",
-    "notes": [
-        "The resource Tolking is a termbase consisting of terms, definitions and other conceptual information relating to a wide range of domains, developed for and by the interpreting services offered by Bergen municipality (Bergen kommune)."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/121"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Interpreting"
-        },
-        {
-            "name": "Terminology"
-        },
-        {
-            "name": "Terminological"
-        },
-        {
-            "name": "Termbase"
-        }
-    ],
-    "title": [
-        "Bergen municipality's interpreter's termbase"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0ae240fc-2fdf-503d-a33e-0f738c7ca646.json b/oaitestdata/clarin-oai_dc/SET_1/json/0ae240fc-2fdf-503d-a33e-0f738c7ca646.json
deleted file mode 100644
index fcebb343..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0ae240fc-2fdf-503d-a33e-0f738c7ca646.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3999",
-    "MetadataAccess": [
-        "oai:ota:oucs:3999"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Vaughan, Thomas, fl. 1772-1820."
-    ],
-    "fulltext": "oai:ota:oucs:3999;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3999.xml;The hotel: or, the double valet. A farce, in two acts. As it is performed at the Theatre-Royal in Drury-Lane. By Thomas Vaughan, Esq.;Vaughan, Thomas, fl. 1772-1820.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0ae240fc-2fdf-503d-a33e-0f738c7ca646",
-    "oai_identifier": [
-        "oai:ota:oucs:3999"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The hotel: or, the double valet. A farce, in two acts. As it is performed at the Theatre-Royal in Drury-Lane. By Thomas Vaughan, Esq."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3999.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0afb5b21-7583-57d8-a227-e61fbf6b18f3.json b/oaitestdata/clarin-oai_dc/SET_1/json/0afb5b21-7583-57d8-a227-e61fbf6b18f3.json
deleted file mode 100644
index 411d4979..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0afb5b21-7583-57d8-a227-e61fbf6b18f3.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 718",
-        "text/plain; charset=utf-8",
-        "text/xml",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/238",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/238"
-    ],
-    "PID": "http://hdl.handle.net/11321/238",
-    "PublicationTimestamp": "2013-01-26T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Marci\u0144czuk, Micha\u0142",
-        "Maziarz, Marek",
-        "Wardy\u0144ski, Adam",
-        "Radziszewski, Adam",
-        "Broda, Bartosz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/238;2016-02-29T10:02:59Z;hdl_11321_3;hdl_11321_4;Wikipedia articles extracted from Polish Corpus of Wroc\u0142aw University of Technology;Maziarz, Marek;Broda, Bartosz;Marci\u0144czuk, Micha\u0142;Radziszewski, Adam;Wardy\u0144ski, Adam;free corpus;open license;The resource is the part of the Polish Corpus of Wroc\u0142aw University of Technology (fully available on the website http://nlp.pwr.wroc.pl/kpwr). The documents within this collection are the samples of the Polish Wikipedia articles manually annotated on the level of chunks and selected predicate-argument relations, named entities, relations between named entities, anaphora relations and word senses.;2013-01-26;corpus;http://hdl.handle.net/11321/238;pol;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;text/plain; charset=utf-8;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 718;Wroc\u0142aw University of Technology;http://nlp.pwr.wroc.pl/kpwr",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0afb5b21-7583-57d8-a227-e61fbf6b18f3",
-    "notes": [
-        "The resource is the part of the Polish Corpus of Wroc\u0142aw University of Technology (fully available on the website http://nlp.pwr.wroc.pl/kpwr). The documents within this collection are the samples of the Polish Wikipedia articles manually annotated on the level of chunks and selected predicate-argument relations, named entities, relations between named entities, anaphora relations and word senses."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/238"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "free corpus"
-        },
-        {
-            "name": "open license"
-        }
-    ],
-    "title": [
-        "Wikipedia articles extracted from Polish Corpus of Wroc\u0142aw University of Technology"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0b1ac959-93fc-5d58-9df5-0754a1d9c890.json b/oaitestdata/clarin-oai_dc/SET_1/json/0b1ac959-93fc-5d58-9df5-0754a1d9c890.json
deleted file mode 100644
index c9206c8e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0b1ac959-93fc-5d58-9df5-0754a1d9c890.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "King's College London"
-    ],
-    "Contributor": [
-        "Nelson, Prof. Janet L.",
-        "director, project"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/tei+xml",
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-862",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-862"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-862",
-    "PublicationTimestamp": "2005-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2005"
-    ],
-    "Publisher": [
-        "King's College London"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-862;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Anglos-Saxon charters;Nelson, Prof. Janet L.;director, project;Charters written in Anglo-Saxon England before A.D. 900, marked-up in TEI XML. Browsable online.;2005;corpus;http://hdl.handle.net/11372/LRT-862;eng;application/tei+xml;downloadable_files_count: 0;United Kingdom;King's College London;http://www.aschart.kcl.ac.uk/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0b1ac959-93fc-5d58-9df5-0754a1d9c890",
-    "notes": [
-        "Charters written in Anglo-Saxon England before A.D. 900, marked-up in TEI XML. Browsable online."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-862"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Anglos-Saxon charters"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0b23a652-323a-5df2-abd3-478b451e6645.json b/oaitestdata/clarin-oai_dc/SET_1/json/0b23a652-323a-5df2-abd3-478b451e6645.json
deleted file mode 100644
index 0ea2cef4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0b23a652-323a-5df2-abd3-478b451e6645.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3447",
-    "MetadataAccess": [
-        "oai:ota:oucs:3447"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Defoe, Daniel, 1661?-1731."
-    ],
-    "fulltext": "oai:ota:oucs:3447;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3447.xml;The conduct of some people: about pleading guilty. With some reasons why it was not thought proper to shew mercy to some who desir'd it.;Defoe, Daniel, 1661?-1731.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0b23a652-323a-5df2-abd3-478b451e6645",
-    "oai_identifier": [
-        "oai:ota:oucs:3447"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The conduct of some people: about pleading guilty. With some reasons why it was not thought proper to shew mercy to some who desir'd it."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3447.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0b2e0dce-d993-5ba2-9d53-71bfbe0a968b.json b/oaitestdata/clarin-oai_dc/SET_1/json/0b2e0dce-d993-5ba2-9d53-71bfbe0a968b.json
deleted file mode 100644
index 85751a70..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0b2e0dce-d993-5ba2-9d53-71bfbe0a968b.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4532",
-    "MetadataAccess": [
-        "oai:ota:oucs:4532"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dennis, John, 1657-1734."
-    ],
-    "fulltext": "oai:ota:oucs:4532;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4532.xml;An essay on the genius and writings of Shakespear: with some letters of criticism to The spectator. By Mr. Dennis;Dennis, John, 1657-1734.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0b2e0dce-d993-5ba2-9d53-71bfbe0a968b",
-    "oai_identifier": [
-        "oai:ota:oucs:4532"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An essay on the genius and writings of Shakespear: with some letters of criticism to The spectator. By Mr. Dennis"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4532.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0b3b0272-c5ac-59aa-b02d-a2ea7d4a3ce2.json b/oaitestdata/clarin-oai_dc/SET_1/json/0b3b0272-c5ac-59aa-b02d-a2ea7d4a3ce2.json
deleted file mode 100644
index eef2eead..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0b3b0272-c5ac-59aa-b02d-a2ea7d4a3ce2.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/pdf"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/294",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/294"
-    ],
-    "PID": "http://hdl.handle.net/11321/294",
-    "PublicationTimestamp": "2016-04-25T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Oleksy, Marcin",
-        "Marci\u0144czuk, Micha\u0142",
-        "Dziob, Agnieszka"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/294;2016-06-06T11:39:57Z;hdl_11321_3;hdl_11321_4;KPWr annotation guidelines - named entities;Marci\u0144czuk, Micha\u0142;Oleksy, Marcin;Dziob, Agnieszka;named entities;annotation guidelines;corpora annotation;Named entities annotation guidelines describing the process of manual annotation of documents in Polish Corpus of Wroc\u0142aw University of Technology (KPWr);2016-04-25;languageDescription;http://hdl.handle.net/11321/294;pol;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;application/pdf;downloadable_files_count: 1;Wroc\u0142aw University of Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0b3b0272-c5ac-59aa-b02d-a2ea7d4a3ce2",
-    "notes": [
-        "Named entities annotation guidelines describing the process of manual annotation of documents in Polish Corpus of Wroc\u0142aw University of Technology (KPWr)"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/294"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "named entities"
-        },
-        {
-            "name": "annotation guidelines"
-        },
-        {
-            "name": "corpora annotation"
-        }
-    ],
-    "title": [
-        "KPWr annotation guidelines - named entities"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0b8c31d6-0e17-58cb-8d58-1eb0fb7696b8.json b/oaitestdata/clarin-oai_dc/SET_1/json/0b8c31d6-0e17-58cb-8d58-1eb0fb7696b8.json
deleted file mode 100644
index 836fbeab..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0b8c31d6-0e17-58cb-8d58-1eb0fb7696b8.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "University of West Bohemia, Department of Cybernetics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 9",
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1587",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1587"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1587",
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "University of West Bohemia, Department of Cybernetics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Tihelka, Daniel",
-        "Matou\u0161ek, Jind\u0159ich"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1587;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;English TTS speech corpus of air traffic (pilot) messages - Czech accent;Matou\u0161ek, Jind\u0159ich;Tihelka, Daniel;speech corpus;text-to-speech (TTS);pitch-marks;The corpus contains recordings of male speaker, native in Czech, talking in English. The sentences that were read by the speaker originate in the domain of air traffic control (ATC), specifically the messages used by plane pilots during routine flight. The text in the corpus originates from the transcripts of the real recordings, part of which has been released in LINDAT/CLARIN (http://hdl.handle.net/11858/00-097C-0000-0001-CCA1-0), and individual phrases were selected by special algorithm described in J\u016fzov\u00e1, M. and Tihelka, D.: Minimum Text Corpus Selection for Limited Domain Speech Synthesis (DOI 10.1007/978-3-319-10816-2_48). The corpus was used to create a limited domain speech synthesis system capable of simulating a pilot communication with an ATC officer.;2015-12-11;corpus;http://hdl.handle.net/11234/1-1587;eng;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;application/zip;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain; charset=utf-8;downloadable_files_count: 9;University of West Bohemia, Department of Cybernetics;http://itblp.zcu.cz",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0b8c31d6-0e17-58cb-8d58-1eb0fb7696b8",
-    "notes": [
-        "The corpus contains recordings of male speaker, native in Czech, talking in English. The sentences that were read by the speaker originate in the domain of air traffic control (ATC), specifically the messages used by plane pilots during routine flight. The text in the corpus originates from the transcripts of the real recordings, part of which has been released in LINDAT/CLARIN (http://hdl.handle.net/11858/00-097C-0000-0001-CCA1-0), and individual phrases were selected by special algorithm described in J\u016fzov\u00e1, M. and Tihelka, D.: Minimum Text Corpus Selection for Limited Domain Speech Synthesis (DOI 10.1007/978-3-319-10816-2_48). The corpus was used to create a limited domain speech synthesis system capable of simulating a pilot communication with an ATC officer."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1587"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech corpus"
-        },
-        {
-            "name": "text-to-speech TTS"
-        },
-        {
-            "name": "pitch-marks"
-        }
-    ],
-    "title": [
-        "English TTS speech corpus of air traffic (pilot) messages - Czech accent"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0b9bf343-f726-5807-aae1-e9330c91121c.json b/oaitestdata/clarin-oai_dc/SET_1/json/0b9bf343-f726-5807-aae1-e9330c91121c.json
deleted file mode 100644
index ae88efea..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0b9bf343-f726-5807-aae1-e9330c91121c.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish",
-        "Bulgarian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/52",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/52"
-    ],
-    "PID": "http://hdl.handle.net/10794/52",
-    "PublicationTimestamp": "2015-04-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/52;2017-10-31T12:20:08Z;hdl_10794_1;hdl_10794_2;ASPAC \u2013 Swedish-Bulgarian (2017-10-16);ASPAC \u2013 svenska-bulgariska (2017-10-16);n/a, n/a;ASPAC;Parallel;Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.;Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat.;2015-04-16;corpus;http://hdl.handle.net/10794/52;swe;bul;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/octet-stream;application/gzip;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/aspacsvbg",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0b9bf343-f726-5807-aae1-e9330c91121c",
-    "notes": [
-        "Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.",
-        "Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/52"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ASPAC"
-        },
-        {
-            "name": "Parallel"
-        }
-    ],
-    "title": [
-        "ASPAC \u2013 Swedish-Bulgarian (2017-10-16)",
-        "ASPAC \u2013 svenska-bulgariska (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0bba79cc-1065-5b36-86e6-afacb7264e4e.json b/oaitestdata/clarin-oai_dc/SET_1/json/0bba79cc-1065-5b36-86e6-afacb7264e4e.json
deleted file mode 100644
index d4e811f3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0bba79cc-1065-5b36-86e6-afacb7264e4e.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2851",
-    "MetadataAccess": [
-        "oai:ota:oucs:2851"
-    ],
-    "PublicationTimestamp": "1758-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1758"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2851;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2851.xml;An answer to The craftsman;Swift, Jonathan, 1667-1745;1758;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0bba79cc-1065-5b36-86e6-afacb7264e4e",
-    "oai_identifier": [
-        "oai:ota:oucs:2851"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An answer to The craftsman"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2851.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0bd72c12-0c84-54c9-882c-d1f0a0416217.json b/oaitestdata/clarin-oai_dc/SET_1/json/0bd72c12-0c84-54c9-882c-d1f0a0416217.json
deleted file mode 100644
index 0b6cc30a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0bd72c12-0c84-54c9-882c-d1f0a0416217.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5505",
-    "MetadataAccess": [
-        "oai:ota:oucs:5505"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Paine, Thomas, 1737-1809."
-    ],
-    "fulltext": "oai:ota:oucs:5505;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5505.xml;The decline & fall of the English system of finance: By Thomas Paine, author of Common sense, American crisis, Age of reason, &c. [One line of quotation];Paine, Thomas, 1737-1809.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0bd72c12-0c84-54c9-882c-d1f0a0416217",
-    "oai_identifier": [
-        "oai:ota:oucs:5505"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The decline & fall of the English system of finance: By Thomas Paine, author of Common sense, American crisis, Age of reason, &c. [One line of quotation]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5505.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0bf34588-94e4-57d3-aaf9-185c613851ff.json b/oaitestdata/clarin-oai_dc/SET_1/json/0bf34588-94e4-57d3-aaf9-185c613851ff.json
deleted file mode 100644
index e186897a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0bf34588-94e4-57d3-aaf9-185c613851ff.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Delbecque, Nicole"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 54 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0465",
-    "MetadataAccess": [
-        "oai:ota:oucs:0465"
-    ],
-    "PublicationTimestamp": "1969-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1969"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Wymark, Olwen"
-    ],
-    "fulltext": "oai:ota:oucs:0465;2018-07-27T14:11:30Z;http://ota.ox.ac.uk/headers/0465.xml;Stay where you are / Olwen Wymark;Wymark, Olwen;1969;text_and_corpus_linguistics;English drama -- 20th century;eng;Oxford Text Archive, University of Oxford;Delbecque, Nicole;(1 file : ca. 54 KB);Text;Plays;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0bf34588-94e4-57d3-aaf9-185c613851ff",
-    "oai_identifier": [
-        "oai:ota:oucs:0465"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- th century"
-        }
-    ],
-    "title": [
-        "Stay where you are / Olwen Wymark"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0465.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0c2652d4-d91c-54d0-9be8-936cbce60c55.json b/oaitestdata/clarin-oai_dc/SET_1/json/0c2652d4-d91c-54d0-9be8-936cbce60c55.json
deleted file mode 100644
index 1073d88e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0c2652d4-d91c-54d0-9be8-936cbce60c55.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/41",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/41"
-    ],
-    "PID": "http://hdl.handle.net/10794/41",
-    "PublicationTimestamp": "2012-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/41;2017-10-27T12:28:26Z;hdl_10794_1;hdl_10794_2;Swedish FrameNet (2017-10-16);Svenskt frasn\u00e4t (2017-10-16);n/a, n/a;Swedish;Swedish FrameNet++.;Svenskt FrasN\u00e4t++.;2012-05-30;lexicalConceptualResource;http://hdl.handle.net/10794/41;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/swefn",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0c2652d4-d91c-54d0-9be8-936cbce60c55",
-    "notes": [
-        "Swedish FrameNet++.",
-        "Svenskt FrasN\u00e4t++."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/41"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        }
-    ],
-    "title": [
-        "Swedish FrameNet (2017-10-16)",
-        "Svenskt frasn\u00e4t (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0c2c9e92-38db-558b-b464-69bd9dac6e2c.json b/oaitestdata/clarin-oai_dc/SET_1/json/0c2c9e92-38db-558b-b464-69bd9dac6e2c.json
deleted file mode 100644
index 08ca2767..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0c2c9e92-38db-558b-b464-69bd9dac6e2c.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Ibtikarat team"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/xml",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Arabic"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1946",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1946"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1946",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Ibtikarat team"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)",
-        "http://creativecommons.org/licenses/by-nc/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Namly, Driss"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1946;2017-02-06T11:05:37Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;\"Al wassit\" LMF Arabic dictionary;Namly, Driss;lexical semantics;An LMF conformant XML-based file containing the electronic version of al wassit dictionary. An Arabic monolingual dictionary accomplished by the Academy of the Arabic Language in Cairo;2015;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1946;ara;Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0);http://creativecommons.org/licenses/by-nc/4.0/;PUB;text/xml;text/plain; charset=utf-8;downloadable_files_count: 1;Ibtikarat team;http://arabic.emi.ac.ma/ibtikarat/?q=Resources",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0c2c9e92-38db-558b-b464-69bd9dac6e2c",
-    "notes": [
-        "An LMF conformant XML-based file containing the electronic version of al wassit dictionary. An Arabic monolingual dictionary accomplished by the Academy of the Arabic Language in Cairo"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1946"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "lexical semantics"
-        }
-    ],
-    "title": [
-        "\"Al wassit\" LMF Arabic dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0c3282ef-4298-5942-86f4-7001201fccef.json b/oaitestdata/clarin-oai_dc/SET_1/json/0c3282ef-4298-5942-86f4-7001201fccef.json
deleted file mode 100644
index 015391a9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0c3282ef-4298-5942-86f4-7001201fccef.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3512",
-    "MetadataAccess": [
-        "oai:ota:oucs:3512"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dudley, H. Bate, Sir (Henry Bate), 1745-1824."
-    ],
-    "fulltext": "oai:ota:oucs:3512;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3512.xml;Cursory remarks on Mr. Gilbert's last bill: for the better relief, and employment of the poor, &c. and his considerations thereon: in a letter to that gentleman. By H. Bate Dudley, ...;Dudley, H. Bate, Sir (Henry Bate), 1745-1824.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0c3282ef-4298-5942-86f4-7001201fccef",
-    "oai_identifier": [
-        "oai:ota:oucs:3512"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Cursory remarks on Mr. Gilbert's last bill: for the better relief, and employment of the poor, &c. and his considerations thereon: in a letter to that gentleman. By H. Bate Dudley, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3512.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0c3a314f-9724-5cb3-8f47-388709dd3c31.json b/oaitestdata/clarin-oai_dc/SET_1/json/0c3a314f-9724-5cb3-8f47-388709dd3c31.json
deleted file mode 100644
index ff5ae232..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0c3a314f-9724-5cb3-8f47-388709dd3c31.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Francis, Louis"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(9 files : total of ca. 388 KB)"
-    ],
-    "Language": [
-        "English",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2420",
-    "MetadataAccess": [
-        "oai:ota:oucs:2420"
-    ],
-    "PublicationTimestamp": "1997-06-01T11:59:59Z",
-    "PublicationYear": [
-        "1997"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Commentaries"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Horace"
-    ],
-    "fulltext": "oai:ota:oucs:2420;2018-06-18T12:25:58Z;http://ota.ox.ac.uk/headers/2420.xml;Carmina. Liber 4. English & Latin;Verba ambigua Horati : the enigma of Book IV;Horace;1997-06-01;text_and_corpus_linguistics;Academic dissertations;Latin poetry;Translations;eng;lat;This text seeks to explore Book IV of Horace's Odes not as isolated works of adulatory verse, but as a collection of subliminal vignettes on Roman society in the early days of the Principate. That they were written as individual items over a period of time, ranging from 13 BC. to 8 BC., is not disputed. That they were really intended by Horace as a complete entity in their own right is the primary argument of this work and is supported by a full translation, commentary and analysis of the Latin text in which the order of the odes has been reconstituted ;Oxford Text Archive, University of Oxford;Francis, Louis;Francis, Louis;(9 files : total of ca. 388 KB);Text;Commentaries;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0c3a314f-9724-5cb3-8f47-388709dd3c31",
-    "notes": [
-        "This text seeks to explore Book IV of Horace's Odes not as isolated works of adulatory verse, but as a collection of subliminal vignettes on Roman society in the early days of the Principate. That they were written as individual items over a period of time, ranging from 13 BC. to 8 BC., is not disputed. That they were really intended by Horace as a complete entity in their own right is the primary argument of this work and is supported by a full translation, commentary and analysis of the Latin text in which the order of the odes has been reconstituted "
-    ],
-    "oai_identifier": [
-        "oai:ota:oucs:2420"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Academic dissertations"
-        },
-        {
-            "name": "Latin poetry"
-        },
-        {
-            "name": "Translations"
-        }
-    ],
-    "title": [
-        "Carmina. Liber 4. English & Latin",
-        "Verba ambigua Horati : the enigma of Book IV"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2420.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0c4114d4-2d2f-5ca1-8399-ffcde32b94d0.json b/oaitestdata/clarin-oai_dc/SET_1/json/0c4114d4-2d2f-5ca1-8399-ffcde32b94d0.json
deleted file mode 100644
index 3b4dc382..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0c4114d4-2d2f-5ca1-8399-ffcde32b94d0.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish",
-        "Belarusian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/77",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/77"
-    ],
-    "PID": "http://hdl.handle.net/10794/77",
-    "PublicationTimestamp": "2015-04-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/77;2017-11-01T07:57:16Z;hdl_10794_1;hdl_10794_2;ASPAC \u2013 Swedish-Belarusian (2017-10-16);ASPAC \u2013 svenska-vitryska (2017-10-16);n/a, n/a;ASPAC;Parallel;Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.;Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat.;2015-04-16;corpus;http://hdl.handle.net/10794/77;swe;bel;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/octet-stream;application/gzip;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/aspacsvbe",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0c4114d4-2d2f-5ca1-8399-ffcde32b94d0",
-    "notes": [
-        "Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.",
-        "Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/77"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ASPAC"
-        },
-        {
-            "name": "Parallel"
-        }
-    ],
-    "title": [
-        "ASPAC \u2013 Swedish-Belarusian (2017-10-16)",
-        "ASPAC \u2013 svenska-vitryska (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0c730a8f-c319-5fc7-be7b-a0d5716ed400.json b/oaitestdata/clarin-oai_dc/SET_1/json/0c730a8f-c319-5fc7-be7b-a0d5716ed400.json
deleted file mode 100644
index bf0f9e4b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0c730a8f-c319-5fc7-be7b-a0d5716ed400.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Institute of Czech Language, Czech Academy of Sciences",
-        "Masaryk University, NLP Centre"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Czech",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-8BD2-2",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-8BD2-2"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-8BD2-2",
-    "PublicationTimestamp": "2009-01-14T11:59:59Z",
-    "PublicationYear": [
-        "2009"
-    ],
-    "Publisher": [
-        "Institute of Czech Language, Czech Academy of Sciences",
-        "Masaryk University, NLP Centre"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Svobodov\u00e1, Ivana",
-        "Pro\u0161ek, Martin",
-        "Kopeck\u00fd, Jakub",
-        "M\u017eourkov\u00e1, Hana",
-        "Pala, Karel",
-        "Smejkalov\u00e1, Kamila",
-        "Pravdov\u00e1, Mark\u00e9ta",
-        "\u010cern\u00e1, Anna",
-        "Hlav\u00e1\u010dkov\u00e1, Dana",
-        "Chrom\u00fd, Jan",
-        "Bene\u0161, Martin",
-        "Uhl\u00ed\u0159ov\u00e1, Ludmila",
-        "Prok\u0161ov\u00e1, Hana",
-        "Kone\u010dn\u00e1, Hana",
-        "\u0160merk, Pavel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-8BD2-2;2016-04-06T16:39:49Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;The Internet Language Reference Book;\u0160merk, Pavel;Pravdov\u00e1, Mark\u00e9ta;Bene\u0161, Martin;\u010cern\u00e1, Anna;Hlav\u00e1\u010dkov\u00e1, Dana;Chrom\u00fd, Jan;Kone\u010dn\u00e1, Hana;Kopeck\u00fd, Jakub;M\u017eourkov\u00e1, Hana;Pala, Karel;Prok\u0161ov\u00e1, Hana;Pro\u0161ek, Martin;Smejkalov\u00e1, Kamila;Svobodov\u00e1, Ivana;Uhl\u00ed\u0159ov\u00e1, Ludmila;literature;The ILRB has been created by two cooperating teams - by the team of the Institute of Czech Language, Czech Academy of Sciences and the team of the NLP Centre at the Faculty of Informatics, Masaryk University (2004-2008).\r\n\r\nThe tool consists of two sections: wordlist and reference (explanatory) one. Comments and remarks are welcome and should be send to the address poradna@ujc.cas.cz.\r\n\r\n1. Wordlist section\r\nIt contains more than 60 000 dictionary entries and is based on the glossary of the School Rules of Czech Orthography, the Dictionary of the Literary Czech and selected entries from the New Dictionary of Words of Foreign Origin and Dictionary of Neologisms. The entries typically include information that is asked about frequently by the users. Also inflectional forms of the particular words forms are offered in the form of tables thanks to the morphological analyzer ajka created at the Faculty of Informatics, MU. The dictionary part is linked to the explanatory one through the hypertext links.\r\n\r\n2. Reference section\r\nIt comprises the explanations about linguistic phenomena described in the Rules of Czech Orthography and contemporary Czech grammars, frequently and repeatedly asked by the users turning to the Linguistic Advisory Line in the Institute of Czech Language. In the offered explanations some typical spelling problems are dealt with including the appropriate recommendations. The ILRB is regularly updated and completed, new expressions are added and made more precise.;2009-01-14;toolService;http://hdl.handle.net/11858/00-097C-0000-0023-8BD2-2;ces;eng;downloadable_files_count: 0;Institute of Czech Language, Czech Academy of Sciences;Masaryk University, NLP Centre;http://prirucka.ujc.cas.cz/l/en/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0c730a8f-c319-5fc7-be7b-a0d5716ed400",
-    "notes": [
-        "The ILRB has been created by two cooperating teams - by the team of the Institute of Czech Language, Czech Academy of Sciences and the team of the NLP Centre at the Faculty of Informatics, Masaryk University (2004-2008).\r\n\r\nThe tool consists of two sections: wordlist and reference (explanatory) one. Comments and remarks are welcome and should be send to the address poradna@ujc.cas.cz.\r\n\r\n1. Wordlist section\r\nIt contains more than 60 000 dictionary entries and is based on the glossary of the School Rules of Czech Orthography, the Dictionary of the Literary Czech and selected entries from the New Dictionary of Words of Foreign Origin and Dictionary of Neologisms. The entries typically include information that is asked about frequently by the users. Also inflectional forms of the particular words forms are offered in the form of tables thanks to the morphological analyzer ajka created at the Faculty of Informatics, MU. The dictionary part is linked to the explanatory one through the hypertext links.\r\n\r\n2. Reference section\r\nIt comprises the explanations about linguistic phenomena described in the Rules of Czech Orthography and contemporary Czech grammars, frequently and repeatedly asked by the users turning to the Linguistic Advisory Line in the Institute of Czech Language. In the offered explanations some typical spelling problems are dealt with including the appropriate recommendations. The ILRB is regularly updated and completed, new expressions are added and made more precise."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-8BD2-2"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "literature"
-        }
-    ],
-    "title": [
-        "The Internet Language Reference Book"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0cacbd20-9672-57fa-b8a7-be346aa609c9.json b/oaitestdata/clarin-oai_dc/SET_1/json/0cacbd20-9672-57fa-b8a7-be346aa609c9.json
deleted file mode 100644
index 2d45e641..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0cacbd20-9672-57fa-b8a7-be346aa609c9.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/279",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/279"
-    ],
-    "PID": "http://hdl.handle.net/11321/279",
-    "PublicationTimestamp": "2016-06-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "K\u0119dzia, Pawe\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/279;2016-06-03T12:49:51Z;hdl_11321_3;hdl_11321_4;Plumper;K\u0119dzia, Pawe\u0142;Ontology mapping;Mapping;SUMO;plWordNet;Ontology mapper. Mapping plWordNet onto SUMO ontology.;2016-06-01;toolService;http://hdl.handle.net/11321/279;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 1;Wroc\u0142aw University of Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0cacbd20-9672-57fa-b8a7-be346aa609c9",
-    "notes": [
-        "Ontology mapper. Mapping plWordNet onto SUMO ontology."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/279"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Ontology mapping"
-        },
-        {
-            "name": "Mapping"
-        },
-        {
-            "name": "SUMO"
-        },
-        {
-            "name": "plWordNet"
-        }
-    ],
-    "title": [
-        "Plumper"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0cb4d421-8923-55b9-9370-f2ba0c137546.json b/oaitestdata/clarin-oai_dc/SET_1/json/0cb4d421-8923-55b9-9370-f2ba0c137546.json
deleted file mode 100644
index 97d021c6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0cb4d421-8923-55b9-9370-f2ba0c137546.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 286 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1602",
-    "MetadataAccess": [
-        "oai:ota:oucs:1602"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Jonson, Ben, 1573?-1637"
-    ],
-    "fulltext": "oai:ota:oucs:1602;2018-02-16T10:42:06Z;http://ota.ox.ac.uk/headers/1602.xml;Bartholomew Fair;Jonson, Ben, 1573?-1637;default: 1976-01-01;text_and_corpus_linguistics;Plays -- England -- 17th century;Comedies -- England -- 17th century;eng;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 286 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0cb4d421-8923-55b9-9370-f2ba0c137546",
-    "oai_identifier": [
-        "oai:ota:oucs:1602"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        },
-        {
-            "name": "Comedies -- England -- th century"
-        }
-    ],
-    "title": [
-        "Bartholomew Fair"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1602.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0cde3969-e144-58f3-955a-b4e01771c820.json b/oaitestdata/clarin-oai_dc/SET_1/json/0cde3969-e144-58f3-955a-b4e01771c820.json
deleted file mode 100644
index 94cd29e0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0cde3969-e144-58f3-955a-b4e01771c820.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "Contributor": [
-        "Marimon, Montserrat"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-536",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-536"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-536",
-    "PublicationTimestamp": "2008-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2008"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-536;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Spanish Resource Grammar;Marimon, Montserrat;HPSG like grammar for the analysis of  Spanish, implemented in LKB;2008;languageDescription;http://hdl.handle.net/11372/LRT-536;spa;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra;http://logon.iula.upf.edu/logon",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0cde3969-e144-58f3-955a-b4e01771c820",
-    "notes": [
-        "HPSG like grammar for the analysis of  Spanish, implemented in LKB"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-536"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Spanish Resource Grammar"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0ce583fe-43f0-51a8-b2fc-6fc24f961ab8.json b/oaitestdata/clarin-oai_dc/SET_1/json/0ce583fe-43f0-51a8-b2fc-6fc24f961ab8.json
deleted file mode 100644
index d4c676ea..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0ce583fe-43f0-51a8-b2fc-6fc24f961ab8.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Hart, Michael"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 189 KB)",
-        "text/plain"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1499",
-    "MetadataAccess": [
-        "oai:ota:oucs:1499"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Longfellow, Henry Wadsworth, 1807-1882"
-    ],
-    "fulltext": "oai:ota:oucs:1499;2018-02-16T10:42:06Z;http://ota.ox.ac.uk/headers/1499.xml;The song of Hiawatha / Henry W. Longfellow;Longfellow, Henry Wadsworth, 1807-1882;text_and_corpus_linguistics;American poetry -- 19th century;Oxford Text Archive, University of Oxford;Hart, Michael;text/plain;(1 file : ca. 189 KB);Text;Poems;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0ce583fe-43f0-51a8-b2fc-6fc24f961ab8",
-    "oai_identifier": [
-        "oai:ota:oucs:1499"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "American poetry -- th century"
-        }
-    ],
-    "title": [
-        "The song of Hiawatha / Henry W. Longfellow"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1499.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0cf6672c-a306-5dc4-a066-9722531e7ad6.json b/oaitestdata/clarin-oai_dc/SET_1/json/0cf6672c-a306-5dc4-a066-9722531e7ad6.json
deleted file mode 100644
index e705d4a7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0cf6672c-a306-5dc4-a066-9722531e7ad6.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 88.8 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2219",
-    "MetadataAccess": [
-        "oai:ota:oucs:2219"
-    ],
-    "PublicationTimestamp": "1874-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1874"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Periodicals"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:2219;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/2219.xml;International review (New York, N.Y. : 1874);The International review (1);1874-1883;text_and_corpus_linguistics;Periodicals -- United States -- 19th century;eng;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 88.8 KB);Text;Periodicals;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0cf6672c-a306-5dc4-a066-9722531e7ad6",
-    "oai_identifier": [
-        "oai:ota:oucs:2219"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Periodicals -- United States -- th century"
-        }
-    ],
-    "title": [
-        "International review (New York, N.Y. : 1874)",
-        "The International review (1)"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2219.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0d1aeab8-793f-510e-bf4b-1d325875b385.json b/oaitestdata/clarin-oai_dc/SET_1/json/0d1aeab8-793f-510e-bf4b-1d325875b385.json
deleted file mode 100644
index 46f768c9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0d1aeab8-793f-510e-bf4b-1d325875b385.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Craig, Hugh"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 199 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1450",
-    "MetadataAccess": [
-        "oai:ota:oucs:1450"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Shakespeare, William, 1564-1616"
-    ],
-    "fulltext": "oai:ota:oucs:1450;2018-02-16T10:42:06Z;http://ota.ox.ac.uk/headers/1450.xml;Othello : [1622] / William Shakespeare;Shakespeare, William, 1564-1616;text_and_corpus_linguistics;English drama -- Early modern and Elizabethan, 1500-1600;Oxford Text Archive, University of Oxford;Craig, Hugh;(1 file : ca. 199 KB);Text;Plays;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0d1aeab8-793f-510e-bf4b-1d325875b385",
-    "oai_identifier": [
-        "oai:ota:oucs:1450"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- Early modern Elizabethan"
-        }
-    ],
-    "title": [
-        "Othello : [1622] / William Shakespeare"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1450.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0d31044d-dfbc-56a1-bb02-d353f12fb9fb.json b/oaitestdata/clarin-oai_dc/SET_1/json/0d31044d-dfbc-56a1-bb02-d353f12fb9fb.json
deleted file mode 100644
index d8b3c6d9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0d31044d-dfbc-56a1-bb02-d353f12fb9fb.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, Dept. of Swedish Language, G\u00f6teborg University"
-    ],
-    "Contributor": [
-        "Forsberg, Markus",
-        "Borin, Lars"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-296",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-296"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-296",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, Dept. of Swedish Language, G\u00f6teborg University"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Sweden"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-296;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;SALDO;Borin, Lars;Forsberg, Markus;SALDO (Swedish Associative Thesaurus version 2) is an extensive lexicon resource for modern Swedish written language created for the purpose of language technology research and for the development of language technology applications. SALDO may be viewed as a basic lexical resouce for a Swedish BLARK. SALDO builds on Swedish Associative Thesaurus, a semantic lexicon for Swedish.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-296;swe;downloadable_files_count: 0;Sweden;Spr\u00e5kbanken, Dept. of Swedish Language, G\u00f6teborg University;http://spraakbanken.gu.se/resource/saldo",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0d31044d-dfbc-56a1-bb02-d353f12fb9fb",
-    "notes": [
-        "SALDO (Swedish Associative Thesaurus version 2) is an extensive lexicon resource for modern Swedish written language created for the purpose of language technology research and for the development of language technology applications. SALDO may be viewed as a basic lexical resouce for a Swedish BLARK. SALDO builds on Swedish Associative Thesaurus, a semantic lexicon for Swedish."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-296"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "SALDO"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0d4131f4-2018-57e5-84e2-7473bb8b23d1.json b/oaitestdata/clarin-oai_dc/SET_1/json/0d4131f4-2018-57e5-84e2-7473bb8b23d1.json
deleted file mode 100644
index 85a15004..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0d4131f4-2018-57e5-84e2-7473bb8b23d1.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "The Research Institute for the Languages of Finland"
-    ],
-    "Contributor": [
-        "Lehtinen, Outi"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-842",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-842"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-842",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "The Research Institute for the Languages of Finland"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Finland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-842;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Lexicon of the Finno-Swedish place name endigs (= Namnledslexicon);Lehtinen, Outi;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-842;swe;downloadable_files_count: 0;Finland;The Research Institute for the Languages of Finland;http://kaino.kotus.fi/svenska/ledlex/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0d4131f4-2018-57e5-84e2-7473bb8b23d1",
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-842"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Lexicon of the Finno-Swedish place name endigs (= Namnledslexicon)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0d61cd92-0fec-583b-8b96-b2cc2788bc76.json b/oaitestdata/clarin-oai_dc/SET_1/json/0d61cd92-0fec-583b-8b96-b2cc2788bc76.json
deleted file mode 100644
index 34f71e2b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0d61cd92-0fec-583b-8b96-b2cc2788bc76.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5473",
-    "MetadataAccess": [
-        "oai:ota:oucs:5473"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Burney, Fanny, 1752-1840."
-    ],
-    "fulltext": "oai:ota:oucs:5473;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5473.xml;Evelina: or, a young lady's entrance into the world. ... [pt.1];Burney, Fanny, 1752-1840.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0d61cd92-0fec-583b-8b96-b2cc2788bc76",
-    "oai_identifier": [
-        "oai:ota:oucs:5473"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Evelina: or, a young lady's entrance into the world. ... [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5473.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0d67983a-4efd-5620-9663-7a642ebb5bc7.json b/oaitestdata/clarin-oai_dc/SET_1/json/0d67983a-4efd-5620-9663-7a642ebb5bc7.json
deleted file mode 100644
index 76607ed9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0d67983a-4efd-5620-9663-7a642ebb5bc7.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Tilde"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-319",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-319"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-319",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Tilde"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Latvia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-319;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Tilde English-Latvian SMT system;English-Latvian factored SMT system trained on different parallel texts;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-319;eng;downloadable_files_count: 0;Latvia;Tilde;http://translate.tilde.com",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0d67983a-4efd-5620-9663-7a642ebb5bc7",
-    "notes": [
-        "English-Latvian factored SMT system trained on different parallel texts"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-319"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Tilde English-Latvian SMT system"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0d816c04-61df-5f1f-85bb-19cd956d383f.json b/oaitestdata/clarin-oai_dc/SET_1/json/0d816c04-61df-5f1f-85bb-19cd956d383f.json
deleted file mode 100644
index 8a998192..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0d816c04-61df-5f1f-85bb-19cd956d383f.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Instytucja: Uniwersytet..."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "downloadable_files_count: 10",
-        "application/vnd.oasis.opendocument.text",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/412",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/412"
-    ],
-    "PID": "http://hdl.handle.net/11321/412",
-    "PublicationTimestamp": "2017-06-29T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Instytucja: Uniwersytet..."
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Drugie nazwisko, Drugie imi\u0119",
-        "Nazwisko, Imi\u0119"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/412;2017-06-29T07:52:46Z;hdl_11321_3;hdl_11321_4;Korpus_Testowy;Drugie nazwisko, Drugie imi\u0119;Nazwisko, Imi\u0119;warsztaty;test;korpus;Korpus testowy - warsztaty II LSHC;2017-06-29;corpus;http://hdl.handle.net/11321/412;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;text/plain;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;application/vnd.oasis.opendocument.text;text/plain;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;downloadable_files_count: 10;Instytucja: Uniwersytet...",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0d816c04-61df-5f1f-85bb-19cd956d383f",
-    "notes": [
-        "Korpus testowy - warsztaty II LSHC"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/412"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "warsztaty"
-        },
-        {
-            "name": "test"
-        },
-        {
-            "name": "korpus"
-        }
-    ],
-    "title": [
-        "Korpus_Testowy"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0d830808-5ecc-5e56-88eb-069ce6649f12.json b/oaitestdata/clarin-oai_dc/SET_1/json/0d830808-5ecc-5e56-88eb-069ce6649f12.json
deleted file mode 100644
index 03d6f881..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0d830808-5ecc-5e56-88eb-069ce6649f12.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 3"
-    ],
-    "Language": [
-        "English",
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1466",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1466"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1466",
-    "PublicationTimestamp": "2015-01-29T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/610516"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU General Public License, version 2",
-        "http://www.gnu.org/licenses/gpl-2.0.html",
-        "PUB"
-    ],
-    "author": [
-        "Rosa, Rudolf"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1466;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Depfix: Automatic Post-editing of SMT;Rosa, Rudolf;machine translation;post-editing;Treex;morphology;parsing;Depfix, a tool for Automatic Post-editing of SMT.\r\nSee the project website for more information.;2015-01-29;toolService;http://hdl.handle.net/11234/1-1466;eng;ces;info:eu-repo/grantAgreement/EC/FP7/610516;GNU General Public License, version 2;http://www.gnu.org/licenses/gpl-2.0.html;PUB;application/x-gzip;application/x-gzip;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 3;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/depfix",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0d830808-5ecc-5e56-88eb-069ce6649f12",
-    "notes": [
-        "Depfix, a tool for Automatic Post-editing of SMT.\r\nSee the project website for more information."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1466"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "post-editing"
-        },
-        {
-            "name": "Treex"
-        },
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "parsing"
-        }
-    ],
-    "title": [
-        "Depfix: Automatic Post-editing of SMT"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0d996050-64b3-5246-aa8f-e2509c1ab4af.json b/oaitestdata/clarin-oai_dc/SET_1/json/0d996050-64b3-5246-aa8f-e2509c1ab4af.json
deleted file mode 100644
index 79f41bcc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0d996050-64b3-5246-aa8f-e2509c1ab4af.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Franciszka Cezarego"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229077",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229077"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D03-6",
-    "PublicationTimestamp": "1645-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1645"
-    ],
-    "Publisher": [
-        "Drukarnia Franciszka Cezarego"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/229077",
-        "oai:jbc.bj.uj.edu.pl:publication:240720"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1601/1700"
-    ],
-    "TempCoverageBegin": 50506804799,
-    "TempCoverageEnd": 50506804799,
-    "TemporalCoverage": " point in time : 1601-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1601-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1601-07-01T11:59:59Z",
-    "author": [
-        "Przetocki, Jacek (ca 1599-ca 1655)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229077;2019-03-01T12:44:29Z;Brzeg nieprze\u017cytey Wieczno\u015bci, Do ktorego Staro\u017cytny \u0141ab\u0119\u0107, ostatniego prawie Dvnina z Modlyszowic, [...] P. Stanis\u0142awa Modliszowskiego, Hrabie Skrzynskiego. I. K. M. Dworzanina, P\u0142ywai\u0105c fortunnie po \u00dferokim morzu Krolestwa Polskiego przez lat 521 [...] Szcz\u0119\u015bliwie Roku 1645. 21. Aprilis dop\u0142yn\u0105\u0142, y wy\u00dfed\u0142 30. Maij. Roku tego\u017c, na l\u0105d Grobowy, w Konieckim Ko\u015bciele Farnym;Przetocki, Jacek (ca 1599-ca 1655);starodruki 17\u00a0w.;Szczawi\u0144ski, Jan Szymon (16..-16..). Adr. ded.;Drukarnia Franciszka Cezarego;1645;starodruk;application/xml;clarind-uds:poldilemma-229077;hdl:11858/00-246C-0000-0023-8D03-6;Biblioteka Jagiello\u0144ska, BJ St. Dr. 311352 I;pol;http://jbc.bj.uj.edu.pl/Content/229077;oai:jbc.bj.uj.edu.pl:publication:240720;1601/1700;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0d996050-64b3-5246-aa8f-e2509c1ab4af",
-    "notes": [
-        "Szczawi\u0144ski, Jan Szymon (16..-16..). Adr. ded."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229077"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Brzeg nieprze\u017cytey Wieczno\u015bci, Do ktorego Staro\u017cytny \u0141ab\u0119\u0107, ostatniego prawie Dvnina z Modlyszowic, [...] P. Stanis\u0142awa Modliszowskiego, Hrabie Skrzynskiego. I. K. M. Dworzanina, P\u0142ywai\u0105c fortunnie po \u00dferokim morzu Krolestwa Polskiego przez lat 521 [...] Szcz\u0119\u015bliwie Roku 1645. 21. Aprilis dop\u0142yn\u0105\u0142, y wy\u00dfed\u0142 30. Maij. Roku tego\u017c, na l\u0105d Grobowy, w Konieckim Ko\u015bciele Farnym"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0dabb0d2-641e-5797-92ab-8ed1d272ff61.json b/oaitestdata/clarin-oai_dc/SET_1/json/0dabb0d2-641e-5797-92ab-8ed1d272ff61.json
deleted file mode 100644
index 3a48a39e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0dabb0d2-641e-5797-92ab-8ed1d272ff61.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=7bb3d93a5e6611e2a2aa782bcb07413528d5704eaab2438288d07c528748fd16",
-    "MetadataAccess": [
-        "7bb3d93a5e6611e2a2aa782bcb07413528d5704eaab2438288d07c528748fd16"
-    ],
-    "PublicationTimestamp": "2013-01-31T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "7bb3d93a5e6611e2a2aa782bcb07413528d5704eaab2438288d07c528748fd16;2018-11-15T16:40:02Z;toolService;toolService:service;MLSS Sentence Splitter Web Service;The MLSS Sentence Splitter is a web service tool, which takes text as input and outputs the identified sentences surrounded by tags. The tool was tuned for Maltese. The download for this resource only contains the narrative description in a Word file.\n\nThe web service has one methods which can be invoked:\n- String tagSentences(String text)\n\nThe method takes a string as input, that being the text to be split into sentences, and returns another string of that text tagged.\n\nThe format of the output is as follows:\n<sentence> sentence_text </sentence> \n;2013-01-31",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0dabb0d2-641e-5797-92ab-8ed1d272ff61",
-    "notes": [
-        "The MLSS Sentence Splitter is a web service tool, which takes text as input and outputs the identified sentences surrounded by tags. The tool was tuned for Maltese. The download for this resource only contains the narrative description in a Word file.\n\nThe web service has one methods which can be invoked:\n- String tagSentences(String text)\n\nThe method takes a string as input, that being the text to be split into sentences, and returns another string of that text tagged.\n\nThe format of the output is as follows:\n<sentence> sentence_text </sentence> \n"
-    ],
-    "oai_identifier": [
-        "7bb3d93a5e6611e2a2aa782bcb07413528d5704eaab2438288d07c528748fd16"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:service"
-    ],
-    "state": "active",
-    "title": [
-        "MLSS Sentence Splitter Web Service"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0db5e7ed-53c9-5e22-8d71-56b118c4f02f.json b/oaitestdata/clarin-oai_dc/SET_1/json/0db5e7ed-53c9-5e22-8d71-56b118c4f02f.json
deleted file mode 100644
index 3a6010d3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0db5e7ed-53c9-5e22-8d71-56b118c4f02f.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contributor": [
-        "Asmussen, J\u00f6rg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Danish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-269",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-269"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-269",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Denmark"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-269;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;DanNet;Asmussen, J\u00f6rg;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-269;dan;downloadable_files_count: 0;Denmark;http://ordnet.dk/korpusdk",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0db5e7ed-53c9-5e22-8d71-56b118c4f02f",
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-269"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "DanNet"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0db82c17-97a4-5f25-8dfa-9ef2214937b3.json b/oaitestdata/clarin-oai_dc/SET_1/json/0db82c17-97a4-5f25-8dfa-9ef2214937b3.json
deleted file mode 100644
index da29a656..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0db82c17-97a4-5f25-8dfa-9ef2214937b3.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/116",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/116"
-    ],
-    "PID": "http://hdl.handle.net/10794/116",
-    "PublicationTimestamp": "2012-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/116;2017-11-01T16:38:16Z;hdl_10794_1;hdl_10794_2;Bonnier novels II (1980/81) (2017-03-17);Bonniersromaner II (1980/81) (2017-03-17);n/a, n/a;Swedish;Novels;A corpus of 60 Bonnier novels from 1980-81. The material is sentence scrambled.;En korpus av 60 Bonniersromaner fr\u00e5n 1980-81. Materialet \u00e4r meningsomkastat.;2012-05-30;corpus;http://hdl.handle.net/10794/116;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/romii",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0db82c17-97a4-5f25-8dfa-9ef2214937b3",
-    "notes": [
-        "A corpus of 60 Bonnier novels from 1980-81. The material is sentence scrambled.",
-        "En korpus av 60 Bonniersromaner fr\u00e5n 1980-81. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/116"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Novels"
-        }
-    ],
-    "title": [
-        "Bonnier novels II (1980/81) (2017-03-17)",
-        "Bonniersromaner II (1980/81) (2017-03-17)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0dc44ff4-0168-5fb9-85ce-cef73ba26704.json b/oaitestdata/clarin-oai_dc/SET_1/json/0dc44ff4-0168-5fb9-85ce-cef73ba26704.json
deleted file mode 100644
index 7984f16e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0dc44ff4-0168-5fb9-85ce-cef73ba26704.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "University of Southampton and Newcastle University"
-    ],
-    "Contributor": [
-        "Myles, Florence",
-        "Mitchell, Rosamond"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "French"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-877",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-877"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-877",
-    "PublicationTimestamp": "2008-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2008"
-    ],
-    "Publisher": [
-        "University of Southampton and Newcastle University"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-877;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;French learner language oral corpora;Myles, Florence;Mitchell, Rosamond;Seven French L2 corpora. Digital sound files and related transcripts formatted using CHILDES software. The database currently contains over 4000 files (sound files, transcripts and morphosyntactically tagged transcripts). .;2008;corpus;http://hdl.handle.net/11372/LRT-877;fra;downloadable_files_count: 0;United Kingdom;University of Southampton and Newcastle University;http://www.flloc.soton.ac.uk/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0dc44ff4-0168-5fb9-85ce-cef73ba26704",
-    "notes": [
-        "Seven French L2 corpora. Digital sound files and related transcripts formatted using CHILDES software. The database currently contains over 4000 files (sound files, transcripts and morphosyntactically tagged transcripts). ."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-877"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "French learner language oral corpora"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0dcb2e91-e7eb-57a6-adf1-56732031840e.json b/oaitestdata/clarin-oai_dc/SET_1/json/0dcb2e91-e7eb-57a6-adf1-56732031840e.json
deleted file mode 100644
index d8b04b71..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0dcb2e91-e7eb-57a6-adf1-56732031840e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3582",
-    "MetadataAccess": [
-        "oai:ota:oucs:3582"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Griffith, Mrs. (Elizabeth), 1720?-1793."
-    ],
-    "fulltext": "oai:ota:oucs:3582;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3582.xml;The double mistake: A comedy. As it is performed at the Theatre-Royal in Covent-Garden.;Griffith, Mrs. (Elizabeth), 1720?-1793.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0dcb2e91-e7eb-57a6-adf1-56732031840e",
-    "oai_identifier": [
-        "oai:ota:oucs:3582"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The double mistake: A comedy. As it is performed at the Theatre-Royal in Covent-Garden."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3582.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0dce1970-e04a-5d42-8dd5-3b20b426d488.json b/oaitestdata/clarin-oai_dc/SET_1/json/0dce1970-e04a-5d42-8dd5-3b20b426d488.json
deleted file mode 100644
index c40a3f57..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0dce1970-e04a-5d42-8dd5-3b20b426d488.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3069",
-    "MetadataAccess": [
-        "oai:ota:oucs:3069"
-    ],
-    "PublicationTimestamp": "1827-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1827"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Blake, William, 1757-1827"
-    ],
-    "fulltext": "oai:ota:oucs:3069;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3069.xml;Poems. Selections;Selected poems;Blake, William, 1757-1827;not after: 1827;text_and_corpus_linguistics;Poems -- Great Britain;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0dce1970-e04a-5d42-8dd5-3b20b426d488",
-    "oai_identifier": [
-        "oai:ota:oucs:3069"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- Great Britain"
-        }
-    ],
-    "title": [
-        "Poems. Selections",
-        "Selected poems"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3069.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0dda13d9-8296-59b3-b578-21b8f600b226.json b/oaitestdata/clarin-oai_dc/SET_1/json/0dda13d9-8296-59b3-b578-21b8f600b226.json
deleted file mode 100644
index 1b288993..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0dda13d9-8296-59b3-b578-21b8f600b226.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=a7dda836059911e7a2aa782bcb07413520ba00f85fe74d2589f5da3162302103",
-    "MetadataAccess": [
-        "a7dda836059911e7a2aa782bcb07413520ba00f85fe74d2589f5da3162302103"
-    ],
-    "PublicationTimestamp": "2017-03-10T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "fulltext": "a7dda836059911e7a2aa782bcb07413520ba00f85fe74d2589f5da3162302103;2018-11-15T16:40:32Z;toolService;toolService:tool;Dutch to English Machine translation module;Technical Description:\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/Pilot1_technical_description.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/TechnicalDescriptionPilot2_D2.7.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2016/11/TechnicalDescriptionPilot3_D2.10.pdf;2017-03-10",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0dda13d9-8296-59b3-b578-21b8f600b226",
-    "notes": [
-        "Technical Description:\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/Pilot1_technical_description.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/TechnicalDescriptionPilot2_D2.7.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2016/11/TechnicalDescriptionPilot3_D2.10.pdf"
-    ],
-    "oai_identifier": [
-        "a7dda836059911e7a2aa782bcb07413520ba00f85fe74d2589f5da3162302103"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "Dutch to English Machine translation module"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0e1ce4b6-9536-5114-bc9a-f44dfa30219f.json b/oaitestdata/clarin-oai_dc/SET_1/json/0e1ce4b6-9536-5114-bc9a-f44dfa30219f.json
deleted file mode 100644
index 502772f5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0e1ce4b6-9536-5114-bc9a-f44dfa30219f.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "Contributor": [
-        "Yzaguirre, Llu\u00eds de"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Catalan"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-305",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-305"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-305",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-305;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;SOLC;Yzaguirre, Llu\u00eds de;An orthologic server for Catalan. A query system for the orthologic dictionary which allows making searches using dialectal and pragmatic variables.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-305;cat;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra;http://retoc.iula.upf.edu/SOLC/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0e1ce4b6-9536-5114-bc9a-f44dfa30219f",
-    "notes": [
-        "An orthologic server for Catalan. A query system for the orthologic dictionary which allows making searches using dialectal and pragmatic variables."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-305"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "SOLC"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0e248e3a-b9b9-5987-882a-b0ffb0fec148.json b/oaitestdata/clarin-oai_dc/SET_1/json/0e248e3a-b9b9-5987-882a-b0ffb0fec148.json
deleted file mode 100644
index 629779fe..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0e248e3a-b9b9-5987-882a-b0ffb0fec148.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Jan Wieczorek"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/632",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/632"
-    ],
-    "PID": "http://hdl.handle.net/11321/632",
-    "PublicationTimestamp": "2019-03-18T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Jan Wieczorek"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Wieczorek, Jan"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/632;2019-03-18T11:18:18Z;hdl_11321_3;hdl_11321_478;poznan lista 2;Wieczorek, Jan;pr\u00f3bka;pr\u00f3ba 2;2019-03-18;corpus;http://hdl.handle.net/11321/632;pol;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;application/vnd.openxmlformats-officedocument.wordprocessingml.document;downloadable_files_count: 1;Jan Wieczorek",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0e248e3a-b9b9-5987-882a-b0ffb0fec148",
-    "notes": [
-        "pr\u00f3ba 2"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/632"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_478"
-    ],
-    "state": "active",
-    "tags": [],
-    "title": [
-        "poznan lista 2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0e45aedc-1282-58de-8802-00d57242a806.json b/oaitestdata/clarin-oai_dc/SET_1/json/0e45aedc-1282-58de-8802-00d57242a806.json
deleted file mode 100644
index 40a03b0c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0e45aedc-1282-58de-8802-00d57242a806.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=34e4d1d6cf5e11e1a404080027e73ea2296e3e6e58204292a7dbc1b0aae74f85",
-    "MetadataAccess": [
-        "34e4d1d6cf5e11e1a404080027e73ea2296e3e6e58204292a7dbc1b0aae74f85"
-    ],
-    "PublicationTimestamp": "2012-07-16T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "fulltext": "34e4d1d6cf5e11e1a404080027e73ea2296e3e6e58204292a7dbc1b0aae74f85;2019-02-27T12:09:06Z;lexicalConceptualResource;lexicalConceptualResource:lexicon;Ontology for the area of Nanoscience and Nanotechnology;The Ontology for the area of Nanoscience and Nanotechnology (Ontologia para a \u00c3\u00a1rea de Nanoci\u00c3\u00aancia e Nanotecnologia) is constituted by 511 terms of this field of knowledge. It was extracted from a corpus collected from the Web, with a total of 2.570.792 words;2012-07-16",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0e45aedc-1282-58de-8802-00d57242a806",
-    "notes": [
-        "The Ontology for the area of Nanoscience and Nanotechnology (Ontologia para a \u00c3\u00a1rea de Nanoci\u00c3\u00aancia e Nanotecnologia) is constituted by 511 terms of this field of knowledge. It was extracted from a corpus collected from the Web, with a total of 2.570.792 words"
-    ],
-    "oai_identifier": [
-        "34e4d1d6cf5e11e1a404080027e73ea2296e3e6e58204292a7dbc1b0aae74f85"
-    ],
-    "oai_set": [
-        "lexicalConceptualResource",
-        "lexicalConceptualResource:lexicon"
-    ],
-    "state": "active",
-    "title": [
-        "Ontology for the area of Nanoscience and Nanotechnology"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0e4a9b68-338e-5f13-ac5b-054b8ada915f.json b/oaitestdata/clarin-oai_dc/SET_1/json/0e4a9b68-338e-5f13-ac5b-054b8ada915f.json
deleted file mode 100644
index 2f1039d1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0e4a9b68-338e-5f13-ac5b-054b8ada915f.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3357",
-    "MetadataAccess": [
-        "oai:ota:oucs:3357"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hill, Aaron, 1685-1750."
-    ],
-    "fulltext": "oai:ota:oucs:3357;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3357.xml;Athelwold: a tragedy. As it is acted at the Theatre-Royal in Drury-Lane, by His Majesty's servants.;Hill, Aaron, 1685-1750.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0e4a9b68-338e-5f13-ac5b-054b8ada915f",
-    "oai_identifier": [
-        "oai:ota:oucs:3357"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Athelwold: a tragedy. As it is acted at the Theatre-Royal in Drury-Lane, by His Majesty's servants."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3357.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0e686ab6-11bd-5d2d-a144-e54b47709031.json b/oaitestdata/clarin-oai_dc/SET_1/json/0e686ab6-11bd-5d2d-a144-e54b47709031.json
deleted file mode 100644
index b2d261d8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0e686ab6-11bd-5d2d-a144-e54b47709031.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Arts, University of Ljubljana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1026",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1026"
-    ],
-    "PID": "http://hdl.handle.net/11356/1026",
-    "PublicationTimestamp": "2015-05-07T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Faculty of Arts, University of Ljubljana"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "https://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Fi\u0161er, Darja"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1026;2017-01-20T13:58:56Z;hdl_11356_1023;hdl_11356_1024;Semantic lexicon of Slovene sloWNet 3.1;Fi\u0161er, Darja;semantic lexicon;synsets;synonyms;wordnet;semantic description;sloWNet is the Slovene WordNet developed in the expand approach: it contains the complete Princeton WordNet 3.0 and over 70,000 Slovene literals. These literals have been added automatically using different types of existing resources, such as bilingual dictionaries, parallel corpora and Wikipedia. Using the sloWTool and sloWCrowd platforms, 33,000 literals have been subsequently hand-validated.;2015-05-07;lexicalConceptualResource;http://hdl.handle.net/11356/1026;slv;eng;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);https://creativecommons.org/licenses/by-sa/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Faculty of Arts, University of Ljubljana;http://lojze.lugos.si/darja/research/slownet/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0e686ab6-11bd-5d2d-a144-e54b47709031",
-    "notes": [
-        "sloWNet is the Slovene WordNet developed in the expand approach: it contains the complete Princeton WordNet 3.0 and over 70,000 Slovene literals. These literals have been added automatically using different types of existing resources, such as bilingual dictionaries, parallel corpora and Wikipedia. Using the sloWTool and sloWCrowd platforms, 33,000 literals have been subsequently hand-validated."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1026"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "semantic lexicon"
-        },
-        {
-            "name": "synsets"
-        },
-        {
-            "name": "synonyms"
-        },
-        {
-            "name": "wordnet"
-        },
-        {
-            "name": "semantic description"
-        }
-    ],
-    "title": [
-        "Semantic lexicon of Slovene sloWNet 3.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0e6bd07c-77d7-5a93-9410-26e17381363b.json b/oaitestdata/clarin-oai_dc/SET_1/json/0e6bd07c-77d7-5a93-9410-26e17381363b.json
deleted file mode 100644
index a93d8700..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0e6bd07c-77d7-5a93-9410-26e17381363b.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "application/x-xz",
-        "downloadable_files_count: 4"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0015-A780-9",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0015-A780-9"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0015-A780-9",
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-1673"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Haji\u010d, Jan",
-        "Hlav\u00e1\u010dov\u00e1, Jaroslava"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0015-A780-9;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;MorfFlex CZ;Haji\u010d, Jan;Hlav\u00e1\u010dov\u00e1, Jaroslava;morphological dictionary;morphology;Czech;Czech morphological dictionary developed originally by Jan Haji\u010d as a spelling checker and lemmatization dictionary. Currently it contains full morphological information for each covered wordform, as well as some derivational, semantic and named entity information.;2013;lexicalConceptualResource;http://hdl.handle.net/11858/00-097C-0000-0015-A780-9;ces;http://hdl.handle.net/11234/1-1673;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/x-xz;application/x-xz;application/x-gzip;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/morfflex",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0e6bd07c-77d7-5a93-9410-26e17381363b",
-    "notes": [
-        "Czech morphological dictionary developed originally by Jan Haji\u010d as a spelling checker and lemmatization dictionary. Currently it contains full morphological information for each covered wordform, as well as some derivational, semantic and named entity information."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0015-A780-9"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphological dictionary"
-        },
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "Czech"
-        }
-    ],
-    "title": [
-        "MorfFlex CZ"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0e8d1766-7129-5e3b-b892-8f4c7a5c6043.json b/oaitestdata/clarin-oai_dc/SET_1/json/0e8d1766-7129-5e3b-b892-8f4c7a5c6043.json
deleted file mode 100644
index 547914cf..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0e8d1766-7129-5e3b-b892-8f4c7a5c6043.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-942",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-942"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-942",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-942;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Old High German;ca. 700.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-942;deu;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#ahd",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0e8d1766-7129-5e3b-b892-8f4c7a5c6043",
-    "notes": [
-        "ca. 700.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-942"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Old High German"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0e982efb-c743-5a7f-b317-e2ec6b6aa69e.json b/oaitestdata/clarin-oai_dc/SET_1/json/0e982efb-c743-5a7f-b317-e2ec6b6aa69e.json
deleted file mode 100644
index 69c83d4c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0e982efb-c743-5a7f-b317-e2ec6b6aa69e.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Bell, Timothy C."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(0 files : total of ca. 0 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1250",
-    "MetadataAccess": [
-        "oai:ota:oucs:1250"
-    ],
-    "PublicationYear": [
-        "unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Anthologies"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:1250;2018-03-06T16:09:15Z;http://ota.ox.ac.uk/headers/1250.xml;Calgary compression corpus;unknown;text_and_corpus_linguistics;Anthologies -- Canada -- 20th century;Linguistic analysis (Linguistics);eng;Oxford Text Archive, University of Oxford;Bell, Timothy C.;(0 files : total of ca. 0 KB);Text;Anthologies;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0e982efb-c743-5a7f-b317-e2ec6b6aa69e",
-    "oai_identifier": [
-        "oai:ota:oucs:1250"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Anthologies -- Canada -- th century"
-        },
-        {
-            "name": "Linguistic analysis Linguistics"
-        }
-    ],
-    "title": [
-        "Calgary compression corpus"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1250.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0ea02679-7507-59f2-9cea-5f8536da9d97.json b/oaitestdata/clarin-oai_dc/SET_1/json/0ea02679-7507-59f2-9cea-5f8536da9d97.json
deleted file mode 100644
index 6128f0c2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0ea02679-7507-59f2-9cea-5f8536da9d97.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "Contributor": [
-        "Mihalcea, Rada"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English",
-        "Romanian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-493",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-493"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-493",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Romania"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-493;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Romanian-English dictionary;Mihalcea, Rada;38,000 entries, XML;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-493;eng;ron;downloadable_files_count: 0;Romania;http://lit.csci.unt.edu/%7Erada/downloads/RoNLP/R.E.tralex",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0ea02679-7507-59f2-9cea-5f8536da9d97",
-    "notes": [
-        "38,000 entries, XML"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-493"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Romanian-English dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0ec2d4a4-2ec8-50e6-b471-c7c761b2c5ff.json b/oaitestdata/clarin-oai_dc/SET_1/json/0ec2d4a4-2ec8-50e6-b471-c7c761b2c5ff.json
deleted file mode 100644
index 7cebdc28..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0ec2d4a4-2ec8-50e6-b471-c7c761b2c5ff.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 267 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2180",
-    "MetadataAccess": [
-        "oai:ota:oucs:2180"
-    ],
-    "PublicationTimestamp": "1740-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1740"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Devotional literature"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Law, William, 1686-1761"
-    ],
-    "fulltext": "oai:ota:oucs:2180;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/2180.xml;An appeal to all that doubt, or disbelieve the truths of the Gospel : whether they be Deists, Arians, Socinians, or nominal Christians, in which the true grounds and reasons of the whole Christian faith and life are plainly and fully demonstrated, to which are added, some animadversions upon Dr. Trapp's late reply / William Law;Law, William, 1686-1761;1740;text_and_corpus_linguistics;Theology -- Miscellaneous Christian texts -- English;Oxford Text Archive, University of Oxford;Triggs, Jeffery;text/sgml;(1 file : ca. 267 KB);Text;Devotional literature;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0ec2d4a4-2ec8-50e6-b471-c7c761b2c5ff",
-    "oai_identifier": [
-        "oai:ota:oucs:2180"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Theology -- Miscellaneous Christian texts -- English"
-        }
-    ],
-    "title": [
-        "An appeal to all that doubt, or disbelieve the truths of the Gospel : whether they be Deists, Arians, Socinians, or nominal Christians, in which the true grounds and reasons of the whole Christian faith and life are plainly and fully demonstrated, to which are added, some animadversions upon Dr. Trapp's late reply / William Law"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2180.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0ec6e3fe-bab4-5eca-9880-8632e501d332.json b/oaitestdata/clarin-oai_dc/SET_1/json/0ec6e3fe-bab4-5eca-9880-8632e501d332.json
deleted file mode 100644
index a083f89d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0ec6e3fe-bab4-5eca-9880-8632e501d332.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Royster, Paul"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 294 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1815",
-    "MetadataAccess": [
-        "oai:ota:oucs:1815"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Politics"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Jefferson, Thomas, 1743-1826"
-    ],
-    "fulltext": "oai:ota:oucs:1815;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1815.xml;Miscellany / Thomas Jefferson;Jefferson, Thomas, 1743-1826;text_and_corpus_linguistics;American literature -- 18th century;Oxford Text Archive, University of Oxford;Royster, Paul;text/sgml;(1 file : ca. 294 KB);Text;Politics;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0ec6e3fe-bab4-5eca-9880-8632e501d332",
-    "oai_identifier": [
-        "oai:ota:oucs:1815"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "American literature -- th century"
-        }
-    ],
-    "title": [
-        "Miscellany / Thomas Jefferson"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1815.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0ec87ed4-48b1-51c0-a5ed-53c27a1c5eff.json b/oaitestdata/clarin-oai_dc/SET_1/json/0ec87ed4-48b1-51c0-a5ed-53c27a1c5eff.json
deleted file mode 100644
index ba2a3d96..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0ec87ed4-48b1-51c0-a5ed-53c27a1c5eff.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5580",
-    "MetadataAccess": [
-        "oai:ota:oucs:5580"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Warren, Martin, 1696-1735."
-    ],
-    "fulltext": "oai:ota:oucs:5580;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5580.xml;I have perused a pamphlet entitled, Some reasons why the practice of inoculation ought to be introduced into the town of Bury at present, and have been surprized to find this elaborate piece so little in substance,;Warren, Martin, 1696-1735.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0ec87ed4-48b1-51c0-a5ed-53c27a1c5eff",
-    "oai_identifier": [
-        "oai:ota:oucs:5580"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "I have perused a pamphlet entitled, Some reasons why the practice of inoculation ought to be introduced into the town of Bury at present, and have been surprized to find this elaborate piece so little in substance,"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5580.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0ef8b0e4-f021-59f9-a5b5-f3290b5cb36f.json b/oaitestdata/clarin-oai_dc/SET_1/json/0ef8b0e4-f021-59f9-a5b5-f3290b5cb36f.json
deleted file mode 100644
index d47f787a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0ef8b0e4-f021-59f9-a5b5-f3290b5cb36f.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "UG"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/vnd.oasis.opendocument.text",
-        "downloadable_files_count: 10",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/472",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/472"
-    ],
-    "PID": "http://hdl.handle.net/11321/472",
-    "PublicationTimestamp": "2018-05-19T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "UG"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "plWordNet",
-        "http://clarin-pl.eu/en/licenses/plwordnet-2/",
-        "PUB"
-    ],
-    "author": [
-        "Smith, Gary"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/472;2018-05-19T08:42:22Z;hdl_11321_3;hdl_11321_4;Warsztaty Clarin;Smith, Gary;Polish;HHHUY;2018-05-19;corpus;http://hdl.handle.net/11321/472;pol;plWordNet;http://clarin-pl.eu/en/licenses/plwordnet-2/;PUB;text/plain; charset=utf-8;application/vnd.oasis.opendocument.text;text/plain;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;downloadable_files_count: 10;UG",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0ef8b0e4-f021-59f9-a5b5-f3290b5cb36f",
-    "notes": [
-        "HHHUY"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/472"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Polish"
-        }
-    ],
-    "title": [
-        "Warsztaty Clarin"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0efc8c71-37d3-5602-8fd9-098c77f147aa.json b/oaitestdata/clarin-oai_dc/SET_1/json/0efc8c71-37d3-5602-8fd9-098c77f147aa.json
deleted file mode 100644
index cdea217a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0efc8c71-37d3-5602-8fd9-098c77f147aa.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Marzena Ga\u0142kowska"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/vnd.oasis.opendocument.text",
-        "downloadable_files_count: 10",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/489",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/489"
-    ],
-    "PID": "http://hdl.handle.net/11321/489",
-    "PublicationTimestamp": "2018-06-19T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Marzena Ga\u0142kowska"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Super Cool License",
-        "http://www.google.com",
-        "ACA"
-    ],
-    "author": [
-        "Ga\u0142kowska, Marzena"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/489;2018-06-19T11:18:23Z;hdl_11321_3;hdl_11321_4;Teksty warsztatowe;Ga\u0142kowska, Marzena;warsztaty;Korpus testowy w ramach warsztat\u00f3w Clarin-pl, Wroc\u0142aw 2018.;2018-06-19;corpus;http://hdl.handle.net/11321/489;pol;Super Cool License;http://www.google.com;ACA;text/plain; charset=utf-8;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.oasis.opendocument.text;text/plain;application/vnd.oasis.opendocument.text;text/plain;text/plain;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;downloadable_files_count: 10;Marzena Ga\u0142kowska",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0efc8c71-37d3-5602-8fd9-098c77f147aa",
-    "notes": [
-        "Korpus testowy w ramach warsztat\u00f3w Clarin-pl, Wroc\u0142aw 2018."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/489"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "warsztaty"
-        }
-    ],
-    "title": [
-        "Teksty warsztatowe"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0f16b1cd-752d-56e3-943c-7e0f0f1a08f5.json b/oaitestdata/clarin-oai_dc/SET_1/json/0f16b1cd-752d-56e3-943c-7e0f0f1a08f5.json
deleted file mode 100644
index 53204cd2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0f16b1cd-752d-56e3-943c-7e0f0f1a08f5.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3330",
-    "MetadataAccess": [
-        "oai:ota:oucs:3330"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Murphy, Arthur, 1727-1805."
-    ],
-    "fulltext": "oai:ota:oucs:3330;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3330.xml;Genuine memoirs of the life and adventures of the celebrated Miss Ann Elliot: Written by a gentleman intimately acquainted with her; ...;Murphy, Arthur, 1727-1805.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0f16b1cd-752d-56e3-943c-7e0f0f1a08f5",
-    "oai_identifier": [
-        "oai:ota:oucs:3330"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Genuine memoirs of the life and adventures of the celebrated Miss Ann Elliot: Written by a gentleman intimately acquainted with her; ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3330.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0f26b9c3-1534-59ee-8180-090dc2c454b5.json b/oaitestdata/clarin-oai_dc/SET_1/json/0f26b9c3-1534-59ee-8180-090dc2c454b5.json
deleted file mode 100644
index 46120f83..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0f26b9c3-1534-59ee-8180-090dc2c454b5.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Simov, Kiril"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Bulgarian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-193",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-193"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-193",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Bulgaria"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-193;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;BulTreeBank;Simov, Kiril;HPSG-based annotation including: constituent structure, dependency relations, named entities (classified as person, organisation, location or other names), coreferential relations. Annotation in XML;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-193;bul;downloadable_files_count: 0;Bulgaria;http://www.bultreebank.org/dpbtb/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0f26b9c3-1534-59ee-8180-090dc2c454b5",
-    "notes": [
-        "HPSG-based annotation including: constituent structure, dependency relations, named entities (classified as person, organisation, location or other names), coreferential relations. Annotation in XML"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-193"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "BulTreeBank"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0f2fe858-6192-5a58-ae2d-f1f9d4f7e03d.json b/oaitestdata/clarin-oai_dc/SET_1/json/0f2fe858-6192-5a58-ae2d-f1f9d4f7e03d.json
deleted file mode 100644
index 02a01196..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0f2fe858-6192-5a58-ae2d-f1f9d4f7e03d.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Charles University in Prague, \u00da\u010cJTK"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-3FBB-3",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-3FBB-3"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-3FBB-3",
-    "PublicationTimestamp": "2013-12-18T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Charles University in Prague, \u00da\u010cJTK"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11858/00-097C-0000-0019-89A0-9"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Gol\u00e1\u0148ov\u00e1, Hana",
-        "\u0160ebesta, Karel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-3FBB-3;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;AKCES 2 ver. 2;\u0160ebesta, Karel;Gol\u00e1\u0148ov\u00e1, Hana;youth language;classroom;language acquisition corpus;AKCES;Corpus AKCES 2 ver. 2 consists of full, unabridged trancripts of recordings of classes at Czech elementary and secondary schools (AKCES/CLAC - Czech Language Acquisition Corpora). It is the same data as the corpus \"Schola 2010\" (see the link for search), but all the proper names have been removed in order to protect the privacy of participants.;2013-12-18;corpus;http://hdl.handle.net/11858/00-097C-0000-0023-3FBB-3;ces;http://hdl.handle.net/11858/00-097C-0000-0019-89A0-9;Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0);http://creativecommons.org/licenses/by-nc-nd/3.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University in Prague, \u00da\u010cJTK;http://akces.ff.cuni.cz",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0f2fe858-6192-5a58-ae2d-f1f9d4f7e03d",
-    "notes": [
-        "Corpus AKCES 2 ver. 2 consists of full, unabridged trancripts of recordings of classes at Czech elementary and secondary schools (AKCES/CLAC - Czech Language Acquisition Corpora). It is the same data as the corpus \"Schola 2010\" (see the link for search), but all the proper names have been removed in order to protect the privacy of participants."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-3FBB-3"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "youth language"
-        },
-        {
-            "name": "classroom"
-        },
-        {
-            "name": "language acquisition corpus"
-        },
-        {
-            "name": "AKCES"
-        }
-    ],
-    "title": [
-        "AKCES 2 ver. 2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0f3a19f8-438e-53fb-8b2d-6c00300aa341.json b/oaitestdata/clarin-oai_dc/SET_1/json/0f3a19f8-438e-53fb-8b2d-6c00300aa341.json
deleted file mode 100644
index 32dd30bb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0f3a19f8-438e-53fb-8b2d-6c00300aa341.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Masaryk University, NLP Centre"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-D709-F",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-D709-F"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-D709-F",
-    "PublicationTimestamp": "2011-12-16T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Masaryk University, NLP Centre"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Gr\u00e1c, Marek"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-D709-F;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;BushBank;Gr\u00e1c, Marek;interannotator agreement;corpus;chunks;phrases;clauses;Czech corpus annotated for NP and clause chunks by 3-11 annotators (with average inter-annotator agreement at 88%). It consists of 10,000 sentences.;2011-12-16;corpus;http://hdl.handle.net/11858/00-097C-0000-0001-D709-F;ces;Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0);http://creativecommons.org/licenses/by-nc-nd/3.0/;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Masaryk University, NLP Centre",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0f3a19f8-438e-53fb-8b2d-6c00300aa341",
-    "notes": [
-        "Czech corpus annotated for NP and clause chunks by 3-11 annotators (with average inter-annotator agreement at 88%). It consists of 10,000 sentences."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-D709-F"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "interannotator agreement"
-        },
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "chunks"
-        },
-        {
-            "name": "phrases"
-        },
-        {
-            "name": "clauses"
-        }
-    ],
-    "title": [
-        "BushBank"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0f735727-eae3-5e11-b34b-b11d0bf3e5da.json b/oaitestdata/clarin-oai_dc/SET_1/json/0f735727-eae3-5e11-b34b-b11d0bf3e5da.json
deleted file mode 100644
index 7bbffc36..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0f735727-eae3-5e11-b34b-b11d0bf3e5da.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3864",
-    "MetadataAccess": [
-        "oai:ota:oucs:3864"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Centlivre, Susanna, 1667?-1723."
-    ],
-    "fulltext": "oai:ota:oucs:3864;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3864.xml;The Gotham election: a farce. By Mrs. Centlivre.;Centlivre, Susanna, 1667?-1723.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0f735727-eae3-5e11-b34b-b11d0bf3e5da",
-    "oai_identifier": [
-        "oai:ota:oucs:3864"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The Gotham election: a farce. By Mrs. Centlivre."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3864.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0f8b89ff-894b-50a2-b891-89baca2926d5.json b/oaitestdata/clarin-oai_dc/SET_1/json/0f8b89ff-894b-50a2-b891-89baca2926d5.json
deleted file mode 100644
index b9f64e23..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0f8b89ff-894b-50a2-b891-89baca2926d5.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "University of Heidelberg, Heidelberger Akademie der Wissenschaften"
-    ],
-    "Contributor": [
-        "Deutsch, Andreas"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-979",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-979"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-979",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Heidelberg, Heidelberger Akademie der Wissenschaften"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-979;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Deutsches Rechtsw\u00f6rterbuch (DRW);Deutsch, Andreas;Germanistik;A dictionary of old legal German. Includes words up until 1800. Historisches W\u00f6rterbuch; Dokumentation von Rechtsw\u00f6rtern sowie W\u00f6rtern mit rechtlichen Bez\u00fcgen (bis etwa 1800);2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-979;deu;downloadable_files_count: 0;Germany;University of Heidelberg, Heidelberger Akademie der Wissenschaften;http://drw-www.adw.uni-heidelberg.de/drw/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0f8b89ff-894b-50a2-b891-89baca2926d5",
-    "notes": [
-        "A dictionary of old legal German. Includes words up until 1800. Historisches W\u00f6rterbuch; Dokumentation von Rechtsw\u00f6rtern sowie W\u00f6rtern mit rechtlichen Bez\u00fcgen (bis etwa 1800)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-979"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Deutsches Rechtsw\u00f6rterbuch (DRW)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0f9a5715-4ab9-5998-8b38-19216bbf5fea.json b/oaitestdata/clarin-oai_dc/SET_1/json/0f9a5715-4ab9-5998-8b38-19216bbf5fea.json
deleted file mode 100644
index ccc379e0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0f9a5715-4ab9-5998-8b38-19216bbf5fea.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4666",
-    "MetadataAccess": [
-        "oai:ota:oucs:4666"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Mason, William, 1725-1797."
-    ],
-    "fulltext": "oai:ota:oucs:4666;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4666.xml;Mus\u00c3\u00a6us: a monody to the memory of Mr. Pope: in imitation of Milton's Lycidas.;Mason, William, 1725-1797.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0f9a5715-4ab9-5998-8b38-19216bbf5fea",
-    "oai_identifier": [
-        "oai:ota:oucs:4666"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Mus\u00c3\u00a6us: a monody to the memory of Mr. Pope: in imitation of Milton's Lycidas."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4666.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0fa7bab8-b1dc-5052-ab54-214b9d0924b7.json b/oaitestdata/clarin-oai_dc/SET_1/json/0fa7bab8-b1dc-5052-ab54-214b9d0924b7.json
deleted file mode 100644
index 17252b67..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0fa7bab8-b1dc-5052-ab54-214b9d0924b7.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "between 1 and 2 MB"
-    ],
-    "Language": [
-        "Latin",
-        "Old English (ca. 450-1100)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0512",
-    "MetadataAccess": [
-        "oai:ota:oucs:0512"
-    ],
-    "PublicationTimestamp": "1100-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1100"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Phrase books"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Unknown"
-    ],
-    "fulltext": "oai:ota:oucs:0512;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0512.xml; Early scholastic colloquies / compiled by David Howlett;Unknown;900-1100;text_and_corpus_linguistics;Phrase books -- England;lat;ang;Oxford Text Archive, University of Oxford;between 1 and 2 MB;Text;Phrase books;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0fa7bab8-b1dc-5052-ab54-214b9d0924b7",
-    "oai_identifier": [
-        "oai:ota:oucs:0512"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Phrase books -- England"
-        }
-    ],
-    "title": [
-        " Early scholastic colloquies / compiled by David Howlett"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0512.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0fbaf55f-e188-5bec-af0d-ca4d025c2bf0.json b/oaitestdata/clarin-oai_dc/SET_1/json/0fbaf55f-e188-5bec-af0d-ca4d025c2bf0.json
deleted file mode 100644
index f7fa6927..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0fbaf55f-e188-5bec-af0d-ca4d025c2bf0.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 303 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "Galician"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0656",
-    "MetadataAccess": [
-        "oai:ota:oucs:0656"
-    ],
-    "PublicationTimestamp": "1863-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1863"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Castro, Rosal\u00c3\u00ada de, 1837-1885"
-    ],
-    "fulltext": "oai:ota:oucs:0656;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0656.xml;Poes\u00c3\u00ada completa en galego / Rosal\u00c3\u00ada de Castro;Castro, Rosal\u00c3\u00ada de, 1837-1885;1863-1880;text_and_corpus_linguistics;Poems -- Spain -- 19th century;glg;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 303 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0fbaf55f-e188-5bec-af0d-ca4d025c2bf0",
-    "oai_identifier": [
-        "oai:ota:oucs:0656"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- Spain -- th century"
-        }
-    ],
-    "title": [
-        "Poes\u00c3\u00ada completa en galego / Rosal\u00c3\u00ada de Castro"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0656.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0fd66267-3575-5649-84a3-cf9de23fe5ec.json b/oaitestdata/clarin-oai_dc/SET_1/json/0fd66267-3575-5649-84a3-cf9de23fe5ec.json
deleted file mode 100644
index 3ae170ce..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0fd66267-3575-5649-84a3-cf9de23fe5ec.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "University of Gda\u0144sk"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/596",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/596"
-    ],
-    "PID": "http://hdl.handle.net/11321/596",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "University of Gda\u0144sk"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN-EULA-ACA-v1.0",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca",
-        "ACA"
-    ],
-    "author": [
-        "Moru\u015b, Micha\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/596;2018-08-21T12:35:46Z;hdl_11321_3;hdl_11321_4;ma\u0142esermony;Moru\u015b, Micha\u0142;english sermons;ma\u0142e sermony;2018;corpus;http://hdl.handle.net/11321/596;eng;CLARIN-EULA-ACA-v1.0;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca;ACA;text/plain; charset=utf-8;text/plain;downloadable_files_count: 1;University of Gda\u0144sk",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0fd66267-3575-5649-84a3-cf9de23fe5ec",
-    "notes": [
-        "ma\u0142e sermony"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/596"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "english sermons"
-        }
-    ],
-    "title": [
-        "ma\u0142esermony"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0fd68d7e-37ac-5f3f-a6e3-d4c3f701dd37.json b/oaitestdata/clarin-oai_dc/SET_1/json/0fd68d7e-37ac-5f3f-a6e3-d4c3f701dd37.json
deleted file mode 100644
index 473ac31d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0fd68d7e-37ac-5f3f-a6e3-d4c3f701dd37.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "English",
-        "Czech",
-        "Russian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1791",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1791"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1791",
-    "PublicationTimestamp": "2016-09-30T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CC-BY-NC-SA + LDC99T42",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/license-pcedt2",
-        "RES"
-    ],
-    "author": [
-        "Nov\u00e1k, Michal",
-        "Nedoluzhko, Anna",
-        "Schwarz (Khoroshkina), Anna"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1791;2018-07-02T22:05:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Prague Czech-English Dependency Treebank 2.0 - Russian translation;Nov\u00e1k, Michal;Nedoluzhko, Anna;Schwarz (Khoroshkina), Anna;multilingual;coreference;Prague Czech-English Dependency Treebank - Russian translation (PCEDT-R) is a project of translating a subset of Prague Czech-English Dependency Treebank 2.0 (PCEDT 2.0) to Russian and linguistically annotating the Russian translations with emphasis on coreference and cross-lingual alignment of coreferential expressions. Cross-lingual comparison of coreference means is currently the purpose that drives development of this corpus.\r\n\r\nThe current version 0.5 is a preliminary version, which contains (+ denotes new features):\r\n  * complete PCEDT 2.0 documents \"wsj_1900\"-\"wsj_1949\"\r\n  * Czech-English word alignment of coreferential expressions annotated manually mainly on the t-layer\r\n  + Russian translations of the original English sentences\r\n  + automatic tokenization, part-of-speech tagging and morphological analysis for Russian\r\n  + automatic word alignment between all Czech and Russian words\r\n  + manual alignment between Russian and the other two languages on possessive pronouns;2016-09-30;corpus;http://hdl.handle.net/11234/1-1791;eng;ces;rus;CC-BY-NC-SA + LDC99T42;https://lindat.mff.cuni.cz/repository/xmlui/page/license-pcedt2;RES;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0fd68d7e-37ac-5f3f-a6e3-d4c3f701dd37",
-    "notes": [
-        "Prague Czech-English Dependency Treebank - Russian translation (PCEDT-R) is a project of translating a subset of Prague Czech-English Dependency Treebank 2.0 (PCEDT 2.0) to Russian and linguistically annotating the Russian translations with emphasis on coreference and cross-lingual alignment of coreferential expressions. Cross-lingual comparison of coreference means is currently the purpose that drives development of this corpus.\r\n\r\nThe current version 0.5 is a preliminary version, which contains (+ denotes new features):\r\n  * complete PCEDT 2.0 documents \"wsj_1900\"-\"wsj_1949\"\r\n  * Czech-English word alignment of coreferential expressions annotated manually mainly on the t-layer\r\n  + Russian translations of the original English sentences\r\n  + automatic tokenization, part-of-speech tagging and morphological analysis for Russian\r\n  + automatic word alignment between all Czech and Russian words\r\n  + manual alignment between Russian and the other two languages on possessive pronouns"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1791"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "multilingual"
-        },
-        {
-            "name": "coreference"
-        }
-    ],
-    "title": [
-        "Prague Czech-English Dependency Treebank 2.0 - Russian translation"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0fddb2f8-85c7-530f-9013-889f1a7f6b47.json b/oaitestdata/clarin-oai_dc/SET_1/json/0fddb2f8-85c7-530f-9013-889f1a7f6b47.json
deleted file mode 100644
index 27e68081..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0fddb2f8-85c7-530f-9013-889f1a7f6b47.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4909",
-    "MetadataAccess": [
-        "oai:ota:oucs:4909"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Townley, James, 1714-1778."
-    ],
-    "fulltext": "oai:ota:oucs:4909;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4909.xml;A sermon preach'd before the Right Honourable the Lord Mayor the aldermen, and citizens of London, at the cathedral church of St. Paul, on Friday the twenty ninth day of May, 1741. ... By James Townley,;Townley, James, 1714-1778.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0fddb2f8-85c7-530f-9013-889f1a7f6b47",
-    "oai_identifier": [
-        "oai:ota:oucs:4909"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A sermon preach'd before the Right Honourable the Lord Mayor the aldermen, and citizens of London, at the cathedral church of St. Paul, on Friday the twenty ninth day of May, 1741. ... By James Townley,"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4909.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0fe0bd2e-3013-5114-be70-bfe77e81455e.json b/oaitestdata/clarin-oai_dc/SET_1/json/0fe0bd2e-3013-5114-be70-bfe77e81455e.json
deleted file mode 100644
index 86127d02..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0fe0bd2e-3013-5114-be70-bfe77e81455e.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 132 KB)"
-    ],
-    "Language": [
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0410",
-    "MetadataAccess": [
-        "oai:ota:oucs:0410"
-    ],
-    "PublicationYear": [
-        "0-79"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:0410;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0410.xml;Dipinti on amphorae from Rome and Pompeii from Corpus Inscriptionum Latinarum 4 and 15;0-79;text_and_corpus_linguistics;Memorials (Commemorative);Anthologies;lat;Oxford Text Archive, University of Oxford;(1 file : ca. 132 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0fe0bd2e-3013-5114-be70-bfe77e81455e",
-    "oai_identifier": [
-        "oai:ota:oucs:0410"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Memorials Commemorative"
-        },
-        {
-            "name": "Anthologies"
-        }
-    ],
-    "title": [
-        "Dipinti on amphorae from Rome and Pompeii from Corpus Inscriptionum Latinarum 4 and 15"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0410.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0ff4853e-d60d-5306-bb37-506057f7b88c.json b/oaitestdata/clarin-oai_dc/SET_1/json/0ff4853e-d60d-5306-bb37-506057f7b88c.json
deleted file mode 100644
index 1399cb5c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0ff4853e-d60d-5306-bb37-506057f7b88c.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology",
-        "University of Lodz"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/pdf"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/550",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/550"
-    ],
-    "PID": "http://hdl.handle.net/11321/550",
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology",
-        "University of Lodz"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0)",
-        "http://creativecommons.org/licenses/by-nc/3.0/",
-        "CC"
-    ],
-    "author": [
-        "P\u0119zik, Piotr"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/550;2018-07-23T11:55:15Z;hdl_11321_3;hdl_11321_4;HaskEN;P\u0119zik, Piotr;collocation dictionary;phraseological database;HaskEN is an English phraseological database designed for language professionals including linguists, language teachers, lexicographers, language materials developers and translators. Query results can be visualised and exported as spreadsheets.;2014;toolService;http://hdl.handle.net/11321/550;eng;Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0);http://creativecommons.org/licenses/by-nc/3.0/;CC;text/plain; charset=utf-8;application/pdf;downloadable_files_count: 1;University of Lodz;Wroc\u0142aw University of Technology;http://pelcra.pl/hask_en/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0ff4853e-d60d-5306-bb37-506057f7b88c",
-    "notes": [
-        "HaskEN is an English phraseological database designed for language professionals including linguists, language teachers, lexicographers, language materials developers and translators. Query results can be visualised and exported as spreadsheets."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/550"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "collocation dictionary"
-        },
-        {
-            "name": "phraseological database"
-        }
-    ],
-    "title": [
-        "HaskEN"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/0ff62514-9586-53f8-911b-e64ec0c2e019.json b/oaitestdata/clarin-oai_dc/SET_1/json/0ff62514-9586-53f8-911b-e64ec0c2e019.json
deleted file mode 100644
index 3baf5940..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/0ff62514-9586-53f8-911b-e64ec0c2e019.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3649",
-    "MetadataAccess": [
-        "oai:ota:oucs:3649"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Defoe, Daniel, 1661?-1731."
-    ],
-    "fulltext": "oai:ota:oucs:3649;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3649.xml;An enquiry into the danger and consequences of a war with the Dutch;Defoe, Daniel, 1661?-1731.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0ff62514-9586-53f8-911b-e64ec0c2e019",
-    "oai_identifier": [
-        "oai:ota:oucs:3649"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An enquiry into the danger and consequences of a war with the Dutch"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3649.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/10033f96-55a1-523f-8418-37c1d29ea489.json b/oaitestdata/clarin-oai_dc/SET_1/json/10033f96-55a1-523f-8418-37c1d29ea489.json
deleted file mode 100644
index 86a7807f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/10033f96-55a1-523f-8418-37c1d29ea489.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 7.98 KB)"
-    ],
-    "Language": [
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0328",
-    "MetadataAccess": [
-        "oai:ota:oucs:0328"
-    ],
-    "PublicationYear": [
-        "81 BCE-43 BCE"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Cicero, Marcus Tullius"
-    ],
-    "fulltext": "oai:ota:oucs:0328;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0328.xml;Ad Octavianum;Cicero, Marcus Tullius;81 BCE-43 BCE;text_and_corpus_linguistics;Letters;lat;Oxford Text Archive, University of Oxford;(1 file : ca. 7.98 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "10033f96-55a1-523f-8418-37c1d29ea489",
-    "oai_identifier": [
-        "oai:ota:oucs:0328"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Letters"
-        }
-    ],
-    "title": [
-        "Ad Octavianum"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0328.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/101b9217-6355-5229-93f0-cfef245ac941.json b/oaitestdata/clarin-oai_dc/SET_1/json/101b9217-6355-5229-93f0-cfef245ac941.json
deleted file mode 100644
index 5e4c3454..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/101b9217-6355-5229-93f0-cfef245ac941.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2703",
-    "MetadataAccess": [
-        "oai:ota:oucs:2703"
-    ],
-    "PublicationTimestamp": "1727-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1727"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2703;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2703.xml;A proposal for correcting, improving and ascertaining the English tongue;Swift, Jonathan, 1667-1745;1727;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "101b9217-6355-5229-93f0-cfef245ac941",
-    "oai_identifier": [
-        "oai:ota:oucs:2703"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A proposal for correcting, improving and ascertaining the English tongue"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2703.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/101bcf3a-dd78-53ab-bd87-ad072e01d85c.json b/oaitestdata/clarin-oai_dc/SET_1/json/101bcf3a-dd78-53ab-bd87-ad072e01d85c.json
deleted file mode 100644
index c83376ac..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/101bcf3a-dd78-53ab-bd87-ad072e01d85c.json
+++ /dev/null
@@ -1,91 +0,0 @@
-{
-    "Contributor": [
-        "Jukka Tyrkk\u00f6",
-        "Hendrik De Smet",
-        "Susanne Flach",
-        "Hans-J\u00fcrgen Diller"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=\"\"\"oai:fedora.clarin-d.uni-saarland.de:clarind-uds:clmet-31\"\"\"",
-    "MetadataAccess": [
-        "\"\"\"oai:fedora.clarin-d.uni-saarland.de:clarind-uds:clmet-31\"\"\""
-    ],
-    "PID": "http://hdl.handle.net/21.11119/0000-0002-43F3-0",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "RelatedIdentifier": [
-        "Diller, H., De Smet, H., Tyrkk\u00f6, J. (2011). A European database of descriptors of English electronic texts. The European English Messenger 19, 21-35."
-    ],
-    "ResourceType": [
-        "Collection",
-        "Written Corpus",
-        "Diachronic Corpus"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "Great Britain",
-        "Ireland",
-        "1710/1920"
-    ],
-    "TemporalCoverage": [
-        "Great Britain",
-        "Ireland",
-        "1710/1920"
-    ],
-    "author": [
-        "KU Leuven"
-    ],
-    "fulltext": "\"\"\"oai:fedora.clarin-d.uni-saarland.de:clarind-uds:clmet-31\"\"\";2018-10-12T13:41:23Z;The Corpus of Late Modern English Texts, version 3.1;KU Leuven;Late Modern English;corpus linguistics;language change;written language;genre classification;CLMET3.1 is a principled collection of public domain texts drawn from various online archiving projects. In total, the corpus contains some 34 million words of running text. It incorporates CLMET, CLMETEV, and CLMET3.0, and has been compiled following roughly the same principles, that is:\n\n    The corpus covers the period 1710-1920, divided into three 70-year sub-periods.\n    The texts making up the corpus have all been written by British and Irish authors who are native speakers of English.\n    The corpus never contains more than three texts by the same author.\n    The texts within each sub-period have been written by authors born within a correspondingly restricted sub-period. \n\nHowever, compared to the earlier versions, it comes with a number of important improvements (in addition to being substantially bigger):\n\n    CLMET3.1 comes with an explicit genre classification.\n    It is approximately genre-balanced.\n    It is part-of-speech tagged.\n    The corpus files have standardized text headers containing descriptive meta-data.\n    For each text, explicit information is provided on text provenance.\n    The corpus architecture allows subsequent expansions. \n    The corpus is CWB compatible.;Hendrik De Smet;Susanne Flach;Hans-J\u00fcrgen Diller;Jukka Tyrkk\u00f6;2018;Collection;Written Corpus;Diachronic Corpus;application/zip;clarind-uds:clmet-31;hdl:21.11119/0000-0002-43F3-0;See corpus files;eng;Diller, H., De Smet, H., Tyrkk\u00f6, J. (2011). A European database of descriptors of English electronic texts. The European English Messenger 19, 21-35.;Great Britain;Ireland;1710/1920;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "101bcf3a-dd78-53ab-bd87-ad072e01d85c",
-    "notes": [
-        "CLMET3.1 is a principled collection of public domain texts drawn from various online archiving projects. In total, the corpus contains some 34 million words of running text. It incorporates CLMET, CLMETEV, and CLMET3.0, and has been compiled following roughly the same principles, that is:\n\n    The corpus covers the period 1710-1920, divided into three 70-year sub-periods.\n    The texts making up the corpus have all been written by British and Irish authors who are native speakers of English.\n    The corpus never contains more than three texts by the same author.\n    The texts within each sub-period have been written by authors born within a correspondingly restricted sub-period. \n\nHowever, compared to the earlier versions, it comes with a number of important improvements (in addition to being substantially bigger):\n\n    CLMET3.1 comes with an explicit genre classification.\n    It is approximately genre-balanced.\n    It is part-of-speech tagged.\n    The corpus files have standardized text headers containing descriptive meta-data.\n    For each text, explicit information is provided on text provenance.\n    The corpus architecture allows subsequent expansions. \n    The corpus is CWB compatible."
-    ],
-    "oai_identifier": [
-        "\"\"\"oai:fedora.clarin-d.uni-saarland.de:clarind-uds:clmet-31\"\"\""
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Late Modern English"
-        },
-        {
-            "name": "corpus linguistics"
-        },
-        {
-            "name": "language change"
-        },
-        {
-            "name": "written language"
-        },
-        {
-            "name": "genre classification"
-        }
-    ],
-    "title": [
-        "The Corpus of Late Modern English Texts, version 3.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/102ad385-2b22-56c7-967f-1ab3dd77420c.json b/oaitestdata/clarin-oai_dc/SET_1/json/102ad385-2b22-56c7-967f-1ab3dd77420c.json
deleted file mode 100644
index 3942559e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/102ad385-2b22-56c7-967f-1ab3dd77420c.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Iluzjon"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/220",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/220"
-    ],
-    "PID": "http://hdl.handle.net/11321/220",
-    "PublicationTimestamp": "2015-06-18T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Iluzjon"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0)",
-        "http://creativecommons.org/licenses/by-nc/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Mularczyk, Andrzej"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/220;2015-06-18T18:50:27Z;hdl_11321_3;hdl_11321_4;Sami swoi;Mularczyk, Andrzej;Film fabularny.;2015-06-18;corpus;http://hdl.handle.net/11321/220;polish;Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0);http://creativecommons.org/licenses/by-nc/3.0/;CC;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain; charset=utf-8;downloadable_files_count: 1;Iluzjon",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "102ad385-2b22-56c7-967f-1ab3dd77420c",
-    "notes": [
-        "Film fabularny."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/220"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Sami swoi"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/102dc346-653d-5d0f-8b77-eb103f24ffaa.json b/oaitestdata/clarin-oai_dc/SET_1/json/102dc346-653d-5d0f-8b77-eb103f24ffaa.json
deleted file mode 100644
index dbb42544..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/102dc346-653d-5d0f-8b77-eb103f24ffaa.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5094",
-    "MetadataAccess": [
-        "oai:ota:oucs:5094"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Duck, Arthur."
-    ],
-    "fulltext": "oai:ota:oucs:5094;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5094.xml;The thresher's miscellany: or, poems on several subjects, written by Arthur Duck. Now a poor thresher in the county of Suffolk, ... though formerly an Eton-scholar. ...;Duck, Arthur.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "102dc346-653d-5d0f-8b77-eb103f24ffaa",
-    "oai_identifier": [
-        "oai:ota:oucs:5094"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The thresher's miscellany: or, poems on several subjects, written by Arthur Duck. Now a poor thresher in the county of Suffolk, ... though formerly an Eton-scholar. ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5094.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/103c42c4-d441-544c-ba2f-0b2e934c3c16.json b/oaitestdata/clarin-oai_dc/SET_1/json/103c42c4-d441-544c-ba2f-0b2e934c3c16.json
deleted file mode 100644
index 1f877877..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/103c42c4-d441-544c-ba2f-0b2e934c3c16.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "University of Tartu"
-    ],
-    "Contributor": [
-        "Muischnek, Kadri"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/tei+xml",
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Estonian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1068",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1068"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1068",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Tartu"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Estonia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1068;2016-04-06T16:39:49Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Estonian Reference Corpus;Muischnek, Kadri;Collection of Estonian texts (divided into subcorpora); ca 175 million words; TEI;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1068;est;application/tei+xml;downloadable_files_count: 0;Estonia;University of Tartu;http://www.cl.ut.ee/korpused/segakorpus/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "103c42c4-d441-544c-ba2f-0b2e934c3c16",
-    "notes": [
-        "Collection of Estonian texts (divided into subcorpora); ca 175 million words; TEI"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1068"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Estonian Reference Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1049d755-9b94-528c-b3f6-99bc3962bb98.json b/oaitestdata/clarin-oai_dc/SET_1/json/1049d755-9b94-528c-b3f6-99bc3962bb98.json
deleted file mode 100644
index c99397df..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1049d755-9b94-528c-b3f6-99bc3962bb98.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4349",
-    "MetadataAccess": [
-        "oai:ota:oucs:4349"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pratt, Mr. (Samuel Jackson), 1749-1814."
-    ],
-    "fulltext": "oai:ota:oucs:4349;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4349.xml;Shenstone-Green: or, the new Paradise lost. Being a history of human nature. In three volumes. ... Written by the proprietor of the Green. The editor Courtney Melmoth. [pt.3];Pratt, Mr. (Samuel Jackson), 1749-1814.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1049d755-9b94-528c-b3f6-99bc3962bb98",
-    "oai_identifier": [
-        "oai:ota:oucs:4349"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Shenstone-Green: or, the new Paradise lost. Being a history of human nature. In three volumes. ... Written by the proprietor of the Green. The editor Courtney Melmoth. [pt.3]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4349.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1056b649-9285-53c3-99bb-2440352d1b65.json b/oaitestdata/clarin-oai_dc/SET_1/json/1056b649-9285-53c3-99bb-2440352d1b65.json
deleted file mode 100644
index e26f3285..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1056b649-9285-53c3-99bb-2440352d1b65.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "NLX-Natural Language and Speech Group, University of Lisbon"
-    ],
-    "Contributor": [
-        "Branco, Ant\u00f3nio"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Portuguese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1222",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1222"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1222",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "NLX-Natural Language and Speech Group, University of Lisbon"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Portugal"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1222;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LX-Center;Branco, Ant\u00f3nio;LXCenter hosts the linguistic services developed in all or part by the NLX-Natural Language and Speech Group at the University of Lisbon, Department of Informatics. These services are freely available online on a best-effort basis to help foster the education, research and development in the realm of natural language science and technology.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1222;por;downloadable_files_count: 0;Portugal;NLX-Natural Language and Speech Group, University of Lisbon;http://lxcenter.di.fc.ul.pt/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1056b649-9285-53c3-99bb-2440352d1b65",
-    "notes": [
-        "LXCenter hosts the linguistic services developed in all or part by the NLX-Natural Language and Speech Group at the University of Lisbon, Department of Informatics. These services are freely available online on a best-effort basis to help foster the education, research and development in the realm of natural language science and technology."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1222"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LX-Center"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1061a5f6-35c2-508d-aeab-6cfcfea9f1c8.json b/oaitestdata/clarin-oai_dc/SET_1/json/1061a5f6-35c2-508d-aeab-6cfcfea9f1c8.json
deleted file mode 100644
index 1715999f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1061a5f6-35c2-508d-aeab-6cfcfea9f1c8.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia WW. OO. Bazylian\u00f3w"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-611",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-611"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D2F-6",
-    "PublicationTimestamp": "1712-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1712"
-    ],
-    "Publisher": [
-        "Drukarnia WW. OO. Bazylian\u00f3w"
-    ],
-    "RelatedIdentifier": [
-        "http://pbc.biaman.pl/Content/611"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "author": [
-        "Rakiewicz, Augustyn"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-611;2019-03-01T17:24:31Z;Snopek mirrhy gorzkiey m\u0119ki Jezusowey, y Jego Matki Nay\u015bwi\u0119tszey Panny Serdecznych bole\u015bci [...].;Rakiewicz, Augustyn;Kazania polskie 18 w.;ilo\u015b\u0107 skan\u00f3w: 146  ;  sygn. S-44;Drukarnia WW. OO. Bazylian\u00f3w;1712;starodruk;application/xml;clarind-uds:poldilemma-611;hdl:11858/00-246C-0000-0023-8D2F-6;pol;lat;http://pbc.biaman.pl/Content/611;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1061a5f6-35c2-508d-aeab-6cfcfea9f1c8",
-    "notes": [
-        "ilo\u015b\u0107 skan\u00f3w: 146  ;  sygn. S-44"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-611"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Kazania polskie w."
-        }
-    ],
-    "title": [
-        "Snopek mirrhy gorzkiey m\u0119ki Jezusowey, y Jego Matki Nay\u015bwi\u0119tszey Panny Serdecznych bole\u015bci [...]."
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/107d6355-97d7-5549-9e7a-1cfaa5ddf121.json b/oaitestdata/clarin-oai_dc/SET_1/json/107d6355-97d7-5549-9e7a-1cfaa5ddf121.json
deleted file mode 100644
index ff8755ba..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/107d6355-97d7-5549-9e7a-1cfaa5ddf121.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "University of Sheffield"
-    ],
-    "Contributor": [
-        "Funk, Adam",
-        "Peters, Wim"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1396",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1396"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1396",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Sheffield"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1396;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;GATE-ANNIE;Funk, Adam;Peters, Wim;GATE-ANNIE, developed by the GATE group at the University of Sheffield (http;//www.gate.ac.uk; Cunningham et al., 2002,) is an Information Extraction (IE) web service for English. It consists of the following main language processing tools: tokeniser, sentence splitter, POS tagger, coreference resolver and named entity recogniser. \r\nThe named entity recogniser identifies and categorizes entity names (such as persons, organizations, and location names), temporal expressions (dates and times), and certain types of numerical expressions (monetary values and percentages). \r\nGATE-ANNIE returns the fully annotated document in GATE XML format. The file saved by the client contains ANNIE's output in the default AnnotationSet and\r\nthe input document's HTML or XML mark-up in the \"Original markups\" AnnotationSet.\r\n\r\n\r\nH. Cunningham, D. Maynard, K. Bontcheva, and V. Tablan. 2002. GATE: A Framework and Graphical Development Environment for Robust NLP Tools and Applications. In Proceedings of the 40th Anniversary Meeting of the Association for Computational Linguistics (ACL-02).;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1396;downloadable_files_count: 0;United Kingdom;University of Sheffield",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "107d6355-97d7-5549-9e7a-1cfaa5ddf121",
-    "notes": [
-        "GATE-ANNIE, developed by the GATE group at the University of Sheffield (http;//www.gate.ac.uk; Cunningham et al., 2002,) is an Information Extraction (IE) web service for English. It consists of the following main language processing tools: tokeniser, sentence splitter, POS tagger, coreference resolver and named entity recogniser. \r\nThe named entity recogniser identifies and categorizes entity names (such as persons, organizations, and location names), temporal expressions (dates and times), and certain types of numerical expressions (monetary values and percentages). \r\nGATE-ANNIE returns the fully annotated document in GATE XML format. The file saved by the client contains ANNIE's output in the default AnnotationSet and\r\nthe input document's HTML or XML mark-up in the \"Original markups\" AnnotationSet.\r\n\r\n\r\nH. Cunningham, D. Maynard, K. Bontcheva, and V. Tablan. 2002. GATE: A Framework and Graphical Development Environment for Robust NLP Tools and Applications. In Proceedings of the 40th Anniversary Meeting of the Association for Computational Linguistics (ACL-02)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1396"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "GATE-ANNIE"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/108d731a-a873-5bb4-a44d-9c57b942055e.json b/oaitestdata/clarin-oai_dc/SET_1/json/108d731a-a873-5bb4-a44d-9c57b942055e.json
deleted file mode 100644
index 33501e0c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/108d731a-a873-5bb4-a44d-9c57b942055e.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contributor": [
-        "Comeyne, Robrecht"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Danish",
-        "Dutch",
-        "English",
-        "Finnish",
-        "French",
-        "German",
-        "Modern Greek (1453-)",
-        "Italian",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-174",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-174"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-174",
-    "PublicationTimestamp": "2001-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2001"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-174;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;SpeechDat-Car databases;Comeyne, Robrecht;9 speech databases for training and testing multilingual speech recognition applications in the car environment. Contains parallel 4 channel in-car recordings and a GSM channel. Contains interesting phonetically rich material. All orthographically transcribed. Speaker information included for gender, age, accent. Including pronunciation lexicon.;2001;corpus;http://hdl.handle.net/11372/LRT-174;dan;nld;eng;fin;fra;deu;ell;ita;spa;downloadable_files_count: 0;http://www.speechdat.org/SP-CAR/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "108d731a-a873-5bb4-a44d-9c57b942055e",
-    "notes": [
-        "9 speech databases for training and testing multilingual speech recognition applications in the car environment. Contains parallel 4 channel in-car recordings and a GSM channel. Contains interesting phonetically rich material. All orthographically transcribed. Speaker information included for gender, age, accent. Including pronunciation lexicon."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-174"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "SpeechDat-Car databases"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/10a40873-7c67-5395-8883-c1a6645fe918.json b/oaitestdata/clarin-oai_dc/SET_1/json/10a40873-7c67-5395-8883-c1a6645fe918.json
deleted file mode 100644
index 03f2135d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/10a40873-7c67-5395-8883-c1a6645fe918.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Delbecque, Nicole"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 91 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0476",
-    "MetadataAccess": [
-        "oai:ota:oucs:0476"
-    ],
-    "PublicationTimestamp": "1966-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1966"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Mercer, David, 1928-1980"
-    ],
-    "fulltext": "oai:ota:oucs:0476;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0476.xml;Belcher's luck / David Mercer;Mercer, David, 1928-1980;1966;text_and_corpus_linguistics;English drama -- 20th century;eng;Oxford Text Archive, University of Oxford;Delbecque, Nicole;text/plain;(1 file : ca. 91 KB);Text;Plays;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "10a40873-7c67-5395-8883-c1a6645fe918",
-    "oai_identifier": [
-        "oai:ota:oucs:0476"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- th century"
-        }
-    ],
-    "title": [
-        "Belcher's luck / David Mercer"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0476.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/10c6ee54-1eb1-565c-b14c-ec7504ad19e8.json b/oaitestdata/clarin-oai_dc/SET_1/json/10c6ee54-1eb1-565c-b14c-ec7504ad19e8.json
deleted file mode 100644
index 082d3ef0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/10c6ee54-1eb1-565c-b14c-ec7504ad19e8.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3672",
-    "MetadataAccess": [
-        "oai:ota:oucs:3672"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pope, Alexander, 1688-1744."
-    ],
-    "fulltext": "oai:ota:oucs:3672;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3672.xml;The Dunciad: With notes variorum, and the prolegomena of Scriblerus. Written in the year, 1727.;Pope, Alexander, 1688-1744.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "10c6ee54-1eb1-565c-b14c-ec7504ad19e8",
-    "oai_identifier": [
-        "oai:ota:oucs:3672"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The Dunciad: With notes variorum, and the prolegomena of Scriblerus. Written in the year, 1727."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3672.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/10c8b771-350e-56bb-aa34-e77a7bc0f0b8.json b/oaitestdata/clarin-oai_dc/SET_1/json/10c8b771-350e-56bb-aa34-e77a7bc0f0b8.json
deleted file mode 100644
index abe28f5b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/10c8b771-350e-56bb-aa34-e77a7bc0f0b8.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Adam Mickiewicz University"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 22",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/464",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/464"
-    ],
-    "PID": "http://hdl.handle.net/11321/464",
-    "PublicationTimestamp": "2018-04-13T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Adam Mickiewicz University"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "plWordNet",
-        "http://clarin-pl.eu/en/licenses/plwordnet-2/",
-        "PUB"
-    ],
-    "author": [
-        "Kasperek, Hanna"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/464;2018-04-13T07:56:05Z;hdl_11321_3;hdl_11321_4;Polish politics with linguistic background;Kasperek, Hanna;politician;MP;speech;Speeches by MPs with language background.;2018-04-13;corpus;http://hdl.handle.net/11321/464;Polish;plWordNet;http://clarin-pl.eu/en/licenses/plwordnet-2/;PUB;text/plain; charset=utf-8;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;downloadable_files_count: 22;Adam Mickiewicz University",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "10c8b771-350e-56bb-aa34-e77a7bc0f0b8",
-    "notes": [
-        "Speeches by MPs with language background."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/464"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "politician"
-        },
-        {
-            "name": "MP"
-        },
-        {
-            "name": "speech"
-        }
-    ],
-    "title": [
-        "Polish politics with linguistic background"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/10eb3ac4-dbd0-5d3f-828c-e9f6f96110d2.json b/oaitestdata/clarin-oai_dc/SET_1/json/10eb3ac4-dbd0-5d3f-828c-e9f6f96110d2.json
deleted file mode 100644
index 0b109764..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/10eb3ac4-dbd0-5d3f-828c-e9f6f96110d2.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=dcb9fd566c9211e2a2aa782bcb07413586a54ee5131340e9af937b576f71c5b0",
-    "MetadataAccess": [
-        "dcb9fd566c9211e2a2aa782bcb07413586a54ee5131340e9af937b576f71c5b0"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "dcb9fd566c9211e2a2aa782bcb07413586a54ee5131340e9af937b576f71c5b0;2018-11-15T16:40:11Z;toolService;toolService:service;U-Compare Species Disambiguation Service ;Web service created by exporting UIMA-based workflow from the U-Compare text mining system.\nFunctionality: Identifies biological named entities and disambiguates them according to\nspecies, by assigning a species ID from the NCBI taxonomy. Also identifies sentences and tokens.\nTools in workflow: GENIA Sentence Splitter, GENIA Tagger (with tokenisation), Species Word Detector, ExtractAbbrev, Species Disambiguator (all from the University of Manchester) \nNOTE: The licence provided covers the web service only. Tools used to create the workflow may have their own licences;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "10eb3ac4-dbd0-5d3f-828c-e9f6f96110d2",
-    "notes": [
-        "Web service created by exporting UIMA-based workflow from the U-Compare text mining system.\nFunctionality: Identifies biological named entities and disambiguates them according to\nspecies, by assigning a species ID from the NCBI taxonomy. Also identifies sentences and tokens.\nTools in workflow: GENIA Sentence Splitter, GENIA Tagger (with tokenisation), Species Word Detector, ExtractAbbrev, Species Disambiguator (all from the University of Manchester) \nNOTE: The licence provided covers the web service only. Tools used to create the workflow may have their own licences"
-    ],
-    "oai_identifier": [
-        "dcb9fd566c9211e2a2aa782bcb07413586a54ee5131340e9af937b576f71c5b0"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:service"
-    ],
-    "state": "active",
-    "title": [
-        "U-Compare Species Disambiguation Service "
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1107830c-d98b-5212-9089-1e9eb4cae9ff.json b/oaitestdata/clarin-oai_dc/SET_1/json/1107830c-d98b-5212-9089-1e9eb4cae9ff.json
deleted file mode 100644
index 0de0aa77..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1107830c-d98b-5212-9089-1e9eb4cae9ff.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3981",
-    "MetadataAccess": [
-        "oai:ota:oucs:3981"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Warton, Thomas, 1728-1790."
-    ],
-    "fulltext": "oai:ota:oucs:3981;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3981.xml;Five pastoral eclogues: the scenes of which are suppos'd to lie among the shepherds, oppress'd by the war in Germany;Warton, Thomas, 1728-1790.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1107830c-d98b-5212-9089-1e9eb4cae9ff",
-    "oai_identifier": [
-        "oai:ota:oucs:3981"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Five pastoral eclogues: the scenes of which are suppos'd to lie among the shepherds, oppress'd by the war in Germany"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3981.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/116aa3c9-efab-52a4-a050-1be839280d79.json b/oaitestdata/clarin-oai_dc/SET_1/json/116aa3c9-efab-52a4-a050-1be839280d79.json
deleted file mode 100644
index 18c18695..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/116aa3c9-efab-52a4-a050-1be839280d79.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 3",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/446",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/446"
-    ],
-    "PID": "http://hdl.handle.net/11321/446",
-    "PublicationTimestamp": "2017-11-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "Janz, Arkadiusz",
-        "Kaszewski, Dominik"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/446;2017-11-30T14:39:33Z;hdl_11321_3;hdl_11321_4;Tests for Word Embeddings;Kaszewski, Dominik;Janz, Arkadiusz;plWordNet;Word2Vec;Evaluation tools (WBST, HWBST, EWBST)  for word embedding models used to assess and compare the usefulness of different word embeddings;2017-11-30;toolService;http://hdl.handle.net/11321/446;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 3;Wroc\u0142aw University of Science and Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "116aa3c9-efab-52a4-a050-1be839280d79",
-    "notes": [
-        "Evaluation tools (WBST, HWBST, EWBST)  for word embedding models used to assess and compare the usefulness of different word embeddings"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/446"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "plWordNet"
-        },
-        {
-            "name": "WordVec"
-        }
-    ],
-    "title": [
-        "Tests for Word Embeddings"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/117431ab-0f52-5950-a2ef-d69082b15721.json b/oaitestdata/clarin-oai_dc/SET_1/json/117431ab-0f52-5950-a2ef-d69082b15721.json
deleted file mode 100644
index e025f115..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/117431ab-0f52-5950-a2ef-d69082b15721.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 106 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0602",
-    "MetadataAccess": [
-        "oai:ota:oucs:0602"
-    ],
-    "PublicationTimestamp": "1661-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1661"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Webster, John, 1580?-1625?"
-    ],
-    "fulltext": "oai:ota:oucs:0602;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0602.xml;A cure for a cuckold;Webster, John, 1580?-1625?;1661;text_and_corpus_linguistics;Plays -- England -- 17th century;Comedies -- England -- 17th century;eng;Oxford Text Archive, University of Oxford;(1 file : ca. 106 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "117431ab-0f52-5950-a2ef-d69082b15721",
-    "oai_identifier": [
-        "oai:ota:oucs:0602"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        },
-        {
-            "name": "Comedies -- England -- th century"
-        }
-    ],
-    "title": [
-        "A cure for a cuckold"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0602.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1183b862-1bb9-57fa-be01-817ce659b2ee.json b/oaitestdata/clarin-oai_dc/SET_1/json/1183b862-1bb9-57fa-be01-817ce659b2ee.json
deleted file mode 100644
index f8f94b7e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1183b862-1bb9-57fa-be01-817ce659b2ee.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-927",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-927"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-927",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-927;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Tokharian B (West);ca. 200.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-927;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#TochB",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1183b862-1bb9-57fa-be01-817ce659b2ee",
-    "notes": [
-        "ca. 200.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-927"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Tokharian B (West)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/11900802-e645-512a-bee9-0d7c8f361e46.json b/oaitestdata/clarin-oai_dc/SET_1/json/11900802-e645-512a-bee9-0d7c8f361e46.json
deleted file mode 100644
index eabf5264..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/11900802-e645-512a-bee9-0d7c8f361e46.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Polish-Japanese Academy of Information Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/526",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/526"
-    ],
-    "PID": "http://hdl.handle.net/11321/526",
-    "PublicationTimestamp": "2018-07-08T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Polish-Japanese Academy of Information Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Wo\u0142k, Krzysztof",
-        "Marasek, Krzysztof",
-        "Kor\u017einek, Danijel"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/526;2018-07-15T08:02:44Z;hdl_11321_3;hdl_11321_4;Speech Recognition System for Polish: Polish Film Chronicles;Kor\u017einek, Danijel;Marasek, Krzysztof;Wo\u0142k, Krzysztof;speech recognition;speech alignment;This resource contains dockerized models and scripts of an automatic speech recognition system for Polish trained on recording of the Polish Film Chronicles. The system is based on the Kaldi toolkit. The scripts include methods for performing speech recognition, forced alignment and a lenient alignment of audio. The Github repository contains information on how to use the tool.;2018-07-08;toolService;http://hdl.handle.net/11321/526;pol;downloadable_files_count: 0;Polish-Japanese Academy of Information Technology;https://hub.docker.com/r/danijel3/clarin-pl-speechtools/tags/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "11900802-e645-512a-bee9-0d7c8f361e46",
-    "notes": [
-        "This resource contains dockerized models and scripts of an automatic speech recognition system for Polish trained on recording of the Polish Film Chronicles. The system is based on the Kaldi toolkit. The scripts include methods for performing speech recognition, forced alignment and a lenient alignment of audio. The Github repository contains information on how to use the tool."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/526"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech recognition"
-        },
-        {
-            "name": "speech alignment"
-        }
-    ],
-    "title": [
-        "Speech Recognition System for Polish: Polish Film Chronicles"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/11b59a15-b63c-5226-a7a2-31e5c1a0dfd7.json b/oaitestdata/clarin-oai_dc/SET_1/json/11b59a15-b63c-5226-a7a2-31e5c1a0dfd7.json
deleted file mode 100644
index 98967f3c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/11b59a15-b63c-5226-a7a2-31e5c1a0dfd7.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Institut f\u00fcr Deutsche Sprache"
-    ],
-    "Contributor": [
-        "M\u00fcller-Spitzer, Dr. Carolin"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1147",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1147"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1147",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut f\u00fcr Deutsche Sprache"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1147;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;elexiko \u2013 Online-W\u00f6rterbuch zur deutschen Gegenwartssprache;M\u00fcller-Spitzer, Dr. Carolin;Germanistik;Schwerpunkt: Bedeutungs-/Verwendungsbeschreibung; zus\u00e4tzlich: Angabe von Orthographie, Worttrennung und grammatischen Informationen; befindet sich noch im Aufbau;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1147;deu;downloadable_files_count: 0;Germany;Institut f\u00fcr Deutsche Sprache;http://www.owid.de/wb/elexiko/start.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "11b59a15-b63c-5226-a7a2-31e5c1a0dfd7",
-    "notes": [
-        "Schwerpunkt: Bedeutungs-/Verwendungsbeschreibung; zus\u00e4tzlich: Angabe von Orthographie, Worttrennung und grammatischen Informationen; befindet sich noch im Aufbau"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1147"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "elexiko \u2013 Online-W\u00f6rterbuch zur deutschen Gegenwartssprache"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/11de8c00-fa36-58e0-9463-eefb023fb494.json b/oaitestdata/clarin-oai_dc/SET_1/json/11de8c00-fa36-58e0-9463-eefb023fb494.json
deleted file mode 100644
index b220b42e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/11de8c00-fa36-58e0-9463-eefb023fb494.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "University of Oxford Text Archive",
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3115",
-    "MetadataAccess": [
-        "oai:ota:oucs:3115"
-    ],
-    "PublicationTimestamp": "1584-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1584"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hakluyt, Richard, 1552?-1616"
-    ],
-    "fulltext": "oai:ota:oucs:3115;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3115.xml;Discourse of Western Planting;A particuler discourse concerning the greate necessitie and manifolde commodyties that are like to growe to this realme of Englande by the westerne discoueries lately attempted, written in the yere 1584 : known as discourse of western planting;Hakluyt, Richard, 1552?-1616;not after: 1584;text_and_corpus_linguistics;America -- Discovery and exploration -- English;eng;Oxford Text Archive, University of Oxford;University of Oxford Text Archive;Triggs, Jeffery;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "11de8c00-fa36-58e0-9463-eefb023fb494",
-    "oai_identifier": [
-        "oai:ota:oucs:3115"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "America -- Discovery exploration -- English"
-        }
-    ],
-    "title": [
-        "Discourse of Western Planting",
-        "A particuler discourse concerning the greate necessitie and manifolde commodyties that are like to growe to this realme of Englande by the westerne discoueries lately attempted, written in the yere 1584 : known as discourse of western planting"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3115.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/11e9e419-a6a9-5846-86ca-cce30653d2e5.json b/oaitestdata/clarin-oai_dc/SET_1/json/11e9e419-a6a9-5846-86ca-cce30653d2e5.json
deleted file mode 100644
index 30841ada..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/11e9e419-a6a9-5846-86ca-cce30653d2e5.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Radboud University Nijmegen"
-    ],
-    "Contributor": [
-        "Crasborn, Onno"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-561",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-561"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-561",
-    "PublicationTimestamp": "2008-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2008"
-    ],
-    "Publisher": [
-        "Radboud University Nijmegen"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons BY-NC-SA 3.0 NL license",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/nl/"
-    ],
-    "SpatialCoverage": [
-        "Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-561;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Corpus Nederlandse Gebarentaal (CNGT);Crasborn, Onno;Linguistics;language technology;The Corpus NGT is a collection of data from deaf signers using Sign Language of the Netherlands (NGT). The data consist of recordings with multiple synchronised video cameras, accompanied by gloss and translation annotations.;2008;corpus;http://hdl.handle.net/11372/LRT-561;Creative Commons BY-NC-SA 3.0 NL license;http://creativecommons.org/licenses/by-nc-sa/3.0/nl/;downloadable_files_count: 0;Netherlands (the);Radboud University Nijmegen;http://www.corpusngt.nl;http://corpus1.mpi.nl/ds/imdi_browser/?openpath=MPI319374%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "11e9e419-a6a9-5846-86ca-cce30653d2e5",
-    "notes": [
-        "The Corpus NGT is a collection of data from deaf signers using Sign Language of the Netherlands (NGT). The data consist of recordings with multiple synchronised video cameras, accompanied by gloss and translation annotations."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-561"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Linguistics"
-        },
-        {
-            "name": "language technology"
-        }
-    ],
-    "title": [
-        "Corpus Nederlandse Gebarentaal (CNGT)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/120e85d3-8497-5bb1-bff8-fefeb864148f.json b/oaitestdata/clarin-oai_dc/SET_1/json/120e85d3-8497-5bb1-bff8-fefeb864148f.json
deleted file mode 100644
index 4928a1f0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/120e85d3-8497-5bb1-bff8-fefeb864148f.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3272",
-    "MetadataAccess": [
-        "oai:ota:oucs:3272"
-    ],
-    "PublicationTimestamp": "1903-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1903"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Kipling, Rudyard, 1865-1936"
-    ],
-    "fulltext": "oai:ota:oucs:3272;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3272.xml;The Five Nations;Kipling, Rudyard, 1865-1936;not after: 1903;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "120e85d3-8497-5bb1-bff8-fefeb864148f",
-    "oai_identifier": [
-        "oai:ota:oucs:3272"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The Five Nations"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3272.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1220e8cd-3263-50c0-8b0e-6d3ad33488c0.json b/oaitestdata/clarin-oai_dc/SET_1/json/1220e8cd-3263-50c0-8b0e-6d3ad33488c0.json
deleted file mode 100644
index e13038a0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1220e8cd-3263-50c0-8b0e-6d3ad33488c0.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4057",
-    "MetadataAccess": [
-        "oai:ota:oucs:4057"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Churchill, Charles, 1731-1764."
-    ],
-    "fulltext": "oai:ota:oucs:4057;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4057.xml;The ghost: By C. Churchill. Book III.;Ghost.;Churchill, Charles, 1731-1764.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1220e8cd-3263-50c0-8b0e-6d3ad33488c0",
-    "oai_identifier": [
-        "oai:ota:oucs:4057"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The ghost: By C. Churchill. Book III.",
-        "Ghost."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4057.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1235fe5f-dbe4-539a-af68-32616f6d727f.json b/oaitestdata/clarin-oai_dc/SET_1/json/1235fe5f-dbe4-539a-af68-32616f6d727f.json
deleted file mode 100644
index 083619a8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1235fe5f-dbe4-539a-af68-32616f6d727f.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "greater than 5 MB"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0389",
-    "MetadataAccess": [
-        "oai:ota:oucs:0389"
-    ],
-    "PublicationYear": [
-        "325-393"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Addresses"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Libanius"
-    ],
-    "fulltext": "oai:ota:oucs:0389;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0389.xml;Libanii opera;Collected works  / compiled by Thesaurus Linguae Graecae;Libanius;325-393;text_and_corpus_linguistics;Addresses -- 4th century;grc;Oxford Text Archive, University of Oxford;greater than 5 MB;Text;Addresses;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1235fe5f-dbe4-539a-af68-32616f6d727f",
-    "oai_identifier": [
-        "oai:ota:oucs:0389"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Addresses -- th century"
-        }
-    ],
-    "title": [
-        "Libanii opera",
-        "Collected works  / compiled by Thesaurus Linguae Graecae"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0389.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/123672d7-41a5-5aa1-ac39-9c64f6c4e4a3.json b/oaitestdata/clarin-oai_dc/SET_1/json/123672d7-41a5-5aa1-ac39-9c64f6c4e4a3.json
deleted file mode 100644
index 1445d351..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/123672d7-41a5-5aa1-ac39-9c64f6c4e4a3.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Berlin-Brandenburg Academy of Sciences and Humanities"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/tei+xml",
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-978",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-978"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-978",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Berlin-Brandenburg Academy of Sciences and Humanities"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-978;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Korpus Berliner Zeitung;Articles from the 'Berliner Zeitung' online edition from 3.1.1994 to 31.12.2005. About 252 million tokens in 869,000 articles. Part of the DWDS project.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-978;deu;application/tei+xml;downloadable_files_count: 0;Germany;Berlin-Brandenburg Academy of Sciences and Humanities;http://www.dwds.de/ressourcen/korpora/#part_2",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "123672d7-41a5-5aa1-ac39-9c64f6c4e4a3",
-    "notes": [
-        "Articles from the 'Berliner Zeitung' online edition from 3.1.1994 to 31.12.2005. About 252 million tokens in 869,000 articles. Part of the DWDS project."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-978"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Korpus Berliner Zeitung"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1238e91f-6af7-5693-b961-85b16e3769ff.json b/oaitestdata/clarin-oai_dc/SET_1/json/1238e91f-6af7-5693-b961-85b16e3769ff.json
deleted file mode 100644
index 4d774f08..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1238e91f-6af7-5693-b961-85b16e3769ff.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2773",
-    "MetadataAccess": [
-        "oai:ota:oucs:2773"
-    ],
-    "PublicationTimestamp": "1758-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1758"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2773;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2773.xml;The history of the four last years of the Queen.;Swift, Jonathan, 1667-1745;1758;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1238e91f-6af7-5693-b961-85b16e3769ff",
-    "oai_identifier": [
-        "oai:ota:oucs:2773"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The history of the four last years of the Queen."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2773.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/126dfefe-a184-5d9b-be0a-e738d867ab3c.json b/oaitestdata/clarin-oai_dc/SET_1/json/126dfefe-a184-5d9b-be0a-e738d867ab3c.json
deleted file mode 100644
index d2a751f8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/126dfefe-a184-5d9b-be0a-e738d867ab3c.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Imam Khomeini International University"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 4",
-        "application/x-rar-compressed"
-    ],
-    "Language": [],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1531",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1531"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1531",
-    "PublicationTimestamp": "2015-10-30T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Imam Khomeini International University"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Rahimi, Adel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1531;2017-04-18T14:19:19Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Balaxan Corpus of Kurmanji;Rahimi, Adel;speech corpus;corpus;Balaxan is the first speech corpus of Kurmanji Kurdish with 58 utterances by speakers of Kurmanji. utterances are divided into 4 categories based on their sentence structures: Declarative, Imperative, Interrogative, and Exclamatory. The corpus has subtitles both in Kurmanji (Latin alphabet) and English.;2015-10-30;corpus;http://hdl.handle.net/11372/LRT-1531;kmr;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/x-rar-compressed;application/x-rar-compressed;application/x-rar-compressed;application/x-rar-compressed;text/plain; charset=utf-8;downloadable_files_count: 4;Imam Khomeini International University;http://adelra.github.com/balaxan",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "126dfefe-a184-5d9b-be0a-e738d867ab3c",
-    "notes": [
-        "Balaxan is the first speech corpus of Kurmanji Kurdish with 58 utterances by speakers of Kurmanji. utterances are divided into 4 categories based on their sentence structures: Declarative, Imperative, Interrogative, and Exclamatory. The corpus has subtitles both in Kurmanji (Latin alphabet) and English."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1531"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech corpus"
-        },
-        {
-            "name": "corpus"
-        }
-    ],
-    "title": [
-        "Balaxan Corpus of Kurmanji"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/128b6a4d-6d1b-5316-837e-12b01e5c9770.json b/oaitestdata/clarin-oai_dc/SET_1/json/128b6a4d-6d1b-5316-837e-12b01e5c9770.json
deleted file mode 100644
index e6cf7e18..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/128b6a4d-6d1b-5316-837e-12b01e5c9770.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Rodziewicz"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 17",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/91",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/91"
-    ],
-    "PID": "http://hdl.handle.net/11321/91",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Rodziewicz"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Rodziewicz, Rodziewicz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/91;2017-05-30T14:20:59Z;hdl_11321_3;hdl_11321_4;MWE Rodziewicz;Rodziewicz, Rodziewicz;Rodziewicz;2015-04-08;corpus;http://hdl.handle.net/11321/91;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 17;Rodziewicz",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "128b6a4d-6d1b-5316-837e-12b01e5c9770",
-    "notes": [
-        "Rodziewicz"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/91"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Rodziewicz"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/12945813-84e3-540d-bffe-30f48b33214c.json b/oaitestdata/clarin-oai_dc/SET_1/json/12945813-84e3-540d-bffe-30f48b33214c.json
deleted file mode 100644
index 7ef86501..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/12945813-84e3-540d-bffe-30f48b33214c.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "between 1 and 2 MB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0400",
-    "MetadataAccess": [
-        "oai:ota:oucs:0400"
-    ],
-    "PublicationTimestamp": "1921-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1921"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Dictionaries"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Unknown"
-    ],
-    "fulltext": "oai:ota:oucs:0400;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0400.xml; Thorndike-Lorge magazine count  / compiled by Yael Cycowicz;Unknown;1921;text_and_corpus_linguistics;Dictionaries -- United States -- 20th century;eng;Oxford Text Archive, University of Oxford;between 1 and 2 MB;Text;Dictionaries;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "12945813-84e3-540d-bffe-30f48b33214c",
-    "oai_identifier": [
-        "oai:ota:oucs:0400"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Dictionaries -- United States -- th century"
-        }
-    ],
-    "title": [
-        " Thorndike-Lorge magazine count  / compiled by Yael Cycowicz"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0400.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/129ed772-1b0f-5c66-a5fc-d9703c47ed27.json b/oaitestdata/clarin-oai_dc/SET_1/json/129ed772-1b0f-5c66-a5fc-d9703c47ed27.json
deleted file mode 100644
index 771fc72d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/129ed772-1b0f-5c66-a5fc-d9703c47ed27.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3474",
-    "MetadataAccess": [
-        "oai:ota:oucs:3474"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Craven, Elizabeth Craven, Baroness, 1750-1828."
-    ],
-    "fulltext": "oai:ota:oucs:3474;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3474.xml;Songs, duets, trios, &c. in The silver tankard; or, ehe [sic] point at Portsmouth. As performed at the Theatre-Royal in the Hay-Market;Silver tankard.;Craven, Elizabeth Craven, Baroness, 1750-1828.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "129ed772-1b0f-5c66-a5fc-d9703c47ed27",
-    "oai_identifier": [
-        "oai:ota:oucs:3474"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Songs, duets, trios, &c. in The silver tankard; or, ehe [sic] point at Portsmouth. As performed at the Theatre-Royal in the Hay-Market",
-        "Silver tankard."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3474.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/129f0035-4d16-5841-8483-faa9820de63e.json b/oaitestdata/clarin-oai_dc/SET_1/json/129f0035-4d16-5841-8483-faa9820de63e.json
deleted file mode 100644
index 83643423..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/129f0035-4d16-5841-8483-faa9820de63e.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/pdf"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/532",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/532"
-    ],
-    "PID": "http://hdl.handle.net/11321/532",
-    "PublicationTimestamp": "2018-07-20T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Oleksy, Marcin",
-        "Koco\u0144, Jan"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/532;2018-07-23T11:56:12Z;hdl_11321_3;hdl_11321_4;KPWr annotation guidelines - events (attributes and relations);Oleksy, Marcin;Koco\u0144, Jan;events;events instances;attributes for event;events;event attributes;TimeML;KPWr annotation guidelines - events instances attributes and relations between events instances;2018-07-20;languageDescription;http://hdl.handle.net/11321/532;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain; charset=utf-8;application/pdf;downloadable_files_count: 1;Wroc\u0142aw University of Science and Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "129f0035-4d16-5841-8483-faa9820de63e",
-    "notes": [
-        "KPWr annotation guidelines - events instances attributes and relations between events instances"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/532"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "events"
-        },
-        {
-            "name": "events instances"
-        },
-        {
-            "name": "attributes event"
-        },
-        {
-            "name": "events"
-        },
-        {
-            "name": "event attributes"
-        },
-        {
-            "name": "TimeML"
-        }
-    ],
-    "title": [
-        "KPWr annotation guidelines - events (attributes and relations)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/12a0431f-fa99-5832-826c-08ab44a578e4.json b/oaitestdata/clarin-oai_dc/SET_1/json/12a0431f-fa99-5832-826c-08ab44a578e4.json
deleted file mode 100644
index a973aaf4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/12a0431f-fa99-5832-826c-08ab44a578e4.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1584",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1584"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1584",
-    "PublicationTimestamp": "2015-11-30T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Mozilla Public License 2.0",
-        "http://opensource.org/licenses/MPL-2.0",
-        "PUB"
-    ],
-    "author": [
-        "Straka, Milan"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1584;2018-07-02T22:05:54Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Parsito;Straka, Milan;parser;dependency parser;Parsito is a fast open-source dependency parser written in C++. Parsito is based on greedy transition-based parsing, it has very high accuracy and achieves a throughput of 30K words per second. Parsito can be trained on any input data without feature engineering, because it utilizes artificial neural network classifier. Trained models for all treebanks from Universal Dependencies project are available (37 treebanks as of Dec 2015).\r\n\r\nParsito is a free software under Mozilla Public License 2.0 (http://www.mozilla.org/MPL/2.0/) and the linguistic models are free for non-commercial use and distributed under CC BY-NC-SA (http://creativecommons.org/licenses/by-nc-sa/4.0/) license, although for some models the original data used to create the model may impose additional licensing conditions.\r\n\r\nParsito website http://ufal.mff.cuni.cz/parsito contains download links of both\r\nthe released packages and trained models, hosts documentation and offers online\r\ndemo.\r\n\r\nParsito development repository http://github.com/ufal/parsito is hosted on\r\nGitHub.;2015-11-30;toolService;http://hdl.handle.net/11234/1-1584;eng;Mozilla Public License 2.0;http://opensource.org/licenses/MPL-2.0;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/parsito",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "12a0431f-fa99-5832-826c-08ab44a578e4",
-    "notes": [
-        "Parsito is a fast open-source dependency parser written in C++. Parsito is based on greedy transition-based parsing, it has very high accuracy and achieves a throughput of 30K words per second. Parsito can be trained on any input data without feature engineering, because it utilizes artificial neural network classifier. Trained models for all treebanks from Universal Dependencies project are available (37 treebanks as of Dec 2015).\r\n\r\nParsito is a free software under Mozilla Public License 2.0 (http://www.mozilla.org/MPL/2.0/) and the linguistic models are free for non-commercial use and distributed under CC BY-NC-SA (http://creativecommons.org/licenses/by-nc-sa/4.0/) license, although for some models the original data used to create the model may impose additional licensing conditions.\r\n\r\nParsito website http://ufal.mff.cuni.cz/parsito contains download links of both\r\nthe released packages and trained models, hosts documentation and offers online\r\ndemo.\r\n\r\nParsito development repository http://github.com/ufal/parsito is hosted on\r\nGitHub."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1584"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parser"
-        },
-        {
-            "name": "dependency parser"
-        }
-    ],
-    "title": [
-        "Parsito"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/12a18489-3bbf-5b6d-9ce5-74dbe144c7f5.json b/oaitestdata/clarin-oai_dc/SET_1/json/12a18489-3bbf-5b6d-9ce5-74dbe144c7f5.json
deleted file mode 100644
index a1460352..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/12a18489-3bbf-5b6d-9ce5-74dbe144c7f5.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Marek Troszy\u0144ski"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/150",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/150"
-    ],
-    "PID": "http://hdl.handle.net/11321/150",
-    "PublicationTimestamp": "2015-04-13T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Marek Troszy\u0144ski"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Troszynski, Marek"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/150;2015-04-13T13:53:43Z;hdl_11321_3;hdl_11321_4;Romowie02;Troszynski, Marek;Romowie w polskim internecie;2015-04-13;corpus;http://hdl.handle.net/11321/150;pol;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain; charset=utf-8;downloadable_files_count: 1;Marek Troszy\u0144ski",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "12a18489-3bbf-5b6d-9ce5-74dbe144c7f5",
-    "notes": [
-        "Romowie w polskim internecie"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/150"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Romowie02"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/12a2dd4d-2355-5db4-bc24-e15648eac371.json b/oaitestdata/clarin-oai_dc/SET_1/json/12a2dd4d-2355-5db4-bc24-e15648eac371.json
deleted file mode 100644
index db51c92d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/12a2dd4d-2355-5db4-bc24-e15648eac371.json
+++ /dev/null
@@ -1,102 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 6",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Persian",
-        "Macedonian",
-        "Polish",
-        "Russian",
-        "Serbian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1042",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1042"
-    ],
-    "PID": "http://hdl.handle.net/11356/1042",
-    "PublicationTimestamp": "2010-05-14T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/211938",
-        "https://doi.org/10.1007/s10579-011-9174-8",
-        "http://hdl.handle.net/11372/LRT-675"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)",
-        "https://creativecommons.org/licenses/by-nc/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Divjak, Dagmar",
-        "Krstev, Cvetana",
-        "Vitas, Du\u0161ko",
-        "Radziszewski, Adam",
-        "Sharoff, Serge",
-        "Kotsyba, Natalia",
-        "Erjavec, Toma\u017e",
-        "Zdravkova, Katerina",
-        "Kopotev, Mikhail",
-        "Sokolovsky, Paul",
-        "Derzhanski, Ivan",
-        "Petrovski, Aleksandar",
-        "QasemiZadeh, Behrang",
-        "Feldman, Anna"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1042;2018-05-28T11:24:49Z;hdl_11356_1023;hdl_11356_1024;MULTEXT-East non-commercial lexicons 4.0;Erjavec, Toma\u017e;Derzhanski, Ivan;Divjak, Dagmar;Feldman, Anna;Kopotev, Mikhail;Kotsyba, Natalia;Krstev, Cvetana;Petrovski, Aleksandar;QasemiZadeh, Behrang;Radziszewski, Adam;Sharoff, Serge;Sokolovsky, Paul;Vitas, Du\u0161ko;Zdravkova, Katerina;lemmatisation;inflection;tagging;multilingual;The MULTEXT-East morphosyntactic lexicons have a simple structure, where each line is a lexical entry with three tab-separated fields: (1) the word-form, the inflected form of the word; (2) the lemma, the base-form of the word; (3) the MSD, the morphosyntactic description of the word-form, i.e., its fine-grained PoS tag, as defined in the MULTEXT-East morphosyntactic specifications. \r\n\r\nThis submission contains the non-commercial MULTEXT-East lexicons, while a separate submission (http://hdl.handle.net/11356/1041) gives those that are freely available.;2010-05-14;lexicalConceptualResource;http://hdl.handle.net/11356/1042;fas;mkd;pol;rus;srp;info:eu-repo/grantAgreement/EC/FP7/211938;https://doi.org/10.1007/s10579-011-9174-8;http://hdl.handle.net/11372/LRT-675;Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0);https://creativecommons.org/licenses/by-nc/4.0/;PUB;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;text/plain;text/plain; charset=utf-8;downloadable_files_count: 6;Jo\u017eef Stefan Institute;http://nl.ijs.si/ME/V4/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "12a2dd4d-2355-5db4-bc24-e15648eac371",
-    "notes": [
-        "The MULTEXT-East morphosyntactic lexicons have a simple structure, where each line is a lexical entry with three tab-separated fields: (1) the word-form, the inflected form of the word; (2) the lemma, the base-form of the word; (3) the MSD, the morphosyntactic description of the word-form, i.e., its fine-grained PoS tag, as defined in the MULTEXT-East morphosyntactic specifications. \r\n\r\nThis submission contains the non-commercial MULTEXT-East lexicons, while a separate submission (http://hdl.handle.net/11356/1041) gives those that are freely available."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1042"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "lemmatisation"
-        },
-        {
-            "name": "inflection"
-        },
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "multilingual"
-        }
-    ],
-    "title": [
-        "MULTEXT-East non-commercial lexicons 4.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/12a4738f-4921-5891-9ef0-f301b5a81eaa.json b/oaitestdata/clarin-oai_dc/SET_1/json/12a4738f-4921-5891-9ef0-f301b5a81eaa.json
deleted file mode 100644
index f0ac8f46..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/12a4738f-4921-5891-9ef0-f301b5a81eaa.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Estonian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-528",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-528"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-528",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "SpatialCoverage": [
-        "Estonia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-528;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Constraint Grammar of Estonian;general written, Constraint Grammar;2014-07-30;languageDescription;http://hdl.handle.net/11372/LRT-528;est;downloadable_files_count: 0;Estonia;http://www.ut.ee/~kaili/Grammar",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "12a4738f-4921-5891-9ef0-f301b5a81eaa",
-    "notes": [
-        "general written, Constraint Grammar"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-528"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Constraint Grammar of Estonian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/12b1b81a-eef1-57dc-a2cc-e6bc95f0c7a9.json b/oaitestdata/clarin-oai_dc/SET_1/json/12b1b81a-eef1-57dc-a2cc-e6bc95f0c7a9.json
deleted file mode 100644
index a3d6d6da..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/12b1b81a-eef1-57dc-a2cc-e6bc95f0c7a9.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Dabrowska, Kaczkowski, Prus, Reymont, Sienkiewicz, Mniszek"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/plain",
-        "downloadable_files_count: 10"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/99",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/99"
-    ],
-    "PID": "http://hdl.handle.net/11321/99",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Dabrowska, Kaczkowski, Prus, Reymont, Sienkiewicz, Mniszek"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Dabrowska, Dabrowska, Kaczkowski, Prus, Reymont, Sienkiewicz, Mniszek Kaczkowski, Prus, Reymont, Sienkiewicz, Mniszek"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/99;2015-04-08T13:51:22Z;hdl_11321_3;hdl_11321_4;MWE 10 Najwi\u0119kszych;Dabrowska, Dabrowska, Kaczkowski, Prus, Reymont, Sienkiewicz, Mniszek Kaczkowski, Prus, Reymont, Sienkiewicz, Mniszek;dabrowska_nocednie3_1933.txt     \r\nprus_emancypantki_1894.txt  \r\nsienkiewicz_ogniem_1884.txt\r\nkaczkowski_grob_1857.txt         \r\nprus_faraon_1897.txt        \r\nsienkiewicz_rodzina_1894.txt\r\nkaczkowski_olbrachtowi_1889.txt  \r\nprus_lalka_1890.txt\r\nmniszek_gehenna_1914.txt        \r\nreymont_chlopi_1908.txt;2015-04-08;corpus;http://hdl.handle.net/11321/99;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain; charset=utf-8;downloadable_files_count: 10;Dabrowska, Kaczkowski, Prus, Reymont, Sienkiewicz, Mniszek",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "12b1b81a-eef1-57dc-a2cc-e6bc95f0c7a9",
-    "notes": [
-        "dabrowska_nocednie3_1933.txt     \r\nprus_emancypantki_1894.txt  \r\nsienkiewicz_ogniem_1884.txt\r\nkaczkowski_grob_1857.txt         \r\nprus_faraon_1897.txt        \r\nsienkiewicz_rodzina_1894.txt\r\nkaczkowski_olbrachtowi_1889.txt  \r\nprus_lalka_1890.txt\r\nmniszek_gehenna_1914.txt        \r\nreymont_chlopi_1908.txt"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/99"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE 10 Najwi\u0119kszych"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/12cc97c6-d6bc-54af-ac00-89f01cfd95b2.json b/oaitestdata/clarin-oai_dc/SET_1/json/12cc97c6-d6bc-54af-ac00-89f01cfd95b2.json
deleted file mode 100644
index 7e55d6b1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/12cc97c6-d6bc-54af-ac00-89f01cfd95b2.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5139",
-    "MetadataAccess": [
-        "oai:ota:oucs:5139"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Murphy, Arthur, 1727-1805."
-    ],
-    "fulltext": "oai:ota:oucs:5139;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5139.xml;The upholsterer: or what news? A farce, in two acts. As it is performed at the Theatre Royal, in Drury-Lane. By the author of The apprentice.;Murphy, Arthur, 1727-1805.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "12cc97c6-d6bc-54af-ac00-89f01cfd95b2",
-    "oai_identifier": [
-        "oai:ota:oucs:5139"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The upholsterer: or what news? A farce, in two acts. As it is performed at the Theatre Royal, in Drury-Lane. By the author of The apprentice."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5139.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/12eefd71-d56c-54c4-ab9d-4a962f0c9226.json b/oaitestdata/clarin-oai_dc/SET_1/json/12eefd71-d56c-54c4-ab9d-4a962f0c9226.json
deleted file mode 100644
index 4fe37af8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/12eefd71-d56c-54c4-ab9d-4a962f0c9226.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "A"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1683",
-    "MetadataAccess": [
-        "oai:ota:oucs:1683"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Unknown"
-    ],
-    "fulltext": "oai:ota:oucs:1683;2018-04-16T15:30:51Z;http://ota.ox.ac.uk/headers/1683.xml;Octovian;Unknown;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;A;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "12eefd71-d56c-54c4-ab9d-4a962f0c9226",
-    "oai_identifier": [
-        "oai:ota:oucs:1683"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Octovian"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1683.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/12ff6f35-4df6-5bd8-aa41-96ab2619d6e9.json b/oaitestdata/clarin-oai_dc/SET_1/json/12ff6f35-4df6-5bd8-aa41-96ab2619d6e9.json
deleted file mode 100644
index 4cf63ec8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/12ff6f35-4df6-5bd8-aa41-96ab2619d6e9.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-C7FD-6",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-C7FD-6"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0022-C7FD-6",
-    "PublicationTimestamp": "2013-09-10T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Artistic License (Perl) 1.0",
-        "http://opensource.org/licenses/Artistic-Perl-1.0",
-        "PUB"
-    ],
-    "author": [
-        "Sedl\u00e1k, Michal"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-C7FD-6;2018-07-02T22:05:53Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;PMLTQ::Web;Sedl\u00e1k, Michal;Perl;PML-TQ;PML;Simple web build on the top of the PML Tree Query service.;2013-09-10;toolService;http://hdl.handle.net/11858/00-097C-0000-0022-C7FD-6;Artistic License (Perl) 1.0;http://opensource.org/licenses/Artistic-Perl-1.0;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://redmine.ms.mff.cuni.cz/projects/pmltq-web",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "12ff6f35-4df6-5bd8-aa41-96ab2619d6e9",
-    "notes": [
-        "Simple web build on the top of the PML Tree Query service."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-C7FD-6"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Perl"
-        },
-        {
-            "name": "PML-TQ"
-        },
-        {
-            "name": "PML"
-        }
-    ],
-    "title": [
-        "PMLTQ::Web"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/132e1338-fa5e-5df5-a2a8-54d3b8a301ed.json b/oaitestdata/clarin-oai_dc/SET_1/json/132e1338-fa5e-5df5-a2a8-54d3b8a301ed.json
deleted file mode 100644
index 2e923b76..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/132e1338-fa5e-5df5-a2a8-54d3b8a301ed.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "A"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1731",
-    "MetadataAccess": [
-        "oai:ota:oucs:1731"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Collections, corpora etc"
-    ],
-    "fulltext": "oai:ota:oucs:1731;2018-04-16T15:30:51Z;http://ota.ox.ac.uk/headers/1731.xml;Hugo Corpus;Collections, corpora etc;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;A;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "132e1338-fa5e-5df5-a2a8-54d3b8a301ed",
-    "oai_identifier": [
-        "oai:ota:oucs:1731"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Hugo Corpus"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1731.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/135ecc4c-e1b7-597b-8711-ff9f7afc7a28.json b/oaitestdata/clarin-oai_dc/SET_1/json/135ecc4c-e1b7-597b-8711-ff9f7afc7a28.json
deleted file mode 100644
index 018ea34d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/135ecc4c-e1b7-597b-8711-ff9f7afc7a28.json
+++ /dev/null
@@ -1,91 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 3",
-        "application/pdf",
-        "text/html",
-        "application/zip"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0008-E130-A",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0008-E130-A"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0008-E130-A",
-    "PublicationTimestamp": "2012-11-14T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11858/00-097C-0000-0023-1AAF-3"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "M\u00edrovsk\u00fd, Ji\u0159\u00ed",
-        "Nedoluzhko, Anna",
-        "Rysov\u00e1, Magdal\u00e9na",
-        "Pergler, Ji\u0159\u00ed",
-        "Zik\u00e1nov\u00e1, \u0160\u00e1rka",
-        "Haji\u010dov\u00e1, Eva",
-        "Pavl\u00edkov\u00e1, Veronika",
-        "J\u00ednov\u00e1, Pavl\u00edna",
-        "Pol\u00e1kov\u00e1, Lucie",
-        "Zde\u0148kov\u00e1, Jana",
-        "Ocel\u00e1k, Radek"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0008-E130-A;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Prague Discourse Treebank 1.0;Pol\u00e1kov\u00e1, Lucie;J\u00ednov\u00e1, Pavl\u00edna;Zik\u00e1nov\u00e1, \u0160\u00e1rka;Haji\u010dov\u00e1, Eva;M\u00edrovsk\u00fd, Ji\u0159\u00ed;Nedoluzhko, Anna;Rysov\u00e1, Magdal\u00e9na;Pavl\u00edkov\u00e1, Veronika;Zde\u0148kov\u00e1, Jana;Pergler, Ji\u0159\u00ed;Ocel\u00e1k, Radek;discourse;treebank;annotation;Annotation of discourse relations is a project related to the Prague Dependency Treebank 2.5. It represents a new manually annotated layer of language description, above the existing layers of the PDT, and it portrays linguistic phenomena from the perspective of discourse structure and coherence.;2012-11-14;corpus;PDiT 1.0;http://hdl.handle.net/11858/00-097C-0000-0008-E130-A;ces;http://hdl.handle.net/11858/00-097C-0000-0023-1AAF-3;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;text/plain; charset=utf-8;application/zip;text/html;application/pdf;downloadable_files_count: 3;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/discourse/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "135ecc4c-e1b7-597b-8711-ff9f7afc7a28",
-    "notes": [
-        "Annotation of discourse relations is a project related to the Prague Dependency Treebank 2.5. It represents a new manually annotated layer of language description, above the existing layers of the PDT, and it portrays linguistic phenomena from the perspective of discourse structure and coherence."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0008-E130-A"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "discourse"
-        },
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "annotation"
-        }
-    ],
-    "title": [
-        "Prague Discourse Treebank 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1390805c-7f61-5ef8-b554-d716d28fd612.json b/oaitestdata/clarin-oai_dc/SET_1/json/1390805c-7f61-5ef8-b554-d716d28fd612.json
deleted file mode 100644
index f239de34..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1390805c-7f61-5ef8-b554-d716d28fd612.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "French"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-448",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-448"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-448",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "France"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-448;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Lefff 2.0;100.000 entries, text;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-448;fra;downloadable_files_count: 0;France;http://www.labri.fr/perso/clement/lefff/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1390805c-7f61-5ef8-b554-d716d28fd612",
-    "notes": [
-        "100.000 entries, text"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-448"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Lefff 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/139a5b7d-85f7-5cc5-8c54-76b8dde07bfa.json b/oaitestdata/clarin-oai_dc/SET_1/json/139a5b7d-85f7-5cc5-8c54-76b8dde07bfa.json
deleted file mode 100644
index 4be5c1fe..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/139a5b7d-85f7-5cc5-8c54-76b8dde07bfa.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 58.9 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1951",
-    "MetadataAccess": [
-        "oai:ota:oucs:1951"
-    ],
-    "PublicationTimestamp": "1581-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1581"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Peele, George, 1556-1596"
-    ],
-    "fulltext": "oai:ota:oucs:1951;2018-04-16T14:11:10Z;http://ota.ox.ac.uk/headers/1951.xml;The arraignment of Paris / by George Peele;Peele, George, 1556-1596;1581-1584;text_and_corpus_linguistics;Plays -- England -- 16th century;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 58.9 KB);Text;Plays;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "139a5b7d-85f7-5cc5-8c54-76b8dde07bfa",
-    "oai_identifier": [
-        "oai:ota:oucs:1951"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        }
-    ],
-    "title": [
-        "The arraignment of Paris / by George Peele"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1951.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/139c0319-1799-5fb4-8019-d64fee78b328.json b/oaitestdata/clarin-oai_dc/SET_1/json/139c0319-1799-5fb4-8019-d64fee78b328.json
deleted file mode 100644
index 6b795473..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/139c0319-1799-5fb4-8019-d64fee78b328.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4310",
-    "MetadataAccess": [
-        "oai:ota:oucs:4310"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dennis, John, 1657-1734."
-    ],
-    "fulltext": "oai:ota:oucs:4310;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4310.xml;The characters and conduct of Sir John Edgar: and his three deputy-governours. During the adminstration of the late separate ministry. In a third and fourth letter to the Knight. With a picture of Sir John, drawn by a pen, exactly after the life.;Dennis, John, 1657-1734.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "139c0319-1799-5fb4-8019-d64fee78b328",
-    "oai_identifier": [
-        "oai:ota:oucs:4310"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The characters and conduct of Sir John Edgar: and his three deputy-governours. During the adminstration of the late separate ministry. In a third and fourth letter to the Knight. With a picture of Sir John, drawn by a pen, exactly after the life."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4310.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/13f75d80-c670-5dc6-a667-0de82bc2da6b.json b/oaitestdata/clarin-oai_dc/SET_1/json/13f75d80-c670-5dc6-a667-0de82bc2da6b.json
deleted file mode 100644
index a0588d7f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/13f75d80-c670-5dc6-a667-0de82bc2da6b.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "The Danish Language Council",
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml",
-        "text/plain; charset=utf-8",
-        "text/plain",
-        "application/zip",
-        "downloadable_files_count: 15",
-        "application/pdf"
-    ],
-    "Language": [
-        "Danish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repository.clarin.dk:20.500.12115/14",
-    "MetadataAccess": [
-        "oai:repository.clarin.dk:20.500.12115/14"
-    ],
-    "PID": "http://hdl.handle.net/20.500.12115/14",
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "The Danish Language Council",
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN-ACA-NC",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NC=1&NORED=1",
-        "ACA"
-    ],
-    "author": [
-        "Hansen, Dorte Haltrup",
-        "Braasch, Anna",
-        "Olsen, Sussi",
-        "Jakob, Halskov"
-    ],
-    "fulltext": "oai:repository.clarin.dk:20.500.12115/14;2018-06-28T13:25:19Z;hdl_20.500.12115_1;hdl_20.500.12115_3;DK-CLARIN LSP Corpus - Health domain;Olsen, Sussi;Braasch, Anna;Jakob, Halskov;Hansen, Dorte Haltrup;Health;Texts in the Health and Medicine Domain come from netpatient.dk, S\u00f8fartsstyrelsen, Sundhedsstyrelsen, regionH, Libris, Aktuel Naturvidenskab and have been collected in the DK-CLARIN project, WP2.2, 2008 - 2011. \r\nThe corpus consists of 3,972,573 words in 3273 files. \r\nCommunicative setting/Number of files: expert->expert (27) expert->advanced (40) expert->basic (3206).\r\nAll texts are in XML TEIP5 format (TEIP5DKCLARIN-format), with tokenisation, sentence and paragraph segmentation, pos-tagging, lemmatisation and termhood annotation placed in separate text external spangroups. \r\n\"DK-CLARIN LSP Corpus - Health and Medicine domain\" is a part of the Danish DK-CLARIN LSP corpus consisting of seven sub-corpora from following subject domains: Agriculture, Construction, Economics, Environment, Health, IT and Nanotechnology.;2011;corpus;http://hdl.handle.net/20.500.12115/14;dan;CLARIN-ACA-NC;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NC=1&NORED=1;ACA;text/plain; charset=utf-8;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;text/plain;text/xml;text/xml;application/pdf;application/pdf;application/pdf;text/xml;downloadable_files_count: 15;Centre for Language Technology, NorS, University of Copenhagen;The Danish Language Council",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "13f75d80-c670-5dc6-a667-0de82bc2da6b",
-    "notes": [
-        "Texts in the Health and Medicine Domain come from netpatient.dk, S\u00f8fartsstyrelsen, Sundhedsstyrelsen, regionH, Libris, Aktuel Naturvidenskab and have been collected in the DK-CLARIN project, WP2.2, 2008 - 2011. \r\nThe corpus consists of 3,972,573 words in 3273 files. \r\nCommunicative setting/Number of files: expert->expert (27) expert->advanced (40) expert->basic (3206).\r\nAll texts are in XML TEIP5 format (TEIP5DKCLARIN-format), with tokenisation, sentence and paragraph segmentation, pos-tagging, lemmatisation and termhood annotation placed in separate text external spangroups. \r\n\"DK-CLARIN LSP Corpus - Health and Medicine domain\" is a part of the Danish DK-CLARIN LSP corpus consisting of seven sub-corpora from following subject domains: Agriculture, Construction, Economics, Environment, Health, IT and Nanotechnology."
-    ],
-    "oai_identifier": [
-        "oai:repository.clarin.dk:20.500.12115/14"
-    ],
-    "oai_set": [
-        "hdl_20.500.12115_1",
-        "hdl_20.500.12115_3"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Health"
-        }
-    ],
-    "title": [
-        "DK-CLARIN LSP Corpus - Health domain"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/13fc970b-510f-5bf5-8a1b-0767494f1dff.json b/oaitestdata/clarin-oai_dc/SET_1/json/13fc970b-510f-5bf5-8a1b-0767494f1dff.json
deleted file mode 100644
index b59d75fe..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/13fc970b-510f-5bf5-8a1b-0767494f1dff.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4392",
-    "MetadataAccess": [
-        "oai:ota:oucs:4392"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Marat, Jean Paul, 1743-1793."
-    ],
-    "fulltext": "oai:ota:oucs:4392;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4392.xml;Chains of slavery: A work wherein the clandestine and villianous attempts of princes to ruin liberty are pointed out, ...;Chains of slavery. French.;Marat, Jean Paul, 1743-1793.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "13fc970b-510f-5bf5-8a1b-0767494f1dff",
-    "oai_identifier": [
-        "oai:ota:oucs:4392"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Chains of slavery: A work wherein the clandestine and villianous attempts of princes to ruin liberty are pointed out, ...",
-        "Chains of slavery. French."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4392.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/140bdd61-c814-5f89-aff7-8bd6c91e8c11.json b/oaitestdata/clarin-oai_dc/SET_1/json/140bdd61-c814-5f89-aff7-8bd6c91e8c11.json
deleted file mode 100644
index 7b06174d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/140bdd61-c814-5f89-aff7-8bd6c91e8c11.json
+++ /dev/null
@@ -1,88 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Czech",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1480",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1480"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1480",
-    "PublicationTimestamp": "2015-05-19T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/247762",
-        "info:eu-repo/grantAgreement/EC/FP7/610516",
-        "http://hdl.handle.net/11858/00-097C-0000-0023-7AEB-4"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Artistic License 2.0",
-        "http://opensource.org/licenses/Artistic-2.0",
-        "PUB"
-    ],
-    "author": [
-        "Rosa, Rudolf"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1480;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;MSTperl parser (2015-05-19);Rosa, Rudolf;parser;NLP;Treex;parsing;dependency;MSTperl is a Perl reimplementation of the MST parser of Ryan McDonald (http://www.seas.upenn.edu/~strctlrn/MSTParser/MSTParser.html).\r\n\r\nMST parser (Maximum Spanning Tree parser) is a state-of-the-art natural language dependency parser -- a tool that takes a sentence and returns its dependency tree.\r\n\r\nIn MSTperl, only some functionality was implemented; the limitations include the following:\r\nthe parser is a non-projective one, curently with no possibility of enforcing the requirement of projectivity of the parse trees;\r\nonly first-order features are supported, i.e. no second-order or third-order features are possible;\r\nthe implementation of MIRA is that of a single-best MIRA, with a closed-form update instead of using quadratic programming.\r\n\r\nOn the other hand, the parser supports several advanced features:\r\nparallel features, i.e. enriching the parser input with word-aligned sentence in other language;\r\nadding large-scale information, i.e. the feature set enriched with features corresponding to pointwise mutual information of word pairs in a large corpus (CzEng);\r\nweighted/unweighted parser model interpolation;\r\ncombination of several instances of the MSTperl parser (through MST algorithm);\r\ncombination of several existing parses from any parsers (through MST algorithm).\r\n\r\nThe MSTperl parser is tuned for parsing Czech. Trained models are available for Czech, English and German. We can train the parser for other languages on demand, or you can train it yourself -- the guidelines are part of the documentation.\r\n\r\nThe parser, together with detailed documentation, is avalable on CPAN (http://search.cpan.org/~rur/Treex-Parser-MSTperl/).;2015-05-19;toolService;http://hdl.handle.net/11234/1-1480;ces;eng;info:eu-repo/grantAgreement/EC/FP7/247762;info:eu-repo/grantAgreement/EC/FP7/610516;http://hdl.handle.net/11858/00-097C-0000-0023-7AEB-4;Artistic License 2.0;http://opensource.org/licenses/Artistic-2.0;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://ufal.mff.cuni.cz/tools/mstperl-parser",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "140bdd61-c814-5f89-aff7-8bd6c91e8c11",
-    "notes": [
-        "MSTperl is a Perl reimplementation of the MST parser of Ryan McDonald (http://www.seas.upenn.edu/~strctlrn/MSTParser/MSTParser.html).\r\n\r\nMST parser (Maximum Spanning Tree parser) is a state-of-the-art natural language dependency parser -- a tool that takes a sentence and returns its dependency tree.\r\n\r\nIn MSTperl, only some functionality was implemented; the limitations include the following:\r\nthe parser is a non-projective one, curently with no possibility of enforcing the requirement of projectivity of the parse trees;\r\nonly first-order features are supported, i.e. no second-order or third-order features are possible;\r\nthe implementation of MIRA is that of a single-best MIRA, with a closed-form update instead of using quadratic programming.\r\n\r\nOn the other hand, the parser supports several advanced features:\r\nparallel features, i.e. enriching the parser input with word-aligned sentence in other language;\r\nadding large-scale information, i.e. the feature set enriched with features corresponding to pointwise mutual information of word pairs in a large corpus (CzEng);\r\nweighted/unweighted parser model interpolation;\r\ncombination of several instances of the MSTperl parser (through MST algorithm);\r\ncombination of several existing parses from any parsers (through MST algorithm).\r\n\r\nThe MSTperl parser is tuned for parsing Czech. Trained models are available for Czech, English and German. We can train the parser for other languages on demand, or you can train it yourself -- the guidelines are part of the documentation.\r\n\r\nThe parser, together with detailed documentation, is avalable on CPAN (http://search.cpan.org/~rur/Treex-Parser-MSTperl/)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1480"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parser"
-        },
-        {
-            "name": "NLP"
-        },
-        {
-            "name": "Treex"
-        },
-        {
-            "name": "parsing"
-        },
-        {
-            "name": "dependency"
-        }
-    ],
-    "title": [
-        "MSTperl parser (2015-05-19)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/141151c7-355a-5ca4-ace8-b2209b735918.json b/oaitestdata/clarin-oai_dc/SET_1/json/141151c7-355a-5ca4-ace8-b2209b735918.json
deleted file mode 100644
index 1388659e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/141151c7-355a-5ca4-ace8-b2209b735918.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3410",
-    "MetadataAccess": [
-        "oai:ota:oucs:3410"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Sterne, Laurence, 1713-1768."
-    ],
-    "fulltext": "oai:ota:oucs:3410;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3410.xml;A political romance: addressed to - -, Esq. of York. To which is subjoined a key ...;Sterne, Laurence, 1713-1768.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "141151c7-355a-5ca4-ace8-b2209b735918",
-    "oai_identifier": [
-        "oai:ota:oucs:3410"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A political romance: addressed to - -, Esq. of York. To which is subjoined a key ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3410.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/142565e3-d8d0-5600-aa9f-31f0fb409fe8.json b/oaitestdata/clarin-oai_dc/SET_1/json/142565e3-d8d0-5600-aa9f-31f0fb409fe8.json
deleted file mode 100644
index 9deca488..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/142565e3-d8d0-5600-aa9f-31f0fb409fe8.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 99 KB)"
-    ],
-    "Language": [
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0369",
-    "MetadataAccess": [
-        "oai:ota:oucs:0369"
-    ],
-    "PublicationYear": [
-        "384-385"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Addresses"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Symmachus, Quintus Aurelius, d. 405"
-    ],
-    "fulltext": "oai:ota:oucs:0369;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0369.xml;Relationes / Symmachus;Relations;Symmachus, Quintus Aurelius, d. 405;384-385;text_and_corpus_linguistics;Speeches, addresses, etc., Latin -- 4th century;lat;Oxford Text Archive, University of Oxford;(1 file : ca. 99 KB);Text;Addresses;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "142565e3-d8d0-5600-aa9f-31f0fb409fe8",
-    "oai_identifier": [
-        "oai:ota:oucs:0369"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Speeches"
-        },
-        {
-            "name": "addresses"
-        },
-        {
-            "name": "etc."
-        },
-        {
-            "name": "Latin -- th century"
-        }
-    ],
-    "title": [
-        "Relationes / Symmachus",
-        "Relations"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0369.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/143c2732-3a93-5231-b238-8f7442dbe61d.json b/oaitestdata/clarin-oai_dc/SET_1/json/143c2732-3a93-5231-b238-8f7442dbe61d.json
deleted file mode 100644
index 6afa3fc3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/143c2732-3a93-5231-b238-8f7442dbe61d.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Wojciecha Goreckiego"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229213",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229213"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D0C-3",
-    "PublicationTimestamp": "1684-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1684"
-    ],
-    "Publisher": [
-        "Drukarnia Wojciecha Goreckiego"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/229213",
-        "oai:jbc.bj.uj.edu.pl:publication:240854"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1601/1700"
-    ],
-    "TempCoverageBegin": 50506804799,
-    "TempCoverageEnd": 50506804799,
-    "TemporalCoverage": " point in time : 1601-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1601-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1601-07-01T11:59:59Z",
-    "author": [
-        "Grocholicki, Piotr Aleksander ( -1702)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229213;2019-03-01T13:06:44Z;Katechism Katholicki, To Iest Navka Chrzescianska, Wszystkim Wiernym, tylko co do rozumu przyd\u0105, pod dusznym zatraceniem iako naywi\u0119cey si\u0119 iey mog\u0105 nauczy\u0107, pami\u0119ta\u0107 y pod\u0142ug niey si\u0119 sprawowa\u0107 potrzebna : Ktorey Naprzod Duchowni Pasterze, Rodzicy, Nauczyciele ie\u017celi nie vcz\u0105, \u015bmiertelnie grze\u00df\u0105 [...];Grocholicki, Piotr Aleksander ( -1702);starodruki 17\u00a0w.;Ma\u0142achowski, Jan (1623-1699). Adr. ded.;Drukarnia Wojciecha Goreckiego;1684;starodruk;application/xml;clarind-uds:poldilemma-229213;hdl:11858/00-246C-0000-0023-8D0C-3;Biblioteka Jagiello\u0144ska, BJ St. Dr. 35624 I;pol;http://jbc.bj.uj.edu.pl/Content/229213;oai:jbc.bj.uj.edu.pl:publication:240854;1601/1700;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "143c2732-3a93-5231-b238-8f7442dbe61d",
-    "notes": [
-        "Ma\u0142achowski, Jan (1623-1699). Adr. ded."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229213"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Katechism Katholicki, To Iest Navka Chrzescianska, Wszystkim Wiernym, tylko co do rozumu przyd\u0105, pod dusznym zatraceniem iako naywi\u0119cey si\u0119 iey mog\u0105 nauczy\u0107, pami\u0119ta\u0107 y pod\u0142ug niey si\u0119 sprawowa\u0107 potrzebna : Ktorey Naprzod Duchowni Pasterze, Rodzicy, Nauczyciele ie\u017celi nie vcz\u0105, \u015bmiertelnie grze\u00df\u0105 [...]"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1441daca-436c-58e1-b9b5-768a90eb4780.json b/oaitestdata/clarin-oai_dc/SET_1/json/1441daca-436c-58e1-b9b5-768a90eb4780.json
deleted file mode 100644
index 20484aee..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1441daca-436c-58e1-b9b5-768a90eb4780.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=8c13600ccd0711e1a404080027e73ea2f9cfd28f51d5437b8f5827c516c348fe",
-    "MetadataAccess": [
-        "8c13600ccd0711e1a404080027e73ea2f9cfd28f51d5437b8f5827c516c348fe"
-    ],
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "8c13600ccd0711e1a404080027e73ea2f9cfd28f51d5437b8f5827c516c348fe;2019-02-27T12:08:48Z;lexicalConceptualResource;lexicalConceptualResource:lexicon;LEX-MWE-PT: Word Combination in Portuguese Language;This lexicon includes multiword expressions (MWE) of European Portuguese extracted from a balanced 50,8M word written corpus \u00e2\u0080\u0093 a subcorpus of the Reference Corpus of Contemporary Portuguese (CRPC). This corpus covers different genres, being mainly constituted by journalistic texts (59%), but it also includes texts from literature (21%), magazines (15%), miscellaneous, supreme court verdicts, parliament sessions and leaflets (5%). The MWE lexicon covers 1.198 lemmas (composed of single words from different POS categories: nouns, adjectives, verbs and adverbs) and a total of 12.753 MWE lemmas (which include inflectional variants of the MWE lemmas) and 242.233 concordances of those MWE expressions manually verified.;2015-12-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1441daca-436c-58e1-b9b5-768a90eb4780",
-    "notes": [
-        "This lexicon includes multiword expressions (MWE) of European Portuguese extracted from a balanced 50,8M word written corpus \u00e2\u0080\u0093 a subcorpus of the Reference Corpus of Contemporary Portuguese (CRPC). This corpus covers different genres, being mainly constituted by journalistic texts (59%), but it also includes texts from literature (21%), magazines (15%), miscellaneous, supreme court verdicts, parliament sessions and leaflets (5%). The MWE lexicon covers 1.198 lemmas (composed of single words from different POS categories: nouns, adjectives, verbs and adverbs) and a total of 12.753 MWE lemmas (which include inflectional variants of the MWE lemmas) and 242.233 concordances of those MWE expressions manually verified."
-    ],
-    "oai_identifier": [
-        "8c13600ccd0711e1a404080027e73ea2f9cfd28f51d5437b8f5827c516c348fe"
-    ],
-    "oai_set": [
-        "lexicalConceptualResource",
-        "lexicalConceptualResource:lexicon"
-    ],
-    "state": "active",
-    "title": [
-        "LEX-MWE-PT: Word Combination in Portuguese Language"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/144a2a6a-3fea-56f0-9f61-86dcea966fce.json b/oaitestdata/clarin-oai_dc/SET_1/json/144a2a6a-3fea-56f0-9f61-86dcea966fce.json
deleted file mode 100644
index 10f10c48..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/144a2a6a-3fea-56f0-9f61-86dcea966fce.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/92",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/92"
-    ],
-    "PID": "http://hdl.handle.net/10794/92",
-    "PublicationTimestamp": "2013-03-06T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/92;2017-10-25T11:53:28Z;hdl_10794_1;hdl_10794_2;Blog mix 1998 (2017-02-17);Bloggmix 1998 (2017-02-17);n/a, n/a;Swedish;Blog;The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.;Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat.;2013-03-06;corpus;http://hdl.handle.net/10794/92;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/bloggmix1998",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "144a2a6a-3fea-56f0-9f61-86dcea966fce",
-    "notes": [
-        "The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.",
-        "Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/92"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Blog"
-        }
-    ],
-    "title": [
-        "Blog mix 1998 (2017-02-17)",
-        "Bloggmix 1998 (2017-02-17)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/145c5ea9-9a03-5dae-8022-2bf14f8ee38b.json b/oaitestdata/clarin-oai_dc/SET_1/json/145c5ea9-9a03-5dae-8022-2bf14f8ee38b.json
deleted file mode 100644
index f63173a9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/145c5ea9-9a03-5dae-8022-2bf14f8ee38b.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-679",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-679"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-679",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Code of conduct"
-    ],
-    "SpatialCoverage": [
-        "Mexico"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-679;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Lacandon corpus;Documentation of the Lacandon project (DoBeS project);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-679;Code of conduct;downloadable_files_count: 0;Mexico;http://corpus1.mpi.nl/ds/imdi_browser/?openpath=MPI80139%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "145c5ea9-9a03-5dae-8022-2bf14f8ee38b",
-    "notes": [
-        "Documentation of the Lacandon project (DoBeS project)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-679"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Lacandon corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1463f5a9-68f9-5e5b-88ad-03542899cc7d.json b/oaitestdata/clarin-oai_dc/SET_1/json/1463f5a9-68f9-5e5b-88ad-03542899cc7d.json
deleted file mode 100644
index a3b09ae5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1463f5a9-68f9-5e5b-88ad-03542899cc7d.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Delbecque, Nicole"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 109 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0455",
-    "MetadataAccess": [
-        "oai:ota:oucs:0455"
-    ],
-    "PublicationTimestamp": "1965-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1965"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Shaffer, Peter, 1926-"
-    ],
-    "fulltext": "oai:ota:oucs:0455;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0455.xml;Black comedy : a comedy / by Peter Shaffer;Shaffer, Peter, 1926-;1965;text_and_corpus_linguistics;English drama -- 20th century;eng;Oxford Text Archive, University of Oxford;Delbecque, Nicole;(1 file : ca. 109 KB);Text;Plays;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1463f5a9-68f9-5e5b-88ad-03542899cc7d",
-    "oai_identifier": [
-        "oai:ota:oucs:0455"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- th century"
-        }
-    ],
-    "title": [
-        "Black comedy : a comedy / by Peter Shaffer"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0455.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1467289b-5e49-5646-b760-8a1fa9fc0fbd.json b/oaitestdata/clarin-oai_dc/SET_1/json/1467289b-5e49-5646-b760-8a1fa9fc0fbd.json
deleted file mode 100644
index 03302ade..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1467289b-5e49-5646-b760-8a1fa9fc0fbd.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/20",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/20"
-    ],
-    "PID": "http://hdl.handle.net/11321/20",
-    "PublicationTimestamp": "2011-04-05T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "\u015aniatowski, Tomasz",
-        "Radziszewski, Adam"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/20;2016-01-21T14:25:21Z;hdl_11321_3;hdl_11321_4;MACA;Radziszewski, Adam;\u015aniatowski, Tomasz;Utilities are simple programs referencing the corresponding API functions, hence similar functionality may be easily obtained by using the libraries.;2011-04-05;toolService;http://hdl.handle.net/11321/20;pol;downloadable_files_count: 0;Wroc\u0142aw University of Technology;http://nlp.pwr.wroc.pl/redmine/projects/libpltagger/wiki/User_guide",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1467289b-5e49-5646-b760-8a1fa9fc0fbd",
-    "notes": [
-        "Utilities are simple programs referencing the corresponding API functions, hence similar functionality may be easily obtained by using the libraries."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/20"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MACA"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/148753d1-e8ab-55a5-ad80-ac5473ad7d01.json b/oaitestdata/clarin-oai_dc/SET_1/json/148753d1-e8ab-55a5-ad80-ac5473ad7d01.json
deleted file mode 100644
index 47b9b522..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/148753d1-e8ab-55a5-ad80-ac5473ad7d01.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5444",
-    "MetadataAccess": [
-        "oai:ota:oucs:5444"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Francis, Philip, Sir, 1740-1818."
-    ],
-    "fulltext": "oai:ota:oucs:5444;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5444.xml;Speech of Mr. Francis, on the suspension of the Habeas Corpus Act, Friday, January 23, 1795;Francis, Philip, Sir, 1740-1818.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "148753d1-e8ab-55a5-ad80-ac5473ad7d01",
-    "oai_identifier": [
-        "oai:ota:oucs:5444"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Speech of Mr. Francis, on the suspension of the Habeas Corpus Act, Friday, January 23, 1795"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5444.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1496c65b-11f3-509e-9c6a-ab005f7bc664.json b/oaitestdata/clarin-oai_dc/SET_1/json/1496c65b-11f3-509e-9c6a-ab005f7bc664.json
deleted file mode 100644
index 05788a45..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1496c65b-11f3-509e-9c6a-ab005f7bc664.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "McCarty, Willard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(34 files : ca. 2.95 MB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1324",
-    "MetadataAccess": [
-        "oai:ota:oucs:1324"
-    ],
-    "PublicationTimestamp": "1987-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1987"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Anthologies"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:1324;2018-03-07T12:37:09Z;http://ota.ox.ac.uk/headers/1324.xml;The complete Humanist electronic discussion group : 1987-1989;1987-1989;text_and_corpus_linguistics;Linguistic analysis (Linguistics);Computer bulletin boards;Anthologies -- 20th century;eng;Oxford Text Archive, University of Oxford;McCarty, Willard;text/plain;(34 files : ca. 2.95 MB);Text;Anthologies;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1496c65b-11f3-509e-9c6a-ab005f7bc664",
-    "oai_identifier": [
-        "oai:ota:oucs:1324"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Linguistic analysis Linguistics"
-        },
-        {
-            "name": "Computer bulletin boards"
-        },
-        {
-            "name": "Anthologies -- th century"
-        }
-    ],
-    "title": [
-        "The complete Humanist electronic discussion group : 1987-1989"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1324.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/149a7fb6-22f0-5915-9b7e-31844224db33.json b/oaitestdata/clarin-oai_dc/SET_1/json/149a7fb6-22f0-5915-9b7e-31844224db33.json
deleted file mode 100644
index 100256ec..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/149a7fb6-22f0-5915-9b7e-31844224db33.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/gzip",
-        "downloadable_files_count: 4",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish",
-        "Turkmen"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/74",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/74"
-    ],
-    "PID": "http://hdl.handle.net/10794/74",
-    "PublicationTimestamp": "2015-04-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/74;2017-10-31T15:47:14Z;hdl_10794_1;hdl_10794_2;ASPAC \u2013 Swedish-Turkmen (2017-10-16);ASPAC \u2013 svenska-turkmeniska (2017-10-16);n/a, n/a;ASPAC;Parallel;Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.;Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat.;2015-04-16;corpus;http://hdl.handle.net/10794/74;swe;tuk;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/gzip;application/gzip;downloadable_files_count: 4;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/aspacsvtk",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "149a7fb6-22f0-5915-9b7e-31844224db33",
-    "notes": [
-        "Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.",
-        "Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/74"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ASPAC"
-        },
-        {
-            "name": "Parallel"
-        }
-    ],
-    "title": [
-        "ASPAC \u2013 Swedish-Turkmen (2017-10-16)",
-        "ASPAC \u2013 svenska-turkmeniska (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/149ea35c-b0d6-5e11-86db-af6cf3d1eb0a.json b/oaitestdata/clarin-oai_dc/SET_1/json/149ea35c-b0d6-5e11-86db-af6cf3d1eb0a.json
deleted file mode 100644
index ed09543f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/149ea35c-b0d6-5e11-86db-af6cf3d1eb0a.json
+++ /dev/null
@@ -1,181 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 122"
-    ],
-    "Language": [
-        "Afrikaans",
-        "Amharic",
-        "Arabic",
-        "Aragonese",
-        "Asturian",
-        "Azerbaijani",
-        "Belarusian",
-        "Bengali",
-        "Bosnian",
-        "Breton",
-        "Buginese",
-        "Bulgarian",
-        "Catalan",
-        "Cebuano",
-        "Czech",
-        "Chuvash",
-        "Corsican",
-        "Welsh",
-        "Danish",
-        "German",
-        "Modern Greek (1453-)",
-        "English",
-        "Esperanto",
-        "Estonian",
-        "Basque",
-        "Faroese",
-        "Persian",
-        "Finnish",
-        "French",
-        "Western Frisian",
-        "Scottish Gaelic",
-        "Irish",
-        "Galician",
-        "Gujarati",
-        "Haitian",
-        "Hebrew",
-        "Hindi",
-        "Croatian",
-        "Upper Sorbian",
-        "Hungarian",
-        "Armenian",
-        "Ido",
-        "Interlingua (International Auxiliary Language Association)",
-        "Indonesian",
-        "Icelandic",
-        "Italian",
-        "Javanese",
-        "Japanese",
-        "Kannada",
-        "Georgian",
-        "Kazakh",
-        "Korean",
-        "Kurdish",
-        "Latin",
-        "Latvian",
-        "Limburgan",
-        "Lithuanian",
-        "Luxembourgish",
-        "Malayalam",
-        "Marathi",
-        "Macedonian",
-        "Malagasy",
-        "Mongolian",
-        "Maori",
-        "Malay (macrolanguage)",
-        "Burmese",
-        "Neapolitan",
-        "Low German",
-        "Nepali (macrolanguage)",
-        "Newari",
-        "Dutch",
-        "Norwegian Nynorsk",
-        "Norwegian",
-        "Occitan (post 1500)",
-        "Ossetian",
-        "Pampanga",
-        "Polish",
-        "Portuguese",
-        "Quechua",
-        "Romanian",
-        "Russian",
-        "Yakut",
-        "Sicilian",
-        "Scots",
-        "Slovak",
-        "Slovenian",
-        "Spanish",
-        "Albanian",
-        "Serbian",
-        "Sundanese",
-        "Swahili (macrolanguage)",
-        "Swedish",
-        "Tamil",
-        "Tatar",
-        "Telugu",
-        "Tajik",
-        "Tagalog",
-        "Thai",
-        "Turkish",
-        "Ukrainian",
-        "Urdu",
-        "Uzbek",
-        "Vietnamese",
-        "Volap\u00fck",
-        "Waray (Philippines)",
-        "Walloon",
-        "Yiddish",
-        "Yoruba",
-        "Chinese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-6133-9",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-6133-9"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0022-6133-9",
-    "PublicationTimestamp": "2011-12-20T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11858/00-097C-0000-0022-60D6-1"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0)",
-        "http://creativecommons.org/licenses/by-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Majli\u0161, Martin"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-6133-9;2018-07-02T22:05:53Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;W2C \u2013 Web to Corpus \u2013 Corpora;Majli\u0161, Martin;multilingual corpora;A set of corpora for 120 languages automatically collected from wikipedia and the web.\r\n\r\nCollected using the W2C toolset: http://hdl.handle.net/11858/00-097C-0000-0022-60D6-1;2011-12-20;corpus;http://hdl.handle.net/11858/00-097C-0000-0022-6133-9;afr;als;amh;ara;arg;arz;ast;aze;bel;ben;bos;bpy;bre;bug;bul;cat;ceb;ces;chv;cos;cym;dan;deu;diq;ell;eng;epo;est;eus;fao;fas;fin;fra;fry;gan;gla;gle;glg;glk;guj;hat;hbs;heb;hif;hin;hrv;hsb;hun;hye;ido;ina;ind;isl;ita;jav;jpn;kan;kat;kaz;kor;kur;lat;lav;lim;lit;lmo;ltz;mal;mar;mkd;mlg;mon;mri;msa;mya;nap;nds;nep;new;nld;nno;nor;oci;oss;pam;pms;pol;por;que;ron;rus;sah;scn;sco;slk;slv;spa;sqi;srp;sun;swa;swe;tam;tat;tel;tgk;tgl;tha;tur;ukr;urd;uzb;vec;vie;vol;war;wln;yid;yor;zho;http://hdl.handle.net/11858/00-097C-0000-0022-60D6-1;Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0);http://creativecommons.org/licenses/by-sa/3.0/;PUB;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 122;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "149ea35c-b0d6-5e11-86db-af6cf3d1eb0a",
-    "notes": [
-        "A set of corpora for 120 languages automatically collected from wikipedia and the web.\r\n\r\nCollected using the W2C toolset: http://hdl.handle.net/11858/00-097C-0000-0022-60D6-1"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-6133-9"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "multilingual corpora"
-        }
-    ],
-    "title": [
-        "W2C \u2013 Web to Corpus \u2013 Corpora"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/14b306fb-b539-58f6-8497-60431abe13d8.json b/oaitestdata/clarin-oai_dc/SET_1/json/14b306fb-b539-58f6-8497-60431abe13d8.json
deleted file mode 100644
index 921bc95f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/14b306fb-b539-58f6-8497-60431abe13d8.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "IPI PAN"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "downloadable_files_count: 10",
-        "application/vnd.oasis.opendocument.text",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/388",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/388"
-    ],
-    "PID": "http://hdl.handle.net/11321/388",
-    "PublicationTimestamp": "2017-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "IPI PAN"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Siwirska, Anna"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/388;2017-05-30T11:54:56Z;hdl_11321_3;hdl_11321_4;warsztaty_ipipan;Siwirska, Anna;warsztat;pliki;materia\u0142y na warsztaty;2017-05-30;languageDescription;http://hdl.handle.net/11321/388;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;text/plain;application/vnd.oasis.opendocument.text;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;application/vnd.oasis.opendocument.text;application/msword;downloadable_files_count: 10;IPI PAN",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "14b306fb-b539-58f6-8497-60431abe13d8",
-    "notes": [
-        "materia\u0142y na warsztaty"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/388"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "warsztat"
-        },
-        {
-            "name": "pliki"
-        }
-    ],
-    "title": [
-        "warsztaty_ipipan"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/14c4b507-8514-54ef-87d5-389bca4b6777.json b/oaitestdata/clarin-oai_dc/SET_1/json/14c4b507-8514-54ef-87d5-389bca4b6777.json
deleted file mode 100644
index a483f9f7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/14c4b507-8514-54ef-87d5-389bca4b6777.json
+++ /dev/null
@@ -1,94 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/x-tar",
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 6"
-    ],
-    "Language": [
-        "Czech",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1458",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1458"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1458",
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/231720",
-        "info:eu-repo/grantAgreement/EC/FP7/247762",
-        "http://hdl.handle.net/11858/00-097C-0000-0001-4916-9"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "Popel, Martin",
-        "Du\u0161ek, Ond\u0159ej",
-        "Nov\u00e1k, Michal",
-        "Galu\u0161\u010d\u00e1kov\u00e1, Petra",
-        "Mar\u0161\u00edk, Ji\u0159\u00ed",
-        "Bojar, Ond\u0159ej",
-        "Tamchyna, Ale\u0161",
-        "Majli\u0161, Martin",
-        "Mare\u010dek, David"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1458;2018-07-02T22:05:53Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Czech-English Parallel Corpus 1.0 (CzEng 1.0);Bojar, Ond\u0159ej;\u017dabokrtsk\u00fd, Zden\u011bk;Du\u0161ek, Ond\u0159ej;Galu\u0161\u010d\u00e1kov\u00e1, Petra;Majli\u0161, Martin;Mare\u010dek, David;Mar\u0161\u00edk, Ji\u0159\u00ed;Nov\u00e1k, Michal;Popel, Martin;Tamchyna, Ale\u0161;corpus;parallel corpus;treebank;alignment;CzEng 1.0 is the fourth release of a sentence-parallel Czech-English corpus compiled at the Institute of Formal and Applied Linguistics (\u00daFAL) freely available for non-commercial research purposes.\r\n\r\nCzEng 1.0 contains 15 million parallel sentences (233 million English and 206 million Czech tokens) from seven different types of sources automatically annotated at surface and deep (a- and t-) layers of syntactic representation.;2011-12;corpus;http://hdl.handle.net/11234/1-1458;ces;eng;info:eu-repo/grantAgreement/EC/FP7/231720;info:eu-repo/grantAgreement/EC/FP7/247762;http://hdl.handle.net/11858/00-097C-0000-0001-4916-9;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;text/plain; charset=utf-8;downloadable_files_count: 6;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/czeng",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "14c4b507-8514-54ef-87d5-389bca4b6777",
-    "notes": [
-        "CzEng 1.0 is the fourth release of a sentence-parallel Czech-English corpus compiled at the Institute of Formal and Applied Linguistics (\u00daFAL) freely available for non-commercial research purposes.\r\n\r\nCzEng 1.0 contains 15 million parallel sentences (233 million English and 206 million Czech tokens) from seven different types of sources automatically annotated at surface and deep (a- and t-) layers of syntactic representation."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1458"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "parallel corpus"
-        },
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "alignment"
-        }
-    ],
-    "title": [
-        "Czech-English Parallel Corpus 1.0 (CzEng 1.0)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/14e24290-cd00-5513-bb26-393f1e1660ad.json b/oaitestdata/clarin-oai_dc/SET_1/json/14e24290-cd00-5513-bb26-393f1e1660ad.json
deleted file mode 100644
index dbe80415..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/14e24290-cd00-5513-bb26-393f1e1660ad.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4138",
-    "MetadataAccess": [
-        "oai:ota:oucs:4138"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dudley, H. Bate, Sir (Henry Bate), 1745-1824."
-    ],
-    "fulltext": "oai:ota:oucs:4138;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4138.xml;The travellers in Switzerland: A comic opera, in three acts: as performed at the Theatre Royal, Covent Garden. By Mr. Bate Dudley.;Dudley, H. Bate, Sir (Henry Bate), 1745-1824.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "14e24290-cd00-5513-bb26-393f1e1660ad",
-    "oai_identifier": [
-        "oai:ota:oucs:4138"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The travellers in Switzerland: A comic opera, in three acts: as performed at the Theatre Royal, Covent Garden. By Mr. Bate Dudley."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4138.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/14e63973-e0b9-558f-84b3-ee3482fb2d48.json b/oaitestdata/clarin-oai_dc/SET_1/json/14e63973-e0b9-558f-84b3-ee3482fb2d48.json
deleted file mode 100644
index ef098d77..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/14e63973-e0b9-558f-84b3-ee3482fb2d48.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-687",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-687"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-687",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Code of conduct"
-    ],
-    "SpatialCoverage": [
-        "Russia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-687;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Kola-Sami corpus;Documentation of the Kola-Sami corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-687;Code of conduct;downloadable_files_count: 0;Russia;http://corpus1.mpi.nl/ds/imdi_browser/?openpath=MPI363060%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "14e63973-e0b9-558f-84b3-ee3482fb2d48",
-    "notes": [
-        "Documentation of the Kola-Sami corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-687"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Kola-Sami corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/14eac402-8c9d-5998-a947-13f9e0e086c4.json b/oaitestdata/clarin-oai_dc/SET_1/json/14eac402-8c9d-5998-a947-13f9e0e086c4.json
deleted file mode 100644
index 639c19e4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/14eac402-8c9d-5998-a947-13f9e0e086c4.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5645",
-    "MetadataAccess": [
-        "oai:ota:oucs:5645"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Morland, John, M.D."
-    ],
-    "fulltext": "oai:ota:oucs:5645;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5645.xml;A rational account of the causes of chronic diseases: ... By John Morland, M.D.;Morland, John, M.D.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "14eac402-8c9d-5998-a947-13f9e0e086c4",
-    "oai_identifier": [
-        "oai:ota:oucs:5645"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A rational account of the causes of chronic diseases: ... By John Morland, M.D."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5645.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1508f2bf-54bb-5dc3-8d05-d11d4497e3a1.json b/oaitestdata/clarin-oai_dc/SET_1/json/1508f2bf-54bb-5dc3-8d05-d11d4497e3a1.json
deleted file mode 100644
index 007e09ae..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1508f2bf-54bb-5dc3-8d05-d11d4497e3a1.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Wynne, Martin"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-219",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-219"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-219",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-219;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Arts and Humanities Data Service Literature, Languages and Linguistics;Wynne, Martin;Electronic texts, corpora, lexicons. other;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-219;eng;downloadable_files_count: 0;United Kingdom;http://www.ahds.ac.uk/litlangling/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1508f2bf-54bb-5dc3-8d05-d11d4497e3a1",
-    "notes": [
-        "Electronic texts, corpora, lexicons. other"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-219"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Arts and Humanities Data Service Literature, Languages and Linguistics"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/150f0ce7-d2c5-5e1e-b392-d9f08a36737c.json b/oaitestdata/clarin-oai_dc/SET_1/json/150f0ce7-d2c5-5e1e-b392-d9f08a36737c.json
deleted file mode 100644
index f5bdab7a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/150f0ce7-d2c5-5e1e-b392-d9f08a36737c.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Berglund, Ylva"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-446",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-446"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-446",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-446;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;British National Corpus;Berglund, Ylva;General reference corpus; 100 million words; POS, lemma, descriptive metadata;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-446;eng;downloadable_files_count: 0;United Kingdom;http://www.natcorp.ox.ac.uk/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "150f0ce7-d2c5-5e1e-b392-d9f08a36737c",
-    "notes": [
-        "General reference corpus; 100 million words; POS, lemma, descriptive metadata"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-446"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "British National Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1515a981-2de4-5512-ad5a-2baea66ffd6d.json b/oaitestdata/clarin-oai_dc/SET_1/json/1515a981-2de4-5512-ad5a-2baea66ffd6d.json
deleted file mode 100644
index 6e0ecb32..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1515a981-2de4-5512-ad5a-2baea66ffd6d.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Department of Languages and Literatures, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/81",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/81"
-    ],
-    "PID": "http://hdl.handle.net/10794/81",
-    "PublicationTimestamp": "2012-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Department of Languages and Literatures, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/81;2017-10-26T08:12:18Z;hdl_10794_1;hdl_10794_2;Banco de Datos de Prensa Espa\u00f1ola 1977 (SOL) (2014-09-30);Banco de Datos de Prensa Espa\u00f1ola 1977 (SOL) (2014-09-30);n/a, n/a;SOL;Part of SOL - Spanish Online. Sentence scrambled.;Del av SOL - Spanska Online. Materialet \u00e4r meningsomkastat.;2012-05-30;corpus;http://hdl.handle.net/10794/81;spa;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Department of Languages and Literatures, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/pe77",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1515a981-2de4-5512-ad5a-2baea66ffd6d",
-    "notes": [
-        "Part of SOL - Spanish Online. Sentence scrambled.",
-        "Del av SOL - Spanska Online. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/81"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "SOL"
-        }
-    ],
-    "title": [
-        "Banco de Datos de Prensa Espa\u00f1ola 1977 (SOL) (2014-09-30)",
-        "Banco de Datos de Prensa Espa\u00f1ola 1977 (SOL) (2014-09-30)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1516b929-6904-5f77-9fc3-f675cc58d953.json b/oaitestdata/clarin-oai_dc/SET_1/json/1516b929-6904-5f77-9fc3-f675cc58d953.json
deleted file mode 100644
index 5aad8b65..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1516b929-6904-5f77-9fc3-f675cc58d953.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Information Studies Novo mesto"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 8",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1109",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1109"
-    ],
-    "PID": "http://hdl.handle.net/11356/1109",
-    "PublicationTimestamp": "2017-05-09T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Faculty of Information Studies Novo mesto"
-    ],
-    "RelatedIdentifier": [
-        "https://doi.org/10.1007/s10579-018-9413-3"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "https://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Bu\u010dar, Jo\u017ee"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1109;2018-03-12T16:19:19Z;hdl_11356_1023;hdl_11356_1024;Automatically sentiment annotated Slovenian news corpus AutoSentiNews 1.0;Bu\u010dar, Jo\u017ee;news corpus;sentiment classification;opinion mining;The corpus contains 256,567 documents from the Slovenian news portals 24ur, Dnevnik, Finance, Rtvslo, and \u017durnal24. These portals contain political, business, economic and financial content. The submission contains 7 files: 5 of them, which are named after the news portal, contain raw news in txt format retrieved with R crawlers for five Slovenian web media 1.0 (http://hdl.handle.net/11356/1105). The file AutoSentiNews contains of 5 text files that contain 256,567 news articles annotated as positive, negative or neutral at the document level. 1,0427 of them were manually annotated (cf. Manually sentiment annotated Slovenian news corpus SentiNews 1.0, http://hdl.handle.net/11356/1110) and the remaining 246,140 news were annotated automatically. The file SloStopWords contains of 1,784 stop words for Slovene.;2017-05-09;corpus;http://hdl.handle.net/11356/1109;slv;https://doi.org/10.1007/s10579-018-9413-3;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);https://creativecommons.org/licenses/by-sa/4.0/;PUB;text/plain;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;text/plain;text/plain; charset=utf-8;downloadable_files_count: 8;Faculty of Information Studies Novo mesto;https://github.com/19Joey85/Sentiment-annotated-news-corpus-and-sentiment-lexicon-in-Slovene/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1516b929-6904-5f77-9fc3-f675cc58d953",
-    "notes": [
-        "The corpus contains 256,567 documents from the Slovenian news portals 24ur, Dnevnik, Finance, Rtvslo, and \u017durnal24. These portals contain political, business, economic and financial content. The submission contains 7 files: 5 of them, which are named after the news portal, contain raw news in txt format retrieved with R crawlers for five Slovenian web media 1.0 (http://hdl.handle.net/11356/1105). The file AutoSentiNews contains of 5 text files that contain 256,567 news articles annotated as positive, negative or neutral at the document level. 1,0427 of them were manually annotated (cf. Manually sentiment annotated Slovenian news corpus SentiNews 1.0, http://hdl.handle.net/11356/1110) and the remaining 246,140 news were annotated automatically. The file SloStopWords contains of 1,784 stop words for Slovene."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1109"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "news corpus"
-        },
-        {
-            "name": "sentiment classification"
-        },
-        {
-            "name": "opinion mining"
-        }
-    ],
-    "title": [
-        "Automatically sentiment annotated Slovenian news corpus AutoSentiNews 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/151ce722-1629-5ecd-947a-6c7e7f9ddeae.json b/oaitestdata/clarin-oai_dc/SET_1/json/151ce722-1629-5ecd-947a-6c7e7f9ddeae.json
deleted file mode 100644
index da3ff026..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/151ce722-1629-5ecd-947a-6c7e7f9ddeae.json
+++ /dev/null
@@ -1,88 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 5",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Slovak",
-        "Croatian",
-        "Norwegian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1971",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1971"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1971",
-    "PublicationTimestamp": "2017-01-28T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/H2020/644402",
-        "http://web.science.mq.edu.au/~smalmasi/vardial4/pdf/VarDial26.pdf"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "Zeman, Daniel",
-        "Mare\u010dek, David",
-        "Rosa, Rudolf"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1971;2017-11-09T14:21:56Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Slavic Forest, Norwegian Wood (models);Rosa, Rudolf;Zeman, Daniel;Mare\u010dek, David;\u017dabokrtsk\u00fd, Zden\u011bk;parsing;dependency parser;cross-lingual parsing;universal dependencies;Trained models for UDPipe used to produce our final submission to the Vardial 2017 CLP shared task (https://bitbucket.org/hy-crossNLP/vardial2017). The SK model was trained on CS data, the HR model on SL data, and the SV model on a concatenation of DA and NO data. The scripts and commands used to create the models are part of separate submission (http://hdl.handle.net/11234/1-1970).\r\nThe models were trained with UDPipe version 3e65d69 from 3rd Jan 2017, obtained from\r\nhttps://github.com/ufal/udpipe -- their functionality with newer or older versions of UDPipe is not guaranteed.\r\n\r\nWe list here the Bash command sequences that can be used to reproduce our results submitted to VarDial 2017. The input files must be in CoNLLU format. The models only use the form, UPOS, and Universal Features fields (SK only uses the form). You must have UDPipe installed. The feats2FEAT.py script, which prunes the universal features, is bundled with this submission.\r\n\r\nSK -- tag and parse with the model:\r\n\r\nudpipe --tag --parse sk-translex.v2.norm.feats07.w2v.trainonpred.udpipe sk-ud-predPoS-test.conllu\r\n\r\nA slightly better after-deadline model (sk-translex.v2.norm.Case-feats07.w2v.trainonpred.udpipe), which we mention in the accompanying paper, is also included. It is applied in the same way (udpipe --tag --parse sk-translex.v2.norm.Case-feats07.w2v.trainonpred.udpipe sk-ud-predPoS-test.conllu).\r\n\r\nHR -- prune the Features to keep only Case and parse with the model:\r\n\r\npython3 feats2FEAT.py Case < hr-ud-predPoS-test.conllu | udpipe --parse hr-translex.v2.norm.Case.w2v.trainonpred.udpipe\r\n\r\n\r\nNO -- put the UPOS annotation aside, tag Features with the model, merge with the left-aside UPOS annotation, and parse with the model (this hassle is because UDPipe cannot be told to keep UPOS and only change Features):\r\n\r\ncut -f1-4 no-ud-predPoS-test.conllu > tmp\r\n\r\nudpipe --tag no-translex.v2.norm.tgttagupos.srctagfeats.Case.w2v.udpipe no-ud-predPoS-test.conllu | cut -f5- | paste tmp - | sed 's/^\\t$//'  | udpipe --parse no-translex.v2.norm.tgttagupos.srctagfeats.Case.w2v.udpipe;2017-01-28;toolService;http://hdl.handle.net/11234/1-1971;slk;hrv;nor;info:eu-repo/grantAgreement/EC/H2020/644402;http://web.science.mq.edu.au/~smalmasi/vardial4/pdf/VarDial26.pdf;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 5;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "151ce722-1629-5ecd-947a-6c7e7f9ddeae",
-    "notes": [
-        "Trained models for UDPipe used to produce our final submission to the Vardial 2017 CLP shared task (https://bitbucket.org/hy-crossNLP/vardial2017). The SK model was trained on CS data, the HR model on SL data, and the SV model on a concatenation of DA and NO data. The scripts and commands used to create the models are part of separate submission (http://hdl.handle.net/11234/1-1970).\r\nThe models were trained with UDPipe version 3e65d69 from 3rd Jan 2017, obtained from\r\nhttps://github.com/ufal/udpipe -- their functionality with newer or older versions of UDPipe is not guaranteed.\r\n\r\nWe list here the Bash command sequences that can be used to reproduce our results submitted to VarDial 2017. The input files must be in CoNLLU format. The models only use the form, UPOS, and Universal Features fields (SK only uses the form). You must have UDPipe installed. The feats2FEAT.py script, which prunes the universal features, is bundled with this submission.\r\n\r\nSK -- tag and parse with the model:\r\n\r\nudpipe --tag --parse sk-translex.v2.norm.feats07.w2v.trainonpred.udpipe sk-ud-predPoS-test.conllu\r\n\r\nA slightly better after-deadline model (sk-translex.v2.norm.Case-feats07.w2v.trainonpred.udpipe), which we mention in the accompanying paper, is also included. It is applied in the same way (udpipe --tag --parse sk-translex.v2.norm.Case-feats07.w2v.trainonpred.udpipe sk-ud-predPoS-test.conllu).\r\n\r\nHR -- prune the Features to keep only Case and parse with the model:\r\n\r\npython3 feats2FEAT.py Case < hr-ud-predPoS-test.conllu | udpipe --parse hr-translex.v2.norm.Case.w2v.trainonpred.udpipe\r\n\r\n\r\nNO -- put the UPOS annotation aside, tag Features with the model, merge with the left-aside UPOS annotation, and parse with the model (this hassle is because UDPipe cannot be told to keep UPOS and only change Features):\r\n\r\ncut -f1-4 no-ud-predPoS-test.conllu > tmp\r\n\r\nudpipe --tag no-translex.v2.norm.tgttagupos.srctagfeats.Case.w2v.udpipe no-ud-predPoS-test.conllu | cut -f5- | paste tmp - | sed 's/^\\t$//'  | udpipe --parse no-translex.v2.norm.tgttagupos.srctagfeats.Case.w2v.udpipe"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1971"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parsing"
-        },
-        {
-            "name": "dependency parser"
-        },
-        {
-            "name": "cross-lingual parsing"
-        },
-        {
-            "name": "universal dependencies"
-        }
-    ],
-    "title": [
-        "Slavic Forest, Norwegian Wood (models)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/154121c7-fdfa-538e-b196-bb329b6d0653.json b/oaitestdata/clarin-oai_dc/SET_1/json/154121c7-fdfa-538e-b196-bb329b6d0653.json
deleted file mode 100644
index 505087d9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/154121c7-fdfa-538e-b196-bb329b6d0653.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3691",
-    "MetadataAccess": [
-        "oai:ota:oucs:3691"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pope, Alexander, 1688-1744."
-    ],
-    "fulltext": "oai:ota:oucs:3691;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3691.xml;Of the knowledge and characters of men: An epistle to the Right Honourable Richard Lord Viscount Cobham.;Pope, Alexander, 1688-1744.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "154121c7-fdfa-538e-b196-bb329b6d0653",
-    "oai_identifier": [
-        "oai:ota:oucs:3691"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Of the knowledge and characters of men: An epistle to the Right Honourable Richard Lord Viscount Cobham."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3691.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/155e176b-cf09-5085-8c4b-c18ff806e143.json b/oaitestdata/clarin-oai_dc/SET_1/json/155e176b-cf09-5085-8c4b-c18ff806e143.json
deleted file mode 100644
index ed7974d5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/155e176b-cf09-5085-8c4b-c18ff806e143.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "Contributor": [
-        "Woli\u0144ski, Marcin"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-312",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-312"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-312",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Poland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-312;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;\u015awigra;Woli\u0144ski, Marcin;Implementation of \u015awidzi\u0144ski's formal grammar of Polish. Requires a parser (Birnam parser available as a separate tool) and a morphological analyser (no free analyser for Polish; Morfeusz can be used with restrictions - in this case the whole set is available for academic and non-commercial use only).;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-312;pol;downloadable_files_count: 0;Poland;Institute of Computer Science, Polish Academy of Sciences;http://nlp.ipipan.waw.pl/~wolinski/swigra/swigra1.00rc6.zip",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "155e176b-cf09-5085-8c4b-c18ff806e143",
-    "notes": [
-        "Implementation of \u015awidzi\u0144ski's formal grammar of Polish. Requires a parser (Birnam parser available as a separate tool) and a morphological analyser (no free analyser for Polish; Morfeusz can be used with restrictions - in this case the whole set is available for academic and non-commercial use only)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-312"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "\u015awigra"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/156abd64-a374-56ba-a1e4-c405a5095afe.json b/oaitestdata/clarin-oai_dc/SET_1/json/156abd64-a374-56ba-a1e4-c405a5095afe.json
deleted file mode 100644
index 0564dfb6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/156abd64-a374-56ba-a1e4-c405a5095afe.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1004",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1004"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1004",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1004;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LAC Goemai Corpus;Language and Cognition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1004;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI27485%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "156abd64-a374-56ba-a1e4-c405a5095afe",
-    "notes": [
-        "Language and Cognition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1004"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LAC Goemai Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/158468d4-4ca6-57a7-82e7-4bda8fb91c54.json b/oaitestdata/clarin-oai_dc/SET_1/json/158468d4-4ca6-57a7-82e7-4bda8fb91c54.json
deleted file mode 100644
index 367e79c9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/158468d4-4ca6-57a7-82e7-4bda8fb91c54.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Sejm RP"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 30",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/158",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/158"
-    ],
-    "PID": "http://hdl.handle.net/11321/158",
-    "PublicationTimestamp": "2015-04-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Sejm RP"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Sejm RP"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/158;2017-05-29T13:50:46Z;hdl_11321_3;hdl_11321_4;expose 1990-2014;Sejm RP;expose MSZ 1990-2014;2015-04-16;corpus;http://hdl.handle.net/11321/158;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;application/zip;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 30;Sejm RP;C:\\Users\\media\\Dropbox\\Dropbox\\Dropbox\\!WAD\\Expose MSZ 1955-2014\\expose msz 1955-1989\\expose 1955-89 txt",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "158468d4-4ca6-57a7-82e7-4bda8fb91c54",
-    "notes": [
-        "expose MSZ 1990-2014"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/158"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "expose 1990-2014"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/158c17a3-cccd-5004-b8b7-0fe719296511.json b/oaitestdata/clarin-oai_dc/SET_1/json/158c17a3-cccd-5004-b8b7-0fe719296511.json
deleted file mode 100644
index 1ef82e77..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/158c17a3-cccd-5004-b8b7-0fe719296511.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4136",
-    "MetadataAccess": [
-        "oai:ota:oucs:4136"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Murphy, Arthur, 1727-1805."
-    ],
-    "fulltext": "oai:ota:oucs:4136;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4136.xml;Know your own mind: a comedy, performed at the Theatre-Royal, in Covent-Garden.;Murphy, Arthur, 1727-1805.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "158c17a3-cccd-5004-b8b7-0fe719296511",
-    "oai_identifier": [
-        "oai:ota:oucs:4136"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Know your own mind: a comedy, performed at the Theatre-Royal, in Covent-Garden."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4136.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/159a5572-715e-5b90-b597-bffa3e9580d9.json b/oaitestdata/clarin-oai_dc/SET_1/json/159a5572-715e-5b90-b597-bffa3e9580d9.json
deleted file mode 100644
index 1a016736..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/159a5572-715e-5b90-b597-bffa3e9580d9.json
+++ /dev/null
@@ -1,90 +0,0 @@
-{
-    "Contact": [
-        "Bulgarian Academy of Sciences, IICT-BAS",
-        "University of the Basque Country, UPV/EHU",
-        "Faculty of Science, Univeristy of Lisbon, FCUL",
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Basque",
-        "Bulgarian",
-        "Czech",
-        "English",
-        "Portuguese",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1476",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1476"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1476",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Bulgarian Academy of Sciences, IICT-BAS",
-        "University of the Basque Country, UPV/EHU",
-        "Faculty of Science, Univeristy of Lisbon, FCUL",
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/610516"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Branco, Ant\u00f3nio",
-        "Simov, Kiril",
-        "Popel, Martin",
-        "Agirre, Eneko"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1476;2018-07-02T22:05:53Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;QTLeap WSD/NED corpus;Agirre, Eneko;Branco, Ant\u00f3nio;Popel, Martin;Simov, Kiril;annotated corpus;multilingual;This corpora is part of Deliverable 5.5 of the European Commission project QTLeap FP7-ICT-2013.4.1-610516 (http://qtleap.eu). \r\n\r\nThe texts are Q&A interactions from the real-user scenario (batches 1 and 2). The interactions in this corpus are available in Basque, Bulgarian, Czech, English, Portuguese and Spanish. \r\n\r\nThe texts have been automatically annotated with NLP tools, including Word Sense Disambiguation, Named Entity Disambiguation and Coreference resolution. Please check deliverable D5.6 in http://qtleap.eu/deliverables for more information.;2015;corpus;http://hdl.handle.net/11234/1-1476;eus;bul;ces;eng;por;spa;info:eu-repo/grantAgreement/EC/FP7/610516;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;University of the Basque Country, UPV/EHU;Faculty of Science, Univeristy of Lisbon, FCUL;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);Bulgarian Academy of Sciences, IICT-BAS;http://qtleap.eu",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "159a5572-715e-5b90-b597-bffa3e9580d9",
-    "notes": [
-        "This corpora is part of Deliverable 5.5 of the European Commission project QTLeap FP7-ICT-2013.4.1-610516 (http://qtleap.eu). \r\n\r\nThe texts are Q&A interactions from the real-user scenario (batches 1 and 2). The interactions in this corpus are available in Basque, Bulgarian, Czech, English, Portuguese and Spanish. \r\n\r\nThe texts have been automatically annotated with NLP tools, including Word Sense Disambiguation, Named Entity Disambiguation and Coreference resolution. Please check deliverable D5.6 in http://qtleap.eu/deliverables for more information."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1476"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "annotated corpus"
-        },
-        {
-            "name": "multilingual"
-        }
-    ],
-    "title": [
-        "QTLeap WSD/NED corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/15b996f8-75f9-53b5-a7a1-0b5f6f859220.json b/oaitestdata/clarin-oai_dc/SET_1/json/15b996f8-75f9-53b5-a7a1-0b5f6f859220.json
deleted file mode 100644
index 83290981..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/15b996f8-75f9-53b5-a7a1-0b5f6f859220.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Na\u0142kowska"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 4",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/87",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/87"
-    ],
-    "PID": "http://hdl.handle.net/11321/87",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Na\u0142kowska"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Na\u0142kowska, Na\u0142kowska"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/87;2015-04-10T21:06:41Z;hdl_11321_3;hdl_11321_4;MWE Na\u0142kowska;Na\u0142kowska, Na\u0142kowska;Na\u0142kowska;2015-04-08;corpus;http://hdl.handle.net/11321/87;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;application/zip;text/plain; charset=utf-8;downloadable_files_count: 4;Na\u0142kowska",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "15b996f8-75f9-53b5-a7a1-0b5f6f859220",
-    "notes": [
-        "Na\u0142kowska"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/87"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Na\u0142kowska"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/15b9f50d-631e-5a40-9986-117ba87cfdd0.json b/oaitestdata/clarin-oai_dc/SET_1/json/15b9f50d-631e-5a40-9986-117ba87cfdd0.json
deleted file mode 100644
index a099baad..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/15b9f50d-631e-5a40-9986-117ba87cfdd0.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "The Research Institute for the Languages of Finland"
-    ],
-    "Contributor": [
-        "Suutari, Toni",
-        "Ruppel, Klaas"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Finnish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-824",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-824"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-824",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "The Research Institute for the Languages of Finland"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Finland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-824;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Etymological Reference Database;Ruppel, Klaas;Suutari, Toni;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-824;fin;downloadable_files_count: 0;Finland;The Research Institute for the Languages of Finland;http://kaino.kotus.fi/sanat/evita/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "15b9f50d-631e-5a40-9986-117ba87cfdd0",
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-824"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Etymological Reference Database"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/15bfaca9-4521-5373-bf30-b1341afd3903.json b/oaitestdata/clarin-oai_dc/SET_1/json/15bfaca9-4521-5373-bf30-b1341afd3903.json
deleted file mode 100644
index efcfa8b5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/15bfaca9-4521-5373-bf30-b1341afd3903.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4195",
-    "MetadataAccess": [
-        "oai:ota:oucs:4195"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "More, Hannah, 1745-1833."
-    ],
-    "fulltext": "oai:ota:oucs:4195;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4195.xml;Sunday reading. The servant man turned soldier; or, the fair weather Christian, A parable;More, Hannah, 1745-1833.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "15bfaca9-4521-5373-bf30-b1341afd3903",
-    "oai_identifier": [
-        "oai:ota:oucs:4195"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Sunday reading. The servant man turned soldier; or, the fair weather Christian, A parable"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4195.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/15bfc7a1-ed95-5c52-b697-92f57812867a.json b/oaitestdata/clarin-oai_dc/SET_1/json/15bfc7a1-ed95-5c52-b697-92f57812867a.json
deleted file mode 100644
index 86832e23..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/15bfc7a1-ed95-5c52-b697-92f57812867a.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Wojciech Jastrz\u0119bski"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/plain",
-        "downloadable_files_count: 4"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/503",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/503"
-    ],
-    "PID": "http://hdl.handle.net/11321/503",
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wojciech Jastrz\u0119bski"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Super Cool License",
-        "http://www.google.com",
-        "ACA"
-    ],
-    "author": [
-        "Jastrz\u0119bski, Wojciech"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/503;2018-06-19T12:49:04Z;hdl_11321_3;hdl_11321_4;Komentarze do filmu YT \"b\u00f3jka w s\u0105dzie okr\u0119gowym\" testowe;Jastrz\u0119bski, Wojciech;komentarze internetowe;Testowe komentarze do filmu \"b\u00f3jka w s\u0105dzie okr\u0119gowym\" https://www.youtube.com/watch?v=PjToTi5S6Do\r\nkomentarze 1 \"like\" i wi\u0119cej, d\u0142u\u017csze ni\u017c 100 znak\u00f3w;2016;corpus;http://hdl.handle.net/11321/503;pol;Super Cool License;http://www.google.com;ACA;text/plain; charset=utf-8;text/plain;text/plain;text/plain;text/plain;downloadable_files_count: 4;Wojciech Jastrz\u0119bski",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "15bfc7a1-ed95-5c52-b697-92f57812867a",
-    "notes": [
-        "Testowe komentarze do filmu \"b\u00f3jka w s\u0105dzie okr\u0119gowym\" https://www.youtube.com/watch?v=PjToTi5S6Do\r\nkomentarze 1 \"like\" i wi\u0119cej, d\u0142u\u017csze ni\u017c 100 znak\u00f3w"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/503"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "komentarze internetowe"
-        }
-    ],
-    "title": [
-        "Komentarze do filmu YT \"b\u00f3jka w s\u0105dzie okr\u0119gowym\" testowe"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/15bffee5-b38f-5f4a-863c-9ead9ad861c8.json b/oaitestdata/clarin-oai_dc/SET_1/json/15bffee5-b38f-5f4a-863c-9ead9ad861c8.json
deleted file mode 100644
index 46513751..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/15bffee5-b38f-5f4a-863c-9ead9ad861c8.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-993",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-993"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-993",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-993;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LAC Yucatec Corpus;Language and Cognition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-993;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI33036%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "15bffee5-b38f-5f4a-863c-9ead9ad861c8",
-    "notes": [
-        "Language and Cognition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-993"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LAC Yucatec Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/15c8a5f7-a6e5-5ae7-8a54-0aa51ab6c808.json b/oaitestdata/clarin-oai_dc/SET_1/json/15c8a5f7-a6e5-5ae7-8a54-0aa51ab6c808.json
deleted file mode 100644
index 053611f2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/15c8a5f7-a6e5-5ae7-8a54-0aa51ab6c808.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5564",
-    "MetadataAccess": [
-        "oai:ota:oucs:5564"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Brand, Robert."
-    ],
-    "fulltext": "oai:ota:oucs:5564;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5564.xml;The true method of reducing ruptures: and retaining them in the abdomen, and in the navel: ... To which is added, a postscript. By Robert Brand, ...;Brand, Robert.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "15c8a5f7-a6e5-5ae7-8a54-0aa51ab6c808",
-    "oai_identifier": [
-        "oai:ota:oucs:5564"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The true method of reducing ruptures: and retaining them in the abdomen, and in the navel: ... To which is added, a postscript. By Robert Brand, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5564.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/15ea761c-45e4-5ada-aab5-6709d4c874da.json b/oaitestdata/clarin-oai_dc/SET_1/json/15ea761c-45e4-5ada-aab5-6709d4c874da.json
deleted file mode 100644
index db8fb2af..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/15ea761c-45e4-5ada-aab5-6709d4c874da.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "A"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1697",
-    "MetadataAccess": [
-        "oai:ota:oucs:1697"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hawthorne, Nathaniel"
-    ],
-    "fulltext": "oai:ota:oucs:1697;2018-05-17T09:29:11Z;http://ota.ox.ac.uk/headers/1697.xml;The scarlet letter;Hawthorne, Nathaniel;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;A;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "15ea761c-45e4-5ada-aab5-6709d4c874da",
-    "oai_identifier": [
-        "oai:ota:oucs:1697"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The scarlet letter"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1697.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/15fa73b2-5a45-538e-8259-91b37d6502a2.json b/oaitestdata/clarin-oai_dc/SET_1/json/15fa73b2-5a45-538e-8259-91b37d6502a2.json
deleted file mode 100644
index a816a56f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/15fa73b2-5a45-538e-8259-91b37d6502a2.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 7",
-        "text/plain",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1670",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1670"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1670",
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Jur\u010d\u00ed\u010dek, Filip",
-        "Vodol\u00e1n, Miroslav"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1670;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Question Dialogs Dataset;Vodol\u00e1n, Miroslav;Jur\u010d\u00ed\u010dek, Filip;question dialogs;interactive learning;Dataset collected from natural dialogs which enables to test the ability of dialog systems to interactively learn new facts from user utterances throughout the dialog. The dataset, consisting of 1900 dialogs, allows simulation of an interactive gaining of denotations and questions explanations from users which can be used for the interactive learning.;2016;lexicalConceptualResource;http://hdl.handle.net/11234/1-1670;eng;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;PUB;application/octet-stream;application/octet-stream;application/octet-stream;text/plain;application/octet-stream;application/octet-stream;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 7;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "15fa73b2-5a45-538e-8259-91b37d6502a2",
-    "notes": [
-        "Dataset collected from natural dialogs which enables to test the ability of dialog systems to interactively learn new facts from user utterances throughout the dialog. The dataset, consisting of 1900 dialogs, allows simulation of an interactive gaining of denotations and questions explanations from users which can be used for the interactive learning."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1670"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "question dialogs"
-        },
-        {
-            "name": "interactive learning"
-        }
-    ],
-    "title": [
-        "Question Dialogs Dataset"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/161eae44-60a0-5f48-90b8-47bb46ec6a5a.json b/oaitestdata/clarin-oai_dc/SET_1/json/161eae44-60a0-5f48-90b8-47bb46ec6a5a.json
deleted file mode 100644
index 9383bc41..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/161eae44-60a0-5f48-90b8-47bb46ec6a5a.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 412 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1651",
-    "MetadataAccess": [
-        "oai:ota:oucs:1651"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Twain, Mark, 1835-1910"
-    ],
-    "fulltext": "oai:ota:oucs:1651;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1651.xml;The adventures of Tom Sawyer;Twain, Mark, 1835-1910;default: 1976-01-01;text_and_corpus_linguistics;Fiction -- United States -- 19th century;Novels -- United States -- 19th century;eng;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 412 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "161eae44-60a0-5f48-90b8-47bb46ec6a5a",
-    "oai_identifier": [
-        "oai:ota:oucs:1651"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- United States -- th century"
-        },
-        {
-            "name": "Novels -- United States -- th century"
-        }
-    ],
-    "title": [
-        "The adventures of Tom Sawyer"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1651.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/162ed56d-48bb-5e89-9ae1-19fb91e11e8e.json b/oaitestdata/clarin-oai_dc/SET_1/json/162ed56d-48bb-5e89-9ae1-19fb91e11e8e.json
deleted file mode 100644
index dd9e64c3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/162ed56d-48bb-5e89-9ae1-19fb91e11e8e.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Delbecque, Nicole"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 117 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0449",
-    "MetadataAccess": [
-        "oai:ota:oucs:0449"
-    ],
-    "PublicationTimestamp": "1966-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1966"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pinner, David, 1940-"
-    ],
-    "fulltext": "oai:ota:oucs:0449;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0449.xml;Dickon / David Pinner;Pinner, David, 1940-;1966;text_and_corpus_linguistics;English drama -- 20th century;eng;Oxford Text Archive, University of Oxford;Delbecque, Nicole;(1 file : ca. 117 KB);Text;Plays;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "162ed56d-48bb-5e89-9ae1-19fb91e11e8e",
-    "oai_identifier": [
-        "oai:ota:oucs:0449"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- th century"
-        }
-    ],
-    "title": [
-        "Dickon / David Pinner"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0449.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/163e075b-8428-5c03-aad5-358b188fb9b8.json b/oaitestdata/clarin-oai_dc/SET_1/json/163e075b-8428-5c03-aad5-358b188fb9b8.json
deleted file mode 100644
index d67e261d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/163e075b-8428-5c03-aad5-358b188fb9b8.json
+++ /dev/null
@@ -1,113 +0,0 @@
-{
-    "Contact": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 3",
-        "application/zip"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1181",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1181"
-    ],
-    "PID": "http://hdl.handle.net/11356/1181",
-    "PublicationTimestamp": "2018-03-16T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11356/1210",
-        "http://hdl.handle.net/11356/1165"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/"
-    ],
-    "author": [
-        "Krek, Simon",
-        "\u0160krjanec, Iza",
-        "Zupan, Katja",
-        "Arhar Holdt, \u0160pela",
-        "Dobrovoljc, Kaja",
-        "Zajc, Anja",
-        "Erjavec, Toma\u017e",
-        "Kuzman, Taja",
-        "Gantar, Polona",
-        "Ledinek, Nina",
-        "\u010cibej, Jaka",
-        "Jezer\u0161ek, Lucija",
-        "Kav\u010di\u010d, Teja",
-        "Marko, Dafne",
-        "Holz, Nanika",
-        "Mo\u017ee, Sara"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1181;2019-01-26T20:42:21Z;hdl_11356_1023;hdl_11356_1024;Training corpus ssj500k 2.1;Krek, Simon;Dobrovoljc, Kaja;Erjavec, Toma\u017e;Mo\u017ee, Sara;Ledinek, Nina;Holz, Nanika;Zupan, Katja;Gantar, Polona;Kuzman, Taja;\u010cibej, Jaka;Arhar Holdt, \u0160pela;Kav\u010di\u010d, Teja;\u0160krjanec, Iza;Marko, Dafne;Jezer\u0161ek, Lucija;Zajc, Anja;tagging;dependency treebank;parsing;named entities;tokenisation;manual annotation;TEI;verbal multiword expressions;semantic role labelling;The ssj500k training corpus contains about 500,000 tokens manually annotated on the levels of tokenisation, sentence segmentation, morphosyntactic tagging, and lemmatisation. About half of the corpus is also manually annotated with syntactic dependencies, named entities, and verbal multiword expressions. About a quarter of the corpus is annotated with semantic role labels.\r\n\r\nThe annotations of the ssj500k corpus follow (1) the MULTEXT-East V5 morphosyntactic specifications for Slovene, http://nl.ijs.si/ME/V5/msd/, (2) the JOS dependency schema, http://nl.ijs.si/jos/bib/jos-skladnja-navodila.pdf, (3) the Janes annotation guidelines for Slovenian named entities, http://nl.ijs.si/janes/wp-content/uploads/2017/09/SlovenianNER-eng-v1.1.pdf, and (4) the Guidelines of the PARSEME shared task on verbal multiword expressions, http://parsemefr.lif.univ-mrs.fr/parseme-st-guidelines/1.1/\r\nThe vocabulary of (1) and (2) is provided in the back element and (3) and (4) in the teiHeader of the TEI encoded corpus. The semantic role labels are also documented in the teiHeader.;2018-03-16;corpus;http://hdl.handle.net/11356/1181;slv;http://hdl.handle.net/11356/1210;http://hdl.handle.net/11356/1165;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);PUB;https://creativecommons.org/licenses/by-nc-sa/4.0/;text/plain; charset=utf-8;application/zip;application/zip;application/zip;downloadable_files_count: 3;Centre for Language Resources and Technologies, University of Ljubljana;http://eng.slovenscina.eu/tehnologije/ucni-korpus",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "163e075b-8428-5c03-aad5-358b188fb9b8",
-    "notes": [
-        "The ssj500k training corpus contains about 500,000 tokens manually annotated on the levels of tokenisation, sentence segmentation, morphosyntactic tagging, and lemmatisation. About half of the corpus is also manually annotated with syntactic dependencies, named entities, and verbal multiword expressions. About a quarter of the corpus is annotated with semantic role labels.\r\n\r\nThe annotations of the ssj500k corpus follow (1) the MULTEXT-East V5 morphosyntactic specifications for Slovene, http://nl.ijs.si/ME/V5/msd/, (2) the JOS dependency schema, http://nl.ijs.si/jos/bib/jos-skladnja-navodila.pdf, (3) the Janes annotation guidelines for Slovenian named entities, http://nl.ijs.si/janes/wp-content/uploads/2017/09/SlovenianNER-eng-v1.1.pdf, and (4) the Guidelines of the PARSEME shared task on verbal multiword expressions, http://parsemefr.lif.univ-mrs.fr/parseme-st-guidelines/1.1/\r\nThe vocabulary of (1) and (2) is provided in the back element and (3) and (4) in the teiHeader of the TEI encoded corpus. The semantic role labels are also documented in the teiHeader."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1181"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "dependency treebank"
-        },
-        {
-            "name": "parsing"
-        },
-        {
-            "name": "named entities"
-        },
-        {
-            "name": "tokenisation"
-        },
-        {
-            "name": "manual annotation"
-        },
-        {
-            "name": "TEI"
-        },
-        {
-            "name": "verbal multiword expressions"
-        },
-        {
-            "name": "semantic role labelling"
-        }
-    ],
-    "title": [
-        "Training corpus ssj500k 2.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/164bf2b4-b04b-5ad7-997c-6b97a75868a1.json b/oaitestdata/clarin-oai_dc/SET_1/json/164bf2b4-b04b-5ad7-997c-6b97a75868a1.json
deleted file mode 100644
index 8afaa45b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/164bf2b4-b04b-5ad7-997c-6b97a75868a1.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Leibniz Universit\u00e4t Hannover"
-    ],
-    "Contributor": [
-        "Diewald, Prof. Dr. Gabriele"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1130",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1130"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1130",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Leibniz Universit\u00e4t Hannover"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1130;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Kali-Korpus;Diewald, Prof. Dr. Gabriele;Germanistik;Diachronic corpus with focus on annotation and lemmatization of verbal categories; diachrones Korpus mit Fokus auf  Annotation und Lemmatisierung von Verbalkategorien;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1130;deu;downloadable_files_count: 0;Germany;Leibniz Universit\u00e4t Hannover;http://www.kali.uni-hannover.de",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "164bf2b4-b04b-5ad7-997c-6b97a75868a1",
-    "notes": [
-        "Diachronic corpus with focus on annotation and lemmatization of verbal categories; diachrones Korpus mit Fokus auf  Annotation und Lemmatisierung von Verbalkategorien"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1130"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Kali-Korpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1658e5a4-5961-53a1-8dd3-7c6b3d4bf5d5.json b/oaitestdata/clarin-oai_dc/SET_1/json/1658e5a4-5961-53a1-8dd3-7c6b3d4bf5d5.json
deleted file mode 100644
index b9849218..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1658e5a4-5961-53a1-8dd3-7c6b3d4bf5d5.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4264",
-    "MetadataAccess": [
-        "oai:ota:oucs:4264"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "O'Keeffe, John, 1747-1833."
-    ],
-    "fulltext": "oai:ota:oucs:4264;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4264.xml;Wild oats: or, the strolling gentlemen. A comedy, in five acts, as performed at the Theatre Royal, Covent-Garden. By John O'Keefe, Esq.;O'Keeffe, John, 1747-1833.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1658e5a4-5961-53a1-8dd3-7c6b3d4bf5d5",
-    "oai_identifier": [
-        "oai:ota:oucs:4264"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Wild oats: or, the strolling gentlemen. A comedy, in five acts, as performed at the Theatre Royal, Covent-Garden. By John O'Keefe, Esq."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4264.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/165f0948-03fe-541d-b686-e8e1d26f1d5c.json b/oaitestdata/clarin-oai_dc/SET_1/json/165f0948-03fe-541d-b686-e8e1d26f1d5c.json
deleted file mode 100644
index bfd310d0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/165f0948-03fe-541d-b686-e8e1d26f1d5c.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovak"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-AADA-9",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-AADA-9"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0006-AADA-9",
-    "PublicationTimestamp": "2012-05-15T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/231720"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Galu\u0161\u010d\u00e1kov\u00e1, Petra",
-        "Bojar, Ond\u0159ej"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-AADA-9;2018-07-02T22:05:53Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;WMT 2011 Testing Set;Galu\u0161\u010d\u00e1kov\u00e1, Petra;Bojar, Ond\u0159ej;WMT;test data;Slovak;Testing set from WMT 2011 [1] competition, manually translated from Czech and English into Slovak. Test set contains 3003 sentences in Czech, Slovak and English. Test set is described in [2].\r\n\r\nReferences: \r\n[1] http://www.statmt.org/wmt11/evaluation-task.html\r\n[2] Petra Galu\u0161\u010d\u00e1kov\u00e1 and Ond\u0159ej Bojar. Improving SMT by Using Parallel Data of a Closely Related Language. In Human Language Technologies - The Baltic Perspective - Proceedings of the Fifth International Conference Baltic HLT 2012, volume 247 of Frontiers in AI and Applications, pages 58-65, Amsterdam, Netherlands, October 2012. IOS Press.;2012-05-15;lexicalConceptualResource;http://hdl.handle.net/11858/00-097C-0000-0006-AADA-9;slk;info:eu-repo/grantAgreement/EC/FP7/231720;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "165f0948-03fe-541d-b686-e8e1d26f1d5c",
-    "notes": [
-        "Testing set from WMT 2011 [1] competition, manually translated from Czech and English into Slovak. Test set contains 3003 sentences in Czech, Slovak and English. Test set is described in [2].\r\n\r\nReferences: \r\n[1] http://www.statmt.org/wmt11/evaluation-task.html\r\n[2] Petra Galu\u0161\u010d\u00e1kov\u00e1 and Ond\u0159ej Bojar. Improving SMT by Using Parallel Data of a Closely Related Language. In Human Language Technologies - The Baltic Perspective - Proceedings of the Fifth International Conference Baltic HLT 2012, volume 247 of Frontiers in AI and Applications, pages 58-65, Amsterdam, Netherlands, October 2012. IOS Press."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-AADA-9"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "WMT"
-        },
-        {
-            "name": "test data"
-        },
-        {
-            "name": "Slovak"
-        }
-    ],
-    "title": [
-        "WMT 2011 Testing Set"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/16617b77-e6c3-59d5-879c-e4dfae0a7f21.json b/oaitestdata/clarin-oai_dc/SET_1/json/16617b77-e6c3-59d5-879c-e4dfae0a7f21.json
deleted file mode 100644
index ce3339d2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/16617b77-e6c3-59d5-879c-e4dfae0a7f21.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "wolnelektury.pl"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 14",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/438",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/438"
-    ],
-    "PID": "http://hdl.handle.net/11321/438",
-    "PublicationTimestamp": "2017-11-03T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "wolnelektury.pl"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Marciniak, Ma\u0142gorzata"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/438;2017-11-03T18:01:40Z;hdl_11321_3;hdl_11321_4;\"Fatalne jaja\" Bu\u0142hakow;Marciniak, Ma\u0142gorzata;korpus;korpus tekstowy;Story \"Fatallne Jaja\" Michai\u0142 Bu\u0142hakow;2017-11-03;corpus;http://hdl.handle.net/11321/438;pol;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;text/plain; charset=utf-8;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;downloadable_files_count: 14;wolnelektury.pl;http://clarin-pl.eu/pl/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "16617b77-e6c3-59d5-879c-e4dfae0a7f21",
-    "notes": [
-        "Story \"Fatallne Jaja\" Michai\u0142 Bu\u0142hakow"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/438"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "korpus"
-        },
-        {
-            "name": "korpus tekstowy"
-        }
-    ],
-    "title": [
-        "\"Fatalne jaja\" Bu\u0142hakow"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/16621de4-6714-5aed-95ad-18ec67a788ff.json b/oaitestdata/clarin-oai_dc/SET_1/json/16621de4-6714-5aed-95ad-18ec67a788ff.json
deleted file mode 100644
index 706f9003..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/16621de4-6714-5aed-95ad-18ec67a788ff.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "application/pdf",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1199",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1199"
-    ],
-    "PID": "http://hdl.handle.net/11356/1199",
-    "PublicationTimestamp": "2018-08-18T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "https://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Bitenc, Maja",
-        "Erjavec, Toma\u017e",
-        "Fi\u0161er, Darja",
-        "Ljube\u0161i\u0107, Nikola"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1199;2018-08-18T16:17:39Z;hdl_11356_1023;hdl_11356_1024;Bilingual terminology extraction dataset KAS-biterm 1.0;Erjavec, Toma\u017e;Fi\u0161er, Darja;Ljube\u0161i\u0107, Nikola;Bitenc, Maja;terminology;manual annotation;The KAS-biterm bilingual term extraction dataset contains complete sentences selected from PhD theses from the KAS corpus of Slovene academic writing. Only sentences that have a high chance of containing the term in the original language and its translation into Slovene were chosen, by using three CQL patterms in noSketch Engine. These sentences are manually annotated for (1) terms, (2) partial terms and (3) abbreviations in (a) Slovene, (b) English, or (c) other language. Links between the Slovene terms and their equivalents in the other languages, as well as their abbreviations, are encoded as well.\r\nThe resource can serve as a training set for supervised learning of bilingual term extraction tools and their benchmarking.;2018-08-18;corpus;http://hdl.handle.net/11356/1199;slv;eng;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);https://creativecommons.org/licenses/by-sa/4.0/;PUB;application/zip;application/pdf;text/plain; charset=utf-8;downloadable_files_count: 2;Jo\u017eef Stefan Institute;http://nl.ijs.si/kas/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "16621de4-6714-5aed-95ad-18ec67a788ff",
-    "notes": [
-        "The KAS-biterm bilingual term extraction dataset contains complete sentences selected from PhD theses from the KAS corpus of Slovene academic writing. Only sentences that have a high chance of containing the term in the original language and its translation into Slovene were chosen, by using three CQL patterms in noSketch Engine. These sentences are manually annotated for (1) terms, (2) partial terms and (3) abbreviations in (a) Slovene, (b) English, or (c) other language. Links between the Slovene terms and their equivalents in the other languages, as well as their abbreviations, are encoded as well.\r\nThe resource can serve as a training set for supervised learning of bilingual term extraction tools and their benchmarking."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1199"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "terminology"
-        },
-        {
-            "name": "manual annotation"
-        }
-    ],
-    "title": [
-        "Bilingual terminology extraction dataset KAS-biterm 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/168def6f-2936-5039-9706-ceb70419c4f7.json b/oaitestdata/clarin-oai_dc/SET_1/json/168def6f-2936-5039-9706-ceb70419c4f7.json
deleted file mode 100644
index 87239623..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/168def6f-2936-5039-9706-ceb70419c4f7.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-990",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-990"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-990",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-990;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LAC Miranya Corpus;Language and Cognition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-990;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI33492%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "168def6f-2936-5039-9706-ceb70419c4f7",
-    "notes": [
-        "Language and Cognition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-990"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LAC Miranya Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/168ff16f-5195-58a6-b916-c5eb88dab547.json b/oaitestdata/clarin-oai_dc/SET_1/json/168ff16f-5195-58a6-b916-c5eb88dab547.json
deleted file mode 100644
index c6287cf5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/168ff16f-5195-58a6-b916-c5eb88dab547.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4714",
-    "MetadataAccess": [
-        "oai:ota:oucs:4714"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hume, David, 1711-1776."
-    ],
-    "fulltext": "oai:ota:oucs:4714;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4714.xml;The life of David Hume, Esq: Written by himself. To which is added, a letter from Adam Smith, LL.D. to William Strahan, Esq.;Hume, David, 1711-1776.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "168ff16f-5195-58a6-b916-c5eb88dab547",
-    "oai_identifier": [
-        "oai:ota:oucs:4714"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The life of David Hume, Esq: Written by himself. To which is added, a letter from Adam Smith, LL.D. to William Strahan, Esq."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4714.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/16941cd9-fdc6-558f-af12-b8fc303e56f8.json b/oaitestdata/clarin-oai_dc/SET_1/json/16941cd9-fdc6-558f-af12-b8fc303e56f8.json
deleted file mode 100644
index 0b999a60..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/16941cd9-fdc6-558f-af12-b8fc303e56f8.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "IPS"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/plain",
-        "downloadable_files_count: 96"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/517",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/517"
-    ],
-    "PID": "http://hdl.handle.net/11321/517",
-    "PublicationTimestamp": "2018-07-06T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "IPS"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Kowalska, Agata"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/517;2018-07-13T13:51:15Z;hdl_11321_3;hdl_11321_4;Warsztat;Kowalska, Agata;warsztaty nauka;warsztaat;J\u0119zyk warsztat\u00f3w;2018-07-06;corpus;http://hdl.handle.net/11321/517;pol;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;downloadable_files_count: 96;IPS",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "16941cd9-fdc6-558f-af12-b8fc303e56f8",
-    "notes": [
-        "J\u0119zyk warsztat\u00f3w"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/517"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "warsztaty nauka"
-        },
-        {
-            "name": "warsztaat"
-        }
-    ],
-    "title": [
-        "Warsztat"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/16bd32c0-16c4-5897-a5f2-121766797239.json b/oaitestdata/clarin-oai_dc/SET_1/json/16bd32c0-16c4-5897-a5f2-121766797239.json
deleted file mode 100644
index b1c62459..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/16bd32c0-16c4-5897-a5f2-121766797239.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1149",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1149"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1149",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1149;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Deutsches W\u00f6rterbuch - The Free Dictionary;Germanistik;Angabe von grammatischen Informationen, Worterkl\u00e4rungen, typischen (syntaktischen) Verbindungen, idiomatischen Wendungen und Beispiels\u00e4tzen; M\u00f6glichkeit, sich \u00dcbersetzungen des jeweiligen Wortes anzeigen zu lassen;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1149;deu;downloadable_files_count: 0;http://de.thefreedictionary.com/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "16bd32c0-16c4-5897-a5f2-121766797239",
-    "notes": [
-        "Angabe von grammatischen Informationen, Worterkl\u00e4rungen, typischen (syntaktischen) Verbindungen, idiomatischen Wendungen und Beispiels\u00e4tzen; M\u00f6glichkeit, sich \u00dcbersetzungen des jeweiligen Wortes anzeigen zu lassen"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1149"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Deutsches W\u00f6rterbuch - The Free Dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/16c704c2-1eb0-5ffb-8d95-8d5746be83d3.json b/oaitestdata/clarin-oai_dc/SET_1/json/16c704c2-1eb0-5ffb-8d95-8d5746be83d3.json
deleted file mode 100644
index 9705f048..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/16c704c2-1eb0-5ffb-8d95-8d5746be83d3.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4432",
-    "MetadataAccess": [
-        "oai:ota:oucs:4432"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Mendez, Moses, d. 1758."
-    ],
-    "fulltext": "oai:ota:oucs:4432;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4432.xml;The shepherds lottery. A musical entertainment: As it is perform'd by His Majesty's Company of comedians at the Theatre-Royal in Drury-Lane. The music compos'd by Dr. Boyce.;Mendez, Moses, d. 1758.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "16c704c2-1eb0-5ffb-8d95-8d5746be83d3",
-    "oai_identifier": [
-        "oai:ota:oucs:4432"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The shepherds lottery. A musical entertainment: As it is perform'd by His Majesty's Company of comedians at the Theatre-Royal in Drury-Lane. The music compos'd by Dr. Boyce."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4432.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/16ed0185-616c-5dc5-92ac-f04a9f28f039.json b/oaitestdata/clarin-oai_dc/SET_1/json/16ed0185-616c-5dc5-92ac-f04a9f28f039.json
deleted file mode 100644
index e3d4b28a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/16ed0185-616c-5dc5-92ac-f04a9f28f039.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Roventini, Adriana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-471",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-471"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-471",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Italy"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-471;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;ItalWordNet;Roventini, Adriana;50.000 synsets, XML;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-471;ita;downloadable_files_count: 0;Italy;http://www.ilc.cnr.it/iwndb_php/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "16ed0185-616c-5dc5-92ac-f04a9f28f039",
-    "notes": [
-        "50.000 synsets, XML"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-471"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "ItalWordNet"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/16ff7861-4040-55a1-93fa-7e0a91455800.json b/oaitestdata/clarin-oai_dc/SET_1/json/16ff7861-4040-55a1-93fa-7e0a91455800.json
deleted file mode 100644
index 9b03192f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/16ff7861-4040-55a1-93fa-7e0a91455800.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "School of Languages, Cultures & Linguistics, Monash University"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-720",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-720"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-720",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "School of Languages, Cultures & Linguistics, Monash University"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Code of conduct"
-    ],
-    "SpatialCoverage": [
-        "Papua New Guinea"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-720;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Saliba / Logea corpus;Documentation of the Saliba and Logea project (DoBeS project);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-720;Code of conduct;downloadable_files_count: 0;Papua New Guinea;School of Languages, Cultures & Linguistics, Monash University;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI529540%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "16ff7861-4040-55a1-93fa-7e0a91455800",
-    "notes": [
-        "Documentation of the Saliba and Logea project (DoBeS project)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-720"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Saliba / Logea corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1717a74a-bc54-5677-90ac-a418a8607da5.json b/oaitestdata/clarin-oai_dc/SET_1/json/1717a74a-bc54-5677-90ac-a418a8607da5.json
deleted file mode 100644
index 0c72ce29..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1717a74a-bc54-5677-90ac-a418a8607da5.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Baumann, Walter"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 576 KB)"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1663",
-    "MetadataAccess": [
-        "oai:ota:oucs:1663"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Goethe, Johann Wolfgang von, 1749-1832"
-    ],
-    "fulltext": "oai:ota:oucs:1663;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1663.xml;Faust;Faust / Johann Wolfgang von Goethe;Goethe, Johann Wolfgang von, 1749-1832;text_and_corpus_linguistics;German drama (Tragedy) -- 18th century;deu;Oxford Text Archive, University of Oxford;Baumann, Walter;text/sgml;(1 file : ca. 576 KB);Text;Plays;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1717a74a-bc54-5677-90ac-a418a8607da5",
-    "oai_identifier": [
-        "oai:ota:oucs:1663"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "German drama Tragedy -- th century"
-        }
-    ],
-    "title": [
-        "Faust",
-        "Faust / Johann Wolfgang von Goethe"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1663.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1737d017-d059-5010-a5d4-73ef7d9fc620.json b/oaitestdata/clarin-oai_dc/SET_1/json/1737d017-d059-5010-a5d4-73ef7d9fc620.json
deleted file mode 100644
index 54a8d09d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1737d017-d059-5010-a5d4-73ef7d9fc620.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4345",
-    "MetadataAccess": [
-        "oai:ota:oucs:4345"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Holcroft, Thomas, 1745-1809."
-    ],
-    "fulltext": "oai:ota:oucs:4345;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4345.xml;The family picture; or, domestic dialogues on amiable and interesting subjects; ... By Thomas Holcroft,: [pt.1];Holcroft, Thomas, 1745-1809.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1737d017-d059-5010-a5d4-73ef7d9fc620",
-    "oai_identifier": [
-        "oai:ota:oucs:4345"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The family picture; or, domestic dialogues on amiable and interesting subjects; ... By Thomas Holcroft,: [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4345.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/174ec81c-9498-554d-8db9-0f72783168d1.json b/oaitestdata/clarin-oai_dc/SET_1/json/174ec81c-9498-554d-8db9-0f72783168d1.json
deleted file mode 100644
index 4428a1a7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/174ec81c-9498-554d-8db9-0f72783168d1.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "NLX-Natural Language and Speech Group, University of Lisbon"
-    ],
-    "Contributor": [
-        "Branco, Ant\u00f3nio",
-        "Silva, Jo\u00e3o"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Portuguese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1227",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1227"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1227",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "NLX-Natural Language and Speech Group, University of Lisbon"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Portugal"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1227;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LX-Splitter;Branco, Ant\u00f3nio;Silva, Jo\u00e3o;Automatic segmenter of paragraphs and sentences of Portuguese. Marks sentence boundaries with s\u2026/s, and paragraph boundaries with p\u2026/p. Unwraps sentences split over different lines. A f-score of 99.94% was obtained when testing on a 12,000 sentence corpus accurately hand tagged with respect to sentence and paragraph boundaries.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1227;por;downloadable_files_count: 0;Portugal;NLX-Natural Language and Speech Group, University of Lisbon;http://lxsuite.di.fc.ul.pt/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "174ec81c-9498-554d-8db9-0f72783168d1",
-    "notes": [
-        "Automatic segmenter of paragraphs and sentences of Portuguese. Marks sentence boundaries with s\u2026/s, and paragraph boundaries with p\u2026/p. Unwraps sentences split over different lines. A f-score of 99.94% was obtained when testing on a 12,000 sentence corpus accurately hand tagged with respect to sentence and paragraph boundaries."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1227"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LX-Splitter"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/174f9369-075f-58ee-90cc-0b1763460ca1.json b/oaitestdata/clarin-oai_dc/SET_1/json/174f9369-075f-58ee-90cc-0b1763460ca1.json
deleted file mode 100644
index b2f51142..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/174f9369-075f-58ee-90cc-0b1763460ca1.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "British Academy and the University of Wales, Bangor"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3021",
-    "MetadataAccess": [
-        "oai:ota:oucs:3021"
-    ],
-    "PublicationTimestamp": "1645-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1645"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Milton, John, 1608-1674"
-    ],
-    "fulltext": "oai:ota:oucs:3021;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3021.xml;Poems of Mr. John Milton, both English and\n\tLatin, and, A maske of the same author [1645];Milton, John, 1608-1674;not after: 1645;text_and_corpus_linguistics;English poetry -- 17th century;eng;Oxford Text Archive, University of Oxford;British Academy and the University of Wales, Bangor;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "174f9369-075f-58ee-90cc-0b1763460ca1",
-    "oai_identifier": [
-        "oai:ota:oucs:3021"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English poetry -- th century"
-        }
-    ],
-    "title": [
-        "Poems of Mr. John Milton, both English and\n\tLatin, and, A maske of the same author [1645]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3021.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/17739076-5e49-559c-81f1-f37ac6ed9aaa.json b/oaitestdata/clarin-oai_dc/SET_1/json/17739076-5e49-559c-81f1-f37ac6ed9aaa.json
deleted file mode 100644
index ed445976..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/17739076-5e49-559c-81f1-f37ac6ed9aaa.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "J. K. Mci v Rzeczypospolitey XX. Scholarum Piarum"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-6368",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-6368"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D30-D",
-    "PublicationTimestamp": "1782-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1782"
-    ],
-    "Publisher": [
-        "J. K. Mci v Rzeczypospolitey XX. Scholarum Piarum"
-    ],
-    "RelatedIdentifier": [
-        "http://dlibra.bibliotekaelblaska.pl/Content/6368",
-        "oai:dlibra.bibliotekaelblaska.pl:publication:6264"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "author": [
-        "Ostrowski Teodor"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-6368;2019-03-01T17:26:33Z;Inwentarz praw, traktatow y konstytucyi koronnych y W. X. Lit. Od Sejmu Konwokacyinego w R. 1764\u2026.;Ostrowski Teodor;s\u0105downictwo;prawo karne;Towarzystwo Prawnicze;Ostrowski, Teodor;Teodor Ostrowski, historyk i prawnik polski (1750 \u20141802), pijar, profesor Collegium Nobilium i Korpusu kadet\u00f3w. Powo\u0142any przez Sejm Czteroletni do deputacji, kt\u00f3ra mia\u0142a u\u0142o\u017cy\u0107 kodeks cywilny i karny. Tw\u00f3rca prawa s\u0105dowego (proces, prawo prywatne i karne). Przedstawiciel my\u015bli humanitarnej epoki stanis\u0142awowskiej. Czynny uczestnik Towarzystwa Prawniczego. Jego dzie\u0142o \u201eInwentarz praw\u2026\u201d to synteza prawa polskiego. Druk wydany w drukarni J. K. Mci v Rzeczypospolitey XX. Scholarum Piarum w Warszawie. Format 2\u00b0.;J. K. Mci v Rzeczypospolitey XX. Scholarum Piarum;1782;starodruk;application/xml;clarind-uds:poldilemma-6368;hdl:11858/00-246C-0000-0023-8D30-D;XVIII. 3;pol;lat;http://dlibra.bibliotekaelblaska.pl/Content/6368;oai:dlibra.bibliotekaelblaska.pl:publication:6264;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "17739076-5e49-559c-81f1-f37ac6ed9aaa",
-    "notes": [
-        "Teodor Ostrowski, historyk i prawnik polski (1750 \u20141802), pijar, profesor Collegium Nobilium i Korpusu kadet\u00f3w. Powo\u0142any przez Sejm Czteroletni do deputacji, kt\u00f3ra mia\u0142a u\u0142o\u017cy\u0107 kodeks cywilny i karny. Tw\u00f3rca prawa s\u0105dowego (proces, prawo prywatne i karne). Przedstawiciel my\u015bli humanitarnej epoki stanis\u0142awowskiej. Czynny uczestnik Towarzystwa Prawniczego. Jego dzie\u0142o \u201eInwentarz praw\u2026\u201d to synteza prawa polskiego. Druk wydany w drukarni J. K. Mci v Rzeczypospolitey XX. Scholarum Piarum w Warszawie. Format 2\u00b0."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-6368"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "prawo karne"
-        },
-        {
-            "name": "Towarzystwo Prawnicze"
-        },
-        {
-            "name": "Ostrowski"
-        },
-        {
-            "name": "Teodor"
-        }
-    ],
-    "title": [
-        "Inwentarz praw, traktatow y konstytucyi koronnych y W. X. Lit. Od Sejmu Konwokacyinego w R. 1764\u2026."
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/177523f6-912a-5f8f-8570-8e9f9939ed92.json b/oaitestdata/clarin-oai_dc/SET_1/json/177523f6-912a-5f8f-8570-8e9f9939ed92.json
deleted file mode 100644
index 88031654..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/177523f6-912a-5f8f-8570-8e9f9939ed92.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia JKM y Rzeczypospolitey Scholarum Piarum"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-2782",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-2782"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D14-F",
-    "PublicationTimestamp": "1765-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1765"
-    ],
-    "Publisher": [
-        "Drukarnia JKM y Rzeczypospolitey Scholarum Piarum"
-    ],
-    "RelatedIdentifier": [
-        "http://pbc.biaman.pl/Content/2782"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "author": [
-        "\u015amiglecki, Marcin (ca 1560 - 1619)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-2782;2019-03-01T13:29:02Z;Uwagi potrzebne do przestrogi i Sumienia Wiernym Chrystusowym wszelkiego dostoje\u0144stwa Urz\u0119du i Stanu zw\u0142aszcza do rad publicznych y do s\u0105d\u00f3w nale\u017c\u0105cych;\u015amiglecki, Marcin (ca 1560 - 1619);ilo\u015b\u0107 skan\u00f3w: 29 ; sygn. S-1075;Drukarnia JKM y Rzeczypospolitey Scholarum Piarum;1765;starodruk;application/xml;clarind-uds:poldilemma-2782;hdl:11858/00-246C-0000-0023-8D14-F;pol;lat;http://pbc.biaman.pl/Content/2782;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "177523f6-912a-5f8f-8570-8e9f9939ed92",
-    "notes": [
-        "ilo\u015b\u0107 skan\u00f3w: 29 ; sygn. S-1075"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-2782"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "title": [
-        "Uwagi potrzebne do przestrogi i Sumienia Wiernym Chrystusowym wszelkiego dostoje\u0144stwa Urz\u0119du i Stanu zw\u0142aszcza do rad publicznych y do s\u0105d\u00f3w nale\u017c\u0105cych"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/17b17195-baa8-5807-9edb-d5e29add903d.json b/oaitestdata/clarin-oai_dc/SET_1/json/17b17195-baa8-5807-9edb-d5e29add903d.json
deleted file mode 100644
index dd2f9210..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/17b17195-baa8-5807-9edb-d5e29add903d.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "European Language Resources Association (ELRA)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2884",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2884"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2884",
-    "PublicationTimestamp": "2018-05-07T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "European Language Resources Association (ELRA)"
-    ],
-    "RelatedIdentifier": [
-        "http://www.lrec-conf.org/proceedings/lrec2018/summaries/671.html"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Kr\u00e1l, Pavel",
-        "Lenc, Ladislav"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2884;2018-11-16T07:43:15Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Czech Text Document Corpus v 2.0;Kr\u00e1l, Pavel;Lenc, Ladislav;corpus;Czech;document classification;multi-label;text;BASIC INFORMATION\r\n--------------------\r\nCzech Text Document Corpus v 2.0 is a collection of text documents for automatic document classification in Czech language. It is composed of the text documents provided by the Czech News Agency and is freely available for research purposes. This corpus was created in order to facilitate a straightforward comparison of the document classification approaches on Czech data. It is particularly dedicated to evaluation of multi-label document classification approaches, because one document is usually labelled with more than one label. Besides the information about the document classes, the corpus is also annotated at the morphological layer.\r\n\r\nThe main part (for training and testing) is composed of 11,955 real newspaper articles. We provide also a development set which is intended to be used for tuning of the hyper-parameters of the created models. This set contains 2735 additional articles.\r\n\r\nThe total category number is 60 out of which 37 most frequent ones are used for classification. The reason of this reduction is to keep only the classes with the sufficient number of occurrences to train the models.\r\n\r\nTechnical Details\r\n------------------------\r\nText documents are stored in the individual text files using UTF-8 encoding. Each filename is composed of the serial number and the list of the categories abbreviations separated by the underscore symbol and the .txt suffix. Serial numbers are composed of five digits and the numerical series starts from the value one.\r\n\r\nFor instance the file 00046_kul_nab_mag.txt represents the document file number 46 annotated by the categories kul (culture), nab (religion) and mag (magazine selection). The content of the document, i.e. the word tokens, is stored in one line. The tokens are separated by the space symbols.\r\n\r\nEvery text document was further automatically mophologically analyzed. This analysis includes lemmatization, POS tagging and syntactic parsing. The fully annotated files are stored in .conll files. We also provide the lemmatized form, file with suffix .lemma, and appropriate POS-tags, see .pos files. The tokenized version of the documents is also available in .tok files.\r\n\r\nThis corpus is available only for research purposes for free. Commercial use in any form is strictly excluded.;2018-05-07;corpus;http://hdl.handle.net/11234/1-2884;ces;http://www.lrec-conf.org/proceedings/lrec2018/summaries/671.html;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;European Language Resources Association (ELRA);http://ctdc.kiv.zcu.cz/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "17b17195-baa8-5807-9edb-d5e29add903d",
-    "notes": [
-        "BASIC INFORMATION\r\n--------------------\r\nCzech Text Document Corpus v 2.0 is a collection of text documents for automatic document classification in Czech language. It is composed of the text documents provided by the Czech News Agency and is freely available for research purposes. This corpus was created in order to facilitate a straightforward comparison of the document classification approaches on Czech data. It is particularly dedicated to evaluation of multi-label document classification approaches, because one document is usually labelled with more than one label. Besides the information about the document classes, the corpus is also annotated at the morphological layer.\r\n\r\nThe main part (for training and testing) is composed of 11,955 real newspaper articles. We provide also a development set which is intended to be used for tuning of the hyper-parameters of the created models. This set contains 2735 additional articles.\r\n\r\nThe total category number is 60 out of which 37 most frequent ones are used for classification. The reason of this reduction is to keep only the classes with the sufficient number of occurrences to train the models.\r\n\r\nTechnical Details\r\n------------------------\r\nText documents are stored in the individual text files using UTF-8 encoding. Each filename is composed of the serial number and the list of the categories abbreviations separated by the underscore symbol and the .txt suffix. Serial numbers are composed of five digits and the numerical series starts from the value one.\r\n\r\nFor instance the file 00046_kul_nab_mag.txt represents the document file number 46 annotated by the categories kul (culture), nab (religion) and mag (magazine selection). The content of the document, i.e. the word tokens, is stored in one line. The tokens are separated by the space symbols.\r\n\r\nEvery text document was further automatically mophologically analyzed. This analysis includes lemmatization, POS tagging and syntactic parsing. The fully annotated files are stored in .conll files. We also provide the lemmatized form, file with suffix .lemma, and appropriate POS-tags, see .pos files. The tokenized version of the documents is also available in .tok files.\r\n\r\nThis corpus is available only for research purposes for free. Commercial use in any form is strictly excluded."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2884"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "Czech"
-        },
-        {
-            "name": "document classification"
-        },
-        {
-            "name": "multi-label"
-        },
-        {
-            "name": "text"
-        }
-    ],
-    "title": [
-        "Czech Text Document Corpus v 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/17c4caff-1b5d-5bc2-a3d7-e430153a86a0.json b/oaitestdata/clarin-oai_dc/SET_1/json/17c4caff-1b5d-5bc2-a3d7-e430153a86a0.json
deleted file mode 100644
index 0f95a0d8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/17c4caff-1b5d-5bc2-a3d7-e430153a86a0.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "autor"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "downloadable_files_count: 10",
-        "application/vnd.oasis.opendocument.text",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/483",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/483"
-    ],
-    "PID": "http://hdl.handle.net/11321/483",
-    "PublicationTimestamp": "2018-06-19T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "autor"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Sarna, Pawe\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/483;2018-06-19T11:18:05Z;hdl_11321_3;hdl_11321_4;abc;Sarna, Pawe\u0142;Polska;opis testowy;2018-06-19;corpus;http://hdl.handle.net/11321/483;pol;Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0);http://creativecommons.org/licenses/by-nc-nd/3.0/;CC;text/plain; charset=utf-8;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.oasis.opendocument.text;text/plain;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;downloadable_files_count: 10;autor",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "17c4caff-1b5d-5bc2-a3d7-e430153a86a0",
-    "notes": [
-        "opis testowy"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/483"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Polska"
-        }
-    ],
-    "title": [
-        "abc"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/17ca2c20-6969-5899-9d65-8c096351468e.json b/oaitestdata/clarin-oai_dc/SET_1/json/17ca2c20-6969-5899-9d65-8c096351468e.json
deleted file mode 100644
index db06aee8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/17ca2c20-6969-5899-9d65-8c096351468e.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Staatsbibliothek zu Berlin (Musikabteilung)",
-        "Musikwissenschaftliches Seminar Detmold/Paderborn"
-    ],
-    "Contributor": [
-        "Allroggen, Prof. Dr. Gerhard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1141",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1141"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1141",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Staatsbibliothek zu Berlin (Musikabteilung)",
-        "Musikwissenschaftliches Seminar Detmold/Paderborn"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1141;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Carl-Maria-von-Weber-Gesamtausgabe (WeGA);Allroggen, Prof. Dr. Gerhard;Germanistik;Weber's diary entries, letters, writings, and opera; Tageb\u00fccher, Briefe, Schriften und Werke Webers;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1141;deu;downloadable_files_count: 0;Germany;Musikwissenschaftliches Seminar Detmold/Paderborn;Staatsbibliothek zu Berlin (Musikabteilung);http://www.weber-gesamtausgabe.de/de/Index",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "17ca2c20-6969-5899-9d65-8c096351468e",
-    "notes": [
-        "Weber's diary entries, letters, writings, and opera; Tageb\u00fccher, Briefe, Schriften und Werke Webers"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1141"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Carl-Maria-von-Weber-Gesamtausgabe (WeGA)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/17cc8b27-5cd8-5946-a73a-fa1c28478ea7.json b/oaitestdata/clarin-oai_dc/SET_1/json/17cc8b27-5cd8-5946-a73a-fa1c28478ea7.json
deleted file mode 100644
index 1cc4f5a6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/17cc8b27-5cd8-5946-a73a-fa1c28478ea7.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/100",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/100"
-    ],
-    "PID": "http://hdl.handle.net/10794/100",
-    "PublicationTimestamp": "2013-03-06T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/100;2017-10-25T11:32:41Z;hdl_10794_1;hdl_10794_2;Blog mix 2006 (2017-02-17);Bloggmix 2006 (2017-02-17);n/a, n/a;Swedish;Blog;The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.;Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat.;2013-03-06;corpus;http://hdl.handle.net/10794/100;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/bloggmix2006",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "17cc8b27-5cd8-5946-a73a-fa1c28478ea7",
-    "notes": [
-        "The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.",
-        "Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/100"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Blog"
-        }
-    ],
-    "title": [
-        "Blog mix 2006 (2017-02-17)",
-        "Bloggmix 2006 (2017-02-17)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/17f02033-9108-50f7-80a0-95939c09764e.json b/oaitestdata/clarin-oai_dc/SET_1/json/17f02033-9108-50f7-80a0-95939c09764e.json
deleted file mode 100644
index 50340d37..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/17f02033-9108-50f7-80a0-95939c09764e.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/107",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/107"
-    ],
-    "PID": "http://hdl.handle.net/10794/107",
-    "PublicationTimestamp": "2013-03-06T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/107;2017-10-25T06:34:36Z;hdl_10794_1;hdl_10794_2;Blog mix 2013 (2017-02-24);Bloggmix 2013 (2017-02-24);n/a, n/a;Swedish;Blog;The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.;Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat.;2013-03-06;corpus;http://hdl.handle.net/10794/107;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;http://creativecommons.org/licenses/by/4.0/;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/bloggmix2013",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "17f02033-9108-50f7-80a0-95939c09764e",
-    "notes": [
-        "The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.",
-        "Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/107"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Blog"
-        }
-    ],
-    "title": [
-        "Blog mix 2013 (2017-02-24)",
-        "Bloggmix 2013 (2017-02-24)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/18422072-b1b9-552f-a36c-57fd5769f77f.json b/oaitestdata/clarin-oai_dc/SET_1/json/18422072-b1b9-552f-a36c-57fd5769f77f.json
deleted file mode 100644
index c2650765..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/18422072-b1b9-552f-a36c-57fd5769f77f.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3768",
-    "MetadataAccess": [
-        "oai:ota:oucs:3768"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gilpin, William, 1724-1804."
-    ],
-    "fulltext": "oai:ota:oucs:3768;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3768.xml;The Lord's cup: or, the dispensations of providence with regard to good and evil, considered in a sermon; by William Gilpin,...;Gilpin, William, 1724-1804.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "18422072-b1b9-552f-a36c-57fd5769f77f",
-    "oai_identifier": [
-        "oai:ota:oucs:3768"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The Lord's cup: or, the dispensations of providence with regard to good and evil, considered in a sermon; by William Gilpin,..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3768.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/184624c5-b1e9-5e44-bba0-6646d6391794.json b/oaitestdata/clarin-oai_dc/SET_1/json/184624c5-b1e9-5e44-bba0-6646d6391794.json
deleted file mode 100644
index 28f5626e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/184624c5-b1e9-5e44-bba0-6646d6391794.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Meertens Institute KNAW The Netherlands"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-606",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-606"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-606",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Meertens Institute KNAW The Netherlands"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Belgium||Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-606;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Morphological Atlas of the Dutch Dialects (MAND);The Morphological Atlas of the Dutch Dialects (MAND) is based on phonetically transcribed speech. The speech recordings were made during a period from 1980 until 1995.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-606;nld;downloadable_files_count: 0;Belgium||Netherlands (the);Meertens Institute KNAW The Netherlands;http://www.meertens.knaw.nl/mand/database/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "184624c5-b1e9-5e44-bba0-6646d6391794",
-    "notes": [
-        "The Morphological Atlas of the Dutch Dialects (MAND) is based on phonetically transcribed speech. The speech recordings were made during a period from 1980 until 1995."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-606"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Morphological Atlas of the Dutch Dialects (MAND)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/185631fd-4336-5ac5-8816-433d31a52ade.json b/oaitestdata/clarin-oai_dc/SET_1/json/185631fd-4336-5ac5-8816-433d31a52ade.json
deleted file mode 100644
index a0e2aee2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/185631fd-4336-5ac5-8816-433d31a52ade.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Wroclaw University of Technology",
-        "University of Lodz"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "application/pdf",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/47",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/47"
-    ],
-    "PID": "http://hdl.handle.net/11321/47",
-    "PublicationTimestamp": "2014-10-24T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Wroclaw University of Technology",
-        "University of Lodz"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0)",
-        "http://creativecommons.org/licenses/by-nc/3.0/",
-        "CC"
-    ],
-    "author": [
-        "P\u0119zik, Piotr"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/47;2016-06-02T20:20:25Z;hdl_11321_3;hdl_11321_4;Spokes search engine for Polish conversational data;P\u0119zik, Piotr;corpus search engine;conversational data;spoken conversational Polish;Spokes is an online service for conversational corpus data search and exploration as part of the Polish CLARIN infrastructure. The underlying corpus contains more than 2 million words of time-aligned transcriptions of casual spoken discourse. The service is available both as a web application and as a REST service.;2014-10-24;toolService;http://hdl.handle.net/11321/47;pol;Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0);http://creativecommons.org/licenses/by-nc/3.0/;CC;text/plain; charset=utf-8;application/pdf;application/zip;downloadable_files_count: 2;University of Lodz;Wroclaw University of Technology;http://spokes.clarin-pl.eu/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "185631fd-4336-5ac5-8816-433d31a52ade",
-    "notes": [
-        "Spokes is an online service for conversational corpus data search and exploration as part of the Polish CLARIN infrastructure. The underlying corpus contains more than 2 million words of time-aligned transcriptions of casual spoken discourse. The service is available both as a web application and as a REST service."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/47"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus search engine"
-        },
-        {
-            "name": "conversational data"
-        },
-        {
-            "name": "spoken conversational Polish"
-        }
-    ],
-    "title": [
-        "Spokes search engine for Polish conversational data"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/185e8c1c-e286-5fe3-af91-efb622c99606.json b/oaitestdata/clarin-oai_dc/SET_1/json/185e8c1c-e286-5fe3-af91-efb622c99606.json
deleted file mode 100644
index 757c5045..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/185e8c1c-e286-5fe3-af91-efb622c99606.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "95 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1940",
-    "MetadataAccess": [
-        "oai:ota:oucs:1940"
-    ],
-    "PublicationTimestamp": "1626-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1626"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Fiction"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Campanella, Tommaso"
-    ],
-    "fulltext": "oai:ota:oucs:1940;2018-04-16T11:42:32Z;http://ota.ox.ac.uk/headers/1940.xml;The city of the sun;Campanella, Tommaso;1626;text_and_corpus_linguistics;Fiction -- Italy -- 17th century;Fantasy literature -- Italy -- 17th century;Utopian literature -- Italy -- 17th century;Essays -- Italy -- 17th century;eng;Oxford Text Archive, University of Oxford;95 KB;Text;Fiction;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "185e8c1c-e286-5fe3-af91-efb622c99606",
-    "oai_identifier": [
-        "oai:ota:oucs:1940"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- Italy -- th century"
-        },
-        {
-            "name": "Fantasy literature -- Italy -- th century"
-        },
-        {
-            "name": "Utopian literature -- Italy -- th century"
-        },
-        {
-            "name": "Essays -- Italy -- th century"
-        }
-    ],
-    "title": [
-        "The city of the sun"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1940.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/186c88af-ab9f-5416-a8a1-0569e35faa36.json b/oaitestdata/clarin-oai_dc/SET_1/json/186c88af-ab9f-5416-a8a1-0569e35faa36.json
deleted file mode 100644
index 3f52af3e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/186c88af-ab9f-5416-a8a1-0569e35faa36.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2711",
-    "MetadataAccess": [
-        "oai:ota:oucs:2711"
-    ],
-    "PublicationTimestamp": "1765-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1765"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2711;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2711 2711.xml;A discourse to prove the antiquity of the English tongue;Swift, Jonathan, 1667-1745;1765;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "186c88af-ab9f-5416-a8a1-0569e35faa36",
-    "oai_identifier": [
-        "oai:ota:oucs:2711"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A discourse to prove the antiquity of the English tongue"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2711"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1874188e-e0cb-548a-b7ff-a1a9dfdb6f0b.json b/oaitestdata/clarin-oai_dc/SET_1/json/1874188e-e0cb-548a-b7ff-a1a9dfdb6f0b.json
deleted file mode 100644
index f127145f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1874188e-e0cb-548a-b7ff-a1a9dfdb6f0b.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4803",
-    "MetadataAccess": [
-        "oai:ota:oucs:4803"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Donovan, E. (Edward), 1768-1837."
-    ],
-    "fulltext": "oai:ota:oucs:4803;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4803.xml;The natural history of British insects: explaining them in their several states, with the periods of their transformations, their food, \u00c5\u0093conomy, &c. Together with the history of such minute insects as require investigation by the microscope. The whole illustrated by coloured figures, ... By E. Donovan. [pt.3];Donovan, E. (Edward), 1768-1837.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1874188e-e0cb-548a-b7ff-a1a9dfdb6f0b",
-    "oai_identifier": [
-        "oai:ota:oucs:4803"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The natural history of British insects: explaining them in their several states, with the periods of their transformations, their food, \u00c5\u0093conomy, &c. Together with the history of such minute insects as require investigation by the microscope. The whole illustrated by coloured figures, ... By E. Donovan. [pt.3]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4803.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1887dbb1-9553-5c2b-bcb1-02e5abdce680.json b/oaitestdata/clarin-oai_dc/SET_1/json/1887dbb1-9553-5c2b-bcb1-02e5abdce680.json
deleted file mode 100644
index ff1bc1ac..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1887dbb1-9553-5c2b-bcb1-02e5abdce680.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Dell, Thomas"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 338 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2042",
-    "MetadataAccess": [
-        "oai:ota:oucs:2042"
-    ],
-    "PublicationTimestamp": "1968-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1968"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Essays"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Kirkland, Winifred Margaretta, 1872-1943"
-    ],
-    "fulltext": "oai:ota:oucs:2042;2018-03-01T16:30:42Z;http://ota.ox.ac.uk/headers/2042.xml;The joys of being a woman and other papers / Winifred Kirkland;Kirkland, Winifred Margaretta, 1872-1943;1968;text_and_corpus_linguistics;American essays -- 20th century;eng;Oxford Text Archive, University of Oxford;Dell, Thomas;text/plain;(1 file : ca. 338 KB);Text;Essays;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1887dbb1-9553-5c2b-bcb1-02e5abdce680",
-    "oai_identifier": [
-        "oai:ota:oucs:2042"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "American essays -- th century"
-        }
-    ],
-    "title": [
-        "The joys of being a woman and other papers / Winifred Kirkland"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2042.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/18b5a4f9-f773-5ce9-bb03-b6d5b95a456a.json b/oaitestdata/clarin-oai_dc/SET_1/json/18b5a4f9-f773-5ce9-bb03-b6d5b95a456a.json
deleted file mode 100644
index c992a247..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/18b5a4f9-f773-5ce9-bb03-b6d5b95a456a.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=23dbd074fb5511e1a2aa782bcb0741356105c7004ea040b1a049488e4bc14763",
-    "MetadataAccess": [
-        "23dbd074fb5511e1a2aa782bcb0741356105c7004ea040b1a049488e4bc14763"
-    ],
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "23dbd074fb5511e1a2aa782bcb0741356105c7004ea040b1a049488e4bc14763;2018-11-15T16:39:43Z;corpus;corpus:text;CINTIL-DependencyBank;The CINTIL-DepBank (Branco et al., 2011a) is a corpus of grammatical dependencies of Portuguese texts composed of 10,039 sentences and 110,166 tokens taken from different sources and domains: news (8,861 sentences; 101,430 tokens), novels (399 sentences; 3,082 tokens) (see 3.2.). In addition, there are 779 sentences (5,654 tokens) that are used for regression testing of the computational grammar that supported the annotation of the corpus (cf. Section 4.6.).\nThe CINTIL-DepBank is aligned to a constituency bank, the CINTIL-TreeBank (see Branco et al., 2011b). The key bridging elements are the grammatical function tags decoring the nodes, in the treebank, and the arcs, in the dependencybank (see http://lxcenter.di.fc.ul.pt/services/en/LXServicesSearcher.html). This means that the CINTIL-DepBank was extended from the CINTIL-PropBank so that besides the tags for the different dependency relations, the arcs are further decorated with tags indicating the semantic relation at stake.\nThe main motivation behind the creation of this resource was to build a high quality data set with dependencyinformation that could support the development of a large set of automatic resources and tools for Portuguese for NLP studies.;2015-12-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "18b5a4f9-f773-5ce9-bb03-b6d5b95a456a",
-    "notes": [
-        "The CINTIL-DepBank (Branco et al., 2011a) is a corpus of grammatical dependencies of Portuguese texts composed of 10,039 sentences and 110,166 tokens taken from different sources and domains: news (8,861 sentences; 101,430 tokens), novels (399 sentences; 3,082 tokens) (see 3.2.). In addition, there are 779 sentences (5,654 tokens) that are used for regression testing of the computational grammar that supported the annotation of the corpus (cf. Section 4.6.).\nThe CINTIL-DepBank is aligned to a constituency bank, the CINTIL-TreeBank (see Branco et al., 2011b). The key bridging elements are the grammatical function tags decoring the nodes, in the treebank, and the arcs, in the dependencybank (see http://lxcenter.di.fc.ul.pt/services/en/LXServicesSearcher.html). This means that the CINTIL-DepBank was extended from the CINTIL-PropBank so that besides the tags for the different dependency relations, the arcs are further decorated with tags indicating the semantic relation at stake.\nThe main motivation behind the creation of this resource was to build a high quality data set with dependencyinformation that could support the development of a large set of automatic resources and tools for Portuguese for NLP studies."
-    ],
-    "oai_identifier": [
-        "23dbd074fb5511e1a2aa782bcb0741356105c7004ea040b1a049488e4bc14763"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "CINTIL-DependencyBank"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/18bbd963-bd67-5910-bb17-8df6d85d10a9.json b/oaitestdata/clarin-oai_dc/SET_1/json/18bbd963-bd67-5910-bb17-8df6d85d10a9.json
deleted file mode 100644
index b900a4ea..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/18bbd963-bd67-5910-bb17-8df6d85d10a9.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "IPI PAN"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "downloadable_files_count: 10",
-        "application/vnd.oasis.opendocument.text",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/399",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/399"
-    ],
-    "PID": "http://hdl.handle.net/11321/399",
-    "PublicationTimestamp": "2017-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "IPI PAN"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Smith, Donald"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/399;2017-05-30T11:56:13Z;hdl_11321_3;hdl_11321_4;PM;Smith, Donald;koteczek;kotek;2017-05-30;corpus;http://hdl.handle.net/11321/399;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;text/plain;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;application/vnd.oasis.opendocument.text;downloadable_files_count: 10;IPI PAN",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "18bbd963-bd67-5910-bb17-8df6d85d10a9",
-    "notes": [
-        "kotek"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/399"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "koteczek"
-        }
-    ],
-    "title": [
-        "PM"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/18d9a550-1135-53b1-8fbe-23614da23f5b.json b/oaitestdata/clarin-oai_dc/SET_1/json/18d9a550-1135-53b1-8fbe-23614da23f5b.json
deleted file mode 100644
index 39303571..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/18d9a550-1135-53b1-8fbe-23614da23f5b.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Jezuit\u00f3w"
-    ],
-    "Contributor": [
-        "Radli\u0144ski, Jakub Pawe\u0142 (ca 1680-1762). [T\u0142.]"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Latin",
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-143951",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-143951"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CDC-8",
-    "PublicationTimestamp": "1733-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1733"
-    ],
-    "Publisher": [
-        "Drukarnia Jezuit\u00f3w"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/143951",
-        "oai:jbc.bj.uj.edu.pl:publication:152128"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1701/1800"
-    ],
-    "TempCoverageBegin": 53662478399,
-    "TempCoverageEnd": 53662478399,
-    "TemporalCoverage": " point in time : 1701-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1701-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1701-07-01T11:59:59Z",
-    "author": [
-        "Samuel Rabi Maroka\u0144ski"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-143951;2019-02-28T18:11:20Z;Prawda Chrzescianska Od nieprzyiaciela swego Zeznana : To iest Traktat Rabina Samuela, Pokazui\u0105cy b\u0142\u0119dy \u017cydowskie oko\u0142o zachowania Prawa Moy\u017ceszowego, y przy\u015bcia Messyaszowego, ktorego \u017cydzi [!] czekai\u0105. [...]Prawda Chrzescianska Od nieprzyiaciela swego Zeznana : To iest Traktat Rabina Samuela, Pokazui\u0105cy b\u0142\u0119dy \u017cydowskie oko\u0142o zachowania Prawa Moy\u017ceszowego, y przy\u015bcia Messyaszowego, ktorego \u017cydzi [!] czekai\u0105. [...];Samuel Rabi Maroka\u0144ski;starodruki 18\u00a0w.;Potocki, J\u00f3zef (1673-1751). [Adr. ded.];Potocka, Ludwika (1712-1785). [Adr. ded.];Drukarnia Jezuit\u00f3w;Radli\u0144ski, Jakub Pawe\u0142 (ca 1680-1762). [T\u0142.];1733;starodruk;application/xml;clarind-uds:poldilemma-143951;hdl:11858/00-246C-0000-0023-8CDC-8;Biblioteka Jagiello\u0144ska, BJ St. Dr. 35187 I;lat;pol;http://jbc.bj.uj.edu.pl/Content/143951;oai:jbc.bj.uj.edu.pl:publication:152128;1701/1800;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "18d9a550-1135-53b1-8fbe-23614da23f5b",
-    "notes": [
-        "Potocki, J\u00f3zef (1673-1751). [Adr. ded.]",
-        "Potocka, Ludwika (1712-1785). [Adr. ded.]"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-143951"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Prawda Chrzescianska Od nieprzyiaciela swego Zeznana : To iest Traktat Rabina Samuela, Pokazui\u0105cy b\u0142\u0119dy \u017cydowskie oko\u0142o zachowania Prawa Moy\u017ceszowego, y przy\u015bcia Messyaszowego, ktorego \u017cydzi [!] czekai\u0105. [...]Prawda Chrzescianska Od nieprzyiaciela swego Zeznana : To iest Traktat Rabina Samuela, Pokazui\u0105cy b\u0142\u0119dy \u017cydowskie oko\u0142o zachowania Prawa Moy\u017ceszowego, y przy\u015bcia Messyaszowego, ktorego \u017cydzi [!] czekai\u0105. [...]"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/18e20c63-b9a3-5438-8990-db4305bdeafd.json b/oaitestdata/clarin-oai_dc/SET_1/json/18e20c63-b9a3-5438-8990-db4305bdeafd.json
deleted file mode 100644
index 12f69865..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/18e20c63-b9a3-5438-8990-db4305bdeafd.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "w Drukarni J. K. Mci y Rzeczypospolitey u XX. Scholarum Piarum"
-    ],
-    "Contributor": [
-        "Drukarnia Pijar\u00f3w (Warszawa)",
-        "Karwowski, Joachim (1736-1821). T\u0142."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229204",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229204"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D0B-5",
-    "PublicationTimestamp": "1774-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1774"
-    ],
-    "Publisher": [
-        "w Drukarni J. K. Mci y Rzeczypospolitey u XX. Scholarum Piarum"
-    ],
-    "RelatedIdentifier": [
-        "http://rcin.org.pl/Content/30364",
-        "oai:rcin.org.pl:publication:23040"
-    ],
-    "ResourceType": [
-        "Text",
-        "Early printed book (1501-1800)"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "author": [
-        "Contant d'Orville, Andr\u00e9-Guillaume (1730?-1800?)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229204;2019-03-01T13:04:42Z;Opisanie Naturalne, Historyczne y Polityczne roznych kraiow swiata to jest Ich po\u0142o\u017cenie, Klima, Historya, Rewolucye [...];Contant d'Orville, Andr\u00e9-Guillaume (1730?-1800?);geographical descriptions;history;politics;East Asia;[2], 353, [6] pp. ; 8\u02bf;Ded. aut., t\u0142. Joachim Karwowski S.P.: \"Do Jasnie Wielmoznego Jmci Pana Jerzego Potockiego [...]\";Data na s. tyt.: MDCCLXXIV;Estr. XV-XVIII t. 3 p. 388;w Drukarni J. K. Mci y Rzeczypospolitey u XX. Scholarum Piarum;Karwowski, Joachim (1736-1821). T\u0142.;Drukarnia Pijar\u00f3w (Warszawa);1774;Text;Early printed book (1501-1800);application/xml;clarind-uds:poldilemma-229204;hdl:11858/00-246C-0000-0023-8D0B-5;CBGiO\u015a. IGiPZ PAN, call no. 782;http://katalog.pan.pl/webpac-bin/210bgiosEN/wgbroker.exe?new+-access+top+search+open+NR+xx002552431;pol;http://rcin.org.pl/Content/30364;oai:rcin.org.pl:publication:23040;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "18e20c63-b9a3-5438-8990-db4305bdeafd",
-    "notes": [
-        "[2], 353, [6] pp. ; 8\u02bf",
-        "Ded. aut., t\u0142. Joachim Karwowski S.P.: \"Do Jasnie Wielmoznego Jmci Pana Jerzego Potockiego [...]\"",
-        "Data na s. tyt.: MDCCLXXIV",
-        "Estr. XV-XVIII t. 3 p. 388"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229204"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "geographical descriptions"
-        },
-        {
-            "name": "history"
-        },
-        {
-            "name": "politics"
-        },
-        {
-            "name": "East Asia"
-        }
-    ],
-    "title": [
-        "Opisanie Naturalne, Historyczne y Polityczne roznych kraiow swiata to jest Ich po\u0142o\u017cenie, Klima, Historya, Rewolucye [...]"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/18f30202-a1e6-5baf-b450-916cc9b64fe1.json b/oaitestdata/clarin-oai_dc/SET_1/json/18f30202-a1e6-5baf-b450-916cc9b64fe1.json
deleted file mode 100644
index f2081594..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/18f30202-a1e6-5baf-b450-916cc9b64fe1.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Institute of Mathematics and Computer Science, University of Latvia"
-    ],
-    "Contributor": [
-        "Skadina, Inguna",
-        "Virza, Madars"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Latvian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1216",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1216"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1216",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institute of Mathematics and Computer Science, University of Latvia"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Latvia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1216;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Latvian tagger;Virza, Madars;Skadina, Inguna;HMM-based tagger of Latvian texts. The tagger uses information from SemTi-Kamols morphological analyser, the tagset is derived from MULTEXT-East project.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1216;lav;downloadable_files_count: 0;Latvia;Institute of Mathematics and Computer Science, University of Latvia;http://eksperimenti.ailab.lv/tagger/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "18f30202-a1e6-5baf-b450-916cc9b64fe1",
-    "notes": [
-        "HMM-based tagger of Latvian texts. The tagger uses information from SemTi-Kamols morphological analyser, the tagset is derived from MULTEXT-East project."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1216"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Latvian tagger"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/190ef35e-79f1-54e7-b681-15bec73b1156.json b/oaitestdata/clarin-oai_dc/SET_1/json/190ef35e-79f1-54e7-b681-15bec73b1156.json
deleted file mode 100644
index 1e43b914..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/190ef35e-79f1-54e7-b681-15bec73b1156.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5546",
-    "MetadataAccess": [
-        "oai:ota:oucs:5546"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Tissot, S. A. D. (Samuel Auguste David), 1728-1797."
-    ],
-    "fulltext": "oai:ota:oucs:5546;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5546.xml;The lady's physician: A practical treatise on the various disorders incident to the fair sex. ... Written originally in French, by M. Tissot, ... Translated by an eminent physician.;Tissot, S. A. D. (Samuel Auguste David), 1728-1797.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "190ef35e-79f1-54e7-b681-15bec73b1156",
-    "oai_identifier": [
-        "oai:ota:oucs:5546"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The lady's physician: A practical treatise on the various disorders incident to the fair sex. ... Written originally in French, by M. Tissot, ... Translated by an eminent physician."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5546.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/193c9cd6-8778-58b8-ac11-3ab900f69507.json b/oaitestdata/clarin-oai_dc/SET_1/json/193c9cd6-8778-58b8-ac11-3ab900f69507.json
deleted file mode 100644
index e24a59c5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/193c9cd6-8778-58b8-ac11-3ab900f69507.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3343",
-    "MetadataAccess": [
-        "oai:ota:oucs:3343"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pinkerton, John, 1758-1826."
-    ],
-    "fulltext": "oai:ota:oucs:3343;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3343.xml;Letters of literature: By Robert Heron, Esq.;Pinkerton, John, 1758-1826.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "193c9cd6-8778-58b8-ac11-3ab900f69507",
-    "oai_identifier": [
-        "oai:ota:oucs:3343"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Letters of literature: By Robert Heron, Esq."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3343.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1977f6f7-adc2-56f0-a146-b9b29ff8befb.json b/oaitestdata/clarin-oai_dc/SET_1/json/1977f6f7-adc2-56f0-a146-b9b29ff8befb.json
deleted file mode 100644
index 986dd480..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1977f6f7-adc2-56f0-a146-b9b29ff8befb.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/336",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/336"
-    ],
-    "PID": "http://hdl.handle.net/11321/336",
-    "PublicationTimestamp": "2017-02-13T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Marci\u0144czuk, Micha\u0142",
-        "Krautforst, Micha\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/336;2017-02-13T07:05:46Z;hdl_11321_3;hdl_11321_4;python-g419wikitools-1.0;Marci\u0144czuk, Micha\u0142;Krautforst, Micha\u0142;Wikipedia;multi-word phrase inflection;dictionary;Zestaw skrypt\u00f3w w j\u0119zyku Python do wygenerowania s\u0142ownika odmiany fraz w oparciu o linki wewn\u0119trzne Wikipedii. Efektem analizy dumpa Wikipedii jest zestaw plik\u00f3w, zawieraj\u0105cych:\r\n\r\nA) wikilinks-difflen.txt \u2014 frazy maj\u0105 r\u00f3\u017cn\u0105 liczb\u0119 token\u00f3w,\r\nB) wikilinks-samelen* \u2014 frazy maj\u0105 tak\u0105 sam\u0105 liczb\u0119 token\u00f3w,\r\n 1. wikilinks-samelen-textbase.txt \u2014 ka\u017cda para token\u00f3w ma przynajmniej jedn\u0105 wsp\u00f3ln\u0105 form\u0119 bazow\u0105,\r\n 1.a) wikilinks-samelen-textbase-one.txt \u2014 frazy zawieraj\u0105 po jednym tokenie,\r\n 1.b) wikilinks-samelen-textbase-multi.txt \u2014 frazy zawieraj\u0105 wi\u0119cej ni\u017c jeden token,\r\n 2. wikilinks-samelen-rules.txt \u2014 co najmniej jedna para token\u00f3w nie zosta\u0142a dopasowana przez formy bazowe, tylko przez zastosowanie regu\u0142 podmiany ko\u0144c\u00f3wek dla formy tekstowej.\r\n 3. wikilinks-samelen-different.txt  \u2014 pozosta\u0142e frazy, kt\u00f3re nie zosta\u0142y dopasowane.\r\n\r\nPrzyk\u0142ad zawarto\u015bci pliku wikilinks-samelen-textbase-multi.txt:\r\nTransformacja ustrojowa\ttransformacji ustrojowej\ttransformacji ustrojowych\r\nKonstytucja ZSRR\tKonstytucji ZSRR\r\nRajd Tatrza\u0144ski\tRajdzie Tatrza\u0144skim\r\nMacierz dyskowa\tmacierz\u0105 dyskow\u0105\tmacierzy dyskowych\r\nOsiedle Ptasie\tOsiedle Ptasie\r\nobjaw Brudzi\u0144skiego\tobjawy Brudzi\u0144skiego\r\nCh\u0142opskie Stronnictwo Radykalne\tCh\u0142opskiego Stronnictwa Radykalnego\r\nMelanie Klein\tMelani\u0105 Klein\r\nJakub Soko\u0142owski\tJakuba Soko\u0142owskiego\r\nLetnie Igrzyska Olimpijskie M\u0142odzie\u017cy 2010\tLetnich Igrzysk Olimpijskich M\u0142odzie\u017cy 2010\r\nwyrabianie ciasta\twyrabiania ciasta\r\nbitwa nad rzek\u0105 Czoroch\tbitwie nad rzek\u0105 Czoroch\r\nNerw b\u0142\u0119dny\tnerwu b\u0142\u0119dnego\tnerw\u00f3w b\u0142\u0119dnych\r\nPakt trzech\tpaktu trzech\tPaktu Trzech\tPaktu trzech\r\nKomisja Episkopatu Polski ds. Ekumenizmu\tKomisji Episkopatu Polski ds. Ekumenizmu\r\nFlaga Albanii\tflag\u0119 Albanii\tflagi Albanii\r\nBitwa pod Chrobrzem\tbitwie pod Chrobrzem\r\nPatriarcha Indii Zachodnich\tpatriarch\u0119 Indii Zachodnich\r\nprocesy fizjologiczne\tproces fizjologiczny\r\nenergetyka j\u0105drowa\tenergetyk\u0119 j\u0105drow\u0105\tenergetyce j\u0105drowej\tenergetyk\u0105 j\u0105drow\u0105\tenergetyki j\u0105drowej\r\nzdanie syntetyczne\tzdania syntetyczne\r\nFranciszek Ksawery\tFranciszek Ksawery\tFranciszka Ksawerego\tFranciszkiem Ksawerym\r\nObw\u00f3d Tirana\tobwodzie Tirana;2017-02-13;toolService;http://hdl.handle.net/11321/336;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;Wroc\u0142aw University of Science and Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1977f6f7-adc2-56f0-a146-b9b29ff8befb",
-    "notes": [
-        "Zestaw skrypt\u00f3w w j\u0119zyku Python do wygenerowania s\u0142ownika odmiany fraz w oparciu o linki wewn\u0119trzne Wikipedii. Efektem analizy dumpa Wikipedii jest zestaw plik\u00f3w, zawieraj\u0105cych:\r\n\r\nA) wikilinks-difflen.txt \u2014 frazy maj\u0105 r\u00f3\u017cn\u0105 liczb\u0119 token\u00f3w,\r\nB) wikilinks-samelen* \u2014 frazy maj\u0105 tak\u0105 sam\u0105 liczb\u0119 token\u00f3w,\r\n 1. wikilinks-samelen-textbase.txt \u2014 ka\u017cda para token\u00f3w ma przynajmniej jedn\u0105 wsp\u00f3ln\u0105 form\u0119 bazow\u0105,\r\n 1.a) wikilinks-samelen-textbase-one.txt \u2014 frazy zawieraj\u0105 po jednym tokenie,\r\n 1.b) wikilinks-samelen-textbase-multi.txt \u2014 frazy zawieraj\u0105 wi\u0119cej ni\u017c jeden token,\r\n 2. wikilinks-samelen-rules.txt \u2014 co najmniej jedna para token\u00f3w nie zosta\u0142a dopasowana przez formy bazowe, tylko przez zastosowanie regu\u0142 podmiany ko\u0144c\u00f3wek dla formy tekstowej.\r\n 3. wikilinks-samelen-different.txt  \u2014 pozosta\u0142e frazy, kt\u00f3re nie zosta\u0142y dopasowane.\r\n\r\nPrzyk\u0142ad zawarto\u015bci pliku wikilinks-samelen-textbase-multi.txt:\r\nTransformacja ustrojowa\ttransformacji ustrojowej\ttransformacji ustrojowych\r\nKonstytucja ZSRR\tKonstytucji ZSRR\r\nRajd Tatrza\u0144ski\tRajdzie Tatrza\u0144skim\r\nMacierz dyskowa\tmacierz\u0105 dyskow\u0105\tmacierzy dyskowych\r\nOsiedle Ptasie\tOsiedle Ptasie\r\nobjaw Brudzi\u0144skiego\tobjawy Brudzi\u0144skiego\r\nCh\u0142opskie Stronnictwo Radykalne\tCh\u0142opskiego Stronnictwa Radykalnego\r\nMelanie Klein\tMelani\u0105 Klein\r\nJakub Soko\u0142owski\tJakuba Soko\u0142owskiego\r\nLetnie Igrzyska Olimpijskie M\u0142odzie\u017cy 2010\tLetnich Igrzysk Olimpijskich M\u0142odzie\u017cy 2010\r\nwyrabianie ciasta\twyrabiania ciasta\r\nbitwa nad rzek\u0105 Czoroch\tbitwie nad rzek\u0105 Czoroch\r\nNerw b\u0142\u0119dny\tnerwu b\u0142\u0119dnego\tnerw\u00f3w b\u0142\u0119dnych\r\nPakt trzech\tpaktu trzech\tPaktu Trzech\tPaktu trzech\r\nKomisja Episkopatu Polski ds. Ekumenizmu\tKomisji Episkopatu Polski ds. Ekumenizmu\r\nFlaga Albanii\tflag\u0119 Albanii\tflagi Albanii\r\nBitwa pod Chrobrzem\tbitwie pod Chrobrzem\r\nPatriarcha Indii Zachodnich\tpatriarch\u0119 Indii Zachodnich\r\nprocesy fizjologiczne\tproces fizjologiczny\r\nenergetyka j\u0105drowa\tenergetyk\u0119 j\u0105drow\u0105\tenergetyce j\u0105drowej\tenergetyk\u0105 j\u0105drow\u0105\tenergetyki j\u0105drowej\r\nzdanie syntetyczne\tzdania syntetyczne\r\nFranciszek Ksawery\tFranciszek Ksawery\tFranciszka Ksawerego\tFranciszkiem Ksawerym\r\nObw\u00f3d Tirana\tobwodzie Tirana"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/336"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Wikipedia"
-        },
-        {
-            "name": "multi-word phrase inflection"
-        },
-        {
-            "name": "dictionary"
-        }
-    ],
-    "title": [
-        "python-g419wikitools-1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/19bb64c4-89f9-5c25-a3a1-5eb4e0fc74cb.json b/oaitestdata/clarin-oai_dc/SET_1/json/19bb64c4-89f9-5c25-a3a1-5eb4e0fc74cb.json
deleted file mode 100644
index ff384408..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/19bb64c4-89f9-5c25-a3a1-5eb4e0fc74cb.json
+++ /dev/null
@@ -1,88 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1213",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1213"
-    ],
-    "PID": "http://hdl.handle.net/11356/1213",
-    "PublicationTimestamp": "2019-02-13T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "http://www.lrec-conf.org/proceedings/lrec2010/summaries/139.html",
-        "http://hdl.handle.net/11356/1037"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)",
-        "https://creativecommons.org/licenses/by-nc/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Krek, Simon",
-        "Erjavec, Toma\u017e",
-        "Dobrovoljc, Kaja"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1213;2019-02-13T17:15:30Z;hdl_11356_1023;hdl_11356_1024;Training corpus jos1M 1.2;Erjavec, Toma\u017e;Krek, Simon;Dobrovoljc, Kaja;tagging;lemmatisation;manual annotation;TEI;CONLL-U;The jos1M corpus contains 1 million words of sampled paragraphs from the Gigafida corpus. It is meant to serve as a training corpus for word-level tagging of Slovene. This silver-standard corpus is annotated for morphosyntactic descriptions and lemmas with about one fourth of the more problematic annotations hand-validated.\r\n\r\nThe morphosyntactic descriptions are given in both the JOS/MULTEXT-East framework (http://nl.ijs.si/ME/V6/msd/), as well as in the framework of Universal Dependencies for Slovene (https://universaldependencies.org/treebanks/sl_ssj/index.html).\r\n\r\nThe corpus is available in source TEI XML with the MSDs in English or Slovene and in the derived vertical format, used by CQP and (no)Sketch Engine concordancers and in CONLL-U, used by Universal Dependencies. Note that the corpus does not contain syntactic dependencies. \r\n\r\nThe texts or paragraphs of the jos1M corpus overlap with this of the ssj500k annotated corpus (http://hdl.handle.net/11356/1210), but the latter has been fully manually annotated, as well as having its tokenisation and sentence segmentation corrected. The texts and paragraphs in the jos1M corpus are marked if they are also included in ssj500k, while the CONLL-U is also split into the part that is included in ssj500k and that which is not. The latter can serve as an additional training set for morphosyntactic tagging and lemmatisation to ssj500k.;2019-02-13;corpus;http://hdl.handle.net/11356/1213;slv;http://www.lrec-conf.org/proceedings/lrec2010/summaries/139.html;http://hdl.handle.net/11356/1037;Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0);https://creativecommons.org/licenses/by-nc/4.0/;PUB;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 4;Jo\u017eef Stefan Institute;http://nl.ijs.si/jos/jos1M-en.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "19bb64c4-89f9-5c25-a3a1-5eb4e0fc74cb",
-    "notes": [
-        "The jos1M corpus contains 1 million words of sampled paragraphs from the Gigafida corpus. It is meant to serve as a training corpus for word-level tagging of Slovene. This silver-standard corpus is annotated for morphosyntactic descriptions and lemmas with about one fourth of the more problematic annotations hand-validated.\r\n\r\nThe morphosyntactic descriptions are given in both the JOS/MULTEXT-East framework (http://nl.ijs.si/ME/V6/msd/), as well as in the framework of Universal Dependencies for Slovene (https://universaldependencies.org/treebanks/sl_ssj/index.html).\r\n\r\nThe corpus is available in source TEI XML with the MSDs in English or Slovene and in the derived vertical format, used by CQP and (no)Sketch Engine concordancers and in CONLL-U, used by Universal Dependencies. Note that the corpus does not contain syntactic dependencies. \r\n\r\nThe texts or paragraphs of the jos1M corpus overlap with this of the ssj500k annotated corpus (http://hdl.handle.net/11356/1210), but the latter has been fully manually annotated, as well as having its tokenisation and sentence segmentation corrected. The texts and paragraphs in the jos1M corpus are marked if they are also included in ssj500k, while the CONLL-U is also split into the part that is included in ssj500k and that which is not. The latter can serve as an additional training set for morphosyntactic tagging and lemmatisation to ssj500k."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1213"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "lemmatisation"
-        },
-        {
-            "name": "manual annotation"
-        },
-        {
-            "name": "TEI"
-        },
-        {
-            "name": "CONLL-U"
-        }
-    ],
-    "title": [
-        "Training corpus jos1M 1.2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/19bfbb87-42e2-5b2c-9735-2de157b92446.json b/oaitestdata/clarin-oai_dc/SET_1/json/19bfbb87-42e2-5b2c-9735-2de157b92446.json
deleted file mode 100644
index 8d937a01..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/19bfbb87-42e2-5b2c-9735-2de157b92446.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5042",
-    "MetadataAccess": [
-        "oai:ota:oucs:5042"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Trusler, John, 1735-1820."
-    ],
-    "fulltext": "oai:ota:oucs:5042;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5042.xml;The habitable world described: or the present state of the people in all parts of the globe, from north to south; shewing the situation, extent, climate, ... including all the new discoveries: ... With a great variety of maps and copper-plates, ... By the Rev. Dr. John Trusler. ... [pt.8];Trusler, John, 1735-1820.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "19bfbb87-42e2-5b2c-9735-2de157b92446",
-    "oai_identifier": [
-        "oai:ota:oucs:5042"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The habitable world described: or the present state of the people in all parts of the globe, from north to south; shewing the situation, extent, climate, ... including all the new discoveries: ... With a great variety of maps and copper-plates, ... By the Rev. Dr. John Trusler. ... [pt.8]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5042.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/19c74826-1202-5769-8252-c48ecd2efba6.json b/oaitestdata/clarin-oai_dc/SET_1/json/19c74826-1202-5769-8252-c48ecd2efba6.json
deleted file mode 100644
index d2a54af4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/19c74826-1202-5769-8252-c48ecd2efba6.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "CNTS - Language Technology Group, \r\nUniversity of Antwerp",
-        "ILK, Tilburg University"
-    ],
-    "Contributor": [
-        "Bosch, Antal van den",
-        "Daelemans, Walter"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1329",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1329"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1329",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "CNTS - Language Technology Group, \r\nUniversity of Antwerp",
-        "ILK, Tilburg University"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Belgium||Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1329;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Memory-Based Tagger Generation and tagging;Daelemans, Walter;Bosch, Antal van den;tagger;memory-based tagger;MBT is a memory-based tagger-generator and tagger in one. The tagger-generator part can generate a sequence tagger on the basis of a training set of tagged sequences; the tagger part can tag new sequences. MBT can, for instance, be used to generate part-of-speech taggers or chunkers for natural language processing.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1329;downloadable_files_count: 0;Belgium||Netherlands (the);CNTS - Language Technology Group, \r\nUniversity of Antwerp;ILK, Tilburg University;http://ilk.uvt.nl/mbt/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "19c74826-1202-5769-8252-c48ecd2efba6",
-    "notes": [
-        "MBT is a memory-based tagger-generator and tagger in one. The tagger-generator part can generate a sequence tagger on the basis of a training set of tagged sequences; the tagger part can tag new sequences. MBT can, for instance, be used to generate part-of-speech taggers or chunkers for natural language processing."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1329"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "tagger"
-        },
-        {
-            "name": "memory-based tagger"
-        }
-    ],
-    "title": [
-        "Memory-Based Tagger Generation and tagging"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/19e68d44-a008-5ce1-a2c6-cc296ff0574b.json b/oaitestdata/clarin-oai_dc/SET_1/json/19e68d44-a008-5ce1-a2c6-cc296ff0574b.json
deleted file mode 100644
index 7e936f5f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/19e68d44-a008-5ce1-a2c6-cc296ff0574b.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "A"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1764",
-    "MetadataAccess": [
-        "oai:ota:oucs:1764"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Doyle, Sir Arthur Conan"
-    ],
-    "fulltext": "oai:ota:oucs:1764;2018-04-16T15:30:51Z;http://ota.ox.ac.uk/headers/1764.xml;The Hound of the Baskervilles;Doyle, Sir Arthur Conan;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;A;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "19e68d44-a008-5ce1-a2c6-cc296ff0574b",
-    "oai_identifier": [
-        "oai:ota:oucs:1764"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The Hound of the Baskervilles"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1764.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1a03ab13-94b4-5a1e-9b12-56ae4611a6db.json b/oaitestdata/clarin-oai_dc/SET_1/json/1a03ab13-94b4-5a1e-9b12-56ae4611a6db.json
deleted file mode 100644
index 87a1cb9f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1a03ab13-94b4-5a1e-9b12-56ae4611a6db.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4263",
-    "MetadataAccess": [
-        "oai:ota:oucs:4263"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "O'Keeffe, John, 1747-1833."
-    ],
-    "fulltext": "oai:ota:oucs:4263;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4263.xml;The dead alive: a comic opera: In two acts. As it is performed at the theatres in London and Dublin. By John O'Keeffe, Esq.;O'Keeffe, John, 1747-1833.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1a03ab13-94b4-5a1e-9b12-56ae4611a6db",
-    "oai_identifier": [
-        "oai:ota:oucs:4263"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The dead alive: a comic opera: In two acts. As it is performed at the theatres in London and Dublin. By John O'Keeffe, Esq."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4263.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1a1bd15c-a00d-5bf3-8c49-54498c8502eb.json b/oaitestdata/clarin-oai_dc/SET_1/json/1a1bd15c-a00d-5bf3-8c49-54498c8502eb.json
deleted file mode 100644
index 63fcef04..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1a1bd15c-a00d-5bf3-8c49-54498c8502eb.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml-dtd",
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 4",
-        "application/pdf",
-        "application/zip"
-    ],
-    "Language": [
-        "Danish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repository.clarin.dk:20.500.12115/23",
-    "MetadataAccess": [
-        "oai:repository.clarin.dk:20.500.12115/23"
-    ],
-    "PID": "http://hdl.handle.net/20.500.12115/23",
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Hansen, Dorte Haltrup",
-        "Braasch, Anna",
-        "Olsen, Sussi",
-        "Offersgaard, Lene"
-    ],
-    "fulltext": "oai:repository.clarin.dk:20.500.12115/23;2018-06-28T13:27:23Z;hdl_20.500.12115_1;hdl_20.500.12115_3;STO syntax (v2) - LMF format;Braasch, Anna;Olsen, Sussi;Hansen, Dorte Haltrup;Offersgaard, Lene;syntax;LMF;The STO (SprogTeknologisk Ordbase) lexicon is a comprehensive computational lexicon of Danish developed for NLP/HLT applications. The syntax layer of the lexicon, presented here in Lexical Markup Format (LMF), contains a vocabulary of 84,159 entries (nouns, verbs and adjectives). The syntax is linked to the morphological layer through ID's.\r\nThe Lexical Markup Language is an internationally well\u2010known and accepted XML format and the ISO standard for Natural Language Processing (NLP) lexicons. See www.lexicalmarkupframework.org for more information on LMF and the attached documentation for the marke-up of STO.\r\nSTO LMF is created within the framework of the EU project MetaNord, and was carried out by Center for Language Technology (CST) in 2011 - 2013;2013;lexicalConceptualResource;http://hdl.handle.net/20.500.12115/23;dan;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;PUB;text/plain; charset=utf-8;application/zip;application/xml-dtd;application/pdf;application/pdf;downloadable_files_count: 4;Centre for Language Technology, NorS, University of Copenhagen;https://cst.ku.dk/sto_ordbase/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1a1bd15c-a00d-5bf3-8c49-54498c8502eb",
-    "notes": [
-        "The STO (SprogTeknologisk Ordbase) lexicon is a comprehensive computational lexicon of Danish developed for NLP/HLT applications. The syntax layer of the lexicon, presented here in Lexical Markup Format (LMF), contains a vocabulary of 84,159 entries (nouns, verbs and adjectives). The syntax is linked to the morphological layer through ID's.\r\nThe Lexical Markup Language is an internationally well\u2010known and accepted XML format and the ISO standard for Natural Language Processing (NLP) lexicons. See www.lexicalmarkupframework.org for more information on LMF and the attached documentation for the marke-up of STO.\r\nSTO LMF is created within the framework of the EU project MetaNord, and was carried out by Center for Language Technology (CST) in 2011 - 2013"
-    ],
-    "oai_identifier": [
-        "oai:repository.clarin.dk:20.500.12115/23"
-    ],
-    "oai_set": [
-        "hdl_20.500.12115_1",
-        "hdl_20.500.12115_3"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "syntax"
-        },
-        {
-            "name": "LMF"
-        }
-    ],
-    "title": [
-        "STO syntax (v2) - LMF format"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1a2c0e18-370a-5f84-8180-6dfc5e4b54f1.json b/oaitestdata/clarin-oai_dc/SET_1/json/1a2c0e18-370a-5f84-8180-6dfc5e4b54f1.json
deleted file mode 100644
index 5c61e3bb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1a2c0e18-370a-5f84-8180-6dfc5e4b54f1.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Simov, Kiril"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Bulgarian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-238",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-238"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-238",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Bulgaria"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-238;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;BulTreeBank Frequency List;Simov, Kiril;100 000 most frequent Cyrillic tokens in the BulTreeBank text archive, UTF-16 list of token-frequency pairs;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-238;bul;downloadable_files_count: 0;Bulgaria;http://www.bultreebank.org/resources/BTB-FreqList100000.zip",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1a2c0e18-370a-5f84-8180-6dfc5e4b54f1",
-    "notes": [
-        "100 000 most frequent Cyrillic tokens in the BulTreeBank text archive, UTF-16 list of token-frequency pairs"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-238"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "BulTreeBank Frequency List"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1a3de987-45a5-55c6-9566-79ce08ba5326.json b/oaitestdata/clarin-oai_dc/SET_1/json/1a3de987-45a5-55c6-9566-79ce08ba5326.json
deleted file mode 100644
index a6b5b0e2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1a3de987-45a5-55c6-9566-79ce08ba5326.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Slovenian",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1061",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1061"
-    ],
-    "PID": "http://hdl.handle.net/11356/1061",
-    "PublicationTimestamp": "2016-03-10T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/324414"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN.SI User Licence for Internet Corpora",
-        "ACA",
-        "http://www.clarin.si/info/wp-content/uploads/2016/01/CLARIN.SI-WAC-2016-01.pdf"
-    ],
-    "author": [
-        "Espl\u00e0-Gomis, Miquel",
-        "Klubi\u010dka, Filip",
-        "Ortiz Rojas, Sergio",
-        "Ljube\u0161i\u0107, Nikola",
-        "Toral, Antonio"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1061;2019-02-23T17:12:01Z;hdl_11356_1023;hdl_11356_1024;Slovene-English parallel corpus slenWaC 1.0;Ljube\u0161i\u0107, Nikola;Espl\u00e0-Gomis, Miquel;Ortiz Rojas, Sergio;Klubi\u010dka, Filip;Toral, Antonio;parallel corpus;web corpus;multilingual;The slenWaC corpus version 1.0 consists of parallel Slovene-English texts crawled from the .si top-level domain for Slovenia. The corpus was built with Spidextor (https://github.com/abumatran/spidextor), a tool that glues together the output of SpiderLing used for crawling and Bitextor used for bitext extraction. The accuracy of the extracted bitext on the segment level is around 67% and on the word level around 68%.;2016-03-10;corpus;http://hdl.handle.net/11356/1061;slv;eng;info:eu-repo/grantAgreement/EC/FP7/324414;CLARIN.SI User Licence for Internet Corpora;ACA;http://www.clarin.si/info/wp-content/uploads/2016/01/CLARIN.SI-WAC-2016-01.pdf;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;Jo\u017eef Stefan Institute",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1a3de987-45a5-55c6-9566-79ce08ba5326",
-    "notes": [
-        "The slenWaC corpus version 1.0 consists of parallel Slovene-English texts crawled from the .si top-level domain for Slovenia. The corpus was built with Spidextor (https://github.com/abumatran/spidextor), a tool that glues together the output of SpiderLing used for crawling and Bitextor used for bitext extraction. The accuracy of the extracted bitext on the segment level is around 67% and on the word level around 68%."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1061"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parallel corpus"
-        },
-        {
-            "name": "web corpus"
-        },
-        {
-            "name": "multilingual"
-        }
-    ],
-    "title": [
-        "Slovene-English parallel corpus slenWaC 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1a43ad7d-9599-5685-b111-72688bcfede7.json b/oaitestdata/clarin-oai_dc/SET_1/json/1a43ad7d-9599-5685-b111-72688bcfede7.json
deleted file mode 100644
index 8f9352b6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1a43ad7d-9599-5685-b111-72688bcfede7.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "University of Amsterdam",
-        "Radboud University Nijmegen",
-        "Utrecht University"
-    ],
-    "Contributor": [
-        "Crasborn, Onno"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-623",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-623"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-623",
-    "PublicationTimestamp": "2010-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "University of Amsterdam",
-        "Radboud University Nijmegen",
-        "Utrecht University"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-623;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Visual Database for Sign Language (VISIBASE);Crasborn, Onno;The Visibase corpus is the outcome of a NWO Investment Grant (1996-2001), which aimed to digitise and describe all sign language video material that was present in the late 1990s at the sign language research groups at the University of Amsterdam and at Leiden University. In the course of the project, all analogue video tapes were copied to professional digital video tapes (DVCAM). Fragments of the 300+ hour corpus have been converted to MPEG-1 and MPEG-2 files.;2010;corpus;http://hdl.handle.net/11372/LRT-623;downloadable_files_count: 0;Netherlands (the);Radboud University Nijmegen;University of Amsterdam;Utrecht University;http://corpus1.mpi.nl/ds/imdi_browser/?openpath=MPI319375%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1a43ad7d-9599-5685-b111-72688bcfede7",
-    "notes": [
-        "The Visibase corpus is the outcome of a NWO Investment Grant (1996-2001), which aimed to digitise and describe all sign language video material that was present in the late 1990s at the sign language research groups at the University of Amsterdam and at Leiden University. In the course of the project, all analogue video tapes were copied to professional digital video tapes (DVCAM). Fragments of the 300+ hour corpus have been converted to MPEG-1 and MPEG-2 files."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-623"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Visual Database for Sign Language (VISIBASE)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1a6affc5-dc12-5ef4-ad04-1384e043e33d.json b/oaitestdata/clarin-oai_dc/SET_1/json/1a6affc5-dc12-5ef4-ad04-1384e043e33d.json
deleted file mode 100644
index 8d96ac43..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1a6affc5-dc12-5ef4-ad04-1384e043e33d.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4073",
-    "MetadataAccess": [
-        "oai:ota:oucs:4073"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Burke, Edmund, 1729-1797."
-    ],
-    "fulltext": "oai:ota:oucs:4073;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4073.xml;Observations on a late state of the nation;Burke, Edmund, 1729-1797.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1a6affc5-dc12-5ef4-ad04-1384e043e33d",
-    "oai_identifier": [
-        "oai:ota:oucs:4073"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Observations on a late state of the nation"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4073.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1a6c7b6d-c7f2-5c43-842c-c650ec83b347.json b/oaitestdata/clarin-oai_dc/SET_1/json/1a6c7b6d-c7f2-5c43-842c-c650ec83b347.json
deleted file mode 100644
index f2e90239..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1a6c7b6d-c7f2-5c43-842c-c650ec83b347.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Comeyne, Robrecht"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Modern Greek (1453-)",
-        "Turkish",
-        "Arabic",
-        "Hebrew"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-597",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-597"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-597",
-    "PublicationTimestamp": "2002-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2002"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-597;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;OrienTel Telephone databases;Comeyne, Robrecht;Multilingual access to interactive communication services for the Mediterranean and the Middle East;Collection of telephone databases from mediterranean region, incl. (variants of) Arabic. 500-1000 speakers per database, all orthographically transcribed. Speaker information regarding gender, age and accent. Phonetic lexicons included.;2002;corpus;http://hdl.handle.net/11372/LRT-597;ell;tur;ara;heb;downloadable_files_count: 0;http://www.speechdat.org/ORIENTEL/index.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1a6c7b6d-c7f2-5c43-842c-c650ec83b347",
-    "notes": [
-        "Collection of telephone databases from mediterranean region, incl. (variants of) Arabic. 500-1000 speakers per database, all orthographically transcribed. Speaker information regarding gender, age and accent. Phonetic lexicons included."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-597"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [],
-    "title": [
-        "OrienTel Telephone databases"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1a6e0973-2c6c-57f4-9c6f-734ee68d76cb.json b/oaitestdata/clarin-oai_dc/SET_1/json/1a6e0973-2c6c-57f4-9c6f-734ee68d76cb.json
deleted file mode 100644
index 5a558edd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1a6e0973-2c6c-57f4-9c6f-734ee68d76cb.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Craig, Hugh"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 188 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1436",
-    "MetadataAccess": [
-        "oai:ota:oucs:1436"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Jonson, Ben, 1573?-1637"
-    ],
-    "fulltext": "oai:ota:oucs:1436;2018-02-16T10:42:06Z;http://ota.ox.ac.uk/headers/1436.xml;Cynthia's revels [1601] / Ben Jonson;Jonson, Ben, 1573?-1637;text_and_corpus_linguistics;English drama -- 17th century;Oxford Text Archive, University of Oxford;Craig, Hugh;(1 file : ca. 188 KB);Text;Plays;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1a6e0973-2c6c-57f4-9c6f-734ee68d76cb",
-    "oai_identifier": [
-        "oai:ota:oucs:1436"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- th century"
-        }
-    ],
-    "title": [
-        "Cynthia's revels [1601] / Ben Jonson"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1436.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1a7153e8-d6d7-580a-b206-8fd394690b73.json b/oaitestdata/clarin-oai_dc/SET_1/json/1a7153e8-d6d7-580a-b206-8fd394690b73.json
deleted file mode 100644
index 26acb1a0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1a7153e8-d6d7-580a-b206-8fd394690b73.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "Georgian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-954",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-954"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-954",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-954;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Old Georgian;ca. 4.000.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-954;kat;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#georgant",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1a7153e8-d6d7-580a-b206-8fd394690b73",
-    "notes": [
-        "ca. 4.000.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-954"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Old Georgian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1a7751f4-d7ad-5c51-afdc-4bc38a73ef5c.json b/oaitestdata/clarin-oai_dc/SET_1/json/1a7751f4-d7ad-5c51-afdc-4bc38a73ef5c.json
deleted file mode 100644
index f6c5eb42..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1a7751f4-d7ad-5c51-afdc-4bc38a73ef5c.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "\u017beromski"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 6",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/97",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/97"
-    ],
-    "PID": "http://hdl.handle.net/11321/97",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "\u017beromski"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "\u017beromski, \u017beromski"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/97;2015-05-19T13:33:42Z;hdl_11321_3;hdl_11321_4;MWE \u017beromski;\u017beromski, \u017beromski;\u017beromski;2015-04-08;corpus;http://hdl.handle.net/11321/97;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 6;\u017beromski",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1a7751f4-d7ad-5c51-afdc-4bc38a73ef5c",
-    "notes": [
-        "\u017beromski"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/97"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE \u017beromski"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1a8c83b4-f842-5e83-9882-5c2e9f937145.json b/oaitestdata/clarin-oai_dc/SET_1/json/1a8c83b4-f842-5e83-9882-5c2e9f937145.json
deleted file mode 100644
index 6789e609..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1a8c83b4-f842-5e83-9882-5c2e9f937145.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Huet, G\u00e9rard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Sanskrit"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-976",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-976"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-976",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "France"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-976;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Sanskrit Heritage Site;Huet, G\u00e9rard;Hypertext encyclopedia of Indian Culture, arranged according to Sanskrit entries. The site \"also gives access to automated lexical and grammatical resources for Sanskrit\".;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-976;san;downloadable_files_count: 0;France;http://sanskrit.inria.fr/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1a8c83b4-f842-5e83-9882-5c2e9f937145",
-    "notes": [
-        "Hypertext encyclopedia of Indian Culture, arranged according to Sanskrit entries. The site \"also gives access to automated lexical and grammatical resources for Sanskrit\"."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-976"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Sanskrit Heritage Site"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1aa2309d-2dae-55e3-91f8-402ab0f35cef.json b/oaitestdata/clarin-oai_dc/SET_1/json/1aa2309d-2dae-55e3-91f8-402ab0f35cef.json
deleted file mode 100644
index f761fac6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1aa2309d-2dae-55e3-91f8-402ab0f35cef.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4800",
-    "MetadataAccess": [
-        "oai:ota:oucs:4800"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Betterton, Thomas, 1635?-1710."
-    ],
-    "fulltext": "oai:ota:oucs:4800;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4800.xml;The amorous widow: or, the wanton wife. A comedy. As it is perform'd by Her Majesty's servants. Written by the late famous Mr. Thomas Betterton. Now first printed from the original copy.;Betterton, Thomas, 1635?-1710.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1aa2309d-2dae-55e3-91f8-402ab0f35cef",
-    "oai_identifier": [
-        "oai:ota:oucs:4800"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The amorous widow: or, the wanton wife. A comedy. As it is perform'd by Her Majesty's servants. Written by the late famous Mr. Thomas Betterton. Now first printed from the original copy."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4800.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1aad6f74-e10c-5bc8-a044-a245174e36d5.json b/oaitestdata/clarin-oai_dc/SET_1/json/1aad6f74-e10c-5bc8-a044-a245174e36d5.json
deleted file mode 100644
index b9ba2f34..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1aad6f74-e10c-5bc8-a044-a245174e36d5.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3586",
-    "MetadataAccess": [
-        "oai:ota:oucs:3586"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Churchill, Charles, 1731-1764."
-    ],
-    "fulltext": "oai:ota:oucs:3586;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3586.xml;The candidate. A poem. By C. Churchill;Churchill, Charles, 1731-1764.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1aad6f74-e10c-5bc8-a044-a245174e36d5",
-    "oai_identifier": [
-        "oai:ota:oucs:3586"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The candidate. A poem. By C. Churchill"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3586.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1abdcae6-3438-5cef-a6c9-9b108edd7025.json b/oaitestdata/clarin-oai_dc/SET_1/json/1abdcae6-3438-5cef-a6c9-9b108edd7025.json
deleted file mode 100644
index feaa818f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1abdcae6-3438-5cef-a6c9-9b108edd7025.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain",
-        "(1 file : ca. 39 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0037",
-    "MetadataAccess": [
-        "oai:ota:oucs:0037"
-    ],
-    "PublicationTimestamp": "1594-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1594"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Daniel, Samuel, 1562-1619"
-    ],
-    "fulltext": "oai:ota:oucs:0037;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0037.xml;Rosamund;The complaint of Rosamond;Daniel, Samuel, 1562-1619;1594;text_and_corpus_linguistics;Poems -- England -- 16th century;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 39 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1abdcae6-3438-5cef-a6c9-9b108edd7025",
-    "oai_identifier": [
-        "oai:ota:oucs:0037"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- England -- th century"
-        }
-    ],
-    "title": [
-        "Rosamund",
-        "The complaint of Rosamond"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0037.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1acf2da0-e89b-53cb-b3ad-624e7aee22db.json b/oaitestdata/clarin-oai_dc/SET_1/json/1acf2da0-e89b-53cb-b3ad-624e7aee22db.json
deleted file mode 100644
index 7751133a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1acf2da0-e89b-53cb-b3ad-624e7aee22db.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/108",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/108"
-    ],
-    "PID": "http://hdl.handle.net/10794/108",
-    "PublicationTimestamp": "2014-10-06T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/108;2017-10-25T06:31:39Z;hdl_10794_1;hdl_10794_2;Blog mix 2014 (2017-02-24);Bloggmix 2014 (2017-02-24);n/a, n/a;Swedish;Blog;The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.;Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat.;2014-10-06;corpus;http://hdl.handle.net/10794/108;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/bloggmix2014",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1acf2da0-e89b-53cb-b3ad-624e7aee22db",
-    "notes": [
-        "The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.",
-        "Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/108"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Blog"
-        }
-    ],
-    "title": [
-        "Blog mix 2014 (2017-02-24)",
-        "Bloggmix 2014 (2017-02-24)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1aefbfe7-57ef-5031-9cd2-9493c6c9366f.json b/oaitestdata/clarin-oai_dc/SET_1/json/1aefbfe7-57ef-5031-9cd2-9493c6c9366f.json
deleted file mode 100644
index be5b0e74..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1aefbfe7-57ef-5031-9cd2-9493c6c9366f.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/93",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/93"
-    ],
-    "PID": "http://hdl.handle.net/10794/93",
-    "PublicationTimestamp": "2013-03-06T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/93;2017-10-25T11:51:27Z;hdl_10794_1;hdl_10794_2;Blog mix 1999 (2017-02-17);Bloggmix 1999 (2017-02-17);n/a, n/a;Swedish;Blog;The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.;Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat.;2013-03-06;corpus;http://hdl.handle.net/10794/93;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/bloggmix1999",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1aefbfe7-57ef-5031-9cd2-9493c6c9366f",
-    "notes": [
-        "The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.",
-        "Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/93"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Blog"
-        }
-    ],
-    "title": [
-        "Blog mix 1999 (2017-02-17)",
-        "Bloggmix 1999 (2017-02-17)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1afb5c61-9b11-5cb0-b68c-33953887a04c.json b/oaitestdata/clarin-oai_dc/SET_1/json/1afb5c61-9b11-5cb0-b68c-33953887a04c.json
deleted file mode 100644
index b87e72eb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1afb5c61-9b11-5cb0-b68c-33953887a04c.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4958",
-    "MetadataAccess": [
-        "oai:ota:oucs:4958"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Sidney, Algernon, 1622-1683."
-    ],
-    "fulltext": "oai:ota:oucs:4958;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4958.xml;Letters of the Honourable Algernon Sydney, to the Honourable Henry Savile. Ambassador in France. In the year 1679, &c. Now first printed from the originals in Mr. Sydney's own hand;Sidney, Algernon, 1622-1683.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1afb5c61-9b11-5cb0-b68c-33953887a04c",
-    "oai_identifier": [
-        "oai:ota:oucs:4958"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Letters of the Honourable Algernon Sydney, to the Honourable Henry Savile. Ambassador in France. In the year 1679, &c. Now first printed from the originals in Mr. Sydney's own hand"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4958.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1b21146e-f691-51fd-80df-810686ee6833.json b/oaitestdata/clarin-oai_dc/SET_1/json/1b21146e-f691-51fd-80df-810686ee6833.json
deleted file mode 100644
index 609d5ecc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1b21146e-f691-51fd-80df-810686ee6833.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "less than 512 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1328",
-    "MetadataAccess": [
-        "oai:ota:oucs:1328"
-    ],
-    "PublicationYear": [
-        "Unspecified"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Satires"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Crown,  Mr.  (John),  1640?-1712"
-    ],
-    "fulltext": "oai:ota:oucs:1328;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1328.xml; City politiques  / compiled by David Bond;Crown,  Mr.  (John),  1640?-1712;Unspecified;text_and_corpus_linguistics;Satires -- England -- 17th century;eng;Oxford Text Archive, University of Oxford;less than 512 KB;Text;Satires;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1b21146e-f691-51fd-80df-810686ee6833",
-    "oai_identifier": [
-        "oai:ota:oucs:1328"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Satires -- England -- th century"
-        }
-    ],
-    "title": [
-        " City politiques  / compiled by David Bond"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1328.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1b21282f-eb58-588a-9c2c-c6ba693a6f80.json b/oaitestdata/clarin-oai_dc/SET_1/json/1b21282f-eb58-588a-9c2c-c6ba693a6f80.json
deleted file mode 100644
index d918b80d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1b21282f-eb58-588a-9c2c-c6ba693a6f80.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-AAFE-A",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-AAFE-A"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0006-AAFE-A",
-    "PublicationTimestamp": "2012-05-22T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Haji\u010d, Jan",
-        "Homola, Petr",
-        "Kubo\u0148, Vladislav"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-AAFE-A;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;\u010ces\u00edlko;Haji\u010d, Jan;Kubo\u0148, Vladislav;Homola, Petr;machine translation;Czech-Slovak translation;\u010ces\u00edlko is a tool enabling the fast and efficient translation from one source language into many target languages, which are mutually related.;2012-05-22;toolService;http://hdl.handle.net/11858/00-097C-0000-0006-AAFE-A;ces;Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0);http://creativecommons.org/licenses/by-nc-nd/3.0/;PUB;text/plain; charset=utf-8;application/x-gzip;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://quest.ms.mff.cuni.cz/cesilko/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1b21282f-eb58-588a-9c2c-c6ba693a6f80",
-    "notes": [
-        "\u010ces\u00edlko is a tool enabling the fast and efficient translation from one source language into many target languages, which are mutually related."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-AAFE-A"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "Czech-Slovak translation"
-        }
-    ],
-    "title": [
-        "\u010ces\u00edlko"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1b2dcde2-ee2e-54ca-84b8-58426309381f.json b/oaitestdata/clarin-oai_dc/SET_1/json/1b2dcde2-ee2e-54ca-84b8-58426309381f.json
deleted file mode 100644
index 55c86457..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1b2dcde2-ee2e-54ca-84b8-58426309381f.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/49",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/49"
-    ],
-    "PID": "http://hdl.handle.net/10794/49",
-    "PublicationTimestamp": "2012-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/49;2017-10-27T16:51:54Z;hdl_10794_1;hdl_10794_2;Academic texts \u2013 Humanities 1997\u20132012 (2017-10-16);Akademiska texter \u2013 Humaniora 1997\u20132012 (2017-10-16);n/a, n/a;Swedish;Academic texts;Humanties;A corpus with academic texts from 1997\u20132012. The material is sentence scrambled.;En korpus med akademiska texter fr\u00e5n humaniora 1997\u20132012. Materialet \u00e4r meningsomkastat.;2012-05-30;corpus;http://hdl.handle.net/10794/49;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/sweachum",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1b2dcde2-ee2e-54ca-84b8-58426309381f",
-    "notes": [
-        "A corpus with academic texts from 1997\u20132012. The material is sentence scrambled.",
-        "En korpus med akademiska texter fr\u00e5n humaniora 1997\u20132012. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/49"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Academic texts"
-        },
-        {
-            "name": "Humanties"
-        }
-    ],
-    "title": [
-        "Academic texts \u2013 Humanities 1997\u20132012 (2017-10-16)",
-        "Akademiska texter \u2013 Humaniora 1997\u20132012 (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1b4098ab-2002-5a84-8173-7677b97d97e4.json b/oaitestdata/clarin-oai_dc/SET_1/json/1b4098ab-2002-5a84-8173-7677b97d97e4.json
deleted file mode 100644
index 5db41eb0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1b4098ab-2002-5a84-8173-7677b97d97e4.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=3986375c568611e2a2aa782bcb074135a5a6e077fbba41fea04b83c43bc70e1a",
-    "MetadataAccess": [
-        "3986375c568611e2a2aa782bcb074135a5a6e077fbba41fea04b83c43bc70e1a"
-    ],
-    "PublicationTimestamp": "2013-01-04T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "3986375c568611e2a2aa782bcb074135a5a6e077fbba41fea04b83c43bc70e1a;2018-11-15T16:39:59Z;toolService;toolService:suiteOfTools;ComLinToo: The Computational Linguistics Toolset;The Computational Linguistics Toolset is a set of tools for computational linguistics. It contains re-usable code for cleaning, splitting, refining, and taking samples from corpora (ICE, Penn, and a native one), for tagging them using the TnT-tagger, for doing permutation statistics on N-grams (useful for finding statistically significant syntactical differences between any two sets of tagged texts), and various examination-tools. The tools themselves are well documented;2013-01-04",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1b4098ab-2002-5a84-8173-7677b97d97e4",
-    "notes": [
-        "The Computational Linguistics Toolset is a set of tools for computational linguistics. It contains re-usable code for cleaning, splitting, refining, and taking samples from corpora (ICE, Penn, and a native one), for tagging them using the TnT-tagger, for doing permutation statistics on N-grams (useful for finding statistically significant syntactical differences between any two sets of tagged texts), and various examination-tools. The tools themselves are well documented"
-    ],
-    "oai_identifier": [
-        "3986375c568611e2a2aa782bcb074135a5a6e077fbba41fea04b83c43bc70e1a"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:suiteOfTools"
-    ],
-    "state": "active",
-    "title": [
-        "ComLinToo: The Computational Linguistics Toolset"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1b599955-cdc5-587a-a8ca-a3b050efd044.json b/oaitestdata/clarin-oai_dc/SET_1/json/1b599955-cdc5-587a-a8ca-a3b050efd044.json
deleted file mode 100644
index 4befae66..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1b599955-cdc5-587a-a8ca-a3b050efd044.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5532",
-    "MetadataAccess": [
-        "oai:ota:oucs:5532"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Skrimshire, F. (Fenwick), 1774 or 5-1855."
-    ],
-    "fulltext": "oai:ota:oucs:5532;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5532.xml;Information to parents respecting the vaccine inoculation: or, the inoculation for cow-pox. By F. Skrimshire, M.D.;Skrimshire, F. (Fenwick), 1774 or 5-1855.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1b599955-cdc5-587a-a8ca-a3b050efd044",
-    "oai_identifier": [
-        "oai:ota:oucs:5532"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Information to parents respecting the vaccine inoculation: or, the inoculation for cow-pox. By F. Skrimshire, M.D."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5532.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1bad1e6b-a060-5576-b2a3-fcb074669302.json b/oaitestdata/clarin-oai_dc/SET_1/json/1bad1e6b-a060-5576-b2a3-fcb074669302.json
deleted file mode 100644
index a49a9e15..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1bad1e6b-a060-5576-b2a3-fcb074669302.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Center for Dutch Language and Speech, University of Antwerp"
-    ],
-    "Contributor": [
-        "Daelemans, Walter"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-638",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-638"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-638",
-    "PublicationTimestamp": "2008-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2008"
-    ],
-    "Publisher": [
-        "Center for Dutch Language and Speech, University of Antwerp"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Belgium"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-638;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Luo Corpus;Daelemans, Walter;Document classification (based on web-mining);2008;corpus;http://hdl.handle.net/11372/LRT-638;downloadable_files_count: 0;Belgium;Center for Dutch Language and Speech, University of Antwerp;http://aflat.org",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1bad1e6b-a060-5576-b2a3-fcb074669302",
-    "notes": [
-        "Document classification (based on web-mining)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-638"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Luo Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1bb1b3f4-eaeb-56f7-9344-b5b2b7d7c2a3.json b/oaitestdata/clarin-oai_dc/SET_1/json/1bb1b3f4-eaeb-56f7-9344-b5b2b7d7c2a3.json
deleted file mode 100644
index 9ddc527d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1bb1b3f4-eaeb-56f7-9344-b5b2b7d7c2a3.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1010",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1010"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1010",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1010;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LAC Chontal Corpus;Language and Cognition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1010;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI33437%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1bb1b3f4-eaeb-56f7-9344-b5b2b7d7c2a3",
-    "notes": [
-        "Language and Cognition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1010"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LAC Chontal Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1bc427db-e575-52ad-a511-3b437668fa55.json b/oaitestdata/clarin-oai_dc/SET_1/json/1bc427db-e575-52ad-a511-3b437668fa55.json
deleted file mode 100644
index e378afac..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1bc427db-e575-52ad-a511-3b437668fa55.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Fryske Akademy"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2192",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2192"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2192",
-    "PublicationTimestamp": "2017-05-29T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Fryske Akademy"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU General Public License 2 or later (GPL-2.0)",
-        "http://opensource.org/licenses/GPL-2.0",
-        "PUB"
-    ],
-    "author": [
-        "Van de Velde, Hans",
-        "Heeringa, Wilbert"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2192;2017-06-06T08:24:13Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Visible Vowels;Van de Velde, Hans;Heeringa, Wilbert;language variation;dialect variation;f0;formants;duration;normalization;visualization;phonetics;This program enables the user to visualize f0 contours, to plot vowels in the F1/F2 space for multiple points in the vowel interval, e.g. at 20%, 50% and 80%, and to visualize vowel durations.\r\n\r\n(The tool is implemented in R. We used the following packages: phonR, gplots, plotrix, lattice, readxl, WriteXLS, DT,\r\n psych and pracma. We thank the developers of these packages.);2017-05-29;toolService;http://hdl.handle.net/11372/LRT-2192;GNU General Public License 2 or later (GPL-2.0);http://opensource.org/licenses/GPL-2.0;PUB;application/vnd.openxmlformats-officedocument.spreadsheetml.sheet;text/plain; charset=utf-8;downloadable_files_count: 1;Fryske Akademy;https://fryske-akademy.nl/fa-apps/VisVow/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1bc427db-e575-52ad-a511-3b437668fa55",
-    "notes": [
-        "This program enables the user to visualize f0 contours, to plot vowels in the F1/F2 space for multiple points in the vowel interval, e.g. at 20%, 50% and 80%, and to visualize vowel durations.\r\n\r\n(The tool is implemented in R. We used the following packages: phonR, gplots, plotrix, lattice, readxl, WriteXLS, DT,\r\n psych and pracma. We thank the developers of these packages.)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2192"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "language variation"
-        },
-        {
-            "name": "dialect variation"
-        },
-        {
-            "name": "formants"
-        },
-        {
-            "name": "duration"
-        },
-        {
-            "name": "normalization"
-        },
-        {
-            "name": "visualization"
-        },
-        {
-            "name": "phonetics"
-        }
-    ],
-    "title": [
-        "Visible Vowels"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1bda8344-4e4a-5bf3-a7a0-538b6f0c374d.json b/oaitestdata/clarin-oai_dc/SET_1/json/1bda8344-4e4a-5bf3-a7a0-538b6f0c374d.json
deleted file mode 100644
index bd1aa8b9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1bda8344-4e4a-5bf3-a7a0-538b6f0c374d.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "University of Surrey, Surrey Morphology Group"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-727",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-727"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-727",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Surrey, Surrey Morphology Group"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-727;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Slavonic Colour Lexicon;Full report on the research activities and results of the project: Predicting the past: reconstructing the Slavonic colour lexicon;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-727;downloadable_files_count: 0;Germany;University of Surrey, Surrey Morphology Group;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI318941%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1bda8344-4e4a-5bf3-a7a0-538b6f0c374d",
-    "notes": [
-        "Full report on the research activities and results of the project: Predicting the past: reconstructing the Slavonic colour lexicon"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-727"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Slavonic Colour Lexicon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1be84bcc-ff0e-5e5f-be2e-ccbd6f698dcc.json b/oaitestdata/clarin-oai_dc/SET_1/json/1be84bcc-ff0e-5e5f-be2e-ccbd6f698dcc.json
deleted file mode 100644
index 34d68de9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1be84bcc-ff0e-5e5f-be2e-ccbd6f698dcc.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Girona City Council"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Catalan",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1118",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1118"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1118",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Girona City Council"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1118;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Digitized Press;digitized corpus;Collection of different digitized mastheads in Catalan and Spanish, covering a time span from 1808 to 2008. The collection, which is kept in the Girona City Council Archive, totals 1.599.733  digitized pages.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1118;cat;spa;downloadable_files_count: 0;Spain;Girona City Council;http://www.girona.cat/sgdap/cat/premsa.php",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1be84bcc-ff0e-5e5f-be2e-ccbd6f698dcc",
-    "notes": [
-        "Collection of different digitized mastheads in Catalan and Spanish, covering a time span from 1808 to 2008. The collection, which is kept in the Girona City Council Archive, totals 1.599.733  digitized pages."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1118"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "digitized corpus"
-        }
-    ],
-    "title": [
-        "Digitized Press"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1bee339d-c42e-53de-9029-d0d4b6b2ea90.json b/oaitestdata/clarin-oai_dc/SET_1/json/1bee339d-c42e-53de-9029-d0d4b6b2ea90.json
deleted file mode 100644
index de7ba0d6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1bee339d-c42e-53de-9029-d0d4b6b2ea90.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 147 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0051",
-    "MetadataAccess": [
-        "oai:ota:oucs:0051"
-    ],
-    "PublicationTimestamp": "1526-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1526"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Erasmus, Desiderius, d. 1536"
-    ],
-    "fulltext": "oai:ota:oucs:0051;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0051.xml;De immensa Dei misericordia. English;De immensa Dei misericordia : a sermon of the excedynge great mercy of God / made by the most famous doctour maister Erasmus Roterodamus ; translated out of Latine into Englisshe at the request of the most honourable and vertuous lady, the Lady Margaret Countese of Salisbury;Erasmus, Desiderius, d. 1536;1526;text_and_corpus_linguistics;Addresses;Sermons;Translations -- England -- 16th century;eng;Oxford Text Archive, University of Oxford;(1 file : ca. 147 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1bee339d-c42e-53de-9029-d0d4b6b2ea90",
-    "oai_identifier": [
-        "oai:ota:oucs:0051"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Addresses"
-        },
-        {
-            "name": "Sermons"
-        },
-        {
-            "name": "Translations -- England -- th century"
-        }
-    ],
-    "title": [
-        "De immensa Dei misericordia. English",
-        "De immensa Dei misericordia : a sermon of the excedynge great mercy of God / made by the most famous doctour maister Erasmus Roterodamus ; translated out of Latine into Englisshe at the request of the most honourable and vertuous lady, the Lady Margaret Countese of Salisbury"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0051.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1bfb53f1-022b-5b2e-8929-45c66e4d3a83.json b/oaitestdata/clarin-oai_dc/SET_1/json/1bfb53f1-022b-5b2e-8929-45c66e4d3a83.json
deleted file mode 100644
index f376f164..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1bfb53f1-022b-5b2e-8929-45c66e4d3a83.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/34",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/34"
-    ],
-    "PID": "http://hdl.handle.net/11321/34",
-    "PublicationTimestamp": "2011-06-14T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "\u015aniatowski, Tomasz",
-        "Wardy\u0144ski, Adam",
-        "Radziszewski, Adam"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/34;2016-01-21T14:35:40Z;hdl_11321_3;hdl_11321_4;WCCL;Radziszewski, Adam;Wardy\u0144ski, Adam;\u015aniatowski, Tomasz;WCCL (Wroc\u0142aw Corpus Constraint Language) is a formalism for writing functional expressions evaluated on morpho-syntactically annotated text. These expressions may be used directly as features for Machine Learning classification.\r\n\r\nImplementation-wise, WCCL is a set of simple command-line utils, as well as the underlying C++ library with Python wrappers, suitable for rapid development of taggers, chunkers, etc.\r\n\r\nWCCL is targeted at Polish, although the only obstacle to processing other inflectional languages is probably the assumed string representation of tags and corpus I/O formats.;2011-06-14;toolService;http://hdl.handle.net/11321/34;pol;downloadable_files_count: 0;Wroc\u0142aw University of Technology;http://nlp.pwr.wroc.pl/redmine/projects/joskipi/wiki/Install",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1bfb53f1-022b-5b2e-8929-45c66e4d3a83",
-    "notes": [
-        "WCCL (Wroc\u0142aw Corpus Constraint Language) is a formalism for writing functional expressions evaluated on morpho-syntactically annotated text. These expressions may be used directly as features for Machine Learning classification.\r\n\r\nImplementation-wise, WCCL is a set of simple command-line utils, as well as the underlying C++ library with Python wrappers, suitable for rapid development of taggers, chunkers, etc.\r\n\r\nWCCL is targeted at Polish, although the only obstacle to processing other inflectional languages is probably the assumed string representation of tags and corpus I/O formats."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/34"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "WCCL"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1c169a39-152f-5bce-9ecd-88fa647bad37.json b/oaitestdata/clarin-oai_dc/SET_1/json/1c169a39-152f-5bce-9ecd-88fa647bad37.json
deleted file mode 100644
index 4ae6a877..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1c169a39-152f-5bce-9ecd-88fa647bad37.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4709",
-    "MetadataAccess": [
-        "oai:ota:oucs:4709"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hume, David, 1711-1776."
-    ],
-    "fulltext": "oai:ota:oucs:4709;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4709.xml;The history of England: under the House of Tudor. ... By David Hume, Esq; In two volumes. ... [pt.1];Hume, David, 1711-1776.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1c169a39-152f-5bce-9ecd-88fa647bad37",
-    "oai_identifier": [
-        "oai:ota:oucs:4709"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The history of England: under the House of Tudor. ... By David Hume, Esq; In two volumes. ... [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4709.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1c3bd563-a7fb-5be6-8da8-818c01aa9d6f.json b/oaitestdata/clarin-oai_dc/SET_1/json/1c3bd563-a7fb-5be6-8da8-818c01aa9d6f.json
deleted file mode 100644
index 4fe1e0ff..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1c3bd563-a7fb-5be6-8da8-818c01aa9d6f.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Michael More"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/vnd.oasis.opendocument.text",
-        "downloadable_files_count: 14",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/474",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/474"
-    ],
-    "PID": "http://hdl.handle.net/11321/474",
-    "PublicationTimestamp": "2018-05-19T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Michael More"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "plWordNet",
-        "http://clarin-pl.eu/en/licenses/plwordnet-2/",
-        "PUB"
-    ],
-    "author": [
-        "More, Michael"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/474;2018-05-19T08:43:00Z;hdl_11321_3;hdl_11321_4;Sanda\u0142y sanda\u0142y;More, Michael;warsztaty;lingwistylka;korpus warsztatowy;2018-05-19;corpus;http://hdl.handle.net/11321/474;pol;plWordNet;http://clarin-pl.eu/en/licenses/plwordnet-2/;PUB;text/plain; charset=utf-8;text/plain;text/plain;text/plain;text/plain;application/vnd.oasis.opendocument.text;text/plain;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.oasis.opendocument.text;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;downloadable_files_count: 14;Michael More",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1c3bd563-a7fb-5be6-8da8-818c01aa9d6f",
-    "notes": [
-        "korpus warsztatowy"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/474"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "warsztaty"
-        },
-        {
-            "name": "lingwistylka"
-        }
-    ],
-    "title": [
-        "Sanda\u0142y sanda\u0142y"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1c4040fb-bea2-5359-b1c6-6cd9bafd4e81.json b/oaitestdata/clarin-oai_dc/SET_1/json/1c4040fb-bea2-5359-b1c6-6cd9bafd4e81.json
deleted file mode 100644
index 8e8c66e7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1c4040fb-bea2-5359-b1c6-6cd9bafd4e81.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2874",
-    "MetadataAccess": [
-        "oai:ota:oucs:2874"
-    ],
-    "PublicationTimestamp": "1726-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1726"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2874;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2874.xml;Gulliver's Travels;Swift, Jonathan, 1667-1745;1726;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1c4040fb-bea2-5359-b1c6-6cd9bafd4e81",
-    "oai_identifier": [
-        "oai:ota:oucs:2874"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Gulliver's Travels"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2874.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1c44120f-a060-5ffe-93f5-1cbe0bfb6928.json b/oaitestdata/clarin-oai_dc/SET_1/json/1c44120f-a060-5ffe-93f5-1cbe0bfb6928.json
deleted file mode 100644
index e718ecef..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1c44120f-a060-5ffe-93f5-1cbe0bfb6928.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "University of Tartu"
-    ],
-    "Contributor": [
-        "Habicht, K\u00fclli"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Estonian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-644",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-644"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-644",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Tartu"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Estonia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-644;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Corpus of Old Written Estonian;Habicht, K\u00fclli;Corpus of texts written fully or partly in Estonian, from 13.-19. century; 1,5 million words;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-644;est;downloadable_files_count: 0;Estonia;University of Tartu;http://www.murre.ut.ee/vakkur/Korpused/korpused.htm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1c44120f-a060-5ffe-93f5-1cbe0bfb6928",
-    "notes": [
-        "Corpus of texts written fully or partly in Estonian, from 13.-19. century; 1,5 million words"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-644"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus of Old Written Estonian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1c6130db-2da1-516a-9c7b-e09598af2a16.json b/oaitestdata/clarin-oai_dc/SET_1/json/1c6130db-2da1-516a-9c7b-e09598af2a16.json
deleted file mode 100644
index 643bc544..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1c6130db-2da1-516a-9c7b-e09598af2a16.json
+++ /dev/null
@@ -1,95 +0,0 @@
-{
-    "Contact": [
-        "Lehrstuhl Englische Sprach- und \u00dcbersetzungswissenschaft, Fakult\u00e4t P, Fachrichtung Sprachwissenschaft und Sprachtechnologie, Universit\u00e4t des Saarlandes, Campus A2.2, 66123 Saarbr\u00fccken, Germany"
-    ],
-    "Contributor": [
-        "J\u00f6rg Knappen",
-        "Stefan Fischer",
-        "Stefania Degaetano-Ortlieb",
-        "Elke Teich",
-        "Hannah Kermes",
-        "Katrin Menzel"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:rsc-v4",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:rsc-v4"
-    ],
-    "PID": "http://hdl.handle.net/21.11119/0000-0001-7E8B-6",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Lehrstuhl Englische Sprach- und \u00dcbersetzungswissenschaft, Fakult\u00e4t P, Fachrichtung Sprachwissenschaft und Sprachtechnologie, Universit\u00e4t des Saarlandes, Campus A2.2, 66123 Saarbr\u00fccken, Germany"
-    ],
-    "RelatedIdentifier": [
-        "Kermes, Hannah, Stefania Degaetano, Ashraf Khamis, J\u00f6rg Knappen, and Elke Teich. 2016. \u201cThe Royal Society Corpus: From Uncharted Data to Corpus.\u201d In Proceedings of the LREC 2016. Portoroz, Slovenia. http://www.lrec-conf.org/proceedings/lrec2016/summaries/792.html",
-        "Teich, Elke, Stefania Degaetano-Ortlieb, Stefan Fischer, Hannah Kermes, Ashraf Khamis, and J\u00f6rg Knappen, \"The Royal Society Corpus\", hdl:11858/00-246C-0000-0023-8D26-7, 2016",
-        "Knappen, J\u00f6rg, Fischer, Stefan, Kermes, Hannah, Teich, Elke, and Fankhauser, Peter. 2017. \"The Making of the Royal Society Corpus.\" In Proceedings of the NoDaLiDa 2017 Workshop on Processing Historical Language. G\u00f6teborg, Sweden. Link\u00f6ping University Electronic Press. http://www.ep.liu.se/ecp/article.asp?issue=133%26article=003"
-    ],
-    "ResourceType": [
-        "Collection",
-        "Written Corpus",
-        "Diachronic Corpus"
-    ],
-    "Rights": [
-        "CC-BY-SA-NC-4.0"
-    ],
-    "SpatialCoverage": [
-        "1665/1869",
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " period : ( 1665-07-01T11:59:59Z - None ) ",
-    "author": [
-        "Elke Teich, Lehrstuhl Englische Sprach- und \u00dcbersetzungswissenschaft, Fakult\u00e4t P, Fachrichtung Sprachwissenschaft und Sprachtechnologie, Universit\u00e4t des Saarlandes, Campus A2.2, 66123 Saarbr\u00fccken, Germany"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:rsc-v4;2018-06-27T13:53:53Z;The Royal Society Corpus Version 4.0;Elke Teich, Lehrstuhl Englische Sprach- und \u00dcbersetzungswissenschaft, Fakult\u00e4t P, Fachrichtung Sprachwissenschaft und Sprachtechnologie, Universit\u00e4t des Saarlandes, Campus A2.2, 66123 Saarbr\u00fccken, Germany;Early Modern English;Late Modern English;Science;Scientific English;Language change;The Royal Society Corpus (RSC) is based on the first two centuries of the Philosophical Transactions of the Royal Society of London from its beginning in 1665 to 1869. It includes all publications of the journal written mainly in English and containing running text. The Philosophical Transactions was the first periodical of scientific writing in England.\n\nThe RSC Version 4 consists of approximately 32 million tokens and is encoded for text type (abstracts, articles), author, year of publication. Information about decade and 50-year periods are also available allowing for a diachronic analysis of different granularity. We also annotate the two most important topics of each text according to a topic model consisting of 24 topics. The full topic model is also available for download.\n\nThe corpus is tokenized and linguistically annotated for lemma and part-of-speech using TreeTagger (Schmid 1994, Schmid 1995). For spelling normalization we use a trained model of VARD (Baron and Rayson 2008). As a special feature, we encode with each unit (word token) its average surprisal, i.e. the average amount of information it encodes in number of bits, with words as units and trigram as contexts [cf. Genzel and Charniak 2002).\n\nThe release 4.0 of the corpus includes an improved OCR correction and removal of non-text tokens like formul\u00e6 and tables.;Lehrstuhl Englische Sprach- und \u00dcbersetzungswissenschaft, Fakult\u00e4t P, Fachrichtung Sprachwissenschaft und Sprachtechnologie, Universit\u00e4t des Saarlandes, Campus A2.2, 66123 Saarbr\u00fccken, Germany;Elke Teich;Stefania Degaetano-Ortlieb;Stefan Fischer;Hannah Kermes;J\u00f6rg Knappen;Katrin Menzel;2018;Collection;Written Corpus;Diachronic Corpus;text/xml;clarind-uds:rsc-v4;hdl:21.11119/0000-0001-7E8B-6;eng;Kermes, Hannah, Stefania Degaetano, Ashraf Khamis, J\u00f6rg Knappen, and Elke Teich. 2016. \u201cThe Royal Society Corpus: From Uncharted Data to Corpus.\u201d In Proceedings of the LREC 2016. Portoroz, Slovenia. http://www.lrec-conf.org/proceedings/lrec2016/summaries/792.html;Teich, Elke, Stefania Degaetano-Ortlieb, Stefan Fischer, Hannah Kermes, Ashraf Khamis, and J\u00f6rg Knappen, \"The Royal Society Corpus\", hdl:11858/00-246C-0000-0023-8D26-7, 2016;Knappen, J\u00f6rg, Fischer, Stefan, Kermes, Hannah, Teich, Elke, and Fankhauser, Peter. 2017. \"The Making of the Royal Society Corpus.\" In Proceedings of the NoDaLiDa 2017 Workshop on Processing Historical Language. G\u00f6teborg, Sweden. Link\u00f6ping University Electronic Press. http://www.ep.liu.se/ecp/article.asp?issue=133%26article=003;1665/1869;United Kingdom;CC-BY-SA-NC-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1c6130db-2da1-516a-9c7b-e09598af2a16",
-    "notes": [
-        "The Royal Society Corpus (RSC) is based on the first two centuries of the Philosophical Transactions of the Royal Society of London from its beginning in 1665 to 1869. It includes all publications of the journal written mainly in English and containing running text. The Philosophical Transactions was the first periodical of scientific writing in England.\n\nThe RSC Version 4 consists of approximately 32 million tokens and is encoded for text type (abstracts, articles), author, year of publication. Information about decade and 50-year periods are also available allowing for a diachronic analysis of different granularity. We also annotate the two most important topics of each text according to a topic model consisting of 24 topics. The full topic model is also available for download.\n\nThe corpus is tokenized and linguistically annotated for lemma and part-of-speech using TreeTagger (Schmid 1994, Schmid 1995). For spelling normalization we use a trained model of VARD (Baron and Rayson 2008). As a special feature, we encode with each unit (word token) its average surprisal, i.e. the average amount of information it encodes in number of bits, with words as units and trigram as contexts [cf. Genzel and Charniak 2002).\n\nThe release 4.0 of the corpus includes an improved OCR correction and removal of non-text tokens like formul\u00e6 and tables."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:rsc-v4"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Early Modern English"
-        },
-        {
-            "name": "Late Modern English"
-        },
-        {
-            "name": "Science"
-        },
-        {
-            "name": "Scientific English"
-        },
-        {
-            "name": "Language change"
-        }
-    ],
-    "title": [
-        "The Royal Society Corpus Version 4.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1c6dc327-71b8-5679-a99c-cd9dc9a4cf77.json b/oaitestdata/clarin-oai_dc/SET_1/json/1c6dc327-71b8-5679-a99c-cd9dc9a4cf77.json
deleted file mode 100644
index 263be20a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1c6dc327-71b8-5679-a99c-cd9dc9a4cf77.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5686",
-    "MetadataAccess": [
-        "oai:ota:oucs:5686"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Howlett, John, 1731-1804."
-    ],
-    "fulltext": "oai:ota:oucs:5686;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5686.xml;Observations on the increased population, healthiness, &c. of the town of Maidstone;Howlett, John, 1731-1804.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1c6dc327-71b8-5679-a99c-cd9dc9a4cf77",
-    "oai_identifier": [
-        "oai:ota:oucs:5686"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Observations on the increased population, healthiness, &c. of the town of Maidstone"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5686.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1c93a0b1-b541-5465-8b76-f17f5f7c242e.json b/oaitestdata/clarin-oai_dc/SET_1/json/1c93a0b1-b541-5465-8b76-f17f5f7c242e.json
deleted file mode 100644
index acdb0ed5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1c93a0b1-b541-5465-8b76-f17f5f7c242e.json
+++ /dev/null
@@ -1,99 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 3",
-        "application/pdf",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Serbian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1171",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1171"
-    ],
-    "PID": "http://hdl.handle.net/11356/1171",
-    "PublicationTimestamp": "2017-12-16T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "http://dx.doi.org/10.4312/slo2.0.2016.2.156-188",
-        "http://hdl.handle.net/11356/1120"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "Erjavec, Toma\u017e",
-        "Samard\u017ei\u0107, Tanja",
-        "Ljube\u0161i\u0107, Nikola",
-        "Mili\u010devi\u0107, Maja"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1171;2018-10-24T20:48:18Z;hdl_11356_1023;hdl_11356_1024;Serbian Twitter training corpus ReLDI-NormTagNER-sr 2.0;Ljube\u0161i\u0107, Nikola;Erjavec, Toma\u017e;Mili\u010devi\u0107, Maja;Samard\u017ei\u0107, Tanja;computer-mediated communication;tokenisation;word normalisation;tagging;lemmatisation;named entities;manual annotation;TEI;ReLDI-NormTagNER-sr 2.0 is a manually annotated corpus of Serbian tweets. It is meant as a gold-standard training and testing dataset for tokenisation, sentence segmentation, word normalisation, morphosyntactic tagging, lemmatisation and named entity recognition of non-standard Serbian. Each tweet is also annotated for its automatically assigned standardness levels (T = technical standardness, L = linguistic standardness). As an update to version 1.1, 2.0 adds annotations for named entities.;2017-12-16;corpus;http://hdl.handle.net/11356/1171;srp;http://dx.doi.org/10.4312/slo2.0.2016.2.156-188;http://hdl.handle.net/11356/1120;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;https://creativecommons.org/licenses/by/4.0/;application/zip;application/zip;application/pdf;text/plain; charset=utf-8;downloadable_files_count: 3;Jo\u017eef Stefan Institute;https://reldi.spur.uzh.ch/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1c93a0b1-b541-5465-8b76-f17f5f7c242e",
-    "notes": [
-        "ReLDI-NormTagNER-sr 2.0 is a manually annotated corpus of Serbian tweets. It is meant as a gold-standard training and testing dataset for tokenisation, sentence segmentation, word normalisation, morphosyntactic tagging, lemmatisation and named entity recognition of non-standard Serbian. Each tweet is also annotated for its automatically assigned standardness levels (T = technical standardness, L = linguistic standardness). As an update to version 1.1, 2.0 adds annotations for named entities."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1171"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "computer-mediated communication"
-        },
-        {
-            "name": "tokenisation"
-        },
-        {
-            "name": "word normalisation"
-        },
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "lemmatisation"
-        },
-        {
-            "name": "named entities"
-        },
-        {
-            "name": "manual annotation"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "Serbian Twitter training corpus ReLDI-NormTagNER-sr 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1c978843-b2b1-5cea-a95b-d4fd7a7ddaf7.json b/oaitestdata/clarin-oai_dc/SET_1/json/1c978843-b2b1-5cea-a95b-d4fd7a7ddaf7.json
deleted file mode 100644
index 16f92d2b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1c978843-b2b1-5cea-a95b-d4fd7a7ddaf7.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 28.6 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1318",
-    "MetadataAccess": [
-        "oai:ota:oucs:1318"
-    ],
-    "PublicationTimestamp": "1658-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1658"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "D'Avenant, William, Sir, 1606-1688"
-    ],
-    "fulltext": "oai:ota:oucs:1318;2018-03-07T11:52:24Z;http://ota.ox.ac.uk/headers/1318.xml;The cruelty of the Spaniards in Peru : exprest by instrumentall and vocall musick and by art of perspective in scenes, &c / [by Sir William D'Avenant] represented daily at the *Cockpit* in Drury-Lane at three after noone punctually;D'Avenant, William, Sir, 1606-1688;1658;text_and_corpus_linguistics;Plays -- England -- 17th century;Operas -- England -- 17th century;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 28.6 KB);Text;Plays;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1c978843-b2b1-5cea-a95b-d4fd7a7ddaf7",
-    "oai_identifier": [
-        "oai:ota:oucs:1318"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        },
-        {
-            "name": "Operas -- England -- th century"
-        }
-    ],
-    "title": [
-        "The cruelty of the Spaniards in Peru : exprest by instrumentall and vocall musick and by art of perspective in scenes, &c / [by Sir William D'Avenant] represented daily at the *Cockpit* in Drury-Lane at three after noone punctually"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1318.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1ca0cf5f-5eb8-5c6f-b2c0-0be3536007a9.json b/oaitestdata/clarin-oai_dc/SET_1/json/1ca0cf5f-5eb8-5c6f-b2c0-0be3536007a9.json
deleted file mode 100644
index 1766c4f3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1ca0cf5f-5eb8-5c6f-b2c0-0be3536007a9.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "University of Lisbon, CLUL-Centro de Lingu\u00edstica da Universidade de Lisboa"
-    ],
-    "Contributor": [
-        "Mendes, Am\u00e1lia"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Portuguese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-206",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-206"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-206",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Lisbon, CLUL-Centro de Lingu\u00edstica da Universidade de Lisboa"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Portugal"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-206;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;CORDIAL-SIN;Mendes, Am\u00e1lia;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-206;por;downloadable_files_count: 0;Portugal;University of Lisbon, CLUL-Centro de Lingu\u00edstica da Universidade de Lisboa;http://www.clul.ul.pt/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1ca0cf5f-5eb8-5c6f-b2c0-0be3536007a9",
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-206"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "CORDIAL-SIN"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1ca1ebaa-9ca3-51be-9174-469f7bcff75f.json b/oaitestdata/clarin-oai_dc/SET_1/json/1ca1ebaa-9ca3-51be-9174-469f7bcff75f.json
deleted file mode 100644
index 6f7349c5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1ca1ebaa-9ca3-51be-9174-469f7bcff75f.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Dell, Thomas"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 163 KB)",
-        "text/plain"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1981",
-    "MetadataAccess": [
-        "oai:ota:oucs:1981"
-    ],
-    "PublicationTimestamp": "1971-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1971"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Higgins, Colin, 1941-1988"
-    ],
-    "fulltext": "oai:ota:oucs:1981;2018-04-16T15:09:56Z;http://ota.ox.ac.uk/headers/1981.xml;Harold and Maude / Colin Higgins;Higgins, Colin, 1941-1988;1971;text_and_corpus_linguistics;American fiction -- 20th century;Oxford Text Archive, University of Oxford;Dell, Thomas;text/plain;(1 file : ca. 163 KB);Text;Novels;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1ca1ebaa-9ca3-51be-9174-469f7bcff75f",
-    "oai_identifier": [
-        "oai:ota:oucs:1981"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "American fiction -- th century"
-        }
-    ],
-    "title": [
-        "Harold and Maude / Colin Higgins"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1981.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1ca4da02-d6f9-5bc1-9a40-38b16ff83b08.json b/oaitestdata/clarin-oai_dc/SET_1/json/1ca4da02-d6f9-5bc1-9a40-38b16ff83b08.json
deleted file mode 100644
index 540d3fd7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1ca4da02-d6f9-5bc1-9a40-38b16ff83b08.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Oxford University Computing Services"
-    ],
-    "Contributor": [
-        "Burnard, Lou",
-        "Dodd, Anthony"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-339",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-339"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-339",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Oxford University Computing Services"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-339;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;XAIRA;Burnard, Lou;Dodd, Anthony;Xaira is the current name for a new version of SARA, the text searching software originally developed at OUCS for use with the British National Corpus. This new version has been entirely re-written as a general purpose XML search engine, which will operate on any corpus of well-formed XML documents. It is however best used with TEI-conformant documents.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-339;downloadable_files_count: 0;Oxford University Computing Services;http://xaira.sourceforge.net/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1ca4da02-d6f9-5bc1-9a40-38b16ff83b08",
-    "notes": [
-        "Xaira is the current name for a new version of SARA, the text searching software originally developed at OUCS for use with the British National Corpus. This new version has been entirely re-written as a general purpose XML search engine, which will operate on any corpus of well-formed XML documents. It is however best used with TEI-conformant documents."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-339"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "XAIRA"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1ca613d4-ffb2-5eef-8a71-5b0033b463ab.json b/oaitestdata/clarin-oai_dc/SET_1/json/1ca613d4-ffb2-5eef-8a71-5b0033b463ab.json
deleted file mode 100644
index a99e787f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1ca613d4-ffb2-5eef-8a71-5b0033b463ab.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=bf3f3ddae6f111e6a2aa782bcb07413596226304088749ceb1dd8cfa0a5bfdb3",
-    "MetadataAccess": [
-        "bf3f3ddae6f111e6a2aa782bcb07413596226304088749ceb1dd8cfa0a5bfdb3"
-    ],
-    "PublicationTimestamp": "2017-01-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "fulltext": "bf3f3ddae6f111e6a2aa782bcb07413596226304088749ceb1dd8cfa0a5bfdb3;2018-11-15T16:40:28Z;corpus;corpus:text;LX-LR4DistSemEval;A collection of language resources for the evaluation of distributional semantic models of Portuguese:\n\nLX-SimLex-999:\n http://metashare.metanet4u.eu/go2/lx-simlex-999\n\nLX-Rare Word Similarity Data set: \nhttp://metashare.metanet4u.eu/go2/lx-rare-word-similarity-dataset\n\nLX-WordSim-353:\nhttp://metashare.metanet4u.eu/go2/lx-wordsim-353\n\nLX-ESSLLI 2008:\nhttp://metashare.metanet4u.eu/go2/lx-esslli-2008\n\nLX-Battig:\nhttp://metashare.metanet4u.eu/go2/lx-battig\n\nLX-AP:\nhttp://metashare.metanet4u.eu/go2/lx-ap\n\nLX-4WAnalogies:\nhttp://metashare.metanet4u.eu/go2/lx-4wanalogies\n\nLX-4WAnalogiesBR:\nhttp://metashare.metanet4u.eu/go2/lx-4wanalogiesbr\n\nThey are also publicly available through github:\nhttps://github.com/nlx-group ;2017-01-30",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1ca613d4-ffb2-5eef-8a71-5b0033b463ab",
-    "notes": [
-        "A collection of language resources for the evaluation of distributional semantic models of Portuguese:\n\nLX-SimLex-999:\n http://metashare.metanet4u.eu/go2/lx-simlex-999\n\nLX-Rare Word Similarity Data set: \nhttp://metashare.metanet4u.eu/go2/lx-rare-word-similarity-dataset\n\nLX-WordSim-353:\nhttp://metashare.metanet4u.eu/go2/lx-wordsim-353\n\nLX-ESSLLI 2008:\nhttp://metashare.metanet4u.eu/go2/lx-esslli-2008\n\nLX-Battig:\nhttp://metashare.metanet4u.eu/go2/lx-battig\n\nLX-AP:\nhttp://metashare.metanet4u.eu/go2/lx-ap\n\nLX-4WAnalogies:\nhttp://metashare.metanet4u.eu/go2/lx-4wanalogies\n\nLX-4WAnalogiesBR:\nhttp://metashare.metanet4u.eu/go2/lx-4wanalogiesbr\n\nThey are also publicly available through github:\nhttps://github.com/nlx-group "
-    ],
-    "oai_identifier": [
-        "bf3f3ddae6f111e6a2aa782bcb07413596226304088749ceb1dd8cfa0a5bfdb3"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "LX-LR4DistSemEval"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1cac3142-2292-595c-b810-1a0eb8aca0e5.json b/oaitestdata/clarin-oai_dc/SET_1/json/1cac3142-2292-595c-b810-1a0eb8aca0e5.json
deleted file mode 100644
index f29acc3f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1cac3142-2292-595c-b810-1a0eb8aca0e5.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3354",
-    "MetadataAccess": [
-        "oai:ota:oucs:3354"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Whiston, William, 1667-1752."
-    ],
-    "fulltext": "oai:ota:oucs:3354;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3354.xml;Mr. Whiston's Letter of thanks to the Right Reverend the Lord Bishop of London: for his late letter to his clergy against the use of new forms of doxology, &c.;Whiston, William, 1667-1752.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1cac3142-2292-595c-b810-1a0eb8aca0e5",
-    "oai_identifier": [
-        "oai:ota:oucs:3354"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Mr. Whiston's Letter of thanks to the Right Reverend the Lord Bishop of London: for his late letter to his clergy against the use of new forms of doxology, &c."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3354.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1ce053c2-577a-5eb3-91e4-91faa15ac9b8.json b/oaitestdata/clarin-oai_dc/SET_1/json/1ce053c2-577a-5eb3-91e4-91faa15ac9b8.json
deleted file mode 100644
index 5baeb1d3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1ce053c2-577a-5eb3-91e4-91faa15ac9b8.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-87",
-    "MetadataAccess": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-87"
-    ],
-    "PID": "http://hdl.handle.net/20.500.11752/ILC-87",
-    "PublicationTimestamp": "2017-11-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "author": [
-        "AA. VV., AA. VV."
-    ],
-    "fulltext": "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-87;2018-07-23T09:13:44Z;hdl_000-c0-111_38;hdl_000-c0-111_49;Primo Levi Selected Works;AA. VV., AA. VV.;Nazi extermination camps;Imprisonment;Lager;Drama;This is a collection of some of Primo Levi's works:\r\n  Terza pagina (La stampa) (EINAUDI 1986) \r\n  Storie naturali (EINAUDI 1966) \r\n  Se questo \u00e8 un uomo (EINAUDI 1958) \r\n  Se non ora quando (Vol. II Einaudi 1988 --- da Ediz. EINAUDI 1981) \r\n  Lilit (EINUADI 1981) \r\n  L'altrui mestiere (EINAUDI 1985) \r\n  La tregua (EINAUDI 1981) \r\n  La ricerca delle radici La chiave a stella (Vol. II Einaudi 1988) \r\n  Il sistema periodico (EINAUDI 1975)\r\n  I sommersi e i salvati (Vol. I Einaudi 1987 --- da Ediz. Giulio Einaudi editore S.p.a. Torino Gli struzzi 1986) \r\n  Vizio di forma (Einaudi 1971)\r\n\r\nThis corpus was created in the 1990s.;2017-11-30;corpus;http://hdl.handle.net/20.500.11752/ILC-87;ita;downloadable_files_count: 0;Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1ce053c2-577a-5eb3-91e4-91faa15ac9b8",
-    "notes": [
-        "This is a collection of some of Primo Levi's works:\r\n  Terza pagina (La stampa) (EINAUDI 1986) \r\n  Storie naturali (EINAUDI 1966) \r\n  Se questo \u00e8 un uomo (EINAUDI 1958) \r\n  Se non ora quando (Vol. II Einaudi 1988 --- da Ediz. EINAUDI 1981) \r\n  Lilit (EINUADI 1981) \r\n  L'altrui mestiere (EINAUDI 1985) \r\n  La tregua (EINAUDI 1981) \r\n  La ricerca delle radici La chiave a stella (Vol. II Einaudi 1988) \r\n  Il sistema periodico (EINAUDI 1975)\r\n  I sommersi e i salvati (Vol. I Einaudi 1987 --- da Ediz. Giulio Einaudi editore S.p.a. Torino Gli struzzi 1986) \r\n  Vizio di forma (Einaudi 1971)\r\n\r\nThis corpus was created in the 1990s."
-    ],
-    "oai_identifier": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-87"
-    ],
-    "oai_set": [
-        "hdl_000-c0-111_38",
-        "hdl_000-c0-111_49"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Nazi extermination camps"
-        },
-        {
-            "name": "Imprisonment"
-        },
-        {
-            "name": "Lager"
-        },
-        {
-            "name": "Drama"
-        }
-    ],
-    "title": [
-        "Primo Levi Selected Works"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1ce60243-ad4f-5da8-9bf2-cf3071b506b7.json b/oaitestdata/clarin-oai_dc/SET_1/json/1ce60243-ad4f-5da8-9bf2-cf3071b506b7.json
deleted file mode 100644
index 411998e1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1ce60243-ad4f-5da8-9bf2-cf3071b506b7.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "SWPS University, Centre for Trauma, Crisis and Growth"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 3",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/455",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/455"
-    ],
-    "PID": "http://hdl.handle.net/11321/455",
-    "PublicationTimestamp": "2018-01-17T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "SWPS University, Centre for Trauma, Crisis and Growth"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN-EULA-ACA-v1.0",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca",
-        "ACA"
-    ],
-    "author": [
-        "Zi\u0119ba, Mariusz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/455;2018-01-17T17:25:25Z;hdl_11321_3;hdl_11321_4;Trauma i kryzys;Zi\u0119ba, Mariusz;trauma;crisis;narrative interviews;2018-01-17;corpus;http://hdl.handle.net/11321/455;pol;CLARIN-EULA-ACA-v1.0;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca;ACA;text/plain; charset=utf-8;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;downloadable_files_count: 3;SWPS University, Centre for Trauma, Crisis and Growth",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1ce60243-ad4f-5da8-9bf2-cf3071b506b7",
-    "notes": [
-        "narrative interviews"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/455"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "trauma"
-        },
-        {
-            "name": "crisis"
-        }
-    ],
-    "title": [
-        "Trauma i kryzys"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1cf32cbb-7d40-5c3c-9c49-6ba87d40fd96.json b/oaitestdata/clarin-oai_dc/SET_1/json/1cf32cbb-7d40-5c3c-9c49-6ba87d40fd96.json
deleted file mode 100644
index df50ec74..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1cf32cbb-7d40-5c3c-9c49-6ba87d40fd96.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1136",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1136"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1136",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1136;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Projekt Gutenberg;Germanistik;Access to novels, narratives, novellas, fairy tales, and legends; Zugriff auf Romane, Erz\u00e4hlungen, Novellen, M\u00e4rchen, Fabeln und Sagen;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1136;deu;downloadable_files_count: 0;Germany;http://gutenberg.spiegel.de/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1cf32cbb-7d40-5c3c-9c49-6ba87d40fd96",
-    "notes": [
-        "Access to novels, narratives, novellas, fairy tales, and legends; Zugriff auf Romane, Erz\u00e4hlungen, Novellen, M\u00e4rchen, Fabeln und Sagen"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1136"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Projekt Gutenberg"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1d1913a3-aad2-51d3-ba25-ec7e153b2a4c.json b/oaitestdata/clarin-oai_dc/SET_1/json/1d1913a3-aad2-51d3-ba25-ec7e153b2a4c.json
deleted file mode 100644
index 573683af..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1d1913a3-aad2-51d3-ba25-ec7e153b2a4c.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "Contributor": [
-        "Khayari, Mahjid",
-        "Schneider, St\u00e9phane"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "French"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-452",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-452"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-452",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "France"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-452;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TermSciences;Khayari, Mahjid;Schneider, St\u00e9phane;500.000 terms (fr, en, de, es), RDB / XML;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-452;fra;downloadable_files_count: 0;France;http://www.termsciences.fr/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1d1913a3-aad2-51d3-ba25-ec7e153b2a4c",
-    "notes": [
-        "500.000 terms (fr, en, de, es), RDB / XML"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-452"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TermSciences"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1d22af7e-bafe-5f09-bbbd-2a3473a31bfa.json b/oaitestdata/clarin-oai_dc/SET_1/json/1d22af7e-bafe-5f09-bbbd-2a3473a31bfa.json
deleted file mode 100644
index f58656cd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1d22af7e-bafe-5f09-bbbd-2a3473a31bfa.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Ibtikarat team"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/xml",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Arabic"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1937",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1937"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1937",
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Ibtikarat team"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)",
-        "http://creativecommons.org/licenses/by-nc/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Namly, Driss"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1937;2017-02-06T11:04:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;NAFIS Arabic Stemming Gold Standard Corpus;Namly, Driss;corpus;stemming;;Gold Standard Corpus;Normalized Arabic Fragments for Inestimable Stemming (NAFIS) is an Arabic stemming gold standard corpus composed by a collection of texts, selected to be representative of Arabic stemming tasks and manually annotated.;2016;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1937;ara;Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0);http://creativecommons.org/licenses/by-nc/4.0/;PUB;text/xml;text/plain; charset=utf-8;downloadable_files_count: 1;Ibtikarat team;http://arabic.emi.ac.ma/ibtikarat/?q=Resources",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1d22af7e-bafe-5f09-bbbd-2a3473a31bfa",
-    "notes": [
-        "Normalized Arabic Fragments for Inestimable Stemming (NAFIS) is an Arabic stemming gold standard corpus composed by a collection of texts, selected to be representative of Arabic stemming tasks and manually annotated."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1937"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "stemming"
-        },
-        {
-            "name": "Gold Standard Corpus"
-        }
-    ],
-    "title": [
-        "NAFIS Arabic Stemming Gold Standard Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1d320642-eea5-5b72-8f50-a0c792971ece.json b/oaitestdata/clarin-oai_dc/SET_1/json/1d320642-eea5-5b72-8f50-a0c792971ece.json
deleted file mode 100644
index 847ccdf2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1d320642-eea5-5b72-8f50-a0c792971ece.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-925",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-925"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-925",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-925;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Carian;ca. 700 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-925;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#kar",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1d320642-eea5-5b72-8f50-a0c792971ece",
-    "notes": [
-        "ca. 700 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-925"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Carian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1d3e88e6-3dea-51b9-8d10-fab4b959c452.json b/oaitestdata/clarin-oai_dc/SET_1/json/1d3e88e6-3dea-51b9-8d10-fab4b959c452.json
deleted file mode 100644
index 025bb31d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1d3e88e6-3dea-51b9-8d10-fab4b959c452.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Universit\u00e0 degli studi di Napoli Federico II"
-    ],
-    "Contributor": [
-        "Leoni, Federico Albano"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-865",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-865"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-865",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Universit\u00e0 degli studi di Napoli Federico II"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Italy"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-865;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;CLIPS : corpora e lessici di italiano parlato e scritto;Leoni, Federico Albano;Audio files of about 100 hours of speech from 15 different cities in Italy. Various recordings are transcribed to read in PDF;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-865;ita;downloadable_files_count: 0;Italy;Universit\u00e0 degli studi di Napoli Federico II;http://www.clips.unina.it/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1d3e88e6-3dea-51b9-8d10-fab4b959c452",
-    "notes": [
-        "Audio files of about 100 hours of speech from 15 different cities in Italy. Various recordings are transcribed to read in PDF"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-865"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "CLIPS : corpora e lessici di italiano parlato e scritto"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1d3ffa57-acf2-5daa-9e17-99ad8be14923.json b/oaitestdata/clarin-oai_dc/SET_1/json/1d3ffa57-acf2-5daa-9e17-99ad8be14923.json
deleted file mode 100644
index d4f35f21..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1d3ffa57-acf2-5daa-9e17-99ad8be14923.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Wroclaw University of Science and Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/298",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/298"
-    ],
-    "PID": "http://hdl.handle.net/11321/298",
-    "PublicationTimestamp": "2016-04-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroclaw University of Science and Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "Walkowiak, Tomasz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/298;2016-06-06T14:42:18Z;hdl_11321_3;hdl_11321_4;NLP Web services and  NLP workflow engine;Walkowiak, Tomasz;web services;NLP tools;language processing workflows;Web based system for natural language processing of texts in Polish. It allows running complex workflows of language and machine learning tools. Making it avaliable via REST Web Services.;2016-04-01;toolService;http://hdl.handle.net/11321/298;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;Wroclaw University of Science and Technology;http://ws.clarin-pl.eu/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1d3ffa57-acf2-5daa-9e17-99ad8be14923",
-    "notes": [
-        "Web based system for natural language processing of texts in Polish. It allows running complex workflows of language and machine learning tools. Making it avaliable via REST Web Services."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/298"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "web services"
-        },
-        {
-            "name": "NLP tools"
-        },
-        {
-            "name": "language processing workflows"
-        }
-    ],
-    "title": [
-        "NLP Web services and  NLP workflow engine"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1d63e2df-4385-5273-b57b-04b365785f6d.json b/oaitestdata/clarin-oai_dc/SET_1/json/1d63e2df-4385-5273-b57b-04b365785f6d.json
deleted file mode 100644
index acaeaa02..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1d63e2df-4385-5273-b57b-04b365785f6d.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3529",
-    "MetadataAccess": [
-        "oai:ota:oucs:3529"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Burke, Edmund, 1729-1797."
-    ],
-    "fulltext": "oai:ota:oucs:3529;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3529.xml;Mr. Burke's speech, in Westminster-Hall, on the 18th and 19th of February, 1788: with explanatory notes. ... With a preface, ...;Burke, Edmund, 1729-1797.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1d63e2df-4385-5273-b57b-04b365785f6d",
-    "oai_identifier": [
-        "oai:ota:oucs:3529"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Mr. Burke's speech, in Westminster-Hall, on the 18th and 19th of February, 1788: with explanatory notes. ... With a preface, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3529.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1d78d1de-311a-50fe-9b13-243988655a21.json b/oaitestdata/clarin-oai_dc/SET_1/json/1d78d1de-311a-50fe-9b13-243988655a21.json
deleted file mode 100644
index 990aa42b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1d78d1de-311a-50fe-9b13-243988655a21.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 75.7 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1621",
-    "MetadataAccess": [
-        "oai:ota:oucs:1621"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Marlowe, Christopher, 1564-1593"
-    ],
-    "fulltext": "oai:ota:oucs:1621;2018-02-16T10:42:06Z;http://ota.ox.ac.uk/headers/1621.xml;The tragical history of Doctor Faustus;Marlowe, Christopher, 1564-1593;default: 1976-01-01;text_and_corpus_linguistics;Plays -- England -- 17th century;eng;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 75.7 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1d78d1de-311a-50fe-9b13-243988655a21",
-    "oai_identifier": [
-        "oai:ota:oucs:1621"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        }
-    ],
-    "title": [
-        "The tragical history of Doctor Faustus"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1621.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1da0ca0c-6487-59f1-8b65-15bc1eecbaa1.json b/oaitestdata/clarin-oai_dc/SET_1/json/1da0ca0c-6487-59f1-8b65-15bc1eecbaa1.json
deleted file mode 100644
index 04091aa5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1da0ca0c-6487-59f1-8b65-15bc1eecbaa1.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2857",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2857"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2857",
-    "PublicationTimestamp": "2018-08-30T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU General Public Licence, version 3",
-        "http://opensource.org/licenses/GPL-3.0",
-        "PUB"
-    ],
-    "author": [
-        "Zeman, Daniel",
-        "Cardenas Acosta, Ronald"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2857;2018-08-31T17:26:47Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Morphological Analyzer for Shipibo-Konibo;Cardenas Acosta, Ronald;Zeman, Daniel;morphological analyzer;finite state transducer;This tool is the first morphological analyzer ever for this language.\r\nThe analyzer is a FST that produces all possible segmentations and tagging sequences in a word-by-word fashion.;2018-08-30;toolService;http://hdl.handle.net/11234/1-2857;shp;GNU General Public Licence, version 3;http://opensource.org/licenses/GPL-3.0;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://github.com/ronaldahmed/morph-shk",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1da0ca0c-6487-59f1-8b65-15bc1eecbaa1",
-    "notes": [
-        "This tool is the first morphological analyzer ever for this language.\r\nThe analyzer is a FST that produces all possible segmentations and tagging sequences in a word-by-word fashion."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2857"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphological analyzer"
-        },
-        {
-            "name": "finite state transducer"
-        }
-    ],
-    "title": [
-        "Morphological Analyzer for Shipibo-Konibo"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1dada85c-a518-57ac-bd8e-f604eaebfd82.json b/oaitestdata/clarin-oai_dc/SET_1/json/1dada85c-a518-57ac-bd8e-f604eaebfd82.json
deleted file mode 100644
index 4ee41f67..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1dada85c-a518-57ac-bd8e-f604eaebfd82.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5142",
-    "MetadataAccess": [
-        "oai:ota:oucs:5142"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Jephson, Robert, 1736-1803."
-    ],
-    "fulltext": "oai:ota:oucs:5142;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5142.xml;The confessions of James Baptiste Couteau: citizen of France, written by himself: and translated from the original French, by Robert Jephson, Esq. Illustrated with nine engravings. ... [pt.2];Jephson, Robert, 1736-1803.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1dada85c-a518-57ac-bd8e-f604eaebfd82",
-    "oai_identifier": [
-        "oai:ota:oucs:5142"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The confessions of James Baptiste Couteau: citizen of France, written by himself: and translated from the original French, by Robert Jephson, Esq. Illustrated with nine engravings. ... [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5142.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1db1452f-0d02-5b68-a852-947f8b98a21a.json b/oaitestdata/clarin-oai_dc/SET_1/json/1db1452f-0d02-5b68-a852-947f8b98a21a.json
deleted file mode 100644
index dd784f83..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1db1452f-0d02-5b68-a852-947f8b98a21a.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Krstev, Cvetana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Serbian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-499",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-499"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-499",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Serbia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-499;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;SrpRec - Serbian morphological electronic dictionary;Krstev, Cvetana;~83.000 lemmata; ~ 1.200.000 word forms, LADL-format;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-499;srp;downloadable_files_count: 0;Serbia;http://infolingu.univ-mlv.fr/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1db1452f-0d02-5b68-a852-947f8b98a21a",
-    "notes": [
-        "~83.000 lemmata; ~ 1.200.000 word forms, LADL-format"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-499"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "SrpRec - Serbian morphological electronic dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1db9e8f9-f693-5763-bd53-597364be327b.json b/oaitestdata/clarin-oai_dc/SET_1/json/1db9e8f9-f693-5763-bd53-597364be327b.json
deleted file mode 100644
index b2c9e640..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1db9e8f9-f693-5763-bd53-597364be327b.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Finnish",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1060",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1060"
-    ],
-    "PID": "http://hdl.handle.net/11356/1060",
-    "PublicationTimestamp": "2016-03-09T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/324414"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN.SI User Licence for Internet Corpora",
-        "ACA",
-        "http://www.clarin.si/info/wp-content/uploads/2016/01/CLARIN.SI-WAC-2016-01.pdf"
-    ],
-    "author": [
-        "Espl\u00e0-Gomis, Miquel",
-        "Klubi\u010dka, Filip",
-        "Ortiz Rojas, Sergio",
-        "Ljube\u0161i\u0107, Nikola",
-        "Toral, Antonio"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1060;2019-02-23T17:12:42Z;hdl_11356_1023;hdl_11356_1024;Finnish-English parallel corpus fienWaC 1.0;Ljube\u0161i\u0107, Nikola;Espl\u00e0-Gomis, Miquel;Ortiz Rojas, Sergio;Klubi\u010dka, Filip;Toral, Antonio;parallel corpus;web corpus;multilingual;The fienWaC corpus version 1.0 consists of parallel Finnish-English texts crawled from the .fi top-level domain for Finland. The corpus was built with Spidextor (https://github.com/abumatran/spidextor), a tool that glues together the output of SpiderLing used for crawling and Bitextor used for bitext extraction. The accuracy of the extracted bitext, given the evaluation results on other languages, can be estimated at 74% on the segment level and 76% on the word level.;2016-03-09;corpus;http://hdl.handle.net/11356/1060;fin;eng;info:eu-repo/grantAgreement/EC/FP7/324414;CLARIN.SI User Licence for Internet Corpora;ACA;http://www.clarin.si/info/wp-content/uploads/2016/01/CLARIN.SI-WAC-2016-01.pdf;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;Jo\u017eef Stefan Institute",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1db9e8f9-f693-5763-bd53-597364be327b",
-    "notes": [
-        "The fienWaC corpus version 1.0 consists of parallel Finnish-English texts crawled from the .fi top-level domain for Finland. The corpus was built with Spidextor (https://github.com/abumatran/spidextor), a tool that glues together the output of SpiderLing used for crawling and Bitextor used for bitext extraction. The accuracy of the extracted bitext, given the evaluation results on other languages, can be estimated at 74% on the segment level and 76% on the word level."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1060"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parallel corpus"
-        },
-        {
-            "name": "web corpus"
-        },
-        {
-            "name": "multilingual"
-        }
-    ],
-    "title": [
-        "Finnish-English parallel corpus fienWaC 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1dc06786-74b0-56b2-bff0-726fb4ae4f8c.json b/oaitestdata/clarin-oai_dc/SET_1/json/1dc06786-74b0-56b2-bff0-726fb4ae4f8c.json
deleted file mode 100644
index 33c4f10d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1dc06786-74b0-56b2-bff0-726fb4ae4f8c.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-160",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-160"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-160",
-    "PublicationTimestamp": "2014-06-24T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "author": [
-        "Stra\u0148\u00e1k, Pavel",
-        "Peterek, Nino",
-        "Bed\u0159ichov\u00e1, Zuzanna",
-        "\u0160ormov\u00e1, Kate\u0159ina",
-        "\u0160ebesta, Karel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-160;2018-07-02T22:05:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;ROMi 1.0;\u0160ebesta, Karel;Bed\u0159ichov\u00e1, Zuzanna;\u0160ormov\u00e1, Kate\u0159ina;Stra\u0148\u00e1k, Pavel;Peterek, Nino;ethnolect;spoken corpora;Czech of Romany pupils;ROMi represents a specific subcorpus of CZESL (Czech as a Second Language). It collects examples of language use, both spoken and written, of Czech Romani children and teen-agers. The range of materials exceeds 1,5 million words. \r\n\r\nLanguage Material\r\nThe material presents uses of spoken language by language-specific group of Romani speakers using Czech as their first language. However, this form of the language is specifically different from Czech as used by the Czech-speaking majority, both on the spoken and secondarily on the written level. It concerns the so-called Romani ethnolect of Czech, i.e. a variety of Czech used by Romani communities mainly in the Czech Republic. We may detect obvious influence of Romani, Slovak and Hungarian. Furthermore, many of the recorded speakers live in social exclusion and thus their language production is influenced by both factors, i.e. by Romani ethnolect and social exclusion.\r\n\r\nThe language material was collected in the years 2009 \u2013 2012 under the Education for Competitiveness Operational Programme, within the framework of the project Innovations of Czech as a Second Language Education collaboratively by the Technical University of Liberec and the Institute of Czech Language and Theory of Communication, Faculty of Arts, Charles University. The language material was processed with support of Institute of Formal and Applied Linguistics - project LINDAT-Clarin.\r\n\r\nIt concerns 110 recordings obtained in various environments \u2013 the collection of material took place both in schools and also in several non-profit organizations offering leisure time activities to Romani students. Apart from the school setting, the recordings thus come from the environment of extracurricular activities, sport matches and households. Both the respondents and the collectors are Romani. The samples were acquired in all regions of the Czech Republic, although the majority of recordings were obtained in the Central Bohemia, South Bohemia, \u00dast\u00ed and Vyso\u010dina Region. The age of the respondents ranges from 12 to 28 years. The collected samples are also accompanied by metadata relating to the following areas:\r\nThe collected samples are accompanied by metadata relating to the following areas:\r\n\u2022\tThe place of origin (the place of collection, the size of the residence and dialect area, region, environment (school, extracurricular, private); socially excluded locality.\r\n\u2022\tThe circumstances of the collection expressing the extent of control exercised by the collector (topic assigned/non-assigned).\r\n\u2022\tThe respondent (the age of the student; class/year; sex; type of the school; subjective knowledge of Romani; first language \u2013 the one the student considers to be his first; communicative environment in the family \u2013 which language(s) is/are used for communication in the family. \r\n\u2022\tThe place of data collection \u2013 in the case of schools metadata comprise characteristics of the type of school (primary, for students with special needs, remedial, vocational, secondary), the founder (state, church, private organisation), in the case of the place of individual collection of data you may find organisation, interest group markings, etc.\r\n\u2022\tThe collector (the abbreviation of collector\u00b4s name and his work area, in some cases also his age).\r\n\r\nDelimiting the group of respondents\r\nThe respondents are constituted by students of primary schools, schools for students with special needs, secondary schools and by teenagers who have just completed the compulsory education. For the purposes of the language material collection, those students who consider themselves to be Romani or who are considered Romani by others were included to the sample. Moreover, a language criterion was added to this definition - thus those students in whose families Romani is spoken at home were also included. Active knowledge of the Romani language was not required since hardly a third of Romani children living in the Czech Republic nowadays is competent in this language.\r\n\r\nEthical aspects of the data collection and processing\r\nAs regards the content of the language material, it places demands on the data processing from the ethical point of view. Frequently, the texts and recordings feature highly interesting material; the respondents talk about their life stories fully distant or inconceivable for the social majority. During the transcription process, all materials are anonymized and identification data are removed. \r\n\r\nField Research\r\n\r\nWhen dealing with the environment threatened by social exclusion, it is highly important to consider especially the needs and opportunities of the group members as well as the needs of those individuals, who find themselves or work in such an environment. During the developmental process of the corpus, we became decidedly convinced that it is necessary to accommodate different demands on material quality of texts and recordings and not to overburden both the respondents and the collectors with limiting or impossible requirements. Therefore, the corpus comprises several recordings of lower technical quality which were acquired in the presence of other persons, with the television turned on, etc. Firstly, the recordings would not even have come into existence under different circumstances \u2013 it is natural that the interviewing of younger children was taking place directly in their households, in the presence of their parents. Secondly, the recordings would have been made, yet they would have been influenced by the unnaturalness of the situation, consequently affecting the language material. Apart from the interviews with younger children, it regards especially those conversations between the collectros and their peers, e.g. inside leisure time clubs.\r\n\r\nCharacteristics of the recordings\r\nThe collected recordings come both from the school environment (especially conversations of teacher assistants with individual students) and from the leisure time facilities (interest groups, after-school tutoring). In most cases it concerns conversations of the collector and the individual, alternatively a pair of respondents. The length of the recordings differs, although the majority ranges from 20 to 35 minutes. A single recording approximately contains 2 495 words. The quality of recordings is influenced by the limits of field-utilizable technologies and the effort to increase authenticity to the maximum.\r\n\r\nTranscription of the recordings\r\nThe rules for transcription of the recordings are based on similar ones designed for SCHOLA corpus. Transcriptions are carried out by the means of folkloristic transcription, i.e. the closest to the written record, especially adapted for the purposes of computational processing, following the practice established in the Czech National Corpus. The transcription is performed with the help of the Transcriber programme, which connects the sound and graphic track.;2014-06-24;corpus;http://hdl.handle.net/11234/1-160;ces;downloadable_files_count: 0;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://lindat.mff.cuni.cz/services/dialogy.org",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1dc06786-74b0-56b2-bff0-726fb4ae4f8c",
-    "notes": [
-        "ROMi represents a specific subcorpus of CZESL (Czech as a Second Language). It collects examples of language use, both spoken and written, of Czech Romani children and teen-agers. The range of materials exceeds 1,5 million words. \r\n\r\nLanguage Material\r\nThe material presents uses of spoken language by language-specific group of Romani speakers using Czech as their first language. However, this form of the language is specifically different from Czech as used by the Czech-speaking majority, both on the spoken and secondarily on the written level. It concerns the so-called Romani ethnolect of Czech, i.e. a variety of Czech used by Romani communities mainly in the Czech Republic. We may detect obvious influence of Romani, Slovak and Hungarian. Furthermore, many of the recorded speakers live in social exclusion and thus their language production is influenced by both factors, i.e. by Romani ethnolect and social exclusion.\r\n\r\nThe language material was collected in the years 2009 \u2013 2012 under the Education for Competitiveness Operational Programme, within the framework of the project Innovations of Czech as a Second Language Education collaboratively by the Technical University of Liberec and the Institute of Czech Language and Theory of Communication, Faculty of Arts, Charles University. The language material was processed with support of Institute of Formal and Applied Linguistics - project LINDAT-Clarin.\r\n\r\nIt concerns 110 recordings obtained in various environments \u2013 the collection of material took place both in schools and also in several non-profit organizations offering leisure time activities to Romani students. Apart from the school setting, the recordings thus come from the environment of extracurricular activities, sport matches and households. Both the respondents and the collectors are Romani. The samples were acquired in all regions of the Czech Republic, although the majority of recordings were obtained in the Central Bohemia, South Bohemia, \u00dast\u00ed and Vyso\u010dina Region. The age of the respondents ranges from 12 to 28 years. The collected samples are also accompanied by metadata relating to the following areas:\r\nThe collected samples are accompanied by metadata relating to the following areas:\r\n\u2022\tThe place of origin (the place of collection, the size of the residence and dialect area, region, environment (school, extracurricular, private); socially excluded locality.\r\n\u2022\tThe circumstances of the collection expressing the extent of control exercised by the collector (topic assigned/non-assigned).\r\n\u2022\tThe respondent (the age of the student; class/year; sex; type of the school; subjective knowledge of Romani; first language \u2013 the one the student considers to be his first; communicative environment in the family \u2013 which language(s) is/are used for communication in the family. \r\n\u2022\tThe place of data collection \u2013 in the case of schools metadata comprise characteristics of the type of school (primary, for students with special needs, remedial, vocational, secondary), the founder (state, church, private organisation), in the case of the place of individual collection of data you may find organisation, interest group markings, etc.\r\n\u2022\tThe collector (the abbreviation of collector\u00b4s name and his work area, in some cases also his age).\r\n\r\nDelimiting the group of respondents\r\nThe respondents are constituted by students of primary schools, schools for students with special needs, secondary schools and by teenagers who have just completed the compulsory education. For the purposes of the language material collection, those students who consider themselves to be Romani or who are considered Romani by others were included to the sample. Moreover, a language criterion was added to this definition - thus those students in whose families Romani is spoken at home were also included. Active knowledge of the Romani language was not required since hardly a third of Romani children living in the Czech Republic nowadays is competent in this language.\r\n\r\nEthical aspects of the data collection and processing\r\nAs regards the content of the language material, it places demands on the data processing from the ethical point of view. Frequently, the texts and recordings feature highly interesting material; the respondents talk about their life stories fully distant or inconceivable for the social majority. During the transcription process, all materials are anonymized and identification data are removed. \r\n\r\nField Research\r\n\r\nWhen dealing with the environment threatened by social exclusion, it is highly important to consider especially the needs and opportunities of the group members as well as the needs of those individuals, who find themselves or work in such an environment. During the developmental process of the corpus, we became decidedly convinced that it is necessary to accommodate different demands on material quality of texts and recordings and not to overburden both the respondents and the collectors with limiting or impossible requirements. Therefore, the corpus comprises several recordings of lower technical quality which were acquired in the presence of other persons, with the television turned on, etc. Firstly, the recordings would not even have come into existence under different circumstances \u2013 it is natural that the interviewing of younger children was taking place directly in their households, in the presence of their parents. Secondly, the recordings would have been made, yet they would have been influenced by the unnaturalness of the situation, consequently affecting the language material. Apart from the interviews with younger children, it regards especially those conversations between the collectros and their peers, e.g. inside leisure time clubs.\r\n\r\nCharacteristics of the recordings\r\nThe collected recordings come both from the school environment (especially conversations of teacher assistants with individual students) and from the leisure time facilities (interest groups, after-school tutoring). In most cases it concerns conversations of the collector and the individual, alternatively a pair of respondents. The length of the recordings differs, although the majority ranges from 20 to 35 minutes. A single recording approximately contains 2 495 words. The quality of recordings is influenced by the limits of field-utilizable technologies and the effort to increase authenticity to the maximum.\r\n\r\nTranscription of the recordings\r\nThe rules for transcription of the recordings are based on similar ones designed for SCHOLA corpus. Transcriptions are carried out by the means of folkloristic transcription, i.e. the closest to the written record, especially adapted for the purposes of computational processing, following the practice established in the Czech National Corpus. The transcription is performed with the help of the Transcriber programme, which connects the sound and graphic track."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-160"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ethnolect"
-        },
-        {
-            "name": "spoken corpora"
-        },
-        {
-            "name": "Czech Romany pupils"
-        }
-    ],
-    "title": [
-        "ROMi 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1dc297f8-b2f8-5645-8bd4-3c229e7ad7e1.json b/oaitestdata/clarin-oai_dc/SET_1/json/1dc297f8-b2f8-5645-8bd4-3c229e7ad7e1.json
deleted file mode 100644
index 9109fa91..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1dc297f8-b2f8-5645-8bd4-3c229e7ad7e1.json
+++ /dev/null
@@ -1,106 +0,0 @@
-{
-    "Contact": [
-        "Pedagogical University of Krak\u00f3w",
-        "Jagiellonian University"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 100",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/57",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/57"
-    ],
-    "PID": "http://hdl.handle.net/11321/57",
-    "PublicationTimestamp": "2015-03-18T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Pedagogical University of Krak\u00f3w",
-        "Jagiellonian University"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Eder, Maciej",
-        "Rybicki, Jan"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/57;2015-04-02T08:22:10Z;hdl_11321_3;hdl_11321_4;Late 19th- and Early 20th-Century Polish Novels;Eder, Maciej;Rybicki, Jan;prose;novel;literature;19th-century novels;20th-century novels;positivism in Poland;proza;powie\u015b\u0107;literatura;powie\u015b\u0107 XIX-wieczna;powie\u015b\u0107 XX-wieczna;pozytywizm w Polsce;Corpus of late 19th- and early 20th-century literary texts intended as benchmark collection for text categorization. It contains 100 Polish novels written by various authors. Each text is stored as separate .txt file.;2015-03-18;corpus;http://hdl.handle.net/11321/57;pol;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain; charset=utf-8;downloadable_files_count: 100;Pedagogical University of Krak\u00f3w;Jagiellonian University",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1dc297f8-b2f8-5645-8bd4-3c229e7ad7e1",
-    "notes": [
-        "Corpus of late 19th- and early 20th-century literary texts intended as benchmark collection for text categorization. It contains 100 Polish novels written by various authors. Each text is stored as separate .txt file."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/57"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "prose"
-        },
-        {
-            "name": "novel"
-        },
-        {
-            "name": "literature"
-        },
-        {
-            "name": "th-century novels"
-        },
-        {
-            "name": "th-century novels"
-        },
-        {
-            "name": "positivism Poland"
-        },
-        {
-            "name": "proza"
-        },
-        {
-            "name": "proza"
-        },
-        {
-            "name": "literatura"
-        },
-        {
-            "name": "literatura"
-        },
-        {
-            "name": "literatura"
-        },
-        {
-            "name": "pozytywizm w Polsce"
-        }
-    ],
-    "title": [
-        "Late 19th- and Early 20th-Century Polish Novels"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1de063dd-3b12-5cb9-babb-22112db7dbd9.json b/oaitestdata/clarin-oai_dc/SET_1/json/1de063dd-3b12-5cb9-babb-22112db7dbd9.json
deleted file mode 100644
index ea0721cd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1de063dd-3b12-5cb9-babb-22112db7dbd9.json
+++ /dev/null
@@ -1,49 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4984",
-    "MetadataAccess": [
-        "oai:ota:oucs:4984"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:4984;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4984.xml;A collection of poems in four volumes. By several hands: [pt.1];text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1de063dd-3b12-5cb9-babb-22112db7dbd9",
-    "oai_identifier": [
-        "oai:ota:oucs:4984"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A collection of poems in four volumes. By several hands: [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4984.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1de4cc71-e974-5c22-a331-5644df6e7e3e.json b/oaitestdata/clarin-oai_dc/SET_1/json/1de4cc71-e974-5c22-a331-5644df6e7e3e.json
deleted file mode 100644
index bec00e75..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1de4cc71-e974-5c22-a331-5644df6e7e3e.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "ClarinPL"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 105",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish",
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/58",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/58"
-    ],
-    "PID": "http://hdl.handle.net/11321/58",
-    "PublicationTimestamp": "2015-04-07T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "ClarinPL"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Pisarze, Pisarze"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/58;2015-04-13T08:10:42Z;hdl_11321_3;hdl_11321_4;Stylo;Pisarze, Pisarze;Pisarze, Pisarze;Stylometria, pisarze.;2015-04-07;corpus;http://hdl.handle.net/11321/58;pol;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;application/zip;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 105;ClarinPL;ClarinPL",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1de4cc71-e974-5c22-a331-5644df6e7e3e",
-    "notes": [
-        "Stylometria, pisarze."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/58"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Stylo"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1deb145e-e092-52c5-b0ad-d3bd4f9ed9b1.json b/oaitestdata/clarin-oai_dc/SET_1/json/1deb145e-e092-52c5-b0ad-d3bd4f9ed9b1.json
deleted file mode 100644
index 86c763ae..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1deb145e-e092-52c5-b0ad-d3bd4f9ed9b1.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=27b9084aa35a11e1a404080027e73ea2cbbed158889c419d80bae3f160cba3e5",
-    "MetadataAccess": [
-        "27b9084aa35a11e1a404080027e73ea2cbbed158889c419d80bae3f160cba3e5"
-    ],
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "27b9084aa35a11e1a404080027e73ea2cbbed158889c419d80bae3f160cba3e5;2018-11-15T16:39:22Z;lexicalConceptualResource;lexicalConceptualResource:wordList;LX-Abbreviations;LX-Abbreviations resource is a collection of abbreviations of different types from European Portuguese composed by 208 words. Each type of abbreviation is mannually divided and annotated with grammatical categories, gender and number, and, finally, with the respective abbreviations.;2015-12-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1deb145e-e092-52c5-b0ad-d3bd4f9ed9b1",
-    "notes": [
-        "LX-Abbreviations resource is a collection of abbreviations of different types from European Portuguese composed by 208 words. Each type of abbreviation is mannually divided and annotated with grammatical categories, gender and number, and, finally, with the respective abbreviations."
-    ],
-    "oai_identifier": [
-        "27b9084aa35a11e1a404080027e73ea2cbbed158889c419d80bae3f160cba3e5"
-    ],
-    "oai_set": [
-        "lexicalConceptualResource",
-        "lexicalConceptualResource:wordList"
-    ],
-    "state": "active",
-    "title": [
-        "LX-Abbreviations"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1df8af9f-7d14-5eec-a2ed-afa2cf1875eb.json b/oaitestdata/clarin-oai_dc/SET_1/json/1df8af9f-7d14-5eec-a2ed-afa2cf1875eb.json
deleted file mode 100644
index 9bec7595..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1df8af9f-7d14-5eec-a2ed-afa2cf1875eb.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Linguistic Modeling Department, IPP, Bulgarian Academy of Sciences"
-    ],
-    "Contributor": [
-        "Simov, Kiril"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1240",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1240"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1240",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Linguistic Modeling Department, IPP, Bulgarian Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Bulgaria"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Simov, Kiril"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1240;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;BulTreeBank Tokenizer;Simov, Kiril;Simov, Kiril;The tokenizer is covering all languages that use Latin1, Laitn2, Latin3 and Cyrillic tables of Unicode. Can be extended to cover other tables in Unicode if necessary. The implementation is as a cascaded regular grammar in CLaRK. It recognizes over 60 token categories. It is easy to be adapted to new token categories.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1240;downloadable_files_count: 0;Bulgaria;Linguistic Modeling Department, IPP, Bulgarian Academy of Sciences;http://www.bultreebank.org/clark/index.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1df8af9f-7d14-5eec-a2ed-afa2cf1875eb",
-    "notes": [
-        "The tokenizer is covering all languages that use Latin1, Laitn2, Latin3 and Cyrillic tables of Unicode. Can be extended to cover other tables in Unicode if necessary. The implementation is as a cascaded regular grammar in CLaRK. It recognizes over 60 token categories. It is easy to be adapted to new token categories."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1240"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "BulTreeBank Tokenizer"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1e19416a-8f01-532f-a63a-620f99edd7c6.json b/oaitestdata/clarin-oai_dc/SET_1/json/1e19416a-8f01-532f-a63a-620f99edd7c6.json
deleted file mode 100644
index 1fd4b376..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1e19416a-8f01-532f-a63a-620f99edd7c6.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "A"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1556",
-    "MetadataAccess": [
-        "oai:ota:oucs:1556"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Emerson, Ralph Waldo"
-    ],
-    "fulltext": "oai:ota:oucs:1556;2018-04-16T15:30:51Z;http://ota.ox.ac.uk/headers/1556.xml;Essays; Second series;Emerson, Ralph Waldo;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;A;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1e19416a-8f01-532f-a63a-620f99edd7c6",
-    "oai_identifier": [
-        "oai:ota:oucs:1556"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Essays; Second series"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1556.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1e384e59-f2c0-5632-bcb5-d453687c774b.json b/oaitestdata/clarin-oai_dc/SET_1/json/1e384e59-f2c0-5632-bcb5-d453687c774b.json
deleted file mode 100644
index 8198d081..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1e384e59-f2c0-5632-bcb5-d453687c774b.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=403030c4cb7d11e1a404080027e73ea231c8cb2c48f64d778a4e08ab322c7399",
-    "MetadataAccess": [
-        "403030c4cb7d11e1a404080027e73ea231c8cb2c48f64d778a4e08ab322c7399"
-    ],
-    "PublicationTimestamp": "2012-11-27T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "fulltext": "403030c4cb7d11e1a404080027e73ea231c8cb2c48f64d778a4e08ab322c7399;2018-11-15T16:39:39Z;toolService;toolService:tool;FORMA;FORMA is a probabilistic tool for morphological tagging and lemmatization of text. The purpose of this tool is to obtain annotated text to be processed by other NLP tools (see Gonzalez et al., 2006).;2012-11-27",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1e384e59-f2c0-5632-bcb5-d453687c774b",
-    "notes": [
-        "FORMA is a probabilistic tool for morphological tagging and lemmatization of text. The purpose of this tool is to obtain annotated text to be processed by other NLP tools (see Gonzalez et al., 2006)."
-    ],
-    "oai_identifier": [
-        "403030c4cb7d11e1a404080027e73ea231c8cb2c48f64d778a4e08ab322c7399"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "FORMA"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1e57e55b-37e6-5487-83a7-fdea1c8a47a7.json b/oaitestdata/clarin-oai_dc/SET_1/json/1e57e55b-37e6-5487-83a7-fdea1c8a47a7.json
deleted file mode 100644
index bdaaf4ca..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1e57e55b-37e6-5487-83a7-fdea1c8a47a7.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 81 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0630",
-    "MetadataAccess": [
-        "oai:ota:oucs:0630"
-    ],
-    "PublicationTimestamp": "1590-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1590"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Munday, Anthony, 1553-1633"
-    ],
-    "fulltext": "oai:ota:oucs:0630;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0630.xml;The book of John a Kent & John a Cumber;Munday, Anthony, 1553-1633;1590;text_and_corpus_linguistics;Plays -- England -- 16th century;eng;Oxford Text Archive, University of Oxford;(1 file : ca. 81 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1e57e55b-37e6-5487-83a7-fdea1c8a47a7",
-    "oai_identifier": [
-        "oai:ota:oucs:0630"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        }
-    ],
-    "title": [
-        "The book of John a Kent & John a Cumber"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0630.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1e70f3aa-82fc-581d-b29d-6de13f4058aa.json b/oaitestdata/clarin-oai_dc/SET_1/json/1e70f3aa-82fc-581d-b29d-6de13f4058aa.json
deleted file mode 100644
index 4543e683..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1e70f3aa-82fc-581d-b29d-6de13f4058aa.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Pigman, G.W."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 206 KB)",
-        "text/plain"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1714",
-    "MetadataAccess": [
-        "oai:ota:oucs:1714"
-    ],
-    "PublicationTimestamp": "1530-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1530"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Surrey, Henry Howard, Earl of, 1517?-1547"
-    ],
-    "fulltext": "oai:ota:oucs:1714;2018-05-08T14:08:14Z;http://ota.ox.ac.uk/headers/1714.xml;Poems / Henry Howard, Earl of Surrey;Surrey, Henry Howard, Earl of, 1517?-1547;1530-1547;text_and_corpus_linguistics;Love poetry, English -- 16th century;Oxford Text Archive, University of Oxford;Pigman, G.W.;text/plain;(1 file : ca. 206 KB);Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1e70f3aa-82fc-581d-b29d-6de13f4058aa",
-    "oai_identifier": [
-        "oai:ota:oucs:1714"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Love poetry"
-        },
-        {
-            "name": "English -- th century"
-        }
-    ],
-    "title": [
-        "Poems / Henry Howard, Earl of Surrey"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1714.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1e728ac4-7ad4-5236-9ae6-27e21b56c5d8.json b/oaitestdata/clarin-oai_dc/SET_1/json/1e728ac4-7ad4-5236-9ae6-27e21b56c5d8.json
deleted file mode 100644
index 40ee862b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1e728ac4-7ad4-5236-9ae6-27e21b56c5d8.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Centre for Speech Technology Research, University of Edinburgh"
-    ],
-    "Contributor": [
-        "White, Laurence",
-        "King, Simon"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-875",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-875"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-875",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Centre for Speech Technology Research, University of Edinburgh"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-875;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;EUSTACE : Edinburgh University speech timing archive and corpus of English;White, Laurence;King, Simon;Speech corpus comprising 4608 spoken sentences recorded for speech timing research. The complete archive, available for downloading, includes a structured list of the sentences, the speech recordings and the label files, plus full documentation.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-875;eng;downloadable_files_count: 0;United Kingdom;Centre for Speech Technology Research, University of Edinburgh;http://www.cstr.ed.ac.uk/projects/eustace/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1e728ac4-7ad4-5236-9ae6-27e21b56c5d8",
-    "notes": [
-        "Speech corpus comprising 4608 spoken sentences recorded for speech timing research. The complete archive, available for downloading, includes a structured list of the sentences, the speech recordings and the label files, plus full documentation."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-875"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "EUSTACE : Edinburgh University speech timing archive and corpus of English"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1e7296b6-7416-5359-b862-b468c47e9495.json b/oaitestdata/clarin-oai_dc/SET_1/json/1e7296b6-7416-5359-b862-b468c47e9495.json
deleted file mode 100644
index 4a2db36a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1e7296b6-7416-5359-b862-b468c47e9495.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4629",
-    "MetadataAccess": [
-        "oai:ota:oucs:4629"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Woolston, Thomas, 1670-1733."
-    ],
-    "fulltext": "oai:ota:oucs:4629;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4629.xml;A sixth discourse on the miracles of our Saviour: in view of the present controversy between infidels and apostates. By Tho. Woolston, ...;Woolston, Thomas, 1670-1733.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1e7296b6-7416-5359-b862-b468c47e9495",
-    "oai_identifier": [
-        "oai:ota:oucs:4629"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A sixth discourse on the miracles of our Saviour: in view of the present controversy between infidels and apostates. By Tho. Woolston, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4629.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1e7ecc8c-34d4-56b3-9efd-f33f9b59cbb0.json b/oaitestdata/clarin-oai_dc/SET_1/json/1e7ecc8c-34d4-56b3-9efd-f33f9b59cbb0.json
deleted file mode 100644
index a0cf22de..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1e7ecc8c-34d4-56b3-9efd-f33f9b59cbb0.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Department of Information Technology, Gauhati University, Assam, India"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Assamese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/620",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/620"
-    ],
-    "PID": "http://hdl.handle.net/11321/620",
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Department of Information Technology, Gauhati University, Assam, India"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Sarma, Prof. Shikhar Kr."
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/620;2019-01-08T11:13:55Z;hdl_11321_3;hdl_11321_610;Assamese POS Tagger;Sarma, Prof. Shikhar Kr.;Assamese NLP;Assamese POS Tagger;Assamese Part of Speech;Assamese CRF++;Gauhati University;Assamese POS tagger is a CRF++ based POS Tagger. CRF++ is a customizable open source Conditional Random Fields for tagging/labeling continuos text. CRF++ is implemented for generic purpose and can be applied to any natural language provided the tagset. CRF++ tool is designed in C++ language.\r\n\r\n-------\r\n1. These Assamese NLP resources including the Tools and Applications are developed\r\nduring Research and Development Projects as well as Masters and Ph.D. thesis\r\nworks.\r\n2. These are mainly developed or generated at Gauhati University Department of\r\nComputer Science and Department of Information Technology.\r\n3. These resources are used by students and researchers for further studies, researches, as\r\nwell as for design and development of tools and applications.\r\n4. Computational Linguistics in Assamese is not rich, and Natural Language Processing\r\nworks have mainly started during last two decades, and most of the resources are first\r\ngeneration resources, and with ample scope for upgrading, enriching, and purifying.\r\n5. These are very good and essential resources for all the researchers in Assamese NLP, as\r\nthe language requires more and more NLP works to make Assamese a rich media for\r\nthe digital world.\r\n6. Anyone interested, or in need of such resources may express their interest for the\r\nrequired resources, and the way of availability will be advised/informed accordingly.\r\n7. These are purely research materials and could only be used for further research only.\r\n8. Researchers may visit the NLP Lab of Department of Information Technology, Gauhati\r\nUniversity, Guwahati, India or contact us.\r\n9. Researchers interested in collaborative works, and also students for project works, are\r\nwelcome.\r\n10. Contact person is Professor Shikhar Kr. Sarma, Department of Information\r\nTechnology, Gauhati University, Guwahati 781014, Assam, India. Email-\r\nsks@gauhati.ac.in;2019-01-08;toolService;http://hdl.handle.net/11321/620;asm;downloadable_files_count: 0;Department of Information Technology, Gauhati University, Assam, India",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1e7ecc8c-34d4-56b3-9efd-f33f9b59cbb0",
-    "notes": [
-        "Assamese POS tagger is a CRF++ based POS Tagger. CRF++ is a customizable open source Conditional Random Fields for tagging/labeling continuos text. CRF++ is implemented for generic purpose and can be applied to any natural language provided the tagset. CRF++ tool is designed in C++ language.\r\n\r\n-------\r\n1. These Assamese NLP resources including the Tools and Applications are developed\r\nduring Research and Development Projects as well as Masters and Ph.D. thesis\r\nworks.\r\n2. These are mainly developed or generated at Gauhati University Department of\r\nComputer Science and Department of Information Technology.\r\n3. These resources are used by students and researchers for further studies, researches, as\r\nwell as for design and development of tools and applications.\r\n4. Computational Linguistics in Assamese is not rich, and Natural Language Processing\r\nworks have mainly started during last two decades, and most of the resources are first\r\ngeneration resources, and with ample scope for upgrading, enriching, and purifying.\r\n5. These are very good and essential resources for all the researchers in Assamese NLP, as\r\nthe language requires more and more NLP works to make Assamese a rich media for\r\nthe digital world.\r\n6. Anyone interested, or in need of such resources may express their interest for the\r\nrequired resources, and the way of availability will be advised/informed accordingly.\r\n7. These are purely research materials and could only be used for further research only.\r\n8. Researchers may visit the NLP Lab of Department of Information Technology, Gauhati\r\nUniversity, Guwahati, India or contact us.\r\n9. Researchers interested in collaborative works, and also students for project works, are\r\nwelcome.\r\n10. Contact person is Professor Shikhar Kr. Sarma, Department of Information\r\nTechnology, Gauhati University, Guwahati 781014, Assam, India. Email-\r\nsks@gauhati.ac.in"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/620"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_610"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Assamese NLP"
-        },
-        {
-            "name": "Assamese POS Tagger"
-        },
-        {
-            "name": "Assamese Part Speech"
-        },
-        {
-            "name": "Assamese CRF"
-        },
-        {
-            "name": "Gauhati University"
-        }
-    ],
-    "title": [
-        "Assamese POS Tagger"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1ea64cca-380a-5ec9-8288-8aa6fc729427.json b/oaitestdata/clarin-oai_dc/SET_1/json/1ea64cca-380a-5ec9-8288-8aa6fc729427.json
deleted file mode 100644
index 4640bff3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1ea64cca-380a-5ec9-8288-8aa6fc729427.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Charles University in Prague, \u00da\u010cJTK"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0019-89A0-9",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0019-89A0-9"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0019-89A0-9",
-    "PublicationTimestamp": "2013-05-11T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Charles University in Prague, \u00da\u010cJTK"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11858/00-097C-0000-0023-3FBB-3"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Gol\u00e1\u0148ov\u00e1, Hana",
-        "\u0160ebesta, Karel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0019-89A0-9;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;AKCES 2;\u0160ebesta, Karel;Gol\u00e1\u0148ov\u00e1, Hana;youth language;classroom;language acquisition corpus;AKCES;Corpus AKCES 2 consists of trancripts of recordings of classes at Czech elementary and secondary schools (AKCES/CLAC - Czech Language Acquisition Corpora). It is the same data as the corpus \"Schola 2010\" (see the link for search), but all the proper names have been removed in order to protect the privacy of participants.;2013-05-11;corpus;http://hdl.handle.net/11858/00-097C-0000-0019-89A0-9;ces;http://hdl.handle.net/11858/00-097C-0000-0023-3FBB-3;Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0);http://creativecommons.org/licenses/by-nc-nd/3.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University in Prague, \u00da\u010cJTK;http://akces.ff.cuni.cz",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1ea64cca-380a-5ec9-8288-8aa6fc729427",
-    "notes": [
-        "Corpus AKCES 2 consists of trancripts of recordings of classes at Czech elementary and secondary schools (AKCES/CLAC - Czech Language Acquisition Corpora). It is the same data as the corpus \"Schola 2010\" (see the link for search), but all the proper names have been removed in order to protect the privacy of participants."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0019-89A0-9"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "youth language"
-        },
-        {
-            "name": "classroom"
-        },
-        {
-            "name": "language acquisition corpus"
-        },
-        {
-            "name": "AKCES"
-        }
-    ],
-    "title": [
-        "AKCES 2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1eb69d9b-489e-556e-b718-7da3d6f8567f.json b/oaitestdata/clarin-oai_dc/SET_1/json/1eb69d9b-489e-556e-b718-7da3d6f8567f.json
deleted file mode 100644
index 7ecd83e5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1eb69d9b-489e-556e-b718-7da3d6f8567f.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "Contributor": [
-        "Cristea, Dan"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English",
-        "Romanian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-191",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-191"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-191",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Romania"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-191;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;ConsILR - Consortium for the Romanian Language: Resources & Tools;Cristea, Dan;Resources and tools developed for Romanian;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-191;eng;ron;downloadable_files_count: 0;Romania;http://consilr.info.uaic.ro",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1eb69d9b-489e-556e-b718-7da3d6f8567f",
-    "notes": [
-        "Resources and tools developed for Romanian"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-191"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "ConsILR - Consortium for the Romanian Language: Resources & Tools"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1ec6a5ac-c221-578d-8bb0-8aad91d6d226.json b/oaitestdata/clarin-oai_dc/SET_1/json/1ec6a5ac-c221-578d-8bb0-8aad91d6d226.json
deleted file mode 100644
index c24f884d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1ec6a5ac-c221-578d-8bb0-8aad91d6d226.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=ce4287c2059811e7a2aa782bcb074135da914cac14344de0b55f2ba50c4e24c1",
-    "MetadataAccess": [
-        "ce4287c2059811e7a2aa782bcb074135da914cac14344de0b55f2ba50c4e24c1"
-    ],
-    "PublicationTimestamp": "2017-03-10T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "fulltext": "ce4287c2059811e7a2aa782bcb074135da914cac14344de0b55f2ba50c4e24c1;2018-11-15T16:40:31Z;toolService;toolService:tool;Spanish to English Machine translation module;Technical Description:\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/Pilot1_technical_description.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/TechnicalDescriptionPilot2_D2.7.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2016/11/TechnicalDescriptionPilot3_D2.10.pdf;2017-03-10",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1ec6a5ac-c221-578d-8bb0-8aad91d6d226",
-    "notes": [
-        "Technical Description:\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/Pilot1_technical_description.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/TechnicalDescriptionPilot2_D2.7.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2016/11/TechnicalDescriptionPilot3_D2.10.pdf"
-    ],
-    "oai_identifier": [
-        "ce4287c2059811e7a2aa782bcb074135da914cac14344de0b55f2ba50c4e24c1"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "Spanish to English Machine translation module"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1ed26cd0-b7d4-59f2-bcd6-7a754eb7b56a.json b/oaitestdata/clarin-oai_dc/SET_1/json/1ed26cd0-b7d4-59f2-bcd6-7a754eb7b56a.json
deleted file mode 100644
index 2594ec7a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1ed26cd0-b7d4-59f2-bcd6-7a754eb7b56a.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Croatian",
-        "German",
-        "Russian",
-        "Turkish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1047",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1047"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1047",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1047;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;L2 Acquisition Christine Dimroth;Language Acquisition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1047;hrv;deu;rus;tur;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI26961%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1ed26cd0-b7d4-59f2-bcd6-7a754eb7b56a",
-    "notes": [
-        "Language Acquisition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1047"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "L2 Acquisition Christine Dimroth"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1edbf30c-bf47-5dd4-8227-d7af575659d7.json b/oaitestdata/clarin-oai_dc/SET_1/json/1edbf30c-bf47-5dd4-8227-d7af575659d7.json
deleted file mode 100644
index 263ce88f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1edbf30c-bf47-5dd4-8227-d7af575659d7.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3966",
-    "MetadataAccess": [
-        "oai:ota:oucs:3966"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Boswell, James, 1740-1795."
-    ],
-    "fulltext": "oai:ota:oucs:3966;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3966.xml;Dorando: a Spanish tale.;Boswell, James, 1740-1795.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1edbf30c-bf47-5dd4-8227-d7af575659d7",
-    "oai_identifier": [
-        "oai:ota:oucs:3966"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Dorando: a Spanish tale."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3966.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1ef23ead-f0f5-5dd0-8949-9a8d6b661b0f.json b/oaitestdata/clarin-oai_dc/SET_1/json/1ef23ead-f0f5-5dd0-8949-9a8d6b661b0f.json
deleted file mode 100644
index c859cebc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1ef23ead-f0f5-5dd0-8949-9a8d6b661b0f.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contributor": [
-        "Borin, Lars"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-514",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-514"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-514",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Sweden"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-514;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Schlyter;Borin, Lars;appr. 16,000 entries, various (XML version underway);2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-514;downloadable_files_count: 0;Sweden;http://spraakbanken.gu.se/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1ef23ead-f0f5-5dd0-8949-9a8d6b661b0f",
-    "notes": [
-        "appr. 16,000 entries, various (XML version underway)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-514"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Schlyter"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1f0163e1-d9f0-5f0d-9c1d-b359b46b61f2.json b/oaitestdata/clarin-oai_dc/SET_1/json/1f0163e1-d9f0-5f0d-9c1d-b359b46b61f2.json
deleted file mode 100644
index 948b0816..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1f0163e1-d9f0-5f0d-9c1d-b359b46b61f2.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 233 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0061",
-    "MetadataAccess": [
-        "oai:ota:oucs:0061"
-    ],
-    "PublicationTimestamp": "1830-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1830"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gaskell, Elizabeth Cleghorn, 1810-1865"
-    ],
-    "fulltext": "oai:ota:oucs:0061;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0061.xml;Some passages from Chomley ; The deserted mansion ; A fear for the future ...;Gaskell, Elizabeth Cleghorn, 1810-1865;1830-1869;text_and_corpus_linguistics;Periodicals -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;(1 file : ca. 233 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1f0163e1-d9f0-5f0d-9c1d-b359b46b61f2",
-    "oai_identifier": [
-        "oai:ota:oucs:0061"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Periodicals -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Some passages from Chomley ; The deserted mansion ; A fear for the future ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0061.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1f077449-d592-5276-8484-af4f47545769.json b/oaitestdata/clarin-oai_dc/SET_1/json/1f077449-d592-5276-8484-af4f47545769.json
deleted file mode 100644
index c59cd69d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1f077449-d592-5276-8484-af4f47545769.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Iwaszkiewicz"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 5",
-        "application/zip",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/76",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/76"
-    ],
-    "PID": "http://hdl.handle.net/11321/76",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Iwaszkiewicz"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Iwaszkiewicz, Iwaszkiewicz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/76;2015-04-10T20:27:52Z;hdl_11321_3;hdl_11321_4;MWE Iwaszkiewicz;Iwaszkiewicz, Iwaszkiewicz;Iwaszkiewicz;2015-04-08;corpus;http://hdl.handle.net/11321/76;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 5;Iwaszkiewicz",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1f077449-d592-5276-8484-af4f47545769",
-    "notes": [
-        "Iwaszkiewicz"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/76"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Iwaszkiewicz"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1f177188-2cd1-5b92-93cd-5f7e90038cff.json b/oaitestdata/clarin-oai_dc/SET_1/json/1f177188-2cd1-5b92-93cd-5f7e90038cff.json
deleted file mode 100644
index 1291afc2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1f177188-2cd1-5b92-93cd-5f7e90038cff.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Slovenian Academy of Sciences and Arts",
-        "ZRC SAZU",
-        "dr. Bruno Breschi Foundation"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1092",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1092"
-    ],
-    "PID": "http://hdl.handle.net/11356/1092",
-    "PublicationTimestamp": "2006-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2006"
-    ],
-    "Publisher": [
-        "Slovenian Academy of Sciences and Arts",
-        "ZRC SAZU",
-        "dr. Bruno Breschi Foundation"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Snoj, Marko"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1092;2017-05-15T09:47:34Z;hdl_11356_1023;hdl_11356_1024;Dictionary of the Slovenian Language in the Works of Janez Svetokri\u0161ki;Snoj, Marko;dictionary;historical language;lexicography;The Dictionary of the Slovenian Language in the Works of Janez Svetokri\u0161ki (Slovar jezika Janeza Svetokri\u0161kega) presents and explains the lexis, including proper nouns, from 233 sermons published by Janez Svetokri\u0161ki in five volumes under the common title Sacrum promptuarium between 1691 and 1707. The dictionary contains 8,540 dictionary entries, which display and treat the entire Slovenian lexis, including proper nouns, used in the above-mentioned work. Each dictionary entry consists of 1. the headword, 2. the presentation of morphological characteristics, 3. the description of meaning and 4. examples of use. Entries containing loanwords additionally include etymologies. Some entries may here provide other philological or linguistic comments. Each entry describing a proper noun ends with the most basic encyclopaedic information. The Dictionary of the Slovenian Language in the Works of Janez Svetokri\u0161ki is the first dictionary to treat the lexis of a Slovenian author from a period before the introduction of Gaj's Latin alphabet. The dictionary is distinguished by a modern, but not too complex display of material, by comprehensive citations of all attested variants and by the inclusion of encyclopaedic information about proper nouns, all of which in many respects facilitates the reading of the original baroque text or makes it possible in the first place.\r\n\r\nThis dictionary was published as a printed book:\r\nSnoj, Marko. Slovar jezika Janeza Svetokri\u0161kega. Ljubljana : Zalo\u017eba ZRC, 2006. ISBN 961-6568-45-0.;2006;lexicalConceptualResource;http://hdl.handle.net/11356/1092;slv;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Slovenian Academy of Sciences and Arts;dr. Bruno Breschi Foundation;ZRC SAZU;http://www.fran.si/139/slovar-jezika-janeza-svetokriskega",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1f177188-2cd1-5b92-93cd-5f7e90038cff",
-    "notes": [
-        "The Dictionary of the Slovenian Language in the Works of Janez Svetokri\u0161ki (Slovar jezika Janeza Svetokri\u0161kega) presents and explains the lexis, including proper nouns, from 233 sermons published by Janez Svetokri\u0161ki in five volumes under the common title Sacrum promptuarium between 1691 and 1707. The dictionary contains 8,540 dictionary entries, which display and treat the entire Slovenian lexis, including proper nouns, used in the above-mentioned work. Each dictionary entry consists of 1. the headword, 2. the presentation of morphological characteristics, 3. the description of meaning and 4. examples of use. Entries containing loanwords additionally include etymologies. Some entries may here provide other philological or linguistic comments. Each entry describing a proper noun ends with the most basic encyclopaedic information. The Dictionary of the Slovenian Language in the Works of Janez Svetokri\u0161ki is the first dictionary to treat the lexis of a Slovenian author from a period before the introduction of Gaj's Latin alphabet. The dictionary is distinguished by a modern, but not too complex display of material, by comprehensive citations of all attested variants and by the inclusion of encyclopaedic information about proper nouns, all of which in many respects facilitates the reading of the original baroque text or makes it possible in the first place.\r\n\r\nThis dictionary was published as a printed book:\r\nSnoj, Marko. Slovar jezika Janeza Svetokri\u0161kega. Ljubljana : Zalo\u017eba ZRC, 2006. ISBN 961-6568-45-0."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1092"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "dictionary"
-        },
-        {
-            "name": "historical language"
-        },
-        {
-            "name": "lexicography"
-        }
-    ],
-    "title": [
-        "Dictionary of the Slovenian Language in the Works of Janez Svetokri\u0161ki"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1f2fa1f6-b333-5fb9-9869-c98e582cceb7.json b/oaitestdata/clarin-oai_dc/SET_1/json/1f2fa1f6-b333-5fb9-9869-c98e582cceb7.json
deleted file mode 100644
index 45918898..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1f2fa1f6-b333-5fb9-9869-c98e582cceb7.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2753",
-    "MetadataAccess": [
-        "oai:ota:oucs:2753"
-    ],
-    "PublicationTimestamp": "1712-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1712"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2753;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2753.xml;Some reasons to prove, that no person is obliged by his principles, as a Whig, to oppose Her Majesty or her present ministry. In a letter to a Whig-lord;Swift, Jonathan, 1667-1745;1712;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1f2fa1f6-b333-5fb9-9869-c98e582cceb7",
-    "oai_identifier": [
-        "oai:ota:oucs:2753"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Some reasons to prove, that no person is obliged by his principles, as a Whig, to oppose Her Majesty or her present ministry. In a letter to a Whig-lord"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2753.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1f35862c-8377-5a8f-9b3b-0d26223aa104.json b/oaitestdata/clarin-oai_dc/SET_1/json/1f35862c-8377-5a8f-9b3b-0d26223aa104.json
deleted file mode 100644
index ef148ce3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1f35862c-8377-5a8f-9b3b-0d26223aa104.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4054",
-    "MetadataAccess": [
-        "oai:ota:oucs:4054"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Bailey, J. (John), 1750-1819."
-    ],
-    "fulltext": "oai:ota:oucs:4054;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4054.xml;General view of the agriculture of the county of Northumberland: with observations on the means of its improvement; drawn up for the consideration of the Board of Agriculture and Internal Improvement, by J. Bailey and G. Culley.;Bailey, J. (John), 1750-1819.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1f35862c-8377-5a8f-9b3b-0d26223aa104",
-    "oai_identifier": [
-        "oai:ota:oucs:4054"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "General view of the agriculture of the county of Northumberland: with observations on the means of its improvement; drawn up for the consideration of the Board of Agriculture and Internal Improvement, by J. Bailey and G. Culley."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4054.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1f4056cf-f497-5eaa-b598-da6a99ea4911.json b/oaitestdata/clarin-oai_dc/SET_1/json/1f4056cf-f497-5eaa-b598-da6a99ea4911.json
deleted file mode 100644
index 1d358895..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1f4056cf-f497-5eaa-b598-da6a99ea4911.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "37 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1302",
-    "MetadataAccess": [
-        "oai:ota:oucs:1302"
-    ],
-    "PublicationTimestamp": "1655-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1655"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Cam\u00c3\u00b5es, Lu\u00c3\u00ads de"
-    ],
-    "fulltext": "oai:ota:oucs:1302;2018-03-07T11:07:13Z;http://ota.ox.ac.uk/headers/1302.xml; The Lusiads  / compiled by T.N. Corns;Cam\u00c3\u00b5es, Lu\u00c3\u00ads de;1655;text_and_corpus_linguistics;Poems -- Portugal -- 16th century;eng;Oxford Text Archive, University of Oxford;37 KB;Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1f4056cf-f497-5eaa-b598-da6a99ea4911",
-    "oai_identifier": [
-        "oai:ota:oucs:1302"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- Portugal -- th century"
-        }
-    ],
-    "title": [
-        " The Lusiads  / compiled by T.N. Corns"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1302.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1f477677-139f-51d7-b26c-ad2491c3f26d.json b/oaitestdata/clarin-oai_dc/SET_1/json/1f477677-139f-51d7-b26c-ad2491c3f26d.json
deleted file mode 100644
index 5e523f18..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1f477677-139f-51d7-b26c-ad2491c3f26d.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5516",
-    "MetadataAccess": [
-        "oai:ota:oucs:5516"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Alderson, John, 1757-1829."
-    ],
-    "fulltext": "oai:ota:oucs:5516;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5516.xml;An essay on the rhus toxicodendron: pubescent poison oak, or sumach, with cases shewing it's efficacy in the cure of paralysis, ... By John Alderson, ...;Alderson, John, 1757-1829.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1f477677-139f-51d7-b26c-ad2491c3f26d",
-    "oai_identifier": [
-        "oai:ota:oucs:5516"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An essay on the rhus toxicodendron: pubescent poison oak, or sumach, with cases shewing it's efficacy in the cure of paralysis, ... By John Alderson, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5516.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1f57e888-1390-54ff-90dc-9c9441a87bc8.json b/oaitestdata/clarin-oai_dc/SET_1/json/1f57e888-1390-54ff-90dc-9c9441a87bc8.json
deleted file mode 100644
index 0cafec1b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1f57e888-1390-54ff-90dc-9c9441a87bc8.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Craig, Hugh"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 176 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2067",
-    "MetadataAccess": [
-        "oai:ota:oucs:2067"
-    ],
-    "PublicationTimestamp": "1601-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1601"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Jonson, Ben, 1573?-1637"
-    ],
-    "fulltext": "oai:ota:oucs:2067;2018-03-02T11:57:06Z;http://ota.ox.ac.uk/headers/2067.xml;Every man in his humour;Every man in his humour [1601] / Ben Jonson;Jonson, Ben, 1573?-1637;1601;text_and_corpus_linguistics;English drama -- 17th century;Oxford Text Archive, University of Oxford;Craig, Hugh;text/sgml;(1 file : ca. 176 KB);Text;Plays;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1f57e888-1390-54ff-90dc-9c9441a87bc8",
-    "oai_identifier": [
-        "oai:ota:oucs:2067"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- th century"
-        }
-    ],
-    "title": [
-        "Every man in his humour",
-        "Every man in his humour [1601] / Ben Jonson"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2067.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1f656695-078c-5fa9-9cad-057c7bad1e86.json b/oaitestdata/clarin-oai_dc/SET_1/json/1f656695-078c-5fa9-9cad-057c7bad1e86.json
deleted file mode 100644
index 34f9b079..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1f656695-078c-5fa9-9cad-057c7bad1e86.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "Avestan"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-911",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-911"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-911",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-911;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Avestan;ca. 300.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-911;ave;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#avest",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1f656695-078c-5fa9-9cad-057c7bad1e86",
-    "notes": [
-        "ca. 300.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-911"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Avestan"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1f691060-7c3d-50dd-a6af-1b45e34d996c.json b/oaitestdata/clarin-oai_dc/SET_1/json/1f691060-7c3d-50dd-a6af-1b45e34d996c.json
deleted file mode 100644
index 23cd2bce..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1f691060-7c3d-50dd-a6af-1b45e34d996c.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "University of Helsinki"
-    ],
-    "Contributor": [
-        "Lind\u00e9n, Krister"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1301",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1301"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1301",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Helsinki"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Finland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1301;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Helsinki Finite State Technology;Lind\u00e9n, Krister;finite state transducer;morphological analyzer;The Helsinki Finite-State Transducer software is intended for the implementation of morphological analysers and other tools which are based on weighted and unweigted finite-state transducer technology. The feasibility of the HFST toolkit has been demonstrated by full-fledged open source implementations of Finnish, Swedish, English, French and Northern S\u00e1mi lexicons.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1301;downloadable_files_count: 0;Finland;University of Helsinki",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1f691060-7c3d-50dd-a6af-1b45e34d996c",
-    "notes": [
-        "The Helsinki Finite-State Transducer software is intended for the implementation of morphological analysers and other tools which are based on weighted and unweigted finite-state transducer technology. The feasibility of the HFST toolkit has been demonstrated by full-fledged open source implementations of Finnish, Swedish, English, French and Northern S\u00e1mi lexicons."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1301"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "finite state transducer"
-        },
-        {
-            "name": "morphological analyzer"
-        }
-    ],
-    "title": [
-        "Helsinki Finite State Technology"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1f6bf7a3-9b71-500f-a034-bb12214eec60.json b/oaitestdata/clarin-oai_dc/SET_1/json/1f6bf7a3-9b71-500f-a034-bb12214eec60.json
deleted file mode 100644
index a6225e59..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1f6bf7a3-9b71-500f-a034-bb12214eec60.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=e5ad1db81c5f11e2a2aa782bcb074135120115ce2d3b4f4ab0b3e9958b77d1f2",
-    "MetadataAccess": [
-        "e5ad1db81c5f11e2a2aa782bcb074135120115ce2d3b4f4ab0b3e9958b77d1f2"
-    ],
-    "PublicationTimestamp": "2012-10-24T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "fulltext": "e5ad1db81c5f11e2a2aa782bcb074135120115ce2d3b4f4ab0b3e9958b77d1f2;2018-11-15T16:39:45Z;toolService;toolService:tool;Dizer;DiZer 2.0 is a web interface for discourse parsing. It is based on DiZer (Pardo and Nunes, 2008), the first discourse parser for Brazilian Portuguese. The system aims at producing the discourse structure of a source text following the Rhetorical Structure Theory \u00e2\u0080\u0093 RST (Mann and Thompson, 1987), one of the most used discourse theories in Computational Linguistics and Natural Language Processing.\n\nDiZer 2.0 also allows the customization for other languages, being minimally necessary a discourse segmenter and a list of discourse patterns, which correlate text superficial markers to RST characteristics. DiZer 2.0 is currently customized for Brazilian Portuguese and Spanish.\n;2012-10-24",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1f6bf7a3-9b71-500f-a034-bb12214eec60",
-    "notes": [
-        "DiZer 2.0 is a web interface for discourse parsing. It is based on DiZer (Pardo and Nunes, 2008), the first discourse parser for Brazilian Portuguese. The system aims at producing the discourse structure of a source text following the Rhetorical Structure Theory \u00e2\u0080\u0093 RST (Mann and Thompson, 1987), one of the most used discourse theories in Computational Linguistics and Natural Language Processing.\n\nDiZer 2.0 also allows the customization for other languages, being minimally necessary a discourse segmenter and a list of discourse patterns, which correlate text superficial markers to RST characteristics. DiZer 2.0 is currently customized for Brazilian Portuguese and Spanish.\n"
-    ],
-    "oai_identifier": [
-        "e5ad1db81c5f11e2a2aa782bcb074135120115ce2d3b4f4ab0b3e9958b77d1f2"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "Dizer"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1f74cf9a-ec69-5dc6-a7e2-e59d409b4077.json b/oaitestdata/clarin-oai_dc/SET_1/json/1f74cf9a-ec69-5dc6-a7e2-e59d409b4077.json
deleted file mode 100644
index 77f9a452..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1f74cf9a-ec69-5dc6-a7e2-e59d409b4077.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "NHH Norwegian School of Economics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Norwegian Nynorsk",
-        "Norwegian Bokm\u00e5l",
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/120",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/120"
-    ],
-    "PID": "http://hdl.handle.net/11509/120",
-    "PublicationTimestamp": "2017-01-10T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "NHH Norwegian School of Economics"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "CLARIN_ACA",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NORED=1",
-        "ACA"
-    ],
-    "author": [
-        "Simonn\u00e6s, Ingrid"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/120;2017-01-18T09:22:38Z;hdl_11509_1;hdl_11509_2;Norwegian-German legal terminology;Simonn\u00e6s, Ingrid;Law;Termbase;Terminological;Terminology;The resource NOJU is a terminological database containing terms, definitions and other conceptual information in Norwegian and German within legal domains.;2017-01-10;lexicalConceptualResource;http://hdl.handle.net/11509/120;nno;nob;deu;CLARIN_ACA;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NORED=1;ACA;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;NHH Norwegian School of Economics;http://www.terminologi.no",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1f74cf9a-ec69-5dc6-a7e2-e59d409b4077",
-    "notes": [
-        "The resource NOJU is a terminological database containing terms, definitions and other conceptual information in Norwegian and German within legal domains."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/120"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Law"
-        },
-        {
-            "name": "Termbase"
-        },
-        {
-            "name": "Terminological"
-        },
-        {
-            "name": "Terminology"
-        }
-    ],
-    "title": [
-        "Norwegian-German legal terminology"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1f847ece-3ea5-5c19-859d-46277d446158.json b/oaitestdata/clarin-oai_dc/SET_1/json/1f847ece-3ea5-5c19-859d-46277d446158.json
deleted file mode 100644
index cb53bc0c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1f847ece-3ea5-5c19-859d-46277d446158.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "TALG Research Group (University of Vigo)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Galician"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-617",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-617"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-617",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "TALG Research Group (University of Vigo)"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-617;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Neoteca;Galician neology databank;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-617;glg;downloadable_files_count: 0;Spain;TALG Research Group (University of Vigo);http://sli.uvigo.es/neoteca",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1f847ece-3ea5-5c19-859d-46277d446158",
-    "notes": [
-        "Galician neology databank"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-617"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Neoteca"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1f8ae75b-a6c8-5911-a36a-487824a6e765.json b/oaitestdata/clarin-oai_dc/SET_1/json/1f8ae75b-a6c8-5911-a36a-487824a6e765.json
deleted file mode 100644
index bda6d600..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1f8ae75b-a6c8-5911-a36a-487824a6e765.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "University of Zagreb, Faculty of Humanities and Social Sciences"
-    ],
-    "Contributor": [
-        "Tadi\u0107, Marko"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Croatian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-194",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-194"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-194",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Zagreb, Faculty of Humanities and Social Sciences"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Croatia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-194;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Croatian Dependency Treebank;Tadi\u0107, Marko;Manually tagged dependency treebank, analytical layer according to the PDT formalism adapted for Croatian;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-194;hrv;application/octet-stream;downloadable_files_count: 0;Croatia;University of Zagreb, Faculty of Humanities and Social Sciences;http://hobs.ffzg.hr",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1f8ae75b-a6c8-5911-a36a-487824a6e765",
-    "notes": [
-        "Manually tagged dependency treebank, analytical layer according to the PDT formalism adapted for Croatian"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-194"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Croatian Dependency Treebank"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1f8b5dbc-0e52-5efb-839d-fcfc61d371fa.json b/oaitestdata/clarin-oai_dc/SET_1/json/1f8b5dbc-0e52-5efb-839d-fcfc61d371fa.json
deleted file mode 100644
index 15be8f9c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1f8b5dbc-0e52-5efb-839d-fcfc61d371fa.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5480",
-    "MetadataAccess": [
-        "oai:ota:oucs:5480"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Parnell, Thomas, 1679-1718."
-    ],
-    "fulltext": "oai:ota:oucs:5480;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5480.xml;The hermit: To which are added, A hymn to contentment; Health, an eclogue; and A night piece, on death. By Dr. Thomas Parnell, ...;Parnell, Thomas, 1679-1718.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1f8b5dbc-0e52-5efb-839d-fcfc61d371fa",
-    "oai_identifier": [
-        "oai:ota:oucs:5480"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The hermit: To which are added, A hymn to contentment; Health, an eclogue; and A night piece, on death. By Dr. Thomas Parnell, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5480.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1fad03dc-a19d-54a5-b904-dfedd1c9ffc2.json b/oaitestdata/clarin-oai_dc/SET_1/json/1fad03dc-a19d-54a5-b904-dfedd1c9ffc2.json
deleted file mode 100644
index 052c95e0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1fad03dc-a19d-54a5-b904-dfedd1c9ffc2.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "A"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1415",
-    "MetadataAccess": [
-        "oai:ota:oucs:1415"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Unknown"
-    ],
-    "fulltext": "oai:ota:oucs:1415;2018-04-16T15:30:51Z;http://ota.ox.ac.uk/headers/1415.xml;T\u00c3\u00a1in b\u00c3\u00b3 c\u00c3\u00baailnge;Unknown;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;A;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1fad03dc-a19d-54a5-b904-dfedd1c9ffc2",
-    "oai_identifier": [
-        "oai:ota:oucs:1415"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "T\u00c3\u00a1in b\u00c3\u00b3 c\u00c3\u00baailnge"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1415.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1fb4159f-430e-5501-9f38-1497ee8230e4.json b/oaitestdata/clarin-oai_dc/SET_1/json/1fb4159f-430e-5501-9f38-1497ee8230e4.json
deleted file mode 100644
index af6db1a0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1fb4159f-430e-5501-9f38-1497ee8230e4.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia \u0141azarzowa"
-    ],
-    "Contributor": [
-        "Trzecieski, Andrzej (ca 1525-ca 1584)",
-        "Rej, Miko\u0142aj (1505-1569)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-166119",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-166119"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CEF-D",
-    "PublicationTimestamp": "1567-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1567"
-    ],
-    "Publisher": [
-        "Drukarnia \u0141azarzowa"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/166119",
-        "oai:jbc.bj.uj.edu.pl:publication:174576"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1501/1600"
-    ],
-    "TempCoverageBegin": 47351044799,
-    "TempCoverageEnd": 47351044799,
-    "TemporalCoverage": " point in time : 1501-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1501-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1501-07-01T11:59:59Z",
-    "author": [
-        "Groicki, Bart\u0142omiej (ca 1534-1605)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-166119;2019-03-01T10:55:42Z;Tytu\u0142y Prawa Maydeburskiego, do Porz\u0105dku y do Artyku\u0142\u00f3w pierwey po Polsku wydanych : W sprawach tego czasu nawi\u0119cey k\u0142opotnych s tego\u017c Prawa Maydebur[skiego] przydane [...];Groicki, Bart\u0142omiej (ca 1534-1605);starodruki 16\u00a0w.;Sp\u0142awski, Stanis\u0142aw (15..?-1569). [Adr. ded.];http://www.bj.uj.edu.pl/uj/katalog?search=KEYWORD&function=CARDSCR&u1=12&t1=xx002006352 Wsp\u00f3\u0142opr. z: BJ St. Dr. Cim. 4437;Drukarnia \u0141azarzowa;Trzecieski, Andrzej (ca 1525-ca 1584);Rej, Miko\u0142aj (1505-1569);1567;starodruk;application/xml;clarind-uds:poldilemma-166119;hdl:11858/00-246C-0000-0023-8CEF-D;Biblioteka Jagiello\u0144ska, BJ St. Dr. Cim. Qu 5015;pol;lat;http://jbc.bj.uj.edu.pl/Content/166119;oai:jbc.bj.uj.edu.pl:publication:174576;1501/1600;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1fb4159f-430e-5501-9f38-1497ee8230e4",
-    "notes": [
-        "Sp\u0142awski, Stanis\u0142aw (15..?-1569). [Adr. ded.]",
-        "http://www.bj.uj.edu.pl/uj/katalog?search=KEYWORD&function=CARDSCR&u1=12&t1=xx002006352 Wsp\u00f3\u0142opr. z: BJ St. Dr. Cim. 4437"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-166119"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Tytu\u0142y Prawa Maydeburskiego, do Porz\u0105dku y do Artyku\u0142\u00f3w pierwey po Polsku wydanych : W sprawach tego czasu nawi\u0119cey k\u0142opotnych s tego\u017c Prawa Maydebur[skiego] przydane [...]"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1fd87e44-01eb-554c-8da5-b67c13da7a69.json b/oaitestdata/clarin-oai_dc/SET_1/json/1fd87e44-01eb-554c-8da5-b67c13da7a69.json
deleted file mode 100644
index 3d17d050..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1fd87e44-01eb-554c-8da5-b67c13da7a69.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Ensslin, Astrid",
-        "Bennett, Paul",
-        "Durrell, Martin",
-        "Economic and Social Research Council (ESRC)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml",
-        "154 files : ca. 5.54 MB"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2537",
-    "MetadataAccess": [
-        "oai:ota:oucs:2537"
-    ],
-    "PublicationTimestamp": "1650-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1650"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Linguistic corpora"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License. This is a very liberal license that grants certain rights for non-commercial use, especially your right to use GerManC for your own research, but also reserves certain rights for the original creators of GerManC.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:2537;2018-10-15T09:04:33Z;http://ota.ox.ac.uk/headers/2537.xml;GerManC. A Historical Corpus of German Newspapers 1650-1800 (first version);GerManC 2007 Version;1650-1800;text_and_corpus_linguistics;Linguistic analysis (Linguistics);German language--Written German;deu;The corpus consists of 45 text samples of some 200 words each from German newspapers of the early modern period 1650-1800. There are three texts each from five German regions - North Germany, West Germany, East Central Germany, South-West Germany (including Switzerland) and South-East Germany (including Austria) - for each fifty year sub-period. The corpus consists first of a set of unannoted text files contained in sets of folders for each region and period, and also of files with each individual text, and secondly of a set of xml files each of which contains one fully annotated text, organised into folders according to sub-period and region. In addition there is a documentation file which provides a full account of each stage of the corpus construction and annotation, together with any necessary modification of TEI standards. This file also contains a complete reference list of all the names of places, organisations and historical personages occuring in the corpus. Finally, a source file provides full bibiographic details of the original texts ;Oxford Text Archive, University of Oxford;Durrell, Martin;Ensslin, Astrid;Bennett, Paul;Economic and Social Research Council (ESRC);Durrell, Martin;text/xml;154 files : ca. 5.54 MB;Text;Linguistic corpora;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License. This is a very liberal license that grants certain rights for non-commercial use, especially your right to use GerManC for your own research, but also reserves certain rights for the original creators of GerManC.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1fd87e44-01eb-554c-8da5-b67c13da7a69",
-    "notes": [
-        "The corpus consists of 45 text samples of some 200 words each from German newspapers of the early modern period 1650-1800. There are three texts each from five German regions - North Germany, West Germany, East Central Germany, South-West Germany (including Switzerland) and South-East Germany (including Austria) - for each fifty year sub-period. The corpus consists first of a set of unannoted text files contained in sets of folders for each region and period, and also of files with each individual text, and secondly of a set of xml files each of which contains one fully annotated text, organised into folders according to sub-period and region. In addition there is a documentation file which provides a full account of each stage of the corpus construction and annotation, together with any necessary modification of TEI standards. This file also contains a complete reference list of all the names of places, organisations and historical personages occuring in the corpus. Finally, a source file provides full bibiographic details of the original texts "
-    ],
-    "oai_identifier": [
-        "oai:ota:oucs:2537"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Linguistic analysis Linguistics"
-        },
-        {
-            "name": "German language--Written German"
-        }
-    ],
-    "title": [
-        "GerManC. A Historical Corpus of German Newspapers 1650-1800 (first version)",
-        "GerManC 2007 Version"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2537.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1fee5090-c945-5116-b5e0-8da779709f4a.json b/oaitestdata/clarin-oai_dc/SET_1/json/1fee5090-c945-5116-b5e0-8da779709f4a.json
deleted file mode 100644
index 1da47706..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1fee5090-c945-5116-b5e0-8da779709f4a.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3097",
-    "MetadataAccess": [
-        "oai:ota:oucs:3097"
-    ],
-    "PublicationTimestamp": "1853-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1853"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gaskell, Elizabeth Cleghorn, 1810-1865"
-    ],
-    "fulltext": "oai:ota:oucs:3097;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3097.xml;Cumberland sheep-shearers;Gaskell, Elizabeth Cleghorn, 1810-1865;not after: 1853;text_and_corpus_linguistics;Fiction -- Great Britain -- 19th century;Short stories -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1fee5090-c945-5116-b5e0-8da779709f4a",
-    "oai_identifier": [
-        "oai:ota:oucs:3097"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- Great Britain -- th century"
-        },
-        {
-            "name": "Short stories -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Cumberland sheep-shearers"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3097.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1ff7b1c1-27f2-5df6-8c79-2af5e2e0147d.json b/oaitestdata/clarin-oai_dc/SET_1/json/1ff7b1c1-27f2-5df6-8c79-2af5e2e0147d.json
deleted file mode 100644
index d742f44f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1ff7b1c1-27f2-5df6-8c79-2af5e2e0147d.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Charles University"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2927",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2927"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2927",
-    "PublicationTimestamp": "2019-01-25T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Charles University"
-    ],
-    "RelatedIdentifier": [
-        "http://ufal.mff.cuni.cz/~hana/bib/hana-hladka-2018-oslo.pdf"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Hana, Ji\u0159\u00ed",
-        "Hladk\u00e1, Barbora"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2927;2019-01-25T17:19:41Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Czesl - Universal Dependencies Release 0.5;Hana, Ji\u0159\u00ed;Hladk\u00e1, Barbora;learner corpus;syntactic annotation;universal dependencies;Syntactic annotation of 1600 sentences from the Czesl-MAN corpus using the framework of Universal Dependencies 2.3;2019-01-25;corpus;http://hdl.handle.net/11234/1-2927;ces;http://ufal.mff.cuni.cz/~hana/bib/hana-hladka-2018-oslo.pdf;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;PUB;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University;https://bitbucket.org/czesl/czesl-ud",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1ff7b1c1-27f2-5df6-8c79-2af5e2e0147d",
-    "notes": [
-        "Syntactic annotation of 1600 sentences from the Czesl-MAN corpus using the framework of Universal Dependencies 2.3"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2927"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "learner corpus"
-        },
-        {
-            "name": "syntactic annotation"
-        },
-        {
-            "name": "universal dependencies"
-        }
-    ],
-    "title": [
-        "Czesl - Universal Dependencies Release 0.5"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/1ff800ef-9632-5b41-ab78-60a44249f036.json b/oaitestdata/clarin-oai_dc/SET_1/json/1ff800ef-9632-5b41-ab78-60a44249f036.json
deleted file mode 100644
index fc97c90c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/1ff800ef-9632-5b41-ab78-60a44249f036.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "The Peter Skautrup Centre, Aarhus University"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "text/xml",
-        "application/zip"
-    ],
-    "Language": [
-        "Danish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repository.clarin.dk:20.500.12115/27",
-    "MetadataAccess": [
-        "oai:repository.clarin.dk:20.500.12115/27"
-    ],
-    "PID": "http://hdl.handle.net/20.500.12115/27",
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "The Peter Skautrup Centre, Aarhus University"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "S\u00f8rensen, Viggo"
-    ],
-    "fulltext": "oai:repository.clarin.dk:20.500.12115/27;2018-06-28T13:28:09Z;hdl_20.500.12115_1;hdl_20.500.12115_3;Jysk Ordbog (a-h), 17. April, 2011, xml-edition;S\u00f8rensen, Viggo;dialectology;Jysk Ordbog covers the dialects of Jutland c. 1700-1920. When finished the dictionary will contain c. 55.000 lemmas (often including sublemmas). The current version contains app. 16,00 entries. The word information comprises (1) pronunciation (in a simple, slightly extended Dania), (2) inflection, (3) meaning(s), (4) range, and (5) origin. Usage is shown by quotations.;2011;lexicalConceptualResource;http://hdl.handle.net/20.500.12115/27;dan;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;PUB;text/plain; charset=utf-8;application/zip;text/xml;downloadable_files_count: 2;The Peter Skautrup Centre, Aarhus University;http://jysk.au.dk/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1ff800ef-9632-5b41-ab78-60a44249f036",
-    "notes": [
-        "Jysk Ordbog covers the dialects of Jutland c. 1700-1920. When finished the dictionary will contain c. 55.000 lemmas (often including sublemmas). The current version contains app. 16,00 entries. The word information comprises (1) pronunciation (in a simple, slightly extended Dania), (2) inflection, (3) meaning(s), (4) range, and (5) origin. Usage is shown by quotations."
-    ],
-    "oai_identifier": [
-        "oai:repository.clarin.dk:20.500.12115/27"
-    ],
-    "oai_set": [
-        "hdl_20.500.12115_1",
-        "hdl_20.500.12115_3"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "dialectology"
-        }
-    ],
-    "title": [
-        "Jysk Ordbog (a-h), 17. April, 2011, xml-edition"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/202c6f56-17cb-5cc2-906f-700dfe67be70.json b/oaitestdata/clarin-oai_dc/SET_1/json/202c6f56-17cb-5cc2-906f-700dfe67be70.json
deleted file mode 100644
index dc8f6743..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/202c6f56-17cb-5cc2-906f-700dfe67be70.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Amsterdam Centre for Language and Communication, University of Amsterdam"
-    ],
-    "Contributor": [
-        "Son, Rob van"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-734",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-734"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-734",
-    "PublicationTimestamp": "2001-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2001"
-    ],
-    "Publisher": [
-        "Amsterdam Centre for Language and Communication, University of Amsterdam"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GPL"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-734;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;IFA Spoken Language Corpus;Son, Rob van;hand-segmented speech;2001;corpus;http://hdl.handle.net/11372/LRT-734;nld;GPL;downloadable_files_count: 0;Amsterdam Centre for Language and Communication, University of Amsterdam;http://www.fon.hum.uva.nl/IFA-SpokenLanguageCorpora/IFAcorpus/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "202c6f56-17cb-5cc2-906f-700dfe67be70",
-    "notes": [
-        "hand-segmented speech"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-734"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "IFA Spoken Language Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/202f6071-971b-59eb-9542-76a8a34167bd.json b/oaitestdata/clarin-oai_dc/SET_1/json/202f6071-971b-59eb-9542-76a8a34167bd.json
deleted file mode 100644
index c0b8099c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/202f6071-971b-59eb-9542-76a8a34167bd.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "NHH Norwegian School of Economics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "application/octet-stream",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Norwegian Bokm\u00e5l",
-        "Norwegian Nynorsk",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/119",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/119"
-    ],
-    "PID": "http://hdl.handle.net/11509/119",
-    "PublicationTimestamp": "2017-01-10T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "NHH Norwegian School of Economics"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource",
-        "Terminology",
-        "Terminological",
-        "Termbase"
-    ],
-    "Rights": [
-        "CLARIN_ACA",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NORED=1",
-        "ACA"
-    ],
-    "author": [
-        "NHH Norwegian School of Economics"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/119;2017-01-18T09:20:46Z;hdl_11509_1;hdl_11509_2;Maritime dictionary;NHH Norwegian School of Economics;Maritime;Terminology;Terminological;Termbase;The resource Maritim ordbok is a terminological database containing terms, definitions and other conceptual information in Norwegian and other languages within the maritime domains.;2017-01-10;lexicalConceptualResource;Terminology;Terminological;Termbase;http://hdl.handle.net/11509/119;nob;nno;eng;CLARIN_ACA;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NORED=1;ACA;application/zip;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;NHH Norwegian School of Economics;http://www.terminologi.no",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "202f6071-971b-59eb-9542-76a8a34167bd",
-    "notes": [
-        "The resource Maritim ordbok is a terminological database containing terms, definitions and other conceptual information in Norwegian and other languages within the maritime domains."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/119"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Maritime"
-        },
-        {
-            "name": "Terminology"
-        },
-        {
-            "name": "Terminological"
-        },
-        {
-            "name": "Termbase"
-        }
-    ],
-    "title": [
-        "Maritime dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/20378bf1-87d3-59f4-8faf-7cf39c3a1c63.json b/oaitestdata/clarin-oai_dc/SET_1/json/20378bf1-87d3-59f4-8faf-7cf39c3a1c63.json
deleted file mode 100644
index 26987d96..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/20378bf1-87d3-59f4-8faf-7cf39c3a1c63.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "Filesize uncompressed: 324 KBytes. "
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1679",
-    "MetadataAccess": [
-        "oai:ota:oucs:1679"
-    ],
-    "PublicationTimestamp": "1485-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1485"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Anonymous"
-    ],
-    "fulltext": "oai:ota:oucs:1679;2018-07-27T13:48:59Z;http://ota.ox.ac.uk/headers/1679.xml;Everyman;A machine-readable transcription;Anonymous;1485;text_and_corpus_linguistics;Oxford Text Archive, University of Oxford;Filesize uncompressed: 324 KBytes. ;Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "20378bf1-87d3-59f4-8faf-7cf39c3a1c63",
-    "oai_identifier": [
-        "oai:ota:oucs:1679"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Everyman",
-        "A machine-readable transcription"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1679.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/205e53a2-8494-5939-b9f6-a9073e42b4dc.json b/oaitestdata/clarin-oai_dc/SET_1/json/205e53a2-8494-5939-b9f6-a9073e42b4dc.json
deleted file mode 100644
index 276e2238..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/205e53a2-8494-5939-b9f6-a9073e42b4dc.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1153",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1153"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1153",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1153;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Wanders Deutsches Sprichw\u00f6rter-Lexikon;Germanistik;entstanden zwischen 1830 und 1880; erarbeitet von Karl Friedrich Wilhelm Wander; Angabe von Sprichw\u00f6rtern, in denen der jeweilige Suchbegriff vorkommt; neben deutschen Sprichw\u00f6rtern auch Hinweis auf \u00e4hnliche (au\u00dfer-)europ\u00e4ische Wendungen; enth\u00e4lt 250.000 Sprichw\u00f6rter;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1153;deu;downloadable_files_count: 0;http://www.zeno.org/Wander-1867",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "205e53a2-8494-5939-b9f6-a9073e42b4dc",
-    "notes": [
-        "entstanden zwischen 1830 und 1880; erarbeitet von Karl Friedrich Wilhelm Wander; Angabe von Sprichw\u00f6rtern, in denen der jeweilige Suchbegriff vorkommt; neben deutschen Sprichw\u00f6rtern auch Hinweis auf \u00e4hnliche (au\u00dfer-)europ\u00e4ische Wendungen; enth\u00e4lt 250.000 Sprichw\u00f6rter"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1153"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Wanders Deutsches Sprichw\u00f6rter-Lexikon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/20774048-8598-5cc7-8300-79969adf3bd1.json b/oaitestdata/clarin-oai_dc/SET_1/json/20774048-8598-5cc7-8300-79969adf3bd1.json
deleted file mode 100644
index 43a2a9b5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/20774048-8598-5cc7-8300-79969adf3bd1.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "text/html",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Arabic"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4872-3",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4872-3"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-4872-3",
-    "PublicationTimestamp": "2009-11-02T10:34:20Z",
-    "PublicationYear": [
-        "2009"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "PUB",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/"
-    ],
-    "author": [
-        "\u0160naidauf, Jan",
-        "Hassanov\u00e1, Kamila",
-        "Be\u0161ka, Emanuel",
-        "Haji\u010d, Jan",
-        "Kracmar, Jakub",
-        "Smr\u017e, Otakar",
-        "Pajas, Petr",
-        "Zem\u00e1nek, Petr"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4872-3;2019-01-23T19:09:35Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Prague Arabic Dependency Treebank 1.0;Haji\u010d, Jan;Smr\u017e, Otakar;Zem\u00e1nek, Petr;Pajas, Petr;\u0160naidauf, Jan;Be\u0161ka, Emanuel;Kracmar, Jakub;Hassanov\u00e1, Kamila;corpus;Arabic;The PADT project might be summarized as an open-ended activity of the Center for Computational Linguistics, the Institute of Formal and Applied Linguistics, and the Institute of Comparative Linguistics, Charles University in Prague, resting in multi-level annotation of Arabic language resources in the light of the theory of Functional Generative Description (Sgall et al., 1986; Haji\u010dov\u00e1 and Sgall, 2003).;2009-11-02T10:34:20Z;corpus;http://hdl.handle.net/11858/00-097C-0000-0001-4872-3;ara;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);PUB;http://creativecommons.org/licenses/by-nc-sa/3.0/;application/zip;text/html;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/padt",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "20774048-8598-5cc7-8300-79969adf3bd1",
-    "notes": [
-        "The PADT project might be summarized as an open-ended activity of the Center for Computational Linguistics, the Institute of Formal and Applied Linguistics, and the Institute of Comparative Linguistics, Charles University in Prague, resting in multi-level annotation of Arabic language resources in the light of the theory of Functional Generative Description (Sgall et al., 1986; Haji\u010dov\u00e1 and Sgall, 2003)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4872-3"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "Arabic"
-        }
-    ],
-    "title": [
-        "Prague Arabic Dependency Treebank 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2081fa58-b80a-598c-a874-29f131b4984a.json b/oaitestdata/clarin-oai_dc/SET_1/json/2081fa58-b80a-598c-a874-29f131b4984a.json
deleted file mode 100644
index 9bcf61a3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2081fa58-b80a-598c-a874-29f131b4984a.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Survey of English Usage, University College London"
-    ],
-    "Contributor": [
-        "Aarts, Gas"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-900",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-900"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-900",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Survey of English Usage, University College London"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-900;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Diachronic Corpus of Present-Day Spoken English (DCPSE);Aarts, Gas;A parsed corpus of spoken English. Ca 400,000 words from ICE-GB (early 1990s) and 400,000 words from the London-Lund Corpus (late 1960s-early 1980s). The orthographic transcriptions have been normalised and annotated.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-900;eng;downloadable_files_count: 0;United Kingdom;Survey of English Usage, University College London;http://www.ucl.ac.uk/english-usage/projects/dcpse/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2081fa58-b80a-598c-a874-29f131b4984a",
-    "notes": [
-        "A parsed corpus of spoken English. Ca 400,000 words from ICE-GB (early 1990s) and 400,000 words from the London-Lund Corpus (late 1960s-early 1980s). The orthographic transcriptions have been normalised and annotated."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-900"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Diachronic Corpus of Present-Day Spoken English (DCPSE)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2092056b-7435-5d6d-8661-2709d9727785.json b/oaitestdata/clarin-oai_dc/SET_1/json/2092056b-7435-5d6d-8661-2709d9727785.json
deleted file mode 100644
index 0973bd5c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2092056b-7435-5d6d-8661-2709d9727785.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Rahtz, S.P.Q."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 186 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1223",
-    "MetadataAccess": [
-        "oai:ota:oucs:1223"
-    ],
-    "PublicationTimestamp": "1975-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1975"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hinton, S.E."
-    ],
-    "fulltext": "oai:ota:oucs:1223;2018-03-05T15:14:52Z;http://ota.ox.ac.uk/headers/1223.xml;That was then, this is now / S.E. Hinton;Hinton, S.E.;1975;text_and_corpus_linguistics;American fiction -- 20th century;eng;Oxford Text Archive, University of Oxford;Rahtz, S.P.Q.;(1 file : ca. 186 KB);Text;Novels;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2092056b-7435-5d6d-8661-2709d9727785",
-    "oai_identifier": [
-        "oai:ota:oucs:1223"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "American fiction -- th century"
-        }
-    ],
-    "title": [
-        "That was then, this is now / S.E. Hinton"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1223.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/20b29207-2bb7-5591-87b1-461ababd150c.json b/oaitestdata/clarin-oai_dc/SET_1/json/20b29207-2bb7-5591-87b1-461ababd150c.json
deleted file mode 100644
index 2504a31a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/20b29207-2bb7-5591-87b1-461ababd150c.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Kiel University"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-722",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-722"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-722",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Kiel University"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Code of conduct"
-    ],
-    "SpatialCoverage": [
-        "Papua New Guinea"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-722;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Teop corpus;Documentation of the Teop project (DoBeS project);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-722;Code of conduct;downloadable_files_count: 0;Papua New Guinea;Kiel University;http://www.mpi.nl/DOBES/projects/teop/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "20b29207-2bb7-5591-87b1-461ababd150c",
-    "notes": [
-        "Documentation of the Teop project (DoBeS project)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-722"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Teop corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/20bcd4f8-eb7f-5477-825e-7499a3d1f307.json b/oaitestdata/clarin-oai_dc/SET_1/json/20bcd4f8-eb7f-5477-825e-7499a3d1f307.json
deleted file mode 100644
index 40e9006e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/20bcd4f8-eb7f-5477-825e-7499a3d1f307.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5635",
-    "MetadataAccess": [
-        "oai:ota:oucs:5635"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Griffith, Richard, d. 1788."
-    ],
-    "fulltext": "oai:ota:oucs:5635;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5635.xml;The triumvirate: or, the authentic memoirs of A. B. and C. In two volumes. ... [pt.1];Griffith, Richard, d. 1788.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "20bcd4f8-eb7f-5477-825e-7499a3d1f307",
-    "oai_identifier": [
-        "oai:ota:oucs:5635"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The triumvirate: or, the authentic memoirs of A. B. and C. In two volumes. ... [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5635.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/20d4706c-7862-59e6-ae56-cd1d27ec7b58.json b/oaitestdata/clarin-oai_dc/SET_1/json/20d4706c-7862-59e6-ae56-cd1d27ec7b58.json
deleted file mode 100644
index 08329067..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/20d4706c-7862-59e6-ae56-cd1d27ec7b58.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paterson, Kevin"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "4 files : ca. 411 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2516",
-    "MetadataAccess": [
-        "oai:ota:oucs:2516"
-    ],
-    "PublicationTimestamp": "2005-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2005"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Databases"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Paterson, Kevin"
-    ],
-    "fulltext": "oai:ota:oucs:2516;2018-05-24T15:55:34Z;http://ota.ox.ac.uk/headers/2516.xml;Discourse context and the processing of contrastive focus in silent reading (SPSS data files);Paterson, Kevin;2005-2006;text_and_corpus_linguistics;Comprehension;Psychology tests;Eye Movements;eng;Words such as \u00e2\u0080\u009conly\u00e2\u0080\u009d and \u00e2\u0080\u009ceven\u00e2\u0080\u009d indicate that a contrast is to be made between information that is given in a sentence and some alternatives. For example, a sentence such as \u00e2\u0080\u009cOnly Mary kissed John\u00e2\u0080\u009d means that Mary kissed John but no-one else did. However, sentences that contain these words often have more than one possible meaning, depending on which part of the sentence is used to form the contrast. We conducted three experiments in which we analysed eye movements during reading to investigate skilled readers\u00e2\u0080\u0099 understanding of sentences containing \u00e2\u0080\u009conly\u00e2\u0080\u009d. The results demonstrated that skilled readers make rapid use of grammatical and contextual knowledge to select the appropriate meaning of a sentence, but that grammatical knowledge has the more important role. Although these findings are directly informative about skilled reading, they may also provide insights into problems that might be encountered by beginning readers or people with reading difficulty. ;Oxford Text Archive, University of Oxford;Paterson, Kevin;4 files : ca. 411 KB;Text;Databases;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "20d4706c-7862-59e6-ae56-cd1d27ec7b58",
-    "notes": [
-        "Words such as \u00e2\u0080\u009conly\u00e2\u0080\u009d and \u00e2\u0080\u009ceven\u00e2\u0080\u009d indicate that a contrast is to be made between information that is given in a sentence and some alternatives. For example, a sentence such as \u00e2\u0080\u009cOnly Mary kissed John\u00e2\u0080\u009d means that Mary kissed John but no-one else did. However, sentences that contain these words often have more than one possible meaning, depending on which part of the sentence is used to form the contrast. We conducted three experiments in which we analysed eye movements during reading to investigate skilled readers\u00e2\u0080\u0099 understanding of sentences containing \u00e2\u0080\u009conly\u00e2\u0080\u009d. The results demonstrated that skilled readers make rapid use of grammatical and contextual knowledge to select the appropriate meaning of a sentence, but that grammatical knowledge has the more important role. Although these findings are directly informative about skilled reading, they may also provide insights into problems that might be encountered by beginning readers or people with reading difficulty. "
-    ],
-    "oai_identifier": [
-        "oai:ota:oucs:2516"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Comprehension"
-        },
-        {
-            "name": "Psychology tests"
-        },
-        {
-            "name": "Eye Movements"
-        }
-    ],
-    "title": [
-        "Discourse context and the processing of contrastive focus in silent reading (SPSS data files)"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2516.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/20e041ab-0b34-526e-9c45-908e4bb6d023.json b/oaitestdata/clarin-oai_dc/SET_1/json/20e041ab-0b34-526e-9c45-908e4bb6d023.json
deleted file mode 100644
index ad00d00b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/20e041ab-0b34-526e-9c45-908e4bb6d023.json
+++ /dev/null
@@ -1,98 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 5",
-        "application/zip",
-        "application/pdf",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1085",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1085"
-    ],
-    "PID": "http://hdl.handle.net/11356/1085",
-    "PublicationTimestamp": "2016-12-30T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11356/1123",
-        "http://hdl.handle.net/11356/1079",
-        "http://hdl.handle.net/11356/1081"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by-sa/4.0/"
-    ],
-    "author": [
-        "\u010cibej, Jaka",
-        "Ljube\u0161i\u0107, Nikola",
-        "Erjavec, Toma\u017e",
-        "Fi\u0161er, Darja",
-        "Arhar Holdt, \u0160pela"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1085;2018-10-24T20:58:42Z;hdl_11356_1023;hdl_11356_1024;CMC training corpus Janes-Tag 1.2;Erjavec, Toma\u017e;Fi\u0161er, Darja;\u010cibej, Jaka;Arhar Holdt, \u0160pela;Ljube\u0161i\u0107, Nikola;computer-mediated communication;tokenisation;word normalisation;tagging;lemmatisation;manual annotation;TEI;Janes-Tag is a manually annotated corpus of Slovene Computer-Mediated Communication (CMC). It is meant as a gold-standard training and testing dataset for tokenisation, sentence segmentation, word normalisation, morphosyntactic tagging and lemmatisation of non-standard Slovene. As the corpus has been carefully manually annotated, it is also suitable for detailed linguistic explorations which require highly accurate and reliable annotations.\r\n\r\nA slightly older version of this corpus is described in:\r\nERJAVEC, Toma\u017e, \u010cIBEJ, Jaka, ARHAR HOLDT, \u0160pela, LJUBE\u0160I\u0106, Nikola, FI\u0160ER, Darja. Gold-standard datasets for annotation of Slovene computer-mediated communication. In Proceedings of RASLAN 2016: Recent Advances in Slavonic Natural Language Processing. Brno: Tribun EU, 2016, pp. 29-40, https://nlp.fi.muni.cz/raslan/raslan16.pdf\r\n\r\nNote that a related corpus, Janes-Norm is also available, cf. http://hdl.handle.net/11356/1084.;2016-12-30;corpus;http://hdl.handle.net/11356/1085;slv;http://hdl.handle.net/11356/1123;http://hdl.handle.net/11356/1079;http://hdl.handle.net/11356/1081;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);PUB;https://creativecommons.org/licenses/by-sa/4.0/;application/pdf;application/pdf;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 5;Jo\u017eef Stefan Institute;http://nl.ijs.si/janes/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "20e041ab-0b34-526e-9c45-908e4bb6d023",
-    "notes": [
-        "Janes-Tag is a manually annotated corpus of Slovene Computer-Mediated Communication (CMC). It is meant as a gold-standard training and testing dataset for tokenisation, sentence segmentation, word normalisation, morphosyntactic tagging and lemmatisation of non-standard Slovene. As the corpus has been carefully manually annotated, it is also suitable for detailed linguistic explorations which require highly accurate and reliable annotations.\r\n\r\nA slightly older version of this corpus is described in:\r\nERJAVEC, Toma\u017e, \u010cIBEJ, Jaka, ARHAR HOLDT, \u0160pela, LJUBE\u0160I\u0106, Nikola, FI\u0160ER, Darja. Gold-standard datasets for annotation of Slovene computer-mediated communication. In Proceedings of RASLAN 2016: Recent Advances in Slavonic Natural Language Processing. Brno: Tribun EU, 2016, pp. 29-40, https://nlp.fi.muni.cz/raslan/raslan16.pdf\r\n\r\nNote that a related corpus, Janes-Norm is also available, cf. http://hdl.handle.net/11356/1084."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1085"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "computer-mediated communication"
-        },
-        {
-            "name": "tokenisation"
-        },
-        {
-            "name": "word normalisation"
-        },
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "lemmatisation"
-        },
-        {
-            "name": "manual annotation"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "CMC training corpus Janes-Tag 1.2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/20e3b29a-1d9c-5b60-8199-a1f4a0196305.json b/oaitestdata/clarin-oai_dc/SET_1/json/20e3b29a-1d9c-5b60-8199-a1f4a0196305.json
deleted file mode 100644
index 53a94153..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/20e3b29a-1d9c-5b60-8199-a1f4a0196305.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3430",
-    "MetadataAccess": [
-        "oai:ota:oucs:3430"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Johnson, Samuel, 1709-1784."
-    ],
-    "fulltext": "oai:ota:oucs:3430;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3430.xml;The Rambler.: [pt.1];Johnson, Samuel, 1709-1784.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "20e3b29a-1d9c-5b60-8199-a1f4a0196305",
-    "oai_identifier": [
-        "oai:ota:oucs:3430"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The Rambler.: [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3430.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/20f25e02-08f9-5031-b3bd-748d84155229.json b/oaitestdata/clarin-oai_dc/SET_1/json/20f25e02-08f9-5031-b3bd-748d84155229.json
deleted file mode 100644
index cf48e9af..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/20f25e02-08f9-5031-b3bd-748d84155229.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3810",
-    "MetadataAccess": [
-        "oai:ota:oucs:3810"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Jerningham, Mr. (Edward), 1737?-1812."
-    ],
-    "fulltext": "oai:ota:oucs:3810;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3810.xml;Abelard to Eloisa: a poem. By Mr. Jerningham.;Jerningham, Mr. (Edward), 1737?-1812.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "20f25e02-08f9-5031-b3bd-748d84155229",
-    "oai_identifier": [
-        "oai:ota:oucs:3810"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Abelard to Eloisa: a poem. By Mr. Jerningham."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3810.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/210fdf56-d656-514f-9b19-d562af7f5c73.json b/oaitestdata/clarin-oai_dc/SET_1/json/210fdf56-d656-514f-9b19-d562af7f5c73.json
deleted file mode 100644
index 80eec8dd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/210fdf56-d656-514f-9b19-d562af7f5c73.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Department of Information Technology, Gauhati University, Assam, India"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Assamese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/617",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/617"
-    ],
-    "PID": "http://hdl.handle.net/11321/617",
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Department of Information Technology, Gauhati University, Assam, India"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "author": [
-        "Sarma, Prof. Shikhar Kr."
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/617;2019-01-08T10:52:22Z;hdl_11321_3;hdl_11321_610;Assamese-English Bilingual Dictionary;Sarma, Prof. Shikhar Kr.;Assamese NLP;Words;Assamese Lemas;Assamese English Bilingual Dictionery;Assamese-English;Gauhati University;The Bilingual dictionary is created for Assamese-English.. In the Bilingual dictionary English meaning of Assamese words are given with POS of the words.\r\n\r\n---\r\n\r\n1. These Assamese NLP resources including the Tools and Applications are developed\r\nduring Research and Development Projects as well as Masters and Ph.D. thesis\r\nworks.\r\n2. These are mainly developed or generated at Gauhati University Department of\r\nComputer Science and Department of Information Technology.\r\n3. These resources are used by students and researchers for further studies, researches, as\r\nwell as for design and development of tools and applications.\r\n4. Computational Linguistics in Assamese is not rich, and Natural Language Processing\r\nworks have mainly started during last two decades, and most of the resources are first\r\ngeneration resources, and with ample scope for upgrading, enriching, and purifying.\r\n5. These are very good and essential resources for all the researchers in Assamese NLP, as\r\nthe language requires more and more NLP works to make Assamese a rich media for\r\nthe digital world.\r\n6. Anyone interested, or in need of such resources may express their interest for the\r\nrequired resources, and the way of availability will be advised/informed accordingly.\r\n7. These are purely research materials and could only be used for further research only.\r\n8. Researchers may visit the NLP Lab of Department of Information Technology, Gauhati\r\nUniversity, Guwahati, India or contact us.\r\n9. Researchers interested in collaborative works, and also students for project works, are\r\nwelcome.\r\n10. Contact person is Professor Shikhar Kr. Sarma, Department of Information\r\nTechnology, Gauhati University, Guwahati 781014, Assam, India. Email-\r\nsks@gauhati.ac.in;2019-01-08;lexicalConceptualResource;http://hdl.handle.net/11321/617;asm;downloadable_files_count: 0;Department of Information Technology, Gauhati University, Assam, India",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "210fdf56-d656-514f-9b19-d562af7f5c73",
-    "notes": [
-        "The Bilingual dictionary is created for Assamese-English.. In the Bilingual dictionary English meaning of Assamese words are given with POS of the words.\r\n\r\n---\r\n\r\n1. These Assamese NLP resources including the Tools and Applications are developed\r\nduring Research and Development Projects as well as Masters and Ph.D. thesis\r\nworks.\r\n2. These are mainly developed or generated at Gauhati University Department of\r\nComputer Science and Department of Information Technology.\r\n3. These resources are used by students and researchers for further studies, researches, as\r\nwell as for design and development of tools and applications.\r\n4. Computational Linguistics in Assamese is not rich, and Natural Language Processing\r\nworks have mainly started during last two decades, and most of the resources are first\r\ngeneration resources, and with ample scope for upgrading, enriching, and purifying.\r\n5. These are very good and essential resources for all the researchers in Assamese NLP, as\r\nthe language requires more and more NLP works to make Assamese a rich media for\r\nthe digital world.\r\n6. Anyone interested, or in need of such resources may express their interest for the\r\nrequired resources, and the way of availability will be advised/informed accordingly.\r\n7. These are purely research materials and could only be used for further research only.\r\n8. Researchers may visit the NLP Lab of Department of Information Technology, Gauhati\r\nUniversity, Guwahati, India or contact us.\r\n9. Researchers interested in collaborative works, and also students for project works, are\r\nwelcome.\r\n10. Contact person is Professor Shikhar Kr. Sarma, Department of Information\r\nTechnology, Gauhati University, Guwahati 781014, Assam, India. Email-\r\nsks@gauhati.ac.in"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/617"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_610"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Assamese NLP"
-        },
-        {
-            "name": "Words"
-        },
-        {
-            "name": "Assamese Lemas"
-        },
-        {
-            "name": "Assamese English Bilingual Dictionery"
-        },
-        {
-            "name": "Assamese-English"
-        },
-        {
-            "name": "Gauhati University"
-        }
-    ],
-    "title": [
-        "Assamese-English Bilingual Dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/21181c4e-c5fb-5b5c-9ec2-8951ba17e34d.json b/oaitestdata/clarin-oai_dc/SET_1/json/21181c4e-c5fb-5b5c-9ec2-8951ba17e34d.json
deleted file mode 100644
index 3225c78f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/21181c4e-c5fb-5b5c-9ec2-8951ba17e34d.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Imperial College London",
-        "Iliffe, Rob",
-        "European Commission",
-        "Royal Society",
-        "AHRB"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "1725 files: ca. 331 MB",
-        "text/xml"
-    ],
-    "Language": [
-        "English",
-        "Latin",
-        "Ancient Greek (to 1453)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2479",
-    "MetadataAccess": [
-        "oai:ota:oucs:2479"
-    ],
-    "PublicationTimestamp": "2004-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2004"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Biographies"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Young, John",
-        "Hawkins, Michael",
-        "Iliffe, Rob"
-    ],
-    "fulltext": "oai:ota:oucs:2479;2018-02-16T10:42:06Z;http://ota.ox.ac.uk/headers/2479.xml;The Newton Project;The Newton Manuscript Project;Iliffe, Rob;Young, John;Hawkins, Michael;2004;text_and_corpus_linguistics;Physics--Religious aspects;Physics--Bibliography;Physics literature;eng;lat;grc;The resource consists of a number of different pages or files giving information on Newton's life and work and also on the development of the Newton Project. There is also detailed information relating to editorial principles and technical issues relating to the web site. The central focus of the resource is the series of XML encoded transcriptions of Newton's theological works, personal notebooks, all draft biographical information about Newton dating from the eighteenth century, and also many of his early scientific papers. ;Oxford Text Archive, University of Oxford;AHRB;Royal Society;European Commission;Imperial College London;Iliffe, Rob;text/xml;1725 files: ca. 331 MB;Text;Biographies;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "21181c4e-c5fb-5b5c-9ec2-8951ba17e34d",
-    "notes": [
-        "The resource consists of a number of different pages or files giving information on Newton's life and work and also on the development of the Newton Project. There is also detailed information relating to editorial principles and technical issues relating to the web site. The central focus of the resource is the series of XML encoded transcriptions of Newton's theological works, personal notebooks, all draft biographical information about Newton dating from the eighteenth century, and also many of his early scientific papers. "
-    ],
-    "oai_identifier": [
-        "oai:ota:oucs:2479"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Physics--Religious aspects"
-        },
-        {
-            "name": "Physics--Bibliography"
-        },
-        {
-            "name": "Physics literature"
-        }
-    ],
-    "title": [
-        "The Newton Project",
-        "The Newton Manuscript Project"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2479.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/211c4bfc-aa81-5c0f-90aa-f4a29e119c30.json b/oaitestdata/clarin-oai_dc/SET_1/json/211c4bfc-aa81-5c0f-90aa-f4a29e119c30.json
deleted file mode 100644
index d5d2624a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/211c4bfc-aa81-5c0f-90aa-f4a29e119c30.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Prus"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/106",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/106"
-    ],
-    "PID": "http://hdl.handle.net/11321/106",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Prus"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Prus, Prus"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/106;2015-04-08T14:09:43Z;hdl_11321_3;hdl_11321_4;MWE Prus, Emancypantki, Tom 1;Prus, Prus;Prus;2015-04-08;corpus;http://hdl.handle.net/11321/106;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain; charset=utf-8;downloadable_files_count: 1;Prus",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "211c4bfc-aa81-5c0f-90aa-f4a29e119c30",
-    "notes": [
-        "Prus"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/106"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Prus, Emancypantki, Tom 1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2126621a-97e0-5c56-91f4-83f73068522d.json b/oaitestdata/clarin-oai_dc/SET_1/json/2126621a-97e0-5c56-91f4-83f73068522d.json
deleted file mode 100644
index 0de45c86..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2126621a-97e0-5c56-91f4-83f73068522d.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Quechua"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-991",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-991"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-991",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-991;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LAC Cusco Quechua Corpus;Language and Cognition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-991;que;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI33960%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2126621a-97e0-5c56-91f4-83f73068522d",
-    "notes": [
-        "Language and Cognition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-991"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LAC Cusco Quechua Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/212918f0-e341-5b49-8926-113389eb187e.json b/oaitestdata/clarin-oai_dc/SET_1/json/212918f0-e341-5b49-8926-113389eb187e.json
deleted file mode 100644
index b9828fe2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/212918f0-e341-5b49-8926-113389eb187e.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3220",
-    "MetadataAccess": [
-        "oai:ota:oucs:3220"
-    ],
-    "PublicationTimestamp": "1551-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1551"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "More, Thomas, Sir, Saint, 1478-1535"
-    ],
-    "fulltext": "oai:ota:oucs:3220;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3220.xml;Utopia;More, Thomas, Sir, Saint, 1478-1535;1551;text_and_corpus_linguistics;Fiction -- England -- 16th century;Fantasy literature -- England -- 16th century;Utopian literature -- England -- 16th century;Essays -- England -- 16th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "212918f0-e341-5b49-8926-113389eb187e",
-    "oai_identifier": [
-        "oai:ota:oucs:3220"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- England -- th century"
-        },
-        {
-            "name": "Fantasy literature -- England -- th century"
-        },
-        {
-            "name": "Utopian literature -- England -- th century"
-        },
-        {
-            "name": "Essays -- England -- th century"
-        }
-    ],
-    "title": [
-        "Utopia"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3220.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2151b440-8fa1-5d00-889a-0323afc65a00.json b/oaitestdata/clarin-oai_dc/SET_1/json/2151b440-8fa1-5d00-889a-0323afc65a00.json
deleted file mode 100644
index d8178650..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2151b440-8fa1-5d00-889a-0323afc65a00.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4895",
-    "MetadataAccess": [
-        "oai:ota:oucs:4895"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Trusler, John, 1735-1820."
-    ],
-    "fulltext": "oai:ota:oucs:4895;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4895.xml;A descriptive account of the islands lately discovered in the South-Seas: Giving a full detail of the present state of the inhabitants, their government, religion, ... by the Reverend Dr. John Trusler, ...;Trusler, John, 1735-1820.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2151b440-8fa1-5d00-889a-0323afc65a00",
-    "oai_identifier": [
-        "oai:ota:oucs:4895"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A descriptive account of the islands lately discovered in the South-Seas: Giving a full detail of the present state of the inhabitants, their government, religion, ... by the Reverend Dr. John Trusler, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4895.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/21761edd-d495-583a-92a2-f2079ca00a4c.json b/oaitestdata/clarin-oai_dc/SET_1/json/21761edd-d495-583a-92a2-f2079ca00a4c.json
deleted file mode 100644
index a4f6c34f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/21761edd-d495-583a-92a2-f2079ca00a4c.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/292",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/292"
-    ],
-    "PID": "http://hdl.handle.net/11321/292",
-    "PublicationTimestamp": "2016-04-25T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Marci\u0144czuk, Micha\u0142",
-        "Kaczmarek, Adam"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/292;2016-06-06T11:02:23Z;hdl_11321_3;hdl_11321_4;Liner2.5 model Minos;Kaczmarek, Adam;Marci\u0144czuk, Micha\u0142;information extraction;null subject;coreference;A model for Liner2.5 to recognize verbs without an explicit subject.;2016-04-25;lexicalConceptualResource;http://hdl.handle.net/11321/292;pol;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;Wroc\u0142aw University of Technology;http://nlp.pwr.wroc.pl/narzedzia-i-zasoby/narzedzia/liner2",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "21761edd-d495-583a-92a2-f2079ca00a4c",
-    "notes": [
-        "A model for Liner2.5 to recognize verbs without an explicit subject."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/292"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "information extraction"
-        },
-        {
-            "name": "null subject"
-        },
-        {
-            "name": "coreference"
-        }
-    ],
-    "title": [
-        "Liner2.5 model Minos"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2179d5d5-22c8-566b-bf56-0df1a03fd130.json b/oaitestdata/clarin-oai_dc/SET_1/json/2179d5d5-22c8-566b-bf56-0df1a03fd130.json
deleted file mode 100644
index 0a615497..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2179d5d5-22c8-566b-bf56-0df1a03fd130.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Druk. P. Dufour"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-8576",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-8576"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D3C-6",
-    "PublicationTimestamp": "1789-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1789"
-    ],
-    "Publisher": [
-        "Druk. P. Dufour"
-    ],
-    "RelatedIdentifier": [
-        "http://www.pbc.rzeszow.pl/Content/8576",
-        "oai:www.pbc.rzeszow.pl:publication:9288"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "author": [
-        "M\u0119drzecki, Adam ( -1832)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-8576;2019-03-01T17:46:52Z;Prawa miast polskich do w\u0142adzy rz\u0105dowey, wykonywaj\u0105cey i s\u0105downiczey;M\u0119drzecki, Adam ( -1832);prawo pa\u0144stwowe - Polska - 14-18 w.;rz\u0105d (organ pa\u0144stw.);Tyt., nazwa aut., wydawcy, miejsce i rok wyd. wg K. Estreicher: Bibliografia polska. T. 22 i 25;Na s. tyt. wers: \u201ew\u0142adzy prawodawczey\u201d wydrukowany na pasku papieru i naklejony w zast\u0119pstwie pierwotnych s\u0142\u00f3w: \u201ew\u0142adzy rz\u0105dowey\u201d;Druk. P. Dufour;1789;starodruk;application/xml;clarind-uds:poldilemma-8576;hdl:11858/00-246C-0000-0023-8D3C-6;Sygnatura orygina\u0142u: SD-967;pol;lat;http://www.pbc.rzeszow.pl/Content/8576;oai:www.pbc.rzeszow.pl:publication:9288;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2179d5d5-22c8-566b-bf56-0df1a03fd130",
-    "notes": [
-        "Tyt., nazwa aut., wydawcy, miejsce i rok wyd. wg K. Estreicher: Bibliografia polska. T. 22 i 25",
-        "Na s. tyt. wers: \u201ew\u0142adzy prawodawczey\u201d wydrukowany na pasku papieru i naklejony w zast\u0119pstwie pierwotnych s\u0142\u00f3w: \u201ew\u0142adzy rz\u0105dowey\u201d"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-8576"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Prawa miast polskich do w\u0142adzy rz\u0105dowey, wykonywaj\u0105cey i s\u0105downiczey"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/218b113a-d675-5a8c-8fbc-61edf27871de.json b/oaitestdata/clarin-oai_dc/SET_1/json/218b113a-d675-5a8c-8fbc-61edf27871de.json
deleted file mode 100644
index b364f517..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/218b113a-d675-5a8c-8fbc-61edf27871de.json
+++ /dev/null
@@ -1,128 +0,0 @@
-{
-    "Contact": [
-        "Universal Dependencies Consortium"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 3"
-    ],
-    "Language": [
-        "Czech",
-        "German",
-        "English",
-        "Spanish",
-        "Finnish",
-        "French",
-        "Irish",
-        "Italian",
-        "Swedish",
-        "Hungarian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1464",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1464"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1464",
-    "PublicationTimestamp": "2015-01-15T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Universal Dependencies Consortium"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/LRT-1478"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Universal Dependencies 1.0 License Set",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/license-ud-1.0",
-        "PUB"
-    ],
-    "author": [
-        "Manning, Christopher",
-        "Bosco, Cristina",
-        "Lynn, Teresa",
-        "Ginter, Filip",
-        "Pyysalo, Sampo",
-        "Kanerva, Jenna",
-        "Choi, Jinho",
-        "Haji\u010d, Jan",
-        "Vincze, Veronika",
-        "Simi, Maria",
-        "Dozat, Timothy",
-        "Tsarfaty, Reut",
-        "Goldberg, Yoav",
-        "Zeman, Daniel",
-        "Nivre, Joakim",
-        "Petrov, Slav",
-        "Foster, Jennifer",
-        "Smith, Aaron",
-        "de Marneffe, Marie-Catherine",
-        "Lenci, Alessandro",
-        "Farkas, Rich\u00e1rd",
-        "Missil\u00e4, Anna",
-        "Montemagni, Simonetta",
-        "McDonald, Ryan",
-        "Silveira, Natalia",
-        "Laippala, Veronika"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1464;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Universal Dependencies 1.0;Nivre, Joakim;Bosco, Cristina;Choi, Jinho;de Marneffe, Marie-Catherine;Dozat, Timothy;Farkas, Rich\u00e1rd;Foster, Jennifer;Ginter, Filip;Goldberg, Yoav;Haji\u010d, Jan;Kanerva, Jenna;Laippala, Veronika;Lenci, Alessandro;Lynn, Teresa;Manning, Christopher;McDonald, Ryan;Missil\u00e4, Anna;Montemagni, Simonetta;Petrov, Slav;Pyysalo, Sampo;Silveira, Natalia;Simi, Maria;Smith, Aaron;Tsarfaty, Reut;Vincze, Veronika;Zeman, Daniel;treebank;dependency;syntax;morphology;harmonized annotation;interset;universal tagset;stanford dependencies;Universal Dependencies is a project that seeks to develop cross-linguistically consistent treebank annotation for many languages, with the goal of facilitating multilingual parser development, cross-lingual learning, and parsing research from a language typology perspective. The annotation scheme is based on (universal) Stanford dependencies (de Marneffe et al., 2006, 2008, 2014), Google universal part-of-speech tags (Petrov et al., 2012), and the Interset interlingua for morphosyntactic tagsets (Zeman, 2008).;2015-01-15;corpus;http://hdl.handle.net/11234/1-1464;ces;deu;eng;spa;fin;fra;gle;ita;swe;hun;http://hdl.handle.net/11234/LRT-1478;Universal Dependencies 1.0 License Set;https://lindat.mff.cuni.cz/repository/xmlui/page/license-ud-1.0;PUB;text/plain; charset=utf-8;application/x-gzip;application/x-gzip;application/x-gzip;downloadable_files_count: 3;Universal Dependencies Consortium;http://universaldependencies.github.io/docs/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "218b113a-d675-5a8c-8fbc-61edf27871de",
-    "notes": [
-        "Universal Dependencies is a project that seeks to develop cross-linguistically consistent treebank annotation for many languages, with the goal of facilitating multilingual parser development, cross-lingual learning, and parsing research from a language typology perspective. The annotation scheme is based on (universal) Stanford dependencies (de Marneffe et al., 2006, 2008, 2014), Google universal part-of-speech tags (Petrov et al., 2012), and the Interset interlingua for morphosyntactic tagsets (Zeman, 2008)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1464"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "dependency"
-        },
-        {
-            "name": "syntax"
-        },
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "harmonized annotation"
-        },
-        {
-            "name": "interset"
-        },
-        {
-            "name": "universal tagset"
-        },
-        {
-            "name": "stanford dependencies"
-        }
-    ],
-    "title": [
-        "Universal Dependencies 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/218be1dc-ff85-5a92-a1c4-b7b85cf8c6e4.json b/oaitestdata/clarin-oai_dc/SET_1/json/218be1dc-ff85-5a92-a1c4-b7b85cf8c6e4.json
deleted file mode 100644
index 4ab74ec9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/218be1dc-ff85-5a92-a1c4-b7b85cf8c6e4.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=d1713e2a616e11e2a2aa782bcb07413598c77c99d681403c80d35ed76cea7826",
-    "MetadataAccess": [
-        "d1713e2a616e11e2a2aa782bcb07413598c77c99d681403c80d35ed76cea7826"
-    ],
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "d1713e2a616e11e2a2aa782bcb07413598c77c99d681403c80d35ed76cea7826;2019-02-27T12:09:30Z;corpus;corpus:text;TreeBankPT;The TreeBankPT (Branco et al., 2011) is a corpus of syntactic constituency trees of the translated news composed of 3,406 sentences and 44,598 tokens taken from the Wall Street Journal.\nFor the creation of this TreeBank we adopted a semi-automatic analysis with a double-blind annotation followed by adjudication. The resulting dataset contains one information level: phrase constituency.\nThe main motivation behind the creation of this resource was to build a high quality data set with syntactic information that could support the development of a large set of automatic resources and tools for Portuguese for NLP studies.\nThe development of this resource started under the METANET4U project (at: http://metanet4u.eu/) whose main goal is to contribute to the establishment of a pan-European digital platform that makes available language resources and services, encompassing both datasets and software tools, for speech and language processing, and supports a new generation of exchange facilities for them. \n;2015-12-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "218be1dc-ff85-5a92-a1c4-b7b85cf8c6e4",
-    "notes": [
-        "The TreeBankPT (Branco et al., 2011) is a corpus of syntactic constituency trees of the translated news composed of 3,406 sentences and 44,598 tokens taken from the Wall Street Journal.\nFor the creation of this TreeBank we adopted a semi-automatic analysis with a double-blind annotation followed by adjudication. The resulting dataset contains one information level: phrase constituency.\nThe main motivation behind the creation of this resource was to build a high quality data set with syntactic information that could support the development of a large set of automatic resources and tools for Portuguese for NLP studies.\nThe development of this resource started under the METANET4U project (at: http://metanet4u.eu/) whose main goal is to contribute to the establishment of a pan-European digital platform that makes available language resources and services, encompassing both datasets and software tools, for speech and language processing, and supports a new generation of exchange facilities for them. \n"
-    ],
-    "oai_identifier": [
-        "d1713e2a616e11e2a2aa782bcb07413598c77c99d681403c80d35ed76cea7826"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "TreeBankPT"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/21a5e4b2-f547-52a3-b879-07f2dc179bd4.json b/oaitestdata/clarin-oai_dc/SET_1/json/21a5e4b2-f547-52a3-b879-07f2dc179bd4.json
deleted file mode 100644
index 70d6de81..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/21a5e4b2-f547-52a3-b879-07f2dc179bd4.json
+++ /dev/null
@@ -1,112 +0,0 @@
-{
-    "Contact": [
-        "Institute for Applied Linguistics, Eurac Research"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 10",
-        "text/html",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech",
-        "German",
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin.eurac.edu:20.500.12124/6",
-    "MetadataAccess": [
-        "oai:clarin.eurac.edu:20.500.12124/6"
-    ],
-    "PID": "http://hdl.handle.net/20.500.12124/6",
-    "PublicationTimestamp": "2018-08-24T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Institute for Applied Linguistics, Eurac Research"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/200250",
-        "https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-docs/tags/v1.1",
-        "https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-text/tags/v1.1",
-        "https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-metadata/tags/v1.1",
-        "https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-tasks/tags/v1.1",
-        "https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-paula/tags/v1.1",
-        "https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-annis/tags/v1.1",
-        "https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-exmaralda/tags/v1.1",
-        "https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-solr/tags/v1.1",
-        "https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-relannis/tags/v1.1",
-        "http://www.lrec-conf.org/proceedings/lrec2014/summaries/606.html",
-        "http://hdl.handle.net/20.500.12124/5"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Blaschitz, Verena",
-        "Wisniewski, Katrin",
-        "Vodi\u010dkov\u00e1, Kate\u0159ina",
-        "Pe\u010den\u00fd, Pavel",
-        "Klein, Gudrun",
-        "Hana, Jirka",
-        "Krivanek, Julia",
-        "Lyding, Verena",
-        "Abel, Andrea",
-        "Plassmann, Sybille",
-        "Lauppe, Louise",
-        "Vettori, Chiara",
-        "Nicolas, Lionel",
-        "\u0160tindlov\u00e1, Barbora",
-        "Woldt, Claudia",
-        "Bykh, Serhiy",
-        "Meurers, Detmar",
-        "\u010curdov\u00e1, Veronika",
-        "Sch\u00f6ne, Karin",
-        "Boyd, Adriane"
-    ],
-    "fulltext": "oai:clarin.eurac.edu:20.500.12124/6;2018-09-04T09:26:59Z;hdl_20.500.12124_1;hdl_20.500.12124_4;MERLIN Written Learner Corpus for Czech, German, Italian 1.1;Wisniewski, Katrin;Abel, Andrea;Vodi\u010dkov\u00e1, Kate\u0159ina;Plassmann, Sybille;Meurers, Detmar;Woldt, Claudia;Sch\u00f6ne, Karin;Blaschitz, Verena;Lyding, Verena;Nicolas, Lionel;Vettori, Chiara;Pe\u010den\u00fd, Pavel;Hana, Jirka;\u010curdov\u00e1, Veronika;\u0160tindlov\u00e1, Barbora;Klein, Gudrun;Lauppe, Louise;Boyd, Adriane;Bykh, Serhiy;Krivanek, Julia;CEFR;language learning;learner corpus;The MERLIN corpus is a written learner corpus for Czech, German, and Italian that has been designed to illustrate the Common European Framework of Reference for Languages (CEFR) with authentic learner data. The corpus contains learner texts produced in standardized language certifications covering CEFR levels A1-C1. The MERLIN annotation scheme includes a wide range of language characteristics that provide researchers with concrete examples of learner performance and progress across multiple proficiency levels.;2018-08-24;corpus;http://hdl.handle.net/20.500.12124/6;ces;deu;ita;info:eu-repo/grantAgreement/EC/FP7/200250;https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-docs/tags/v1.1;https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-text/tags/v1.1;https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-metadata/tags/v1.1;https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-tasks/tags/v1.1;https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-paula/tags/v1.1;https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-annis/tags/v1.1;https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-exmaralda/tags/v1.1;https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-solr/tags/v1.1;https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-relannis/tags/v1.1;http://www.lrec-conf.org/proceedings/lrec2014/summaries/606.html;http://hdl.handle.net/20.500.12124/5;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;PUB;text/html;text/html;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 10;Institute for Applied Linguistics, Eurac Research;https://merlin-platform.eu",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "21a5e4b2-f547-52a3-b879-07f2dc179bd4",
-    "notes": [
-        "The MERLIN corpus is a written learner corpus for Czech, German, and Italian that has been designed to illustrate the Common European Framework of Reference for Languages (CEFR) with authentic learner data. The corpus contains learner texts produced in standardized language certifications covering CEFR levels A1-C1. The MERLIN annotation scheme includes a wide range of language characteristics that provide researchers with concrete examples of learner performance and progress across multiple proficiency levels."
-    ],
-    "oai_identifier": [
-        "oai:clarin.eurac.edu:20.500.12124/6"
-    ],
-    "oai_set": [
-        "hdl_20.500.12124_1",
-        "hdl_20.500.12124_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "CEFR"
-        },
-        {
-            "name": "language learning"
-        },
-        {
-            "name": "learner corpus"
-        }
-    ],
-    "title": [
-        "MERLIN Written Learner Corpus for Czech, German, Italian 1.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/21b94c4b-c542-5707-8198-a316295b75de.json b/oaitestdata/clarin-oai_dc/SET_1/json/21b94c4b-c542-5707-8198-a316295b75de.json
deleted file mode 100644
index 6906e5de..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/21b94c4b-c542-5707-8198-a316295b75de.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-58",
-    "MetadataAccess": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-58"
-    ],
-    "PID": "http://hdl.handle.net/20.500.11752/ILC-58",
-    "PublicationTimestamp": "2016-09-26T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "author": [
-        "D'\u00c1vila, Teresa di Ges\u00f9"
-    ],
-    "fulltext": "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-58;2018-07-23T09:13:43Z;hdl_000-c0-111_38;hdl_000-c0-111_49;Corpus delle Opere di S.Teresa de \u00c1vila;D'\u00c1vila, Teresa di Ges\u00f9;Fede;Teologia;Religione;Il corpus \u00e8 costituito dalla raccolta delle seguenti opere, fra parentesi la sigla del testo usata nel riferimento: \r\nLIBRO DE LA VIDA (VIDA), \r\nCAMINO DE PERFECCION (CAM), \r\nLAS FUNDACIONES (FUN), \r\nCARTAS (CAR), \r\nEL CASTILLO INTERIOR (MOR), \r\nCONCEPTOS (CONC), \r\nRELACIONES (RELA), \r\nEXCLAMACIONES (EXCL), \r\nCONSTITUCIONES (CONS), \r\nMODO DE VISITAR LOS CONVENTOS (MODO), \r\nPOESIAS (POES), \r\nAPUNTES (APUN).\r\n\r\nL\u2019archivio testuale (con le relative annotazioni linguistiche) \u00e8 stato prodotto negli anni \u201980-'90. Questo progetto di ricerca, promosso dal prof. Guido Mancini con i fondi del 40%-60%, \u00e8 frutto della collaborazione tra l'Universit\u00e0 di Pisa, di Torino con il prof. Ruffinatto e l'ILC-CNR di Pisa. \r\nPer quanto riguarda le fonti, si precisa che nel caso delle Cartas, l'edizione di riferimento si basa sul testo curato da Tom\u00e1s Alvarez e Simeon de la S. Familia, ed. Monte Carmelo, Burgos, 1981; il riferimento al testo viene indicato con il numero della lettera, seguito dal paragrafo e dalla riga. Per le altre opere \u00e8 stato utilizzato il testo curato da Tom\u00e1s de la Cruz, Teresa de Jes\u00fas, Obras Completas, ed. Monte Carmelo, Burgos, 1977. Nel riferimento viene posta la sigla del titolo dell'opera, seguita dall'eventuale numero del capitolo, del paragrafo e della riga all'interno del paragrafo.;2016-09-26;corpus;http://hdl.handle.net/20.500.11752/ILC-58;spa;downloadable_files_count: 0;Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "21b94c4b-c542-5707-8198-a316295b75de",
-    "notes": [
-        "Il corpus \u00e8 costituito dalla raccolta delle seguenti opere, fra parentesi la sigla del testo usata nel riferimento: \r\nLIBRO DE LA VIDA (VIDA), \r\nCAMINO DE PERFECCION (CAM), \r\nLAS FUNDACIONES (FUN), \r\nCARTAS (CAR), \r\nEL CASTILLO INTERIOR (MOR), \r\nCONCEPTOS (CONC), \r\nRELACIONES (RELA), \r\nEXCLAMACIONES (EXCL), \r\nCONSTITUCIONES (CONS), \r\nMODO DE VISITAR LOS CONVENTOS (MODO), \r\nPOESIAS (POES), \r\nAPUNTES (APUN).\r\n\r\nL\u2019archivio testuale (con le relative annotazioni linguistiche) \u00e8 stato prodotto negli anni \u201980-'90. Questo progetto di ricerca, promosso dal prof. Guido Mancini con i fondi del 40%-60%, \u00e8 frutto della collaborazione tra l'Universit\u00e0 di Pisa, di Torino con il prof. Ruffinatto e l'ILC-CNR di Pisa. \r\nPer quanto riguarda le fonti, si precisa che nel caso delle Cartas, l'edizione di riferimento si basa sul testo curato da Tom\u00e1s Alvarez e Simeon de la S. Familia, ed. Monte Carmelo, Burgos, 1981; il riferimento al testo viene indicato con il numero della lettera, seguito dal paragrafo e dalla riga. Per le altre opere \u00e8 stato utilizzato il testo curato da Tom\u00e1s de la Cruz, Teresa de Jes\u00fas, Obras Completas, ed. Monte Carmelo, Burgos, 1977. Nel riferimento viene posta la sigla del titolo dell'opera, seguita dall'eventuale numero del capitolo, del paragrafo e della riga all'interno del paragrafo."
-    ],
-    "oai_identifier": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-58"
-    ],
-    "oai_set": [
-        "hdl_000-c0-111_38",
-        "hdl_000-c0-111_49"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Fede"
-        },
-        {
-            "name": "Teologia"
-        },
-        {
-            "name": "Religione"
-        }
-    ],
-    "title": [
-        "Corpus delle Opere di S.Teresa de \u00c1vila"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/21cfed79-8aba-57d2-87de-823e745ec089.json b/oaitestdata/clarin-oai_dc/SET_1/json/21cfed79-8aba-57d2-87de-823e745ec089.json
deleted file mode 100644
index ab28513c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/21cfed79-8aba-57d2-87de-823e745ec089.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Humboldt-Universit\u00e4t zu Berlin"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1022",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1022"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1022",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Humboldt-Universit\u00e4t zu Berlin"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1022;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Ridges - Register in Diachronic German Science;Germanistik;Possibility to download the Ridges herbology corpus as a whole or parts of it; M\u00f6glichkeit zum Download des Ridges Herbology-Korpus als Ganzes oder einzelner Teildokumente;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1022;deu;downloadable_files_count: 0;Germany;Humboldt-Universit\u00e4t zu Berlin;http://korpling.german.hu-berlin.de/ridges/index_de.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "21cfed79-8aba-57d2-87de-823e745ec089",
-    "notes": [
-        "Possibility to download the Ridges herbology corpus as a whole or parts of it; M\u00f6glichkeit zum Download des Ridges Herbology-Korpus als Ganzes oder einzelner Teildokumente"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1022"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Ridges - Register in Diachronic German Science"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/21d52a89-6180-5837-9b7c-3d53ffb5bbe3.json b/oaitestdata/clarin-oai_dc/SET_1/json/21d52a89-6180-5837-9b7c-3d53ffb5bbe3.json
deleted file mode 100644
index 6e9546c3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/21d52a89-6180-5837-9b7c-3d53ffb5bbe3.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4280",
-    "MetadataAccess": [
-        "oai:ota:oucs:4280"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hill, Aaron, 1685-1750."
-    ],
-    "fulltext": "oai:ota:oucs:4280;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4280.xml;Gideon; or, the patriot. An epic poem: in twelve books. Upon a Hebrew plan. In honour of the two chief virtues of a people; intrepidity in foreign war: and spirit of domestic liberty. With miscellaneous notes, and large reflections,;Hill, Aaron, 1685-1750.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "21d52a89-6180-5837-9b7c-3d53ffb5bbe3",
-    "oai_identifier": [
-        "oai:ota:oucs:4280"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Gideon; or, the patriot. An epic poem: in twelve books. Upon a Hebrew plan. In honour of the two chief virtues of a people; intrepidity in foreign war: and spirit of domestic liberty. With miscellaneous notes, and large reflections,"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4280.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/21ec5ec7-ebc8-5296-b476-98714ce7d796.json b/oaitestdata/clarin-oai_dc/SET_1/json/21ec5ec7-ebc8-5296-b476-98714ce7d796.json
deleted file mode 100644
index 06f30ffc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/21ec5ec7-ebc8-5296-b476-98714ce7d796.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "Contributor": [
-        "Gardellini, Mariano"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1164",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1164"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1164",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1164;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Access rights Management System;Gardellini, Mariano;A tool to grant and deny the access to (parts of) an IMDI-based corpus. Support for advanced settings like ACLs.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1164;downloadable_files_count: 0;Netherlands (the);Max Planck Institute for Psycholinguistics;http://tla.mpi.nl/tools/tla-tools/ams/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "21ec5ec7-ebc8-5296-b476-98714ce7d796",
-    "notes": [
-        "A tool to grant and deny the access to (parts of) an IMDI-based corpus. Support for advanced settings like ACLs."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1164"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Access rights Management System"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/221854ed-5c5f-5c4b-9659-d4095414d340.json b/oaitestdata/clarin-oai_dc/SET_1/json/221854ed-5c5f-5c4b-9659-d4095414d340.json
deleted file mode 100644
index 4914c0ec..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/221854ed-5c5f-5c4b-9659-d4095414d340.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 34 KB)"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0268",
-    "MetadataAccess": [
-        "oai:ota:oucs:0268"
-    ],
-    "PublicationYear": [
-        "150-180"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Sermons"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Melito, Saint, Bishop of Sardis, 2nd cent."
-    ],
-    "fulltext": "oai:ota:oucs:0268;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0268.xml;Selections / Meliton;Melito, Saint, Bishop of Sardis, 2nd cent.;150-180;text_and_corpus_linguistics;Sermons -- Greek -- 2nd Century;grc;Oxford Text Archive, University of Oxford;(1 file : ca. 34 KB);Text;Sermons;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "221854ed-5c5f-5c4b-9659-d4095414d340",
-    "oai_identifier": [
-        "oai:ota:oucs:0268"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Sermons -- Greek -- nd Century"
-        }
-    ],
-    "title": [
-        "Selections / Meliton"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0268.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2232bfbb-eaaa-544c-9dd5-4e284c47f7be.json b/oaitestdata/clarin-oai_dc/SET_1/json/2232bfbb-eaaa-544c-9dd5-4e284c47f7be.json
deleted file mode 100644
index 015f224f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2232bfbb-eaaa-544c-9dd5-4e284c47f7be.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3918",
-    "MetadataAccess": [
-        "oai:ota:oucs:3918"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Kames, Henry Home, Lord, 1696-1782."
-    ],
-    "fulltext": "oai:ota:oucs:3918;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3918.xml;Elements of criticism: In three volumes. ... [pt.3];Kames, Henry Home, Lord, 1696-1782.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2232bfbb-eaaa-544c-9dd5-4e284c47f7be",
-    "oai_identifier": [
-        "oai:ota:oucs:3918"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Elements of criticism: In three volumes. ... [pt.3]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3918.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2238e103-62b8-5bac-9e61-183d0d188266.json b/oaitestdata/clarin-oai_dc/SET_1/json/2238e103-62b8-5bac-9e61-183d0d188266.json
deleted file mode 100644
index 327c9829..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2238e103-62b8-5bac-9e61-183d0d188266.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2623",
-    "MetadataAccess": [
-        "oai:ota:oucs:2623"
-    ],
-    "PublicationTimestamp": "1711-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1711"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2623;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2623.xml;The sentiments of a Church of England man;Swift, Jonathan, 1667-1745;1711;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2238e103-62b8-5bac-9e61-183d0d188266",
-    "oai_identifier": [
-        "oai:ota:oucs:2623"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The sentiments of a Church of England man"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2623.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/223d8362-445a-5e05-ad37-03b93acab903.json b/oaitestdata/clarin-oai_dc/SET_1/json/223d8362-445a-5e05-ad37-03b93acab903.json
deleted file mode 100644
index 0fb2bf25..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/223d8362-445a-5e05-ad37-03b93acab903.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3087",
-    "MetadataAccess": [
-        "oai:ota:oucs:3087"
-    ],
-    "PublicationTimestamp": "1858-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1858"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Eliot, George, 1819-1880"
-    ],
-    "fulltext": "oai:ota:oucs:3087;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3087.xml;The sad fortunes of the Reverend Amos Barton;Eliot, George, 1819-1880;not after: 1858;text_and_corpus_linguistics;Fiction -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "223d8362-445a-5e05-ad37-03b93acab903",
-    "oai_identifier": [
-        "oai:ota:oucs:3087"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "The sad fortunes of the Reverend Amos Barton"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3087.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2244f4bd-a547-5adc-a78e-93cef765094b.json b/oaitestdata/clarin-oai_dc/SET_1/json/2244f4bd-a547-5adc-a78e-93cef765094b.json
deleted file mode 100644
index ae12f2ac..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2244f4bd-a547-5adc-a78e-93cef765094b.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3413",
-    "MetadataAccess": [
-        "oai:ota:oucs:3413"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dibdin, Charles, 1745-1814."
-    ],
-    "fulltext": "oai:ota:oucs:3413;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3413.xml;Proposals for publishing by subscription, dedicated, with permission, to the most noble the Marquis of Salisbury, A complete history of the English stage ... The whole written, with the asistance of interesting documents, collected in the course of five and thirty years, by Mr. Dibdin;Complete history of the English stage.;Dibdin, Charles, 1745-1814.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2244f4bd-a547-5adc-a78e-93cef765094b",
-    "oai_identifier": [
-        "oai:ota:oucs:3413"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Proposals for publishing by subscription, dedicated, with permission, to the most noble the Marquis of Salisbury, A complete history of the English stage ... The whole written, with the asistance of interesting documents, collected in the course of five and thirty years, by Mr. Dibdin",
-        "Complete history of the English stage."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3413.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/22752b6a-b76e-51f0-9124-082d770c1101.json b/oaitestdata/clarin-oai_dc/SET_1/json/22752b6a-b76e-51f0-9124-082d770c1101.json
deleted file mode 100644
index ee283212..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/22752b6a-b76e-51f0-9124-082d770c1101.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Krzysztofa Schedla"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-159981",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-159981"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CE6-0",
-    "PublicationTimestamp": "1674-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1674"
-    ],
-    "Publisher": [
-        "Drukarnia Krzysztofa Schedla"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/159981",
-        "oai:jbc.bj.uj.edu.pl:publication:168324"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1601/1700"
-    ],
-    "TempCoverageBegin": 50506804799,
-    "TempCoverageEnd": 50506804799,
-    "TemporalCoverage": " point in time : 1601-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1601-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1601-07-01T11:59:59Z",
-    "author": [
-        "Leszczy\u0144ski, Samuel (1637-1676)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-159981;2019-02-28T18:41:43Z;Classicvm Niesmiertelney S\u0142awy, Jasnie Wielmoznych Wodzow Koronnych, Y Wielkiego Xi\u0119st: Litewskiego [...] : Po \u00dfcz\u0119\u015bliwey y nies\u0142ychaney Victoriey Pod Hocimiem [sic!], Dnia XI. Nouembra, Roku Pa\u0144skiego 1673. otrzymaney; Stylo Panegyrico, a Oyczystym Rytme[m] Opisane, Roku Pa\u0144skiego. 1674. Dnia 20. Marca.;Leszczy\u0144ski, Samuel (1637-1676);starodruki 17\u00a0w.;Jan III Sobieski (kr\u00f3l Polski ; 1629-1696). [Adr. ded.];Drukarnia Krzysztofa Schedla;1674;starodruk;application/xml;clarind-uds:poldilemma-159981;hdl:11858/00-246C-0000-0023-8CE6-0;Biblioteka Jagiello\u0144ska, BJ St. Dr. 923 I;pol;lat;http://jbc.bj.uj.edu.pl/Content/159981;oai:jbc.bj.uj.edu.pl:publication:168324;1601/1700;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "22752b6a-b76e-51f0-9124-082d770c1101",
-    "notes": [
-        "Jan III Sobieski (kr\u00f3l Polski ; 1629-1696). [Adr. ded.]"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-159981"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Classicvm Niesmiertelney S\u0142awy, Jasnie Wielmoznych Wodzow Koronnych, Y Wielkiego Xi\u0119st: Litewskiego [...] : Po \u00dfcz\u0119\u015bliwey y nies\u0142ychaney Victoriey Pod Hocimiem [sic!], Dnia XI. Nouembra, Roku Pa\u0144skiego 1673. otrzymaney; Stylo Panegyrico, a Oyczystym Rytme[m] Opisane, Roku Pa\u0144skiego. 1674. Dnia 20. Marca."
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/227f16f3-3089-5f30-8dd8-7e2e087c4a49.json b/oaitestdata/clarin-oai_dc/SET_1/json/227f16f3-3089-5f30-8dd8-7e2e087c4a49.json
deleted file mode 100644
index c1778702..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/227f16f3-3089-5f30-8dd8-7e2e087c4a49.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/21",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/21"
-    ],
-    "PID": "http://hdl.handle.net/10794/21",
-    "PublicationTimestamp": "2012-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/21;2017-10-27T15:32:06Z;hdl_10794_1;hdl_10794_2;Dalin Dictionary - Base Material (2017-10-16);Dalin Ordbok \u00d6fver Svenska Spr\u00e5ket - basmaterial (2017-10-16);n/a, n/a;Swedish;Dictionary;Dalin's Dictionary of 19th century Swedish - base material.;Dalins ordbok - Ordbok \u00f6ver 1800-talsspr\u00e5ket, basmaterial.;2012-05-30;lexicalConceptualResource;http://hdl.handle.net/10794/21;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/dalin-base",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "227f16f3-3089-5f30-8dd8-7e2e087c4a49",
-    "notes": [
-        "Dalin's Dictionary of 19th century Swedish - base material.",
-        "Dalins ordbok - Ordbok \u00f6ver 1800-talsspr\u00e5ket, basmaterial."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/21"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Dictionary"
-        }
-    ],
-    "title": [
-        "Dalin Dictionary - Base Material (2017-10-16)",
-        "Dalin Ordbok \u00d6fver Svenska Spr\u00e5ket - basmaterial (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/229d39d1-ef5f-5771-b8b0-1faf8f9904f2.json b/oaitestdata/clarin-oai_dc/SET_1/json/229d39d1-ef5f-5771-b8b0-1faf8f9904f2.json
deleted file mode 100644
index 9a540722..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/229d39d1-ef5f-5771-b8b0-1faf8f9904f2.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4827",
-    "MetadataAccess": [
-        "oai:ota:oucs:4827"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gilpin, William, 1724-1804."
-    ],
-    "fulltext": "oai:ota:oucs:4827;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4827.xml;Observations on the River Wye: and several parts of South Wales, &c. relative chiefly to picturesque beauty; made in the summer of the year 1770, second edition, by William Gilpin, ...;Gilpin, William, 1724-1804.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "229d39d1-ef5f-5771-b8b0-1faf8f9904f2",
-    "oai_identifier": [
-        "oai:ota:oucs:4827"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Observations on the River Wye: and several parts of South Wales, &c. relative chiefly to picturesque beauty; made in the summer of the year 1770, second edition, by William Gilpin, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4827.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/22a722dd-9666-5534-9f47-442efce181ae.json b/oaitestdata/clarin-oai_dc/SET_1/json/22a722dd-9666-5534-9f47-442efce181ae.json
deleted file mode 100644
index 805ba289..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/22a722dd-9666-5534-9f47-442efce181ae.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4212",
-    "MetadataAccess": [
-        "oai:ota:oucs:4212"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Cugoano, Ottobah."
-    ],
-    "fulltext": "oai:ota:oucs:4212;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4212.xml;Thoughts and sentiments on the evil and wicked traffic of the slavery: and commerce of the human species, humbly submitted to the inhabitants of Great-Britain, by Ottobah Cugoano, ...;Cugoano, Ottobah.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "22a722dd-9666-5534-9f47-442efce181ae",
-    "oai_identifier": [
-        "oai:ota:oucs:4212"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Thoughts and sentiments on the evil and wicked traffic of the slavery: and commerce of the human species, humbly submitted to the inhabitants of Great-Britain, by Ottobah Cugoano, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4212.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/22b1c36f-5f59-555b-b0ec-e24c6d470152.json b/oaitestdata/clarin-oai_dc/SET_1/json/22b1c36f-5f59-555b-b0ec-e24c6d470152.json
deleted file mode 100644
index f6e34547..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/22b1c36f-5f59-555b-b0ec-e24c6d470152.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Fern\u00c3\u00a1ndez-Corugedo, S. G. (Santiago Gonz\u00c3\u00a1lez)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "3 files, c. 102 KB"
-    ],
-    "Language": [
-        "Middle English (1100-1500)",
-        "English",
-        "Hebrew"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1398",
-    "MetadataAccess": [
-        "oai:ota:oucs:1398"
-    ],
-    "PublicationTimestamp": "1100-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1100"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Anthologies",
-        "Linguistic corpora"
-    ],
-    "Rights": [
-        "Available for non-commercial use on condition that the terms of the BNC Licence are observed and that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:1398;2018-05-08T14:08:14Z;http://ota.ox.ac.uk/headers/1398.xml;Anthology of Middle English texts / Santiago Gonzalez y Fernandez-Corugedo;1100-1400;text_and_corpus_linguistics;English literature -- Middle English, 1100-1500;enm;eng;heb;Oxford Text Archive, University of Oxford;Fern\u00c3\u00a1ndez-Corugedo, S. G. (Santiago Gonz\u00c3\u00a1lez);Fern\u00c3\u00a1ndez-Corugedo, S. G. (Santiago Gonz\u00c3\u00a1lez);3 files, c. 102 KB;Text;Anthologies;Linguistic corpora;Available for non-commercial use on condition that the terms of the BNC Licence are observed and that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "22b1c36f-5f59-555b-b0ec-e24c6d470152",
-    "oai_identifier": [
-        "oai:ota:oucs:1398"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English literature -- Middle English"
-        }
-    ],
-    "title": [
-        "Anthology of Middle English texts / Santiago Gonzalez y Fernandez-Corugedo"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1398.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/22cb7ddf-00c5-5ef9-b508-562f2a9cd3d7.json b/oaitestdata/clarin-oai_dc/SET_1/json/22cb7ddf-00c5-5ef9-b508-562f2a9cd3d7.json
deleted file mode 100644
index 2d448436..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/22cb7ddf-00c5-5ef9-b508-562f2a9cd3d7.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1138",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1138"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1138",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1138;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;documentArchiv.de / Historische Dokumenten- und Quellensammlung zur deutschen Geschichte ab 1800;Germanistik;Documents on German history (e.g. German Empire; Weimar Republic; National Socialism; Federal Republic of Germany; German Democratic Republic); Dokumente zur deutschen Geschichte (z.B. Deutsches Kaiserreich; Weimarer Republik; Nationalsozialismus; Bundesrepublik Deutschland; Deutsche Demokratische Republik);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1138;deu;downloadable_files_count: 0;Germany;http://www.documentarchiv.de/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "22cb7ddf-00c5-5ef9-b508-562f2a9cd3d7",
-    "notes": [
-        "Documents on German history (e.g. German Empire; Weimar Republic; National Socialism; Federal Republic of Germany; German Democratic Republic); Dokumente zur deutschen Geschichte (z.B. Deutsches Kaiserreich; Weimarer Republik; Nationalsozialismus; Bundesrepublik Deutschland; Deutsche Demokratische Republik)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1138"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "documentArchiv.de / Historische Dokumenten- und Quellensammlung zur deutschen Geschichte ab 1800"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/22eb629a-98b1-58d1-8a8f-76a1f249da4d.json b/oaitestdata/clarin-oai_dc/SET_1/json/22eb629a-98b1-58d1-8a8f-76a1f249da4d.json
deleted file mode 100644
index f8ec59a2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/22eb629a-98b1-58d1-8a8f-76a1f249da4d.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=f843c67a492311e2a2aa782bcb07413511cf382137004b7f8961efc791d9586a",
-    "MetadataAccess": [
-        "f843c67a492311e2a2aa782bcb07413511cf382137004b7f8961efc791d9586a"
-    ],
-    "PublicationTimestamp": "2013-01-21T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "f843c67a492311e2a2aa782bcb07413511cf382137004b7f8961efc791d9586a;2018-11-15T16:39:59Z;corpus;corpus:text;Spoken Corpus Mozambique ;The Spoken Corpus Mozambique contains approximately 121,958 running words of spoken Portuguese from Mozambique. It includes 40 transcriptions of spoken recordings (in a total of 40 hours of recordings) that were recorded between 1986 and 1987.;2013-01-21",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "22eb629a-98b1-58d1-8a8f-76a1f249da4d",
-    "notes": [
-        "The Spoken Corpus Mozambique contains approximately 121,958 running words of spoken Portuguese from Mozambique. It includes 40 transcriptions of spoken recordings (in a total of 40 hours of recordings) that were recorded between 1986 and 1987."
-    ],
-    "oai_identifier": [
-        "f843c67a492311e2a2aa782bcb07413511cf382137004b7f8961efc791d9586a"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "Spoken Corpus Mozambique "
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/23028c21-5814-53e8-a62c-c77cf1127904.json b/oaitestdata/clarin-oai_dc/SET_1/json/23028c21-5814-53e8-a62c-c77cf1127904.json
deleted file mode 100644
index 1f508d6b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/23028c21-5814-53e8-a62c-c77cf1127904.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=0cbb1cd82d8211e2a2aa782bcb074135cf096a63d7aa4b34b65db9e6255d0d39",
-    "MetadataAccess": [
-        "0cbb1cd82d8211e2a2aa782bcb074135cf096a63d7aa4b34b65db9e6255d0d39"
-    ],
-    "PublicationTimestamp": "2012-11-13T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "fulltext": "0cbb1cd82d8211e2a2aa782bcb074135cf096a63d7aa4b34b65db9e6255d0d39;2018-11-15T16:39:48Z;corpus;corpus:text;CINTIL-QATreeBank;CINTIL-QATreebank is a treebank composed of Portuguese sentences that can be used to support the development of Question Answering systems. This Treebank includes 111 declarative sentences from the pre-existing CINTIL-Treebank (see Branco et al. 2011) whose syntactic structure was manually transformed into their non-declarative counterpart: interrogative and imperative clauses.\n\nThe non-declarative sentences are annotated with several layers of linguistic information, namely (i) trees with information on constituency and grammatical function; (ii) sentence type; (iii) interrogative pronoun; (iv) question type; and (v) semantic type of expected answer. Moreover, these non-declarative sentences are paired with their declarative counterparts and associated with the expected answer snippets.\n;2012-11-13",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "23028c21-5814-53e8-a62c-c77cf1127904",
-    "notes": [
-        "CINTIL-QATreebank is a treebank composed of Portuguese sentences that can be used to support the development of Question Answering systems. This Treebank includes 111 declarative sentences from the pre-existing CINTIL-Treebank (see Branco et al. 2011) whose syntactic structure was manually transformed into their non-declarative counterpart: interrogative and imperative clauses.\n\nThe non-declarative sentences are annotated with several layers of linguistic information, namely (i) trees with information on constituency and grammatical function; (ii) sentence type; (iii) interrogative pronoun; (iv) question type; and (v) semantic type of expected answer. Moreover, these non-declarative sentences are paired with their declarative counterparts and associated with the expected answer snippets.\n"
-    ],
-    "oai_identifier": [
-        "0cbb1cd82d8211e2a2aa782bcb074135cf096a63d7aa4b34b65db9e6255d0d39"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "CINTIL-QATreeBank"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2304a24f-7013-5534-ac7b-680ed942726c.json b/oaitestdata/clarin-oai_dc/SET_1/json/2304a24f-7013-5534-ac7b-680ed942726c.json
deleted file mode 100644
index 9643ec50..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2304a24f-7013-5534-ac7b-680ed942726c.json
+++ /dev/null
@@ -1,108 +0,0 @@
-{
-    "Contact": [
-        "Charles University"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "application/pdf",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-162",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-162"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-162",
-    "PublicationTimestamp": "2014-07-27T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11858/00-097C-0000-0023-95B1-E"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0)",
-        "http://creativecommons.org/licenses/by-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Jane\u0161, Petr",
-        "\u0160tindlov\u00e1, Barbora",
-        "Rosen, Alexandr",
-        "Hrdli\u010dka, Milan",
-        "\u0160ormov\u00e1, Kate\u0159ina",
-        "Toufarov\u00e1, Dagmar",
-        "Pol\u00e1\u010dkov\u00e1, Marie",
-        "Richter, Michal",
-        "Hrdli\u010dkov\u00e1, Tereza",
-        "\u0160ebesta, Karel",
-        "Pierscieniak, Piotr",
-        "Lund\u00e1kov\u00e1, Kate\u0159ina",
-        "Bed\u0159ichov\u00e1, Zuzanna",
-        "Hana, Ji\u0159\u00ed",
-        "Jel\u00ednek, Tom\u00e1\u0161",
-        "\u0160kodov\u00e1, Svatava",
-        "Skoumalov\u00e1, Hana",
-        "Straka, Milan",
-        "Sl\u00e1dek, \u0160imon",
-        "Petkevi\u010d, Vladim\u00edr"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-162;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;AKCES 5 (CzeSL-SGT) Release 2;\u0160ebesta, Karel;Bed\u0159ichov\u00e1, Zuzanna;\u0160ormov\u00e1, Kate\u0159ina;\u0160tindlov\u00e1, Barbora;Hrdli\u010dka, Milan;Hrdli\u010dkov\u00e1, Tereza;Hana, Ji\u0159\u00ed;Petkevi\u010d, Vladim\u00edr;Jel\u00ednek, Tom\u00e1\u0161;\u0160kodov\u00e1, Svatava;Pol\u00e1\u010dkov\u00e1, Marie;Jane\u0161, Petr;Lund\u00e1kov\u00e1, Kate\u0159ina;Skoumalov\u00e1, Hana;Sl\u00e1dek, \u0160imon;Pierscieniak, Piotr;Toufarov\u00e1, Dagmar;Richter, Michal;Straka, Milan;Rosen, Alexandr;learner corpus;Czech as a foreign language;Czech language acquisition corpora;AKCES;non-native speakers;second language acquistion;Essays written by non-native learners of Czech, a part of AKCES/CLAC \u2013 Czech Language Acquisition Corpora. CzeSL-SGT stands for Czech as a Second Language with Spelling, Grammar and Tags. Extends the \u201cforeign\u201d (ciz) part of AKCES 3 (CzeSL-plain) by texts collected in 2013. Original forms and automatic corrections are tagged, lemmatized and assigned erros labels. Most texts have metadata attributes (30 items) about the author and the text.\r\nIn addition to a few minor bugs, fixes a critical issue in Release 1: the native speakers of Ukrainian (s_L1:\"uk\") were wrongly labelled as speakers of \"other European languages\" (s_L1_group=\"IE\"),  instead of speakers of a Slavic language (s_L1_group=\"S\"). The file is now a regular XML document, with all annotation represented as XML attributes.;2014-07-27;corpus;http://hdl.handle.net/11234/1-162;ces;http://hdl.handle.net/11858/00-097C-0000-0023-95B1-E;Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0);http://creativecommons.org/licenses/by-sa/3.0/;PUB;application/zip;application/pdf;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University;http://utkl.ff.cuni.cz/learncorp/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2304a24f-7013-5534-ac7b-680ed942726c",
-    "notes": [
-        "Essays written by non-native learners of Czech, a part of AKCES/CLAC \u2013 Czech Language Acquisition Corpora. CzeSL-SGT stands for Czech as a Second Language with Spelling, Grammar and Tags. Extends the \u201cforeign\u201d (ciz) part of AKCES 3 (CzeSL-plain) by texts collected in 2013. Original forms and automatic corrections are tagged, lemmatized and assigned erros labels. Most texts have metadata attributes (30 items) about the author and the text.\r\nIn addition to a few minor bugs, fixes a critical issue in Release 1: the native speakers of Ukrainian (s_L1:\"uk\") were wrongly labelled as speakers of \"other European languages\" (s_L1_group=\"IE\"),  instead of speakers of a Slavic language (s_L1_group=\"S\"). The file is now a regular XML document, with all annotation represented as XML attributes."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-162"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "learner corpus"
-        },
-        {
-            "name": "Czech foreign language"
-        },
-        {
-            "name": "Czech language acquisition corpora"
-        },
-        {
-            "name": "AKCES"
-        },
-        {
-            "name": "non-native speakers"
-        },
-        {
-            "name": "second language acquistion"
-        }
-    ],
-    "title": [
-        "AKCES 5 (CzeSL-SGT) Release 2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/230f4a64-970b-57bf-8fdc-61ef0827c273.json b/oaitestdata/clarin-oai_dc/SET_1/json/230f4a64-970b-57bf-8fdc-61ef0827c273.json
deleted file mode 100644
index ce35a5f9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/230f4a64-970b-57bf-8fdc-61ef0827c273.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3592",
-    "MetadataAccess": [
-        "oai:ota:oucs:3592"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gay, John, 1685-1732."
-    ],
-    "fulltext": "oai:ota:oucs:3592;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3592.xml;Achilles: An opera. As it is perform'd at the Theatre-Royal in Covent-Garden. Written by the late Mr. Gay. With the musick prefix'd to each song.;Gay, John, 1685-1732.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "230f4a64-970b-57bf-8fdc-61ef0827c273",
-    "oai_identifier": [
-        "oai:ota:oucs:3592"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Achilles: An opera. As it is perform'd at the Theatre-Royal in Covent-Garden. Written by the late Mr. Gay. With the musick prefix'd to each song."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3592.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/232139a3-9fa0-5d45-b48d-b4d39f74bc19.json b/oaitestdata/clarin-oai_dc/SET_1/json/232139a3-9fa0-5d45-b48d-b4d39f74bc19.json
deleted file mode 100644
index 0a97b2b6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/232139a3-9fa0-5d45-b48d-b4d39f74bc19.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=d2fb3020059811e7a2aa782bcb074135753d376d9bf34dbf88cb4a6e416a2322",
-    "MetadataAccess": [
-        "d2fb3020059811e7a2aa782bcb074135753d376d9bf34dbf88cb4a6e416a2322"
-    ],
-    "PublicationTimestamp": "2017-03-10T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "fulltext": "d2fb3020059811e7a2aa782bcb074135753d376d9bf34dbf88cb4a6e416a2322;2018-11-15T16:40:32Z;toolService;toolService:tool;English to Dutch Machine translation module;Technical Description:\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/Pilot1_technical_description.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/TechnicalDescriptionPilot2_D2.7.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2016/11/TechnicalDescriptionPilot3_D2.10.pdf;2017-03-10",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "232139a3-9fa0-5d45-b48d-b4d39f74bc19",
-    "notes": [
-        "Technical Description:\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/Pilot1_technical_description.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/TechnicalDescriptionPilot2_D2.7.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2016/11/TechnicalDescriptionPilot3_D2.10.pdf"
-    ],
-    "oai_identifier": [
-        "d2fb3020059811e7a2aa782bcb074135753d376d9bf34dbf88cb4a6e416a2322"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "English to Dutch Machine translation module"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/233a0ebc-40e5-5a2d-b8db-6f8985c1bd7e.json b/oaitestdata/clarin-oai_dc/SET_1/json/233a0ebc-40e5-5a2d-b8db-6f8985c1bd7e.json
deleted file mode 100644
index 2521bfe7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/233a0ebc-40e5-5a2d-b8db-6f8985c1bd7e.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-915",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-915"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-915",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-915;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Parthian;ca. 200.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-915;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#parth",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "233a0ebc-40e5-5a2d-b8db-6f8985c1bd7e",
-    "notes": [
-        "ca. 200.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-915"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Parthian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/234d1206-6944-5e4f-8162-5767b23d7a47.json b/oaitestdata/clarin-oai_dc/SET_1/json/234d1206-6944-5e4f-8162-5767b23d7a47.json
deleted file mode 100644
index 8f215238..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/234d1206-6944-5e4f-8162-5767b23d7a47.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "University of Sheffield"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 4"
-    ],
-    "Language": [
-        "English",
-        "German",
-        "Czech",
-        "Latvian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2619",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2619"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2619",
-    "PublicationTimestamp": "2018-02-19T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "University of Sheffield"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/H2020/645452",
-        "http://hdl.handle.net/11372/LRT-1974"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "AGREEMENT ON THE USE OF DATA IN QT21",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21",
-        "PUB"
-    ],
-    "author": [
-        "Fernandez, Ramon",
-        "Martins, Andr\u00e9",
-        "Logacheva, Varvara",
-        "Specia, Lucia",
-        "Blain, Frederic"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2619;2018-05-21T15:04:37Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;WMT18 Quality Estimation Shared Task Training and Development Data;Specia, Lucia;Logacheva, Varvara;Blain, Frederic;Fernandez, Ramon;Martins, Andr\u00e9;machine translation;quality estimation;machine learning;Training and development data for the WMT18 QE task. Test data will be published as a separate item.\r\n\r\nThis shared task will build on its previous six editions to further examine automatic methods for estimating the quality of machine translation output at run-time, without relying on reference translations. We include word-level, phrase-level and sentence-level estimation. All tasks make use of datasets produced from post-editions by professional translators. The datasets are domain-specific (IT and life sciences/pharma domains) and extend from those used previous years with more instances and more languages. One important addition is that this year we also include datasets with neural MT outputs. In addition to advancing the state of the art at all prediction levels, our specific goals are:\r\n\r\nTo study the performance of quality estimation approaches on the output of neural MT systems. We will do so by providing datasets for two language language pairs where the same source segments are translated by both a statistical phrase-based and a neural MT system.\r\n\r\nTo study the predictability of deleted words, i.e. words that are missing in the MT output. TO do so, for the first time we provide data annotated for such errors at training time.\r\n\r\nTo study the effectiveness of explicitly assigned labels for phrases. We will do so by providing a dataset where each phrase in the output of a phrase-based statistical MT system was annotated by human translators.\r\nTo study the effect of different language pairs. We will do so by providing datasets created in similar ways for four language language pairs.\r\n\r\nTo investigate the utility of detailed information logged during post-editing. We will do so by providing post-editing time, keystrokes, and actual edits.\r\n\r\nMeasure progress over years at all prediction levels. We will do so by using last year's test set for comparative experiments.\r\n\r\nIn-house statistical and neural MT systems were built to produce translations for all tasks. MT system-dependent information can be made available under request. The data is publicly available but since it has been provided by our industry partners it is subject to specific terms and conditions. However, these have no practical implications on the use of this data for research purposes. Participants are allowed to explore any additional data and resources deemed relevant.;2018-02-19;corpus;http://hdl.handle.net/11372/LRT-2619;eng;deu;ces;lav;info:eu-repo/grantAgreement/EC/H2020/645452;http://hdl.handle.net/11372/LRT-1974;AGREEMENT ON THE USE OF DATA IN QT21;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21;PUB;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 4;University of Sheffield;http://www.statmt.org/wmt18/quality-estimation-task.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "234d1206-6944-5e4f-8162-5767b23d7a47",
-    "notes": [
-        "Training and development data for the WMT18 QE task. Test data will be published as a separate item.\r\n\r\nThis shared task will build on its previous six editions to further examine automatic methods for estimating the quality of machine translation output at run-time, without relying on reference translations. We include word-level, phrase-level and sentence-level estimation. All tasks make use of datasets produced from post-editions by professional translators. The datasets are domain-specific (IT and life sciences/pharma domains) and extend from those used previous years with more instances and more languages. One important addition is that this year we also include datasets with neural MT outputs. In addition to advancing the state of the art at all prediction levels, our specific goals are:\r\n\r\nTo study the performance of quality estimation approaches on the output of neural MT systems. We will do so by providing datasets for two language language pairs where the same source segments are translated by both a statistical phrase-based and a neural MT system.\r\n\r\nTo study the predictability of deleted words, i.e. words that are missing in the MT output. TO do so, for the first time we provide data annotated for such errors at training time.\r\n\r\nTo study the effectiveness of explicitly assigned labels for phrases. We will do so by providing a dataset where each phrase in the output of a phrase-based statistical MT system was annotated by human translators.\r\nTo study the effect of different language pairs. We will do so by providing datasets created in similar ways for four language language pairs.\r\n\r\nTo investigate the utility of detailed information logged during post-editing. We will do so by providing post-editing time, keystrokes, and actual edits.\r\n\r\nMeasure progress over years at all prediction levels. We will do so by using last year's test set for comparative experiments.\r\n\r\nIn-house statistical and neural MT systems were built to produce translations for all tasks. MT system-dependent information can be made available under request. The data is publicly available but since it has been provided by our industry partners it is subject to specific terms and conditions. However, these have no practical implications on the use of this data for research purposes. Participants are allowed to explore any additional data and resources deemed relevant."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2619"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "quality estimation"
-        },
-        {
-            "name": "machine learning"
-        }
-    ],
-    "title": [
-        "WMT18 Quality Estimation Shared Task Training and Development Data"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/235a72e9-fe2c-5f99-8c94-d325b18fa6c7.json b/oaitestdata/clarin-oai_dc/SET_1/json/235a72e9-fe2c-5f99-8c94-d325b18fa6c7.json
deleted file mode 100644
index e2ff6454..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/235a72e9-fe2c-5f99-8c94-d325b18fa6c7.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contributor": [
-        "Simov, Kiril"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Bulgarian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-175",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-175"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-175",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-175;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;BulTreeBank Text Archive;Simov, Kiril;72 000 000 tokens, 15% fiction, 78% newspapers and 7% legal texts, government bulletins and others;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-175;bul;downloadable_files_count: 0;http://www.clarin.eu",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "235a72e9-fe2c-5f99-8c94-d325b18fa6c7",
-    "notes": [
-        "72 000 000 tokens, 15% fiction, 78% newspapers and 7% legal texts, government bulletins and others"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-175"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "BulTreeBank Text Archive"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2373be12-d46a-5260-bc48-8fe4c6a95ed1.json b/oaitestdata/clarin-oai_dc/SET_1/json/2373be12-d46a-5260-bc48-8fe4c6a95ed1.json
deleted file mode 100644
index 3b4e3868..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2373be12-d46a-5260-bc48-8fe4c6a95ed1.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "ClarinPL"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 34",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/60",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/60"
-    ],
-    "PID": "http://hdl.handle.net/11321/60",
-    "PublicationTimestamp": "2015-04-07T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "ClarinPL"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Prus, Boles\u0142aw Prus"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/60;2015-06-18T10:54:05Z;hdl_11321_3;hdl_11321_4;Faraon;Prus, Boles\u0142aw Prus;Faraon;2015-04-07;corpus;http://hdl.handle.net/11321/60;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 34;ClarinPL",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2373be12-d46a-5260-bc48-8fe4c6a95ed1",
-    "notes": [
-        "Faraon"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/60"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Faraon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2383f059-37d9-5543-9d23-233549bd8b7f.json b/oaitestdata/clarin-oai_dc/SET_1/json/2383f059-37d9-5543-9d23-233549bd8b7f.json
deleted file mode 100644
index ffc995e0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2383f059-37d9-5543-9d23-233549bd8b7f.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Marek Lukasik"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 3",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/157",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/157"
-    ],
-    "PID": "http://hdl.handle.net/11321/157",
-    "PublicationTimestamp": "2015-04-14T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Marek Lukasik"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Lukasik, Marek"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/157;2015-04-14T12:58:08Z;hdl_11321_3;hdl_11321_4;Astro-corp;Lukasik, Marek;Astronomia.;2015-04-14;corpus;http://hdl.handle.net/11321/157;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;text/plain; charset=utf-8;downloadable_files_count: 3;Marek Lukasik",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2383f059-37d9-5543-9d23-233549bd8b7f",
-    "notes": [
-        "Astronomia."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/157"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Astro-corp"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2389eb32-1023-5ddb-83f6-fef1312ca2e5.json b/oaitestdata/clarin-oai_dc/SET_1/json/2389eb32-1023-5ddb-83f6-fef1312ca2e5.json
deleted file mode 100644
index 74101b78..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2389eb32-1023-5ddb-83f6-fef1312ca2e5.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3122",
-    "MetadataAccess": [
-        "oai:ota:oucs:3122"
-    ],
-    "PublicationTimestamp": "1880-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1880"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "James, William, 1842-1910"
-    ],
-    "fulltext": "oai:ota:oucs:3122;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3122.xml;Great men and their environment;James, William, 1842-1910;not after: 1880;text_and_corpus_linguistics;Periodicals -- United States -- 19th century;Essays -- United States -- 19th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2389eb32-1023-5ddb-83f6-fef1312ca2e5",
-    "oai_identifier": [
-        "oai:ota:oucs:3122"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Periodicals -- United States -- th century"
-        },
-        {
-            "name": "Essays -- United States -- th century"
-        }
-    ],
-    "title": [
-        "Great men and their environment"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3122.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/23c17fa0-5f03-5950-90d1-d50d82490b40.json b/oaitestdata/clarin-oai_dc/SET_1/json/23c17fa0-5f03-5950-90d1-d50d82490b40.json
deleted file mode 100644
index 7a4cc3e4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/23c17fa0-5f03-5950-90d1-d50d82490b40.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=b1c1a89a0b6611e5a2aa782bcb074135dca9d493ea3845a488aec73eb281e73b",
-    "MetadataAccess": [
-        "b1c1a89a0b6611e5a2aa782bcb074135dca9d493ea3845a488aec73eb281e73b"
-    ],
-    "PublicationTimestamp": "2015-06-05T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "b1c1a89a0b6611e5a2aa782bcb074135dca9d493ea3845a488aec73eb281e73b;2018-11-15T16:40:16Z;toolService;toolService:tool;ixa-pipe-coref-eu;ixa-pipe-coref-eu is a Basque coreference resolution tool, which is an adaptation of Stanford Deterministic Coreference Resolution (http://www-nlp.stanford.edu/downloads/dcoref.shtml).\n\nThis tool reads a text document annotated with lemmas, named entities and constituents formated in Natural Language Processing Annotation Format (NAF) (http://wordpress.let.vupr.nl/naf/) and outputs a new NAF document.\n\nThis tool is partly funded by the European Commission project QTLeap FP7-ICT-2013.4.1-610516 (http://qtleap.eu). This tool is distributed under the license GPL v3.0.;2015-06-05",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "23c17fa0-5f03-5950-90d1-d50d82490b40",
-    "notes": [
-        "ixa-pipe-coref-eu is a Basque coreference resolution tool, which is an adaptation of Stanford Deterministic Coreference Resolution (http://www-nlp.stanford.edu/downloads/dcoref.shtml).\n\nThis tool reads a text document annotated with lemmas, named entities and constituents formated in Natural Language Processing Annotation Format (NAF) (http://wordpress.let.vupr.nl/naf/) and outputs a new NAF document.\n\nThis tool is partly funded by the European Commission project QTLeap FP7-ICT-2013.4.1-610516 (http://qtleap.eu). This tool is distributed under the license GPL v3.0."
-    ],
-    "oai_identifier": [
-        "b1c1a89a0b6611e5a2aa782bcb074135dca9d493ea3845a488aec73eb281e73b"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "ixa-pipe-coref-eu"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/23de06d8-f635-53c7-88c7-2c19e9e6478f.json b/oaitestdata/clarin-oai_dc/SET_1/json/23de06d8-f635-53c7-88c7-2c19e9e6478f.json
deleted file mode 100644
index c77f483f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/23de06d8-f635-53c7-88c7-2c19e9e6478f.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Portuguese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-395",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-395"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-395",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-395;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Europarl: European Parliament Proceedings Parallel Corpus 1996-2003;Parallel corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-395;por;downloadable_files_count: 0;United Kingdom;http://www.statmt.org/europarl/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "23de06d8-f635-53c7-88c7-2c19e9e6478f",
-    "notes": [
-        "Parallel corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-395"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Europarl: European Parliament Proceedings Parallel Corpus 1996-2003"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2400846d-ba42-5b5c-9b33-73effcbf85cd.json b/oaitestdata/clarin-oai_dc/SET_1/json/2400846d-ba42-5b5c-9b33-73effcbf85cd.json
deleted file mode 100644
index 3788186a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2400846d-ba42-5b5c-9b33-73effcbf85cd.json
+++ /dev/null
@@ -1,100 +0,0 @@
-{
-    "Contact": [
-        "Institut f\u00fcr Phonetik, Universit\u00e4t des Saarlandes"
-    ],
-    "Contributor": [
-        "Tamara Hausmann",
-        "Anja Moos",
-        "Olga Trifsik",
-        "William J. Barry",
-        "Manfred Just",
-        "Rossella Caradonna",
-        "Markus Walz",
-        "Christian Dressler",
-        "Attilio Erriquez",
-        "Manfred P\u00fctzer",
-        "Bogdan Woldert-Jokisz",
-        "Slavomir Tengowski",
-        "Silke Jarmut"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "audio/x-wav",
-        "audio/x-egg",
-        "application/x-nsp",
-        "text/plain"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:saarbrueckerstimmdatenbank",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:saarbrueckerstimmdatenbank"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0005-BD12-3",
-    "PublicationTimestamp": "2004-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2004"
-    ],
-    "Publisher": [
-        "Institut f\u00fcr Phonetik, Universit\u00e4t des Saarlandes"
-    ],
-    "ResourceType": [
-        "Collection"
-    ],
-    "Rights": [
-        "Copyrighted"
-    ],
-    "SpatialCoverage": [
-        "Germany",
-        "1997/2004"
-    ],
-    "TemporalCoverage": " period : ( None - 1997-07-01T11:59:59Z ) ",
-    "author": [
-        "Database of healthy and pathological voices / Voice profiles DFG BA 737/9-6",
-        "Institut f\u00fcr Phonetik, Universit\u00e4t des Saarlandes"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:saarbrueckerstimmdatenbank;2014-06-03T12:55:04Z;Saarbr\u00fccker Stimmdatenbank;Institut f\u00fcr Phonetik, Universit\u00e4t des Saarlandes;Database of healthy and pathological voices / Voice profiles DFG BA 737/9-6;voice database;healthy voice profile;pathological voice profile;acoustic signal;electroglottographic signal;The Saarbr\u00fccker Stimmdatenbank is a collection of voice recordings from more than 2000 persons. Recordings are classified according to healthy and pathological voice profiles on the basis of the acoustic and electroglottographic signals. \n    The speech signal and the EGG signal have been stored in separate files. Any comments about the recordings are contained in an associated text-file. \n    The material can be queried through a web search interface, and the selecte audio files can be exported.;Die Saarbr\u00fccker Stimmdatenbank ist eine Sammlung von Sprachaufnahmen von \u00fcber 2000 Personen. Die Aufnahmen wurden anhand der akustischen und elektroglottographischen Signale klassifiziert in gesunde und pathologische Sprachprofile. \n    Das Sprachsignal und das EGG Signal sind in separaten Dateien gespeichert. Eventuelle Kommentare sind in einer Textdatei gespeichert. \n    Die Datenbank kann \u00fcber ein Webinterface abgefragt werden, ausgew\u00e4hlte Audiodateien k\u00f6nnen exportiert werden.;Institut f\u00fcr Phonetik, Universit\u00e4t des Saarlandes;Bogdan Woldert-Jokisz;William J. Barry;Manfred P\u00fctzer;Manfred Just;Rossella Caradonna;Christian Dressler;Attilio Erriquez;Tamara Hausmann;Silke Jarmut;Anja Moos;Slavomir Tengowski;Olga Trifsik;Markus Walz;Bogdan Woldert-Jokisz;2004;Collection;text/plain;application/x-nsp;audio/x-egg;audio/x-wav;clarind-uds:saarbrueckerstimmdatenbank;hdl:11858/00-246C-0000-0005-BD12-3;deu;Germany;1997/2004;Copyrighted",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2400846d-ba42-5b5c-9b33-73effcbf85cd",
-    "notes": [
-        "The Saarbr\u00fccker Stimmdatenbank is a collection of voice recordings from more than 2000 persons. Recordings are classified according to healthy and pathological voice profiles on the basis of the acoustic and electroglottographic signals. \n    The speech signal and the EGG signal have been stored in separate files. Any comments about the recordings are contained in an associated text-file. \n    The material can be queried through a web search interface, and the selecte audio files can be exported.",
-        "Die Saarbr\u00fccker Stimmdatenbank ist eine Sammlung von Sprachaufnahmen von \u00fcber 2000 Personen. Die Aufnahmen wurden anhand der akustischen und elektroglottographischen Signale klassifiziert in gesunde und pathologische Sprachprofile. \n    Das Sprachsignal und das EGG Signal sind in separaten Dateien gespeichert. Eventuelle Kommentare sind in einer Textdatei gespeichert. \n    Die Datenbank kann \u00fcber ein Webinterface abgefragt werden, ausgew\u00e4hlte Audiodateien k\u00f6nnen exportiert werden."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:saarbrueckerstimmdatenbank"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "voice database"
-        },
-        {
-            "name": "healthy voice profile"
-        },
-        {
-            "name": "pathological voice profile"
-        },
-        {
-            "name": "acoustic signal"
-        },
-        {
-            "name": "electroglottographic signal"
-        }
-    ],
-    "title": [
-        "Saarbr\u00fccker Stimmdatenbank"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/243dc2c4-a212-5719-9d92-36c5f80d4bbc.json b/oaitestdata/clarin-oai_dc/SET_1/json/243dc2c4-a212-5719-9d92-36c5f80d4bbc.json
deleted file mode 100644
index 30676361..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/243dc2c4-a212-5719-9d92-36c5f80d4bbc.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=f6648890616e11e2a2aa782bcb0741352f715f1d899d4a769d1729f097c1b215",
-    "MetadataAccess": [
-        "f6648890616e11e2a2aa782bcb0741352f715f1d899d4a769d1729f097c1b215"
-    ],
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "f6648890616e11e2a2aa782bcb0741352f715f1d899d4a769d1729f097c1b215;2018-11-15T16:40:04Z;corpus;corpus:text;DependencyBankPT;The DepBankPT (Branco et al., 2011a) is a corpus of grammatical dependencies of the translated news composed of 3,406 sentences and 44,598 tokens taken from the Wall Street Journal.\nThe DepBankPT is aligned to a constituency bank, the TreeBankPT (see Branco et al., 2011b). The key bridging elements are the grammatical function tags decoring the nodes, in the treebank, and the arcs, in the dependencybank (see http://lxcenter.di.fc.ul.pt/services/en/LXServicesSearcher.html). This means that the DepBankPT was extended from the PropBank PT so that besides the tags for the different dependency relations, the arcs are further decorated with tags indicating the semantic relation at stake.\nThe main motivation behind the creation of this resource was to build a high quality data set with dependency information that could support the development of a large set of automatic resources and tools for Portuguese for NLP studies.\nThe development of this resource started under the METANET4U project (at: http://metanet4u.eu/) whose main goal is to contribute to the establishment of a pan-European digital platform that makes available language resources and services, encompassing both datasets and software tools, for speech and language processing, and supports a new generation of exchange facilities for them. \n;2015-12-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "243dc2c4-a212-5719-9d92-36c5f80d4bbc",
-    "notes": [
-        "The DepBankPT (Branco et al., 2011a) is a corpus of grammatical dependencies of the translated news composed of 3,406 sentences and 44,598 tokens taken from the Wall Street Journal.\nThe DepBankPT is aligned to a constituency bank, the TreeBankPT (see Branco et al., 2011b). The key bridging elements are the grammatical function tags decoring the nodes, in the treebank, and the arcs, in the dependencybank (see http://lxcenter.di.fc.ul.pt/services/en/LXServicesSearcher.html). This means that the DepBankPT was extended from the PropBank PT so that besides the tags for the different dependency relations, the arcs are further decorated with tags indicating the semantic relation at stake.\nThe main motivation behind the creation of this resource was to build a high quality data set with dependency information that could support the development of a large set of automatic resources and tools for Portuguese for NLP studies.\nThe development of this resource started under the METANET4U project (at: http://metanet4u.eu/) whose main goal is to contribute to the establishment of a pan-European digital platform that makes available language resources and services, encompassing both datasets and software tools, for speech and language processing, and supports a new generation of exchange facilities for them. \n"
-    ],
-    "oai_identifier": [
-        "f6648890616e11e2a2aa782bcb0741352f715f1d899d4a769d1729f097c1b215"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "DependencyBankPT"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2489987a-d952-5063-ab27-f15603a41281.json b/oaitestdata/clarin-oai_dc/SET_1/json/2489987a-d952-5063-ab27-f15603a41281.json
deleted file mode 100644
index 0cf5bc9c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2489987a-d952-5063-ab27-f15603a41281.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(3 files : ca. 4.75, 467, 576 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0650",
-    "MetadataAccess": [
-        "oai:ota:oucs:0650"
-    ],
-    "PublicationTimestamp": "1722-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1722"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Scores"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Bach, Johann Sebastian, 1685-1750"
-    ],
-    "fulltext": "oai:ota:oucs:0650;2018-02-28T11:54:31Z;http://ota.ox.ac.uk/headers/0650.xml;Wohltemperierte Klavier, 1. T. English. Selections;Wohltemperierte Klavier, 2. T. English. Selections;Well-tempered clavier preludes and fugues : volume I and volume II [excerpts];Bach, Johann Sebastian, 1685-1750;1722-1742;text_and_corpus_linguistics;Musical works -- Germany -- 18th century;Scores -- Germany -- 18th century;eng;Oxford Text Archive, University of Oxford;text/plain;(3 files : ca. 4.75, 467, 576 KB);Text;Scores;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2489987a-d952-5063-ab27-f15603a41281",
-    "oai_identifier": [
-        "oai:ota:oucs:0650"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Musical works -- Germany -- th century"
-        },
-        {
-            "name": "Scores -- Germany -- th century"
-        }
-    ],
-    "title": [
-        "Wohltemperierte Klavier, 1. T. English. Selections",
-        "Wohltemperierte Klavier, 2. T. English. Selections",
-        "Well-tempered clavier preludes and fugues : volume I and volume II [excerpts]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0650.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2494fe3f-48c3-50a3-98b3-bca5ad5c3e84.json b/oaitestdata/clarin-oai_dc/SET_1/json/2494fe3f-48c3-50a3-98b3-bca5ad5c3e84.json
deleted file mode 100644
index 87e3e414..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2494fe3f-48c3-50a3-98b3-bca5ad5c3e84.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/50",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/50"
-    ],
-    "PID": "http://hdl.handle.net/10794/50",
-    "PublicationTimestamp": "2013-02-08T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/50;2017-10-27T16:54:41Z;hdl_10794_1;hdl_10794_2;Academic texts \u2013 Social science 1997\u20132012 (2017-10-16);Academic texts \u2013 Samh\u00e4llsvetenskap 1997\u20132012 (2017-10-16);n/a, n/a;Swedish;Academic texts;Social sciences;A corpus with academic texts in Social sciences from 1997\u20132012. The material is sentence scrambled.;En korpus med akademiska texter fr\u00e5n samh\u00e4llsvetenskap 1997\u20132012. Materialet \u00e4r meningsomkastat.;2013-02-08;corpus;http://hdl.handle.net/10794/50;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/sweacsam",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2494fe3f-48c3-50a3-98b3-bca5ad5c3e84",
-    "notes": [
-        "A corpus with academic texts in Social sciences from 1997\u20132012. The material is sentence scrambled.",
-        "En korpus med akademiska texter fr\u00e5n samh\u00e4llsvetenskap 1997\u20132012. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/50"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Academic texts"
-        },
-        {
-            "name": "Social sciences"
-        }
-    ],
-    "title": [
-        "Academic texts \u2013 Social science 1997\u20132012 (2017-10-16)",
-        "Academic texts \u2013 Samh\u00e4llsvetenskap 1997\u20132012 (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/24a5169d-6e85-5336-bb23-c2f3ce89ea70.json b/oaitestdata/clarin-oai_dc/SET_1/json/24a5169d-6e85-5336-bb23-c2f3ce89ea70.json
deleted file mode 100644
index 6eec521f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/24a5169d-6e85-5336-bb23-c2f3ce89ea70.json
+++ /dev/null
@@ -1,40 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=12fdc090a35e11e1a404080027e73ea2c200dc17aff642fe980ba7a2da7f5ca1",
-    "MetadataAccess": [
-        "12fdc090a35e11e1a404080027e73ea2c200dc17aff642fe980ba7a2da7f5ca1"
-    ],
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "12fdc090a35e11e1a404080027e73ea2c200dc17aff642fe980ba7a2da7f5ca1;2019-02-27T12:09:04Z;corpus;corpus:text;corpus:audio;corpus:text:audio;Spoken Portuguese - Geographical and Social Varieties;This resource includes a spoken Portuguese corpus exemplifying the Portuguese spoken in Portugal, Brazil, Angola, Cape Verde, Guinea-Bissau, Mozambique, Sao Tome and Principe, Macao, Goa and East-Timor - with aligned sound and orthographic transcription - collected among sociolinguistically diverse speakers. It consists of recordings from informal conversations, conferences and media.;2015-12-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "24a5169d-6e85-5336-bb23-c2f3ce89ea70",
-    "notes": [
-        "This resource includes a spoken Portuguese corpus exemplifying the Portuguese spoken in Portugal, Brazil, Angola, Cape Verde, Guinea-Bissau, Mozambique, Sao Tome and Principe, Macao, Goa and East-Timor - with aligned sound and orthographic transcription - collected among sociolinguistically diverse speakers. It consists of recordings from informal conversations, conferences and media."
-    ],
-    "oai_identifier": [
-        "12fdc090a35e11e1a404080027e73ea2c200dc17aff642fe980ba7a2da7f5ca1"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text",
-        "corpus:audio",
-        "corpus:text:audio"
-    ],
-    "state": "active",
-    "title": [
-        "Spoken Portuguese - Geographical and Social Varieties"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/24a95345-5c61-5263-b6f1-0b986c1c384d.json b/oaitestdata/clarin-oai_dc/SET_1/json/24a95345-5c61-5263-b6f1-0b986c1c384d.json
deleted file mode 100644
index b02692db..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/24a95345-5c61-5263-b6f1-0b986c1c384d.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4555",
-    "MetadataAccess": [
-        "oai:ota:oucs:4555"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Defoe, Daniel, 1661?-1731."
-    ],
-    "fulltext": "oai:ota:oucs:4555;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4555.xml;The family instructor: In two parts. I. Relating to family breaches, and their obstructing religious duties. II. To the great mistake of mixing the passions, in the managing and correcting of children. ... Vol.II. [pt.2];Family instructor.;Defoe, Daniel, 1661?-1731.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "24a95345-5c61-5263-b6f1-0b986c1c384d",
-    "oai_identifier": [
-        "oai:ota:oucs:4555"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The family instructor: In two parts. I. Relating to family breaches, and their obstructing religious duties. II. To the great mistake of mixing the passions, in the managing and correcting of children. ... Vol.II. [pt.2]",
-        "Family instructor."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4555.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/24bc072c-182d-5aaa-83e8-80ab69445c26.json b/oaitestdata/clarin-oai_dc/SET_1/json/24bc072c-182d-5aaa-83e8-80ab69445c26.json
deleted file mode 100644
index 75582bb8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/24bc072c-182d-5aaa-83e8-80ab69445c26.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "between 512 KB and 1 MB "
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0657",
-    "MetadataAccess": [
-        "oai:ota:oucs:0657"
-    ],
-    "PublicationTimestamp": "1870-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1870"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Mystery and detective fiction"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dickens, Charles, 1812-1870"
-    ],
-    "fulltext": "oai:ota:oucs:0657;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0657.xml;The mystery of Edwin Drood  / compiled by J. Aldridge;Dickens, Charles, 1812-1870;1870;text_and_corpus_linguistics;Mystery and detective fiction -- England -- 19th century;eng;Oxford Text Archive, University of Oxford;between 512 KB and 1 MB ;Text;Mystery and detective fiction;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "24bc072c-182d-5aaa-83e8-80ab69445c26",
-    "oai_identifier": [
-        "oai:ota:oucs:0657"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The mystery of Edwin Drood  / compiled by J. Aldridge"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0657.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/24bce759-564c-510a-9a1c-a43ce73e13ae.json b/oaitestdata/clarin-oai_dc/SET_1/json/24bce759-564c-510a-9a1c-a43ce73e13ae.json
deleted file mode 100644
index 51d4ad35..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/24bce759-564c-510a-9a1c-a43ce73e13ae.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1969",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1969"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1969",
-    "PublicationTimestamp": "2017-02-20T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Public Domain Mark (PD)",
-        "http://creativecommons.org/publicdomain/mark/1.0/",
-        "PUB"
-    ],
-    "author": [
-        "Baran\u010d\u00edkov\u00e1, Petra",
-        "Kettnerov\u00e1, V\u00e1clava"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1969;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;ParaDi: Dictionary of Paraphrases of Czech Complex Predicates with Light Verbs;Baran\u010d\u00edkov\u00e1, Petra;Kettnerov\u00e1, V\u00e1clava;light verb construction;paraphrases;Dictionary of single verb paraphrases of Czech light verb constructions.;2017-02-20;lexicalConceptualResource;http://hdl.handle.net/11234/1-1969;ces;Public Domain Mark (PD);http://creativecommons.org/publicdomain/mark/1.0/;PUB;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "24bce759-564c-510a-9a1c-a43ce73e13ae",
-    "notes": [
-        "Dictionary of single verb paraphrases of Czech light verb constructions."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1969"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "light verb construction"
-        },
-        {
-            "name": "paraphrases"
-        }
-    ],
-    "title": [
-        "ParaDi: Dictionary of Paraphrases of Czech Complex Predicates with Light Verbs"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/24d55c43-9122-50e0-b450-79ec37e7ef5c.json b/oaitestdata/clarin-oai_dc/SET_1/json/24d55c43-9122-50e0-b450-79ec37e7ef5c.json
deleted file mode 100644
index ce0daedd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/24d55c43-9122-50e0-b450-79ec37e7ef5c.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5086",
-    "MetadataAccess": [
-        "oai:ota:oucs:5086"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pratt, Mr. (Samuel Jackson), 1749-1814."
-    ],
-    "fulltext": "oai:ota:oucs:5086;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5086.xml;The pupil of pleasure: or, the new system illustrated. Inscribed to Mrs. Eugenia Stanhope, editor of Lord Chesterfield's letters. By Courtney Melmoth. ... [pt.2];Pratt, Mr. (Samuel Jackson), 1749-1814.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "24d55c43-9122-50e0-b450-79ec37e7ef5c",
-    "oai_identifier": [
-        "oai:ota:oucs:5086"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The pupil of pleasure: or, the new system illustrated. Inscribed to Mrs. Eugenia Stanhope, editor of Lord Chesterfield's letters. By Courtney Melmoth. ... [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5086.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/24d5d24d-c718-5b22-a967-a25a964cca56.json b/oaitestdata/clarin-oai_dc/SET_1/json/24d5d24d-c718-5b22-a967-a25a964cca56.json
deleted file mode 100644
index 8157691c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/24d5d24d-c718-5b22-a967-a25a964cca56.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "Contributor": [
-        "Tropf, Herbert"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Czech",
-        "Hungarian",
-        "Polish",
-        "Russian",
-        "Slovak"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-599",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-599"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-599",
-    "PublicationTimestamp": "2000-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-599;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;SpeechDat-East databases;Tropf, Herbert;These databases serve as an important resource for the performance of voice driven teleservice systems in practical implementations;5 telephone databases recorded over the PSTN. Contains interesting phonetically rich material. All orthographically transcribed. Speaker information included for gender, age, accent. Including pronunciation lexicon.;2000;corpus;http://hdl.handle.net/11372/LRT-599;ces;hun;pol;rus;slk;downloadable_files_count: 0;http://www.fee.vutbr.cz/SPEECHDAT-E/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "24d5d24d-c718-5b22-a967-a25a964cca56",
-    "notes": [
-        "5 telephone databases recorded over the PSTN. Contains interesting phonetically rich material. All orthographically transcribed. Speaker information included for gender, age, accent. Including pronunciation lexicon."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-599"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [],
-    "title": [
-        "SpeechDat-East databases"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/24ec5c56-8462-50b6-8c8b-a27e2ec80418.json b/oaitestdata/clarin-oai_dc/SET_1/json/24ec5c56-8462-50b6-8c8b-a27e2ec80418.json
deleted file mode 100644
index f7d42b78..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/24ec5c56-8462-50b6-8c8b-a27e2ec80418.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/13",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/13"
-    ],
-    "PID": "http://hdl.handle.net/10794/13",
-    "PublicationTimestamp": "2015-12-09T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/13;2017-10-27T15:59:11Z;hdl_10794_1;hdl_10794_2;Bliss characters (2017-10-16);Bliss-bokst\u00e4ver (2017-10-16);n/a, n/a;Swedish;Bliss;Bliss characters.;Bliss-bokst\u00e4ver.;2015-12-09;lexicalConceptualResource;http://hdl.handle.net/10794/13;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/blisschar",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "24ec5c56-8462-50b6-8c8b-a27e2ec80418",
-    "notes": [
-        "Bliss characters.",
-        "Bliss-bokst\u00e4ver."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/13"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Bliss"
-        }
-    ],
-    "title": [
-        "Bliss characters (2017-10-16)",
-        "Bliss-bokst\u00e4ver (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/24fb4a00-d080-5cbb-aff1-62e32ec482cc.json b/oaitestdata/clarin-oai_dc/SET_1/json/24fb4a00-d080-5cbb-aff1-62e32ec482cc.json
deleted file mode 100644
index 524e105b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/24fb4a00-d080-5cbb-aff1-62e32ec482cc.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5249",
-    "MetadataAccess": [
-        "oai:ota:oucs:5249"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Holcroft, Thomas, 1745-1809."
-    ],
-    "fulltext": "oai:ota:oucs:5249;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5249.xml;Anna St. Ives: a novel. By Thomas Holcroft. ... [pt.1];Holcroft, Thomas, 1745-1809.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "24fb4a00-d080-5cbb-aff1-62e32ec482cc",
-    "oai_identifier": [
-        "oai:ota:oucs:5249"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Anna St. Ives: a novel. By Thomas Holcroft. ... [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5249.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/24fe1c12-ae31-5503-86b7-7efa193a75f7.json b/oaitestdata/clarin-oai_dc/SET_1/json/24fe1c12-ae31-5503-86b7-7efa193a75f7.json
deleted file mode 100644
index c745554b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/24fe1c12-ae31-5503-86b7-7efa193a75f7.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Institute of Mathematics and Computer Science, University of Latvia"
-    ],
-    "Contributor": [
-        "Gr\u016bz\u012btis, Normunds",
-        "B\u0101rzdi\u0146\u0161, Guntis"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Latvian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-300",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-300"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-300",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institute of Mathematics and Computer Science, University of Latvia"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Latvia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-300;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;A simplified front-end for SemTi-Kamols morphological analyser;Gr\u016bz\u012btis, Normunds;B\u0101rzdi\u0146\u0161, Guntis;morphological analyzer;A simplified front-end (in a form of a RESTful web service) of the SemTi-Kamols morphological analyzer. Mainly for demonstration purposes.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-300;lav;downloadable_files_count: 0;Latvia;Institute of Mathematics and Computer Science, University of Latvia;http://eksperimenti.ailab.lv/kamols/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "24fe1c12-ae31-5503-86b7-7efa193a75f7",
-    "notes": [
-        "A simplified front-end (in a form of a RESTful web service) of the SemTi-Kamols morphological analyzer. Mainly for demonstration purposes."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-300"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphological analyzer"
-        }
-    ],
-    "title": [
-        "A simplified front-end for SemTi-Kamols morphological analyser"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/24fe3490-17ad-591e-baa0-bba9456b4767.json b/oaitestdata/clarin-oai_dc/SET_1/json/24fe3490-17ad-591e-baa0-bba9456b4767.json
deleted file mode 100644
index 579e8b46..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/24fe3490-17ad-591e-baa0-bba9456b4767.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5295",
-    "MetadataAccess": [
-        "oai:ota:oucs:5295"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Congreve, William, 1670-1729."
-    ],
-    "fulltext": "oai:ota:oucs:5295;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5295.xml;A letter from Mr. Congreve to the Right Honourable the Lord Viscount Cobham;Congreve, William, 1670-1729.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "24fe3490-17ad-591e-baa0-bba9456b4767",
-    "oai_identifier": [
-        "oai:ota:oucs:5295"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A letter from Mr. Congreve to the Right Honourable the Lord Viscount Cobham"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5295.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2501ce6f-19d2-5178-b89b-766f30318524.json b/oaitestdata/clarin-oai_dc/SET_1/json/2501ce6f-19d2-5178-b89b-766f30318524.json
deleted file mode 100644
index 35ff438e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2501ce6f-19d2-5178-b89b-766f30318524.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Universitas"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/411",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/411"
-    ],
-    "PID": "http://hdl.handle.net/11321/411",
-    "PublicationTimestamp": "2017-06-29T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Universitas"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Daniel, Marczuk",
-        "Szabat, Marta"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/411;2017-06-29T07:52:41Z;hdl_11321_3;hdl_11321_4;korpus testowy;Szabat, Marta;Daniel, Marczuk;transkrypcje;korpus tekstowy;KORPUS TESTOWY NA WARSZTATY;2017-06-29;corpus;http://hdl.handle.net/11321/411;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;Universitas",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2501ce6f-19d2-5178-b89b-766f30318524",
-    "notes": [
-        "KORPUS TESTOWY NA WARSZTATY"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/411"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "transkrypcje"
-        },
-        {
-            "name": "korpus tekstowy"
-        }
-    ],
-    "title": [
-        "korpus testowy"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/25033448-4ce0-5900-afa2-2ff364f83eac.json b/oaitestdata/clarin-oai_dc/SET_1/json/25033448-4ce0-5900-afa2-2ff364f83eac.json
deleted file mode 100644
index 5236685a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/25033448-4ce0-5900-afa2-2ff364f83eac.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "The Danish Language Council",
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain",
-        "text/xml",
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 8",
-        "application/zip",
-        "application/pdf"
-    ],
-    "Language": [
-        "Danish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repository.clarin.dk:20.500.12115/17",
-    "MetadataAccess": [
-        "oai:repository.clarin.dk:20.500.12115/17"
-    ],
-    "PID": "http://hdl.handle.net/20.500.12115/17",
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "The Danish Language Council",
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN-ACA-NC",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NC=1&NORED=1",
-        "ACA"
-    ],
-    "author": [
-        "Hansen, Dorte Haltrup",
-        "Braasch, Anna",
-        "Olsen, Sussi",
-        "Jakob, Halskov"
-    ],
-    "fulltext": "oai:repository.clarin.dk:20.500.12115/17;2018-06-28T13:26:10Z;hdl_20.500.12115_1;hdl_20.500.12115_3;DK-CLARIN LSP Corpus - Agriculture domain;Olsen, Sussi;Braasch, Anna;Jakob, Halskov;Hansen, Dorte Haltrup;Agriculture;Texts in the Agriculture domain come from  Danmarks JordbrugsForskning and have been collected in the DK-CLARIN project, WP2.2, 2008 - 2011. \r\nThe corpus consists of 2,376,029 words in 216 files. \r\nCommunicative setting/Number of files: expert->expert (45) expert->advanced (24) expert->basic (142) advanced->basic (5).\r\nAll texts are in XML TEIP5 format (TEIP5DKCLARIN-format), with tokenisation, pos-tagging, sentence and paragraph segmentation, lemmatisation and termhood annotation placed in separate text external spangroups. \r\n\"DK-CLARIN LSP Corpus - Agriculture domain\" is a part of the Danish DK-CLARIN LSP corpus consisting of seven sub-corpora from following subject domains: Agriculture, Construction, Economics, Environment, Health, IT and Nanotechnology.;2011;corpus;http://hdl.handle.net/20.500.12115/17;dan;CLARIN-ACA-NC;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NC=1&NORED=1;ACA;text/plain; charset=utf-8;application/zip;text/plain;application/pdf;application/pdf;application/pdf;text/xml;text/xml;text/xml;downloadable_files_count: 8;Centre for Language Technology, NorS, University of Copenhagen;The Danish Language Council",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "25033448-4ce0-5900-afa2-2ff364f83eac",
-    "notes": [
-        "Texts in the Agriculture domain come from  Danmarks JordbrugsForskning and have been collected in the DK-CLARIN project, WP2.2, 2008 - 2011. \r\nThe corpus consists of 2,376,029 words in 216 files. \r\nCommunicative setting/Number of files: expert->expert (45) expert->advanced (24) expert->basic (142) advanced->basic (5).\r\nAll texts are in XML TEIP5 format (TEIP5DKCLARIN-format), with tokenisation, pos-tagging, sentence and paragraph segmentation, lemmatisation and termhood annotation placed in separate text external spangroups. \r\n\"DK-CLARIN LSP Corpus - Agriculture domain\" is a part of the Danish DK-CLARIN LSP corpus consisting of seven sub-corpora from following subject domains: Agriculture, Construction, Economics, Environment, Health, IT and Nanotechnology."
-    ],
-    "oai_identifier": [
-        "oai:repository.clarin.dk:20.500.12115/17"
-    ],
-    "oai_set": [
-        "hdl_20.500.12115_1",
-        "hdl_20.500.12115_3"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Agriculture"
-        }
-    ],
-    "title": [
-        "DK-CLARIN LSP Corpus - Agriculture domain"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/251d514f-1e96-5d48-8f42-061b85f9288a.json b/oaitestdata/clarin-oai_dc/SET_1/json/251d514f-1e96-5d48-8f42-061b85f9288a.json
deleted file mode 100644
index a273fc75..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/251d514f-1e96-5d48-8f42-061b85f9288a.json
+++ /dev/null
@@ -1,49 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4289",
-    "MetadataAccess": [
-        "oai:ota:oucs:4289"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:4289;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4289.xml;Select Scotish ballads.: [pt.1];text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "251d514f-1e96-5d48-8f42-061b85f9288a",
-    "oai_identifier": [
-        "oai:ota:oucs:4289"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Select Scotish ballads.: [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4289.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/25290be8-e95c-50ba-8944-7834fd42ce1b.json b/oaitestdata/clarin-oai_dc/SET_1/json/25290be8-e95c-50ba-8944-7834fd42ce1b.json
deleted file mode 100644
index 7941f1de..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/25290be8-e95c-50ba-8944-7834fd42ce1b.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "n/a"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/470",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/470"
-    ],
-    "PID": "http://hdl.handle.net/11321/470",
-    "PublicationTimestamp": "2018-05-18T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "n/a"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN-EULA-ACA-v1.0",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca",
-        "ACA"
-    ],
-    "author": [
-        "Kur, Maciej"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/470;2018-05-18T10:54:26Z;hdl_11321_3;hdl_11321_4;Korpus - specyfikacje;Kur, Maciej;construction;n/a;2018-05-18;corpus;http://hdl.handle.net/11321/470;PL;CLARIN-EULA-ACA-v1.0;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca;ACA;text/plain; charset=utf-8;application/msword;application/msword;downloadable_files_count: 2;n/a",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "25290be8-e95c-50ba-8944-7834fd42ce1b",
-    "notes": [
-        "n/a"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/470"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "construction"
-        }
-    ],
-    "title": [
-        "Korpus - specyfikacje"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2532a27a-6343-595d-b9c9-7406039f1a93.json b/oaitestdata/clarin-oai_dc/SET_1/json/2532a27a-6343-595d-b9c9-7406039f1a93.json
deleted file mode 100644
index 0972e5b5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2532a27a-6343-595d-b9c9-7406039f1a93.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "UE w Katoiwcach"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "text/richtext",
-        "downloadable_files_count: 88",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/221",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/221"
-    ],
-    "PID": "http://hdl.handle.net/11321/221",
-    "PublicationTimestamp": "2015-06-22T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "UE w Katoiwcach"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Konieczna, Dorota"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/221;2015-06-24T11:21:50Z;hdl_11321_3;hdl_11321_4;Mining blogs;Konieczna, Dorota;blog;mining;Blogi dotycz\u0105ce g\u00f3rnictwa. Zakres: 01.01.2015 - 20.06.2015. Wpisy wraz z komentarzami.;2015-06-22;corpus;http://hdl.handle.net/11321/221;Polish;Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0);http://creativecommons.org/licenses/by-nc-nd/3.0/;CC;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 88;UE w Katoiwcach;http://www.ue.katowice.pl/no_cache.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2532a27a-6343-595d-b9c9-7406039f1a93",
-    "notes": [
-        "Blogi dotycz\u0105ce g\u00f3rnictwa. Zakres: 01.01.2015 - 20.06.2015. Wpisy wraz z komentarzami."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/221"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "blog"
-        },
-        {
-            "name": "mining"
-        }
-    ],
-    "title": [
-        "Mining blogs"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2578e0d8-9440-5234-b910-61c4fa30411f.json b/oaitestdata/clarin-oai_dc/SET_1/json/2578e0d8-9440-5234-b910-61c4fa30411f.json
deleted file mode 100644
index 1a985ce0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2578e0d8-9440-5234-b910-61c4fa30411f.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Hochschule Augsburg"
-    ],
-    "Contributor": [
-        "Harsch, Prof. em. Ulrich"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1126",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1126"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1126",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Hochschule Augsburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1126;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Bibliotheca Augustana / Bibliotheca Germanica;Harsch, Prof. em. Ulrich;Germanistik;Chronology of German literature (Old High German literature, Middle High German literature, Early New High German literature, New High German literature); Chronologie der deutschen Literatur (alt-, mittel-, fr\u00fchneu-, neuhochdeutsche Literatur);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1126;deu;downloadable_files_count: 0;Germany;Hochschule Augsburg;http://www.hs-augsburg.de/~harsch/germanica/Chronologie/d_chrono.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2578e0d8-9440-5234-b910-61c4fa30411f",
-    "notes": [
-        "Chronology of German literature (Old High German literature, Middle High German literature, Early New High German literature, New High German literature); Chronologie der deutschen Literatur (alt-, mittel-, fr\u00fchneu-, neuhochdeutsche Literatur)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1126"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Bibliotheca Augustana / Bibliotheca Germanica"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/257caf05-d7c5-5cc9-bbfd-ea632e6f0d99.json b/oaitestdata/clarin-oai_dc/SET_1/json/257caf05-d7c5-5cc9-bbfd-ea632e6f0d99.json
deleted file mode 100644
index 52a04fd9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/257caf05-d7c5-5cc9-bbfd-ea632e6f0d99.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=dcdd306c18fd11e6a2aa782bcb0741351c96c57f9ce945b28dd5f347470c5a4d",
-    "MetadataAccess": [
-        "dcdd306c18fd11e6a2aa782bcb0741351c96c57f9ce945b28dd5f347470c5a4d"
-    ],
-    "PublicationTimestamp": "2016-05-13T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "fulltext": "dcdd306c18fd11e6a2aa782bcb0741351c96c57f9ce945b28dd5f347470c5a4d;2018-11-15T16:40:21Z;corpus;corpus:text;Elhuyar-QTLeap WSD/NED corpus;This corpus is created from documents from translation memorios of Elhuyar Fundation (obtained via Eleka, member of the Advisory Board of Potential Users).;2016-05-13",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "257caf05-d7c5-5cc9-bbfd-ea632e6f0d99",
-    "notes": [
-        "This corpus is created from documents from translation memorios of Elhuyar Fundation (obtained via Eleka, member of the Advisory Board of Potential Users)."
-    ],
-    "oai_identifier": [
-        "dcdd306c18fd11e6a2aa782bcb0741351c96c57f9ce945b28dd5f347470c5a4d"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "Elhuyar-QTLeap WSD/NED corpus"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/258d5d50-ab86-57fb-9551-fc53af55bb3a.json b/oaitestdata/clarin-oai_dc/SET_1/json/258d5d50-ab86-57fb-9551-fc53af55bb3a.json
deleted file mode 100644
index 079ab010..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/258d5d50-ab86-57fb-9551-fc53af55bb3a.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3972",
-    "MetadataAccess": [
-        "oai:ota:oucs:3972"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pilon, Frederick, 1750-1788."
-    ],
-    "fulltext": "oai:ota:oucs:3972;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3972.xml;The fair American: a comic opera, in three acts; as it is performed, with universal applause, at the Theatre-Royal, Drury-Lane. Written by F. Pilon.;Pilon, Frederick, 1750-1788.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "258d5d50-ab86-57fb-9551-fc53af55bb3a",
-    "oai_identifier": [
-        "oai:ota:oucs:3972"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The fair American: a comic opera, in three acts; as it is performed, with universal applause, at the Theatre-Royal, Drury-Lane. Written by F. Pilon."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3972.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/258f0456-b767-5761-bc5e-a0f8625cf173.json b/oaitestdata/clarin-oai_dc/SET_1/json/258f0456-b767-5761-bc5e-a0f8625cf173.json
deleted file mode 100644
index 20b40070..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/258f0456-b767-5761-bc5e-a0f8625cf173.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Hunter, Lynette",
-        "British Academy"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "4 files : ca. 2.7 MB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2504",
-    "MetadataAccess": [
-        "oai:ota:oucs:2504"
-    ],
-    "PublicationTimestamp": "1641-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1641"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Letters"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hunter, Lynette"
-    ],
-    "fulltext": "oai:ota:oucs:2504;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/2504.xml;The Letters of Dorothy Moore 1641-1649;Hunter, Lynette;1641-1649;text_and_corpus_linguistics;Great Britain -- History -- Commonwealth and Protectorate, 1649-1660 -- Biography;Great Britain -- Politics and government -- 1649-1660;Women--Education;eng;Letters written by a mid-seventeenth century intellectual who held a significant role in religious, political, scientific and educational change in the period 1635-1661. ;Oxford Text Archive, University of Oxford;British Academy;Hunter, Lynette;4 files : ca. 2.7 MB;Text;Letters;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "258f0456-b767-5761-bc5e-a0f8625cf173",
-    "notes": [
-        "Letters written by a mid-seventeenth century intellectual who held a significant role in religious, political, scientific and educational change in the period 1635-1661. "
-    ],
-    "oai_identifier": [
-        "oai:ota:oucs:2504"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Great Britain -- History -- Commonwealth Protectorate"
-        },
-        {
-            "name": "- -- Biography"
-        },
-        {
-            "name": "Great Britain -- Politics government -- -"
-        },
-        {
-            "name": "Women--Education"
-        }
-    ],
-    "title": [
-        "The Letters of Dorothy Moore 1641-1649"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2504.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/25977fee-0d65-5a49-97e8-dff29d468572.json b/oaitestdata/clarin-oai_dc/SET_1/json/25977fee-0d65-5a49-97e8-dff29d468572.json
deleted file mode 100644
index 32f16d70..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/25977fee-0d65-5a49-97e8-dff29d468572.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 13",
-        "application/zip",
-        "application/octet-stream",
-        "application/gzip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/466",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/466"
-    ],
-    "PID": "http://hdl.handle.net/11321/466",
-    "PublicationTimestamp": "2018-04-03T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Sas, Jerzy"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/466;2018-09-18T12:58:36Z;hdl_11321_3;hdl_11321_4;Acoustic Data Building Toolset;Sas, Jerzy;speech recognition;deep neural networks;machine learning;This folder contains data and software tools (in python)  that can be used in experiments with phoneme recognition in speech samples recorder in Polish. Acoustic data used here were extracted from CLARIN-PL speech corpus after rejecting speech samples, where recorded sequence of words does not correspond strictly to the word sequence declared as the sample orthographic transcription. In order to use the python programs and data published here, the appropriate folder structure should be created. Follow the steps below:\r\n1) create the root folder and set the environment variable ASR_DATASET_ROOT that points to this folder (let's call it ROOT),\r\n2) create the subfolders in the ROOT folder: train, devel, test, doc and src in the root folder,\r\n3) download ar files: test.tar.gz, devel.tar.gz, train.tar.gz, doc.tar.gz, src.tar.gz and unpack then in the corresponding folders,\r\n4)download aux.tar.gz and unpack it directly to ROOT folder.\r\n\r\nMore information can be found in doc/README.pdf.\r\n\r\nIf you find this dataset useful, please make reference in your related papers to the paper: \"\r\nAcoustic Data Building Toolset for Easy Experimentation with Neural Network-based Speech Recognition in Polish and English\" (https://ieeexplore.ieee.org/document/8431366/)\r\n\r\n\r\n\r\nBibtex:\r\n@INPROCEEDINGS{8431366, \r\nauthor={J. Sas}, \r\nbooktitle={2018 11th International Conference on Human System Interaction (HSI)}, \r\ntitle={Acoustic Data Building Toolset for Easy Experimentation with Neural Network-based Speech Recognition in Polish and English}, \r\nyear={2018}, \r\nvolume={}, \r\nnumber={}, \r\npages={93-99}, \r\ndoi={10.1109/HSI.2018.8431366}, \r\nISSN={}, \r\nmonth={July},};2018-04-03;corpus;http://hdl.handle.net/11321/466;pol;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;text/plain; charset=utf-8;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/zip;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 13;Wroc\u0142aw University of Science and Technology;https://github.com/ASR-K2-WrUT/nn asr",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "25977fee-0d65-5a49-97e8-dff29d468572",
-    "notes": [
-        "This folder contains data and software tools (in python)  that can be used in experiments with phoneme recognition in speech samples recorder in Polish. Acoustic data used here were extracted from CLARIN-PL speech corpus after rejecting speech samples, where recorded sequence of words does not correspond strictly to the word sequence declared as the sample orthographic transcription. In order to use the python programs and data published here, the appropriate folder structure should be created. Follow the steps below:\r\n1) create the root folder and set the environment variable ASR_DATASET_ROOT that points to this folder (let's call it ROOT),\r\n2) create the subfolders in the ROOT folder: train, devel, test, doc and src in the root folder,\r\n3) download ar files: test.tar.gz, devel.tar.gz, train.tar.gz, doc.tar.gz, src.tar.gz and unpack then in the corresponding folders,\r\n4)download aux.tar.gz and unpack it directly to ROOT folder.\r\n\r\nMore information can be found in doc/README.pdf.\r\n\r\nIf you find this dataset useful, please make reference in your related papers to the paper: \"\r\nAcoustic Data Building Toolset for Easy Experimentation with Neural Network-based Speech Recognition in Polish and English\" (https://ieeexplore.ieee.org/document/8431366/)\r\n\r\n\r\n\r\nBibtex:\r\n@INPROCEEDINGS{8431366, \r\nauthor={J. Sas}, \r\nbooktitle={2018 11th International Conference on Human System Interaction (HSI)}, \r\ntitle={Acoustic Data Building Toolset for Easy Experimentation with Neural Network-based Speech Recognition in Polish and English}, \r\nyear={2018}, \r\nvolume={}, \r\nnumber={}, \r\npages={93-99}, \r\ndoi={10.1109/HSI.2018.8431366}, \r\nISSN={}, \r\nmonth={July},}"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/466"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech recognition"
-        },
-        {
-            "name": "deep neural networks"
-        },
-        {
-            "name": "machine learning"
-        }
-    ],
-    "title": [
-        "Acoustic Data Building Toolset"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/25a3fba0-8905-51b5-ac20-855841b3adcd.json b/oaitestdata/clarin-oai_dc/SET_1/json/25a3fba0-8905-51b5-ac20-855841b3adcd.json
deleted file mode 100644
index 7c510a6b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/25a3fba0-8905-51b5-ac20-855841b3adcd.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2856",
-    "MetadataAccess": [
-        "oai:ota:oucs:2856"
-    ],
-    "PublicationTimestamp": "1735-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1735"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2856;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2856.xml;The humble petition of the footmen in and about the city of Dublin ;Swift, Jonathan, 1667-1745;1735;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "25a3fba0-8905-51b5-ac20-855841b3adcd",
-    "oai_identifier": [
-        "oai:ota:oucs:2856"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The humble petition of the footmen in and about the city of Dublin "
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2856.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/25aec374-0fe7-56d5-802e-01602e073954.json b/oaitestdata/clarin-oai_dc/SET_1/json/25aec374-0fe7-56d5-802e-01602e073954.json
deleted file mode 100644
index 7c911274..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/25aec374-0fe7-56d5-802e-01602e073954.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/561",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/561"
-    ],
-    "PID": "http://hdl.handle.net/11321/561",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "BSD 2 Clause",
-        "https://opensource.org/licenses/BSD-2-Clause",
-        "PUB"
-    ],
-    "author": [
-        "Nito\u0144, Bart\u0142omiej"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/561;2018-07-26T12:00:31Z;hdl_11321_3;hdl_11321_4;Periphraser;Nito\u0144, Bart\u0142omiej;nominal phrases;semantic base;semantic knowledge base browser;automatic semantic and syntactic normalization;REST API;automatic error detection;Periphraser is a tool for storing and presenting knowledge base of conventionalized periphrastic nominal expressions (i.e. phrases headed by a noun) together with their textually attested realizations. For instance, the database entry for the phrase ,,Robert Lewandowski'' in the demo for Polish will include the phrase ,,the Polish international'' while ,,pediatrics'' will be featured as ,,medical care for children''. It allows contacting with database using REST API as well as exporting it to XML or CSV format. For Polish language, it also provides some more complex mechanisms like: automatic semantic and syntactic normalization, errors autodetection (also based on NKJP frequency and amount of results returned by the web browser), and simple interface for commenting and marking possibly wrong entries or ones needing improvement.;2018;toolService;http://hdl.handle.net/11321/561;pol;BSD 2 Clause;https://opensource.org/licenses/BSD-2-Clause;PUB;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;Institute of Computer Science, Polish Academy of Sciences;http://zil.ipipan.waw.pl/Periphraser",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "25aec374-0fe7-56d5-802e-01602e073954",
-    "notes": [
-        "Periphraser is a tool for storing and presenting knowledge base of conventionalized periphrastic nominal expressions (i.e. phrases headed by a noun) together with their textually attested realizations. For instance, the database entry for the phrase ,,Robert Lewandowski'' in the demo for Polish will include the phrase ,,the Polish international'' while ,,pediatrics'' will be featured as ,,medical care for children''. It allows contacting with database using REST API as well as exporting it to XML or CSV format. For Polish language, it also provides some more complex mechanisms like: automatic semantic and syntactic normalization, errors autodetection (also based on NKJP frequency and amount of results returned by the web browser), and simple interface for commenting and marking possibly wrong entries or ones needing improvement."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/561"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "nominal phrases"
-        },
-        {
-            "name": "semantic base"
-        },
-        {
-            "name": "semantic knowledge base browser"
-        },
-        {
-            "name": "automatic semantic syntactic normalization"
-        },
-        {
-            "name": "REST API"
-        },
-        {
-            "name": "automatic error detection"
-        }
-    ],
-    "title": [
-        "Periphraser"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/25b4b934-2b89-5570-ba62-bd9300cb38b6.json b/oaitestdata/clarin-oai_dc/SET_1/json/25b4b934-2b89-5570-ba62-bd9300cb38b6.json
deleted file mode 100644
index eff6c8c4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/25b4b934-2b89-5570-ba62-bd9300cb38b6.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4996",
-    "MetadataAccess": [
-        "oai:ota:oucs:4996"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Aikin, John, 1747-1822."
-    ],
-    "fulltext": "oai:ota:oucs:4996;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4996.xml;Evenings at home; or, the juvenile budget opened: Consisting of a variety of miscellaneous pieces, ... [pt.3];Aikin, John, 1747-1822.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "25b4b934-2b89-5570-ba62-bd9300cb38b6",
-    "oai_identifier": [
-        "oai:ota:oucs:4996"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Evenings at home; or, the juvenile budget opened: Consisting of a variety of miscellaneous pieces, ... [pt.3]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4996.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/25c2f5af-7a38-522b-96c2-0bdad3c2247e.json b/oaitestdata/clarin-oai_dc/SET_1/json/25c2f5af-7a38-522b-96c2-0bdad3c2247e.json
deleted file mode 100644
index 426790a8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/25c2f5af-7a38-522b-96c2-0bdad3c2247e.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1401",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1401"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1401",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1401;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;xsltproc;Format conversion service: a command line tool for applying XSLT stylesheets to XML documents;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1401;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "25c2f5af-7a38-522b-96c2-0bdad3c2247e",
-    "notes": [
-        "Format conversion service: a command line tool for applying XSLT stylesheets to XML documents"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1401"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "xsltproc"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/25c5ddc4-cb21-551c-a639-47538dcb46c0.json b/oaitestdata/clarin-oai_dc/SET_1/json/25c5ddc4-cb21-551c-a639-47538dcb46c0.json
deleted file mode 100644
index 1f192256..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/25c5ddc4-cb21-551c-a639-47538dcb46c0.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4547",
-    "MetadataAccess": [
-        "oai:ota:oucs:4547"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Defoe, Daniel, 1661?-1731."
-    ],
-    "fulltext": "oai:ota:oucs:4547;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4547.xml;A collection of the writings of the author of The true-born English-man.;Defoe, Daniel, 1661?-1731.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "25c5ddc4-cb21-551c-a639-47538dcb46c0",
-    "oai_identifier": [
-        "oai:ota:oucs:4547"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A collection of the writings of the author of The true-born English-man."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4547.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/25d2b046-755b-5849-b3fd-c56cda00e51d.json b/oaitestdata/clarin-oai_dc/SET_1/json/25d2b046-755b-5849-b3fd-c56cda00e51d.json
deleted file mode 100644
index fb1918e8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/25d2b046-755b-5849-b3fd-c56cda00e51d.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "McGuire, Lori"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 569 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0574",
-    "MetadataAccess": [
-        "oai:ota:oucs:0574"
-    ],
-    "PublicationTimestamp": "1978-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1978"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Memoirs"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "O'Malley, Ernie, 1898-1957"
-    ],
-    "fulltext": "oai:ota:oucs:0574;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0574.xml;The singing flame / Earn\u00c3\u00a1n O'Malley;O'Malley, Ernie, 1898-1957;1978;text_and_corpus_linguistics;Ireland -- History -- 20th century;eng;Oxford Text Archive, University of Oxford;McGuire, Lori;text/plain;(1 file : ca. 569 KB);Text;Memoirs;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "25d2b046-755b-5849-b3fd-c56cda00e51d",
-    "oai_identifier": [
-        "oai:ota:oucs:0574"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Ireland -- History -- th century"
-        }
-    ],
-    "title": [
-        "The singing flame / Earn\u00c3\u00a1n O'Malley"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0574.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/25efe23d-e699-5c77-b049-ec05c4e1cb1a.json b/oaitestdata/clarin-oai_dc/SET_1/json/25efe23d-e699-5c77-b049-ec05c4e1cb1a.json
deleted file mode 100644
index d4cad9fa..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/25efe23d-e699-5c77-b049-ec05c4e1cb1a.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Borin, Lars"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-516",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-516"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-516",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Sweden"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-516;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;SAL (Svenskt associationslexikon);Borin, Lars;appr. 72,000 entries (including many proper names and MWUs),  various, including RDF/XML;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-516;swe;downloadable_files_count: 0;Sweden;http://spraakbanken.gu.se/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "25efe23d-e699-5c77-b049-ec05c4e1cb1a",
-    "notes": [
-        "appr. 72,000 entries (including many proper names and MWUs),  various, including RDF/XML"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-516"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "SAL (Svenskt associationslexikon)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/25f1fe4a-6486-5d3c-83d6-5be9c215faf0.json b/oaitestdata/clarin-oai_dc/SET_1/json/25f1fe4a-6486-5d3c-83d6-5be9c215faf0.json
deleted file mode 100644
index 8039264e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/25f1fe4a-6486-5d3c-83d6-5be9c215faf0.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1408",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1408"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1408",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1408;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;vocabulary_analysis;Statistical analysis service:\nIt calculates different lexicometric measures and displays them graphically (tokens, types, hapaxes & type/token ratio).;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1408;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "25f1fe4a-6486-5d3c-83d6-5be9c215faf0",
-    "notes": [
-        "Statistical analysis service:\nIt calculates different lexicometric measures and displays them graphically (tokens, types, hapaxes & type/token ratio)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1408"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "vocabulary_analysis"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/260e754f-70da-58cb-b600-ea110bce841c.json b/oaitestdata/clarin-oai_dc/SET_1/json/260e754f-70da-58cb-b600-ea110bce841c.json
deleted file mode 100644
index 88551a5a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/260e754f-70da-58cb-b600-ea110bce841c.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/17",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/17"
-    ],
-    "PID": "http://hdl.handle.net/11321/17",
-    "PublicationTimestamp": "2014-01-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "author": [
-        "Radziszewski, Adam"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/17;2016-01-21T14:34:52Z;hdl_11321_3;hdl_11321_4;KPWr-lemma;Radziszewski, Adam;KPWr (Polish Corpus of Wroc\u0142aw University of Technology, pl. Korpus J\u0119zyka Polskiego Politechniki Wroc\u0142awskiej) is a corpus of written and spoken documents available on the Creative Common license. The texts are divided into 14 categories (blogs, science, stenographic recordings, etc.). The documents are annotated on the level of chunks and selected predicate-argument relations, named entities, relations between named entities, anaphora relations and word senses.;2014-01-01;corpus;http://hdl.handle.net/11321/17;pol;downloadable_files_count: 0;Wroc\u0142aw University of Technology;http://nlp.pwr.wroc.pl/kpwr",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "260e754f-70da-58cb-b600-ea110bce841c",
-    "notes": [
-        "KPWr (Polish Corpus of Wroc\u0142aw University of Technology, pl. Korpus J\u0119zyka Polskiego Politechniki Wroc\u0142awskiej) is a corpus of written and spoken documents available on the Creative Common license. The texts are divided into 14 categories (blogs, science, stenographic recordings, etc.). The documents are annotated on the level of chunks and selected predicate-argument relations, named entities, relations between named entities, anaphora relations and word senses."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/17"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "KPWr-lemma"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/26215347-6dd1-5dff-8679-a14f23035bcc.json b/oaitestdata/clarin-oai_dc/SET_1/json/26215347-6dd1-5dff-8679-a14f23035bcc.json
deleted file mode 100644
index 95a5ff03..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/26215347-6dd1-5dff-8679-a14f23035bcc.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "University of Lisbon, CLUL-Centro de Lingu\u00edstica da Universidade de Lisboa"
-    ],
-    "Contributor": [
-        "Branco, Ant\u00f3nio"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Portuguese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-386",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-386"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-386",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Lisbon, CLUL-Centro de Lingu\u00edstica da Universidade de Lisboa"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Portugal"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-386;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Nexing Corpus;Branco, Ant\u00f3nio;Psycholinguistics experiments on reasoning;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-386;por;downloadable_files_count: 0;Portugal;University of Lisbon, CLUL-Centro de Lingu\u00edstica da Universidade de Lisboa;http://www.di.fc.ul.pt/~ahb/nexingcorpus.htm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "26215347-6dd1-5dff-8679-a14f23035bcc",
-    "notes": [
-        "Psycholinguistics experiments on reasoning"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-386"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Nexing Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/263deac1-6503-5521-8dd9-dded0206e2e9.json b/oaitestdata/clarin-oai_dc/SET_1/json/263deac1-6503-5521-8dd9-dded0206e2e9.json
deleted file mode 100644
index 9b682397..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/263deac1-6503-5521-8dd9-dded0206e2e9.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2724",
-    "MetadataAccess": [
-        "oai:ota:oucs:2724"
-    ],
-    "PublicationTimestamp": "1766-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1766"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2724;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2724.xml;Journal to Stella [letters I, XLI-LXV];Swift, Jonathan, 1667-1745;1766;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "263deac1-6503-5521-8dd9-dded0206e2e9",
-    "oai_identifier": [
-        "oai:ota:oucs:2724"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Journal to Stella [letters I, XLI-LXV]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2724.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/26441fad-3a11-540e-b13c-952d7ee549f3.json b/oaitestdata/clarin-oai_dc/SET_1/json/26441fad-3a11-540e-b13c-952d7ee549f3.json
deleted file mode 100644
index 2e327f88..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/26441fad-3a11-540e-b13c-952d7ee549f3.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1036",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1036"
-    ],
-    "PID": "http://hdl.handle.net/11356/1036",
-    "PublicationTimestamp": "2013-09-30T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Krek, Simon",
-        "Kosem, Iztok",
-        "Stritar Ku\u010duk, Mojca",
-        "Rozman, Tadeja",
-        "Arhar Holdt, \u0160pela",
-        "Stabej, Marko",
-        "Krap\u0161 Vodopivec, Irena"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1036;2018-10-29T17:06:34Z;hdl_11356_1023;hdl_11356_1024;Learners' corpus \u0160olar 1.0;Rozman, Tadeja;Stritar Ku\u010duk, Mojca;Kosem, Iztok;Krek, Simon;Krap\u0161 Vodopivec, Irena;Arhar Holdt, \u0160pela;Stabej, Marko;developmental corpus;error annotation;student writing;\u0160olar consists of 2,703 texts written by students in Slovene secondary schools (age 15-19) and pupils in the 7th-9th grade of primary school (13-15), with a small percentage also from the 6th grade. School essays form the majority of the corpus (64.2%) while other material includes texts created during lessons, such as text recapitulations or descriptions, examples of formal applications etc. Part of the corpus is annotated with teachers' corrections using a  custom system of labels.;2013-09-30;corpus;http://hdl.handle.net/11356/1036;slv;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);https://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Centre for Language Resources and Technologies, University of Ljubljana;http://eng.slovenscina.eu/korpusi/solar",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "26441fad-3a11-540e-b13c-952d7ee549f3",
-    "notes": [
-        "\u0160olar consists of 2,703 texts written by students in Slovene secondary schools (age 15-19) and pupils in the 7th-9th grade of primary school (13-15), with a small percentage also from the 6th grade. School essays form the majority of the corpus (64.2%) while other material includes texts created during lessons, such as text recapitulations or descriptions, examples of formal applications etc. Part of the corpus is annotated with teachers' corrections using a  custom system of labels."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1036"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "developmental corpus"
-        },
-        {
-            "name": "error annotation"
-        },
-        {
-            "name": "student writing"
-        }
-    ],
-    "title": [
-        "Learners' corpus \u0160olar 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2651dd31-b922-5a8d-9a25-8144d04f9c37.json b/oaitestdata/clarin-oai_dc/SET_1/json/2651dd31-b922-5a8d-9a25-8144d04f9c37.json
deleted file mode 100644
index 94cb9016..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2651dd31-b922-5a8d-9a25-8144d04f9c37.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 1.47 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1627",
-    "MetadataAccess": [
-        "oai:ota:oucs:1627"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Marlowe, Christopher, 1564-1593"
-    ],
-    "fulltext": "oai:ota:oucs:1627;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1627.xml;Rare;Marlowe, Christopher, 1564-1593;default: 1976-01-01;text_and_corpus_linguistics;Poems -- England -- 16th century;eng;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 1.47 KB);Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2651dd31-b922-5a8d-9a25-8144d04f9c37",
-    "oai_identifier": [
-        "oai:ota:oucs:1627"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- England -- th century"
-        }
-    ],
-    "title": [
-        "Rare"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1627.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/26597244-09b0-5017-9a6b-801794cb7145.json b/oaitestdata/clarin-oai_dc/SET_1/json/26597244-09b0-5017-9a6b-801794cb7145.json
deleted file mode 100644
index 33e0dccf..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/26597244-09b0-5017-9a6b-801794cb7145.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=ff612a7070e311e5a2aa782bcb0741355868b1a6d9e44c7aa222d1fc8dbcd098",
-    "MetadataAccess": [
-        "ff612a7070e311e5a2aa782bcb0741355868b1a6d9e44c7aa222d1fc8dbcd098"
-    ],
-    "PublicationTimestamp": "2015-10-21T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "ff612a7070e311e5a2aa782bcb0741355868b1a6d9e44c7aa222d1fc8dbcd098;2018-11-15T16:40:17Z;corpus;corpus:text;CINTIL DependencyBank PREMIUM;CINTIL DependencyBank PREMIUM is a corpus of Portuguese utterances manually annotated with the representation of grammatical dependency relations and the information of part-of-speech, inflection and lemmas. It is being developed and maintained at the University of Lisbon. The current version is composed by 3,000 sentences (79,378 tokens) taken from portuguese newspaper articles.\n\nThe approach we follow is to build on top of an existing resource by adding a new annotation layer. We take the existing CINTIL corpus (Barreto et al., 2006), a 1 million token corpus already annotated with manually verified information on part-of-speech, morphology and named entities, and add syntactic function tags by automatically analysing it with a state-of-the-art dependency parser (LX-DepParser1). This tentative automatic annotation is then manually corrected.The manual correction is done by two annotators under a double-blind scheme, that is followed by adjudication by a third annotator. This process is supported by a general purpose annotation tool, WebAnno (https://code.google.com/p/webanno/).\nThe main motivation behind the creation of this resource was to create a corpus with a large variety of annotated phenomena that can be used for training statistical dependency parsers that are to be used in applications that deal with unrestricted text. Besides that, it enables linguistic studies that need to search the corpus for specific dependency structures.\n\nThis work was partly funded by the Portuguese Foundation for Science and Technology through the Portuguese project DP4LT (PTDC/EEI-SII/1940/2012) and by the European Commision through project QTLeap (EC/FP7/610516).;2015-10-21",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "26597244-09b0-5017-9a6b-801794cb7145",
-    "notes": [
-        "CINTIL DependencyBank PREMIUM is a corpus of Portuguese utterances manually annotated with the representation of grammatical dependency relations and the information of part-of-speech, inflection and lemmas. It is being developed and maintained at the University of Lisbon. The current version is composed by 3,000 sentences (79,378 tokens) taken from portuguese newspaper articles.\n\nThe approach we follow is to build on top of an existing resource by adding a new annotation layer. We take the existing CINTIL corpus (Barreto et al., 2006), a 1 million token corpus already annotated with manually verified information on part-of-speech, morphology and named entities, and add syntactic function tags by automatically analysing it with a state-of-the-art dependency parser (LX-DepParser1). This tentative automatic annotation is then manually corrected.The manual correction is done by two annotators under a double-blind scheme, that is followed by adjudication by a third annotator. This process is supported by a general purpose annotation tool, WebAnno (https://code.google.com/p/webanno/).\nThe main motivation behind the creation of this resource was to create a corpus with a large variety of annotated phenomena that can be used for training statistical dependency parsers that are to be used in applications that deal with unrestricted text. Besides that, it enables linguistic studies that need to search the corpus for specific dependency structures.\n\nThis work was partly funded by the Portuguese Foundation for Science and Technology through the Portuguese project DP4LT (PTDC/EEI-SII/1940/2012) and by the European Commision through project QTLeap (EC/FP7/610516)."
-    ],
-    "oai_identifier": [
-        "ff612a7070e311e5a2aa782bcb0741355868b1a6d9e44c7aa222d1fc8dbcd098"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "CINTIL DependencyBank PREMIUM"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2677ca9e-de45-59dd-9b09-002e1c39eed3.json b/oaitestdata/clarin-oai_dc/SET_1/json/2677ca9e-de45-59dd-9b09-002e1c39eed3.json
deleted file mode 100644
index 319cee20..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2677ca9e-de45-59dd-9b09-002e1c39eed3.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Polski Instytut Studi\u00f3w Nad Sztuk\u0105 \u015awiata"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 254",
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/octet-stream",
-        "application/pdf",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/597",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/597"
-    ],
-    "PID": "http://hdl.handle.net/11321/597",
-    "PublicationTimestamp": "2018-08-30T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Polski Instytut Studi\u00f3w Nad Sztuk\u0105 \u015awiata"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN-EULA-ACA-v1.0",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca",
-        "ACA"
-    ],
-    "author": [
-        "Wieczorek, Jan",
-        "Zarzycki, Jakub"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/597;2018-08-30T09:50:16Z;hdl_11321_3;hdl_11321_478;Siemiradzki 1.0;Zarzycki, Jakub;Wieczorek, Jan;history of art;Henryk Siemiradzki;Materia\u0142y do opracowania katalogu prac Henryka Siemiradzkiego.;2018-08-30;corpus;http://hdl.handle.net/11321/597;pol;CLARIN-EULA-ACA-v1.0;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca;ACA;text/plain; charset=utf-8;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/pdf;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/pdf;application/pdf;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/pdf;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/pdf;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/pdf;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/pdf;application/pdf;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/msword;application/pdf;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/msword;application/msword;application/msword;application/msword;application/pdf;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/pdf;application/msword;application/msword;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/pdf;application/msword;application/msword;application/pdf;application/msword;application/pdf;application/pdf;application/msword;application/msword;application/pdf;application/msword;application/pdf;application/msword;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/pdf;application/pdf;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/pdf;application/msword;application/msword;application/pdf;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/octet-stream;application/msword;application/msword;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/msword;application/msword;application/msword;application/pdf;application/msword;application/msword;application/msword;application/msword;application/pdf;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/msword;application/pdf;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/pdf;application/pdf;application/msword;application/msword;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/msword;application/msword;application/msword;downloadable_files_count: 254;Polski Instytut Studi\u00f3w Nad Sztuk\u0105 \u015awiata",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2677ca9e-de45-59dd-9b09-002e1c39eed3",
-    "notes": [
-        "Materia\u0142y do opracowania katalogu prac Henryka Siemiradzkiego."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/597"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_478"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "history art"
-        },
-        {
-            "name": "Henryk Siemiradzki"
-        }
-    ],
-    "title": [
-        "Siemiradzki 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/267f32f1-0843-530c-9942-3a23681aa39a.json b/oaitestdata/clarin-oai_dc/SET_1/json/267f32f1-0843-530c-9942-3a23681aa39a.json
deleted file mode 100644
index 31cddea9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/267f32f1-0843-530c-9942-3a23681aa39a.json
+++ /dev/null
@@ -1,363 +0,0 @@
-{
-    "Contact": [
-        "Universal Dependencies Consortium"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 3"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)",
-        "Arabic",
-        "Basque",
-        "Bulgarian",
-        "Croatian",
-        "Czech",
-        "Danish",
-        "Dutch",
-        "English",
-        "Estonian",
-        "Finnish",
-        "French",
-        "German",
-        "Gothic",
-        "Modern Greek (1453-)",
-        "Hebrew",
-        "Hindi",
-        "Hungarian",
-        "Indonesian",
-        "Irish",
-        "Italian",
-        "Japanese",
-        "Latin",
-        "Norwegian",
-        "Church Slavic",
-        "Persian",
-        "Polish",
-        "Portuguese",
-        "Romanian",
-        "Slovenian",
-        "Spanish",
-        "Swedish",
-        "Tamil",
-        "Catalan",
-        "Chinese",
-        "Galician",
-        "Kazakh",
-        "Latvian",
-        "Russian",
-        "Turkish",
-        "Coptic",
-        "Sanskrit",
-        "Slovak",
-        "Ukrainian",
-        "Uighur",
-        "Vietnamese",
-        "Belarusian",
-        "Korean",
-        "Lithuanian",
-        "Urdu",
-        "Northern Sami",
-        "Upper Sorbian",
-        "Afrikaans",
-        "Marathi",
-        "Serbian",
-        "Telugu"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2515",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2515"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2515",
-    "PublicationTimestamp": "2017-11-15T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Universal Dependencies Consortium"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-1983",
-        "http://hdl.handle.net/11234/1-2837"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Licence Universal Dependencies v2.1",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-2.1",
-        "PUB"
-    ],
-    "author": [
-        "Ion, Radu",
-        "Seraji, Mojgan",
-        "Lee, John",
-        "Manning, Christopher",
-        "Cebiro\u011flu Eryi\u011fit, G\u00fcl\u015fen",
-        "Ma\u0161ek, Jan",
-        "Uszkoreit, Hans",
-        "Hlav\u00e1\u010dov\u00e1, Jaroslava",
-        "Passarotti, Marco",
-        "Nguy\u1ec5n Th\u1ecb, L\u01b0\u01a1ng",
-        "Zhu, Hanzhi",
-        "Villemonte de la Clergerie, Eric",
-        "B\u00f6rstell, Carl",
-        "Macketanz, Vivien",
-        "Agi\u0107, \u017deljko",
-        "Simionescu, Radu",
-        "Muischnek, Kadri",
-        "Choi, Jinho",
-        "Washington, Jonathan North",
-        "Romanenko, Mykhailo",
-        "Montemagni, Simonetta",
-        "Davidson, Elizabeth",
-        "Ojala, Stina",
-        "Ure\u0161ov\u00e1, Zde\u0148ka",
-        "Moskalevskyi, Bohdan",
-        "Stella, Antonio",
-        "Rovati, Davide",
-        "Bank, Sebastian",
-        "Seeker, Wolfgang",
-        "Harris, Kim",
-        "Rademaker, Alexandre",
-        "Dirix, Peter",
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "Sanguinetti, Manuela",
-        "Mititelu, C\u0103t\u0103lin",
-        "Cinkov\u00e1, Silvie",
-        "Irimia, Elena",
-        "Lambertino, Lorenzo",
-        "Yu, Zhuoran",
-        "Simk\u00f3, Katalin",
-        "Badmaeva, Elena",
-        "Hladk\u00e1, Barbora",
-        "Trosterud, Trond",
-        "Krek, Simon",
-        "G\u00f6k\u0131rmak, Memduh",
-        "L\u00ea H\u1ed3ng, Ph\u01b0\u01a1ng",
-        "\u00d8vrelid, Lilja",
-        "Galbraith, Daniel",
-        "Lenci, Alessandro",
-        "Seddah, Djam\u00e9",
-        "Martins, Andr\u00e9",
-        "Ginter, Filip",
-        "Erjavec, Toma\u017e",
-        "Bick, Eckhard",
-        "Osenova, Petya",
-        "Mart\u00ednez Alonso, H\u00e9ctor",
-        "Kettnerov\u00e1, V\u00e1clava",
-        "Kayadelen, Tolga",
-        "Vajjala, Sowmya",
-        "Li, Josie",
-        "Haug, Dag",
-        "Rehm, Georg",
-        "Rinaldi, Larissa",
-        "Lynn, Teresa",
-        "Plank, Barbara",
-        "Sagot, Beno\u00eet",
-        "Freitas, Cl\u00e1udia",
-        "Varga, Viktor",
-        "Lyashevskaya, Olga",
-        "J\u00f8rgensen, Fredrik",
-        "M\u0103r\u0103nduc, C\u0103t\u0103lina",
-        "Ka\u015f\u0131kara, H\u00fcner",
-        "Pyysalo, Sampo",
-        "Kanerva, Jenna",
-        "Sulubacak, Umut",
-        "Sz\u00e1nt\u00f3, Zsolt",
-        "Chalub, Fabricio",
-        "Marheinecke, Katrin",
-        "Atutxa, Aitziber",
-        "Augustinus, Liesbeth",
-        "Goldberg, Yoav",
-        "Matsumoto, Yuji",
-        "Dozat, Timothy",
-        "Ateyah, Luma",
-        "G\u00f3mez Guinovart, Xavier",
-        "M\u00fc\u00fcrisep, Kaili",
-        "Saul\u012bte, Baiba",
-        "Caron, Gauthier",
-        "Mandl, Michael",
-        "Nivre, Joakim",
-        "Prokopidis, Prokopis",
-        "Petrov, Slav",
-        "Reddy, Siva",
-        "Guillaume, Bruno",
-        "Gr\u016bz\u012btis, Normunds",
-        "Cetin, Savas",
-        "Haji\u010d jr., Jan",
-        "Perrier, Guy",
-        "Trukhina, Anna",
-        "Nainwani, Pinkey",
-        "de Marneffe, Marie-Catherine",
-        "Antonsen, Lene",
-        "Attia, Mohammed",
-        "Schuster, Sebastian",
-        "Missil\u00e4, Anna",
-        "Rama, Taraka",
-        "Dwivedi, Puneet",
-        "Hohle, Petter",
-        "Makazhanov, Aibek",
-        "Tyers, Francis",
-        "McDonald, Ryan",
-        "Pretkalni\u0146a, Lauma",
-        "Farkas, Rich\u00e1rd",
-        "Moreno Romero, Laura",
-        "Bouma, Gosse",
-        "Ramasamy, Loganathan",
-        "Bosco, Cristina",
-        "Kirchner, Jesse",
-        "Fernandez Alcalde, Hector",
-        "Eli, Marhaba",
-        "Barbu Mititelu, Verginica",
-        "Ravishankar, Vinit",
-        "de Paiva, Valeria",
-        "Grioni, Matias",
-        "Real, Livy",
-        "Lertpradit, Saran",
-        "Asahara, Masayuki",
-        "Pitler, Emily",
-        "Suhr, Alane",
-        "Miekka, Niko",
-        "Miyao, Yusuke",
-        "Vincze, Veronika",
-        "Bhat, Riyaz Ahmad",
-        "Garcia, Marcos",
-        "Loginova, Olga",
-        "Shimada, Atsuko",
-        "Straka, Milan",
-        "van Niekerk, Daniel",
-        "Tanaka, Takaaki",
-        "Nguy\u1ec5n Th\u1ecb Minh, Huy\u1ec1n",
-        "Sichinava, Dmitry",
-        "Puolakainen, Tiina",
-        "Tsarfaty, Reut",
-        "Taji, Dima",
-        "Goenaga, Iakes",
-        "Rituma, Laura",
-        "H\u00e0 M\u1ef9, Linh",
-        "Habash, Nizar",
-        "Mori, Shinsuke",
-        "Samard\u017ei\u0107, Tanja",
-        "Droganova, Kira",
-        "Li, Keying",
-        "Elkahky, Ali",
-        "Connor, Miriam",
-        "Mare\u010dek, David",
-        "Smith, Aaron",
-        "Banerjee, Esha",
-        "Nedoluzhko, Anna",
-        "Strnadov\u00e1, Jana",
-        "More, Amir",
-        "Mendon\u00e7a, Gustavo",
-        "\u0160imkov\u00e1, M\u00e1ria",
-        "Gajdo\u0161ov\u00e1, Katar\u00edna",
-        "Zeman, Daniel",
-        "Celano, Giuseppe G. A.",
-        "Dobrovoljc, Kaja",
-        "Jel\u00ednek, Tom\u00e1\u0161",
-        "Bobicev, Victoria",
-        "Popel, Martin",
-        "Laippala, Veronika",
-        "Gojenola, Koldo",
-        "Gerdes, Kim",
-        "Lando, Tatiana",
-        "Simov, Kiril",
-        "Ballesteros, Miguel",
-        "Nurmi, Hanna",
-        "Nikolaev, Vitaly",
-        "Wir\u00e9n, Mats",
-        "Perez, Cenel-Augusto",
-        "Bauer, John",
-        "Ljube\u0161i\u0107, Nikola",
-        "Wong, Tak-sum",
-        "Ahrenberg, Lars",
-        "Ne\u0161pore-B\u0113rzkalne, Gunta",
-        "Simi, Maria",
-        "Diaz de Ilarraza, Arantza",
-        "Rosa, Rudolf",
-        "Aranzabe, Maria Jesus",
-        "Li, Cheuk Ying",
-        "Candito, Marie",
-        "Shen, Mo",
-        "Saleh, Shadi",
-        "Burchardt, Aljoscha",
-        "Bengoetxea, Kepa",
-        "van Noord, Gertjan",
-        "Wallin, Lars",
-        "Zeldes, Amir",
-        "Pascual, Elena",
-        "\u00d6stling, Robert",
-        "Johannsen, Anders",
-        "Foster, Jennifer",
-        "G\u00e4rdenfors, Moa",
-        "\u00c7\u00f6ltekin, \u00c7a\u011fr\u0131",
-        "Piitulainen, Jussi",
-        "Uematsu, Sumire",
-        "Gonz\u00e1les Saavedra, Berta",
-        "Uria, Larraitz",
-        "Leung, Herman",
-        "Kanayama, Hiroshi",
-        "Haji\u010d, Jan",
-        "Bowman, Sam",
-        "Kotsyba, Natalia",
-        "Silveira, Natalia",
-        "Hociung, Florinel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2515;2018-07-16T08:08:45Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Universal Dependencies 2.1;Nivre, Joakim;Agi\u0107, \u017deljko;Ahrenberg, Lars;Antonsen, Lene;Aranzabe, Maria Jesus;Asahara, Masayuki;Ateyah, Luma;Attia, Mohammed;Atutxa, Aitziber;Augustinus, Liesbeth;Badmaeva, Elena;Ballesteros, Miguel;Banerjee, Esha;Bank, Sebastian;Barbu Mititelu, Verginica;Bauer, John;Bengoetxea, Kepa;Bhat, Riyaz Ahmad;Bick, Eckhard;Bobicev, Victoria;B\u00f6rstell, Carl;Bosco, Cristina;Bouma, Gosse;Bowman, Sam;Burchardt, Aljoscha;Candito, Marie;Caron, Gauthier;Cebiro\u011flu Eryi\u011fit, G\u00fcl\u015fen;Celano, Giuseppe G. A.;Cetin, Savas;Chalub, Fabricio;Choi, Jinho;Cinkov\u00e1, Silvie;\u00c7\u00f6ltekin, \u00c7a\u011fr\u0131;Connor, Miriam;Davidson, Elizabeth;de Marneffe, Marie-Catherine;de Paiva, Valeria;Diaz de Ilarraza, Arantza;Dirix, Peter;Dobrovoljc, Kaja;Dozat, Timothy;Droganova, Kira;Dwivedi, Puneet;Eli, Marhaba;Elkahky, Ali;Erjavec, Toma\u017e;Farkas, Rich\u00e1rd;Fernandez Alcalde, Hector;Foster, Jennifer;Freitas, Cl\u00e1udia;Gajdo\u0161ov\u00e1, Katar\u00edna;Galbraith, Daniel;Garcia, Marcos;G\u00e4rdenfors, Moa;Gerdes, Kim;Ginter, Filip;Goenaga, Iakes;Gojenola, Koldo;G\u00f6k\u0131rmak, Memduh;Goldberg, Yoav;G\u00f3mez Guinovart, Xavier;Gonz\u00e1les Saavedra, Berta;Grioni, Matias;Gr\u016bz\u012btis, Normunds;Guillaume, Bruno;Habash, Nizar;Haji\u010d, Jan;Haji\u010d jr., Jan;H\u00e0 M\u1ef9, Linh;Harris, Kim;Haug, Dag;Hladk\u00e1, Barbora;Hlav\u00e1\u010dov\u00e1, Jaroslava;Hociung, Florinel;Hohle, Petter;Ion, Radu;Irimia, Elena;Jel\u00ednek, Tom\u00e1\u0161;Johannsen, Anders;J\u00f8rgensen, Fredrik;Ka\u015f\u0131kara, H\u00fcner;Kanayama, Hiroshi;Kanerva, Jenna;Kayadelen, Tolga;Kettnerov\u00e1, V\u00e1clava;Kirchner, Jesse;Kotsyba, Natalia;Krek, Simon;Laippala, Veronika;Lambertino, Lorenzo;Lando, Tatiana;Lee, John;L\u00ea H\u1ed3ng, Ph\u01b0\u01a1ng;Lenci, Alessandro;Lertpradit, Saran;Leung, Herman;Li, Cheuk Ying;Li, Josie;Li, Keying;Ljube\u0161i\u0107, Nikola;Loginova, Olga;Lyashevskaya, Olga;Lynn, Teresa;Macketanz, Vivien;Makazhanov, Aibek;Mandl, Michael;Manning, Christopher;M\u0103r\u0103nduc, C\u0103t\u0103lina;Mare\u010dek, David;Marheinecke, Katrin;Mart\u00ednez Alonso, H\u00e9ctor;Martins, Andr\u00e9;Ma\u0161ek, Jan;Matsumoto, Yuji;McDonald, Ryan;Mendon\u00e7a, Gustavo;Miekka, Niko;Missil\u00e4, Anna;Mititelu, C\u0103t\u0103lin;Miyao, Yusuke;Montemagni, Simonetta;More, Amir;Moreno Romero, Laura;Mori, Shinsuke;Moskalevskyi, Bohdan;Muischnek, Kadri;M\u00fc\u00fcrisep, Kaili;Nainwani, Pinkey;Nedoluzhko, Anna;Ne\u0161pore-B\u0113rzkalne, Gunta;Nguy\u1ec5n Th\u1ecb, L\u01b0\u01a1ng;Nguy\u1ec5n Th\u1ecb Minh, Huy\u1ec1n;Nikolaev, Vitaly;Nurmi, Hanna;Ojala, Stina;Osenova, Petya;\u00d6stling, Robert;\u00d8vrelid, Lilja;Pascual, Elena;Passarotti, Marco;Perez, Cenel-Augusto;Perrier, Guy;Petrov, Slav;Piitulainen, Jussi;Pitler, Emily;Plank, Barbara;Popel, Martin;Pretkalni\u0146a, Lauma;Prokopidis, Prokopis;Puolakainen, Tiina;Pyysalo, Sampo;Rademaker, Alexandre;Ramasamy, Loganathan;Rama, Taraka;Ravishankar, Vinit;Real, Livy;Reddy, Siva;Rehm, Georg;Rinaldi, Larissa;Rituma, Laura;Romanenko, Mykhailo;Rosa, Rudolf;Rovati, Davide;Sagot, Beno\u00eet;Saleh, Shadi;Samard\u017ei\u0107, Tanja;Sanguinetti, Manuela;Saul\u012bte, Baiba;Schuster, Sebastian;Seddah, Djam\u00e9;Seeker, Wolfgang;Seraji, Mojgan;Shen, Mo;Shimada, Atsuko;Sichinava, Dmitry;Silveira, Natalia;Simi, Maria;Simionescu, Radu;Simk\u00f3, Katalin;\u0160imkov\u00e1, M\u00e1ria;Simov, Kiril;Smith, Aaron;Stella, Antonio;Straka, Milan;Strnadov\u00e1, Jana;Suhr, Alane;Sulubacak, Umut;Sz\u00e1nt\u00f3, Zsolt;Taji, Dima;Tanaka, Takaaki;Trosterud, Trond;Trukhina, Anna;Tsarfaty, Reut;Tyers, Francis;Uematsu, Sumire;Ure\u0161ov\u00e1, Zde\u0148ka;Uria, Larraitz;Uszkoreit, Hans;Vajjala, Sowmya;van Niekerk, Daniel;van Noord, Gertjan;Varga, Viktor;Villemonte de la Clergerie, Eric;Vincze, Veronika;Wallin, Lars;Washington, Jonathan North;Wir\u00e9n, Mats;Wong, Tak-sum;Yu, Zhuoran;\u017dabokrtsk\u00fd, Zden\u011bk;Zeldes, Amir;Zeman, Daniel;Zhu, Hanzhi;treebank;dependency;syntax;morphology;harmonized annotation;interset;universal tagset;stanford dependencies;Universal Dependencies is a project that seeks to develop cross-linguistically consistent treebank annotation for many languages, with the goal of facilitating multilingual parser development, cross-lingual learning, and parsing research from a language typology perspective. The annotation scheme is based on (universal) Stanford dependencies (de Marneffe et al., 2006, 2008, 2014), Google universal part-of-speech tags (Petrov et al., 2012), and the Interset interlingua for morphosyntactic tagsets (Zeman, 2008).;2017-11-15;corpus;http://hdl.handle.net/11234/1-2515;grc;ara;eus;bul;hrv;ces;dan;nld;eng;est;fin;fra;deu;got;ell;heb;hin;hun;ind;gle;ita;jpn;lat;nor;chu;fas;pol;por;ron;slv;spa;swe;tam;cat;zho;glg;kaz;lav;rus;tur;cop;san;slk;ukr;uig;vie;bel;kor;lit;urd;bxr;kmr;sme;hsb;afr;yue;mar;srp;swl;tel;http://hdl.handle.net/11234/1-1983;http://hdl.handle.net/11234/1-2837;Licence Universal Dependencies v2.1;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-2.1;PUB;application/x-gzip;application/x-gzip;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 3;Universal Dependencies Consortium;http://universaldependencies.org/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "267f32f1-0843-530c-9942-3a23681aa39a",
-    "notes": [
-        "Universal Dependencies is a project that seeks to develop cross-linguistically consistent treebank annotation for many languages, with the goal of facilitating multilingual parser development, cross-lingual learning, and parsing research from a language typology perspective. The annotation scheme is based on (universal) Stanford dependencies (de Marneffe et al., 2006, 2008, 2014), Google universal part-of-speech tags (Petrov et al., 2012), and the Interset interlingua for morphosyntactic tagsets (Zeman, 2008)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2515"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "dependency"
-        },
-        {
-            "name": "syntax"
-        },
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "harmonized annotation"
-        },
-        {
-            "name": "interset"
-        },
-        {
-            "name": "universal tagset"
-        },
-        {
-            "name": "stanford dependencies"
-        }
-    ],
-    "title": [
-        "Universal Dependencies 2.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/268c0980-687c-5a44-9844-c1489e94a1b6.json b/oaitestdata/clarin-oai_dc/SET_1/json/268c0980-687c-5a44-9844-c1489e94a1b6.json
deleted file mode 100644
index 808ba6f1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/268c0980-687c-5a44-9844-c1489e94a1b6.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "McCleery, Alistair, 1954-"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain",
-        "(1 file : ca. 182 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1206",
-    "MetadataAccess": [
-        "oai:ota:oucs:1206"
-    ],
-    "PublicationTimestamp": "1808-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1808"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Lamb, Charles, 1775-1834"
-    ],
-    "fulltext": "oai:ota:oucs:1206;2018-03-05T13:22:36Z;http://ota.ox.ac.uk/headers/1206.xml;Adventures of Ulysses;The adventures of Ulysses / Charles Lamb;Lamb, Charles, 1775-1834;1808;text_and_corpus_linguistics;Epic poetry, Greek -- B.C.;eng;Oxford Text Archive, University of Oxford;McCleery, Alistair, 1954-;text/plain;(1 file : ca. 182 KB);Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "268c0980-687c-5a44-9844-c1489e94a1b6",
-    "oai_identifier": [
-        "oai:ota:oucs:1206"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Epic poetry"
-        },
-        {
-            "name": "Greek -- B.C."
-        }
-    ],
-    "title": [
-        "Adventures of Ulysses",
-        "The adventures of Ulysses / Charles Lamb"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1206.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2696e6a7-cc94-51b9-869c-bdbb479b4b73.json b/oaitestdata/clarin-oai_dc/SET_1/json/2696e6a7-cc94-51b9-869c-bdbb479b4b73.json
deleted file mode 100644
index 197d2ad8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2696e6a7-cc94-51b9-869c-bdbb479b4b73.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3923",
-    "MetadataAccess": [
-        "oai:ota:oucs:3923"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Warton, Joseph, 1722-1800."
-    ],
-    "fulltext": "oai:ota:oucs:3923;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3923.xml;The enthusiast: or, the lover of nature. A poem;Warton, Joseph, 1722-1800.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2696e6a7-cc94-51b9-869c-bdbb479b4b73",
-    "oai_identifier": [
-        "oai:ota:oucs:3923"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The enthusiast: or, the lover of nature. A poem"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3923.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/26bd0d47-49d0-5f55-b0d3-b058e02532d9.json b/oaitestdata/clarin-oai_dc/SET_1/json/26bd0d47-49d0-5f55-b0d3-b058e02532d9.json
deleted file mode 100644
index 72c86916..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/26bd0d47-49d0-5f55-b0d3-b058e02532d9.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Digital Library, http://wals.info/author"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-852",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-852"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-852",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Digital Library, http://wals.info/author"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Creative Commons Attribution-Noncommercial-No Derivative Works 2.0 Germany - http://creativecommons.org/licenses/by-nc-nd/2.0/de/deed.en",
-        "http://wals.info/about/legal"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-852;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;The World Atlas of Language Structures Online;WALS is a large database of structural (phonological, grammatical, lexical) properties of languages gathered from descriptive materials (such as reference grammars) by a team of more than 40 authors  (many of them the leading authorities on the subject).;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-852;Creative Commons Attribution-Noncommercial-No Derivative Works 2.0 Germany - http://creativecommons.org/licenses/by-nc-nd/2.0/de/deed.en;http://wals.info/about/legal;downloadable_files_count: 0;Max Planck Digital Library, http://wals.info/author;http://wals.info/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "26bd0d47-49d0-5f55-b0d3-b058e02532d9",
-    "notes": [
-        "WALS is a large database of structural (phonological, grammatical, lexical) properties of languages gathered from descriptive materials (such as reference grammars) by a team of more than 40 authors  (many of them the leading authorities on the subject)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-852"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "The World Atlas of Language Structures Online"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/26c1075f-9b79-516d-9fc1-4783b379a180.json b/oaitestdata/clarin-oai_dc/SET_1/json/26c1075f-9b79-516d-9fc1-4783b379a180.json
deleted file mode 100644
index d1a7d0fb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/26c1075f-9b79-516d-9fc1-4783b379a180.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics",
-        "University of Utrecht/Netherlands Graduate School of Linguistics",
-        "Data Archiving and Networked Services",
-        "Meertens Institute KNAW The Netherlands"
-    ],
-    "Contributor": [
-        "Windhouwer, Menzo",
-        "Dimitriadis, Alexis",
-        "Grootveld, Marjan",
-        "Kemps-Snijders, Marc",
-        "Akerman, Vesa",
-        "Zeeman, Rob"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-327",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-327"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-327",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics",
-        "University of Utrecht/Netherlands Graduate School of Linguistics",
-        "Data Archiving and Networked Services",
-        "Meertens Institute KNAW The Netherlands"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-327;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Typological Database System;Dimitriadis, Alexis;Windhouwer, Menzo;Kemps-Snijders, Marc;Zeeman, Rob;Akerman, Vesa;Grootveld, Marjan;typological database;The Typological Database System (TDS) is a web-based service that provides integrated access to a collection of independently created typological databases. It was developed with support from NWO grant 380-30-004 / INV-03-12 and from participating universities, and provides continued availability and extended documentation for its component databases, through a uniform structure and search interface. Web technologies evolve rapidly, and the system had begun to show its age even before the end of the project in 2009, motivating migration of the data collection to an archival platform. Through its Project Call 1, CLARIN-NL granted funding for migrating the resource to a durable, archival environment and converting it to a true web service architecture.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-327;eng;downloadable_files_count: 0;Netherlands (the);Max Planck Institute for Psycholinguistics;University of Utrecht/Netherlands Graduate School of Linguistics;Data Archiving and Networked Services;Meertens Institute KNAW The Netherlands;http://www.persistent-identifier.nl/?identifier=urn:nbn:nl:ui:13-6oz8-ik",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "26c1075f-9b79-516d-9fc1-4783b379a180",
-    "notes": [
-        "The Typological Database System (TDS) is a web-based service that provides integrated access to a collection of independently created typological databases. It was developed with support from NWO grant 380-30-004 / INV-03-12 and from participating universities, and provides continued availability and extended documentation for its component databases, through a uniform structure and search interface. Web technologies evolve rapidly, and the system had begun to show its age even before the end of the project in 2009, motivating migration of the data collection to an archival platform. Through its Project Call 1, CLARIN-NL granted funding for migrating the resource to a durable, archival environment and converting it to a true web service architecture."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-327"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "typological database"
-        }
-    ],
-    "title": [
-        "Typological Database System"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/26cb2796-aeae-5a65-8e19-998d99cbfced.json b/oaitestdata/clarin-oai_dc/SET_1/json/26cb2796-aeae-5a65-8e19-998d99cbfced.json
deleted file mode 100644
index 37165804..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/26cb2796-aeae-5a65-8e19-998d99cbfced.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Gothenburg University Library, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/83",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/83"
-    ],
-    "PID": "http://hdl.handle.net/10794/83",
-    "PublicationTimestamp": "2016-12-14T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Gothenburg University Library, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/83;2017-10-26T07:58:26Z;hdl_10794_1;hdl_10794_2;Bet\u00e4nkande (2017-10-16);Bet\u00e4nkande (2017-10-16);n/a, n/a;Swedish;Part of the Riksdag's open data. 1971-12-31\u20132016-02-22.;Riksdagens \u00f6ppna data: Utskottens bet\u00e4nkanden och utl\u00e5tanden, inklusive rksdagens beslut, en sammanfattning av voteringsresultaten och Beslut i korthet. 1971-12-31\u20132016-02-22.;2016-12-14;corpus;http://hdl.handle.net/10794/83;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/octet-stream;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Gothenburg University Library, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/rd-bet",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "26cb2796-aeae-5a65-8e19-998d99cbfced",
-    "notes": [
-        "Part of the Riksdag's open data. 1971-12-31\u20132016-02-22.",
-        "Riksdagens \u00f6ppna data: Utskottens bet\u00e4nkanden och utl\u00e5tanden, inklusive rksdagens beslut, en sammanfattning av voteringsresultaten och Beslut i korthet. 1971-12-31\u20132016-02-22."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/83"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        }
-    ],
-    "title": [
-        "Bet\u00e4nkande (2017-10-16)",
-        "Bet\u00e4nkande (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/26d92095-dc38-54cd-8c96-67899ceecef7.json b/oaitestdata/clarin-oai_dc/SET_1/json/26d92095-dc38-54cd-8c96-67899ceecef7.json
deleted file mode 100644
index 61630c27..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/26d92095-dc38-54cd-8c96-67899ceecef7.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4569",
-    "MetadataAccess": [
-        "oai:ota:oucs:4569"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "O'Keeffe, John, 1747-1833."
-    ],
-    "fulltext": "oai:ota:oucs:4569;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4569.xml;The world in a village: a comedy, in five acts, as performed with universal applause at the Theatre Royal, Covent-Garden. Written by John O'Keefe, ...;O'Keeffe, John, 1747-1833.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "26d92095-dc38-54cd-8c96-67899ceecef7",
-    "oai_identifier": [
-        "oai:ota:oucs:4569"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The world in a village: a comedy, in five acts, as performed with universal applause at the Theatre Royal, Covent-Garden. Written by John O'Keefe, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4569.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/26dfe28b-da32-5cd0-81d8-46252f7b9aec.json b/oaitestdata/clarin-oai_dc/SET_1/json/26dfe28b-da32-5cd0-81d8-46252f7b9aec.json
deleted file mode 100644
index 7ec57dfe..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/26dfe28b-da32-5cd0-81d8-46252f7b9aec.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/467",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/467"
-    ],
-    "PID": "http://hdl.handle.net/11321/467",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "author": [
-        "Ogrodniczuk, Maciej"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/467;2018-05-07T01:38:44Z;hdl_11321_3;hdl_11321_4;Polish Parliamentary Corpus;Ogrodniczuk, Maciej;Polish;parliamentary data;corpus;The Polish Parliamentary Corpus (PPC) is a large collection of linguistically analysed documents from the proceedings of Polish Parliament, Sejm and Senate. The corpus files are made available in TEI P5 format compatible with the annotation used by the National Corpus of Polish.;2018;corpus;http://hdl.handle.net/11321/467;pol;downloadable_files_count: 0;Institute of Computer Science, Polish Academy of Sciences;http://clip.ipipan.waw.pl/PPC",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "26dfe28b-da32-5cd0-81d8-46252f7b9aec",
-    "notes": [
-        "The Polish Parliamentary Corpus (PPC) is a large collection of linguistically analysed documents from the proceedings of Polish Parliament, Sejm and Senate. The corpus files are made available in TEI P5 format compatible with the annotation used by the National Corpus of Polish."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/467"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Polish"
-        },
-        {
-            "name": "parliamentary data"
-        },
-        {
-            "name": "corpus"
-        }
-    ],
-    "title": [
-        "Polish Parliamentary Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/26e38e74-4ba0-5cf4-a18b-f832e302aa05.json b/oaitestdata/clarin-oai_dc/SET_1/json/26e38e74-4ba0-5cf4-a18b-f832e302aa05.json
deleted file mode 100644
index 68ba7466..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/26e38e74-4ba0-5cf4-a18b-f832e302aa05.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish",
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/57",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/57"
-    ],
-    "PID": "http://hdl.handle.net/10794/57",
-    "PublicationTimestamp": "2015-04-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/57;2017-10-31T12:30:43Z;hdl_10794_1;hdl_10794_2;ASPAC \u2013 Swedish-Italian (2017-10-16);ASPAC \u2013 svenska-italienska (2017-10-16);n/a, n/a;ASPAC;Parallel;Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.;Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat.;2015-04-16;corpus;http://hdl.handle.net/10794/57;swe;ita;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/octet-stream;application/gzip;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/aspacsvit",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "26e38e74-4ba0-5cf4-a18b-f832e302aa05",
-    "notes": [
-        "Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.",
-        "Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/57"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ASPAC"
-        },
-        {
-            "name": "Parallel"
-        }
-    ],
-    "title": [
-        "ASPAC \u2013 Swedish-Italian (2017-10-16)",
-        "ASPAC \u2013 svenska-italienska (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/26f1a9c3-9d17-5586-9667-5703c8f291cc.json b/oaitestdata/clarin-oai_dc/SET_1/json/26f1a9c3-9d17-5586-9667-5703c8f291cc.json
deleted file mode 100644
index ecc30fec..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/26f1a9c3-9d17-5586-9667-5703c8f291cc.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Bear, Richard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(3 files : ca. 35, 176, 18 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1796",
-    "MetadataAccess": [
-        "oai:ota:oucs:1796"
-    ],
-    "PublicationTimestamp": "1765-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1765"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Ballad operas"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gay, John, 1685-1732"
-    ],
-    "fulltext": "oai:ota:oucs:1796;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/1796.xml;Beggar's opera. Libretto.;The beggar's opera / [text] by John Gay ; transcribed with an introduction, notes and bibliography by Richard Bear; John Gay's The beggar's opera;Gay, John, 1685-1732;1765;text_and_corpus_linguistics;Ballad operas;Oxford Text Archive, University of Oxford;Bear, Richard;Bear, Richard;text/sgml;(3 files : ca. 35, 176, 18 KB);Text;Ballad operas;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "26f1a9c3-9d17-5586-9667-5703c8f291cc",
-    "oai_identifier": [
-        "oai:ota:oucs:1796"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Ballad operas"
-        }
-    ],
-    "title": [
-        "Beggar's opera. Libretto.",
-        "The beggar's opera / [text] by John Gay ; transcribed with an introduction, notes and bibliography by Richard Bear",
-        " John Gay's The beggar's opera"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1796.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/27095f74-86ac-5000-994d-cd7cf593691b.json b/oaitestdata/clarin-oai_dc/SET_1/json/27095f74-86ac-5000-994d-cd7cf593691b.json
deleted file mode 100644
index 2b608e0f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/27095f74-86ac-5000-994d-cd7cf593691b.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "A"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1558",
-    "MetadataAccess": [
-        "oai:ota:oucs:1558"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Emerson, Ralph Waldo"
-    ],
-    "fulltext": "oai:ota:oucs:1558;2018-04-16T15:30:51Z;http://ota.ox.ac.uk/headers/1558.xml;Representative man;Emerson, Ralph Waldo;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;A;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "27095f74-86ac-5000-994d-cd7cf593691b",
-    "oai_identifier": [
-        "oai:ota:oucs:1558"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Representative man"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1558.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/271236f5-53ea-591a-9347-f71d0b698b50.json b/oaitestdata/clarin-oai_dc/SET_1/json/271236f5-53ea-591a-9347-f71d0b698b50.json
deleted file mode 100644
index 16e8bfee..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/271236f5-53ea-591a-9347-f71d0b698b50.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "The Research Institute for the Languages of Finland"
-    ],
-    "Contributor": [
-        "Lounela, Mikko"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Finnish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-826",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-826"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-826",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "The Research Institute for the Languages of Finland"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Finland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-826;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Frequency list: Old Literary Finnish;Lounela, Mikko;Frequency list of the Corpus of Old Literary Finnish, 3 425 382 words;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-826;fin;downloadable_files_count: 0;Finland;The Research Institute for the Languages of Finland;http://kaino.kotus.fi/sanat/taajuuslista/vks.php",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "271236f5-53ea-591a-9347-f71d0b698b50",
-    "notes": [
-        "Frequency list of the Corpus of Old Literary Finnish, 3 425 382 words"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-826"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Frequency list: Old Literary Finnish"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/271c99b5-3ab3-5365-8623-84cebfb3a63b.json b/oaitestdata/clarin-oai_dc/SET_1/json/271c99b5-3ab3-5365-8623-84cebfb3a63b.json
deleted file mode 100644
index ebc5f308..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/271c99b5-3ab3-5365-8623-84cebfb3a63b.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Formal Linguistics Department of Warsaw University"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "image/png",
-        "downloadable_files_count: 3",
-        "application/octet-stream"
-    ],
-    "Language": [],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/475",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/475"
-    ],
-    "PID": "http://hdl.handle.net/11321/475",
-    "PublicationTimestamp": "2015-04-15T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Formal Linguistics Department of Warsaw University"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "Bie\u0144, Janusz S."
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/475;2018-05-21T08:03:28Z;hdl_11321_3;hdl_11321_4;A lexicographical browser for DjVu;Bie\u0144, Janusz S.;lexicography slips Djvu browser indexer;The program is an indexer and browser for the scans of lexicographical paper slips. The slips are presented in DjVu format and an appropriate relational database stores the information about them. The integration of three approaches: incremental search, binary search and the so-called occasional indexing which consists in refinement of the stored information while searching, offers easy and convenient browsing.;2015-04-15;toolService;http://hdl.handle.net/11321/475;N/A;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;image/png;image/png;application/octet-stream;downloadable_files_count: 3;Formal Linguistics Department of Warsaw University;https://bitbucket.org/jsbien/ndt/wiki/wyniki#!przegladarka-materiaow-leksykograficznych-a-lexicographical-browser",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "271c99b5-3ab3-5365-8623-84cebfb3a63b",
-    "notes": [
-        "The program is an indexer and browser for the scans of lexicographical paper slips. The slips are presented in DjVu format and an appropriate relational database stores the information about them. The integration of three approaches: incremental search, binary search and the so-called occasional indexing which consists in refinement of the stored information while searching, offers easy and convenient browsing."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/475"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "lexicography slips Djvu browser indexer"
-        }
-    ],
-    "title": [
-        "A lexicographical browser for DjVu"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/27200cea-e207-53ef-a0ff-46e90fbae5ac.json b/oaitestdata/clarin-oai_dc/SET_1/json/27200cea-e207-53ef-a0ff-46e90fbae5ac.json
deleted file mode 100644
index d2b41944..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/27200cea-e207-53ef-a0ff-46e90fbae5ac.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4690",
-    "MetadataAccess": [
-        "oai:ota:oucs:4690"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Carey, George Saville, 1743-1807."
-    ],
-    "fulltext": "oai:ota:oucs:4690;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4690.xml;The old women weatherwise, an interlude: as performed at the Theatre Royal in Drury-Lane.;Carey, George Saville, 1743-1807.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "27200cea-e207-53ef-a0ff-46e90fbae5ac",
-    "oai_identifier": [
-        "oai:ota:oucs:4690"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The old women weatherwise, an interlude: as performed at the Theatre Royal in Drury-Lane."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4690.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/27269a5e-ce62-5cd3-9f59-087b0990f044.json b/oaitestdata/clarin-oai_dc/SET_1/json/27269a5e-ce62-5cd3-9f59-087b0990f044.json
deleted file mode 100644
index df923702..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/27269a5e-ce62-5cd3-9f59-087b0990f044.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "University of Joensuu"
-    ],
-    "Contributor": [
-        "Niemi, Jussi"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Finnish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-804",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-804"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-804",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Joensuu"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Finland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-804;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;The Karjalainen Corpus;Niemi, Jussi;computer corpus of Finnish newspaper texts of the 1990s (newspaper Karjalainen, Joensuu);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-804;fin;downloadable_files_count: 0;Finland;University of Joensuu;http://www.csc.fi",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "27269a5e-ce62-5cd3-9f59-087b0990f044",
-    "notes": [
-        "computer corpus of Finnish newspaper texts of the 1990s (newspaper Karjalainen, Joensuu)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-804"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "The Karjalainen Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2729701f-93b6-5d10-a705-8d6c8a8049f0.json b/oaitestdata/clarin-oai_dc/SET_1/json/2729701f-93b6-5d10-a705-8d6c8a8049f0.json
deleted file mode 100644
index 2dc4edec..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2729701f-93b6-5d10-a705-8d6c8a8049f0.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Strindbergsprojektet"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/79",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/79"
-    ],
-    "PID": "http://hdl.handle.net/10794/79",
-    "PublicationTimestamp": "2012-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Strindbergsprojektet"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/79;2017-10-26T08:28:42Z;hdl_10794_1;hdl_10794_2;August Strindberg's novels (2017-10-16);August Strindbergs romaner (2017-10-16);n/a, n/a;Swedish;Novels;Part of the collected works of August Strindberg.\r\n\r\nAugust Strindberg's novels and dramas have been published as a national edition, Nationalupplagan av August Strindbergs samlade verk, by Stockholm University and Norstedts.\r\n\r\nThe material is not proofread by the editors, and may thus contain minor errors and deviations from the printed volumes. For more information about the publication of the Collected Works, see the homepage of the Strindberg project. See also the frequency and word explanation query.\r\n\r\nThe material is sentence scrambled.;Del av August Strindbergs samlade verk.\r\n\r\nAugust Strindbergs romaner och dramer har utgivits som Nationalupplagan av August Strindbergs samlade verk av Stockholms universitet och Norstedts.\r\n\r\nMaterialet i databaserna \u00e4r ej korrekturl\u00e4st av utgivarna, sm\u00e4rre felaktigheter och avvikelser fr\u00e5n de tryckta volymerna kan d\u00e4rf\u00f6r f\u00f6rekomma. F\u00f6r mer information om utgivningen av Samlade Verk, se Strindbergsprojektets hemsida. Se \u00e4ven frekvens- och ordf\u00f6rklaringss\u00f6kning.\r\n\r\nMaterialet \u00e4r meningsomkastat.;2012-05-30;corpus;http://hdl.handle.net/10794/79;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;http://creativecommons.org/licenses/by/4.0/;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Strindbergsprojektet;https://spraakbanken.gu.se/swe/resurs/strindbergromaner",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2729701f-93b6-5d10-a705-8d6c8a8049f0",
-    "notes": [
-        "Part of the collected works of August Strindberg.\r\n\r\nAugust Strindberg's novels and dramas have been published as a national edition, Nationalupplagan av August Strindbergs samlade verk, by Stockholm University and Norstedts.\r\n\r\nThe material is not proofread by the editors, and may thus contain minor errors and deviations from the printed volumes. For more information about the publication of the Collected Works, see the homepage of the Strindberg project. See also the frequency and word explanation query.\r\n\r\nThe material is sentence scrambled.",
-        "Del av August Strindbergs samlade verk.\r\n\r\nAugust Strindbergs romaner och dramer har utgivits som Nationalupplagan av August Strindbergs samlade verk av Stockholms universitet och Norstedts.\r\n\r\nMaterialet i databaserna \u00e4r ej korrekturl\u00e4st av utgivarna, sm\u00e4rre felaktigheter och avvikelser fr\u00e5n de tryckta volymerna kan d\u00e4rf\u00f6r f\u00f6rekomma. F\u00f6r mer information om utgivningen av Samlade Verk, se Strindbergsprojektets hemsida. Se \u00e4ven frekvens- och ordf\u00f6rklaringss\u00f6kning.\r\n\r\nMaterialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/79"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Novels"
-        }
-    ],
-    "title": [
-        "August Strindberg's novels (2017-10-16)",
-        "August Strindbergs romaner (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/272fed3b-f8e9-5237-a98b-914ca8b2f130.json b/oaitestdata/clarin-oai_dc/SET_1/json/272fed3b-f8e9-5237-a98b-914ca8b2f130.json
deleted file mode 100644
index f68ba96f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/272fed3b-f8e9-5237-a98b-914ca8b2f130.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/46",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/46"
-    ],
-    "PID": "http://hdl.handle.net/10794/46",
-    "PublicationTimestamp": "2012-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/46;2017-10-27T06:37:24Z;hdl_10794_1;hdl_10794_2;S\u00f6derwall Supplement (2017-10-16);S\u00f6derwall Supplement (2017-10-16);n/a, n/a;Swedish;Dictionary;Dictionary of Old Swedish, supplement.;Ordbok \u00f6ver svenska medeltidsspr\u00e5ket, supplement.;2012-05-30;lexicalConceptualResource;http://hdl.handle.net/10794/46;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/soederwall-supp",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "272fed3b-f8e9-5237-a98b-914ca8b2f130",
-    "notes": [
-        "Dictionary of Old Swedish, supplement.",
-        "Ordbok \u00f6ver svenska medeltidsspr\u00e5ket, supplement."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/46"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Dictionary"
-        }
-    ],
-    "title": [
-        "S\u00f6derwall Supplement (2017-10-16)",
-        "S\u00f6derwall Supplement (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/274f7473-a081-5828-848b-59c761a3a81d.json b/oaitestdata/clarin-oai_dc/SET_1/json/274f7473-a081-5828-848b-59c761a3a81d.json
deleted file mode 100644
index df24b40f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/274f7473-a081-5828-848b-59c761a3a81d.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4470",
-    "MetadataAccess": [
-        "oai:ota:oucs:4470"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Defoe, Daniel, 1661?-1731."
-    ],
-    "fulltext": "oai:ota:oucs:4470;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4470.xml;A new test of the Church of England's loyalty: or, Whiggish loyalty and church loyalty compar'd.;Defoe, Daniel, 1661?-1731.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "274f7473-a081-5828-848b-59c761a3a81d",
-    "oai_identifier": [
-        "oai:ota:oucs:4470"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A new test of the Church of England's loyalty: or, Whiggish loyalty and church loyalty compar'd."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4470.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/279d2ed8-c1c1-5d91-b4df-ef4155c5aa51.json b/oaitestdata/clarin-oai_dc/SET_1/json/279d2ed8-c1c1-5d91-b4df-ef4155c5aa51.json
deleted file mode 100644
index 06081234..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/279d2ed8-c1c1-5d91-b4df-ef4155c5aa51.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Gabler, Hans Walter, 1938-"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 373 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1605",
-    "MetadataAccess": [
-        "oai:ota:oucs:1605"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Short stories"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Joyce, James, 1882-1941"
-    ],
-    "fulltext": "oai:ota:oucs:1605;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1605.xml;Dubliners / James Joyce;Joyce, James, 1882-1941;text_and_corpus_linguistics;Short stories, Irish -- 20th century;Oxford Text Archive, University of Oxford;Gabler, Hans Walter, 1938-;text/sgml;(1 file : ca. 373 KB);Text;Short stories;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "279d2ed8-c1c1-5d91-b4df-ef4155c5aa51",
-    "oai_identifier": [
-        "oai:ota:oucs:1605"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Short stories"
-        },
-        {
-            "name": "Irish -- th century"
-        }
-    ],
-    "title": [
-        "Dubliners / James Joyce"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1605.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/27f682d5-cb73-55ba-95c3-4491456f562f.json b/oaitestdata/clarin-oai_dc/SET_1/json/27f682d5-cb73-55ba-95c3-4491456f562f.json
deleted file mode 100644
index df80b644..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/27f682d5-cb73-55ba-95c3-4491456f562f.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-85",
-    "MetadataAccess": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-85"
-    ],
-    "PID": "http://hdl.handle.net/20.500.11752/ILC-85",
-    "PublicationTimestamp": "2017-10-18T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Del Gratta, Riccardo"
-    ],
-    "fulltext": "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-85;2018-11-08T08:31:45Z;hdl_000-c0-111_38;hdl_000-c0-111_78;Java Porting of OpeNER tokenizer web service for WebLicht;Del Gratta, Riccardo;tokenization;tokenisation;Test WebLicht (https://weblicht.sfs.uni-tuebingen.de/) registry entry for Opener webservice comprising tokenisation only.;2017-10-18;toolService;http://hdl.handle.net/20.500.11752/ILC-85;ita;application/octet-stream;downloadable_files_count: 0;Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR);https://github.com/cnr-ilc/linguistic-tools-for-weblicht/tree/master/Tokenizer-Base-Service",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "27f682d5-cb73-55ba-95c3-4491456f562f",
-    "notes": [
-        "Test WebLicht (https://weblicht.sfs.uni-tuebingen.de/) registry entry for Opener webservice comprising tokenisation only."
-    ],
-    "oai_identifier": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-85"
-    ],
-    "oai_set": [
-        "hdl_000-c0-111_38",
-        "hdl_000-c0-111_78"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "tokenization"
-        },
-        {
-            "name": "tokenisation"
-        }
-    ],
-    "title": [
-        "Java Porting of OpeNER tokenizer web service for WebLicht"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2837d743-e2b7-5659-8e2f-93a16a0b6886.json b/oaitestdata/clarin-oai_dc/SET_1/json/2837d743-e2b7-5659-8e2f-93a16a0b6886.json
deleted file mode 100644
index 3ae5d2c4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2837d743-e2b7-5659-8e2f-93a16a0b6886.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-10B2-F",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-10B2-F"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-10B2-F",
-    "PublicationTimestamp": "2013-09-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/288487"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0)",
-        "http://creativecommons.org/licenses/by-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Bojar, Ond\u0159ej",
-        "Tamchyna, Ale\u0161",
-        "Zeman, Daniel",
-        "Mach\u00e1\u010dek, Matou\u0161"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-10B2-F;2018-07-02T22:05:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Many Czech References for 50 Sentences Selected from WMT11 Data;Bojar, Ond\u0159ej;Mach\u00e1\u010dek, Matou\u0161;Tamchyna, Ale\u0161;Zeman, Daniel;machine translation;automatic machine translation evaluation;reference translation;This dataset contains the whole set of very many Czech translations for 50 English source sentences coming from WMT11 test set (http://www.statmt.org/wmt11).\r\n\r\nIn total, there are 15431447 Czech sentences, i.e. 300k reference translations per source English sentence on average, but the exact number greatly varies across sentences.\r\n\r\nYou can find more details in included README file.\r\n\r\nIf you use this dataset, please cite the following paper which describes the technique used to construct the Czech translations:\r\n\r\nBojar Ond\u0159ej, Mach\u00e1\u010dek Matou\u0161, Tamchyna Ale\u0161, Zeman Daniel:\r\nScratching the Surface of Possible Translations.\r\nLecture Notes in Computer Science, Vol. 8082, Text, Speech and Dialogue: 16th\r\nInternational Conference, TSD 2013. Proceedings, Copyright \u00a9 Springer Verlag,\r\nBerlin / Heidelberg, ISBN 978-3-642-40584-6, ISSN 0302-9743, pp. 465-474, 2013, DOI: 10.1007/978-3-642-40585-3_59;2013-09-01;corpus;http://hdl.handle.net/11858/00-097C-0000-0023-10B2-F;ces;info:eu-repo/grantAgreement/EC/FP7/288487;Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0);http://creativecommons.org/licenses/by-sa/3.0/;PUB;application/zip;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2837d743-e2b7-5659-8e2f-93a16a0b6886",
-    "notes": [
-        "This dataset contains the whole set of very many Czech translations for 50 English source sentences coming from WMT11 test set (http://www.statmt.org/wmt11).\r\n\r\nIn total, there are 15431447 Czech sentences, i.e. 300k reference translations per source English sentence on average, but the exact number greatly varies across sentences.\r\n\r\nYou can find more details in included README file.\r\n\r\nIf you use this dataset, please cite the following paper which describes the technique used to construct the Czech translations:\r\n\r\nBojar Ond\u0159ej, Mach\u00e1\u010dek Matou\u0161, Tamchyna Ale\u0161, Zeman Daniel:\r\nScratching the Surface of Possible Translations.\r\nLecture Notes in Computer Science, Vol. 8082, Text, Speech and Dialogue: 16th\r\nInternational Conference, TSD 2013. Proceedings, Copyright \u00a9 Springer Verlag,\r\nBerlin / Heidelberg, ISBN 978-3-642-40584-6, ISSN 0302-9743, pp. 465-474, 2013, DOI: 10.1007/978-3-642-40585-3_59"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-10B2-F"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "automatic machine translation evaluation"
-        },
-        {
-            "name": "reference translation"
-        }
-    ],
-    "title": [
-        "Many Czech References for 50 Sentences Selected from WMT11 Data"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2844e46d-bc32-5ccf-8312-d8604bc60b30.json b/oaitestdata/clarin-oai_dc/SET_1/json/2844e46d-bc32-5ccf-8312-d8604bc60b30.json
deleted file mode 100644
index 59b3b874..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2844e46d-bc32-5ccf-8312-d8604bc60b30.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "National Library of Latvia"
-    ],
-    "Contributor": [
-        "Gr\u012bnfelde, Inga"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German",
-        "Latvian",
-        "Russian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-856",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-856"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-856",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "National Library of Latvia"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Latvia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-856;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Latvian National Digital Library \u201cLetonica\u201d;Gr\u012bnfelde, Inga;Its aim is to ensure digitising the collections of the National Library of Latvia and other similar organisations, by making them accessible on the Internet. The creation of the digital library lays the foundation for uniform principles of processing, storing the digitised materials and ensuring access to them.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-856;deu;lav;rus;downloadable_files_count: 0;Latvia;National Library of Latvia;http://www.lnb.lv/lv/digitala-biblioteka",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2844e46d-bc32-5ccf-8312-d8604bc60b30",
-    "notes": [
-        "Its aim is to ensure digitising the collections of the National Library of Latvia and other similar organisations, by making them accessible on the Internet. The creation of the digital library lays the foundation for uniform principles of processing, storing the digitised materials and ensuring access to them."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-856"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Latvian National Digital Library \u201cLetonica\u201d"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/286fff71-a030-5743-93b1-40d3bdf1a455.json b/oaitestdata/clarin-oai_dc/SET_1/json/286fff71-a030-5743-93b1-40d3bdf1a455.json
deleted file mode 100644
index 59b58119..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/286fff71-a030-5743-93b1-40d3bdf1a455.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Department of Information Technology, Gauhati University, Assam, India"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Assamese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/619",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/619"
-    ],
-    "PID": "http://hdl.handle.net/11321/619",
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Department of Information Technology, Gauhati University, Assam, India"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "author": [
-        "Sarma, Prof. Shikhar Kr."
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/619;2019-01-08T11:10:14Z;hdl_11321_3;hdl_11321_610;Assamese Corpus;Sarma, Prof. Shikhar Kr.;Assamese NLP;Assamese Corpus;Assamese Corpora;Gauhati University;Assamese Corpus was developed in the NLP Lab of Gauhati University. Total size of Assamese Corpus (in terms of words) is 1.6 million (1613551 words). The Corpus is prepared following the guidelines of Corpus Encoding Standard and is UNICODE encoded. Corpus for Assamese language was developed keeping in mind certain issues like- Size of the corpus, Genre or domain selection, Range of writers, data collection, Computerization of data, Validation of corpus. The types of genre/domain used in the corpus were- Literature, Learned-Material and Media which includes Newspapers.\r\n\r\n-------\r\n\r\n1. These Assamese NLP resources including the Tools and Applications are developed\r\nduring Research and Development Projects as well as Masters and Ph.D. thesis\r\nworks.\r\n2. These are mainly developed or generated at Gauhati University Department of\r\nComputer Science and Department of Information Technology.\r\n3. These resources are used by students and researchers for further studies, researches, as\r\nwell as for design and development of tools and applications.\r\n4. Computational Linguistics in Assamese is not rich, and Natural Language Processing\r\nworks have mainly started during last two decades, and most of the resources are first\r\ngeneration resources, and with ample scope for upgrading, enriching, and purifying.\r\n5. These are very good and essential resources for all the researchers in Assamese NLP, as\r\nthe language requires more and more NLP works to make Assamese a rich media for\r\nthe digital world.\r\n6. Anyone interested, or in need of such resources may express their interest for the\r\nrequired resources, and the way of availability will be advised/informed accordingly.\r\n7. These are purely research materials and could only be used for further research only.\r\n8. Researchers may visit the NLP Lab of Department of Information Technology, Gauhati\r\nUniversity, Guwahati, India or contact us.\r\n9. Researchers interested in collaborative works, and also students for project works, are\r\nwelcome.\r\n10. Contact person is Professor Shikhar Kr. Sarma, Department of Information\r\nTechnology, Gauhati University, Guwahati 781014, Assam, India. Email-\r\nsks@gauhati.ac.in;2019-01-08;corpus;http://hdl.handle.net/11321/619;asm;downloadable_files_count: 0;Department of Information Technology, Gauhati University, Assam, India",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "286fff71-a030-5743-93b1-40d3bdf1a455",
-    "notes": [
-        "Assamese Corpus was developed in the NLP Lab of Gauhati University. Total size of Assamese Corpus (in terms of words) is 1.6 million (1613551 words). The Corpus is prepared following the guidelines of Corpus Encoding Standard and is UNICODE encoded. Corpus for Assamese language was developed keeping in mind certain issues like- Size of the corpus, Genre or domain selection, Range of writers, data collection, Computerization of data, Validation of corpus. The types of genre/domain used in the corpus were- Literature, Learned-Material and Media which includes Newspapers.\r\n\r\n-------\r\n\r\n1. These Assamese NLP resources including the Tools and Applications are developed\r\nduring Research and Development Projects as well as Masters and Ph.D. thesis\r\nworks.\r\n2. These are mainly developed or generated at Gauhati University Department of\r\nComputer Science and Department of Information Technology.\r\n3. These resources are used by students and researchers for further studies, researches, as\r\nwell as for design and development of tools and applications.\r\n4. Computational Linguistics in Assamese is not rich, and Natural Language Processing\r\nworks have mainly started during last two decades, and most of the resources are first\r\ngeneration resources, and with ample scope for upgrading, enriching, and purifying.\r\n5. These are very good and essential resources for all the researchers in Assamese NLP, as\r\nthe language requires more and more NLP works to make Assamese a rich media for\r\nthe digital world.\r\n6. Anyone interested, or in need of such resources may express their interest for the\r\nrequired resources, and the way of availability will be advised/informed accordingly.\r\n7. These are purely research materials and could only be used for further research only.\r\n8. Researchers may visit the NLP Lab of Department of Information Technology, Gauhati\r\nUniversity, Guwahati, India or contact us.\r\n9. Researchers interested in collaborative works, and also students for project works, are\r\nwelcome.\r\n10. Contact person is Professor Shikhar Kr. Sarma, Department of Information\r\nTechnology, Gauhati University, Guwahati 781014, Assam, India. Email-\r\nsks@gauhati.ac.in"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/619"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_610"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Assamese NLP"
-        },
-        {
-            "name": "Assamese Corpus"
-        },
-        {
-            "name": "Assamese Corpora"
-        },
-        {
-            "name": "Gauhati University"
-        }
-    ],
-    "title": [
-        "Assamese Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/287968a5-fe39-5e0b-894d-ff068f0767e7.json b/oaitestdata/clarin-oai_dc/SET_1/json/287968a5-fe39-5e0b-894d-ff068f0767e7.json
deleted file mode 100644
index f73a8d30..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/287968a5-fe39-5e0b-894d-ff068f0767e7.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=0ec6596a6c9e11e2a2aa782bcb074135c53f8f4bd0f4434ba9d574e58f19ce7f",
-    "MetadataAccess": [
-        "0ec6596a6c9e11e2a2aa782bcb074135c53f8f4bd0f4434ba9d574e58f19ce7f"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "0ec6596a6c9e11e2a2aa782bcb074135c53f8f4bd0f4434ba9d574e58f19ce7f;2018-11-15T16:40:12Z;toolService;toolService:tool;U-Compare Apertium Part-of-Speech Tagging Workflow;This is a workflow that is designed especially for use in the UIMA-based U-Compare workbench (see separate META-SHARE record).  The workflow is in \"ucz\" format (specific to U-Compare) and can be imported via the \"Import Workflow\" item in the \"Workflows\" menu of the U-Compare interface. It includes the \"Apertium Mopho\" and \"Apertium POS\" UIMA components, that are not part of U-Compare's component library. These two components are part the the Apertium Machine Translation system.  \n\nThe purpose of the workflow is to perform tokenisation, morphological analysis and part of speech tagging on plain text. \n\nThe provided workflow can currently operate on a subset of the languages that are supported by the Apertium system, namely:  English, Spanish, Calatan, Galician, Portuguese and Basque.  ;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "287968a5-fe39-5e0b-894d-ff068f0767e7",
-    "notes": [
-        "This is a workflow that is designed especially for use in the UIMA-based U-Compare workbench (see separate META-SHARE record).  The workflow is in \"ucz\" format (specific to U-Compare) and can be imported via the \"Import Workflow\" item in the \"Workflows\" menu of the U-Compare interface. It includes the \"Apertium Mopho\" and \"Apertium POS\" UIMA components, that are not part of U-Compare's component library. These two components are part the the Apertium Machine Translation system.  \n\nThe purpose of the workflow is to perform tokenisation, morphological analysis and part of speech tagging on plain text. \n\nThe provided workflow can currently operate on a subset of the languages that are supported by the Apertium system, namely:  English, Spanish, Calatan, Galician, Portuguese and Basque.  "
-    ],
-    "oai_identifier": [
-        "0ec6596a6c9e11e2a2aa782bcb074135c53f8f4bd0f4434ba9d574e58f19ce7f"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "U-Compare Apertium Part-of-Speech Tagging Workflow"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/288fc1bd-30d7-506b-bfdd-84e6072035c0.json b/oaitestdata/clarin-oai_dc/SET_1/json/288fc1bd-30d7-506b-bfdd-84e6072035c0.json
deleted file mode 100644
index 8f0ce6d7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/288fc1bd-30d7-506b-bfdd-84e6072035c0.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "295 KB"
-    ],
-    "Language": [
-        "Middle High German (ca. 1050-1500)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1956",
-    "MetadataAccess": [
-        "oai:ota:oucs:1956"
-    ],
-    "PublicationTimestamp": "1220-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1220"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Der Stricker"
-    ],
-    "fulltext": "oai:ota:oucs:1956;2018-04-16T14:11:10Z;http://ota.ox.ac.uk/headers/1956.xml;Daniel von dem bl\u00c3\u00bchenden Tal;Der Stricker;1220;text_and_corpus_linguistics;Romances -- Germany -- 13th century;Poems -- Germany -- 13th century;gmh;Oxford Text Archive, University of Oxford;295 KB;Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "288fc1bd-30d7-506b-bfdd-84e6072035c0",
-    "oai_identifier": [
-        "oai:ota:oucs:1956"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Romances -- Germany -- th century"
-        },
-        {
-            "name": "Poems -- Germany -- th century"
-        }
-    ],
-    "title": [
-        "Daniel von dem bl\u00c3\u00bchenden Tal"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1956.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/289cf865-1fab-5a4a-89ac-1c10ab03e87f.json b/oaitestdata/clarin-oai_dc/SET_1/json/289cf865-1fab-5a4a-89ac-1c10ab03e87f.json
deleted file mode 100644
index 3d6ff198..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/289cf865-1fab-5a4a-89ac-1c10ab03e87f.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3836",
-    "MetadataAccess": [
-        "oai:ota:oucs:3836"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Burke, Edmund, 1729-1797."
-    ],
-    "fulltext": "oai:ota:oucs:3836;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3836.xml;The beauties of the late Right Hon. Edmund Burke, selected from the writings, &c. of that extraordinary man, ... To which is prefixed, a sketch of the life, with some original anecdotes of Mr. Burke. In two volumes.: [pt.2];Burke, Edmund, 1729-1797.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "289cf865-1fab-5a4a-89ac-1c10ab03e87f",
-    "oai_identifier": [
-        "oai:ota:oucs:3836"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The beauties of the late Right Hon. Edmund Burke, selected from the writings, &c. of that extraordinary man, ... To which is prefixed, a sketch of the life, with some original anecdotes of Mr. Burke. In two volumes.: [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3836.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/28bb5ca7-c2fb-596f-9600-5d2f2897f1f7.json b/oaitestdata/clarin-oai_dc/SET_1/json/28bb5ca7-c2fb-596f-9600-5d2f2897f1f7.json
deleted file mode 100644
index 83459b0d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/28bb5ca7-c2fb-596f-9600-5d2f2897f1f7.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "University of Warsaw"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/msword",
-        "downloadable_files_count: 4",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/347",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/347"
-    ],
-    "PID": "http://hdl.handle.net/11321/347",
-    "PublicationTimestamp": "2017-04-25T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "University of Warsaw"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Winiarska, Izabela"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/347;2017-04-25T14:09:27Z;hdl_11321_3;hdl_11321_4;New Gospels;Winiarska, Izabela;old Polish;Nowe Ateny;2017-04-25;corpus;http://hdl.handle.net/11321/347;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;application/zip;application/msword;application/msword;application/msword;downloadable_files_count: 4;University of Warsaw;http/www.us.edu.pl",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "28bb5ca7-c2fb-596f-9600-5d2f2897f1f7",
-    "notes": [
-        "Nowe Ateny"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/347"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "old Polish"
-        }
-    ],
-    "title": [
-        "New Gospels"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/28bd6184-0810-5be9-b2a0-9c9aa010b11d.json b/oaitestdata/clarin-oai_dc/SET_1/json/28bd6184-0810-5be9-b2a0-9c9aa010b11d.json
deleted file mode 100644
index de8cf29a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/28bd6184-0810-5be9-b2a0-9c9aa010b11d.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3925",
-    "MetadataAccess": [
-        "oai:ota:oucs:3925"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Mason, William, 1725-1797."
-    ],
-    "fulltext": "oai:ota:oucs:3925;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3925.xml;An epistle to Dr. Shebbeare: to which is added an ode to Sir Fletcher Norton, in imitation of Horace, Ode VIII. Book IV. By Malcolm MacGreggor, of Knightsbridge, Esq. ...;Mason, William, 1725-1797.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "28bd6184-0810-5be9-b2a0-9c9aa010b11d",
-    "oai_identifier": [
-        "oai:ota:oucs:3925"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An epistle to Dr. Shebbeare: to which is added an ode to Sir Fletcher Norton, in imitation of Horace, Ode VIII. Book IV. By Malcolm MacGreggor, of Knightsbridge, Esq. ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3925.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/28e6db38-af40-5d61-a1d3-cb6d09903cc0.json b/oaitestdata/clarin-oai_dc/SET_1/json/28e6db38-af40-5d61-a1d3-cb6d09903cc0.json
deleted file mode 100644
index a016f16a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/28e6db38-af40-5d61-a1d3-cb6d09903cc0.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3944",
-    "MetadataAccess": [
-        "oai:ota:oucs:3944"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "More, Hannah, 1745-1833."
-    ],
-    "fulltext": "oai:ota:oucs:3944;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3944.xml;Essays on various subjects: principally designed for young ladies.;More, Hannah, 1745-1833.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "28e6db38-af40-5d61-a1d3-cb6d09903cc0",
-    "oai_identifier": [
-        "oai:ota:oucs:3944"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Essays on various subjects: principally designed for young ladies."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3944.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/28eea68e-1b2e-5347-8fb0-f9ba3a54182c.json b/oaitestdata/clarin-oai_dc/SET_1/json/28eea68e-1b2e-5347-8fb0-f9ba3a54182c.json
deleted file mode 100644
index e73600d2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/28eea68e-1b2e-5347-8fb0-f9ba3a54182c.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "University of Lisbon"
-    ],
-    "Contributor": [
-        "Branco, Ant\u00f3nio"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Portuguese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-648",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-648"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-648",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Lisbon"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Portugal"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-648;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;MWNPT - MultiWordNet of Portuguese;Branco, Ant\u00f3nio;Wordnet of Portuguese with 18 000 synsets and 25 lemmata, alligned with other wordnets for other languages, including English Princeton WordNet.;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-648;por;downloadable_files_count: 0;Portugal;University of Lisbon;http://multiwordnet.itc.it/online/multiwordnet.php",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "28eea68e-1b2e-5347-8fb0-f9ba3a54182c",
-    "notes": [
-        "Wordnet of Portuguese with 18 000 synsets and 25 lemmata, alligned with other wordnets for other languages, including English Princeton WordNet."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-648"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "MWNPT - MultiWordNet of Portuguese"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/28fe5e97-4b7a-5a91-8e39-130e76a446f5.json b/oaitestdata/clarin-oai_dc/SET_1/json/28fe5e97-4b7a-5a91-8e39-130e76a446f5.json
deleted file mode 100644
index fdedfc41..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/28fe5e97-4b7a-5a91-8e39-130e76a446f5.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/285",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/285"
-    ],
-    "PID": "http://hdl.handle.net/11321/285",
-    "PublicationTimestamp": "2016-06-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "K\u0119dzia, Pawe\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/285;2016-06-03T13:33:30Z;hdl_11321_3;hdl_11321_4;Defender;K\u0119dzia, Pawe\u0142;parser;deepened parser;shallow parser;Deepened lexical parser into nominal phrase.;2016-06-01;toolService;http://hdl.handle.net/11321/285;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 1;Wroc\u0142aw University of Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "28fe5e97-4b7a-5a91-8e39-130e76a446f5",
-    "notes": [
-        "Deepened lexical parser into nominal phrase."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/285"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parser"
-        },
-        {
-            "name": "deepened parser"
-        },
-        {
-            "name": "shallow parser"
-        }
-    ],
-    "title": [
-        "Defender"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/291d4f3d-b31c-5c0c-ba5a-35fe064f2c15.json b/oaitestdata/clarin-oai_dc/SET_1/json/291d4f3d-b31c-5c0c-ba5a-35fe064f2c15.json
deleted file mode 100644
index eca5aa36..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/291d4f3d-b31c-5c0c-ba5a-35fe064f2c15.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish",
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/71",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/71"
-    ],
-    "PID": "http://hdl.handle.net/10794/71",
-    "PublicationTimestamp": "2015-04-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/71;2017-10-31T15:42:22Z;hdl_10794_1;hdl_10794_2;ASPAC \u2013 Swedish-Slovene (2017-10-16);ASPAC \u2013 svenska-slovenska (2017-10-16);n/a, n/a;ASPAC;Parallel;Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.;Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat.;2015-04-16;corpus;http://hdl.handle.net/10794/71;swe;slv;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/octet-stream;application/gzip;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/aspacsvsl",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "291d4f3d-b31c-5c0c-ba5a-35fe064f2c15",
-    "notes": [
-        "Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.",
-        "Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/71"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ASPAC"
-        },
-        {
-            "name": "Parallel"
-        }
-    ],
-    "title": [
-        "ASPAC \u2013 Swedish-Slovene (2017-10-16)",
-        "ASPAC \u2013 svenska-slovenska (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/291e38c4-d7b5-5dfe-adc6-6ef0630ab1f6.json b/oaitestdata/clarin-oai_dc/SET_1/json/291e38c4-d7b5-5dfe-adc6-6ef0630ab1f6.json
deleted file mode 100644
index 3e71695f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/291e38c4-d7b5-5dfe-adc6-6ef0630ab1f6.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=951aa0106c0411e2a2aa782bcb0741355b8c1b8dc35844d08dc1d9ff804c482a",
-    "MetadataAccess": [
-        "951aa0106c0411e2a2aa782bcb0741355b8c1b8dc35844d08dc1d9ff804c482a"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "951aa0106c0411e2a2aa782bcb0741355b8c1b8dc35844d08dc1d9ff804c482a;2018-11-15T16:40:09Z;toolService;toolService:service;U-Compare Syntactic Parsing Service;Web service created by exporting UIMA-based workflow from the U-Compare text mining system.\nFunctionality: Carries out syntactic parsing on plain text\nTools in workflow: Cafetiere Sentence Splitter (University of Manchester), OpenNLP Tokenizer (Apache), STEPP Tagger (University of Manchester), Enju Parser (University of Manchester)\nNOTE: The licence provided covers the web service only. Tools used to create the workflow may have their own licences\n;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "291e38c4-d7b5-5dfe-adc6-6ef0630ab1f6",
-    "notes": [
-        "Web service created by exporting UIMA-based workflow from the U-Compare text mining system.\nFunctionality: Carries out syntactic parsing on plain text\nTools in workflow: Cafetiere Sentence Splitter (University of Manchester), OpenNLP Tokenizer (Apache), STEPP Tagger (University of Manchester), Enju Parser (University of Manchester)\nNOTE: The licence provided covers the web service only. Tools used to create the workflow may have their own licences\n"
-    ],
-    "oai_identifier": [
-        "951aa0106c0411e2a2aa782bcb0741355b8c1b8dc35844d08dc1d9ff804c482a"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:service"
-    ],
-    "state": "active",
-    "title": [
-        "U-Compare Syntactic Parsing Service"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2926e8ac-0fca-53ea-8ab5-61855c052b91.json b/oaitestdata/clarin-oai_dc/SET_1/json/2926e8ac-0fca-53ea-8ab5-61855c052b91.json
deleted file mode 100644
index dc311f29..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2926e8ac-0fca-53ea-8ab5-61855c052b91.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Vizja Press&It"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/vnd.oasis.opendocument.text",
-        "downloadable_files_count: 11",
-        "application/zip",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/397",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/397"
-    ],
-    "PID": "http://hdl.handle.net/11321/397",
-    "PublicationTimestamp": "2017-02-03T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Vizja Press&It"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Jacennik, Barbara"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/397;2017-05-30T14:07:35Z;hdl_11321_3;hdl_11321_4;Sports supplements;Jacennik, Barbara;Jacennik, Barbara;Jacennik, Barbara;Health communication;Corpus of texts on dietary sports supplements.;2017-02-03;corpus;http://hdl.handle.net/11321/397;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;text/plain;text/plain;text/plain;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/msword;application/zip;downloadable_files_count: 11;Vizja Press&It",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2926e8ac-0fca-53ea-8ab5-61855c052b91",
-    "notes": [
-        "Corpus of texts on dietary sports supplements."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/397"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Health communication"
-        }
-    ],
-    "title": [
-        "Sports supplements"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2955e0b1-a392-59aa-99c5-054b3c0bcb3b.json b/oaitestdata/clarin-oai_dc/SET_1/json/2955e0b1-a392-59aa-99c5-054b3c0bcb3b.json
deleted file mode 100644
index c9025070..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2955e0b1-a392-59aa-99c5-054b3c0bcb3b.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Williams, Graham"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml",
-        "58 files: c. 578 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2545",
-    "MetadataAccess": [
-        "oai:ota:oucs:2545"
-    ],
-    "PublicationTimestamp": "1575-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1575"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Correspondence"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Williams, Graham"
-    ],
-    "fulltext": "oai:ota:oucs:2545;2018-03-01T11:09:46Z;http://ota.ox.ac.uk/headers/2545.xml;The Letters of Joan and Maria Thynne, 1575-1611;Williams, Graham;1575-1611;text_and_corpus_linguistics;eng;This resource is comprised of 52 diplomatic XML transcriptions of familiar letters, transcribed directly from their manuscript sources at Longleat Library, Wiltshire. The letters were written by two early modern women, Joan and Maria Thynne, between 1575-1611. Many of these were written by the women themselves, however, there are also scribal examples from Joan (an aspect of meta-data recorded in the XML). All the letters are written to family members (mostly husbands) and provide a rich source of information to do with language, social history and the composition of everyday women's letters in late Elizabethan/early Jacobean England. ;Oxford Text Archive, University of Oxford;Williams, Graham;text/xml;58 files: c. 578 KB;Text;Correspondence;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2955e0b1-a392-59aa-99c5-054b3c0bcb3b",
-    "notes": [
-        "This resource is comprised of 52 diplomatic XML transcriptions of familiar letters, transcribed directly from their manuscript sources at Longleat Library, Wiltshire. The letters were written by two early modern women, Joan and Maria Thynne, between 1575-1611. Many of these were written by the women themselves, however, there are also scribal examples from Joan (an aspect of meta-data recorded in the XML). All the letters are written to family members (mostly husbands) and provide a rich source of information to do with language, social history and the composition of everyday women's letters in late Elizabethan/early Jacobean England. "
-    ],
-    "oai_identifier": [
-        "oai:ota:oucs:2545"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The Letters of Joan and Maria Thynne, 1575-1611"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2545.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/295b577d-ebc3-5e19-8d7d-a07d42dc9327.json b/oaitestdata/clarin-oai_dc/SET_1/json/295b577d-ebc3-5e19-8d7d-a07d42dc9327.json
deleted file mode 100644
index c57b325a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/295b577d-ebc3-5e19-8d7d-a07d42dc9327.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "NLX-Natural Language and Speech Group, University of Lisbon"
-    ],
-    "Contributor": [
-        "Branco, Ant\u00f3nio",
-        "Silva, Jo\u00e3o"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Portuguese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1228",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1228"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1228",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "NLX-Natural Language and Speech Group, University of Lisbon"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Portugal"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1228;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LX-Suite;Branco, Ant\u00f3nio;Silva, Jo\u00e3o;LX-Suite is composed by a pipeline of the following tools: LX-Splitter, LX-Tokenizer, LX-Tagger, LX-Lemmatizer, and LX-Inflector.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1228;por;downloadable_files_count: 0;Portugal;NLX-Natural Language and Speech Group, University of Lisbon;http://lxsuite.di.fc.ul.pt",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "295b577d-ebc3-5e19-8d7d-a07d42dc9327",
-    "notes": [
-        "LX-Suite is composed by a pipeline of the following tools: LX-Splitter, LX-Tokenizer, LX-Tagger, LX-Lemmatizer, and LX-Inflector."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1228"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LX-Suite"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2964bb02-a7dc-5bf5-bc85-1416ed976801.json b/oaitestdata/clarin-oai_dc/SET_1/json/2964bb02-a7dc-5bf5-bc85-1416ed976801.json
deleted file mode 100644
index fae21bac..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2964bb02-a7dc-5bf5-bc85-1416ed976801.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Wroclaw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/14",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/14"
-    ],
-    "PID": "http://hdl.handle.net/11321/14",
-    "PublicationTimestamp": "2014-09-25T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Wroclaw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Walkowiak, Tomasz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/14;2014-09-25T13:07:29Z;hdl_11321_1;hdl_11321_2;WCRFT WebLichtService;Walkowiak, Tomasz;WCRFT service for WebLicht;2014-09-25;toolService;http://hdl.handle.net/11321/14;pol;application/octet-stream;application/octet-stream;downloadable_files_count: 0;Wroclaw University of Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2964bb02-a7dc-5bf5-bc85-1416ed976801",
-    "notes": [
-        "WCRFT service for WebLicht"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/14"
-    ],
-    "oai_set": [
-        "hdl_11321_1",
-        "hdl_11321_2"
-    ],
-    "state": "active",
-    "title": [
-        "WCRFT WebLichtService"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/29a63d0e-c273-5cdd-b9ff-bc1bfe04ff88.json b/oaitestdata/clarin-oai_dc/SET_1/json/29a63d0e-c273-5cdd-b9ff-bc1bfe04ff88.json
deleted file mode 100644
index 07185395..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/29a63d0e-c273-5cdd-b9ff-bc1bfe04ff88.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 1.82 MB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1495",
-    "MetadataAccess": [
-        "oai:ota:oucs:1495"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "United States. Central Intelligence Agency"
-    ],
-    "fulltext": "oai:ota:oucs:1495;2018-05-17T09:29:11Z;http://ota.ox.ac.uk/headers/1495.xml;The World factbook 1990 : electronic version;United States. Central Intelligence Agency;default: 1976-01-01;text_and_corpus_linguistics;Periodicals -- United States -- 20th century;Official gazettes -- United States -- 20th century;Yearbooks -- United States -- 20th century;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 1.82 MB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "29a63d0e-c273-5cdd-b9ff-bc1bfe04ff88",
-    "oai_identifier": [
-        "oai:ota:oucs:1495"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Periodicals -- United States -- th century"
-        },
-        {
-            "name": "Official gazettes -- United States -- th century"
-        },
-        {
-            "name": "Yearbooks -- United States -- th century"
-        }
-    ],
-    "title": [
-        "The World factbook 1990 : electronic version"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1495.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/29aa33c2-e1c5-52d0-b078-d70ea5c02e7f.json b/oaitestdata/clarin-oai_dc/SET_1/json/29aa33c2-e1c5-52d0-b078-d70ea5c02e7f.json
deleted file mode 100644
index 1938c3d1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/29aa33c2-e1c5-52d0-b078-d70ea5c02e7f.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Sygiety\u0144ski"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 3",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/94",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/94"
-    ],
-    "PID": "http://hdl.handle.net/11321/94",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Sygiety\u0144ski"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Sygiety\u0144ski, Sygiety\u0144ski"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/94;2015-04-08T13:38:09Z;hdl_11321_3;hdl_11321_4;MWE Sygiety\u0144ski;Sygiety\u0144ski, Sygiety\u0144ski;Sygiety\u0144ski;2015-04-08;corpus;http://hdl.handle.net/11321/94;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;text/plain; charset=utf-8;downloadable_files_count: 3;Sygiety\u0144ski",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "29aa33c2-e1c5-52d0-b078-d70ea5c02e7f",
-    "notes": [
-        "Sygiety\u0144ski"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/94"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Sygiety\u0144ski"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/29c048ee-05b5-5e8a-99b2-8c46d76152e8.json b/oaitestdata/clarin-oai_dc/SET_1/json/29c048ee-05b5-5e8a-99b2-8c46d76152e8.json
deleted file mode 100644
index a5832d55..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/29c048ee-05b5-5e8a-99b2-8c46d76152e8.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "University of Manchester"
-    ],
-    "Contributor": [
-        "Matras, Yaron"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-717",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-717"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-717",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Manchester"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-717;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;ROMLEX;Matras, Yaron;Lexical database covering 25 Romani dialects with translations into English and, for some dialects, other European languages.;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-717;downloadable_files_count: 0;United Kingdom;University of Manchester;http://romani.kfunigraz.ac.at/romlex/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "29c048ee-05b5-5e8a-99b2-8c46d76152e8",
-    "notes": [
-        "Lexical database covering 25 Romani dialects with translations into English and, for some dialects, other European languages."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-717"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "ROMLEX"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/29d5ebd2-8735-5c3d-8325-4e6b0eb46783.json b/oaitestdata/clarin-oai_dc/SET_1/json/29d5ebd2-8735-5c3d-8325-4e6b0eb46783.json
deleted file mode 100644
index 733e3987..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/29d5ebd2-8735-5c3d-8325-4e6b0eb46783.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 180 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1818",
-    "MetadataAccess": [
-        "oai:ota:oucs:1818"
-    ],
-    "PublicationTimestamp": "1903-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1903"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "London, Jack, 1876-1916"
-    ],
-    "fulltext": "oai:ota:oucs:1818;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/1818.xml;The call of the wild / Jack London;London, Jack, 1876-1916;1903;text_and_corpus_linguistics;American fiction -- 20th century;Oxford Text Archive, University of Oxford;Triggs, Jeffery;text/sgml;(1 file : ca. 180 KB);Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "29d5ebd2-8735-5c3d-8325-4e6b0eb46783",
-    "oai_identifier": [
-        "oai:ota:oucs:1818"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "American fiction -- th century"
-        }
-    ],
-    "title": [
-        "The call of the wild / Jack London"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1818.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2a39b055-5e01-5cc0-9a46-7c45c07e56e4.json b/oaitestdata/clarin-oai_dc/SET_1/json/2a39b055-5e01-5cc0-9a46-7c45c07e56e4.json
deleted file mode 100644
index 9dda228c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2a39b055-5e01-5cc0-9a46-7c45c07e56e4.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/115",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/115"
-    ],
-    "PID": "http://hdl.handle.net/10794/115",
-    "PublicationTimestamp": "2012-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/115;2017-11-01T16:36:23Z;hdl_10794_1;hdl_10794_2;Bonnier novels I (1976/77) (2017-10-04);Bonniersromaner I (1976/77) (2017-10-04);n/a, n/a;Swedish;Novels;A corpus of 69 Bonnier novels from 1976-77.\r\n\r\nThe material is sentence scrambled.;En korpus av 69 Bonniersromaner fr\u00e5n 1976-77. Materialet \u00e4r meningsomkastat.;2012-05-30;corpus;http://hdl.handle.net/10794/115;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/romi",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2a39b055-5e01-5cc0-9a46-7c45c07e56e4",
-    "notes": [
-        "A corpus of 69 Bonnier novels from 1976-77.\r\n\r\nThe material is sentence scrambled.",
-        "En korpus av 69 Bonniersromaner fr\u00e5n 1976-77. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/115"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Novels"
-        }
-    ],
-    "title": [
-        "Bonnier novels I (1976/77) (2017-10-04)",
-        "Bonniersromaner I (1976/77) (2017-10-04)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2a4b46b2-8ea7-517d-a753-ce9b8b2a6a23.json b/oaitestdata/clarin-oai_dc/SET_1/json/2a4b46b2-8ea7-517d-a753-ce9b8b2a6a23.json
deleted file mode 100644
index 6742a599..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2a4b46b2-8ea7-517d-a753-ce9b8b2a6a23.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Crane, Gregory, 1957-"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 378 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0069",
-    "MetadataAccess": [
-        "oai:ota:oucs:0069"
-    ],
-    "PublicationTimestamp": "1828-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1828"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Fiction"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Sherry, Charles",
-        "Hawthorne, Nathaniel, 1804-1864",
-        "Mitford, Mary Russell, 1787-1855"
-    ],
-    "fulltext": "oai:ota:oucs:0069;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0069.xml;Selections / Nathaniel Hawthorne, Charles Sherry and Mary Russell Mitford;Hawthorne, Nathaniel, 1804-1864;Sherry, Charles;Mitford, Mary Russell, 1787-1855;1828-64;text_and_corpus_linguistics;American fiction -- 19th century;eng;Oxford Text Archive, University of Oxford;Crane, Gregory, 1957-;text/plain;(1 file : ca. 378 KB);Text;Fiction;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2a4b46b2-8ea7-517d-a753-ce9b8b2a6a23",
-    "oai_identifier": [
-        "oai:ota:oucs:0069"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "American fiction -- th century"
-        }
-    ],
-    "title": [
-        "Selections / Nathaniel Hawthorne, Charles Sherry and Mary Russell Mitford"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0069.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2a520354-9ca6-5038-a426-573bb256136b.json b/oaitestdata/clarin-oai_dc/SET_1/json/2a520354-9ca6-5038-a426-573bb256136b.json
deleted file mode 100644
index 4e828e16..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2a520354-9ca6-5038-a426-573bb256136b.json
+++ /dev/null
@@ -1,106 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 16",
-        "text/plain",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Albanian",
-        "Bosnian",
-        "Bulgarian",
-        "Croatian",
-        "English",
-        "German",
-        "Hungarian",
-        "Polish",
-        "Portuguese",
-        "Serbian",
-        "Russian",
-        "Slovak",
-        "Slovenian",
-        "Spanish",
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1054",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1054"
-    ],
-    "PID": "http://hdl.handle.net/11356/1054",
-    "PublicationTimestamp": "2016-02-23T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/610704",
-        "info:eu-repo/grantAgreement/EC/FP7/317532",
-        "info:eu-repo/grantAgreement/EC/H2020/640772",
-        "https://dx.doi.org/10.1371/journal.pone.0155036",
-        "https://dx.doi.org/10.1371/journal.pone.0194317"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "https://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Mozeti\u010d, Igor",
-        "Gr\u010dar, Miha",
-        "Smailovi\u0107, Jasmina"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1054;2018-05-28T11:33:21Z;hdl_11356_1023;hdl_11356_1024;Twitter sentiment for 15 European languages;Mozeti\u010d, Igor;Gr\u010dar, Miha;Smailovi\u0107, Jasmina;sentiment classification;Twitter;inter-annotator agreement;annotator self-agreement;multilingual;The dataset contains over 1.6 million tweets (tweet IDs), labeled with sentiment by human annotators.\r\nThere are 15 Twitter corpora for the corresponding 15 European languages. The data can be used to train and evaluate Twitter sentiment classifiers, to compute annotator agreement, or to study the differences between language usage on Twitter.\r\n\r\nThe data analysis is described in the following papers:\r\n\r\nI. Mozeti\u010d, M. Gr\u010dar, J. Smailovi\u0107. Multilingual Twitter sentiment classification: The role of human annotators, PLoS ONE 11(5): e0155036, doi: 10.1371/journal.pone.e0155036, 2016.\r\n(http://dx.doi.org/10.1371/journal.pone.0155036)\r\n\r\nI. Mozeti\u010d, L. Torgo, V. Cerqueira, J. Smailovi\u0107. How to evaluate sentiment classifiers for Twitter time-ordered data?, PLoS ONE 13(3): e0194317, doi: 10.1371/journal.pone.0194317, 2018.\r\n(https://dx.doi.org/10.1371/journal.pone.0194317);2016-02-23;corpus;http://hdl.handle.net/11356/1054;sqi;bos;bul;hrv;eng;deu;hun;pol;por;srp;rus;slk;slv;spa;swe;info:eu-repo/grantAgreement/EC/FP7/610704;info:eu-repo/grantAgreement/EC/FP7/317532;info:eu-repo/grantAgreement/EC/H2020/640772;https://dx.doi.org/10.1371/journal.pone.0155036;https://dx.doi.org/10.1371/journal.pone.0194317;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);https://creativecommons.org/licenses/by-sa/4.0/;PUB;text/plain;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 16;Jo\u017eef Stefan Institute",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2a520354-9ca6-5038-a426-573bb256136b",
-    "notes": [
-        "The dataset contains over 1.6 million tweets (tweet IDs), labeled with sentiment by human annotators.\r\nThere are 15 Twitter corpora for the corresponding 15 European languages. The data can be used to train and evaluate Twitter sentiment classifiers, to compute annotator agreement, or to study the differences between language usage on Twitter.\r\n\r\nThe data analysis is described in the following papers:\r\n\r\nI. Mozeti\u010d, M. Gr\u010dar, J. Smailovi\u0107. Multilingual Twitter sentiment classification: The role of human annotators, PLoS ONE 11(5): e0155036, doi: 10.1371/journal.pone.e0155036, 2016.\r\n(http://dx.doi.org/10.1371/journal.pone.0155036)\r\n\r\nI. Mozeti\u010d, L. Torgo, V. Cerqueira, J. Smailovi\u0107. How to evaluate sentiment classifiers for Twitter time-ordered data?, PLoS ONE 13(3): e0194317, doi: 10.1371/journal.pone.0194317, 2018.\r\n(https://dx.doi.org/10.1371/journal.pone.0194317)"
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1054"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "sentiment classification"
-        },
-        {
-            "name": "Twitter"
-        },
-        {
-            "name": "inter-annotator agreement"
-        },
-        {
-            "name": "annotator self-agreement"
-        },
-        {
-            "name": "multilingual"
-        }
-    ],
-    "title": [
-        "Twitter sentiment for 15 European languages"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2a665ec0-dd7f-5e9c-9df4-b068926ecdbb.json b/oaitestdata/clarin-oai_dc/SET_1/json/2a665ec0-dd7f-5e9c-9df4-b068926ecdbb.json
deleted file mode 100644
index aba0ba80..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2a665ec0-dd7f-5e9c-9df4-b068926ecdbb.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 464 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1945",
-    "MetadataAccess": [
-        "oai:ota:oucs:1945"
-    ],
-    "PublicationTimestamp": "1871-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1871"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "MacDonald, George, 1824-1905"
-    ],
-    "fulltext": "oai:ota:oucs:1945;2018-04-16T14:11:10Z;http://ota.ox.ac.uk/headers/1945.xml;At the back of the north wind / by George MacDonald;MacDonald, George, 1824-1905;1871;text_and_corpus_linguistics;Juvenile literature -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 464 KB);Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2a665ec0-dd7f-5e9c-9df4-b068926ecdbb",
-    "oai_identifier": [
-        "oai:ota:oucs:1945"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Juvenile literature -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "At the back of the north wind / by George MacDonald"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1945.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2a88a8b5-dac9-599f-94eb-4a0f2671301a.json b/oaitestdata/clarin-oai_dc/SET_1/json/2a88a8b5-dac9-599f-94eb-4a0f2671301a.json
deleted file mode 100644
index 7c6e990d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2a88a8b5-dac9-599f-94eb-4a0f2671301a.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Polish-Japanese Academy of Information Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/527",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/527"
-    ],
-    "PID": "http://hdl.handle.net/11321/527",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Polish-Japanese Academy of Information Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Wo\u0142k, Krzysztof",
-        "Marasek, Krzysztof",
-        "Brocki, \u0141ukasz",
-        "Kor\u017einek, Danijel"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/527;2018-07-17T18:34:43Z;hdl_11321_3;hdl_11321_4;Transcriptions of the Polish Film Chronicles (Polska Kronika Filmowa) - years 1945-1962;Kor\u017einek, Danijel;Marasek, Krzysztof;Brocki, \u0141ukasz;Wo\u0142k, Krzysztof;orthographic transcription of speech;hand checked;This is the orthographic transcription of the audio of the Polish Film Chronicles (Polska Kronika Filmowa - PKF) between the years 1945-1962. The transcription is mostly hand-checked and should match the audio to a high degree. Only the narrator is transcribed (which is the vast majority of all speech in the recordings).;2018-07-01;corpus;http://hdl.handle.net/11321/527;pol;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;text/plain;downloadable_files_count: 1;Polish-Japanese Academy of Information Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2a88a8b5-dac9-599f-94eb-4a0f2671301a",
-    "notes": [
-        "This is the orthographic transcription of the audio of the Polish Film Chronicles (Polska Kronika Filmowa - PKF) between the years 1945-1962. The transcription is mostly hand-checked and should match the audio to a high degree. Only the narrator is transcribed (which is the vast majority of all speech in the recordings)."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/527"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "orthographic transcription speech"
-        },
-        {
-            "name": "hand checked"
-        }
-    ],
-    "title": [
-        "Transcriptions of the Polish Film Chronicles (Polska Kronika Filmowa) - years 1945-1962"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2aad099e-658a-57ea-8f6d-9835f45f2298.json b/oaitestdata/clarin-oai_dc/SET_1/json/2aad099e-658a-57ea-8f6d-9835f45f2298.json
deleted file mode 100644
index 231db3b7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2aad099e-658a-57ea-8f6d-9835f45f2298.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "University of Lisbon, CLUL-Centro de Lingu\u00edstica da Universidade de Lisboa"
-    ],
-    "Contributor": [
-        "Mendes, Am\u00e1lia"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Portuguese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-392",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-392"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-392",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Lisbon, CLUL-Centro de Lingu\u00edstica da Universidade de Lisboa"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Portugal"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-392;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;PAROLE Portuguese Corpus;Mendes, Am\u00e1lia;News;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-392;por;downloadable_files_count: 0;Portugal;University of Lisbon, CLUL-Centro de Lingu\u00edstica da Universidade de Lisboa;http://www.elda.org/catalogue/en/text/W0024.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2aad099e-658a-57ea-8f6d-9835f45f2298",
-    "notes": [
-        "News"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-392"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "PAROLE Portuguese Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2ab46146-f9dc-5be7-9287-c1ab6f1742b5.json b/oaitestdata/clarin-oai_dc/SET_1/json/2ab46146-f9dc-5be7-9287-c1ab6f1742b5.json
deleted file mode 100644
index f3165ddc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2ab46146-f9dc-5be7-9287-c1ab6f1742b5.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Seidel-Grzesi\u0144ska, Agnieszka"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "downloadable_files_count: 70"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/494",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/494"
-    ],
-    "PID": "http://hdl.handle.net/11321/494",
-    "PublicationTimestamp": "2018-06-19T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Seidel-Grzesi\u0144ska, Agnieszka"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Super Cool License",
-        "http://www.google.com",
-        "ACA"
-    ],
-    "author": [
-        "Seidel-Grzesi\u0144ska, Agnieszka"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/494;2018-06-19T11:20:11Z;hdl_11321_3;hdl_11321_4;Protestant Architecture Bohemia;Seidel-Grzesi\u0144ska, Agnieszka;architecture baroque protestants;Research Project : Protestant Building in Europe in Baroque;2018-06-19;corpus;http://hdl.handle.net/11321/494;pol;Super Cool License;http://www.google.com;ACA;text/plain; charset=utf-8;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;downloadable_files_count: 70;Seidel-Grzesi\u0144ska, Agnieszka",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2ab46146-f9dc-5be7-9287-c1ab6f1742b5",
-    "notes": [
-        "Research Project : Protestant Building in Europe in Baroque"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/494"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "architecture baroque protestants"
-        }
-    ],
-    "title": [
-        "Protestant Architecture Bohemia"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2aca1429-b2a6-5fc1-9085-26f579f74d77.json b/oaitestdata/clarin-oai_dc/SET_1/json/2aca1429-b2a6-5fc1-9085-26f579f74d77.json
deleted file mode 100644
index 0c6275d5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2aca1429-b2a6-5fc1-9085-26f579f74d77.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-73",
-    "MetadataAccess": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-73"
-    ],
-    "PID": "http://hdl.handle.net/20.500.11752/ILC-73",
-    "PublicationTimestamp": "2016-10-18T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/296451"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0",
-        "PUB"
-    ],
-    "author": [
-        "Russo, Irene",
-        "Quochi, Valeria",
-        "Frontini, Francesca"
-    ],
-    "fulltext": "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-73;2018-07-23T09:13:44Z;hdl_000-c0-111_38;hdl_000-c0-111_49;OpeNER Sentiment Lexicon Italian - LMF;Russo, Irene;Frontini, Francesca;Quochi, Valeria;Sentiment analysis;Polarity;Computational lexicon;Il Lessico Italiano dei Sentimenti \u00e8 stato sviluppato in modo semi-automatico da ItalWordNet v.2 partendo da una lista di 1.000 parole-chiave controllate manualmente. Contiene 24.293 entrate lessicali annotate con polarit\u00e0 positiva/negativa/neutra. E' distribuito in formato LMF.\r\n\r\nThe Italian Sentiment Lexicon was semi-automatically developed from ItalWordNet v.2 starting from a list of seed key-words classified manually. It contains 24.293 lexical entries annotated for positive/negative/neutral polarity. It is distributed in XML-LMF format.;2016-10-18;lexicalConceptualResource;http://hdl.handle.net/20.500.11752/ILC-73;ita;info:eu-repo/grantAgreement/EC/FP7/296451;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR);http://www.opener-project.eu",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2aca1429-b2a6-5fc1-9085-26f579f74d77",
-    "notes": [
-        "Il Lessico Italiano dei Sentimenti \u00e8 stato sviluppato in modo semi-automatico da ItalWordNet v.2 partendo da una lista di 1.000 parole-chiave controllate manualmente. Contiene 24.293 entrate lessicali annotate con polarit\u00e0 positiva/negativa/neutra. E' distribuito in formato LMF.\r\n\r\nThe Italian Sentiment Lexicon was semi-automatically developed from ItalWordNet v.2 starting from a list of seed key-words classified manually. It contains 24.293 lexical entries annotated for positive/negative/neutral polarity. It is distributed in XML-LMF format."
-    ],
-    "oai_identifier": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-73"
-    ],
-    "oai_set": [
-        "hdl_000-c0-111_38",
-        "hdl_000-c0-111_49"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Sentiment analysis"
-        },
-        {
-            "name": "Polarity"
-        },
-        {
-            "name": "Computational lexicon"
-        }
-    ],
-    "title": [
-        "OpeNER Sentiment Lexicon Italian - LMF"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2ad11a46-af43-5019-8e50-9ae6c10079db.json b/oaitestdata/clarin-oai_dc/SET_1/json/2ad11a46-af43-5019-8e50-9ae6c10079db.json
deleted file mode 100644
index b072aa61..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2ad11a46-af43-5019-8e50-9ae6c10079db.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Universit\u00e0 di Parma"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
-    ],
-    "Language": [
-        "Italian",
-        "Ancient Greek (to 1453)",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/OPEN-86",
-    "MetadataAccess": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/OPEN-86"
-    ],
-    "PID": "http://hdl.handle.net/20.500.11752/OPEN-86",
-    "PublicationTimestamp": "2017-10-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Universit\u00e0 di Parma"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Stefanini, Alberto",
-        "Monachini, Monica",
-        "Nicolosi, Anika"
-    ],
-    "fulltext": "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/OPEN-86;2018-07-23T09:13:44Z;hdl_000-c0-111_39;hdl_000-c0-111_43;Survey Data: Current practice of digital resources and tools for studies on Digital Classics;Nicolosi, Anika;Monachini, Monica;Stefanini, Alberto;Survey data;Digital classics;Users' needs;This dataset contains the original responses to a questionnaire run from May to September 2016 on a sample of Italian digital humanists with focus of interest on ancient Greek philology about Current practice of digital resources and tools for studies on Digital Classics: namely Ancient Greek. The survey is now available on-line at \r\nhttp://www.clarin-it.it/it/content/sondaggio-current-practice-digital-classics-tools.\r\n\r\nThe majority of questions were closed questions where respondents had to tick a box, occasionally multiple choice was allowed. A few questions required free text provision. The questionnaire was designed using 'Google Forms' and was run on the same platform in the autumn 2016. \r\n\r\nThe results of the survey are briefly presented to the CLARIN Annual Conference 2017 (18-21 September 2017, Budapest). Abstracts available here: \r\nhttps://www.clarin.eu/sites/default/files/Monachini-Nicolosi-Stefanini-CLARIN2017_paper_3.pdf.;2017-10-31;corpus;http://hdl.handle.net/20.500.11752/OPEN-86;ita;grc;eng;Creative Commons - Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0);http://creativecommons.org/licenses/by-nc-nd/4.0/;PUB;application/vnd.openxmlformats-officedocument.spreadsheetml.sheet;text/plain; charset=utf-8;downloadable_files_count: 1;Universit\u00e0 di Parma",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2ad11a46-af43-5019-8e50-9ae6c10079db",
-    "notes": [
-        "This dataset contains the original responses to a questionnaire run from May to September 2016 on a sample of Italian digital humanists with focus of interest on ancient Greek philology about Current practice of digital resources and tools for studies on Digital Classics: namely Ancient Greek. The survey is now available on-line at \r\nhttp://www.clarin-it.it/it/content/sondaggio-current-practice-digital-classics-tools.\r\n\r\nThe majority of questions were closed questions where respondents had to tick a box, occasionally multiple choice was allowed. A few questions required free text provision. The questionnaire was designed using 'Google Forms' and was run on the same platform in the autumn 2016. \r\n\r\nThe results of the survey are briefly presented to the CLARIN Annual Conference 2017 (18-21 September 2017, Budapest). Abstracts available here: \r\nhttps://www.clarin.eu/sites/default/files/Monachini-Nicolosi-Stefanini-CLARIN2017_paper_3.pdf."
-    ],
-    "oai_identifier": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/OPEN-86"
-    ],
-    "oai_set": [
-        "hdl_000-c0-111_39",
-        "hdl_000-c0-111_43"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Survey data"
-        },
-        {
-            "name": "Digital classics"
-        },
-        {
-            "name": "Users needs"
-        }
-    ],
-    "title": [
-        "Survey Data: Current practice of digital resources and tools for studies on Digital Classics"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2ad37d10-27fb-5597-a319-1d79bc1dca84.json b/oaitestdata/clarin-oai_dc/SET_1/json/2ad37d10-27fb-5597-a319-1d79bc1dca84.json
deleted file mode 100644
index 4742e0c5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2ad37d10-27fb-5597-a319-1d79bc1dca84.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 5",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "English",
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1459",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1459"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1459",
-    "PublicationTimestamp": "2014-11-21T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-1450"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU General Public License, version 2",
-        "http://www.gnu.org/licenses/gpl-2.0.html",
-        "PUB"
-    ],
-    "author": [
-        "Rosa, Rudolf"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1459;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Fairytale child (2014-11-21);Rosa, Rudolf;dialogue system;morphological generation;Treex;morphological analysis;interactive;Fairytale Child is a simple chatbot trying to simulate a curious child. It asks the user to tell a fairy tale, often interrupting to ask for details and clarifications. However, it remembers what it was told and tries to show it if possible.\r\n\r\nThe chatbot can communicate in Czech and in English. It analyzes the morphology of each sentence produced by the user with natural language processing tools, tries to identify potential questions to ask, and then asks one. A morphological generator is employed to generate correctly inflected sentences in Czech, so that the resulting sentences sound as natural as possible.\r\n\r\nPoh\u00e1dkov\u00e9 d\u00edt\u011b je jednoduch\u00fd chatbot, simuluj\u00edc\u00ed zv\u00eddav\u00e9 d\u00edt\u011b. Po\u017e\u00e1d\u00e1 u\u017eivatele, aby mu vypr\u00e1v\u011bl poh\u00e1dku, ale \u010dasto ho p\u0159eru\u0161uje, aby se zeptal na detaily a vysv\u011btlen\u00ed. Pamatuje si ale, co mu u\u017eivatel \u0159ekl, a sna\u017e\u00ed se to pokud mo\u017eno d\u00e1t najevo.\r\n\r\nChatbot um\u00ed komunikovat \u010desky a anglicky. Analyzuje tvaroslov\u00ed ka\u017ed\u00e9 u\u017eivatelovy v\u011bty pomoc\u00ed NLP n\u00e1stroj\u016f, pokus\u00ed se nal\u00e9zt chodnou ot\u00e1zku, a tu pak polo\u017e\u00ed. Aby tvo\u0159en\u00e9 \u010desk\u00e9 v\u011bty zn\u011bly co nejp\u0159irozen\u011bji, vyu\u017e\u00edv\u00e1 se pro sklo\u0148ov\u00e1n\u00ed tvaroslovn\u00fd gener\u00e1tor.;2014-11-21;toolService;http://hdl.handle.net/11234/1-1459;eng;ces;http://hdl.handle.net/11234/1-1450;GNU General Public License, version 2;http://www.gnu.org/licenses/gpl-2.0.html;PUB;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 5;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://ufal.mff.cuni.cz/dite",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2ad37d10-27fb-5597-a319-1d79bc1dca84",
-    "notes": [
-        "Fairytale Child is a simple chatbot trying to simulate a curious child. It asks the user to tell a fairy tale, often interrupting to ask for details and clarifications. However, it remembers what it was told and tries to show it if possible.\r\n\r\nThe chatbot can communicate in Czech and in English. It analyzes the morphology of each sentence produced by the user with natural language processing tools, tries to identify potential questions to ask, and then asks one. A morphological generator is employed to generate correctly inflected sentences in Czech, so that the resulting sentences sound as natural as possible.\r\n\r\nPoh\u00e1dkov\u00e9 d\u00edt\u011b je jednoduch\u00fd chatbot, simuluj\u00edc\u00ed zv\u00eddav\u00e9 d\u00edt\u011b. Po\u017e\u00e1d\u00e1 u\u017eivatele, aby mu vypr\u00e1v\u011bl poh\u00e1dku, ale \u010dasto ho p\u0159eru\u0161uje, aby se zeptal na detaily a vysv\u011btlen\u00ed. Pamatuje si ale, co mu u\u017eivatel \u0159ekl, a sna\u017e\u00ed se to pokud mo\u017eno d\u00e1t najevo.\r\n\r\nChatbot um\u00ed komunikovat \u010desky a anglicky. Analyzuje tvaroslov\u00ed ka\u017ed\u00e9 u\u017eivatelovy v\u011bty pomoc\u00ed NLP n\u00e1stroj\u016f, pokus\u00ed se nal\u00e9zt chodnou ot\u00e1zku, a tu pak polo\u017e\u00ed. Aby tvo\u0159en\u00e9 \u010desk\u00e9 v\u011bty zn\u011bly co nejp\u0159irozen\u011bji, vyu\u017e\u00edv\u00e1 se pro sklo\u0148ov\u00e1n\u00ed tvaroslovn\u00fd gener\u00e1tor."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1459"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "dialogue system"
-        },
-        {
-            "name": "morphological generation"
-        },
-        {
-            "name": "Treex"
-        },
-        {
-            "name": "morphological analysis"
-        },
-        {
-            "name": "interactive"
-        }
-    ],
-    "title": [
-        "Fairytale child (2014-11-21)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2b1f37a0-be21-501a-9dc3-e094356538d1.json b/oaitestdata/clarin-oai_dc/SET_1/json/2b1f37a0-be21-501a-9dc3-e094356538d1.json
deleted file mode 100644
index e827ea5c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2b1f37a0-be21-501a-9dc3-e094356538d1.json
+++ /dev/null
@@ -1,107 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "text/plain",
-        "downloadable_files_count: 2"
-    ],
-    "Language": [
-        "English",
-        "Czech",
-        "French",
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-866E-1",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-866E-1"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-866E-1",
-    "PublicationTimestamp": "2014-04-28T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/257528",
-        "http://hdl.handle.net/11234/1-2122"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0)",
-        "http://creativecommons.org/licenses/by-nc/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Haji\u010d, Jan",
-        "Du\u0161ek, Ond\u0159ej",
-        "Ure\u0161ov\u00e1, Zde\u0148ka",
-        "Hlav\u00e1\u010dov\u00e1, Jaroslava",
-        "Pecina, Pavel",
-        "Tamchyna, Ale\u0161"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-866E-1;2018-07-02T22:05:53Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Khresmoi Summary Translation Test Data 1.1;Du\u0161ek, Ond\u0159ej;Haji\u010d, Jan;Hlav\u00e1\u010dov\u00e1, Jaroslava;Pecina, Pavel;Tamchyna, Ale\u0161;Ure\u0161ov\u00e1, Zde\u0148ka;corpus;test data;medical;health;machine translation;Czech;French;German;English;This package contains data sets for development and testing of machine translation of sentences from summaries of medical articles between Czech, English, French, and German.;2014-04-28;corpus;http://hdl.handle.net/11858/00-097C-0000-0023-866E-1;eng;ces;fra;deu;info:eu-repo/grantAgreement/EC/FP7/257528;http://hdl.handle.net/11234/1-2122;Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0);http://creativecommons.org/licenses/by-nc/3.0/;PUB;application/x-gzip;text/plain;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://khresmoi.eu/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2b1f37a0-be21-501a-9dc3-e094356538d1",
-    "notes": [
-        "This package contains data sets for development and testing of machine translation of sentences from summaries of medical articles between Czech, English, French, and German."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-866E-1"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "test data"
-        },
-        {
-            "name": "medical"
-        },
-        {
-            "name": "health"
-        },
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "Czech"
-        },
-        {
-            "name": "French"
-        },
-        {
-            "name": "German"
-        },
-        {
-            "name": "English"
-        }
-    ],
-    "title": [
-        "Khresmoi Summary Translation Test Data 1.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2b294f2b-c9c1-5ba9-8e0f-a10068c25851.json b/oaitestdata/clarin-oai_dc/SET_1/json/2b294f2b-c9c1-5ba9-8e0f-a10068c25851.json
deleted file mode 100644
index ea52d3c7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2b294f2b-c9c1-5ba9-8e0f-a10068c25851.json
+++ /dev/null
@@ -1,49 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5597",
-    "MetadataAccess": [
-        "oai:ota:oucs:5597"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:5597;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5597.xml;An essay pointing out the cause, effects and method of treating the present epidemic fever: In a letter to a young physician.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2b294f2b-c9c1-5ba9-8e0f-a10068c25851",
-    "oai_identifier": [
-        "oai:ota:oucs:5597"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An essay pointing out the cause, effects and method of treating the present epidemic fever: In a letter to a young physician."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5597.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2b30572a-07b7-5698-9761-042589ee28d5.json b/oaitestdata/clarin-oai_dc/SET_1/json/2b30572a-07b7-5698-9761-042589ee28d5.json
deleted file mode 100644
index 3fea4b1e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2b30572a-07b7-5698-9761-042589ee28d5.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Przemys\u0142aw \u017bukiewicz",
-        "Rafa\u0142 Zimny",
-        "Jan Wieczorek"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/602",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/602"
-    ],
-    "PID": "http://hdl.handle.net/11321/602",
-    "PublicationTimestamp": "2018-09-11T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Przemys\u0142aw \u017bukiewicz",
-        "Rafa\u0142 Zimny",
-        "Jan Wieczorek"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11321/599"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN-EULA-ACA-v1.0",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca",
-        "ACA"
-    ],
-    "author": [
-        "Wieczorek, Jan",
-        "Zimny, Rafa\u0142",
-        "\u017bukiewicz, Przemys\u0142aw"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/602;2018-09-18T11:15:05Z;hdl_11321_3;hdl_11321_478;Korpus przem\u00f3wie\u0144 noworocznych (2018-09-18);Zimny, Rafa\u0142;\u017bukiewicz, Przemys\u0142aw;Wieczorek, Jan;przem\u00f3wienia;polityka;Fragment korpusu polskich przem\u00f3wie\u0144 politycznych;2018-09-11;corpus;http://hdl.handle.net/11321/602;pol;http://hdl.handle.net/11321/599;CLARIN-EULA-ACA-v1.0;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca;ACA;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;Jan Wieczorek;Rafa\u0142 Zimny;Przemys\u0142aw \u017bukiewicz",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2b30572a-07b7-5698-9761-042589ee28d5",
-    "notes": [
-        "Fragment korpusu polskich przem\u00f3wie\u0144 politycznych"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/602"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_478"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "polityka"
-        }
-    ],
-    "title": [
-        "Korpus przem\u00f3wie\u0144 noworocznych (2018-09-18)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2b462d45-3e76-5069-8dde-4b2edcc8b066.json b/oaitestdata/clarin-oai_dc/SET_1/json/2b462d45-3e76-5069-8dde-4b2edcc8b066.json
deleted file mode 100644
index 76de4c68..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2b462d45-3e76-5069-8dde-4b2edcc8b066.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1037",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1037"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1037",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1037;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;L1 Acquisition Penelope Brown Tzeltal;Language Acquisition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1037;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI236%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2b462d45-3e76-5069-8dde-4b2edcc8b066",
-    "notes": [
-        "Language Acquisition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1037"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "L1 Acquisition Penelope Brown Tzeltal"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2b694f2b-09a7-5f94-a77f-476001c4605f.json b/oaitestdata/clarin-oai_dc/SET_1/json/2b694f2b-09a7-5f94-a77f-476001c4605f.json
deleted file mode 100644
index a73ca3c6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2b694f2b-09a7-5f94-a77f-476001c4605f.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 32.1 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1870",
-    "MetadataAccess": [
-        "oai:ota:oucs:1870"
-    ],
-    "PublicationTimestamp": "1914-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1914"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Short stories"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Stoker, Bram, 1847-1912"
-    ],
-    "fulltext": "oai:ota:oucs:1870;2018-04-11T16:03:39Z;http://ota.ox.ac.uk/headers/1870.xml;Dracula's guest : 1914 / by Bram Stoker;Stoker, Bram, 1847-1912;1914;text_and_corpus_linguistics;Fiction -- Great Britain -- 20th century;Short stories -- Great Britain -- 20th century;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 32.1 KB);Text;Short stories;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2b694f2b-09a7-5f94-a77f-476001c4605f",
-    "oai_identifier": [
-        "oai:ota:oucs:1870"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- Great Britain -- th century"
-        },
-        {
-            "name": "Short stories -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Dracula's guest : 1914 / by Bram Stoker"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1870.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2b6ff424-d97c-5ccc-b184-fe840efaf311.json b/oaitestdata/clarin-oai_dc/SET_1/json/2b6ff424-d97c-5ccc-b184-fe840efaf311.json
deleted file mode 100644
index 2e7944e7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2b6ff424-d97c-5ccc-b184-fe840efaf311.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Slovenian",
-        "Croatian",
-        "Serbian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1157",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1157"
-    ],
-    "PID": "http://hdl.handle.net/11356/1157",
-    "PublicationTimestamp": "2017-09-29T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "http://www.lrec-conf.org/proceedings/lrec2016/summaries/811.html"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Erjavec, Toma\u017e",
-        "Perov\u0161ek, Matic",
-        "Ljube\u0161i\u0107, Nikola"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1157;2019-02-23T17:33:02Z;hdl_11356_1023;hdl_11356_1077;ReLDI tag+lemma web service for WebLicht;Ljube\u0161i\u0107, Nikola;Perov\u0161ek, Matic;Erjavec, Toma\u017e;tagging;lemmatisation;WebLicht (https://weblicht.sfs.uni-tuebingen.de/) registry entry for webservice comprising tokenisation, PoS tagging, and lemmatisation.;2017-09-29;toolService;http://hdl.handle.net/11356/1157;slv;hrv;srp;http://www.lrec-conf.org/proceedings/lrec2016/summaries/811.html;application/octet-stream;downloadable_files_count: 0;Jo\u017eef Stefan Institute;https://github.com/clarinsi",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2b6ff424-d97c-5ccc-b184-fe840efaf311",
-    "notes": [
-        "WebLicht (https://weblicht.sfs.uni-tuebingen.de/) registry entry for webservice comprising tokenisation, PoS tagging, and lemmatisation."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1157"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1077"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "lemmatisation"
-        }
-    ],
-    "title": [
-        "ReLDI tag+lemma web service for WebLicht"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2b8184b0-f832-55b2-9038-9ab9469c4c72.json b/oaitestdata/clarin-oai_dc/SET_1/json/2b8184b0-f832-55b2-9038-9ab9469c4c72.json
deleted file mode 100644
index be2348b5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2b8184b0-f832-55b2-9038-9ab9469c4c72.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Center for Information and Language Processing, University of Munich"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 4",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/LRT-1484",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/LRT-1484"
-    ],
-    "PID": "http://hdl.handle.net/11234/LRT-1484",
-    "PublicationTimestamp": "2015-03-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center for Information and Language Processing, University of Munich"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "M\u00fcller, Thomas",
-        "Sch\u00fctze, Hinrich",
-        "Caratti, Francesca",
-        "Recknagel, Arne"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/LRT-1484;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;A morphological layer for the German part of the SMULTRON corpus;M\u00fcller, Thomas;Sch\u00fctze, Hinrich;Caratti, Francesca;Recknagel, Arne;morphology;morphological tagging;PoS tagging;A morphological layer for the German part of the SMULTRON corpus. Layer was annotated according to the STTS tagset and the annotation guidelines of the Tiger corpus.\r\n\r\nCoordinator: Thomas M\u00fcller\r\nAnnotators: Francesca Caratti, Arne Recknagel\r\n\r\nThis distribution contains a morphological layer for the SMULTRON corpus [0].\r\nThe annotation process is described in :\r\n\r\n@InProceedings{mueller2015,\r\n  author = {M\\\"uller, Thomas and Sch\\\"utze, Hinrich},\r\n  title = {Robust Morphological Tagging with Word Representations},\r\n  booktitle = {Proceedings of NAACL},\r\n  year = {2015},\r\n}\r\n\r\n[0] http://www.cl.uzh.ch/research/parallelcorpora/paralleltreebanks/smultron_en.html;2015-03-01;corpus;http://hdl.handle.net/11234/LRT-1484;deu;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;PUB;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 4;Center for Information and Language Processing, University of Munich;http://cistern.cis.lmu.de/marmot/naacl2015/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2b8184b0-f832-55b2-9038-9ab9469c4c72",
-    "notes": [
-        "A morphological layer for the German part of the SMULTRON corpus. Layer was annotated according to the STTS tagset and the annotation guidelines of the Tiger corpus.\r\n\r\nCoordinator: Thomas M\u00fcller\r\nAnnotators: Francesca Caratti, Arne Recknagel\r\n\r\nThis distribution contains a morphological layer for the SMULTRON corpus [0].\r\nThe annotation process is described in :\r\n\r\n@InProceedings{mueller2015,\r\n  author = {M\\\"uller, Thomas and Sch\\\"utze, Hinrich},\r\n  title = {Robust Morphological Tagging with Word Representations},\r\n  booktitle = {Proceedings of NAACL},\r\n  year = {2015},\r\n}\r\n\r\n[0] http://www.cl.uzh.ch/research/parallelcorpora/paralleltreebanks/smultron_en.html"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/LRT-1484"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "morphological tagging"
-        },
-        {
-            "name": "PoS tagging"
-        }
-    ],
-    "title": [
-        "A morphological layer for the German part of the SMULTRON corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2b961a00-2b72-5e43-846a-8d2027c76a5b.json b/oaitestdata/clarin-oai_dc/SET_1/json/2b961a00-2b72-5e43-846a-8d2027c76a5b.json
deleted file mode 100644
index 2edc84e4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2b961a00-2b72-5e43-846a-8d2027c76a5b.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 79.3 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1565",
-    "MetadataAccess": [
-        "oai:ota:oucs:1565"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Fielding, Henry, 1707-1754"
-    ],
-    "fulltext": "oai:ota:oucs:1565;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/1565.xml;Shamela;Fielding, Henry, 1707-1754;default: 1976-01-01;text_and_corpus_linguistics;Fiction -- Great Britain -- 18th century;Novels -- Great Britain -- 18th century;Parodies -- Great Britain -- 18th century;eng;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 79.3 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2b961a00-2b72-5e43-846a-8d2027c76a5b",
-    "oai_identifier": [
-        "oai:ota:oucs:1565"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- Great Britain -- th century"
-        },
-        {
-            "name": "Novels -- Great Britain -- th century"
-        },
-        {
-            "name": "Parodies -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Shamela"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1565.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2bc265d6-f16c-5600-b67b-d3e4ed089eb4.json b/oaitestdata/clarin-oai_dc/SET_1/json/2bc265d6-f16c-5600-b67b-d3e4ed089eb4.json
deleted file mode 100644
index 039c7f35..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2bc265d6-f16c-5600-b67b-d3e4ed089eb4.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1155",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1155"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1155",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1155;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Bilder-Conversations-Lexikon;Germanistik;digitale Ausgabe der ersten Auflage des \"Bilder-Conversations-Lexikons f\u00fcr das deutsche Volk\" (1837-1841); \"Handbuch zur Verbreitung gemeinn\u00fctziger Kenntnisse und zur Unterhaltung\" (Selbstbeschreibung im Vorwort); beinhaltet zahlreiche Abbildungen und Landkarten;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1155;deu;downloadable_files_count: 0;http://www.zeno.org/Brockhaus-1837",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2bc265d6-f16c-5600-b67b-d3e4ed089eb4",
-    "notes": [
-        "digitale Ausgabe der ersten Auflage des \"Bilder-Conversations-Lexikons f\u00fcr das deutsche Volk\" (1837-1841); \"Handbuch zur Verbreitung gemeinn\u00fctziger Kenntnisse und zur Unterhaltung\" (Selbstbeschreibung im Vorwort); beinhaltet zahlreiche Abbildungen und Landkarten"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1155"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Bilder-Conversations-Lexikon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2bd08698-9be8-53bd-807d-518a4c5e18ec.json b/oaitestdata/clarin-oai_dc/SET_1/json/2bd08698-9be8-53bd-807d-518a4c5e18ec.json
deleted file mode 100644
index 8c08bfd5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2bd08698-9be8-53bd-807d-518a4c5e18ec.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Unifob AS"
-    ],
-    "Contributor": [
-        "Andersen, Gisle"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Norwegian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-370",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-370"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-370",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Unifob AS"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Norway"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-370;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;The Norwegian Newspaper Corpus;Andersen, Gisle;Dynamic, web-based newspaper corpus; 700 000 000 ws and growing; multitagged;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-370;nor;downloadable_files_count: 0;Norway;Unifob AS;http://avis.uib.no/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2bd08698-9be8-53bd-807d-518a4c5e18ec",
-    "notes": [
-        "Dynamic, web-based newspaper corpus; 700 000 000 ws and growing; multitagged"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-370"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "The Norwegian Newspaper Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2c06ef1c-b1bd-5e6e-81cc-982198f0c970.json b/oaitestdata/clarin-oai_dc/SET_1/json/2c06ef1c-b1bd-5e6e-81cc-982198f0c970.json
deleted file mode 100644
index 5ff7aef0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2c06ef1c-b1bd-5e6e-81cc-982198f0c970.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5069",
-    "MetadataAccess": [
-        "oai:ota:oucs:5069"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Congreve, William, 1670-1729."
-    ],
-    "fulltext": "oai:ota:oucs:5069;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5069.xml;A hymn to harmony: written in honour of St. Cecilia's day, M DCC I. By Mr. Congreve. Set to musick by Mr. John Eccles, ...;Congreve, William, 1670-1729.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2c06ef1c-b1bd-5e6e-81cc-982198f0c970",
-    "oai_identifier": [
-        "oai:ota:oucs:5069"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A hymn to harmony: written in honour of St. Cecilia's day, M DCC I. By Mr. Congreve. Set to musick by Mr. John Eccles, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5069.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2c0faaeb-8fe8-5c6b-8172-09c38a68ec79.json b/oaitestdata/clarin-oai_dc/SET_1/json/2c0faaeb-8fe8-5c6b-8172-09c38a68ec79.json
deleted file mode 100644
index 59345d10..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2c0faaeb-8fe8-5c6b-8172-09c38a68ec79.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "University of Sheffield"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 7"
-    ],
-    "Language": [
-        "English",
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1646",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1646"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1646",
-    "PublicationTimestamp": "2016-02-29T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "University of Sheffield"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/H2020/645452",
-        "http://hdl.handle.net/11372/LRT-1631",
-        "http://hdl.handle.net/11372/LRT-1974"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "AGREEMENT ON THE USE OF DATA IN QT21",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21",
-        "PUB"
-    ],
-    "author": [
-        "Scarton, Carolina",
-        "Logacheva, Varvara",
-        "Specia, Lucia"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1646;2017-09-04T10:29:31Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;WMT16 Quality Estimation Shared Task Training and Development Data;Specia, Lucia;Logacheva, Varvara;Scarton, Carolina;machine translation;quality estimation;machine learning;Training and development data for the WMT16 QE task. Test data will be published as a separate item.\r\n\r\nThis shared task will build on its previous four editions to further examine automatic methods for estimating the quality of machine translation output at run-time, without relying on reference translations. We include word-level, sentence-level and document-level estimation. The sentence and word-level tasks will explore a large dataset produced from post-editions by professional translators (as opposed to crowdsourced translations as in the previous year). For the first time, the data will be domain-specific (IT domain). The document-level task will use, for the first time, entire documents, which have been human annotated for quality indirectly in two ways: through reading comprehension tests and through a two-stage post-editing exercise. Our tasks have the following goals:\r\n\r\n- To advance work on sentence and word-level quality estimation by providing domain-specific, larger and professionally annotated datasets.\r\n- To study the utility of detailed information logged during post-editing (time, keystrokes, actual edits) for different levels of prediction.\r\n- To analyse the effectiveness of different types of quality labels provided by humans for longer texts in document-level prediction.\r\n\r\nThis year's shared task provides new training and test datasets for all tasks, and allows participants to explore any additional data and resources deemed relevant. A in-house MT system was used to produce translations for the sentence and word-level tasks, and multiple MT systems were used to produce translations for the document-level task. Therefore, MT system-dependent information will be made available where possible.;2016-02-29;corpus;http://hdl.handle.net/11372/LRT-1646;eng;deu;info:eu-repo/grantAgreement/EC/H2020/645452;http://hdl.handle.net/11372/LRT-1631;http://hdl.handle.net/11372/LRT-1974;AGREEMENT ON THE USE OF DATA IN QT21;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21;PUB;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 7;University of Sheffield;http://www.statmt.org/wmt16/quality-estimation-task.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2c0faaeb-8fe8-5c6b-8172-09c38a68ec79",
-    "notes": [
-        "Training and development data for the WMT16 QE task. Test data will be published as a separate item.\r\n\r\nThis shared task will build on its previous four editions to further examine automatic methods for estimating the quality of machine translation output at run-time, without relying on reference translations. We include word-level, sentence-level and document-level estimation. The sentence and word-level tasks will explore a large dataset produced from post-editions by professional translators (as opposed to crowdsourced translations as in the previous year). For the first time, the data will be domain-specific (IT domain). The document-level task will use, for the first time, entire documents, which have been human annotated for quality indirectly in two ways: through reading comprehension tests and through a two-stage post-editing exercise. Our tasks have the following goals:\r\n\r\n- To advance work on sentence and word-level quality estimation by providing domain-specific, larger and professionally annotated datasets.\r\n- To study the utility of detailed information logged during post-editing (time, keystrokes, actual edits) for different levels of prediction.\r\n- To analyse the effectiveness of different types of quality labels provided by humans for longer texts in document-level prediction.\r\n\r\nThis year's shared task provides new training and test datasets for all tasks, and allows participants to explore any additional data and resources deemed relevant. A in-house MT system was used to produce translations for the sentence and word-level tasks, and multiple MT systems were used to produce translations for the document-level task. Therefore, MT system-dependent information will be made available where possible."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1646"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "quality estimation"
-        },
-        {
-            "name": "machine learning"
-        }
-    ],
-    "title": [
-        "WMT16 Quality Estimation Shared Task Training and Development Data"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2c11eb8b-67fd-5275-8c09-cf4a1d1716d7.json b/oaitestdata/clarin-oai_dc/SET_1/json/2c11eb8b-67fd-5275-8c09-cf4a1d1716d7.json
deleted file mode 100644
index f4c9968b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2c11eb8b-67fd-5275-8c09-cf4a1d1716d7.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Ibtikarate"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/xml",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Arabic"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1935",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1935"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1935",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Ibtikarate"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)",
-        "http://creativecommons.org/licenses/by-nc/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Namly, Driss"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1935;2017-02-06T11:04:46Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Special Nouns Lexicon;Namly, Driss;particles;An XML-based file containing Arabic Stop-words respecting nouns syntax; particle nouns, signal nouns, separated pronouns and connected nouns \r\n\r\nCitation: Driss Namly, Yasser Regragui, Karim Bouzoubaa. \"Interoperable Arabic language resources building and exploitation in SAFAR platform\". 13th ACS/IEEE International Conference on Computer Systems and Applications (AICCSA) November 29th to December 2nd, 2016.;2015;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1935;ara;Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0);http://creativecommons.org/licenses/by-nc/4.0/;PUB;text/xml;text/plain; charset=utf-8;downloadable_files_count: 1;Ibtikarate;http://arabic.emi.ac.ma/ibtikarat/?q=Resources",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2c11eb8b-67fd-5275-8c09-cf4a1d1716d7",
-    "notes": [
-        "An XML-based file containing Arabic Stop-words respecting nouns syntax; particle nouns, signal nouns, separated pronouns and connected nouns \r\n\r\nCitation: Driss Namly, Yasser Regragui, Karim Bouzoubaa. \"Interoperable Arabic language resources building and exploitation in SAFAR platform\". 13th ACS/IEEE International Conference on Computer Systems and Applications (AICCSA) November 29th to December 2nd, 2016."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1935"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "particles"
-        }
-    ],
-    "title": [
-        "Special Nouns Lexicon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2c28bd7b-1fde-5b59-b886-4221ae11db18.json b/oaitestdata/clarin-oai_dc/SET_1/json/2c28bd7b-1fde-5b59-b886-4221ae11db18.json
deleted file mode 100644
index 63015adb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2c28bd7b-1fde-5b59-b886-4221ae11db18.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-908",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-908"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-908",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-908;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Prakrit;ca. 7.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-908;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#gprkt",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2c28bd7b-1fde-5b59-b886-4221ae11db18",
-    "notes": [
-        "ca. 7.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-908"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Prakrit"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2c40937d-bf64-5cc5-8b0f-507b67feb75d.json b/oaitestdata/clarin-oai_dc/SET_1/json/2c40937d-bf64-5cc5-8b0f-507b67feb75d.json
deleted file mode 100644
index 57cff5a8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2c40937d-bf64-5cc5-8b0f-507b67feb75d.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "s.n."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-94320",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-94320"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D40-9",
-    "PublicationTimestamp": "1793-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1793"
-    ],
-    "Publisher": [
-        "s.n."
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/94320",
-        "oai:jbc.bj.uj.edu.pl:publication:101279"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1701/1800"
-    ],
-    "TempCoverageBegin": 53662478399,
-    "TempCoverageEnd": 53662478399,
-    "TemporalCoverage": " point in time : 1701-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1701-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1701-07-01T11:59:59Z",
-    "author": [
-        "Skrzetuski, Kajetan J\u00f3zef (1743-1806)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-94320;2019-03-01T17:55:00Z;Prawid\u0142a Pocz\u0105tkowe Nauki obyczaiow, Do Poi\u0119cia Ucz\u0105cey Si\u0119 M\u0142odzi Przystosowane;Skrzetuski, Kajetan J\u00f3zef (1743-1806);starodruki 18\u00a0w.;s.n.;1793;starodruk;application/xml;clarind-uds:poldilemma-94320;hdl:11858/00-246C-0000-0023-8D40-9;Biblioteka Jagiello\u0144ska, BJ St. Dr. 2429 I;pol;http://jbc.bj.uj.edu.pl/Content/94320;oai:jbc.bj.uj.edu.pl:publication:101279;1701/1800;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2c40937d-bf64-5cc5-8b0f-507b67feb75d",
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-94320"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Prawid\u0142a Pocz\u0105tkowe Nauki obyczaiow, Do Poi\u0119cia Ucz\u0105cey Si\u0119 M\u0142odzi Przystosowane"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2c574e0b-f46c-5594-bc12-a5ab64d9c3bf.json b/oaitestdata/clarin-oai_dc/SET_1/json/2c574e0b-f46c-5594-bc12-a5ab64d9c3bf.json
deleted file mode 100644
index 8ba81781..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2c574e0b-f46c-5594-bc12-a5ab64d9c3bf.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Royster, Paul"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3238",
-    "MetadataAccess": [
-        "oai:ota:oucs:3238"
-    ],
-    "PublicationTimestamp": "1875-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1875"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "James, Henry, 1843-1916"
-    ],
-    "fulltext": "oai:ota:oucs:3238;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3238.xml;Roderick Hudson;Roderick Hudson;James, Henry, 1843-1916;not after: 1875;text_and_corpus_linguistics;American literature -- 19th century;eng;Oxford Text Archive, University of Oxford;Royster, Paul;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2c574e0b-f46c-5594-bc12-a5ab64d9c3bf",
-    "oai_identifier": [
-        "oai:ota:oucs:3238"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "American literature -- th century"
-        }
-    ],
-    "title": [
-        "Roderick Hudson",
-        "Roderick Hudson"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3238.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2c57c440-7fa6-5cdc-bd37-629d55501d17.json b/oaitestdata/clarin-oai_dc/SET_1/json/2c57c440-7fa6-5cdc-bd37-629d55501d17.json
deleted file mode 100644
index c6675fa1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2c57c440-7fa6-5cdc-bd37-629d55501d17.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Uniwersytet Miko\u0142aja Kopernika w Toruniu"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 86",
-        "text/plain; charset=utf-8",
-        "text/plain"
-    ],
-    "Language": [],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/522",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/522"
-    ],
-    "PID": "http://hdl.handle.net/11321/522",
-    "PublicationTimestamp": "2018-07-13T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Uniwersytet Miko\u0142aja Kopernika w Toruniu"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Clarin, Ania"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/522;2018-07-13T13:52:01Z;hdl_11321_3;hdl_11321_4;Warsztat;Clarin, Ania;europose\u0142;korpus testowy;2018-07-13;corpus;http://hdl.handle.net/11321/522;polski;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;downloadable_files_count: 86;Uniwersytet Miko\u0142aja Kopernika w Toruniu",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2c57c440-7fa6-5cdc-bd37-629d55501d17",
-    "notes": [
-        "korpus testowy"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/522"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Warsztat"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2c612d3a-8211-5f4f-9854-7547258cf884.json b/oaitestdata/clarin-oai_dc/SET_1/json/2c612d3a-8211-5f4f-9854-7547258cf884.json
deleted file mode 100644
index 1e2ad214..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2c612d3a-8211-5f4f-9854-7547258cf884.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "image/png",
-        "downloadable_files_count: 1"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48F8-6",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48F8-6"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-48F8-6",
-    "PublicationTimestamp": "2009-11-02T09:33:08Z",
-    "PublicationYear": [
-        "2009"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU General Public License, version 2",
-        "http://www.gnu.org/licenses/gpl-2.0.html",
-        "PUB"
-    ],
-    "author": [
-        "Pajas, Petr",
-        "Mare\u010dek, David"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48F8-6;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;MEd;Pajas, Petr;Mare\u010dek, David;annotation tool;MEd is an annotation tool in which linearly-structured annotations of text or audio data can be created and edited. The tool supports multiple stacked layers of annotations that can be interconnected by links. MEd can also be used for other purposes, such as word-to-word alignment of parallel corpora.;2009-11-02T09:33:08Z;toolService;http://hdl.handle.net/11858/00-097C-0000-0001-48F8-6;GNU General Public License, version 2;http://www.gnu.org/licenses/gpl-2.0.html;PUB;image/png;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2c612d3a-8211-5f4f-9854-7547258cf884",
-    "notes": [
-        "MEd is an annotation tool in which linearly-structured annotations of text or audio data can be created and edited. The tool supports multiple stacked layers of annotations that can be interconnected by links. MEd can also be used for other purposes, such as word-to-word alignment of parallel corpora."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48F8-6"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "annotation tool"
-        }
-    ],
-    "title": [
-        "MEd"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2c6f0bac-7995-5f14-9939-ae0020681a25.json b/oaitestdata/clarin-oai_dc/SET_1/json/2c6f0bac-7995-5f14-9939-ae0020681a25.json
deleted file mode 100644
index a3960275..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2c6f0bac-7995-5f14-9939-ae0020681a25.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "University of Lisbon"
-    ],
-    "Contributor": [
-        "Branco, Ant\u00f3nio"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Portuguese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-564",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-564"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-564",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Lisbon"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Portugal"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-564;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;CINTIL-International Corpus of Portuguese;Branco, Ant\u00f3nio;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-564;por;downloadable_files_count: 0;Portugal;University of Lisbon;http://cintil.ul.pt",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2c6f0bac-7995-5f14-9939-ae0020681a25",
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-564"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "CINTIL-International Corpus of Portuguese"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2c809ba6-a403-5edc-b7ce-8ac4487f3aff.json b/oaitestdata/clarin-oai_dc/SET_1/json/2c809ba6-a403-5edc-b7ce-8ac4487f3aff.json
deleted file mode 100644
index 7b783e6c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2c809ba6-a403-5edc-b7ce-8ac4487f3aff.json
+++ /dev/null
@@ -1,88 +0,0 @@
-{
-    "Contact": [
-        "Polish-Japanese Academy of Information Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/gzip",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/296",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/296"
-    ],
-    "PID": "http://hdl.handle.net/11321/296",
-    "PublicationTimestamp": "2016-06-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Polish-Japanese Academy of Information Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "BSD 2 Clause",
-        "https://opensource.org/licenses/BSD-2-Clause",
-        "PUB"
-    ],
-    "author": [
-        "Marasek, Krzysztof",
-        "Brocki, \u0141ukasz",
-        "Kor\u017einek, Danijel"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/296;2016-06-06T13:04:21Z;hdl_11321_3;hdl_11321_4;Polish Speech Services;Kor\u017einek, Danijel;Marasek, Krzysztof;Brocki, \u0141ukasz;speech tools;alignemnt;speaker diarization;asr;voice activity detection;keyword spotting;This archive contains the source code and configuration of the speech tools web service available at http://mowa.clarin-pl.eu/mowa. The services provided include:\r\n+ speech to text alignemnt\r\n+ speaker diarization\r\n+ speech transcription\r\n+ speech activity detection and noise classification\r\n+ keyword spotting;2016-06-01;toolService;http://hdl.handle.net/11321/296;pol;BSD 2 Clause;https://opensource.org/licenses/BSD-2-Clause;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/gzip;downloadable_files_count: 1;Polish-Japanese Academy of Information Technology;http://mowa.clarin-pl.eu/mowa/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2c809ba6-a403-5edc-b7ce-8ac4487f3aff",
-    "notes": [
-        "This archive contains the source code and configuration of the speech tools web service available at http://mowa.clarin-pl.eu/mowa. The services provided include:\r\n+ speech to text alignemnt\r\n+ speaker diarization\r\n+ speech transcription\r\n+ speech activity detection and noise classification\r\n+ keyword spotting"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/296"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech tools"
-        },
-        {
-            "name": "alignemnt"
-        },
-        {
-            "name": "speaker diarization"
-        },
-        {
-            "name": "asr"
-        },
-        {
-            "name": "voice activity detection"
-        },
-        {
-            "name": "keyword spotting"
-        }
-    ],
-    "title": [
-        "Polish Speech Services"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2c98745b-6abc-50a7-93b3-4fcf3cf17dc4.json b/oaitestdata/clarin-oai_dc/SET_1/json/2c98745b-6abc-50a7-93b3-4fcf3cf17dc4.json
deleted file mode 100644
index 6c3080b7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2c98745b-6abc-50a7-93b3-4fcf3cf17dc4.json
+++ /dev/null
@@ -1,91 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Electrical Engineering and Computer Science, University of Maribor"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 3",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1069",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1069"
-    ],
-    "PID": "http://hdl.handle.net/11356/1069",
-    "PublicationTimestamp": "2016-08-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Faculty of Electrical Engineering and Computer Science, University of Maribor"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11356/1158"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by-nc/4.0/"
-    ],
-    "author": [
-        "Sepesy Mau\u010dec, Mirjam",
-        "Erjavec, Toma\u017e",
-        "Poto\u010dnik, Toma\u017e",
-        "Verdonik, Darinka"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1069;2018-10-18T22:25:12Z;hdl_11356_1023;hdl_11356_1024;Spoken corpus Gos VideoLectures 1.0 (transcription);Verdonik, Darinka;Poto\u010dnik, Toma\u017e;Sepesy Mau\u010dec, Mirjam;Erjavec, Toma\u017e;speech database;spoken corpus;academic speech;speech transcription;speech recognition;TEI;Gos Videolectures is an add-on to the Gos reference speech corpus of Slovene (http://hdl.handle.net/11356/1040), and covers public academic speech. The Gos Videolectures recordings are a  selection of public lectures available through web-portal Videolectures.net provided by the Jo\u017eef Stefan Institute, and covers in its first release 4.5 hours of speech. \r\n\r\nThis resource contains only the transcriptions of the corpus - the audio recordings are avaiable at CLARIN.SI handle http://hdl.handle.net/11356/1070.\r\n\r\nAll transcriptions for Gos Videolectures were done manually and carefully checked. The main guidelines for transcription were those of the Gos corpus (http://www.korpus-gos.net/Support/About). The transcription tool Transcriber 1.5.1 (http://trans.sourceforge.net/en/presentation.php) was used for making transcriptions. It can be also used for reading or exporting transcriptions (.trs files) to different formats. \r\n\r\nThe transcriptions comprise the TRS files with tabular metadata, their conversion to TEI and to the CWB vertical file format. Each recording has two TRS files, one with the phonetic and the other with the normalised transcription. The TEI and CWB encodings join these two transcriptions at the token level, with the normalised words being also automatically PoS tagged and lemmatised. \r\n\r\nThe corpus can be used for training continuous speech recognition for Slovene language, for phonetic research or any other research of Slovene academic speech.;2016-08-01;corpus;http://hdl.handle.net/11356/1069;slv;http://hdl.handle.net/11356/1158;Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0);PUB;https://creativecommons.org/licenses/by-nc/4.0/;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 3;Faculty of Electrical Engineering and Computer Science, University of Maribor",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2c98745b-6abc-50a7-93b3-4fcf3cf17dc4",
-    "notes": [
-        "Gos Videolectures is an add-on to the Gos reference speech corpus of Slovene (http://hdl.handle.net/11356/1040), and covers public academic speech. The Gos Videolectures recordings are a  selection of public lectures available through web-portal Videolectures.net provided by the Jo\u017eef Stefan Institute, and covers in its first release 4.5 hours of speech. \r\n\r\nThis resource contains only the transcriptions of the corpus - the audio recordings are avaiable at CLARIN.SI handle http://hdl.handle.net/11356/1070.\r\n\r\nAll transcriptions for Gos Videolectures were done manually and carefully checked. The main guidelines for transcription were those of the Gos corpus (http://www.korpus-gos.net/Support/About). The transcription tool Transcriber 1.5.1 (http://trans.sourceforge.net/en/presentation.php) was used for making transcriptions. It can be also used for reading or exporting transcriptions (.trs files) to different formats. \r\n\r\nThe transcriptions comprise the TRS files with tabular metadata, their conversion to TEI and to the CWB vertical file format. Each recording has two TRS files, one with the phonetic and the other with the normalised transcription. The TEI and CWB encodings join these two transcriptions at the token level, with the normalised words being also automatically PoS tagged and lemmatised. \r\n\r\nThe corpus can be used for training continuous speech recognition for Slovene language, for phonetic research or any other research of Slovene academic speech."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1069"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech database"
-        },
-        {
-            "name": "spoken corpus"
-        },
-        {
-            "name": "academic speech"
-        },
-        {
-            "name": "speech transcription"
-        },
-        {
-            "name": "speech recognition"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "Spoken corpus Gos VideoLectures 1.0 (transcription)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2c98c080-4a87-55c1-999d-a367404e3bd9.json b/oaitestdata/clarin-oai_dc/SET_1/json/2c98c080-4a87-55c1-999d-a367404e3bd9.json
deleted file mode 100644
index 2f6ec00b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2c98c080-4a87-55c1-999d-a367404e3bd9.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Waite, Stephen V.F."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 218 KB)"
-    ],
-    "Language": [
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0347",
-    "MetadataAccess": [
-        "oai:ota:oucs:0347"
-    ],
-    "PublicationYear": [
-        "8"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Ovid, 43 B.C.-17 or 18 A.D."
-    ],
-    "fulltext": "oai:ota:oucs:0347;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0347.xml;Fasti / Ovid;Festivals;Fastorum libri VI : fragmenta;Ovid, 43 B.C.-17 or 18 A.D.;8;text_and_corpus_linguistics;Elegiac poetry, Latin -- 1st century;lat;Oxford Text Archive, University of Oxford;Waite, Stephen V.F.;(1 file : ca. 218 KB);Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2c98c080-4a87-55c1-999d-a367404e3bd9",
-    "oai_identifier": [
-        "oai:ota:oucs:0347"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Elegiac poetry"
-        },
-        {
-            "name": "Latin -- st century"
-        }
-    ],
-    "title": [
-        "Fasti / Ovid",
-        "Festivals",
-        "Fastorum libri VI : fragmenta"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0347.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2caa6ccb-8e03-5cd5-85ed-8af4688e0642.json b/oaitestdata/clarin-oai_dc/SET_1/json/2caa6ccb-8e03-5cd5-85ed-8af4688e0642.json
deleted file mode 100644
index 1a81cc15..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2caa6ccb-8e03-5cd5-85ed-8af4688e0642.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2688",
-    "MetadataAccess": [
-        "oai:ota:oucs:2688"
-    ],
-    "PublicationTimestamp": "1709-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1709"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2688;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2688.xml;A vindication of Isaac Bickerstaff;Swift, Jonathan, 1667-1745;1709;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2caa6ccb-8e03-5cd5-85ed-8af4688e0642",
-    "oai_identifier": [
-        "oai:ota:oucs:2688"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A vindication of Isaac Bickerstaff"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2688.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2cb35fb9-ef83-5dc6-a0b6-dad3569f0045.json b/oaitestdata/clarin-oai_dc/SET_1/json/2cb35fb9-ef83-5dc6-a0b6-dad3569f0045.json
deleted file mode 100644
index 870fbc93..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2cb35fb9-ef83-5dc6-a0b6-dad3569f0045.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3638",
-    "MetadataAccess": [
-        "oai:ota:oucs:3638"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Paley, William, 1743-1805."
-    ],
-    "fulltext": "oai:ota:oucs:3638;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3638.xml;Advice addressed to the young clergy of the diocese of Carlisle: in a sermon, preached ... on Sunday, July 29th, 1781. By William Paley, ...;Paley, William, 1743-1805.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2cb35fb9-ef83-5dc6-a0b6-dad3569f0045",
-    "oai_identifier": [
-        "oai:ota:oucs:3638"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Advice addressed to the young clergy of the diocese of Carlisle: in a sermon, preached ... on Sunday, July 29th, 1781. By William Paley, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3638.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2cc6f701-0e19-5ec5-9b6a-373abcbf42e4.json b/oaitestdata/clarin-oai_dc/SET_1/json/2cc6f701-0e19-5ec5-9b6a-373abcbf42e4.json
deleted file mode 100644
index 94a6d6ef..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2cc6f701-0e19-5ec5-9b6a-373abcbf42e4.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain",
-        "(1 file : ca. 102 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2261",
-    "MetadataAccess": [
-        "oai:ota:oucs:2261"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Browning, Robert, 1812-1889"
-    ],
-    "fulltext": "oai:ota:oucs:2261;2018-02-16T10:42:06Z;http://ota.ox.ac.uk/headers/2261.xml;Colombe's birthday;Browning, Robert, 1812-1889;default: 1976-01-01;text_and_corpus_linguistics;Plays -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 102 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2cc6f701-0e19-5ec5-9b6a-373abcbf42e4",
-    "oai_identifier": [
-        "oai:ota:oucs:2261"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Colombe's birthday"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2261.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2cd0e782-dd6f-52bd-b377-8d1342f89823.json b/oaitestdata/clarin-oai_dc/SET_1/json/2cd0e782-dd6f-52bd-b377-8d1342f89823.json
deleted file mode 100644
index 2421886c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2cd0e782-dd6f-52bd-b377-8d1342f89823.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Computer and Information Science, University of Ljubljana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/pdf",
-        "text/plain",
-        "downloadable_files_count: 8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1097",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1097"
-    ],
-    "PID": "http://hdl.handle.net/11356/1097",
-    "PublicationTimestamp": "2017-04-14T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Faculty of Computer and Information Science, University of Ljubljana"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Robnik-\u0160ikonja, Marko",
-        "Kadunc, Klemen"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1097;2017-05-28T08:38:58Z;hdl_11356_1023;hdl_11356_1024;Slovene sentiment lexicon KSS 1.1;Kadunc, Klemen;Robnik-\u0160ikonja, Marko;opinion lexicon;sentiment lexicon;Slovene opinion lexicon KSS is based on the manually translated opinion lexicon of Hu & Liu (2004). The lexicon is updated with some positive and negative words typical for Slovenian language. There are three versions of the lexicon.\r\n\r\n1.  Lexicon containing all word forms extended with Sloleks, a lexicon of Slovene word forms. It contains 90,620 entries, 62,941 negative word forms and 27,679 positive word forms.\r\n2. Lexicon containing only lemmas, containing 5,125 negative words and 1,911 positive words.\r\n3. The original version used in (Kadunc & Robnik-\u0160ikonja, 2016), containing 6,687 negative entries and  2,645 positive entries.\r\n\r\nEach version of the lexicon contains two files, one for negative and one for positive words in a text format, one word per line. The lexicon also contains some multi-word units where the individual words are joined with an underscore, e.g. \"bolezenska_znamenja\".\r\n\r\nThe KSS lexicon was developed as part of BSc Thesis (Kadunc, 2016) and empirically evaluated on a corpus of web commentaries about different topics (business, politics, sport and other topics) from 4 Slovene web portals (RtvSlo, 24ur, Finance, Reporter). That corpus is available from http://hdl.handle.net/11356/1115\r\n\r\n\r\nReferences:\r\n1. Minqing Hu in Bing Liu (2004). Mining opinion features in customer reviews. In Proceedings of AAAI Conference on Artificial Intelligence, vol. 4, pp. 755\u2013760 http://www.aaai.org/Papers/AAAI/2004/AAAI04-119.pdf \r\n2. Klemen Kadunc (2016). Dolo\u010danje sentimenta slovenskim spletnim komentarjem s pomo\u010djo strojnega u\u010denja. Diplomsko delo. Univerza v Ljubljani, Fakulteta za ra\u010dunalni\u0161tvo in informatiko (in Slovene). http://eprints.fri.uni-lj.si/3317/\r\n3. Klemen Kadunc, Marko Robnik-\u0160ikonja (2016). Analiza mnenj s pomo\u010djo strojnega u\u010denja in slovenskega leksikona sentimenta. Conference on Language Technologies & Digital Humanities, Ljubljana (in Slovene), http://www.sdjt.si/wp/wp-content/uploads/2016/09/JTDH-2016_Kadunc-et-al_Analiza-mnenj-s-pomocjo-strojnega-ucenja.pdf;2017-04-14;lexicalConceptualResource;http://hdl.handle.net/11356/1097;slv;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;PUB;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;application/pdf;application/pdf;text/plain; charset=utf-8;downloadable_files_count: 8;Faculty of Computer and Information Science, University of Ljubljana;http://lkm.fri.uni-lj.si/rmarko/repozitorij/opinionLexicon",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2cd0e782-dd6f-52bd-b377-8d1342f89823",
-    "notes": [
-        "Slovene opinion lexicon KSS is based on the manually translated opinion lexicon of Hu & Liu (2004). The lexicon is updated with some positive and negative words typical for Slovenian language. There are three versions of the lexicon.\r\n\r\n1.  Lexicon containing all word forms extended with Sloleks, a lexicon of Slovene word forms. It contains 90,620 entries, 62,941 negative word forms and 27,679 positive word forms.\r\n2. Lexicon containing only lemmas, containing 5,125 negative words and 1,911 positive words.\r\n3. The original version used in (Kadunc & Robnik-\u0160ikonja, 2016), containing 6,687 negative entries and  2,645 positive entries.\r\n\r\nEach version of the lexicon contains two files, one for negative and one for positive words in a text format, one word per line. The lexicon also contains some multi-word units where the individual words are joined with an underscore, e.g. \"bolezenska_znamenja\".\r\n\r\nThe KSS lexicon was developed as part of BSc Thesis (Kadunc, 2016) and empirically evaluated on a corpus of web commentaries about different topics (business, politics, sport and other topics) from 4 Slovene web portals (RtvSlo, 24ur, Finance, Reporter). That corpus is available from http://hdl.handle.net/11356/1115\r\n\r\n\r\nReferences:\r\n1. Minqing Hu in Bing Liu (2004). Mining opinion features in customer reviews. In Proceedings of AAAI Conference on Artificial Intelligence, vol. 4, pp. 755\u2013760 http://www.aaai.org/Papers/AAAI/2004/AAAI04-119.pdf \r\n2. Klemen Kadunc (2016). Dolo\u010danje sentimenta slovenskim spletnim komentarjem s pomo\u010djo strojnega u\u010denja. Diplomsko delo. Univerza v Ljubljani, Fakulteta za ra\u010dunalni\u0161tvo in informatiko (in Slovene). http://eprints.fri.uni-lj.si/3317/\r\n3. Klemen Kadunc, Marko Robnik-\u0160ikonja (2016). Analiza mnenj s pomo\u010djo strojnega u\u010denja in slovenskega leksikona sentimenta. Conference on Language Technologies & Digital Humanities, Ljubljana (in Slovene), http://www.sdjt.si/wp/wp-content/uploads/2016/09/JTDH-2016_Kadunc-et-al_Analiza-mnenj-s-pomocjo-strojnega-ucenja.pdf"
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1097"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "opinion lexicon"
-        },
-        {
-            "name": "sentiment lexicon"
-        }
-    ],
-    "title": [
-        "Slovene sentiment lexicon KSS 1.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2cd29aaa-6d2c-5d66-b8f4-45aa7a252ee8.json b/oaitestdata/clarin-oai_dc/SET_1/json/2cd29aaa-6d2c-5d66-b8f4-45aa7a252ee8.json
deleted file mode 100644
index ec1c53d6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2cd29aaa-6d2c-5d66-b8f4-45aa7a252ee8.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3518",
-    "MetadataAccess": [
-        "oai:ota:oucs:3518"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Griffith, Mrs. (Elizabeth), 1720?-1793."
-    ],
-    "fulltext": "oai:ota:oucs:3518;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3518.xml;The delicate distress, a novel: in letters. In two volumes. By Frances. ... [pt.1];Griffith, Mrs. (Elizabeth), 1720?-1793.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2cd29aaa-6d2c-5d66-b8f4-45aa7a252ee8",
-    "oai_identifier": [
-        "oai:ota:oucs:3518"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The delicate distress, a novel: in letters. In two volumes. By Frances. ... [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3518.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2cdb0ac8-56a3-55d8-b1a9-c9c96f594ad2.json b/oaitestdata/clarin-oai_dc/SET_1/json/2cdb0ac8-56a3-55d8-b1a9-c9c96f594ad2.json
deleted file mode 100644
index 8b5b596d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2cdb0ac8-56a3-55d8-b1a9-c9c96f594ad2.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 73.1 KB)"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0236",
-    "MetadataAccess": [
-        "oai:ota:oucs:0236"
-    ],
-    "PublicationYear": [
-        "392 BCE"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Aristophanes"
-    ],
-    "fulltext": "oai:ota:oucs:0236;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0236.xml;Ecclesiazusae;The Ecclesiazousae of Aristophanes;The Assemblywomen;Aristophanes;392 BCE;text_and_corpus_linguistics;Plays -- Greece -- B.C.;grc;Oxford Text Archive, University of Oxford;(1 file : ca. 73.1 KB);Text;Plays;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2cdb0ac8-56a3-55d8-b1a9-c9c96f594ad2",
-    "oai_identifier": [
-        "oai:ota:oucs:0236"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- Greece -- B.C."
-        }
-    ],
-    "title": [
-        "Ecclesiazusae",
-        "The Ecclesiazousae of Aristophanes",
-        "The Assemblywomen"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0236.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2cefe8af-f797-57b9-9552-0f1caac92ee8.json b/oaitestdata/clarin-oai_dc/SET_1/json/2cefe8af-f797-57b9-9552-0f1caac92ee8.json
deleted file mode 100644
index 1f1d4163..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2cefe8af-f797-57b9-9552-0f1caac92ee8.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Meertens Institute KNAW The Netherlands"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-605",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-605"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-605",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Meertens Institute KNAW The Netherlands"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Belgium||Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-605;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;DynaSAND (Dynamic Syntactic Atlas of the Dutch dialects);The Dynamic Syntactic Atlas of the Dutch dialects (DynaSAND) is an on-line tool for dialect syntax research. DynaSAND consists of a database, a search engine, a cartographic component and a bibliography.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-605;nld;downloadable_files_count: 0;Belgium||Netherlands (the);Meertens Institute KNAW The Netherlands;http://www.meertens.knaw.nl/sand",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2cefe8af-f797-57b9-9552-0f1caac92ee8",
-    "notes": [
-        "The Dynamic Syntactic Atlas of the Dutch dialects (DynaSAND) is an on-line tool for dialect syntax research. DynaSAND consists of a database, a search engine, a cartographic component and a bibliography."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-605"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "DynaSAND (Dynamic Syntactic Atlas of the Dutch dialects)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2d19b9a1-c59f-55a1-99f6-a820ac09cbb2.json b/oaitestdata/clarin-oai_dc/SET_1/json/2d19b9a1-c59f-55a1-99f6-a820ac09cbb2.json
deleted file mode 100644
index 9446719b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2d19b9a1-c59f-55a1-99f6-a820ac09cbb2.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "QT21 project"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "English",
-        "German",
-        "Czech",
-        "Latvian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2390",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2390"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2390",
-    "PublicationTimestamp": "2017-09-18T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "QT21 project"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/H2020/645452"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "AGREEMENT ON THE USE OF DATA IN QT21",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21",
-        "PUB"
-    ],
-    "author": [
-        "Specia, Lucia"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2390;2017-09-18T16:47:30Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;QT21 Data;Specia, Lucia;machine translation;post-editing;error annotation;mqm;Post-editing and MQM annotations produced by the QT21 project. As described in\r\n\r\n@InProceedings{specia-etal_MTSummit:2017,\r\n  author    = {Specia, Lucia  and  Kim Harris and Fr\u00e9d\u00e9ric Blain and Aljoscha Burchardt and Viviven Macketanz and Inguna Skadi\u0146a and Matteo Negri and and Marco Turchi},\r\n  title     = {Translation Quality and Productivity: A Study on Rich Morphology Languages},\r\n  booktitle = {Proceedings of Machine Translation Summit XVI},\r\n  year      = {2017},\r\n  pages = {55--71},\r\n  address   = {Nagoya, Japan},\r\n};2017-09-18;corpus;http://hdl.handle.net/11372/LRT-2390;eng;deu;ces;lav;info:eu-repo/grantAgreement/EC/H2020/645452;AGREEMENT ON THE USE OF DATA IN QT21;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21;PUB;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 2;QT21 project",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2d19b9a1-c59f-55a1-99f6-a820ac09cbb2",
-    "notes": [
-        "Post-editing and MQM annotations produced by the QT21 project. As described in\r\n\r\n@InProceedings{specia-etal_MTSummit:2017,\r\n  author    = {Specia, Lucia  and  Kim Harris and Fr\u00e9d\u00e9ric Blain and Aljoscha Burchardt and Viviven Macketanz and Inguna Skadi\u0146a and Matteo Negri and and Marco Turchi},\r\n  title     = {Translation Quality and Productivity: A Study on Rich Morphology Languages},\r\n  booktitle = {Proceedings of Machine Translation Summit XVI},\r\n  year      = {2017},\r\n  pages = {55--71},\r\n  address   = {Nagoya, Japan},\r\n}"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2390"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "post-editing"
-        },
-        {
-            "name": "error annotation"
-        },
-        {
-            "name": "mqm"
-        }
-    ],
-    "title": [
-        "QT21 Data"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2d674168-c84d-5399-870d-11cc46f55854.json b/oaitestdata/clarin-oai_dc/SET_1/json/2d674168-c84d-5399-870d-11cc46f55854.json
deleted file mode 100644
index 7ab01bf6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2d674168-c84d-5399-870d-11cc46f55854.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "University of Silesia"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 19",
-        "text/plain; charset=utf-8",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/352",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/352"
-    ],
-    "PID": "http://hdl.handle.net/11321/352",
-    "PublicationTimestamp": "2017-04-25T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "University of Silesia"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Rafa\u0142 Molencki"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/352;2017-04-25T14:09:29Z;hdl_11321_3;hdl_11321_4;Rafal;Rafa\u0142 Molencki;conjunction;sp\u00f3jnik;korpus;2017-04-25;corpus;http://hdl.handle.net/11321/352;Polish, English;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;downloadable_files_count: 19;University of Silesia;http://www.us.edu.pl",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2d674168-c84d-5399-870d-11cc46f55854",
-    "notes": [
-        "korpus"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/352"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "conjunction"
-        },
-        {
-            "name": "conjunction"
-        }
-    ],
-    "title": [
-        "Rafal"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2d713f63-621e-5fef-8cc1-10cf7faf9a39.json b/oaitestdata/clarin-oai_dc/SET_1/json/2d713f63-621e-5fef-8cc1-10cf7faf9a39.json
deleted file mode 100644
index 6d6150e6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2d713f63-621e-5fef-8cc1-10cf7faf9a39.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Siemens, Raymond George, 1966-"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(3 files : ca. 567, 424, 1.5 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2047",
-    "MetadataAccess": [
-        "oai:ota:oucs:2047"
-    ],
-    "PublicationTimestamp": "1557-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1557"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Anthologies"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Surrey, Henry Howard, Earl of, 1517?-1547",
-        "Tottel, Richard, d. 1594"
-    ],
-    "fulltext": "oai:ota:oucs:2047;2018-03-02T09:53:42Z;http://ota.ox.ac.uk/headers/2047.xml;Tottel's Miscellany : [1557];Tottel, Richard, d. 1594;Surrey, Henry Howard, Earl of, 1517?-1547;1557;text_and_corpus_linguistics;Linguistic analysis (Linguistics);Anthologies -- Great Britain -- 16th century;Oxford Text Archive, University of Oxford;Siemens, Raymond George, 1966-;(3 files : ca. 567, 424, 1.5 KB);Text;Anthologies;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2d713f63-621e-5fef-8cc1-10cf7faf9a39",
-    "oai_identifier": [
-        "oai:ota:oucs:2047"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Linguistic analysis Linguistics"
-        },
-        {
-            "name": "Anthologies -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Tottel's Miscellany : [1557]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2047.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2d8ea5f8-7288-50f5-9d52-33fd93b93c62.json b/oaitestdata/clarin-oai_dc/SET_1/json/2d8ea5f8-7288-50f5-9d52-33fd93b93c62.json
deleted file mode 100644
index 590eb6f5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2d8ea5f8-7288-50f5-9d52-33fd93b93c62.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/x-tar",
-        "application/zip",
-        "downloadable_files_count: 47",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Multiple languages"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1989",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1989"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1989",
-    "PublicationTimestamp": "2017-03-15T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Haji\u010d, Jan",
-        "Straka, Milan",
-        "Ginter, Filip",
-        "Luotolahti, Juhani",
-        "Zeman, Daniel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1989;2018-09-03T09:16:19Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;CoNLL 2017 Shared Task - Automatically Annotated Raw Texts and Word Embeddings;Ginter, Filip;Haji\u010d, Jan;Luotolahti, Juhani;Straka, Milan;Zeman, Daniel;CoNLL 2017;word embeddings;automatic annotation;Automatic segmentation, tokenization and morphological and syntactic annotations of raw texts in 45 languages, generated by UDPipe (http://ufal.mff.cuni.cz/udpipe), together with word embeddings of dimension 100 computed from lowercased texts by word2vec (https://code.google.com/archive/p/word2vec/).\r\n\r\nFor each language, automatic annotations in CoNLL-U format are provided in a separate archive. The word embeddings for all languages are distributed in one archive.\r\n\r\nNote that the CC BY-SA-NC 4.0 license applies to the automatically generated annotations and word embeddings, not to the underlying data, which may have different license and impose additional restrictions.\r\n\r\nUpdate 2018-09-03\r\n===============\r\nAdded data in the 4 \u201csurprise languages\u201d from the 2017 ST: Buryat, Kurmanji, North Sami and Upper Sorbian. This has been promised before, during CoNLL-ST 2018 we gave the participants a link to this record saying the data was here. It wasn't, sorry. But now it is.;2017-03-15;languageDescription;http://hdl.handle.net/11234/1-1989;mul;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/x-tar;application/zip;text/plain; charset=utf-8;downloadable_files_count: 47;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2d8ea5f8-7288-50f5-9d52-33fd93b93c62",
-    "notes": [
-        "Automatic segmentation, tokenization and morphological and syntactic annotations of raw texts in 45 languages, generated by UDPipe (http://ufal.mff.cuni.cz/udpipe), together with word embeddings of dimension 100 computed from lowercased texts by word2vec (https://code.google.com/archive/p/word2vec/).\r\n\r\nFor each language, automatic annotations in CoNLL-U format are provided in a separate archive. The word embeddings for all languages are distributed in one archive.\r\n\r\nNote that the CC BY-SA-NC 4.0 license applies to the automatically generated annotations and word embeddings, not to the underlying data, which may have different license and impose additional restrictions.\r\n\r\nUpdate 2018-09-03\r\n===============\r\nAdded data in the 4 \u201csurprise languages\u201d from the 2017 ST: Buryat, Kurmanji, North Sami and Upper Sorbian. This has been promised before, during CoNLL-ST 2018 we gave the participants a link to this record saying the data was here. It wasn't, sorry. But now it is."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1989"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "CoNLL"
-        },
-        {
-            "name": "word embeddings"
-        },
-        {
-            "name": "automatic annotation"
-        }
-    ],
-    "title": [
-        "CoNLL 2017 Shared Task - Automatically Annotated Raw Texts and Word Embeddings"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2dac628f-2858-530f-97f7-51d1d5a898dc.json b/oaitestdata/clarin-oai_dc/SET_1/json/2dac628f-2858-530f-97f7-51d1d5a898dc.json
deleted file mode 100644
index 9e7876d3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2dac628f-2858-530f-97f7-51d1d5a898dc.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 453 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1807",
-    "MetadataAccess": [
-        "oai:ota:oucs:1807"
-    ],
-    "PublicationTimestamp": "1993-03-01T11:59:59Z",
-    "PublicationYear": [
-        "1993"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "James, Henry, 1843-1916"
-    ],
-    "fulltext": "oai:ota:oucs:1807;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/1807.xml;Confidence;Confidence / Henry James;James, Henry, 1843-1916;1993-03-01;text_and_corpus_linguistics;American literature -- 19th century;eng;Oxford Text Archive, University of Oxford;Triggs, Jeffery;text/sgml;(1 file : ca. 453 KB);Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2dac628f-2858-530f-97f7-51d1d5a898dc",
-    "oai_identifier": [
-        "oai:ota:oucs:1807"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "American literature -- th century"
-        }
-    ],
-    "title": [
-        "Confidence",
-        "Confidence / Henry James"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1807.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2db20033-1cc9-5814-86ab-38ac0a408a9e.json b/oaitestdata/clarin-oai_dc/SET_1/json/2db20033-1cc9-5814-86ab-38ac0a408a9e.json
deleted file mode 100644
index e2724b07..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2db20033-1cc9-5814-86ab-38ac0a408a9e.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/95",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/95"
-    ],
-    "PID": "http://hdl.handle.net/10794/95",
-    "PublicationTimestamp": "2013-03-06T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/95;2017-10-25T11:46:24Z;hdl_10794_1;hdl_10794_2;Blog mix 2001 (2017-02-17);Bloggmix 2001 (2017-02-17);n/a, n/a;Swedish;Blog;The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.;Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat.;2013-03-06;corpus;http://hdl.handle.net/10794/95;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/bloggmix2001",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2db20033-1cc9-5814-86ab-38ac0a408a9e",
-    "notes": [
-        "The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.",
-        "Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/95"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Blog"
-        }
-    ],
-    "title": [
-        "Blog mix 2001 (2017-02-17)",
-        "Bloggmix 2001 (2017-02-17)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2db66d25-9da2-5a50-82ac-c4ca70a5b378.json b/oaitestdata/clarin-oai_dc/SET_1/json/2db66d25-9da2-5a50-82ac-c4ca70a5b378.json
deleted file mode 100644
index 0b327a89..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2db66d25-9da2-5a50-82ac-c4ca70a5b378.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Waite, Stephen V.F."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 243 KB)"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0266",
-    "MetadataAccess": [
-        "oai:ota:oucs:0266"
-    ],
-    "PublicationYear": [
-        "420 BCE-350 BCE"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Isaeus, ca. 420-ca. 350 B.C."
-    ],
-    "fulltext": "oai:ota:oucs:0266;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0266.xml;Isaeus / [by] Isaeus ; with an English translation by Edward Seymour Forster;Isaeus, ca. 420-ca. 350 B.C.;420 BCE-350 BCE;text_and_corpus_linguistics;Poetry, Greek -- Early works to 1800;grc;Oxford Text Archive, University of Oxford;Waite, Stephen V.F.;(1 file : ca. 243 KB);Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2db66d25-9da2-5a50-82ac-c4ca70a5b378",
-    "oai_identifier": [
-        "oai:ota:oucs:0266"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poetry"
-        },
-        {
-            "name": "Greek -- Early works"
-        }
-    ],
-    "title": [
-        "Isaeus / [by] Isaeus ; with an English translation by Edward Seymour Forster"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0266.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2dced3ed-3b03-56f0-b22d-3ba08d9dd6b9.json b/oaitestdata/clarin-oai_dc/SET_1/json/2dced3ed-3b03-56f0-b22d-3ba08d9dd6b9.json
deleted file mode 100644
index f1fd775a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2dced3ed-3b03-56f0-b22d-3ba08d9dd6b9.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-966",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-966"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-966",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-966;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS North Picene;48 tokens;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-966;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#npik",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2dced3ed-3b03-56f0-b22d-3ba08d9dd6b9",
-    "notes": [
-        "48 tokens"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-966"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS North Picene"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2dd0fa9c-ed35-51a0-a297-cb79f52789ff.json b/oaitestdata/clarin-oai_dc/SET_1/json/2dd0fa9c-ed35-51a0-a297-cb79f52789ff.json
deleted file mode 100644
index eaec607c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2dd0fa9c-ed35-51a0-a297-cb79f52789ff.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Newcastle University"
-    ],
-    "Contributor": [
-        "Corrigan, Karen"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/tei+xml",
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-894",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-894"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-894",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Newcastle University"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-894;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Newcastle electronic corpus of Tyneside English (NECTE);Corrigan, Karen;A corpus of dialect speech from Tyneside in North-East England. digitized audio, standard orthographic transcription, phonetic transcription, and part-of-speech tagged;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-894;eng;application/tei+xml;downloadable_files_count: 0;United Kingdom;Newcastle University;http://www.ncl.ac.uk/necte/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2dd0fa9c-ed35-51a0-a297-cb79f52789ff",
-    "notes": [
-        "A corpus of dialect speech from Tyneside in North-East England. digitized audio, standard orthographic transcription, phonetic transcription, and part-of-speech tagged"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-894"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Newcastle electronic corpus of Tyneside English (NECTE)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2dd1fcf3-e473-57a4-a009-a0a2a19a85a1.json b/oaitestdata/clarin-oai_dc/SET_1/json/2dd1fcf3-e473-57a4-a009-a0a2a19a85a1.json
deleted file mode 100644
index 3ec038f3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2dd1fcf3-e473-57a4-a009-a0a2a19a85a1.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4120",
-    "MetadataAccess": [
-        "oai:ota:oucs:4120"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Arbuthnot, John, 1667-1735."
-    ],
-    "fulltext": "oai:ota:oucs:4120;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4120.xml;A postscript to John Bull: containing the history of the Crown-Inn, with the death of the widow, and what happened thereon.;Arbuthnot, John, 1667-1735.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2dd1fcf3-e473-57a4-a009-a0a2a19a85a1",
-    "oai_identifier": [
-        "oai:ota:oucs:4120"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A postscript to John Bull: containing the history of the Crown-Inn, with the death of the widow, and what happened thereon."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4120.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2ddc2d16-3452-56f6-a350-db5c0c46e244.json b/oaitestdata/clarin-oai_dc/SET_1/json/2ddc2d16-3452-56f6-a350-db5c0c46e244.json
deleted file mode 100644
index 9274f534..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2ddc2d16-3452-56f6-a350-db5c0c46e244.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Sienkiewicz"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/111",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/111"
-    ],
-    "PID": "http://hdl.handle.net/11321/111",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Sienkiewicz"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Sienkiewicz, Sienkiewicz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/111;2015-04-08T14:15:30Z;hdl_11321_3;hdl_11321_4;MWE Sienkiewicz, Rodzina Po\u0142anieckich;Sienkiewicz, Sienkiewicz;Sienkiewicz;2015-04-08;corpus;http://hdl.handle.net/11321/111;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain; charset=utf-8;downloadable_files_count: 1;Sienkiewicz",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2ddc2d16-3452-56f6-a350-db5c0c46e244",
-    "notes": [
-        "Sienkiewicz"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/111"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Sienkiewicz, Rodzina Po\u0142anieckich"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2dedfc31-4ecb-574a-a532-8d0c7f11ffc5.json b/oaitestdata/clarin-oai_dc/SET_1/json/2dedfc31-4ecb-574a-a532-8d0c7f11ffc5.json
deleted file mode 100644
index fcf62c9e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2dedfc31-4ecb-574a-a532-8d0c7f11ffc5.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=7095d3ac1c4c11e2a2aa782bcb07413529180c96d3904812b3a8eaf6ec88ad9d",
-    "MetadataAccess": [
-        "7095d3ac1c4c11e2a2aa782bcb07413529180c96d3904812b3a8eaf6ec88ad9d"
-    ],
-    "PublicationTimestamp": "2012-10-22T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "fulltext": "7095d3ac1c4c11e2a2aa782bcb07413529180c96d3904812b3a8eaf6ec88ad9d;2018-11-15T16:39:43Z;toolService;toolService:tool;SENTER;SENTER is a SENtence splitTER for Portuguese.;2012-10-22",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2dedfc31-4ecb-574a-a532-8d0c7f11ffc5",
-    "notes": [
-        "SENTER is a SENtence splitTER for Portuguese."
-    ],
-    "oai_identifier": [
-        "7095d3ac1c4c11e2a2aa782bcb07413529180c96d3904812b3a8eaf6ec88ad9d"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "SENTER"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2df8b4e7-ccf8-54aa-8aa9-918ed1565740.json b/oaitestdata/clarin-oai_dc/SET_1/json/2df8b4e7-ccf8-54aa-8aa9-918ed1565740.json
deleted file mode 100644
index 79d25e15..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2df8b4e7-ccf8-54aa-8aa9-918ed1565740.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-924",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-924"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-924",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-924;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Pisidian;ca. 80 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-924;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#pisid",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2df8b4e7-ccf8-54aa-8aa9-918ed1565740",
-    "notes": [
-        "ca. 80 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-924"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Pisidian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2dff3d7e-350c-5be4-8c7d-1bd589170bbf.json b/oaitestdata/clarin-oai_dc/SET_1/json/2dff3d7e-350c-5be4-8c7d-1bd589170bbf.json
deleted file mode 100644
index fef37bf4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2dff3d7e-350c-5be4-8c7d-1bd589170bbf.json
+++ /dev/null
@@ -1,89 +0,0 @@
-{
-    "Contact": [
-        "Uppsala University",
-        "Universit\u00e4t des Saarlandes"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "text/plain",
-        "application/pdf",
-        "downloadable_files_count: 4"
-    ],
-    "Language": [
-        "English",
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2614",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2614"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2614",
-    "PublicationTimestamp": "2018-05-08T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Uppsala University",
-        "Universit\u00e4t des Saarlandes"
-    ],
-    "RelatedIdentifier": [
-        "http://www.lrec-conf.org/proceedings/lrec2018/summaries/941.html"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Hardmeier, Christian",
-        "Krielke, Pauline",
-        "Lapshinova-Koltunski, Ekaterina"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2614;2018-05-08T12:07:36Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;ParCorFull: A Parallel Corpus Annotated with Full Coreference;Lapshinova-Koltunski, Ekaterina;Hardmeier, Christian;Krielke, Pauline;parallel corpus;annotated corpus;coreference;anaphora resolution;ParCorFull is a parallel corpus annotated with full coreference chains that has been created to address an important problem that machine translation and other multilingual natural language processing (NLP) technologies face -- translation of coreference across languages. Our corpus contains parallel texts for the language pair English-German, two major European languages. Despite being typologically very close, these languages still have systemic differences in the realisation of coreference, and thus pose problems for multilingual coreference resolution and machine translation. Our parallel corpus covers the genres of planned speech (public lectures) and newswire. It is richly annotated for coreference in both languages, including annotation of both nominal coreference and reference to antecedents expressed as clauses, sentences and verb phrases. This resource supports research in the areas of natural language processing, contrastive linguistics and translation studies on the mechanisms involved in coreference translation in order to develop a better understanding of the phenomenon.;2018-05-08;corpus;http://hdl.handle.net/11372/LRT-2614;eng;deu;http://www.lrec-conf.org/proceedings/lrec2018/summaries/941.html;Creative Commons - Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0);http://creativecommons.org/licenses/by-nc-nd/4.0/;PUB;application/pdf;application/x-gzip;text/plain;application/pdf;text/plain; charset=utf-8;downloadable_files_count: 4;Universit\u00e4t des Saarlandes;Uppsala University;https://github.com/chardmeier/parcor-full",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2dff3d7e-350c-5be4-8c7d-1bd589170bbf",
-    "notes": [
-        "ParCorFull is a parallel corpus annotated with full coreference chains that has been created to address an important problem that machine translation and other multilingual natural language processing (NLP) technologies face -- translation of coreference across languages. Our corpus contains parallel texts for the language pair English-German, two major European languages. Despite being typologically very close, these languages still have systemic differences in the realisation of coreference, and thus pose problems for multilingual coreference resolution and machine translation. Our parallel corpus covers the genres of planned speech (public lectures) and newswire. It is richly annotated for coreference in both languages, including annotation of both nominal coreference and reference to antecedents expressed as clauses, sentences and verb phrases. This resource supports research in the areas of natural language processing, contrastive linguistics and translation studies on the mechanisms involved in coreference translation in order to develop a better understanding of the phenomenon."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2614"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parallel corpus"
-        },
-        {
-            "name": "annotated corpus"
-        },
-        {
-            "name": "coreference"
-        },
-        {
-            "name": "anaphora resolution"
-        }
-    ],
-    "title": [
-        "ParCorFull: A Parallel Corpus Annotated with Full Coreference"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2e1d5db0-1080-5f75-9d4e-ca8ecc2be2be.json b/oaitestdata/clarin-oai_dc/SET_1/json/2e1d5db0-1080-5f75-9d4e-ca8ecc2be2be.json
deleted file mode 100644
index b19b76a3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2e1d5db0-1080-5f75-9d4e-ca8ecc2be2be.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Laboratory of Phonetics and Speech Technology, Tallinn University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1377",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1377"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1377",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Laboratory of Phonetics and Speech Technology, Tallinn University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Estonia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1377;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Estonian Text-to-Speech Synthesiser for the Blind;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1377;downloadable_files_count: 0;Estonia;Laboratory of Phonetics and Speech Technology, Tallinn University of Technology;https://phon.ioc.ee/dokuwiki/doku.php?id=projects:projects.et",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2e1d5db0-1080-5f75-9d4e-ca8ecc2be2be",
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1377"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Estonian Text-to-Speech Synthesiser for the Blind"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2e1f7ff1-385a-54c9-8ebf-f78500984275.json b/oaitestdata/clarin-oai_dc/SET_1/json/2e1f7ff1-385a-54c9-8ebf-f78500984275.json
deleted file mode 100644
index 06189866..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2e1f7ff1-385a-54c9-8ebf-f78500984275.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2467",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2467"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2467",
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Ku\u010dera, Ond\u0159ej",
-        "Kuchy\u0148ov\u00e1, Karol\u00edna",
-        "Hladk\u00e1, Barbora"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2467;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;STYX 1.0 (2017-10-03);Hladk\u00e1, Barbora;Ku\u010dera, Ond\u0159ej;Kuchy\u0148ov\u00e1, Karol\u00edna;annotated corpus;syntax;sentence diagramming;STYX 1.0 is a corpus of Czech sentences selected from the Prague Dependency treebank. The criterion for including sentences into STYX was their suitability for practicing Czech morphology and syntax in elementary schools. The sentences contain both the PDT annotations and the school sentence analyses. The school sentence analyses were created by transforming the PDT annotations using handcrafted rules. Altogether the STYX 1.0 corpus contains 11 655 sentences.\r\n\r\nOriginally, the STYX 1.0 corpus was an inseparable part of the Styx system (http://hdl.handle.net/11858/00-097C-0000-0001-48FB-F);2017;corpus;http://hdl.handle.net/11234/1-2467;ces;Creative Commons - Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0);http://creativecommons.org/licenses/by-nc-nd/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/styx",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2e1f7ff1-385a-54c9-8ebf-f78500984275",
-    "notes": [
-        "STYX 1.0 is a corpus of Czech sentences selected from the Prague Dependency treebank. The criterion for including sentences into STYX was their suitability for practicing Czech morphology and syntax in elementary schools. The sentences contain both the PDT annotations and the school sentence analyses. The school sentence analyses were created by transforming the PDT annotations using handcrafted rules. Altogether the STYX 1.0 corpus contains 11 655 sentences.\r\n\r\nOriginally, the STYX 1.0 corpus was an inseparable part of the Styx system (http://hdl.handle.net/11858/00-097C-0000-0001-48FB-F)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2467"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "annotated corpus"
-        },
-        {
-            "name": "syntax"
-        },
-        {
-            "name": "sentence diagramming"
-        }
-    ],
-    "title": [
-        "STYX 1.0 (2017-10-03)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2e2c5168-86d4-5a0d-bdf4-6f20f4178011.json b/oaitestdata/clarin-oai_dc/SET_1/json/2e2c5168-86d4-5a0d-bdf4-6f20f4178011.json
deleted file mode 100644
index c60de875..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2e2c5168-86d4-5a0d-bdf4-6f20f4178011.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5189",
-    "MetadataAccess": [
-        "oai:ota:oucs:5189"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Inchbald, Mrs., 1753-1821."
-    ],
-    "fulltext": "oai:ota:oucs:5189;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5189.xml;A simple story: In four volumes. By Mrs. Inchbald. [pt.4];Inchbald, Mrs., 1753-1821.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2e2c5168-86d4-5a0d-bdf4-6f20f4178011",
-    "oai_identifier": [
-        "oai:ota:oucs:5189"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A simple story: In four volumes. By Mrs. Inchbald. [pt.4]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5189.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2e455d29-1a61-5342-b14d-9ba49bafcbea.json b/oaitestdata/clarin-oai_dc/SET_1/json/2e455d29-1a61-5342-b14d-9ba49bafcbea.json
deleted file mode 100644
index c5af1883..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2e455d29-1a61-5342-b14d-9ba49bafcbea.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Simov, Kiril"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Bulgarian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-222",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-222"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-222",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Bulgaria"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-222;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;BulTreeBank POS Corpus;Simov, Kiril;Written, synchronic, general, manually annotated; 50 000 tokens, 2600 sentences extracted from the BulTreeBank Text Archive in order to contain the most frequent ambiguity classes in Bulgarian;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-222;bul;downloadable_files_count: 0;Bulgaria;http://www.bultreebank.org/Resources.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2e455d29-1a61-5342-b14d-9ba49bafcbea",
-    "notes": [
-        "Written, synchronic, general, manually annotated; 50 000 tokens, 2600 sentences extracted from the BulTreeBank Text Archive in order to contain the most frequent ambiguity classes in Bulgarian"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-222"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "BulTreeBank POS Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2e733415-4a3c-582f-8dd3-0c62462ffc27.json b/oaitestdata/clarin-oai_dc/SET_1/json/2e733415-4a3c-582f-8dd3-0c62462ffc27.json
deleted file mode 100644
index 1b941c31..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2e733415-4a3c-582f-8dd3-0c62462ffc27.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Smith, John B."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain",
-        "(1 file : ca. 267 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0147",
-    "MetadataAccess": [
-        "oai:ota:oucs:0147"
-    ],
-    "PublicationTimestamp": "1906-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1906"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Short stories"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Woolf, Virginia, 1882-1941"
-    ],
-    "fulltext": "oai:ota:oucs:0147;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0147.xml;A haunted house : and other short stories / Virginia Woolf;Woolf, Virginia, 1882-1941;1906-1941;text_and_corpus_linguistics;Short stories, English -- 20th century;eng;Oxford Text Archive, University of Oxford;Smith, John B.;text/plain;(1 file : ca. 267 KB);Text;Short stories;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2e733415-4a3c-582f-8dd3-0c62462ffc27",
-    "oai_identifier": [
-        "oai:ota:oucs:0147"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Short stories"
-        },
-        {
-            "name": "English -- th century"
-        }
-    ],
-    "title": [
-        "A haunted house : and other short stories / Virginia Woolf"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0147.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2e75d0e9-ab74-5e19-8022-1cc6fd954a0d.json b/oaitestdata/clarin-oai_dc/SET_1/json/2e75d0e9-ab74-5e19-8022-1cc6fd954a0d.json
deleted file mode 100644
index b8554e5c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2e75d0e9-ab74-5e19-8022-1cc6fd954a0d.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "The Research Institute for the Languages of Finland"
-    ],
-    "Contributor": [
-        "Lounela, Mikko"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Finnish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-772",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-772"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-772",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "The Research Institute for the Languages of Finland"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Finland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-772;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Corpus of Early Literary Finnish;Lounela, Mikko;period: 1809-1899;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-772;fin;downloadable_files_count: 0;Finland;The Research Institute for the Languages of Finland;http://kaino.kotus.fi/korpus/1800/meta/1800_coll_rdf.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2e75d0e9-ab74-5e19-8022-1cc6fd954a0d",
-    "notes": [
-        "period: 1809-1899"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-772"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus of Early Literary Finnish"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2e78bcb1-f4d5-5ff4-b905-78bf53d76b16.json b/oaitestdata/clarin-oai_dc/SET_1/json/2e78bcb1-f4d5-5ff4-b905-78bf53d76b16.json
deleted file mode 100644
index bff6696f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2e78bcb1-f4d5-5ff4-b905-78bf53d76b16.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4324",
-    "MetadataAccess": [
-        "oai:ota:oucs:4324"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Defoe, Daniel, 1661?-1731."
-    ],
-    "fulltext": "oai:ota:oucs:4324;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4324.xml;Considerations upon the eighth and ninth articles of the treaty of commerce and navigation, now publish'd by authority. With some enquiries into the damages that may accrue to the English trade from them;Defoe, Daniel, 1661?-1731.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2e78bcb1-f4d5-5ff4-b905-78bf53d76b16",
-    "oai_identifier": [
-        "oai:ota:oucs:4324"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Considerations upon the eighth and ninth articles of the treaty of commerce and navigation, now publish'd by authority. With some enquiries into the damages that may accrue to the English trade from them"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4324.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2e7fa6e8-c1e4-507f-b952-a29e9d5ef712.json b/oaitestdata/clarin-oai_dc/SET_1/json/2e7fa6e8-c1e4-507f-b952-a29e9d5ef712.json
deleted file mode 100644
index 9e18258c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2e7fa6e8-c1e4-507f-b952-a29e9d5ef712.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "University of Antwerp, University of Tilburg"
-    ],
-    "Contributor": [
-        "Bosch, Antal van den",
-        "Daelemans, Walter"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-318",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-318"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-318",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Antwerp, University of Tilburg"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Belgium||Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-318;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Tilburg Memory-Based Learner;Daelemans, Walter;Bosch, Antal van den;An elegantly simple and robust machine-learning method, based on the combination of ideas from a number of MBL implementations, resulting in a useful tool for NLP research.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-318;downloadable_files_count: 0;Belgium||Netherlands (the);University of Antwerp, University of Tilburg;http://ilk.uvt.nl/timbl/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2e7fa6e8-c1e4-507f-b952-a29e9d5ef712",
-    "notes": [
-        "An elegantly simple and robust machine-learning method, based on the combination of ideas from a number of MBL implementations, resulting in a useful tool for NLP research."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-318"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Tilburg Memory-Based Learner"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2e8922b3-04f2-5675-b396-85ce3ac40321.json b/oaitestdata/clarin-oai_dc/SET_1/json/2e8922b3-04f2-5675-b396-85ce3ac40321.json
deleted file mode 100644
index 0803532e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2e8922b3-04f2-5675-b396-85ce3ac40321.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "s.n."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-165062",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-165062"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CEB-6",
-    "PublicationTimestamp": "1605-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1605"
-    ],
-    "Publisher": [
-        "s.n."
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/165062",
-        "oai:jbc.bj.uj.edu.pl:publication:173487"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1601/1700"
-    ],
-    "TempCoverageBegin": 50506804799,
-    "TempCoverageEnd": 50506804799,
-    "TemporalCoverage": " point in time : 1601-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1601-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1601-07-01T11:59:59Z",
-    "author": [
-        "Pociej, Hipacy (1541-1613)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-165062;2019-03-01T10:47:34Z;O Przywileiach Nadanych od Naia\u015bnieyszych Krolow Polskich, y przednieyszych niektorych dowodach, ktore \u015bwi\u0119t\u0105 Uni\u0105 wielce zalecai\u0105 y potwierdzai\u0105;Pociej, Hipacy (1541-1613);starodruki 17\u00a0w.;s.n.;[1605];starodruk;application/xml;clarind-uds:poldilemma-165062;hdl:11858/00-246C-0000-0023-8CEB-6;Biblioteka Jagiello\u0144ska, BJ St. Dr. Cim. 5123;pol;lat;http://jbc.bj.uj.edu.pl/Content/165062;oai:jbc.bj.uj.edu.pl:publication:173487;1601/1700;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2e8922b3-04f2-5675-b396-85ce3ac40321",
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-165062"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "O Przywileiach Nadanych od Naia\u015bnieyszych Krolow Polskich, y przednieyszych niektorych dowodach, ktore \u015bwi\u0119t\u0105 Uni\u0105 wielce zalecai\u0105 y potwierdzai\u0105"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2e8fee31-3228-5d6f-a695-6baea90e85a0.json b/oaitestdata/clarin-oai_dc/SET_1/json/2e8fee31-3228-5d6f-a695-6baea90e85a0.json
deleted file mode 100644
index 3a9d6b9e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2e8fee31-3228-5d6f-a695-6baea90e85a0.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "text/xml",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Southern Sami",
-        "Norwegian Bokm\u00e5l"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/95",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/95"
-    ],
-    "PID": "http://hdl.handle.net/11509/95",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "The Divvun group at UiT The Arctic University of Norway",
-        "Giellatekno - Saami Language Technology, UiT The Arctic University of Norway"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/95;2016-09-06T12:59:04Z;hdl_11509_1;hdl_11509_2;South Saami-Norwegian Bokm\u00e5l dictionary;Giellatekno - Saami Language Technology, UiT The Arctic University of Norway;The Divvun group at UiT The Arctic University of Norway;Bilingual Lexicon;Norwegian;South Saami;Machine-readable Dictionary;The South Saami-Norwegian Bokm\u00e5l dictionary is the work done by Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language communities. In particular, the following colleagues have contributed to the creation of the ressource: Tove Brustad, Albert J\u00e5ma, Lene Antonsen, Ciprian Gerstenberger, Trond Trosterud, Maja Kappfjell, Sissel J\u00e5ma, Toini Bergstr\u00f8m, Marit Fjellheim, Sjur Moshagen, and Thomas Omma. The dictionary contains 11047 entries in Giellatekno's dictionary xml format. In spite of the extensive quality control, it may contain entries with objectionable translations. If you find any errors or want to add more words, download the file, edit it, and send it back to giellatekno@uit.no and feedback@divvun.no.\r\nPlease note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata).;2015;lexicalConceptualResource;http://hdl.handle.net/11509/95;sma;nob;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;text/xml;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Giellatekno - Saami Language Technology;http://giellatekno.uit.no/index.eng.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2e8fee31-3228-5d6f-a695-6baea90e85a0",
-    "notes": [
-        "The South Saami-Norwegian Bokm\u00e5l dictionary is the work done by Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language communities. In particular, the following colleagues have contributed to the creation of the ressource: Tove Brustad, Albert J\u00e5ma, Lene Antonsen, Ciprian Gerstenberger, Trond Trosterud, Maja Kappfjell, Sissel J\u00e5ma, Toini Bergstr\u00f8m, Marit Fjellheim, Sjur Moshagen, and Thomas Omma. The dictionary contains 11047 entries in Giellatekno's dictionary xml format. In spite of the extensive quality control, it may contain entries with objectionable translations. If you find any errors or want to add more words, download the file, edit it, and send it back to giellatekno@uit.no and feedback@divvun.no.\r\nPlease note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata)."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/95"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Bilingual Lexicon"
-        },
-        {
-            "name": "Norwegian"
-        },
-        {
-            "name": "South Saami"
-        },
-        {
-            "name": "Machine-readable Dictionary"
-        }
-    ],
-    "title": [
-        "South Saami-Norwegian Bokm\u00e5l dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2eb73c26-ae44-54a8-85fe-efe700e3a882.json b/oaitestdata/clarin-oai_dc/SET_1/json/2eb73c26-ae44-54a8-85fe-efe700e3a882.json
deleted file mode 100644
index bb239a48..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2eb73c26-ae44-54a8-85fe-efe700e3a882.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "text/plain",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1821",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1821"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1821",
-    "PublicationTimestamp": "2016-11-07T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-2509"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "BSD 2-Clause \"Simplified\" or \"FreeBSD\" license",
-        "http://opensource.org/licenses/BSD-2-Clause",
-        "PUB"
-    ],
-    "author": [
-        "Nov\u00e1k, Michal",
-        "M\u00edrovsk\u00fd, Ji\u0159\u00ed",
-        "Rysov\u00e1, Magdal\u00e9na",
-        "Rysov\u00e1, Kate\u0159ina"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1821;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;EVALD 1.0 for Foreigners;Rysov\u00e1, Kate\u0159ina;M\u00edrovsk\u00fd, Ji\u0159\u00ed;Nov\u00e1k, Michal;Rysov\u00e1, Magdal\u00e9na;text coherence;discourse;automatic evaluation;non-native speakers;EVALD 1.0 for Foreigners is a software for automatic evaluation of surface coherence (cohesion) in Czech texts written by non-native speakers of Czech.;2016-11-07;toolService;http://hdl.handle.net/11234/1-1821;ces;http://hdl.handle.net/11234/1-2509;BSD 2-Clause \"Simplified\" or \"FreeBSD\" license;http://opensource.org/licenses/BSD-2-Clause;PUB;text/plain; charset=utf-8;text/plain;application/octet-stream;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://ufal.mff.cuni.cz/evald",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2eb73c26-ae44-54a8-85fe-efe700e3a882",
-    "notes": [
-        "EVALD 1.0 for Foreigners is a software for automatic evaluation of surface coherence (cohesion) in Czech texts written by non-native speakers of Czech."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1821"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "text coherence"
-        },
-        {
-            "name": "discourse"
-        },
-        {
-            "name": "automatic evaluation"
-        },
-        {
-            "name": "non-native speakers"
-        }
-    ],
-    "title": [
-        "EVALD 1.0 for Foreigners"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2ebbf0f9-8873-52f9-8295-453cc50905b8.json b/oaitestdata/clarin-oai_dc/SET_1/json/2ebbf0f9-8873-52f9-8295-453cc50905b8.json
deleted file mode 100644
index 578e0ec4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2ebbf0f9-8873-52f9-8295-453cc50905b8.json
+++ /dev/null
@@ -1,114 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "text/html",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-1AAF-3",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-1AAF-3"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-1AAF-3",
-    "PublicationTimestamp": "2013-12-31T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11858/00-097C-0000-0006-DB11-8",
-        "http://hdl.handle.net/11858/00-097C-0000-0008-E130-A",
-        "http://hdl.handle.net/11234/1-1905",
-        "http://hdl.handle.net/11234/1-2621"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "M\u00edrovsk\u00fd, Ji\u0159\u00ed",
-        "Nedoluzhko, Anna",
-        "Kol\u00e1\u0159ov\u00e1, Veronika",
-        "Haji\u010d, Jan",
-        "Pol\u00e1kov\u00e1, Lucie",
-        "\u0160t\u011bp\u00e1nek, Jan",
-        "Mikulov\u00e1, Marie",
-        "Zik\u00e1nov\u00e1, \u0160\u00e1rka",
-        "\u0160ev\u010d\u00edkov\u00e1, Magda",
-        "Haji\u010dov\u00e1, Eva",
-        "Bej\u010dek, Eduard",
-        "Panevov\u00e1, Jarmila",
-        "J\u00ednov\u00e1, Pavl\u00edna",
-        "Kettnerov\u00e1, V\u00e1clava"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-1AAF-3;2018-07-02T22:05:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Prague Dependency Treebank 3.0;Bej\u010dek, Eduard;Haji\u010dov\u00e1, Eva;Haji\u010d, Jan;J\u00ednov\u00e1, Pavl\u00edna;Kettnerov\u00e1, V\u00e1clava;Kol\u00e1\u0159ov\u00e1, Veronika;Mikulov\u00e1, Marie;M\u00edrovsk\u00fd, Ji\u0159\u00ed;Nedoluzhko, Anna;Panevov\u00e1, Jarmila;Pol\u00e1kov\u00e1, Lucie;\u0160ev\u010d\u00edkov\u00e1, Magda;\u0160t\u011bp\u00e1nek, Jan;Zik\u00e1nov\u00e1, \u0160\u00e1rka;treebank;dependency;tectogrammatics;topic-focus articulation;multiword expressions;coreference;bridging relations;discourse;PDT;PDT 3.0 is a new version of Prague Dependency Treebank. It contains a large amount of Czech texts with complex and interlinked morphological (2 million words), syntactic (1.5 MW) and semantic annotation (0.8 MW); in addition, certain properties of sentence information structure, multiword expressions, coreference, bridging relations and discourse relations are annotated at the semantic level.;2013-12-31;corpus;PDT 3.0;http://hdl.handle.net/11858/00-097C-0000-0023-1AAF-3;ces;http://hdl.handle.net/11858/00-097C-0000-0006-DB11-8;http://hdl.handle.net/11858/00-097C-0000-0008-E130-A;http://hdl.handle.net/11234/1-1905;http://hdl.handle.net/11234/1-2621;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;text/html;application/zip;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/pdt3.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2ebbf0f9-8873-52f9-8295-453cc50905b8",
-    "notes": [
-        "PDT 3.0 is a new version of Prague Dependency Treebank. It contains a large amount of Czech texts with complex and interlinked morphological (2 million words), syntactic (1.5 MW) and semantic annotation (0.8 MW); in addition, certain properties of sentence information structure, multiword expressions, coreference, bridging relations and discourse relations are annotated at the semantic level."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-1AAF-3"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "dependency"
-        },
-        {
-            "name": "tectogrammatics"
-        },
-        {
-            "name": "topic-focus articulation"
-        },
-        {
-            "name": "multiword expressions"
-        },
-        {
-            "name": "coreference"
-        },
-        {
-            "name": "bridging relations"
-        },
-        {
-            "name": "discourse"
-        },
-        {
-            "name": "PDT"
-        }
-    ],
-    "title": [
-        "Prague Dependency Treebank 3.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2ec64985-d4b0-5219-9bbe-642916bb16e6.json b/oaitestdata/clarin-oai_dc/SET_1/json/2ec64985-d4b0-5219-9bbe-642916bb16e6.json
deleted file mode 100644
index 1c149d2a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2ec64985-d4b0-5219-9bbe-642916bb16e6.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3821",
-    "MetadataAccess": [
-        "oai:ota:oucs:3821"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Richardson, Samuel, 1689-1761."
-    ],
-    "fulltext": "oai:ota:oucs:3821;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3821.xml;An address to the public, on the treatment which the editor of the History of Sir Charles Grandison has met with from certain booksellers and printers in Dublin. Including observations on Mr. Faulkner's defence of himself, published in his Irish news-paper of Nov. 3. 1753;Richardson, Samuel, 1689-1761.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2ec64985-d4b0-5219-9bbe-642916bb16e6",
-    "oai_identifier": [
-        "oai:ota:oucs:3821"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An address to the public, on the treatment which the editor of the History of Sir Charles Grandison has met with from certain booksellers and printers in Dublin. Including observations on Mr. Faulkner's defence of himself, published in his Irish news-paper of Nov. 3. 1753"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3821.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2ee77c33-020a-5a32-9a3e-c6d7a43ac36c.json b/oaitestdata/clarin-oai_dc/SET_1/json/2ee77c33-020a-5a32-9a3e-c6d7a43ac36c.json
deleted file mode 100644
index a004e12d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2ee77c33-020a-5a32-9a3e-c6d7a43ac36c.json
+++ /dev/null
@@ -1,49 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5640",
-    "MetadataAccess": [
-        "oai:ota:oucs:5640"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:5640;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5640.xml;A practical display of the philosophical system called animal magnetism, in which is explained different modes of treating, with some medical observations on the diseases of the human body,;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2ee77c33-020a-5a32-9a3e-c6d7a43ac36c",
-    "oai_identifier": [
-        "oai:ota:oucs:5640"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A practical display of the philosophical system called animal magnetism, in which is explained different modes of treating, with some medical observations on the diseases of the human body,"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5640.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2eeae4ea-efa1-5eff-ae63-c900f7951078.json b/oaitestdata/clarin-oai_dc/SET_1/json/2eeae4ea-efa1-5eff-ae63-c900f7951078.json
deleted file mode 100644
index a4dd3a2b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2eeae4ea-efa1-5eff-ae63-c900f7951078.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 70 KB)"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0274",
-    "MetadataAccess": [
-        "oai:ota:oucs:0274"
-    ],
-    "PublicationYear": [
-        "409 BCE-405 BCE"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Sophocles"
-    ],
-    "fulltext": "oai:ota:oucs:0274;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0274.xml;Electra / Sophocles;The Electra of Sophocles;Sophocles;409 BCE-405 BCE;text_and_corpus_linguistics;Greek drama (Tragedy) -- 5th century B.C.;grc;Oxford Text Archive, University of Oxford;(1 file : ca. 70 KB);Text;Plays;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2eeae4ea-efa1-5eff-ae63-c900f7951078",
-    "oai_identifier": [
-        "oai:ota:oucs:0274"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Greek drama Tragedy -- th century B.C."
-        }
-    ],
-    "title": [
-        "Electra / Sophocles",
-        "The Electra of Sophocles"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0274.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2f06e9c4-dcea-5e8b-96ad-7f0b95fae699.json b/oaitestdata/clarin-oai_dc/SET_1/json/2f06e9c4-dcea-5e8b-96ad-7f0b95fae699.json
deleted file mode 100644
index d5eba1ef..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2f06e9c4-dcea-5e8b-96ad-7f0b95fae699.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 848 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1802",
-    "MetadataAccess": [
-        "oai:ota:oucs:1802"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hardy, Thomas, 1840-1928"
-    ],
-    "fulltext": "oai:ota:oucs:1802;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/1802.xml;Far from the madding crowd / Thomas Hardy;Hardy, Thomas, 1840-1928;text_and_corpus_linguistics;English fiction -- 19th century;Oxford Text Archive, University of Oxford;Triggs, Jeffery;text/sgml;(1 file : ca. 848 KB);Text;Novels;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2f06e9c4-dcea-5e8b-96ad-7f0b95fae699",
-    "oai_identifier": [
-        "oai:ota:oucs:1802"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English fiction -- th century"
-        }
-    ],
-    "title": [
-        "Far from the madding crowd / Thomas Hardy"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1802.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2f089c04-ca1f-5621-9819-e8dd2ede2504.json b/oaitestdata/clarin-oai_dc/SET_1/json/2f089c04-ca1f-5621-9819-e8dd2ede2504.json
deleted file mode 100644
index 1f2d41aa..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2f089c04-ca1f-5621-9819-e8dd2ede2504.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5582",
-    "MetadataAccess": [
-        "oai:ota:oucs:5582"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Buchan, William, 1729-1805."
-    ],
-    "fulltext": "oai:ota:oucs:5582;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5582.xml;A letter to the patentee, concerning the medical properties of the fleecy hosiery: By William Buchan,...;Buchan, William, 1729-1805.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2f089c04-ca1f-5621-9819-e8dd2ede2504",
-    "oai_identifier": [
-        "oai:ota:oucs:5582"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A letter to the patentee, concerning the medical properties of the fleecy hosiery: By William Buchan,..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5582.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2f1d3912-d1cc-5051-845e-9935309a1b7b.json b/oaitestdata/clarin-oai_dc/SET_1/json/2f1d3912-d1cc-5051-845e-9935309a1b7b.json
deleted file mode 100644
index cf3d1f5f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2f1d3912-d1cc-5051-845e-9935309a1b7b.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3589",
-    "MetadataAccess": [
-        "oai:ota:oucs:3589"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Churchill, Charles, 1731-1764."
-    ],
-    "fulltext": "oai:ota:oucs:3589;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3589.xml;Gotham. A poem. Book II. By C. Churchill;Churchill, Charles, 1731-1764.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2f1d3912-d1cc-5051-845e-9935309a1b7b",
-    "oai_identifier": [
-        "oai:ota:oucs:3589"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Gotham. A poem. Book II. By C. Churchill"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3589.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2f3d6d90-d547-539c-9669-8d752c581bcf.json b/oaitestdata/clarin-oai_dc/SET_1/json/2f3d6d90-d547-539c-9669-8d752c581bcf.json
deleted file mode 100644
index 7b2a53b5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2f3d6d90-d547-539c-9669-8d752c581bcf.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3127",
-    "MetadataAccess": [
-        "oai:ota:oucs:3127"
-    ],
-    "PublicationTimestamp": "1920-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1920"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Lawrence, D.H. (David Herbert), 1885-1930"
-    ],
-    "fulltext": "oai:ota:oucs:3127;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3127.xml;Women in Love;Lawrence, D.H. (David Herbert), 1885-1930;not after: 1920;text_and_corpus_linguistics;English fiction -- 20th century;eng;Oxford Text Archive, University of Oxford;Triggs, Jeffery;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2f3d6d90-d547-539c-9669-8d752c581bcf",
-    "oai_identifier": [
-        "oai:ota:oucs:3127"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English fiction -- th century"
-        }
-    ],
-    "title": [
-        "Women in Love"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3127.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2f4cc0ed-3323-5caa-84d4-f5f8e241c511.json b/oaitestdata/clarin-oai_dc/SET_1/json/2f4cc0ed-3323-5caa-84d4-f5f8e241c511.json
deleted file mode 100644
index d6c19bcb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2f4cc0ed-3323-5caa-84d4-f5f8e241c511.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Department of Informatics, Human Language Technology Group, University of Szeged"
-    ],
-    "Contributor": [
-        "Vincze, Veronika"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/xml"
-    ],
-    "Language": [
-        "Hungarian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-200",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-200"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-200",
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "Department of Informatics, Human Language Technology Group, University of Szeged"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Hungary"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-200;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Szeged Treebank 1.0;Vincze, Veronika;82,000 sentences with shallow syntactic annotation (NP-level).;2003;corpus;http://hdl.handle.net/11372/LRT-200;hun;application/xml;downloadable_files_count: 0;Hungary;Department of Informatics, Human Language Technology Group, University of Szeged;http://www.inf.u-szeged.hu/projectdirs/hlt/index_en.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2f4cc0ed-3323-5caa-84d4-f5f8e241c511",
-    "notes": [
-        "82,000 sentences with shallow syntactic annotation (NP-level)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-200"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Szeged Treebank 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2f588b04-d8b2-5518-a1a4-913c35fe9cc6.json b/oaitestdata/clarin-oai_dc/SET_1/json/2f588b04-d8b2-5518-a1a4-913c35fe9cc6.json
deleted file mode 100644
index 53c00835..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2f588b04-d8b2-5518-a1a4-913c35fe9cc6.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "between 1 and 2 MB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1229",
-    "MetadataAccess": [
-        "oai:ota:oucs:1229"
-    ],
-    "PublicationTimestamp": "1813-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1813"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Austen, Jane,  1775-1817"
-    ],
-    "fulltext": "oai:ota:oucs:1229;2018-02-21T11:28:16Z;http://ota.ox.ac.uk/headers/1229.xml; Pride and prejudice  : (tagged version) / compiled by J.F. Burrows;Austen, Jane,  1775-1817;1813;text_and_corpus_linguistics;Novels -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;between 1 and 2 MB;Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2f588b04-d8b2-5518-a1a4-913c35fe9cc6",
-    "oai_identifier": [
-        "oai:ota:oucs:1229"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Novels -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        " Pride and prejudice  : (tagged version) / compiled by J.F. Burrows"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1229.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2f710663-bd98-53e5-9fac-c2e3cbc889a2.json b/oaitestdata/clarin-oai_dc/SET_1/json/2f710663-bd98-53e5-9fac-c2e3cbc889a2.json
deleted file mode 100644
index 189752b9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2f710663-bd98-53e5-9fac-c2e3cbc889a2.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-1B22-8",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-1B22-8"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-1B22-8",
-    "PublicationTimestamp": "2014-01-09T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "Straka, Milan",
-        "Strakov\u00e1, Jana",
-        "\u0160ev\u010d\u00edkov\u00e1, Magda"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-1B22-8;2018-07-02T22:05:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Czech Named Entity Corpus 2.0;\u0160ev\u010d\u00edkov\u00e1, Magda;\u017dabokrtsk\u00fd, Zden\u011bk;Strakov\u00e1, Jana;Straka, Milan;named entity recognition;Czech Named Entity Corpus 2.0 is a corpus of 8993 Czech sentences with manually annotated 35220 Czech named entities, classified according to a two-level hierarchy of 46 named entities.;2014-01-09;corpus;http://hdl.handle.net/11858/00-097C-0000-0023-1B22-8;ces;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/cnec/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2f710663-bd98-53e5-9fac-c2e3cbc889a2",
-    "notes": [
-        "Czech Named Entity Corpus 2.0 is a corpus of 8993 Czech sentences with manually annotated 35220 Czech named entities, classified according to a two-level hierarchy of 46 named entities."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-1B22-8"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "named entity recognition"
-        }
-    ],
-    "title": [
-        "Czech Named Entity Corpus 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2f7c36d8-3da3-5256-bdfe-83e81a8dc6d1.json b/oaitestdata/clarin-oai_dc/SET_1/json/2f7c36d8-3da3-5256-bdfe-83e81a8dc6d1.json
deleted file mode 100644
index c249e475..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2f7c36d8-3da3-5256-bdfe-83e81a8dc6d1.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3986",
-    "MetadataAccess": [
-        "oai:ota:oucs:3986"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "More, Hannah, 1745-1833."
-    ],
-    "fulltext": "oai:ota:oucs:3986;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3986.xml;The Hackney coachman; or, the way to get a good fare;More, Hannah, 1745-1833.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2f7c36d8-3da3-5256-bdfe-83e81a8dc6d1",
-    "oai_identifier": [
-        "oai:ota:oucs:3986"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The Hackney coachman; or, the way to get a good fare"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3986.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2f81402a-c297-5ba4-aece-691ca682d466.json b/oaitestdata/clarin-oai_dc/SET_1/json/2f81402a-c297-5ba4-aece-691ca682d466.json
deleted file mode 100644
index a0d9ee8e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2f81402a-c297-5ba4-aece-691ca682d466.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5466",
-    "MetadataAccess": [
-        "oai:ota:oucs:5466"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Whitehead, William, of Newcastle."
-    ],
-    "fulltext": "oai:ota:oucs:5466;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5466.xml;The Newcastle and Gateshead directory: for 1782, 83, and 84. Containing the names, trades, and situation of the warehouses, shops, &c. ...;Whitehead, William, of Newcastle.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2f81402a-c297-5ba4-aece-691ca682d466",
-    "oai_identifier": [
-        "oai:ota:oucs:5466"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The Newcastle and Gateshead directory: for 1782, 83, and 84. Containing the names, trades, and situation of the warehouses, shops, &c. ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5466.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2fa23387-455a-51f3-8ee3-db9c1deb5d25.json b/oaitestdata/clarin-oai_dc/SET_1/json/2fa23387-455a-51f3-8ee3-db9c1deb5d25.json
deleted file mode 100644
index d6cf59c1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2fa23387-455a-51f3-8ee3-db9c1deb5d25.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4278",
-    "MetadataAccess": [
-        "oai:ota:oucs:4278"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pinkerton, John, 1758-1826."
-    ],
-    "fulltext": "oai:ota:oucs:4278;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4278.xml;A new tale of a tub: written for the delight and instruction of every British subject in particular, and all the world in general.;Pinkerton, John, 1758-1826.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2fa23387-455a-51f3-8ee3-db9c1deb5d25",
-    "oai_identifier": [
-        "oai:ota:oucs:4278"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A new tale of a tub: written for the delight and instruction of every British subject in particular, and all the world in general."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4278.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2fb10c18-9efc-572e-aa67-fddadc4e64f4.json b/oaitestdata/clarin-oai_dc/SET_1/json/2fb10c18-9efc-572e-aa67-fddadc4e64f4.json
deleted file mode 100644
index 042a702c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2fb10c18-9efc-572e-aa67-fddadc4e64f4.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "PWR Test"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/380",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/380"
-    ],
-    "PID": "http://hdl.handle.net/11321/380",
-    "PublicationTimestamp": "2017-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "PWR Test"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "Tomasz, Naskr\u0119t"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/380;2017-05-30T09:47:35Z;hdl_11321_3;hdl_11321_4;Warsztaty Test 3;Tomasz, Naskr\u0119t;test;test;2017-05-30;corpus;http://hdl.handle.net/11321/380;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;PWR Test",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2fb10c18-9efc-572e-aa67-fddadc4e64f4",
-    "notes": [
-        "test"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/380"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "test"
-        }
-    ],
-    "title": [
-        "Warsztaty Test 3"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2fc4f2f3-6d78-5526-9b6e-fd97edbc292a.json b/oaitestdata/clarin-oai_dc/SET_1/json/2fc4f2f3-6d78-5526-9b6e-fd97edbc292a.json
deleted file mode 100644
index c280970e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2fc4f2f3-6d78-5526-9b6e-fd97edbc292a.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5641",
-    "MetadataAccess": [
-        "oai:ota:oucs:5641"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Musgrave, Samuel, 1732-1780."
-    ],
-    "fulltext": "oai:ota:oucs:5641;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5641.xml;Remarks on Dr. Boerhaave's Theory of the attrition of the blood in the lungs. By Samuel Musgrave,;Musgrave, Samuel, 1732-1780.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2fc4f2f3-6d78-5526-9b6e-fd97edbc292a",
-    "oai_identifier": [
-        "oai:ota:oucs:5641"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Remarks on Dr. Boerhaave's Theory of the attrition of the blood in the lungs. By Samuel Musgrave,"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5641.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2fd9d8a0-eff7-5742-a45a-7dbcc26d99d4.json b/oaitestdata/clarin-oai_dc/SET_1/json/2fd9d8a0-eff7-5742-a45a-7dbcc26d99d4.json
deleted file mode 100644
index d052643f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2fd9d8a0-eff7-5742-a45a-7dbcc26d99d4.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4229",
-    "MetadataAccess": [
-        "oai:ota:oucs:4229"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Cowley, Mrs. (Hannah), 1743-1809."
-    ],
-    "fulltext": "oai:ota:oucs:4229;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4229.xml;The town before you, a comedy: as acted at the Theatre-Royal, Covent-Garden. By Mrs. Cowley.;Cowley, Mrs. (Hannah), 1743-1809.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2fd9d8a0-eff7-5742-a45a-7dbcc26d99d4",
-    "oai_identifier": [
-        "oai:ota:oucs:4229"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The town before you, a comedy: as acted at the Theatre-Royal, Covent-Garden. By Mrs. Cowley."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4229.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2fe11697-2ec4-58a2-a6fd-f2351408e45c.json b/oaitestdata/clarin-oai_dc/SET_1/json/2fe11697-2ec4-58a2-a6fd-f2351408e45c.json
deleted file mode 100644
index 8a1eba19..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2fe11697-2ec4-58a2-a6fd-f2351408e45c.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5031",
-    "MetadataAccess": [
-        "oai:ota:oucs:5031"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Parnell, Thomas, 1679-1718."
-    ],
-    "fulltext": "oai:ota:oucs:5031;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5031.xml;The works: in verse and prose, of Dr. Thomas Parnell, ... Enlarged with variations and poems, not before publish'd.;Parnell, Thomas, 1679-1718.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2fe11697-2ec4-58a2-a6fd-f2351408e45c",
-    "oai_identifier": [
-        "oai:ota:oucs:5031"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The works: in verse and prose, of Dr. Thomas Parnell, ... Enlarged with variations and poems, not before publish'd."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5031.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2fe9075b-11e9-5074-9798-9224ab2d598e.json b/oaitestdata/clarin-oai_dc/SET_1/json/2fe9075b-11e9-5074-9798-9224ab2d598e.json
deleted file mode 100644
index b91ccd4b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2fe9075b-11e9-5074-9798-9224ab2d598e.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=1b16b09ca35a11e1a404080027e73ea29318f60f576147adbd7a74790748894a",
-    "MetadataAccess": [
-        "1b16b09ca35a11e1a404080027e73ea29318f60f576147adbd7a74790748894a"
-    ],
-    "PublicationTimestamp": "2015-12-14T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "1b16b09ca35a11e1a404080027e73ea29318f60f576147adbd7a74790748894a;2019-02-27T12:08:55Z;lexicalConceptualResource;lexicalConceptualResource:framenet;SemLink;SemLink is a project whose aim is to link together different lexical resources via a set of mappings. These mappings will make it possible to combine the different information provided by these different lexical resources for tasks such as inferencing. In the current release, two mappings are available: 1) a mapping between VerbNet and PropBank. 2) a mapping between VerbNet and FrameNet. The version of FrameNet used is v1.2 ;2015-12-14",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2fe9075b-11e9-5074-9798-9224ab2d598e",
-    "notes": [
-        "SemLink is a project whose aim is to link together different lexical resources via a set of mappings. These mappings will make it possible to combine the different information provided by these different lexical resources for tasks such as inferencing. In the current release, two mappings are available: 1) a mapping between VerbNet and PropBank. 2) a mapping between VerbNet and FrameNet. The version of FrameNet used is v1.2 "
-    ],
-    "oai_identifier": [
-        "1b16b09ca35a11e1a404080027e73ea29318f60f576147adbd7a74790748894a"
-    ],
-    "oai_set": [
-        "lexicalConceptualResource",
-        "lexicalConceptualResource:framenet"
-    ],
-    "state": "active",
-    "title": [
-        "SemLink"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2fed18cc-6918-56e5-a4c9-7fd092014efe.json b/oaitestdata/clarin-oai_dc/SET_1/json/2fed18cc-6918-56e5-a4c9-7fd092014efe.json
deleted file mode 100644
index 66734679..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2fed18cc-6918-56e5-a4c9-7fd092014efe.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-935",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-935"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-935",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-935;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Old Slovenian;ca. 800 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-935;slv;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#aslov",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2fed18cc-6918-56e5-a4c9-7fd092014efe",
-    "notes": [
-        "ca. 800 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-935"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Old Slovenian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2fed5ccd-95c4-5d52-9aa5-d46ada1d97e7.json b/oaitestdata/clarin-oai_dc/SET_1/json/2fed5ccd-95c4-5d52-9aa5-d46ada1d97e7.json
deleted file mode 100644
index 314527b8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2fed5ccd-95c4-5d52-9aa5-d46ada1d97e7.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Smith, Donald Jr"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/481",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/481"
-    ],
-    "PID": "http://hdl.handle.net/11321/481",
-    "PublicationTimestamp": "2018-06-19T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Smith, Donald Jr"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Super Cool License",
-        "http://www.google.com",
-        "ACA"
-    ],
-    "author": [
-        "Smith, Donald Jr"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/481;2018-06-19T11:18:04Z;hdl_11321_3;hdl_11321_4;korpus_11;Smith, Donald Jr;test;korpus pr\u00f3bny;2018-06-19;corpus;http://hdl.handle.net/11321/481;pol;Super Cool License;http://www.google.com;ACA;text/plain; charset=utf-8;application/msword;text/plain;downloadable_files_count: 2;Smith, Donald Jr",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2fed5ccd-95c4-5d52-9aa5-d46ada1d97e7",
-    "notes": [
-        "korpus pr\u00f3bny"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/481"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "test"
-        }
-    ],
-    "title": [
-        "korpus_11"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2ff13a2d-a312-58c2-937e-f2876bbd9a21.json b/oaitestdata/clarin-oai_dc/SET_1/json/2ff13a2d-a312-58c2-937e-f2876bbd9a21.json
deleted file mode 100644
index 841765b7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2ff13a2d-a312-58c2-937e-f2876bbd9a21.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "text/plain",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/269",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/269"
-    ],
-    "PID": "http://hdl.handle.net/11321/269",
-    "PublicationTimestamp": "2016-05-29T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "Sikora, Piotr"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/269;2016-05-31T07:53:56Z;hdl_11321_3;hdl_11321_4;Topos\u0142aw 2 (2016-05-31);Sikora, Piotr;inflection;multi-word units;Topos\u0142aw 2 is an editor of multi-world unit inflection lexicons.;2016-05-29;toolService;http://hdl.handle.net/11321/269;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;text/plain;application/octet-stream;downloadable_files_count: 2;Institute of Computer Science, Polish Academy of Sciences;http://zil.ipipan.waw.pl/Toposlaw",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2ff13a2d-a312-58c2-937e-f2876bbd9a21",
-    "notes": [
-        "Topos\u0142aw 2 is an editor of multi-world unit inflection lexicons."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/269"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "inflection"
-        },
-        {
-            "name": "multi-word units"
-        }
-    ],
-    "title": [
-        "Topos\u0142aw 2 (2016-05-31)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/2ff74715-9df7-5273-9db0-800dd902cd02.json b/oaitestdata/clarin-oai_dc/SET_1/json/2ff74715-9df7-5273-9db0-800dd902cd02.json
deleted file mode 100644
index 93367bea..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/2ff74715-9df7-5273-9db0-800dd902cd02.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4724",
-    "MetadataAccess": [
-        "oai:ota:oucs:4724"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Francis, Philip, Sir, 1740-1818."
-    ],
-    "fulltext": "oai:ota:oucs:4724;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4724.xml;The question as it stood in March 1798;Francis, Philip, Sir, 1740-1818.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2ff74715-9df7-5273-9db0-800dd902cd02",
-    "oai_identifier": [
-        "oai:ota:oucs:4724"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The question as it stood in March 1798"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4724.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/30181e64-d158-50c4-a835-bbce1e905651.json b/oaitestdata/clarin-oai_dc/SET_1/json/30181e64-d158-50c4-a835-bbce1e905651.json
deleted file mode 100644
index 25f1b5ff..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/30181e64-d158-50c4-a835-bbce1e905651.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Dutch",
-        "English",
-        "French",
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1048",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1048"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1048",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1048;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;L2 Acquisition Finiteness and Scope;Language Acquisition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1048;nld;eng;fra;deu;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI516911%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "30181e64-d158-50c4-a835-bbce1e905651",
-    "notes": [
-        "Language Acquisition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1048"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "L2 Acquisition Finiteness and Scope"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/302c7efa-b334-558c-a72c-4ce3863317c1.json b/oaitestdata/clarin-oai_dc/SET_1/json/302c7efa-b334-558c-a72c-4ce3863317c1.json
deleted file mode 100644
index 266824e0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/302c7efa-b334-558c-a72c-4ce3863317c1.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4044",
-    "MetadataAccess": [
-        "oai:ota:oucs:4044"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "White, Gilbert, 1720-1793."
-    ],
-    "fulltext": "oai:ota:oucs:4044;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4044.xml;A naturalist's calendar, with observations in various branches of natural history; extracted from the papers of the late Rev. Gilbert White,;White, Gilbert, 1720-1793.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "302c7efa-b334-558c-a72c-4ce3863317c1",
-    "oai_identifier": [
-        "oai:ota:oucs:4044"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A naturalist's calendar, with observations in various branches of natural history; extracted from the papers of the late Rev. Gilbert White,"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4044.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3032f56d-e167-5bf3-b209-95b648fd2195.json b/oaitestdata/clarin-oai_dc/SET_1/json/3032f56d-e167-5bf3-b209-95b648fd2195.json
deleted file mode 100644
index e82d69f2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3032f56d-e167-5bf3-b209-95b648fd2195.json
+++ /dev/null
@@ -1,136 +0,0 @@
-{
-    "Contact": [
-        "Technische Universit\u00e4t Darmstadt"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/x-gzip",
-        "downloadable_files_count: 62",
-        "text/plain"
-    ],
-    "Language": [
-        "Afrikaans",
-        "Arabic",
-        "Bengali",
-        "Bulgarian",
-        "Czech",
-        "Danish",
-        "German",
-        "Modern Greek (1453-)",
-        "English",
-        "Estonian",
-        "Persian",
-        "Finnish",
-        "French",
-        "Gujarati",
-        "Hebrew",
-        "Hindi",
-        "Croatian",
-        "Hungarian",
-        "Indonesian",
-        "Italian",
-        "Japanese",
-        "Kannada",
-        "Korean",
-        "Latvian",
-        "Lithuanian",
-        "Malayalam",
-        "Marathi",
-        "Macedonian",
-        "Nepali (macrolanguage)",
-        "Dutch",
-        "Norwegian",
-        "Panjabi",
-        "Polish",
-        "Portuguese",
-        "Romanian",
-        "Russian",
-        "Slovak",
-        "Slovenian",
-        "Somali",
-        "Spanish",
-        "Albanian",
-        "Swahili (macrolanguage)",
-        "Swedish",
-        "Tamil",
-        "Telugu",
-        "Tagalog",
-        "Thai",
-        "Turkish",
-        "Ukrainian",
-        "Undetermined",
-        "Urdu",
-        "Vietnamese",
-        "Chinese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2208",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2208"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2208",
-    "PublicationTimestamp": "2016-04-14T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Technische Universit\u00e4t Darmstadt"
-    ],
-    "RelatedIdentifier": [
-        "http://www.lrec-conf.org/proceedings/lrec2016/pdf/388_Paper.pdf"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "PUB",
-        "http://creativecommons.org/licenses/by-sa/4.0/"
-    ],
-    "author": [
-        "Habernal, Ivan",
-        "Gurevych, Iryna",
-        "Zayed, Omnia"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2208;2019-01-02T14:28:24Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;C4Corpus (CC BY-SA part);Gurevych, Iryna;Habernal, Ivan;Zayed, Omnia;CommonCrawl;Creative Commons;Web corpus;Amazon Web Services;A large web corpus (over 10 billion tokens) licensed under CreativeCommons license family in 50+ languages that has been extracted from CommonCrawl, the largest publicly available general Web crawl to date with about 2 billion crawled URLs.;2016-04-14;corpus;http://hdl.handle.net/11372/LRT-2208;afr;ara;ben;bul;ces;dan;deu;ell;eng;est;fas;fin;fra;guj;heb;hin;hrv;hun;ind;ita;jpn;kan;kor;lav;lit;mal;mar;mkd;nep;nld;nor;pan;pol;por;ron;rus;slk;slv;som;spa;sqi;swa;swe;tam;tel;tgl;tha;tur;ukr;und;urd;vie;zho;http://www.lrec-conf.org/proceedings/lrec2016/pdf/388_Paper.pdf;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);PUB;http://creativecommons.org/licenses/by-sa/4.0/;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;text/plain;downloadable_files_count: 62;Technische Universit\u00e4t Darmstadt;https://dkpro.github.io/dkpro-c4corpus/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3032f56d-e167-5bf3-b209-95b648fd2195",
-    "notes": [
-        "A large web corpus (over 10 billion tokens) licensed under CreativeCommons license family in 50+ languages that has been extracted from CommonCrawl, the largest publicly available general Web crawl to date with about 2 billion crawled URLs."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2208"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "CommonCrawl"
-        },
-        {
-            "name": "Creative Commons"
-        },
-        {
-            "name": "Web corpus"
-        },
-        {
-            "name": "Amazon Web Services"
-        }
-    ],
-    "title": [
-        "C4Corpus (CC BY-SA part)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3043ab0c-96c3-5129-a3b6-5d6865163f55.json b/oaitestdata/clarin-oai_dc/SET_1/json/3043ab0c-96c3-5129-a3b6-5d6865163f55.json
deleted file mode 100644
index dfc26cea..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3043ab0c-96c3-5129-a3b6-5d6865163f55.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=82f8e7aadb1f11e1a404080027e73ea2e2410a9e40dd4dab905cbc5e120a15ed",
-    "MetadataAccess": [
-        "82f8e7aadb1f11e1a404080027e73ea2e2410a9e40dd4dab905cbc5e120a15ed"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "82f8e7aadb1f11e1a404080027e73ea2e2410a9e40dd4dab905cbc5e120a15ed;2018-11-15T16:39:24Z;toolService;toolService:tool;UIMA Apertium Translator;This tool translates text from a source language into a target language. It operates on text that has previously been tokenised and morphologically analysed, and POS-tagged. Target language tokens are assigned POS tags and morphological analyses. The Apertium Translator is a module of Apertium machine translation system  (Armentano-Ollet et al., 2006). The provided tool can currently operate on a subset of the languages that are supported by the Apertium system, namely:  English, Spanish, Calatan, Galician, Portuguese and Basque. \n\nNOTE: The morphological analysis required and POS tagging prior to running the transfer component  MUST be carried out by running the Apertium morphological analyser (which also performs tokenisation), followed by the Apertium POS tagger.\nThe tool is provided as a UIMA  (Ferrucci et al., 2006) component, specifically as Java archive (jar) file, which can be incorporated within any UIMA workflow. It can be run within the U-Compare text mining platform (Kano et al., 2009; Kano et al., 2011; see separate META-SHARE record), since the types of annotations it produces are compliant with the U-Compare. However, U-Compare does not currently support visualization of the output of this tool, since multiple subjects of analysis (sofas) are used. The output of the tool may, however, be visualized using the UIMA annotion viewer. \n;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3043ab0c-96c3-5129-a3b6-5d6865163f55",
-    "notes": [
-        "This tool translates text from a source language into a target language. It operates on text that has previously been tokenised and morphologically analysed, and POS-tagged. Target language tokens are assigned POS tags and morphological analyses. The Apertium Translator is a module of Apertium machine translation system  (Armentano-Ollet et al., 2006). The provided tool can currently operate on a subset of the languages that are supported by the Apertium system, namely:  English, Spanish, Calatan, Galician, Portuguese and Basque. \n\nNOTE: The morphological analysis required and POS tagging prior to running the transfer component  MUST be carried out by running the Apertium morphological analyser (which also performs tokenisation), followed by the Apertium POS tagger.\nThe tool is provided as a UIMA  (Ferrucci et al., 2006) component, specifically as Java archive (jar) file, which can be incorporated within any UIMA workflow. It can be run within the U-Compare text mining platform (Kano et al., 2009; Kano et al., 2011; see separate META-SHARE record), since the types of annotations it produces are compliant with the U-Compare. However, U-Compare does not currently support visualization of the output of this tool, since multiple subjects of analysis (sofas) are used. The output of the tool may, however, be visualized using the UIMA annotion viewer. \n"
-    ],
-    "oai_identifier": [
-        "82f8e7aadb1f11e1a404080027e73ea2e2410a9e40dd4dab905cbc5e120a15ed"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "UIMA Apertium Translator"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3054db29-4ded-54c7-9304-9bb703c63ce7.json b/oaitestdata/clarin-oai_dc/SET_1/json/3054db29-4ded-54c7-9304-9bb703c63ce7.json
deleted file mode 100644
index 8a069d04..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3054db29-4ded-54c7-9304-9bb703c63ce7.json
+++ /dev/null
@@ -1,133 +0,0 @@
-{
-    "Contact": [
-        "Charles University"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/x-tar",
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Arabic",
-        "Basque",
-        "Bengali",
-        "Bulgarian",
-        "Catalan",
-        "Croatian",
-        "Czech",
-        "Danish",
-        "Dutch",
-        "English",
-        "Estonian",
-        "Finnish",
-        "French",
-        "German",
-        "Modern Greek (1453-)",
-        "Ancient Greek (to 1453)",
-        "Hebrew",
-        "Hindi",
-        "Hungarian",
-        "Indonesian",
-        "Irish",
-        "Italian",
-        "Japanese",
-        "Latin",
-        "Persian",
-        "Polish",
-        "Portuguese",
-        "Romanian",
-        "Russian",
-        "Slovak",
-        "Slovenian",
-        "Spanish",
-        "Swedish",
-        "Tamil",
-        "Telugu",
-        "Turkish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1508",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1508"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1508",
-    "PublicationTimestamp": "2015-08-18T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Charles University"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11858/00-097C-0000-0023-9551-4"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "HamleDT 3.0 License Terms",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-hamledt-3.0",
-        "PUB"
-    ],
-    "author": [
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "Popel, Martin",
-        "Ramasamy, Loganathan",
-        "\u0160t\u011bp\u00e1nek, Jan",
-        "Ma\u0161ek, Jan",
-        "Zeman, Daniel",
-        "Rosa, Rudolf",
-        "Mare\u010dek, David"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1508;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;HamleDT 3.0;Zeman, Daniel;Mare\u010dek, David;Ma\u0161ek, Jan;Popel, Martin;Ramasamy, Loganathan;Rosa, Rudolf;\u0160t\u011bp\u00e1nek, Jan;\u017dabokrtsk\u00fd, Zden\u011bk;annotated corpus;morphology;syntax;dependency;treebank;harmonized annotation;common annotation style;HamleDT (HArmonized Multi-LanguagE Dependency Treebank) is a compilation of existing dependency treebanks (or dependency conversions of other treebanks), transformed so that they all conform to the same annotation style. This version uses Universal Dependencies as the common annotation style.\r\n\r\nUpdate (November 1017): for a current collection of harmonized dependency  treebanks, we recommend using the Universal Dependencies (UD). All of the corpora that are distributed in HamleDT in full are also part of the UD project; only some corpora from the Patch group (where HamleDT provides only the harmonizing scripts but not the full corpus data) are available in HamleDT but not in UD.;2015-08-18;corpus;http://hdl.handle.net/11234/1-1508;ara;eus;ben;bul;cat;hrv;ces;dan;nld;eng;est;fin;fra;deu;ell;grc;heb;hin;hun;ind;gle;ita;jpn;lat;fas;pol;por;ron;rus;slk;slv;spa;swe;tam;tel;tur;http://hdl.handle.net/11858/00-097C-0000-0023-9551-4;HamleDT 3.0 License Terms;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-hamledt-3.0;PUB;text/plain; charset=utf-8;application/x-tar;downloadable_files_count: 1;Charles University;http://ufal.mff.cuni.cz/hamledt",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3054db29-4ded-54c7-9304-9bb703c63ce7",
-    "notes": [
-        "HamleDT (HArmonized Multi-LanguagE Dependency Treebank) is a compilation of existing dependency treebanks (or dependency conversions of other treebanks), transformed so that they all conform to the same annotation style. This version uses Universal Dependencies as the common annotation style.\r\n\r\nUpdate (November 1017): for a current collection of harmonized dependency  treebanks, we recommend using the Universal Dependencies (UD). All of the corpora that are distributed in HamleDT in full are also part of the UD project; only some corpora from the Patch group (where HamleDT provides only the harmonizing scripts but not the full corpus data) are available in HamleDT but not in UD."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1508"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "annotated corpus"
-        },
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "syntax"
-        },
-        {
-            "name": "dependency"
-        },
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "harmonized annotation"
-        },
-        {
-            "name": "common annotation style"
-        }
-    ],
-    "title": [
-        "HamleDT 3.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/30568f83-e09d-5065-b9f7-1f5c9e9ec9b6.json b/oaitestdata/clarin-oai_dc/SET_1/json/30568f83-e09d-5065-b9f7-1f5c9e9ec9b6.json
deleted file mode 100644
index bbdca88d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/30568f83-e09d-5065-b9f7-1f5c9e9ec9b6.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "University of Helsinki"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Finnish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1992",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1992"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1992",
-    "PublicationTimestamp": "2017-03-22T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "University of Helsinki"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU General Public Licence, version 3",
-        "http://opensource.org/licenses/GPL-3.0",
-        "PUB"
-    ],
-    "author": [
-        "Pirinen, Tommi A",
-        "Johnson, Ryan",
-        "Tyers, Francis M.",
-        "Listenmaa, Inari",
-        "Kuokkala, Juha"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1992;2017-03-30T15:15:15Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Open morphology of Finnish;Pirinen, Tommi A;Listenmaa, Inari;Johnson, Ryan;Tyers, Francis M.;Kuokkala, Juha;morphological analysis;morphological dictionary;Omorfi is free and open source project containing various tools and data for handling Finnish texts in a linguistically motivated manner. The main components of this repository are:\r\n\r\n1) a lexical database containing hundreds of thousands of words (c.f. lexical statistics),\r\n2) a collection of scripts to convert lexical database into formats used by upstream NLP tools (c.f. lexical processing),\r\n3) an autotools setup to build and install (or package, or deploy): the scripts, the database, and simple APIs / convenience processing tools, and\r\n4) a collection of relatively simple APIs for a selection of languages and scripts to apply the NLP tools and access the database;2017-03-22;toolService;http://hdl.handle.net/11372/LRT-1992;fin;GNU General Public Licence, version 3;http://opensource.org/licenses/GPL-3.0;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;University of Helsinki;https://github.com/flammie/omorfi",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "30568f83-e09d-5065-b9f7-1f5c9e9ec9b6",
-    "notes": [
-        "Omorfi is free and open source project containing various tools and data for handling Finnish texts in a linguistically motivated manner. The main components of this repository are:\r\n\r\n1) a lexical database containing hundreds of thousands of words (c.f. lexical statistics),\r\n2) a collection of scripts to convert lexical database into formats used by upstream NLP tools (c.f. lexical processing),\r\n3) an autotools setup to build and install (or package, or deploy): the scripts, the database, and simple APIs / convenience processing tools, and\r\n4) a collection of relatively simple APIs for a selection of languages and scripts to apply the NLP tools and access the database"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1992"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphological analysis"
-        },
-        {
-            "name": "morphological dictionary"
-        }
-    ],
-    "title": [
-        "Open morphology of Finnish"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3059209c-f682-50d5-9219-06abc28b5186.json b/oaitestdata/clarin-oai_dc/SET_1/json/3059209c-f682-50d5-9219-06abc28b5186.json
deleted file mode 100644
index 03269b8c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3059209c-f682-50d5-9219-06abc28b5186.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3760",
-    "MetadataAccess": [
-        "oai:ota:oucs:3760"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Kelly, Hugh, 1739-1777."
-    ],
-    "fulltext": "oai:ota:oucs:3760;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3760.xml;False delicacy: a comedy; as it is performed at the Theatre-Royal in Drury-Lane. By His Majesty's servants. By Hugh Kelly.;Kelly, Hugh, 1739-1777.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3059209c-f682-50d5-9219-06abc28b5186",
-    "oai_identifier": [
-        "oai:ota:oucs:3760"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "False delicacy: a comedy; as it is performed at the Theatre-Royal in Drury-Lane. By His Majesty's servants. By Hugh Kelly."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3760.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3061c7df-a3b9-5b1e-8b52-f0e385bad845.json b/oaitestdata/clarin-oai_dc/SET_1/json/3061c7df-a3b9-5b1e-8b52-f0e385bad845.json
deleted file mode 100644
index f622564a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3061c7df-a3b9-5b1e-8b52-f0e385bad845.json
+++ /dev/null
@@ -1,287 +0,0 @@
-{
-    "Contact": [
-        "Universal Dependencies Consortium"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 4"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)",
-        "Arabic",
-        "Basque",
-        "Bulgarian",
-        "Croatian",
-        "Czech",
-        "Danish",
-        "Dutch",
-        "English",
-        "Estonian",
-        "Finnish",
-        "French",
-        "German",
-        "Gothic",
-        "Modern Greek (1453-)",
-        "Hebrew",
-        "Hindi",
-        "Hungarian",
-        "Indonesian",
-        "Irish",
-        "Italian",
-        "Japanese",
-        "Latin",
-        "Norwegian",
-        "Church Slavic",
-        "Persian",
-        "Polish",
-        "Portuguese",
-        "Romanian",
-        "Slovenian",
-        "Spanish",
-        "Swedish",
-        "Tamil",
-        "Catalan",
-        "Chinese",
-        "Galician",
-        "Kazakh",
-        "Latvian",
-        "Russian",
-        "Turkish",
-        "Coptic",
-        "Sanskrit",
-        "Slovak",
-        "Ukrainian",
-        "Uighur",
-        "Vietnamese",
-        "Belarusian",
-        "Korean",
-        "Lithuanian",
-        "Urdu"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1976",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1976"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1976",
-    "PublicationTimestamp": "2017-03-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Universal Dependencies Consortium"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-1983"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Licence Universal Dependencies v2.0",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-2.0",
-        "PUB"
-    ],
-    "author": [
-        "Ion, Radu",
-        "Seraji, Mojgan",
-        "Manning, Christopher",
-        "Cebiro\u011flu Eryi\u011fit, G\u00fcl\u015fen",
-        "Passarotti, Marco",
-        "Nguy\u1ec5n Th\u1ecb, L\u01b0\u01a1ng",
-        "Zhu, Hanzhi",
-        "Osenova, Petya",
-        "Agi\u0107, \u017deljko",
-        "Simionescu, Radu",
-        "Muischnek, Kadri",
-        "Choi, Jinho",
-        "Washington, Jonathan North",
-        "Montemagni, Simonetta",
-        "Davidson, Elizabeth",
-        "Ojala, Stina",
-        "Moskalevskyi, Bohdan",
-        "Seeker, Wolfgang",
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "Sanguinetti, Manuela",
-        "Irimia, Elena",
-        "Simk\u00f3, Katalin",
-        "Hladk\u00e1, Barbora",
-        "Krek, Simon",
-        "G\u00f6k\u0131rmak, Memduh",
-        "L\u00ea H\u1ed3ng, Ph\u01b0\u01a1ng",
-        "\u00d8vrelid, Lilja",
-        "Galbraith, Daniel",
-        "Lenci, Alessandro",
-        "Seddah, Djam\u00e9",
-        "Martins, Andr\u00e9",
-        "Ginter, Filip",
-        "Mititelu, Verginica",
-        "Erjavec, Toma\u017e",
-        "Johannsen, Anders",
-        "Bick, Eckhard",
-        "Mart\u00ednez Alonso, H\u00e9ctor",
-        "Schuster, Sebastian",
-        "Haug, Dag",
-        "Lynn, Teresa",
-        "Plank, Barbara",
-        "Freitas, Cl\u00e1udia",
-        "Varga, Viktor",
-        "Lyashevskaya, Olga",
-        "J\u00f8rgensen, Fredrik",
-        "M\u0103r\u0103nduc, C\u0103t\u0103lina",
-        "Ka\u015f\u0131kara, H\u00fcner",
-        "Pyysalo, Sampo",
-        "Kanerva, Jenna",
-        "Sulubacak, Umut",
-        "Sz\u00e1nt\u00f3, Zsolt",
-        "Chalub, Fabricio",
-        "Ma\u0161ek, Jan",
-        "Atutxa, Aitziber",
-        "Goldberg, Yoav",
-        "Matsumoto, Yuji",
-        "Dozat, Timothy",
-        "G\u00f3mez Guinovart, Xavier",
-        "M\u00fc\u00fcrisep, Kaili",
-        "Saul\u012bte, Baiba",
-        "Bauer, John",
-        "Piitulainen, Jussi",
-        "Nivre, Joakim",
-        "Prokopidis, Prokopis",
-        "Petrov, Slav",
-        "Guillaume, Bruno",
-        "Gr\u016bz\u012btis, Normunds",
-        "Perrier, Guy",
-        "de Marneffe, Marie-Catherine",
-        "Missil\u00e4, Anna",
-        "Dwivedi, Puneet",
-        "Hohle, Petter",
-        "Makazhanov, Aibek",
-        "McDonald, Ryan",
-        "Pretkalni\u0146a, Lauma",
-        "Farkas, Rich\u00e1rd",
-        "Ramasamy, Loganathan",
-        "Bosco, Cristina",
-        "Eli, Marhaba",
-        "Mori, Shunsuke",
-        "de Paiva, Valeria",
-        "Grioni, Matias",
-        "Real, Livy",
-        "Asahara, Masayuki",
-        "Suhr, Alane",
-        "Tanaka, Takaaki",
-        "Miyao, Yusuke",
-        "Vincze, Veronika",
-        "Bhat, Riyaz Ahmad",
-        "Mustafina, Nina",
-        "Garcia, Marcos",
-        "Nguy\u1ec5n Th\u1ecb Minh, Huy\u1ec1n",
-        "Sichinava, Dmitry",
-        "Puolakainen, Tiina",
-        "Tsarfaty, Reut",
-        "Taji, Dima",
-        "Goenaga, Iakes",
-        "Rituma, Laura",
-        "H\u00e0 M\u1ef9, Linh",
-        "Habash, Nizar",
-        "Droganova, Kira",
-        "Shen, Mo",
-        "Connor, Miriam",
-        "Mare\u010dek, David",
-        "Smith, Aaron",
-        "More, Amir",
-        "\u0160imkov\u00e1, M\u00e1ria",
-        "Gajdo\u0161ov\u00e1, Katar\u00edna",
-        "Zeman, Daniel",
-        "Celano, Giuseppe G. A.",
-        "Dobrovoljc, Kaja",
-        "Popel, Martin",
-        "Laippala, Veronika",
-        "Gojenola, Koldo",
-        "Simov, Kiril",
-        "Ballesteros, Miguel",
-        "Nurmi, Hanna",
-        "Nikolaev, Vitaly",
-        "Perez, Cenel-Augusto",
-        "Rademaker, Alexandre",
-        "Tyers, Francis",
-        "Ahrenberg, Lars",
-        "Shakurova, Lena",
-        "Diaz de Ilarraza, Arantza",
-        "Rosa, Rudolf",
-        "Aranzabe, Maria Jesus",
-        "Candito, Marie",
-        "Saleh, Shadi",
-        "Simi, Maria",
-        "Bengoetxea, Kepa",
-        "van Noord, Gertjan",
-        "Zeldes, Amir",
-        "Pascual, Elena",
-        "Bouma, Gosse",
-        "Foster, Jennifer",
-        "\u00c7\u00f6ltekin, \u00c7a\u011fr\u0131",
-        "Uematsu, Sumire",
-        "Gonz\u00e1les Saavedra, Berta",
-        "Uria, Larraitz",
-        "Ljube\u0161i\u0107, Nikola",
-        "Kanayama, Hiroshi",
-        "Haji\u010d, Jan",
-        "Bowman, Sam",
-        "Kotsyba, Natalia",
-        "Silveira, Natalia"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1976;2018-07-02T22:05:54Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Universal Dependencies 2.0 alpha (obsolete);Nivre, Joakim;Agi\u0107, \u017deljko;Ahrenberg, Lars;Aranzabe, Maria Jesus;Asahara, Masayuki;Atutxa, Aitziber;Ballesteros, Miguel;Bauer, John;Bengoetxea, Kepa;Bhat, Riyaz Ahmad;Bick, Eckhard;Bosco, Cristina;Bouma, Gosse;Bowman, Sam;Candito, Marie;Cebiro\u011flu Eryi\u011fit, G\u00fcl\u015fen;Celano, Giuseppe G. A.;Chalub, Fabricio;Choi, Jinho;\u00c7\u00f6ltekin, \u00c7a\u011fr\u0131;Connor, Miriam;Davidson, Elizabeth;de Marneffe, Marie-Catherine;de Paiva, Valeria;Diaz de Ilarraza, Arantza;Dobrovoljc, Kaja;Dozat, Timothy;Droganova, Kira;Dwivedi, Puneet;Eli, Marhaba;Erjavec, Toma\u017e;Farkas, Rich\u00e1rd;Foster, Jennifer;Freitas, Cl\u00e1udia;Gajdo\u0161ov\u00e1, Katar\u00edna;Galbraith, Daniel;Garcia, Marcos;Ginter, Filip;Goenaga, Iakes;Gojenola, Koldo;G\u00f6k\u0131rmak, Memduh;Goldberg, Yoav;G\u00f3mez Guinovart, Xavier;Gonz\u00e1les Saavedra, Berta;Grioni, Matias;Gr\u016bz\u012btis, Normunds;Guillaume, Bruno;Habash, Nizar;Haji\u010d, Jan;H\u00e0 M\u1ef9, Linh;Haug, Dag;Hladk\u00e1, Barbora;Hohle, Petter;Ion, Radu;Irimia, Elena;Johannsen, Anders;J\u00f8rgensen, Fredrik;Ka\u015f\u0131kara, H\u00fcner;Kanayama, Hiroshi;Kanerva, Jenna;Kotsyba, Natalia;Krek, Simon;Laippala, Veronika;L\u00ea H\u1ed3ng, Ph\u01b0\u01a1ng;Lenci, Alessandro;Ljube\u0161i\u0107, Nikola;Lyashevskaya, Olga;Lynn, Teresa;Makazhanov, Aibek;Manning, Christopher;M\u0103r\u0103nduc, C\u0103t\u0103lina;Mare\u010dek, David;Mart\u00ednez Alonso, H\u00e9ctor;Martins, Andr\u00e9;Ma\u0161ek, Jan;Matsumoto, Yuji;McDonald, Ryan;Missil\u00e4, Anna;Mititelu, Verginica;Miyao, Yusuke;Montemagni, Simonetta;More, Amir;Mori, Shunsuke;Moskalevskyi, Bohdan;Muischnek, Kadri;Mustafina, Nina;M\u00fc\u00fcrisep, Kaili;Nguy\u1ec5n Th\u1ecb, L\u01b0\u01a1ng;Nguy\u1ec5n Th\u1ecb Minh, Huy\u1ec1n;Nikolaev, Vitaly;Nurmi, Hanna;Ojala, Stina;Osenova, Petya;\u00d8vrelid, Lilja;Pascual, Elena;Passarotti, Marco;Perez, Cenel-Augusto;Perrier, Guy;Petrov, Slav;Piitulainen, Jussi;Plank, Barbara;Popel, Martin;Pretkalni\u0146a, Lauma;Prokopidis, Prokopis;Puolakainen, Tiina;Pyysalo, Sampo;Rademaker, Alexandre;Ramasamy, Loganathan;Real, Livy;Rituma, Laura;Rosa, Rudolf;Saleh, Shadi;Sanguinetti, Manuela;Saul\u012bte, Baiba;Schuster, Sebastian;Seddah, Djam\u00e9;Seeker, Wolfgang;Seraji, Mojgan;Shakurova, Lena;Shen, Mo;Sichinava, Dmitry;Silveira, Natalia;Simi, Maria;Simionescu, Radu;Simk\u00f3, Katalin;\u0160imkov\u00e1, M\u00e1ria;Simov, Kiril;Smith, Aaron;Suhr, Alane;Sulubacak, Umut;Sz\u00e1nt\u00f3, Zsolt;Taji, Dima;Tanaka, Takaaki;Tsarfaty, Reut;Tyers, Francis;Uematsu, Sumire;Uria, Larraitz;van Noord, Gertjan;Varga, Viktor;Vincze, Veronika;Washington, Jonathan North;\u017dabokrtsk\u00fd, Zden\u011bk;Zeldes, Amir;Zeman, Daniel;Zhu, Hanzhi;treebank;dependency;syntax;morphology;harmonized annotation;interset;universal tagset;stanford dependencies;This release contains errors in several files. Please use http://hdl.handle.net/11234/1-1983 instead.;2017-03-01;corpus;http://hdl.handle.net/11234/1-1976;grc;ara;eus;bul;hrv;ces;dan;nld;eng;est;fin;fra;deu;got;ell;heb;hin;hun;ind;gle;ita;jpn;lat;nor;chu;fas;pol;por;ron;slv;spa;swe;tam;cat;zho;glg;kaz;lav;rus;tur;cop;san;slk;ukr;uig;vie;bel;kor;lit;urd;http://hdl.handle.net/11234/1-1983;Licence Universal Dependencies v2.0;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-2.0;PUB;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Universal Dependencies Consortium;http://universaldependencies.org/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3061c7df-a3b9-5b1e-8b52-f0e385bad845",
-    "notes": [
-        "This release contains errors in several files. Please use http://hdl.handle.net/11234/1-1983 instead."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1976"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "dependency"
-        },
-        {
-            "name": "syntax"
-        },
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "harmonized annotation"
-        },
-        {
-            "name": "interset"
-        },
-        {
-            "name": "universal tagset"
-        },
-        {
-            "name": "stanford dependencies"
-        }
-    ],
-    "title": [
-        "Universal Dependencies 2.0 alpha (obsolete)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3074cb26-6a0d-5803-8520-d0050a22c66e.json b/oaitestdata/clarin-oai_dc/SET_1/json/3074cb26-6a0d-5803-8520-d0050a22c66e.json
deleted file mode 100644
index fd3a35d0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3074cb26-6a0d-5803-8520-d0050a22c66e.json
+++ /dev/null
@@ -1,301 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 299",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Abkhazian",
-        "Achinese",
-        "Adyghe",
-        "Afrikaans",
-        "Akan",
-        "Amharic",
-        "Old English (ca. 450-1100)",
-        "Arabic",
-        "Official Aramaic (700-300 BCE)",
-        "Aragonese",
-        "Assamese",
-        "Asturian",
-        "Avaric",
-        "Aymara",
-        "Azerbaijani",
-        "Bashkir",
-        "Bambara",
-        "Belarusian",
-        "Bengali",
-        "Bislama",
-        "Tibetan",
-        "Bosnian",
-        "Breton",
-        "Buginese",
-        "Bulgarian",
-        "Catalan",
-        "Cebuano",
-        "Czech",
-        "Chamorro",
-        "Chechen",
-        "Cherokee",
-        "Church Slavic",
-        "Chuvash",
-        "Cheyenne",
-        "Cornish",
-        "Corsican",
-        "Cree",
-        "Crimean Tatar",
-        "Kashubian",
-        "Welsh",
-        "Danish",
-        "German",
-        "Dinka",
-        "Dhivehi",
-        "Lower Sorbian",
-        "Dzongkha",
-        "Modern Greek (1453-)",
-        "English",
-        "Esperanto",
-        "Estonian",
-        "Basque",
-        "Ewe",
-        "Faroese",
-        "Persian",
-        "Fijian",
-        "Finnish",
-        "French",
-        "Northern Frisian",
-        "Western Frisian",
-        "Fulah",
-        "Friulian",
-        "Scottish Gaelic",
-        "Irish",
-        "Galician",
-        "Manx",
-        "Gothic",
-        "Guarani",
-        "Gujarati",
-        "Haitian",
-        "Hausa",
-        "Hawaiian",
-        "Hebrew",
-        "Herero",
-        "Hindi",
-        "Hiri Motu",
-        "Croatian",
-        "Upper Sorbian",
-        "Hungarian",
-        "Armenian",
-        "Igbo",
-        "Ido",
-        "Inuktitut",
-        "Interlingue",
-        "Iloko",
-        "Interlingua (International Auxiliary Language Association)",
-        "Indonesian",
-        "Inupiaq",
-        "Icelandic",
-        "Italian",
-        "Javanese",
-        "Lojban",
-        "Japanese",
-        "Kara-Kalpak",
-        "Kabyle",
-        "Kalaallisut",
-        "Kannada",
-        "Kashmiri",
-        "Georgian",
-        "Kanuri",
-        "Kazakh",
-        "Kabardian",
-        "Central Khmer",
-        "Kikuyu",
-        "Kinyarwanda",
-        "Kirghiz",
-        "Komi",
-        "Kongo",
-        "Korean",
-        "Karachay-Balkar",
-        "Kurdish",
-        "Ladino",
-        "Lao",
-        "Latin",
-        "Latvian",
-        "Lezghian",
-        "Limburgan",
-        "Lingala",
-        "Lithuanian",
-        "Luxembourgish",
-        "Ganda",
-        "Marshallese",
-        "Maithili",
-        "Malayalam",
-        "Marathi",
-        "Moksha",
-        "Minangkabau",
-        "Macedonian",
-        "Malagasy",
-        "Maltese",
-        "Mongolian",
-        "Maori",
-        "Malay (macrolanguage)",
-        "Creek",
-        "Mirandese",
-        "Burmese",
-        "Erzya",
-        "Neapolitan",
-        "Nauru",
-        "Navajo",
-        "Ndonga",
-        "Low German",
-        "Nepali (macrolanguage)",
-        "Newari",
-        "Dutch",
-        "Norwegian Nynorsk",
-        "Norwegian",
-        "Pedi",
-        "Nyanja",
-        "Occitan (post 1500)",
-        "Oriya (macrolanguage)",
-        "Oromo",
-        "Ossetian",
-        "Pangasinan",
-        "Pampanga",
-        "Panjabi",
-        "Papiamento",
-        "Pali",
-        "Polish",
-        "Portuguese",
-        "Pushto",
-        "Quechua",
-        "Romansh",
-        "Romanian",
-        "Rundi",
-        "Macedo-Romanian",
-        "Russian",
-        "Sango",
-        "Yakut",
-        "Sanskrit",
-        "Sicilian",
-        "Scots",
-        "Sinhala",
-        "Slovak",
-        "Slovenian",
-        "Northern Sami",
-        "Samoan",
-        "Shona",
-        "Sindhi",
-        "Somali",
-        "Southern Sotho",
-        "Spanish",
-        "Albanian",
-        "Sardinian",
-        "Sranan Tongo",
-        "Serbian",
-        "Swati",
-        "Sundanese",
-        "Swahili (macrolanguage)",
-        "Swedish",
-        "Tahitian",
-        "Tamil",
-        "Tatar",
-        "Telugu",
-        "Tetum",
-        "Tajik",
-        "Tagalog",
-        "Thai",
-        "Tigrinya",
-        "Tonga (Tonga Islands)",
-        "Tok Pisin",
-        "Tswana",
-        "Tsonga",
-        "Turkmen",
-        "Tumbuka",
-        "Turkish",
-        "Twi",
-        "Tuvinian",
-        "Udmurt",
-        "Uighur",
-        "Ukrainian",
-        "Urdu",
-        "Uzbek",
-        "Venda",
-        "Vietnamese",
-        "Volap\u00fck",
-        "Waray (Philippines)",
-        "Walloon",
-        "Wolof",
-        "Kalmyk",
-        "Xhosa",
-        "Yiddish",
-        "Yoruba",
-        "Zhuang",
-        "Chinese",
-        "Zulu"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2735",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2735"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2735",
-    "PublicationTimestamp": "2018-02-25T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0)",
-        "http://creativecommons.org/licenses/by-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Rosa, Rudolf"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2735;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Plaintext Wikipedia dump 2018;Rosa, Rudolf;Wikipedia;text corpora;monolingual corpus;Wikipedia plain text data obtained from Wikipedia dumps with WikiExtractor in February 2018.\r\n\r\nThe data come from all Wikipedias for which dumps could be downloaded at [https://dumps.wikimedia.org/]. This amounts to 297 Wikipedias, usually corresponding to individual languages and identified by their ISO codes. Several special Wikipedias are included, most notably \"simple\" (Simple English Wikipedia) and \"incubator\" (tiny hatching Wikipedias in various languages).\r\nFor a list of all the Wikipedias, see [https://meta.wikimedia.org/wiki/List_of_Wikipedias].\r\n\r\nThe script which can be used to get new version of the data is included, but note that Wikipedia limits the download speed for downloading a lot of the dumps, so it takes a few days to download all of them (but one or a few can be downloaded fast).\r\nAlso, the format of the dumps changes time to time, so the script will probably eventually stop working one day.\r\nThe WikiExtractor tool [http://medialab.di.unipi.it/wiki/Wikipedia_Extractor] used to extract text from the Wikipedia dumps is not mine, I only modified it slightly to produce plaintext outputs [https://github.com/ptakopysk/wikiextractor].;2018-02-25;corpus;http://hdl.handle.net/11234/1-2735;abk;ace;ady;afr;aka;als;amh;ang;ara;arc;arg;arz;asm;ast;atj;ava;aym;azb;aze;bak;bam;bar;bcl;bel;ben;bis;bjn;bod;bos;bpy;bre;bug;bul;bxr;cat;cdo;ceb;ces;cha;che;chr;chu;chv;chy;ckb;cor;cos;cre;crh;csb;cym;dan;deu;din;diq;div;dsb;dzo;ell;eng;epo;est;eus;ewe;ext;fao;fas;fij;fin;fra;frp;frr;fry;ful;fur;gag;gan;gla;gle;glg;glk;glv;gom;got;grn;guj;hak;hat;hau;haw;hbs;heb;her;hif;hin;hmo;hrv;hsb;hun;hye;ibo;ido;iku;ile;ilo;ina;ind;ipk;isl;ita;jam;jav;jbo;jpn;kaa;kab;kal;kan;kas;kat;kau;kaz;kbd;kbp;khm;kik;kin;kir;koi;kom;kon;kor;krc;ksh;kur;lad;lao;lat;lav;lbe;lez;lij;lim;lin;lit;lmo;lrc;ltg;ltz;lug;lzh;mah;mai;mal;mar;mdf;mhr;min;mkd;mlg;mlt;mon;mri;mrj;msa;mus;mwl;mya;myv;mzn;nan;nap;nau;nav;ndo;nds;nep;new;nld;nno;nor;nov;nso;nya;oci;olo;ori;orm;oss;pag;pam;pan;pap;pcd;pdc;pfl;pih;pli;pms;pnb;pnt;pol;por;pus;que;rmy;roh;ron;rue;run;rup;rus;sag;sah;san;scn;sco;sgs;sin;slk;slv;sme;smo;sna;snd;som;sot;spa;sqi;srd;srn;srp;ssw;stq;sun;swa;swe;szl;tah;tam;tat;tcy;tel;ten;tet;tgk;tgl;tha;tir;ton;tpi;tsn;tso;tuk;tum;tur;twi;tyv;udm;uig;ukr;urd;uzb;vec;ven;vep;vie;vls;vol;vro;war;wln;wol;wuu;xal;xho;xmf;yid;yor;yue;zea;zha;zho;zul;Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0);http://creativecommons.org/licenses/by-sa/3.0/;PUB;application/octet-stream;application/octet-stream;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 299;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3074cb26-6a0d-5803-8520-d0050a22c66e",
-    "notes": [
-        "Wikipedia plain text data obtained from Wikipedia dumps with WikiExtractor in February 2018.\r\n\r\nThe data come from all Wikipedias for which dumps could be downloaded at [https://dumps.wikimedia.org/]. This amounts to 297 Wikipedias, usually corresponding to individual languages and identified by their ISO codes. Several special Wikipedias are included, most notably \"simple\" (Simple English Wikipedia) and \"incubator\" (tiny hatching Wikipedias in various languages).\r\nFor a list of all the Wikipedias, see [https://meta.wikimedia.org/wiki/List_of_Wikipedias].\r\n\r\nThe script which can be used to get new version of the data is included, but note that Wikipedia limits the download speed for downloading a lot of the dumps, so it takes a few days to download all of them (but one or a few can be downloaded fast).\r\nAlso, the format of the dumps changes time to time, so the script will probably eventually stop working one day.\r\nThe WikiExtractor tool [http://medialab.di.unipi.it/wiki/Wikipedia_Extractor] used to extract text from the Wikipedia dumps is not mine, I only modified it slightly to produce plaintext outputs [https://github.com/ptakopysk/wikiextractor]."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2735"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Wikipedia"
-        },
-        {
-            "name": "text corpora"
-        },
-        {
-            "name": "monolingual corpus"
-        }
-    ],
-    "title": [
-        "Plaintext Wikipedia dump 2018"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3094f7e9-2241-587b-8993-9c11670f5b5f.json b/oaitestdata/clarin-oai_dc/SET_1/json/3094f7e9-2241-587b-8993-9c11670f5b5f.json
deleted file mode 100644
index 86c11837..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3094f7e9-2241-587b-8993-9c11670f5b5f.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra",
-        "Centre de Terminologia TERMCAT"
-    ],
-    "Contributor": [
-        "Nazar, Rogelio"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Catalan"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1194",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1194"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1194",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra",
-        "Centre de Terminologia TERMCAT"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1194;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;ESTEN;Nazar, Rogelio;Terminology management.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1194;cat;downloadable_files_count: 0;Spain;Centre de Terminologia TERMCAT;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra;http://esten.iula.upf.edu/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3094f7e9-2241-587b-8993-9c11670f5b5f",
-    "notes": [
-        "Terminology management."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1194"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "ESTEN"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/309f453e-97b9-5183-8b8d-a13e5799ef7e.json b/oaitestdata/clarin-oai_dc/SET_1/json/309f453e-97b9-5183-8b8d-a13e5799ef7e.json
deleted file mode 100644
index ba1b552d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/309f453e-97b9-5183-8b8d-a13e5799ef7e.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "The Research Institute for the Languages of Finland"
-    ],
-    "Contributor": [
-        "Alanen, Timo"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Finnish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-840",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-840"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-840",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "The Research Institute for the Languages of Finland"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Finland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-840;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Land survey register of S\u00e4\u00e4minki and Rantasalmi from the years 1562-1563;Alanen, Timo;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-840;fin;downloadable_files_count: 0;Finland;The Research Institute for the Languages of Finland;http://scripta.kotus.fi/www/verkkojulkaisut/julk4/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "309f453e-97b9-5183-8b8d-a13e5799ef7e",
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-840"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Land survey register of S\u00e4\u00e4minki and Rantasalmi from the years 1562-1563"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/30a58f0b-d5e4-539d-baa3-7ad588876c73.json b/oaitestdata/clarin-oai_dc/SET_1/json/30a58f0b-d5e4-539d-baa3-7ad588876c73.json
deleted file mode 100644
index 9eb328b9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/30a58f0b-d5e4-539d-baa3-7ad588876c73.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Craig, Hugh"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 136 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1452",
-    "MetadataAccess": [
-        "oai:ota:oucs:1452"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Shakespeare, William, 1564-1616"
-    ],
-    "fulltext": "oai:ota:oucs:1452;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1452.xml;The tempest : [1623 Folio] / William Shakespeare;Shakespeare, William, 1564-1616;text_and_corpus_linguistics;English drama -- Early modern and Elizabethan, 1500-1600;Oxford Text Archive, University of Oxford;Craig, Hugh;(1 file : ca. 136 KB);Text;Plays;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "30a58f0b-d5e4-539d-baa3-7ad588876c73",
-    "oai_identifier": [
-        "oai:ota:oucs:1452"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- Early modern Elizabethan"
-        }
-    ],
-    "title": [
-        "The tempest : [1623 Folio] / William Shakespeare"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1452.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/30a7148d-2a3c-5e85-9e0b-6c4738ddc0f1.json b/oaitestdata/clarin-oai_dc/SET_1/json/30a7148d-2a3c-5e85-9e0b-6c4738ddc0f1.json
deleted file mode 100644
index 7a0f6708..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/30a7148d-2a3c-5e85-9e0b-6c4738ddc0f1.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2612",
-    "MetadataAccess": [
-        "oai:ota:oucs:2612"
-    ],
-    "PublicationTimestamp": "1720-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1720"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2612;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2612.xml;Miscellaneous works, comical & diverting (1720) (Booksellers advertisement and Table to Tale of a Tub);Swift, Jonathan, 1667-1745;1720;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "30a7148d-2a3c-5e85-9e0b-6c4738ddc0f1",
-    "oai_identifier": [
-        "oai:ota:oucs:2612"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Miscellaneous works, comical & diverting (1720) (Booksellers advertisement and Table to Tale of a Tub)"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2612.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/30be4572-d254-521b-a26c-439cb3104df1.json b/oaitestdata/clarin-oai_dc/SET_1/json/30be4572-d254-521b-a26c-439cb3104df1.json
deleted file mode 100644
index 83e4475a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/30be4572-d254-521b-a26c-439cb3104df1.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Masaryk University, NLP Centre"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-CCDF-8",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-CCDF-8"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-CCDF-8",
-    "PublicationTimestamp": "2011-12-16T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Masaryk University, NLP Centre"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "NLP Centre Web Corpus License",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/license-NLPC-WeC",
-        "ACA"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-CCDF-8;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;enTenTen;English large corpus;Very large English web corpus enTenTEn, comprising 3,268,798,627 tokens.;2011-12-16;corpus;http://hdl.handle.net/11858/00-097C-0000-0001-CCDF-8;eng;NLP Centre Web Corpus License;https://lindat.mff.cuni.cz/repository/xmlui/page/license-NLPC-WeC;ACA;text/plain; charset=utf-8;application/x-gzip;downloadable_files_count: 1;Masaryk University, NLP Centre",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "30be4572-d254-521b-a26c-439cb3104df1",
-    "notes": [
-        "Very large English web corpus enTenTEn, comprising 3,268,798,627 tokens."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-CCDF-8"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "English large corpus"
-        }
-    ],
-    "title": [
-        "enTenTen"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/30e0f202-6f08-56a7-8a9c-5bb7e7753f19.json b/oaitestdata/clarin-oai_dc/SET_1/json/30e0f202-6f08-56a7-8a9c-5bb7e7753f19.json
deleted file mode 100644
index 9672dae1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/30e0f202-6f08-56a7-8a9c-5bb7e7753f19.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "University of Helsinki"
-    ],
-    "Contributor": [
-        "Vasko, Anna-Liisa"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-746",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-746"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-746",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Helsinki"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-746;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Helsinki Corpus of British English Dialects;Vasko, Anna-Liisa;Collection of orthographically transcribed audio recorded speech, mainly from East Anglia and the South-West, with a minor collection from Lancashire. The recordings were made in the 1970s and the 1980s by Finnish postgraduates.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-746;eng;text/plain;downloadable_files_count: 0;University of Helsinki;http://www.helsinki.fi/varieng/CoRD/corpora/Dialects/index.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "30e0f202-6f08-56a7-8a9c-5bb7e7753f19",
-    "notes": [
-        "Collection of orthographically transcribed audio recorded speech, mainly from East Anglia and the South-West, with a minor collection from Lancashire. The recordings were made in the 1970s and the 1980s by Finnish postgraduates."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-746"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Helsinki Corpus of British English Dialects"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3112ac76-d780-5cc9-bbbf-acf4d88151ab.json b/oaitestdata/clarin-oai_dc/SET_1/json/3112ac76-d780-5cc9-bbbf-acf4d88151ab.json
deleted file mode 100644
index 98b8c9b2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3112ac76-d780-5cc9-bbbf-acf4d88151ab.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=c6599c86bc6d11e1a404080027e73ea2fb149db7ca074dd7b2ac8f2608eda2dc",
-    "MetadataAccess": [
-        "c6599c86bc6d11e1a404080027e73ea2fb149db7ca074dd7b2ac8f2608eda2dc"
-    ],
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "c6599c86bc6d11e1a404080027e73ea2fb149db7ca074dd7b2ac8f2608eda2dc;2018-11-15T16:39:31Z;corpus;corpus:audio;MalToBi/SPAN Corpus;Audio corpus: 8 subfolders with .wav files\nEach containing :\n\u00e2\u0080\u00a2\t2 sound files containing a read story (\u00e2\u0080\u009cThe sun and the wind\u00e2\u0080\u009d, each by speaker A and speaker B)\n\u00e2\u0080\u00a2\t2 sound files containing each 30 read sentences (each by speaker A and speaker B)\n\u00e2\u0080\u00a2\t2 x each of the 30 sentences as a single sound file (each by speaker A and speaker B)\n\u00e2\u0080\u00a2\t2 x 26 phrases in individual files (each by speaker A and speaker B)\n;2015-12-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3112ac76-d780-5cc9-bbbf-acf4d88151ab",
-    "notes": [
-        "Audio corpus: 8 subfolders with .wav files\nEach containing :\n\u00e2\u0080\u00a2\t2 sound files containing a read story (\u00e2\u0080\u009cThe sun and the wind\u00e2\u0080\u009d, each by speaker A and speaker B)\n\u00e2\u0080\u00a2\t2 sound files containing each 30 read sentences (each by speaker A and speaker B)\n\u00e2\u0080\u00a2\t2 x each of the 30 sentences as a single sound file (each by speaker A and speaker B)\n\u00e2\u0080\u00a2\t2 x 26 phrases in individual files (each by speaker A and speaker B)\n"
-    ],
-    "oai_identifier": [
-        "c6599c86bc6d11e1a404080027e73ea2fb149db7ca074dd7b2ac8f2608eda2dc"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:audio"
-    ],
-    "state": "active",
-    "title": [
-        "MalToBi/SPAN Corpus"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/31171c17-68fc-5daf-bbb3-edf009aeff8a.json b/oaitestdata/clarin-oai_dc/SET_1/json/31171c17-68fc-5daf-bbb3-edf009aeff8a.json
deleted file mode 100644
index 638a10c0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/31171c17-68fc-5daf-bbb3-edf009aeff8a.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5116",
-    "MetadataAccess": [
-        "oai:ota:oucs:5116"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Sharp, Granville, 1735-1813."
-    ],
-    "fulltext": "oai:ota:oucs:5116;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5116.xml;Tracts, concerning the ancient and only true legal means of national defence, by a free militia: ...;Sharp, Granville, 1735-1813.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "31171c17-68fc-5daf-bbb3-edf009aeff8a",
-    "oai_identifier": [
-        "oai:ota:oucs:5116"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Tracts, concerning the ancient and only true legal means of national defence, by a free militia: ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5116.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3144f765-69d5-527b-8e54-9f789bc67e73.json b/oaitestdata/clarin-oai_dc/SET_1/json/3144f765-69d5-527b-8e54-9f789bc67e73.json
deleted file mode 100644
index 0beaa275..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3144f765-69d5-527b-8e54-9f789bc67e73.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "University of Potsdam, Dept. of Linguistics",
-        "Humboldt-University Berlin, Institut f\u00fcr deutsche Sprache und Linguistik"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1167",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1167"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1167",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Potsdam, Dept. of Linguistics",
-        "Humboldt-University Berlin, Institut f\u00fcr deutsche Sprache und Linguistik"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1167;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;ANNIS;ANNIS2 is an open source, versatile web browser-based search and visualization architecture for complex multilevel linguistic corpora with diverse types of annotation. ANNIS, which stands for ANNotation of Information Structure, has been designed to provide access to the data of the SFB 632 - \"Information Structure: The Linguistic Means for Structuring Utterances, Sentences and Texts\". Since information structure interacts with linguistic phenomena on many levels, ANNIS2 addresses the SFB's need to concurrently annotate, query and visualize data from such varied areas as syntax, semantics, morphology, prosody, referentiality, lexis and more. For project working with spoken language, support for audio / video annotations is also required.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1167;downloadable_files_count: 0;Germany;University of Potsdam, Dept. of Linguistics;Humboldt-University Berlin, Institut f\u00fcr deutsche Sprache und Linguistik;http://annis2.sfb632.uni-potsdam.de/Annis/search.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3144f765-69d5-527b-8e54-9f789bc67e73",
-    "notes": [
-        "ANNIS2 is an open source, versatile web browser-based search and visualization architecture for complex multilevel linguistic corpora with diverse types of annotation. ANNIS, which stands for ANNotation of Information Structure, has been designed to provide access to the data of the SFB 632 - \"Information Structure: The Linguistic Means for Structuring Utterances, Sentences and Texts\". Since information structure interacts with linguistic phenomena on many levels, ANNIS2 addresses the SFB's need to concurrently annotate, query and visualize data from such varied areas as syntax, semantics, morphology, prosody, referentiality, lexis and more. For project working with spoken language, support for audio / video annotations is also required."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1167"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "ANNIS"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/314ac95b-16d8-5cde-81e5-cbe53797b364.json b/oaitestdata/clarin-oai_dc/SET_1/json/314ac95b-16d8-5cde-81e5-cbe53797b364.json
deleted file mode 100644
index 14a728c9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/314ac95b-16d8-5cde-81e5-cbe53797b364.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2819",
-    "MetadataAccess": [
-        "oai:ota:oucs:2819"
-    ],
-    "PublicationTimestamp": "1735-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1735"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2819;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2819.xml;Drapier's Letters VI, To the Lord Chancellor Middleton;Swift, Jonathan, 1667-1745;1735;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "314ac95b-16d8-5cde-81e5-cbe53797b364",
-    "oai_identifier": [
-        "oai:ota:oucs:2819"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Drapier's Letters VI, To the Lord Chancellor Middleton"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2819.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/314dec4f-c44f-5371-ae28-3ae73d32ad49.json b/oaitestdata/clarin-oai_dc/SET_1/json/314dec4f-c44f-5371-ae28-3ae73d32ad49.json
deleted file mode 100644
index a0faf085..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/314dec4f-c44f-5371-ae28-3ae73d32ad49.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3908",
-    "MetadataAccess": [
-        "oai:ota:oucs:3908"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Sharp, Granville, 1735-1813."
-    ],
-    "fulltext": "oai:ota:oucs:3908;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3908.xml;A declaration of the people's natural right to a share in the legislature: which is the fundamental principle of the British constitution of state. By Granville Sharp.;Sharp, Granville, 1735-1813.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "314dec4f-c44f-5371-ae28-3ae73d32ad49",
-    "oai_identifier": [
-        "oai:ota:oucs:3908"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A declaration of the people's natural right to a share in the legislature: which is the fundamental principle of the British constitution of state. By Granville Sharp."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3908.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3155db3d-6d76-5fd7-9d5c-28f36d328fcc.json b/oaitestdata/clarin-oai_dc/SET_1/json/3155db3d-6d76-5fd7-9d5c-28f36d328fcc.json
deleted file mode 100644
index 9fdc54e5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3155db3d-6d76-5fd7-9d5c-28f36d328fcc.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Linguistic Modeling Department, IPP, Bulgarian Academy of Sciences"
-    ],
-    "Contributor": [
-        "Simov, Kiril"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1241",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1241"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1241",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Linguistic Modeling Department, IPP, Bulgarian Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Bulgaria"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Simov, Kiril",
-        "Osenova, Petya"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1241;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;BulTreeBank Morphological Analyzer;Simov, Kiril;Osenova, Petya;Simov, Kiril;It is used morphological lexicon of Bulgarian (100 000 lemmas) compiled as a finite-state automaton in CLaRK System. It requires the text to be first tokenized and it is applied in each token. Includes also guessers for unknown words and Named Entities gazetteers. If the corresponding resources are available for a different language, then it can be tuned to it.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1241;downloadable_files_count: 0;Bulgaria;Linguistic Modeling Department, IPP, Bulgarian Academy of Sciences",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3155db3d-6d76-5fd7-9d5c-28f36d328fcc",
-    "notes": [
-        "It is used morphological lexicon of Bulgarian (100 000 lemmas) compiled as a finite-state automaton in CLaRK System. It requires the text to be first tokenized and it is applied in each token. Includes also guessers for unknown words and Named Entities gazetteers. If the corresponding resources are available for a different language, then it can be tuned to it."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1241"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "BulTreeBank Morphological Analyzer"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/315bbff5-f465-5d1f-8cc7-1d12ef03d1a2.json b/oaitestdata/clarin-oai_dc/SET_1/json/315bbff5-f465-5d1f-8cc7-1d12ef03d1a2.json
deleted file mode 100644
index ecc21aa3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/315bbff5-f465-5d1f-8cc7-1d12ef03d1a2.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Prest, John M."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "382 KB",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0552",
-    "MetadataAccess": [
-        "oai:ota:oucs:0552"
-    ],
-    "PublicationTimestamp": "1856-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1856"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Memoirs"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Peel, Robert, Sir, 1788-1850"
-    ],
-    "fulltext": "oai:ota:oucs:0552;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0552.xml;Memoirs / by the Right Honourable Sir Robert Peel;Peel, Robert, Sir, 1788-1850;1856-1857;text_and_corpus_linguistics;Autobiography -- 20th century;eng;Oxford Text Archive, University of Oxford;Prest, John M.;text/plain;382 KB;Text;Memoirs;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "315bbff5-f465-5d1f-8cc7-1d12ef03d1a2",
-    "oai_identifier": [
-        "oai:ota:oucs:0552"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Autobiography -- th century"
-        }
-    ],
-    "title": [
-        "Memoirs / by the Right Honourable Sir Robert Peel"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0552.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/318d08c3-e386-5009-9a2a-cc97019f5535.json b/oaitestdata/clarin-oai_dc/SET_1/json/318d08c3-e386-5009-9a2a-cc97019f5535.json
deleted file mode 100644
index f3bbece4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/318d08c3-e386-5009-9a2a-cc97019f5535.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=bdd9f3b66b3711e2a2aa782bcb0741356d33b026b0814900abeb63dd1958ae58",
-    "MetadataAccess": [
-        "bdd9f3b66b3711e2a2aa782bcb0741356d33b026b0814900abeb63dd1958ae58"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "bdd9f3b66b3711e2a2aa782bcb0741356d33b026b0814900abeb63dd1958ae58;2018-11-15T16:40:07Z;toolService;toolService:service;U-Compare Tokenisation service;Web service created by exporting UIMA-based workflow from the U-Compare text mining system.\nFunctionality: Identifies sentences and tokens in plain text.\nTools in workflow: Freeling sentence splitter web service (service provided by the PANACEA project), LX-Tokenizer (web service provided by the University of Lisbon)\nNOTE: The licence provided covers the web service only. Tools used to create the workflow may have their own licences;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "318d08c3-e386-5009-9a2a-cc97019f5535",
-    "notes": [
-        "Web service created by exporting UIMA-based workflow from the U-Compare text mining system.\nFunctionality: Identifies sentences and tokens in plain text.\nTools in workflow: Freeling sentence splitter web service (service provided by the PANACEA project), LX-Tokenizer (web service provided by the University of Lisbon)\nNOTE: The licence provided covers the web service only. Tools used to create the workflow may have their own licences"
-    ],
-    "oai_identifier": [
-        "bdd9f3b66b3711e2a2aa782bcb0741356d33b026b0814900abeb63dd1958ae58"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:service"
-    ],
-    "state": "active",
-    "title": [
-        "U-Compare Tokenisation service"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/31959f4e-b1a7-5f4e-985f-00b7d675d6f7.json b/oaitestdata/clarin-oai_dc/SET_1/json/31959f4e-b1a7-5f4e-985f-00b7d675d6f7.json
deleted file mode 100644
index 4bbd4016..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/31959f4e-b1a7-5f4e-985f-00b7d675d6f7.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Wikipedia"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 100",
-        "text/plain"
-    ],
-    "Language": [],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/216",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/216"
-    ],
-    "PID": "http://hdl.handle.net/11321/216",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Wikipedia"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Wikipedia"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/216;2015-06-10T14:32:56Z;hdl_11321_3;hdl_11321_4;Wiki test;Wikipedia;Wikipedia, kategorie Szachy i Samochody - zbi\u00f3r testowy dla klasyfikatora;2015;corpus;http://hdl.handle.net/11321/216;polski;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain; charset=utf-8;downloadable_files_count: 100;Wikipedia",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "31959f4e-b1a7-5f4e-985f-00b7d675d6f7",
-    "notes": [
-        "Wikipedia, kategorie Szachy i Samochody - zbi\u00f3r testowy dla klasyfikatora"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/216"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Wiki test"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/31a7e549-d6e0-511c-99d4-abe667d55c5e.json b/oaitestdata/clarin-oai_dc/SET_1/json/31a7e549-d6e0-511c-99d4-abe667d55c5e.json
deleted file mode 100644
index 0c029a90..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/31a7e549-d6e0-511c-99d4-abe667d55c5e.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "University of Malta"
-    ],
-    "Contributor": [
-        "Attard, Duncan",
-        "Rosner, Mike"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1235",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1235"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1235",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Malta"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1235;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;maltitok;Attard, Duncan;Rosner, Mike;A tokeniser for the Maltese language. The tokeniser accepts UTF8 text and produces UTF8 text, so can be used in a pipeline.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1235;downloadable_files_count: 0;University of Malta;http://staff.um.edu.mt/mros1/MLRS/tools",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "31a7e549-d6e0-511c-99d4-abe667d55c5e",
-    "notes": [
-        "A tokeniser for the Maltese language. The tokeniser accepts UTF8 text and produces UTF8 text, so can be used in a pipeline."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1235"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "maltitok"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/31a95874-f3c5-58fa-872b-0bf340631cbc.json b/oaitestdata/clarin-oai_dc/SET_1/json/31a95874-f3c5-58fa-872b-0bf340631cbc.json
deleted file mode 100644
index 64076def..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/31a95874-f3c5-58fa-872b-0bf340631cbc.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Academy of Sciences"
-    ],
-    "Contributor": [
-        "Kontra, Mikl\u00f3s"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Hungarian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1019",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1019"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1019",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Academy of Sciences"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Hungary"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1019;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Budapest Sociolinguistic Interview (BSI);Kontra, Mikl\u00f3s;BSI is a large-scale survey which provides reliable data on and analyses of the varieties of Hungarian spoken in Budapest.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1019;hun;downloadable_files_count: 0;Hungary;Academy of Sciences;http://www.nytud.hu/buszi/bsi.htm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "31a95874-f3c5-58fa-872b-0bf340631cbc",
-    "notes": [
-        "BSI is a large-scale survey which provides reliable data on and analyses of the varieties of Hungarian spoken in Budapest."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1019"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Budapest Sociolinguistic Interview (BSI)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/31b6b6b6-c379-592a-ab99-151db2e616df.json b/oaitestdata/clarin-oai_dc/SET_1/json/31b6b6b6-c379-592a-ab99-151db2e616df.json
deleted file mode 100644
index 41de0e64..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/31b6b6b6-c379-592a-ab99-151db2e616df.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Czech",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1804",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1804"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1804",
-    "PublicationTimestamp": "2016-10-20T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Mare\u010dek, David"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1804;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Czech-English Manual Word Alignment;Mare\u010dek, David;word alignment;parallel corpus;Corpus of manually aligned Czech-English parallel sentences. It comprises 2500 parallel sentences from 7 different sources.;2016-10-20;corpus;http://hdl.handle.net/11234/1-1804;ces;eng;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/czech-english-manual-word-alignment",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "31b6b6b6-c379-592a-ab99-151db2e616df",
-    "notes": [
-        "Corpus of manually aligned Czech-English parallel sentences. It comprises 2500 parallel sentences from 7 different sources."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1804"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "word alignment"
-        },
-        {
-            "name": "parallel corpus"
-        }
-    ],
-    "title": [
-        "Czech-English Manual Word Alignment"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/31d312bc-8c76-5590-a04d-1d191259ee13.json b/oaitestdata/clarin-oai_dc/SET_1/json/31d312bc-8c76-5590-a04d-1d191259ee13.json
deleted file mode 100644
index efd9be76..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/31d312bc-8c76-5590-a04d-1d191259ee13.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Ruhr-Universit\u00e4t Bochum"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-724",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-724"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-724",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Ruhr-Universit\u00e4t Bochum"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Code of conduct"
-    ],
-    "SpatialCoverage": [
-        "Indonesia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-724;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Waima'a corpus;Documentation of the Waima'a project (DoBeS project);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-724;Code of conduct;downloadable_files_count: 0;Indonesia;Ruhr-Universit\u00e4t Bochum;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI538936%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "31d312bc-8c76-5590-a04d-1d191259ee13",
-    "notes": [
-        "Documentation of the Waima'a project (DoBeS project)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-724"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Waima'a corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/31d4ca8e-f531-5e69-b49a-066c255f0c15.json b/oaitestdata/clarin-oai_dc/SET_1/json/31d4ca8e-f531-5e69-b49a-066c255f0c15.json
deleted file mode 100644
index 444ef374..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/31d4ca8e-f531-5e69-b49a-066c255f0c15.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Flannagan, Roy",
-        "Burnard, Lou",
-        "Corns, Thomas N."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 219 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2228",
-    "MetadataAccess": [
-        "oai:ota:oucs:2228"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Milton, John, 1608-1674"
-    ],
-    "fulltext": "oai:ota:oucs:2228;2018-10-16T09:05:04Z;http://ota.ox.ac.uk/headers/2228.xml;Paradise regained, and, Samson Agonistes [1671] / John Milton;Milton, John, 1608-1674;text_and_corpus_linguistics;Epic poetry, English -- 17th century;eng;Oxford Text Archive, University of Oxford;Corns, Thomas N.;Flannagan, Roy;Burnard, Lou;text/sgml;(1 file : ca. 219 KB);Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "31d4ca8e-f531-5e69-b49a-066c255f0c15",
-    "oai_identifier": [
-        "oai:ota:oucs:2228"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Epic poetry"
-        },
-        {
-            "name": "English -- th century"
-        }
-    ],
-    "title": [
-        "Paradise regained, and, Samson Agonistes [1671] / John Milton"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2228.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/31d594f9-c5ab-5056-96d1-f8c01fa038ee.json b/oaitestdata/clarin-oai_dc/SET_1/json/31d594f9-c5ab-5056-96d1-f8c01fa038ee.json
deleted file mode 100644
index f2963d98..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/31d594f9-c5ab-5056-96d1-f8c01fa038ee.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Masaryk University, NLP Centre"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "text/plain"
-    ],
-    "Language": [
-        "English",
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1932",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1932"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1932",
-    "PublicationTimestamp": "2016-12-02T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Masaryk University, NLP Centre"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Blahu\u0161, Marek",
-        "Baisa, V\u00edt",
-        "\u0160tromajerov\u00e1, Ad\u00e9la"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1932;2018-10-29T14:08:59Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;English-Czech Corpus from Wikipedia;\u0160tromajerov\u00e1, Ad\u00e9la;Baisa, V\u00edt;Blahu\u0161, Marek;Wikipedia;Sentence-parallel corpus made from English and Czech Wikipedias based on translated articles from English into Czech.\r\n\r\nThe work done is described in the paper: \u0160TROMAJEROV\u00c1, Ad\u00e9la, V\u00edt BAISA a Marek BLAHU\u0160. Between Comparable and Parallel: English-Czech Corpus from Wikipedia. In RASLAN 2016 Recent Advances in Slavonic Natural Language Processing. Brno: Tribun EU, 2016. s. 3-8, 6 s. ISBN 978-80-263-1095-2.;2016-12-02;corpus;http://hdl.handle.net/11234/1-1932;eng;ces;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;PUB;text/plain;text/plain; charset=utf-8;downloadable_files_count: 1;Masaryk University, NLP Centre;https://www.muni.cz/vyzkum/publikace/1362553",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "31d594f9-c5ab-5056-96d1-f8c01fa038ee",
-    "notes": [
-        "Sentence-parallel corpus made from English and Czech Wikipedias based on translated articles from English into Czech.\r\n\r\nThe work done is described in the paper: \u0160TROMAJEROV\u00c1, Ad\u00e9la, V\u00edt BAISA a Marek BLAHU\u0160. Between Comparable and Parallel: English-Czech Corpus from Wikipedia. In RASLAN 2016 Recent Advances in Slavonic Natural Language Processing. Brno: Tribun EU, 2016. s. 3-8, 6 s. ISBN 978-80-263-1095-2."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1932"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Wikipedia"
-        }
-    ],
-    "title": [
-        "English-Czech Corpus from Wikipedia"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/31e4c7cc-859e-5ada-ae79-614c0dd185cf.json b/oaitestdata/clarin-oai_dc/SET_1/json/31e4c7cc-859e-5ada-ae79-614c0dd185cf.json
deleted file mode 100644
index 17ce253e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/31e4c7cc-859e-5ada-ae79-614c0dd185cf.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "University of Liverpool, University of Birmingham, University of Barcelona"
-    ],
-    "Contributor": [
-        "Severin, Prof. D.S."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-873",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-873"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-873",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Liverpool, University of Birmingham, University of Barcelona"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Spain||United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-873;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Electronic corpus of 15th-century Castilian cancionero manuscripts;Severin, Prof. D.S.;Dutton lyric corpus of 15th century cancioneros, and the Severin-Maguire corpus of didactic poetry (15th century Castilian cancionero poetry);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-873;downloadable_files_count: 0;Spain||United Kingdom;University of Liverpool, University of Birmingham, University of Barcelona;http://cancionerovirtual.liv.ac.uk/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "31e4c7cc-859e-5ada-ae79-614c0dd185cf",
-    "notes": [
-        "Dutton lyric corpus of 15th century cancioneros, and the Severin-Maguire corpus of didactic poetry (15th century Castilian cancionero poetry)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-873"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Electronic corpus of 15th-century Castilian cancionero manuscripts"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3201044e-bce5-5d09-bac0-0314cfa09a2b.json b/oaitestdata/clarin-oai_dc/SET_1/json/3201044e-bce5-5d09-bac0-0314cfa09a2b.json
deleted file mode 100644
index c55dcdb1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3201044e-bce5-5d09-bac0-0314cfa09a2b.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "A"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1702",
-    "MetadataAccess": [
-        "oai:ota:oucs:1702"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Wells, H.G."
-    ],
-    "fulltext": "oai:ota:oucs:1702;2018-05-17T09:29:11Z;http://ota.ox.ac.uk/headers/1702.xml;The time machine;Wells, H.G.;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;A;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3201044e-bce5-5d09-bac0-0314cfa09a2b",
-    "oai_identifier": [
-        "oai:ota:oucs:1702"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The time machine"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1702.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3225dd69-04b0-50f8-a892-b7380c312d36.json b/oaitestdata/clarin-oai_dc/SET_1/json/3225dd69-04b0-50f8-a892-b7380c312d36.json
deleted file mode 100644
index 44e3cdcb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3225dd69-04b0-50f8-a892-b7380c312d36.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2603",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2603"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2603",
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://ceur-ws.org/Vol-1779/02bejeck.pdf"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Bej\u010dek, Eduard"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2603;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Czech Verbal MWEs;Bej\u010dek, Eduard;lexicon;verbs;multiword expressions;forms;lemmatization;Lexicon of Czech verbal multiword expressions (VMWEs) used in Parseme Shared Task 2017. https://typo.uni-konstanz.de/parseme/index.php/2-general/142-parseme-shared-task-on-automatic-detection-of-verbal-mwes\r\n\r\nLexicon consists of 4785 VMWEs, categorized into four categories according to Parseme Shared Task (PST) typology: IReflV (inherently reflexive verbs), LVC (light verb constructions), ID (idiomatic expressions) and OTH (other VMWEs with other than verbal syntactic head).\r\n\r\nVerbal multiword expressions as well as deverbative variants of VMWEs were annotated during the preparation phase of PST. These data were published as http://hdl.handle.net/11372/LRT-2282. Czech part includes 14,536 VMWE occurences:\r\n   1611 ID\r\n  10000 IReflV\r\n   2923 LVC\r\n      2 OTH\r\n This lexicon was created out of Czech data. Each lexicon entry is represented by one line in the form:\r\n\r\ntype     lemmas     frequency     PoS    [used form 1; used form 2; ... ]\r\n\r\n(columns are separated by tabs) where:\r\n type ... is the type of VMWE in PST typology\r\n lemmas ... are space separated lemmatized forms of all words that constitutes the VMWE\r\n frequency ... is the absolute frequency of this item in PST data\r\n PoS ... is a space separated list of parts of speech of individual words (in the same order as in \"lemmas\")\r\n final field contains a list of all (1 to 18) used forms found in the data (since Czech is a flective language).;2017;lexicalConceptualResource;http://hdl.handle.net/11234/1-2603;ces;http://ceur-ws.org/Vol-1779/02bejeck.pdf;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3225dd69-04b0-50f8-a892-b7380c312d36",
-    "notes": [
-        "Lexicon of Czech verbal multiword expressions (VMWEs) used in Parseme Shared Task 2017. https://typo.uni-konstanz.de/parseme/index.php/2-general/142-parseme-shared-task-on-automatic-detection-of-verbal-mwes\r\n\r\nLexicon consists of 4785 VMWEs, categorized into four categories according to Parseme Shared Task (PST) typology: IReflV (inherently reflexive verbs), LVC (light verb constructions), ID (idiomatic expressions) and OTH (other VMWEs with other than verbal syntactic head).\r\n\r\nVerbal multiword expressions as well as deverbative variants of VMWEs were annotated during the preparation phase of PST. These data were published as http://hdl.handle.net/11372/LRT-2282. Czech part includes 14,536 VMWE occurences:\r\n   1611 ID\r\n  10000 IReflV\r\n   2923 LVC\r\n      2 OTH\r\n This lexicon was created out of Czech data. Each lexicon entry is represented by one line in the form:\r\n\r\ntype     lemmas     frequency     PoS    [used form 1; used form 2; ... ]\r\n\r\n(columns are separated by tabs) where:\r\n type ... is the type of VMWE in PST typology\r\n lemmas ... are space separated lemmatized forms of all words that constitutes the VMWE\r\n frequency ... is the absolute frequency of this item in PST data\r\n PoS ... is a space separated list of parts of speech of individual words (in the same order as in \"lemmas\")\r\n final field contains a list of all (1 to 18) used forms found in the data (since Czech is a flective language)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2603"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "lexicon"
-        },
-        {
-            "name": "verbs"
-        },
-        {
-            "name": "multiword expressions"
-        },
-        {
-            "name": "forms"
-        },
-        {
-            "name": "lemmatization"
-        }
-    ],
-    "title": [
-        "Czech Verbal MWEs"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/328167d7-767f-5392-919b-c27161fe09f5.json b/oaitestdata/clarin-oai_dc/SET_1/json/328167d7-767f-5392-919b-c27161fe09f5.json
deleted file mode 100644
index d4f04f1b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/328167d7-767f-5392-919b-c27161fe09f5.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Jan Koco\u0144"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/zip",
-        "downloadable_files_count: 3",
-        "application/octet-stream"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/453",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/453"
-    ],
-    "PID": "http://hdl.handle.net/11321/453",
-    "PublicationTimestamp": "2018-01-15T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Jan Koco\u0144"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Koco\u0144, Jan"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/453;2018-01-15T17:25:00Z;hdl_11321_3;hdl_11321_4;CorpoGrabber-Desktop: The Toolchain to Automatic Acquiring and Extraction of the Website Content;Koco\u0144, Jan;CorpoGrabber;Desktop version of CorpoGrabber CLI;2018-01-15;toolService;http://hdl.handle.net/11321/453;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain; charset=utf-8;application/octet-stream;application/zip;application/octet-stream;downloadable_files_count: 3;Jan Koco\u0144",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "328167d7-767f-5392-919b-c27161fe09f5",
-    "notes": [
-        "Desktop version of CorpoGrabber CLI"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/453"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "CorpoGrabber"
-        }
-    ],
-    "title": [
-        "CorpoGrabber-Desktop: The Toolchain to Automatic Acquiring and Extraction of the Website Content"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3289c0c3-04f9-5d14-a975-e21495fd425f.json b/oaitestdata/clarin-oai_dc/SET_1/json/3289c0c3-04f9-5d14-a975-e21495fd425f.json
deleted file mode 100644
index 5695903c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3289c0c3-04f9-5d14-a975-e21495fd425f.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "IPI PAN"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "downloadable_files_count: 10",
-        "application/vnd.oasis.opendocument.text",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/391",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/391"
-    ],
-    "PID": "http://hdl.handle.net/11321/391",
-    "PublicationTimestamp": "2017-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "IPI PAN"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Kozio\u0142, Ewa"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/391;2017-05-30T11:55:05Z;hdl_11321_3;hdl_11321_4;Test szkolenie;Kozio\u0142, Ewa;korpus;ghkjhkjh;2017-05-30;corpus;http://hdl.handle.net/11321/391;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;text/plain;text/plain;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.oasis.opendocument.text;text/plain;application/vnd.oasis.opendocument.text;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;downloadable_files_count: 10;IPI PAN",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3289c0c3-04f9-5d14-a975-e21495fd425f",
-    "notes": [
-        "ghkjhkjh"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/391"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "korpus"
-        }
-    ],
-    "title": [
-        "Test szkolenie"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3301ad4c-638e-5250-a8cb-3eddd2f2281a.json b/oaitestdata/clarin-oai_dc/SET_1/json/3301ad4c-638e-5250-a8cb-3eddd2f2281a.json
deleted file mode 100644
index 07ce9bd8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3301ad4c-638e-5250-a8cb-3eddd2f2281a.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Taylor, Gary, 1953-"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 159 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0138",
-    "MetadataAccess": [
-        "oai:ota:oucs:0138"
-    ],
-    "PublicationTimestamp": "1609-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1609"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Shakespeare, William, 1564-1616"
-    ],
-    "fulltext": "oai:ota:oucs:0138;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0138.xml;Poems : [1609] / William Shakespeare;Shakespeare, William, 1564-1616;1609;text_and_corpus_linguistics;English poetry -- Early modern, 1500-1700;eng;Oxford Text Archive, University of Oxford;Taylor, Gary, 1953-;(1 file : ca. 159 KB);Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3301ad4c-638e-5250-a8cb-3eddd2f2281a",
-    "oai_identifier": [
-        "oai:ota:oucs:0138"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English poetry -- Early modern"
-        }
-    ],
-    "title": [
-        "Poems : [1609] / William Shakespeare"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0138.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3304493a-f626-516f-9d30-6a386d0af204.json b/oaitestdata/clarin-oai_dc/SET_1/json/3304493a-f626-516f-9d30-6a386d0af204.json
deleted file mode 100644
index 391f9d6f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3304493a-f626-516f-9d30-6a386d0af204.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=98c2a97a328311e2a2aa782bcb074135bcdfb897a7e841fd873a6bf68c435870",
-    "MetadataAccess": [
-        "98c2a97a328311e2a2aa782bcb074135bcdfb897a7e841fd873a6bf68c435870"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "98c2a97a328311e2a2aa782bcb074135bcdfb897a7e841fd873a6bf68c435870;2018-11-15T16:39:51Z;toolService;toolService:tool;UIMA/U-Compare Enju parser;Syntactic parser for English. Outputs predicate-argument structures. Also outputs base forms for each token. \n\nThe tool is provided as a UIMA component, which forms part of the in-built library of components provided with the U-Compare platform (see separate META-SHARE record)  for building and evaluating text mining workflows. The U-Compare Workbench (see separate META-SHARE record) provides a graphical drag-and drop interface for the rapid creation of workflows. \n;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3304493a-f626-516f-9d30-6a386d0af204",
-    "notes": [
-        "Syntactic parser for English. Outputs predicate-argument structures. Also outputs base forms for each token. \n\nThe tool is provided as a UIMA component, which forms part of the in-built library of components provided with the U-Compare platform (see separate META-SHARE record)  for building and evaluating text mining workflows. The U-Compare Workbench (see separate META-SHARE record) provides a graphical drag-and drop interface for the rapid creation of workflows. \n"
-    ],
-    "oai_identifier": [
-        "98c2a97a328311e2a2aa782bcb074135bcdfb897a7e841fd873a6bf68c435870"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "UIMA/U-Compare Enju parser"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3312c128-76b0-52fd-b63d-17cdbca3866e.json b/oaitestdata/clarin-oai_dc/SET_1/json/3312c128-76b0-52fd-b63d-17cdbca3866e.json
deleted file mode 100644
index e6838c61..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3312c128-76b0-52fd-b63d-17cdbca3866e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4579",
-    "MetadataAccess": [
-        "oai:ota:oucs:4579"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Lennox, Charlotte, ca. 1729-1804."
-    ],
-    "fulltext": "oai:ota:oucs:4579;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4579.xml;Euphemia. By Mrs. Charlotte Lennox. In four volumes.: [pt.2];Lennox, Charlotte, ca. 1729-1804.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3312c128-76b0-52fd-b63d-17cdbca3866e",
-    "oai_identifier": [
-        "oai:ota:oucs:4579"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Euphemia. By Mrs. Charlotte Lennox. In four volumes.: [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4579.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/33230fc5-7a76-5ac6-99c2-d3ffd890a587.json b/oaitestdata/clarin-oai_dc/SET_1/json/33230fc5-7a76-5ac6-99c2-d3ffd890a587.json
deleted file mode 100644
index 6dbccb46..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/33230fc5-7a76-5ac6-99c2-d3ffd890a587.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Institute of Mathematics and Computer Science, University of Latvia"
-    ],
-    "Contributor": [
-        "Gr\u016bz\u012btis, Normunds"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/xml"
-    ],
-    "Language": [
-        "Latvian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-476",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-476"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-476",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institute of Mathematics and Computer Science, University of Latvia"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Latvia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-476;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Concise dictionary of Latvian;Gr\u016bz\u012btis, Normunds;> 25 000 entries;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-476;lav;application/xml;downloadable_files_count: 0;Latvia;Institute of Mathematics and Computer Science, University of Latvia;http://www.tezaurs.lv/lvv/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "33230fc5-7a76-5ac6-99c2-d3ffd890a587",
-    "notes": [
-        "> 25 000 entries"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-476"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Concise dictionary of Latvian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3354e871-10d4-5f00-953a-24a72bb242bc.json b/oaitestdata/clarin-oai_dc/SET_1/json/3354e871-10d4-5f00-953a-24a72bb242bc.json
deleted file mode 100644
index 59b33623..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3354e871-10d4-5f00-953a-24a72bb242bc.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4347",
-    "MetadataAccess": [
-        "oai:ota:oucs:4347"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pratt, Mr. (Samuel Jackson), 1749-1814."
-    ],
-    "fulltext": "oai:ota:oucs:4347;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4347.xml;Shenstone-Green: or, the new Paradise lost. Being a history of human nature. In three volumes. ... Written by the proprietor of the Green. The editor Courtney Melmoth. [pt.1];Pratt, Mr. (Samuel Jackson), 1749-1814.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3354e871-10d4-5f00-953a-24a72bb242bc",
-    "oai_identifier": [
-        "oai:ota:oucs:4347"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Shenstone-Green: or, the new Paradise lost. Being a history of human nature. In three volumes. ... Written by the proprietor of the Green. The editor Courtney Melmoth. [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4347.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3364bc89-2720-553e-8c1e-f726886bc5e9.json b/oaitestdata/clarin-oai_dc/SET_1/json/3364bc89-2720-553e-8c1e-f726886bc5e9.json
deleted file mode 100644
index 0e6b3495..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3364bc89-2720-553e-8c1e-f726886bc5e9.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4896",
-    "MetadataAccess": [
-        "oai:ota:oucs:4896"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Trusler, John, 1735-1820."
-    ],
-    "fulltext": "oai:ota:oucs:4896;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4896.xml;Luxury no political evil: but demonstratively proved to be necessary to the preservation and prosperity of states. Addressed to the British senate.;Trusler, John, 1735-1820.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3364bc89-2720-553e-8c1e-f726886bc5e9",
-    "oai_identifier": [
-        "oai:ota:oucs:4896"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Luxury no political evil: but demonstratively proved to be necessary to the preservation and prosperity of states. Addressed to the British senate."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4896.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/33679436-2f4a-5654-8488-6ef6abace403.json b/oaitestdata/clarin-oai_dc/SET_1/json/33679436-2f4a-5654-8488-6ef6abace403.json
deleted file mode 100644
index faf88112..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/33679436-2f4a-5654-8488-6ef6abace403.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "Church Slavic"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-932",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-932"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-932",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-932;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Old Church Slavic;ca. 200.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-932;chu;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#aksl",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "33679436-2f4a-5654-8488-6ef6abace403",
-    "notes": [
-        "ca. 200.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-932"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Old Church Slavic"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/336f6833-010c-5ccc-8ce0-e7affb5519ba.json b/oaitestdata/clarin-oai_dc/SET_1/json/336f6833-010c-5ccc-8ce0-e7affb5519ba.json
deleted file mode 100644
index a21e1c7e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/336f6833-010c-5ccc-8ce0-e7affb5519ba.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Meertens Institute KNAW The Netherlands"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-607",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-607"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-607",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Meertens Institute KNAW The Netherlands"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Belgium||Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-607;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Plant names in Dutch dialect (PLAND);Plant names in Dutch dialect;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-607;nld;downloadable_files_count: 0;Belgium||Netherlands (the);Meertens Institute KNAW The Netherlands;http://www.meertens.knaw.nl/pland/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "336f6833-010c-5ccc-8ce0-e7affb5519ba",
-    "notes": [
-        "Plant names in Dutch dialect"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-607"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Plant names in Dutch dialect (PLAND)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3381f7d5-ea5e-53ad-b757-73d2d330fdfc.json b/oaitestdata/clarin-oai_dc/SET_1/json/3381f7d5-ea5e-53ad-b757-73d2d330fdfc.json
deleted file mode 100644
index 3c31d2f3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3381f7d5-ea5e-53ad-b757-73d2d330fdfc.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 3",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1194",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1194"
-    ],
-    "PID": "http://hdl.handle.net/11356/1194",
-    "PublicationTimestamp": "2018-08-03T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11356/1053"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "https://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Dobrovoljc, Kaja"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1194;2018-08-03T18:45:16Z;hdl_11356_1023;hdl_11356_1024;IMP corpus n-grams 2.0;Dobrovoljc, Kaja;n-grams;wordlist;multiword expressions;A collection of n-grams extracted from the IMP corpus of historical Slovene (cf. http://nl.ijs.si/imp/). Three sets of n-gram lists are provided for lowercased word n-grams of length 1 to 5:\r\n- extensive frequency lists of all extracted n-grams\r\n- filtered frequency lists of n-grams with minimum frequency 10/mil.\r\n- adjusted frequency list of all n-grams with minimum frequency 10/mil.\r\n\r\nOnly n-grams within sentences have been counted, ignoring punctuation. For the filtered and adjusted list, only n-grams occurring in at least 2 different texts have been extracted.\r\n\r\nKey references:\r\n- K. Dobrovoljc, 2018. N-gram frequency lists for reference corpora of Slovenian language. Proceedings of the Language Technologies & Digital Humanities Conference 2018.\r\n- T. Erjavec. 2015. The IMP historical Slovene language resources. Language resources and evaluation 49/3, 753-775. doi: 10.1007/s10579-015-9294-7.\r\n- M. B. O\u2019Donnell, 2010. The adjusted frequency list: A method to produce cluster-sensitive frequency lists. ICAME Journal 35, 135\u2013169.;2018-08-03;lexicalConceptualResource;http://hdl.handle.net/11356/1194;slv;http://hdl.handle.net/11356/1053;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);https://creativecommons.org/licenses/by-sa/4.0/;PUB;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 3;Centre for Language Resources and Technologies, University of Ljubljana",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3381f7d5-ea5e-53ad-b757-73d2d330fdfc",
-    "notes": [
-        "A collection of n-grams extracted from the IMP corpus of historical Slovene (cf. http://nl.ijs.si/imp/). Three sets of n-gram lists are provided for lowercased word n-grams of length 1 to 5:\r\n- extensive frequency lists of all extracted n-grams\r\n- filtered frequency lists of n-grams with minimum frequency 10/mil.\r\n- adjusted frequency list of all n-grams with minimum frequency 10/mil.\r\n\r\nOnly n-grams within sentences have been counted, ignoring punctuation. For the filtered and adjusted list, only n-grams occurring in at least 2 different texts have been extracted.\r\n\r\nKey references:\r\n- K. Dobrovoljc, 2018. N-gram frequency lists for reference corpora of Slovenian language. Proceedings of the Language Technologies & Digital Humanities Conference 2018.\r\n- T. Erjavec. 2015. The IMP historical Slovene language resources. Language resources and evaluation 49/3, 753-775. doi: 10.1007/s10579-015-9294-7.\r\n- M. B. O\u2019Donnell, 2010. The adjusted frequency list: A method to produce cluster-sensitive frequency lists. ICAME Journal 35, 135\u2013169."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1194"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "n-grams"
-        },
-        {
-            "name": "wordlist"
-        },
-        {
-            "name": "multiword expressions"
-        }
-    ],
-    "title": [
-        "IMP corpus n-grams 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3398969f-3c52-5f66-bc26-9fc9763d18d6.json b/oaitestdata/clarin-oai_dc/SET_1/json/3398969f-3c52-5f66-bc26-9fc9763d18d6.json
deleted file mode 100644
index 24b0acfe..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3398969f-3c52-5f66-bc26-9fc9763d18d6.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48F9-4",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48F9-4"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-48F9-4",
-    "PublicationTimestamp": "2009-11-02T09:25:18Z",
-    "PublicationYear": [
-        "2009"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU General Public License, version 2",
-        "http://www.gnu.org/licenses/gpl-2.0.html",
-        "PUB"
-    ],
-    "author": [
-        "Krbec, Pavel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48F9-4;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;HMM tagger;Krbec, Pavel;tagger;morphology;The HMM-based Tagger is a software for morphological disambiguation (tagging) of Czech texts. The algorithm is statistical, based on the Hidden Markov Models.;2009-11-02T09:25:18Z;toolService;http://hdl.handle.net/11858/00-097C-0000-0001-48F9-4;ces;GNU General Public License, version 2;http://www.gnu.org/licenses/gpl-2.0.html;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/pdt/Morphology_and_Tagging/Tagging/MM_tagger/index.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3398969f-3c52-5f66-bc26-9fc9763d18d6",
-    "notes": [
-        "The HMM-based Tagger is a software for morphological disambiguation (tagging) of Czech texts. The algorithm is statistical, based on the Hidden Markov Models."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48F9-4"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "tagger"
-        },
-        {
-            "name": "morphology"
-        }
-    ],
-    "title": [
-        "HMM tagger"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/339900eb-ad0a-5a2a-9d38-ca39c9bbd69a.json b/oaitestdata/clarin-oai_dc/SET_1/json/339900eb-ad0a-5a2a-9d38-ca39c9bbd69a.json
deleted file mode 100644
index 55c9fc2c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/339900eb-ad0a-5a2a-9d38-ca39c9bbd69a.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-941",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-941"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-941",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-941;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Old Dutch;ca. 70.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-941;nld;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#mndl",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "339900eb-ad0a-5a2a-9d38-ca39c9bbd69a",
-    "notes": [
-        "ca. 70.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-941"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Old Dutch"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/33a7b23e-f184-59da-ae5d-f40b0a8d5b17.json b/oaitestdata/clarin-oai_dc/SET_1/json/33a7b23e-f184-59da-ae5d-f40b0a8d5b17.json
deleted file mode 100644
index 34fb8922..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/33a7b23e-f184-59da-ae5d-f40b0a8d5b17.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5550",
-    "MetadataAccess": [
-        "oai:ota:oucs:5550"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Rock, Dr. (Richard), 1708-1774."
-    ],
-    "fulltext": "oai:ota:oucs:5550;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5550.xml;A treatise of the venereal disease: plainly discovering and directing both sexes, how they may become their own doctors. Teaching them plainly, and perfectly to know their own condition ... And how to cure themselves ... Also to heal all gleets ...;Rock, Dr. (Richard), 1708-1774.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "33a7b23e-f184-59da-ae5d-f40b0a8d5b17",
-    "oai_identifier": [
-        "oai:ota:oucs:5550"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A treatise of the venereal disease: plainly discovering and directing both sexes, how they may become their own doctors. Teaching them plainly, and perfectly to know their own condition ... And how to cure themselves ... Also to heal all gleets ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5550.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/33b757aa-700d-50a4-8308-761708e6cefc.json b/oaitestdata/clarin-oai_dc/SET_1/json/33b757aa-700d-50a4-8308-761708e6cefc.json
deleted file mode 100644
index eaf99aa2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/33b757aa-700d-50a4-8308-761708e6cefc.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "B"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1544",
-    "MetadataAccess": [
-        "oai:ota:oucs:1544"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Defoe, Daniel,  1661?-1731"
-    ],
-    "fulltext": "oai:ota:oucs:1544;2018-04-16T15:30:51Z;http://ota.ox.ac.uk/headers/1544.xml;Robinson Crusoe;Defoe, Daniel,  1661?-1731;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;B;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "33b757aa-700d-50a4-8308-761708e6cefc",
-    "oai_identifier": [
-        "oai:ota:oucs:1544"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Robinson Crusoe"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1544.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/33cd8360-114b-5bb5-93fe-758442c5f71b.json b/oaitestdata/clarin-oai_dc/SET_1/json/33cd8360-114b-5bb5-93fe-758442c5f71b.json
deleted file mode 100644
index 158d5764..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/33cd8360-114b-5bb5-93fe-758442c5f71b.json
+++ /dev/null
@@ -1,109 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Bulgarian",
-        "Czech",
-        "English",
-        "Estonian",
-        "Hungarian",
-        "Lithuanian",
-        "Romanian",
-        "Russian",
-        "Slovenian",
-        "Serbian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1044",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1044"
-    ],
-    "PID": "http://hdl.handle.net/11356/1044",
-    "PublicationTimestamp": "2010-05-14T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/211938",
-        "https://doi.org/10.1007/s10579-011-9174-8",
-        "http://hdl.handle.net/11372/LRT-675"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Oravecz, Csaba",
-        "Kaalep, Heiki-Jaan",
-        "Krstev, Cvetana",
-        "Petkevi\u010d, Vladim\u00edr",
-        "Dimitrova, Ludmila",
-        "Priest-Dorman, Greg",
-        "Sryvkin, Sergey",
-        "Vukovi\u0107, Olga",
-        "Tufi\u015f, Dan",
-        "Sokolovsky, Paul",
-        "Erjavec, Toma\u017e",
-        "Sinapova, Lydia",
-        "Orav, Heili",
-        "Villandi, Viire",
-        "Paldre, Leho",
-        "Utka, Andrius",
-        "Bruda, \u015etefan",
-        "Simov, Kiril",
-        "Ide, Nancy",
-        "Vitas, Du\u0161ko"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1044;2017-09-29T14:05:02Z;hdl_11356_1023;hdl_11356_1024;MULTEXT-East \"1984\" document corpus 4.0;Erjavec, Toma\u017e;Bruda, \u015etefan;Dimitrova, Ludmila;Ide, Nancy;Kaalep, Heiki-Jaan;Krstev, Cvetana;Orav, Heili;Oravecz, Csaba;Paldre, Leho;Petkevi\u010d, Vladim\u00edr;Priest-Dorman, Greg;Simov, Kiril;Sinapova, Lydia;Sokolovsky, Paul;Sryvkin, Sergey;Tufi\u015f, Dan;Utka, Andrius;Villandi, Viire;Vitas, Du\u0161ko;Vukovi\u0107, Olga;parallel corpus;multilingual;TEI;The novel \"1984\" by George Orwell is the central component of the MULTEXT-East corpus. This parallel and sentence aligned corpus contains the novel in the English original (about 100,000 words in length), and its translations into a number of languages. \r\n\r\nThis version of the corpus contains structurally annotated texts only, which contain elements such as the paragraph, the footnote, and highlighted text. In terms of linguistic annotations, the text contain names and sentences.\r\n\r\nThe linguistically annotated texts are a separate submission (http://hdl.handle.net/11356/1043) also with somewhat different languages.;2010-05-14;corpus;http://hdl.handle.net/11356/1044;bul;ces;eng;est;hun;lit;ron;rus;slv;srp;info:eu-repo/grantAgreement/EC/FP7/211938;https://doi.org/10.1007/s10579-011-9174-8;http://hdl.handle.net/11372/LRT-675;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);https://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Jo\u017eef Stefan Institute;http://nl.ijs.si/ME/V4/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "33cd8360-114b-5bb5-93fe-758442c5f71b",
-    "notes": [
-        "The novel \"1984\" by George Orwell is the central component of the MULTEXT-East corpus. This parallel and sentence aligned corpus contains the novel in the English original (about 100,000 words in length), and its translations into a number of languages. \r\n\r\nThis version of the corpus contains structurally annotated texts only, which contain elements such as the paragraph, the footnote, and highlighted text. In terms of linguistic annotations, the text contain names and sentences.\r\n\r\nThe linguistically annotated texts are a separate submission (http://hdl.handle.net/11356/1043) also with somewhat different languages."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1044"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parallel corpus"
-        },
-        {
-            "name": "multilingual"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "MULTEXT-East \"1984\" document corpus 4.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/33ddc85b-3634-52f9-bfbb-fbe7042a2beb.json b/oaitestdata/clarin-oai_dc/SET_1/json/33ddc85b-3634-52f9-bfbb-fbe7042a2beb.json
deleted file mode 100644
index acd43b85..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/33ddc85b-3634-52f9-bfbb-fbe7042a2beb.json
+++ /dev/null
@@ -1,95 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "application/zip"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1138",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1138"
-    ],
-    "PID": "http://hdl.handle.net/11356/1138",
-    "PublicationTimestamp": "2017-08-17T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "http://slovenscina2.0.trojina.si/arhiv/2016-2/2016-2-04/",
-        "http://nl.ijs.si/janes/viri/avtomatsko-oznaceni-korpusi/#Janes-Blog",
-        "https://doi.org/10.1007/s10579-018-9425-z"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "Erjavec, Toma\u017e",
-        "Ljube\u0161i\u0107, Nikola",
-        "Fi\u0161er, Darja"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1138;2018-10-29T10:30:54Z;hdl_11356_1023;hdl_11356_1024;Blog post and comment corpus Janes-Blog 1.0;Erjavec, Toma\u017e;Ljube\u0161i\u0107, Nikola;Fi\u0161er, Darja;computer-mediated communication;blogs;word normalisation;tagging;lemmatisation;named entities;TEI;Janes-Blog is an annotated corpus of Slovene blogs from websites rtvslo.si and publishwall.si from the period 2006-10 to 2016-01. The corpus is structured into individual texts containing the post of the blog and comments on the post, together with their metadata. The texts in the corpus are tokenised, sentence segmented, word normalised, morphosyntactically tagged, lemmatised and annotated with named entities. Due to protection of privacy, usernames are not included in the metadata and 'person' as well as 'person derivative' named entities have been removed from the texts.;2017-08-17;corpus;http://hdl.handle.net/11356/1138;slv;http://slovenscina2.0.trojina.si/arhiv/2016-2/2016-2-04/;http://nl.ijs.si/janes/viri/avtomatsko-oznaceni-korpusi/#Janes-Blog;https://doi.org/10.1007/s10579-018-9425-z;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;https://creativecommons.org/licenses/by/4.0/;text/plain; charset=utf-8;application/zip;application/zip;downloadable_files_count: 2;Jo\u017eef Stefan Institute;http://nl.ijs.si/janes/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "33ddc85b-3634-52f9-bfbb-fbe7042a2beb",
-    "notes": [
-        "Janes-Blog is an annotated corpus of Slovene blogs from websites rtvslo.si and publishwall.si from the period 2006-10 to 2016-01. The corpus is structured into individual texts containing the post of the blog and comments on the post, together with their metadata. The texts in the corpus are tokenised, sentence segmented, word normalised, morphosyntactically tagged, lemmatised and annotated with named entities. Due to protection of privacy, usernames are not included in the metadata and 'person' as well as 'person derivative' named entities have been removed from the texts."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1138"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "computer-mediated communication"
-        },
-        {
-            "name": "blogs"
-        },
-        {
-            "name": "word normalisation"
-        },
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "lemmatisation"
-        },
-        {
-            "name": "named entities"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "Blog post and comment corpus Janes-Blog 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/33f97eb3-d7e3-5787-86b2-bbe5d2867c59.json b/oaitestdata/clarin-oai_dc/SET_1/json/33f97eb3-d7e3-5787-86b2-bbe5d2867c59.json
deleted file mode 100644
index f9e36369..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/33f97eb3-d7e3-5787-86b2-bbe5d2867c59.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Berent"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 9",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/68",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/68"
-    ],
-    "PID": "http://hdl.handle.net/11321/68",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Berent"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Berent, Berent"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/68;2015-05-19T13:33:39Z;hdl_11321_3;hdl_11321_4;MWE Berent;Berent, Berent;Berent;2015-04-08;corpus;http://hdl.handle.net/11321/68;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 9;Berent",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "33f97eb3-d7e3-5787-86b2-bbe5d2867c59",
-    "notes": [
-        "Berent"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/68"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Berent"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3423557b-9bd6-50c9-8be7-b4125ef50b54.json b/oaitestdata/clarin-oai_dc/SET_1/json/3423557b-9bd6-50c9-8be7-b4125ef50b54.json
deleted file mode 100644
index 0c4692b8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3423557b-9bd6-50c9-8be7-b4125ef50b54.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3872",
-    "MetadataAccess": [
-        "oai:ota:oucs:3872"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Centlivre, Susanna, 1667?-1723."
-    ],
-    "fulltext": "oai:ota:oucs:3872;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3872.xml;The beau's duel: or a soldier for the ladies. A comedy, as it is acted at the New Theater in Lincolns-Inn-Fields, by Her Majesties servants.;Centlivre, Susanna, 1667?-1723.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3423557b-9bd6-50c9-8be7-b4125ef50b54",
-    "oai_identifier": [
-        "oai:ota:oucs:3872"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The beau's duel: or a soldier for the ladies. A comedy, as it is acted at the New Theater in Lincolns-Inn-Fields, by Her Majesties servants."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3872.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/342760e7-20c4-5f14-a01e-ab181e7f42d7.json b/oaitestdata/clarin-oai_dc/SET_1/json/342760e7-20c4-5f14-a01e-ab181e7f42d7.json
deleted file mode 100644
index 5457ef72..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/342760e7-20c4-5f14-a01e-ab181e7f42d7.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Piotra Dufoura"
-    ],
-    "Contributor": [
-        "\u0141adowski, Remigiusz (1738-1798). [ T\u0142.]"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-230806",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-230806"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D0E-0",
-    "PublicationTimestamp": "1792-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1792"
-    ],
-    "Publisher": [
-        "Drukarnia Piotra Dufoura"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/230806",
-        "oai:jbc.bj.uj.edu.pl:publication:242469"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1701/1800"
-    ],
-    "TempCoverageBegin": 53662478399,
-    "TempCoverageEnd": 53662478399,
-    "TemporalCoverage": " point in time : 1701-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1701-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1701-07-01T11:59:59Z",
-    "author": [
-        "Wilson, Henryk"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-230806;2019-03-01T13:10:48Z;Opisanie wysp Pelew, w cz\u0119\u015bci zachodniey Oceanu Spokoynego le\u017c\u0105cych u\u0142o\u017cone z dziennikow i podania kapitana Henryka Wilson i ludzi iego, ktorzy si\u0119 rozbi\u0142, na okr\u0119cie Kompanii Indyi Wschodnich nazwanym Antelope w miesi\u0105cu sierpniu 1783 [...];Wilson, Henryk;starodruki 18\u00a0w.;Drukarnia Piotra Dufoura;\u0141adowski, Remigiusz (1738-1798). [ T\u0142.];1792;starodruk;application/xml;clarind-uds:poldilemma-230806;hdl:11858/00-246C-0000-0023-8D0E-0;Biblioteka Jagiello\u0144ska, BJ St. Dr. 30234 I;http://jbc.bj.uj.edu.pl/Content/230806;oai:jbc.bj.uj.edu.pl:publication:242469;1701/1800;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "342760e7-20c4-5f14-a01e-ab181e7f42d7",
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-230806"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Opisanie wysp Pelew, w cz\u0119\u015bci zachodniey Oceanu Spokoynego le\u017c\u0105cych u\u0142o\u017cone z dziennikow i podania kapitana Henryka Wilson i ludzi iego, ktorzy si\u0119 rozbi\u0142, na okr\u0119cie Kompanii Indyi Wschodnich nazwanym Antelope w miesi\u0105cu sierpniu 1783 [...]"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/342e616d-7390-5148-9815-3b4277e79b0b.json b/oaitestdata/clarin-oai_dc/SET_1/json/342e616d-7390-5148-9815-3b4277e79b0b.json
deleted file mode 100644
index ca1d3684..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/342e616d-7390-5148-9815-3b4277e79b0b.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4529",
-    "MetadataAccess": [
-        "oai:ota:oucs:4529"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Defoe, Daniel, 1661?-1731."
-    ],
-    "fulltext": "oai:ota:oucs:4529;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4529.xml;A tour thro' the whole island of Great Britain: Divided into circuits or journeys. Giving a particular and entertaining account of whatever is curious, and worth observation; ... By a gentleman. ... [pt.3];Defoe, Daniel, 1661?-1731.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "342e616d-7390-5148-9815-3b4277e79b0b",
-    "oai_identifier": [
-        "oai:ota:oucs:4529"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A tour thro' the whole island of Great Britain: Divided into circuits or journeys. Giving a particular and entertaining account of whatever is curious, and worth observation; ... By a gentleman. ... [pt.3]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4529.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/345348f8-b9da-5cc9-a558-6d4bbcb37fc7.json b/oaitestdata/clarin-oai_dc/SET_1/json/345348f8-b9da-5cc9-a558-6d4bbcb37fc7.json
deleted file mode 100644
index f62324bd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/345348f8-b9da-5cc9-a558-6d4bbcb37fc7.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Information Studies Novo mesto"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 5",
-        "text/plain; charset=utf-8",
-        "application/pdf",
-        "text/plain"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1110",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1110"
-    ],
-    "PID": "http://hdl.handle.net/11356/1110",
-    "PublicationTimestamp": "2017-04-29T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Faculty of Information Studies Novo mesto"
-    ],
-    "RelatedIdentifier": [
-        "https://doi.org/10.1007/s10579-018-9413-3"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "https://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Bu\u010dar, Jo\u017ee"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1110;2018-12-02T19:42:20Z;hdl_11356_1023;hdl_11356_1024;Manually sentiment annotated Slovenian news corpus SentiNews 1.0;Bu\u010dar, Jo\u017ee;news corpus;sentiment classification;opinion mining;manual annotation;Between 2 and 6 annotators independently sentiment annotated a stratified random sample of 10,427 documents from the Slovenian news portals 24ur, Dnevnik, Finance, Rtvslo, and \u017durnal24. These portals contain political, business, economic and financial content. The texts were annotated using the five-level Lickert scale (1 \u2013 very negative, 2 \u2013 negative, 3 \u2013 neutral, 4 \u2013 positive, and 5 \u2013 very positive) on three levels of granularity, i.e. on the document, paragraph, and sentence level.;2017-04-29;corpus;http://hdl.handle.net/11356/1110;slv;https://doi.org/10.1007/s10579-018-9413-3;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);https://creativecommons.org/licenses/by-sa/4.0/;PUB;text/plain;text/plain;text/plain;text/plain;application/pdf;text/plain; charset=utf-8;downloadable_files_count: 5;Faculty of Information Studies Novo mesto;https://github.com/19Joey85/Sentiment-annotated-news-corpus-and-sentiment-lexicon-in-Slovene/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "345348f8-b9da-5cc9-a558-6d4bbcb37fc7",
-    "notes": [
-        "Between 2 and 6 annotators independently sentiment annotated a stratified random sample of 10,427 documents from the Slovenian news portals 24ur, Dnevnik, Finance, Rtvslo, and \u017durnal24. These portals contain political, business, economic and financial content. The texts were annotated using the five-level Lickert scale (1 \u2013 very negative, 2 \u2013 negative, 3 \u2013 neutral, 4 \u2013 positive, and 5 \u2013 very positive) on three levels of granularity, i.e. on the document, paragraph, and sentence level."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1110"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "news corpus"
-        },
-        {
-            "name": "sentiment classification"
-        },
-        {
-            "name": "opinion mining"
-        },
-        {
-            "name": "manual annotation"
-        }
-    ],
-    "title": [
-        "Manually sentiment annotated Slovenian news corpus SentiNews 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3459f5a1-37eb-59c4-9777-5b5e03d06075.json b/oaitestdata/clarin-oai_dc/SET_1/json/3459f5a1-37eb-59c4-9777-5b5e03d06075.json
deleted file mode 100644
index 42d78f5b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3459f5a1-37eb-59c4-9777-5b5e03d06075.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "420 KB"
-    ],
-    "Language": [
-        "French"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1104",
-    "MetadataAccess": [
-        "oai:ota:oucs:1104"
-    ],
-    "PublicationTimestamp": "1742-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1742"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Fiction"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Cr\u00c3\u00a9billon,  Monsieur de (Claude-Prosper Jolyot), 1707-1777"
-    ],
-    "fulltext": "oai:ota:oucs:1104;2018-03-05T12:05:10Z;http://ota.ox.ac.uk/headers/1104.xml;Le sopha / compiled by Jennifer Darzentas;Cr\u00c3\u00a9billon,  Monsieur de (Claude-Prosper Jolyot), 1707-1777;1742;text_and_corpus_linguistics;Fiction -- France -- 18th century;fra;Oxford Text Archive, University of Oxford;420 KB;Text;Fiction;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3459f5a1-37eb-59c4-9777-5b5e03d06075",
-    "oai_identifier": [
-        "oai:ota:oucs:1104"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- France -- th century"
-        }
-    ],
-    "title": [
-        "Le sopha / compiled by Jennifer Darzentas"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1104.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/347b9d36-b13a-51b5-9926-0ccc92bc1578.json b/oaitestdata/clarin-oai_dc/SET_1/json/347b9d36-b13a-51b5-9926-0ccc92bc1578.json
deleted file mode 100644
index 008ad21e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/347b9d36-b13a-51b5-9926-0ccc92bc1578.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5352",
-    "MetadataAccess": [
-        "oai:ota:oucs:5352"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Goldsmith, Oliver, 1730?-1774."
-    ],
-    "fulltext": "oai:ota:oucs:5352;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5352.xml;The vicar of Wakefield: a tale. Supposed to be written by himself. ... [pt.1];Goldsmith, Oliver, 1730?-1774.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "347b9d36-b13a-51b5-9926-0ccc92bc1578",
-    "oai_identifier": [
-        "oai:ota:oucs:5352"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The vicar of Wakefield: a tale. Supposed to be written by himself. ... [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5352.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3482bcae-8220-54a9-805b-00ff9e7c1ddf.json b/oaitestdata/clarin-oai_dc/SET_1/json/3482bcae-8220-54a9-805b-00ff9e7c1ddf.json
deleted file mode 100644
index 10d98cfe..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3482bcae-8220-54a9-805b-00ff9e7c1ddf.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=14c21c7827f811e6a2aa782bcb0741350dcd9beb0baa4857839bd854d616ea8d",
-    "MetadataAccess": [
-        "14c21c7827f811e6a2aa782bcb0741350dcd9beb0baa4857839bd854d616ea8d"
-    ],
-    "PublicationTimestamp": "2016-06-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "fulltext": "14c21c7827f811e6a2aa782bcb0741350dcd9beb0baa4857839bd854d616ea8d;2018-11-15T16:40:22Z;corpus;corpus:text;QTLeap LRT-M31-WP4;Treebanks and semantic lexicons for Basque, Bulgarian, Dutch, German and Portuguese. Created within European project QTLeap.;2016-06-01",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3482bcae-8220-54a9-805b-00ff9e7c1ddf",
-    "notes": [
-        "Treebanks and semantic lexicons for Basque, Bulgarian, Dutch, German and Portuguese. Created within European project QTLeap."
-    ],
-    "oai_identifier": [
-        "14c21c7827f811e6a2aa782bcb0741350dcd9beb0baa4857839bd854d616ea8d"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "QTLeap LRT-M31-WP4"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3484ae72-1127-5cca-881c-4f7d815f5f6b.json b/oaitestdata/clarin-oai_dc/SET_1/json/3484ae72-1127-5cca-881c-4f7d815f5f6b.json
deleted file mode 100644
index ae28efb6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3484ae72-1127-5cca-881c-4f7d815f5f6b.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=b4001f14328411e2a2aa782bcb0741357a9b05fa16e24671b5f4ff4aa0f6fb81",
-    "MetadataAccess": [
-        "b4001f14328411e2a2aa782bcb0741357a9b05fa16e24671b5f4ff4aa0f6fb81"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "b4001f14328411e2a2aa782bcb0741357a9b05fa16e24671b5f4ff4aa0f6fb81;2018-11-15T16:39:51Z;toolService;toolService:tool;GENIA Tagger;The GENIA tagger analyzes English sentences and outputs the base forms, part-of-speech tags, chunk tags, and named entity tags. The tagger is specifically tuned for biomedical text such as MEDLINE abstracts. ;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3484ae72-1127-5cca-881c-4f7d815f5f6b",
-    "notes": [
-        "The GENIA tagger analyzes English sentences and outputs the base forms, part-of-speech tags, chunk tags, and named entity tags. The tagger is specifically tuned for biomedical text such as MEDLINE abstracts. "
-    ],
-    "oai_identifier": [
-        "b4001f14328411e2a2aa782bcb0741357a9b05fa16e24671b5f4ff4aa0f6fb81"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "GENIA Tagger"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3484e15a-3a2e-5cfb-bc8b-e571851cc04b.json b/oaitestdata/clarin-oai_dc/SET_1/json/3484e15a-3a2e-5cfb-bc8b-e571851cc04b.json
deleted file mode 100644
index 97a87bd5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3484e15a-3a2e-5cfb-bc8b-e571851cc04b.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=8488fe0ae6de11e6a2aa782bcb0741351cffdfbc76c44c978fda58d3bfefbd56",
-    "MetadataAccess": [
-        "8488fe0ae6de11e6a2aa782bcb0741351cffdfbc76c44c978fda58d3bfefbd56"
-    ],
-    "PublicationTimestamp": "2017-01-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "fulltext": "8488fe0ae6de11e6a2aa782bcb0741351cffdfbc76c44c978fda58d3bfefbd56;2018-11-15T16:40:26Z;corpus;corpus:text;LX-ESSLLI 2008;The LX-ESSLLI 2008 data set was created from the ESSLLI 2008 Distributional Semantic Workshop shared-task set, made of 44 concrete nouns grouped in 6 semantic categories (4 animate and 2 inanimate). The grouping is done in an hierarchical way following the top 10 properties from the McRae (2005) norms: bird-animal-natural; ground animal-animal-natural; fruit tree-vegetable-natural; green-vegetable-natural; tool-artifact-artifact; vehicle-artifact-artifact.\nWe kept the organization into the same categories, resulting in a list with the same size as the original data set. ;2017-01-30",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3484e15a-3a2e-5cfb-bc8b-e571851cc04b",
-    "notes": [
-        "The LX-ESSLLI 2008 data set was created from the ESSLLI 2008 Distributional Semantic Workshop shared-task set, made of 44 concrete nouns grouped in 6 semantic categories (4 animate and 2 inanimate). The grouping is done in an hierarchical way following the top 10 properties from the McRae (2005) norms: bird-animal-natural; ground animal-animal-natural; fruit tree-vegetable-natural; green-vegetable-natural; tool-artifact-artifact; vehicle-artifact-artifact.\nWe kept the organization into the same categories, resulting in a list with the same size as the original data set. "
-    ],
-    "oai_identifier": [
-        "8488fe0ae6de11e6a2aa782bcb0741351cffdfbc76c44c978fda58d3bfefbd56"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "LX-ESSLLI 2008"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/34890308-de55-5d12-9e18-e235dda9919c.json b/oaitestdata/clarin-oai_dc/SET_1/json/34890308-de55-5d12-9e18-e235dda9919c.json
deleted file mode 100644
index 3ebd6bb2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/34890308-de55-5d12-9e18-e235dda9919c.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "less than 512 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0044",
-    "MetadataAccess": [
-        "oai:ota:oucs:0044"
-    ],
-    "PublicationTimestamp": "1864-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1864"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dostoevski, Fyodor,  1821-1881"
-    ],
-    "fulltext": "oai:ota:oucs:0044;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0044.xml; Notes from underground  / compiled by John B. Smith;Dostoevski, Fyodor,  1821-1881;1864;text_and_corpus_linguistics;Novels -- Russia -- 19th century;eng;Oxford Text Archive, University of Oxford;less than 512 KB;Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "34890308-de55-5d12-9e18-e235dda9919c",
-    "oai_identifier": [
-        "oai:ota:oucs:0044"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Novels -- Russia -- th century"
-        }
-    ],
-    "title": [
-        " Notes from underground  / compiled by John B. Smith"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0044.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3498095d-cba6-52fb-a29f-692fda96978a.json b/oaitestdata/clarin-oai_dc/SET_1/json/3498095d-cba6-52fb-a29f-692fda96978a.json
deleted file mode 100644
index 23aba973..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3498095d-cba6-52fb-a29f-692fda96978a.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "Contributor": [
-        "secretar\u00eda, Iula"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Catalan",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1193",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1193"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1193",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1193;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Estaci\u00f3 Terminus;secretar\u00eda, Iula;Tool for terminology management.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1193;cat;spa;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra;http://melot.upf.edu/Terminus2009/index.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3498095d-cba6-52fb-a29f-692fda96978a",
-    "notes": [
-        "Tool for terminology management."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1193"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Estaci\u00f3 Terminus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/34a5d49f-7b8c-5e0d-8ede-dc14bc22d152.json b/oaitestdata/clarin-oai_dc/SET_1/json/34a5d49f-7b8c-5e0d-8ede-dc14bc22d152.json
deleted file mode 100644
index 427fb511..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/34a5d49f-7b8c-5e0d-8ede-dc14bc22d152.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "VideoLectures.NET"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 3",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1189",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1189"
-    ],
-    "PID": "http://hdl.handle.net/11356/1189",
-    "PublicationTimestamp": "2018-08-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "VideoLectures.NET"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11356/1159"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by-nc-nd/4.0/"
-    ],
-    "author": [
-        "VideoLectures.NET"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1189;2018-10-24T20:57:17Z;hdl_11356_1023;hdl_11356_1024;Spoken corpus Gos VideoLectures 3.0 (audio);VideoLectures.NET;speech database;spoken corpus;academic speech;speech recognition;speech recordings;Gos VideoLectures is an add-on to the Gos reference corpus of spoken Slovene (http://hdl.handle.net/11356/1040), and covers public academic speech. The Gos VideoLectures corpus contains a selection of public lectures available through the web portal Videolectures.net provided by the Jo\u017eef Stefan Institute, and covers 37 lectures with 16 hours of speech. \r\nThis resource contains only audio recordings of the corpus \u2013 annotated transcriptions are available at http://hdl.handle.net/11356/1190.;2018-08-01;corpus;http://hdl.handle.net/11356/1189;slv;http://hdl.handle.net/11356/1159;Creative Commons - Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0);PUB;https://creativecommons.org/licenses/by-nc-nd/4.0/;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 3;VideoLectures.NET",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "34a5d49f-7b8c-5e0d-8ede-dc14bc22d152",
-    "notes": [
-        "Gos VideoLectures is an add-on to the Gos reference corpus of spoken Slovene (http://hdl.handle.net/11356/1040), and covers public academic speech. The Gos VideoLectures corpus contains a selection of public lectures available through the web portal Videolectures.net provided by the Jo\u017eef Stefan Institute, and covers 37 lectures with 16 hours of speech. \r\nThis resource contains only audio recordings of the corpus \u2013 annotated transcriptions are available at http://hdl.handle.net/11356/1190."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1189"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech database"
-        },
-        {
-            "name": "spoken corpus"
-        },
-        {
-            "name": "academic speech"
-        },
-        {
-            "name": "speech recognition"
-        },
-        {
-            "name": "speech recordings"
-        }
-    ],
-    "title": [
-        "Spoken corpus Gos VideoLectures 3.0 (audio)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/34e5bfd7-fe10-5b6f-8d4a-fbe44c6274e6.json b/oaitestdata/clarin-oai_dc/SET_1/json/34e5bfd7-fe10-5b6f-8d4a-fbe44c6274e6.json
deleted file mode 100644
index 5e4ba7e3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/34e5bfd7-fe10-5b6f-8d4a-fbe44c6274e6.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Woodhouse, J.R. (John Robert)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 59 KB)"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0408",
-    "MetadataAccess": [
-        "oai:ota:oucs:0408"
-    ],
-    "PublicationTimestamp": "1970-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1970"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Songs"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Vretos, Marinos Papadopoulos, 1828-1891"
-    ],
-    "fulltext": "oai:ota:oucs:0408;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0408.xml;Canti popolari della Grecia moderna / di Marino Vretos;Greek popular songs;Vretos, Marinos Papadopoulos, 1828-1891;1970;text_and_corpus_linguistics;Songs, Greek (Modern) -- Translations -- Italian -- 19th century;ita;Oxford Text Archive, University of Oxford;Woodhouse, J.R. (John Robert);(1 file : ca. 59 KB);Text;Songs;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "34e5bfd7-fe10-5b6f-8d4a-fbe44c6274e6",
-    "oai_identifier": [
-        "oai:ota:oucs:0408"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Songs"
-        }
-    ],
-    "title": [
-        "Canti popolari della Grecia moderna / di Marino Vretos",
-        "Greek popular songs"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0408.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/34ff8662-e520-5346-842a-5b04899fde67.json b/oaitestdata/clarin-oai_dc/SET_1/json/34ff8662-e520-5346-842a-5b04899fde67.json
deleted file mode 100644
index e28ca3f2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/34ff8662-e520-5346-842a-5b04899fde67.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Lao"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1028",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1028"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1028",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1028;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LAC Lao Corpus;Language and Cognition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1028;lao;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI29850%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "34ff8662-e520-5346-842a-5b04899fde67",
-    "notes": [
-        "Language and Cognition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1028"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LAC Lao Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/35028ef6-eb01-5239-9102-2099ad18431d.json b/oaitestdata/clarin-oai_dc/SET_1/json/35028ef6-eb01-5239-9102-2099ad18431d.json
deleted file mode 100644
index 59b04f1f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/35028ef6-eb01-5239-9102-2099ad18431d.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4950",
-    "MetadataAccess": [
-        "oai:ota:oucs:4950"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Darwin, Erasmus, 1731-1802."
-    ],
-    "fulltext": "oai:ota:oucs:4950;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4950.xml;Zoonomia: or, the laws of organic life. ... By Erasmus Darwin, ... [pt.1];Darwin, Erasmus, 1731-1802.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "35028ef6-eb01-5239-9102-2099ad18431d",
-    "oai_identifier": [
-        "oai:ota:oucs:4950"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Zoonomia: or, the laws of organic life. ... By Erasmus Darwin, ... [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4950.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/354d4e1e-5891-5e5d-9557-e27f5e5b9cb9.json b/oaitestdata/clarin-oai_dc/SET_1/json/354d4e1e-5891-5e5d-9557-e27f5e5b9cb9.json
deleted file mode 100644
index 261059be..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/354d4e1e-5891-5e5d-9557-e27f5e5b9cb9.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "ZRC SAZU"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian",
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1114",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1114"
-    ],
-    "PID": "http://hdl.handle.net/11356/1114",
-    "PublicationTimestamp": "2006-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2006"
-    ],
-    "Publisher": [
-        "ZRC SAZU"
-    ],
-    "RelatedIdentifier": [
-        "http://www.fran.si/136/maks-pletersnik-slovensko-nemski-slovar/datoteke/Pletersnik_Uvod.pdf",
-        "http://www.srl.si/sql_pdf/SRL_2006_4_29.pdf",
-        "http://www.ff.um.si/dotCMS/detailProduct?categoryInode=8426&inode=8810"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Jazbec, Helena",
-        "Pleter\u0161nik, Maks",
-        "Dobrovoljc, Helena",
-        "Furlan, Metka"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1114;2017-07-01T10:47:43Z;hdl_11356_1023;hdl_11356_1024;Slovenian-German Dictionary of Maks Pleter\u0161nik (1894-1895);Pleter\u0161nik, Maks;Furlan, Metka;Dobrovoljc, Helena;Jazbec, Helena;dictionary;lexicography;historical language;The Slovenian-German Dictionary of Maks Pleter\u0161nik was first published in 1894-1895. It contains 103,185 dictionary entries. Beside standard and dialect lexis of the 19th century Slovenian language it includes also an important part of lexis from 16th onwards. The dictionary is based on lexical material collected by Oroslav Caf, Fran Miklo\u0161i\u010d, Fran Levstik, Fran Erjavec etc., and is enriched with the lexis of literature, newspapers, specialized literature and dictionaries. The dictionary was re-published by ZRC SAZU in 2006 and this publication is the source of the XML encoded version of this repository entry.\r\n\r\nThis dictionary was published as a printed book:\r\n\u2022 Original edition: Pleter\u0161nik, Maks. Slovensko-nem\u0161ki slovar. V Ljubljani : Knezo\u0161kofijstvo, 1894.\r\n\u2022 Re-published edition: Pleter\u0161nik, Maks. Slovensko-nem\u0161ki slovar. Transliterirana izd. Ljubljana : Zalo\u017eba ZRC, ZRC SAZU, 2006. ISBN 961-6568-31-0.;2006;lexicalConceptualResource;http://hdl.handle.net/11356/1114;slv;deu;http://www.fran.si/136/maks-pletersnik-slovensko-nemski-slovar/datoteke/Pletersnik_Uvod.pdf;http://www.srl.si/sql_pdf/SRL_2006_4_29.pdf;http://www.ff.um.si/dotCMS/detailProduct?categoryInode=8426&inode=8810;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;ZRC SAZU;http://www.fran.si/136/maks-pletersnik-slovensko-nemski-slovar",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "354d4e1e-5891-5e5d-9557-e27f5e5b9cb9",
-    "notes": [
-        "The Slovenian-German Dictionary of Maks Pleter\u0161nik was first published in 1894-1895. It contains 103,185 dictionary entries. Beside standard and dialect lexis of the 19th century Slovenian language it includes also an important part of lexis from 16th onwards. The dictionary is based on lexical material collected by Oroslav Caf, Fran Miklo\u0161i\u010d, Fran Levstik, Fran Erjavec etc., and is enriched with the lexis of literature, newspapers, specialized literature and dictionaries. The dictionary was re-published by ZRC SAZU in 2006 and this publication is the source of the XML encoded version of this repository entry.\r\n\r\nThis dictionary was published as a printed book:\r\n\u2022 Original edition: Pleter\u0161nik, Maks. Slovensko-nem\u0161ki slovar. V Ljubljani : Knezo\u0161kofijstvo, 1894.\r\n\u2022 Re-published edition: Pleter\u0161nik, Maks. Slovensko-nem\u0161ki slovar. Transliterirana izd. Ljubljana : Zalo\u017eba ZRC, ZRC SAZU, 2006. ISBN 961-6568-31-0."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1114"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "dictionary"
-        },
-        {
-            "name": "lexicography"
-        },
-        {
-            "name": "historical language"
-        }
-    ],
-    "title": [
-        "Slovenian-German Dictionary of Maks Pleter\u0161nik (1894-1895)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/35540440-d1b0-5c70-b1b2-e9cea1c98ee6.json b/oaitestdata/clarin-oai_dc/SET_1/json/35540440-d1b0-5c70-b1b2-e9cea1c98ee6.json
deleted file mode 100644
index 1f2f61b1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/35540440-d1b0-5c70-b1b2-e9cea1c98ee6.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Universit\u00e0 di Parma"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/vnd.openxmlformats-officedocument.presentationml.presentation",
-        "text/plain; charset=utf-8",
-        "application/pdf",
-        "downloadable_files_count: 2"
-    ],
-    "Language": [
-        "Italian",
-        "English",
-        "Ancient Greek (to 1453)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/OPEN-83",
-    "MetadataAccess": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/OPEN-83"
-    ],
-    "PID": "http://hdl.handle.net/20.500.11752/OPEN-83",
-    "PublicationTimestamp": "2017-10-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Universit\u00e0 di Parma"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Stefanini, Alberto",
-        "Monachini, Monica",
-        "Nicolosi, Anika"
-    ],
-    "fulltext": "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/OPEN-83;2018-07-23T09:13:44Z;hdl_000-c0-111_39;hdl_000-c0-111_43;HT-Archilochus (Hyper-Text Archilochus);Nicolosi, Anika;Monachini, Monica;Stefanini, Alberto;Ancient Greek;Digital Edition;This data is a sample from a collection of fragments of a Greek poet, Archilochus, which is based on text, translations and commentary edited by Anika Nicolosi (2013). This data is being produced in the context of a project that overviews the requirements for a scholarly digital edition of Archilochus.  This data includes a few fragments of the Greek poet which are used to build and test a prototype (HT-Archilochus), in view of developing a full digital edition (DEA-Digital Edition and Archilochus). \r\n\r\nThis sample responds to the outcomes of a survey with several practitioners of Digital Classics and provides the learner with a set of resources and tools that ease a critical assessment of ancient text.\r\n\r\nThe survey (Current practice with Digital Classics tools: use practice of digital resources and tools for studies on Digital Classics), supplementary to a master degree thesis discussed at the University of Parma, was performed from May to September 2016 on a sample of Italian digital humanists with focus of interest on ancient Greek philology and it is now available on-line,and still open for participation, at http://www.clarin-it.it/it/content/sondaggio-current-practice-digital-classics-tools.\r\n\r\nThe survey is in line with the principles behind the recent user engagement strategy developed by CLARIN-ERIC (www.clarin.eu) and constitutes one of the national efforts undertaken by CLARIN-IT to contribute to the wider impact of CLARIN on Digital Classicists. News about the research\u2019s results was given at Clarin Conference 2107 (18-21 September 2017, Budapest): A Survey on the Use and the Needs for Digital Resources and related Tools by Ancient Greek Scholars In Italy (Poster)\r\n\r\nWarning: at this moment to better display the sample please use the font Hellenica;2017-10-01;corpus;http://hdl.handle.net/20.500.11752/OPEN-83;ita;eng;grc;Creative Commons - Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0);http://creativecommons.org/licenses/by-nc-nd/4.0/;PUB;application/vnd.openxmlformats-officedocument.presentationml.presentation;application/pdf;text/plain; charset=utf-8;downloadable_files_count: 2;Universit\u00e0 di Parma;http://unipr.academia.edu/AnikaNicolosi",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "35540440-d1b0-5c70-b1b2-e9cea1c98ee6",
-    "notes": [
-        "This data is a sample from a collection of fragments of a Greek poet, Archilochus, which is based on text, translations and commentary edited by Anika Nicolosi (2013). This data is being produced in the context of a project that overviews the requirements for a scholarly digital edition of Archilochus.  This data includes a few fragments of the Greek poet which are used to build and test a prototype (HT-Archilochus), in view of developing a full digital edition (DEA-Digital Edition and Archilochus). \r\n\r\nThis sample responds to the outcomes of a survey with several practitioners of Digital Classics and provides the learner with a set of resources and tools that ease a critical assessment of ancient text.\r\n\r\nThe survey (Current practice with Digital Classics tools: use practice of digital resources and tools for studies on Digital Classics), supplementary to a master degree thesis discussed at the University of Parma, was performed from May to September 2016 on a sample of Italian digital humanists with focus of interest on ancient Greek philology and it is now available on-line,and still open for participation, at http://www.clarin-it.it/it/content/sondaggio-current-practice-digital-classics-tools.\r\n\r\nThe survey is in line with the principles behind the recent user engagement strategy developed by CLARIN-ERIC (www.clarin.eu) and constitutes one of the national efforts undertaken by CLARIN-IT to contribute to the wider impact of CLARIN on Digital Classicists. News about the research\u2019s results was given at Clarin Conference 2107 (18-21 September 2017, Budapest): A Survey on the Use and the Needs for Digital Resources and related Tools by Ancient Greek Scholars In Italy (Poster)\r\n\r\nWarning: at this moment to better display the sample please use the font Hellenica"
-    ],
-    "oai_identifier": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/OPEN-83"
-    ],
-    "oai_set": [
-        "hdl_000-c0-111_39",
-        "hdl_000-c0-111_43"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Ancient Greek"
-        },
-        {
-            "name": "Digital Edition"
-        }
-    ],
-    "title": [
-        "HT-Archilochus (Hyper-Text Archilochus)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/356014c9-7ba2-5a85-9cec-3ccc72bba762.json b/oaitestdata/clarin-oai_dc/SET_1/json/356014c9-7ba2-5a85-9cec-3ccc72bba762.json
deleted file mode 100644
index 507c7416..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/356014c9-7ba2-5a85-9cec-3ccc72bba762.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "The National Library of Sweden"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/89",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/89"
-    ],
-    "PID": "http://hdl.handle.net/10794/89",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "The National Library of Sweden"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/89;2017-10-25T14:38:21Z;hdl_10794_1;hdl_10794_2;Blekingsposten 1860's (2015-04-08);Blekingsposten 1860-talet (2015-04-08);n/a, n/a;Swedish;News;A corpus with texts from Blekingeposten 1860\u20131869.;En korpus med texter fr\u00e5n Blekingeposten p\u00e5 1860-talet (1860\u20131869).;2015-04-08;corpus;http://hdl.handle.net/10794/89;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;The National Library of Sweden;https://spraakbanken.gu.se/swe/resurs/kubhist-blekingsposten-1860",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "356014c9-7ba2-5a85-9cec-3ccc72bba762",
-    "notes": [
-        "A corpus with texts from Blekingeposten 1860\u20131869.",
-        "En korpus med texter fr\u00e5n Blekingeposten p\u00e5 1860-talet (1860\u20131869)."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/89"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "News"
-        }
-    ],
-    "title": [
-        "Blekingsposten 1860's (2015-04-08)",
-        "Blekingsposten 1860-talet (2015-04-08)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/356c2976-25cd-5168-a136-14679e5c7fb9.json b/oaitestdata/clarin-oai_dc/SET_1/json/356c2976-25cd-5168-a136-14679e5c7fb9.json
deleted file mode 100644
index 7b615e26..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/356c2976-25cd-5168-a136-14679e5c7fb9.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "application/pdf",
-        "application/octet-stream"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/291",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/291"
-    ],
-    "PID": "http://hdl.handle.net/11321/291",
-    "PublicationTimestamp": "2016-04-25T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "Marci\u0144czuk, Micha\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/291;2016-06-07T04:49:47Z;hdl_11321_3;hdl_11321_4;SpatialPL;Marci\u0144czuk, Micha\u0142;spatial expression recognition;information extraction;patial role labelling;SpatialPl is a tool for automatic recognition of spatial expressions in Polish texts;2016-04-25;toolService;http://hdl.handle.net/11321/291;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;application/pdf;downloadable_files_count: 2;Wroc\u0142aw University of Technology;http://nlp.pwr.wroc.pl/narzedzia-i-zasoby/narzedzia/spatialpl",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "356c2976-25cd-5168-a136-14679e5c7fb9",
-    "notes": [
-        "SpatialPl is a tool for automatic recognition of spatial expressions in Polish texts"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/291"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "spatial expression recognition"
-        },
-        {
-            "name": "information extraction"
-        },
-        {
-            "name": "patial role labelling"
-        }
-    ],
-    "title": [
-        "SpatialPL"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/357fc9ca-bb55-5163-b91a-dcfdd125ad09.json b/oaitestdata/clarin-oai_dc/SET_1/json/357fc9ca-bb55-5163-b91a-dcfdd125ad09.json
deleted file mode 100644
index b7e0b295..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/357fc9ca-bb55-5163-b91a-dcfdd125ad09.json
+++ /dev/null
@@ -1,198 +0,0 @@
-{
-    "Contact": [
-        "PARSEME"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 21",
-        "application/pdf",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Bulgarian",
-        "Czech",
-        "German",
-        "Modern Greek (1453-)",
-        "Spanish",
-        "Persian",
-        "French",
-        "Hebrew",
-        "Hungarian",
-        "Italian",
-        "Lithuanian",
-        "Maltese",
-        "Polish",
-        "Portuguese",
-        "Romanian",
-        "Slovenian",
-        "Swedish",
-        "Turkish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2282",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2282"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2282",
-    "PublicationTimestamp": "2017-01-20T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "PARSEME"
-    ],
-    "RelatedIdentifier": [
-        "http://multiword.sourceforge.net/mwe2017/proceedings/MWE201704.pdf",
-        "http://hdl.handle.net/11372/LRT-2842"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "PARSEME Shared Task Data (v. 1.0) Agreement",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-mwe-1.0",
-        "PUB"
-    ],
-    "author": [
-        "De Santis, Anna",
-        "Fabri, Ray",
-        "Raffone, Annalisa",
-        "Simk\u00f3, Katalin",
-        "Ure\u0161ov\u00e1, Zdenka",
-        "Tanti, Marc",
-        "Villavicencio, Aline",
-        "Busuttil, Jael",
-        "Czerepowicka, Monika",
-        "Gantar, Polona",
-        "Fotopoulou, Aggeliki",
-        "Hn\u00e1tkov\u00e1, Milena",
-        "Elyovich, Hevi",
-        "Bonnici, Janice",
-        "Boz, Mert",
-        "Cap, Fabienne",
-        "Boizou, Loic",
-        "Oakes, Michael",
-        "Cordeiro, Silvio Ricardo",
-        "Gatt, Anabelle",
-        "QasemiZadeh, Behrang",
-        "Bumbulien\u0117, Ieva",
-        "Krek, Simon",
-        "Stefanova, Valentina",
-        "Galea, Luke",
-        "Spagnol, Michael",
-        "Mart\u00ednez Alonso, H\u00e9ctor",
-        "Malka, Ruth",
-        "Lynn, Teresa",
-        "Din\u00e7, Tutkum",
-        "van der Plas, Lonneke",
-        "Liebeskind, Chaya",
-        "Antoine, Jean-Yves",
-        "Rizea, Monica-Mihaela",
-        "Kov\u00e1cs, Vikt\u00f3ria",
-        "Ionescu, Mihaela",
-        "Ramisch, Renata",
-        "Herrero, Carlos",
-        "Nivre, Joakim",
-        "Todorova, Maria",
-        "Rimkut\u0117, Erika",
-        "Findlay, Jamie",
-        "Azzopardi, Kirsty",
-        "Aceta, Cristina",
-        "Cherchi, Manuela",
-        "Doucet, Antoine",
-        "Muscat, Amanda",
-        "Caruso, Valeria",
-        "Farrugia, Alison",
-        "Pasquer, Caroline",
-        "Barbu Mititelu, Verginica",
-        "Parmentier, Yannick",
-        "Sulubacak, Umut",
-        "Miral, Ay\u015fenur",
-        "Stoyanova, Ivelina",
-        "Vincze, Veronika",
-        "Parra Escart\u00edn, Carla",
-        "Pia di Buono, Maria",
-        "Eryi\u011fit, G\u00fcl\u015fen",
-        "Monti, Johanna",
-        "Gatt, Albert",
-        "McCrae, John",
-        "El Maarouf, Ismail",
-        "Savary, Agata",
-        "Ha-Cohen Kerner, Yaakov",
-        "Onofrei, Mihaela",
-        "Klyueva, Natalia",
-        "Priego Sanchez, Belem",
-        "Sangati, Federico",
-        "Leseva, Svetlozara",
-        "Koeva, Svetla",
-        "Zilio, Leonardo",
-        "Jagfeld, Glorianna",
-        "Stymne, Sara",
-        "Attard, Greta",
-        "Louisou, Sevi",
-        "Aduriz, Itziar",
-        "de Medeiros Caseli, Helena",
-        "Constant, Matthieu",
-        "Candito, Marie",
-        "Giouli, Voula",
-        "Adal\u0131, K\u00fcbra",
-        "Tabone, Nicole",
-        "Dimitrova, Tsvetana",
-        "Bej\u010dek, Eduard",
-        "Kuzman, Taja",
-        "Ramisch, Carlos",
-        "Foufi, Vassiliki",
-        "Kovalevskait\u0117, Jolanta",
-        "I\u00f1urrieta, Uxoa",
-        "Galea, Sara Anne"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2282;2018-08-16T11:45:05Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Annotated corpora and tools of the PARSEME Shared Task on Automatic Identification of Verbal Multiword Expressions (edition 1.0);Savary, Agata;Ramisch, Carlos;Cordeiro, Silvio Ricardo;Sangati, Federico;Vincze, Veronika;QasemiZadeh, Behrang;Candito, Marie;Cap, Fabienne;Giouli, Voula;Stoyanova, Ivelina;Doucet, Antoine;Adal\u0131, K\u00fcbra;Barbu Mititelu, Verginica;Bej\u010dek, Eduard;El Maarouf, Ismail;Eryi\u011fit, G\u00fcl\u015fen;Galea, Luke;Ha-Cohen Kerner, Yaakov;Liebeskind, Chaya;Monti, Johanna;Parra Escart\u00edn, Carla;Kovalevskait\u0117, Jolanta;Krek, Simon;van der Plas, Lonneke;Aceta, Cristina;Aduriz, Itziar;Antoine, Jean-Yves;Attard, Greta;Azzopardi, Kirsty;Boizou, Loic;Bonnici, Janice;Boz, Mert;Bumbulien\u0117, Ieva;Busuttil, Jael;Caruso, Valeria;Cherchi, Manuela;Constant, Matthieu;Czerepowicka, Monika;De Santis, Anna;Dimitrova, Tsvetana;Din\u00e7, Tutkum;Elyovich, Hevi;Fabri, Ray;Farrugia, Alison;Findlay, Jamie;Fotopoulou, Aggeliki;Foufi, Vassiliki;Galea, Sara Anne;Gantar, Polona;Gatt, Albert;Gatt, Anabelle;Herrero, Carlos;I\u00f1urrieta, Uxoa;Jagfeld, Glorianna;Hn\u00e1tkov\u00e1, Milena;Ionescu, Mihaela;Klyueva, Natalia;Koeva, Svetla;Kov\u00e1cs, Vikt\u00f3ria;Kuzman, Taja;Leseva, Svetlozara;Louisou, Sevi;Lynn, Teresa;Malka, Ruth;Mart\u00ednez Alonso, H\u00e9ctor;McCrae, John;de Medeiros Caseli, Helena;Miral, Ay\u015fenur;Muscat, Amanda;Nivre, Joakim;Oakes, Michael;Onofrei, Mihaela;Parmentier, Yannick;Pasquer, Caroline;Pia di Buono, Maria;Priego Sanchez, Belem;Raffone, Annalisa;Ramisch, Renata;Rimkut\u0117, Erika;Rizea, Monica-Mihaela;Simk\u00f3, Katalin;Spagnol, Michael;Stefanova, Valentina;Stymne, Sara;Sulubacak, Umut;Tabone, Nicole;Tanti, Marc;Todorova, Maria;Ure\u0161ov\u00e1, Zdenka;Villavicencio, Aline;Zilio, Leonardo;Multiword expressions;verbal multiword expressions;idioms;light-verb constructions;verb-particle constructions;inherently reflexive verbs;The PARSEME shared task aims at identifying verbal MWEs in running texts. Verbal MWEs include idioms (let the cat out of the bag), light verb constructions (make a decision), verb-particle constructions (give up), and inherently reflexive verbs (se suicider 'to suicide' in French). VMWEs were annotated according to the universal guidelines in 18 languages. The corpora are provided in the parsemetsv format, inspired by the CONLL-U format.\r\n \r\nFor most languages, paired files in the CONLL-U format - not necessarily using UD tagsets - containing parts of speech, lemmas, morphological features and/or syntactic dependencies are also provided. Depending on the language, the information comes from treebanks (e.g., Universal Dependencies) or from automatic parsers trained on treebanks (e.g., UDPipe).\r\n \r\nThis item contains training and test data, tools and the universal guidelines file.;2017-01-20;corpus;http://hdl.handle.net/11372/LRT-2282;bul;ces;deu;ell;spa;fas;fra;heb;hun;ita;lit;mlt;pol;por;ron;slv;swe;tur;http://multiword.sourceforge.net/mwe2017/proceedings/MWE201704.pdf;http://hdl.handle.net/11372/LRT-2842;PARSEME Shared Task Data (v. 1.0) Agreement;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-mwe-1.0;PUB;application/octet-stream;application/pdf;application/pdf;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 21;PARSEME;http://multiword.sf.net/sharedtask2017",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "357fc9ca-bb55-5163-b91a-dcfdd125ad09",
-    "notes": [
-        "The PARSEME shared task aims at identifying verbal MWEs in running texts. Verbal MWEs include idioms (let the cat out of the bag), light verb constructions (make a decision), verb-particle constructions (give up), and inherently reflexive verbs (se suicider 'to suicide' in French). VMWEs were annotated according to the universal guidelines in 18 languages. The corpora are provided in the parsemetsv format, inspired by the CONLL-U format.\r\n \r\nFor most languages, paired files in the CONLL-U format - not necessarily using UD tagsets - containing parts of speech, lemmas, morphological features and/or syntactic dependencies are also provided. Depending on the language, the information comes from treebanks (e.g., Universal Dependencies) or from automatic parsers trained on treebanks (e.g., UDPipe).\r\n \r\nThis item contains training and test data, tools and the universal guidelines file."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2282"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Multiword expressions"
-        },
-        {
-            "name": "verbal multiword expressions"
-        },
-        {
-            "name": "idioms"
-        },
-        {
-            "name": "light-verb constructions"
-        },
-        {
-            "name": "verb-particle constructions"
-        },
-        {
-            "name": "inherently reflexive verbs"
-        }
-    ],
-    "title": [
-        "Annotated corpora and tools of the PARSEME Shared Task on Automatic Identification of Verbal Multiword Expressions (edition 1.0)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/35c91c7d-3dc3-5adc-af31-048c8f90c46a.json b/oaitestdata/clarin-oai_dc/SET_1/json/35c91c7d-3dc3-5adc-af31-048c8f90c46a.json
deleted file mode 100644
index 2054a9a4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/35c91c7d-3dc3-5adc-af31-048c8f90c46a.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "University of Zagreb, Faculty of Humanities and Social Sciences"
-    ],
-    "Contributor": [
-        "Tadi\u0107, Marko"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Croatian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-234",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-234"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-234",
-    "PublicationTimestamp": "1996-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1996"
-    ],
-    "Publisher": [
-        "University of Zagreb, Faculty of Humanities and Social Sciences"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Croatia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-234;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;One-million Corpus of Croatian Literary Language;Tadi\u0107, Marko;written; reference corpus; general; diachornic; monolingual;1996;corpus;http://hdl.handle.net/11372/LRT-234;hrv;downloadable_files_count: 0;Croatia;University of Zagreb, Faculty of Humanities and Social Sciences;http://hnk.ffzg.hr",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "35c91c7d-3dc3-5adc-af31-048c8f90c46a",
-    "notes": [
-        "written; reference corpus; general; diachornic; monolingual"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-234"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "One-million Corpus of Croatian Literary Language"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/35e7cb29-0409-5a92-b7fb-f92bb91d173d.json b/oaitestdata/clarin-oai_dc/SET_1/json/35e7cb29-0409-5a92-b7fb-f92bb91d173d.json
deleted file mode 100644
index 8fb215f6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/35e7cb29-0409-5a92-b7fb-f92bb91d173d.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 220 KB)"
-    ],
-    "Language": [
-        "English",
-        "Latin",
-        "French"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1886",
-    "MetadataAccess": [
-        "oai:ota:oucs:1886"
-    ],
-    "PublicationTimestamp": "1681-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1681"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Marvell, Andrew, 1621-1678"
-    ],
-    "fulltext": "oai:ota:oucs:1886;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/1886.xml;Miscellaneous poems / Andrew Marvell;Marvell, Andrew, 1621-1678;1681;text_and_corpus_linguistics;English poetry -- Early modern, 1500-1700;eng;lat;fra;Oxford Text Archive, University of Oxford;Triggs, Jeffery;text/sgml;(1 file : ca. 220 KB);Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "35e7cb29-0409-5a92-b7fb-f92bb91d173d",
-    "oai_identifier": [
-        "oai:ota:oucs:1886"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English poetry -- Early modern"
-        }
-    ],
-    "title": [
-        "Miscellaneous poems / Andrew Marvell"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1886.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3602e1c5-74ef-5dbc-b467-65c39d882317.json b/oaitestdata/clarin-oai_dc/SET_1/json/3602e1c5-74ef-5dbc-b467-65c39d882317.json
deleted file mode 100644
index c0158185..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3602e1c5-74ef-5dbc-b467-65c39d882317.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1179",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1179"
-    ],
-    "PID": "http://hdl.handle.net/11356/1179",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "http://www.informatica.si/index.php/informatica/article/view/985"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Krek, Simon",
-        "Erjavec, Toma\u017e",
-        "Ljube\u0161i\u0107, Nikola",
-        "Dobrovoljc, Kaja"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1179;2018-02-14T11:37:40Z;hdl_11356_1023;hdl_11356_1024;Automatically constructed multiword lexicon slMWELex v0.5;Ljube\u0161i\u0107, Nikola;Krek, Simon;Dobrovoljc, Kaja;Erjavec, Toma\u017e;multiword expressions;collocations;The slMWELex lexicon is an automatically constructed lexicon of Slovene multiword expression candidates (mostly collocations) from the parsed KRES corpus by using the DepMWEx [depmueks] tool (https://github.com/nljubesi/depmwex). The tool extracts MWE candidates from parse trees by applying tree patterns and ranking by occurrence statistics.;2015;lexicalConceptualResource;http://hdl.handle.net/11356/1179;slv;http://www.informatica.si/index.php/informatica/article/view/985;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Jo\u017eef Stefan Institute;http://nlp.ffzg.hr/resources/lexicons/slmwelex/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3602e1c5-74ef-5dbc-b467-65c39d882317",
-    "notes": [
-        "The slMWELex lexicon is an automatically constructed lexicon of Slovene multiword expression candidates (mostly collocations) from the parsed KRES corpus by using the DepMWEx [depmueks] tool (https://github.com/nljubesi/depmwex). The tool extracts MWE candidates from parse trees by applying tree patterns and ranking by occurrence statistics."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1179"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "multiword expressions"
-        },
-        {
-            "name": "collocations"
-        }
-    ],
-    "title": [
-        "Automatically constructed multiword lexicon slMWELex v0.5"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3620fd07-fbf5-5586-80ac-ca00a02f9079.json b/oaitestdata/clarin-oai_dc/SET_1/json/3620fd07-fbf5-5586-80ac-ca00a02f9079.json
deleted file mode 100644
index 327393e9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3620fd07-fbf5-5586-80ac-ca00a02f9079.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "MASt"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/pdf"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/152",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/152"
-    ],
-    "PID": "http://hdl.handle.net/11321/152",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "MASt"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0)",
-        "http://creativecommons.org/licenses/by-nc/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Edward Opali\u0144ski, Opali\u0144ski",
-        "Opali\u0144ski, E."
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/152;2015-04-13T20:20:58Z;hdl_11321_3;hdl_11321_4;Elita W\u0142adzy;Opali\u0144ski, E.;Edward Opali\u0144ski, Opali\u0144ski;o elitach;2015;corpus;http://hdl.handle.net/11321/152;pol;Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0);http://creativecommons.org/licenses/by-nc/3.0/;CC;application/pdf;text/plain; charset=utf-8;downloadable_files_count: 1;MASt",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3620fd07-fbf5-5586-80ac-ca00a02f9079",
-    "notes": [
-        "o elitach"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/152"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Elita W\u0142adzy"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/362e0bb6-7702-590d-83c1-134afb9342e6.json b/oaitestdata/clarin-oai_dc/SET_1/json/362e0bb6-7702-590d-83c1-134afb9342e6.json
deleted file mode 100644
index d0d03b52..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/362e0bb6-7702-590d-83c1-134afb9342e6.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "Contributor": [
-        "Bennett, Dr Paul",
-        "Durrell, Professor Martin"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-882",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-882"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-882",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-882;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;GerManC : A representative historical corpus of German 1650-1800;Durrell, Professor Martin;Bennett, Dr Paul;The ultimate aim of the project is to compile a representative historical corpus of written German for the years 1650-1800. The complete GerManC corpus will contain 2000 word samples from nine genres;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-882;deu;downloadable_files_count: 0;United Kingdom;http://www.llc.manchester.ac.uk/research/projects/germanc/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "362e0bb6-7702-590d-83c1-134afb9342e6",
-    "notes": [
-        "The ultimate aim of the project is to compile a representative historical corpus of written German for the years 1650-1800. The complete GerManC corpus will contain 2000 word samples from nine genres"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-882"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "GerManC : A representative historical corpus of German 1650-1800"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3634c3f0-683f-5809-8e94-e6d07238e89a.json b/oaitestdata/clarin-oai_dc/SET_1/json/3634c3f0-683f-5809-8e94-e6d07238e89a.json
deleted file mode 100644
index 1f443de9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3634c3f0-683f-5809-8e94-e6d07238e89a.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4864",
-    "MetadataAccess": [
-        "oai:ota:oucs:4864"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Donovan, E. (Edward), 1768-1837."
-    ],
-    "fulltext": "oai:ota:oucs:4864;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4864.xml;An epitome of the natural history of the insects of China: comprising figures and descriptions ... By E. Donovan, ...;Donovan, E. (Edward), 1768-1837.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3634c3f0-683f-5809-8e94-e6d07238e89a",
-    "oai_identifier": [
-        "oai:ota:oucs:4864"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An epitome of the natural history of the insects of China: comprising figures and descriptions ... By E. Donovan, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4864.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/36367174-9502-5c7c-97d8-8d3841106b5b.json b/oaitestdata/clarin-oai_dc/SET_1/json/36367174-9502-5c7c-97d8-8d3841106b5b.json
deleted file mode 100644
index 1305d744..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/36367174-9502-5c7c-97d8-8d3841106b5b.json
+++ /dev/null
@@ -1,94 +0,0 @@
-{
-    "Contact": [
-        "Charles University"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 4",
-        "application/pdf",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-000C-2293-0",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-000C-2293-0"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-000C-2293-0",
-    "PublicationTimestamp": "2012-12-12T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Charles University"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u0160\u0165astn\u00fd, Klement",
-        "Jane\u0161, Petr",
-        "\u0160tindlov\u00e1, Barbora",
-        "Hrdli\u010dka, Milan",
-        "Petkevi\u010d, Vladim\u00edr",
-        "Sl\u00e1dek, \u0160imon",
-        "Hrdli\u010dkov\u00e1, Tereza",
-        "Hana, Ji\u0159\u00ed",
-        "Lund\u00e1kov\u00e1, Kate\u0159ina",
-        "Bed\u0159ichov\u00e1, Zuzanna",
-        "Jel\u00ednek, Tom\u00e1\u0161",
-        "\u0160kodov\u00e1, Svatava",
-        "Skoumalov\u00e1, Hana",
-        "\u0160ebesta, Karel",
-        "Rosen, Alexandr"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-000C-2293-0;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;AKCES 4;\u0160ebesta, Karel;Bed\u0159ichov\u00e1, Zuzanna;\u0160tindlov\u00e1, Barbora;Hrdli\u010dka, Milan;Hrdli\u010dkov\u00e1, Tereza;Hana, Ji\u0159\u00ed;Rosen, Alexandr;Petkevi\u010d, Vladim\u00edr;Jel\u00ednek, Tom\u00e1\u0161;\u0160kodov\u00e1, Svatava;Jane\u0161, Petr;Lund\u00e1kov\u00e1, Kate\u0159ina;Skoumalov\u00e1, Hana;\u0160\u0165astn\u00fd, Klement;Sl\u00e1dek, \u0160imon;language of children;Czech language acquisition;adolescents;AKCES;Corpus AKCES 4 includes texts written in czech by youth growing up in locations at risk of social exclusion (AKCES/CLAC - Czech Language Acquisition Corpora);2012-12-12;corpus;http://hdl.handle.net/11858/00-097C-0000-000C-2293-0;ces;Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0);http://creativecommons.org/licenses/by-nc-nd/3.0/;PUB;application/zip;application/pdf;application/pdf;application/pdf;text/plain; charset=utf-8;downloadable_files_count: 4;Charles University;http://utkl.ff.cuni.cz/learncorp/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "36367174-9502-5c7c-97d8-8d3841106b5b",
-    "notes": [
-        "Corpus AKCES 4 includes texts written in czech by youth growing up in locations at risk of social exclusion (AKCES/CLAC - Czech Language Acquisition Corpora)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-000C-2293-0"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "language children"
-        },
-        {
-            "name": "Czech language acquisition"
-        },
-        {
-            "name": "adolescents"
-        },
-        {
-            "name": "AKCES"
-        }
-    ],
-    "title": [
-        "AKCES 4"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/36451f47-b023-54c6-a75d-74e1f6aa7943.json b/oaitestdata/clarin-oai_dc/SET_1/json/36451f47-b023-54c6-a75d-74e1f6aa7943.json
deleted file mode 100644
index e76914ee..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/36451f47-b023-54c6-a75d-74e1f6aa7943.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2747",
-    "MetadataAccess": [
-        "oai:ota:oucs:2747"
-    ],
-    "PublicationTimestamp": "1712-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1712"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2747;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2747.xml;The conduct of the allies;Swift, Jonathan, 1667-1745;1712;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "36451f47-b023-54c6-a75d-74e1f6aa7943",
-    "oai_identifier": [
-        "oai:ota:oucs:2747"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The conduct of the allies"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2747.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/364e8bc2-317a-5a11-92f1-2e47ca6e9a41.json b/oaitestdata/clarin-oai_dc/SET_1/json/364e8bc2-317a-5a11-92f1-2e47ca6e9a41.json
deleted file mode 100644
index c3d25aaf..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/364e8bc2-317a-5a11-92f1-2e47ca6e9a41.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish",
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/63",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/63"
-    ],
-    "PID": "http://hdl.handle.net/10794/63",
-    "PublicationTimestamp": "2015-04-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/63;2017-10-31T12:43:35Z;hdl_10794_1;hdl_10794_2;ASPAC \u2013 Swedish-Dutch (2017-10-16);ASPAC \u2013 svenska-nederl\u00e4ndska (2017-10-16);n/a, n/a;ASPAC;Parallel;Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.;Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat.;2015-04-16;corpus;http://hdl.handle.net/10794/63;swe;nld;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/octet-stream;application/gzip;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/aspacsvnl",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "364e8bc2-317a-5a11-92f1-2e47ca6e9a41",
-    "notes": [
-        "Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.",
-        "Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/63"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ASPAC"
-        },
-        {
-            "name": "Parallel"
-        }
-    ],
-    "title": [
-        "ASPAC \u2013 Swedish-Dutch (2017-10-16)",
-        "ASPAC \u2013 svenska-nederl\u00e4ndska (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3656fa80-3829-5ee2-a0ec-ec3757a13fb8.json b/oaitestdata/clarin-oai_dc/SET_1/json/3656fa80-3829-5ee2-a0ec-ec3757a13fb8.json
deleted file mode 100644
index 726fbc8e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3656fa80-3829-5ee2-a0ec-ec3757a13fb8.json
+++ /dev/null
@@ -1,203 +0,0 @@
-{
-    "Contact": [
-        "PARSEME"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 22",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Bulgarian",
-        "German",
-        "Modern Greek (1453-)",
-        "Spanish",
-        "Persian",
-        "French",
-        "Hebrew",
-        "Hungarian",
-        "Italian",
-        "Lithuanian",
-        "Polish",
-        "Portuguese",
-        "Romanian",
-        "Slovenian",
-        "Turkish",
-        "Hindi",
-        "Basque",
-        "English",
-        "Croatian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2842",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2842"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2842",
-    "PublicationTimestamp": "2018-04-30T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "PARSEME"
-    ],
-    "RelatedIdentifier": [
-        "http://aclweb.org/anthology/W18-4925",
-        "http://hdl.handle.net/11372/LRT-2282"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "PARSEME Shared Task Data (v. 1.1) Agreement",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-mwe-1.1",
-        "PUB"
-    ],
-    "author": [
-        "Raffone, Annalisa",
-        "Pascucci, Antonio",
-        "Simk\u00f3, Katalin",
-        "Gurrutxaga, Antton",
-        "Estarrona, Ainara",
-        "Ehren, Rafael",
-        "Villavicencio, Aline",
-        "Gantar, Polona",
-        "Fotopoulou, Aggeliki",
-        "Elyovich, Hevi",
-        "Somers, Clarissa",
-        "Pasquer, Caroline",
-        "Arhar Holdt, \u0160pela",
-        "Palka-Binkiewicz, Emilia",
-        "Walsh, Abigail",
-        "Boizou, Loic",
-        "Papadelli, Stella",
-        "Kocijan, Kristina",
-        "Erden, Berna",
-        "Cook, Paul",
-        "QasemiZadeh, Behrang",
-        "Krek, Simon",
-        "Stefanova, Valentina",
-        "Kav\u010di\u010d, Teja",
-        "Mart\u00ednez Alonso, H\u00e9ctor",
-        "Blagus, Goranka",
-        "Diab, Mona",
-        "Kov\u00e1cs, Vikt\u00f3ria",
-        "Liebeskind, Chaya",
-        "Antoine, Jean-Yves",
-        "Zilio, Leonardo",
-        "Gonzalez, Itziar",
-        "Shukla, Vishakha",
-        "Vaidya, Ashwini",
-        "\u010cibej, Jaka",
-        "Puri, Vandana",
-        "Ratori, Shraddha",
-        "Ionescu, Mihaela",
-        "Ramisch, Renata",
-        "Urizar, Ruben",
-        "Taslimipoor, Shiva",
-        "Todorova, Maria",
-        "Jazbec, Ivo-Pavao",
-        "Srivastava, Shubham",
-        "Lichte, Timm",
-        "G\u00fcng\u00f6r, Tunga",
-        "Aceta, Cristina",
-        "Caruso, Valeria",
-        "Geeraert, Kristina",
-        "Matas, Ivana",
-        "Barbu Mititelu, Verginica",
-        "Parmentier, Yannick",
-        "Bonial, Claire",
-        "Stoyanova, Ivelina",
-        "Vincze, Veronika",
-        "Parra Escart\u00edn, Carla",
-        "Pia di Buono, Maria",
-        "Monti, Johanna",
-        "McCrae, John",
-        "Riccio, Anna",
-        "Elbadrashiny, Mohamed",
-        "Savary, Agata",
-        "Ha-Cohen Kerner, Yaakov",
-        "Bhatia, Archna",
-        "Onofrei, Mihaela",
-        "Klyueva, Natalia",
-        "Malka, Ruth",
-        "Sangati, Federico",
-        "Leseva, Svetlozara",
-        "van Gompel, Maarten",
-        "Jain, Kanishka",
-        "\u0160najder, Jan",
-        "de Medeiros Caseli, Helena",
-        "Aduriz, Itziar",
-        "Buljan, Maja",
-        "Berk, G\u00f6zde",
-        "Constant, Matthieu",
-        "Ibrahim, Rehab",
-        "Bielinskien\u0117, Agn\u0117",
-        "Candito, Marie",
-        "Cordeiro, Silvio Ricardo",
-        "Giouli, Voula",
-        "Dimitrova, Tsvetana",
-        "Schneider, Nathan",
-        "Kuzman, Taja",
-        "Ramisch, Carlos",
-        "Markantonatou, Stella",
-        "Foufi, Vassiliki",
-        "Theoxari, Natasa",
-        "Ljube\u0161i\u0107, Nikola",
-        "Kovalevskait\u0117, Jolanta",
-        "Hawwari, Abdelati",
-        "I\u00f1urrieta, Uxoa"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2842;2018-08-16T11:45:05Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Annotated corpora and tools of the PARSEME Shared Task on Automatic Identification of Verbal Multiword Expressions (edition 1.1);Ramisch, Carlos;Cordeiro, Silvio Ricardo;Savary, Agata;Vincze, Veronika;Barbu Mititelu, Verginica;Bhatia, Archna;Buljan, Maja;Candito, Marie;Gantar, Polona;Giouli, Voula;G\u00fcng\u00f6r, Tunga;Hawwari, Abdelati;I\u00f1urrieta, Uxoa;Kovalevskait\u0117, Jolanta;Krek, Simon;Lichte, Timm;Liebeskind, Chaya;Monti, Johanna;Parra Escart\u00edn, Carla;QasemiZadeh, Behrang;Ramisch, Renata;Schneider, Nathan;Stoyanova, Ivelina;Vaidya, Ashwini;Walsh, Abigail;Aceta, Cristina;Aduriz, Itziar;Antoine, Jean-Yves;Arhar Holdt, \u0160pela;Berk, G\u00f6zde;Bielinskien\u0117, Agn\u0117;Blagus, Goranka;Boizou, Loic;Bonial, Claire;Caruso, Valeria;\u010cibej, Jaka;Constant, Matthieu;Cook, Paul;Diab, Mona;Dimitrova, Tsvetana;Ehren, Rafael;Elbadrashiny, Mohamed;Elyovich, Hevi;Erden, Berna;Estarrona, Ainara;Fotopoulou, Aggeliki;Foufi, Vassiliki;Geeraert, Kristina;van Gompel, Maarten;Gonzalez, Itziar;Gurrutxaga, Antton;Ha-Cohen Kerner, Yaakov;Ibrahim, Rehab;Ionescu, Mihaela;Jain, Kanishka;Jazbec, Ivo-Pavao;Kav\u010di\u010d, Teja;Klyueva, Natalia;Kocijan, Kristina;Kov\u00e1cs, Vikt\u00f3ria;Kuzman, Taja;Leseva, Svetlozara;Ljube\u0161i\u0107, Nikola;Malka, Ruth;Markantonatou, Stella;Mart\u00ednez Alonso, H\u00e9ctor;Matas, Ivana;McCrae, John;de Medeiros Caseli, Helena;Onofrei, Mihaela;Palka-Binkiewicz, Emilia;Papadelli, Stella;Parmentier, Yannick;Pascucci, Antonio;Pasquer, Caroline;Pia di Buono, Maria;Puri, Vandana;Raffone, Annalisa;Ratori, Shraddha;Riccio, Anna;Sangati, Federico;Shukla, Vishakha;Simk\u00f3, Katalin;\u0160najder, Jan;Somers, Clarissa;Srivastava, Shubham;Stefanova, Valentina;Taslimipoor, Shiva;Theoxari, Natasa;Todorova, Maria;Urizar, Ruben;Villavicencio, Aline;Zilio, Leonardo;Multiword expressions;verbal multiword expressions;light-verb constructions;verb-particle constructions;inherently reflexive verbs;verbal idioms;multi-verb constructions;This multilingual resource contains corpora in which verbal MWEs have been manually annotated. VMWEs include idioms (let the cat out of the bag), light-verb constructions (make a decision), verb-particle constructions (give up), inherently reflexive verbs (help oneself), and multi-verb constructions (make do). VMWEs were annotated according to the universal guidelines in 19 languages. The corpora are provided in the cupt format, inspired by the CONLL-U format. The corpora were used in the 1.1 edition of the PARSEME Shared Task (2018).\r\n \r\nFor most languages, morphological and syntactic information \u00ad\u00ad\u00ad\u00ad\u2013 not necessarily using UD tagsets \u2013 including parts of speech, lemmas, morphological features and/or syntactic dependencies are also provided. Depending on the language, the information comes from treebanks (e.g., Universal Dependencies) or from automatic parsers trained on treebanks (e.g., UDPipe).\r\n \r\nThis item contains training, development and test data, as well as the evaluation tools used in the PARSEME Shared Task 1.1 (2018).\r\n\r\nThe annotation guidelines are available online: http://parsemefr.lif.univ-mrs.fr/parseme-st-guidelines/1.1;2018-04-30;corpus;http://hdl.handle.net/11372/LRT-2842;bul;deu;ell;spa;fas;fra;heb;hun;ita;lit;pol;por;ron;slv;tur;hin;eus;eng;hrv;http://aclweb.org/anthology/W18-4925;http://hdl.handle.net/11372/LRT-2282;PARSEME Shared Task Data (v. 1.1) Agreement;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-mwe-1.1;PUB;application/octet-stream;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 22;PARSEME;http://multiword.sf.net/sharedtask2018",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3656fa80-3829-5ee2-a0ec-ec3757a13fb8",
-    "notes": [
-        "This multilingual resource contains corpora in which verbal MWEs have been manually annotated. VMWEs include idioms (let the cat out of the bag), light-verb constructions (make a decision), verb-particle constructions (give up), inherently reflexive verbs (help oneself), and multi-verb constructions (make do). VMWEs were annotated according to the universal guidelines in 19 languages. The corpora are provided in the cupt format, inspired by the CONLL-U format. The corpora were used in the 1.1 edition of the PARSEME Shared Task (2018).\r\n \r\nFor most languages, morphological and syntactic information \u00ad\u00ad\u00ad\u00ad\u2013 not necessarily using UD tagsets \u2013 including parts of speech, lemmas, morphological features and/or syntactic dependencies are also provided. Depending on the language, the information comes from treebanks (e.g., Universal Dependencies) or from automatic parsers trained on treebanks (e.g., UDPipe).\r\n \r\nThis item contains training, development and test data, as well as the evaluation tools used in the PARSEME Shared Task 1.1 (2018).\r\n\r\nThe annotation guidelines are available online: http://parsemefr.lif.univ-mrs.fr/parseme-st-guidelines/1.1"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2842"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Multiword expressions"
-        },
-        {
-            "name": "verbal multiword expressions"
-        },
-        {
-            "name": "light-verb constructions"
-        },
-        {
-            "name": "verb-particle constructions"
-        },
-        {
-            "name": "inherently reflexive verbs"
-        },
-        {
-            "name": "verbal idioms"
-        },
-        {
-            "name": "multi-verb constructions"
-        }
-    ],
-    "title": [
-        "Annotated corpora and tools of the PARSEME Shared Task on Automatic Identification of Verbal Multiword Expressions (edition 1.1)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/36578a40-36b6-5f2e-b0bc-4cfe810a6f13.json b/oaitestdata/clarin-oai_dc/SET_1/json/36578a40-36b6-5f2e-b0bc-4cfe810a6f13.json
deleted file mode 100644
index 1fc4ac31..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/36578a40-36b6-5f2e-b0bc-4cfe810a6f13.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Slovenian",
-        "Croatian",
-        "Serbian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1145",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1145"
-    ],
-    "PID": "http://hdl.handle.net/11356/1145",
-    "PublicationTimestamp": "2017-09-12T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "http://www.lrec-conf.org/proceedings/lrec2016/summaries/811.html"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Erjavec, Toma\u017e",
-        "Perov\u0161ek, Matic",
-        "Ljube\u0161i\u0107, Nikola"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1145;2019-02-23T17:35:01Z;hdl_11356_1023;hdl_11356_1077;ReLDI tag+lemma+parse web service for WebLicht;Ljube\u0161i\u0107, Nikola;Perov\u0161ek, Matic;Erjavec, Toma\u017e;tagging;lemmatisation;parsing;WebLicht (https://weblicht.sfs.uni-tuebingen.de/) registry entry for webservice comprising tokenisation, PoS tagging, lemmatisation and dependency parsing. \r\n\r\nTool source files are available under https://github.com/clarinsi;2017-09-12;toolService;http://hdl.handle.net/11356/1145;slv;hrv;srp;http://www.lrec-conf.org/proceedings/lrec2016/summaries/811.html;application/octet-stream;downloadable_files_count: 0;Jo\u017eef Stefan Institute;https://github.com/clarinsi",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "36578a40-36b6-5f2e-b0bc-4cfe810a6f13",
-    "notes": [
-        "WebLicht (https://weblicht.sfs.uni-tuebingen.de/) registry entry for webservice comprising tokenisation, PoS tagging, lemmatisation and dependency parsing. \r\n\r\nTool source files are available under https://github.com/clarinsi"
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1145"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1077"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "lemmatisation"
-        },
-        {
-            "name": "parsing"
-        }
-    ],
-    "title": [
-        "ReLDI tag+lemma+parse web service for WebLicht"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/36745379-696f-5ea0-9510-08ddcc84ddcd.json b/oaitestdata/clarin-oai_dc/SET_1/json/36745379-696f-5ea0-9510-08ddcc84ddcd.json
deleted file mode 100644
index 43c2c08a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/36745379-696f-5ea0-9510-08ddcc84ddcd.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3059",
-    "MetadataAccess": [
-        "oai:ota:oucs:3059"
-    ],
-    "PublicationTimestamp": "1916-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1916"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Burroughs, Edgar Rice, 1875-1950"
-    ],
-    "fulltext": "oai:ota:oucs:3059;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3059.xml;The Beasts of Tarzan;Burroughs, Edgar Rice, 1875-1950;not after: 1916;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "36745379-696f-5ea0-9510-08ddcc84ddcd",
-    "oai_identifier": [
-        "oai:ota:oucs:3059"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The Beasts of Tarzan"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3059.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3682d64d-992c-54f4-9962-be90184f12d3.json b/oaitestdata/clarin-oai_dc/SET_1/json/3682d64d-992c-54f4-9962-be90184f12d3.json
deleted file mode 100644
index f8d6aa57..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3682d64d-992c-54f4-9962-be90184f12d3.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Institut f\u00fcr Phonetik und Sprachverarbeitung, M\u00fcnchen"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-333",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-333"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-333",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut f\u00fcr Phonetik und Sprachverarbeitung, M\u00fcnchen"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-333;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;WikiSpeech;WikiSpeech is a content management system for the web-based creation of speech databases for the development of spoken language technology and basic research. Its main features are full support for the typical recording, annotation and project administration workflow, easy editing of the speech content, plus a fully localizable user interface. For the creation of a new speech database, it is only necessary to open a new project within WikiSpeech, provide a link to any static project information pages and upload the prompt material to be presented to the speakers. Recordings and annotation are performed via the WWW in a platform independent manner on any Java compatible computer. WikiSpeech currently has been localized to four languages: German, English, Romanian and Russian.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-333;downloadable_files_count: 0;Germany;Institut f\u00fcr Phonetik und Sprachverarbeitung, M\u00fcnchen;http://webapp.phonetik.uni-muenchen.de/wikispeech/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3682d64d-992c-54f4-9962-be90184f12d3",
-    "notes": [
-        "WikiSpeech is a content management system for the web-based creation of speech databases for the development of spoken language technology and basic research. Its main features are full support for the typical recording, annotation and project administration workflow, easy editing of the speech content, plus a fully localizable user interface. For the creation of a new speech database, it is only necessary to open a new project within WikiSpeech, provide a link to any static project information pages and upload the prompt material to be presented to the speakers. Recordings and annotation are performed via the WWW in a platform independent manner on any Java compatible computer. WikiSpeech currently has been localized to four languages: German, English, Romanian and Russian."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-333"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "WikiSpeech"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/368f06af-d64f-56f5-b489-a7730c4fa76b.json b/oaitestdata/clarin-oai_dc/SET_1/json/368f06af-d64f-56f5-b489-a7730c4fa76b.json
deleted file mode 100644
index 72599a5e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/368f06af-d64f-56f5-b489-a7730c4fa76b.json
+++ /dev/null
@@ -1,101 +0,0 @@
-{
-    "Contact": [
-        "Universit\u00e4t des Saarlandes"
-    ],
-    "Contributor": [
-        "Ekaterina Lapshinova-Koltunski",
-        "Prof. Erich Steiner",
-        "Katrin Menzel",
-        "Kerstin Kunz",
-        "Marilisa Amoia",
-        "Jose Manuel Martinez Martinez"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml"
-    ],
-    "Language": [
-        "German",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:gecco",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:gecco"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CF7-A",
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Universit\u00e4t des Saarlandes"
-    ],
-    "RelatedIdentifier": [
-        "Lapshinova-Koltunski, E., K. Kunz and M. Amoia (2012). Compiling a Multilingual Corpus. In Heliana Mello, Massimo Pettorino and Tommaso Raso (eds). Proceedings of the VIIth GSCP-2012 International Conference: Speech and Corpora. Firenze: Firenze University Press. pp. 29-34.",
-        "Lapshinova-Koltunski, E. and K. Kunz (2014). Annotating Cohesion for Multillingual Analysis. In Proceedings of the 10th Joint ACL - ISO Workshop on Interoperable Semantic Annotation, Reykjavik, May 26, 2014",
-        "Menzel, Katrin (2014): Guidelines for the manual annotation of ellipses, DFG-Projektbericht.",
-        "Further publications: http://www.gecco.uni-saarland.de/GECCo/Publikationen.html"
-    ],
-    "ResourceType": [
-        "Collection"
-    ],
-    "Rights": [
-        "Copyrighted"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "GECCo Team, LS Steiner"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:gecco;2015-02-27T14:39:45Z;GECCo;GECCo Team, LS Steiner;corpus linguistics;linguistics;translation;spoken language;cohesion;language contrasts;discourse phenomena;offers a continuum of different text types (registers) from written to spoken discourse. More precisely, it includes English and German texts of 14 registers, eight of which represent written discourse and include fictional texts (FICTION), political essays (ESSAY), instruction manuals (INSTR), popular-scientific texts (POPSCI), letters to shareholders (SHARE), prepared political speeches (SPEECH), tourism leaflets (TOU) and corporate websites (WEB). This part was imported from the existing corpus CroCo described in (Hansen-Schirra et al., 2013). The written texts are saved in two subcorpora according to the language: English written texts (EO), German written texts\n(GO). The further registers are of spoken discourse and include recorded and transcribed interviews and academic speeches, see (Lapshinova-Koltunski et al., 2012).\nThe spoken texts are also stored in two further subcorpora classified according to the language of origin: English spoken texts (EO-SPOKEN) and German spoken texts (GO-SPOKEN).\nThe whole number of words contained in the corpus comprise ca. 1,4 Mio. The corpus is pre-annotated on several levels, which include information on tokens, lemmas, morpho-syntactic features (e.g. case, number, etc.), parts-of-speech, pharse chunks and their grammatical functions, as well as and sentence boundaries. The annotation of the written part was partly imported from CroCo, whereas for the spoken part, we use Stanford POS Tagger (Toutanova et al., 2003) and the Stanford Parser (Klein and Manning, 2003). \nThis corpus is also annotated for the information on cohesion (devices and relations), including coreference, conjunctive relations, substitution, ellipsis and lexical cohesion. The semi-automatic procedures were described in lapshinova and Kunz (2014). The annotation of ellipsis is manual and the scheme is described in Menzel (2014). The corpus is encoded in the CWB format (CWB, 2010) and can be queried with Corpus Query Processor (CQP) (Evert, 2005).;GECCo ist ein bilinguales Korpus (der Name ist vom Projekttitel 'German-English Contrasts in Cohesion' abgeleitet), das insgesamt ca. 1,44 Millionen Tokens enth\u00e4lt und sowohl parallele als auch vergleichbare Subkorpora f\u00fcr Englisch und Deutsch umfasst. GECCo beinhaltet gegenw\u00e4rtig 12 Register, zu denen sowohl gesprochensprachliche als auch geschriebene Textsorten geh\u00f6ren: ESSAY, FICTION, INSTR, POPSCI, SHARE, SPEECH, TOU, WEB, ACADEMIC, FORUM, INTERVIEW, TALKSHOW, MEDCONSULT, SERMON (je ca. 30.000 Tokens pro Register im jeweiligen Subkorpus). Die Texte der geschriebenen Register sind aus dem CroCo-Korpus \u00fcbernommen worden, vgl. Hansen-Schirra et al. (2012). Register gesprochener Sprache wurden im Rahmen des GECCo-Projekts gesammelt und annotiert. Probleme der Korpuskompilierung, Zusammenstellung und Annotation dieser Register wurden in Lapshinova et al. (2012) beschrieben. Beschaffung des gesprochensprachlichen Materials ist kompliziert, weil es viel manuellen Aufwand (Transkription) mit sich bringt. Zu beachten ist dabei, dass das Sprachmaterial in beiden Sprachen gesammelt wird und vergleichbar sein soll. Aus diesem Grund ist der geschriebene Teil von GECCo bisher gr\u00f6\u00dfer als\nder gesprochene. Das Korpus ist auf verschiedenen Ebenen annotiert und enth\u00e4lt Informationen \u00fcber Tokens, Lemmata, morpho-syntaktische Eigenschaften (z.B. Genus, Numerus, Kasus usw.) und Wortarten. Syntaktische Annotationen schlie\u00dfen Phrasen-(chunks) und Satzgrenzen ein. Phrasen sind zus\u00e4tzlich mit ihren grammatischen Funktionen markiert. Diese Annotationen der geschriebenen Korpusregister wurden aus CroCo importiert. F\u00fcr das gesprochene englische Subkorpus verwenden wir den Stanford POS Tagger (Toutanova et al., 2003) und den Stanford Parser (Klein and Manning, 2003). F\u00fcr das gesprochene Deutsch wurde MATE (Bohnet, 2010) verwendet. Das Korpus ist auch mit Informationen \u00fcber Koh\u00e4sionsmitteln annotiert: Koreferenz, Konjunktionen, Ellipsen, Substitution und lexikalische Koh\u00e4sion. Das semi-automatische Annotationsverfahren f\u00fcr Koreferenz, Konnektoren und Substitution ist in Lapshinova und Kunz (2014) detailliert beschrieben. Die Annotation von Ellipsen erfolgt zurzeit ausschlie\u00dflich manuell. Das Schema und die Kategorien sind in detaillierten projektinternen Richtlinien dokumentiert (Menzel 2014). Das Gesamtkorpus ist im CWB-Format gespeichert (CWB, 2010), welches Abfragen mit dem Corpus Query Processor (CQP; Evert, 2005) erm\u00f6glicht. Es gibt auch MMAX-Dateien.;Universit\u00e4t des Saarlandes;Ekaterina Lapshinova-Koltunski;Katrin Menzel;Kerstin Kunz;Marilisa Amoia;Prof. Erich Steiner;Jose Manuel Martinez Martinez;2013;Collection;text/xml;clarind-uds:gecco;hdl:11858/00-246C-0000-0023-8CF7-A;EO/GO/ETRANS/GTRANS-ESSAY/FICTION/INSTR/POPSCI/SHARE/SPEECH/TOU/WEB from CroCo (clarind-uds:croco);EO-INTERVIEW: from the BACKBONE project and ELISA corpus files, compiled at Englisches Seminar, Universit\u00e4t T\u00fcbingen, interviews about hobbies, work etc.;GO-INTERVIEW: from the BACKBONE project, compiled at Englisches Seminar, Universit\u00e4t T\u00fcbingen, interviews about hobbies, work etc.;EO-ACADEMIC: lectures from Michigan Corpus of Academic Spoken English;GO-ACADEMIC: lectures at UdS collected by within the Visual University project and transcribed by student assistants of GECCo team;EO/GO-FORUM: discussions in internet forums (travel, skin disorders, European politics, coffee, giving up smoking, roses, emotions and singing, depressions, crafting/DIY) collected by student assistants of GECCo team;EO-TALKSHOW: collected transcriptions of TV talkshows from the web (by GECCO team);GO-TALKSHOW: TV talkshows collected and transcribed by student assistants of GECCo team;EO-MEDONCULT:  medical consultations from BNC;GO-MEDONCULT:  medical consultation, Anamnese oder Aufkl\u00e4rungsgespr\u00e4chfrom the Dolmetschen im Krankenhaus Korpus;EO-SERMON: sermons from BNC;GO-SERMON: sermons from the Predigtarchiv Oberpfarr- und Domkirche zu Berlin;deu;eng;Lapshinova-Koltunski, E., K. Kunz and M. Amoia (2012). Compiling a Multilingual Corpus. In Heliana Mello, Massimo Pettorino and Tommaso Raso (eds). Proceedings of the VIIth GSCP-2012 International Conference: Speech and Corpora. Firenze: Firenze University Press. pp. 29-34.;Lapshinova-Koltunski, E. and K. Kunz (2014). Annotating Cohesion for Multillingual Analysis. In Proceedings of the 10th Joint ACL - ISO Workshop on Interoperable Semantic Annotation, Reykjavik, May 26, 2014;Menzel, Katrin (2014): Guidelines for the manual annotation of ellipses, DFG-Projektbericht.;Further publications: http://www.gecco.uni-saarland.de/GECCo/Publikationen.html;Germany;Copyrighted",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "368f06af-d64f-56f5-b489-a7730c4fa76b",
-    "notes": [
-        "offers a continuum of different text types (registers) from written to spoken discourse. More precisely, it includes English and German texts of 14 registers, eight of which represent written discourse and include fictional texts (FICTION), political essays (ESSAY), instruction manuals (INSTR), popular-scientific texts (POPSCI), letters to shareholders (SHARE), prepared political speeches (SPEECH), tourism leaflets (TOU) and corporate websites (WEB). This part was imported from the existing corpus CroCo described in (Hansen-Schirra et al., 2013). The written texts are saved in two subcorpora according to the language: English written texts (EO), German written texts\n(GO). The further registers are of spoken discourse and include recorded and transcribed interviews and academic speeches, see (Lapshinova-Koltunski et al., 2012).\nThe spoken texts are also stored in two further subcorpora classified according to the language of origin: English spoken texts (EO-SPOKEN) and German spoken texts (GO-SPOKEN).\nThe whole number of words contained in the corpus comprise ca. 1,4 Mio. The corpus is pre-annotated on several levels, which include information on tokens, lemmas, morpho-syntactic features (e.g. case, number, etc.), parts-of-speech, pharse chunks and their grammatical functions, as well as and sentence boundaries. The annotation of the written part was partly imported from CroCo, whereas for the spoken part, we use Stanford POS Tagger (Toutanova et al., 2003) and the Stanford Parser (Klein and Manning, 2003). \nThis corpus is also annotated for the information on cohesion (devices and relations), including coreference, conjunctive relations, substitution, ellipsis and lexical cohesion. The semi-automatic procedures were described in lapshinova and Kunz (2014). The annotation of ellipsis is manual and the scheme is described in Menzel (2014). The corpus is encoded in the CWB format (CWB, 2010) and can be queried with Corpus Query Processor (CQP) (Evert, 2005).",
-        "GECCo ist ein bilinguales Korpus (der Name ist vom Projekttitel 'German-English Contrasts in Cohesion' abgeleitet), das insgesamt ca. 1,44 Millionen Tokens enth\u00e4lt und sowohl parallele als auch vergleichbare Subkorpora f\u00fcr Englisch und Deutsch umfasst. GECCo beinhaltet gegenw\u00e4rtig 12 Register, zu denen sowohl gesprochensprachliche als auch geschriebene Textsorten geh\u00f6ren: ESSAY, FICTION, INSTR, POPSCI, SHARE, SPEECH, TOU, WEB, ACADEMIC, FORUM, INTERVIEW, TALKSHOW, MEDCONSULT, SERMON (je ca. 30.000 Tokens pro Register im jeweiligen Subkorpus). Die Texte der geschriebenen Register sind aus dem CroCo-Korpus \u00fcbernommen worden, vgl. Hansen-Schirra et al. (2012). Register gesprochener Sprache wurden im Rahmen des GECCo-Projekts gesammelt und annotiert. Probleme der Korpuskompilierung, Zusammenstellung und Annotation dieser Register wurden in Lapshinova et al. (2012) beschrieben. Beschaffung des gesprochensprachlichen Materials ist kompliziert, weil es viel manuellen Aufwand (Transkription) mit sich bringt. Zu beachten ist dabei, dass das Sprachmaterial in beiden Sprachen gesammelt wird und vergleichbar sein soll. Aus diesem Grund ist der geschriebene Teil von GECCo bisher gr\u00f6\u00dfer als\nder gesprochene. Das Korpus ist auf verschiedenen Ebenen annotiert und enth\u00e4lt Informationen \u00fcber Tokens, Lemmata, morpho-syntaktische Eigenschaften (z.B. Genus, Numerus, Kasus usw.) und Wortarten. Syntaktische Annotationen schlie\u00dfen Phrasen-(chunks) und Satzgrenzen ein. Phrasen sind zus\u00e4tzlich mit ihren grammatischen Funktionen markiert. Diese Annotationen der geschriebenen Korpusregister wurden aus CroCo importiert. F\u00fcr das gesprochene englische Subkorpus verwenden wir den Stanford POS Tagger (Toutanova et al., 2003) und den Stanford Parser (Klein and Manning, 2003). F\u00fcr das gesprochene Deutsch wurde MATE (Bohnet, 2010) verwendet. Das Korpus ist auch mit Informationen \u00fcber Koh\u00e4sionsmitteln annotiert: Koreferenz, Konjunktionen, Ellipsen, Substitution und lexikalische Koh\u00e4sion. Das semi-automatische Annotationsverfahren f\u00fcr Koreferenz, Konnektoren und Substitution ist in Lapshinova und Kunz (2014) detailliert beschrieben. Die Annotation von Ellipsen erfolgt zurzeit ausschlie\u00dflich manuell. Das Schema und die Kategorien sind in detaillierten projektinternen Richtlinien dokumentiert (Menzel 2014). Das Gesamtkorpus ist im CWB-Format gespeichert (CWB, 2010), welches Abfragen mit dem Corpus Query Processor (CQP; Evert, 2005) erm\u00f6glicht. Es gibt auch MMAX-Dateien."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:gecco"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus linguistics"
-        },
-        {
-            "name": "linguistics"
-        },
-        {
-            "name": "translation"
-        },
-        {
-            "name": "spoken language"
-        },
-        {
-            "name": "cohesion"
-        },
-        {
-            "name": "language contrasts"
-        },
-        {
-            "name": "discourse phenomena"
-        }
-    ],
-    "title": [
-        "GECCo"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/369b0559-d74a-5a7b-977c-da91078c9ed5.json b/oaitestdata/clarin-oai_dc/SET_1/json/369b0559-d74a-5a7b-977c-da91078c9ed5.json
deleted file mode 100644
index 1c0ae4e2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/369b0559-d74a-5a7b-977c-da91078c9ed5.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5724",
-    "MetadataAccess": [
-        "oai:ota:oucs:5724"
-    ],
-    "PublicationTimestamp": "1623-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1623"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Shakespeare, William, 1564-1616"
-    ],
-    "fulltext": "oai:ota:oucs:5724;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/5724.xml;THE Taming of the Shrew.;Shakespeare, William, 1564-1616;not after: 1623;text_and_corpus_linguistics;Plays -- England -- 16th century;Plays -- England -- 17th century;Comedies -- England -- 16th century;Comedies -- England -- 17th century;Tragedies -- England -- 16th century;Tragedies -- England -- 17th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "369b0559-d74a-5a7b-977c-da91078c9ed5",
-    "oai_identifier": [
-        "oai:ota:oucs:5724"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        },
-        {
-            "name": "Comedies -- England -- th century"
-        },
-        {
-            "name": "Comedies -- England -- th century"
-        },
-        {
-            "name": "Tragedies -- England -- th century"
-        },
-        {
-            "name": "Tragedies -- England -- th century"
-        }
-    ],
-    "title": [
-        "THE Taming of the Shrew."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5724.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/36c77b41-95ce-5ffb-8867-e9c9c6755dea.json b/oaitestdata/clarin-oai_dc/SET_1/json/36c77b41-95ce-5ffb-8867-e9c9c6755dea.json
deleted file mode 100644
index 7a29028e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/36c77b41-95ce-5ffb-8867-e9c9c6755dea.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Asmussen, J\u00f6rg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Danish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-267",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-267"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-267",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Denmark"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-267;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;FLEXIKON;Asmussen, J\u00f6rg;80.000 entries, flat, tab-separated file;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-267;dan;downloadable_files_count: 0;Denmark;http://ordnet.dk/korpusdk",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "36c77b41-95ce-5ffb-8867-e9c9c6755dea",
-    "notes": [
-        "80.000 entries, flat, tab-separated file"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-267"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "FLEXIKON"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/36dd0373-66e7-5f38-b2c4-3b48a454fddc.json b/oaitestdata/clarin-oai_dc/SET_1/json/36dd0373-66e7-5f38-b2c4-3b48a454fddc.json
deleted file mode 100644
index 528e4dc9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/36dd0373-66e7-5f38-b2c4-3b48a454fddc.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2812",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2812"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2812",
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "https://ufal.mff.cuni.cz/pbml/107/art-vicic-kubon-homola.pdf"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Homola, Petr",
-        "Vi\u010di\u010d, Jernej",
-        "Kubo\u0148, Vladislav"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2812;2018-07-02T22:05:54Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;\u010ces\u00edlko 2.0 Shallow Transfer RBMT framework (opensource version);Vi\u010di\u010d, Jernej;Kubo\u0148, Vladislav;Homola, Petr;Shallow Parse;Shallow Transfer Rule-Based Machine Translation;stochastic ranker;related languages;toolbox;The system \u010ces\u00edlko (language data and software tools) was first developed as an answer to a growing need of translation and localisation from one source language to many target languages. The starting system belonged to the Shallow Parse, Shallow Transfer Rule-Based Machine Translation \u2013 (RBMT) paradigm and it was designed primarily for translation of related languages. The latest implementation of the system uses a stochastic ranker; so technically it belongs to the hybrid machine translation paradigm, using stochastic methods combined with the traditional Shallow Transfer RBMT methods. The system has been stripped of the accompanying language resources due to copyright restrictions. The data that is available is just for demonstrative purposes.;2016;toolService;http://hdl.handle.net/11234/1-2812;https://ufal.mff.cuni.cz/pbml/107/art-vicic-kubon-homola.pdf;downloadable_files_count: 0;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://github.com/cesilko/cesilko",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "36dd0373-66e7-5f38-b2c4-3b48a454fddc",
-    "notes": [
-        "The system \u010ces\u00edlko (language data and software tools) was first developed as an answer to a growing need of translation and localisation from one source language to many target languages. The starting system belonged to the Shallow Parse, Shallow Transfer Rule-Based Machine Translation \u2013 (RBMT) paradigm and it was designed primarily for translation of related languages. The latest implementation of the system uses a stochastic ranker; so technically it belongs to the hybrid machine translation paradigm, using stochastic methods combined with the traditional Shallow Transfer RBMT methods. The system has been stripped of the accompanying language resources due to copyright restrictions. The data that is available is just for demonstrative purposes."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2812"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Shallow Parse"
-        },
-        {
-            "name": "Shallow Transfer Rule-Based Machine Translation"
-        },
-        {
-            "name": "stochastic ranker"
-        },
-        {
-            "name": "related languages"
-        },
-        {
-            "name": "toolbox"
-        }
-    ],
-    "title": [
-        "\u010ces\u00edlko 2.0 Shallow Transfer RBMT framework (opensource version)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/36de9c3d-acf9-5f4b-9699-f54551e49ff2.json b/oaitestdata/clarin-oai_dc/SET_1/json/36de9c3d-acf9-5f4b-9699-f54551e49ff2.json
deleted file mode 100644
index 804158ea..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/36de9c3d-acf9-5f4b-9699-f54551e49ff2.json
+++ /dev/null
@@ -1,97 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1512",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1512"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1512",
-    "PublicationTimestamp": "2015-10-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Haji\u010d, Jan",
-        "\u0160indlerov\u00e1, Jana",
-        "Ure\u0161ov\u00e1, Zde\u0148ka",
-        "Fu\u010d\u00edkov\u00e1, Eva"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1512;2018-07-02T22:05:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;CzEngVallex;Ure\u0161ov\u00e1, Zde\u0148ka;Fu\u010d\u00edkov\u00e1, Eva;Haji\u010d, Jan;\u0160indlerov\u00e1, Jana;verbal valency;argument structure;valency frame;lexicon;corpus annotation;translation equivalent;comparative syntax;comparative semantics;valency annotation;CzEngVallex is a bilingual valency lexicon of corresponding Czech and English verbs. It connects 20835 aligned valency frame pairs (verb senses) which are translations of each other, aligning their arguments as well. The CzEngVallex serves as a powerful, real-text-based database of frame-to-frame and subsequently argument-to-argument pairs and can be used for example for machine translation applications. It uses the data from the Prague Czech-English Dependency Treebank project (PCEDT 2.0, http://hdl.handle.net/11858/00-097C-0000-0015-8DAF-4) and it also takes advantage of two existing valency lexicons: PDT-Vallex for Czech and EngVallex for English, using the same view of valency (based on the Functional Generative Description theory).   The CzEngVallex is available in an XML format in the LINDAT/CLARIN repository, and also in a searchable form (see the \u201cMore Apps\u201d tab) interlinked with PDT-Vallex (http://hdl.handle.net/11858/00-097C-0000-0023-4338-F),EngVallex (http://hdl.handle.net/11858/00-097C-0000-0023-4337-2) and with examples from the PCEDT.;2015-10-01;lexicalConceptualResource;http://hdl.handle.net/11234/1-1512;eng;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/czengvallex",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "36de9c3d-acf9-5f4b-9699-f54551e49ff2",
-    "notes": [
-        "CzEngVallex is a bilingual valency lexicon of corresponding Czech and English verbs. It connects 20835 aligned valency frame pairs (verb senses) which are translations of each other, aligning their arguments as well. The CzEngVallex serves as a powerful, real-text-based database of frame-to-frame and subsequently argument-to-argument pairs and can be used for example for machine translation applications. It uses the data from the Prague Czech-English Dependency Treebank project (PCEDT 2.0, http://hdl.handle.net/11858/00-097C-0000-0015-8DAF-4) and it also takes advantage of two existing valency lexicons: PDT-Vallex for Czech and EngVallex for English, using the same view of valency (based on the Functional Generative Description theory).   The CzEngVallex is available in an XML format in the LINDAT/CLARIN repository, and also in a searchable form (see the \u201cMore Apps\u201d tab) interlinked with PDT-Vallex (http://hdl.handle.net/11858/00-097C-0000-0023-4338-F),EngVallex (http://hdl.handle.net/11858/00-097C-0000-0023-4337-2) and with examples from the PCEDT."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1512"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "verbal valency"
-        },
-        {
-            "name": "argument structure"
-        },
-        {
-            "name": "valency frame"
-        },
-        {
-            "name": "lexicon"
-        },
-        {
-            "name": "corpus annotation"
-        },
-        {
-            "name": "translation equivalent"
-        },
-        {
-            "name": "comparative syntax"
-        },
-        {
-            "name": "comparative semantics"
-        },
-        {
-            "name": "valency annotation"
-        }
-    ],
-    "title": [
-        "CzEngVallex"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/36e908cf-70a8-5432-adb8-6b7bd438df69.json b/oaitestdata/clarin-oai_dc/SET_1/json/36e908cf-70a8-5432-adb8-6b7bd438df69.json
deleted file mode 100644
index 924b6b98..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/36e908cf-70a8-5432-adb8-6b7bd438df69.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3312",
-    "MetadataAccess": [
-        "oai:ota:oucs:3312"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Duck, Stephen, 1705-1756."
-    ],
-    "fulltext": "oai:ota:oucs:3312;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3312.xml;Every man in his own way: An epistle to a friend. By Stephen Duck.;Duck, Stephen, 1705-1756.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "36e908cf-70a8-5432-adb8-6b7bd438df69",
-    "oai_identifier": [
-        "oai:ota:oucs:3312"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Every man in his own way: An epistle to a friend. By Stephen Duck."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3312.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/37013baf-6c3d-5c8f-a979-70607eabbc85.json b/oaitestdata/clarin-oai_dc/SET_1/json/37013baf-6c3d-5c8f-a979-70607eabbc85.json
deleted file mode 100644
index 2372815c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/37013baf-6c3d-5c8f-a979-70607eabbc85.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 465 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2052",
-    "MetadataAccess": [
-        "oai:ota:oucs:2052"
-    ],
-    "PublicationTimestamp": "1749-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1749"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Cleland, John, 1709-1789"
-    ],
-    "fulltext": "oai:ota:oucs:2052;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/2052.xml;Memoirs of a woman of pleasure (Fanny Hill) / by John Cleland;Cleland, John, 1709-1789;1749;text_and_corpus_linguistics;Fiction -- England -- 18th century;eng;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 465 KB);Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "37013baf-6c3d-5c8f-a979-70607eabbc85",
-    "oai_identifier": [
-        "oai:ota:oucs:2052"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- England -- th century"
-        }
-    ],
-    "title": [
-        "Memoirs of a woman of pleasure (Fanny Hill) / by John Cleland"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2052.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/37034e63-0090-5c72-8570-990d63bb306a.json b/oaitestdata/clarin-oai_dc/SET_1/json/37034e63-0090-5c72-8570-990d63bb306a.json
deleted file mode 100644
index 6f12bee9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/37034e63-0090-5c72-8570-990d63bb306a.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 255 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "French"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0215",
-    "MetadataAccess": [
-        "oai:ota:oucs:0215"
-    ],
-    "PublicationTimestamp": "1888-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1888"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Maupassant, Guy de, 1850-1893"
-    ],
-    "fulltext": "oai:ota:oucs:0215;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0215.xml;Pierre et Jean;Maupassant, Guy de, 1850-1893;1888;text_and_corpus_linguistics;Novels -- France -- 19th century;fra;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 255 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "37034e63-0090-5c72-8570-990d63bb306a",
-    "oai_identifier": [
-        "oai:ota:oucs:0215"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Novels -- France -- th century"
-        }
-    ],
-    "title": [
-        "Pierre et Jean"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0215.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3703dbb7-ce91-5865-93f6-41b3c60d2cd8.json b/oaitestdata/clarin-oai_dc/SET_1/json/3703dbb7-ce91-5865-93f6-41b3c60d2cd8.json
deleted file mode 100644
index b2f10337..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3703dbb7-ce91-5865-93f6-41b3c60d2cd8.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4396",
-    "MetadataAccess": [
-        "oai:ota:oucs:4396"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Radcliffe, Ann Ward, 1764-1823."
-    ],
-    "fulltext": "oai:ota:oucs:4396;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4396.xml;The mysteries of Udolpho: a romance; interspersed with some pieces of poetry. By Ann Radcliffe, ... In four volumes. ... [pt.4];Radcliffe, Ann Ward, 1764-1823.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3703dbb7-ce91-5865-93f6-41b3c60d2cd8",
-    "oai_identifier": [
-        "oai:ota:oucs:4396"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The mysteries of Udolpho: a romance; interspersed with some pieces of poetry. By Ann Radcliffe, ... In four volumes. ... [pt.4]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4396.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/371f06f2-5ce8-5bf7-8ad5-86731eeb1677.json b/oaitestdata/clarin-oai_dc/SET_1/json/371f06f2-5ce8-5bf7-8ad5-86731eeb1677.json
deleted file mode 100644
index 200e139a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/371f06f2-5ce8-5bf7-8ad5-86731eeb1677.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Maria Curie-Sk\u0142odowska University in Lublin"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "downloadable_files_count: 2"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/416",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/416"
-    ],
-    "PID": "http://hdl.handle.net/11321/416",
-    "PublicationTimestamp": "2017-07-12T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Maria Curie-Sk\u0142odowska University in Lublin"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Kosacka, Kalina"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/416;2017-07-12T12:52:14Z;hdl_11321_3;hdl_11321_4;Niepokoj - korpus;Kosacka, Kalina;niepok\u00f3j;niepok\u00f3j;2017-07-12;corpus;http://hdl.handle.net/11321/416;pol;Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0);http://creativecommons.org/licenses/by-nc-nd/3.0/;CC;text/plain; charset=utf-8;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;downloadable_files_count: 2;Maria Curie-Sk\u0142odowska University in Lublin",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "371f06f2-5ce8-5bf7-8ad5-86731eeb1677",
-    "notes": [
-        "niepok\u00f3j"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/416"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Niepokoj - korpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/373bbe76-a152-5863-a549-cac2cebec5d7.json b/oaitestdata/clarin-oai_dc/SET_1/json/373bbe76-a152-5863-a549-cac2cebec5d7.json
deleted file mode 100644
index d2926326..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/373bbe76-a152-5863-a549-cac2cebec5d7.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3594",
-    "MetadataAccess": [
-        "oai:ota:oucs:3594"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Bentley, R. (Richard), 1708-1782."
-    ],
-    "fulltext": "oai:ota:oucs:3594;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3594.xml;Philodamus. A tragedy;Bentley, R. (Richard), 1708-1782.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "373bbe76-a152-5863-a549-cac2cebec5d7",
-    "oai_identifier": [
-        "oai:ota:oucs:3594"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Philodamus. A tragedy"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3594.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/373c56e3-3646-5790-89ba-f3de9258c5a6.json b/oaitestdata/clarin-oai_dc/SET_1/json/373c56e3-3646-5790-89ba-f3de9258c5a6.json
deleted file mode 100644
index 99a5633e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/373c56e3-3646-5790-89ba-f3de9258c5a6.json
+++ /dev/null
@@ -1,91 +0,0 @@
-{
-    "Contact": [
-        "Masaryk University, NLP Centre"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Amharic"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2587",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2587"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2587",
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Masaryk University, NLP Centre"
-    ],
-    "RelatedIdentifier": [
-        "https://link.springer.com/chapter/10.1007/978-3-319-45510-5_34",
-        "https://www.sketchengine.co.uk/wp-content/uploads/2015/05/Corpus_Factory_2010.pdf",
-        "http://habit-project.eu/wiki/AmharicCorpus"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "NLP Centre Web Corpus License",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/license-NLPC-WeC",
-        "ACA"
-    ],
-    "author": [
-        "Suchomel, V\u00edt",
-        "Rychl\u00fd, Pavel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2587;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Amharic Web Corpus;Suchomel, V\u00edt;Rychl\u00fd, Pavel;Amharic;text corpus;web corpus;under-resourced language;corpus annotation;morphological tagger;Amharic web corpus. Crawled by SpiderLing in August 2013 and October 2015 and January 2016. Encoded in UTF-8, cleaned, deduplicated. Tagged by TreeTagger trained on Amharic WIC corpus.;2016;corpus;http://hdl.handle.net/11234/1-2587;amh;https://link.springer.com/chapter/10.1007/978-3-319-45510-5_34;https://www.sketchengine.co.uk/wp-content/uploads/2015/05/Corpus_Factory_2010.pdf;http://habit-project.eu/wiki/AmharicCorpus;NLP Centre Web Corpus License;https://lindat.mff.cuni.cz/repository/xmlui/page/license-NLPC-WeC;ACA;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Masaryk University, NLP Centre;http://habit-project.eu/wiki/HabitSystemFinal",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "373c56e3-3646-5790-89ba-f3de9258c5a6",
-    "notes": [
-        "Amharic web corpus. Crawled by SpiderLing in August 2013 and October 2015 and January 2016. Encoded in UTF-8, cleaned, deduplicated. Tagged by TreeTagger trained on Amharic WIC corpus."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2587"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Amharic"
-        },
-        {
-            "name": "text corpus"
-        },
-        {
-            "name": "web corpus"
-        },
-        {
-            "name": "under-resourced language"
-        },
-        {
-            "name": "corpus annotation"
-        },
-        {
-            "name": "morphological tagger"
-        }
-    ],
-    "title": [
-        "Amharic Web Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/374ebff2-6438-53f6-ab5b-5da6d7e5cd12.json b/oaitestdata/clarin-oai_dc/SET_1/json/374ebff2-6438-53f6-ab5b-5da6d7e5cd12.json
deleted file mode 100644
index 2a0f5f66..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/374ebff2-6438-53f6-ab5b-5da6d7e5cd12.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-487E-B",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-487E-B"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-487E-B",
-    "PublicationTimestamp": "2009-01-05T11:59:59Z",
-    "PublicationYear": [
-        "2009"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Haji\u010d, Jan",
-        "Stra\u0148\u00e1k, Pavel",
-        "\u0160t\u011bp\u00e1nek, Jan"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-487E-B;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;CoNLL 2009 Shared Task Czech Trial Set;Haji\u010d, Jan;Stra\u0148\u00e1k, Pavel;\u0160t\u011bp\u00e1nek, Jan;conll-st;Czech trial (example) data for CoNLL 2009 Shared Task. The data are generated from PDT 2.0. LDC2009E32B;2009-01-05;corpus;http://www.aclweb.org/anthology/W09-1201;http://hdl.handle.net/11858/00-097C-0000-0001-487E-B;ces;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "374ebff2-6438-53f6-ab5b-5da6d7e5cd12",
-    "notes": [
-        "Czech trial (example) data for CoNLL 2009 Shared Task. The data are generated from PDT 2.0. LDC2009E32B"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-487E-B"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "conll-st"
-        }
-    ],
-    "title": [
-        "CoNLL 2009 Shared Task Czech Trial Set"
-    ],
-    "url": "http://www.aclweb.org/anthology/W09-1201"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/37623a0a-1ef5-5300-9b39-621b30a066c3.json b/oaitestdata/clarin-oai_dc/SET_1/json/37623a0a-1ef5-5300-9b39-621b30a066c3.json
deleted file mode 100644
index 24c8d3f4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/37623a0a-1ef5-5300-9b39-621b30a066c3.json
+++ /dev/null
@@ -1,89 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1031",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1031"
-    ],
-    "PID": "http://hdl.handle.net/11356/1031",
-    "PublicationTimestamp": "2014-07-28T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/215064",
-        "https://doi.org/10.1007/s10579-015-9294-7"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by-sa/4.0/"
-    ],
-    "author": [
-        "Erjavec, Toma\u017e"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1031;2018-10-24T20:47:10Z;hdl_11356_1023;hdl_11356_1024;Digital library and corpus of historical Slovene IMP 1.1;Erjavec, Toma\u017e;historical language;word modernisation;lemmatisation;tagging;digital library;TEI;The IMP digital library contains historical Slovene books and other publications, together 658 texts with over 45,000 pages from the period 1584-1919.  Each text contains extensive meta-data, per-page links to facsimiles, and hand-corrected transcriptions with structural and editorial annotations.\r\n\r\nThese texts were annotated to be used as a language corpus.  In the corpus each word is marked-up with its modernised form, lemma, and morphosyntactic description (fine grained PoS tag). Note that the annotations are automatic, so they contain a fair amount of errors.\r\n\r\nThe digital library is available in source TEI P5 XML and derived HTML. The corpus is available in source TEI P5 XML and in the simpler and smaller vertical format, used by various concordancers, e.g. CWB and Sketch Engine. Note that the vertical format does not contain all the information from the source TEI.;2014-07-28;corpus;http://hdl.handle.net/11356/1031;slv;info:eu-repo/grantAgreement/EC/FP7/215064;https://doi.org/10.1007/s10579-015-9294-7;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);PUB;https://creativecommons.org/licenses/by-sa/4.0/;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 4;Jo\u017eef Stefan Institute;http://nl.ijs.si/imp/index-en.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "37623a0a-1ef5-5300-9b39-621b30a066c3",
-    "notes": [
-        "The IMP digital library contains historical Slovene books and other publications, together 658 texts with over 45,000 pages from the period 1584-1919.  Each text contains extensive meta-data, per-page links to facsimiles, and hand-corrected transcriptions with structural and editorial annotations.\r\n\r\nThese texts were annotated to be used as a language corpus.  In the corpus each word is marked-up with its modernised form, lemma, and morphosyntactic description (fine grained PoS tag). Note that the annotations are automatic, so they contain a fair amount of errors.\r\n\r\nThe digital library is available in source TEI P5 XML and derived HTML. The corpus is available in source TEI P5 XML and in the simpler and smaller vertical format, used by various concordancers, e.g. CWB and Sketch Engine. Note that the vertical format does not contain all the information from the source TEI."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1031"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "historical language"
-        },
-        {
-            "name": "word modernisation"
-        },
-        {
-            "name": "lemmatisation"
-        },
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "digital library"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "Digital library and corpus of historical Slovene IMP 1.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/37644467-99ea-5e7b-8562-fcd8cf6ab152.json b/oaitestdata/clarin-oai_dc/SET_1/json/37644467-99ea-5e7b-8562-fcd8cf6ab152.json
deleted file mode 100644
index 0ddd85fd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/37644467-99ea-5e7b-8562-fcd8cf6ab152.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Centre for Applied Language Studies, University of Jyv\u00e4skyl\u00e4"
-    ],
-    "Contributor": [
-        "Tarnanen, Mirja"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English",
-        "Finnish",
-        "French",
-        "German",
-        "Italian",
-        "Russian",
-        "Spanish",
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-806",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-806"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-806",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Centre for Applied Language Studies, University of Jyv\u00e4skyl\u00e4"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Finland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-806;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;The National Certificates corpus;Tarnanen, Mirja;The NC test results, background information, speaking and writing performances in 9 foreign / second languages. A web-based data base (html files).;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-806;eng;fin;fra;deu;ita;rus;spa;swe;downloadable_files_count: 0;Finland;Centre for Applied Language Studies, University of Jyv\u00e4skyl\u00e4;http://yki-korpus.jyu.fi/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "37644467-99ea-5e7b-8562-fcd8cf6ab152",
-    "notes": [
-        "The NC test results, background information, speaking and writing performances in 9 foreign / second languages. A web-based data base (html files)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-806"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "The National Certificates corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/377b9363-5002-5fef-bf85-9c86de3a5146.json b/oaitestdata/clarin-oai_dc/SET_1/json/377b9363-5002-5fef-bf85-9c86de3a5146.json
deleted file mode 100644
index 73f27ca1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/377b9363-5002-5fef-bf85-9c86de3a5146.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Free University Amsterdam, Faculty of Theology, Werkgroep Informatica"
-    ],
-    "Contributor": [
-        "Talstra, Prof. Dr. Eep"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Hebrew"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1053",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1053"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1053",
-    "PublicationTimestamp": "2010-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "Free University Amsterdam, Faculty of Theology, Werkgroep Informatica"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Access after registration and consent"
-    ],
-    "SpatialCoverage": [
-        "Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1053;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;WIVU Old Testament Hebrew Database;Talstra, Prof. Dr. Eep;linguistically aided literary analysis of Hebrew Old Testament;Morphologically and grammatically annotated Hebrew text of Old Testament;2010;corpus;http://hdl.handle.net/11372/LRT-1053;heb;Access after registration and consent;downloadable_files_count: 0;Netherlands (the);Free University Amsterdam, Faculty of Theology, Werkgroep Informatica;http://wivu.dans.knaw.nl",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "377b9363-5002-5fef-bf85-9c86de3a5146",
-    "notes": [
-        "Morphologically and grammatically annotated Hebrew text of Old Testament"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1053"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "linguistically aided literary analysis Hebrew Old Testament"
-        }
-    ],
-    "title": [
-        "WIVU Old Testament Hebrew Database"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3784e69a-7151-5916-bb9d-d5f1619f2a30.json b/oaitestdata/clarin-oai_dc/SET_1/json/3784e69a-7151-5916-bb9d-d5f1619f2a30.json
deleted file mode 100644
index 05ebbb27..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3784e69a-7151-5916-bb9d-d5f1619f2a30.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "[S. n.]"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-38",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-38"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D19-5",
-    "PublicationTimestamp": "1754-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1754"
-    ],
-    "Publisher": [
-        "[S. n.]"
-    ],
-    "RelatedIdentifier": [
-        "http://pbc.biaman.pl/Content/38"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-38;2019-03-01T15:25:34Z;Akta publiczne do interessu ordynacyi Ostrogskiey nale\u017c\u0105ce;Ostrogscy;Polska 18 w.;ilo\u015b\u0107 skan\u00f3w: 196 ; sygn. St-303;[S. n.];1754;starodruk;application/xml;clarind-uds:poldilemma-38;hdl:11858/00-246C-0000-0023-8D19-5;pol;lat;http://pbc.biaman.pl/Content/38;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3784e69a-7151-5916-bb9d-d5f1619f2a30",
-    "notes": [
-        "ilo\u015b\u0107 skan\u00f3w: 196 ; sygn. St-303"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-38"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Ostrogscy"
-        },
-        {
-            "name": "Polska w."
-        }
-    ],
-    "title": [
-        "Akta publiczne do interessu ordynacyi Ostrogskiey nale\u017c\u0105ce"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/37a8e733-d61a-5b85-a622-e89e7380bf02.json b/oaitestdata/clarin-oai_dc/SET_1/json/37a8e733-d61a-5b85-a622-e89e7380bf02.json
deleted file mode 100644
index b5cd5371..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/37a8e733-d61a-5b85-a622-e89e7380bf02.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4624",
-    "MetadataAccess": [
-        "oai:ota:oucs:4624"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Paley, William, 1743-1805."
-    ],
-    "fulltext": "oai:ota:oucs:4624;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4624.xml;Reasons for contentment: addressed to the labouring part of the British public. By William Paley, ...;Paley, William, 1743-1805.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "37a8e733-d61a-5b85-a622-e89e7380bf02",
-    "oai_identifier": [
-        "oai:ota:oucs:4624"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Reasons for contentment: addressed to the labouring part of the British public. By William Paley, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4624.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/37c156ad-583d-5467-a81f-553d2a4ce4de.json b/oaitestdata/clarin-oai_dc/SET_1/json/37c156ad-583d-5467-a81f-553d2a4ce4de.json
deleted file mode 100644
index ffe54a38..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/37c156ad-583d-5467-a81f-553d2a4ce4de.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "Middle High German (ca. 1050-1500)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3226",
-    "MetadataAccess": [
-        "oai:ota:oucs:3226"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "von Aue, Hartmann, 12th cent."
-    ],
-    "fulltext": "oai:ota:oucs:3226;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3226.xml;Der arme Heinrich;von Aue, Hartmann, 12th cent.;default: 1976-01-01;text_and_corpus_linguistics;Poems -- Germany -- 12th century;Epics -- Germany -- 12th century;Devotional literature -- Germany -- 12th century;gmh;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "37c156ad-583d-5467-a81f-553d2a4ce4de",
-    "oai_identifier": [
-        "oai:ota:oucs:3226"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- Germany -- th century"
-        },
-        {
-            "name": "Epics -- Germany -- th century"
-        },
-        {
-            "name": "Devotional literature -- Germany -- th century"
-        }
-    ],
-    "title": [
-        "Der arme Heinrich"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3226.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/37e1e5e6-e4e5-50d9-bdcf-f2246ef78796.json b/oaitestdata/clarin-oai_dc/SET_1/json/37e1e5e6-e4e5-50d9-bdcf-f2246ef78796.json
deleted file mode 100644
index 18fbc91f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/37e1e5e6-e4e5-50d9-bdcf-f2246ef78796.json
+++ /dev/null
@@ -1,49 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3451",
-    "MetadataAccess": [
-        "oai:ota:oucs:3451"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:3451;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3451.xml;Burnet and Bradbury: or the confederacy of the press and the pulpit for the blood of the last ministry.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "37e1e5e6-e4e5-50d9-bdcf-f2246ef78796",
-    "oai_identifier": [
-        "oai:ota:oucs:3451"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Burnet and Bradbury: or the confederacy of the press and the pulpit for the blood of the last ministry."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3451.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/380012df-50d8-54a7-af6e-1a2f9c28cf31.json b/oaitestdata/clarin-oai_dc/SET_1/json/380012df-50d8-54a7-af6e-1a2f9c28cf31.json
deleted file mode 100644
index e1a1fa15..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/380012df-50d8-54a7-af6e-1a2f9c28cf31.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2719",
-    "MetadataAccess": [
-        "oai:ota:oucs:2719"
-    ],
-    "PublicationTimestamp": "1765-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1765"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2719;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2719.xml;The dying speech of Tom Ashe;Swift, Jonathan, 1667-1745;1765;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "380012df-50d8-54a7-af6e-1a2f9c28cf31",
-    "oai_identifier": [
-        "oai:ota:oucs:2719"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The dying speech of Tom Ashe"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2719.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3811469d-e2fe-5ae9-b3b6-35a2c6151c1b.json b/oaitestdata/clarin-oai_dc/SET_1/json/3811469d-e2fe-5ae9-b3b6-35a2c6151c1b.json
deleted file mode 100644
index 77087db3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3811469d-e2fe-5ae9-b3b6-35a2c6151c1b.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "Contributor": [
-        "Bizjak, Aleksandra",
-        "Jakopin, Primoz"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-419",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-419"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-419",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Slovenia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-419;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;POS-beseda;Jakopin, Primoz;Bizjak, Aleksandra;written/monolingual/fiction corpus; 1 mil. words; word-level, own tagset;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-419;slv;downloadable_files_count: 0;Slovenia;http://bos.zrc-sazu.si/gradivo.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3811469d-e2fe-5ae9-b3b6-35a2c6151c1b",
-    "notes": [
-        "written/monolingual/fiction corpus; 1 mil. words; word-level, own tagset"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-419"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "POS-beseda"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3821f2f4-ddc4-546d-8aa6-957f6f31cab1.json b/oaitestdata/clarin-oai_dc/SET_1/json/3821f2f4-ddc4-546d-8aa6-957f6f31cab1.json
deleted file mode 100644
index 42becab7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3821f2f4-ddc4-546d-8aa6-957f6f31cab1.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1900",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1900"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1900",
-    "PublicationTimestamp": "2016-12-07T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-2594"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "BSD 3-Clause \"New\" or \"Revised\" license",
-        "http://opensource.org/licenses/BSD-3-Clause",
-        "PUB"
-    ],
-    "author": [
-        "Haji\u010d, Jan",
-        "Ko\u0161arko, Ond\u0159ej"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1900;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;VIADAT-REPO;Ko\u0161arko, Ond\u0159ej;Haji\u010d, Jan;digital data;digital repository;VIADAT-REPO is a modification to lindat-dspace platform; it's a part of the VIADAT project and as such will be a part of a \"virtual assistant\" for processing, annotation, enrichment and accessing of audio and video recordings.;2016-12-07;toolService;http://hdl.handle.net/11234/1-1900;http://hdl.handle.net/11234/1-2594;BSD 3-Clause \"New\" or \"Revised\" license;http://opensource.org/licenses/BSD-3-Clause;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://ufal.mff.cuni.cz/grants/viadat",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3821f2f4-ddc4-546d-8aa6-957f6f31cab1",
-    "notes": [
-        "VIADAT-REPO is a modification to lindat-dspace platform; it's a part of the VIADAT project and as such will be a part of a \"virtual assistant\" for processing, annotation, enrichment and accessing of audio and video recordings."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1900"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "digital data"
-        },
-        {
-            "name": "digital repository"
-        }
-    ],
-    "title": [
-        "VIADAT-REPO"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3834c7e9-ff8c-528e-afb1-a214f53cc234.json b/oaitestdata/clarin-oai_dc/SET_1/json/3834c7e9-ff8c-528e-afb1-a214f53cc234.json
deleted file mode 100644
index e050469f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3834c7e9-ff8c-528e-afb1-a214f53cc234.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "English",
-        "Czech",
-        "Finnish",
-        "Russian",
-        "Slovak"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2616",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2616"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2616",
-    "PublicationTimestamp": "2018-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Licence Universal Dependencies v2.1",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-2.1",
-        "PUB"
-    ],
-    "author": [
-        "Kanerva, Jenna",
-        "Ginter, Filip",
-        "Zeman, Daniel",
-        "Droganova, Kira"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2616;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Artificial Treebank with Ellipsis;Droganova, Kira;Zeman, Daniel;Kanerva, Jenna;Ginter, Filip;universal dependencies;ellipsis;gapping;Artificially created treebank of elliptical constructions (gapping), in the annotation style of Universal Dependencies. Data taken from UD 2.1 release, and from large web corpora parsed by two parsers. Input data are filtered, sentences are identified where gapping could be applied, then those sentences are transformed, one or more words are omitted, resulting in a sentence with gapping. Details in Droganova et al.: Parse Me if You Can: Artificial Treebanks for Parsing Experiments on Elliptical Constructions, LREC 2018, Miyazaki, Japan.;2018-02-15;corpus;http://hdl.handle.net/11234/1-2616;eng;ces;fin;rus;slk;Licence Universal Dependencies v2.1;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-2.1;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3834c7e9-ff8c-528e-afb1-a214f53cc234",
-    "notes": [
-        "Artificially created treebank of elliptical constructions (gapping), in the annotation style of Universal Dependencies. Data taken from UD 2.1 release, and from large web corpora parsed by two parsers. Input data are filtered, sentences are identified where gapping could be applied, then those sentences are transformed, one or more words are omitted, resulting in a sentence with gapping. Details in Droganova et al.: Parse Me if You Can: Artificial Treebanks for Parsing Experiments on Elliptical Constructions, LREC 2018, Miyazaki, Japan."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2616"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "universal dependencies"
-        },
-        {
-            "name": "ellipsis"
-        },
-        {
-            "name": "gapping"
-        }
-    ],
-    "title": [
-        "Artificial Treebank with Ellipsis"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3835f656-2ed1-5eac-a8e5-368d0ba00aa0.json b/oaitestdata/clarin-oai_dc/SET_1/json/3835f656-2ed1-5eac-a8e5-368d0ba00aa0.json
deleted file mode 100644
index dd285a60..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3835f656-2ed1-5eac-a8e5-368d0ba00aa0.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "University of Tartu"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Estonian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-568",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-568"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-568",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Tartu"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Estonia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-568;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TEKsaurus;Estonian Wordnet, 10000 synsets;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-568;est;downloadable_files_count: 0;Estonia;University of Tartu;http://www.cl.ut.ee/ressursid/teksaurus/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3835f656-2ed1-5eac-a8e5-368d0ba00aa0",
-    "notes": [
-        "Estonian Wordnet, 10000 synsets"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-568"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TEKsaurus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/38459832-2394-5dac-ae63-feb1366c17f2.json b/oaitestdata/clarin-oai_dc/SET_1/json/38459832-2394-5dac-ae63-feb1366c17f2.json
deleted file mode 100644
index 2cdedbac..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/38459832-2394-5dac-ae63-feb1366c17f2.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contributor": [
-        "Dyvik, Helge"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-532",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-532"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-532",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "SpatialCoverage": [
-        "Norway"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-532;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;NorGram;Dyvik, Helge;All central constructions; lexicon >80 000 lemmas, Lexical-Functional Grammar (LFG) and Minimal Recursion Semantics (MRS);2014-07-30;languageDescription;http://hdl.handle.net/11372/LRT-532;downloadable_files_count: 0;Norway;http://iness.uib.no/iness/xle-web",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "38459832-2394-5dac-ae63-feb1366c17f2",
-    "notes": [
-        "All central constructions; lexicon >80 000 lemmas, Lexical-Functional Grammar (LFG) and Minimal Recursion Semantics (MRS)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-532"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "NorGram"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/384cd445-6c95-5320-893f-ca682c817d5e.json b/oaitestdata/clarin-oai_dc/SET_1/json/384cd445-6c95-5320-893f-ca682c817d5e.json
deleted file mode 100644
index e36c83e4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/384cd445-6c95-5320-893f-ca682c817d5e.json
+++ /dev/null
@@ -1,95 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-4670-6",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-4670-6"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-4670-6",
-    "PublicationTimestamp": "2014-02-21T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-1740"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0)",
-        "http://creativecommons.org/licenses/by-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u017dilka, Luk\u00e1\u0161",
-        "Jur\u010d\u00ed\u010dek, Filip",
-        "Du\u0161ek, Ond\u0159ej",
-        "Pl\u00e1tek, Ond\u0159ej",
-        "Korvas, Mat\u011bj"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-4670-6;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Vystadial 2013 \u2013 Czech data;Korvas, Mat\u011bj;Pl\u00e1tek, Ond\u0159ej;Du\u0161ek, Ond\u0159ej;\u017dilka, Luk\u00e1\u0161;Jur\u010d\u00ed\u010dek, Filip;acoustic data;speech corpus;spoken corpus;orthographic transcriptions;telephone speech;voip;dialogue system;Vystadial 2013 is a dataset of telephone conversations in English and Czech, developed for training acoustic models for automatic speech recognition in spoken dialogue systems. It ships in three parts: Czech data, English data, and scripts.\r\n\r\nThe data comprise over 41 hours of speech in English and over 15 hours in Czech, plus orthographic transcriptions. The scripts implement data pre-processing and building acoustic models using the HTK and Kaldi toolkits.\r\n\r\nThis is the Czech data part of the dataset.;2014-02-21;corpus;http://hdl.handle.net/11858/00-097C-0000-0023-4670-6;ces;http://hdl.handle.net/11234/1-1740;Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0);http://creativecommons.org/licenses/by-sa/3.0/;PUB;text/plain; charset=utf-8;application/x-gzip;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics;https://ufal.mff.cuni.cz/grants/vystadial",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "384cd445-6c95-5320-893f-ca682c817d5e",
-    "notes": [
-        "Vystadial 2013 is a dataset of telephone conversations in English and Czech, developed for training acoustic models for automatic speech recognition in spoken dialogue systems. It ships in three parts: Czech data, English data, and scripts.\r\n\r\nThe data comprise over 41 hours of speech in English and over 15 hours in Czech, plus orthographic transcriptions. The scripts implement data pre-processing and building acoustic models using the HTK and Kaldi toolkits.\r\n\r\nThis is the Czech data part of the dataset."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-4670-6"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "acoustic data"
-        },
-        {
-            "name": "speech corpus"
-        },
-        {
-            "name": "spoken corpus"
-        },
-        {
-            "name": "orthographic transcriptions"
-        },
-        {
-            "name": "telephone speech"
-        },
-        {
-            "name": "voip"
-        },
-        {
-            "name": "dialogue system"
-        }
-    ],
-    "title": [
-        "Vystadial 2013 \u2013 Czech data"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/385a50e7-ffa8-5780-9313-341797cb8d35.json b/oaitestdata/clarin-oai_dc/SET_1/json/385a50e7-ffa8-5780-9313-341797cb8d35.json
deleted file mode 100644
index 5f16e8db..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/385a50e7-ffa8-5780-9313-341797cb8d35.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=41eced9cabc711e1a404080027e73ea2fd1949c0f7104c8a984017468f75157a",
-    "MetadataAccess": [
-        "41eced9cabc711e1a404080027e73ea2fd1949c0f7104c8a984017468f75157a"
-    ],
-    "PublicationTimestamp": "2013-01-31T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "41eced9cabc711e1a404080027e73ea2fd1949c0f7104c8a984017468f75157a;2018-11-15T16:39:31Z;corpus;corpus:text;Maltese Wikipedia;This corpus is part of the collection of the Wikipedia Dumps which was retrieved from  wikipedia.org on April 8, 2010.  It comes with two individual XML files, one containing the Wikipedia articles and another containing the metadata about it.\n;2013-01-31",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "385a50e7-ffa8-5780-9313-341797cb8d35",
-    "notes": [
-        "This corpus is part of the collection of the Wikipedia Dumps which was retrieved from  wikipedia.org on April 8, 2010.  It comes with two individual XML files, one containing the Wikipedia articles and another containing the metadata about it.\n"
-    ],
-    "oai_identifier": [
-        "41eced9cabc711e1a404080027e73ea2fd1949c0f7104c8a984017468f75157a"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "Maltese Wikipedia"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/38878025-3eca-5584-9b19-383430b6ee93.json b/oaitestdata/clarin-oai_dc/SET_1/json/38878025-3eca-5584-9b19-383430b6ee93.json
deleted file mode 100644
index ac24efa8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/38878025-3eca-5584-9b19-383430b6ee93.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "UJ"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "downloadable_files_count: 10",
-        "application/vnd.oasis.opendocument.text",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/406",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/406"
-    ],
-    "PID": "http://hdl.handle.net/11321/406",
-    "PublicationTimestamp": "2017-06-29T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "UJ"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Kryg, Jagoda"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/406;2017-06-29T07:52:31Z;hdl_11321_3;hdl_11321_4;korpus testowy;Kryg, Jagoda;korpus tekstowy;transkrypcje;warsztaty;korpus testowy - warsztaty dspace;2017-06-29;corpus;http://hdl.handle.net/11321/406;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.oasis.opendocument.text;text/plain;text/plain;application/vnd.oasis.opendocument.text;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;downloadable_files_count: 10;UJ",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "38878025-3eca-5584-9b19-383430b6ee93",
-    "notes": [
-        "korpus testowy - warsztaty dspace"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/406"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "korpus tekstowy"
-        },
-        {
-            "name": "transkrypcje"
-        },
-        {
-            "name": "warsztaty"
-        }
-    ],
-    "title": [
-        "korpus testowy"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/388d3140-e674-5f2f-96d4-9e7d4de535d3.json b/oaitestdata/clarin-oai_dc/SET_1/json/388d3140-e674-5f2f-96d4-9e7d4de535d3.json
deleted file mode 100644
index d4680d65..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/388d3140-e674-5f2f-96d4-9e7d4de535d3.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3568",
-    "MetadataAccess": [
-        "oai:ota:oucs:3568"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Brown, John, 1715-1766."
-    ],
-    "fulltext": "oai:ota:oucs:3568;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3568.xml;Thoughts on civil liberty: on licentiousness, and faction. By the author of Essays on the characteristics, &c.;Brown, John, 1715-1766.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "388d3140-e674-5f2f-96d4-9e7d4de535d3",
-    "oai_identifier": [
-        "oai:ota:oucs:3568"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Thoughts on civil liberty: on licentiousness, and faction. By the author of Essays on the characteristics, &c."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3568.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3890da8d-0a2a-5044-9bd6-f09b9fd8f93e.json b/oaitestdata/clarin-oai_dc/SET_1/json/3890da8d-0a2a-5044-9bd6-f09b9fd8f93e.json
deleted file mode 100644
index 242652dc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3890da8d-0a2a-5044-9bd6-f09b9fd8f93e.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "ClarinPL"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/553",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/553"
-    ],
-    "PID": "http://hdl.handle.net/11321/553",
-    "PublicationTimestamp": "2018-07-24T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "ClarinPL"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Za\u015bko-Zieli\u0144ska, Monika"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/553;2018-07-24T11:42:41Z;hdl_11321_3;hdl_11321_4;Emotional Annotations Dictionary;Za\u015bko-Zieli\u0144ska, Monika;dictionary;emotional annotations;universal values;emotions;lexical units with emotions;List of lexical units with  emotional annotation extracted from Polish Wordnet (S\u0142owosie\u0107 4.0);2018-07-24;lexicalConceptualResource;http://hdl.handle.net/11321/553;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;ClarinPL;https://plwordnet.clarin-pl.eu",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3890da8d-0a2a-5044-9bd6-f09b9fd8f93e",
-    "notes": [
-        "List of lexical units with  emotional annotation extracted from Polish Wordnet (S\u0142owosie\u0107 4.0)"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/553"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "dictionary"
-        },
-        {
-            "name": "emotional annotations"
-        },
-        {
-            "name": "universal values"
-        },
-        {
-            "name": "emotions"
-        },
-        {
-            "name": "lexical units emotions"
-        }
-    ],
-    "title": [
-        "Emotional Annotations Dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/389e50df-9844-5517-be2c-a7fdf60a0c6e.json b/oaitestdata/clarin-oai_dc/SET_1/json/389e50df-9844-5517-be2c-a7fdf60a0c6e.json
deleted file mode 100644
index efd8bfd2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/389e50df-9844-5517-be2c-a7fdf60a0c6e.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Academy of Sciences"
-    ],
-    "Contributor": [
-        "V\u00e1radi, Tam\u00e1s"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/xml"
-    ],
-    "Language": [
-        "Hungarian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-345",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-345"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-345",
-    "PublicationTimestamp": "2005-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2005"
-    ],
-    "Publisher": [
-        "Academy of Sciences"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Hungary"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-345;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Hungarian National Corpus;V\u00e1radi, Tam\u00e1s;synchronic corpus;Written general synchronic reference corpus; 190m tokens; POS annotated XML;2005;corpus;http://hdl.handle.net/11372/LRT-345;hun;application/xml;downloadable_files_count: 0;Hungary;Academy of Sciences;http://corpus.nytud.hu/mnsz/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "389e50df-9844-5517-be2c-a7fdf60a0c6e",
-    "notes": [
-        "Written general synchronic reference corpus; 190m tokens; POS annotated XML"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-345"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "synchronic corpus"
-        }
-    ],
-    "title": [
-        "Hungarian National Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/38ae3f93-27fc-5d8a-8b3c-c719d96b5341.json b/oaitestdata/clarin-oai_dc/SET_1/json/38ae3f93-27fc-5d8a-8b3c-c719d96b5341.json
deleted file mode 100644
index e9ed5b3f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/38ae3f93-27fc-5d8a-8b3c-c719d96b5341.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2657",
-    "MetadataAccess": [
-        "oai:ota:oucs:2657"
-    ],
-    "PublicationTimestamp": "1765-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1765"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2657;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2657.xml;Thoughts on religion;Swift, Jonathan, 1667-1745;1765;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "38ae3f93-27fc-5d8a-8b3c-c719d96b5341",
-    "oai_identifier": [
-        "oai:ota:oucs:2657"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Thoughts on religion"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2657.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/38e9c5c7-bc94-5803-b6d0-ddbc92be1791.json b/oaitestdata/clarin-oai_dc/SET_1/json/38e9c5c7-bc94-5803-b6d0-ddbc92be1791.json
deleted file mode 100644
index 16f3df8b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/38e9c5c7-bc94-5803-b6d0-ddbc92be1791.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Tilde"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Latvian",
-        "Lithuanian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-558",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-558"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-558",
-    "PublicationTimestamp": "2007-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2007"
-    ],
-    "Publisher": [
-        "Tilde"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Latvia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-558;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Lithuanian-Latvian dictionary;The dictionary is based on Lithuanian-Latvian dictionary (1995) by Jons Balkevi\u010ds, Laimute Balode, Apolonija Boj\u0101te, Valters Subatnieks, ed. by Alberts Sarkanis. It contains ca. 60 00 lexical entries, inclusion of morphlogical analysis tools allows search for word forms.;2007;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-558;lav;lit;application/octet-stream;downloadable_files_count: 0;Latvia;Tilde;http://lietuviu.letonika.lv",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "38e9c5c7-bc94-5803-b6d0-ddbc92be1791",
-    "notes": [
-        "The dictionary is based on Lithuanian-Latvian dictionary (1995) by Jons Balkevi\u010ds, Laimute Balode, Apolonija Boj\u0101te, Valters Subatnieks, ed. by Alberts Sarkanis. It contains ca. 60 00 lexical entries, inclusion of morphlogical analysis tools allows search for word forms."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-558"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Lithuanian-Latvian dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/38ebbb68-89fe-58bd-b2ab-88617cd2fe30.json b/oaitestdata/clarin-oai_dc/SET_1/json/38ebbb68-89fe-58bd-b2ab-88617cd2fe30.json
deleted file mode 100644
index 6faadf35..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/38ebbb68-89fe-58bd-b2ab-88617cd2fe30.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Pisarze"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 58",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/101",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/101"
-    ],
-    "PID": "http://hdl.handle.net/11321/101",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Pisarze"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Pisarze, Pisarze"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/101;2015-06-08T10:53:34Z;hdl_11321_3;hdl_11321_4;MWE Wiek XX;Pisarze, Pisarze;berent_diogenes_1937.txt\r\nberent_kamienie_1918.txt\r\nberent_prochno_1903.txt\r\ndabrowska_nocednie1_1931.txt\r\ndabrowska_nocednie2_1932.txt\r\ndabrowska_nocednie3_1933.txt\r\ndmochowska_dwor_1903.txt\r\ndmochowska_obraczka_1907.txt\r\ndmochowska_odlamana_1914.txt\r\ndomanska_historia_1913.txt\r\ndomanska_krysia_1914.txt\r\ndomanska_paziowie_1910.txt\r\ngojawiczynska_dziewczeta_1935.txt\r\ngojawiczynska_jablon_1937.txt\r\ngojawiczynska_ziemia_1934.txt\r\niwaszkiewicz_czerwone_1934.txt\r\niwaszkiewicz_mlyn_1936.txt\r\niwaszkiewicz_panny_1932.txt\r\nkossak_bog_1935.txt\r\nkossak_oreza_1937.txt\r\nkossak_zmilosci_1925.txt\r\nkrzemieniecka_fatum_1904.txt\r\nkrzemieniecka_odejdzie_1910.txt\r\nkrzemieniecka_wichry_1923.txt\r\nkuncewiczowa_cudzoziemka_1936.txt\r\nkuncewiczowa_ksiezyce_1933.txt\r\nkuncewiczowa_twarz_1928.txt\r\nmakuszynski_basie_1937.txt\r\nmakuszynski_drodze_1917.txt\r\nmakuszynski_szalenstwa_1940.txt\r\nmniszek_gehenna_1914.txt\r\nmniszek_ordynat_1910.txt\r\nmniszek_tredowata_1909.txt\r\nmostowicz_hanki_1939.txt\r\nmostowicz_kariera_1932.txt\r\nmostowicz_murek_1936.txt\r\nnalkowska_granica_1935.txt\r\nnalkowska_kobiety_1906.txt\r\nnalkowska_romans_1923.txt\r\norzeszkowa_gloria_1910.txt\r\nreymont_chlopi_1908.txt\r\nrodziewicz_lato_1920.txt\r\nsamozwaniec_ustach_1922.txt\r\nswietochowski_drygalowie_1914.txt\r\nswietochowski_twinko_1936.txt\r\nsygietynski_ogien_1918.txt\r\nzapolska_smierc_1911.txt\r\nzapolska_tagiejew_1905.txt\r\nzarzycka_dzikuska_1927.txt\r\nzarzycka_irka_1931.txt\r\nzarzycka_wiatr_1934.txt\r\nzeromski_przedwiosnie_1924.txt\r\nzulawski_laus_1914.txt\r\nzulawski_srebrnym_1903.txt\r\nzulawski_zwyciezca_1910.txt;2015-04-08;corpus;http://hdl.handle.net/11321/101;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 58;Pisarze",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "38ebbb68-89fe-58bd-b2ab-88617cd2fe30",
-    "notes": [
-        "berent_diogenes_1937.txt\r\nberent_kamienie_1918.txt\r\nberent_prochno_1903.txt\r\ndabrowska_nocednie1_1931.txt\r\ndabrowska_nocednie2_1932.txt\r\ndabrowska_nocednie3_1933.txt\r\ndmochowska_dwor_1903.txt\r\ndmochowska_obraczka_1907.txt\r\ndmochowska_odlamana_1914.txt\r\ndomanska_historia_1913.txt\r\ndomanska_krysia_1914.txt\r\ndomanska_paziowie_1910.txt\r\ngojawiczynska_dziewczeta_1935.txt\r\ngojawiczynska_jablon_1937.txt\r\ngojawiczynska_ziemia_1934.txt\r\niwaszkiewicz_czerwone_1934.txt\r\niwaszkiewicz_mlyn_1936.txt\r\niwaszkiewicz_panny_1932.txt\r\nkossak_bog_1935.txt\r\nkossak_oreza_1937.txt\r\nkossak_zmilosci_1925.txt\r\nkrzemieniecka_fatum_1904.txt\r\nkrzemieniecka_odejdzie_1910.txt\r\nkrzemieniecka_wichry_1923.txt\r\nkuncewiczowa_cudzoziemka_1936.txt\r\nkuncewiczowa_ksiezyce_1933.txt\r\nkuncewiczowa_twarz_1928.txt\r\nmakuszynski_basie_1937.txt\r\nmakuszynski_drodze_1917.txt\r\nmakuszynski_szalenstwa_1940.txt\r\nmniszek_gehenna_1914.txt\r\nmniszek_ordynat_1910.txt\r\nmniszek_tredowata_1909.txt\r\nmostowicz_hanki_1939.txt\r\nmostowicz_kariera_1932.txt\r\nmostowicz_murek_1936.txt\r\nnalkowska_granica_1935.txt\r\nnalkowska_kobiety_1906.txt\r\nnalkowska_romans_1923.txt\r\norzeszkowa_gloria_1910.txt\r\nreymont_chlopi_1908.txt\r\nrodziewicz_lato_1920.txt\r\nsamozwaniec_ustach_1922.txt\r\nswietochowski_drygalowie_1914.txt\r\nswietochowski_twinko_1936.txt\r\nsygietynski_ogien_1918.txt\r\nzapolska_smierc_1911.txt\r\nzapolska_tagiejew_1905.txt\r\nzarzycka_dzikuska_1927.txt\r\nzarzycka_irka_1931.txt\r\nzarzycka_wiatr_1934.txt\r\nzeromski_przedwiosnie_1924.txt\r\nzulawski_laus_1914.txt\r\nzulawski_srebrnym_1903.txt\r\nzulawski_zwyciezca_1910.txt"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/101"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Wiek XX"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/38ff5acf-74e9-56bb-9c1a-8ea7befe363d.json b/oaitestdata/clarin-oai_dc/SET_1/json/38ff5acf-74e9-56bb-9c1a-8ea7befe363d.json
deleted file mode 100644
index c7a24a6f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/38ff5acf-74e9-56bb-9c1a-8ea7befe363d.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "University of West Bohemia, Department of Cybernetics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 9",
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1588",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1588"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1588",
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "University of West Bohemia, Department of Cybernetics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Tihelka, Daniel",
-        "Matou\u0161ek, Jind\u0159ich"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1588;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;English TTS speech corpus of air traffic (pilot) messages - German accent;Matou\u0161ek, Jind\u0159ich;Tihelka, Daniel;speech corpus;text-to-speech (TTS);pitch-marks;The corpus contains recordings of male speaker, native in German, talking in English. The sentences that were read by the speaker originate in the domain of air traffic control (ATC), specifically the messages used by plane pilots during routine flight. The text in the corpus originates from the transcripts of the real recordings, part of which has been released in LINDAT/CLARIN (http://hdl.handle.net/11858/00-097C-0000-0001-CCA1-0), and individual phrases were selected by special algorithm described in J\u016fzov\u00e1, M. and Tihelka, D.: Minimum Text Corpus Selection for Limited Domain Speech Synthesis (DOI 10.1007/978-3-319-10816-2_48). The corpus was used to create a limited domain speech synthesis system capable of simulating a pilot communication with an ATC officer.;2015-12-11;corpus;http://hdl.handle.net/11234/1-1588;eng;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;application/zip;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain; charset=utf-8;downloadable_files_count: 9;University of West Bohemia, Department of Cybernetics;http://itblp.zcu.cz",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "38ff5acf-74e9-56bb-9c1a-8ea7befe363d",
-    "notes": [
-        "The corpus contains recordings of male speaker, native in German, talking in English. The sentences that were read by the speaker originate in the domain of air traffic control (ATC), specifically the messages used by plane pilots during routine flight. The text in the corpus originates from the transcripts of the real recordings, part of which has been released in LINDAT/CLARIN (http://hdl.handle.net/11858/00-097C-0000-0001-CCA1-0), and individual phrases were selected by special algorithm described in J\u016fzov\u00e1, M. and Tihelka, D.: Minimum Text Corpus Selection for Limited Domain Speech Synthesis (DOI 10.1007/978-3-319-10816-2_48). The corpus was used to create a limited domain speech synthesis system capable of simulating a pilot communication with an ATC officer."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1588"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech corpus"
-        },
-        {
-            "name": "text-to-speech TTS"
-        },
-        {
-            "name": "pitch-marks"
-        }
-    ],
-    "title": [
-        "English TTS speech corpus of air traffic (pilot) messages - German accent"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/39013b6b-5268-53c4-8f4e-03934cea5fce.json b/oaitestdata/clarin-oai_dc/SET_1/json/39013b6b-5268-53c4-8f4e-03934cea5fce.json
deleted file mode 100644
index 1bfcb4f9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/39013b6b-5268-53c4-8f4e-03934cea5fce.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5723",
-    "MetadataAccess": [
-        "oai:ota:oucs:5723"
-    ],
-    "PublicationTimestamp": "1623-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1623"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Shakespeare, William, 1564-1616"
-    ],
-    "fulltext": "oai:ota:oucs:5723;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/5723.xml;Twelfe Night, Or what you will.;Shakespeare, William, 1564-1616;not after: 1623;text_and_corpus_linguistics;Plays -- England -- 16th century;Plays -- England -- 17th century;Comedies -- England -- 16th century;Comedies -- England -- 17th century;Tragedies -- England -- 16th century;Tragedies -- England -- 17th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "39013b6b-5268-53c4-8f4e-03934cea5fce",
-    "oai_identifier": [
-        "oai:ota:oucs:5723"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        },
-        {
-            "name": "Comedies -- England -- th century"
-        },
-        {
-            "name": "Comedies -- England -- th century"
-        },
-        {
-            "name": "Tragedies -- England -- th century"
-        },
-        {
-            "name": "Tragedies -- England -- th century"
-        }
-    ],
-    "title": [
-        "Twelfe Night, Or what you will."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5723.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3922645f-ae14-51e2-a9ac-aa56a655ff70.json b/oaitestdata/clarin-oai_dc/SET_1/json/3922645f-ae14-51e2-a9ac-aa56a655ff70.json
deleted file mode 100644
index 62d4060b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3922645f-ae14-51e2-a9ac-aa56a655ff70.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Ibtikarat team"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/xml",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Arabic"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1942",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1942"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1942",
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Ibtikarat team"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)",
-        "http://creativecommons.org/licenses/by-nc/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Loukili, Taoufik"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1942;2017-02-06T11:05:21Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Arabic Proclitics Lexicon;Loukili, Taoufik;proclitics;An XML-based file containing all Arabic proclitics;2014;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1942;ara;Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0);http://creativecommons.org/licenses/by-nc/4.0/;PUB;text/xml;text/plain; charset=utf-8;downloadable_files_count: 1;Ibtikarat team;http://arabic.emi.ac.ma/ibtikarat/?q=Resources",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3922645f-ae14-51e2-a9ac-aa56a655ff70",
-    "notes": [
-        "An XML-based file containing all Arabic proclitics"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1942"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "proclitics"
-        }
-    ],
-    "title": [
-        "Arabic Proclitics Lexicon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3948fe69-1070-531b-820d-5201ab234424.json b/oaitestdata/clarin-oai_dc/SET_1/json/3948fe69-1070-531b-820d-5201ab234424.json
deleted file mode 100644
index 05bda3ab..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3948fe69-1070-531b-820d-5201ab234424.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Ewa Dulna-Rak"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/richtext",
-        "downloadable_files_count: 206"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/319",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/319"
-    ],
-    "PID": "http://hdl.handle.net/11321/319",
-    "PublicationTimestamp": "2016-07-24T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Ewa Dulna-Rak"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Dulna-Rak, Ewa"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/319;2016-08-11T17:56:45Z;hdl_11321_3;hdl_11321_4;Aleksander Zelwerowicz - teksty teatralne;Dulna-Rak, Ewa;theatre;Teksty teatralne Aleksandra Zelwerowicza;2016-07-24;corpus;http://hdl.handle.net/11321/319;pol;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;text/plain; charset=utf-8;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;downloadable_files_count: 206;Ewa Dulna-Rak",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3948fe69-1070-531b-820d-5201ab234424",
-    "notes": [
-        "Teksty teatralne Aleksandra Zelwerowicza"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/319"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "theatre"
-        }
-    ],
-    "title": [
-        "Aleksander Zelwerowicz - teksty teatralne"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3960adc9-c4ae-543c-af58-e76dced22e77.json b/oaitestdata/clarin-oai_dc/SET_1/json/3960adc9-c4ae-543c-af58-e76dced22e77.json
deleted file mode 100644
index eaf52fd4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3960adc9-c4ae-543c-af58-e76dced22e77.json
+++ /dev/null
@@ -1,92 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 4",
-        "application/pdf",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1084",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1084"
-    ],
-    "PID": "http://hdl.handle.net/11356/1084",
-    "PublicationTimestamp": "2016-12-30T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "http://nl.ijs.si/janes/viri/rocno-oznaceni-korpusi/#Janes-Norm",
-        "https://doi.org/10.1007/s10579-018-9425-z",
-        "http://hdl.handle.net/11356/1083",
-        "http://hdl.handle.net/11356/1080"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by-sa/4.0/"
-    ],
-    "author": [
-        "\u010cibej, Jaka",
-        "Erjavec, Toma\u017e",
-        "Fi\u0161er, Darja",
-        "Arhar Holdt, \u0160pela"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1084;2018-10-24T20:55:34Z;hdl_11356_1023;hdl_11356_1024;CMC training corpus Janes-Norm 1.2;Erjavec, Toma\u017e;Fi\u0161er, Darja;\u010cibej, Jaka;Arhar Holdt, \u0160pela;computer-mediated communication;tokenisation;word normalisation;manual annotation;TEI;Janes-Norm is a manually annotated corpus of Slovene Computer-Mediated Communication (CMC). It is meant as a gold-standard training and testing dataset for tokenisation, sentence segmentation and word normalisation of non-standard Slovene. As the corpus has been carefully manually annotated, it is also suitable for detailed linguistic explorations which require highly accurate and reliable annotations.\r\n\r\nA slightly older version of this corpus is described in:\r\nERJAVEC, Toma\u017e, \u010cIBEJ, Jaka, ARHAR HOLDT, \u0160pela, LJUBE\u0160I\u0106, Nikola, FI\u0160ER, Darja. Gold-standard datasets for annotation of Slovene computer-mediated communication. In Proceedings of RASLAN 2016: Recent Advances in Slavonic Natural Language Processing. Brno: Tribun EU, 2016, pp. 29-40, https://nlp.fi.muni.cz/raslan/raslan16.pdf\r\n\r\nNote that the corpus is also annotated with morphosyntactic descriptions and lemmas. These annotations are manual where the texts correspond to the Janes-Tag corpus (http://hdl.handle.net/11356/1085) and automatic for the other texts.;2016-12-30;corpus;http://hdl.handle.net/11356/1084;slv;http://nl.ijs.si/janes/viri/rocno-oznaceni-korpusi/#Janes-Norm;https://doi.org/10.1007/s10579-018-9425-z;http://hdl.handle.net/11356/1083;http://hdl.handle.net/11356/1080;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);PUB;https://creativecommons.org/licenses/by-sa/4.0/;application/pdf;application/pdf;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 4;Jo\u017eef Stefan Institute;http://nl.ijs.si/janes/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3960adc9-c4ae-543c-af58-e76dced22e77",
-    "notes": [
-        "Janes-Norm is a manually annotated corpus of Slovene Computer-Mediated Communication (CMC). It is meant as a gold-standard training and testing dataset for tokenisation, sentence segmentation and word normalisation of non-standard Slovene. As the corpus has been carefully manually annotated, it is also suitable for detailed linguistic explorations which require highly accurate and reliable annotations.\r\n\r\nA slightly older version of this corpus is described in:\r\nERJAVEC, Toma\u017e, \u010cIBEJ, Jaka, ARHAR HOLDT, \u0160pela, LJUBE\u0160I\u0106, Nikola, FI\u0160ER, Darja. Gold-standard datasets for annotation of Slovene computer-mediated communication. In Proceedings of RASLAN 2016: Recent Advances in Slavonic Natural Language Processing. Brno: Tribun EU, 2016, pp. 29-40, https://nlp.fi.muni.cz/raslan/raslan16.pdf\r\n\r\nNote that the corpus is also annotated with morphosyntactic descriptions and lemmas. These annotations are manual where the texts correspond to the Janes-Tag corpus (http://hdl.handle.net/11356/1085) and automatic for the other texts."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1084"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "computer-mediated communication"
-        },
-        {
-            "name": "tokenisation"
-        },
-        {
-            "name": "word normalisation"
-        },
-        {
-            "name": "manual annotation"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "CMC training corpus Janes-Norm 1.2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3962234c-6b3b-5eef-8d32-6062e0b2c461.json b/oaitestdata/clarin-oai_dc/SET_1/json/3962234c-6b3b-5eef-8d32-6062e0b2c461.json
deleted file mode 100644
index bb2df3e9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3962234c-6b3b-5eef-8d32-6062e0b2c461.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Bergen University Library"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml",
-        "downloadable_files_count: 1",
-        "text/plain"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/81",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/81"
-    ],
-    "PID": "http://hdl.handle.net/11509/81",
-    "PublicationTimestamp": "2005-02-14T11:59:59Z",
-    "PublicationYear": [
-        "2005"
-    ],
-    "Publisher": [
-        "Bergen University Library"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0)",
-        "http://creativecommons.org/licenses/by-nc/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Moreau, Francois"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/81;2016-04-15T05:59:20Z;hdl_11509_1;hdl_11509_2;UBB-1576-02-23.xml;Moreau, Francois;Charter;Transcription of charter in Bergen University Library Special Collections.;2005-02-14;corpus;http://hdl.handle.net/11509/81;deu;Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0);http://creativecommons.org/licenses/by-nc/3.0/;CC;text/xml;text/plain;downloadable_files_count: 1;Bergen University Library;http://ub.uib.no/diplom/transkripsjon/UBB-1576-02-23.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3962234c-6b3b-5eef-8d32-6062e0b2c461",
-    "notes": [
-        "Transcription of charter in Bergen University Library Special Collections."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/81"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Charter"
-        }
-    ],
-    "title": [
-        "UBB-1576-02-23.xml"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/39655141-6b08-589d-a729-032960d7835c.json b/oaitestdata/clarin-oai_dc/SET_1/json/39655141-6b08-589d-a729-032960d7835c.json
deleted file mode 100644
index 953d2120..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/39655141-6b08-589d-a729-032960d7835c.json
+++ /dev/null
@@ -1,213 +0,0 @@
-{
-    "Contact": [
-        "Universal Dependencies Consortium"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 3"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)",
-        "Arabic",
-        "Basque",
-        "Bulgarian",
-        "Croatian",
-        "Czech",
-        "Danish",
-        "Dutch",
-        "English",
-        "Estonian",
-        "Finnish",
-        "French",
-        "German",
-        "Gothic",
-        "Modern Greek (1453-)",
-        "Hebrew",
-        "Hindi",
-        "Hungarian",
-        "Indonesian",
-        "Irish",
-        "Italian",
-        "Japanese",
-        "Latin",
-        "Norwegian",
-        "Church Slavic",
-        "Persian",
-        "Polish",
-        "Portuguese",
-        "Romanian",
-        "Slovenian",
-        "Spanish",
-        "Swedish",
-        "Tamil"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1548",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1548"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1548",
-    "PublicationTimestamp": "2015-11-15T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Universal Dependencies Consortium"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/LRT-1478",
-        "http://hdl.handle.net/11234/1-1699"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Licence Universal Dependencies v1.2",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-1.2",
-        "PUB"
-    ],
-    "author": [
-        "Ion, Radu",
-        "Seraji, Mojgan",
-        "Manning, Christopher",
-        "Passarotti, Marco",
-        "Zhu, Hanzhi",
-        "Osenova, Petya",
-        "Agi\u0107, \u017deljko",
-        "Simionescu, Radu",
-        "Montemagni, Simonetta",
-        "Seeker, Wolfgang",
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "Irimia, Elena",
-        "Simk\u00f3, Katalin",
-        "Krek, Simon",
-        "Suhr, Alane",
-        "Galbraith, Daniel",
-        "Lenci, Alessandro",
-        "Mititelu, Verginica",
-        "Erjavec, Toma\u017e",
-        "Mart\u00ednez Alonso, H\u00e9ctor",
-        "Schuster, Sebastian",
-        "Haug, Dag",
-        "Lynn, Teresa",
-        "Plank, Barbara",
-        "Gojenola, Koldo",
-        "Varga, Viktor",
-        "M\u0103r\u0103nduc, C\u0103t\u0103lina",
-        "Pyysalo, Sampo",
-        "Kanerva, Jenna",
-        "Sz\u00e1nt\u00f3, Zsolt",
-        "Haji\u010d, Jan",
-        "Ma\u0161ek, Jan",
-        "Atutxa, Aitziber",
-        "Goldberg, Yoav",
-        "Matsumoto, Yuji",
-        "Dozat, Timothy",
-        "Bauer, John",
-        "Asahara, Masayuki",
-        "Nivre, Joakim",
-        "Zeman, Daniel",
-        "Petrov, Slav",
-        "Guillaume, Bruno",
-        "Prokopidis, Prokopis",
-        "de Marneffe, Marie-Catherine",
-        "\u0160t\u011bp\u00e1nek, Jan",
-        "Perez, Cenel-Augusto",
-        "Laippala, Veronika",
-        "McDonald, Ryan",
-        "Farkas, Rich\u00e1rd",
-        "Ramasamy, Loganathan",
-        "Bosco, Cristina",
-        "Ginter, Filip",
-        "Mori, Shunsuke",
-        "Piitulainen, Jussi",
-        "Tanaka, Takaaki",
-        "Miyao, Yusuke",
-        "Vincze, Veronika",
-        "Bhat, Riyaz Ahmad",
-        "Tsarfaty, Reut",
-        "Goenaga, Iakes",
-        "Johannsen, Anders",
-        "Connor, Miriam",
-        "Mare\u010dek, David",
-        "Smith, Aaron",
-        "\u00d8vrelid, Lilja",
-        "Celano, Giuseppe G. A.",
-        "Dobrovoljc, Kaja",
-        "Popel, Martin",
-        "Missil\u00e4, Anna",
-        "Simov, Kiril",
-        "Ballesteros, Miguel",
-        "Nurmi, Hanna",
-        "Uematsu, Sumire",
-        "Gonzales, Berta",
-        "Diaz de Ilarraza, Arantza",
-        "Rosa, Rudolf",
-        "Aranzabe, Maria Jesus",
-        "Saleh, Shadi",
-        "Simi, Maria",
-        "Bengoetxea, Kepa",
-        "Pascual, Elena",
-        "Foster, Jennifer",
-        "Uria, Larraitz",
-        "Ljube\u0161i\u0107, Nikola",
-        "Kanayama, Hiroshi",
-        "Bowman, Sam",
-        "Silveira, Natalia"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1548;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Universal Dependencies 1.2;Nivre, Joakim;Agi\u0107, \u017deljko;Aranzabe, Maria Jesus;Asahara, Masayuki;Atutxa, Aitziber;Ballesteros, Miguel;Bauer, John;Bengoetxea, Kepa;Bhat, Riyaz Ahmad;Bosco, Cristina;Bowman, Sam;Celano, Giuseppe G. A.;Connor, Miriam;de Marneffe, Marie-Catherine;Diaz de Ilarraza, Arantza;Dobrovoljc, Kaja;Dozat, Timothy;Erjavec, Toma\u017e;Farkas, Rich\u00e1rd;Foster, Jennifer;Galbraith, Daniel;Ginter, Filip;Goenaga, Iakes;Gojenola, Koldo;Goldberg, Yoav;Gonzales, Berta;Guillaume, Bruno;Haji\u010d, Jan;Haug, Dag;Ion, Radu;Irimia, Elena;Johannsen, Anders;Kanayama, Hiroshi;Kanerva, Jenna;Krek, Simon;Laippala, Veronika;Lenci, Alessandro;Ljube\u0161i\u0107, Nikola;Lynn, Teresa;Manning, Christopher;M\u0103r\u0103nduc, C\u0103t\u0103lina;Mare\u010dek, David;Mart\u00ednez Alonso, H\u00e9ctor;Ma\u0161ek, Jan;Matsumoto, Yuji;McDonald, Ryan;Missil\u00e4, Anna;Mititelu, Verginica;Miyao, Yusuke;Montemagni, Simonetta;Mori, Shunsuke;Nurmi, Hanna;Osenova, Petya;\u00d8vrelid, Lilja;Pascual, Elena;Passarotti, Marco;Perez, Cenel-Augusto;Petrov, Slav;Piitulainen, Jussi;Plank, Barbara;Popel, Martin;Prokopidis, Prokopis;Pyysalo, Sampo;Ramasamy, Loganathan;Rosa, Rudolf;Saleh, Shadi;Schuster, Sebastian;Seeker, Wolfgang;Seraji, Mojgan;Silveira, Natalia;Simi, Maria;Simionescu, Radu;Simk\u00f3, Katalin;Simov, Kiril;Smith, Aaron;\u0160t\u011bp\u00e1nek, Jan;Suhr, Alane;Sz\u00e1nt\u00f3, Zsolt;Tanaka, Takaaki;Tsarfaty, Reut;Uematsu, Sumire;Uria, Larraitz;Varga, Viktor;Vincze, Veronika;\u017dabokrtsk\u00fd, Zden\u011bk;Zeman, Daniel;Zhu, Hanzhi;treebank;dependency;syntax;morphology;harmonized annotation;interset;universal tagset;stanford dependencies;Universal Dependencies is a project that seeks to develop cross-linguistically consistent treebank annotation for many languages, with the goal of facilitating multilingual parser development, cross-lingual learning, and parsing research from a language typology perspective. The annotation scheme is based on (universal) Stanford dependencies (de Marneffe et al., 2006, 2008, 2014), Google universal part-of-speech tags (Petrov et al., 2012), and the Interset interlingua for morphosyntactic tagsets (Zeman, 2008).;2015-11-15;corpus;http://hdl.handle.net/11234/1-1548;grc;ara;eus;bul;hrv;ces;dan;nld;eng;est;fin;fra;deu;got;ell;heb;hin;hun;ind;gle;ita;jpn;lat;nor;chu;fas;pol;por;ron;slv;spa;swe;tam;http://hdl.handle.net/11234/LRT-1478;http://hdl.handle.net/11234/1-1699;Licence Universal Dependencies v1.2;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-1.2;PUB;text/plain; charset=utf-8;application/x-gzip;application/x-gzip;application/x-gzip;downloadable_files_count: 3;Universal Dependencies Consortium;http://universaldependencies.github.io/docs/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "39655141-6b08-589d-a729-032960d7835c",
-    "notes": [
-        "Universal Dependencies is a project that seeks to develop cross-linguistically consistent treebank annotation for many languages, with the goal of facilitating multilingual parser development, cross-lingual learning, and parsing research from a language typology perspective. The annotation scheme is based on (universal) Stanford dependencies (de Marneffe et al., 2006, 2008, 2014), Google universal part-of-speech tags (Petrov et al., 2012), and the Interset interlingua for morphosyntactic tagsets (Zeman, 2008)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1548"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "dependency"
-        },
-        {
-            "name": "syntax"
-        },
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "harmonized annotation"
-        },
-        {
-            "name": "interset"
-        },
-        {
-            "name": "universal tagset"
-        },
-        {
-            "name": "stanford dependencies"
-        }
-    ],
-    "title": [
-        "Universal Dependencies 1.2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/399045b1-5576-53ea-954e-724202cb73ed.json b/oaitestdata/clarin-oai_dc/SET_1/json/399045b1-5576-53ea-954e-724202cb73ed.json
deleted file mode 100644
index 48f754fe..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/399045b1-5576-53ea-954e-724202cb73ed.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 745 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1829",
-    "MetadataAccess": [
-        "oai:ota:oucs:1829"
-    ],
-    "PublicationTimestamp": "1721-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1721"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Defoe, Daniel, 1661?-1731"
-    ],
-    "fulltext": "oai:ota:oucs:1829;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/1829.xml;The history and misfortunes of the famous Moll Flanders, etc. / by Daniel Defoe;Defoe, Daniel, 1661?-1731;1721;text_and_corpus_linguistics;Fiction -- England -- 18th century;Picaresque fiction -- England -- 18th century;eng;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 745 KB);Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "399045b1-5576-53ea-954e-724202cb73ed",
-    "oai_identifier": [
-        "oai:ota:oucs:1829"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- England -- th century"
-        },
-        {
-            "name": "Picaresque fiction -- England -- th century"
-        }
-    ],
-    "title": [
-        "The history and misfortunes of the famous Moll Flanders, etc. / by Daniel Defoe"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1829.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/39af0098-aaa4-5ca6-ad6c-7edd91a90368.json b/oaitestdata/clarin-oai_dc/SET_1/json/39af0098-aaa4-5ca6-ad6c-7edd91a90368.json
deleted file mode 100644
index d1c907fd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/39af0098-aaa4-5ca6-ad6c-7edd91a90368.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=a3c297c4486111e2a2aa782bcb07413510a103f90b964b3aa62a658afe18f904",
-    "MetadataAccess": [
-        "a3c297c4486111e2a2aa782bcb07413510a103f90b964b3aa62a658afe18f904"
-    ],
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "a3c297c4486111e2a2aa782bcb07413510a103f90b964b3aa62a658afe18f904;2019-02-27T12:09:24Z;corpus;corpus:text;LT Corpus;The LT Corpus (Literary Corpus) contains approximately 1,781,083 running words of European and Brazilian Portuguese. It includes 70 copyright-free classics (61 Portugal and 9 from Brazil) published before 1940.;2015-12-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "39af0098-aaa4-5ca6-ad6c-7edd91a90368",
-    "notes": [
-        "The LT Corpus (Literary Corpus) contains approximately 1,781,083 running words of European and Brazilian Portuguese. It includes 70 copyright-free classics (61 Portugal and 9 from Brazil) published before 1940."
-    ],
-    "oai_identifier": [
-        "a3c297c4486111e2a2aa782bcb07413510a103f90b964b3aa62a658afe18f904"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "LT Corpus"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/39c95468-24f8-548e-a237-26ce21e46630.json b/oaitestdata/clarin-oai_dc/SET_1/json/39c95468-24f8-548e-a237-26ce21e46630.json
deleted file mode 100644
index 8da95ed6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/39c95468-24f8-548e-a237-26ce21e46630.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Russian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1038",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1038"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1038",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1038;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;L1 Acquisition Stoll;Language Acquisition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1038;rus;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI10214%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "39c95468-24f8-548e-a237-26ce21e46630",
-    "notes": [
-        "Language Acquisition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1038"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "L1 Acquisition Stoll"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/39dbea79-489d-51a7-b9c6-5f0173e84e62.json b/oaitestdata/clarin-oai_dc/SET_1/json/39dbea79-489d-51a7-b9c6-5f0173e84e62.json
deleted file mode 100644
index 2e24f00c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/39dbea79-489d-51a7-b9c6-5f0173e84e62.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3744",
-    "MetadataAccess": [
-        "oai:ota:oucs:3744"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Garrick, David, 1717-1779."
-    ],
-    "fulltext": "oai:ota:oucs:3744;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3744.xml;The sick monkey, a fable;Garrick, David, 1717-1779.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "39dbea79-489d-51a7-b9c6-5f0173e84e62",
-    "oai_identifier": [
-        "oai:ota:oucs:3744"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The sick monkey, a fable"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3744.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/39e120b2-70ad-54e6-8afb-182f929e2303.json b/oaitestdata/clarin-oai_dc/SET_1/json/39e120b2-70ad-54e6-8afb-182f929e2303.json
deleted file mode 100644
index d303bac8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/39e120b2-70ad-54e6-8afb-182f929e2303.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "The Research Institute for the Languages of Finland"
-    ],
-    "Contributor": [
-        "Alanen, Timo"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Finnish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-839",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-839"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-839",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "The Research Institute for the Languages of Finland"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Finland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-839;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Johan Habermans land survey register of Pien-Savo district from 1620s (= Ed. Timo Alanen 2004: Johan Habermanin maantarkastuslue;Alanen, Timo;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-839;fin;downloadable_files_count: 0;Finland;The Research Institute for the Languages of Finland;http://scripta.kotus.fi/www/verkkojulkaisut/julk2/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "39e120b2-70ad-54e6-8afb-182f929e2303",
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-839"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Johan Habermans land survey register of Pien-Savo district from 1620s (= Ed. Timo Alanen 2004: Johan Habermanin maantarkastuslue"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3a4416c0-272d-5d45-8db7-7a3711cdc768.json b/oaitestdata/clarin-oai_dc/SET_1/json/3a4416c0-272d-5d45-8db7-7a3711cdc768.json
deleted file mode 100644
index 834d263b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3a4416c0-272d-5d45-8db7-7a3711cdc768.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "between 512 KB and 1 MB "
-    ],
-    "Language": [],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0404",
-    "MetadataAccess": [
-        "oai:ota:oucs:0404"
-    ],
-    "PublicationTimestamp": "1140-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1140"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Devotional literature"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Unknown"
-    ],
-    "fulltext": "oai:ota:oucs:0404;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0404.xml; Li quatre livre des Reis  / compiled by Clive Roderick Sneddon;Unknown;1140;text_and_corpus_linguistics;Devotional literature -- France -- 12th century;xno;Oxford Text Archive, University of Oxford;between 512 KB and 1 MB ;Text;Devotional literature;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3a4416c0-272d-5d45-8db7-7a3711cdc768",
-    "oai_identifier": [
-        "oai:ota:oucs:0404"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Devotional literature -- France -- th century"
-        }
-    ],
-    "title": [
-        " Li quatre livre des Reis  / compiled by Clive Roderick Sneddon"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0404.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3a8fb5ba-9ed2-51f1-a13b-0f949570164f.json b/oaitestdata/clarin-oai_dc/SET_1/json/3a8fb5ba-9ed2-51f1-a13b-0f949570164f.json
deleted file mode 100644
index 89673656..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3a8fb5ba-9ed2-51f1-a13b-0f949570164f.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Fakult\u00e4t Geisteswissenschaften, Universit\u00e4t Duisburg-Essen",
-        "Korpora.org"
-    ],
-    "Contributor": [
-        "Schr\u00f6der, Prof. Dr. Bernhard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1123",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1123"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1123",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Fakult\u00e4t Geisteswissenschaften, Universit\u00e4t Duisburg-Essen",
-        "Korpora.org"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1123;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LIMAS Corpus;Schr\u00f6der, Prof. Dr. Bernhard;Germanistik;1970s \"representative\" corpus of German created by the research group \"Linguistik und Maschinelle Sprachbearbeitung\" (linguistics and language processing); Zeitschnittkorpus der deutschen Schriftsprache von 1970; Querschnitt durch verschiedene Textsorten;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1123;deu;downloadable_files_count: 0;Germany;Korpora.org;Fakult\u00e4t Geisteswissenschaften, Universit\u00e4t Duisburg-Essen;http://www.korpora.org/Limas",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3a8fb5ba-9ed2-51f1-a13b-0f949570164f",
-    "notes": [
-        "1970s \"representative\" corpus of German created by the research group \"Linguistik und Maschinelle Sprachbearbeitung\" (linguistics and language processing); Zeitschnittkorpus der deutschen Schriftsprache von 1970; Querschnitt durch verschiedene Textsorten"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1123"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "LIMAS Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3a92f7c4-d3cb-5abb-b5b5-604539fe33cc.json b/oaitestdata/clarin-oai_dc/SET_1/json/3a92f7c4-d3cb-5abb-b5b5-604539fe33cc.json
deleted file mode 100644
index 7aca4a0e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3a92f7c4-d3cb-5abb-b5b5-604539fe33cc.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/octet-stream",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/258",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/258"
-    ],
-    "PID": "http://hdl.handle.net/11321/258",
-    "PublicationTimestamp": "2016-05-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "Woli\u0144ski, Marcin"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/258;2016-05-13T13:26:13Z;hdl_11321_3;hdl_11321_4;\u015awigra;Woli\u0144ski, Marcin;syntax;Polish;parser;constituency grammar;\u015awigra is a parser of Polish generating constituency trees using a DCG style grammar stemming from Marek \u015awidzi\u0144ski\u2019s grammar \u201cGramatyka formalna j\u0119zyka polskiego\u201d (1992). The grammar was heavily rewritten for the purpose of annotating the Sk\u0142adnica treebank. The structure of trees was simplified with respect to \u015awidzi\u0144ski\u2019s version, many new types of constructions were included (in particular various forms of coordinated structures), a statistical disambiguating component was added. Moreover, the Clarin version of \u015awigra uses the valency dictionary Walenty developed within Clarin.;2016-05-01;languageDescription;http://hdl.handle.net/11321/258;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/zip;application/octet-stream;application/octet-stream;downloadable_files_count: 1;Institute of Computer Science, Polish Academy of Sciences;http://zil.ipipan.waw.pl/%C5%9Awigra",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3a92f7c4-d3cb-5abb-b5b5-604539fe33cc",
-    "notes": [
-        "\u015awigra is a parser of Polish generating constituency trees using a DCG style grammar stemming from Marek \u015awidzi\u0144ski\u2019s grammar \u201cGramatyka formalna j\u0119zyka polskiego\u201d (1992). The grammar was heavily rewritten for the purpose of annotating the Sk\u0142adnica treebank. The structure of trees was simplified with respect to \u015awidzi\u0144ski\u2019s version, many new types of constructions were included (in particular various forms of coordinated structures), a statistical disambiguating component was added. Moreover, the Clarin version of \u015awigra uses the valency dictionary Walenty developed within Clarin."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/258"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "syntax"
-        },
-        {
-            "name": "Polish"
-        },
-        {
-            "name": "parser"
-        },
-        {
-            "name": "constituency grammar"
-        }
-    ],
-    "title": [
-        "\u015awigra"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3a9f41cf-33a5-5504-bd7e-32610131fe94.json b/oaitestdata/clarin-oai_dc/SET_1/json/3a9f41cf-33a5-5504-bd7e-32610131fe94.json
deleted file mode 100644
index 2b0ab9e2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3a9f41cf-33a5-5504-bd7e-32610131fe94.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "The Department of Modern Languages, University of Helsinki",
-        "University of Helsinki"
-    ],
-    "Contributor": [
-        "Kopotev, Mikhail",
-        "Mustajoki, Arto"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Russian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-755",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-755"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-755",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "The Department of Modern Languages, University of Helsinki",
-        "University of Helsinki"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Finland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-755;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Progress test on Russian language KARTTU;Kopotev, Mikhail;Mustajoki, Arto;Progress test on language competence in Russian;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-755;rus;application/octet-stream;downloadable_files_count: 0;Finland;The Department of Modern Languages, University of Helsinki;University of Helsinki;http://www.helsinki.fi/venaja/english/e-material/karttu.htm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3a9f41cf-33a5-5504-bd7e-32610131fe94",
-    "notes": [
-        "Progress test on language competence in Russian"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-755"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Progress test on Russian language KARTTU"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3aa3fdd5-6892-57ef-9416-871374ce66db.json b/oaitestdata/clarin-oai_dc/SET_1/json/3aa3fdd5-6892-57ef-9416-871374ce66db.json
deleted file mode 100644
index 0006ced8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3aa3fdd5-6892-57ef-9416-871374ce66db.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5253",
-    "MetadataAccess": [
-        "oai:ota:oucs:5253"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Holcroft, Thomas, 1745-1809."
-    ],
-    "fulltext": "oai:ota:oucs:5253;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5253.xml;Anna St. Ives: a novel. By Thomas Holcroft. ... [pt.5];Holcroft, Thomas, 1745-1809.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3aa3fdd5-6892-57ef-9416-871374ce66db",
-    "oai_identifier": [
-        "oai:ota:oucs:5253"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Anna St. Ives: a novel. By Thomas Holcroft. ... [pt.5]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5253.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3acb782d-1f44-5ca0-a1b0-27bdbaeb82e5.json b/oaitestdata/clarin-oai_dc/SET_1/json/3acb782d-1f44-5ca0-a1b0-27bdbaeb82e5.json
deleted file mode 100644
index d671d826..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3acb782d-1f44-5ca0-a1b0-27bdbaeb82e5.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 63.3 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2156",
-    "MetadataAccess": [
-        "oai:ota:oucs:2156"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gaskell, Elizabeth Cleghorn, 1810-1865"
-    ],
-    "fulltext": "oai:ota:oucs:2156;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/2156.xml;The Manchester marriage / by Elizabeth Gaskell;Gaskell, Elizabeth Cleghorn, 1810-1865;text_and_corpus_linguistics;Fiction -- Great Britain -- 19th century;Short stories -- Great Britain -- 19th century;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 63.3 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3acb782d-1f44-5ca0-a1b0-27bdbaeb82e5",
-    "oai_identifier": [
-        "oai:ota:oucs:2156"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- Great Britain -- th century"
-        },
-        {
-            "name": "Short stories -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "The Manchester marriage / by Elizabeth Gaskell"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2156.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3b200a6c-14e1-5328-96a7-b6eb25e67b02.json b/oaitestdata/clarin-oai_dc/SET_1/json/3b200a6c-14e1-5328-96a7-b6eb25e67b02.json
deleted file mode 100644
index d40b029b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3b200a6c-14e1-5328-96a7-b6eb25e67b02.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4017",
-    "MetadataAccess": [
-        "oai:ota:oucs:4017"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Burke, Edmund, 1729-1797."
-    ],
-    "fulltext": "oai:ota:oucs:4017;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4017.xml;A letter from the Right Hon. Edmund Burke, M.P. in the kingdom of Great Britain, to Sir Hercules Langrishe: Bart. M.P. on the subject of Roman Catholics of Ireland, and the propriety of admitting them to the elective franchise, consistently with the principles of the constitution as established at the Revolution.;Burke, Edmund, 1729-1797.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3b200a6c-14e1-5328-96a7-b6eb25e67b02",
-    "oai_identifier": [
-        "oai:ota:oucs:4017"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A letter from the Right Hon. Edmund Burke, M.P. in the kingdom of Great Britain, to Sir Hercules Langrishe: Bart. M.P. on the subject of Roman Catholics of Ireland, and the propriety of admitting them to the elective franchise, consistently with the principles of the constitution as established at the Revolution."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4017.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3b20b206-1e50-562c-a5ea-40e7324d5904.json b/oaitestdata/clarin-oai_dc/SET_1/json/3b20b206-1e50-562c-a5ea-40e7324d5904.json
deleted file mode 100644
index 82381568..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3b20b206-1e50-562c-a5ea-40e7324d5904.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5128",
-    "MetadataAccess": [
-        "oai:ota:oucs:5128"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Sterne, Laurence, 1713-1768."
-    ],
-    "fulltext": "oai:ota:oucs:5128;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5128.xml;Explanatory remarks upon The life and opinions of Tristram Shandy: wherein, the morals and politics of this piece are clearly laid open, by Jeremiah Kunastrokius, M.D.;Sterne, Laurence, 1713-1768.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3b20b206-1e50-562c-a5ea-40e7324d5904",
-    "oai_identifier": [
-        "oai:ota:oucs:5128"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Explanatory remarks upon The life and opinions of Tristram Shandy: wherein, the morals and politics of this piece are clearly laid open, by Jeremiah Kunastrokius, M.D."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5128.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3b2ea980-482f-56b0-b73c-34aa30ad6483.json b/oaitestdata/clarin-oai_dc/SET_1/json/3b2ea980-482f-56b0-b73c-34aa30ad6483.json
deleted file mode 100644
index 6520021a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3b2ea980-482f-56b0-b73c-34aa30ad6483.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain",
-        "(1 file : ca. 25.3 KB)"
-    ],
-    "Language": [
-        "Middle English (1100-1500)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1323",
-    "MetadataAccess": [
-        "oai:ota:oucs:1323"
-    ],
-    "PublicationTimestamp": "1120-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1120"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:1323;2018-03-07T12:15:11Z;http://ota.ox.ac.uk/headers/1323.xml;Sawles warde;Sawles warde;1120-1141;text_and_corpus_linguistics;Devotional literature -- England -- 13th century;Allegories -- England -- 13th century;enm;A 13th century rendering, with considerable variations and additions, of Hugo of St. Victor's De anima, book 4, chapters 13-15 ;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 25.3 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3b2ea980-482f-56b0-b73c-34aa30ad6483",
-    "notes": [
-        "A 13th century rendering, with considerable variations and additions, of Hugo of St. Victor's De anima, book 4, chapters 13-15 "
-    ],
-    "oai_identifier": [
-        "oai:ota:oucs:1323"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Devotional literature -- England -- th century"
-        },
-        {
-            "name": "Allegories -- England -- th century"
-        }
-    ],
-    "title": [
-        "Sawles warde",
-        "Sawles warde"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1323.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3b40d76a-b08e-5abf-94f0-8ab60f97fa6d.json b/oaitestdata/clarin-oai_dc/SET_1/json/3b40d76a-b08e-5abf-94f0-8ab60f97fa6d.json
deleted file mode 100644
index 7127e648..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3b40d76a-b08e-5abf-94f0-8ab60f97fa6d.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1674",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1674"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1674",
-    "PublicationTimestamp": "2016-03-10T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11858/00-097C-0000-0023-68D8-1",
-        "http://hdl.handle.net/11234/1-1836"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Straka, Milan",
-        "Strakov\u00e1, Jana"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1674;2018-07-02T22:05:53Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Czech Models (MorfFlex CZ 160310 + PDT 3.0) for MorphoDiTa 160310;Straka, Milan;Strakov\u00e1, Jana;MorphoDiTa;Czech;morphological analysis;morphological generation;PoS tagging;Czech models for MorphoDiTa, providing morphological analysis, morphological generation and part-of-speech tagging.\r\n\r\nThe morphological dictionary is created from MorfFlex CZ 160310 and the PoS tagger is trained on Prague Dependency Treebank 3.0 (PDT).;2016-03-10;languageDescription;http://hdl.handle.net/11234/1-1674;ces;http://hdl.handle.net/11858/00-097C-0000-0023-68D8-1;http://hdl.handle.net/11234/1-1836;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/morphodita/users-manual#czech-morfflex-pdt",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3b40d76a-b08e-5abf-94f0-8ab60f97fa6d",
-    "notes": [
-        "Czech models for MorphoDiTa, providing morphological analysis, morphological generation and part-of-speech tagging.\r\n\r\nThe morphological dictionary is created from MorfFlex CZ 160310 and the PoS tagger is trained on Prague Dependency Treebank 3.0 (PDT)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1674"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "MorphoDiTa"
-        },
-        {
-            "name": "Czech"
-        },
-        {
-            "name": "morphological analysis"
-        },
-        {
-            "name": "morphological generation"
-        },
-        {
-            "name": "PoS tagging"
-        }
-    ],
-    "title": [
-        "Czech Models (MorfFlex CZ 160310 + PDT 3.0) for MorphoDiTa 160310"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3b648756-54f5-51c4-9972-d4bd59198b88.json b/oaitestdata/clarin-oai_dc/SET_1/json/3b648756-54f5-51c4-9972-d4bd59198b88.json
deleted file mode 100644
index af65a0d9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3b648756-54f5-51c4-9972-d4bd59198b88.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3050",
-    "MetadataAccess": [
-        "oai:ota:oucs:3050"
-    ],
-    "PublicationTimestamp": "1909-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1909"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Montgomery, Lucy Maud, 1874-1942"
-    ],
-    "fulltext": "oai:ota:oucs:3050;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3050.xml;Anne of Avonlea;Montgomery, Lucy Maud, 1874-1942;not after: 1909;text_and_corpus_linguistics;Children's literature, Canadian -- 20th century;eng;Oxford Text Archive, University of Oxford;Triggs, Jeffery;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3b648756-54f5-51c4-9972-d4bd59198b88",
-    "oai_identifier": [
-        "oai:ota:oucs:3050"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Childrens literature"
-        },
-        {
-            "name": "Canadian -- th century"
-        }
-    ],
-    "title": [
-        "Anne of Avonlea"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3050.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3b83268e-c7d3-5e2c-bb2f-11a2160edd66.json b/oaitestdata/clarin-oai_dc/SET_1/json/3b83268e-c7d3-5e2c-bb2f-11a2160edd66.json
deleted file mode 100644
index 7a50cb9a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3b83268e-c7d3-5e2c-bb2f-11a2160edd66.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5190",
-    "MetadataAccess": [
-        "oai:ota:oucs:5190"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dennis, John, 1657-1734."
-    ],
-    "fulltext": "oai:ota:oucs:5190;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5190.xml;The advancement and reformation of modern poetry: A critical discourse. In two parts. ... By Mr Dennis.;Dennis, John, 1657-1734.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3b83268e-c7d3-5e2c-bb2f-11a2160edd66",
-    "oai_identifier": [
-        "oai:ota:oucs:5190"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The advancement and reformation of modern poetry: A critical discourse. In two parts. ... By Mr Dennis."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5190.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3b86d718-0d9a-5a59-b7a4-38c52f57be9d.json b/oaitestdata/clarin-oai_dc/SET_1/json/3b86d718-0d9a-5a59-b7a4-38c52f57be9d.json
deleted file mode 100644
index b9833bf7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3b86d718-0d9a-5a59-b7a4-38c52f57be9d.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4038",
-    "MetadataAccess": [
-        "oai:ota:oucs:4038"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Garrick, David, 1717-1779."
-    ],
-    "fulltext": "oai:ota:oucs:4038;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4038.xml;May-day: or, the little gipsy: A musical farce, of one act. To which is added The theatrical candidates. A musical prelude. As they are both performed at the Theatre-Royal, in Drury-Lane.;Garrick, David, 1717-1779.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3b86d718-0d9a-5a59-b7a4-38c52f57be9d",
-    "oai_identifier": [
-        "oai:ota:oucs:4038"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "May-day: or, the little gipsy: A musical farce, of one act. To which is added The theatrical candidates. A musical prelude. As they are both performed at the Theatre-Royal, in Drury-Lane."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4038.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3b8e956a-7225-57bb-96da-cdfc2577d263.json b/oaitestdata/clarin-oai_dc/SET_1/json/3b8e956a-7225-57bb-96da-cdfc2577d263.json
deleted file mode 100644
index 1887856b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3b8e956a-7225-57bb-96da-cdfc2577d263.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Prus"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/108",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/108"
-    ],
-    "PID": "http://hdl.handle.net/11321/108",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Prus"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Prus, Prus"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/108;2015-04-14T12:56:11Z;hdl_11321_3;hdl_11321_4;MWE Prus, Lalka;Prus, Prus;Prus;2015-04-08;corpus;http://hdl.handle.net/11321/108;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;application/zip;text/plain; charset=utf-8;downloadable_files_count: 2;Prus",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3b8e956a-7225-57bb-96da-cdfc2577d263",
-    "notes": [
-        "Prus"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/108"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Prus, Lalka"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3b97b8e9-27fc-51df-8341-653688bbcaa0.json b/oaitestdata/clarin-oai_dc/SET_1/json/3b97b8e9-27fc-51df-8341-653688bbcaa0.json
deleted file mode 100644
index 9f14e3aa..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3b97b8e9-27fc-51df-8341-653688bbcaa0.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml",
-        "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
-        "application/xml-dtd",
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 5",
-        "application/pdf"
-    ],
-    "Language": [
-        "Danish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repository.clarin.dk:20.500.12115/26",
-    "MetadataAccess": [
-        "oai:repository.clarin.dk:20.500.12115/26"
-    ],
-    "PID": "http://hdl.handle.net/20.500.12115/26",
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Pedersen, Bolette Sandford",
-        "Nimb, Sanni",
-        "Hansen, Dorte Haltrup",
-        "Olsen, Sussi"
-    ],
-    "fulltext": "oai:repository.clarin.dk:20.500.12115/26;2018-06-28T13:27:59Z;hdl_20.500.12115_1;hdl_20.500.12115_3;STO semantics (The Danish SIMPLE Lexicon) - LMF format;Pedersen, Bolette Sandford;Olsen, Sussi;Nimb, Sanni;Hansen, Dorte Haltrup;semantics;LMF;The language specific encodings in The Danish SIMPLE Lexicon are performed on the basis of a unified, ontology-based semantic model - the so-called SIMPLE model - representing an extended Qualia Structure based partly on Pustejovsky (1995), partly on experiences in preceding lexical projects such as Genelex, WordNet and EuroWordNet.\r\nThe SIMPLE project started in April 1998 and was completed in April 2000.\r\nThe Danish SIMPLE Lexicon was ajusted and converted to LMF in the METANORD-project i 2014. App 10,000 senses are mapped to the syntax layer in STO (6943 nouns, 2000 verbs and 1000 adjectives).;2014;lexicalConceptualResource;http://hdl.handle.net/20.500.12115/26;dan;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;PUB;text/plain; charset=utf-8;text/xml;application/pdf;application/vnd.openxmlformats-officedocument.spreadsheetml.sheet;application/xml-dtd;application/pdf;downloadable_files_count: 5;Centre for Language Technology, NorS, University of Copenhagen",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3b97b8e9-27fc-51df-8341-653688bbcaa0",
-    "notes": [
-        "The language specific encodings in The Danish SIMPLE Lexicon are performed on the basis of a unified, ontology-based semantic model - the so-called SIMPLE model - representing an extended Qualia Structure based partly on Pustejovsky (1995), partly on experiences in preceding lexical projects such as Genelex, WordNet and EuroWordNet.\r\nThe SIMPLE project started in April 1998 and was completed in April 2000.\r\nThe Danish SIMPLE Lexicon was ajusted and converted to LMF in the METANORD-project i 2014. App 10,000 senses are mapped to the syntax layer in STO (6943 nouns, 2000 verbs and 1000 adjectives)."
-    ],
-    "oai_identifier": [
-        "oai:repository.clarin.dk:20.500.12115/26"
-    ],
-    "oai_set": [
-        "hdl_20.500.12115_1",
-        "hdl_20.500.12115_3"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "semantics"
-        },
-        {
-            "name": "LMF"
-        }
-    ],
-    "title": [
-        "STO semantics (The Danish SIMPLE Lexicon) - LMF format"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3ba9312d-daf0-5470-aaae-5827e2f0956e.json b/oaitestdata/clarin-oai_dc/SET_1/json/3ba9312d-daf0-5470-aaae-5827e2f0956e.json
deleted file mode 100644
index d462339e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3ba9312d-daf0-5470-aaae-5827e2f0956e.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Survey of English Usage, University College London"
-    ],
-    "Contributor": [
-        "Arts, Bas"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-887",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-887"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-887",
-    "PublicationTimestamp": "1998-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1998"
-    ],
-    "Publisher": [
-        "Survey of English Usage, University College London"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-887;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;International Corpus of English: UK (ICE-GB);Arts, Bas;1 million words spoken and written English from UK. POS-tagged and parsed. Digitised speech recordings aligned w text. Part of the International Corpus of English (ICE).;1998;corpus;http://hdl.handle.net/11372/LRT-887;eng;downloadable_files_count: 0;United Kingdom;Survey of English Usage, University College London;http://www.ucl.ac.uk/english-usage/projects/ice-gb/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3ba9312d-daf0-5470-aaae-5827e2f0956e",
-    "notes": [
-        "1 million words spoken and written English from UK. POS-tagged and parsed. Digitised speech recordings aligned w text. Part of the International Corpus of English (ICE)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-887"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "International Corpus of English: UK (ICE-GB)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3bac1f1e-a200-590c-b7f7-035f45aed618.json b/oaitestdata/clarin-oai_dc/SET_1/json/3bac1f1e-a200-590c-b7f7-035f45aed618.json
deleted file mode 100644
index 7ffb7b77..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3bac1f1e-a200-590c-b7f7-035f45aed618.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "A"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1726",
-    "MetadataAccess": [
-        "oai:ota:oucs:1726"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Montgomery, Lucy Maud"
-    ],
-    "fulltext": "oai:ota:oucs:1726;2018-05-17T09:29:11Z;http://ota.ox.ac.uk/headers/1726.xml;Anne of Avonlea;Montgomery, Lucy Maud;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;A;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3bac1f1e-a200-590c-b7f7-035f45aed618",
-    "oai_identifier": [
-        "oai:ota:oucs:1726"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Anne of Avonlea"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1726.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3bdffa2b-027a-5c53-8279-14766ba9c85f.json b/oaitestdata/clarin-oai_dc/SET_1/json/3bdffa2b-027a-5c53-8279-14766ba9c85f.json
deleted file mode 100644
index ff187d8c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3bdffa2b-027a-5c53-8279-14766ba9c85f.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Wytw\u00f3rnia Film\u00f3w Dokumentalnych i Fabularnych",
-        "Polish-Japanese Academy of Information Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/plain",
-        "downloadable_files_count: 2"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/426",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/426"
-    ],
-    "PID": "http://hdl.handle.net/11321/426",
-    "PublicationTimestamp": "2017-10-06T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Wytw\u00f3rnia Film\u00f3w Dokumentalnych i Fabularnych",
-        "Polish-Japanese Academy of Information Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0)",
-        "http://creativecommons.org/licenses/by-nc/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Kor\u017einek, Danijel"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/426;2017-10-06T20:11:06Z;hdl_11321_3;hdl_11321_4;Transkrypcja fonetyczna Kronik RP;Kor\u017einek, Danijel;phonetics;This is a phonetic transcription of the \"Kroniki RP\" data set using the G2P tool available at mowa.clarin-pl.eu.;2017-10-06;corpus;http://hdl.handle.net/11321/426;pol;Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0);http://creativecommons.org/licenses/by-nc/3.0/;CC;text/plain; charset=utf-8;text/plain;text/plain;downloadable_files_count: 2;Polish-Japanese Academy of Information Technology;Wytw\u00f3rnia Film\u00f3w Dokumentalnych i Fabularnych",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3bdffa2b-027a-5c53-8279-14766ba9c85f",
-    "notes": [
-        "This is a phonetic transcription of the \"Kroniki RP\" data set using the G2P tool available at mowa.clarin-pl.eu."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/426"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "phonetics"
-        }
-    ],
-    "title": [
-        "Transkrypcja fonetyczna Kronik RP"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3be03295-01d8-5d47-acb8-236ef0b2339e.json b/oaitestdata/clarin-oai_dc/SET_1/json/3be03295-01d8-5d47-acb8-236ef0b2339e.json
deleted file mode 100644
index 06315c4b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3be03295-01d8-5d47-acb8-236ef0b2339e.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Akademicka"
-    ],
-    "Contributor": [
-        "Heski, J\u00f3zef Ksawery (17..-ca 1810). Il."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229158",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229158"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D04-4",
-    "PublicationTimestamp": "1756-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1756"
-    ],
-    "Publisher": [
-        "Drukarnia Akademicka"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/229158",
-        "oai:jbc.bj.uj.edu.pl:publication:240802"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1701/1800"
-    ],
-    "TempCoverageBegin": 53662478399,
-    "TempCoverageEnd": 53662478399,
-    "TemporalCoverage": " point in time : 1701-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1701-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1701-07-01T11:59:59Z",
-    "author": [
-        "Szyszko, Donat (1709-1773)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229158;2019-03-01T12:46:31Z;Droga W Prawo do fortunney wieczno\u015b\u0107i y na krok nie z drogi; bo Tr\u00f3ykrzy\u017cast\u0105 Gimbutow Podkow\u0105, Ju\u017c do mety z\u0142otego wieku, Ju\u017c do zamierzonego po\u0107iech Niebieskich celu, y terminu, zabieraj\u0105cemu \u015bi\u0119 [...] Grzegorzowi Antoniemu Kunasewiczowi Gimbutowi [...] Utorowana;Szyszko, Donat (1709-1773);starodruki 18\u00a0w.;Gimbuttowa, R\u00f3\u017ca. Adr. ded.;Drukarnia Akademicka;Heski, J\u00f3zef Ksawery (17..-ca 1810). Il.;[1756];starodruk;application/xml;clarind-uds:poldilemma-229158;hdl:11858/00-246C-0000-0023-8D04-4;Biblioteka Jagiello\u0144ska, BJ St. Dr. 589424 III;pol;http://jbc.bj.uj.edu.pl/Content/229158;oai:jbc.bj.uj.edu.pl:publication:240802;1701/1800;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3be03295-01d8-5d47-acb8-236ef0b2339e",
-    "notes": [
-        "Gimbuttowa, R\u00f3\u017ca. Adr. ded."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229158"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Droga W Prawo do fortunney wieczno\u015b\u0107i y na krok nie z drogi; bo Tr\u00f3ykrzy\u017cast\u0105 Gimbutow Podkow\u0105, Ju\u017c do mety z\u0142otego wieku, Ju\u017c do zamierzonego po\u0107iech Niebieskich celu, y terminu, zabieraj\u0105cemu \u015bi\u0119 [...] Grzegorzowi Antoniemu Kunasewiczowi Gimbutowi [...] Utorowana"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3be56ee7-be68-591b-b450-4527c70c94f0.json b/oaitestdata/clarin-oai_dc/SET_1/json/3be56ee7-be68-591b-b450-4527c70c94f0.json
deleted file mode 100644
index 9f1dded9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3be56ee7-be68-591b-b450-4527c70c94f0.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "University of Stuttgart"
-    ],
-    "Contributor": [
-        "Schmid, Helmut"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-309",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-309"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-309",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Stuttgart"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-309;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Stuttgart Finite State Transducer Tools;Schmid, Helmut;SFST is a finite state transducer toolkit for the implementation of morphologies and other applications of finite state transducers. SFST comprises a compiler and several tools for transforming, printing and applying transducers.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-309;downloadable_files_count: 0;Germany;University of Stuttgart;http://www.ims.uni-stuttgart.de/projekte/gramotron/SOFTWARE/SFST.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3be56ee7-be68-591b-b450-4527c70c94f0",
-    "notes": [
-        "SFST is a finite state transducer toolkit for the implementation of morphologies and other applications of finite state transducers. SFST comprises a compiler and several tools for transforming, printing and applying transducers."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-309"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Stuttgart Finite State Transducer Tools"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3c441bd7-e8ff-5478-8dfc-7f18787aa021.json b/oaitestdata/clarin-oai_dc/SET_1/json/3c441bd7-e8ff-5478-8dfc-7f18787aa021.json
deleted file mode 100644
index e62ef10b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3c441bd7-e8ff-5478-8dfc-7f18787aa021.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "Contributor": [
-        "Zinn, Claus"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-329",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-329"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-329",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-329;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;ViCoS: Visualizing Conceptual Spaces;Zinn, Claus;lexical relations;annotation tool;Extension of LEXUS to define semantic relations between lexical entries within or across lexica;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-329;downloadable_files_count: 0;Netherlands (the);Max Planck Institute for Psycholinguistics;http://tla.mpi.nl/tools/tla-tools/lexus/vicos/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3c441bd7-e8ff-5478-8dfc-7f18787aa021",
-    "notes": [
-        "Extension of LEXUS to define semantic relations between lexical entries within or across lexica"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-329"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "lexical relations"
-        },
-        {
-            "name": "annotation tool"
-        }
-    ],
-    "title": [
-        "ViCoS: Visualizing Conceptual Spaces"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3c51d9a3-3beb-5e8e-b970-3b8fc14d368d.json b/oaitestdata/clarin-oai_dc/SET_1/json/3c51d9a3-3beb-5e8e-b970-3b8fc14d368d.json
deleted file mode 100644
index ca6b3427..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3c51d9a3-3beb-5e8e-b970-3b8fc14d368d.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Machine Learning and NLP group at Trento"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English",
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-322",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-322"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-322",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Machine Learning and NLP group at Trento"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-322;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;SenTube;sentiment analysis;Sentiment analysis of Youtube videos with joint models of text and speech;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-322;eng;ita;downloadable_files_count: 0;Machine Learning and NLP group at Trento;http://disi.unitn.it/~haponchyk/ikernels/projects/sentube/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3c51d9a3-3beb-5e8e-b970-3b8fc14d368d",
-    "notes": [
-        "Sentiment analysis of Youtube videos with joint models of text and speech"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-322"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "sentiment analysis"
-        }
-    ],
-    "title": [
-        "SenTube"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3c5f6d5f-4dac-5929-8c6e-292ae6e8ec8f.json b/oaitestdata/clarin-oai_dc/SET_1/json/3c5f6d5f-4dac-5929-8c6e-292ae6e8ec8f.json
deleted file mode 100644
index 26236893..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3c5f6d5f-4dac-5929-8c6e-292ae6e8ec8f.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contributor": [
-        "Wynne, Martin"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-217",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-217"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-217",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-217;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TRACTOR;Wynne, Martin;Corpora, lexical resources;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-217;downloadable_files_count: 0;United Kingdom;http://www.ahds.ac.uk/litlangling",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3c5f6d5f-4dac-5929-8c6e-292ae6e8ec8f",
-    "notes": [
-        "Corpora, lexical resources"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-217"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TRACTOR"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3c6e16ae-5d19-53e3-a2be-82693f616872.json b/oaitestdata/clarin-oai_dc/SET_1/json/3c6e16ae-5d19-53e3-a2be-82693f616872.json
deleted file mode 100644
index 2b8642fa..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3c6e16ae-5d19-53e3-a2be-82693f616872.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-953",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-953"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-953",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-953;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Phrygian;ca. 4.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-953;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#phryg",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3c6e16ae-5d19-53e3-a2be-82693f616872",
-    "notes": [
-        "ca. 4.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-953"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Phrygian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3c87962f-482a-5a09-b689-c60e8c19accc.json b/oaitestdata/clarin-oai_dc/SET_1/json/3c87962f-482a-5a09-b689-c60e8c19accc.json
deleted file mode 100644
index daad65e5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3c87962f-482a-5a09-b689-c60e8c19accc.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/588",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/588"
-    ],
-    "PID": "http://hdl.handle.net/11321/588",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "Woli\u0144ski, Marcin"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/588;2018-07-27T08:58:36Z;hdl_11321_3;hdl_11321_4;\u015awigra \u2014 a parser of Polish;Woli\u0144ski, Marcin;parser;Polish;constituency parsing;syntax;\u015awigra is a parser of Polish generating constituency trees using a DCG style grammar stemming from Marek \u015awidzi\u0144ski\u2019s grammar \u201cGramatyka formalna j\u0119zyka polskiego\u201d (1992). The grammar was heavily rewritten for the purpose of annotating the Sk\u0142adnica treebank. The structure of trees was simplified with respect to \u015awidzi\u0144ski\u2019s version, many new types of constructions were included (in particular various forms of coordinated structures), a statistical disambiguating component was added. Moreover, the Clarin version of \u015awigra uses the valency dictionary Walenty developed within Clarin.;2018-07;languageDescription;http://hdl.handle.net/11321/588;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;Institute of Computer Science, Polish Academy of Sciences;http://zil.ipipan.waw.pl/%C5%9Awigra",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3c87962f-482a-5a09-b689-c60e8c19accc",
-    "notes": [
-        "\u015awigra is a parser of Polish generating constituency trees using a DCG style grammar stemming from Marek \u015awidzi\u0144ski\u2019s grammar \u201cGramatyka formalna j\u0119zyka polskiego\u201d (1992). The grammar was heavily rewritten for the purpose of annotating the Sk\u0142adnica treebank. The structure of trees was simplified with respect to \u015awidzi\u0144ski\u2019s version, many new types of constructions were included (in particular various forms of coordinated structures), a statistical disambiguating component was added. Moreover, the Clarin version of \u015awigra uses the valency dictionary Walenty developed within Clarin."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/588"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parser"
-        },
-        {
-            "name": "Polish"
-        },
-        {
-            "name": "constituency parsing"
-        },
-        {
-            "name": "syntax"
-        }
-    ],
-    "title": [
-        "\u015awigra \u2014 a parser of Polish"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3c99d0f3-1d44-5de6-b26a-6b49225106b9.json b/oaitestdata/clarin-oai_dc/SET_1/json/3c99d0f3-1d44-5de6-b26a-6b49225106b9.json
deleted file mode 100644
index aaab6b76..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3c99d0f3-1d44-5de6-b26a-6b49225106b9.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "less than 512 KB"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0296",
-    "MetadataAccess": [
-        "oai:ota:oucs:0296"
-    ],
-    "PublicationYear": [
-        "270 BCE"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Herodas"
-    ],
-    "fulltext": "oai:ota:oucs:0296;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0296.xml; Mimiamboi / compiled by Thesaurus Linguae Graecae;The mimes of Herodas;Herodas;270 BCE;text_and_corpus_linguistics;Plays -- 3rd century B.C.;grc;Oxford Text Archive, University of Oxford;less than 512 KB;Text;Plays;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3c99d0f3-1d44-5de6-b26a-6b49225106b9",
-    "oai_identifier": [
-        "oai:ota:oucs:0296"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- rd century B.C."
-        }
-    ],
-    "title": [
-        " Mimiamboi / compiled by Thesaurus Linguae Graecae",
-        "The mimes of Herodas"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0296.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3ca411ec-e97f-5c15-a81c-6e8ad80f169e.json b/oaitestdata/clarin-oai_dc/SET_1/json/3ca411ec-e97f-5c15-a81c-6e8ad80f169e.json
deleted file mode 100644
index 519426c6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3ca411ec-e97f-5c15-a81c-6e8ad80f169e.json
+++ /dev/null
@@ -1,94 +0,0 @@
-{
-    "Contact": [
-        "Uppsala University"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 5",
-        "application/zip",
-        "application/x-gzip",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "English",
-        "French",
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2394",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2394"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2394",
-    "PublicationTimestamp": "2017-09-20T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Uppsala University"
-    ],
-    "RelatedIdentifier": [
-        "http://aclweb.org/anthology/W/W16/W16-2345.pdf"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Hardmeier, Christian",
-        "Cettolo, Mauro",
-        "Stymne, Sara",
-        "Nakov, Preslav",
-        "Tiedemann, J\u00f6rg",
-        "Webber, Bonnie",
-        "Guillou, Liane",
-        "Versley, Yannick",
-        "Popescu-Belis, Andrei"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2394;2017-09-22T09:21:10Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;DiscoMT 2016 Shared Task on Cross-lingual Pronoun Prediction;Guillou, Liane;Hardmeier, Christian;Nakov, Preslav;Stymne, Sara;Tiedemann, J\u00f6rg;Versley, Yannick;Cettolo, Mauro;Webber, Bonnie;Popescu-Belis, Andrei;machine translation;coreference;discourse;pronouns;Files for the DiscoMT 2016 shared task on cross-lingual pronoun prediction;2017-09-20;corpus;http://hdl.handle.net/11372/LRT-2394;eng;fra;deu;http://aclweb.org/anthology/W/W16/W16-2345.pdf;Creative Commons - Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0);http://creativecommons.org/licenses/by-nc-nd/4.0/;PUB;application/octet-stream;application/x-gzip;application/x-gzip;application/zip;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 5;Uppsala University;http://www.statmt.org/wmt16/pronoun-task.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3ca411ec-e97f-5c15-a81c-6e8ad80f169e",
-    "notes": [
-        "Files for the DiscoMT 2016 shared task on cross-lingual pronoun prediction"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2394"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "coreference"
-        },
-        {
-            "name": "discourse"
-        },
-        {
-            "name": "pronouns"
-        }
-    ],
-    "title": [
-        "DiscoMT 2016 Shared Task on Cross-lingual Pronoun Prediction"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3ca473ac-6c0d-5bad-9634-ffddfcd4e954.json b/oaitestdata/clarin-oai_dc/SET_1/json/3ca473ac-6c0d-5bad-9634-ffddfcd4e954.json
deleted file mode 100644
index 00f2e5f5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3ca473ac-6c0d-5bad-9634-ffddfcd4e954.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technolgy"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/15",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/15"
-    ],
-    "PID": "http://hdl.handle.net/11321/15",
-    "PublicationTimestamp": "2012-04-18T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technolgy"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Radziszewski, Adam"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/15;2014-09-30T13:07:50Z;hdl_11321_3;hdl_11321_4;IOBBER;Radziszewski, Adam;IOBBER is a chunker for Polish. Its job is to recognise syntactic phrases (chunks) in Polish text.\r\nThe name comes from IOB tags that are assigned to tokens to represent chunks (strictly speaking, we use IOB2 representation).\r\nHere is an example sentence annotated with NP and VP chunks:;2012-04-18;toolService;http://hdl.handle.net/11321/15;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;downloadable_files_count: 0;Wroc\u0142aw University of Technolgy;Wroc\u0142aw University of Technolgy;http://nlp.pwr.wroc.pl/redmine/projects/iobber/wiki",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3ca473ac-6c0d-5bad-9634-ffddfcd4e954",
-    "notes": [
-        "IOBBER is a chunker for Polish. Its job is to recognise syntactic phrases (chunks) in Polish text.\r\nThe name comes from IOB tags that are assigned to tokens to represent chunks (strictly speaking, we use IOB2 representation).\r\nHere is an example sentence annotated with NP and VP chunks:"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/15"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "IOBBER"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3cb195c2-1adf-5039-b420-5b812bc17f19.json b/oaitestdata/clarin-oai_dc/SET_1/json/3cb195c2-1adf-5039-b420-5b812bc17f19.json
deleted file mode 100644
index d51aea07..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3cb195c2-1adf-5039-b420-5b812bc17f19.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German",
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1049",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1049"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1049",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1049;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Blingual Language Acquisition Julka Corpus;Language Acquisition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1049;deu;pol;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI519685%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3cb195c2-1adf-5039-b420-5b812bc17f19",
-    "notes": [
-        "Language Acquisition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1049"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Blingual Language Acquisition Julka Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3cbc9823-e23e-5dc8-a82b-18a76292dc12.json b/oaitestdata/clarin-oai_dc/SET_1/json/3cbc9823-e23e-5dc8-a82b-18a76292dc12.json
deleted file mode 100644
index 29ddc537..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3cbc9823-e23e-5dc8-a82b-18a76292dc12.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology",
-        "University of Lodz"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/pdf"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/549",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/549"
-    ],
-    "PID": "http://hdl.handle.net/11321/549",
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology",
-        "University of Lodz"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0)",
-        "http://creativecommons.org/licenses/by-nc/3.0/",
-        "CC"
-    ],
-    "author": [
-        "P\u0119zik, Piotr"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/549;2018-07-23T11:54:59Z;hdl_11321_3;hdl_11321_4;HaskPL;P\u0119zik, Piotr;collocation dictionary;phraseological database;HaskPL is a Polish phraseological database designed for language professionals including linguists, language teachers, lexicographers, language materials developers and translators. Query results can be visualised and exported as spreadsheets. A complementary tool is HaskProof (http://pelcra.clarin-pl.eu:9894/#/lang/pl) identifying potential collocations in any text inserted by the user.;2013;toolService;http://hdl.handle.net/11321/549;pol;Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0);http://creativecommons.org/licenses/by-nc/3.0/;CC;text/plain; charset=utf-8;application/pdf;downloadable_files_count: 1;University of Lodz;Wroc\u0142aw University of Technology;http://pelcra.clarin-pl.eu/hask_pl/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3cbc9823-e23e-5dc8-a82b-18a76292dc12",
-    "notes": [
-        "HaskPL is a Polish phraseological database designed for language professionals including linguists, language teachers, lexicographers, language materials developers and translators. Query results can be visualised and exported as spreadsheets. A complementary tool is HaskProof (http://pelcra.clarin-pl.eu:9894/#/lang/pl) identifying potential collocations in any text inserted by the user."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/549"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "collocation dictionary"
-        },
-        {
-            "name": "phraseological database"
-        }
-    ],
-    "title": [
-        "HaskPL"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3cd2ed55-f2d4-5684-a256-10ca55c17019.json b/oaitestdata/clarin-oai_dc/SET_1/json/3cd2ed55-f2d4-5684-a256-10ca55c17019.json
deleted file mode 100644
index 15f7d8a5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3cd2ed55-f2d4-5684-a256-10ca55c17019.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5191",
-    "MetadataAccess": [
-        "oai:ota:oucs:5191"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dennis, John, 1657-1734."
-    ],
-    "fulltext": "oai:ota:oucs:5191;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5191.xml;The battle of Ramillia: or, the power of union. A poem. In five books. By Mr. Dennis.;Dennis, John, 1657-1734.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3cd2ed55-f2d4-5684-a256-10ca55c17019",
-    "oai_identifier": [
-        "oai:ota:oucs:5191"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The battle of Ramillia: or, the power of union. A poem. In five books. By Mr. Dennis."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5191.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3cd5e0e5-f584-5678-96b8-ac6b18013f1b.json b/oaitestdata/clarin-oai_dc/SET_1/json/3cd5e0e5-f584-5678-96b8-ac6b18013f1b.json
deleted file mode 100644
index 5cb33c55..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3cd5e0e5-f584-5678-96b8-ac6b18013f1b.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "University of Leipzig"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1150",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1150"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1150",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Leipzig"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1150;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Wortschatz-Portal der Universit\u00e4t Leipzig;Germanistik;Angabe von Wort, Anzahl, H\u00e4ufigkeitsklasse, Beschreibung, Sachgebiet, Morphologie, Relationen zu anderen W\u00f6rtern (z. B. Synonymie), Links zu anderen W\u00f6rtern, Dornseiff-Bedeutungsgruppen, Beispielen (u.a. entnommen aus spiegel.de, sueddeutsche.de), signifikanten Kookkurenzen, signifikanten linken und rechten Nachbarn;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1150;deu;downloadable_files_count: 0;Germany;University of Leipzig;http://wortschatz.uni-leipzig.de/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3cd5e0e5-f584-5678-96b8-ac6b18013f1b",
-    "notes": [
-        "Angabe von Wort, Anzahl, H\u00e4ufigkeitsklasse, Beschreibung, Sachgebiet, Morphologie, Relationen zu anderen W\u00f6rtern (z. B. Synonymie), Links zu anderen W\u00f6rtern, Dornseiff-Bedeutungsgruppen, Beispielen (u.a. entnommen aus spiegel.de, sueddeutsche.de), signifikanten Kookkurenzen, signifikanten linken und rechten Nachbarn"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1150"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Wortschatz-Portal der Universit\u00e4t Leipzig"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3ce471af-6dae-57b4-bc57-bfe72b047735.json b/oaitestdata/clarin-oai_dc/SET_1/json/3ce471af-6dae-57b4-bc57-bfe72b047735.json
deleted file mode 100644
index b93bb2cd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3ce471af-6dae-57b4-bc57-bfe72b047735.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3741",
-    "MetadataAccess": [
-        "oai:ota:oucs:3741"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Francklin, Thomas, 1721-1784."
-    ],
-    "fulltext": "oai:ota:oucs:3741;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3741.xml;A sermon preach'd at the parish church of St. Peter's Cornhill; on the Sunday after the late dreadful fire in that neighbourhood. By Thomas Francklin,;Francklin, Thomas, 1721-1784.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3ce471af-6dae-57b4-bc57-bfe72b047735",
-    "oai_identifier": [
-        "oai:ota:oucs:3741"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A sermon preach'd at the parish church of St. Peter's Cornhill; on the Sunday after the late dreadful fire in that neighbourhood. By Thomas Francklin,"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3741.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3d0279c8-7a4b-5cca-adcc-2b9165763aab.json b/oaitestdata/clarin-oai_dc/SET_1/json/3d0279c8-7a4b-5cca-adcc-2b9165763aab.json
deleted file mode 100644
index 1cebb0f4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3d0279c8-7a4b-5cca-adcc-2b9165763aab.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3767",
-    "MetadataAccess": [
-        "oai:ota:oucs:3767"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Berkeley, George, 1733-1795."
-    ],
-    "fulltext": "oai:ota:oucs:3767;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3767.xml;An inquiry into the origin of episcopacy, in a discourse preached in June, 1790. By a dignitary of the Church of England;Berkeley, George, 1733-1795.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3d0279c8-7a4b-5cca-adcc-2b9165763aab",
-    "oai_identifier": [
-        "oai:ota:oucs:3767"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An inquiry into the origin of episcopacy, in a discourse preached in June, 1790. By a dignitary of the Church of England"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3767.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3d13d21e-766d-5371-a13c-63002ad4fec9.json b/oaitestdata/clarin-oai_dc/SET_1/json/3d13d21e-766d-5371-a13c-63002ad4fec9.json
deleted file mode 100644
index 6e0c78ae..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3d13d21e-766d-5371-a13c-63002ad4fec9.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Amebis, d. o. o., Kamnik"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1185",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1185"
-    ],
-    "PID": "http://hdl.handle.net/11356/1185",
-    "PublicationTimestamp": "2018-04-15T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Amebis, d. o. o., Kamnik"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11356/1055",
-        "http://www.sdjt.si/wp/wp-content/uploads/2018/09/JTDH-2018_Holozan_Zbirka-primerov-rabe-vejice-Vejica-1-3.pdf"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Holozan, Peter"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1185;2018-10-18T23:18:20Z;hdl_11356_1023;hdl_11356_1024;Corpus of comma placement Vejica 1.3;Holozan, Peter;comma placement;error annotation;manual annotation;A collection of sentences demonstrating and correcting comma usage.\r\nThe sentences come from five sources:\r\n- KUST: a Slovene learner corpus, http://nl.ijs.si/isjt06/proc/26_Stritar.pdf\r\n- \u0160olar: a corpus of student writing, http://www.slovenscina.eu/korpusi/solar\r\n- Lektor: a corpus of proof-reading corrections, http://www.slovenscina.eu/korpusi/lektor\r\n- Wikipedija: https://sl.wikipedia.org/wiki/Glavna_stran\r\n- Janes: Tweet comma corpus Janes-Vejica 1.0, http://hdl.handle.net/11356/1088\r\nFor Janes, the comma corrections from the source corpus were used. For Lektor, the comma corrections of proof-readers were used, and additional corrections added by Peter Holozan. For other texts, the comma errors were manually marked by Peter Holozan.;2018-04-15;corpus;http://hdl.handle.net/11356/1185;slv;http://hdl.handle.net/11356/1055;http://www.sdjt.si/wp/wp-content/uploads/2018/09/JTDH-2018_Holozan_Zbirka-primerov-rabe-vejice-Vejica-1-3.pdf;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);https://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;text/plain;application/zip;text/plain; charset=utf-8;downloadable_files_count: 2;Amebis, d. o. o., Kamnik;http://peter.amebis.si/vejica.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3d13d21e-766d-5371-a13c-63002ad4fec9",
-    "notes": [
-        "A collection of sentences demonstrating and correcting comma usage.\r\nThe sentences come from five sources:\r\n- KUST: a Slovene learner corpus, http://nl.ijs.si/isjt06/proc/26_Stritar.pdf\r\n- \u0160olar: a corpus of student writing, http://www.slovenscina.eu/korpusi/solar\r\n- Lektor: a corpus of proof-reading corrections, http://www.slovenscina.eu/korpusi/lektor\r\n- Wikipedija: https://sl.wikipedia.org/wiki/Glavna_stran\r\n- Janes: Tweet comma corpus Janes-Vejica 1.0, http://hdl.handle.net/11356/1088\r\nFor Janes, the comma corrections from the source corpus were used. For Lektor, the comma corrections of proof-readers were used, and additional corrections added by Peter Holozan. For other texts, the comma errors were manually marked by Peter Holozan."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1185"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "comma placement"
-        },
-        {
-            "name": "error annotation"
-        },
-        {
-            "name": "manual annotation"
-        }
-    ],
-    "title": [
-        "Corpus of comma placement Vejica 1.3"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3d3514b8-780e-50fc-87a5-8827307f82e9.json b/oaitestdata/clarin-oai_dc/SET_1/json/3d3514b8-780e-50fc-87a5-8827307f82e9.json
deleted file mode 100644
index cc29a3d5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3d3514b8-780e-50fc-87a5-8827307f82e9.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 892 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2212",
-    "MetadataAccess": [
-        "oai:ota:oucs:2212"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Philosophical texts -- Great Britain -- 18th century"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Smith, Adam, 1723-1790"
-    ],
-    "fulltext": "oai:ota:oucs:2212;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/2212.xml;The theory of moral sentiments / by Adam Smith;Smith, Adam, 1723-1790;default: 1976-01-01;text_and_corpus_linguistics;Academic dissertations -- Great Britain -- 18th century;eng;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 892 KB);Text;Philosophical texts -- Great Britain -- 18th century;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3d3514b8-780e-50fc-87a5-8827307f82e9",
-    "oai_identifier": [
-        "oai:ota:oucs:2212"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Academic dissertations -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "The theory of moral sentiments / by Adam Smith"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2212.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3d4c0039-4f48-57ac-aec5-1d10e6223ce4.json b/oaitestdata/clarin-oai_dc/SET_1/json/3d4c0039-4f48-57ac-aec5-1d10e6223ce4.json
deleted file mode 100644
index f816bc8b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3d4c0039-4f48-57ac-aec5-1d10e6223ce4.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Estonian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-282",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-282"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-282",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Estonia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-282;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Database of Estonian Multi-word Verbs;17 500 entries;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-282;est;downloadable_files_count: 0;Estonia;http://www.cl.ut.ee/ressursid/pysiyhendid/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3d4c0039-4f48-57ac-aec5-1d10e6223ce4",
-    "notes": [
-        "17 500 entries"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-282"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Database of Estonian Multi-word Verbs"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3d7456ac-af3b-5820-ac5c-26a50b1d25ab.json b/oaitestdata/clarin-oai_dc/SET_1/json/3d7456ac-af3b-5820-ac5c-26a50b1d25ab.json
deleted file mode 100644
index 0c857e4c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3d7456ac-af3b-5820-ac5c-26a50b1d25ab.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5590",
-    "MetadataAccess": [
-        "oai:ota:oucs:5590"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Browne, Joseph, fl. 1700-1721."
-    ],
-    "fulltext": "oai:ota:oucs:5590;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5590.xml;Antidotaria; or, a collection of antidotes against the plague, and other malignant diseases. Together, with some decent and useful remarks, on the late Pharmacopeia Londinensis, ... By Joseph Browne, L.L.M.D;Browne, Joseph, fl. 1700-1721.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3d7456ac-af3b-5820-ac5c-26a50b1d25ab",
-    "oai_identifier": [
-        "oai:ota:oucs:5590"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Antidotaria; or, a collection of antidotes against the plague, and other malignant diseases. Together, with some decent and useful remarks, on the late Pharmacopeia Londinensis, ... By Joseph Browne, L.L.M.D"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5590.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3d74d8ae-4dfe-5d69-9967-3ddd6a873057.json b/oaitestdata/clarin-oai_dc/SET_1/json/3d74d8ae-4dfe-5d69-9967-3ddd6a873057.json
deleted file mode 100644
index ad5d7ad5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3d74d8ae-4dfe-5d69-9967-3ddd6a873057.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Monaco, James, 1943-"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 767 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0705",
-    "MetadataAccess": [
-        "oai:ota:oucs:0705"
-    ],
-    "PublicationTimestamp": "1985-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1985"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Essays"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Monaco, James, 1943-"
-    ],
-    "fulltext": "oai:ota:oucs:0705;2018-02-28T13:57:21Z;http://ota.ox.ac.uk/headers/0705.xml;The connoisseur\u00e2\u0080\u0099s guide to the movies / James Monaco;Monaco, James, 1943-;1985;text_and_corpus_linguistics;Motion pictures -- Reviews;eng;Oxford Text Archive, University of Oxford;Monaco, James, 1943-;(1 file : ca. 767 KB);Text;Essays;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3d74d8ae-4dfe-5d69-9967-3ddd6a873057",
-    "oai_identifier": [
-        "oai:ota:oucs:0705"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Motion pictures -- Reviews"
-        }
-    ],
-    "title": [
-        "The connoisseur\u00e2\u0080\u0099s guide to the movies / James Monaco"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0705.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3d74daf9-3b34-5324-9f72-815dc80702b7.json b/oaitestdata/clarin-oai_dc/SET_1/json/3d74daf9-3b34-5324-9f72-815dc80702b7.json
deleted file mode 100644
index 9cedf272..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3d74daf9-3b34-5324-9f72-815dc80702b7.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Institut f\u00fcr Deutsche Sprache"
-    ],
-    "Contributor": [
-        "Strecker, Bruno",
-        "Konopka, Marek"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-542",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-542"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-542",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut f\u00fcr Deutsche Sprache"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-542;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Grammatisches Informationssystem (grammis);Strecker, Bruno;Konopka, Marek;Web Information System \u2013 contains e.g. a linked terminological knowledge-base, XML format;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-542;deu;downloadable_files_count: 0;Germany;Institut f\u00fcr Deutsche Sprache;http://www.ids-mannheim.de/grammis/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3d74daf9-3b34-5324-9f72-815dc80702b7",
-    "notes": [
-        "Web Information System \u2013 contains e.g. a linked terminological knowledge-base, XML format"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-542"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Grammatisches Informationssystem (grammis)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3d922f81-9ef2-5163-b462-3bf052124668.json b/oaitestdata/clarin-oai_dc/SET_1/json/3d922f81-9ef2-5163-b462-3bf052124668.json
deleted file mode 100644
index 2ff41c1f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3d922f81-9ef2-5163-b462-3bf052124668.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/109",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/109"
-    ],
-    "PID": "http://hdl.handle.net/10794/109",
-    "PublicationTimestamp": "2016-04-04T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/109;2017-10-24T14:03:57Z;hdl_10794_1;hdl_10794_2;Blog mix 2015 (2017-05-16);Bloggmix 2015 (2017-05-16);n/a, n/a;Swedish;Blog;The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.;Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat.;2016-04-04;corpus;http://hdl.handle.net/10794/109;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/bloggmix2015",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3d922f81-9ef2-5163-b462-3bf052124668",
-    "notes": [
-        "The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.",
-        "Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/109"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Blog"
-        }
-    ],
-    "title": [
-        "Blog mix 2015 (2017-05-16)",
-        "Bloggmix 2015 (2017-05-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3da5cb1c-203b-5dd0-a715-1d1c446e6bc3.json b/oaitestdata/clarin-oai_dc/SET_1/json/3da5cb1c-203b-5dd0-a715-1d1c446e6bc3.json
deleted file mode 100644
index 138f9864..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3da5cb1c-203b-5dd0-a715-1d1c446e6bc3.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "Middle English (1100-1500)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3306",
-    "MetadataAccess": [
-        "oai:ota:oucs:3306"
-    ],
-    "PublicationTimestamp": "1350-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1350"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:3306;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3306.xml;Sir Gawain and the Green Knight;1350-1399;text_and_corpus_linguistics;enm;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3da5cb1c-203b-5dd0-a715-1d1c446e6bc3",
-    "oai_identifier": [
-        "oai:ota:oucs:3306"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Sir Gawain and the Green Knight"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3306.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3da680ae-d56d-5793-a467-de68536f493c.json b/oaitestdata/clarin-oai_dc/SET_1/json/3da680ae-d56d-5793-a467-de68536f493c.json
deleted file mode 100644
index 9beb3444..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3da680ae-d56d-5793-a467-de68536f493c.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 4",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "English",
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1450",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1450"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1450",
-    "PublicationTimestamp": "2014-09-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-1449",
-        "http://hdl.handle.net/11234/1-1459"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU General Public License, version 2",
-        "http://www.gnu.org/licenses/gpl-2.0.html",
-        "PUB"
-    ],
-    "author": [
-        "Rosa, Rudolf"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1450;2018-07-02T22:05:53Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Fairytale child (2014-09-30);Rosa, Rudolf;dialogue system;morphological generation;Treex;morphological analysis;interactive;Fairytale Child is a simple chatbot trying to simulate a curious child. It asks the user to tell a fairy tale, often interrupting to ask for details and clarifications. However, it remembers what it was told and tries to show it if possible.\r\n\r\nThe chatbot can communicate in Czech and in English. It analyzes the morphology of each sentence produced by the user with natural language processing tools, tries to identify potential questions to ask, and then asks one. A morphological generator is employed to generate correctly inflected sentences in Czech, so that the resulting sentences sound as natural as possible.\r\n\r\nPoh\u00e1dkov\u00e9 d\u00edt\u011b je jednoduch\u00fd chatbot, simuluj\u00edc\u00ed zv\u00eddav\u00e9 d\u00edt\u011b. Po\u017e\u00e1d\u00e1 u\u017eivatele, aby mu vypr\u00e1v\u011bl poh\u00e1dku, ale \u010dasto ho p\u0159eru\u0161uje, aby se zeptal na detaily a vysv\u011btlen\u00ed. Pamatuje si ale, co mu u\u017eivatel \u0159ekl, a sna\u017e\u00ed se to pokud mo\u017eno d\u00e1t najevo.\r\n\r\nChatbot um\u00ed komunikovat \u010desky a anglicky. Analyzuje tvaroslov\u00ed ka\u017ed\u00e9 u\u017eivatelovy v\u011bty pomoc\u00ed NLP n\u00e1stroj\u016f, pokus\u00ed se nal\u00e9zt chodnou ot\u00e1zku, a tu pak polo\u017e\u00ed. Aby tvo\u0159en\u00e9 \u010desk\u00e9 v\u011bty zn\u011bly co nejp\u0159irozen\u011bji, vyu\u017e\u00edv\u00e1 se pro sklo\u0148ov\u00e1n\u00ed tvaroslovn\u00fd gener\u00e1tor.;2014-09-30;toolService;http://hdl.handle.net/11234/1-1450;eng;ces;http://hdl.handle.net/11234/1-1449;http://hdl.handle.net/11234/1-1459;GNU General Public License, version 2;http://www.gnu.org/licenses/gpl-2.0.html;PUB;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 4;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://ufal.mff.cuni.cz/dite",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3da680ae-d56d-5793-a467-de68536f493c",
-    "notes": [
-        "Fairytale Child is a simple chatbot trying to simulate a curious child. It asks the user to tell a fairy tale, often interrupting to ask for details and clarifications. However, it remembers what it was told and tries to show it if possible.\r\n\r\nThe chatbot can communicate in Czech and in English. It analyzes the morphology of each sentence produced by the user with natural language processing tools, tries to identify potential questions to ask, and then asks one. A morphological generator is employed to generate correctly inflected sentences in Czech, so that the resulting sentences sound as natural as possible.\r\n\r\nPoh\u00e1dkov\u00e9 d\u00edt\u011b je jednoduch\u00fd chatbot, simuluj\u00edc\u00ed zv\u00eddav\u00e9 d\u00edt\u011b. Po\u017e\u00e1d\u00e1 u\u017eivatele, aby mu vypr\u00e1v\u011bl poh\u00e1dku, ale \u010dasto ho p\u0159eru\u0161uje, aby se zeptal na detaily a vysv\u011btlen\u00ed. Pamatuje si ale, co mu u\u017eivatel \u0159ekl, a sna\u017e\u00ed se to pokud mo\u017eno d\u00e1t najevo.\r\n\r\nChatbot um\u00ed komunikovat \u010desky a anglicky. Analyzuje tvaroslov\u00ed ka\u017ed\u00e9 u\u017eivatelovy v\u011bty pomoc\u00ed NLP n\u00e1stroj\u016f, pokus\u00ed se nal\u00e9zt chodnou ot\u00e1zku, a tu pak polo\u017e\u00ed. Aby tvo\u0159en\u00e9 \u010desk\u00e9 v\u011bty zn\u011bly co nejp\u0159irozen\u011bji, vyu\u017e\u00edv\u00e1 se pro sklo\u0148ov\u00e1n\u00ed tvaroslovn\u00fd gener\u00e1tor."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1450"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "dialogue system"
-        },
-        {
-            "name": "morphological generation"
-        },
-        {
-            "name": "Treex"
-        },
-        {
-            "name": "morphological analysis"
-        },
-        {
-            "name": "interactive"
-        }
-    ],
-    "title": [
-        "Fairytale child (2014-09-30)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3dabd009-a89d-5acf-b8d8-db62ecbb8a81.json b/oaitestdata/clarin-oai_dc/SET_1/json/3dabd009-a89d-5acf-b8d8-db62ecbb8a81.json
deleted file mode 100644
index 04cd9bc8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3dabd009-a89d-5acf-b8d8-db62ecbb8a81.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "The Grundtvig Centre"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 8",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Danish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repository.clarin.dk:20.500.12115/31",
-    "MetadataAccess": [
-        "oai:repository.clarin.dk:20.500.12115/31"
-    ],
-    "PID": "http://hdl.handle.net/20.500.12115/31",
-    "PublicationTimestamp": "2018-06-29T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "The Grundtvig Centre"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)",
-        "PUB",
-        "http://creativecommons.org/licenses/by-nc/4.0/"
-    ],
-    "author": [
-        "Ravn, Kim Steen"
-    ],
-    "fulltext": "oai:repository.clarin.dk:20.500.12115/31;2018-11-27T12:32:33Z;hdl_20.500.12115_1;hdl_20.500.12115_3;Grundtvig's Works Corpus, v. 1.12, April 2018;Ravn, Kim Steen;Critical edition;N. F. S. Grundtvig;literature;Gruntvig's Works version 1.12, april 2018 contains N.F.S. Grundtvig's authorship. Corpus folder containing edited texts and OCR texts.;2018-06-29;corpus;http://hdl.handle.net/20.500.12115/31;dan;Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0);PUB;http://creativecommons.org/licenses/by-nc/4.0/;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 8;The Grundtvig Centre;http://www.grundtvigsv\u00e6rker.dk",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3dabd009-a89d-5acf-b8d8-db62ecbb8a81",
-    "notes": [
-        "Gruntvig's Works version 1.12, april 2018 contains N.F.S. Grundtvig's authorship. Corpus folder containing edited texts and OCR texts."
-    ],
-    "oai_identifier": [
-        "oai:repository.clarin.dk:20.500.12115/31"
-    ],
-    "oai_set": [
-        "hdl_20.500.12115_1",
-        "hdl_20.500.12115_3"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Critical edition"
-        },
-        {
-            "name": "N. F. S. Grundtvig"
-        },
-        {
-            "name": "literature"
-        }
-    ],
-    "title": [
-        "Grundtvig's Works Corpus, v. 1.12, April 2018"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3dbe2c3d-44f9-5464-bfb3-f7300529818e.json b/oaitestdata/clarin-oai_dc/SET_1/json/3dbe2c3d-44f9-5464-bfb3-f7300529818e.json
deleted file mode 100644
index 6a6a80ba..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3dbe2c3d-44f9-5464-bfb3-f7300529818e.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "University of Lisbon, CLUL-Centro de Lingu\u00edstica da Universidade de Lisboa",
-        "NLX-Natural Language and Speech Group, University of Lisbon"
-    ],
-    "Contributor": [
-        "Branco, Ant\u00f3nio",
-        "Silva, Jo\u00e3o"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Portuguese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1178",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1178"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1178",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Lisbon, CLUL-Centro de Lingu\u00edstica da Universidade de Lisboa",
-        "NLX-Natural Language and Speech Group, University of Lisbon"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Portugal"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1178;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;CINTIL Online Concordancer;Branco, Ant\u00f3nio;Silva, Jo\u00e3o;CINTIL online concordancer (is a freely available online concordancing service to support the research usage of the CINTIL Corpus. It allows the use of generic patterns to specify the occurrences to be retrieved. This permits to uncover linguistic structures of high complexity and use this service as a powerful research tool.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1178;por;downloadable_files_count: 0;Portugal;University of Lisbon, CLUL-Centro de Lingu\u00edstica da Universidade de Lisboa;NLX-Natural Language and Speech Group, University of Lisbon;http://cintil.ul.pt/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3dbe2c3d-44f9-5464-bfb3-f7300529818e",
-    "notes": [
-        "CINTIL online concordancer (is a freely available online concordancing service to support the research usage of the CINTIL Corpus. It allows the use of generic patterns to specify the occurrences to be retrieved. This permits to uncover linguistic structures of high complexity and use this service as a powerful research tool."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1178"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "CINTIL Online Concordancer"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3dc79a61-4b8a-5128-a10b-5695aaf7dbfb.json b/oaitestdata/clarin-oai_dc/SET_1/json/3dc79a61-4b8a-5128-a10b-5695aaf7dbfb.json
deleted file mode 100644
index 757d50a1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3dc79a61-4b8a-5128-a10b-5695aaf7dbfb.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4747",
-    "MetadataAccess": [
-        "oai:ota:oucs:4747"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "MacDonald, John, b. 1741?"
-    ],
-    "fulltext": "oai:ota:oucs:4747;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4747.xml;Travels, in various parts of Europe, Asia, and Africa, during a series of thirty years and upwards. By John MacDonald,;MacDonald, John, b. 1741?;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3dc79a61-4b8a-5128-a10b-5695aaf7dbfb",
-    "oai_identifier": [
-        "oai:ota:oucs:4747"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Travels, in various parts of Europe, Asia, and Africa, during a series of thirty years and upwards. By John MacDonald,"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4747.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3dcc4701-1fba-5b64-9974-c15bbcca64b8.json b/oaitestdata/clarin-oai_dc/SET_1/json/3dcc4701-1fba-5b64-9974-c15bbcca64b8.json
deleted file mode 100644
index 48bdc56a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3dcc4701-1fba-5b64-9974-c15bbcca64b8.json
+++ /dev/null
@@ -1,91 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Electrical Engineering, University of Ljubljana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 3",
-        "application/pdf",
-        "application/zip"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1125",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1125"
-    ],
-    "PID": "http://hdl.handle.net/11356/1125",
-    "PublicationTimestamp": "2017-06-17T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Faculty of Electrical Engineering, University of Ljubljana"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/201634",
-        "http://dx.doi.org/10.1023/A:1023462002932"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Dobri\u0161ek, Simon",
-        "Pave\u0161i\u0107, Nikola",
-        "\u017dganec Gros, Jerneja",
-        "\u017dibert, Janez",
-        "Miheli\u010d, France"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1125;2017-09-29T14:19:38Z;hdl_11356_1023;hdl_11356_1024;Speech Database of Spoken Flight Information Enquiries SOFES 1.0;Dobri\u0161ek, Simon;\u017dganec Gros, Jerneja;\u017dibert, Janez;Miheli\u010d, France;Pave\u0161i\u0107, Nikola;speech database;speech recognition;spoken corpus;speech transcription;TEI;The SOFES speech database (Spoken Flight Enquiries in Slovene) is a collection of transcribed and segmented audio recordings of spoken flight-information enquiries in Slovene. SOFES is built on the basis of the GOPOLIS speech database, which was acquired and compiled by the members of LUKS at the Faculty of Electrical Engineering, University of Ljubljana in the period 1996\u20131998. The main purpose of the GOPOLIS speech database was the development of an automatic spoken-dialogue system for users who are enquiring about flight information over the telephone. The content of SOFES is, however, sufficiently diverse to allow for the development of more generalized acoustic models of spoken Slovene, which are the key components of various speech technologies, such as speech recognizers and speech synthesizers, as well as biometric speaker-recognition systems, etc.;2017-06-17;corpus;http://hdl.handle.net/11356/1125;slv;info:eu-repo/grantAgreement/EC/FP7/201634;http://dx.doi.org/10.1023/A:1023462002932;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);https://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;text/plain; charset=utf-8;application/pdf;application/pdf;application/zip;downloadable_files_count: 3;Faculty of Electrical Engineering, University of Ljubljana",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3dcc4701-1fba-5b64-9974-c15bbcca64b8",
-    "notes": [
-        "The SOFES speech database (Spoken Flight Enquiries in Slovene) is a collection of transcribed and segmented audio recordings of spoken flight-information enquiries in Slovene. SOFES is built on the basis of the GOPOLIS speech database, which was acquired and compiled by the members of LUKS at the Faculty of Electrical Engineering, University of Ljubljana in the period 1996\u20131998. The main purpose of the GOPOLIS speech database was the development of an automatic spoken-dialogue system for users who are enquiring about flight information over the telephone. The content of SOFES is, however, sufficiently diverse to allow for the development of more generalized acoustic models of spoken Slovene, which are the key components of various speech technologies, such as speech recognizers and speech synthesizers, as well as biometric speaker-recognition systems, etc."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1125"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech database"
-        },
-        {
-            "name": "speech recognition"
-        },
-        {
-            "name": "spoken corpus"
-        },
-        {
-            "name": "speech transcription"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "Speech Database of Spoken Flight Information Enquiries SOFES 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3de59bd7-be9f-5747-b0d5-e78d540b02ce.json b/oaitestdata/clarin-oai_dc/SET_1/json/3de59bd7-be9f-5747-b0d5-e78d540b02ce.json
deleted file mode 100644
index 4c8c76a3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3de59bd7-be9f-5747-b0d5-e78d540b02ce.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "greater than 5 MB"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)",
-        "Hebrew"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1111",
-    "MetadataAccess": [
-        "oai:ota:oucs:1111"
-    ],
-    "PublicationYear": [
-        "600 BCE-100 BCE"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Devotional literature"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:1111;2018-03-05T14:20:38Z;http://ota.ox.ac.uk/headers/1111.xml; Aligned texts of Hebrew and Greek Jewish Scriptures  : (CATSS database : TLG format) / compiled by the Computer Assisted Tools for Septuagint Studies project under Emanuel Tov and Robert A. Kraft;600 BCE-100 BCE;text_and_corpus_linguistics;Devotional literature -- Israel;grc;heb;Oxford Text Archive, University of Oxford;greater than 5 MB;Text;Devotional literature;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3de59bd7-be9f-5747-b0d5-e78d540b02ce",
-    "oai_identifier": [
-        "oai:ota:oucs:1111"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Devotional literature -- Israel"
-        }
-    ],
-    "title": [
-        " Aligned texts of Hebrew and Greek Jewish Scriptures  : (CATSS database : TLG format) / compiled by the Computer Assisted Tools for Septuagint Studies project under Emanuel Tov and Robert A. Kraft"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1111.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3e0dcb34-8b9c-5eb6-96d3-71e5392da0db.json b/oaitestdata/clarin-oai_dc/SET_1/json/3e0dcb34-8b9c-5eb6-96d3-71e5392da0db.json
deleted file mode 100644
index 8ca3b38e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3e0dcb34-8b9c-5eb6-96d3-71e5392da0db.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5671",
-    "MetadataAccess": [
-        "oai:ota:oucs:5671"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Amory, Thomas, 1691?-1788?"
-    ],
-    "fulltext": "oai:ota:oucs:5671;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5671.xml;The life of John Buncle: Esq; containing various observations and reflections, made in several parts of the world, and many extraordinary relations. [pt.2];Amory, Thomas, 1691?-1788?;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3e0dcb34-8b9c-5eb6-96d3-71e5392da0db",
-    "oai_identifier": [
-        "oai:ota:oucs:5671"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The life of John Buncle: Esq; containing various observations and reflections, made in several parts of the world, and many extraordinary relations. [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5671.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3e203036-179b-52d5-b5f9-9d7a06bed2a2.json b/oaitestdata/clarin-oai_dc/SET_1/json/3e203036-179b-52d5-b5f9-9d7a06bed2a2.json
deleted file mode 100644
index f46c0093..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3e203036-179b-52d5-b5f9-9d7a06bed2a2.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Burnard, Lou"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 271 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0095",
-    "MetadataAccess": [
-        "oai:ota:oucs:0095"
-    ],
-    "PublicationTimestamp": "1678-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1678"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Marvell, Andrew, 1621-1678"
-    ],
-    "fulltext": "oai:ota:oucs:0095;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0095.xml;Miscellaneous poems / Andrew Marvell;Marvell, Andrew, 1621-1678;1678;text_and_corpus_linguistics;English poetry -- Early modern, 1500-1700;eng;Oxford Text Archive, University of Oxford;Burnard, Lou;(1 file : ca. 271 KB);Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3e203036-179b-52d5-b5f9-9d7a06bed2a2",
-    "oai_identifier": [
-        "oai:ota:oucs:0095"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English poetry -- Early modern"
-        }
-    ],
-    "title": [
-        "Miscellaneous poems / Andrew Marvell"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0095.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3e3eea55-eefe-591b-b981-15a7ccbece63.json b/oaitestdata/clarin-oai_dc/SET_1/json/3e3eea55-eefe-591b-b981-15a7ccbece63.json
deleted file mode 100644
index 2c674c94..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3e3eea55-eefe-591b-b981-15a7ccbece63.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Craig, Hugh"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 217 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1438",
-    "MetadataAccess": [
-        "oai:ota:oucs:1438"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Jonson, Ben, 1573?-1637"
-    ],
-    "fulltext": "oai:ota:oucs:1438;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1438.xml;Epicoene;Epicoene [1616] / Ben Jonson;The silent woman;Jonson, Ben, 1573?-1637;text_and_corpus_linguistics;English drama -- 17th century;Oxford Text Archive, University of Oxford;Craig, Hugh;(1 file : ca. 217 KB);Text;Plays;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3e3eea55-eefe-591b-b981-15a7ccbece63",
-    "oai_identifier": [
-        "oai:ota:oucs:1438"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- th century"
-        }
-    ],
-    "title": [
-        "Epicoene",
-        "Epicoene [1616] / Ben Jonson",
-        "The silent woman"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1438.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3e58020d-3791-53bb-a928-7491e33ce218.json b/oaitestdata/clarin-oai_dc/SET_1/json/3e58020d-3791-53bb-a928-7491e33ce218.json
deleted file mode 100644
index 7d50e697..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3e58020d-3791-53bb-a928-7491e33ce218.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/26",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/26"
-    ],
-    "PID": "http://hdl.handle.net/11321/26",
-    "PublicationTimestamp": "2011-07-21T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Radziszewski, Adam"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/26;2016-01-21T14:29:12Z;hdl_11321_3;hdl_11321_4;WMBT;Radziszewski, Adam;WMBT (Wroc\u0142aw Memory-Based Tagger) is a simple morpho-syntactic tagger for Polish producing state-of-the-art results. WMBT uses TiMBL API as the underlying Memory-Based Learning implementation. The features for classification are generated by using WCCL.\r\n\r\nWMBT uses a tiered tagging approach. Grammatical class is disambiguated first, then subsequent attributes (as defined in a config file) are taken care of. Each attribute may be supplied a different set of features.\r\n\r\nThe software package comes with default configurations for KIPI/IPIC and NKJP tagsets (kipi-guess.ini and nkjp-guess.ini).;2011-07-21;toolService;http://hdl.handle.net/11321/26;pol;downloadable_files_count: 0;Wroc\u0142aw University of Technology;http://nlp.pwr.wroc.pl/redmine/projects/wmbt/wiki",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3e58020d-3791-53bb-a928-7491e33ce218",
-    "notes": [
-        "WMBT (Wroc\u0142aw Memory-Based Tagger) is a simple morpho-syntactic tagger for Polish producing state-of-the-art results. WMBT uses TiMBL API as the underlying Memory-Based Learning implementation. The features for classification are generated by using WCCL.\r\n\r\nWMBT uses a tiered tagging approach. Grammatical class is disambiguated first, then subsequent attributes (as defined in a config file) are taken care of. Each attribute may be supplied a different set of features.\r\n\r\nThe software package comes with default configurations for KIPI/IPIC and NKJP tagsets (kipi-guess.ini and nkjp-guess.ini)."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/26"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "WMBT"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3e5bf48f-5a45-5026-aa1b-ac5145061265.json b/oaitestdata/clarin-oai_dc/SET_1/json/3e5bf48f-5a45-5026-aa1b-ac5145061265.json
deleted file mode 100644
index 067dc2b3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3e5bf48f-5a45-5026-aa1b-ac5145061265.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Woodhouse, J.R., (John Robert), 1937-"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 27 KB)"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0303",
-    "MetadataAccess": [
-        "oai:ota:oucs:0303"
-    ],
-    "PublicationTimestamp": "1524-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1524"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Academic dissertations"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Machiavelli, Niccol\u00c3\u00b2, 1469-1527"
-    ],
-    "fulltext": "oai:ota:oucs:0303;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0303.xml;Discorso o Dialogo intorno alla nostra lingua / Nicol\u00c3\u00b2 Machiavelli;Machiavelli, Niccol\u00c3\u00b2, 1469-1527;1524;text_and_corpus_linguistics;Italian language -- History;ita;Oxford Text Archive, University of Oxford;Woodhouse, J.R., (John Robert), 1937-;(1 file : ca. 27 KB);Text;Academic dissertations;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3e5bf48f-5a45-5026-aa1b-ac5145061265",
-    "oai_identifier": [
-        "oai:ota:oucs:0303"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Italian language -- History"
-        }
-    ],
-    "title": [
-        "Discorso o Dialogo intorno alla nostra lingua / Nicol\u00c3\u00b2 Machiavelli"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0303.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3e880fe5-d9cf-56dd-a28a-6542e828fd16.json b/oaitestdata/clarin-oai_dc/SET_1/json/3e880fe5-d9cf-56dd-a28a-6542e828fd16.json
deleted file mode 100644
index bb7dfb9c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3e880fe5-d9cf-56dd-a28a-6542e828fd16.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "University of Warsaw"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "text/plain"
-    ],
-    "Language": [
-        "Belarusian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/379",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/379"
-    ],
-    "PID": "http://hdl.handle.net/11321/379",
-    "PublicationTimestamp": "2017-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "University of Warsaw"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Peljak-\u0141api\u0144ska, Angelika"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/379;2017-05-30T09:07:28Z;hdl_11321_3;hdl_11321_4;Christie (Belarusian);Peljak-\u0141api\u0144ska, Angelika;Belarusian;Test text Belarusian;2017-05-30;corpus;http://hdl.handle.net/11321/379;bel;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;text/plain;downloadable_files_count: 1;University of Warsaw",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3e880fe5-d9cf-56dd-a28a-6542e828fd16",
-    "notes": [
-        "Test text Belarusian"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/379"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Belarusian"
-        }
-    ],
-    "title": [
-        "Christie (Belarusian)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3e8c0c3e-ed83-50eb-a5ee-3449a3fa16a8.json b/oaitestdata/clarin-oai_dc/SET_1/json/3e8c0c3e-ed83-50eb-a5ee-3449a3fa16a8.json
deleted file mode 100644
index 8f160474..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3e8c0c3e-ed83-50eb-a5ee-3449a3fa16a8.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Sprachwissenschaftliches Institut, Universit\u00e4t Bochum"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-723",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-723"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-723",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Sprachwissenschaftliches Institut, Universit\u00e4t Bochum"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Code of conduct"
-    ],
-    "SpatialCoverage": [
-        "Indonesia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-723;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Totoli corpus;Documentation of the Totoli project (DoBeS project);2014-07-30;toolService;http://hdl.handle.net/11372/LRT-723;Code of conduct;downloadable_files_count: 0;Indonesia;Sprachwissenschaftliches Institut, Universit\u00e4t Bochum;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI337086%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3e8c0c3e-ed83-50eb-a5ee-3449a3fa16a8",
-    "notes": [
-        "Documentation of the Totoli project (DoBeS project)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-723"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Totoli corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3e9a0541-3d80-51da-a495-78af68e9a2c1.json b/oaitestdata/clarin-oai_dc/SET_1/json/3e9a0541-3d80-51da-a495-78af68e9a2c1.json
deleted file mode 100644
index e1de8bb4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3e9a0541-3d80-51da-a495-78af68e9a2c1.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Smith, G. Gregory (George Gregory), 1865-1932"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 31.5 KB)"
-    ],
-    "Language": [
-        "Scots"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2230",
-    "MetadataAccess": [
-        "oai:ota:oucs:2230"
-    ],
-    "PublicationTimestamp": "1460-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1460"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Henryson, Robert, 1430?-1506?"
-    ],
-    "fulltext": "oai:ota:oucs:2230;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/2230.xml;Poems. Selections;[The minor poems of Robert Henryson];Henryson, Robert, 1430?-1506?;1460-1500;text_and_corpus_linguistics;Poems -- Scotland -- 14th century;sco;Oxford Text Archive, University of Oxford;Smith, G. Gregory (George Gregory), 1865-1932;(1 file : ca. 31.5 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3e9a0541-3d80-51da-a495-78af68e9a2c1",
-    "oai_identifier": [
-        "oai:ota:oucs:2230"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- Scotland -- th century"
-        }
-    ],
-    "title": [
-        "Poems. Selections",
-        "[The minor poems of Robert Henryson]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2230.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3ea9be7d-6983-5880-a705-b4bde94823ff.json b/oaitestdata/clarin-oai_dc/SET_1/json/3ea9be7d-6983-5880-a705-b4bde94823ff.json
deleted file mode 100644
index 9fe7281e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3ea9be7d-6983-5880-a705-b4bde94823ff.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/267",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/267"
-    ],
-    "PID": "http://hdl.handle.net/11321/267",
-    "PublicationTimestamp": "2016-02-29T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Aceda\u0144ski, Szymon"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/267;2016-05-31T05:34:48Z;hdl_11321_3;hdl_11321_4;Krokodyl: A hybrid depencency parser of Polish;Aceda\u0144ski, Szymon;syntax;Polish;dependency parsing;Krokodyl is an experimental hybrid deep depencency parser of Polish.\r\n\r\nKrokodyl has been developed at the Institute of Computer Science, Polish Academy\r\nof Sciences (IPI PAN) within the CLARIN-PL project. It was create to evaluate\r\na hybrid approach to parsing: combining syntactic, lexical and semantic\r\nfeatures for dependency parsing.\r\n\r\nIt uses a number of tools as components of the feature generation chain, namely\r\nthe Spejd Grammar, MALT parsing engine, MATE, the Polish Wordnet, the Skladnica\r\ntreebank.;2016-02-29;toolService;http://hdl.handle.net/11321/267;pol;application/octet-stream;application/octet-stream;downloadable_files_count: 0;Institute of Computer Science, Polish Academy of Sciences",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3ea9be7d-6983-5880-a705-b4bde94823ff",
-    "notes": [
-        "Krokodyl is an experimental hybrid deep depencency parser of Polish.\r\n\r\nKrokodyl has been developed at the Institute of Computer Science, Polish Academy\r\nof Sciences (IPI PAN) within the CLARIN-PL project. It was create to evaluate\r\na hybrid approach to parsing: combining syntactic, lexical and semantic\r\nfeatures for dependency parsing.\r\n\r\nIt uses a number of tools as components of the feature generation chain, namely\r\nthe Spejd Grammar, MALT parsing engine, MATE, the Polish Wordnet, the Skladnica\r\ntreebank."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/267"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "syntax"
-        },
-        {
-            "name": "Polish"
-        },
-        {
-            "name": "dependency parsing"
-        }
-    ],
-    "title": [
-        "Krokodyl: A hybrid depencency parser of Polish"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3edf27dd-c2c5-5bdd-aba6-7d775f97b487.json b/oaitestdata/clarin-oai_dc/SET_1/json/3edf27dd-c2c5-5bdd-aba6-7d775f97b487.json
deleted file mode 100644
index 53ddabec..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3edf27dd-c2c5-5bdd-aba6-7d775f97b487.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "A"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0522",
-    "MetadataAccess": [
-        "oai:ota:oucs:0522"
-    ],
-    "PublicationTimestamp": "1948-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1948"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Fry, Christopher, 1907-2005"
-    ],
-    "fulltext": "oai:ota:oucs:0522;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0522.xml;The lady's not for burning;Fry, Christopher, 1907-2005;1948;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;A;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3edf27dd-c2c5-5bdd-aba6-7d775f97b487",
-    "oai_identifier": [
-        "oai:ota:oucs:0522"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The lady's not for burning"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0522.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3efea76c-2d17-5997-aeed-474c829982d8.json b/oaitestdata/clarin-oai_dc/SET_1/json/3efea76c-2d17-5997-aeed-474c829982d8.json
deleted file mode 100644
index e7ecb048..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3efea76c-2d17-5997-aeed-474c829982d8.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5561",
-    "MetadataAccess": [
-        "oai:ota:oucs:5561"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Leny, R."
-    ],
-    "fulltext": "oai:ota:oucs:5561;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5561.xml;Remarkable case of a boy, who lost a considerable portion of brain: and is recovered, without detriment to any faculty, mental or corporeal. By R. Leny.;Leny, R.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3efea76c-2d17-5997-aeed-474c829982d8",
-    "oai_identifier": [
-        "oai:ota:oucs:5561"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Remarkable case of a boy, who lost a considerable portion of brain: and is recovered, without detriment to any faculty, mental or corporeal. By R. Leny."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5561.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3f16cbe1-e4d9-5323-bb59-185b972d5e8b.json b/oaitestdata/clarin-oai_dc/SET_1/json/3f16cbe1-e4d9-5323-bb59-185b972d5e8b.json
deleted file mode 100644
index 070a03fe..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3f16cbe1-e4d9-5323-bb59-185b972d5e8b.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-923",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-923"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-923",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-923;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Lycian and Milyan;ca. 7.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-923;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#lyk",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3f16cbe1-e4d9-5323-bb59-185b972d5e8b",
-    "notes": [
-        "ca. 7.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-923"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Lycian and Milyan"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3f5cefa2-327a-5bf8-a553-71db2acc66b7.json b/oaitestdata/clarin-oai_dc/SET_1/json/3f5cefa2-327a-5bf8-a553-71db2acc66b7.json
deleted file mode 100644
index fdf2a806..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3f5cefa2-327a-5bf8-a553-71db2acc66b7.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "W Drukarni Kr\u00f3lewskiej przy Akademii"
-    ],
-    "Contributor": [
-        "Plater, Tadeusz (t\u0142.)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-8936",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-8936"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D3F-F",
-    "PublicationTimestamp": "1780-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1780"
-    ],
-    "Publisher": [
-        "W Drukarni Kr\u00f3lewskiej przy Akademii"
-    ],
-    "RelatedIdentifier": [
-        "http://www.pbc.rzeszow.pl/Content/8936",
-        "oai:www.pbc.rzeszow.pl:publication:9673"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "author": [
-        "Sarbiewski, Maciej Kazimierz (1595-1640) [et al.]"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-8936;2019-03-01T17:52:58Z;Mysli wybrane z francuskiego oraz Piesni z Sarbiewskiego Parodye toz wiersze na rozne materye przek\u0142adania Tadeusza Platera Starosty Dawlunskiego ucz\u0105cego si\u0119 w Konwikcie J. K. M. Wile\u0144skim Sztuki Krasom\u00f3wskiey i Rymotw\u00f3rskiey;Sarbiewski, Maciej Kazimierz (1595-1640) [et al.];literatura polska - 17 w.;przek\u0142ady - 18 w.;stare druki;Zawiera odr\u0119czne zapiski;Uszkodzone dwie pierwsze karty;W Drukarni Kr\u00f3lewskiej przy Akademii;Plater, Tadeusz (t\u0142.);1780;starodruk;application/xml;clarind-uds:poldilemma-8936;hdl:11858/00-246C-0000-0023-8D3F-F;Sygnatura orygina\u0142u: Cz 1/St;pol;lat;http://www.pbc.rzeszow.pl/Content/8936;oai:www.pbc.rzeszow.pl:publication:9673;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3f5cefa2-327a-5bf8-a553-71db2acc66b7",
-    "notes": [
-        "Zawiera odr\u0119czne zapiski",
-        "Uszkodzone dwie pierwsze karty"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-8936"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "literatura polska - w."
-        },
-        {
-            "name": "literatura polska - w."
-        },
-        {
-            "name": "stare druki"
-        }
-    ],
-    "title": [
-        "Mysli wybrane z francuskiego oraz Piesni z Sarbiewskiego Parodye toz wiersze na rozne materye przek\u0142adania Tadeusza Platera Starosty Dawlunskiego ucz\u0105cego si\u0119 w Konwikcie J. K. M. Wile\u0144skim Sztuki Krasom\u00f3wskiey i Rymotw\u00f3rskiey"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3f85c526-51d9-5a3d-ad87-04eeaee40191.json b/oaitestdata/clarin-oai_dc/SET_1/json/3f85c526-51d9-5a3d-ad87-04eeaee40191.json
deleted file mode 100644
index 173c87af..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3f85c526-51d9-5a3d-ad87-04eeaee40191.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Real Academia Espa\u00f1ola"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/tei+xml",
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-896",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-896"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-896",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Real Academia Espa\u00f1ola"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-896;2016-04-06T16:39:56Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;El Corpus diacr\u00f3nico del espa\u00f1ol (CORDE);Written, diachronic corpus with a variety of text types produced before 1975. About 250 mwd.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-896;spa;application/tei+xml;downloadable_files_count: 0;Spain;Real Academia Espa\u00f1ola;http://www.rae.es/rae/gestores/gespub000019.nsf/voTodosporId/B4E26FC2520104D8C125716400455C06?OpenDocument&i=1",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3f85c526-51d9-5a3d-ad87-04eeaee40191",
-    "notes": [
-        "Written, diachronic corpus with a variety of text types produced before 1975. About 250 mwd."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-896"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "El Corpus diacr\u00f3nico del espa\u00f1ol (CORDE)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3f9422d4-2e0b-50a5-ae9c-3e10ee12f9c2.json b/oaitestdata/clarin-oai_dc/SET_1/json/3f9422d4-2e0b-50a5-ae9c-3e10ee12f9c2.json
deleted file mode 100644
index 046cb563..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3f9422d4-2e0b-50a5-ae9c-3e10ee12f9c2.json
+++ /dev/null
@@ -1,106 +0,0 @@
-{
-    "Contact": [
-        "University of Bergen"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 6",
-        "text/plain; charset=utf-8",
-        "text/plain",
-        "application/vnd.ms-excel"
-    ],
-    "Language": [
-        "Spanish",
-        "Norwegian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/73",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/73"
-    ],
-    "PID": "http://hdl.handle.net/11509/73",
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "University of Bergen"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN_ACA",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NORED=1",
-        "ACA"
-    ],
-    "author": [
-        "Hareide, Lidun"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/73;2016-06-01T11:43:35Z;hdl_11509_1;hdl_11509_2;The Norwegian-Spanish Parallel Corpus;Hareide, Lidun;Annotation;Bilingual Lexicon Induction;Document Classification;Intra - Document Coreference Resolution;Language Identification;Language Modelling;Lexicon Access;Lexicon Acquisition From Corpora;Lexicon Enhancement;Lexicon Extraction From Lexica;Linguistic Research;Machine Translation;Named Entity Recognition;Natural Language Generation;Natural Language Understanding;Parsing;The Norwegian Spanish Parallel Corpus (NSPC) was created at the University of Bergen, Norway. The corpus is primarily constructed for research in Translation Studies, and is built to be roughly comparable to the Spanish-English P-ACTRES corpus. The NSPC is a parallel, unidirectional translation corpus of contemporary Norwegian written texts translated into Spanish, published between 2000 and 2009. It contains fiction and non-fiction, and each text is classified according to genre, the author's gender and the gender and mother tongue of the translator.;2013;corpus;http://hdl.handle.net/11509/73;spa;nor;CLARIN_ACA;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NORED=1;ACA;application/gzip;application/vnd.ms-excel;application/vnd.ms-excel;application/gzip;application/gzip;text/plain;text/plain; charset=utf-8;downloadable_files_count: 6;University of Bergen",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3f9422d4-2e0b-50a5-ae9c-3e10ee12f9c2",
-    "notes": [
-        "The Norwegian Spanish Parallel Corpus (NSPC) was created at the University of Bergen, Norway. The corpus is primarily constructed for research in Translation Studies, and is built to be roughly comparable to the Spanish-English P-ACTRES corpus. The NSPC is a parallel, unidirectional translation corpus of contemporary Norwegian written texts translated into Spanish, published between 2000 and 2009. It contains fiction and non-fiction, and each text is classified according to genre, the author's gender and the gender and mother tongue of the translator."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/73"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Annotation"
-        },
-        {
-            "name": "Bilingual Lexicon Induction"
-        },
-        {
-            "name": "Document Classification"
-        },
-        {
-            "name": "Intra - Document Coreference Resolution"
-        },
-        {
-            "name": "Language Identification"
-        },
-        {
-            "name": "Language Modelling"
-        },
-        {
-            "name": "Lexicon Access"
-        },
-        {
-            "name": "Lexicon Acquisition Corpora"
-        },
-        {
-            "name": "Lexicon Enhancement"
-        },
-        {
-            "name": "Lexicon Extraction Lexica"
-        },
-        {
-            "name": "Linguistic Research"
-        },
-        {
-            "name": "Machine Translation"
-        }
-    ],
-    "title": [
-        "The Norwegian-Spanish Parallel Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3f94ed44-8246-5a1f-ada0-25ff577b782f.json b/oaitestdata/clarin-oai_dc/SET_1/json/3f94ed44-8246-5a1f-ada0-25ff577b782f.json
deleted file mode 100644
index ac131596..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3f94ed44-8246-5a1f-ada0-25ff577b782f.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "between 512 KB and 1 MB "
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0534",
-    "MetadataAccess": [
-        "oai:ota:oucs:0534"
-    ],
-    "PublicationTimestamp": "1926-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1926"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Devanny, Jean,  1894-1962"
-    ],
-    "fulltext": "oai:ota:oucs:0534;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0534.xml; The butcher shop  / compiled by Julia Swannell;Devanny, Jean,  1894-1962;1926;text_and_corpus_linguistics;Novels -- New Zealand -- 20th century;eng;Oxford Text Archive, University of Oxford;between 512 KB and 1 MB ;Text;Novels;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3f94ed44-8246-5a1f-ada0-25ff577b782f",
-    "oai_identifier": [
-        "oai:ota:oucs:0534"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Novels -- New Zealand -- th century"
-        }
-    ],
-    "title": [
-        " The butcher shop  / compiled by Julia Swannell"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0534.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3facd114-f93b-562d-9c08-1c140f3d46ec.json b/oaitestdata/clarin-oai_dc/SET_1/json/3facd114-f93b-562d-9c08-1c140f3d46ec.json
deleted file mode 100644
index 46f66bf9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3facd114-f93b-562d-9c08-1c140f3d46ec.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5649",
-    "MetadataAccess": [
-        "oai:ota:oucs:5649"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Bromehead, Joseph, b. 1747 or 8."
-    ],
-    "fulltext": "oai:ota:oucs:5649;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5649.xml;An oration on the utility of public infirmaries: Occasioned by the opening of the Radcliffe Infirmary at Oxford. By Joseph Bromehead, ...;Bromehead, Joseph, b. 1747 or 8.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3facd114-f93b-562d-9c08-1c140f3d46ec",
-    "oai_identifier": [
-        "oai:ota:oucs:5649"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An oration on the utility of public infirmaries: Occasioned by the opening of the Radcliffe Infirmary at Oxford. By Joseph Bromehead, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5649.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3fedbcfc-7b78-5307-ad5d-6dec74721955.json b/oaitestdata/clarin-oai_dc/SET_1/json/3fedbcfc-7b78-5307-ad5d-6dec74721955.json
deleted file mode 100644
index 7dbbb930..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3fedbcfc-7b78-5307-ad5d-6dec74721955.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "\u017bu\u0142awski"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 3",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/98",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/98"
-    ],
-    "PID": "http://hdl.handle.net/11321/98",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "\u017bu\u0142awski"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "\u017bu\u0142awski, \u017bu\u0142awski"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/98;2015-04-08T13:43:25Z;hdl_11321_3;hdl_11321_4;MWE \u017bu\u0142awski;\u017bu\u0142awski, \u017bu\u0142awski;\u017bu\u0142awski;2015-04-08;corpus;http://hdl.handle.net/11321/98;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;text/plain; charset=utf-8;downloadable_files_count: 3;\u017bu\u0142awski",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3fedbcfc-7b78-5307-ad5d-6dec74721955",
-    "notes": [
-        "\u017bu\u0142awski"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/98"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE \u017bu\u0142awski"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/3ff01ea5-c553-56cf-b93c-295afef51e31.json b/oaitestdata/clarin-oai_dc/SET_1/json/3ff01ea5-c553-56cf-b93c-295afef51e31.json
deleted file mode 100644
index d3d21278..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/3ff01ea5-c553-56cf-b93c-295afef51e31.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-919",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-919"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-919",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-919;2016-04-06T16:39:56Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Hittite;ca. 200.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-919;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#heth",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3ff01ea5-c553-56cf-b93c-295afef51e31",
-    "notes": [
-        "ca. 200.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-919"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Hittite"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/400a2e78-bebe-575e-acf5-93bef5854be2.json b/oaitestdata/clarin-oai_dc/SET_1/json/400a2e78-bebe-575e-acf5-93bef5854be2.json
deleted file mode 100644
index e0f8dcb5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/400a2e78-bebe-575e-acf5-93bef5854be2.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-999",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-999"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-999",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-999;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LAC Savosavo Corpus;Language and Cognition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-999;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI50526%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "400a2e78-bebe-575e-acf5-93bef5854be2",
-    "notes": [
-        "Language and Cognition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-999"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LAC Savosavo Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4010ee80-aa00-52ac-a454-8d1de4076b89.json b/oaitestdata/clarin-oai_dc/SET_1/json/4010ee80-aa00-52ac-a454-8d1de4076b89.json
deleted file mode 100644
index 9d431e12..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4010ee80-aa00-52ac-a454-8d1de4076b89.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4823",
-    "MetadataAccess": [
-        "oai:ota:oucs:4823"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Trusler, John, 1735-1820."
-    ],
-    "fulltext": "oai:ota:oucs:4823;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4823.xml;Modern times: or the adventures of Gabriel Outcast. Supposed to be written by himself. In imitation of Gil Blas. ... [pt.2];Trusler, John, 1735-1820.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4010ee80-aa00-52ac-a454-8d1de4076b89",
-    "oai_identifier": [
-        "oai:ota:oucs:4823"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Modern times: or the adventures of Gabriel Outcast. Supposed to be written by himself. In imitation of Gil Blas. ... [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4823.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4019ecd0-1f91-5f6a-be46-8a675e2be443.json b/oaitestdata/clarin-oai_dc/SET_1/json/4019ecd0-1f91-5f6a-be46-8a675e2be443.json
deleted file mode 100644
index a8e889de..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4019ecd0-1f91-5f6a-be46-8a675e2be443.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/320",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/320"
-    ],
-    "PID": "http://hdl.handle.net/11321/320",
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Maziarz, Marek",
-        "Wendelberger, Micha\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/320;2016-10-14T14:28:07Z;hdl_11321_3;hdl_11321_4;S\u0142ownik kolokacji rzeczownikowo-przymiotnikowych z uzgodnieniem;Wendelberger, Micha\u0142;Maziarz, Marek;kolokacja;S\u0142ownik zawiera uzgodnione kolokacje rzeczownikowo-przymiotnikowe z korpusu S\u0142owosieci wraz z informacj\u0105 o frekwencji poszczeg\u00f3lnych wyst\u0105pie\u0144 (w szyku NA i AN, z wyrazem pomi\u0119dzy cz\u0142onami i bez oraz z informacj\u0105 o liczbie). Nag\u0142\u00f3wek tego pliku jest nast\u0119puj\u0105cy:\r\n\r\npunktacja\tkrotka\tsuma wystapien\tab sg\tba sg\ta_b sg\tb_a sg\tab pl\tba pl\ta_b pl\tb_a pl\tformy napotkane...\r\n\r\nPrzyk\u0142adowo dla po\u0142\u0105czenia \"link zewn\u0119trzny\" mamy nast\u0119puj\u0105cy opis w S\u0142owniku.\r\n0.006348\tsubst:link adj:zewn\u0119trzny\t247849\t2592 (1.045798%)\t7 (0.002824%)\t0 (0.000000%)\t1 (0.000403%)\t245191 (98.927573%)\t57 (0.022998%)\t0 (0.000000%)\t1 (0.000403%)\t\t242812 Linki zewn\u0119trzne\t2081 Link zewn\u0119trzny\t1321 linki zewn\u0119trzne\t616 link\u00f3w zewn\u0119trznych\t349 link zewn\u0119trzny\t226 Linki Zewn\u0119trzne\t141 linkach zewn\u0119trznych\t80 linku zewn\u0119trznego\t42 linku zewn\u0119trznym\t40 linkami zewn\u0119trznymi\t39 Zewn\u0119trzne linki\t31 linkiem zewn\u0119trznym\t14 Linkach zewn\u0119trznych\t10 Link\u00f3w zewn\u0119trznych\t8 zewn\u0119trznych link\u00f3w\t7 Link Zewn\u0119trzny\t6 LInki zewn\u0119trzne\t6 zewn\u0119trzne linki\t4 zewn\u0119trzny link\t3 LINKI ZEWN\u0118TRZNE\t3 zewn\u0119trzne Linki\t1 Link\u00f3w Zewn\u0119trznych\t1 Linkami Zewn\u0119trznymi\t1 zewn\u0119trzne linki\t1 zewn\u0119trzny link\t1 zewn\u0119trznym linku\t1 zewn\u0119trzny Link\t1 zewn\u0119trznego linku\t1 zewn\u0119trznych linkach\t1 linkowi zewn\u0119trznemu\t1 Linkiem zewn\u0119trznym;2016;lexicalConceptualResource;http://hdl.handle.net/11321/320;polski;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;Wroc\u0142aw University of Technology;http://clarin-pl.eu",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4019ecd0-1f91-5f6a-be46-8a675e2be443",
-    "notes": [
-        "S\u0142ownik zawiera uzgodnione kolokacje rzeczownikowo-przymiotnikowe z korpusu S\u0142owosieci wraz z informacj\u0105 o frekwencji poszczeg\u00f3lnych wyst\u0105pie\u0144 (w szyku NA i AN, z wyrazem pomi\u0119dzy cz\u0142onami i bez oraz z informacj\u0105 o liczbie). Nag\u0142\u00f3wek tego pliku jest nast\u0119puj\u0105cy:\r\n\r\npunktacja\tkrotka\tsuma wystapien\tab sg\tba sg\ta_b sg\tb_a sg\tab pl\tba pl\ta_b pl\tb_a pl\tformy napotkane...\r\n\r\nPrzyk\u0142adowo dla po\u0142\u0105czenia \"link zewn\u0119trzny\" mamy nast\u0119puj\u0105cy opis w S\u0142owniku.\r\n0.006348\tsubst:link adj:zewn\u0119trzny\t247849\t2592 (1.045798%)\t7 (0.002824%)\t0 (0.000000%)\t1 (0.000403%)\t245191 (98.927573%)\t57 (0.022998%)\t0 (0.000000%)\t1 (0.000403%)\t\t242812 Linki zewn\u0119trzne\t2081 Link zewn\u0119trzny\t1321 linki zewn\u0119trzne\t616 link\u00f3w zewn\u0119trznych\t349 link zewn\u0119trzny\t226 Linki Zewn\u0119trzne\t141 linkach zewn\u0119trznych\t80 linku zewn\u0119trznego\t42 linku zewn\u0119trznym\t40 linkami zewn\u0119trznymi\t39 Zewn\u0119trzne linki\t31 linkiem zewn\u0119trznym\t14 Linkach zewn\u0119trznych\t10 Link\u00f3w zewn\u0119trznych\t8 zewn\u0119trznych link\u00f3w\t7 Link Zewn\u0119trzny\t6 LInki zewn\u0119trzne\t6 zewn\u0119trzne linki\t4 zewn\u0119trzny link\t3 LINKI ZEWN\u0118TRZNE\t3 zewn\u0119trzne Linki\t1 Link\u00f3w Zewn\u0119trznych\t1 Linkami Zewn\u0119trznymi\t1 zewn\u0119trzne linki\t1 zewn\u0119trzny link\t1 zewn\u0119trznym linku\t1 zewn\u0119trzny Link\t1 zewn\u0119trznego linku\t1 zewn\u0119trznych linkach\t1 linkowi zewn\u0119trznemu\t1 Linkiem zewn\u0119trznym"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/320"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "kolokacja"
-        }
-    ],
-    "title": [
-        "S\u0142ownik kolokacji rzeczownikowo-przymiotnikowych z uzgodnieniem"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/404d7707-9932-577c-ba3a-95e631ec386a.json b/oaitestdata/clarin-oai_dc/SET_1/json/404d7707-9932-577c-ba3a-95e631ec386a.json
deleted file mode 100644
index 30da76a1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/404d7707-9932-577c-ba3a-95e631ec386a.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "University of Warsaw"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/vnd.oasis.opendocument.text",
-        "downloadable_files_count: 10",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/371",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/371"
-    ],
-    "PID": "http://hdl.handle.net/11321/371",
-    "PublicationTimestamp": "2017-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "University of Warsaw"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Peljak-\u0141api\u0144ska, Angelika"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/371;2017-05-30T07:54:23Z;hdl_11321_3;hdl_11321_4;Test corpus;Peljak-\u0141api\u0144ska, Angelika;various;Test corpus of Polish texts;2017-05-30;corpus;http://hdl.handle.net/11321/371;pol;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/vnd.oasis.opendocument.text;text/plain;downloadable_files_count: 10;University of Warsaw",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "404d7707-9932-577c-ba3a-95e631ec386a",
-    "notes": [
-        "Test corpus of Polish texts"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/371"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "various"
-        }
-    ],
-    "title": [
-        "Test corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/405b3437-c3db-54fc-9227-7efca0d18463.json b/oaitestdata/clarin-oai_dc/SET_1/json/405b3437-c3db-54fc-9227-7efca0d18463.json
deleted file mode 100644
index 354b05dd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/405b3437-c3db-54fc-9227-7efca0d18463.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4655",
-    "MetadataAccess": [
-        "oai:ota:oucs:4655"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hayley, William, 1745-1820."
-    ],
-    "fulltext": "oai:ota:oucs:4655;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4655.xml;Ode to Mr. Wright of Derby. By William Hayley, Esq;Hayley, William, 1745-1820.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "405b3437-c3db-54fc-9227-7efca0d18463",
-    "oai_identifier": [
-        "oai:ota:oucs:4655"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Ode to Mr. Wright of Derby. By William Hayley, Esq"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4655.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/406ea2f8-89ae-5c2c-bb8e-3fb866e0f46f.json b/oaitestdata/clarin-oai_dc/SET_1/json/406ea2f8-89ae-5c2c-bb8e-3fb866e0f46f.json
deleted file mode 100644
index ef74c437..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/406ea2f8-89ae-5c2c-bb8e-3fb866e0f46f.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4256",
-    "MetadataAccess": [
-        "oai:ota:oucs:4256"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hutton, Charles, 1737-1823."
-    ],
-    "fulltext": "oai:ota:oucs:4256;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4256.xml;Elements of conic sections: with select exercises in various branches of mathematics and philosophy. For the use of the Royal Military Academy at Woolwich. By Charles Hutton, ...;Hutton, Charles, 1737-1823.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "406ea2f8-89ae-5c2c-bb8e-3fb866e0f46f",
-    "oai_identifier": [
-        "oai:ota:oucs:4256"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Elements of conic sections: with select exercises in various branches of mathematics and philosophy. For the use of the Royal Military Academy at Woolwich. By Charles Hutton, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4256.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4088132e-840c-5485-9041-3ebbb1c00377.json b/oaitestdata/clarin-oai_dc/SET_1/json/4088132e-840c-5485-9041-3ebbb1c00377.json
deleted file mode 100644
index 55db1f83..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4088132e-840c-5485-9041-3ebbb1c00377.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "Sanskrit"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-906",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-906"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-906",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-906;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Classical and Epic Sanskrit;ca. 5.000.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-906;san;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#epkl",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4088132e-840c-5485-9041-3ebbb1c00377",
-    "notes": [
-        "ca. 5.000.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-906"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Classical and Epic Sanskrit"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/40911ca5-53f4-5cca-9990-39fca1e3d9ea.json b/oaitestdata/clarin-oai_dc/SET_1/json/40911ca5-53f4-5cca-9990-39fca1e3d9ea.json
deleted file mode 100644
index 0017c527..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/40911ca5-53f4-5cca-9990-39fca1e3d9ea.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Leona Mamonicza"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-84357",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-84357"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D39-C",
-    "PublicationTimestamp": "1622-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1622"
-    ],
-    "Publisher": [
-        "Drukarnia Leona Mamonicza"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/84357",
-        "oai:jbc.bj.uj.edu.pl:publication:90966"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1601/1700"
-    ],
-    "TempCoverageBegin": 50506804799,
-    "TempCoverageEnd": 50506804799,
-    "TemporalCoverage": " point in time : 1601-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1601-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1601-07-01T11:59:59Z",
-    "author": [
-        "Rochowicz, Stanis\u0142aw ( -1636)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-84357;2019-03-01T17:40:47Z;Kazanie Na Rocznicy \u015b. pami\u0119ci Jasnie Wielmo\u017cnego Pana [...] Iana Karola Chodkiewicza [...] Woiewody Wile\u0144skiego, Hetmana Wielkiego X. Lith: [...];Rochowicz, Stanis\u0142aw ( -1636);starodruki 17\u00a0w.;Chodkiewiczowa, Anna Alojza (1600-1654). Adr. ded.;Drukarnia Leona Mamonicza;[1622];starodruk;application/xml;clarind-uds:poldilemma-84357;hdl:11858/00-246C-0000-0023-8D39-C;Biblioteka Jagiello\u0144ska, BJ St. Dr. 25517 I;pol;lat;http://jbc.bj.uj.edu.pl/Content/84357;oai:jbc.bj.uj.edu.pl:publication:90966;1601/1700;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "40911ca5-53f4-5cca-9990-39fca1e3d9ea",
-    "notes": [
-        "Chodkiewiczowa, Anna Alojza (1600-1654). Adr. ded."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-84357"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Kazanie Na Rocznicy \u015b. pami\u0119ci Jasnie Wielmo\u017cnego Pana [...] Iana Karola Chodkiewicza [...] Woiewody Wile\u0144skiego, Hetmana Wielkiego X. Lith: [...]"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/409c0053-245d-5d1f-8abb-5495f72943e1.json b/oaitestdata/clarin-oai_dc/SET_1/json/409c0053-245d-5d1f-8abb-5495f72943e1.json
deleted file mode 100644
index 0ee38ebf..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/409c0053-245d-5d1f-8abb-5495f72943e1.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Wojciech Jaworski"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/337",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/337"
-    ],
-    "PID": "http://hdl.handle.net/11321/337",
-    "PublicationTimestamp": "2016-10-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wojciech Jaworski"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Jaworski, Wojciech"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/337;2017-02-21T08:32:53Z;hdl_11321_3;hdl_11321_4;ENIAMtoolkit;Jaworski, Wojciech;lemmatization;part of speech tagging;tokenization;MWE detection;sentence boundaries detection;ENIAMtoolkit is a collection of libraries that:\r\n- perform tokenization, lemmatization, part of speech tagging;\r\n- detect MWE and abbreviations;\r\n- split text into sentences.;2016-10-01;toolService;http://hdl.handle.net/11321/337;N/A;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 1;Wojciech Jaworski;http://zil.ipipan.waw.pl/ENIAM",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "409c0053-245d-5d1f-8abb-5495f72943e1",
-    "notes": [
-        "ENIAMtoolkit is a collection of libraries that:\r\n- perform tokenization, lemmatization, part of speech tagging;\r\n- detect MWE and abbreviations;\r\n- split text into sentences."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/337"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "lemmatization"
-        },
-        {
-            "name": "part speech tagging"
-        },
-        {
-            "name": "tokenization"
-        },
-        {
-            "name": "MWE detection"
-        },
-        {
-            "name": "sentence boundaries detection"
-        }
-    ],
-    "title": [
-        "ENIAMtoolkit"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/40a87c94-6982-50d9-a633-5c2f469672d2.json b/oaitestdata/clarin-oai_dc/SET_1/json/40a87c94-6982-50d9-a633-5c2f469672d2.json
deleted file mode 100644
index 3e70d8fd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/40a87c94-6982-50d9-a633-5c2f469672d2.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Mihalcea, Rada"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Romanian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-192",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-192"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-192",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United States"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-192;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Resources and Tools for Romanian NLP;Mihalcea, Rada;Resources and tools developed for Romanian;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-192;ron;downloadable_files_count: 0;United States;http://www.cs.unt.edu/~rada/downloads.html#romanian",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "40a87c94-6982-50d9-a633-5c2f469672d2",
-    "notes": [
-        "Resources and tools developed for Romanian"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-192"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Resources and Tools for Romanian NLP"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/40babafe-bc7b-5324-b9a7-2f785b8838b7.json b/oaitestdata/clarin-oai_dc/SET_1/json/40babafe-bc7b-5324-b9a7-2f785b8838b7.json
deleted file mode 100644
index 1be58a57..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/40babafe-bc7b-5324-b9a7-2f785b8838b7.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2650",
-    "MetadataAccess": [
-        "oai:ota:oucs:2650"
-    ],
-    "PublicationTimestamp": "1727-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1727"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2650;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2650.xml;A letter to a young gentleman, lately enter\u00e2\u0080\u0099d into holy orders;Swift, Jonathan, 1667-1745;1727;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "40babafe-bc7b-5324-b9a7-2f785b8838b7",
-    "oai_identifier": [
-        "oai:ota:oucs:2650"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A letter to a young gentleman, lately enter\u00e2\u0080\u0099d into holy orders"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2650.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/40bac448-8f29-511f-b068-099267c639de.json b/oaitestdata/clarin-oai_dc/SET_1/json/40bac448-8f29-511f-b068-099267c639de.json
deleted file mode 100644
index bb14f130..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/40bac448-8f29-511f-b068-099267c639de.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4787",
-    "MetadataAccess": [
-        "oai:ota:oucs:4787"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gentleman, Francis, 1728-1784."
-    ],
-    "fulltext": "oai:ota:oucs:4787;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4787.xml;Royal fables. By Francis Gentleman;Gentleman, Francis, 1728-1784.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "40bac448-8f29-511f-b068-099267c639de",
-    "oai_identifier": [
-        "oai:ota:oucs:4787"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Royal fables. By Francis Gentleman"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4787.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/40bd9b84-e91f-5ba8-9d86-8d3e48b29d10.json b/oaitestdata/clarin-oai_dc/SET_1/json/40bd9b84-e91f-5ba8-9d86-8d3e48b29d10.json
deleted file mode 100644
index 169f501f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/40bd9b84-e91f-5ba8-9d86-8d3e48b29d10.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5182",
-    "MetadataAccess": [
-        "oai:ota:oucs:5182"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Craven, Elizabeth Craven, Baroness, 1750-1828."
-    ],
-    "fulltext": "oai:ota:oucs:5182;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5182.xml;Airs and chorusses in The Princess of Georgia: an opera: written by Her Serene Highness the Margravine of Anspach, and performed at Brandenburgh-House Theatre, 1798.;Princess of Georgia;Craven, Elizabeth Craven, Baroness, 1750-1828.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "40bd9b84-e91f-5ba8-9d86-8d3e48b29d10",
-    "oai_identifier": [
-        "oai:ota:oucs:5182"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Airs and chorusses in The Princess of Georgia: an opera: written by Her Serene Highness the Margravine of Anspach, and performed at Brandenburgh-House Theatre, 1798.",
-        "Princess of Georgia"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5182.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/40c01847-fd6d-54d9-8c69-e25643903b04.json b/oaitestdata/clarin-oai_dc/SET_1/json/40c01847-fd6d-54d9-8c69-e25643903b04.json
deleted file mode 100644
index eaa4e1af..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/40c01847-fd6d-54d9-8c69-e25643903b04.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 2"
-    ],
-    "Language": [
-        "Slovak",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-AAE0-A",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-AAE0-A"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0006-AAE0-A",
-    "PublicationTimestamp": "2012-05-15T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Galu\u0161\u010d\u00e1kov\u00e1, Petra",
-        "Garab\u00edk, Radovan",
-        "Bojar, Ond\u0159ej"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-AAE0-A;2018-07-02T22:05:53Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;English-Slovak Parallel Corpus;Galu\u0161\u010d\u00e1kov\u00e1, Petra;Garab\u00edk, Radovan;Bojar, Ond\u0159ej;parallel corpus;English-Slovak corpus;English-Slovak parallel corpus consisting of several freely available corpora (Acquis [1], Europarl [2], Official Journal of the European Union [3] and part of OPUS corpus [4] \u2013 EMEA,  EUConst, KDE4 and PHP) and downloaded website of European Commission [5]. Corpus is published in both in plaintext format and with an automatic morphological annotation. \r\n\r\nReferences:\r\n[1] http://langtech.jrc.it/JRC-Acquis.html/\r\n[2] http://www.statmt.org/europarl/\r\n[3] http://apertium.eu/data\r\n[4] http://opus.lingfil.uu.se/\r\n[5] http://ec.europa.eu/;2012-05-15;corpus;http://hdl.handle.net/11858/00-097C-0000-0006-AAE0-A;slk;eng;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/x-gzip;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "40c01847-fd6d-54d9-8c69-e25643903b04",
-    "notes": [
-        "English-Slovak parallel corpus consisting of several freely available corpora (Acquis [1], Europarl [2], Official Journal of the European Union [3] and part of OPUS corpus [4] \u2013 EMEA,  EUConst, KDE4 and PHP) and downloaded website of European Commission [5]. Corpus is published in both in plaintext format and with an automatic morphological annotation. \r\n\r\nReferences:\r\n[1] http://langtech.jrc.it/JRC-Acquis.html/\r\n[2] http://www.statmt.org/europarl/\r\n[3] http://apertium.eu/data\r\n[4] http://opus.lingfil.uu.se/\r\n[5] http://ec.europa.eu/"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-AAE0-A"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parallel corpus"
-        },
-        {
-            "name": "English-Slovak corpus"
-        }
-    ],
-    "title": [
-        "English-Slovak Parallel Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/40c4305c-e15c-55e3-ab62-2a779ccbcba8.json b/oaitestdata/clarin-oai_dc/SET_1/json/40c4305c-e15c-55e3-ab62-2a779ccbcba8.json
deleted file mode 100644
index 2f680148..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/40c4305c-e15c-55e3-ab62-2a779ccbcba8.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-C7F6-3",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-C7F6-3"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0022-C7F6-3",
-    "PublicationTimestamp": "2009-01-01T11:59:59Z",
-    "PublicationYear": [
-        "2009"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU General Public License, version 2",
-        "http://www.gnu.org/licenses/gpl-2.0.html",
-        "PUB"
-    ],
-    "author": [
-        "Pajas, Petr",
-        "\u0160t\u011bp\u00e1nek, Jan",
-        "Sedl\u00e1k, Michal"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-C7F6-3;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;PML Tree Query;Pajas, Petr;\u0160t\u011bp\u00e1nek, Jan;Sedl\u00e1k, Michal;treebank;query;search;System for querying annotated treebanks in PML format. The querying uses it own query language with graphical representation. It has two different implementations (SQL and Perl) and several clients (TrEd, browser-based, command line interface).;2009-01-01;toolService;http://hdl.handle.net/11858/00-097C-0000-0022-C7F6-3;eng;GNU General Public License, version 2;http://www.gnu.org/licenses/gpl-2.0.html;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/pmltq",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "40c4305c-e15c-55e3-ab62-2a779ccbcba8",
-    "notes": [
-        "System for querying annotated treebanks in PML format. The querying uses it own query language with graphical representation. It has two different implementations (SQL and Perl) and several clients (TrEd, browser-based, command line interface)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-C7F6-3"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "query"
-        },
-        {
-            "name": "search"
-        }
-    ],
-    "title": [
-        "PML Tree Query"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/40d215b1-6c46-5df0-bb71-083ecb9780ba.json b/oaitestdata/clarin-oai_dc/SET_1/json/40d215b1-6c46-5df0-bb71-083ecb9780ba.json
deleted file mode 100644
index a9f33925..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/40d215b1-6c46-5df0-bb71-083ecb9780ba.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5070",
-    "MetadataAccess": [
-        "oai:ota:oucs:5070"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Robins, Benjamin, 1707-1751."
-    ],
-    "fulltext": "oai:ota:oucs:5070;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5070.xml;A discourse concerning the nature and certainty of Sir Isaac Newton's Methods of fluxions, and of prime and ultimate ratios. By Benjamin Robins, F.R.S;Robins, Benjamin, 1707-1751.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "40d215b1-6c46-5df0-bb71-083ecb9780ba",
-    "oai_identifier": [
-        "oai:ota:oucs:5070"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A discourse concerning the nature and certainty of Sir Isaac Newton's Methods of fluxions, and of prime and ultimate ratios. By Benjamin Robins, F.R.S"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5070.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/40dacba8-9fe6-5541-958c-5dcc19ae08b0.json b/oaitestdata/clarin-oai_dc/SET_1/json/40dacba8-9fe6-5541-958c-5dcc19ae08b0.json
deleted file mode 100644
index fa68d85b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/40dacba8-9fe6-5541-958c-5dcc19ae08b0.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Lyne, Anthony A."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 585 KB)"
-    ],
-    "Language": [
-        "French"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0569",
-    "MetadataAccess": [
-        "oai:ota:oucs:0569"
-    ],
-    "PublicationTimestamp": "1970-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1970"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Letters"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Lyne, Anthony A."
-    ],
-    "fulltext": "oai:ota:oucs:0569;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0569.xml;Modern business correspondence / Anthony A. Lyne;Lyne, Anthony A.;1970-1979;text_and_corpus_linguistics;Business communication -- France -- 20th century;fra;Oxford Text Archive, University of Oxford;Lyne, Anthony A.;(1 file : ca. 585 KB);Text;Letters;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "40dacba8-9fe6-5541-958c-5dcc19ae08b0",
-    "oai_identifier": [
-        "oai:ota:oucs:0569"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Business communication -- France -- th century"
-        }
-    ],
-    "title": [
-        "Modern business correspondence / Anthony A. Lyne"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0569.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/40f36a34-323a-5365-a3aa-dc2306fa32f0.json b/oaitestdata/clarin-oai_dc/SET_1/json/40f36a34-323a-5365-a3aa-dc2306fa32f0.json
deleted file mode 100644
index 77ad8c9f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/40f36a34-323a-5365-a3aa-dc2306fa32f0.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Link\u00f6ping University"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Swedish",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1513",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1513"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1513",
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Link\u00f6ping University"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11372/LRT-1517"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "author": [
-        "Ahrenberg, Lars",
-        "Holmqvist, Maria"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1513;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;A Gold Standard Word Alignment for English-Swedish;Ahrenberg, Lars;Holmqvist, Maria;word alignment;A Gold Standard Word Alignment for English-Swedish (GES) is a resource containing 1164 manually word aligned sentences pairs from English and Swedish versions of Europarl v. 2.\r\n\r\nThe data can be found here: https://www.ida.liu.se/labs/nlplab/ges/;2011;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1513;swe;eng;http://hdl.handle.net/11372/LRT-1517;downloadable_files_count: 0;Link\u00f6ping University;https://www.ida.liu.se/labs/nlplab/ges/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "40f36a34-323a-5365-a3aa-dc2306fa32f0",
-    "notes": [
-        "A Gold Standard Word Alignment for English-Swedish (GES) is a resource containing 1164 manually word aligned sentences pairs from English and Swedish versions of Europarl v. 2.\r\n\r\nThe data can be found here: https://www.ida.liu.se/labs/nlplab/ges/"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1513"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "word alignment"
-        }
-    ],
-    "title": [
-        "A Gold Standard Word Alignment for English-Swedish"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/40f814bb-5b15-55f4-bf0c-7cedb80ee785.json b/oaitestdata/clarin-oai_dc/SET_1/json/40f814bb-5b15-55f4-bf0c-7cedb80ee785.json
deleted file mode 100644
index ef6a29ad..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/40f814bb-5b15-55f4-bf0c-7cedb80ee785.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "PAN"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "downloadable_files_count: 10",
-        "application/vnd.oasis.opendocument.text",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/396",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/396"
-    ],
-    "PID": "http://hdl.handle.net/11321/396",
-    "PublicationTimestamp": "2017-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "PAN"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Sobolewska, Katarzyna"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/396;2017-05-30T11:55:26Z;hdl_11321_3;hdl_11321_4;Corpus IPI PAN;Sobolewska, Katarzyna;corpus;korpus;2017-05-30;corpus;http://hdl.handle.net/11321/396;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;application/msword;application/vnd.oasis.opendocument.text;text/plain;application/vnd.oasis.opendocument.text;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;downloadable_files_count: 10;PAN",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "40f814bb-5b15-55f4-bf0c-7cedb80ee785",
-    "notes": [
-        "korpus"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/396"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        }
-    ],
-    "title": [
-        "Corpus IPI PAN"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/40f91fe0-a137-5aae-9fda-3dddf6920d54.json b/oaitestdata/clarin-oai_dc/SET_1/json/40f91fe0-a137-5aae-9fda-3dddf6920d54.json
deleted file mode 100644
index 469e107d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/40f91fe0-a137-5aae-9fda-3dddf6920d54.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5220",
-    "MetadataAccess": [
-        "oai:ota:oucs:5220"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dibdin, Charles, 1745-1814."
-    ],
-    "fulltext": "oai:ota:oucs:5220;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5220.xml;The younger brother: a novel, in three volumes, written by Mr. Dibdin. ... [pt.3];Dibdin, Charles, 1745-1814.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "40f91fe0-a137-5aae-9fda-3dddf6920d54",
-    "oai_identifier": [
-        "oai:ota:oucs:5220"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The younger brother: a novel, in three volumes, written by Mr. Dibdin. ... [pt.3]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5220.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/40fc149b-00dd-5844-ba0c-687a1fe13ff1.json b/oaitestdata/clarin-oai_dc/SET_1/json/40fc149b-00dd-5844-ba0c-687a1fe13ff1.json
deleted file mode 100644
index 5f8ab6c6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/40fc149b-00dd-5844-ba0c-687a1fe13ff1.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=e7eeba84059711e7a2aa782bcb074135195eb553cb954192ba08a4f22d044e78",
-    "MetadataAccess": [
-        "e7eeba84059711e7a2aa782bcb074135195eb553cb954192ba08a4f22d044e78"
-    ],
-    "PublicationTimestamp": "2017-03-10T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "fulltext": "e7eeba84059711e7a2aa782bcb074135195eb553cb954192ba08a4f22d044e78;2018-11-15T16:40:31Z;toolService;toolService:tool;English to Basque Machine translation module;Technical Description:\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/Pilot1_technical_description.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/TechnicalDescriptionPilot2_D2.7.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2016/11/TechnicalDescriptionPilot3_D2.10.pdf;2017-03-10",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "40fc149b-00dd-5844-ba0c-687a1fe13ff1",
-    "notes": [
-        "Technical Description:\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/Pilot1_technical_description.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/TechnicalDescriptionPilot2_D2.7.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2016/11/TechnicalDescriptionPilot3_D2.10.pdf"
-    ],
-    "oai_identifier": [
-        "e7eeba84059711e7a2aa782bcb074135195eb553cb954192ba08a4f22d044e78"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "English to Basque Machine translation module"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/410895ae-4fa9-50b6-9e6b-a88a33fbe84a.json b/oaitestdata/clarin-oai_dc/SET_1/json/410895ae-4fa9-50b6-9e6b-a88a33fbe84a.json
deleted file mode 100644
index 02ca2098..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/410895ae-4fa9-50b6-9e6b-a88a33fbe84a.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 673 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2181",
-    "MetadataAccess": [
-        "oai:ota:oucs:2181"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Lawrence, D.H. (David Herbert), 1885-1930"
-    ],
-    "fulltext": "oai:ota:oucs:2181;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/2181.xml;Lady Chatterley's lover / D.H. Lawrence;Lawrence, D.H. (David Herbert), 1885-1930;text_and_corpus_linguistics;English fiction -- 20th century;Oxford Text Archive, University of Oxford;Triggs, Jeffery;text/sgml;(1 file : ca. 673 KB);Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "410895ae-4fa9-50b6-9e6b-a88a33fbe84a",
-    "oai_identifier": [
-        "oai:ota:oucs:2181"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English fiction -- th century"
-        }
-    ],
-    "title": [
-        "Lady Chatterley's lover / D.H. Lawrence"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2181.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4132f525-75f9-5a39-8686-5f6becb4ecac.json b/oaitestdata/clarin-oai_dc/SET_1/json/4132f525-75f9-5a39-8686-5f6becb4ecac.json
deleted file mode 100644
index b91a1be6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4132f525-75f9-5a39-8686-5f6becb4ecac.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Department of Languages, University of Jyv\u00e4skyl\u00e4"
-    ],
-    "Contributor": [
-        "Ullakonoja, Riikka"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Dutch",
-        "Finnish",
-        "Russian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-798",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-798"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-798",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Department of Languages, University of Jyv\u00e4skyl\u00e4"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-798;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Intas corpus;Ullakonoja, Riikka;A corpus of spontaneous discussions and read-aloud performances from native speakers of different ages. Parallel corpus in Russian, Finnish, and Dutch.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-798;nld;fin;rus;downloadable_files_count: 0;Department of Languages, University of Jyv\u00e4skyl\u00e4",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4132f525-75f9-5a39-8686-5f6becb4ecac",
-    "notes": [
-        "A corpus of spontaneous discussions and read-aloud performances from native speakers of different ages. Parallel corpus in Russian, Finnish, and Dutch."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-798"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Intas corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4135464e-b92b-56fa-ad9e-954fc3faf232.json b/oaitestdata/clarin-oai_dc/SET_1/json/4135464e-b92b-56fa-ad9e-954fc3faf232.json
deleted file mode 100644
index 7f4cbd74..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4135464e-b92b-56fa-ad9e-954fc3faf232.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/110",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/110"
-    ],
-    "PID": "http://hdl.handle.net/10794/110",
-    "PublicationTimestamp": "2013-03-06T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/110;2017-10-24T14:03:01Z;hdl_10794_1;hdl_10794_2;Blog mix unknown date (2017-02-24);Bloggmix ok\u00e4nt datum (2017-02-24);n/a, n/a;Swedish;Blog;The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.;Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat.;2013-03-06;corpus;http://hdl.handle.net/10794/110;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/bloggmixodat",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4135464e-b92b-56fa-ad9e-954fc3faf232",
-    "notes": [
-        "The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.",
-        "Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/110"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Blog"
-        }
-    ],
-    "title": [
-        "Blog mix unknown date (2017-02-24)",
-        "Bloggmix ok\u00e4nt datum (2017-02-24)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4159a294-b22b-5021-93c9-115d1722dd19.json b/oaitestdata/clarin-oai_dc/SET_1/json/4159a294-b22b-5021-93c9-115d1722dd19.json
deleted file mode 100644
index 771bb708..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4159a294-b22b-5021-93c9-115d1722dd19.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-171",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-171"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-171",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-171;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TextGrid Repository (TextGridRep);Germanistik;TextGrid has purchased the Zeno.org online library (literary, historical, scientific, ... texts) and successively converts it to TEI. TextGrid hat die Online-Bibliothek von Zeno.org (literarische, naturwissenschaftliche, historische, ... Texte) erworben und konvertiert diese sukzessive in ein g\u00fcltiges TEI-Format.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-171;deu;downloadable_files_count: 0;Germany;http://www.textgridrep.de/repository.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4159a294-b22b-5021-93c9-115d1722dd19",
-    "notes": [
-        "TextGrid has purchased the Zeno.org online library (literary, historical, scientific, ... texts) and successively converts it to TEI. TextGrid hat die Online-Bibliothek von Zeno.org (literarische, naturwissenschaftliche, historische, ... Texte) erworben und konvertiert diese sukzessive in ein g\u00fcltiges TEI-Format."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-171"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "TextGrid Repository (TextGridRep)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/415d0edc-0498-5135-b76d-870100f74502.json b/oaitestdata/clarin-oai_dc/SET_1/json/415d0edc-0498-5135-b76d-870100f74502.json
deleted file mode 100644
index 4ebdcd10..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/415d0edc-0498-5135-b76d-870100f74502.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5523",
-    "MetadataAccess": [
-        "oai:ota:oucs:5523"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Smith, Hugh, 1736?-1789."
-    ],
-    "fulltext": "oai:ota:oucs:5523;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5523.xml;An enlarged syllabus of philosophical lectures: delivered by Hugh Smith ... With the principles on which his conjectures are founded concerning animal life, and the laws of the animal oeconomy. These principles are applied not only to the general doctrine of the glands, but likewise to some new thoughts on the nervous system, the gout, and paralytic complaints.;Smith, Hugh, 1736?-1789.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "415d0edc-0498-5135-b76d-870100f74502",
-    "oai_identifier": [
-        "oai:ota:oucs:5523"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An enlarged syllabus of philosophical lectures: delivered by Hugh Smith ... With the principles on which his conjectures are founded concerning animal life, and the laws of the animal oeconomy. These principles are applied not only to the general doctrine of the glands, but likewise to some new thoughts on the nervous system, the gout, and paralytic complaints."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5523.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/41734cd9-a416-5c8f-8a6d-35de7f273861.json b/oaitestdata/clarin-oai_dc/SET_1/json/41734cd9-a416-5c8f-8a6d-35de7f273861.json
deleted file mode 100644
index a091c180..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/41734cd9-a416-5c8f-8a6d-35de7f273861.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "University of Helsinki"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-748",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-748"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-748",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Helsinki"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-748;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Helsinki Corpus of Older Scots (HCOS);A balanced multi-genre corpus modelled on the Helsinki Corpus, covering the years 1450-1700.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-748;eng;text/plain;downloadable_files_count: 0;University of Helsinki;http://ota.oucs.ox.ac.uk/headers/2081.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "41734cd9-a416-5c8f-8a6d-35de7f273861",
-    "notes": [
-        "A balanced multi-genre corpus modelled on the Helsinki Corpus, covering the years 1450-1700."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-748"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Helsinki Corpus of Older Scots (HCOS)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/417e1a3b-2f4d-5b5c-ae58-39ebb1186933.json b/oaitestdata/clarin-oai_dc/SET_1/json/417e1a3b-2f4d-5b5c-ae58-39ebb1186933.json
deleted file mode 100644
index cb0566cd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/417e1a3b-2f4d-5b5c-ae58-39ebb1186933.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "A"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1612",
-    "MetadataAccess": [
-        "oai:ota:oucs:1612"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "London, Jack"
-    ],
-    "fulltext": "oai:ota:oucs:1612;2018-04-16T15:30:51Z;http://ota.ox.ac.uk/headers/1612.xml;White Fang;London, Jack;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;A;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "417e1a3b-2f4d-5b5c-ae58-39ebb1186933",
-    "oai_identifier": [
-        "oai:ota:oucs:1612"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "White Fang"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1612.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/41a0844a-d448-5264-976e-3578aa6abac1.json b/oaitestdata/clarin-oai_dc/SET_1/json/41a0844a-d448-5264-976e-3578aa6abac1.json
deleted file mode 100644
index 8f3f6847..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/41a0844a-d448-5264-976e-3578aa6abac1.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4740",
-    "MetadataAccess": [
-        "oai:ota:oucs:4740"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hayley, William, 1745-1820."
-    ],
-    "fulltext": "oai:ota:oucs:4740;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4740.xml;Plays of three acts: written for a private theatre. By William Hayley, Esq.;Hayley, William, 1745-1820.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "41a0844a-d448-5264-976e-3578aa6abac1",
-    "oai_identifier": [
-        "oai:ota:oucs:4740"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Plays of three acts: written for a private theatre. By William Hayley, Esq."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4740.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/41b4f7c4-4b2b-533d-b943-7740e1797b0b.json b/oaitestdata/clarin-oai_dc/SET_1/json/41b4f7c4-4b2b-533d-b943-7740e1797b0b.json
deleted file mode 100644
index d69d0beb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/41b4f7c4-4b2b-533d-b943-7740e1797b0b.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=e3405bf2bc8e11e1a404080027e73ea22b673876d16248a995f3064f6708b6c3",
-    "MetadataAccess": [
-        "e3405bf2bc8e11e1a404080027e73ea22b673876d16248a995f3064f6708b6c3"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "e3405bf2bc8e11e1a404080027e73ea22b673876d16248a995f3064f6708b6c3;2018-11-15T16:39:29Z;toolService;toolService:tool;UIMA/U-Compare OpenNLP POS Tagger;This is a UIMA wrapper for the OpenNLP Tokenizer tool. It assigns part-of-speech tags to tokens in English text. The tagset used in from the Penn Treebank). The tool forms part of the in-built library of components provided with the U-Compare platform (Kano et al., 2009; Kano et al., 2011; see separate META-SHARE record)  for building and evaluating text mining workflows. The U-Compare Workbench (see separate META-SHARE record) provides a graphical drag-and drop interface for the rapid creation of workflows. \n;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "41b4f7c4-4b2b-533d-b943-7740e1797b0b",
-    "notes": [
-        "This is a UIMA wrapper for the OpenNLP Tokenizer tool. It assigns part-of-speech tags to tokens in English text. The tagset used in from the Penn Treebank). The tool forms part of the in-built library of components provided with the U-Compare platform (Kano et al., 2009; Kano et al., 2011; see separate META-SHARE record)  for building and evaluating text mining workflows. The U-Compare Workbench (see separate META-SHARE record) provides a graphical drag-and drop interface for the rapid creation of workflows. \n"
-    ],
-    "oai_identifier": [
-        "e3405bf2bc8e11e1a404080027e73ea22b673876d16248a995f3064f6708b6c3"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "UIMA/U-Compare OpenNLP POS Tagger"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/41c42967-dcfb-5e50-a1bd-4f7de6a9009f.json b/oaitestdata/clarin-oai_dc/SET_1/json/41c42967-dcfb-5e50-a1bd-4f7de6a9009f.json
deleted file mode 100644
index c5a63235..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/41c42967-dcfb-5e50-a1bd-4f7de6a9009f.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Society for Danish Language and Literature (DSL)",
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 6",
-        "application/pdf",
-        "text/plain",
-        "application/zip"
-    ],
-    "Language": [
-        "Danish",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repository.clarin.dk:20.500.12115/24",
-    "MetadataAccess": [
-        "oai:repository.clarin.dk:20.500.12115/24"
-    ],
-    "PID": "http://hdl.handle.net/20.500.12115/24",
-    "PublicationTimestamp": "2013-01-03T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Society for Danish Language and Literature (DSL)",
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "RelatedIdentifier": [
-        "https://pdfs.semanticscholar.org/6891/69de00c63d58bd68229cb0b3469a617f5ab3.pdf"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "DanNet 1.0 License",
-        "https://cst.ku.dk/projekter/dannet/license.txt",
-        "PUB"
-    ],
-    "author": [
-        "S\u00f8rensen, Nicolai Hartvig",
-        "Nimb, Sanni",
-        "Lorentzen, Henrik",
-        "Asmussen. J\u00f8rg",
-        "Trap-Jensen, Lars",
-        "Pedersen, Bolette Sandford"
-    ],
-    "fulltext": "oai:repository.clarin.dk:20.500.12115/24;2018-11-19T13:44:11Z;hdl_20.500.12115_1;hdl_20.500.12115_3;DanNet, Danish Wordnet (v 2.2) - csv-format;Pedersen, Bolette Sandford;Nimb, Sanni;S\u00f8rensen, Nicolai Hartvig;Trap-Jensen, Lars;Lorentzen, Henrik;Asmussen. J\u00f8rg;wordnet;DanNet is a Danish lexical semantic wordnet; i.e. a language resource where the semantic relations between words are expressed in a formal language and thereby made usable for IT systems dealing with intelligent information handling. The DanNet database contains at present 65,000 concepts described in form of so-called synsets (sets of synonyms) related to one another by hyperonyms and hypernyms and for about 50 % of the concepts by other types of relations, e.g. used_for. All concepts are furthermore related to an ontological type (e.g. Human, Artifact or Activity). About 5,000 Danish synsets are linked to the equivalent English synsets of Princeton WordNet. Through the multilingual wordnet initiative Wordties (wordties.cst.dk), DanNet is linked to the Finnish, Swedish, Estonian and Polish wordnet.;2013-01-03;lexicalConceptualResource;http://hdl.handle.net/20.500.12115/24;dan;eng;https://pdfs.semanticscholar.org/6891/69de00c63d58bd68229cb0b3469a617f5ab3.pdf;DanNet 1.0 License;https://cst.ku.dk/projekter/dannet/license.txt;PUB;text/plain; charset=utf-8;application/zip;text/plain;text/plain;text/plain;application/pdf;application/pdf;downloadable_files_count: 6;Centre for Language Technology, NorS, University of Copenhagen;Society for Danish Language and Literature (DSL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "41c42967-dcfb-5e50-a1bd-4f7de6a9009f",
-    "notes": [
-        "DanNet is a Danish lexical semantic wordnet; i.e. a language resource where the semantic relations between words are expressed in a formal language and thereby made usable for IT systems dealing with intelligent information handling. The DanNet database contains at present 65,000 concepts described in form of so-called synsets (sets of synonyms) related to one another by hyperonyms and hypernyms and for about 50 % of the concepts by other types of relations, e.g. used_for. All concepts are furthermore related to an ontological type (e.g. Human, Artifact or Activity). About 5,000 Danish synsets are linked to the equivalent English synsets of Princeton WordNet. Through the multilingual wordnet initiative Wordties (wordties.cst.dk), DanNet is linked to the Finnish, Swedish, Estonian and Polish wordnet."
-    ],
-    "oai_identifier": [
-        "oai:repository.clarin.dk:20.500.12115/24"
-    ],
-    "oai_set": [
-        "hdl_20.500.12115_1",
-        "hdl_20.500.12115_3"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "wordnet"
-        }
-    ],
-    "title": [
-        "DanNet, Danish Wordnet (v 2.2) - csv-format"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/41c6020f-3b6a-5a1b-b666-a3bd264f984e.json b/oaitestdata/clarin-oai_dc/SET_1/json/41c6020f-3b6a-5a1b-b666-a3bd264f984e.json
deleted file mode 100644
index 0e7b7b7f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/41c6020f-3b6a-5a1b-b666-a3bd264f984e.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Somali"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/11",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/11"
-    ],
-    "PID": "http://hdl.handle.net/10794/11",
-    "PublicationTimestamp": "2015-11-20T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/11;2017-10-27T16:40:22Z;hdl_10794_1;hdl_10794_2;Af-Soomaali 2001 (2017-10-16);Af-Soomaali 2001 (2017-10-16);n/a, n/a;Somali;Corpus;Af-Soomaali 2001. The material is sentence scrambled.;Af-Soomaali 2001. Materialet \u00e4r meningsomkastat.;2015-11-20;corpus;http://hdl.handle.net/10794/11;som;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/somali-2001",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "41c6020f-3b6a-5a1b-b666-a3bd264f984e",
-    "notes": [
-        "Af-Soomaali 2001. The material is sentence scrambled.",
-        "Af-Soomaali 2001. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/11"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Somali"
-        },
-        {
-            "name": "Corpus"
-        }
-    ],
-    "title": [
-        "Af-Soomaali 2001 (2017-10-16)",
-        "Af-Soomaali 2001 (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/41ca29ee-e4c7-5462-97e7-98d90c03294e.json b/oaitestdata/clarin-oai_dc/SET_1/json/41ca29ee-e4c7-5462-97e7-98d90c03294e.json
deleted file mode 100644
index 63aad8e8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/41ca29ee-e4c7-5462-97e7-98d90c03294e.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Matras, Yaron"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "3 files: ca. 12 MB"
-    ],
-    "Language": [
-        "English",
-        "Romany"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2483",
-    "MetadataAccess": [
-        "oai:ota:oucs:2483"
-    ],
-    "PublicationTimestamp": "2004-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2004"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Linguistic corpora"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Els\u00c3\u00adk, Viktor",
-        "Matras, Yaron"
-    ],
-    "fulltext": "oai:ota:oucs:2483;2018-02-16T10:42:06Z;http://ota.ox.ac.uk/headers/2483.xml;Morphosyntactic typology of Romani: Database enhancement;RMS Database;Matras, Yaron;Els\u00c3\u00adk, Viktor;2004;text_and_corpus_linguistics;Linguistics;Romany language;Dialectology;Languages in contact;Typology (Linguistics);eng;rom;The resource contains grammatical descriptions of around 100 varieties of Romani. The description is organised by chapters following standard grammatical outlines. Chapters include questions, and data are arranged in data fields (text fields containing examples), and analytical fields (pre-defined value lists). ;Oxford Text Archive, University of Oxford;Matras, Yaron;3 files: ca. 12 MB;Text;Linguistic corpora;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "41ca29ee-e4c7-5462-97e7-98d90c03294e",
-    "notes": [
-        "The resource contains grammatical descriptions of around 100 varieties of Romani. The description is organised by chapters following standard grammatical outlines. Chapters include questions, and data are arranged in data fields (text fields containing examples), and analytical fields (pre-defined value lists). "
-    ],
-    "oai_identifier": [
-        "oai:ota:oucs:2483"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Linguistics"
-        },
-        {
-            "name": "Romany language"
-        },
-        {
-            "name": "Dialectology"
-        },
-        {
-            "name": "Languages contact"
-        },
-        {
-            "name": "Typology Linguistics"
-        }
-    ],
-    "title": [
-        "Morphosyntactic typology of Romani: Database enhancement",
-        "RMS Database"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2483.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/41cccb60-2a27-5b37-9463-889c182585e7.json b/oaitestdata/clarin-oai_dc/SET_1/json/41cccb60-2a27-5b37-9463-889c182585e7.json
deleted file mode 100644
index fec63f17..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/41cccb60-2a27-5b37-9463-889c182585e7.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 7",
-        "text/xml"
-    ],
-    "Language": [
-        "Vietnamese",
-        "Czech",
-        "English",
-        "German",
-        "French",
-        "Spanish",
-        "Russian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1594",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1594"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1594",
-    "PublicationTimestamp": "2015-11-05T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Bojar, Ond\u0159ej",
-        "Hoang, Duc Tam"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1594;2018-07-02T22:05:53Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;WMT 13 Test Set;Hoang, Duc Tam;Bojar, Ond\u0159ej;test data;parallel corpus;Vietnamese;We provide the Vietnamese version of the multi-lingual test set from WMT 2013 [1] competition. The Vietnamese version was manually translated from English. For completeness, this record contains the 3000 sentences in all the WMT 2013 original languages (Czech, English, French, German, Russian and Spanish), extended with our Vietnamese version. Test set is used in [2] to evaluate translation between Czech, English and Vietnamese.\r\n\r\nReferences\r\n1. http://www.statmt.org/wmt13/evaluation-task.html\r\n2. Duc Tam Hoang and Ond\u0159ej Bojar, The Prague Bulletin of Mathematical Linguistics. Volume 104, Issue 1, Pages 75--86, ISSN 1804-0462. 9/2015;2015-11-05;corpus;http://hdl.handle.net/11234/1-1594;vie;ces;eng;deu;fra;spa;rus;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/xml;text/plain; charset=utf-8;downloadable_files_count: 7;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "41cccb60-2a27-5b37-9463-889c182585e7",
-    "notes": [
-        "We provide the Vietnamese version of the multi-lingual test set from WMT 2013 [1] competition. The Vietnamese version was manually translated from English. For completeness, this record contains the 3000 sentences in all the WMT 2013 original languages (Czech, English, French, German, Russian and Spanish), extended with our Vietnamese version. Test set is used in [2] to evaluate translation between Czech, English and Vietnamese.\r\n\r\nReferences\r\n1. http://www.statmt.org/wmt13/evaluation-task.html\r\n2. Duc Tam Hoang and Ond\u0159ej Bojar, The Prague Bulletin of Mathematical Linguistics. Volume 104, Issue 1, Pages 75--86, ISSN 1804-0462. 9/2015"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1594"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "test data"
-        },
-        {
-            "name": "parallel corpus"
-        },
-        {
-            "name": "Vietnamese"
-        }
-    ],
-    "title": [
-        "WMT 13 Test Set"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/41e2e84f-1a04-5632-ba46-09884ac3c387.json b/oaitestdata/clarin-oai_dc/SET_1/json/41e2e84f-1a04-5632-ba46-09884ac3c387.json
deleted file mode 100644
index 4b88fe54..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/41e2e84f-1a04-5632-ba46-09884ac3c387.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3556",
-    "MetadataAccess": [
-        "oai:ota:oucs:3556"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Boswell, James, 1740-1795."
-    ],
-    "fulltext": "oai:ota:oucs:3556;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3556.xml;A letter to the people of Scotland, on the alarming attempt to infringe the Articles of the Union, and introduce a most pernicious innovation, by diminishing the number of the lords of session. By James Boswell, Esq;Boswell, James, 1740-1795.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "41e2e84f-1a04-5632-ba46-09884ac3c387",
-    "oai_identifier": [
-        "oai:ota:oucs:3556"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A letter to the people of Scotland, on the alarming attempt to infringe the Articles of the Union, and introduce a most pernicious innovation, by diminishing the number of the lords of session. By James Boswell, Esq"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3556.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/41e5efcb-d332-5ecf-8039-d4d48daef5dc.json b/oaitestdata/clarin-oai_dc/SET_1/json/41e5efcb-d332-5ecf-8039-d4d48daef5dc.json
deleted file mode 100644
index 034746c0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/41e5efcb-d332-5ecf-8039-d4d48daef5dc.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Howard-Hill, T. H. (Trevor Howard)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 14 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0078",
-    "MetadataAccess": [
-        "oai:ota:oucs:0078"
-    ],
-    "PublicationTimestamp": "1618-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1618"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Masques"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Jonson, Ben, 1573?-1637"
-    ],
-    "fulltext": "oai:ota:oucs:0078;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0078.xml;Pleasure reconcil'd to virtue / Ben Jonson;Jonson, Ben, 1573?-1637;1618;text_and_corpus_linguistics;Masques -- 17th century;eng;Oxford Text Archive, University of Oxford;Howard-Hill, T. H. (Trevor Howard);(1 file : ca. 14 KB);Text;Masques;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "41e5efcb-d332-5ecf-8039-d4d48daef5dc",
-    "oai_identifier": [
-        "oai:ota:oucs:0078"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Masques -- th century"
-        }
-    ],
-    "title": [
-        "Pleasure reconcil'd to virtue / Ben Jonson"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0078.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/420777b2-c365-5965-a71a-cdc780724398.json b/oaitestdata/clarin-oai_dc/SET_1/json/420777b2-c365-5965-a71a-cdc780724398.json
deleted file mode 100644
index 0e8c2d09..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/420777b2-c365-5965-a71a-cdc780724398.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia JKM y Rzeczypospolitey Scholarum Piarum"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/pdf"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-1265",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-1265"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CDA-C",
-    "PublicationTimestamp": "1760-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1760"
-    ],
-    "Publisher": [
-        "Drukarnia JKM y Rzeczypospolitey Scholarum Piarum"
-    ],
-    "RelatedIdentifier": [
-        "http://pbc.biaman.pl/Content/1265"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "author": [
-        "[Kocha\u0144ski, Dominik ]"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-1265;2019-02-28T18:07:16Z;Prawdy moralne theologiczne niektore Kazaniami, inne Kontrowersyami w Mi\u0144sku podczas [...] r. 1759 [...] missyi dominikanow po Xi\u0119stwie Litewskim predykuj\u0105cych dowiedzione. Na rozkaz s\u0105dz\u0105cego si\u0119 tam wtedy Trybuna\u0142u G\u0142\u00f3wnego W.X.L. [...] wszystkie w kszta\u0142cie kazan wydrukowane [...] 1760.;[Kocha\u0144ski, Dominik ];Nauki moralne - 18 w.;ilo\u015b\u0107 skan\u00f3w: 197 ; sygn. S-79;Drukarnia JKM y Rzeczypospolitey Scholarum Piarum;1760;starodruk;application/pdf;clarind-uds:poldilemma-1265;hdl:11858/00-246C-0000-0023-8CDA-C;pol;lat;http://pbc.biaman.pl/Content/1265;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "420777b2-c365-5965-a71a-cdc780724398",
-    "notes": [
-        "ilo\u015b\u0107 skan\u00f3w: 197 ; sygn. S-79"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-1265"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Nauki moralne - w."
-        }
-    ],
-    "title": [
-        "Prawdy moralne theologiczne niektore Kazaniami, inne Kontrowersyami w Mi\u0144sku podczas [...] r. 1759 [...] missyi dominikanow po Xi\u0119stwie Litewskim predykuj\u0105cych dowiedzione. Na rozkaz s\u0105dz\u0105cego si\u0119 tam wtedy Trybuna\u0142u G\u0142\u00f3wnego W.X.L. [...] wszystkie w kszta\u0142cie kazan wydrukowane [...] 1760."
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4226ad43-7f2b-5095-b46b-2009d5a4329f.json b/oaitestdata/clarin-oai_dc/SET_1/json/4226ad43-7f2b-5095-b46b-2009d5a4329f.json
deleted file mode 100644
index a08f71df..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4226ad43-7f2b-5095-b46b-2009d5a4329f.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 146 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1573",
-    "MetadataAccess": [
-        "oai:ota:oucs:1573"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Franklin, Benjamin, 1706-1790"
-    ],
-    "fulltext": "oai:ota:oucs:1573;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1573.xml;Philadelphia, 1785-1790;Franklin, Benjamin, 1706-1790;default: 1976-01-01;text_and_corpus_linguistics;Letters -- United States -- 18th century;eng;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 146 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4226ad43-7f2b-5095-b46b-2009d5a4329f",
-    "oai_identifier": [
-        "oai:ota:oucs:1573"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Letters -- United States -- th century"
-        }
-    ],
-    "title": [
-        "Philadelphia, 1785-1790"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1573.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/42369969-8276-558f-a9f0-c2e39ef8c367.json b/oaitestdata/clarin-oai_dc/SET_1/json/42369969-8276-558f-a9f0-c2e39ef8c367.json
deleted file mode 100644
index 0f519116..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/42369969-8276-558f-a9f0-c2e39ef8c367.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2893",
-    "MetadataAccess": [
-        "oai:ota:oucs:2893"
-    ],
-    "PublicationTimestamp": "1760-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1760"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2893;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2893.xml;Preface to Voltaire's Essay;Swift, Jonathan, 1667-1745;1760;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "42369969-8276-558f-a9f0-c2e39ef8c367",
-    "oai_identifier": [
-        "oai:ota:oucs:2893"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Preface to Voltaire's Essay"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2893.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4250343a-1a0d-5d5f-9ed8-f6778dcd2aff.json b/oaitestdata/clarin-oai_dc/SET_1/json/4250343a-1a0d-5d5f-9ed8-f6778dcd2aff.json
deleted file mode 100644
index 6a8d3a07..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4250343a-1a0d-5d5f-9ed8-f6778dcd2aff.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contributor": [
-        "Paikens, P\u0113teris",
-        "B\u0101rzdi\u0146\u0161, Guntis"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Latvian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-299",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-299"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-299",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Latvia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-299;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;SemTi-Kamols morphological analyser;Paikens, P\u0113teris;B\u0101rzdi\u0146\u0161, Guntis;morphological analyzer;A Java library for morphological analysis of Latvian. The lexicon covers ~50 000 lemmas. A set of robust derivation rules is also used.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-299;lav;downloadable_files_count: 0;Latvia;http://www.semti-kamols.lv/doc_upl/morphology-r742.zip",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4250343a-1a0d-5d5f-9ed8-f6778dcd2aff",
-    "notes": [
-        "A Java library for morphological analysis of Latvian. The lexicon covers ~50 000 lemmas. A set of robust derivation rules is also used."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-299"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphological analyzer"
-        }
-    ],
-    "title": [
-        "SemTi-Kamols morphological analyser"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4255e3ca-fbac-506b-b283-12d9c7e77723.json b/oaitestdata/clarin-oai_dc/SET_1/json/4255e3ca-fbac-506b-b283-12d9c7e77723.json
deleted file mode 100644
index b03a13e2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4255e3ca-fbac-506b-b283-12d9c7e77723.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3211",
-    "MetadataAccess": [
-        "oai:ota:oucs:3211"
-    ],
-    "PublicationTimestamp": "1869-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1869"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Trollope, Anthony, 1815-1882"
-    ],
-    "fulltext": "oai:ota:oucs:3211;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3211.xml;Phineas Finn;Trollope, Anthony, 1815-1882;not after: 1869;text_and_corpus_linguistics;Novels -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4255e3ca-fbac-506b-b283-12d9c7e77723",
-    "oai_identifier": [
-        "oai:ota:oucs:3211"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Novels -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Phineas Finn"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3211.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/425617cc-8676-553c-bf26-3b164bd214d7.json b/oaitestdata/clarin-oai_dc/SET_1/json/425617cc-8676-553c-bf26-3b164bd214d7.json
deleted file mode 100644
index 839c050f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/425617cc-8676-553c-bf26-3b164bd214d7.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-C73C-7",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-C73C-7"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0022-C73C-7",
-    "PublicationTimestamp": "2007-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2007"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11858/00-097C-0000-0023-1B04-C"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "Strakov\u00e1, Jana",
-        "\u0160ev\u010d\u00edkov\u00e1, Magda"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-C73C-7;2018-07-02T22:05:53Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Czech Named Entity Corpus 1.0;\u0160ev\u010d\u00edkov\u00e1, Magda;\u017dabokrtsk\u00fd, Zden\u011bk;Strakov\u00e1, Jana;named entity recognition;named entitity corpus;Czech;NER;corpus;The presented Czech Named Entity Corpus 1.0 is the first publicly available corpus providing a large body of manually annotated named entities in Czech sentences, including a fine-grained classification.;2007;corpus;http://hdl.handle.net/11858/00-097C-0000-0022-C73C-7;ces;http://hdl.handle.net/11858/00-097C-0000-0023-1B04-C;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "425617cc-8676-553c-bf26-3b164bd214d7",
-    "notes": [
-        "The presented Czech Named Entity Corpus 1.0 is the first publicly available corpus providing a large body of manually annotated named entities in Czech sentences, including a fine-grained classification."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-C73C-7"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "named entity recognition"
-        },
-        {
-            "name": "named entitity corpus"
-        },
-        {
-            "name": "Czech"
-        },
-        {
-            "name": "NER"
-        },
-        {
-            "name": "corpus"
-        }
-    ],
-    "title": [
-        "Czech Named Entity Corpus 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/425af52a-ebbf-5c3a-a089-6d7912c3744e.json b/oaitestdata/clarin-oai_dc/SET_1/json/425af52a-ebbf-5c3a-a089-6d7912c3744e.json
deleted file mode 100644
index d11db9ba..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/425af52a-ebbf-5c3a-a089-6d7912c3744e.json
+++ /dev/null
@@ -1,40 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=30d4a088a35a11e1a404080027e73ea2ca727b99f24940f89f64d0fab8994f4d",
-    "MetadataAccess": [
-        "30d4a088a35a11e1a404080027e73ea2ca727b99f24940f89f64d0fab8994f4d"
-    ],
-    "PublicationTimestamp": "2015-12-10T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "30d4a088a35a11e1a404080027e73ea2ca727b99f24940f89f64d0fab8994f4d;2019-02-27T12:08:45Z;corpus;corpus:text;corpus:audio;corpus:text:audio;GREC;GREC is a semantically annotated corpus of 240 MEDLINE abstracts (167 on the subject of E. coli species and 73 on the subject of the Human species) which is intended for training IE systems and/or resources which are used to extract events from biomedical literature. ;2015-12-10",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "425af52a-ebbf-5c3a-a089-6d7912c3744e",
-    "notes": [
-        "GREC is a semantically annotated corpus of 240 MEDLINE abstracts (167 on the subject of E. coli species and 73 on the subject of the Human species) which is intended for training IE systems and/or resources which are used to extract events from biomedical literature. "
-    ],
-    "oai_identifier": [
-        "30d4a088a35a11e1a404080027e73ea2ca727b99f24940f89f64d0fab8994f4d"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text",
-        "corpus:audio",
-        "corpus:text:audio"
-    ],
-    "state": "active",
-    "title": [
-        "GREC"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4268fae8-2583-59b1-a132-985ec8bd3eae.json b/oaitestdata/clarin-oai_dc/SET_1/json/4268fae8-2583-59b1-a132-985ec8bd3eae.json
deleted file mode 100644
index 7e583434..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4268fae8-2583-59b1-a132-985ec8bd3eae.json
+++ /dev/null
@@ -1,94 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/531",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/531"
-    ],
-    "PID": "http://hdl.handle.net/11321/531",
-    "PublicationTimestamp": "2018-07-19T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Koco\u0144, Jan"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/531;2018-07-23T12:57:04Z;hdl_11321_3;hdl_11321_4;Liner2.5-events and event relations;Koco\u0144, Jan;Liner2;events;event attributes;relations between events;TimeML;atrybuty opis\u00f3w sytuacji;wyznaczniki modalno\u015bci;modality;modality relations;Liner2.5 configured for the recognition of event attributes and event relations;2018-07-19;toolService;http://hdl.handle.net/11321/531;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;Wroc\u0142aw University of Science and Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4268fae8-2583-59b1-a132-985ec8bd3eae",
-    "notes": [
-        "Liner2.5 configured for the recognition of event attributes and event relations"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/531"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Liner"
-        },
-        {
-            "name": "events"
-        },
-        {
-            "name": "event attributes"
-        },
-        {
-            "name": "relations events"
-        },
-        {
-            "name": "TimeML"
-        },
-        {
-            "name": "TimeML"
-        },
-        {
-            "name": "TimeML"
-        },
-        {
-            "name": "modality"
-        },
-        {
-            "name": "modality relations"
-        }
-    ],
-    "title": [
-        "Liner2.5-events and event relations"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/426bef24-a07d-5998-a131-449c2de62a3b.json b/oaitestdata/clarin-oai_dc/SET_1/json/426bef24-a07d-5998-a131-449c2de62a3b.json
deleted file mode 100644
index 49d64481..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/426bef24-a07d-5998-a131-449c2de62a3b.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Copenhagen Business School"
-    ],
-    "Contributor": [
-        "Schou, Lasse",
-        "Jakobsen, Arnt Lykke"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-321",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-321"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-321",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Copenhagen Business School"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Denmark"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-321;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Translog 2006;Jakobsen, Arnt Lykke;Schou, Lasse;Translog 2006 is the leading tool for analysing human text production processes. It was originally designed for translation process research, but can be used for a variety of personal learning, teaching, and research purposes.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-321;downloadable_files_count: 0;Denmark;Copenhagen Business School;http://www.translog.dk/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "426bef24-a07d-5998-a131-449c2de62a3b",
-    "notes": [
-        "Translog 2006 is the leading tool for analysing human text production processes. It was originally designed for translation process research, but can be used for a variety of personal learning, teaching, and research purposes."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-321"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Translog 2006"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/428edd5c-d634-5fbd-8ec5-61fa1be364a7.json b/oaitestdata/clarin-oai_dc/SET_1/json/428edd5c-d634-5fbd-8ec5-61fa1be364a7.json
deleted file mode 100644
index 61ffa760..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/428edd5c-d634-5fbd-8ec5-61fa1be364a7.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-4087-6",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-4087-6"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-4087-6",
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11858/00-097C-0000-0001-48F2-1",
-        "http://hdl.handle.net/11234/1-1481"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Mi\u0161utka, Jozef",
-        "Kamran, Amir",
-        "Haji\u010d, Jan",
-        "Ko\u0161arko, Ond\u0159ej",
-        "Vandas, Karel",
-        "Jos\u00edfko, Michal",
-        "Pajas, Petr",
-        "Sedl\u00e1k, Michal",
-        "Jawaid, Bushra",
-        "Stra\u0148\u00e1k, Pavel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-4087-6;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Linguistic digital repository based on DSpace;Pajas, Petr;Vandas, Karel;Mi\u0161utka, Jozef;Kamran, Amir;Jawaid, Bushra;Ko\u0161arko, Ond\u0159ej;Sedl\u00e1k, Michal;Jos\u00edfko, Michal;Stra\u0148\u00e1k, Pavel;Haji\u010d, Jan;linguistics;digital data;digital repository;language repository;linguistic data;One of the goals of LINDAT/CLARIN Centre for Language Research Infrastructure is to provide technical background to institutions or researchers who wants to share their tools and data used for research in linguistics or related research fields. The digital repository is built on a highly customised DSpace platform.;2014;toolService;http://hdl.handle.net/11858/00-097C-0000-0023-4087-6;http://hdl.handle.net/11858/00-097C-0000-0001-48F2-1;http://hdl.handle.net/11234/1-1481;downloadable_files_count: 0;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://svn.ms.mff.cuni.cz/redmine/projects/dspace-modifications",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "428edd5c-d634-5fbd-8ec5-61fa1be364a7",
-    "notes": [
-        "One of the goals of LINDAT/CLARIN Centre for Language Research Infrastructure is to provide technical background to institutions or researchers who wants to share their tools and data used for research in linguistics or related research fields. The digital repository is built on a highly customised DSpace platform."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-4087-6"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "linguistics"
-        },
-        {
-            "name": "digital data"
-        },
-        {
-            "name": "digital repository"
-        },
-        {
-            "name": "language repository"
-        },
-        {
-            "name": "linguistic data"
-        }
-    ],
-    "title": [
-        "Linguistic digital repository based on DSpace"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/42980109-4ed3-5b2a-9135-ae7f10871e67.json b/oaitestdata/clarin-oai_dc/SET_1/json/42980109-4ed3-5b2a-9135-ae7f10871e67.json
deleted file mode 100644
index 46cd4c43..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/42980109-4ed3-5b2a-9135-ae7f10871e67.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Borin, Lars"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-515",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-515"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-515",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Sweden"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-515;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Svenska ord/Lexin;Borin, Lars;appr. 20,000 entries, XML;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-515;swe;downloadable_files_count: 0;Sweden;http://spraakbanken.gu.se/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "42980109-4ed3-5b2a-9135-ae7f10871e67",
-    "notes": [
-        "appr. 20,000 entries, XML"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-515"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Svenska ord/Lexin"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/42a898a4-37f3-554a-84cf-6eb108b3620b.json b/oaitestdata/clarin-oai_dc/SET_1/json/42a898a4-37f3-554a-84cf-6eb108b3620b.json
deleted file mode 100644
index 671010a6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/42a898a4-37f3-554a-84cf-6eb108b3620b.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, Dept. of Swedish Language, G\u00f6teborg University"
-    ],
-    "Contributor": [
-        "Olsson, Leif-J\u00f6ran"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1195",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1195"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1195",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, Dept. of Swedish Language, G\u00f6teborg University"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Sweden"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1195;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;eXist;Olsson, Leif-J\u00f6ran;eXist-db is an open source database management system entirely built on XML technology. It stores XML data according to the XML data model and features efficient, index-based XQuery processing.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1195;downloadable_files_count: 0;Sweden;Spr\u00e5kbanken, Dept. of Swedish Language, G\u00f6teborg University;http://exist-db.org/exist/apps/homepage/index.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "42a898a4-37f3-554a-84cf-6eb108b3620b",
-    "notes": [
-        "eXist-db is an open source database management system entirely built on XML technology. It stores XML data according to the XML data model and features efficient, index-based XQuery processing."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1195"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "eXist"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/42c1852b-fe22-5e22-94b7-5e8c3609f893.json b/oaitestdata/clarin-oai_dc/SET_1/json/42c1852b-fe22-5e22-94b7-5e8c3609f893.json
deleted file mode 100644
index e4b92da7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/42c1852b-fe22-5e22-94b7-5e8c3609f893.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "text/xml",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Northern Sami"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/106",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/106"
-    ],
-    "PID": "http://hdl.handle.net/11509/106",
-    "PublicationTimestamp": "2015-10-10T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "The Divvun group at UiT The Arctic University of Norway",
-        "Giellatekno - Saami Language Technology, UiT The Arctic University of Norway"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/106;2016-09-06T13:03:01Z;hdl_11509_1;hdl_11509_2;North Saami lemma frequency list;Giellatekno - Saami Language Technology, UiT The Arctic University of Norway;The Divvun group at UiT The Arctic University of Norway;The Divvun group at UiT The Arctic University of Norway;Lemma Frequencies;North Saami;The North Saami lemma frequency list is work done by the Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language community. In particular, Ciprian-Virgil Gerstenberger compiled the list from the entire SIKOR North Saami corpus version 2015-10-10. The data is in an one-lemma-per-line format with the following values: <ABS_FREQ> <LEMMA> <POS>. Since the list has been derived automatically, it may contain wrong values. In case you find any errors the creators would appreciate your feedback sent to giellatekno@uit.no and feedback@divvun.no. Please note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata).;2015-10-10;corpus;http://hdl.handle.net/11509/106;sme;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;text/xml;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Giellatekno - Saami Language Technology;http://giellatekno.uit.no/index.eng.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "42c1852b-fe22-5e22-94b7-5e8c3609f893",
-    "notes": [
-        "The North Saami lemma frequency list is work done by the Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language community. In particular, Ciprian-Virgil Gerstenberger compiled the list from the entire SIKOR North Saami corpus version 2015-10-10. The data is in an one-lemma-per-line format with the following values: <ABS_FREQ> <LEMMA> <POS>. Since the list has been derived automatically, it may contain wrong values. In case you find any errors the creators would appreciate your feedback sent to giellatekno@uit.no and feedback@divvun.no. Please note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata)."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/106"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Lemma Frequencies"
-        },
-        {
-            "name": "North Saami"
-        }
-    ],
-    "title": [
-        "North Saami lemma frequency list"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/42c40f3f-4d49-5049-a0ba-9972ae53e16b.json b/oaitestdata/clarin-oai_dc/SET_1/json/42c40f3f-4d49-5049-a0ba-9972ae53e16b.json
deleted file mode 100644
index 486026f8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/42c40f3f-4d49-5049-a0ba-9972ae53e16b.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Delbecque, Nicole"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain",
-        "(1 file : ca. 119 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0439",
-    "MetadataAccess": [
-        "oai:ota:oucs:0439"
-    ],
-    "PublicationTimestamp": "1970-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1970"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Laffan, K.B. (Kevin Barry)"
-    ],
-    "fulltext": "oai:ota:oucs:0439;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0439.xml;It's a two-foot-six-inches-above-the-ground world : a comedy / by Kevin Laffan;Laffan, K.B. (Kevin Barry);1970;text_and_corpus_linguistics;English drama -- 20th century;eng;Oxford Text Archive, University of Oxford;Delbecque, Nicole;text/plain;(1 file : ca. 119 KB);Text;Plays;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "42c40f3f-4d49-5049-a0ba-9972ae53e16b",
-    "oai_identifier": [
-        "oai:ota:oucs:0439"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- th century"
-        }
-    ],
-    "title": [
-        "It's a two-foot-six-inches-above-the-ground world : a comedy / by Kevin Laffan"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0439.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/42cfd83f-398b-56d6-a499-0060ea4b944d.json b/oaitestdata/clarin-oai_dc/SET_1/json/42cfd83f-398b-56d6-a499-0060ea4b944d.json
deleted file mode 100644
index 3dd109fa..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/42cfd83f-398b-56d6-a499-0060ea4b944d.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Romanian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-492",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-492"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-492",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Romania"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-492;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Romanian Explanatory Dictionary;292.792 definitions;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-492;ron;downloadable_files_count: 0;Romania;http://dexonline.ro/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "42cfd83f-398b-56d6-a499-0060ea4b944d",
-    "notes": [
-        "292.792 definitions"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-492"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Romanian Explanatory Dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/42d53d72-148f-57f6-b650-9052b7e100db.json b/oaitestdata/clarin-oai_dc/SET_1/json/42d53d72-148f-57f6-b650-9052b7e100db.json
deleted file mode 100644
index fa505b29..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/42d53d72-148f-57f6-b650-9052b7e100db.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "University of Tartu"
-    ],
-    "Contributor": [
-        "Lindstr\u00f6m, Liina"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Estonian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-643",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-643"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-643",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Tartu"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Estonia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-643;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Estonian Dialect Corpus;Lindstr\u00f6m, Liina;Recordings of different Estonian dialects, 900000 words, transcribed and partly (400000 words) morphologically annotated;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-643;est;application/octet-stream;downloadable_files_count: 0;Estonia;University of Tartu;http://www.murre.ut.ee/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "42d53d72-148f-57f6-b650-9052b7e100db",
-    "notes": [
-        "Recordings of different Estonian dialects, 900000 words, transcribed and partly (400000 words) morphologically annotated"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-643"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Estonian Dialect Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/42edbb8b-2d32-5ef8-9b16-82ba7a417930.json b/oaitestdata/clarin-oai_dc/SET_1/json/42edbb8b-2d32-5ef8-9b16-82ba7a417930.json
deleted file mode 100644
index 7a52a102..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/42edbb8b-2d32-5ef8-9b16-82ba7a417930.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3359",
-    "MetadataAccess": [
-        "oai:ota:oucs:3359"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Holcroft, Thomas, 1745-1809."
-    ],
-    "fulltext": "oai:ota:oucs:3359;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3359.xml;The man of ten thousand: a comedy. As it is acted at the Theatre-Royal, Drury-Lane. The second edition. By Thomas Holcroft.;Holcroft, Thomas, 1745-1809.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "42edbb8b-2d32-5ef8-9b16-82ba7a417930",
-    "oai_identifier": [
-        "oai:ota:oucs:3359"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The man of ten thousand: a comedy. As it is acted at the Theatre-Royal, Drury-Lane. The second edition. By Thomas Holcroft."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3359.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4304fa92-6460-5a1e-bb72-47ef162457d3.json b/oaitestdata/clarin-oai_dc/SET_1/json/4304fa92-6460-5a1e-bb72-47ef162457d3.json
deleted file mode 100644
index 7ab31ede..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4304fa92-6460-5a1e-bb72-47ef162457d3.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Jan Wieczorek"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 4",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/424",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/424"
-    ],
-    "PID": "http://hdl.handle.net/11321/424",
-    "PublicationTimestamp": "2017-09-19T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Jan Wieczorek"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "wielu, autor\u00f3w"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/424;2017-09-20T10:27:48Z;hdl_11321_3;hdl_11321_4;Przem\u00f3wienia polityczne - test;wielu, autor\u00f3w;przem\u00f3wienia;polityka;retoryka;Test korpsusu przem\u00f3wie\u0144;2017-09-19;corpus;http://hdl.handle.net/11321/424;pol;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/zip;downloadable_files_count: 4;Jan Wieczorek",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4304fa92-6460-5a1e-bb72-47ef162457d3",
-    "notes": [
-        "Test korpsusu przem\u00f3wie\u0144"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/424"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "polityka"
-        },
-        {
-            "name": "retoryka"
-        }
-    ],
-    "title": [
-        "Przem\u00f3wienia polityczne - test"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/435154fc-71ec-5dd5-bf03-9ec0e39226b1.json b/oaitestdata/clarin-oai_dc/SET_1/json/435154fc-71ec-5dd5-bf03-9ec0e39226b1.json
deleted file mode 100644
index b76a1408..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/435154fc-71ec-5dd5-bf03-9ec0e39226b1.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Wiktor Walentynowicz"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 4",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/425",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/425"
-    ],
-    "PID": "http://hdl.handle.net/11321/425",
-    "PublicationTimestamp": "2017-09-25T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Wiktor Walentynowicz"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Walentynowicz, Wiktor"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/425;2017-09-25T11:46:32Z;hdl_11321_3;hdl_11321_4;MorphoDiTa-based tagger for Polish language;Walentynowicz, Wiktor;part of speech tagging;tagger;Polish;MorphoDiTa-based tagger for Polish language. It is a tool for morphosyntactic unification for the Polish language, according to the NKJP tagset.;2017-09-25;toolService;http://hdl.handle.net/11321/425;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 4;Wiktor Walentynowicz",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "435154fc-71ec-5dd5-bf03-9ec0e39226b1",
-    "notes": [
-        "MorphoDiTa-based tagger for Polish language. It is a tool for morphosyntactic unification for the Polish language, according to the NKJP tagset."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/425"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "part speech tagging"
-        },
-        {
-            "name": "tagger"
-        },
-        {
-            "name": "Polish"
-        }
-    ],
-    "title": [
-        "MorphoDiTa-based tagger for Polish language"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/43604501-383a-5afd-8fbc-d11641dd36f1.json b/oaitestdata/clarin-oai_dc/SET_1/json/43604501-383a-5afd-8fbc-d11641dd36f1.json
deleted file mode 100644
index 414c5ed3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/43604501-383a-5afd-8fbc-d11641dd36f1.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3681",
-    "MetadataAccess": [
-        "oai:ota:oucs:3681"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pope, Alexander, 1688-1744."
-    ],
-    "fulltext": "oai:ota:oucs:3681;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3681.xml;A further account of the most deplorable condition of Mr. Edmund Curll, bookseller. Since his being poison'd on the 28th of March. To be publish'd weekly;Pope, Alexander, 1688-1744.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "43604501-383a-5afd-8fbc-d11641dd36f1",
-    "oai_identifier": [
-        "oai:ota:oucs:3681"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A further account of the most deplorable condition of Mr. Edmund Curll, bookseller. Since his being poison'd on the 28th of March. To be publish'd weekly"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3681.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4379d2c3-71d1-5e43-be1e-9549a24edf57.json b/oaitestdata/clarin-oai_dc/SET_1/json/4379d2c3-71d1-5e43-be1e-9549a24edf57.json
deleted file mode 100644
index 95bc01d9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4379d2c3-71d1-5e43-be1e-9549a24edf57.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4530",
-    "MetadataAccess": [
-        "oai:ota:oucs:4530"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Defoe, Daniel, 1661?-1731."
-    ],
-    "fulltext": "oai:ota:oucs:4530;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4530.xml;A tour thro' the whole island of Great Britain: Divided into circuits or journeys. Giving a particular and entertaining account of whatever is curious, and worth observation; ... By a gentleman. ... [pt.4];Defoe, Daniel, 1661?-1731.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4379d2c3-71d1-5e43-be1e-9549a24edf57",
-    "oai_identifier": [
-        "oai:ota:oucs:4530"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A tour thro' the whole island of Great Britain: Divided into circuits or journeys. Giving a particular and entertaining account of whatever is curious, and worth observation; ... By a gentleman. ... [pt.4]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4530.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/438eb2f4-ac4b-51fc-9cb2-1713fec3554f.json b/oaitestdata/clarin-oai_dc/SET_1/json/438eb2f4-ac4b-51fc-9cb2-1713fec3554f.json
deleted file mode 100644
index 77e41289..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/438eb2f4-ac4b-51fc-9cb2-1713fec3554f.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Sven Sellmer"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Sanskrit"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/457",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/457"
-    ],
-    "PID": "http://hdl.handle.net/11321/457",
-    "PublicationTimestamp": "2018-04-11T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Sven Sellmer"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Sellmer, Sven"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/457;2018-04-11T09:50:08Z;hdl_11321_3;hdl_11321_4;Mahabharata_sample;Sellmer, Sven;Sanskrit epics;lemmatised Sanskrit text with lemma IDs, white-space delimited;2018-04-11;corpus;http://hdl.handle.net/11321/457;Sanskrit;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;Sven Sellmer",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "438eb2f4-ac4b-51fc-9cb2-1713fec3554f",
-    "notes": [
-        "lemmatised Sanskrit text with lemma IDs, white-space delimited"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/457"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Sanskrit epics"
-        }
-    ],
-    "title": [
-        "Mahabharata_sample"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/439b24fd-32c3-5314-b228-b36c6354b7ea.json b/oaitestdata/clarin-oai_dc/SET_1/json/439b24fd-32c3-5314-b228-b36c6354b7ea.json
deleted file mode 100644
index 7a737c77..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/439b24fd-32c3-5314-b228-b36c6354b7ea.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2866",
-    "MetadataAccess": [
-        "oai:ota:oucs:2866"
-    ],
-    "PublicationTimestamp": "1738-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1738"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2866;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2866.xml;A proposal for giving badges to the beggars in all the parishes of Dublin;Swift, Jonathan, 1667-1745;1738;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "439b24fd-32c3-5314-b228-b36c6354b7ea",
-    "oai_identifier": [
-        "oai:ota:oucs:2866"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A proposal for giving badges to the beggars in all the parishes of Dublin"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2866.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/43b3a001-4803-5c5c-bb7f-130ac9dcf517.json b/oaitestdata/clarin-oai_dc/SET_1/json/43b3a001-4803-5c5c-bb7f-130ac9dcf517.json
deleted file mode 100644
index c0a31a9b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/43b3a001-4803-5c5c-bb7f-130ac9dcf517.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4563",
-    "MetadataAccess": [
-        "oai:ota:oucs:4563"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Lennox, Charlotte, ca. 1729-1804."
-    ],
-    "fulltext": "oai:ota:oucs:4563;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4563.xml;Henrietta: By the author of The female Quixote. In two volumes. ... [pt.1];Lennox, Charlotte, ca. 1729-1804.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "43b3a001-4803-5c5c-bb7f-130ac9dcf517",
-    "oai_identifier": [
-        "oai:ota:oucs:4563"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Henrietta: By the author of The female Quixote. In two volumes. ... [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4563.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/43bd1998-2ef9-5e8a-8d84-f536aa60ce7e.json b/oaitestdata/clarin-oai_dc/SET_1/json/43bd1998-2ef9-5e8a-8d84-f536aa60ce7e.json
deleted file mode 100644
index cef487ea..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/43bd1998-2ef9-5e8a-8d84-f536aa60ce7e.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, Dept. of Swedish Language, G\u00f6teborg University"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1303",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1303"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1303",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, Dept. of Swedish Language, G\u00f6teborg University"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Sweden"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Forsberg, Markus",
-        "Ranta, Aarne"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1303;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Functional Morphology;Forsberg, Markus;Ranta, Aarne;morphology;Functional Morphology is a development environment for computational morphologies.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1303;downloadable_files_count: 0;Sweden;Spr\u00e5kbanken, Dept. of Swedish Language, G\u00f6teborg University;http://www.cs.chalmers.se/~markus/FM/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "43bd1998-2ef9-5e8a-8d84-f536aa60ce7e",
-    "notes": [
-        "Functional Morphology is a development environment for computational morphologies."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1303"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphology"
-        }
-    ],
-    "title": [
-        "Functional Morphology"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/43de06ce-e5c7-5262-83ad-b238562d99b6.json b/oaitestdata/clarin-oai_dc/SET_1/json/43de06ce-e5c7-5262-83ad-b238562d99b6.json
deleted file mode 100644
index dd3a53fe..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/43de06ce-e5c7-5262-83ad-b238562d99b6.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Chinese",
-        "Czech",
-        "English",
-        "French",
-        "German",
-        "Latin",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1072",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1072"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1072",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United States"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1072;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Botanicus Digital Library;Germanistik;Digital copies of historical botanic papers from the Missouri Botanical Garden Library; Bilddigitalisate von historischen botanischen Schriften; deutschsprachige Texte stellen nur einen Teilbereich dar;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1072;zho;ces;eng;fra;deu;lat;spa;downloadable_files_count: 0;United States;http://www.botanicus.org/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "43de06ce-e5c7-5262-83ad-b238562d99b6",
-    "notes": [
-        "Digital copies of historical botanic papers from the Missouri Botanical Garden Library; Bilddigitalisate von historischen botanischen Schriften; deutschsprachige Texte stellen nur einen Teilbereich dar"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1072"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Botanicus Digital Library"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/43e3b680-640f-5a3c-a87d-92b647bd75f9.json b/oaitestdata/clarin-oai_dc/SET_1/json/43e3b680-640f-5a3c-a87d-92b647bd75f9.json
deleted file mode 100644
index c35abdd6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/43e3b680-640f-5a3c-a87d-92b647bd75f9.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Universiteit van Amsterdam"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-688",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-688"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-688",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Universiteit van Amsterdam"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Code of conduct"
-    ],
-    "SpatialCoverage": [
-        "Sri Lanka"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-688;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Sri Lanka Malay corpus;Documentation of the Sri Lanka Malay project (DoBeS project);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-688;Code of conduct;downloadable_files_count: 0;Sri Lanka;Universiteit van Amsterdam;http://corpus1.mpi.nl/ds/imdi_browser/?openpath=MPI515582%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "43e3b680-640f-5a3c-a87d-92b647bd75f9",
-    "notes": [
-        "Documentation of the Sri Lanka Malay project (DoBeS project)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-688"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Sri Lanka Malay corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/43e71835-889b-58d4-834b-a99b4a70ecd4.json b/oaitestdata/clarin-oai_dc/SET_1/json/43e71835-889b-58d4-834b-a99b4a70ecd4.json
deleted file mode 100644
index 791f3000..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/43e71835-889b-58d4-834b-a99b4a70ecd4.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-57",
-    "MetadataAccess": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-57"
-    ],
-    "PID": "http://hdl.handle.net/20.500.11752/ILC-57",
-    "PublicationTimestamp": "2016-05-18T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Rosmini - Serbati, Antonio"
-    ],
-    "fulltext": "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-57;2018-07-23T09:13:44Z;hdl_000-c0-111_38;hdl_000-c0-111_49;Corpus Antonio Rosmini - Serbati;Rosmini - Serbati, Antonio;Lessico Rosminiano;Filosofia;Religione;Philosophy;Religion;Rosminian Lexicon;Corpus Rosmini\r\nRaccolta di opere per il Lessico Rosminiano realizzata in collaborazione con il Centro di Studi per i Problemi Filosofici e Religiosi dell'800 italiano e francese negli anni '70 - '80 (oggi ISPF-CNR).\r\n\r\n----\r\n\r\nNel 1969 il C.N.R. istituisce, sotto la direzione di Michele Federico Sciacca, presso l\u2019Istituto\r\ndi Filosofia della Facolt\u00e0 di Magistero dell\u2019Universit\u00e0 degli Studi di Genova, il\r\nCentro di studio dei problemi filosofici e religiosi dell\u2019Ottocento italiano e francese. Nel\r\n1971 a Sciacca succede Maria Adelaide Raschini, ordinario di Storia della Filosofia.\r\nNel 1981 viene nominato direttore Evandro Agazzi, ordinario di filosofia della scienza.\r\nQuesti nel 1982, interrompendo l\u2019attivit\u00e0 pi\u00f9 caratterizzante del Centro, ovvero\r\nl\u2019elaborazione del Lessico Rosminiano, in accordo con il Consiglio scientifico, amplia\r\ngli ambiti di ricerca del Centro, estendendoli ai temi e problemi della filosofia\r\ncontemporanea in generale, avvia nuove collaborazioni con l\u2019Istituto di Filosofia della\r\nFacolt\u00e0 di Lettere e Filosofia, muta il nome del Centro in Centro di studio sulla filosofia\r\ncontemporanea (C.S.F.C.)\r\nNell\u2019ottobre del 1999, viene nominato direttore pro tempore Franco Ottonello, Primo\r\nRicercatore del Centro stesso.\r\nIl 30 aprile 2002 il C.S.F.C. viene soppresso, mentre il personale ancora in servizio al\r\ndicembre 2001 confluisce nell\u2019Istituto per la storia del pensiero filosofico e scientifico\r\nmoderno di Napoli, diretto da Enrico Isacco Rambaldi Feldmann, ordinario di Storia\r\ndella Filosofia dell\u2019Universit\u00e0 di Milano.\r\n\r\nFonte: \r\nSilvia Caianiello \u2013 Manuela Sanna (Napoli, ISPF, 2011)\r\n\u201cIstituto per la storia del pensiero filosofico e scientifico moderno\u201d del Consiglio Nazionale delle Ricerche;2016-05-18;corpus;http://hdl.handle.net/20.500.11752/ILC-57;ita;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "43e71835-889b-58d4-834b-a99b4a70ecd4",
-    "notes": [
-        "Corpus Rosmini\r\nRaccolta di opere per il Lessico Rosminiano realizzata in collaborazione con il Centro di Studi per i Problemi Filosofici e Religiosi dell'800 italiano e francese negli anni '70 - '80 (oggi ISPF-CNR).\r\n\r\n----\r\n\r\nNel 1969 il C.N.R. istituisce, sotto la direzione di Michele Federico Sciacca, presso l\u2019Istituto\r\ndi Filosofia della Facolt\u00e0 di Magistero dell\u2019Universit\u00e0 degli Studi di Genova, il\r\nCentro di studio dei problemi filosofici e religiosi dell\u2019Ottocento italiano e francese. Nel\r\n1971 a Sciacca succede Maria Adelaide Raschini, ordinario di Storia della Filosofia.\r\nNel 1981 viene nominato direttore Evandro Agazzi, ordinario di filosofia della scienza.\r\nQuesti nel 1982, interrompendo l\u2019attivit\u00e0 pi\u00f9 caratterizzante del Centro, ovvero\r\nl\u2019elaborazione del Lessico Rosminiano, in accordo con il Consiglio scientifico, amplia\r\ngli ambiti di ricerca del Centro, estendendoli ai temi e problemi della filosofia\r\ncontemporanea in generale, avvia nuove collaborazioni con l\u2019Istituto di Filosofia della\r\nFacolt\u00e0 di Lettere e Filosofia, muta il nome del Centro in Centro di studio sulla filosofia\r\ncontemporanea (C.S.F.C.)\r\nNell\u2019ottobre del 1999, viene nominato direttore pro tempore Franco Ottonello, Primo\r\nRicercatore del Centro stesso.\r\nIl 30 aprile 2002 il C.S.F.C. viene soppresso, mentre il personale ancora in servizio al\r\ndicembre 2001 confluisce nell\u2019Istituto per la storia del pensiero filosofico e scientifico\r\nmoderno di Napoli, diretto da Enrico Isacco Rambaldi Feldmann, ordinario di Storia\r\ndella Filosofia dell\u2019Universit\u00e0 di Milano.\r\n\r\nFonte: \r\nSilvia Caianiello \u2013 Manuela Sanna (Napoli, ISPF, 2011)\r\n\u201cIstituto per la storia del pensiero filosofico e scientifico moderno\u201d del Consiglio Nazionale delle Ricerche"
-    ],
-    "oai_identifier": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-57"
-    ],
-    "oai_set": [
-        "hdl_000-c0-111_38",
-        "hdl_000-c0-111_49"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Lessico Rosminiano"
-        },
-        {
-            "name": "Filosofia"
-        },
-        {
-            "name": "Religione"
-        },
-        {
-            "name": "Philosophy"
-        },
-        {
-            "name": "Religion"
-        },
-        {
-            "name": "Rosminian Lexicon"
-        }
-    ],
-    "title": [
-        "Corpus Antonio Rosmini - Serbati"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/43e9fde3-028f-596d-8497-56ff9d52c649.json b/oaitestdata/clarin-oai_dc/SET_1/json/43e9fde3-028f-596d-8497-56ff9d52c649.json
deleted file mode 100644
index 0e2d7da4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/43e9fde3-028f-596d-8497-56ff9d52c649.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Warsztatowski"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "downloadable_files_count: 10",
-        "application/vnd.oasis.opendocument.text",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/435",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/435"
-    ],
-    "PID": "http://hdl.handle.net/11321/435",
-    "PublicationTimestamp": "2017-10-12T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Warsztatowski"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "IS PAS corpora license",
-        "http://clarin-pl.eu/en/licenses/is-pas-corpora-license/",
-        "CC"
-    ],
-    "author": [
-        "warsztatowski, warsztatoslaw"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/435;2017-10-12T15:09:42Z;hdl_11321_3;hdl_11321_4;Warsztaty olsztyn js;warsztatowski, warsztatoslaw;warsztaty;Warsztaty Olsztyn 12.10;2017-10-12;corpus;http://hdl.handle.net/11321/435;pol;IS PAS corpora license;http://clarin-pl.eu/en/licenses/is-pas-corpora-license/;CC;text/plain; charset=utf-8;text/plain;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;text/plain;application/vnd.oasis.opendocument.text;downloadable_files_count: 10;Warsztatowski",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "43e9fde3-028f-596d-8497-56ff9d52c649",
-    "notes": [
-        "Warsztaty Olsztyn 12.10"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/435"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "warsztaty"
-        }
-    ],
-    "title": [
-        "Warsztaty olsztyn js"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4439a459-5a30-5514-88df-fa0686071d75.json b/oaitestdata/clarin-oai_dc/SET_1/json/4439a459-5a30-5514-88df-fa0686071d75.json
deleted file mode 100644
index 269ab353..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4439a459-5a30-5514-88df-fa0686071d75.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Bailey, Richard W.",
-        "Robinson, Jay L., 1932-"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(10 files : total of ca. 20.6 MB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0171",
-    "MetadataAccess": [
-        "oai:ota:oucs:0171"
-    ],
-    "PublicationTimestamp": "1400-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1400"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Anthologies"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:0171;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0171.xml;Michigan Early Modern English materials / compiled by Richard W. Bailey, Jay L. Robinson, James W. Downer, and Patricia V. Lehman;1400-1899;text_and_corpus_linguistics;Linguistic analysis (Linguistics);Anthologies -- United States -- 20th century;eng;Oxford Text Archive, University of Oxford;Bailey, Richard W.;Robinson, Jay L., 1932-;Bailey, Richard W.;text/plain;(10 files : total of ca. 20.6 MB);Text;Anthologies;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4439a459-5a30-5514-88df-fa0686071d75",
-    "oai_identifier": [
-        "oai:ota:oucs:0171"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Linguistic analysis Linguistics"
-        },
-        {
-            "name": "Anthologies -- United States -- th century"
-        }
-    ],
-    "title": [
-        "Michigan Early Modern English materials / compiled by Richard W. Bailey, Jay L. Robinson, James W. Downer, and Patricia V. Lehman"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0171.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/444534b7-c4ad-572d-b44d-2103a4395339.json b/oaitestdata/clarin-oai_dc/SET_1/json/444534b7-c4ad-572d-b44d-2103a4395339.json
deleted file mode 100644
index 5bbcc9c3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/444534b7-c4ad-572d-b44d-2103a4395339.json
+++ /dev/null
@@ -1,103 +0,0 @@
-{
-    "Contact": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 3",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1165",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1165"
-    ],
-    "PID": "http://hdl.handle.net/11356/1165",
-    "PublicationTimestamp": "2017-11-23T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11356/1052",
-        "http://hdl.handle.net/11356/1181"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Krek, Simon",
-        "Zupan, Katja",
-        "Dobrovoljc, Kaja",
-        "Erjavec, Toma\u017e",
-        "Kuzman, Taja",
-        "Gantar, Polona",
-        "Ledinek, Nina",
-        "Holz, Nanika",
-        "Mo\u017ee, Sara"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1165;2018-05-28T11:32:45Z;hdl_11356_1023;hdl_11356_1024;Training corpus ssj500k 2.0;Krek, Simon;Dobrovoljc, Kaja;Erjavec, Toma\u017e;Mo\u017ee, Sara;Ledinek, Nina;Holz, Nanika;Zupan, Katja;Gantar, Polona;Kuzman, Taja;tagging;dependency treebank;parsing;named entities;tokenisation;manual annotation;TEI;verbal multiword expressions;The ssj500k training corpus contains about 500,000 tokens manually annotated on the levels of tokenisation, sentence segmentation, morphosyntactic tagging, and lemmatisation. About half of the corpus is also manually annotated with syntactic dependencies, named entities, and verbal multiword expressions. \r\n\r\nThe annotations of the ssj500k corpus follow (1) the MULTEXT-East V5 morphosyntactic specifications for Slovene, http://nl.ijs.si/ME/V5/msd/, (2) the JOS dependency schema, http://nl.ijs.si/jos/bib/jos-skladnja-navodila.pdf, (3) the Janes Annotation guidelines for Slovenian named entities, http://nl.ijs.si/janes/wp-content/uploads/2017/09/SlovenianNER-eng-v1.1.pdf, and the Guidelines of the PARSEME shared task on verbal multiword expressions, http://parsemefr.lif.univ-mrs.fr/parseme-st-guidelines/1.0/\r\nThe vocabulary of (1) and (2) is provided in the back element and (3) and (4) in the teiHeader of the TEI encoded corpus.;2017-11-23;corpus;http://hdl.handle.net/11356/1165;slv;http://hdl.handle.net/11356/1052;http://hdl.handle.net/11356/1181;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);https://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 3;Centre for Language Resources and Technologies, University of Ljubljana;http://eng.slovenscina.eu/tehnologije/ucni-korpus",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "444534b7-c4ad-572d-b44d-2103a4395339",
-    "notes": [
-        "The ssj500k training corpus contains about 500,000 tokens manually annotated on the levels of tokenisation, sentence segmentation, morphosyntactic tagging, and lemmatisation. About half of the corpus is also manually annotated with syntactic dependencies, named entities, and verbal multiword expressions. \r\n\r\nThe annotations of the ssj500k corpus follow (1) the MULTEXT-East V5 morphosyntactic specifications for Slovene, http://nl.ijs.si/ME/V5/msd/, (2) the JOS dependency schema, http://nl.ijs.si/jos/bib/jos-skladnja-navodila.pdf, (3) the Janes Annotation guidelines for Slovenian named entities, http://nl.ijs.si/janes/wp-content/uploads/2017/09/SlovenianNER-eng-v1.1.pdf, and the Guidelines of the PARSEME shared task on verbal multiword expressions, http://parsemefr.lif.univ-mrs.fr/parseme-st-guidelines/1.0/\r\nThe vocabulary of (1) and (2) is provided in the back element and (3) and (4) in the teiHeader of the TEI encoded corpus."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1165"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "dependency treebank"
-        },
-        {
-            "name": "parsing"
-        },
-        {
-            "name": "named entities"
-        },
-        {
-            "name": "tokenisation"
-        },
-        {
-            "name": "manual annotation"
-        },
-        {
-            "name": "TEI"
-        },
-        {
-            "name": "verbal multiword expressions"
-        }
-    ],
-    "title": [
-        "Training corpus ssj500k 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/444b6a78-feaf-5102-91fb-345b27f3d975.json b/oaitestdata/clarin-oai_dc/SET_1/json/444b6a78-feaf-5102-91fb-345b27f3d975.json
deleted file mode 100644
index d83c267f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/444b6a78-feaf-5102-91fb-345b27f3d975.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "TALG Research Group (University of Vigo)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Galician"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-618",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-618"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-618",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "TALG Research Group (University of Vigo)"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-618;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Aqu\u00e9n - Toponimia galega;Galician Toponymy Database, 40,000 entries;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-618;glg;downloadable_files_count: 0;Spain;TALG Research Group (University of Vigo);http://sli.uvigo.es/toponimia",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "444b6a78-feaf-5102-91fb-345b27f3d975",
-    "notes": [
-        "Galician Toponymy Database, 40,000 entries"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-618"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Aqu\u00e9n - Toponimia galega"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/444be4eb-fa42-5432-acc0-5c403ab1170e.json b/oaitestdata/clarin-oai_dc/SET_1/json/444be4eb-fa42-5432-acc0-5c403ab1170e.json
deleted file mode 100644
index 45b1725d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/444be4eb-fa42-5432-acc0-5c403ab1170e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1008",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1008"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1008",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1008;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LAC Jaminjung/Ngaliwurru Corpus;Language and Cognition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1008;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI28904%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "444be4eb-fa42-5432-acc0-5c403ab1170e",
-    "notes": [
-        "Language and Cognition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1008"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LAC Jaminjung/Ngaliwurru Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/444cdd56-22f4-5202-aab8-eb41cdf23610.json b/oaitestdata/clarin-oai_dc/SET_1/json/444cdd56-22f4-5202-aab8-eb41cdf23610.json
deleted file mode 100644
index 4925589f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/444cdd56-22f4-5202-aab8-eb41cdf23610.json
+++ /dev/null
@@ -1,90 +0,0 @@
-{
-    "Contact": [
-        "Wroclaw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/289",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/289"
-    ],
-    "PID": "http://hdl.handle.net/11321/289",
-    "PublicationTimestamp": "2016-04-27T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroclaw University of Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Piasecki, Maciej",
-        "Szpakowicz, Stan",
-        "Maziarz, Marek"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/289;2016-06-03T14:44:36Z;hdl_11321_3;hdl_11321_4;Polish corpus of plWordNet usage examples;Maziarz, Marek;Piasecki, Maciej;Szpakowicz, Stan;plWordNet;corpus;usage examples;Creative Commons;sense;semantics;lexicography;Corpus of 83k usage examples taken from plWordNet 3.0. All annotated with specific sense. All published on open licences.;2016-04-27;corpus;http://hdl.handle.net/11321/289;Polish;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 1;Wroclaw University of Technology;http://clarin-pl.eu/pl/o-projekcie/clarin-pl/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "444cdd56-22f4-5202-aab8-eb41cdf23610",
-    "notes": [
-        "Corpus of 83k usage examples taken from plWordNet 3.0. All annotated with specific sense. All published on open licences."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/289"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "plWordNet"
-        },
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "usage examples"
-        },
-        {
-            "name": "Creative Commons"
-        },
-        {
-            "name": "sense"
-        },
-        {
-            "name": "semantics"
-        },
-        {
-            "name": "lexicography"
-        }
-    ],
-    "title": [
-        "Polish corpus of plWordNet usage examples"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4456ecf1-eac5-5eae-96e1-a24409e056e0.json b/oaitestdata/clarin-oai_dc/SET_1/json/4456ecf1-eac5-5eae-96e1-a24409e056e0.json
deleted file mode 100644
index 21e41c5a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4456ecf1-eac5-5eae-96e1-a24409e056e0.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish",
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/73",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/73"
-    ],
-    "PID": "http://hdl.handle.net/10794/73",
-    "PublicationTimestamp": "2015-04-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/73;2017-10-31T15:45:21Z;hdl_10794_1;hdl_10794_2;ASPAC \u2013 Swedish-Czech (2017-10-16);ASPAC \u2013 svenska-tjeckiska (2017-10-16);n/a, n/a;ASPAC;Parallel;Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.;Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat.;2015-04-16;corpus;http://hdl.handle.net/10794/73;swe;ces;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/octet-stream;application/gzip;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/aspacsvcs",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4456ecf1-eac5-5eae-96e1-a24409e056e0",
-    "notes": [
-        "Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.",
-        "Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/73"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ASPAC"
-        },
-        {
-            "name": "Parallel"
-        }
-    ],
-    "title": [
-        "ASPAC \u2013 Swedish-Czech (2017-10-16)",
-        "ASPAC \u2013 svenska-tjeckiska (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/44611c25-fc50-54f3-abcf-0e51680efc80.json b/oaitestdata/clarin-oai_dc/SET_1/json/44611c25-fc50-54f3-abcf-0e51680efc80.json
deleted file mode 100644
index 1bc1f1e7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/44611c25-fc50-54f3-abcf-0e51680efc80.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3121",
-    "MetadataAccess": [
-        "oai:ota:oucs:3121"
-    ],
-    "PublicationTimestamp": "1904-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1904"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "James, Henry, 1843-1916"
-    ],
-    "fulltext": "oai:ota:oucs:3121;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3121.xml;The Golden Bowl;James, Henry, 1843-1916;not after: 1904;text_and_corpus_linguistics;Fiction -- Great Britain -- 19th century;Novels -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "44611c25-fc50-54f3-abcf-0e51680efc80",
-    "oai_identifier": [
-        "oai:ota:oucs:3121"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- Great Britain -- th century"
-        },
-        {
-            "name": "Novels -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "The Golden Bowl"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3121.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/446726fa-2ad5-5346-946a-4adef078b0f9.json b/oaitestdata/clarin-oai_dc/SET_1/json/446726fa-2ad5-5346-946a-4adef078b0f9.json
deleted file mode 100644
index e8d951fe..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/446726fa-2ad5-5346-946a-4adef078b0f9.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Ibtikarat Team"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/xml",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Arabic"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1938",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1938"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1938",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Ibtikarat Team"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)",
-        "http://creativecommons.org/licenses/by-nc/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Namly, Driss"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1938;2017-02-06T11:05:02Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Contemporary Arabic dictionary;Namly, Driss;lexical semantics;An XML-based file containing the electronic version of al logha al arabia al moassira (Contemporary Arabic) dictionary. An Arabic monolingual dictionary accomplished by Ahmed Mukhtar Abdul Hamid Omar (deceased: 1424) with the help of a working group;2015;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1938;ara;Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0);http://creativecommons.org/licenses/by-nc/4.0/;PUB;text/xml;text/plain; charset=utf-8;downloadable_files_count: 1;Ibtikarat Team;http://arabic.emi.ac.ma/ibtikarat/?q=Resources",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "446726fa-2ad5-5346-946a-4adef078b0f9",
-    "notes": [
-        "An XML-based file containing the electronic version of al logha al arabia al moassira (Contemporary Arabic) dictionary. An Arabic monolingual dictionary accomplished by Ahmed Mukhtar Abdul Hamid Omar (deceased: 1424) with the help of a working group"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1938"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "lexical semantics"
-        }
-    ],
-    "title": [
-        "Contemporary Arabic dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/44b049f2-7c09-57e7-a212-966e3f374a68.json b/oaitestdata/clarin-oai_dc/SET_1/json/44b049f2-7c09-57e7-a212-966e3f374a68.json
deleted file mode 100644
index 7b4872e5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/44b049f2-7c09-57e7-a212-966e3f374a68.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "Contributor": [
-        "Woli\u0144ski, Marcin"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-274",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-274"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-274",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Poland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-274;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Morfeusz;Woli\u0144ski, Marcin;Morfeusz is a morphological analyser (not stemmer, not tagger) for Polish, withouth a guesser - so it's a morphological dictionary of a kind. Note it's a library, not a ready program. There exist modules developed by external authors, allowing to use Morfeusz in Java and Python.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-274;pol;downloadable_files_count: 0;Poland;Institute of Computer Science, Polish Academy of Sciences;http://sgjp.pl/morfeusz/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "44b049f2-7c09-57e7-a212-966e3f374a68",
-    "notes": [
-        "Morfeusz is a morphological analyser (not stemmer, not tagger) for Polish, withouth a guesser - so it's a morphological dictionary of a kind. Note it's a library, not a ready program. There exist modules developed by external authors, allowing to use Morfeusz in Java and Python."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-274"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Morfeusz"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/44b8be9b-0bf1-5fcf-b8a9-5486864708e6.json b/oaitestdata/clarin-oai_dc/SET_1/json/44b8be9b-0bf1-5fcf-b8a9-5486864708e6.json
deleted file mode 100644
index 59948901..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/44b8be9b-0bf1-5fcf-b8a9-5486864708e6.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Universidade Nova de Lisboa, Centro de Lingu\u00edstica"
-    ],
-    "Contributor": [
-        "Xavier, Maria Francisca"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Portuguese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-390",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-390"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-390",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Universidade Nova de Lisboa, Centro de Lingu\u00edstica"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Portugal"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-390;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Corpus Informatizado de Portugu\u00eas Medieval;Xavier, Maria Francisca;Medieval Portuguese;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-390;por;downloadable_files_count: 0;Portugal;Universidade Nova de Lisboa, Centro de Lingu\u00edstica;http://cipm.fcsh.unl.pt/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "44b8be9b-0bf1-5fcf-b8a9-5486864708e6",
-    "notes": [
-        "Medieval Portuguese"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-390"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus Informatizado de Portugu\u00eas Medieval"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/44de59bd-9426-5cf7-a40b-7dedd789f733.json b/oaitestdata/clarin-oai_dc/SET_1/json/44de59bd-9426-5cf7-a40b-7dedd789f733.json
deleted file mode 100644
index 79c49095..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/44de59bd-9426-5cf7-a40b-7dedd789f733.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "66 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0553",
-    "MetadataAccess": [
-        "oai:ota:oucs:0553"
-    ],
-    "PublicationTimestamp": "1919-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1919"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Juvenilia"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Ashford, Daisy"
-    ],
-    "fulltext": "oai:ota:oucs:0553;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0553.xml; The young visiters  / compiled by Roger Mitton;Ashford, Daisy;1919;text_and_corpus_linguistics;Juvenilia -- England -- 20th century;eng;Oxford Text Archive, University of Oxford;66 KB;Text;Juvenilia;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "44de59bd-9426-5cf7-a40b-7dedd789f733",
-    "oai_identifier": [
-        "oai:ota:oucs:0553"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Juvenilia -- England -- th century"
-        }
-    ],
-    "title": [
-        " The young visiters  / compiled by Roger Mitton"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0553.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/44f9fe34-e0a2-5969-a9c6-c1cb67e7d73e.json b/oaitestdata/clarin-oai_dc/SET_1/json/44f9fe34-e0a2-5969-a9c6-c1cb67e7d73e.json
deleted file mode 100644
index 715e8e61..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/44f9fe34-e0a2-5969-a9c6-c1cb67e7d73e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3619",
-    "MetadataAccess": [
-        "oai:ota:oucs:3619"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Defoe, Daniel, 1661?-1731."
-    ],
-    "fulltext": "oai:ota:oucs:3619;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3619.xml;The evident advantages to Great Britain and its allies from the approaching war: especially in matters of trade. To which is added two curious plans, one of the port and bay of Havana; the other of Porto-Belo;Defoe, Daniel, 1661?-1731.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "44f9fe34-e0a2-5969-a9c6-c1cb67e7d73e",
-    "oai_identifier": [
-        "oai:ota:oucs:3619"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The evident advantages to Great Britain and its allies from the approaching war: especially in matters of trade. To which is added two curious plans, one of the port and bay of Havana; the other of Porto-Belo"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3619.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/44fe5826-cbcd-5e6f-a901-67dabd5ac904.json b/oaitestdata/clarin-oai_dc/SET_1/json/44fe5826-cbcd-5e6f-a901-67dabd5ac904.json
deleted file mode 100644
index d7a91a74..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/44fe5826-cbcd-5e6f-a901-67dabd5ac904.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Lexical Computing"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/x-xz"
-    ],
-    "Language": [
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2506",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2506"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2506",
-    "PublicationTimestamp": "2012-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Lexical Computing"
-    ],
-    "RelatedIdentifier": [
-        "https://www.sketchengine.co.uk/wp-content/uploads/2015/05/Latin_historical_corpus_2013.pdf"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "McGillivray, Barbara"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2506;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;LatinISE corpus;McGillivray, Barbara;latin corpus;The LatinISE corpus is a text corpus collected from the LacusCurtius, Intratext and Musisque Deoque websites. Corpus texts have rich metadata containing information as genre, title, century or specific date.\r\n\r\nThis Latin corpus was built by Barbara McGillivray.;2012;corpus;http://hdl.handle.net/11234/1-2506;lat;https://www.sketchengine.co.uk/wp-content/uploads/2015/05/Latin_historical_corpus_2013.pdf;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;PUB;application/x-xz;text/plain; charset=utf-8;downloadable_files_count: 1;Lexical Computing;https://www.sketchengine.co.uk/latin-corpus/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "44fe5826-cbcd-5e6f-a901-67dabd5ac904",
-    "notes": [
-        "The LatinISE corpus is a text corpus collected from the LacusCurtius, Intratext and Musisque Deoque websites. Corpus texts have rich metadata containing information as genre, title, century or specific date.\r\n\r\nThis Latin corpus was built by Barbara McGillivray."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2506"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "latin corpus"
-        }
-    ],
-    "title": [
-        "LatinISE corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/451d59a0-590d-5ede-bbcb-68e2a610dcc5.json b/oaitestdata/clarin-oai_dc/SET_1/json/451d59a0-590d-5ede-bbcb-68e2a610dcc5.json
deleted file mode 100644
index 4fc870e1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/451d59a0-590d-5ede-bbcb-68e2a610dcc5.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3591",
-    "MetadataAccess": [
-        "oai:ota:oucs:3591"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Churchill, Charles, 1731-1764."
-    ],
-    "fulltext": "oai:ota:oucs:3591;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3591.xml;The author: A poem. By C. Churchill.;Churchill, Charles, 1731-1764.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "451d59a0-590d-5ede-bbcb-68e2a610dcc5",
-    "oai_identifier": [
-        "oai:ota:oucs:3591"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The author: A poem. By C. Churchill."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3591.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/45235093-17fd-5d5b-a714-4318084c641d.json b/oaitestdata/clarin-oai_dc/SET_1/json/45235093-17fd-5d5b-a714-4318084c641d.json
deleted file mode 100644
index cfc565a5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/45235093-17fd-5d5b-a714-4318084c641d.json
+++ /dev/null
@@ -1,93 +0,0 @@
-{
-    "Contact": [
-        "Humboldt-Universit\u00e4t zu Berlin, Institut f\u00fcr Slawistik, Prof. Dr. Roland Meyer"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "German",
-        "Latin",
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8C44-B",
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Humboldt-Universit\u00e4t zu Berlin, Institut f\u00fcr Slawistik, Prof. Dr. Roland Meyer"
-    ],
-    "RelatedIdentifier": [
-        "http://fbc.pionier.net.pl/owoc (Federacja Bibliotek Cyfrowych)"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1600/1800",
-        "Poland"
-    ],
-    "TemporalCoverage": " period : ( 1600-07-01T11:59:59Z - None ) ",
-    "author": [
-        "Humboldt-Universit\u00e4t zu Berlin, Institut f\u00fcr Slawistik, Prof. Dr. Roland Meyer"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma;2019-02-22T17:30:46Z;\"PolDiLemma\" Middle Polish Diachrone Lemmatised Corpus;Humboldt-Universit\u00e4t zu Berlin, Institut f\u00fcr Slawistik, Prof. Dr. Roland Meyer;corpus linguistics;historical linguistics;Middle Polish period;political texts;religious texts;historical texts;scientific texts;The PolDiLemma corpus is a diachronic corpus made of political, religious, scientific and historical texts from different authors of the Middle Polish period (16th-18th century). It contains in total ca. 7 million tokens.\nCharacteristic for this period is the slow development of a supra-regional standard language, a process of standardisation on the basis of the variety of the Polish nobility, under the influence of Latin and other foreign languages as well as different social or regional varieties. \nAll texts (free licenses) are gathered from Federacja Bibliotek Cyfrowych (Digital Library Federation). The Middle Polish texts illustrate the history of the language and give the opportunity to explore some first-hand evidence of the development of Polish in its historical context. \nStudying the history of the language is a way to familiarize oneself with aspects of the history of Poland in general. It also helps to build up valuable methodological knowledge in diachronic linguistics and philology.;Humboldt-Universit\u00e4t zu Berlin, Institut f\u00fcr Slawistik, Prof. Dr. Roland Meyer;2013/2014;Dataset;application/xml;clarind-uds:poldilemma;hdl:11858/00-246C-0000-0023-8C44-B;Federacja Bibliotek Cyfrowych;pol;deu;lat;ces;http://fbc.pionier.net.pl/owoc (Federacja Bibliotek Cyfrowych);1600/1800;Poland;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "45235093-17fd-5d5b-a714-4318084c641d",
-    "notes": [
-        "The PolDiLemma corpus is a diachronic corpus made of political, religious, scientific and historical texts from different authors of the Middle Polish period (16th-18th century). It contains in total ca. 7 million tokens.\nCharacteristic for this period is the slow development of a supra-regional standard language, a process of standardisation on the basis of the variety of the Polish nobility, under the influence of Latin and other foreign languages as well as different social or regional varieties. \nAll texts (free licenses) are gathered from Federacja Bibliotek Cyfrowych (Digital Library Federation). The Middle Polish texts illustrate the history of the language and give the opportunity to explore some first-hand evidence of the development of Polish in its historical context. \nStudying the history of the language is a way to familiarize oneself with aspects of the history of Poland in general. It also helps to build up valuable methodological knowledge in diachronic linguistics and philology."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus linguistics"
-        },
-        {
-            "name": "historical linguistics"
-        },
-        {
-            "name": "Middle Polish period"
-        },
-        {
-            "name": "political texts"
-        },
-        {
-            "name": "religious texts"
-        },
-        {
-            "name": "historical texts"
-        },
-        {
-            "name": "scientific texts"
-        }
-    ],
-    "title": [
-        "\"PolDiLemma\" Middle Polish Diachrone Lemmatised Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/456de542-4111-56df-8c0f-5d0aaf0e86df.json b/oaitestdata/clarin-oai_dc/SET_1/json/456de542-4111-56df-8c0f-5d0aaf0e86df.json
deleted file mode 100644
index 3d0c012a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/456de542-4111-56df-8c0f-5d0aaf0e86df.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4450",
-    "MetadataAccess": [
-        "oai:ota:oucs:4450"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Holcroft, Thomas, 1745-1809."
-    ],
-    "fulltext": "oai:ota:oucs:4450;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4450.xml;The adventures of Hugh Trevor: By Thomas Holcroft. ... [pt.2];Holcroft, Thomas, 1745-1809.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "456de542-4111-56df-8c0f-5d0aaf0e86df",
-    "oai_identifier": [
-        "oai:ota:oucs:4450"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The adventures of Hugh Trevor: By Thomas Holcroft. ... [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4450.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4573f5fb-883a-5140-8f5b-34b530a0db83.json b/oaitestdata/clarin-oai_dc/SET_1/json/4573f5fb-883a-5140-8f5b-34b530a0db83.json
deleted file mode 100644
index 7aed960c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4573f5fb-883a-5140-8f5b-34b530a0db83.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Jezuit\u00f3w"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-189302",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-189302"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CF5-E",
-    "PublicationTimestamp": "1756-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1756"
-    ],
-    "Publisher": [
-        "Drukarnia Jezuit\u00f3w"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/189302",
-        "oai:jbc.bj.uj.edu.pl:publication:200426"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1701/1800"
-    ],
-    "TempCoverageBegin": 53662478399,
-    "TempCoverageEnd": 53662478399,
-    "TemporalCoverage": " point in time : 1701-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1701-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1701-07-01T11:59:59Z",
-    "author": [
-        "Urbanowski, Paulin ( -1770)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-189302;2019-03-01T11:05:51Z;Apellacya Z Korony Polskiey Do W. X. L. Trybuna\u0142u G\u0142. Largicyi [...] Jerzego Detlofa [...] Fleminga Szerewskiego [...] Starosty, Genera\u0142a-Leutenanta Infanteryi, Podskarbiego Wielkiego [...] y Marsza\u0142ka Trybuna\u0142u W. X. L. Y Jego Godnych Kollegow [...] PP. Deputat\u00f3w Zaniesiona. : Na Expens Kanonizacyi B. Jana z Dukli Polaka Zakonu S. O. Franciszka [...] \u0141aski \u017cebrz\u0105ca. Kazaniem Koronacyi N. Panny Bole\u015bney Jaros\u0142awskiey zaszczycona, mianym przez X. P. Urbanowskiego Ruskiey Prowincyi Bernardy\u0144skiey Kanonizacyi B. Jana z Dukli Prokuratora;Urbanowski, Paulin ( -1770);starodruki 18\u00a0w.;Flemming, Jan Jerzy Detlov (1699-1771). Adr. ded.;Drukarnia Jezuit\u00f3w;1756;starodruk;application/xml;clarind-uds:poldilemma-189302;hdl:11858/00-246C-0000-0023-8CF5-E;Biblioteka Jagiello\u0144ska, BJ St. Dr. 22678 III;pol;lat;http://jbc.bj.uj.edu.pl/Content/189302;oai:jbc.bj.uj.edu.pl:publication:200426;1701/1800;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4573f5fb-883a-5140-8f5b-34b530a0db83",
-    "notes": [
-        "Flemming, Jan Jerzy Detlov (1699-1771). Adr. ded."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-189302"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Apellacya Z Korony Polskiey Do W. X. L. Trybuna\u0142u G\u0142. Largicyi [...] Jerzego Detlofa [...] Fleminga Szerewskiego [...] Starosty, Genera\u0142a-Leutenanta Infanteryi, Podskarbiego Wielkiego [...] y Marsza\u0142ka Trybuna\u0142u W. X. L. Y Jego Godnych Kollegow [...] PP. Deputat\u00f3w Zaniesiona. : Na Expens Kanonizacyi B. Jana z Dukli Polaka Zakonu S. O. Franciszka [...] \u0141aski \u017cebrz\u0105ca. Kazaniem Koronacyi N. Panny Bole\u015bney Jaros\u0142awskiey zaszczycona, mianym przez X. P. Urbanowskiego Ruskiey Prowincyi Bernardy\u0144skiey Kanonizacyi B. Jana z Dukli Prokuratora"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/458636b2-0e91-54fb-8e83-3608d0320445.json b/oaitestdata/clarin-oai_dc/SET_1/json/458636b2-0e91-54fb-8e83-3608d0320445.json
deleted file mode 100644
index 70a7ae77..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/458636b2-0e91-54fb-8e83-3608d0320445.json
+++ /dev/null
@@ -1,156 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Humanities and Social Sciences, University of Zagreb",
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Afrikaans",
-        "Arabic",
-        "Azerbaijani",
-        "Belarusian",
-        "Bulgarian",
-        "Bengali",
-        "Bosnian",
-        "Catalan",
-        "Cebuano",
-        "Czech",
-        "Welsh",
-        "Danish",
-        "German",
-        "Modern Greek (1453-)",
-        "English",
-        "Esperanto",
-        "Spanish",
-        "Estonian",
-        "Basque",
-        "Persian",
-        "Finnish",
-        "French",
-        "Western Frisian",
-        "Galician",
-        "Gujarati",
-        "Hebrew",
-        "Hindi",
-        "Croatian",
-        "Hungarian",
-        "Armenian",
-        "Indonesian",
-        "Icelandic",
-        "Italian",
-        "Japanese",
-        "Georgian",
-        "Kazakh",
-        "Central Khmer",
-        "Kannada",
-        "Korean",
-        "Kirghiz",
-        "Latin",
-        "Luxembourgish",
-        "Lithuanian",
-        "Latvian",
-        "Malagasy",
-        "Macedonian",
-        "Malayalam",
-        "Mongolian",
-        "Marathi",
-        "Malay (macrolanguage)",
-        "Burmese",
-        "Nepali (macrolanguage)",
-        "Dutch",
-        "Norwegian",
-        "Panjabi",
-        "Polish",
-        "Portuguese",
-        "Romanian",
-        "Russian",
-        "Sinhala",
-        "Slovak",
-        "Slovenian",
-        "Albanian",
-        "Serbian",
-        "Swedish",
-        "Tamil",
-        "Telugu",
-        "Tajik",
-        "Thai",
-        "Tagalog",
-        "Turkish",
-        "Ukrainian",
-        "Urdu",
-        "Uzbek",
-        "Vietnamese",
-        "Chinese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1187",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1187"
-    ],
-    "PID": "http://hdl.handle.net/11356/1187",
-    "PublicationTimestamp": "2018-05-28T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Faculty of Humanities and Social Sciences, University of Zagreb",
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "https://arxiv.org/abs/1807.02903"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "https://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Ljube\u0161i\u0107, Nikola"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1187;2018-09-18T08:34:05Z;hdl_11356_1023;hdl_11356_1024;Concreteness and imageability lexicon MEGA.HR-Crossling;Ljube\u0161i\u0107, Nikola;concreteness;imageability;multilingual;The lexicon contains concreteness and imageability predictions of words in 77 languages. The resource is built via supervised machine learning, using average human responses obtained for Croatian lexemes inside the MEGAHR project (http://megahr.ffzg.unizg.hr) as the response variable, and the Facebook cross-lingual word embeddings (https://github.com/Babylonpartners/fastText_multilingual) as explanatory variables. The Spearman correlation of human responses and automatic annotations on the Croatian-English language pair is ~0.8 for concreteness and ~0.7 for imageability.;2018-05-28;lexicalConceptualResource;http://hdl.handle.net/11356/1187;afr;ara;aze;bel;bul;ben;bos;cat;ceb;ces;cym;dan;deu;ell;eng;epo;spa;est;eus;fas;fin;fra;fry;glg;guj;heb;hin;hrv;hun;hye;ind;isl;ita;jpn;kat;kaz;khm;kan;kor;kir;lat;ltz;lit;lav;mlg;mkd;mal;mon;mar;msa;mya;nep;nld;nor;pan;pol;por;ron;rus;hbs;sin;slk;slv;sqi;srp;swe;tam;tel;tgk;tha;tgl;tur;ukr;urd;uzb;vie;zho;https://arxiv.org/abs/1807.02903;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);https://creativecommons.org/licenses/by-sa/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Jo\u017eef Stefan Institute;Faculty of Humanities and Social Sciences, University of Zagreb;https://github.com/clarinsi/megahr-crossling",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "458636b2-0e91-54fb-8e83-3608d0320445",
-    "notes": [
-        "The lexicon contains concreteness and imageability predictions of words in 77 languages. The resource is built via supervised machine learning, using average human responses obtained for Croatian lexemes inside the MEGAHR project (http://megahr.ffzg.unizg.hr) as the response variable, and the Facebook cross-lingual word embeddings (https://github.com/Babylonpartners/fastText_multilingual) as explanatory variables. The Spearman correlation of human responses and automatic annotations on the Croatian-English language pair is ~0.8 for concreteness and ~0.7 for imageability."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1187"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "concreteness"
-        },
-        {
-            "name": "imageability"
-        },
-        {
-            "name": "multilingual"
-        }
-    ],
-    "title": [
-        "Concreteness and imageability lexicon MEGA.HR-Crossling"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/45cefc90-7976-5779-b5ed-6eaae8d12c1d.json b/oaitestdata/clarin-oai_dc/SET_1/json/45cefc90-7976-5779-b5ed-6eaae8d12c1d.json
deleted file mode 100644
index 80293f2c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/45cefc90-7976-5779-b5ed-6eaae8d12c1d.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3698",
-    "MetadataAccess": [
-        "oai:ota:oucs:3698"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pope, Alexander, 1688-1744."
-    ],
-    "fulltext": "oai:ota:oucs:3698;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3698.xml;Poems occasion'd by reading the travels of Captain Lemuel Gulliver, explanatory and commendatory;Several copies of verses on occasion of Mr. Gulliver's travels;Pope, Alexander, 1688-1744.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "45cefc90-7976-5779-b5ed-6eaae8d12c1d",
-    "oai_identifier": [
-        "oai:ota:oucs:3698"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Poems occasion'd by reading the travels of Captain Lemuel Gulliver, explanatory and commendatory",
-        "Several copies of verses on occasion of Mr. Gulliver's travels"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3698.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/45f0e04f-c0b9-5340-93ec-83e92f8b3311.json b/oaitestdata/clarin-oai_dc/SET_1/json/45f0e04f-c0b9-5340-93ec-83e92f8b3311.json
deleted file mode 100644
index dff5970c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/45f0e04f-c0b9-5340-93ec-83e92f8b3311.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology",
-        "University of Lodz"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/pdf"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/544",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/544"
-    ],
-    "PID": "http://hdl.handle.net/11321/544",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology",
-        "University of Lodz"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "P\u0119zik, Piotr"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/544;2018-07-23T11:51:15Z;hdl_11321_3;hdl_11321_4;PELCRA EMO corpus;P\u0119zik, Piotr;spoken data;annotated corpus;focused interviews;structured interviews;mixed register;The corpus comprises 30 focused structured interviews (17 hours and ca. 200000 word tokens) centred on the topic of emotions. The corpus has bibliographic, morphosyntactic and sociolinguistic annotation.;2018;corpus;http://hdl.handle.net/11321/544;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;application/pdf;downloadable_files_count: 1;University of Lodz;Wroc\u0142aw University of Technology;http://spokes.clarin-pl.eu/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "45f0e04f-c0b9-5340-93ec-83e92f8b3311",
-    "notes": [
-        "The corpus comprises 30 focused structured interviews (17 hours and ca. 200000 word tokens) centred on the topic of emotions. The corpus has bibliographic, morphosyntactic and sociolinguistic annotation."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/544"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "spoken data"
-        },
-        {
-            "name": "annotated corpus"
-        },
-        {
-            "name": "focused interviews"
-        },
-        {
-            "name": "structured interviews"
-        },
-        {
-            "name": "mixed register"
-        }
-    ],
-    "title": [
-        "PELCRA EMO corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/45f222bf-3e90-5106-a146-b7b9695b037d.json b/oaitestdata/clarin-oai_dc/SET_1/json/45f222bf-3e90-5106-a146-b7b9695b037d.json
deleted file mode 100644
index 9bcb613a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/45f222bf-3e90-5106-a146-b7b9695b037d.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia J.K.M. XX Trynitarzy"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-232107",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-232107"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D0F-E",
-    "PublicationTimestamp": "1792-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1792"
-    ],
-    "Publisher": [
-        "Drukarnia J.K.M. XX Trynitarzy"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/232107",
-        "oai:jbc.bj.uj.edu.pl:publication:243786"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1701/1800"
-    ],
-    "TempCoverageBegin": 53662478399,
-    "TempCoverageEnd": 53662478399,
-    "TemporalCoverage": " point in time : 1701-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1701-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1701-07-01T11:59:59Z",
-    "author": [
-        "M\u0119ci\u0144ski, J\u00f3zef (1748-1814)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-232107;2019-03-01T13:12:50Z;Kazanie na pogrzebie Jasnie Wielmozney Heleny z Trejerow Skarszewski, podstoliny urz\u0119dowskiey [...] miane przez J\u00f3zefa M\u0119ci\u0144skiego [...] w kosciele bychawieckim dnia 7. listopada roku 1792;M\u0119ci\u0144ski, J\u00f3zef (1748-1814);starodruki 18\u00a0w.;Drukarnia J.K.M. XX Trynitarzy;1792;starodruk;application/xml;clarind-uds:poldilemma-232107;hdl:11858/00-246C-0000-0023-8D0F-E;Biblioteka Jagiello\u0144ska, BJ St. Dr. 25715 I;pol;http://jbc.bj.uj.edu.pl/Content/232107;oai:jbc.bj.uj.edu.pl:publication:243786;1701/1800;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "45f222bf-3e90-5106-a146-b7b9695b037d",
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-232107"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Kazanie na pogrzebie Jasnie Wielmozney Heleny z Trejerow Skarszewski, podstoliny urz\u0119dowskiey [...] miane przez J\u00f3zefa M\u0119ci\u0144skiego [...] w kosciele bychawieckim dnia 7. listopada roku 1792"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4603bf49-9379-50af-b450-51fd6bac5355.json b/oaitestdata/clarin-oai_dc/SET_1/json/4603bf49-9379-50af-b450-51fd6bac5355.json
deleted file mode 100644
index c8ddbf84..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4603bf49-9379-50af-b450-51fd6bac5355.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4503",
-    "MetadataAccess": [
-        "oai:ota:oucs:4503"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Williams, Helen Maria, 1762-1827."
-    ],
-    "fulltext": "oai:ota:oucs:4503;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4503.xml;Julia, a novel; interspersed with some poetical pieces. By Helen Maria Williams. In two volumes.: [pt.1];Williams, Helen Maria, 1762-1827.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4603bf49-9379-50af-b450-51fd6bac5355",
-    "oai_identifier": [
-        "oai:ota:oucs:4503"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Julia, a novel; interspersed with some poetical pieces. By Helen Maria Williams. In two volumes.: [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4503.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/46599bed-6522-556c-a014-0162df9e735e.json b/oaitestdata/clarin-oai_dc/SET_1/json/46599bed-6522-556c-a014-0162df9e735e.json
deleted file mode 100644
index 8d6c60a5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/46599bed-6522-556c-a014-0162df9e735e.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "Contributor": [
-        "Variaci\u00f3, Iula"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-509",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-509"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-509",
-    "PublicationTimestamp": "1993-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1993"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-509;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Corpus de narratives d\u2019angloparlants immigrats a Espanya en temps aparent (TA);Variaci\u00f3, Iula;Oral corpus containing 166 narratives in English elicited by means of Labovian techniques. Participants from the UK (England, Wales, Scotland), Ireland, USA, Australia and South Africa.;1993;corpus;http://hdl.handle.net/11372/LRT-509;eng;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra;http://www.iula.upf.edu/recurs08ca.htm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "46599bed-6522-556c-a014-0162df9e735e",
-    "notes": [
-        "Oral corpus containing 166 narratives in English elicited by means of Labovian techniques. Participants from the UK (England, Wales, Scotland), Ireland, USA, Australia and South Africa."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-509"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus de narratives d\u2019angloparlants immigrats a Espanya en temps aparent (TA)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/466a5645-80fb-5a2c-a54c-3a63970a01b2.json b/oaitestdata/clarin-oai_dc/SET_1/json/466a5645-80fb-5a2c-a54c-3a63970a01b2.json
deleted file mode 100644
index 4cf8c241..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/466a5645-80fb-5a2c-a54c-3a63970a01b2.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Forum"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "downloadable_files_count: 10",
-        "application/vnd.oasis.opendocument.text",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/432",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/432"
-    ],
-    "PID": "http://hdl.handle.net/11321/432",
-    "PublicationTimestamp": "2017-10-12T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Forum"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN-EULA-ACA-v1.0",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca",
-        "ACA"
-    ],
-    "author": [
-        "Przybylska, Renata"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/432;2017-10-12T15:08:59Z;hdl_11321_3;hdl_11321_4;Korpus Renata;Przybylska, Renata;warsztaty;description;2017-10-12;corpus;http://hdl.handle.net/11321/432;pol;CLARIN-EULA-ACA-v1.0;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca;ACA;text/plain; charset=utf-8;text/plain;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.oasis.opendocument.text;text/plain;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;text/plain;downloadable_files_count: 10;Forum",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "466a5645-80fb-5a2c-a54c-3a63970a01b2",
-    "notes": [
-        "description"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/432"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "warsztaty"
-        }
-    ],
-    "title": [
-        "Korpus Renata"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4674b576-d3f3-5d2e-9df2-8165aa3ae548.json b/oaitestdata/clarin-oai_dc/SET_1/json/4674b576-d3f3-5d2e-9df2-8165aa3ae548.json
deleted file mode 100644
index fb00bfce..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4674b576-d3f3-5d2e-9df2-8165aa3ae548.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "nicht angegeben",
-        "b.w."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-6073",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-6073"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D2E-8",
-    "PublicationTimestamp": "1784-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1784"
-    ],
-    "Publisher": [
-        "nicht angegeben",
-        "b.w."
-    ],
-    "RelatedIdentifier": [
-        "http://dlibra.bibliotekaelblaska.pl/Content/6073",
-        "oai:dlibra.bibliotekaelblaska.pl:publication:6296"
-    ],
-    "ResourceType": [
-        "starodruk",
-        "alter Druck"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-6073;2019-03-01T17:22:30Z;Publicandum : jakim sposobem karani bydz maj\u0105 pasterze, owczarze albo parobcy y pa\u0144stwo ich, kiedy si\u0119 odwa\u017c\u0105 pasa\u0107...;Publicandum : jakim sposobem karani bydz maj\u0105 pasterze, owczarze albo parobcy y pa\u0144stwo ich, kiedy si\u0119 odwa\u017c\u0105 pasa\u0107...;Prusy - administracja kr\u00f3lewska - 18 w.;rozporz\u0105dzenia - wypas byd\u0142a;Verordnungen - Tierweiden;Rozporz\u0105dzenie skierowane do pasterzy, owczarzy i parobk\u00f3w, m\u00f3wi\u0105ce o zakazie wypasu zwierz\u0105t w lasach kr\u00f3lewskich, pod gro\u017ab\u0105 wysokich grzywien i kar. Rozporz\u0105dzenie podpisane przez barona Schulenburga. Dwukartkowy, dwukolumnowy druk urz\u0119dowy w j\u0119zyku polskim i niemieckim wydany w formacie 2\u00b0. Pochodzi z kolekcji S. Gierszewskiego.;Die an die Hirten, Sch\u00e4fer und andere Dienstleute gerichtete Verordnung betreffend das Verbot des Tierweidens in den k\u00f6niglichen W\u00e4ldern. Die Verletzung des Verbots war mit hohen Strafen belegt. Die Verordnung wurde vom Freiherr von Schulenburg unterschrieben. Zweispaltige Amtsurkunde, in polnischer und deutscher Sprache. Format 2\u00b0. Stammt aus der Sammlung von S. Gierszewski.;b.w.;nicht angegeben;1784;1784;starodruk;alter Druck;application/xml;clarind-uds:poldilemma-6073;hdl:11858/00-246C-0000-0023-8D2E-8;XVIII. 266;XVIII. 266;pol;ger;http://dlibra.bibliotekaelblaska.pl/Content/6073;oai:dlibra.bibliotekaelblaska.pl:publication:6296;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4674b576-d3f3-5d2e-9df2-8165aa3ae548",
-    "notes": [
-        "Rozporz\u0105dzenie skierowane do pasterzy, owczarzy i parobk\u00f3w, m\u00f3wi\u0105ce o zakazie wypasu zwierz\u0105t w lasach kr\u00f3lewskich, pod gro\u017ab\u0105 wysokich grzywien i kar. Rozporz\u0105dzenie podpisane przez barona Schulenburga. Dwukartkowy, dwukolumnowy druk urz\u0119dowy w j\u0119zyku polskim i niemieckim wydany w formacie 2\u00b0. Pochodzi z kolekcji S. Gierszewskiego.",
-        "Die an die Hirten, Sch\u00e4fer und andere Dienstleute gerichtete Verordnung betreffend das Verbot des Tierweidens in den k\u00f6niglichen W\u00e4ldern. Die Verletzung des Verbots war mit hohen Strafen belegt. Die Verordnung wurde vom Freiherr von Schulenburg unterschrieben. Zweispaltige Amtsurkunde, in polnischer und deutscher Sprache. Format 2\u00b0. Stammt aus der Sammlung von S. Gierszewski."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-6073"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Verordnungen - Tierweiden"
-        }
-    ],
-    "title": [
-        "Publicandum : jakim sposobem karani bydz maj\u0105 pasterze, owczarze albo parobcy y pa\u0144stwo ich, kiedy si\u0119 odwa\u017c\u0105 pasa\u0107...",
-        "Publicandum : jakim sposobem karani bydz maj\u0105 pasterze, owczarze albo parobcy y pa\u0144stwo ich, kiedy si\u0119 odwa\u017c\u0105 pasa\u0107..."
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4684be50-9a12-58a1-bff9-45ed7e8432b4.json b/oaitestdata/clarin-oai_dc/SET_1/json/4684be50-9a12-58a1-bff9-45ed7e8432b4.json
deleted file mode 100644
index 6b55287f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4684be50-9a12-58a1-bff9-45ed7e8432b4.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/x-bzip2",
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 3",
-        "application/zip"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-000D-F67C-5",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-000D-F67C-5"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-000D-F67C-5",
-    "PublicationTimestamp": "2013-02-02T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-1469"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "BSD 2-Clause \"Simplified\" or \"FreeBSD\" license",
-        "http://opensource.org/licenses/BSD-2-Clause",
-        "PUB"
-    ],
-    "author": [
-        "Richter, Michal"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-000D-F67C-5;2018-07-02T22:05:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Korektor;Richter, Michal;grammar checker;spellchecker;Statistical spell- and (occasional) grammar-checker. There are three versions: a unix command line utility and an OS X SpellServer with a System Service, that integrates with native OS X GUI applications, and a web service run by Lindat-Clarin, that can be used either through a web form in a browser, or by web applications using API.;2013-02-02;toolService;http://hdl.handle.net/11858/00-097C-0000-000D-F67C-5;ces;http://hdl.handle.net/11234/1-1469;BSD 2-Clause \"Simplified\" or \"FreeBSD\" license;http://opensource.org/licenses/BSD-2-Clause;PUB;text/plain; charset=utf-8;application/zip;application/zip;application/x-bzip2;downloadable_files_count: 3;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://redmine.ms.mff.cuni.cz/projects/korektor",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4684be50-9a12-58a1-bff9-45ed7e8432b4",
-    "notes": [
-        "Statistical spell- and (occasional) grammar-checker. There are three versions: a unix command line utility and an OS X SpellServer with a System Service, that integrates with native OS X GUI applications, and a web service run by Lindat-Clarin, that can be used either through a web form in a browser, or by web applications using API."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-000D-F67C-5"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "grammar checker"
-        },
-        {
-            "name": "spellchecker"
-        }
-    ],
-    "title": [
-        "Korektor"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/46969df8-5e0e-5dcb-a283-ed733544ed89.json b/oaitestdata/clarin-oai_dc/SET_1/json/46969df8-5e0e-5dcb-a283-ed733544ed89.json
deleted file mode 100644
index f605cff7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/46969df8-5e0e-5dcb-a283-ed733544ed89.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5358",
-    "MetadataAccess": [
-        "oai:ota:oucs:5358"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Ritson, Joseph, 1752-1803."
-    ],
-    "fulltext": "oai:ota:oucs:5358;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5358.xml;Observations on the three first volumes of the History of English Poetry. In a familiar letter to the author;Ritson, Joseph, 1752-1803.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "46969df8-5e0e-5dcb-a283-ed733544ed89",
-    "oai_identifier": [
-        "oai:ota:oucs:5358"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Observations on the three first volumes of the History of English Poetry. In a familiar letter to the author"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5358.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/46b54d20-bcb0-5a3c-b4b9-674d8eae0b4c.json b/oaitestdata/clarin-oai_dc/SET_1/json/46b54d20-bcb0-5a3c-b4b9-674d8eae0b4c.json
deleted file mode 100644
index 6806640b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/46b54d20-bcb0-5a3c-b4b9-674d8eae0b4c.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "IBL",
-        "IBL PAN"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/vnd.oasis.opendocument.text",
-        "downloadable_files_count: 10",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/383",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/383"
-    ],
-    "PID": "http://hdl.handle.net/11321/383",
-    "PublicationTimestamp": "2017-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "IBL",
-        "IBL PAN"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Troszynski, Marek"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/383;2017-05-30T11:54:43Z;hdl_11321_3;hdl_11321_4;Korpus przyk\u0142adowy;Troszynski, Marek;clarin \u0107wiczenia test teksty;rozmaite teksty ciekawe literackie;2017-05-30;corpus;http://hdl.handle.net/11321/383;polski;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;text/plain;application/msword;text/plain;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;application/vnd.oasis.opendocument.text;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;downloadable_files_count: 10;IBL;IBL PAN",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "46b54d20-bcb0-5a3c-b4b9-674d8eae0b4c",
-    "notes": [
-        "rozmaite teksty ciekawe literackie"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/383"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Korpus przyk\u0142adowy"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/46b55680-4377-5e5b-b545-1e021525b12a.json b/oaitestdata/clarin-oai_dc/SET_1/json/46b55680-4377-5e5b-b545-1e021525b12a.json
deleted file mode 100644
index 2219f7e8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/46b55680-4377-5e5b-b545-1e021525b12a.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1027",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1027"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1027",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1027;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LAC Kri Corpus;Language and Cognition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1027;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI29388%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "46b55680-4377-5e5b-b545-1e021525b12a",
-    "notes": [
-        "Language and Cognition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1027"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LAC Kri Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/46d3203f-58d4-5522-b34e-1dd6c9ed1057.json b/oaitestdata/clarin-oai_dc/SET_1/json/46d3203f-58d4-5522-b34e-1dd6c9ed1057.json
deleted file mode 100644
index 56e39291..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/46d3203f-58d4-5522-b34e-1dd6c9ed1057.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4330",
-    "MetadataAccess": [
-        "oai:ota:oucs:4330"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Defoe, Daniel, 1661?-1731."
-    ],
-    "fulltext": "oai:ota:oucs:4330;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4330.xml;An essay upon buying and selling of speeches. In a letter to a worshipfull Justice of the Peace, being also a member of a certain worshipfull society of speech-makers;Defoe, Daniel, 1661?-1731.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "46d3203f-58d4-5522-b34e-1dd6c9ed1057",
-    "oai_identifier": [
-        "oai:ota:oucs:4330"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An essay upon buying and selling of speeches. In a letter to a worshipfull Justice of the Peace, being also a member of a certain worshipfull society of speech-makers"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4330.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/46fd0ff9-cd15-566f-9a74-865d29ebafbf.json b/oaitestdata/clarin-oai_dc/SET_1/json/46fd0ff9-cd15-566f-9a74-865d29ebafbf.json
deleted file mode 100644
index 253d1c40..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/46fd0ff9-cd15-566f-9a74-865d29ebafbf.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Uniwersytet Miko\u0142aja Kopernika w Toruniu"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/vnd.oasis.opendocument.text",
-        "application/zip",
-        "downloadable_files_count: 14",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/404",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/404"
-    ],
-    "PID": "http://hdl.handle.net/11321/404",
-    "PublicationTimestamp": "2017-06-29T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Uniwersytet Miko\u0142aja Kopernika w Toruniu"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Pawlaczyk, Angelika"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/404;2017-07-06T10:33:31Z;hdl_11321_3;hdl_11321_4;Korpus testowy;Pawlaczyk, Angelika;korpus;transkrypcja;staroobrz\u0119dowcy;Korpus testowy LSHC, Krak\u00f3w 2017;2017-06-29;corpus;http://hdl.handle.net/11321/404;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;application/vnd.oasis.opendocument.text;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;text/plain;text/plain;text/plain;application/zip;application/zip;application/zip;application/zip;downloadable_files_count: 14;Uniwersytet Miko\u0142aja Kopernika w Toruniu",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "46fd0ff9-cd15-566f-9a74-865d29ebafbf",
-    "notes": [
-        "Korpus testowy LSHC, Krak\u00f3w 2017"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/404"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "korpus"
-        },
-        {
-            "name": "transkrypcja"
-        },
-        {
-            "name": "transkrypcja"
-        }
-    ],
-    "title": [
-        "Korpus testowy"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/47157f6c-512b-54b2-83dc-6dadd5b507bb.json b/oaitestdata/clarin-oai_dc/SET_1/json/47157f6c-512b-54b2-83dc-6dadd5b507bb.json
deleted file mode 100644
index 8df92db9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/47157f6c-512b-54b2-83dc-6dadd5b507bb.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 1 MB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2159",
-    "MetadataAccess": [
-        "oai:ota:oucs:2159"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gaskell, Elizabeth Cleghorn, 1810-1865"
-    ],
-    "fulltext": "oai:ota:oucs:2159;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/2159.xml;North and south / by Elizabeth Gaskell;Gaskell, Elizabeth Cleghorn, 1810-1865;text_and_corpus_linguistics;Fiction -- Great Britain -- 19th century;Novels -- Great Britain -- 19th century;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 1 MB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "47157f6c-512b-54b2-83dc-6dadd5b507bb",
-    "oai_identifier": [
-        "oai:ota:oucs:2159"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- Great Britain -- th century"
-        },
-        {
-            "name": "Novels -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "North and south / by Elizabeth Gaskell"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2159.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/471e9d2d-79f0-5880-84e2-ed59b4ca11a9.json b/oaitestdata/clarin-oai_dc/SET_1/json/471e9d2d-79f0-5880-84e2-ed59b4ca11a9.json
deleted file mode 100644
index d48ab83c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/471e9d2d-79f0-5880-84e2-ed59b4ca11a9.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contributor": [
-        "Piperidis, Stelios"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English",
-        "French",
-        "Modern Greek (1453-)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-326",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-326"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-326",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Greece"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-326;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;MUSA Multilingual Multimodal Corpus;Piperidis, Stelios;Multilingual (EN, EL, FR); multimodal (Video, Text); parallel (EN, EL, FR subtitles); comparable (transcripts, subtitles); 120 hours;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-326;eng;fra;ell;downloadable_files_count: 0;Greece;http://sifnos.ilsp.gr/musa",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "471e9d2d-79f0-5880-84e2-ed59b4ca11a9",
-    "notes": [
-        "Multilingual (EN, EL, FR); multimodal (Video, Text); parallel (EN, EL, FR subtitles); comparable (transcripts, subtitles); 120 hours"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-326"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "MUSA Multilingual Multimodal Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4724dc23-87df-5f18-9cfd-2eac9732bbf4.json b/oaitestdata/clarin-oai_dc/SET_1/json/4724dc23-87df-5f18-9cfd-2eac9732bbf4.json
deleted file mode 100644
index f29af8bd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4724dc23-87df-5f18-9cfd-2eac9732bbf4.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Waite, Stephen V.F."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 133 KB)"
-    ],
-    "Language": [
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1670",
-    "MetadataAccess": [
-        "oai:ota:oucs:1670"
-    ],
-    "PublicationYear": [
-        "[198?]"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Ovid, 43 B.C.-17 or 18 A.D."
-    ],
-    "fulltext": "oai:ota:oucs:1670;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/1670.xml;Ars amatoria / Ovid;The art of love;Ovid, 43 B.C.-17 or 18 A.D.;[198?];text_and_corpus_linguistics;Love poetry, Classical -- 1st century;lat;Oxford Text Archive, University of Oxford;Waite, Stephen V.F.;text/sgml;(1 file : ca. 133 KB);Text;Poems;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4724dc23-87df-5f18-9cfd-2eac9732bbf4",
-    "oai_identifier": [
-        "oai:ota:oucs:1670"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Love poetry"
-        },
-        {
-            "name": "Classical -- st century"
-        }
-    ],
-    "title": [
-        "Ars amatoria / Ovid",
-        "The art of love"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1670.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/475167a7-2f23-5377-b7b7-a68ec6e0c058.json b/oaitestdata/clarin-oai_dc/SET_1/json/475167a7-2f23-5377-b7b7-a68ec6e0c058.json
deleted file mode 100644
index 7929cebb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/475167a7-2f23-5377-b7b7-a68ec6e0c058.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4641",
-    "MetadataAccess": [
-        "oai:ota:oucs:4641"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gibbon, Edward, 1737-1794."
-    ],
-    "fulltext": "oai:ota:oucs:4641;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4641.xml;The history of the decline and fall of the Roman Empire: By Edward Gibbon, Esq; ... [pt.3];Gibbon, Edward, 1737-1794.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "475167a7-2f23-5377-b7b7-a68ec6e0c058",
-    "oai_identifier": [
-        "oai:ota:oucs:4641"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The history of the decline and fall of the Roman Empire: By Edward Gibbon, Esq; ... [pt.3]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4641.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/47883105-6d8d-56ff-89cf-b8826d1829ef.json b/oaitestdata/clarin-oai_dc/SET_1/json/47883105-6d8d-56ff-89cf-b8826d1829ef.json
deleted file mode 100644
index cd605cec..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/47883105-6d8d-56ff-89cf-b8826d1829ef.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Instytut Filologii Polskiej"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/vnd.oasis.opendocument.text",
-        "downloadable_files_count: 10",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/431",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/431"
-    ],
-    "PID": "http://hdl.handle.net/11321/431",
-    "PublicationTimestamp": "2017-10-11T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Instytut Filologii Polskiej"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Piotrowicz, Anna"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/431;2017-10-12T10:13:48Z;hdl_11321_3;hdl_11321_4;Ania-warsztaty;Piotrowicz, Anna;proper name;name;semantic;text;2017-10-11;corpus;http://hdl.handle.net/11321/431;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;application/vnd.oasis.opendocument.text;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;text/plain;text/plain;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;downloadable_files_count: 10;Instytut Filologii Polskiej",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "47883105-6d8d-56ff-89cf-b8826d1829ef",
-    "notes": [
-        "text"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/431"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "proper name"
-        },
-        {
-            "name": "name"
-        },
-        {
-            "name": "semantic"
-        }
-    ],
-    "title": [
-        "Ania-warsztaty"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/47915e1d-f78e-5920-9627-c4a4d634b25a.json b/oaitestdata/clarin-oai_dc/SET_1/json/47915e1d-f78e-5920-9627-c4a4d634b25a.json
deleted file mode 100644
index 4e586eec..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/47915e1d-f78e-5920-9627-c4a4d634b25a.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Pijar\u00f3w"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-228964",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-228964"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D00-C",
-    "PublicationTimestamp": "1783-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1783"
-    ],
-    "Publisher": [
-        "Drukarnia Pijar\u00f3w"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/228964",
-        "oai:jbc.bj.uj.edu.pl:publication:240607"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1701/1800"
-    ],
-    "TempCoverageBegin": 53662478399,
-    "TempCoverageEnd": 53662478399,
-    "TemporalCoverage": " point in time : 1701-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1701-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1701-07-01T11:59:59Z",
-    "author": [
-        "Skrzetuski, Kajetan J\u00f3zef (1743-1806)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-228964;2019-03-01T11:24:05Z;Kazanie Na Niedziel\u0119 Pierwsz\u0105 Po Trzech Krolach : O powolno\u015bci, potrzebney w m\u0142odym wieku do nabycia rozumu y cnoty Miane w kaplicy Collegium Nobilium Scholarum Piarum;Skrzetuski, Kajetan J\u00f3zef (1743-1806);starodruki 18\u00a0w.;Poniatowski, Micha\u0142 Jerzy (1736-1794). Adr. ded.;Drukarnia Pijar\u00f3w;1783;starodruk;application/xml;clarind-uds:poldilemma-228964;hdl:11858/00-246C-0000-0023-8D00-C;Biblioteka Jagiello\u0144ska, BJ St. Dr. 37656 I;pol;http://jbc.bj.uj.edu.pl/Content/228964;oai:jbc.bj.uj.edu.pl:publication:240607;1701/1800;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "47915e1d-f78e-5920-9627-c4a4d634b25a",
-    "notes": [
-        "Poniatowski, Micha\u0142 Jerzy (1736-1794). Adr. ded."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-228964"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Kazanie Na Niedziel\u0119 Pierwsz\u0105 Po Trzech Krolach : O powolno\u015bci, potrzebney w m\u0142odym wieku do nabycia rozumu y cnoty Miane w kaplicy Collegium Nobilium Scholarum Piarum"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/47a18b06-0e2a-5d5e-88d4-6f8aaaefe9e9.json b/oaitestdata/clarin-oai_dc/SET_1/json/47a18b06-0e2a-5d5e-88d4-6f8aaaefe9e9.json
deleted file mode 100644
index 8c54bab4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/47a18b06-0e2a-5d5e-88d4-6f8aaaefe9e9.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Institut d'Estudis Catalans"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Catalan"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1117",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1117"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1117",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut d'Estudis Catalans"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1117;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Corpus Textual lnformatitzat de la Llengua Catalana (CTILC);corpus;Corpus containing Catalan texts written in the time span from 1832 to 1988 and totalling over 52 million words.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1117;cat;downloadable_files_count: 0;Spain;Institut d'Estudis Catalans;http://ctilc.iec.cat/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "47a18b06-0e2a-5d5e-88d4-6f8aaaefe9e9",
-    "notes": [
-        "Corpus containing Catalan texts written in the time span from 1832 to 1988 and totalling over 52 million words."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1117"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        }
-    ],
-    "title": [
-        "Corpus Textual lnformatitzat de la Llengua Catalana (CTILC)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/47a9b194-1687-55c2-8957-493a3d9c8f7b.json b/oaitestdata/clarin-oai_dc/SET_1/json/47a9b194-1687-55c2-8957-493a3d9c8f7b.json
deleted file mode 100644
index d1ec55a8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/47a9b194-1687-55c2-8957-493a3d9c8f7b.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Academy of Sciences"
-    ],
-    "Contributor": [
-        "Szab\u00f3, P\u00e9ter Tam\u00e1s"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/xml"
-    ],
-    "Language": [
-        "Hungarian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1017",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1017"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1017",
-    "PublicationTimestamp": "2005-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2005"
-    ],
-    "Publisher": [
-        "Academy of Sciences"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Hungary"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1017;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Hungarian Historical Corpus;Szab\u00f3, P\u00e9ter Tam\u00e1s;Containing 27 million running words the Hungarian Historical Corpus provides a valuable basis for research on the history of words of Hungarian between the second half of the 18th century and 2000.;2005;corpus;http://hdl.handle.net/11372/LRT-1017;hun;application/xml;downloadable_files_count: 0;Hungary;Academy of Sciences;http://www.nytud.hu/hhc/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "47a9b194-1687-55c2-8957-493a3d9c8f7b",
-    "notes": [
-        "Containing 27 million running words the Hungarian Historical Corpus provides a valuable basis for research on the history of words of Hungarian between the second half of the 18th century and 2000."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1017"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Hungarian Historical Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/47b033ca-8f81-5d58-8286-82880e69e51a.json b/oaitestdata/clarin-oai_dc/SET_1/json/47b033ca-8f81-5d58-8286-82880e69e51a.json
deleted file mode 100644
index 7fe1602c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/47b033ca-8f81-5d58-8286-82880e69e51a.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Marek Lukasik"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 4",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/155",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/155"
-    ],
-    "PID": "http://hdl.handle.net/11321/155",
-    "PublicationTimestamp": "2015-04-14T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Marek Lukasik"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "\u0141ukasik, Marek"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/155;2015-04-16T17:23:32Z;hdl_11321_3;hdl_11321_4;Astronomy;\u0141ukasik, Marek;Astronomy.;2015-04-14;corpus;http://hdl.handle.net/11321/155;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 4;Marek Lukasik",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "47b033ca-8f81-5d58-8286-82880e69e51a",
-    "notes": [
-        "Astronomy."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/155"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Astronomy"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/47b4c9dc-b18f-5358-83f8-a87ab5c2b124.json b/oaitestdata/clarin-oai_dc/SET_1/json/47b4c9dc-b18f-5358-83f8-a87ab5c2b124.json
deleted file mode 100644
index 33696186..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/47b4c9dc-b18f-5358-83f8-a87ab5c2b124.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Czech",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1731",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1731"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1731",
-    "PublicationTimestamp": "2016-06-12T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Rosa, Rudolf"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1731;2018-07-02T22:05:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Czech and English abstracts of \u00daFAL papers;Rosa, Rudolf;parallel corpus;scientific texts;abstracts;This is a document-aligned parallel corpus of English and Czech abstracts of scientific papers published by authors from the Institute of Formal and Applied Linguistics, Charles University in Prague, as reported in the institute's system Biblio. For each publication, the authors are obliged to provide both the original abstract in Czech or English, and its translation into English or Czech, respectively. No filtering was performed, except for removing entries missing the Czech or English abstract, and replacing newline and tabulator characters by spaces.;2016-06-12;corpus;http://hdl.handle.net/11234/1-1731;ces;eng;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/biblio/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "47b4c9dc-b18f-5358-83f8-a87ab5c2b124",
-    "notes": [
-        "This is a document-aligned parallel corpus of English and Czech abstracts of scientific papers published by authors from the Institute of Formal and Applied Linguistics, Charles University in Prague, as reported in the institute's system Biblio. For each publication, the authors are obliged to provide both the original abstract in Czech or English, and its translation into English or Czech, respectively. No filtering was performed, except for removing entries missing the Czech or English abstract, and replacing newline and tabulator characters by spaces."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1731"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parallel corpus"
-        },
-        {
-            "name": "scientific texts"
-        },
-        {
-            "name": "abstracts"
-        }
-    ],
-    "title": [
-        "Czech and English abstracts of \u00daFAL papers"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/47c9aa26-04a7-5420-aae0-27d898a95bc6.json b/oaitestdata/clarin-oai_dc/SET_1/json/47c9aa26-04a7-5420-aae0-27d898a95bc6.json
deleted file mode 100644
index 14acdd98..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/47c9aa26-04a7-5420-aae0-27d898a95bc6.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "Contributor": [
-        "Przepi\u00f3rkowski, Adam"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-308",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-308"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-308",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-308;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Spejd;Przepi\u00f3rkowski, Adam;Tool for partial parsing and rule-based morphosyntactic disambiguation;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-308;downloadable_files_count: 0;Institute of Computer Science, Polish Academy of Sciences;http://nlp.ipipan.waw.pl/Spejd/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "47c9aa26-04a7-5420-aae0-27d898a95bc6",
-    "notes": [
-        "Tool for partial parsing and rule-based morphosyntactic disambiguation"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-308"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Spejd"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/47e20067-680a-5c77-b224-8ce944b587b4.json b/oaitestdata/clarin-oai_dc/SET_1/json/47e20067-680a-5c77-b224-8ce944b587b4.json
deleted file mode 100644
index 1c7317c0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/47e20067-680a-5c77-b224-8ce944b587b4.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4721",
-    "MetadataAccess": [
-        "oai:ota:oucs:4721"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Francis, Philip, Sir, 1740-1818."
-    ],
-    "fulltext": "oai:ota:oucs:4721;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4721.xml;Two speeches in the House of Commons on the original East-India Bill and on the amended Bill, on the 16th and 26th of July, 1784, by Philip Francis, Esq;Francis, Philip, Sir, 1740-1818.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "47e20067-680a-5c77-b224-8ce944b587b4",
-    "oai_identifier": [
-        "oai:ota:oucs:4721"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Two speeches in the House of Commons on the original East-India Bill and on the amended Bill, on the 16th and 26th of July, 1784, by Philip Francis, Esq"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4721.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/484313fe-41bd-5e43-bf7b-34a464429d50.json b/oaitestdata/clarin-oai_dc/SET_1/json/484313fe-41bd-5e43-bf7b-34a464429d50.json
deleted file mode 100644
index 69339085..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/484313fe-41bd-5e43-bf7b-34a464429d50.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5119",
-    "MetadataAccess": [
-        "oai:ota:oucs:5119"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Griffith, Mrs. (Elizabeth), 1720?-1793."
-    ],
-    "fulltext": "oai:ota:oucs:5119;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5119.xml;The morality of Shakespeare's drama illustrated: By Mrs. Griffith.;Griffith, Mrs. (Elizabeth), 1720?-1793.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "484313fe-41bd-5e43-bf7b-34a464429d50",
-    "oai_identifier": [
-        "oai:ota:oucs:5119"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The morality of Shakespeare's drama illustrated: By Mrs. Griffith."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5119.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4865936b-01b2-5e31-997c-eda85f7aa1f3.json b/oaitestdata/clarin-oai_dc/SET_1/json/4865936b-01b2-5e31-997c-eda85f7aa1f3.json
deleted file mode 100644
index e2d14cf1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4865936b-01b2-5e31-997c-eda85f7aa1f3.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/33",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/33"
-    ],
-    "PID": "http://hdl.handle.net/11321/33",
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Piasecki, Maciej",
-        "Wndelberger, Micha\u0142",
-        "Zawadzki, Maciej",
-        "Broda, Bartosz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/33;2016-01-19T13:34:22Z;hdl_11321_3;hdl_11321_4;Vector Extractor;Piasecki, Maciej;Broda, Bartosz;Wndelberger, Micha\u0142;Zawadzki, Maciej;Collocations presented are based on co-occurrences of a selected noun with several features describing it and linked with it by syntactic dependencies. The recognised features are: modification by an adjective (AdjMod), modification by a noun in genitive (NGenMod), coordination with a noun (NCoord) and linking to a verb as its subject (VSubj).;2014;toolService;http://hdl.handle.net/11321/33;pol;downloadable_files_count: 0;Wroc\u0142aw University of Technology;http://www.clarin-pl.eu/vector-extractor/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4865936b-01b2-5e31-997c-eda85f7aa1f3",
-    "notes": [
-        "Collocations presented are based on co-occurrences of a selected noun with several features describing it and linked with it by syntactic dependencies. The recognised features are: modification by an adjective (AdjMod), modification by a noun in genitive (NGenMod), coordination with a noun (NCoord) and linking to a verb as its subject (VSubj)."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/33"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Vector Extractor"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/487c3a77-6959-5d8b-84b1-d7392241c250.json b/oaitestdata/clarin-oai_dc/SET_1/json/487c3a77-6959-5d8b-84b1-d7392241c250.json
deleted file mode 100644
index 1a9f24dc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/487c3a77-6959-5d8b-84b1-d7392241c250.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "Persian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-917",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-917"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-917",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-917;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS New Persian;ca. 300.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-917;fas;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#npers",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "487c3a77-6959-5d8b-84b1-d7392241c250",
-    "notes": [
-        "ca. 300.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-917"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS New Persian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/48b3d0f6-39b8-587d-88e3-7c08df2f8ac3.json b/oaitestdata/clarin-oai_dc/SET_1/json/48b3d0f6-39b8-587d-88e3-7c08df2f8ac3.json
deleted file mode 100644
index 420b9cb1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/48b3d0f6-39b8-587d-88e3-7c08df2f8ac3.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "text/plain",
-        "downloadable_files_count: 2"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/39",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/39"
-    ],
-    "PID": "http://hdl.handle.net/11321/39",
-    "PublicationTimestamp": "2013-09-24T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "author": [
-        "Piasecki, Dominik",
-        "Piasecki, Maciej",
-        "Marci\u0144czuk, Micha\u0142",
-        "Radziszewski, Adam"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/39;2016-10-21T14:04:30Z;hdl_11321_3;hdl_11321_4;Pytania i odpowiedzi z serwisu wikipedyjnego \"Czy wiesz\", wersja 1.1;Marci\u0144czuk, Micha\u0142;Piasecki, Dominik;Piasecki, Maciej;Radziszewski, Adam;Czy wiesz\u201d (pol. \u201cDid you know\u201d) is a set of 4721 questions, each linked to a Wikipedia article that contains the answer.\r\nFor 250 questions a detailed manual analysis has been performed. What results is attachment of manually-checked answer-bearing fragments to each of those selected questions. Some questions are assigned multiple fragments.\r\nThe data set has been obtained from the Polish \u201cDid you know\u201d wikiproject. The dataset is made to facilitate evaluation and development of Polish QA systems.;2013-09-24;corpus;http://hdl.handle.net/11321/39;pol;application/zip;text/plain;downloadable_files_count: 2;Wroc\u0142aw University of Technology;http://nlp.pwr.wroc.pl/narzedzia-i-zasoby/zasoby/zbior-pytan-i-odpowiedzi-czy-wiesz",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "48b3d0f6-39b8-587d-88e3-7c08df2f8ac3",
-    "notes": [
-        "Czy wiesz\u201d (pol. \u201cDid you know\u201d) is a set of 4721 questions, each linked to a Wikipedia article that contains the answer.\r\nFor 250 questions a detailed manual analysis has been performed. What results is attachment of manually-checked answer-bearing fragments to each of those selected questions. Some questions are assigned multiple fragments.\r\nThe data set has been obtained from the Polish \u201cDid you know\u201d wikiproject. The dataset is made to facilitate evaluation and development of Polish QA systems."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/39"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Pytania i odpowiedzi z serwisu wikipedyjnego \"Czy wiesz\", wersja 1.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/48ceaf0e-2890-59f6-ae0f-87bdad97d664.json b/oaitestdata/clarin-oai_dc/SET_1/json/48ceaf0e-2890-59f6-ae0f-87bdad97d664.json
deleted file mode 100644
index 67a938ac..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/48ceaf0e-2890-59f6-ae0f-87bdad97d664.json
+++ /dev/null
@@ -1,91 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "German",
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0008-D259-7",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0008-D259-7"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0008-D259-7",
-    "PublicationTimestamp": "2012-11-13T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/231720"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Koubov\u00e1, Anna",
-        "Petrdl\u00edkov\u00e1, Jana",
-        "Nov\u00e1kov\u00e1, Petra",
-        "Du\u0161ek, Ond\u0159ej",
-        "Zeman, Daniel",
-        "B\u0159e\u010dkov\u00e1, Jana",
-        "Farka\u010dov\u00e1, Hana",
-        "Lukavsk\u00e1, Jana",
-        "Ka\u010denov\u00e1, Krist\u00fdna",
-        "Bojar, Ond\u0159ej",
-        "Gro\u0161pic, Pavel",
-        "Knechtov\u00e1, Eva"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0008-D259-7;2018-07-02T22:05:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Additional German-Czech reference translations of the WMT'11 test set;Bojar, Ond\u0159ej;Zeman, Daniel;Du\u0161ek, Ond\u0159ej;B\u0159e\u010dkov\u00e1, Jana;Farka\u010dov\u00e1, Hana;Gro\u0161pic, Pavel;Ka\u010denov\u00e1, Krist\u00fdna;Knechtov\u00e1, Eva;Koubov\u00e1, Anna;Lukavsk\u00e1, Jana;Nov\u00e1kov\u00e1, Petra;Petrdl\u00edkov\u00e1, Jana;reference translation;German-Czech;parallel corpus;Additional three Czech reference translations of the whole WMT 2011 data set (http://www.statmt.org/wmt11/test.tgz), translated from the German originals. Original segmentation of the WMT 2011 data is preserved.;2012-11-13;corpus;http://hdl.handle.net/11858/00-097C-0000-0008-D259-7;deu;ces;info:eu-repo/grantAgreement/EC/FP7/231720;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "48ceaf0e-2890-59f6-ae0f-87bdad97d664",
-    "notes": [
-        "Additional three Czech reference translations of the whole WMT 2011 data set (http://www.statmt.org/wmt11/test.tgz), translated from the German originals. Original segmentation of the WMT 2011 data is preserved."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0008-D259-7"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "reference translation"
-        },
-        {
-            "name": "German-Czech"
-        },
-        {
-            "name": "parallel corpus"
-        }
-    ],
-    "title": [
-        "Additional German-Czech reference translations of the WMT'11 test set"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/48db4cf2-1413-5ad1-984f-fcf403c26a02.json b/oaitestdata/clarin-oai_dc/SET_1/json/48db4cf2-1413-5ad1-984f-fcf403c26a02.json
deleted file mode 100644
index b797d969..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/48db4cf2-1413-5ad1-984f-fcf403c26a02.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Italian",
-        "Ancient Greek (to 1453)",
-        "Arabic",
-        "Latin",
-        "Croatian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-55",
-    "MetadataAccess": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-55"
-    ],
-    "PID": "http://hdl.handle.net/20.500.11752/ILC-55",
-    "PublicationTimestamp": "2014-05-26T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Del Gratta, Riccardo",
-        "Boschetti, Federico"
-    ],
-    "fulltext": "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-55;2018-07-23T09:13:44Z;hdl_000-c0-111_38;hdl_000-c0-111_49;CophiWordNet Search Interface 1.0;Boschetti, Federico;Del Gratta, Riccardo;Wordnets;Search Interface;Gui;This interface allows you to browse several wordnets in different languages.\r\nItalian, Ancient Greek, Latin, Croatian, Arabic\r\nEach wordnet is mapped on PWN 3.0 and the interface may be extended with other wordnets (please ask contact person).;2014-05-26;toolService;http://hdl.handle.net/20.500.11752/ILC-55;ita;grc;ara;lat;hrv;downloadable_files_count: 0;Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR);http://www.cophilab.eu",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "48db4cf2-1413-5ad1-984f-fcf403c26a02",
-    "notes": [
-        "This interface allows you to browse several wordnets in different languages.\r\nItalian, Ancient Greek, Latin, Croatian, Arabic\r\nEach wordnet is mapped on PWN 3.0 and the interface may be extended with other wordnets (please ask contact person)."
-    ],
-    "oai_identifier": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-55"
-    ],
-    "oai_set": [
-        "hdl_000-c0-111_38",
-        "hdl_000-c0-111_49"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Wordnets"
-        },
-        {
-            "name": "Search Interface"
-        },
-        {
-            "name": "Gui"
-        }
-    ],
-    "title": [
-        "CophiWordNet Search Interface 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/48dc183b-ad83-54e1-8852-200841c3a2a7.json b/oaitestdata/clarin-oai_dc/SET_1/json/48dc183b-ad83-54e1-8852-200841c3a2a7.json
deleted file mode 100644
index 9f221c03..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/48dc183b-ad83-54e1-8852-200841c3a2a7.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Westf\u00e4lische Wilhelms-Universit\u00e4t M\u00fcnster"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "French",
-        "German",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1014",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1014"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1014",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Westf\u00e4lische Wilhelms-Universit\u00e4t M\u00fcnster"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1014;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Digitale Sammlungen der Universit\u00e4ts- und Landesbibliothek M\u00fcnster;Germanistik;Digital copies of historical books and journals from the ULB M\u00fcnster; collections from the region of Westphalia; Bilddigitalisate von B\u00fcchern und Zeitschriften aus dem historischen Bestand der ULB M\u00fcnster sowie Sammlungen aus der Region Westfalen;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1014;fra;deu;lat;downloadable_files_count: 0;Germany;Westf\u00e4lische Wilhelms-Universit\u00e4t M\u00fcnster;http://sammlungen.uni-muenster.de/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "48dc183b-ad83-54e1-8852-200841c3a2a7",
-    "notes": [
-        "Digital copies of historical books and journals from the ULB M\u00fcnster; collections from the region of Westphalia; Bilddigitalisate von B\u00fcchern und Zeitschriften aus dem historischen Bestand der ULB M\u00fcnster sowie Sammlungen aus der Region Westfalen"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1014"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Digitale Sammlungen der Universit\u00e4ts- und Landesbibliothek M\u00fcnster"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/48ea0625-d099-58a2-a24d-feb778d57140.json b/oaitestdata/clarin-oai_dc/SET_1/json/48ea0625-d099-58a2-a24d-feb778d57140.json
deleted file mode 100644
index 6bcea0f0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/48ea0625-d099-58a2-a24d-feb778d57140.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=e3c657e6059711e7a2aa782bcb074135e559ae3ea2584ac8896f9dea803852b0",
-    "MetadataAccess": [
-        "e3c657e6059711e7a2aa782bcb074135e559ae3ea2584ac8896f9dea803852b0"
-    ],
-    "PublicationTimestamp": "2017-03-10T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "fulltext": "e3c657e6059711e7a2aa782bcb074135e559ae3ea2584ac8896f9dea803852b0;2018-11-15T16:40:31Z;toolService;toolService:tool;Czech to English Machine translation module;Technical Description:\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/Pilot1_technical_description.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/TechnicalDescriptionPilot2_D2.7.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2016/11/TechnicalDescriptionPilot3_D2.10.pdf;2017-03-10",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "48ea0625-d099-58a2-a24d-feb778d57140",
-    "notes": [
-        "Technical Description:\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/Pilot1_technical_description.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/TechnicalDescriptionPilot2_D2.7.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2016/11/TechnicalDescriptionPilot3_D2.10.pdf"
-    ],
-    "oai_identifier": [
-        "e3c657e6059711e7a2aa782bcb074135e559ae3ea2584ac8896f9dea803852b0"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "Czech to English Machine translation module"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/48f09096-4a58-5474-9980-7f262f47ec7d.json b/oaitestdata/clarin-oai_dc/SET_1/json/48f09096-4a58-5474-9980-7f262f47ec7d.json
deleted file mode 100644
index 77e2c1b4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/48f09096-4a58-5474-9980-7f262f47ec7d.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "A"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1784",
-    "MetadataAccess": [
-        "oai:ota:oucs:1784"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Douglass, Frederick"
-    ],
-    "fulltext": "oai:ota:oucs:1784;2018-05-17T09:29:11Z;http://ota.ox.ac.uk/headers/1784.xml;Autobiography;Douglass, Frederick;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;A;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "48f09096-4a58-5474-9980-7f262f47ec7d",
-    "oai_identifier": [
-        "oai:ota:oucs:1784"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Autobiography"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1784.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/492d2f81-ab7f-5385-9af5-1308f60c2249.json b/oaitestdata/clarin-oai_dc/SET_1/json/492d2f81-ab7f-5385-9af5-1308f60c2249.json
deleted file mode 100644
index 6d0861d9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/492d2f81-ab7f-5385-9af5-1308f60c2249.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "The Danish Language Council",
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml",
-        "text/plain; charset=utf-8",
-        "application/pdf",
-        "downloadable_files_count: 11",
-        "application/zip",
-        "text/plain"
-    ],
-    "Language": [
-        "Danish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repository.clarin.dk:20.500.12115/9",
-    "MetadataAccess": [
-        "oai:repository.clarin.dk:20.500.12115/9"
-    ],
-    "PID": "http://hdl.handle.net/20.500.12115/9",
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "The Danish Language Council",
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN-ACA-NC",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NC=1&NORED=1",
-        "ACA"
-    ],
-    "author": [
-        "Hansen, Dorte Haltrup",
-        "Braasch, Anna",
-        "Olsen, Sussi",
-        "Jakob, Halskov"
-    ],
-    "fulltext": "oai:repository.clarin.dk:20.500.12115/9;2018-06-28T13:22:32Z;hdl_20.500.12115_1;hdl_20.500.12115_3;DK-CLARIN LSP Corpus - Construction domain;Olsen, Sussi;Braasch, Anna;Hansen, Dorte Haltrup;Jakob, Halskov;Construction;Texts in the Construction Domain come from Statens Byggeforskningsinstitut, Erhvervs- og byggestyrelsen and Murerfagets Oplysningsr\u00e5d and have been collected in the DK-CLARIN project, WP2.2, 2008 - 2011. \r\nThe corpus consists of 577,392 words in 35 files. \r\nCommunicative setting/Number of files: expert->expert (18) expert->advanced (6) expert->basic (11).\r\nAll texts are in XML TEIP5 format (TEIP5DKCLARIN-format), with tokenisation, sentence and paragraph segmentation, pos-tagging, lemmatisation and termhood annotation placed in separate text external spangroups. \r\n\"DK-CLARIN LSP Corpus - Construction domain\" is a part of the Danish DK-CLARIN LSP corpus consisting of seven sub-corpora from following subject domains: Agriculture, Construction, Economics, Environment, Health, IT and Nanotechnology.;2011;corpus;http://hdl.handle.net/20.500.12115/9;dan;CLARIN-ACA-NC;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NC=1&NORED=1;ACA;application/zip;application/zip;application/zip;application/zip;application/pdf;application/pdf;application/pdf;text/plain;text/xml;text/xml;text/xml;text/plain; charset=utf-8;downloadable_files_count: 11;Centre for Language Technology, NorS, University of Copenhagen;The Danish Language Council",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "492d2f81-ab7f-5385-9af5-1308f60c2249",
-    "notes": [
-        "Texts in the Construction Domain come from Statens Byggeforskningsinstitut, Erhvervs- og byggestyrelsen and Murerfagets Oplysningsr\u00e5d and have been collected in the DK-CLARIN project, WP2.2, 2008 - 2011. \r\nThe corpus consists of 577,392 words in 35 files. \r\nCommunicative setting/Number of files: expert->expert (18) expert->advanced (6) expert->basic (11).\r\nAll texts are in XML TEIP5 format (TEIP5DKCLARIN-format), with tokenisation, sentence and paragraph segmentation, pos-tagging, lemmatisation and termhood annotation placed in separate text external spangroups. \r\n\"DK-CLARIN LSP Corpus - Construction domain\" is a part of the Danish DK-CLARIN LSP corpus consisting of seven sub-corpora from following subject domains: Agriculture, Construction, Economics, Environment, Health, IT and Nanotechnology."
-    ],
-    "oai_identifier": [
-        "oai:repository.clarin.dk:20.500.12115/9"
-    ],
-    "oai_set": [
-        "hdl_20.500.12115_1",
-        "hdl_20.500.12115_3"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Construction"
-        }
-    ],
-    "title": [
-        "DK-CLARIN LSP Corpus - Construction domain"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4934f74d-0449-5ced-b0cd-487f1e5b9dea.json b/oaitestdata/clarin-oai_dc/SET_1/json/4934f74d-0449-5ced-b0cd-487f1e5b9dea.json
deleted file mode 100644
index 66770931..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4934f74d-0449-5ced-b0cd-487f1e5b9dea.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Jakopin, Primo\u017e"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-505",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-505"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-505",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Slovenia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-505;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Dictionary of Standard Slovenian Language;Jakopin, Primo\u017e;93.500 entries, XML-compatible;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-505;slv;downloadable_files_count: 0;Slovenia;http://bos.zrc-sazu.si/sskj_en.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4934f74d-0449-5ced-b0cd-487f1e5b9dea",
-    "notes": [
-        "93.500 entries, XML-compatible"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-505"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Dictionary of Standard Slovenian Language"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/49403e9f-1d18-52fb-944e-12eeea124d55.json b/oaitestdata/clarin-oai_dc/SET_1/json/49403e9f-1d18-52fb-944e-12eeea124d55.json
deleted file mode 100644
index 92eb73b7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/49403e9f-1d18-52fb-944e-12eeea124d55.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3540",
-    "MetadataAccess": [
-        "oai:ota:oucs:3540"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Boswell, James, 1740-1795."
-    ],
-    "fulltext": "oai:ota:oucs:3540;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3540.xml;Reflections on the late alarming bankruptcies in Scotland: Addressed to all ranks: ... with advice to such, how to conduct themselves at this crisis.;Boswell, James, 1740-1795.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "49403e9f-1d18-52fb-944e-12eeea124d55",
-    "oai_identifier": [
-        "oai:ota:oucs:3540"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Reflections on the late alarming bankruptcies in Scotland: Addressed to all ranks: ... with advice to such, how to conduct themselves at this crisis."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3540.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/496c2b89-96b4-555c-824e-78ab04adbca6.json b/oaitestdata/clarin-oai_dc/SET_1/json/496c2b89-96b4-555c-824e-78ab04adbca6.json
deleted file mode 100644
index 8933775a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/496c2b89-96b4-555c-824e-78ab04adbca6.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Preston, Michael James"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(4 files : ca. 242, 242, 241, 172 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0068",
-    "MetadataAccess": [
-        "oai:ota:oucs:0068"
-    ],
-    "PublicationTimestamp": "1892-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1892"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hardy, Thomas, 1840-1928"
-    ],
-    "fulltext": "oai:ota:oucs:0068;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0068.xml;Tess of the D\"Urbervilles : an authoritative text / by Thomas Hardy;Hardy, Thomas, 1840-1928;1892;text_and_corpus_linguistics;English fiction -- 19th century;Oxford Text Archive, University of Oxford;Preston, Michael James;(4 files : ca. 242, 242, 241, 172 KB);Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "496c2b89-96b4-555c-824e-78ab04adbca6",
-    "oai_identifier": [
-        "oai:ota:oucs:0068"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English fiction -- th century"
-        }
-    ],
-    "title": [
-        "Tess of the D\"Urbervilles : an authoritative text / by Thomas Hardy"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0068.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4984c323-fa25-5898-8145-35c099bcf0e6.json b/oaitestdata/clarin-oai_dc/SET_1/json/4984c323-fa25-5898-8145-35c099bcf0e6.json
deleted file mode 100644
index 950c4680..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4984c323-fa25-5898-8145-35c099bcf0e6.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "Contributor": [
-        "Variaci\u00f3, Iula"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Catalan",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1106",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1106"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1106",
-    "PublicationTimestamp": "1993-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1993"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1106;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Corpus d\u2019entrevistes socioling\u00fc\u00edstiques a castellanoparlants i catalanoparlants en temps aparent (TA);Variaci\u00f3, Iula;oral corpus;Oral corpus containing 15 sociolinguistic interviews in Spanish and Catalan,  carried out by means of  Labovian techniques.;1993;corpus;http://hdl.handle.net/11372/LRT-1106;cat;spa;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra;http://www.iula.upf.edu/recurs08ca.htm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4984c323-fa25-5898-8145-35c099bcf0e6",
-    "notes": [
-        "Oral corpus containing 15 sociolinguistic interviews in Spanish and Catalan,  carried out by means of  Labovian techniques."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1106"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "oral corpus"
-        }
-    ],
-    "title": [
-        "Corpus d\u2019entrevistes socioling\u00fc\u00edstiques a castellanoparlants i catalanoparlants en temps aparent (TA)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/49f58697-8977-5347-ba81-5bb0e9b70eb9.json b/oaitestdata/clarin-oai_dc/SET_1/json/49f58697-8977-5347-ba81-5bb0e9b70eb9.json
deleted file mode 100644
index 6b3153a6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/49f58697-8977-5347-ba81-5bb0e9b70eb9.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/pdf"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/284",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/284"
-    ],
-    "PID": "http://hdl.handle.net/11321/284",
-    "PublicationTimestamp": "2016-04-25T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Oleksy, Marcin",
-        "Marci\u0144czuk, Micha\u0142",
-        "Koco\u0144, Jan",
-        "Berna\u015b, Tomasz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/284;2016-06-03T13:22:09Z;hdl_11321_3;hdl_11321_4;KPWr annotation guidelines - temporal expressions;Marci\u0144czuk, Micha\u0142;Oleksy, Marcin;Koco\u0144, Jan;Berna\u015b, Tomasz;temporal expressions;annotation guidelines;corpora annotation;Temporal expressions annotation guidelines describing the process of manual annotation of documents in Polish Corpus of Wroc\u0142aw University of Technology (KPWr);2016-04-25;languageDescription;http://hdl.handle.net/11321/284;pol;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;application/pdf;downloadable_files_count: 1;Wroc\u0142aw University of Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "49f58697-8977-5347-ba81-5bb0e9b70eb9",
-    "notes": [
-        "Temporal expressions annotation guidelines describing the process of manual annotation of documents in Polish Corpus of Wroc\u0142aw University of Technology (KPWr)"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/284"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "temporal expressions"
-        },
-        {
-            "name": "annotation guidelines"
-        },
-        {
-            "name": "corpora annotation"
-        }
-    ],
-    "title": [
-        "KPWr annotation guidelines - temporal expressions"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4a052bce-6d08-51a6-a568-e4e647415bee.json b/oaitestdata/clarin-oai_dc/SET_1/json/4a052bce-6d08-51a6-a568-e4e647415bee.json
deleted file mode 100644
index e6f5cac4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4a052bce-6d08-51a6-a568-e4e647415bee.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Mertens, Piet"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "French"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-450",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-450"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-450",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "France"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-450;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;DicoValence;Mertens, Piet;3700 entries, text;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-450;fra;downloadable_files_count: 0;France;http://bach.arts.kuleuven.be/dicovalence/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4a052bce-6d08-51a6-a568-e4e647415bee",
-    "notes": [
-        "3700 entries, text"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-450"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "DicoValence"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4a05e904-459f-520b-9302-8ea8039e3f26.json b/oaitestdata/clarin-oai_dc/SET_1/json/4a05e904-459f-520b-9302-8ea8039e3f26.json
deleted file mode 100644
index 395f0155..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4a05e904-459f-520b-9302-8ea8039e3f26.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Department of Linguistics and Nordic Studies, University of Oslo"
-    ],
-    "Contributor": [
-        "Fjeld, Ruth Vatvedt"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-673",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-673"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-673",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Department of Linguistics and Nordic Studies, University of Oslo"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Norway"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-673;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;The Corpus for Bokm\u00e5l Lexicography LBK;Fjeld, Ruth Vatvedt;100 mill. words from newspapers, novels, magazines etc. LBK is a representative, weighted corpus made for lexicographic purposes.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-673;downloadable_files_count: 0;Norway;Department of Linguistics and Nordic Studies, University of Oslo;http://www.hf.uio.no/iln/tjenester/kunnskap/samlinger/bokmal/veiledningkorpus/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4a05e904-459f-520b-9302-8ea8039e3f26",
-    "notes": [
-        "100 mill. words from newspapers, novels, magazines etc. LBK is a representative, weighted corpus made for lexicographic purposes."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-673"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "The Corpus for Bokm\u00e5l Lexicography LBK"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4a0732d6-10b2-5186-bc57-b4d0bbe88bda.json b/oaitestdata/clarin-oai_dc/SET_1/json/4a0732d6-10b2-5186-bc57-b4d0bbe88bda.json
deleted file mode 100644
index 72bd4b51..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4a0732d6-10b2-5186-bc57-b4d0bbe88bda.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "University of Glasgow"
-    ],
-    "Contributor": [
-        "Corbett, John"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-897",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-897"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-897",
-    "PublicationTimestamp": "2007-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2007"
-    ],
-    "Publisher": [
-        "University of Glasgow"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-897;2016-04-06T16:39:56Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Scottish corpus of texts and speech (SCOTS);Corbett, John;Written and spoken (20%) texts for the languages of Scotland. Ca 4 mwd. Orthographic transcriptions are synchronised with the source audio or video.;2007;corpus;http://hdl.handle.net/11372/LRT-897;eng;downloadable_files_count: 0;United Kingdom;University of Glasgow;http://www.scottishcorpus.ac.uk/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4a0732d6-10b2-5186-bc57-b4d0bbe88bda",
-    "notes": [
-        "Written and spoken (20%) texts for the languages of Scotland. Ca 4 mwd. Orthographic transcriptions are synchronised with the source audio or video."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-897"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Scottish corpus of texts and speech (SCOTS)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4a14b3a2-8d32-5a69-a73d-9ed61f243421.json b/oaitestdata/clarin-oai_dc/SET_1/json/4a14b3a2-8d32-5a69-a73d-9ed61f243421.json
deleted file mode 100644
index c5c6ba76..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4a14b3a2-8d32-5a69-a73d-9ed61f243421.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/299",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/299"
-    ],
-    "PID": "http://hdl.handle.net/11321/299",
-    "PublicationTimestamp": "2016-06-06T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "Walkowiak, Tomasz",
-        "Piasecki, Maciej",
-        "M\u0142ynarczyk, Ksenia"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/299;2016-06-06T15:02:03Z;hdl_11321_3;hdl_11321_4;Cinderella - tool for Clustering and Classifications of Texts in Polish;Piasecki, Maciej;M\u0142ynarczyk, Ksenia;Walkowiak, Tomasz;clustering;classification;NLP;System for clustering and classifications of Texts in Polish. Source code.;2016-06-06;toolService;http://hdl.handle.net/11321/299;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;Wroc\u0142aw University of Science and Technology;http://clarin-pl.eu",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4a14b3a2-8d32-5a69-a73d-9ed61f243421",
-    "notes": [
-        "System for clustering and classifications of Texts in Polish. Source code."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/299"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "clustering"
-        },
-        {
-            "name": "classification"
-        },
-        {
-            "name": "NLP"
-        }
-    ],
-    "title": [
-        "Cinderella - tool for Clustering and Classifications of Texts in Polish"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4a15441b-c893-5e23-b034-6dcfec2046a8.json b/oaitestdata/clarin-oai_dc/SET_1/json/4a15441b-c893-5e23-b034-6dcfec2046a8.json
deleted file mode 100644
index 1741f4e5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4a15441b-c893-5e23-b034-6dcfec2046a8.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-944",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-944"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-944",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-944;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Early New High German;ca. 300.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-944;deu;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#nhd",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4a15441b-c893-5e23-b034-6dcfec2046a8",
-    "notes": [
-        "ca. 300.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-944"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Early New High German"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4a2d13bc-268d-5975-bdf9-3bc22372046c.json b/oaitestdata/clarin-oai_dc/SET_1/json/4a2d13bc-268d-5975-bdf9-3bc22372046c.json
deleted file mode 100644
index b6c846fb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4a2d13bc-268d-5975-bdf9-3bc22372046c.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish",
-        "Russian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/67",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/67"
-    ],
-    "PID": "http://hdl.handle.net/10794/67",
-    "PublicationTimestamp": "2015-04-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/67;2017-10-31T15:25:06Z;hdl_10794_1;hdl_10794_2;ASPAC \u2013 Swedish-Russian (2017-10-16);ASPAC \u2013 svenska-ryska (2017-10-16);n/a, n/a;ASPAC;Parallel;Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.;Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat.;2015-04-16;corpus;http://hdl.handle.net/10794/67;swe;rus;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/octet-stream;application/gzip;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/aspacsvru",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4a2d13bc-268d-5975-bdf9-3bc22372046c",
-    "notes": [
-        "Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.",
-        "Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/67"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ASPAC"
-        },
-        {
-            "name": "Parallel"
-        }
-    ],
-    "title": [
-        "ASPAC \u2013 Swedish-Russian (2017-10-16)",
-        "ASPAC \u2013 svenska-ryska (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4a3d6c4b-555b-5200-a461-f144cc6d25f4.json b/oaitestdata/clarin-oai_dc/SET_1/json/4a3d6c4b-555b-5200-a461-f144cc6d25f4.json
deleted file mode 100644
index 7def4cf4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4a3d6c4b-555b-5200-a461-f144cc6d25f4.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "researchgate.net"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/pdf"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/477",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/477"
-    ],
-    "PID": "http://hdl.handle.net/11321/477",
-    "PublicationTimestamp": "2018-06-02T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "researchgate.net"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Ryznar, Zygmunt"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/477;2018-06-07T20:10:59Z;hdl_11321_3;hdl_11321_4;Linguistic presentation of object structure and relations in OSL language;Ryznar, Zygmunt;object structure and relations;business it human specification language;object geometric mapping;OSL is a markup universal  language for linguistic description of  any object  in terms of structure  and behavior. The kernel is presented and subsets for IT system,  business  and  human-being.   Special atention is given to geometrical structures suggested as  new data types.;2018-06-02;languageDescription;http://hdl.handle.net/11321/477;eng;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;application/pdf;downloadable_files_count: 1;researchgate.net;http://ryznar-zygmunt.eu/ipedia/OSL-D.pdf",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4a3d6c4b-555b-5200-a461-f144cc6d25f4",
-    "notes": [
-        "OSL is a markup universal  language for linguistic description of  any object  in terms of structure  and behavior. The kernel is presented and subsets for IT system,  business  and  human-being.   Special atention is given to geometrical structures suggested as  new data types."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/477"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "object structure relations"
-        },
-        {
-            "name": "business human specification language"
-        },
-        {
-            "name": "object geometric mapping"
-        }
-    ],
-    "title": [
-        "Linguistic presentation of object structure and relations in OSL language"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4a4dae93-ca19-560f-8c9f-5cfd47a7f2f6.json b/oaitestdata/clarin-oai_dc/SET_1/json/4a4dae93-ca19-560f-8c9f-5cfd47a7f2f6.json
deleted file mode 100644
index b307cc3f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4a4dae93-ca19-560f-8c9f-5cfd47a7f2f6.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3185",
-    "MetadataAccess": [
-        "oai:ota:oucs:3185"
-    ],
-    "PublicationTimestamp": "1891-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1891"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Stevenson, Robert Louis, 1850-1894"
-    ],
-    "fulltext": "oai:ota:oucs:3185;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3185.xml;In the South Seas;Stevenson, Robert Louis, 1850-1894;not after: 1891;text_and_corpus_linguistics;Scottish literature -- 19th century;eng;Oxford Text Archive, University of Oxford;Triggs, Jeffery;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4a4dae93-ca19-560f-8c9f-5cfd47a7f2f6",
-    "oai_identifier": [
-        "oai:ota:oucs:3185"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Scottish literature -- th century"
-        }
-    ],
-    "title": [
-        "In the South Seas"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3185.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4a51ce81-4f2e-542a-bdd6-dbd12df85563.json b/oaitestdata/clarin-oai_dc/SET_1/json/4a51ce81-4f2e-542a-bdd6-dbd12df85563.json
deleted file mode 100644
index 30b54561..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4a51ce81-4f2e-542a-bdd6-dbd12df85563.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 172 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1327",
-    "MetadataAccess": [
-        "oai:ota:oucs:1327"
-    ],
-    "PublicationTimestamp": "1682-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1682"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Behn, Aphra, 1640-1689"
-    ],
-    "fulltext": "oai:ota:oucs:1327;2018-03-07T12:37:09Z;http://ota.ox.ac.uk/headers/1327.xml;The city heiress, or, Sir Timothy Treat-all;Behn, Aphra, 1640-1689;1682;text_and_corpus_linguistics;Plays -- England -- 17th century;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 172 KB);Text;Plays;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4a51ce81-4f2e-542a-bdd6-dbd12df85563",
-    "oai_identifier": [
-        "oai:ota:oucs:1327"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        }
-    ],
-    "title": [
-        "The city heiress, or, Sir Timothy Treat-all"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1327.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4a58eb8e-f7e9-565a-8608-b2c7410807c0.json b/oaitestdata/clarin-oai_dc/SET_1/json/4a58eb8e-f7e9-565a-8608-b2c7410807c0.json
deleted file mode 100644
index 1006b9fd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4a58eb8e-f7e9-565a-8608-b2c7410807c0.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4077",
-    "MetadataAccess": [
-        "oai:ota:oucs:4077"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Duck, Stephen, 1705-1756."
-    ],
-    "fulltext": "oai:ota:oucs:4077;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4077.xml;An ode on the battle of Dettingen: Humbly inscrib'd to the King. By Stephen Duck.;Duck, Stephen, 1705-1756.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4a58eb8e-f7e9-565a-8608-b2c7410807c0",
-    "oai_identifier": [
-        "oai:ota:oucs:4077"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An ode on the battle of Dettingen: Humbly inscrib'd to the King. By Stephen Duck."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4077.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4a77fce1-1a4d-5f7e-b1b9-02d8f3300186.json b/oaitestdata/clarin-oai_dc/SET_1/json/4a77fce1-1a4d-5f7e-b1b9-02d8f3300186.json
deleted file mode 100644
index 2806abd4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4a77fce1-1a4d-5f7e-b1b9-02d8f3300186.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Chapman, R. W. (Robert William), 1881-1960"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 805 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1520",
-    "MetadataAccess": [
-        "oai:ota:oucs:1520"
-    ],
-    "PublicationTimestamp": "1796-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1796"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Letters"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Austen, Jane, 1775-1817"
-    ],
-    "fulltext": "oai:ota:oucs:1520;2018-02-20T10:53:30Z;http://ota.ox.ac.uk/headers/1520.xml;Jane Austen's letters to her sister Cassandra and others;Austen, Jane, 1775-1817;1796-1817;text_and_corpus_linguistics;English letters -- 19th century;eng;Oxford Text Archive, University of Oxford;Chapman, R. W. (Robert William), 1881-1960;text/sgml;(1 file : ca. 805 KB);Text;Letters;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4a77fce1-1a4d-5f7e-b1b9-02d8f3300186",
-    "oai_identifier": [
-        "oai:ota:oucs:1520"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English letters -- th century"
-        }
-    ],
-    "title": [
-        "Jane Austen's letters to her sister Cassandra and others"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1520.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4a7f9dbf-6e87-594f-9031-9baf0d231af1.json b/oaitestdata/clarin-oai_dc/SET_1/json/4a7f9dbf-6e87-594f-9031-9baf0d231af1.json
deleted file mode 100644
index 714f3928..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4a7f9dbf-6e87-594f-9031-9baf0d231af1.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "University of St. Andrews"
-    ],
-    "Contributor": [
-        "Nederhof, Mark-Jan"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1066",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1066"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1066",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of St. Andrews"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1066;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;St Andrews corpus of Ancient Egyptian;Nederhof, Mark-Jan;Collection of Ancient Egyptian texts, containing hieroglyphs, a transliteration and a translation.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1066;downloadable_files_count: 0;United Kingdom;University of St. Andrews;http://www.cs.st-andrews.ac.uk/~mjn/egyptian/texts/index.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4a7f9dbf-6e87-594f-9031-9baf0d231af1",
-    "notes": [
-        "Collection of Ancient Egyptian texts, containing hieroglyphs, a transliteration and a translation."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1066"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "St Andrews corpus of Ancient Egyptian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4a89b7c1-afd0-53ee-9162-1be1509515bd.json b/oaitestdata/clarin-oai_dc/SET_1/json/4a89b7c1-afd0-53ee-9162-1be1509515bd.json
deleted file mode 100644
index d4b46833..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4a89b7c1-afd0-53ee-9162-1be1509515bd.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 21",
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/zip",
-        "application/vnd.oasis.opendocument.text",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/54",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/54"
-    ],
-    "PID": "http://hdl.handle.net/11321/54",
-    "PublicationTimestamp": "2015-04-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Oleksy, Marcin"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/54;2015-04-10T08:57:49Z;hdl_11321_3;hdl_11321_4;Open license texts sample;Oleksy, Marcin;story;tale;news;Sample corpus of texts distributed under open license. It consists of 20 documents in TXT, DOCX, DOC or ODT format.;2015-04-01;corpus;http://hdl.handle.net/11321/54;pol;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;application/vnd.oasis.opendocument.text;application/msword;application/vnd.oasis.opendocument.text;text/plain;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.oasis.opendocument.text;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.oasis.opendocument.text;text/plain;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;text/plain;application/vnd.oasis.opendocument.text;text/plain;application/zip;text/plain; charset=utf-8;downloadable_files_count: 21;Wroc\u0142aw University of Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4a89b7c1-afd0-53ee-9162-1be1509515bd",
-    "notes": [
-        "Sample corpus of texts distributed under open license. It consists of 20 documents in TXT, DOCX, DOC or ODT format."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/54"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "story"
-        },
-        {
-            "name": "tale"
-        },
-        {
-            "name": "news"
-        }
-    ],
-    "title": [
-        "Open license texts sample"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4a8e766b-5972-55f9-b221-e5fbb9f8a2d2.json b/oaitestdata/clarin-oai_dc/SET_1/json/4a8e766b-5972-55f9-b221-e5fbb9f8a2d2.json
deleted file mode 100644
index 62febfa7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4a8e766b-5972-55f9-b221-e5fbb9f8a2d2.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "1.2 MB"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0281",
-    "MetadataAccess": [
-        "oai:ota:oucs:0281"
-    ],
-    "PublicationYear": [
-        "440 BCE-400 BCE"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Thucydides"
-    ],
-    "fulltext": "oai:ota:oucs:0281;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0281.xml;Complete works;Thucydides;440 BCE-400 BCE;text_and_corpus_linguistics;grc;Oxford Text Archive, University of Oxford;1.2 MB;Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4a8e766b-5972-55f9-b221-e5fbb9f8a2d2",
-    "oai_identifier": [
-        "oai:ota:oucs:0281"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Complete works"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0281.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4a946705-68d8-56e3-8fa6-2362cfc0b172.json b/oaitestdata/clarin-oai_dc/SET_1/json/4a946705-68d8-56e3-8fa6-2362cfc0b172.json
deleted file mode 100644
index ad64494c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4a946705-68d8-56e3-8fa6-2362cfc0b172.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "less than 512 KB"
-    ],
-    "Language": [
-        "Official Aramaic (700-300 BCE)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0140",
-    "MetadataAccess": [
-        "oai:ota:oucs:0140"
-    ],
-    "PublicationYear": [
-        "500 BCE-1 BCE"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Devotional literature"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Unknown"
-    ],
-    "fulltext": "oai:ota:oucs:0140;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0140.xml; Psalms  : (Targum text) / compiled by Richard T. White;Unknown;500 BCE-1 BCE;text_and_corpus_linguistics;Devotional literature -- Israel;arc;Oxford Text Archive, University of Oxford;less than 512 KB;Text;Devotional literature;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4a946705-68d8-56e3-8fa6-2362cfc0b172",
-    "oai_identifier": [
-        "oai:ota:oucs:0140"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Devotional literature -- Israel"
-        }
-    ],
-    "title": [
-        " Psalms  : (Targum text) / compiled by Richard T. White"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0140.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4abebf93-16fa-5426-936f-d0fab5d03f9d.json b/oaitestdata/clarin-oai_dc/SET_1/json/4abebf93-16fa-5426-936f-d0fab5d03f9d.json
deleted file mode 100644
index 37f714c8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4abebf93-16fa-5426-936f-d0fab5d03f9d.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Berlin-Brandenburg Academy of Sciences and Humanities"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/tei+xml",
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-974",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-974"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-974",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Berlin-Brandenburg Academy of Sciences and Humanities"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-974;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;DDR-Korpus;9 million words in 1150 texts from GDR written between 1949 and 1990. Part of the DWDS project;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-974;deu;application/tei+xml;downloadable_files_count: 0;Germany;Berlin-Brandenburg Academy of Sciences and Humanities;http://www.dwds.de/ressourcen/korpora/#part_1",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4abebf93-16fa-5426-936f-d0fab5d03f9d",
-    "notes": [
-        "9 million words in 1150 texts from GDR written between 1949 and 1990. Part of the DWDS project"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-974"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "DDR-Korpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4ace1f96-8e16-535c-ab6e-8971c7c603d5.json b/oaitestdata/clarin-oai_dc/SET_1/json/4ace1f96-8e16-535c-ab6e-8971c7c603d5.json
deleted file mode 100644
index 97744283..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4ace1f96-8e16-535c-ab6e-8971c7c603d5.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3947",
-    "MetadataAccess": [
-        "oai:ota:oucs:3947"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Wakefield, Gilbert, 1756-1801."
-    ],
-    "fulltext": "oai:ota:oucs:3947;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3947.xml;An examination of The age of reason: or an investigation of true and fabulous theology, by Thomas Paine: by Gilbert Wakefield, ...;Wakefield, Gilbert, 1756-1801.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4ace1f96-8e16-535c-ab6e-8971c7c603d5",
-    "oai_identifier": [
-        "oai:ota:oucs:3947"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An examination of The age of reason: or an investigation of true and fabulous theology, by Thomas Paine: by Gilbert Wakefield, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3947.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4af4d355-a411-5282-8f76-574caf7f9323.json b/oaitestdata/clarin-oai_dc/SET_1/json/4af4d355-a411-5282-8f76-574caf7f9323.json
deleted file mode 100644
index 36f63149..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4af4d355-a411-5282-8f76-574caf7f9323.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Universit\u00e4t Hamburg"
-    ],
-    "Contributor": [
-        "Sarnowsky, Prof. Dr. J\u00fcrgen"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1140",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1140"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1140",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Universit\u00e4t Hamburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1140;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Die mittelalterlichen Schuld- und Rechnungsb\u00fccher des Deutschen Ordens um 1400;Sarnowsky, Prof. Dr. J\u00fcrgen;Germanistik;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1140;deu;downloadable_files_count: 0;Germany;Universit\u00e4t Hamburg;http://www.schuredo.uni-hamburg.de/content/below/index.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4af4d355-a411-5282-8f76-574caf7f9323",
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1140"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Die mittelalterlichen Schuld- und Rechnungsb\u00fccher des Deutschen Ordens um 1400"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4b0d2f55-1285-5040-80b5-092b5b9e0c35.json b/oaitestdata/clarin-oai_dc/SET_1/json/4b0d2f55-1285-5040-80b5-092b5b9e0c35.json
deleted file mode 100644
index 5406d6e4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4b0d2f55-1285-5040-80b5-092b5b9e0c35.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Arts, Institute of the Czech National Corpus, Charles University in Prague"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-3B09-4",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-3B09-4"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-3B09-4",
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Faculty of Arts, Institute of the Czech National Corpus, Charles University in Prague"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Czech National Corpus (Shuffled Corpus Data)",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/license-cnc",
-        "ACA"
-    ],
-    "author": [
-        "Hn\u00e1tkov\u00e1, Milena",
-        "Petkevi\u010d, Vladim\u00edr",
-        "K\u0159en, Michal",
-        "Jel\u00ednek, Tom\u00e1\u0161",
-        "Skoumalov\u00e1, Hana",
-        "Proch\u00e1zka, Pavel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-3B09-4;2018-10-08T09:46:33Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;SYN2013PUB: corpus of written Czech newspapers;K\u0159en, Michal;Hn\u00e1tkov\u00e1, Milena;Jel\u00ednek, Tom\u00e1\u0161;Petkevi\u010d, Vladim\u00edr;Proch\u00e1zka, Pavel;Skoumalov\u00e1, Hana;corpus;written language;Corpus of contemporary Czech newspapers and magazines sized 935 MW. It contains various titles published between 2005\u20132009. The corpus is lemmatized and morphologically tagged by a combination of stochastic and rule-based methods. The corpus is provided in a (semi-XML) vertical format used as an input to the Manatee query engine. The data thus correspond to the corpus available via query interface to registered users of the CNC with one important exception: they are shuffled, i.e. divided into blocks sized max. 100 words (respecting the sentence boundaries) whose ordering was randomized within the given document.;2013;corpus;http://hdl.handle.net/11858/00-097C-0000-0023-3B09-4;ces;Czech National Corpus (Shuffled Corpus Data);https://lindat.mff.cuni.cz/repository/xmlui/page/license-cnc;ACA;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Faculty of Arts, Institute of the Czech National Corpus, Charles University in Prague;http://wiki.korpus.cz/doku.php/en:cnk:syn2013pub",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4b0d2f55-1285-5040-80b5-092b5b9e0c35",
-    "notes": [
-        "Corpus of contemporary Czech newspapers and magazines sized 935 MW. It contains various titles published between 2005\u20132009. The corpus is lemmatized and morphologically tagged by a combination of stochastic and rule-based methods. The corpus is provided in a (semi-XML) vertical format used as an input to the Manatee query engine. The data thus correspond to the corpus available via query interface to registered users of the CNC with one important exception: they are shuffled, i.e. divided into blocks sized max. 100 words (respecting the sentence boundaries) whose ordering was randomized within the given document."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-3B09-4"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "written language"
-        }
-    ],
-    "title": [
-        "SYN2013PUB: corpus of written Czech newspapers"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4b1d4833-71a3-598c-a074-0d4f7dc98326.json b/oaitestdata/clarin-oai_dc/SET_1/json/4b1d4833-71a3-598c-a074-0d4f7dc98326.json
deleted file mode 100644
index 2134e251..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4b1d4833-71a3-598c-a074-0d4f7dc98326.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-630",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-630"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-630",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Code of conduct"
-    ],
-    "SpatialCoverage": [
-        "Canada"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-630;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Beaver corpus;Documentation of the Beaver project (DoBeS project);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-630;Code of conduct;application/octet-stream;downloadable_files_count: 0;Canada;http://corpus1.mpi.nl/ds/imdi_browser/?openpath=MPI79025%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4b1d4833-71a3-598c-a074-0d4f7dc98326",
-    "notes": [
-        "Documentation of the Beaver project (DoBeS project)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-630"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Beaver corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4b2f8209-37fb-5158-ba2b-31737f0cdb6c.json b/oaitestdata/clarin-oai_dc/SET_1/json/4b2f8209-37fb-5158-ba2b-31737f0cdb6c.json
deleted file mode 100644
index 7b1fdcff..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4b2f8209-37fb-5158-ba2b-31737f0cdb6c.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Ibtikarat team"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/xml",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Arabic"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1944",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1944"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1944",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Ibtikarat team"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)",
-        "http://creativecommons.org/licenses/by-nc/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Namly, Driss"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1944;2017-02-06T11:05:29Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LMF Contemporary Arabic dictionary;Namly, Driss;lexical semantics;An LMF conformant XML-based file containing the electronic version of al logha al arabia al moassira (Contemporary Arabic) dictionary. An Arabic monolingual dictionary accomplished by Ahmed Mukhtar Abdul Hamid Omar (deceased: 1424) with the help of a working group;2015;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1944;ara;Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0);http://creativecommons.org/licenses/by-nc/4.0/;PUB;text/xml;text/plain; charset=utf-8;downloadable_files_count: 1;Ibtikarat team;http://arabic.emi.ac.ma/ibtikarat/?q=Resources",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4b2f8209-37fb-5158-ba2b-31737f0cdb6c",
-    "notes": [
-        "An LMF conformant XML-based file containing the electronic version of al logha al arabia al moassira (Contemporary Arabic) dictionary. An Arabic monolingual dictionary accomplished by Ahmed Mukhtar Abdul Hamid Omar (deceased: 1424) with the help of a working group"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1944"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "lexical semantics"
-        }
-    ],
-    "title": [
-        "LMF Contemporary Arabic dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4b447685-472d-54ab-a16c-f54199731e79.json b/oaitestdata/clarin-oai_dc/SET_1/json/4b447685-472d-54ab-a16c-f54199731e79.json
deleted file mode 100644
index 313a75fc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4b447685-472d-54ab-a16c-f54199731e79.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 205 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "Old French (842-ca. 1400)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0184",
-    "MetadataAccess": [
-        "oai:ota:oucs:0184"
-    ],
-    "PublicationTimestamp": "1170-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1170"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Chr\u00c3\u00a9tien, de Troyes, 12th cent."
-    ],
-    "fulltext": "oai:ota:oucs:0184;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0184.xml;Chevalier au lyon;Ywain;Chr\u00c3\u00a9tien, de Troyes, 12th cent.;1170-1179;text_and_corpus_linguistics;Poems -- France -- 12th century;Romances -- France -- 12th century;fro;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 205 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4b447685-472d-54ab-a16c-f54199731e79",
-    "oai_identifier": [
-        "oai:ota:oucs:0184"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- France -- th century"
-        },
-        {
-            "name": "Romances -- France -- th century"
-        }
-    ],
-    "title": [
-        "Chevalier au lyon",
-        "Ywain"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0184.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4b611d41-e489-50ca-8780-fa0cf71058a7.json b/oaitestdata/clarin-oai_dc/SET_1/json/4b611d41-e489-50ca-8780-fa0cf71058a7.json
deleted file mode 100644
index b910340c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4b611d41-e489-50ca-8780-fa0cf71058a7.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "University of Bergen"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "application/octet-stream",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Norwegian Bokm\u00e5l",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/117",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/117"
-    ],
-    "PID": "http://hdl.handle.net/11509/117",
-    "PublicationTimestamp": "2017-01-10T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "University of Bergen"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "CLARIN_PUB-BY",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaPub?BY=1",
-        "PUB"
-    ],
-    "author": [
-        "H\u00f8is\u00e6ter, Tore"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/117;2017-01-18T09:17:59Z;hdl_11509_1;hdl_11509_2;Marine evertebrates;H\u00f8is\u00e6ter, Tore;Marine fauna;Terminology;Terminological;Termbase;The resource Marine Evertebrater is a terminological database containing terms in Norwegian Bokm\u00e5l and Latin designating family/genus/species of marine evertebrates in the Norwegian marine fauna.;2017-01-10;lexicalConceptualResource;http://hdl.handle.net/11509/117;nob;lat;CLARIN_PUB-BY;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaPub?BY=1;PUB;application/zip;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;University of Bergen;https://www.terminologi.no",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4b611d41-e489-50ca-8780-fa0cf71058a7",
-    "notes": [
-        "The resource Marine Evertebrater is a terminological database containing terms in Norwegian Bokm\u00e5l and Latin designating family/genus/species of marine evertebrates in the Norwegian marine fauna."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/117"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Marine fauna"
-        },
-        {
-            "name": "Terminology"
-        },
-        {
-            "name": "Terminological"
-        },
-        {
-            "name": "Termbase"
-        }
-    ],
-    "title": [
-        "Marine evertebrates"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4b96e2d9-5177-5fdc-95e5-b4741209bb73.json b/oaitestdata/clarin-oai_dc/SET_1/json/4b96e2d9-5177-5fdc-95e5-b4741209bb73.json
deleted file mode 100644
index 203e8b8d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4b96e2d9-5177-5fdc-95e5-b4741209bb73.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-721",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-721"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-721",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Code of conduct"
-    ],
-    "SpatialCoverage": [
-        "Malaysia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-721;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Semang corpus;Documentation of the Semang project (DoBeS project);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-721;Code of conduct;downloadable_files_count: 0;Malaysia;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI553373%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4b96e2d9-5177-5fdc-95e5-b4741209bb73",
-    "notes": [
-        "Documentation of the Semang project (DoBeS project)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-721"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Semang corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4b9cb51a-a4aa-5894-b0bb-bca582796823.json b/oaitestdata/clarin-oai_dc/SET_1/json/4b9cb51a-a4aa-5894-b0bb-bca582796823.json
deleted file mode 100644
index 8b3c3646..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4b9cb51a-a4aa-5894-b0bb-bca582796823.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Kraszewski"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 4",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/80",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/80"
-    ],
-    "PID": "http://hdl.handle.net/11321/80",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Kraszewski"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Kraszewski, Kraszewski"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/80;2015-04-14T12:55:11Z;hdl_11321_3;hdl_11321_4;MWE Kraszewski;Kraszewski, Kraszewski;Kraszewski;2015-04-08;corpus;http://hdl.handle.net/11321/80;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;application/zip;text/plain; charset=utf-8;downloadable_files_count: 4;Kraszewski",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4b9cb51a-a4aa-5894-b0bb-bca582796823",
-    "notes": [
-        "Kraszewski"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/80"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Kraszewski"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4bdee988-2404-58a6-93f3-3bce6b0c87f1.json b/oaitestdata/clarin-oai_dc/SET_1/json/4bdee988-2404-58a6-93f3-3bce6b0c87f1.json
deleted file mode 100644
index def02b09..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4bdee988-2404-58a6-93f3-3bce6b0c87f1.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "University of Tampere"
-    ],
-    "Contributor": [
-        "Mikhailov, Mikhail"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Finnish",
-        "Russian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1076",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1076"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1076",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Tampere"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Finland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1076;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;ParRus, Russian-Finnish parallel corpus of literary texts;Mikhailov, Mikhail;Russian literary texts (classical literature & 20th century) and their translations into Finnish aligned in paragraph level;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1076;fin;rus;application/octet-stream;downloadable_files_count: 0;Finland;University of Tampere;https://mustikka.uta.fi/corpora",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4bdee988-2404-58a6-93f3-3bce6b0c87f1",
-    "notes": [
-        "Russian literary texts (classical literature & 20th century) and their translations into Finnish aligned in paragraph level"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1076"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "ParRus, Russian-Finnish parallel corpus of literary texts"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4c1e0d4c-7463-5ede-8d4e-b70197063123.json b/oaitestdata/clarin-oai_dc/SET_1/json/4c1e0d4c-7463-5ede-8d4e-b70197063123.json
deleted file mode 100644
index 757e1bcc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4c1e0d4c-7463-5ede-8d4e-b70197063123.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=0c819d18059711e7a2aa782bcb074135b16cedee74904d20b353ddfa8a6ec947",
-    "MetadataAccess": [
-        "0c819d18059711e7a2aa782bcb074135b16cedee74904d20b353ddfa8a6ec947"
-    ],
-    "PublicationTimestamp": "2017-03-10T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "fulltext": "0c819d18059711e7a2aa782bcb074135b16cedee74904d20b353ddfa8a6ec947;2018-11-15T16:40:30Z;toolService;toolService:tool;English to Spanish Machine translation module;Technical Description:\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/Pilot1_technical_description.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/TechnicalDescriptionPilot2_D2.7.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2016/11/TechnicalDescriptionPilot3_D2.10.pdf;2017-03-10",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4c1e0d4c-7463-5ede-8d4e-b70197063123",
-    "notes": [
-        "Technical Description:\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/Pilot1_technical_description.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/TechnicalDescriptionPilot2_D2.7.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2016/11/TechnicalDescriptionPilot3_D2.10.pdf"
-    ],
-    "oai_identifier": [
-        "0c819d18059711e7a2aa782bcb074135b16cedee74904d20b353ddfa8a6ec947"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "English to Spanish Machine translation module"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4c3ce41b-9c83-5bab-9002-6d03f07d4b90.json b/oaitestdata/clarin-oai_dc/SET_1/json/4c3ce41b-9c83-5bab-9002-6d03f07d4b90.json
deleted file mode 100644
index b49ed49a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4c3ce41b-9c83-5bab-9002-6d03f07d4b90.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Sienkiewicz"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 10",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/92",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/92"
-    ],
-    "PID": "http://hdl.handle.net/11321/92",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Sienkiewicz"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Sienkiewicz, Sienkiewicz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/92;2015-04-14T12:55:39Z;hdl_11321_3;hdl_11321_4;MWE Sienkiewicz;Sienkiewicz, Sienkiewicz;Sienkiewicz;2015-04-08;corpus;http://hdl.handle.net/11321/92;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 10;Sienkiewicz",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4c3ce41b-9c83-5bab-9002-6d03f07d4b90",
-    "notes": [
-        "Sienkiewicz"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/92"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Sienkiewicz"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4c5ab8a9-1282-5296-a77b-6d619ceea38b.json b/oaitestdata/clarin-oai_dc/SET_1/json/4c5ab8a9-1282-5296-a77b-6d619ceea38b.json
deleted file mode 100644
index f8290308..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4c5ab8a9-1282-5296-a77b-6d619ceea38b.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5595",
-    "MetadataAccess": [
-        "oai:ota:oucs:5595"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Threlfal, William."
-    ],
-    "fulltext": "oai:ota:oucs:5595;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5595.xml;Essay on epilepsy. In which a new theory of that disease is attempted, from which the proximate cause is investigated, and indications brought from thence; shewing clearly the consistency of the method of cure. By W. Threlfal,;Threlfal, William.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4c5ab8a9-1282-5296-a77b-6d619ceea38b",
-    "oai_identifier": [
-        "oai:ota:oucs:5595"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Essay on epilepsy. In which a new theory of that disease is attempted, from which the proximate cause is investigated, and indications brought from thence; shewing clearly the consistency of the method of cure. By W. Threlfal,"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5595.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4c7ca542-1407-5fa0-b64d-0fd8106a76d4.json b/oaitestdata/clarin-oai_dc/SET_1/json/4c7ca542-1407-5fa0-b64d-0fd8106a76d4.json
deleted file mode 100644
index 145c9bdf..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4c7ca542-1407-5fa0-b64d-0fd8106a76d4.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German",
-        "Italian",
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1050",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1050"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1050",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1050;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;L2 Acquisition P-Moll Norbert Dittmar;Language Acquisition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1050;deu;ita;pol;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI20139%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4c7ca542-1407-5fa0-b64d-0fd8106a76d4",
-    "notes": [
-        "Language Acquisition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1050"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "L2 Acquisition P-Moll Norbert Dittmar"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4c7e83bd-303c-5fbe-9cd8-48d15ab25eb6.json b/oaitestdata/clarin-oai_dc/SET_1/json/4c7e83bd-303c-5fbe-9cd8-48d15ab25eb6.json
deleted file mode 100644
index 15ed638a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4c7e83bd-303c-5fbe-9cd8-48d15ab25eb6.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Fortier, Paul A."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 213 KB)"
-    ],
-    "Language": [
-        "French"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0194",
-    "MetadataAccess": [
-        "oai:ota:oucs:0194"
-    ],
-    "PublicationTimestamp": "1957-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1957"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Robbe-Grillet, Alain, 1922-"
-    ],
-    "fulltext": "oai:ota:oucs:0194;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0194.xml;La jalousie / Alain Robbe-Grillet;Jealousy;Robbe-Grillet, Alain, 1922-;1957;text_and_corpus_linguistics;French fiction -- 20th century;fra;Oxford Text Archive, University of Oxford;Fortier, Paul A.;(1 file : ca. 213 KB);Text;Novels;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4c7e83bd-303c-5fbe-9cd8-48d15ab25eb6",
-    "oai_identifier": [
-        "oai:ota:oucs:0194"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "French fiction -- th century"
-        }
-    ],
-    "title": [
-        "La jalousie / Alain Robbe-Grillet",
-        "Jealousy"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0194.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4c8c7200-c93a-5995-adf6-059517d40d53.json b/oaitestdata/clarin-oai_dc/SET_1/json/4c8c7200-c93a-5995-adf6-059517d40d53.json
deleted file mode 100644
index 9550d552..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4c8c7200-c93a-5995-adf6-059517d40d53.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "438 KB"
-    ],
-    "Language": [],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1177",
-    "MetadataAccess": [
-        "oai:ota:oucs:1177"
-    ],
-    "PublicationTimestamp": "1945-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1945"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Short stories"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "M\u00c3\u00a1ire"
-    ],
-    "fulltext": "oai:ota:oucs:1177;2018-03-05T14:20:38Z;http://ota.ox.ac.uk/headers/1177.xml;Sc\u00c3\u00a9al \u00c3\u00bar agus sean-sc\u00c3\u00a9al / compiled by Kieran Devine;M\u00c3\u00a1ire;1945;text_and_corpus_linguistics;Short stories -- Ireland -- 20th century;iri;Oxford Text Archive, University of Oxford;438 KB;Text;Short stories;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4c8c7200-c93a-5995-adf6-059517d40d53",
-    "oai_identifier": [
-        "oai:ota:oucs:1177"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Short stories -- Ireland -- th century"
-        }
-    ],
-    "title": [
-        "Sc\u00c3\u00a9al \u00c3\u00bar agus sean-sc\u00c3\u00a9al / compiled by Kieran Devine"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1177.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4ca39fdd-ed6c-56b7-a0ab-9b2c160edf43.json b/oaitestdata/clarin-oai_dc/SET_1/json/4ca39fdd-ed6c-56b7-a0ab-9b2c160edf43.json
deleted file mode 100644
index 7f43c8d0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4ca39fdd-ed6c-56b7-a0ab-9b2c160edf43.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1032",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1032"
-    ],
-    "PID": "http://hdl.handle.net/11356/1032",
-    "PublicationTimestamp": "2014-09-13T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/215064",
-        "https://doi.org/10.1007/s10579-015-9294-7"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Erjavec, Toma\u017e"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1032;2017-10-02T13:15:47Z;hdl_11356_1023;hdl_11356_1024;Lexicon of historical Slovene imp25k 1.1;Erjavec, Toma\u017e;historical language;modernisation;lemmatisation;tagging;TEI;The imp25k lexicon of historical Slovene was created automatically from the goo300k and foo3M annotated corpora and contains attested and manually verified word forms and their annotations with examples of use. A lexicon entry contains the modern lemma with its part-of-speech and, for archaic words, its gloss (closest modern equivalent(s) or short explanation of their meaning). The lemma is followed by its modern word forms from the corpus (i.e. the complete paradigm of the lemma is not given), and each of these has all its attested historical word forms with examples of usage.\r\n\r\nThe lexicon is available in source TEI P5 XML and in the much smaller and simpler derived tabular format, which does not contain usage examples. In the latter, multi-word units are joined with the underscore. The 1st column is the word form, the 2nd its modern equivalent, the 3rd its modern lemma, 4th its PoS tag from the IMP morphosyntactic specification, and 5th (where present) the gloss, e.g.:\r\nako_ravno<TAB>akoravno<TAB>akoravno<TAB>C<TAB>\u010deprav<LF> \r\nor \r\nak-li<TAB>ako_li<TAB>ako_li<TAB>C_Q<TAB><LF>;2014-09-13;lexicalConceptualResource;http://hdl.handle.net/11356/1032;slv;info:eu-repo/grantAgreement/EC/FP7/215064;https://doi.org/10.1007/s10579-015-9294-7;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;PUB;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 2;Jo\u017eef Stefan Institute;http://nl.ijs.si/imp/index-en.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4ca39fdd-ed6c-56b7-a0ab-9b2c160edf43",
-    "notes": [
-        "The imp25k lexicon of historical Slovene was created automatically from the goo300k and foo3M annotated corpora and contains attested and manually verified word forms and their annotations with examples of use. A lexicon entry contains the modern lemma with its part-of-speech and, for archaic words, its gloss (closest modern equivalent(s) or short explanation of their meaning). The lemma is followed by its modern word forms from the corpus (i.e. the complete paradigm of the lemma is not given), and each of these has all its attested historical word forms with examples of usage.\r\n\r\nThe lexicon is available in source TEI P5 XML and in the much smaller and simpler derived tabular format, which does not contain usage examples. In the latter, multi-word units are joined with the underscore. The 1st column is the word form, the 2nd its modern equivalent, the 3rd its modern lemma, 4th its PoS tag from the IMP morphosyntactic specification, and 5th (where present) the gloss, e.g.:\r\nako_ravno<TAB>akoravno<TAB>akoravno<TAB>C<TAB>\u010deprav<LF> \r\nor \r\nak-li<TAB>ako_li<TAB>ako_li<TAB>C_Q<TAB><LF>"
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1032"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "historical language"
-        },
-        {
-            "name": "modernisation"
-        },
-        {
-            "name": "lemmatisation"
-        },
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "Lexicon of historical Slovene imp25k 1.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4ce8ac2f-066c-51af-b611-332c35b3ae65.json b/oaitestdata/clarin-oai_dc/SET_1/json/4ce8ac2f-066c-51af-b611-332c35b3ae65.json
deleted file mode 100644
index 100f4951..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4ce8ac2f-066c-51af-b611-332c35b3ae65.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Anna Raczy\u0144ska"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "downloadable_files_count: 10",
-        "application/vnd.oasis.opendocument.text",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/488",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/488"
-    ],
-    "PID": "http://hdl.handle.net/11321/488",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Anna Raczy\u0144ska"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Super Cool License",
-        "http://www.google.com",
-        "ACA"
-    ],
-    "author": [
-        "Raczy\u0144ska, Anna"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/488;2018-06-19T11:18:13Z;hdl_11321_3;hdl_11321_4;literatura warsztatowa;Raczy\u0144ska, Anna;warsztaty polski politechnika;Korpus testowy w ramach warsztat\u00f3w CLARIN-PL;2018;corpus;http://hdl.handle.net/11321/488;pol;Super Cool License;http://www.google.com;ACA;text/plain; charset=utf-8;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.oasis.opendocument.text;text/plain;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;downloadable_files_count: 10;Anna Raczy\u0144ska",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4ce8ac2f-066c-51af-b611-332c35b3ae65",
-    "notes": [
-        "Korpus testowy w ramach warsztat\u00f3w CLARIN-PL"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/488"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "warsztaty polski politechnika"
-        }
-    ],
-    "title": [
-        "literatura warsztatowa"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4d043519-3927-5676-8d05-510a1de479d7.json b/oaitestdata/clarin-oai_dc/SET_1/json/4d043519-3927-5676-8d05-510a1de479d7.json
deleted file mode 100644
index 0c13fa5e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4d043519-3927-5676-8d05-510a1de479d7.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 55.8 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0583",
-    "MetadataAccess": [
-        "oai:ota:oucs:0583"
-    ],
-    "PublicationTimestamp": "1604-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1604"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Middleton, Thomas, d. 1627"
-    ],
-    "fulltext": "oai:ota:oucs:0583;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0583.xml;The blacke booke;Middleton, Thomas, d. 1627;1604;text_and_corpus_linguistics;Fiction -- England -- 17th century;Picaresque fiction -- England -- 17th century;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 55.8 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4d043519-3927-5676-8d05-510a1de479d7",
-    "oai_identifier": [
-        "oai:ota:oucs:0583"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- England -- th century"
-        },
-        {
-            "name": "Picaresque fiction -- England -- th century"
-        }
-    ],
-    "title": [
-        "The blacke booke"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0583.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4d25aa79-98ba-594a-ab11-6d3d394e8d9e.json b/oaitestdata/clarin-oai_dc/SET_1/json/4d25aa79-98ba-594a-ab11-6d3d394e8d9e.json
deleted file mode 100644
index 5dacc53f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4d25aa79-98ba-594a-ab11-6d3d394e8d9e.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=e45a22d8e6e211e6a2aa782bcb074135d600636f20ac4dc48908525783af830b",
-    "MetadataAccess": [
-        "e45a22d8e6e211e6a2aa782bcb074135d600636f20ac4dc48908525783af830b"
-    ],
-    "PublicationTimestamp": "2017-01-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "fulltext": "e45a22d8e6e211e6a2aa782bcb074135d600636f20ac4dc48908525783af830b;2018-11-15T16:40:28Z;corpus;corpus:text;LX-4WAnalogiesBR;The test set described in was used as the basis for the assessment of word embeddings. An example entry in this data set would read: \u00e2\u0080\u0098Berlin Germany Lisbon Portugal\u00e2\u0080\u0099. With these four words relations \u00e2\u0080\u0093 as in this example \u00e2\u0080\u0093 one can test semantic analogies by using any of the possible combinations of three of the four word vectors in one entry and testing whether or not the resulting vector is similar to the (fourth) word vector missing from the combination being tested. In the example above, the completed analogy should read: \u00e2\u0080\u0098Berlin is to Germany as Lisbon is to Portugal\u00e2\u0080\u0099. \nThe test set contains five types of semantic analogy: common capitals and countries, all capitals and countries, currency, cities and states, and family relations. Nine types of syntactic analogy are also represented: adjective to adverb, opposite, comparative, superlative, present participle, nationality (adjective), past tense, plural nouns and plural verbs. The test set contains a total of 8869 semantic and 10675 syntactic entries.\nFor the evaluation of the Portuguese word embeddings, the original English test set was translated into Brazilian Portuguese by skilled, native Portuguese-speaking\nlanguage experts. The resulting translations, LX-4WAnalogiesBR, and corresponding English terms are available at http://github.com/nlx-group.\n;2017-01-30",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4d25aa79-98ba-594a-ab11-6d3d394e8d9e",
-    "notes": [
-        "The test set described in was used as the basis for the assessment of word embeddings. An example entry in this data set would read: \u00e2\u0080\u0098Berlin Germany Lisbon Portugal\u00e2\u0080\u0099. With these four words relations \u00e2\u0080\u0093 as in this example \u00e2\u0080\u0093 one can test semantic analogies by using any of the possible combinations of three of the four word vectors in one entry and testing whether or not the resulting vector is similar to the (fourth) word vector missing from the combination being tested. In the example above, the completed analogy should read: \u00e2\u0080\u0098Berlin is to Germany as Lisbon is to Portugal\u00e2\u0080\u0099. \nThe test set contains five types of semantic analogy: common capitals and countries, all capitals and countries, currency, cities and states, and family relations. Nine types of syntactic analogy are also represented: adjective to adverb, opposite, comparative, superlative, present participle, nationality (adjective), past tense, plural nouns and plural verbs. The test set contains a total of 8869 semantic and 10675 syntactic entries.\nFor the evaluation of the Portuguese word embeddings, the original English test set was translated into Brazilian Portuguese by skilled, native Portuguese-speaking\nlanguage experts. The resulting translations, LX-4WAnalogiesBR, and corresponding English terms are available at http://github.com/nlx-group.\n"
-    ],
-    "oai_identifier": [
-        "e45a22d8e6e211e6a2aa782bcb074135d600636f20ac4dc48908525783af830b"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "LX-4WAnalogiesBR"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4d28b9f5-def1-5e6b-aa91-e4f275d3a10d.json b/oaitestdata/clarin-oai_dc/SET_1/json/4d28b9f5-def1-5e6b-aa91-e4f275d3a10d.json
deleted file mode 100644
index 001f2b91..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4d28b9f5-def1-5e6b-aa91-e4f275d3a10d.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Computer and Information Science, University of Ljubljana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 4",
-        "application/pdf",
-        "application/zip"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1115",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1115"
-    ],
-    "PID": "http://hdl.handle.net/11356/1115",
-    "PublicationTimestamp": "2017-05-28T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Faculty of Computer and Information Science, University of Ljubljana"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Robnik-\u0160ikonja, Marko",
-        "Kadunc, Klemen"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1115;2017-05-28T08:41:46Z;hdl_11356_1023;hdl_11356_1024;Opinion corpus of Slovene web commentaries KKS 1.001;Kadunc, Klemen;Robnik-\u0160ikonja, Marko;web commentaries;opinion corpus;sentiment analysis;The corpus of web commentaries with sentiment categorizations was developed as a part of BSc Thesis (Kadunc, 2016) and served for evaluation of the Slovene Sentiment Lexicon KSS \r\nhttp://hdl.handle.net/11356/1097. It contains web commentaries about different topics (business, politics, sport, and other) from 4 Slovene web portals (RtvSlo, 24ur, Finance, Reporter). The corpus is in XML format and available in two forms:\r\n- original corpus, containing 4,777 commentaries, 898 positive, 3,291 negative and 588 neutral commentaries.\r\n- balanced corpus, a subset of the original corpus, containing 1,740 commentaries, 580 of each type of sentiment (positive, negative and neutral).\r\n\r\nReferences:\r\nKlemen Kadunc (2016). Dolo\u010danje sentimenta slovenskim spletnim komentarjem s pomo\u010djo strojnega u\u010denja. Diplomsko delo. Univerza v Ljubljani, Fakulteta za ra\u010dunalni\u0161tvo in informatiko (in Slovene). http://eprints.fri.uni-lj.si/3317/\r\nKlemen Kadunc, Marko Robnik-\u0160ikonja (2016). Analiza mnenj s pomo\u010djo strojnega u\u010denja in slovenskega leksikona sentimenta. Conference on Language Technologies & Digital Humanities, Ljubljana (in Slovene). http://www.sdjt.si/wp/dogodki/konference/jtdh-2016/zbornik/;2017-05-28;corpus;http://hdl.handle.net/11356/1115;slv;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;PUB;text/plain; charset=utf-8;application/zip;application/zip;application/pdf;application/pdf;downloadable_files_count: 4;Faculty of Computer and Information Science, University of Ljubljana;http://lkm.fri.uni-lj.si/rmarko/repozitorij/opinionCorpus",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4d28b9f5-def1-5e6b-aa91-e4f275d3a10d",
-    "notes": [
-        "The corpus of web commentaries with sentiment categorizations was developed as a part of BSc Thesis (Kadunc, 2016) and served for evaluation of the Slovene Sentiment Lexicon KSS \r\nhttp://hdl.handle.net/11356/1097. It contains web commentaries about different topics (business, politics, sport, and other) from 4 Slovene web portals (RtvSlo, 24ur, Finance, Reporter). The corpus is in XML format and available in two forms:\r\n- original corpus, containing 4,777 commentaries, 898 positive, 3,291 negative and 588 neutral commentaries.\r\n- balanced corpus, a subset of the original corpus, containing 1,740 commentaries, 580 of each type of sentiment (positive, negative and neutral).\r\n\r\nReferences:\r\nKlemen Kadunc (2016). Dolo\u010danje sentimenta slovenskim spletnim komentarjem s pomo\u010djo strojnega u\u010denja. Diplomsko delo. Univerza v Ljubljani, Fakulteta za ra\u010dunalni\u0161tvo in informatiko (in Slovene). http://eprints.fri.uni-lj.si/3317/\r\nKlemen Kadunc, Marko Robnik-\u0160ikonja (2016). Analiza mnenj s pomo\u010djo strojnega u\u010denja in slovenskega leksikona sentimenta. Conference on Language Technologies & Digital Humanities, Ljubljana (in Slovene). http://www.sdjt.si/wp/dogodki/konference/jtdh-2016/zbornik/"
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1115"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "web commentaries"
-        },
-        {
-            "name": "opinion corpus"
-        },
-        {
-            "name": "sentiment analysis"
-        }
-    ],
-    "title": [
-        "Opinion corpus of Slovene web commentaries KKS 1.001"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4d372ba3-7ac4-5c5d-8350-e509ebc25c1f.json b/oaitestdata/clarin-oai_dc/SET_1/json/4d372ba3-7ac4-5c5d-8350-e509ebc25c1f.json
deleted file mode 100644
index 3d517e0c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4d372ba3-7ac4-5c5d-8350-e509ebc25c1f.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=fafce15ccf3011e1a404080027e73ea2bbc3f718cfbf452989472b8f2bd5f392",
-    "MetadataAccess": [
-        "fafce15ccf3011e1a404080027e73ea2bbc3f718cfbf452989472b8f2bd5f392"
-    ],
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "fafce15ccf3011e1a404080027e73ea2bbc3f718cfbf452989472b8f2bd5f392;2019-02-27T12:08:58Z;lexicalConceptualResource;lexicalConceptualResource:lexicon;Simple Portuguese Lexicon;The SIMPLE Portuguese Lexicon is constituted by 10.438 entries semantically encoded, accordingly to the parole common encoding standards. ;2015-12-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4d372ba3-7ac4-5c5d-8350-e509ebc25c1f",
-    "notes": [
-        "The SIMPLE Portuguese Lexicon is constituted by 10.438 entries semantically encoded, accordingly to the parole common encoding standards. "
-    ],
-    "oai_identifier": [
-        "fafce15ccf3011e1a404080027e73ea2bbc3f718cfbf452989472b8f2bd5f392"
-    ],
-    "oai_set": [
-        "lexicalConceptualResource",
-        "lexicalConceptualResource:lexicon"
-    ],
-    "state": "active",
-    "title": [
-        "Simple Portuguese Lexicon"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4d55fbc3-f376-5b5e-96d7-00e261cccf93.json b/oaitestdata/clarin-oai_dc/SET_1/json/4d55fbc3-f376-5b5e-96d7-00e261cccf93.json
deleted file mode 100644
index 9fc0e19a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4d55fbc3-f376-5b5e-96d7-00e261cccf93.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3968",
-    "MetadataAccess": [
-        "oai:ota:oucs:3968"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Home, John, 1722-1808."
-    ],
-    "fulltext": "oai:ota:oucs:3968;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3968.xml;Douglas: a tragedy. As it is acted at the Theatre-Royal in Covent-Garden.;Home, John, 1722-1808.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4d55fbc3-f376-5b5e-96d7-00e261cccf93",
-    "oai_identifier": [
-        "oai:ota:oucs:3968"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Douglas: a tragedy. As it is acted at the Theatre-Royal in Covent-Garden."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3968.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4d78f3b3-b4c0-5f15-be93-388f71886ad3.json b/oaitestdata/clarin-oai_dc/SET_1/json/4d78f3b3-b4c0-5f15-be93-388f71886ad3.json
deleted file mode 100644
index 02c71909..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4d78f3b3-b4c0-5f15-be93-388f71886ad3.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4234",
-    "MetadataAccess": [
-        "oai:ota:oucs:4234"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "More, Hannah, 1745-1833."
-    ],
-    "fulltext": "oai:ota:oucs:4234;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4234.xml;Turn the carpet; or, the two weavers: a new song in a dialogue between Dick and John.;More, Hannah, 1745-1833.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4d78f3b3-b4c0-5f15-be93-388f71886ad3",
-    "oai_identifier": [
-        "oai:ota:oucs:4234"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Turn the carpet; or, the two weavers: a new song in a dialogue between Dick and John."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4234.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4d86fa84-66fb-57ed-8951-033b9d58d0ee.json b/oaitestdata/clarin-oai_dc/SET_1/json/4d86fa84-66fb-57ed-8951-033b9d58d0ee.json
deleted file mode 100644
index 6d542b6d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4d86fa84-66fb-57ed-8951-033b9d58d0ee.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Academia"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 3",
-        "application/pdf"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2838",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2838"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2838",
-    "PublicationTimestamp": "2018-07-10T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Academia"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Slav\u00ed\u010dkov\u00e1, Eleonora"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2838;2018-07-10T14:31:47Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Retrograde Morphemic Dictionary of Czech;Slav\u00ed\u010dkov\u00e1, Eleonora;morphemes;morphology;The data contains the morphemic dictionary scanned in the PDF format. It is divided into 3 parts:\r\nintroductions.pdf - pp. 11-102\r\nmain_dictionary.pdf - pp. 113-506\r\nappendices.pdf - pp. 509-645;2018-07-10;lexicalConceptualResource;http://hdl.handle.net/11234/1-2838;ces;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/pdf;application/pdf;application/pdf;text/plain; charset=utf-8;downloadable_files_count: 3;Academia",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4d86fa84-66fb-57ed-8951-033b9d58d0ee",
-    "notes": [
-        "The data contains the morphemic dictionary scanned in the PDF format. It is divided into 3 parts:\r\nintroductions.pdf - pp. 11-102\r\nmain_dictionary.pdf - pp. 113-506\r\nappendices.pdf - pp. 509-645"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2838"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphemes"
-        },
-        {
-            "name": "morphology"
-        }
-    ],
-    "title": [
-        "Retrograde Morphemic Dictionary of Czech"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4d8db6f3-de02-55ef-b391-941b53c39a46.json b/oaitestdata/clarin-oai_dc/SET_1/json/4d8db6f3-de02-55ef-b391-941b53c39a46.json
deleted file mode 100644
index 6270a0e1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4d8db6f3-de02-55ef-b391-941b53c39a46.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Howard-Hill, T.H. (Trevor Howard)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 98 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0098",
-    "MetadataAccess": [
-        "oai:ota:oucs:0098"
-    ],
-    "PublicationTimestamp": "1613-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1613"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Middleton, Thomas, d. 1627"
-    ],
-    "fulltext": "oai:ota:oucs:0098;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0098.xml;The witch / Thomas Middleton;Middleton, Thomas, d. 1627;1613-1316;text_and_corpus_linguistics;English drama -- 17th century;eng;Oxford Text Archive, University of Oxford;Howard-Hill, T.H. (Trevor Howard);(1 file : ca. 98 KB);Text;Plays;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4d8db6f3-de02-55ef-b391-941b53c39a46",
-    "oai_identifier": [
-        "oai:ota:oucs:0098"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- th century"
-        }
-    ],
-    "title": [
-        "The witch / Thomas Middleton"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0098.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4d9b28be-b7c4-5379-9e0a-9e413da59425.json b/oaitestdata/clarin-oai_dc/SET_1/json/4d9b28be-b7c4-5379-9e0a-9e413da59425.json
deleted file mode 100644
index d1ea0ffd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4d9b28be-b7c4-5379-9e0a-9e413da59425.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Beczkowska"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 4",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/67",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/67"
-    ],
-    "PID": "http://hdl.handle.net/11321/67",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Beczkowska"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Beczkowska, Beczkowska"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/67;2015-04-14T12:53:48Z;hdl_11321_3;hdl_11321_4;MWE Beczkowska;Beczkowska, Beczkowska;Beczkowska;2015-04-08;corpus;http://hdl.handle.net/11321/67;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;application/zip;text/plain; charset=utf-8;downloadable_files_count: 4;Beczkowska",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4d9b28be-b7c4-5379-9e0a-9e413da59425",
-    "notes": [
-        "Beczkowska"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/67"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Beczkowska"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4ddea0e1-cefd-5c40-8c99-4df7ac66a14c.json b/oaitestdata/clarin-oai_dc/SET_1/json/4ddea0e1-cefd-5c40-8c99-4df7ac66a14c.json
deleted file mode 100644
index 9e411abe..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4ddea0e1-cefd-5c40-8c99-4df7ac66a14c.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Barnard, David T."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(2 files : ca. 445, 3 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1316",
-    "MetadataAccess": [
-        "oai:ota:oucs:1316"
-    ],
-    "PublicationTimestamp": "1859-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1859"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Tennyson, Alfred Tennyson, Baron, 1809-1892"
-    ],
-    "fulltext": "oai:ota:oucs:1316;2018-03-07T11:52:24Z;http://ota.ox.ac.uk/headers/1316.xml;Idylls of the King / Alfred, Lord Tennyson;Tennyson, Alfred Tennyson, Baron, 1809-1892;1859;text_and_corpus_linguistics;English poetry -- 19th century;eng;Oxford Text Archive, University of Oxford;Barnard, David T.;text/plain;(2 files : ca. 445, 3 KB);Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4ddea0e1-cefd-5c40-8c99-4df7ac66a14c",
-    "oai_identifier": [
-        "oai:ota:oucs:1316"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English poetry -- th century"
-        }
-    ],
-    "title": [
-        "Idylls of the King / Alfred, Lord Tennyson"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1316.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4de0d785-ddfd-57b0-adcd-14e7fc622727.json b/oaitestdata/clarin-oai_dc/SET_1/json/4de0d785-ddfd-57b0-adcd-14e7fc622727.json
deleted file mode 100644
index 6a30f8da..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4de0d785-ddfd-57b0-adcd-14e7fc622727.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3271",
-    "MetadataAccess": [
-        "oai:ota:oucs:3271"
-    ],
-    "PublicationTimestamp": "1919-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1919"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Kipling, Rudyard, 1865-1936"
-    ],
-    "fulltext": "oai:ota:oucs:3271;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3271.xml;The Eyes of Asia;Kipling, Rudyard, 1865-1936;not after: 1919;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4de0d785-ddfd-57b0-adcd-14e7fc622727",
-    "oai_identifier": [
-        "oai:ota:oucs:3271"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The Eyes of Asia"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3271.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4e016b00-50b6-5cfe-a00c-38f52db59e6c.json b/oaitestdata/clarin-oai_dc/SET_1/json/4e016b00-50b6-5cfe-a00c-38f52db59e6c.json
deleted file mode 100644
index 659cd56c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4e016b00-50b6-5cfe-a00c-38f52db59e6c.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/32",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/32"
-    ],
-    "PID": "http://hdl.handle.net/10794/32",
-    "PublicationTimestamp": "2012-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/32;2017-10-27T14:29:25Z;hdl_10794_1;hdl_10794_2;Parole;Parole;n/a, n/a;Swedish;PAROLE;The Swedish PAROLE Lexicon - A language technology resource with access to syntactic information.;Svenskt PAROLE-lexikon - En spr\u00e5kteknologisk resurs med syntaktisk information.;2012-05-30;lexicalConceptualResource;http://hdl.handle.net/10794/32;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/gzip;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/parolelex",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4e016b00-50b6-5cfe-a00c-38f52db59e6c",
-    "notes": [
-        "The Swedish PAROLE Lexicon - A language technology resource with access to syntactic information.",
-        "Svenskt PAROLE-lexikon - En spr\u00e5kteknologisk resurs med syntaktisk information."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/32"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "PAROLE"
-        }
-    ],
-    "title": [
-        "Parole",
-        "Parole"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4e1748e5-9080-5338-a7b7-7d300e2d278b.json b/oaitestdata/clarin-oai_dc/SET_1/json/4e1748e5-9080-5338-a7b7-7d300e2d278b.json
deleted file mode 100644
index 1e0edd40..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4e1748e5-9080-5338-a7b7-7d300e2d278b.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "University of West Bohemia",
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "text/html",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2375",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2375"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2375",
-    "PublicationTimestamp": "2017-11-02T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "University of West Bohemia",
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Haji\u010d, Jan",
-        "Mikulov\u00e1, Marie",
-        "Peterek, Nino",
-        "Romportl, Jan",
-        "Spousta, Miroslav",
-        "Gr\u016fber, Martin",
-        "Pajas, Petr",
-        "Ircing, Pavel",
-        "Leg\u00e1t, Milan"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2375;2017-11-09T14:20:29Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Prague DaTabase of Spoken Czech 1.0;Haji\u010d, Jan;Pajas, Petr;Ircing, Pavel;Romportl, Jan;Peterek, Nino;Spousta, Miroslav;Mikulov\u00e1, Marie;Gr\u016fber, Martin;Leg\u00e1t, Milan;spoken corpus;speech recognition;speech reconstruction;PDTSC 1.0 is a multi-purpose corpus of spoken language. 768,888 tokens, 73,374 sentences and 7,324 minutes of spontaneous dialog speech have been recorded, transcribed and edited in several interlinked layers: audio recordings, automatic and manual transcription and manually reconstructed text.\r\n\r\nPDTSC 1.0 is a delayed release of data annotated in 2012. It is an update of Prague Dependency Treebank of Spoken Language (PDTSL) 0.5 (published in 2009). In 2017, Prague Dependency Treebank of Spoken Czech (PDTSC) 2.0 was published as an update of PDTSC 1.0.;2017-11-02;corpus;http://hdl.handle.net/11234/1-2375;ces;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;text/html;application/zip;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);University of West Bohemia;https://ufal.mff.cuni.cz/pdtsc1.0/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4e1748e5-9080-5338-a7b7-7d300e2d278b",
-    "notes": [
-        "PDTSC 1.0 is a multi-purpose corpus of spoken language. 768,888 tokens, 73,374 sentences and 7,324 minutes of spontaneous dialog speech have been recorded, transcribed and edited in several interlinked layers: audio recordings, automatic and manual transcription and manually reconstructed text.\r\n\r\nPDTSC 1.0 is a delayed release of data annotated in 2012. It is an update of Prague Dependency Treebank of Spoken Language (PDTSL) 0.5 (published in 2009). In 2017, Prague Dependency Treebank of Spoken Czech (PDTSC) 2.0 was published as an update of PDTSC 1.0."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2375"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "spoken corpus"
-        },
-        {
-            "name": "speech recognition"
-        },
-        {
-            "name": "speech reconstruction"
-        }
-    ],
-    "title": [
-        "Prague DaTabase of Spoken Czech 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4e38df5a-7b9f-5ad4-b258-46fc05cca366.json b/oaitestdata/clarin-oai_dc/SET_1/json/4e38df5a-7b9f-5ad4-b258-46fc05cca366.json
deleted file mode 100644
index 119c7183..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4e38df5a-7b9f-5ad4-b258-46fc05cca366.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technolgy"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/24",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/24"
-    ],
-    "PID": "http://hdl.handle.net/11321/24",
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technolgy"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "K\u0119dzia, Pawe\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/24;2016-01-21T14:33:43Z;hdl_11321_3;hdl_11321_4;RL-Button;K\u0119dzia, Pawe\u0142;W kontek\u015bcie rzutowania leksykalnych sieci semantycznych, idea algorytmu Relaxation Labeling (RL) zaproponowanego przez autor\u00f3w w [1], polega na okre\u015blaniu wag potencjalnych powi\u0105za\u0144 pomi\u0119dzy par\u0105 synset\u00f3w, uwzgl\u0119dniaj\u0105c zadane wcze\u015bniej ograniczenia. Waga takiego powi\u0105zania jest odpowiednio modyfikowana: mo\u017ce by\u0107 zwi\u0119kszana b\u0105d\u017a zmniejszana, jednak suma wag dla potencjalnych odpowiednik\u00f3w danego sysnetu zawsze musi wynosi\u0107 1. Podstawowa wersja agorytmu zosta\u0142a rozszerzona o dodatkowe \u017ar\u00f3d\u0142o informacji, nazwane niepodwa\u017calnymi powi\u0105zaniami. Algorytm uwzgl\u0119dnia wprowadzone r\u0119cznie powi\u0105zania, traktuj\u0105c je jako powi\u0105zania, kt\u00f3re nie mog\u0105 by\u0107 zmodyfikowane.;2014;toolService;http://hdl.handle.net/11321/24;pol;downloadable_files_count: 0;Wroc\u0142aw University of Technolgy;http://nlp.pwr.wroc.pl/pl/narzedzia-i-zasoby/rl-button",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4e38df5a-7b9f-5ad4-b258-46fc05cca366",
-    "notes": [
-        "W kontek\u015bcie rzutowania leksykalnych sieci semantycznych, idea algorytmu Relaxation Labeling (RL) zaproponowanego przez autor\u00f3w w [1], polega na okre\u015blaniu wag potencjalnych powi\u0105za\u0144 pomi\u0119dzy par\u0105 synset\u00f3w, uwzgl\u0119dniaj\u0105c zadane wcze\u015bniej ograniczenia. Waga takiego powi\u0105zania jest odpowiednio modyfikowana: mo\u017ce by\u0107 zwi\u0119kszana b\u0105d\u017a zmniejszana, jednak suma wag dla potencjalnych odpowiednik\u00f3w danego sysnetu zawsze musi wynosi\u0107 1. Podstawowa wersja agorytmu zosta\u0142a rozszerzona o dodatkowe \u017ar\u00f3d\u0142o informacji, nazwane niepodwa\u017calnymi powi\u0105zaniami. Algorytm uwzgl\u0119dnia wprowadzone r\u0119cznie powi\u0105zania, traktuj\u0105c je jako powi\u0105zania, kt\u00f3re nie mog\u0105 by\u0107 zmodyfikowane."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/24"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "RL-Button"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4e497366-8672-5f1f-8c68-a736ee219610.json b/oaitestdata/clarin-oai_dc/SET_1/json/4e497366-8672-5f1f-8c68-a736ee219610.json
deleted file mode 100644
index c7ad3cc9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4e497366-8672-5f1f-8c68-a736ee219610.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Big Room"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 95",
-        "text/plain"
-    ],
-    "Language": [],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/519",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/519"
-    ],
-    "PID": "http://hdl.handle.net/11321/519",
-    "PublicationTimestamp": "2018-07-13T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Big Room"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Super Cool License",
-        "http://www.google.com",
-        "ACA"
-    ],
-    "author": [
-        "Workshop 1"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/519;2018-07-13T13:51:23Z;hdl_11321_3;hdl_11321_4;Corpus People;Workshop 1;Politics;Corpus People;2018-07-13;corpus;http://hdl.handle.net/11321/519;crk;Super Cool License;http://www.google.com;ACA;text/plain; charset=utf-8;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;downloadable_files_count: 95;Big Room",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4e497366-8672-5f1f-8c68-a736ee219610",
-    "notes": [
-        "Corpus People"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/519"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Politics"
-        }
-    ],
-    "title": [
-        "Corpus People"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4e53ca1d-aac5-504c-8ebe-65fe11e9befa.json b/oaitestdata/clarin-oai_dc/SET_1/json/4e53ca1d-aac5-504c-8ebe-65fe11e9befa.json
deleted file mode 100644
index f40a0420..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4e53ca1d-aac5-504c-8ebe-65fe11e9befa.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "TALG Research Group (University of Vigo)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English",
-        "Galician"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-619",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-619"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-619",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "TALG Research Group (University of Vigo)"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-619;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Dicionario CLUVI ingl\u00e9s-galego;Corpus-based English-Galician bilingual dictionary;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-619;eng;glg;downloadable_files_count: 0;Spain;TALG Research Group (University of Vigo);http://sli.uvigo.es/dicionario",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4e53ca1d-aac5-504c-8ebe-65fe11e9befa",
-    "notes": [
-        "Corpus-based English-Galician bilingual dictionary"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-619"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Dicionario CLUVI ingl\u00e9s-galego"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4e55a7bc-ed0f-5393-a6ed-76a4350051b0.json b/oaitestdata/clarin-oai_dc/SET_1/json/4e55a7bc-ed0f-5393-a6ed-76a4350051b0.json
deleted file mode 100644
index a7d1f88f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4e55a7bc-ed0f-5393-a6ed-76a4350051b0.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "application/pdf",
-        "downloadable_files_count: 2"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-60D6-1",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-60D6-1"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0022-60D6-1",
-    "PublicationTimestamp": "2011-12-20T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11858/00-097C-0000-0022-6133-9"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0)",
-        "http://creativecommons.org/licenses/by-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Majli\u0161, Martin"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-60D6-1;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;W2C \u2013 Web to Corpus \u2013 tool;Majli\u0161, Martin;web data;wikipedia;corpus creation;A tool used to build multilingual corpora from wikipedia. Download the web pages, convert them to plain text, identify language, etc.\r\n\r\nA set of 120 corpora collected using this tool is available at https://ufal-point.mff.cuni.cz/xmlui/handle/11858/00-097C-0000-0022-6133-9;2011-12-20;toolService;http://hdl.handle.net/11858/00-097C-0000-0022-60D6-1;http://hdl.handle.net/11858/00-097C-0000-0022-6133-9;Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0);http://creativecommons.org/licenses/by-sa/3.0/;PUB;application/x-gzip;application/pdf;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4e55a7bc-ed0f-5393-a6ed-76a4350051b0",
-    "notes": [
-        "A tool used to build multilingual corpora from wikipedia. Download the web pages, convert them to plain text, identify language, etc.\r\n\r\nA set of 120 corpora collected using this tool is available at https://ufal-point.mff.cuni.cz/xmlui/handle/11858/00-097C-0000-0022-6133-9"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-60D6-1"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "web data"
-        },
-        {
-            "name": "wikipedia"
-        },
-        {
-            "name": "corpus creation"
-        }
-    ],
-    "title": [
-        "W2C \u2013 Web to Corpus \u2013 tool"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4e697477-ac6b-52fd-a931-0a6b4e3c1826.json b/oaitestdata/clarin-oai_dc/SET_1/json/4e697477-ac6b-52fd-a931-0a6b4e3c1826.json
deleted file mode 100644
index ea2845fd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4e697477-ac6b-52fd-a931-0a6b4e3c1826.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4794",
-    "MetadataAccess": [
-        "oai:ota:oucs:4794"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Doddridge, Philip, 1702-1751."
-    ],
-    "fulltext": "oai:ota:oucs:4794;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4794.xml;Hymns founded on various texts in the holy scriptures: By the late Reverend Philip Doddridge, D.D. Published from the author's manuscript by Job Orton.;Doddridge, Philip, 1702-1751.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4e697477-ac6b-52fd-a931-0a6b4e3c1826",
-    "oai_identifier": [
-        "oai:ota:oucs:4794"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Hymns founded on various texts in the holy scriptures: By the late Reverend Philip Doddridge, D.D. Published from the author's manuscript by Job Orton."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4794.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4e6bab25-82df-5e92-b7ec-6be8ed9487a5.json b/oaitestdata/clarin-oai_dc/SET_1/json/4e6bab25-82df-5e92-b7ec-6be8ed9487a5.json
deleted file mode 100644
index 5e731050..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4e6bab25-82df-5e92-b7ec-6be8ed9487a5.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=23452ca8a35a11e1a404080027e73ea2d0884e62ca8f466fa0f6be6e1e397cd4",
-    "MetadataAccess": [
-        "23452ca8a35a11e1a404080027e73ea2d0884e62ca8f466fa0f6be6e1e397cd4"
-    ],
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "23452ca8a35a11e1a404080027e73ea2d0884e62ca8f466fa0f6be6e1e397cd4;2019-02-27T12:08:52Z;lexicalConceptualResource;lexicalConceptualResource:lexicon;Multifunctional Computational Lexicon of Contemporary Portuguese;The resource consists of a Portuguese frequency lexicon based on a 16 million words corpus of written and spoken texts from different genres. The lexicon contains 26.443 entries (lemma) and 140 ;2015-12-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4e6bab25-82df-5e92-b7ec-6be8ed9487a5",
-    "notes": [
-        "The resource consists of a Portuguese frequency lexicon based on a 16 million words corpus of written and spoken texts from different genres. The lexicon contains 26.443 entries (lemma) and 140 "
-    ],
-    "oai_identifier": [
-        "23452ca8a35a11e1a404080027e73ea2d0884e62ca8f466fa0f6be6e1e397cd4"
-    ],
-    "oai_set": [
-        "lexicalConceptualResource",
-        "lexicalConceptualResource:lexicon"
-    ],
-    "state": "active",
-    "title": [
-        "Multifunctional Computational Lexicon of Contemporary Portuguese"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4e751b53-9bee-551f-a610-0d9fc1c57ed4.json b/oaitestdata/clarin-oai_dc/SET_1/json/4e751b53-9bee-551f-a610-0d9fc1c57ed4.json
deleted file mode 100644
index 991799b8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4e751b53-9bee-551f-a610-0d9fc1c57ed4.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Humanities and Social Sciences, University of Zagreb"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Croatian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1067",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1067"
-    ],
-    "PID": "http://hdl.handle.net/11356/1067",
-    "PublicationTimestamp": "2016-06-23T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Faculty of Humanities and Social Sciences, University of Zagreb"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/324414",
-        "http://hdl.handle.net/11356/1056",
-        "http://hdl.handle.net/11356/1072"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "GNU General Public Licence, version 3",
-        "http://opensource.org/licenses/GPL-3.0",
-        "PUB"
-    ],
-    "author": [
-        "Ljube\u0161i\u0107, Nikola"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1067;2017-06-27T18:10:32Z;hdl_11356_1023;hdl_11356_1024;Inflectional lexicon hrLex 1.1;Ljube\u0161i\u0107, Nikola;lexicon;morphology;inflection;hrLex is a large inflectional lexicon of Croatian language where each entry consists of a (wordform, lemma, MSD, frequency, per-million frequency) 5-tuple. The (wordform, lemma, MSD) triple frequencies are calculated on the hrWaC v2.2 corpus. The MSD tagset follows the MULTEXT-East V5 tagset for Croatian available at http://nl.ijs.si/ME/V5/msd/html/msd-hr.html.;2016-06-23;lexicalConceptualResource;http://hdl.handle.net/11356/1067;hrv;info:eu-repo/grantAgreement/EC/FP7/324414;http://hdl.handle.net/11356/1056;http://hdl.handle.net/11356/1072;GNU General Public Licence, version 3;http://opensource.org/licenses/GPL-3.0;PUB;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Faculty of Humanities and Social Sciences, University of Zagreb;http://nlp.ffzg.hr/resources/lexicons/hrlex/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4e751b53-9bee-551f-a610-0d9fc1c57ed4",
-    "notes": [
-        "hrLex is a large inflectional lexicon of Croatian language where each entry consists of a (wordform, lemma, MSD, frequency, per-million frequency) 5-tuple. The (wordform, lemma, MSD) triple frequencies are calculated on the hrWaC v2.2 corpus. The MSD tagset follows the MULTEXT-East V5 tagset for Croatian available at http://nl.ijs.si/ME/V5/msd/html/msd-hr.html."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1067"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "lexicon"
-        },
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "inflection"
-        }
-    ],
-    "title": [
-        "Inflectional lexicon hrLex 1.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4e81805e-0f95-5f01-87bb-a03a0c491b37.json b/oaitestdata/clarin-oai_dc/SET_1/json/4e81805e-0f95-5f01-87bb-a03a0c491b37.json
deleted file mode 100644
index df13f8ab..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4e81805e-0f95-5f01-87bb-a03a0c491b37.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Research Institute for Artificial Intelligence, Romanian Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English",
-        "Romanian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1299",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1299"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1299",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Research Institute for Artificial Intelligence, Romanian Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Romania"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Tufi\u015f, Dan",
-        "Ceau\u015fu, Alexandru"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1299;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;MEBA word aligner;Tufi\u015f, Dan;Ceau\u015fu, Alexandru;word aligner;MEBA is a lexical aligner, implemented in C#, based on an iterative algorithm that uses pre-processing steps: sentence alignment ([[http://www.clarin.eu/tools/sal-sentence-aligner|SAL]]), tokenization, POS-tagging and lemmatization (through [[http://www.clarin.eu/tools/ttl-tokenizing-tagging-and-lemmatizing-free-running-texts|TTL]], sentence chunking. Similar to YAWA aligner, MEBA generates the links step by step, beginning with the most probable (anchor links). The links to be\r\nadded at any later step are supported or restricted by the links created in the previous iterations. The aligner has different weights and different significance thresholds on each feature and iteration. Each of the iterations can be configured to align different categories of tokens (named entities, dates and numbers, content words, functional words, punctuation) in decreasing order of statistical evidence.\r\nMEBA has an individual F-measure of 81.71% and it is currently integrated in the platform [[http://www.clarin.eu/tools/cowal-combined-word-aligner|COWAL]].\r\nMore detailed descriptions are available in [[http://www.racai.ro/~tufis/papers|the following papers]]: \r\n  -- Dan Tufi\u015f (2007). Exploiting Aligned Parallel Corpora in Multilingual Studies and Applications. In Toru Ishida, Susan R. Fussell, and Piek T.J.M. Vossen (eds.), Intercultural Collaboration. First International Workshop (IWIC 2007), volume 4568 of Lecture Notes in Computer Science, pp. 103-117. Springer-Verlag, August 2007. ISBN 978-3-540-73999-9. \r\n  -- -- Dan Tufi\u015f, Radu Ion, Alexandru Ceau\u015fu, and Dan \u015etef\u0103nescu (2006). Improved Lexical Alignment by Combining Multiple Reified Alignments. In Toru Ishida, Susan R. Fussell, and Piek T.J.M. Vossen (eds.), Proceedings of the 11th Conference EACL2006, pp. 153-160, Trento, Italy, April 2006. Association for Computational Linguistics. ISBN 1-9324-32-61-2.\r\n  -- Dan  Tufi\u015f, Radu Ion, Alexandru Ceau\u015fu, and Dan \u015etef\u0103nescu (2005). Combined Aligners. In Proceedings of the ACL Workshop on Building and Using Parallel Texts: Data-Driven Machine Translation and Beyond, pp. 107-110, Ann Arbor, USA, June 2005. Association for Computational Linguistics. ISBN 978-973-703-208-9.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1299;eng;ron;downloadable_files_count: 0;Romania;Research Institute for Artificial Intelligence, Romanian Academy of Sciences",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4e81805e-0f95-5f01-87bb-a03a0c491b37",
-    "notes": [
-        "MEBA is a lexical aligner, implemented in C#, based on an iterative algorithm that uses pre-processing steps: sentence alignment ([[http://www.clarin.eu/tools/sal-sentence-aligner|SAL]]), tokenization, POS-tagging and lemmatization (through [[http://www.clarin.eu/tools/ttl-tokenizing-tagging-and-lemmatizing-free-running-texts|TTL]], sentence chunking. Similar to YAWA aligner, MEBA generates the links step by step, beginning with the most probable (anchor links). The links to be\r\nadded at any later step are supported or restricted by the links created in the previous iterations. The aligner has different weights and different significance thresholds on each feature and iteration. Each of the iterations can be configured to align different categories of tokens (named entities, dates and numbers, content words, functional words, punctuation) in decreasing order of statistical evidence.\r\nMEBA has an individual F-measure of 81.71% and it is currently integrated in the platform [[http://www.clarin.eu/tools/cowal-combined-word-aligner|COWAL]].\r\nMore detailed descriptions are available in [[http://www.racai.ro/~tufis/papers|the following papers]]: \r\n  -- Dan Tufi\u015f (2007). Exploiting Aligned Parallel Corpora in Multilingual Studies and Applications. In Toru Ishida, Susan R. Fussell, and Piek T.J.M. Vossen (eds.), Intercultural Collaboration. First International Workshop (IWIC 2007), volume 4568 of Lecture Notes in Computer Science, pp. 103-117. Springer-Verlag, August 2007. ISBN 978-3-540-73999-9. \r\n  -- -- Dan Tufi\u015f, Radu Ion, Alexandru Ceau\u015fu, and Dan \u015etef\u0103nescu (2006). Improved Lexical Alignment by Combining Multiple Reified Alignments. In Toru Ishida, Susan R. Fussell, and Piek T.J.M. Vossen (eds.), Proceedings of the 11th Conference EACL2006, pp. 153-160, Trento, Italy, April 2006. Association for Computational Linguistics. ISBN 1-9324-32-61-2.\r\n  -- Dan  Tufi\u015f, Radu Ion, Alexandru Ceau\u015fu, and Dan \u015etef\u0103nescu (2005). Combined Aligners. In Proceedings of the ACL Workshop on Building and Using Parallel Texts: Data-Driven Machine Translation and Beyond, pp. 107-110, Ann Arbor, USA, June 2005. Association for Computational Linguistics. ISBN 978-973-703-208-9."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1299"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "word aligner"
-        }
-    ],
-    "title": [
-        "MEBA word aligner"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4e95251c-21e9-581a-a261-9eaa2d92f29d.json b/oaitestdata/clarin-oai_dc/SET_1/json/4e95251c-21e9-581a-a261-9eaa2d92f29d.json
deleted file mode 100644
index ca9720ff..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4e95251c-21e9-581a-a261-9eaa2d92f29d.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3373",
-    "MetadataAccess": [
-        "oai:ota:oucs:3373"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pratt, Mr. (Samuel Jackson), 1749-1814."
-    ],
-    "fulltext": "oai:ota:oucs:3373;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3373.xml;Emma Corbett: or, the miseries of civil war. Founded on some recent circumstances which happened in America. By the author of Liberal opinions, Pupil of pleasure, Shenstone Green, &c. ... [pt.3];Pratt, Mr. (Samuel Jackson), 1749-1814.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4e95251c-21e9-581a-a261-9eaa2d92f29d",
-    "oai_identifier": [
-        "oai:ota:oucs:3373"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Emma Corbett: or, the miseries of civil war. Founded on some recent circumstances which happened in America. By the author of Liberal opinions, Pupil of pleasure, Shenstone Green, &c. ... [pt.3]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3373.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4e9bdb7e-7367-5e33-af0c-99ed5ad70491.json b/oaitestdata/clarin-oai_dc/SET_1/json/4e9bdb7e-7367-5e33-af0c-99ed5ad70491.json
deleted file mode 100644
index 899bbeb9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4e9bdb7e-7367-5e33-af0c-99ed5ad70491.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3327",
-    "MetadataAccess": [
-        "oai:ota:oucs:3327"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Kemble, John Philip, 1757-1823."
-    ],
-    "fulltext": "oai:ota:oucs:3327;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3327.xml;The female officer: or the humours of the army, a comedy. Altered from Shadwell.;Kemble, John Philip, 1757-1823.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4e9bdb7e-7367-5e33-af0c-99ed5ad70491",
-    "oai_identifier": [
-        "oai:ota:oucs:3327"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The female officer: or the humours of the army, a comedy. Altered from Shadwell."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3327.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4eb7da7e-fb95-55bb-9804-b810d320323f.json b/oaitestdata/clarin-oai_dc/SET_1/json/4eb7da7e-fb95-55bb-9804-b810d320323f.json
deleted file mode 100644
index 56f3d169..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4eb7da7e-fb95-55bb-9804-b810d320323f.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3258",
-    "MetadataAccess": [
-        "oai:ota:oucs:3258"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hawthorne, Nathaniel, 1804-1864"
-    ],
-    "fulltext": "oai:ota:oucs:3258;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3258.xml;The scarlet letter;Hawthorne, Nathaniel, 1804-1864;default: 1976-01-01;text_and_corpus_linguistics;Novels -- United States -- 19th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4eb7da7e-fb95-55bb-9804-b810d320323f",
-    "oai_identifier": [
-        "oai:ota:oucs:3258"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Novels -- United States -- th century"
-        }
-    ],
-    "title": [
-        "The scarlet letter"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3258.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4ed70240-e8f9-5df4-9c3b-1a7f722ce07d.json b/oaitestdata/clarin-oai_dc/SET_1/json/4ed70240-e8f9-5df4-9c3b-1a7f722ce07d.json
deleted file mode 100644
index 01a8231b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4ed70240-e8f9-5df4-9c3b-1a7f722ce07d.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "School of Computing, University of Dundee"
-    ],
-    "Contributor": [
-        "Reed, Chris",
-        "Rowe, Glenn"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1170",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1170"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1170",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "School of Computing, University of Dundee"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1170;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Araucaria;Reed, Chris;Rowe, Glenn;argument analyzer;Araucaria is a software tool for analysing arguments. It aids a user in reconstructing and diagramming an argument using a simple point-and-click interface. The software also supports argumentation schemes, and provides a user-customisable set of schemes with which to analyse arguments. Written in Java, released under the GNU General Public License.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1170;downloadable_files_count: 0;United Kingdom;School of Computing, University of Dundee;http://araucaria.computing.dundee.ac.uk/doku.php",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4ed70240-e8f9-5df4-9c3b-1a7f722ce07d",
-    "notes": [
-        "Araucaria is a software tool for analysing arguments. It aids a user in reconstructing and diagramming an argument using a simple point-and-click interface. The software also supports argumentation schemes, and provides a user-customisable set of schemes with which to analyse arguments. Written in Java, released under the GNU General Public License."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1170"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "argument analyzer"
-        }
-    ],
-    "title": [
-        "Araucaria"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4ede2d2a-979e-5f6f-b8d1-314b8414249f.json b/oaitestdata/clarin-oai_dc/SET_1/json/4ede2d2a-979e-5f6f-b8d1-314b8414249f.json
deleted file mode 100644
index a673e0a1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4ede2d2a-979e-5f6f-b8d1-314b8414249f.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2722",
-    "MetadataAccess": [
-        "oai:ota:oucs:2722"
-    ],
-    "PublicationTimestamp": "1721-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1721"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2722;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2722.xml;A letter of advice to a young poet;Swift, Jonathan, 1667-1745;1721;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4ede2d2a-979e-5f6f-b8d1-314b8414249f",
-    "oai_identifier": [
-        "oai:ota:oucs:2722"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A letter of advice to a young poet"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2722.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4edec9ba-2342-5bae-a075-05814de3edf9.json b/oaitestdata/clarin-oai_dc/SET_1/json/4edec9ba-2342-5bae-a075-05814de3edf9.json
deleted file mode 100644
index 2752db84..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4edec9ba-2342-5bae-a075-05814de3edf9.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "text/xml",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/108",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/108"
-    ],
-    "PID": "http://hdl.handle.net/11509/108",
-    "PublicationTimestamp": "2015-10-17T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "The Divvun group at UiT The Arctic University of Norway",
-        "Giellatekno - Saami Language Technology, UiT The Arctic University of Norway"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/108;2016-09-06T12:53:01Z;hdl_11509_1;hdl_11509_2;Kven N-grams;Giellatekno - Saami Language Technology, UiT The Arctic University of Norway;The Divvun group at UiT The Arctic University of Norway;Kven;Ngram;1-gram;2-gram;3-gram;Language Model;The Kven N-gram data set is work done by the Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language community. In particular, Ciprian-Virgil Gerstenberger compiled the data set from the entire SIKOR Kven corpus version 2015-08-30. The length of the N-grams ranges from unigrams (single words) to tri-grams (25961 unigrams, 78497 bigrams, 27690 trigrams). Only N-grams within sentences have been counted. The data format follows the ARPA backoff N-gram models and has been generated using SRILM, the SRI Language Modeling Toolkit (http://www.speech.sri.com/projects/srilm/). Since the N-grams have been derived automatically, they may contain wrong values. In case you find any errors the creators would appreciate your feedback sent to giellatekno@uit.no and feedback@divvun.no. Please note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata).;2015-10-17;corpus;http://hdl.handle.net/11509/108;fkv;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;application/zip;text/plain; charset=utf-8;text/xml;downloadable_files_count: 1;Giellatekno - Saami Language Technology;http://giellatekno.uit.no/index.eng.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4edec9ba-2342-5bae-a075-05814de3edf9",
-    "notes": [
-        "The Kven N-gram data set is work done by the Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language community. In particular, Ciprian-Virgil Gerstenberger compiled the data set from the entire SIKOR Kven corpus version 2015-08-30. The length of the N-grams ranges from unigrams (single words) to tri-grams (25961 unigrams, 78497 bigrams, 27690 trigrams). Only N-grams within sentences have been counted. The data format follows the ARPA backoff N-gram models and has been generated using SRILM, the SRI Language Modeling Toolkit (http://www.speech.sri.com/projects/srilm/). Since the N-grams have been derived automatically, they may contain wrong values. In case you find any errors the creators would appreciate your feedback sent to giellatekno@uit.no and feedback@divvun.no. Please note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata)."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/108"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Kven"
-        },
-        {
-            "name": "Ngram"
-        },
-        {
-            "name": "-gram"
-        },
-        {
-            "name": "-gram"
-        },
-        {
-            "name": "-gram"
-        },
-        {
-            "name": "Language Model"
-        }
-    ],
-    "title": [
-        "Kven N-grams"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4ee02294-7d48-5a63-8d13-110ffaa7b8be.json b/oaitestdata/clarin-oai_dc/SET_1/json/4ee02294-7d48-5a63-8d13-110ffaa7b8be.json
deleted file mode 100644
index 10314267..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4ee02294-7d48-5a63-8d13-110ffaa7b8be.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "The Research Institute for the Languages of Finland"
-    ],
-    "Contributor": [
-        "Ainiala, Terhi"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Finnish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-822",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-822"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-822",
-    "PublicationTimestamp": "2007-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2007"
-    ],
-    "Publisher": [
-        "The Research Institute for the Languages of Finland"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Finland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-822;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Atlas of Place Names;Ainiala, Terhi;The digital atlas illustrates the distribution of 234 common Finnish place-name elements based on data in the Names Archive.;2007;toolService;http://hdl.handle.net/11372/LRT-822;fin;downloadable_files_count: 0;Finland;The Research Institute for the Languages of Finland;http://kaino.kotus.fi/nikar/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4ee02294-7d48-5a63-8d13-110ffaa7b8be",
-    "notes": [
-        "The digital atlas illustrates the distribution of 234 common Finnish place-name elements based on data in the Names Archive."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-822"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Atlas of Place Names"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4eef48a4-6928-5a1e-85f0-3de68d6c3f70.json b/oaitestdata/clarin-oai_dc/SET_1/json/4eef48a4-6928-5a1e-85f0-3de68d6c3f70.json
deleted file mode 100644
index 1cab60ad..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4eef48a4-6928-5a1e-85f0-3de68d6c3f70.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3987",
-    "MetadataAccess": [
-        "oai:ota:oucs:3987"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dibdin, Charles, 1745-1814."
-    ],
-    "fulltext": "oai:ota:oucs:3987;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3987.xml;Harvest-home: A comic opera, in two acts. As performed, with universal applause, at the Theatre-Royal, in the Hay-Market. By Mr. Dibdin.;Dibdin, Charles, 1745-1814.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4eef48a4-6928-5a1e-85f0-3de68d6c3f70",
-    "oai_identifier": [
-        "oai:ota:oucs:3987"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Harvest-home: A comic opera, in two acts. As performed, with universal applause, at the Theatre-Royal, in the Hay-Market. By Mr. Dibdin."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3987.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4ef19786-9d33-500c-93e8-573bfc5557db.json b/oaitestdata/clarin-oai_dc/SET_1/json/4ef19786-9d33-500c-93e8-573bfc5557db.json
deleted file mode 100644
index 59c428c7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4ef19786-9d33-500c-93e8-573bfc5557db.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2855",
-    "MetadataAccess": [
-        "oai:ota:oucs:2855"
-    ],
-    "PublicationTimestamp": "1735-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1735"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2855;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2855.xml;City cries, instrumental and vocal: or, an examination of certain abuses, corruptions, and enormities, in London and Dublin;Swift, Jonathan, 1667-1745;1735;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4ef19786-9d33-500c-93e8-573bfc5557db",
-    "oai_identifier": [
-        "oai:ota:oucs:2855"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "City cries, instrumental and vocal: or, an examination of certain abuses, corruptions, and enormities, in London and Dublin"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2855.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4f0e536e-4a8c-51d4-979d-8797f2a86f29.json b/oaitestdata/clarin-oai_dc/SET_1/json/4f0e536e-4a8c-51d4-979d-8797f2a86f29.json
deleted file mode 100644
index d1894384..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4f0e536e-4a8c-51d4-979d-8797f2a86f29.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "application/gzip",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/87",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/87"
-    ],
-    "PID": "http://hdl.handle.net/10794/87",
-    "PublicationTimestamp": "2015-04-28T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/87;2017-10-25T14:44:38Z;hdl_10794_1;hdl_10794_2;Biblioteksbladet (2015-05-19);Biblioteksbladet (2015-05-19);n/a, n/a;Swedish;Libraries;Biblioteksbladet 1916\u20131940.;Biblioteksbladet 1916\u20131940.;2015-04-28;corpus;http://hdl.handle.net/10794/87;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;text/plain; charset=utf-8;application/octet-stream;application/gzip;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/runeberg-biblblad",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4f0e536e-4a8c-51d4-979d-8797f2a86f29",
-    "notes": [
-        "Biblioteksbladet 1916\u20131940.",
-        "Biblioteksbladet 1916\u20131940."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/87"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Libraries"
-        }
-    ],
-    "title": [
-        "Biblioteksbladet (2015-05-19)",
-        "Biblioteksbladet (2015-05-19)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4f186c56-0c80-5a50-988b-931f15c37fce.json b/oaitestdata/clarin-oai_dc/SET_1/json/4f186c56-0c80-5a50-988b-931f15c37fce.json
deleted file mode 100644
index 2039fcb1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4f186c56-0c80-5a50-988b-931f15c37fce.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=2d875be6a35a11e1a404080027e73ea2fd1adfb79b3648ae9fff2932e82cf95a",
-    "MetadataAccess": [
-        "2d875be6a35a11e1a404080027e73ea2fd1adfb79b3648ae9fff2932e82cf95a"
-    ],
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "2d875be6a35a11e1a404080027e73ea2fd1adfb79b3648ae9fff2932e82cf95a;2019-02-27T12:08:51Z;corpus;corpus:text;Maltese Acquis Communautaire ;This is the Maltese version of the Acquis Communautaire (AC), which is the total body of European Union (EU) law applicable in the EU Member States. It consists of selected texts between the 1950s and today, translated to Maltese.;2015-12-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4f186c56-0c80-5a50-988b-931f15c37fce",
-    "notes": [
-        "This is the Maltese version of the Acquis Communautaire (AC), which is the total body of European Union (EU) law applicable in the EU Member States. It consists of selected texts between the 1950s and today, translated to Maltese."
-    ],
-    "oai_identifier": [
-        "2d875be6a35a11e1a404080027e73ea2fd1adfb79b3648ae9fff2932e82cf95a"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "Maltese Acquis Communautaire "
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4f192f98-202e-566d-8374-24dec92e1243.json b/oaitestdata/clarin-oai_dc/SET_1/json/4f192f98-202e-566d-8374-24dec92e1243.json
deleted file mode 100644
index 042bcefd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4f192f98-202e-566d-8374-24dec92e1243.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "D"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2211",
-    "MetadataAccess": [
-        "oai:ota:oucs:2211"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Collections, corpora etc"
-    ],
-    "fulltext": "oai:ota:oucs:2211;2018-04-16T15:30:51Z;http://ota.ox.ac.uk/headers/2211.xml;Corpus of Brazilian media Portuguese;Collections, corpora etc;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;D;Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4f192f98-202e-566d-8374-24dec92e1243",
-    "oai_identifier": [
-        "oai:ota:oucs:2211"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Corpus of Brazilian media Portuguese"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2211.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4f29ecaa-7a6a-507e-afa2-68267789fd38.json b/oaitestdata/clarin-oai_dc/SET_1/json/4f29ecaa-7a6a-507e-afa2-68267789fd38.json
deleted file mode 100644
index a8d94eed..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4f29ecaa-7a6a-507e-afa2-68267789fd38.json
+++ /dev/null
@@ -1,98 +0,0 @@
-{
-    "Contributor": [
-        "Jiri Semecky",
-        "Marco Pennacchiotti",
-        "Manfred Pinkal",
-        "Aljoscha Burchardt",
-        "Anette Frank",
-        "Caroline Sporleder",
-        "Hagen F\u00fcrstenau",
-        "Katrin Erk",
-        "Dennis Spohr",
-        "Gemma Boleda",
-        "Ines Rehbein",
-        "Josef Ruppenhofer",
-        "Andrea Kowalski",
-        "Sebastian Pad\u00f3"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:salsa",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:salsa"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0005-BD13-1",
-    "PublicationTimestamp": "2006-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2006"
-    ],
-    "RelatedIdentifier": [
-        "A. Burchardt, K. Erk, A. Frank, A. Kowalski, S. Pad\u00f3 and M. Pinkal:\nThe SALSA Corpus: a German Corpus Resource for Lexical Semantics.\nProceedings of LREC 2006, Genoa, Italy. http://www.dfki.de/lt/publication_show.php?id=3611",
-        "List of publications of the SALSA project: http://www.coli.uni-saarland.de/projects/salsa/page.php?id=publications",
-        "Text-SALSA XML format: http://www.nlpado.de/~sebastian/pub/papers/lrec04_erk.pdf",
-        "Framenet: https://framenet.icsi.berkeley.edu/fndrupal/",
-        "FrameNet Transformer: http://www.coli.uni-saarland.de/projects/salsa/fnt/",
-        "WordNet Detour to FrameNet: http://www.coli.uni-saarland.de/~albu/cgi-bin/FN-Detour-short.html",
-        "Shalmaneser: A Shallow Semantic Parser: http://www.coli.uni-saarland.de/projects/salsa/shal/"
-    ],
-    "ResourceType": [
-        "Collection"
-    ],
-    "Rights": [
-        "Copyrighted, Agreement needed",
-        "SALSA license agreement: http://www.coli.uni-saarland.de/projects/salsa/corpus/doc/license.html",
-        "Precondition to use SALSA is to sign TIGER's license agreement: http://www.ims.uni-stuttgart.de/projekte/TIGER/TIGERCorpus/license/htmllicense.shtml"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Manfred Pinkal\nUniversit\u00e4t des Saarlandes\nFachrichtung 4.7 Allgemeine Linguistik\nPostfach 15 11 50\n66041 Saarbr\u00fccken, Germany"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:salsa;2014-06-03T12:59:07Z;SALSA - The SAarbr\u00fccken Lexical Semantics Annotation and Analysis Project;Manfred Pinkal\nUniversit\u00e4t des Saarlandes\nFachrichtung 4.7 Allgemeine Linguistik\nPostfach 15 11 50\n66041 Saarbr\u00fccken, Germany;treebank;newspaper;written corpus;frame semantics;The SALSA corpus is based on the TIGER corpus. The TIGER corpus (Version 2.1) consists of app. 900,000 tokens (50,000 sentences) of German newspaper text, taken from the Frankfurter Rundschau. The corpus was semi-automatically POS-tagged and annotated with syntactic structure. Moreover, it contains morphological and lemma information for terminal nodes. (cf. TIGER corpus website) SALSA provides an additional annotation layer to the TIGER corpus: FrameNet semantic roles.;Das SALSA-Korpus basiert auf dem Tiger-Korpus. Letzteres besteht aus ca. 900.000 Token (50.000 S\u00e4tzen) deutschen Zeitungstextes aus der Frankfurter Rundschau. Das Korpus wurde semi-automatisch syntaktisch annotiert und enth\u00e4lt au\u00dferdem POS, Lemma und morphologische Information. (s.a. TIGER-Korpus-Webseite) SALSA f\u00fcgt der TIGER-Annotation eine weitere Annotationsebene mit semantischen Rollen (FrameNet) hinzu.;Manfred Pinkal;Hagen F\u00fcrstenau;Ines Rehbein;Josef Ruppenhofer;Caroline Sporleder;Gemma Boleda;Aljoscha Burchardt;Katrin Erk;Anette Frank;Andrea Kowalski;Sebastian Pad\u00f3;Marco Pennacchiotti;Jiri Semecky;Dennis Spohr;2006;Collection;text/xml;hdl:11858/00-246C-0000-0005-BD13-1;clarind-uds:salsa;TIGER;http://www.ims.uni-stuttgart.de/projekte/TIGER/;FrameNet;https://framenet.icsi.berkeley.edu/fndrupal/;deu;A. Burchardt, K. Erk, A. Frank, A. Kowalski, S. Pad\u00f3 and M. Pinkal:\nThe SALSA Corpus: a German Corpus Resource for Lexical Semantics.\nProceedings of LREC 2006, Genoa, Italy. http://www.dfki.de/lt/publication_show.php?id=3611;List of publications of the SALSA project: http://www.coli.uni-saarland.de/projects/salsa/page.php?id=publications;Text-SALSA XML format: http://www.nlpado.de/~sebastian/pub/papers/lrec04_erk.pdf;Framenet: https://framenet.icsi.berkeley.edu/fndrupal/;FrameNet Transformer: http://www.coli.uni-saarland.de/projects/salsa/fnt/;WordNet Detour to FrameNet: http://www.coli.uni-saarland.de/~albu/cgi-bin/FN-Detour-short.html;Shalmaneser: A Shallow Semantic Parser: http://www.coli.uni-saarland.de/projects/salsa/shal/;Germany;Copyrighted, Agreement needed;SALSA license agreement: http://www.coli.uni-saarland.de/projects/salsa/corpus/doc/license.html;Precondition to use SALSA is to sign TIGER's license agreement: http://www.ims.uni-stuttgart.de/projekte/TIGER/TIGERCorpus/license/htmllicense.shtml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4f29ecaa-7a6a-507e-afa2-68267789fd38",
-    "notes": [
-        "The SALSA corpus is based on the TIGER corpus. The TIGER corpus (Version 2.1) consists of app. 900,000 tokens (50,000 sentences) of German newspaper text, taken from the Frankfurter Rundschau. The corpus was semi-automatically POS-tagged and annotated with syntactic structure. Moreover, it contains morphological and lemma information for terminal nodes. (cf. TIGER corpus website) SALSA provides an additional annotation layer to the TIGER corpus: FrameNet semantic roles.",
-        "Das SALSA-Korpus basiert auf dem Tiger-Korpus. Letzteres besteht aus ca. 900.000 Token (50.000 S\u00e4tzen) deutschen Zeitungstextes aus der Frankfurter Rundschau. Das Korpus wurde semi-automatisch syntaktisch annotiert und enth\u00e4lt au\u00dferdem POS, Lemma und morphologische Information. (s.a. TIGER-Korpus-Webseite) SALSA f\u00fcgt der TIGER-Annotation eine weitere Annotationsebene mit semantischen Rollen (FrameNet) hinzu."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:salsa"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "newspaper"
-        },
-        {
-            "name": "written corpus"
-        },
-        {
-            "name": "frame semantics"
-        }
-    ],
-    "title": [
-        "SALSA - The SAarbr\u00fccken Lexical Semantics Annotation and Analysis Project"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4f6beb7e-1fea-5268-878d-32a2231547c5.json b/oaitestdata/clarin-oai_dc/SET_1/json/4f6beb7e-1fea-5268-878d-32a2231547c5.json
deleted file mode 100644
index 9e9c52a5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4f6beb7e-1fea-5268-878d-32a2231547c5.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Dziedzic\u00f3w Jakuba Siebeneichera"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-162762",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-162762"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CE7-E",
-    "PublicationTimestamp": "1615-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1615"
-    ],
-    "Publisher": [
-        "Drukarnia Dziedzic\u00f3w Jakuba Siebeneichera"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/162762",
-        "oai:jbc.bj.uj.edu.pl:publication:171125"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1601/1700"
-    ],
-    "TempCoverageBegin": 50506804799,
-    "TempCoverageEnd": 50506804799,
-    "TemporalCoverage": " point in time : 1601-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1601-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1601-07-01T11:59:59Z",
-    "author": [
-        "Kunicki, Wac\u0142aw (1580-1653)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-162762;2019-02-28T18:43:44Z;Obraz Szlachcica Polskiego;Kunicki, Wac\u0142aw (1580-1653);starodruki 17\u00a0w.;\u0141ahodowski, Jan (15..-1622). [Adr. ded.];Drukarnia Dziedzic\u00f3w Jakuba Siebeneichera;1615;starodruk;application/xml;clarind-uds:poldilemma-162762;hdl:11858/00-246C-0000-0023-8CE7-E;Biblioteka Jagiello\u0144ska, BJ St. Dr. 10796 I;pol;lat;http://jbc.bj.uj.edu.pl/Content/162762;oai:jbc.bj.uj.edu.pl:publication:171125;1601/1700;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4f6beb7e-1fea-5268-878d-32a2231547c5",
-    "notes": [
-        "\u0141ahodowski, Jan (15..-1622). [Adr. ded.]"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-162762"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Obraz Szlachcica Polskiego"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4f7084b8-0719-5c8b-b2c9-db00866ade3e.json b/oaitestdata/clarin-oai_dc/SET_1/json/4f7084b8-0719-5c8b-b2c9-db00866ade3e.json
deleted file mode 100644
index d2c5c7b2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4f7084b8-0719-5c8b-b2c9-db00866ade3e.json
+++ /dev/null
@@ -1,102 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 24",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Bulgarian",
-        "Czech",
-        "Danish",
-        "German",
-        "Modern Greek (1453-)",
-        "English",
-        "Spanish",
-        "Estonian",
-        "Finnish",
-        "French",
-        "Hungarian",
-        "Italian",
-        "Lithuanian",
-        "Latvian",
-        "Dutch",
-        "Polish",
-        "Portuguese",
-        "Romanian",
-        "Croatian",
-        "Slovak",
-        "Slovenian",
-        "Swedish",
-        "Irish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1197",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1197"
-    ],
-    "PID": "http://hdl.handle.net/11356/1197",
-    "PublicationTimestamp": "2018-08-15T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "Erjavec, Toma\u017e",
-        "Ljube\u0161i\u0107, Nikola"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1197;2018-10-24T20:56:47Z;hdl_11356_1023;hdl_11356_1024;JRC EU DGT Translation Memory Parsebank DGT-UD 1.0;Ljube\u0161i\u0107, Nikola;Erjavec, Toma\u017e;European law;parallel corpus;dependency parsebank;multilingual;DGT-UD is a 2 billion word 23-language parallel syntactically parsed corpus, which consists of the JRC DGT translation memory of European law, automatically annotated with UD-Pipe 1.2 (http://ufal.mff.cuni.cz/udpipe) using Universal Dependencies 2.0 models (http://hdl.handle.net/11234/1-2364). \r\nNote that the European Commission retains ownership of the source texts.;2018-08-15;corpus;http://hdl.handle.net/11356/1197;bul;ces;dan;deu;ell;eng;spa;est;fin;fra;hun;ita;lit;lav;nld;pol;por;ron;hrv;slk;slv;swe;gle;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;https://creativecommons.org/licenses/by/4.0/;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 24;Jo\u017eef Stefan Institute;https://ec.europa.eu/jrc/en/language-technologies/dgt-translation-memory",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4f7084b8-0719-5c8b-b2c9-db00866ade3e",
-    "notes": [
-        "DGT-UD is a 2 billion word 23-language parallel syntactically parsed corpus, which consists of the JRC DGT translation memory of European law, automatically annotated with UD-Pipe 1.2 (http://ufal.mff.cuni.cz/udpipe) using Universal Dependencies 2.0 models (http://hdl.handle.net/11234/1-2364). \r\nNote that the European Commission retains ownership of the source texts."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1197"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "European law"
-        },
-        {
-            "name": "parallel corpus"
-        },
-        {
-            "name": "dependency parsebank"
-        },
-        {
-            "name": "multilingual"
-        }
-    ],
-    "title": [
-        "JRC EU DGT Translation Memory Parsebank DGT-UD 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4fd84ef1-02ba-50e6-b845-6ec92c7a952b.json b/oaitestdata/clarin-oai_dc/SET_1/json/4fd84ef1-02ba-50e6-b845-6ec92c7a952b.json
deleted file mode 100644
index 055123ed..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4fd84ef1-02ba-50e6-b845-6ec92c7a952b.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "between 1 and 2 MB"
-    ],
-    "Language": [
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0329",
-    "MetadataAccess": [
-        "oai:ota:oucs:0329"
-    ],
-    "PublicationYear": [
-        "438"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Legal formularies"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Unknown"
-    ],
-    "fulltext": "oai:ota:oucs:0329;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0329.xml; Codex Theodosianus  / compiled by Nicholas Palmer ; revised by Tony Honor\u00c3\u00a9;Unknown;438;text_and_corpus_linguistics;Laws -- 5th century;Legal formularies -- 5th century;lat;Oxford Text Archive, University of Oxford;between 1 and 2 MB;Text;Legal formularies;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4fd84ef1-02ba-50e6-b845-6ec92c7a952b",
-    "oai_identifier": [
-        "oai:ota:oucs:0329"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Laws -- th century"
-        },
-        {
-            "name": "Legal formularies -- th century"
-        }
-    ],
-    "title": [
-        " Codex Theodosianus  / compiled by Nicholas Palmer ; revised by Tony Honor\u00c3\u00a9"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0329.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4fec2de0-963c-50b4-bd2e-4f95f2a470c0.json b/oaitestdata/clarin-oai_dc/SET_1/json/4fec2de0-963c-50b4-bd2e-4f95f2a470c0.json
deleted file mode 100644
index 0945c956..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4fec2de0-963c-50b4-bd2e-4f95f2a470c0.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "Filesize uncompressed: 155 KBytes."
-    ],
-    "Language": [
-        "Middle English (1100-1500)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1680",
-    "MetadataAccess": [
-        "oai:ota:oucs:1680"
-    ],
-    "PublicationTimestamp": "1350-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1350"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Anonymous"
-    ],
-    "fulltext": "oai:ota:oucs:1680;2018-05-17T09:37:46Z;http://ota.ox.ac.uk/headers/1680.xml;Sir Gawayne and the Grene Knyght;A machine-readable transcription;Anonymous;1350-1399;text_and_corpus_linguistics;enm;Oxford Text Archive, University of Oxford;Filesize uncompressed: 155 KBytes.;Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4fec2de0-963c-50b4-bd2e-4f95f2a470c0",
-    "oai_identifier": [
-        "oai:ota:oucs:1680"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Sir Gawayne and the Grene Knyght",
-        "A machine-readable transcription"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1680.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4ff11677-eca6-5af8-b01a-631d4fc2b620.json b/oaitestdata/clarin-oai_dc/SET_1/json/4ff11677-eca6-5af8-b01a-631d4fc2b620.json
deleted file mode 100644
index 29cb2a55..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4ff11677-eca6-5af8-b01a-631d4fc2b620.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "TALG Research Group (University of Vigo)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Galician"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-615",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-615"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-615",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "TALG Research Group (University of Vigo)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-615;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Corpus T\u00e9cnico do Galego;Domain-specific corpus (Law, Computing, Medicine, Economy, Sociology and Environment), 22 million words;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-615;glg;downloadable_files_count: 0;Spain;TALG Research Group (University of Vigo);http://sli.uvigo.es/CTG",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4ff11677-eca6-5af8-b01a-631d4fc2b620",
-    "notes": [
-        "Domain-specific corpus (Law, Computing, Medicine, Economy, Sociology and Environment), 22 million words"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-615"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus T\u00e9cnico do Galego"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/4ff492ee-bc30-5762-92dd-47095ad4e963.json b/oaitestdata/clarin-oai_dc/SET_1/json/4ff492ee-bc30-5762-92dd-47095ad4e963.json
deleted file mode 100644
index 5b4cdbd9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/4ff492ee-bc30-5762-92dd-47095ad4e963.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Dept. Speech, Music and Hearing, CSC, KTH"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-331",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-331"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-331",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Dept. Speech, Music and Hearing, CSC, KTH"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Sweden"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-331;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;WaveSurfer;WaveSurfer is an Open Source tool for sound visualization and manipulation. It has been designed to suit both novice and advanced users. WaveSurfer has a simple and logical user interface that provides functionality in an intuitive way and which can be adapted to different tasks. It can be used as a stand-alone tool for a wide range of tasks in speech research and education. Typical applications are speech/sound analysis and sound annotation/transcription. WaveSurfer can also serve as a platform for more advanced/specialized applications. This is accomplished either through extending the WaveSurfer application with new custom plug-ins or by embedding WaveSurfer visualization components in other applications.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-331;downloadable_files_count: 0;Sweden;Dept. Speech, Music and Hearing, CSC, KTH;http://www.speech.kth.se/wavesurfer/index.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4ff492ee-bc30-5762-92dd-47095ad4e963",
-    "notes": [
-        "WaveSurfer is an Open Source tool for sound visualization and manipulation. It has been designed to suit both novice and advanced users. WaveSurfer has a simple and logical user interface that provides functionality in an intuitive way and which can be adapted to different tasks. It can be used as a stand-alone tool for a wide range of tasks in speech research and education. Typical applications are speech/sound analysis and sound annotation/transcription. WaveSurfer can also serve as a platform for more advanced/specialized applications. This is accomplished either through extending the WaveSurfer application with new custom plug-ins or by embedding WaveSurfer visualization components in other applications."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-331"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "WaveSurfer"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/50009164-c9c3-5a05-be9d-6ada9fbc975c.json b/oaitestdata/clarin-oai_dc/SET_1/json/50009164-c9c3-5a05-be9d-6ada9fbc975c.json
deleted file mode 100644
index 27555ccf..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/50009164-c9c3-5a05-be9d-6ada9fbc975c.json
+++ /dev/null
@@ -1,49 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5077",
-    "MetadataAccess": [
-        "oai:ota:oucs:5077"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:5077;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5077.xml;The lucubrations of Isaac Bickerstaff Esq: revised and corrected by the author. ... [pt.4];text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "50009164-c9c3-5a05-be9d-6ada9fbc975c",
-    "oai_identifier": [
-        "oai:ota:oucs:5077"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The lucubrations of Isaac Bickerstaff Esq: revised and corrected by the author. ... [pt.4]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5077.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/500f2378-d927-5a96-8661-fbb8e829e3f1.json b/oaitestdata/clarin-oai_dc/SET_1/json/500f2378-d927-5a96-8661-fbb8e829e3f1.json
deleted file mode 100644
index a313101e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/500f2378-d927-5a96-8661-fbb8e829e3f1.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2144",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2144"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2144",
-    "PublicationTimestamp": "2017-04-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Haji\u010d, Jan",
-        "N\u00e1plava, Jakub",
-        "Straka, Milan"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2144;2018-07-02T22:05:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Automatically generated spelling correction corpus for Czech (Czech-SEC-AG);Haji\u010d, Jan;N\u00e1plava, Jakub;Straka, Milan;spelling correction;natural language correction;Automatically generated spelling correction corpus for Czech (Czesl-SEC-AG) is a corpus containg text with automatically generated spelling errors. To create spelling errors, a character error model containing probabilities of character substitution, insertion, deletion and probabilities of swaping two adjacent characters is used. Besides these probabilities, also the probabilities of changing character casing are considered. The original clean text on which the spelling errors were generated is PDT3.0 (http://hdl.handle.net/11858/00-097C-0000-0023-1AAF-3). The original train/dev/test sentence split of PDT3.0 corpus is preserved in this dataset.\r\n\r\nBesides the data with artificial spelling errors, we also publish texts from which the character error model was created. These are the original manual transcript of an audiobook \u0160vejk and its corrected version performed by authors of Korektor (http://ufal.mff.cuni.cz/korektor). These data are similarly to CzeSL Grammatical Error Correction Dataset (CzeSL-GEC: http://hdl.handle.net/11234/1-2143) processed into four sets based on error difficulty present.;2017-04-30;corpus;http://hdl.handle.net/11234/1-2144;ces;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "500f2378-d927-5a96-8661-fbb8e829e3f1",
-    "notes": [
-        "Automatically generated spelling correction corpus for Czech (Czesl-SEC-AG) is a corpus containg text with automatically generated spelling errors. To create spelling errors, a character error model containing probabilities of character substitution, insertion, deletion and probabilities of swaping two adjacent characters is used. Besides these probabilities, also the probabilities of changing character casing are considered. The original clean text on which the spelling errors were generated is PDT3.0 (http://hdl.handle.net/11858/00-097C-0000-0023-1AAF-3). The original train/dev/test sentence split of PDT3.0 corpus is preserved in this dataset.\r\n\r\nBesides the data with artificial spelling errors, we also publish texts from which the character error model was created. These are the original manual transcript of an audiobook \u0160vejk and its corrected version performed by authors of Korektor (http://ufal.mff.cuni.cz/korektor). These data are similarly to CzeSL Grammatical Error Correction Dataset (CzeSL-GEC: http://hdl.handle.net/11234/1-2143) processed into four sets based on error difficulty present."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2144"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "spelling correction"
-        },
-        {
-            "name": "natural language correction"
-        }
-    ],
-    "title": [
-        "Automatically generated spelling correction corpus for Czech (Czech-SEC-AG)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/50249b40-fbae-5faa-853b-b359639b45f6.json b/oaitestdata/clarin-oai_dc/SET_1/json/50249b40-fbae-5faa-853b-b359639b45f6.json
deleted file mode 100644
index 9671d278..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/50249b40-fbae-5faa-853b-b359639b45f6.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/102",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/102"
-    ],
-    "PID": "http://hdl.handle.net/10794/102",
-    "PublicationTimestamp": "2013-03-06T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/102;2017-10-25T11:28:36Z;hdl_10794_1;hdl_10794_2;Blog mix 2008 (2017-02-17);Bloggmix 2008 (2017-02-17);n/a, n/a;Swedish;Blog;The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.;Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat.;2013-03-06;corpus;http://hdl.handle.net/10794/102;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/bloggmix2008",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "50249b40-fbae-5faa-853b-b359639b45f6",
-    "notes": [
-        "The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.",
-        "Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/102"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Blog"
-        }
-    ],
-    "title": [
-        "Blog mix 2008 (2017-02-17)",
-        "Bloggmix 2008 (2017-02-17)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/50388f2b-53f4-5b88-a90c-7015bb2265f2.json b/oaitestdata/clarin-oai_dc/SET_1/json/50388f2b-53f4-5b88-a90c-7015bb2265f2.json
deleted file mode 100644
index 90aefd7a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/50388f2b-53f4-5b88-a90c-7015bb2265f2.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "text/html",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0005-BCCF-3",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0005-BCCF-3"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0005-BCCF-3",
-    "PublicationTimestamp": "2012-02-20T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "M\u00edrovsk\u00fd, Ji\u0159\u00ed",
-        "Nedoluzhko, Anna"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0005-BCCF-3;2018-07-02T22:05:54Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Extended Textual Coreference and Bridging Relations in PDT 2.0;Nedoluzhko, Anna;M\u00edrovsk\u00fd, Ji\u0159\u00ed;bridging anaphora;textual coreference;PDT;Annotation of extended textual coreference and bridging relations in the Prague Dependency Treebank 2.0;2012-02-20;corpus;http://hdl.handle.net/11858/00-097C-0000-0005-BCCF-3;ces;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;text/html;application/zip;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "50388f2b-53f4-5b88-a90c-7015bb2265f2",
-    "notes": [
-        "Annotation of extended textual coreference and bridging relations in the Prague Dependency Treebank 2.0"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0005-BCCF-3"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "bridging anaphora"
-        },
-        {
-            "name": "textual coreference"
-        },
-        {
-            "name": "PDT"
-        }
-    ],
-    "title": [
-        "Extended Textual Coreference and Bridging Relations in PDT 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/50424e77-c1c0-5b95-8885-2c2b57bdf24f.json b/oaitestdata/clarin-oai_dc/SET_1/json/50424e77-c1c0-5b95-8885-2c2b57bdf24f.json
deleted file mode 100644
index 4ccc7ce3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/50424e77-c1c0-5b95-8885-2c2b57bdf24f.json
+++ /dev/null
@@ -1,91 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/560",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/560"
-    ],
-    "PID": "http://hdl.handle.net/11321/560",
-    "PublicationTimestamp": "2018-07-26T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Mykowiecka, Agnieszka Anna"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/560;2018-07-26T11:23:12Z;hdl_11321_3;hdl_11321_4;TimeAssign;Mykowiecka, Agnieszka Anna;TimeML;TIMEX3;temporal expressions;deep learning;word embeddings;LSTM;recogniton;information extraction;TimeAssign is a program which recognizes temporal expressions and assigns TimeML labels to words in Polish text using a Bi-LSTM based neural net and wordform embeddings.;2018-07-26;toolService;http://hdl.handle.net/11321/560;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Institute of Computer Science, Polish Academy of Sciences",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "50424e77-c1c0-5b95-8885-2c2b57bdf24f",
-    "notes": [
-        "TimeAssign is a program which recognizes temporal expressions and assigns TimeML labels to words in Polish text using a Bi-LSTM based neural net and wordform embeddings."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/560"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "TimeML"
-        },
-        {
-            "name": "TIMEX"
-        },
-        {
-            "name": "temporal expressions"
-        },
-        {
-            "name": "deep learning"
-        },
-        {
-            "name": "word embeddings"
-        },
-        {
-            "name": "LSTM"
-        },
-        {
-            "name": "recogniton"
-        },
-        {
-            "name": "information extraction"
-        }
-    ],
-    "title": [
-        "TimeAssign"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/50563070-8233-5e29-89b4-15a9e170b110.json b/oaitestdata/clarin-oai_dc/SET_1/json/50563070-8233-5e29-89b4-15a9e170b110.json
deleted file mode 100644
index 1bdb139f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/50563070-8233-5e29-89b4-15a9e170b110.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "University of Lodz"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/287",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/287"
-    ],
-    "PID": "http://hdl.handle.net/11321/287",
-    "PublicationTimestamp": "2016-03-04T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "University of Lodz"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Dr\u00f3\u017ad\u017c, \u0141ukasz",
-        "Kowalczyk, Pawe\u0142",
-        "P\u0119zik, Piotr",
-        "Wilk, Pawe\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/287;2016-06-03T14:30:34Z;hdl_11321_3;hdl_11321_4;PELCRA for National Corpus of Polish Search Engine 2;P\u0119zik, Piotr;Kowalczyk, Pawe\u0142;Dr\u00f3\u017ad\u017c, \u0141ukasz;Wilk, Pawe\u0142;National Corpus of Polish;NKJP;corpus search engine;The PELCRA for NKJP search engine 2 provides access to the full National Corpus of Polish dataset (over 1.5 billion word tokens). In addition to linguistically motivated corpus queries, it supports a number of data exploration and visualisation features. Most of the functionality of the search engine is available through a REST web service. Access to the API is available upon request.;2016-03-04;toolService;http://hdl.handle.net/11321/287;pol;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;CC;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;University of Lodz;http://pelcra.clarin-pl.eu/NKJP/#home",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "50563070-8233-5e29-89b4-15a9e170b110",
-    "notes": [
-        "The PELCRA for NKJP search engine 2 provides access to the full National Corpus of Polish dataset (over 1.5 billion word tokens). In addition to linguistically motivated corpus queries, it supports a number of data exploration and visualisation features. Most of the functionality of the search engine is available through a REST web service. Access to the API is available upon request."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/287"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "National Corpus Polish"
-        },
-        {
-            "name": "NKJP"
-        },
-        {
-            "name": "corpus search engine"
-        }
-    ],
-    "title": [
-        "PELCRA for National Corpus of Polish Search Engine 2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/50a72b2b-7add-5357-9452-ad89b78a9113.json b/oaitestdata/clarin-oai_dc/SET_1/json/50a72b2b-7add-5357-9452-ad89b78a9113.json
deleted file mode 100644
index d25efbae..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/50a72b2b-7add-5357-9452-ad89b78a9113.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/vnd.ms-excel"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/28",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/28"
-    ],
-    "PID": "http://hdl.handle.net/10794/28",
-    "PublicationTimestamp": "2012-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/28;2017-10-27T14:57:34Z;hdl_10794_1;hdl_10794_2;Kelly (2017-10-16);Kelly (2017-10-16);n/a, n/a;Swedish;CEFR;Keywords for Language Learning for Young and adults alike.;Nyckelord f\u00f6r spr\u00e5kinl\u00e4rning f\u00f6r unga och vuxna.;2012-05-30;lexicalConceptualResource;http://hdl.handle.net/10794/28;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/gzip;application/vnd.ms-excel;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/kelly",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "50a72b2b-7add-5357-9452-ad89b78a9113",
-    "notes": [
-        "Keywords for Language Learning for Young and adults alike.",
-        "Nyckelord f\u00f6r spr\u00e5kinl\u00e4rning f\u00f6r unga och vuxna."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/28"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "CEFR"
-        }
-    ],
-    "title": [
-        "Kelly (2017-10-16)",
-        "Kelly (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/50be4c4d-27d7-59b5-a579-95b74885db10.json b/oaitestdata/clarin-oai_dc/SET_1/json/50be4c4d-27d7-59b5-a579-95b74885db10.json
deleted file mode 100644
index 2d7419d4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/50be4c4d-27d7-59b5-a579-95b74885db10.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Lancashire, Ian"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 44 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1033",
-    "MetadataAccess": [
-        "oai:ota:oucs:1033"
-    ],
-    "PublicationTimestamp": "1565-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1565"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Wager, W. (William)"
-    ],
-    "fulltext": "oai:ota:oucs:1033;2018-03-05T10:37:10Z;http://ota.ox.ac.uk/headers/1033.xml;Enough is as good as a feast / W. Wager;A comedy or enterlude intitled : Inough is as good as a feast;Wager, W. (William);1565;text_and_corpus_linguistics;English drama -- Early modern and Elizabethan, 1500-1600;eng;Oxford Text Archive, University of Oxford;Lancashire, Ian;(1 file : ca. 44 KB);Text;Plays;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "50be4c4d-27d7-59b5-a579-95b74885db10",
-    "oai_identifier": [
-        "oai:ota:oucs:1033"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- Early modern Elizabethan"
-        }
-    ],
-    "title": [
-        "Enough is as good as a feast / W. Wager",
-        "A comedy or enterlude intitled : Inough is as good as a feast"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1033.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/50c38c27-4e2c-5a89-92cc-0b8632604741.json b/oaitestdata/clarin-oai_dc/SET_1/json/50c38c27-4e2c-5a89-92cc-0b8632604741.json
deleted file mode 100644
index 56a4761f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/50c38c27-4e2c-5a89-92cc-0b8632604741.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "application/zip",
-        "application/octet-stream"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1485",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1485"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1485",
-    "PublicationTimestamp": "2015-05-19T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU General Public Licence, version 3",
-        "http://opensource.org/licenses/GPL-3.0",
-        "PUB"
-    ],
-    "author": [
-        "Rosa, Rudolf"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1485;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;MSTperl delexicalized parser transfer scripts and configuration files;Rosa, Rudolf;parsing;delexicalized parser transfer;This is a set of MSTperl parser configuration files and scripts for delexicalized parser transfer. They were used in the work reported in arXiv:1506.04897 (http://arxiv.org/abs/1506.04897), as well as several related papers. The MSTperl parser is available at http://hdl.handle.net/11234/1-1480;2015-05-19;toolService;http://hdl.handle.net/11234/1-1485;GNU General Public Licence, version 3;http://opensource.org/licenses/GPL-3.0;PUB;text/plain; charset=utf-8;application/octet-stream;application/zip;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://ufal.mff.cuni.cz/tools/mstperl-parser",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "50c38c27-4e2c-5a89-92cc-0b8632604741",
-    "notes": [
-        "This is a set of MSTperl parser configuration files and scripts for delexicalized parser transfer. They were used in the work reported in arXiv:1506.04897 (http://arxiv.org/abs/1506.04897), as well as several related papers. The MSTperl parser is available at http://hdl.handle.net/11234/1-1480"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1485"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parsing"
-        },
-        {
-            "name": "delexicalized parser transfer"
-        }
-    ],
-    "title": [
-        "MSTperl delexicalized parser transfer scripts and configuration files"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/50ca0183-7f1f-5b05-85a6-28852e2a7621.json b/oaitestdata/clarin-oai_dc/SET_1/json/50ca0183-7f1f-5b05-85a6-28852e2a7621.json
deleted file mode 100644
index 284c454c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/50ca0183-7f1f-5b05-85a6-28852e2a7621.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4041",
-    "MetadataAccess": [
-        "oai:ota:oucs:4041"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gentleman, Francis, 1728-1784."
-    ],
-    "fulltext": "oai:ota:oucs:4041;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4041.xml;Narcissa and Eliza. A dramatic tale. By Francis Gentleman;Gentleman, Francis, 1728-1784.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "50ca0183-7f1f-5b05-85a6-28852e2a7621",
-    "oai_identifier": [
-        "oai:ota:oucs:4041"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Narcissa and Eliza. A dramatic tale. By Francis Gentleman"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4041.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/50ce66da-4e44-57cb-be1a-3211f655a5b1.json b/oaitestdata/clarin-oai_dc/SET_1/json/50ce66da-4e44-57cb-be1a-3211f655a5b1.json
deleted file mode 100644
index f68d0ae2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/50ce66da-4e44-57cb-be1a-3211f655a5b1.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3134",
-    "MetadataAccess": [
-        "oai:ota:oucs:3134"
-    ],
-    "PublicationTimestamp": "1898-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1898"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Westcott, Edward Noyes, 1847-1898"
-    ],
-    "fulltext": "oai:ota:oucs:3134;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3134.xml;David Harum: a story of American life;Westcott, Edward Noyes, 1847-1898;not after: 1898;text_and_corpus_linguistics;American fiction -- 19th century;eng;Oxford Text Archive, University of Oxford;Triggs, Jeffery;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "50ce66da-4e44-57cb-be1a-3211f655a5b1",
-    "oai_identifier": [
-        "oai:ota:oucs:3134"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "American fiction -- th century"
-        }
-    ],
-    "title": [
-        "David Harum: a story of American life"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3134.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/50d946fb-a99b-51dc-a24c-6b8fa50f6d4e.json b/oaitestdata/clarin-oai_dc/SET_1/json/50d946fb-a99b-51dc-a24c-6b8fa50f6d4e.json
deleted file mode 100644
index 3a5ef553..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/50d946fb-a99b-51dc-a24c-6b8fa50f6d4e.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 101 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1892",
-    "MetadataAccess": [
-        "oai:ota:oucs:1892"
-    ],
-    "PublicationTimestamp": "1914-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1914"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Sandburg, Carl, 1878-1967"
-    ],
-    "fulltext": "oai:ota:oucs:1892;2018-04-16T09:30:54Z;http://ota.ox.ac.uk/headers/1892.xml;Chicago poems / by Carl Sandburg;Sandburg, Carl, 1878-1967;1914;text_and_corpus_linguistics;Poems -- United States -- 20th century;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 101 KB);Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "50d946fb-a99b-51dc-a24c-6b8fa50f6d4e",
-    "oai_identifier": [
-        "oai:ota:oucs:1892"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- United States -- th century"
-        }
-    ],
-    "title": [
-        "Chicago poems / by Carl Sandburg"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1892.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/50d9c482-5db2-5dd5-903c-2fd933a9f1b7.json b/oaitestdata/clarin-oai_dc/SET_1/json/50d9c482-5db2-5dd5-903c-2fd933a9f1b7.json
deleted file mode 100644
index d7574ce3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/50d9c482-5db2-5dd5-903c-2fd933a9f1b7.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3845",
-    "MetadataAccess": [
-        "oai:ota:oucs:3845"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Arbuthnot, John, 1667-1735."
-    ],
-    "fulltext": "oai:ota:oucs:3845;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3845.xml;An appendix to the history of the Crown-Inn: with a key to the whole;Arbuthnot, John, 1667-1735.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "50d9c482-5db2-5dd5-903c-2fd933a9f1b7",
-    "oai_identifier": [
-        "oai:ota:oucs:3845"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An appendix to the history of the Crown-Inn: with a key to the whole"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3845.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/50db80fa-5ed1-5011-826e-a0a469e41223.json b/oaitestdata/clarin-oai_dc/SET_1/json/50db80fa-5ed1-5011-826e-a0a469e41223.json
deleted file mode 100644
index 72479706..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/50db80fa-5ed1-5011-826e-a0a469e41223.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-961",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-961"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-961",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-961;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Bats (Tsova-Tush);ca. 100.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-961;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#batsbi",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "50db80fa-5ed1-5011-826e-a0a469e41223",
-    "notes": [
-        "ca. 100.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-961"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Bats (Tsova-Tush)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/50e89ce0-8be2-544f-9293-f5eee2f1023f.json b/oaitestdata/clarin-oai_dc/SET_1/json/50e89ce0-8be2-544f-9293-f5eee2f1023f.json
deleted file mode 100644
index c6955c23..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/50e89ce0-8be2-544f-9293-f5eee2f1023f.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Micha\u0142 i Grzegorz Schedl"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-520",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-520"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D20-4",
-    "PublicationTimestamp": "1678-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1678"
-    ],
-    "Publisher": [
-        "Micha\u0142 i Grzegorz Schedl"
-    ],
-    "RelatedIdentifier": [
-        "http://pbc.biaman.pl/Content/520"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-520;2019-03-01T15:35:44Z;Konstytucya Seymu Walnego Ordynaryinego Sze\u015b\u0107 Niedzielnego.W Grodnie roku pa\u0144skiego M.DC.LXXVIII (1678) dnia XV Grudnia odprawui\u0105cego si\u0119. Cum gratia et privilegio S.R.M.;Konstytucja 1678 r.;ilo\u015b\u0107 skan\u00f3w: 38  ; sygn. St- 342;Micha\u0142 i Grzegorz Schedl;1678;starodruk;application/xml;clarind-uds:poldilemma-520;hdl:11858/00-246C-0000-0023-8D20-4;pol;lat;http://pbc.biaman.pl/Content/520;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "50e89ce0-8be2-544f-9293-f5eee2f1023f",
-    "notes": [
-        "ilo\u015b\u0107 skan\u00f3w: 38  ; sygn. St- 342"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-520"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Konstytucja r."
-        }
-    ],
-    "title": [
-        "Konstytucya Seymu Walnego Ordynaryinego Sze\u015b\u0107 Niedzielnego.W Grodnie roku pa\u0144skiego M.DC.LXXVIII (1678) dnia XV Grudnia odprawui\u0105cego si\u0119. Cum gratia et privilegio S.R.M."
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/50f0df43-6fba-5b4f-afbf-8ac2826a6227.json b/oaitestdata/clarin-oai_dc/SET_1/json/50f0df43-6fba-5b4f-afbf-8ac2826a6227.json
deleted file mode 100644
index a77e2c18..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/50f0df43-6fba-5b4f-afbf-8ac2826a6227.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 87.9 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0083",
-    "MetadataAccess": [
-        "oai:ota:oucs:0083"
-    ],
-    "PublicationTimestamp": "1597-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1597"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Petau de Maulette, Genevi\u00c3\u00a8ve"
-    ],
-    "fulltext": "oai:ota:oucs:0083;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0083.xml;Virtue's tears for the loss of the most christian King Henry Third of the name, King of France, and the untimely death of the most noble and heroic gentleman, Walter Devoreux, who was slain before Rouen in France / first written in French by the most excellent learned gentlewoman, Madam Genevieve [sic], Petau Maulette ; and paraphrastically translated into English by Gervase Markham;Devoreux, or, Virtue's tears;Petau de Maulette, Genevi\u00c3\u00a8ve;1597;text_and_corpus_linguistics;Poems -- France -- 16th century;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 87.9 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "50f0df43-6fba-5b4f-afbf-8ac2826a6227",
-    "oai_identifier": [
-        "oai:ota:oucs:0083"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- France -- th century"
-        }
-    ],
-    "title": [
-        "Virtue's tears for the loss of the most christian King Henry Third of the name, King of France, and the untimely death of the most noble and heroic gentleman, Walter Devoreux, who was slain before Rouen in France / first written in French by the most excellent learned gentlewoman, Madam Genevieve [sic], Petau Maulette ; and paraphrastically translated into English by Gervase Markham",
-        "Devoreux, or, Virtue's tears"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0083.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/510c6fcb-88a2-54d7-85f4-a79a00f067f5.json b/oaitestdata/clarin-oai_dc/SET_1/json/510c6fcb-88a2-54d7-85f4-a79a00f067f5.json
deleted file mode 100644
index 046e942d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/510c6fcb-88a2-54d7-85f4-a79a00f067f5.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "NLX-Natural Language and Speech Group, University of Lisbon"
-    ],
-    "Contributor": [
-        "Ferreira, Eduardo",
-        "Branco, Ant\u00f3nio",
-        "Balsa, Jo\u00e3o",
-        "Silveira, Sara"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Portuguese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1226",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1226"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1226",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "NLX-Natural Language and Speech Group, University of Lisbon"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Portugal"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1226;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LX-NER;Balsa, Jo\u00e3o;Branco, Ant\u00f3nio;Ferreira, Eduardo;Silveira, Sara;LX-NER is a Named Entity Recognizer for Portuguese. LX-NER takes a segment of Portuguese text and identifies, circumscribes and classifies the expressions for named entities it contains. Furthermore, each named entity receives a standard representation. It handles the following types of expressions: * Number-based expressions o Numbers: Expressions denoting numbers are marked as NUMEX. A list of subtypes is considered, allowing for a more refined classification of these expressions: + Arabic: Entities expressed by a sequence of digits, with the option of using a period to separate a string of 3 digits, counting from the right. + Decimal: Entities expressed by an arabic number followed by a decimal part, with a comma separating both parts. + Non-compliant: Entities expressed by digits, the period and comma symbols, organized in any possible way. All entities not covered by the previous 2 subtypes are included here. + Roman: Entities expressed by the roman letters [IVXLCDM], in either uppercase or lowercase, with the string of letters obeying the well-formedness rules for roman numerals. + Cardinal: Entities that are expressed by a full or partial word description of an arabic or decimal number. A full cardinal numeral is composed of words, while a partial cardinal number is a hybrid composed by words and arabic or decimal numbers. + Fraction: Entities expressed by arabic, decimal or cardinal numbers, and specific symbols or expressions representing division. + Magnitude class: Entities expressed by arabic, decimal or cardinal numbers together with expressions representing numerical magnitude. o Measures: Terms expressing measure values are marked as MEASEX. A list of subtypes is considered, allowing for a more refined classification of these expressions: + Currency: Expressions composed of an arabic, decimal or cardinal number followed by a word or expression representing a currency (e.g. libras). + Time: Expressions composed of an arabic, decimal or cardinal number followed by a word or expression representing a time measure (e.g. segundos). + Scientifc units: Expressions composed of an arabic, decimal or cardinal number followed by a word or expression representing a scientific unit (e.g. toneladas). o Time: Terms expressing time are marked as TIMEX. A list of subtypes is considered, allowing for a more refined classification of these expressions: + Date: Expressions representing a date, whose components can be a day of the week (e.g. Segunda-Feira), a day of the month (e.g. 27), a month (e.g. Novembro) or a year (e.g. 2006). + Time periods: Expressions made by arabic, roman or cardinal numbers and an explicit indication of a period of time concerning a specific year, decade or century. + Time of the day: Expressions with different formats, indicating a specific time of the day. o Addresses: Expressions conveying addresses are marked as ADDREX. A list of subparts is considered, allowing for a more refined classification of these expressions: + Global section: Expressions referring to the global position of a certain location (e.g. Rua Almeida Garrett). This address part is mandatory for an address to be recognized. + Local section: Expressions referring to a specific position within the global position (e.g. N\u00ba 17 - 7\u00ba Dto). + Zip code: Expressions referring to the zip code component of an address (e.g. 3654-548 Lisboa). * Name-based expressions o Names: Expressions conveying names are marked as NAMEX. A list of subtypes is considered, allowing for a more refined classification of these expressions: + Persons: Expressions conveying names of people, with the option of considering the job or social status of a person if present (e.g. Presidente Cavaco Silva). + Organizations: Expressions conveying names of companies (e.g. LG Electronics) and political organizations (e.g. ONU). + Locations: Expressions referring to specific geographical locations (e.g. Portugal). + Events: Expressions referring to competitions, conferences, workshops and similar events (e.g. 2\u00aa Confer\u00eancia Sobre o Acesso Livre ao Conhecimento). + Works: Expressions referring to movies, books, paintings and similar works (e.g. O Retrato de Dorian Gray). + Miscellaneous: Expressions referring to entities that can't be classified according to any of the previous subtypes (e.g. Boeing 747).;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1226;por;downloadable_files_count: 0;Portugal;NLX-Natural Language and Speech Group, University of Lisbon;http://lxner.di.fc.ul.pt",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "510c6fcb-88a2-54d7-85f4-a79a00f067f5",
-    "notes": [
-        "LX-NER is a Named Entity Recognizer for Portuguese. LX-NER takes a segment of Portuguese text and identifies, circumscribes and classifies the expressions for named entities it contains. Furthermore, each named entity receives a standard representation. It handles the following types of expressions: * Number-based expressions o Numbers: Expressions denoting numbers are marked as NUMEX. A list of subtypes is considered, allowing for a more refined classification of these expressions: + Arabic: Entities expressed by a sequence of digits, with the option of using a period to separate a string of 3 digits, counting from the right. + Decimal: Entities expressed by an arabic number followed by a decimal part, with a comma separating both parts. + Non-compliant: Entities expressed by digits, the period and comma symbols, organized in any possible way. All entities not covered by the previous 2 subtypes are included here. + Roman: Entities expressed by the roman letters [IVXLCDM], in either uppercase or lowercase, with the string of letters obeying the well-formedness rules for roman numerals. + Cardinal: Entities that are expressed by a full or partial word description of an arabic or decimal number. A full cardinal numeral is composed of words, while a partial cardinal number is a hybrid composed by words and arabic or decimal numbers. + Fraction: Entities expressed by arabic, decimal or cardinal numbers, and specific symbols or expressions representing division. + Magnitude class: Entities expressed by arabic, decimal or cardinal numbers together with expressions representing numerical magnitude. o Measures: Terms expressing measure values are marked as MEASEX. A list of subtypes is considered, allowing for a more refined classification of these expressions: + Currency: Expressions composed of an arabic, decimal or cardinal number followed by a word or expression representing a currency (e.g. libras). + Time: Expressions composed of an arabic, decimal or cardinal number followed by a word or expression representing a time measure (e.g. segundos). + Scientifc units: Expressions composed of an arabic, decimal or cardinal number followed by a word or expression representing a scientific unit (e.g. toneladas). o Time: Terms expressing time are marked as TIMEX. A list of subtypes is considered, allowing for a more refined classification of these expressions: + Date: Expressions representing a date, whose components can be a day of the week (e.g. Segunda-Feira), a day of the month (e.g. 27), a month (e.g. Novembro) or a year (e.g. 2006). + Time periods: Expressions made by arabic, roman or cardinal numbers and an explicit indication of a period of time concerning a specific year, decade or century. + Time of the day: Expressions with different formats, indicating a specific time of the day. o Addresses: Expressions conveying addresses are marked as ADDREX. A list of subparts is considered, allowing for a more refined classification of these expressions: + Global section: Expressions referring to the global position of a certain location (e.g. Rua Almeida Garrett). This address part is mandatory for an address to be recognized. + Local section: Expressions referring to a specific position within the global position (e.g. N\u00ba 17 - 7\u00ba Dto). + Zip code: Expressions referring to the zip code component of an address (e.g. 3654-548 Lisboa). * Name-based expressions o Names: Expressions conveying names are marked as NAMEX. A list of subtypes is considered, allowing for a more refined classification of these expressions: + Persons: Expressions conveying names of people, with the option of considering the job or social status of a person if present (e.g. Presidente Cavaco Silva). + Organizations: Expressions conveying names of companies (e.g. LG Electronics) and political organizations (e.g. ONU). + Locations: Expressions referring to specific geographical locations (e.g. Portugal). + Events: Expressions referring to competitions, conferences, workshops and similar events (e.g. 2\u00aa Confer\u00eancia Sobre o Acesso Livre ao Conhecimento). + Works: Expressions referring to movies, books, paintings and similar works (e.g. O Retrato de Dorian Gray). + Miscellaneous: Expressions referring to entities that can't be classified according to any of the previous subtypes (e.g. Boeing 747)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1226"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LX-NER"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5135d5cb-deac-5f4a-aa74-43c463992186.json b/oaitestdata/clarin-oai_dc/SET_1/json/5135d5cb-deac-5f4a-aa74-43c463992186.json
deleted file mode 100644
index bd30c6e2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5135d5cb-deac-5f4a-aa74-43c463992186.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "University of Tampere"
-    ],
-    "Contributor": [
-        "Mikhailov, Mikhail",
-        "Isolahti, Nina"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Finnish",
-        "Russian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1077",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1077"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1077",
-    "PublicationTimestamp": "2008-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2008"
-    ],
-    "Publisher": [
-        "University of Tampere"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Finland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1077;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Comparable Russian-Finnish corpus of juridical texts;Mikhailov, Mikhail;Isolahti, Nina;Juridical texts in Russian and Finnish arranged as a comparable text corpus;2008;corpus;http://hdl.handle.net/11372/LRT-1077;fin;rus;application/octet-stream;downloadable_files_count: 0;Finland;University of Tampere;https://mustikka.uta.fi/corpora",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5135d5cb-deac-5f4a-aa74-43c463992186",
-    "notes": [
-        "Juridical texts in Russian and Finnish arranged as a comparable text corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1077"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Comparable Russian-Finnish corpus of juridical texts"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5139514b-f8e9-50df-84e5-8cacd76a012b.json b/oaitestdata/clarin-oai_dc/SET_1/json/5139514b-f8e9-50df-84e5-8cacd76a012b.json
deleted file mode 100644
index 54bb055c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5139514b-f8e9-50df-84e5-8cacd76a012b.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5329",
-    "MetadataAccess": [
-        "oai:ota:oucs:5329"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Goldsmith, Oliver, 1730?-1774."
-    ],
-    "fulltext": "oai:ota:oucs:5329;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5329.xml;The haunch of venison: a poetical epistle to Lord Clare. By the late Dr. Goldsmith. With a head of the author, drawn by Henry Bunbury, Esq; and etched by Bretherton.;Goldsmith, Oliver, 1730?-1774.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5139514b-f8e9-50df-84e5-8cacd76a012b",
-    "oai_identifier": [
-        "oai:ota:oucs:5329"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The haunch of venison: a poetical epistle to Lord Clare. By the late Dr. Goldsmith. With a head of the author, drawn by Henry Bunbury, Esq; and etched by Bretherton."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5329.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/516be1b1-e83b-5b28-996b-c70e02f2afc0.json b/oaitestdata/clarin-oai_dc/SET_1/json/516be1b1-e83b-5b28-996b-c70e02f2afc0.json
deleted file mode 100644
index fb92c397..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/516be1b1-e83b-5b28-996b-c70e02f2afc0.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-997",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-997"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-997",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-997;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LAC Kilivila Corpus;Language and Cognition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-997;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI50292%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "516be1b1-e83b-5b28-996b-c70e02f2afc0",
-    "notes": [
-        "Language and Cognition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-997"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LAC Kilivila Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/516db657-58cb-571e-917d-f98e455bac60.json b/oaitestdata/clarin-oai_dc/SET_1/json/516db657-58cb-571e-917d-f98e455bac60.json
deleted file mode 100644
index 37987f35..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/516db657-58cb-571e-917d-f98e455bac60.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "University of Helsinki"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-741",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-741"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-741",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Helsinki"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-741;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Corpus of Early English Correspondence Sampler (CEECS);Personal correspondence from England between the years 1418-1680. Compiled as a tool for historical sociolinguistics.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-741;eng;text/plain;downloadable_files_count: 0;University of Helsinki;http://ota.ahds.ac.uk/headers/2461.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "516db657-58cb-571e-917d-f98e455bac60",
-    "notes": [
-        "Personal correspondence from England between the years 1418-1680. Compiled as a tool for historical sociolinguistics."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-741"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus of Early English Correspondence Sampler (CEECS)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/51a3374f-3913-56e2-84d2-811d4d38c8b2.json b/oaitestdata/clarin-oai_dc/SET_1/json/51a3374f-3913-56e2-84d2-811d4d38c8b2.json
deleted file mode 100644
index 965b3fda..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/51a3374f-3913-56e2-84d2-811d4d38c8b2.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=1482d61cbc8b11e1a404080027e73ea29d64920c024040c48eb9253f7ead371c",
-    "MetadataAccess": [
-        "1482d61cbc8b11e1a404080027e73ea29d64920c024040c48eb9253f7ead371c"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "1482d61cbc8b11e1a404080027e73ea29d64920c024040c48eb9253f7ead371c;2018-11-15T16:39:33Z;toolService;toolService:tool;UIMA/U-Compare GENIA Tokeniser (GENIA Tagger) ;Tokenisation is one of the functionalities of the GENIA tagger, which additionally outputs the base forms, part-of-speech tags, chunk tags, and named entity tags. The tagger is specifically tuned for biomedical text such as MEDLINE abstracts. \nThe tool is a UIMA component, which forms part of the in-built library of components provided with the U-Compare platform see separate META-SHARE record)  for building and evaluating text mining workflows.;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "51a3374f-3913-56e2-84d2-811d4d38c8b2",
-    "notes": [
-        "Tokenisation is one of the functionalities of the GENIA tagger, which additionally outputs the base forms, part-of-speech tags, chunk tags, and named entity tags. The tagger is specifically tuned for biomedical text such as MEDLINE abstracts. \nThe tool is a UIMA component, which forms part of the in-built library of components provided with the U-Compare platform see separate META-SHARE record)  for building and evaluating text mining workflows."
-    ],
-    "oai_identifier": [
-        "1482d61cbc8b11e1a404080027e73ea29d64920c024040c48eb9253f7ead371c"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "UIMA/U-Compare GENIA Tokeniser (GENIA Tagger) "
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/51adaef6-d1a2-5775-bbe0-f1b825663758.json b/oaitestdata/clarin-oai_dc/SET_1/json/51adaef6-d1a2-5775-bbe0-f1b825663758.json
deleted file mode 100644
index 6762a152..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/51adaef6-d1a2-5775-bbe0-f1b825663758.json
+++ /dev/null
@@ -1,49 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3399",
-    "MetadataAccess": [
-        "oai:ota:oucs:3399"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:3399;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3399.xml;Pigs' meat; or, lessons for the swinish multitude: Published in weekly penny numbers, collected by the poor man's advocate (an old veteran in the cause of freedom) in the course of his reading for more than twenty years. Intended to promote among the labouring part of mankind proper ideas of their situation, of their importance, and of their rights. And to convince them that their forlorn condition has not been entirely overlooked and forgotten, nor their just cause unpleaded, neither by their maker not by the best and most enlightened of men in all ages. [pt.2];text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "51adaef6-d1a2-5775-bbe0-f1b825663758",
-    "oai_identifier": [
-        "oai:ota:oucs:3399"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Pigs' meat; or, lessons for the swinish multitude: Published in weekly penny numbers, collected by the poor man's advocate (an old veteran in the cause of freedom) in the course of his reading for more than twenty years. Intended to promote among the labouring part of mankind proper ideas of their situation, of their importance, and of their rights. And to convince them that their forlorn condition has not been entirely overlooked and forgotten, nor their just cause unpleaded, neither by their maker not by the best and most enlightened of men in all ages. [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3399.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/51b55353-42e9-5319-954b-178a03f86312.json b/oaitestdata/clarin-oai_dc/SET_1/json/51b55353-42e9-5319-954b-178a03f86312.json
deleted file mode 100644
index 71cd0896..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/51b55353-42e9-5319-954b-178a03f86312.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Jakopin, Primoz"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-552",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-552"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-552",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Slovenia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-552;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Assigning lemmas and part-of-speech to wordform lists;Jakopin, Primoz;online service;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-552;slv;downloadable_files_count: 0;Slovenia;http://bos.zrc-sazu.si/dol_lem.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "51b55353-42e9-5319-954b-178a03f86312",
-    "notes": [
-        "online service"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-552"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Assigning lemmas and part-of-speech to wordform lists"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/51c80282-d19d-5b86-8950-9b99bb303e3f.json b/oaitestdata/clarin-oai_dc/SET_1/json/51c80282-d19d-5b86-8950-9b99bb303e3f.json
deleted file mode 100644
index ec610cd4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/51c80282-d19d-5b86-8950-9b99bb303e3f.json
+++ /dev/null
@@ -1,49 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5368",
-    "MetadataAccess": [
-        "oai:ota:oucs:5368"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:5368;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5368.xml;The poetical calendar: Containing a collection of scarce and valuable pieces of poetry: ... by the most eminent hands. Intended as a supplement to Mr. Dodsley's collection. Written and selected by Francis Fawkes, M. A. and William Woty. In twelve volumes. [pt.10];text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "51c80282-d19d-5b86-8950-9b99bb303e3f",
-    "oai_identifier": [
-        "oai:ota:oucs:5368"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The poetical calendar: Containing a collection of scarce and valuable pieces of poetry: ... by the most eminent hands. Intended as a supplement to Mr. Dodsley's collection. Written and selected by Francis Fawkes, M. A. and William Woty. In twelve volumes. [pt.10]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5368.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/51cbe46b-45ce-5ce6-995f-8112cc91f848.json b/oaitestdata/clarin-oai_dc/SET_1/json/51cbe46b-45ce-5ce6-995f-8112cc91f848.json
deleted file mode 100644
index a35e3068..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/51cbe46b-45ce-5ce6-995f-8112cc91f848.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4697",
-    "MetadataAccess": [
-        "oai:ota:oucs:4697"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Aikin, John, 1747-1822."
-    ],
-    "fulltext": "oai:ota:oucs:4697;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4697.xml;Miscellaneous pieces, in prose: by J. and A. L. Aikin.;Aikin, John, 1747-1822.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "51cbe46b-45ce-5ce6-995f-8112cc91f848",
-    "oai_identifier": [
-        "oai:ota:oucs:4697"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Miscellaneous pieces, in prose: by J. and A. L. Aikin."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4697.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/51ce35d8-3e3b-5f8b-b549-76e89d9830e7.json b/oaitestdata/clarin-oai_dc/SET_1/json/51ce35d8-3e3b-5f8b-b549-76e89d9830e7.json
deleted file mode 100644
index 348b4d9a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/51ce35d8-3e3b-5f8b-b549-76e89d9830e7.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5722",
-    "MetadataAccess": [
-        "oai:ota:oucs:5722"
-    ],
-    "PublicationTimestamp": "1623-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1623"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Shakespeare, William, 1564-1616"
-    ],
-    "fulltext": "oai:ota:oucs:5722;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/5722.xml;THE Two Gentlemen of Verona.;Shakespeare, William, 1564-1616;not after: 1623;text_and_corpus_linguistics;Plays -- England -- 16th century;Plays -- England -- 17th century;Comedies -- England -- 16th century;Comedies -- England -- 17th century;Tragedies -- England -- 16th century;Tragedies -- England -- 17th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "51ce35d8-3e3b-5f8b-b549-76e89d9830e7",
-    "oai_identifier": [
-        "oai:ota:oucs:5722"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        },
-        {
-            "name": "Comedies -- England -- th century"
-        },
-        {
-            "name": "Comedies -- England -- th century"
-        },
-        {
-            "name": "Tragedies -- England -- th century"
-        },
-        {
-            "name": "Tragedies -- England -- th century"
-        }
-    ],
-    "title": [
-        "THE Two Gentlemen of Verona."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5722.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/51d359ce-93ce-54b7-88c4-8c419136678b.json b/oaitestdata/clarin-oai_dc/SET_1/json/51d359ce-93ce-54b7-88c4-8c419136678b.json
deleted file mode 100644
index 0508fe39..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/51d359ce-93ce-54b7-88c4-8c419136678b.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5114",
-    "MetadataAccess": [
-        "oai:ota:oucs:5114"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Lewis, M. G. (Matthew Gregory), 1775-1818."
-    ],
-    "fulltext": "oai:ota:oucs:5114;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5114.xml;The castle spectre: a drama. In five acts. ... By M.G. Lewis, ...;Lewis, M. G. (Matthew Gregory), 1775-1818.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "51d359ce-93ce-54b7-88c4-8c419136678b",
-    "oai_identifier": [
-        "oai:ota:oucs:5114"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The castle spectre: a drama. In five acts. ... By M.G. Lewis, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5114.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/51f0761a-279d-54d7-8fe5-40e761b065c2.json b/oaitestdata/clarin-oai_dc/SET_1/json/51f0761a-279d-54d7-8fe5-40e761b065c2.json
deleted file mode 100644
index 3ee4e43b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/51f0761a-279d-54d7-8fe5-40e761b065c2.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Phonetics Laboratory, University of Oxford"
-    ],
-    "Contributor": [
-        "Kochanski, Dr G.",
-        "Coleman, Dr J."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-890",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-890"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-890",
-    "PublicationTimestamp": "2002-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2002"
-    ],
-    "Publisher": [
-        "Phonetics Laboratory, University of Oxford"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-890;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;IViE corpus: English Intonation in the British Isles;Coleman, Dr J.;Kochanski, Dr G.;36 hours of speech recordings of nine urban varieties of UK English, collected among 16-year-olds in secondary schools. Part of the corpus has been prosodically transcribed.;2002;corpus;http://hdl.handle.net/11372/LRT-890;eng;downloadable_files_count: 0;United Kingdom;Phonetics Laboratory, University of Oxford;http://www.phon.ox.ac.uk/IViE/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "51f0761a-279d-54d7-8fe5-40e761b065c2",
-    "notes": [
-        "36 hours of speech recordings of nine urban varieties of UK English, collected among 16-year-olds in secondary schools. Part of the corpus has been prosodically transcribed."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-890"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "IViE corpus: English Intonation in the British Isles"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/51f6025c-127b-56b0-b12c-f7c988d87a80.json b/oaitestdata/clarin-oai_dc/SET_1/json/51f6025c-127b-56b0-b12c-f7c988d87a80.json
deleted file mode 100644
index 9dd5b1c8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/51f6025c-127b-56b0-b12c-f7c988d87a80.json
+++ /dev/null
@@ -1,90 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 86",
-        "application/zip",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Multiple languages"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2898",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2898"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2898",
-    "PublicationTimestamp": "2018-11-15T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-2364"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Straka, Milan",
-        "Strakov\u00e1, Jana"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2898;2018-11-23T13:50:23Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Universal Dependencies 2.3 Models for UDPipe (2018-11-15);Straka, Milan;Strakov\u00e1, Jana;tokenizer;POS tagger;lemmatization;tagger;parser;dependency parser;Tokenizer, POS Tagger, Lemmatizer and Parser models for 84 treebanks of 56 languages of Universal Depenencies 2.3 Treebanks, created solely using UD 2.3 data (http://hdl.handle.net/11234/1-2895). The model documentation including performance can be found at http://ufal.mff.cuni.cz/udpipe/models#universal_dependencies_23_models .\r\n\r\nTo use these models, you need UDPipe binary version at least 1.2, which you can download from http://ufal.mff.cuni.cz/udpipe .\r\n\r\nIn addition to models itself, all additional data and value of hyperparameters used for training are available in the second archive, allowing reproducible training.;2018-11-15;toolService;http://hdl.handle.net/11234/1-2898;mul;http://hdl.handle.net/11234/1-2364;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;application/zip;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 86;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/udpipe",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "51f6025c-127b-56b0-b12c-f7c988d87a80",
-    "notes": [
-        "Tokenizer, POS Tagger, Lemmatizer and Parser models for 84 treebanks of 56 languages of Universal Depenencies 2.3 Treebanks, created solely using UD 2.3 data (http://hdl.handle.net/11234/1-2895). The model documentation including performance can be found at http://ufal.mff.cuni.cz/udpipe/models#universal_dependencies_23_models .\r\n\r\nTo use these models, you need UDPipe binary version at least 1.2, which you can download from http://ufal.mff.cuni.cz/udpipe .\r\n\r\nIn addition to models itself, all additional data and value of hyperparameters used for training are available in the second archive, allowing reproducible training."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2898"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "tokenizer"
-        },
-        {
-            "name": "POS tagger"
-        },
-        {
-            "name": "lemmatization"
-        },
-        {
-            "name": "tagger"
-        },
-        {
-            "name": "parser"
-        },
-        {
-            "name": "dependency parser"
-        }
-    ],
-    "title": [
-        "Universal Dependencies 2.3 Models for UDPipe (2018-11-15)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5202c8d5-2aa6-5268-ab72-43dceb3f4e6f.json b/oaitestdata/clarin-oai_dc/SET_1/json/5202c8d5-2aa6-5268-ab72-43dceb3f4e6f.json
deleted file mode 100644
index 6a6a271b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5202c8d5-2aa6-5268-ab72-43dceb3f4e6f.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/octet-stream",
-        "application/x-bzip2",
-        "application/zip",
-        "downloadable_files_count: 7",
-        "application/pdf"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48FB-F",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48FB-F"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-48FB-F",
-    "PublicationTimestamp": "2009-11-02T09:42:50Z",
-    "PublicationYear": [
-        "2009"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU General Public Licence, version 3",
-        "http://opensource.org/licenses/GPL-3.0",
-        "PUB"
-    ],
-    "author": [
-        "Ku\u010dera, Ond\u0159ej"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48FB-F;2018-07-02T22:05:53Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;STYX;Ku\u010dera, Ond\u0159ej;education;morphology;syntax;The STYX system is an electronic exercise book for practising Czech morphology and syntax consisting of more than 11, 000 sentences.;2009-11-02T09:42:50Z;toolService;http://hdl.handle.net/11858/00-097C-0000-0001-48FB-F;ces;GNU General Public Licence, version 3;http://opensource.org/licenses/GPL-3.0;PUB;application/pdf;application/pdf;application/octet-stream;application/x-bzip2;application/x-bzip2;application/zip;application/x-bzip2;text/plain; charset=utf-8;downloadable_files_count: 7;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/styx/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5202c8d5-2aa6-5268-ab72-43dceb3f4e6f",
-    "notes": [
-        "The STYX system is an electronic exercise book for practising Czech morphology and syntax consisting of more than 11, 000 sentences."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48FB-F"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "education"
-        },
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "syntax"
-        }
-    ],
-    "title": [
-        "STYX"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/523c5267-71e3-541a-ab95-42cbc2004eb8.json b/oaitestdata/clarin-oai_dc/SET_1/json/523c5267-71e3-541a-ab95-42cbc2004eb8.json
deleted file mode 100644
index 6b16cfc4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/523c5267-71e3-541a-ab95-42cbc2004eb8.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(2 files : ca. 44.5, 4.88 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "Middle High German (ca. 1050-1500)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1999",
-    "MetadataAccess": [
-        "oai:ota:oucs:1999"
-    ],
-    "PublicationTimestamp": "1217-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1217"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Wolfram, von Eschenbach, 12th cent"
-    ],
-    "fulltext": "oai:ota:oucs:1999;2018-03-05T12:24:09Z;http://ota.ox.ac.uk/headers/1999.xml;Titurel;Wolfram, von Eschenbach, 12th cent;1217;text_and_corpus_linguistics;Poems -- Germany -- 12th century;Epics -- Germany -- 12th century;gmh;Oxford Text Archive, University of Oxford;text/plain;(2 files : ca. 44.5, 4.88 KB);Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "523c5267-71e3-541a-ab95-42cbc2004eb8",
-    "oai_identifier": [
-        "oai:ota:oucs:1999"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- Germany -- th century"
-        },
-        {
-            "name": "Epics -- Germany -- th century"
-        }
-    ],
-    "title": [
-        "Titurel"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1999.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/52517ed8-37a6-5027-ac9b-78558cdf325e.json b/oaitestdata/clarin-oai_dc/SET_1/json/52517ed8-37a6-5027-ac9b-78558cdf325e.json
deleted file mode 100644
index e4c26a29..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/52517ed8-37a6-5027-ac9b-78558cdf325e.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "UW"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "downloadable_files_count: 10",
-        "application/vnd.oasis.opendocument.text",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/433",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/433"
-    ],
-    "PID": "http://hdl.handle.net/11321/433",
-    "PublicationTimestamp": "2017-10-12T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "UW"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Adamczyk, Mateusz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/433;2017-10-12T15:09:14Z;hdl_11321_3;hdl_11321_4;Korpusi\u0105tko_Mateusz_Adamczyk(warsztaty);Adamczyk, Mateusz;korpus;Ma\u0142y korpus;2017-10-12;corpus;http://hdl.handle.net/11321/433;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;text/plain;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;application/vnd.oasis.opendocument.text;text/plain;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;downloadable_files_count: 10;UW",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "52517ed8-37a6-5027-ac9b-78558cdf325e",
-    "notes": [
-        "Ma\u0142y korpus"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/433"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "korpus"
-        }
-    ],
-    "title": [
-        "Korpusi\u0105tko_Mateusz_Adamczyk(warsztaty)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5261203a-a5dc-57cd-940b-0dac04d24981.json b/oaitestdata/clarin-oai_dc/SET_1/json/5261203a-a5dc-57cd-940b-0dac04d24981.json
deleted file mode 100644
index f2635048..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5261203a-a5dc-57cd-940b-0dac04d24981.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=1a171f22719e11e5a2aa782bcb074135530d6c33185d42539d22846d41ff5ec2",
-    "MetadataAccess": [
-        "1a171f22719e11e5a2aa782bcb074135530d6c33185d42539d22846d41ff5ec2"
-    ],
-    "PublicationTimestamp": "2015-10-13T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "1a171f22719e11e5a2aa782bcb074135530d6c33185d42539d22846d41ff5ec2;2018-11-15T16:40:18Z;lexicalConceptualResource;lexicalConceptualResource:terminologicalResource;Time-sensitive inventory of medical terminology;This inventory contains a set of terms that are relevant to the study of medical history.\n\nThe inventory is organised as a set of \"heading terms\", belonging to one of seven different semantic categories, each of which is accompanied by a set of semantically-related terms. There are around 175,000 heading terms. \n\nThe nature of the semantic relationship holding between the heading term and each related term varies. A pair of related terms may, for example be synonyms of each other, one term may be more or less specific than the other, one may be a part of the other, one may be used in the treatment of the other, etc. \n;2015-10-13",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5261203a-a5dc-57cd-940b-0dac04d24981",
-    "notes": [
-        "This inventory contains a set of terms that are relevant to the study of medical history.\n\nThe inventory is organised as a set of \"heading terms\", belonging to one of seven different semantic categories, each of which is accompanied by a set of semantically-related terms. There are around 175,000 heading terms. \n\nThe nature of the semantic relationship holding between the heading term and each related term varies. A pair of related terms may, for example be synonyms of each other, one term may be more or less specific than the other, one may be a part of the other, one may be used in the treatment of the other, etc. \n"
-    ],
-    "oai_identifier": [
-        "1a171f22719e11e5a2aa782bcb074135530d6c33185d42539d22846d41ff5ec2"
-    ],
-    "oai_set": [
-        "lexicalConceptualResource",
-        "lexicalConceptualResource:terminologicalResource"
-    ],
-    "state": "active",
-    "title": [
-        "Time-sensitive inventory of medical terminology"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/526ef685-f4ef-5cf4-b351-e1239a652a4a.json b/oaitestdata/clarin-oai_dc/SET_1/json/526ef685-f4ef-5cf4-b351-e1239a652a4a.json
deleted file mode 100644
index a4d9d166..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/526ef685-f4ef-5cf4-b351-e1239a652a4a.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/247",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/247"
-    ],
-    "PID": "http://hdl.handle.net/11321/247",
-    "PublicationTimestamp": "2014-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Marci\u0144czuk, Micha\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/247;2016-02-23T11:54:32Z;hdl_11321_3;hdl_11321_4;NELexicon2;Marci\u0144czuk, Micha\u0142;dictionary;proper names;NELexicon2 to rozszerzona wersj\u0105 gazetteera nazw w\u0142asnych, kt\u00f3ra zawiera ponad 2,3 miliona unikalnych napis\u00f3w. NELexicon zosta\u0142 wzmogacony o nast\u0119puj\u0105ce zasoby:\r\n\r\n- zdrobnienia imion,\r\n- obcoj\u0119zyczne formy polskich imion,\r\n- nazwy wyci\u0105gni\u0119te z infobox\u00f3w polskiej Wikipedii,\r\n- formy odmiany nazw z infobox\u00f3w polskiej Wikipedii wyci\u0105gni\u0119te z link\u00f3w wewn\u0119trznych Wikipedii,\r\n- lista nazw rozpoznanych przez Liner2 z modelem 56 nam o liczbie wyst\u0105pie\u0144 r\u00f3wnej lub wi\u0119kszej ni\u017c 5. Jako, \u017ce nazwy zosta\u0142y rozpoznane automatycznie, to lista mo\u017ce zawiera\u0107 b\u0142\u0119dnie rozpoznane nazwy.\r\n- formy odmiany nazw wyci\u0105gni\u0119te z polskiego Wikis\u0142ownika.;2014-05-30;toolService;http://hdl.handle.net/11321/247;pol;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;Wroc\u0142aw University of Technology;http://clarin-pl.eu",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "526ef685-f4ef-5cf4-b351-e1239a652a4a",
-    "notes": [
-        "NELexicon2 to rozszerzona wersj\u0105 gazetteera nazw w\u0142asnych, kt\u00f3ra zawiera ponad 2,3 miliona unikalnych napis\u00f3w. NELexicon zosta\u0142 wzmogacony o nast\u0119puj\u0105ce zasoby:\r\n\r\n- zdrobnienia imion,\r\n- obcoj\u0119zyczne formy polskich imion,\r\n- nazwy wyci\u0105gni\u0119te z infobox\u00f3w polskiej Wikipedii,\r\n- formy odmiany nazw z infobox\u00f3w polskiej Wikipedii wyci\u0105gni\u0119te z link\u00f3w wewn\u0119trznych Wikipedii,\r\n- lista nazw rozpoznanych przez Liner2 z modelem 56 nam o liczbie wyst\u0105pie\u0144 r\u00f3wnej lub wi\u0119kszej ni\u017c 5. Jako, \u017ce nazwy zosta\u0142y rozpoznane automatycznie, to lista mo\u017ce zawiera\u0107 b\u0142\u0119dnie rozpoznane nazwy.\r\n- formy odmiany nazw wyci\u0105gni\u0119te z polskiego Wikis\u0142ownika."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/247"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "dictionary"
-        },
-        {
-            "name": "proper names"
-        }
-    ],
-    "title": [
-        "NELexicon2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/526f9aef-f801-54a4-a995-28ee5637558d.json b/oaitestdata/clarin-oai_dc/SET_1/json/526f9aef-f801-54a4-a995-28ee5637558d.json
deleted file mode 100644
index cb02d2db..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/526f9aef-f801-54a4-a995-28ee5637558d.json
+++ /dev/null
@@ -1,88 +0,0 @@
-{
-    "Contact": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-65",
-    "MetadataAccess": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-65"
-    ],
-    "PID": "http://hdl.handle.net/20.500.11752/ILC-65",
-    "PublicationTimestamp": "2016-10-19T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/211423"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Soria, Claudia",
-        "Toral, Antonio",
-        "Monachini, Monica"
-    ],
-    "fulltext": "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-65;2018-07-23T09:13:44Z;hdl_000-c0-111_38;hdl_000-c0-111_49;ItalWordNet Kyoto;Monachini, Monica;Soria, Claudia;Toral, Antonio;Italian;Lexical Semantics;WordNet;Lexicon;Lexical Markup Framework (LMF);This is an LMF compliant version of Italwordnet created from the original DB in 2008, and used for reasearch in the context of the Knowledge Yielding Ontologies for Transition-based Organisations (KYOTO) project.\r\nIt contains:\r\n49514 synsets\r\n67105 senses\r\n47141 lemmas\r\n131792 SynsetRelations;2016-10-19;lexicalConceptualResource;http://hdl.handle.net/20.500.11752/ILC-65;ita;info:eu-repo/grantAgreement/EC/FP7/211423;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/gzip;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 2;Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR);http://www.ilc.cnr.it/it/content/kyoto",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "526f9aef-f801-54a4-a995-28ee5637558d",
-    "notes": [
-        "This is an LMF compliant version of Italwordnet created from the original DB in 2008, and used for reasearch in the context of the Knowledge Yielding Ontologies for Transition-based Organisations (KYOTO) project.\r\nIt contains:\r\n49514 synsets\r\n67105 senses\r\n47141 lemmas\r\n131792 SynsetRelations"
-    ],
-    "oai_identifier": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-65"
-    ],
-    "oai_set": [
-        "hdl_000-c0-111_38",
-        "hdl_000-c0-111_49"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Italian"
-        },
-        {
-            "name": "Lexical Semantics"
-        },
-        {
-            "name": "WordNet"
-        },
-        {
-            "name": "Lexicon"
-        },
-        {
-            "name": "Lexical Markup Framework LMF"
-        }
-    ],
-    "title": [
-        "ItalWordNet Kyoto"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/52741ec6-3dd5-5d85-afbc-d80c30cf46b3.json b/oaitestdata/clarin-oai_dc/SET_1/json/52741ec6-3dd5-5d85-afbc-d80c30cf46b3.json
deleted file mode 100644
index 507ffaec..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/52741ec6-3dd5-5d85-afbc-d80c30cf46b3.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 445 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1610",
-    "MetadataAccess": [
-        "oai:ota:oucs:1610"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Lessing, Doris May, 1919-"
-    ],
-    "fulltext": "oai:ota:oucs:1610;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1610.xml;The summer before the dark;Lessing, Doris May, 1919-;default: 1976-01-01;text_and_corpus_linguistics;Fiction -- Great Britain -- 20th century;Novels -- Great Britain -- 20th century;eng;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 445 KB);Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "52741ec6-3dd5-5d85-afbc-d80c30cf46b3",
-    "oai_identifier": [
-        "oai:ota:oucs:1610"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- Great Britain -- th century"
-        },
-        {
-            "name": "Novels -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "The summer before the dark"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1610.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/527e3211-1f1e-53be-a490-cf59621fb6a4.json b/oaitestdata/clarin-oai_dc/SET_1/json/527e3211-1f1e-53be-a490-cf59621fb6a4.json
deleted file mode 100644
index d1e6c250..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/527e3211-1f1e-53be-a490-cf59621fb6a4.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Zarzycka"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 3",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/96",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/96"
-    ],
-    "PID": "http://hdl.handle.net/11321/96",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Zarzycka"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Zarzycka, Zarzycka"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/96;2015-04-08T13:41:07Z;hdl_11321_3;hdl_11321_4;MWE Zarzycka;Zarzycka, Zarzycka;Zarzycka;2015-04-08;corpus;http://hdl.handle.net/11321/96;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;text/plain; charset=utf-8;downloadable_files_count: 3;Zarzycka",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "527e3211-1f1e-53be-a490-cf59621fb6a4",
-    "notes": [
-        "Zarzycka"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/96"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Zarzycka"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/528b5db9-2089-5e97-968e-5b0633b44aed.json b/oaitestdata/clarin-oai_dc/SET_1/json/528b5db9-2089-5e97-968e-5b0633b44aed.json
deleted file mode 100644
index 687d3c4f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/528b5db9-2089-5e97-968e-5b0633b44aed.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Gilliver, Peter"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 481 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0530",
-    "MetadataAccess": [
-        "oai:ota:oucs:0530"
-    ],
-    "PublicationTimestamp": "1953-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1953"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Wain, John"
-    ],
-    "fulltext": "oai:ota:oucs:0530;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0530.xml;Hurry on down / John Wain;Wain, John;1953;text_and_corpus_linguistics;English fiction -- 20th century;eng;Oxford Text Archive, University of Oxford;Gilliver, Peter;text/plain;(1 file : ca. 481 KB);Text;Novels;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "528b5db9-2089-5e97-968e-5b0633b44aed",
-    "oai_identifier": [
-        "oai:ota:oucs:0530"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English fiction -- th century"
-        }
-    ],
-    "title": [
-        "Hurry on down / John Wain"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0530.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/528cbbfd-2384-5135-bbc7-dd010155272d.json b/oaitestdata/clarin-oai_dc/SET_1/json/528cbbfd-2384-5135-bbc7-dd010155272d.json
deleted file mode 100644
index 1dee0e06..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/528cbbfd-2384-5135-bbc7-dd010155272d.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4338",
-    "MetadataAccess": [
-        "oai:ota:oucs:4338"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Defoe, Daniel, 1661?-1731."
-    ],
-    "fulltext": "oai:ota:oucs:4338;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4338.xml;What if the Swedes should come?: With some thoughts about keeping the army on foot, whether they come or not.;Defoe, Daniel, 1661?-1731.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "528cbbfd-2384-5135-bbc7-dd010155272d",
-    "oai_identifier": [
-        "oai:ota:oucs:4338"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "What if the Swedes should come?: With some thoughts about keeping the army on foot, whether they come or not."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4338.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/52fa6c27-e1bf-56a5-8d1c-ec1625691afc.json b/oaitestdata/clarin-oai_dc/SET_1/json/52fa6c27-e1bf-56a5-8d1c-ec1625691afc.json
deleted file mode 100644
index 2aaf6fda..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/52fa6c27-e1bf-56a5-8d1c-ec1625691afc.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1953",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1953"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1953",
-    "PublicationTimestamp": "2016-12-22T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU General Public Licence, version 3",
-        "http://opensource.org/licenses/GPL-3.0",
-        "PUB"
-    ],
-    "author": [
-        "Straka, Milan",
-        "Mare\u010dek, David"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1953;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;LiStr: Linguistic Structure Induction Tookit;Mare\u010dek, David;Straka, Milan;parsing;unsupervised machine learning;machine translation;grammar induction;This toolkit comprises the tools and supporting scripts for unsupervised induction of dependency trees from raw texts or texts with already assigned part-of-speech tags. There are also scripts for simple machine translation based on unsupervised parsing and scripts for minimally supervised parsing into Universal-Dependencies style.;2016-12-22;toolService;http://hdl.handle.net/11234/1-1953;eng;GNU General Public Licence, version 3;http://opensource.org/licenses/GPL-3.0;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/listr",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "52fa6c27-e1bf-56a5-8d1c-ec1625691afc",
-    "notes": [
-        "This toolkit comprises the tools and supporting scripts for unsupervised induction of dependency trees from raw texts or texts with already assigned part-of-speech tags. There are also scripts for simple machine translation based on unsupervised parsing and scripts for minimally supervised parsing into Universal-Dependencies style."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1953"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parsing"
-        },
-        {
-            "name": "unsupervised machine learning"
-        },
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "grammar induction"
-        }
-    ],
-    "title": [
-        "LiStr: Linguistic Structure Induction Tookit"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/530d2da5-1ca4-504f-8dcb-2f8645b02556.json b/oaitestdata/clarin-oai_dc/SET_1/json/530d2da5-1ca4-504f-8dcb-2f8645b02556.json
deleted file mode 100644
index ad20f6a8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/530d2da5-1ca4-504f-8dcb-2f8645b02556.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5262",
-    "MetadataAccess": [
-        "oai:ota:oucs:5262"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Holcroft, Thomas, 1745-1809."
-    ],
-    "fulltext": "oai:ota:oucs:5262;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5262.xml;A narrative of facts, relating to a prosecution for high treason: including the address to the jury, which the court refused to hear: ... and the defence the author had prepared, if he had been brought to trial. By Thomas Holcroft.;Holcroft, Thomas, 1745-1809.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "530d2da5-1ca4-504f-8dcb-2f8645b02556",
-    "oai_identifier": [
-        "oai:ota:oucs:5262"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A narrative of facts, relating to a prosecution for high treason: including the address to the jury, which the court refused to hear: ... and the defence the author had prepared, if he had been brought to trial. By Thomas Holcroft."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5262.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/53199374-8a85-5f73-a581-d3ef46d93f81.json b/oaitestdata/clarin-oai_dc/SET_1/json/53199374-8a85-5f73-a581-d3ef46d93f81.json
deleted file mode 100644
index df788022..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/53199374-8a85-5f73-a581-d3ef46d93f81.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Golluscio, Dr. Luc\u00eda"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-681",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-681"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-681",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Code of conduct"
-    ],
-    "SpatialCoverage": [
-        "Argentina"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-681;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Chaco languages corpus;Golluscio, Dr. Luc\u00eda;Documentation of the Chaco project (DoBeS project);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-681;Code of conduct;downloadable_files_count: 0;Argentina;http://corpus1.mpi.nl/ds/imdi_browser/?openpath=MPI79070%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "53199374-8a85-5f73-a581-d3ef46d93f81",
-    "notes": [
-        "Documentation of the Chaco project (DoBeS project)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-681"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Chaco languages corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5370aaff-62c3-5fa8-a17b-0092286c7d10.json b/oaitestdata/clarin-oai_dc/SET_1/json/5370aaff-62c3-5fa8-a17b-0092286c7d10.json
deleted file mode 100644
index 2675d9a9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5370aaff-62c3-5fa8-a17b-0092286c7d10.json
+++ /dev/null
@@ -1,211 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Arabic",
-        "Bulgarian",
-        "Czech",
-        "Catalan",
-        "Church Slavic",
-        "Danish",
-        "German",
-        "Modern Greek (1453-)",
-        "English",
-        "Spanish",
-        "Estonian",
-        "Basque",
-        "Persian",
-        "Finnish",
-        "French",
-        "Irish",
-        "Galician",
-        "Gothic",
-        "Ancient Greek (to 1453)",
-        "Hebrew",
-        "Hindi",
-        "Croatian",
-        "Upper Sorbian",
-        "Hungarian",
-        "Indonesian",
-        "Italian",
-        "Japanese",
-        "Kazakh",
-        "Korean",
-        "Latin",
-        "Latvian",
-        "Dutch",
-        "Norwegian",
-        "Polish",
-        "Portuguese",
-        "Romanian",
-        "Russian",
-        "Slovak",
-        "Slovenian",
-        "Northern Sami",
-        "Swedish",
-        "Turkish",
-        "Uighur",
-        "Ukrainian",
-        "Urdu",
-        "Vietnamese",
-        "Chinese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2424",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2424"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2424",
-    "PublicationTimestamp": "2017-09-27T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Licence Universal Dependencies v2.0",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-2.0",
-        "PUB"
-    ],
-    "author": [
-        "Park, Jungyeul",
-        "Manning, Christopher",
-        "\u00d6nder, Berkay Furkan",
-        "Gamallo, Pablo",
-        "G\u00f3mez-Rodr\u00edguez, Carlos",
-        "Sarkar, Sudeshna",
-        "Yu, Xiang",
-        "Kuhn, Jonas",
-        "Cheng, Yao",
-        "Muraoka, Masayasu",
-        "Wisniewski, Guillaume",
-        "Sagot, Beno\u00eet",
-        "Che, Wanxiang",
-        "Luotolahti, Juhani",
-        "Guo, Jiang",
-        "Yoshikawa, Katsumasa",
-        "Qian, Xian",
-        "Tufi\u015f, Dan",
-        "Potthast, Martin",
-        "Vilares, David",
-        "Yvon, Fran\u00e7ois",
-        "Basirat, Ali",
-        "Matsumoto, Yuji",
-        "Seddah, Djam\u00e9",
-        "Hornby, Ryan",
-        "Yuret, Deniz",
-        "Ji, Tao",
-        "Asadullah, Munshi",
-        "Zhang, Xingxing",
-        "Schill, Erik",
-        "Dras, Mark",
-        "Wang, Yuxuan",
-        "Aufrant, Lauriane",
-        "Henderson, James",
-        "Noji, Hiroshi",
-        "Kuan, Yu",
-        "de Lhoneux, Miryam",
-        "Goldberg, Yoav",
-        "Lan, Man",
-        "Wu, Yuanbin",
-        "Dozat, Timothy",
-        "Lopez, Adam",
-        "Zaffar, Affan",
-        "Vania, Clara",
-        "Nivre, Joakim",
-        "Zeman, Daniel",
-        "Manabe, Hitoshi",
-        "Hinrichs, Erhard",
-        "Falenska, Agnieszka",
-        "Taylor, Clark",
-        "K\u0131rnap, \u00d6mer",
-        "Merlo, Paola",
-        "Heinecke, Johannes",
-        "Ginter, Filip",
-        "Stymne, Sara",
-        "Liu, Yang",
-        "Popel, Martin",
-        "Wu, Felix G.",
-        "Garcia, Marcos",
-        "Straka, Milan",
-        "Qi, Peng",
-        "Tsarfaty, Reut",
-        "Johnson, Mark",
-        "Moor, Christophe",
-        "Sato, Motoki",
-        "Teng, Dechuan",
-        "Lim, Kyungtae",
-        "More, Amir",
-        "Poibeau, Thierry",
-        "Zhao, Hai",
-        "Cakici, Ruket",
-        "Kiperwasser, Eliyahu",
-        "Sofroniev, Pavel",
-        "Liu, Ting",
-        "Boro\u015f, Tiberiu",
-        "Shi, Tianze",
-        "Azizoglu, Heval",
-        "Bj\u00f6rkelund, Anders",
-        "Wang, Haozhou",
-        "Zhao, Huaipeng",
-        "Das, Ayan",
-        "Shao, Yan",
-        "Dumitrescu, Stefan Daniel",
-        "de la Clergerie, Eric",
-        "Zheng, Bo",
-        "Kanerva, Jenna",
-        "Chen, Xilun",
-        "Zhang, Zhisong",
-        "Wang, Hao",
-        "Strakov\u00e1, Jana",
-        "Akku\u015f, Burak Kerim",
-        "Kanayama, Hiroshi",
-        "Nguyen, Dat Quoc"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2424;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;CoNLL 2017 Shared Task System Outputs;Zeman, Daniel;Potthast, Martin;Straka, Milan;Popel, Martin;Dozat, Timothy;Qi, Peng;Manning, Christopher;Shi, Tianze;Wu, Felix G.;Chen, Xilun;Cheng, Yao;Bj\u00f6rkelund, Anders;Falenska, Agnieszka;Yu, Xiang;Kuhn, Jonas;Che, Wanxiang;Guo, Jiang;Wang, Yuxuan;Zheng, Bo;Zhao, Huaipeng;Liu, Yang;Teng, Dechuan;Liu, Ting;Lim, Kyungtae;Poibeau, Thierry;Sato, Motoki;Manabe, Hitoshi;Noji, Hiroshi;Matsumoto, Yuji;K\u0131rnap, \u00d6mer;\u00d6nder, Berkay Furkan;Yuret, Deniz;Strakov\u00e1, Jana;Vania, Clara;Zhang, Xingxing;Lopez, Adam;Heinecke, Johannes;Asadullah, Munshi;Kanerva, Jenna;Luotolahti, Juhani;Ginter, Filip;Kuan, Yu;Sofroniev, Pavel;Schill, Erik;Hinrichs, Erhard;Nguyen, Dat Quoc;Dras, Mark;Johnson, Mark;Qian, Xian;Liu, Yang;Vilares, David;G\u00f3mez-Rodr\u00edguez, Carlos;Aufrant, Lauriane;Wisniewski, Guillaume;Yvon, Fran\u00e7ois;Dumitrescu, Stefan Daniel;Boro\u015f, Tiberiu;Tufi\u015f, Dan;Das, Ayan;Zaffar, Affan;Sarkar, Sudeshna;Wang, Hao;Zhao, Hai;Zhang, Zhisong;Hornby, Ryan;Taylor, Clark;Park, Jungyeul;de Lhoneux, Miryam;Shao, Yan;Basirat, Ali;Kiperwasser, Eliyahu;Stymne, Sara;Goldberg, Yoav;Nivre, Joakim;Akku\u015f, Burak Kerim;Azizoglu, Heval;Cakici, Ruket;Moor, Christophe;Merlo, Paola;Henderson, James;Wang, Haozhou;Ji, Tao;Wu, Yuanbin;Lan, Man;de la Clergerie, Eric;Sagot, Beno\u00eet;Seddah, Djam\u00e9;More, Amir;Tsarfaty, Reut;Kanayama, Hiroshi;Muraoka, Masayasu;Yoshikawa, Katsumasa;Garcia, Marcos;Gamallo, Pablo;dependency parser;parsebank;This package contains the system outputs from the CoNLL 2017 Shared Task in Multilingual Parsing from Raw Text to Universal Dependencies.;2017-09-27;corpus;http://hdl.handle.net/11234/1-2424;ara;bul;bxr;ces;cat;chu;dan;deu;ell;eng;spa;est;eus;fas;fin;fra;gle;glg;got;grc;heb;hin;hrv;hsb;hun;ind;ita;jpn;kaz;kmr;kor;lat;lav;nld;nor;pol;por;ron;rus;slk;slv;sme;swe;tur;uig;ukr;urd;vie;zho;Licence Universal Dependencies v2.0;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-2.0;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://universaldependencies.org/conll17/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5370aaff-62c3-5fa8-a17b-0092286c7d10",
-    "notes": [
-        "This package contains the system outputs from the CoNLL 2017 Shared Task in Multilingual Parsing from Raw Text to Universal Dependencies."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2424"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "dependency parser"
-        },
-        {
-            "name": "parsebank"
-        }
-    ],
-    "title": [
-        "CoNLL 2017 Shared Task System Outputs"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/537f4623-7f61-57a0-8094-55cccc3a9077.json b/oaitestdata/clarin-oai_dc/SET_1/json/537f4623-7f61-57a0-8094-55cccc3a9077.json
deleted file mode 100644
index b0a3ffc0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/537f4623-7f61-57a0-8094-55cccc3a9077.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology",
-        "University of Lodz"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/pdf"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/547",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/547"
-    ],
-    "PID": "http://hdl.handle.net/11321/547",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology",
-        "University of Lodz"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "P\u0119zik, Piotr"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/547;2018-07-23T11:54:05Z;hdl_11321_3;hdl_11321_4;PELCRA EMI corpus;P\u0119zik, Piotr;spoaken data;casual interviews;Scotland;The corpus comprises open interviews with Polish people residing in Scotland.;2018;corpus;http://hdl.handle.net/11321/547;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;application/pdf;downloadable_files_count: 1;University of Lodz;Wroc\u0142aw University of Technology;http://spokes.clarin-pl.eu/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "537f4623-7f61-57a0-8094-55cccc3a9077",
-    "notes": [
-        "The corpus comprises open interviews with Polish people residing in Scotland."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/547"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "spoaken data"
-        },
-        {
-            "name": "casual interviews"
-        },
-        {
-            "name": "Scotland"
-        }
-    ],
-    "title": [
-        "PELCRA EMI corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/538356cf-8376-566e-8482-f660418d23e3.json b/oaitestdata/clarin-oai_dc/SET_1/json/538356cf-8376-566e-8482-f660418d23e3.json
deleted file mode 100644
index 75e4fa7d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/538356cf-8376-566e-8482-f660418d23e3.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3963",
-    "MetadataAccess": [
-        "oai:ota:oucs:3963"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hawkins, John, Sir, 1719-1789."
-    ],
-    "fulltext": "oai:ota:oucs:3963;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3963.xml;A dissertation on the armorial ensigns of the County of Middlesex, and of the Abbey and City of Westminster. By Sir John Hawkins, Knt.;Hawkins, John, Sir, 1719-1789.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "538356cf-8376-566e-8482-f660418d23e3",
-    "oai_identifier": [
-        "oai:ota:oucs:3963"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A dissertation on the armorial ensigns of the County of Middlesex, and of the Abbey and City of Westminster. By Sir John Hawkins, Knt."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3963.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/539d155b-b914-5280-9400-7769fbd264f2.json b/oaitestdata/clarin-oai_dc/SET_1/json/539d155b-b914-5280-9400-7769fbd264f2.json
deleted file mode 100644
index 53ddbd88..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/539d155b-b914-5280-9400-7769fbd264f2.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "McDonald, Peter"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 327 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0595",
-    "MetadataAccess": [
-        "oai:ota:oucs:0595"
-    ],
-    "PublicationTimestamp": "1250-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1250"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Ancient religious texts"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:0595;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0595.xml;Book of the dead;The book of the dead;1250 BCE;text_and_corpus_linguistics;Fiction;Myths and legends;eng;Books of the dead are Egyptian funerary texts and consist of spells, charms, and formulas to be said by the deceased during their journey to the Underworld. Such texts were originally inscribed in stone but later were written on papyrus and often contained illustrations. They were commissioned by the deceased before their death ;Oxford Text Archive, University of Oxford;McDonald, Peter;text/plain;(1 file : ca. 327 KB);Text;Ancient religious texts;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "539d155b-b914-5280-9400-7769fbd264f2",
-    "notes": [
-        "Books of the dead are Egyptian funerary texts and consist of spells, charms, and formulas to be said by the deceased during their journey to the Underworld. Such texts were originally inscribed in stone but later were written on papyrus and often contained illustrations. They were commissioned by the deceased before their death "
-    ],
-    "oai_identifier": [
-        "oai:ota:oucs:0595"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction"
-        },
-        {
-            "name": "Myths legends"
-        }
-    ],
-    "title": [
-        "Book of the dead",
-        "The book of the dead"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0595.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/53a7ce20-bd87-54f6-aef6-ef009b8316be.json b/oaitestdata/clarin-oai_dc/SET_1/json/53a7ce20-bd87-54f6-aef6-ef009b8316be.json
deleted file mode 100644
index 41e53149..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/53a7ce20-bd87-54f6-aef6-ef009b8316be.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "s.n."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-165752",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-165752"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CED-2",
-    "PublicationTimestamp": "1790-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1790"
-    ],
-    "Publisher": [
-        "s.n."
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/165752",
-        "oai:jbc.bj.uj.edu.pl:publication:174208"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1701/1800"
-    ],
-    "TempCoverageBegin": 53662478399,
-    "TempCoverageEnd": 53662478399,
-    "TemporalCoverage": " point in time : 1701-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1701-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1701-07-01T11:59:59Z",
-    "author": [
-        "Jezierski, Franciszek Salezy (1740-1791)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-165752;2019-03-01T10:51:38Z;O Bez-Krolewiach W Polszcze Y O Wybieraniu Krolow pocz\u0105wszy od \u015bmierci Zygmunta Augusta Jagie\u0142\u0142y a\u017c do Naszych czas\u00f3w : Dzie\u0142o w tera\u017anieyszych okoliczno\u015bciach do wiadomo\u015bci przydatne;Jezierski, Franciszek Salezy (1740-1791);starodruki 18\u00a0w.;http://www.bj.uj.edu.pl/uj/katalog?search=KEYWORD&function=CARDSCR&u1=12&t1=xx001935361 Wsp\u00f3\u0142opr. z: BJ St. Dr. 390536 I;s.n.;1790;starodruk;application/xml;clarind-uds:poldilemma-165752;hdl:11858/00-246C-0000-0023-8CED-2;Biblioteka Jagiello\u0144ska, BJ St. Dr. 11095 I;pol;http://jbc.bj.uj.edu.pl/Content/165752;oai:jbc.bj.uj.edu.pl:publication:174208;1701/1800;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "53a7ce20-bd87-54f6-aef6-ef009b8316be",
-    "notes": [
-        "http://www.bj.uj.edu.pl/uj/katalog?search=KEYWORD&function=CARDSCR&u1=12&t1=xx001935361 Wsp\u00f3\u0142opr. z: BJ St. Dr. 390536 I"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-165752"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "O Bez-Krolewiach W Polszcze Y O Wybieraniu Krolow pocz\u0105wszy od \u015bmierci Zygmunta Augusta Jagie\u0142\u0142y a\u017c do Naszych czas\u00f3w : Dzie\u0142o w tera\u017anieyszych okoliczno\u015bciach do wiadomo\u015bci przydatne"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/53c4519c-6a72-5589-9100-bc4865e4cc69.json b/oaitestdata/clarin-oai_dc/SET_1/json/53c4519c-6a72-5589-9100-bc4865e4cc69.json
deleted file mode 100644
index 3a65014d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/53c4519c-6a72-5589-9100-bc4865e4cc69.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3830",
-    "MetadataAccess": [
-        "oai:ota:oucs:3830"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Murphy, Arthur, 1727-1805."
-    ],
-    "fulltext": "oai:ota:oucs:3830;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3830.xml;All in the wrong: A comedy. As it is acted at the Theatre-Royal in Drury-Lane. By Mr. Murphy.;Murphy, Arthur, 1727-1805.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "53c4519c-6a72-5589-9100-bc4865e4cc69",
-    "oai_identifier": [
-        "oai:ota:oucs:3830"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "All in the wrong: A comedy. As it is acted at the Theatre-Royal in Drury-Lane. By Mr. Murphy."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3830.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/53c5c6bc-ffbc-5650-9862-93a7e6e6d31a.json b/oaitestdata/clarin-oai_dc/SET_1/json/53c5c6bc-ffbc-5650-9862-93a7e6e6d31a.json
deleted file mode 100644
index 60f1cc3e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/53c5c6bc-ffbc-5650-9862-93a7e6e6d31a.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4173",
-    "MetadataAccess": [
-        "oai:ota:oucs:4173"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dow, Alexander, d. 1779."
-    ],
-    "fulltext": "oai:ota:oucs:4173;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4173.xml;Sethona: A tragedy. As it is performed at the Theatre-Royal in Drury-Lane.;Dow, Alexander, d. 1779.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "53c5c6bc-ffbc-5650-9862-93a7e6e6d31a",
-    "oai_identifier": [
-        "oai:ota:oucs:4173"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Sethona: A tragedy. As it is performed at the Theatre-Royal in Drury-Lane."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4173.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/53daacd0-4f3f-5f5d-a7e2-35571a08b624.json b/oaitestdata/clarin-oai_dc/SET_1/json/53daacd0-4f3f-5f5d-a7e2-35571a08b624.json
deleted file mode 100644
index 90364d41..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/53daacd0-4f3f-5f5d-a7e2-35571a08b624.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/octet-stream",
-        "text/plain",
-        "application/zip",
-        "downloadable_files_count: 4",
-        "application/pdf"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/265",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/265"
-    ],
-    "PID": "http://hdl.handle.net/11321/265",
-    "PublicationTimestamp": "2016-05-29T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "BSD 2 Clause",
-        "https://opensource.org/licenses/BSD-2-Clause",
-        "PUB"
-    ],
-    "author": [
-        "Rychlik, Piotr"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/265;2016-05-29T08:24:31Z;hdl_11321_3;hdl_11321_4;tokenizer;Rychlik, Piotr;tokenization;Tokenizer is a tool with wich one can design dedicated tokenizers for texts from some domain of interest.;2016-05-29;toolService;http://hdl.handle.net/11321/265;pol;BSD 2 Clause;https://opensource.org/licenses/BSD-2-Clause;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;text/plain;application/zip;application/octet-stream;application/pdf;downloadable_files_count: 4;Institute of Computer Science, Polish Academy of Sciences",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "53daacd0-4f3f-5f5d-a7e2-35571a08b624",
-    "notes": [
-        "Tokenizer is a tool with wich one can design dedicated tokenizers for texts from some domain of interest."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/265"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "tokenization"
-        }
-    ],
-    "title": [
-        "tokenizer"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/53e5e913-9d88-5980-8572-34e2205e28c3.json b/oaitestdata/clarin-oai_dc/SET_1/json/53e5e913-9d88-5980-8572-34e2205e28c3.json
deleted file mode 100644
index 8dcf4b1e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/53e5e913-9d88-5980-8572-34e2205e28c3.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-994",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-994"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-994",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-994;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LAC English Corpus;Language and Cognition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-994;eng;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI31778%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "53e5e913-9d88-5980-8572-34e2205e28c3",
-    "notes": [
-        "Language and Cognition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-994"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LAC English Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/53ed9de4-0332-59c0-bd9a-0a2c0b059b16.json b/oaitestdata/clarin-oai_dc/SET_1/json/53ed9de4-0332-59c0-bd9a-0a2c0b059b16.json
deleted file mode 100644
index 5087813b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/53ed9de4-0332-59c0-bd9a-0a2c0b059b16.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Wilson, David"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(2 files : ca. 463 KB)",
-        "text/plain"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1718",
-    "MetadataAccess": [
-        "oai:ota:oucs:1718"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Joyce, James, 1882-1941"
-    ],
-    "fulltext": "oai:ota:oucs:1718;2018-02-16T10:42:06Z;http://ota.ox.ac.uk/headers/1718.xml;Portrait of the artist as a young man;A portrait of the artist as a young man / James Joyce;Joyce, James, 1882-1941;text_and_corpus_linguistics;Irish literature -- 20th century;Oxford Text Archive, University of Oxford;Wilson, David;text/plain;(2 files : ca. 463 KB);Text;Novels;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "53ed9de4-0332-59c0-bd9a-0a2c0b059b16",
-    "oai_identifier": [
-        "oai:ota:oucs:1718"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Irish literature -- th century"
-        }
-    ],
-    "title": [
-        "Portrait of the artist as a young man",
-        "A portrait of the artist as a young man / James Joyce"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1718.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/54297a31-021f-54bf-8db2-e1157008bd5e.json b/oaitestdata/clarin-oai_dc/SET_1/json/54297a31-021f-54bf-8db2-e1157008bd5e.json
deleted file mode 100644
index 77543922..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/54297a31-021f-54bf-8db2-e1157008bd5e.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Masaryk University, NLP Centre"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Somali"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2591",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2591"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2591",
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Masaryk University, NLP Centre"
-    ],
-    "RelatedIdentifier": [
-        "https://www.sketchengine.co.uk/wp-content/uploads/2015/05/Corpus_Factory_2010.pdf",
-        "http://habit-project.eu/wiki/SomaliCorpus"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "NLP Centre Web Corpus License",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/license-NLPC-WeC",
-        "ACA"
-    ],
-    "author": [
-        "Suchomel, V\u00edt",
-        "Rychl\u00fd, Pavel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2591;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Somali Web Corpus;Suchomel, V\u00edt;Rychl\u00fd, Pavel;text corpora;Ethiopian languages;web corpora;under-resourced languages;Somali;Somali web corpus. Crawled by SpiderLing in January 2016. Encoded in UTF-8, cleaned, deduplicated.;2016;corpus;http://hdl.handle.net/11234/1-2591;som;https://www.sketchengine.co.uk/wp-content/uploads/2015/05/Corpus_Factory_2010.pdf;http://habit-project.eu/wiki/SomaliCorpus;NLP Centre Web Corpus License;https://lindat.mff.cuni.cz/repository/xmlui/page/license-NLPC-WeC;ACA;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Masaryk University, NLP Centre;http://habit-project.eu/wiki/HabitSystemFinal",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "54297a31-021f-54bf-8db2-e1157008bd5e",
-    "notes": [
-        "Somali web corpus. Crawled by SpiderLing in January 2016. Encoded in UTF-8, cleaned, deduplicated."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2591"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "text corpora"
-        },
-        {
-            "name": "Ethiopian languages"
-        },
-        {
-            "name": "web corpora"
-        },
-        {
-            "name": "under-resourced languages"
-        },
-        {
-            "name": "Somali"
-        }
-    ],
-    "title": [
-        "Somali Web Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5433d8ae-e30b-5c5e-bd71-cf2f50624318.json b/oaitestdata/clarin-oai_dc/SET_1/json/5433d8ae-e30b-5c5e-bd71-cf2f50624318.json
deleted file mode 100644
index 8cac9714..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5433d8ae-e30b-5c5e-bd71-cf2f50624318.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4078",
-    "MetadataAccess": [
-        "oai:ota:oucs:4078"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Garrick, David, 1717-1779."
-    ],
-    "fulltext": "oai:ota:oucs:4078;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4078.xml;An ode on the death of Mr. Pelham;Garrick, David, 1717-1779.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5433d8ae-e30b-5c5e-bd71-cf2f50624318",
-    "oai_identifier": [
-        "oai:ota:oucs:4078"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An ode on the death of Mr. Pelham"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4078.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/54353a09-20e1-5339-9838-5bae4bdda8f3.json b/oaitestdata/clarin-oai_dc/SET_1/json/54353a09-20e1-5339-9838-5bae4bdda8f3.json
deleted file mode 100644
index 1216dd64..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/54353a09-20e1-5339-9838-5bae4bdda8f3.json
+++ /dev/null
@@ -1,92 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 11",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Czech",
-        "Slovak",
-        "Slovenian",
-        "Croatian",
-        "Danish",
-        "Swedish",
-        "Norwegian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1970",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1970"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1970",
-    "PublicationTimestamp": "2017-01-28T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/H2020/644402",
-        "http://web.science.mq.edu.au/~smalmasi/vardial4/pdf/VarDial26.pdf"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU General Public License 2 or later (GPL-2.0)",
-        "http://opensource.org/licenses/GPL-2.0",
-        "PUB"
-    ],
-    "author": [
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "Zeman, Daniel",
-        "Mare\u010dek, David",
-        "Rosa, Rudolf"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1970;2017-11-09T14:21:55Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Slavic Forest, Norwegian Wood (scripts);Rosa, Rudolf;Zeman, Daniel;Mare\u010dek, David;\u017dabokrtsk\u00fd, Zden\u011bk;parsing;dependency parser;universal dependencies;cross-lingual parsing;Tools and scripts used to create the cross-lingual parsing models submitted to VarDial 2017 shared task (https://bitbucket.org/hy-crossNLP/vardial2017), as described in the linked paper. The trained UDPipe models themselves are published in a separate submission (https://lindat.mff.cuni.cz/repository/xmlui/handle/11234/1-1971).\r\n\r\nFor each source (SS, e.g. sl) and target (TT, e.g. hr) language,\r\nyou need to add the following into this directory:\r\n\r\n- treebanks (Universal Dependencies v1.4):\r\nSS-ud-train.conllu\r\nTT-ud-predPoS-dev.conllu\r\n\r\n- parallel data (OpenSubtitles from Opus):\r\nOpenSubtitles2016.SS-TT.SS\r\nOpenSubtitles2016.SS-TT.TT\r\n!!! If they are originally called ...TT-SS... instead of ...SS-TT...,\r\nyou need to symlink them (or move, or copy) !!!\r\n\r\n- target tagging model\r\nTT.tagger.udpipe\r\n\r\nAll of these can be obtained from https://bitbucket.org/hy-crossNLP/vardial2017\r\n\r\n\r\nYou also need to have:\r\n- Bash\r\n- Perl 5\r\n- Python 3\r\n- word2vec (https://code.google.com/archive/p/word2vec/); we used rev 41 from 15th Sep 2014\r\n- udpipe (https://github.com/ufal/udpipe); we used commit 3e65d69 from 3rd Jan 2017\r\n- Treex (https://github.com/ufal/treex); we used commit d27ee8a from 21st Dec 2016\r\n\r\n\r\nThe most basic setup is the sl-hr one (train_sl-hr.sh):\r\n- normalization of deprels\r\n- 1:1 word-alignment of parallel data with Monolingual Greedy Aligner\r\n- simple word-by-word translation of source treebank\r\n- pre-training of target word embeddings\r\n- simplification of morpho feats (use only Case)\r\n- and finally, training and evaluating the parser\r\n\r\nBoth da+sv-no (train_ds-no.sh) and cs-sk (train_cs-sk.sh) add some cross-tagging, which seems to be useful only in\r\nspecific cases (see paper for details).\r\nMoreover, cs-sk also adds more morpho features, selecting those that\r\nseem to be very often shared in parallel data.\r\n\r\nThe whole pipeline takes tens of hours to run, and uses several GB of RAM, so make sure to use a powerful computer.;2017-01-28;toolService;http://hdl.handle.net/11234/1-1970;ces;slk;slv;hrv;dan;swe;nor;info:eu-repo/grantAgreement/EC/H2020/644402;http://web.science.mq.edu.au/~smalmasi/vardial4/pdf/VarDial26.pdf;GNU General Public License 2 or later (GPL-2.0);http://opensource.org/licenses/GPL-2.0;PUB;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 11;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "54353a09-20e1-5339-9838-5bae4bdda8f3",
-    "notes": [
-        "Tools and scripts used to create the cross-lingual parsing models submitted to VarDial 2017 shared task (https://bitbucket.org/hy-crossNLP/vardial2017), as described in the linked paper. The trained UDPipe models themselves are published in a separate submission (https://lindat.mff.cuni.cz/repository/xmlui/handle/11234/1-1971).\r\n\r\nFor each source (SS, e.g. sl) and target (TT, e.g. hr) language,\r\nyou need to add the following into this directory:\r\n\r\n- treebanks (Universal Dependencies v1.4):\r\nSS-ud-train.conllu\r\nTT-ud-predPoS-dev.conllu\r\n\r\n- parallel data (OpenSubtitles from Opus):\r\nOpenSubtitles2016.SS-TT.SS\r\nOpenSubtitles2016.SS-TT.TT\r\n!!! If they are originally called ...TT-SS... instead of ...SS-TT...,\r\nyou need to symlink them (or move, or copy) !!!\r\n\r\n- target tagging model\r\nTT.tagger.udpipe\r\n\r\nAll of these can be obtained from https://bitbucket.org/hy-crossNLP/vardial2017\r\n\r\n\r\nYou also need to have:\r\n- Bash\r\n- Perl 5\r\n- Python 3\r\n- word2vec (https://code.google.com/archive/p/word2vec/); we used rev 41 from 15th Sep 2014\r\n- udpipe (https://github.com/ufal/udpipe); we used commit 3e65d69 from 3rd Jan 2017\r\n- Treex (https://github.com/ufal/treex); we used commit d27ee8a from 21st Dec 2016\r\n\r\n\r\nThe most basic setup is the sl-hr one (train_sl-hr.sh):\r\n- normalization of deprels\r\n- 1:1 word-alignment of parallel data with Monolingual Greedy Aligner\r\n- simple word-by-word translation of source treebank\r\n- pre-training of target word embeddings\r\n- simplification of morpho feats (use only Case)\r\n- and finally, training and evaluating the parser\r\n\r\nBoth da+sv-no (train_ds-no.sh) and cs-sk (train_cs-sk.sh) add some cross-tagging, which seems to be useful only in\r\nspecific cases (see paper for details).\r\nMoreover, cs-sk also adds more morpho features, selecting those that\r\nseem to be very often shared in parallel data.\r\n\r\nThe whole pipeline takes tens of hours to run, and uses several GB of RAM, so make sure to use a powerful computer."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1970"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parsing"
-        },
-        {
-            "name": "dependency parser"
-        },
-        {
-            "name": "universal dependencies"
-        },
-        {
-            "name": "cross-lingual parsing"
-        }
-    ],
-    "title": [
-        "Slavic Forest, Norwegian Wood (scripts)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/544a03c0-c724-52f9-82a7-27fb8959dc00.json b/oaitestdata/clarin-oai_dc/SET_1/json/544a03c0-c724-52f9-82a7-27fb8959dc00.json
deleted file mode 100644
index 620227a6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/544a03c0-c724-52f9-82a7-27fb8959dc00.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=7e264d6aa3e611e5a2aa782bcb0741350bec1f4ff348475eab24a1a571916566",
-    "MetadataAccess": [
-        "7e264d6aa3e611e5a2aa782bcb0741350bec1f4ff348475eab24a1a571916566"
-    ],
-    "PublicationTimestamp": "2015-12-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "7e264d6aa3e611e5a2aa782bcb0741350bec1f4ff348475eab24a1a571916566;2018-11-15T16:40:19Z;corpus;corpus:text;CINTIL-WordSenses ;The CINTIL-WordSenses corpus, built upon the CINTIL International Corpus of Portuguese (Barreto et al., 2006), is composed of 23,825 sentences of written Portuguese with open-class terms manually disambiguated and annotated with synset identifiers from the Portuguese MultiWordNet (MWNPT) (Pianti et al., 2002). From a total of 508,717 tokens of which 193,443 are open-class (potentially ambiguous) terms, 45,502 have been annotated with synset identifiers.\n\nThe development of the CINTIL-WordSenses corpus has been funded by the EU project QTLeap (EC/FP7/610516) and the Portuguese project DP4LT (PTDC/EEI-\nSII/1940/2012).;2015-12-16",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "544a03c0-c724-52f9-82a7-27fb8959dc00",
-    "notes": [
-        "The CINTIL-WordSenses corpus, built upon the CINTIL International Corpus of Portuguese (Barreto et al., 2006), is composed of 23,825 sentences of written Portuguese with open-class terms manually disambiguated and annotated with synset identifiers from the Portuguese MultiWordNet (MWNPT) (Pianti et al., 2002). From a total of 508,717 tokens of which 193,443 are open-class (potentially ambiguous) terms, 45,502 have been annotated with synset identifiers.\n\nThe development of the CINTIL-WordSenses corpus has been funded by the EU project QTLeap (EC/FP7/610516) and the Portuguese project DP4LT (PTDC/EEI-\nSII/1940/2012)."
-    ],
-    "oai_identifier": [
-        "7e264d6aa3e611e5a2aa782bcb0741350bec1f4ff348475eab24a1a571916566"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "CINTIL-WordSenses "
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/544bd292-0b3b-59df-a097-c04639a6558a.json b/oaitestdata/clarin-oai_dc/SET_1/json/544bd292-0b3b-59df-a097-c04639a6558a.json
deleted file mode 100644
index 6d44878b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/544bd292-0b3b-59df-a097-c04639a6558a.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3715",
-    "MetadataAccess": [
-        "oai:ota:oucs:3715"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Paine, Thomas, 1737-1809."
-    ],
-    "fulltext": "oai:ota:oucs:3715;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3715.xml;A letter to Mr. Secretary Dundas. In answer to his speech on the late proclamation. By Thomas Paine;Letter to Mr. Henry Dundas;Paine, Thomas, 1737-1809.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "544bd292-0b3b-59df-a097-c04639a6558a",
-    "oai_identifier": [
-        "oai:ota:oucs:3715"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A letter to Mr. Secretary Dundas. In answer to his speech on the late proclamation. By Thomas Paine",
-        "Letter to Mr. Henry Dundas"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3715.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/54536eb0-6222-5b5d-9f03-a736fda57de8.json b/oaitestdata/clarin-oai_dc/SET_1/json/54536eb0-6222-5b5d-9f03-a736fda57de8.json
deleted file mode 100644
index fce2f1c4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/54536eb0-6222-5b5d-9f03-a736fda57de8.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1431",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1431"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1431",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1431;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;COLDIC;Tool for dictionary management;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1431;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra;http://www.iula.upf.edu/recurs01ca.htm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "54536eb0-6222-5b5d-9f03-a736fda57de8",
-    "notes": [
-        "Tool for dictionary management"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1431"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "COLDIC"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/546e02ad-ce76-5629-8c78-fc12725f7362.json b/oaitestdata/clarin-oai_dc/SET_1/json/546e02ad-ce76-5629-8c78-fc12725f7362.json
deleted file mode 100644
index 77c44264..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/546e02ad-ce76-5629-8c78-fc12725f7362.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3555",
-    "MetadataAccess": [
-        "oai:ota:oucs:3555"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Barbauld, Mrs. (Anna Letitia), 1743-1825."
-    ],
-    "fulltext": "oai:ota:oucs:3555;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3555.xml;Poems;Barbauld, Mrs. (Anna Letitia), 1743-1825.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "546e02ad-ce76-5629-8c78-fc12725f7362",
-    "oai_identifier": [
-        "oai:ota:oucs:3555"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Poems"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3555.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/546fa785-61b8-51dd-a22e-64c50a94f32e.json b/oaitestdata/clarin-oai_dc/SET_1/json/546fa785-61b8-51dd-a22e-64c50a94f32e.json
deleted file mode 100644
index 866d8d9d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/546fa785-61b8-51dd-a22e-64c50a94f32e.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=fba0b4cc324411e2a2aa782bcb0741356c4ffec5a08e4251aeb1850b91bdf8ad",
-    "MetadataAccess": [
-        "fba0b4cc324411e2a2aa782bcb0741356c4ffec5a08e4251aeb1850b91bdf8ad"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "fba0b4cc324411e2a2aa782bcb0741356c4ffec5a08e4251aeb1850b91bdf8ad;2018-11-15T16:39:49Z;toolService;toolService:tool;UIMA/U-Compare NEMine;The purpose of the tool is to identify gene and protein names in biomedical text. \n\nThe tool is provided as a UIMA component, which forms part of the in-built library of components provided with the U-Compare platform for building and evaluating text mining workflows. The U-Compare Workbench provides a graphical drag-and drop interface for the rapid creation of workflows. \n;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "546fa785-61b8-51dd-a22e-64c50a94f32e",
-    "notes": [
-        "The purpose of the tool is to identify gene and protein names in biomedical text. \n\nThe tool is provided as a UIMA component, which forms part of the in-built library of components provided with the U-Compare platform for building and evaluating text mining workflows. The U-Compare Workbench provides a graphical drag-and drop interface for the rapid creation of workflows. \n"
-    ],
-    "oai_identifier": [
-        "fba0b4cc324411e2a2aa782bcb0741356c4ffec5a08e4251aeb1850b91bdf8ad"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "UIMA/U-Compare NEMine"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/547a9c73-3335-5218-998f-1296e87d65fa.json b/oaitestdata/clarin-oai_dc/SET_1/json/547a9c73-3335-5218-998f-1296e87d65fa.json
deleted file mode 100644
index a692958c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/547a9c73-3335-5218-998f-1296e87d65fa.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5254",
-    "MetadataAccess": [
-        "oai:ota:oucs:5254"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Holcroft, Thomas, 1745-1809."
-    ],
-    "fulltext": "oai:ota:oucs:5254;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5254.xml;Anna St. Ives: a novel. By Thomas Holcroft. ... [pt.6];Holcroft, Thomas, 1745-1809.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "547a9c73-3335-5218-998f-1296e87d65fa",
-    "oai_identifier": [
-        "oai:ota:oucs:5254"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Anna St. Ives: a novel. By Thomas Holcroft. ... [pt.6]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5254.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/549445d8-ba11-55e4-8b6c-2a3a1fce88f8.json b/oaitestdata/clarin-oai_dc/SET_1/json/549445d8-ba11-55e4-8b6c-2a3a1fce88f8.json
deleted file mode 100644
index 9677c356..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/549445d8-ba11-55e4-8b6c-2a3a1fce88f8.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1418",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1418"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1418",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1418;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Catalan Annotated Corpora CQP;This RESTful service allows to define a sub-corpus from different annotated corpora. The service includes a POS tag harmonisation process where original tags are converted to EAGLES/Parole format. The eventual sub-corpus is indexed using the IMS CWB tool. The user receives an ID which can be used by the CQP service to exploit the sub-corpus.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1418;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "549445d8-ba11-55e4-8b6c-2a3a1fce88f8",
-    "notes": [
-        "This RESTful service allows to define a sub-corpus from different annotated corpora. The service includes a POS tag harmonisation process where original tags are converted to EAGLES/Parole format. The eventual sub-corpus is indexed using the IMS CWB tool. The user receives an ID which can be used by the CQP service to exploit the sub-corpus."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1418"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Catalan Annotated Corpora CQP"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/549abdbc-ce6f-5b75-a788-78604bf69133.json b/oaitestdata/clarin-oai_dc/SET_1/json/549abdbc-ce6f-5b75-a788-78604bf69133.json
deleted file mode 100644
index 7249646e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/549abdbc-ce6f-5b75-a788-78604bf69133.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "Institute of Slavic Studies, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 55",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish",
-        "Bulgarian",
-        "Russian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/308",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/308"
-    ],
-    "PID": "http://hdl.handle.net/11321/308",
-    "PublicationTimestamp": "2016-06-07T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Institute of Slavic Studies, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "IS PAS corpora license",
-        "http://clarin-pl.eu/en/licenses/is-pas-corpora-license/",
-        "CC"
-    ],
-    "author": [
-        "Sato\u0142a-Sta\u015bkowiak, Joanna",
-        "Natalia, Kotsyba",
-        "Kisiel, Anna",
-        "Koseska-Toszewa, Violetta",
-        "Sosnowski, Wojciech"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/308;2017-11-21T12:51:42Z;hdl_11321_3;hdl_11321_4;Polish-Bulgarian-Russian Parallel Corpus;Kisiel, Anna;Koseska-Toszewa, Violetta;Natalia, Kotsyba;Sato\u0142a-Sta\u015bkowiak, Joanna;Sosnowski, Wojciech;parallel corpora;Polish;Russian;Bulgarian;Database;2016-06-07;corpus;http://hdl.handle.net/11321/308;pol;bul;rus;IS PAS corpora license;http://clarin-pl.eu/en/licenses/is-pas-corpora-license/;CC;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 55;Institute of Slavic Studies, Polish Academy of Sciences",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "549abdbc-ce6f-5b75-a788-78604bf69133",
-    "notes": [
-        "Database"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/308"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parallel corpora"
-        },
-        {
-            "name": "Polish"
-        },
-        {
-            "name": "Russian"
-        },
-        {
-            "name": "Bulgarian"
-        }
-    ],
-    "title": [
-        "Polish-Bulgarian-Russian Parallel Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/54b09832-1608-558c-9160-9423f6dcf33c.json b/oaitestdata/clarin-oai_dc/SET_1/json/54b09832-1608-558c-9160-9423f6dcf33c.json
deleted file mode 100644
index 3b10334b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/54b09832-1608-558c-9160-9423f6dcf33c.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "less than 512 KB"
-    ],
-    "Language": [
-        "French"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0609",
-    "MetadataAccess": [
-        "oai:ota:oucs:0609"
-    ],
-    "PublicationTimestamp": "1736-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1736"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Fiction"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Cr\u00c3\u00a9billon,  Monsieur de (Claude-Prosper Jolyot),  1707-1777"
-    ],
-    "fulltext": "oai:ota:oucs:0609;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0609.xml; Les \u00c3\u00a9garements du coeur et de l'esprit / compiled by Jennifer Darzentas;Cr\u00c3\u00a9billon,  Monsieur de (Claude-Prosper Jolyot),  1707-1777;1736;text_and_corpus_linguistics;Fiction -- France -- 18th century;fra;Oxford Text Archive, University of Oxford;less than 512 KB;Text;Fiction;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "54b09832-1608-558c-9160-9423f6dcf33c",
-    "oai_identifier": [
-        "oai:ota:oucs:0609"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- France -- th century"
-        }
-    ],
-    "title": [
-        " Les \u00c3\u00a9garements du coeur et de l'esprit / compiled by Jennifer Darzentas"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0609.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/54b17c2f-4f3a-53ab-939c-30025c233201.json b/oaitestdata/clarin-oai_dc/SET_1/json/54b17c2f-4f3a-53ab-939c-30025c233201.json
deleted file mode 100644
index a9c05b31..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/54b17c2f-4f3a-53ab-939c-30025c233201.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/42",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/42"
-    ],
-    "PID": "http://hdl.handle.net/10794/42",
-    "PublicationTimestamp": "2012-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/42;2017-10-27T11:19:58Z;hdl_10794_1;hdl_10794_2;Swedberg's Swensk Ordabok (2017-10-16);Swedbergs Swensk ordabok (2017-10-16);n/a, n/a;Swedish;Dictionary;Swedberg's Swensk Ordabok. 18th century.;Swedbergs Swensk ordabok.;2012-05-30;lexicalConceptualResource;http://hdl.handle.net/10794/42;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/swedberg",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "54b17c2f-4f3a-53ab-939c-30025c233201",
-    "notes": [
-        "Swedberg's Swensk Ordabok. 18th century.",
-        "Swedbergs Swensk ordabok."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/42"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Dictionary"
-        }
-    ],
-    "title": [
-        "Swedberg's Swensk Ordabok (2017-10-16)",
-        "Swedbergs Swensk ordabok (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/54dd140b-6bae-58a3-a26e-ef3d65a6c97e.json b/oaitestdata/clarin-oai_dc/SET_1/json/54dd140b-6bae-58a3-a26e-ef3d65a6c97e.json
deleted file mode 100644
index f21d2583..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/54dd140b-6bae-58a3-a26e-ef3d65a6c97e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4602",
-    "MetadataAccess": [
-        "oai:ota:oucs:4602"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Addison, Joseph, 1672-1719."
-    ],
-    "fulltext": "oai:ota:oucs:4602;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4602.xml;Two poems: viz. I. On the deluge, paradise, the burning of the world, and of the new heavens and new earth. An ode to. Dr. Burnett. II. In praise of physic and poetry. An ode to Dr. Hannes. Written by Mr. Addison.;Addison, Joseph, 1672-1719.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "54dd140b-6bae-58a3-a26e-ef3d65a6c97e",
-    "oai_identifier": [
-        "oai:ota:oucs:4602"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Two poems: viz. I. On the deluge, paradise, the burning of the world, and of the new heavens and new earth. An ode to. Dr. Burnett. II. In praise of physic and poetry. An ode to Dr. Hannes. Written by Mr. Addison."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4602.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/54e9cc32-1c04-5914-a8f4-909966bd8d29.json b/oaitestdata/clarin-oai_dc/SET_1/json/54e9cc32-1c04-5914-a8f4-909966bd8d29.json
deleted file mode 100644
index 20289f6a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/54e9cc32-1c04-5914-a8f4-909966bd8d29.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "application/pdf",
-        "downloadable_files_count: 4"
-    ],
-    "Language": [
-        "Urdu"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-65A9-5",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-65A9-5"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-65A9-5",
-    "PublicationTimestamp": "2014-03-22T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/288487"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Bojar, Ond\u0159ej",
-        "Jawaid, Bushra",
-        "Kamran, Amir"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-65A9-5;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Urdu Monolingual Corpus;Jawaid, Bushra;Kamran, Amir;Bojar, Ond\u0159ej;Urdu;monolingual data;annotated data;corpus;We release a sizeable monolingual Urdu corpus automatically tagged with part-of-speech tags. We extend the work of Jawaid and Bojar (2012) who use three different taggers and then apply a voting scheme to disambiguate among the different choices suggested by each tagger. We run this complex ensemble on a large monolingual corpus and release the both plain and tagged corpora.;2014-03-22;lexicalConceptualResource;http://hdl.handle.net/11858/00-097C-0000-0023-65A9-5;urd;info:eu-repo/grantAgreement/EC/FP7/288487;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/x-gzip;application/x-gzip;application/pdf;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "54e9cc32-1c04-5914-a8f4-909966bd8d29",
-    "notes": [
-        "We release a sizeable monolingual Urdu corpus automatically tagged with part-of-speech tags. We extend the work of Jawaid and Bojar (2012) who use three different taggers and then apply a voting scheme to disambiguate among the different choices suggested by each tagger. We run this complex ensemble on a large monolingual corpus and release the both plain and tagged corpora."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-65A9-5"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Urdu"
-        },
-        {
-            "name": "monolingual data"
-        },
-        {
-            "name": "annotated data"
-        },
-        {
-            "name": "corpus"
-        }
-    ],
-    "title": [
-        "Urdu Monolingual Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5508b9d7-8977-5a1b-8931-414904c01953.json b/oaitestdata/clarin-oai_dc/SET_1/json/5508b9d7-8977-5a1b-8931-414904c01953.json
deleted file mode 100644
index eda4a365..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5508b9d7-8977-5a1b-8931-414904c01953.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "Hebrew"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-963",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-963"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-963",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-963;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Hebrew;ca. 500.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-963;heb;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#hebraica",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5508b9d7-8977-5a1b-8931-414904c01953",
-    "notes": [
-        "ca. 500.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-963"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Hebrew"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/550fe6e0-0643-51c6-95f5-40a295b76f37.json b/oaitestdata/clarin-oai_dc/SET_1/json/550fe6e0-0643-51c6-95f5-40a295b76f37.json
deleted file mode 100644
index 6372ccf7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/550fe6e0-0643-51c6-95f5-40a295b76f37.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1516",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1516"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1516",
-    "PublicationTimestamp": "2015-10-18T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-2498"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Kr\u00ed\u017e, Vincent",
-        "Ure\u0161ov\u00e1, Zde\u0148ka",
-        "Hladk\u00e1, Barbora"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1516;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Czech Legal Text Treebank;Kr\u00ed\u017e, Vincent;Hladk\u00e1, Barbora;Ure\u0161ov\u00e1, Zde\u0148ka;treebank;corpus;Czech;legal texts;legal domain;The Czech Legal Text Treebank (CLTT) is a collection of 1133 manually annotated dependency trees. CLTT consists of two legal documents: The Accounting Act (563/1991 Coll., as amended) and Decree on Double-entry Accounting for undertakers (500/2002 Coll., as amended).;2015-10-18;corpus;http://hdl.handle.net/11234/1-1516;ces;http://hdl.handle.net/11234/1-2498;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://ufal.mff.cuni.cz/czech-legal-text-treebank",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "550fe6e0-0643-51c6-95f5-40a295b76f37",
-    "notes": [
-        "The Czech Legal Text Treebank (CLTT) is a collection of 1133 manually annotated dependency trees. CLTT consists of two legal documents: The Accounting Act (563/1991 Coll., as amended) and Decree on Double-entry Accounting for undertakers (500/2002 Coll., as amended)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1516"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "Czech"
-        },
-        {
-            "name": "legal texts"
-        },
-        {
-            "name": "legal domain"
-        }
-    ],
-    "title": [
-        "Czech Legal Text Treebank"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/55268b4e-dffa-587e-b5bd-652487f66474.json b/oaitestdata/clarin-oai_dc/SET_1/json/55268b4e-dffa-587e-b5bd-652487f66474.json
deleted file mode 100644
index c50bf6eb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/55268b4e-dffa-587e-b5bd-652487f66474.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "[Jan Wolrab]"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-16680",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-16680"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CF0-7",
-    "PublicationTimestamp": "1627-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1627"
-    ],
-    "Publisher": [
-        "[Jan Wolrab]"
-    ],
-    "RelatedIdentifier": [
-        "http://rcin.org.pl/Content/16680",
-        "oai:rcin.org.pl:publication:34237"
-    ],
-    "ResourceType": [
-        "Early printed book (1501-1800)",
-        "Ksi\u0105\u017cka",
-        "Stary druk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "author": [
-        "Szembek, Fryderyk"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-16680;2019-03-01T10:59:46Z;Gratis pleba\u0144ski, gratis wy\u0107wiczony w jezuickich szko\u0142ach krakowskich;Szembek, Fryderyk;p. 520;[Jan Wolrab];1627;Early printed book (1501-1800);Ksi\u0105\u017cka;Stary druk;application/xml;clarind-uds:poldilemma-16680;hdl:11858/00-246C-0000-0023-8CF0-7;pol;lat;http://rcin.org.pl/Content/16680;oai:rcin.org.pl:publication:34237;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "55268b4e-dffa-587e-b5bd-652487f66474",
-    "notes": [
-        "p. 520"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-16680"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "title": [
-        "Gratis pleba\u0144ski, gratis wy\u0107wiczony w jezuickich szko\u0142ach krakowskich"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/55390ad7-8b0c-5215-a2fa-7b6724df1438.json b/oaitestdata/clarin-oai_dc/SET_1/json/55390ad7-8b0c-5215-a2fa-7b6724df1438.json
deleted file mode 100644
index 3cddf8c3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/55390ad7-8b0c-5215-a2fa-7b6724df1438.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 4",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2123",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2123"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2123",
-    "PublicationTimestamp": "2017-01-13T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Olivov\u00e1, Jana",
-        "Dvo\u0159\u00e1k, Josef",
-        "Du\u0161ek, Ond\u0159ej",
-        "Jur\u010d\u00ed\u010dek, Filip",
-        "\u0160tichov\u00e1, Eva",
-        "Star\u00fd, Michal",
-        "Hejda, Mat\u011bj",
-        "Grycov\u00e1, Petra"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2123;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Czech restaurant information dataset for NLG;Du\u0161ek, Ond\u0159ej;Jur\u010d\u00ed\u010dek, Filip;Dvo\u0159\u00e1k, Josef;Grycov\u00e1, Petra;Hejda, Mat\u011bj;Olivov\u00e1, Jana;Star\u00fd, Michal;\u0160tichov\u00e1, Eva;natural language generation;dialogue system;morphological generation;This is a dataset for natural language generation (NLG) in task-oriented spoken dialogue systems with Czech as the target language. It originated as a translation of the English San Francisco Restaurants dataset by Wen et al. (2015).\r\n\r\nIt includes input dialogue acts and the corresponding output natural language paraphrases in Czech. Since the dataset is intended for recurrent neural network based NLG systems using delexicalization, inflection tables for all slot values appearing verbatim in the text are provided.;2017-01-13;corpus;http://hdl.handle.net/11234/1-2123;ces;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;PUB;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 4;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://github.com/UFAL-DSG/cs_restaurant_dataset",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "55390ad7-8b0c-5215-a2fa-7b6724df1438",
-    "notes": [
-        "This is a dataset for natural language generation (NLG) in task-oriented spoken dialogue systems with Czech as the target language. It originated as a translation of the English San Francisco Restaurants dataset by Wen et al. (2015).\r\n\r\nIt includes input dialogue acts and the corresponding output natural language paraphrases in Czech. Since the dataset is intended for recurrent neural network based NLG systems using delexicalization, inflection tables for all slot values appearing verbatim in the text are provided."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2123"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "natural language generation"
-        },
-        {
-            "name": "dialogue system"
-        },
-        {
-            "name": "morphological generation"
-        }
-    ],
-    "title": [
-        "Czech restaurant information dataset for NLG"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/555f4d14-797f-5889-afac-ff7511ae0371.json b/oaitestdata/clarin-oai_dc/SET_1/json/555f4d14-797f-5889-afac-ff7511ae0371.json
deleted file mode 100644
index 6d00f797..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/555f4d14-797f-5889-afac-ff7511ae0371.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/x-bzip2",
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48FD-B",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48FD-B"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-48FD-B",
-    "PublicationTimestamp": "2009-11-02T09:48:39Z",
-    "PublicationYear": [
-        "2009"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU General Public License, version 2",
-        "http://www.gnu.org/licenses/gpl-2.0.html",
-        "PUB"
-    ],
-    "author": [
-        "Marek, Michal"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48FD-B;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Victor;Marek, Michal;html cleaning;Victor is a web page cleaning tool. It is aimed at removing menu, ads, footers, headers, etc. from HTML web pages, so that only main web page content remains. Victor is based on a conditional random fields algorithm.;2009-11-02T09:48:39Z;toolService;http://hdl.handle.net/11858/00-097C-0000-0001-48FD-B;GNU General Public License, version 2;http://www.gnu.org/licenses/gpl-2.0.html;PUB;application/x-bzip2;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/victor/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "555f4d14-797f-5889-afac-ff7511ae0371",
-    "notes": [
-        "Victor is a web page cleaning tool. It is aimed at removing menu, ads, footers, headers, etc. from HTML web pages, so that only main web page content remains. Victor is based on a conditional random fields algorithm."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48FD-B"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "html cleaning"
-        }
-    ],
-    "title": [
-        "Victor"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5585e9bf-6e78-5404-9614-c56106b00bb3.json b/oaitestdata/clarin-oai_dc/SET_1/json/5585e9bf-6e78-5404-9614-c56106b00bb3.json
deleted file mode 100644
index b7b94412..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5585e9bf-6e78-5404-9614-c56106b00bb3.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "less than 512 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0428",
-    "MetadataAccess": [
-        "oai:ota:oucs:0428"
-    ],
-    "PublicationTimestamp": "1972-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1972"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Bennett, Alan,  1934-"
-    ],
-    "fulltext": "oai:ota:oucs:0428;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0428.xml; Getting on  / compiled by Dirk Geens;Bennett, Alan,  1934-;1972;text_and_corpus_linguistics;Plays -- Great Britain -- 20th century;eng;Forms part of the Louvain corpus of modern English drama deposited in 1983. The text does not conform to modern standards of text encoding. The text is all capitals, with words broken over line boundaries, undocumented markup characters, and numeric codes for the identities of the players. ;Oxford Text Archive, University of Oxford;less than 512 KB;Text;Plays;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5585e9bf-6e78-5404-9614-c56106b00bb3",
-    "notes": [
-        "Forms part of the Louvain corpus of modern English drama deposited in 1983. The text does not conform to modern standards of text encoding. The text is all capitals, with words broken over line boundaries, undocumented markup characters, and numeric codes for the identities of the players. "
-    ],
-    "oai_identifier": [
-        "oai:ota:oucs:0428"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        " Getting on  / compiled by Dirk Geens"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0428.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/55a3cae9-3d85-5ad4-b78e-b4ebaf423d7e.json b/oaitestdata/clarin-oai_dc/SET_1/json/55a3cae9-3d85-5ad4-b78e-b4ebaf423d7e.json
deleted file mode 100644
index 476100c7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/55a3cae9-3d85-5ad4-b78e-b4ebaf423d7e.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "University of Helsinki",
-        "CSC - the Finnish IT Center for Science"
-    ],
-    "Contributor": [
-        "Siiroinen, Mari",
-        "Aalto, Tero"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Finnish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-743",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-743"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-743",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Helsinki",
-        "CSC - the Finnish IT Center for Science"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Finland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-743;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Digital Morphology Archives for Finnish Dialects;Aalto, Tero;Siiroinen, Mari;A morphologically annotated digital database of 159 Finnish parish dialects containing transcribed sentences of spontaneous dialectal speech;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-743;fin;application/octet-stream;downloadable_files_count: 0;Finland;CSC - the Finnish IT Center for Science;University of Helsinki;http://www.csc.fi",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "55a3cae9-3d85-5ad4-b78e-b4ebaf423d7e",
-    "notes": [
-        "A morphologically annotated digital database of 159 Finnish parish dialects containing transcribed sentences of spontaneous dialectal speech"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-743"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Digital Morphology Archives for Finnish Dialects"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/55c4fcac-f58c-517f-82b3-6b3691a65c12.json b/oaitestdata/clarin-oai_dc/SET_1/json/55c4fcac-f58c-517f-82b3-6b3691a65c12.json
deleted file mode 100644
index ad1f000d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/55c4fcac-f58c-517f-82b3-6b3691a65c12.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3214",
-    "MetadataAccess": [
-        "oai:ota:oucs:3214"
-    ],
-    "PublicationTimestamp": "1889-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1889"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Twain, Mark, 1835-1910"
-    ],
-    "fulltext": "oai:ota:oucs:3214;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3214.xml;A Connecticut yankee in King Arthur's court;Twain, Mark, 1835-1910;not after: 1889;text_and_corpus_linguistics;Fiction -- United States -- 19th century;Fantasy literature -- United States -- 19th century;Novels -- United States -- 19th century;Satires -- United States -- 19th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "55c4fcac-f58c-517f-82b3-6b3691a65c12",
-    "oai_identifier": [
-        "oai:ota:oucs:3214"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- United States -- th century"
-        },
-        {
-            "name": "Fantasy literature -- United States -- th century"
-        },
-        {
-            "name": "Novels -- United States -- th century"
-        },
-        {
-            "name": "Satires -- United States -- th century"
-        }
-    ],
-    "title": [
-        "A Connecticut yankee in King Arthur's court"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3214.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/55cb227d-6638-551c-b70a-31fef1fad9cf.json b/oaitestdata/clarin-oai_dc/SET_1/json/55cb227d-6638-551c-b70a-31fef1fad9cf.json
deleted file mode 100644
index dea9a00f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/55cb227d-6638-551c-b70a-31fef1fad9cf.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=0fe53eaa5e6211e2a2aa782bcb074135e21251a82a294e44a8dfa8e48e6f894b",
-    "MetadataAccess": [
-        "0fe53eaa5e6211e2a2aa782bcb074135e21251a82a294e44a8dfa8e48e6f894b"
-    ],
-    "PublicationTimestamp": "2013-01-31T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "0fe53eaa5e6211e2a2aa782bcb074135e21251a82a294e44a8dfa8e48e6f894b;2018-11-15T16:40:01Z;toolService;toolService:service;MLSS Paragraph Splitter Web service;The paragraph splitter is a web service tool which takes text as input and outputs the identified paragraphs surrounded by tags. The tool is language independent. The download for this resource only contains the narrative description in a Word file.\n\nThe service has one method which can be invoked:\n- String tagParagraphs(String text)\n\nThe method takes a string as input, that being the text to be split into paragraphs, and returns another string of that text tagged.\n\nThe format of the output is as follows:\n<paragraph> paragraph_text </paragraph>\n;2013-01-31",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "55cb227d-6638-551c-b70a-31fef1fad9cf",
-    "notes": [
-        "The paragraph splitter is a web service tool which takes text as input and outputs the identified paragraphs surrounded by tags. The tool is language independent. The download for this resource only contains the narrative description in a Word file.\n\nThe service has one method which can be invoked:\n- String tagParagraphs(String text)\n\nThe method takes a string as input, that being the text to be split into paragraphs, and returns another string of that text tagged.\n\nThe format of the output is as follows:\n<paragraph> paragraph_text </paragraph>\n"
-    ],
-    "oai_identifier": [
-        "0fe53eaa5e6211e2a2aa782bcb074135e21251a82a294e44a8dfa8e48e6f894b"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:service"
-    ],
-    "state": "active",
-    "title": [
-        "MLSS Paragraph Splitter Web service"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/55ccd5b8-e5f4-5d2a-ab08-d11cb531e04c.json b/oaitestdata/clarin-oai_dc/SET_1/json/55ccd5b8-e5f4-5d2a-ab08-d11cb531e04c.json
deleted file mode 100644
index fbac3c06..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/55ccd5b8-e5f4-5d2a-ab08-d11cb531e04c.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5240",
-    "MetadataAccess": [
-        "oai:ota:oucs:5240"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Buffon, Georges Louis Leclerc, comte de, 1707-1788."
-    ],
-    "fulltext": "oai:ota:oucs:5240;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5240.xml;The natural history of birds: From the French of the Count de Buffon. Illustrated with engravings; and a preface, notes, and additions, by the translator. In nine volumes. ... [pt.1];Histoire naturelle des oiseaux. English;Buffon, Georges Louis Leclerc, comte de, 1707-1788.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "55ccd5b8-e5f4-5d2a-ab08-d11cb531e04c",
-    "oai_identifier": [
-        "oai:ota:oucs:5240"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The natural history of birds: From the French of the Count de Buffon. Illustrated with engravings; and a preface, notes, and additions, by the translator. In nine volumes. ... [pt.1]",
-        "Histoire naturelle des oiseaux. English"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5240.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/56177d8e-2c3d-5a34-b8fe-913ac445fec4.json b/oaitestdata/clarin-oai_dc/SET_1/json/56177d8e-2c3d-5a34-b8fe-913ac445fec4.json
deleted file mode 100644
index 1f641bb1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/56177d8e-2c3d-5a34-b8fe-913ac445fec4.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "Trojina, Institute for Applied Slovene Studies",
-        "Faculty of Arts, University of Ljubljana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1053",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1053"
-    ],
-    "PID": "http://hdl.handle.net/11356/1053",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Trojina, Institute for Applied Slovene Studies",
-        "Faculty of Arts, University of Ljubljana"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11356/1194"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "https://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Dobrovoljc, Kaja"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1053;2018-08-03T18:45:16Z;hdl_11356_1023;hdl_11356_1024;IMP corpus n-grams 1.0;Dobrovoljc, Kaja;n-grams;wordlist;multiword expressions;historical language;This is a collection of n-grams extracted from the IMP corpus of historical Slovene (http://hdl.handle.net/11356/1031). In addition to the separate lists of n-grams for tokens and their attributes (modernised form, morphosyntacic tag, lemma), an adjusted frequency list with statistical substring reduction has also been added (as described in O'Donnell 2011). Only n-grams within sentences have been counted.;2015-07-01;lexicalConceptualResource;http://hdl.handle.net/11356/1053;slv;http://hdl.handle.net/11356/1194;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);https://creativecommons.org/licenses/by-sa/4.0/;PUB;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 4;Trojina, Institute for Applied Slovene Studies;Faculty of Arts, University of Ljubljana;http://nl.ijs.si/imp/index-en.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "56177d8e-2c3d-5a34-b8fe-913ac445fec4",
-    "notes": [
-        "This is a collection of n-grams extracted from the IMP corpus of historical Slovene (http://hdl.handle.net/11356/1031). In addition to the separate lists of n-grams for tokens and their attributes (modernised form, morphosyntacic tag, lemma), an adjusted frequency list with statistical substring reduction has also been added (as described in O'Donnell 2011). Only n-grams within sentences have been counted."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1053"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "n-grams"
-        },
-        {
-            "name": "wordlist"
-        },
-        {
-            "name": "multiword expressions"
-        },
-        {
-            "name": "historical language"
-        }
-    ],
-    "title": [
-        "IMP corpus n-grams 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/56301463-bfc3-5db4-8591-d7d6748e4b88.json b/oaitestdata/clarin-oai_dc/SET_1/json/56301463-bfc3-5db4-8591-d7d6748e4b88.json
deleted file mode 100644
index 63954311..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/56301463-bfc3-5db4-8591-d7d6748e4b88.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-965",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-965"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-965",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-965;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Syriac;ca. 900.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-965;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#syriaca",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "56301463-bfc3-5db4-8591-d7d6748e4b88",
-    "notes": [
-        "ca. 900.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-965"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Syriac"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/564c2963-dbdb-55e9-8050-4a4d37204038.json b/oaitestdata/clarin-oai_dc/SET_1/json/564c2963-dbdb-55e9-8050-4a4d37204038.json
deleted file mode 100644
index 99f9e55a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/564c2963-dbdb-55e9-8050-4a4d37204038.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/16",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/16"
-    ],
-    "PID": "http://hdl.handle.net/11321/16",
-    "PublicationTimestamp": "2014-01-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Marci\u0144czuk, Micha\u0142",
-        "Maziarz, Marek",
-        "Radziszewski, Adam",
-        "Broda, Bartosz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/16;2017-11-08T09:25:02Z;hdl_11321_3;hdl_11321_4;Polish Corpus of Wroc\u0142aw University of Technology 1.1;Korpus J\u0119zyka Polskiego Politechniki Wroc\u0142awskiej (KPWr) 1.1;Maziarz, Marek;Broda, Bartosz;Marci\u0144czuk, Micha\u0142;Radziszewski, Adam;KPWr (Polish Corpus of Wroc\u0142aw University of Technology, pl. Korpus J\u0119zyka Polskiego Politechniki Wroc\u0142awskiej) is a corpus of written and spoken documents available on the Creative Common license. The texts are divided into 14 categories (blogs, science, stenographic recordings, etc.). The documents are annotated on the level of chunks and selected predicate-argument relations, named entities, relations between named entities, anaphora relations and word senses.;2014-01-01;corpus;http://hdl.handle.net/11321/16;pol;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;downloadable_files_count: 0;Wroc\u0142aw University of Technology;http://nlp.pwr.wroc.pl/narzedzia-i-zasoby/zasoby/kpwr",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "564c2963-dbdb-55e9-8050-4a4d37204038",
-    "notes": [
-        "KPWr (Polish Corpus of Wroc\u0142aw University of Technology, pl. Korpus J\u0119zyka Polskiego Politechniki Wroc\u0142awskiej) is a corpus of written and spoken documents available on the Creative Common license. The texts are divided into 14 categories (blogs, science, stenographic recordings, etc.). The documents are annotated on the level of chunks and selected predicate-argument relations, named entities, relations between named entities, anaphora relations and word senses."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/16"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Polish Corpus of Wroc\u0142aw University of Technology 1.1",
-        "Korpus J\u0119zyka Polskiego Politechniki Wroc\u0142awskiej (KPWr) 1.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5651dedc-bc5b-5598-8ab7-783db48cd779.json b/oaitestdata/clarin-oai_dc/SET_1/json/5651dedc-bc5b-5598-8ab7-783db48cd779.json
deleted file mode 100644
index 180f5ee1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5651dedc-bc5b-5598-8ab7-783db48cd779.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 567 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1982",
-    "MetadataAccess": [
-        "oai:ota:oucs:1982"
-    ],
-    "PublicationTimestamp": "1895-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1895"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Short stories"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Stevenson, Robert Louis, 1850-1894"
-    ],
-    "fulltext": "oai:ota:oucs:1982;2018-04-16T15:24:51Z;http://ota.ox.ac.uk/headers/1982.xml;New Arabian nights / by Robert Louis Stevenson;Stevenson, Robert Louis, 1850-1894;1895;text_and_corpus_linguistics;Fiction -- Great Britain -- 19th century;Short stories -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 567 KB);Text;Short stories;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5651dedc-bc5b-5598-8ab7-783db48cd779",
-    "oai_identifier": [
-        "oai:ota:oucs:1982"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- Great Britain -- th century"
-        },
-        {
-            "name": "Short stories -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "New Arabian nights / by Robert Louis Stevenson"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1982.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5652c48e-8338-5add-b2a5-2c2131eb1726.json b/oaitestdata/clarin-oai_dc/SET_1/json/5652c48e-8338-5add-b2a5-2c2131eb1726.json
deleted file mode 100644
index fc716dbe..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5652c48e-8338-5add-b2a5-2c2131eb1726.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-76",
-    "MetadataAccess": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-76"
-    ],
-    "PID": "http://hdl.handle.net/20.500.11752/ILC-76",
-    "PublicationTimestamp": "2012-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/248064"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Rubino, Francesco"
-    ],
-    "fulltext": "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-76;2018-04-06T07:34:58Z;hdl_000-c0-111_38;hdl_000-c0-111_49;SCF Extractor (IT);Rubino, Francesco;Subcategorisation frames extraction;Automatic lexical acquisition;Italian;SCF Extractor (IT) is a service that performs inductive subcategorisation extraction from dependency parsed texts, formatted according to the CoNLL-X format. This tool/service was optimized for Italian. The SCF Extractor tool was developed at CNR-ILC and deployed as a soap web service within the EU-FP7-STREP PANACEA project (www.panacea-lr.eu). The service requires 2 input data: 1) a dependency parsed text corpus the CONLL-X format; 2) a list of verb lemmas for which the subcategorization frames will be extracted. For details on the tool design please see: \r\n- Rimell, Laura, N\u00faria Bel, Muntsa Padr\u00f3, Francesca Frontini, Monica Monachini and \r\nValeria Quochi. 2012. D6.2 Integrated Final Version of the Components\r\nfor Lexical Acquisition. Final Project Report. EC/FP7/248064. PANACEA project.\r\n- Caselli, Tommaso; Frontini, Francesca; Quochi, Valeria; Rubino, Francesco and Russo, Irene. (2012). Customizable SCF Acquisition in Italian.In Proceedings of LREC 2012, Istanbul, Turkey.;2012;toolService;http://hdl.handle.net/20.500.11752/ILC-76;ita;info:eu-repo/grantAgreement/EC/FP7/248064;downloadable_files_count: 0;Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR);http://www.panacea-lr.eu/system/deliverables/PANACEA_D6.2.pdf",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5652c48e-8338-5add-b2a5-2c2131eb1726",
-    "notes": [
-        "SCF Extractor (IT) is a service that performs inductive subcategorisation extraction from dependency parsed texts, formatted according to the CoNLL-X format. This tool/service was optimized for Italian. The SCF Extractor tool was developed at CNR-ILC and deployed as a soap web service within the EU-FP7-STREP PANACEA project (www.panacea-lr.eu). The service requires 2 input data: 1) a dependency parsed text corpus the CONLL-X format; 2) a list of verb lemmas for which the subcategorization frames will be extracted. For details on the tool design please see: \r\n- Rimell, Laura, N\u00faria Bel, Muntsa Padr\u00f3, Francesca Frontini, Monica Monachini and \r\nValeria Quochi. 2012. D6.2 Integrated Final Version of the Components\r\nfor Lexical Acquisition. Final Project Report. EC/FP7/248064. PANACEA project.\r\n- Caselli, Tommaso; Frontini, Francesca; Quochi, Valeria; Rubino, Francesco and Russo, Irene. (2012). Customizable SCF Acquisition in Italian.In Proceedings of LREC 2012, Istanbul, Turkey."
-    ],
-    "oai_identifier": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-76"
-    ],
-    "oai_set": [
-        "hdl_000-c0-111_38",
-        "hdl_000-c0-111_49"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Subcategorisation frames extraction"
-        },
-        {
-            "name": "Automatic lexical acquisition"
-        },
-        {
-            "name": "Italian"
-        }
-    ],
-    "title": [
-        "SCF Extractor (IT)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/566515a0-b30a-5c06-8856-5f9e976e4877.json b/oaitestdata/clarin-oai_dc/SET_1/json/566515a0-b30a-5c06-8856-5f9e976e4877.json
deleted file mode 100644
index 3dd61fdf..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/566515a0-b30a-5c06-8856-5f9e976e4877.json
+++ /dev/null
@@ -1,88 +0,0 @@
-{
-    "Contact": [
-        "The Norwegian Association of Higher Education Institutions"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "application/octet-stream",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Norwegian Bokm\u00e5l",
-        "English",
-        "Norwegian Nynorsk"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/122",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/122"
-    ],
-    "PID": "http://hdl.handle.net/11509/122",
-    "PublicationTimestamp": "2017-01-10T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "The Norwegian Association of Higher Education Institutions"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11509/4"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "CLARIN_PUB-BY",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaPub?BY=1",
-        "PUB"
-    ],
-    "author": [
-        "The Norwegian Association of Higher Education Institutions"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/122;2017-01-18T09:26:35Z;hdl_11509_1;hdl_11509_2;UHR's Termbase for Norwegian higher education institutions;The Norwegian Association of Higher Education Institutions;Administration;Higher education;Termbase;Terminological;Terminology;The resource UHR-basen is a terminological database containing terms, definitions and other conceptual information in Norwegian and English within administrative domains in higher education. \r\nThe termbase translates between British English and Norwegian bokm\u00e5l and Norwegian nynorsk, respectively.\r\nThe term base is owned by the Norwegian Association of Higher Education Institutions (UHR).\r\nThe term base has been made downloadable in TBX format by the META-NORD group at University of Bergen, with the kind permission of UHR.;2017-01-10;lexicalConceptualResource;http://hdl.handle.net/11509/122;nob;eng;nno;http://hdl.handle.net/11509/4;CLARIN_PUB-BY;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaPub?BY=1;PUB;application/zip;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;The Norwegian Association of Higher Education Institutions;http://www.terminologi.no",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "566515a0-b30a-5c06-8856-5f9e976e4877",
-    "notes": [
-        "The resource UHR-basen is a terminological database containing terms, definitions and other conceptual information in Norwegian and English within administrative domains in higher education. \r\nThe termbase translates between British English and Norwegian bokm\u00e5l and Norwegian nynorsk, respectively.\r\nThe term base is owned by the Norwegian Association of Higher Education Institutions (UHR).\r\nThe term base has been made downloadable in TBX format by the META-NORD group at University of Bergen, with the kind permission of UHR."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/122"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Administration"
-        },
-        {
-            "name": "Higher education"
-        },
-        {
-            "name": "Termbase"
-        },
-        {
-            "name": "Terminological"
-        },
-        {
-            "name": "Terminology"
-        }
-    ],
-    "title": [
-        "UHR's Termbase for Norwegian higher education institutions"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5676ed06-e68f-52b7-a343-c5b6aba0e8e8.json b/oaitestdata/clarin-oai_dc/SET_1/json/5676ed06-e68f-52b7-a343-c5b6aba0e8e8.json
deleted file mode 100644
index 05294a76..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5676ed06-e68f-52b7-a343-c5b6aba0e8e8.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "A"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1747",
-    "MetadataAccess": [
-        "oai:ota:oucs:1747"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Trollope, Anthony"
-    ],
-    "fulltext": "oai:ota:oucs:1747;2018-04-16T15:30:51Z;http://ota.ox.ac.uk/headers/1747.xml;Dr Wortle\"s School;Trollope, Anthony;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;A;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5676ed06-e68f-52b7-a343-c5b6aba0e8e8",
-    "oai_identifier": [
-        "oai:ota:oucs:1747"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Dr Wortle\"s School"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1747.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/56781a79-acaf-5cb8-af65-d736636a9e69.json b/oaitestdata/clarin-oai_dc/SET_1/json/56781a79-acaf-5cb8-af65-d736636a9e69.json
deleted file mode 100644
index 41700fbe..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/56781a79-acaf-5cb8-af65-d736636a9e69.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/551",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/551"
-    ],
-    "PID": "http://hdl.handle.net/11321/551",
-    "PublicationTimestamp": "2018-07-23T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "author": [
-        "Wr\u00f3blewska, Alina"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/551;2018-07-23T20:16:10Z;hdl_11321_3;hdl_11321_4;Polish Dependency Bank;Wr\u00f3blewska, Alina;Polish Dependency Bank;PDB;dependency grammar;Polish Dependency Bank (PDB) is the largest set of manually annotated dependency trees. PDB consists of more than 22K trees with 15.8 tokens per sentence on the average.;2018-07-23;lexicalConceptualResource;http://hdl.handle.net/11321/551;pol;downloadable_files_count: 0;Institute of Computer Science, Polish Academy of Sciences;http://zil.ipipan.waw.pl/PDB",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "56781a79-acaf-5cb8-af65-d736636a9e69",
-    "notes": [
-        "Polish Dependency Bank (PDB) is the largest set of manually annotated dependency trees. PDB consists of more than 22K trees with 15.8 tokens per sentence on the average."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/551"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Polish Dependency Bank"
-        },
-        {
-            "name": "PDB"
-        },
-        {
-            "name": "dependency grammar"
-        }
-    ],
-    "title": [
-        "Polish Dependency Bank"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/567e1372-6805-5732-9f25-d67bb9a09deb.json b/oaitestdata/clarin-oai_dc/SET_1/json/567e1372-6805-5732-9f25-d67bb9a09deb.json
deleted file mode 100644
index e29d311c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/567e1372-6805-5732-9f25-d67bb9a09deb.json
+++ /dev/null
@@ -1,88 +0,0 @@
-{
-    "Contact": [
-        "Charles University, UFAL"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "text/plain",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2509",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2509"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2509",
-    "PublicationTimestamp": "2017-11-13T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Charles University, UFAL"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-1821",
-        "http://hdl.handle.net/11234/1-2864"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Nov\u00e1k, Michal",
-        "M\u00edrovsk\u00fd, Ji\u0159\u00ed",
-        "Haji\u010dov\u00e1, Eva",
-        "Rysov\u00e1, Magdal\u00e9na",
-        "Rysov\u00e1, Kate\u0159ina"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2509;2018-10-23T16:43:28Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;EVALD 2.0 for Foreigners;Nov\u00e1k, Michal;Rysov\u00e1, Kate\u0159ina;M\u00edrovsk\u00fd, Ji\u0159\u00ed;Rysov\u00e1, Magdal\u00e9na;Haji\u010dov\u00e1, Eva;text coherence;discourse;automatic evaluation;non-native speakers;EVALD 2.0 for Foreigners is a software for automatic evaluation of surface coherence (cohesion) in Czech texts written by non-native speakers of Czech.;2017-11-13;toolService;http://hdl.handle.net/11234/1-2509;ces;http://hdl.handle.net/11234/1-1821;http://hdl.handle.net/11234/1-2864;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;text/plain;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University, UFAL;https://ufal.mff.cuni.cz/evald",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "567e1372-6805-5732-9f25-d67bb9a09deb",
-    "notes": [
-        "EVALD 2.0 for Foreigners is a software for automatic evaluation of surface coherence (cohesion) in Czech texts written by non-native speakers of Czech."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2509"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "text coherence"
-        },
-        {
-            "name": "discourse"
-        },
-        {
-            "name": "automatic evaluation"
-        },
-        {
-            "name": "non-native speakers"
-        }
-    ],
-    "title": [
-        "EVALD 2.0 for Foreigners"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/567e5900-709d-5d60-bf5c-7a04da19f764.json b/oaitestdata/clarin-oai_dc/SET_1/json/567e5900-709d-5d60-bf5c-7a04da19f764.json
deleted file mode 100644
index 9a858a70..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/567e5900-709d-5d60-bf5c-7a04da19f764.json
+++ /dev/null
@@ -1,88 +0,0 @@
-{
-    "Contact": [
-        "UAM"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/richtext",
-        "application/pdf",
-        "downloadable_files_count: 2"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/245",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/245"
-    ],
-    "PID": "http://hdl.handle.net/11321/245",
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "UAM"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Adamczyk, El\u017cbieta",
-        "Kopaczyk, Joanna",
-        "W\u0142odarczyk, Matylda"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/245;2016-02-10T07:37:16Z;hdl_11321_3;hdl_11321_4;ROThA_Vol. 2;W\u0142odarczyk, Matylda;Kopaczyk, Joanna;Adamczyk, El\u017cbieta;multilingualism;code-switching;medieval court oaths;Old Polish;Medieval Latin;Greater Poland;trial;2016;corpus;http://hdl.handle.net/11321/245;Old Polish, Latin, Polish;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;text/plain; charset=utf-8;application/pdf;text/richtext;downloadable_files_count: 2;UAM;http//:wa.amu.edu.pl",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "567e5900-709d-5d60-bf5c-7a04da19f764",
-    "notes": [
-        "trial"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/245"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "multilingualism"
-        },
-        {
-            "name": "code-switching"
-        },
-        {
-            "name": "medieval court oaths"
-        },
-        {
-            "name": "Old Polish"
-        },
-        {
-            "name": "Medieval Latin"
-        },
-        {
-            "name": "Greater Poland"
-        }
-    ],
-    "title": [
-        "ROThA_Vol. 2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/56b18e4d-5ee4-513a-906a-fa1b6fed883a.json b/oaitestdata/clarin-oai_dc/SET_1/json/56b18e4d-5ee4-513a-906a-fa1b6fed883a.json
deleted file mode 100644
index c4a4bcd0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/56b18e4d-5ee4-513a-906a-fa1b6fed883a.json
+++ /dev/null
@@ -1,92 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-        "University of Amsterdam, ILLC"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 5",
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "English",
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1672",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1672"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1672",
-    "PublicationTimestamp": "2016-03-21T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-        "University of Amsterdam, ILLC"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/H2020/645452"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Stanojevic, Milos",
-        "Bojar, Ond\u0159ej",
-        "Jawaid, Bushra",
-        "Kamran, Amir"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1672;2017-11-09T14:20:27Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;WMT16 Tuning Shared Task Models (English-to-Czech);Kamran, Amir;Jawaid, Bushra;Bojar, Ond\u0159ej;Stanojevic, Milos;WMT16;machine translation;tuning;baseline models;shared task;This item contains models to tune for the WMT16 Tuning shared task for English-to-Czech.\r\n\r\nCzEng 1.6pre (http://ufal.mff.cuni.cz/czeng/czeng16pre) corpus is used for the training of the translation models. The data is tokenized (using Moses tokenizer), lowercased and sentences longer than 60 words and shorter than 4 words are removed before training. Alignment is done using fast_align (https://github.com/clab/fast_align) and the standard Moses pipeline is used for training.\r\n\r\nTwo 5-gram language models are trained using KenLM: one only using the CzEng Czech data and the other is trained using all available Czech mono data for WMT except Common Crawl.\r\n\r\nAlso included are two lexicalized bidirectional reordering models, word based and hierarchical, with msd conditioned on both source and target of processed CzEng.;2016-03-21;corpus;http://hdl.handle.net/11372/LRT-1672;eng;ces;info:eu-repo/grantAgreement/EC/H2020/645452;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/x-gzip;application/x-gzip;application/x-gzip;application/octet-stream;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 5;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);University of Amsterdam, ILLC;http://www.statmt.org/wmt16/tuning-task/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "56b18e4d-5ee4-513a-906a-fa1b6fed883a",
-    "notes": [
-        "This item contains models to tune for the WMT16 Tuning shared task for English-to-Czech.\r\n\r\nCzEng 1.6pre (http://ufal.mff.cuni.cz/czeng/czeng16pre) corpus is used for the training of the translation models. The data is tokenized (using Moses tokenizer), lowercased and sentences longer than 60 words and shorter than 4 words are removed before training. Alignment is done using fast_align (https://github.com/clab/fast_align) and the standard Moses pipeline is used for training.\r\n\r\nTwo 5-gram language models are trained using KenLM: one only using the CzEng Czech data and the other is trained using all available Czech mono data for WMT except Common Crawl.\r\n\r\nAlso included are two lexicalized bidirectional reordering models, word based and hierarchical, with msd conditioned on both source and target of processed CzEng."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1672"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "WMT"
-        },
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "tuning"
-        },
-        {
-            "name": "baseline models"
-        },
-        {
-            "name": "shared task"
-        }
-    ],
-    "title": [
-        "WMT16 Tuning Shared Task Models (English-to-Czech)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/56b28b52-89c1-5c65-a756-c04ccaa94ee1.json b/oaitestdata/clarin-oai_dc/SET_1/json/56b28b52-89c1-5c65-a756-c04ccaa94ee1.json
deleted file mode 100644
index eca8160a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/56b28b52-89c1-5c65-a756-c04ccaa94ee1.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Institut f\u00fcr Deutsche Sprache"
-    ],
-    "Contributor": [
-        "Klosa, Annette"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-456",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-456"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-456",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut f\u00fcr Deutsche Sprache"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-456;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;elexiko-W\u00f6rterbuch (im elexiko-Portal);Klosa, Annette;XML;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-456;deu;downloadable_files_count: 0;Germany;Institut f\u00fcr Deutsche Sprache;http://www.owid.de/elexiko_/index.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "56b28b52-89c1-5c65-a756-c04ccaa94ee1",
-    "notes": [
-        "XML"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-456"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "elexiko-W\u00f6rterbuch (im elexiko-Portal)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/56d893c1-adc1-5a77-b3ab-08771aeb0d15.json b/oaitestdata/clarin-oai_dc/SET_1/json/56d893c1-adc1-5a77-b3ab-08771aeb0d15.json
deleted file mode 100644
index cde084d7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/56d893c1-adc1-5a77-b3ab-08771aeb0d15.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/84",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/84"
-    ],
-    "PID": "http://hdl.handle.net/10794/84",
-    "PublicationTimestamp": "2015-12-10T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/84;2017-10-26T07:52:34Z;hdl_10794_1;hdl_10794_2;Bet\u00e4nkande ang\u00e5ende likformig uppst\u00e4llning av grammatiska l\u00e4rob\u00f6cker (2015-12-11);Bet\u00e4nkande ang\u00e5ende likformig uppst\u00e4llning av grammatiska l\u00e4rob\u00f6cker (2015-12-11);n/a, n/a;Swedish;Deliberation report;Deliberation report on conformity of coursebooks in grammar 1882.;Bet\u00e4nkande ang\u00e5ende likformig uppst\u00e4llning av grammatiska l\u00e4rob\u00f6cker 1882.;2015-12-10;corpus;http://hdl.handle.net/10794/84;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;http://creativecommons.org/licenses/by/4.0/;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/betankande",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "56d893c1-adc1-5a77-b3ab-08771aeb0d15",
-    "notes": [
-        "Deliberation report on conformity of coursebooks in grammar 1882.",
-        "Bet\u00e4nkande ang\u00e5ende likformig uppst\u00e4llning av grammatiska l\u00e4rob\u00f6cker 1882."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/84"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Deliberation report"
-        }
-    ],
-    "title": [
-        "Bet\u00e4nkande ang\u00e5ende likformig uppst\u00e4llning av grammatiska l\u00e4rob\u00f6cker (2015-12-11)",
-        "Bet\u00e4nkande ang\u00e5ende likformig uppst\u00e4llning av grammatiska l\u00e4rob\u00f6cker (2015-12-11)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/56dddd0c-f219-5b94-a51d-5c60029de65d.json b/oaitestdata/clarin-oai_dc/SET_1/json/56dddd0c-f219-5b94-a51d-5c60029de65d.json
deleted file mode 100644
index 931aba34..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/56dddd0c-f219-5b94-a51d-5c60029de65d.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Greg, W.W. (Walter Wilson), 1875-1959",
-        "Lancashire, Ian"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 118 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1343",
-    "MetadataAccess": [
-        "oai:ota:oucs:1343"
-    ],
-    "PublicationTimestamp": "1553-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1553"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Udall, Nicholas, 1505-1556"
-    ],
-    "fulltext": "oai:ota:oucs:1343;2018-04-26T12:27:17Z;http://ota.ox.ac.uk/headers/1343.xml;Respublica : an interlude for Christmas 1553 / Nicholas Udall;Udall, Nicholas, 1505-1556;1553;text_and_corpus_linguistics;English drama -- 16th century;eng;Oxford Text Archive, University of Oxford;Greg, W.W. (Walter Wilson), 1875-1959;Lancashire, Ian;(1 file : ca. 118 KB);Text;Plays;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "56dddd0c-f219-5b94-a51d-5c60029de65d",
-    "oai_identifier": [
-        "oai:ota:oucs:1343"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- th century"
-        }
-    ],
-    "title": [
-        "Respublica : an interlude for Christmas 1553 / Nicholas Udall"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1343.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/56ed53e8-715a-5006-ac9c-5aa5b73076c5.json b/oaitestdata/clarin-oai_dc/SET_1/json/56ed53e8-715a-5006-ac9c-5aa5b73076c5.json
deleted file mode 100644
index 4fed34d9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/56ed53e8-715a-5006-ac9c-5aa5b73076c5.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3427",
-    "MetadataAccess": [
-        "oai:ota:oucs:3427"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Radcliffe, Ann Ward, 1764-1823."
-    ],
-    "fulltext": "oai:ota:oucs:3427;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3427.xml;The romance of the forest: interspersed with some pieces of poetry. By the authoress of \"A Sicilian romance,\" &c. In two volumes. ... [pt.2];Radcliffe, Ann Ward, 1764-1823.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "56ed53e8-715a-5006-ac9c-5aa5b73076c5",
-    "oai_identifier": [
-        "oai:ota:oucs:3427"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The romance of the forest: interspersed with some pieces of poetry. By the authoress of \"A Sicilian romance,\" &c. In two volumes. ... [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3427.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/56eedb50-9a11-59ed-9834-6e6b592a49fc.json b/oaitestdata/clarin-oai_dc/SET_1/json/56eedb50-9a11-59ed-9834-6e6b592a49fc.json
deleted file mode 100644
index 4ef26fab..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/56eedb50-9a11-59ed-9834-6e6b592a49fc.json
+++ /dev/null
@@ -1,99 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 3",
-        "application/pdf",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Croatian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1170",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1170"
-    ],
-    "PID": "http://hdl.handle.net/11356/1170",
-    "PublicationTimestamp": "2017-12-16T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "http://dx.doi.org/10.4312/slo2.0.2016.2.156-188",
-        "http://hdl.handle.net/11356/1121"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "Erjavec, Toma\u017e",
-        "Samard\u017ei\u0107, Tanja",
-        "Ljube\u0161i\u0107, Nikola",
-        "Mili\u010devi\u0107, Maja"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1170;2018-10-24T20:18:20Z;hdl_11356_1023;hdl_11356_1024;Croatian Twitter training corpus ReLDI-NormTagNER-hr 2.0;Ljube\u0161i\u0107, Nikola;Erjavec, Toma\u017e;Mili\u010devi\u0107, Maja;Samard\u017ei\u0107, Tanja;computer-mediated communication;tokenisation;word normalisation;tagging;lemmatisation;named entities;manual annotation;TEI;ReLDI-NormTagNER-hr 2.0 is a manually annotated corpus of Croatian tweets. It is meant as a gold-standard training and testing dataset for tokenisation, sentence segmentation, word normalisation, morphosyntactic tagging, lemmatisation and named entity recognition of non-standard Croatian. Each tweet is also annotated for its automatically assigned standardness levels (T = technical standardness, L = linguistic standardness). As an update to version 1.1, 2.0 adds annotations for named entities.;2017-12-16;corpus;http://hdl.handle.net/11356/1170;hrv;http://dx.doi.org/10.4312/slo2.0.2016.2.156-188;http://hdl.handle.net/11356/1121;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;https://creativecommons.org/licenses/by/4.0/;application/zip;application/zip;application/pdf;text/plain; charset=utf-8;downloadable_files_count: 3;Jo\u017eef Stefan Institute;https://reldi.spur.uzh.ch/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "56eedb50-9a11-59ed-9834-6e6b592a49fc",
-    "notes": [
-        "ReLDI-NormTagNER-hr 2.0 is a manually annotated corpus of Croatian tweets. It is meant as a gold-standard training and testing dataset for tokenisation, sentence segmentation, word normalisation, morphosyntactic tagging, lemmatisation and named entity recognition of non-standard Croatian. Each tweet is also annotated for its automatically assigned standardness levels (T = technical standardness, L = linguistic standardness). As an update to version 1.1, 2.0 adds annotations for named entities."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1170"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "computer-mediated communication"
-        },
-        {
-            "name": "tokenisation"
-        },
-        {
-            "name": "word normalisation"
-        },
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "lemmatisation"
-        },
-        {
-            "name": "named entities"
-        },
-        {
-            "name": "manual annotation"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "Croatian Twitter training corpus ReLDI-NormTagNER-hr 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/56fc9cc7-8c5c-55f3-98c0-9dc1a83ff25b.json b/oaitestdata/clarin-oai_dc/SET_1/json/56fc9cc7-8c5c-55f3-98c0-9dc1a83ff25b.json
deleted file mode 100644
index c457fc4c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/56fc9cc7-8c5c-55f3-98c0-9dc1a83ff25b.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "The Department of Modern Languages, University of Helsinki",
-        "University of Helsinki"
-    ],
-    "Contributor": [
-        "Kopotev, Mikhail",
-        "Mustajoki, Arto"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Russian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-745",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-745"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-745",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "The Department of Modern Languages, University of Helsinki",
-        "University of Helsinki"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Finland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-745;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Helsinki annotated corpus of Russian language HANCO;Kopotev, Mikhail;Mustajoki, Arto;Coprus linguistics;Morphologically and syntactically annotated corpus of the modern Russian language.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-745;rus;application/octet-stream;downloadable_files_count: 0;Finland;The Department of Modern Languages, University of Helsinki;University of Helsinki;http://www.helsinki.fi/venaja/english/e-material/hanco/index.htm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "56fc9cc7-8c5c-55f3-98c0-9dc1a83ff25b",
-    "notes": [
-        "Morphologically and syntactically annotated corpus of the modern Russian language."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-745"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Coprus linguistics"
-        }
-    ],
-    "title": [
-        "Helsinki annotated corpus of Russian language HANCO"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/57530216-05e5-5352-8375-15d88b5e4aa5.json b/oaitestdata/clarin-oai_dc/SET_1/json/57530216-05e5-5352-8375-15d88b5e4aa5.json
deleted file mode 100644
index b71ef1ac..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/57530216-05e5-5352-8375-15d88b5e4aa5.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5049",
-    "MetadataAccess": [
-        "oai:ota:oucs:5049"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Trusler, John, 1735-1820."
-    ],
-    "fulltext": "oai:ota:oucs:5049;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5049.xml;The habitable world described: or the present state of the people in all parts of the globe, from north to south; shewing the situation, extent, climate, ... including all the new discoveries: ... With a great variety of maps and copper-plates, ... By the Rev. Dr. John Trusler. ... [pt.15];Trusler, John, 1735-1820.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "57530216-05e5-5352-8375-15d88b5e4aa5",
-    "oai_identifier": [
-        "oai:ota:oucs:5049"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The habitable world described: or the present state of the people in all parts of the globe, from north to south; shewing the situation, extent, climate, ... including all the new discoveries: ... With a great variety of maps and copper-plates, ... By the Rev. Dr. John Trusler. ... [pt.15]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5049.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/575f713c-5ecd-5ee6-bd27-ffcbcc9aaf31.json b/oaitestdata/clarin-oai_dc/SET_1/json/575f713c-5ecd-5ee6-bd27-ffcbcc9aaf31.json
deleted file mode 100644
index 222368db..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/575f713c-5ecd-5ee6-bd27-ffcbcc9aaf31.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3857",
-    "MetadataAccess": [
-        "oai:ota:oucs:3857"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Donovan, E. (Edward), 1768-1837."
-    ],
-    "fulltext": "oai:ota:oucs:3857;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3857.xml;The natural history of British shells: ... By E. Donovan, ... [pt.1];Donovan, E. (Edward), 1768-1837.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "575f713c-5ecd-5ee6-bd27-ffcbcc9aaf31",
-    "oai_identifier": [
-        "oai:ota:oucs:3857"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The natural history of British shells: ... By E. Donovan, ... [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3857.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/578cee21-de42-50a3-ba88-ce09a58eaa60.json b/oaitestdata/clarin-oai_dc/SET_1/json/578cee21-de42-50a3-ba88-ce09a58eaa60.json
deleted file mode 100644
index bf84dbd1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/578cee21-de42-50a3-ba88-ce09a58eaa60.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3048",
-    "MetadataAccess": [
-        "oai:ota:oucs:3048"
-    ],
-    "PublicationTimestamp": "1899-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1899"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Conrad, Joseph, 1857-1924"
-    ],
-    "fulltext": "oai:ota:oucs:3048;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3048.xml;Lord Jim;Conrad, Joseph, 1857-1924;1899;text_and_corpus_linguistics;British -- Indonesia -- Fiction;Seafaring life -- Indonesia -- Fiction;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "578cee21-de42-50a3-ba88-ce09a58eaa60",
-    "oai_identifier": [
-        "oai:ota:oucs:3048"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "British -- Indonesia -- Fiction"
-        },
-        {
-            "name": "Seafaring life -- Indonesia -- Fiction"
-        }
-    ],
-    "title": [
-        "Lord Jim"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3048.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/57cd1e7b-3de7-57bb-b18b-ba01d58798a2.json b/oaitestdata/clarin-oai_dc/SET_1/json/57cd1e7b-3de7-57bb-b18b-ba01d58798a2.json
deleted file mode 100644
index ecfda0ed..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/57cd1e7b-3de7-57bb-b18b-ba01d58798a2.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "Contributor": [
-        "Lorente, Merc\u00e8"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Catalan",
-        "English",
-        "French",
-        "Galician",
-        "Italian",
-        "Portuguese",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-702",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-702"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-702",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-702;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Basic vocabulary on the Human Genome;Lorente, Merc\u00e8;A vocabulary resulting from the cooperation of the groups of REALITER network that collects the basic terminology mostly used in texts about Genomics. It contains equivalents in English, Peninsular and Latinamerican Spanish, French, Italian, Galician, Portuguese and Catalan.;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-702;cat;eng;fra;glg;ita;por;spa;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra;http://www.iula.upf.edu/rec/vbgenoma/esp/index.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "57cd1e7b-3de7-57bb-b18b-ba01d58798a2",
-    "notes": [
-        "A vocabulary resulting from the cooperation of the groups of REALITER network that collects the basic terminology mostly used in texts about Genomics. It contains equivalents in English, Peninsular and Latinamerican Spanish, French, Italian, Galician, Portuguese and Catalan."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-702"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Basic vocabulary on the Human Genome"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/57d03ed4-8df5-5c54-920c-a24548aec1fe.json b/oaitestdata/clarin-oai_dc/SET_1/json/57d03ed4-8df5-5c54-920c-a24548aec1fe.json
deleted file mode 100644
index fae1d04f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/57d03ed4-8df5-5c54-920c-a24548aec1fe.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4369",
-    "MetadataAccess": [
-        "oai:ota:oucs:4369"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Sheridan, Richard Brinsley, 1751-1816."
-    ],
-    "fulltext": "oai:ota:oucs:4369;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4369.xml;The duenna: a comic opera. In three acts. As performed at the Theatre Royal, Covent Garden: with universal applause. By R. B. Sheridan, Esq;Sheridan, Richard Brinsley, 1751-1816.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "57d03ed4-8df5-5c54-920c-a24548aec1fe",
-    "oai_identifier": [
-        "oai:ota:oucs:4369"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The duenna: a comic opera. In three acts. As performed at the Theatre Royal, Covent Garden: with universal applause. By R. B. Sheridan, Esq"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4369.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/57fa3e65-4e5b-5828-b7d4-1dc0f9022c72.json b/oaitestdata/clarin-oai_dc/SET_1/json/57fa3e65-4e5b-5828-b7d4-1dc0f9022c72.json
deleted file mode 100644
index 2bc14fe1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/57fa3e65-4e5b-5828-b7d4-1dc0f9022c72.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(2 files : ca. 105, 82 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "Serbian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0382",
-    "MetadataAccess": [
-        "oai:ota:oucs:0382"
-    ],
-    "PublicationTimestamp": "1840-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1840"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Peter II, Prince-Bishop of Montenegro, 1813-1851"
-    ],
-    "fulltext": "oai:ota:oucs:0382;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0382.xml;Gorski vijenac;\u00d0\u0093\u00d0\u00be\u00d1\u0080\u00d1\u0081\u00d0\u00ba\u00d0\u00b8 \u00d0\u00b2\u00d0\u00b8\u00d1\u0098\u00d0\u00b5\u00d0\u00bd\u00d0\u00b0\u00d1\u0086;The mountain wreath;Peter II, Prince-Bishop of Montenegro, 1813-1851;1840-1867;text_and_corpus_linguistics;Serbian literature;Montenegrin literature;srp;cnr;Oxford Text Archive, University of Oxford;text/plain;(2 files : ca. 105, 82 KB);Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "57fa3e65-4e5b-5828-b7d4-1dc0f9022c72",
-    "oai_identifier": [
-        "oai:ota:oucs:0382"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Serbian literature"
-        },
-        {
-            "name": "Montenegrin literature"
-        }
-    ],
-    "title": [
-        "Gorski vijenac",
-        "\u00d0\u0093\u00d0\u00be\u00d1\u0080\u00d1\u0081\u00d0\u00ba\u00d0\u00b8 \u00d0\u00b2\u00d0\u00b8\u00d1\u0098\u00d0\u00b5\u00d0\u00bd\u00d0\u00b0\u00d1\u0086",
-        "The mountain wreath"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0382.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/58152879-293a-5c1c-a8a0-a3b081955d92.json b/oaitestdata/clarin-oai_dc/SET_1/json/58152879-293a-5c1c-a8a0-a3b081955d92.json
deleted file mode 100644
index 04e7d9cc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/58152879-293a-5c1c-a8a0-a3b081955d92.json
+++ /dev/null
@@ -1,127 +0,0 @@
-{
-    "Contact": [
-        "CLARIN-D",
-        "Universit\u00e4t des Saarlandes",
-        "Justus Liebig University Giessen",
-        "Tim Hitchcock",
-        "Robert Shoemaker"
-    ],
-    "Contributor": [
-        "Sumithra Velupillai",
-        "Schneider, Ulrike",
-        "Justus Liebig University Giessen. Faculty 05 Language, Literature, Culture. \nDepartment of English. English Linguistics and History of English",
-        "Langbein, Sven",
-        "Wunderlich, Julie",
-        "Nissel, Magnus",
-        "Kr\u00e4mer, Christina",
-        "Widlitzki, Bianca",
-        "El Basiouni, Sina",
-        "Halpap, Melanie",
-        "Hartmann, Carina",
-        "Reeh, Elisabeth",
-        "Petri, Sonja",
-        "Molke, Veronika",
-        "Werner, Janina",
-        "Bundesministerium f\u00fcr Bildung und Forschung",
-        "Maiwald, Patrick",
-        "Brunner, Christine",
-        "Puga, Karin",
-        "Batt, Oleg",
-        "Deutsche Forschungsgemeinschaft",
-        "Schunert, Nora",
-        "Breitenbach, Daniela",
-        "Salomon, Saskia",
-        "Huber, Magnus",
-        "Kircili, Kathrin"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:oldbailey",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:oldbailey"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CFB-2",
-    "Publisher": [
-        "CLARIN-D",
-        "Universit\u00e4t des Saarlandes",
-        "Justus Liebig University Giessen",
-        "Tim Hitchcock",
-        "Robert Shoemaker"
-    ],
-    "RelatedIdentifier": [
-        "uni-giessen.de/oldbaileycorpus/search.html",
-        "uni-giessen.de/oldbaileycorpus/download.html"
-    ],
-    "ResourceType": [
-        "Dataset",
-        "spoken text"
-    ],
-    "Rights": [
-        "You are free to: Share - copy and redistribute the material in any medium or format; Adapt - remix, transform, and build upon the material. Under the following terms: Attribution - You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use. NonCommercial - You may not use the material for commercial purposes. ShareAlike - If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original. No additional restrictions - You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits."
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:oldbailey;2016-07-22T16:17:59Z;The Old Bailey Corpus;historical linguistics;morphology;syntax;pragmatics;semantics;text and corpus linguistics;historical sociolinguistics;historical corpus;courtroom language;Late Modern English;British English;The Old Bailey Corpus is a sociolinguistically, pragmatically and textually annotated selection of the Proceedings of the Old Bailey. These speech-related texts document Late Modern English in London's Central Criminal Court from 1720 to 1913;Robert Shoemaker;Tim Hitchcock;Justus Liebig University Giessen;Universit\u00e4t des Saarlandes;CLARIN-D;Justus Liebig University Giessen. Faculty 05 Language, Literature, Culture. \nDepartment of English. English Linguistics and History of English;Huber, Magnus;Huber, Magnus;Nissel, Magnus;Nissel, Magnus;Maiwald, Patrick;Maiwald, Patrick;Puga, Karin;Puga, Karin;Werner, Janina;Werner, Janina;Widlitzki, Bianca;Widlitzki, Bianca;El Basiouni, Sina;Hartmann, Carina;Kircili, Kathrin;Reeh, Elisabeth;Salomon, Saskia;Breitenbach, Daniela;Wunderlich, Julie;Batt, Oleg;Schunert, Nora;Petri, Sonja;Brunner, Christine;Kr\u00e4mer, Christina;Schneider, Ulrike;Langbein, Sven;Halpap, Melanie;Molke, Veronika;Sumithra Velupillai;Deutsche Forschungsgemeinschaft;Bundesministerium f\u00fcr Bildung und Forschung;Dataset;spoken text;text/xml;clarind-uds:oldbailey;hdl:11858/00-246C-0000-0023-8CFB-2;eng;uni-giessen.de/oldbaileycorpus/search.html;uni-giessen.de/oldbaileycorpus/download.html;You are free to: Share - copy and redistribute the material in any medium or format; Adapt - remix, transform, and build upon the material. Under the following terms: Attribution - You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use. NonCommercial - You may not use the material for commercial purposes. ShareAlike - If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original. No additional restrictions - You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "58152879-293a-5c1c-a8a0-a3b081955d92",
-    "notes": [
-        "The Old Bailey Corpus is a sociolinguistically, pragmatically and textually annotated selection of the Proceedings of the Old Bailey. These speech-related texts document Late Modern English in London's Central Criminal Court from 1720 to 1913"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:oldbailey"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "historical linguistics"
-        },
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "syntax"
-        },
-        {
-            "name": "pragmatics"
-        },
-        {
-            "name": "semantics"
-        },
-        {
-            "name": "text corpus linguistics"
-        },
-        {
-            "name": "historical sociolinguistics"
-        },
-        {
-            "name": "historical corpus"
-        },
-        {
-            "name": "courtroom language"
-        },
-        {
-            "name": "Late Modern English"
-        },
-        {
-            "name": "British English"
-        }
-    ],
-    "title": [
-        "The Old Bailey Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/581b9c93-ff07-5f6b-bb92-29e62e7b260b.json b/oaitestdata/clarin-oai_dc/SET_1/json/581b9c93-ff07-5f6b-bb92-29e62e7b260b.json
deleted file mode 100644
index f49fe8b7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/581b9c93-ff07-5f6b-bb92-29e62e7b260b.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5346",
-    "MetadataAccess": [
-        "oai:ota:oucs:5346"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Goldsmith, Oliver, 1730?-1774."
-    ],
-    "fulltext": "oai:ota:oucs:5346;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5346.xml;The miscellaneous works of Oliver Goldsmith, M.B. Containing all his essays and poems;Goldsmith, Oliver, 1730?-1774.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "581b9c93-ff07-5f6b-bb92-29e62e7b260b",
-    "oai_identifier": [
-        "oai:ota:oucs:5346"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The miscellaneous works of Oliver Goldsmith, M.B. Containing all his essays and poems"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5346.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/582b4bfd-4090-5c91-b10d-609b82de0bcd.json b/oaitestdata/clarin-oai_dc/SET_1/json/582b4bfd-4090-5c91-b10d-609b82de0bcd.json
deleted file mode 100644
index 8892ad07..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/582b4bfd-4090-5c91-b10d-609b82de0bcd.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Institute of Mathematics and Computer Science, University of Latvia"
-    ],
-    "Contributor": [
-        "Lev\u0101ne-Petrova, Krist\u012bne"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Latvian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-185",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-185"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-185",
-    "PublicationTimestamp": "2001-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2001"
-    ],
-    "Publisher": [
-        "Institute of Mathematics and Computer Science, University of Latvia"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Latvia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-185;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Corpus \"Pl\u0101ns ledus\";Lev\u0101ne-Petrova, Krist\u012bne;Morphologically tagged and lemmatized text sample (> 16 000 running words), publicly available via Bonito interface;2001;corpus;http://hdl.handle.net/11372/LRT-185;lav;text/sgml;downloadable_files_count: 0;Latvia;Institute of Mathematics and Computer Science, University of Latvia;http://www.korpuss.lv",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "582b4bfd-4090-5c91-b10d-609b82de0bcd",
-    "notes": [
-        "Morphologically tagged and lemmatized text sample (> 16 000 running words), publicly available via Bonito interface"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-185"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus \"Pl\u0101ns ledus\""
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/582e326c-283b-5ba2-abcd-5545ef663f9b.json b/oaitestdata/clarin-oai_dc/SET_1/json/582e326c-283b-5ba2-abcd-5545ef663f9b.json
deleted file mode 100644
index 1080d13c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/582e326c-283b-5ba2-abcd-5545ef663f9b.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 721 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2015",
-    "MetadataAccess": [
-        "oai:ota:oucs:2015"
-    ],
-    "PublicationTimestamp": "1855-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1855"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Bulfinch, Thomas, 1796-1867"
-    ],
-    "fulltext": "oai:ota:oucs:2015;2018-03-01T11:55:06Z;http://ota.ox.ac.uk/headers/2015.xml;Bulfinch's Mythology: the age of fable, or, Stories of gods and heroes;Bulfinch, Thomas, 1796-1867;1855;text_and_corpus_linguistics;Fiction -- United States -- 19th century;Fables -- United States -- 19th century;Myths and legends -- United States -- 19th century;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 721 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "582e326c-283b-5ba2-abcd-5545ef663f9b",
-    "oai_identifier": [
-        "oai:ota:oucs:2015"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- United States -- th century"
-        },
-        {
-            "name": "Fables -- United States -- th century"
-        }
-    ],
-    "title": [
-        "Bulfinch's Mythology: the age of fable, or, Stories of gods and heroes"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2015.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/58333b11-502e-5a0d-962d-237c6a4bec7c.json b/oaitestdata/clarin-oai_dc/SET_1/json/58333b11-502e-5a0d-962d-237c6a4bec7c.json
deleted file mode 100644
index 17f62297..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/58333b11-502e-5a0d-962d-237c6a4bec7c.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-75",
-    "MetadataAccess": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-75"
-    ],
-    "PID": "http://hdl.handle.net/20.500.11752/ILC-75",
-    "PublicationTimestamp": "2012-09-01T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/248064"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Francesco Rubino"
-    ],
-    "fulltext": "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-75;2018-12-05T08:39:50Z;hdl_000-c0-111_38;hdl_000-c0-111_49;Desr web service;Francesco Rubino;Dependency parser;Italian Language;Written language;Syntactic analysis;Desr is a web service that performs dependency parsing on Italian tokenised, part-of-speech tagged, morphologically analysed texts. The web service was originally deployed by CNR-ILC within the EU-FP7-STREP PANACEA project (www.panacea-lr.eu) and implements the 2007 DeSR Parser [r4] code developed at the University of Pisa by Prof. Attardi and his group, and available at https://sourceforge.net/p/desr/code/HEAD/tree/branches. \r\nFor details on the tool and code please see http://desr.sourceforge.net and the scientific references therein.;2012-09-01;toolService;http://hdl.handle.net/20.500.11752/ILC-75;ita;info:eu-repo/grantAgreement/EC/FP7/248064;downloadable_files_count: 0;Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR);http://www.panacea-lr.eu",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "58333b11-502e-5a0d-962d-237c6a4bec7c",
-    "notes": [
-        "Desr is a web service that performs dependency parsing on Italian tokenised, part-of-speech tagged, morphologically analysed texts. The web service was originally deployed by CNR-ILC within the EU-FP7-STREP PANACEA project (www.panacea-lr.eu) and implements the 2007 DeSR Parser [r4] code developed at the University of Pisa by Prof. Attardi and his group, and available at https://sourceforge.net/p/desr/code/HEAD/tree/branches. \r\nFor details on the tool and code please see http://desr.sourceforge.net and the scientific references therein."
-    ],
-    "oai_identifier": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-75"
-    ],
-    "oai_set": [
-        "hdl_000-c0-111_38",
-        "hdl_000-c0-111_49"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Dependency parser"
-        },
-        {
-            "name": "Italian Language"
-        },
-        {
-            "name": "Written language"
-        },
-        {
-            "name": "Syntactic analysis"
-        }
-    ],
-    "title": [
-        "Desr web service"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/584130be-71a4-5856-9f17-b33a06fc932d.json b/oaitestdata/clarin-oai_dc/SET_1/json/584130be-71a4-5856-9f17-b33a06fc932d.json
deleted file mode 100644
index cc183b66..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/584130be-71a4-5856-9f17-b33a06fc932d.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=1080f78c18e511e6a2aa782bcb074135cc49b387f62540ec8422441f375c1f65",
-    "MetadataAccess": [
-        "1080f78c18e511e6a2aa782bcb074135cc49b387f62540ec8422441f375c1f65"
-    ],
-    "PublicationTimestamp": "2016-05-13T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "fulltext": "1080f78c18e511e6a2aa782bcb074135cc49b387f62540ec8422441f375c1f65;2018-11-15T16:40:20Z;corpus;corpus:text;News-QTLeap WSD/NED corpus;The texts are sentences from the News parallel corpus. The texts contain monolingual sentences from parallel corpora for the following pairs: Basque-English, Bulgarian-English, Czech-English, Portuguese-English and Spanish-English. The English corpus is comprised by the English side of the Spanish-English corpus.\nThe texts have been automatically annotated with NLP tools, including Word\nSense Disambiguation, Named Entity Disambiguation and Coreference\nresolution.;2016-05-13",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "584130be-71a4-5856-9f17-b33a06fc932d",
-    "notes": [
-        "The texts are sentences from the News parallel corpus. The texts contain monolingual sentences from parallel corpora for the following pairs: Basque-English, Bulgarian-English, Czech-English, Portuguese-English and Spanish-English. The English corpus is comprised by the English side of the Spanish-English corpus.\nThe texts have been automatically annotated with NLP tools, including Word\nSense Disambiguation, Named Entity Disambiguation and Coreference\nresolution."
-    ],
-    "oai_identifier": [
-        "1080f78c18e511e6a2aa782bcb074135cc49b387f62540ec8422441f375c1f65"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "News-QTLeap WSD/NED corpus"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/58579171-f078-57fc-9f5d-5be4f53a1dc6.json b/oaitestdata/clarin-oai_dc/SET_1/json/58579171-f078-57fc-9f5d-5be4f53a1dc6.json
deleted file mode 100644
index 82a05376..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/58579171-f078-57fc-9f5d-5be4f53a1dc6.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology",
-        "University of Warsaw"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/zip",
-        "downloadable_files_count: 10",
-        "application/msword"
-    ],
-    "Language": [],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/365",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/365"
-    ],
-    "PID": "http://hdl.handle.net/11321/365",
-    "PublicationTimestamp": "2017-04-25T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology",
-        "University of Warsaw"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "K\u0119pi\u0144ska, ALINA"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/365;2017-07-08T16:21:56Z;hdl_11321_3;hdl_11321_4;diachronic1;K\u0119pi\u0144ska, ALINA;diachronic;HISTORY;2017-04-25;corpus;http://hdl.handle.net/11321/365;pso;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;application/msword;application/msword;application/msword;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;downloadable_files_count: 10;University of Warsaw;Wroc\u0142aw University of Technology;http://www.us.edu.pl",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "58579171-f078-57fc-9f5d-5be4f53a1dc6",
-    "notes": [
-        "HISTORY"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/365"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "diachronic"
-        }
-    ],
-    "title": [
-        "diachronic1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/58676b59-399a-57c1-a627-f6abf88aff26.json b/oaitestdata/clarin-oai_dc/SET_1/json/58676b59-399a-57c1-a627-f6abf88aff26.json
deleted file mode 100644
index 1f23dd84..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/58676b59-399a-57c1-a627-f6abf88aff26.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5002",
-    "MetadataAccess": [
-        "oai:ota:oucs:5002"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Taylor, Thomas, 1738-1816."
-    ],
-    "fulltext": "oai:ota:oucs:5002;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5002.xml;An answer to the first part of The age of reason: Printed in 1794. By Thomas Taylor, V.D.M.;Taylor, Thomas, 1738-1816.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "58676b59-399a-57c1-a627-f6abf88aff26",
-    "oai_identifier": [
-        "oai:ota:oucs:5002"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An answer to the first part of The age of reason: Printed in 1794. By Thomas Taylor, V.D.M."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5002.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5879c93f-fbe4-5137-9713-16b55d51d4fa.json b/oaitestdata/clarin-oai_dc/SET_1/json/5879c93f-fbe4-5137-9713-16b55d51d4fa.json
deleted file mode 100644
index f3073b81..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5879c93f-fbe4-5137-9713-16b55d51d4fa.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "application/gzip",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/537",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/537"
-    ],
-    "PID": "http://hdl.handle.net/11321/537",
-    "PublicationTimestamp": "2018-07-20T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Lupa, Jan",
-        "Jaworski, Wojciech",
-        "Oklesi\u0144ski, Daniel"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/537;2018-07-22T07:26:20Z;hdl_11321_3;hdl_11321_4;Integrated Parser;Jaworski, Wojciech;Oklesi\u0144ski, Daniel;Lupa, Jan;constituency parsing;dependency parsing;Integrated parser is an application that combines and normalizes outputs of several parsers for Polish. It is based on ENIAM processing stream extended with Polish Dependency Parser, \u015awigra and POLFIE. Particular parsers may turned on and off according to the user requirements.;2018-07-20;toolService;http://hdl.handle.net/11321/537;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain; charset=utf-8;application/octet-stream;application/gzip;downloadable_files_count: 2;Institute of Computer Science, Polish Academy of Sciences",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5879c93f-fbe4-5137-9713-16b55d51d4fa",
-    "notes": [
-        "Integrated parser is an application that combines and normalizes outputs of several parsers for Polish. It is based on ENIAM processing stream extended with Polish Dependency Parser, \u015awigra and POLFIE. Particular parsers may turned on and off according to the user requirements."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/537"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "constituency parsing"
-        },
-        {
-            "name": "dependency parsing"
-        }
-    ],
-    "title": [
-        "Integrated Parser"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5885ab76-561c-52c4-bda7-3134e5090f14.json b/oaitestdata/clarin-oai_dc/SET_1/json/5885ab76-561c-52c4-bda7-3134e5090f14.json
deleted file mode 100644
index 5416b863..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5885ab76-561c-52c4-bda7-3134e5090f14.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "Contributor": [
-        "Gullberg, Marianne"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-612",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-612"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-612",
-    "PublicationTimestamp": "2007-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2007"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-612;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Code-switching conversation corpus;Gullberg, Marianne;The code-switching corpus consists of 5x30-minute conversations between four speakers (i.e. a total of 20 speakers). The speakers are bilingual speakers of Papiamento (a creole langauge spoken in the Dutch Antilles) and Dutch. In the course of their free conversations, they engage in code-switching, that is, they use both languages within the same utterance in systematic ways. The corpus is fully transcribed and glossed, coded for language and word class, in ELAN.;2007;corpus;http://hdl.handle.net/11372/LRT-612;nld;downloadable_files_count: 0;Netherlands (the);Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser/?openpath=MPI75934%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5885ab76-561c-52c4-bda7-3134e5090f14",
-    "notes": [
-        "The code-switching corpus consists of 5x30-minute conversations between four speakers (i.e. a total of 20 speakers). The speakers are bilingual speakers of Papiamento (a creole langauge spoken in the Dutch Antilles) and Dutch. In the course of their free conversations, they engage in code-switching, that is, they use both languages within the same utterance in systematic ways. The corpus is fully transcribed and glossed, coded for language and word class, in ELAN."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-612"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Code-switching conversation corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/58863c39-2f88-5fdd-a131-9f9113b224a3.json b/oaitestdata/clarin-oai_dc/SET_1/json/58863c39-2f88-5fdd-a131-9f9113b224a3.json
deleted file mode 100644
index 957e12cc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/58863c39-2f88-5fdd-a131-9f9113b224a3.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5426",
-    "MetadataAccess": [
-        "oai:ota:oucs:5426"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Sheridan, Richard, d. 1793."
-    ],
-    "fulltext": "oai:ota:oucs:5426;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5426.xml;Mr. Sheridan's argument in the case of Daly against Magee, on a motion to discharge the defendant on common bail;Sheridan, Richard, d. 1793.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "58863c39-2f88-5fdd-a131-9f9113b224a3",
-    "oai_identifier": [
-        "oai:ota:oucs:5426"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Mr. Sheridan's argument in the case of Daly against Magee, on a motion to discharge the defendant on common bail"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5426.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/588a08ba-1591-5e98-bc33-5d093c3b2800.json b/oaitestdata/clarin-oai_dc/SET_1/json/588a08ba-1591-5e98-bc33-5d093c3b2800.json
deleted file mode 100644
index 63e77805..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/588a08ba-1591-5e98-bc33-5d093c3b2800.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-62",
-    "MetadataAccess": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-62"
-    ],
-    "PID": "http://hdl.handle.net/20.500.11752/ILC-62",
-    "PublicationTimestamp": "2016-12-02T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Bertagna, Francesca",
-        "Marinelli, Rita",
-        "Roventini, Adriana"
-    ],
-    "fulltext": "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-62;2018-01-26T10:58:30Z;hdl_000-c0-111_38;hdl_000-c0-111_49;ItalWordNet v.2;Roventini, Adriana;Marinelli, Rita;Bertagna, Francesca;Italian Language;WordNet;Lexical Semantics;Language Resource;ItalWordNet (IWN) is a lexical-semantic database developed in the framework of two different research projects: EuroWordNet (EWN) and Sistema Integrato per il Trattamento Automatico del Linguaggio (SI-TAL).\r\n\r\nIWN is structured in the same way as the Princeton WordNet, namely around the notion of synset. Following the model designed in EWN, IWN encodes a rich set of semantic relations. In addition to the internal language relations, equivalence relations were also encoded between Italian synsets and the closest concepts in an Inter-Lingual Index (ILI), a separate language-independent module containing all WN1.5 synsets but not the relations among them.\r\nIWN now contains information about Italian Nouns, Verbs, Adjectives and Adverbs. \r\n\r\nThis SQL version of IWN v2.0 contains a corrected and revised version of the original IWN:\r\n49350 Synsets (of which: 3459 proper nouns, 32073 nominal, 8903 verbal, 4374 adjectival, 541 adverbial)\r\n48416 Lemmas (of which: 3918 proper nouns, 29527 nouns, 8015 verbs, 5808 adjectives, 1090 adverbs)\r\n68478 Senses;2016-12-02;lexicalConceptualResource;http://hdl.handle.net/20.500.11752/ILC-62;ita;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;text/plain;text/plain; charset=utf-8;downloadable_files_count: 2;Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR);http://www.ilc.cnr.it/it/content/italwordnet",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "588a08ba-1591-5e98-bc33-5d093c3b2800",
-    "notes": [
-        "ItalWordNet (IWN) is a lexical-semantic database developed in the framework of two different research projects: EuroWordNet (EWN) and Sistema Integrato per il Trattamento Automatico del Linguaggio (SI-TAL).\r\n\r\nIWN is structured in the same way as the Princeton WordNet, namely around the notion of synset. Following the model designed in EWN, IWN encodes a rich set of semantic relations. In addition to the internal language relations, equivalence relations were also encoded between Italian synsets and the closest concepts in an Inter-Lingual Index (ILI), a separate language-independent module containing all WN1.5 synsets but not the relations among them.\r\nIWN now contains information about Italian Nouns, Verbs, Adjectives and Adverbs. \r\n\r\nThis SQL version of IWN v2.0 contains a corrected and revised version of the original IWN:\r\n49350 Synsets (of which: 3459 proper nouns, 32073 nominal, 8903 verbal, 4374 adjectival, 541 adverbial)\r\n48416 Lemmas (of which: 3918 proper nouns, 29527 nouns, 8015 verbs, 5808 adjectives, 1090 adverbs)\r\n68478 Senses"
-    ],
-    "oai_identifier": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-62"
-    ],
-    "oai_set": [
-        "hdl_000-c0-111_38",
-        "hdl_000-c0-111_49"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Italian Language"
-        },
-        {
-            "name": "WordNet"
-        },
-        {
-            "name": "Lexical Semantics"
-        },
-        {
-            "name": "Language Resource"
-        }
-    ],
-    "title": [
-        "ItalWordNet v.2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/58adccac-cd0c-5150-a594-8d5d50af664f.json b/oaitestdata/clarin-oai_dc/SET_1/json/58adccac-cd0c-5150-a594-8d5d50af664f.json
deleted file mode 100644
index a8eee74c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/58adccac-cd0c-5150-a594-8d5d50af664f.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3553",
-    "MetadataAccess": [
-        "oai:ota:oucs:3553"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hayley, William, 1745-1820."
-    ],
-    "fulltext": "oai:ota:oucs:3553;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3553.xml;Occasional stanzas, written at the request of the Revolution Society: and recited on their anniversary, November 4, 1788. To which is added, Queen Mary to King William, during his campaign in Ireland, 1690; a poetical epistle. By William Hayley, Esq.;Hayley, William, 1745-1820.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "58adccac-cd0c-5150-a594-8d5d50af664f",
-    "oai_identifier": [
-        "oai:ota:oucs:3553"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Occasional stanzas, written at the request of the Revolution Society: and recited on their anniversary, November 4, 1788. To which is added, Queen Mary to King William, during his campaign in Ireland, 1690; a poetical epistle. By William Hayley, Esq."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3553.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/58ae3554-5e03-5aba-ae4a-c9e717be6227.json b/oaitestdata/clarin-oai_dc/SET_1/json/58ae3554-5e03-5aba-ae4a-c9e717be6227.json
deleted file mode 100644
index b4218241..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/58ae3554-5e03-5aba-ae4a-c9e717be6227.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "Welsh"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-951",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-951"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-951",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-951;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Middle Welsh;ca. 20.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-951;cym;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#kymr",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "58ae3554-5e03-5aba-ae4a-c9e717be6227",
-    "notes": [
-        "ca. 20.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-951"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Middle Welsh"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/58c3801a-ecfe-5cc5-ae1e-6e765338d0b5.json b/oaitestdata/clarin-oai_dc/SET_1/json/58c3801a-ecfe-5cc5-ae1e-6e765338d0b5.json
deleted file mode 100644
index b75c54f9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/58c3801a-ecfe-5cc5-ae1e-6e765338d0b5.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Polish-Japanese Academy of Information Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/gzip",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/295",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/295"
-    ],
-    "PID": "http://hdl.handle.net/11321/295",
-    "PublicationTimestamp": "2016-06-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Polish-Japanese Academy of Information Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "BSD 2 Clause",
-        "https://opensource.org/licenses/BSD-2-Clause",
-        "PUB"
-    ],
-    "author": [
-        "Marasek, Krzysztof",
-        "Brocki, \u0141ukasz",
-        "Kor\u017einek, Danijel"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/295;2016-06-06T13:04:00Z;hdl_11321_3;hdl_11321_4;Polish Grapheme-to-phoneme tool and service;Kor\u017einek, Danijel;Brocki, \u0141ukasz;Marasek, Krzysztof;phonetisation;grapheme-to-phoneme;This archive contains the source code of the Polish grapheme-to-phoneme conversion tool and the webservice located at http://mowa.clarin-pl.eu/transcriber/;2016-06-01;toolService;http://hdl.handle.net/11321/295;pol;BSD 2 Clause;https://opensource.org/licenses/BSD-2-Clause;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/gzip;downloadable_files_count: 1;Polish-Japanese Academy of Information Technology;http://mowa.clarin-pl.eu/transcriber/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "58c3801a-ecfe-5cc5-ae1e-6e765338d0b5",
-    "notes": [
-        "This archive contains the source code of the Polish grapheme-to-phoneme conversion tool and the webservice located at http://mowa.clarin-pl.eu/transcriber/"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/295"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "phonetisation"
-        },
-        {
-            "name": "grapheme-to-phoneme"
-        }
-    ],
-    "title": [
-        "Polish Grapheme-to-phoneme tool and service"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/58cacbb4-c02b-5362-9746-1de4f3f04845.json b/oaitestdata/clarin-oai_dc/SET_1/json/58cacbb4-c02b-5362-9746-1de4f3f04845.json
deleted file mode 100644
index 0d455d0c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/58cacbb4-c02b-5362-9746-1de4f3f04845.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4490",
-    "MetadataAccess": [
-        "oai:ota:oucs:4490"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Defoe, Daniel, 1661?-1731."
-    ],
-    "fulltext": "oai:ota:oucs:4490;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4490.xml;A declaration of truth to Benjamin Hoadly: one of the high priests of the land, and of the degree whom men call bishops. By a ministring friend, who writ to Tho. Bradbury, a dealer in many words.;Defoe, Daniel, 1661?-1731.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "58cacbb4-c02b-5362-9746-1de4f3f04845",
-    "oai_identifier": [
-        "oai:ota:oucs:4490"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A declaration of truth to Benjamin Hoadly: one of the high priests of the land, and of the degree whom men call bishops. By a ministring friend, who writ to Tho. Bradbury, a dealer in many words."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4490.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/58d4e715-b0bf-52f6-883d-6ac697216280.json b/oaitestdata/clarin-oai_dc/SET_1/json/58d4e715-b0bf-52f6-883d-6ac697216280.json
deleted file mode 100644
index a48465f1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/58d4e715-b0bf-52f6-883d-6ac697216280.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=dce1279e1c5d11e2a2aa782bcb074135fa867e60fcaa4d918f097c19a238d82b",
-    "MetadataAccess": [
-        "dce1279e1c5d11e2a2aa782bcb074135fa867e60fcaa4d918f097c19a238d82b"
-    ],
-    "PublicationTimestamp": "2012-10-22T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "fulltext": "dce1279e1c5d11e2a2aa782bcb074135fa867e60fcaa4d918f097c19a238d82b;2018-11-15T16:39:44Z;toolService;toolService:tool;GistSumm;GistSumm (GIST SUMMarizer) is a summarization tool for Portuguese. It uses the gist as a guideline to identify and select text segments to include in the final extract. Automatically produced extracts have been evaluated under the light of gist preservation and textuality.;2012-10-22",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "58d4e715-b0bf-52f6-883d-6ac697216280",
-    "notes": [
-        "GistSumm (GIST SUMMarizer) is a summarization tool for Portuguese. It uses the gist as a guideline to identify and select text segments to include in the final extract. Automatically produced extracts have been evaluated under the light of gist preservation and textuality."
-    ],
-    "oai_identifier": [
-        "dce1279e1c5d11e2a2aa782bcb074135fa867e60fcaa4d918f097c19a238d82b"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "GistSumm"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/58db81e9-e0ce-582d-a214-bd134f41e0e6.json b/oaitestdata/clarin-oai_dc/SET_1/json/58db81e9-e0ce-582d-a214-bd134f41e0e6.json
deleted file mode 100644
index 6a5a7023..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/58db81e9-e0ce-582d-a214-bd134f41e0e6.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "CaenCNRTL, Crisco"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "French"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-453",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-453"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-453",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "France"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-453;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Base de synonymes CRISCO;CaenCNRTL, Crisco;49.000, RDB;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-453;fra;downloadable_files_count: 0;France;http://www.cnrtl.fr/synonymie/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "58db81e9-e0ce-582d-a214-bd134f41e0e6",
-    "notes": [
-        "49.000, RDB"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-453"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Base de synonymes CRISCO"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/58e18a39-b3d2-5116-86b3-e248c961733a.json b/oaitestdata/clarin-oai_dc/SET_1/json/58e18a39-b3d2-5116-86b3-e248c961733a.json
deleted file mode 100644
index b6cfe2c8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/58e18a39-b3d2-5116-86b3-e248c961733a.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=b7e3d0a63af611e2a2aa782bcb07413546f527e1332140b2987cf0d7a49ab3e0",
-    "MetadataAccess": [
-        "b7e3d0a63af611e2a2aa782bcb07413546f527e1332140b2987cf0d7a49ab3e0"
-    ],
-    "PublicationTimestamp": "2012-11-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "fulltext": "b7e3d0a63af611e2a2aa782bcb07413546f527e1332140b2987cf0d7a49ab3e0;2018-11-15T16:39:55Z;lexicalConceptualResource;lexicalConceptualResource:other;Maltese Wiktionary;This lexicon is part of the collection of the Wikimedia Dumps which was retrieved as an XML file from  http://dumps.wikimedia.org/mtwiktionary/20121105/ on November 5, 2012. In the Wikimedia dump, it is accompanied by a text file mtwiktionary-20121105-pages-articles-multistream-index.txt which lists all the wiki pages contained in the XML file. Both files are contained in the zip file downloadable from META-SHARE.\n\nThese files come from an automatically generated dump file of all pages within the Maltese Wiktionary wiki. The pages therein consist of manually constructed pages for articles and (semi-) automatically generated pages for the meta-content. Manual construction of the article pages allows for not sticking strictly to the agreed schema for entries in the Wiktionary. \n\nIn view of this mix of article pages, languages, meta-pages and other information, this resource is rather unreliable.\n;2012-11-30",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "58e18a39-b3d2-5116-86b3-e248c961733a",
-    "notes": [
-        "This lexicon is part of the collection of the Wikimedia Dumps which was retrieved as an XML file from  http://dumps.wikimedia.org/mtwiktionary/20121105/ on November 5, 2012. In the Wikimedia dump, it is accompanied by a text file mtwiktionary-20121105-pages-articles-multistream-index.txt which lists all the wiki pages contained in the XML file. Both files are contained in the zip file downloadable from META-SHARE.\n\nThese files come from an automatically generated dump file of all pages within the Maltese Wiktionary wiki. The pages therein consist of manually constructed pages for articles and (semi-) automatically generated pages for the meta-content. Manual construction of the article pages allows for not sticking strictly to the agreed schema for entries in the Wiktionary. \n\nIn view of this mix of article pages, languages, meta-pages and other information, this resource is rather unreliable.\n"
-    ],
-    "oai_identifier": [
-        "b7e3d0a63af611e2a2aa782bcb07413546f527e1332140b2987cf0d7a49ab3e0"
-    ],
-    "oai_set": [
-        "lexicalConceptualResource",
-        "lexicalConceptualResource:other"
-    ],
-    "state": "active",
-    "title": [
-        "Maltese Wiktionary"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5913c01b-c604-591c-b1e6-3393d81cc1b9.json b/oaitestdata/clarin-oai_dc/SET_1/json/5913c01b-c604-591c-b1e6-3393d81cc1b9.json
deleted file mode 100644
index 1450a71c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5913c01b-c604-591c-b1e6-3393d81cc1b9.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Smith, John B."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 374 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0149",
-    "MetadataAccess": [
-        "oai:ota:oucs:0149"
-    ],
-    "PublicationTimestamp": "1925-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1925"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Woolf, Virginia, 1882-1941"
-    ],
-    "fulltext": "oai:ota:oucs:0149;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0149.xml;Mrs. Dalloway / Virginia Woolf;Woolf, Virginia, 1882-1941;1925;text_and_corpus_linguistics;English fiction -- 20th century;eng;Oxford Text Archive, University of Oxford;Smith, John B.;(1 file : ca. 374 KB);Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5913c01b-c604-591c-b1e6-3393d81cc1b9",
-    "oai_identifier": [
-        "oai:ota:oucs:0149"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English fiction -- th century"
-        }
-    ],
-    "title": [
-        "Mrs. Dalloway / Virginia Woolf"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0149.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5924b36b-6b1c-5fd7-b3a6-f781a449161f.json b/oaitestdata/clarin-oai_dc/SET_1/json/5924b36b-6b1c-5fd7-b3a6-f781a449161f.json
deleted file mode 100644
index 16f2eaed..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5924b36b-6b1c-5fd7-b3a6-f781a449161f.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=2f653816a35a11e1a404080027e73ea2a7992eabb2a743e28c715f0094353cb8",
-    "MetadataAccess": [
-        "2f653816a35a11e1a404080027e73ea2a7992eabb2a743e28c715f0094353cb8"
-    ],
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "2f653816a35a11e1a404080027e73ea2a7992eabb2a743e28c715f0094353cb8;2019-02-27T12:09:08Z;corpus;corpus:text;English Acquis Communautaire;This is the English version of the Acquis Communautaire (AC), which is the total body of European Union (EU) law applicable in the EU Member States. It consists of selected texts between the 1950s and today.;2015-12-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5924b36b-6b1c-5fd7-b3a6-f781a449161f",
-    "notes": [
-        "This is the English version of the Acquis Communautaire (AC), which is the total body of European Union (EU) law applicable in the EU Member States. It consists of selected texts between the 1950s and today."
-    ],
-    "oai_identifier": [
-        "2f653816a35a11e1a404080027e73ea2a7992eabb2a743e28c715f0094353cb8"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "English Acquis Communautaire"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5927f8ff-6762-58bc-8a5f-f08a100b7696.json b/oaitestdata/clarin-oai_dc/SET_1/json/5927f8ff-6762-58bc-8a5f-f08a100b7696.json
deleted file mode 100644
index 352f752f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5927f8ff-6762-58bc-8a5f-f08a100b7696.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 6",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Serbian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1063",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1063"
-    ],
-    "PID": "http://hdl.handle.net/11356/1063",
-    "PublicationTimestamp": "2016-05-12T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by-sa/4.0/"
-    ],
-    "author": [
-        "Klubi\u010dka, Filip",
-        "Ljube\u0161i\u0107, Nikola"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1063;2018-10-24T20:49:24Z;hdl_11356_1023;hdl_11356_1024;Serbian web corpus srWaC 1.1;Ljube\u0161i\u0107, Nikola;Klubi\u010dka, Filip;web corpus;tagging;lemmatisation;The Serbian web corpus srWaC was built by crawling the .rs top-level domain in 2014. The corpus was near-deduplicated on paragraph level, normalised via diacritic restoration, morphosyntactically annotated and lemmatised. The corpus is shuffled by paragraphs. Each paragraph contains metadata on the URL, domain and language identification (Serbian vs. Croatian).\r\n\r\nVersion 1.0 of this corpus is described in http://www.aclweb.org/anthology/W14-0405. Version 1.1 contains newer and better linguistic annotations.;2016-05-12;corpus;http://hdl.handle.net/11356/1063;srp;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);PUB;https://creativecommons.org/licenses/by-sa/4.0/;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 6;Jo\u017eef Stefan Institute;http://nlp.ffzg.hr/resources/corpora/srwac/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5927f8ff-6762-58bc-8a5f-f08a100b7696",
-    "notes": [
-        "The Serbian web corpus srWaC was built by crawling the .rs top-level domain in 2014. The corpus was near-deduplicated on paragraph level, normalised via diacritic restoration, morphosyntactically annotated and lemmatised. The corpus is shuffled by paragraphs. Each paragraph contains metadata on the URL, domain and language identification (Serbian vs. Croatian).\r\n\r\nVersion 1.0 of this corpus is described in http://www.aclweb.org/anthology/W14-0405. Version 1.1 contains newer and better linguistic annotations."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1063"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "web corpus"
-        },
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "lemmatisation"
-        }
-    ],
-    "title": [
-        "Serbian web corpus srWaC 1.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/592e9536-b4c2-5aa7-835f-0831430509bd.json b/oaitestdata/clarin-oai_dc/SET_1/json/592e9536-b4c2-5aa7-835f-0831430509bd.json
deleted file mode 100644
index cef1df48..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/592e9536-b4c2-5aa7-835f-0831430509bd.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4559",
-    "MetadataAccess": [
-        "oai:ota:oucs:4559"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Inchbald, Mrs., 1753-1821."
-    ],
-    "fulltext": "oai:ota:oucs:4559;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4559.xml;Every one has his fault: a comedy, in five acts, as it is performed at the Theatre Royal, Covent-Garden. By Mrs. Inchbald.;Inchbald, Mrs., 1753-1821.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "592e9536-b4c2-5aa7-835f-0831430509bd",
-    "oai_identifier": [
-        "oai:ota:oucs:4559"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Every one has his fault: a comedy, in five acts, as it is performed at the Theatre Royal, Covent-Garden. By Mrs. Inchbald."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4559.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/595a0721-f45a-5fb4-aefb-b0dfc6820509.json b/oaitestdata/clarin-oai_dc/SET_1/json/595a0721-f45a-5fb4-aefb-b0dfc6820509.json
deleted file mode 100644
index aa4a8149..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/595a0721-f45a-5fb4-aefb-b0dfc6820509.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "University College, Cork"
-    ],
-    "Contributor": [
-        "Morgan, Dr. Hiram",
-        "F\u00e4rber, Beatrix"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/tei+xml",
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English",
-        "Irish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-864",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-864"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-864",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University College, Cork"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Ireland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-864;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;CELT Corpus of Electronic Texts;F\u00e4rber, Beatrix;Morgan, Dr. Hiram;searchable online corpus of multilingual texts of Irish literature and history;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-864;eng;gle;lat;application/tei+xml;downloadable_files_count: 0;Ireland;University College, Cork;http://www.ucc.ie/celt/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "595a0721-f45a-5fb4-aefb-b0dfc6820509",
-    "notes": [
-        "searchable online corpus of multilingual texts of Irish literature and history"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-864"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "CELT Corpus of Electronic Texts"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/595deefa-81cf-530c-b5dc-ace54148f680.json b/oaitestdata/clarin-oai_dc/SET_1/json/595deefa-81cf-530c-b5dc-ace54148f680.json
deleted file mode 100644
index 6a207e97..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/595deefa-81cf-530c-b5dc-ace54148f680.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "text/xml",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Norwegian Bokm\u00e5l"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/92",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/92"
-    ],
-    "PID": "http://hdl.handle.net/11509/92",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "CC",
-        "http://creativecommons.org/licenses/by/3.0/"
-    ],
-    "author": [
-        "Giellatekno - Saami Language Technology, UiT The Arctic University of Norway"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/92;2016-09-06T12:37:52Z;hdl_11509_1;hdl_11509_2;Norwegian Bokm\u00e5l-Kven dictionary;Giellatekno - Saami Language Technology, UiT The Arctic University of Norway;Bilingual Lexicon;Dictionary;Kven;Norwegian;The Norwegian Bokm\u00e5l-Kven dictionary is the work done by Giellatekno, UiT The Arctic University of Norway, Kainun institutti, as well as by members of the language communities. In particular, the following colleagues have contributed to the creation of the ressource: Terje Aronsen, Verena Schall, Eira S\u00f6derholm, Trond Trosterud, Tove Reibo, and Ciprian Gerstenberger. The dictionary contains 7716 entries in Giellatekno's dictionary xml format. In spite of the extensive quality control, it may contain entries with objectionable translations. If you find any errors or want to add more words, download the file, edit it, and send it back to giellatekno@uit.no.\r\nPlease note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata).;2015;lexicalConceptualResource;http://hdl.handle.net/11509/92;nob;fkv;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);CC;http://creativecommons.org/licenses/by/3.0/;application/zip;text/plain; charset=utf-8;text/xml;downloadable_files_count: 1;Giellatekno - Saami Language Technology;http://giellatekno.uit.no/index.eng.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "595deefa-81cf-530c-b5dc-ace54148f680",
-    "notes": [
-        "The Norwegian Bokm\u00e5l-Kven dictionary is the work done by Giellatekno, UiT The Arctic University of Norway, Kainun institutti, as well as by members of the language communities. In particular, the following colleagues have contributed to the creation of the ressource: Terje Aronsen, Verena Schall, Eira S\u00f6derholm, Trond Trosterud, Tove Reibo, and Ciprian Gerstenberger. The dictionary contains 7716 entries in Giellatekno's dictionary xml format. In spite of the extensive quality control, it may contain entries with objectionable translations. If you find any errors or want to add more words, download the file, edit it, and send it back to giellatekno@uit.no.\r\nPlease note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata)."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/92"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Bilingual Lexicon"
-        },
-        {
-            "name": "Dictionary"
-        },
-        {
-            "name": "Kven"
-        },
-        {
-            "name": "Norwegian"
-        }
-    ],
-    "title": [
-        "Norwegian Bokm\u00e5l-Kven dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/595df213-9fdb-5b70-b26e-1eaa43e0fd8c.json b/oaitestdata/clarin-oai_dc/SET_1/json/595df213-9fdb-5b70-b26e-1eaa43e0fd8c.json
deleted file mode 100644
index c403dcf4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/595df213-9fdb-5b70-b26e-1eaa43e0fd8c.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "English",
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1664",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1664"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1664",
-    "PublicationTimestamp": "2016-03-30T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/610516"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CC-BY-NC-SA + LDC99T42",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/license-pcedt2",
-        "RES"
-    ],
-    "author": [
-        "Nov\u00e1k, Michal",
-        "Cinkov\u00e1, Silvie",
-        "Nedoluzhko, Anna",
-        "Mikulov\u00e1, Marie",
-        "M\u00edrovsk\u00fd, Ji\u0159\u00ed"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1664;2018-07-02T22:05:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Prague Czech-English Dependency Treebank 2.0 Coref;Nedoluzhko, Anna;Nov\u00e1k, Michal;Cinkov\u00e1, Silvie;Mikulov\u00e1, Marie;M\u00edrovsk\u00fd, Ji\u0159\u00ed;multilingual;coreference;The Prague Czech-English Dependency Treebank 2.0 Coref (PCEDT 2.0 Coref) is a parallel treebank building upon the original PCEDT 2.0 release and enriching it with the extended manual annotation of coreference, as well as with an improved automatic annotation of the coreferential expression alignment.;2016-03-30;corpus;http://hdl.handle.net/11234/1-1664;eng;ces;info:eu-repo/grantAgreement/EC/FP7/610516;CC-BY-NC-SA + LDC99T42;https://lindat.mff.cuni.cz/repository/xmlui/page/license-pcedt2;RES;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/pcedt2.0-coref",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "595df213-9fdb-5b70-b26e-1eaa43e0fd8c",
-    "notes": [
-        "The Prague Czech-English Dependency Treebank 2.0 Coref (PCEDT 2.0 Coref) is a parallel treebank building upon the original PCEDT 2.0 release and enriching it with the extended manual annotation of coreference, as well as with an improved automatic annotation of the coreferential expression alignment."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1664"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "multilingual"
-        },
-        {
-            "name": "coreference"
-        }
-    ],
-    "title": [
-        "Prague Czech-English Dependency Treebank 2.0 Coref"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/596a30f6-dfac-5aa2-8939-def7e109d9fc.json b/oaitestdata/clarin-oai_dc/SET_1/json/596a30f6-dfac-5aa2-8939-def7e109d9fc.json
deleted file mode 100644
index 167bef79..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/596a30f6-dfac-5aa2-8939-def7e109d9fc.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/94",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/94"
-    ],
-    "PID": "http://hdl.handle.net/10794/94",
-    "PublicationTimestamp": "2013-03-06T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/94;2017-10-25T11:49:18Z;hdl_10794_1;hdl_10794_2;Blog mix 2000 (2017-02-17);Bloggmix 2000 (2017-02-17);n/a, n/a;Swedish;Blog;The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.;Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat.;2013-03-06;corpus;http://hdl.handle.net/10794/94;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;http://creativecommons.org/licenses/by/4.0/;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/bloggmix2000",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "596a30f6-dfac-5aa2-8939-def7e109d9fc",
-    "notes": [
-        "The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.",
-        "Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/94"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Blog"
-        }
-    ],
-    "title": [
-        "Blog mix 2000 (2017-02-17)",
-        "Bloggmix 2000 (2017-02-17)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/597044ff-3044-5f6b-8aa1-d1535c93bf28.json b/oaitestdata/clarin-oai_dc/SET_1/json/597044ff-3044-5f6b-8aa1-d1535c93bf28.json
deleted file mode 100644
index 47bb7355..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/597044ff-3044-5f6b-8aa1-d1535c93bf28.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 3",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1037",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1037"
-    ],
-    "PID": "http://hdl.handle.net/11356/1037",
-    "PublicationTimestamp": "2010-03-07T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "http://www.lrec-conf.org/proceedings/lrec2010/summaries/139.html",
-        "http://hdl.handle.net/11356/1213"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)",
-        "https://creativecommons.org/licenses/by-nc/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Krek, Simon",
-        "Erjavec, Toma\u017e"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1037;2019-02-13T17:16:52Z;hdl_11356_1023;hdl_11356_1024;Training corpus jos1M 1.1;Erjavec, Toma\u017e;Krek, Simon;tagging;lemmatisation;manual annotation;TEI;The jos1M corpus contains 1 million words of sampled paragraphs from the FidaPLUS corpus. It is meant to serve as a training corpus for word-level tagging of Slovene. This silver-standard corpus is annotated for morphosyntactic descriptions (fine grained PoS tags) and lemmas, with about one fourth of the most problematic annotations hand-validated.\r\n\r\nThe corpus is available in source TEI P5 XML and in the simpler and smaller vertical format, used by various concordancers. Note that the vertical format does not contain all of the information from the source TEI.;2010-03-07;corpus;http://hdl.handle.net/11356/1037;slv;http://www.lrec-conf.org/proceedings/lrec2010/summaries/139.html;http://hdl.handle.net/11356/1213;Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0);https://creativecommons.org/licenses/by-nc/4.0/;PUB;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 3;Jo\u017eef Stefan Institute;http://nl.ijs.si/jos/jos1M-en.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "597044ff-3044-5f6b-8aa1-d1535c93bf28",
-    "notes": [
-        "The jos1M corpus contains 1 million words of sampled paragraphs from the FidaPLUS corpus. It is meant to serve as a training corpus for word-level tagging of Slovene. This silver-standard corpus is annotated for morphosyntactic descriptions (fine grained PoS tags) and lemmas, with about one fourth of the most problematic annotations hand-validated.\r\n\r\nThe corpus is available in source TEI P5 XML and in the simpler and smaller vertical format, used by various concordancers. Note that the vertical format does not contain all of the information from the source TEI."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1037"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "lemmatisation"
-        },
-        {
-            "name": "manual annotation"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "Training corpus jos1M 1.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5981a981-d9c1-53f2-be1b-ce1281ccbe00.json b/oaitestdata/clarin-oai_dc/SET_1/json/5981a981-d9c1-53f2-be1b-ce1281ccbe00.json
deleted file mode 100644
index e228f507..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5981a981-d9c1-53f2-be1b-ce1281ccbe00.json
+++ /dev/null
@@ -1,92 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "English",
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2824",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2824"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2824",
-    "PublicationTimestamp": "2018-06-07T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Haji\u010dov\u00e1, Eva",
-        "Haji\u010d, Jan",
-        "Ure\u0161ov\u00e1, Zde\u0148ka",
-        "Fu\u010d\u00edkov\u00e1, Eva"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2824;2018-09-21T08:36:37Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;CzEngClass 0.2;Ure\u0161ov\u00e1, Zde\u0148ka;Fu\u010d\u00edkov\u00e1, Eva;Haji\u010dov\u00e1, Eva;Haji\u010d, Jan;verbal valency;predicate argument structure;semantic roles;bilingual corpus annotation;translational equivalence;comparative syntax;comparative semantics;The CzEngClass synonym verb lexicon is a result of a project investigating semantic \u2018equivalence\u2019 of verb senses and their valency behavior in parallel Czech-English language resources, i.e., relating verb meanings with respect to contextually-based verb synonymy. The lexicon entries are linked to PDT-Vallex (http://hdl.handle.net/11858/00-097C-0000-0023-4338-F), EngVallex (http://hdl.handle.net/11858/00-097C-0000-0023-4337-2), CzEngVallex (http://hdl.handle.net/11234/1-1512), FrameNet (https://framenet.icsi.berkeley.edu/fndrupal/), VerbNet (http://verbs.colorado.edu/verbnet/index.html), PropBank (http://verbs.colorado.edu/%7Empalmer/projects/ace.html),  Ontonotes (http://verbs.colorado.edu/html_groupings/), and Czech (http://hdl.handle.net/11858/00-097C-0000-0001-4880-3) and English Wordnets (https://wordnet.princeton.edu/). Part of the dataset are files reflecting annotators choices and agreement for assignment of verbs to classes.;2018-06-07;lexicalConceptualResource;http://hdl.handle.net/11234/1-2824;eng;ces;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 4;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/czengclass",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5981a981-d9c1-53f2-be1b-ce1281ccbe00",
-    "notes": [
-        "The CzEngClass synonym verb lexicon is a result of a project investigating semantic \u2018equivalence\u2019 of verb senses and their valency behavior in parallel Czech-English language resources, i.e., relating verb meanings with respect to contextually-based verb synonymy. The lexicon entries are linked to PDT-Vallex (http://hdl.handle.net/11858/00-097C-0000-0023-4338-F), EngVallex (http://hdl.handle.net/11858/00-097C-0000-0023-4337-2), CzEngVallex (http://hdl.handle.net/11234/1-1512), FrameNet (https://framenet.icsi.berkeley.edu/fndrupal/), VerbNet (http://verbs.colorado.edu/verbnet/index.html), PropBank (http://verbs.colorado.edu/%7Empalmer/projects/ace.html),  Ontonotes (http://verbs.colorado.edu/html_groupings/), and Czech (http://hdl.handle.net/11858/00-097C-0000-0001-4880-3) and English Wordnets (https://wordnet.princeton.edu/). Part of the dataset are files reflecting annotators choices and agreement for assignment of verbs to classes."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2824"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "verbal valency"
-        },
-        {
-            "name": "predicate argument structure"
-        },
-        {
-            "name": "semantic roles"
-        },
-        {
-            "name": "bilingual corpus annotation"
-        },
-        {
-            "name": "translational equivalence"
-        },
-        {
-            "name": "comparative syntax"
-        },
-        {
-            "name": "comparative semantics"
-        }
-    ],
-    "title": [
-        "CzEngClass 0.2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/598d05fa-74db-54c6-918c-205ef47c0d92.json b/oaitestdata/clarin-oai_dc/SET_1/json/598d05fa-74db-54c6-918c-205ef47c0d92.json
deleted file mode 100644
index 890b1552..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/598d05fa-74db-54c6-918c-205ef47c0d92.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3676",
-    "MetadataAccess": [
-        "oai:ota:oucs:3676"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pope, Alexander, 1688-1744."
-    ],
-    "fulltext": "oai:ota:oucs:3676;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3676.xml;An essay on man: being the first book of ethic epistles. To Henry St. John, L. Bolingbroke.;Pope, Alexander, 1688-1744.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "598d05fa-74db-54c6-918c-205ef47c0d92",
-    "oai_identifier": [
-        "oai:ota:oucs:3676"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An essay on man: being the first book of ethic epistles. To Henry St. John, L. Bolingbroke."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3676.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/59ad7931-d3a1-5ffa-87c4-460fa6752b0a.json b/oaitestdata/clarin-oai_dc/SET_1/json/59ad7931-d3a1-5ffa-87c4-460fa6752b0a.json
deleted file mode 100644
index e70bcc46..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/59ad7931-d3a1-5ffa-87c4-460fa6752b0a.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "University of Bergen"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "text/xml",
-        "downloadable_files_count: 1",
-        "text/plain",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "German",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/79",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/79"
-    ],
-    "PID": "http://hdl.handle.net/11509/79",
-    "PublicationTimestamp": "2012-04-18T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "University of Bergen"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Parra Escart\u00edn, Carla"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/79;2016-04-15T05:59:20Z;hdl_11509_1;hdl_11509_2;Parallel Corpus of documents from the Technical Regulations Information System for German-Spanish (v0.3);Parra Escart\u00edn, Carla;Corpus;TRIS Spanish-German parallel corpus (v0.3)\r\n\r\nSpecialized parallel corpus Spanish-German (ES-ES, DE-AT and DE-DE), texts from the European Commission between 1997-2010. \r\nThe texts are technical regulations in a variety of domains. This third version is sentence aligned and is in TMX and TEI format. \r\nTMX files are sentence aligned while TEI encoded files have the information about sentence alignment in stand-off annotation. \r\nEvery sentence includes information about the domain, the year and the file it belongs to as well as the sentence number. It contains files written in Austria and translated into European Spanish from three different domains: \r\n- B00: Construction (205 files; 70,648 sentences; 1,563,000 words; time frame: 1999-2010) \r\n- C00A: Agriculture, Fishing and Foodstuffs (12 files; 4879 sentences; 137,354 words; time frame: 1999-2001) \r\n- H00: Domestic and Leisure Equipment (12 files; 1229 sentences; 58328 words; time frame: 2005-2010) \r\n\r\nAdditionally the corpus has also been Part-Of-Speech tagged using the TreeTagger POS tagger and the POS tagged files are also available. \r\n\r\nVersions 0.1 and 0.2 are kept as individual records because they are (currently) intended to be downloaded individually. \r\n\r\nVersion 0.3 is encoded in TEI P5 and includes files from two new domains not included in versions 0.1 and 0.2: C00A (Agriculture, Fishing and Foodstuffs), which is currently under alignment and H00 (Domestic and Leisure Equipment), which includes all files available in the database up to 2010.;2012-04-18;corpus;http://hdl.handle.net/11509/79;deu;spa;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;CC;application/zip;text/plain;text/xml;application/octet-stream;downloadable_files_count: 1;University of Bergen;http://clara.b.uib.no/fellows/carla-parra-escartin/tris/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "59ad7931-d3a1-5ffa-87c4-460fa6752b0a",
-    "notes": [
-        "TRIS Spanish-German parallel corpus (v0.3)\r\n\r\nSpecialized parallel corpus Spanish-German (ES-ES, DE-AT and DE-DE), texts from the European Commission between 1997-2010. \r\nThe texts are technical regulations in a variety of domains. This third version is sentence aligned and is in TMX and TEI format. \r\nTMX files are sentence aligned while TEI encoded files have the information about sentence alignment in stand-off annotation. \r\nEvery sentence includes information about the domain, the year and the file it belongs to as well as the sentence number. It contains files written in Austria and translated into European Spanish from three different domains: \r\n- B00: Construction (205 files; 70,648 sentences; 1,563,000 words; time frame: 1999-2010) \r\n- C00A: Agriculture, Fishing and Foodstuffs (12 files; 4879 sentences; 137,354 words; time frame: 1999-2001) \r\n- H00: Domestic and Leisure Equipment (12 files; 1229 sentences; 58328 words; time frame: 2005-2010) \r\n\r\nAdditionally the corpus has also been Part-Of-Speech tagged using the TreeTagger POS tagger and the POS tagged files are also available. \r\n\r\nVersions 0.1 and 0.2 are kept as individual records because they are (currently) intended to be downloaded individually. \r\n\r\nVersion 0.3 is encoded in TEI P5 and includes files from two new domains not included in versions 0.1 and 0.2: C00A (Agriculture, Fishing and Foodstuffs), which is currently under alignment and H00 (Domestic and Leisure Equipment), which includes all files available in the database up to 2010."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/79"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Corpus"
-        }
-    ],
-    "title": [
-        "Parallel Corpus of documents from the Technical Regulations Information System for German-Spanish (v0.3)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/59adb270-9dc6-5c23-9cc0-7dbadbb994fc.json b/oaitestdata/clarin-oai_dc/SET_1/json/59adb270-9dc6-5c23-9cc0-7dbadbb994fc.json
deleted file mode 100644
index 5ab76e52..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/59adb270-9dc6-5c23-9cc0-7dbadbb994fc.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Jan Wieczorek"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 50",
-        "application/vnd.oasis.opendocument.text"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/505",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/505"
-    ],
-    "PID": "http://hdl.handle.net/11321/505",
-    "PublicationTimestamp": "2018-06-24T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Jan Wieczorek"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Super Cool License",
-        "http://www.google.com",
-        "ACA"
-    ],
-    "author": [
-        "Wieczorek, Jan"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/505;2018-06-24T19:04:40Z;hdl_11321_3;hdl_11321_478;korpus testowy euro;Wieczorek, Jan;eu;european union;Korpus europarlamentu do r\u00f3\u017cnych test\u00f3w;2018-06-24;corpus;http://hdl.handle.net/11321/505;pol;Super Cool License;http://www.google.com;ACA;text/plain; charset=utf-8;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;downloadable_files_count: 50;Jan Wieczorek",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "59adb270-9dc6-5c23-9cc0-7dbadbb994fc",
-    "notes": [
-        "Korpus europarlamentu do r\u00f3\u017cnych test\u00f3w"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/505"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_478"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "eu"
-        },
-        {
-            "name": "european union"
-        }
-    ],
-    "title": [
-        "korpus testowy euro"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/59ce136a-b550-5c54-9f7a-8fc3cb950796.json b/oaitestdata/clarin-oai_dc/SET_1/json/59ce136a-b550-5c54-9f7a-8fc3cb950796.json
deleted file mode 100644
index bf59c0b7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/59ce136a-b550-5c54-9f7a-8fc3cb950796.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5647",
-    "MetadataAccess": [
-        "oai:ota:oucs:5647"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Fournel, M. (Jean-Fran\u00c3\u00a7ois), 1745-1820."
-    ],
-    "fulltext": "oai:ota:oucs:5647;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5647.xml;An essay on somnambulism, or sleep-walking: produced by animal electricity and magnetism. As well as by sympathy, &c. As performed by the Rev. John Bell, ...;Essai sur les probabilit\u00c3\u00a9s du somnambulisme magn\u00c3\u00a9tique. English;Fournel, M. (Jean-Fran\u00c3\u00a7ois), 1745-1820.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "59ce136a-b550-5c54-9f7a-8fc3cb950796",
-    "oai_identifier": [
-        "oai:ota:oucs:5647"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An essay on somnambulism, or sleep-walking: produced by animal electricity and magnetism. As well as by sympathy, &c. As performed by the Rev. John Bell, ...",
-        "Essai sur les probabilit\u00c3\u00a9s du somnambulisme magn\u00c3\u00a9tique. English"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5647.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/59d9d9f3-3e2d-5634-9f88-4cbc14eab764.json b/oaitestdata/clarin-oai_dc/SET_1/json/59d9d9f3-3e2d-5634-9f88-4cbc14eab764.json
deleted file mode 100644
index 2976879d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/59d9d9f3-3e2d-5634-9f88-4cbc14eab764.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "Institute for Applied Linguistics, Eurac Research"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin.eurac.edu:20.500.12124/3",
-    "MetadataAccess": [
-        "oai:clarin.eurac.edu:20.500.12124/3"
-    ],
-    "PID": "http://hdl.handle.net/20.500.12124/3",
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Institute for Applied Linguistics, Eurac Research"
-    ],
-    "RelatedIdentifier": [
-        "http://aclweb.org/anthology/W14-0406"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Stemle, Egon",
-        "Pirrelli, Vito",
-        "Dell\u2019Orletta, Felice",
-        "Lyding, Verena",
-        "Lenci, Alessandro",
-        "Castagnoli, Sara",
-        "Borghetti, Claudia",
-        "Brunello, Marco",
-        "Dittmann, Henrik"
-    ],
-    "fulltext": "oai:clarin.eurac.edu:20.500.12124/3;2018-09-10T12:15:59Z;hdl_20.500.12124_1;hdl_20.500.12124_2;PAIS\u00c0 Corpus of Italian Web Text;Lyding, Verena;Stemle, Egon;Borghetti, Claudia;Brunello, Marco;Castagnoli, Sara;Dell\u2019Orletta, Felice;Dittmann, Henrik;Lenci, Alessandro;Pirrelli, Vito;web corpus;language learning;The Pais\u00e0 corpus is a large collection of Italian web texts, licensed under Creative Commons (Attribution-ShareAlike and Attribution-Noncommercial-ShareAlike). It has been created in the context of the project PAIS\u00c0.\r\n\r\nAll documents were selected in two different ways. A part of the corpus was constructed using a method inspired by the WaCky project. We created 50,000 word pairs by randomly combining terms from an Italian basic vocabulary list, and used the pairs as queries to the Yahoo! search engine in order to retrieve candidate pages. We limited hits to pages in Italian with a Creative Commons license of type: CC-Attribution, CC-Attribution-Sharealike, CC-Attribution-Sharealike-Non-commercial, and CC-Attribution-Non-commercial. Pages that were wrongly tagged as CC-licensed were eliminated using a black-list that was populated by manual inspection of earlier versions of the corpus. The retrieved pages were automatically cleaned using the KrdWrd system.\r\n\r\nThe remaining pages in the PAIS\u00c0 corpus come from the Italian versions of various Wikimedia Foundation projects, namely: Wikipedia, Wikinews, Wikisource, Wikibooks, Wikiversity, Wikivoyage. The official Wikimedia Foundation dumps were used, extracting text with Wikipedia Extractor.\r\n\r\nOnce all materials were downloaded, the collection was filtered discarding empty documents or documents containing less than 150 words.\r\n\r\nThe corpus contains approximately 380,000 documents coming from about 1,000 different websites, for a total of about 250 million words. Approximately 260,000 documents are from Wikipedia, approx. 5,600 from other Wikimedia Foundation projects. About 9,300 documents come from Indymedia, and we estimate that about 65,000 documents come from blog services.;2013-01;corpus;http://hdl.handle.net/20.500.12124/3;ita;http://aclweb.org/anthology/W14-0406;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/gzip;application/gzip;application/gzip;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Institute for Applied Linguistics, Eurac Research;http://www.corpusitaliano.it",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "59d9d9f3-3e2d-5634-9f88-4cbc14eab764",
-    "notes": [
-        "The Pais\u00e0 corpus is a large collection of Italian web texts, licensed under Creative Commons (Attribution-ShareAlike and Attribution-Noncommercial-ShareAlike). It has been created in the context of the project PAIS\u00c0.\r\n\r\nAll documents were selected in two different ways. A part of the corpus was constructed using a method inspired by the WaCky project. We created 50,000 word pairs by randomly combining terms from an Italian basic vocabulary list, and used the pairs as queries to the Yahoo! search engine in order to retrieve candidate pages. We limited hits to pages in Italian with a Creative Commons license of type: CC-Attribution, CC-Attribution-Sharealike, CC-Attribution-Sharealike-Non-commercial, and CC-Attribution-Non-commercial. Pages that were wrongly tagged as CC-licensed were eliminated using a black-list that was populated by manual inspection of earlier versions of the corpus. The retrieved pages were automatically cleaned using the KrdWrd system.\r\n\r\nThe remaining pages in the PAIS\u00c0 corpus come from the Italian versions of various Wikimedia Foundation projects, namely: Wikipedia, Wikinews, Wikisource, Wikibooks, Wikiversity, Wikivoyage. The official Wikimedia Foundation dumps were used, extracting text with Wikipedia Extractor.\r\n\r\nOnce all materials were downloaded, the collection was filtered discarding empty documents or documents containing less than 150 words.\r\n\r\nThe corpus contains approximately 380,000 documents coming from about 1,000 different websites, for a total of about 250 million words. Approximately 260,000 documents are from Wikipedia, approx. 5,600 from other Wikimedia Foundation projects. About 9,300 documents come from Indymedia, and we estimate that about 65,000 documents come from blog services."
-    ],
-    "oai_identifier": [
-        "oai:clarin.eurac.edu:20.500.12124/3"
-    ],
-    "oai_set": [
-        "hdl_20.500.12124_1",
-        "hdl_20.500.12124_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "web corpus"
-        },
-        {
-            "name": "language learning"
-        }
-    ],
-    "title": [
-        "PAIS\u00c0 Corpus of Italian Web Text"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/59f396a0-6e71-56e5-9b33-8b0fbf67733f.json b/oaitestdata/clarin-oai_dc/SET_1/json/59f396a0-6e71-56e5-9b33-8b0fbf67733f.json
deleted file mode 100644
index 05bbab45..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/59f396a0-6e71-56e5-9b33-8b0fbf67733f.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Institut f\u00fcr Deutsche Sprache"
-    ],
-    "Contributor": [
-        "Steffens, Doris"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-457",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-457"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-457",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut f\u00fcr Deutsche Sprache"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-457;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;W\u00f6rterbuch der Neologismen der 90er Jahre (im elexiko-Portal);Steffens, Doris;neologisms database;ca. 700 entries, XML;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-457;deu;downloadable_files_count: 0;Germany;Institut f\u00fcr Deutsche Sprache;http://www.ids-mannheim.de/elexiko/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "59f396a0-6e71-56e5-9b33-8b0fbf67733f",
-    "notes": [
-        "ca. 700 entries, XML"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-457"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "neologisms database"
-        }
-    ],
-    "title": [
-        "W\u00f6rterbuch der Neologismen der 90er Jahre (im elexiko-Portal)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5a096ec8-8bc8-5fd3-a4c8-a3868083b1d0.json b/oaitestdata/clarin-oai_dc/SET_1/json/5a096ec8-8bc8-5fd3-a4c8-a3868083b1d0.json
deleted file mode 100644
index 9c6c4c1c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5a096ec8-8bc8-5fd3-a4c8-a3868083b1d0.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/octet-stream",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/252",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/252"
-    ],
-    "PID": "http://hdl.handle.net/11321/252",
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "BSD 2 Clause",
-        "https://opensource.org/licenses/BSD-2-Clause",
-        "PUB"
-    ],
-    "author": [
-        "Nito\u0144, Bart\u0142omiej",
-        "Bartosiak, Tomasz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/252;2016-04-29T15:58:07Z;hdl_11321_3;hdl_11321_4;Slowal;Nito\u0144, Bart\u0142omiej;Bartosiak, Tomasz;valence dictionary editor;syntactic schema;semantic frame;valence dictionary browser;Slowal is a web tool designed for creating, editing and browsing valence dictionaries. So far, it has mainly been used for creating The Polish Valence Dictionary (Walenty).\r\n\r\nSlowal supports the process of creating the dictionary; it also facilitates access by making it possible to browse the dictionary using an advanced built-in filtering system, covering both syntactic and semantic phenomena. Slowal also gives control over the work of lexicographers involved in creating dictionary, for instance by using predefined lists of values, which prevents spelling errors and enforces consistency, as well as by imposing strict validation rules.\r\n\r\nLast but not least, the created dictionary can be exported from Slowal in various formats: plain text, TeX, PDF, and TEI XML.;2016;toolService;http://hdl.handle.net/11321/252;pol;BSD 2 Clause;https://opensource.org/licenses/BSD-2-Clause;PUB;text/plain; charset=utf-8;application/zip;application/octet-stream;application/octet-stream;downloadable_files_count: 1;Institute of Computer Science, Polish Academy of Sciences;http://zil.ipipan.waw.pl/Slowal",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5a096ec8-8bc8-5fd3-a4c8-a3868083b1d0",
-    "notes": [
-        "Slowal is a web tool designed for creating, editing and browsing valence dictionaries. So far, it has mainly been used for creating The Polish Valence Dictionary (Walenty).\r\n\r\nSlowal supports the process of creating the dictionary; it also facilitates access by making it possible to browse the dictionary using an advanced built-in filtering system, covering both syntactic and semantic phenomena. Slowal also gives control over the work of lexicographers involved in creating dictionary, for instance by using predefined lists of values, which prevents spelling errors and enforces consistency, as well as by imposing strict validation rules.\r\n\r\nLast but not least, the created dictionary can be exported from Slowal in various formats: plain text, TeX, PDF, and TEI XML."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/252"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "valence dictionary editor"
-        },
-        {
-            "name": "syntactic schema"
-        },
-        {
-            "name": "semantic frame"
-        },
-        {
-            "name": "valence dictionary browser"
-        }
-    ],
-    "title": [
-        "Slowal"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5a10b77f-5186-5227-a3dc-d4769fddc2b7.json b/oaitestdata/clarin-oai_dc/SET_1/json/5a10b77f-5186-5227-a3dc-d4769fddc2b7.json
deleted file mode 100644
index cf152201..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5a10b77f-5186-5227-a3dc-d4769fddc2b7.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "Contributor": [
-        "Lorente, Merc\u00e8"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Basque",
-        "Catalan",
-        "English",
-        "Galician",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1114",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1114"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1114",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1114;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Vocabulario multiling\u00fce de econom\u00eda;Lorente, Merc\u00e8;terminology database;Multilingual terminological resource containing 20.941 terms from the Economics, Finance and Banking domains.;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1114;eus;cat;eng;glg;spa;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra;http://ricoterm.iula.upf.edu/docums/vocecon/esp/index.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5a10b77f-5186-5227-a3dc-d4769fddc2b7",
-    "notes": [
-        "Multilingual terminological resource containing 20.941 terms from the Economics, Finance and Banking domains."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1114"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "terminology database"
-        }
-    ],
-    "title": [
-        "Vocabulario multiling\u00fce de econom\u00eda"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5a1c6598-b7bb-5bbc-aa1f-f32b4942dbf7.json b/oaitestdata/clarin-oai_dc/SET_1/json/5a1c6598-b7bb-5bbc-aa1f-f32b4942dbf7.json
deleted file mode 100644
index e420ada1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5a1c6598-b7bb-5bbc-aa1f-f32b4942dbf7.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4599",
-    "MetadataAccess": [
-        "oai:ota:oucs:4599"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Jerningham, Mr. (Edward), 1737?-1812."
-    ],
-    "fulltext": "oai:ota:oucs:4599;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4599.xml;The nun: an elegy: By the author of the Magdalens.;Jerningham, Mr. (Edward), 1737?-1812.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5a1c6598-b7bb-5bbc-aa1f-f32b4942dbf7",
-    "oai_identifier": [
-        "oai:ota:oucs:4599"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The nun: an elegy: By the author of the Magdalens."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4599.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5a2a81e5-f6f7-5b25-bb6d-1804aa14f680.json b/oaitestdata/clarin-oai_dc/SET_1/json/5a2a81e5-f6f7-5b25-bb6d-1804aa14f680.json
deleted file mode 100644
index d845fb3a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5a2a81e5-f6f7-5b25-bb6d-1804aa14f680.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Department of Linguistics and Nordic Studies, University of Oslo"
-    ],
-    "Contributor": [
-        "N\u00f8klestad, Anders",
-        "Berge, Kjell Lars"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Norwegian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-658",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-658"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-658",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Department of Linguistics and Nordic Studies, University of Oslo"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Norway"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-658;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;KAL Corpus;N\u00f8klestad, Anders;Berge, Kjell Lars;3300 texts written by pupils for the final in Norwegian language in 1998, 1999, 2000 and 2001. The database also includes associated grades and other background material.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-658;nor;downloadable_files_count: 0;Norway;Department of Linguistics and Nordic Studies, University of Oslo;http://prosjekt.hihm.no/r97-kal/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5a2a81e5-f6f7-5b25-bb6d-1804aa14f680",
-    "notes": [
-        "3300 texts written by pupils for the final in Norwegian language in 1998, 1999, 2000 and 2001. The database also includes associated grades and other background material."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-658"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "KAL Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5a3ebf22-f11c-567d-a05d-c820dbe0e9f0.json b/oaitestdata/clarin-oai_dc/SET_1/json/5a3ebf22-f11c-567d-a05d-c820dbe0e9f0.json
deleted file mode 100644
index a4012737..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5a3ebf22-f11c-567d-a05d-c820dbe0e9f0.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-6042",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-6042"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D2D-A",
-    "PublicationTimestamp": "1645-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1645"
-    ],
-    "RelatedIdentifier": [
-        "http://dlibra.bibliotekaelblaska.pl/Content/6042",
-        "oai:dlibra.bibliotekaelblaska.pl:publication:6256"
-    ],
-    "ResourceType": [
-        "starodruk",
-        "alter Druck"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-6042;2019-03-01T17:20:27Z;Dowod iasney szkody, ktora ponosi Krolestwo Polskie z cudzoziemskich Pieniedzy...;Dowod iasney szkody, ktora ponosi Krolestwo Polskie z cudzoziemskich Pieniedzy...;polityka monetarna;Geldpolitik;Memoria\u0142 na Sejm Walny w 1643. Dowodzi on strat, jakie ponosi\u0142a Rzeczpospolita w zwi\u0105zku z zalewaniem jej przez obc\u0105 walut\u0119, zw\u0142aszcza przez monety \u015bl\u0105skie oraz talary z\u0142ote i lewkowe. Jest to druk urz\u0119dowy, wydany w formacie 4\u00ba, pochodz\u0105cy z kolekcji S. Gierszewskiego.;Denkschrift an das allgemein-polnische Parlament, das 1643 stattfand. Das Druckerzeugnis zeigt auf, welche Verluste Polen wegen der \u00dcberflutung durch fremde W\u00e4hrung zu leiden hat, besonders durch schlesische M\u00fcnzen, goldene Talern und Rigsdaler. Amtliches Druckerzeugnis; Format-4\u00ba; aus der Sammlung vom Professor S. Gierszewski;1645;1645;starodruk;alter Druck;application/xml;clarind-uds:poldilemma-6042;hdl:11858/00-246C-0000-0023-8D2D-A;XVII. 66;XVII. 66;pol;lat;http://dlibra.bibliotekaelblaska.pl/Content/6042;oai:dlibra.bibliotekaelblaska.pl:publication:6256;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5a3ebf22-f11c-567d-a05d-c820dbe0e9f0",
-    "notes": [
-        "Memoria\u0142 na Sejm Walny w 1643. Dowodzi on strat, jakie ponosi\u0142a Rzeczpospolita w zwi\u0105zku z zalewaniem jej przez obc\u0105 walut\u0119, zw\u0142aszcza przez monety \u015bl\u0105skie oraz talary z\u0142ote i lewkowe. Jest to druk urz\u0119dowy, wydany w formacie 4\u00ba, pochodz\u0105cy z kolekcji S. Gierszewskiego.",
-        "Denkschrift an das allgemein-polnische Parlament, das 1643 stattfand. Das Druckerzeugnis zeigt auf, welche Verluste Polen wegen der \u00dcberflutung durch fremde W\u00e4hrung zu leiden hat, besonders durch schlesische M\u00fcnzen, goldene Talern und Rigsdaler. Amtliches Druckerzeugnis; Format-4\u00ba; aus der Sammlung vom Professor S. Gierszewski"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-6042"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "polityka monetarna"
-        },
-        {
-            "name": "Geldpolitik"
-        }
-    ],
-    "title": [
-        "Dowod iasney szkody, ktora ponosi Krolestwo Polskie z cudzoziemskich Pieniedzy...",
-        "Dowod iasney szkody, ktora ponosi Krolestwo Polskie z cudzoziemskich Pieniedzy..."
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5a432ba4-1216-5a92-92ac-f19105aafff0.json b/oaitestdata/clarin-oai_dc/SET_1/json/5a432ba4-1216-5a92-92ac-f19105aafff0.json
deleted file mode 100644
index f4688065..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5a432ba4-1216-5a92-92ac-f19105aafff0.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "University of Tartu"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Estonian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1067",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1067"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1067",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Tartu"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Estonia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1067;2016-04-06T16:39:49Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Corpus query for Estonian corpora;Web application for querying the automatically morphologically disambiguated Mixed corpus of Estonian;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1067;est;downloadable_files_count: 0;Estonia;University of Tartu;http://www.keeleveeb.ee/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5a432ba4-1216-5a92-92ac-f19105aafff0",
-    "notes": [
-        "Web application for querying the automatically morphologically disambiguated Mixed corpus of Estonian"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1067"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus query for Estonian corpora"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5a461410-ae81-5546-afde-3cc5d394e4b2.json b/oaitestdata/clarin-oai_dc/SET_1/json/5a461410-ae81-5546-afde-3cc5d394e4b2.json
deleted file mode 100644
index 39ac750d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5a461410-ae81-5546-afde-3cc5d394e4b2.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "University of Tartu"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/plain"
-    ],
-    "Language": [
-        "Estonian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-646",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-646"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-646",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Tartu"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Estonia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-646;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Estonian Frequency Dictionary;10000 most frequent lemmas, 1000 most frequent word forms, based on 1 million words of journals and fiction;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-646;est;text/plain;downloadable_files_count: 0;Estonia;University of Tartu;http://www.cl.ut.ee/ressursid/sagedused/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5a461410-ae81-5546-afde-3cc5d394e4b2",
-    "notes": [
-        "10000 most frequent lemmas, 1000 most frequent word forms, based on 1 million words of journals and fiction"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-646"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Estonian Frequency Dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5a4e5745-79cd-51dc-a351-1f9f664aa455.json b/oaitestdata/clarin-oai_dc/SET_1/json/5a4e5745-79cd-51dc-a351-1f9f664aa455.json
deleted file mode 100644
index bc5a5896..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5a4e5745-79cd-51dc-a351-1f9f664aa455.json
+++ /dev/null
@@ -1,100 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 3",
-        "text/plain",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "English",
-        "Spanish",
-        "Polish",
-        "Russian",
-        "Hungarian",
-        "German",
-        "Swedish",
-        "Slovak",
-        "Slovenian",
-        "Portuguese",
-        "Bulgarian",
-        "Albanian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1048",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1048"
-    ],
-    "PID": "http://hdl.handle.net/11356/1048",
-    "PublicationTimestamp": "2015-09-14T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/610704",
-        "info:eu-repo/grantAgreement/EC/FP7/317532",
-        "info:eu-repo/grantAgreement/EC/H2020/640772",
-        "https://doi.org/10.1371/journal.pone.0144296"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by-sa/4.0/"
-    ],
-    "author": [
-        "Sluban, Borut",
-        "Mozeti\u010d, Igor",
-        "Smailovi\u0107, Jasmina",
-        "Kralj Novak, Petra"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1048;2018-10-16T10:39:49Z;hdl_11356_1023;hdl_11356_1024;Emoji Sentiment Ranking 1.0;Kralj Novak, Petra;Smailovi\u0107, Jasmina;Sluban, Borut;Mozeti\u010d, Igor;sentiment classification;emojis;Unicode;multilingual;A lexicon of 751 emoji characters with automatically assigned sentiment.\r\nThe sentiment is computed from 70,000 tweets, labeled by 83 human annotators\r\nin 13 European languages.\r\nThe process and analysis of emoji sentiment ranking is described in the\r\npaper:  Kralj Novak P, Smailovi\u0107 J, Sluban B, Mozeti\u010d I (2015) Sentiment of Emojis. PLoS ONE 10(12): e0144296. doi:10.1371/journal.pone.0144296;2015-09-14;lexicalConceptualResource;http://hdl.handle.net/11356/1048;eng;spa;pol;rus;hun;deu;swe;hbs;slk;slv;por;bul;sqi;info:eu-repo/grantAgreement/EC/FP7/610704;info:eu-repo/grantAgreement/EC/FP7/317532;info:eu-repo/grantAgreement/EC/H2020/640772;https://doi.org/10.1371/journal.pone.0144296;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);PUB;https://creativecommons.org/licenses/by-sa/4.0/;text/plain; charset=utf-8;text/plain;application/octet-stream;application/octet-stream;downloadable_files_count: 3;Jo\u017eef Stefan Institute",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5a4e5745-79cd-51dc-a351-1f9f664aa455",
-    "notes": [
-        "A lexicon of 751 emoji characters with automatically assigned sentiment.\r\nThe sentiment is computed from 70,000 tweets, labeled by 83 human annotators\r\nin 13 European languages.\r\nThe process and analysis of emoji sentiment ranking is described in the\r\npaper:  Kralj Novak P, Smailovi\u0107 J, Sluban B, Mozeti\u010d I (2015) Sentiment of Emojis. PLoS ONE 10(12): e0144296. doi:10.1371/journal.pone.0144296"
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1048"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "sentiment classification"
-        },
-        {
-            "name": "emojis"
-        },
-        {
-            "name": "Unicode"
-        },
-        {
-            "name": "multilingual"
-        }
-    ],
-    "title": [
-        "Emoji Sentiment Ranking 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5a5afebb-7103-545c-8338-63c9938d38ac.json b/oaitestdata/clarin-oai_dc/SET_1/json/5a5afebb-7103-545c-8338-63c9938d38ac.json
deleted file mode 100644
index 64f41a4b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5a5afebb-7103-545c-8338-63c9938d38ac.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "smith"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "downloadable_files_count: 11",
-        "application/vnd.oasis.opendocument.text",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/487",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/487"
-    ],
-    "PID": "http://hdl.handle.net/11321/487",
-    "PublicationTimestamp": "2018-06-19T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "smith"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "Kamieniecki, Jan"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/487;2018-06-19T11:18:12Z;hdl_11321_3;hdl_11321_4;data;Kamieniecki, Jan;warsztaty politechnika;fsfncbcywu swdno;2018-06-19;corpus;http://hdl.handle.net/11321/487;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/vnd.oasis.opendocument.text;application/msword;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;text/plain;downloadable_files_count: 11;smith",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5a5afebb-7103-545c-8338-63c9938d38ac",
-    "notes": [
-        "fsfncbcywu swdno"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/487"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "warsztaty politechnika"
-        }
-    ],
-    "title": [
-        "data"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5a5f6811-882d-5c23-9575-d5a25b452fc1.json b/oaitestdata/clarin-oai_dc/SET_1/json/5a5f6811-882d-5c23-9575-d5a25b452fc1.json
deleted file mode 100644
index 4835fddd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5a5f6811-882d-5c23-9575-d5a25b452fc1.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "[s.n.]"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-27478",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-27478"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D13-2",
-    "PublicationTimestamp": "1767-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1767"
-    ],
-    "Publisher": [
-        "[s.n.]"
-    ],
-    "RelatedIdentifier": [
-        "http://rcin.org.pl/Content/27478",
-        "oai:rcin.org.pl:publication:45560"
-    ],
-    "ResourceType": [
-        "Text",
-        "Early printed book (1501-1800)"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "author": [
-        "Tetsch, Christoph Ludwig (1735-1793)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-27478;2019-03-01T13:27:00Z;Krotki Wywod Ktorym Dowodzi Si\u0119, Iz Miastom Y Mieszczanom Xi\u0119sw [!] Kurlandyi Y Semigallyi Prawo Wzgl\u0119dem Appellacyi Do S\u0105dow J.K.Mci Relacyinych Sprawiedliwie S\u0142uzy;Tetsch, Christoph Ludwig (1735-1793);Law - Poland - 18th c.;Kurlandia (\u0141otwa);Aut. i data wyd. wg Estr.;[9] k., sygn. A-B4, C1 ; 4\u00b0;Estr. XV-XVIII, 31, 118;Liczne cytaty w j\u0119z. \u0142ac.;[s.n.];[1767];Text;Early printed book (1501-1800);application/xml;clarind-uds:poldilemma-27478;hdl:11858/00-246C-0000-0023-8D13-2;IBL PAN, call no. XVIII.2.686;http://katalog.pan.pl/webpac-bin/233biblitEN/wgbroker.exe?new+-access+top+search+open+NR+xx002792892;pol;lat;http://rcin.org.pl/Content/27478;oai:rcin.org.pl:publication:45560;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5a5f6811-882d-5c23-9575-d5a25b452fc1",
-    "notes": [
-        "Aut. i data wyd. wg Estr.",
-        "[9] k., sygn. A-B4, C1 ; 4\u00b0",
-        "Estr. XV-XVIII, 31, 118",
-        "Liczne cytaty w j\u0119z. \u0142ac."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-27478"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Law - Poland - th c."
-        },
-        {
-            "name": "Law - Poland - th c."
-        }
-    ],
-    "title": [
-        "Krotki Wywod Ktorym Dowodzi Si\u0119, Iz Miastom Y Mieszczanom Xi\u0119sw [!] Kurlandyi Y Semigallyi Prawo Wzgl\u0119dem Appellacyi Do S\u0105dow J.K.Mci Relacyinych Sprawiedliwie S\u0142uzy"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5a70807b-1755-57da-b5e5-4fa48cfb8312.json b/oaitestdata/clarin-oai_dc/SET_1/json/5a70807b-1755-57da-b5e5-4fa48cfb8312.json
deleted file mode 100644
index 12e72f8b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5a70807b-1755-57da-b5e5-4fa48cfb8312.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 85 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0008",
-    "MetadataAccess": [
-        "oai:ota:oucs:0008"
-    ],
-    "PublicationTimestamp": "1595-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1595"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Shakespeare, William, 1564-1616"
-    ],
-    "fulltext": "oai:ota:oucs:0008;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0008.xml;King Henry vi. pt. 3.;The true tragedie of Richard Duke of York ...;Shakespeare, William, 1564-1616;1595;text_and_corpus_linguistics;Plays -- England -- 16th century;eng;Oxford Text Archive, University of Oxford;(1 file : ca. 85 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5a70807b-1755-57da-b5e5-4fa48cfb8312",
-    "oai_identifier": [
-        "oai:ota:oucs:0008"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        }
-    ],
-    "title": [
-        "King Henry vi. pt. 3.",
-        "The true tragedie of Richard Duke of York ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0008.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5a878450-a248-5282-8ac4-afcf42b873e6.json b/oaitestdata/clarin-oai_dc/SET_1/json/5a878450-a248-5282-8ac4-afcf42b873e6.json
deleted file mode 100644
index f79302be..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5a878450-a248-5282-8ac4-afcf42b873e6.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4656",
-    "MetadataAccess": [
-        "oai:ota:oucs:4656"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Delap, J. (John), 1725-1812."
-    ],
-    "fulltext": "oai:ota:oucs:4656;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4656.xml;Elegy on the death of His Grace the Duke of Rutland. By Dr. Delap;Delap, J. (John), 1725-1812.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5a878450-a248-5282-8ac4-afcf42b873e6",
-    "oai_identifier": [
-        "oai:ota:oucs:4656"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Elegy on the death of His Grace the Duke of Rutland. By Dr. Delap"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4656.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5aa429e5-dc08-5a30-af21-fadc42d267c1.json b/oaitestdata/clarin-oai_dc/SET_1/json/5aa429e5-dc08-5a30-af21-fadc42d267c1.json
deleted file mode 100644
index d21360ba..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5aa429e5-dc08-5a30-af21-fadc42d267c1.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Emanuel Modrzejewski"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/223",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/223"
-    ],
-    "PID": "http://hdl.handle.net/11321/223",
-    "PublicationTimestamp": "2015-07-12T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Emanuel Modrzejewski"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0)",
-        "http://creativecommons.org/licenses/by-nc/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Emanuel Modrzejewski"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/223;2015-07-12T11:36:37Z;hdl_11321_3;hdl_11321_4;fronda;Emanuel Modrzejewski;Some texts of fronda.pl;2015-07-12;corpus;http://hdl.handle.net/11321/223;Polish;Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0);http://creativecommons.org/licenses/by-nc/3.0/;CC;text/plain;text/plain; charset=utf-8;downloadable_files_count: 1;Emanuel Modrzejewski",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5aa429e5-dc08-5a30-af21-fadc42d267c1",
-    "notes": [
-        "Some texts of fronda.pl"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/223"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "fronda"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5ab315ec-36fb-53f9-8541-a2cc42507210.json b/oaitestdata/clarin-oai_dc/SET_1/json/5ab315ec-36fb-53f9-8541-a2cc42507210.json
deleted file mode 100644
index 48788023..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5ab315ec-36fb-53f9-8541-a2cc42507210.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Polish-Japanese Academy of Information Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/622",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/622"
-    ],
-    "PID": "http://hdl.handle.net/11321/622",
-    "PublicationTimestamp": "2019-01-17T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Polish-Japanese Academy of Information Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Brocki, \u0141ukasz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/622;2019-01-18T08:23:50Z;hdl_11321_3;hdl_11321_4;Speech activity annotation for a subset of the Clarin-PL studio corpus;Brocki, \u0141ukasz;speech activity;voice activity;SAD;VAD;This is a hand-checked annotation of speech activity within a subset of the Clarin-PL studio corpus, containing 20 session with 619 recordings. This submission does not contain any audio files - these can be found either in the submission http://hdl.handle.net/11321/236, or under URL: http://mowa.clarin-pl.eu/korpusy;2019-01-17;corpus;http://hdl.handle.net/11321/622;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;Polish-Japanese Academy of Information Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5ab315ec-36fb-53f9-8541-a2cc42507210",
-    "notes": [
-        "This is a hand-checked annotation of speech activity within a subset of the Clarin-PL studio corpus, containing 20 session with 619 recordings. This submission does not contain any audio files - these can be found either in the submission http://hdl.handle.net/11321/236, or under URL: http://mowa.clarin-pl.eu/korpusy"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/622"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech activity"
-        },
-        {
-            "name": "voice activity"
-        },
-        {
-            "name": "SAD"
-        },
-        {
-            "name": "VAD"
-        }
-    ],
-    "title": [
-        "Speech activity annotation for a subset of the Clarin-PL studio corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5ac6ae1c-a9fc-50cf-a94b-143a4d547bfb.json b/oaitestdata/clarin-oai_dc/SET_1/json/5ac6ae1c-a9fc-50cf-a94b-143a4d547bfb.json
deleted file mode 100644
index 670d384e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5ac6ae1c-a9fc-50cf-a94b-143a4d547bfb.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Stanis\u0142awa Bertutowicza"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-148473",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-148473"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CDD-6",
-    "PublicationTimestamp": "1648-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1648"
-    ],
-    "Publisher": [
-        "Drukarnia Stanis\u0142awa Bertutowicza"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/148473",
-        "oai:jbc.bj.uj.edu.pl:publication:156696"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1601/1700"
-    ],
-    "TempCoverageBegin": 50506804799,
-    "TempCoverageEnd": 50506804799,
-    "TemporalCoverage": " point in time : 1601-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1601-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1601-07-01T11:59:59Z",
-    "author": [
-        "Gorczyn, Jan Aleksander (ca 1618-post 1694)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-148473;2019-02-28T18:13:22Z;Pami\u0119c O Cnotach, Szcz\u0119sciv, Dzielnosci, Naiasnieyszego y Niezwyciezonego Monarchy W\u0142adys\u0142awa IV.[...] Krola Polskiego, Wielkiego Xi\u0105\u017c\u0119cia Litewskiego [...] &c. &c. Dziedzicznego Krola [...];Gorczyn, Jan Aleksander (ca 1618-post 1694);starodruki 17\u00a0w.;Pstroko\u0144ski, Stanis\u0142aw (ca 1591-1657). [Adr. ded.];Drukarnia Stanis\u0142awa Bertutowicza;1648;starodruk;application/xml;clarind-uds:poldilemma-148473;hdl:11858/00-246C-0000-0023-8CDD-6;Biblioteka Jagiello\u0144ska, BJ St. Dr. 24745 I;pol;http://jbc.bj.uj.edu.pl/Content/148473;oai:jbc.bj.uj.edu.pl:publication:156696;1601/1700;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5ac6ae1c-a9fc-50cf-a94b-143a4d547bfb",
-    "notes": [
-        "Pstroko\u0144ski, Stanis\u0142aw (ca 1591-1657). [Adr. ded.]"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-148473"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Pami\u0119c O Cnotach, Szcz\u0119sciv, Dzielnosci, Naiasnieyszego y Niezwyciezonego Monarchy W\u0142adys\u0142awa IV.[...] Krola Polskiego, Wielkiego Xi\u0105\u017c\u0119cia Litewskiego [...] &c. &c. Dziedzicznego Krola [...]"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5acad8de-e8f0-50f1-bef4-bde0b3f98f22.json b/oaitestdata/clarin-oai_dc/SET_1/json/5acad8de-e8f0-50f1-bef4-bde0b3f98f22.json
deleted file mode 100644
index f86e7653..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5acad8de-e8f0-50f1-bef4-bde0b3f98f22.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Research Institute for the Languages of Finland"
-    ],
-    "Contributor": [
-        "Suutari, Toni"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-834",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-834"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-834",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Research Institute for the Languages of Finland"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-834;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Electronic Vepsian Word List;Suutari, Toni;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-834;downloadable_files_count: 0;Research Institute for the Languages of Finland;http://kaino.kotus.fi/sanat/vepsa/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5acad8de-e8f0-50f1-bef4-bde0b3f98f22",
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-834"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Electronic Vepsian Word List"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5ad845d0-9310-5d76-ab1b-2e457670ad30.json b/oaitestdata/clarin-oai_dc/SET_1/json/5ad845d0-9310-5d76-ab1b-2e457670ad30.json
deleted file mode 100644
index 61b158b2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5ad845d0-9310-5d76-ab1b-2e457670ad30.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4246",
-    "MetadataAccess": [
-        "oai:ota:oucs:4246"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Thomson, James, 1700-1748."
-    ],
-    "fulltext": "oai:ota:oucs:4246;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4246.xml;Winter: A poem. By James Thomson, ...;Thomson, James, 1700-1748.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5ad845d0-9310-5d76-ab1b-2e457670ad30",
-    "oai_identifier": [
-        "oai:ota:oucs:4246"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Winter: A poem. By James Thomson, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4246.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5b379282-5959-5ec8-8076-a93444861438.json b/oaitestdata/clarin-oai_dc/SET_1/json/5b379282-5959-5ec8-8076-a93444861438.json
deleted file mode 100644
index f80ce895..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5b379282-5959-5ec8-8076-a93444861438.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 117 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0642",
-    "MetadataAccess": [
-        "oai:ota:oucs:0642"
-    ],
-    "PublicationTimestamp": "1607-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1607"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Tourneur, Cyril, 1575?-1626"
-    ],
-    "fulltext": "oai:ota:oucs:0642;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0642.xml;Revenger's tragedy;The reuengers tragaedie;Tourneur, Cyril, 1575?-1626;1607;text_and_corpus_linguistics;Plays -- England -- 17th century;Tragedies -- England -- 17th century;eng;Oxford Text Archive, University of Oxford;(1 file : ca. 117 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5b379282-5959-5ec8-8076-a93444861438",
-    "oai_identifier": [
-        "oai:ota:oucs:0642"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        },
-        {
-            "name": "Tragedies -- England -- th century"
-        }
-    ],
-    "title": [
-        "Revenger's tragedy",
-        "The reuengers tragaedie"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0642.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5b406f2e-a29a-5529-9975-4ed5277cc022.json b/oaitestdata/clarin-oai_dc/SET_1/json/5b406f2e-a29a-5529-9975-4ed5277cc022.json
deleted file mode 100644
index 68c71393..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5b406f2e-a29a-5529-9975-4ed5277cc022.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "between 1 and 2 MB"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0397",
-    "MetadataAccess": [
-        "oai:ota:oucs:0397"
-    ],
-    "PublicationYear": [
-        "50-150"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Devotional literature"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Unknown"
-    ],
-    "fulltext": "oai:ota:oucs:0397;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0397.xml; The Greek New Testament  / compiled by Thesaurus Linguae Graecae;Unknown;50-150;text_and_corpus_linguistics;Devotional literature;grc;Oxford Text Archive, University of Oxford;between 1 and 2 MB;Text;Devotional literature;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5b406f2e-a29a-5529-9975-4ed5277cc022",
-    "oai_identifier": [
-        "oai:ota:oucs:0397"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Devotional literature"
-        }
-    ],
-    "title": [
-        " The Greek New Testament  / compiled by Thesaurus Linguae Graecae"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0397.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5b611d3d-fb33-5a8c-96f6-4300a93ac442.json b/oaitestdata/clarin-oai_dc/SET_1/json/5b611d3d-fb33-5a8c-96f6-4300a93ac442.json
deleted file mode 100644
index 65baae32..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5b611d3d-fb33-5a8c-96f6-4300a93ac442.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4539",
-    "MetadataAccess": [
-        "oai:ota:oucs:4539"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Defoe, Daniel, 1661?-1731."
-    ],
-    "fulltext": "oai:ota:oucs:4539;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4539.xml;Ye true-born Englishmen proceed: Our trifling crimes detect, ...;Defoe, Daniel, 1661?-1731.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5b611d3d-fb33-5a8c-96f6-4300a93ac442",
-    "oai_identifier": [
-        "oai:ota:oucs:4539"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Ye true-born Englishmen proceed: Our trifling crimes detect, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4539.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5b86bb36-4f72-5baa-afe2-6f0f4dba6b55.json b/oaitestdata/clarin-oai_dc/SET_1/json/5b86bb36-4f72-5baa-afe2-6f0f4dba6b55.json
deleted file mode 100644
index 47910398..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5b86bb36-4f72-5baa-afe2-6f0f4dba6b55.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 391 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "Middle English (1100-1500)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1362",
-    "MetadataAccess": [
-        "oai:ota:oucs:1362"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Chaucer, Geoffrey, d. 1400"
-    ],
-    "fulltext": "oai:ota:oucs:1362;2018-02-16T10:42:06Z;http://ota.ox.ac.uk/headers/1362.xml;Troilus & Criseyde;Chaucer, Geoffrey, d. 1400;default: 1976-01-01;text_and_corpus_linguistics;Poems -- England -- 14th century;enm;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 391 KB);Text;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5b86bb36-4f72-5baa-afe2-6f0f4dba6b55",
-    "oai_identifier": [
-        "oai:ota:oucs:1362"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- England -- th century"
-        }
-    ],
-    "title": [
-        "Troilus & Criseyde"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1362.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5bac0236-8c13-56ca-b80a-8081274e455a.json b/oaitestdata/clarin-oai_dc/SET_1/json/5bac0236-8c13-56ca-b80a-8081274e455a.json
deleted file mode 100644
index 8eda086f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5bac0236-8c13-56ca-b80a-8081274e455a.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3971",
-    "MetadataAccess": [
-        "oai:ota:oucs:3971"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Holcroft, Thomas, 1745-1809."
-    ],
-    "fulltext": "oai:ota:oucs:3971;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3971.xml;Duplicity: a comedy. As it is performed at the Theatre-Royal, in Covent-Garden. By Thomas Holcroft.;Holcroft, Thomas, 1745-1809.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5bac0236-8c13-56ca-b80a-8081274e455a",
-    "oai_identifier": [
-        "oai:ota:oucs:3971"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Duplicity: a comedy. As it is performed at the Theatre-Royal, in Covent-Garden. By Thomas Holcroft."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3971.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5bbad1e6-baa2-5495-983a-d9b7458babae.json b/oaitestdata/clarin-oai_dc/SET_1/json/5bbad1e6-baa2-5495-983a-d9b7458babae.json
deleted file mode 100644
index 49e7582c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5bbad1e6-baa2-5495-983a-d9b7458babae.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=acae1ab62f3e11e2a2aa782bcb074135cbaf365868fe4aecb947bcf617c8395b",
-    "MetadataAccess": [
-        "acae1ab62f3e11e2a2aa782bcb074135cbaf365868fe4aecb947bcf617c8395b"
-    ],
-    "PublicationTimestamp": "2012-11-15T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "fulltext": "acae1ab62f3e11e2a2aa782bcb074135cbaf365868fe4aecb947bcf617c8395b;2018-11-15T16:39:49Z;toolService;toolService:suiteOfTools;ACOPOST - A Collection of POS Taggers;ACOPOST is a free and open source collection of four part-of-speech taggers (t3, met, tbt, and et). In corpus linguistics, part-of-speech tagging (POS tagging or POST), also called grammatical tagging or word-category disambiguation, is the process of marking up the words in a text (corpus) as corresponding to a particular part of speech, based on both its definition, as well as its context \u00e2\u0080\u0094 i.e. relationship with adjacent and related words in a phrase, sentence, or paragraph. A simplified form of this is commonly taught to school-age children, in the identification of words as nouns, verbs, adjectives, adverbs, etc. Once performed by hand, POS tagging is now done in the context of computational linguistics, using algorithms which associate discrete terms, as well as hidden parts of speech, in accordance with a set of descriptive tags.\n\n;2012-11-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5bbad1e6-baa2-5495-983a-d9b7458babae",
-    "notes": [
-        "ACOPOST is a free and open source collection of four part-of-speech taggers (t3, met, tbt, and et). In corpus linguistics, part-of-speech tagging (POS tagging or POST), also called grammatical tagging or word-category disambiguation, is the process of marking up the words in a text (corpus) as corresponding to a particular part of speech, based on both its definition, as well as its context \u00e2\u0080\u0094 i.e. relationship with adjacent and related words in a phrase, sentence, or paragraph. A simplified form of this is commonly taught to school-age children, in the identification of words as nouns, verbs, adjectives, adverbs, etc. Once performed by hand, POS tagging is now done in the context of computational linguistics, using algorithms which associate discrete terms, as well as hidden parts of speech, in accordance with a set of descriptive tags.\n\n"
-    ],
-    "oai_identifier": [
-        "acae1ab62f3e11e2a2aa782bcb074135cbaf365868fe4aecb947bcf617c8395b"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:suiteOfTools"
-    ],
-    "state": "active",
-    "title": [
-        "ACOPOST - A Collection of POS Taggers"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5bbd171d-0459-50f5-9df7-374937a39ccc.json b/oaitestdata/clarin-oai_dc/SET_1/json/5bbd171d-0459-50f5-9df7-374937a39ccc.json
deleted file mode 100644
index 87dd7052..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5bbd171d-0459-50f5-9df7-374937a39ccc.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Masaryk University, NLP Centre"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Amharic"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2593",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2593"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2593",
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Masaryk University, NLP Centre"
-    ],
-    "RelatedIdentifier": [
-        "https://link.springer.com/chapter/10.1007/978-3-319-45510-5_34",
-        "https://www.sketchengine.co.uk/wp-content/uploads/2015/05/Corpus_Factory_2010.pdf"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Rychl\u00fd, Pavel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2593;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Amharic WIC Corpus;Rychl\u00fd, Pavel;text corpora;Ethiopian languages;web corpora;under-resourced languages;Amharic;Substantially cleaned version of existing morphologically annotated WIC Corpus.;2016;corpus;http://hdl.handle.net/11234/1-2593;amh;https://link.springer.com/chapter/10.1007/978-3-319-45510-5_34;https://www.sketchengine.co.uk/wp-content/uploads/2015/05/Corpus_Factory_2010.pdf;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Masaryk University, NLP Centre;http://habit-project.eu/wiki/HabitSystemFinal",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5bbd171d-0459-50f5-9df7-374937a39ccc",
-    "notes": [
-        "Substantially cleaned version of existing morphologically annotated WIC Corpus."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2593"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "text corpora"
-        },
-        {
-            "name": "Ethiopian languages"
-        },
-        {
-            "name": "web corpora"
-        },
-        {
-            "name": "under-resourced languages"
-        },
-        {
-            "name": "Amharic"
-        }
-    ],
-    "title": [
-        "Amharic WIC Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5bd0f233-5c02-585a-af9f-eaaee641b4c3.json b/oaitestdata/clarin-oai_dc/SET_1/json/5bd0f233-5c02-585a-af9f-eaaee641b4c3.json
deleted file mode 100644
index 17c70bf1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5bd0f233-5c02-585a-af9f-eaaee641b4c3.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "ClarinPL"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 20",
-        "text/plain; charset=utf-8",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/61",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/61"
-    ],
-    "PID": "http://hdl.handle.net/11321/61",
-    "PublicationTimestamp": "2015-04-07T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "ClarinPL"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Pisarze, Pisarze"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/61;2015-04-07T15:18:32Z;hdl_11321_3;hdl_11321_4;Sample20;Pisarze, Pisarze;prus_faraon_1897.txt\r\nbalucki_przebudzeni_1864.txt\r\nreymont_komediantka_1896.txt\r\nzeromski_syzyfowe_1897.txt\r\nzapolska_kaska_1888.txt\r\nkraszewski_piast_1888.txt\r\ndeotyma_panienka_1893.txt\r\nswietochowski_prawdy_1888.txt\r\ngodlewska_kwiat_1897.txt\r\nmarrene_bozek_1871.txt\r\nbalucki_murzyn_1875.txt\r\nsygietynski_calvados_1884.txt\r\nkorzeniowski_krewni_1856.txt\r\ndeotyma_rozdrozu_1877.txt\r\nzeromski_bezdomni_1899.txt\r\nkorzeniowski_emeryt_1851.txt\r\nkaczkowski_grob_1857.txt\r\nsienkiewicz_ogniem_1884.txt\r\nsienkiewicz_rodzina_1894.txt\r\ndeotyma_zagadka_1879.txt;2015-04-07;corpus;http://hdl.handle.net/11321/61;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain; charset=utf-8;downloadable_files_count: 20;ClarinPL",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5bd0f233-5c02-585a-af9f-eaaee641b4c3",
-    "notes": [
-        "prus_faraon_1897.txt\r\nbalucki_przebudzeni_1864.txt\r\nreymont_komediantka_1896.txt\r\nzeromski_syzyfowe_1897.txt\r\nzapolska_kaska_1888.txt\r\nkraszewski_piast_1888.txt\r\ndeotyma_panienka_1893.txt\r\nswietochowski_prawdy_1888.txt\r\ngodlewska_kwiat_1897.txt\r\nmarrene_bozek_1871.txt\r\nbalucki_murzyn_1875.txt\r\nsygietynski_calvados_1884.txt\r\nkorzeniowski_krewni_1856.txt\r\ndeotyma_rozdrozu_1877.txt\r\nzeromski_bezdomni_1899.txt\r\nkorzeniowski_emeryt_1851.txt\r\nkaczkowski_grob_1857.txt\r\nsienkiewicz_ogniem_1884.txt\r\nsienkiewicz_rodzina_1894.txt\r\ndeotyma_zagadka_1879.txt"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/61"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Sample20"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5be344cb-49e0-5e4a-9185-66b89fff9a95.json b/oaitestdata/clarin-oai_dc/SET_1/json/5be344cb-49e0-5e4a-9185-66b89fff9a95.json
deleted file mode 100644
index e9b2985c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5be344cb-49e0-5e4a-9185-66b89fff9a95.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/12",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/12"
-    ],
-    "PID": "http://hdl.handle.net/11321/12",
-    "PublicationTimestamp": "2012-10-09T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Piasecki, Maciej"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/12;2016-01-21T14:33:12Z;hdl_11321_3;hdl_11321_4;Fextor;Piasecki, Maciej;Fextor is a tool for extracting features from the collections of texts. It is characterized by high flexibility, while maintaining the performance and simplicity.\r\n\r\nFeatures are extracted from  text snippets, defined according to the type of pointer (token, annotation or pair annotations).  This allows the simultaneous generation of multiple features for a single document.\r\n\r\nDefining new types of features can be done by implementing in python or using a description in wccl language.\r\n\r\nFextor supports two formats of corpora - Poliqarp and CCL. The extracted features are saved in CSV format, with the possibility of converting to a matrix format, for use in LexCSD package.;2012-10-09;toolService;http://hdl.handle.net/11321/12;pol;downloadable_files_count: 0;Wroc\u0142aw University of Technology;http://nlp.pwr.wroc.pl/pl/narzedzia-i-zasoby/fextor",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5be344cb-49e0-5e4a-9185-66b89fff9a95",
-    "notes": [
-        "Fextor is a tool for extracting features from the collections of texts. It is characterized by high flexibility, while maintaining the performance and simplicity.\r\n\r\nFeatures are extracted from  text snippets, defined according to the type of pointer (token, annotation or pair annotations).  This allows the simultaneous generation of multiple features for a single document.\r\n\r\nDefining new types of features can be done by implementing in python or using a description in wccl language.\r\n\r\nFextor supports two formats of corpora - Poliqarp and CCL. The extracted features are saved in CSV format, with the possibility of converting to a matrix format, for use in LexCSD package."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/12"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Fextor"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5bee65fa-9db2-5d8d-aae7-6ac598eeb42f.json b/oaitestdata/clarin-oai_dc/SET_1/json/5bee65fa-9db2-5d8d-aae7-6ac598eeb42f.json
deleted file mode 100644
index aa03acd0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5bee65fa-9db2-5d8d-aae7-6ac598eeb42f.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=72fffc8e2cbf11e2a2aa782bcb074135a38bf90ea7b349c0a396e58f53999a92",
-    "MetadataAccess": [
-        "72fffc8e2cbf11e2a2aa782bcb074135a38bf90ea7b349c0a396e58f53999a92"
-    ],
-    "PublicationTimestamp": "2012-11-12T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "fulltext": "72fffc8e2cbf11e2a2aa782bcb074135a38bf90ea7b349c0a396e58f53999a92;2018-11-15T16:39:47Z;corpus;corpus:text;TimeBankPT;TimeBankPT, a TimeML annotated corpus of Portuguese, is the first corpus of Portuguese with rich temporal annotations (i.e. it includes annotations not only of temporal expressions but also about events and temporal relations).\n\nThe annotation scheme used is similar to TimeML. TimeBankPT is the result of adapting the English corpus used in the first TempEval challenge to the Portuguese language. \nTimeML is a rich annotation scheme in so far as it allows for the annotation of several phenomena related to time: the times, dates and periods denoted by temporal expressions, events, temporal relations, etc.\n\nSome of the features of TimeBankPT:\n- It uses the new Portuguese spelling (official document describing it, Wikipedia article). \n- It was automatically checked for errors using reasoning code. \n- It contains around 70,000 words of text, divided in a train set and a test set. \n- It contains annotations for events, temporal expressions and temporal relations. \n;2012-11-12",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5bee65fa-9db2-5d8d-aae7-6ac598eeb42f",
-    "notes": [
-        "TimeBankPT, a TimeML annotated corpus of Portuguese, is the first corpus of Portuguese with rich temporal annotations (i.e. it includes annotations not only of temporal expressions but also about events and temporal relations).\n\nThe annotation scheme used is similar to TimeML. TimeBankPT is the result of adapting the English corpus used in the first TempEval challenge to the Portuguese language. \nTimeML is a rich annotation scheme in so far as it allows for the annotation of several phenomena related to time: the times, dates and periods denoted by temporal expressions, events, temporal relations, etc.\n\nSome of the features of TimeBankPT:\n- It uses the new Portuguese spelling (official document describing it, Wikipedia article). \n- It was automatically checked for errors using reasoning code. \n- It contains around 70,000 words of text, divided in a train set and a test set. \n- It contains annotations for events, temporal expressions and temporal relations. \n"
-    ],
-    "oai_identifier": [
-        "72fffc8e2cbf11e2a2aa782bcb074135a38bf90ea7b349c0a396e58f53999a92"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "TimeBankPT"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5c116e13-ba0c-51ef-9b83-a1a0249b1f43.json b/oaitestdata/clarin-oai_dc/SET_1/json/5c116e13-ba0c-51ef-9b83-a1a0249b1f43.json
deleted file mode 100644
index 411fc75b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5c116e13-ba0c-51ef-9b83-a1a0249b1f43.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2674",
-    "MetadataAccess": [
-        "oai:ota:oucs:2674"
-    ],
-    "PublicationTimestamp": "1735-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1735"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2674;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2674.xml;A meditation upon a broomstick;Swift, Jonathan, 1667-1745;1735;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5c116e13-ba0c-51ef-9b83-a1a0249b1f43",
-    "oai_identifier": [
-        "oai:ota:oucs:2674"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A meditation upon a broomstick"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2674.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5c570c2e-191c-5b88-9958-cc7e341d6601.json b/oaitestdata/clarin-oai_dc/SET_1/json/5c570c2e-191c-5b88-9958-cc7e341d6601.json
deleted file mode 100644
index 6b34c7de..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5c570c2e-191c-5b88-9958-cc7e341d6601.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "s.n."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229074",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229074"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D02-8",
-    "PublicationTimestamp": "1774-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1774"
-    ],
-    "Publisher": [
-        "s.n."
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/229074",
-        "oai:jbc.bj.uj.edu.pl:publication:240717"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1701/1800"
-    ],
-    "TempCoverageBegin": 53662478399,
-    "TempCoverageEnd": 53662478399,
-    "TemporalCoverage": " point in time : 1701-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1701-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1701-07-01T11:59:59Z",
-    "author": [
-        "Putanowicz, J\u00f3zef Alojzy (1737-1788)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229074;2019-03-01T12:42:27Z;Stan Wewn\u0119trzny Y Zewn\u0119trzny Studii Generalis Universitatis Cracoviensis 1774;Putanowicz, J\u00f3zef Alojzy (1737-1788);starodruki 18\u00a0w.;s.n.;[1774];starodruk;application/xml;clarind-uds:poldilemma-229074;hdl:11858/00-246C-0000-0023-8D02-8;Biblioteka Jagiello\u0144ska, BJ St. Dr. 113453 III;pol;http://jbc.bj.uj.edu.pl/Content/229074;oai:jbc.bj.uj.edu.pl:publication:240717;1701/1800;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5c570c2e-191c-5b88-9958-cc7e341d6601",
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229074"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Stan Wewn\u0119trzny Y Zewn\u0119trzny Studii Generalis Universitatis Cracoviensis 1774"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5c57f06f-3238-55c5-bb81-6b2fce880057.json b/oaitestdata/clarin-oai_dc/SET_1/json/5c57f06f-3238-55c5-bb81-6b2fce880057.json
deleted file mode 100644
index 06025466..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5c57f06f-3238-55c5-bb81-6b2fce880057.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "University of West Bohemia, Department of Cybernetics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 9",
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1462",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1462"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1462",
-    "PublicationTimestamp": "2014-12-15T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of West Bohemia, Department of Cybernetics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Tihelka, Daniel",
-        "Matou\u0161ek, Jind\u0159ich"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1462;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;English TTS speech corpus of air traffic (pilot) messages - Serbian accent;Matou\u0161ek, Jind\u0159ich;Tihelka, Daniel;speech corpus;text-to-speech (TTS);pitch-marks;The corpus contains recordings of male speaker, native in Serbian, talking in English. The sentences that were read by the speaker originate in the domain of air traffic control (ATC), specifically the messages used by plane pilots during routine flight. The text in the corpus originates from the transcripts of the real recordings, part of which has been released in LINDAT/CLARIN (http://hdl.handle.net/11858/00-097C-0000-0001-CCA1-0), and individual phrases were selected by special algorithm described in J\u016fzov\u00e1, M. and Tihelka, D.: Minimum Text Corpus Selection for Limited Domain Speech Synthesis (DOI 10.1007/978-3-319-10816-2_48). The corpus was used to create a limited domain speech synthesis system capable of simulating a pilot communication with an ATC officer.;2014-12-15;corpus;http://hdl.handle.net/11234/1-1462;eng;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/zip;application/zip;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain; charset=utf-8;downloadable_files_count: 9;University of West Bohemia, Department of Cybernetics;http://itblp.zcu.cz",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5c57f06f-3238-55c5-bb81-6b2fce880057",
-    "notes": [
-        "The corpus contains recordings of male speaker, native in Serbian, talking in English. The sentences that were read by the speaker originate in the domain of air traffic control (ATC), specifically the messages used by plane pilots during routine flight. The text in the corpus originates from the transcripts of the real recordings, part of which has been released in LINDAT/CLARIN (http://hdl.handle.net/11858/00-097C-0000-0001-CCA1-0), and individual phrases were selected by special algorithm described in J\u016fzov\u00e1, M. and Tihelka, D.: Minimum Text Corpus Selection for Limited Domain Speech Synthesis (DOI 10.1007/978-3-319-10816-2_48). The corpus was used to create a limited domain speech synthesis system capable of simulating a pilot communication with an ATC officer."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1462"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech corpus"
-        },
-        {
-            "name": "text-to-speech TTS"
-        },
-        {
-            "name": "pitch-marks"
-        }
-    ],
-    "title": [
-        "English TTS speech corpus of air traffic (pilot) messages - Serbian accent"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5c61f90e-8ca1-541b-b4b8-a7cbc3d3e47e.json b/oaitestdata/clarin-oai_dc/SET_1/json/5c61f90e-8ca1-541b-b4b8-a7cbc3d3e47e.json
deleted file mode 100644
index 66f0880d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5c61f90e-8ca1-541b-b4b8-a7cbc3d3e47e.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-AAF5-B",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-AAF5-B"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0022-AAF5-B",
-    "PublicationTimestamp": "2013-08-13T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/257528"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Apache License 2.0",
-        "http://opensource.org/licenses/Apache-2.0",
-        "PUB"
-    ],
-    "author": [
-        "Du\u0161ek, Ond\u0159ej",
-        "Tamchyna, Ale\u0161",
-        "Rosa, Rudolf"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-AAF5-B;2018-07-02T22:05:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;MTMonkey;Tamchyna, Ale\u0161;Du\u0161ek, Ond\u0159ej;Rosa, Rudolf;machine translation;distributed computing;web service;infrastructure;MTMonkey is a web service which handles and distributes JSON-encoded HTTP requests for machine translation (MT) among multiple machines running an MT system, including text pre- and post processing.\r\n\r\nIt consists of an application server and remote workers which handle text processing and communicate translation requests to MT systems. The communication between the application server and the workers is based on the XML-RPC protocol.;2013-08-13;toolService;http://hdl.handle.net/11858/00-097C-0000-0022-AAF5-B;info:eu-repo/grantAgreement/EC/FP7/257528;Apache License 2.0;http://opensource.org/licenses/Apache-2.0;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://github.com/ufal/mtmonkey",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5c61f90e-8ca1-541b-b4b8-a7cbc3d3e47e",
-    "notes": [
-        "MTMonkey is a web service which handles and distributes JSON-encoded HTTP requests for machine translation (MT) among multiple machines running an MT system, including text pre- and post processing.\r\n\r\nIt consists of an application server and remote workers which handle text processing and communicate translation requests to MT systems. The communication between the application server and the workers is based on the XML-RPC protocol."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-AAF5-B"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "distributed computing"
-        },
-        {
-            "name": "web service"
-        },
-        {
-            "name": "infrastructure"
-        }
-    ],
-    "title": [
-        "MTMonkey"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5c6931ee-c3ec-5fee-9944-e33c9f490d74.json b/oaitestdata/clarin-oai_dc/SET_1/json/5c6931ee-c3ec-5fee-9944-e33c9f490d74.json
deleted file mode 100644
index 98132ad8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5c6931ee-c3ec-5fee-9944-e33c9f490d74.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "Contributor": [
-        "Nazar, Rogelio"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-288",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-288"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-288",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-288;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;POPPINS;Nazar, Rogelio;Document classifier;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-288;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra;http://www.poppinsweb.com/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5c6931ee-c3ec-5fee-9944-e33c9f490d74",
-    "notes": [
-        "Document classifier"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-288"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "POPPINS"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5c6d931a-bc5a-522a-a380-078938559d90.json b/oaitestdata/clarin-oai_dc/SET_1/json/5c6d931a-bc5a-522a-a380-078938559d90.json
deleted file mode 100644
index c0c41f7f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5c6d931a-bc5a-522a-a380-078938559d90.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/15",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/15"
-    ],
-    "PID": "http://hdl.handle.net/10794/15",
-    "PublicationTimestamp": "2015-05-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Allwood, Jens",
-        "Borin, Lars"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/15;2017-10-27T15:53:50Z;hdl_10794_1;hdl_10794_2;Bring (2015-05-08);Bring (2015-05-08);Borin, Lars;Allwood, Jens;Swedish;Thesaurus;A digital version of Bring's thesaurus (1930).;Brings \"Svenskt ordf\u00f6rr\u00e5d ordnat i begreppsklasser\" (1930) i digital version.;2015-05-08;lexicalConceptualResource;http://hdl.handle.net/10794/15;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/bring",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5c6d931a-bc5a-522a-a380-078938559d90",
-    "notes": [
-        "A digital version of Bring's thesaurus (1930).",
-        "Brings \"Svenskt ordf\u00f6rr\u00e5d ordnat i begreppsklasser\" (1930) i digital version."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/15"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Thesaurus"
-        }
-    ],
-    "title": [
-        "Bring (2015-05-08)",
-        "Bring (2015-05-08)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5cdfdd51-f011-5dce-9f63-2c5ff237b733.json b/oaitestdata/clarin-oai_dc/SET_1/json/5cdfdd51-f011-5dce-9f63-2c5ff237b733.json
deleted file mode 100644
index 7cf8bf62..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5cdfdd51-f011-5dce-9f63-2c5ff237b733.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 3",
-        "application/pdf",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-FF60-B",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-FF60-B"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0022-FF60-B",
-    "PublicationTimestamp": "2013-12-02T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Bojar, Ond\u0159ej",
-        "Veselovsk\u00e1, Kate\u0159ina"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-FF60-B;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Czech SubLex 1.0;Veselovsk\u00e1, Kate\u0159ina;Bojar, Ond\u0159ej;subjectivity lexicon;sentiment analysis;opinion mining;polarity clues;Czech subjectivity lexicon, i.e. a list of subjectivity clues for sentiment analysis in Czech. The list contains 4626 evaluative items (1672 positive and 2954 negative) together with their part of speech tags, polarity orientation and source information.\r\nThe core of the Czech subjectivity lexicon has been gained by automatic translation of a freely available English subjectivity lexicon downloaded from http://www.cs.pitt.edu/mpqa/subj_lexicon.html. For translating the data into Czech, we used parallel corpus CzEng 1.0 containing 15 million parallel sentences (233 million English and 206 million Czech tokens) from seven different types of sources automatically annotated at surface and deep layers of syntactic representation. Afterwards, the lexicon has been manually refined by an experienced annotator.;2013-12-02;lexicalConceptualResource;http://hdl.handle.net/11858/00-097C-0000-0022-FF60-B;ces;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/octet-stream;application/octet-stream;application/pdf;text/plain; charset=utf-8;downloadable_files_count: 3;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/seance",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5cdfdd51-f011-5dce-9f63-2c5ff237b733",
-    "notes": [
-        "Czech subjectivity lexicon, i.e. a list of subjectivity clues for sentiment analysis in Czech. The list contains 4626 evaluative items (1672 positive and 2954 negative) together with their part of speech tags, polarity orientation and source information.\r\nThe core of the Czech subjectivity lexicon has been gained by automatic translation of a freely available English subjectivity lexicon downloaded from http://www.cs.pitt.edu/mpqa/subj_lexicon.html. For translating the data into Czech, we used parallel corpus CzEng 1.0 containing 15 million parallel sentences (233 million English and 206 million Czech tokens) from seven different types of sources automatically annotated at surface and deep layers of syntactic representation. Afterwards, the lexicon has been manually refined by an experienced annotator."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-FF60-B"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "subjectivity lexicon"
-        },
-        {
-            "name": "sentiment analysis"
-        },
-        {
-            "name": "opinion mining"
-        },
-        {
-            "name": "polarity clues"
-        }
-    ],
-    "title": [
-        "Czech SubLex 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5d1ebb6c-84a2-5cc3-b78c-0404430b1293.json b/oaitestdata/clarin-oai_dc/SET_1/json/5d1ebb6c-84a2-5cc3-b78c-0404430b1293.json
deleted file mode 100644
index d82af01a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5d1ebb6c-84a2-5cc3-b78c-0404430b1293.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=2a9f4324a3ee11e5a2aa782bcb07413520283843eabf49538981a282956038e8",
-    "MetadataAccess": [
-        "2a9f4324a3ee11e5a2aa782bcb07413520283843eabf49538981a282956038e8"
-    ],
-    "PublicationTimestamp": "2015-12-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "2a9f4324a3ee11e5a2aa782bcb07413520283843eabf49538981a282956038e8;2018-11-15T16:40:19Z;corpus;corpus:text;CINTIL-NamedEntities;The CINTIL-NamedEntities corpus, built upon the CINTIL International Corpus of Portuguese (Barreto et al., 2006), is composed of 30,493 sentences of written Portuguese with named entities manually disambiguated and annotated with links to appropriate pages in the Portuguese Dbpedia (Lehmann et al., 2012). From a total of 684,467 tokens from which 26,371 named entities were recognized, 16,120 have been annotated with links to appropriate entires in DBpedia.\n\nThe development of the CINTIL-NamedEntities corpus has been funded by the EU project QTLeap (EC/FP7/610516) and the Portuguese project DP4LT (PTDC/EEI-SII/1940/2012).;2015-12-16",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5d1ebb6c-84a2-5cc3-b78c-0404430b1293",
-    "notes": [
-        "The CINTIL-NamedEntities corpus, built upon the CINTIL International Corpus of Portuguese (Barreto et al., 2006), is composed of 30,493 sentences of written Portuguese with named entities manually disambiguated and annotated with links to appropriate pages in the Portuguese Dbpedia (Lehmann et al., 2012). From a total of 684,467 tokens from which 26,371 named entities were recognized, 16,120 have been annotated with links to appropriate entires in DBpedia.\n\nThe development of the CINTIL-NamedEntities corpus has been funded by the EU project QTLeap (EC/FP7/610516) and the Portuguese project DP4LT (PTDC/EEI-SII/1940/2012)."
-    ],
-    "oai_identifier": [
-        "2a9f4324a3ee11e5a2aa782bcb07413520283843eabf49538981a282956038e8"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "CINTIL-NamedEntities"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5d338f72-269b-5f9d-9c5a-b0ebbdcb9c75.json b/oaitestdata/clarin-oai_dc/SET_1/json/5d338f72-269b-5f9d-9c5a-b0ebbdcb9c75.json
deleted file mode 100644
index b9232025..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5d338f72-269b-5f9d-9c5a-b0ebbdcb9c75.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4647",
-    "MetadataAccess": [
-        "oai:ota:oucs:4647"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Jurin, James, 1684-1750."
-    ],
-    "fulltext": "oai:ota:oucs:4647;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4647.xml;The minute mathematician: or, the free-thinker no just-thinker. Set forth in a second letter to the author of The analyst; containing a defence of Sir Isaac Newton and the British mathematicians, ... By Philalethes Cantabrigiensis;Jurin, James, 1684-1750.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5d338f72-269b-5f9d-9c5a-b0ebbdcb9c75",
-    "oai_identifier": [
-        "oai:ota:oucs:4647"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The minute mathematician: or, the free-thinker no just-thinker. Set forth in a second letter to the author of The analyst; containing a defence of Sir Isaac Newton and the British mathematicians, ... By Philalethes Cantabrigiensis"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4647.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5d3de83d-e164-5cef-b775-661a8a8ca528.json b/oaitestdata/clarin-oai_dc/SET_1/json/5d3de83d-e164-5cef-b775-661a8a8ca528.json
deleted file mode 100644
index b57673c8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5d3de83d-e164-5cef-b775-661a8a8ca528.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3623",
-    "MetadataAccess": [
-        "oai:ota:oucs:3623"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Henry, David, 1710-1792."
-    ],
-    "fulltext": "oai:ota:oucs:3623;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3623.xml;An historical account of all the voyages round the world, performed by English navigators; including those lately undertaken by order of His present Majesty. The whole faithfully extracted from the journals of the voyagers. ... In four volumes.: [pt.2];Henry, David, 1710-1792.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5d3de83d-e164-5cef-b775-661a8a8ca528",
-    "oai_identifier": [
-        "oai:ota:oucs:3623"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An historical account of all the voyages round the world, performed by English navigators; including those lately undertaken by order of His present Majesty. The whole faithfully extracted from the journals of the voyagers. ... In four volumes.: [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3623.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5d44ff9c-6334-57e5-96a8-6b2348e75754.json b/oaitestdata/clarin-oai_dc/SET_1/json/5d44ff9c-6334-57e5-96a8-6b2348e75754.json
deleted file mode 100644
index 2d81d97a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5d44ff9c-6334-57e5-96a8-6b2348e75754.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "University of York"
-    ],
-    "Contributor": [
-        "Pintzuk, Susan"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-885",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-885"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-885",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of York"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-885;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;York-Helsinki Parsed Corpus of Old English Poetry;Pintzuk, Susan;A selection of poetic texts (71,490 words) from the Old English Section of the Helsinki Corpus of English Texts, syntactically and morphologically annotated.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-885;eng;downloadable_files_count: 0;United Kingdom;University of York;http://www-users.york.ac.uk/~lang18/pcorpus.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5d44ff9c-6334-57e5-96a8-6b2348e75754",
-    "notes": [
-        "A selection of poetic texts (71,490 words) from the Old English Section of the Helsinki Corpus of English Texts, syntactically and morphologically annotated."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-885"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "York-Helsinki Parsed Corpus of Old English Poetry"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5d4b34a0-cf9d-5919-8df0-a174c1b0aca8.json b/oaitestdata/clarin-oai_dc/SET_1/json/5d4b34a0-cf9d-5919-8df0-a174c1b0aca8.json
deleted file mode 100644
index b8038807..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5d4b34a0-cf9d-5919-8df0-a174c1b0aca8.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2660",
-    "MetadataAccess": [
-        "oai:ota:oucs:2660"
-    ],
-    "PublicationTimestamp": "1732-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1732"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2660;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2660.xml;Considerations upon two bills ... relating to the clergy of Ireland;Swift, Jonathan, 1667-1745;1732;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5d4b34a0-cf9d-5919-8df0-a174c1b0aca8",
-    "oai_identifier": [
-        "oai:ota:oucs:2660"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Considerations upon two bills ... relating to the clergy of Ireland"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2660.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5d4bc41d-22ea-5fcb-8483-a16cf1c91a8f.json b/oaitestdata/clarin-oai_dc/SET_1/json/5d4bc41d-22ea-5fcb-8483-a16cf1c91a8f.json
deleted file mode 100644
index 01288799..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5d4bc41d-22ea-5fcb-8483-a16cf1c91a8f.json
+++ /dev/null
@@ -1,97 +0,0 @@
-{
-    "Contact": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 3",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1052",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1052"
-    ],
-    "PID": "http://hdl.handle.net/11356/1052",
-    "PublicationTimestamp": "2015-10-26T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11356/1165",
-        "http://hdl.handle.net/11356/1029"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/"
-    ],
-    "author": [
-        "Krek, Simon",
-        "Dobrovoljc, Kaja",
-        "Erjavec, Toma\u017e",
-        "Ledinek, Nina",
-        "Holz, Nanika",
-        "Mo\u017ee, Sara"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1052;2019-01-26T20:47:25Z;hdl_11356_1023;hdl_11356_1024;Training corpus ssj500k 1.4;Krek, Simon;Dobrovoljc, Kaja;Erjavec, Toma\u017e;Mo\u017ee, Sara;Ledinek, Nina;Holz, Nanika;tagging;dependency treebank;parsing;named entities;tokenisation;manual annotation;TEI;The ssj500k training corpus contains 500,000 words, manually annotated on the levels of tokenization, sentence segmentation, morphosyntactic tagging, lemmatisation, named entities, and, partially, syntactic dependencies. The ssj500k corpus uses the MULTEXT-East / JOS morphosyntactic tagset and the JOS dependency schema and is based on the jos100k and jos1M corpora. Note that this entry updates ssj500k 1.3 by fixing many annotation errors.;2015-10-26;corpus;http://hdl.handle.net/11356/1052;slv;http://hdl.handle.net/11356/1165;http://hdl.handle.net/11356/1029;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);PUB;https://creativecommons.org/licenses/by-nc-sa/4.0/;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 3;Centre for Language Resources and Technologies, University of Ljubljana;http://eng.slovenscina.eu/tehnologije/ucni-korpus",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5d4bc41d-22ea-5fcb-8483-a16cf1c91a8f",
-    "notes": [
-        "The ssj500k training corpus contains 500,000 words, manually annotated on the levels of tokenization, sentence segmentation, morphosyntactic tagging, lemmatisation, named entities, and, partially, syntactic dependencies. The ssj500k corpus uses the MULTEXT-East / JOS morphosyntactic tagset and the JOS dependency schema and is based on the jos100k and jos1M corpora. Note that this entry updates ssj500k 1.3 by fixing many annotation errors."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1052"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "dependency treebank"
-        },
-        {
-            "name": "parsing"
-        },
-        {
-            "name": "named entities"
-        },
-        {
-            "name": "tokenisation"
-        },
-        {
-            "name": "manual annotation"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "Training corpus ssj500k 1.4"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5d83ee51-2d71-537e-b566-8f292311db11.json b/oaitestdata/clarin-oai_dc/SET_1/json/5d83ee51-2d71-537e-b566-8f292311db11.json
deleted file mode 100644
index 0f7ecdb9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5d83ee51-2d71-537e-b566-8f292311db11.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4314",
-    "MetadataAccess": [
-        "oai:ota:oucs:4314"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Defoe, Daniel, 1661?-1731."
-    ],
-    "fulltext": "oai:ota:oucs:4314;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4314.xml;The advantages of peace and commerce: with some remarks on the East-India trade.;Defoe, Daniel, 1661?-1731.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5d83ee51-2d71-537e-b566-8f292311db11",
-    "oai_identifier": [
-        "oai:ota:oucs:4314"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The advantages of peace and commerce: with some remarks on the East-India trade."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4314.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5daf1b07-14e2-5652-9dae-b4d7e5632f40.json b/oaitestdata/clarin-oai_dc/SET_1/json/5daf1b07-14e2-5652-9dae-b4d7e5632f40.json
deleted file mode 100644
index fcdd8299..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5daf1b07-14e2-5652-9dae-b4d7e5632f40.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=a8550c806ec311e2a2aa782bcb074135a2cd490541a5448b93b0ccd040237406",
-    "MetadataAccess": [
-        "a8550c806ec311e2a2aa782bcb074135a2cd490541a5448b93b0ccd040237406"
-    ],
-    "PublicationTimestamp": "2013-02-04T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "a8550c806ec311e2a2aa782bcb074135a2cd490541a5448b93b0ccd040237406;2019-02-27T12:09:40Z;toolService;toolService:tool;U-Compare speech synthesis and visualisation workflow;This is a workflow that is designed especially for use in the UIMA-based U-Compare workbench (see separate META-SHARE record).  The workflow is in \"ucz\" format (specific to U-Compare) and can be imported via the \"Import Workflow\" item in the \"Workflows\" menu of the U-Compare interface. It includes the \"Synthesizer Annotator\" component (based on the Ogimios speech synthesis software, developed at Universitat Polit\u00c3\u00a8cnica de Catalunya) and the \"Synthesizer Annotation Viewer\" component, developed at the University of Manchester. The latter component provides a visualisation of the speech signals and transcriptions of individual words.  \n\n;2013-02-04",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5daf1b07-14e2-5652-9dae-b4d7e5632f40",
-    "notes": [
-        "This is a workflow that is designed especially for use in the UIMA-based U-Compare workbench (see separate META-SHARE record).  The workflow is in \"ucz\" format (specific to U-Compare) and can be imported via the \"Import Workflow\" item in the \"Workflows\" menu of the U-Compare interface. It includes the \"Synthesizer Annotator\" component (based on the Ogimios speech synthesis software, developed at Universitat Polit\u00c3\u00a8cnica de Catalunya) and the \"Synthesizer Annotation Viewer\" component, developed at the University of Manchester. The latter component provides a visualisation of the speech signals and transcriptions of individual words.  \n\n"
-    ],
-    "oai_identifier": [
-        "a8550c806ec311e2a2aa782bcb074135a2cd490541a5448b93b0ccd040237406"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "U-Compare speech synthesis and visualisation workflow"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5ddf39e2-eefd-5961-b353-56fb90baec50.json b/oaitestdata/clarin-oai_dc/SET_1/json/5ddf39e2-eefd-5961-b353-56fb90baec50.json
deleted file mode 100644
index f6a27b20..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5ddf39e2-eefd-5961-b353-56fb90baec50.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/30",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/30"
-    ],
-    "PID": "http://hdl.handle.net/10794/30",
-    "PublicationTimestamp": "2012-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/30;2017-10-27T14:37:33Z;hdl_10794_1;hdl_10794_2;LWT (2017-10-16);LWT (2017-10-16);n/a, n/a;Swedish;Typology;Loan Word Typology list.;L\u00e5nordstypologi.;2012-05-30;lexicalConceptualResource;http://hdl.handle.net/10794/30;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/lwt",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5ddf39e2-eefd-5961-b353-56fb90baec50",
-    "notes": [
-        "Loan Word Typology list.",
-        "L\u00e5nordstypologi."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/30"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Typology"
-        }
-    ],
-    "title": [
-        "LWT (2017-10-16)",
-        "LWT (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5df1aaaf-f50d-52be-a60d-e79381828f89.json b/oaitestdata/clarin-oai_dc/SET_1/json/5df1aaaf-f50d-52be-a60d-e79381828f89.json
deleted file mode 100644
index 567ba958..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5df1aaaf-f50d-52be-a60d-e79381828f89.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Portuguese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-396",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-396"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-396",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Italy"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-396;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;The JRC-Acquis Multilingual Parallel Corpus;Law;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-396;por;downloadable_files_count: 0;Italy;http://langtech.jrc.it/JRC-Acquis.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5df1aaaf-f50d-52be-a60d-e79381828f89",
-    "notes": [
-        "Law"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-396"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "The JRC-Acquis Multilingual Parallel Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5df845df-5d00-541b-8422-02e139a349f5.json b/oaitestdata/clarin-oai_dc/SET_1/json/5df845df-5d00-541b-8422-02e139a349f5.json
deleted file mode 100644
index 907001f1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5df845df-5d00-541b-8422-02e139a349f5.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=f30f4d04486111e2a2aa782bcb07413522a84532f1d443ffb62c5fcf3c59545a",
-    "MetadataAccess": [
-        "f30f4d04486111e2a2aa782bcb07413522a84532f1d443ffb62c5fcf3c59545a"
-    ],
-    "PublicationTimestamp": "2013-01-21T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "f30f4d04486111e2a2aa782bcb07413522a84532f1d443ffb62c5fcf3c59545a;2019-02-27T12:09:25Z;corpus;corpus:text;EUROPARL Corpus\nParallel Corpora: Portuguese-English\n;The EUROPARL Corpus (subpart Portuguese-English of the parallel corpora), available at http://www.statmt.org/europarl/, was extracted from the proceedings of the European Parliament (Koehn, 2005). It contains transcriptions of sessions dating back from 1996 to 2011, in a total of approximately 58,324,562 tokens words of European Portuguese (L1) and 49,216,896 tokens of English (translation).;2013-01-21",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5df845df-5d00-541b-8422-02e139a349f5",
-    "notes": [
-        "The EUROPARL Corpus (subpart Portuguese-English of the parallel corpora), available at http://www.statmt.org/europarl/, was extracted from the proceedings of the European Parliament (Koehn, 2005). It contains transcriptions of sessions dating back from 1996 to 2011, in a total of approximately 58,324,562 tokens words of European Portuguese (L1) and 49,216,896 tokens of English (translation)."
-    ],
-    "oai_identifier": [
-        "f30f4d04486111e2a2aa782bcb07413522a84532f1d443ffb62c5fcf3c59545a"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "EUROPARL Corpus\nParallel Corpora: Portuguese-English\n"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5e150ae7-caf2-57d5-b158-e95fa4f2205e.json b/oaitestdata/clarin-oai_dc/SET_1/json/5e150ae7-caf2-57d5-b158-e95fa4f2205e.json
deleted file mode 100644
index 00a67ee9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5e150ae7-caf2-57d5-b158-e95fa4f2205e.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=4dc94c44bc7c11e1a404080027e73ea26de48b275c064ef79134fc7632d15394",
-    "MetadataAccess": [
-        "4dc94c44bc7c11e1a404080027e73ea26de48b275c064ef79134fc7632d15394"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "4dc94c44bc7c11e1a404080027e73ea26de48b275c064ef79134fc7632d15394;2018-11-15T16:39:36Z;toolService;toolService:platform;U-Compare Platform;The purpose of the U-Compare platform is to facilitate easy and rapid development and evaluation of NLP and text mining systems. It includes utilities (including a graphical user interface, the U-Compare workbench, see separate record in META-SHARE) to create workflows from individual, interoperable NLP tools and resources, a customisable system to create and evaluate different workflows, and different utilities to visualise different types of annotations produced by workflows.  U-Compare is packaged with the world\u00e2\u0080\u0099s largest repository of UIMA components. This repository, which originally consisted largely of tools for processing English biomedical text, in being considerably enlarged as ongoing work, to include tools that can operate on a number of European languages and multilingual tools.;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5e150ae7-caf2-57d5-b158-e95fa4f2205e",
-    "notes": [
-        "The purpose of the U-Compare platform is to facilitate easy and rapid development and evaluation of NLP and text mining systems. It includes utilities (including a graphical user interface, the U-Compare workbench, see separate record in META-SHARE) to create workflows from individual, interoperable NLP tools and resources, a customisable system to create and evaluate different workflows, and different utilities to visualise different types of annotations produced by workflows.  U-Compare is packaged with the world\u00e2\u0080\u0099s largest repository of UIMA components. This repository, which originally consisted largely of tools for processing English biomedical text, in being considerably enlarged as ongoing work, to include tools that can operate on a number of European languages and multilingual tools."
-    ],
-    "oai_identifier": [
-        "4dc94c44bc7c11e1a404080027e73ea26de48b275c064ef79134fc7632d15394"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:platform"
-    ],
-    "state": "active",
-    "title": [
-        "U-Compare Platform"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5e275fb6-94e7-5a31-915f-c27fe0598272.json b/oaitestdata/clarin-oai_dc/SET_1/json/5e275fb6-94e7-5a31-915f-c27fe0598272.json
deleted file mode 100644
index 9257f7cf..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5e275fb6-94e7-5a31-915f-c27fe0598272.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4175",
-    "MetadataAccess": [
-        "oai:ota:oucs:4175"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Lloyd, Robert."
-    ],
-    "fulltext": "oai:ota:oucs:4175;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4175.xml;[Shakespeare: an epistle to Mr. Garrick; with an ode to genius.];Lloyd, Robert.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5e275fb6-94e7-5a31-915f-c27fe0598272",
-    "oai_identifier": [
-        "oai:ota:oucs:4175"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "[Shakespeare: an epistle to Mr. Garrick; with an ode to genius.]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4175.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5e3f6d4a-98de-548d-8315-6af4872a2cd8.json b/oaitestdata/clarin-oai_dc/SET_1/json/5e3f6d4a-98de-548d-8315-6af4872a2cd8.json
deleted file mode 100644
index 2d528eb5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5e3f6d4a-98de-548d-8315-6af4872a2cd8.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "text/html",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2538",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2538"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2538",
-    "PublicationTimestamp": "2017-12-24T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "M\u00edrovsk\u00fd, Ji\u0159\u00ed",
-        "Pol\u00e1kov\u00e1, Lucie",
-        "Rysov\u00e1, Magdal\u00e9na",
-        "Synkov\u00e1, Pavl\u00edna"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2538;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;CzeDLex 0.5;M\u00edrovsk\u00fd, Ji\u0159\u00ed;Synkov\u00e1, Pavl\u00edna;Rysov\u00e1, Magdal\u00e9na;Pol\u00e1kov\u00e1, Lucie;lexicon;discourse annotation;CzeDLex 0.5 is a pilot version of a lexicon of Czech discourse connectives. The lexicon contains connectives partially automatically extracted from the Prague Discourse Treebank 2.0 (PDiT 2.0), a large corpus annotated manually with discourse relations. The most frequent entries in the lexicon (covering more than 2/3 of the discourse relations annotated in the PDiT 2.0) have been manually checked, translated to English and supplemented with additional linguistic information.;2017-12-24;lexicalConceptualResource;http://hdl.handle.net/11234/1-2538;ces;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;text/html;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://ufal.mff.cuni.cz/textlink-cz/czedlex0.5",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5e3f6d4a-98de-548d-8315-6af4872a2cd8",
-    "notes": [
-        "CzeDLex 0.5 is a pilot version of a lexicon of Czech discourse connectives. The lexicon contains connectives partially automatically extracted from the Prague Discourse Treebank 2.0 (PDiT 2.0), a large corpus annotated manually with discourse relations. The most frequent entries in the lexicon (covering more than 2/3 of the discourse relations annotated in the PDiT 2.0) have been manually checked, translated to English and supplemented with additional linguistic information."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2538"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "lexicon"
-        },
-        {
-            "name": "discourse annotation"
-        }
-    ],
-    "title": [
-        "CzeDLex 0.5"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5e5affb2-7284-5a72-9b7d-bc98a7e9fa02.json b/oaitestdata/clarin-oai_dc/SET_1/json/5e5affb2-7284-5a72-9b7d-bc98a7e9fa02.json
deleted file mode 100644
index a4ef4689..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5e5affb2-7284-5a72-9b7d-bc98a7e9fa02.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5047",
-    "MetadataAccess": [
-        "oai:ota:oucs:5047"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Trusler, John, 1735-1820."
-    ],
-    "fulltext": "oai:ota:oucs:5047;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5047.xml;The habitable world described: or the present state of the people in all parts of the globe, from north to south; shewing the situation, extent, climate, ... including all the new discoveries: ... With a great variety of maps and copper-plates, ... By the Rev. Dr. John Trusler. ... [pt.13];Trusler, John, 1735-1820.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5e5affb2-7284-5a72-9b7d-bc98a7e9fa02",
-    "oai_identifier": [
-        "oai:ota:oucs:5047"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The habitable world described: or the present state of the people in all parts of the globe, from north to south; shewing the situation, extent, climate, ... including all the new discoveries: ... With a great variety of maps and copper-plates, ... By the Rev. Dr. John Trusler. ... [pt.13]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5047.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5e5d8075-5d51-5104-a9b4-a566a1d1e7ac.json b/oaitestdata/clarin-oai_dc/SET_1/json/5e5d8075-5d51-5104-a9b4-a566a1d1e7ac.json
deleted file mode 100644
index c5826d75..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5e5d8075-5d51-5104-a9b4-a566a1d1e7ac.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4248",
-    "MetadataAccess": [
-        "oai:ota:oucs:4248"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Funnell, William."
-    ],
-    "fulltext": "oai:ota:oucs:4248;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4248.xml;A voyage round the world. Containing an account of Captain Dampier's expedition into the South-Seas in the ship St George, in the years 1703 and 1704. ... Together with the author's voyage from Amapalla ... By William Funnell,;Funnell, William.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5e5d8075-5d51-5104-a9b4-a566a1d1e7ac",
-    "oai_identifier": [
-        "oai:ota:oucs:4248"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A voyage round the world. Containing an account of Captain Dampier's expedition into the South-Seas in the ship St George, in the years 1703 and 1704. ... Together with the author's voyage from Amapalla ... By William Funnell,"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4248.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5e6b21ea-992f-55e3-bb82-41e26545e007.json b/oaitestdata/clarin-oai_dc/SET_1/json/5e6b21ea-992f-55e3-bb82-41e26545e007.json
deleted file mode 100644
index 49c91338..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5e6b21ea-992f-55e3-bb82-41e26545e007.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5677",
-    "MetadataAccess": [
-        "oai:ota:oucs:5677"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Maiden Hospital (Edinburgh, Scotland)"
-    ],
-    "fulltext": "oai:ota:oucs:5677;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5677.xml;Statutes of the Maiden Hospital: founded by the company of merchants of Edinburgh, and Mary Erskine.;Maiden Hospital (Edinburgh, Scotland);text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5e6b21ea-992f-55e3-bb82-41e26545e007",
-    "oai_identifier": [
-        "oai:ota:oucs:5677"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Statutes of the Maiden Hospital: founded by the company of merchants of Edinburgh, and Mary Erskine."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5677.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5e7686dd-77f2-5763-9997-cb7ca53ecce7.json b/oaitestdata/clarin-oai_dc/SET_1/json/5e7686dd-77f2-5763-9997-cb7ca53ecce7.json
deleted file mode 100644
index 51bb1200..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5e7686dd-77f2-5763-9997-cb7ca53ecce7.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "Oslo University",
-        "Charles University"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "English",
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1956",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1956"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1956",
-    "PublicationTimestamp": "2017-01-28T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Oslo University",
-        "Charles University"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-1742"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Kuhlmann, Marco",
-        "Haji\u010d, Jan",
-        "Ivanova, Angelina",
-        "Zeman, Daniel",
-        "Miyao, Yusuke",
-        "Flickinger, Dan",
-        "Oepen, Stephan"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1956;2018-07-02T22:05:54Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Open SDP 1.2;Flickinger, Dan;Haji\u010d, Jan;Ivanova, Angelina;Kuhlmann, Marco;Miyao, Yusuke;Oepen, Stephan;Zeman, Daniel;semantic dependency;parsing;The original SDP 2014 and 2015 data collections were made available under task-specific \u2018evaluation\u2019 licenses to registered SemEval participants. In mid-2016, all original data has been bundled with system submissions, supporting software, an additional SDP-style collection of semantic dependency graphs, and additional background material (from which some of the SDP target representations were derived) for release through the Linguistic Data Consortium (with LDC catalogue number LDC2016\u2009T10).\r\n\r\nOne of the four English target representations (viz. DM) and the entire Czech data (in the PSD target representation) are not derivative of LDC-licensed annotations and, thus, can be made available for direct download (Open SDP; version 1.2; January 2017) under a more permissive licensing scheme, viz. the Creative Common Attribution-NonCommercial-ShareAlike license. This package also includes some \u2018richer\u2019 meaning representations from which the English bi-lexical DM graphs derive, viz. scope-underspecified logical forms and more abstract, non-lexicalized \u2018semantic networks\u2019. The latter of these are formally (if not linguistically) similar to Abstract Meaning Representation (AMR) and are available in a range of serializations, including in AMR-like syntax.\r\n\r\nVersion 1.1 was released April 2016. Version 1.2 adds the 2015 Turku system, which was accidentally left out from version 1.1.\r\n\r\nPlease use the following bibliographic reference for the SDP 2016 data:\r\n\r\n  @string{C:LREC = {{I}nternational {C}onference on\r\n                    {L}anguage {R}esources and {E}valuation}}\r\n  @string{LREC:16 = {Proceedings of the 10th } # C:LREC}\r\n  @string{L:LREC:16 = {Portoro\\v{z}, Slovenia}}\r\n\r\n  @inproceedings{Oep:Kuh:Miy:16,\r\n    author = {Oepen, Stephan  and  Kuhlmann, Marco  and  Miyao, Yusuke  \r\n              and  Zeman, Daniel  and  Cinkov{\\'a}, Silvie  \r\n              and  Flickinger, Dan  and  Haji\\v{c}, Jan  \r\n              and  Ivanova, Angelina and Ure\\v{s}ov{\\'a}, Zde\\v{n}ka},\r\n    title = {Towards Comparability of Linguistic Graph Banks for Semantic Parsing},\r\n    booktitle = LREC:16\r\n    year = 2016,\r\n    address = L:LREC:16,\r\n    pages = {3991--3995}\r\n  };2017-01-28;corpus;http://hdl.handle.net/11234/1-1956;eng;ces;http://hdl.handle.net/11234/1-1742;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Oslo University;Charles University;http://sdp.delph-in.net/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5e7686dd-77f2-5763-9997-cb7ca53ecce7",
-    "notes": [
-        "The original SDP 2014 and 2015 data collections were made available under task-specific \u2018evaluation\u2019 licenses to registered SemEval participants. In mid-2016, all original data has been bundled with system submissions, supporting software, an additional SDP-style collection of semantic dependency graphs, and additional background material (from which some of the SDP target representations were derived) for release through the Linguistic Data Consortium (with LDC catalogue number LDC2016\u2009T10).\r\n\r\nOne of the four English target representations (viz. DM) and the entire Czech data (in the PSD target representation) are not derivative of LDC-licensed annotations and, thus, can be made available for direct download (Open SDP; version 1.2; January 2017) under a more permissive licensing scheme, viz. the Creative Common Attribution-NonCommercial-ShareAlike license. This package also includes some \u2018richer\u2019 meaning representations from which the English bi-lexical DM graphs derive, viz. scope-underspecified logical forms and more abstract, non-lexicalized \u2018semantic networks\u2019. The latter of these are formally (if not linguistically) similar to Abstract Meaning Representation (AMR) and are available in a range of serializations, including in AMR-like syntax.\r\n\r\nVersion 1.1 was released April 2016. Version 1.2 adds the 2015 Turku system, which was accidentally left out from version 1.1.\r\n\r\nPlease use the following bibliographic reference for the SDP 2016 data:\r\n\r\n  @string{C:LREC = {{I}nternational {C}onference on\r\n                    {L}anguage {R}esources and {E}valuation}}\r\n  @string{LREC:16 = {Proceedings of the 10th } # C:LREC}\r\n  @string{L:LREC:16 = {Portoro\\v{z}, Slovenia}}\r\n\r\n  @inproceedings{Oep:Kuh:Miy:16,\r\n    author = {Oepen, Stephan  and  Kuhlmann, Marco  and  Miyao, Yusuke  \r\n              and  Zeman, Daniel  and  Cinkov{\\'a}, Silvie  \r\n              and  Flickinger, Dan  and  Haji\\v{c}, Jan  \r\n              and  Ivanova, Angelina and Ure\\v{s}ov{\\'a}, Zde\\v{n}ka},\r\n    title = {Towards Comparability of Linguistic Graph Banks for Semantic Parsing},\r\n    booktitle = LREC:16\r\n    year = 2016,\r\n    address = L:LREC:16,\r\n    pages = {3991--3995}\r\n  }"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1956"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "semantic dependency"
-        },
-        {
-            "name": "parsing"
-        }
-    ],
-    "title": [
-        "Open SDP 1.2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5ebf4cf0-de7b-53f4-b4f4-c92829465c2d.json b/oaitestdata/clarin-oai_dc/SET_1/json/5ebf4cf0-de7b-53f4-b4f4-c92829465c2d.json
deleted file mode 100644
index 29e1b6e7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5ebf4cf0-de7b-53f4-b4f4-c92829465c2d.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 128 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1704",
-    "MetadataAccess": [
-        "oai:ota:oucs:1704"
-    ],
-    "PublicationTimestamp": "1992-06-15T11:59:59Z",
-    "PublicationYear": [
-        "1992"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Wordsworth, William, 1770-1850"
-    ],
-    "fulltext": "oai:ota:oucs:1704;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1704.xml;Lyrical ballads / William Wordsworth and Samuel Taylor Coleridge;Wordsworth, William, 1770-1850;1992-06-15;text_and_corpus_linguistics;Poems -- Great Britain -- 18th century;Lyric poems -- Great Britain -- 18th century;eng;This is the original version of the work taken from the first anonymous Bristol imprint of 1798 ;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 128 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5ebf4cf0-de7b-53f4-b4f4-c92829465c2d",
-    "notes": [
-        "This is the original version of the work taken from the first anonymous Bristol imprint of 1798 "
-    ],
-    "oai_identifier": [
-        "oai:ota:oucs:1704"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- Great Britain -- th century"
-        },
-        {
-            "name": "Lyric poems -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Lyrical ballads / William Wordsworth and Samuel Taylor Coleridge"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1704.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5ece7292-c3a8-59b2-9ab4-454d652e8b6f.json b/oaitestdata/clarin-oai_dc/SET_1/json/5ece7292-c3a8-59b2-9ab4-454d652e8b6f.json
deleted file mode 100644
index c09e9475..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5ece7292-c3a8-59b2-9ab4-454d652e8b6f.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4189",
-    "MetadataAccess": [
-        "oai:ota:oucs:4189"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Bickerstaff, Isaac, 1735-1812."
-    ],
-    "fulltext": "oai:ota:oucs:4189;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4189.xml;The sultan, or a peep into the seraglio: A farce, in two acts. By Isaac Bickerstaffe. Acted at the Theatres Royal in Drury-Lane and Covent-Garden.;Bickerstaff, Isaac, 1735-1812.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5ece7292-c3a8-59b2-9ab4-454d652e8b6f",
-    "oai_identifier": [
-        "oai:ota:oucs:4189"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The sultan, or a peep into the seraglio: A farce, in two acts. By Isaac Bickerstaffe. Acted at the Theatres Royal in Drury-Lane and Covent-Garden."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4189.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5ecf44ed-3b1d-55b8-af3c-c73de4913eb6.json b/oaitestdata/clarin-oai_dc/SET_1/json/5ecf44ed-3b1d-55b8-af3c-c73de4913eb6.json
deleted file mode 100644
index b2d26038..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5ecf44ed-3b1d-55b8-af3c-c73de4913eb6.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3729",
-    "MetadataAccess": [
-        "oai:ota:oucs:3729"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Burke, William, 1730-1798."
-    ],
-    "fulltext": "oai:ota:oucs:3729;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3729.xml;An account of the European settlements in America: In six parts. ... In two volumes. ... [pt.1];Burke, William, 1730-1798.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5ecf44ed-3b1d-55b8-af3c-c73de4913eb6",
-    "oai_identifier": [
-        "oai:ota:oucs:3729"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An account of the European settlements in America: In six parts. ... In two volumes. ... [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3729.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5f06d420-2ead-5a91-838a-25206f981499.json b/oaitestdata/clarin-oai_dc/SET_1/json/5f06d420-2ead-5a91-838a-25206f981499.json
deleted file mode 100644
index fd106715..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5f06d420-2ead-5a91-838a-25206f981499.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4111",
-    "MetadataAccess": [
-        "oai:ota:oucs:4111"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Churchill, Charles, 1731-1764."
-    ],
-    "fulltext": "oai:ota:oucs:4111;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4111.xml;Night: An epistle to Robert Lloyd. By the author.;Churchill, Charles, 1731-1764.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5f06d420-2ead-5a91-838a-25206f981499",
-    "oai_identifier": [
-        "oai:ota:oucs:4111"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Night: An epistle to Robert Lloyd. By the author."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4111.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5f18688a-9f9c-5073-b17a-c94d0baf3a92.json b/oaitestdata/clarin-oai_dc/SET_1/json/5f18688a-9f9c-5073-b17a-c94d0baf3a92.json
deleted file mode 100644
index e4f031f3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5f18688a-9f9c-5073-b17a-c94d0baf3a92.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3101",
-    "MetadataAccess": [
-        "oai:ota:oucs:3101"
-    ],
-    "PublicationTimestamp": "1849-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1849"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gaskell, Elizabeth Cleghorn, 1810-1865"
-    ],
-    "fulltext": "oai:ota:oucs:3101;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3101.xml;Hand and heart;Gaskell, Elizabeth Cleghorn, 1810-1865;not after: 1849;text_and_corpus_linguistics;Fiction -- Great Britain -- 19th century;Short stories -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5f18688a-9f9c-5073-b17a-c94d0baf3a92",
-    "oai_identifier": [
-        "oai:ota:oucs:3101"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- Great Britain -- th century"
-        },
-        {
-            "name": "Short stories -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Hand and heart"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3101.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5f24f8f5-0e19-5722-84ee-52ff12f1913a.json b/oaitestdata/clarin-oai_dc/SET_1/json/5f24f8f5-0e19-5722-84ee-52ff12f1913a.json
deleted file mode 100644
index 2dd29671..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5f24f8f5-0e19-5722-84ee-52ff12f1913a.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3496",
-    "MetadataAccess": [
-        "oai:ota:oucs:3496"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Berkeley, George, 1685-1753."
-    ],
-    "fulltext": "oai:ota:oucs:3496;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3496.xml;A word to the wise: or, an exhortation to the Roman Catholic clergy of Ireland: By a member of the established church.;Berkeley, George, 1685-1753.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5f24f8f5-0e19-5722-84ee-52ff12f1913a",
-    "oai_identifier": [
-        "oai:ota:oucs:3496"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A word to the wise: or, an exhortation to the Roman Catholic clergy of Ireland: By a member of the established church."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3496.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5f3e8ec6-e670-593f-81cb-487d9177af59.json b/oaitestdata/clarin-oai_dc/SET_1/json/5f3e8ec6-e670-593f-81cb-487d9177af59.json
deleted file mode 100644
index 01153dd7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5f3e8ec6-e670-593f-81cb-487d9177af59.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3096",
-    "MetadataAccess": [
-        "oai:ota:oucs:3096"
-    ],
-    "PublicationTimestamp": "1853-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1853"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gaskell, Elizabeth Cleghorn, 1810-1865"
-    ],
-    "fulltext": "oai:ota:oucs:3096;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3096.xml;Cranford;Gaskell, Elizabeth Cleghorn, 1810-1865;not after: 1853;text_and_corpus_linguistics;English fiction -- 19th century;eng;Oxford Text Archive, University of Oxford;Triggs, Jeffery;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5f3e8ec6-e670-593f-81cb-487d9177af59",
-    "oai_identifier": [
-        "oai:ota:oucs:3096"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English fiction -- th century"
-        }
-    ],
-    "title": [
-        "Cranford"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3096.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5f3fd4b7-9359-5cbe-b161-74adfb9b6d1d.json b/oaitestdata/clarin-oai_dc/SET_1/json/5f3fd4b7-9359-5cbe-b161-74adfb9b6d1d.json
deleted file mode 100644
index 22795650..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5f3fd4b7-9359-5cbe-b161-74adfb9b6d1d.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Estonian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-250",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-250"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-250",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Estonia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-250;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Corpus of Present-day Written Estonian;written general; 95 mio words; TEI/SGML;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-250;est;downloadable_files_count: 0;Estonia;http://www.cl.ut.ee/korpused/morfkorpus/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5f3fd4b7-9359-5cbe-b161-74adfb9b6d1d",
-    "notes": [
-        "written general; 95 mio words; TEI/SGML"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-250"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus of Present-day Written Estonian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5f52f903-d5c9-5567-aca9-65830449fa42.json b/oaitestdata/clarin-oai_dc/SET_1/json/5f52f903-d5c9-5567-aca9-65830449fa42.json
deleted file mode 100644
index 3cab8ce0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5f52f903-d5c9-5567-aca9-65830449fa42.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1323",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1323"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1323",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1323;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Synpathy;annotation tool;Synpathy is a tool for annotating, analyzing, and graphically editing the syntactical structure of sentences (e.g. linguisticly annotated text corpora), developed at the Max Planck Institute for Psycholinguistics, Nijmegen, the Netherlands. The application is based on the SyntaxViewer from the TIGER search project developed by the IMS (Institute f\u00fcr Maschinelle Sprachverarbeitung, University of Stuttgart).\r\n\r\nSince all (non) terminal node features values are user definable a wide range of linguistic descriptions like syntax trees, functional structures, dependency-style structures or predicate-argument structures can be accommodated. The annotated text together with its treebank graph information is stored separately from the list of labels used in the graph (features). Output formats are in persistent TIGER-XML. This facilitates the further processing of the data by other linguistic applications (like ELAN and ANNEX).;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1323;downloadable_files_count: 0;Netherlands (the);Max Planck Institute for Psycholinguistics;https://tla.mpi.nl/tools/tla-tools/older-tools/synpathy/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5f52f903-d5c9-5567-aca9-65830449fa42",
-    "notes": [
-        "Synpathy is a tool for annotating, analyzing, and graphically editing the syntactical structure of sentences (e.g. linguisticly annotated text corpora), developed at the Max Planck Institute for Psycholinguistics, Nijmegen, the Netherlands. The application is based on the SyntaxViewer from the TIGER search project developed by the IMS (Institute f\u00fcr Maschinelle Sprachverarbeitung, University of Stuttgart).\r\n\r\nSince all (non) terminal node features values are user definable a wide range of linguistic descriptions like syntax trees, functional structures, dependency-style structures or predicate-argument structures can be accommodated. The annotated text together with its treebank graph information is stored separately from the list of labels used in the graph (features). Output formats are in persistent TIGER-XML. This facilitates the further processing of the data by other linguistic applications (like ELAN and ANNEX)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1323"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "annotation tool"
-        }
-    ],
-    "title": [
-        "Synpathy"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5f598c86-b5de-5b6b-9c63-5a1b762daec7.json b/oaitestdata/clarin-oai_dc/SET_1/json/5f598c86-b5de-5b6b-9c63-5a1b762daec7.json
deleted file mode 100644
index ab45a59f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5f598c86-b5de-5b6b-9c63-5a1b762daec7.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paksoy, H.B., 1948-"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 65 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2220",
-    "MetadataAccess": [
-        "oai:ota:oucs:2220"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Chronicals"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Paksoy, H.B., 1948-"
-    ],
-    "fulltext": "oai:ota:oucs:2220;2018-02-16T10:42:06Z;http://ota.ox.ac.uk/headers/2220.xml;Alpamysh : Central Asian identity under Russian rule / Paksoy, H.B., 1948-;Paksoy, H.B., 1948-;text_and_corpus_linguistics;Asia, Central -- History -- 20th century;eng;Oxford Text Archive, University of Oxford;Paksoy, H.B., 1948-;text/plain;(1 file : ca. 65 KB);Text;Chronicals;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5f598c86-b5de-5b6b-9c63-5a1b762daec7",
-    "oai_identifier": [
-        "oai:ota:oucs:2220"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Asia"
-        },
-        {
-            "name": "Central -- History -- th century"
-        }
-    ],
-    "title": [
-        "Alpamysh : Central Asian identity under Russian rule / Paksoy, H.B., 1948-"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2220.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5f7142e8-bc99-5f2e-8b6a-28f497ecfd3f.json b/oaitestdata/clarin-oai_dc/SET_1/json/5f7142e8-bc99-5f2e-8b6a-28f497ecfd3f.json
deleted file mode 100644
index 679ccc4e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5f7142e8-bc99-5f2e-8b6a-28f497ecfd3f.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3946",
-    "MetadataAccess": [
-        "oai:ota:oucs:3946"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Francis, Philip, 1708?-1773."
-    ],
-    "fulltext": "oai:ota:oucs:3946;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3946.xml;Eugenia: a tragedy. As it is acted at the Theatre-Royal, in Drury-Lane. By His Majesty's servants;Francis, Philip, 1708?-1773.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5f7142e8-bc99-5f2e-8b6a-28f497ecfd3f",
-    "oai_identifier": [
-        "oai:ota:oucs:3946"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Eugenia: a tragedy. As it is acted at the Theatre-Royal, in Drury-Lane. By His Majesty's servants"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3946.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5f9ab791-469e-5666-b76e-5792341611d5.json b/oaitestdata/clarin-oai_dc/SET_1/json/5f9ab791-469e-5666-b76e-5792341611d5.json
deleted file mode 100644
index abf595b2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5f9ab791-469e-5666-b76e-5792341611d5.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "UW"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/463",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/463"
-    ],
-    "PID": "http://hdl.handle.net/11321/463",
-    "PublicationTimestamp": "2018-04-12T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "UW"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "PDT 2.0 License",
-        "http://ufal.mff.cuni.cz/pdt2.0/doc/pdt-guide/en/html/ch07.html",
-        "ACA"
-    ],
-    "author": [
-        "Ochma\u0144ski, Miko\u0142aj"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/463;2018-04-12T14:35:16Z;hdl_11321_3;hdl_11321_4;Blogi_zip 02;Ochma\u0144ski, Miko\u0142aj;blogi;blogi zip;2018-04-12;corpus;http://hdl.handle.net/11321/463;pol;PDT 2.0 License;http://ufal.mff.cuni.cz/pdt2.0/doc/pdt-guide/en/html/ch07.html;ACA;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;UW",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5f9ab791-469e-5666-b76e-5792341611d5",
-    "notes": [
-        "blogi zip"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/463"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "blogi"
-        }
-    ],
-    "title": [
-        "Blogi_zip 02"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5fb8a072-5a2b-5635-9a96-c885adade125.json b/oaitestdata/clarin-oai_dc/SET_1/json/5fb8a072-5a2b-5635-9a96-c885adade125.json
deleted file mode 100644
index f9141e52..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5fb8a072-5a2b-5635-9a96-c885adade125.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Kompetenzzentrum f\u00fcr elektronische Erschlie\u00dfungs",
-        "Publikationsverfahren in den Geisteswissenschaften"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-969",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-969"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-969",
-    "PublicationTimestamp": "2004-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2004"
-    ],
-    "Publisher": [
-        "Kompetenzzentrum f\u00fcr elektronische Erschlie\u00dfungs",
-        "Publikationsverfahren in den Geisteswissenschaften"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-969;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Das Deutsche W\u00f6rterbuch von Jacob und Wilhelm Grimm;Online edition of the Grimm brothers' \"Deutsche W\u00f6rterbuch\" (1838). Each word shows the Grimms' etymological sources. Also available on CD-ROM;2004;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-969;deu;downloadable_files_count: 0;Germany;Kompetenzzentrum f\u00fcr elektronische Erschlie\u00dfungs;Publikationsverfahren in den Geisteswissenschaften;http://germazope.uni-trier.de/Projects/DWB",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5fb8a072-5a2b-5635-9a96-c885adade125",
-    "notes": [
-        "Online edition of the Grimm brothers' \"Deutsche W\u00f6rterbuch\" (1838). Each word shows the Grimms' etymological sources. Also available on CD-ROM"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-969"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Das Deutsche W\u00f6rterbuch von Jacob und Wilhelm Grimm"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5fba95c0-5fb6-57be-914a-7727e12820a4.json b/oaitestdata/clarin-oai_dc/SET_1/json/5fba95c0-5fb6-57be-914a-7727e12820a4.json
deleted file mode 100644
index c19254cd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5fba95c0-5fb6-57be-914a-7727e12820a4.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3204",
-    "MetadataAccess": [
-        "oai:ota:oucs:3204"
-    ],
-    "PublicationTimestamp": "1864-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1864"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Trollope, Anthony, 1815-1882"
-    ],
-    "fulltext": "oai:ota:oucs:3204;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3204.xml;Can you forgive her?;Trollope, Anthony, 1815-1882;not after: 1864;text_and_corpus_linguistics;Novels -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5fba95c0-5fb6-57be-914a-7727e12820a4",
-    "oai_identifier": [
-        "oai:ota:oucs:3204"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Novels -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Can you forgive her?"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3204.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5fdfeefc-32bb-55b5-9f4e-4b4fa0073097.json b/oaitestdata/clarin-oai_dc/SET_1/json/5fdfeefc-32bb-55b5-9f4e-4b4fa0073097.json
deleted file mode 100644
index 25f39805..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5fdfeefc-32bb-55b5-9f4e-4b4fa0073097.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Research Institute for Artificial Intelligence, Romanian Academy of Sciences"
-    ],
-    "Contributor": [
-        "Tufi\u015f, Dan",
-        "Ceau\u015fu, Alexandru"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-198",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-198"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-198",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Research Institute for Artificial Intelligence, Romanian Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Romania"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-198;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;ABC - Language Identifier;Tufi\u015f, Dan;Ceau\u015fu, Alexandru;The application, developed in C#, automatically identifies the language of a text written in one of the 21 European Union languages. By using training texts in different languages (approx. 1.5Mb of text for each language), a training module counts the prefixes (the first 3 characters) and the suffixes (4 characters endings) for all the words in the texts, for each language. For every language two models are constructed, containing the weights (percentages) of prefixes and suffixes in the texts representing a language. In the prediction phase, for a new text, two models are built on the fly in a similar manner. These models are then compared with the stored models representing each language for which the application was trained. Using comparison functions, the best model is chose. More detailed descriptions are available in [[http://www.racai.ro/~tufis/papers|the following papers]]: -- Dan Tufi\u015f, Radu Ion, Alexandru Ceau\u015fu, and Dan \u015etef\u0103nescu (2008). RACAI's Linguistic Web Services. In Proceedings of the 6th Language Resources and Evaluation Conference - LREC 2008, Marrakech, Morocco, May 2008. ELRA - European Language Resources Association. ISBN 2-9517408-4-0. -- Dan Tufi\u015f and Alexandru Ceau\u015fu (2007). Diacritics Restoration in Romanian Texts. In Elena Paskaleva and Milena Slavcheva (eds.), A Common Natural Language Processing Paradigm for Balkan Languages - RANLP 2007 Workshop Proceedings, pp. 49-56, Borovets, Bulgaria, September 2007. INCOMA Ltd., Shoumen, Bulgaria. ISBN 978-954-91743-8-0. -- Dan Tufi\u015f and Adrian Chi\u0163u (1999). Automatic Insertion of Diacritics in Romanian Texts. In Ferenc Kiefer, G\u00e1bor Kiss, and J\u00falia Pajzs (eds.), Proceedings of the 5th International Workshop on Computational Lexicography (COMPLEX 1999), pp. 185-194, Pecs, Hungary, May 1999. Linguistics Institute, Hungarian Academy of Sciences.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-198;downloadable_files_count: 0;Romania;Research Institute for Artificial Intelligence, Romanian Academy of Sciences;http://www.racai.ro/webservices/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5fdfeefc-32bb-55b5-9f4e-4b4fa0073097",
-    "notes": [
-        "The application, developed in C#, automatically identifies the language of a text written in one of the 21 European Union languages. By using training texts in different languages (approx. 1.5Mb of text for each language), a training module counts the prefixes (the first 3 characters) and the suffixes (4 characters endings) for all the words in the texts, for each language. For every language two models are constructed, containing the weights (percentages) of prefixes and suffixes in the texts representing a language. In the prediction phase, for a new text, two models are built on the fly in a similar manner. These models are then compared with the stored models representing each language for which the application was trained. Using comparison functions, the best model is chose. More detailed descriptions are available in [[http://www.racai.ro/~tufis/papers|the following papers]]: -- Dan Tufi\u015f, Radu Ion, Alexandru Ceau\u015fu, and Dan \u015etef\u0103nescu (2008). RACAI's Linguistic Web Services. In Proceedings of the 6th Language Resources and Evaluation Conference - LREC 2008, Marrakech, Morocco, May 2008. ELRA - European Language Resources Association. ISBN 2-9517408-4-0. -- Dan Tufi\u015f and Alexandru Ceau\u015fu (2007). Diacritics Restoration in Romanian Texts. In Elena Paskaleva and Milena Slavcheva (eds.), A Common Natural Language Processing Paradigm for Balkan Languages - RANLP 2007 Workshop Proceedings, pp. 49-56, Borovets, Bulgaria, September 2007. INCOMA Ltd., Shoumen, Bulgaria. ISBN 978-954-91743-8-0. -- Dan Tufi\u015f and Adrian Chi\u0163u (1999). Automatic Insertion of Diacritics in Romanian Texts. In Ferenc Kiefer, G\u00e1bor Kiss, and J\u00falia Pajzs (eds.), Proceedings of the 5th International Workshop on Computational Lexicography (COMPLEX 1999), pp. 185-194, Pecs, Hungary, May 1999. Linguistics Institute, Hungarian Academy of Sciences."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-198"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "ABC - Language Identifier"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/5feb3fa6-6b0c-5b2c-9937-5c78ddccbb78.json b/oaitestdata/clarin-oai_dc/SET_1/json/5feb3fa6-6b0c-5b2c-9937-5c78ddccbb78.json
deleted file mode 100644
index 99b2d670..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/5feb3fa6-6b0c-5b2c-9937-5c78ddccbb78.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 5",
-        "text/plain; charset=utf-8",
-        "application/pdf",
-        "application/x-xz"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2889",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2889"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2889",
-    "PublicationTimestamp": "2018-11-13T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "BSD 3-Clause \"New\" or \"Revised\" license",
-        "http://opensource.org/licenses/BSD-3-Clause",
-        "PUB"
-    ],
-    "author": [
-        "Haji\u010d, Jan",
-        "B\u00f6hm, Stanislav"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2889;2018-11-13T12:23:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;VIADAT-SEARCH;B\u00f6hm, Stanislav;Haji\u010d, Jan;oral history;speech;search;VIADAT-SEARCH in connection with VIADAT-REPO enables searching transcripts of oral history recordings. Language analysis has been used to preprocess the recordings, which makes it possible to search the fulltext using multiple criteria, including names, different forms of the same word etc.\r\n\r\nDeveloped in cooperation with \u00daSD AV \u010cR and NFA.;2018-11-13;toolService;http://hdl.handle.net/11234/1-2889;BSD 3-Clause \"New\" or \"Revised\" license;http://opensource.org/licenses/BSD-3-Clause;PUB;application/x-xz;application/pdf;application/pdf;application/pdf;application/pdf;text/plain; charset=utf-8;downloadable_files_count: 5;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://ufal.mff.cuni.cz/grants/viadat",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5feb3fa6-6b0c-5b2c-9937-5c78ddccbb78",
-    "notes": [
-        "VIADAT-SEARCH in connection with VIADAT-REPO enables searching transcripts of oral history recordings. Language analysis has been used to preprocess the recordings, which makes it possible to search the fulltext using multiple criteria, including names, different forms of the same word etc.\r\n\r\nDeveloped in cooperation with \u00daSD AV \u010cR and NFA."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2889"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "oral history"
-        },
-        {
-            "name": "speech"
-        },
-        {
-            "name": "search"
-        }
-    ],
-    "title": [
-        "VIADAT-SEARCH"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/600185c2-4151-51cb-bb1d-87aacc880f5e.json b/oaitestdata/clarin-oai_dc/SET_1/json/600185c2-4151-51cb-bb1d-87aacc880f5e.json
deleted file mode 100644
index 4adca836..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/600185c2-4151-51cb-bb1d-87aacc880f5e.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Royster, Paul"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3026",
-    "MetadataAccess": [
-        "oai:ota:oucs:3026"
-    ],
-    "PublicationTimestamp": "1916-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1916"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "James, Henry, 1843-1916"
-    ],
-    "fulltext": "oai:ota:oucs:3026;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3026.xml;Essays on literature;James, Henry, 1843-1916;not after: 1916;text_and_corpus_linguistics;American essays -- 19th century;eng;Oxford Text Archive, University of Oxford;Royster, Paul;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "600185c2-4151-51cb-bb1d-87aacc880f5e",
-    "oai_identifier": [
-        "oai:ota:oucs:3026"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "American essays -- th century"
-        }
-    ],
-    "title": [
-        "Essays on literature"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3026.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/604af3bb-1d59-558b-adac-7a9732c60d14.json b/oaitestdata/clarin-oai_dc/SET_1/json/604af3bb-1d59-558b-adac-7a9732c60d14.json
deleted file mode 100644
index bb2ce668..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/604af3bb-1d59-558b-adac-7a9732c60d14.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Fakult\u00e4t Geisteswissenschaften, Universit\u00e4t Duisburg-Essen",
-        "Korpora.org"
-    ],
-    "Contributor": [
-        "Fisseni, Bernhard",
-        "Schmitz, Dr. Hans-Christian",
-        "Schr\u00f6der, Prof. Dr. Bernhard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1122",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1122"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1122",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Fakult\u00e4t Geisteswissenschaften, Universit\u00e4t Duisburg-Essen",
-        "Korpora.org"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1122;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Kant-Korpus (Daten des Projekts Bereitstellung und Pflege von Immanuel Kants Werken in elektronischer Form);Schr\u00f6der, Prof. Dr. Bernhard;Schmitz, Dr. Hans-Christian;Fisseni, Bernhard;Germanistik;Philosophical texts of the 18th century: Full text of the authoritative \"Akademie-Ausgabe\" (excluding most footnotes and editorial notes) and reference texts like A.G. Baumgarten's \"Metaphysica\".;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1122;deu;lat;downloadable_files_count: 0;Germany;Korpora.org;Fakult\u00e4t Geisteswissenschaften, Universit\u00e4t Duisburg-Essen;http://www.korpora.org/Kant/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "604af3bb-1d59-558b-adac-7a9732c60d14",
-    "notes": [
-        "Philosophical texts of the 18th century: Full text of the authoritative \"Akademie-Ausgabe\" (excluding most footnotes and editorial notes) and reference texts like A.G. Baumgarten's \"Metaphysica\"."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1122"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Kant-Korpus (Daten des Projekts Bereitstellung und Pflege von Immanuel Kants Werken in elektronischer Form)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/60505144-0e98-5390-84d0-b401109803d2.json b/oaitestdata/clarin-oai_dc/SET_1/json/60505144-0e98-5390-84d0-b401109803d2.json
deleted file mode 100644
index 057511cc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/60505144-0e98-5390-84d0-b401109803d2.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/301",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/301"
-    ],
-    "PID": "http://hdl.handle.net/11321/301",
-    "PublicationTimestamp": "2016-04-25T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Marci\u0144czuk, Micha\u0142",
-        "Koco\u0144, Jan"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/301;2016-06-07T05:19:43Z;hdl_11321_3;hdl_11321_4;Liner2.5 model Events;Koco\u0144, Jan;Marci\u0144czuk, Micha\u0142;information extraction;events;event mentions;A model for Liner2 to recognize event mentions.;2016-04-25;languageDescription;http://hdl.handle.net/11321/301;pol;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;Wroc\u0142aw University of Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "60505144-0e98-5390-84d0-b401109803d2",
-    "notes": [
-        "A model for Liner2 to recognize event mentions."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/301"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "information extraction"
-        },
-        {
-            "name": "events"
-        },
-        {
-            "name": "event mentions"
-        }
-    ],
-    "title": [
-        "Liner2.5 model Events"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/605a19e7-9c01-5c8b-a037-389e46cd386d.json b/oaitestdata/clarin-oai_dc/SET_1/json/605a19e7-9c01-5c8b-a037-389e46cd386d.json
deleted file mode 100644
index e9dab70d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/605a19e7-9c01-5c8b-a037-389e46cd386d.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-921",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-921"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-921",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-921;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Palaic;ca. 4.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-921;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#pal",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "605a19e7-9c01-5c8b-a037-389e46cd386d",
-    "notes": [
-        "ca. 4.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-921"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Palaic"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/606cfffd-0c10-5ed9-9a47-f9616296f926.json b/oaitestdata/clarin-oai_dc/SET_1/json/606cfffd-0c10-5ed9-9a47-f9616296f926.json
deleted file mode 100644
index 04718ce6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/606cfffd-0c10-5ed9-9a47-f9616296f926.json
+++ /dev/null
@@ -1,93 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 8",
-        "application/pdf",
-        "application/zip"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-B098-5",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-B098-5"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-B098-5",
-    "PublicationTimestamp": "2006-07-21T11:59:59Z",
-    "PublicationYear": [
-        "2006"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11858/00-097C-0000-0006-DB11-8"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "PDT 2.0 License",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/license-pdt2",
-        "ACA"
-    ],
-    "author": [
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "Panevov\u00e1, Jarmila",
-        "Ure\u0161ov\u00e1, Zde\u0148ka",
-        "Haji\u010d, Jan",
-        "\u0160ev\u010d\u00edkov\u00e1-Raz\u00edmov\u00e1, Magda",
-        "\u0160t\u011bp\u00e1nek, Jan",
-        "Mikulov\u00e1, Marie",
-        "Haji\u010dov\u00e1, Eva",
-        "Sgall, Petr",
-        "Pajas, Petr",
-        "Havelka, Ji\u0159\u00ed"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-B098-5;2018-07-02T22:05:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Prague Dependency Treebank 2.0 (PDT 2.0);Haji\u010d, Jan;Panevov\u00e1, Jarmila;Haji\u010dov\u00e1, Eva;Sgall, Petr;Pajas, Petr;\u0160t\u011bp\u00e1nek, Jan;Havelka, Ji\u0159\u00ed;Mikulov\u00e1, Marie;\u017dabokrtsk\u00fd, Zden\u011bk;\u0160ev\u010d\u00edkov\u00e1-Raz\u00edmov\u00e1, Magda;Ure\u0161ov\u00e1, Zde\u0148ka;corpus;Czech;treebank;PDT;The Prague Dependency Treebank 2.0 (PDT 2.0) contains a large amount of Czech texts with complex and interlinked morphological (two million words), syntactic (1.5 MW) and complex semantic annotation (0.8 MW); in addition, certain properties of sentence information structure and coreference relations are annotated at the semantic level.\r\n\r\nPDT 2.0 is based on the long-standing Praguian linguistic tradition, adapted for the current Computational Linguistics research needs. The corpus itself uses the latest annotation technology. Software tools for corpus search, annotation and language analysis are included. Extensive documentation (in English) is provided as well.;2006-07-21;corpus;LDC2006T01;http://hdl.handle.net/11858/00-097C-0000-0001-B098-5;ces;http://hdl.handle.net/11858/00-097C-0000-0006-DB11-8;PDT 2.0 License;https://lindat.mff.cuni.cz/repository/xmlui/page/license-pdt2;ACA;text/plain; charset=utf-8;application/zip;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;downloadable_files_count: 8;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/pdt2.0/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "606cfffd-0c10-5ed9-9a47-f9616296f926",
-    "notes": [
-        "The Prague Dependency Treebank 2.0 (PDT 2.0) contains a large amount of Czech texts with complex and interlinked morphological (two million words), syntactic (1.5 MW) and complex semantic annotation (0.8 MW); in addition, certain properties of sentence information structure and coreference relations are annotated at the semantic level.\r\n\r\nPDT 2.0 is based on the long-standing Praguian linguistic tradition, adapted for the current Computational Linguistics research needs. The corpus itself uses the latest annotation technology. Software tools for corpus search, annotation and language analysis are included. Extensive documentation (in English) is provided as well."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-B098-5"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "Czech"
-        },
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "PDT"
-        }
-    ],
-    "title": [
-        "Prague Dependency Treebank 2.0 (PDT 2.0)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/60824435-7260-5e9f-bfc3-c5d33007d641.json b/oaitestdata/clarin-oai_dc/SET_1/json/60824435-7260-5e9f-bfc3-c5d33007d641.json
deleted file mode 100644
index 85c5a48f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/60824435-7260-5e9f-bfc3-c5d33007d641.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "The Danish Language Council",
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml",
-        "text/plain; charset=utf-8",
-        "text/plain",
-        "downloadable_files_count: 11",
-        "application/zip",
-        "application/pdf"
-    ],
-    "Language": [
-        "Danish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repository.clarin.dk:20.500.12115/13",
-    "MetadataAccess": [
-        "oai:repository.clarin.dk:20.500.12115/13"
-    ],
-    "PID": "http://hdl.handle.net/20.500.12115/13",
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "The Danish Language Council",
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN-ACA-NC",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NC=1&NORED=1",
-        "ACA"
-    ],
-    "author": [
-        "Hansen, Dorte Haltrup",
-        "Braasch, Anna",
-        "Olsen, Sussi",
-        "Jakob, Halskov"
-    ],
-    "fulltext": "oai:repository.clarin.dk:20.500.12115/13;2018-06-28T13:24:55Z;hdl_20.500.12115_1;hdl_20.500.12115_3;DK-CLARIN LSP Corpus - Environment domain;Olsen, Sussi;Braasch, Anna;Jakob, Halskov;Hansen, Dorte Haltrup;Environment;Texts in the Environment Domain come from Hovedland, Danske Milj\u00f8unders\u00f8gelser, Det \u00d8kologiske R\u00e5d and Aktuel Naturvidenskab(via DMI).\r\nThe corpus consists of 1,478,298 words in 93 files. \r\nCommunicative setting/Number of files: expert->expert (2) expert->advanced (23) expert->basic (68).\r\nAll texts are in XML TEIP5 format (TEIP5DKCLARIN-format), with tokenisation, pos-tagging, sentence and paragraph segmentation, lemmatisation and termhood annotation placed in separate text external spangroups. \r\n\"DK-CLARIN LSP Corpus - Environment domain\" is a part of the Danish DK-CLARIN LSP corpus consisting of seven sub-corpora from following subject domains: Agriculture, Construction, Economics, Environment, Health, IT and Nanotechnology.;2011;corpus;http://hdl.handle.net/20.500.12115/13;dan;CLARIN-ACA-NC;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NC=1&NORED=1;ACA;text/plain; charset=utf-8;application/zip;application/zip;application/zip;application/zip;text/plain;application/pdf;text/xml;application/pdf;application/pdf;text/xml;text/xml;downloadable_files_count: 11;Centre for Language Technology, NorS, University of Copenhagen;The Danish Language Council",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "60824435-7260-5e9f-bfc3-c5d33007d641",
-    "notes": [
-        "Texts in the Environment Domain come from Hovedland, Danske Milj\u00f8unders\u00f8gelser, Det \u00d8kologiske R\u00e5d and Aktuel Naturvidenskab(via DMI).\r\nThe corpus consists of 1,478,298 words in 93 files. \r\nCommunicative setting/Number of files: expert->expert (2) expert->advanced (23) expert->basic (68).\r\nAll texts are in XML TEIP5 format (TEIP5DKCLARIN-format), with tokenisation, pos-tagging, sentence and paragraph segmentation, lemmatisation and termhood annotation placed in separate text external spangroups. \r\n\"DK-CLARIN LSP Corpus - Environment domain\" is a part of the Danish DK-CLARIN LSP corpus consisting of seven sub-corpora from following subject domains: Agriculture, Construction, Economics, Environment, Health, IT and Nanotechnology."
-    ],
-    "oai_identifier": [
-        "oai:repository.clarin.dk:20.500.12115/13"
-    ],
-    "oai_set": [
-        "hdl_20.500.12115_1",
-        "hdl_20.500.12115_3"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Environment"
-        }
-    ],
-    "title": [
-        "DK-CLARIN LSP Corpus - Environment domain"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/608ec5a7-39dd-5f79-9a13-84c6d5b12c91.json b/oaitestdata/clarin-oai_dc/SET_1/json/608ec5a7-39dd-5f79-9a13-84c6d5b12c91.json
deleted file mode 100644
index d3d5a576..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/608ec5a7-39dd-5f79-9a13-84c6d5b12c91.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "Ossetian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-918",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-918"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-918",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-918;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Ossetian;ca. 40.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-918;oss;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#osset",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "608ec5a7-39dd-5f79-9a13-84c6d5b12c91",
-    "notes": [
-        "ca. 40.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-918"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Ossetian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/60c20488-95f1-58de-b6d1-98336632aad4.json b/oaitestdata/clarin-oai_dc/SET_1/json/60c20488-95f1-58de-b6d1-98336632aad4.json
deleted file mode 100644
index e09777b2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/60c20488-95f1-58de-b6d1-98336632aad4.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3761",
-    "MetadataAccess": [
-        "oai:ota:oucs:3761"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Lennox, Charlotte, ca. 1729-1804."
-    ],
-    "fulltext": "oai:ota:oucs:3761;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3761.xml;The sister: a comedy. By Mrs. Charlotte Lennox.;Lennox, Charlotte, ca. 1729-1804.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "60c20488-95f1-58de-b6d1-98336632aad4",
-    "oai_identifier": [
-        "oai:ota:oucs:3761"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The sister: a comedy. By Mrs. Charlotte Lennox."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3761.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/60d77971-c651-5f8a-b4e3-e343c687d1d0.json b/oaitestdata/clarin-oai_dc/SET_1/json/60d77971-c651-5f8a-b4e3-e343c687d1d0.json
deleted file mode 100644
index 17da37bd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/60d77971-c651-5f8a-b4e3-e343c687d1d0.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/pdf"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/589",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/589"
-    ],
-    "PID": "http://hdl.handle.net/11321/589",
-    "PublicationTimestamp": "2018-07-27T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "K\u0119dzia, Pawe\u0142",
-        "Oleksy, Marcin",
-        "Wieczorek, Jan",
-        "Turek, Agnieszka"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/589;2018-07-27T09:23:29Z;hdl_11321_3;hdl_11321_4;KPWr annotation guidelines - keywords (1.0);Oleksy, Marcin;Wieczorek, Jan;Turek, Agnieszka;K\u0119dzia, Pawe\u0142;keywords;KPWr;annotated corpus;metadata;Annotation guidelines (first version) for keywords in KPWr (Polish Corpus of Wroc\u0142aw University of Technology (https://clarin-pl.eu/dspace/handle/11321/270).;2018-07-27;languageDescription;http://hdl.handle.net/11321/589;pol;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;application/pdf;downloadable_files_count: 1;Wroc\u0142aw University of Science and Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "60d77971-c651-5f8a-b4e3-e343c687d1d0",
-    "notes": [
-        "Annotation guidelines (first version) for keywords in KPWr (Polish Corpus of Wroc\u0142aw University of Technology (https://clarin-pl.eu/dspace/handle/11321/270)."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/589"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "keywords"
-        },
-        {
-            "name": "KPWr"
-        },
-        {
-            "name": "annotated corpus"
-        },
-        {
-            "name": "metadata"
-        }
-    ],
-    "title": [
-        "KPWr annotation guidelines - keywords (1.0)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/60e8a470-60ee-5f43-8b52-e962ed45c779.json b/oaitestdata/clarin-oai_dc/SET_1/json/60e8a470-60ee-5f43-8b52-e962ed45c779.json
deleted file mode 100644
index bbf00950..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/60e8a470-60ee-5f43-8b52-e962ed45c779.json
+++ /dev/null
@@ -1,92 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-4671-4",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-4671-4"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-4671-4",
-    "PublicationTimestamp": "2014-02-21T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0)",
-        "http://creativecommons.org/licenses/by-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u017dilka, Luk\u00e1\u0161",
-        "Jur\u010d\u00ed\u010dek, Filip",
-        "Du\u0161ek, Ond\u0159ej",
-        "Pl\u00e1tek, Ond\u0159ej",
-        "Korvas, Mat\u011bj"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-4671-4;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Vystadial 2013 \u2013 English data;Korvas, Mat\u011bj;Pl\u00e1tek, Ond\u0159ej;Du\u0161ek, Ond\u0159ej;\u017dilka, Luk\u00e1\u0161;Jur\u010d\u00ed\u010dek, Filip;acoustic data;speech corpus;spoken corpus;orthographic transcriptions;telephone speech;voip;dialogue system;Vystadial 2013 is a dataset of telephone conversations in English and Czech, developed for training acoustic models for automatic speech recognition in spoken dialogue systems. It ships in three parts: Czech data, English data, and scripts.\r\n\r\nThe data comprise over 41 hours of speech in English and over 15 hours in Czech, plus orthographic transcriptions. The scripts implement data pre-processing and building acoustic models using the HTK and Kaldi toolkits.\r\n\r\nThis is the English data part of the dataset.;2014-02-21;corpus;http://hdl.handle.net/11858/00-097C-0000-0023-4671-4;eng;Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0);http://creativecommons.org/licenses/by-sa/3.0/;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics;https://ufal.mff.cuni.cz/grants/vystadial",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "60e8a470-60ee-5f43-8b52-e962ed45c779",
-    "notes": [
-        "Vystadial 2013 is a dataset of telephone conversations in English and Czech, developed for training acoustic models for automatic speech recognition in spoken dialogue systems. It ships in three parts: Czech data, English data, and scripts.\r\n\r\nThe data comprise over 41 hours of speech in English and over 15 hours in Czech, plus orthographic transcriptions. The scripts implement data pre-processing and building acoustic models using the HTK and Kaldi toolkits.\r\n\r\nThis is the English data part of the dataset."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-4671-4"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "acoustic data"
-        },
-        {
-            "name": "speech corpus"
-        },
-        {
-            "name": "spoken corpus"
-        },
-        {
-            "name": "orthographic transcriptions"
-        },
-        {
-            "name": "telephone speech"
-        },
-        {
-            "name": "voip"
-        },
-        {
-            "name": "dialogue system"
-        }
-    ],
-    "title": [
-        "Vystadial 2013 \u2013 English data"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/60edab01-9662-5bdf-8da6-93f799cd6d2d.json b/oaitestdata/clarin-oai_dc/SET_1/json/60edab01-9662-5bdf-8da6-93f799cd6d2d.json
deleted file mode 100644
index 6033f80b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/60edab01-9662-5bdf-8da6-93f799cd6d2d.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics",
-        "University of Stockholm",
-        "Radboud University Nijmegen",
-        "City University London"
-    ],
-    "Contributor": [
-        "Crasborn, Onno"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "video/mpeg",
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-570",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-570"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-570",
-    "PublicationTimestamp": "2004-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2004"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics",
-        "University of Stockholm",
-        "Radboud University Nijmegen",
-        "City University London"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons BY-NC-SA 3.0 NL license",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/nl/"
-    ],
-    "SpatialCoverage": [
-        "Netherlands (the)||Sweden||United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-570;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;ECHO corpus;Crasborn, Onno;This is a corpus of four European sign languages. It contains richly annotated video files of Sign Language of the Netherlands (Nederlandse Gebarentaal), British Sign Language, and Swedish Sign Language; data include narratives, dialogues, small lexicons, and poetry. In addition, parts of a corpus of German Sign Language (Deutsche Geb\u00e4rdensprache) is included that was already published on paper before.;2004;corpus;http://hdl.handle.net/11372/LRT-570;Creative Commons BY-NC-SA 3.0 NL license;http://creativecommons.org/licenses/by-nc-sa/3.0/nl/;video/mpeg;downloadable_files_count: 0;Netherlands (the)||Sweden||United Kingdom;Radboud University Nijmegen;Max Planck Institute for Psycholinguistics;University of Stockholm;City University London;http://corpus1.mpi.nl/ds/imdi_browser/?openpath=MPI84302%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "60edab01-9662-5bdf-8da6-93f799cd6d2d",
-    "notes": [
-        "This is a corpus of four European sign languages. It contains richly annotated video files of Sign Language of the Netherlands (Nederlandse Gebarentaal), British Sign Language, and Swedish Sign Language; data include narratives, dialogues, small lexicons, and poetry. In addition, parts of a corpus of German Sign Language (Deutsche Geb\u00e4rdensprache) is included that was already published on paper before."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-570"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "ECHO corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/615e9b72-1118-577a-8658-d89d1197fa19.json b/oaitestdata/clarin-oai_dc/SET_1/json/615e9b72-1118-577a-8658-d89d1197fa19.json
deleted file mode 100644
index 356a9dfd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/615e9b72-1118-577a-8658-d89d1197fa19.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain",
-        "(1 file : ca. 72.7 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2044",
-    "MetadataAccess": [
-        "oai:ota:oucs:2044"
-    ],
-    "PublicationTimestamp": "1916-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1916"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Service, Robert W. (Robert William), 1874-1958"
-    ],
-    "fulltext": "oai:ota:oucs:2044;2018-03-02T09:53:42Z;http://ota.ox.ac.uk/headers/2044.xml;The spell of the Yukon and other verses / by Robert W. Service;Service, Robert W. (Robert William), 1874-1958;1916;text_and_corpus_linguistics;Poems -- Canada -- 20th century;Musical works -- Canada -- 20th century;Songs -- Canada -- 20th century;Ballads -- Canada -- 20th century;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 72.7 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "615e9b72-1118-577a-8658-d89d1197fa19",
-    "oai_identifier": [
-        "oai:ota:oucs:2044"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- Canada -- th century"
-        },
-        {
-            "name": "Musical works -- Canada -- th century"
-        },
-        {
-            "name": "Songs -- Canada -- th century"
-        },
-        {
-            "name": "Ballads -- Canada -- th century"
-        }
-    ],
-    "title": [
-        "The spell of the Yukon and other verses / by Robert W. Service"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2044.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6171b0ce-f89e-5525-a34b-c9dbeaefcc04.json b/oaitestdata/clarin-oai_dc/SET_1/json/6171b0ce-f89e-5525-a34b-c9dbeaefcc04.json
deleted file mode 100644
index 03dbfcdd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6171b0ce-f89e-5525-a34b-c9dbeaefcc04.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3143",
-    "MetadataAccess": [
-        "oai:ota:oucs:3143"
-    ],
-    "PublicationTimestamp": "1879-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1879"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "James, Henry, 1843-1916"
-    ],
-    "fulltext": "oai:ota:oucs:3143;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3143.xml;Confidence;Confidence;James, Henry, 1843-1916;not after: 1879;text_and_corpus_linguistics;American literature -- 19th century;eng;Oxford Text Archive, University of Oxford;Triggs, Jeffery;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6171b0ce-f89e-5525-a34b-c9dbeaefcc04",
-    "oai_identifier": [
-        "oai:ota:oucs:3143"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "American literature -- th century"
-        }
-    ],
-    "title": [
-        "Confidence",
-        "Confidence"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3143.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/617c4279-bc58-5491-9b7b-0786aac6d488.json b/oaitestdata/clarin-oai_dc/SET_1/json/617c4279-bc58-5491-9b7b-0786aac6d488.json
deleted file mode 100644
index 728c56ef..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/617c4279-bc58-5491-9b7b-0786aac6d488.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Department of Information Technology, Gauhati University, Assam, India"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Assamese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/611",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/611"
-    ],
-    "PID": "http://hdl.handle.net/11321/611",
-    "PublicationTimestamp": "2019-01-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Department of Information Technology, Gauhati University, Assam, India"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "author": [
-        "Sarma, Prof. Shikhar Kr."
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/611;2019-01-08T11:45:27Z;hdl_11321_3;hdl_11321_610;Assamese POS tagged Text;Sarma, Prof. Shikhar Kr.;Assamese NLP;Assamese POS Tagged text;Assamese Part of Speech tagged text;Assamese CRF++;Gauhati University;Assamese POS tagger is a CRF++ based POS Tagger. Raw text is given to this CRF++ based POS tagger to get POS tagged data. Standard POS tagset is used.\r\n\r\n---\r\n\r\n1. These Assamese NLP resources including the Tools and Applications are developed\r\nduring Research and Development Projects as well as Masters and Ph.D. thesis\r\nworks.\r\n2. These are mainly developed or generated at Gauhati University Department of\r\nComputer Science and Department of Information Technology.\r\n3. These resources are used by students and researchers for further studies, researches, as\r\nwell as for design and development of tools and applications.\r\n4. Computational Linguistics in Assamese is not rich, and Natural Language Processing\r\nworks have mainly started during last two decades, and most of the resources are first\r\ngeneration resources, and with ample scope for upgrading, enriching, and purifying.\r\n5. These are very good and essential resources for all the researchers in Assamese NLP, as\r\nthe language requires more and more NLP works to make Assamese a rich media for\r\nthe digital world.\r\n6. Anyone interested, or in need of such resources may express their interest for the\r\nrequired resources, and the way of availability will be advised/informed accordingly.\r\n7. These are purely research materials and could only be used for further research only.\r\n8. Researchers may visit the NLP Lab of Department of Information Technology, Gauhati\r\nUniversity, Guwahati, India or contact us.\r\n9. Researchers interested in collaborative works, and also students for project works, are\r\nwelcome.\r\n10. Contact person is Professor Shikhar Kr. Sarma, Department of Information\r\nTechnology, Gauhati University, Guwahati 781014, Assam, India. Email-\r\nsks@gauhati.ac.in;2019-01-07;corpus;http://hdl.handle.net/11321/611;asm;downloadable_files_count: 0;Department of Information Technology, Gauhati University, Assam, India",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "617c4279-bc58-5491-9b7b-0786aac6d488",
-    "notes": [
-        "Assamese POS tagger is a CRF++ based POS Tagger. Raw text is given to this CRF++ based POS tagger to get POS tagged data. Standard POS tagset is used.\r\n\r\n---\r\n\r\n1. These Assamese NLP resources including the Tools and Applications are developed\r\nduring Research and Development Projects as well as Masters and Ph.D. thesis\r\nworks.\r\n2. These are mainly developed or generated at Gauhati University Department of\r\nComputer Science and Department of Information Technology.\r\n3. These resources are used by students and researchers for further studies, researches, as\r\nwell as for design and development of tools and applications.\r\n4. Computational Linguistics in Assamese is not rich, and Natural Language Processing\r\nworks have mainly started during last two decades, and most of the resources are first\r\ngeneration resources, and with ample scope for upgrading, enriching, and purifying.\r\n5. These are very good and essential resources for all the researchers in Assamese NLP, as\r\nthe language requires more and more NLP works to make Assamese a rich media for\r\nthe digital world.\r\n6. Anyone interested, or in need of such resources may express their interest for the\r\nrequired resources, and the way of availability will be advised/informed accordingly.\r\n7. These are purely research materials and could only be used for further research only.\r\n8. Researchers may visit the NLP Lab of Department of Information Technology, Gauhati\r\nUniversity, Guwahati, India or contact us.\r\n9. Researchers interested in collaborative works, and also students for project works, are\r\nwelcome.\r\n10. Contact person is Professor Shikhar Kr. Sarma, Department of Information\r\nTechnology, Gauhati University, Guwahati 781014, Assam, India. Email-\r\nsks@gauhati.ac.in"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/611"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_610"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Assamese NLP"
-        },
-        {
-            "name": "Assamese POS Tagged text"
-        },
-        {
-            "name": "Assamese Part Speech tagged text"
-        },
-        {
-            "name": "Assamese CRF"
-        },
-        {
-            "name": "Gauhati University"
-        }
-    ],
-    "title": [
-        "Assamese POS tagged Text"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6193e454-4342-5e04-835e-4e53646af485.json b/oaitestdata/clarin-oai_dc/SET_1/json/6193e454-4342-5e04-835e-4e53646af485.json
deleted file mode 100644
index 6ecece7f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6193e454-4342-5e04-835e-4e53646af485.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=8e5276d46c8d11e2a2aa782bcb0741355e845d0213b14562b425dfa95218eb7b",
-    "MetadataAccess": [
-        "8e5276d46c8d11e2a2aa782bcb0741355e845d0213b14562b425dfa95218eb7b"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "8e5276d46c8d11e2a2aa782bcb0741355e845d0213b14562b425dfa95218eb7b;2018-11-15T16:40:11Z;toolService;toolService:service;U-Compare Segmentation Service ;Web service created by exporting UIMA-based workflow from the U-Compare text mining system.\nFunctionality: Identifies clauses/segments in plain text. Also identifies sentences, tokens, POS tags and lemmas. \nTools in workflow: Cafetiere Sentence Splitter (University of Manchester), TTL Tokenizer (RACAI, Romania), UAIC-\u00c2\u00adPOSTagger (UAIC, Romania) , UAIC-ClauseSplitter (UAIC, Romania)\nNOTE: The licence provided covers the web service only. Tools used to create the workflow may have their own licences\n;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6193e454-4342-5e04-835e-4e53646af485",
-    "notes": [
-        "Web service created by exporting UIMA-based workflow from the U-Compare text mining system.\nFunctionality: Identifies clauses/segments in plain text. Also identifies sentences, tokens, POS tags and lemmas. \nTools in workflow: Cafetiere Sentence Splitter (University of Manchester), TTL Tokenizer (RACAI, Romania), UAIC-\u00c2\u00adPOSTagger (UAIC, Romania) , UAIC-ClauseSplitter (UAIC, Romania)\nNOTE: The licence provided covers the web service only. Tools used to create the workflow may have their own licences\n"
-    ],
-    "oai_identifier": [
-        "8e5276d46c8d11e2a2aa782bcb0741355e845d0213b14562b425dfa95218eb7b"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:service"
-    ],
-    "state": "active",
-    "title": [
-        "U-Compare Segmentation Service "
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/61a7f48b-fbc3-5438-b126-bff6e91fa644.json b/oaitestdata/clarin-oai_dc/SET_1/json/61a7f48b-fbc3-5438-b126-bff6e91fa644.json
deleted file mode 100644
index 4138ba1b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/61a7f48b-fbc3-5438-b126-bff6e91fa644.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Macedonian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-718",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-718"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-718",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Code of conduct"
-    ],
-    "SpatialCoverage": [
-        "French Polynesia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-718;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Marquesan corpus;Documentation of the Marquesan language and culture project (DoBeS project);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-718;mkd;Code of conduct;downloadable_files_count: 0;French Polynesia;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI80685%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "61a7f48b-fbc3-5438-b126-bff6e91fa644",
-    "notes": [
-        "Documentation of the Marquesan language and culture project (DoBeS project)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-718"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Marquesan corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/61aeedd5-739d-5488-b34b-b229ea2a318a.json b/oaitestdata/clarin-oai_dc/SET_1/json/61aeedd5-739d-5488-b34b-b229ea2a318a.json
deleted file mode 100644
index cb73e47b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/61aeedd5-739d-5488-b34b-b229ea2a318a.json
+++ /dev/null
@@ -1,116 +0,0 @@
-{
-    "Contact": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 4",
-        "application/zip"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1210",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1210"
-    ],
-    "PID": "http://hdl.handle.net/11356/1210",
-    "PublicationTimestamp": "2019-01-26T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "RelatedIdentifier": [
-        "https://aclanthology.info/papers/W17-1406/w17-1406",
-        "http://hdl.handle.net/11356/1181"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Krek, Simon",
-        "\u0160krjanec, Iza",
-        "Zupan, Katja",
-        "Arhar Holdt, \u0160pela",
-        "Dobrovoljc, Kaja",
-        "Zajc, Anja",
-        "Erjavec, Toma\u017e",
-        "Kuzman, Taja",
-        "Gantar, Polona",
-        "Ledinek, Nina",
-        "\u010cibej, Jaka",
-        "Jezer\u0161ek, Lucija",
-        "Kav\u010di\u010d, Teja",
-        "Marko, Dafne",
-        "Holz, Nanika",
-        "Mo\u017ee, Sara"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1210;2019-02-11T22:32:59Z;hdl_11356_1023;hdl_11356_1024;Training corpus ssj500k 2.2;Krek, Simon;Dobrovoljc, Kaja;Erjavec, Toma\u017e;Mo\u017ee, Sara;Ledinek, Nina;Holz, Nanika;Zupan, Katja;Gantar, Polona;Kuzman, Taja;\u010cibej, Jaka;Arhar Holdt, \u0160pela;Kav\u010di\u010d, Teja;\u0160krjanec, Iza;Marko, Dafne;Jezer\u0161ek, Lucija;Zajc, Anja;tagging;dependency treebank;parsing;named entities;tokenisation;manual annotation;TEI;verbal multiword expressions;semantic role labelling;CONLL-U;The ssj500k training corpus contains about 500,000 tokens manually annotated on the levels of tokenisation, sentence segmentation, morphosyntactic tagging, and lemmatisation. About half of the corpus is also manually annotated with syntactic dependencies, named entities, and verbal multiword expressions. About a quarter of the corpus is annotated with semantic role labels. The morphosyntactic tags and syntactic dependencies are included both in the JOS/MULTEXT-East framework, as well as in the framework of Universal Dependencies.\r\n\r\nThe annotations of the ssj500k corpus follow (1) the MULTEXT-East V6 morphosyntactic specifications for Slovene, http://nl.ijs.si/ME/V6/msd/, (2) the JOS dependency schema, http://nl.ijs.si/jos/bib/jos-skladnja-navodila.pdf, the Universal Dependencies morphosyntactic specifications and syntactic dependencies for Slovene-SSJ, https://universaldependencies.org/, (4) the Janes annotation guidelines for Slovenian named entities, http://nl.ijs.si/janes/wp-content/uploads/2017/09/SlovenianNER-eng-v1.1.pdf, and (5) the Guidelines of the PARSEME shared task on verbal multiword expressions, http://parsemefr.lif.univ-mrs.fr/parseme-st-guidelines/1.1/\r\nThe vocabulary of (1) and (2) is provided in the back element and (3), (4), and (5) in the teiHeader of the TEI encoded corpus. The semantic role labels are also documented in the teiHeader.\r\n\r\nIn contrast to the previous version 2.1, this version corrects various errata in spacing and text metadata and adds UD morphological and (where it was possible to do so automatically) dependency annotations to the corpus. Note that the UD annotations are not included in the vertical file.;2019-01-26;corpus;http://hdl.handle.net/11356/1210;slv;https://aclanthology.info/papers/W17-1406/w17-1406;http://hdl.handle.net/11356/1181;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);https://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;text/plain; charset=utf-8;application/zip;application/zip;application/zip;application/zip;downloadable_files_count: 4;Centre for Language Resources and Technologies, University of Ljubljana;http://eng.slovenscina.eu/tehnologije/ucni-korpus",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "61aeedd5-739d-5488-b34b-b229ea2a318a",
-    "notes": [
-        "The ssj500k training corpus contains about 500,000 tokens manually annotated on the levels of tokenisation, sentence segmentation, morphosyntactic tagging, and lemmatisation. About half of the corpus is also manually annotated with syntactic dependencies, named entities, and verbal multiword expressions. About a quarter of the corpus is annotated with semantic role labels. The morphosyntactic tags and syntactic dependencies are included both in the JOS/MULTEXT-East framework, as well as in the framework of Universal Dependencies.\r\n\r\nThe annotations of the ssj500k corpus follow (1) the MULTEXT-East V6 morphosyntactic specifications for Slovene, http://nl.ijs.si/ME/V6/msd/, (2) the JOS dependency schema, http://nl.ijs.si/jos/bib/jos-skladnja-navodila.pdf, the Universal Dependencies morphosyntactic specifications and syntactic dependencies for Slovene-SSJ, https://universaldependencies.org/, (4) the Janes annotation guidelines for Slovenian named entities, http://nl.ijs.si/janes/wp-content/uploads/2017/09/SlovenianNER-eng-v1.1.pdf, and (5) the Guidelines of the PARSEME shared task on verbal multiword expressions, http://parsemefr.lif.univ-mrs.fr/parseme-st-guidelines/1.1/\r\nThe vocabulary of (1) and (2) is provided in the back element and (3), (4), and (5) in the teiHeader of the TEI encoded corpus. The semantic role labels are also documented in the teiHeader.\r\n\r\nIn contrast to the previous version 2.1, this version corrects various errata in spacing and text metadata and adds UD morphological and (where it was possible to do so automatically) dependency annotations to the corpus. Note that the UD annotations are not included in the vertical file."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1210"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "dependency treebank"
-        },
-        {
-            "name": "parsing"
-        },
-        {
-            "name": "named entities"
-        },
-        {
-            "name": "tokenisation"
-        },
-        {
-            "name": "manual annotation"
-        },
-        {
-            "name": "TEI"
-        },
-        {
-            "name": "verbal multiword expressions"
-        },
-        {
-            "name": "semantic role labelling"
-        },
-        {
-            "name": "CONLL-U"
-        }
-    ],
-    "title": [
-        "Training corpus ssj500k 2.2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/61cf7d55-1370-5df4-82b2-abb925f53178.json b/oaitestdata/clarin-oai_dc/SET_1/json/61cf7d55-1370-5df4-82b2-abb925f53178.json
deleted file mode 100644
index 71b0f5d5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/61cf7d55-1370-5df4-82b2-abb925f53178.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Department of Informatics, Human Language Technology Group, University of Szeged"
-    ],
-    "Contributor": [
-        "Vincze, Veronika"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/xml"
-    ],
-    "Language": [
-        "Hungarian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-347",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-347"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-347",
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "Department of Informatics, Human Language Technology Group, University of Szeged"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Hungary"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-347;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Szeged Corpus 2.0;Vincze, Veronika;monolingual corpus;annotated corpus;POS annotation;written, monolingual, general, manually POS annotated reference corpus; 1,459,288 tokens; MSD tagset, XML (TEI P4) files;2003;corpus;http://hdl.handle.net/11372/LRT-347;hun;application/xml;downloadable_files_count: 0;Hungary;Department of Informatics, Human Language Technology Group, University of Szeged;http://www.inf.u-szeged.hu/projectdirs/hlt/index_en.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "61cf7d55-1370-5df4-82b2-abb925f53178",
-    "notes": [
-        "written, monolingual, general, manually POS annotated reference corpus; 1,459,288 tokens; MSD tagset, XML (TEI P4) files"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-347"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "monolingual corpus"
-        },
-        {
-            "name": "annotated corpus"
-        },
-        {
-            "name": "POS annotation"
-        }
-    ],
-    "title": [
-        "Szeged Corpus 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/61ec6bb4-ee19-53f6-9251-141d8c927b93.json b/oaitestdata/clarin-oai_dc/SET_1/json/61ec6bb4-ee19-53f6-9251-141d8c927b93.json
deleted file mode 100644
index 8be6d5d9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/61ec6bb4-ee19-53f6-9251-141d8c927b93.json
+++ /dev/null
@@ -1,49 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5153",
-    "MetadataAccess": [
-        "oai:ota:oucs:5153"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:5153;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5153.xml;A collection of poems in six volumes. By several hands: [pt.2];text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "61ec6bb4-ee19-53f6-9251-141d8c927b93",
-    "oai_identifier": [
-        "oai:ota:oucs:5153"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A collection of poems in six volumes. By several hands: [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5153.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/61f04352-f5ab-5bd8-8b32-db4ec135af40.json b/oaitestdata/clarin-oai_dc/SET_1/json/61f04352-f5ab-5bd8-8b32-db4ec135af40.json
deleted file mode 100644
index b7ea38a7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/61f04352-f5ab-5bd8-8b32-db4ec135af40.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=ee76a76428cd11e2a2aa782bcb074135cfab4788a1ee4b41ae86d9989280aa90",
-    "MetadataAccess": [
-        "ee76a76428cd11e2a2aa782bcb074135cfab4788a1ee4b41ae86d9989280aa90"
-    ],
-    "PublicationTimestamp": "2012-11-07T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "fulltext": "ee76a76428cd11e2a2aa782bcb074135cfab4788a1ee4b41ae86d9989280aa90;2018-11-15T16:39:45Z;toolService;toolService:tool;MSTParser;MSTParser is a non-projective dependency parser (see McDonald et al., 2005a, 2006) that searches for maximum spanning trees over directed graphs. Models of dependency structure are based on large-margin discriminative training methods (see McDonald et al., 2005b). Projective parsing is also supported (see McDonald et al., 2005a).\nFor more details about this tool, see please http://www.seas.upenn.edu/~strctlrn/MSTParser/MSTParser.html. \n;2012-11-07",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "61f04352-f5ab-5bd8-8b32-db4ec135af40",
-    "notes": [
-        "MSTParser is a non-projective dependency parser (see McDonald et al., 2005a, 2006) that searches for maximum spanning trees over directed graphs. Models of dependency structure are based on large-margin discriminative training methods (see McDonald et al., 2005b). Projective parsing is also supported (see McDonald et al., 2005a).\nFor more details about this tool, see please http://www.seas.upenn.edu/~strctlrn/MSTParser/MSTParser.html. \n"
-    ],
-    "oai_identifier": [
-        "ee76a76428cd11e2a2aa782bcb074135cfab4788a1ee4b41ae86d9989280aa90"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "MSTParser"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/61f20eaf-7ea9-50d0-9911-203f9f0149bb.json b/oaitestdata/clarin-oai_dc/SET_1/json/61f20eaf-7ea9-50d0-9911-203f9f0149bb.json
deleted file mode 100644
index 973690d6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/61f20eaf-7ea9-50d0-9911-203f9f0149bb.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "University of West Bohemia"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-FE82-7",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-FE82-7"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0022-FE82-7",
-    "PublicationTimestamp": "2013-07-17T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "University of West Bohemia"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0)",
-        "http://creativecommons.org/licenses/by-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Pt\u00e1\u010dek, Tom\u00e1\u0161",
-        "Habernal, Ivan",
-        "Steinberger, Josef"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-FE82-7;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Facebook Data for Sentiment Analysis;Habernal, Ivan;Pt\u00e1\u010dek, Tom\u00e1\u0161;Steinberger, Josef;sentiment analysis;opinion mining;Corpus consisting of 10,000 Facebook posts manually annotated on sentiment (2,587 positive, 5,174 neutral, 1,991 negative and 248 bipolar posts). The archive contains data and statistics in an Excel file (FBData.xlsx) and gold data in two text files with posts (gold-posts.txt) and labels (gols-labels.txt) on corresponding lines.;2013-07-17;corpus;http://hdl.handle.net/11858/00-097C-0000-0022-FE82-7;ces;Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0);http://creativecommons.org/licenses/by-sa/3.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;University of West Bohemia;http://liks.fav.zcu.cz/sentiment/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "61f20eaf-7ea9-50d0-9911-203f9f0149bb",
-    "notes": [
-        "Corpus consisting of 10,000 Facebook posts manually annotated on sentiment (2,587 positive, 5,174 neutral, 1,991 negative and 248 bipolar posts). The archive contains data and statistics in an Excel file (FBData.xlsx) and gold data in two text files with posts (gold-posts.txt) and labels (gols-labels.txt) on corresponding lines."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-FE82-7"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "sentiment analysis"
-        },
-        {
-            "name": "opinion mining"
-        }
-    ],
-    "title": [
-        "Facebook Data for Sentiment Analysis"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/620a261d-0adb-5819-9e25-2ca7a6055fee.json b/oaitestdata/clarin-oai_dc/SET_1/json/620a261d-0adb-5819-9e25-2ca7a6055fee.json
deleted file mode 100644
index 2efb6b14..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/620a261d-0adb-5819-9e25-2ca7a6055fee.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 373 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "Old French (842-ca. 1400)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0175",
-    "MetadataAccess": [
-        "oai:ota:oucs:0175"
-    ],
-    "PublicationTimestamp": "1180-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1180"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:0175;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0175.xml;Aliscans;[Aliscans];1180-1190;text_and_corpus_linguistics;Romances -- France -- 12th century;Gesta -- France -- 12th century;Poems -- France -- 12th century;Musical works -- France -- 12th century;Songs -- France -- 12th century;fro;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 373 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "620a261d-0adb-5819-9e25-2ca7a6055fee",
-    "oai_identifier": [
-        "oai:ota:oucs:0175"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Romances -- France -- th century"
-        },
-        {
-            "name": "Gesta -- France -- th century"
-        },
-        {
-            "name": "Poems -- France -- th century"
-        },
-        {
-            "name": "Musical works -- France -- th century"
-        },
-        {
-            "name": "Songs -- France -- th century"
-        }
-    ],
-    "title": [
-        "Aliscans",
-        "[Aliscans]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0175.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/620a575c-1453-5aab-b854-f0240880bc99.json b/oaitestdata/clarin-oai_dc/SET_1/json/620a575c-1453-5aab-b854-f0240880bc99.json
deleted file mode 100644
index 91628345..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/620a575c-1453-5aab-b854-f0240880bc99.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Budapest University of Technology and Economics Media Research (BME MOKK)",
-        "Academy of Sciences"
-    ],
-    "Contributor": [
-        "Halacsy, Peter"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English",
-        "Hungarian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-349",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-349"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-349",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Budapest University of Technology and Economics Media Research (BME MOKK)",
-        "Academy of Sciences"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CC"
-    ],
-    "SpatialCoverage": [
-        "Hungary"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-349;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Hunglish Corpus;Halacsy, Peter;parallel corpus;Billingual written general; 2 million sentences;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-349;eng;hun;CC;downloadable_files_count: 0;Hungary;Academy of Sciences;Budapest University of Technology and Economics Media Research (BME MOKK);http://mokk.bme.hu/resources/hunglishcorpus",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "620a575c-1453-5aab-b854-f0240880bc99",
-    "notes": [
-        "Billingual written general; 2 million sentences"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-349"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parallel corpus"
-        }
-    ],
-    "title": [
-        "Hunglish Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/620d5cab-c226-5410-ab26-fcfda859969d.json b/oaitestdata/clarin-oai_dc/SET_1/json/620d5cab-c226-5410-ab26-fcfda859969d.json
deleted file mode 100644
index 8aad35be..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/620d5cab-c226-5410-ab26-fcfda859969d.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3304",
-    "MetadataAccess": [
-        "oai:ota:oucs:3304"
-    ],
-    "PublicationTimestamp": "1888-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1888"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Kipling, Rudyard, 1865-1936"
-    ],
-    "fulltext": "oai:ota:oucs:3304;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3304.xml;Tales of the Trade;Kipling, Rudyard, 1865-1936;not after: 1888;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "620d5cab-c226-5410-ab26-fcfda859969d",
-    "oai_identifier": [
-        "oai:ota:oucs:3304"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Tales of the Trade"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3304.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/62253575-bccf-5828-a39b-892931757c1b.json b/oaitestdata/clarin-oai_dc/SET_1/json/62253575-bccf-5828-a39b-892931757c1b.json
deleted file mode 100644
index e5effcf2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/62253575-bccf-5828-a39b-892931757c1b.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "text/plain"
-    ],
-    "Language": [
-        "Slovak"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-AADC-5",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-AADC-5"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0006-AADC-5",
-    "PublicationTimestamp": "2012-05-15T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/231720"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Galu\u0161\u010d\u00e1kov\u00e1, Petra",
-        "Bojar, Ond\u0159ej"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-AADC-5;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Manually Classified Errors in En->Sk Translation;Galu\u0161\u010d\u00e1kov\u00e1, Petra;Bojar, Ond\u0159ej;machine translation;errors classification;EN-SK translation;Manual classification of errors of English-Slovak translation according to the classification introduced by Vilar et al. [1]. 50 sentences randomly selected from WMT 2011 test set [2] were translated by 3 MT systems described in [3] and MT errors were manually marked and classified. Reference translation is included.\r\n\r\nReferences:\r\n[1] David Vilar, Jia Xu, Luis Fernando D\u2019Haro and Hermann Ney. Error Analysis of Machine Translation Output. In International Conference on Language Resources and Evaluation, pages 697-702. Genoa, Italy, May 2006.\r\n[2] http://www.statmt.org/wmt11/evaluation-task.html\r\n[3] Petra Galu\u0161\u010d\u00e1kov\u00e1 and Ond\u0159ej Bojar. Improving SMT by Using Parallel Data of a Closely Related Language. In Human Language Technologies - The Baltic Perspective - Proceedings of the Fifth International Conference Baltic HLT 2012, volume 247 of Frontiers in AI and Applications, pages 58-65, Amsterdam, Netherlands, October 2012. IOS Press.;2012-05-15;lexicalConceptualResource;http://hdl.handle.net/11858/00-097C-0000-0006-AADC-5;slk;info:eu-repo/grantAgreement/EC/FP7/231720;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;text/plain;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "62253575-bccf-5828-a39b-892931757c1b",
-    "notes": [
-        "Manual classification of errors of English-Slovak translation according to the classification introduced by Vilar et al. [1]. 50 sentences randomly selected from WMT 2011 test set [2] were translated by 3 MT systems described in [3] and MT errors were manually marked and classified. Reference translation is included.\r\n\r\nReferences:\r\n[1] David Vilar, Jia Xu, Luis Fernando D\u2019Haro and Hermann Ney. Error Analysis of Machine Translation Output. In International Conference on Language Resources and Evaluation, pages 697-702. Genoa, Italy, May 2006.\r\n[2] http://www.statmt.org/wmt11/evaluation-task.html\r\n[3] Petra Galu\u0161\u010d\u00e1kov\u00e1 and Ond\u0159ej Bojar. Improving SMT by Using Parallel Data of a Closely Related Language. In Human Language Technologies - The Baltic Perspective - Proceedings of the Fifth International Conference Baltic HLT 2012, volume 247 of Frontiers in AI and Applications, pages 58-65, Amsterdam, Netherlands, October 2012. IOS Press."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-AADC-5"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "errors classification"
-        },
-        {
-            "name": "EN-SK translation"
-        }
-    ],
-    "title": [
-        "Manually Classified Errors in En->Sk Translation"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/622ffe94-ded9-5f84-b7b7-027c4171150f.json b/oaitestdata/clarin-oai_dc/SET_1/json/622ffe94-ded9-5f84-b7b7-027c4171150f.json
deleted file mode 100644
index 821d0fd2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/622ffe94-ded9-5f84-b7b7-027c4171150f.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/14",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/14"
-    ],
-    "PID": "http://hdl.handle.net/10794/14",
-    "PublicationTimestamp": "2015-12-09T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/14;2017-10-27T15:57:35Z;hdl_10794_1;hdl_10794_2;Bliss words (2017-10-16);Bliss-ord (2017-10-16);n/a, n/a;Swedish;Bliss;Bliss words.;Bliss-ord.;2015-12-09;lexicalConceptualResource;http://hdl.handle.net/10794/14;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/blissword",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "622ffe94-ded9-5f84-b7b7-027c4171150f",
-    "notes": [
-        "Bliss words.",
-        "Bliss-ord."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/14"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Bliss"
-        }
-    ],
-    "title": [
-        "Bliss words (2017-10-16)",
-        "Bliss-ord (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6231a488-3adb-5b0c-93fc-ac45aae72b59.json b/oaitestdata/clarin-oai_dc/SET_1/json/6231a488-3adb-5b0c-93fc-ac45aae72b59.json
deleted file mode 100644
index f8d53646..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6231a488-3adb-5b0c-93fc-ac45aae72b59.json
+++ /dev/null
@@ -1,90 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Czech",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1713",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1713"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1713",
-    "PublicationTimestamp": "2016-06-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Strakov\u00e1, Jana",
-        "Haji\u010d, Jan, jr.",
-        "Cinkov\u00e1, Silvie",
-        "Haji\u010d, Jakub",
-        "Janou\u0161kov\u00e1, Jolana",
-        "Haji\u010d, Jan",
-        "Straka, Milan",
-        "Ure\u0161ov\u00e1, Miroslava"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1713;2018-07-02T22:05:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;WordSim353-cs: Evaluation Dataset for Lexical Similarity and Relatedness, based on WordSim353;Cinkov\u00e1, Silvie;Strakov\u00e1, Jana;Haji\u010d, Jakub;Haji\u010d, Jan;Haji\u010d, Jan, jr.;Janou\u0161kov\u00e1, Jolana;Straka, Milan;Ure\u0161ov\u00e1, Miroslava;lexical semantics;similarity;relatedness;evaluation;distributional semantics;Czech translation of WordSim353. The Czech translation of English WordSim353 word pairs were obtained from four translators. All translation variants were scored according to the lexical similarity/relatedness annotation instructions for WordSim353 annotators, by 25 Czech annotators. The resulting data set consists of two annotation files: \"WordSim353-cs.csv\" and \"WordSim-cs-Multi.csv\". Both files are encoded in UTF-8, have a header, text is enclosed in double quotes, and columns are separated by commas. The rows are numbered. The WordSim-cs-Multi data set has rows numbered from 1 to 634, whereas the row indices in the WordSim353-cs data set reflect the corresponding row numbers in the WordSim-cs-Multi data set.\r\n\r\nThe WordSim353-cs file contains a one-to-one mapping selection of 353 Czech equivalent pairs whose judgments have proven to be most similar to the judgments of their corresponding English originals (compared by the absolute value of the difference between the means over all annotators in each language counterpart). In one case (\"psychology-cognition\"), two Czech equivalent pairs had identical means as well as confidence intervals, so we randomly selected one. \r\n\r\nThe \"WordSim-cs-Multi.csv\" file contains human judgments for all translation variants. \r\n\r\nIn both data sets, we preserved all 25 individual scores. In the WordSim353-cs data set, we added a column with their Czech means as well as a column containing the original English means and 95% confidence intervals in separate columns for each mean (computed by the CI function in the Rmisc R package). The WordSim-cs-Multi data set contains only the Czech means and confidence intervals. For the most convenient lexical search, we provided separate columns with the respective Czech and English single words, entire word pairs, and eventually an English-Czech quadruple in both data sets.\r\n\r\nThe data set also contains an xls table with the four translations and a preliminary selection of the best variants performed by an adjudicator.;2016-06-01;lexicalConceptualResource;http://hdl.handle.net/11234/1-1713;ces;eng;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/wordsim353-cs",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6231a488-3adb-5b0c-93fc-ac45aae72b59",
-    "notes": [
-        "Czech translation of WordSim353. The Czech translation of English WordSim353 word pairs were obtained from four translators. All translation variants were scored according to the lexical similarity/relatedness annotation instructions for WordSim353 annotators, by 25 Czech annotators. The resulting data set consists of two annotation files: \"WordSim353-cs.csv\" and \"WordSim-cs-Multi.csv\". Both files are encoded in UTF-8, have a header, text is enclosed in double quotes, and columns are separated by commas. The rows are numbered. The WordSim-cs-Multi data set has rows numbered from 1 to 634, whereas the row indices in the WordSim353-cs data set reflect the corresponding row numbers in the WordSim-cs-Multi data set.\r\n\r\nThe WordSim353-cs file contains a one-to-one mapping selection of 353 Czech equivalent pairs whose judgments have proven to be most similar to the judgments of their corresponding English originals (compared by the absolute value of the difference between the means over all annotators in each language counterpart). In one case (\"psychology-cognition\"), two Czech equivalent pairs had identical means as well as confidence intervals, so we randomly selected one. \r\n\r\nThe \"WordSim-cs-Multi.csv\" file contains human judgments for all translation variants. \r\n\r\nIn both data sets, we preserved all 25 individual scores. In the WordSim353-cs data set, we added a column with their Czech means as well as a column containing the original English means and 95% confidence intervals in separate columns for each mean (computed by the CI function in the Rmisc R package). The WordSim-cs-Multi data set contains only the Czech means and confidence intervals. For the most convenient lexical search, we provided separate columns with the respective Czech and English single words, entire word pairs, and eventually an English-Czech quadruple in both data sets.\r\n\r\nThe data set also contains an xls table with the four translations and a preliminary selection of the best variants performed by an adjudicator."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1713"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "lexical semantics"
-        },
-        {
-            "name": "similarity"
-        },
-        {
-            "name": "relatedness"
-        },
-        {
-            "name": "evaluation"
-        },
-        {
-            "name": "distributional semantics"
-        }
-    ],
-    "title": [
-        "WordSim353-cs: Evaluation Dataset for Lexical Similarity and Relatedness, based on WordSim353"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6233b7ee-b214-5a01-b242-04b74d18fe5a.json b/oaitestdata/clarin-oai_dc/SET_1/json/6233b7ee-b214-5a01-b242-04b74d18fe5a.json
deleted file mode 100644
index 143af093..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6233b7ee-b214-5a01-b242-04b74d18fe5a.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/601",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/601"
-    ],
-    "PID": "http://hdl.handle.net/11321/601",
-    "PublicationTimestamp": "2018-09-18T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "plWordNet",
-        "http://clarin-pl.eu/en/licenses/plwordnet-2/",
-        "PUB",
-        "various"
-    ],
-    "author": [
-        "Koz\u0142owska, Zuzanna"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/601;2018-09-18T02:27:04Z;hdl_11321_3;hdl_11321_4;POE;Koz\u0142owska, Zuzanna;poetry;Polish poetry;poezja;poezja polska;XX wiek;20th century;Microcorpus of 20th century Polish poetry;2018-09-18;corpus;http://hdl.handle.net/11321/601;pol;plWordNet;http://clarin-pl.eu/en/licenses/plwordnet-2/;PUB;various;application/octet-stream;downloadable_files_count: 1",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6233b7ee-b214-5a01-b242-04b74d18fe5a",
-    "notes": [
-        "Microcorpus of 20th century Polish poetry"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/601"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "poetry"
-        },
-        {
-            "name": "Polish poetry"
-        },
-        {
-            "name": "poezja"
-        },
-        {
-            "name": "poezja polska"
-        },
-        {
-            "name": "XX wiek"
-        },
-        {
-            "name": "th century"
-        }
-    ],
-    "title": [
-        "POE"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6234dc76-46f4-5d9c-b60a-833b52953e1f.json b/oaitestdata/clarin-oai_dc/SET_1/json/6234dc76-46f4-5d9c-b60a-833b52953e1f.json
deleted file mode 100644
index 95c1c756..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6234dc76-46f4-5d9c-b60a-833b52953e1f.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(2 files : ca. 78.1, 77.2 KB)"
-    ],
-    "Language": [
-        "Middle English (1100-1500)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1684",
-    "MetadataAccess": [
-        "oai:ota:oucs:1684"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:1684;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1684.xml;Owl and the nightingale (Middle English poem);The owl and the nightingale;default: 1976-01-01;text_and_corpus_linguistics;Poems -- England -- 13th century;enm;Oxford Text Archive, University of Oxford;text/sgml;(2 files : ca. 78.1, 77.2 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6234dc76-46f4-5d9c-b60a-833b52953e1f",
-    "oai_identifier": [
-        "oai:ota:oucs:1684"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- England -- th century"
-        }
-    ],
-    "title": [
-        "Owl and the nightingale (Middle English poem)",
-        "The owl and the nightingale"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1684.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/62356bfa-a26c-5b80-9fef-e77d9c121e02.json b/oaitestdata/clarin-oai_dc/SET_1/json/62356bfa-a26c-5b80-9fef-e77d9c121e02.json
deleted file mode 100644
index d6a2be97..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/62356bfa-a26c-5b80-9fef-e77d9c121e02.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contributor": [
-        "Dietrich Klakow",
-        "Grzegorz Chrupa\u0142a"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:seminer",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:seminer"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0005-BD15-E",
-    "PublicationTimestamp": "2010-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "RelatedIdentifier": [
-        "Chrupa\u0142a, G. and Klakow, D. (2010). A Named Entity Labeler for German: exploiting Wikipedia and distributional clusters. In LREC 2010."
-    ],
-    "ResourceType": [
-        "Software"
-    ],
-    "author": [
-        "Grzegorz Chrupa\u0142a\nFR 7.4 Spoken Language Systems\nSaarland University\nSaarbr\u00fccken, Germany"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:seminer;2014-06-03T12:57:06Z;SemiNER;Grzegorz Chrupa\u0142a\nFR 7.4 Spoken Language Systems\nSaarland University\nSaarbr\u00fccken, Germany;NER;named entity recognizer;annotation tool;SemiNER is a semi-supervised Named Entity Recognizer (with pre-trained models for German).;SemiNER ist ein semi-supervised Named Entity Erkenner (trainiert f\u00fcr die Deutsche Sprache).;Grzegorz Chrupa\u0142a;Dietrich Klakow;2010;Software;clarind-uds:seminer;hdl:11858/00-246C-0000-0005-BD15-E;sequor;http://code.google.com/p/sequor/;deu;Chrupa\u0142a, G. and Klakow, D. (2010). A Named Entity Labeler for German: exploiting Wikipedia and distributional clusters. In LREC 2010.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "62356bfa-a26c-5b80-9fef-e77d9c121e02",
-    "notes": [
-        "SemiNER is a semi-supervised Named Entity Recognizer (with pre-trained models for German).",
-        "SemiNER ist ein semi-supervised Named Entity Erkenner (trainiert f\u00fcr die Deutsche Sprache)."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:seminer"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "NER"
-        },
-        {
-            "name": "named entity recognizer"
-        },
-        {
-            "name": "annotation tool"
-        }
-    ],
-    "title": [
-        "SemiNER"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/624c6415-f5d2-52b6-88fd-89723bba304a.json b/oaitestdata/clarin-oai_dc/SET_1/json/624c6415-f5d2-52b6-88fd-89723bba304a.json
deleted file mode 100644
index d5903ac1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/624c6415-f5d2-52b6-88fd-89723bba304a.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Hindi",
-        "Tamil"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1044",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1044"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1044",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1044;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;L1 Acquisition Bhuvana Narasimhan;Language Acquisition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1044;hin;tam;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI9158%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "624c6415-f5d2-52b6-88fd-89723bba304a",
-    "notes": [
-        "Language Acquisition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1044"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "L1 Acquisition Bhuvana Narasimhan"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/625b0561-c6fb-57b7-b254-b84e733bdabb.json b/oaitestdata/clarin-oai_dc/SET_1/json/625b0561-c6fb-57b7-b254-b84e733bdabb.json
deleted file mode 100644
index 5c97b2d4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/625b0561-c6fb-57b7-b254-b84e733bdabb.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4534",
-    "MetadataAccess": [
-        "oai:ota:oucs:4534"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Griffith, Mrs. (Elizabeth), 1720?-1793."
-    ],
-    "fulltext": "oai:ota:oucs:4534;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4534.xml;The history of Lady Barton: a novel, in letters, by Mrs. Griffith. In three volumes. ... [pt.1];Griffith, Mrs. (Elizabeth), 1720?-1793.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "625b0561-c6fb-57b7-b254-b84e733bdabb",
-    "oai_identifier": [
-        "oai:ota:oucs:4534"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The history of Lady Barton: a novel, in letters, by Mrs. Griffith. In three volumes. ... [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4534.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/625ed2dc-7e91-51a7-8d99-d379fdd806b6.json b/oaitestdata/clarin-oai_dc/SET_1/json/625ed2dc-7e91-51a7-8d99-d379fdd806b6.json
deleted file mode 100644
index 4c90f154..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/625ed2dc-7e91-51a7-8d99-d379fdd806b6.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/10",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/10"
-    ],
-    "PID": "http://hdl.handle.net/10794/10",
-    "PublicationTimestamp": "2015-12-09T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/10;2017-10-27T16:09:20Z;hdl_10794_1;hdl_10794_2;Bliss (2017-10-16);Bliss (2017-10-16);n/a, n/a;Swedish;Bliss;Bliss.;Bliss.;2015-12-09;lexicalConceptualResource;http://hdl.handle.net/10794/10;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;http://creativecommons.org/licenses/by/4.0/;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/bliss",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "625ed2dc-7e91-51a7-8d99-d379fdd806b6",
-    "notes": [
-        "Bliss.",
-        "Bliss."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/10"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Bliss"
-        }
-    ],
-    "title": [
-        "Bliss (2017-10-16)",
-        "Bliss (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/62620f10-b63c-5369-b6b0-733804d4ebd7.json b/oaitestdata/clarin-oai_dc/SET_1/json/62620f10-b63c-5369-b6b0-733804d4ebd7.json
deleted file mode 100644
index 00e111ca..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/62620f10-b63c-5369-b6b0-733804d4ebd7.json
+++ /dev/null
@@ -1,97 +0,0 @@
-{
-    "Contact": [
-        "Universit\u00e4t Bamberg, World Language Documentation Centre"
-    ],
-    "Contributor": [
-        "Meijssen, Gerard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Afrikaans",
-        "Arabic",
-        "Basque",
-        "Bulgarian",
-        "Catalan",
-        "Chinese",
-        "Czech",
-        "Danish",
-        "Dutch",
-        "English",
-        "Esperanto",
-        "Estonian",
-        "Finnish",
-        "French",
-        "Galician",
-        "Georgian",
-        "Modern Greek (1453-)",
-        "Hebrew",
-        "Hungarian",
-        "Icelandic",
-        "Indonesian",
-        "Interlingua (International Auxiliary Language Association)",
-        "Irish",
-        "Italian",
-        "Japanese",
-        "Central Khmer",
-        "Norwegian",
-        "Polish",
-        "Portuguese",
-        "Romanian",
-        "Russian",
-        "Serbian",
-        "Slovak",
-        "Spanish",
-        "Swedish",
-        "Turkish",
-        "Ukrainian",
-        "Welsh"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-853",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-853"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-853",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Universit\u00e4t Bamberg, World Language Documentation Centre"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "GFDL or CC",
-        "http://www.omegawiki.org/Licensing"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-853;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;OmegaWiki;Meijssen, Gerard;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-853;afr;ara;eus;bul;cat;zho;ces;dan;nld;eng;epo;est;fin;fra;glg;kat;ell;heb;hun;isl;ind;ina;gle;ita;jpn;khm;nor;pol;por;ron;rus;srp;slk;spa;swe;tur;ukr;cym;GFDL or CC;http://www.omegawiki.org/Licensing;application/octet-stream;downloadable_files_count: 0;Universit\u00e4t Bamberg, World Language Documentation Centre;http://www.omegawiki.org",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "62620f10-b63c-5369-b6b0-733804d4ebd7",
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-853"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "OmegaWiki"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6294f2ce-2f0a-5315-a2c2-81ce12a04554.json b/oaitestdata/clarin-oai_dc/SET_1/json/6294f2ce-2f0a-5315-a2c2-81ce12a04554.json
deleted file mode 100644
index 82057f8d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6294f2ce-2f0a-5315-a2c2-81ce12a04554.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "University of Lisbon, CLUL-Centro de Lingu\u00edstica da Universidade de Lisboa"
-    ],
-    "Contributor": [
-        "Mendes, Am\u00e1lia"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Portuguese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-384",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-384"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-384",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Lisbon, CLUL-Centro de Lingu\u00edstica da Universidade de Lisboa"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Portugal"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-384;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;C-ORAL-ROM-Portuguese - Integrated reference corpora for spoken romance languages;Mendes, Am\u00e1lia;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-384;por;downloadable_files_count: 0;Portugal;University of Lisbon, CLUL-Centro de Lingu\u00edstica da Universidade de Lisboa;http://www.elda.org/catalogue/en/speech/S0172.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6294f2ce-2f0a-5315-a2c2-81ce12a04554",
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-384"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "C-ORAL-ROM-Portuguese - Integrated reference corpora for spoken romance languages"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/62b20ef2-34c7-5998-8fde-f234c5adefb7.json b/oaitestdata/clarin-oai_dc/SET_1/json/62b20ef2-34c7-5998-8fde-f234c5adefb7.json
deleted file mode 100644
index f199950f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/62b20ef2-34c7-5998-8fde-f234c5adefb7.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Serbian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1206",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1206"
-    ],
-    "PID": "http://hdl.handle.net/11356/1206",
-    "PublicationTimestamp": "2018-12-10T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Ljube\u0161i\u0107, Nikola"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1206;2018-12-10T12:49:08Z;hdl_11356_1023;hdl_11356_1024;Word embeddings CLARIN.SI-embed.sr 1.0;Ljube\u0161i\u0107, Nikola;word embeddings;lemmatisation;tagging;CLARIN.SI-embed.sr contains word embeddings induced from the srWaC web corpus. The embeddings are based on the skip-gram model of fastText trained on 554,606,544 tokens of running text for (1) 881,150 lowercased surface forms (e.g., \"srbije\") and (2) 599,416 lowercased lemmas with added part-of-speech information (e.g., \"srbija#Np\").;2018-12-10;lexicalConceptualResource;http://hdl.handle.net/11356/1206;srp;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Jo\u017eef Stefan Institute",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "62b20ef2-34c7-5998-8fde-f234c5adefb7",
-    "notes": [
-        "CLARIN.SI-embed.sr contains word embeddings induced from the srWaC web corpus. The embeddings are based on the skip-gram model of fastText trained on 554,606,544 tokens of running text for (1) 881,150 lowercased surface forms (e.g., \"srbije\") and (2) 599,416 lowercased lemmas with added part-of-speech information (e.g., \"srbija#Np\")."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1206"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "word embeddings"
-        },
-        {
-            "name": "lemmatisation"
-        },
-        {
-            "name": "tagging"
-        }
-    ],
-    "title": [
-        "Word embeddings CLARIN.SI-embed.sr 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/62b261ed-25ca-53a9-9ca7-d76e1a4bb1ab.json b/oaitestdata/clarin-oai_dc/SET_1/json/62b261ed-25ca-53a9-9ca7-d76e1a4bb1ab.json
deleted file mode 100644
index 473df014..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/62b261ed-25ca-53a9-9ca7-d76e1a4bb1ab.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Paw\u0142a J\u00f3zefa Golczewskiego"
-    ],
-    "Contributor": [
-        "Filipowicz, Jan J\u00f3zef (?-ca 1770). [Il.]"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-180798",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-180798"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CF1-5",
-    "PublicationTimestamp": "1745-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1745"
-    ],
-    "Publisher": [
-        "Drukarnia Paw\u0142a J\u00f3zefa Golczewskiego"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/180798",
-        "oai:jbc.bj.uj.edu.pl:publication:191657"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1701/1800"
-    ],
-    "TempCoverageBegin": 53662478399,
-    "TempCoverageEnd": 53662478399,
-    "TemporalCoverage": " point in time : 1701-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1701-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1701-07-01T11:59:59Z",
-    "author": [
-        "Chmielowski, Benedykt (1700-1763)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-180798;2019-03-01T11:01:48Z;Nowe Ateny Albo Akademia Wszelkiey Scyencyi Pe\u0142na : Na Rozne Tytu\u0142y, iak na Classes Podzielona, M\u0105drym dla Memorya\u0142u, Idiotom dla Nauki, Politykom dla praktyki, Melancholikom dla rozrywki Erigowana : Alias O Bogu [...] O Zwierzu [...] O J\u0119zykach [...]. T.1;Chmielowski, Benedykt (1700-1763);starodruki 18\u00a0w.;Drukarnia Paw\u0142a J\u00f3zefa Golczewskiego;Filipowicz, Jan J\u00f3zef (?-ca 1770). [Il.];1745;starodruk;application/xml;clarind-uds:poldilemma-180798;hdl:11858/00-246C-0000-0023-8CF1-5;Biblioteka Jagiello\u0144ska, BJ St. Dr. 5232 I;pol;lat;http://jbc.bj.uj.edu.pl/Content/180798;oai:jbc.bj.uj.edu.pl:publication:191657;1701/1800;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "62b261ed-25ca-53a9-9ca7-d76e1a4bb1ab",
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-180798"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Nowe Ateny Albo Akademia Wszelkiey Scyencyi Pe\u0142na : Na Rozne Tytu\u0142y, iak na Classes Podzielona, M\u0105drym dla Memorya\u0142u, Idiotom dla Nauki, Politykom dla praktyki, Melancholikom dla rozrywki Erigowana : Alias O Bogu [...] O Zwierzu [...] O J\u0119zykach [...]. T.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/63047219-1a2a-5193-88d1-b9c42b1b3152.json b/oaitestdata/clarin-oai_dc/SET_1/json/63047219-1a2a-5193-88d1-b9c42b1b3152.json
deleted file mode 100644
index 3b3f1046..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/63047219-1a2a-5193-88d1-b9c42b1b3152.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3773",
-    "MetadataAccess": [
-        "oai:ota:oucs:3773"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Mason, William, 1719-1791."
-    ],
-    "fulltext": "oai:ota:oucs:3773;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3773.xml;Remarks and observations on the morality and divinity contained in Dr. Free's certain articles: proposed to the Court of Assistants, of the Worshipful Company of Salters. In a letter to the Reverend Dr. Free.;Mason, William, 1719-1791.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "63047219-1a2a-5193-88d1-b9c42b1b3152",
-    "oai_identifier": [
-        "oai:ota:oucs:3773"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Remarks and observations on the morality and divinity contained in Dr. Free's certain articles: proposed to the Court of Assistants, of the Worshipful Company of Salters. In a letter to the Reverend Dr. Free."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3773.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6311dd73-286d-54c5-ad58-6996122c1b3a.json b/oaitestdata/clarin-oai_dc/SET_1/json/6311dd73-286d-54c5-ad58-6996122c1b3a.json
deleted file mode 100644
index d969ad40..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6311dd73-286d-54c5-ad58-6996122c1b3a.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 115 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0624",
-    "MetadataAccess": [
-        "oai:ota:oucs:0624"
-    ],
-    "PublicationTimestamp": "1613-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1613"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Chapman, George, 1559?-1634"
-    ],
-    "fulltext": "oai:ota:oucs:0624;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0624.xml;The revenge of Bussy d'Ambois;Chapman, George, 1559?-1634;1613;text_and_corpus_linguistics;Plays -- England -- 17th century;Tragedies -- England -- 17th century;eng;Oxford Text Archive, University of Oxford;(1 file : ca. 115 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6311dd73-286d-54c5-ad58-6996122c1b3a",
-    "oai_identifier": [
-        "oai:ota:oucs:0624"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        },
-        {
-            "name": "Tragedies -- England -- th century"
-        }
-    ],
-    "title": [
-        "The revenge of Bussy d'Ambois"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0624.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/631d9b90-c2ca-5d62-bea3-faa74a2ae13b.json b/oaitestdata/clarin-oai_dc/SET_1/json/631d9b90-c2ca-5d62-bea3-faa74a2ae13b.json
deleted file mode 100644
index 21060e6e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/631d9b90-c2ca-5d62-bea3-faa74a2ae13b.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "Contributor": [
-        "Przepi\u00f3rkowski, Adam"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-382",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-382"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-382",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Freely available in binary form. Corpus search engine on GPL - see Poliqarp."
-    ],
-    "SpatialCoverage": [
-        "Poland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-382;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;The IPI PAN Corpus;Przepi\u00f3rkowski, Adam;monolingual corpus;morphosyntactic annotation;syntactic annotation;written, general, monolingual, synchronic; 250 million; XML (XCES), morphosyntactic, structural, metada;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-382;pol;Freely available in binary form. Corpus search engine on GPL - see Poliqarp.;downloadable_files_count: 0;Poland;Institute of Computer Science, Polish Academy of Sciences;http://korpus.pl/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "631d9b90-c2ca-5d62-bea3-faa74a2ae13b",
-    "notes": [
-        "written, general, monolingual, synchronic; 250 million; XML (XCES), morphosyntactic, structural, metada"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-382"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "monolingual corpus"
-        },
-        {
-            "name": "morphosyntactic annotation"
-        },
-        {
-            "name": "syntactic annotation"
-        }
-    ],
-    "title": [
-        "The IPI PAN Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6323f4c2-c874-5f63-ae57-d088c0696bf6.json b/oaitestdata/clarin-oai_dc/SET_1/json/6323f4c2-c874-5f63-ae57-d088c0696bf6.json
deleted file mode 100644
index 0623ef63..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6323f4c2-c874-5f63-ae57-d088c0696bf6.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology",
-        "University of Lodz"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/pdf"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/545",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/545"
-    ],
-    "PID": "http://hdl.handle.net/11321/545",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology",
-        "University of Lodz"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "P\u0119zik, Piotr"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/545;2018-07-23T11:52:39Z;hdl_11321_3;hdl_11321_4;PELCRA PARL corpus;P\u0119zik, Piotr;spoken data;parliamentary data;recordings;transcriptions;formal register;The corpus comprises 50 sampled recordings (12 hours) and manual transcriptions (ca. 101 00 word tokens) of parliamentary data.;2018;corpus;http://hdl.handle.net/11321/545;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;application/pdf;downloadable_files_count: 1;University of Lodz;Wroc\u0142aw University of Technology;http://spokes.clarin-pl.eu/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6323f4c2-c874-5f63-ae57-d088c0696bf6",
-    "notes": [
-        "The corpus comprises 50 sampled recordings (12 hours) and manual transcriptions (ca. 101 00 word tokens) of parliamentary data."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/545"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "spoken data"
-        },
-        {
-            "name": "parliamentary data"
-        },
-        {
-            "name": "recordings"
-        },
-        {
-            "name": "transcriptions"
-        },
-        {
-            "name": "formal register"
-        }
-    ],
-    "title": [
-        "PELCRA PARL corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6337792e-7a22-5153-9978-1bd61e2a9bca.json b/oaitestdata/clarin-oai_dc/SET_1/json/6337792e-7a22-5153-9978-1bd61e2a9bca.json
deleted file mode 100644
index 68e8d3ab..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6337792e-7a22-5153-9978-1bd61e2a9bca.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "less than 512 KB"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0238",
-    "MetadataAccess": [
-        "oai:ota:oucs:0238"
-    ],
-    "PublicationYear": [
-        "300 BCE"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Academic dissertations"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Aristoxenus"
-    ],
-    "fulltext": "oai:ota:oucs:0238;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0238.xml; Elementa harmonica  / compiled by Malcolm Brown;Aristoxenus;300 BCE;text_and_corpus_linguistics;Academic dissertations;grc;Oxford Text Archive, University of Oxford;less than 512 KB;Text;Academic dissertations;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6337792e-7a22-5153-9978-1bd61e2a9bca",
-    "oai_identifier": [
-        "oai:ota:oucs:0238"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Academic dissertations"
-        }
-    ],
-    "title": [
-        " Elementa harmonica  / compiled by Malcolm Brown"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0238.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6371cea7-d10f-506d-9e5a-fc1d8d44fa4e.json b/oaitestdata/clarin-oai_dc/SET_1/json/6371cea7-d10f-506d-9e5a-fc1d8d44fa4e.json
deleted file mode 100644
index 92091d30..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6371cea7-d10f-506d-9e5a-fc1d8d44fa4e.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3710",
-    "MetadataAccess": [
-        "oai:ota:oucs:3710"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Paine, Thomas, 1737-1809."
-    ],
-    "fulltext": "oai:ota:oucs:3710;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3710.xml;A discourse delivered by Thomas Paine, at the Society of the Theophilanthropists, at Paris, 1798;Atheism refuted;Paine, Thomas, 1737-1809.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6371cea7-d10f-506d-9e5a-fc1d8d44fa4e",
-    "oai_identifier": [
-        "oai:ota:oucs:3710"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A discourse delivered by Thomas Paine, at the Society of the Theophilanthropists, at Paris, 1798",
-        "Atheism refuted"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3710.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/637fb5d6-6a40-5e81-968e-6ac368982a9d.json b/oaitestdata/clarin-oai_dc/SET_1/json/637fb5d6-6a40-5e81-968e-6ac368982a9d.json
deleted file mode 100644
index 606383ae..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/637fb5d6-6a40-5e81-968e-6ac368982a9d.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contributor": [
-        "Meili\u016bnait\u0117, Violeta"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Lithuanian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-186",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-186"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-186",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-186;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;The Dialect Archive;Meili\u016bnait\u0117, Violeta;The audio collection and the written texts. Now it contains approximately 2000 hours of digitalised and more than 2000 not digitalised audio recordings; 400,000 cards with information on dialectal words, morphology, syntax, etc.; transcripts and notes.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-186;lit;downloadable_files_count: 0;http://tarmes.mch.mii.lt",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "637fb5d6-6a40-5e81-968e-6ac368982a9d",
-    "notes": [
-        "The audio collection and the written texts. Now it contains approximately 2000 hours of digitalised and more than 2000 not digitalised audio recordings; 400,000 cards with information on dialectal words, morphology, syntax, etc.; transcripts and notes."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-186"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "The Dialect Archive"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/63a0d65e-cd41-5cec-9e9e-09f209dba610.json b/oaitestdata/clarin-oai_dc/SET_1/json/63a0d65e-cd41-5cec-9e9e-09f209dba610.json
deleted file mode 100644
index 81affecb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/63a0d65e-cd41-5cec-9e9e-09f209dba610.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5277",
-    "MetadataAccess": [
-        "oai:ota:oucs:5277"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Belloste, Augustin, 1654-1730."
-    ],
-    "fulltext": "oai:ota:oucs:5277;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5277.xml;The hospital-surgeon: or, a new, gentle, and easie way, to cure speedily all sorts of wounds, and other diseases belonging to surgery. ... In three parts. ... By Mr. Belloste, ...;Chirurgien d'hopital. English;Belloste, Augustin, 1654-1730.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "63a0d65e-cd41-5cec-9e9e-09f209dba610",
-    "oai_identifier": [
-        "oai:ota:oucs:5277"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The hospital-surgeon: or, a new, gentle, and easie way, to cure speedily all sorts of wounds, and other diseases belonging to surgery. ... In three parts. ... By Mr. Belloste, ...",
-        "Chirurgien d'hopital. English"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5277.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/63ac79b3-d111-5f98-9d05-7a51d7a861ab.json b/oaitestdata/clarin-oai_dc/SET_1/json/63ac79b3-d111-5f98-9d05-7a51d7a861ab.json
deleted file mode 100644
index f982d8c0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/63ac79b3-d111-5f98-9d05-7a51d7a861ab.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Ule, Louis"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 135 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1618",
-    "MetadataAccess": [
-        "oai:ota:oucs:1618"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Marlowe, Christopher, 1564-1593"
-    ],
-    "fulltext": "oai:ota:oucs:1618;2018-02-16T10:42:06Z;http://ota.ox.ac.uk/headers/1618.xml;Edward the Second : the troublesome reign and lamentable death of Edward the Second, King of England, with the tragical fall of proud Mortimer / Christopher Marlowe;Marlowe, Christopher, 1564-1593;text_and_corpus_linguistics;English drama -- Early modern and Elizabethan, 1500-1600;Oxford Text Archive, University of Oxford;Ule, Louis;text/sgml;(1 file : ca. 135 KB);Text;Plays;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "63ac79b3-d111-5f98-9d05-7a51d7a861ab",
-    "oai_identifier": [
-        "oai:ota:oucs:1618"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- Early modern Elizabethan"
-        }
-    ],
-    "title": [
-        "Edward the Second : the troublesome reign and lamentable death of Edward the Second, King of England, with the tragical fall of proud Mortimer / Christopher Marlowe"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1618.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/63c9fbf8-2042-5b24-b9e9-966f33f90bcf.json b/oaitestdata/clarin-oai_dc/SET_1/json/63c9fbf8-2042-5b24-b9e9-966f33f90bcf.json
deleted file mode 100644
index 6f6e96bd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/63c9fbf8-2042-5b24-b9e9-966f33f90bcf.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Fakult\u00e4t Geisteswissenschaften, Universit\u00e4t Duisburg-Essen",
-        "Korpora.org"
-    ],
-    "Contributor": [
-        "Fisseni, Bernhard",
-        "Wegera, Prof. Dr. Klaus-Peter",
-        "Schmitz, Dr. Hans-Christian",
-        "Schr\u00f6der, Prof. Dr. Bernhard",
-        "Solms, Prof. Dr. Hans-Joachim"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1121",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1121"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1121",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Fakult\u00e4t Geisteswissenschaften, Universit\u00e4t Duisburg-Essen",
-        "Korpora.org"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1121;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Bonner Fr\u00fchneuhochdeutschkorpus (FnhdC);Schr\u00f6der, Prof. Dr. Bernhard;Wegera, Prof. Dr. Klaus-Peter;Solms, Prof. Dr. Hans-Joachim;Schmitz, Dr. Hans-Christian;Fisseni, Bernhard;Germanistik;Digital, morphologically annotated (N, V, A) part of the Bonn Corpus of Early New High German; used to create the Grammatik des Fr\u00fchneuhochdeutschen (III. Nouns; IV. Verbs; VI. Adjectives); morphologisch annotiert; Materialgrundlage f\u00fcr die Erarbeitung der B\u00e4nde 3, 4 und 6 der \"Grammatik des Fr\u00fchneuhochdeutschen\";2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1121;deu;downloadable_files_count: 0;Germany;Korpora.org;Fakult\u00e4t Geisteswissenschaften, Universit\u00e4t Duisburg-Essen;http://www.korpora.org/Fnhd",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "63c9fbf8-2042-5b24-b9e9-966f33f90bcf",
-    "notes": [
-        "Digital, morphologically annotated (N, V, A) part of the Bonn Corpus of Early New High German; used to create the Grammatik des Fr\u00fchneuhochdeutschen (III. Nouns; IV. Verbs; VI. Adjectives); morphologisch annotiert; Materialgrundlage f\u00fcr die Erarbeitung der B\u00e4nde 3, 4 und 6 der \"Grammatik des Fr\u00fchneuhochdeutschen\""
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1121"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Bonner Fr\u00fchneuhochdeutschkorpus (FnhdC)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/63e84fa9-4fa7-5064-8bf8-fe51a0848fbb.json b/oaitestdata/clarin-oai_dc/SET_1/json/63e84fa9-4fa7-5064-8bf8-fe51a0848fbb.json
deleted file mode 100644
index 60b91f85..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/63e84fa9-4fa7-5064-8bf8-fe51a0848fbb.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Royster, Paul"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 1.18 MB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1587",
-    "MetadataAccess": [
-        "oai:ota:oucs:1587"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "James, Henry, 1843-1916"
-    ],
-    "fulltext": "oai:ota:oucs:1587;2018-02-16T10:42:06Z;http://ota.ox.ac.uk/headers/1587.xml;American writers : [Henry James] / Henry James;James, Henry, 1843-1916;text_and_corpus_linguistics;American literature -- 19th century;Oxford Text Archive, University of Oxford;Royster, Paul;text/sgml;(1 file : ca. 1.18 MB);Text;Novels;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "63e84fa9-4fa7-5064-8bf8-fe51a0848fbb",
-    "oai_identifier": [
-        "oai:ota:oucs:1587"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "American literature -- th century"
-        }
-    ],
-    "title": [
-        "American writers : [Henry James] / Henry James"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1587.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/640ee901-f851-57e6-b2e1-bf3118df504c.json b/oaitestdata/clarin-oai_dc/SET_1/json/640ee901-f851-57e6-b2e1-bf3118df504c.json
deleted file mode 100644
index e90e95ba..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/640ee901-f851-57e6-b2e1-bf3118df504c.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1040",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1040"
-    ],
-    "PID": "http://hdl.handle.net/11356/1040",
-    "PublicationTimestamp": "2013-09-30T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Krek, Simon",
-        "Zwitter Vitez, Ana",
-        "Erjavec, Toma\u017e",
-        "Stabej, Marko",
-        "Zemljari\u010d Miklav\u010di\u010d, Jana"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1040;2017-09-29T13:48:00Z;hdl_11356_1023;hdl_11356_1024;Spoken corpus Gos 1.0;Zwitter Vitez, Ana;Zemljari\u010d Miklav\u010di\u010d, Jana;Krek, Simon;Stabej, Marko;Erjavec, Toma\u017e;speech transcription;spoken corpus;TEI;GOS is a corpus of spoken Slovene that includes the transcripts of approximately 120 hours of speech recorded in various situations: radio and TV shows, school lessons and lectures, private conversations between friends or within the family, work meetings, consultations, conversations in buying and selling situations, etc. All speech is transcribed in two versions \u2013 with pronunciation-based spelling and with standardized spelling \u2013 and it comprises over one million words. The corpus can be searched by means of the web concordancer where it is also possible to listen to the corresponding recordings: http://www.korpus-gos.net.;2013-09-30;corpus;http://hdl.handle.net/11356/1040;slv;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);https://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 2;Centre for Language Resources and Technologies, University of Ljubljana;http://eng.slovenscina.eu/korpusi/gos",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "640ee901-f851-57e6-b2e1-bf3118df504c",
-    "notes": [
-        "GOS is a corpus of spoken Slovene that includes the transcripts of approximately 120 hours of speech recorded in various situations: radio and TV shows, school lessons and lectures, private conversations between friends or within the family, work meetings, consultations, conversations in buying and selling situations, etc. All speech is transcribed in two versions \u2013 with pronunciation-based spelling and with standardized spelling \u2013 and it comprises over one million words. The corpus can be searched by means of the web concordancer where it is also possible to listen to the corresponding recordings: http://www.korpus-gos.net."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1040"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech transcription"
-        },
-        {
-            "name": "spoken corpus"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "Spoken corpus Gos 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6428086f-bf36-5e06-bab2-4b7dc887e1fe.json b/oaitestdata/clarin-oai_dc/SET_1/json/6428086f-bf36-5e06-bab2-4b7dc887e1fe.json
deleted file mode 100644
index af136f44..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6428086f-bf36-5e06-bab2-4b7dc887e1fe.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "Modern Greek (1453-)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-946",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-946"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-946",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-946;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Homeric Greek;ca. 80.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-946;ell;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#hom",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6428086f-bf36-5e06-bab2-4b7dc887e1fe",
-    "notes": [
-        "ca. 80.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-946"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Homeric Greek"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6436a12a-4751-59ab-b5a3-74a79eede19e.json b/oaitestdata/clarin-oai_dc/SET_1/json/6436a12a-4751-59ab-b5a3-74a79eede19e.json
deleted file mode 100644
index 8076e782..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6436a12a-4751-59ab-b5a3-74a79eede19e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3849",
-    "MetadataAccess": [
-        "oai:ota:oucs:3849"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Lloyd, Robert, 1733-1764."
-    ],
-    "fulltext": "oai:ota:oucs:3849;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3849.xml;Arcadia; or, the shepherd's wedding: A dramatic pastoral. As it is performed at the Theatre-Royal in Drury-Lane. The music composed by Mr. Stanley.;Lloyd, Robert, 1733-1764.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6436a12a-4751-59ab-b5a3-74a79eede19e",
-    "oai_identifier": [
-        "oai:ota:oucs:3849"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Arcadia; or, the shepherd's wedding: A dramatic pastoral. As it is performed at the Theatre-Royal in Drury-Lane. The music composed by Mr. Stanley."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3849.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/646d383f-73f5-5a90-8fab-6fe531aa2e6c.json b/oaitestdata/clarin-oai_dc/SET_1/json/646d383f-73f5-5a90-8fab-6fe531aa2e6c.json
deleted file mode 100644
index 04117663..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/646d383f-73f5-5a90-8fab-6fe531aa2e6c.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(7 files : total of ca. 1.6 MB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2093",
-    "MetadataAccess": [
-        "oai:ota:oucs:2093"
-    ],
-    "PublicationTimestamp": "1777-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1777"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Newpapers",
-        "Anthologies",
-        "Linguistic corpora"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:2093;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/2093.xml;New York newspaper advertisements and news items : 1777-1779;1777-1779;text_and_corpus_linguistics;News Papers -- United States -- 18th century;Linguistic analysis (Linguistics);Anthologies -- United States -- 20th century;eng;Oxford Text Archive, University of Oxford;Triggs, Jeffery;text/sgml;(7 files : total of ca. 1.6 MB);Text;Newpapers;Anthologies;Linguistic corpora;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "646d383f-73f5-5a90-8fab-6fe531aa2e6c",
-    "oai_identifier": [
-        "oai:ota:oucs:2093"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "News Papers -- United States -- th century"
-        },
-        {
-            "name": "Linguistic analysis Linguistics"
-        },
-        {
-            "name": "Anthologies -- United States -- th century"
-        }
-    ],
-    "title": [
-        "New York newspaper advertisements and news items : 1777-1779"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2093.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/648705e3-55dc-55fb-b50f-8da0604218f3.json b/oaitestdata/clarin-oai_dc/SET_1/json/648705e3-55dc-55fb-b50f-8da0604218f3.json
deleted file mode 100644
index aa0cc788..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/648705e3-55dc-55fb-b50f-8da0604218f3.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-281",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-281"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-281",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-281;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;OpenStreetMap Extended API;REST-style web service that can return relevant geographical information (including toponyms, which is probably the most relevant for CLARIN) given a specific area as input Especially useful in combination with http://wiki.openstreetmap.org/wiki/Osmosis to carve out certain areas based on pre-defined polygons (e.g. country boundaries).;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-281;downloadable_files_count: 0;http://wiki.openstreetmap.org/wiki/Osmxapi#Tag_Query",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "648705e3-55dc-55fb-b50f-8da0604218f3",
-    "notes": [
-        "REST-style web service that can return relevant geographical information (including toponyms, which is probably the most relevant for CLARIN) given a specific area as input Especially useful in combination with http://wiki.openstreetmap.org/wiki/Osmosis to carve out certain areas based on pre-defined polygons (e.g. country boundaries)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-281"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "OpenStreetMap Extended API"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/64b11c58-e51f-5cce-b264-f1c35378a922.json b/oaitestdata/clarin-oai_dc/SET_1/json/64b11c58-e51f-5cce-b264-f1c35378a922.json
deleted file mode 100644
index e943f104..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/64b11c58-e51f-5cce-b264-f1c35378a922.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Borin, Lars"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-422",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-422"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-422",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Sweden"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-422;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;SVANTE (SVenska ANdraspr\u00e5ksTExter);Borin, Lars;Interlanguage/Learner corpus (essays written by SL Swedish learners with many native languages); appr. 200 kW; POS tags; base forms of words (in TEI/XCES XML format);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-422;swe;downloadable_files_count: 0;Sweden;http://spraakbanken.gu.se/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "64b11c58-e51f-5cce-b264-f1c35378a922",
-    "notes": [
-        "Interlanguage/Learner corpus (essays written by SL Swedish learners with many native languages); appr. 200 kW; POS tags; base forms of words (in TEI/XCES XML format)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-422"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "SVANTE (SVenska ANdraspr\u00e5ksTExter)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/64c28d50-031d-595a-8946-de23585711ba.json b/oaitestdata/clarin-oai_dc/SET_1/json/64c28d50-031d-595a-8946-de23585711ba.json
deleted file mode 100644
index 44582fa0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/64c28d50-031d-595a-8946-de23585711ba.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "J.K.Mci. i Rzeczypospolitey"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-5973",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-5973"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D2C-C",
-    "PublicationTimestamp": "1781-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1781"
-    ],
-    "Publisher": [
-        "J.K.Mci. i Rzeczypospolitey"
-    ],
-    "RelatedIdentifier": [
-        "http://dlibra.bibliotekaelblaska.pl/Content/5973",
-        "oai:dlibra.bibliotekaelblaska.pl:publication:6370"
-    ],
-    "ResourceType": [
-        "starodruk",
-        "alter Druck"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-5973;2019-03-01T16:02:07Z;Dworskie nabozenstwo ktore kazdy nabozny oboiey p\u0142ci cz\u0142owiek kazdego czasu odprawowac mo\u017ce przez iednego \u2026;Dworskie nabozenstwo ktore kazdy nabozny oboiey p\u0142ci cz\u0142owiek kazdego czasu odprawowac mo\u017ce przez iednego \u2026;modlitewnik;Towarzystwo Jezusowe;Gebetbuch;Gesellschaft Jesu;Jezuici (pe\u0142na nazwa: Towarzystwo Jezusowe ) \u2013 m\u0119ski papieski zakon apostolski Ko\u015bcio\u0142a rzymskokatolickiego, zatwierdzony przez papie\u017ca Paw\u0142a III 27 wrze\u015bnia 1540 r. Towarzystwo Jezusowe zosta\u0142o za\u0142o\u017cone w g\u0142\u00f3wnej mierze do walki z reformacj\u0105, by broni\u0107 i rozszerza\u0107 wiar\u0119 oraz nauk\u0119 Ko\u015bcio\u0142a rzymskokatolickiego, przede wszystkim przez publiczne nauczanie, \u0107wiczenia duchowne, edukacj\u0119 i udzielanie sakrament\u00f3w. Od samego pocz\u0105tku podstawowymi zasadami jezuit\u00f3w, odr\u00f3\u017cniaj\u0105cymi go od innych zakon\u00f3w, by\u0142y: akcentowanie pos\u0142usze\u0144stwa wobec papie\u017ca i prze\u0142o\u017conych, sta\u0142e edukowanie w\u0142asnych cz\u0142onk\u00f3w - tak aby posiadali oni mo\u017cliwie jak najlepsze wykszta\u0142cenie, nie ograniczaj\u0105ce si\u0119 tylko do wykszta\u0142cenia czysto religijnego- aby byli zdolni dobrze rozumie\u0107 aktualnie panuj\u0105cego \"ducha wsp\u00f3\u0142czesno\u015bci\". Modlitewnik w j\u0119zyku polskim, wydany w drukarni J.K.Mci. i Rzeczypospolitey, w formacie 4\u00b0. Ka\u017cda modlitwa zamieszczona jest w tabelach na ka\u017cdej stronie ( ka\u017cda tabela podzielona na 15 rubryk). Starodruk nie posiada oprawy.;Jesuitenorden (die Gesellschaft Jesu) ist ein m\u00e4nnlicher Orden, der 1540 vom Papst Paul den III. anerkannt wurde. Seine Hauptvoraussetzungen waren Kampf mit der Reformation, Verteidigung und Verbreitung der katholischen Glaube durch Predigen, Exerzitien, Erziehung und Erteilung der Sakramente. Vom Anfang an waren der Gehorsam gegen\u00fcber dem Generaloberen und dem Papst und st\u00e4ndige (nicht nur religi\u00f6se) Selbstbildung zwecks des guten Verst\u00e4ndnisses des Gegenwartsgeistes Hauptprinzipien des Ordens. Das Gebetbuch im Polnischen, wurde in der k\u00f6niglichen Buchdruckerei, im 4\u00ba Format herausgegeben. Jedes Gebet wurde in einer Tabelle enthalten. Einband fehlt.;J.K.Mci. i Rzeczypospolitey;J.K.Mci. i Rzeczypospolitey;1781;1781;starodruk;alter Druck;application/xml;clarind-uds:poldilemma-5973;hdl:11858/00-246C-0000-0023-8D2C-C;XVIII. 140;XVIII. 140;pol;lat;http://dlibra.bibliotekaelblaska.pl/Content/5973;oai:dlibra.bibliotekaelblaska.pl:publication:6370;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "64c28d50-031d-595a-8946-de23585711ba",
-    "notes": [
-        "Jezuici (pe\u0142na nazwa: Towarzystwo Jezusowe ) \u2013 m\u0119ski papieski zakon apostolski Ko\u015bcio\u0142a rzymskokatolickiego, zatwierdzony przez papie\u017ca Paw\u0142a III 27 wrze\u015bnia 1540 r. Towarzystwo Jezusowe zosta\u0142o za\u0142o\u017cone w g\u0142\u00f3wnej mierze do walki z reformacj\u0105, by broni\u0107 i rozszerza\u0107 wiar\u0119 oraz nauk\u0119 Ko\u015bcio\u0142a rzymskokatolickiego, przede wszystkim przez publiczne nauczanie, \u0107wiczenia duchowne, edukacj\u0119 i udzielanie sakrament\u00f3w. Od samego pocz\u0105tku podstawowymi zasadami jezuit\u00f3w, odr\u00f3\u017cniaj\u0105cymi go od innych zakon\u00f3w, by\u0142y: akcentowanie pos\u0142usze\u0144stwa wobec papie\u017ca i prze\u0142o\u017conych, sta\u0142e edukowanie w\u0142asnych cz\u0142onk\u00f3w - tak aby posiadali oni mo\u017cliwie jak najlepsze wykszta\u0142cenie, nie ograniczaj\u0105ce si\u0119 tylko do wykszta\u0142cenia czysto religijnego- aby byli zdolni dobrze rozumie\u0107 aktualnie panuj\u0105cego \"ducha wsp\u00f3\u0142czesno\u015bci\". Modlitewnik w j\u0119zyku polskim, wydany w drukarni J.K.Mci. i Rzeczypospolitey, w formacie 4\u00b0. Ka\u017cda modlitwa zamieszczona jest w tabelach na ka\u017cdej stronie ( ka\u017cda tabela podzielona na 15 rubryk). Starodruk nie posiada oprawy.",
-        "Jesuitenorden (die Gesellschaft Jesu) ist ein m\u00e4nnlicher Orden, der 1540 vom Papst Paul den III. anerkannt wurde. Seine Hauptvoraussetzungen waren Kampf mit der Reformation, Verteidigung und Verbreitung der katholischen Glaube durch Predigen, Exerzitien, Erziehung und Erteilung der Sakramente. Vom Anfang an waren der Gehorsam gegen\u00fcber dem Generaloberen und dem Papst und st\u00e4ndige (nicht nur religi\u00f6se) Selbstbildung zwecks des guten Verst\u00e4ndnisses des Gegenwartsgeistes Hauptprinzipien des Ordens. Das Gebetbuch im Polnischen, wurde in der k\u00f6niglichen Buchdruckerei, im 4\u00ba Format herausgegeben. Jedes Gebet wurde in einer Tabelle enthalten. Einband fehlt."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-5973"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "modlitewnik"
-        },
-        {
-            "name": "Towarzystwo Jezusowe"
-        },
-        {
-            "name": "Gebetbuch"
-        },
-        {
-            "name": "Gesellschaft Jesu"
-        }
-    ],
-    "title": [
-        "Dworskie nabozenstwo ktore kazdy nabozny oboiey p\u0142ci cz\u0142owiek kazdego czasu odprawowac mo\u017ce przez iednego \u2026",
-        "Dworskie nabozenstwo ktore kazdy nabozny oboiey p\u0142ci cz\u0142owiek kazdego czasu odprawowac mo\u017ce przez iednego \u2026"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/65117ca3-6814-51f0-b23f-714e8062944d.json b/oaitestdata/clarin-oai_dc/SET_1/json/65117ca3-6814-51f0-b23f-714e8062944d.json
deleted file mode 100644
index b929847a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/65117ca3-6814-51f0-b23f-714e8062944d.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Institut f\u00fcr Deutsche Sprache"
-    ],
-    "Contributor": [
-        "Schmidt, Thomas",
-        "Sch\u00fctte, Wilfried"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1198",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1198"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1198",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut f\u00fcr Deutsche Sprache"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1198;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;FOLKER;Schmidt, Thomas;Sch\u00fctte, Wilfried;Audio transcription editor used for the construction of the FOLK corpus;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1198;downloadable_files_count: 0;Institut f\u00fcr Deutsche Sprache;http://agd.ids-mannheim.de/folker_en.shtml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "65117ca3-6814-51f0-b23f-714e8062944d",
-    "notes": [
-        "Audio transcription editor used for the construction of the FOLK corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1198"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "FOLKER"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/65321342-0b4e-5b14-89c1-2ecf965fffec.json b/oaitestdata/clarin-oai_dc/SET_1/json/65321342-0b4e-5b14-89c1-2ecf965fffec.json
deleted file mode 100644
index c85cfab0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/65321342-0b4e-5b14-89c1-2ecf965fffec.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 62.1 KB)"
-    ],
-    "Language": [
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0353",
-    "MetadataAccess": [
-        "oai:ota:oucs:0353"
-    ],
-    "PublicationYear": [
-        "254 BCE-184 BCE"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Plautus, Titus Maccius"
-    ],
-    "fulltext": "oai:ota:oucs:0353;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0353.xml;Amphitruo;Plautus, Titus Maccius;254 BCE-184 BCE;text_and_corpus_linguistics;Plays -- Italy -- B.C.;Comedies -- Italy -- B.C.;lat;Oxford Text Archive, University of Oxford;(1 file : ca. 62.1 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "65321342-0b4e-5b14-89c1-2ecf965fffec",
-    "oai_identifier": [
-        "oai:ota:oucs:0353"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- Italy -- B.C."
-        },
-        {
-            "name": "Comedies -- Italy -- B.C."
-        }
-    ],
-    "title": [
-        "Amphitruo"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0353.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/65344f84-ff26-5a2d-8b85-c8615e3b2ec6.json b/oaitestdata/clarin-oai_dc/SET_1/json/65344f84-ff26-5a2d-8b85-c8615e3b2ec6.json
deleted file mode 100644
index dce1291c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/65344f84-ff26-5a2d-8b85-c8615e3b2ec6.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3656",
-    "MetadataAccess": [
-        "oai:ota:oucs:3656"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pope, Alexander, 1688-1744."
-    ],
-    "fulltext": "oai:ota:oucs:3656;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3656.xml;Letters of Mr. Wycherley & Mr. Pope, from the year 1704 to 1710: [pt.2];Pope, Alexander, 1688-1744.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "65344f84-ff26-5a2d-8b85-c8615e3b2ec6",
-    "oai_identifier": [
-        "oai:ota:oucs:3656"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Letters of Mr. Wycherley & Mr. Pope, from the year 1704 to 1710: [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3656.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/65367ce0-95bc-5917-ad60-45bab12d6f5a.json b/oaitestdata/clarin-oai_dc/SET_1/json/65367ce0-95bc-5917-ad60-45bab12d6f5a.json
deleted file mode 100644
index 30fd7f1a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/65367ce0-95bc-5917-ad60-45bab12d6f5a.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Kucera, Karel"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3010",
-    "MetadataAccess": [
-        "oai:ota:oucs:3010"
-    ],
-    "PublicationTimestamp": "1923-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1923"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Ha\u00c5\u00a1ek, Jaroslav, 1883-1923"
-    ],
-    "fulltext": "oai:ota:oucs:3010;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3010.xml;Osudy dobr\u00c3\u00a9ho voj\u00c3\u00a1ka Svejka za svetov\u00c3\u00a9 v\u00c3\u00a1lky;The Good Soldier Schweik;Ha\u00c5\u00a1ek, Jaroslav, 1883-1923;not after: 1923;text_and_corpus_linguistics;Czech fiction -- 20th century;ces;Oxford Text Archive, University of Oxford;Kucera, Karel;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "65367ce0-95bc-5917-ad60-45bab12d6f5a",
-    "oai_identifier": [
-        "oai:ota:oucs:3010"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Czech fiction -- th century"
-        }
-    ],
-    "title": [
-        "Osudy dobr\u00c3\u00a9ho voj\u00c3\u00a1ka Svejka za svetov\u00c3\u00a9 v\u00c3\u00a1lky",
-        "The Good Soldier Schweik"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3010.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6550cce7-f890-595a-9f72-8a2cec573f75.json b/oaitestdata/clarin-oai_dc/SET_1/json/6550cce7-f890-595a-9f72-8a2cec573f75.json
deleted file mode 100644
index 961ebad8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6550cce7-f890-595a-9f72-8a2cec573f75.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1850",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1850"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1850",
-    "PublicationTimestamp": "2016-12-05T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Apache License 2.0",
-        "http://opensource.org/licenses/Apache-2.0",
-        "PUB"
-    ],
-    "author": [
-        "Haji\u010d, Jan Jr"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1850;2018-07-02T22:05:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;MUSCIMarker;Haji\u010d, Jan Jr;image annotation;Python;music notation;MUSCIMarker is an open-source tool for annotating visual objects and their relationships in binary images. It is implemented in Python, known to run on Windows, Linux and OS X, and supports working offline. MUSCIMarker is being used for creating a dataset of musical notation symbols, but can support any object set.\r\n\r\n\r\nThe user documentation online is currently (12.2016) incomplete, as it is continually changing to reflect annotators' comments and incorporate new features. This version of the software is *not* the final one, and it is under continuous development (we're currently working on adding grayscale image support with auto-binarization, and Android support for touch-based annotation). However, the current version (1.1) has already been used to annotate more than 100 pages of sheet music, over all the major desktop OSes, and I believe it is already in a state where it can be useful beyond my immediate music notation data gathering use case.;2016-12-05;toolService;http://hdl.handle.net/11234/1-1850;Apache License 2.0;http://opensource.org/licenses/Apache-2.0;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://muscimarker.readthedocs.io",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6550cce7-f890-595a-9f72-8a2cec573f75",
-    "notes": [
-        "MUSCIMarker is an open-source tool for annotating visual objects and their relationships in binary images. It is implemented in Python, known to run on Windows, Linux and OS X, and supports working offline. MUSCIMarker is being used for creating a dataset of musical notation symbols, but can support any object set.\r\n\r\n\r\nThe user documentation online is currently (12.2016) incomplete, as it is continually changing to reflect annotators' comments and incorporate new features. This version of the software is *not* the final one, and it is under continuous development (we're currently working on adding grayscale image support with auto-binarization, and Android support for touch-based annotation). However, the current version (1.1) has already been used to annotate more than 100 pages of sheet music, over all the major desktop OSes, and I believe it is already in a state where it can be useful beyond my immediate music notation data gathering use case."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1850"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "image annotation"
-        },
-        {
-            "name": "Python"
-        },
-        {
-            "name": "music notation"
-        }
-    ],
-    "title": [
-        "MUSCIMarker"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/65568663-fd95-53de-bc55-5f657e836c81.json b/oaitestdata/clarin-oai_dc/SET_1/json/65568663-fd95-53de-bc55-5f657e836c81.json
deleted file mode 100644
index 590cedc0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/65568663-fd95-53de-bc55-5f657e836c81.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2891",
-    "MetadataAccess": [
-        "oai:ota:oucs:2891"
-    ],
-    "PublicationTimestamp": "1765-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1765"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2891;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2891.xml;Public absurdities in England;Swift, Jonathan, 1667-1745;1765;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "65568663-fd95-53de-bc55-5f657e836c81",
-    "oai_identifier": [
-        "oai:ota:oucs:2891"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Public absurdities in England"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2891.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/65673ff0-c91a-5e91-988e-25c29d6cdd7b.json b/oaitestdata/clarin-oai_dc/SET_1/json/65673ff0-c91a-5e91-988e-25c29d6cdd7b.json
deleted file mode 100644
index 6e647cf6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/65673ff0-c91a-5e91-988e-25c29d6cdd7b.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Mackenzie, D.N. (David Neil)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(2 files : ca. 384, 2 KB)"
-    ],
-    "Language": [
-        "Kurdish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0249",
-    "MetadataAccess": [
-        "oai:ota:oucs:0249"
-    ],
-    "PublicationTimestamp": "1918-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1918"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Anthologies"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hark\u00c4\u00ab, Mull\u00c4\u0081 Sa\u00d8\u00b9\u00c4\u00abd"
-    ],
-    "fulltext": "oai:ota:oucs:0249;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0249.xml;Shamd\u00c4\u00abn\u00c4\u0081n\u00c4\u00ab Kurdish texts / Mull\u00c4\u0081 Sa\u00d8\u00b9\u00c4\u00abd Hark\u00c4\u00ab;Hark\u00c4\u00ab, Mull\u00c4\u0081 Sa\u00d8\u00b9\u00c4\u00abd;1918;text_and_corpus_linguistics;Languages, Modern -- Iran -- Study and teaching ;kur;Oxford Text Archive, University of Oxford;Mackenzie, D.N. (David Neil);Mackenzie, D.N. (David Neil);(2 files : ca. 384, 2 KB);Text;Anthologies;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "65673ff0-c91a-5e91-988e-25c29d6cdd7b",
-    "oai_identifier": [
-        "oai:ota:oucs:0249"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Languages"
-        },
-        {
-            "name": "Modern -- Iran -- Study teaching"
-        }
-    ],
-    "title": [
-        "Shamd\u00c4\u00abn\u00c4\u0081n\u00c4\u00ab Kurdish texts / Mull\u00c4\u0081 Sa\u00d8\u00b9\u00c4\u00abd Hark\u00c4\u00ab"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0249.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/657fc9c4-abe7-58c4-ae9a-450f488e9927.json b/oaitestdata/clarin-oai_dc/SET_1/json/657fc9c4-abe7-58c4-ae9a-450f488e9927.json
deleted file mode 100644
index 15d6bc7a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/657fc9c4-abe7-58c4-ae9a-450f488e9927.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Center for Sprogteknologi,  University of Copenhagen"
-    ],
-    "Contributor": [
-        "Jongejan, Bart"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-292",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-292"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-292",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Center for Sprogteknologi,  University of Copenhagen"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Denmark"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-292;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;repetitiveness checker;Jongejan, Bart;1) Finds repeated sequences of words in documents (repetitiveness checker) 2) Finds common sequences of words in several documents (version comparison) A sequence of words consists of minimally two words. There is no upper limit of the number of words in a sequence, but sequences do not transgress sentence delimiters. There are several weight functions to choose from, each defining \"good\" sequences in a different way, based on word frequency, sequence lenght and number of repetitions.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-292;downloadable_files_count: 0;Denmark;Center for Sprogteknologi,  University of Copenhagen;http://cst.dk/tools/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "657fc9c4-abe7-58c4-ae9a-450f488e9927",
-    "notes": [
-        "1) Finds repeated sequences of words in documents (repetitiveness checker) 2) Finds common sequences of words in several documents (version comparison) A sequence of words consists of minimally two words. There is no upper limit of the number of words in a sequence, but sequences do not transgress sentence delimiters. There are several weight functions to choose from, each defining \"good\" sequences in a different way, based on word frequency, sequence lenght and number of repetitions."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-292"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "repetitiveness checker"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/65ad5902-7fcb-57e1-9ee1-c767ec5bd8e5.json b/oaitestdata/clarin-oai_dc/SET_1/json/65ad5902-7fcb-57e1-9ee1-c767ec5bd8e5.json
deleted file mode 100644
index 91986cf5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/65ad5902-7fcb-57e1-9ee1-c767ec5bd8e5.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Ruef, Beni"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml",
-        "(24 files : ca. 8.82 MB)"
-    ],
-    "Language": [
-        "Old English (ca. 450-1100)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2470",
-    "MetadataAccess": [
-        "oai:ota:oucs:2470"
-    ],
-    "PublicationTimestamp": "2002-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2002"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Linguistic corpora"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:2470;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/2470.xml;The Brooklyn Corpus of Old English : TEI XML conformant edition;2002-08;text_and_corpus_linguistics;English language--Old English, ca. 450-1100;Linguistic analysis (Linguistics);English prose literature Old English, ca. 450-1100;ang;The Brooklyn Corpus is an annotated version of prose texts from the Old English Section of the Helsinki Corpus, representing a range of dates of composition, authors, and genres. It contains more than 106 000 words of Old English; the samples from the the longer texts are 5000 to 10 000 words in length. The texts are syntactically and morphologically annotated, and each Old English word is glossed. Besides the syntactic annotation, the TEI.2 [XML conformant] edition of the Brooklyn Corpus contains all the annotations from the original edition, i.e. part-of-speech tags, complete morphology, lemmata, and Modern English glosses. ;Oxford Text Archive, University of Oxford;Ruef, Beni;Ruef, Beni;text/xml;(24 files : ca. 8.82 MB);Text;Linguistic corpora;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "65ad5902-7fcb-57e1-9ee1-c767ec5bd8e5",
-    "notes": [
-        "The Brooklyn Corpus is an annotated version of prose texts from the Old English Section of the Helsinki Corpus, representing a range of dates of composition, authors, and genres. It contains more than 106 000 words of Old English; the samples from the the longer texts are 5000 to 10 000 words in length. The texts are syntactically and morphologically annotated, and each Old English word is glossed. Besides the syntactic annotation, the TEI.2 [XML conformant] edition of the Brooklyn Corpus contains all the annotations from the original edition, i.e. part-of-speech tags, complete morphology, lemmata, and Modern English glosses. "
-    ],
-    "oai_identifier": [
-        "oai:ota:oucs:2470"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English language--Old English"
-        },
-        {
-            "name": "ca. -"
-        },
-        {
-            "name": "Linguistic analysis Linguistics"
-        },
-        {
-            "name": "English prose literature Old English"
-        },
-        {
-            "name": "ca. -"
-        }
-    ],
-    "title": [
-        "The Brooklyn Corpus of Old English : TEI XML conformant edition"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2470.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/65b9b5c5-5a09-5a53-9286-137a808b0299.json b/oaitestdata/clarin-oai_dc/SET_1/json/65b9b5c5-5a09-5a53-9286-137a808b0299.json
deleted file mode 100644
index 27a28b0b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/65b9b5c5-5a09-5a53-9286-137a808b0299.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Bulgarian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/69",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/69"
-    ],
-    "PID": "http://hdl.handle.net/11509/69",
-    "PublicationTimestamp": "2012-03-29T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Super Cool License",
-        "http://www.google.com",
-        "ACA"
-    ],
-    "author": [
-        "Simov, Kiril"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/69;2016-04-15T05:59:20Z;hdl_11509_1;hdl_11509_2;the Morphologically Annotated Part of BulTreeBank;Simov, Kiril;Corpus;Text;Bulgarian;This distribution represents only the morphological information encoded in BulTreeBank - HPSG-based Treebank of Bulgarian. It contains about 214.000 tokens. It was used for the training of the TreeTagger for Bulgarian.  It contains sentences from Bulgarian Grammar Textbooks, Newspapers, Literature and other sources of texts.;2012-03-29;corpus;http://iness.uib.no/;http://hdl.handle.net/11509/69;bul;Super Cool License;http://www.google.com;ACA;downloadable_files_count: 0;http://iness.uib.no/;http://www.bultreebank.org/btbmorf/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "65b9b5c5-5a09-5a53-9286-137a808b0299",
-    "notes": [
-        "This distribution represents only the morphological information encoded in BulTreeBank - HPSG-based Treebank of Bulgarian. It contains about 214.000 tokens. It was used for the training of the TreeTagger for Bulgarian.  It contains sentences from Bulgarian Grammar Textbooks, Newspapers, Literature and other sources of texts."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/69"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Corpus"
-        },
-        {
-            "name": "Text"
-        },
-        {
-            "name": "Bulgarian"
-        }
-    ],
-    "title": [
-        "the Morphologically Annotated Part of BulTreeBank"
-    ],
-    "url": "http://iness.uib.no/"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/65cfafe9-6b6e-5b9f-a5ee-07f6276a85d2.json b/oaitestdata/clarin-oai_dc/SET_1/json/65cfafe9-6b6e-5b9f-a5ee-07f6276a85d2.json
deleted file mode 100644
index 05f7aa5c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/65cfafe9-6b6e-5b9f-a5ee-07f6276a85d2.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/311",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/311"
-    ],
-    "PID": "http://hdl.handle.net/11321/311",
-    "PublicationTimestamp": "2016-06-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "K\u0119dzia, Pawe\u0142",
-        "Piasecki, Maciej",
-        "Gut, Anna",
-        "Treter, Wojciech"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/311;2016-06-09T06:55:32Z;hdl_11321_3;hdl_11321_4;Summary;Treter, Wojciech;Piasecki, Maciej;Gut, Anna;K\u0119dzia, Pawe\u0142;Summary;Summarization;Extraction;Summary is text summarizer which based on the most importat sentences extraction.;2016-06-01;toolService;http://hdl.handle.net/11321/311;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 1;Wroc\u0142aw University of Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "65cfafe9-6b6e-5b9f-a5ee-07f6276a85d2",
-    "notes": [
-        "Summary is text summarizer which based on the most importat sentences extraction."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/311"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Summary"
-        },
-        {
-            "name": "Summarization"
-        },
-        {
-            "name": "Extraction"
-        }
-    ],
-    "title": [
-        "Summary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/65fe0c98-8036-577c-8981-9cf20153c5dd.json b/oaitestdata/clarin-oai_dc/SET_1/json/65fe0c98-8036-577c-8981-9cf20153c5dd.json
deleted file mode 100644
index 98a9af3f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/65fe0c98-8036-577c-8981-9cf20153c5dd.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "University of Helsinki"
-    ],
-    "Contributor": [
-        "Lind\u00e9n, Krister"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1201",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1201"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1201",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Helsinki"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1201;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Helsinki Finite-State Technology;Lind\u00e9n, Krister;The Helsinki Finite-State Transducer software is intended for the implementation of morphological analysers and other tools which are based on weighted and unweigted finite-state transducer technology. The feasibility of the HFST toolkit has been demonstrated by full-fledged open source implementations of Finnish, Swedish, English, French and Northern S\u00e1mi lexicons.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1201;downloadable_files_count: 0;University of Helsinki;http://www.ling.helsinki.fi/kieliteknologia/tutkimus/hfst/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "65fe0c98-8036-577c-8981-9cf20153c5dd",
-    "notes": [
-        "The Helsinki Finite-State Transducer software is intended for the implementation of morphological analysers and other tools which are based on weighted and unweigted finite-state transducer technology. The feasibility of the HFST toolkit has been demonstrated by full-fledged open source implementations of Finnish, Swedish, English, French and Northern S\u00e1mi lexicons."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1201"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Helsinki Finite-State Technology"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/661ee34f-b934-5bfa-9fee-daa1a79ff043.json b/oaitestdata/clarin-oai_dc/SET_1/json/661ee34f-b934-5bfa-9fee-daa1a79ff043.json
deleted file mode 100644
index 53186cf7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/661ee34f-b934-5bfa-9fee-daa1a79ff043.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Budapest Technical University Media Research Centre"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1336",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1336"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1336",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Budapest Technical University Media Research Centre"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Hungary"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Simon, Eszter",
-        "Varga, D\u00e1niel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1336;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;hunner - named entitiy recognizer for Hungarian;Varga, D\u00e1niel;Simon, Eszter;Hungarian named entity recognition with a maximum entropy approach;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1336;downloadable_files_count: 0;Hungary;Budapest Technical University Media Research Centre",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "661ee34f-b934-5bfa-9fee-daa1a79ff043",
-    "notes": [
-        "Hungarian named entity recognition with a maximum entropy approach"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1336"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "hunner - named entitiy recognizer for Hungarian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/662b6357-b773-54df-8bc8-74db009ae8be.json b/oaitestdata/clarin-oai_dc/SET_1/json/662b6357-b773-54df-8bc8-74db009ae8be.json
deleted file mode 100644
index d605b5a4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/662b6357-b773-54df-8bc8-74db009ae8be.json
+++ /dev/null
@@ -1,89 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1025",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1025"
-    ],
-    "PID": "http://hdl.handle.net/11356/1025",
-    "PublicationTimestamp": "2015-05-05T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/215064",
-        "https://doi.org/10.1007/s10579-015-9294-7"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "Erjavec, Toma\u017e"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1025;2018-10-24T20:47:48Z;hdl_11356_1023;hdl_11356_1024;Reference corpus of historical Slovene goo300k 1.2;Erjavec, Toma\u017e;historical language;word modernisation;lemmatisation;tagging;manual annotation;TEI;goo300k is a manually annotated reference corpus of historical Slovene. It contains 1,100 pages (about 300,000 tokens) sampled from 89 texts from the period 1584-1899.\r\n\r\nEach text contains extensive meta-data and  per-page links to facsimiles, while the word tokens in the texts are annotated with their modernised word-form, lemma, part-of-speech, and, for archaic words, their nearest modern synonyms or short explanation. \r\n\r\nThe corpus is available in source TEI P5 XML and in the simpler and smaller vertical format, used by various concordancers. Note that the vertical format does not contain all the information from the source TEI.;2015-05-05;corpus;http://hdl.handle.net/11356/1025;slv;info:eu-repo/grantAgreement/EC/FP7/215064;https://doi.org/10.1007/s10579-015-9294-7;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;https://creativecommons.org/licenses/by/4.0/;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 2;Jo\u017eef Stefan Institute;http://nl.ijs.si/imp/index-en.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "662b6357-b773-54df-8bc8-74db009ae8be",
-    "notes": [
-        "goo300k is a manually annotated reference corpus of historical Slovene. It contains 1,100 pages (about 300,000 tokens) sampled from 89 texts from the period 1584-1899.\r\n\r\nEach text contains extensive meta-data and  per-page links to facsimiles, while the word tokens in the texts are annotated with their modernised word-form, lemma, part-of-speech, and, for archaic words, their nearest modern synonyms or short explanation. \r\n\r\nThe corpus is available in source TEI P5 XML and in the simpler and smaller vertical format, used by various concordancers. Note that the vertical format does not contain all the information from the source TEI."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1025"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "historical language"
-        },
-        {
-            "name": "word modernisation"
-        },
-        {
-            "name": "lemmatisation"
-        },
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "manual annotation"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "Reference corpus of historical Slovene goo300k 1.2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/66400909-f58a-556e-9f3a-886a2aeda6cf.json b/oaitestdata/clarin-oai_dc/SET_1/json/66400909-f58a-556e-9f3a-886a2aeda6cf.json
deleted file mode 100644
index 97f3cc41..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/66400909-f58a-556e-9f3a-886a2aeda6cf.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3714",
-    "MetadataAccess": [
-        "oai:ota:oucs:3714"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Paine, Thomas, 1737-1809."
-    ],
-    "fulltext": "oai:ota:oucs:3714;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3714.xml;A letter to George Washington: on the subject of the late treaty concluded between Great-Britain and the United States of America, including other matters. By Thomas Paine, ...;Paine, Thomas, 1737-1809.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "66400909-f58a-556e-9f3a-886a2aeda6cf",
-    "oai_identifier": [
-        "oai:ota:oucs:3714"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A letter to George Washington: on the subject of the late treaty concluded between Great-Britain and the United States of America, including other matters. By Thomas Paine, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3714.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/664fd6e3-7ed6-5bea-9b30-8ef2cab6ac95.json b/oaitestdata/clarin-oai_dc/SET_1/json/664fd6e3-7ed6-5bea-9b30-8ef2cab6ac95.json
deleted file mode 100644
index 78869eaa..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/664fd6e3-7ed6-5bea-9b30-8ef2cab6ac95.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/32",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/32"
-    ],
-    "PID": "http://hdl.handle.net/11321/32",
-    "PublicationTimestamp": "2010-08-11T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "\u015aniatowski, Tomasz",
-        "Radziszewski, Adam"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/32;2016-01-21T14:14:38Z;hdl_11321_3;hdl_11321_4;Toki;Radziszewski, Adam;\u015aniatowski, Tomasz;Toki is a configurable tokeniser, i.e. a module for segmentation of running text into tokens (word-like units) and sentences.;2010-08-11;toolService;http://hdl.handle.net/11321/32;pol;downloadable_files_count: 0;Wroc\u0142aw University of Technology;http://nlp.pwr.wroc.pl/narzedzia-i-zasoby/toki-tokeniser",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "664fd6e3-7ed6-5bea-9b30-8ef2cab6ac95",
-    "notes": [
-        "Toki is a configurable tokeniser, i.e. a module for segmentation of running text into tokens (word-like units) and sentences."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/32"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Toki"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/66548e4b-c770-5035-8e02-7a624c570cf0.json b/oaitestdata/clarin-oai_dc/SET_1/json/66548e4b-c770-5035-8e02-7a624c570cf0.json
deleted file mode 100644
index 6e90a505..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/66548e4b-c770-5035-8e02-7a624c570cf0.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3976",
-    "MetadataAccess": [
-        "oai:ota:oucs:3976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hill, Aaron, 1685-1750."
-    ],
-    "fulltext": "oai:ota:oucs:3976;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3976.xml;The fanciad. An heroic poem. In six cantos. To His Grace the Duke of Marlborough, on the turn of his genius to arms;Hill, Aaron, 1685-1750.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "66548e4b-c770-5035-8e02-7a624c570cf0",
-    "oai_identifier": [
-        "oai:ota:oucs:3976"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The fanciad. An heroic poem. In six cantos. To His Grace the Duke of Marlborough, on the turn of his genius to arms"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3976.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/665e87d9-6df4-5dc5-a098-07954b804949.json b/oaitestdata/clarin-oai_dc/SET_1/json/665e87d9-6df4-5dc5-a098-07954b804949.json
deleted file mode 100644
index a27a4db6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/665e87d9-6df4-5dc5-a098-07954b804949.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "University of Oslo"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Norwegian Bokm\u00e5l",
-        "Norwegian Nynorsk"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/123",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/123"
-    ],
-    "PID": "http://hdl.handle.net/11509/123",
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "University of Oslo"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Norsk lisens for offentlige data (NLOD) 1.0",
-        "https://data.norge.no/nlod/no/1.0",
-        "PUB"
-    ],
-    "author": [
-        "S\u00f8yland, Martin G.",
-        "Lapponi, Emanuele"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/123;2017-10-03T17:02:06Z;hdl_11509_1;hdl_11509_2;Talk of Norway;Lapponi, Emanuele;S\u00f8yland, Martin G.;parliamentary data;political science;nlp;parliamentary analysis;Talk of Norway is a collection of Norwegian Parliament speeches from 1998 to 2016. \r\nEvery speech is richly annotated with metadata harvested from different sources, and augmented with language type, sentence, token, lemma, part-of-speech, and morphological feature annotations.;2016;corpus;http://hdl.handle.net/11509/123;nob;nno;Norsk lisens for offentlige data (NLOD) 1.0;https://data.norge.no/nlod/no/1.0;PUB;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 1;University of Oslo;http://www.mn.uio.no/ifi/english/research/projects/ton/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "665e87d9-6df4-5dc5-a098-07954b804949",
-    "notes": [
-        "Talk of Norway is a collection of Norwegian Parliament speeches from 1998 to 2016. \r\nEvery speech is richly annotated with metadata harvested from different sources, and augmented with language type, sentence, token, lemma, part-of-speech, and morphological feature annotations."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/123"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parliamentary data"
-        },
-        {
-            "name": "political science"
-        },
-        {
-            "name": "nlp"
-        },
-        {
-            "name": "parliamentary analysis"
-        }
-    ],
-    "title": [
-        "Talk of Norway"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/666cc99e-5c61-5a90-8bd1-616ece87d1cc.json b/oaitestdata/clarin-oai_dc/SET_1/json/666cc99e-5c61-5a90-8bd1-616ece87d1cc.json
deleted file mode 100644
index b87a8435..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/666cc99e-5c61-5a90-8bd1-616ece87d1cc.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Delbecque, Nicole"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 77 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0450",
-    "MetadataAccess": [
-        "oai:ota:oucs:0450"
-    ],
-    "PublicationTimestamp": "1971-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1971"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pinter, Harold, 1930-"
-    ],
-    "fulltext": "oai:ota:oucs:0450;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0450.xml;Old times / Harold Pinter;Pinter, Harold, 1930-;1971;text_and_corpus_linguistics;English drama -- 20th century;Oxford Text Archive, University of Oxford;Delbecque, Nicole;(1 file : ca. 77 KB);Text;Plays;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "666cc99e-5c61-5a90-8bd1-616ece87d1cc",
-    "oai_identifier": [
-        "oai:ota:oucs:0450"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- th century"
-        }
-    ],
-    "title": [
-        "Old times / Harold Pinter"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0450.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/66830837-0d7f-5709-a062-3b003fb97b37.json b/oaitestdata/clarin-oai_dc/SET_1/json/66830837-0d7f-5709-a062-3b003fb97b37.json
deleted file mode 100644
index 28948f85..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/66830837-0d7f-5709-a062-3b003fb97b37.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Hansen, Chris"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 448 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1518",
-    "MetadataAccess": [
-        "oai:ota:oucs:1518"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Fairy tales",
-        "Anthologies"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:1518;2018-02-16T10:42:06Z;http://ota.ox.ac.uk/headers/1518.xml;Collection of fairy stories / Chris Hansen;text_and_corpus_linguistics;Fairy tales;English language -- United States -- 20th century;eng;Oxford Text Archive, University of Oxford;Hansen, Chris;Hansen, Chris;text/plain;(1 file : ca. 448 KB);Text;Fairy tales;Anthologies;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "66830837-0d7f-5709-a062-3b003fb97b37",
-    "oai_identifier": [
-        "oai:ota:oucs:1518"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fairy tales"
-        },
-        {
-            "name": "English language -- United States -- th century"
-        }
-    ],
-    "title": [
-        "Collection of fairy stories / Chris Hansen"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1518.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6683b097-cb58-5585-b543-644c93af6867.json b/oaitestdata/clarin-oai_dc/SET_1/json/6683b097-cb58-5585-b543-644c93af6867.json
deleted file mode 100644
index 58795a9c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6683b097-cb58-5585-b543-644c93af6867.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "Filesize uncompressed: 274 KBytes. "
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1896",
-    "MetadataAccess": [
-        "oai:ota:oucs:1896"
-    ],
-    "PublicationTimestamp": "1895-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1895"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Fiction -- Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Crane, Stephen, 1871-1900"
-    ],
-    "fulltext": "oai:ota:oucs:1896;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/1896.xml;The Red Badge of Courage;A machine-readable transcription;Crane, Stephen, 1871-1900;1895;text_and_corpus_linguistics;Novels -- United States -- 19th century;eng;Oxford Text Archive, University of Oxford;Filesize uncompressed: 274 KBytes. ;Text;Fiction -- Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6683b097-cb58-5585-b543-644c93af6867",
-    "oai_identifier": [
-        "oai:ota:oucs:1896"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Novels -- United States -- th century"
-        }
-    ],
-    "title": [
-        "The Red Badge of Courage",
-        "A machine-readable transcription"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1896.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6684e44e-a5b0-522b-8fa2-10bdd37b8fc9.json b/oaitestdata/clarin-oai_dc/SET_1/json/6684e44e-a5b0-522b-8fa2-10bdd37b8fc9.json
deleted file mode 100644
index 6280bc50..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6684e44e-a5b0-522b-8fa2-10bdd37b8fc9.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "University of Sheffield"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 8"
-    ],
-    "Language": [
-        "English",
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1974",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1974"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1974",
-    "PublicationTimestamp": "2017-02-27T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "University of Sheffield"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/H2020/645452",
-        "http://hdl.handle.net/11372/LRT-1646",
-        "http://hdl.handle.net/11372/LRT-2619"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "AGREEMENT ON THE USE OF DATA IN QT21",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21",
-        "PUB"
-    ],
-    "author": [
-        "Logacheva, Varvara",
-        "Specia, Lucia"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1974;2018-02-19T13:59:24Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;WMT17 Quality Estimation Shared Task Training and Development Data;Specia, Lucia;Logacheva, Varvara;machine translation;quality estimation;machine learning;Training and development data for the WMT17 QE task. Test data will be published as a separate item.\r\n\r\nThis shared task will build on its previous five editions to further examine automatic methods for estimating the quality of machine translation output at run-time, without relying on reference translations. We include word-level, phrase-level and sentence-level estimation. All tasks will make use of a large dataset produced from post-editions by professional translators. The data will be domain-specific (IT and Pharmaceutical domains) and substantially larger than in previous years. In addition to advancing the state of the art at all prediction levels, our goals include:\r\n\r\n- To test the effectiveness of larger (domain-specific and professionally annotated) datasets. We will do so by increasing the size of one of last year's training sets.\r\n- To study the effect of language direction and domain. We will do so by providing two datasets created in similar ways, but for different domains and language directions.\r\n- To investigate the utility of detailed information logged during post-editing. We will do so by providing post-editing time, keystrokes, and actual edits.\r\n\r\nThis year's shared task provides new training and test datasets for all tasks, and allows participants to explore any additional data and resources deemed relevant. A in-house MT system was used to produce translations for all tasks. MT system-dependent information can be made available under request. The data is publicly available but since it has been provided by our industry partners it is subject to specific terms and conditions. However, these have no practical implications on the use of this data for research purposes.;2017-02-27;corpus;http://hdl.handle.net/11372/LRT-1974;eng;deu;info:eu-repo/grantAgreement/EC/H2020/645452;http://hdl.handle.net/11372/LRT-1646;http://hdl.handle.net/11372/LRT-2619;AGREEMENT ON THE USE OF DATA IN QT21;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21;PUB;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 8;University of Sheffield;http://www.statmt.org/wmt17/quality-estimation-task.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6684e44e-a5b0-522b-8fa2-10bdd37b8fc9",
-    "notes": [
-        "Training and development data for the WMT17 QE task. Test data will be published as a separate item.\r\n\r\nThis shared task will build on its previous five editions to further examine automatic methods for estimating the quality of machine translation output at run-time, without relying on reference translations. We include word-level, phrase-level and sentence-level estimation. All tasks will make use of a large dataset produced from post-editions by professional translators. The data will be domain-specific (IT and Pharmaceutical domains) and substantially larger than in previous years. In addition to advancing the state of the art at all prediction levels, our goals include:\r\n\r\n- To test the effectiveness of larger (domain-specific and professionally annotated) datasets. We will do so by increasing the size of one of last year's training sets.\r\n- To study the effect of language direction and domain. We will do so by providing two datasets created in similar ways, but for different domains and language directions.\r\n- To investigate the utility of detailed information logged during post-editing. We will do so by providing post-editing time, keystrokes, and actual edits.\r\n\r\nThis year's shared task provides new training and test datasets for all tasks, and allows participants to explore any additional data and resources deemed relevant. A in-house MT system was used to produce translations for all tasks. MT system-dependent information can be made available under request. The data is publicly available but since it has been provided by our industry partners it is subject to specific terms and conditions. However, these have no practical implications on the use of this data for research purposes."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1974"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "quality estimation"
-        },
-        {
-            "name": "machine learning"
-        }
-    ],
-    "title": [
-        "WMT17 Quality Estimation Shared Task Training and Development Data"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/66890a3a-367c-5c48-a354-bc9505e6f8b5.json b/oaitestdata/clarin-oai_dc/SET_1/json/66890a3a-367c-5c48-a354-bc9505e6f8b5.json
deleted file mode 100644
index acedcf60..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/66890a3a-367c-5c48-a354-bc9505e6f8b5.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Oriental Studies, University of Oxford"
-    ],
-    "Contributor": [
-        "Black, Jeremy"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-874",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-874"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-874",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Faculty of Oriental Studies, University of Oxford"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-874;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Electronic text corpus of Sumerian literature (ETCSL);Black, Jeremy;A selection of nearly 400 literary compositions recorded on sources which come from ancient Mesopotamia and date to the late third and early second millennia BCE.  The corpus contains Sumerian texts in transliteration, English prose translations and bibliographical information for each composition. The transliterations and the translations can be searched, browsed and read online using the tools of the website.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-874;downloadable_files_count: 0;United Kingdom;Faculty of Oriental Studies, University of Oxford;http://etcsl.orinst.ox.ac.uk/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "66890a3a-367c-5c48-a354-bc9505e6f8b5",
-    "notes": [
-        "A selection of nearly 400 literary compositions recorded on sources which come from ancient Mesopotamia and date to the late third and early second millennia BCE.  The corpus contains Sumerian texts in transliteration, English prose translations and bibliographical information for each composition. The transliterations and the translations can be searched, browsed and read online using the tools of the website."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-874"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Electronic text corpus of Sumerian literature (ETCSL)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/66a4a104-c39c-5c93-a7ab-325825aa70fb.json b/oaitestdata/clarin-oai_dc/SET_1/json/66a4a104-c39c-5c93-a7ab-325825aa70fb.json
deleted file mode 100644
index c22d845b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/66a4a104-c39c-5c93-a7ab-325825aa70fb.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3900",
-    "MetadataAccess": [
-        "oai:ota:oucs:3900"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Wesley, John, 1703-1791."
-    ],
-    "fulltext": "oai:ota:oucs:3900;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3900.xml;Hymns and sacred poems: Published by John Wesley, ... and Charles Wesley, ...;Wesley, John, 1703-1791.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "66a4a104-c39c-5c93-a7ab-325825aa70fb",
-    "oai_identifier": [
-        "oai:ota:oucs:3900"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Hymns and sacred poems: Published by John Wesley, ... and Charles Wesley, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3900.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/66b7aa25-776d-588e-8350-3e39a3a41dd5.json b/oaitestdata/clarin-oai_dc/SET_1/json/66b7aa25-776d-588e-8350-3e39a3a41dd5.json
deleted file mode 100644
index 4fea8421..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/66b7aa25-776d-588e-8350-3e39a3a41dd5.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1201",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1201"
-    ],
-    "PID": "http://hdl.handle.net/11356/1201",
-    "PublicationTimestamp": "2018-10-27T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "https://drive.google.com/file/d/13m7PFn49_tnEfFjcbqk8cugG4ZTy2A5I/view"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "https://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Erjavec, Toma\u017e",
-        "Ljube\u0161i\u0107, Nikola",
-        "Fi\u0161er, Darja"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1201;2018-10-27T13:50:26Z;hdl_11356_1023;hdl_11356_1024;Dataset and baseline model of moderated content FRENK-MMC-RTV 1.0;Ljube\u0161i\u0107, Nikola;Erjavec, Toma\u017e;Fi\u0161er, Darja;computer-mediated communication;news comments;content moderation;FRENK-MMC-RTV is a dataset of moderated newspaper comments from the website rtvslo.si with metadata on the time of publishing, user identifier, thread identifier and whether the comment was deleted by the moderators or not. The full text of each comment is encrypted via a character-replacement method so that the comments are not readable by humans. Basic punctuation is not encrypted in order to enable tokenization. The main use of this dataset are experiments on automating comment moderation. For real-world usage, a fastText classification model trained on non-encrypted data is made available as well.;2018-10-27;corpus;http://hdl.handle.net/11356/1201;slv;https://drive.google.com/file/d/13m7PFn49_tnEfFjcbqk8cugG4ZTy2A5I/view;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);https://creativecommons.org/licenses/by-sa/4.0/;PUB;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 2;Jo\u017eef Stefan Institute;http://nl.ijs.si/frenk/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "66b7aa25-776d-588e-8350-3e39a3a41dd5",
-    "notes": [
-        "FRENK-MMC-RTV is a dataset of moderated newspaper comments from the website rtvslo.si with metadata on the time of publishing, user identifier, thread identifier and whether the comment was deleted by the moderators or not. The full text of each comment is encrypted via a character-replacement method so that the comments are not readable by humans. Basic punctuation is not encrypted in order to enable tokenization. The main use of this dataset are experiments on automating comment moderation. For real-world usage, a fastText classification model trained on non-encrypted data is made available as well."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1201"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "computer-mediated communication"
-        },
-        {
-            "name": "news comments"
-        },
-        {
-            "name": "content moderation"
-        }
-    ],
-    "title": [
-        "Dataset and baseline model of moderated content FRENK-MMC-RTV 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/66b82d7f-a74a-59d6-a05c-3f6859b8653a.json b/oaitestdata/clarin-oai_dc/SET_1/json/66b82d7f-a74a-59d6-a05c-3f6859b8653a.json
deleted file mode 100644
index ac7487ef..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/66b82d7f-a74a-59d6-a05c-3f6859b8653a.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-996",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-996"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-996",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-996;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LAC Tidore Corpus;Language and Cognition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-996;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI50928%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "66b82d7f-a74a-59d6-a05c-3f6859b8653a",
-    "notes": [
-        "Language and Cognition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-996"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LAC Tidore Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/66bd63da-3c96-50d6-9f9d-8d44e7db8438.json b/oaitestdata/clarin-oai_dc/SET_1/json/66bd63da-3c96-50d6-9f9d-8d44e7db8438.json
deleted file mode 100644
index f4f90d45..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/66bd63da-3c96-50d6-9f9d-8d44e7db8438.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3364",
-    "MetadataAccess": [
-        "oai:ota:oucs:3364"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Anstey, Christopher, 1724-1805."
-    ],
-    "fulltext": "oai:ota:oucs:3364;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3364.xml;The new Bath guide: or, memoirs of the B-r-d family. In a series of poetical epistles.;Anstey, Christopher, 1724-1805.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "66bd63da-3c96-50d6-9f9d-8d44e7db8438",
-    "oai_identifier": [
-        "oai:ota:oucs:3364"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The new Bath guide: or, memoirs of the B-r-d family. In a series of poetical epistles."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3364.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/66cc8cd9-3996-55ed-ad47-4c7b678b8ce8.json b/oaitestdata/clarin-oai_dc/SET_1/json/66cc8cd9-3996-55ed-ad47-4c7b678b8ce8.json
deleted file mode 100644
index 4fd93625..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/66cc8cd9-3996-55ed-ad47-4c7b678b8ce8.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Institute of Slavic Studies, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 84",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish",
-        "Ukrainian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/535",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/535"
-    ],
-    "PID": "http://hdl.handle.net/11321/535",
-    "PublicationTimestamp": "2018-07-21T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Institute of Slavic Studies, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "IS PAS corpora license",
-        "http://clarin-pl.eu/en/licenses/is-pas-corpora-license/",
-        "CC"
-    ],
-    "author": [
-        "Tymoshuk, Roman",
-        "Duszkin, Maksim",
-        "Roszko, Roman",
-        "Sosnowski, Wojciech"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/535;2018-07-21T20:51:36Z;hdl_11321_3;hdl_11321_4;Polish-Ukrainian Parallel Corpus;Roszko, Roman;Tymoshuk, Roman;Duszkin, Maksim;Sosnowski, Wojciech;Polish;Ukrainian;Parallel Corpora;Polish-Ukrainian Parallel Corpus;2018-07-21;corpus;http://hdl.handle.net/11321/535;pol;ukr;IS PAS corpora license;http://clarin-pl.eu/en/licenses/is-pas-corpora-license/;CC;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 84;Institute of Slavic Studies, Polish Academy of Sciences",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "66cc8cd9-3996-55ed-ad47-4c7b678b8ce8",
-    "notes": [
-        "Polish-Ukrainian Parallel Corpus"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/535"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Polish"
-        },
-        {
-            "name": "Ukrainian"
-        },
-        {
-            "name": "Parallel Corpora"
-        }
-    ],
-    "title": [
-        "Polish-Ukrainian Parallel Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/66cf0067-f156-5431-aa15-5ab13320f0c8.json b/oaitestdata/clarin-oai_dc/SET_1/json/66cf0067-f156-5431-aa15-5ab13320f0c8.json
deleted file mode 100644
index 2474ae6e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/66cf0067-f156-5431-aa15-5ab13320f0c8.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3428",
-    "MetadataAccess": [
-        "oai:ota:oucs:3428"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Addison, Joseph, 1672-1719."
-    ],
-    "fulltext": "oai:ota:oucs:3428;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3428.xml;The resurrection. A poem: Written by Mr. Addison.;Resurrectio delineata ad altare col. Magd. Oxon. English and Latin;Addison, Joseph, 1672-1719.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "66cf0067-f156-5431-aa15-5ab13320f0c8",
-    "oai_identifier": [
-        "oai:ota:oucs:3428"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The resurrection. A poem: Written by Mr. Addison.",
-        "Resurrectio delineata ad altare col. Magd. Oxon. English and Latin"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3428.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/66df5ebf-43f7-5635-b708-11e57dd58065.json b/oaitestdata/clarin-oai_dc/SET_1/json/66df5ebf-43f7-5635-b708-11e57dd58065.json
deleted file mode 100644
index f190bdc8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/66df5ebf-43f7-5635-b708-11e57dd58065.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "ENS de Lyon - CNRS, ICAR Laboratory"
-    ],
-    "Contributor": [
-        "Heiden, Serge"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1059",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1059"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1059",
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "ENS de Lyon - CNRS, ICAR Laboratory"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "EPL V1.0; GNU GPL V2.0; GNU GPL V3.0; GNU LGPL V2.1",
-        "Copyright \u00a9 2010-2013 ENS de Lyon; Copyright \u00a9 2007-2010 ENS de Lyon, CNRS, INRP, University of Lyon 2, University of Franche-Comt\u00e9, University of Nice Sophia Antipolis, University of Paris 3."
-    ],
-    "SpatialCoverage": [
-        "France"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1059;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TXM;Heiden, Serge;TXM is a Unicode - XML & TEI compatible text/corpus analysis environment and graphical client based on the CQP search engine and the R statistical environment (http://textometrie.ens-lyon.fr/?lang=en).;2013;toolService;http://hdl.handle.net/11372/LRT-1059;EPL V1.0; GNU GPL V2.0; GNU GPL V3.0; GNU LGPL V2.1;Copyright \u00a9 2010-2013 ENS de Lyon; Copyright \u00a9 2007-2010 ENS de Lyon, CNRS, INRP, University of Lyon 2, University of Franche-Comt\u00e9, University of Nice Sophia Antipolis, University of Paris 3.;downloadable_files_count: 0;France;ENS de Lyon - CNRS, ICAR Laboratory;http://sourceforge.net/projects/txm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "66df5ebf-43f7-5635-b708-11e57dd58065",
-    "notes": [
-        "TXM is a Unicode - XML & TEI compatible text/corpus analysis environment and graphical client based on the CQP search engine and the R statistical environment (http://textometrie.ens-lyon.fr/?lang=en)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1059"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TXM"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6701dd84-63b7-544a-b940-61034d8b270e.json b/oaitestdata/clarin-oai_dc/SET_1/json/6701dd84-63b7-544a-b940-61034d8b270e.json
deleted file mode 100644
index 7e99abeb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6701dd84-63b7-544a-b940-61034d8b270e.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Catalan",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1174",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1174"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1174",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1174;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;BUSCANEO;Tool for neologism extraction.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1174;cat;spa;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra;http://obneo.iula.upf.edu/buscaneo/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6701dd84-63b7-544a-b940-61034d8b270e",
-    "notes": [
-        "Tool for neologism extraction."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1174"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "BUSCANEO"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/67278893-3219-567e-babd-cc9dd6c13474.json b/oaitestdata/clarin-oai_dc/SET_1/json/67278893-3219-567e-babd-cc9dd6c13474.json
deleted file mode 100644
index d539a239..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/67278893-3219-567e-babd-cc9dd6c13474.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4006",
-    "MetadataAccess": [
-        "oai:ota:oucs:4006"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Colman, George, 1762-1836."
-    ],
-    "fulltext": "oai:ota:oucs:4006;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4006.xml;The iron chest: a play; in three acts. Written by George Colman, the younger. With a preface. First represented at the Theatre-Royal, Drury-Lane, on Saturday, 12th March, 1796.;Colman, George, 1762-1836.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "67278893-3219-567e-babd-cc9dd6c13474",
-    "oai_identifier": [
-        "oai:ota:oucs:4006"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The iron chest: a play; in three acts. Written by George Colman, the younger. With a preface. First represented at the Theatre-Royal, Drury-Lane, on Saturday, 12th March, 1796."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4006.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/67365bd4-9535-54ab-9adb-a936cdb7659e.json b/oaitestdata/clarin-oai_dc/SET_1/json/67365bd4-9535-54ab-9adb-a936cdb7659e.json
deleted file mode 100644
index 01266813..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/67365bd4-9535-54ab-9adb-a936cdb7659e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4203",
-    "MetadataAccess": [
-        "oai:ota:oucs:4203"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Kenrick, W. (William), 1725?-1779."
-    ],
-    "fulltext": "oai:ota:oucs:4203;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4203.xml;The spleen: or, the offspring of folly. A lyri-comi-tragic tale. In four cantos. ... Dedicated to George Colman, Esq. Author of the spleen, a comic piece, ...;Kenrick, W. (William), 1725?-1779.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "67365bd4-9535-54ab-9adb-a936cdb7659e",
-    "oai_identifier": [
-        "oai:ota:oucs:4203"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The spleen: or, the offspring of folly. A lyri-comi-tragic tale. In four cantos. ... Dedicated to George Colman, Esq. Author of the spleen, a comic piece, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4203.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6744bc1c-7547-56d9-8157-2fc8a2baa926.json b/oaitestdata/clarin-oai_dc/SET_1/json/6744bc1c-7547-56d9-8157-2fc8a2baa926.json
deleted file mode 100644
index a1597b5b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6744bc1c-7547-56d9-8157-2fc8a2baa926.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/559",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/559"
-    ],
-    "PID": "http://hdl.handle.net/11321/559",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "Bartosiak, Tomasz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/559;2018-07-26T10:46:42Z;hdl_11321_3;hdl_11321_4;Pred-A-tor;Bartosiak, Tomasz;Polish;constituency parsing;syntax-semantics interface;Tool for creating predicate-argument structures based on syntactic trees created by \u015awigra parser (http://zil.ipipan.waw.pl/%C5%9Awigra);2018;toolService;http://hdl.handle.net/11321/559;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;Institute of Computer Science, Polish Academy of Sciences",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6744bc1c-7547-56d9-8157-2fc8a2baa926",
-    "notes": [
-        "Tool for creating predicate-argument structures based on syntactic trees created by \u015awigra parser (http://zil.ipipan.waw.pl/%C5%9Awigra)"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/559"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Polish"
-        },
-        {
-            "name": "constituency parsing"
-        },
-        {
-            "name": "syntax-semantics interface"
-        }
-    ],
-    "title": [
-        "Pred-A-tor"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/674e87ca-5b2c-597b-8c8d-1b879020c3e0.json b/oaitestdata/clarin-oai_dc/SET_1/json/674e87ca-5b2c-597b-8c8d-1b879020c3e0.json
deleted file mode 100644
index d1a757bd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/674e87ca-5b2c-597b-8c8d-1b879020c3e0.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "ClarinPL"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 6",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/66",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/66"
-    ],
-    "PID": "http://hdl.handle.net/11321/66",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "ClarinPL"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Ba\u0142ucki, Ba\u0142ucki"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/66;2015-05-19T13:40:52Z;hdl_11321_3;hdl_11321_4;MWE Ba\u0142ucki;Ba\u0142ucki, Ba\u0142ucki;Ba\u0142ucki;2015-04-08;corpus;http://hdl.handle.net/11321/66;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 6;ClarinPL",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "674e87ca-5b2c-597b-8c8d-1b879020c3e0",
-    "notes": [
-        "Ba\u0142ucki"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/66"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Ba\u0142ucki"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/67624b5d-f989-52b7-b7c9-a6482ceb5855.json b/oaitestdata/clarin-oai_dc/SET_1/json/67624b5d-f989-52b7-b7c9-a6482ceb5855.json
deleted file mode 100644
index 47d2732d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/67624b5d-f989-52b7-b7c9-a6482ceb5855.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "University of York"
-    ],
-    "Contributor": [
-        "Pintzuk, Susan",
-        "Taylor, Ann",
-        "Beths, Frank",
-        "Warner, Anthony"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-901",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-901"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-901",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of York"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-901;2016-04-06T16:39:56Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;York-Toronto-Helsinki Parsed Corpus of Old English Prose (YCOE);Taylor, Ann;Warner, Anthony;Pintzuk, Susan;Beths, Frank;1.5 million word syntactically-annotated corpus of Old English prose texts;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-901;eng;downloadable_files_count: 0;United Kingdom;University of York;http://www-users.york.ac.uk/~lang22/YcoeHome1.htm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "67624b5d-f989-52b7-b7c9-a6482ceb5855",
-    "notes": [
-        "1.5 million word syntactically-annotated corpus of Old English prose texts"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-901"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "York-Toronto-Helsinki Parsed Corpus of Old English Prose (YCOE)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6787a265-1c70-5638-a0b7-051f9cf19d8f.json b/oaitestdata/clarin-oai_dc/SET_1/json/6787a265-1c70-5638-a0b7-051f9cf19d8f.json
deleted file mode 100644
index 54875d8f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6787a265-1c70-5638-a0b7-051f9cf19d8f.json
+++ /dev/null
@@ -1,90 +0,0 @@
-{
-    "Contact": [
-        "Bulgarian Academy of Sciences, IICT-BAS",
-        "University of the Basque Country, UPV/EHU",
-        "Faculty of Science, Univeristy of Lisbon, FCUL",
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Basque",
-        "Bulgarian",
-        "Czech",
-        "English",
-        "Portuguese",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1477",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1477"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1477",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Bulgarian Academy of Sciences, IICT-BAS",
-        "University of the Basque Country, UPV/EHU",
-        "Faculty of Science, Univeristy of Lisbon, FCUL",
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/610516"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Branco, Ant\u00f3nio",
-        "Simov, Kiril",
-        "Popel, Martin",
-        "Agirre, Eneko"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1477;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Europarl QTLeap WSD/NED corpus;Agirre, Eneko;Branco, Ant\u00f3nio;Popel, Martin;Simov, Kiril;annotated corpus;multilingual;This corpora is part of Deliverable 5.5 of the European Commission project QTLeap FP7-ICT-2013.4.1-610516 (http://qtleap.eu). \r\n\r\nThe texts are sentences from the Europarl parallel corpus (Koehn, 2005). We selected the monolingual sentences from parallel corpora for the following pairs: Bulgarian-English, Czech-English, Portuguese-English and Spanish-English. The English corpus is comprised by the English side of the Spanish-English corpus. \r\n\r\nBasque is not in Europarl. In addition, it contains the Basque and English sides of the GNOME corpus. \r\n\r\nThe texts have been automatically annotated with NLP tools, including Word Sense Disambiguation, Named Entity Disambiguation and Coreference resolution. Please check deliverable D5.6 in http://qtleap.eu/deliverables for more information.;2015;corpus;http://hdl.handle.net/11234/1-1477;eus;bul;ces;eng;por;spa;info:eu-repo/grantAgreement/EC/FP7/610516;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;text/plain; charset=utf-8;application/x-gzip;downloadable_files_count: 1;University of the Basque Country, UPV/EHU;Faculty of Science, Univeristy of Lisbon, FCUL;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);Bulgarian Academy of Sciences, IICT-BAS;http://qtleap.eu",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6787a265-1c70-5638-a0b7-051f9cf19d8f",
-    "notes": [
-        "This corpora is part of Deliverable 5.5 of the European Commission project QTLeap FP7-ICT-2013.4.1-610516 (http://qtleap.eu). \r\n\r\nThe texts are sentences from the Europarl parallel corpus (Koehn, 2005). We selected the monolingual sentences from parallel corpora for the following pairs: Bulgarian-English, Czech-English, Portuguese-English and Spanish-English. The English corpus is comprised by the English side of the Spanish-English corpus. \r\n\r\nBasque is not in Europarl. In addition, it contains the Basque and English sides of the GNOME corpus. \r\n\r\nThe texts have been automatically annotated with NLP tools, including Word Sense Disambiguation, Named Entity Disambiguation and Coreference resolution. Please check deliverable D5.6 in http://qtleap.eu/deliverables for more information."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1477"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "annotated corpus"
-        },
-        {
-            "name": "multilingual"
-        }
-    ],
-    "title": [
-        "Europarl QTLeap WSD/NED corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/67993fad-d1d6-543b-83e9-24dc5a7742fb.json b/oaitestdata/clarin-oai_dc/SET_1/json/67993fad-d1d6-543b-83e9-24dc5a7742fb.json
deleted file mode 100644
index d60490c5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/67993fad-d1d6-543b-83e9-24dc5a7742fb.json
+++ /dev/null
@@ -1,182 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/x-tar",
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Belarusian",
-        "Bosnian",
-        "Bulgarian",
-        "Czech",
-        "Croatian",
-        "Upper Sorbian",
-        "Macedonian",
-        "Polish",
-        "Russian",
-        "Slovak",
-        "Slovenian",
-        "Serbian",
-        "Ukrainian",
-        "Latvian",
-        "Lithuanian",
-        "Afrikaans",
-        "Danish",
-        "German",
-        "English",
-        "Faroese",
-        "Western Frisian",
-        "Swiss German",
-        "Icelandic",
-        "Limburgan",
-        "Luxembourgish",
-        "Low German",
-        "Dutch",
-        "Norwegian Nynorsk",
-        "Norwegian",
-        "Scots",
-        "Swedish",
-        "Yiddish",
-        "Aragonese",
-        "Asturian",
-        "Catalan",
-        "French",
-        "Galician",
-        "Haitian",
-        "Italian",
-        "Latin",
-        "Neapolitan",
-        "Portuguese",
-        "Romanian",
-        "Spanish",
-        "Walloon",
-        "Breton",
-        "Welsh",
-        "Scottish Gaelic",
-        "Irish",
-        "Modern Greek (1453-)",
-        "Armenian",
-        "Albanian",
-        "Persian",
-        "Kurdish",
-        "Tajik",
-        "Bengali",
-        "Gujarati",
-        "Hindi",
-        "Marathi",
-        "Nepali (macrolanguage)",
-        "Urdu",
-        "Amharic",
-        "Arabic",
-        "Hebrew",
-        "Estonian",
-        "Finnish",
-        "Hungarian",
-        "Basque",
-        "Georgian",
-        "Chuvash",
-        "Azerbaijani",
-        "Turkish",
-        "Uzbek",
-        "Kazakh",
-        "Tatar",
-        "Yakut",
-        "Korean",
-        "Mongolian",
-        "Telugu",
-        "Kannada",
-        "Malayalam",
-        "Tamil",
-        "Newari",
-        "Vietnamese",
-        "Indonesian",
-        "Javanese",
-        "Malagasy",
-        "Maori",
-        "Malay (macrolanguage)",
-        "Pampanga",
-        "Sundanese",
-        "Tagalog",
-        "Waray (Philippines)",
-        "Swahili (macrolanguage)",
-        "Esperanto",
-        "Ido",
-        "Interlingua (International Auxiliary Language Association)",
-        "Volap\u00fck"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1743",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1743"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1743",
-    "PublicationTimestamp": "2016-06-20T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-1662"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "Yu, Zhiwei",
-        "Zeman, Daniel",
-        "Mare\u010dek, David"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1743;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Deltacorpus 1.1;Mare\u010dek, David;Yu, Zhiwei;Zeman, Daniel;\u017dabokrtsk\u00fd, Zden\u011bk;part of speech;tagging;semi-supervised;cross-language;Texts in 107 languages from the W2C corpus (http://hdl.handle.net/11858/00-097C-0000-0022-6133-9), first 1,000,000 tokens per language, tagged by the delexicalized tagger described in Yu et al. (2016, LREC, Portoro\u017e, Slovenia).\r\n\r\nChanges in version 1.1: \r\n\r\n1. Universal Dependencies tagset instead of the older and smaller Google Universal POS tagset. \r\n\r\n2. SVM classifier trained on Universal Dependencies 1.2 instead of HamleDT 2.0. \r\n\r\n3. Balto-Slavic languages, Germanic languages and Romance languages were tagged by classifier trained only on the respective group of languages. Other languages were tagged by a classifier trained on all available languages. The \"c7\" combination from version 1.0 is no longer used.;2016-06-20;corpus;http://hdl.handle.net/11234/1-1743;bel;bos;bul;ces;hbs;hrv;hsb;mkd;pol;rus;slk;slv;srp;ukr;lav;lit;afr;dan;deu;eng;fao;fry;gsw;isl;lim;ltz;nds;nld;nno;nor;sco;swe;yid;arg;ast;cat;fra;glg;hat;ita;lat;lmo;nap;pms;por;ron;spa;vec;wln;bre;cym;gla;gle;ell;hye;sqi;diq;fas;glk;kur;tgk;ben;bpy;guj;hif;hin;mar;nep;urd;amh;ara;arz;heb;est;fin;hun;eus;kat;chv;aze;tur;uzb;kaz;tat;sah;kor;mon;tel;kan;mal;tam;new;vie;ind;jav;mlg;mri;msa;pam;sun;tgl;war;swa;epo;ido;ina;vol;http://hdl.handle.net/11234/1-1662;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;PUB;application/x-tar;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/deltacorpus",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "67993fad-d1d6-543b-83e9-24dc5a7742fb",
-    "notes": [
-        "Texts in 107 languages from the W2C corpus (http://hdl.handle.net/11858/00-097C-0000-0022-6133-9), first 1,000,000 tokens per language, tagged by the delexicalized tagger described in Yu et al. (2016, LREC, Portoro\u017e, Slovenia).\r\n\r\nChanges in version 1.1: \r\n\r\n1. Universal Dependencies tagset instead of the older and smaller Google Universal POS tagset. \r\n\r\n2. SVM classifier trained on Universal Dependencies 1.2 instead of HamleDT 2.0. \r\n\r\n3. Balto-Slavic languages, Germanic languages and Romance languages were tagged by classifier trained only on the respective group of languages. Other languages were tagged by a classifier trained on all available languages. The \"c7\" combination from version 1.0 is no longer used."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1743"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "part speech"
-        },
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "semi-supervised"
-        },
-        {
-            "name": "cross-language"
-        }
-    ],
-    "title": [
-        "Deltacorpus 1.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/67a91577-a4ed-5ebd-b8ab-a9d3bf022ef0.json b/oaitestdata/clarin-oai_dc/SET_1/json/67a91577-a4ed-5ebd-b8ab-a9d3bf022ef0.json
deleted file mode 100644
index 6abbf627..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/67a91577-a4ed-5ebd-b8ab-a9d3bf022ef0.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3846",
-    "MetadataAccess": [
-        "oai:ota:oucs:3846"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Sharp, Granville, 1735-1813."
-    ],
-    "fulltext": "oai:ota:oucs:3846;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3846.xml;An appendix to the Representation: (printed in the year 1769,) of the injustice and dangerous tendency of tolerating slavery, or of admitting the least claim of private property in the persons of men in England. By Granville Sharp.;Sharp, Granville, 1735-1813.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "67a91577-a4ed-5ebd-b8ab-a9d3bf022ef0",
-    "oai_identifier": [
-        "oai:ota:oucs:3846"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An appendix to the Representation: (printed in the year 1769,) of the injustice and dangerous tendency of tolerating slavery, or of admitting the least claim of private property in the persons of men in England. By Granville Sharp."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3846.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/67aae7c3-51a0-5aca-a37a-ac4296599135.json b/oaitestdata/clarin-oai_dc/SET_1/json/67aae7c3-51a0-5aca-a37a-ac4296599135.json
deleted file mode 100644
index 88f84f06..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/67aae7c3-51a0-5aca-a37a-ac4296599135.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "http://clarino.uib.no/iness/"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Norwegian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/90",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/90"
-    ],
-    "PID": "http://hdl.handle.net/11509/90",
-    "PublicationTimestamp": "2015-08-17T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "http://clarino.uib.no/iness/"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "author": [
-        "Ros\u00e9n, Victoria"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/90;2016-04-15T05:59:21Z;hdl_11509_1;hdl_11509_2;INESS list of lexical units unknown to the NorGram lexicon;Ros\u00e9n, Victoria;Lexical Conceptual Resource;In the INESS project, Norwegian texts in Norwegian Bokm\u00e5l and Nynorsk are parsed with the NorGram grammar and lexicon. When text is parsed, there will always be words that are unknown to the morphological analyzer and/or the lexicon. INESS has therefore developed an intelligent browser-based preprocessing interface which facilitates, among other things, the efficient treatment of unknown word forms. The list of word forms that have not been automatically recognized are manually inspected.\r\nWhile some of these result from OCR errors and others are simply typos, most unrecognized word forms are productive compounds, words only occurring in MWEs, names, foreign words, neologisms, interjections, dialect words, and systematic, or intended, misspellings. To read more about the types of lexical units registered, please refer to the documentation at http://clarino.uib.no/iness/page?page-id=Text_preprocessing.;2015-08-17;lexicalConceptualResource;http://hdl.handle.net/11509/90;nor;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;http://clarino.uib.no/iness/;http://clarino.uib.no/iness/page",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "67aae7c3-51a0-5aca-a37a-ac4296599135",
-    "notes": [
-        "In the INESS project, Norwegian texts in Norwegian Bokm\u00e5l and Nynorsk are parsed with the NorGram grammar and lexicon. When text is parsed, there will always be words that are unknown to the morphological analyzer and/or the lexicon. INESS has therefore developed an intelligent browser-based preprocessing interface which facilitates, among other things, the efficient treatment of unknown word forms. The list of word forms that have not been automatically recognized are manually inspected.\r\nWhile some of these result from OCR errors and others are simply typos, most unrecognized word forms are productive compounds, words only occurring in MWEs, names, foreign words, neologisms, interjections, dialect words, and systematic, or intended, misspellings. To read more about the types of lexical units registered, please refer to the documentation at http://clarino.uib.no/iness/page?page-id=Text_preprocessing."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/90"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Lexical Conceptual Resource"
-        }
-    ],
-    "title": [
-        "INESS list of lexical units unknown to the NorGram lexicon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/67d9a783-a8ac-5f8c-a647-14398592cca8.json b/oaitestdata/clarin-oai_dc/SET_1/json/67d9a783-a8ac-5f8c-a647-14398592cca8.json
deleted file mode 100644
index a4f5a60f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/67d9a783-a8ac-5f8c-a647-14398592cca8.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "University of Oslo"
-    ],
-    "Contributor": [
-        "Wet\u00e5s, \u00c5se"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Norwegian",
-        "Norwegian Nynorsk"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-671",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-671"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-671",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Oslo"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-671;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Norsk ordbok;Wet\u00e5s, \u00c5se;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-671;nor;nno;downloadable_files_count: 0;University of Oslo;http://no2014.uio.no/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "67d9a783-a8ac-5f8c-a647-14398592cca8",
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-671"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Norsk ordbok"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/67e14818-2b88-59a8-ad6b-7d2ac0b834cd.json b/oaitestdata/clarin-oai_dc/SET_1/json/67e14818-2b88-59a8-ad6b-7d2ac0b834cd.json
deleted file mode 100644
index cd81a8db..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/67e14818-2b88-59a8-ad6b-7d2ac0b834cd.json
+++ /dev/null
@@ -1,94 +0,0 @@
-{
-    "Contact": [
-        "Insight Centre for Data Analytics, National University of Ireland, Galway"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Slovenian",
-        "Serbian",
-        "German",
-        "Spanish",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1065",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1065"
-    ],
-    "PID": "http://hdl.handle.net/11356/1065",
-    "PublicationTimestamp": "2016-05-24T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Insight Centre for Data Analytics, National University of Ireland, Galway"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/H2020/644333",
-        "http://www.lrec-conf.org/proceedings/lrec2016/summaries/405.html"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "https://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Popovi\u0107, Maja",
-        "Ar\u010dan, Mihael"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1065;2018-02-28T10:30:56Z;hdl_11356_1023;hdl_11356_1024;Post-edited and error annotated machine translation corpus PErr 1.0;Popovi\u0107, Maja;Ar\u010dan, Mihael;parallel corpus;machine translation;post-editing;error annotation;manual annotation;multilingual;The PE\u00b2rr corpus contains source language texts from different domains along with their automatically generated translations into several morphologically rich languages, their post-edited versions, and error annotations of the performed post-edit operations. The main advantage of the corpus is the fusion of post-editing and error classification tasks, which have usually been seen as two independent tasks, although naturally they are not.;2016-05-24;corpus;http://hdl.handle.net/11356/1065;slv;srp;deu;spa;eng;info:eu-repo/grantAgreement/EC/H2020/644333;http://www.lrec-conf.org/proceedings/lrec2016/summaries/405.html;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);https://creativecommons.org/licenses/by-sa/4.0/;PUB;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;Insight Centre for Data Analytics, National University of Ireland, Galway;http://nlp.insight-centre.org/research/resources/pe2rr/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "67e14818-2b88-59a8-ad6b-7d2ac0b834cd",
-    "notes": [
-        "The PE\u00b2rr corpus contains source language texts from different domains along with their automatically generated translations into several morphologically rich languages, their post-edited versions, and error annotations of the performed post-edit operations. The main advantage of the corpus is the fusion of post-editing and error classification tasks, which have usually been seen as two independent tasks, although naturally they are not."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1065"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parallel corpus"
-        },
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "post-editing"
-        },
-        {
-            "name": "error annotation"
-        },
-        {
-            "name": "manual annotation"
-        },
-        {
-            "name": "multilingual"
-        }
-    ],
-    "title": [
-        "Post-edited and error annotated machine translation corpus PErr 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/67ee958c-3068-5231-b33d-a0ddc88e256e.json b/oaitestdata/clarin-oai_dc/SET_1/json/67ee958c-3068-5231-b33d-a0ddc88e256e.json
deleted file mode 100644
index 53cc9968..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/67ee958c-3068-5231-b33d-a0ddc88e256e.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Frisian Academy"
-    ],
-    "Contributor": [
-        "Siebinga, Sjoerd"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-881",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-881"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-881",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Frisian Academy"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-881;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Old Frisian corpus;Siebinga, Sjoerd;We are presently collecting Old Frisian texts, and we will start on the construction of an Old Frisian corpus in the near future.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-881;downloadable_files_count: 0;Netherlands (the);Frisian Academy;http://www.fa.knaw.nl/fa/3departments-and-disciplines/department-of-linguistics/taalkorpora_en_/frisian-language-corpus",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "67ee958c-3068-5231-b33d-a0ddc88e256e",
-    "notes": [
-        "We are presently collecting Old Frisian texts, and we will start on the construction of an Old Frisian corpus in the near future."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-881"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Old Frisian corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/68041a03-e765-5d02-af49-38e2446b86a6.json b/oaitestdata/clarin-oai_dc/SET_1/json/68041a03-e765-5d02-af49-38e2446b86a6.json
deleted file mode 100644
index d8cf7f22..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/68041a03-e765-5d02-af49-38e2446b86a6.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "University of Sheffield"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 3"
-    ],
-    "Language": [
-        "English",
-        "German",
-        "Czech",
-        "Latvian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2805",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2805"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2805",
-    "PublicationTimestamp": "2018-05-21T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "University of Sheffield"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/H2020/645452",
-        "http://hdl.handle.net/11372/LRT-2135"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "AGREEMENT ON THE USE OF DATA IN QT21",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21",
-        "PUB"
-    ],
-    "author": [
-        "Fernandez, Ramon",
-        "Martins, Andr\u00e9",
-        "Logacheva, Varvara",
-        "Specia, Lucia",
-        "Blain, Frederic"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2805;2018-05-21T15:23:41Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;WMT18 Quality Estimation Shared Task Test Data;Specia, Lucia;Logacheva, Varvara;Blain, Frederic;Fernandez, Ramon;Martins, Andr\u00e9;machine translation;quality estimation;machine learning;Test data for the WMT18 QE task. Train data can be downloaded from http://hdl.handle.net/11372/LRT-2619.\r\n\r\nThis shared task will build on its previous six editions to further examine automatic methods for estimating the quality of machine translation output at run-time, without relying on reference translations. We include word-level, phrase-level and sentence-level estimation. All tasks make use of datasets produced from post-editions by professional translators. The datasets are domain-specific (IT and life sciences/pharma domains) and extend from those used previous years with more instances and more languages. One important addition is that this year we also include datasets with neural MT outputs. In addition to advancing the state of the art at all prediction levels, our specific goals are:\r\n\r\nTo study the performance of quality estimation approaches on the output of neural MT systems. We will do so by providing datasets for two language language pairs where the same source segments are translated by both a statistical phrase-based and a neural MT system.\r\n\r\nTo study the predictability of deleted words, i.e. words that are missing in the MT output. TO do so, for the first time we provide data annotated for such errors at training time.\r\n\r\nTo study the effectiveness of explicitly assigned labels for phrases. We will do so by providing a dataset where each phrase in the output of a phrase-based statistical MT system was annotated by human translators.\r\n\r\nTo study the effect of different language pairs. We will do so by providing datasets created in similar ways for four language language pairs.\r\n\r\nTo investigate the utility of detailed information logged during post-editing. We will do so by providing post-editing time, keystrokes, and actual edits.\r\n\r\nMeasure progress over years at all prediction levels. We will do so by using last year's test set for comparative experiments.\r\n\r\nIn-house statistical and neural MT systems were built to produce translations for all tasks. MT system-dependent information can be made available under request. The data is publicly available but since it has been provided by our industry partners it is subject to specific terms and conditions. However, these have no practical implications on the use of this data for research purposes. Participants are allowed to explore any additional data and resources deemed relevant.;2018-05-21;corpus;http://hdl.handle.net/11372/LRT-2805;eng;deu;ces;lav;info:eu-repo/grantAgreement/EC/H2020/645452;http://hdl.handle.net/11372/LRT-2135;AGREEMENT ON THE USE OF DATA IN QT21;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21;PUB;application/x-gzip;application/x-gzip;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 3;University of Sheffield;http://www.statmt.org/wmt18/quality-estimation-task.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "68041a03-e765-5d02-af49-38e2446b86a6",
-    "notes": [
-        "Test data for the WMT18 QE task. Train data can be downloaded from http://hdl.handle.net/11372/LRT-2619.\r\n\r\nThis shared task will build on its previous six editions to further examine automatic methods for estimating the quality of machine translation output at run-time, without relying on reference translations. We include word-level, phrase-level and sentence-level estimation. All tasks make use of datasets produced from post-editions by professional translators. The datasets are domain-specific (IT and life sciences/pharma domains) and extend from those used previous years with more instances and more languages. One important addition is that this year we also include datasets with neural MT outputs. In addition to advancing the state of the art at all prediction levels, our specific goals are:\r\n\r\nTo study the performance of quality estimation approaches on the output of neural MT systems. We will do so by providing datasets for two language language pairs where the same source segments are translated by both a statistical phrase-based and a neural MT system.\r\n\r\nTo study the predictability of deleted words, i.e. words that are missing in the MT output. TO do so, for the first time we provide data annotated for such errors at training time.\r\n\r\nTo study the effectiveness of explicitly assigned labels for phrases. We will do so by providing a dataset where each phrase in the output of a phrase-based statistical MT system was annotated by human translators.\r\n\r\nTo study the effect of different language pairs. We will do so by providing datasets created in similar ways for four language language pairs.\r\n\r\nTo investigate the utility of detailed information logged during post-editing. We will do so by providing post-editing time, keystrokes, and actual edits.\r\n\r\nMeasure progress over years at all prediction levels. We will do so by using last year's test set for comparative experiments.\r\n\r\nIn-house statistical and neural MT systems were built to produce translations for all tasks. MT system-dependent information can be made available under request. The data is publicly available but since it has been provided by our industry partners it is subject to specific terms and conditions. However, these have no practical implications on the use of this data for research purposes. Participants are allowed to explore any additional data and resources deemed relevant."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2805"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "quality estimation"
-        },
-        {
-            "name": "machine learning"
-        }
-    ],
-    "title": [
-        "WMT18 Quality Estimation Shared Task Test Data"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/680ea6fe-0a89-5a2d-8a65-c356a3a50358.json b/oaitestdata/clarin-oai_dc/SET_1/json/680ea6fe-0a89-5a2d-8a65-c356a3a50358.json
deleted file mode 100644
index d5aaa585..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/680ea6fe-0a89-5a2d-8a65-c356a3a50358.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1043",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1043"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1043",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1043;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;L2 Acquisition Ursula Stephany & Christine Dimroth;Language Acquisition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1043;deu;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI27095%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "680ea6fe-0a89-5a2d-8a65-c356a3a50358",
-    "notes": [
-        "Language Acquisition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1043"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "L2 Acquisition Ursula Stephany & Christine Dimroth"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6824536a-bf0b-58c2-b5b8-28f5203bc64f.json b/oaitestdata/clarin-oai_dc/SET_1/json/6824536a-bf0b-58c2-b5b8-28f5203bc64f.json
deleted file mode 100644
index bddd6e7c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6824536a-bf0b-58c2-b5b8-28f5203bc64f.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "McMahon, Kenneth"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain",
-        "(1 file : ca. 53 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1711",
-    "MetadataAccess": [
-        "oai:ota:oucs:1711"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Van Dyke, Henry, 1852-1933"
-    ],
-    "fulltext": "oai:ota:oucs:1711;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1711.xml;The story of the other wise man / by Henry Van Dyke;Van Dyke, Henry, 1852-1933;text_and_corpus_linguistics;American fiction -- 20th century;Oxford Text Archive, University of Oxford;McMahon, Kenneth;text/plain;(1 file : ca. 53 KB);Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6824536a-bf0b-58c2-b5b8-28f5203bc64f",
-    "oai_identifier": [
-        "oai:ota:oucs:1711"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "American fiction -- th century"
-        }
-    ],
-    "title": [
-        "The story of the other wise man / by Henry Van Dyke"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1711.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6849b5f3-8599-5e1b-a7ba-19a7a2502dc8.json b/oaitestdata/clarin-oai_dc/SET_1/json/6849b5f3-8599-5e1b-a7ba-19a7a2502dc8.json
deleted file mode 100644
index 5afd00a4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6849b5f3-8599-5e1b-a7ba-19a7a2502dc8.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "European Commission",
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 6",
-        "text/xml",
-        "application/pdf",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Danish",
-        "English",
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repository.clarin.dk:20.500.12115/28",
-    "MetadataAccess": [
-        "oai:repository.clarin.dk:20.500.12115/28"
-    ],
-    "PID": "http://hdl.handle.net/20.500.12115/28",
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "European Commission",
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN-ACA-NC",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NC=1&NORED=1",
-        "ACA"
-    ],
-    "author": [
-        "Hansen, Dorte Haltrup",
-        "Offersgaard, Lene"
-    ],
-    "fulltext": "oai:repository.clarin.dk:20.500.12115/28;2018-06-28T13:28:19Z;hdl_20.500.12115_1;hdl_20.500.12115_3;DK-CLARIN Rapid Parallel Corpus 1993-2003 (da-en-de);Hansen, Dorte Haltrup;Offersgaard, Lene;press relase;politics;EU;The corpus consists of press releases from the European Commission Press Relase Database (Rapid) harvested in 2009 (http://europa.eu/rapid/search.htm).\r\nEach of the 5330 press releases (files) exist in Danish, English and German with app. 3,000,000 words for each language.\r\nAll texts are in XML TEIP5 format (TEIP5DKCLARIN-format), the Danish and English texts with tokenisation, pos-tagging, sentence and paragraph segmentation, lemmatisation and termhood annotation, and the German texts  with tokenisation sentence and paragraph segmentation.\r\nThe annotations are placed in separate text external spangroups.\r\nThe corpus was collected and processed in the work package 2.6 of the Danish CLARIN project (see http://dkclarin.ku.dk/english) by University of Copenhagen, Centre for Language Technology.\r\nThe aim of the Danish CLARIN consortium was to construct a Danish research infrastructure for the humanities integrating written, spoken, and visual records into a coherent and systematic digital repository. \r\nThe project ran from January 2008 until the end of 2010.;2011;corpus;http://hdl.handle.net/20.500.12115/28;dan;eng;deu;CLARIN-ACA-NC;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NC=1&NORED=1;ACA;application/zip;application/zip;application/zip;text/xml;application/pdf;application/pdf;text/plain; charset=utf-8;downloadable_files_count: 6;Centre for Language Technology, NorS, University of Copenhagen;European Commission",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6849b5f3-8599-5e1b-a7ba-19a7a2502dc8",
-    "notes": [
-        "The corpus consists of press releases from the European Commission Press Relase Database (Rapid) harvested in 2009 (http://europa.eu/rapid/search.htm).\r\nEach of the 5330 press releases (files) exist in Danish, English and German with app. 3,000,000 words for each language.\r\nAll texts are in XML TEIP5 format (TEIP5DKCLARIN-format), the Danish and English texts with tokenisation, pos-tagging, sentence and paragraph segmentation, lemmatisation and termhood annotation, and the German texts  with tokenisation sentence and paragraph segmentation.\r\nThe annotations are placed in separate text external spangroups.\r\nThe corpus was collected and processed in the work package 2.6 of the Danish CLARIN project (see http://dkclarin.ku.dk/english) by University of Copenhagen, Centre for Language Technology.\r\nThe aim of the Danish CLARIN consortium was to construct a Danish research infrastructure for the humanities integrating written, spoken, and visual records into a coherent and systematic digital repository. \r\nThe project ran from January 2008 until the end of 2010."
-    ],
-    "oai_identifier": [
-        "oai:repository.clarin.dk:20.500.12115/28"
-    ],
-    "oai_set": [
-        "hdl_20.500.12115_1",
-        "hdl_20.500.12115_3"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "press relase"
-        },
-        {
-            "name": "politics"
-        },
-        {
-            "name": "EU"
-        }
-    ],
-    "title": [
-        "DK-CLARIN Rapid Parallel Corpus 1993-2003 (da-en-de)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/688f71af-6458-5bd2-83a2-700142dbf6ba.json b/oaitestdata/clarin-oai_dc/SET_1/json/688f71af-6458-5bd2-83a2-700142dbf6ba.json
deleted file mode 100644
index 944286cf..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/688f71af-6458-5bd2-83a2-700142dbf6ba.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2690",
-    "MetadataAccess": [
-        "oai:ota:oucs:2690"
-    ],
-    "PublicationTimestamp": "1727-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1727"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2690;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2690.xml;A vindication of Isaac Bickerstaff;Swift, Jonathan, 1667-1745;1727;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "688f71af-6458-5bd2-83a2-700142dbf6ba",
-    "oai_identifier": [
-        "oai:ota:oucs:2690"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A vindication of Isaac Bickerstaff"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2690.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/68a951ca-9346-5a2e-9fde-1d86a7c6c0eb.json b/oaitestdata/clarin-oai_dc/SET_1/json/68a951ca-9346-5a2e-9fde-1d86a7c6c0eb.json
deleted file mode 100644
index 05e67d79..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/68a951ca-9346-5a2e-9fde-1d86a7c6c0eb.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Smith, John B."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 374 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1634",
-    "MetadataAccess": [
-        "oai:ota:oucs:1634"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Plath, Sylvia"
-    ],
-    "fulltext": "oai:ota:oucs:1634;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1634.xml;The bell jar / Sylvia Plath;Plath, Sylvia;text_and_corpus_linguistics;English literature -- 20th century;Oxford Text Archive, University of Oxford;Smith, John B.;text/sgml;(1 file : ca. 374 KB);Text;Novels;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "68a951ca-9346-5a2e-9fde-1d86a7c6c0eb",
-    "oai_identifier": [
-        "oai:ota:oucs:1634"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English literature -- th century"
-        }
-    ],
-    "title": [
-        "The bell jar / Sylvia Plath"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1634.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/68b025b9-f57e-5aa7-a264-2b6ea7f82041.json b/oaitestdata/clarin-oai_dc/SET_1/json/68b025b9-f57e-5aa7-a264-2b6ea7f82041.json
deleted file mode 100644
index 194ffdeb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/68b025b9-f57e-5aa7-a264-2b6ea7f82041.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "less than 512 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1222",
-    "MetadataAccess": [
-        "oai:ota:oucs:1222"
-    ],
-    "PublicationTimestamp": "1980-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1980"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dailey, Janet"
-    ],
-    "fulltext": "oai:ota:oucs:1222;2018-03-05T15:14:52Z;http://ota.ox.ac.uk/headers/1222.xml;The thawing of Mara / compiled by Elaine Vail and Sebastian Rahtz;Dailey, Janet;1980;text_and_corpus_linguistics;Novels -- United States -- 20th century;eng;Oxford Text Archive, University of Oxford;less than 512 KB;Text;Novels;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "68b025b9-f57e-5aa7-a264-2b6ea7f82041",
-    "oai_identifier": [
-        "oai:ota:oucs:1222"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Novels -- United States -- th century"
-        }
-    ],
-    "title": [
-        "The thawing of Mara / compiled by Elaine Vail and Sebastian Rahtz"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1222.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/68b1d1b7-3646-5a7d-be2d-80920f4ef287.json b/oaitestdata/clarin-oai_dc/SET_1/json/68b1d1b7-3646-5a7d-be2d-80920f4ef287.json
deleted file mode 100644
index fb45502b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/68b1d1b7-3646-5a7d-be2d-80920f4ef287.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Krzemieniecka"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 4",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/81",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/81"
-    ],
-    "PID": "http://hdl.handle.net/11321/81",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Krzemieniecka"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Krzemieniecka, Krzemieniecka"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/81;2015-06-08T10:37:01Z;hdl_11321_3;hdl_11321_4;MWE Krzemieniecka;Krzemieniecka, Krzemieniecka;Krzemieniecka;2015-04-08;corpus;http://hdl.handle.net/11321/81;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;application/zip;text/plain; charset=utf-8;downloadable_files_count: 4;Krzemieniecka",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "68b1d1b7-3646-5a7d-be2d-80920f4ef287",
-    "notes": [
-        "Krzemieniecka"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/81"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Krzemieniecka"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/68b863e4-6e86-5abb-bd77-e298c523e4ea.json b/oaitestdata/clarin-oai_dc/SET_1/json/68b863e4-6e86-5abb-bd77-e298c523e4ea.json
deleted file mode 100644
index 45df9576..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/68b863e4-6e86-5abb-bd77-e298c523e4ea.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=ec6368e0408311e2a2aa782bcb07413599aab1f1d40746118b407fb829dd4977",
-    "MetadataAccess": [
-        "ec6368e0408311e2a2aa782bcb07413599aab1f1d40746118b407fb829dd4977"
-    ],
-    "PublicationTimestamp": "2013-01-31T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "ec6368e0408311e2a2aa782bcb07413599aab1f1d40746118b407fb829dd4977;2018-11-15T16:39:55Z;corpus;corpus:text;MLRS Corpus;142,397 Maltese texts from 10 genres.\n\nThe file \u00e2\u0080\u009ccorpus.zip\u00e2\u0080\u009d expands into a folder \u00e2\u0080\u009ccorpus\u00e2\u0080\u009d, containing the file \u00e2\u0080\u009ctagged.zip\u00e2\u0080\u009d, which expands into the folder \u00e2\u0080\u009ccwb.final\u00e2\u0080\u009d. This folder contains the files:\n\u00e2\u0080\u00a2\tfilelist.txt\n\u00e2\u0080\u00a2\tmalti02.academic.txt\n\u00e2\u0080\u00a2\tmalti02.law.txt\n\u00e2\u0080\u00a2\tmalti02.literature.txt\n\u00e2\u0080\u00a2\tmalti02.metadata.txt\n\u00e2\u0080\u00a2\tmalti02.misc.txt\n\u00e2\u0080\u00a2\tmalti02.parl.txt\n\u00e2\u0080\u00a2\tmalti02.parl.txt.bak\n\u00e2\u0080\u00a2\tmalti02.press.txt\n\u00e2\u0080\u00a2\tmalti02.religion.txt\n\u00e2\u0080\u00a2\tmalti02.speeches.txt\n\u00e2\u0080\u00a2\tmalti02.web.genral.txt\n\u00e2\u0080\u00a2\tmalti02.web.wiki.txt\n\u00e2\u0080\u00a2\tREADME.txt\n\u00e2\u0080\u00a2\tremoved-from-corpus.txt\n\u00e2\u0080\u00a2\ttend.txt\n\u00e2\u0080\u00a2\ttstart.txt\n\nAll texts of a genre are in one .txt file for that genre. In this file,  texts are marked with the XML tags <t>\u00e2\u0080\u00a6</t>, paragraphs are marked <p>\u00e2\u0080\u00a6</p>, sentences are marked <s>\u00e2\u0080\u00a6</s>, and one word per line, followed by a tab and its POS tag. ;2013-01-31",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "68b863e4-6e86-5abb-bd77-e298c523e4ea",
-    "notes": [
-        "142,397 Maltese texts from 10 genres.\n\nThe file \u00e2\u0080\u009ccorpus.zip\u00e2\u0080\u009d expands into a folder \u00e2\u0080\u009ccorpus\u00e2\u0080\u009d, containing the file \u00e2\u0080\u009ctagged.zip\u00e2\u0080\u009d, which expands into the folder \u00e2\u0080\u009ccwb.final\u00e2\u0080\u009d. This folder contains the files:\n\u00e2\u0080\u00a2\tfilelist.txt\n\u00e2\u0080\u00a2\tmalti02.academic.txt\n\u00e2\u0080\u00a2\tmalti02.law.txt\n\u00e2\u0080\u00a2\tmalti02.literature.txt\n\u00e2\u0080\u00a2\tmalti02.metadata.txt\n\u00e2\u0080\u00a2\tmalti02.misc.txt\n\u00e2\u0080\u00a2\tmalti02.parl.txt\n\u00e2\u0080\u00a2\tmalti02.parl.txt.bak\n\u00e2\u0080\u00a2\tmalti02.press.txt\n\u00e2\u0080\u00a2\tmalti02.religion.txt\n\u00e2\u0080\u00a2\tmalti02.speeches.txt\n\u00e2\u0080\u00a2\tmalti02.web.genral.txt\n\u00e2\u0080\u00a2\tmalti02.web.wiki.txt\n\u00e2\u0080\u00a2\tREADME.txt\n\u00e2\u0080\u00a2\tremoved-from-corpus.txt\n\u00e2\u0080\u00a2\ttend.txt\n\u00e2\u0080\u00a2\ttstart.txt\n\nAll texts of a genre are in one .txt file for that genre. In this file,  texts are marked with the XML tags <t>\u00e2\u0080\u00a6</t>, paragraphs are marked <p>\u00e2\u0080\u00a6</p>, sentences are marked <s>\u00e2\u0080\u00a6</s>, and one word per line, followed by a tab and its POS tag. "
-    ],
-    "oai_identifier": [
-        "ec6368e0408311e2a2aa782bcb07413599aab1f1d40746118b407fb829dd4977"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "MLRS Corpus"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/68ba9c5a-f60d-5a1d-b299-2b1c492f09cc.json b/oaitestdata/clarin-oai_dc/SET_1/json/68ba9c5a-f60d-5a1d-b299-2b1c492f09cc.json
deleted file mode 100644
index 14ce55d0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/68ba9c5a-f60d-5a1d-b299-2b1c492f09cc.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3184",
-    "MetadataAccess": [
-        "oai:ota:oucs:3184"
-    ],
-    "PublicationTimestamp": "1550-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1550"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Sherry, Richard, ca. 1506-ca. 1555"
-    ],
-    "fulltext": "oai:ota:oucs:3184;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3184.xml;A treatise of schemes & tropes: very profytable for the better understanding of good authors, gathered out of the best grammarians & oratours ;Sherry, Richard, ca. 1506-ca. 1555;not after: 1550;text_and_corpus_linguistics;Textbooks -- England -- 16th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "68ba9c5a-f60d-5a1d-b299-2b1c492f09cc",
-    "oai_identifier": [
-        "oai:ota:oucs:3184"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Textbooks -- England -- th century"
-        }
-    ],
-    "title": [
-        "A treatise of schemes & tropes: very profytable for the better understanding of good authors, gathered out of the best grammarians & oratours "
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3184.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/68e5d1ac-ccd5-581f-8a86-50228e42ab91.json b/oaitestdata/clarin-oai_dc/SET_1/json/68e5d1ac-ccd5-581f-8a86-50228e42ab91.json
deleted file mode 100644
index e4a9692d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/68e5d1ac-ccd5-581f-8a86-50228e42ab91.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 93.7 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1640",
-    "MetadataAccess": [
-        "oai:ota:oucs:1640"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Spenser, Edmund, 1552?-1599"
-    ],
-    "fulltext": "oai:ota:oucs:1640;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/1640.xml;Amoretti and Epithalamion / written not long since by Edmunde Spenser;Spenser, Edmund, 1552?-1599;default: 1976-01-01;text_and_corpus_linguistics;Poems -- England -- 16th century;eng;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 93.7 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "68e5d1ac-ccd5-581f-8a86-50228e42ab91",
-    "oai_identifier": [
-        "oai:ota:oucs:1640"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- England -- th century"
-        }
-    ],
-    "title": [
-        "Amoretti and Epithalamion / written not long since by Edmunde Spenser"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1640.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/68f0123b-5efe-5ecf-ba65-4d3a01e3db3d.json b/oaitestdata/clarin-oai_dc/SET_1/json/68f0123b-5efe-5ecf-ba65-4d3a01e3db3d.json
deleted file mode 100644
index 984baf6c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/68f0123b-5efe-5ecf-ba65-4d3a01e3db3d.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "MASt"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 71",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/151",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/151"
-    ],
-    "PID": "http://hdl.handle.net/11321/151",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "MASt"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/3.0/",
-        "CC"
-    ],
-    "author": [
-        "MASt, S"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/151;2015-04-13T20:07:18Z;hdl_11321_3;hdl_11321_4;Przeglad Wszechpolski 02/1900;MASt, S;skany Przegl\u0105du Wszechpolskiego;2015;corpus;http://hdl.handle.net/11321/151;pol;Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0);http://creativecommons.org/licenses/by-nc-nd/3.0/;CC;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 71;MASt",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "68f0123b-5efe-5ecf-ba65-4d3a01e3db3d",
-    "notes": [
-        "skany Przegl\u0105du Wszechpolskiego"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/151"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Przeglad Wszechpolski 02/1900"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/68f86e37-a22c-518d-ba06-8194c02ea0d3.json b/oaitestdata/clarin-oai_dc/SET_1/json/68f86e37-a22c-518d-ba06-8194c02ea0d3.json
deleted file mode 100644
index 7e306648..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/68f86e37-a22c-518d-ba06-8194c02ea0d3.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "less than 512 KB"
-    ],
-    "Language": [
-        "Welsh"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1401",
-    "MetadataAccess": [
-        "oai:ota:oucs:1401"
-    ],
-    "PublicationYear": [
-        "Unspecified"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Romances"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:1401;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1401.xml; Ronabwy  : [from] Llyfr Gwyn Rhydderch / compiled by Nancy H. Rose;Unspecified;text_and_corpus_linguistics;Myths and legends -- Wales;Romances -- Wales;cym;Oxford Text Archive, University of Oxford;less than 512 KB;Text;Romances;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "68f86e37-a22c-518d-ba06-8194c02ea0d3",
-    "oai_identifier": [
-        "oai:ota:oucs:1401"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Myths legends -- Wales"
-        },
-        {
-            "name": "Romances -- Wales"
-        }
-    ],
-    "title": [
-        " Ronabwy  : [from] Llyfr Gwyn Rhydderch / compiled by Nancy H. Rose"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1401.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6917c5a0-ead6-551e-a217-a6bb7c73edd4.json b/oaitestdata/clarin-oai_dc/SET_1/json/6917c5a0-ead6-551e-a217-a6bb7c73edd4.json
deleted file mode 100644
index a19d4a81..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6917c5a0-ead6-551e-a217-a6bb7c73edd4.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5174",
-    "MetadataAccess": [
-        "oai:ota:oucs:5174"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Arbuthnot, John, 1667-1735."
-    ],
-    "fulltext": "oai:ota:oucs:5174;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5174.xml;An essay concerning the nature of aliments: and the choice of them, according to the different constitutions of human bodies. ... By John Arbuthnot, ...;Arbuthnot, John, 1667-1735.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6917c5a0-ead6-551e-a217-a6bb7c73edd4",
-    "oai_identifier": [
-        "oai:ota:oucs:5174"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An essay concerning the nature of aliments: and the choice of them, according to the different constitutions of human bodies. ... By John Arbuthnot, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5174.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/692884d6-f061-564f-9934-29adcfe8c23a.json b/oaitestdata/clarin-oai_dc/SET_1/json/692884d6-f061-564f-9934-29adcfe8c23a.json
deleted file mode 100644
index df7c5d8d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/692884d6-f061-564f-9934-29adcfe8c23a.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/3",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/3"
-    ],
-    "PID": "http://hdl.handle.net/10794/3",
-    "PublicationTimestamp": "2015-03-04T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "Forsberg, Markus",
-        "Borin, Lars",
-        "L\u00f6nngren, Lennart"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/3;2017-10-27T16:34:24Z;hdl_10794_1;hdl_10794_2;Saldo;Saldo;Borin, Lars;L\u00f6nngren, Lennart;Forsberg, Markus;Swedish;Associative;Thesaurus;SALDO (Swedish Associative Thesaurus version 2) is an extensive lexicon resource for modern Swedish written language. Version 2.3.;SALDO (Svenskt Associationslexikon version 2) \u00e4r ett semantiskt och morfologiskt lexikon f\u00f6r moderns svenskt skriftspr\u00e5k f\u00f6r spr\u00e5kteknologi. Version 2.3.;2015-03-04;lexicalConceptualResource;http://hdl.handle.net/10794/3;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;http://creativecommons.org/licenses/by/4.0/;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/saldo",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "692884d6-f061-564f-9934-29adcfe8c23a",
-    "notes": [
-        "SALDO (Swedish Associative Thesaurus version 2) is an extensive lexicon resource for modern Swedish written language. Version 2.3.",
-        "SALDO (Svenskt Associationslexikon version 2) \u00e4r ett semantiskt och morfologiskt lexikon f\u00f6r moderns svenskt skriftspr\u00e5k f\u00f6r spr\u00e5kteknologi. Version 2.3."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/3"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Associative"
-        },
-        {
-            "name": "Thesaurus"
-        }
-    ],
-    "title": [
-        "Saldo",
-        "Saldo"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6934fadf-562c-565b-b951-0b0c6a52bdc7.json b/oaitestdata/clarin-oai_dc/SET_1/json/6934fadf-562c-565b-b951-0b0c6a52bdc7.json
deleted file mode 100644
index 1daed709..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6934fadf-562c-565b-b951-0b0c6a52bdc7.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "wolnelektury.pl"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 7",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/163",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/163"
-    ],
-    "PID": "http://hdl.handle.net/11321/163",
-    "PublicationTimestamp": "2015-05-15T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "wolnelektury.pl"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Zawadzki, Maciej"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/163;2015-05-15T10:15:58Z;hdl_11321_3;hdl_11321_4;Andersen fairy tales;Zawadzki, Maciej;Some fairy tales of Hans Christian Andersen.;2015-05-15;corpus;http://hdl.handle.net/11321/163;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain; charset=utf-8;downloadable_files_count: 7;wolnelektury.pl",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6934fadf-562c-565b-b951-0b0c6a52bdc7",
-    "notes": [
-        "Some fairy tales of Hans Christian Andersen."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/163"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Andersen fairy tales"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/69430614-3698-5c02-8caa-a035f4b1e3a5.json b/oaitestdata/clarin-oai_dc/SET_1/json/69430614-3698-5c02-8caa-a035f4b1e3a5.json
deleted file mode 100644
index bb0cb51e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/69430614-3698-5c02-8caa-a035f4b1e3a5.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Aneta Kusz"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 4",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/vnd.oasis.opendocument.text"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/480",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/480"
-    ],
-    "PID": "http://hdl.handle.net/11321/480",
-    "PublicationTimestamp": "2018-06-19T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Aneta Kusz"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Super Cool License",
-        "http://www.google.com",
-        "ACA"
-    ],
-    "author": [
-        "Kusz, Aneta"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/480;2018-06-19T11:18:02Z;hdl_11321_3;hdl_11321_4;Pragmatheme;Kusz, Aneta;Warsztaty umcs;Korpus testowy w ramach warsztat\u00f3w szkoleniowych;2018-06-19;corpus;http://hdl.handle.net/11321/480;pol;Super Cool License;http://www.google.com;ACA;text/plain; charset=utf-8;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;downloadable_files_count: 4;Aneta Kusz",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "69430614-3698-5c02-8caa-a035f4b1e3a5",
-    "notes": [
-        "Korpus testowy w ramach warsztat\u00f3w szkoleniowych"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/480"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Warsztaty umcs"
-        }
-    ],
-    "title": [
-        "Pragmatheme"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6944fe52-e0e1-5cf4-a686-f740100e3900.json b/oaitestdata/clarin-oai_dc/SET_1/json/6944fe52-e0e1-5cf4-a686-f740100e3900.json
deleted file mode 100644
index e8e8e44b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6944fe52-e0e1-5cf4-a686-f740100e3900.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "Centre for English Corpus Linguistics, Universit\u00e9 catholique de Louvain"
-    ],
-    "Contributor": [
-        "Granger, Sylviane"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-859",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-859"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-859",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Centre for English Corpus Linguistics, Universit\u00e9 catholique de Louvain"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-859;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;ICLE International Corpus of Learner English;Granger, Sylviane;over 3 million words of writing by learners of English from 14 different mother tongue backgrounds;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-859;eng;downloadable_files_count: 0;Centre for English Corpus Linguistics, Universit\u00e9 catholique de Louvain;http://cecl.fltr.ucl.ac.be/Cecl-Projects/Icle/icle.htm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6944fe52-e0e1-5cf4-a686-f740100e3900",
-    "notes": [
-        "over 3 million words of writing by learners of English from 14 different mother tongue backgrounds"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-859"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "ICLE International Corpus of Learner English"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6953964e-6479-59a8-9c80-4279397013f5.json b/oaitestdata/clarin-oai_dc/SET_1/json/6953964e-6479-59a8-9c80-4279397013f5.json
deleted file mode 100644
index d1bb9c79..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6953964e-6479-59a8-9c80-4279397013f5.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "text/xml",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/103",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/103"
-    ],
-    "PID": "http://hdl.handle.net/11509/103",
-    "PublicationTimestamp": "2015-08-03T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "The Divvun group at UiT The Arctic University of Norway",
-        "Giellatekno - Saami Language Technology, UiT The Arctic University of Norway"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/103;2016-09-06T12:50:26Z;hdl_11509_1;hdl_11509_2;SIKOR Kven free corpus;Giellatekno - Saami Language Technology, UiT The Arctic University of Norway;The Divvun group at UiT The Arctic University of Norway;Monolingual Corpus;Text Corpus;Kven Finnish;The SIKOR Kven free corpus is a monolingual text corpus of Kven that contains administrative, law, religious, non-fiction, fiction, and news texts. It is work done by the Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language community. In particular, the following colleagues have contributed to the creation of the ressource: Ciprian Gerstenberger, B\u00f8rre Gaup, Sindre Trosterud, Leena Niiranen, Kaisa Maliniemi, Paula Paksuniemi, Mervi Haavisto, Trond Trosterud, and Anne-Kaisa R\u00e4is\u00e4nen. Linguistically, the data set (21,024 sentences; 182,697 tokens) features word form, lemma, and morphosyntactic analysis. The corpus has been automatically processed and linguistically analyzed with the Giellatekno/Divvun tools. Therefore, it may contain wrong annotations. In case you find any errors the creators would appreciate your feedback sent to giellatekno@uit.no and feedback@divvun.no.\r\nPlease note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata).;2015-08-03;corpus;http://hdl.handle.net/11509/103;fkv;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;application/zip;text/plain; charset=utf-8;text/xml;downloadable_files_count: 1;Giellatekno - Saami Language Technology;http://giellatekno.uit.no/index.eng.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6953964e-6479-59a8-9c80-4279397013f5",
-    "notes": [
-        "The SIKOR Kven free corpus is a monolingual text corpus of Kven that contains administrative, law, religious, non-fiction, fiction, and news texts. It is work done by the Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language community. In particular, the following colleagues have contributed to the creation of the ressource: Ciprian Gerstenberger, B\u00f8rre Gaup, Sindre Trosterud, Leena Niiranen, Kaisa Maliniemi, Paula Paksuniemi, Mervi Haavisto, Trond Trosterud, and Anne-Kaisa R\u00e4is\u00e4nen. Linguistically, the data set (21,024 sentences; 182,697 tokens) features word form, lemma, and morphosyntactic analysis. The corpus has been automatically processed and linguistically analyzed with the Giellatekno/Divvun tools. Therefore, it may contain wrong annotations. In case you find any errors the creators would appreciate your feedback sent to giellatekno@uit.no and feedback@divvun.no.\r\nPlease note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata)."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/103"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Monolingual Corpus"
-        },
-        {
-            "name": "Text Corpus"
-        },
-        {
-            "name": "Kven Finnish"
-        }
-    ],
-    "title": [
-        "SIKOR Kven free corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6962c95b-7aef-5200-8306-7da6f7dc838d.json b/oaitestdata/clarin-oai_dc/SET_1/json/6962c95b-7aef-5200-8306-7da6f7dc838d.json
deleted file mode 100644
index 8c463d62..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6962c95b-7aef-5200-8306-7da6f7dc838d.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "The Russell Trust",
-        "Skretkowicz, Victor",
-        "Rennie, Susan",
-        "Scottish National Dictionaries Association (SNDA) 2001-2003",
-        "Scottish Language Dictionaries Limited (SLD) 2003-2004",
-        "University of Dundee",
-        "AHRB"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "8 files: ca. 147 MB",
-        "text/xml"
-    ],
-    "Language": [
-        "English",
-        "Scots"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2478",
-    "MetadataAccess": [
-        "oai:ota:oucs:2478"
-    ],
-    "PublicationTimestamp": "1100-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1100"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Dictionaries"
-    ],
-    "Rights": [
-        "This is item is currently archived but no longer available for download. Please address all queries to the Scottish Language Dictionaries Ltd. via the website given in the notes below.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:2478;2019-02-25T12:06:14Z;http://ota.ox.ac.uk/headers/2478.xml;Dictionary of the Scots Language (DSL);1100-1975;text_and_corpus_linguistics;Encyclopedias and dictionaries;Scots language;eng;sco;The main aim of The Dictionary of the Scots Language (DSL) project was to digitise two major historical Scots dictionaries. Its object was to produce an online resource that shows how Scots words have developed and been used from the early Middle Ages to the twentieth century. The resources are the \"Dictionary of the Older Scottish Tongue\" (DOST) and the \"Scottish National Dictionary\" (SND). DOST was compiled and published in paper between 1931 and 2002, and SND between 1931 and 1976. They are the most comprehensive dictionaries available for, respectively, older Scots and modern Scots, and are therefore essential research tools. The DSL project considerably increases access to these rich research resources, by making them freely available worldwide on the Internet. It also makes possible new ways to retrieve the information contained in the printed sources, so that full information on the usage of Scots words will be more readily available to scholars. ;Oxford Text Archive, University of Oxford;Rennie, Susan;AHRB;University of Dundee;Scottish National Dictionaries Association (SNDA) 2001-2003;Scottish Language Dictionaries Limited (SLD) 2003-2004;The Russell Trust;Skretkowicz, Victor;text/xml;8 files: ca. 147 MB;Text;Dictionaries;This is item is currently archived but no longer available for download. Please address all queries to the Scottish Language Dictionaries Ltd. via the website given in the notes below.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6962c95b-7aef-5200-8306-7da6f7dc838d",
-    "notes": [
-        "The main aim of The Dictionary of the Scots Language (DSL) project was to digitise two major historical Scots dictionaries. Its object was to produce an online resource that shows how Scots words have developed and been used from the early Middle Ages to the twentieth century. The resources are the \"Dictionary of the Older Scottish Tongue\" (DOST) and the \"Scottish National Dictionary\" (SND). DOST was compiled and published in paper between 1931 and 2002, and SND between 1931 and 1976. They are the most comprehensive dictionaries available for, respectively, older Scots and modern Scots, and are therefore essential research tools. The DSL project considerably increases access to these rich research resources, by making them freely available worldwide on the Internet. It also makes possible new ways to retrieve the information contained in the printed sources, so that full information on the usage of Scots words will be more readily available to scholars. "
-    ],
-    "oai_identifier": [
-        "oai:ota:oucs:2478"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Encyclopedias dictionaries"
-        },
-        {
-            "name": "Scots language"
-        }
-    ],
-    "title": [
-        "Dictionary of the Scots Language (DSL)"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2478.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/696f74d8-d935-50b2-89e7-a18ceba6e35e.json b/oaitestdata/clarin-oai_dc/SET_1/json/696f74d8-d935-50b2-89e7-a18ceba6e35e.json
deleted file mode 100644
index 16ce9c33..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/696f74d8-d935-50b2-89e7-a18ceba6e35e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5120",
-    "MetadataAccess": [
-        "oai:ota:oucs:5120"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Lloyd, Robert, 1733-1764."
-    ],
-    "fulltext": "oai:ota:oucs:5120;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5120.xml;The tears and triump[hs] of Parnassus: an ode for musick, as it is perform'd at the Theatre-Royal in Drury-Lane.;Lloyd, Robert, 1733-1764.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "696f74d8-d935-50b2-89e7-a18ceba6e35e",
-    "oai_identifier": [
-        "oai:ota:oucs:5120"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The tears and triump[hs] of Parnassus: an ode for musick, as it is perform'd at the Theatre-Royal in Drury-Lane."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5120.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6981eeff-4165-52de-ae72-9212b8de1c7a.json b/oaitestdata/clarin-oai_dc/SET_1/json/6981eeff-4165-52de-ae72-9212b8de1c7a.json
deleted file mode 100644
index 1502a36b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6981eeff-4165-52de-ae72-9212b8de1c7a.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 198 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1572",
-    "MetadataAccess": [
-        "oai:ota:oucs:1572"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Fletcher, John, 1579-1625"
-    ],
-    "fulltext": "oai:ota:oucs:1572;2018-02-16T10:42:06Z;http://ota.ox.ac.uk/headers/1572.xml;The woman's prize;Fletcher, John, 1579-1625;default: 1976-01-01;text_and_corpus_linguistics;Plays -- England -- 17th century;Comedies -- England -- 17th century;eng;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 198 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6981eeff-4165-52de-ae72-9212b8de1c7a",
-    "oai_identifier": [
-        "oai:ota:oucs:1572"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        },
-        {
-            "name": "Comedies -- England -- th century"
-        }
-    ],
-    "title": [
-        "The woman's prize"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1572.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/698937d4-95bf-55f4-9afc-bac0a770e8c0.json b/oaitestdata/clarin-oai_dc/SET_1/json/698937d4-95bf-55f4-9afc-bac0a770e8c0.json
deleted file mode 100644
index be45f388..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/698937d4-95bf-55f4-9afc-bac0a770e8c0.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/28",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/28"
-    ],
-    "PID": "http://hdl.handle.net/11321/28",
-    "PublicationTimestamp": "2013-05-22T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Marci\u0144czuk, Micha\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/28;2016-01-19T13:29:50Z;hdl_11321_3;hdl_11321_4;Serel (WS);Marci\u0144czuk, Micha\u0142;Serel is a Python framework for recognition relations between annotations in text.;2013-05-22;toolService;http://hdl.handle.net/11321/28;pol;downloadable_files_count: 0;Wroc\u0142aw University of Technology;http://www.clarin-pl.eu/demo/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "698937d4-95bf-55f4-9afc-bac0a770e8c0",
-    "notes": [
-        "Serel is a Python framework for recognition relations between annotations in text."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/28"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Serel (WS)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6991c4cd-f75b-5a3d-a869-f0b1bb8d0f8e.json b/oaitestdata/clarin-oai_dc/SET_1/json/6991c4cd-f75b-5a3d-a869-f0b1bb8d0f8e.json
deleted file mode 100644
index abf4ddcd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6991c4cd-f75b-5a3d-a869-f0b1bb8d0f8e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3757",
-    "MetadataAccess": [
-        "oai:ota:oucs:3757"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Francis, Philip, 1708?-1773."
-    ],
-    "fulltext": "oai:ota:oucs:3757;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3757.xml;A letter from the Cocoa Tree, to the country gentlemen;Francis, Philip, 1708?-1773.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6991c4cd-f75b-5a3d-a869-f0b1bb8d0f8e",
-    "oai_identifier": [
-        "oai:ota:oucs:3757"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A letter from the Cocoa Tree, to the country gentlemen"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3757.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6999e43c-1c3d-50d5-ba4c-8c8893717548.json b/oaitestdata/clarin-oai_dc/SET_1/json/6999e43c-1c3d-50d5-ba4c-8c8893717548.json
deleted file mode 100644
index 0cda9943..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6999e43c-1c3d-50d5-ba4c-8c8893717548.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Behrang-QasemiZadeh"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 4",
-        "text/plain",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Persian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1547",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1547"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1547",
-    "PublicationTimestamp": "2015-11-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Behrang-QasemiZadeh"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "QasemiZadeh, Behrang"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1547;2017-04-18T14:23:40Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;FAspell;QasemiZadeh, Behrang;spellchecking;spellchecker;Evaluation Dataset for Automatic Spell Checking;FASpell dataset was developed for the evaluation of spell checking algorithms. It contains a set of pairs of misspelled Persian words and their corresponding corrected forms similar to the ASpell dataset used for English.\r\n\r\nThe dataset consists of two parts:\r\na) faspell_main: list of 5050 pairs collected from errors made by elementary school pupils and professional typists.\r\nb) faspell_ocr: list of 800 pairs collected from the output of a Farsi OCR system.;2015-11-11;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1547;fas;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/octet-stream;text/plain;text/plain;text/plain; charset=utf-8;downloadable_files_count: 4;Behrang-QasemiZadeh;http://pars.ie/lr/faspell_dataset",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6999e43c-1c3d-50d5-ba4c-8c8893717548",
-    "notes": [
-        "FASpell dataset was developed for the evaluation of spell checking algorithms. It contains a set of pairs of misspelled Persian words and their corresponding corrected forms similar to the ASpell dataset used for English.\r\n\r\nThe dataset consists of two parts:\r\na) faspell_main: list of 5050 pairs collected from errors made by elementary school pupils and professional typists.\r\nb) faspell_ocr: list of 800 pairs collected from the output of a Farsi OCR system."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1547"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "spellchecking"
-        },
-        {
-            "name": "spellchecker"
-        },
-        {
-            "name": "Evaluation Dataset Automatic Spell Checking"
-        }
-    ],
-    "title": [
-        "FAspell"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/69a2cf3b-65f0-5e68-b0aa-06725662a89d.json b/oaitestdata/clarin-oai_dc/SET_1/json/69a2cf3b-65f0-5e68-b0aa-06725662a89d.json
deleted file mode 100644
index ccabbe6f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/69a2cf3b-65f0-5e68-b0aa-06725662a89d.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1002",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1002"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1002",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1002;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LAC Tzeltal Corpus;Language and Cognition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1002;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI31783%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "69a2cf3b-65f0-5e68-b0aa-06725662a89d",
-    "notes": [
-        "Language and Cognition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1002"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LAC Tzeltal Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/69aafd9c-befb-518b-8506-c6adc586bef5.json b/oaitestdata/clarin-oai_dc/SET_1/json/69aafd9c-befb-518b-8506-c6adc586bef5.json
deleted file mode 100644
index c1cca601..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/69aafd9c-befb-518b-8506-c6adc586bef5.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Arabic"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48F4-E",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48F4-E"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-48F4-E",
-    "PublicationTimestamp": "2009-11-02T09:19:05Z",
-    "PublicationYear": [
-        "2009"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "http://opensource.org/licenses/GPL-3.0"
-    ],
-    "author": [
-        "Buckwalter, Tim",
-        "Smr\u017e, Otakar",
-        "Bielick\u00fd, Viktor"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48F4-E;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;ElixirFM;Smr\u017e, Otakar;Bielick\u00fd, Viktor;Buckwalter, Tim;Arabic morphology;ElixirFM;ElixirFM is a high-level implementation of Functional Arabic\r\nMorphology documented at http://elixir-fm.wiki.sourceforge.net/. The\r\ncore of ElixirFM is written in Haskell, while interfaces in Perl\r\nsupport lexicon editing and other interactions.;2009-11-02T09:19:05Z;toolService;http://hdl.handle.net/11858/00-097C-0000-0001-48F4-E;ara;http://opensource.org/licenses/GPL-3.0;text/plain; charset=utf-8;downloadable_files_count: 0;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://github.com/otakar-smrz/elixir-fm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "69aafd9c-befb-518b-8506-c6adc586bef5",
-    "notes": [
-        "ElixirFM is a high-level implementation of Functional Arabic\r\nMorphology documented at http://elixir-fm.wiki.sourceforge.net/. The\r\ncore of ElixirFM is written in Haskell, while interfaces in Perl\r\nsupport lexicon editing and other interactions."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48F4-E"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Arabic morphology"
-        },
-        {
-            "name": "ElixirFM"
-        }
-    ],
-    "title": [
-        "ElixirFM"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/69ae8d61-7636-5e0e-97c1-fe0fb18e60e9.json b/oaitestdata/clarin-oai_dc/SET_1/json/69ae8d61-7636-5e0e-97c1-fe0fb18e60e9.json
deleted file mode 100644
index 88bf9396..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/69ae8d61-7636-5e0e-97c1-fe0fb18e60e9.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "Contact": [
-        "The Research Institute for the Languages of Finland"
-    ],
-    "Contributor": [
-        "Torikka, Marja",
-        "Vihtari, Jari"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-829",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-829"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-829",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "The Research Institute for the Languages of Finland"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Finland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-829;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Dictionary of Carelian (= Karjalan kielen sanakirja);Torikka, Marja;Vihtari, Jari;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-829;downloadable_files_count: 0;Finland;The Research Institute for the Languages of Finland;http://kaino.kotus.fi/cgi-bin/kks/kks_etusivu.cgi",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "69ae8d61-7636-5e0e-97c1-fe0fb18e60e9",
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-829"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Dictionary of Carelian (= Karjalan kielen sanakirja)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/69c8d101-e43e-5391-b658-0fd5dc2d33b7.json b/oaitestdata/clarin-oai_dc/SET_1/json/69c8d101-e43e-5391-b658-0fd5dc2d33b7.json
deleted file mode 100644
index da454cae..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/69c8d101-e43e-5391-b658-0fd5dc2d33b7.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Joint Research Centre of the EU"
-    ],
-    "Contributor": [
-        "Steinberger, Ralf"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Bulgarian",
-        "Czech",
-        "Danish",
-        "Dutch",
-        "English",
-        "Estonian",
-        "Finnish",
-        "French",
-        "German",
-        "Modern Greek (1453-)",
-        "Hungarian",
-        "Italian",
-        "Latvian",
-        "Maltese",
-        "Norwegian",
-        "Polish",
-        "Portuguese",
-        "Romanian",
-        "Slovak",
-        "Slovenian",
-        "Spanish",
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-404",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-404"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-404",
-    "PublicationTimestamp": "2008-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2008"
-    ],
-    "Publisher": [
-        "Joint Research Centre of the EU"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Italy"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-404;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;JRC-Acquis;Steinberger, Ralf;The largest parallel corpus, contains EU law, the Acquis Communautaire in 22 languages.;2008;corpus;http://hdl.handle.net/11372/LRT-404;bul;ces;dan;nld;eng;est;fin;fra;deu;ell;hun;ita;lav;mlt;nor;pol;por;ron;slk;slv;spa;swe;downloadable_files_count: 0;Italy;Joint Research Centre of the EU;http://langtech.jrc.it/JRC-Acquis.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "69c8d101-e43e-5391-b658-0fd5dc2d33b7",
-    "notes": [
-        "The largest parallel corpus, contains EU law, the Acquis Communautaire in 22 languages."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-404"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "JRC-Acquis"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/69f64d4b-57f5-58ea-b5f8-0862ea0bb0aa.json b/oaitestdata/clarin-oai_dc/SET_1/json/69f64d4b-57f5-58ea-b5f8-0862ea0bb0aa.json
deleted file mode 100644
index 758c1db0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/69f64d4b-57f5-58ea-b5f8-0862ea0bb0aa.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Berlin-Brandenburg Academy of Sciences and Humanities"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/tei+xml",
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1012",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1012"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1012",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Berlin-Brandenburg Academy of Sciences and Humanities"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1012;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Regionenkorpus (C4-Korpus);corpus;The C4 corpus is a joined effort of the project Digitales W\u00f6rterbuch der deutschen Sprache (DWDS), the Austrian Academy Corpus (AAC), the Korpus S\u00fcdtirol and the Schweizer Textkorpus (CHTK). The Corpus is composed of corpora of all four partner institutions.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1012;deu;application/tei+xml;downloadable_files_count: 0;Berlin-Brandenburg Academy of Sciences and Humanities;http://www.dwds.de/ressourcen/c4/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "69f64d4b-57f5-58ea-b5f8-0862ea0bb0aa",
-    "notes": [
-        "The C4 corpus is a joined effort of the project Digitales W\u00f6rterbuch der deutschen Sprache (DWDS), the Austrian Academy Corpus (AAC), the Korpus S\u00fcdtirol and the Schweizer Textkorpus (CHTK). The Corpus is composed of corpora of all four partner institutions."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1012"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        }
-    ],
-    "title": [
-        "Regionenkorpus (C4-Korpus)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6a13ae98-fd35-5fd7-afad-c4e108f5b9ec.json b/oaitestdata/clarin-oai_dc/SET_1/json/6a13ae98-fd35-5fd7-afad-c4e108f5b9ec.json
deleted file mode 100644
index 7608f2be..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6a13ae98-fd35-5fd7-afad-c4e108f5b9ec.json
+++ /dev/null
@@ -1,140 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2621",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2621"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2621",
-    "PublicationTimestamp": "2018-02-19T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/249119",
-        "info:eu-repo/grantAgreement/EC/FP7/247762",
-        "info:eu-repo/grantAgreement/EC/FP7/610516",
-        "http://hdl.handle.net/11858/00-097C-0000-0023-1AAF-3",
-        "http://hdl.handle.net/11234/1-1905"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Rysov\u00e1, Magdal\u00e9na",
-        "Havelka, Ji\u0159\u00ed",
-        "Haji\u010dov\u00e1, Eva",
-        "Pol\u00e1kov\u00e1, Lucie",
-        "Panevov\u00e1, Jarmila",
-        "Haji\u010d, Jan",
-        "Ku\u010dov\u00e1, Lucie",
-        "Ure\u0161ov\u00e1, Zde\u0148ka",
-        "Lopatkov\u00e1, Mark\u00e9ta",
-        "Bur\u00e1\u0148ov\u00e1, Eva",
-        "K\u00e1rn\u00edk, Ji\u0159\u00ed",
-        "Sgall, Petr",
-        "Stra\u0148\u00e1k, Pavel",
-        "Nedoluzhko, Anna",
-        "Synkov\u00e1, Pavl\u00edna",
-        "M\u00edrovsk\u00fd, Ji\u0159\u00ed",
-        "Homola, Petr",
-        "Mikulov\u00e1, Marie",
-        "Zeman, Daniel",
-        "\u0160ev\u010d\u00edkov\u00e1, Magda",
-        "B\u00e9mov\u00e1, Alevtina",
-        "Bej\u010dek, Eduard",
-        "Pajas, Petr",
-        "Spoustov\u00e1, Johanka",
-        "Kol\u00e1\u0159ov\u00e1, Veronika",
-        "Klyueva, Natalia",
-        "\u0160t\u011bp\u00e1nek, Jan",
-        "Zik\u00e1nov\u00e1, \u0160\u00e1rka",
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "Kettnerov\u00e1, V\u00e1clava",
-        "Vidov\u00e1 Hladk\u00e1, Barbora"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2621;2018-02-20T01:15:58Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Prague Dependency Treebank 3.5;Haji\u010d, Jan;Bej\u010dek, Eduard;B\u00e9mov\u00e1, Alevtina;Bur\u00e1\u0148ov\u00e1, Eva;Haji\u010dov\u00e1, Eva;Havelka, Ji\u0159\u00ed;Homola, Petr;K\u00e1rn\u00edk, Ji\u0159\u00ed;Kettnerov\u00e1, V\u00e1clava;Klyueva, Natalia;Kol\u00e1\u0159ov\u00e1, Veronika;Ku\u010dov\u00e1, Lucie;Lopatkov\u00e1, Mark\u00e9ta;Mikulov\u00e1, Marie;M\u00edrovsk\u00fd, Ji\u0159\u00ed;Nedoluzhko, Anna;Pajas, Petr;Panevov\u00e1, Jarmila;Pol\u00e1kov\u00e1, Lucie;Rysov\u00e1, Magdal\u00e9na;Sgall, Petr;Spoustov\u00e1, Johanka;Stra\u0148\u00e1k, Pavel;Synkov\u00e1, Pavl\u00edna;\u0160ev\u010d\u00edkov\u00e1, Magda;\u0160t\u011bp\u00e1nek, Jan;Ure\u0161ov\u00e1, Zde\u0148ka;Vidov\u00e1 Hladk\u00e1, Barbora;Zeman, Daniel;Zik\u00e1nov\u00e1, \u0160\u00e1rka;\u017dabokrtsk\u00fd, Zden\u011bk;treebank;dependency;tectogrammatics;topic-focus articulation;multiword expressions;coreference;bridging relations;discourse;morphology;syntax;tokenization;lemmatization;clauses;semantics;semantic relations;lexical semantics;lexicon;The Prague Dependency Treebank 3.5 is the 2018 edition of the core Prague Dependency Treebank (PDT). It contains all PDT annotation made at the Institute of Formal and Applied Linguistics under various projects between 1996 and 2018 on the original texts, i.e., all annotation from PDT 1.0, PDT 2.0, PDT 2.5, PDT 3.0, PDiT 1.0 and PDiT 2.0, plus corrections, new structure of basic documentation and new list of authors covering all previous editions. The Prague Dependency Treebank 3.5 (PDT 3.5) contains the same texts as the previous versions since 2.0; there are 49,431 annotated sentences (over 800 thousand nodes) on all layers, from tectogrammatical to words, and additional sentences on the analytical (surface dependency syntax) and morphological layers of annotation (approx. 2 million words in total). Closely linked to the tectogarammtical layer is the annotation of sentence information structure, multiword expressions, coreference, bridging relations and discourse relations.;2018-02-19;corpus;http://hdl.handle.net/11234/1-2621;ces;info:eu-repo/grantAgreement/EC/FP7/249119;info:eu-repo/grantAgreement/EC/FP7/247762;info:eu-repo/grantAgreement/EC/FP7/610516;http://hdl.handle.net/11858/00-097C-0000-0023-1AAF-3;http://hdl.handle.net/11234/1-1905;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/pdt3.5",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6a13ae98-fd35-5fd7-afad-c4e108f5b9ec",
-    "notes": [
-        "The Prague Dependency Treebank 3.5 is the 2018 edition of the core Prague Dependency Treebank (PDT). It contains all PDT annotation made at the Institute of Formal and Applied Linguistics under various projects between 1996 and 2018 on the original texts, i.e., all annotation from PDT 1.0, PDT 2.0, PDT 2.5, PDT 3.0, PDiT 1.0 and PDiT 2.0, plus corrections, new structure of basic documentation and new list of authors covering all previous editions. The Prague Dependency Treebank 3.5 (PDT 3.5) contains the same texts as the previous versions since 2.0; there are 49,431 annotated sentences (over 800 thousand nodes) on all layers, from tectogrammatical to words, and additional sentences on the analytical (surface dependency syntax) and morphological layers of annotation (approx. 2 million words in total). Closely linked to the tectogarammtical layer is the annotation of sentence information structure, multiword expressions, coreference, bridging relations and discourse relations."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2621"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "dependency"
-        },
-        {
-            "name": "tectogrammatics"
-        },
-        {
-            "name": "topic-focus articulation"
-        },
-        {
-            "name": "multiword expressions"
-        },
-        {
-            "name": "coreference"
-        },
-        {
-            "name": "bridging relations"
-        },
-        {
-            "name": "discourse"
-        },
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "syntax"
-        },
-        {
-            "name": "tokenization"
-        },
-        {
-            "name": "lemmatization"
-        }
-    ],
-    "title": [
-        "Prague Dependency Treebank 3.5"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6a23f5b3-f36e-51a1-b9e1-2dc3b692c7da.json b/oaitestdata/clarin-oai_dc/SET_1/json/6a23f5b3-f36e-51a1-b9e1-2dc3b692c7da.json
deleted file mode 100644
index 704a9742..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6a23f5b3-f36e-51a1-b9e1-2dc3b692c7da.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Institute of Mathematics and Computer Science, University of Latvia"
-    ],
-    "Contributor": [
-        "B\u0113rzi\u0146a-Reinsone, Sanita"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Latvian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-621",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-621"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-621",
-    "PublicationTimestamp": "1997-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1997"
-    ],
-    "Publisher": [
-        "Institute of Mathematics and Computer Science, University of Latvia"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Latvia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-621;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Latvian Folk Beliefs;B\u0113rzi\u0146a-Reinsone, Sanita;Latvian folk beliefs collected by P\u0113teris \u0160mits, published in 1940-1941 (4 volumes);1997;corpus;http://hdl.handle.net/11372/LRT-621;lav;downloadable_files_count: 0;Latvia;Institute of Mathematics and Computer Science, University of Latvia;http://valoda.ailab.lv/folklora/ticejumi/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6a23f5b3-f36e-51a1-b9e1-2dc3b692c7da",
-    "notes": [
-        "Latvian folk beliefs collected by P\u0113teris \u0160mits, published in 1940-1941 (4 volumes)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-621"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Latvian Folk Beliefs"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6a35550d-8d68-58c9-83e6-da24ed12d2ab.json b/oaitestdata/clarin-oai_dc/SET_1/json/6a35550d-8d68-58c9-83e6-da24ed12d2ab.json
deleted file mode 100644
index e13a85f0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6a35550d-8d68-58c9-83e6-da24ed12d2ab.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "less than 512 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0626",
-    "MetadataAccess": [
-        "oai:ota:oucs:0626"
-    ],
-    "PublicationTimestamp": "1925-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1925"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Cather, Willa,  1873-1947"
-    ],
-    "fulltext": "oai:ota:oucs:0626;2018-02-28T10:49:17Z;http://ota.ox.ac.uk/headers/0626.xml;The professor's house  / compiled by the Academic Data and Program Services of Princeton University Computing Center;Cather, Willa,  1873-1947;1925;text_and_corpus_linguistics;Novels -- United States -- 20th century;eng;Oxford Text Archive, University of Oxford;less than 512 KB;Text;Novels;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6a35550d-8d68-58c9-83e6-da24ed12d2ab",
-    "oai_identifier": [
-        "oai:ota:oucs:0626"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Novels -- United States -- th century"
-        }
-    ],
-    "title": [
-        "The professor's house  / compiled by the Academic Data and Program Services of Princeton University Computing Center"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0626.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6a4204a7-5c44-5fba-8a3a-0a70bd292a48.json b/oaitestdata/clarin-oai_dc/SET_1/json/6a4204a7-5c44-5fba-8a3a-0a70bd292a48.json
deleted file mode 100644
index 7ba85c06..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6a4204a7-5c44-5fba-8a3a-0a70bd292a48.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "54 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1296",
-    "MetadataAccess": [
-        "oai:ota:oucs:1296"
-    ],
-    "PublicationTimestamp": "1667-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1667"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dryden, John,  1631-1700"
-    ],
-    "fulltext": "oai:ota:oucs:1296;2018-03-06T16:38:11Z;http://ota.ox.ac.uk/headers/1296.xml;Annus mirabilis  / compiled by Thomas N. Corns;Dryden, John,  1631-1700;1667;text_and_corpus_linguistics;Poems -- England -- 17th century;eng;Oxford Text Archive, University of Oxford;54 KB;Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6a4204a7-5c44-5fba-8a3a-0a70bd292a48",
-    "oai_identifier": [
-        "oai:ota:oucs:1296"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- England -- th century"
-        }
-    ],
-    "title": [
-        "Annus mirabilis  / compiled by Thomas N. Corns"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1296.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6a42ef4b-7cd3-54bf-890d-3d6130446ac4.json b/oaitestdata/clarin-oai_dc/SET_1/json/6a42ef4b-7cd3-54bf-890d-3d6130446ac4.json
deleted file mode 100644
index 8ec42451..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6a42ef4b-7cd3-54bf-890d-3d6130446ac4.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "text/xml",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/104",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/104"
-    ],
-    "PID": "http://hdl.handle.net/11509/104",
-    "PublicationTimestamp": "2015-08-30T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "CC",
-        "http://creativecommons.org/licenses/by/3.0/"
-    ],
-    "author": [
-        "The Divvun group at UiT The Arctic University of Norway",
-        "Giellatekno - Saami Language Technology, UiT The Arctic University of Norway"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/104;2016-09-06T12:33:40Z;hdl_11509_1;hdl_11509_2;Kven lemma frequency list;Giellatekno - Saami Language Technology, UiT The Arctic University of Norway;The Divvun group at UiT The Arctic University of Norway;Lemma Frequencies;Kven Finnish;The Kven lemma frequency list is work done by the Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language community. In particular, Ciprian-Virgil Gerstenberger compiled the list from the entire SIKOR Kven corpus version 2015-08-30. The data is in an one-lemma-per-line format with the following values: <ABS_FREQ> <LEMMA> <POS>. Since the list has been derived automatically, it may contain wrong values. In case you find any errors the creators would appreciate your feedback sent to giellatekno@uit.no and feedback@divvun.no. Please note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata).;2015-08-30;corpus;http://hdl.handle.net/11509/104;fkv;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);CC;http://creativecommons.org/licenses/by/3.0/;text/xml;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Giellatekno - Saami Language Technology;http://giellatekno.uit.no/index.eng.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6a42ef4b-7cd3-54bf-890d-3d6130446ac4",
-    "notes": [
-        "The Kven lemma frequency list is work done by the Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language community. In particular, Ciprian-Virgil Gerstenberger compiled the list from the entire SIKOR Kven corpus version 2015-08-30. The data is in an one-lemma-per-line format with the following values: <ABS_FREQ> <LEMMA> <POS>. Since the list has been derived automatically, it may contain wrong values. In case you find any errors the creators would appreciate your feedback sent to giellatekno@uit.no and feedback@divvun.no. Please note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata)."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/104"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Lemma Frequencies"
-        },
-        {
-            "name": "Kven Finnish"
-        }
-    ],
-    "title": [
-        "Kven lemma frequency list"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6a500a32-189c-5474-a737-01a53ab9bd90.json b/oaitestdata/clarin-oai_dc/SET_1/json/6a500a32-189c-5474-a737-01a53ab9bd90.json
deleted file mode 100644
index 94a158f8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6a500a32-189c-5474-a737-01a53ab9bd90.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4906",
-    "MetadataAccess": [
-        "oai:ota:oucs:4906"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Macpherson, James, 1736-1796."
-    ],
-    "fulltext": "oai:ota:oucs:4906;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4906.xml;The highlander: a poem: in six cantos.;Macpherson, James, 1736-1796.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6a500a32-189c-5474-a737-01a53ab9bd90",
-    "oai_identifier": [
-        "oai:ota:oucs:4906"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The highlander: a poem: in six cantos."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4906.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6a6c0d6d-0f2f-5bf3-bf4f-2f1e9d5f5d39.json b/oaitestdata/clarin-oai_dc/SET_1/json/6a6c0d6d-0f2f-5bf3-bf4f-2f1e9d5f5d39.json
deleted file mode 100644
index 8fe6c47d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6a6c0d6d-0f2f-5bf3-bf4f-2f1e9d5f5d39.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-913",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-913"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-913",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-913;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Khotanese Sakan;ca. 200.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-913;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#khot",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6a6c0d6d-0f2f-5bf3-bf4f-2f1e9d5f5d39",
-    "notes": [
-        "ca. 200.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-913"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Khotanese Sakan"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6a9691a6-dacd-53d8-a883-3d4d60a879fb.json b/oaitestdata/clarin-oai_dc/SET_1/json/6a9691a6-dacd-53d8-a883-3d4d60a879fb.json
deleted file mode 100644
index 18619f36..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6a9691a6-dacd-53d8-a883-3d4d60a879fb.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain",
-        "(1 file : ca. 982 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1055",
-    "MetadataAccess": [
-        "oai:ota:oucs:1055"
-    ],
-    "PublicationTimestamp": "1861-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1861"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dickens, Charles, 1812-1870"
-    ],
-    "fulltext": "oai:ota:oucs:1055;2018-03-05T11:07:41Z;http://ota.ox.ac.uk/headers/1055.xml;Great expectations;Dickens, Charles, 1812-1870;1861;text_and_corpus_linguistics;Fiction -- Great Britain -- 19th century;Novels -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 982 KB);Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6a9691a6-dacd-53d8-a883-3d4d60a879fb",
-    "oai_identifier": [
-        "oai:ota:oucs:1055"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- Great Britain -- th century"
-        },
-        {
-            "name": "Novels -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Great expectations"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1055.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6ac05cd9-aa10-5ff9-bc44-8fb63bd55f2c.json b/oaitestdata/clarin-oai_dc/SET_1/json/6ac05cd9-aa10-5ff9-bc44-8fb63bd55f2c.json
deleted file mode 100644
index 069e7a2a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6ac05cd9-aa10-5ff9-bc44-8fb63bd55f2c.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3883",
-    "MetadataAccess": [
-        "oai:ota:oucs:3883"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Jephson, Robert, 1736-1803."
-    ],
-    "fulltext": "oai:ota:oucs:3883;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3883.xml;Conspiracy, a tragedy. By R. Jephson, Esq;Jephson, Robert, 1736-1803.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6ac05cd9-aa10-5ff9-bc44-8fb63bd55f2c",
-    "oai_identifier": [
-        "oai:ota:oucs:3883"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Conspiracy, a tragedy. By R. Jephson, Esq"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3883.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6ae77dec-c642-529f-b128-4c19abf0744a.json b/oaitestdata/clarin-oai_dc/SET_1/json/6ae77dec-c642-529f-b128-4c19abf0744a.json
deleted file mode 100644
index 9fd5e03a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6ae77dec-c642-529f-b128-4c19abf0744a.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-984",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-984"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-984",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-984;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LAC Jahai Corpus;Language and Cognition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-984;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI29197%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6ae77dec-c642-529f-b128-4c19abf0744a",
-    "notes": [
-        "Language and Cognition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-984"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LAC Jahai Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6afbdcae-6689-5918-ae50-51147d113093.json b/oaitestdata/clarin-oai_dc/SET_1/json/6afbdcae-6689-5918-ae50-51147d113093.json
deleted file mode 100644
index 898c694f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6afbdcae-6689-5918-ae50-51147d113093.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 440 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "Middle English (1100-1500)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1375",
-    "MetadataAccess": [
-        "oai:ota:oucs:1375"
-    ],
-    "PublicationTimestamp": "1989-05-18T11:59:59Z",
-    "PublicationYear": [
-        "1989"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Langland, William, 1330?-1400?"
-    ],
-    "fulltext": "oai:ota:oucs:1375;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1375.xml;Piers Plowman : B-Text / from Skeat;Langland, William, 1330?-1400?;1989-05-18;text_and_corpus_linguistics;Poems -- England -- 14th century;enm;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 440 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6afbdcae-6689-5918-ae50-51147d113093",
-    "oai_identifier": [
-        "oai:ota:oucs:1375"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- England -- th century"
-        }
-    ],
-    "title": [
-        "Piers Plowman : B-Text / from Skeat"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1375.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6afe97fb-12bb-5bbc-9bca-3b6ef730a6b8.json b/oaitestdata/clarin-oai_dc/SET_1/json/6afe97fb-12bb-5bbc-9bca-3b6ef730a6b8.json
deleted file mode 100644
index f73cf0db..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6afe97fb-12bb-5bbc-9bca-3b6ef730a6b8.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Institute of Mathematics and Computer Science, University of Latvia"
-    ],
-    "Contributor": [
-        "Lev\u0101ne-Petrova, Krist\u012bne"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Latvian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-184",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-184"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-184",
-    "PublicationTimestamp": "2002-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2002"
-    ],
-    "Publisher": [
-        "Institute of Mathematics and Computer Science, University of Latvia"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Latvia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-184;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Latvian literature classics;Lev\u0101ne-Petrova, Krist\u012bne;Selected masterpieces of Latvian literature from the end of the 19th century and the beginning of the 20th century;2002;corpus;http://hdl.handle.net/11372/LRT-184;lav;downloadable_files_count: 0;Latvia;Institute of Mathematics and Computer Science, University of Latvia;http://valoda.ailab.lv/korpuss/klasika/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6afe97fb-12bb-5bbc-9bca-3b6ef730a6b8",
-    "notes": [
-        "Selected masterpieces of Latvian literature from the end of the 19th century and the beginning of the 20th century"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-184"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Latvian literature classics"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6b016f28-96e8-525d-b568-e66bd807bb87.json b/oaitestdata/clarin-oai_dc/SET_1/json/6b016f28-96e8-525d-b568-e66bd807bb87.json
deleted file mode 100644
index 84e60b3d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6b016f28-96e8-525d-b568-e66bd807bb87.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "text/plain",
-        "downloadable_files_count: 2"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1581",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1581"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1581",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Bojar, Ond\u0159ej",
-        "Tamchyna, Ale\u0161"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1581;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;TMODS:ENG-CZE -- query translation;Tamchyna, Ale\u0161;Bojar, Ond\u0159ej;machine translation;query translationn;AMALACH project component TMODS:ENG-CZE; machine translation of queries from Czech to English. This archive contains models for the Moses decoder (binarized, pruned to allow for real-time translation) and configuration files for the MTMonkey toolkit. The aim of this package is to provide a full service for Czech->English translation which can be easily utilized as a component in a larger software solution. (The required tools are freely available and an installation guide is included in the package.)\r\n\r\nThe translation models were trained on CzEng 1.0 corpus and Europarl. Monolingual data for LM estimation additionally contains WMT news crawls until 2013.;2015;toolService;http://hdl.handle.net/11234/1-1581;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/x-gzip;text/plain;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/grants/amalach",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6b016f28-96e8-525d-b568-e66bd807bb87",
-    "notes": [
-        "AMALACH project component TMODS:ENG-CZE; machine translation of queries from Czech to English. This archive contains models for the Moses decoder (binarized, pruned to allow for real-time translation) and configuration files for the MTMonkey toolkit. The aim of this package is to provide a full service for Czech->English translation which can be easily utilized as a component in a larger software solution. (The required tools are freely available and an installation guide is included in the package.)\r\n\r\nThe translation models were trained on CzEng 1.0 corpus and Europarl. Monolingual data for LM estimation additionally contains WMT news crawls until 2013."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1581"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "query translationn"
-        }
-    ],
-    "title": [
-        "TMODS:ENG-CZE -- query translation"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6b2621a9-93db-514e-896f-2f076da10abd.json b/oaitestdata/clarin-oai_dc/SET_1/json/6b2621a9-93db-514e-896f-2f076da10abd.json
deleted file mode 100644
index dbf90e30..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6b2621a9-93db-514e-896f-2f076da10abd.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Dell, Thomas"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 428 KB)",
-        "text/plain"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1948",
-    "MetadataAccess": [
-        "oai:ota:oucs:1948"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Lewis, Sinclair, 1885-1951"
-    ],
-    "fulltext": "oai:ota:oucs:1948;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1948.xml;Our Mr. Wrenn : the romantic adventures of a gentle man / Sinclair Lewis;Lewis, Sinclair, 1885-1951;text_and_corpus_linguistics;American fiction -- 20th century;Oxford Text Archive, University of Oxford;Dell, Thomas;text/plain;(1 file : ca. 428 KB);Text;Novels;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6b2621a9-93db-514e-896f-2f076da10abd",
-    "oai_identifier": [
-        "oai:ota:oucs:1948"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "American fiction -- th century"
-        }
-    ],
-    "title": [
-        "Our Mr. Wrenn : the romantic adventures of a gentle man / Sinclair Lewis"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1948.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6b37483c-0a92-5ec1-bd49-9762140b2732.json b/oaitestdata/clarin-oai_dc/SET_1/json/6b37483c-0a92-5ec1-bd49-9762140b2732.json
deleted file mode 100644
index 58bf4eb7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6b37483c-0a92-5ec1-bd49-9762140b2732.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3245",
-    "MetadataAccess": [
-        "oai:ota:oucs:3245"
-    ],
-    "PublicationTimestamp": "1911-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1911"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Muir, John, 1838-1914"
-    ],
-    "fulltext": "oai:ota:oucs:3245;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3245.xml;My first summer in the Sierra;Muir, John, 1838-1914;not after: 1911;text_and_corpus_linguistics;Travel literature -- United States -- 20th century;eng;Oxford Text Archive, University of Oxford;Triggs, Jeffery;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6b37483c-0a92-5ec1-bd49-9762140b2732",
-    "oai_identifier": [
-        "oai:ota:oucs:3245"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Travel literature -- United States -- th century"
-        }
-    ],
-    "title": [
-        "My first summer in the Sierra"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3245.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6b5e49ac-ab31-53ad-b9ee-6355899ad59a.json b/oaitestdata/clarin-oai_dc/SET_1/json/6b5e49ac-ab31-53ad-b9ee-6355899ad59a.json
deleted file mode 100644
index 190d9cbf..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6b5e49ac-ab31-53ad-b9ee-6355899ad59a.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Research Group in Computational Linguistics, University of Wolverhampton"
-    ],
-    "Contributor": [
-        "Mitkov, Prof. Ruslan"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-869",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-869"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-869",
-    "PublicationTimestamp": "2005-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2005"
-    ],
-    "Publisher": [
-        "Research Group in Computational Linguistics, University of Wolverhampton"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-869;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;CAST corpus (Computer-Aided Summarisation Tool);Mitkov, Prof. Ruslan;Sentences annotated for important units of text for summarisation. 145,473 words / 6584 sentences;2005;corpus;http://hdl.handle.net/11372/LRT-869;eng;downloadable_files_count: 0;United Kingdom;Research Group in Computational Linguistics, University of Wolverhampton;http://clg.wlv.ac.uk/projects/CAST/corpus/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6b5e49ac-ab31-53ad-b9ee-6355899ad59a",
-    "notes": [
-        "Sentences annotated for important units of text for summarisation. 145,473 words / 6584 sentences"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-869"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "CAST corpus (Computer-Aided Summarisation Tool)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6b680354-6701-5eac-a588-6f0a8a491fc5.json b/oaitestdata/clarin-oai_dc/SET_1/json/6b680354-6701-5eac-a588-6f0a8a491fc5.json
deleted file mode 100644
index 3fcf0559..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6b680354-6701-5eac-a588-6f0a8a491fc5.json
+++ /dev/null
@@ -1,49 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4431",
-    "MetadataAccess": [
-        "oai:ota:oucs:4431"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:4431;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4431.xml;An account of the proceedings against the rebels, and other prisoners, tried before the Lord Chief Justice Jefferies: and other judges in the west of England, in 1685. for taking arms under the Duke of Monmouth. ... To which is prefix'd, the Duke of Monmouth's, the Earl of Argyle's, and the Pretender's declarations, that the reader may the better judge of the cause of the several rebellions.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6b680354-6701-5eac-a588-6f0a8a491fc5",
-    "oai_identifier": [
-        "oai:ota:oucs:4431"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An account of the proceedings against the rebels, and other prisoners, tried before the Lord Chief Justice Jefferies: and other judges in the west of England, in 1685. for taking arms under the Duke of Monmouth. ... To which is prefix'd, the Duke of Monmouth's, the Earl of Argyle's, and the Pretender's declarations, that the reader may the better judge of the cause of the several rebellions."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4431.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6b6f0466-617e-5d85-9240-d33f8b0664a1.json b/oaitestdata/clarin-oai_dc/SET_1/json/6b6f0466-617e-5d85-9240-d33f8b0664a1.json
deleted file mode 100644
index 33c38126..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6b6f0466-617e-5d85-9240-d33f8b0664a1.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3524",
-    "MetadataAccess": [
-        "oai:ota:oucs:3524"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Richardson, Samuel, 1689-1761."
-    ],
-    "fulltext": "oai:ota:oucs:3524;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3524.xml;The history of Sir Charles Grandison: In a series of letters published from the originals, by the editor of Pamela and Clarissa. In seven volumes. ... [pt.3];Sir Charles Grandison;Richardson, Samuel, 1689-1761.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6b6f0466-617e-5d85-9240-d33f8b0664a1",
-    "oai_identifier": [
-        "oai:ota:oucs:3524"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The history of Sir Charles Grandison: In a series of letters published from the originals, by the editor of Pamela and Clarissa. In seven volumes. ... [pt.3]",
-        "Sir Charles Grandison"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3524.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6b75336f-3814-59f2-8c76-1229b3a2c000.json b/oaitestdata/clarin-oai_dc/SET_1/json/6b75336f-3814-59f2-8c76-1229b3a2c000.json
deleted file mode 100644
index f3f43d9a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6b75336f-3814-59f2-8c76-1229b3a2c000.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3179",
-    "MetadataAccess": [
-        "oai:ota:oucs:3179"
-    ],
-    "PublicationTimestamp": "1917-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1917"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Phillips, David Graham, 1867-1911"
-    ],
-    "fulltext": "oai:ota:oucs:3179;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3179.xml;Susan Lenox: her rise and fall [sic] ;Phillips, David Graham, 1867-1911;not after: 1917;text_and_corpus_linguistics;Fiction -- United States -- 20th century;Novels -- United States -- 20th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6b75336f-3814-59f2-8c76-1229b3a2c000",
-    "oai_identifier": [
-        "oai:ota:oucs:3179"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- United States -- th century"
-        },
-        {
-            "name": "Novels -- United States -- th century"
-        }
-    ],
-    "title": [
-        "Susan Lenox: her rise and fall [sic] "
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3179.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6b88775c-68c5-52c8-b7a5-92d291e04009.json b/oaitestdata/clarin-oai_dc/SET_1/json/6b88775c-68c5-52c8-b7a5-92d291e04009.json
deleted file mode 100644
index a3e81e6c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6b88775c-68c5-52c8-b7a5-92d291e04009.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/310",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/310"
-    ],
-    "PID": "http://hdl.handle.net/11321/310",
-    "PublicationTimestamp": "2016-06-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "K\u0119dzia, Pawe\u0142",
-        "Janz, Arkadiusz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/310;2016-06-09T05:48:24Z;hdl_11321_3;hdl_11321_4;Entailment;Janz, Arkadiusz;K\u0119dzia, Pawe\u0142;Entailment;Semantic Relations;DRT;Entailment is a tool for recognizing semantic relations between sentences.;2016-06-01;toolService;http://hdl.handle.net/11321/310;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 1;Wroc\u0142aw University of Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6b88775c-68c5-52c8-b7a5-92d291e04009",
-    "notes": [
-        "Entailment is a tool for recognizing semantic relations between sentences."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/310"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Entailment"
-        },
-        {
-            "name": "Semantic Relations"
-        },
-        {
-            "name": "DRT"
-        }
-    ],
-    "title": [
-        "Entailment"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6ba910fc-888d-56a6-b8e5-7f3bf546650c.json b/oaitestdata/clarin-oai_dc/SET_1/json/6ba910fc-888d-56a6-b8e5-7f3bf546650c.json
deleted file mode 100644
index 619152a7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6ba910fc-888d-56a6-b8e5-7f3bf546650c.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Richter, Aemilius Ludwig, 1808-1864"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(2 files : ca. 1.51, 1.67 MB)"
-    ],
-    "Language": [
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0699",
-    "MetadataAccess": [
-        "oai:ota:oucs:0699"
-    ],
-    "PublicationYear": [
-        "367-383"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Legal formularies"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gratian, 12th cent."
-    ],
-    "fulltext": "oai:ota:oucs:0699;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0699.xml;Decretum;Concordia discordantium canonum ac primum de iure naturae et constitutionis / Gratianus;Gratian, 12th cent.;367-383;text_and_corpus_linguistics;Legal formularies -- 12th century;lat;Oxford Text Archive, University of Oxford;Richter, Aemilius Ludwig, 1808-1864;(2 files : ca. 1.51, 1.67 MB);Text;Legal formularies;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6ba910fc-888d-56a6-b8e5-7f3bf546650c",
-    "oai_identifier": [
-        "oai:ota:oucs:0699"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Legal formularies -- th century"
-        }
-    ],
-    "title": [
-        "Decretum",
-        "Concordia discordantium canonum ac primum de iure naturae et constitutionis / Gratianus"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0699.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6bae3d68-83e8-5bbc-a523-8d58b0be40ba.json b/oaitestdata/clarin-oai_dc/SET_1/json/6bae3d68-83e8-5bbc-a523-8d58b0be40ba.json
deleted file mode 100644
index 9ff1258f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6bae3d68-83e8-5bbc-a523-8d58b0be40ba.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "Contributor": [
-        "Variaci\u00f3, Iula"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1110",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1110"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1110",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1110;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Corpus d\u2019extractes de gravacions d\u2019Internet en temps aparent (TA) i temps real (TR) amb finalitats forenses;Variaci\u00f3, Iula;corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1110;eng;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra;http://www.iula.upf.edu/recurs08ca.htm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6bae3d68-83e8-5bbc-a523-8d58b0be40ba",
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1110"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        }
-    ],
-    "title": [
-        "Corpus d\u2019extractes de gravacions d\u2019Internet en temps aparent (TA) i temps real (TR) amb finalitats forenses"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6bb95132-dee5-524e-9f3d-ce30d5ececcc.json b/oaitestdata/clarin-oai_dc/SET_1/json/6bb95132-dee5-524e-9f3d-ce30d5ececcc.json
deleted file mode 100644
index e3e1c4af..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6bb95132-dee5-524e-9f3d-ce30d5ececcc.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "University of Bergen, Department of Linguistic, Literary and Aesthetic Studies"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "audio/x-wav",
-        "downloadable_files_count: 7",
-        "text/plain; charset=utf-8",
-        "application/pdf",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish",
-        "Norwegian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/126",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/126"
-    ],
-    "PID": "http://hdl.handle.net/11509/126",
-    "PublicationTimestamp": "2019-02-25T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "University of Bergen, Department of Linguistic, Literary and Aesthetic Studies"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN_ACA",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NORED=1",
-        "ACA"
-    ],
-    "author": [
-        "Kristoffersen, Gjert"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/126;2019-02-25T14:34:17Z;hdl_11509_1;hdl_11509_2;The Level Stress recordings: \u00c4lvdalen_90;Kristoffersen, Gjert;Phonology;Recording equipment\r\nThe recordings were done by means of a cassette recorder (Sony TC-D5M) and Sony\r\nlavaliere microphones. They were digitized in the 1990s.\r\nThe set consists of two speakers, father and grown-up daughter. The original full recordings\r\nhave been lost, and they are therefore reconstructed from a series of single files saved into one\r\nwav file.\r\n\r\nThe speakers\r\nThe two speakers, born in 1921 and 1944, were recruited with the help of the Swedish linguist\r\nGunnar Nystr\u00f6m, who has a thorough knowledge of Dalarna and the Dalarna dialects. At the\r\ntime of recording, they lived in the villages of Karlsarvet and Brunnsberg. A third speaker\r\nwas also recorded, a man born in 1921, but due to his weak voice, extremely non-fluent\r\nreading and background noise generated by some technical failure, this recording has not been\r\nincluded in the collection.\r\n\r\nFor the full background description of this item, see the file \"\u00c4lvdalen_90: Background.pdf\".\r\n\r\nFor the full description of the whole project, see these files:\r\n     The Level Stress recordings.pdf\r\n     LevelStress_Glossary.pdf\r\n     Level Stress_Speaker and Sound File Codes.pdf\r\n\r\nThe data should be used only for research and development purposes.;2019-02-25;corpus;http://hdl.handle.net/11509/126;swe;nor;CLARIN_ACA;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NORED=1;ACA;audio/x-wav;audio/x-wav;application/pdf;application/pdf;application/pdf;application/pdf;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 7;University of Bergen, Department of Linguistic, Literary and Aesthetic Studies;http://terminologi.no",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6bb95132-dee5-524e-9f3d-ce30d5ececcc",
-    "notes": [
-        "Recording equipment\r\nThe recordings were done by means of a cassette recorder (Sony TC-D5M) and Sony\r\nlavaliere microphones. They were digitized in the 1990s.\r\nThe set consists of two speakers, father and grown-up daughter. The original full recordings\r\nhave been lost, and they are therefore reconstructed from a series of single files saved into one\r\nwav file.\r\n\r\nThe speakers\r\nThe two speakers, born in 1921 and 1944, were recruited with the help of the Swedish linguist\r\nGunnar Nystr\u00f6m, who has a thorough knowledge of Dalarna and the Dalarna dialects. At the\r\ntime of recording, they lived in the villages of Karlsarvet and Brunnsberg. A third speaker\r\nwas also recorded, a man born in 1921, but due to his weak voice, extremely non-fluent\r\nreading and background noise generated by some technical failure, this recording has not been\r\nincluded in the collection.\r\n\r\nFor the full background description of this item, see the file \"\u00c4lvdalen_90: Background.pdf\".\r\n\r\nFor the full description of the whole project, see these files:\r\n     The Level Stress recordings.pdf\r\n     LevelStress_Glossary.pdf\r\n     Level Stress_Speaker and Sound File Codes.pdf\r\n\r\nThe data should be used only for research and development purposes."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/126"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Phonology"
-        }
-    ],
-    "title": [
-        "The Level Stress recordings: \u00c4lvdalen_90"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6bc2472d-42e9-524b-82f0-e5b6d8088e8e.json b/oaitestdata/clarin-oai_dc/SET_1/json/6bc2472d-42e9-524b-82f0-e5b6d8088e8e.json
deleted file mode 100644
index 3d2770e6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6bc2472d-42e9-524b-82f0-e5b6d8088e8e.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=0a91f7c4328211e2a2aa782bcb07413588941be5d4324351828c784c6700f980",
-    "MetadataAccess": [
-        "0a91f7c4328211e2a2aa782bcb07413588941be5d4324351828c784c6700f980"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "0a91f7c4328211e2a2aa782bcb07413588941be5d4324351828c784c6700f980;2018-11-15T16:39:50Z;toolService;toolService:tool;Enju parser;Enju is a syntactic parser for English. The grammar used by the parser is based on Head Driven Phrase Structure Grammar (HPSG). Enju can analyse syntactic/semantic structures of English sentences can output phrase structure and predicate-argument structures. ;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6bc2472d-42e9-524b-82f0-e5b6d8088e8e",
-    "notes": [
-        "Enju is a syntactic parser for English. The grammar used by the parser is based on Head Driven Phrase Structure Grammar (HPSG). Enju can analyse syntactic/semantic structures of English sentences can output phrase structure and predicate-argument structures. "
-    ],
-    "oai_identifier": [
-        "0a91f7c4328211e2a2aa782bcb07413588941be5d4324351828c784c6700f980"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "Enju parser"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6bc9b364-142f-5660-a7d6-3015ef54a552.json b/oaitestdata/clarin-oai_dc/SET_1/json/6bc9b364-142f-5660-a7d6-3015ef54a552.json
deleted file mode 100644
index 128d2281..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6bc9b364-142f-5660-a7d6-3015ef54a552.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "The National Library of Sweden"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/112",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/112"
-    ],
-    "PID": "http://hdl.handle.net/10794/112",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "The National Library of Sweden"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/112;2017-11-01T13:47:54Z;hdl_10794_1;hdl_10794_2;Bolln\u00e4s tidning 1880's (2015-08-31);Bolln\u00e4s tidning 1880-talet (2015-08-31);n/a, n/a;Swedish;News;A corpus with texts from Bolln\u00e4s tidning in the 1880's (1880-01\u20131880-05).;En korpus med texter fr\u00e5n Bolln\u00e4s tidning p\u00e5 1880-talet (1880-01\u20131880-05).;2015-04-08;corpus;http://hdl.handle.net/10794/112;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;http://creativecommons.org/licenses/by/4.0/;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;The National Library of Sweden;https://spraakbanken.gu.se/swe/resurs/kubhist-bollnastidning-1880",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6bc9b364-142f-5660-a7d6-3015ef54a552",
-    "notes": [
-        "A corpus with texts from Bolln\u00e4s tidning in the 1880's (1880-01\u20131880-05).",
-        "En korpus med texter fr\u00e5n Bolln\u00e4s tidning p\u00e5 1880-talet (1880-01\u20131880-05)."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/112"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "News"
-        }
-    ],
-    "title": [
-        "Bolln\u00e4s tidning 1880's (2015-08-31)",
-        "Bolln\u00e4s tidning 1880-talet (2015-08-31)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6bcb57ff-66e9-5364-80e5-ab97b5d94623.json b/oaitestdata/clarin-oai_dc/SET_1/json/6bcb57ff-66e9-5364-80e5-ab97b5d94623.json
deleted file mode 100644
index 6d730c4b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6bcb57ff-66e9-5364-80e5-ab97b5d94623.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5406",
-    "MetadataAccess": [
-        "oai:ota:oucs:5406"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pennant, Thomas, 1726-1798."
-    ],
-    "fulltext": "oai:ota:oucs:5406;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5406.xml;The journey from Chester to London;Pennant, Thomas, 1726-1798.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6bcb57ff-66e9-5364-80e5-ab97b5d94623",
-    "oai_identifier": [
-        "oai:ota:oucs:5406"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The journey from Chester to London"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5406.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6bfa68b4-6739-5fba-82b0-9da3ef34abf3.json b/oaitestdata/clarin-oai_dc/SET_1/json/6bfa68b4-6739-5fba-82b0-9da3ef34abf3.json
deleted file mode 100644
index d0393bed..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6bfa68b4-6739-5fba-82b0-9da3ef34abf3.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(2 files : ca. 82, 176 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0344",
-    "MetadataAccess": [
-        "oai:ota:oucs:0344"
-    ],
-    "PublicationYear": [
-        "804-810"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Utopian literature"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "More, Thomas, Sir, Saint, 1478-1535"
-    ],
-    "fulltext": "oai:ota:oucs:0344;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0344.xml;Utopia : Parts 1 and 2 / Sir Thomas More;More, Thomas, Sir, Saint, 1478-1535;804-810;text_and_corpus_linguistics;Utopias in literature -- 16th century;Oxford Text Archive, University of Oxford;(2 files : ca. 82, 176 KB);Text;Utopian literature;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6bfa68b4-6739-5fba-82b0-9da3ef34abf3",
-    "oai_identifier": [
-        "oai:ota:oucs:0344"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Utopias literature -- th century"
-        }
-    ],
-    "title": [
-        "Utopia : Parts 1 and 2 / Sir Thomas More"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0344.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6bfb3833-68c9-504d-899a-a94fd891707d.json b/oaitestdata/clarin-oai_dc/SET_1/json/6bfb3833-68c9-504d-899a-a94fd891707d.json
deleted file mode 100644
index 873d7b5d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6bfb3833-68c9-504d-899a-a94fd891707d.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1730",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1730"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1730",
-    "PublicationTimestamp": "2016-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Bojar, Ond\u0159ej",
-        "Kocmi, Tom"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1730;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Extended Morphosyntactic Testset for Word2Vec;Kocmi, Tom;Bojar, Ond\u0159ej;syntactic questions;We have created test set for syntactic questions presented in the paper [1] which is more general than Mikolov's [2]. Since we were interested in morphosyntactic relations, we extended only the questions of the syntactic type with exception of nationality adjectives which is already covered completely in Mikolov's test set.\r\n\r\nWe constructed the pairs more or less manually, taking inspiration in the Czech side of the CzEng corpus [3], where explicit morphological annotation allows to identify various pairs of Czech words (different grades of adjectives, words and their negations, etc.). The word-aligned English words often shared the same properties. Another sources of pairs were acquired from various webpages usually written for learners of English. For example for verb tense, we relied on a freely available list of English verbs and their morphological variations.\r\n\r\nWe have included 100-1000 different pairs for each question set. The questions were constructed from the pairs similarly as by Mikolov: generating all possible pairs of pairs. This leads to millions of questions, so we randomly selected 1000 instances per question set, to keep the test set in the same order of magnitude. Additionally, we decided to extend set of questions on opposites to cover not only opposites of adjectives but also of nouns and verbs.;2016-05-30;lexicalConceptualResource;http://hdl.handle.net/11234/1-1730;eng;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6bfb3833-68c9-504d-899a-a94fd891707d",
-    "notes": [
-        "We have created test set for syntactic questions presented in the paper [1] which is more general than Mikolov's [2]. Since we were interested in morphosyntactic relations, we extended only the questions of the syntactic type with exception of nationality adjectives which is already covered completely in Mikolov's test set.\r\n\r\nWe constructed the pairs more or less manually, taking inspiration in the Czech side of the CzEng corpus [3], where explicit morphological annotation allows to identify various pairs of Czech words (different grades of adjectives, words and their negations, etc.). The word-aligned English words often shared the same properties. Another sources of pairs were acquired from various webpages usually written for learners of English. For example for verb tense, we relied on a freely available list of English verbs and their morphological variations.\r\n\r\nWe have included 100-1000 different pairs for each question set. The questions were constructed from the pairs similarly as by Mikolov: generating all possible pairs of pairs. This leads to millions of questions, so we randomly selected 1000 instances per question set, to keep the test set in the same order of magnitude. Additionally, we decided to extend set of questions on opposites to cover not only opposites of adjectives but also of nouns and verbs."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1730"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "syntactic questions"
-        }
-    ],
-    "title": [
-        "Extended Morphosyntactic Testset for Word2Vec"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6c1316c1-3d8e-5bbf-86b7-24f5b2629ad3.json b/oaitestdata/clarin-oai_dc/SET_1/json/6c1316c1-3d8e-5bbf-86b7-24f5b2629ad3.json
deleted file mode 100644
index 83e7bb5b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6c1316c1-3d8e-5bbf-86b7-24f5b2629ad3.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3133",
-    "MetadataAccess": [
-        "oai:ota:oucs:3133"
-    ],
-    "PublicationTimestamp": "1764-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1764"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Thacher, Oxenbridge, 1719-1765"
-    ],
-    "fulltext": "oai:ota:oucs:3133;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3133.xml;The sentiments of a British American;Thacher, Oxenbridge, 1719-1765;not after: 1764;text_and_corpus_linguistics;United States -- History -- Revolution, 1775-1783;eng;Oxford Text Archive, University of Oxford;Triggs, Jeffery;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6c1316c1-3d8e-5bbf-86b7-24f5b2629ad3",
-    "oai_identifier": [
-        "oai:ota:oucs:3133"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "United States -- History -- Revolution"
-        }
-    ],
-    "title": [
-        "The sentiments of a British American"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3133.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6c1f196a-e5e3-5164-bf96-bb4988e7fb70.json b/oaitestdata/clarin-oai_dc/SET_1/json/6c1f196a-e5e3-5164-bf96-bb4988e7fb70.json
deleted file mode 100644
index 936b22aa..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6c1f196a-e5e3-5164-bf96-bb4988e7fb70.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Germanic Lexicon Project"
-    ],
-    "Contributor": [
-        "Crist, Sean"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-982",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-982"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-982",
-    "PublicationTimestamp": "2006-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2006"
-    ],
-    "Publisher": [
-        "Germanic Lexicon Project"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Czech Republic"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-982;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;W\u00f6rterbuch der Indogermanischen Sprachen: Dritter Teil: Wortschatz der Germanischen Spracheinheit;Crist, Sean;A dictionary of reconstructed Proto-Germanic, organized by reconstructed lemmata, with each entry including the attested reflexes in the daughter Germanic languages, as well as cognates in the other Indo-European branches.;2006;toolService;http://hdl.handle.net/11372/LRT-982;downloadable_files_count: 0;Czech Republic;Germanic Lexicon Project;http://lexicon.ff.cuni.cz/texts/pgmc_torp_about.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6c1f196a-e5e3-5164-bf96-bb4988e7fb70",
-    "notes": [
-        "A dictionary of reconstructed Proto-Germanic, organized by reconstructed lemmata, with each entry including the attested reflexes in the daughter Germanic languages, as well as cognates in the other Indo-European branches."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-982"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "W\u00f6rterbuch der Indogermanischen Sprachen: Dritter Teil: Wortschatz der Germanischen Spracheinheit"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6c25e111-e26a-5c83-8a10-1d6d74223480.json b/oaitestdata/clarin-oai_dc/SET_1/json/6c25e111-e26a-5c83-8a10-1d6d74223480.json
deleted file mode 100644
index 51a67178..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6c25e111-e26a-5c83-8a10-1d6d74223480.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "ClarinPL"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/plain",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/vnd.oasis.opendocument.text",
-        "downloadable_files_count: 17",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/414",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/414"
-    ],
-    "PID": "http://hdl.handle.net/11321/414",
-    "PublicationTimestamp": "2017-07-09T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "ClarinPL"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Idczak, Aleksandra"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/414;2017-07-09T16:19:04Z;hdl_11321_3;hdl_11321_4;Korpus testowy;Idczak, Aleksandra;test;Pr\u00f3ba - Test - Poligon;2017-07-09;corpus;http://hdl.handle.net/11321/414;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;text/plain;application/msword;text/plain;application/msword;application/vnd.oasis.opendocument.text;downloadable_files_count: 17;ClarinPL",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6c25e111-e26a-5c83-8a10-1d6d74223480",
-    "notes": [
-        "Pr\u00f3ba - Test - Poligon"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/414"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "test"
-        }
-    ],
-    "title": [
-        "Korpus testowy"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6c4b2fcd-19f2-5c75-a861-80eff1eec27a.json b/oaitestdata/clarin-oai_dc/SET_1/json/6c4b2fcd-19f2-5c75-a861-80eff1eec27a.json
deleted file mode 100644
index a42ba44b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6c4b2fcd-19f2-5c75-a861-80eff1eec27a.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "A"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1548",
-    "MetadataAccess": [
-        "oai:ota:oucs:1548"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dickens, Charles"
-    ],
-    "fulltext": "oai:ota:oucs:1548;2018-04-16T15:30:51Z;http://ota.ox.ac.uk/headers/1548.xml;A Christmas carol;Dickens, Charles;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;A;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6c4b2fcd-19f2-5c75-a861-80eff1eec27a",
-    "oai_identifier": [
-        "oai:ota:oucs:1548"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A Christmas carol"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1548.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6c4dc3b2-f882-57dd-a81f-270cfab621ad.json b/oaitestdata/clarin-oai_dc/SET_1/json/6c4dc3b2-f882-57dd-a81f-270cfab621ad.json
deleted file mode 100644
index 78350b48..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6c4dc3b2-f882-57dd-a81f-270cfab621ad.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Marek Troszy\u0144ski"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
-    ],
-    "Language": [],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/249",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/249"
-    ],
-    "PID": "http://hdl.handle.net/11321/249",
-    "PublicationTimestamp": "2016-04-25T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Marek Troszy\u0144ski"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0)",
-        "http://creativecommons.org/licenses/by-nc/3.0/",
-        "CC"
-    ],
-    "author": [
-        "UGC"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/249;2016-04-25T13:12:13Z;hdl_11321_3;hdl_11321_4;UGC_Ukraincy_01_16;UGC;Ukrai\u0144cy;Ukrainiec;Ukrainka;Teksty pobrane z wykorzystaniem us\u0142ugi Brand24;2016-04-25;corpus;http://hdl.handle.net/11321/249;Polski;Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0);http://creativecommons.org/licenses/by-nc/3.0/;CC;text/plain; charset=utf-8;application/vnd.openxmlformats-officedocument.wordprocessingml.document;downloadable_files_count: 1;Marek Troszy\u0144ski",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6c4dc3b2-f882-57dd-a81f-270cfab621ad",
-    "notes": [
-        "Teksty pobrane z wykorzystaniem us\u0142ugi Brand24"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/249"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Ukrainiec"
-        },
-        {
-            "name": "Ukrainka"
-        }
-    ],
-    "title": [
-        "UGC_Ukraincy_01_16"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6c6702ba-8cca-5cec-8167-46df56af20a4.json b/oaitestdata/clarin-oai_dc/SET_1/json/6c6702ba-8cca-5cec-8167-46df56af20a4.json
deleted file mode 100644
index d7a29c39..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6c6702ba-8cca-5cec-8167-46df56af20a4.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4947",
-    "MetadataAccess": [
-        "oai:ota:oucs:4947"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gentleman, Francis, 1728-1784."
-    ],
-    "fulltext": "oai:ota:oucs:4947;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4947.xml;The dramatic censor: or, critical companion. ... [pt.1];Gentleman, Francis, 1728-1784.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6c6702ba-8cca-5cec-8167-46df56af20a4",
-    "oai_identifier": [
-        "oai:ota:oucs:4947"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The dramatic censor: or, critical companion. ... [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4947.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6c69b23a-c4c0-5c0c-9de5-d241af1fcd9b.json b/oaitestdata/clarin-oai_dc/SET_1/json/6c69b23a-c4c0-5c0c-9de5-d241af1fcd9b.json
deleted file mode 100644
index 19b1c531..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6c69b23a-c4c0-5c0c-9de5-d241af1fcd9b.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4430",
-    "MetadataAccess": [
-        "oai:ota:oucs:4430"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Defoe, Daniel, 1661?-1731."
-    ],
-    "fulltext": "oai:ota:oucs:4430;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4430.xml;Advice to the people of Great Britain: with respect to two important points of their future conduct. I. What they ought to expect from the King. II. How they ought to behave to him.;Defoe, Daniel, 1661?-1731.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6c69b23a-c4c0-5c0c-9de5-d241af1fcd9b",
-    "oai_identifier": [
-        "oai:ota:oucs:4430"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Advice to the people of Great Britain: with respect to two important points of their future conduct. I. What they ought to expect from the King. II. How they ought to behave to him."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4430.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6c75b6f5-cdcc-5160-a30f-f61fde6de002.json b/oaitestdata/clarin-oai_dc/SET_1/json/6c75b6f5-cdcc-5160-a30f-f61fde6de002.json
deleted file mode 100644
index a1353711..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6c75b6f5-cdcc-5160-a30f-f61fde6de002.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Linguistic Modeling Department, IPP, Bulgarian Academy of Sciences"
-    ],
-    "Contributor": [
-        "Simov, Alex",
-        "Kouylekov, Milen",
-        "Simov, Kiril"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1173",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1173"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1173",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Linguistic Modeling Department, IPP, Bulgarian Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Bulgaria"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1173;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;CLaRK System - an XML-based system for Corpora Development;Simov, Kiril;Simov, Alex;Kouylekov, Milen;corpus development;The CLaRK System incorporates several technologies:  - XML technology - Unicode - Cascaded Regular Grammars; - Constraints over XML Documents  On the basis of these technologies the following tools are implemented: XML Editor, Unicode Tokeniser, Sorting tool, Removing and Extracting tool, Concordancer, XSLT tool, Cascaded Regular Grammar tool, etc.  1 Unicode tokenization  In order to provide possibility for imposing constraints over the textual node and to segment them in meaningful way, the CLaRK System supports a user-defined hierarchy of tokenisers. At the very basic level the user can define a tokeniser in terms of a set of token types. In this basic tokeniser each token type is defined by a set of UNICODE symbols. Above this basic level tokenisers, the user can define other tokenisers, for which the token types are defined as regular expressions over the tokens of some other tokeniser, the so called parent tokeniser.  2 Regular Grammars  The regular grammars are the basic mechanism for linguistic processing of the content of an XML document within the system. The regular grammar processor applies a set of rules over the content of some elements in the document and incorporates the categories of the rules back in the document as XML mark-up. The content is processed before the application of the grammar rules in the following way: textual nodes are tokenized with respect to some appropriate tokeniser, the element nodes are textualized on the basis of XPath expressions that determine the important information about the element. The recognized word is substituted by a new XML mark-up, which can or can not contain the word.  3 Constraints  The constraints that we implemented in the CLaRK System are generally based on the XPath language. We use XPath expressions to determine some data within one or several XML documents and thus we evaluate some predicates over the data. There are two modes of using a constraint. In the first mode the constraint is used for validity check, similar to the validity check, which is based on DTD or XML schema. In the second mode, the constraint is used to support the change of the document in order it to satisfy the constraint. There are three types of constraints, implemented in the system: regular expression constraints, number restriction constraints, value restriction constraints.  4 Macro Language  In the CLaRK System the tools support a mechanism for describing their settings. On the basis of these descriptions (called queries) a tool can be applied only by pointing to a certain description record. Each query contains the states of all settings and options which the corresponding tool has. Once having this kind of queries there is a special tool for combining and applying them in groups (macros). During application the queries are executed successively and the result from an application is an input for the next one.  For a better control on the process of applying several queries in one we introduce several conditional operators. These operators can determine the next query for application depending on certain conditions. When a condition for such an operator is satisfied, the execution continues from a location defined in the operator. The mechanism for addressing queries is based on user defined labels. When a condition is not satisfied the operator is ignored and the process continues from the position following the operator. In this way constructions like IF-THEN-ELSE and WHILE-DO easily can be expressed.  The system supports five types of control operators:  IF (XPath): the condition is an XPath expression which is evaluated on the current working document. If the result is a non-empty node-set, non-empty string, positive number or true boolean value the condition is satisfied;  IF NOT (XPath): the same kind of condition as the previous one but the approving result is negated;  IF CHANGED: the condition is satisfied if the preceding operation has changed the current working document or has produced a non-empty result document (depending on the operation);  IF NOT CHANGED: the condition is satisfied if either the previous operation did not change the working document or did not produce a non-empty result.  GOTO: unconditional changing the execution position.  Each macro defined in the system can have its own query and can be incorporated in another macro. In this way some limited form of subroutine can be implemented.  The new version of CLaRK will support server applications, calls to/from external programs.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1173;downloadable_files_count: 0;Bulgaria;Linguistic Modeling Department, IPP, Bulgarian Academy of Sciences;http://www.bultreebank.org/clark/index.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6c75b6f5-cdcc-5160-a30f-f61fde6de002",
-    "notes": [
-        "The CLaRK System incorporates several technologies:  - XML technology - Unicode - Cascaded Regular Grammars; - Constraints over XML Documents  On the basis of these technologies the following tools are implemented: XML Editor, Unicode Tokeniser, Sorting tool, Removing and Extracting tool, Concordancer, XSLT tool, Cascaded Regular Grammar tool, etc.  1 Unicode tokenization  In order to provide possibility for imposing constraints over the textual node and to segment them in meaningful way, the CLaRK System supports a user-defined hierarchy of tokenisers. At the very basic level the user can define a tokeniser in terms of a set of token types. In this basic tokeniser each token type is defined by a set of UNICODE symbols. Above this basic level tokenisers, the user can define other tokenisers, for which the token types are defined as regular expressions over the tokens of some other tokeniser, the so called parent tokeniser.  2 Regular Grammars  The regular grammars are the basic mechanism for linguistic processing of the content of an XML document within the system. The regular grammar processor applies a set of rules over the content of some elements in the document and incorporates the categories of the rules back in the document as XML mark-up. The content is processed before the application of the grammar rules in the following way: textual nodes are tokenized with respect to some appropriate tokeniser, the element nodes are textualized on the basis of XPath expressions that determine the important information about the element. The recognized word is substituted by a new XML mark-up, which can or can not contain the word.  3 Constraints  The constraints that we implemented in the CLaRK System are generally based on the XPath language. We use XPath expressions to determine some data within one or several XML documents and thus we evaluate some predicates over the data. There are two modes of using a constraint. In the first mode the constraint is used for validity check, similar to the validity check, which is based on DTD or XML schema. In the second mode, the constraint is used to support the change of the document in order it to satisfy the constraint. There are three types of constraints, implemented in the system: regular expression constraints, number restriction constraints, value restriction constraints.  4 Macro Language  In the CLaRK System the tools support a mechanism for describing their settings. On the basis of these descriptions (called queries) a tool can be applied only by pointing to a certain description record. Each query contains the states of all settings and options which the corresponding tool has. Once having this kind of queries there is a special tool for combining and applying them in groups (macros). During application the queries are executed successively and the result from an application is an input for the next one.  For a better control on the process of applying several queries in one we introduce several conditional operators. These operators can determine the next query for application depending on certain conditions. When a condition for such an operator is satisfied, the execution continues from a location defined in the operator. The mechanism for addressing queries is based on user defined labels. When a condition is not satisfied the operator is ignored and the process continues from the position following the operator. In this way constructions like IF-THEN-ELSE and WHILE-DO easily can be expressed.  The system supports five types of control operators:  IF (XPath): the condition is an XPath expression which is evaluated on the current working document. If the result is a non-empty node-set, non-empty string, positive number or true boolean value the condition is satisfied;  IF NOT (XPath): the same kind of condition as the previous one but the approving result is negated;  IF CHANGED: the condition is satisfied if the preceding operation has changed the current working document or has produced a non-empty result document (depending on the operation);  IF NOT CHANGED: the condition is satisfied if either the previous operation did not change the working document or did not produce a non-empty result.  GOTO: unconditional changing the execution position.  Each macro defined in the system can have its own query and can be incorporated in another macro. In this way some limited form of subroutine can be implemented.  The new version of CLaRK will support server applications, calls to/from external programs."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1173"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus development"
-        }
-    ],
-    "title": [
-        "CLaRK System - an XML-based system for Corpora Development"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6c8f6d70-8cc9-5931-b0b1-a839d0ecc79b.json b/oaitestdata/clarin-oai_dc/SET_1/json/6c8f6d70-8cc9-5931-b0b1-a839d0ecc79b.json
deleted file mode 100644
index c73af26f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6c8f6d70-8cc9-5931-b0b1-a839d0ecc79b.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-43CD-0",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-43CD-0"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-43CD-0",
-    "PublicationTimestamp": "2014-02-14T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11858/00-097C-0000-0001-48FE-9"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Straka, Milan",
-        "Strakov\u00e1, Jana"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-43CD-0;2018-07-02T22:05:53Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;MorphoDiTa: Morphological Dictionary and Tagger;Straka, Milan;Strakov\u00e1, Jana;tagging;morphological analysis;morphological generation;tokenization;MorphoDiTa: Morphological Dictionary and Tagger is an open-source tool for morphological analysis of natural language texts. It performs morphological analysis, morphological generation, tagging and tokenization and is distributed as a standalone tool or a library, along with trained linguistic models. In the Czech language, MorphoDiTa achieves state-of-the-art results with a throughput around 10-200K words per second. MorphoDiTa is a free software under LGPL license and the linguistic models are free for non-commercial use and distributed under CC BY-NC-SA license, although for some models the original data used to create the model may impose additional licensing conditions.;2014-02-14;toolService;http://hdl.handle.net/11858/00-097C-0000-0023-43CD-0;eng;http://hdl.handle.net/11858/00-097C-0000-0001-48FE-9;downloadable_files_count: 0;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/morphodita",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6c8f6d70-8cc9-5931-b0b1-a839d0ecc79b",
-    "notes": [
-        "MorphoDiTa: Morphological Dictionary and Tagger is an open-source tool for morphological analysis of natural language texts. It performs morphological analysis, morphological generation, tagging and tokenization and is distributed as a standalone tool or a library, along with trained linguistic models. In the Czech language, MorphoDiTa achieves state-of-the-art results with a throughput around 10-200K words per second. MorphoDiTa is a free software under LGPL license and the linguistic models are free for non-commercial use and distributed under CC BY-NC-SA license, although for some models the original data used to create the model may impose additional licensing conditions."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-43CD-0"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "morphological analysis"
-        },
-        {
-            "name": "morphological generation"
-        },
-        {
-            "name": "tokenization"
-        }
-    ],
-    "title": [
-        "MorphoDiTa: Morphological Dictionary and Tagger"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6ca1d9af-5a0c-576c-87cd-ab42f87977c1.json b/oaitestdata/clarin-oai_dc/SET_1/json/6ca1d9af-5a0c-576c-87cd-ab42f87977c1.json
deleted file mode 100644
index 1fc33669..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6ca1d9af-5a0c-576c-87cd-ab42f87977c1.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1007",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1007"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1007",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1007;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LAC Umpithamu Corpus;Language and Cognition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1007;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI576232%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6ca1d9af-5a0c-576c-87cd-ab42f87977c1",
-    "notes": [
-        "Language and Cognition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1007"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LAC Umpithamu Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6cb73552-98e9-5199-a5f2-b224c5282d99.json b/oaitestdata/clarin-oai_dc/SET_1/json/6cb73552-98e9-5199-a5f2-b224c5282d99.json
deleted file mode 100644
index 7f7327d5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6cb73552-98e9-5199-a5f2-b224c5282d99.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3844",
-    "MetadataAccess": [
-        "oai:ota:oucs:3844"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Arbuthnot, John, 1667-1735."
-    ],
-    "fulltext": "oai:ota:oucs:3844;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3844.xml;An appendix to John Bull still in his senses: or, Law is a bottomless-pit. Printed from a manuscript found in the cabinet of the famous Sir Humphry Polesworth: and publish'd, (as well as the three former parts) by the author of the New Atalantis.;Arbuthnot, John, 1667-1735.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6cb73552-98e9-5199-a5f2-b224c5282d99",
-    "oai_identifier": [
-        "oai:ota:oucs:3844"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An appendix to John Bull still in his senses: or, Law is a bottomless-pit. Printed from a manuscript found in the cabinet of the famous Sir Humphry Polesworth: and publish'd, (as well as the three former parts) by the author of the New Atalantis."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3844.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6d17a3dd-058a-5dab-a707-30982f4aa7a0.json b/oaitestdata/clarin-oai_dc/SET_1/json/6d17a3dd-058a-5dab-a707-30982f4aa7a0.json
deleted file mode 100644
index 7c0d0290..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6d17a3dd-058a-5dab-a707-30982f4aa7a0.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1404",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1404"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1404",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1404;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;freeling_tagging;Freeling-based part-of-speech tagger.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1404;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6d17a3dd-058a-5dab-a707-30982f4aa7a0",
-    "notes": [
-        "Freeling-based part-of-speech tagger."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1404"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "freeling_tagging"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6d845760-1934-5548-9eb5-00f2224f5711.json b/oaitestdata/clarin-oai_dc/SET_1/json/6d845760-1934-5548-9eb5-00f2224f5711.json
deleted file mode 100644
index b44bd7a4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6d845760-1934-5548-9eb5-00f2224f5711.json
+++ /dev/null
@@ -1,49 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4683",
-    "MetadataAccess": [
-        "oai:ota:oucs:4683"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:4683;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4683.xml;Aristotle's master-piece: or the secrets of generation display'd in all the parts thereof; ... Very necessary for all midwives, nurses and young-married-women.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6d845760-1934-5548-9eb5-00f2224f5711",
-    "oai_identifier": [
-        "oai:ota:oucs:4683"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Aristotle's master-piece: or the secrets of generation display'd in all the parts thereof; ... Very necessary for all midwives, nurses and young-married-women."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4683.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6da10c84-161c-5a7c-a746-4a90de70926d.json b/oaitestdata/clarin-oai_dc/SET_1/json/6da10c84-161c-5a7c-a746-4a90de70926d.json
deleted file mode 100644
index 93ced838..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6da10c84-161c-5a7c-a746-4a90de70926d.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2619",
-    "MetadataAccess": [
-        "oai:ota:oucs:2619"
-    ],
-    "PublicationTimestamp": "1705-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1705"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2619;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2619.xml;Wotton's Observations on A Tale of a tub;Swift, Jonathan, 1667-1745;1705;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6da10c84-161c-5a7c-a746-4a90de70926d",
-    "oai_identifier": [
-        "oai:ota:oucs:2619"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Wotton's Observations on A Tale of a tub"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2619.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6db28df9-1353-5083-9d22-d4e178b82494.json b/oaitestdata/clarin-oai_dc/SET_1/json/6db28df9-1353-5083-9d22-d4e178b82494.json
deleted file mode 100644
index f0adeac2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6db28df9-1353-5083-9d22-d4e178b82494.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=0176c39ae9cd11e4a2aa782bcb074135ba7d767f645a48dca1d50ee3c9504253",
-    "MetadataAccess": [
-        "0176c39ae9cd11e4a2aa782bcb074135ba7d767f645a48dca1d50ee3c9504253"
-    ],
-    "PublicationTimestamp": "2016-11-02T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "fulltext": "0176c39ae9cd11e4a2aa782bcb074135ba7d767f645a48dca1d50ee3c9504253;2018-11-15T16:40:14Z;corpus;corpus:text;QTLeap Corpus V1.2;The QTLeap corpus is composed by 4000 question and answer pairs in the domain of computer and IT troubleshooting for both hardware and software. This material was collected using a support service via chat, this implies that the corpus is composed by naturally occurring utterances produced by users while interacting with a service.\nThe corpus was collected selecting the data contained in a database where all the interactions with the clients are saved. Only interactions composed by one question and the respective answer were included in the corpus.;2016-11-02",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6db28df9-1353-5083-9d22-d4e178b82494",
-    "notes": [
-        "The QTLeap corpus is composed by 4000 question and answer pairs in the domain of computer and IT troubleshooting for both hardware and software. This material was collected using a support service via chat, this implies that the corpus is composed by naturally occurring utterances produced by users while interacting with a service.\nThe corpus was collected selecting the data contained in a database where all the interactions with the clients are saved. Only interactions composed by one question and the respective answer were included in the corpus."
-    ],
-    "oai_identifier": [
-        "0176c39ae9cd11e4a2aa782bcb074135ba7d767f645a48dca1d50ee3c9504253"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "QTLeap Corpus V1.2"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6db8591d-8225-5ecd-a049-de78a30446de.json b/oaitestdata/clarin-oai_dc/SET_1/json/6db8591d-8225-5ecd-a049-de78a30446de.json
deleted file mode 100644
index 3a636a55..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6db8591d-8225-5ecd-a049-de78a30446de.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Anna Niepytalska-Osiecka"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 102",
-        "text/plain; charset=utf-8",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/441",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/441"
-    ],
-    "PID": "http://hdl.handle.net/11321/441",
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Anna Niepytalska-Osiecka"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Niepytalska-Osiecka, Anna"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/441;2017-11-21T08:36:38Z;hdl_11321_3;hdl_11321_4;Feminism2;Niepytalska-Osiecka, Anna;feminism feminist;How do Poles understand the concepts of feminism and feminist and how do they use these terms? Reconnaissance.;2017;corpus;http://hdl.handle.net/11321/441;polish;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;downloadable_files_count: 102;Anna Niepytalska-Osiecka;https://www.researchgate.net/project/How-do-Poles-understand-the-concepts-of-feminism-and-feminist-and-how-do-they-use-these-terms-Reconnaissance",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6db8591d-8225-5ecd-a049-de78a30446de",
-    "notes": [
-        "How do Poles understand the concepts of feminism and feminist and how do they use these terms? Reconnaissance."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/441"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "feminism feminist"
-        }
-    ],
-    "title": [
-        "Feminism2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6dc06557-75e0-55e6-932d-bf551edbef39.json b/oaitestdata/clarin-oai_dc/SET_1/json/6dc06557-75e0-55e6-932d-bf551edbef39.json
deleted file mode 100644
index 380d0c5e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6dc06557-75e0-55e6-932d-bf551edbef39.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Royster, Paul"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 1.3 MB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1629",
-    "MetadataAccess": [
-        "oai:ota:oucs:1629"
-    ],
-    "PublicationTimestamp": "1849-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1849"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Melville, Herman, 1819-1891"
-    ],
-    "fulltext": "oai:ota:oucs:1629;2018-07-27T10:07:04Z;http://ota.ox.ac.uk/headers/1629.xml;Moby Dick / Herman Melville;The whale;Melville, Herman, 1819-1891;1849;text_and_corpus_linguistics;American literature -- 19th century;Oxford Text Archive, University of Oxford;Royster, Paul;text/sgml;(1 file : ca. 1.3 MB);Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6dc06557-75e0-55e6-932d-bf551edbef39",
-    "oai_identifier": [
-        "oai:ota:oucs:1629"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "American literature -- th century"
-        }
-    ],
-    "title": [
-        "Moby Dick / Herman Melville",
-        "The whale"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1629.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6ddc05cb-b475-58b1-84d6-bbac7146e5a8.json b/oaitestdata/clarin-oai_dc/SET_1/json/6ddc05cb-b475-58b1-84d6-bbac7146e5a8.json
deleted file mode 100644
index 9121965b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6ddc05cb-b475-58b1-84d6-bbac7146e5a8.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 2"
-    ],
-    "Language": [
-        "Slovak",
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-AADF-0",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-AADF-0"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0006-AADF-0",
-    "PublicationTimestamp": "2012-05-15T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/231720"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Galu\u0161\u010d\u00e1kov\u00e1, Petra",
-        "Garab\u00edk, Radovan",
-        "Bojar, Ond\u0159ej"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-AADF-0;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Czech-Slovak Parallel Corpus;Galu\u0161\u010d\u00e1kov\u00e1, Petra;Garab\u00edk, Radovan;Bojar, Ond\u0159ej;parallel corpus;Czech-Slovak corpus;Czech-Slovak parallel corpus consisting of several freely available corpora (Acquis [1], Europarl [2], Official Journal of the European Union [3] and part of OPUS corpus [4] \u2013 EMEA,  EUConst, KDE4 and PHP) and downloaded website of European Commission [5]. Corpus is published in both in plaintext format and with an automatic morphological annotation. \r\n\r\nReferences: \r\n[1] http://langtech.jrc.it/JRC-Acquis.html/\r\n[2] http://www.statmt.org/europarl/\r\n[3] http://apertium.eu/data\r\n[4] http://opus.lingfil.uu.se/\r\n[5] http://ec.europa.eu/;2012-05-15;corpus;http://hdl.handle.net/11858/00-097C-0000-0006-AADF-0;slk;ces;info:eu-repo/grantAgreement/EC/FP7/231720;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/x-gzip;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6ddc05cb-b475-58b1-84d6-bbac7146e5a8",
-    "notes": [
-        "Czech-Slovak parallel corpus consisting of several freely available corpora (Acquis [1], Europarl [2], Official Journal of the European Union [3] and part of OPUS corpus [4] \u2013 EMEA,  EUConst, KDE4 and PHP) and downloaded website of European Commission [5]. Corpus is published in both in plaintext format and with an automatic morphological annotation. \r\n\r\nReferences: \r\n[1] http://langtech.jrc.it/JRC-Acquis.html/\r\n[2] http://www.statmt.org/europarl/\r\n[3] http://apertium.eu/data\r\n[4] http://opus.lingfil.uu.se/\r\n[5] http://ec.europa.eu/"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-AADF-0"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parallel corpus"
-        },
-        {
-            "name": "Czech-Slovak corpus"
-        }
-    ],
-    "title": [
-        "Czech-Slovak Parallel Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6deab4ab-d60b-5448-9f28-872c2744513a.json b/oaitestdata/clarin-oai_dc/SET_1/json/6deab4ab-d60b-5448-9f28-872c2744513a.json
deleted file mode 100644
index 92c3a826..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6deab4ab-d60b-5448-9f28-872c2744513a.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "s.n."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-153925",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-153925"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CE3-5",
-    "PublicationTimestamp": "1773-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1773"
-    ],
-    "Publisher": [
-        "s.n."
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/153925",
-        "oai:jbc.bj.uj.edu.pl:publication:162210"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1701/1800"
-    ],
-    "TempCoverageBegin": 53662478399,
-    "TempCoverageEnd": 53662478399,
-    "TemporalCoverage": " point in time : 1701-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1701-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1701-07-01T11:59:59Z",
-    "author": [
-        "Minasowicz, J\u00f3zef Epifani (1718-1796)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-153925;2019-02-28T18:35:37Z;Za\u0142uszczyny Albo Zbior Rymow Oyczystych Wielkiemu Imieniowi Jasnie Wielmoznego [...] Jozefa Andrzeia Hrabi na Za\u0142uskach Junoszy Za\u0142uskiego [...] Biskupa Kiiowskiego Y Czerniechowskiego [...];Minasowicz, J\u00f3zef Epifani (1718-1796);starodruki 18\u00a0w.;poezja polska 18\u00a0w.;Za\u0142uski, J\u00f3zef Andrzej (1702-1774). [Adr. ded.];s.n.;1773;starodruk;application/xml;clarind-uds:poldilemma-153925;hdl:11858/00-246C-0000-0023-8CE3-5;Biblioteka Jagiello\u0144ska, BJ St. Dr. 390308 I;pol;http://jbc.bj.uj.edu.pl/Content/153925;oai:jbc.bj.uj.edu.pl:publication:162210;1701/1800;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6deab4ab-d60b-5448-9f28-872c2744513a",
-    "notes": [
-        "Za\u0142uski, J\u00f3zef Andrzej (1702-1774). [Adr. ded.]"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-153925"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Za\u0142uszczyny Albo Zbior Rymow Oyczystych Wielkiemu Imieniowi Jasnie Wielmoznego [...] Jozefa Andrzeia Hrabi na Za\u0142uskach Junoszy Za\u0142uskiego [...] Biskupa Kiiowskiego Y Czerniechowskiego [...]"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6df4b396-1685-583f-a4f8-1c83e17e93ef.json b/oaitestdata/clarin-oai_dc/SET_1/json/6df4b396-1685-583f-a4f8-1c83e17e93ef.json
deleted file mode 100644
index 8d7384a8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6df4b396-1685-583f-a4f8-1c83e17e93ef.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1679",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1679"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1679",
-    "PublicationTimestamp": "2016-03-31T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/H2020/645452"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Bojar, Ond\u0159ej",
-        "Zelenina, Maria",
-        "D\u011bcht\u011brenko, Filip"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1679;2018-07-02T22:05:54Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Eye-Tracking Recordings from a Pilot Study of WMT-style MT Outputs Ranking;Bojar, Ond\u0159ej;D\u011bcht\u011brenko, Filip;Zelenina, Maria;eye-tracking;MT evaluation;This package contains the eye-tracker recordings of 8 subjects evaluating English-to-Czech machine translation quality using the WMT-style ranking of sentences.\r\n\r\nWe provide the set of sentences evaluated, the exact screens presented to the annotators (including bounding box information for every area of interest and even for individual letters in the text) and finally the raw EyeLink II files with gaze trajectories.\r\n\r\nThe description of the experiment can be found in the paper:\r\n\r\nOnd\u0159ej Bojar, Filip D\u011bcht\u011brenko, Maria Zelenina. A Pilot Eye-Tracking Study of WMT-Style Ranking Evaluation.\r\nProceedings of the LREC 2016 Workshop \u201cTranslation Evaluation \u2013 From Fragmented Tools\r\nand Data Sets to an Integrated Ecosystem\u201d, Georg Rehm, Aljoscha Burchardt et al. (eds.). pp. 20-26. May 2016, Portoro\u017e, Slovenia.\r\n\r\nThis work has received funding from the European Union's Horizon 2020 research\r\nand innovation programme under grant agreement no. 645452 (QT21). This work was\r\npartially financially supported by the Government of Russian Federation, Grant\r\n074-U01.\r\n\r\nThis work has been using language resources developed, stored and distributed\r\nby the LINDAT/CLARIN project of the Ministry of Education, Youth and Sports of\r\nthe Czech Republic (project LM2010013).;2016-03-31;corpus;http://hdl.handle.net/11234/1-1679;ces;eng;info:eu-repo/grantAgreement/EC/H2020/645452;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6df4b396-1685-583f-a4f8-1c83e17e93ef",
-    "notes": [
-        "This package contains the eye-tracker recordings of 8 subjects evaluating English-to-Czech machine translation quality using the WMT-style ranking of sentences.\r\n\r\nWe provide the set of sentences evaluated, the exact screens presented to the annotators (including bounding box information for every area of interest and even for individual letters in the text) and finally the raw EyeLink II files with gaze trajectories.\r\n\r\nThe description of the experiment can be found in the paper:\r\n\r\nOnd\u0159ej Bojar, Filip D\u011bcht\u011brenko, Maria Zelenina. A Pilot Eye-Tracking Study of WMT-Style Ranking Evaluation.\r\nProceedings of the LREC 2016 Workshop \u201cTranslation Evaluation \u2013 From Fragmented Tools\r\nand Data Sets to an Integrated Ecosystem\u201d, Georg Rehm, Aljoscha Burchardt et al. (eds.). pp. 20-26. May 2016, Portoro\u017e, Slovenia.\r\n\r\nThis work has received funding from the European Union's Horizon 2020 research\r\nand innovation programme under grant agreement no. 645452 (QT21). This work was\r\npartially financially supported by the Government of Russian Federation, Grant\r\n074-U01.\r\n\r\nThis work has been using language resources developed, stored and distributed\r\nby the LINDAT/CLARIN project of the Ministry of Education, Youth and Sports of\r\nthe Czech Republic (project LM2010013)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1679"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "eye-tracking"
-        },
-        {
-            "name": "MT evaluation"
-        }
-    ],
-    "title": [
-        "Eye-Tracking Recordings from a Pilot Study of WMT-style MT Outputs Ranking"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6df7e7bb-3bd7-5e6e-a2c3-65c4920aaee3.json b/oaitestdata/clarin-oai_dc/SET_1/json/6df7e7bb-3bd7-5e6e-a2c3-65c4920aaee3.json
deleted file mode 100644
index a1b4afd0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6df7e7bb-3bd7-5e6e-a2c3-65c4920aaee3.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "Contact": [
-        "Royal Institute of Linguistics and Anthropology, Leiden, The Netherlands"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "audio/x-wav",
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-725",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-725"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-725",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Royal Institute of Linguistics and Anthropology, Leiden, The Netherlands"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Suriname"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-725;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Carib (Karinya) corpus;The data on the Carib language is collected by dr. Berend Hoff in the period 1955-1965. See: B.J. Hoff, The Carib Language, Phonology, Morphology, Text and Word Index. Verhandelingen van het Koninklijk Instituut voor Taal-, Land-, en Volkenkunde (Royal Institute of Linguistics and Anthropology) Vol. 55 (1968), Martinus Nijhoff: The Hague.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-725;audio/x-wav;downloadable_files_count: 0;Suriname;Royal Institute of Linguistics and Anthropology, Leiden, The Netherlands;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI359273%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6df7e7bb-3bd7-5e6e-a2c3-65c4920aaee3",
-    "notes": [
-        "The data on the Carib language is collected by dr. Berend Hoff in the period 1955-1965. See: B.J. Hoff, The Carib Language, Phonology, Morphology, Text and Word Index. Verhandelingen van het Koninklijk Instituut voor Taal-, Land-, en Volkenkunde (Royal Institute of Linguistics and Anthropology) Vol. 55 (1968), Martinus Nijhoff: The Hague."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-725"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Carib (Karinya) corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6e2f6b74-8495-5cbd-a174-395217206ba6.json b/oaitestdata/clarin-oai_dc/SET_1/json/6e2f6b74-8495-5cbd-a174-395217206ba6.json
deleted file mode 100644
index d784e323..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6e2f6b74-8495-5cbd-a174-395217206ba6.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contributor": [
-        "Hidley, Greg",
-        "Macrae-Gibson, O.d."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-867",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-867"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-867",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-867;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Complete Corpus of Anglo-Saxon Poetry;Hidley, Greg;Macrae-Gibson, O.d.;Plain-text electronic editions of Old English poems;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-867;eng;text/plain;downloadable_files_count: 0;United Kingdom;http://www.sacred-texts.com/neu/ascp/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6e2f6b74-8495-5cbd-a174-395217206ba6",
-    "notes": [
-        "Plain-text electronic editions of Old English poems"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-867"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Complete Corpus of Anglo-Saxon Poetry"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6e48415e-fa56-5dc7-8a13-39bfa3f423c8.json b/oaitestdata/clarin-oai_dc/SET_1/json/6e48415e-fa56-5dc7-8a13-39bfa3f423c8.json
deleted file mode 100644
index b7e819c2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6e48415e-fa56-5dc7-8a13-39bfa3f423c8.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Emilia"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/zip",
-        "downloadable_files_count: 9",
-        "application/vnd.oasis.opendocument.text"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/242",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/242"
-    ],
-    "PID": "http://hdl.handle.net/11321/242",
-    "PublicationTimestamp": "2016-01-27T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Emilia"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Ka, Emilia"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/242;2017-05-30T13:56:42Z;hdl_11321_3;hdl_11321_4;Teksty reklam TVP ABC;Ka, Emilia;reklama;teksty reklam emitowane na kanale TVP ABC miedzy lipcem 2014 a styczniem 2015;2016-01-27;corpus;http://hdl.handle.net/11321/242;pol;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;text/plain; charset=utf-8;application/vnd.oasis.opendocument.text;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;downloadable_files_count: 9;Emilia",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6e48415e-fa56-5dc7-8a13-39bfa3f423c8",
-    "notes": [
-        "teksty reklam emitowane na kanale TVP ABC miedzy lipcem 2014 a styczniem 2015"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/242"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "reklama"
-        }
-    ],
-    "title": [
-        "Teksty reklam TVP ABC"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6e548e45-6ca4-5ed2-803b-8c87f8ebb353.json b/oaitestdata/clarin-oai_dc/SET_1/json/6e548e45-6ca4-5ed2-803b-8c87f8ebb353.json
deleted file mode 100644
index 72a8f0d0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6e548e45-6ca4-5ed2-803b-8c87f8ebb353.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "Wroclaw University of Science and Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/415",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/415"
-    ],
-    "PID": "http://hdl.handle.net/11321/415",
-    "PublicationTimestamp": "2017-07-11T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Wroclaw University of Science and Technology"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Wroclaw University of Science and Technology"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/415;2017-07-28T11:57:11Z;hdl_11321_3;hdl_11321_4;Word combination lexicons;Wroclaw University of Science and Technology;multi-word units;lexicalisation;phraseology;idiom;terminology;corpus linguistics;10 lexicons comprising of several hundreds word combinations exhibiting various stages of lexicalisation (from free word combinations to fixed idioms) manually annotated by many linguists according to linguistic criteria (like semantic compositionality, syntactic idiosyncracy, terminological nature etc.) and intuitive sense of lexicalisation.;2017-07-11;lexicalConceptualResource;http://hdl.handle.net/11321/415;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;Wroclaw University of Science and Technology;http://nlp.pwr.wroc.pl",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6e548e45-6ca4-5ed2-803b-8c87f8ebb353",
-    "notes": [
-        "10 lexicons comprising of several hundreds word combinations exhibiting various stages of lexicalisation (from free word combinations to fixed idioms) manually annotated by many linguists according to linguistic criteria (like semantic compositionality, syntactic idiosyncracy, terminological nature etc.) and intuitive sense of lexicalisation."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/415"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "multi-word units"
-        },
-        {
-            "name": "lexicalisation"
-        },
-        {
-            "name": "phraseology"
-        },
-        {
-            "name": "idiom"
-        },
-        {
-            "name": "terminology"
-        },
-        {
-            "name": "corpus linguistics"
-        }
-    ],
-    "title": [
-        "Word combination lexicons"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6e5cc939-72ca-5370-acaa-ecd8e0fe8397.json b/oaitestdata/clarin-oai_dc/SET_1/json/6e5cc939-72ca-5370-acaa-ecd8e0fe8397.json
deleted file mode 100644
index afd29321..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6e5cc939-72ca-5370-acaa-ecd8e0fe8397.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Federacja Bibliotek Cyfrowych"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/162",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/162"
-    ],
-    "PID": "http://hdl.handle.net/11321/162",
-    "PublicationTimestamp": "2015-05-06T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Federacja Bibliotek Cyfrowych"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0)",
-        "http://creativecommons.org/licenses/by-sa/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Federacja Bibliotek Cyfrowych, Malak Piotr"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/162;2015-05-06T11:59:31Z;hdl_11321_3;hdl_11321_4;FBC metadata;Federacja Bibliotek Cyfrowych, Malak Piotr;digital libraries;Metadata of Polish digital libraries resources descriptions.;2015-05-06;corpus;http://hdl.handle.net/11321/162;pol;Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0);http://creativecommons.org/licenses/by-sa/3.0/;CC;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Federacja Bibliotek Cyfrowych;http://wizualizacjainformacji.pl/projekt.php",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6e5cc939-72ca-5370-acaa-ecd8e0fe8397",
-    "notes": [
-        "Metadata of Polish digital libraries resources descriptions."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/162"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "digital libraries"
-        }
-    ],
-    "title": [
-        "FBC metadata"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6e5d9f4d-0aef-517f-a674-3a0331caac05.json b/oaitestdata/clarin-oai_dc/SET_1/json/6e5d9f4d-0aef-517f-a674-3a0331caac05.json
deleted file mode 100644
index cf99c400..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6e5d9f4d-0aef-517f-a674-3a0331caac05.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "The Research Institute for the Languages of Finland"
-    ],
-    "Contributor": [
-        "Lounela, Mikko"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Finnish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-773",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-773"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-773",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "The Research Institute for the Languages of Finland"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Finland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-773;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Corpus of Finnish Literary Classics;Lounela, Mikko;period: 1880s&#8211;1930s;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-773;fin;downloadable_files_count: 0;Finland;The Research Institute for the Languages of Finland;http://kaino.kotus.fi/korpus/klassikot/meta/klassikot_coll_rdf.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6e5d9f4d-0aef-517f-a674-3a0331caac05",
-    "notes": [
-        "period: 1880s&#8211;1930s"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-773"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus of Finnish Literary Classics"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6e67039a-9970-59bc-b651-a419ecc4862b.json b/oaitestdata/clarin-oai_dc/SET_1/json/6e67039a-9970-59bc-b651-a419ecc4862b.json
deleted file mode 100644
index 539655f3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6e67039a-9970-59bc-b651-a419ecc4862b.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Gabler, Hans Walter, 1938-"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 457 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1359",
-    "MetadataAccess": [
-        "oai:ota:oucs:1359"
-    ],
-    "PublicationTimestamp": "1904-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1904"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Joyce, James, 1882-1941"
-    ],
-    "fulltext": "oai:ota:oucs:1359;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/1359.xml;Portrait of the artist as a young man;A portrait of the artist as a young man / James Joyce;Joyce, James, 1882-1941;1904;text_and_corpus_linguistics;Irish literature -- 20th century;eng;Oxford Text Archive, University of Oxford;Gabler, Hans Walter, 1938-;(1 file : ca. 457 KB);Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6e67039a-9970-59bc-b651-a419ecc4862b",
-    "oai_identifier": [
-        "oai:ota:oucs:1359"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Irish literature -- th century"
-        }
-    ],
-    "title": [
-        "Portrait of the artist as a young man",
-        "A portrait of the artist as a young man / James Joyce"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1359.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6e766df3-ece8-5125-946f-966dd5fe3435.json b/oaitestdata/clarin-oai_dc/SET_1/json/6e766df3-ece8-5125-946f-966dd5fe3435.json
deleted file mode 100644
index 85c680b8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6e766df3-ece8-5125-946f-966dd5fe3435.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Berlin-Brandenburg Academy of Sciences and Humanities"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/tei+xml",
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-977",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-977"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-977",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Berlin-Brandenburg Academy of Sciences and Humanities"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-977;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;ZEIT-Korpus (ZEIT & ZEIT online);Corpus of the weekly Die Zeit from 1946 - present day (complete runs from 1996). Over 100 million words in 200,000 articles. Updated daily. Part of DWDS project.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-977;deu;application/tei+xml;downloadable_files_count: 0;Germany;Berlin-Brandenburg Academy of Sciences and Humanities;http://www.dwds.de/ressourcen/korpora/#part_2",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6e766df3-ece8-5125-946f-966dd5fe3435",
-    "notes": [
-        "Corpus of the weekly Die Zeit from 1946 - present day (complete runs from 1996). Over 100 million words in 200,000 articles. Updated daily. Part of DWDS project."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-977"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "ZEIT-Korpus (ZEIT & ZEIT online)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6e8c21c5-92f9-511f-bfb5-d41ccb20500c.json b/oaitestdata/clarin-oai_dc/SET_1/json/6e8c21c5-92f9-511f-bfb5-d41ccb20500c.json
deleted file mode 100644
index b3e91def..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6e8c21c5-92f9-511f-bfb5-d41ccb20500c.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5163",
-    "MetadataAccess": [
-        "oai:ota:oucs:5163"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dampier, William, 1652-1715."
-    ],
-    "fulltext": "oai:ota:oucs:5163;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5163.xml;Voyages and descriptions: vol.II. In three parts, viz. I. A supplement of the voyage round the world, ... 2. Two voyages to Campeachy; ... 3. A discourse of trade-winds, breezes, storms, ... By Capt. William Dampier. Illustrated with particular maps and draughts. To which is added, a general index to both volumes. The third edition.;New voyage round the world.;Dampier, William, 1652-1715.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6e8c21c5-92f9-511f-bfb5-d41ccb20500c",
-    "oai_identifier": [
-        "oai:ota:oucs:5163"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Voyages and descriptions: vol.II. In three parts, viz. I. A supplement of the voyage round the world, ... 2. Two voyages to Campeachy; ... 3. A discourse of trade-winds, breezes, storms, ... By Capt. William Dampier. Illustrated with particular maps and draughts. To which is added, a general index to both volumes. The third edition.",
-        "New voyage round the world."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5163.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6eb90f0c-bbab-5bb6-ab96-bfd90f53d5f1.json b/oaitestdata/clarin-oai_dc/SET_1/json/6eb90f0c-bbab-5bb6-ab96-bfd90f53d5f1.json
deleted file mode 100644
index d592a687..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6eb90f0c-bbab-5bb6-ab96-bfd90f53d5f1.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3922",
-    "MetadataAccess": [
-        "oai:ota:oucs:3922"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gough, Strickland, d. 1752."
-    ],
-    "fulltext": "oai:ota:oucs:3922;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3922.xml;An enquiry into the causes of the decay of the dissenting interest: In a letter to a dissenting minister.;Gough, Strickland, d. 1752.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6eb90f0c-bbab-5bb6-ab96-bfd90f53d5f1",
-    "oai_identifier": [
-        "oai:ota:oucs:3922"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An enquiry into the causes of the decay of the dissenting interest: In a letter to a dissenting minister."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3922.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6ed51058-09e6-5e16-ae8a-cda208fe69b2.json b/oaitestdata/clarin-oai_dc/SET_1/json/6ed51058-09e6-5e16-ae8a-cda208fe69b2.json
deleted file mode 100644
index 66493152..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6ed51058-09e6-5e16-ae8a-cda208fe69b2.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Masaryk University, NLP Centre"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/x-xz"
-    ],
-    "Language": [
-        "Slovak"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-CCDB-0",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-CCDB-0"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-CCDB-0",
-    "PublicationTimestamp": "2011-12-16T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Masaryk University, NLP Centre"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/3.0/",
-        "PUB"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-CCDB-0;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;skTenTen;Slovak large corpus;Slovak large web corpus skTenTen, comprising 876,003,720 tokens.;2011-12-16;corpus;http://hdl.handle.net/11858/00-097C-0000-0001-CCDB-0;slk;Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0);http://creativecommons.org/licenses/by-nc-nd/3.0/;PUB;application/x-xz;text/plain; charset=utf-8;downloadable_files_count: 1;Masaryk University, NLP Centre",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6ed51058-09e6-5e16-ae8a-cda208fe69b2",
-    "notes": [
-        "Slovak large web corpus skTenTen, comprising 876,003,720 tokens."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-CCDB-0"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Slovak large corpus"
-        }
-    ],
-    "title": [
-        "skTenTen"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6ee73bd7-bbf9-50ec-bc2d-dbee1fc51ad9.json b/oaitestdata/clarin-oai_dc/SET_1/json/6ee73bd7-bbf9-50ec-bc2d-dbee1fc51ad9.json
deleted file mode 100644
index cbac96e7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6ee73bd7-bbf9-50ec-bc2d-dbee1fc51ad9.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 3",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Czech",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1650",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1650"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1650",
-    "PublicationTimestamp": "2016-02-22T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Apache License 2.0",
-        "http://opensource.org/licenses/Apache-2.0",
-        "PUB"
-    ],
-    "author": [
-        "Libovick\u00fd, Jind\u0159ich"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1650;2018-07-02T22:05:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;KER - Keyword Extractor;Libovick\u00fd, Jind\u0159ich;keyword extraction;KER is a keyword extractor that was designed for scanned texts in Czech and English. It is based on the standard tf-idf algorithm with the idf tables trained on texts from Wikipedia. To deal with the data sparsity, texts are preprocessed by Morphodita: morphological dictionary and tagger.;2016-02-22;toolService;http://hdl.handle.net/11234/1-1650;ces;eng;Apache License 2.0;http://opensource.org/licenses/Apache-2.0;PUB;application/x-gzip;application/octet-stream;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 3;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6ee73bd7-bbf9-50ec-bc2d-dbee1fc51ad9",
-    "notes": [
-        "KER is a keyword extractor that was designed for scanned texts in Czech and English. It is based on the standard tf-idf algorithm with the idf tables trained on texts from Wikipedia. To deal with the data sparsity, texts are preprocessed by Morphodita: morphological dictionary and tagger."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1650"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "keyword extraction"
-        }
-    ],
-    "title": [
-        "KER - Keyword Extractor"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6ee9c5ac-df7e-5d9e-8f85-b71f936053be.json b/oaitestdata/clarin-oai_dc/SET_1/json/6ee9c5ac-df7e-5d9e-8f85-b71f936053be.json
deleted file mode 100644
index ab487dac..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6ee9c5ac-df7e-5d9e-8f85-b71f936053be.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-926",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-926"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-926",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-926;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Tokharian A (East);ca. 100.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-926;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#TochA",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6ee9c5ac-df7e-5d9e-8f85-b71f936053be",
-    "notes": [
-        "ca. 100.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-926"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Tokharian A (East)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6efb5333-cb3e-53b2-ab07-4aeafb8030b3.json b/oaitestdata/clarin-oai_dc/SET_1/json/6efb5333-cb3e-53b2-ab07-4aeafb8030b3.json
deleted file mode 100644
index ec45a4fb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6efb5333-cb3e-53b2-ab07-4aeafb8030b3.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=bf2ccab65e6911e2a2aa782bcb0741354e5fd3c2b7424178bfdb8521ff85c7ce",
-    "MetadataAccess": [
-        "bf2ccab65e6911e2a2aa782bcb0741354e5fd3c2b7424178bfdb8521ff85c7ce"
-    ],
-    "PublicationTimestamp": "2013-01-31T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "bf2ccab65e6911e2a2aa782bcb0741354e5fd3c2b7424178bfdb8521ff85c7ce;2018-11-15T16:40:02Z;toolService;toolService:service;MLSS Tagger Web Service;The part of speech tagger for Maltese is based on TnT, the statistical part of speech tagger by Thorsten Brants (http://www.coli.uni-saarland.de/~thorsten/tnt/). It was modified for  the Maltese Language Resource Server (MLRS) by Albert Gatt (Linguistics Department, University of Malta). The model for Maltese was trained on manually tagged texts and has reached an accuracy of 96%. Below is a list of the tags which are used, along with a description. The web service for the Maltese Language Software Services (MLSS) was provided by Andrew Attard.\n\nThe tagset list can be found here:\nhttp://metanet4u.research.um.edu.mt/POS.jsp\n\nThe service has two methods which can be invoked:\n\u00e2\u0080\u00a2\tString tagOneWordReturn(String text)\n\u00e2\u0080\u00a2\tString tagParagraphReturn(String text)\n\nBoth methods take a string as input, i.e., the text to be tagged, and return another string, i.e., the tagged text. The difference between the two is tagOneWordReturn returns the output as one word per line, while the other returns it as tagged paragraphs (if any paragraphs occur in the input string).\n\nThe format of the output is:\nword_TAG\n;2013-01-31",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6efb5333-cb3e-53b2-ab07-4aeafb8030b3",
-    "notes": [
-        "The part of speech tagger for Maltese is based on TnT, the statistical part of speech tagger by Thorsten Brants (http://www.coli.uni-saarland.de/~thorsten/tnt/). It was modified for  the Maltese Language Resource Server (MLRS) by Albert Gatt (Linguistics Department, University of Malta). The model for Maltese was trained on manually tagged texts and has reached an accuracy of 96%. Below is a list of the tags which are used, along with a description. The web service for the Maltese Language Software Services (MLSS) was provided by Andrew Attard.\n\nThe tagset list can be found here:\nhttp://metanet4u.research.um.edu.mt/POS.jsp\n\nThe service has two methods which can be invoked:\n\u00e2\u0080\u00a2\tString tagOneWordReturn(String text)\n\u00e2\u0080\u00a2\tString tagParagraphReturn(String text)\n\nBoth methods take a string as input, i.e., the text to be tagged, and return another string, i.e., the tagged text. The difference between the two is tagOneWordReturn returns the output as one word per line, while the other returns it as tagged paragraphs (if any paragraphs occur in the input string).\n\nThe format of the output is:\nword_TAG\n"
-    ],
-    "oai_identifier": [
-        "bf2ccab65e6911e2a2aa782bcb0741354e5fd3c2b7424178bfdb8521ff85c7ce"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:service"
-    ],
-    "state": "active",
-    "title": [
-        "MLSS Tagger Web Service"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6f048186-f338-5e58-9ed5-dd62316336f0.json b/oaitestdata/clarin-oai_dc/SET_1/json/6f048186-f338-5e58-9ed5-dd62316336f0.json
deleted file mode 100644
index a19188bb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6f048186-f338-5e58-9ed5-dd62316336f0.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "UW"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 11",
-        "text/plain; charset=utf-8",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/460",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/460"
-    ],
-    "PID": "http://hdl.handle.net/11321/460",
-    "PublicationTimestamp": "2018-04-12T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "UW"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Ochma\u0144ski, Miko\u0142aj"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/460;2018-04-12T09:34:19Z;hdl_11321_3;hdl_11321_4;Blogosferaksiazki2018;Ochma\u0144ski, Miko\u0142aj;blogi;blogosfera;ksi\u0105\u017cki;Teksty z wybranych blog\u00f3w ksi\u0105\u017ckowych;2018-04-12;corpus;http://hdl.handle.net/11321/460;pol;Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0);http://creativecommons.org/licenses/by-nc-nd/3.0/;CC;text/plain; charset=utf-8;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;downloadable_files_count: 11;UW",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6f048186-f338-5e58-9ed5-dd62316336f0",
-    "notes": [
-        "Teksty z wybranych blog\u00f3w ksi\u0105\u017ckowych"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/460"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "blogi"
-        },
-        {
-            "name": "blogosfera"
-        },
-        {
-            "name": "blogosfera"
-        }
-    ],
-    "title": [
-        "Blogosferaksiazki2018"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6f26eb47-52e8-5014-a70a-5c55ba7d34c8.json b/oaitestdata/clarin-oai_dc/SET_1/json/6f26eb47-52e8-5014-a70a-5c55ba7d34c8.json
deleted file mode 100644
index 40d9b9ac..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6f26eb47-52e8-5014-a70a-5c55ba7d34c8.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "MASt"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/154",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/154"
-    ],
-    "PID": "http://hdl.handle.net/11321/154",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "MASt"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Super Cool License",
-        "http://www.google.com",
-        "ACA"
-    ],
-    "author": [
-        "Mickiewicz, Mickiewicz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/154;2015-04-13T20:59:37Z;hdl_11321_3;hdl_11321_4;Pan Tadeusz;Mickiewicz, Mickiewicz;poemat;2015;corpus;http://hdl.handle.net/11321/154;pol;Super Cool License;http://www.google.com;ACA;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 1;MASt",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6f26eb47-52e8-5014-a70a-5c55ba7d34c8",
-    "notes": [
-        "poemat"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/154"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Pan Tadeusz"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6f9db361-b5ed-5101-8492-29b3e9940f36.json b/oaitestdata/clarin-oai_dc/SET_1/json/6f9db361-b5ed-5101-8492-29b3e9940f36.json
deleted file mode 100644
index ee12be6f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6f9db361-b5ed-5101-8492-29b3e9940f36.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-920",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-920"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-920",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-920;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Luwian;ca. 30.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-920;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#luv",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6f9db361-b5ed-5101-8492-29b3e9940f36",
-    "notes": [
-        "ca. 30.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-920"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Luwian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6f9e99de-f8d4-57fd-8300-7325050704ca.json b/oaitestdata/clarin-oai_dc/SET_1/json/6f9e99de-f8d4-57fd-8300-7325050704ca.json
deleted file mode 100644
index 0e1e90d7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6f9e99de-f8d4-57fd-8300-7325050704ca.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Gr\u00f6nros, Eija-Riitta"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Finnish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-445",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-445"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-445",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Finland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-445;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Modern Finnish Glossary of the Research Institute for the Languages of Finland (Kotimaisten kielten tutkimuskeskuksen nykysuomen;Gr\u00f6nros, Eija-Riitta;94 110 words, XML;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-445;fin;downloadable_files_count: 0;Finland;http://kaino.kotus.fi/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6f9e99de-f8d4-57fd-8300-7325050704ca",
-    "notes": [
-        "94 110 words, XML"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-445"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Modern Finnish Glossary of the Research Institute for the Languages of Finland (Kotimaisten kielten tutkimuskeskuksen nykysuomen"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6f9fbb22-0c5d-5416-97ae-efcd6bf3914d.json b/oaitestdata/clarin-oai_dc/SET_1/json/6f9fbb22-0c5d-5416-97ae-efcd6bf3914d.json
deleted file mode 100644
index b3352049..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6f9fbb22-0c5d-5416-97ae-efcd6bf3914d.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Godlewska"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 9",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/74",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/74"
-    ],
-    "PID": "http://hdl.handle.net/11321/74",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Godlewska"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Godlewska, Godlewska"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/74;2015-05-19T13:36:46Z;hdl_11321_3;hdl_11321_4;MWE Godlewska;Godlewska, Godlewska;Godlewska;2015-04-08;corpus;http://hdl.handle.net/11321/74;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 9;Godlewska",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6f9fbb22-0c5d-5416-97ae-efcd6bf3914d",
-    "notes": [
-        "Godlewska"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/74"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Godlewska"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6fd801dc-09c6-57b8-b56a-d8db0c299cab.json b/oaitestdata/clarin-oai_dc/SET_1/json/6fd801dc-09c6-57b8-b56a-d8db0c299cab.json
deleted file mode 100644
index ea4564a4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6fd801dc-09c6-57b8-b56a-d8db0c299cab.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 13",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech",
-        "Vietnamese",
-        "Romanian",
-        "Polish",
-        "Slovak",
-        "Spanish",
-        "Croatian",
-        "Irish",
-        "Latvian",
-        "Hungarian",
-        "French",
-        "Turkish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2607",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2607"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2607",
-    "PublicationTimestamp": "2018-01-31T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "N\u00e1plava, Jakub",
-        "Straka, Milan",
-        "Stra\u0148\u00e1k, Pavel",
-        "Haji\u010d, Jan"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2607;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Corpus for training and evaluating diacritics restoration systems;N\u00e1plava, Jakub;Straka, Milan;Haji\u010d, Jan;Stra\u0148\u00e1k, Pavel;diacritical marks generation;natural language correction;Corpus of texts in 12 languages. For each language, we provide one training, one development and one testing set acquired from Wikipedia articles. Moreover, each language dataset contains (substantially larger) training set collected from (general) Web texts. All sets, except for Wikipedia and Web training sets that can contain similar sentences, are disjoint. Data are segmented into sentences which are further word tokenized.\r\n\r\nAll data in the corpus contain diacritics. To strip diacritics from them, use Python script diacritization_stripping.py contained within attached stripping_diacritics.zip. This script has two modes. We generally recommend using method called uninames, which for some languages behaves better. \r\n\r\nThe code for training recurrent neural-network based model for diacritics restoration is located at https://github.com/arahusky/diacritics_restoration.;2018-01-31;corpus;http://hdl.handle.net/11234/1-2607;ces;vie;ron;pol;slk;spa;hrv;gle;lav;hun;fra;tur;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 13;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6fd801dc-09c6-57b8-b56a-d8db0c299cab",
-    "notes": [
-        "Corpus of texts in 12 languages. For each language, we provide one training, one development and one testing set acquired from Wikipedia articles. Moreover, each language dataset contains (substantially larger) training set collected from (general) Web texts. All sets, except for Wikipedia and Web training sets that can contain similar sentences, are disjoint. Data are segmented into sentences which are further word tokenized.\r\n\r\nAll data in the corpus contain diacritics. To strip diacritics from them, use Python script diacritization_stripping.py contained within attached stripping_diacritics.zip. This script has two modes. We generally recommend using method called uninames, which for some languages behaves better. \r\n\r\nThe code for training recurrent neural-network based model for diacritics restoration is located at https://github.com/arahusky/diacritics_restoration."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2607"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "diacritical marks generation"
-        },
-        {
-            "name": "natural language correction"
-        }
-    ],
-    "title": [
-        "Corpus for training and evaluating diacritics restoration systems"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6fe9f6af-8761-53ad-bac1-62fe328e4856.json b/oaitestdata/clarin-oai_dc/SET_1/json/6fe9f6af-8761-53ad-bac1-62fe328e4856.json
deleted file mode 100644
index 73901f55..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6fe9f6af-8761-53ad-bac1-62fe328e4856.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4172",
-    "MetadataAccess": [
-        "oai:ota:oucs:4172"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Berkeley, George, 1685-1753."
-    ],
-    "fulltext": "oai:ota:oucs:4172;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4172.xml;A sermon preached before the Incorporated Society for the Propagation of the Gospel in Foreign Parts: at their anniversary meeting in the parish-church of St Mary-le-Bow, on Friday, February 18. 1731. By George Berkeley, ...;Berkeley, George, 1685-1753.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6fe9f6af-8761-53ad-bac1-62fe328e4856",
-    "oai_identifier": [
-        "oai:ota:oucs:4172"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A sermon preached before the Incorporated Society for the Propagation of the Gospel in Foreign Parts: at their anniversary meeting in the parish-church of St Mary-le-Bow, on Friday, February 18. 1731. By George Berkeley, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4172.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6ff5343c-2f0d-5874-9427-cbc2971b5342.json b/oaitestdata/clarin-oai_dc/SET_1/json/6ff5343c-2f0d-5874-9427-cbc2971b5342.json
deleted file mode 100644
index 8f4765f4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6ff5343c-2f0d-5874-9427-cbc2971b5342.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/230",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/230"
-    ],
-    "PID": "http://hdl.handle.net/11321/230",
-    "PublicationTimestamp": "2015-10-30T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Marci\u0144czuk, Micha\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/230;2016-01-21T14:26:06Z;hdl_11321_3;hdl_11321_4;Wcrft test;Marci\u0144czuk, Micha\u0142;corpora;Wcrft test;2015-10-30;corpus;http://hdl.handle.net/11321/230;pol;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;text/plain; charset=utf-8;text/plain;downloadable_files_count: 1;Wroc\u0142aw University of Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6ff5343c-2f0d-5874-9427-cbc2971b5342",
-    "notes": [
-        "Wcrft test"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/230"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpora"
-        }
-    ],
-    "title": [
-        "Wcrft test"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/6ffc7434-455f-5082-b218-20b307a092da.json b/oaitestdata/clarin-oai_dc/SET_1/json/6ffc7434-455f-5082-b218-20b307a092da.json
deleted file mode 100644
index 7a2776cd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/6ffc7434-455f-5082-b218-20b307a092da.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5122",
-    "MetadataAccess": [
-        "oai:ota:oucs:5122"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hayley, William, 1745-1820."
-    ],
-    "fulltext": "oai:ota:oucs:5122;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5122.xml;Poems: consisting of odes, sonnets, songs, and occasional verses. By William Hayley, Esq.;Hayley, William, 1745-1820.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6ffc7434-455f-5082-b218-20b307a092da",
-    "oai_identifier": [
-        "oai:ota:oucs:5122"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Poems: consisting of odes, sonnets, songs, and occasional verses. By William Hayley, Esq."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5122.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7023288f-8bfb-5836-9d48-f98ced060467.json b/oaitestdata/clarin-oai_dc/SET_1/json/7023288f-8bfb-5836-9d48-f98ced060467.json
deleted file mode 100644
index db206004..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7023288f-8bfb-5836-9d48-f98ced060467.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4658",
-    "MetadataAccess": [
-        "oai:ota:oucs:4658"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Kenrick, W. (William), 1725?-1779."
-    ],
-    "fulltext": "oai:ota:oucs:4658;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4658.xml;Poems; ludicrous, satirical and moral;Kenrick, W. (William), 1725?-1779.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7023288f-8bfb-5836-9d48-f98ced060467",
-    "oai_identifier": [
-        "oai:ota:oucs:4658"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Poems; ludicrous, satirical and moral"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4658.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7023885a-2e6a-5fbb-b688-6a3f58cecb56.json b/oaitestdata/clarin-oai_dc/SET_1/json/7023885a-2e6a-5fbb-b688-6a3f58cecb56.json
deleted file mode 100644
index 3c035200..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7023885a-2e6a-5fbb-b688-6a3f58cecb56.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contributor": [
-        "Torikka, Marja"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-443",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-443"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-443",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Finland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-443;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Digital Listing of the Dictionary of Karelian (Karjalan kielen sanakirjan hakusanaluettelo);Torikka, Marja;94 532 words, XML (data), HTML (interface);2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-443;downloadable_files_count: 0;Finland;http://kaino.kotus.fi/sanat/kkss",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7023885a-2e6a-5fbb-b688-6a3f58cecb56",
-    "notes": [
-        "94 532 words, XML (data), HTML (interface)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-443"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Digital Listing of the Dictionary of Karelian (Karjalan kielen sanakirjan hakusanaluettelo)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/703b232d-79a2-52d1-9a3b-7a49ac6cf8ba.json b/oaitestdata/clarin-oai_dc/SET_1/json/703b232d-79a2-52d1-9a3b-7a49ac6cf8ba.json
deleted file mode 100644
index cd1ed444..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/703b232d-79a2-52d1-9a3b-7a49ac6cf8ba.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=f8fc859a059211e7a2aa782bcb0741350d3bf50c37a84b72aba78027323c781c",
-    "MetadataAccess": [
-        "f8fc859a059211e7a2aa782bcb0741350d3bf50c37a84b72aba78027323c781c"
-    ],
-    "PublicationTimestamp": "2017-03-10T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "fulltext": "f8fc859a059211e7a2aa782bcb0741350d3bf50c37a84b72aba78027323c781c;2018-11-15T16:40:29Z;toolService;toolService:tool;Portuguese to English Machine translation module;Technical Description:\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/Pilot1_technical_description.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/TechnicalDescriptionPilot2_D2.7.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2016/11/TechnicalDescriptionPilot3_D2.10.pdf;2017-03-10",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "703b232d-79a2-52d1-9a3b-7a49ac6cf8ba",
-    "notes": [
-        "Technical Description:\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/Pilot1_technical_description.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/TechnicalDescriptionPilot2_D2.7.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2016/11/TechnicalDescriptionPilot3_D2.10.pdf"
-    ],
-    "oai_identifier": [
-        "f8fc859a059211e7a2aa782bcb0741350d3bf50c37a84b72aba78027323c781c"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "Portuguese to English Machine translation module"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/703f341a-6892-5a3a-94ed-90e610ac45a8.json b/oaitestdata/clarin-oai_dc/SET_1/json/703f341a-6892-5a3a-94ed-90e610ac45a8.json
deleted file mode 100644
index 84f22dc5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/703f341a-6892-5a3a-94ed-90e610ac45a8.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4856",
-    "MetadataAccess": [
-        "oai:ota:oucs:4856"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Jones, Henry, 1721-1770."
-    ],
-    "fulltext": "oai:ota:oucs:4856;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4856.xml;The Earl of Essex: A tragedy. As it is acted at the Theatre Royal in Covent-Garden. Written by Mr. Henry Jones.;Jones, Henry, 1721-1770.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "703f341a-6892-5a3a-94ed-90e610ac45a8",
-    "oai_identifier": [
-        "oai:ota:oucs:4856"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The Earl of Essex: A tragedy. As it is acted at the Theatre Royal in Covent-Garden. Written by Mr. Henry Jones."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4856.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/703f73a2-b895-50f0-8769-a9f80e9d04ca.json b/oaitestdata/clarin-oai_dc/SET_1/json/703f73a2-b895-50f0-8769-a9f80e9d04ca.json
deleted file mode 100644
index 3a4869de..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/703f73a2-b895-50f0-8769-a9f80e9d04ca.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=389ebe92d63711e1a404080027e73ea2a4b6c6e4ac464aa8976d233a6f26790b",
-    "MetadataAccess": [
-        "389ebe92d63711e1a404080027e73ea2a4b6c6e4ac464aa8976d233a6f26790b"
-    ],
-    "PublicationTimestamp": "2012-09-04T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "fulltext": "389ebe92d63711e1a404080027e73ea2a4b6c6e4ac464aa8976d233a6f26790b;2018-11-15T16:39:32Z;corpus;corpus:text;BioLexicon;The BioLexicon is a large-scale, wide-coverage computational lexicon covering the biomedical domain. A large part of the lexicon is concerned with covering biomedical terms and their variants. Entries for domain-specific verbs include syntactic and semantic information. The lexicon includes entries that correspond to biomedical-specific vocabulary, as well as general language words. ;2012-09-04",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "703f73a2-b895-50f0-8769-a9f80e9d04ca",
-    "notes": [
-        "The BioLexicon is a large-scale, wide-coverage computational lexicon covering the biomedical domain. A large part of the lexicon is concerned with covering biomedical terms and their variants. Entries for domain-specific verbs include syntactic and semantic information. The lexicon includes entries that correspond to biomedical-specific vocabulary, as well as general language words. "
-    ],
-    "oai_identifier": [
-        "389ebe92d63711e1a404080027e73ea2a4b6c6e4ac464aa8976d233a6f26790b"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "BioLexicon"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/704d2d41-de24-55ff-b7fe-cb7c067d4c8f.json b/oaitestdata/clarin-oai_dc/SET_1/json/704d2d41-de24-55ff-b7fe-cb7c067d4c8f.json
deleted file mode 100644
index bd2b6866..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/704d2d41-de24-55ff-b7fe-cb7c067d4c8f.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "University of Gda\u0144sk"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 4",
-        "application/pdf",
-        "application/zip"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/594",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/594"
-    ],
-    "PID": "http://hdl.handle.net/11321/594",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "University of Gda\u0144sk"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN-EULA-ACA-v1.0",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca",
-        "ACA"
-    ],
-    "author": [
-        "Moru\u015b, Micha\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/594;2018-08-21T12:27:19Z;hdl_11321_3;hdl_11321_4;SpakowanesermonyEN;Moru\u015b, Micha\u0142;sermons;Sermons;2018;corpus;http://hdl.handle.net/11321/594;eng;CLARIN-EULA-ACA-v1.0;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca;ACA;text/plain; charset=utf-8;application/pdf;application/pdf;application/pdf;application/zip;downloadable_files_count: 4;University of Gda\u0144sk",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "704d2d41-de24-55ff-b7fe-cb7c067d4c8f",
-    "notes": [
-        "Sermons"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/594"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "sermons"
-        }
-    ],
-    "title": [
-        "SpakowanesermonyEN"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7069a905-efca-56c2-8be7-ada8f418f2d5.json b/oaitestdata/clarin-oai_dc/SET_1/json/7069a905-efca-56c2-8be7-ada8f418f2d5.json
deleted file mode 100644
index 5747964b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7069a905-efca-56c2-8be7-ada8f418f2d5.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/51",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/51"
-    ],
-    "PID": "http://hdl.handle.net/10794/51",
-    "PublicationTimestamp": "2014-10-31T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/51;2017-10-31T12:17:47Z;hdl_10794_1;hdl_10794_2;ASPAC \u2013 Swedish (2017-10-16);ASPAC \u2013 svenska (2017-10-16);n/a, n/a;Swedish;ASPAC;The Swedish part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.;Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat.;2014-10-31;corpus;http://hdl.handle.net/10794/51;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/aspacsv",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7069a905-efca-56c2-8be7-ada8f418f2d5",
-    "notes": [
-        "The Swedish part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.",
-        "Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/51"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "ASPAC"
-        }
-    ],
-    "title": [
-        "ASPAC \u2013 Swedish (2017-10-16)",
-        "ASPAC \u2013 svenska (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/70d96c0e-1b23-5892-b7c0-1a4a37a03388.json b/oaitestdata/clarin-oai_dc/SET_1/json/70d96c0e-1b23-5892-b7c0-1a4a37a03388.json
deleted file mode 100644
index 5a3d090f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/70d96c0e-1b23-5892-b7c0-1a4a37a03388.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3851",
-    "MetadataAccess": [
-        "oai:ota:oucs:3851"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Cibber, Theophilus, 1703-1758."
-    ],
-    "fulltext": "oai:ota:oucs:3851;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3851.xml;The association: or, liberty and loyalty. Verses occasion'd by the present unnatural rebellion. By Theophilus Cibber;Cibber, Theophilus, 1703-1758.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "70d96c0e-1b23-5892-b7c0-1a4a37a03388",
-    "oai_identifier": [
-        "oai:ota:oucs:3851"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The association: or, liberty and loyalty. Verses occasion'd by the present unnatural rebellion. By Theophilus Cibber"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3851.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/70f5bb54-8660-5a80-abad-cedcc69a4cc8.json b/oaitestdata/clarin-oai_dc/SET_1/json/70f5bb54-8660-5a80-abad-cedcc69a4cc8.json
deleted file mode 100644
index 992778a9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/70f5bb54-8660-5a80-abad-cedcc69a4cc8.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Craig, Hugh"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 192 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2032",
-    "MetadataAccess": [
-        "oai:ota:oucs:2032"
-    ],
-    "PublicationTimestamp": "1607-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1607"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Jonson, Ben, 1573?-1637"
-    ],
-    "fulltext": "oai:ota:oucs:2032;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/2032.xml;Volpone;Volpone [1607] / Ben Jonson;The foxe;Jonson, Ben, 1573?-1637;1607;text_and_corpus_linguistics;English drama -- 17th century;eng;Oxford Text Archive, University of Oxford;Craig, Hugh;text/sgml;(1 file : ca. 192 KB);Text;Plays;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "70f5bb54-8660-5a80-abad-cedcc69a4cc8",
-    "oai_identifier": [
-        "oai:ota:oucs:2032"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- th century"
-        }
-    ],
-    "title": [
-        "Volpone",
-        "Volpone [1607] / Ben Jonson",
-        "The foxe"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2032.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/70fdf5a4-5046-5980-9574-00605cd10077.json b/oaitestdata/clarin-oai_dc/SET_1/json/70fdf5a4-5046-5980-9574-00605cd10077.json
deleted file mode 100644
index 09a90a40..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/70fdf5a4-5046-5980-9574-00605cd10077.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "UMK"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 104",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/202",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/202"
-    ],
-    "PID": "http://hdl.handle.net/11321/202",
-    "PublicationTimestamp": "2015-05-21T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "UMK"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "G\u0119bka-Wolak, Ma\u0142gorzata"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/202;2017-11-14T19:36:30Z;hdl_11321_3;hdl_11321_4;Kodeksy;G\u0119bka-Wolak, Ma\u0142gorzata;j\u0119zyk prawny;kodeks;Korpus zawiera kodeksy karne;2015-05-21;corpus;http://hdl.handle.net/11321/202;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;text/plain;text/plain;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 104;UMK",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "70fdf5a4-5046-5980-9574-00605cd10077",
-    "notes": [
-        "Korpus zawiera kodeksy karne"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/202"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "kodeks"
-        }
-    ],
-    "title": [
-        "Kodeksy"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7101951e-abb8-5d84-a030-408b27ea3646.json b/oaitestdata/clarin-oai_dc/SET_1/json/7101951e-abb8-5d84-a030-408b27ea3646.json
deleted file mode 100644
index f90ce154..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7101951e-abb8-5d84-a030-408b27ea3646.json
+++ /dev/null
@@ -1,110 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 3",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0015-8DAF-4",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0015-8DAF-4"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0015-8DAF-4",
-    "PublicationTimestamp": "2012-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/231720",
-        "info:eu-repo/grantAgreement/EC/FP7/247762"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CC-BY-NC-SA + LDC99T42",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/license-pcedt2",
-        "RES"
-    ],
-    "author": [
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "Panevov\u00e1, Jarmila",
-        "Ure\u0161ov\u00e1, Zde\u0148ka",
-        "Haji\u010d, Jan",
-        "\u0160t\u011bp\u00e1nek, Jan",
-        "Mikulov\u00e1, Marie",
-        "Popelka, Jan",
-        "Toman, Josef",
-        "Fu\u010d\u00edkov\u00e1, Eva",
-        "Haji\u010dov\u00e1, Eva",
-        "Cinkov\u00e1, Silvie",
-        "Sgall, Petr",
-        "Pajas, Petr",
-        "\u0160indlerov\u00e1, Jana",
-        "Semeck\u00fd, Ji\u0159\u00ed"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0015-8DAF-4;2017-11-09T14:20:27Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Prague Czech-English Dependency Treebank 2.0;Haji\u010d, Jan;Haji\u010dov\u00e1, Eva;Panevov\u00e1, Jarmila;Sgall, Petr;Cinkov\u00e1, Silvie;Fu\u010d\u00edkov\u00e1, Eva;Mikulov\u00e1, Marie;Pajas, Petr;Popelka, Jan;Semeck\u00fd, Ji\u0159\u00ed;\u0160indlerov\u00e1, Jana;\u0160t\u011bp\u00e1nek, Jan;Toman, Josef;Ure\u0161ov\u00e1, Zde\u0148ka;\u017dabokrtsk\u00fd, Zden\u011bk;parallel treebank;PCEDT;parallel corpus;Wall Street Journal;WSJ;Penn Treebank;dependency annotation;PDT;Texts\r\n\r\nThe Prague Czech-English Dependency Treebank 2.0 (PCEDT 2.0) is a major update of the Prague Czech-English Dependency Treebank 1.0 (LDC2004T25). It is a manually parsed Czech-English parallel corpus sized over 1.2 million running words in almost 50,000 sentences for each part.\r\n\r\nData\r\n\r\nThe English part contains the entire Penn Treebank - Wall Street Journal Section (LDC99T42). The Czech part consists of Czech translations of all of the Penn Treebank-WSJ texts. The corpus is 1:1 sentence-aligned. An additional automatic alignment on the node level (different for each annotation layer) is part of this release, too. The original Penn Treebank-like file structure (25 sections, each containing up to one hundred files) has been preserved. Only those PTB documents which have both POS and structural annotation (total of 2312 documents) have been translated to Czech and made part of this release.\r\n\r\nEach language part is enhanced with a comprehensive manual linguistic annotation in the PDT 2.0 style (LDC2006T01, Prague Dependency Treebank 2.0). The main features of this annotation style are:\r\ndependency structure of the content words and coordinating and similar structures (function words are attached as their attribute values)\r\nsemantic labeling of content words and types of coordinating structures\r\nargument structure, including an argument structure (\"valency\") lexicon for both languages\r\nellipsis and anaphora resolution.\r\nThis annotation style is called tectogrammatical annotation and it constitutes the tectogrammatical layer in the corpus. For more details see below and documentation.\r\n\r\nAnnotation of the Czech part\r\n\r\nSentences of the Czech translation were automatically morphologically annotated and parsed into surface-syntax dependency trees in the PDT 2.0 annotation style. This annotation style is sometimes called analytical annotation; it constitutes the analytical layer of the corpus. The manual tectogrammatical (deep-syntax) annotation was built as a separate layer above the automatic analytical (surface-syntax) parse. A sample of 2,000 sentences was manually annotated on the analytical layer.\r\n\r\nAnnotation of the English part\r\n\r\nThe resulting manual tectogrammatical annotation was built above an automatic transformation of the original phrase-structure annotation of the Penn Treebank into surface dependency (analytical) representations, using the following additional linguistic information from other sources:\r\nPropBank (LDC2004T14)\r\nVerbNet\r\nNomBank (LDC2008T23)\r\nflat noun phrase structures (by courtesy of D. Vadas and J.R. Curran)\r\nFor each sentence, the original Penn Treebank phrase structure trees are preserved in this corpus together with their links to the analytical and tectogrammatical annotation.;2012;corpus;http://hdl.handle.net/11858/00-097C-0000-0015-8DAF-4;ces;eng;info:eu-repo/grantAgreement/EC/FP7/231720;info:eu-repo/grantAgreement/EC/FP7/247762;CC-BY-NC-SA + LDC99T42;https://lindat.mff.cuni.cz/repository/xmlui/page/license-pcedt2;RES;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 3;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/pcedt2.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7101951e-abb8-5d84-a030-408b27ea3646",
-    "notes": [
-        "Texts\r\n\r\nThe Prague Czech-English Dependency Treebank 2.0 (PCEDT 2.0) is a major update of the Prague Czech-English Dependency Treebank 1.0 (LDC2004T25). It is a manually parsed Czech-English parallel corpus sized over 1.2 million running words in almost 50,000 sentences for each part.\r\n\r\nData\r\n\r\nThe English part contains the entire Penn Treebank - Wall Street Journal Section (LDC99T42). The Czech part consists of Czech translations of all of the Penn Treebank-WSJ texts. The corpus is 1:1 sentence-aligned. An additional automatic alignment on the node level (different for each annotation layer) is part of this release, too. The original Penn Treebank-like file structure (25 sections, each containing up to one hundred files) has been preserved. Only those PTB documents which have both POS and structural annotation (total of 2312 documents) have been translated to Czech and made part of this release.\r\n\r\nEach language part is enhanced with a comprehensive manual linguistic annotation in the PDT 2.0 style (LDC2006T01, Prague Dependency Treebank 2.0). The main features of this annotation style are:\r\ndependency structure of the content words and coordinating and similar structures (function words are attached as their attribute values)\r\nsemantic labeling of content words and types of coordinating structures\r\nargument structure, including an argument structure (\"valency\") lexicon for both languages\r\nellipsis and anaphora resolution.\r\nThis annotation style is called tectogrammatical annotation and it constitutes the tectogrammatical layer in the corpus. For more details see below and documentation.\r\n\r\nAnnotation of the Czech part\r\n\r\nSentences of the Czech translation were automatically morphologically annotated and parsed into surface-syntax dependency trees in the PDT 2.0 annotation style. This annotation style is sometimes called analytical annotation; it constitutes the analytical layer of the corpus. The manual tectogrammatical (deep-syntax) annotation was built as a separate layer above the automatic analytical (surface-syntax) parse. A sample of 2,000 sentences was manually annotated on the analytical layer.\r\n\r\nAnnotation of the English part\r\n\r\nThe resulting manual tectogrammatical annotation was built above an automatic transformation of the original phrase-structure annotation of the Penn Treebank into surface dependency (analytical) representations, using the following additional linguistic information from other sources:\r\nPropBank (LDC2004T14)\r\nVerbNet\r\nNomBank (LDC2008T23)\r\nflat noun phrase structures (by courtesy of D. Vadas and J.R. Curran)\r\nFor each sentence, the original Penn Treebank phrase structure trees are preserved in this corpus together with their links to the analytical and tectogrammatical annotation."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0015-8DAF-4"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parallel treebank"
-        },
-        {
-            "name": "PCEDT"
-        },
-        {
-            "name": "parallel corpus"
-        },
-        {
-            "name": "Wall Street Journal"
-        },
-        {
-            "name": "WSJ"
-        },
-        {
-            "name": "Penn Treebank"
-        },
-        {
-            "name": "dependency annotation"
-        },
-        {
-            "name": "PDT"
-        }
-    ],
-    "title": [
-        "Prague Czech-English Dependency Treebank 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/71026691-5ac5-5a5a-a525-dda37440cc35.json b/oaitestdata/clarin-oai_dc/SET_1/json/71026691-5ac5-5a5a-a525-dda37440cc35.json
deleted file mode 100644
index 4773fe3b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/71026691-5ac5-5a5a-a525-dda37440cc35.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3109",
-    "MetadataAccess": [
-        "oai:ota:oucs:3109"
-    ],
-    "PublicationTimestamp": "1863-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1863"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gaskell, Elizabeth Cleghorn, 1810-1865"
-    ],
-    "fulltext": "oai:ota:oucs:3109;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3109.xml;Cousin Phillis;Gaskell, Elizabeth Cleghorn, 1810-1865;not after: 1863;text_and_corpus_linguistics;Fiction -- Great Britain -- 19th century;Novels -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "71026691-5ac5-5a5a-a525-dda37440cc35",
-    "oai_identifier": [
-        "oai:ota:oucs:3109"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- Great Britain -- th century"
-        },
-        {
-            "name": "Novels -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Cousin Phillis"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3109.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7143fed5-7dfb-506a-aedb-5371ed7d673e.json b/oaitestdata/clarin-oai_dc/SET_1/json/7143fed5-7dfb-506a-aedb-5371ed7d673e.json
deleted file mode 100644
index 39503a29..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7143fed5-7dfb-506a-aedb-5371ed7d673e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3378",
-    "MetadataAccess": [
-        "oai:ota:oucs:3378"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Darwin, Erasmus, 1731-1802."
-    ],
-    "fulltext": "oai:ota:oucs:3378;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3378.xml;The golden age, a poetical epistle: from Erasmus D-n, M.D. to Thomas Beddoes, M.D.;Darwin, Erasmus, 1731-1802.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7143fed5-7dfb-506a-aedb-5371ed7d673e",
-    "oai_identifier": [
-        "oai:ota:oucs:3378"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The golden age, a poetical epistle: from Erasmus D-n, M.D. to Thomas Beddoes, M.D."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3378.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/714c676a-c40a-5dd2-a926-d07a8739ea11.json b/oaitestdata/clarin-oai_dc/SET_1/json/714c676a-c40a-5dd2-a926-d07a8739ea11.json
deleted file mode 100644
index fe2149ea..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/714c676a-c40a-5dd2-a926-d07a8739ea11.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Universit\u00e4t Trier"
-    ],
-    "Contributor": [
-        "Plate, Dr. Ralf",
-        "M.a., Ute Recker-Hamm"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1133",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1133"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1133",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Universit\u00e4t Trier"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1133;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Digitales Mittelhochdeutsches Textarchiv;Plate, Dr. Ralf;M.a., Ute Recker-Hamm;Germanistik;Collection of (philologically reliable) Middle High German texts; Sammlung von (philologisch zuverl\u00e4ssigen) mittelhochdeutschen Texten;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1133;deu;downloadable_files_count: 0;Germany;Universit\u00e4t Trier;http://mhgta.uni-trier.de/katalogsuche.php?ses_id=265c6722bde5cf2bb294c4c7f59d0c1f&suchwort=*&gesendet=suchen",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "714c676a-c40a-5dd2-a926-d07a8739ea11",
-    "notes": [
-        "Collection of (philologically reliable) Middle High German texts; Sammlung von (philologisch zuverl\u00e4ssigen) mittelhochdeutschen Texten"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1133"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Digitales Mittelhochdeutsches Textarchiv"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/716bc82b-41df-58bf-9af2-92c615039b7d.json b/oaitestdata/clarin-oai_dc/SET_1/json/716bc82b-41df-58bf-9af2-92c615039b7d.json
deleted file mode 100644
index 55f155e8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/716bc82b-41df-58bf-9af2-92c615039b7d.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/53",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/53"
-    ],
-    "PID": "http://hdl.handle.net/10794/53",
-    "PublicationTimestamp": "2015-04-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/53;2017-10-31T12:22:34Z;hdl_10794_1;hdl_10794_2;ASPAC \u2013 Swedish-English (2017-10-16);ASPAC \u2013 svenska-engelska (2017-10-16);n/a, n/a;ASPAC;Parallel;Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.;Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat.;2015-04-16;corpus;http://hdl.handle.net/10794/53;swe;eng;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/octet-stream;application/gzip;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/aspacsven",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "716bc82b-41df-58bf-9af2-92c615039b7d",
-    "notes": [
-        "Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.",
-        "Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/53"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ASPAC"
-        },
-        {
-            "name": "Parallel"
-        }
-    ],
-    "title": [
-        "ASPAC \u2013 Swedish-English (2017-10-16)",
-        "ASPAC \u2013 svenska-engelska (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/718a231c-2762-5ce6-a8d9-ce89e3e8bb9c.json b/oaitestdata/clarin-oai_dc/SET_1/json/718a231c-2762-5ce6-a8d9-ce89e3e8bb9c.json
deleted file mode 100644
index 40e2e198..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/718a231c-2762-5ce6-a8d9-ce89e3e8bb9c.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "[s.n.]"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-28298",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-28298"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D16-B",
-    "PublicationTimestamp": "1763-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1763"
-    ],
-    "Publisher": [
-        "[s.n.]"
-    ],
-    "RelatedIdentifier": [
-        "http://rcin.org.pl/Content/28298",
-        "oai:rcin.org.pl:publication:46139"
-    ],
-    "ResourceType": [
-        "Text",
-        "Early printed book (1501-1800)"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "author": [
-        "Lubomirski, Antoni (1718-1782)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-28298;2019-03-01T13:33:04Z;Oyczyzn\u0119 kochai\u0105ca, Prawa czcz\u0105ca, Krolowi \u017cyczliwa, Wierna Rada, Co zwi\u0119\u017ale, w Radzie Senatu mowi\u0142a, teraz obszerniey, dla wiadomo\u015bci wszystkich Trzech Stanow, opisuie, dok\u0142ada y wydaie Roku 1763;Lubomirski, Antoni (1718-1782);Kurlandia (\u0141otwa);Polish journalistic writing - 18th c.;Aut. wg Estr.;Tyt. nag\u0142.;W Estr. uwaga: \"[...] Jest to dodatek do wydanej zarazem broszury: Pami\u0105tka kurland. interess\u00f3w [...]\";[17] k., sygn. A-D4, E1 ; 4\u00b0;Estr. XV-XVIII, 21, 458 (b\u0142\u0119dna data w odpisie tyt.);Estr. XV-XVIII, 26, 16;Dwa do\u0142\u0105czone dokumenty w j\u0119z. \u0142ac.;[s.n.];[1763];Text;Early printed book (1501-1800);application/xml;clarind-uds:poldilemma-28298;hdl:11858/00-246C-0000-0023-8D16-B;IBL PAN, call no. XVIII.2.1282;http://katalog.pan.pl/webpac-bin/233biblitEN/wgbroker.exe?new+-access+top+search+open+NR+xx002808491;pol;lat;http://rcin.org.pl/Content/28298;oai:rcin.org.pl:publication:46139;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "718a231c-2762-5ce6-a8d9-ce89e3e8bb9c",
-    "notes": [
-        "Aut. wg Estr.",
-        "Tyt. nag\u0142.",
-        "W Estr. uwaga: \"[...] Jest to dodatek do wydanej zarazem broszury: Pami\u0105tka kurland. interess\u00f3w [...]\"",
-        "[17] k., sygn. A-D4, E1 ; 4\u00b0",
-        "Estr. XV-XVIII, 21, 458 (b\u0142\u0119dna data w odpisie tyt.)",
-        "Estr. XV-XVIII, 26, 16",
-        "Dwa do\u0142\u0105czone dokumenty w j\u0119z. \u0142ac."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-28298"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Polish journalistic writing - th c."
-        }
-    ],
-    "title": [
-        "Oyczyzn\u0119 kochai\u0105ca, Prawa czcz\u0105ca, Krolowi \u017cyczliwa, Wierna Rada, Co zwi\u0119\u017ale, w Radzie Senatu mowi\u0142a, teraz obszerniey, dla wiadomo\u015bci wszystkich Trzech Stanow, opisuie, dok\u0142ada y wydaie Roku 1763"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/719b058e-32ae-58c4-93a3-1c08a507df5a.json b/oaitestdata/clarin-oai_dc/SET_1/json/719b058e-32ae-58c4-93a3-1c08a507df5a.json
deleted file mode 100644
index 43e316f7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/719b058e-32ae-58c4-93a3-1c08a507df5a.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Survey of English Usage, University College London"
-    ],
-    "Contributor": [
-        "Arts, Bas"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-889",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-889"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-889",
-    "PublicationTimestamp": "1998-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1998"
-    ],
-    "Publisher": [
-        "Survey of English Usage, University College London"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-889;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;International Corpus of English: Great Britain (ICE-GB);Arts, Bas;One million words of written and spoken English from Great Britain. Transcriptions aligned with digitised speech recordings. POS-tagged and parsed. Part of the International Corpus of English project. Custom-made search software: ICE-CUP;1998;corpus;http://hdl.handle.net/11372/LRT-889;eng;downloadable_files_count: 0;United Kingdom;Survey of English Usage, University College London;http://www.ucl.ac.uk/english-usage/projects/ice-gb/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "719b058e-32ae-58c4-93a3-1c08a507df5a",
-    "notes": [
-        "One million words of written and spoken English from Great Britain. Transcriptions aligned with digitised speech recordings. POS-tagged and parsed. Part of the International Corpus of English project. Custom-made search software: ICE-CUP"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-889"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "International Corpus of English: Great Britain (ICE-GB)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/71a0775f-01cb-5273-a214-d83aff9b1f94.json b/oaitestdata/clarin-oai_dc/SET_1/json/71a0775f-01cb-5273-a214-d83aff9b1f94.json
deleted file mode 100644
index 8ec92455..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/71a0775f-01cb-5273-a214-d83aff9b1f94.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "less than 512 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0426",
-    "MetadataAccess": [
-        "oai:ota:oucs:0426"
-    ],
-    "PublicationTimestamp": "1969-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1969"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Barnes, Peter,  1931-"
-    ],
-    "fulltext": "oai:ota:oucs:0426;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0426.xml; The ruling class  / compiled by Dirk Geens;Barnes, Peter,  1931-;1969;text_and_corpus_linguistics;Plays -- Great Britain -- 20th century;eng;Forms part of the Louvain corpus of modern English drama deposited in 1983. The text does not conform to modern standards of text encoding. The text is all capitals, with words broken over line boundaries, undocumented markup characters, and numeric codes for the identities of the players. ;Oxford Text Archive, University of Oxford;less than 512 KB;Text;Plays;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "71a0775f-01cb-5273-a214-d83aff9b1f94",
-    "notes": [
-        "Forms part of the Louvain corpus of modern English drama deposited in 1983. The text does not conform to modern standards of text encoding. The text is all capitals, with words broken over line boundaries, undocumented markup characters, and numeric codes for the identities of the players. "
-    ],
-    "oai_identifier": [
-        "oai:ota:oucs:0426"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        " The ruling class  / compiled by Dirk Geens"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0426.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/71aabf09-e949-5c5d-82ee-2c9866b166c9.json b/oaitestdata/clarin-oai_dc/SET_1/json/71aabf09-e949-5c5d-82ee-2c9866b166c9.json
deleted file mode 100644
index 280e499f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/71aabf09-e949-5c5d-82ee-2c9866b166c9.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contributor": [
-        "Schmidt, Thomas"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English",
-        "French",
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1054",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1054"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1054",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Germany||United States"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1054;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Kicktionary;Schmidt, Thomas;Electronic dictionary of football language, using FrameNet and WordNet approaches;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1054;eng;fra;deu;downloadable_files_count: 0;Germany||United States;http://www.kicktionary.de",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "71aabf09-e949-5c5d-82ee-2c9866b166c9",
-    "notes": [
-        "Electronic dictionary of football language, using FrameNet and WordNet approaches"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1054"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Kicktionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/71acb489-643a-5685-ae77-01e52f625021.json b/oaitestdata/clarin-oai_dc/SET_1/json/71acb489-643a-5685-ae77-01e52f625021.json
deleted file mode 100644
index 6f935a22..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/71acb489-643a-5685-ae77-01e52f625021.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3439",
-    "MetadataAccess": [
-        "oai:ota:oucs:3439"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Garrick, David, 1717-1779."
-    ],
-    "fulltext": "oai:ota:oucs:3439;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3439.xml;To Mr. Gray, on his odes;Garrick, David, 1717-1779.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "71acb489-643a-5685-ae77-01e52f625021",
-    "oai_identifier": [
-        "oai:ota:oucs:3439"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "To Mr. Gray, on his odes"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3439.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/71af54ed-2044-5f8b-a586-12924c07c469.json b/oaitestdata/clarin-oai_dc/SET_1/json/71af54ed-2044-5f8b-a586-12924c07c469.json
deleted file mode 100644
index 0e666d99..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/71af54ed-2044-5f8b-a586-12924c07c469.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Przemys\u0142aw \u017bukiewicz",
-        "Rafa\u0142 Zimny",
-        "Jan Wieczorek"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 44",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/605",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/605"
-    ],
-    "PID": "http://hdl.handle.net/11321/605",
-    "PublicationTimestamp": "2018-09-11T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Przemys\u0142aw \u017bukiewicz",
-        "Rafa\u0142 Zimny",
-        "Jan Wieczorek"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11321/603"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN-EULA-ACA-v1.0",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca",
-        "ACA"
-    ],
-    "author": [
-        "Wieczorek, Jan",
-        "Zimny, Rafa\u0142",
-        "\u017bukiewicz, Przemys\u0142aw"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/605;2018-09-24T12:11:13Z;hdl_11321_3;hdl_11321_478;Korpus przem\u00f3wie\u0144 noworocznych 3.0 (2018-09-24);Zimny, Rafa\u0142;\u017bukiewicz, Przemys\u0142aw;Wieczorek, Jan;przem\u00f3wienia;polityka;Fragment korpusu polskich przem\u00f3wie\u0144 politycznych;2018-09-11;corpus;http://hdl.handle.net/11321/605;pol;http://hdl.handle.net/11321/603;CLARIN-EULA-ACA-v1.0;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca;ACA;text/plain; charset=utf-8;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;downloadable_files_count: 44;Jan Wieczorek;Rafa\u0142 Zimny;Przemys\u0142aw \u017bukiewicz",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "71af54ed-2044-5f8b-a586-12924c07c469",
-    "notes": [
-        "Fragment korpusu polskich przem\u00f3wie\u0144 politycznych"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/605"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_478"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "polityka"
-        }
-    ],
-    "title": [
-        "Korpus przem\u00f3wie\u0144 noworocznych 3.0 (2018-09-24)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/71c707ca-bb6d-5257-8af0-d5bb87bc143c.json b/oaitestdata/clarin-oai_dc/SET_1/json/71c707ca-bb6d-5257-8af0-d5bb87bc143c.json
deleted file mode 100644
index 1ede8343..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/71c707ca-bb6d-5257-8af0-d5bb87bc143c.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "TALG Research Group (University of Vigo)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Basque",
-        "Catalan",
-        "English",
-        "French",
-        "Galician",
-        "German",
-        "Portuguese",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-614",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-614"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-614",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "TALG Research Group (University of Vigo)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-614;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Corpus CLUVI;Parallel corpus, 22 million words;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-614;eus;cat;eng;fra;glg;deu;por;spa;downloadable_files_count: 0;Spain;TALG Research Group (University of Vigo);http://sli.uvigo.es/CLUVI",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "71c707ca-bb6d-5257-8af0-d5bb87bc143c",
-    "notes": [
-        "Parallel corpus, 22 million words"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-614"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus CLUVI"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/71fc046c-b567-52ee-9e66-35d943283d10.json b/oaitestdata/clarin-oai_dc/SET_1/json/71fc046c-b567-52ee-9e66-35d943283d10.json
deleted file mode 100644
index 2ec9d70e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/71fc046c-b567-52ee-9e66-35d943283d10.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=a7ea7a8e2cb811e2a2aa782bcb074135ffcac606a29341d581999e6ff55ed5b8",
-    "MetadataAccess": [
-        "a7ea7a8e2cb811e2a2aa782bcb074135ffcac606a29341d581999e6ff55ed5b8"
-    ],
-    "PublicationTimestamp": "2012-11-12T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "fulltext": "a7ea7a8e2cb811e2a2aa782bcb074135ffcac606a29341d581999e6ff55ed5b8;2018-11-15T16:39:47Z;corpus;corpus:text;Porlex;Porlex v2 (see Gomes & Castro, 2003) is a computerized lexical database in European Portuguese containing psycholinguistic and cognitive information that is useful to select stimulus materials for experiments and/or training vocabularies. It was built on the basis of a middle-sized adult lexicon, and provides orthographic, phonological, phonetic, part-of-speech, and neighborhood information for about 27,374 words (uninflected content words and inflected function words), presented as an Excel file. \n\nPorlex words come from the Dicion\u00c3\u00a1rio Universal Fundamental (Texto Editora, 1998) that was selected because of its size. In the process of compiling the remaining source informations, it became clear that the final selection of the lexical entries had to be fine tuned. For that purpose, we used Porto Editora (Costa & Melo, 1997) and C\u00c3\u00a2ndido de Figueiredo dictionaries (1996), as well as the grammars of Cunha and Cintra (1987), Mateus, Brito, Duarte and Faria (1989), and Vilela (1995).\n\nLexical entries, grammatical and morphological classification, syllabication, phonetic transcription and frequency information (\u00e2\u0089\u00885% of the lexical entries, imported from the Fundamental Portuguese \u00e2\u0080\u0093 a spoken corpus) were collected from various sources. Porlex gives additional information about the characteristics of spoken words; for example, how many schwas they include, how they are divided into syllables, where is the stressed syllable; also a pointer for ambisyllabicity, the length in number of phonemes or of syllables, and two different types of phonetic patterns, one based on a gross classification of speech sounds, another more distinctive. \n;2012-11-12",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "71fc046c-b567-52ee-9e66-35d943283d10",
-    "notes": [
-        "Porlex v2 (see Gomes & Castro, 2003) is a computerized lexical database in European Portuguese containing psycholinguistic and cognitive information that is useful to select stimulus materials for experiments and/or training vocabularies. It was built on the basis of a middle-sized adult lexicon, and provides orthographic, phonological, phonetic, part-of-speech, and neighborhood information for about 27,374 words (uninflected content words and inflected function words), presented as an Excel file. \n\nPorlex words come from the Dicion\u00c3\u00a1rio Universal Fundamental (Texto Editora, 1998) that was selected because of its size. In the process of compiling the remaining source informations, it became clear that the final selection of the lexical entries had to be fine tuned. For that purpose, we used Porto Editora (Costa & Melo, 1997) and C\u00c3\u00a2ndido de Figueiredo dictionaries (1996), as well as the grammars of Cunha and Cintra (1987), Mateus, Brito, Duarte and Faria (1989), and Vilela (1995).\n\nLexical entries, grammatical and morphological classification, syllabication, phonetic transcription and frequency information (\u00e2\u0089\u00885% of the lexical entries, imported from the Fundamental Portuguese \u00e2\u0080\u0093 a spoken corpus) were collected from various sources. Porlex gives additional information about the characteristics of spoken words; for example, how many schwas they include, how they are divided into syllables, where is the stressed syllable; also a pointer for ambisyllabicity, the length in number of phonemes or of syllables, and two different types of phonetic patterns, one based on a gross classification of speech sounds, another more distinctive. \n"
-    ],
-    "oai_identifier": [
-        "a7ea7a8e2cb811e2a2aa782bcb074135ffcac606a29341d581999e6ff55ed5b8"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "Porlex"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/71fe8731-7ba0-5f36-a2a7-eda8577600d4.json b/oaitestdata/clarin-oai_dc/SET_1/json/71fe8731-7ba0-5f36-a2a7-eda8577600d4.json
deleted file mode 100644
index a024c336..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/71fe8731-7ba0-5f36-a2a7-eda8577600d4.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Jan Koco\u0144"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 20",
-        "text/plain; charset=utf-8",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/344",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/344"
-    ],
-    "PID": "http://hdl.handle.net/11321/344",
-    "PublicationTimestamp": "2017-04-21T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Jan Koco\u0144"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN-EULA-ACA-v1.0",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca",
-        "ACA"
-    ],
-    "author": [
-        "Koco\u0144, Jan"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/344;2017-04-25T11:07:10Z;hdl_11321_3;hdl_11321_4;Diachrono;Koco\u0144, Jan;corpus;diachronic;Polish texts from 17th to 19th century;2017-04-21;corpus;http://hdl.handle.net/11321/344;pol;CLARIN-EULA-ACA-v1.0;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca;ACA;text/plain; charset=utf-8;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;downloadable_files_count: 20;Jan Koco\u0144",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "71fe8731-7ba0-5f36-a2a7-eda8577600d4",
-    "notes": [
-        "Polish texts from 17th to 19th century"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/344"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "diachronic"
-        }
-    ],
-    "title": [
-        "Diachrono"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/71fe88c6-0f43-5dbf-b2fe-ba83204ee0c5.json b/oaitestdata/clarin-oai_dc/SET_1/json/71fe88c6-0f43-5dbf-b2fe-ba83204ee0c5.json
deleted file mode 100644
index f981ca8b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/71fe88c6-0f43-5dbf-b2fe-ba83204ee0c5.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2718",
-    "MetadataAccess": [
-        "oai:ota:oucs:2718"
-    ],
-    "PublicationTimestamp": "1765-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1765"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2718;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2718.xml;Laws for the Dean's servants;Swift, Jonathan, 1667-1745;1765;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "71fe88c6-0f43-5dbf-b2fe-ba83204ee0c5",
-    "oai_identifier": [
-        "oai:ota:oucs:2718"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Laws for the Dean's servants"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2718.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7214e4d9-0019-5c00-aa50-14a8cd123518.json b/oaitestdata/clarin-oai_dc/SET_1/json/7214e4d9-0019-5c00-aa50-14a8cd123518.json
deleted file mode 100644
index 7fee04e9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7214e4d9-0019-5c00-aa50-14a8cd123518.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1515",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1515"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1515",
-    "PublicationTimestamp": "2015-10-13T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU General Public Licence, version 3",
-        "http://opensource.org/licenses/GPL-3.0",
-        "PUB"
-    ],
-    "author": [
-        "Luk\u0161ov\u00e1, Ivana",
-        "Hladk\u00e1, Barbora"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1515;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Information extraction from EIA documents;Luk\u0161ov\u00e1, Ivana;Hladk\u00e1, Barbora;information extraction;rule-based extraction;Environmental impact assessment (EIA) is the formal process used to predict the environmental consequences of a plan. We present a rule-based extraction system to mine Czech EIA documents. The extraction rules work with a set of documents enriched with morphological information and manually created vocabularies of terms supposed to be extracted from the documents, e.g. basic information about the project (address, ID company, ...), data on the impacts and outcomes (waste substances, endangered species, ...), a final opinion. The documents Notice of Intent contains the section BI2 with the information on the scope (capacity) of the plan.;2015-10-13;toolService;http://hdl.handle.net/11234/1-1515;ces;GNU General Public Licence, version 3;http://opensource.org/licenses/GPL-3.0;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/grants/intelligent-library",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7214e4d9-0019-5c00-aa50-14a8cd123518",
-    "notes": [
-        "Environmental impact assessment (EIA) is the formal process used to predict the environmental consequences of a plan. We present a rule-based extraction system to mine Czech EIA documents. The extraction rules work with a set of documents enriched with morphological information and manually created vocabularies of terms supposed to be extracted from the documents, e.g. basic information about the project (address, ID company, ...), data on the impacts and outcomes (waste substances, endangered species, ...), a final opinion. The documents Notice of Intent contains the section BI2 with the information on the scope (capacity) of the plan."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1515"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "information extraction"
-        },
-        {
-            "name": "rule-based extraction"
-        }
-    ],
-    "title": [
-        "Information extraction from EIA documents"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7220422c-3152-5b57-92b1-f3ae2312a03a.json b/oaitestdata/clarin-oai_dc/SET_1/json/7220422c-3152-5b57-92b1-f3ae2312a03a.json
deleted file mode 100644
index 292f4e49..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7220422c-3152-5b57-92b1-f3ae2312a03a.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5318",
-    "MetadataAccess": [
-        "oai:ota:oucs:5318"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dampier, William, 1652-1715."
-    ],
-    "fulltext": "oai:ota:oucs:5318;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5318.xml;A voyage to New Holland, &c. in the year, 1699: Wherein are described, the Canary-Islands, the Isles of Mayo and St Jago. The Bay of All Saints, with the forts and town of Bahia in Brasil. ... A table of all the variations observ'd in this voyage. ... The isles and coast, &c. of New Holland. ... Illustrated with several maps and draughts; ... Vol.III. By Captain William Dampier.;New voyage round the world.;Dampier, William, 1652-1715.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7220422c-3152-5b57-92b1-f3ae2312a03a",
-    "oai_identifier": [
-        "oai:ota:oucs:5318"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A voyage to New Holland, &c. in the year, 1699: Wherein are described, the Canary-Islands, the Isles of Mayo and St Jago. The Bay of All Saints, with the forts and town of Bahia in Brasil. ... A table of all the variations observ'd in this voyage. ... The isles and coast, &c. of New Holland. ... Illustrated with several maps and draughts; ... Vol.III. By Captain William Dampier.",
-        "New voyage round the world."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5318.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7228ad80-3683-5660-867a-f83e1ce6b9fe.json b/oaitestdata/clarin-oai_dc/SET_1/json/7228ad80-3683-5660-867a-f83e1ce6b9fe.json
deleted file mode 100644
index 5b9a9d7f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7228ad80-3683-5660-867a-f83e1ce6b9fe.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Centro de Tecnolog\u00edas y Aplicaciones del Lenguaje y del Habla (TALP)"
-    ],
-    "Contributor": [
-        "Berm\u00fadez, Meritxell Gonz\u00e1lez"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1187",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1187"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1187",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Centro de Tecnolog\u00edas y Aplicaciones del Lenguaje y del Habla (TALP)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1187;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;DiSi: Flexible Dialogue System;Berm\u00fadez, Meritxell Gonz\u00e1lez;Dialogue manager;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1187;spa;downloadable_files_count: 0;Spain;Centro de Tecnolog\u00edas y Aplicaciones del Lenguaje y del Habla (TALP);http://www.lsi.upc.es/~nlp/disi/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7228ad80-3683-5660-867a-f83e1ce6b9fe",
-    "notes": [
-        "Dialogue manager"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1187"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "DiSi: Flexible Dialogue System"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7232ac18-866d-55e5-9b92-8c9826fed221.json b/oaitestdata/clarin-oai_dc/SET_1/json/7232ac18-866d-55e5-9b92-8c9826fed221.json
deleted file mode 100644
index 5cf3c6cc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7232ac18-866d-55e5-9b92-8c9826fed221.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contributor": [
-        "Gloning, Prof. Dr. Thomas"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1128",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1128"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1128",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1128;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Textsammlung von Thomas Gloning;Gloning, Prof. Dr. Thomas;Germanistik;i.a. collection of old herbal books, old cookery books and texts on the history of  German language in print media; u.a. eine Sammlung von alten Kr\u00e4uterb\u00fcchern, alten Kochb\u00fcchern und Texten zur Geschichte der deutschen Pressesprache;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1128;deu;lat;downloadable_files_count: 0;Germany;http://www.uni-giessen.de/gloning/etexte.htm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7232ac18-866d-55e5-9b92-8c9826fed221",
-    "notes": [
-        "i.a. collection of old herbal books, old cookery books and texts on the history of  German language in print media; u.a. eine Sammlung von alten Kr\u00e4uterb\u00fcchern, alten Kochb\u00fcchern und Texten zur Geschichte der deutschen Pressesprache"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1128"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Textsammlung von Thomas Gloning"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7235af45-fed7-548b-b09a-a02d4b2378f8.json b/oaitestdata/clarin-oai_dc/SET_1/json/7235af45-fed7-548b-b09a-a02d4b2378f8.json
deleted file mode 100644
index da01c3ce..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7235af45-fed7-548b-b09a-a02d4b2378f8.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Andrzeja Piotrkowczyka"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-94778",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-94778"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D41-7",
-    "PublicationTimestamp": "1635-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1635"
-    ],
-    "Publisher": [
-        "Drukarnia Andrzeja Piotrkowczyka"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/94778",
-        "oai:jbc.bj.uj.edu.pl:publication:101741"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1601/1700"
-    ],
-    "TempCoverageBegin": 50506804799,
-    "TempCoverageEnd": 50506804799,
-    "TemporalCoverage": " point in time : 1601-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1601-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1601-07-01T11:59:59Z",
-    "author": [
-        "Ostrowski, Jakub ( -1638)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-94778;2019-03-01T17:57:02Z;Wiek Smierci\u0105 skrocony Naiasnieyszego Alexandra Carola, Polskiego, y Szwedskiego, Krolewica / Przez [...] X. Iakvba Ostrowskiego [...] Przy pogrzebie z \u017calem og\u0142oszony w Roku [...] M. DC. XXXV. Dnia Lutego VII;Ostrowski, Jakub ( -1638);starodruki 17\u00a0w.;Jan II Kazimierz (kr\u00f3l Polski ; 1609-1672). [Adr. ded.];S\u0142owikowski, Justus (ca 1595-1654). [Aut. ded.];Drukarnia Andrzeja Piotrkowczyka;[1635];starodruk;application/xml;clarind-uds:poldilemma-94778;hdl:11858/00-246C-0000-0023-8D41-7;Biblioteka Jagiello\u0144ska, BJ St. Dr. 294387 I;pol;http://jbc.bj.uj.edu.pl/Content/94778;oai:jbc.bj.uj.edu.pl:publication:101741;1601/1700;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7235af45-fed7-548b-b09a-a02d4b2378f8",
-    "notes": [
-        "Jan II Kazimierz (kr\u00f3l Polski ; 1609-1672). [Adr. ded.]",
-        "S\u0142owikowski, Justus (ca 1595-1654). [Aut. ded.]"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-94778"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Wiek Smierci\u0105 skrocony Naiasnieyszego Alexandra Carola, Polskiego, y Szwedskiego, Krolewica / Przez [...] X. Iakvba Ostrowskiego [...] Przy pogrzebie z \u017calem og\u0142oszony w Roku [...] M. DC. XXXV. Dnia Lutego VII"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/723e702f-0884-5eef-ac69-09f22bc206f7.json b/oaitestdata/clarin-oai_dc/SET_1/json/723e702f-0884-5eef-ac69-09f22bc206f7.json
deleted file mode 100644
index 593e6e07..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/723e702f-0884-5eef-ac69-09f22bc206f7.json
+++ /dev/null
@@ -1,88 +0,0 @@
-{
-    "Contact": [
-        "Lehrstuhl Phonetik (Fachrichtung 4.7) und Lehrstuhl Slavistik (Fachrichtung 4.4) der Philosophischen Fakult\u00e4t II der Universit\u00e4t des Saarlandes"
-    ],
-    "Contributor": [
-        "William Barry",
-        "Marko Pallmann",
-        "Juro Frahnow",
-        "Holger von Rauch",
-        "Roland Marti",
-        "Bistra Andreeva",
-        "Jutta Kaiser",
-        "Helena Pallmann",
-        "Olga Trifsik"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "audio/mpeg",
-        "audio/x-wav"
-    ],
-    "Language": [
-        "Lower Sorbian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:genie",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:genie"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0005-BD10-7",
-    "PublicationTimestamp": "2006-11-06T11:59:59Z",
-    "PublicationYear": [
-        "2006"
-    ],
-    "Publisher": [
-        "Lehrstuhl Phonetik (Fachrichtung 4.7) und Lehrstuhl Slavistik (Fachrichtung 4.4) der Philosophischen Fakult\u00e4t II der Universit\u00e4t des Saarlandes"
-    ],
-    "ResourceType": [
-        "Collection"
-    ],
-    "Rights": [
-        "Copyrighted, Registration necessary",
-        "License: http://genie.coli.uni-saarland.de/cgi-bin/benutzer.html"
-    ],
-    "SpatialCoverage": [
-        "1951/2006",
-        "Lausitz"
-    ],
-    "TemporalCoverage": " period : ( 1951-07-01T11:59:59Z - None ) ",
-    "author": [
-        "Roland Marti\nFR 4.4 Slavistik\nUniversit\u00e4t des Saarlandes\nPostfach 15 11 50\nD\u201366041 Saarbr\u00fccken"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:genie;2014-06-03T12:59:07Z;GENIE \u2013 GEsprochenes NIEdersorbisch/Wendisch;Roland Marti\nFR 4.4 Slavistik\nUniversit\u00e4t des Saarlandes\nPostfach 15 11 50\nD\u201366041 Saarbr\u00fccken;Lausitz;Spoken Language;Dialect;The corpus GENIE - spoken Niedersorbisch/Wendisch gives acces to the spoken Variants of these languages via a databases.  It presents one of the two only autochthone slavic minority languages in Germany, which is spoken in the Lausitz by less than 10,000 people in a native way, in acustic form. The language is endangered. It shows the development and changes due to the regional and temporal aspects of the language during the last decade. It provides spoken language material for scientific research especially in the area of phonetics. It includes 350 audio files with over 62 hours of selected niedersorbische speech recordings from different sources and eras. It provides detailed information for each recording, which makes it possible to search for recordings with specific characteristics The audio files are available uncompressed as .wav files and compressed as .mp3 files.;Das Korpus GENIE \u2013 GEsprochenes NIEdersorbisch/Wendisch macht das Niedersorbische/Wendische in seinen gesprochenen Variet\u00e4ten durch eine Datenbank mit Webanwendung im Netz zug\u00e4nglich.  Es pr\u00e4sentiert in akustischer Form eine der beiden einzigen autochthonen slawischen Minderheitssprachen in Deutschland, die in der Lausitz von weniger als 10.000 Personen auf muttersprachlichem Niveau gesprochen wird und in ihrer Existenz bedroht ist. Es zeigt die Entwicklung und die regional und zeitlich bedingten Ver\u00e4nderungen in dieser Sprache im letzten Jahrhundert auf. Es stellt sprachliches Material f\u00fcr wissenschaftliche Untersuchungen, insbesondere auf dem Gebiet der Phonetik, zur Verf\u00fcgung. Es enth\u00e4lt \u00fcber 62 Stunden ausgew\u00e4hlte niedersorbische Sprachaufnahmen aus verschiedenen Quellen und Epochen in knapp 350 Audiodateien. Es liefert zu allen Aufnahmen ausf\u00fchrliche Informationen, \u00fcber die gezielt nach Aufnahmen mit bestimmten Eigenschaften gesucht werden kann. Es h\u00e4lt alle Audiodateien sowohl unkompromiert als .wav-Dateien wie auch als komprimierte .mp3-Dateien zum Download bereit.;Lehrstuhl Phonetik (Fachrichtung 4.7) und Lehrstuhl Slavistik (Fachrichtung 4.4) der Philosophischen Fakult\u00e4t II der Universit\u00e4t des Saarlandes;Roland Marti;Holger von Rauch;Juro Frahnow;Jutta Kaiser;Helena Pallmann;Marko Pallmann;Olga Trifsik;Bistra Andreeva;William Barry;2006-11-06;Collection;audio/x-wav;audio/mpeg;clarind-uds:genie;hdl:11858/00-246C-0000-0005-BD10-7;Archiv des Sorbischen Rundfunks: http://www.rbb-online.de/radio/sorbisches_programm/sorbisches_programm.html;Best\u00e4nde des Sorbischen Kulturarchivs im Serbski institut z.t.: http://www.serbski-institut.de/;dsb;1951/2006;Lausitz;Copyrighted, Registration necessary;License: http://genie.coli.uni-saarland.de/cgi-bin/benutzer.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "723e702f-0884-5eef-ac69-09f22bc206f7",
-    "notes": [
-        "The corpus GENIE - spoken Niedersorbisch/Wendisch gives acces to the spoken Variants of these languages via a databases.  It presents one of the two only autochthone slavic minority languages in Germany, which is spoken in the Lausitz by less than 10,000 people in a native way, in acustic form. The language is endangered. It shows the development and changes due to the regional and temporal aspects of the language during the last decade. It provides spoken language material for scientific research especially in the area of phonetics. It includes 350 audio files with over 62 hours of selected niedersorbische speech recordings from different sources and eras. It provides detailed information for each recording, which makes it possible to search for recordings with specific characteristics The audio files are available uncompressed as .wav files and compressed as .mp3 files.",
-        "Das Korpus GENIE \u2013 GEsprochenes NIEdersorbisch/Wendisch macht das Niedersorbische/Wendische in seinen gesprochenen Variet\u00e4ten durch eine Datenbank mit Webanwendung im Netz zug\u00e4nglich.  Es pr\u00e4sentiert in akustischer Form eine der beiden einzigen autochthonen slawischen Minderheitssprachen in Deutschland, die in der Lausitz von weniger als 10.000 Personen auf muttersprachlichem Niveau gesprochen wird und in ihrer Existenz bedroht ist. Es zeigt die Entwicklung und die regional und zeitlich bedingten Ver\u00e4nderungen in dieser Sprache im letzten Jahrhundert auf. Es stellt sprachliches Material f\u00fcr wissenschaftliche Untersuchungen, insbesondere auf dem Gebiet der Phonetik, zur Verf\u00fcgung. Es enth\u00e4lt \u00fcber 62 Stunden ausgew\u00e4hlte niedersorbische Sprachaufnahmen aus verschiedenen Quellen und Epochen in knapp 350 Audiodateien. Es liefert zu allen Aufnahmen ausf\u00fchrliche Informationen, \u00fcber die gezielt nach Aufnahmen mit bestimmten Eigenschaften gesucht werden kann. Es h\u00e4lt alle Audiodateien sowohl unkompromiert als .wav-Dateien wie auch als komprimierte .mp3-Dateien zum Download bereit."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:genie"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Lausitz"
-        },
-        {
-            "name": "Spoken Language"
-        },
-        {
-            "name": "Dialect"
-        }
-    ],
-    "title": [
-        "GENIE \u2013 GEsprochenes NIEdersorbisch/Wendisch"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/724f8b5a-e5c0-5e3a-afc1-010db7f3eef6.json b/oaitestdata/clarin-oai_dc/SET_1/json/724f8b5a-e5c0-5e3a-afc1-010db7f3eef6.json
deleted file mode 100644
index 1ac3dead..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/724f8b5a-e5c0-5e3a-afc1-010db7f3eef6.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Piotr Elert"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Latin",
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-237950",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-237950"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D11-6",
-    "PublicationTimestamp": "1633-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1633"
-    ],
-    "Publisher": [
-        "Piotr Elert"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/237950",
-        "oai:jbc.bj.uj.edu.pl:publication:249751"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1601/1700"
-    ],
-    "TempCoverageBegin": 50506804799,
-    "TempCoverageEnd": 50506804799,
-    "TemporalCoverage": " point in time : 1601-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1601-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1601-07-01T11:59:59Z",
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-237950;2019-03-01T13:20:54Z;Sczesne stad\u0142o Iego Msci p. Samuela z Hvsiatyna Kalinowskiego, czernichowskiego [...] starosty, z Iey Mci\u0105 Pann\u0105 Vrszvl\u0105 Brigitt\u0105 z T\u0119czyna Ossolinsk\u0105 [...] oyczyst\u0105 muz\u0105 ws\u0142awione;starodruki 17\u00a0w.;Kalinowski, Samuel Jerzy ( -1652). [Adr. ded.];Ossoli\u0144ska, Urszula Brygida (16..-16..). [Adr. ded.];Piotr Elert;[1633];starodruk;application/xml;clarind-uds:poldilemma-237950;hdl:11858/00-246C-0000-0023-8D11-6;Biblioteka Jagiello\u0144ska, BJ St. Dr. 3627 III;lat;pol;http://jbc.bj.uj.edu.pl/Content/237950;oai:jbc.bj.uj.edu.pl:publication:249751;1601/1700;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "724f8b5a-e5c0-5e3a-afc1-010db7f3eef6",
-    "notes": [
-        "Kalinowski, Samuel Jerzy ( -1652). [Adr. ded.]",
-        "Ossoli\u0144ska, Urszula Brygida (16..-16..). [Adr. ded.]"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-237950"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Sczesne stad\u0142o Iego Msci p. Samuela z Hvsiatyna Kalinowskiego, czernichowskiego [...] starosty, z Iey Mci\u0105 Pann\u0105 Vrszvl\u0105 Brigitt\u0105 z T\u0119czyna Ossolinsk\u0105 [...] oyczyst\u0105 muz\u0105 ws\u0142awione"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/72506ada-32ce-5f5f-8ace-4bbad4a2bb7c.json b/oaitestdata/clarin-oai_dc/SET_1/json/72506ada-32ce-5f5f-8ace-4bbad4a2bb7c.json
deleted file mode 100644
index b07dafb1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/72506ada-32ce-5f5f-8ace-4bbad4a2bb7c.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Waite, Stephen V.F."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 45 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0259",
-    "MetadataAccess": [
-        "oai:ota:oucs:0259"
-    ],
-    "PublicationYear": [
-        "700 BCE"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hesiod"
-    ],
-    "fulltext": "oai:ota:oucs:0259;2018-07-27T14:11:29Z;http://ota.ox.ac.uk/headers/0259.xml;Theogony. Greek;Theogonia / Hesiod;Theogony;Hesiod;700 BCE;text_and_corpus_linguistics;Greek poetry, Hellenistic -- Origins;grc;Oxford Text Archive, University of Oxford;Waite, Stephen V.F.;text/plain;(1 file : ca. 45 KB);Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "72506ada-32ce-5f5f-8ace-4bbad4a2bb7c",
-    "oai_identifier": [
-        "oai:ota:oucs:0259"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Greek poetry"
-        },
-        {
-            "name": "Hellenistic -- Origins"
-        }
-    ],
-    "title": [
-        "Theogony. Greek",
-        "Theogonia / Hesiod",
-        "Theogony"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0259.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/72555ec1-5fde-565a-9d69-c44e33bd067d.json b/oaitestdata/clarin-oai_dc/SET_1/json/72555ec1-5fde-565a-9d69-c44e33bd067d.json
deleted file mode 100644
index 5f8c09e6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/72555ec1-5fde-565a-9d69-c44e33bd067d.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Carrer, Luisa"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml",
-        "(10 files : ca. 55.8 MB)"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2454",
-    "MetadataAccess": [
-        "oai:ota:oucs:2454"
-    ],
-    "PublicationTimestamp": "1836-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1836"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Periodicals"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:2454;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/2454.xml;La Favilla, A Triestine Journal (1836-1846);1836-1846;text_and_corpus_linguistics;Italian literature -- 19th century;ces;Oxford Text Archive, University of Oxford;Carrer, Luisa;text/xml;(10 files : ca. 55.8 MB);Text;Periodicals;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "72555ec1-5fde-565a-9d69-c44e33bd067d",
-    "oai_identifier": [
-        "oai:ota:oucs:2454"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Italian literature -- th century"
-        }
-    ],
-    "title": [
-        "La Favilla, A Triestine Journal (1836-1846)"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2454.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/725778f0-63a1-5f2c-9dcc-c8faeaa04027.json b/oaitestdata/clarin-oai_dc/SET_1/json/725778f0-63a1-5f2c-9dcc-c8faeaa04027.json
deleted file mode 100644
index b4a7579c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/725778f0-63a1-5f2c-9dcc-c8faeaa04027.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/272",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/272"
-    ],
-    "PID": "http://hdl.handle.net/11321/272",
-    "PublicationTimestamp": "2016-05-31T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "Sikora, Piotr"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/272;2016-05-31T20:47:23Z;hdl_11321_3;hdl_11321_4;Topos\u0142aw 2;Sikora, Piotr;inflection;lexicography;multi-word units;Topos\u0142aw 2 is an editor of multi-word unit inflection lexicons.;2016-05-31;toolService;http://hdl.handle.net/11321/272;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 2;Institute of Computer Science, Polish Academy of Sciences;http://zil.ipipan.waw.pl/Toposlaw2",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "725778f0-63a1-5f2c-9dcc-c8faeaa04027",
-    "notes": [
-        "Topos\u0142aw 2 is an editor of multi-word unit inflection lexicons."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/272"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "inflection"
-        },
-        {
-            "name": "lexicography"
-        },
-        {
-            "name": "multi-word units"
-        }
-    ],
-    "title": [
-        "Topos\u0142aw 2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/726c2d96-01e0-537f-b488-be7f615903b2.json b/oaitestdata/clarin-oai_dc/SET_1/json/726c2d96-01e0-537f-b488-be7f615903b2.json
deleted file mode 100644
index 55d8a16c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/726c2d96-01e0-537f-b488-be7f615903b2.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4542",
-    "MetadataAccess": [
-        "oai:ota:oucs:4542"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Lennox, Charlotte, ca. 1729-1804."
-    ],
-    "fulltext": "oai:ota:oucs:4542;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4542.xml;The female Quixote: or, the adventures of Arabella. In two volumes. ... [pt.1];Lennox, Charlotte, ca. 1729-1804.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "726c2d96-01e0-537f-b488-be7f615903b2",
-    "oai_identifier": [
-        "oai:ota:oucs:4542"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The female Quixote: or, the adventures of Arabella. In two volumes. ... [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4542.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/726f4b6d-6102-57b6-bf76-6761d85d91a0.json b/oaitestdata/clarin-oai_dc/SET_1/json/726f4b6d-6102-57b6-bf76-6761d85d91a0.json
deleted file mode 100644
index 3faa75ca..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/726f4b6d-6102-57b6-bf76-6761d85d91a0.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Svenska Akademien"
-    ],
-    "Contributor": [
-        "Mattisson, Anki"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1013",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1013"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1013",
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Svenska Akademien"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Sweden"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1013;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Svenska Akademiens ordbok (SAOB);Mattisson, Anki;Historical dictionary of the Swedish language. Includes information about pronunciation, inflexions, variant forms, etymologies, usages and definitions.;2014;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1013;swe;downloadable_files_count: 0;Sweden;Svenska Akademien;http://www.saob.se/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "726f4b6d-6102-57b6-bf76-6761d85d91a0",
-    "notes": [
-        "Historical dictionary of the Swedish language. Includes information about pronunciation, inflexions, variant forms, etymologies, usages and definitions."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1013"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Svenska Akademiens ordbok (SAOB)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7277c0ba-22f0-5578-aa40-00be4b2612c7.json b/oaitestdata/clarin-oai_dc/SET_1/json/7277c0ba-22f0-5578-aa40-00be4b2612c7.json
deleted file mode 100644
index 6d05e9b4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7277c0ba-22f0-5578-aa40-00be4b2612c7.json
+++ /dev/null
@@ -1,93 +0,0 @@
-{
-    "Contact": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 5",
-        "application/zip",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1039",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1039"
-    ],
-    "PID": "http://hdl.handle.net/11356/1039",
-    "PublicationTimestamp": "2015-06-14T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "RelatedIdentifier": [
-        "https://e-knjige.ff.uni-lj.si/znanstvena-zalozba/catalog/download/2/1/47-1?inline=1",
-        "http://hdl.handle.net/11356/1033"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Krek, Simon",
-        "Holozan, Peter",
-        "Erjavec, Toma\u017e",
-        "Romih, Miro",
-        "Dobrovoljc, Kaja"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1039;2019-01-26T18:54:42Z;hdl_11356_1023;hdl_11356_1024;Morphological lexicon Sloleks 1.2;Dobrovoljc, Kaja;Krek, Simon;Holozan, Peter;Erjavec, Toma\u017e;Romih, Miro;morphology;inflection;word forms;derivation;LMF;lemmatisation;Sloleks is the reference morphological lexicon for Slovenian language, developed to be used in NLP applications and language manuals. Encoded in LMF XML, the lexicon contains approx. 100.000 most frequent Slovenian lemmas, their inflected or derivative word forms and the corresponding grammatical description. Lemmatization rules, part-of-speech categorization and the set of feature-value pairs follow the JOS morphosyntactic specifications. In addition to grammatical information, each word form is also given the information on its absolute corpus frequency and its compliance with the reference language standard.\r\n\r\nNote that this entry updates Sloleks 1.0 by fixing various encoding and content errors.\r\n\r\nThe resource is further described in:\r\n\r\nKaja Dobrovoljc, Simon Krek and Toma\u017e Erjavec, 2017:  The Sloleks Morphological Lexicon and its Future Development. In (Vojko Gorjanc, Polona Gantar, Iztok Kosem and Simon Krek, eds.): Dictionary of Modern Slovene: Problems and Solutions. Ljubljana University Press, Faculty of Arts. https://e-knjige.ff.uni-lj.si/znanstvena-zalozba/catalog/download/2/1/47-1;2015-06-14;lexicalConceptualResource;http://hdl.handle.net/11356/1039;slv;https://e-knjige.ff.uni-lj.si/znanstvena-zalozba/catalog/download/2/1/47-1?inline=1;http://hdl.handle.net/11356/1033;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);https://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 5;Centre for Language Resources and Technologies, University of Ljubljana;http://eng.slovenscina.eu/sloleks/opis",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7277c0ba-22f0-5578-aa40-00be4b2612c7",
-    "notes": [
-        "Sloleks is the reference morphological lexicon for Slovenian language, developed to be used in NLP applications and language manuals. Encoded in LMF XML, the lexicon contains approx. 100.000 most frequent Slovenian lemmas, their inflected or derivative word forms and the corresponding grammatical description. Lemmatization rules, part-of-speech categorization and the set of feature-value pairs follow the JOS morphosyntactic specifications. In addition to grammatical information, each word form is also given the information on its absolute corpus frequency and its compliance with the reference language standard.\r\n\r\nNote that this entry updates Sloleks 1.0 by fixing various encoding and content errors.\r\n\r\nThe resource is further described in:\r\n\r\nKaja Dobrovoljc, Simon Krek and Toma\u017e Erjavec, 2017:  The Sloleks Morphological Lexicon and its Future Development. In (Vojko Gorjanc, Polona Gantar, Iztok Kosem and Simon Krek, eds.): Dictionary of Modern Slovene: Problems and Solutions. Ljubljana University Press, Faculty of Arts. https://e-knjige.ff.uni-lj.si/znanstvena-zalozba/catalog/download/2/1/47-1"
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1039"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "inflection"
-        },
-        {
-            "name": "word forms"
-        },
-        {
-            "name": "derivation"
-        },
-        {
-            "name": "LMF"
-        },
-        {
-            "name": "lemmatisation"
-        }
-    ],
-    "title": [
-        "Morphological lexicon Sloleks 1.2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/727c8602-4990-5e1f-97c5-1cdff6ea099d.json b/oaitestdata/clarin-oai_dc/SET_1/json/727c8602-4990-5e1f-97c5-1cdff6ea099d.json
deleted file mode 100644
index cce17279..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/727c8602-4990-5e1f-97c5-1cdff6ea099d.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Department of Linguistics, The University of Hong Kong"
-    ],
-    "Contributor": [
-        "K.K.Luke, Dr"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-884",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-884"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-884",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Department of Linguistics, The University of Hong Kong"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Hong Kong"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-884;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;International Corpus of English: Hong Kong (ICE-HK);K.K.Luke, Dr;One million words of spoken and written Hong Kong English produced after 1989. Part of the ICE project.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-884;eng;downloadable_files_count: 0;Hong Kong;Department of Linguistics, The University of Hong Kong;http://www.ucl.ac.uk/english-usage/ice/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "727c8602-4990-5e1f-97c5-1cdff6ea099d",
-    "notes": [
-        "One million words of spoken and written Hong Kong English produced after 1989. Part of the ICE project."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-884"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "International Corpus of English: Hong Kong (ICE-HK)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/72824b94-d410-5018-b4c6-e3239d5a44a7.json b/oaitestdata/clarin-oai_dc/SET_1/json/72824b94-d410-5018-b4c6-e3239d5a44a7.json
deleted file mode 100644
index 22e3505f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/72824b94-d410-5018-b4c6-e3239d5a44a7.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Department of Anglo-Saxon, Norse, and Celtic at the University of Cambridge"
-    ],
-    "Contributor": [
-        "Russell, Paul"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Irish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-981",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-981"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-981",
-    "PublicationTimestamp": "2009-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2009"
-    ],
-    "Publisher": [
-        "Department of Anglo-Saxon, Norse, and Celtic at the University of Cambridge"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-981;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Early Irish Glossaries;Russell, Paul;Database of three inter-related early Irish glossaries. The texts, compiled from the eighth century, comprise several thousand headwords followed by entries that can range from single word explanations to whole narratives running to several pages.;2009;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-981;gle;downloadable_files_count: 0;United Kingdom;Department of Anglo-Saxon, Norse, and Celtic at the University of Cambridge;http://www.asnc.cam.ac.uk/irishglossaries/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "72824b94-d410-5018-b4c6-e3239d5a44a7",
-    "notes": [
-        "Database of three inter-related early Irish glossaries. The texts, compiled from the eighth century, comprise several thousand headwords followed by entries that can range from single word explanations to whole narratives running to several pages."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-981"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Early Irish Glossaries"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7288b20f-d9b3-57c1-930a-5a8d872136d7.json b/oaitestdata/clarin-oai_dc/SET_1/json/7288b20f-d9b3-57c1-930a-5a8d872136d7.json
deleted file mode 100644
index a3126425..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7288b20f-d9b3-57c1-930a-5a8d872136d7.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=2c144d4863ec11e2a2aa782bcb074135e8d82734dd3f4e5083ecf05a0f47b80d",
-    "MetadataAccess": [
-        "2c144d4863ec11e2a2aa782bcb074135e8d82734dd3f4e5083ecf05a0f47b80d"
-    ],
-    "PublicationTimestamp": "2014-10-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "fulltext": "2c144d4863ec11e2a2aa782bcb074135e8d82734dd3f4e5083ecf05a0f47b80d;2018-11-15T16:40:06Z;corpus;corpus:text;CINTIL-DeepBank 1.3;CINTIL-DeepBank (Branco et al., 2010) is a corpus of Portuguese texts annotated with deep grammatical information. This document refers to version 1.3 of the corpus, delivered in September of 2015, which adds over 2,000 annotated sentences to the previous version from March 2015. The current version is composed by 17,030 sentences (166,933 tokens) taken from two different sources and domains: news (15,851 sentences; 159,525 tokens), novels (399 sentences; 2,547 tokens). In addition, there are 780 sentences (4,861 tokens) that are used for regression testing of the computational grammar that supported the annotation of the corpus.\n\nCINTIL-DeepBank includes several levels of information for each sentence, including its derivation tree originated during parsing, its syntactic constituency tree, different renderings of MRS based representations of its meaning (Copestake, 2006), and its fully-fledged grammatical representation in AVM format. This is the result of a semi-automatic annotation process by means of automatic analysis by the grammar followed by a double-blind annotation followed by adjudication (see (Branco and Costa, 2008), for a full description of the process).\n\nThe main motivation behind the creation of this resource was to build a high quality data set with rich grammatical information that could support the development of a large set of high level language resources and processing tools for Portuguese.\n\nThe development of this resource started under the project SemanticShare \u00e2\u0080\u0093 Resources and Tools for Semantic Processing (at: http://nlx.di.fc.ul.pt/projects.html) whose main goal was to generate a deep linguistic annotated corpus of Portuguese, with manually verified grammatical representations,  was continued in the project METANET4U-Enhancing the Linguistic Infrastructure of Europe, and in the project QTLeap-Quality Translation by Deep Language Engineering Approaches. ;2014-10-01",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7288b20f-d9b3-57c1-930a-5a8d872136d7",
-    "notes": [
-        "CINTIL-DeepBank (Branco et al., 2010) is a corpus of Portuguese texts annotated with deep grammatical information. This document refers to version 1.3 of the corpus, delivered in September of 2015, which adds over 2,000 annotated sentences to the previous version from March 2015. The current version is composed by 17,030 sentences (166,933 tokens) taken from two different sources and domains: news (15,851 sentences; 159,525 tokens), novels (399 sentences; 2,547 tokens). In addition, there are 780 sentences (4,861 tokens) that are used for regression testing of the computational grammar that supported the annotation of the corpus.\n\nCINTIL-DeepBank includes several levels of information for each sentence, including its derivation tree originated during parsing, its syntactic constituency tree, different renderings of MRS based representations of its meaning (Copestake, 2006), and its fully-fledged grammatical representation in AVM format. This is the result of a semi-automatic annotation process by means of automatic analysis by the grammar followed by a double-blind annotation followed by adjudication (see (Branco and Costa, 2008), for a full description of the process).\n\nThe main motivation behind the creation of this resource was to build a high quality data set with rich grammatical information that could support the development of a large set of high level language resources and processing tools for Portuguese.\n\nThe development of this resource started under the project SemanticShare \u00e2\u0080\u0093 Resources and Tools for Semantic Processing (at: http://nlx.di.fc.ul.pt/projects.html) whose main goal was to generate a deep linguistic annotated corpus of Portuguese, with manually verified grammatical representations,  was continued in the project METANET4U-Enhancing the Linguistic Infrastructure of Europe, and in the project QTLeap-Quality Translation by Deep Language Engineering Approaches. "
-    ],
-    "oai_identifier": [
-        "2c144d4863ec11e2a2aa782bcb074135e8d82734dd3f4e5083ecf05a0f47b80d"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "CINTIL-DeepBank 1.3"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7291b0d1-696b-50d1-9555-f11cf86071c3.json b/oaitestdata/clarin-oai_dc/SET_1/json/7291b0d1-696b-50d1-9555-f11cf86071c3.json
deleted file mode 100644
index 6c53fb3b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7291b0d1-696b-50d1-9555-f11cf86071c3.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Tomasic, Thomas M"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 154 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0582",
-    "MetadataAccess": [
-        "oai:ota:oucs:0582"
-    ],
-    "PublicationYear": [
-        "375-395"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Sermons"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gregory, of Nyssa, Saint, ca. 335-ca. 394"
-    ],
-    "fulltext": "oai:ota:oucs:0582;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0582.xml;De hominis opifico. Latin.;De hominis opifico / Saint Gregory of Nyssa;Gregory, of Nyssa, Saint, ca. 335-ca. 394;375-395;text_and_corpus_linguistics;Sermons -- Turkey -- 4th century;lat;Oxford Text Archive, University of Oxford;Tomasic, Thomas M;text/plain;(1 file : ca. 154 KB);Text;Sermons;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7291b0d1-696b-50d1-9555-f11cf86071c3",
-    "oai_identifier": [
-        "oai:ota:oucs:0582"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Sermons -- Turkey -- th century"
-        }
-    ],
-    "title": [
-        "De hominis opifico. Latin.",
-        "De hominis opifico / Saint Gregory of Nyssa"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0582.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/72a05136-c04d-5e13-a2e6-ccf89752c9a4.json b/oaitestdata/clarin-oai_dc/SET_1/json/72a05136-c04d-5e13-a2e6-ccf89752c9a4.json
deleted file mode 100644
index 07da6077..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/72a05136-c04d-5e13-a2e6-ccf89752c9a4.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/290",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/290"
-    ],
-    "PID": "http://hdl.handle.net/11321/290",
-    "PublicationTimestamp": "2016-06-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "K\u0119dzia, Pawe\u0142",
-        "Orli\u0144ska, Marlena",
-        "Piasecki, Maciej"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/290;2016-06-03T14:49:08Z;hdl_11321_3;hdl_11321_4;WoSeDon;K\u0119dzia, Pawe\u0142;Piasecki, Maciej;Orli\u0144ska, Marlena;WSD;plWordNet;Word Sense Disambiguation;WoSeDon is a tool for Word Sense Disambiguation. It works for polish texts and as a source of possible senses using plWordNet.;2016-06-01;toolService;http://hdl.handle.net/11321/290;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 1;Wroc\u0142aw University of Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "72a05136-c04d-5e13-a2e6-ccf89752c9a4",
-    "notes": [
-        "WoSeDon is a tool for Word Sense Disambiguation. It works for polish texts and as a source of possible senses using plWordNet."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/290"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "WSD"
-        },
-        {
-            "name": "plWordNet"
-        },
-        {
-            "name": "Word Sense Disambiguation"
-        }
-    ],
-    "title": [
-        "WoSeDon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/72a68f7e-033b-5f13-8c78-b76b46f1dca4.json b/oaitestdata/clarin-oai_dc/SET_1/json/72a68f7e-033b-5f13-8c78-b76b46f1dca4.json
deleted file mode 100644
index 3cd04d2c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/72a68f7e-033b-5f13-8c78-b76b46f1dca4.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "Department of Linguistics and Nordic Studies, University of Oslo"
-    ],
-    "Contributor": [
-        "Wangensteen, Boye"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-669",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-669"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-669",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Department of Linguistics and Nordic Studies, University of Oslo"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-669;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Bokm\u00e5lsordboka;Wangensteen, Boye;65 000 entries with definitions, etymology, examples;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-669;downloadable_files_count: 0;Department of Linguistics and Nordic Studies, University of Oslo;http://www.dokpro.uio.no/ordboksoek.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "72a68f7e-033b-5f13-8c78-b76b46f1dca4",
-    "notes": [
-        "65 000 entries with definitions, etymology, examples"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-669"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Bokm\u00e5lsordboka"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/72d81622-32c2-5e82-a5b0-c8cded5a8cc4.json b/oaitestdata/clarin-oai_dc/SET_1/json/72d81622-32c2-5e82-a5b0-c8cded5a8cc4.json
deleted file mode 100644
index 72bc5bd0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/72d81622-32c2-5e82-a5b0-c8cded5a8cc4.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "VideoLectures.NET"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 3",
-        "application/zip"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1159",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1159"
-    ],
-    "PID": "http://hdl.handle.net/11356/1159",
-    "PublicationTimestamp": "2017-10-10T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "VideoLectures.NET"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11356/1189",
-        "http://hdl.handle.net/11356/1070"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by-nc-nd/4.0/"
-    ],
-    "author": [
-        "VideoLectures.NET"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1159;2018-10-24T20:50:11Z;hdl_11356_1023;hdl_11356_1024;Spoken corpus Gos VideoLectures 2.0 (audio);VideoLectures.NET;speech database;spoken corpus;academic speech;speech recognition;speech recordings;Gos VideoLectures is an add-on to the Gos reference corpus of spoken Slovene (http://hdl.handle.net/11356/1040), and covers public academic speech. The Gos VideoLectures corpus contains a selection of public lectures available through the web portal Videolectures.net provided by the Jo\u017eef Stefan Institute, and covers 9.8 hours of speech. \r\nThis resource contains only audio recordings of the corpus \u2013 annotated transcriptions are available at http://hdl.handle.net/11356/1158.;2017-10-10;corpus;http://hdl.handle.net/11356/1159;slv;http://hdl.handle.net/11356/1189;http://hdl.handle.net/11356/1070;Creative Commons - Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0);PUB;https://creativecommons.org/licenses/by-nc-nd/4.0/;text/plain; charset=utf-8;application/zip;application/zip;application/zip;downloadable_files_count: 3;VideoLectures.NET",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "72d81622-32c2-5e82-a5b0-c8cded5a8cc4",
-    "notes": [
-        "Gos VideoLectures is an add-on to the Gos reference corpus of spoken Slovene (http://hdl.handle.net/11356/1040), and covers public academic speech. The Gos VideoLectures corpus contains a selection of public lectures available through the web portal Videolectures.net provided by the Jo\u017eef Stefan Institute, and covers 9.8 hours of speech. \r\nThis resource contains only audio recordings of the corpus \u2013 annotated transcriptions are available at http://hdl.handle.net/11356/1158."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1159"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech database"
-        },
-        {
-            "name": "spoken corpus"
-        },
-        {
-            "name": "academic speech"
-        },
-        {
-            "name": "speech recognition"
-        },
-        {
-            "name": "speech recordings"
-        }
-    ],
-    "title": [
-        "Spoken corpus Gos VideoLectures 2.0 (audio)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/72dab5a1-89b2-551f-976d-4fdee22651d3.json b/oaitestdata/clarin-oai_dc/SET_1/json/72dab5a1-89b2-551f-976d-4fdee22651d3.json
deleted file mode 100644
index 9997bd2b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/72dab5a1-89b2-551f-976d-4fdee22651d3.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Gunby, D.C., (David Charles), 1938-"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 93 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0612",
-    "MetadataAccess": [
-        "oai:ota:oucs:0612"
-    ],
-    "PublicationTimestamp": "1625-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1625"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Letters"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Webster, John, 1580?-1625?"
-    ],
-    "fulltext": "oai:ota:oucs:0612;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0612.xml;A speedie poste with certaine new letters / now published for the helpe of such as are desirous to learne to write letters by I.W., Gent.;The first fruits of new conceits, neuer yet disclosed;Webster, John, 1580?-1625?;1625;text_and_corpus_linguistics;Letter writing -- England -- 16th century;eng;Oxford Text Archive, University of Oxford;Gunby, D.C., (David Charles), 1938-;text/plain;(1 file : ca. 93 KB);Text;Letters;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "72dab5a1-89b2-551f-976d-4fdee22651d3",
-    "oai_identifier": [
-        "oai:ota:oucs:0612"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Letter writing -- England -- th century"
-        }
-    ],
-    "title": [
-        "A speedie poste with certaine new letters / now published for the helpe of such as are desirous to learne to write letters by I.W., Gent.",
-        "The first fruits of new conceits, neuer yet disclosed"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0612.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/72e6a37f-b1ce-5d19-af7d-c3926d8671a2.json b/oaitestdata/clarin-oai_dc/SET_1/json/72e6a37f-b1ce-5d19-af7d-c3926d8671a2.json
deleted file mode 100644
index 5a1de5e7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/72e6a37f-b1ce-5d19-af7d-c3926d8671a2.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Institute of Philosophy of the Czech Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2703",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2703"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2703",
-    "PublicationTimestamp": "2018-09-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Institute of Philosophy of the Czech Academy of Sciences"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "The MIT License (MIT)",
-        "http://opensource.org/licenses/mit-license.php",
-        "PUB"
-    ],
-    "author": [
-        "Hladik, Radim"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2703;2018-09-09T18:08:09Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Czech Sociological Review 1993-2016;Hladik, Radim;sociology;academic writing;scholarly writing;journal;Selected research articles and essays published in Czech Sociological Review from 1993 to 2016. Originally Czech, non-translated material only. 522 documents in total.;2018-09-01;corpus;http://hdl.handle.net/11372/LRT-2703;ces;The MIT License (MIT);http://opensource.org/licenses/mit-license.php;PUB;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 1;Institute of Philosophy of the Czech Academy of Sciences",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "72e6a37f-b1ce-5d19-af7d-c3926d8671a2",
-    "notes": [
-        "Selected research articles and essays published in Czech Sociological Review from 1993 to 2016. Originally Czech, non-translated material only. 522 documents in total."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2703"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "sociology"
-        },
-        {
-            "name": "academic writing"
-        },
-        {
-            "name": "scholarly writing"
-        },
-        {
-            "name": "journal"
-        }
-    ],
-    "title": [
-        "Czech Sociological Review 1993-2016"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/72f9a0e3-84d2-52b9-ab37-0745ae602624.json b/oaitestdata/clarin-oai_dc/SET_1/json/72f9a0e3-84d2-52b9-ab37-0745ae602624.json
deleted file mode 100644
index eaf6c3d8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/72f9a0e3-84d2-52b9-ab37-0745ae602624.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1149",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1149"
-    ],
-    "PID": "http://hdl.handle.net/11356/1149",
-    "PublicationTimestamp": "2017-09-15T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Erjavec, Toma\u017e",
-        "Perov\u0161ek, Matic",
-        "Ljube\u0161i\u0107, Nikola"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1149;2019-02-23T17:33:56Z;hdl_11356_1023;hdl_11356_1077;ReLDI token+tag+lemma+NER web service for WebLicht;Ljube\u0161i\u0107, Nikola;Perov\u0161ek, Matic;Erjavec, Toma\u017e;tagging;named entities;WebLicht (https://weblicht.sfs.uni-tuebingen.de/) registry entry for webservice comprising tokenisation, PoS tagging and Named Entity Recognition. Tool source files are available under https://github.com/clarinsi;2017-09-15;toolService;http://hdl.handle.net/11356/1149;slv;application/octet-stream;downloadable_files_count: 0;Jo\u017eef Stefan Institute",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "72f9a0e3-84d2-52b9-ab37-0745ae602624",
-    "notes": [
-        "WebLicht (https://weblicht.sfs.uni-tuebingen.de/) registry entry for webservice comprising tokenisation, PoS tagging and Named Entity Recognition. Tool source files are available under https://github.com/clarinsi"
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1149"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1077"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "named entities"
-        }
-    ],
-    "title": [
-        "ReLDI token+tag+lemma+NER web service for WebLicht"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/730ea694-9776-5f4f-92ee-98ea9fbf6c9a.json b/oaitestdata/clarin-oai_dc/SET_1/json/730ea694-9776-5f4f-92ee-98ea9fbf6c9a.json
deleted file mode 100644
index 74ffd668..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/730ea694-9776-5f4f-92ee-98ea9fbf6c9a.json
+++ /dev/null
@@ -1,95 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1140",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1140"
-    ],
-    "PID": "http://hdl.handle.net/11356/1140",
-    "PublicationTimestamp": "2017-08-17T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "http://slovenscina2.0.trojina.si/arhiv/2016-2/2016-2-04/",
-        "http://nl.ijs.si/janes/viri/avtomatsko-oznaceni-korpusi/#Janes-News",
-        "https://doi.org/10.1007/s10579-018-9425-z"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "Erjavec, Toma\u017e",
-        "Ljube\u0161i\u0107, Nikola",
-        "Fi\u0161er, Darja"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1140;2018-10-29T10:28:37Z;hdl_11356_1023;hdl_11356_1024;News comment corpus Janes-News 1.0;Erjavec, Toma\u017e;Ljube\u0161i\u0107, Nikola;Fi\u0161er, Darja;computer-mediated communication;news comments;word normalisation;tagging;lemmatisation;named entities;TEI;Janes-News is an annotated corpus of comments on online news articles from websites rtvslo.si, mladina.si, and reporter.si from the period 2007-03 to 2015-01. The corpus is structured into individual texts containing the comments on a news article, together with their metadata. The texts in the corpus are tokenised, sentence segmented, word normalised, morphosyntactically tagged, lemmatised and annotated with named entities. Due to protection of privacy, usernames are not included in the metadata and 'person' as well as 'person derivative' named entities have been removed from the texts.;2017-08-17;corpus;http://hdl.handle.net/11356/1140;slv;http://slovenscina2.0.trojina.si/arhiv/2016-2/2016-2-04/;http://nl.ijs.si/janes/viri/avtomatsko-oznaceni-korpusi/#Janes-News;https://doi.org/10.1007/s10579-018-9425-z;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;https://creativecommons.org/licenses/by/4.0/;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 2;Jo\u017eef Stefan Institute;http://nl.ijs.si/janes/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "730ea694-9776-5f4f-92ee-98ea9fbf6c9a",
-    "notes": [
-        "Janes-News is an annotated corpus of comments on online news articles from websites rtvslo.si, mladina.si, and reporter.si from the period 2007-03 to 2015-01. The corpus is structured into individual texts containing the comments on a news article, together with their metadata. The texts in the corpus are tokenised, sentence segmented, word normalised, morphosyntactically tagged, lemmatised and annotated with named entities. Due to protection of privacy, usernames are not included in the metadata and 'person' as well as 'person derivative' named entities have been removed from the texts."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1140"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "computer-mediated communication"
-        },
-        {
-            "name": "news comments"
-        },
-        {
-            "name": "word normalisation"
-        },
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "lemmatisation"
-        },
-        {
-            "name": "named entities"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "News comment corpus Janes-News 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7323da55-e79e-57c9-b1b3-df50b02b4d54.json b/oaitestdata/clarin-oai_dc/SET_1/json/7323da55-e79e-57c9-b1b3-df50b02b4d54.json
deleted file mode 100644
index 8c7161bd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7323da55-e79e-57c9-b1b3-df50b02b4d54.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3125",
-    "MetadataAccess": [
-        "oai:ota:oucs:3125"
-    ],
-    "PublicationTimestamp": "1740-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1740"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Law, William, 1686-1761"
-    ],
-    "fulltext": "oai:ota:oucs:3125;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3125.xml;An appeal to all that doubt, or disbelieve the truths of the Gospel: whether they be Deists, Arians, Socinians, or nominal Christians, in which the true grounds and reasons of the whole Christian faith and life are plainly and fully demonstrated, to which are added, some animadversions upon Dr. Trapp's late reply;Law, William, 1686-1761;not after: 1740;text_and_corpus_linguistics;Theology -- Miscellaneous Christian texts -- English;eng;Oxford Text Archive, University of Oxford;Triggs, Jeffery;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7323da55-e79e-57c9-b1b3-df50b02b4d54",
-    "oai_identifier": [
-        "oai:ota:oucs:3125"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Theology -- Miscellaneous Christian texts -- English"
-        }
-    ],
-    "title": [
-        "An appeal to all that doubt, or disbelieve the truths of the Gospel: whether they be Deists, Arians, Socinians, or nominal Christians, in which the true grounds and reasons of the whole Christian faith and life are plainly and fully demonstrated, to which are added, some animadversions upon Dr. Trapp's late reply"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3125.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/732aa772-a42d-57b7-8da5-692d333b5f2a.json b/oaitestdata/clarin-oai_dc/SET_1/json/732aa772-a42d-57b7-8da5-692d333b5f2a.json
deleted file mode 100644
index e4c68c4d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/732aa772-a42d-57b7-8da5-692d333b5f2a.json
+++ /dev/null
@@ -1,95 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-4338-F",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-4338-F"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-4338-F",
-    "PublicationTimestamp": "2014-02-13T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11858/00-097C-0000-0015-8DAF-4"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Haji\u010d, Jan",
-        "Panevova, Jarmila",
-        "\u0160t\u011bp\u00e1nek, Jan",
-        "Ure\u0161ov\u00e1, Zde\u0148ka",
-        "Mikulov\u00e1, Marie"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-4338-F;2018-05-24T09:54:21Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;PDT-Vallex: Czech Valency lexicon linked to treebanks;Ure\u0161ov\u00e1, Zde\u0148ka;\u0160t\u011bp\u00e1nek, Jan;Haji\u010d, Jan;Panevova, Jarmila;Mikulov\u00e1, Marie;annotation;corpora;data;lexicon;semantics;valency;PDT;The valency lexicon PDT-Vallex has been built in close connection with the annotation of the Prague Dependency Treebank project (PDT) and its successors (mainly the Prague Czech-English Dependency Treebank project, PCEDT). It contains over 11000 valency frames for more than 7000 verbs which occurred in the PDT or PCEDT. It is available in electronically processable format (XML) together with the aforementioned treebanks (to be viewed and edited by TrEd, the PDT/PCEDT main annotation tool), and also in more human readable form including corpus examples (see the WEBSITE link below). The main feature of the lexicon is its linking to the annotated corpora - each occurrence of each verb is linked to the appropriate valency frame with additional (generalized) information about its usage and surface morphosyntactic form alternatives.;2014-02-13;lexicalConceptualResource;http://hdl.handle.net/11858/00-097C-0000-0023-4338-F;ces;http://hdl.handle.net/11858/00-097C-0000-0015-8DAF-4;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://lindat.mff.cuni.cz/services/PDT-Vallex/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "732aa772-a42d-57b7-8da5-692d333b5f2a",
-    "notes": [
-        "The valency lexicon PDT-Vallex has been built in close connection with the annotation of the Prague Dependency Treebank project (PDT) and its successors (mainly the Prague Czech-English Dependency Treebank project, PCEDT). It contains over 11000 valency frames for more than 7000 verbs which occurred in the PDT or PCEDT. It is available in electronically processable format (XML) together with the aforementioned treebanks (to be viewed and edited by TrEd, the PDT/PCEDT main annotation tool), and also in more human readable form including corpus examples (see the WEBSITE link below). The main feature of the lexicon is its linking to the annotated corpora - each occurrence of each verb is linked to the appropriate valency frame with additional (generalized) information about its usage and surface morphosyntactic form alternatives."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-4338-F"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "annotation"
-        },
-        {
-            "name": "corpora"
-        },
-        {
-            "name": "data"
-        },
-        {
-            "name": "lexicon"
-        },
-        {
-            "name": "semantics"
-        },
-        {
-            "name": "valency"
-        },
-        {
-            "name": "PDT"
-        }
-    ],
-    "title": [
-        "PDT-Vallex: Czech Valency lexicon linked to treebanks"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/734af6ef-6d71-5565-abe3-f8dc3c84b36d.json b/oaitestdata/clarin-oai_dc/SET_1/json/734af6ef-6d71-5565-abe3-f8dc3c84b36d.json
deleted file mode 100644
index 2f8075e2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/734af6ef-6d71-5565-abe3-f8dc3c84b36d.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Warsztat Clarin"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 94",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/510",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/510"
-    ],
-    "PID": "http://hdl.handle.net/11321/510",
-    "PublicationTimestamp": "2018-07-13T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Warsztat Clarin"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Super Cool License",
-        "http://www.google.com",
-        "ACA"
-    ],
-    "author": [
-        "Warsztat, Clarin"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/510;2018-07-13T13:49:42Z;hdl_11321_3;hdl_11321_4;Korpus testowy;Warsztat, Clarin;testowy warsztaty clarin;korpus testowy warsztaty Clarin;2018-07-13;corpus;http://hdl.handle.net/11321/510;pol;Super Cool License;http://www.google.com;ACA;text/plain; charset=utf-8;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;downloadable_files_count: 94;Warsztat Clarin",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "734af6ef-6d71-5565-abe3-f8dc3c84b36d",
-    "notes": [
-        "korpus testowy warsztaty Clarin"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/510"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "testowy warsztaty clarin"
-        }
-    ],
-    "title": [
-        "Korpus testowy"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/735633cc-a811-5b5f-a6a3-934cf651464e.json b/oaitestdata/clarin-oai_dc/SET_1/json/735633cc-a811-5b5f-a6a3-934cf651464e.json
deleted file mode 100644
index 06245f91..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/735633cc-a811-5b5f-a6a3-934cf651464e.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Meertens Institute KNAW The Netherlands"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-608",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-608"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-608",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Meertens Institute KNAW The Netherlands"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-608;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;The Dutch Song Database;The Dutch Song Database (Nederlandse Liederenbank in Dutch) contains more than 125,000 songs in the Dutch and Flemish language, from the Middle Ages through the twentieth century.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-608;nld;downloadable_files_count: 0;Netherlands (the);Meertens Institute KNAW The Netherlands;http://www.liederenbank.nl/index.php?lan=en",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "735633cc-a811-5b5f-a6a3-934cf651464e",
-    "notes": [
-        "The Dutch Song Database (Nederlandse Liederenbank in Dutch) contains more than 125,000 songs in the Dutch and Flemish language, from the Middle Ages through the twentieth century."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-608"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "The Dutch Song Database"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7369954c-b1e7-54e6-ae6a-39db952aa992.json b/oaitestdata/clarin-oai_dc/SET_1/json/7369954c-b1e7-54e6-ae6a-39db952aa992.json
deleted file mode 100644
index b04401cf..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7369954c-b1e7-54e6-ae6a-39db952aa992.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3897",
-    "MetadataAccess": [
-        "oai:ota:oucs:3897"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Murphy, Arthur, 1727-1805."
-    ],
-    "fulltext": "oai:ota:oucs:3897;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3897.xml;The citizen. A farce: As it is performed at the Theatre Royal in Covent Garden. By Arthur Murphy, Esq;.;Murphy, Arthur, 1727-1805.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7369954c-b1e7-54e6-ae6a-39db952aa992",
-    "oai_identifier": [
-        "oai:ota:oucs:3897"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The citizen. A farce: As it is performed at the Theatre Royal in Covent Garden. By Arthur Murphy, Esq;."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3897.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/73770821-2b52-50d1-adeb-0b595007cfec.json b/oaitestdata/clarin-oai_dc/SET_1/json/73770821-2b52-50d1-adeb-0b595007cfec.json
deleted file mode 100644
index 3c7ea944..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/73770821-2b52-50d1-adeb-0b595007cfec.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "between 1 and 2 MB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1224",
-    "MetadataAccess": [
-        "oai:ota:oucs:1224"
-    ],
-    "PublicationTimestamp": "1811-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1811"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Austen, Jane,  1775-1817"
-    ],
-    "fulltext": "oai:ota:oucs:1224;2018-02-21T11:28:16Z;http://ota.ox.ac.uk/headers/1224.xml; Sense and sensibility  : (tagged version) / compiled by J.F. Burrows;Austen, Jane,  1775-1817;1811;text_and_corpus_linguistics;Novels -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;between 1 and 2 MB;Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "73770821-2b52-50d1-adeb-0b595007cfec",
-    "oai_identifier": [
-        "oai:ota:oucs:1224"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Novels -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        " Sense and sensibility  : (tagged version) / compiled by J.F. Burrows"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1224.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/73928d3a-ae77-5407-a4cd-85b6b32608cb.json b/oaitestdata/clarin-oai_dc/SET_1/json/73928d3a-ae77-5407-a4cd-85b6b32608cb.json
deleted file mode 100644
index 21b6b382..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/73928d3a-ae77-5407-a4cd-85b6b32608cb.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5534",
-    "MetadataAccess": [
-        "oai:ota:oucs:5534"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Governor, of Addenbrooke's Hospital."
-    ],
-    "fulltext": "oai:ota:oucs:5534;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5534.xml;Explanatory remarks on the great utility of hospitals for the sick and poor: By a governor of Addenbrooke's Hospital.;Governor, of Addenbrooke's Hospital.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "73928d3a-ae77-5407-a4cd-85b6b32608cb",
-    "oai_identifier": [
-        "oai:ota:oucs:5534"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Explanatory remarks on the great utility of hospitals for the sick and poor: By a governor of Addenbrooke's Hospital."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5534.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/73a11c6a-c7d2-5428-bf0c-033b4f626fcd.json b/oaitestdata/clarin-oai_dc/SET_1/json/73a11c6a-c7d2-5428-bf0c-033b4f626fcd.json
deleted file mode 100644
index 5175b2fd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/73a11c6a-c7d2-5428-bf0c-033b4f626fcd.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1148",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1148"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1148",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1148;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Redensarten;Germanistik;W\u00f6rterbuch f\u00fcr Redensarten, Redewendungen, idiomatische Ausdr\u00fccke, feste Wortverbindungen; die Suchergebnisse werden jeweils nach den vier Dimensionen Redensart \u2013 Erl\u00e4uterung \u2013 Beispiele \u2013 Erg\u00e4nzungen angezeigt;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1148;deu;downloadable_files_count: 0;Germany;http://www.redensarten-index.de/suche.php",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "73a11c6a-c7d2-5428-bf0c-033b4f626fcd",
-    "notes": [
-        "W\u00f6rterbuch f\u00fcr Redensarten, Redewendungen, idiomatische Ausdr\u00fccke, feste Wortverbindungen; die Suchergebnisse werden jeweils nach den vier Dimensionen Redensart \u2013 Erl\u00e4uterung \u2013 Beispiele \u2013 Erg\u00e4nzungen angezeigt"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1148"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Redensarten"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/73bb199b-28cd-5eba-b91b-625207984742.json b/oaitestdata/clarin-oai_dc/SET_1/json/73bb199b-28cd-5eba-b91b-625207984742.json
deleted file mode 100644
index 553b7d6e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/73bb199b-28cd-5eba-b91b-625207984742.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "NHH Norwegian School of Economics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "application/octet-stream",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Norwegian Bokm\u00e5l",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/116",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/116"
-    ],
-    "PID": "http://hdl.handle.net/11509/116",
-    "PublicationTimestamp": "2017-01-10T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "NHH Norwegian School of Economics"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "CLARIN_ACA",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NORED=1",
-        "ACA"
-    ],
-    "author": [
-        "Andersen, Gisle",
-        "Kristiansen, Marita",
-        "Olstad, Vemund"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/116;2017-01-18T09:16:21Z;hdl_11509_1;hdl_11509_2;English for business;Kristiansen, Marita;Olstad, Vemund;Andersen, Gisle;Business administration;Economics;Termbase;Terminological;Terminology;The resource \"English for business\" is a terminological database containing terms, definitions and other conceptual information in Norwegian and English within economics and business administration and some related domains.\r\n\r\nWhen using the resource for research purposes, please refer to NHH Norwegian School of Economics.;2017-01-10;lexicalConceptualResource;http://hdl.handle.net/11509/116;nob;eng;CLARIN_ACA;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NORED=1;ACA;application/zip;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;NHH Norwegian School of Economics;http://www.terminologi.no",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "73bb199b-28cd-5eba-b91b-625207984742",
-    "notes": [
-        "The resource \"English for business\" is a terminological database containing terms, definitions and other conceptual information in Norwegian and English within economics and business administration and some related domains.\r\n\r\nWhen using the resource for research purposes, please refer to NHH Norwegian School of Economics."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/116"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Business administration"
-        },
-        {
-            "name": "Economics"
-        },
-        {
-            "name": "Termbase"
-        },
-        {
-            "name": "Terminological"
-        },
-        {
-            "name": "Terminology"
-        }
-    ],
-    "title": [
-        "English for business"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/73d32e46-124a-5d3a-b8a1-5212e427658a.json b/oaitestdata/clarin-oai_dc/SET_1/json/73d32e46-124a-5d3a-b8a1-5212e427658a.json
deleted file mode 100644
index 062d0869..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/73d32e46-124a-5d3a-b8a1-5212e427658a.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 718 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1816",
-    "MetadataAccess": [
-        "oai:ota:oucs:1816"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Fielding, Henry, 1707-1754"
-    ],
-    "fulltext": "oai:ota:oucs:1816;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/1816.xml;The history of the adventures of Joseph Andrews and his friend Mr. Abraham Adams / by Henry Fielding;Fielding, Henry, 1707-1754;default: 1976-01-01;text_and_corpus_linguistics;Novels -- Great Britain -- 18th century;eng;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 718 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "73d32e46-124a-5d3a-b8a1-5212e427658a",
-    "oai_identifier": [
-        "oai:ota:oucs:1816"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Novels -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "The history of the adventures of Joseph Andrews and his friend Mr. Abraham Adams / by Henry Fielding"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1816.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/73d74539-1535-51b8-8842-60ee48c708aa.json b/oaitestdata/clarin-oai_dc/SET_1/json/73d74539-1535-51b8-8842-60ee48c708aa.json
deleted file mode 100644
index 26434b65..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/73d74539-1535-51b8-8842-60ee48c708aa.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Katholieke Universiteit Leuven Campus Kortrijk, Universit\u00e9 Lille3"
-    ],
-    "Contributor": [
-        "Paulussen, Hans"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Dutch",
-        "French"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-632",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-632"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-632",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Katholieke Universiteit Leuven Campus Kortrijk, Universit\u00e9 Lille3"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Belgium||France"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-632;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;MEDIATIC;Paulussen, Hans;Databank with video-fragments (Dutch and French), transcribed and translated (LINGUATIC-project);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-632;nld;fra;downloadable_files_count: 0;Belgium||France;Katholieke Universiteit Leuven Campus Kortrijk, Universit\u00e9 Lille3;http://www.kuleuven-kortrijk.be/mediatic",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "73d74539-1535-51b8-8842-60ee48c708aa",
-    "notes": [
-        "Databank with video-fragments (Dutch and French), transcribed and translated (LINGUATIC-project)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-632"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "MEDIATIC"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/73df9a7f-9524-5c75-b01c-0ee5332f96d3.json b/oaitestdata/clarin-oai_dc/SET_1/json/73df9a7f-9524-5c75-b01c-0ee5332f96d3.json
deleted file mode 100644
index d48abed8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/73df9a7f-9524-5c75-b01c-0ee5332f96d3.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Instituto de Engenharia de Sistemas e Computadores"
-    ],
-    "Contributor": [
-        "Trancoso, Isabel"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Portuguese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-394",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-394"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-394",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Instituto de Engenharia de Sistemas e Computadores"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Portugal"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-394;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;CORAL;Trancoso, Isabel;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-394;por;downloadable_files_count: 0;Portugal;Instituto de Engenharia de Sistemas e Computadores;http://speech.inesc.pt/projects/coral/coral_pt.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "73df9a7f-9524-5c75-b01c-0ee5332f96d3",
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-394"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "CORAL"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/73e80d56-2951-58a5-a4f7-6a3cbdb3cfd8.json b/oaitestdata/clarin-oai_dc/SET_1/json/73e80d56-2951-58a5-a4f7-6a3cbdb3cfd8.json
deleted file mode 100644
index 7059ede1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/73e80d56-2951-58a5-a4f7-6a3cbdb3cfd8.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Karolina Gruszka"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/vnd.oasis.opendocument.text",
-        "downloadable_files_count: 10",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/486",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/486"
-    ],
-    "PID": "http://hdl.handle.net/11321/486",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Karolina Gruszka"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Super Cool License",
-        "http://www.google.com",
-        "ACA"
-    ],
-    "author": [
-        "Gruszka, Karolina"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/486;2018-06-19T11:18:11Z;hdl_11321_3;hdl_11321_4;Literatura warsztatowa;Gruszka, Karolina;warsztaty;j\u0119zyk polski;Uniwersytet Wroc\u0142awski;Korpus powsta\u0142y na potrzeby warsztat\u00f3w Clarin-Pl;2018;corpus;http://hdl.handle.net/11321/486;pol;Super Cool License;http://www.google.com;ACA;text/plain; charset=utf-8;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;text/plain;text/plain;text/plain;downloadable_files_count: 10;Karolina Gruszka",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "73e80d56-2951-58a5-a4f7-6a3cbdb3cfd8",
-    "notes": [
-        "Korpus powsta\u0142y na potrzeby warsztat\u00f3w Clarin-Pl"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/486"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "warsztaty"
-        },
-        {
-            "name": "warsztaty"
-        },
-        {
-            "name": "warsztaty"
-        }
-    ],
-    "title": [
-        "Literatura warsztatowa"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/741f0c4d-e56e-5337-986f-e695fa052e6b.json b/oaitestdata/clarin-oai_dc/SET_1/json/741f0c4d-e56e-5337-986f-e695fa052e6b.json
deleted file mode 100644
index 7d67f0d1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/741f0c4d-e56e-5337-986f-e695fa052e6b.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "Contributor": [
-        "Auer, Eric",
-        "Klassmann, Alex",
-        "Russel, Albert"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-324",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-324"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-324",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-324;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Trova;Auer, Eric;Klassmann, Alex;Russel, Albert;search engine;corpus search;Trova is a search engine for annotation content archived at The Language Archive. Searchable formats include ELAN EAF, Childes CHAT, Toolbox, PDF, SubRip, Praat TextGrid and others.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-324;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://tla.mpi.nl/tools/tla-tools/trova/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "741f0c4d-e56e-5337-986f-e695fa052e6b",
-    "notes": [
-        "Trova is a search engine for annotation content archived at The Language Archive. Searchable formats include ELAN EAF, Childes CHAT, Toolbox, PDF, SubRip, Praat TextGrid and others."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-324"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "search engine"
-        },
-        {
-            "name": "corpus search"
-        }
-    ],
-    "title": [
-        "Trova"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/745b1907-7e1d-5d65-b1d0-b734c789a5c7.json b/oaitestdata/clarin-oai_dc/SET_1/json/745b1907-7e1d-5d65-b1d0-b734c789a5c7.json
deleted file mode 100644
index 9690e427..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/745b1907-7e1d-5d65-b1d0-b734c789a5c7.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "University of Helsinki"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-747",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-747"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-747",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Helsinki"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-747;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Helsinki Corpus of English Texts (HC);A balanced multi-genre corpus of English texts between the years c. 730-1710.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-747;eng;text/plain;downloadable_files_count: 0;University of Helsinki;http://ota.oucs.ox.ac.uk/headers/1477.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "745b1907-7e1d-5d65-b1d0-b734c789a5c7",
-    "notes": [
-        "A balanced multi-genre corpus of English texts between the years c. 730-1710."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-747"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Helsinki Corpus of English Texts (HC)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/746ffd20-ff84-5223-a036-da3ddf81beca.json b/oaitestdata/clarin-oai_dc/SET_1/json/746ffd20-ff84-5223-a036-da3ddf81beca.json
deleted file mode 100644
index be73945d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/746ffd20-ff84-5223-a036-da3ddf81beca.json
+++ /dev/null
@@ -1,97 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 3",
-        "application/pdf",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Serbian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1096",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1096"
-    ],
-    "PID": "http://hdl.handle.net/11356/1096",
-    "PublicationTimestamp": "2017-04-04T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11356/1120"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "Erjavec, Toma\u017e",
-        "Farka\u0161, Da\u0161a",
-        "Mili\u010devi\u0107, Maja",
-        "Ljube\u0161i\u0107, Nikola",
-        "Klubi\u010dka, Filip",
-        "Vukovi\u0107, Teodora"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1096;2018-10-18T22:26:53Z;hdl_11356_1023;hdl_11356_1024;Serbian Twitter training corpus ReLDI-NormTag-sr 1.0;Ljube\u0161i\u0107, Nikola;Farka\u0161, Da\u0161a;Klubi\u010dka, Filip;Erjavec, Toma\u017e;Mili\u010devi\u0107, Maja;Vukovi\u0107, Teodora;computer-mediated communication;tokenisation;word normalisation;tagging;lemmatisation;manual annotation;TEI;ReLDI-NormTag-sr 1.0 is a manually annotated corpus of Serbian tweets. It is meant as a gold-standard training and testing dataset for tokenisation, sentence segmentation, word normalisation, morphosyntactic tagging and lemmatisation of non-standard Serbian. Each tweet is also annotated for its automatically assigned standardness levels (T = technical standardness, L = linguistic standardness). \r\n\r\nThe corpus construction is (partially) described in: \r\nMILI\u010cEVI\u0106, Maja, LJUBE\u0160I\u0106, Nikola. Tviterasi, tvitera\u0161i or twittera\u0161i? Producing and analysing a normalised dataset of Croatian and Serbian tweets. Sloven\u0161\u010dina 2.0: empirical, applied and interdisciplinary research, 4/2, 2016. ISSN 2335-2736. http://dx.doi.org/10.4312/slo2.0.2016.2.156-188;2017-04-04;corpus;http://hdl.handle.net/11356/1096;srp;http://hdl.handle.net/11356/1120;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;https://creativecommons.org/licenses/by/4.0/;application/zip;application/zip;application/pdf;text/plain; charset=utf-8;downloadable_files_count: 3;Jo\u017eef Stefan Institute;https://reldi.spur.uzh.ch/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "746ffd20-ff84-5223-a036-da3ddf81beca",
-    "notes": [
-        "ReLDI-NormTag-sr 1.0 is a manually annotated corpus of Serbian tweets. It is meant as a gold-standard training and testing dataset for tokenisation, sentence segmentation, word normalisation, morphosyntactic tagging and lemmatisation of non-standard Serbian. Each tweet is also annotated for its automatically assigned standardness levels (T = technical standardness, L = linguistic standardness). \r\n\r\nThe corpus construction is (partially) described in: \r\nMILI\u010cEVI\u0106, Maja, LJUBE\u0160I\u0106, Nikola. Tviterasi, tvitera\u0161i or twittera\u0161i? Producing and analysing a normalised dataset of Croatian and Serbian tweets. Sloven\u0161\u010dina 2.0: empirical, applied and interdisciplinary research, 4/2, 2016. ISSN 2335-2736. http://dx.doi.org/10.4312/slo2.0.2016.2.156-188"
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1096"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "computer-mediated communication"
-        },
-        {
-            "name": "tokenisation"
-        },
-        {
-            "name": "word normalisation"
-        },
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "lemmatisation"
-        },
-        {
-            "name": "manual annotation"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "Serbian Twitter training corpus ReLDI-NormTag-sr 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7477524d-a9d2-5c1b-ad73-b882d9de9566.json b/oaitestdata/clarin-oai_dc/SET_1/json/7477524d-a9d2-5c1b-ad73-b882d9de9566.json
deleted file mode 100644
index 5515f87c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7477524d-a9d2-5c1b-ad73-b882d9de9566.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "University of St. Andrews"
-    ],
-    "Contributor": [
-        "Nederhof, Mark-Jan"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-284",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-284"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-284",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of St. Andrews"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-284;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;PhilologEg;Nederhof, Mark-Jan;a tool for representing and exchanging electronic resources on texts in the Ancient Egyptian language.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-284;downloadable_files_count: 0;United Kingdom;University of St. Andrews;http://www.cs.st-andrews.ac.uk/~mjn/egyptian/align/index.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7477524d-a9d2-5c1b-ad73-b882d9de9566",
-    "notes": [
-        "a tool for representing and exchanging electronic resources on texts in the Ancient Egyptian language."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-284"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "PhilologEg"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/747983a3-f2fa-5292-abbe-7b2a9fbf6c91.json b/oaitestdata/clarin-oai_dc/SET_1/json/747983a3-f2fa-5292-abbe-7b2a9fbf6c91.json
deleted file mode 100644
index c4092a13..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/747983a3-f2fa-5292-abbe-7b2a9fbf6c91.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 524 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1902",
-    "MetadataAccess": [
-        "oai:ota:oucs:1902"
-    ],
-    "PublicationTimestamp": "1905-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1905"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Orczy, Emmuska Orczy, Baroness, 1865-1947"
-    ],
-    "fulltext": "oai:ota:oucs:1902;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/1902.xml;The Scarlet Pimpernel / by Baroness Orczy;Orczy, Emmuska Orczy, Baroness, 1865-1947;1905;text_and_corpus_linguistics;Fiction -- Great Britain -- 20th century;Novels -- Great Britain -- 20th century;eng;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 524 KB);Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "747983a3-f2fa-5292-abbe-7b2a9fbf6c91",
-    "oai_identifier": [
-        "oai:ota:oucs:1902"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- Great Britain -- th century"
-        },
-        {
-            "name": "Novels -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "The Scarlet Pimpernel / by Baroness Orczy"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1902.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/747dd598-c60d-55a6-9ab7-197f96a05812.json b/oaitestdata/clarin-oai_dc/SET_1/json/747dd598-c60d-55a6-9ab7-197f96a05812.json
deleted file mode 100644
index d1894022..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/747dd598-c60d-55a6-9ab7-197f96a05812.json
+++ /dev/null
@@ -1,92 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "English",
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2823",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2823"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2823",
-    "PublicationTimestamp": "2018-06-07T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Haji\u010dov\u00e1, Eva",
-        "Haji\u010d, Jan",
-        "Ure\u0161ov\u00e1, Zde\u0148ka",
-        "Fu\u010d\u00edkov\u00e1, Eva"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2823;2018-07-02T22:05:54Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;CzEngClass 0.1;Ure\u0161ov\u00e1, Zde\u0148ka;Fu\u010d\u00edkov\u00e1, Eva;Haji\u010dov\u00e1, Eva;Haji\u010d, Jan;verbal valency;predicate argument structure;semantic roles;bilingual corpus annotation;translational equivalence;comparative syntax;comparative semantics;The CzEngClass synonym verb lexicon is a result of a project investigating semantic \u2018equivalence\u2019 of verb senses and their valency behavior in parallel Czech-English language resources, i.e., relating verb meanings with respect to contextually-based verb synonymy. The lexicon entries are linked to PDT-Vallex (http://hdl.handle.net/11858/00-097C-0000-0023-4338-F), EngVallex (http://hdl.handle.net/11858/00-097C-0000-0023-4337-2), CzEngVallex (http://hdl.handle.net/11234/1-1512), FrameNet (https://framenet.icsi.berkeley.edu/fndrupal/), VerbNet (http://verbs.colorado.edu/verbnet/index.html), PropBank (http://verbs.colorado.edu/%7Empalmer/projects/ace.html),  Ontonotes (http://verbs.colorado.edu/html_groupings/), and Czech (http://hdl.handle.net/11858/00-097C-0000-0001-4880-3) and English Wordnets (https://wordnet.princeton.edu/). Part of the dataset is a file reflecting annotators choices for assignment of verbs to classes.;2018-06-07;lexicalConceptualResource;http://hdl.handle.net/11234/1-2823;eng;ces;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/czengclass",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "747dd598-c60d-55a6-9ab7-197f96a05812",
-    "notes": [
-        "The CzEngClass synonym verb lexicon is a result of a project investigating semantic \u2018equivalence\u2019 of verb senses and their valency behavior in parallel Czech-English language resources, i.e., relating verb meanings with respect to contextually-based verb synonymy. The lexicon entries are linked to PDT-Vallex (http://hdl.handle.net/11858/00-097C-0000-0023-4338-F), EngVallex (http://hdl.handle.net/11858/00-097C-0000-0023-4337-2), CzEngVallex (http://hdl.handle.net/11234/1-1512), FrameNet (https://framenet.icsi.berkeley.edu/fndrupal/), VerbNet (http://verbs.colorado.edu/verbnet/index.html), PropBank (http://verbs.colorado.edu/%7Empalmer/projects/ace.html),  Ontonotes (http://verbs.colorado.edu/html_groupings/), and Czech (http://hdl.handle.net/11858/00-097C-0000-0001-4880-3) and English Wordnets (https://wordnet.princeton.edu/). Part of the dataset is a file reflecting annotators choices for assignment of verbs to classes."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2823"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "verbal valency"
-        },
-        {
-            "name": "predicate argument structure"
-        },
-        {
-            "name": "semantic roles"
-        },
-        {
-            "name": "bilingual corpus annotation"
-        },
-        {
-            "name": "translational equivalence"
-        },
-        {
-            "name": "comparative syntax"
-        },
-        {
-            "name": "comparative semantics"
-        }
-    ],
-    "title": [
-        "CzEngClass 0.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/747fb6c8-7877-5ea7-9dd0-d6787f15abff.json b/oaitestdata/clarin-oai_dc/SET_1/json/747fb6c8-7877-5ea7-9dd0-d6787f15abff.json
deleted file mode 100644
index 3e364c75..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/747fb6c8-7877-5ea7-9dd0-d6787f15abff.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1460",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1460"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1460",
-    "PublicationTimestamp": "2013-02-02T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Richter, Michal"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1460;2018-07-02T22:05:53Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Czech Models for Korektor 2;Richter, Michal;Korektor;Czech;spellchecker;spellchecking;diacritical marks generation;The Czech models for Korektor 2 created by Michal Richter, 02 Feb 2013. The models can either perform spellchecking and grammarchecking, or only generate diacritical marks.;2013-02-02;languageDescription;http://hdl.handle.net/11234/1-1460;ces;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/korektor",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "747fb6c8-7877-5ea7-9dd0-d6787f15abff",
-    "notes": [
-        "The Czech models for Korektor 2 created by Michal Richter, 02 Feb 2013. The models can either perform spellchecking and grammarchecking, or only generate diacritical marks."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1460"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Korektor"
-        },
-        {
-            "name": "Czech"
-        },
-        {
-            "name": "spellchecker"
-        },
-        {
-            "name": "spellchecking"
-        },
-        {
-            "name": "diacritical marks generation"
-        }
-    ],
-    "title": [
-        "Czech Models for Korektor 2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/749e8a71-fcd4-59ee-ba57-2e2580afebb9.json b/oaitestdata/clarin-oai_dc/SET_1/json/749e8a71-fcd4-59ee-ba57-2e2580afebb9.json
deleted file mode 100644
index a4117493..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/749e8a71-fcd4-59ee-ba57-2e2580afebb9.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1009",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1009"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1009",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1009;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LAC Italian Corpus;Language and Cognition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1009;ita;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI71393%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "749e8a71-fcd4-59ee-ba57-2e2580afebb9",
-    "notes": [
-        "Language and Cognition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1009"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LAC Italian Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/74a69958-664f-5e32-a10b-8c6d60ac1bf1.json b/oaitestdata/clarin-oai_dc/SET_1/json/74a69958-664f-5e32-a10b-8c6d60ac1bf1.json
deleted file mode 100644
index a6c53ff2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/74a69958-664f-5e32-a10b-8c6d60ac1bf1.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2710",
-    "MetadataAccess": [
-        "oai:ota:oucs:2710"
-    ],
-    "PublicationTimestamp": "1765-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1765"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2710;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2710.xml;Of the education of ladies;Swift, Jonathan, 1667-1745;1765;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "74a69958-664f-5e32-a10b-8c6d60ac1bf1",
-    "oai_identifier": [
-        "oai:ota:oucs:2710"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Of the education of ladies"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2710.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/74ab9f34-8cf4-54ce-8cd7-dadf8387e940.json b/oaitestdata/clarin-oai_dc/SET_1/json/74ab9f34-8cf4-54ce-8cd7-dadf8387e940.json
deleted file mode 100644
index 76f75b18..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/74ab9f34-8cf4-54ce-8cd7-dadf8387e940.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Arts and Humanities Research Board (AHRB)",
-        "Pintzuk, Susan",
-        "Taylor, Ann",
-        "Beths, Frank",
-        "Warner, Anthony"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(295 files : ca. 66.7 MB)"
-    ],
-    "Language": [
-        "Old English (ca. 450-1100)",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2462",
-    "MetadataAccess": [
-        "oai:ota:oucs:2462"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Linguistic corpora"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:2462;2018-11-14T10:39:08Z;http://ota.ox.ac.uk/headers/2462.xml;The York-Toronto-Helsinki Parsed Corpus of Old English prose (YCOE);2003;text_and_corpus_linguistics;English language--Old English, ca. 450-1100;English language--Old English, ca. 450-1100--Texts;Linguistic analysis (Linguistics);Frames (Linguistics);ang;lat;The corpus contains 1.5 million words of Old English prose taken from the Toronto Dictionary of Old English Corpus, with special formatting which makes it possible to search conveniently for syntactic structure using a computer search engine. ;Oxford Text Archive, University of Oxford;Taylor, Ann;Warner, Anthony;Pintzuk, Susan;Beths, Frank;Arts and Humanities Research Board (AHRB);Warner, Anthony;(295 files : ca. 66.7 MB);Text;Linguistic corpora;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "74ab9f34-8cf4-54ce-8cd7-dadf8387e940",
-    "notes": [
-        "The corpus contains 1.5 million words of Old English prose taken from the Toronto Dictionary of Old English Corpus, with special formatting which makes it possible to search conveniently for syntactic structure using a computer search engine. "
-    ],
-    "oai_identifier": [
-        "oai:ota:oucs:2462"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English language--Old English"
-        },
-        {
-            "name": "ca. -"
-        },
-        {
-            "name": "English language--Old English"
-        },
-        {
-            "name": "ca. ---Texts"
-        },
-        {
-            "name": "Linguistic analysis Linguistics"
-        },
-        {
-            "name": "Frames Linguistics"
-        }
-    ],
-    "title": [
-        "The York-Toronto-Helsinki Parsed Corpus of Old English prose (YCOE)"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2462.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/74b62aec-4da2-5a11-9232-4814949bfb3c.json b/oaitestdata/clarin-oai_dc/SET_1/json/74b62aec-4da2-5a11-9232-4814949bfb3c.json
deleted file mode 100644
index d91a6d3a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/74b62aec-4da2-5a11-9232-4814949bfb3c.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "less than 512 KB"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1214",
-    "MetadataAccess": [
-        "oai:ota:oucs:1214"
-    ],
-    "PublicationYear": [
-        "500 BCE-443 BCE"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pindar"
-    ],
-    "fulltext": "oai:ota:oucs:1214;2018-03-05T13:55:23Z;http://ota.ox.ac.uk/headers/1214.xml; Collected works / compiled by Thesaurus Linguae Graecae;Pindar;500 BCE-443 BCE;text_and_corpus_linguistics;Poems -- Greece -- 5th century;grc;Oxford Text Archive, University of Oxford;less than 512 KB;Text;Poems;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "74b62aec-4da2-5a11-9232-4814949bfb3c",
-    "oai_identifier": [
-        "oai:ota:oucs:1214"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- Greece -- th century"
-        }
-    ],
-    "title": [
-        " Collected works / compiled by Thesaurus Linguae Graecae"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1214.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/74c5853b-8f82-52e1-857a-1ce8c1eb747c.json b/oaitestdata/clarin-oai_dc/SET_1/json/74c5853b-8f82-52e1-857a-1ce8c1eb747c.json
deleted file mode 100644
index e7beada7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/74c5853b-8f82-52e1-857a-1ce8c1eb747c.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5172",
-    "MetadataAccess": [
-        "oai:ota:oucs:5172"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hill, Aaron, 1685-1750."
-    ],
-    "fulltext": "oai:ota:oucs:5172;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5172.xml;The Roman revenge: A tragedy. By Aaron Hill, Esq;.;Hill, Aaron, 1685-1750.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "74c5853b-8f82-52e1-857a-1ce8c1eb747c",
-    "oai_identifier": [
-        "oai:ota:oucs:5172"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The Roman revenge: A tragedy. By Aaron Hill, Esq;."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5172.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/75005216-c8b4-515c-88a2-414fc3a134ac.json b/oaitestdata/clarin-oai_dc/SET_1/json/75005216-c8b4-515c-88a2-414fc3a134ac.json
deleted file mode 100644
index 3a0b3f3f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/75005216-c8b4-515c-88a2-414fc3a134ac.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish",
-        "Slovak"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/70",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/70"
-    ],
-    "PID": "http://hdl.handle.net/10794/70",
-    "PublicationTimestamp": "2015-04-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/70;2017-10-31T15:40:18Z;hdl_10794_1;hdl_10794_2;ASPAC \u2013 Swedish-Slovak (2017-10-16);ASPAC \u2013 svenska-slovakiska (2017-10-16);n/a, n/a;ASPAC;Parallel;Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.;Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat.;2015-04-16;corpus;http://hdl.handle.net/10794/70;swe;slk;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/octet-stream;application/gzip;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/aspacsvsk",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "75005216-c8b4-515c-88a2-414fc3a134ac",
-    "notes": [
-        "Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.",
-        "Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/70"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ASPAC"
-        },
-        {
-            "name": "Parallel"
-        }
-    ],
-    "title": [
-        "ASPAC \u2013 Swedish-Slovak (2017-10-16)",
-        "ASPAC \u2013 svenska-slovakiska (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/750ba430-0bbd-5f17-9365-977ce555dca0.json b/oaitestdata/clarin-oai_dc/SET_1/json/750ba430-0bbd-5f17-9365-977ce555dca0.json
deleted file mode 100644
index 0370a2a1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/750ba430-0bbd-5f17-9365-977ce555dca0.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "NLX-Natural Language and Speech Group, University of Lisbon"
-    ],
-    "Contributor": [
-        "Branco, Ant\u00f3nio",
-        "Costa, Francisco"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Portuguese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1231",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1231"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1231",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "NLX-Natural Language and Speech Group, University of Lisbon"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Portugal"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1231;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LXGram;Branco, Ant\u00f3nio;Costa, Francisco;LXGram is a grammar for the computational processing of Portuguese. It is being developed under the following major design features: * precision: it is a precision grammar delivering accurate, linguistically grounded information of natural language sentences * deep processing: it is a grammar for deep linguistic processing in as much as besides information on the major syntactic dimensions of grammatical constituency and dependency, it delivers (and generates from) fully-fledged logical representation of the meaning of natural language sentences * large-scale: it is planned not to leave out any sort of regular grammatical construction or phenomena. * multi-purpose: it is intended to make available as much linguistic information as it can possible be made explicit by automatic means, given the current state of the art in language technology, with the goal of offering itself to support the largest possible range of language technology applications.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1231;por;downloadable_files_count: 0;Portugal;NLX-Natural Language and Speech Group, University of Lisbon;http://nlxgroup.di.fc.ul.pt/lxgram/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "750ba430-0bbd-5f17-9365-977ce555dca0",
-    "notes": [
-        "LXGram is a grammar for the computational processing of Portuguese. It is being developed under the following major design features: * precision: it is a precision grammar delivering accurate, linguistically grounded information of natural language sentences * deep processing: it is a grammar for deep linguistic processing in as much as besides information on the major syntactic dimensions of grammatical constituency and dependency, it delivers (and generates from) fully-fledged logical representation of the meaning of natural language sentences * large-scale: it is planned not to leave out any sort of regular grammatical construction or phenomena. * multi-purpose: it is intended to make available as much linguistic information as it can possible be made explicit by automatic means, given the current state of the art in language technology, with the goal of offering itself to support the largest possible range of language technology applications."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1231"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LXGram"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7521aa2e-15a6-5f1a-824a-3f242c52ea7f.json b/oaitestdata/clarin-oai_dc/SET_1/json/7521aa2e-15a6-5f1a-824a-3f242c52ea7f.json
deleted file mode 100644
index 3f9fae45..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7521aa2e-15a6-5f1a-824a-3f242c52ea7f.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "275 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1872",
-    "MetadataAccess": [
-        "oai:ota:oucs:1872"
-    ],
-    "PublicationTimestamp": "1897-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1897"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Wells, H.G."
-    ],
-    "fulltext": "oai:ota:oucs:1872;2018-04-11T16:03:39Z;http://ota.ox.ac.uk/headers/1872.xml;The invisible man;Wells, H.G.;1897;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;275 KB;Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7521aa2e-15a6-5f1a-824a-3f242c52ea7f",
-    "oai_identifier": [
-        "oai:ota:oucs:1872"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The invisible man"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1872.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/75320f19-a936-56f0-be24-8c4406a511fd.json b/oaitestdata/clarin-oai_dc/SET_1/json/75320f19-a936-56f0-be24-8c4406a511fd.json
deleted file mode 100644
index 6eec4eac..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/75320f19-a936-56f0-be24-8c4406a511fd.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "LOGOS"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-572",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-572"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-572",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "LOGOS"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Italy"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-572;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Logos : multilingual e-translation portal;Searchable multilingual text collection (700+ mwd) and a dictionary database of 251 languages and dialects. The Dictionary (ca. 8 mwd) provides translation of a word, definition, grammar, synonym, antonym, image, pronunciation, etc.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-572;downloadable_files_count: 0;Italy;LOGOS;http://www.logos.it/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "75320f19-a936-56f0-be24-8c4406a511fd",
-    "notes": [
-        "Searchable multilingual text collection (700+ mwd) and a dictionary database of 251 languages and dialects. The Dictionary (ca. 8 mwd) provides translation of a word, definition, grammar, synonym, antonym, image, pronunciation, etc."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-572"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Logos : multilingual e-translation portal"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7538cee6-327b-5aca-b863-2db83d977a64.json b/oaitestdata/clarin-oai_dc/SET_1/json/7538cee6-327b-5aca-b863-2db83d977a64.json
deleted file mode 100644
index 5b8fac41..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7538cee6-327b-5aca-b863-2db83d977a64.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Prymasowska"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229188",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229188"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D07-D",
-    "PublicationTimestamp": "1790-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1790"
-    ],
-    "Publisher": [
-        "Drukarnia Prymasowska"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/229188",
-        "oai:jbc.bj.uj.edu.pl:publication:240828"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1701/1800"
-    ],
-    "TempCoverageBegin": 53662478399,
-    "TempCoverageEnd": 53662478399,
-    "TemporalCoverage": " point in time : 1701-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1701-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1701-07-01T11:59:59Z",
-    "author": [
-        "Perzyna, Ludwik (1742-1800)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229188;2019-03-01T12:58:36Z;Nauka Po\u0142o\u017cna Krotko Zebrana Cyrulikom po\u0142o\u017cnym, iako te\u017c i Babom, czyli Kobietom przy rozwi\u0105zaniu rodz\u0105cych Po\u0142o\u017cnic s\u0142u\u017c\u0105cym dla wiadomo\u015bci bardzo potrzebna : Na pytania i odpowiedzi roz\u0142o\u017cona [...];Perzyna, Ludwik (1742-1800);starodruki 18\u00a0w.;Drukarnia Prymasowska;1790;starodruk;application/xml;clarind-uds:poldilemma-229188;hdl:11858/00-246C-0000-0023-8D07-D;Biblioteka Jagiello\u0144ska, BJ St. Dr. 375986 I;pol;http://jbc.bj.uj.edu.pl/Content/229188;oai:jbc.bj.uj.edu.pl:publication:240828;1701/1800;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7538cee6-327b-5aca-b863-2db83d977a64",
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229188"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Nauka Po\u0142o\u017cna Krotko Zebrana Cyrulikom po\u0142o\u017cnym, iako te\u017c i Babom, czyli Kobietom przy rozwi\u0105zaniu rodz\u0105cych Po\u0142o\u017cnic s\u0142u\u017c\u0105cym dla wiadomo\u015bci bardzo potrzebna : Na pytania i odpowiedzi roz\u0142o\u017cona [...]"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7553e77d-6747-5a94-a93e-42761b229f05.json b/oaitestdata/clarin-oai_dc/SET_1/json/7553e77d-6747-5a94-a93e-42761b229f05.json
deleted file mode 100644
index ee2bfaa2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7553e77d-6747-5a94-a93e-42761b229f05.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "Sanskrit"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-907",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-907"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-907",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-907;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Buddhist Sanskrit;ca. 200.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-907;san;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#buskt",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7553e77d-6747-5a94-a93e-42761b229f05",
-    "notes": [
-        "ca. 200.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-907"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Buddhist Sanskrit"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/75623562-b778-5c9a-be59-6c95836619cd.json b/oaitestdata/clarin-oai_dc/SET_1/json/75623562-b778-5c9a-be59-6c95836619cd.json
deleted file mode 100644
index 8f89d04b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/75623562-b778-5c9a-be59-6c95836619cd.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=63649c5218f311e6a2aa782bcb074135d2f0147396bf431691513c6c0db2adea",
-    "MetadataAccess": [
-        "63649c5218f311e6a2aa782bcb074135d2f0147396bf431691513c6c0db2adea"
-    ],
-    "PublicationTimestamp": "2016-05-13T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "fulltext": "63649c5218f311e6a2aa782bcb074135d2f0147396bf431691513c6c0db2adea;2018-11-15T16:40:20Z;corpus;corpus:text;Europarl-QTLeap WSD/NED corpus;The texts are sentences from the Europarl parallel corpus (Koehn, 2005). The textscontain the monolingual sentences from parallel corpora for the following\npairs: Bulgarian-English, Czech-English, Portuguese-English and Spanish-\nEnglish. The English corpus is comprised by the English side of the Spanish-\nEnglish corpus.\nBasque is not in Europarl. In addition, it contains the Basque and English\nsides of the GNOME corpus (Tiedemann, 2012).\nThe texts have been automatically annotated with NLP tools, including Word\nSense Disambiguation, Named Entity Disambiguation and Coreference\nresolution.;2016-05-13",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "75623562-b778-5c9a-be59-6c95836619cd",
-    "notes": [
-        "The texts are sentences from the Europarl parallel corpus (Koehn, 2005). The textscontain the monolingual sentences from parallel corpora for the following\npairs: Bulgarian-English, Czech-English, Portuguese-English and Spanish-\nEnglish. The English corpus is comprised by the English side of the Spanish-\nEnglish corpus.\nBasque is not in Europarl. In addition, it contains the Basque and English\nsides of the GNOME corpus (Tiedemann, 2012).\nThe texts have been automatically annotated with NLP tools, including Word\nSense Disambiguation, Named Entity Disambiguation and Coreference\nresolution."
-    ],
-    "oai_identifier": [
-        "63649c5218f311e6a2aa782bcb074135d2f0147396bf431691513c6c0db2adea"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "Europarl-QTLeap WSD/NED corpus"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7567ca17-4b74-5a82-b76b-bbfc43ce2fb2.json b/oaitestdata/clarin-oai_dc/SET_1/json/7567ca17-4b74-5a82-b76b-bbfc43ce2fb2.json
deleted file mode 100644
index 95440fc7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7567ca17-4b74-5a82-b76b-bbfc43ce2fb2.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Department of Information Technology, Gauhati University, Assam, India"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Assamese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/614",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/614"
-    ],
-    "PID": "http://hdl.handle.net/11321/614",
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Department of Information Technology, Gauhati University, Assam, India"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "author": [
-        "Sarma, Prof. Shikhar Kr."
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/614;2019-01-08T10:44:48Z;hdl_11321_3;hdl_11321_610;Assamese Stopwords;Sarma, Prof. Shikhar Kr.;Assamese NLP;Assamese stopwords;Assamese noise words;Gauhati University;The most frequently occurring words in a context are the stopwords. They do not play an important role in retrieving information. As Stopwords do not contribute any important information towards the context and so they should be removed before processing. These words have very low discrimination value and are sometimes referred to as noise words. Assamese stopword list is created which contains 264 words. Examples are: \u09af\u09c7\u09a4\u09bf\u09df\u09be, \u09af\u09c7\u09a8, \u09af\u09c7\u09a8\u09bf\u09ac\u09be, \u09af\u09c7\u09a8\u09c7, \u09af\u09cb\u0997\u09c7, \u09b2\u0997, \u09b2\u09c8 etc.\r\n\r\n---\r\n\r\n1. These Assamese NLP resources including the Tools and Applications are developed\r\nduring Research and Development Projects as well as Masters and Ph.D. thesis\r\nworks.\r\n2. These are mainly developed or generated at Gauhati University Department of\r\nComputer Science and Department of Information Technology.\r\n3. These resources are used by students and researchers for further studies, researches, as\r\nwell as for design and development of tools and applications.\r\n4. Computational Linguistics in Assamese is not rich, and Natural Language Processing\r\nworks have mainly started during last two decades, and most of the resources are first\r\ngeneration resources, and with ample scope for upgrading, enriching, and purifying.\r\n5. These are very good and essential resources for all the researchers in Assamese NLP, as\r\nthe language requires more and more NLP works to make Assamese a rich media for\r\nthe digital world.\r\n6. Anyone interested, or in need of such resources may express their interest for the\r\nrequired resources, and the way of availability will be advised/informed accordingly.\r\n7. These are purely research materials and could only be used for further research only.\r\n8. Researchers may visit the NLP Lab of Department of Information Technology, Gauhati\r\nUniversity, Guwahati, India or contact us.\r\n9. Researchers interested in collaborative works, and also students for project works, are\r\nwelcome.\r\n10. Contact person is Professor Shikhar Kr. Sarma, Department of Information\r\nTechnology, Gauhati University, Guwahati 781014, Assam, India. Email-\r\nsks@gauhati.ac.in;2019-01-08;lexicalConceptualResource;http://hdl.handle.net/11321/614;asm;downloadable_files_count: 0;Department of Information Technology, Gauhati University, Assam, India",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7567ca17-4b74-5a82-b76b-bbfc43ce2fb2",
-    "notes": [
-        "The most frequently occurring words in a context are the stopwords. They do not play an important role in retrieving information. As Stopwords do not contribute any important information towards the context and so they should be removed before processing. These words have very low discrimination value and are sometimes referred to as noise words. Assamese stopword list is created which contains 264 words. Examples are: \u09af\u09c7\u09a4\u09bf\u09df\u09be, \u09af\u09c7\u09a8, \u09af\u09c7\u09a8\u09bf\u09ac\u09be, \u09af\u09c7\u09a8\u09c7, \u09af\u09cb\u0997\u09c7, \u09b2\u0997, \u09b2\u09c8 etc.\r\n\r\n---\r\n\r\n1. These Assamese NLP resources including the Tools and Applications are developed\r\nduring Research and Development Projects as well as Masters and Ph.D. thesis\r\nworks.\r\n2. These are mainly developed or generated at Gauhati University Department of\r\nComputer Science and Department of Information Technology.\r\n3. These resources are used by students and researchers for further studies, researches, as\r\nwell as for design and development of tools and applications.\r\n4. Computational Linguistics in Assamese is not rich, and Natural Language Processing\r\nworks have mainly started during last two decades, and most of the resources are first\r\ngeneration resources, and with ample scope for upgrading, enriching, and purifying.\r\n5. These are very good and essential resources for all the researchers in Assamese NLP, as\r\nthe language requires more and more NLP works to make Assamese a rich media for\r\nthe digital world.\r\n6. Anyone interested, or in need of such resources may express their interest for the\r\nrequired resources, and the way of availability will be advised/informed accordingly.\r\n7. These are purely research materials and could only be used for further research only.\r\n8. Researchers may visit the NLP Lab of Department of Information Technology, Gauhati\r\nUniversity, Guwahati, India or contact us.\r\n9. Researchers interested in collaborative works, and also students for project works, are\r\nwelcome.\r\n10. Contact person is Professor Shikhar Kr. Sarma, Department of Information\r\nTechnology, Gauhati University, Guwahati 781014, Assam, India. Email-\r\nsks@gauhati.ac.in"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/614"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_610"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Assamese NLP"
-        },
-        {
-            "name": "Assamese stopwords"
-        },
-        {
-            "name": "Assamese noise words"
-        },
-        {
-            "name": "Gauhati University"
-        }
-    ],
-    "title": [
-        "Assamese Stopwords"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7593c395-ca18-5ac5-8b30-b751a94352b8.json b/oaitestdata/clarin-oai_dc/SET_1/json/7593c395-ca18-5ac5-8b30-b751a94352b8.json
deleted file mode 100644
index 4433fc9f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7593c395-ca18-5ac5-8b30-b751a94352b8.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Inuktitut"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-995",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-995"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-995",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-995;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LAC Inuktitut Corpus;Language and Cognition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-995;iku;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI30369%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7593c395-ca18-5ac5-8b30-b751a94352b8",
-    "notes": [
-        "Language and Cognition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-995"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LAC Inuktitut Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7597777a-2d85-592f-8cc6-ca422e4cf400.json b/oaitestdata/clarin-oai_dc/SET_1/json/7597777a-2d85-592f-8cc6-ca422e4cf400.json
deleted file mode 100644
index 7d36a52d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7597777a-2d85-592f-8cc6-ca422e4cf400.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "IPIPAN"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "downloadable_files_count: 10",
-        "application/vnd.oasis.opendocument.text",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/393",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/393"
-    ],
-    "PID": "http://hdl.handle.net/11321/393",
-    "PublicationTimestamp": "2017-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "IPIPAN"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Wawrzyniak-\u015aliwska, Magdalena"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/393;2017-05-30T11:55:08Z;hdl_11321_3;hdl_11321_4;texts1;Wawrzyniak-\u015aliwska, Magdalena;text;a collection of texts;2017-05-30;corpus;http://hdl.handle.net/11321/393;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;text/plain;application/vnd.oasis.opendocument.text;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;application/vnd.oasis.opendocument.text;downloadable_files_count: 10;IPIPAN",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7597777a-2d85-592f-8cc6-ca422e4cf400",
-    "notes": [
-        "a collection of texts"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/393"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "text"
-        }
-    ],
-    "title": [
-        "texts1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7598bbd9-1467-561e-b94f-aa3573d2320b.json b/oaitestdata/clarin-oai_dc/SET_1/json/7598bbd9-1467-561e-b94f-aa3573d2320b.json
deleted file mode 100644
index 0160c4d9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7598bbd9-1467-561e-b94f-aa3573d2320b.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Computer and Information Science, University of Ljubljana",
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1186",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1186"
-    ],
-    "PID": "http://hdl.handle.net/11356/1186",
-    "PublicationTimestamp": "2018-05-08T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Faculty of Computer and Information Science, University of Ljubljana",
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "RelatedIdentifier": [
-        "http://videolectures.net/jota_krsnik_napovedovanje_naglasa/",
-        "https://repozitorij.uni-lj.si/IzpisGradiva.php?id=98276",
-        "http://hdl.handle.net/11356/1156"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u0160ef, Toma\u017e",
-        "Krsnik, Luka",
-        "Krek, Simon",
-        "Robnik-\u0160ikonja, Marko"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1186;2018-05-08T02:04:57Z;hdl_11356_1023;hdl_11356_1024;Automatically stress labelled morphological lexicon Sloleks 1.2,  version 1.1;Krsnik, Luka;Robnik-\u0160ikonja, Marko;\u0160ef, Toma\u017e;Krek, Simon;word stress;This lexicon is an extended version of Sloleks 1.2, http://hdl.handle.net/11356/1039. It contains all the original data from Sloleks with added information about the stress of each word form, which is included in two ways: information about stress location only, and information about stress location and type. Stress assignment was performed automatically, with algorithms based on deep neural networks which correctly predicted accent location in 91.5% and combined accent type and location in 88.5% of test data. Therefore not all accents are correct. \r\nThis updated 1.1 version of the lexicon contains stress asignments with an improved algorithm, which reduces the error by about 1% against the previous 1.0 version.;2018-05-08;lexicalConceptualResource;http://hdl.handle.net/11356/1186;slv;http://videolectures.net/jota_krsnik_napovedovanje_naglasa/;https://repozitorij.uni-lj.si/IzpisGradiva.php?id=98276;http://hdl.handle.net/11356/1156;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);https://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 2;Faculty of Computer and Information Science, University of Ljubljana;Centre for Language Resources and Technologies, University of Ljubljana;https://gitea.cjvt.si/lkrsnik/stress_asignment",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7598bbd9-1467-561e-b94f-aa3573d2320b",
-    "notes": [
-        "This lexicon is an extended version of Sloleks 1.2, http://hdl.handle.net/11356/1039. It contains all the original data from Sloleks with added information about the stress of each word form, which is included in two ways: information about stress location only, and information about stress location and type. Stress assignment was performed automatically, with algorithms based on deep neural networks which correctly predicted accent location in 91.5% and combined accent type and location in 88.5% of test data. Therefore not all accents are correct. \r\nThis updated 1.1 version of the lexicon contains stress asignments with an improved algorithm, which reduces the error by about 1% against the previous 1.0 version."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1186"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "word stress"
-        }
-    ],
-    "title": [
-        "Automatically stress labelled morphological lexicon Sloleks 1.2,  version 1.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/759dcf22-35cd-5749-86c1-a80416ae3e48.json b/oaitestdata/clarin-oai_dc/SET_1/json/759dcf22-35cd-5749-86c1-a80416ae3e48.json
deleted file mode 100644
index a1ad1bc0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/759dcf22-35cd-5749-86c1-a80416ae3e48.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Institute of Mathematics and Computer Science, University of Latvia"
-    ],
-    "Contributor": [
-        "B\u0113rzi\u0146a-Reinsone, Sanita"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Latvian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-713",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-713"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-713",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institute of Mathematics and Computer Science, University of Latvia"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Latvia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-713;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;E-Library of Early Latvian Folkloristics;B\u0113rzi\u0146a-Reinsone, Sanita;E-library of early Latvian folkloristics, contain articles about Latvian folklore and its research dated back to period until 1920. > 200 articles.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-713;lav;downloadable_files_count: 0;Latvia;Institute of Mathematics and Computer Science, University of Latvia;http://www.korpuss.lv/feb/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "759dcf22-35cd-5749-86c1-a80416ae3e48",
-    "notes": [
-        "E-library of early Latvian folkloristics, contain articles about Latvian folklore and its research dated back to period until 1920. > 200 articles."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-713"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "E-Library of Early Latvian Folkloristics"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/75e293e1-161d-598a-b4d8-01ffefef4a47.json b/oaitestdata/clarin-oai_dc/SET_1/json/75e293e1-161d-598a-b4d8-01ffefef4a47.json
deleted file mode 100644
index 1e71a252..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/75e293e1-161d-598a-b4d8-01ffefef4a47.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 458 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0651",
-    "MetadataAccess": [
-        "oai:ota:oucs:0651"
-    ],
-    "PublicationTimestamp": "1621-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1621"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Du Bartas, Guillaume de Salluste, seigneur, 1544-1590"
-    ],
-    "fulltext": "oai:ota:oucs:0651;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0651.xml;Sepmaine. Selections. English ;The divine weeks and works of Guillaume de Saluste, Sieur du Bartas : the third and fourth days of the second week;Du Bartas, Guillaume de Salluste, seigneur, 1544-1590;1621;text_and_corpus_linguistics;Poems;Epics;Translations -- England -- 17th century;eng;Oxford Text Archive, University of Oxford;(1 file : ca. 458 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "75e293e1-161d-598a-b4d8-01ffefef4a47",
-    "oai_identifier": [
-        "oai:ota:oucs:0651"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems"
-        },
-        {
-            "name": "Epics"
-        },
-        {
-            "name": "Translations -- England -- th century"
-        }
-    ],
-    "title": [
-        "Sepmaine. Selections. English ",
-        "The divine weeks and works of Guillaume de Saluste, Sieur du Bartas : the third and fourth days of the second week"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0651.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/75ecf6a2-a2a7-5880-98f2-af15a7c4bd08.json b/oaitestdata/clarin-oai_dc/SET_1/json/75ecf6a2-a2a7-5880-98f2-af15a7c4bd08.json
deleted file mode 100644
index d90e0ee3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/75ecf6a2-a2a7-5880-98f2-af15a7c4bd08.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "IPI PAN"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/vnd.oasis.opendocument.text",
-        "downloadable_files_count: 10",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/392",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/392"
-    ],
-    "PID": "http://hdl.handle.net/11321/392",
-    "PublicationTimestamp": "2017-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "IPI PAN"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Bia\u0142ek, Mariola"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/392;2017-05-30T11:55:06Z;hdl_11321_3;hdl_11321_4;Korpus tekst\u00f3w dowolnych;Bia\u0142ek, Mariola;opowiadania;fragmenty;dramaty;utwory dla dzieci;opowiadania i inne materia\u0142y j\u0119zykowe;2017-05-30;corpus;http://hdl.handle.net/11321/392;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;application/vnd.oasis.opendocument.text;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;application/vnd.oasis.opendocument.text;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;downloadable_files_count: 10;IPI PAN",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "75ecf6a2-a2a7-5880-98f2-af15a7c4bd08",
-    "notes": [
-        "opowiadania i inne materia\u0142y j\u0119zykowe"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/392"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "opowiadania"
-        },
-        {
-            "name": "fragmenty"
-        },
-        {
-            "name": "dramaty"
-        },
-        {
-            "name": "utwory dla dzieci"
-        }
-    ],
-    "title": [
-        "Korpus tekst\u00f3w dowolnych"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7613e9f9-d62e-5784-9880-0e2efc502cb1.json b/oaitestdata/clarin-oai_dc/SET_1/json/7613e9f9-d62e-5784-9880-0e2efc502cb1.json
deleted file mode 100644
index 9d14f34d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7613e9f9-d62e-5784-9880-0e2efc502cb1.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=97afe362bc8c11e1a404080027e73ea2f06e1efdb7704ba6a6382afe4ae3e127",
-    "MetadataAccess": [
-        "97afe362bc8c11e1a404080027e73ea2f06e1efdb7704ba6a6382afe4ae3e127"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "97afe362bc8c11e1a404080027e73ea2f06e1efdb7704ba6a6382afe4ae3e127;2018-11-15T16:39:29Z;toolService;toolService:tool;UIMA/U-Compare GENIA Sentence Detector;The purpose of the tool is to detect sentence boundaries in English text. It is trained on the GENIA corpus of biomedical abstracts and so is particularly suitable for splitting sentences in biomedical texts. The tool is provided as a UIMA component, which forms part of the in-built library of components provided with the U-Compare platform for building and evaluating text mining workflows. The U-Compare Workbench, which provides a graphical drag-and drop interface for the rapid creation of workflows. \n;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7613e9f9-d62e-5784-9880-0e2efc502cb1",
-    "notes": [
-        "The purpose of the tool is to detect sentence boundaries in English text. It is trained on the GENIA corpus of biomedical abstracts and so is particularly suitable for splitting sentences in biomedical texts. The tool is provided as a UIMA component, which forms part of the in-built library of components provided with the U-Compare platform for building and evaluating text mining workflows. The U-Compare Workbench, which provides a graphical drag-and drop interface for the rapid creation of workflows. \n"
-    ],
-    "oai_identifier": [
-        "97afe362bc8c11e1a404080027e73ea2f06e1efdb7704ba6a6382afe4ae3e127"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "UIMA/U-Compare GENIA Sentence Detector"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/763e520c-e208-5a9e-8756-d1142ed50219.json b/oaitestdata/clarin-oai_dc/SET_1/json/763e520c-e208-5a9e-8756-d1142ed50219.json
deleted file mode 100644
index 12b39590..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/763e520c-e208-5a9e-8756-d1142ed50219.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Arts, Institute of the Czech National Corpus, Charles University in Prague"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1593",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1593"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1593",
-    "PublicationTimestamp": "2015-12-18T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Faculty of Arts, Institute of the Czech National Corpus, Charles University in Prague"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Czech National Corpus (Shuffled Corpus Data)",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/license-cnc",
-        "ACA"
-    ],
-    "author": [
-        "Hn\u00e1tkov\u00e1, Milena",
-        "Trune\u010dek, Petr",
-        "Petkevi\u010d, Vladim\u00edr",
-        "Chlumsk\u00e1, Lucie",
-        "\u010capka, Tom\u00e1\u0161",
-        "Vond\u0159i\u010dka, Pavel",
-        "Proch\u00e1zka, Pavel",
-        "\u010cerm\u00e1kov\u00e1, Anna",
-        "Kov\u00e1\u0159\u00edkov\u00e1, Dominika",
-        "K\u0159en, Michal",
-        "Jel\u00ednek, Tom\u00e1\u0161",
-        "Skoumalov\u00e1, Hana",
-        "Cvr\u010dek, V\u00e1clav",
-        "\u0160krabal, Michal",
-        "Zasina, Adrian"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1593;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;SYN2015: representative corpus of written Czech;K\u0159en, Michal;Cvr\u010dek, V\u00e1clav;\u010capka, Tom\u00e1\u0161;\u010cerm\u00e1kov\u00e1, Anna;Hn\u00e1tkov\u00e1, Milena;Chlumsk\u00e1, Lucie;Kov\u00e1\u0159\u00edkov\u00e1, Dominika;Jel\u00ednek, Tom\u00e1\u0161;Petkevi\u010d, Vladim\u00edr;Proch\u00e1zka, Pavel;Skoumalov\u00e1, Hana;\u0160krabal, Michal;Trune\u010dek, Petr;Vond\u0159i\u010dka, Pavel;Zasina, Adrian;representative corpus;written language;Representative corpus of contemporary written Czech sized 100 MW. It was created as a representation of printed language from 2010\u20132014 containing a wide range of text types (fiction, professional literature, newspapers etc.). The corpus is lemmatized, morphologically and syntactically annotated by a combination of stochastic and rule-based methods. The corpus is provided in a (semi-XML) vertical format used as an input to the Manatee query engine. The data thus correspond to the corpus available via the KonText query interface to registered users of the CNC with one important exception: they are shuffled, i.e. divided into blocks sized max. 100 words (respecting the sentence boundaries) with ordering randomized within the given document.;2015-12-18;corpus;http://hdl.handle.net/11234/1-1593;ces;Czech National Corpus (Shuffled Corpus Data);https://lindat.mff.cuni.cz/repository/xmlui/page/license-cnc;ACA;text/plain; charset=utf-8;application/x-gzip;downloadable_files_count: 1;Faculty of Arts, Institute of the Czech National Corpus, Charles University in Prague;https://wiki.korpus.cz/doku.php/cnk:syn2015",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "763e520c-e208-5a9e-8756-d1142ed50219",
-    "notes": [
-        "Representative corpus of contemporary written Czech sized 100 MW. It was created as a representation of printed language from 2010\u20132014 containing a wide range of text types (fiction, professional literature, newspapers etc.). The corpus is lemmatized, morphologically and syntactically annotated by a combination of stochastic and rule-based methods. The corpus is provided in a (semi-XML) vertical format used as an input to the Manatee query engine. The data thus correspond to the corpus available via the KonText query interface to registered users of the CNC with one important exception: they are shuffled, i.e. divided into blocks sized max. 100 words (respecting the sentence boundaries) with ordering randomized within the given document."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1593"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "representative corpus"
-        },
-        {
-            "name": "written language"
-        }
-    ],
-    "title": [
-        "SYN2015: representative corpus of written Czech"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/764163d0-df1e-5050-a344-95f0466f6524.json b/oaitestdata/clarin-oai_dc/SET_1/json/764163d0-df1e-5050-a344-95f0466f6524.json
deleted file mode 100644
index f31c87fa..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/764163d0-df1e-5050-a344-95f0466f6524.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "text/xml",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1467",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1467"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1467",
-    "PublicationTimestamp": "2014-12-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "\u0160ev\u010d\u00edkov\u00e1, Magda"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1467;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;AdjDeriNet: Words Derived from Adjectives in Czech;\u0160ev\u010d\u00edkov\u00e1, Magda;\u017dabokrtsk\u00fd, Zden\u011bk;adjectives;derivation;word-formation;derivational morphology;Lexical network AdjDeriNet consists of pairs of base adjectives and their derivatives. It contains nearly 18 thousand base adjectives that are base words for more than 26 thousand lexemes of several parts of speech.;2014-12-30;lexicalConceptualResource;http://hdl.handle.net/11234/1-1467;ces;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/octet-stream;text/xml;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/selected-derivational-relations",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "764163d0-df1e-5050-a344-95f0466f6524",
-    "notes": [
-        "Lexical network AdjDeriNet consists of pairs of base adjectives and their derivatives. It contains nearly 18 thousand base adjectives that are base words for more than 26 thousand lexemes of several parts of speech."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1467"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "adjectives"
-        },
-        {
-            "name": "derivation"
-        },
-        {
-            "name": "word-formation"
-        },
-        {
-            "name": "derivational morphology"
-        }
-    ],
-    "title": [
-        "AdjDeriNet: Words Derived from Adjectives in Czech"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/764b130b-8212-5154-b146-1d7cf6f8dd3d.json b/oaitestdata/clarin-oai_dc/SET_1/json/764b130b-8212-5154-b146-1d7cf6f8dd3d.json
deleted file mode 100644
index ce7be0f2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/764b130b-8212-5154-b146-1d7cf6f8dd3d.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4188",
-    "MetadataAccess": [
-        "oai:ota:oucs:4188"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Inchbald, Mrs., 1753-1821."
-    ],
-    "fulltext": "oai:ota:oucs:4188;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4188.xml;Such things are: a play, in five acts. As performed at the Theatre Royal, Covent Garden. By Mrs. Inchbald.;Inchbald, Mrs., 1753-1821.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "764b130b-8212-5154-b146-1d7cf6f8dd3d",
-    "oai_identifier": [
-        "oai:ota:oucs:4188"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Such things are: a play, in five acts. As performed at the Theatre Royal, Covent Garden. By Mrs. Inchbald."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4188.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/76696f7d-5a73-5697-8088-87bdc6c09e38.json b/oaitestdata/clarin-oai_dc/SET_1/json/76696f7d-5a73-5697-8088-87bdc6c09e38.json
deleted file mode 100644
index 5c3be8cc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/76696f7d-5a73-5697-8088-87bdc6c09e38.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5587",
-    "MetadataAccess": [
-        "oai:ota:oucs:5587"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Holwell, J. Z. (John Zephaniah), 1711-1798."
-    ],
-    "fulltext": "oai:ota:oucs:5587;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5587.xml;An account of the manner of inoculating for the small pox in the East Indies: With some observations on the practice and mode of treating that disease in those parts. ... By J. Z. Holwell, F.R.S.;Holwell, J. Z. (John Zephaniah), 1711-1798.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "76696f7d-5a73-5697-8088-87bdc6c09e38",
-    "oai_identifier": [
-        "oai:ota:oucs:5587"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An account of the manner of inoculating for the small pox in the East Indies: With some observations on the practice and mode of treating that disease in those parts. ... By J. Z. Holwell, F.R.S."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5587.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/76be1b7e-fc54-501f-bbd1-25bb13ad899e.json b/oaitestdata/clarin-oai_dc/SET_1/json/76be1b7e-fc54-501f-bbd1-25bb13ad899e.json
deleted file mode 100644
index 067145ba..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/76be1b7e-fc54-501f-bbd1-25bb13ad899e.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1159",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1159"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1159",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1159;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Brockhaus' Kleines Konversations-Lexikon;Germanistik;5. Aufl. 1911; Fokus auf Politik, Wirtschaft, Kultur und Technik zu Beginn des 20. Jahrhunderts;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1159;deu;downloadable_files_count: 0;http://www.zeno.org/Brockhaus-1911",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "76be1b7e-fc54-501f-bbd1-25bb13ad899e",
-    "notes": [
-        "5. Aufl. 1911; Fokus auf Politik, Wirtschaft, Kultur und Technik zu Beginn des 20. Jahrhunderts"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1159"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Brockhaus' Kleines Konversations-Lexikon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/76bedab8-8d82-53c7-97ff-fe8d1114dff3.json b/oaitestdata/clarin-oai_dc/SET_1/json/76bedab8-8d82-53c7-97ff-fe8d1114dff3.json
deleted file mode 100644
index cfc3ed5a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/76bedab8-8d82-53c7-97ff-fe8d1114dff3.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3753",
-    "MetadataAccess": [
-        "oai:ota:oucs:3753"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Bentley, R. (Richard), 1708-1782."
-    ],
-    "fulltext": "oai:ota:oucs:3753;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3753.xml;Patriotism, a mock-heroic. In five cantos;Bentley, R. (Richard), 1708-1782.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "76bedab8-8d82-53c7-97ff-fe8d1114dff3",
-    "oai_identifier": [
-        "oai:ota:oucs:3753"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Patriotism, a mock-heroic. In five cantos"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3753.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/77028796-5905-5787-ab4d-112efbf3d9b4.json b/oaitestdata/clarin-oai_dc/SET_1/json/77028796-5905-5787-ab4d-112efbf3d9b4.json
deleted file mode 100644
index 9fb4067d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/77028796-5905-5787-ab4d-112efbf3d9b4.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2868",
-    "MetadataAccess": [
-        "oai:ota:oucs:2868"
-    ],
-    "PublicationTimestamp": "1765-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1765"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2868;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2868.xml;Considerations about maintaining the poor;Swift, Jonathan, 1667-1745;1765;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "77028796-5905-5787-ab4d-112efbf3d9b4",
-    "oai_identifier": [
-        "oai:ota:oucs:2868"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Considerations about maintaining the poor"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2868.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/77091205-2eaa-5ac4-b864-e9c34ad25d56.json b/oaitestdata/clarin-oai_dc/SET_1/json/77091205-2eaa-5ac4-b864-e9c34ad25d56.json
deleted file mode 100644
index 8336908a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/77091205-2eaa-5ac4-b864-e9c34ad25d56.json
+++ /dev/null
@@ -1,89 +0,0 @@
-{
-    "Contact": [
-        "Humboldt-Universit\u00e4t zu Berlin; Institut f\u00fcr Slawistik; Prof. Dr. Roland Meyer, Paul Burzlaff"
-    ],
-    "Contributor": [
-        "Simon Ederer",
-        "Prof. Dr. Roland Meyer",
-        "Paul Burzlaff"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemmatool",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemmatool"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CD2-B",
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Humboldt-Universit\u00e4t zu Berlin; Institut f\u00fcr Slawistik; Prof. Dr. Roland Meyer, Paul Burzlaff"
-    ],
-    "RelatedIdentifier": [
-        "www.fsmbook.com",
-        "http://morfologik.blogspot.de/",
-        "Python"
-    ],
-    "ResourceType": [
-        "Software"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "author": [
-        "Humboldt-Universit\u00e4t zu Berlin; Institut f\u00fcr Slawistik; Prof. Dr. Roland Meyer, Paul Burzlaff"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemmatool;2019-02-22T17:38:52Z;PolDiLemma-Tool;Humboldt-Universit\u00e4t zu Berlin; Institut f\u00fcr Slawistik; Prof. Dr. Roland Meyer, Paul Burzlaff;corpus linguistics;historical linguistics;middle Polish;finite state automata;XFST;stemmer;morphology;Historical word forms may differ in orthography and/or grammatical categories. It is a linguistic challenge to make these old forms accessible. \nThe PolDiLemma-Tool is a Python tool for generating possible middle Polish inflected word forms including the part of speech tags from a given (new) Polish word. It contains a middle Polish morphology in XFST-format (compiled and plain text) and a stemmer (Morfologik: full form lexicon and finite state based stemmer).\n\nShould run on Linux and Windows machines (tested on Ubuntu 12.04, Ubuntu 14.04, and Win 8).\n\nNote: The XFST-Tool needs to be downloaded separately from: www.fsmbook.com\nMorfologik requires JAVA.;Humboldt-Universit\u00e4t zu Berlin; Institut f\u00fcr Slawistik; Prof. Dr. Roland Meyer, Paul Burzlaff;Prof. Dr. Roland Meyer;Paul Burzlaff;Simon Ederer;2013-2014;Software;clarind-uds:poldilemmatool;hdl:11858/00-246C-0000-0023-8CD2-B;pol;www.fsmbook.com;http://morfologik.blogspot.de/;Python;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "77091205-2eaa-5ac4-b864-e9c34ad25d56",
-    "notes": [
-        "Historical word forms may differ in orthography and/or grammatical categories. It is a linguistic challenge to make these old forms accessible. \nThe PolDiLemma-Tool is a Python tool for generating possible middle Polish inflected word forms including the part of speech tags from a given (new) Polish word. It contains a middle Polish morphology in XFST-format (compiled and plain text) and a stemmer (Morfologik: full form lexicon and finite state based stemmer).\n\nShould run on Linux and Windows machines (tested on Ubuntu 12.04, Ubuntu 14.04, and Win 8).\n\nNote: The XFST-Tool needs to be downloaded separately from: www.fsmbook.com\nMorfologik requires JAVA."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemmatool"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus linguistics"
-        },
-        {
-            "name": "historical linguistics"
-        },
-        {
-            "name": "middle Polish"
-        },
-        {
-            "name": "finite state automata"
-        },
-        {
-            "name": "XFST"
-        },
-        {
-            "name": "stemmer"
-        },
-        {
-            "name": "morphology"
-        }
-    ],
-    "title": [
-        "PolDiLemma-Tool"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/77142eab-0fc1-5ed4-b0bc-a7d2c0c6765f.json b/oaitestdata/clarin-oai_dc/SET_1/json/77142eab-0fc1-5ed4-b0bc-a7d2c0c6765f.json
deleted file mode 100644
index f49934f9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/77142eab-0fc1-5ed4-b0bc-a7d2c0c6765f.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4581",
-    "MetadataAccess": [
-        "oai:ota:oucs:4581"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Baratier, Fran\u00c3\u00a7ois, 1682-1751."
-    ],
-    "fulltext": "oai:ota:oucs:4581;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4581.xml;An account of the life of John Philip Barretier: who was master of five languages at the age of nine years. Compiled from his father's letters, &c.;Baratier, Fran\u00c3\u00a7ois, 1682-1751.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "77142eab-0fc1-5ed4-b0bc-a7d2c0c6765f",
-    "oai_identifier": [
-        "oai:ota:oucs:4581"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An account of the life of John Philip Barretier: who was master of five languages at the age of nine years. Compiled from his father's letters, &c."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4581.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7720f7c7-04ca-514d-99cf-2000d535fa1c.json b/oaitestdata/clarin-oai_dc/SET_1/json/7720f7c7-04ca-514d-99cf-2000d535fa1c.json
deleted file mode 100644
index 13c8b7cc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7720f7c7-04ca-514d-99cf-2000d535fa1c.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5681",
-    "MetadataAccess": [
-        "oai:ota:oucs:5681"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Cockell, William."
-    ],
-    "fulltext": "oai:ota:oucs:5681;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5681.xml;An essay on the retroversion of the uterus: illustrated with cases and observations. By William Cockell, ...;Cockell, William.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7720f7c7-04ca-514d-99cf-2000d535fa1c",
-    "oai_identifier": [
-        "oai:ota:oucs:5681"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An essay on the retroversion of the uterus: illustrated with cases and observations. By William Cockell, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5681.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/772895b6-759b-5bb3-9086-05afb6d7e8a0.json b/oaitestdata/clarin-oai_dc/SET_1/json/772895b6-759b-5bb3-9086-05afb6d7e8a0.json
deleted file mode 100644
index 40db7cd4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/772895b6-759b-5bb3-9086-05afb6d7e8a0.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "text/xml",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Lule Sami"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/101",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/101"
-    ],
-    "PID": "http://hdl.handle.net/11509/101",
-    "PublicationTimestamp": "2015-10-10T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "The Divvun group at UiT The Arctic University of Norway",
-        "Giellatekno - Saami Language Technology, UiT The Arctic University of Norway"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/101;2016-09-06T12:56:33Z;hdl_11509_1;hdl_11509_2;SIKOR Lule Saami free corpus;Giellatekno - Saami Language Technology, UiT The Arctic University of Norway;The Divvun group at UiT The Arctic University of Norway;Monolingual Corpus;Text Corpus;Lule Saami;Dependency Tree Bank;The SIKOR Lule Saami free corpus is a monolingual text corpus of Lule Saami that contains news, administrative, law, and religious texts. It is work done by the Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language community. In particular, the following colleagues have contributed to the creation of the ressource: Ciprian Gerstenberger, B\u00f8rre Gaup, Inga-Lill Mikkelsen, and Sandra Nyst\u00f8 Rahka. Linguistically, the data set (48,307 sentences; 535,367 tokens) features word form, lemma, morphosyntactic analysis, and dependency relations between tokens. The corpus has been automatically processed and linguistically analyzed with the Giellatekno/Divvun tools. Therefore, it may contain wrong annotations. In case you find any errors the creators would appreciate your feedback sent to giellatekno@uit.no and feedback@divvun.no.\r\nPlease note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata).;2015-10-10;corpus;http://hdl.handle.net/11509/101;smj;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;application/zip;text/plain; charset=utf-8;text/xml;downloadable_files_count: 1;Giellatekno - Saami Language Technology;http://giellatekno.uit.no/index.eng.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "772895b6-759b-5bb3-9086-05afb6d7e8a0",
-    "notes": [
-        "The SIKOR Lule Saami free corpus is a monolingual text corpus of Lule Saami that contains news, administrative, law, and religious texts. It is work done by the Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language community. In particular, the following colleagues have contributed to the creation of the ressource: Ciprian Gerstenberger, B\u00f8rre Gaup, Inga-Lill Mikkelsen, and Sandra Nyst\u00f8 Rahka. Linguistically, the data set (48,307 sentences; 535,367 tokens) features word form, lemma, morphosyntactic analysis, and dependency relations between tokens. The corpus has been automatically processed and linguistically analyzed with the Giellatekno/Divvun tools. Therefore, it may contain wrong annotations. In case you find any errors the creators would appreciate your feedback sent to giellatekno@uit.no and feedback@divvun.no.\r\nPlease note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata)."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/101"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Monolingual Corpus"
-        },
-        {
-            "name": "Text Corpus"
-        },
-        {
-            "name": "Lule Saami"
-        },
-        {
-            "name": "Dependency Tree Bank"
-        }
-    ],
-    "title": [
-        "SIKOR Lule Saami free corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/77293f33-caf3-5bfa-9c4e-0ffd26a53bf3.json b/oaitestdata/clarin-oai_dc/SET_1/json/77293f33-caf3-5bfa-9c4e-0ffd26a53bf3.json
deleted file mode 100644
index b7735f19..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/77293f33-caf3-5bfa-9c4e-0ffd26a53bf3.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4719",
-    "MetadataAccess": [
-        "oai:ota:oucs:4719"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Akenside, Mark, 1721-1770."
-    ],
-    "fulltext": "oai:ota:oucs:4719;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4719.xml;The poetical works: of Mark Akenside. In two volumes. With the life of the author. ... [pt.2];Akenside, Mark, 1721-1770.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "77293f33-caf3-5bfa-9c4e-0ffd26a53bf3",
-    "oai_identifier": [
-        "oai:ota:oucs:4719"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The poetical works: of Mark Akenside. In two volumes. With the life of the author. ... [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4719.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/77312fc1-7c75-58be-8286-533f82e51625.json b/oaitestdata/clarin-oai_dc/SET_1/json/77312fc1-7c75-58be-8286-533f82e51625.json
deleted file mode 100644
index 1a8d2e74..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/77312fc1-7c75-58be-8286-533f82e51625.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Jan Wieczorek"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/479",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/479"
-    ],
-    "PID": "http://hdl.handle.net/11321/479",
-    "PublicationTimestamp": "2018-06-13T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Jan Wieczorek"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Super Cool License",
-        "http://www.google.com",
-        "ACA"
-    ],
-    "author": [
-        "Wieczorek, Jan"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/479;2018-06-13T12:54:55Z;hdl_11321_3;hdl_11321_478;Siemiradzki test june 2018;Wieczorek, Jan;history of art;test;Siemiradzki;2018-06-13;corpus;http://hdl.handle.net/11321/479;pol;Super Cool License;http://www.google.com;ACA;text/plain; charset=utf-8;application/msword;application/msword;downloadable_files_count: 2;Jan Wieczorek",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "77312fc1-7c75-58be-8286-533f82e51625",
-    "notes": [
-        "Siemiradzki"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/479"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_478"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "history art"
-        },
-        {
-            "name": "test"
-        }
-    ],
-    "title": [
-        "Siemiradzki test june 2018"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7732a4af-4b77-5dd0-8517-60629040c6bf.json b/oaitestdata/clarin-oai_dc/SET_1/json/7732a4af-4b77-5dd0-8517-60629040c6bf.json
deleted file mode 100644
index 9bc1cddb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7732a4af-4b77-5dd0-8517-60629040c6bf.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 21.3 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "Old English (ca. 450-1100)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0815",
-    "MetadataAccess": [
-        "oai:ota:oucs:0815"
-    ],
-    "PublicationYear": [
-        "880-899"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Orosius, Paulus"
-    ],
-    "fulltext": "oai:ota:oucs:0815;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0815.xml;Historiarum adversus paganos libri VII. English (Old English);Alfred's Orosius;Orosius, Paulus;880-899;text_and_corpus_linguistics;Local histories;ang;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 21.3 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7732a4af-4b77-5dd0-8517-60629040c6bf",
-    "oai_identifier": [
-        "oai:ota:oucs:0815"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Local histories"
-        }
-    ],
-    "title": [
-        "Historiarum adversus paganos libri VII. English (Old English)",
-        "Alfred's Orosius"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0815.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/77429d40-cc54-531a-ba19-f08f39127268.json b/oaitestdata/clarin-oai_dc/SET_1/json/77429d40-cc54-531a-ba19-f08f39127268.json
deleted file mode 100644
index 5c8cbc48..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/77429d40-cc54-531a-ba19-f08f39127268.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1412",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1412"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1412",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1412;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;freeling_tokenizer;Freeling-based text tokenizer.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1412;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "77429d40-cc54-531a-ba19-f08f39127268",
-    "notes": [
-        "Freeling-based text tokenizer."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1412"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "freeling_tokenizer"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/774fef08-a05d-50ef-acd6-1121be44cb06.json b/oaitestdata/clarin-oai_dc/SET_1/json/774fef08-a05d-50ef-acd6-1121be44cb06.json
deleted file mode 100644
index 5ae9d1a7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/774fef08-a05d-50ef-acd6-1121be44cb06.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Devine, K. (Kieran), 1946-"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 395 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "Irish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1172",
-    "MetadataAccess": [
-        "oai:ota:oucs:1172"
-    ],
-    "PublicationTimestamp": "1969-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1969"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Fiction"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Mac Grianna, Seosamh"
-    ],
-    "fulltext": "oai:ota:oucs:1172;2018-03-05T12:05:10Z;http://ota.ox.ac.uk/headers/1172.xml;P\u00c3\u00a1driac \u00c3\u0093 Conaire agus aist\u00c3\u00ad / Seosamh Mac Grianna;Mac Grianna, Seosamh;1969;text_and_corpus_linguistics;Irish fiction -- 20th century;gle;Oxford Text Archive, University of Oxford;Devine, K. (Kieran), 1946-;text/plain;(1 file : ca. 395 KB);Text;Fiction;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "774fef08-a05d-50ef-acd6-1121be44cb06",
-    "oai_identifier": [
-        "oai:ota:oucs:1172"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Irish fiction -- th century"
-        }
-    ],
-    "title": [
-        "P\u00c3\u00a1driac \u00c3\u0093 Conaire agus aist\u00c3\u00ad / Seosamh Mac Grianna"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1172.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7759b510-58dd-5076-bbdb-d007a5e543fe.json b/oaitestdata/clarin-oai_dc/SET_1/json/7759b510-58dd-5076-bbdb-d007a5e543fe.json
deleted file mode 100644
index 9558763a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7759b510-58dd-5076-bbdb-d007a5e543fe.json
+++ /dev/null
@@ -1,90 +0,0 @@
-{
-    "Contact": [
-        "Copenhagen Business School"
-    ],
-    "Contributor": [
-        "Buch-Kromann, Matthias"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Danish",
-        "English",
-        "German",
-        "Italian",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1081",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1081"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1081",
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Copenhagen Business School"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU General Public License"
-    ],
-    "SpatialCoverage": [
-        "Denmark"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1081;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Copenhagen Dependency Treebanks versions 1-3;Buch-Kromann, Matthias;parallel treebank;POS annotation;discourse annotation;morphological annotation;syntactic annotation;semantic annotation;Parallel treebanks with annotation of syntax, discourse, coreference, morphology, and semantics. Version 3 also includes the Danish Dependency Treebank (version 1) and the Danish-English Parallel Dependency Treebank (version 2).;2011;corpus;http://hdl.handle.net/11372/LRT-1081;dan;eng;deu;ita;spa;GNU General Public License;application/octet-stream;downloadable_files_count: 0;Denmark;Copenhagen Business School;http://code.google.com/p/copenhagen-dependency-treebank/wiki/CDT",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7759b510-58dd-5076-bbdb-d007a5e543fe",
-    "notes": [
-        "Parallel treebanks with annotation of syntax, discourse, coreference, morphology, and semantics. Version 3 also includes the Danish Dependency Treebank (version 1) and the Danish-English Parallel Dependency Treebank (version 2)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1081"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parallel treebank"
-        },
-        {
-            "name": "POS annotation"
-        },
-        {
-            "name": "discourse annotation"
-        },
-        {
-            "name": "morphological annotation"
-        },
-        {
-            "name": "syntactic annotation"
-        },
-        {
-            "name": "semantic annotation"
-        }
-    ],
-    "title": [
-        "Copenhagen Dependency Treebanks versions 1-3"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/776e2900-113f-5889-b92a-a77394e18b75.json b/oaitestdata/clarin-oai_dc/SET_1/json/776e2900-113f-5889-b92a-a77394e18b75.json
deleted file mode 100644
index 9c2a122e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/776e2900-113f-5889-b92a-a77394e18b75.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Kaczkowski"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 6",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/77",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/77"
-    ],
-    "PID": "http://hdl.handle.net/11321/77",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Kaczkowski"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Kaczkowski, Kaczkowski"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/77;2017-02-04T13:47:43Z;hdl_11321_3;hdl_11321_4;MWE Kaczkowski;Kaczkowski, Kaczkowski;Kaczkowski;2015-04-08;corpus;http://hdl.handle.net/11321/77;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 6;Kaczkowski",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "776e2900-113f-5889-b92a-a77394e18b75",
-    "notes": [
-        "Kaczkowski"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/77"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Kaczkowski"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/777867ef-f01c-5832-97da-46722e0a52f3.json b/oaitestdata/clarin-oai_dc/SET_1/json/777867ef-f01c-5832-97da-46722e0a52f3.json
deleted file mode 100644
index 869c7c41..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/777867ef-f01c-5832-97da-46722e0a52f3.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1659",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1659"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1659",
-    "PublicationTimestamp": "2016-05-23T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Straka, Milan"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1659;2018-07-02T22:05:53Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Universal Dependencies 1.2 Models for UDPipe;Straka, Milan;tokenizer;POS tagger;lemmatization;tagger;parser;dependency parser;Tokenizer, POS Tagger, Lemmatizer and Parser models for all Universal Depenencies 1.2 Treebanks, created solely using UD 1.2 data (http://hdl.handle.net/11234/1-1548).\r\n\r\nTo use these models, you need UDPipe binary, which you can download from http://ufal.mff.cuni.cz/udpipe.;2016-05-23;toolService;http://hdl.handle.net/11234/1-1659;eng;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/udpipe",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "777867ef-f01c-5832-97da-46722e0a52f3",
-    "notes": [
-        "Tokenizer, POS Tagger, Lemmatizer and Parser models for all Universal Depenencies 1.2 Treebanks, created solely using UD 1.2 data (http://hdl.handle.net/11234/1-1548).\r\n\r\nTo use these models, you need UDPipe binary, which you can download from http://ufal.mff.cuni.cz/udpipe."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1659"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "tokenizer"
-        },
-        {
-            "name": "POS tagger"
-        },
-        {
-            "name": "lemmatization"
-        },
-        {
-            "name": "tagger"
-        },
-        {
-            "name": "parser"
-        },
-        {
-            "name": "dependency parser"
-        }
-    ],
-    "title": [
-        "Universal Dependencies 1.2 Models for UDPipe"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/778964c3-4a29-5d9e-9c6c-fb8a5e3edc0f.json b/oaitestdata/clarin-oai_dc/SET_1/json/778964c3-4a29-5d9e-9c6c-fb8a5e3edc0f.json
deleted file mode 100644
index 70c4a38f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/778964c3-4a29-5d9e-9c6c-fb8a5e3edc0f.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain",
-        "(1 file : ca. 31.4 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0584",
-    "MetadataAccess": [
-        "oai:ota:oucs:0584"
-    ],
-    "PublicationTimestamp": "1609-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1609"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Middleton, Thomas, d. 1627"
-    ],
-    "fulltext": "oai:ota:oucs:0584;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0584.xml;Sir Robert Sherley : sent ambassadour in the name of the King of Persia, to Sigismond the Third, King of Poland and Swecia, and to other princes of Europe : his royall entertainement into Cracovia, the cheife citie of Poland, with his pretended comming into England : also, the honourable praise of the same Sir Robert Sherley, given unto him in that kingdome, and here likewise inserted;Middleton, Thomas, d. 1627;1609;text_and_corpus_linguistics;Eulogies -- England -- 17th century;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 31.4 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "778964c3-4a29-5d9e-9c6c-fb8a5e3edc0f",
-    "oai_identifier": [
-        "oai:ota:oucs:0584"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Eulogies -- England -- th century"
-        }
-    ],
-    "title": [
-        "Sir Robert Sherley : sent ambassadour in the name of the King of Persia, to Sigismond the Third, King of Poland and Swecia, and to other princes of Europe : his royall entertainement into Cracovia, the cheife citie of Poland, with his pretended comming into England : also, the honourable praise of the same Sir Robert Sherley, given unto him in that kingdome, and here likewise inserted"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0584.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/779faa8c-109c-55de-b311-e0673b597071.json b/oaitestdata/clarin-oai_dc/SET_1/json/779faa8c-109c-55de-b311-e0673b597071.json
deleted file mode 100644
index a0073512..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/779faa8c-109c-55de-b311-e0673b597071.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "less than 512 KB"
-    ],
-    "Language": [
-        "Welsh"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1400",
-    "MetadataAccess": [
-        "oai:ota:oucs:1400"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Romances"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:1400;2018-05-25T13:48:34Z;http://ota.ox.ac.uk/headers/1400.xml; Kulhwch : [from] Llyfr Gwyn Rhydderch / compiled by Nancy H. Rose;Date unknown;text_and_corpus_linguistics;Myths and legends -- Wales;Romances -- Wales;cym;Oxford Text Archive, University of Oxford;less than 512 KB;Text;Romances;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "779faa8c-109c-55de-b311-e0673b597071",
-    "oai_identifier": [
-        "oai:ota:oucs:1400"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Myths legends -- Wales"
-        },
-        {
-            "name": "Romances -- Wales"
-        }
-    ],
-    "title": [
-        " Kulhwch : [from] Llyfr Gwyn Rhydderch / compiled by Nancy H. Rose"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1400.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/77a4dce6-e1ed-51e0-afa3-263fd8a8adea.json b/oaitestdata/clarin-oai_dc/SET_1/json/77a4dce6-e1ed-51e0-afa3-263fd8a8adea.json
deleted file mode 100644
index c062867f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/77a4dce6-e1ed-51e0-afa3-263fd8a8adea.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-945",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-945"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-945",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-945;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Cimbrian German;ca. 20.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-945;deu;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#nhd",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "77a4dce6-e1ed-51e0-afa3-263fd8a8adea",
-    "notes": [
-        "ca. 20.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-945"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Cimbrian German"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/77aa2303-c928-5676-b354-91a764fc4604.json b/oaitestdata/clarin-oai_dc/SET_1/json/77aa2303-c928-5676-b354-91a764fc4604.json
deleted file mode 100644
index 468d6919..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/77aa2303-c928-5676-b354-91a764fc4604.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "ZRC SAZU"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1129",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1129"
-    ],
-    "PID": "http://hdl.handle.net/11356/1129",
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "ZRC SAZU"
-    ],
-    "RelatedIdentifier": [
-        "http://www.dlib.si/v2/StreamFile.aspx?URN=URN:NBN:SI:doc-5POMCIZX&id=7b7d09a8-f0aa-4451-b292-960bac96b3da&type=PDF"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)",
-        "https://creativecommons.org/licenses/by-nc/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Keber, Janez"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1129;2017-07-01T10:43:50Z;hdl_11356_1023;hdl_11356_1024;Dictionary of Slovenian Phrasemes;Keber, Janez;dictionary;phraseology;lexicography;The 3,002 entries of this dictionary cover the description and explanation of 13,125 Slovenian phrasemes. The use of phrasemes is represented by citations from lexical files built for the Dictionary of the Slovenian Standard Language as well as from the Nova beseda corpus and other resources. The entries also contain etymological information and equivalents in other languages.\r\n\r\nThis dictionary was published as a printed book:\r\nKeber, Janez. Slovar slovenskih frazemov. Ljubljana : Zalo\u017eba ZRC, ZRC SAZU, 2011. ISBN 978-961-254-329-7.;2011;lexicalConceptualResource;http://hdl.handle.net/11356/1129;slv;http://www.dlib.si/v2/StreamFile.aspx?URN=URN:NBN:SI:doc-5POMCIZX&id=7b7d09a8-f0aa-4451-b292-960bac96b3da&type=PDF;Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0);https://creativecommons.org/licenses/by-nc/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;ZRC SAZU;http://www.fran.si/192/janez-keber-frazeoloski-slovar-slovenskega-jezika",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "77aa2303-c928-5676-b354-91a764fc4604",
-    "notes": [
-        "The 3,002 entries of this dictionary cover the description and explanation of 13,125 Slovenian phrasemes. The use of phrasemes is represented by citations from lexical files built for the Dictionary of the Slovenian Standard Language as well as from the Nova beseda corpus and other resources. The entries also contain etymological information and equivalents in other languages.\r\n\r\nThis dictionary was published as a printed book:\r\nKeber, Janez. Slovar slovenskih frazemov. Ljubljana : Zalo\u017eba ZRC, ZRC SAZU, 2011. ISBN 978-961-254-329-7."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1129"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "dictionary"
-        },
-        {
-            "name": "phraseology"
-        },
-        {
-            "name": "lexicography"
-        }
-    ],
-    "title": [
-        "Dictionary of Slovenian Phrasemes"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/77bce262-5770-55df-8885-de1dd4b63ae0.json b/oaitestdata/clarin-oai_dc/SET_1/json/77bce262-5770-55df-8885-de1dd4b63ae0.json
deleted file mode 100644
index 51db624b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/77bce262-5770-55df-8885-de1dd4b63ae0.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4622",
-    "MetadataAccess": [
-        "oai:ota:oucs:4622"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Paley, William, 1743-1805."
-    ],
-    "fulltext": "oai:ota:oucs:4622;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4622.xml;A view of the evidences of Christianity: In three parts. ... By William Paley, ... [pt.1];Paley, William, 1743-1805.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "77bce262-5770-55df-8885-de1dd4b63ae0",
-    "oai_identifier": [
-        "oai:ota:oucs:4622"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A view of the evidences of Christianity: In three parts. ... By William Paley, ... [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4622.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/77c05a2e-131b-57a1-9824-c4f8b279996d.json b/oaitestdata/clarin-oai_dc/SET_1/json/77c05a2e-131b-57a1-9824-c4f8b279996d.json
deleted file mode 100644
index 015e7c05..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/77c05a2e-131b-57a1-9824-c4f8b279996d.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Ibtikarat team"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/xml",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Arabic"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1943",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1943"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1943",
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Ibtikarat team"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)",
-        "http://creativecommons.org/licenses/by-nc/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Loukili, Taoufik"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1943;2017-02-06T11:05:25Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Arabic Enclitics Lexicon;Loukili, Taoufik;Enclitics;An XML-based file containing all Arabic enclitics;2014;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1943;ara;Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0);http://creativecommons.org/licenses/by-nc/4.0/;PUB;text/xml;text/plain; charset=utf-8;downloadable_files_count: 1;Ibtikarat team;http://arabic.emi.ac.ma/ibtikarat/?q=Resources",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "77c05a2e-131b-57a1-9824-c4f8b279996d",
-    "notes": [
-        "An XML-based file containing all Arabic enclitics"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1943"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Enclitics"
-        }
-    ],
-    "title": [
-        "Arabic Enclitics Lexicon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/77dbce44-9228-5b67-85aa-9963ca16642f.json b/oaitestdata/clarin-oai_dc/SET_1/json/77dbce44-9228-5b67-85aa-9963ca16642f.json
deleted file mode 100644
index 90c1d307..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/77dbce44-9228-5b67-85aa-9963ca16642f.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "IBL PAN"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/vnd.oasis.opendocument.text",
-        "downloadable_files_count: 10",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/372",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/372"
-    ],
-    "PID": "http://hdl.handle.net/11321/372",
-    "PublicationTimestamp": "2017-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "IBL PAN"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Kaja, Damian"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/372;2017-05-30T07:54:35Z;hdl_11321_3;hdl_11321_4;warsztaty_2017_dk;Kaja, Damian;literature;varia;2017-05-30;corpus;http://hdl.handle.net/11321/372;pol;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.oasis.opendocument.text;text/plain;application/msword;text/plain;text/plain;application/vnd.oasis.opendocument.text;downloadable_files_count: 10;IBL PAN",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "77dbce44-9228-5b67-85aa-9963ca16642f",
-    "notes": [
-        "varia"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/372"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "literature"
-        }
-    ],
-    "title": [
-        "warsztaty_2017_dk"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/77f0133a-4ed9-5826-970e-c1aeade56472.json b/oaitestdata/clarin-oai_dc/SET_1/json/77f0133a-4ed9-5826-970e-c1aeade56472.json
deleted file mode 100644
index f1cae355..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/77f0133a-4ed9-5826-970e-c1aeade56472.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml",
-        "text/plain; charset=utf-8",
-        "text/plain",
-        "application/zip",
-        "downloadable_files_count: 7",
-        "application/pdf"
-    ],
-    "Language": [
-        "Danish",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repository.clarin.dk:20.500.12115/18",
-    "MetadataAccess": [
-        "oai:repository.clarin.dk:20.500.12115/18"
-    ],
-    "PID": "http://hdl.handle.net/20.500.12115/18",
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN-ACA-NC",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NC=1&NORED=1",
-        "ACA"
-    ],
-    "author": [
-        "Hansen, Dorte Haltrup",
-        "Offersgaard, Lene"
-    ],
-    "fulltext": "oai:repository.clarin.dk:20.500.12115/18;2018-06-28T13:26:20Z;hdl_20.500.12115_1;hdl_20.500.12115_3;DK-CLARIN Parallel Financial Corpus (da-en);Hansen, Dorte Haltrup;Offersgaard, Lene;Economics;The DK-CLARIN Parallel Financial Corpus comprises 4.3 M Danish and 4.8 M English tokens from translated (parallel) documents, mainly annual reports, of the period 2002-2010 from 12 of the biggest Danish companies.\r\nAll texts are in XML TEIP5 format (TEIP5DKCLARIN-format), with tokenisation, pos-tagging, sentence and paragraph segmentation, lemmatisation and termhood annotation placed in separate text external spangroups.\r\nThe corpus was collected and processed in the work package 2.6 of the Danish CLARIN project (see http://dkclarin.ku.dk/english) by University of Copenhagen, Centre for Language Technology.\r\nThe aim of the Danish CLARIN consortium was to construct a Danish research infrastructure for the humanities integrating written, spoken, and visual records into a coherent and systematic digital repository. The project ran from January 2008 until the end of 2010.;2011;corpus;http://hdl.handle.net/20.500.12115/18;dan;eng;CLARIN-ACA-NC;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NC=1&NORED=1;ACA;application/zip;application/zip;text/plain;application/pdf;application/pdf;text/xml;text/xml;text/plain; charset=utf-8;downloadable_files_count: 7;Centre for Language Technology, NorS, University of Copenhagen",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "77f0133a-4ed9-5826-970e-c1aeade56472",
-    "notes": [
-        "The DK-CLARIN Parallel Financial Corpus comprises 4.3 M Danish and 4.8 M English tokens from translated (parallel) documents, mainly annual reports, of the period 2002-2010 from 12 of the biggest Danish companies.\r\nAll texts are in XML TEIP5 format (TEIP5DKCLARIN-format), with tokenisation, pos-tagging, sentence and paragraph segmentation, lemmatisation and termhood annotation placed in separate text external spangroups.\r\nThe corpus was collected and processed in the work package 2.6 of the Danish CLARIN project (see http://dkclarin.ku.dk/english) by University of Copenhagen, Centre for Language Technology.\r\nThe aim of the Danish CLARIN consortium was to construct a Danish research infrastructure for the humanities integrating written, spoken, and visual records into a coherent and systematic digital repository. The project ran from January 2008 until the end of 2010."
-    ],
-    "oai_identifier": [
-        "oai:repository.clarin.dk:20.500.12115/18"
-    ],
-    "oai_set": [
-        "hdl_20.500.12115_1",
-        "hdl_20.500.12115_3"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Economics"
-        }
-    ],
-    "title": [
-        "DK-CLARIN Parallel Financial Corpus (da-en)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/77fa2758-1dda-5a05-8523-3c917ac163e6.json b/oaitestdata/clarin-oai_dc/SET_1/json/77fa2758-1dda-5a05-8523-3c917ac163e6.json
deleted file mode 100644
index e9f81ac0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/77fa2758-1dda-5a05-8523-3c917ac163e6.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "15 files ; 1.5 MB"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1038",
-    "MetadataAccess": [
-        "oai:ota:oucs:1038"
-    ],
-    "PublicationTimestamp": "1987-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1987"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Music"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Corpora, Corpus"
-    ],
-    "fulltext": "oai:ota:oucs:1038;2018-03-05T10:37:10Z;http://ota.ox.ac.uk/headers/1038.xml;Essen corpus of German folksong melodies  / compiled by Helmut Schaffrath;Corpora, Corpus;1987;text_and_corpus_linguistics;Music -- Germany;deu;Oxford Text Archive, University of Oxford;15 files ; 1.5 MB;Text;Music;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "77fa2758-1dda-5a05-8523-3c917ac163e6",
-    "oai_identifier": [
-        "oai:ota:oucs:1038"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Music -- Germany"
-        }
-    ],
-    "title": [
-        "Essen corpus of German folksong melodies  / compiled by Helmut Schaffrath"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1038.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/78126b7c-7c1b-587d-a96e-09ec67dbbf76.json b/oaitestdata/clarin-oai_dc/SET_1/json/78126b7c-7c1b-587d-a96e-09ec67dbbf76.json
deleted file mode 100644
index 021e715c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/78126b7c-7c1b-587d-a96e-09ec67dbbf76.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-958",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-958"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-958",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-958;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Mingrelian;ca. 1.000.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-958;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#megrelica",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "78126b7c-7c1b-587d-a96e-09ec67dbbf76",
-    "notes": [
-        "ca. 1.000.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-958"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Mingrelian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/781a3f8d-aa52-599e-b22c-27dbff178275.json b/oaitestdata/clarin-oai_dc/SET_1/json/781a3f8d-aa52-599e-b22c-27dbff178275.json
deleted file mode 100644
index 4d90fce9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/781a3f8d-aa52-599e-b22c-27dbff178275.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "A"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1541",
-    "MetadataAccess": [
-        "oai:ota:oucs:1541"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Daniel, Samuel"
-    ],
-    "fulltext": "oai:ota:oucs:1541;2018-04-16T15:30:51Z;http://ota.ox.ac.uk/headers/1541.xml;Ulisses and the Syren;Daniel, Samuel;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;A;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "781a3f8d-aa52-599e-b22c-27dbff178275",
-    "oai_identifier": [
-        "oai:ota:oucs:1541"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Ulisses and the Syren"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1541.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/781f4353-df49-53c8-9a33-a60f1e1fa796.json b/oaitestdata/clarin-oai_dc/SET_1/json/781f4353-df49-53c8-9a33-a60f1e1fa796.json
deleted file mode 100644
index 2308bcab..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/781f4353-df49-53c8-9a33-a60f1e1fa796.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Institute of Indology and Tamil Studies, Cologne University"
-    ],
-    "Contributor": [
-        "Funderburk, Jim"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Sanskrit"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-968",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-968"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-968",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institute of Indology and Tamil Studies, Cologne University"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-968;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Cologne Digital Sanskrit Dictionaries;Funderburk, Jim;Sanskrit lexicons. The data is made available as scanned images of the works as well as a digitization of the scanned images, which permits computer-aided analyses and displays of the work. Can be downloaded or queried online.;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-968;san;downloadable_files_count: 0;Germany;Institute of Indology and Tamil Studies, Cologne University;http://www.sanskrit-lexicon.uni-koeln.de/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "781f4353-df49-53c8-9a33-a60f1e1fa796",
-    "notes": [
-        "Sanskrit lexicons. The data is made available as scanned images of the works as well as a digitization of the scanned images, which permits computer-aided analyses and displays of the work. Can be downloaded or queried online."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-968"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Cologne Digital Sanskrit Dictionaries"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/78644e42-e1be-522c-88ee-509825168372.json b/oaitestdata/clarin-oai_dc/SET_1/json/78644e42-e1be-522c-88ee-509825168372.json
deleted file mode 100644
index 4c01d02e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/78644e42-e1be-522c-88ee-509825168372.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4571",
-    "MetadataAccess": [
-        "oai:ota:oucs:4571"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pittis, William, 1674-1724."
-    ],
-    "fulltext": "oai:ota:oucs:4571;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4571.xml;The true-born Englishman: a satyr, answer'd, paragraph by paragraph.;Pittis, William, 1674-1724.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "78644e42-e1be-522c-88ee-509825168372",
-    "oai_identifier": [
-        "oai:ota:oucs:4571"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The true-born Englishman: a satyr, answer'd, paragraph by paragraph."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4571.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/78a0031f-1a80-5e9c-bdea-63ccead37e42.json b/oaitestdata/clarin-oai_dc/SET_1/json/78a0031f-1a80-5e9c-bdea-63ccead37e42.json
deleted file mode 100644
index ed506b74..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/78a0031f-1a80-5e9c-bdea-63ccead37e42.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Polish-Japanese Academy of Information Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/525",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/525"
-    ],
-    "PID": "http://hdl.handle.net/11321/525",
-    "PublicationTimestamp": "2018-07-08T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Polish-Japanese Academy of Information Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Marasek, Krzysztof",
-        "Kor\u017einek, Danijel"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/525;2018-07-15T07:58:30Z;hdl_11321_3;hdl_11321_4;Speech Recognition System for Polish: Parliamentary Speech;Kor\u017einek, Danijel;Marasek, Krzysztof;speech recognition;speech alignment;This resource contains dockerized models and scripts of an automatic speech recognition system for Polish trained on Polish Parliament speeches. The system is based on the Kaldi toolkit. The scripts include methods for performing speech recognition, forced alignment and a lenient alignment of audio. The Github repository contains information on how to use the tool.;2018-07-08;toolService;http://hdl.handle.net/11321/525;pol;downloadable_files_count: 0;Polish-Japanese Academy of Information Technology;https://hub.docker.com/r/danijel3/clarin-pl-speechtools/tags/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "78a0031f-1a80-5e9c-bdea-63ccead37e42",
-    "notes": [
-        "This resource contains dockerized models and scripts of an automatic speech recognition system for Polish trained on Polish Parliament speeches. The system is based on the Kaldi toolkit. The scripts include methods for performing speech recognition, forced alignment and a lenient alignment of audio. The Github repository contains information on how to use the tool."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/525"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech recognition"
-        },
-        {
-            "name": "speech alignment"
-        }
-    ],
-    "title": [
-        "Speech Recognition System for Polish: Parliamentary Speech"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/78cc6b15-fe23-58cb-9299-46a91be73e38.json b/oaitestdata/clarin-oai_dc/SET_1/json/78cc6b15-fe23-58cb-9299-46a91be73e38.json
deleted file mode 100644
index a82841b9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/78cc6b15-fe23-58cb-9299-46a91be73e38.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4720",
-    "MetadataAccess": [
-        "oai:ota:oucs:4720"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Murphy, Arthur, 1727-1805."
-    ],
-    "fulltext": "oai:ota:oucs:4720;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4720.xml;An essay on the life and genius of Samuel Johnson: LL.D. By Arthur Murphy, ...;Murphy, Arthur, 1727-1805.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "78cc6b15-fe23-58cb-9299-46a91be73e38",
-    "oai_identifier": [
-        "oai:ota:oucs:4720"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An essay on the life and genius of Samuel Johnson: LL.D. By Arthur Murphy, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4720.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/78cf2c05-21d8-5491-9289-888dc64f9d68.json b/oaitestdata/clarin-oai_dc/SET_1/json/78cf2c05-21d8-5491-9289-888dc64f9d68.json
deleted file mode 100644
index 5bde29b6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/78cf2c05-21d8-5491-9289-888dc64f9d68.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Evolutionary Anthropology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-694",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-694"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-694",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Evolutionary Anthropology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Code of conduct"
-    ],
-    "SpatialCoverage": [
-        "Mongolia||Russia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-694;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Tofa corpus;Documentation of the Tofa project (DoBeS project);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-694;Code of conduct;downloadable_files_count: 0;Mongolia||Russia;Max Planck Institute for Evolutionary Anthropology;http://corpus1.mpi.nl/ds/imdi_browser/?openpath=MPI81772%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "78cf2c05-21d8-5491-9289-888dc64f9d68",
-    "notes": [
-        "Documentation of the Tofa project (DoBeS project)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-694"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Tofa corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/78db1f85-0beb-5f00-a350-3c13bd1d19dd.json b/oaitestdata/clarin-oai_dc/SET_1/json/78db1f85-0beb-5f00-a350-3c13bd1d19dd.json
deleted file mode 100644
index a4db9c0a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/78db1f85-0beb-5f00-a350-3c13bd1d19dd.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4707",
-    "MetadataAccess": [
-        "oai:ota:oucs:4707"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pratt, Mr. (Samuel Jackson), 1749-1814."
-    ],
-    "fulltext": "oai:ota:oucs:4707;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4707.xml;Family secrets: literary and domestic. By Mr. Pratt. In five volumes. [pt.5];Pratt, Mr. (Samuel Jackson), 1749-1814.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "78db1f85-0beb-5f00-a350-3c13bd1d19dd",
-    "oai_identifier": [
-        "oai:ota:oucs:4707"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Family secrets: literary and domestic. By Mr. Pratt. In five volumes. [pt.5]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4707.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/78e1a778-f100-5a03-af74-dfe2c3744be5.json b/oaitestdata/clarin-oai_dc/SET_1/json/78e1a778-f100-5a03-af74-dfe2c3744be5.json
deleted file mode 100644
index 5c476199..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/78e1a778-f100-5a03-af74-dfe2c3744be5.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=1390982c3aec11e2a2aa782bcb0741350903f12d7d514e119f8386683e41b6f3",
-    "MetadataAccess": [
-        "1390982c3aec11e2a2aa782bcb0741350903f12d7d514e119f8386683e41b6f3"
-    ],
-    "PublicationTimestamp": "2012-11-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "fulltext": "1390982c3aec11e2a2aa782bcb0741350903f12d7d514e119f8386683e41b6f3;2018-11-15T16:39:54Z;lexicalConceptualResource;lexicalConceptualResource:thesaurus;Maltese automatically produced distributional thesaurus;This is an automatically produced distributional thesaurus, which finds words that tend to occur in similar contexts as the target word. It is not a manually constructed thesaurus of synonyms. It was produced by Lexical Computing Ltd on the basis of the MLRS corpus. \nThe file contains lines with the lemma_freq and lemma in first two columns and the rest of the line is a list of up to 20 best matches pairs (lemma+score) that have score at least 0.2.;2012-11-30",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "78e1a778-f100-5a03-af74-dfe2c3744be5",
-    "notes": [
-        "This is an automatically produced distributional thesaurus, which finds words that tend to occur in similar contexts as the target word. It is not a manually constructed thesaurus of synonyms. It was produced by Lexical Computing Ltd on the basis of the MLRS corpus. \nThe file contains lines with the lemma_freq and lemma in first two columns and the rest of the line is a list of up to 20 best matches pairs (lemma+score) that have score at least 0.2."
-    ],
-    "oai_identifier": [
-        "1390982c3aec11e2a2aa782bcb0741350903f12d7d514e119f8386683e41b6f3"
-    ],
-    "oai_set": [
-        "lexicalConceptualResource",
-        "lexicalConceptualResource:thesaurus"
-    ],
-    "state": "active",
-    "title": [
-        "Maltese automatically produced distributional thesaurus"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/791d6063-ca0f-5fb2-8941-7ceb33699c33.json b/oaitestdata/clarin-oai_dc/SET_1/json/791d6063-ca0f-5fb2-8941-7ceb33699c33.json
deleted file mode 100644
index 5c7f838e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/791d6063-ca0f-5fb2-8941-7ceb33699c33.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "IPI PAN"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/gzip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/581",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/581"
-    ],
-    "PID": "http://hdl.handle.net/11321/581",
-    "PublicationTimestamp": "2018-07-26T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "IPI PAN"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "BSD 2 Clause",
-        "https://opensource.org/licenses/BSD-2-Clause",
-        "PUB"
-    ],
-    "author": [
-        "\u017bak, Paulina"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/581;2018-07-26T15:03:54Z;hdl_11321_3;hdl_11321_4;TreeHopper (TreeLSTM): wyd\u017awi\u0119k na poziomie zda\u0144 i fraz;\u017bak, Paulina;sentiment;A Tree-LSTM-based dependency tree sentiment labeler;2018-07-26;toolService;http://hdl.handle.net/11321/581;pol;BSD 2 Clause;https://opensource.org/licenses/BSD-2-Clause;PUB;text/plain; charset=utf-8;application/gzip;downloadable_files_count: 1;IPI PAN;https://github.com/tomekkorbak/treehopper",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "791d6063-ca0f-5fb2-8941-7ceb33699c33",
-    "notes": [
-        "A Tree-LSTM-based dependency tree sentiment labeler"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/581"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "sentiment"
-        }
-    ],
-    "title": [
-        "TreeHopper (TreeLSTM): wyd\u017awi\u0119k na poziomie zda\u0144 i fraz"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/79256068-b875-557f-a1cf-e879fb59501a.json b/oaitestdata/clarin-oai_dc/SET_1/json/79256068-b875-557f-a1cf-e879fb59501a.json
deleted file mode 100644
index e19b8d7a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/79256068-b875-557f-a1cf-e879fb59501a.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "text/xml",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Norwegian Bokm\u00e5l",
-        "Southern Sami"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/93",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/93"
-    ],
-    "PID": "http://hdl.handle.net/11509/93",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "The Divvun group at UiT The Arctic University of Norway",
-        "Giellatekno - Saami Language Technology, UiT The Arctic University of Norway"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/93;2016-09-06T12:55:52Z;hdl_11509_1;hdl_11509_2;Norwegian Bokm\u00e5l-South Saami dictionary;Giellatekno - Saami Language Technology, UiT The Arctic University of Norway;The Divvun group at UiT The Arctic University of Norway;Bilingual Lexicon;Norwegian;South Saami;Machine-readable Dictionary;The Norwegian Bokm\u00e5l-South Saami dictionary is the work done by Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language communities. In particular, the following colleagues have contributed to the creation of the ressource: Tove Brustad, Albert J\u00e5ma, Lene Antonsen, Ciprian Gerstenberger, Trond Trosterud, Maja Kappfjell, Sissel J\u00e5ma, Toini Bergstr\u00f8m, Marit Fjellheim, Sjur Moshagen, and Thomas Omma. The dictionary contains 12951 entries in Giellatekno's dictionary xml format. In spite of the extensive quality control, it may contain entries with objectionable translations. If you find any errors or want to add more words, download the file, edit it, and send it back to giellatekno@uit.no and feedback@divvun.no.\r\nPlease note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata).;2015;lexicalConceptualResource;http://hdl.handle.net/11509/93;nob;sma;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;application/zip;text/plain; charset=utf-8;text/xml;downloadable_files_count: 1;Giellatekno - Saami Language Technology;http://giellatekno.uit.no/index.eng.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "79256068-b875-557f-a1cf-e879fb59501a",
-    "notes": [
-        "The Norwegian Bokm\u00e5l-South Saami dictionary is the work done by Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language communities. In particular, the following colleagues have contributed to the creation of the ressource: Tove Brustad, Albert J\u00e5ma, Lene Antonsen, Ciprian Gerstenberger, Trond Trosterud, Maja Kappfjell, Sissel J\u00e5ma, Toini Bergstr\u00f8m, Marit Fjellheim, Sjur Moshagen, and Thomas Omma. The dictionary contains 12951 entries in Giellatekno's dictionary xml format. In spite of the extensive quality control, it may contain entries with objectionable translations. If you find any errors or want to add more words, download the file, edit it, and send it back to giellatekno@uit.no and feedback@divvun.no.\r\nPlease note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata)."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/93"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Bilingual Lexicon"
-        },
-        {
-            "name": "Norwegian"
-        },
-        {
-            "name": "South Saami"
-        },
-        {
-            "name": "Machine-readable Dictionary"
-        }
-    ],
-    "title": [
-        "Norwegian Bokm\u00e5l-South Saami dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/79404bae-0c8c-5f38-a706-b2f193d30f1a.json b/oaitestdata/clarin-oai_dc/SET_1/json/79404bae-0c8c-5f38-a706-b2f193d30f1a.json
deleted file mode 100644
index a324b2d6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/79404bae-0c8c-5f38-a706-b2f193d30f1a.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4705",
-    "MetadataAccess": [
-        "oai:ota:oucs:4705"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pratt, Mr. (Samuel Jackson), 1749-1814."
-    ],
-    "fulltext": "oai:ota:oucs:4705;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4705.xml;Family secrets: literary and domestic. By Mr. Pratt. In five volumes. [pt.2];Pratt, Mr. (Samuel Jackson), 1749-1814.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "79404bae-0c8c-5f38-a706-b2f193d30f1a",
-    "oai_identifier": [
-        "oai:ota:oucs:4705"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Family secrets: literary and domestic. By Mr. Pratt. In five volumes. [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4705.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/79459790-e402-5f7e-b27f-c20d71bcf3c7.json b/oaitestdata/clarin-oai_dc/SET_1/json/79459790-e402-5f7e-b27f-c20d71bcf3c7.json
deleted file mode 100644
index fcda65da..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/79459790-e402-5f7e-b27f-c20d71bcf3c7.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=1cec28f2a35a11e1a404080027e73ea272c3895430344e23b2034d271b27b6a9",
-    "MetadataAccess": [
-        "1cec28f2a35a11e1a404080027e73ea272c3895430344e23b2034d271b27b6a9"
-    ],
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "1cec28f2a35a11e1a404080027e73ea272c3895430344e23b2034d271b27b6a9;2019-02-27T12:09:00Z;corpus;corpus:text;Laws of Malta - English;The corpus contains the Laws of Malta in English from the official government website. The unannotated raw text files were extracted from the pdf files that can be found on the website.;2015-12-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "79459790-e402-5f7e-b27f-c20d71bcf3c7",
-    "notes": [
-        "The corpus contains the Laws of Malta in English from the official government website. The unannotated raw text files were extracted from the pdf files that can be found on the website."
-    ],
-    "oai_identifier": [
-        "1cec28f2a35a11e1a404080027e73ea272c3895430344e23b2034d271b27b6a9"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "Laws of Malta - English"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/79469373-c04d-5443-8220-30083b2cc95c.json b/oaitestdata/clarin-oai_dc/SET_1/json/79469373-c04d-5443-8220-30083b2cc95c.json
deleted file mode 100644
index cd6ee379..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/79469373-c04d-5443-8220-30083b2cc95c.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "English",
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-161",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-161"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-161",
-    "PublicationTimestamp": "2014-07-24T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-1449"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU General Public License, version 2",
-        "http://www.gnu.org/licenses/gpl-2.0.html",
-        "PUB"
-    ],
-    "author": [
-        "Rosa, Rudolf"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-161;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Fairytale child;Rosa, Rudolf;dialogue system;morphological generation;Treex;morphological analysis;interactive;Fairytale Child is a simple chatbot trying to simulate a curious child. It asks the user to tell a fairy tale, often interrupting to ask for details and clarifications. However, it remembers what it was told and tries to show it if possible.\r\n\r\nThe chatbot can communicate in Czech and in English. It analyzes the morphology of each sentence produced by the user with natural language processing tools, tries to identify potential questions to ask, and then asks one. A morphological generator is employed to generate correctly inflected sentences in Czech, so that the resulting sentences sound as natural as possible.\r\n\r\nPoh\u00e1dkov\u00e9 d\u00edt\u011b je jednoduch\u00fd chatbot, simuluj\u00edc\u00ed zv\u00eddav\u00e9 d\u00edt\u011b. Po\u017e\u00e1d\u00e1 u\u017eivatele, aby mu vypr\u00e1v\u011bl poh\u00e1dku, ale \u010dasto ho p\u0159eru\u0161uje, aby se zeptal na detaily a vysv\u011btlen\u00ed. Pamatuje si ale, co mu u\u017eivatel \u0159ekl, a sna\u017e\u00ed se to pokud mo\u017eno d\u00e1t najevo.\r\n\r\nChatbot um\u00ed komunikovat \u010desky a anglicky. Analyzuje tvaroslov\u00ed ka\u017ed\u00e9 u\u017eivatelovy v\u011bty pomoc\u00ed NLP n\u00e1stroj\u016f, pokus\u00ed se nal\u00e9zt chodnou ot\u00e1zku, a tu pak polo\u017e\u00ed. Aby tvo\u0159en\u00e9 \u010desk\u00e9 v\u011bty zn\u011bly co nejp\u0159irozen\u011bji, vyu\u017e\u00edv\u00e1 se pro sklo\u0148ov\u00e1n\u00ed tvaroslovn\u00fd gener\u00e1tor.;2014-07-24;toolService;http://hdl.handle.net/11234/1-161;eng;ces;http://hdl.handle.net/11234/1-1449;GNU General Public License, version 2;http://www.gnu.org/licenses/gpl-2.0.html;PUB;application/octet-stream;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://ufal.mff.cuni.cz/dite",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "79469373-c04d-5443-8220-30083b2cc95c",
-    "notes": [
-        "Fairytale Child is a simple chatbot trying to simulate a curious child. It asks the user to tell a fairy tale, often interrupting to ask for details and clarifications. However, it remembers what it was told and tries to show it if possible.\r\n\r\nThe chatbot can communicate in Czech and in English. It analyzes the morphology of each sentence produced by the user with natural language processing tools, tries to identify potential questions to ask, and then asks one. A morphological generator is employed to generate correctly inflected sentences in Czech, so that the resulting sentences sound as natural as possible.\r\n\r\nPoh\u00e1dkov\u00e9 d\u00edt\u011b je jednoduch\u00fd chatbot, simuluj\u00edc\u00ed zv\u00eddav\u00e9 d\u00edt\u011b. Po\u017e\u00e1d\u00e1 u\u017eivatele, aby mu vypr\u00e1v\u011bl poh\u00e1dku, ale \u010dasto ho p\u0159eru\u0161uje, aby se zeptal na detaily a vysv\u011btlen\u00ed. Pamatuje si ale, co mu u\u017eivatel \u0159ekl, a sna\u017e\u00ed se to pokud mo\u017eno d\u00e1t najevo.\r\n\r\nChatbot um\u00ed komunikovat \u010desky a anglicky. Analyzuje tvaroslov\u00ed ka\u017ed\u00e9 u\u017eivatelovy v\u011bty pomoc\u00ed NLP n\u00e1stroj\u016f, pokus\u00ed se nal\u00e9zt chodnou ot\u00e1zku, a tu pak polo\u017e\u00ed. Aby tvo\u0159en\u00e9 \u010desk\u00e9 v\u011bty zn\u011bly co nejp\u0159irozen\u011bji, vyu\u017e\u00edv\u00e1 se pro sklo\u0148ov\u00e1n\u00ed tvaroslovn\u00fd gener\u00e1tor."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-161"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "dialogue system"
-        },
-        {
-            "name": "morphological generation"
-        },
-        {
-            "name": "Treex"
-        },
-        {
-            "name": "morphological analysis"
-        },
-        {
-            "name": "interactive"
-        }
-    ],
-    "title": [
-        "Fairytale child"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/794bea20-4e32-55d7-ac7f-47ca7b210201.json b/oaitestdata/clarin-oai_dc/SET_1/json/794bea20-4e32-55d7-ac7f-47ca7b210201.json
deleted file mode 100644
index cf4a98f9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/794bea20-4e32-55d7-ac7f-47ca7b210201.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/7",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/7"
-    ],
-    "PID": "http://hdl.handle.net/11321/7",
-    "PublicationTimestamp": "2012-04-18T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Piasecki, Maciej"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/7;2016-01-19T14:04:26Z;hdl_11321_3;hdl_11321_4;Chunker WS;Piasecki, Maciej;Chunker-WS provides shallow parsing of Polish. The parser may be run against plain text (input format: text, then it runs WCRFT for tagging) or already tagged input (other input formats). Service output will contain tokenisation and tagging, but also boundaries of syntactic phrases as well as phrases' syntactic heads. The service is based on IOBBER, a chunker for Polish. The configuration used here operates on chunk definitions from the KPWr corpus.;2012-04-18;toolService;http://hdl.handle.net/11321/7;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 1;Wroc\u0142aw University of Technology;http://clarin-pl.eu/synat/ws/chunker/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "794bea20-4e32-55d7-ac7f-47ca7b210201",
-    "notes": [
-        "Chunker-WS provides shallow parsing of Polish. The parser may be run against plain text (input format: text, then it runs WCRFT for tagging) or already tagged input (other input formats). Service output will contain tokenisation and tagging, but also boundaries of syntactic phrases as well as phrases' syntactic heads. The service is based on IOBBER, a chunker for Polish. The configuration used here operates on chunk definitions from the KPWr corpus."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/7"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Chunker WS"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/794e812b-18d7-53ec-9525-2308bbfc512b.json b/oaitestdata/clarin-oai_dc/SET_1/json/794e812b-18d7-53ec-9525-2308bbfc512b.json
deleted file mode 100644
index 175ae560..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/794e812b-18d7-53ec-9525-2308bbfc512b.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 3"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4904-2",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4904-2"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-4904-2",
-    "PublicationTimestamp": "2009-11-02T09:22:59Z",
-    "PublicationYear": [
-        "2009"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "PDT 2.0 License",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/license-pdt2",
-        "ACA"
-    ],
-    "author": [
-        "Haji\u010d, Jan"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4904-2;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Feature-based tagger;Haji\u010d, Jan;morphology;tagger;The Feature-based (exponential model) Tagger is a fast implementation of the Czech tagger developed at UFAL and described in the PDT 1.0 documentation (Czech Language Tagging page). In order to get the best possible results, the tagger requires preprocessing by a Czech morphological module with a very high coverage. This module covers a superset of the Czech \"FM\" morphology. Both the morphological module and the tagger are supplied as binary executables, together with all necessary precompiled Czech data. Input must be in the ISO Latin 2 (iso-8859-2) code and follow the csts.dtd definition, and output is produced in the same way (ISO Latin 2 code, csts.dtd). (As is the case with many of the tools provided with PDT 1.0, both executables also accept - and then produce - a \"simplified SGML\", which is not a real, valid SGML, but simply contains at least the tags for words, punctuation, and sentence breaks, one item per line.);2009-11-02T09:22:59Z;toolService;http://hdl.handle.net/11858/00-097C-0000-0001-4904-2;PDT 2.0 License;https://lindat.mff.cuni.cz/repository/xmlui/page/license-pdt2;ACA;application/x-gzip;application/x-gzip;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 3;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/pdt2.0/doc/tools/machine-annotation/index.html#a-ma-tagging",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "794e812b-18d7-53ec-9525-2308bbfc512b",
-    "notes": [
-        "The Feature-based (exponential model) Tagger is a fast implementation of the Czech tagger developed at UFAL and described in the PDT 1.0 documentation (Czech Language Tagging page). In order to get the best possible results, the tagger requires preprocessing by a Czech morphological module with a very high coverage. This module covers a superset of the Czech \"FM\" morphology. Both the morphological module and the tagger are supplied as binary executables, together with all necessary precompiled Czech data. Input must be in the ISO Latin 2 (iso-8859-2) code and follow the csts.dtd definition, and output is produced in the same way (ISO Latin 2 code, csts.dtd). (As is the case with many of the tools provided with PDT 1.0, both executables also accept - and then produce - a \"simplified SGML\", which is not a real, valid SGML, but simply contains at least the tags for words, punctuation, and sentence breaks, one item per line.)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4904-2"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "tagger"
-        }
-    ],
-    "title": [
-        "Feature-based tagger"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/79610213-b15f-5252-b9d9-304263c9fb87.json b/oaitestdata/clarin-oai_dc/SET_1/json/79610213-b15f-5252-b9d9-304263c9fb87.json
deleted file mode 100644
index 9667de4e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/79610213-b15f-5252-b9d9-304263c9fb87.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 378 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1756",
-    "MetadataAccess": [
-        "oai:ota:oucs:1756"
-    ],
-    "PublicationTimestamp": "1906-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1906"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Language resources -- Dictionaries"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Bierce, Ambrose, 1842-1914?"
-    ],
-    "fulltext": "oai:ota:oucs:1756;2018-03-13T17:21:42Z;http://ota.ox.ac.uk/headers/1756.xml;The Devil's dictionary / by Ambrose Bierce;Bierce, Ambrose, 1842-1914?;1906;text_and_corpus_linguistics;Facetiae -- United States -- 20th century;Dictionaries -- United States -- 20th century;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 378 KB);Text;Language resources -- Dictionaries;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "79610213-b15f-5252-b9d9-304263c9fb87",
-    "oai_identifier": [
-        "oai:ota:oucs:1756"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Facetiae -- United States -- th century"
-        },
-        {
-            "name": "Dictionaries -- United States -- th century"
-        }
-    ],
-    "title": [
-        "The Devil's dictionary / by Ambrose Bierce"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1756.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/796d6c74-e5bc-50ca-b577-68ab54bc21f1.json b/oaitestdata/clarin-oai_dc/SET_1/json/796d6c74-e5bc-50ca-b577-68ab54bc21f1.json
deleted file mode 100644
index 411eb47a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/796d6c74-e5bc-50ca-b577-68ab54bc21f1.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-4336-4",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-4336-4"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-4336-4",
-    "PublicationTimestamp": "2014-02-13T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Haji\u010d, Jan"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-4336-4;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Czech Morphological Analyzer v1;Haji\u010d, Jan;morphological analysis;lemmatization;One of the very first steps in automatic processing of Czech text is morphological analysis and lemmatization.;2014-02-13;toolService;http://hdl.handle.net/11858/00-097C-0000-0023-4336-4;ces;downloadable_files_count: 0;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://lindat.mff.cuni.cz/services/morph/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "796d6c74-e5bc-50ca-b577-68ab54bc21f1",
-    "notes": [
-        "One of the very first steps in automatic processing of Czech text is morphological analysis and lemmatization."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-4336-4"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphological analysis"
-        },
-        {
-            "name": "lemmatization"
-        }
-    ],
-    "title": [
-        "Czech Morphological Analyzer v1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7977ac82-a856-50e9-be5e-a5e2ef4f41ba.json b/oaitestdata/clarin-oai_dc/SET_1/json/7977ac82-a856-50e9-be5e-a5e2ef4f41ba.json
deleted file mode 100644
index 45ee48b4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7977ac82-a856-50e9-be5e-a5e2ef4f41ba.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Czech",
-        "English",
-        "German",
-        "Vietnamese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1046",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1046"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1046",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1046;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;L2 Acquisition Barbara Schmiedtova;Language Acquisition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1046;ces;eng;deu;vie;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI23962%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7977ac82-a856-50e9-be5e-a5e2ef4f41ba",
-    "notes": [
-        "Language Acquisition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1046"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "L2 Acquisition Barbara Schmiedtova"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/798982c6-d17f-5f89-94be-210a1a38c859.json b/oaitestdata/clarin-oai_dc/SET_1/json/798982c6-d17f-5f89-94be-210a1a38c859.json
deleted file mode 100644
index 7ea113e8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/798982c6-d17f-5f89-94be-210a1a38c859.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Heath, Jeffrey"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 135 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0936",
-    "MetadataAccess": [
-        "oai:ota:oucs:0936"
-    ],
-    "PublicationTimestamp": "1979-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1979"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Dictionaries"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:0936;2018-02-28T17:09:17Z;http://ota.ox.ac.uk/headers/0936.xml;Nunggubuyu wordlist;1979;text_and_corpus_linguistics;Nunggubuyu (Australian people)  -- Languages;nuy;eng;Oxford Text Archive, University of Oxford;Heath, Jeffrey;Heath, Jeffrey;text/plain;(1 file : ca. 135 KB);Text;Dictionaries;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "798982c6-d17f-5f89-94be-210a1a38c859",
-    "oai_identifier": [
-        "oai:ota:oucs:0936"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Nunggubuyu Australian people -- Languages"
-        }
-    ],
-    "title": [
-        "Nunggubuyu wordlist"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0936.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/79a72951-72c0-530b-ac92-5b78dac55fc0.json b/oaitestdata/clarin-oai_dc/SET_1/json/79a72951-72c0-530b-ac92-5b78dac55fc0.json
deleted file mode 100644
index d991a4a5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/79a72951-72c0-530b-ac92-5b78dac55fc0.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "A"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1707",
-    "MetadataAccess": [
-        "oai:ota:oucs:1707"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Collections, corpora etc"
-    ],
-    "fulltext": "oai:ota:oucs:1707;2018-04-16T15:30:51Z;http://ota.ox.ac.uk/headers/1707.xml;Ancient Hebrew inscriptions;Collections, corpora etc;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;A;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "79a72951-72c0-530b-ac92-5b78dac55fc0",
-    "oai_identifier": [
-        "oai:ota:oucs:1707"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Ancient Hebrew inscriptions"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1707.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/79b4e14a-d09d-54ed-b206-82bc268e7c23.json b/oaitestdata/clarin-oai_dc/SET_1/json/79b4e14a-d09d-54ed-b206-82bc268e7c23.json
deleted file mode 100644
index 04f84c39..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/79b4e14a-d09d-54ed-b206-82bc268e7c23.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/18",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/18"
-    ],
-    "PID": "http://hdl.handle.net/11321/18",
-    "PublicationTimestamp": "2011-12-12T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Janicki, Maciej",
-        "Marci\u0144czuk, Micha\u0142",
-        "Koco\u0144, Jan"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/18;2016-01-21T14:21:12Z;hdl_11321_3;hdl_11321_4;Liner2;Marci\u0144czuk, Micha\u0142;Koco\u0144, Jan;Janicki, Maciej;Rozpoznaje nazwy w\u0142asne w tek\u015bcie polskim.;2011-12-12;toolService;http://hdl.handle.net/11321/18;pol;downloadable_files_count: 0;Wroc\u0142aw University of Technology;http://nlp.pwr.wroc.pl/en/tools-and-resources/liner2-installation",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "79b4e14a-d09d-54ed-b206-82bc268e7c23",
-    "notes": [
-        "Rozpoznaje nazwy w\u0142asne w tek\u015bcie polskim."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/18"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Liner2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/79b7afb7-e5a4-57a4-9208-aaa1e1509875.json b/oaitestdata/clarin-oai_dc/SET_1/json/79b7afb7-e5a4-57a4-9208-aaa1e1509875.json
deleted file mode 100644
index efd4600e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/79b7afb7-e5a4-57a4-9208-aaa1e1509875.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 9.46 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2113",
-    "MetadataAccess": [
-        "oai:ota:oucs:2113"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Blake, William, 1757-1827"
-    ],
-    "fulltext": "oai:ota:oucs:2113;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/2113.xml;Poems. Selections;The book of Thel / by William Blake;Blake, William, 1757-1827;text_and_corpus_linguistics;Poems -- Great Britain -- 18th century;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 9.46 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "79b7afb7-e5a4-57a4-9208-aaa1e1509875",
-    "oai_identifier": [
-        "oai:ota:oucs:2113"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Poems. Selections",
-        "The book of Thel / by William Blake"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2113.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/79d42ffa-cea4-57f0-a090-5587310035c5.json b/oaitestdata/clarin-oai_dc/SET_1/json/79d42ffa-cea4-57f0-a090-5587310035c5.json
deleted file mode 100644
index 7ee56156..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/79d42ffa-cea4-57f0-a090-5587310035c5.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/40",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/40"
-    ],
-    "PID": "http://hdl.handle.net/11321/40",
-    "PublicationTimestamp": "2012-06-18T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "K\u0119dzia, Pawe\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/40;2016-01-21T14:17:51Z;hdl_11321_3;hdl_11321_4;LexCSD;K\u0119dzia, Pawe\u0142;Dostarcza wsp\u00f3lny interfejs dla kilku pakiet\u00f3w zawieraj\u0105cych klasyfikatory, m.in. Weka, TiMBL, chyba te\u017c Orange i NLTK.;2012-06-18;toolService;http://hdl.handle.net/11321/40;pol;downloadable_files_count: 0;Wroc\u0142aw University of Technology;http://nlp.pwr.wroc.pl/pl/narzedzia-i-zasoby/lexcsd",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "79d42ffa-cea4-57f0-a090-5587310035c5",
-    "notes": [
-        "Dostarcza wsp\u00f3lny interfejs dla kilku pakiet\u00f3w zawieraj\u0105cych klasyfikatory, m.in. Weka, TiMBL, chyba te\u017c Orange i NLTK."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/40"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "LexCSD"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/79d6b7da-55db-5bb1-8855-4f218af06c36.json b/oaitestdata/clarin-oai_dc/SET_1/json/79d6b7da-55db-5bb1-8855-4f218af06c36.json
deleted file mode 100644
index 4792a2cc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/79d6b7da-55db-5bb1-8855-4f218af06c36.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Pistol, Ionut"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Romanian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-496",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-496"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-496",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Romania"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-496;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Romanian stopwords;Pistol, Ionut;Aprox 500 entries, txt;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-496;ron;downloadable_files_count: 0;Romania;http://consilr.info.uaic.ro/2014/index.php",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "79d6b7da-55db-5bb1-8855-4f218af06c36",
-    "notes": [
-        "Aprox 500 entries, txt"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-496"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Romanian stopwords"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7a282609-84f9-5831-90db-dcc5e4f656a0.json b/oaitestdata/clarin-oai_dc/SET_1/json/7a282609-84f9-5831-90db-dcc5e4f656a0.json
deleted file mode 100644
index 96936771..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7a282609-84f9-5831-90db-dcc5e4f656a0.json
+++ /dev/null
@@ -1,96 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/542",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/542"
-    ],
-    "PID": "http://hdl.handle.net/11321/542",
-    "PublicationTimestamp": "2018-07-23T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Janicki, Maciej",
-        "Koco\u0144, Jan",
-        "Marci\u0144czuk, Micha\u0142",
-        "Piasecki, Dominik",
-        "Kaczmarek, Adam",
-        "Krautforst, Micha\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/542;2018-07-23T10:47:12Z;hdl_11321_3;hdl_11321_4;Liner2.5;Marci\u0144czuk, Micha\u0142;Koco\u0144, Jan;Kaczmarek, Adam;Krautforst, Micha\u0142;Piasecki, Dominik;Janicki, Maciej;Liner2;NER;information extraction;named entites;temporal expressions;spatial expressions;events;relation extraction;Generic framework for information extraction tasks, including recognition of named entities, temporal expressions, spatial expressions and events.;2018-07-23;toolService;http://hdl.handle.net/11321/542;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;Wroc\u0142aw University of Science and Technology;http://nlp.pwr.wroc.pl/liner2",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7a282609-84f9-5831-90db-dcc5e4f656a0",
-    "notes": [
-        "Generic framework for information extraction tasks, including recognition of named entities, temporal expressions, spatial expressions and events."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/542"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Liner"
-        },
-        {
-            "name": "NER"
-        },
-        {
-            "name": "information extraction"
-        },
-        {
-            "name": "named entites"
-        },
-        {
-            "name": "temporal expressions"
-        },
-        {
-            "name": "spatial expressions"
-        },
-        {
-            "name": "events"
-        },
-        {
-            "name": "relation extraction"
-        }
-    ],
-    "title": [
-        "Liner2.5"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7a3136fc-2eda-59ea-910c-124c4a7b2da7.json b/oaitestdata/clarin-oai_dc/SET_1/json/7a3136fc-2eda-59ea-910c-124c4a7b2da7.json
deleted file mode 100644
index aa805e42..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7a3136fc-2eda-59ea-910c-124c4a7b2da7.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/554",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/554"
-    ],
-    "PID": "http://hdl.handle.net/11321/554",
-    "PublicationTimestamp": "2018-07-24T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "plWordNet",
-        "http://clarin-pl.eu/en/licenses/plwordnet-2/",
-        "PUB"
-    ],
-    "author": [
-        "Wroclaw University of Technology"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/554;2018-07-24T15:25:48Z;hdl_11321_3;hdl_11321_4;plWordNet 4.0;Wroclaw University of Technology;plWordNet;lexical unit;lexico-semantic relations;mapping;Princeton WordNet;bilingual;PLWordNet ver. 4.0 is a lexico-semantic network which reflects the lexical system of the Polish language with projection to the English language. S\u0142owosie\u0107, Princeton Wordnet, EnWordnet together the whole resource currently contains  506815 senses, 347564 synsets and over 1.5M relations and 361177 inter-lingual relations between lexical units. It is now the largest wordnet in the world and is still growing.;2018-07-24;lexicalConceptualResource;http://hdl.handle.net/11321/554;pol;eng;plWordNet;http://clarin-pl.eu/en/licenses/plwordnet-2/;PUB;text/plain; charset=utf-8;application/zip;application/zip;downloadable_files_count: 2;Wroc\u0142aw University of Technology;http://plwordnet.pwr.wroc.pl/wordnet/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7a3136fc-2eda-59ea-910c-124c4a7b2da7",
-    "notes": [
-        "PLWordNet ver. 4.0 is a lexico-semantic network which reflects the lexical system of the Polish language with projection to the English language. S\u0142owosie\u0107, Princeton Wordnet, EnWordnet together the whole resource currently contains  506815 senses, 347564 synsets and over 1.5M relations and 361177 inter-lingual relations between lexical units. It is now the largest wordnet in the world and is still growing."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/554"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "plWordNet"
-        },
-        {
-            "name": "lexical unit"
-        },
-        {
-            "name": "lexico-semantic relations"
-        },
-        {
-            "name": "mapping"
-        },
-        {
-            "name": "Princeton WordNet"
-        },
-        {
-            "name": "bilingual"
-        }
-    ],
-    "title": [
-        "plWordNet 4.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7a47c09c-78de-5e11-87b2-fc74032d86a9.json b/oaitestdata/clarin-oai_dc/SET_1/json/7a47c09c-78de-5e11-87b2-fc74032d86a9.json
deleted file mode 100644
index c8244832..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7a47c09c-78de-5e11-87b2-fc74032d86a9.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Charles University in Prague, \u00da\u010cJTK"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1741",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1741"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1741",
-    "PublicationTimestamp": "2016-06-09T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University in Prague, \u00da\u010cJTK"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Letafkov\u00e1, Jana",
-        "Jel\u00ednkov\u00e1, Blanka",
-        "Gol\u00e1\u0148ov\u00e1, Hana",
-        "\u0160ebesta, Karel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1741;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;AKCES 1;\u0160ebesta, Karel;Gol\u00e1\u0148ov\u00e1, Hana;Letafkov\u00e1, Jana;Jel\u00ednkov\u00e1, Blanka;youth language;written language;Corpus AKCES 1 includes texts written in czech by youth (native speakers); it is the same data as the corpus SKRIPT 2012;2016-06-09;corpus;http://hdl.handle.net/11234/1-1741;ces;Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0);http://creativecommons.org/licenses/by-nc-nd/3.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University in Prague, \u00da\u010cJTK;http://akces.ff.cuni.cz",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7a47c09c-78de-5e11-87b2-fc74032d86a9",
-    "notes": [
-        "Corpus AKCES 1 includes texts written in czech by youth (native speakers); it is the same data as the corpus SKRIPT 2012"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1741"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "youth language"
-        },
-        {
-            "name": "written language"
-        }
-    ],
-    "title": [
-        "AKCES 1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7a587fc7-3b68-5c4e-b341-b4f757249bca.json b/oaitestdata/clarin-oai_dc/SET_1/json/7a587fc7-3b68-5c4e-b341-b4f757249bca.json
deleted file mode 100644
index 307c3523..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7a587fc7-3b68-5c4e-b341-b4f757249bca.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Smith, John B."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(2 files : ca. 387, 391 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1656",
-    "MetadataAccess": [
-        "oai:ota:oucs:1656"
-    ],
-    "PublicationTimestamp": "1927-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1927"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Woolf, Virginia, 1882-1941"
-    ],
-    "fulltext": "oai:ota:oucs:1656;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/1656.xml;To the lighthouse / Virginia Woolf;Woolf, Virginia, 1882-1941;1927;text_and_corpus_linguistics;English fiction -- 20th century;eng;Oxford Text Archive, University of Oxford;Smith, John B.;text/sgml;(2 files : ca. 387, 391 KB);Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7a587fc7-3b68-5c4e-b341-b4f757249bca",
-    "oai_identifier": [
-        "oai:ota:oucs:1656"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English fiction -- th century"
-        }
-    ],
-    "title": [
-        "To the lighthouse / Virginia Woolf"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1656.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7a68d966-febc-5bfb-8cd9-78465e4683c8.json b/oaitestdata/clarin-oai_dc/SET_1/json/7a68d966-febc-5bfb-8cd9-78465e4683c8.json
deleted file mode 100644
index bfd8dbfd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7a68d966-febc-5bfb-8cd9-78465e4683c8.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Natural Language Processing Centre, Faculty of Informatics, Masaryk University"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/x-xz"
-    ],
-    "Language": [
-        "Indonesian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2586",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2586"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2586",
-    "PublicationTimestamp": "2017-12-18T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Natural Language Processing Centre, Faculty of Informatics, Masaryk University"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "NLP Centre Web Corpus License",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/license-NLPC-WeC",
-        "ACA"
-    ],
-    "author": [
-        "Suchomel, V\u00edt",
-        "Medve\u010f, Marek"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2586;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Indonesian web corpus (idWac);Medve\u010f, Marek;Suchomel, V\u00edt;corpus;lemmatization;PoS tagging;Indonesian text corpus from web. Crawling done by SpiderLing in 2017. Filtering by JusText and Onion (see http://corpus.tools/ for details). Tagged and lemmatized by MorphInd (http://septinalarasati.com/morphind/).;2017-12-18;corpus;http://hdl.handle.net/11234/1-2586;ind;NLP Centre Web Corpus License;https://lindat.mff.cuni.cz/repository/xmlui/page/license-NLPC-WeC;ACA;application/x-xz;text/plain; charset=utf-8;downloadable_files_count: 1;Natural Language Processing Centre, Faculty of Informatics, Masaryk University",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7a68d966-febc-5bfb-8cd9-78465e4683c8",
-    "notes": [
-        "Indonesian text corpus from web. Crawling done by SpiderLing in 2017. Filtering by JusText and Onion (see http://corpus.tools/ for details). Tagged and lemmatized by MorphInd (http://septinalarasati.com/morphind/)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2586"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "lemmatization"
-        },
-        {
-            "name": "PoS tagging"
-        }
-    ],
-    "title": [
-        "Indonesian web corpus (idWac)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7a6cca2d-344f-5987-b569-4bc72ff3a6c1.json b/oaitestdata/clarin-oai_dc/SET_1/json/7a6cca2d-344f-5987-b569-4bc72ff3a6c1.json
deleted file mode 100644
index 0fae7a13..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7a6cca2d-344f-5987-b569-4bc72ff3a6c1.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Ule, Louis"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 2 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1625",
-    "MetadataAccess": [
-        "oai:ota:oucs:1625"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Marlowe, Christopher, 1564-1593"
-    ],
-    "fulltext": "oai:ota:oucs:1625;2018-02-16T10:42:06Z;http://ota.ox.ac.uk/headers/1625.xml;Passionate shepherd to his love / Christopher Marlowe;Marlowe, Christopher, 1564-1593;text_and_corpus_linguistics;English poetry -- Early modern, 1500-1700;Oxford Text Archive, University of Oxford;Ule, Louis;text/sgml;(1 file : ca. 2 KB);Text;Poems;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7a6cca2d-344f-5987-b569-4bc72ff3a6c1",
-    "oai_identifier": [
-        "oai:ota:oucs:1625"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English poetry -- Early modern"
-        }
-    ],
-    "title": [
-        "Passionate shepherd to his love / Christopher Marlowe"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1625.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7a6d99ed-afeb-5664-b8ed-04a0b49ccb69.json b/oaitestdata/clarin-oai_dc/SET_1/json/7a6d99ed-afeb-5664-b8ed-04a0b49ccb69.json
deleted file mode 100644
index 3278d202..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7a6d99ed-afeb-5664-b8ed-04a0b49ccb69.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Dell, Thomas"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 174 KB)",
-        "text/plain"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1869",
-    "MetadataAccess": [
-        "oai:ota:oucs:1869"
-    ],
-    "PublicationTimestamp": "1903-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1903"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "London, Jack, 1876-1916"
-    ],
-    "fulltext": "oai:ota:oucs:1869;2018-04-11T16:03:39Z;http://ota.ox.ac.uk/headers/1869.xml;The call of the wild / Jack London;London, Jack, 1876-1916;1903;text_and_corpus_linguistics;American fiction -- 20th century;Oxford Text Archive, University of Oxford;Dell, Thomas;text/plain;(1 file : ca. 174 KB);Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7a6d99ed-afeb-5664-b8ed-04a0b49ccb69",
-    "oai_identifier": [
-        "oai:ota:oucs:1869"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "American fiction -- th century"
-        }
-    ],
-    "title": [
-        "The call of the wild / Jack London"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1869.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7a87a226-2540-523b-8d13-239564e28ac8.json b/oaitestdata/clarin-oai_dc/SET_1/json/7a87a226-2540-523b-8d13-239564e28ac8.json
deleted file mode 100644
index 6a4fc39a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7a87a226-2540-523b-8d13-239564e28ac8.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "Hindi"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-909",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-909"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-909",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-909;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Hindi;ca. 7.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-909;hin;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#hind",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7a87a226-2540-523b-8d13-239564e28ac8",
-    "notes": [
-        "ca. 7.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-909"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Hindi"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7a8ff9b1-fbf5-56d8-affb-8e979959d6d5.json b/oaitestdata/clarin-oai_dc/SET_1/json/7a8ff9b1-fbf5-56d8-affb-8e979959d6d5.json
deleted file mode 100644
index fb115046..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7a8ff9b1-fbf5-56d8-affb-8e979959d6d5.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Arts, Institute of the Czech National Corpus, Charles University in Prague"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-119F-6",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-119F-6"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-119F-6",
-    "PublicationTimestamp": "2010-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "Faculty of Arts, Institute of the Czech National Corpus, Charles University in Prague"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Czech National Corpus (Shuffled Corpus Data)",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/license-cnc",
-        "ACA"
-    ],
-    "author": [
-        "Hn\u00e1tkov\u00e1, Milena",
-        "Petkevi\u010d, Vladim\u00edr",
-        "Kocek, Jan",
-        "Proch\u00e1zka, Pavel",
-        "Schmiedtov\u00e1, V\u011bra",
-        "Barto\u0148, Tom\u00e1\u0161",
-        "K\u0159en, Michal",
-        "Jel\u00ednek, Tom\u00e1\u0161",
-        "Novotn\u00e1, Renata",
-        "Skoumalov\u00e1, Hana",
-        "Cvr\u010dek, V\u00e1clav"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-119F-6;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;SYN2010: balanced corpus of written Czech;K\u0159en, Michal;Barto\u0148, Tom\u00e1\u0161;Cvr\u010dek, V\u00e1clav;Hn\u00e1tkov\u00e1, Milena;Jel\u00ednek, Tom\u00e1\u0161;Kocek, Jan;Novotn\u00e1, Renata;Petkevi\u010d, Vladim\u00edr;Proch\u00e1zka, Pavel;Schmiedtov\u00e1, V\u011bra;Skoumalov\u00e1, Hana;balanced corpus;written language;Balanced corpus of contemporary written Czech sized 100 MW. It was created as a representation of written language from 2005\u20132009 and thus it contains a wide range of text types and genres (fiction, professional literature, newspapers etc.) in balanced proportions. The corpus is lemmatized and morphologically tagged by a combination of stochastic and rule-based methods.\r\nThe corpus is provided in a (semi-XML) vertical format used as an input to the Manatee query engine. The data thus correspond to the corpus available via query interface to registered users of the CNC with one important exception: they are shuffled, i.e. divided into blocks sized max. 100 words (respecting the sentence boundaries) whose ordering was randomized within the given document.;2010;corpus;http://hdl.handle.net/11858/00-097C-0000-0023-119F-6;ces;Czech National Corpus (Shuffled Corpus Data);https://lindat.mff.cuni.cz/repository/xmlui/page/license-cnc;ACA;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Faculty of Arts, Institute of the Czech National Corpus, Charles University in Prague;https://wiki.korpus.cz/doku.php/cnk:syn2010",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7a8ff9b1-fbf5-56d8-affb-8e979959d6d5",
-    "notes": [
-        "Balanced corpus of contemporary written Czech sized 100 MW. It was created as a representation of written language from 2005\u20132009 and thus it contains a wide range of text types and genres (fiction, professional literature, newspapers etc.) in balanced proportions. The corpus is lemmatized and morphologically tagged by a combination of stochastic and rule-based methods.\r\nThe corpus is provided in a (semi-XML) vertical format used as an input to the Manatee query engine. The data thus correspond to the corpus available via query interface to registered users of the CNC with one important exception: they are shuffled, i.e. divided into blocks sized max. 100 words (respecting the sentence boundaries) whose ordering was randomized within the given document."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-119F-6"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "balanced corpus"
-        },
-        {
-            "name": "written language"
-        }
-    ],
-    "title": [
-        "SYN2010: balanced corpus of written Czech"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7ad22198-df78-5885-83d0-cc92f83b20e9.json b/oaitestdata/clarin-oai_dc/SET_1/json/7ad22198-df78-5885-83d0-cc92f83b20e9.json
deleted file mode 100644
index 4c75f726..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7ad22198-df78-5885-83d0-cc92f83b20e9.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1398",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1398"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1398",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1398;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;html2text;Format conversion service: .html to .txt converter;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1398;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7ad22198-df78-5885-83d0-cc92f83b20e9",
-    "notes": [
-        "Format conversion service: .html to .txt converter"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1398"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "html2text"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7b09efb5-7e8f-564d-a820-d95e8eef251f.json b/oaitestdata/clarin-oai_dc/SET_1/json/7b09efb5-7e8f-564d-a820-d95e8eef251f.json
deleted file mode 100644
index 20a1f25f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7b09efb5-7e8f-564d-a820-d95e8eef251f.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Archives of Latvian Folklore, Institute of Literature, Folklore and Art, University of Latvia",
-        "Institute of Mathematics and Computer Science, University of Latvia"
-    ],
-    "Contributor": [
-        "B\u0113rzi\u0146a-Reinsone, Sanita"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Latvian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-622",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-622"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-622",
-    "PublicationTimestamp": "2005-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2005"
-    ],
-    "Publisher": [
-        "Archives of Latvian Folklore, Institute of Literature, Folklore and Art, University of Latvia",
-        "Institute of Mathematics and Computer Science, University of Latvia"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Latvia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-622;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Collection of Latvian proverbs;B\u0113rzi\u0146a-Reinsone, Sanita;Latvian proverbs collected by Archives of Latvian Folklore (~ 20 000 items);2005;corpus;http://hdl.handle.net/11372/LRT-622;lav;downloadable_files_count: 0;Latvia;Archives of Latvian Folklore, Institute of Literature, Folklore and Art, University of Latvia;Institute of Mathematics and Computer Science, University of Latvia;http://valoda.ailab.lv/folklora/sakamvardi/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7b09efb5-7e8f-564d-a820-d95e8eef251f",
-    "notes": [
-        "Latvian proverbs collected by Archives of Latvian Folklore (~ 20 000 items)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-622"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Collection of Latvian proverbs"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7b27d83a-4057-5d67-85b4-2780321c31b3.json b/oaitestdata/clarin-oai_dc/SET_1/json/7b27d83a-4057-5d67-85b4-2780321c31b3.json
deleted file mode 100644
index b98fc648..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7b27d83a-4057-5d67-85b4-2780321c31b3.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0007-70FD-E",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0007-70FD-E"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0007-70FD-E",
-    "PublicationTimestamp": "2006-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2006"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU General Public License, version 2",
-        "http://www.gnu.org/licenses/gpl-2.0.html",
-        "PUB"
-    ],
-    "author": [
-        "Zeman, Daniel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0007-70FD-E;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;DZ Interset;Zeman, Daniel;morphology;NLP;Perl;DZ Interset is a means of converting among various tag sets in natural language processing. The core idea is similar to interlingua-based machine translation. DZ Interset defines a set of features that are encoded by the various tag sets. The set of features should be as universal as possible. It does not need to encode everything that is encoded by any tag set but it should encode all information that people may want to access and/or port from one tag set to another.\r\n\r\nNew tag sets are attached by writing a driver for them. Once the driver is ready, you can easily convert tags between the new set and any other set for which you also have a driver. This reusability is an obvious advantage over writing a targeted conversion procedure each time you need to convert between a particular pair of tag sets.;2006-06;toolService;http://hdl.handle.net/11858/00-097C-0000-0007-70FD-E;GNU General Public License, version 2;http://www.gnu.org/licenses/gpl-2.0.html;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://wiki.ufal.ms.mff.cuni.cz/user:zeman:interset",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7b27d83a-4057-5d67-85b4-2780321c31b3",
-    "notes": [
-        "DZ Interset is a means of converting among various tag sets in natural language processing. The core idea is similar to interlingua-based machine translation. DZ Interset defines a set of features that are encoded by the various tag sets. The set of features should be as universal as possible. It does not need to encode everything that is encoded by any tag set but it should encode all information that people may want to access and/or port from one tag set to another.\r\n\r\nNew tag sets are attached by writing a driver for them. Once the driver is ready, you can easily convert tags between the new set and any other set for which you also have a driver. This reusability is an obvious advantage over writing a targeted conversion procedure each time you need to convert between a particular pair of tag sets."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0007-70FD-E"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "NLP"
-        },
-        {
-            "name": "Perl"
-        }
-    ],
-    "title": [
-        "DZ Interset"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7b3e9091-3cbd-50fe-9349-19597f2ec0d3.json b/oaitestdata/clarin-oai_dc/SET_1/json/7b3e9091-3cbd-50fe-9349-19597f2ec0d3.json
deleted file mode 100644
index a09151f9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7b3e9091-3cbd-50fe-9349-19597f2ec0d3.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/47",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/47"
-    ],
-    "PID": "http://hdl.handle.net/10794/47",
-    "PublicationTimestamp": "2012-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/47;2017-10-27T06:34:14Z;hdl_10794_1;hdl_10794_2;WordNet-SALDO (2017-10-16);WordNet-SALDO (2017-10-16);n/a, n/a;Swedish;Core WordNet;Bilingual;A linking between SALDO senses and Core WordNet.;En l\u00e4nkning mellan SALDO-betydelser och Core WordNet.;2012-05-30;lexicalConceptualResource;http://hdl.handle.net/10794/47;swe;eng;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;http://creativecommons.org/licenses/by/4.0/;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/wordnet-saldo",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7b3e9091-3cbd-50fe-9349-19597f2ec0d3",
-    "notes": [
-        "A linking between SALDO senses and Core WordNet.",
-        "En l\u00e4nkning mellan SALDO-betydelser och Core WordNet."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/47"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Core WordNet"
-        },
-        {
-            "name": "Bilingual"
-        }
-    ],
-    "title": [
-        "WordNet-SALDO (2017-10-16)",
-        "WordNet-SALDO (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7b45ff19-d228-5093-b2cb-3c1bb3bde218.json b/oaitestdata/clarin-oai_dc/SET_1/json/7b45ff19-d228-5093-b2cb-3c1bb3bde218.json
deleted file mode 100644
index 7299be3e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7b45ff19-d228-5093-b2cb-3c1bb3bde218.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4167",
-    "MetadataAccess": [
-        "oai:ota:oucs:4167"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Holcroft, Thomas, 1745-1809."
-    ],
-    "fulltext": "oai:ota:oucs:4167;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4167.xml;Seduction: a comedy: As it is performed at the Theatre-Royal in Drury-Lane. By Thomas Holcroft.;Holcroft, Thomas, 1745-1809.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7b45ff19-d228-5093-b2cb-3c1bb3bde218",
-    "oai_identifier": [
-        "oai:ota:oucs:4167"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Seduction: a comedy: As it is performed at the Theatre-Royal in Drury-Lane. By Thomas Holcroft."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4167.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7b50f770-5787-59dc-abd6-aa9c474e0906.json b/oaitestdata/clarin-oai_dc/SET_1/json/7b50f770-5787-59dc-abd6-aa9c474e0906.json
deleted file mode 100644
index 022707e0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7b50f770-5787-59dc-abd6-aa9c474e0906.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "ATILF"
-    ],
-    "Contributor": [
-        "Petitjean, Etienne"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "French"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-177",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-177"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-177",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "ATILF"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "France"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-177;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Frantext;Petitjean, Etienne;mainly literature (17th to 20th century);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-177;fra;downloadable_files_count: 0;France;ATILF;http://www.cnrtl.fr/corpus/frantext/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7b50f770-5787-59dc-abd6-aa9c474e0906",
-    "notes": [
-        "mainly literature (17th to 20th century)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-177"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Frantext"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7b7e045b-c227-5257-84d5-1b9cb7fdd363.json b/oaitestdata/clarin-oai_dc/SET_1/json/7b7e045b-c227-5257-84d5-1b9cb7fdd363.json
deleted file mode 100644
index 0c457786..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7b7e045b-c227-5257-84d5-1b9cb7fdd363.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "IPIPAN"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/386",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/386"
-    ],
-    "PID": "http://hdl.handle.net/11321/386",
-    "PublicationTimestamp": "2017-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "IPIPAN"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "plWordNet",
-        "http://clarin-pl.eu/en/licenses/plwordnet-2/",
-        "PUB"
-    ],
-    "author": [
-        "Kowalska, Anna"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/386;2017-05-30T11:54:54Z;hdl_11321_3;hdl_11321_4;Dzikie ziele;Kowalska, Anna;story;Polish stories;2017-05-30;corpus;http://hdl.handle.net/11321/386;pol;plWordNet;http://clarin-pl.eu/en/licenses/plwordnet-2/;PUB;text/plain; charset=utf-8;application/vnd.openxmlformats-officedocument.wordprocessingml.document;downloadable_files_count: 1;IPIPAN",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7b7e045b-c227-5257-84d5-1b9cb7fdd363",
-    "notes": [
-        "Polish stories"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/386"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "story"
-        }
-    ],
-    "title": [
-        "Dzikie ziele"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7b805eb8-7b16-5573-995f-a960a9edec8a.json b/oaitestdata/clarin-oai_dc/SET_1/json/7b805eb8-7b16-5573-995f-a960a9edec8a.json
deleted file mode 100644
index 1cb39547..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7b805eb8-7b16-5573-995f-a960a9edec8a.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3818",
-    "MetadataAccess": [
-        "oai:ota:oucs:3818"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Thomson, James, 1700-1748."
-    ],
-    "fulltext": "oai:ota:oucs:3818;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3818.xml;The castle of indolence: an allegorical poem. Written in imitation of Spenser. By James Thomson.;Thomson, James, 1700-1748.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7b805eb8-7b16-5573-995f-a960a9edec8a",
-    "oai_identifier": [
-        "oai:ota:oucs:3818"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The castle of indolence: an allegorical poem. Written in imitation of Spenser. By James Thomson."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3818.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7b823c79-5c10-5554-b84a-042679a0712d.json b/oaitestdata/clarin-oai_dc/SET_1/json/7b823c79-5c10-5554-b84a-042679a0712d.json
deleted file mode 100644
index 58874c7a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7b823c79-5c10-5554-b84a-042679a0712d.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Kaluzi\u0144ska"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 5",
-        "text/plain; charset=utf-8",
-        "text/plain",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/243",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/243"
-    ],
-    "PID": "http://hdl.handle.net/11321/243",
-    "PublicationTimestamp": "2016-01-27T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Kaluzi\u0144ska"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Ka, Emilia"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/243;2017-04-04T10:15:15Z;hdl_11321_3;hdl_11321_4;Tekst reklam TVP ABC ver.2;Ka, Emilia;reklama;tekst reklam emitowanych na tvp abc;2016-01-27;corpus;http://hdl.handle.net/11321/243;pol;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;text/plain; charset=utf-8;text/plain;application/zip;application/zip;application/zip;application/zip;downloadable_files_count: 5;Kaluzi\u0144ska",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7b823c79-5c10-5554-b84a-042679a0712d",
-    "notes": [
-        "tekst reklam emitowanych na tvp abc"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/243"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "reklama"
-        }
-    ],
-    "title": [
-        "Tekst reklam TVP ABC ver.2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7b893c2f-f7d0-58b8-9c34-1bef7f3f2644.json b/oaitestdata/clarin-oai_dc/SET_1/json/7b893c2f-f7d0-58b8-9c34-1bef7f3f2644.json
deleted file mode 100644
index 2343119a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7b893c2f-f7d0-58b8-9c34-1bef7f3f2644.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Masaryk University, NLP Centre"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-CCCF-C",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-CCCF-C"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-CCCF-C",
-    "PublicationTimestamp": "2011-12-15T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Masaryk University, NLP Centre"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/3.0/",
-        "PUB"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-CCCF-C;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;czes;Czech corpus large;First version of the very large Czech corpus Czes created with a new set of tools. It comprises 465,102,710 tokens.;2011-12-15;corpus;http://hdl.handle.net/11858/00-097C-0000-0001-CCCF-C;ces;Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0);http://creativecommons.org/licenses/by-nc-nd/3.0/;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Masaryk University, NLP Centre",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7b893c2f-f7d0-58b8-9c34-1bef7f3f2644",
-    "notes": [
-        "First version of the very large Czech corpus Czes created with a new set of tools. It comprises 465,102,710 tokens."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-CCCF-C"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Czech corpus large"
-        }
-    ],
-    "title": [
-        "czes"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7b8a2574-4958-5ddd-a8ad-478e94bb3b81.json b/oaitestdata/clarin-oai_dc/SET_1/json/7b8a2574-4958-5ddd-a8ad-478e94bb3b81.json
deleted file mode 100644
index 45c0029c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7b8a2574-4958-5ddd-a8ad-478e94bb3b81.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2859",
-    "MetadataAccess": [
-        "oai:ota:oucs:2859"
-    ],
-    "PublicationTimestamp": "1734-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1734"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2859;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2859.xml;Prefatory letter to Mrs. Barber's Poems;Swift, Jonathan, 1667-1745;1734;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7b8a2574-4958-5ddd-a8ad-478e94bb3b81",
-    "oai_identifier": [
-        "oai:ota:oucs:2859"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Prefatory letter to Mrs. Barber's Poems"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2859.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7baaf794-8da8-5374-80a2-ffd1324c5de0.json b/oaitestdata/clarin-oai_dc/SET_1/json/7baaf794-8da8-5374-80a2-ffd1324c5de0.json
deleted file mode 100644
index 43020f66..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7baaf794-8da8-5374-80a2-ffd1324c5de0.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "ING Bank"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/417",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/417"
-    ],
-    "PID": "http://hdl.handle.net/11321/417",
-    "PublicationTimestamp": "2017-07-19T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "ING Bank"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/3.0/",
-        "CC"
-    ],
-    "author": [
-        "anonymous, anonymous"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/417;2017-07-19T15:43:08Z;hdl_11321_3;hdl_11321_4;Korpus forum klient\u00f3w banku;anonymous, anonymous;bank;Corpus of ING Bank forum posts;2017-07-19;corpus;http://hdl.handle.net/11321/417;pol;Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0);http://creativecommons.org/licenses/by-nc-nd/3.0/;CC;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;ING Bank",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7baaf794-8da8-5374-80a2-ffd1324c5de0",
-    "notes": [
-        "Corpus of ING Bank forum posts"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/417"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "bank"
-        }
-    ],
-    "title": [
-        "Korpus forum klient\u00f3w banku"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7bafbf8f-4431-58d5-851a-f34e95535c78.json b/oaitestdata/clarin-oai_dc/SET_1/json/7bafbf8f-4431-58d5-851a-f34e95535c78.json
deleted file mode 100644
index e041f45e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7bafbf8f-4431-58d5-851a-f34e95535c78.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3731",
-    "MetadataAccess": [
-        "oai:ota:oucs:3731"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Blair, Hugh, 1718-1800."
-    ],
-    "fulltext": "oai:ota:oucs:3731;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3731.xml;The importance of religious knowledge to the happiness of mankind. A sermon preached before the Society for propagating Christian Knowledge: at their anniversary meeting in the High Church of Edinburgh, on Monday, January 1. 1750. ... By Hugh Blair ... To which is subjoin'd a short account of the present state of the society;Blair, Hugh, 1718-1800.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7bafbf8f-4431-58d5-851a-f34e95535c78",
-    "oai_identifier": [
-        "oai:ota:oucs:3731"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The importance of religious knowledge to the happiness of mankind. A sermon preached before the Society for propagating Christian Knowledge: at their anniversary meeting in the High Church of Edinburgh, on Monday, January 1. 1750. ... By Hugh Blair ... To which is subjoin'd a short account of the present state of the society"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3731.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7bba00fd-977e-5aed-8833-25d1869e7424.json b/oaitestdata/clarin-oai_dc/SET_1/json/7bba00fd-977e-5aed-8833-25d1869e7424.json
deleted file mode 100644
index 24f7274d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7bba00fd-977e-5aed-8833-25d1869e7424.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Budapest University of Technology and Economics Media Research (BME MOKK)"
-    ],
-    "Contributor": [
-        "Halacsy, Peter"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Hungarian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-348",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-348"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-348",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Budapest University of Technology and Economics Media Research (BME MOKK)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Hungary"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-348;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Hungarian Web Corpus;Halacsy, Peter;web corpus;Monolingual written general; 700 million tokens; Segmentation, disambiguation;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-348;hun;downloadable_files_count: 0;Hungary;Budapest University of Technology and Economics Media Research (BME MOKK);http://Mokk.bme.hu/resources/webcorpus",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7bba00fd-977e-5aed-8833-25d1869e7424",
-    "notes": [
-        "Monolingual written general; 700 million tokens; Segmentation, disambiguation"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-348"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "web corpus"
-        }
-    ],
-    "title": [
-        "Hungarian Web Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7bcec433-d13f-510a-b99d-a8b319ccf015.json b/oaitestdata/clarin-oai_dc/SET_1/json/7bcec433-d13f-510a-b99d-a8b319ccf015.json
deleted file mode 100644
index 61cd3073..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7bcec433-d13f-510a-b99d-a8b319ccf015.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/21",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/21"
-    ],
-    "PID": "http://hdl.handle.net/11321/21",
-    "PublicationTimestamp": "2012-04-04T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Koco\u0144, Jan"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/21;2016-01-21T14:37:33Z;hdl_11321_3;hdl_11321_4;NamEnSim;Koco\u0144, Jan;NamEnSim (Named Entity Similarity Function) is a tool to evaluate the value of the word pair similarity, using heterogeneous named entity similarity function. This tool allows to get the value of similarity between unknown word and items from gazetteers (e.g. person first names, person last names, country names). NamEnSim can also extract multi-word named entities from the source text using similarity function. This tool supports named entities recognition task (NER), e.g. Liner2. In the named entities \"base - form\" matching task NamEnSim achieves the accuracy of 81-96% for the similarity function based on logistic regresion and 84-98% for the similarity function based on inflection rules (results depend on the named entity category).;2012-04-04;toolService;http://hdl.handle.net/11321/21;pol;downloadable_files_count: 0;Wroc\u0142aw University of Technology;http://nlp.pwr.wroc.pl/pl/narzedzia-i-zasoby/namensim",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7bcec433-d13f-510a-b99d-a8b319ccf015",
-    "notes": [
-        "NamEnSim (Named Entity Similarity Function) is a tool to evaluate the value of the word pair similarity, using heterogeneous named entity similarity function. This tool allows to get the value of similarity between unknown word and items from gazetteers (e.g. person first names, person last names, country names). NamEnSim can also extract multi-word named entities from the source text using similarity function. This tool supports named entities recognition task (NER), e.g. Liner2. In the named entities \"base - form\" matching task NamEnSim achieves the accuracy of 81-96% for the similarity function based on logistic regresion and 84-98% for the similarity function based on inflection rules (results depend on the named entity category)."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/21"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "NamEnSim"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7bd30851-56a6-5dc5-aecb-3c1c09c74f19.json b/oaitestdata/clarin-oai_dc/SET_1/json/7bd30851-56a6-5dc5-aecb-3c1c09c74f19.json
deleted file mode 100644
index 86285330..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7bd30851-56a6-5dc5-aecb-3c1c09c74f19.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Grid and High Performance Computing Group,  ITACA, Universidad Polit\u00e9cnica de Valencia",
-        "Universidad de Alicante"
-    ],
-    "Contributor": [
-        "Soriano, Jos\u00e9 Manuel G\u00f3mez"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Arabic",
-        "English",
-        "French",
-        "Italian",
-        "Oromo",
-        "Urdu"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1212",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1212"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1212",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Grid and High Performance Computing Group,  ITACA, Universidad Polit\u00e9cnica de Valencia",
-        "Universidad de Alicante"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1212;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;JIRS;Soriano, Jos\u00e9 Manuel G\u00f3mez;JIRS is a Passage Retrieval system specially suited for Question Answering. It could be adapted to others languages very easily. ask (Written Language): Information Retrieval Applications Question/Answering Environment: OS-independent Access: GPLv3;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1212;ara;eng;fra;ita;orm;urd;downloadable_files_count: 0;Spain;Grid and High Performance Computing Group,  ITACA, Universidad Polit\u00e9cnica de Valencia;Universidad de Alicante;https://sourceforge.net/projects/jirs/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7bd30851-56a6-5dc5-aecb-3c1c09c74f19",
-    "notes": [
-        "JIRS is a Passage Retrieval system specially suited for Question Answering. It could be adapted to others languages very easily. ask (Written Language): Information Retrieval Applications Question/Answering Environment: OS-independent Access: GPLv3"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1212"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "JIRS"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7c05ef93-99d5-50ef-997c-9a93f85ced34.json b/oaitestdata/clarin-oai_dc/SET_1/json/7c05ef93-99d5-50ef-997c-9a93f85ced34.json
deleted file mode 100644
index 79597b7e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7c05ef93-99d5-50ef-997c-9a93f85ced34.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "K\u00f8benhavns Universitet, Center for Sprogteknologi (CST)"
-    ],
-    "Contributor": [
-        "Jongejan, Bart"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1249",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1249"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1249",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "K\u00f8benhavns Universitet, Center for Sprogteknologi (CST)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Denmark"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Jongejan, Bart"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1249;2016-04-06T16:39:49Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;CST's lemmatizer;Jongejan, Bart;Jongejan, Bart;1) Fully automatic rule based lemmatization of inflected languages\n2) Fully automatic training of lemmatization rules based on full form-lemma list;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1249;downloadable_files_count: 0;Denmark;K\u00f8benhavns Universitet, Center for Sprogteknologi (CST);http://cst.dk/download/uk/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7c05ef93-99d5-50ef-997c-9a93f85ced34",
-    "notes": [
-        "1) Fully automatic rule based lemmatization of inflected languages\n2) Fully automatic training of lemmatization rules based on full form-lemma list"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1249"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "CST's lemmatizer"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7c0757c5-3f09-541b-8d0b-a7f77953d692.json b/oaitestdata/clarin-oai_dc/SET_1/json/7c0757c5-3f09-541b-8d0b-a7f77953d692.json
deleted file mode 100644
index 390d0f29..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7c0757c5-3f09-541b-8d0b-a7f77953d692.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/303",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/303"
-    ],
-    "PID": "http://hdl.handle.net/11321/303",
-    "PublicationTimestamp": "2016-04-25T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Gawe\u0142, Wojciech",
-        "Marci\u0144czuk, Micha\u0142",
-        "Gaida, Karol"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/303;2016-06-07T05:11:27Z;hdl_11321_3;hdl_11321_4;Mapa Literacka;Gawe\u0142, Wojciech;Marci\u0144czuk, Micha\u0142;Gaida, Karol;spatial visualisation;geolocation;A web based system for recognition and visualization of geographical objects on a map. The objects are recognized in documents provided be a user.;2016-04-25;toolService;http://hdl.handle.net/11321/303;pol;downloadable_files_count: 0;Wroc\u0142aw University of Technology;http://litmap.clarin-pl.eu/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7c0757c5-3f09-541b-8d0b-a7f77953d692",
-    "notes": [
-        "A web based system for recognition and visualization of geographical objects on a map. The objects are recognized in documents provided be a user."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/303"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "spatial visualisation"
-        },
-        {
-            "name": "geolocation"
-        }
-    ],
-    "title": [
-        "Mapa Literacka"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7c0da7dc-703c-580d-aa2d-5c5816f32424.json b/oaitestdata/clarin-oai_dc/SET_1/json/7c0da7dc-703c-580d-aa2d-5c5816f32424.json
deleted file mode 100644
index 3d36ab27..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7c0da7dc-703c-580d-aa2d-5c5816f32424.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Berlin-Brandenburg Academy of Sciences and Humanities"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-172",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-172"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-172",
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Berlin-Brandenburg Academy of Sciences and Humanities"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CC BY-NC"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-172;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Deutsches Textarchiv (DTA);Germanistik;Historical Linguistics;Corpus Linguisitics;Computational Linguistics;Natural Language Processing;History of German Language and Literature;Corpus of German historical texts ranging from ca. 1600\u20131900;2014;corpus;http://hdl.handle.net/11372/LRT-172;deu;CC BY-NC;downloadable_files_count: 0;Germany;Berlin-Brandenburg Academy of Sciences and Humanities;http://www.deutschestextarchiv.de/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7c0da7dc-703c-580d-aa2d-5c5816f32424",
-    "notes": [
-        "Corpus of German historical texts ranging from ca. 1600\u20131900"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-172"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        },
-        {
-            "name": "Historical Linguistics"
-        },
-        {
-            "name": "Corpus Linguisitics"
-        },
-        {
-            "name": "Computational Linguistics"
-        },
-        {
-            "name": "Natural Language Processing"
-        },
-        {
-            "name": "History German Language Literature"
-        }
-    ],
-    "title": [
-        "Deutsches Textarchiv (DTA)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7c1ac8d4-c974-5aa5-932a-bf7bcf47b4af.json b/oaitestdata/clarin-oai_dc/SET_1/json/7c1ac8d4-c974-5aa5-932a-bf7bcf47b4af.json
deleted file mode 100644
index 61f131c3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7c1ac8d4-c974-5aa5-932a-bf7bcf47b4af.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Dorota"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "application/pdf",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/366",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/366"
-    ],
-    "PID": "http://hdl.handle.net/11321/366",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Dorota"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN-EULA-ACA-v1.0",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca",
-        "ACA"
-    ],
-    "author": [
-        "TVN, Duda Komorowski"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/366;2017-05-26T11:38:26Z;hdl_11321_3;hdl_11321_4;Polish Presidential Debate - 2015;TVN, Duda Komorowski;debate;Transcription of the debate;2015;corpus;http://hdl.handle.net/11321/366;pol;CLARIN-EULA-ACA-v1.0;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca;ACA;text/plain; charset=utf-8;application/pdf;application/zip;downloadable_files_count: 2;Dorota;https://redir.atmcdn.pl/https/o2/tvn/web-content/m/p1/f/253f7b5d921338af34da817c00f42753/dc453e08-b4ea-4ffb-b4f4-7c55b4766fae.pdf",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7c1ac8d4-c974-5aa5-932a-bf7bcf47b4af",
-    "notes": [
-        "Transcription of the debate"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/366"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "debate"
-        }
-    ],
-    "title": [
-        "Polish Presidential Debate - 2015"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7c2f3f4f-b42a-5054-9acc-498665887d88.json b/oaitestdata/clarin-oai_dc/SET_1/json/7c2f3f4f-b42a-5054-9acc-498665887d88.json
deleted file mode 100644
index 7811f752..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7c2f3f4f-b42a-5054-9acc-498665887d88.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 1.34 MB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1909",
-    "MetadataAccess": [
-        "oai:ota:oucs:1909"
-    ],
-    "PublicationTimestamp": "1915-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1915"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Maugham, W. Somerset (William Somerset), 1874-1965"
-    ],
-    "fulltext": "oai:ota:oucs:1909;2018-04-16T10:12:13Z;http://ota.ox.ac.uk/headers/1909.xml;Of human bondage / by W. Somerset Maugham;Maugham, W. Somerset (William Somerset), 1874-1965;1915;text_and_corpus_linguistics;Novels -- Great Britain -- 20th century;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 1.34 MB);Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7c2f3f4f-b42a-5054-9acc-498665887d88",
-    "oai_identifier": [
-        "oai:ota:oucs:1909"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Novels -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Of human bondage / by W. Somerset Maugham"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1909.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7c4424ab-f824-52d8-aff5-ee6b7f59b769.json b/oaitestdata/clarin-oai_dc/SET_1/json/7c4424ab-f824-52d8-aff5-ee6b7f59b769.json
deleted file mode 100644
index 22723564..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7c4424ab-f824-52d8-aff5-ee6b7f59b769.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Simov, Kiril"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Bulgarian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-221",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-221"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-221",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Bulgaria"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-221;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;BulTreeBank Morphosyntactic Corpus;Simov, Kiril;Written, synchronic, general, manually annotated, 1 000 000 tokens divided in three sets: 215 000 tokens used in BulTreeBank HPSG Treebank (see below), additionally 300 000 checked second time, rest about 480 000 checked by the annotators. Morphosyntactic annotation with the BulTreeBank Tagset (http://www.bultreebank.org/TechRep/BTB-TR03.pdf), XML, annotation description in technical reports of BulTreeBank project http://www.bultreebank.org/TechRep;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-221;bul;downloadable_files_count: 0;Bulgaria;http://www.bultreebank.org/btbmorf/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7c4424ab-f824-52d8-aff5-ee6b7f59b769",
-    "notes": [
-        "Written, synchronic, general, manually annotated, 1 000 000 tokens divided in three sets: 215 000 tokens used in BulTreeBank HPSG Treebank (see below), additionally 300 000 checked second time, rest about 480 000 checked by the annotators. Morphosyntactic annotation with the BulTreeBank Tagset (http://www.bultreebank.org/TechRep/BTB-TR03.pdf), XML, annotation description in technical reports of BulTreeBank project http://www.bultreebank.org/TechRep"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-221"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "BulTreeBank Morphosyntactic Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7c5b6556-0976-5966-a1d2-4f55f4078a08.json b/oaitestdata/clarin-oai_dc/SET_1/json/7c5b6556-0976-5966-a1d2-4f55f4078a08.json
deleted file mode 100644
index 15159301..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7c5b6556-0976-5966-a1d2-4f55f4078a08.json
+++ /dev/null
@@ -1,90 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 4",
-        "application/pdf",
-        "application/zip"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1087",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1087"
-    ],
-    "PID": "http://hdl.handle.net/11356/1087",
-    "PublicationTimestamp": "2017-01-20T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "http://nl.ijs.si/janes/viri/rocno-oznaceni-korpusi/#Janes-Kratko",
-        "https://doi.org/10.1007/s10579-018-9425-z"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "https://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Osrajnik, Eneja",
-        "Erjavec, Toma\u017e",
-        "Fi\u0161er, Darja",
-        "Goli, Teja"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1087;2018-12-04T16:12:42Z;hdl_11356_1023;hdl_11356_1024;CMC shortening corpus Janes-Kratko 1.0;Goli, Teja;Osrajnik, Eneja;Fi\u0161er, Darja;Erjavec, Toma\u017e;computer-mediated communication;Twitter;shortening phenomena;TEI;manual annotation;Janes-Kratko is a corpus of Slovene tweets manually annotated with shortening phenomena according to the supplied typology covering different types of spelling, lexical and syntactic shortenings. The corpus was sampled from the Janes-Norm corpus (http://hdl.handle.net/11356/1084), which was manually annotated for tokenisation, sentence segmentation and word normalisation of non-standard Slovene and automatically annotated with morphosyntactic descriptions and lemmas.\r\n\r\nThe corpus is further described in:\r\nGOLI, Teja, OSRAJNIK, Eneja, FI\u0160ER, Darja. Analiza kraj\u0161anja slovenskih sporo\u010dil na dru\u017ebenem omre\u017eju Twitter. Proceedings of the Conference on Language Technologies & Digital Humanities, Ljubljana, Slovenia. 2016, pp. 77-82. http://www.sdjt.si/wp/dogodki/konference/jtdh-2016/zbornik/;2017-01-20;corpus;http://hdl.handle.net/11356/1087;slv;http://nl.ijs.si/janes/viri/rocno-oznaceni-korpusi/#Janes-Kratko;https://doi.org/10.1007/s10579-018-9425-z;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);https://creativecommons.org/licenses/by-sa/4.0/;PUB;text/plain; charset=utf-8;application/pdf;application/zip;application/zip;application/zip;downloadable_files_count: 4;Jo\u017eef Stefan Institute;http://nl.ijs.si/janes/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7c5b6556-0976-5966-a1d2-4f55f4078a08",
-    "notes": [
-        "Janes-Kratko is a corpus of Slovene tweets manually annotated with shortening phenomena according to the supplied typology covering different types of spelling, lexical and syntactic shortenings. The corpus was sampled from the Janes-Norm corpus (http://hdl.handle.net/11356/1084), which was manually annotated for tokenisation, sentence segmentation and word normalisation of non-standard Slovene and automatically annotated with morphosyntactic descriptions and lemmas.\r\n\r\nThe corpus is further described in:\r\nGOLI, Teja, OSRAJNIK, Eneja, FI\u0160ER, Darja. Analiza kraj\u0161anja slovenskih sporo\u010dil na dru\u017ebenem omre\u017eju Twitter. Proceedings of the Conference on Language Technologies & Digital Humanities, Ljubljana, Slovenia. 2016, pp. 77-82. http://www.sdjt.si/wp/dogodki/konference/jtdh-2016/zbornik/"
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1087"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "computer-mediated communication"
-        },
-        {
-            "name": "Twitter"
-        },
-        {
-            "name": "shortening phenomena"
-        },
-        {
-            "name": "TEI"
-        },
-        {
-            "name": "manual annotation"
-        }
-    ],
-    "title": [
-        "CMC shortening corpus Janes-Kratko 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7c8c5666-159e-55d6-9eec-0777b923623d.json b/oaitestdata/clarin-oai_dc/SET_1/json/7c8c5666-159e-55d6-9eec-0777b923623d.json
deleted file mode 100644
index 303f67de..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7c8c5666-159e-55d6-9eec-0777b923623d.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/5-UDPIPE-TOKENIZER",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/5-UDPIPE-TOKENIZER"
-    ],
-    "PID": "http://hdl.handle.net/11234/5-UDPIPE-TOKENIZER",
-    "PublicationTimestamp": "2016-02-08T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Straka, Milan"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/5-UDPIPE-TOKENIZER;2019-01-02T13:42:29Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0023-8C33-2;UDPipe tokenizer Web Service for Weblicht;Straka, Milan;udpipe;UDPipe is a trainable pipeline for tokenizing, tagging, lemmatizing and parsing Universal Treebanks and other CoNLL-U files (https://lindat.mff.cuni.cz/services/udpipe/);2016-02-08;toolService;http://hdl.handle.net/11234/5-UDPIPE-TOKENIZER;application/octet-stream;downloadable_files_count: 0;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://hdl.handle.net/11234/5-UDPIPE-TOKENIZER",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7c8c5666-159e-55d6-9eec-0777b923623d",
-    "notes": [
-        "UDPipe is a trainable pipeline for tokenizing, tagging, lemmatizing and parsing Universal Treebanks and other CoNLL-U files (https://lindat.mff.cuni.cz/services/udpipe/)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/5-UDPIPE-TOKENIZER"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0023-8C33-2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "udpipe"
-        }
-    ],
-    "title": [
-        "UDPipe tokenizer Web Service for Weblicht"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7c955883-31f9-5d32-b62a-57be9c2da114.json b/oaitestdata/clarin-oai_dc/SET_1/json/7c955883-31f9-5d32-b62a-57be9c2da114.json
deleted file mode 100644
index e33a4ae9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7c955883-31f9-5d32-b62a-57be9c2da114.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Marrene"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 5",
-        "application/zip",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/84",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/84"
-    ],
-    "PID": "http://hdl.handle.net/11321/84",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Marrene"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Marrene, Marrene"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/84;2015-05-21T12:03:38Z;hdl_11321_3;hdl_11321_4;MWE Marrene;Marrene, Marrene;Marrene;2015-04-08;corpus;http://hdl.handle.net/11321/84;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 5;Marrene",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7c955883-31f9-5d32-b62a-57be9c2da114",
-    "notes": [
-        "Marrene"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/84"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Marrene"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7cadff3f-fa71-595f-a700-191f22351103.json b/oaitestdata/clarin-oai_dc/SET_1/json/7cadff3f-fa71-595f-a700-191f22351103.json
deleted file mode 100644
index cd383db0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7cadff3f-fa71-595f-a700-191f22351103.json
+++ /dev/null
@@ -1,89 +0,0 @@
-{
-    "Contact": [
-        "Department of Informatics, University of Oslo"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Norwegian Nynorsk",
-        "Norwegian Bokm\u00e5l",
-        "Norwegian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/124",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/124"
-    ],
-    "PID": "http://hdl.handle.net/11509/124",
-    "PublicationTimestamp": "2017-10-23T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Department of Informatics, University of Oslo"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0)",
-        "CC",
-        "http://creativecommons.org/licenses/by-nc/3.0/"
-    ],
-    "author": [
-        "Velldal, Erik",
-        "\u00d8vrelid, Lilja",
-        "Stadsnes, Cathrine",
-        "J\u00f8rgensen, Fredrik",
-        "Bergem, Eivind Alexander",
-        "Touileb, Samia"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/124;2017-10-25T08:45:41Z;hdl_11509_1;hdl_11509_2;NoReC: The Norwegian Review Corpus;Velldal, Erik;\u00d8vrelid, Lilja;Bergem, Eivind Alexander;Stadsnes, Cathrine;Touileb, Samia;J\u00f8rgensen, Fredrik;sentiment analysis;opinion mining;reviews;news;norwegian;While the NoReC dataset was primarily created for training and evaluating models for document-level sentiment analysis, many other use cases are of course possible. The corpus comprises more than 35,000 full-text reviews extracted from eight different major Norwegian news sources: Dagbladet, VG, Aftenposten, Bergens Tidende, F\u00e6drelandsvennen, Stavanger Aftenblad, DinSide.no and P3.no. The reviews cover a range of different domains, including literature, movies, video games, restaurants, music and theater, in addition to product reviews across a range of categories. Each review is labeled with a manually assigned score of 1\u20136, as provided by the rating of the original author. The texts have been pre-processed using UDPipe and are distributed in the CoNLL-U format. However, we also provide HTML files with the raw texts. Documentation and an accompanying Python package are  provided through the following git repository: https://github.com/ltgoslo/norec;2017-10-23;corpus;http://hdl.handle.net/11509/124;nno;nob;nor;Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0);CC;http://creativecommons.org/licenses/by-nc/3.0/;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Department of Informatics, University of Oslo;https://github.com/ltgoslo/norec",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7cadff3f-fa71-595f-a700-191f22351103",
-    "notes": [
-        "While the NoReC dataset was primarily created for training and evaluating models for document-level sentiment analysis, many other use cases are of course possible. The corpus comprises more than 35,000 full-text reviews extracted from eight different major Norwegian news sources: Dagbladet, VG, Aftenposten, Bergens Tidende, F\u00e6drelandsvennen, Stavanger Aftenblad, DinSide.no and P3.no. The reviews cover a range of different domains, including literature, movies, video games, restaurants, music and theater, in addition to product reviews across a range of categories. Each review is labeled with a manually assigned score of 1\u20136, as provided by the rating of the original author. The texts have been pre-processed using UDPipe and are distributed in the CoNLL-U format. However, we also provide HTML files with the raw texts. Documentation and an accompanying Python package are  provided through the following git repository: https://github.com/ltgoslo/norec"
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/124"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "sentiment analysis"
-        },
-        {
-            "name": "opinion mining"
-        },
-        {
-            "name": "reviews"
-        },
-        {
-            "name": "news"
-        },
-        {
-            "name": "norwegian"
-        }
-    ],
-    "title": [
-        "NoReC: The Norwegian Review Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7cafa0a2-234e-53bc-ba74-7927e2745d36.json b/oaitestdata/clarin-oai_dc/SET_1/json/7cafa0a2-234e-53bc-ba74-7927e2745d36.json
deleted file mode 100644
index 4153321b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7cafa0a2-234e-53bc-ba74-7927e2745d36.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/x-tar",
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 2"
-    ],
-    "Language": [
-        "English",
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-EE02-C",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-EE02-C"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0022-EE02-C",
-    "PublicationTimestamp": "2013-11-07T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Bojar, Ond\u0159ej",
-        "Tamchyna, Ale\u0161"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-EE02-C;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Plain-Moses-Chimera;Bojar, Ond\u0159ej;Tamchyna, Ale\u0161;moses;machine translation;Statistical component of Chimera, a state-of-the-art MT system.;2013-11-07;toolService;http://hdl.handle.net/11858/00-097C-0000-0022-EE02-C;eng;ces;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/x-gzip;application/x-tar;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7cafa0a2-234e-53bc-ba74-7927e2745d36",
-    "notes": [
-        "Statistical component of Chimera, a state-of-the-art MT system."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-EE02-C"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "moses"
-        },
-        {
-            "name": "machine translation"
-        }
-    ],
-    "title": [
-        "Plain-Moses-Chimera"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7cb30d45-8bf4-5a15-bc19-e57e2b02163d.json b/oaitestdata/clarin-oai_dc/SET_1/json/7cb30d45-8bf4-5a15-bc19-e57e2b02163d.json
deleted file mode 100644
index fa4b2722..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7cb30d45-8bf4-5a15-bc19-e57e2b02163d.json
+++ /dev/null
@@ -1,115 +0,0 @@
-{
-    "Contact": [
-        "Universit\u00e4t des Saarlandes"
-    ],
-    "Contributor": [
-        "Ekaterina Lapshinova-Koltunski",
-        "Prof. Elke Teich",
-        "Hannah Kermes",
-        "Stefania Degaetano-Ortlieb"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:sascitex",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:sascitex"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CF9-6",
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Universit\u00e4t des Saarlandes"
-    ],
-    "RelatedIdentifier": [
-        "DaSciTeX, hdl:11858/00-246C-0000-0005-BD0F-D",
-        "Degaetano-Ortlieb, S., Kermes, H., Lapshinova-Koltunski, E., and Teich, E. (2013). SciTex - A Diachronic Corpus for Analyzing the Development of Scientific Registers. In P. Bennett, M. Durrell, S. Scheible, and R. J. Whitt (eds.), New Methods in Historical Corpus Linguistics (Vol. 3, S. 93\u2013104). Narr."
-    ],
-    "ResourceType": [
-        "Collection",
-        "Corpus"
-    ],
-    "Rights": [
-        "Copyrighted"
-    ],
-    "SpatialCoverage": [
-        "1970/1989",
-        "World"
-    ],
-    "TemporalCoverage": " period : ( 1970-07-01T11:59:59Z - None ) ",
-    "author": [
-        "Registers in Contact, DFG project TE-198/2",
-        "Universit\u00e4t des Saarlandes"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:sascitex;2017-02-20T16:52:59Z;SaSciTeX;Universit\u00e4t des Saarlandes;Registers in Contact, DFG project TE-198/2;corpus linguistics;linguistics;register;scientific discourse;computer science;computational linguistics;biology;bioinformatics;electrical engineering;micro-electronics;mechanical engineering;computer-aided design;functional variation;Synchronic corpus of scientific texts from 9 different disciplines.;The Saarbr\u00fccken Corpus of Scientific Texts (SaSciTex) contains full English scientific journal articles compiled from nine scientific domains. The corpus has a three-way partition: a center discipline (computer science) four 'pure' contact disciplines (linguistics, biology, mechanical engineering, electrical engineering) and four corresponding 'mixed' disciplines (computational linguistics, bio-informatics, computer-aided design, micro-electronics). The corpus comes in two versions  a small manually checked corpus (approx. one million words) a large corpus (17 million words.);Das Saarbr\u00fccken Corpus of Scientific Texts (SaSciTex) besteht aus Vollversionen Englischer wissenschaftlicher Zeitschriftenartikel und umfasst 9 verschiedene wissenschaftliche Dom\u00e4nen. Der Aufbau des Korpus ist dreigliedrig: eine zentrale Disziplin (Informatik),vier 'reine' Kontaktdisziplinen (Linguistik, Biologie, Maschinen Bau, Elektrotechnik), vier dazugeh\u00f6rige Mischdisziplinen (Computerlinguistik, Bio-Informatik, CAD, Mikroelektronik). Es gibt zwei Versionen des Korpus: ein kleines manuell korrigiertes Korpus (ca. eine Million W\u00f6rter), ein gro\u00dfes Korpus (17 Millionen W\u00f6rter).;Universit\u00e4t des Saarlandes;Prof. Elke Teich;Stefania Degaetano-Ortlieb;Ekaterina Lapshinova-Koltunski;Hannah Kermes;2011/2014;Collection;Corpus;text/xml;clarind-uds:sascitex;hdl:11858/00-246C-0000-0023-8CF9-6;eng;DaSciTeX, hdl:11858/00-246C-0000-0005-BD0F-D;Degaetano-Ortlieb, S., Kermes, H., Lapshinova-Koltunski, E., and Teich, E. (2013). SciTex - A Diachronic Corpus for Analyzing the Development of Scientific Registers. In P. Bennett, M. Durrell, S. Scheible, and R. J. Whitt (eds.), New Methods in Historical Corpus Linguistics (Vol. 3, S. 93\u2013104). Narr.;1970/1989;World;Copyrighted",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7cb30d45-8bf4-5a15-bc19-e57e2b02163d",
-    "notes": [
-        "Synchronic corpus of scientific texts from 9 different disciplines.",
-        "The Saarbr\u00fccken Corpus of Scientific Texts (SaSciTex) contains full English scientific journal articles compiled from nine scientific domains. The corpus has a three-way partition: a center discipline (computer science) four 'pure' contact disciplines (linguistics, biology, mechanical engineering, electrical engineering) and four corresponding 'mixed' disciplines (computational linguistics, bio-informatics, computer-aided design, micro-electronics). The corpus comes in two versions  a small manually checked corpus (approx. one million words) a large corpus (17 million words.)",
-        "Das Saarbr\u00fccken Corpus of Scientific Texts (SaSciTex) besteht aus Vollversionen Englischer wissenschaftlicher Zeitschriftenartikel und umfasst 9 verschiedene wissenschaftliche Dom\u00e4nen. Der Aufbau des Korpus ist dreigliedrig: eine zentrale Disziplin (Informatik),vier 'reine' Kontaktdisziplinen (Linguistik, Biologie, Maschinen Bau, Elektrotechnik), vier dazugeh\u00f6rige Mischdisziplinen (Computerlinguistik, Bio-Informatik, CAD, Mikroelektronik). Es gibt zwei Versionen des Korpus: ein kleines manuell korrigiertes Korpus (ca. eine Million W\u00f6rter), ein gro\u00dfes Korpus (17 Millionen W\u00f6rter)."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:sascitex"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus linguistics"
-        },
-        {
-            "name": "linguistics"
-        },
-        {
-            "name": "register"
-        },
-        {
-            "name": "scientific discourse"
-        },
-        {
-            "name": "computer science"
-        },
-        {
-            "name": "computational linguistics"
-        },
-        {
-            "name": "biology"
-        },
-        {
-            "name": "bioinformatics"
-        },
-        {
-            "name": "electrical engineering"
-        },
-        {
-            "name": "micro-electronics"
-        },
-        {
-            "name": "mechanical engineering"
-        },
-        {
-            "name": "computer-aided design"
-        }
-    ],
-    "title": [
-        "SaSciTeX"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7cc2f98a-694e-52fb-940d-63fc313affad.json b/oaitestdata/clarin-oai_dc/SET_1/json/7cc2f98a-694e-52fb-940d-63fc313affad.json
deleted file mode 100644
index b686dc21..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7cc2f98a-694e-52fb-940d-63fc313affad.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-685",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-685"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-685",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Code of conduct"
-    ],
-    "SpatialCoverage": [
-        "Bolivia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-685;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Yurakar\u00e9 corpus;Documentation of the Yurakar\u00e9 project (DoBeS project);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-685;Code of conduct;downloadable_files_count: 0;Bolivia;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser/?openpath=MPI532886%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7cc2f98a-694e-52fb-940d-63fc313affad",
-    "notes": [
-        "Documentation of the Yurakar\u00e9 project (DoBeS project)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-685"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Yurakar\u00e9 corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7cc9ebc4-bd14-5c7a-a95f-69e3ff1127c4.json b/oaitestdata/clarin-oai_dc/SET_1/json/7cc9ebc4-bd14-5c7a-a95f-69e3ff1127c4.json
deleted file mode 100644
index 8e4ced50..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7cc9ebc4-bd14-5c7a-a95f-69e3ff1127c4.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Spanish",
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/3",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/3"
-    ],
-    "PID": "http://hdl.handle.net/11509/3",
-    "PublicationTimestamp": "2011-11-30T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Parra Escart\u00edn, Carla"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/3;2016-04-15T05:59:20Z;hdl_11509_1;hdl_11509_2;Parallel Corpus of documents from the Technical Regulations Information System for German-Spanish (v0.1);Parra Escart\u00edn, Carla;Corpus;Text;Spanish, Castilian;German;Specialized parallel corpus Spanish-German (Spanish-Austrian and Spanish-German), texts from the European Commission between 1990-2010. The texts are technical regulations in a variety of domains. To be sentence aligned. The current version 0.1 contains the files for 1999-2000 in the domain B00: Construction (51 files; 16731 sentences).;2011-11-30;corpus;NOT_DEFINED_FOR_V2;http://hdl.handle.net/11509/3;spa;ger;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;CC;application/zip;downloadable_files_count: 1",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7cc9ebc4-bd14-5c7a-a95f-69e3ff1127c4",
-    "notes": [
-        "Specialized parallel corpus Spanish-German (Spanish-Austrian and Spanish-German), texts from the European Commission between 1990-2010. The texts are technical regulations in a variety of domains. To be sentence aligned. The current version 0.1 contains the files for 1999-2000 in the domain B00: Construction (51 files; 16731 sentences)."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/3"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Corpus"
-        },
-        {
-            "name": "Text"
-        },
-        {
-            "name": "Spanish"
-        },
-        {
-            "name": "Castilian"
-        },
-        {
-            "name": "German"
-        }
-    ],
-    "title": [
-        "Parallel Corpus of documents from the Technical Regulations Information System for German-Spanish (v0.1)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7cceec46-c36d-5599-8fae-da4dcb928d8f.json b/oaitestdata/clarin-oai_dc/SET_1/json/7cceec46-c36d-5599-8fae-da4dcb928d8f.json
deleted file mode 100644
index 19ad14b7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7cceec46-c36d-5599-8fae-da4dcb928d8f.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish",
-        "Romanian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/66",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/66"
-    ],
-    "PID": "http://hdl.handle.net/10794/66",
-    "PublicationTimestamp": "2015-04-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/66;2017-10-31T15:21:48Z;hdl_10794_1;hdl_10794_2;ASPAC \u2013 Swedish-Romanian (2017-10-16);ASPAC \u2013 svenska-rum\u00e4nska (2017-10-16);n/a, n/a;ASPAC;Parallel;Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.;Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat.;2015-04-16;corpus;http://hdl.handle.net/10794/66;swe;ron;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/octet-stream;application/gzip;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/aspacsvro",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7cceec46-c36d-5599-8fae-da4dcb928d8f",
-    "notes": [
-        "Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.",
-        "Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/66"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ASPAC"
-        },
-        {
-            "name": "Parallel"
-        }
-    ],
-    "title": [
-        "ASPAC \u2013 Swedish-Romanian (2017-10-16)",
-        "ASPAC \u2013 svenska-rum\u00e4nska (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7cd35a27-eaf4-50f2-b36e-fb6efe5499d6.json b/oaitestdata/clarin-oai_dc/SET_1/json/7cd35a27-eaf4-50f2-b36e-fb6efe5499d6.json
deleted file mode 100644
index c3ec2ff0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7cd35a27-eaf4-50f2-b36e-fb6efe5499d6.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Research Institute for Artificial Intelligence, Romanian Academy of Sciences"
-    ],
-    "Contributor": [
-        "Piasecki, Maciej"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/xml"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-486",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-486"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-486",
-    "PublicationTimestamp": "2008-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2008"
-    ],
-    "Publisher": [
-        "Research Institute for Artificial Intelligence, Romanian Academy of Sciences"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Free for non-commercial use"
-    ],
-    "SpatialCoverage": [
-        "Poland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-486;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;plWordNet (S\u0142owosie\u0107);Piasecki, Maciej;currently: about 18 600 lexical units,  about 11 000 synsets, planned (by the end of 2008): 25-30 thousands of lexical units;2008;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-486;pol;Free for non-commercial use;application/xml;downloadable_files_count: 0;Poland;Research Institute for Artificial Intelligence, Romanian Academy of Sciences;http://www.plwordnet.pwr.wroc.pl/browser/?lang=en",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7cd35a27-eaf4-50f2-b36e-fb6efe5499d6",
-    "notes": [
-        "currently: about 18 600 lexical units,  about 11 000 synsets, planned (by the end of 2008): 25-30 thousands of lexical units"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-486"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "plWordNet (S\u0142owosie\u0107)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7cd4a71c-e90a-54c1-b9c6-0f5b4f991b67.json b/oaitestdata/clarin-oai_dc/SET_1/json/7cd4a71c-e90a-54c1-b9c6-0f5b4f991b67.json
deleted file mode 100644
index 18b5379e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7cd4a71c-e90a-54c1-b9c6-0f5b4f991b67.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1032",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1032"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1032",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1032;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;L1 Acquisition Caroline Corpus;Language Acquisition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1032;deu;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI1411%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7cd4a71c-e90a-54c1-b9c6-0f5b4f991b67",
-    "notes": [
-        "Language Acquisition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1032"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "L1 Acquisition Caroline Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7cde67cb-9d8f-59da-b4b1-e2643499ddd8.json b/oaitestdata/clarin-oai_dc/SET_1/json/7cde67cb-9d8f-59da-b4b1-e2643499ddd8.json
deleted file mode 100644
index 0ca3bc54..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7cde67cb-9d8f-59da-b4b1-e2643499ddd8.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/csv",
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 3",
-        "text/plain",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1198",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1198"
-    ],
-    "PID": "http://hdl.handle.net/11356/1198",
-    "PublicationTimestamp": "2018-08-18T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "https://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Erjavec, Toma\u017e",
-        "Robnik \u0160ikonja, Marko",
-        "Udovi\u010d, Bo\u0161tjan",
-        "Fi\u0161er, Darja",
-        "Ljube\u0161i\u0107, Nikola",
-        "Arhar Holdt, \u0160pela",
-        "Bren, Urban"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1198;2018-08-23T09:40:24Z;hdl_11356_1023;hdl_11356_1024;Terminology identification dataset KAS-term 1.0;Erjavec, Toma\u017e;Fi\u0161er, Darja;Ljube\u0161i\u0107, Nikola;Arhar Holdt, \u0160pela;Bren, Urban;Robnik \u0160ikonja, Marko;Udovi\u010d, Bo\u0161tjan;terminology;manual annotation;The dataset contains 22,950 term candidates extracted from 15 Slovenian PhD theses. The term candidates are of length 1 to 4, extracted via morphosyntactic patterns and the frequency threshold of 3. The PhD theses are from the areas of chemistry, computer science and political science. Each of the term candidates is annotated by four annotators as being (1) in-domain term, (2) out-of-domain term, (3) general academic term or (4) not a term. Each term candidate is also annotated with its frequency in the PhD thesis and 7 statistical measures. The resource can serve as a training set for supervised learning of term extraction and for terminology extraction tool benchmarking.;2018-08-18;lexicalConceptualResource;http://hdl.handle.net/11356/1198;slv;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);https://creativecommons.org/licenses/by-sa/4.0/;PUB;application/octet-stream;text/csv;text/plain;text/plain; charset=utf-8;downloadable_files_count: 3;Jo\u017eef Stefan Institute;http://nl.ijs.si/kas/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7cde67cb-9d8f-59da-b4b1-e2643499ddd8",
-    "notes": [
-        "The dataset contains 22,950 term candidates extracted from 15 Slovenian PhD theses. The term candidates are of length 1 to 4, extracted via morphosyntactic patterns and the frequency threshold of 3. The PhD theses are from the areas of chemistry, computer science and political science. Each of the term candidates is annotated by four annotators as being (1) in-domain term, (2) out-of-domain term, (3) general academic term or (4) not a term. Each term candidate is also annotated with its frequency in the PhD thesis and 7 statistical measures. The resource can serve as a training set for supervised learning of term extraction and for terminology extraction tool benchmarking."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1198"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "terminology"
-        },
-        {
-            "name": "manual annotation"
-        }
-    ],
-    "title": [
-        "Terminology identification dataset KAS-term 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7cdf95ac-7a8a-59f7-b528-91a6c95c789e.json b/oaitestdata/clarin-oai_dc/SET_1/json/7cdf95ac-7a8a-59f7-b528-91a6c95c789e.json
deleted file mode 100644
index 44a3b638..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7cdf95ac-7a8a-59f7-b528-91a6c95c789e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5354",
-    "MetadataAccess": [
-        "oai:ota:oucs:5354"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Congreve, William, 1670-1729."
-    ],
-    "fulltext": "oai:ota:oucs:5354;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5354.xml;An impossible thing. A tale;Congreve, William, 1670-1729.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7cdf95ac-7a8a-59f7-b528-91a6c95c789e",
-    "oai_identifier": [
-        "oai:ota:oucs:5354"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An impossible thing. A tale"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5354.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7cf4b603-c61d-5e30-b5b9-a1f5c798f49e.json b/oaitestdata/clarin-oai_dc/SET_1/json/7cf4b603-c61d-5e30-b5b9-a1f5c798f49e.json
deleted file mode 100644
index 4ae8af95..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7cf4b603-c61d-5e30-b5b9-a1f5c798f49e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4583",
-    "MetadataAccess": [
-        "oai:ota:oucs:4583"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Jerningham, Mr. (Edward), 1737?-1812."
-    ],
-    "fulltext": "oai:ota:oucs:4583;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4583.xml;Amabella, a poem;Jerningham, Mr. (Edward), 1737?-1812.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7cf4b603-c61d-5e30-b5b9-a1f5c798f49e",
-    "oai_identifier": [
-        "oai:ota:oucs:4583"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Amabella, a poem"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4583.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7d12fdcc-adc2-5927-ba41-bfe391b2a1fe.json b/oaitestdata/clarin-oai_dc/SET_1/json/7d12fdcc-adc2-5927-ba41-bfe391b2a1fe.json
deleted file mode 100644
index 5da6d55e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7d12fdcc-adc2-5927-ba41-bfe391b2a1fe.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2594",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2594"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2594",
-    "PublicationTimestamp": "2017-12-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-1900"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "BSD 3-Clause \"New\" or \"Revised\" license",
-        "http://opensource.org/licenses/BSD-3-Clause",
-        "PUB"
-    ],
-    "author": [
-        "Haji\u010d, Jan",
-        "Ko\u0161arko, Ond\u0159ej"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2594;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;VIADAT-REPO+DEPOSIT;Ko\u0161arko, Ond\u0159ej;Haji\u010d, Jan;digital data;digital repository;VIADAT-REPO is an additional module to the lindat-dspace platform which allows for depositing data records in the field of oral history, including its specific metadata workflow; it has been created within the VIADAT project and as such will be a part of a \"virtual assistant\" for processing, annotation, enrichment and accessing of audio and video recordings. This package contains VIADAT-DEPOSIT module; bundled with VIADAT-REPO to ease the integration.;2017-12-31;toolService;http://hdl.handle.net/11234/1-2594;http://hdl.handle.net/11234/1-1900;BSD 3-Clause \"New\" or \"Revised\" license;http://opensource.org/licenses/BSD-3-Clause;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://ufal.mff.cuni.cz/grants/viadat",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7d12fdcc-adc2-5927-ba41-bfe391b2a1fe",
-    "notes": [
-        "VIADAT-REPO is an additional module to the lindat-dspace platform which allows for depositing data records in the field of oral history, including its specific metadata workflow; it has been created within the VIADAT project and as such will be a part of a \"virtual assistant\" for processing, annotation, enrichment and accessing of audio and video recordings. This package contains VIADAT-DEPOSIT module; bundled with VIADAT-REPO to ease the integration."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2594"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "digital data"
-        },
-        {
-            "name": "digital repository"
-        }
-    ],
-    "title": [
-        "VIADAT-REPO+DEPOSIT"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7d25caff-c452-53f1-8a3e-895f9f66daca.json b/oaitestdata/clarin-oai_dc/SET_1/json/7d25caff-c452-53f1-8a3e-895f9f66daca.json
deleted file mode 100644
index 47c682df..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7d25caff-c452-53f1-8a3e-895f9f66daca.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Uniwersytet SWPS"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/458",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/458"
-    ],
-    "PID": "http://hdl.handle.net/11321/458",
-    "PublicationTimestamp": "2018-04-11T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Uniwersytet SWPS"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN-EULA-ACA-v1.0",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca",
-        "ACA"
-    ],
-    "author": [
-        "Zi\u0119ba, Mariusz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/458;2018-04-11T19:03:01Z;hdl_11321_3;hdl_11321_4;MZ materia\u0142y na warsztaty Pozna\u0144;Zi\u0119ba, Mariusz;test;materia\u0142y na warsztaty;2018-04-11;corpus;http://hdl.handle.net/11321/458;pol;CLARIN-EULA-ACA-v1.0;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca;ACA;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;Uniwersytet SWPS",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7d25caff-c452-53f1-8a3e-895f9f66daca",
-    "notes": [
-        "materia\u0142y na warsztaty"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/458"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "test"
-        }
-    ],
-    "title": [
-        "MZ materia\u0142y na warsztaty Pozna\u0144"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7d2d7ae8-3443-5a5a-9980-85a77727ba1c.json b/oaitestdata/clarin-oai_dc/SET_1/json/7d2d7ae8-3443-5a5a-9980-85a77727ba1c.json
deleted file mode 100644
index 9fa89496..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7d2d7ae8-3443-5a5a-9980-85a77727ba1c.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "University of Glasgow"
-    ],
-    "Contributor": [
-        "Adams, Alison",
-        "Spangler, Jonathan"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "French"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-876",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-876"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-876",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Glasgow"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-876;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;French emblems at Glasgow;Adams, Alison;Spangler, Jonathan;French emblem books (27 in total) of the 16th century, together with Latin versions where appropriate. Transcribed and facsimile versions, and extensive search functionality.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-876;fra;downloadable_files_count: 0;United Kingdom;University of Glasgow;http://www.emblems.arts.gla.ac.uk/french/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7d2d7ae8-3443-5a5a-9980-85a77727ba1c",
-    "notes": [
-        "French emblem books (27 in total) of the 16th century, together with Latin versions where appropriate. Transcribed and facsimile versions, and extensive search functionality."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-876"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "French emblems at Glasgow"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7d309453-bc64-5955-9519-046973cb22ff.json b/oaitestdata/clarin-oai_dc/SET_1/json/7d309453-bc64-5955-9519-046973cb22ff.json
deleted file mode 100644
index fbe6935a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7d309453-bc64-5955-9519-046973cb22ff.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contributor": [
-        "Tadi\u0107, Marko"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Croatian",
-        "French"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-241",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-241"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-241",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-241;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;French-Croatian Parallel Corpus;Tadi\u0107, Marko;written; domain-specific (fiction); diachronic (the French side); bilingual; parallel; ca 263,000 tokens (148 Kw French; 115 Kw Croatian); XML; S-alignment;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-241;hrv;fra;downloadable_files_count: 0;http://hnk.ffzg.hr",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7d309453-bc64-5955-9519-046973cb22ff",
-    "notes": [
-        "written; domain-specific (fiction); diachronic (the French side); bilingual; parallel; ca 263,000 tokens (148 Kw French; 115 Kw Croatian); XML; S-alignment"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-241"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "French-Croatian Parallel Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7d3116e8-1076-5c25-bb63-1ea959364472.json b/oaitestdata/clarin-oai_dc/SET_1/json/7d3116e8-1076-5c25-bb63-1ea959364472.json
deleted file mode 100644
index ed56cdd5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7d3116e8-1076-5c25-bb63-1ea959364472.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Amsterdam Centre for Language and Communication, University of Amsterdam"
-    ],
-    "Contributor": [
-        "Son, Rob van"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-735",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-735"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-735",
-    "PublicationTimestamp": "2007-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2007"
-    ],
-    "Publisher": [
-        "Amsterdam Centre for Language and Communication, University of Amsterdam"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GPL"
-    ],
-    "SpatialCoverage": [
-        "Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-735;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;IFA Dialog Video corpus;Son, Rob van;annotated video recordings of friendly face-to-face dialogs;2007;corpus;http://hdl.handle.net/11372/LRT-735;nld;GPL;downloadable_files_count: 0;Netherlands (the);Amsterdam Centre for Language and Communication, University of Amsterdam;http://www.fon.hum.uva.nl/IFA-SpokenLanguageCorpora/IFADVcorpus/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7d3116e8-1076-5c25-bb63-1ea959364472",
-    "notes": [
-        "annotated video recordings of friendly face-to-face dialogs"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-735"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "IFA Dialog Video corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7d4151ee-7e87-561f-a155-60d3fa7089e7.json b/oaitestdata/clarin-oai_dc/SET_1/json/7d4151ee-7e87-561f-a155-60d3fa7089e7.json
deleted file mode 100644
index 22fe6a6b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7d4151ee-7e87-561f-a155-60d3fa7089e7.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Croatian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1177",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1177"
-    ],
-    "PID": "http://hdl.handle.net/11356/1177",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "http://www.informatica.si/index.php/informatica/article/view/985"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "Ljube\u0161i\u0107, Nikola"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1177;2018-05-28T11:27:32Z;hdl_11356_1023;hdl_11356_1024;Automatically constructed multiword lexicon hrMWELex v0.5;Ljube\u0161i\u0107, Nikola;multiword expressions;collocations;The hrMWELex lexicon is an automatically constructed lexicon of Croatian multiword expression candidates (mostly collocations) from the parsed hrWaC 2.0 corpus by using the DepMWEx [depmueks] tool (https://github.com/nljubesi/depmwex). The tool extracts MWE candidates from parse trees by applying tree patterns and ranking by occurrence statistics.;2015;lexicalConceptualResource;http://hdl.handle.net/11356/1177;hrv;http://www.informatica.si/index.php/informatica/article/view/985;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;https://creativecommons.org/licenses/by/4.0/;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Jo\u017eef Stefan Institute;http://nlp.ffzg.hr/resources/lexicons/hrmwelex/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7d4151ee-7e87-561f-a155-60d3fa7089e7",
-    "notes": [
-        "The hrMWELex lexicon is an automatically constructed lexicon of Croatian multiword expression candidates (mostly collocations) from the parsed hrWaC 2.0 corpus by using the DepMWEx [depmueks] tool (https://github.com/nljubesi/depmwex). The tool extracts MWE candidates from parse trees by applying tree patterns and ranking by occurrence statistics."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1177"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "multiword expressions"
-        },
-        {
-            "name": "collocations"
-        }
-    ],
-    "title": [
-        "Automatically constructed multiword lexicon hrMWELex v0.5"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7d4b9ebb-1798-5852-bab9-e5c82de7fe0b.json b/oaitestdata/clarin-oai_dc/SET_1/json/7d4b9ebb-1798-5852-bab9-e5c82de7fe0b.json
deleted file mode 100644
index 776f5ddb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7d4b9ebb-1798-5852-bab9-e5c82de7fe0b.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Danish",
-        "Dutch",
-        "English",
-        "Finnish",
-        "French",
-        "German",
-        "Italian",
-        "Latin",
-        "Portuguese",
-        "Russian",
-        "Spanish",
-        "Swedish",
-        "Telugu"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1137",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1137"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1137",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United States"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1137;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Project Gutenberg;Possibility to download or to browse free electronic books; Angebot: Download von und Online-Zugang zu frei verf\u00fcgbaren E-Books; deutschsprachige Literatur stellt nur einen Teilbereich der verf\u00fcgbaren E-Books dar;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1137;dan;nld;eng;fin;fra;deu;ita;lat;por;rus;spa;swe;tel;downloadable_files_count: 0;United States;http://www.gutenberg.org/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7d4b9ebb-1798-5852-bab9-e5c82de7fe0b",
-    "notes": [
-        "Possibility to download or to browse free electronic books; Angebot: Download von und Online-Zugang zu frei verf\u00fcgbaren E-Books; deutschsprachige Literatur stellt nur einen Teilbereich der verf\u00fcgbaren E-Books dar"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1137"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Project Gutenberg"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7d629a9a-df80-5bb5-811e-97e05a27562e.json b/oaitestdata/clarin-oai_dc/SET_1/json/7d629a9a-df80-5bb5-811e-97e05a27562e.json
deleted file mode 100644
index 90976447..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7d629a9a-df80-5bb5-811e-97e05a27562e.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "NLX-Natural Language and Speech Group, University of Lisbon"
-    ],
-    "Contributor": [
-        "Branco, Ant\u00f3nio",
-        "Silva, Jo\u00e3o"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Portuguese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1229",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1229"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1229",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "NLX-Natural Language and Speech Group, University of Lisbon"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Portugal"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1229;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LX-Tagger;Branco, Ant\u00f3nio;Silva, Jo\u00e3o;Automatic part of speech tagger for Portuguese. Assigns a single morpho-syntactic tag, from the tagset here (http://lxsuite.di.fc.ul.pt/lx-suite.html), to every token. The tag is attached to the token, using a / (slash) symbol as separator: um exemplo \u2192 um/IA exemplo/CN Each individual token in multi-token expressions gets the tag of that expression prefixed by \"L\" and followed by the number of its position within the expression: de maneira a que \u2192 de/LCJ1 maneira/LCJ2 a/LCJ3 que/LCJ4 This tagger was developed with TnT software over 90% of a small, 260k token, accurately hand tagged corpus. Accuracy of 96.87% was obtained.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1229;por;downloadable_files_count: 0;Portugal;NLX-Natural Language and Speech Group, University of Lisbon;http://lxsuite.di.fc.ul.pt",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7d629a9a-df80-5bb5-811e-97e05a27562e",
-    "notes": [
-        "Automatic part of speech tagger for Portuguese. Assigns a single morpho-syntactic tag, from the tagset here (http://lxsuite.di.fc.ul.pt/lx-suite.html), to every token. The tag is attached to the token, using a / (slash) symbol as separator: um exemplo \u2192 um/IA exemplo/CN Each individual token in multi-token expressions gets the tag of that expression prefixed by \"L\" and followed by the number of its position within the expression: de maneira a que \u2192 de/LCJ1 maneira/LCJ2 a/LCJ3 que/LCJ4 This tagger was developed with TnT software over 90% of a small, 260k token, accurately hand tagged corpus. Accuracy of 96.87% was obtained."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1229"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LX-Tagger"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7d6961fd-6923-519a-8096-f4ec3108055a.json b/oaitestdata/clarin-oai_dc/SET_1/json/7d6961fd-6923-519a-8096-f4ec3108055a.json
deleted file mode 100644
index abee8b9f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7d6961fd-6923-519a-8096-f4ec3108055a.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3887",
-    "MetadataAccess": [
-        "oai:ota:oucs:3887"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Bickerstaff, Isaac, 1735-1812."
-    ],
-    "fulltext": "oai:ota:oucs:3887;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3887.xml;Judith: A sacred drama. As it is performed at the Theatre Royal in Drury-Lane. The music composed by Dr. Arne.;Bickerstaff, Isaac, 1735-1812.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7d6961fd-6923-519a-8096-f4ec3108055a",
-    "oai_identifier": [
-        "oai:ota:oucs:3887"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Judith: A sacred drama. As it is performed at the Theatre Royal in Drury-Lane. The music composed by Dr. Arne."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3887.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7d6d2b1d-35c4-5021-975f-06c352095866.json b/oaitestdata/clarin-oai_dc/SET_1/json/7d6d2b1d-35c4-5021-975f-06c352095866.json
deleted file mode 100644
index e4ea1b19..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7d6d2b1d-35c4-5021-975f-06c352095866.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Prus"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 10",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/89",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/89"
-    ],
-    "PID": "http://hdl.handle.net/11321/89",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Prus"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Prus, Prus"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/89;2015-06-07T12:48:05Z;hdl_11321_3;hdl_11321_4;MWE Prus;Prus, Prus;Prus;2015-04-08;corpus;http://hdl.handle.net/11321/89;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 10;Prus",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7d6d2b1d-35c4-5021-975f-06c352095866",
-    "notes": [
-        "Prus"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/89"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Prus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7d81ed84-0f6d-5c52-8e58-fc12a35bfb8b.json b/oaitestdata/clarin-oai_dc/SET_1/json/7d81ed84-0f6d-5c52-8e58-fc12a35bfb8b.json
deleted file mode 100644
index 7ee87a1d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7d81ed84-0f6d-5c52-8e58-fc12a35bfb8b.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Royster, Paul"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3237",
-    "MetadataAccess": [
-        "oai:ota:oucs:3237"
-    ],
-    "PublicationTimestamp": "1878-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1878"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "James, Henry, 1843-1916"
-    ],
-    "fulltext": "oai:ota:oucs:3237;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3237.xml;Europeans;The Europeans;James, Henry, 1843-1916;not after: 1878;text_and_corpus_linguistics;American literature -- 19th century;eng;Oxford Text Archive, University of Oxford;Royster, Paul;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7d81ed84-0f6d-5c52-8e58-fc12a35bfb8b",
-    "oai_identifier": [
-        "oai:ota:oucs:3237"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "American literature -- th century"
-        }
-    ],
-    "title": [
-        "Europeans",
-        "The Europeans"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3237.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7d84ee83-d35d-5576-824c-74f3ec457a14.json b/oaitestdata/clarin-oai_dc/SET_1/json/7d84ee83-d35d-5576-824c-74f3ec457a14.json
deleted file mode 100644
index e3df1869..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7d84ee83-d35d-5576-824c-74f3ec457a14.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "IPI PAN"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/584",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/584"
-    ],
-    "PID": "http://hdl.handle.net/11321/584",
-    "PublicationTimestamp": "2018-07-27T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "IPI PAN"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "BSD 2 Clause",
-        "https://opensource.org/licenses/BSD-2-Clause",
-        "PUB"
-    ],
-    "author": [
-        "\u017bak, Paulina",
-        "Skuczy\u0144ska, Beata"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/584;2018-07-26T15:29:36Z;hdl_11321_3;hdl_11321_4;OptaHopper: phrase-level sentiment with opinion targets;\u017bak, Paulina;Skuczy\u0144ska, Beata;sentiment;A phrase- and sentence-level sentiment analysis tool (deep-learning TreeLSTM, TreeHopper) integrated with opinion finding. Any sentiment dictionary may be used as an input feature, including lemma-level and plWordNet emo dictionaries. In the case of plWordNet emo, provided integration with the WSD module. The OPFI (Opinion Finder) app used for opinion target extraction.;2018-07-27;toolService;http://hdl.handle.net/11321/584;pol;BSD 2 Clause;https://opensource.org/licenses/BSD-2-Clause;PUB;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;IPI PAN",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7d84ee83-d35d-5576-824c-74f3ec457a14",
-    "notes": [
-        "A phrase- and sentence-level sentiment analysis tool (deep-learning TreeLSTM, TreeHopper) integrated with opinion finding. Any sentiment dictionary may be used as an input feature, including lemma-level and plWordNet emo dictionaries. In the case of plWordNet emo, provided integration with the WSD module. The OPFI (Opinion Finder) app used for opinion target extraction."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/584"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "sentiment"
-        }
-    ],
-    "title": [
-        "OptaHopper: phrase-level sentiment with opinion targets"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7d99ac01-4aa8-55f2-9f0d-0734773e23c6.json b/oaitestdata/clarin-oai_dc/SET_1/json/7d99ac01-4aa8-55f2-9f0d-0734773e23c6.json
deleted file mode 100644
index a2464010..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7d99ac01-4aa8-55f2-9f0d-0734773e23c6.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4908-9",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4908-9"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-4908-9",
-    "PublicationTimestamp": "2009-11-02T11:59:59Z",
-    "PublicationYear": [
-        "2009"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-2307"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "Kettnerov\u00e1, V\u00e1clava",
-        "Lopatkov\u00e1, Mark\u00e9ta"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4908-9;2018-07-02T22:05:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;VALLEX 2.5;Lopatkov\u00e1, Mark\u00e9ta;\u017dabokrtsk\u00fd, Zden\u011bk;Kettnerov\u00e1, V\u00e1clava;valency;Czech;The Valency Lexicon of Czech Verbs, Version 2.5 (VALLEX 2.5), is a collection of linguistically annotated data and documentation, resulting from an attempt at formal description of valency frames of Czech verbs. VALLEX 2.5 has been developed at the Institute of Formal and Applied Linguistics, Faculty of Mathematics and Physics, Charles University, Prague.\r\nVALLEX 2.5 provides information on the valency structure (combinatorial potential) of verbs in their particular senses - there are roughly 2,730 lexeme entries containing together around 6,460 lexical units (\"senses\").;2009-11-02;lexicalConceptualResource;http://hdl.handle.net/11858/00-097C-0000-0001-4908-9;ces;http://hdl.handle.net/11234/1-2307;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/vallex/2.5/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7d99ac01-4aa8-55f2-9f0d-0734773e23c6",
-    "notes": [
-        "The Valency Lexicon of Czech Verbs, Version 2.5 (VALLEX 2.5), is a collection of linguistically annotated data and documentation, resulting from an attempt at formal description of valency frames of Czech verbs. VALLEX 2.5 has been developed at the Institute of Formal and Applied Linguistics, Faculty of Mathematics and Physics, Charles University, Prague.\r\nVALLEX 2.5 provides information on the valency structure (combinatorial potential) of verbs in their particular senses - there are roughly 2,730 lexeme entries containing together around 6,460 lexical units (\"senses\")."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4908-9"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "valency"
-        },
-        {
-            "name": "Czech"
-        }
-    ],
-    "title": [
-        "VALLEX 2.5"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7d9a7a74-d324-518e-badc-2036851328dc.json b/oaitestdata/clarin-oai_dc/SET_1/json/7d9a7a74-d324-518e-badc-2036851328dc.json
deleted file mode 100644
index b6a2fee9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7d9a7a74-d324-518e-badc-2036851328dc.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Dutch-Flemish HLT Agency"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1511",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1511"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1511",
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Dutch-Flemish HLT Agency"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "author": [
-        "Dutch Language Union"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1511;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Teaching Dutch in primary and secondary education: a video collection;Dutch Language Union;lessons;\"Teaching Dutch in primary and secondary education: a video collection\" is a collection of approx. 80 hours of filmed lessons in Dutch and Flemish primary and secondary schools. The lessons were collected in a searchable database and they were enriched with metadata and annotations.;2014;corpus;http://hdl.handle.net/11372/LRT-1511;nld;downloadable_files_count: 0;Dutch-Flemish HLT Agency;http://tst-centrale.org/nl/producten/corpora/onderwijs-nederlands-in-beeld-onib/6-91",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7d9a7a74-d324-518e-badc-2036851328dc",
-    "notes": [
-        "\"Teaching Dutch in primary and secondary education: a video collection\" is a collection of approx. 80 hours of filmed lessons in Dutch and Flemish primary and secondary schools. The lessons were collected in a searchable database and they were enriched with metadata and annotations."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1511"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "lessons"
-        }
-    ],
-    "title": [
-        "Teaching Dutch in primary and secondary education: a video collection"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7dab17ee-f93c-591a-8632-e31d8e35d0cf.json b/oaitestdata/clarin-oai_dc/SET_1/json/7dab17ee-f93c-591a-8632-e31d8e35d0cf.json
deleted file mode 100644
index d8c739d2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7dab17ee-f93c-591a-8632-e31d8e35d0cf.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/5",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/5"
-    ],
-    "PID": "http://hdl.handle.net/10794/5",
-    "PublicationTimestamp": "2017-04-28T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/10794/4"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Forsberg, Markus",
-        "Borin, Lars",
-        "L\u00f6nngren, Lennart"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/5;2017-10-27T16:28:55Z;hdl_10794_1;hdl_10794_2;Saldo (2017-10-16);Saldo (2017-10-16);Borin, Lars;L\u00f6nngren, Lennart;Forsberg, Markus;Swedish;Associative;Thesaurus;SALDO (Swedish Associative Thesaurus version 2) is an extensive lexicon resource for modern Swedish written language.;SALDO (Svenskt Associationslexikon version 2) \u00e4r ett semantiskt och morfologiskt lexikon f\u00f6r moderns svenskt skriftspr\u00e5k f\u00f6r spr\u00e5kteknologi.;2017-04-28;lexicalConceptualResource;http://hdl.handle.net/10794/5;swe;http://hdl.handle.net/10794/4;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/saldo",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7dab17ee-f93c-591a-8632-e31d8e35d0cf",
-    "notes": [
-        "SALDO (Swedish Associative Thesaurus version 2) is an extensive lexicon resource for modern Swedish written language.",
-        "SALDO (Svenskt Associationslexikon version 2) \u00e4r ett semantiskt och morfologiskt lexikon f\u00f6r moderns svenskt skriftspr\u00e5k f\u00f6r spr\u00e5kteknologi."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/5"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Associative"
-        },
-        {
-            "name": "Thesaurus"
-        }
-    ],
-    "title": [
-        "Saldo (2017-10-16)",
-        "Saldo (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7db107a8-f7c4-5e16-a789-ee1d03472fbb.json b/oaitestdata/clarin-oai_dc/SET_1/json/7db107a8-f7c4-5e16-a789-ee1d03472fbb.json
deleted file mode 100644
index 07635984..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7db107a8-f7c4-5e16-a789-ee1d03472fbb.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Dept. of Language Technology, Research Institute for Linguistics"
-    ],
-    "Contributor": [
-        "Kata, G\u00e1bor",
-        "Tam\u00e1s, V\u00e1radi",
-        "P\u00e9ter, Vajda",
-        "Viktor, Nagy"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Hungarian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1204",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1204"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1204",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Dept. of Language Technology, Research Institute for Linguistics"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Hungary"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1204;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Hungarian Lexical and Syntactic Resources for NooJ;Tam\u00e1s, V\u00e1radi;Kata, G\u00e1bor;Viktor, Nagy;P\u00e9ter, Vajda;NooJ is a linguistic development environment that includes large-coverage dictionaries and grammars, and parses corpora in real time. The large-coverage lexical resources (morphological and syntactic grammars) for Hungarian might be applied to texts in order to locate morphological, lexical and syntactic patterns and tag simple and compound words.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1204;hun;downloadable_files_count: 0;Hungary;Dept. of Language Technology, Research Institute for Linguistics;http://corpus.nytud.hu/nooj/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7db107a8-f7c4-5e16-a789-ee1d03472fbb",
-    "notes": [
-        "NooJ is a linguistic development environment that includes large-coverage dictionaries and grammars, and parses corpora in real time. The large-coverage lexical resources (morphological and syntactic grammars) for Hungarian might be applied to texts in order to locate morphological, lexical and syntactic patterns and tag simple and compound words."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1204"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Hungarian Lexical and Syntactic Resources for NooJ"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7dbd10ee-2e75-549e-8a26-68232329e3a8.json b/oaitestdata/clarin-oai_dc/SET_1/json/7dbd10ee-2e75-549e-8a26-68232329e3a8.json
deleted file mode 100644
index e6f6838c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7dbd10ee-2e75-549e-8a26-68232329e3a8.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5553",
-    "MetadataAccess": [
-        "oai:ota:oucs:5553"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Philanthropos."
-    ],
-    "fulltext": "oai:ota:oucs:5553;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5553.xml;Mr. Ward's practice of physick, as it relates to the publick, impartially considered. In a letter to Thomas Carew,;Philanthropos.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7dbd10ee-2e75-549e-8a26-68232329e3a8",
-    "oai_identifier": [
-        "oai:ota:oucs:5553"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Mr. Ward's practice of physick, as it relates to the publick, impartially considered. In a letter to Thomas Carew,"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5553.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7dc73b54-a838-562d-9089-ef0e4cc2d485.json b/oaitestdata/clarin-oai_dc/SET_1/json/7dc73b54-a838-562d-9089-ef0e4cc2d485.json
deleted file mode 100644
index 9bf4bcc2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7dc73b54-a838-562d-9089-ef0e4cc2d485.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Orzeszkowa"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 5",
-        "application/zip",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/88",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/88"
-    ],
-    "PID": "http://hdl.handle.net/11321/88",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Orzeszkowa"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Orzeszkowa, Orzeszkowa"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/88;2015-04-14T13:00:33Z;hdl_11321_3;hdl_11321_4;MWE Orzeszkowa;Orzeszkowa, Orzeszkowa;Orzeszkowa;2015-04-08;corpus;http://hdl.handle.net/11321/88;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 5;Orzeszkowa",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7dc73b54-a838-562d-9089-ef0e4cc2d485",
-    "notes": [
-        "Orzeszkowa"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/88"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Orzeszkowa"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7dd897e0-5cd3-543f-99af-06ce8fc1cdf0.json b/oaitestdata/clarin-oai_dc/SET_1/json/7dd897e0-5cd3-543f-99af-06ce8fc1cdf0.json
deleted file mode 100644
index e8f224b1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7dd897e0-5cd3-543f-99af-06ce8fc1cdf0.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 202 KB)"
-    ],
-    "Language": [
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0315",
-    "MetadataAccess": [
-        "oai:ota:oucs:0315"
-    ],
-    "PublicationYear": [
-        "400-430"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Patristic texts -- 1st-5th century period"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Augustine, Saint, Bishop of Hippo"
-    ],
-    "fulltext": "oai:ota:oucs:0315;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0315.xml;Selections;Contra academicos ; Contra Cresconium ; De beata vita ... [excerpts] / Augustine;Augustine, Saint, Bishop of Hippo;400-430;text_and_corpus_linguistics;Anthologies -- 1st-5th century period;lat;Oxford Text Archive, University of Oxford;(1 file : ca. 202 KB);Text;Patristic texts -- 1st-5th century period;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7dd897e0-5cd3-543f-99af-06ce8fc1cdf0",
-    "oai_identifier": [
-        "oai:ota:oucs:0315"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Anthologies -- st-th century period"
-        }
-    ],
-    "title": [
-        "Selections",
-        "Contra academicos ; Contra Cresconium ; De beata vita ... [excerpts] / Augustine"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0315.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7de453e0-1f7e-507f-a402-01fb3bf75f74.json b/oaitestdata/clarin-oai_dc/SET_1/json/7de453e0-1f7e-507f-a402-01fb3bf75f74.json
deleted file mode 100644
index a8882549..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7de453e0-1f7e-507f-a402-01fb3bf75f74.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=a83c9d04cb7a11e1a404080027e73ea2359e10ea62b940109aabe03684aa5ea4",
-    "MetadataAccess": [
-        "a83c9d04cb7a11e1a404080027e73ea2359e10ea62b940109aabe03684aa5ea4"
-    ],
-    "PublicationTimestamp": "2012-11-28T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "fulltext": "a83c9d04cb7a11e1a404080027e73ea2359e10ea62b940109aabe03684aa5ea4;2018-11-15T16:39:39Z;lexicalConceptualResource;lexicalConceptualResource:ontology;Hontology;Hontology (H stands for hotel, hostal and hostel) (available at http://ontolp.inf.pucrs.br/Recursos/downloads-Hontology.php) is a new multilingual ontology for the accommodation sector freely available, containing 282 concepts categorized into 16 top-level concepts. \n\nThe concepts of other vocabularies such as Dbpedia.org and Schema.org. were reused and new concepts and properties from online reviews (e.g. booking.com or realtravel.com) with examples of multilingual texts provided by products and services consumers were integrated and manually annotated with different labels, throught terms correlation, rules (lexical patterns) and synonyms, in four languages by experts, English, Portuguese, Spanish and French. For more informations about the Hontology development, the process is described in Chaves and Trojahn (2010), and Chaves et al. (to appear).\n\nHontology is useful for a wide range of applications within the accommodation sector, including ontology-based information extraction, text annotation and information visualisation.;2012-11-28",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7de453e0-1f7e-507f-a402-01fb3bf75f74",
-    "notes": [
-        "Hontology (H stands for hotel, hostal and hostel) (available at http://ontolp.inf.pucrs.br/Recursos/downloads-Hontology.php) is a new multilingual ontology for the accommodation sector freely available, containing 282 concepts categorized into 16 top-level concepts. \n\nThe concepts of other vocabularies such as Dbpedia.org and Schema.org. were reused and new concepts and properties from online reviews (e.g. booking.com or realtravel.com) with examples of multilingual texts provided by products and services consumers were integrated and manually annotated with different labels, throught terms correlation, rules (lexical patterns) and synonyms, in four languages by experts, English, Portuguese, Spanish and French. For more informations about the Hontology development, the process is described in Chaves and Trojahn (2010), and Chaves et al. (to appear).\n\nHontology is useful for a wide range of applications within the accommodation sector, including ontology-based information extraction, text annotation and information visualisation."
-    ],
-    "oai_identifier": [
-        "a83c9d04cb7a11e1a404080027e73ea2359e10ea62b940109aabe03684aa5ea4"
-    ],
-    "oai_set": [
-        "lexicalConceptualResource",
-        "lexicalConceptualResource:ontology"
-    ],
-    "state": "active",
-    "title": [
-        "Hontology"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7df13bda-34a6-5932-8a18-831de9850bbe.json b/oaitestdata/clarin-oai_dc/SET_1/json/7df13bda-34a6-5932-8a18-831de9850bbe.json
deleted file mode 100644
index efc57def..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7df13bda-34a6-5932-8a18-831de9850bbe.json
+++ /dev/null
@@ -1,100 +0,0 @@
-{
-    "Contact": [
-        "University of Leipzig"
-    ],
-    "Contributor": [
-        "Heyer, Prof. Dr. Gerhard",
-        "Quasthoff, apl. Prof. Dr. Uwe"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Afrikaans",
-        "Albanian",
-        "Bulgarian",
-        "Catalan",
-        "Chinese",
-        "Croatian",
-        "Czech",
-        "Danish",
-        "Dutch",
-        "English",
-        "Esperanto",
-        "Estonian",
-        "Finnish",
-        "French",
-        "German",
-        "Hungarian",
-        "Icelandic",
-        "Indonesian",
-        "Italian",
-        "Japanese",
-        "Korean",
-        "Latin",
-        "Latvian",
-        "Lithuanian",
-        "Malay (macrolanguage)",
-        "Norwegian",
-        "Occitan (post 1500)",
-        "Romanian",
-        "Russian",
-        "Slovak",
-        "Slovenian",
-        "Spanish",
-        "Sundanese",
-        "Swedish",
-        "Tagalog",
-        "Turkish",
-        "Vietnamese",
-        "Welsh"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-704",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-704"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-704",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Leipzig"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-704;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Wortschatz;Heyer, Prof. Dr. Gerhard;Quasthoff, apl. Prof. Dr. Uwe;Collected from newspaper texts, webcrawling, etc.: words (+frequency),  cooccurrences (+graph), left/right neighbours, example sentences;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-704;afr;sqi;bul;cat;zho;hrv;ces;dan;nld;eng;epo;est;fin;fra;deu;hun;isl;ind;ita;jpn;kor;lat;lav;lit;msa;nor;oci;ron;rus;slk;slv;spa;sun;swe;tgl;tur;vie;cym;downloadable_files_count: 0;Germany;University of Leipzig;http://corpora.informatik.uni-leipzig.de/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7df13bda-34a6-5932-8a18-831de9850bbe",
-    "notes": [
-        "Collected from newspaper texts, webcrawling, etc.: words (+frequency),  cooccurrences (+graph), left/right neighbours, example sentences"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-704"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Wortschatz"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7e234c18-7324-501e-a513-b6ce749a352c.json b/oaitestdata/clarin-oai_dc/SET_1/json/7e234c18-7324-501e-a513-b6ce749a352c.json
deleted file mode 100644
index 265995b8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7e234c18-7324-501e-a513-b6ce749a352c.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "PWN"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/vnd.oasis.opendocument.text",
-        "downloadable_files_count: 10",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/395",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/395"
-    ],
-    "PID": "http://hdl.handle.net/11321/395",
-    "PublicationTimestamp": "2017-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "PWN"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Smith, John"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/395;2018-06-13T05:36:13Z;hdl_11321_3;hdl_11321_4;corpus of example texts;Smith, John;no keywords;very interesting corpus;2017-05-30;corpus;http://hdl.handle.net/11321/395;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;application/vnd.oasis.opendocument.text;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;text/plain;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/msword;downloadable_files_count: 10;PWN",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7e234c18-7324-501e-a513-b6ce749a352c",
-    "notes": [
-        "very interesting corpus"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/395"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "keywords"
-        }
-    ],
-    "title": [
-        "corpus of example texts"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7e2825a9-a2a9-5422-90de-02dde697998f.json b/oaitestdata/clarin-oai_dc/SET_1/json/7e2825a9-a2a9-5422-90de-02dde697998f.json
deleted file mode 100644
index b661b130..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7e2825a9-a2a9-5422-90de-02dde697998f.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1154",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1154"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1154",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1154;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Conversations-Lexikon oder kurzgefa\u00dftes Handw\u00f6rterbuch;Germanistik;1. Aufl. 1809-1811; Darstellung der Gegenstandsbereiche gesellschaftlicher Konversation; Ber\u00fccksichtigung bedeutender historischer Ereignisse;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1154;deu;downloadable_files_count: 0;http://www.zeno.org/Brockhaus-1809",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7e2825a9-a2a9-5422-90de-02dde697998f",
-    "notes": [
-        "1. Aufl. 1809-1811; Darstellung der Gegenstandsbereiche gesellschaftlicher Konversation; Ber\u00fccksichtigung bedeutender historischer Ereignisse"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1154"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Conversations-Lexikon oder kurzgefa\u00dftes Handw\u00f6rterbuch"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7e448d7c-d5e8-56f7-8227-16792b83ba98.json b/oaitestdata/clarin-oai_dc/SET_1/json/7e448d7c-d5e8-56f7-8227-16792b83ba98.json
deleted file mode 100644
index 77ae31df..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7e448d7c-d5e8-56f7-8227-16792b83ba98.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Evolutionary Anthropology",
-        "Universit\u00e9 Paris X Nanterre"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-650",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-650"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-650",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Evolutionary Anthropology",
-        "Universit\u00e9 Paris X Nanterre"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Code of conduct"
-    ],
-    "SpatialCoverage": [
-        "Brazil||Peru"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-650;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Cashinahua corpus;Documentation of the Cashinahua project (DoBeS project);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-650;Code of conduct;downloadable_files_count: 0;Brazil||Peru;Max Planck Institute for Evolutionary Anthropology;Universit\u00e9 Paris X Nanterre;http://corpus1.mpi.nl/ds/imdi_browser/?openpath=MPI540784%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7e448d7c-d5e8-56f7-8227-16792b83ba98",
-    "notes": [
-        "Documentation of the Cashinahua project (DoBeS project)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-650"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Cashinahua corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7e5cfcb3-6b49-5bc6-9a86-da6e799d8bde.json b/oaitestdata/clarin-oai_dc/SET_1/json/7e5cfcb3-6b49-5bc6-9a86-da6e799d8bde.json
deleted file mode 100644
index dedbfab2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7e5cfcb3-6b49-5bc6-9a86-da6e799d8bde.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Polish-Japanese Academy of Information Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/524",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/524"
-    ],
-    "PID": "http://hdl.handle.net/11321/524",
-    "PublicationTimestamp": "2018-07-08T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Polish-Japanese Academy of Information Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Marasek, Krzysztof",
-        "Kor\u017einek, Danijel"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/524;2018-07-15T07:54:53Z;hdl_11321_3;hdl_11321_4;Speech Recognition System for Polish: Studio Quality;Kor\u017einek, Danijel;Marasek, Krzysztof;speech recognition;speech alignment;This resource contains dockerized models and scripts of an automatic speech recognition system for Polish trained on studio quality speech. The system is based on the Kaldi toolkit. The scripts include methods for performing speech recognition, forced alignment and a lenient alignment of audio. The Github repository contains information on how to use the tool.;2018-07-08;toolService;http://hdl.handle.net/11321/524;pol;downloadable_files_count: 0;Polish-Japanese Academy of Information Technology;https://hub.docker.com/r/danijel3/clarin-pl-speechtools/tags/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7e5cfcb3-6b49-5bc6-9a86-da6e799d8bde",
-    "notes": [
-        "This resource contains dockerized models and scripts of an automatic speech recognition system for Polish trained on studio quality speech. The system is based on the Kaldi toolkit. The scripts include methods for performing speech recognition, forced alignment and a lenient alignment of audio. The Github repository contains information on how to use the tool."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/524"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech recognition"
-        },
-        {
-            "name": "speech alignment"
-        }
-    ],
-    "title": [
-        "Speech Recognition System for Polish: Studio Quality"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7e87043b-c3ac-55b7-8b85-572627ba8355.json b/oaitestdata/clarin-oai_dc/SET_1/json/7e87043b-c3ac-55b7-8b85-572627ba8355.json
deleted file mode 100644
index 6e29b4c4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7e87043b-c3ac-55b7-8b85-572627ba8355.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4565",
-    "MetadataAccess": [
-        "oai:ota:oucs:4565"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Kelly, Hugh, 1739-1777."
-    ],
-    "fulltext": "oai:ota:oucs:4565;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4565.xml;Memoirs of a Magdalen: or, the history of Louisa Mildmay. Now first published from a series of original letters. In two volumes. ... [pt.1];Kelly, Hugh, 1739-1777.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7e87043b-c3ac-55b7-8b85-572627ba8355",
-    "oai_identifier": [
-        "oai:ota:oucs:4565"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Memoirs of a Magdalen: or, the history of Louisa Mildmay. Now first published from a series of original letters. In two volumes. ... [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4565.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7e8b49ca-d7fc-5872-867c-1d570c1c2546.json b/oaitestdata/clarin-oai_dc/SET_1/json/7e8b49ca-d7fc-5872-867c-1d570c1c2546.json
deleted file mode 100644
index 8e876c28..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7e8b49ca-d7fc-5872-867c-1d570c1c2546.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "3 files ; 542 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1014",
-    "MetadataAccess": [
-        "oai:ota:oucs:1014"
-    ],
-    "PublicationYear": [
-        "unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:1014;2018-03-07T12:15:11Z;http://ota.ox.ac.uk/headers/1014.xml;Quran;unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;3 files ; 542 KB;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7e8b49ca-d7fc-5872-867c-1d570c1c2546",
-    "oai_identifier": [
-        "oai:ota:oucs:1014"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Quran"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1014.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7ea969b5-99b6-5f64-b020-63b2b0213baf.json b/oaitestdata/clarin-oai_dc/SET_1/json/7ea969b5-99b6-5f64-b020-63b2b0213baf.json
deleted file mode 100644
index 2943e4e3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7ea969b5-99b6-5f64-b020-63b2b0213baf.json
+++ /dev/null
@@ -1,288 +0,0 @@
-{
-    "Contact": [
-        "Universal Dependencies Consortium"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 4"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)",
-        "Arabic",
-        "Basque",
-        "Bulgarian",
-        "Croatian",
-        "Czech",
-        "Danish",
-        "Dutch",
-        "English",
-        "Estonian",
-        "Finnish",
-        "French",
-        "German",
-        "Gothic",
-        "Modern Greek (1453-)",
-        "Hebrew",
-        "Hindi",
-        "Hungarian",
-        "Indonesian",
-        "Irish",
-        "Italian",
-        "Japanese",
-        "Latin",
-        "Norwegian",
-        "Church Slavic",
-        "Persian",
-        "Polish",
-        "Portuguese",
-        "Romanian",
-        "Slovenian",
-        "Spanish",
-        "Swedish",
-        "Tamil",
-        "Catalan",
-        "Chinese",
-        "Galician",
-        "Kazakh",
-        "Latvian",
-        "Russian",
-        "Turkish",
-        "Coptic",
-        "Sanskrit",
-        "Slovak",
-        "Ukrainian",
-        "Uighur",
-        "Vietnamese",
-        "Belarusian",
-        "Korean",
-        "Lithuanian",
-        "Urdu"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1983",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1983"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1983",
-    "PublicationTimestamp": "2017-03-13T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Universal Dependencies Consortium"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-1827",
-        "http://hdl.handle.net/11234/1-2515"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Licence Universal Dependencies v2.0",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-2.0",
-        "PUB"
-    ],
-    "author": [
-        "Ion, Radu",
-        "Seraji, Mojgan",
-        "Manning, Christopher",
-        "Cebiro\u011flu Eryi\u011fit, G\u00fcl\u015fen",
-        "Passarotti, Marco",
-        "Nguy\u1ec5n Th\u1ecb, L\u01b0\u01a1ng",
-        "Zhu, Hanzhi",
-        "Osenova, Petya",
-        "Agi\u0107, \u017deljko",
-        "Simionescu, Radu",
-        "Muischnek, Kadri",
-        "Choi, Jinho",
-        "Washington, Jonathan North",
-        "Montemagni, Simonetta",
-        "Davidson, Elizabeth",
-        "Ojala, Stina",
-        "Moskalevskyi, Bohdan",
-        "Seeker, Wolfgang",
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "Sanguinetti, Manuela",
-        "Irimia, Elena",
-        "Simk\u00f3, Katalin",
-        "Hladk\u00e1, Barbora",
-        "Krek, Simon",
-        "G\u00f6k\u0131rmak, Memduh",
-        "L\u00ea H\u1ed3ng, Ph\u01b0\u01a1ng",
-        "\u00d8vrelid, Lilja",
-        "Galbraith, Daniel",
-        "Lenci, Alessandro",
-        "Seddah, Djam\u00e9",
-        "Martins, Andr\u00e9",
-        "Ginter, Filip",
-        "Mititelu, Verginica",
-        "Erjavec, Toma\u017e",
-        "Johannsen, Anders",
-        "Bick, Eckhard",
-        "Mart\u00ednez Alonso, H\u00e9ctor",
-        "Schuster, Sebastian",
-        "Haug, Dag",
-        "Lynn, Teresa",
-        "Plank, Barbara",
-        "Freitas, Cl\u00e1udia",
-        "Varga, Viktor",
-        "Lyashevskaya, Olga",
-        "J\u00f8rgensen, Fredrik",
-        "M\u0103r\u0103nduc, C\u0103t\u0103lina",
-        "Ka\u015f\u0131kara, H\u00fcner",
-        "Pyysalo, Sampo",
-        "Kanerva, Jenna",
-        "Sulubacak, Umut",
-        "Sz\u00e1nt\u00f3, Zsolt",
-        "Chalub, Fabricio",
-        "Ma\u0161ek, Jan",
-        "Atutxa, Aitziber",
-        "Goldberg, Yoav",
-        "Matsumoto, Yuji",
-        "Dozat, Timothy",
-        "G\u00f3mez Guinovart, Xavier",
-        "M\u00fc\u00fcrisep, Kaili",
-        "Saul\u012bte, Baiba",
-        "Bauer, John",
-        "Piitulainen, Jussi",
-        "Nivre, Joakim",
-        "Prokopidis, Prokopis",
-        "Petrov, Slav",
-        "Guillaume, Bruno",
-        "Gr\u016bz\u012btis, Normunds",
-        "Perrier, Guy",
-        "de Marneffe, Marie-Catherine",
-        "Missil\u00e4, Anna",
-        "Dwivedi, Puneet",
-        "Hohle, Petter",
-        "Makazhanov, Aibek",
-        "McDonald, Ryan",
-        "Pretkalni\u0146a, Lauma",
-        "Farkas, Rich\u00e1rd",
-        "Ramasamy, Loganathan",
-        "Bosco, Cristina",
-        "Eli, Marhaba",
-        "Mori, Shunsuke",
-        "de Paiva, Valeria",
-        "Grioni, Matias",
-        "Real, Livy",
-        "Asahara, Masayuki",
-        "Suhr, Alane",
-        "Tanaka, Takaaki",
-        "Miyao, Yusuke",
-        "Vincze, Veronika",
-        "Bhat, Riyaz Ahmad",
-        "Mustafina, Nina",
-        "Garcia, Marcos",
-        "Nguy\u1ec5n Th\u1ecb Minh, Huy\u1ec1n",
-        "Sichinava, Dmitry",
-        "Puolakainen, Tiina",
-        "Tsarfaty, Reut",
-        "Taji, Dima",
-        "Goenaga, Iakes",
-        "Rituma, Laura",
-        "H\u00e0 M\u1ef9, Linh",
-        "Habash, Nizar",
-        "Droganova, Kira",
-        "Shen, Mo",
-        "Connor, Miriam",
-        "Mare\u010dek, David",
-        "Smith, Aaron",
-        "More, Amir",
-        "\u0160imkov\u00e1, M\u00e1ria",
-        "Gajdo\u0161ov\u00e1, Katar\u00edna",
-        "Zeman, Daniel",
-        "Celano, Giuseppe G. A.",
-        "Dobrovoljc, Kaja",
-        "Popel, Martin",
-        "Laippala, Veronika",
-        "Gojenola, Koldo",
-        "Simov, Kiril",
-        "Ballesteros, Miguel",
-        "Nurmi, Hanna",
-        "Nikolaev, Vitaly",
-        "Perez, Cenel-Augusto",
-        "Rademaker, Alexandre",
-        "Tyers, Francis",
-        "Ahrenberg, Lars",
-        "Shakurova, Lena",
-        "Diaz de Ilarraza, Arantza",
-        "Rosa, Rudolf",
-        "Aranzabe, Maria Jesus",
-        "Candito, Marie",
-        "Saleh, Shadi",
-        "Simi, Maria",
-        "Bengoetxea, Kepa",
-        "van Noord, Gertjan",
-        "Zeldes, Amir",
-        "Pascual, Elena",
-        "Bouma, Gosse",
-        "Foster, Jennifer",
-        "\u00c7\u00f6ltekin, \u00c7a\u011fr\u0131",
-        "Uematsu, Sumire",
-        "Gonz\u00e1les Saavedra, Berta",
-        "Uria, Larraitz",
-        "Ljube\u0161i\u0107, Nikola",
-        "Kanayama, Hiroshi",
-        "Haji\u010d, Jan",
-        "Bowman, Sam",
-        "Kotsyba, Natalia",
-        "Silveira, Natalia"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1983;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Universal Dependencies 2.0;Nivre, Joakim;Agi\u0107, \u017deljko;Ahrenberg, Lars;Aranzabe, Maria Jesus;Asahara, Masayuki;Atutxa, Aitziber;Ballesteros, Miguel;Bauer, John;Bengoetxea, Kepa;Bhat, Riyaz Ahmad;Bick, Eckhard;Bosco, Cristina;Bouma, Gosse;Bowman, Sam;Candito, Marie;Cebiro\u011flu Eryi\u011fit, G\u00fcl\u015fen;Celano, Giuseppe G. A.;Chalub, Fabricio;Choi, Jinho;\u00c7\u00f6ltekin, \u00c7a\u011fr\u0131;Connor, Miriam;Davidson, Elizabeth;de Marneffe, Marie-Catherine;de Paiva, Valeria;Diaz de Ilarraza, Arantza;Dobrovoljc, Kaja;Dozat, Timothy;Droganova, Kira;Dwivedi, Puneet;Eli, Marhaba;Erjavec, Toma\u017e;Farkas, Rich\u00e1rd;Foster, Jennifer;Freitas, Cl\u00e1udia;Gajdo\u0161ov\u00e1, Katar\u00edna;Galbraith, Daniel;Garcia, Marcos;Ginter, Filip;Goenaga, Iakes;Gojenola, Koldo;G\u00f6k\u0131rmak, Memduh;Goldberg, Yoav;G\u00f3mez Guinovart, Xavier;Gonz\u00e1les Saavedra, Berta;Grioni, Matias;Gr\u016bz\u012btis, Normunds;Guillaume, Bruno;Habash, Nizar;Haji\u010d, Jan;H\u00e0 M\u1ef9, Linh;Haug, Dag;Hladk\u00e1, Barbora;Hohle, Petter;Ion, Radu;Irimia, Elena;Johannsen, Anders;J\u00f8rgensen, Fredrik;Ka\u015f\u0131kara, H\u00fcner;Kanayama, Hiroshi;Kanerva, Jenna;Kotsyba, Natalia;Krek, Simon;Laippala, Veronika;L\u00ea H\u1ed3ng, Ph\u01b0\u01a1ng;Lenci, Alessandro;Ljube\u0161i\u0107, Nikola;Lyashevskaya, Olga;Lynn, Teresa;Makazhanov, Aibek;Manning, Christopher;M\u0103r\u0103nduc, C\u0103t\u0103lina;Mare\u010dek, David;Mart\u00ednez Alonso, H\u00e9ctor;Martins, Andr\u00e9;Ma\u0161ek, Jan;Matsumoto, Yuji;McDonald, Ryan;Missil\u00e4, Anna;Mititelu, Verginica;Miyao, Yusuke;Montemagni, Simonetta;More, Amir;Mori, Shunsuke;Moskalevskyi, Bohdan;Muischnek, Kadri;Mustafina, Nina;M\u00fc\u00fcrisep, Kaili;Nguy\u1ec5n Th\u1ecb, L\u01b0\u01a1ng;Nguy\u1ec5n Th\u1ecb Minh, Huy\u1ec1n;Nikolaev, Vitaly;Nurmi, Hanna;Ojala, Stina;Osenova, Petya;\u00d8vrelid, Lilja;Pascual, Elena;Passarotti, Marco;Perez, Cenel-Augusto;Perrier, Guy;Petrov, Slav;Piitulainen, Jussi;Plank, Barbara;Popel, Martin;Pretkalni\u0146a, Lauma;Prokopidis, Prokopis;Puolakainen, Tiina;Pyysalo, Sampo;Rademaker, Alexandre;Ramasamy, Loganathan;Real, Livy;Rituma, Laura;Rosa, Rudolf;Saleh, Shadi;Sanguinetti, Manuela;Saul\u012bte, Baiba;Schuster, Sebastian;Seddah, Djam\u00e9;Seeker, Wolfgang;Seraji, Mojgan;Shakurova, Lena;Shen, Mo;Sichinava, Dmitry;Silveira, Natalia;Simi, Maria;Simionescu, Radu;Simk\u00f3, Katalin;\u0160imkov\u00e1, M\u00e1ria;Simov, Kiril;Smith, Aaron;Suhr, Alane;Sulubacak, Umut;Sz\u00e1nt\u00f3, Zsolt;Taji, Dima;Tanaka, Takaaki;Tsarfaty, Reut;Tyers, Francis;Uematsu, Sumire;Uria, Larraitz;van Noord, Gertjan;Varga, Viktor;Vincze, Veronika;Washington, Jonathan North;\u017dabokrtsk\u00fd, Zden\u011bk;Zeldes, Amir;Zeman, Daniel;Zhu, Hanzhi;treebank;dependency;syntax;morphology;harmonized annotation;interset;universal tagset;stanford dependencies;Universal Dependencies is a project that seeks to develop cross-linguistically consistent treebank annotation for many languages, with the goal of facilitating multilingual parser development, cross-lingual learning, and parsing research from a language typology perspective. The annotation scheme is based on (universal) Stanford dependencies (de Marneffe et al., 2006, 2008, 2014), Google universal part-of-speech tags (Petrov et al., 2012), and the Interset interlingua for morphosyntactic tagsets (Zeman, 2008).\r\n\r\nThis release is special in that the treebanks will be used as training/development data in the CoNLL 2017 shared task (http://universaldependencies.org/conll17/). Test data are not released, except for the few treebanks that do not take part in the shared task. 64 treebanks will be in the shared task, and they correspond to the following 45 languages: Ancient Greek, Arabic, Basque, Bulgarian, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, Galician, German, Gothic, Greek, Hebrew, Hindi, Hungarian, Indonesian, Irish, Italian, Japanese, Kazakh, Korean, Latin, Latvian, Norwegian, Old Church Slavonic, Persian, Polish, Portuguese, Romanian, Russian, Slovak, Slovenian, Spanish, Swedish, Turkish, Ukrainian, Urdu, Uyghur and Vietnamese.\r\n\r\nThis release fixes a bug in http://hdl.handle.net/11234/1-1976. Changed files: ud-tools-v2.0.tgz (conllu_to_text.pl, conllu_to_conllx.pl; added text_without_spaces.pl), ud-treebanks-conll2017.tgz (fi_ftb-ud-train.txt, he-ud-train.txt, it-ud-train.txt, pt_br-ud-train.txt, es-ud-train.txt) and ud-treebanks-v2.0.tgz (fi_ftb-ud-train.txt, he-ud-train.txt, it-ud-train.txt, pt_br-ud-train.txt, es-ud-train.txt, ar_nyuad-ud-dev.txt, ar_nyuad-ud-test.txt, ar_nyuad-ud-train.txt, cop-ud-dev.txt, cop-ud-test.txt, cop-ud-train.txt, sa-ud-dev.txt, sa-ud-test.txt, sa-ud-train.txt).;2017-03-13;corpus;http://hdl.handle.net/11234/1-1983;grc;ara;eus;bul;hrv;ces;dan;nld;eng;est;fin;fra;deu;got;ell;heb;hin;hun;ind;gle;ita;jpn;lat;nor;chu;fas;pol;por;ron;slv;spa;swe;tam;cat;zho;glg;kaz;lav;rus;tur;cop;san;slk;ukr;uig;vie;bel;kor;lit;urd;http://hdl.handle.net/11234/1-1827;http://hdl.handle.net/11234/1-2515;Licence Universal Dependencies v2.0;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-2.0;PUB;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Universal Dependencies Consortium;http://universaldependencies.org/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7ea969b5-99b6-5f64-b020-63b2b0213baf",
-    "notes": [
-        "Universal Dependencies is a project that seeks to develop cross-linguistically consistent treebank annotation for many languages, with the goal of facilitating multilingual parser development, cross-lingual learning, and parsing research from a language typology perspective. The annotation scheme is based on (universal) Stanford dependencies (de Marneffe et al., 2006, 2008, 2014), Google universal part-of-speech tags (Petrov et al., 2012), and the Interset interlingua for morphosyntactic tagsets (Zeman, 2008).\r\n\r\nThis release is special in that the treebanks will be used as training/development data in the CoNLL 2017 shared task (http://universaldependencies.org/conll17/). Test data are not released, except for the few treebanks that do not take part in the shared task. 64 treebanks will be in the shared task, and they correspond to the following 45 languages: Ancient Greek, Arabic, Basque, Bulgarian, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, Galician, German, Gothic, Greek, Hebrew, Hindi, Hungarian, Indonesian, Irish, Italian, Japanese, Kazakh, Korean, Latin, Latvian, Norwegian, Old Church Slavonic, Persian, Polish, Portuguese, Romanian, Russian, Slovak, Slovenian, Spanish, Swedish, Turkish, Ukrainian, Urdu, Uyghur and Vietnamese.\r\n\r\nThis release fixes a bug in http://hdl.handle.net/11234/1-1976. Changed files: ud-tools-v2.0.tgz (conllu_to_text.pl, conllu_to_conllx.pl; added text_without_spaces.pl), ud-treebanks-conll2017.tgz (fi_ftb-ud-train.txt, he-ud-train.txt, it-ud-train.txt, pt_br-ud-train.txt, es-ud-train.txt) and ud-treebanks-v2.0.tgz (fi_ftb-ud-train.txt, he-ud-train.txt, it-ud-train.txt, pt_br-ud-train.txt, es-ud-train.txt, ar_nyuad-ud-dev.txt, ar_nyuad-ud-test.txt, ar_nyuad-ud-train.txt, cop-ud-dev.txt, cop-ud-test.txt, cop-ud-train.txt, sa-ud-dev.txt, sa-ud-test.txt, sa-ud-train.txt)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1983"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "dependency"
-        },
-        {
-            "name": "syntax"
-        },
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "harmonized annotation"
-        },
-        {
-            "name": "interset"
-        },
-        {
-            "name": "universal tagset"
-        },
-        {
-            "name": "stanford dependencies"
-        }
-    ],
-    "title": [
-        "Universal Dependencies 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7eb46cfc-6584-5afe-9af9-b8c7fdb0a03c.json b/oaitestdata/clarin-oai_dc/SET_1/json/7eb46cfc-6584-5afe-9af9-b8c7fdb0a03c.json
deleted file mode 100644
index fa5ed471..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7eb46cfc-6584-5afe-9af9-b8c7fdb0a03c.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-683",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-683"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-683",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Code of conduct"
-    ],
-    "SpatialCoverage": [
-        "Bolivia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-683;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Movima corpus;Documentation of the Movima project (DoBeS project);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-683;Code of conduct;downloadable_files_count: 0;Bolivia;http://corpus1.mpi.nl/ds/imdi_browser/?openpath=MPI515581%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7eb46cfc-6584-5afe-9af9-b8c7fdb0a03c",
-    "notes": [
-        "Documentation of the Movima project (DoBeS project)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-683"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Movima corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7ed3452b-b068-55b9-9357-abf89673d010.json b/oaitestdata/clarin-oai_dc/SET_1/json/7ed3452b-b068-55b9-9357-abf89673d010.json
deleted file mode 100644
index b48bf8af..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7ed3452b-b068-55b9-9357-abf89673d010.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Royster, Paul"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 1.63 MB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1588",
-    "MetadataAccess": [
-        "oai:ota:oucs:1588"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "James, Henry, 1843-1916"
-    ],
-    "fulltext": "oai:ota:oucs:1588;2018-02-16T10:42:06Z;http://ota.ox.ac.uk/headers/1588.xml;English writers : [Henry James] / Henry James;James, Henry, 1843-1916;text_and_corpus_linguistics;American literature -- 19th century;Oxford Text Archive, University of Oxford;Royster, Paul;text/sgml;(1 file : ca. 1.63 MB);Text;Novels;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7ed3452b-b068-55b9-9357-abf89673d010",
-    "oai_identifier": [
-        "oai:ota:oucs:1588"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "American literature -- th century"
-        }
-    ],
-    "title": [
-        "English writers : [Henry James] / Henry James"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1588.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7edf3d0e-2d8e-57a7-b2b0-e71bf174ce52.json b/oaitestdata/clarin-oai_dc/SET_1/json/7edf3d0e-2d8e-57a7-b2b0-e71bf174ce52.json
deleted file mode 100644
index b71e79d8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7edf3d0e-2d8e-57a7-b2b0-e71bf174ce52.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3581",
-    "MetadataAccess": [
-        "oai:ota:oucs:3581"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Goldsmith, Oliver, 1730?-1774."
-    ],
-    "fulltext": "oai:ota:oucs:3581;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3581.xml;She stoops to conquer: or, the mistakes of a night. A comedy. As it is acted at the Theatre-Royal in Covent-Garden. Written by Doctor Goldsmith.;Goldsmith, Oliver, 1730?-1774.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7edf3d0e-2d8e-57a7-b2b0-e71bf174ce52",
-    "oai_identifier": [
-        "oai:ota:oucs:3581"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "She stoops to conquer: or, the mistakes of a night. A comedy. As it is acted at the Theatre-Royal in Covent-Garden. Written by Doctor Goldsmith."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3581.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7ef866aa-6922-5b6f-a755-b4908bea7d1c.json b/oaitestdata/clarin-oai_dc/SET_1/json/7ef866aa-6922-5b6f-a755-b4908bea7d1c.json
deleted file mode 100644
index eacb4c8f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7ef866aa-6922-5b6f-a755-b4908bea7d1c.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Craig, Hugh"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3248",
-    "MetadataAccess": [
-        "oai:ota:oucs:3248"
-    ],
-    "PublicationTimestamp": "1607-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1607"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Jonson, Ben, 1573?-1637"
-    ],
-    "fulltext": "oai:ota:oucs:3248;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3248.xml;Volpone;Volpone;The foxe;Jonson, Ben, 1573?-1637;not after: 1607;text_and_corpus_linguistics;English drama -- 17th century;eng;Oxford Text Archive, University of Oxford;Craig, Hugh;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7ef866aa-6922-5b6f-a755-b4908bea7d1c",
-    "oai_identifier": [
-        "oai:ota:oucs:3248"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- th century"
-        }
-    ],
-    "title": [
-        "Volpone",
-        "Volpone",
-        "The foxe"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3248.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7efbc3d6-cc63-5f35-bbda-e59ac8d20eb2.json b/oaitestdata/clarin-oai_dc/SET_1/json/7efbc3d6-cc63-5f35-bbda-e59ac8d20eb2.json
deleted file mode 100644
index 4d8bbfba..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7efbc3d6-cc63-5f35-bbda-e59ac8d20eb2.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/36",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/36"
-    ],
-    "PID": "http://hdl.handle.net/11321/36",
-    "PublicationTimestamp": "2014-05-19T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Warzocha, Rados\u0142aw",
-        "Radziszewski, Adam"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/36;2016-01-21T14:22:06Z;hdl_11321_3;hdl_11321_4;WCRFT2;Radziszewski, Adam;Warzocha, Rados\u0142aw;WCRFT is a morphosyntactic tagger for Polish. The tagger brings together Conditional Random Fields (CRF) and tiered tagging of plain tekst.;2014-05-19;toolService;http://hdl.handle.net/11321/36;pol;downloadable_files_count: 0;Wroc\u0142aw University of Technology;http://nlp.pwr.wroc.pl/redmine/projects/wcrft/wiki/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7efbc3d6-cc63-5f35-bbda-e59ac8d20eb2",
-    "notes": [
-        "WCRFT is a morphosyntactic tagger for Polish. The tagger brings together Conditional Random Fields (CRF) and tiered tagging of plain tekst."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/36"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "WCRFT2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7f50b236-aaa9-5575-b8e9-3ed7f740d62b.json b/oaitestdata/clarin-oai_dc/SET_1/json/7f50b236-aaa9-5575-b8e9-3ed7f740d62b.json
deleted file mode 100644
index 692fd27f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7f50b236-aaa9-5575-b8e9-3ed7f740d62b.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Instytut Neofilologii UP"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/zip",
-        "application/vnd.oasis.opendocument.text",
-        "downloadable_files_count: 13",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/407",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/407"
-    ],
-    "PID": "http://hdl.handle.net/11321/407",
-    "PublicationTimestamp": "2017-06-29T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Instytut Neofilologii UP"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Gajewska, Anna"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/407;2019-01-31T10:43:39Z;hdl_11321_3;hdl_11321_4;korpus testowy;Gajewska, Anna;korpus;Polish;novel;korpus testowy warsztat\u00f3w Dspace;2017-06-29;corpus;http://hdl.handle.net/11321/407;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;text/plain;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;text/plain;application/zip;application/zip;application/zip;downloadable_files_count: 13;Instytut Neofilologii UP",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7f50b236-aaa9-5575-b8e9-3ed7f740d62b",
-    "notes": [
-        "korpus testowy warsztat\u00f3w Dspace"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/407"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "korpus"
-        },
-        {
-            "name": "Polish"
-        },
-        {
-            "name": "novel"
-        }
-    ],
-    "title": [
-        "korpus testowy"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7f6488e9-d641-599d-9ccf-689f107cc3ea.json b/oaitestdata/clarin-oai_dc/SET_1/json/7f6488e9-d641-599d-9ccf-689f107cc3ea.json
deleted file mode 100644
index a94345ec..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7f6488e9-d641-599d-9ccf-689f107cc3ea.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/pdf"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/281",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/281"
-    ],
-    "PID": "http://hdl.handle.net/11321/281",
-    "PublicationTimestamp": "2016-04-25T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Nowak, Joanna",
-        "Maziarz, Marek",
-        "Wieczorek, Jan",
-        "Marci\u0144czuk, Micha\u0142",
-        "Wardy\u0144ski, Adam",
-        "Radziszewski, Adam",
-        "Oleksy, Marcin",
-        "Piasecki, Maciej"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/281;2016-06-03T13:12:59Z;hdl_11321_3;hdl_11321_4;KPWr annotation guidelines - coreference;Maziarz, Marek;Marci\u0144czuk, Micha\u0142;Oleksy, Marcin;Piasecki, Maciej;Radziszewski, Adam;Nowak, Joanna;Wardy\u0144ski, Adam;Wieczorek, Jan;coreference;annotation guidelines;corpora annotation;Coreference annotation guidelines describing the process of manual annotation of documents in Polish Corpus of Wroc\u0142aw University of Technology (KPWr);2016-04-25;languageDescription;http://hdl.handle.net/11321/281;pol;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;application/pdf;downloadable_files_count: 1;Wroc\u0142aw University of Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7f6488e9-d641-599d-9ccf-689f107cc3ea",
-    "notes": [
-        "Coreference annotation guidelines describing the process of manual annotation of documents in Polish Corpus of Wroc\u0142aw University of Technology (KPWr)"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/281"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "coreference"
-        },
-        {
-            "name": "annotation guidelines"
-        },
-        {
-            "name": "corpora annotation"
-        }
-    ],
-    "title": [
-        "KPWr annotation guidelines - coreference"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7f6e8e71-a40c-5025-96ef-3a020f3fda64.json b/oaitestdata/clarin-oai_dc/SET_1/json/7f6e8e71-a40c-5025-96ef-3a020f3fda64.json
deleted file mode 100644
index 3701615d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7f6e8e71-a40c-5025-96ef-3a020f3fda64.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Barkatulla, A.K."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 511 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1290",
-    "MetadataAccess": [
-        "oai:ota:oucs:1290"
-    ],
-    "PublicationTimestamp": "1986-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1986"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Indexes"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Khan, Abdur Rauf"
-    ],
-    "fulltext": "oai:ota:oucs:1290;2018-03-06T16:27:17Z;http://ota.ox.ac.uk/headers/1290.xml;Thematic index to the Qur'an / Abdur Rauf Khan;Khan, Abdur Rauf;1986;text_and_corpus_linguistics;Koran -- Indexes;eng;Oxford Text Archive, University of Oxford;Barkatulla, A.K.;text/plain;(1 file : ca. 511 KB);Text;Indexes;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7f6e8e71-a40c-5025-96ef-3a020f3fda64",
-    "oai_identifier": [
-        "oai:ota:oucs:1290"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Koran -- Indexes"
-        }
-    ],
-    "title": [
-        "Thematic index to the Qur'an / Abdur Rauf Khan"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1290.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7f8e5833-842d-569c-bc69-f6b2f85705b4.json b/oaitestdata/clarin-oai_dc/SET_1/json/7f8e5833-842d-569c-bc69-f6b2f85705b4.json
deleted file mode 100644
index 13ec264c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7f8e5833-842d-569c-bc69-f6b2f85705b4.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=834dfa6ca12a11e6a2aa782bcb074135a731473a10da4b04b0523d389854400d",
-    "MetadataAccess": [
-        "834dfa6ca12a11e6a2aa782bcb074135a731473a10da4b04b0523d389854400d"
-    ],
-    "PublicationTimestamp": "2016-11-03T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "fulltext": "834dfa6ca12a11e6a2aa782bcb074135a731473a10da4b04b0523d389854400d;2018-11-15T16:40:24Z;corpus;corpus:text;QTLeap News Corpus;This corpus is a sample extracted from the corpus made available by the annual workshops/conferences on Statistical Machine Translation (WMT, see \\url{http://www.statmt.org/}) from the News domain. To this end, 1104 English sentences and their corresponding human translations into Czech, German and Spanish from WMT 2012 and WMT 2013 translation tasks were taken as basis. \nAs not all project languages are represented at WMT, the missing translations have been produced by professional translators. These 1104 English sentences were then professionally translated to Bulgarian, Dutch, Portuguese and Basque via a subcontract from QTLeap.\nThe sentences were chosen such that their original source language was English, i.e., \u00e2\u0080\u009creversed translations\u00e2\u0080\u009d originating from languages other than English that exist in the WMT datasets have been ignored. \n;2016-11-03",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7f8e5833-842d-569c-bc69-f6b2f85705b4",
-    "notes": [
-        "This corpus is a sample extracted from the corpus made available by the annual workshops/conferences on Statistical Machine Translation (WMT, see \\url{http://www.statmt.org/}) from the News domain. To this end, 1104 English sentences and their corresponding human translations into Czech, German and Spanish from WMT 2012 and WMT 2013 translation tasks were taken as basis. \nAs not all project languages are represented at WMT, the missing translations have been produced by professional translators. These 1104 English sentences were then professionally translated to Bulgarian, Dutch, Portuguese and Basque via a subcontract from QTLeap.\nThe sentences were chosen such that their original source language was English, i.e., \u00e2\u0080\u009creversed translations\u00e2\u0080\u009d originating from languages other than English that exist in the WMT datasets have been ignored. \n"
-    ],
-    "oai_identifier": [
-        "834dfa6ca12a11e6a2aa782bcb074135a731473a10da4b04b0523d389854400d"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "QTLeap News Corpus"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7f9a72e6-e8d0-5ce6-84be-99acb5dd0b48.json b/oaitestdata/clarin-oai_dc/SET_1/json/7f9a72e6-e8d0-5ce6-84be-99acb5dd0b48.json
deleted file mode 100644
index c7db2f30..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7f9a72e6-e8d0-5ce6-84be-99acb5dd0b48.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 201 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2229",
-    "MetadataAccess": [
-        "oai:ota:oucs:2229"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Comedies"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Shakespeare, William, 1564-1616",
-        "Fletcher, John, 1579-1625"
-    ],
-    "fulltext": "oai:ota:oucs:2229;2018-10-16T09:05:42Z;http://ota.ox.ac.uk/headers/2229.xml;Two noble kinsmen;Fletcher, John, 1579-1625;Shakespeare, William, 1564-1616;default: 1976-01-01;text_and_corpus_linguistics;Plays -- England -- 17th century;Comedies -- England -- 17th century;eng;Oxford Text Archive, University of Oxford;(1 file : ca. 201 KB);Text;Comedies;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7f9a72e6-e8d0-5ce6-84be-99acb5dd0b48",
-    "oai_identifier": [
-        "oai:ota:oucs:2229"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        },
-        {
-            "name": "Comedies -- England -- th century"
-        }
-    ],
-    "title": [
-        "Two noble kinsmen"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2229.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7f9aaea8-0779-5c91-a73b-99b21c386f65.json b/oaitestdata/clarin-oai_dc/SET_1/json/7f9aaea8-0779-5c91-a73b-99b21c386f65.json
deleted file mode 100644
index 79499b30..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7f9aaea8-0779-5c91-a73b-99b21c386f65.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "267 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1240",
-    "MetadataAccess": [
-        "oai:ota:oucs:1240"
-    ],
-    "PublicationTimestamp": "1513-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1513"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Barclay, Alexander,  1475?-1552"
-    ],
-    "fulltext": "oai:ota:oucs:1240;2018-03-05T17:31:43Z;http://ota.ox.ac.uk/headers/1240.xml;The eclogues of Alexander Barclay / compiled by Greg Waite;Barclay, Alexander,  1475?-1552;1513;text_and_corpus_linguistics;Poems -- England -- 16th century;eng;Oxford Text Archive, University of Oxford;267 KB;Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7f9aaea8-0779-5c91-a73b-99b21c386f65",
-    "oai_identifier": [
-        "oai:ota:oucs:1240"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- England -- th century"
-        }
-    ],
-    "title": [
-        "The eclogues of Alexander Barclay / compiled by Greg Waite"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1240.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7fbbc1cc-264a-5245-9805-3838a5165614.json b/oaitestdata/clarin-oai_dc/SET_1/json/7fbbc1cc-264a-5245-9805-3838a5165614.json
deleted file mode 100644
index c02dfba0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7fbbc1cc-264a-5245-9805-3838a5165614.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Bolz, Norbert W."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 30 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0672",
-    "MetadataAccess": [
-        "oai:ota:oucs:0672"
-    ],
-    "PublicationTimestamp": "1592-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1592"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Satires"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Greene, Robert, 1558?-1592"
-    ],
-    "fulltext": "oai:ota:oucs:0672;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0672.xml;The black book's messenger / by Robert Greene;Greene, Robert, 1558?-1592;1592;text_and_corpus_linguistics;Satire, English -- 16th century;eng;Oxford Text Archive, University of Oxford;Bolz, Norbert W.;(1 file : ca. 30 KB);Text;Satires;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7fbbc1cc-264a-5245-9805-3838a5165614",
-    "oai_identifier": [
-        "oai:ota:oucs:0672"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Satire"
-        },
-        {
-            "name": "English -- th century"
-        }
-    ],
-    "title": [
-        "The black book's messenger / by Robert Greene"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0672.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/7fe1b54e-c4a4-5711-aa62-180f146615a5.json b/oaitestdata/clarin-oai_dc/SET_1/json/7fe1b54e-c4a4-5711-aa62-180f146615a5.json
deleted file mode 100644
index 640c9206..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/7fe1b54e-c4a4-5711-aa62-180f146615a5.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Maciej Duklewski"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 86",
-        "text/plain; charset=utf-8",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/509",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/509"
-    ],
-    "PID": "http://hdl.handle.net/11321/509",
-    "PublicationTimestamp": "2018-07-13T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Maciej Duklewski"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "Duklewski, Maciej"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/509;2018-07-13T13:48:51Z;hdl_11321_3;hdl_11321_4;Korpus testowy;Duklewski, Maciej;test;Du\u017cy Pok\u00f3j;2018-07-13;corpus;http://hdl.handle.net/11321/509;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;downloadable_files_count: 86;Maciej Duklewski",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7fe1b54e-c4a4-5711-aa62-180f146615a5",
-    "notes": [
-        "Du\u017cy Pok\u00f3j"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/509"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "test"
-        }
-    ],
-    "title": [
-        "Korpus testowy"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8003d9eb-645e-56ff-8326-03d13cb6e123.json b/oaitestdata/clarin-oai_dc/SET_1/json/8003d9eb-645e-56ff-8326-03d13cb6e123.json
deleted file mode 100644
index 12755ecd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8003d9eb-645e-56ff-8326-03d13cb6e123.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "University of Luxembourg"
-    ],
-    "Contributor": [
-        "Gilles, Peter"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Luxembourgish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1124",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1124"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1124",
-    "PublicationTimestamp": "2010-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "University of Luxembourg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Germany||Luxembourg"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1124;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Dictionaries of Luxembourgish;Gilles, Peter;Online database of three older dictionaries of Luxembourgish from 1849, 1905, and 1950;2010;corpus;http://hdl.handle.net/11372/LRT-1124;ltz;application/octet-stream;downloadable_files_count: 0;Germany||Luxembourg;University of Luxembourg;http://infolux.uni.lu/worterbucher/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8003d9eb-645e-56ff-8326-03d13cb6e123",
-    "notes": [
-        "Online database of three older dictionaries of Luxembourgish from 1849, 1905, and 1950"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1124"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Dictionaries of Luxembourgish"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8043c368-8c15-5c42-a56c-47858a4c1bdf.json b/oaitestdata/clarin-oai_dc/SET_1/json/8043c368-8c15-5c42-a56c-47858a4c1bdf.json
deleted file mode 100644
index 631f1e71..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8043c368-8c15-5c42-a56c-47858a4c1bdf.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Estonian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-258",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-258"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-258",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Estonia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-258;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Shallow syntactically disambiguated corpus;written general; 300 000 words; local tagset (POS, syntactic functions);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-258;est;downloadable_files_count: 0;Estonia;http://www.ut.ee/~kaili/Korpus/Syntax",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8043c368-8c15-5c42-a56c-47858a4c1bdf",
-    "notes": [
-        "written general; 300 000 words; local tagset (POS, syntactic functions)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-258"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Shallow syntactically disambiguated corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8047ae02-22fd-5474-a40a-f9b49fdd8555.json b/oaitestdata/clarin-oai_dc/SET_1/json/8047ae02-22fd-5474-a40a-f9b49fdd8555.json
deleted file mode 100644
index 6150cfb6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8047ae02-22fd-5474-a40a-f9b49fdd8555.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "less than 512 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0435",
-    "MetadataAccess": [
-        "oai:ota:oucs:0435"
-    ],
-    "PublicationTimestamp": "1969-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1969"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "England, Barry"
-    ],
-    "fulltext": "oai:ota:oucs:0435;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0435.xml; Conduct unbecoming  / compiled by Dirk Geens;England, Barry;1969;text_and_corpus_linguistics;Plays -- Great Britain -- 20th century;eng;Forms part of the Louvain corpus of modern English drama deposited in 1983. The text does not conform to modern standards of text encoding. The text is all capitals, with words broken over line boundaries, undocumented markup characters, and numeric codes for the identities of the players. ;Oxford Text Archive, University of Oxford;less than 512 KB;Text;Plays;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8047ae02-22fd-5474-a40a-f9b49fdd8555",
-    "notes": [
-        "Forms part of the Louvain corpus of modern English drama deposited in 1983. The text does not conform to modern standards of text encoding. The text is all capitals, with words broken over line boundaries, undocumented markup characters, and numeric codes for the identities of the players. "
-    ],
-    "oai_identifier": [
-        "oai:ota:oucs:0435"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        " Conduct unbecoming  / compiled by Dirk Geens"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0435.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8062789b-6058-52b1-8627-424b50918ef2.json b/oaitestdata/clarin-oai_dc/SET_1/json/8062789b-6058-52b1-8627-424b50918ef2.json
deleted file mode 100644
index 2d98b07c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8062789b-6058-52b1-8627-424b50918ef2.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3771",
-    "MetadataAccess": [
-        "oai:ota:oucs:3771"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gilpin, William, 1724-1804."
-    ],
-    "fulltext": "oai:ota:oucs:3771;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3771.xml;An explanation of the duties of religion, for the use of Boldre School, in New Forest. N.B. The small paper prefixed, which is the ground-work of this explanation, is distributed in little books among the children of the parish,;Gilpin, William, 1724-1804.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8062789b-6058-52b1-8627-424b50918ef2",
-    "oai_identifier": [
-        "oai:ota:oucs:3771"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An explanation of the duties of religion, for the use of Boldre School, in New Forest. N.B. The small paper prefixed, which is the ground-work of this explanation, is distributed in little books among the children of the parish,"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3771.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/80644f7e-b12d-5c07-9ae7-5c96234b2649.json b/oaitestdata/clarin-oai_dc/SET_1/json/80644f7e-b12d-5c07-9ae7-5c96234b2649.json
deleted file mode 100644
index 0853df52..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/80644f7e-b12d-5c07-9ae7-5c96234b2649.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/101",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/101"
-    ],
-    "PID": "http://hdl.handle.net/10794/101",
-    "PublicationTimestamp": "2013-03-06T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/101;2017-10-25T11:27:44Z;hdl_10794_1;hdl_10794_2;Blog mix 2007 (2017-02-17);Bloggmix 2007 (2017-02-17);n/a, n/a;Swedish;Blog;The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.;Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat.;2013-03-06;corpus;http://hdl.handle.net/10794/101;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/bloggmix2007",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "80644f7e-b12d-5c07-9ae7-5c96234b2649",
-    "notes": [
-        "The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.",
-        "Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/101"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Blog"
-        }
-    ],
-    "title": [
-        "Blog mix 2007 (2017-02-17)",
-        "Bloggmix 2007 (2017-02-17)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8086d59a-6712-5bff-9480-54534a3cb4ea.json b/oaitestdata/clarin-oai_dc/SET_1/json/8086d59a-6712-5bff-9480-54534a3cb4ea.json
deleted file mode 100644
index 45f2c17a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8086d59a-6712-5bff-9480-54534a3cb4ea.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3584",
-    "MetadataAccess": [
-        "oai:ota:oucs:3584"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Brown, John, 1715-1766."
-    ],
-    "fulltext": "oai:ota:oucs:3584;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3584.xml;An additional dialogue of the dead, between Pericles and Aristides: being a sequel to the dialogue between Pericles and Cosmo;Brown, John, 1715-1766.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8086d59a-6712-5bff-9480-54534a3cb4ea",
-    "oai_identifier": [
-        "oai:ota:oucs:3584"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An additional dialogue of the dead, between Pericles and Aristides: being a sequel to the dialogue between Pericles and Cosmo"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3584.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/80a7411a-d840-5153-975c-288b1d02a8bb.json b/oaitestdata/clarin-oai_dc/SET_1/json/80a7411a-d840-5153-975c-288b1d02a8bb.json
deleted file mode 100644
index b573adb6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/80a7411a-d840-5153-975c-288b1d02a8bb.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 3",
-        "application/pdf",
-        "text/html",
-        "text/plain; charset=utf-8"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4902-6",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4902-6"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-4902-6",
-    "PublicationTimestamp": "2009-11-02T09:27:18Z",
-    "PublicationYear": [
-        "2009"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Hana, Ji\u0159\u00ed"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4902-6;2018-07-02T22:05:53Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;LAW;Hana, Ji\u0159\u00ed;language annotation;Lexical Annotation Workbench (LAW) is an integrated environment for morphological annotation. It supports simple morphological annotation (assigning a lemma and tag to a word), integration and comparison of different annotations of the same text, searching for particular word, tag etc.;2009-11-02T09:27:18Z;toolService;http://hdl.handle.net/11858/00-097C-0000-0001-4902-6;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;PUB;text/html;application/pdf;application/zip;text/plain; charset=utf-8;downloadable_files_count: 3;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://purl.org/net/jh/law",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "80a7411a-d840-5153-975c-288b1d02a8bb",
-    "notes": [
-        "Lexical Annotation Workbench (LAW) is an integrated environment for morphological annotation. It supports simple morphological annotation (assigning a lemma and tag to a word), integration and comparison of different annotations of the same text, searching for particular word, tag etc."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4902-6"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "language annotation"
-        }
-    ],
-    "title": [
-        "LAW"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/80ac41b2-c59b-5bc5-a32c-dd048e5de07a.json b/oaitestdata/clarin-oai_dc/SET_1/json/80ac41b2-c59b-5bc5-a32c-dd048e5de07a.json
deleted file mode 100644
index 1cfa7353..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/80ac41b2-c59b-5bc5-a32c-dd048e5de07a.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-962",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-962"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-962",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-962;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Udi;ca. 200.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-962;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#udica",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "80ac41b2-c59b-5bc5-a32c-dd048e5de07a",
-    "notes": [
-        "ca. 200.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-962"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Udi"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/80b2a875-1a88-5832-aeb6-e4b927bd5322.json b/oaitestdata/clarin-oai_dc/SET_1/json/80b2a875-1a88-5832-aeb6-e4b927bd5322.json
deleted file mode 100644
index 4a78f2c1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/80b2a875-1a88-5832-aeb6-e4b927bd5322.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 4",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1456",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1456"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1456",
-    "PublicationTimestamp": "2014-11-05T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-2514"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU General Public Licence, version 3",
-        "http://opensource.org/licenses/GPL-3.0",
-        "PUB"
-    ],
-    "author": [
-        "Rosa, Rudolf"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1456;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Terminal-based CoNLL-file viewer;Rosa, Rudolf;conll;terminal;console;text-based;file-viewer;A simple way of browsing CoNLL format files in your terminal. Fast and text-based.;2014-11-05;toolService;http://hdl.handle.net/11234/1-1456;eng;http://hdl.handle.net/11234/1-2514;GNU General Public Licence, version 3;http://opensource.org/licenses/GPL-3.0;PUB;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 4;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "80b2a875-1a88-5832-aeb6-e4b927bd5322",
-    "notes": [
-        "A simple way of browsing CoNLL format files in your terminal. Fast and text-based."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1456"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "conll"
-        },
-        {
-            "name": "terminal"
-        },
-        {
-            "name": "console"
-        },
-        {
-            "name": "text-based"
-        },
-        {
-            "name": "file-viewer"
-        }
-    ],
-    "title": [
-        "Terminal-based CoNLL-file viewer"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/80e5141e-7325-5e27-91d2-21672d41762a.json b/oaitestdata/clarin-oai_dc/SET_1/json/80e5141e-7325-5e27-91d2-21672d41762a.json
deleted file mode 100644
index 05894d28..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/80e5141e-7325-5e27-91d2-21672d41762a.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Forskning.no"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain"
-    ],
-    "Language": [
-        "Norwegian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/80",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/80"
-    ],
-    "PID": "http://hdl.handle.net/11509/80",
-    "PublicationTimestamp": "2013-05-20T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Forskning.no"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN_RES-DEP-*",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaRes?ID=1&PERM=1&PLAN=1&BY=1&NORED=1&DEP=1",
-        "RES"
-    ],
-    "author": [
-        "Kristiansen, Nina"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/80;2016-06-01T12:04:16Z;hdl_11509_1;hdl_11509_2;Forskning.no;Kristiansen, Nina;Science;Data set containing texts from the popular science website Forskning.no.\r\n The text material is constituted by articles published by Forskning.no (CLARINO's agreement also includes the permission to use future articles to be published by Forskning.no) belonging to the following three categories:\r\n1) Articles written by journalists employed at Forskning.no\r\n2) Articles written by member institutions of Forskning.no (76 universities, colleges, research\r\ncenters, research departments in government agencies and more). These articles are written by staff journalists, information officers and other non-academic staff. Each article has been edited by Forskning.no.\r\n3) Articles from the newsdesk NRK Viten, with whom Forskning.no cooperates. These articles are written by NRK journalists. A full list of partner/cooperation institutions may be presented on demand.;2013-05-20;corpus;http://hdl.handle.net/11509/80;nor;CLARIN_RES-DEP-*;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaRes?ID=1&PERM=1&PLAN=1&BY=1&NORED=1&DEP=1;RES;application/gzip;text/plain;downloadable_files_count: 1;Forskning.no",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "80e5141e-7325-5e27-91d2-21672d41762a",
-    "notes": [
-        "Data set containing texts from the popular science website Forskning.no.\r\n The text material is constituted by articles published by Forskning.no (CLARINO's agreement also includes the permission to use future articles to be published by Forskning.no) belonging to the following three categories:\r\n1) Articles written by journalists employed at Forskning.no\r\n2) Articles written by member institutions of Forskning.no (76 universities, colleges, research\r\ncenters, research departments in government agencies and more). These articles are written by staff journalists, information officers and other non-academic staff. Each article has been edited by Forskning.no.\r\n3) Articles from the newsdesk NRK Viten, with whom Forskning.no cooperates. These articles are written by NRK journalists. A full list of partner/cooperation institutions may be presented on demand."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/80"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Science"
-        }
-    ],
-    "title": [
-        "Forskning.no"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/80ea454e-2e10-5885-93b9-c00042e93a09.json b/oaitestdata/clarin-oai_dc/SET_1/json/80ea454e-2e10-5885-93b9-c00042e93a09.json
deleted file mode 100644
index 0626f160..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/80ea454e-2e10-5885-93b9-c00042e93a09.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-67",
-    "MetadataAccess": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-67"
-    ],
-    "PID": "http://hdl.handle.net/20.500.11752/ILC-67",
-    "PublicationTimestamp": "2016-11-16T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "author": [
-        "AA. VV., AA. VV."
-    ],
-    "fulltext": "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-67;2018-07-23T09:13:43Z;hdl_000-c0-111_38;hdl_000-c0-111_49;Dialoghi Italiani di Giordano Bruno;AA. VV., AA. VV.;Philosophy;Religion;Science;This collection of the works of Giordano Bruno was packaged in the 70s - 80s in cooperation with the Insitute for the European Intellectual Lexicon, then called Study Centre of the CNR, ILIESI today.\r\n\r\nThe first works in this collection were originally encoded on mechanographic punched cards around 1969, at the beginning of the humanities computing era.;2016-11-16;corpus;http://hdl.handle.net/20.500.11752/ILC-67;ita;downloadable_files_count: 0;Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "80ea454e-2e10-5885-93b9-c00042e93a09",
-    "notes": [
-        "This collection of the works of Giordano Bruno was packaged in the 70s - 80s in cooperation with the Insitute for the European Intellectual Lexicon, then called Study Centre of the CNR, ILIESI today.\r\n\r\nThe first works in this collection were originally encoded on mechanographic punched cards around 1969, at the beginning of the humanities computing era."
-    ],
-    "oai_identifier": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-67"
-    ],
-    "oai_set": [
-        "hdl_000-c0-111_38",
-        "hdl_000-c0-111_49"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Philosophy"
-        },
-        {
-            "name": "Religion"
-        },
-        {
-            "name": "Science"
-        }
-    ],
-    "title": [
-        "Dialoghi Italiani di Giordano Bruno"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/810677d2-7f39-58c2-b075-cfa3ccac01c8.json b/oaitestdata/clarin-oai_dc/SET_1/json/810677d2-7f39-58c2-b075-cfa3ccac01c8.json
deleted file mode 100644
index 793840da..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/810677d2-7f39-58c2-b075-cfa3ccac01c8.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Evolutionary Anthropology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-654",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-654"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-654",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Evolutionary Anthropology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Code of conduct"
-    ],
-    "SpatialCoverage": [
-        "Botswana"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-654;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Taa corpus;Documentation of the Taa project (DoBeS project);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-654;Code of conduct;downloadable_files_count: 0;Botswana;Max Planck Institute for Evolutionary Anthropology;http://corpus1.mpi.nl/ds/imdi_browser/?openpath=MPI318963%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "810677d2-7f39-58c2-b075-cfa3ccac01c8",
-    "notes": [
-        "Documentation of the Taa project (DoBeS project)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-654"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Taa corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/81156483-535b-542d-b1ab-b1a4f04d6001.json b/oaitestdata/clarin-oai_dc/SET_1/json/81156483-535b-542d-b1ab-b1a4f04d6001.json
deleted file mode 100644
index d1ee7ae9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/81156483-535b-542d-b1ab-b1a4f04d6001.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "ClarinPL"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "downloadable_files_count: 10",
-        "application/vnd.oasis.opendocument.text",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/384",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/384"
-    ],
-    "PID": "http://hdl.handle.net/11321/384",
-    "PublicationTimestamp": "2017-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "ClarinPL"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Kowalski, John"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/384;2017-05-30T11:54:45Z;hdl_11321_3;hdl_11321_4;corpus;Kowalski, John;corpus;test;corpus\r\ncorpus\r\ncorpus;2017-05-30;corpus;http://hdl.handle.net/11321/384;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;text/plain;application/msword;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;downloadable_files_count: 10;ClarinPL",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "81156483-535b-542d-b1ab-b1a4f04d6001",
-    "notes": [
-        "corpus\r\ncorpus\r\ncorpus"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/384"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "test"
-        }
-    ],
-    "title": [
-        "corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/812a6d97-7e49-5a43-bbe3-33e2e622d311.json b/oaitestdata/clarin-oai_dc/SET_1/json/812a6d97-7e49-5a43-bbe3-33e2e622d311.json
deleted file mode 100644
index 0996d2ec..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/812a6d97-7e49-5a43-bbe3-33e2e622d311.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "author"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/vnd.oasis.opendocument.text",
-        "downloadable_files_count: 10",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/484",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/484"
-    ],
-    "PID": "http://hdl.handle.net/11321/484",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "author"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Super Cool License",
-        "http://www.google.com",
-        "ACA"
-    ],
-    "author": [
-        "Klyus, Julia"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/484;2018-06-19T11:18:08Z;hdl_11321_3;hdl_11321_4;Hedgehog;Klyus, Julia;warsztaty;politechnika;clarin;korpus testowy - warsztaty Clarin;2018;corpus;http://hdl.handle.net/11321/484;pol;Super Cool License;http://www.google.com;ACA;text/plain; charset=utf-8;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/vnd.oasis.opendocument.text;application/msword;text/plain;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.oasis.opendocument.text;text/plain;downloadable_files_count: 10;author",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "812a6d97-7e49-5a43-bbe3-33e2e622d311",
-    "notes": [
-        "korpus testowy - warsztaty Clarin"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/484"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "warsztaty"
-        },
-        {
-            "name": "politechnika"
-        },
-        {
-            "name": "clarin"
-        }
-    ],
-    "title": [
-        "Hedgehog"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/81710916-2fe7-5b71-b82e-1b19e8a34430.json b/oaitestdata/clarin-oai_dc/SET_1/json/81710916-2fe7-5b71-b82e-1b19e8a34430.json
deleted file mode 100644
index 880c7ee4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/81710916-2fe7-5b71-b82e-1b19e8a34430.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4620",
-    "MetadataAccess": [
-        "oai:ota:oucs:4620"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Francklin, Thomas, 1721-1784."
-    ],
-    "fulltext": "oai:ota:oucs:4620;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4620.xml;A dissertation on antient tragedy;Francklin, Thomas, 1721-1784.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "81710916-2fe7-5b71-b82e-1b19e8a34430",
-    "oai_identifier": [
-        "oai:ota:oucs:4620"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A dissertation on antient tragedy"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4620.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8175fe23-a554-5228-a9eb-10f747048c2d.json b/oaitestdata/clarin-oai_dc/SET_1/json/8175fe23-a554-5228-a9eb-10f747048c2d.json
deleted file mode 100644
index 36d0970d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8175fe23-a554-5228-a9eb-10f747048c2d.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Universidad de Alicante"
-    ],
-    "Contributor": [
-        "G\u00f3mez, Jos\u00e9 M."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1276",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1276"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1276",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Universidad de Alicante"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Navarro, Sergio",
-        "G\u00f3mez, Jos\u00e9 M.",
-        "Mart\u00ednez-Barco, Patricio"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1276;2016-04-06T16:39:49Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;InTime;G\u00f3mez, Jos\u00e9 M.;Navarro, Sergio;Mart\u00ednez-Barco, Patricio;G\u00f3mez, Jos\u00e9 M.;Integration Platform of Natural Language Processing resources;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1276;downloadable_files_count: 0;Spain;Universidad de Alicante;http://intime.dlsi.ua.es:8080/intime/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8175fe23-a554-5228-a9eb-10f747048c2d",
-    "notes": [
-        "Integration Platform of Natural Language Processing resources"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1276"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "InTime"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/817c0909-b223-58e7-a2c7-6fe6815d8f6e.json b/oaitestdata/clarin-oai_dc/SET_1/json/817c0909-b223-58e7-a2c7-6fe6815d8f6e.json
deleted file mode 100644
index a5f13425..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/817c0909-b223-58e7-a2c7-6fe6815d8f6e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5410",
-    "MetadataAccess": [
-        "oai:ota:oucs:5410"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Sharp, Granville, 1735-1813."
-    ],
-    "fulltext": "oai:ota:oucs:5410;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5410.xml;A circular letter to the several petitioning counties, cities, and towns, addressed to their respective general meetings, against the late proposition for a triennial election of representatives. By Granville Sharp;Sharp, Granville, 1735-1813.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "817c0909-b223-58e7-a2c7-6fe6815d8f6e",
-    "oai_identifier": [
-        "oai:ota:oucs:5410"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A circular letter to the several petitioning counties, cities, and towns, addressed to their respective general meetings, against the late proposition for a triennial election of representatives. By Granville Sharp"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5410.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/81886925-3ebf-5ec6-ac89-e2d6e5bfc6c9.json b/oaitestdata/clarin-oai_dc/SET_1/json/81886925-3ebf-5ec6-ac89-e2d6e5bfc6c9.json
deleted file mode 100644
index 309ae3b0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/81886925-3ebf-5ec6-ac89-e2d6e5bfc6c9.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5700",
-    "MetadataAccess": [
-        "oai:ota:oucs:5700"
-    ],
-    "PublicationTimestamp": "1623-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1623"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Shakespeare, William, 1564-1616"
-    ],
-    "fulltext": "oai:ota:oucs:5700;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/5700.xml;As you Like it.;Shakespeare, William, 1564-1616;not after: 1623;text_and_corpus_linguistics;Plays -- England -- 16th century;Plays -- England -- 17th century;Comedies -- England -- 16th century;Comedies -- England -- 17th century;Tragedies -- England -- 16th century;Tragedies -- England -- 17th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "81886925-3ebf-5ec6-ac89-e2d6e5bfc6c9",
-    "oai_identifier": [
-        "oai:ota:oucs:5700"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        },
-        {
-            "name": "Comedies -- England -- th century"
-        },
-        {
-            "name": "Comedies -- England -- th century"
-        },
-        {
-            "name": "Tragedies -- England -- th century"
-        },
-        {
-            "name": "Tragedies -- England -- th century"
-        }
-    ],
-    "title": [
-        "As you Like it."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5700.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8191ce0c-6d60-50f1-a9a9-fde4f5e93591.json b/oaitestdata/clarin-oai_dc/SET_1/json/8191ce0c-6d60-50f1-a9a9-fde4f5e93591.json
deleted file mode 100644
index a5e0ff82..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8191ce0c-6d60-50f1-a9a9-fde4f5e93591.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/306",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/306"
-    ],
-    "PID": "http://hdl.handle.net/11321/306",
-    "PublicationTimestamp": "2016-06-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "CC"
-    ],
-    "author": [
-        "K\u0119dzia, Pawe\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/306;2016-06-07T12:44:20Z;hdl_11321_3;hdl_11321_4;Bilingual Cascade Dictionary;K\u0119dzia, Pawe\u0142;bilingual;dictionary;Polish-English;English-Polish;cascade dictionary;Bilingual Cascade Dictionary is a collection of dictionaries organised in a cascade with the top-most dictionaries having the highest priority in applications.;2016-06-01;lexicalConceptualResource;http://hdl.handle.net/11321/306;pol;eng;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;CC;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 1;Wroc\u0142aw University of Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8191ce0c-6d60-50f1-a9a9-fde4f5e93591",
-    "notes": [
-        "Bilingual Cascade Dictionary is a collection of dictionaries organised in a cascade with the top-most dictionaries having the highest priority in applications."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/306"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "bilingual"
-        },
-        {
-            "name": "dictionary"
-        },
-        {
-            "name": "Polish-English"
-        },
-        {
-            "name": "English-Polish"
-        },
-        {
-            "name": "cascade dictionary"
-        }
-    ],
-    "title": [
-        "Bilingual Cascade Dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/81b54151-2439-574f-9797-d4e2d2219e6e.json b/oaitestdata/clarin-oai_dc/SET_1/json/81b54151-2439-574f-9797-d4e2d2219e6e.json
deleted file mode 100644
index 3310d9c2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/81b54151-2439-574f-9797-d4e2d2219e6e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4151",
-    "MetadataAccess": [
-        "oai:ota:oucs:4151"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dennis, John, 1657-1734."
-    ],
-    "fulltext": "oai:ota:oucs:4151;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4151.xml;Reflections critical and satyrical, upon a late rhapsody call'd, An essay upon criticism: By Mr. Dennis.;Dennis, John, 1657-1734.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "81b54151-2439-574f-9797-d4e2d2219e6e",
-    "oai_identifier": [
-        "oai:ota:oucs:4151"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Reflections critical and satyrical, upon a late rhapsody call'd, An essay upon criticism: By Mr. Dennis."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4151.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/81b57196-36f2-5d59-b1c8-92e608ea0605.json b/oaitestdata/clarin-oai_dc/SET_1/json/81b57196-36f2-5d59-b1c8-92e608ea0605.json
deleted file mode 100644
index c143f6c2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/81b57196-36f2-5d59-b1c8-92e608ea0605.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4027",
-    "MetadataAccess": [
-        "oai:ota:oucs:4027"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Manley, Mrs. (Mary de la Rivi\u00c3\u00a8re), 1663-1724."
-    ],
-    "fulltext": "oai:ota:oucs:4027;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4027.xml;Lucius, the first Christian King of Britain: A tragedy. As it is acted at the Theatre-Royal in Drury-Lane. By His Majesty's servants. By Mrs. Manley.;Manley, Mrs. (Mary de la Rivi\u00c3\u00a8re), 1663-1724.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "81b57196-36f2-5d59-b1c8-92e608ea0605",
-    "oai_identifier": [
-        "oai:ota:oucs:4027"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Lucius, the first Christian King of Britain: A tragedy. As it is acted at the Theatre-Royal in Drury-Lane. By His Majesty's servants. By Mrs. Manley."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4027.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/81b6f7f9-866f-5b48-8019-2f2a76df45f1.json b/oaitestdata/clarin-oai_dc/SET_1/json/81b6f7f9-866f-5b48-8019-2f2a76df45f1.json
deleted file mode 100644
index b98123b9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/81b6f7f9-866f-5b48-8019-2f2a76df45f1.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3056",
-    "MetadataAccess": [
-        "oai:ota:oucs:3056"
-    ],
-    "PublicationTimestamp": "1898-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1898"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Wells, H.G. (Herbert George), 1866-1946"
-    ],
-    "fulltext": "oai:ota:oucs:3056;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3056.xml;The time machine;Wells, H.G. (Herbert George), 1866-1946;not after: 1898;text_and_corpus_linguistics;English fiction -- 19th century;eng;Oxford Text Archive, University of Oxford;Triggs, Jeffery;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "81b6f7f9-866f-5b48-8019-2f2a76df45f1",
-    "oai_identifier": [
-        "oai:ota:oucs:3056"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English fiction -- th century"
-        }
-    ],
-    "title": [
-        "The time machine"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3056.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/81c8be09-c415-5540-90d9-92899459ea90.json b/oaitestdata/clarin-oai_dc/SET_1/json/81c8be09-c415-5540-90d9-92899459ea90.json
deleted file mode 100644
index 69f54bfb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/81c8be09-c415-5540-90d9-92899459ea90.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3091",
-    "MetadataAccess": [
-        "oai:ota:oucs:3091"
-    ],
-    "PublicationTimestamp": "1531-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1531"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Elyot, Thomas, Sir, 1490?-1546"
-    ],
-    "fulltext": "oai:ota:oucs:3091;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3091.xml;The boke named The gouernour;Elyot, Thomas, Sir, 1490?-1546;not after: 1531;text_and_corpus_linguistics;Academic dissertations -- England -- 16th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "81c8be09-c415-5540-90d9-92899459ea90",
-    "oai_identifier": [
-        "oai:ota:oucs:3091"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Academic dissertations -- England -- th century"
-        }
-    ],
-    "title": [
-        "The boke named The gouernour"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3091.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/81d78942-62e5-54b0-9416-5089d53c0f4e.json b/oaitestdata/clarin-oai_dc/SET_1/json/81d78942-62e5-54b0-9416-5089d53c0f4e.json
deleted file mode 100644
index b0717803..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/81d78942-62e5-54b0-9416-5089d53c0f4e.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Estonian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-253",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-253"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-253",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Estonia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-253;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Corpus of Spoken Estonian;spoken general; 1 mio words; local tagset;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-253;est;downloadable_files_count: 0;Estonia;http://www.cl.ut.ee/suuline/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "81d78942-62e5-54b0-9416-5089d53c0f4e",
-    "notes": [
-        "spoken general; 1 mio words; local tagset"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-253"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus of Spoken Estonian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/81d8c410-a445-53d2-8c4b-5d3700af1f5e.json b/oaitestdata/clarin-oai_dc/SET_1/json/81d8c410-a445-53d2-8c4b-5d3700af1f5e.json
deleted file mode 100644
index 20da8da4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/81d8c410-a445-53d2-8c4b-5d3700af1f5e.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=19bd5872a35a11e1a404080027e73ea2389997a9e3ac4aeab1c1e5a698951c82",
-    "MetadataAccess": [
-        "19bd5872a35a11e1a404080027e73ea2389997a9e3ac4aeab1c1e5a698951c82"
-    ],
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "19bd5872a35a11e1a404080027e73ea2389997a9e3ac4aeab1c1e5a698951c82;2019-02-27T12:09:01Z;corpus;corpus:text;GENIA Event Corpus with meta-knowledge annotation;The corpus consists of 1000 MEDLINE abstracts. It is a subset of the original GENIA POS & term corpus, which was selected using the three MeSH terms human, blood cells and transcription factors. In each sentence, three types of information are annotated 1) biomedical terms are identified and assigned categories from the GENIA term ontology. 2) event structures are identified and assigned categories from the GENIA event ontology. 3) Thirdly, detailed information is annotated about how the event should be interpreted, according to its textual context. We call this information meta-knowledge. ;2015-12-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "81d8c410-a445-53d2-8c4b-5d3700af1f5e",
-    "notes": [
-        "The corpus consists of 1000 MEDLINE abstracts. It is a subset of the original GENIA POS & term corpus, which was selected using the three MeSH terms human, blood cells and transcription factors. In each sentence, three types of information are annotated 1) biomedical terms are identified and assigned categories from the GENIA term ontology. 2) event structures are identified and assigned categories from the GENIA event ontology. 3) Thirdly, detailed information is annotated about how the event should be interpreted, according to its textual context. We call this information meta-knowledge. "
-    ],
-    "oai_identifier": [
-        "19bd5872a35a11e1a404080027e73ea2389997a9e3ac4aeab1c1e5a698951c82"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "GENIA Event Corpus with meta-knowledge annotation"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/81f40234-d79a-5bd3-9ef8-8998f03b6749.json b/oaitestdata/clarin-oai_dc/SET_1/json/81f40234-d79a-5bd3-9ef8-8998f03b6749.json
deleted file mode 100644
index ae27a955..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/81f40234-d79a-5bd3-9ef8-8998f03b6749.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "between 512 KB and 1 MB "
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0067",
-    "MetadataAccess": [
-        "oai:ota:oucs:0067"
-    ],
-    "PublicationTimestamp": "1874-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1874"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hardy, Thomas,  1840-1928"
-    ],
-    "fulltext": "oai:ota:oucs:0067;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0067.xml; Far from the madding crowd ;Hardy, Thomas,  1840-1928;1874;text_and_corpus_linguistics;Novels -- England -- 19th century;eng;Oxford Text Archive, University of Oxford;between 512 KB and 1 MB ;Text;Novels;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "81f40234-d79a-5bd3-9ef8-8998f03b6749",
-    "oai_identifier": [
-        "oai:ota:oucs:0067"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Novels -- England -- th century"
-        }
-    ],
-    "title": [
-        " Far from the madding crowd "
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0067.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/81f8798e-d499-56d6-875a-fd0f182d3ced.json b/oaitestdata/clarin-oai_dc/SET_1/json/81f8798e-d499-56d6-875a-fd0f182d3ced.json
deleted file mode 100644
index 57330fc9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/81f8798e-d499-56d6-875a-fd0f182d3ced.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3579",
-    "MetadataAccess": [
-        "oai:ota:oucs:3579"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Griffith, Mrs. (Elizabeth), 1720?-1793."
-    ],
-    "fulltext": "oai:ota:oucs:3579;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3579.xml;The times: a comedy: As it is now performing at the Theatre-Royal in Drury-Lane. By Mrs. Griffith.;Griffith, Mrs. (Elizabeth), 1720?-1793.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "81f8798e-d499-56d6-875a-fd0f182d3ced",
-    "oai_identifier": [
-        "oai:ota:oucs:3579"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The times: a comedy: As it is now performing at the Theatre-Royal in Drury-Lane. By Mrs. Griffith."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3579.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/820e3266-5adf-5cde-977a-568c33871a8c.json b/oaitestdata/clarin-oai_dc/SET_1/json/820e3266-5adf-5cde-977a-568c33871a8c.json
deleted file mode 100644
index b4827b13..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/820e3266-5adf-5cde-977a-568c33871a8c.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Mateusz Nowa\u0107"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 28",
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/vnd.oasis.opendocument.text",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/493",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/493"
-    ],
-    "PID": "http://hdl.handle.net/11321/493",
-    "PublicationTimestamp": "2018-06-19T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Mateusz Nowa\u0107"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Nowa\u0107, Mateusz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/493;2018-06-19T11:19:14Z;hdl_11321_3;hdl_11321_4;Test1;Nowa\u0107, Mateusz;warsztaty;Jest to opis testowy w ramach warsztat\u00f3w.;2018-06-19;corpus;http://hdl.handle.net/11321/493;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain; charset=utf-8;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.oasis.opendocument.text;text/plain;application/vnd.oasis.opendocument.text;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;application/msword;application/vnd.oasis.opendocument.text;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.oasis.opendocument.text;application/msword;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.oasis.opendocument.text;text/plain;text/plain;downloadable_files_count: 28;Mateusz Nowa\u0107",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "820e3266-5adf-5cde-977a-568c33871a8c",
-    "notes": [
-        "Jest to opis testowy w ramach warsztat\u00f3w."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/493"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "warsztaty"
-        }
-    ],
-    "title": [
-        "Test1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/820fe1eb-079f-5994-abaf-22c6ac333259.json b/oaitestdata/clarin-oai_dc/SET_1/json/820fe1eb-079f-5994-abaf-22c6ac333259.json
deleted file mode 100644
index 8f65e393..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/820fe1eb-079f-5994-abaf-22c6ac333259.json
+++ /dev/null
@@ -1,88 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1481",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1481"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1481",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11858/00-097C-0000-0023-4087-6"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "BSD 3-Clause \"New\" or \"Revised\" license",
-        "http://opensource.org/licenses/BSD-3-Clause",
-        "PUB"
-    ],
-    "author": [
-        "Mi\u0161utka, Jozef",
-        "Ramasamy, Loganathan",
-        "Kamran, Amir",
-        "Haji\u010d, Jan",
-        "Ko\u0161arko, Ond\u0159ej",
-        "Jos\u00edfko, Michal",
-        "Stra\u0148\u00e1k, Pavel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1481;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Linguistic digital repository based on DSpace 5.2;Mi\u0161utka, Jozef;Kamran, Amir;Ko\u0161arko, Ond\u0159ej;Jos\u00edfko, Michal;Ramasamy, Loganathan;Stra\u0148\u00e1k, Pavel;Haji\u010d, Jan;linguistics;digital data;digital repository;language repository;linguistic data;One of the goals of LINDAT/CLARIN Centre for Language Research Infrastructure is to provide technical background to institutions or researchers who wants to share their tools and data used for research in linguistics or related research fields. The digital repository is built on a highly customised DSpace platform.;2015;toolService;http://hdl.handle.net/11234/1-1481;http://hdl.handle.net/11858/00-097C-0000-0023-4087-6;BSD 3-Clause \"New\" or \"Revised\" license;http://opensource.org/licenses/BSD-3-Clause;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://github.com/ufal/lindat-dspace",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "820fe1eb-079f-5994-abaf-22c6ac333259",
-    "notes": [
-        "One of the goals of LINDAT/CLARIN Centre for Language Research Infrastructure is to provide technical background to institutions or researchers who wants to share their tools and data used for research in linguistics or related research fields. The digital repository is built on a highly customised DSpace platform."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1481"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "linguistics"
-        },
-        {
-            "name": "digital data"
-        },
-        {
-            "name": "digital repository"
-        },
-        {
-            "name": "language repository"
-        },
-        {
-            "name": "linguistic data"
-        }
-    ],
-    "title": [
-        "Linguistic digital repository based on DSpace 5.2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/821f73fe-5d83-586e-a1c8-de02e5093818.json b/oaitestdata/clarin-oai_dc/SET_1/json/821f73fe-5d83-586e-a1c8-de02e5093818.json
deleted file mode 100644
index fe40b1f3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/821f73fe-5d83-586e-a1c8-de02e5093818.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Polish-Japanese Academy of Information Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "English",
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/528",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/528"
-    ],
-    "PID": "http://hdl.handle.net/11321/528",
-    "PublicationTimestamp": "2018-07-18T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Polish-Japanese Academy of Information Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Wo\u0142k, Krzysztof"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/528;2018-07-18T07:56:06Z;hdl_11321_3;hdl_11321_4;Parallel Corpora from Comparable Corpora tool;Wo\u0142k, Krzysztof;comparable;parallel;corpora;wikipedia;tool;builder;Script consists of 2 parts:\r\n\r\narticle parser\r\naligner\r\nRequired software (install before using script):\r\n\r\nyalign\r\nadditional Ubuntu packages:\r\nmongodb\r\nipython\r\npython-nose\r\npython-werkzeug\r\nWiki article parser\r\nArticle parser works in 2 steps:\r\n\r\nExtracts articles from wiki dumps\r\nSaves extracted articles to local DB (Mongo DB)\r\nBefore using parser, wiki dumps should be downloaded and extracted to some directory (directory should contain *.xml, *.sql files). For each language 2 dump files should be downloaded - articles and language link dumps, here is examples:\r\n\r\nPL:\r\n\r\nhttp://dumps.wikimedia.org/plwiki/latest/plwiki-latest-pages-articles.xml.bz2\r\nhttp://dumps.wikimedia.org/plwiki/latest/plwiki-latest-langlinks.sql.gz\r\nEN:\r\n\r\nhttp://dumps.wikimedia.org/enwiki/latest/enwiki-latest-pages-articles.xml.bz2\r\nhttp://dumps.wikimedia.org/enwiki/latest/enwiki-latest-langlinks.sql.gz\r\nIMPORTANT NOTE: Engilsh dumps after extraction will require about 50 Gb of free space. During parsing parser can require up to 8 Gb ram.\r\n\r\nArticle parser have option \"main language\" - its language for which articles extracted from other languages only if it exist in main language. Eg. if main language is PL, then article extractor first extracts all article for PL, then article for other languages and only if such articles exists in PL translation. This reduces space requirements.\r\n\r\nFor help use:\r\n\r\n$ python parse_wiki_dumps.py -h\r\n\r\nExample command:\r\n\r\n$ python parse_wiki_dumps.py -d ~/temp/wikipedia_dump/ -l pl -v\r\n\r\nWikipedia aligner\r\nAligner can be used when article extracted from dumps.\r\n\r\nAligner takes article pairs for given language pair, aligns text and saves parallel corpara to 2 files. Option \"-s\" can be used to limit number of symbols in file (by default size is 50000000 symbols, thats around 50-60Mb)\r\n\r\nBy default aligner tries to continue aligning where it was stopped, to force aligning from begining need to use \"--restart\" key\r\n\r\nFor help use:\r\n\r\n$ python align.py -h\r\n\r\nExample command:\r\n\r\n$ python align.py -o wikipedia -l en-pl -v\r\n\r\nEuronews crawler\r\nCrawler finds links to articles using euronews archive http://euronews.com/2004/, and in parallel extracts and saves article texts to DB.\r\n\r\nFor help use:\r\n\r\n$ python parse_euronews.py -h\r\n\r\nExample command:\r\n\r\n$ python parse_euronews.py -l en,pl -v\r\n\r\nEuronews aligner\r\nStarting aligner for euronews articles:\r\n\r\n$ python align.py -o euronews -l en-pl -v\r\n\r\nSaving articles in plain text\r\nScript \"save_plain_text.py\" can be used to save all articles in plain text format, it accepts path for saving articles, languages of articles to be saved, and source of articles (euronews, wikipedia).\r\n\r\nFor help use:\r\n\r\n$ python save_plain_text.py -h\r\n\r\nExample command:\r\n\r\n$ python save_plain_text.py -l en,pl -r [path] -o euronews\r\n\r\nYalign selection\r\nThis script tries random parameters for model of yalign in order to get best parameters for aligning provided text samples.\r\n\r\nBefore using yalign_selection script need to prepare article samples using prepare_random_sampling.py script.\r\n\r\nCreating folder with article samples can be done with this command:\r\n\r\n$ python prepare_random_sampling.py -o wikipedia -c 10 -l ru-en -v\r\n\r\n-o wikipedia - source of articles can be wikipedia or euronews\r\n\r\n-c 10 - number of articles to extract\r\n\r\n-l ru-en - languages to extract\r\n\r\nThis script will create \"article_samples\" folder with articles files, then you can create manually aligned files (you need align article of second language), for this example you need to align \"en\" file, files named \"_orig\" - should be left unmodified\r\n\r\nThen manual aligning is ready you can run selection script here is example:\r\n\r\n$ python yalign_selection.py --samples article_samples/ --lang1 ru --lang2 en --threshold 0.1536422609112349e-6 --threshold_step 0.0000001 --threshold_step_count 10 --penalty 0.014928930455303857 --penalty_step 0.0001 --penalty_step_count 1 -m ru-en\r\n\r\nHere is what each parameter means:\r\n\r\n--samples article_samples/ - path to article samples folder\r\n\r\n--lang1 ru --lang2 en - languages to align (articles of second language should be aligned manually, script will be using \"??_orig\" files, align them automatically and will compare with manually aligned)\r\n\r\n--threshold 0.1536422609112349e-6 - threshold value of model, selection will be made around this value\r\n\r\n--threshold_step 0.0000001 - step of changing value\r\n\r\n--threshold_step_count 10 - number of steps to check below and above vaule, eg if value 10, step 1, and count 2, script will check 8 9 10 11 12\r\n\r\nsame parameters for penalty\r\n\r\n-m ru-en - path to yalign model\r\n\r\nAlso you can use (to tweak comparison of text lines in files):\r\n\r\n--length and --similarity --length - min diffirence in length in order to mark lines similar, 1 - same length, 0.5 - at least half of length --similarity - similarity of text in lines, 1 - exactly same, 0 - completely different. For similarity check sentences compared as sequence of characters.\r\n\r\nIt has multiprocessing support already. Use -t option to set number of threads, by default it sets number of threads equal to number of CPU.\r\n\r\nfor additional parameters you can use '-h' key.\r\n\r\nThen yalign_selection.py script will finish work it will produce csv file, with first column equal to threshold, second column equal to penalty, and third is similarity for this parameters.\r\n\r\nAlign with HUNALING method\r\nIn order to use hunalign you need add \"--hunalign\" option in align.py script, here is example:\r\n\r\n$ python align.py -l li-hu -r align_result -o wikipedia --hunalign\r\n\r\nIn my empirical study it provides better results when articles are translations of each other or simillar in leghth and content.\r\n\r\nAlign From fodler\r\nFor aligning already aligned texts using hunalign:\r\n\r\nCommand exmaple is:\r\n\r\n$ python align_aligned_using_hunalign.py source/ target/\r\n\r\nFinal info\r\nWo\u0142k, K., & Marasek, K. (2015, September). Tuned and GPU-accelerated parallel data mining from comparable corpora. In International Conference on Text, Speech, and Dialogue (pp. 32-40). Springer International Publishing.\r\n\r\nhttp://arxiv.org/pdf/1509.08639\r\n\r\nFor more detailed usage instruction see howto.pdf.\r\n\r\nFor any questions: | Krzysztof Wolk | krzysztof@wolk.pl;2018-07-18;toolService;http://hdl.handle.net/11321/528;eng;pol;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;Polish-Japanese Academy of Information Technology;https://github.com/krzwolk/yalign",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "821f73fe-5d83-586e-a1c8-de02e5093818",
-    "notes": [
-        "Script consists of 2 parts:\r\n\r\narticle parser\r\naligner\r\nRequired software (install before using script):\r\n\r\nyalign\r\nadditional Ubuntu packages:\r\nmongodb\r\nipython\r\npython-nose\r\npython-werkzeug\r\nWiki article parser\r\nArticle parser works in 2 steps:\r\n\r\nExtracts articles from wiki dumps\r\nSaves extracted articles to local DB (Mongo DB)\r\nBefore using parser, wiki dumps should be downloaded and extracted to some directory (directory should contain *.xml, *.sql files). For each language 2 dump files should be downloaded - articles and language link dumps, here is examples:\r\n\r\nPL:\r\n\r\nhttp://dumps.wikimedia.org/plwiki/latest/plwiki-latest-pages-articles.xml.bz2\r\nhttp://dumps.wikimedia.org/plwiki/latest/plwiki-latest-langlinks.sql.gz\r\nEN:\r\n\r\nhttp://dumps.wikimedia.org/enwiki/latest/enwiki-latest-pages-articles.xml.bz2\r\nhttp://dumps.wikimedia.org/enwiki/latest/enwiki-latest-langlinks.sql.gz\r\nIMPORTANT NOTE: Engilsh dumps after extraction will require about 50 Gb of free space. During parsing parser can require up to 8 Gb ram.\r\n\r\nArticle parser have option \"main language\" - its language for which articles extracted from other languages only if it exist in main language. Eg. if main language is PL, then article extractor first extracts all article for PL, then article for other languages and only if such articles exists in PL translation. This reduces space requirements.\r\n\r\nFor help use:\r\n\r\n$ python parse_wiki_dumps.py -h\r\n\r\nExample command:\r\n\r\n$ python parse_wiki_dumps.py -d ~/temp/wikipedia_dump/ -l pl -v\r\n\r\nWikipedia aligner\r\nAligner can be used when article extracted from dumps.\r\n\r\nAligner takes article pairs for given language pair, aligns text and saves parallel corpara to 2 files. Option \"-s\" can be used to limit number of symbols in file (by default size is 50000000 symbols, thats around 50-60Mb)\r\n\r\nBy default aligner tries to continue aligning where it was stopped, to force aligning from begining need to use \"--restart\" key\r\n\r\nFor help use:\r\n\r\n$ python align.py -h\r\n\r\nExample command:\r\n\r\n$ python align.py -o wikipedia -l en-pl -v\r\n\r\nEuronews crawler\r\nCrawler finds links to articles using euronews archive http://euronews.com/2004/, and in parallel extracts and saves article texts to DB.\r\n\r\nFor help use:\r\n\r\n$ python parse_euronews.py -h\r\n\r\nExample command:\r\n\r\n$ python parse_euronews.py -l en,pl -v\r\n\r\nEuronews aligner\r\nStarting aligner for euronews articles:\r\n\r\n$ python align.py -o euronews -l en-pl -v\r\n\r\nSaving articles in plain text\r\nScript \"save_plain_text.py\" can be used to save all articles in plain text format, it accepts path for saving articles, languages of articles to be saved, and source of articles (euronews, wikipedia).\r\n\r\nFor help use:\r\n\r\n$ python save_plain_text.py -h\r\n\r\nExample command:\r\n\r\n$ python save_plain_text.py -l en,pl -r [path] -o euronews\r\n\r\nYalign selection\r\nThis script tries random parameters for model of yalign in order to get best parameters for aligning provided text samples.\r\n\r\nBefore using yalign_selection script need to prepare article samples using prepare_random_sampling.py script.\r\n\r\nCreating folder with article samples can be done with this command:\r\n\r\n$ python prepare_random_sampling.py -o wikipedia -c 10 -l ru-en -v\r\n\r\n-o wikipedia - source of articles can be wikipedia or euronews\r\n\r\n-c 10 - number of articles to extract\r\n\r\n-l ru-en - languages to extract\r\n\r\nThis script will create \"article_samples\" folder with articles files, then you can create manually aligned files (you need align article of second language), for this example you need to align \"en\" file, files named \"_orig\" - should be left unmodified\r\n\r\nThen manual aligning is ready you can run selection script here is example:\r\n\r\n$ python yalign_selection.py --samples article_samples/ --lang1 ru --lang2 en --threshold 0.1536422609112349e-6 --threshold_step 0.0000001 --threshold_step_count 10 --penalty 0.014928930455303857 --penalty_step 0.0001 --penalty_step_count 1 -m ru-en\r\n\r\nHere is what each parameter means:\r\n\r\n--samples article_samples/ - path to article samples folder\r\n\r\n--lang1 ru --lang2 en - languages to align (articles of second language should be aligned manually, script will be using \"??_orig\" files, align them automatically and will compare with manually aligned)\r\n\r\n--threshold 0.1536422609112349e-6 - threshold value of model, selection will be made around this value\r\n\r\n--threshold_step 0.0000001 - step of changing value\r\n\r\n--threshold_step_count 10 - number of steps to check below and above vaule, eg if value 10, step 1, and count 2, script will check 8 9 10 11 12\r\n\r\nsame parameters for penalty\r\n\r\n-m ru-en - path to yalign model\r\n\r\nAlso you can use (to tweak comparison of text lines in files):\r\n\r\n--length and --similarity --length - min diffirence in length in order to mark lines similar, 1 - same length, 0.5 - at least half of length --similarity - similarity of text in lines, 1 - exactly same, 0 - completely different. For similarity check sentences compared as sequence of characters.\r\n\r\nIt has multiprocessing support already. Use -t option to set number of threads, by default it sets number of threads equal to number of CPU.\r\n\r\nfor additional parameters you can use '-h' key.\r\n\r\nThen yalign_selection.py script will finish work it will produce csv file, with first column equal to threshold, second column equal to penalty, and third is similarity for this parameters.\r\n\r\nAlign with HUNALING method\r\nIn order to use hunalign you need add \"--hunalign\" option in align.py script, here is example:\r\n\r\n$ python align.py -l li-hu -r align_result -o wikipedia --hunalign\r\n\r\nIn my empirical study it provides better results when articles are translations of each other or simillar in leghth and content.\r\n\r\nAlign From fodler\r\nFor aligning already aligned texts using hunalign:\r\n\r\nCommand exmaple is:\r\n\r\n$ python align_aligned_using_hunalign.py source/ target/\r\n\r\nFinal info\r\nWo\u0142k, K., & Marasek, K. (2015, September). Tuned and GPU-accelerated parallel data mining from comparable corpora. In International Conference on Text, Speech, and Dialogue (pp. 32-40). Springer International Publishing.\r\n\r\nhttp://arxiv.org/pdf/1509.08639\r\n\r\nFor more detailed usage instruction see howto.pdf.\r\n\r\nFor any questions: | Krzysztof Wolk | krzysztof@wolk.pl"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/528"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "comparable"
-        },
-        {
-            "name": "parallel"
-        },
-        {
-            "name": "corpora"
-        },
-        {
-            "name": "wikipedia"
-        },
-        {
-            "name": "tool"
-        },
-        {
-            "name": "builder"
-        }
-    ],
-    "title": [
-        "Parallel Corpora from Comparable Corpora tool"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8237a7c2-71b0-5ce2-a54b-daae2c0d3931.json b/oaitestdata/clarin-oai_dc/SET_1/json/8237a7c2-71b0-5ce2-a54b-daae2c0d3931.json
deleted file mode 100644
index dcb0f021..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8237a7c2-71b0-5ce2-a54b-daae2c0d3931.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5292",
-    "MetadataAccess": [
-        "oai:ota:oucs:5292"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Barbauld, Mrs. (Anna Letitia), 1743-1825."
-    ],
-    "fulltext": "oai:ota:oucs:5292;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5292.xml;Remarks on Mr. Gilbert Wakefield's Enquiry into the expediency and propriety of public or social worship: By Anna L\u00c3\u00a6titia Barbauld.;Barbauld, Mrs. (Anna Letitia), 1743-1825.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8237a7c2-71b0-5ce2-a54b-daae2c0d3931",
-    "oai_identifier": [
-        "oai:ota:oucs:5292"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Remarks on Mr. Gilbert Wakefield's Enquiry into the expediency and propriety of public or social worship: By Anna L\u00c3\u00a6titia Barbauld."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5292.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/82586451-9351-5638-8603-cf829fb2f0e8.json b/oaitestdata/clarin-oai_dc/SET_1/json/82586451-9351-5638-8603-cf829fb2f0e8.json
deleted file mode 100644
index 17266955..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/82586451-9351-5638-8603-cf829fb2f0e8.json
+++ /dev/null
@@ -1,92 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 6",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2839",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2839"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2839",
-    "PublicationTimestamp": "2018-07-13T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://ceur-ws.org/Vol-2203/138.pdf"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Popel, Martin",
-        "Libovick\u00fd, Jind\u0159ich",
-        "Helcl, Jind\u0159ich",
-        "Rosa, Rudolf"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2839;2018-09-21T08:39:11Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Czech image captioning, machine translation, and sentiment analysis (Neural Monkey models);Libovick\u00fd, Jind\u0159ich;Rosa, Rudolf;Helcl, Jind\u0159ich;Popel, Martin;sentiment analysis;machine translation;image captioning;neural networks;transformer;Neural Monkey;This submission contains trained end-to-end models for the Neural Monkey toolkit for Czech and English, solving three NLP tasks: machine translation, image captioning, and sentiment analysis.\r\nThe models are trained on standard datasets and achieve state-of-the-art or near state-of-the-art performance in the tasks.\r\nThe models are described in the accompanying paper.\r\nThe same models can also be invoked via the online demo: https://ufal.mff.cuni.cz/grants/lsd\r\n\r\nThere are several separate ZIP archives here, each containing one model solving one of the tasks for one language.\r\n\r\nTo use a model, you first need to install Neural Monkey: https://github.com/ufal/neuralmonkey\r\nTo ensure correct functioning of the model, please use the exact version of Neural Monkey specified by the commit hash stored in the 'git_commit' file in the model directory.\r\n\r\nEach model directory contains a 'run.ini' Neural Monkey configuration file, to be used to run the model. See the Neural Monkey documentation to learn how to do that (you may need to update some paths to correspond to your filesystem organization).\r\nThe 'experiment.ini' file, which was used to train the model, is also included.\r\nThen there are files containing the model itself, files containing the input and output vocabularies, etc.\r\n\r\nFor the sentiment analyzers, you should tokenize your input data using the Moses tokenizer: https://pypi.org/project/mosestokenizer/\r\n\r\nFor the machine translation, you do not need to tokenize the data, as this is done by the model.\r\n\r\nFor image captioning, you need to:\r\n- download a trained ResNet: http://download.tensorflow.org/models/resnet_v2_50_2017_04_14.tar.gz\r\n- clone the git repository with TensorFlow models: https://github.com/tensorflow/models\r\n- preprocess the input images with the Neural Monkey 'scripts/imagenet_features.py' script (https://github.com/ufal/neuralmonkey/blob/master/scripts/imagenet_features.py) -- you need to specify the path to ResNet and to the TensorFlow models to this script\r\n\r\nFeel free to contact the authors of this submission in case you run into problems!;2018-07-13;toolService;http://hdl.handle.net/11234/1-2839;ces;eng;http://ceur-ws.org/Vol-2203/138.pdf;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 6;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://ufal.mff.cuni.cz/grants/lsd",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "82586451-9351-5638-8603-cf829fb2f0e8",
-    "notes": [
-        "This submission contains trained end-to-end models for the Neural Monkey toolkit for Czech and English, solving three NLP tasks: machine translation, image captioning, and sentiment analysis.\r\nThe models are trained on standard datasets and achieve state-of-the-art or near state-of-the-art performance in the tasks.\r\nThe models are described in the accompanying paper.\r\nThe same models can also be invoked via the online demo: https://ufal.mff.cuni.cz/grants/lsd\r\n\r\nThere are several separate ZIP archives here, each containing one model solving one of the tasks for one language.\r\n\r\nTo use a model, you first need to install Neural Monkey: https://github.com/ufal/neuralmonkey\r\nTo ensure correct functioning of the model, please use the exact version of Neural Monkey specified by the commit hash stored in the 'git_commit' file in the model directory.\r\n\r\nEach model directory contains a 'run.ini' Neural Monkey configuration file, to be used to run the model. See the Neural Monkey documentation to learn how to do that (you may need to update some paths to correspond to your filesystem organization).\r\nThe 'experiment.ini' file, which was used to train the model, is also included.\r\nThen there are files containing the model itself, files containing the input and output vocabularies, etc.\r\n\r\nFor the sentiment analyzers, you should tokenize your input data using the Moses tokenizer: https://pypi.org/project/mosestokenizer/\r\n\r\nFor the machine translation, you do not need to tokenize the data, as this is done by the model.\r\n\r\nFor image captioning, you need to:\r\n- download a trained ResNet: http://download.tensorflow.org/models/resnet_v2_50_2017_04_14.tar.gz\r\n- clone the git repository with TensorFlow models: https://github.com/tensorflow/models\r\n- preprocess the input images with the Neural Monkey 'scripts/imagenet_features.py' script (https://github.com/ufal/neuralmonkey/blob/master/scripts/imagenet_features.py) -- you need to specify the path to ResNet and to the TensorFlow models to this script\r\n\r\nFeel free to contact the authors of this submission in case you run into problems!"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2839"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "sentiment analysis"
-        },
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "image captioning"
-        },
-        {
-            "name": "neural networks"
-        },
-        {
-            "name": "transformer"
-        },
-        {
-            "name": "Neural Monkey"
-        }
-    ],
-    "title": [
-        "Czech image captioning, machine translation, and sentiment analysis (Neural Monkey models)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8291f70a-4538-541f-984d-5f9cda8ca68a.json b/oaitestdata/clarin-oai_dc/SET_1/json/8291f70a-4538-541f-984d-5f9cda8ca68a.json
deleted file mode 100644
index ac9f1e49..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8291f70a-4538-541f-984d-5f9cda8ca68a.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Russian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/34",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/34"
-    ],
-    "PID": "http://hdl.handle.net/10794/34",
-    "PublicationTimestamp": "2016-02-05T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/34;2017-10-27T14:23:41Z;hdl_10794_1;hdl_10794_2;Russian Constructicon (2017-10-16);Ryskt konstruktikon (2017-10-16);n/a, n/a;Russian;Constructicon;A Russian Constructicon.;Ett ryskt konstruktikon.;2016-02-05;lexicalConceptualResource;http://hdl.handle.net/10794/34;rus;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/konstruktikon-rus",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8291f70a-4538-541f-984d-5f9cda8ca68a",
-    "notes": [
-        "A Russian Constructicon.",
-        "Ett ryskt konstruktikon."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/34"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Russian"
-        },
-        {
-            "name": "Constructicon"
-        }
-    ],
-    "title": [
-        "Russian Constructicon (2017-10-16)",
-        "Ryskt konstruktikon (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8292efbb-b2a4-54d9-9a9f-b8bd5f110eb3.json b/oaitestdata/clarin-oai_dc/SET_1/json/8292efbb-b2a4-54d9-9a9f-b8bd5f110eb3.json
deleted file mode 100644
index 81018019..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8292efbb-b2a4-54d9-9a9f-b8bd5f110eb3.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4410",
-    "MetadataAccess": [
-        "oai:ota:oucs:4410"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hutchinson, William, 1715-1801."
-    ],
-    "fulltext": "oai:ota:oucs:4410;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4410.xml;A treatise on practical seamanship: ... By William Hutchinson, mariner, and dock master, at Liverpool.;Hutchinson, William, 1715-1801.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8292efbb-b2a4-54d9-9a9f-b8bd5f110eb3",
-    "oai_identifier": [
-        "oai:ota:oucs:4410"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A treatise on practical seamanship: ... By William Hutchinson, mariner, and dock master, at Liverpool."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4410.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/82ac3b46-5b9a-5482-a70f-2b657649e7cd.json b/oaitestdata/clarin-oai_dc/SET_1/json/82ac3b46-5b9a-5482-a70f-2b657649e7cd.json
deleted file mode 100644
index 8f694279..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/82ac3b46-5b9a-5482-a70f-2b657649e7cd.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 83 KB)"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0260",
-    "MetadataAccess": [
-        "oai:ota:oucs:0260"
-    ],
-    "PublicationYear": [
-        "750 BCE-650 BCE"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hesiod"
-    ],
-    "fulltext": "oai:ota:oucs:0260;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0260.xml;Fragmenta Hesiodea / Hesiod;Hesiod;750 BCE-650 BCE;text_and_corpus_linguistics;Didactic poetry, Greek -- Origins;grc;Oxford Text Archive, University of Oxford;(1 file : ca. 83 KB);Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "82ac3b46-5b9a-5482-a70f-2b657649e7cd",
-    "oai_identifier": [
-        "oai:ota:oucs:0260"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Didactic poetry"
-        },
-        {
-            "name": "Greek -- Origins"
-        }
-    ],
-    "title": [
-        "Fragmenta Hesiodea / Hesiod"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0260.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/82aee357-f77c-5906-9ece-ad83647a2731.json b/oaitestdata/clarin-oai_dc/SET_1/json/82aee357-f77c-5906-9ece-ad83647a2731.json
deleted file mode 100644
index baa5d4f3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/82aee357-f77c-5906-9ece-ad83647a2731.json
+++ /dev/null
@@ -1,90 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Russian",
-        "Swedish",
-        "Czech",
-        "Italian",
-        "Yiddish",
-        "Turkish",
-        "Ukrainian",
-        "Serbian",
-        "French",
-        "German",
-        "Mongolian",
-        "Dutch",
-        "Lithuanian",
-        "Dargwa",
-        "Moksha",
-        "Korean"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/24",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/24"
-    ],
-    "PID": "http://hdl.handle.net/10794/24",
-    "PublicationTimestamp": "2012-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/24;2018-04-24T08:28:48Z;hdl_10794_1;hdl_10794_2;Multilingual Constructicon (2017-10-16);Flerspr\u00e5kigt konstruktikon (2017-10-16);n/a, n/a;Multilingual;Constructicon;A multilingual constructicon.;Ett flerspr\u00e5kigt konstruktikon.;2012-05-30;lexicalConceptualResource;http://hdl.handle.net/10794/24;rus;swe;ces;ita;yid;tur;ukr;srp;fra;deu;mon;nld;lit;dar;mdf;kor;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;http://creativecommons.org/licenses/by/4.0/;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/konstruktikon-multi",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "82aee357-f77c-5906-9ece-ad83647a2731",
-    "notes": [
-        "A multilingual constructicon.",
-        "Ett flerspr\u00e5kigt konstruktikon."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/24"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Multilingual"
-        },
-        {
-            "name": "Constructicon"
-        }
-    ],
-    "title": [
-        "Multilingual Constructicon (2017-10-16)",
-        "Flerspr\u00e5kigt konstruktikon (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/82c51506-1297-568c-8fad-e01b8f68cf7e.json b/oaitestdata/clarin-oai_dc/SET_1/json/82c51506-1297-568c-8fad-e01b8f68cf7e.json
deleted file mode 100644
index 40da4fcf..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/82c51506-1297-568c-8fad-e01b8f68cf7e.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/103",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/103"
-    ],
-    "PID": "http://hdl.handle.net/10794/103",
-    "PublicationTimestamp": "2013-03-06T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/103;2017-10-25T11:21:38Z;hdl_10794_1;hdl_10794_2;Blog mix 2009 (2017-02-17);Bloggmix 2009 (2017-02-17);n/a, n/a;Swedish;Blog;The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.;Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat.;2013-03-06;corpus;http://hdl.handle.net/10794/103;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/bloggmix2009",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "82c51506-1297-568c-8fad-e01b8f68cf7e",
-    "notes": [
-        "The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.",
-        "Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/103"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Blog"
-        }
-    ],
-    "title": [
-        "Blog mix 2009 (2017-02-17)",
-        "Bloggmix 2009 (2017-02-17)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/82e0a022-84d4-5725-9dea-44ba1790a4cc.json b/oaitestdata/clarin-oai_dc/SET_1/json/82e0a022-84d4-5725-9dea-44ba1790a4cc.json
deleted file mode 100644
index 5a60d158..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/82e0a022-84d4-5725-9dea-44ba1790a4cc.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 129 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0320",
-    "MetadataAccess": [
-        "oai:ota:oucs:0320"
-    ],
-    "PublicationYear": [
-        "505-523"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Patristic texts -- Italy -- 6th-10th century period"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Boethius, d. 524"
-    ],
-    "fulltext": "oai:ota:oucs:0320;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0320.xml;De syllogismo hypothetico : liber primus;Boethius, d. 524;505-523;text_and_corpus_linguistics;Academic dissertations -- Italy -- 6th-10th century period;lat;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 129 KB);Text;Patristic texts -- Italy -- 6th-10th century period;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "82e0a022-84d4-5725-9dea-44ba1790a4cc",
-    "oai_identifier": [
-        "oai:ota:oucs:0320"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Academic dissertations -- Italy -- th-th century period"
-        }
-    ],
-    "title": [
-        "De syllogismo hypothetico : liber primus"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0320.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/82e81b02-5cdb-5888-ac65-5868e9cb54ab.json b/oaitestdata/clarin-oai_dc/SET_1/json/82e81b02-5cdb-5888-ac65-5868e9cb54ab.json
deleted file mode 100644
index c4f2fc19..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/82e81b02-5cdb-5888-ac65-5868e9cb54ab.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-xz",
-        "downloadable_files_count: 2"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1673",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1673"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1673",
-    "PublicationTimestamp": "2016-03-10T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11858/00-097C-0000-0015-A780-9"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Haji\u010d, Jan",
-        "Hlav\u00e1\u010dov\u00e1, Jaroslava"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1673;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;MorfFlex CZ 160310;Haji\u010d, Jan;Hlav\u00e1\u010dov\u00e1, Jaroslava;morphological dictionary;morphology;Czech;Czech morphological dictionary developed originally by Jan Haji\u010d as a spelling checker and lemmatization dictionary. Currently it contains full morphological information for each covered wordform, as well as some derivational, semantic and named entity information.;2016-03-10;lexicalConceptualResource;http://hdl.handle.net/11234/1-1673;ces;http://hdl.handle.net/11858/00-097C-0000-0015-A780-9;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/x-xz;application/x-xz;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/morfflex",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "82e81b02-5cdb-5888-ac65-5868e9cb54ab",
-    "notes": [
-        "Czech morphological dictionary developed originally by Jan Haji\u010d as a spelling checker and lemmatization dictionary. Currently it contains full morphological information for each covered wordform, as well as some derivational, semantic and named entity information."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1673"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphological dictionary"
-        },
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "Czech"
-        }
-    ],
-    "title": [
-        "MorfFlex CZ 160310"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/82f0e6bf-603e-576e-8cdb-862e31be3836.json b/oaitestdata/clarin-oai_dc/SET_1/json/82f0e6bf-603e-576e-8cdb-862e31be3836.json
deleted file mode 100644
index 0273f365..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/82f0e6bf-603e-576e-8cdb-862e31be3836.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Kossak"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 5",
-        "application/zip",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/79",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/79"
-    ],
-    "PID": "http://hdl.handle.net/11321/79",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Kossak"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Kossak, Kossak"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/79;2015-05-21T12:06:17Z;hdl_11321_3;hdl_11321_4;MWE Kossak;Kossak, Kossak;Kossak;2015-04-08;corpus;http://hdl.handle.net/11321/79;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 5;Kossak",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "82f0e6bf-603e-576e-8cdb-862e31be3836",
-    "notes": [
-        "Kossak"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/79"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Kossak"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8302ee4b-5bc4-511c-88d0-bceaea727795.json b/oaitestdata/clarin-oai_dc/SET_1/json/8302ee4b-5bc4-511c-88d0-bceaea727795.json
deleted file mode 100644
index a459e3c1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8302ee4b-5bc4-511c-88d0-bceaea727795.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3175",
-    "MetadataAccess": [
-        "oai:ota:oucs:3175"
-    ],
-    "PublicationTimestamp": "1869-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1869"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Mill, John Stuart, 1806-1873"
-    ],
-    "fulltext": "oai:ota:oucs:3175;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3175.xml;The subjection of women;Mill, John Stuart, 1806-1873;not after: 1869;text_and_corpus_linguistics;Essays -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8302ee4b-5bc4-511c-88d0-bceaea727795",
-    "oai_identifier": [
-        "oai:ota:oucs:3175"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Essays -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "The subjection of women"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3175.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/83036be2-ef22-5b1a-b4d6-be571fc7c892.json b/oaitestdata/clarin-oai_dc/SET_1/json/83036be2-ef22-5b1a-b4d6-be571fc7c892.json
deleted file mode 100644
index eae3c9d7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/83036be2-ef22-5b1a-b4d6-be571fc7c892.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5533",
-    "MetadataAccess": [
-        "oai:ota:oucs:5533"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Smith, Hugh, 1736?-1789."
-    ],
-    "fulltext": "oai:ota:oucs:5533;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5533.xml;The family physician: being a collection of useful family remedies. Together with plain and full directions for administering them, and properly nursing the sick, where the advice of a physician is difficult to be procured. ... By Hugh Smith, ...;Smith, Hugh, 1736?-1789.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "83036be2-ef22-5b1a-b4d6-be571fc7c892",
-    "oai_identifier": [
-        "oai:ota:oucs:5533"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The family physician: being a collection of useful family remedies. Together with plain and full directions for administering them, and properly nursing the sick, where the advice of a physician is difficult to be procured. ... By Hugh Smith, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5533.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/830512eb-a3ce-5e59-bd63-a198fc637756.json b/oaitestdata/clarin-oai_dc/SET_1/json/830512eb-a3ce-5e59-bd63-a198fc637756.json
deleted file mode 100644
index ad10d144..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/830512eb-a3ce-5e59-bd63-a198fc637756.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Estonian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-255",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-255"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-255",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Estonia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-255;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Morphologically disambiguated corpus;written general; 600 000 words; local tagset; manually disambiguated;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-255;est;downloadable_files_count: 0;Estonia;http://www.cl.ut.ee/korpused/morfkorpus/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "830512eb-a3ce-5e59-bd63-a198fc637756",
-    "notes": [
-        "written general; 600 000 words; local tagset; manually disambiguated"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-255"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Morphologically disambiguated corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/83132a63-b0c1-5347-8c5c-61d0b66c44c6.json b/oaitestdata/clarin-oai_dc/SET_1/json/83132a63-b0c1-5347-8c5c-61d0b66c44c6.json
deleted file mode 100644
index 0ddf574a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/83132a63-b0c1-5347-8c5c-61d0b66c44c6.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3666",
-    "MetadataAccess": [
-        "oai:ota:oucs:3666"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pope, Alexander, 1688-1744."
-    ],
-    "fulltext": "oai:ota:oucs:3666;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3666.xml;The character of Katharine, late Duchess of Buckinghamshire and Normanby: By the late Mr. Pope.;Pope, Alexander, 1688-1744.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "83132a63-b0c1-5347-8c5c-61d0b66c44c6",
-    "oai_identifier": [
-        "oai:ota:oucs:3666"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The character of Katharine, late Duchess of Buckinghamshire and Normanby: By the late Mr. Pope."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3666.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/831cd2c8-aff5-5e72-9f1d-ae1e42bede47.json b/oaitestdata/clarin-oai_dc/SET_1/json/831cd2c8-aff5-5e72-9f1d-ae1e42bede47.json
deleted file mode 100644
index ca389e95..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/831cd2c8-aff5-5e72-9f1d-ae1e42bede47.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/pdf"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/283",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/283"
-    ],
-    "PID": "http://hdl.handle.net/11321/283",
-    "PublicationTimestamp": "2016-04-25T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Koco\u0144, Jan",
-        "Wieczorek, Jan",
-        "Marci\u0144czuk, Micha\u0142",
-        "Wolski, Micha\u0142",
-        "Oleksy, Marcin",
-        "Berna\u015b, Tomasz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/283;2016-06-03T13:19:32Z;hdl_11321_3;hdl_11321_4;KPWr annotation guidelines - events;Marci\u0144czuk, Micha\u0142;Oleksy, Marcin;Koco\u0144, Jan;Wieczorek, Jan;Berna\u015b, Tomasz;Wolski, Micha\u0142;events;annotation guidelines;corpora annotation;Events annotation guidelines describing the process of manual annotation of documents in Polish Corpus of Wroc\u0142aw University of Technology (KPWr);2016-04-25;languageDescription;http://hdl.handle.net/11321/283;pol;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;application/pdf;downloadable_files_count: 1;Wroc\u0142aw University of Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "831cd2c8-aff5-5e72-9f1d-ae1e42bede47",
-    "notes": [
-        "Events annotation guidelines describing the process of manual annotation of documents in Polish Corpus of Wroc\u0142aw University of Technology (KPWr)"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/283"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "events"
-        },
-        {
-            "name": "annotation guidelines"
-        },
-        {
-            "name": "corpora annotation"
-        }
-    ],
-    "title": [
-        "KPWr annotation guidelines - events"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8326682b-9891-5b9f-9cf1-ac26b17f5359.json b/oaitestdata/clarin-oai_dc/SET_1/json/8326682b-9891-5b9f-9cf1-ac26b17f5359.json
deleted file mode 100644
index 09425647..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8326682b-9891-5b9f-9cf1-ac26b17f5359.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "The Research Institute for the Languages of Finland"
-    ],
-    "Contributor": [
-        "Lounela, Mikko"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Finnish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-825",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-825"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-825",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "The Research Institute for the Languages of Finland"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Finland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-825;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Frequency list: Early Modern Finnish;Lounela, Mikko;word frequencies;Frequency list of the Corpus of Early Modern Finnish, 4 862 190 words;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-825;fin;downloadable_files_count: 0;Finland;The Research Institute for the Languages of Finland;http://kaino.kotus.fi/sanat/taajuuslista/vns.php",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8326682b-9891-5b9f-9cf1-ac26b17f5359",
-    "notes": [
-        "Frequency list of the Corpus of Early Modern Finnish, 4 862 190 words"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-825"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "word frequencies"
-        }
-    ],
-    "title": [
-        "Frequency list: Early Modern Finnish"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8339b6fa-60ca-5fdc-8481-649f09910570.json b/oaitestdata/clarin-oai_dc/SET_1/json/8339b6fa-60ca-5fdc-8481-649f09910570.json
deleted file mode 100644
index 9bc7353d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8339b6fa-60ca-5fdc-8481-649f09910570.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4788",
-    "MetadataAccess": [
-        "oai:ota:oucs:4788"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Malthus, T. R. (Thomas Robert), 1766-1834."
-    ],
-    "fulltext": "oai:ota:oucs:4788;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4788.xml;An essay on the principle of population, as it affects the future improvement of society. With remarks on the speculations of Mr. Godwin, M. Condorcet, and other writers;Malthus, T. R. (Thomas Robert), 1766-1834.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8339b6fa-60ca-5fdc-8481-649f09910570",
-    "oai_identifier": [
-        "oai:ota:oucs:4788"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An essay on the principle of population, as it affects the future improvement of society. With remarks on the speculations of Mr. Godwin, M. Condorcet, and other writers"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4788.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/83662db4-e8ac-5f10-be55-4ec63146cf61.json b/oaitestdata/clarin-oai_dc/SET_1/json/83662db4-e8ac-5f10-be55-4ec63146cf61.json
deleted file mode 100644
index 554f6a3c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/83662db4-e8ac-5f10-be55-4ec63146cf61.json
+++ /dev/null
@@ -1,94 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-xz",
-        "downloadable_files_count: 2"
-    ],
-    "Language": [
-        "Multiple languages"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2859",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2859"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2859",
-    "PublicationTimestamp": "2018-05-02T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "Rights": [
-        "Licence Universal Dependencies v2.2",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-2.2",
-        "PUB"
-    ],
-    "author": [
-        "Straka, Milan"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2859;2018-09-05T11:07:23Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;CoNLL 2018 Shared Task - UDPipe Baseline Models and Supplementary Materials;Straka, Milan;CoNLL 2018;tokenizer;POS tagger;lemmatization;tagger;parser;dependency parser;morphology;treebank;Baseline UDPipe models for CoNLL 2018 Shared Task in UD Parsing, and supplementary material.\r\n\r\nThe models require UDPipe version at least 1.2 and are evaluated using the official evaluation script. The models were trained using a custom data split for treebanks where no development data is provided. Also, we trained an additional \"Mixed\" model, which uses 200 sentences from every training data. All information needed to replicate the model training (hyperparameters, modified train-dev split, and pre-computed word embeddings for the parser) are included in the archive.\r\n\r\nAdditionaly, we provide UD 2.2 CoNLL 2018 training data with automatically predicted morphology. We utilize the baseline models on development data and perform 10-fold jack-knifing (each fold is predicted with a model trained on the rest of the folds) on the training data.;2018-05-02;languageDescription;http://hdl.handle.net/11234/1-2859;mul;Licence Universal Dependencies v2.2;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-2.2;PUB;application/x-xz;application/x-xz;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/udpipe",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "83662db4-e8ac-5f10-be55-4ec63146cf61",
-    "notes": [
-        "Baseline UDPipe models for CoNLL 2018 Shared Task in UD Parsing, and supplementary material.\r\n\r\nThe models require UDPipe version at least 1.2 and are evaluated using the official evaluation script. The models were trained using a custom data split for treebanks where no development data is provided. Also, we trained an additional \"Mixed\" model, which uses 200 sentences from every training data. All information needed to replicate the model training (hyperparameters, modified train-dev split, and pre-computed word embeddings for the parser) are included in the archive.\r\n\r\nAdditionaly, we provide UD 2.2 CoNLL 2018 training data with automatically predicted morphology. We utilize the baseline models on development data and perform 10-fold jack-knifing (each fold is predicted with a model trained on the rest of the folds) on the training data."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2859"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "CoNLL"
-        },
-        {
-            "name": "tokenizer"
-        },
-        {
-            "name": "POS tagger"
-        },
-        {
-            "name": "lemmatization"
-        },
-        {
-            "name": "tagger"
-        },
-        {
-            "name": "parser"
-        },
-        {
-            "name": "dependency parser"
-        },
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "treebank"
-        }
-    ],
-    "title": [
-        "CoNLL 2018 Shared Task - UDPipe Baseline Models and Supplementary Materials"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/83694308-0d7a-515d-ba18-9e909fb5befe.json b/oaitestdata/clarin-oai_dc/SET_1/json/83694308-0d7a-515d-ba18-9e909fb5befe.json
deleted file mode 100644
index b0972ca6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/83694308-0d7a-515d-ba18-9e909fb5befe.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4858",
-    "MetadataAccess": [
-        "oai:ota:oucs:4858"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hayley, William, 1745-1820."
-    ],
-    "fulltext": "oai:ota:oucs:4858;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4858.xml;Two dialogues: containing a comparative view of the lives, characters, and writings, of Philip, the late Earl of Chesterfield, and of Dr. Samuel Johnson.;Hayley, William, 1745-1820.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "83694308-0d7a-515d-ba18-9e909fb5befe",
-    "oai_identifier": [
-        "oai:ota:oucs:4858"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Two dialogues: containing a comparative view of the lives, characters, and writings, of Philip, the late Earl of Chesterfield, and of Dr. Samuel Johnson."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4858.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/83732b22-0018-5813-9d15-97b54c73ac5a.json b/oaitestdata/clarin-oai_dc/SET_1/json/83732b22-0018-5813-9d15-97b54c73ac5a.json
deleted file mode 100644
index fc040d85..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/83732b22-0018-5813-9d15-97b54c73ac5a.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "153 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1476",
-    "MetadataAccess": [
-        "oai:ota:oucs:1476"
-    ],
-    "PublicationTimestamp": "1865-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1865"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Carroll, Lewis"
-    ],
-    "fulltext": "oai:ota:oucs:1476;2018-02-28T17:09:17Z;http://ota.ox.ac.uk/headers/1476.xml;Alice in Wonderland;Carroll, Lewis;1865;text_and_corpus_linguistics;Juvenile literature -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;153 KB;Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "83732b22-0018-5813-9d15-97b54c73ac5a",
-    "oai_identifier": [
-        "oai:ota:oucs:1476"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Juvenile literature -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Alice in Wonderland"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1476.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/83882ad0-5293-5717-a65a-799d10d74a98.json b/oaitestdata/clarin-oai_dc/SET_1/json/83882ad0-5293-5717-a65a-799d10d74a98.json
deleted file mode 100644
index e511c6e8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/83882ad0-5293-5717-a65a-799d10d74a98.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/29",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/29"
-    ],
-    "PID": "http://hdl.handle.net/10794/29",
-    "PublicationTimestamp": "2012-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/29;2017-10-27T14:39:52Z;hdl_10794_1;hdl_10794_2;Constructicon (2017-10-16);Konstruktikon (2017-10-16);n/a, n/a;Swedish;Constructicon;A Swedish Constructicon.;Ett svenskt konstruktikon.;2012-05-30;lexicalConceptualResource;http://hdl.handle.net/10794/29;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/konstruktikon",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "83882ad0-5293-5717-a65a-799d10d74a98",
-    "notes": [
-        "A Swedish Constructicon.",
-        "Ett svenskt konstruktikon."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/29"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Constructicon"
-        }
-    ],
-    "title": [
-        "Constructicon (2017-10-16)",
-        "Konstruktikon (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/839db035-da7b-5a4d-ab3f-16c6caf3df68.json b/oaitestdata/clarin-oai_dc/SET_1/json/839db035-da7b-5a4d-ab3f-16c6caf3df68.json
deleted file mode 100644
index 112c898d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/839db035-da7b-5a4d-ab3f-16c6caf3df68.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5402",
-    "MetadataAccess": [
-        "oai:ota:oucs:5402"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Sheridan, Richard Brinsley, 1751-1816."
-    ],
-    "fulltext": "oai:ota:oucs:5402;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5402.xml;Songs duetts, choruses, &c. in a new and appropriate entertainment, called The glorious first of June: Performed, for the first time, by Their Majesties servants at the Theatre Royal Drury Lane, for the benefit of the widows and orphans of the brave men who fell in the engagements under Earl Howe.;Glorious first of June.;Sheridan, Richard Brinsley, 1751-1816.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "839db035-da7b-5a4d-ab3f-16c6caf3df68",
-    "oai_identifier": [
-        "oai:ota:oucs:5402"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Songs duetts, choruses, &c. in a new and appropriate entertainment, called The glorious first of June: Performed, for the first time, by Their Majesties servants at the Theatre Royal Drury Lane, for the benefit of the widows and orphans of the brave men who fell in the engagements under Earl Howe.",
-        "Glorious first of June."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5402.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/839ebf3b-a19d-5ae2-8e89-32843fb3e118.json b/oaitestdata/clarin-oai_dc/SET_1/json/839ebf3b-a19d-5ae2-8e89-32843fb3e118.json
deleted file mode 100644
index be308e04..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/839ebf3b-a19d-5ae2-8e89-32843fb3e118.json
+++ /dev/null
@@ -1,49 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5656",
-    "MetadataAccess": [
-        "oai:ota:oucs:5656"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:5656;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5656.xml;A pill to purge the dispensary doctors: or, a cure for the present state of physick.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "839ebf3b-a19d-5ae2-8e89-32843fb3e118",
-    "oai_identifier": [
-        "oai:ota:oucs:5656"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A pill to purge the dispensary doctors: or, a cure for the present state of physick."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5656.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/83e4b733-36a8-57fb-b78b-06a6c02980d0.json b/oaitestdata/clarin-oai_dc/SET_1/json/83e4b733-36a8-57fb-b78b-06a6c02980d0.json
deleted file mode 100644
index 3b620dc8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/83e4b733-36a8-57fb-b78b-06a6c02980d0.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=c949c9c0e6de11e6a2aa782bcb074135e259542a800e4fc9abbaf20e5e6eb706",
-    "MetadataAccess": [
-        "c949c9c0e6de11e6a2aa782bcb074135e259542a800e4fc9abbaf20e5e6eb706"
-    ],
-    "PublicationTimestamp": "2017-01-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "fulltext": "c949c9c0e6de11e6a2aa782bcb074135e259542a800e4fc9abbaf20e5e6eb706;2018-11-15T16:40:26Z;corpus;corpus:text;LX-Battig;The LX-Battig was created from Battig test.set (Baroni et al., 2010). This data set has 83 concrete concepts of the following 10 categories: mammals, birds, fish, vegetables, fruit, trees, vehicles, clothes, tools and kitchenware. The categories names and the concepts were translated by two translators and adjudicated by a third one. ;2017-01-30",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "83e4b733-36a8-57fb-b78b-06a6c02980d0",
-    "notes": [
-        "The LX-Battig was created from Battig test.set (Baroni et al., 2010). This data set has 83 concrete concepts of the following 10 categories: mammals, birds, fish, vegetables, fruit, trees, vehicles, clothes, tools and kitchenware. The categories names and the concepts were translated by two translators and adjudicated by a third one. "
-    ],
-    "oai_identifier": [
-        "c949c9c0e6de11e6a2aa782bcb074135e259542a800e4fc9abbaf20e5e6eb706"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "LX-Battig"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/83ea0eb3-fa61-5230-9064-e18fa4d32211.json b/oaitestdata/clarin-oai_dc/SET_1/json/83ea0eb3-fa61-5230-9064-e18fa4d32211.json
deleted file mode 100644
index c10d1a3b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/83ea0eb3-fa61-5230-9064-e18fa4d32211.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3352",
-    "MetadataAccess": [
-        "oai:ota:oucs:3352"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hawkins, William, 1722-1801."
-    ],
-    "fulltext": "oai:ota:oucs:3352;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3352.xml;Female empire: or, winter celebrated at London;Hawkins, William, 1722-1801.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "83ea0eb3-fa61-5230-9064-e18fa4d32211",
-    "oai_identifier": [
-        "oai:ota:oucs:3352"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Female empire: or, winter celebrated at London"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3352.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/83ecaaef-4296-52ea-ad48-c54da7586b83.json b/oaitestdata/clarin-oai_dc/SET_1/json/83ecaaef-4296-52ea-ad48-c54da7586b83.json
deleted file mode 100644
index 50e677fc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/83ecaaef-4296-52ea-ad48-c54da7586b83.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Sargent, Valerie M."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(10 files : total of ca. 1.3 MB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0081",
-    "MetadataAccess": [
-        "oai:ota:oucs:0081"
-    ],
-    "PublicationTimestamp": "1817-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1817"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Keats, John, 1795-1821"
-    ],
-    "fulltext": "oai:ota:oucs:0081;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0081.xml;The poems of John Keats / John Keats;Keats, John, 1795-1821;1817;text_and_corpus_linguistics;English poetry -- 19th century;eng;Oxford Text Archive, University of Oxford;Sargent, Valerie M.;(10 files : total of ca. 1.3 MB);Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "83ecaaef-4296-52ea-ad48-c54da7586b83",
-    "oai_identifier": [
-        "oai:ota:oucs:0081"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English poetry -- th century"
-        }
-    ],
-    "title": [
-        "The poems of John Keats / John Keats"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0081.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/83ee6bbe-244a-5f5f-8bbb-d9ec92f46d59.json b/oaitestdata/clarin-oai_dc/SET_1/json/83ee6bbe-244a-5f5f-8bbb-d9ec92f46d59.json
deleted file mode 100644
index 9e495a28..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/83ee6bbe-244a-5f5f-8bbb-d9ec92f46d59.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Clarin PL"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/226",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/226"
-    ],
-    "PID": "http://hdl.handle.net/11321/226",
-    "PublicationTimestamp": "2015-09-02T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Clarin PL"
-    ],
-    "ResourceType": [
-        "tool"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Tomasz, Naskr\u0119t"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/226;2015-12-31T00:30:04Z;hdl_11321_3;hdl_11321_4;WordnetLoom 2;Tomasz, Naskr\u0119t;wordnetloom;s\u0142owosie\u0107;Aplikacja do edycji i budowy s\u0142owosieci;2015-09-02;tool;http://hdl.handle.net/11321/226;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Clarin PL",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "83ee6bbe-244a-5f5f-8bbb-d9ec92f46d59",
-    "notes": [
-        "Aplikacja do edycji i budowy s\u0142owosieci"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/226"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "wordnetloom"
-        },
-        {
-            "name": "wordnetloom"
-        }
-    ],
-    "title": [
-        "WordnetLoom 2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/83f45e59-b634-52db-a7cd-4c36eddbfc38.json b/oaitestdata/clarin-oai_dc/SET_1/json/83f45e59-b634-52db-a7cd-4c36eddbfc38.json
deleted file mode 100644
index 41a93add..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/83f45e59-b634-52db-a7cd-4c36eddbfc38.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Hilton, John (John L.)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 223 KB)"
-    ],
-    "Language": [
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0711",
-    "MetadataAccess": [
-        "oai:ota:oucs:0711"
-    ],
-    "PublicationYear": [
-        "54-68"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Satires"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Petronius Arbiter"
-    ],
-    "fulltext": "oai:ota:oucs:0711;2018-02-28T14:40:18Z;http://ota.ox.ac.uk/headers/0711.xml;Petronii Saturae / Petronius;Satires;Saturae;Petronius Arbiter;54-68;text_and_corpus_linguistics;Satire, Latin -- 1st century;lat;Oxford Text Archive, University of Oxford;Hilton, John (John L.);(1 file : ca. 223 KB);Text;Satires;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "83f45e59-b634-52db-a7cd-4c36eddbfc38",
-    "oai_identifier": [
-        "oai:ota:oucs:0711"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Satire"
-        },
-        {
-            "name": "Latin -- st century"
-        }
-    ],
-    "title": [
-        "Petronii Saturae / Petronius",
-        "Satires",
-        "Saturae"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0711.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/83fee28f-13a4-5566-bdc8-9b18be15e4e7.json b/oaitestdata/clarin-oai_dc/SET_1/json/83fee28f-13a4-5566-bdc8-9b18be15e4e7.json
deleted file mode 100644
index b8eb57c6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/83fee28f-13a4-5566-bdc8-9b18be15e4e7.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "The Research Institute for the Languages of Finland"
-    ],
-    "Contributor": [
-        "Suutari, Toni"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Finnish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-777",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-777"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-777",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "The Research Institute for the Languages of Finland"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Finland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-777;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Corpus of Proverbs and Other Colloquial Expressions;Suutari, Toni;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-777;fin;downloadable_files_count: 0;Finland;The Research Institute for the Languages of Finland;http://kaino.kotus.fi/korpus/sp/meta/sp_coll_rdf.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "83fee28f-13a4-5566-bdc8-9b18be15e4e7",
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-777"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus of Proverbs and Other Colloquial Expressions"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/841d23b8-7e08-5ca4-a4a7-392b862afbc3.json b/oaitestdata/clarin-oai_dc/SET_1/json/841d23b8-7e08-5ca4-a4a7-392b862afbc3.json
deleted file mode 100644
index ffd5e01e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/841d23b8-7e08-5ca4-a4a7-392b862afbc3.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 7",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1455",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1455"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1455",
-    "PublicationTimestamp": "2012-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0)",
-        "http://creativecommons.org/licenses/by-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Kr\u016fza, Old\u0159ich"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1455;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Spoken corpus of Karel Mako\u0148;Kr\u016fza, Old\u0159ich;single speaker;spoken corpus;christianity;mystic;Talks of Karel Mako\u0148 given to his friends in the course of late sixties through early nineties of the 20th century. The topic is mostly christian mysticism.;2012;corpus;http://hdl.handle.net/11372/LRT-1455;ces;Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0);http://creativecommons.org/licenses/by-sa/3.0/;PUB;application/zip;text/plain;application/zip;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 7;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://www.makon.fm/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "841d23b8-7e08-5ca4-a4a7-392b862afbc3",
-    "notes": [
-        "Talks of Karel Mako\u0148 given to his friends in the course of late sixties through early nineties of the 20th century. The topic is mostly christian mysticism."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1455"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "single speaker"
-        },
-        {
-            "name": "spoken corpus"
-        },
-        {
-            "name": "christianity"
-        },
-        {
-            "name": "mystic"
-        }
-    ],
-    "title": [
-        "Spoken corpus of Karel Mako\u0148"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/842231af-0eb2-57c6-b20d-07e9e280a9f4.json b/oaitestdata/clarin-oai_dc/SET_1/json/842231af-0eb2-57c6-b20d-07e9e280a9f4.json
deleted file mode 100644
index 38c2e6b3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/842231af-0eb2-57c6-b20d-07e9e280a9f4.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Department of Information Technology, Gauhati University, Assam, India"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Assamese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/613",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/613"
-    ],
-    "PID": "http://hdl.handle.net/11321/613",
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Department of Information Technology, Gauhati University, Assam, India"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "author": [
-        "Sarma, Prof. Shikhar Kr."
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/613;2019-01-08T10:42:09Z;hdl_11321_3;hdl_11321_610;Assamese spell variation list;Sarma, Prof. Shikhar Kr.;Assamese NLP;Assamese spell variations;Gauhati University;A spelling variant of a word occurs when a word may not have only a single correct spelling. There are many different ways in which it can be spelled in linguistics. A spell variation list comprising 5000 words, mainly named entities was compiled for Assamese language.\r\n\r\n---\r\n\r\n1. These Assamese NLP resources including the Tools and Applications are developed\r\nduring Research and Development Projects as well as Masters and Ph.D. thesis\r\nworks.\r\n2. These are mainly developed or generated at Gauhati University Department of\r\nComputer Science and Department of Information Technology.\r\n3. These resources are used by students and researchers for further studies, researches, as\r\nwell as for design and development of tools and applications.\r\n4. Computational Linguistics in Assamese is not rich, and Natural Language Processing\r\nworks have mainly started during last two decades, and most of the resources are first\r\ngeneration resources, and with ample scope for upgrading, enriching, and purifying.\r\n5. These are very good and essential resources for all the researchers in Assamese NLP, as\r\nthe language requires more and more NLP works to make Assamese a rich media for\r\nthe digital world.\r\n6. Anyone interested, or in need of such resources may express their interest for the\r\nrequired resources, and the way of availability will be advised/informed accordingly.\r\n7. These are purely research materials and could only be used for further research only.\r\n8. Researchers may visit the NLP Lab of Department of Information Technology, Gauhati\r\nUniversity, Guwahati, India or contact us.\r\n9. Researchers interested in collaborative works, and also students for project works, are\r\nwelcome.\r\n10. Contact person is Professor Shikhar Kr. Sarma, Department of Information\r\nTechnology, Gauhati University, Guwahati 781014, Assam, India. Email-\r\nsks@gauhati.ac.in;2019-01-08;lexicalConceptualResource;http://hdl.handle.net/11321/613;asm;downloadable_files_count: 0;Department of Information Technology, Gauhati University, Assam, India",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "842231af-0eb2-57c6-b20d-07e9e280a9f4",
-    "notes": [
-        "A spelling variant of a word occurs when a word may not have only a single correct spelling. There are many different ways in which it can be spelled in linguistics. A spell variation list comprising 5000 words, mainly named entities was compiled for Assamese language.\r\n\r\n---\r\n\r\n1. These Assamese NLP resources including the Tools and Applications are developed\r\nduring Research and Development Projects as well as Masters and Ph.D. thesis\r\nworks.\r\n2. These are mainly developed or generated at Gauhati University Department of\r\nComputer Science and Department of Information Technology.\r\n3. These resources are used by students and researchers for further studies, researches, as\r\nwell as for design and development of tools and applications.\r\n4. Computational Linguistics in Assamese is not rich, and Natural Language Processing\r\nworks have mainly started during last two decades, and most of the resources are first\r\ngeneration resources, and with ample scope for upgrading, enriching, and purifying.\r\n5. These are very good and essential resources for all the researchers in Assamese NLP, as\r\nthe language requires more and more NLP works to make Assamese a rich media for\r\nthe digital world.\r\n6. Anyone interested, or in need of such resources may express their interest for the\r\nrequired resources, and the way of availability will be advised/informed accordingly.\r\n7. These are purely research materials and could only be used for further research only.\r\n8. Researchers may visit the NLP Lab of Department of Information Technology, Gauhati\r\nUniversity, Guwahati, India or contact us.\r\n9. Researchers interested in collaborative works, and also students for project works, are\r\nwelcome.\r\n10. Contact person is Professor Shikhar Kr. Sarma, Department of Information\r\nTechnology, Gauhati University, Guwahati 781014, Assam, India. Email-\r\nsks@gauhati.ac.in"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/613"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_610"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Assamese NLP"
-        },
-        {
-            "name": "Assamese spell variations"
-        },
-        {
-            "name": "Gauhati University"
-        }
-    ],
-    "title": [
-        "Assamese spell variation list"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/84391f8e-a4bd-5a22-b1f4-b4183b045204.json b/oaitestdata/clarin-oai_dc/SET_1/json/84391f8e-a4bd-5a22-b1f4-b4183b045204.json
deleted file mode 100644
index cbdc0d43..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/84391f8e-a4bd-5a22-b1f4-b4183b045204.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-93",
-    "MetadataAccess": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-93"
-    ],
-    "PID": "http://hdl.handle.net/20.500.11752/ILC-93",
-    "PublicationTimestamp": "2012-05-22T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/248064",
-        "http://www.lrec-conf.org/proceedings/lrec2012/workshops/06.LREC%202012%20Merging%20Proceedings.pdf"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Rubino, Francesco",
-        "Abrate, Matteo",
-        "Frontini, Francesca",
-        "Quochi, Valeria",
-        "Del Gratta, Riccardo",
-        "Lo Duca, Angelica",
-        "Monachini, Monica"
-    ],
-    "fulltext": "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-93;2018-12-05T08:54:15Z;hdl_000-c0-111_38;hdl_000-c0-111_49;LMF Merger;Del Gratta, Riccardo;Frontini, Francesca;Monachini, Monica;Quochi, Valeria;Rubino, Francesco;Abrate, Matteo;Lo Duca, Angelica;LFM Standard;(semi-)automatic Lexicon Merging;Similarity Score;This is an LMF Lexical Merger web-service for the automatic merging of Lexical Entries from two distinct LMF lexicons. The web-service takes two LMF lexicons, A and B, and a set of directives in input and outputs one or more LMF merged lexicon(s) according to different merging scenarios. Further details can be found in: Riccardo Del Gratta & Francesca Frontini & Monica Monachini &Valeria Quochi & Francesco Rubino& Matteo Abrate & Angelica Lo Duca. 2012. L-LEME: an Automatic Lexical Merger based on the LMF Standard. In Proceedings of the Workshop on\r\nLanguage Resource Merging (Colocated wiyh LREC 2012), May, 22 2012, Istanbul, Turkey;2012-05-22;toolService;http://hdl.handle.net/20.500.11752/ILC-93;ita;info:eu-repo/grantAgreement/EC/FP7/248064;http://www.lrec-conf.org/proceedings/lrec2012/workshops/06.LREC%202012%20Merging%20Proceedings.pdf;downloadable_files_count: 0;Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR);http://www.panacea-lr.eu",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "84391f8e-a4bd-5a22-b1f4-b4183b045204",
-    "notes": [
-        "This is an LMF Lexical Merger web-service for the automatic merging of Lexical Entries from two distinct LMF lexicons. The web-service takes two LMF lexicons, A and B, and a set of directives in input and outputs one or more LMF merged lexicon(s) according to different merging scenarios. Further details can be found in: Riccardo Del Gratta & Francesca Frontini & Monica Monachini &Valeria Quochi & Francesco Rubino& Matteo Abrate & Angelica Lo Duca. 2012. L-LEME: an Automatic Lexical Merger based on the LMF Standard. In Proceedings of the Workshop on\r\nLanguage Resource Merging (Colocated wiyh LREC 2012), May, 22 2012, Istanbul, Turkey"
-    ],
-    "oai_identifier": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-93"
-    ],
-    "oai_set": [
-        "hdl_000-c0-111_38",
-        "hdl_000-c0-111_49"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "LFM Standard"
-        },
-        {
-            "name": "semi-automatic Lexicon Merging"
-        },
-        {
-            "name": "Similarity Score"
-        }
-    ],
-    "title": [
-        "LMF Merger"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/843d76b9-c19c-591c-b03b-1dc6f1aa1880.json b/oaitestdata/clarin-oai_dc/SET_1/json/843d76b9-c19c-591c-b03b-1dc6f1aa1880.json
deleted file mode 100644
index 387811dc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/843d76b9-c19c-591c-b03b-1dc6f1aa1880.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Department of Circuit Theory, Czech Technical University in Prague, Faculty of Electrical Engineering"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 3",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1597",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1597"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1597",
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Department of Circuit Theory, Czech Technical University in Prague, Faculty of Electrical Engineering"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0)",
-        "http://creativecommons.org/licenses/by-nc/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "B\u00e1rt\u016f, Marek",
-        "Grill, Pavel",
-        "Tu\u010dkov\u00e1, Jana",
-        "Vav\u0159ina, Josef"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1597;2016-12-16T09:50:16Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Speech databases of typical children and children with SLI;Tu\u010dkov\u00e1, Jana;Grill, Pavel;Vav\u0159ina, Josef;B\u00e1rt\u016f, Marek;Specific Language Impairments;Developmental Dysphasia;Children Pathological Speech;Our Laboratory of Artificial Neural Network Applications (LANNA) in the Czech Technical University in Prague (head of the laboratory is professor Jana Tu\u010dkov\u00e1) collaborates on a project with the Department of Paediatric Neurology, 2nd Faculty of Medicine of Charles University in Prague and with the Motol University Hospital (head of clinic is professor Vladim\u00edr Kom\u00e1rek), which focuses on the study of children with SLI.\r\n\r\nThe speech database contains two subgroups of recordings of children's speech from different types of speakers. The first subgroup (healthy) consists of recordings of children without speech disorders; the second subgroup (patients) consists of recordings of children with SLI. These children have different degrees of severity (1 \u2013 mild, 2 \u2013 moderate, and 3 \u2013 severe). The speech therapists and specialists from Motol Hospital decided upon this classification. The children\u2019s speech was recorded in the period 2003-2013. These databases were commonly created in a schoolroom or a speech therapist\u2019s consulting room, in the presence of surrounding background noise. This situation simulates the natural environment in which the children live, and is important for capturing the normal behavior of children. The database of healthy children\u2019s speech was created as a referential database for the computer processing of children\u2019s speech. It was recorded on the SONY digital Dictaphone (sampling frequency, fs = 16 kHz, 16-bit resolution in stereo mode in the standardized wav format) and on the MD SONY MZ-N710 (sampling frequency, fs = 44.1 kHz, 16-bit resolution in stereo mode in the standardized wav format). The corpus was recorded in the natural environment of a schoolroom and in a clinic. This subgroup contains a total of 44 native Czech participants (15 boys, 29 girls) aged 4 to 12 years, and was recorded during the period 2003\u20132005. The database of children with SLI was recorded in a private speech therapist\u2019s office. The children\u2019s speech is captured by means of a SHURE lapel microphone using the solution by the company AVID (MBox \u2013 USB AD/DA converter and ProTools LE software) on an Apple laptop (iBook G4). The sound recordings are saved in the standardized wav format. The sampling frequency is set to 44.1 kHz with 16-bit resolution in mono mode. This subgroup contains a total of 54 native Czech participants (35 boys, 19 girls) aged 6 to 12 years, and was recorded during the period 2009\u20132013. This package contains wav data sets for development and testing methods for detection children with SLI.\r\n\r\nSoftware pack:\r\nFORANA - was developed the original software FORANA for formants analysis. It is based on the MATLAB programming environment. The development of this software was mainly driven by the need to have the ability to complete formant analysis correctly and full automation of the process of extracting formants from the recorded speech signals. Development of this application is still running. Software was developed in the LANNA at CTU FEE in Prague.\r\n\r\nLABELING - the program LABELING is used for segmentation of the speech signal. It is a part of SOMLab program system. Software was developed in the LANNA at CTU FEE in Prague.\r\n\r\nPRAAT - is an acoustic analysis software. The Praat program was created by Paul Boersma and David Weenink of the Institute of Phonetics Sciences of the University of Amsterdam. Home page: http://www.praat.org or http://www.fon.hum.uva.nl/praat/.;2013;corpus;http://hdl.handle.net/11372/LRT-1597;ces;Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0);http://creativecommons.org/licenses/by-nc/3.0/;PUB;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 3;Department of Circuit Theory, Czech Technical University in Prague, Faculty of Electrical Engineering;http://ajatubar.feld.cvut.cz/lanna/en/index.php?page=vyzkum",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "843d76b9-c19c-591c-b03b-1dc6f1aa1880",
-    "notes": [
-        "Our Laboratory of Artificial Neural Network Applications (LANNA) in the Czech Technical University in Prague (head of the laboratory is professor Jana Tu\u010dkov\u00e1) collaborates on a project with the Department of Paediatric Neurology, 2nd Faculty of Medicine of Charles University in Prague and with the Motol University Hospital (head of clinic is professor Vladim\u00edr Kom\u00e1rek), which focuses on the study of children with SLI.\r\n\r\nThe speech database contains two subgroups of recordings of children's speech from different types of speakers. The first subgroup (healthy) consists of recordings of children without speech disorders; the second subgroup (patients) consists of recordings of children with SLI. These children have different degrees of severity (1 \u2013 mild, 2 \u2013 moderate, and 3 \u2013 severe). The speech therapists and specialists from Motol Hospital decided upon this classification. The children\u2019s speech was recorded in the period 2003-2013. These databases were commonly created in a schoolroom or a speech therapist\u2019s consulting room, in the presence of surrounding background noise. This situation simulates the natural environment in which the children live, and is important for capturing the normal behavior of children. The database of healthy children\u2019s speech was created as a referential database for the computer processing of children\u2019s speech. It was recorded on the SONY digital Dictaphone (sampling frequency, fs = 16 kHz, 16-bit resolution in stereo mode in the standardized wav format) and on the MD SONY MZ-N710 (sampling frequency, fs = 44.1 kHz, 16-bit resolution in stereo mode in the standardized wav format). The corpus was recorded in the natural environment of a schoolroom and in a clinic. This subgroup contains a total of 44 native Czech participants (15 boys, 29 girls) aged 4 to 12 years, and was recorded during the period 2003\u20132005. The database of children with SLI was recorded in a private speech therapist\u2019s office. The children\u2019s speech is captured by means of a SHURE lapel microphone using the solution by the company AVID (MBox \u2013 USB AD/DA converter and ProTools LE software) on an Apple laptop (iBook G4). The sound recordings are saved in the standardized wav format. The sampling frequency is set to 44.1 kHz with 16-bit resolution in mono mode. This subgroup contains a total of 54 native Czech participants (35 boys, 19 girls) aged 6 to 12 years, and was recorded during the period 2009\u20132013. This package contains wav data sets for development and testing methods for detection children with SLI.\r\n\r\nSoftware pack:\r\nFORANA - was developed the original software FORANA for formants analysis. It is based on the MATLAB programming environment. The development of this software was mainly driven by the need to have the ability to complete formant analysis correctly and full automation of the process of extracting formants from the recorded speech signals. Development of this application is still running. Software was developed in the LANNA at CTU FEE in Prague.\r\n\r\nLABELING - the program LABELING is used for segmentation of the speech signal. It is a part of SOMLab program system. Software was developed in the LANNA at CTU FEE in Prague.\r\n\r\nPRAAT - is an acoustic analysis software. The Praat program was created by Paul Boersma and David Weenink of the Institute of Phonetics Sciences of the University of Amsterdam. Home page: http://www.praat.org or http://www.fon.hum.uva.nl/praat/."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1597"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Specific Language Impairments"
-        },
-        {
-            "name": "Developmental Dysphasia"
-        },
-        {
-            "name": "Children Pathological Speech"
-        }
-    ],
-    "title": [
-        "Speech databases of typical children and children with SLI"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8448b3a8-384c-5221-9857-5d98c33cfc5d.json b/oaitestdata/clarin-oai_dc/SET_1/json/8448b3a8-384c-5221-9857-5d98c33cfc5d.json
deleted file mode 100644
index a3afaf2f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8448b3a8-384c-5221-9857-5d98c33cfc5d.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-7D42-8",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-7D42-8"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-7D42-8",
-    "PublicationTimestamp": "2014-03-04T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Straka, Milan",
-        "Strakov\u00e1, Jana"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-7D42-8;2018-07-02T22:05:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Czech Models (CNEC) for NameTag;Straka, Milan;Strakov\u00e1, Jana;NameTag;Czech;named entity recognition;Czech models for NameTag, providing recognition of named entities.\r\n\r\nThe models are trained on Czech Named Entity Corpus 2.0 and 1.1.;2014-03-04;languageDescription;http://hdl.handle.net/11858/00-097C-0000-0023-7D42-8;ces;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/nametag/users-manual#czech-cnec",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8448b3a8-384c-5221-9857-5d98c33cfc5d",
-    "notes": [
-        "Czech models for NameTag, providing recognition of named entities.\r\n\r\nThe models are trained on Czech Named Entity Corpus 2.0 and 1.1."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-7D42-8"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "NameTag"
-        },
-        {
-            "name": "Czech"
-        },
-        {
-            "name": "named entity recognition"
-        }
-    ],
-    "title": [
-        "Czech Models (CNEC) for NameTag"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/845516b6-21c5-519b-a871-f2570554c6b0.json b/oaitestdata/clarin-oai_dc/SET_1/json/845516b6-21c5-519b-a871-f2570554c6b0.json
deleted file mode 100644
index bf78113e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/845516b6-21c5-519b-a871-f2570554c6b0.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5620",
-    "MetadataAccess": [
-        "oai:ota:oucs:5620"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Robinson, Nicholas, 1697?-1775."
-    ],
-    "fulltext": "oai:ota:oucs:5620;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5620.xml;A treatise on the virtues and efficacy of a crust of bread: eat early in a morning fasting, to which are added some particular remarks concerning the great cures accomplished by the saliva or fasting spittle, ... By Nicholas Robinson, ...;Robinson, Nicholas, 1697?-1775.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "845516b6-21c5-519b-a871-f2570554c6b0",
-    "oai_identifier": [
-        "oai:ota:oucs:5620"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A treatise on the virtues and efficacy of a crust of bread: eat early in a morning fasting, to which are added some particular remarks concerning the great cures accomplished by the saliva or fasting spittle, ... By Nicholas Robinson, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5620.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8471d32e-9754-58cd-8d02-c0eee8a88a72.json b/oaitestdata/clarin-oai_dc/SET_1/json/8471d32e-9754-58cd-8d02-c0eee8a88a72.json
deleted file mode 100644
index d33b7c3e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8471d32e-9754-58cd-8d02-c0eee8a88a72.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Jan Wieczorek"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/richtext",
-        "downloadable_files_count: 50"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/628",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/628"
-    ],
-    "PID": "http://hdl.handle.net/11321/628",
-    "PublicationTimestamp": "2019-02-28T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Jan Wieczorek"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Lewandowski, Robert"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/628;2019-02-28T21:23:45Z;hdl_11321_3;hdl_11321_4;Potchefstroom demo;Lewandowski, Robert;literature;evolution;mickiewicz;Test Corpus (North-West University, Potchefstroom, South Africa);2019-02-28;corpus;http://hdl.handle.net/11321/628;eng;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;downloadable_files_count: 50;Jan Wieczorek",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8471d32e-9754-58cd-8d02-c0eee8a88a72",
-    "notes": [
-        "Test Corpus (North-West University, Potchefstroom, South Africa)"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/628"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "literature"
-        },
-        {
-            "name": "evolution"
-        },
-        {
-            "name": "mickiewicz"
-        }
-    ],
-    "title": [
-        "Potchefstroom demo"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/84738640-1985-5f3c-b1c6-cc231b1a3698.json b/oaitestdata/clarin-oai_dc/SET_1/json/84738640-1985-5f3c-b1c6-cc231b1a3698.json
deleted file mode 100644
index 2d81f059..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/84738640-1985-5f3c-b1c6-cc231b1a3698.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3212",
-    "MetadataAccess": [
-        "oai:ota:oucs:3212"
-    ],
-    "PublicationTimestamp": "1873-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1873"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Trollope, Anthony, 1815-1882"
-    ],
-    "fulltext": "oai:ota:oucs:3212;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3212.xml;The Eustace diamonds, vol. I;Trollope, Anthony, 1815-1882;not after: 1873;text_and_corpus_linguistics;Novels -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "84738640-1985-5f3c-b1c6-cc231b1a3698",
-    "oai_identifier": [
-        "oai:ota:oucs:3212"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Novels -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "The Eustace diamonds, vol. I"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3212.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8491178f-7b9a-57f2-8dd7-5f5129d694e6.json b/oaitestdata/clarin-oai_dc/SET_1/json/8491178f-7b9a-57f2-8dd7-5f5129d694e6.json
deleted file mode 100644
index 642a4203..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8491178f-7b9a-57f2-8dd7-5f5129d694e6.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Craig, Hugh"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 144 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1449",
-    "MetadataAccess": [
-        "oai:ota:oucs:1449"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Shakespeare, William, 1564-1616"
-    ],
-    "fulltext": "oai:ota:oucs:1449;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1449.xml;Macbeth : [1623 Folio] / William Shakespeare;Shakespeare, William, 1564-1616;text_and_corpus_linguistics;English drama -- Early modern and Elizabethan, 1500-1600;Oxford Text Archive, University of Oxford;Craig, Hugh;(1 file : ca. 144 KB);Text;Plays;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8491178f-7b9a-57f2-8dd7-5f5129d694e6",
-    "oai_identifier": [
-        "oai:ota:oucs:1449"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- Early modern Elizabethan"
-        }
-    ],
-    "title": [
-        "Macbeth : [1623 Folio] / William Shakespeare"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1449.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/84c0ee75-9131-55cc-a173-f1fd7d01980d.json b/oaitestdata/clarin-oai_dc/SET_1/json/84c0ee75-9131-55cc-a173-f1fd7d01980d.json
deleted file mode 100644
index 086e4b9b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/84c0ee75-9131-55cc-a173-f1fd7d01980d.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/263",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/263"
-    ],
-    "PID": "http://hdl.handle.net/11321/263",
-    "PublicationTimestamp": "2016-05-25T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Marci\u0144czuk, Micha\u0142",
-        "Koco\u0144, Jan",
-        "Krautforst, Micha\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/263;2016-05-25T12:01:53Z;hdl_11321_3;hdl_11321_4;Liner2.5 model NER;Marci\u0144czuk, Micha\u0142;Koco\u0144, Jan;Krautforst, Micha\u0142;NER;Przygotowa\u0142: Micha\u0142 Marci\u0144czuk <marcinczuk@gmail.com>\r\nData: 25.05.2016\r\nProjekt: Clarin-PL (http://clarin-pl.eu)\r\nAutorzy: Micha\u0142 Marci\u0144czuk, Jan Koco\u0144, Micha\u0142 Krautforst\r\n\r\nModele do narz\u0119dzia Liner2.5 do rozpoznawania jednostek identyfikacyjnych.\r\n\r\nNarz\u0119dzie Liner2.5 dost\u0119pne jest pod linkiem http://hdl.handle.net/11321/231.\r\n\r\nPaczka zawiera trzy modele:\r\n1. config-nam.ini -- granice jednostek identyfikacyjnych,\r\n2. config-top9.ini -- granice i og\u00f3lna kategoryzacja jednostek (9 kategorii),\r\n3. config-n82.ini -- granice i szczeg\u00f3\u0142owa kategoryzacja jednostek (82 kategorie).;2016-05-25;toolService;http://hdl.handle.net/11321/263;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;Wroc\u0142aw University of Technology;http://nlp.pwr.wroc.pl/liner2",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "84c0ee75-9131-55cc-a173-f1fd7d01980d",
-    "notes": [
-        "Przygotowa\u0142: Micha\u0142 Marci\u0144czuk <marcinczuk@gmail.com>\r\nData: 25.05.2016\r\nProjekt: Clarin-PL (http://clarin-pl.eu)\r\nAutorzy: Micha\u0142 Marci\u0144czuk, Jan Koco\u0144, Micha\u0142 Krautforst\r\n\r\nModele do narz\u0119dzia Liner2.5 do rozpoznawania jednostek identyfikacyjnych.\r\n\r\nNarz\u0119dzie Liner2.5 dost\u0119pne jest pod linkiem http://hdl.handle.net/11321/231.\r\n\r\nPaczka zawiera trzy modele:\r\n1. config-nam.ini -- granice jednostek identyfikacyjnych,\r\n2. config-top9.ini -- granice i og\u00f3lna kategoryzacja jednostek (9 kategorii),\r\n3. config-n82.ini -- granice i szczeg\u00f3\u0142owa kategoryzacja jednostek (82 kategorie)."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/263"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "NER"
-        }
-    ],
-    "title": [
-        "Liner2.5 model NER"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/84cd87a3-5fc3-52c0-917d-58e4c67834a7.json b/oaitestdata/clarin-oai_dc/SET_1/json/84cd87a3-5fc3-52c0-917d-58e4c67834a7.json
deleted file mode 100644
index 4d95373b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/84cd87a3-5fc3-52c0-917d-58e4c67834a7.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Department of Linguistics and Nordic Studies, University of Oslo"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Norwegian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-661",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-661"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-661",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Department of Linguistics and Nordic Studies, University of Oslo"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Norway"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-661;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;UPUS Corpus;Video-taped interviews and peer conversations from aprox 55 adolescents living in multilingual and multicultural communities in Oslo.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-661;nor;downloadable_files_count: 0;Norway;Department of Linguistics and Nordic Studies, University of Oslo;http://www.hf.uio.no/iln/forskning/prosjekter/upus/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "84cd87a3-5fc3-52c0-917d-58e4c67834a7",
-    "notes": [
-        "Video-taped interviews and peer conversations from aprox 55 adolescents living in multilingual and multicultural communities in Oslo."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-661"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "UPUS Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/84cde997-31c7-5028-b820-addd8fce4a2d.json b/oaitestdata/clarin-oai_dc/SET_1/json/84cde997-31c7-5028-b820-addd8fce4a2d.json
deleted file mode 100644
index b9e142b4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/84cde997-31c7-5028-b820-addd8fce4a2d.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5208",
-    "MetadataAccess": [
-        "oai:ota:oucs:5208"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Sharp, Granville, 1735-1813."
-    ],
-    "fulltext": "oai:ota:oucs:5208;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5208.xml;The just limitation of slavery: in the laws of God, compared with the unbounded claims of the African traders and British American slaveholders. By Granville Sharp. With a copious appendix: ...;Sharp, Granville, 1735-1813.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "84cde997-31c7-5028-b820-addd8fce4a2d",
-    "oai_identifier": [
-        "oai:ota:oucs:5208"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The just limitation of slavery: in the laws of God, compared with the unbounded claims of the African traders and British American slaveholders. By Granville Sharp. With a copious appendix: ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5208.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/84df0a82-dc6a-52e0-874e-1be3ddce5a5f.json b/oaitestdata/clarin-oai_dc/SET_1/json/84df0a82-dc6a-52e0-874e-1be3ddce5a5f.json
deleted file mode 100644
index 8a19a307..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/84df0a82-dc6a-52e0-874e-1be3ddce5a5f.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3862",
-    "MetadataAccess": [
-        "oai:ota:oucs:3862"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Sharp, Granville, 1735-1813."
-    ],
-    "fulltext": "oai:ota:oucs:3862;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3862.xml;The claims of the people of England.;Sharp, Granville, 1735-1813.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "84df0a82-dc6a-52e0-874e-1be3ddce5a5f",
-    "oai_identifier": [
-        "oai:ota:oucs:3862"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The claims of the people of England."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3862.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/84f3450d-d7e3-5be5-8517-45ab2b88452e.json b/oaitestdata/clarin-oai_dc/SET_1/json/84f3450d-d7e3-5be5-8517-45ab2b88452e.json
deleted file mode 100644
index 8a5d2657..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/84f3450d-d7e3-5be5-8517-45ab2b88452e.json
+++ /dev/null
@@ -1,88 +0,0 @@
-{
-    "Contact": [
-        "Charles University, UFAL"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "text/plain",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2508",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2508"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2508",
-    "PublicationTimestamp": "2017-11-13T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Charles University, UFAL"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-1820",
-        "http://hdl.handle.net/11234/1-2863"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Nov\u00e1k, Michal",
-        "M\u00edrovsk\u00fd, Ji\u0159\u00ed",
-        "Haji\u010dov\u00e1, Eva",
-        "Rysov\u00e1, Magdal\u00e9na",
-        "Rysov\u00e1, Kate\u0159ina"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2508;2018-10-23T16:41:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;EVALD 2.0;Nov\u00e1k, Michal;Rysov\u00e1, Kate\u0159ina;M\u00edrovsk\u00fd, Ji\u0159\u00ed;Rysov\u00e1, Magdal\u00e9na;Haji\u010dov\u00e1, Eva;text coherence;discourse;automatic evaluation;native speakers;EVALD 2.0 serves for automatic evaluation of surface coherence (cohesion) in Czech texts written by native speakers of Czech.;2017-11-13;toolService;http://hdl.handle.net/11234/1-2508;ces;http://hdl.handle.net/11234/1-1820;http://hdl.handle.net/11234/1-2863;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;text/plain;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University, UFAL;https://ufal.mff.cuni.cz/evald",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "84f3450d-d7e3-5be5-8517-45ab2b88452e",
-    "notes": [
-        "EVALD 2.0 serves for automatic evaluation of surface coherence (cohesion) in Czech texts written by native speakers of Czech."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2508"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "text coherence"
-        },
-        {
-            "name": "discourse"
-        },
-        {
-            "name": "automatic evaluation"
-        },
-        {
-            "name": "native speakers"
-        }
-    ],
-    "title": [
-        "EVALD 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8530efe1-146f-526e-a5b6-373edfc3735c.json b/oaitestdata/clarin-oai_dc/SET_1/json/8530efe1-146f-526e-a5b6-373edfc3735c.json
deleted file mode 100644
index 907db701..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8530efe1-146f-526e-a5b6-373edfc3735c.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3100",
-    "MetadataAccess": [
-        "oai:ota:oucs:3100"
-    ],
-    "PublicationTimestamp": "1853-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1853"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gaskell, Elizabeth Cleghorn, 1810-1865"
-    ],
-    "fulltext": "oai:ota:oucs:3100;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3100.xml;My French master;Gaskell, Elizabeth Cleghorn, 1810-1865;not after: 1853;text_and_corpus_linguistics;English fiction -- 19th century;eng;Oxford Text Archive, University of Oxford;Triggs, Jeffery;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8530efe1-146f-526e-a5b6-373edfc3735c",
-    "oai_identifier": [
-        "oai:ota:oucs:3100"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English fiction -- th century"
-        }
-    ],
-    "title": [
-        "My French master"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3100.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8574ed27-9e34-5d60-8f48-5d6c8b501601.json b/oaitestdata/clarin-oai_dc/SET_1/json/8574ed27-9e34-5d60-8f48-5d6c8b501601.json
deleted file mode 100644
index a79a76f5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8574ed27-9e34-5d60-8f48-5d6c8b501601.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Somali"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/117",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/117"
-    ],
-    "PID": "http://hdl.handle.net/10794/117",
-    "PublicationTimestamp": "2016-04-04T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/117;2017-12-14T12:52:10Z;hdl_10794_1;hdl_10794_2;Cilmi-Afeed (2017-11-27);Cilmi-Afeed (2017-11-27);n/a, n/a;Somali;Somali Cilmi-Afeed. The material is sentence scrambled.;Somali Cilmi-Afeed. Materialet \u00e4r meningsomkastat.;2016-04-04;corpus;http://hdl.handle.net/10794/117;som;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/eng/resource/somali-cilmi",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8574ed27-9e34-5d60-8f48-5d6c8b501601",
-    "notes": [
-        "Somali Cilmi-Afeed. The material is sentence scrambled.",
-        "Somali Cilmi-Afeed. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/117"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Somali"
-        }
-    ],
-    "title": [
-        "Cilmi-Afeed (2017-11-27)",
-        "Cilmi-Afeed (2017-11-27)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/85a6df1f-7954-5020-8e1a-4078b97e5e5b.json b/oaitestdata/clarin-oai_dc/SET_1/json/85a6df1f-7954-5020-8e1a-4078b97e5e5b.json
deleted file mode 100644
index b4f71670..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/85a6df1f-7954-5020-8e1a-4078b97e5e5b.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 1200 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1873",
-    "MetadataAccess": [
-        "oai:ota:oucs:1873"
-    ],
-    "PublicationTimestamp": "1881-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1881"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Trollope, Anthony, 1815-1882"
-    ],
-    "fulltext": "oai:ota:oucs:1873;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/1873.xml;Ayala's angel / by Anthony Trollope;Trollope, Anthony, 1815-1882;1881;text_and_corpus_linguistics;Novels -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 1200 KB);Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "85a6df1f-7954-5020-8e1a-4078b97e5e5b",
-    "oai_identifier": [
-        "oai:ota:oucs:1873"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Novels -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Ayala's angel / by Anthony Trollope"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1873.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/85ad6c97-3bfb-5817-aada-12cffec75aa7.json b/oaitestdata/clarin-oai_dc/SET_1/json/85ad6c97-3bfb-5817-aada-12cffec75aa7.json
deleted file mode 100644
index 383f8327..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/85ad6c97-3bfb-5817-aada-12cffec75aa7.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics",
-        "Babylon Centre for Studies of Multilingualism in the Multicultural Society",
-        "Radboud University Nijmegen",
-        "Meertens Institute KNAW The Netherlands"
-    ],
-    "Contributor": [
-        "Boumans, Dr. L."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Arabic",
-        "Dutch",
-        "Turkish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-214",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-214"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-214",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics",
-        "Babylon Centre for Studies of Multilingualism in the Multicultural Society",
-        "Radboud University Nijmegen",
-        "Meertens Institute KNAW The Netherlands"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-214;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Dutch Bilingualism Data Base (DBD);Boumans, Dr. L.;Audio recordings, transcripts,;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-214;ara;nld;tur;downloadable_files_count: 0;Netherlands (the);Radboud University Nijmegen;Max Planck Institute for Psycholinguistics;Meertens Institute KNAW The Netherlands;Babylon Centre for Studies of Multilingualism in the Multicultural Society;http://corpus1.mpi.nl/ds/imdi_browser/?openpath=MPI84720%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "85ad6c97-3bfb-5817-aada-12cffec75aa7",
-    "notes": [
-        "Audio recordings, transcripts,"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-214"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Dutch Bilingualism Data Base (DBD)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/85b5f97a-6028-5922-954d-eaa19a6fdd0d.json b/oaitestdata/clarin-oai_dc/SET_1/json/85b5f97a-6028-5922-954d-eaa19a6fdd0d.json
deleted file mode 100644
index 73fab42a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/85b5f97a-6028-5922-954d-eaa19a6fdd0d.json
+++ /dev/null
@@ -1,92 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-        "University of Amsterdam, ILLC"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 5",
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Czech",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1671",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1671"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1671",
-    "PublicationTimestamp": "2016-03-21T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-        "University of Amsterdam, ILLC"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/H2020/645452"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Stanojevic, Milos",
-        "Bojar, Ond\u0159ej",
-        "Jawaid, Bushra",
-        "Kamran, Amir"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1671;2017-11-09T14:20:30Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;WMT16 Tuning Shared Task Models (Czech-to-English);Kamran, Amir;Jawaid, Bushra;Bojar, Ond\u0159ej;Stanojevic, Milos;WMT16;machine translation;tuning;baseline models;shared task;The item contains models to tune for the WMT16 Tuning shared task for Czech-to-English.\r\n\r\nCzEng 1.6pre (http://ufal.mff.cuni.cz/czeng/czeng16pre) corpus is used for the training of the translation models. The data is tokenized (using Moses tokenizer), lowercased and sentences longer than 60 words and shorter than 4 words are removed before training. Alignment is done using fast_align (https://github.com/clab/fast_align) and the standard Moses pipeline is used for training.\r\n\r\nTwo 5-gram language models are trained using KenLM: one only using the CzEng English data and the other is trained using all available English mono data for WMT except Common Crawl.\r\n\r\nAlso included are two lexicalized bidirectional reordering models, word based and hierarchical, with msd conditioned on both source and target of processed CzEng.;2016-03-21;corpus;http://hdl.handle.net/11372/LRT-1671;ces;eng;info:eu-repo/grantAgreement/EC/H2020/645452;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/x-gzip;application/x-gzip;application/x-gzip;application/octet-stream;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 5;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);University of Amsterdam, ILLC;http://www.statmt.org/wmt16/tuning-task/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "85b5f97a-6028-5922-954d-eaa19a6fdd0d",
-    "notes": [
-        "The item contains models to tune for the WMT16 Tuning shared task for Czech-to-English.\r\n\r\nCzEng 1.6pre (http://ufal.mff.cuni.cz/czeng/czeng16pre) corpus is used for the training of the translation models. The data is tokenized (using Moses tokenizer), lowercased and sentences longer than 60 words and shorter than 4 words are removed before training. Alignment is done using fast_align (https://github.com/clab/fast_align) and the standard Moses pipeline is used for training.\r\n\r\nTwo 5-gram language models are trained using KenLM: one only using the CzEng English data and the other is trained using all available English mono data for WMT except Common Crawl.\r\n\r\nAlso included are two lexicalized bidirectional reordering models, word based and hierarchical, with msd conditioned on both source and target of processed CzEng."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1671"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "WMT"
-        },
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "tuning"
-        },
-        {
-            "name": "baseline models"
-        },
-        {
-            "name": "shared task"
-        }
-    ],
-    "title": [
-        "WMT16 Tuning Shared Task Models (Czech-to-English)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/85d2e6f6-330d-57d4-a13f-a46a1c8f519c.json b/oaitestdata/clarin-oai_dc/SET_1/json/85d2e6f6-330d-57d4-a13f-a46a1c8f519c.json
deleted file mode 100644
index 7c85c244..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/85d2e6f6-330d-57d4-a13f-a46a1c8f519c.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Electrical Engineering and Computing, University of Zagreb"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Croatian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1218",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1218"
-    ],
-    "PID": "http://hdl.handle.net/11356/1218",
-    "PublicationTimestamp": "2018-12-14T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Faculty of Electrical Engineering and Computing, University of Zagreb"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "https://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Alagi\u0107, Domagoj",
-        "\u0160najder, Jan"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1218;2019-03-01T11:31:19Z;hdl_11356_1023;hdl_11356_1024;Croatian SenseGraph 1.0;\u0160najder, Jan;Alagi\u0107, Domagoj;lexical database;semantic lexicon;lexical substitutes;SenseGraph a graph-like structure of word senses of most common words of the standard Croatian language, obtained by relying on human-provided lexical substitutes for target words in context. SenseGraph is encoded in the Lexical Markup Framework (LMF; ISO 24613:2008) format.\r\n\r\nSenseGraphs consists of SenseCells, which are clusters of same-sense words obtained by grouping of words based on the similarity of their lexical substitution sets and the contexts they appear in. SenseCells can be thought of as Synsets in standard computational lexicographic terminology, albeit they exhibit more variability, which can be attributed to sense modulations in specific contexts. SenseCells are linked to each other based on loose semantic relatedness.\r\n\r\nIn total, the resource covers 649 Croatian words across three different part-of-speech tags: nouns, verbs, and adjectives. More specifically, the resource contains 4,172 sentences across 230 nouns, 3,288 sentences across 200 verbs, and 4,116 sentences across 219 adjectives.  Those sentences were then clustered using a lexical-substitution-based clustering method, yielding 2,877 synsets. The sentences were sampled from the SETimes.HR and hrWaC corpora.\r\n\r\nTotal number of sentences: 11,576\r\nTotal number of syncells: 2,877\r\nTotal number of words: 649;2018-12-14;lexicalConceptualResource;http://hdl.handle.net/11356/1218;hrv;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);https://creativecommons.org/licenses/by-sa/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Faculty of Electrical Engineering and Computing, University of Zagreb;http://sensehive.org/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "85d2e6f6-330d-57d4-a13f-a46a1c8f519c",
-    "notes": [
-        "SenseGraph a graph-like structure of word senses of most common words of the standard Croatian language, obtained by relying on human-provided lexical substitutes for target words in context. SenseGraph is encoded in the Lexical Markup Framework (LMF; ISO 24613:2008) format.\r\n\r\nSenseGraphs consists of SenseCells, which are clusters of same-sense words obtained by grouping of words based on the similarity of their lexical substitution sets and the contexts they appear in. SenseCells can be thought of as Synsets in standard computational lexicographic terminology, albeit they exhibit more variability, which can be attributed to sense modulations in specific contexts. SenseCells are linked to each other based on loose semantic relatedness.\r\n\r\nIn total, the resource covers 649 Croatian words across three different part-of-speech tags: nouns, verbs, and adjectives. More specifically, the resource contains 4,172 sentences across 230 nouns, 3,288 sentences across 200 verbs, and 4,116 sentences across 219 adjectives.  Those sentences were then clustered using a lexical-substitution-based clustering method, yielding 2,877 synsets. The sentences were sampled from the SETimes.HR and hrWaC corpora.\r\n\r\nTotal number of sentences: 11,576\r\nTotal number of syncells: 2,877\r\nTotal number of words: 649"
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1218"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "lexical database"
-        },
-        {
-            "name": "semantic lexicon"
-        },
-        {
-            "name": "lexical substitutes"
-        }
-    ],
-    "title": [
-        "Croatian SenseGraph 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/85ed8580-a7c2-54e2-853d-e6bb02da24bd.json b/oaitestdata/clarin-oai_dc/SET_1/json/85ed8580-a7c2-54e2-853d-e6bb02da24bd.json
deleted file mode 100644
index 1783886a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/85ed8580-a7c2-54e2-853d-e6bb02da24bd.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "PWR Test",
-        "Jan Wieczorek"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/631",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/631"
-    ],
-    "PID": "http://hdl.handle.net/11321/631",
-    "PublicationTimestamp": "2019-03-17T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "PWR Test",
-        "Jan Wieczorek"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NoDerivs 3.0 Unported (CC BY-ND 3.0)",
-        "http://creativecommons.org/licenses/by-nd/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Wieczorek, Jan"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/631;2019-03-17T11:30:53Z;hdl_11321_3;hdl_11321_478;probka lista poznan;Wieczorek, Jan;pr\u00f3ba test;pr\u00f3ba test pozna\u0144;2019-03-17;corpus;http://hdl.handle.net/11321/631;pol;Attribution-NoDerivs 3.0 Unported (CC BY-ND 3.0);http://creativecommons.org/licenses/by-nd/3.0/;CC;text/plain; charset=utf-8;application/vnd.openxmlformats-officedocument.wordprocessingml.document;downloadable_files_count: 1;PWR Test;Jan Wieczorek",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "85ed8580-a7c2-54e2-853d-e6bb02da24bd",
-    "notes": [
-        "pr\u00f3ba test pozna\u0144"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/631"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_478"
-    ],
-    "state": "active",
-    "tags": [],
-    "title": [
-        "probka lista poznan"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8611aeb5-4411-51f2-81a4-29096cd2573f.json b/oaitestdata/clarin-oai_dc/SET_1/json/8611aeb5-4411-51f2-81a4-29096cd2573f.json
deleted file mode 100644
index ec318681..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8611aeb5-4411-51f2-81a4-29096cd2573f.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Ruppel, Klaas"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Finnish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-436",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-436"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-436",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Finland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-436;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Database of etymological references(Etymologinen viitetietokanta);Ruppel, Klaas;128,000 word forms. Database;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-436;fin;downloadable_files_count: 0;Finland;http://kaino.kotus.fi",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8611aeb5-4411-51f2-81a4-29096cd2573f",
-    "notes": [
-        "128,000 word forms. Database"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-436"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Database of etymological references(Etymologinen viitetietokanta)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/862460d2-46ed-5797-909e-7bc9fd47f87c.json b/oaitestdata/clarin-oai_dc/SET_1/json/862460d2-46ed-5797-909e-7bc9fd47f87c.json
deleted file mode 100644
index b23e0126..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/862460d2-46ed-5797-909e-7bc9fd47f87c.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Royster, Paul"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 296 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1593",
-    "MetadataAccess": [
-        "oai:ota:oucs:1593"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Politics"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Jefferson, Thomas, 1743-1826"
-    ],
-    "fulltext": "oai:ota:oucs:1593;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1593.xml;Miscellany / Thomas Jefferson;Jefferson, Thomas, 1743-1826;text_and_corpus_linguistics;American literature -- 18th century;Oxford Text Archive, University of Oxford;Royster, Paul;text/sgml;(1 file : ca. 296 KB);Text;Politics;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "862460d2-46ed-5797-909e-7bc9fd47f87c",
-    "oai_identifier": [
-        "oai:ota:oucs:1593"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "American literature -- th century"
-        }
-    ],
-    "title": [
-        "Miscellany / Thomas Jefferson"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1593.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/862eeea5-a15e-5031-8cee-6238aab2e169.json b/oaitestdata/clarin-oai_dc/SET_1/json/862eeea5-a15e-5031-8cee-6238aab2e169.json
deleted file mode 100644
index 0a2e09db..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/862eeea5-a15e-5031-8cee-6238aab2e169.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-417",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-417"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-417",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Slovenia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-417;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Fida PLUS;reference corpus; 300 mil. words; XML / morphosyntactic tags;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-417;slv;downloadable_files_count: 0;Slovenia;http://www.fidaplus.net/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "862eeea5-a15e-5031-8cee-6238aab2e169",
-    "notes": [
-        "reference corpus; 300 mil. words; XML / morphosyntactic tags"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-417"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Fida PLUS"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8635535b-1f8e-599f-97c7-dcca08903d48.json b/oaitestdata/clarin-oai_dc/SET_1/json/8635535b-1f8e-599f-97c7-dcca08903d48.json
deleted file mode 100644
index e082cf56..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8635535b-1f8e-599f-97c7-dcca08903d48.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "University of Zagreb, Faculty of Humanities and Social Sciences"
-    ],
-    "Contributor": [
-        "Tadi\u0107, Marko"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Croatian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-233",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-233"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-233",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Zagreb, Faculty of Humanities and Social Sciences"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Croatia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-233;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Croatian National Corpus;Tadi\u0107, Marko;written; reference corpus; general; synchornic; monolingual; 101,215,912 tokens;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-233;hrv;downloadable_files_count: 0;Croatia;University of Zagreb, Faculty of Humanities and Social Sciences;http://hnk.ffzg.hr",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8635535b-1f8e-599f-97c7-dcca08903d48",
-    "notes": [
-        "written; reference corpus; general; synchornic; monolingual; 101,215,912 tokens"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-233"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Croatian National Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/863a2a62-0d7b-5116-af0b-e52f514c7eff.json b/oaitestdata/clarin-oai_dc/SET_1/json/863a2a62-0d7b-5116-af0b-e52f514c7eff.json
deleted file mode 100644
index 4b87df1a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/863a2a62-0d7b-5116-af0b-e52f514c7eff.json
+++ /dev/null
@@ -1,113 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/octet-stream",
-        "downloadable_files_count: 3",
-        "application/gzip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/251",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/251"
-    ],
-    "PID": "http://hdl.handle.net/11321/251",
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Andrejewicz, Urszula",
-        "Skubida, Natalia",
-        "Kocyba, Natalia",
-        "Wi\u015bniakowska, Lidia",
-        "Patejuk, Agnieszka",
-        "Filipczak, Joanna",
-        "Itoya, Bo\u017cena",
-        "Maciejewska, Ma\u0142gorzata",
-        "Szczyszek, Micha\u0142",
-        "Kaczmarska, El\u017cbieta",
-        "Batko, Piotr",
-        "Zgondek, Maciej",
-        "Zagajewska, Anna",
-        "Drabik, Lidia",
-        "Sulich, Adrian",
-        "Grzeszak, Anna",
-        "Bukowiecka, Halina",
-        "\u015awidzi\u0144ski, Marek",
-        "Norwa, Agnieszka",
-        "Andrzejczuk, Anna",
-        "Przepi\u00f3rkowski, Adam",
-        "Stankiewicz, Anna",
-        "Andrejewicz, J\u0119drzej",
-        "Szymczak, Jakub",
-        "Rosalska, Paulina",
-        "Zawis\u0142awska, Magdalena",
-        "Skwarski, Filip",
-        "\u0141odzi\u0144ska, Agnieszka",
-        "Opacki, Marcin",
-        "\u017bochowska, Natalia",
-        "Woli\u0144ski, Marcin",
-        "Hajnicz, El\u017cbieta",
-        "Brodzi\u0144ska, Magdalena",
-        "Linsztet, Barbara",
-        "W\u00f3jcicka, Alicja",
-        "\u017burowski, Sebastian",
-        "Kalu\u017cna-Go\u0142\u0105b, Marta"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/251;2016-04-28T09:03:29Z;hdl_11321_3;hdl_11321_4;Walenty (2016-04-28);Andrejewicz, J\u0119drzej;Andrejewicz, Urszula;Andrzejczuk, Anna;Batko, Piotr;Brodzi\u0144ska, Magdalena;Bukowiecka, Halina;Drabik, Lidia;Filipczak, Joanna;Grzeszak, Anna;Hajnicz, El\u017cbieta;Itoya, Bo\u017cena;Kaczmarska, El\u017cbieta;Kalu\u017cna-Go\u0142\u0105b, Marta;Kocyba, Natalia;Linsztet, Barbara;\u0141odzi\u0144ska, Agnieszka;Maciejewska, Ma\u0142gorzata;Norwa, Agnieszka;Opacki, Marcin;Patejuk, Agnieszka;Przepi\u00f3rkowski, Adam;Rosalska, Paulina;Skubida, Natalia;Skwarski, Filip;Stankiewicz, Anna;Sulich, Adrian;Szczyszek, Micha\u0142;Szymczak, Jakub;\u015awidzi\u0144ski, Marek;Wi\u015bniakowska, Lidia;Woli\u0144ski, Marcin;W\u00f3jcicka, Alicja;Zagajewska, Anna;Zawis\u0142awska, Magdalena;Zgondek, Maciej;\u017bochowska, Natalia;\u017burowski, Sebastian;valence dictionary;syntactic schema;semantic frame;Walenty is a valence dictionary of Polish developed at the Institute of Computer Science, Polish Academy of Sciences (IPI PAN).\r\n\r\nThe original formalism of Walenty was established by Filip Skwarski, El\u017cbieta Hajnicz, Agnieszka Patejuk, Adam Przepi\u00f3rkowski, Marcin Woli\u0144ski, Marek \u015awidzi\u0144ski, and Magdalena Zawis\u0142awska. It has been further developed by El\u017cbieta Hajnicz, Agnieszka Patejuk, Adam Przepi\u00f3rkowski, and Marcin Woli\u0144ski. The semantic layer has been developed by El\u017cbieta Hajnicz and Anna Andrzejczuk.\r\n\r\nThe original seed of Walenty was provided by the automatic conversion, manually reviewed by Filip Skwarski, of the verbal valence dictionary used by the \u015awigra2 parser (6396 schemata for 1462 lemmata), which was in turn based on SDPV, the Syntactic Dictionary of Polish Verbs by Marek \u015awidzi\u0144ski (4148 schemata for 1064 lemmata). Afterwards, Walenty has been developed independently by adding new entries, syntactic schemata, in particular phraseological ones, and semantic frames.\r\n\r\nWalenty has been edited and compiled using the Slowal tool (http://zil.ipipan.waw.pl/Slowal) created by Bart\u0142omiej Nito\u0144 and Tomasz Bartosiak.;2016;lexicalConceptualResource;http://hdl.handle.net/11321/251;pol;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;application/gzip;application/gzip;application/gzip;application/octet-stream;application/octet-stream;downloadable_files_count: 3;Institute of Computer Science, Polish Academy of Sciences;http://zil.ipipan.waw.pl/Walenty",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "863a2a62-0d7b-5116-af0b-e52f514c7eff",
-    "notes": [
-        "Walenty is a valence dictionary of Polish developed at the Institute of Computer Science, Polish Academy of Sciences (IPI PAN).\r\n\r\nThe original formalism of Walenty was established by Filip Skwarski, El\u017cbieta Hajnicz, Agnieszka Patejuk, Adam Przepi\u00f3rkowski, Marcin Woli\u0144ski, Marek \u015awidzi\u0144ski, and Magdalena Zawis\u0142awska. It has been further developed by El\u017cbieta Hajnicz, Agnieszka Patejuk, Adam Przepi\u00f3rkowski, and Marcin Woli\u0144ski. The semantic layer has been developed by El\u017cbieta Hajnicz and Anna Andrzejczuk.\r\n\r\nThe original seed of Walenty was provided by the automatic conversion, manually reviewed by Filip Skwarski, of the verbal valence dictionary used by the \u015awigra2 parser (6396 schemata for 1462 lemmata), which was in turn based on SDPV, the Syntactic Dictionary of Polish Verbs by Marek \u015awidzi\u0144ski (4148 schemata for 1064 lemmata). Afterwards, Walenty has been developed independently by adding new entries, syntactic schemata, in particular phraseological ones, and semantic frames.\r\n\r\nWalenty has been edited and compiled using the Slowal tool (http://zil.ipipan.waw.pl/Slowal) created by Bart\u0142omiej Nito\u0144 and Tomasz Bartosiak."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/251"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "valence dictionary"
-        },
-        {
-            "name": "syntactic schema"
-        },
-        {
-            "name": "semantic frame"
-        }
-    ],
-    "title": [
-        "Walenty (2016-04-28)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/865370b6-37fb-5eee-9566-2184ed4e03d7.json b/oaitestdata/clarin-oai_dc/SET_1/json/865370b6-37fb-5eee-9566-2184ed4e03d7.json
deleted file mode 100644
index 17bdf8e2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/865370b6-37fb-5eee-9566-2184ed4e03d7.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4607",
-    "MetadataAccess": [
-        "oai:ota:oucs:4607"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Berkeley, George, 1685-1753."
-    ],
-    "fulltext": "oai:ota:oucs:4607;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4607.xml;Advice to the Tories who have taken the oaths;Berkeley, George, 1685-1753.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "865370b6-37fb-5eee-9566-2184ed4e03d7",
-    "oai_identifier": [
-        "oai:ota:oucs:4607"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Advice to the Tories who have taken the oaths"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4607.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/868e183b-3640-5746-83d8-67f76f7004f1.json b/oaitestdata/clarin-oai_dc/SET_1/json/868e183b-3640-5746-83d8-67f76f7004f1.json
deleted file mode 100644
index 33f39715..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/868e183b-3640-5746-83d8-67f76f7004f1.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Adams, Jon-K"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(2 files : ca. 110, 2 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1198",
-    "MetadataAccess": [
-        "oai:ota:oucs:1198"
-    ],
-    "PublicationTimestamp": "1776-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1776"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Politics"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Paine, Thomas, 1737-1809"
-    ],
-    "fulltext": "oai:ota:oucs:1198;2018-03-05T12:19:01Z;http://ota.ox.ac.uk/headers/1198.xml;Common sense / Thomas Paine;Paine, Thomas, 1737-1809;1776;text_and_corpus_linguistics;United States -- Politics and government -- Revolution, 1775-1783;eng;Oxford Text Archive, University of Oxford;Adams, Jon-K;text/plain;(2 files : ca. 110, 2 KB);Text;Politics;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "868e183b-3640-5746-83d8-67f76f7004f1",
-    "oai_identifier": [
-        "oai:ota:oucs:1198"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "United States -- Politics government -- Revolution"
-        }
-    ],
-    "title": [
-        "Common sense / Thomas Paine"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1198.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8691e2c8-89ef-57c0-a8b2-8237fd7fa900.json b/oaitestdata/clarin-oai_dc/SET_1/json/8691e2c8-89ef-57c0-a8b2-8237fd7fa900.json
deleted file mode 100644
index 729ce7fe..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8691e2c8-89ef-57c0-a8b2-8237fd7fa900.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4178",
-    "MetadataAccess": [
-        "oai:ota:oucs:4178"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Lillo, George, 1693-1739."
-    ],
-    "fulltext": "oai:ota:oucs:4178;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4178.xml;Silvia; or, the country burial. An opera: As it is performed at the Theatre-Royal in Lincoln's-Inn Fields. With the musick prefix'd to each song.;Lillo, George, 1693-1739.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8691e2c8-89ef-57c0-a8b2-8237fd7fa900",
-    "oai_identifier": [
-        "oai:ota:oucs:4178"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Silvia; or, the country burial. An opera: As it is performed at the Theatre-Royal in Lincoln's-Inn Fields. With the musick prefix'd to each song."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4178.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/869bd016-8406-51b4-96a4-22fd706aaf88.json b/oaitestdata/clarin-oai_dc/SET_1/json/869bd016-8406-51b4-96a4-22fd706aaf88.json
deleted file mode 100644
index 1b1f7f17..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/869bd016-8406-51b4-96a4-22fd706aaf88.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Hindi"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-987",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-987"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-987",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-987;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LAC Hindi Corpus;Language and Cognition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-987;hin;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI30273%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "869bd016-8406-51b4-96a4-22fd706aaf88",
-    "notes": [
-        "Language and Cognition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-987"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LAC Hindi Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/86a8ccb1-7677-56ea-afea-9f86dd373bed.json b/oaitestdata/clarin-oai_dc/SET_1/json/86a8ccb1-7677-56ea-afea-9f86dd373bed.json
deleted file mode 100644
index 66476c4a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/86a8ccb1-7677-56ea-afea-9f86dd373bed.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4222",
-    "MetadataAccess": [
-        "oai:ota:oucs:4222"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gibbon, Edward, 1737-1794."
-    ],
-    "fulltext": "oai:ota:oucs:4222;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4222.xml;A vindication of some passages in the fifteenth and sixteenth chapters of the History of the decline and fall of the Roman Empire: By the author.;Gibbon, Edward, 1737-1794.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "86a8ccb1-7677-56ea-afea-9f86dd373bed",
-    "oai_identifier": [
-        "oai:ota:oucs:4222"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A vindication of some passages in the fifteenth and sixteenth chapters of the History of the decline and fall of the Roman Empire: By the author."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4222.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/86b76e02-89e7-5be8-baaa-2d5b4f2b9997.json b/oaitestdata/clarin-oai_dc/SET_1/json/86b76e02-89e7-5be8-baaa-2d5b4f2b9997.json
deleted file mode 100644
index 82bc6fa9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/86b76e02-89e7-5be8-baaa-2d5b4f2b9997.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1030",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1030"
-    ],
-    "PID": "http://hdl.handle.net/11356/1030",
-    "PublicationTimestamp": "2013-09-30T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Krek, Simon",
-        "Zaran\u0161ek, Petra",
-        "Drstven\u0161ek, Nina",
-        "Yero\u0161ina, Olga",
-        "\u0160orli, Mojca",
-        "Kosem, Iztok",
-        "Grabnar, Katja",
-        "Kocjan\u010di\u010d, Polonca",
-        "Gantar, Polona"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1030;2017-09-29T13:48:01Z;hdl_11356_1023;hdl_11356_1024;Slovene lexical database 1.0;Gantar, Polona;Krek, Simon;Kosem, Iztok;\u0160orli, Mojca;Kocjan\u010di\u010d, Polonca;Grabnar, Katja;Yero\u0161ina, Olga;Zaran\u0161ek, Petra;Drstven\u0161ek, Nina;lexical database;semantic description;syntactic description;collocations;Slovene Lexical Database was created between 2008 and 2012 and represents a comprehensive syntactic and semantic description of a selected set of Slovene words. The description was based exclusively on the analysis of reference corpora of Slovene.\r\nThe database is structured as a network of interrelated semantic and syntactic information about a particular word. Semantic level represents the top level in the hierarchy with the lexical unit as its core element. This includes all senses of the headwrd, multi-word expressions and phraseological units. Each sense is described with a short semantic indicator and/or whole-sentence definition which includes typical syntactic environment of the headword with the relevant number, form and semantic types in a valency frame (semantic frame). These are also reflected in a number of syntactic structures and corresponding collocations. All the higher types of information are confirmed by a selection of corpus examples. Multi-word expressions and phraseological units are treated independently from particular senses of the headword and have their own internal structure which requires the same types of information as single-word entries or senses.;2013-09-30;lexicalConceptualResource;http://hdl.handle.net/11356/1030;slv;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);https://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;Centre for Language Resources and Technologies, University of Ljubljana;http://eng.slovenscina.eu/spletni-slovar/leksikalna-baza",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "86b76e02-89e7-5be8-baaa-2d5b4f2b9997",
-    "notes": [
-        "Slovene Lexical Database was created between 2008 and 2012 and represents a comprehensive syntactic and semantic description of a selected set of Slovene words. The description was based exclusively on the analysis of reference corpora of Slovene.\r\nThe database is structured as a network of interrelated semantic and syntactic information about a particular word. Semantic level represents the top level in the hierarchy with the lexical unit as its core element. This includes all senses of the headwrd, multi-word expressions and phraseological units. Each sense is described with a short semantic indicator and/or whole-sentence definition which includes typical syntactic environment of the headword with the relevant number, form and semantic types in a valency frame (semantic frame). These are also reflected in a number of syntactic structures and corresponding collocations. All the higher types of information are confirmed by a selection of corpus examples. Multi-word expressions and phraseological units are treated independently from particular senses of the headword and have their own internal structure which requires the same types of information as single-word entries or senses."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1030"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "lexical database"
-        },
-        {
-            "name": "semantic description"
-        },
-        {
-            "name": "syntactic description"
-        },
-        {
-            "name": "collocations"
-        }
-    ],
-    "title": [
-        "Slovene lexical database 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/86b80547-3252-58ce-90f0-68bf4c3ce131.json b/oaitestdata/clarin-oai_dc/SET_1/json/86b80547-3252-58ce-90f0-68bf4c3ce131.json
deleted file mode 100644
index bdacffa6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/86b80547-3252-58ce-90f0-68bf4c3ce131.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5588",
-    "MetadataAccess": [
-        "oai:ota:oucs:5588"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Barbers' Company (London, England)"
-    ],
-    "fulltext": "oai:ota:oucs:5588;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5588.xml;The case of the barbers of London;Barbers' Company (London, England);text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "86b80547-3252-58ce-90f0-68bf4c3ce131",
-    "oai_identifier": [
-        "oai:ota:oucs:5588"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The case of the barbers of London"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5588.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/86bf417f-d7ae-52a6-8aee-7c09803120fa.json b/oaitestdata/clarin-oai_dc/SET_1/json/86bf417f-d7ae-52a6-8aee-7c09803120fa.json
deleted file mode 100644
index f029a3cd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/86bf417f-d7ae-52a6-8aee-7c09803120fa.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "less than 512 KB"
-    ],
-    "Language": [
-        "Middle English (1100-1500)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0062",
-    "MetadataAccess": [
-        "oai:ota:oucs:0062"
-    ],
-    "PublicationTimestamp": "1350-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1350"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:0062;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0062.xml; Sir Gawayne and the Grene Knyght  / compiled by the Data Preparation Service, University of Newcastle upon Tyne Computing Laboratory and John A. Law;1350-1399;text_and_corpus_linguistics;Poems -- England -- 14th century;enm;Oxford Text Archive, University of Oxford;less than 512 KB;Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "86bf417f-d7ae-52a6-8aee-7c09803120fa",
-    "oai_identifier": [
-        "oai:ota:oucs:0062"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- England -- th century"
-        }
-    ],
-    "title": [
-        " Sir Gawayne and the Grene Knyght  / compiled by the Data Preparation Service, University of Newcastle upon Tyne Computing Laboratory and John A. Law"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0062.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/86c24531-5b58-5762-b375-d1c5eb0149a2.json b/oaitestdata/clarin-oai_dc/SET_1/json/86c24531-5b58-5762-b375-d1c5eb0149a2.json
deleted file mode 100644
index b869e1a7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/86c24531-5b58-5762-b375-d1c5eb0149a2.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4894",
-    "MetadataAccess": [
-        "oai:ota:oucs:4894"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dibdin, Charles, 1745-1814."
-    ],
-    "fulltext": "oai:ota:oucs:4894;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4894.xml;Hannah Hewit: or, the female Crusoe. Being the history of a woman of uncommon, mental, and personal accomplishments; who, ... was cast away in the Grosvenor East-Indiaman: and became for three years the sole inhabitant of an island, in the South Seas. Supposed to be written by herself. [pt.3];Dibdin, Charles, 1745-1814.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "86c24531-5b58-5762-b375-d1c5eb0149a2",
-    "oai_identifier": [
-        "oai:ota:oucs:4894"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Hannah Hewit: or, the female Crusoe. Being the history of a woman of uncommon, mental, and personal accomplishments; who, ... was cast away in the Grosvenor East-Indiaman: and became for three years the sole inhabitant of an island, in the South Seas. Supposed to be written by herself. [pt.3]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4894.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/86c273e7-d309-5311-81e9-d0dceb1b34fd.json b/oaitestdata/clarin-oai_dc/SET_1/json/86c273e7-d309-5311-81e9-d0dceb1b34fd.json
deleted file mode 100644
index 00ba9a85..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/86c273e7-d309-5311-81e9-d0dceb1b34fd.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Universit\u00e4t Hamburg"
-    ],
-    "Contributor": [
-        "Sarnowsky, Prof. Dr. J\u00fcrgen"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1139",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1139"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1139",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Universit\u00e4t Hamburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1139;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Das virtuelle Preu\u00dfische Urkundenbuch;Sarnowsky, Prof. Dr. J\u00fcrgen;Germanistik;Register of decrees as well as texts on the history of Prussia and the Teutonic Order; Regesten und Texte zur Geschichte Preu\u00dfens und des Deutschen Ordens;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1139;deu;downloadable_files_count: 0;Germany;Universit\u00e4t Hamburg;http://www1.uni-hamburg.de/Landesforschung/orden.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "86c273e7-d309-5311-81e9-d0dceb1b34fd",
-    "notes": [
-        "Register of decrees as well as texts on the history of Prussia and the Teutonic Order; Regesten und Texte zur Geschichte Preu\u00dfens und des Deutschen Ordens"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1139"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Das virtuelle Preu\u00dfische Urkundenbuch"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/86fd60b0-948a-5258-b687-38124e834c75.json b/oaitestdata/clarin-oai_dc/SET_1/json/86fd60b0-948a-5258-b687-38124e834c75.json
deleted file mode 100644
index 733b9a12..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/86fd60b0-948a-5258-b687-38124e834c75.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4441",
-    "MetadataAccess": [
-        "oai:ota:oucs:4441"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Brand, John, d. 1808."
-    ],
-    "fulltext": "oai:ota:oucs:4441;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4441.xml;Conscience: an ethical essay. By the Reverend J. Brand;Brand, John, d. 1808.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "86fd60b0-948a-5258-b687-38124e834c75",
-    "oai_identifier": [
-        "oai:ota:oucs:4441"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Conscience: an ethical essay. By the Reverend J. Brand"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4441.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/871ea0c0-f8e0-583e-8261-79fb7f20779b.json b/oaitestdata/clarin-oai_dc/SET_1/json/871ea0c0-f8e0-583e-8261-79fb7f20779b.json
deleted file mode 100644
index 12c58d0f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/871ea0c0-f8e0-583e-8261-79fb7f20779b.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=2d804e44358311e2a2aa782bcb074135c438708db8a44c67958e0267594f26bc",
-    "MetadataAccess": [
-        "2d804e44358311e2a2aa782bcb074135c438708db8a44c67958e0267594f26bc"
-    ],
-    "PublicationTimestamp": "2012-11-23T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "fulltext": "2d804e44358311e2a2aa782bcb074135c438708db8a44c67958e0267594f26bc;2019-02-27T12:09:20Z;corpus;corpus:text;CINTIL-LogicalFormBank;The CINTIL-LogicalFormBank (Branco, 2009, and Branco et al., 2011) is a corpus of semantic dependencies of sentences from Portuguese texts composed of 10,039 sentences and 110,166 tokens taken from different sources and domains: news (8,861 sentences; 101,430 tokens), novels (399 sentences; 3,082 tokens) (see 3.2.). In addition, there are 779 sentences (5,654 tokens) that are used for regression testing of the computational grammar that supported the annotation of the corpus (cf. section 4.6.).\n\nThe CINTIL-LogicalFormBank is composed of MRS representations of each sentence\u00e2\u0080\u0099s semantic relations resulting from a previous semi-automatic analysis with a double-blind annotation followed by adjudication (see Branco and Costa, 2008, with a full description of the process). The resulting dataset contains one information level: semantic relations.\n\nThe main motivation behind the creation of this resource was to build a high quality data set with syntactic information that could support the development of a large set of automatic resources and tools for Portuguese for NLP studies.\n\nThe development of this resource started under the project SemanticShare \u00e2\u0080\u0093 Resources and Tools for Semantic Processing (at: http://nlx.di.fc.ul.pt/projects.html) whose main goal was to generate a deep linguistic annotated corpus of Portuguese, with manually verified grammatical representations. \n;2012-11-23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "871ea0c0-f8e0-583e-8261-79fb7f20779b",
-    "notes": [
-        "The CINTIL-LogicalFormBank (Branco, 2009, and Branco et al., 2011) is a corpus of semantic dependencies of sentences from Portuguese texts composed of 10,039 sentences and 110,166 tokens taken from different sources and domains: news (8,861 sentences; 101,430 tokens), novels (399 sentences; 3,082 tokens) (see 3.2.). In addition, there are 779 sentences (5,654 tokens) that are used for regression testing of the computational grammar that supported the annotation of the corpus (cf. section 4.6.).\n\nThe CINTIL-LogicalFormBank is composed of MRS representations of each sentence\u00e2\u0080\u0099s semantic relations resulting from a previous semi-automatic analysis with a double-blind annotation followed by adjudication (see Branco and Costa, 2008, with a full description of the process). The resulting dataset contains one information level: semantic relations.\n\nThe main motivation behind the creation of this resource was to build a high quality data set with syntactic information that could support the development of a large set of automatic resources and tools for Portuguese for NLP studies.\n\nThe development of this resource started under the project SemanticShare \u00e2\u0080\u0093 Resources and Tools for Semantic Processing (at: http://nlx.di.fc.ul.pt/projects.html) whose main goal was to generate a deep linguistic annotated corpus of Portuguese, with manually verified grammatical representations. \n"
-    ],
-    "oai_identifier": [
-        "2d804e44358311e2a2aa782bcb074135c438708db8a44c67958e0267594f26bc"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "CINTIL-LogicalFormBank"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/873cee8f-19d0-5590-b6a7-bc392ac3cb8b.json b/oaitestdata/clarin-oai_dc/SET_1/json/873cee8f-19d0-5590-b6a7-bc392ac3cb8b.json
deleted file mode 100644
index 205f1a67..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/873cee8f-19d0-5590-b6a7-bc392ac3cb8b.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Institute of Mathematics and Computer Science, University of Latvia"
-    ],
-    "Contributor": [
-        "Spektors, Andrejs"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "Latvian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-477",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-477"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-477",
-    "PublicationTimestamp": "2010-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "Institute of Mathematics and Computer Science, University of Latvia"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Latvia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-477;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Dictionary of the standard Latvian language;Spektors, Andrejs;dictionary;~64 000 entries;2010;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-477;lav;text/html;downloadable_files_count: 0;Latvia;Institute of Mathematics and Computer Science, University of Latvia;http://www.tezaurs.lv/llvv/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "873cee8f-19d0-5590-b6a7-bc392ac3cb8b",
-    "notes": [
-        "~64 000 entries"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-477"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "dictionary"
-        }
-    ],
-    "title": [
-        "Dictionary of the standard Latvian language"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/87716c5a-c5b8-58fb-b688-358116400b75.json b/oaitestdata/clarin-oai_dc/SET_1/json/87716c5a-c5b8-58fb-b688-358116400b75.json
deleted file mode 100644
index 12a53c95..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/87716c5a-c5b8-58fb-b688-358116400b75.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Institut f\u00fcr Deutsche Sprache"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1162",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1162"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1162",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut f\u00fcr Deutsche Sprache"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1162;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Valenzw\u00f6rterbuch E-VALBU;Germanistik;elektronisches Valenzw\u00f6rterbuch deutscher Verben;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1162;deu;downloadable_files_count: 0;Germany;Institut f\u00fcr Deutsche Sprache;http://hypermedia2.ids-mannheim.de/evalbu/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "87716c5a-c5b8-58fb-b688-358116400b75",
-    "notes": [
-        "elektronisches Valenzw\u00f6rterbuch deutscher Verben"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1162"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Valenzw\u00f6rterbuch E-VALBU"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/877bdf4d-8b20-505c-99a6-6e649f240afc.json b/oaitestdata/clarin-oai_dc/SET_1/json/877bdf4d-8b20-505c-99a6-6e649f240afc.json
deleted file mode 100644
index f7052fe2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/877bdf4d-8b20-505c-99a6-6e649f240afc.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4708",
-    "MetadataAccess": [
-        "oai:ota:oucs:4708"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dodington, George Bubb, Baron of Melcombe Regis, 1691-1762."
-    ],
-    "fulltext": "oai:ota:oucs:4708;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4708.xml;Occasional observations on a double-titled-paper, about the clear produce of the civil-list revenue, from midsummer 1727, to midsummer last;Dodington, George Bubb, Baron of Melcombe Regis, 1691-1762.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "877bdf4d-8b20-505c-99a6-6e649f240afc",
-    "oai_identifier": [
-        "oai:ota:oucs:4708"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Occasional observations on a double-titled-paper, about the clear produce of the civil-list revenue, from midsummer 1727, to midsummer last"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4708.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/87882fc5-59b5-5d85-b8af-9ebd329b4e47.json b/oaitestdata/clarin-oai_dc/SET_1/json/87882fc5-59b5-5d85-b8af-9ebd329b4e47.json
deleted file mode 100644
index 44befcd0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/87882fc5-59b5-5d85-b8af-9ebd329b4e47.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2697",
-    "MetadataAccess": [
-        "oai:ota:oucs:2697"
-    ],
-    "PublicationTimestamp": "1735-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1735"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2697;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2697.xml;Tatler 230;Swift, Jonathan, 1667-1745;1735;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "87882fc5-59b5-5d85-b8af-9ebd329b4e47",
-    "oai_identifier": [
-        "oai:ota:oucs:2697"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Tatler 230"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2697.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/879a4d9a-665b-59fd-953c-17694e7930fd.json b/oaitestdata/clarin-oai_dc/SET_1/json/879a4d9a-665b-59fd-953c-17694e7930fd.json
deleted file mode 100644
index 89d2f4ee..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/879a4d9a-665b-59fd-953c-17694e7930fd.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2781",
-    "MetadataAccess": [
-        "oai:ota:oucs:2781"
-    ],
-    "PublicationTimestamp": "1746-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1746"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2781;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2781.xml;The story of the injured lady;Swift, Jonathan, 1667-1745;1746;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "879a4d9a-665b-59fd-953c-17694e7930fd",
-    "oai_identifier": [
-        "oai:ota:oucs:2781"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The story of the injured lady"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2781.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/87a26db3-fdc0-5754-98e5-29b7e8777442.json b/oaitestdata/clarin-oai_dc/SET_1/json/87a26db3-fdc0-5754-98e5-29b7e8777442.json
deleted file mode 100644
index 1ddb1ada..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/87a26db3-fdc0-5754-98e5-29b7e8777442.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Franciszka Cezarego"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-148515",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-148515"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CDF-2",
-    "PublicationTimestamp": "1661-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1661"
-    ],
-    "Publisher": [
-        "Drukarnia Franciszka Cezarego"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/148515",
-        "oai:jbc.bj.uj.edu.pl:publication:156741"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1601/1700"
-    ],
-    "TempCoverageBegin": 50506804799,
-    "TempCoverageEnd": 50506804799,
-    "TemporalCoverage": " point in time : 1601-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1601-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1601-07-01T11:59:59Z",
-    "author": [
-        "Cichowski, Miko\u0142aj (1598-1669)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-148515;2019-02-28T18:17:26Z;Obrona Zacnych Y Poboznych Lvdzi : Ktorzy Zbrzydziwszy si\u0119 Bluznierstwami sekty Arryanskiey abo Socynskiey do Ko\u015bcio\u0142a si\u0119 \u015b. Katholickiego vdali : przeciwko Paskwilowi od iakiego\u015b Ministra Arria\u0144skiego przeciw nim napisan\u0119mu y po Podgorzu rozsian\u0119mu;Z Namow\u0105 Do Stanow Koronnych wniesion\u0105, aby przy Konstytucyach przeciw Arryanom vchwalonych statecznie stali;Cichowski, Miko\u0142aj (1598-1669);starodruki 17\u00a0w.;Zaremba, Stanis\u0142aw (16..-1685). [Adr. ded.];Drukarnia Franciszka Cezarego;1661;starodruk;application/xml;clarind-uds:poldilemma-148515;hdl:11858/00-246C-0000-0023-8CDF-2;Biblioteka Jagiello\u0144ska, BJ St. Dr. 39089 I;Biblioteka Jagiello\u0144ska, BJ St. Dr. 39090 I;pol;lat;http://jbc.bj.uj.edu.pl/Content/148515;oai:jbc.bj.uj.edu.pl:publication:156741;1601/1700;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "87a26db3-fdc0-5754-98e5-29b7e8777442",
-    "notes": [
-        "Zaremba, Stanis\u0142aw (16..-1685). [Adr. ded.]"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-148515"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Obrona Zacnych Y Poboznych Lvdzi : Ktorzy Zbrzydziwszy si\u0119 Bluznierstwami sekty Arryanskiey abo Socynskiey do Ko\u015bcio\u0142a si\u0119 \u015b. Katholickiego vdali : przeciwko Paskwilowi od iakiego\u015b Ministra Arria\u0144skiego przeciw nim napisan\u0119mu y po Podgorzu rozsian\u0119mu",
-        "Z Namow\u0105 Do Stanow Koronnych wniesion\u0105, aby przy Konstytucyach przeciw Arryanom vchwalonych statecznie stali"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/87a54583-a7d8-5109-95f1-32b861d1fcbe.json b/oaitestdata/clarin-oai_dc/SET_1/json/87a54583-a7d8-5109-95f1-32b861d1fcbe.json
deleted file mode 100644
index a15a156b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/87a54583-a7d8-5109-95f1-32b861d1fcbe.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4876",
-    "MetadataAccess": [
-        "oai:ota:oucs:4876"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "King, Thomas, fl. 1791."
-    ],
-    "fulltext": "oai:ota:oucs:4876;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4876.xml;A check on uncharitableness: or, an answer to a book, entitled, \"The skeleton; or the Arminian anatomized; and the carnal preacher dissected. By W.H.\" In three parts. ... To which is added, A farther check to uncharitableness: ... By Thomas King.;King, Thomas, fl. 1791.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "87a54583-a7d8-5109-95f1-32b861d1fcbe",
-    "oai_identifier": [
-        "oai:ota:oucs:4876"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A check on uncharitableness: or, an answer to a book, entitled, \"The skeleton; or the Arminian anatomized; and the carnal preacher dissected. By W.H.\" In three parts. ... To which is added, A farther check to uncharitableness: ... By Thomas King."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4876.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/87e35cc5-ba2c-5280-aec9-6854ca116c89.json b/oaitestdata/clarin-oai_dc/SET_1/json/87e35cc5-ba2c-5280-aec9-6854ca116c89.json
deleted file mode 100644
index 3ed7f92e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/87e35cc5-ba2c-5280-aec9-6854ca116c89.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5443",
-    "MetadataAccess": [
-        "oai:ota:oucs:5443"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "King, Thomas, 1730-1805."
-    ],
-    "fulltext": "oai:ota:oucs:5443;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5443.xml;Like master, like man: A comedy of two acts. Alter'd from Sir John Vanbrugh. As perform'd at the Theatre, in Smock-Alley.;King, Thomas, 1730-1805.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "87e35cc5-ba2c-5280-aec9-6854ca116c89",
-    "oai_identifier": [
-        "oai:ota:oucs:5443"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Like master, like man: A comedy of two acts. Alter'd from Sir John Vanbrugh. As perform'd at the Theatre, in Smock-Alley."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5443.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/87ea6aa8-22a6-577a-bfb2-edcf8bd86f7f.json b/oaitestdata/clarin-oai_dc/SET_1/json/87ea6aa8-22a6-577a-bfb2-edcf8bd86f7f.json
deleted file mode 100644
index 9fd10912..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/87ea6aa8-22a6-577a-bfb2-edcf8bd86f7f.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 48.2 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2283",
-    "MetadataAccess": [
-        "oai:ota:oucs:2283"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Fielding, Henry, 1707-1754"
-    ],
-    "fulltext": "oai:ota:oucs:2283;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/2283.xml;A serious address to the people of Great Britain : in which the certain consequences of the present rebellion are fully demonstrated. Necessary to be perused by every lover of his country at this juncture;Fielding, Henry, 1707-1754;default: 1976-01-01;text_and_corpus_linguistics;Addresses -- Great Britain -- 18th century;eng;Oxford Text Archive, University of Oxford;(1 file : ca. 48.2 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "87ea6aa8-22a6-577a-bfb2-edcf8bd86f7f",
-    "oai_identifier": [
-        "oai:ota:oucs:2283"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Addresses -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "A serious address to the people of Great Britain : in which the certain consequences of the present rebellion are fully demonstrated. Necessary to be perused by every lover of his country at this juncture"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2283.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/88263af4-a1bb-579f-b951-e2c2890de0f0.json b/oaitestdata/clarin-oai_dc/SET_1/json/88263af4-a1bb-579f-b951-e2c2890de0f0.json
deleted file mode 100644
index d4d0d758..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/88263af4-a1bb-579f-b951-e2c2890de0f0.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Gilliver, Peter"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 459 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0072",
-    "MetadataAccess": [
-        "oai:ota:oucs:0072"
-    ],
-    "PublicationTimestamp": "1960-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1960"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Storey, David, 1933-"
-    ],
-    "fulltext": "oai:ota:oucs:0072;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0072.xml;This sporting life : a novel / David Storey;Storey, David, 1933-;1960;text_and_corpus_linguistics;English fiction -- 20th century;eng;Oxford Text Archive, University of Oxford;Gilliver, Peter;(1 file : ca. 459 KB);Text;Novels;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "88263af4-a1bb-579f-b951-e2c2890de0f0",
-    "oai_identifier": [
-        "oai:ota:oucs:0072"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English fiction -- th century"
-        }
-    ],
-    "title": [
-        "This sporting life : a novel / David Storey"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0072.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/882b754a-0277-58f6-a276-e8fc11a8d36a.json b/oaitestdata/clarin-oai_dc/SET_1/json/882b754a-0277-58f6-a276-e8fc11a8d36a.json
deleted file mode 100644
index 6402fb78..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/882b754a-0277-58f6-a276-e8fc11a8d36a.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1021",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1021"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1021",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1021;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Zeno.org;Germanistik;Access to full texts (literary, historical, scientific, ... texts); Volltextbibliothek; keine Beschr\u00e4nkung auf literarische Texte (auch z.B. naturwissenschaftliche, geschichtliche, ... Texte);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1021;deu;downloadable_files_count: 0;http://www.zeno.org",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "882b754a-0277-58f6-a276-e8fc11a8d36a",
-    "notes": [
-        "Access to full texts (literary, historical, scientific, ... texts); Volltextbibliothek; keine Beschr\u00e4nkung auf literarische Texte (auch z.B. naturwissenschaftliche, geschichtliche, ... Texte)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1021"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Zeno.org"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/882eac18-e7da-5ab8-a15f-b7a120679f94.json b/oaitestdata/clarin-oai_dc/SET_1/json/882eac18-e7da-5ab8-a15f-b7a120679f94.json
deleted file mode 100644
index 6ef2580e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/882eac18-e7da-5ab8-a15f-b7a120679f94.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 4",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "English",
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1449",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1449"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1449",
-    "PublicationTimestamp": "2014-09-26T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-161",
-        "http://hdl.handle.net/11234/1-1450"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU General Public License, version 2",
-        "http://www.gnu.org/licenses/gpl-2.0.html",
-        "PUB"
-    ],
-    "author": [
-        "Rosa, Rudolf"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1449;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Fairytale child (2014-09-26);Rosa, Rudolf;dialogue system;morphological generation;Treex;morphological analysis;interactive;Fairytale Child is a simple chatbot trying to simulate a curious child. It asks the user to tell a fairy tale, often interrupting to ask for details and clarifications. However, it remembers what it was told and tries to show it if possible.\r\n\r\nThe chatbot can communicate in Czech and in English. It analyzes the morphology of each sentence produced by the user with natural language processing tools, tries to identify potential questions to ask, and then asks one. A morphological generator is employed to generate correctly inflected sentences in Czech, so that the resulting sentences sound as natural as possible.\r\n\r\nPoh\u00e1dkov\u00e9 d\u00edt\u011b je jednoduch\u00fd chatbot, simuluj\u00edc\u00ed zv\u00eddav\u00e9 d\u00edt\u011b. Po\u017e\u00e1d\u00e1 u\u017eivatele, aby mu vypr\u00e1v\u011bl poh\u00e1dku, ale \u010dasto ho p\u0159eru\u0161uje, aby se zeptal na detaily a vysv\u011btlen\u00ed. Pamatuje si ale, co mu u\u017eivatel \u0159ekl, a sna\u017e\u00ed se to pokud mo\u017eno d\u00e1t najevo.\r\n\r\nChatbot um\u00ed komunikovat \u010desky a anglicky. Analyzuje tvaroslov\u00ed ka\u017ed\u00e9 u\u017eivatelovy v\u011bty pomoc\u00ed NLP n\u00e1stroj\u016f, pokus\u00ed se nal\u00e9zt chodnou ot\u00e1zku, a tu pak polo\u017e\u00ed. Aby tvo\u0159en\u00e9 \u010desk\u00e9 v\u011bty zn\u011bly co nejp\u0159irozen\u011bji, vyu\u017e\u00edv\u00e1 se pro sklo\u0148ov\u00e1n\u00ed tvaroslovn\u00fd gener\u00e1tor.;2014-09-26;toolService;http://hdl.handle.net/11234/1-1449;eng;ces;http://hdl.handle.net/11234/1-161;http://hdl.handle.net/11234/1-1450;GNU General Public License, version 2;http://www.gnu.org/licenses/gpl-2.0.html;PUB;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 4;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://ufal.mff.cuni.cz/dite",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "882eac18-e7da-5ab8-a15f-b7a120679f94",
-    "notes": [
-        "Fairytale Child is a simple chatbot trying to simulate a curious child. It asks the user to tell a fairy tale, often interrupting to ask for details and clarifications. However, it remembers what it was told and tries to show it if possible.\r\n\r\nThe chatbot can communicate in Czech and in English. It analyzes the morphology of each sentence produced by the user with natural language processing tools, tries to identify potential questions to ask, and then asks one. A morphological generator is employed to generate correctly inflected sentences in Czech, so that the resulting sentences sound as natural as possible.\r\n\r\nPoh\u00e1dkov\u00e9 d\u00edt\u011b je jednoduch\u00fd chatbot, simuluj\u00edc\u00ed zv\u00eddav\u00e9 d\u00edt\u011b. Po\u017e\u00e1d\u00e1 u\u017eivatele, aby mu vypr\u00e1v\u011bl poh\u00e1dku, ale \u010dasto ho p\u0159eru\u0161uje, aby se zeptal na detaily a vysv\u011btlen\u00ed. Pamatuje si ale, co mu u\u017eivatel \u0159ekl, a sna\u017e\u00ed se to pokud mo\u017eno d\u00e1t najevo.\r\n\r\nChatbot um\u00ed komunikovat \u010desky a anglicky. Analyzuje tvaroslov\u00ed ka\u017ed\u00e9 u\u017eivatelovy v\u011bty pomoc\u00ed NLP n\u00e1stroj\u016f, pokus\u00ed se nal\u00e9zt chodnou ot\u00e1zku, a tu pak polo\u017e\u00ed. Aby tvo\u0159en\u00e9 \u010desk\u00e9 v\u011bty zn\u011bly co nejp\u0159irozen\u011bji, vyu\u017e\u00edv\u00e1 se pro sklo\u0148ov\u00e1n\u00ed tvaroslovn\u00fd gener\u00e1tor."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1449"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "dialogue system"
-        },
-        {
-            "name": "morphological generation"
-        },
-        {
-            "name": "Treex"
-        },
-        {
-            "name": "morphological analysis"
-        },
-        {
-            "name": "interactive"
-        }
-    ],
-    "title": [
-        "Fairytale child (2014-09-26)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/883f6bd1-b240-5761-9062-4b0b4ab30104.json b/oaitestdata/clarin-oai_dc/SET_1/json/883f6bd1-b240-5761-9062-4b0b4ab30104.json
deleted file mode 100644
index 12bc8e40..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/883f6bd1-b240-5761-9062-4b0b4ab30104.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Waite, Stephen V.F."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 105 KB)"
-    ],
-    "Language": [
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0345",
-    "MetadataAccess": [
-        "oai:ota:oucs:0345"
-    ],
-    "PublicationYear": [
-        "16"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Ovid, 43 B.C.-17 or 18 A.D."
-    ],
-    "fulltext": "oai:ota:oucs:0345;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0345.xml;Amores / Ovid;The loves;Ovid, 43 B.C.-17 or 18 A.D.;16;text_and_corpus_linguistics;Love poetry, Classical -- 1st century;lat;Oxford Text Archive, University of Oxford;Waite, Stephen V.F.;(1 file : ca. 105 KB);Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "883f6bd1-b240-5761-9062-4b0b4ab30104",
-    "oai_identifier": [
-        "oai:ota:oucs:0345"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Love poetry"
-        },
-        {
-            "name": "Classical -- st century"
-        }
-    ],
-    "title": [
-        "Amores / Ovid",
-        "The loves"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0345.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8849cfd3-d209-5824-9038-888afd3b3e5b.json b/oaitestdata/clarin-oai_dc/SET_1/json/8849cfd3-d209-5824-9038-888afd3b3e5b.json
deleted file mode 100644
index d3c03828..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8849cfd3-d209-5824-9038-888afd3b3e5b.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1132",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1132"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1132",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Germany||United States"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1132;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Mediaevum - Das altgermanistische Internetportal;Germanistik;On Mediaevum.de, a collection of links to Middle High German texts can be found. These texts are made available via the University of Virginia. Auf Mediaevum.de findet sich eine Linksammlung zu diversen mittelhochdeutschen Texten, welche als Volltexte \u00fcber die University of Virginia erreichbar sind.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1132;deu;downloadable_files_count: 0;Germany||United States;http://texte.mediaevum.de/textkorpora.htm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8849cfd3-d209-5824-9038-888afd3b3e5b",
-    "notes": [
-        "On Mediaevum.de, a collection of links to Middle High German texts can be found. These texts are made available via the University of Virginia. Auf Mediaevum.de findet sich eine Linksammlung zu diversen mittelhochdeutschen Texten, welche als Volltexte \u00fcber die University of Virginia erreichbar sind."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1132"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Mediaevum - Das altgermanistische Internetportal"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/884a3178-78ac-54b2-93c3-b0dc30de7b87.json b/oaitestdata/clarin-oai_dc/SET_1/json/884a3178-78ac-54b2-93c3-b0dc30de7b87.json
deleted file mode 100644
index 0fa35284..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/884a3178-78ac-54b2-93c3-b0dc30de7b87.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "University of Zagreb, Faculty of Humanities and Social Sciences"
-    ],
-    "Contributor": [
-        "Tadi\u0107, Marko"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Croatian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-259",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-259"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-259",
-    "PublicationTimestamp": "1999-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1999"
-    ],
-    "Publisher": [
-        "University of Zagreb, Faculty of Humanities and Social Sciences"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Croatia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-259;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Croatian Frequency Dictionary;Tadi\u0107, Marko;38,573 lemmas, plain text; database file;1999;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-259;hrv;application/octet-stream;downloadable_files_count: 0;Croatia;University of Zagreb, Faculty of Humanities and Social Sciences;http://hml.ffzg.hr/hml/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "884a3178-78ac-54b2-93c3-b0dc30de7b87",
-    "notes": [
-        "38,573 lemmas, plain text; database file"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-259"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Croatian Frequency Dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/88abab98-1b4d-599c-ae92-c6b3a625da68.json b/oaitestdata/clarin-oai_dc/SET_1/json/88abab98-1b4d-599c-ae92-c6b3a625da68.json
deleted file mode 100644
index 6a3cdbd6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/88abab98-1b4d-599c-ae92-c6b3a625da68.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-949",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-949"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-949",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-949;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Latin;ca. 2.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-949;lat;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#lat",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "88abab98-1b4d-599c-ae92-c6b3a625da68",
-    "notes": [
-        "ca. 2.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-949"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Latin"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/88bfd6c9-bc29-5b49-a801-6986720c19ec.json b/oaitestdata/clarin-oai_dc/SET_1/json/88bfd6c9-bc29-5b49-a801-6986720c19ec.json
deleted file mode 100644
index eba2fa55..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/88bfd6c9-bc29-5b49-a801-6986720c19ec.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/pdf"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/625",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/625"
-    ],
-    "PID": "http://hdl.handle.net/11321/625",
-    "PublicationTimestamp": "2019-02-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "CC",
-        "http://creativecommons.org/licenses/by/3.0/"
-    ],
-    "author": [
-        "Oleksy, Marcin",
-        "Marci\u0144czuk, Micha\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/625;2019-02-07T15:21:49Z;hdl_11321_3;hdl_11321_4;KPWr annotation guidelines - named entity and phrase lemmatization 2.0;Marci\u0144czuk, Micha\u0142;Oleksy, Marcin;named entities;lemmatization;Guidelines for named entity and multi-word phrase lemmatization used in in KPWr (Polish Corpus of Wroc\u0142aw University of Technology).;2019-02-07;languageDescription;http://hdl.handle.net/11321/625;pol;lemmatization;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);CC;http://creativecommons.org/licenses/by/3.0/;text/plain; charset=utf-8;application/pdf;downloadable_files_count: 1;Wroc\u0142aw University of Science and Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "88bfd6c9-bc29-5b49-a801-6986720c19ec",
-    "notes": [
-        "Guidelines for named entity and multi-word phrase lemmatization used in in KPWr (Polish Corpus of Wroc\u0142aw University of Technology)."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/625"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "named entities"
-        },
-        {
-            "name": "lemmatization"
-        }
-    ],
-    "title": [
-        "KPWr annotation guidelines - named entity and phrase lemmatization 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/88ccbd42-3c82-5a01-a11f-ad45a2a6daaf.json b/oaitestdata/clarin-oai_dc/SET_1/json/88ccbd42-3c82-5a01-a11f-ad45a2a6daaf.json
deleted file mode 100644
index 7749ed01..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/88ccbd42-3c82-5a01-a11f-ad45a2a6daaf.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Institute of Mathematics and Computer Science, University of Latvia"
-    ],
-    "Contributor": [
-        "B\u0101rzdi\u0146\u0161, Guntis"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Latvian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1252",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1252"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1252",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institute of Mathematics and Computer Science, University of Latvia"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Latvia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Paikens, P\u0113teris",
-        "Poik\u0101ns, Ilm\u0101rs",
-        "Borodkins, Imants"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1252;2016-04-06T16:39:49Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;SemTi-Kamols corpus annotator;Paikens, P\u0113teris;Borodkins, Imants;Poik\u0101ns, Ilm\u0101rs;B\u0101rzdi\u0146\u0161, Guntis;Semi-automatic corpus annotation tool for Latvian. Incorporates the SemTi-Kamols morphological analyzer and dependency chunker.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1252;lav;downloadable_files_count: 0;Latvia;Institute of Mathematics and Computer Science, University of Latvia;http://www.semti-kamols.lv/doc_upl/annotator-r742.zip",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "88ccbd42-3c82-5a01-a11f-ad45a2a6daaf",
-    "notes": [
-        "Semi-automatic corpus annotation tool for Latvian. Incorporates the SemTi-Kamols morphological analyzer and dependency chunker."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1252"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "SemTi-Kamols corpus annotator"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/88d21685-ec64-57ce-b00c-4869e5d5e065.json b/oaitestdata/clarin-oai_dc/SET_1/json/88d21685-ec64-57ce-b00c-4869e5d5e065.json
deleted file mode 100644
index 4ea089d2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/88d21685-ec64-57ce-b00c-4869e5d5e065.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Trojina, Institute for Applied Slovene Studies"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1150",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1150"
-    ],
-    "PID": "http://hdl.handle.net/11356/1150",
-    "PublicationTimestamp": "2018-07-29T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Trojina, Institute for Applied Slovene Studies"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Krek, Simon",
-        "Laskowski, Cyprian",
-        "Kosem, Iztok",
-        "Stritar Ku\u010duk, Mojca",
-        "Rozman, Tadeja",
-        "Arhar Holdt, \u0160pela",
-        "Klemenc, Bojan",
-        "Stabej, Marko",
-        "Krap\u0161 Vodopivec, Irena"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1150;2018-11-21T16:52:08Z;hdl_11356_1023;hdl_11356_1024;Developmental corpus of Slovene (without language corrections) \u0160olar-Clear;Rozman, Tadeja;Stritar Ku\u010duk, Mojca;Kosem, Iztok;Krek, Simon;Krap\u0161 Vodopivec, Irena;Arhar Holdt, \u0160pela;Stabej, Marko;Laskowski, Cyprian;Klemenc, Bojan;student writing;developmental corpus;\u0160olar-Clear is an adapted version of the \u0160olar 1.0 corpus, cf. http://hdl.handle.net/11356/1036. \r\n\r\nThe \u0160olar(-Clear) corpus consists of texts written by students in Slovene primary and secondary schools. School essays form the majority of the corpus (64.2%) while other material includes texts created during lessons, such as text recapitulations or descriptions, examples of formal applications etc.\r\n\r\nUnlike the original \u0160olar corpus, \u0160olar-Clear only includes student texts while language corrections and other types of feedback from the teachers are not included. The corpus can thus be used for processing tasks where the inclusion of corrections hinders or complicates the procedures (e.g. for comparative data extraction, training of language models etc).;2018-07-29;corpus;http://hdl.handle.net/11356/1150;slv;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);https://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;Trojina, Institute for Applied Slovene Studies;http://www.slovenscina.eu/korpusi/solar",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "88d21685-ec64-57ce-b00c-4869e5d5e065",
-    "notes": [
-        "\u0160olar-Clear is an adapted version of the \u0160olar 1.0 corpus, cf. http://hdl.handle.net/11356/1036. \r\n\r\nThe \u0160olar(-Clear) corpus consists of texts written by students in Slovene primary and secondary schools. School essays form the majority of the corpus (64.2%) while other material includes texts created during lessons, such as text recapitulations or descriptions, examples of formal applications etc.\r\n\r\nUnlike the original \u0160olar corpus, \u0160olar-Clear only includes student texts while language corrections and other types of feedback from the teachers are not included. The corpus can thus be used for processing tasks where the inclusion of corrections hinders or complicates the procedures (e.g. for comparative data extraction, training of language models etc)."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1150"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "student writing"
-        },
-        {
-            "name": "developmental corpus"
-        }
-    ],
-    "title": [
-        "Developmental corpus of Slovene (without language corrections) \u0160olar-Clear"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/88d51410-a188-52ae-a51b-c2823cadf096.json b/oaitestdata/clarin-oai_dc/SET_1/json/88d51410-a188-52ae-a51b-c2823cadf096.json
deleted file mode 100644
index f43fac76..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/88d51410-a188-52ae-a51b-c2823cadf096.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "ILSP/R.C. \"Athena\""
-    ],
-    "Contributor": [
-        "Prokopidis, Prokopis"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1310",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1310"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1310",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "ILSP/R.C. \"Athena\""
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Greece"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Papageorgiou, Haris",
-        "Prokopidis, Prokopis"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1310;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;ILSP Lemmatizer;Papageorgiou, Haris;Prokopidis, Prokopis;Prokopidis, Prokopis;lemmatizer;ILSP Lemmatiser consults the ILSP Morphological Lexicon to assign lemmas, based on POS information provided by ILSP FBT Tagger.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1310;downloadable_files_count: 0;Greece;ILSP/R.C. \"Athena\"",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "88d51410-a188-52ae-a51b-c2823cadf096",
-    "notes": [
-        "ILSP Lemmatiser consults the ILSP Morphological Lexicon to assign lemmas, based on POS information provided by ILSP FBT Tagger."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1310"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "lemmatizer"
-        }
-    ],
-    "title": [
-        "ILSP Lemmatizer"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/88d83a8a-01a6-55da-9dc2-8bc9cb02b3f1.json b/oaitestdata/clarin-oai_dc/SET_1/json/88d83a8a-01a6-55da-9dc2-8bc9cb02b3f1.json
deleted file mode 100644
index 0353a597..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/88d83a8a-01a6-55da-9dc2-8bc9cb02b3f1.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Tilde"
-    ],
-    "Contributor": [
-        "Skadi\u0146\u0161, Raivis"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Estonian",
-        "Latvian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-604",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-604"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-604",
-    "PublicationTimestamp": "2007-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2007"
-    ],
-    "Publisher": [
-        "Tilde"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Latvia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-604;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Estonian-Latvian dictionary;Skadi\u0146\u0161, Raivis;Estonian-Latvian dictionary is based on dictionary of K.Aben and suplemented with new lexical entries of modern lexica, ca. 26 000 lexical entries;2007;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-604;est;lav;application/octet-stream;downloadable_files_count: 0;Latvia;Tilde;http://eesti.letonika.lv/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "88d83a8a-01a6-55da-9dc2-8bc9cb02b3f1",
-    "notes": [
-        "Estonian-Latvian dictionary is based on dictionary of K.Aben and suplemented with new lexical entries of modern lexica, ca. 26 000 lexical entries"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-604"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Estonian-Latvian dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/88dee8ce-466c-5f2c-81fd-07709c4a8b88.json b/oaitestdata/clarin-oai_dc/SET_1/json/88dee8ce-466c-5f2c-81fd-07709c4a8b88.json
deleted file mode 100644
index 6c0f5591..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/88dee8ce-466c-5f2c-81fd-07709c4a8b88.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Baumann, Walter"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 500 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0203",
-    "MetadataAccess": [
-        "oai:ota:oucs:0203"
-    ],
-    "PublicationTimestamp": "1808-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1808"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Goethe, Johann Wolfgang von, 1749-1832"
-    ],
-    "fulltext": "oai:ota:oucs:0203;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0203.xml;Faust;Faust / Johann Wolfgang von Goethe;Goethe, Johann Wolfgang von, 1749-1832;1808;text_and_corpus_linguistics;German drama (Tragedy) -- 18th century;deu;Oxford Text Archive, University of Oxford;Baumann, Walter;text/plain;(1 file : ca. 500 KB);Text;Plays;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "88dee8ce-466c-5f2c-81fd-07709c4a8b88",
-    "oai_identifier": [
-        "oai:ota:oucs:0203"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "German drama Tragedy -- th century"
-        }
-    ],
-    "title": [
-        "Faust",
-        "Faust / Johann Wolfgang von Goethe"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0203.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/88e02495-b324-50ef-b471-127bf1af717e.json b/oaitestdata/clarin-oai_dc/SET_1/json/88e02495-b324-50ef-b471-127bf1af717e.json
deleted file mode 100644
index a40b5745..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/88e02495-b324-50ef-b471-127bf1af717e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3577",
-    "MetadataAccess": [
-        "oai:ota:oucs:3577"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Glover, Richard, 1712-1785."
-    ],
-    "fulltext": "oai:ota:oucs:3577;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3577.xml;Medea. A tragedy;Glover, Richard, 1712-1785.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "88e02495-b324-50ef-b471-127bf1af717e",
-    "oai_identifier": [
-        "oai:ota:oucs:3577"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Medea. A tragedy"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3577.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/88e1b8a1-44f3-5de0-bbcf-563925947eca.json b/oaitestdata/clarin-oai_dc/SET_1/json/88e1b8a1-44f3-5de0-bbcf-563925947eca.json
deleted file mode 100644
index d940a4b3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/88e1b8a1-44f3-5de0-bbcf-563925947eca.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/pdf"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/282",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/282"
-    ],
-    "PID": "http://hdl.handle.net/11321/282",
-    "PublicationTimestamp": "2016-04-25T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Oleksy, Marcin",
-        "Wieczorek, Jan",
-        "Marci\u0144czuk, Micha\u0142",
-        "Koco\u0144, Jan"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/282;2016-06-03T13:16:50Z;hdl_11321_3;hdl_11321_4;KPWr annotation guidelines - spatial expressions;Marci\u0144czuk, Micha\u0142;Oleksy, Marcin;Koco\u0144, Jan;Wieczorek, Jan;spatial expressions;annotation guidelines;corpora annotation;Spatial expressions annotation guidelines describing the process of manual annotation of documents in Polish Corpus of Wroc\u0142aw University of Technology (KPWr);2016-04-25;languageDescription;http://hdl.handle.net/11321/282;pol;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;application/pdf;downloadable_files_count: 1;Wroc\u0142aw University of Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "88e1b8a1-44f3-5de0-bbcf-563925947eca",
-    "notes": [
-        "Spatial expressions annotation guidelines describing the process of manual annotation of documents in Polish Corpus of Wroc\u0142aw University of Technology (KPWr)"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/282"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "spatial expressions"
-        },
-        {
-            "name": "annotation guidelines"
-        },
-        {
-            "name": "corpora annotation"
-        }
-    ],
-    "title": [
-        "KPWr annotation guidelines - spatial expressions"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/88fc571d-7689-57ec-b38b-1402efe73d3c.json b/oaitestdata/clarin-oai_dc/SET_1/json/88fc571d-7689-57ec-b38b-1402efe73d3c.json
deleted file mode 100644
index 7a54c6a0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/88fc571d-7689-57ec-b38b-1402efe73d3c.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)",
-        "Datahub"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-66",
-    "MetadataAccess": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-66"
-    ],
-    "PID": "http://hdl.handle.net/20.500.11752/ILC-66",
-    "PublicationTimestamp": "2016-10-18T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)",
-        "Datahub"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "author": [
-        "Bartolini, Roberto"
-    ],
-    "fulltext": "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-66;2018-07-23T09:13:44Z;hdl_000-c0-111_38;hdl_000-c0-111_49;IWN-LOD;Bartolini, Roberto;WordNet;Lexicon;Lexical Semantics;Risorse Lessicali;Linguistic Open Data;This is an RDF- Linguistic Open Data version of the ItalWordNet v.2 as created at the Institute of Computational Linguistics \\\"A. Zampolli\\\" in Pisa (http://hdl.handle.net/20.500.11752/ILC-62). \r\n\r\nThe resource has been created according to the WN2.0 specification, http://www.w3.org/2006/03/wn/wn20/;2016-10-18;lexicalConceptualResource;http://hdl.handle.net/20.500.11752/ILC-66;ita;downloadable_files_count: 0;Datahub;Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR);https://datahub.io/dataset/iwn",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "88fc571d-7689-57ec-b38b-1402efe73d3c",
-    "notes": [
-        "This is an RDF- Linguistic Open Data version of the ItalWordNet v.2 as created at the Institute of Computational Linguistics \\\"A. Zampolli\\\" in Pisa (http://hdl.handle.net/20.500.11752/ILC-62). \r\n\r\nThe resource has been created according to the WN2.0 specification, http://www.w3.org/2006/03/wn/wn20/"
-    ],
-    "oai_identifier": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-66"
-    ],
-    "oai_set": [
-        "hdl_000-c0-111_38",
-        "hdl_000-c0-111_49"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "WordNet"
-        },
-        {
-            "name": "Lexicon"
-        },
-        {
-            "name": "Lexical Semantics"
-        },
-        {
-            "name": "Risorse Lessicali"
-        },
-        {
-            "name": "Linguistic Open Data"
-        }
-    ],
-    "title": [
-        "IWN-LOD"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/88ff151e-4b00-5128-8b93-8b98d8511089.json b/oaitestdata/clarin-oai_dc/SET_1/json/88ff151e-4b00-5128-8b93-8b98d8511089.json
deleted file mode 100644
index ca234b2a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/88ff151e-4b00-5128-8b93-8b98d8511089.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Bolz, Norbert W."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 33 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0681",
-    "MetadataAccess": [
-        "oai:ota:oucs:0681"
-    ],
-    "PublicationTimestamp": "1592-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1592"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Greene, Robert, 1558?-1592"
-    ],
-    "fulltext": "oai:ota:oucs:0681;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0681.xml;A quip for an upstart courtier / by Robert Greene;Greene, Robert, 1558?-1592;1592;text_and_corpus_linguistics;English drama -- Early modern and Elizabethan, 1500-1600;eng;Oxford Text Archive, University of Oxford;Bolz, Norbert W.;(1 file : ca. 33 KB);Text;Plays;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "88ff151e-4b00-5128-8b93-8b98d8511089",
-    "oai_identifier": [
-        "oai:ota:oucs:0681"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- Early modern Elizabethan"
-        }
-    ],
-    "title": [
-        "A quip for an upstart courtier / by Robert Greene"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0681.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/890776d3-d0f2-5d4a-a1ba-0c81ea03c87e.json b/oaitestdata/clarin-oai_dc/SET_1/json/890776d3-d0f2-5d4a-a1ba-0c81ea03c87e.json
deleted file mode 100644
index ce01efc1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/890776d3-d0f2-5d4a-a1ba-0c81ea03c87e.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Lancaster University"
-    ],
-    "Contributor": [
-        "Short, Mick",
-        "Culpeper, Jonathan",
-        "Wynne, Martin",
-        "Semino, Elena"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-903",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-903"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-903",
-    "PublicationTimestamp": "1997-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1997"
-    ],
-    "Publisher": [
-        "Lancaster University"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-903;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Speech, Thought and Writing Presentation Corpus;Culpeper, Jonathan;Semino, Elena;Short, Mick;Wynne, Martin;A corpus of approximately 260,000 words of modern British narrative texts representing three text types (fiction, newpapers, biography) with detailed annotation for all forms of speech, thought and writing presentation which occur in the corpus. Available via OTA.;1997;corpus;http://hdl.handle.net/11372/LRT-903;eng;text/plain;downloadable_files_count: 0;United Kingdom;Lancaster University;http://www.ota.ox.ac.uk/headers/2540.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "890776d3-d0f2-5d4a-a1ba-0c81ea03c87e",
-    "notes": [
-        "A corpus of approximately 260,000 words of modern British narrative texts representing three text types (fiction, newpapers, biography) with detailed annotation for all forms of speech, thought and writing presentation which occur in the corpus. Available via OTA."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-903"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Speech, Thought and Writing Presentation Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/89282234-7d79-56c0-8db0-849c351efad4.json b/oaitestdata/clarin-oai_dc/SET_1/json/89282234-7d79-56c0-8db0-849c351efad4.json
deleted file mode 100644
index f668bc34..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/89282234-7d79-56c0-8db0-849c351efad4.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/9",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/9"
-    ],
-    "PID": "http://hdl.handle.net/11321/9",
-    "PublicationTimestamp": "2010-06-29T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Koco\u0144, Jan"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/9;2016-01-21T14:40:03Z;hdl_11321_3;hdl_11321_4;Corpus-SUCK;Koco\u0144, Jan;Proces przetwarzania umo\u017cliwia pobranie zawarto\u015bci serwis\u00f3w internetowych. Wej\u015bciem dla procesu jest lista adres\u00f3w URL, na wyj\u015bciu uzyskuje si\u0119 zbi\u00f3r plik\u00f3w zawieraj\u0105cych najbardziej istotn\u0105 zawarto\u015b\u0107 (tylko tekst, np. tre\u015b\u0107 artyku\u0142u, bez dodatkowych informacji na stronie) najbardziej istotnych podstron (tylko podstrony zawieraj\u0105ce tekst w odpowiedniej ilo\u015bci, bez zawarto\u015bci typu obrazy, filmy, itp.). Pliki pogrupowane s\u0105 wed\u0142ug \u017ar\u00f3d\u0142a - dla ka\u017cdego linku z wej\u015bciowej listy tworzony jest osobny katalog, w kt\u00f3rym znajduj\u0105 si\u0119 pliki. Ka\u017cdy plik jest osobn\u0105 podstron\u0105. Najbardziej istotna zawarto\u015b\u0107 jest poddana filtrowaniu (domy\u015blnie dokument powinien mie\u0107 min. 300 znak\u00f3w istotnych (nale\u017c\u0105cych do token\u00f3w) oraz min. 20% s\u0142\u00f3w musi by\u0107 znanych (znajdowa\u0107 si\u0119 w s\u0142owniku Morfeusz). Dokumenty po filtrowaniu s\u0105 tagowane przy pomocy narz\u0119dzia WCRFT;2010-06-29;toolService;http://hdl.handle.net/11321/9;pol;eng;downloadable_files_count: 0;Wroc\u0142aw University of Technology;http://nlp.pwr.wroc.pl/redmine/projects/corpora/wiki/Corpus-SUCK",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "89282234-7d79-56c0-8db0-849c351efad4",
-    "notes": [
-        "Proces przetwarzania umo\u017cliwia pobranie zawarto\u015bci serwis\u00f3w internetowych. Wej\u015bciem dla procesu jest lista adres\u00f3w URL, na wyj\u015bciu uzyskuje si\u0119 zbi\u00f3r plik\u00f3w zawieraj\u0105cych najbardziej istotn\u0105 zawarto\u015b\u0107 (tylko tekst, np. tre\u015b\u0107 artyku\u0142u, bez dodatkowych informacji na stronie) najbardziej istotnych podstron (tylko podstrony zawieraj\u0105ce tekst w odpowiedniej ilo\u015bci, bez zawarto\u015bci typu obrazy, filmy, itp.). Pliki pogrupowane s\u0105 wed\u0142ug \u017ar\u00f3d\u0142a - dla ka\u017cdego linku z wej\u015bciowej listy tworzony jest osobny katalog, w kt\u00f3rym znajduj\u0105 si\u0119 pliki. Ka\u017cdy plik jest osobn\u0105 podstron\u0105. Najbardziej istotna zawarto\u015b\u0107 jest poddana filtrowaniu (domy\u015blnie dokument powinien mie\u0107 min. 300 znak\u00f3w istotnych (nale\u017c\u0105cych do token\u00f3w) oraz min. 20% s\u0142\u00f3w musi by\u0107 znanych (znajdowa\u0107 si\u0119 w s\u0142owniku Morfeusz). Dokumenty po filtrowaniu s\u0105 tagowane przy pomocy narz\u0119dzia WCRFT"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/9"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus-SUCK"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/89291310-899b-5050-b9cb-f172e7650afa.json b/oaitestdata/clarin-oai_dc/SET_1/json/89291310-899b-5050-b9cb-f172e7650afa.json
deleted file mode 100644
index 169f264c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/89291310-899b-5050-b9cb-f172e7650afa.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4609",
-    "MetadataAccess": [
-        "oai:ota:oucs:4609"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gray, Thomas, 1716-1771."
-    ],
-    "fulltext": "oai:ota:oucs:4609;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4609.xml;Designs by Mr. R. Bentley, for six poems by Mr. T. Gray;Gray, Thomas, 1716-1771.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "89291310-899b-5050-b9cb-f172e7650afa",
-    "oai_identifier": [
-        "oai:ota:oucs:4609"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Designs by Mr. R. Bentley, for six poems by Mr. T. Gray"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4609.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/896902a8-4ee7-5285-b201-738459eabf1e.json b/oaitestdata/clarin-oai_dc/SET_1/json/896902a8-4ee7-5285-b201-738459eabf1e.json
deleted file mode 100644
index 9ec88a0f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/896902a8-4ee7-5285-b201-738459eabf1e.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "University of Silesia"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 20",
-        "text/plain; charset=utf-8",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/351",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/351"
-    ],
-    "PID": "http://hdl.handle.net/11321/351",
-    "PublicationTimestamp": "2017-04-25T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "University of Silesia"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Grzonka, Ma\u0142gorzata"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/351;2017-04-25T14:09:27Z;hdl_11321_3;hdl_11321_4;Gosia;Grzonka, Ma\u0142gorzata;corpus;Corpus;2017-04-25;corpus;http://hdl.handle.net/11321/351;pol;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;downloadable_files_count: 20;University of Silesia;http://www.us.edu.pl",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "896902a8-4ee7-5285-b201-738459eabf1e",
-    "notes": [
-        "Corpus"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/351"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        }
-    ],
-    "title": [
-        "Gosia"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/89881d91-5b04-5f50-95f5-67dcef3a3ee5.json b/oaitestdata/clarin-oai_dc/SET_1/json/89881d91-5b04-5f50-95f5-67dcef3a3ee5.json
deleted file mode 100644
index 7ed7a61b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/89881d91-5b04-5f50-95f5-67dcef3a3ee5.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=12f708b66ec611e2a2aa782bcb074135b5eea2fc589f44f7b46af04876b6280a",
-    "MetadataAccess": [
-        "12f708b66ec611e2a2aa782bcb074135b5eea2fc589f44f7b46af04876b6280a"
-    ],
-    "PublicationTimestamp": "2013-02-04T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "12f708b66ec611e2a2aa782bcb074135b5eea2fc589f44f7b46af04876b6280a;2018-11-15T16:40:12Z;toolService;toolService:tool;U-Compare/UIMA speech annotation viewer;This is a UIMA component that provides a visualization of speech based output from UIMA workflows. It has been developed at the University of Manchester, using libraries of the Java Speech Toollkit (jstk). It has been designed specifically for use with the U-Compare text mining workbench (see separate META-SHARE record). It provides waveform, power and spectrogram plots. It also shows the location of individual spoken words, if this information is available in the output of the workflow.;2013-02-04",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "89881d91-5b04-5f50-95f5-67dcef3a3ee5",
-    "notes": [
-        "This is a UIMA component that provides a visualization of speech based output from UIMA workflows. It has been developed at the University of Manchester, using libraries of the Java Speech Toollkit (jstk). It has been designed specifically for use with the U-Compare text mining workbench (see separate META-SHARE record). It provides waveform, power and spectrogram plots. It also shows the location of individual spoken words, if this information is available in the output of the workflow."
-    ],
-    "oai_identifier": [
-        "12f708b66ec611e2a2aa782bcb074135b5eea2fc589f44f7b46af04876b6280a"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "U-Compare/UIMA speech annotation viewer"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8992f6e6-230b-5009-8170-90ace82beeea.json b/oaitestdata/clarin-oai_dc/SET_1/json/8992f6e6-230b-5009-8170-90ace82beeea.json
deleted file mode 100644
index 5e4ad1ed..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8992f6e6-230b-5009-8170-90ace82beeea.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Institut f\u00fcr Deutsche Sprache"
-    ],
-    "Contributor": [
-        "Hartung, Martin"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-545",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-545"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-545",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut f\u00fcr Deutsche Sprache"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-545;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Gespr\u00e4chanalytisches Informationssystem (GAIS);Hartung, Martin;web-based information system on scientific community (news, events, persons, job market, mailing list, database on research projects and corpora, bibliography, glossary and links) and recording equipment/software; disciplinary scope: research on conversation and discourse analysis and spoken language;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-545;deu;downloadable_files_count: 0;Germany;Institut f\u00fcr Deutsche Sprache;http://gais.ids-mannheim.de/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8992f6e6-230b-5009-8170-90ace82beeea",
-    "notes": [
-        "web-based information system on scientific community (news, events, persons, job market, mailing list, database on research projects and corpora, bibliography, glossary and links) and recording equipment/software; disciplinary scope: research on conversation and discourse analysis and spoken language"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-545"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Gespr\u00e4chanalytisches Informationssystem (GAIS)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/89c69082-8213-5275-8980-d6dbb62bdc61.json b/oaitestdata/clarin-oai_dc/SET_1/json/89c69082-8213-5275-8980-d6dbb62bdc61.json
deleted file mode 100644
index 0ac9bc02..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/89c69082-8213-5275-8980-d6dbb62bdc61.json
+++ /dev/null
@@ -1,102 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 7",
-        "application/pdf",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1123",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1123"
-    ],
-    "PID": "http://hdl.handle.net/11356/1123",
-    "PublicationTimestamp": "2017-05-14T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "http://nl.ijs.si/janes/viri/rocno-oznaceni-korpusi/#Janes-Tag",
-        "https://doi.org/10.1007/s10579-018-9425-z",
-        "http://hdl.handle.net/11356/1085"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "https://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Ljube\u0161i\u0107, Nikola",
-        "Fi\u0161er, Darja",
-        "Erjavec, Toma\u017e",
-        "Arhar Holdt, \u0160pela",
-        "\u010cibej, Jaka",
-        "Zupan, Katja"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1123;2019-01-22T18:44:57Z;hdl_11356_1023;hdl_11356_1024;CMC training corpus Janes-Tag 2.0;Erjavec, Toma\u017e;Fi\u0161er, Darja;\u010cibej, Jaka;Arhar Holdt, \u0160pela;Ljube\u0161i\u0107, Nikola;Zupan, Katja;computer-mediated communication;tokenisation;word normalisation;tagging;lemmatisation;manual annotation;TEI;named entities;Janes-Tag is a manually annotated corpus of Slovene Computer-Mediated Communication (CMC). It is meant as a gold-standard training and testing dataset for tokenisation, sentence segmentation, word normalisation, morphosyntactic tagging, lemmatisation and named entity annotation of non-standard Slovene. As the corpus has been carefully manually annotated, it is also suitable for detailed linguistic explorations which require highly accurate and reliable annotations. As an update to version 1.2, 2.0 corrects some minor errors and includes named entity annotation. \r\n\r\nA slightly older version of this corpus is described in:\r\nERJAVEC, Toma\u017e, \u010cIBEJ, Jaka, ARHAR HOLDT, \u0160pela, LJUBE\u0160I\u0106, Nikola, FI\u0160ER, Darja. Gold-standard datasets for annotation of Slovene computer-mediated communication. In Proceedings of RASLAN 2016: Recent Advances in Slavonic Natural Language Processing. Brno: Tribun EU, 2016, pp. 29-40, https://nlp.fi.muni.cz/raslan/raslan16.pdf\r\n\r\nNote that a related corpus, Janes-Norm is also available, cf. http://hdl.handle.net/11356/1084.;2017-05-14;corpus;http://hdl.handle.net/11356/1123;slv;http://nl.ijs.si/janes/viri/rocno-oznaceni-korpusi/#Janes-Tag;https://doi.org/10.1007/s10579-018-9425-z;http://hdl.handle.net/11356/1085;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);https://creativecommons.org/licenses/by-sa/4.0/;PUB;application/zip;application/zip;application/zip;application/pdf;application/pdf;application/pdf;application/pdf;text/plain; charset=utf-8;downloadable_files_count: 7;Jo\u017eef Stefan Institute;http://nl.ijs.si/janes/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "89c69082-8213-5275-8980-d6dbb62bdc61",
-    "notes": [
-        "Janes-Tag is a manually annotated corpus of Slovene Computer-Mediated Communication (CMC). It is meant as a gold-standard training and testing dataset for tokenisation, sentence segmentation, word normalisation, morphosyntactic tagging, lemmatisation and named entity annotation of non-standard Slovene. As the corpus has been carefully manually annotated, it is also suitable for detailed linguistic explorations which require highly accurate and reliable annotations. As an update to version 1.2, 2.0 corrects some minor errors and includes named entity annotation. \r\n\r\nA slightly older version of this corpus is described in:\r\nERJAVEC, Toma\u017e, \u010cIBEJ, Jaka, ARHAR HOLDT, \u0160pela, LJUBE\u0160I\u0106, Nikola, FI\u0160ER, Darja. Gold-standard datasets for annotation of Slovene computer-mediated communication. In Proceedings of RASLAN 2016: Recent Advances in Slavonic Natural Language Processing. Brno: Tribun EU, 2016, pp. 29-40, https://nlp.fi.muni.cz/raslan/raslan16.pdf\r\n\r\nNote that a related corpus, Janes-Norm is also available, cf. http://hdl.handle.net/11356/1084."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1123"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "computer-mediated communication"
-        },
-        {
-            "name": "tokenisation"
-        },
-        {
-            "name": "word normalisation"
-        },
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "lemmatisation"
-        },
-        {
-            "name": "manual annotation"
-        },
-        {
-            "name": "TEI"
-        },
-        {
-            "name": "named entities"
-        }
-    ],
-    "title": [
-        "CMC training corpus Janes-Tag 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/89c789e7-02e0-579e-85d3-7ce9aecca87c.json b/oaitestdata/clarin-oai_dc/SET_1/json/89c789e7-02e0-579e-85d3-7ce9aecca87c.json
deleted file mode 100644
index 6b6911d6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/89c789e7-02e0-579e-85d3-7ce9aecca87c.json
+++ /dev/null
@@ -1,49 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5433",
-    "MetadataAccess": [
-        "oai:ota:oucs:5433"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:5433;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5433.xml;The Banb---y apes: or, the monkeys chattering to the magpye. In a letter to a friend in London;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "89c789e7-02e0-579e-85d3-7ce9aecca87c",
-    "oai_identifier": [
-        "oai:ota:oucs:5433"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The Banb---y apes: or, the monkeys chattering to the magpye. In a letter to a friend in London"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5433.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8a161fe8-2b76-5b8c-b4bc-816f97185475.json b/oaitestdata/clarin-oai_dc/SET_1/json/8a161fe8-2b76-5b8c-b4bc-816f97185475.json
deleted file mode 100644
index d6eee77f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8a161fe8-2b76-5b8c-b4bc-816f97185475.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(2 files : ca. 46.8, 45.4 KB)"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2256",
-    "MetadataAccess": [
-        "oai:ota:oucs:2256"
-    ],
-    "PublicationTimestamp": "1978-04-27T11:59:59Z",
-    "PublicationYear": [
-        "1978"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Aeschylus"
-    ],
-    "fulltext": "oai:ota:oucs:2256;2018-07-27T14:11:30Z;http://ota.ox.ac.uk/headers/2256.xml;The Choeforoi of Aeschylus;Aeschylus;1978-04-27;text_and_corpus_linguistics;Plays -- Greece -- B.C.;Tragedies -- Greece -- B.C.;grc;Oxford Text Archive, University of Oxford;(2 files : ca. 46.8, 45.4 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8a161fe8-2b76-5b8c-b4bc-816f97185475",
-    "oai_identifier": [
-        "oai:ota:oucs:2256"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- Greece -- B.C."
-        },
-        {
-            "name": "Tragedies -- Greece -- B.C."
-        }
-    ],
-    "title": [
-        "The Choeforoi of Aeschylus"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2256.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8a1d6899-ffc0-58cf-94a1-691148333eea.json b/oaitestdata/clarin-oai_dc/SET_1/json/8a1d6899-ffc0-58cf-94a1-691148333eea.json
deleted file mode 100644
index 37fdf140..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8a1d6899-ffc0-58cf-94a1-691148333eea.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5393",
-    "MetadataAccess": [
-        "oai:ota:oucs:5393"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pennant, Thomas, 1726-1798."
-    ],
-    "fulltext": "oai:ota:oucs:5393;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5393.xml;British zoology: ... [pt.3];Pennant, Thomas, 1726-1798.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8a1d6899-ffc0-58cf-94a1-691148333eea",
-    "oai_identifier": [
-        "oai:ota:oucs:5393"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "British zoology: ... [pt.3]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5393.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8a215814-a0fc-5ae0-a6de-2f2f2af68c46.json b/oaitestdata/clarin-oai_dc/SET_1/json/8a215814-a0fc-5ae0-a6de-2f2f2af68c46.json
deleted file mode 100644
index f30e1d17..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8a215814-a0fc-5ae0-a6de-2f2f2af68c46.json
+++ /dev/null
@@ -1,89 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 4",
-        "application/pdf",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1083",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1083"
-    ],
-    "PID": "http://hdl.handle.net/11356/1083",
-    "PublicationTimestamp": "2016-12-28T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11356/1084"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by-sa/4.0/"
-    ],
-    "author": [
-        "\u010cibej, Jaka",
-        "Erjavec, Toma\u017e",
-        "Fi\u0161er, Darja",
-        "Arhar Holdt, \u0160pela"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1083;2018-10-18T23:01:44Z;hdl_11356_1023;hdl_11356_1024;CMC training corpus Janes-Norm 1.1;Erjavec, Toma\u017e;Fi\u0161er, Darja;\u010cibej, Jaka;Arhar Holdt, \u0160pela;computer-mediated communication;tokenisation;word normalisation;manual annotation;TEI;Janes-Norm is a manually annotated corpus of Slovene Computer-Mediated Communication (CMC). It is meant as a gold-standard training and testing dataset for tokenisation, sentence segmentation and word normalisation of non-standard Slovene. The corpus is also automatically annotated with morphosyntactic descriptions and lemmas. As the corpus has been carefully manually annotated, it is also suitable for detailed linguistic explorations which require highly accurate and reliable annotations.\r\n\r\nThe corpus is further described in:\r\nERJAVEC, Toma\u017e, \u010cIBEJ, Jaka, ARHAR HOLDT, \u0160pela, LJUBE\u0160I\u0106, Nikola, FI\u0160ER, Darja. Gold-standard datasets for annotation of Slovene computer-mediated communication. In Proceedings of RASLAN 2016: Recent Advances in Slavonic Natural Language Processing. Brno: Tribun EU, 2016, pp. 29-40, https://nlp.fi.muni.cz/raslan/raslan16.pdf\r\n\r\nNote that a related corpus, Janes-Tag is also available, cf. http://hdl.handle.net/11356/1081.;2016-12-28;corpus;http://hdl.handle.net/11356/1083;slv;http://hdl.handle.net/11356/1084;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);PUB;https://creativecommons.org/licenses/by-sa/4.0/;application/pdf;application/pdf;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 4;Jo\u017eef Stefan Institute;http://nl.ijs.si/janes/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8a215814-a0fc-5ae0-a6de-2f2f2af68c46",
-    "notes": [
-        "Janes-Norm is a manually annotated corpus of Slovene Computer-Mediated Communication (CMC). It is meant as a gold-standard training and testing dataset for tokenisation, sentence segmentation and word normalisation of non-standard Slovene. The corpus is also automatically annotated with morphosyntactic descriptions and lemmas. As the corpus has been carefully manually annotated, it is also suitable for detailed linguistic explorations which require highly accurate and reliable annotations.\r\n\r\nThe corpus is further described in:\r\nERJAVEC, Toma\u017e, \u010cIBEJ, Jaka, ARHAR HOLDT, \u0160pela, LJUBE\u0160I\u0106, Nikola, FI\u0160ER, Darja. Gold-standard datasets for annotation of Slovene computer-mediated communication. In Proceedings of RASLAN 2016: Recent Advances in Slavonic Natural Language Processing. Brno: Tribun EU, 2016, pp. 29-40, https://nlp.fi.muni.cz/raslan/raslan16.pdf\r\n\r\nNote that a related corpus, Janes-Tag is also available, cf. http://hdl.handle.net/11356/1081."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1083"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "computer-mediated communication"
-        },
-        {
-            "name": "tokenisation"
-        },
-        {
-            "name": "word normalisation"
-        },
-        {
-            "name": "manual annotation"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "CMC training corpus Janes-Norm 1.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8a3415b9-45ef-5117-99d9-dd36af32266c.json b/oaitestdata/clarin-oai_dc/SET_1/json/8a3415b9-45ef-5117-99d9-dd36af32266c.json
deleted file mode 100644
index 8c9c6868..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8a3415b9-45ef-5117-99d9-dd36af32266c.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=3bb941bc1c5811e2a2aa782bcb074135e44516c278e14d6ab091e2f8a36ffffc",
-    "MetadataAccess": [
-        "3bb941bc1c5811e2a2aa782bcb074135e44516c278e14d6ab091e2f8a36ffffc"
-    ],
-    "PublicationTimestamp": "2012-10-22T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "fulltext": "3bb941bc1c5811e2a2aa782bcb074135e44516c278e14d6ab091e2f8a36ffffc;2018-11-15T16:39:44Z;toolService;toolService:tool;Lemmatizer for Portuguese;Based on the MXPOST part of speech tagger and UNITEX dictionaries for Portuguese, this tool produces the lemmas of the words of a text stored in a plain text file. The source code is also provided. ;2012-10-22",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8a3415b9-45ef-5117-99d9-dd36af32266c",
-    "notes": [
-        "Based on the MXPOST part of speech tagger and UNITEX dictionaries for Portuguese, this tool produces the lemmas of the words of a text stored in a plain text file. The source code is also provided. "
-    ],
-    "oai_identifier": [
-        "3bb941bc1c5811e2a2aa782bcb074135e44516c278e14d6ab091e2f8a36ffffc"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "Lemmatizer for Portuguese"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8a59e66a-68a5-53b6-a61a-b5f9cbeb4d22.json b/oaitestdata/clarin-oai_dc/SET_1/json/8a59e66a-68a5-53b6-a61a-b5f9cbeb4d22.json
deleted file mode 100644
index 5cc8f3d6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8a59e66a-68a5-53b6-a61a-b5f9cbeb4d22.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "The National Library of Sweden"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/90",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/90"
-    ],
-    "PID": "http://hdl.handle.net/10794/90",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "The National Library of Sweden"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/90;2017-10-25T14:34:53Z;hdl_10794_1;hdl_10794_2;Blekingsposten 1870's (2015-04-08);Blekingsposten 1870-talet (2015-04-08);n/a, n/a;Swedish;News;A corpus with texts from Blekingeposten 1870\u20131879.;En korpus med texter fr\u00e5n Blekingeposten p\u00e5 1870-talet (1870\u20131879).;2015-04-08;corpus;http://hdl.handle.net/10794/90;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;The National Library of Sweden;https://spraakbanken.gu.se/swe/resurs/kubhist-blekingsposten-1870",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8a59e66a-68a5-53b6-a61a-b5f9cbeb4d22",
-    "notes": [
-        "A corpus with texts from Blekingeposten 1870\u20131879.",
-        "En korpus med texter fr\u00e5n Blekingeposten p\u00e5 1870-talet (1870\u20131879)."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/90"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "News"
-        }
-    ],
-    "title": [
-        "Blekingsposten 1870's (2015-04-08)",
-        "Blekingsposten 1870-talet (2015-04-08)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8a78a6ae-d384-5864-9117-715637841641.json b/oaitestdata/clarin-oai_dc/SET_1/json/8a78a6ae-d384-5864-9117-715637841641.json
deleted file mode 100644
index c7f95ab6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8a78a6ae-d384-5864-9117-715637841641.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4654",
-    "MetadataAccess": [
-        "oai:ota:oucs:4654"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Paley, William, 1743-1805."
-    ],
-    "fulltext": "oai:ota:oucs:4654;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4654.xml;Hor\u00c3\u00a6 Paulin\u00c3\u00a6: or the truth of the scripture history of St. Paul evinced, ... By William Paley, ...;Paley, William, 1743-1805.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8a78a6ae-d384-5864-9117-715637841641",
-    "oai_identifier": [
-        "oai:ota:oucs:4654"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Hor\u00c3\u00a6 Paulin\u00c3\u00a6: or the truth of the scripture history of St. Paul evinced, ... By William Paley, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4654.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8a7e0c8a-798a-521d-ae02-34ceae336b45.json b/oaitestdata/clarin-oai_dc/SET_1/json/8a7e0c8a-798a-521d-ae02-34ceae336b45.json
deleted file mode 100644
index 352191b9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8a7e0c8a-798a-521d-ae02-34ceae336b45.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1422",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1422"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1422",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1422;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Cercador OBNEO;Search engine of the BOBNEO data bank, a database of neologisms present in the mass media in Spanish and Catalan, written and oral, from 1992.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1422;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra;http://obneo.iula.upf.edu/bobneo/index.php",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8a7e0c8a-798a-521d-ae02-34ceae336b45",
-    "notes": [
-        "Search engine of the BOBNEO data bank, a database of neologisms present in the mass media in Spanish and Catalan, written and oral, from 1992."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1422"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Cercador OBNEO"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8a7ee688-e9ef-5fd5-b293-a1f6a7da8fbf.json b/oaitestdata/clarin-oai_dc/SET_1/json/8a7ee688-e9ef-5fd5-b293-a1f6a7da8fbf.json
deleted file mode 100644
index deaa4eeb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8a7ee688-e9ef-5fd5-b293-a1f6a7da8fbf.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3995",
-    "MetadataAccess": [
-        "oai:ota:oucs:3995"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "More, Hannah, 1745-1833."
-    ],
-    "fulltext": "oai:ota:oucs:3995;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3995.xml;The history of idle Jack Brown: ... being the third part of The two shoemakers.;Two shoemakers.;More, Hannah, 1745-1833.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8a7ee688-e9ef-5fd5-b293-a1f6a7da8fbf",
-    "oai_identifier": [
-        "oai:ota:oucs:3995"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The history of idle Jack Brown: ... being the third part of The two shoemakers.",
-        "Two shoemakers."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3995.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8aa3d6e0-45e7-5835-9316-6267aacbe603.json b/oaitestdata/clarin-oai_dc/SET_1/json/8aa3d6e0-45e7-5835-9316-6267aacbe603.json
deleted file mode 100644
index 48ecda75..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8aa3d6e0-45e7-5835-9316-6267aacbe603.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Research Institute for the Languages of Finland"
-    ],
-    "Contributor": [
-        "Torikka, Marja",
-        "Vihtari, Jari"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-833",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-833"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-833",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Research Institute for the Languages of Finland"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-833;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Digital Listing of Headwors in the Dictionary of Carelian (= Karjalan kielen sanakirja 1-6, 1968-2005);Vihtari, Jari;Torikka, Marja;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-833;downloadable_files_count: 0;Research Institute for the Languages of Finland;http://kaino.kotus.fi/sanat/kkss/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8aa3d6e0-45e7-5835-9316-6267aacbe603",
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-833"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Digital Listing of Headwors in the Dictionary of Carelian (= Karjalan kielen sanakirja 1-6, 1968-2005)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8aaf4039-2d19-5553-a88b-2dcdedcfe3f8.json b/oaitestdata/clarin-oai_dc/SET_1/json/8aaf4039-2d19-5553-a88b-2dcdedcfe3f8.json
deleted file mode 100644
index defa2b04..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8aaf4039-2d19-5553-a88b-2dcdedcfe3f8.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "W Drukarni J. K M\u0107i y Rzpltey u XX Scholarum Piarum"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-8919",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-8919"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D3E-2",
-    "PublicationTimestamp": "1760-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1760"
-    ],
-    "Publisher": [
-        "W Drukarni J. K M\u0107i y Rzpltey u XX Scholarum Piarum"
-    ],
-    "RelatedIdentifier": [
-        "http://www.pbc.rzeszow.pl/Content/8919",
-        "oai:www.pbc.rzeszow.pl:publication:9656"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "author": [
-        "Konarski, Stanis\u0142aw (1700-1773)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-8919;2019-03-01T17:50:56Z;O skutecznym rad sposobie albo O utrzymywaniu ordynaryinych seym\u00f3w;Konarski, Stanis\u0142aw (1700-1773);sejm - 14-18 w.;Polska - polityka - 14-18 w.;stare druki;W Drukarni J. K M\u0107i y Rzpltey u XX Scholarum Piarum;1760;starodruk;application/xml;clarind-uds:poldilemma-8919;hdl:11858/00-246C-0000-0023-8D3E-2;Sygnatura orygina\u0142u: Cz 5/St;pol;lat;http://www.pbc.rzeszow.pl/Content/8919;oai:www.pbc.rzeszow.pl:publication:9656;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8aaf4039-2d19-5553-a88b-2dcdedcfe3f8",
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-8919"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "sejm - - w."
-        },
-        {
-            "name": "Polska - polityka - - w."
-        },
-        {
-            "name": "stare druki"
-        }
-    ],
-    "title": [
-        "O skutecznym rad sposobie albo O utrzymywaniu ordynaryinych seym\u00f3w"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8ad034ff-3af5-56a4-bf8e-212c8a405d14.json b/oaitestdata/clarin-oai_dc/SET_1/json/8ad034ff-3af5-56a4-bf8e-212c8a405d14.json
deleted file mode 100644
index c978898b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8ad034ff-3af5-56a4-bf8e-212c8a405d14.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Abu-MaTran project"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/xml",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "English",
-        "Croatian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1049",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1049"
-    ],
-    "PID": "http://hdl.handle.net/11356/1049",
-    "PublicationTimestamp": "2016-01-28T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Abu-MaTran project"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/324414"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN.SI User Licence for Internet Corpora",
-        "ACA",
-        "http://www.clarin.si/info/wp-content/uploads/2016/01/CLARIN.SI-WAC-2016-01.pdf"
-    ],
-    "author": [
-        "Espl\u00e0-Gomis, Miquel",
-        "Papavassiliou, Vassilis",
-        "Way, Andy",
-        "Ljube\u0161i\u0107, Nikola",
-        "Toral, Antonio",
-        "Prokopidis, Prokopis",
-        "Klubi\u010dka, Filip",
-        "Rubino, Raphael"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1049;2018-10-29T12:15:54Z;hdl_11356_1023;hdl_11356_1024;Tourism English-Croatian Parallel Corpus 2.0;Toral, Antonio;Espl\u00e0-Gomis, Miquel;Klubi\u010dka, Filip;Ljube\u0161i\u0107, Nikola;Papavassiliou, Vassilis;Prokopidis, Prokopis;Rubino, Raphael;Way, Andy;parallel corpus;tourism;multilingual;Sentence aligned parallel corpus built by automatically crawling 25 websites from the tourism domain.;2016-01-28;corpus;http://hdl.handle.net/11356/1049;eng;hrv;info:eu-repo/grantAgreement/EC/FP7/324414;CLARIN.SI User Licence for Internet Corpora;ACA;http://www.clarin.si/info/wp-content/uploads/2016/01/CLARIN.SI-WAC-2016-01.pdf;text/xml;text/plain; charset=utf-8;downloadable_files_count: 1;Abu-MaTran project;http://www.abumatran.eu",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8ad034ff-3af5-56a4-bf8e-212c8a405d14",
-    "notes": [
-        "Sentence aligned parallel corpus built by automatically crawling 25 websites from the tourism domain."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1049"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parallel corpus"
-        },
-        {
-            "name": "tourism"
-        },
-        {
-            "name": "multilingual"
-        }
-    ],
-    "title": [
-        "Tourism English-Croatian Parallel Corpus 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8ad38d9e-2a6d-518a-aa87-c424bc51e857.json b/oaitestdata/clarin-oai_dc/SET_1/json/8ad38d9e-2a6d-518a-aa87-c424bc51e857.json
deleted file mode 100644
index 5e947df8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8ad38d9e-2a6d-518a-aa87-c424bc51e857.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Fondazione Bruno Kessler, Trento, Italy"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "German",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1967",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1967"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1967",
-    "PublicationTimestamp": "2017-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Fondazione Bruno Kessler, Trento, Italy"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "AGREEMENT ON THE USE OF DATA IN QT21 APE Task",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21",
-        "PUB"
-    ],
-    "author": [
-        "Turchi, Marco",
-        "Chatterjee, Rajen",
-        "Negri, Matteo"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1967;2017-09-04T10:30:19Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;WMT17 De-En APE Shared Task Data;Turchi, Marco;Chatterjee, Rajen;Negri, Matteo;machine translation;shared task;automatic post-editing;post-editing;Training and development data for the WMT 2017 Automatic post-editing task  (the same used for the Sentence-level Quality Estimation task). They consist in German-English triplets (source, target and post-edit) belonging to the pharmacological domain and already tokenized. Training and development respectively contain 25,000 and 1,000 triplets. All data is provided by the EU project QT21 (http://www.qt21.eu/).;2017-02-15;corpus;http://hdl.handle.net/11372/LRT-1967;deu;eng;AGREEMENT ON THE USE OF DATA IN QT21 APE Task;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Fondazione Bruno Kessler, Trento, Italy;http://www.statmt.org/wmt17/ape-task.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8ad38d9e-2a6d-518a-aa87-c424bc51e857",
-    "notes": [
-        "Training and development data for the WMT 2017 Automatic post-editing task  (the same used for the Sentence-level Quality Estimation task). They consist in German-English triplets (source, target and post-edit) belonging to the pharmacological domain and already tokenized. Training and development respectively contain 25,000 and 1,000 triplets. All data is provided by the EU project QT21 (http://www.qt21.eu/)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1967"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "shared task"
-        },
-        {
-            "name": "automatic post-editing"
-        },
-        {
-            "name": "post-editing"
-        }
-    ],
-    "title": [
-        "WMT17 De-En APE Shared Task Data"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8ae200cb-0ee4-5c6b-bfd8-65471aede6b3.json b/oaitestdata/clarin-oai_dc/SET_1/json/8ae200cb-0ee4-5c6b-bfd8-65471aede6b3.json
deleted file mode 100644
index 0203f670..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8ae200cb-0ee4-5c6b-bfd8-65471aede6b3.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1142",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1142"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1142",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1142;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;DWDS-W\u00f6rterbuch;Germanistik;setzt sich zusammen aus dem Deutschen W\u00f6rterbuch, dem W\u00f6rterbuch der Deutschen Gegenwartssprache (WDG) sowie dem Etymologischen W\u00f6rterbuch des Deutschen (EtymWb);2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1142;deu;downloadable_files_count: 0;Germany;http://www.dwds.de/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8ae200cb-0ee4-5c6b-bfd8-65471aede6b3",
-    "notes": [
-        "setzt sich zusammen aus dem Deutschen W\u00f6rterbuch, dem W\u00f6rterbuch der Deutschen Gegenwartssprache (WDG) sowie dem Etymologischen W\u00f6rterbuch des Deutschen (EtymWb)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1142"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "DWDS-W\u00f6rterbuch"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8aeeec66-7ad9-5ff4-ac2f-3c9d69710bad.json b/oaitestdata/clarin-oai_dc/SET_1/json/8aeeec66-7ad9-5ff4-ac2f-3c9d69710bad.json
deleted file mode 100644
index f8cac9ce..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8aeeec66-7ad9-5ff4-ac2f-3c9d69710bad.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "Georgian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-955",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-955"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-955",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-955;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Middle Georgian;ca. 1.000.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-955;kat;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#georgmed",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8aeeec66-7ad9-5ff4-ac2f-3c9d69710bad",
-    "notes": [
-        "ca. 1.000.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-955"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Middle Georgian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8af1a524-cd78-5796-b2ad-465e6a2d661d.json b/oaitestdata/clarin-oai_dc/SET_1/json/8af1a524-cd78-5796-b2ad-465e6a2d661d.json
deleted file mode 100644
index 8f112088..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8af1a524-cd78-5796-b2ad-465e6a2d661d.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Andrzeja Piotrkowczyka"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-105641",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-105641"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CD3-9",
-    "PublicationTimestamp": "1625-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1625"
-    ],
-    "Publisher": [
-        "Drukarnia Andrzeja Piotrkowczyka"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/105641",
-        "oai:jbc.bj.uj.edu.pl:publication:112986"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1601/1700"
-    ],
-    "TempCoverageBegin": 50506804799,
-    "TempCoverageEnd": 50506804799,
-    "TemporalCoverage": " point in time : 1601-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1601-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1601-07-01T11:59:59Z",
-    "author": [
-        "Radawiecki, Andrzej ( -1634)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-105641;2019-02-28T17:51:03Z;Prawy Szlachcic, w Kazaniu Na Pogrzebie [...] Andrzeia ze Zmigroda Stadnickiego w osobie iego vkazany we Zmigrodzie dnia 23 Wrze\u015bnia Roku [...] 1614;Radawiecki, Andrzej ( -1634);starodruki 17\u00a0w.;Stadnicki, Adam (ca 1563-1615). Adr. ded.;Drukarnia Andrzeja Piotrkowczyka;1625;starodruk;application/xml;clarind-uds:poldilemma-105641;hdl:11858/00-246C-0000-0023-8CD3-9;Biblioteka Jagiello\u0144ska, BJ St. Dr.\u00a027071 I;pol;http://jbc.bj.uj.edu.pl/Content/105641;oai:jbc.bj.uj.edu.pl:publication:112986;1601/1700;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8af1a524-cd78-5796-b2ad-465e6a2d661d",
-    "notes": [
-        "Stadnicki, Adam (ca 1563-1615). Adr. ded."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-105641"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Prawy Szlachcic, w Kazaniu Na Pogrzebie [...] Andrzeia ze Zmigroda Stadnickiego w osobie iego vkazany we Zmigrodzie dnia 23 Wrze\u015bnia Roku [...] 1614"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8b232a7f-b149-554d-a064-739895143555.json b/oaitestdata/clarin-oai_dc/SET_1/json/8b232a7f-b149-554d-a064-739895143555.json
deleted file mode 100644
index 379f59d8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8b232a7f-b149-554d-a064-739895143555.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 110 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2217",
-    "MetadataAccess": [
-        "oai:ota:oucs:2217"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Protest literature"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "L'Estrange, Roger, Sir, 1616-1704"
-    ],
-    "fulltext": "oai:ota:oucs:2217;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/2217.xml;The Observator : [Selections] / Sir Roger L'Estrange;L'Estrange, Roger, Sir, 1616-1704;text_and_corpus_linguistics;Great Britain -- Politics and government -- 1660-1688;Oxford Text Archive, University of Oxford;Triggs, Jeffery;text/sgml;(1 file : ca. 110 KB);Text;Protest literature;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8b232a7f-b149-554d-a064-739895143555",
-    "oai_identifier": [
-        "oai:ota:oucs:2217"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Great Britain -- Politics government -- -"
-        }
-    ],
-    "title": [
-        "The Observator : [Selections] / Sir Roger L'Estrange"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2217.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8b3691c2-7c2b-5cc3-b9f7-12f9547eb367.json b/oaitestdata/clarin-oai_dc/SET_1/json/8b3691c2-7c2b-5cc3-b9f7-12f9547eb367.json
deleted file mode 100644
index 37709439..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8b3691c2-7c2b-5cc3-b9f7-12f9547eb367.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 3",
-        "text/plain"
-    ],
-    "Language": [
-        "Hindi",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-625F-0",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-625F-0"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-625F-0",
-    "PublicationTimestamp": "2014-03-21T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11858/00-097C-0000-0001-BD17-1"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Bojar, Ond\u0159ej",
-        "Tamchyna, Ale\u0161",
-        "Diatka, Vojt\u011bch",
-        "Zeman, Daniel",
-        "Stra\u0148\u00e1k, Pavel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-625F-0;2018-10-29T14:26:27Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;HindEnCorp 0.5;Bojar, Ond\u0159ej;Diatka, Vojt\u011bch;Stra\u0148\u00e1k, Pavel;Tamchyna, Ale\u0161;Zeman, Daniel;parallel corpus;English-Hindi parallel corpus;sentence-parallel;HindEnCorp parallel texts (sentence-aligned) come from the following sources:\r\nTides, which contains 50K sentence pairs taken mainly from news articles. This dataset was originally col- lected for the DARPA-TIDES surprise-language con- test in 2002, later refined at IIIT Hyderabad and provided for the NLP Tools Contest at ICON 2008 (Venkatapathy, 2008).\r\n\r\nCommentaries by Daniel Pipes contain 322 articles in English written by a journalist Daniel Pipes and translated into Hindi.\r\n\r\nEMILLE. This corpus (Baker et al., 2002) consists of three components: monolingual, parallel and annotated corpora. There are fourteen monolingual sub- corpora, including both written and (for some lan- guages) spoken data for fourteen South Asian lan- guages. The EMILLE monolingual corpora contain in total 92,799,000 words (including 2,627,000 words of transcribed spoken data for Bengali, Gujarati, Hindi, Punjabi and Urdu). The parallel corpus consists of 200,000 words of text in English and its accompanying translations into Hindi and other languages.\r\n\r\nSmaller datasets as collected by Bojar et al. (2010) include the corpus used at ACL 2005 (a subcorpus of EMILLE), a corpus of named entities from Wikipedia (crawled in 2009), and Agriculture domain parallel corpus.\r\n\ufffc\r\nFor the current release, we are extending the parallel corpus using these sources:\r\nIntercorp (\u010cerm\u00e1k and Rosen,2012) is a large multilingual parallel corpus of 32 languages including Hindi. The central language used for alignment is Czech. Intercorp\u2019s core texts amount to 202 million words. These core texts are most suitable for us because their sentence alignment is manually checked and therefore very reliable. They cover predominately short sto- ries and novels. There are seven Hindi texts in Inter- corp. Unfortunately, only for three of them the English translation is available; the other four are aligned only with Czech texts. The Hindi subcorpus of Intercorp contains 118,000 words in Hindi.\r\n\r\nTED talks 3 held in various languages, primarily English, are equipped with transcripts and these are translated into 102 languages. There are 179 talks for which Hindi translation is available.\r\n\r\nThe Indic multi-parallel corpus (Birch et al., 2011; Post et al., 2012) is a corpus of texts from Wikipedia translated from the respective Indian language into English by non-expert translators hired over Mechanical Turk. The quality is thus somewhat mixed in many respects starting from typesetting and punctuation over capi- talization, spelling, word choice to sentence structure. A little bit of control could be in principle obtained from the fact that every input sentence was translated 4 times. We used the 2012 release of the corpus.\r\n\r\nLaunchpad.net is a software collaboration platform that hosts many open-source projects and facilitates also collaborative localization of the tools. We downloaded all revisions of all the hosted projects and extracted the localization (.po) files.\r\n\r\nOther smaller datasets. This time, we added Wikipedia entities as crawled in 2013 (including any morphological variants of the named entitity that appears on the Hindi variant of the Wikipedia page) and words, word examples and quotes from the Shabdkosh online dictionary.;2014-03-21;corpus;http://hdl.handle.net/11858/00-097C-0000-0023-625F-0;hin;eng;http://hdl.handle.net/11858/00-097C-0000-0001-BD17-1;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;text/plain;application/x-gzip;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 3;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8b3691c2-7c2b-5cc3-b9f7-12f9547eb367",
-    "notes": [
-        "HindEnCorp parallel texts (sentence-aligned) come from the following sources:\r\nTides, which contains 50K sentence pairs taken mainly from news articles. This dataset was originally col- lected for the DARPA-TIDES surprise-language con- test in 2002, later refined at IIIT Hyderabad and provided for the NLP Tools Contest at ICON 2008 (Venkatapathy, 2008).\r\n\r\nCommentaries by Daniel Pipes contain 322 articles in English written by a journalist Daniel Pipes and translated into Hindi.\r\n\r\nEMILLE. This corpus (Baker et al., 2002) consists of three components: monolingual, parallel and annotated corpora. There are fourteen monolingual sub- corpora, including both written and (for some lan- guages) spoken data for fourteen South Asian lan- guages. The EMILLE monolingual corpora contain in total 92,799,000 words (including 2,627,000 words of transcribed spoken data for Bengali, Gujarati, Hindi, Punjabi and Urdu). The parallel corpus consists of 200,000 words of text in English and its accompanying translations into Hindi and other languages.\r\n\r\nSmaller datasets as collected by Bojar et al. (2010) include the corpus used at ACL 2005 (a subcorpus of EMILLE), a corpus of named entities from Wikipedia (crawled in 2009), and Agriculture domain parallel corpus.\r\n\ufffc\r\nFor the current release, we are extending the parallel corpus using these sources:\r\nIntercorp (\u010cerm\u00e1k and Rosen,2012) is a large multilingual parallel corpus of 32 languages including Hindi. The central language used for alignment is Czech. Intercorp\u2019s core texts amount to 202 million words. These core texts are most suitable for us because their sentence alignment is manually checked and therefore very reliable. They cover predominately short sto- ries and novels. There are seven Hindi texts in Inter- corp. Unfortunately, only for three of them the English translation is available; the other four are aligned only with Czech texts. The Hindi subcorpus of Intercorp contains 118,000 words in Hindi.\r\n\r\nTED talks 3 held in various languages, primarily English, are equipped with transcripts and these are translated into 102 languages. There are 179 talks for which Hindi translation is available.\r\n\r\nThe Indic multi-parallel corpus (Birch et al., 2011; Post et al., 2012) is a corpus of texts from Wikipedia translated from the respective Indian language into English by non-expert translators hired over Mechanical Turk. The quality is thus somewhat mixed in many respects starting from typesetting and punctuation over capi- talization, spelling, word choice to sentence structure. A little bit of control could be in principle obtained from the fact that every input sentence was translated 4 times. We used the 2012 release of the corpus.\r\n\r\nLaunchpad.net is a software collaboration platform that hosts many open-source projects and facilitates also collaborative localization of the tools. We downloaded all revisions of all the hosted projects and extracted the localization (.po) files.\r\n\r\nOther smaller datasets. This time, we added Wikipedia entities as crawled in 2013 (including any morphological variants of the named entitity that appears on the Hindi variant of the Wikipedia page) and words, word examples and quotes from the Shabdkosh online dictionary."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-625F-0"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parallel corpus"
-        },
-        {
-            "name": "English-Hindi parallel corpus"
-        },
-        {
-            "name": "sentence-parallel"
-        }
-    ],
-    "title": [
-        "HindEnCorp 0.5"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8b421a36-1898-5e84-956c-d4a406ad30fc.json b/oaitestdata/clarin-oai_dc/SET_1/json/8b421a36-1898-5e84-956c-d4a406ad30fc.json
deleted file mode 100644
index fa0cf789..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8b421a36-1898-5e84-956c-d4a406ad30fc.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3015",
-    "MetadataAccess": [
-        "oai:ota:oucs:3015"
-    ],
-    "PublicationTimestamp": "1599-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1599"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Chettle, Henry,(ca. 1560-1607)"
-    ],
-    "fulltext": "oai:ota:oucs:3015;2018-05-25T13:48:34Z;http://ota.ox.ac.uk/headers/3015.xml;The Tragedy Of Hoffman;Chettle, Henry,(ca. 1560-1607);not after: 1599;text_and_corpus_linguistics;Plays -- England -- 17th century;Tragedies -- England -- 17th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8b421a36-1898-5e84-956c-d4a406ad30fc",
-    "oai_identifier": [
-        "oai:ota:oucs:3015"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        },
-        {
-            "name": "Tragedies -- England -- th century"
-        }
-    ],
-    "title": [
-        "The Tragedy Of Hoffman"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3015.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8b45c160-7778-52b2-9b99-43f3f2904be1.json b/oaitestdata/clarin-oai_dc/SET_1/json/8b45c160-7778-52b2-9b99-43f3f2904be1.json
deleted file mode 100644
index 8b5b48ec..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8b45c160-7778-52b2-9b99-43f3f2904be1.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/48",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/48"
-    ],
-    "PID": "http://hdl.handle.net/10794/48",
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/48;2017-10-26T14:23:43Z;hdl_10794_1;hdl_10794_2;Vocation list (2015-01-10);Yrkesbeteckningar (2015-01-10);n/a, n/a;Swedish;Vocations;A list of vocations in Swedish.;En lista \u00f6ver yrkesbeteckningar p\u00e5 svenska.;2015-12-11;lexicalConceptualResource;http://hdl.handle.net/10794/48;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/vocation-list",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8b45c160-7778-52b2-9b99-43f3f2904be1",
-    "notes": [
-        "A list of vocations in Swedish.",
-        "En lista \u00f6ver yrkesbeteckningar p\u00e5 svenska."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/48"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Vocations"
-        }
-    ],
-    "title": [
-        "Vocation list (2015-01-10)",
-        "Yrkesbeteckningar (2015-01-10)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8b4b42af-5bb2-5c29-9002-7281ac43a6cd.json b/oaitestdata/clarin-oai_dc/SET_1/json/8b4b42af-5bb2-5c29-9002-7281ac43a6cd.json
deleted file mode 100644
index adbdf6e9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8b4b42af-5bb2-5c29-9002-7281ac43a6cd.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=f6bac6b859aa11e2a2aa782bcb07413594741ad1234547f2ae9aa68af9034ae4",
-    "MetadataAccess": [
-        "f6bac6b859aa11e2a2aa782bcb07413594741ad1234547f2ae9aa68af9034ae4"
-    ],
-    "PublicationTimestamp": "2013-01-21T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "f6bac6b859aa11e2a2aa782bcb07413594741ad1234547f2ae9aa68af9034ae4;2018-11-15T16:40:01Z;toolService;toolService:tool;Treat;Treat is a toolkit for natural language processing and computational linguistics in Ruby. The Treat project aims to build a language- and algorithm- agnostic NLP framework for Ruby with support for tasks such as document retrieval, text chunking, segmentation and tokenization, natural language parsing, part-of-speech tagging, keyword extraction and named entity recognition.;2013-01-21",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8b4b42af-5bb2-5c29-9002-7281ac43a6cd",
-    "notes": [
-        "Treat is a toolkit for natural language processing and computational linguistics in Ruby. The Treat project aims to build a language- and algorithm- agnostic NLP framework for Ruby with support for tasks such as document retrieval, text chunking, segmentation and tokenization, natural language parsing, part-of-speech tagging, keyword extraction and named entity recognition."
-    ],
-    "oai_identifier": [
-        "f6bac6b859aa11e2a2aa782bcb07413594741ad1234547f2ae9aa68af9034ae4"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "Treat"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8b583260-0884-50b8-9850-d5d629994413.json b/oaitestdata/clarin-oai_dc/SET_1/json/8b583260-0884-50b8-9850-d5d629994413.json
deleted file mode 100644
index f25ee3b3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8b583260-0884-50b8-9850-d5d629994413.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1411",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1411"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1411",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1411;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;kwic;Word concordancer.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1411;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8b583260-0884-50b8-9850-d5d629994413",
-    "notes": [
-        "Word concordancer."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1411"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "kwic"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8b6b85b6-75dd-56ac-a84b-4a5c3f9563c5.json b/oaitestdata/clarin-oai_dc/SET_1/json/8b6b85b6-75dd-56ac-a84b-4a5c3f9563c5.json
deleted file mode 100644
index 39561af0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8b6b85b6-75dd-56ac-a84b-4a5c3f9563c5.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1204",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1204"
-    ],
-    "PID": "http://hdl.handle.net/11356/1204",
-    "PublicationTimestamp": "2018-11-26T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Erjavec, Toma\u017e",
-        "Ljube\u0161i\u0107, Nikola"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1204;2018-11-26T18:25:22Z;hdl_11356_1023;hdl_11356_1024;Word embeddings CLARIN.SI-embed.sl 1.0;Ljube\u0161i\u0107, Nikola;Erjavec, Toma\u017e;word embeddings;lemmatisation;tagging;CLARIN.SI-embed.sl contains word embeddings induced from a large collection of Slovene texts composed of existing corpora of Slovene, e.g GigaFida, Janes, KAS, slWaC etc. The embeddings are based on the skip-gram model of fastText trained on 3,557,125,771 tokens of running text for (1) 2,466,596 lowercased surface forms (e.g., \"slovenije\") and (2) 2,093,848 lowercased lemmas with added part-of-speech information (e.g., \"slovenija#Np\").;2018-11-26;lexicalConceptualResource;http://hdl.handle.net/11356/1204;slv;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/zip;application/octet-stream;application/zip;text/plain; charset=utf-8;downloadable_files_count: 4;Jo\u017eef Stefan Institute",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8b6b85b6-75dd-56ac-a84b-4a5c3f9563c5",
-    "notes": [
-        "CLARIN.SI-embed.sl contains word embeddings induced from a large collection of Slovene texts composed of existing corpora of Slovene, e.g GigaFida, Janes, KAS, slWaC etc. The embeddings are based on the skip-gram model of fastText trained on 3,557,125,771 tokens of running text for (1) 2,466,596 lowercased surface forms (e.g., \"slovenije\") and (2) 2,093,848 lowercased lemmas with added part-of-speech information (e.g., \"slovenija#Np\")."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1204"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "word embeddings"
-        },
-        {
-            "name": "lemmatisation"
-        },
-        {
-            "name": "tagging"
-        }
-    ],
-    "title": [
-        "Word embeddings CLARIN.SI-embed.sl 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8b87dade-02dd-5e59-9892-d1de552e7ac8.json b/oaitestdata/clarin-oai_dc/SET_1/json/8b87dade-02dd-5e59-9892-d1de552e7ac8.json
deleted file mode 100644
index 886976ab..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8b87dade-02dd-5e59-9892-d1de552e7ac8.json
+++ /dev/null
@@ -1,95 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/x-tar",
-        "text/plain; charset=utf-8",
-        "application/x-xz",
-        "downloadable_files_count: 4"
-    ],
-    "Language": [
-        "Multiple languages"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1990",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1990"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1990",
-    "PublicationTimestamp": "2017-03-15T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "Rights": [
-        "Licence Universal Dependencies v2.0",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-2.0",
-        "PUB"
-    ],
-    "author": [
-        "Straka, Milan"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1990;2018-07-02T22:05:54Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;CoNLL 2017 Shared Task - UDPipe Baseline Models and Supplementary Materials;Straka, Milan;CoNLL 2017;tokenizer;POS tagger;lemmatization;tagger;parser;dependency parser;morphology;treebank;Baseline UDPipe models for CoNLL 2017 Shared Task in UD Parsing, and supplementary material.\r\n\r\nThe models require UDPipe version at least 1.1 and are evaluated using the official evaluation script.\r\n\r\nThe models are trained on a slightly different split of the official UD 2.0 CoNLL 2017 training data, so called baselinemodel split, in order to allow comparison of models even during the shared task. This baselinemodel split of UD 2.0 CoNLL 2017 training data is available for download.\r\n\r\nFurthermore, we also provide UD 2.0 CoNLL 2017 training data with automatically predicted morphology. We utilize the baseline models on development data and perform 10-fold jack-knifing (each fold is predicted with a model trained on the rest of the folds) on the training data.\r\n\r\nFinally, we supply all required data and hyperparameter values needed to replicate the baseline models.;2017-03-15;languageDescription;http://hdl.handle.net/11234/1-1990;mul;Licence Universal Dependencies v2.0;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-2.0;PUB;application/x-tar;application/x-xz;application/x-xz;application/x-xz;text/plain; charset=utf-8;downloadable_files_count: 4;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/udpipe",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8b87dade-02dd-5e59-9892-d1de552e7ac8",
-    "notes": [
-        "Baseline UDPipe models for CoNLL 2017 Shared Task in UD Parsing, and supplementary material.\r\n\r\nThe models require UDPipe version at least 1.1 and are evaluated using the official evaluation script.\r\n\r\nThe models are trained on a slightly different split of the official UD 2.0 CoNLL 2017 training data, so called baselinemodel split, in order to allow comparison of models even during the shared task. This baselinemodel split of UD 2.0 CoNLL 2017 training data is available for download.\r\n\r\nFurthermore, we also provide UD 2.0 CoNLL 2017 training data with automatically predicted morphology. We utilize the baseline models on development data and perform 10-fold jack-knifing (each fold is predicted with a model trained on the rest of the folds) on the training data.\r\n\r\nFinally, we supply all required data and hyperparameter values needed to replicate the baseline models."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1990"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "CoNLL"
-        },
-        {
-            "name": "tokenizer"
-        },
-        {
-            "name": "POS tagger"
-        },
-        {
-            "name": "lemmatization"
-        },
-        {
-            "name": "tagger"
-        },
-        {
-            "name": "parser"
-        },
-        {
-            "name": "dependency parser"
-        },
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "treebank"
-        }
-    ],
-    "title": [
-        "CoNLL 2017 Shared Task - UDPipe Baseline Models and Supplementary Materials"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8b9e4288-f0df-5577-b5e1-269b9a0d1bfb.json b/oaitestdata/clarin-oai_dc/SET_1/json/8b9e4288-f0df-5577-b5e1-269b9a0d1bfb.json
deleted file mode 100644
index 48c2ec06..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8b9e4288-f0df-5577-b5e1-269b9a0d1bfb.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Matteo Grella"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2288",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2288"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2288",
-    "PublicationTimestamp": "2017-06-26T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Matteo Grella"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11372/LRT-2629"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Grella, Matteo"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2288;2018-03-02T07:08:02Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Italian Function Words;Grella, Matteo;morphological dictionary;function words;This dictionary is a curated list of Italian function words in a JSON Lines format text file, particularly useful for tasks such as POS-Tagging or Syntactic Parsing. It contains 999 single-word forms and 2501 multi-words forms. Each entry may have the following grammatical features: lemma, pos, mood, tense, person, number, gender, case, degree.;2017-06-26;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-2288;ita;http://hdl.handle.net/11372/LRT-2629;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;Matteo Grella",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8b9e4288-f0df-5577-b5e1-269b9a0d1bfb",
-    "notes": [
-        "This dictionary is a curated list of Italian function words in a JSON Lines format text file, particularly useful for tasks such as POS-Tagging or Syntactic Parsing. It contains 999 single-word forms and 2501 multi-words forms. Each entry may have the following grammatical features: lemma, pos, mood, tense, person, number, gender, case, degree."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2288"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphological dictionary"
-        },
-        {
-            "name": "function words"
-        }
-    ],
-    "title": [
-        "Italian Function Words"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8ba0bc99-29b6-56b2-9102-16c038dda3e3.json b/oaitestdata/clarin-oai_dc/SET_1/json/8ba0bc99-29b6-56b2-9102-16c038dda3e3.json
deleted file mode 100644
index 7e8c4a9f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8ba0bc99-29b6-56b2-9102-16c038dda3e3.json
+++ /dev/null
@@ -1,95 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/x-tar",
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 9"
-    ],
-    "Language": [
-        "Czech",
-        "English",
-        "French",
-        "German",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1912",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1912"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1912",
-    "PublicationTimestamp": "2017-01-05T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Ircing, Pavel",
-        "Haji\u010d, Jan",
-        "\u0160vec, Jan",
-        "Galu\u0161\u010d\u00e1kov\u00e1, Petra",
-        "Pecina, Pavel",
-        "Hoffmannov\u00e1, Petra"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1912;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Czech Malach Cross-lingual Speech Retrieval Test Collection;Galu\u0161\u010d\u00e1kov\u00e1, Petra;Pecina, Pavel;Hoffmannov\u00e1, Petra;Haji\u010d, Jan;Ircing, Pavel;\u0160vec, Jan;annotated corpus;corpus;speech corpus;annotation;audio;multilingual;The package contains Czech recordings of the Visual History Archive which consists of the interviews with the Holocaust survivors. The archive consists of audio recordings, four types of automatic transcripts, manual annotations of selected topics and interviews' metadata. The archive totally contains 353 recordings and 592 hours of interviews.;2017-01-05;corpus;http://hdl.handle.net/11234/1-1912;ces;eng;fra;deu;spa;Creative Commons - Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0);http://creativecommons.org/licenses/by-nc-nd/4.0/;PUB;application/x-gzip;application/x-tar;application/x-tar;application/x-tar;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 9;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/malach-test-collection",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8ba0bc99-29b6-56b2-9102-16c038dda3e3",
-    "notes": [
-        "The package contains Czech recordings of the Visual History Archive which consists of the interviews with the Holocaust survivors. The archive consists of audio recordings, four types of automatic transcripts, manual annotations of selected topics and interviews' metadata. The archive totally contains 353 recordings and 592 hours of interviews."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1912"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "annotated corpus"
-        },
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "speech corpus"
-        },
-        {
-            "name": "annotation"
-        },
-        {
-            "name": "audio"
-        },
-        {
-            "name": "multilingual"
-        }
-    ],
-    "title": [
-        "Czech Malach Cross-lingual Speech Retrieval Test Collection"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8babf8e2-8330-56e3-b487-075bde758f26.json b/oaitestdata/clarin-oai_dc/SET_1/json/8babf8e2-8330-56e3-b487-075bde758f26.json
deleted file mode 100644
index 7bced339..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8babf8e2-8330-56e3-b487-075bde758f26.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=0a241662bc6911e1a404080027e73ea2c9eb952b442542538520035aeb59596d",
-    "MetadataAccess": [
-        "0a241662bc6911e1a404080027e73ea2c9eb952b442542538520035aeb59596d"
-    ],
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "0a241662bc6911e1a404080027e73ea2c9eb952b442542538520035aeb59596d;2018-11-15T16:39:38Z;lexicalConceptualResource;lexicalConceptualResource:other;MFSA_Maltese_Company_Registry;List of companies with further information;2015-12-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8babf8e2-8330-56e3-b487-075bde758f26",
-    "notes": [
-        "List of companies with further information"
-    ],
-    "oai_identifier": [
-        "0a241662bc6911e1a404080027e73ea2c9eb952b442542538520035aeb59596d"
-    ],
-    "oai_set": [
-        "lexicalConceptualResource",
-        "lexicalConceptualResource:other"
-    ],
-    "state": "active",
-    "title": [
-        "MFSA_Maltese_Company_Registry"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8bc6e646-5175-544c-a016-a7b257402cb6.json b/oaitestdata/clarin-oai_dc/SET_1/json/8bc6e646-5175-544c-a016-a7b257402cb6.json
deleted file mode 100644
index fe679719..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8bc6e646-5175-544c-a016-a7b257402cb6.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2768",
-    "MetadataAccess": [
-        "oai:ota:oucs:2768"
-    ],
-    "PublicationTimestamp": "1765-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1765"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2768;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2768.xml;An account of the court and empire of Japan;Swift, Jonathan, 1667-1745;1765;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8bc6e646-5175-544c-a016-a7b257402cb6",
-    "oai_identifier": [
-        "oai:ota:oucs:2768"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An account of the court and empire of Japan"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2768.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8c075c5c-d0ce-586c-b144-d019b541e602.json b/oaitestdata/clarin-oai_dc/SET_1/json/8c075c5c-d0ce-586c-b144-d019b541e602.json
deleted file mode 100644
index d7f70533..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8c075c5c-d0ce-586c-b144-d019b541e602.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Institute of Mathematics and Computer Science, University of Latvia"
-    ],
-    "Contributor": [
-        "Lev\u0101ne-Petrova, Krist\u012bne"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/plain"
-    ],
-    "Language": [
-        "Latvian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-706",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-706"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-706",
-    "PublicationTimestamp": "2008-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2008"
-    ],
-    "Publisher": [
-        "Institute of Mathematics and Computer Science, University of Latvia"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Latvia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-706;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Corpus \"Miljons\";Lev\u0101ne-Petrova, Krist\u012bne;balanced corpus;Balanced corpus of Modern Latvian (~ 1 million running words, currently in plain-text), publicly available via Bonito interface;2008;corpus;http://hdl.handle.net/11372/LRT-706;lav;text/plain;downloadable_files_count: 0;Latvia;Institute of Mathematics and Computer Science, University of Latvia;http://www.korpuss.lv",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8c075c5c-d0ce-586c-b144-d019b541e602",
-    "notes": [
-        "Balanced corpus of Modern Latvian (~ 1 million running words, currently in plain-text), publicly available via Bonito interface"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-706"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "balanced corpus"
-        }
-    ],
-    "title": [
-        "Corpus \"Miljons\""
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8c6aa336-dcb9-5b80-82aa-b321c94e6fd1.json b/oaitestdata/clarin-oai_dc/SET_1/json/8c6aa336-dcb9-5b80-82aa-b321c94e6fd1.json
deleted file mode 100644
index abf506df..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8c6aa336-dcb9-5b80-82aa-b321c94e6fd1.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Collegium Scholarum Piarum"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-42",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-42"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D1B-1",
-    "PublicationTimestamp": "1690-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1690"
-    ],
-    "Publisher": [
-        "Drukarnia Collegium Scholarum Piarum"
-    ],
-    "RelatedIdentifier": [
-        "http://pbc.biaman.pl/Content/42"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "author": [
-        "Za\u0142uski, Andrzej Chryzostom (ca 1648 - 1711)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-42;2019-03-01T15:27:36Z;Mowy r\u00f3\u017cne przez  X.Andrzeja Chryzostoma  Na Za\u0142uskach y B\u0142\u0119dowie Za\u0142uskiego biskupa kijowskiego y czerniechowskiego &c. Miane a Naja\u015bnieyszey Kr\u00f3lowy Mariey Kazimierze Pani Swoiey y Dobrodzieyce Mi\u0142o\u015bciwey Przypisane.;Za\u0142uski, Andrzej Chryzostom (ca 1648 - 1711);Mowy polskie 17 w.;ilo\u015b\u0107 skan\u00f3w: 115 ; sygn.  1167;Drukarnia Collegium Scholarum Piarum;1690;starodruk;application/xml;clarind-uds:poldilemma-42;hdl:11858/00-246C-0000-0023-8D1B-1;pol;lat;http://pbc.biaman.pl/Content/42;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8c6aa336-dcb9-5b80-82aa-b321c94e6fd1",
-    "notes": [
-        "ilo\u015b\u0107 skan\u00f3w: 115 ; sygn.  1167"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-42"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Mowy polskie w."
-        }
-    ],
-    "title": [
-        "Mowy r\u00f3\u017cne przez  X.Andrzeja Chryzostoma  Na Za\u0142uskach y B\u0142\u0119dowie Za\u0142uskiego biskupa kijowskiego y czerniechowskiego &c. Miane a Naja\u015bnieyszey Kr\u00f3lowy Mariey Kazimierze Pani Swoiey y Dobrodzieyce Mi\u0142o\u015bciwey Przypisane."
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8c6be349-7c26-5c1f-a549-10a83dc02903.json b/oaitestdata/clarin-oai_dc/SET_1/json/8c6be349-7c26-5c1f-a549-10a83dc02903.json
deleted file mode 100644
index 0cc269f3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8c6be349-7c26-5c1f-a549-10a83dc02903.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2656",
-    "MetadataAccess": [
-        "oai:ota:oucs:2656"
-    ],
-    "PublicationTimestamp": "1765-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1765"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2656;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2656.xml;A prayer for Stella;Swift, Jonathan, 1667-1745;1765;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8c6be349-7c26-5c1f-a549-10a83dc02903",
-    "oai_identifier": [
-        "oai:ota:oucs:2656"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A prayer for Stella"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2656.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8c74aaf0-218b-5eb3-a31e-3af48933619f.json b/oaitestdata/clarin-oai_dc/SET_1/json/8c74aaf0-218b-5eb3-a31e-3af48933619f.json
deleted file mode 100644
index 518f2afe..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8c74aaf0-218b-5eb3-a31e-3af48933619f.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "University of Sheffield"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 7"
-    ],
-    "Language": [
-        "English",
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2135",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2135"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2135",
-    "PublicationTimestamp": "2017-04-13T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "University of Sheffield"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/H2020/645452",
-        "http://hdl.handle.net/11372/LRT-2805"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "AGREEMENT ON THE USE OF DATA IN QT21",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21",
-        "PUB"
-    ],
-    "author": [
-        "Logacheva, Varvara",
-        "Specia, Lucia"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2135;2018-05-21T15:23:41Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;WMT17 Quality Estimation Shared Test Data;Specia, Lucia;Logacheva, Varvara;machine translation;quality estimation;machine learning;Test data for the WMT17 QE task. Train data can be downloaded from http://hdl.handle.net/11372/LRT-1974\r\n\r\nThis shared task will build on its previous five editions to further examine automatic methods for estimating the quality of machine translation output at run-time, without relying on reference translations. We include word-level, phrase-level and sentence-level estimation. All tasks will make use of a large dataset produced from post-editions by professional translators. The data will be domain-specific (IT and Pharmaceutical domains) and substantially larger than in previous years. In addition to advancing the state of the art at all prediction levels, our goals include:\r\n\r\n- To test the effectiveness of larger (domain-specific and professionally annotated) datasets. We will do so by increasing the size of one of last year's training sets.\r\n- To study the effect of language direction and domain. We will do so by providing two datasets created in similar ways, but for different domains and language directions.\r\n- To investigate the utility of detailed information logged during post-editing. We will do so by providing post-editing time, keystrokes, and actual edits.\r\n\r\nThis year's shared task provides new training and test datasets for all tasks, and allows participants to explore any additional data and resources deemed relevant. A in-house MT system was used to produce translations for all tasks. MT system-dependent information can be made available under request. The data is publicly available but since it has been provided by our industry partners it is subject to specific terms and conditions. However, these have no practical implications on the use of this data for research purposes.;2017-04-13;corpus;http://hdl.handle.net/11372/LRT-2135;eng;deu;info:eu-repo/grantAgreement/EC/H2020/645452;http://hdl.handle.net/11372/LRT-2805;AGREEMENT ON THE USE OF DATA IN QT21;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21;PUB;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 7;University of Sheffield;http://www.statmt.org/wmt17/quality-estimation-task.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8c74aaf0-218b-5eb3-a31e-3af48933619f",
-    "notes": [
-        "Test data for the WMT17 QE task. Train data can be downloaded from http://hdl.handle.net/11372/LRT-1974\r\n\r\nThis shared task will build on its previous five editions to further examine automatic methods for estimating the quality of machine translation output at run-time, without relying on reference translations. We include word-level, phrase-level and sentence-level estimation. All tasks will make use of a large dataset produced from post-editions by professional translators. The data will be domain-specific (IT and Pharmaceutical domains) and substantially larger than in previous years. In addition to advancing the state of the art at all prediction levels, our goals include:\r\n\r\n- To test the effectiveness of larger (domain-specific and professionally annotated) datasets. We will do so by increasing the size of one of last year's training sets.\r\n- To study the effect of language direction and domain. We will do so by providing two datasets created in similar ways, but for different domains and language directions.\r\n- To investigate the utility of detailed information logged during post-editing. We will do so by providing post-editing time, keystrokes, and actual edits.\r\n\r\nThis year's shared task provides new training and test datasets for all tasks, and allows participants to explore any additional data and resources deemed relevant. A in-house MT system was used to produce translations for all tasks. MT system-dependent information can be made available under request. The data is publicly available but since it has been provided by our industry partners it is subject to specific terms and conditions. However, these have no practical implications on the use of this data for research purposes."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2135"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "quality estimation"
-        },
-        {
-            "name": "machine learning"
-        }
-    ],
-    "title": [
-        "WMT17 Quality Estimation Shared Test Data"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8c87ba4b-56e6-58e7-bd27-5ba08f0d3b19.json b/oaitestdata/clarin-oai_dc/SET_1/json/8c87ba4b-56e6-58e7-bd27-5ba08f0d3b19.json
deleted file mode 100644
index 77c179dc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8c87ba4b-56e6-58e7-bd27-5ba08f0d3b19.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4217",
-    "MetadataAccess": [
-        "oai:ota:oucs:4217"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Cumberland, Richard, 1732-1811."
-    ],
-    "fulltext": "oai:ota:oucs:4217;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4217.xml;Timon of Athens: altered from Shakespear, a tragedy. As it is acted at the Theatre-Royal in Drury-Lane.;Cumberland, Richard, 1732-1811.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8c87ba4b-56e6-58e7-bd27-5ba08f0d3b19",
-    "oai_identifier": [
-        "oai:ota:oucs:4217"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Timon of Athens: altered from Shakespear, a tragedy. As it is acted at the Theatre-Royal in Drury-Lane."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4217.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8c907e16-55b6-505f-a058-f7591151c36b.json b/oaitestdata/clarin-oai_dc/SET_1/json/8c907e16-55b6-505f-a058-f7591151c36b.json
deleted file mode 100644
index 55b6e7fa..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8c907e16-55b6-505f-a058-f7591151c36b.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4842",
-    "MetadataAccess": [
-        "oai:ota:oucs:4842"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gilpin, William, 1724-1804."
-    ],
-    "fulltext": "oai:ota:oucs:4842;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4842.xml;Observations relative chiefly to picturesque beauty, made in the year 1776: on several parts of Great Britain; particularly the High-lands of Scotland. ... By William Gilpin, ... [pt.2];Gilpin, William, 1724-1804.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8c907e16-55b6-505f-a058-f7591151c36b",
-    "oai_identifier": [
-        "oai:ota:oucs:4842"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Observations relative chiefly to picturesque beauty, made in the year 1776: on several parts of Great Britain; particularly the High-lands of Scotland. ... By William Gilpin, ... [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4842.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8cb36b3c-6ab8-5cb8-b15e-ae351f27d3d8.json b/oaitestdata/clarin-oai_dc/SET_1/json/8cb36b3c-6ab8-5cb8-b15e-ae351f27d3d8.json
deleted file mode 100644
index 95524e38..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8cb36b3c-6ab8-5cb8-b15e-ae351f27d3d8.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "University of the Basque Country"
-    ],
-    "Contributor": [
-        "Artola, Xabier"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/xml"
-    ],
-    "Language": [
-        "Basque"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1056",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1056"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1056",
-    "PublicationTimestamp": "2010-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "University of the Basque Country"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Only for research and demonstrative purposes"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1056;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;EDBL: Lexical Data Base for Basque (Euskararen Datu-base Lexikala);Artola, Xabier;EDBL (Lexical DataBase for Basque) is the lexical basis needed for the automatic treatment of Basque. It is made up of about 120.000 entries divided into dictionary entries (the same you can find in a conventional dictionay), verb forms and dependent morphemes, all of them with their respective morphological information.;2010;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1056;eus;Only for research and demonstrative purposes;application/xml;downloadable_files_count: 0;Spain;University of the Basque Country;http://ixa2.si.ehu.es/demo/edbl.jsp",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8cb36b3c-6ab8-5cb8-b15e-ae351f27d3d8",
-    "notes": [
-        "EDBL (Lexical DataBase for Basque) is the lexical basis needed for the automatic treatment of Basque. It is made up of about 120.000 entries divided into dictionary entries (the same you can find in a conventional dictionay), verb forms and dependent morphemes, all of them with their respective morphological information."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1056"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "EDBL: Lexical Data Base for Basque (Euskararen Datu-base Lexikala)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8cd84a66-0ea0-58aa-9245-f49eb56af6f4.json b/oaitestdata/clarin-oai_dc/SET_1/json/8cd84a66-0ea0-58aa-9245-f49eb56af6f4.json
deleted file mode 100644
index 407bc486..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8cd84a66-0ea0-58aa-9245-f49eb56af6f4.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-998",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-998"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-998",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-998;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LAC Lavukaleve Corpus;Language and Cognition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-998;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI553462%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8cd84a66-0ea0-58aa-9245-f49eb56af6f4",
-    "notes": [
-        "Language and Cognition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-998"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LAC Lavukaleve Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8cdcf592-a8b6-541b-bab6-c06dab576e4b.json b/oaitestdata/clarin-oai_dc/SET_1/json/8cdcf592-a8b6-541b-bab6-c06dab576e4b.json
deleted file mode 100644
index 5fca60cc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8cdcf592-a8b6-541b-bab6-c06dab576e4b.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/xml",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/4",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/4"
-    ],
-    "PID": "http://hdl.handle.net/10794/4",
-    "PublicationTimestamp": "2017-04-28T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/10794/5"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Forsberg, Markus",
-        "Borin, Lars",
-        "L\u00f6nngren, Lennart"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/4;2017-10-27T16:31:20Z;hdl_10794_1;hdl_10794_2;Saldo (2017-05-24);Saldo (2017-05-24);Borin, Lars;L\u00f6nngren, Lennart;Forsberg, Markus;Swedish;Associative;Thesaurus;SALDO (Swedish Associative Thesaurus version 2) is an extensive lexicon resource for modern Swedish written language.;SALDO (Svenskt Associationslexikon version 2) \u00e4r ett semantiskt och morfologiskt lexikon f\u00f6r moderns svenskt skriftspr\u00e5k f\u00f6r spr\u00e5kteknologi.;2017-04-28;lexicalConceptualResource;http://hdl.handle.net/10794/4;swe;http://hdl.handle.net/10794/5;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;text/xml;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/saldo",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8cdcf592-a8b6-541b-bab6-c06dab576e4b",
-    "notes": [
-        "SALDO (Swedish Associative Thesaurus version 2) is an extensive lexicon resource for modern Swedish written language.",
-        "SALDO (Svenskt Associationslexikon version 2) \u00e4r ett semantiskt och morfologiskt lexikon f\u00f6r moderns svenskt skriftspr\u00e5k f\u00f6r spr\u00e5kteknologi."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/4"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Associative"
-        },
-        {
-            "name": "Thesaurus"
-        }
-    ],
-    "title": [
-        "Saldo (2017-05-24)",
-        "Saldo (2017-05-24)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8d1296bc-77cf-5504-b282-5fa253d001ba.json b/oaitestdata/clarin-oai_dc/SET_1/json/8d1296bc-77cf-5504-b282-5fa253d001ba.json
deleted file mode 100644
index 63fa7615..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8d1296bc-77cf-5504-b282-5fa253d001ba.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 428 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "Middle English (1100-1500)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0500",
-    "MetadataAccess": [
-        "oai:ota:oucs:0500"
-    ],
-    "PublicationTimestamp": "1370-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1370"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Langland, William, 1330?-1400?"
-    ],
-    "fulltext": "oai:ota:oucs:0500;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0500.xml;[Piers Plowman];Langland, William, 1330?-1400?;1370-1390;text_and_corpus_linguistics;Poems -- England -- 14th century;enm;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 428 KB);Text;Poems;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8d1296bc-77cf-5504-b282-5fa253d001ba",
-    "oai_identifier": [
-        "oai:ota:oucs:0500"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- England -- th century"
-        }
-    ],
-    "title": [
-        "[Piers Plowman]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0500.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8d21e170-0390-5a60-ae32-408725e8efb0.json b/oaitestdata/clarin-oai_dc/SET_1/json/8d21e170-0390-5a60-ae32-408725e8efb0.json
deleted file mode 100644
index e284cb57..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8d21e170-0390-5a60-ae32-408725e8efb0.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Wroclaw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/44",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/44"
-    ],
-    "PID": "http://hdl.handle.net/11321/44",
-    "PublicationTimestamp": "2014-10-24T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Wroclaw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Walkowiak, Tomasz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/44;2014-10-24T09:37:56Z;hdl_11321_3;hdl_11321_4;WCRFT Webservice;Walkowiak, Tomasz;tagger;weblicht;Webservice for Weblicht;2014-10-24;toolService;http://hdl.handle.net/11321/44;pol;application/octet-stream;downloadable_files_count: 0;Wroclaw University of Technology;http://nlp.pwr.wroc.pl/redmine/projects/wcrft/wiki",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8d21e170-0390-5a60-ae32-408725e8efb0",
-    "notes": [
-        "Webservice for Weblicht"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/44"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "tagger"
-        },
-        {
-            "name": "weblicht"
-        }
-    ],
-    "title": [
-        "WCRFT Webservice"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8d2b1d76-469d-5de7-8446-c2d4f9af5eda.json b/oaitestdata/clarin-oai_dc/SET_1/json/8d2b1d76-469d-5de7-8446-c2d4f9af5eda.json
deleted file mode 100644
index 84d4fb0b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8d2b1d76-469d-5de7-8446-c2d4f9af5eda.json
+++ /dev/null
@@ -1,88 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 4",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Czech",
-        "English",
-        "Vietnamese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1595",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1595"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1595",
-    "PublicationTimestamp": "2015-11-10T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/H2020/645452"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Bojar, Ond\u0159ej",
-        "Hoang, Duc Tam"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1595;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;CsEnVi Pairwise Parallel Corpora;Hoang, Duc Tam;Bojar, Ond\u0159ej;corpus;Vietnamese;parallel corpus;Czech-Vietnamese corpus;English-Vietnamese corpus;CsEnVi Pairwise Parallel Corpora consist of Vietnamese-Czech parallel corpus and Vietnamese-English parallel corpus. The corpora were assembled from the following sources:\r\n\r\n- OPUS, the open parallel corpus is a growing multilingual corpus of translated open source documents.\r\nThe majority of Vi-En and Vi-Cs bitexts are subtitles from movies and television series. \r\nThe nature of the bitexts are paraphrasing of each other's meaning, rather than translations. \r\n\r\n- TED talks, a collection of short talks on various topics, given primarily in English, transcribed and with transcripts translated to other languages. In our corpus, we use 1198 talks which had English and Vietnamese transcripts available and 784 talks which had Czech and Vietnamese transcripts available in January 2015.\r\n\r\nThe size of the original corpora collected from OPUS and TED talks is as follows:\r\n\r\n                  \tCS/VI                       \tEN/VI\r\nSentence   \t1337199/1337199   \t2035624/2035624\r\nWord          \t9128897/12073975  \t16638364/17565580\t\t\r\nUnique word\t224416/68237         \t91905/78333\r\n\r\nWe improve the quality of the corpora in two steps: normalizing and filtering.\r\n\r\nIn the normalizing step, the corpora are cleaned based on the general format of subtitles and transcripts. For instance, sequences of dots indicate explicit continuation of subtitles across multiple time frames. The sequences of dots are distributed differently in the source and the target side. Removing the sequence of dots, along with a number of other normalization rules, improves the quality of the alignment significantly.\r\nIn the filtering step, we adapt the CzEng filtering tool [1] to filter out bad sentence pairs.\r\n\r\nThe size of cleaned corpora as published is as follows:\r\n\r\n                   \tCS/VI                       \tEN/VI\r\nSentence  \t1091058/1091058    \t1113177/1091058\r\nWord         \t6718184/7646701   \t8518711/8140876\r\nUnique word\t195446/59737         \t69513/58286\r\n\r\nThe corpora are used as training data in [2].\r\n\r\nReferences:\r\n[1] Ond\u0159ej Bojar, Zden\u011bk \u017dabokrtsk\u00fd, et al. 2012. The Joy of Parallelism with CzEng 1.0. Proceedings of LREC2012. ELRA. Istanbul, Turkey.\r\n[2] Duc Tam Hoang and Ond\u0159ej Bojar, The Prague Bulletin of Mathematical Linguistics. Volume 104, Issue 1, Pages 75\u201386, ISSN 1804-0462. 9/2015;2015-11-10;corpus;http://hdl.handle.net/11234/1-1595;ces;eng;vie;info:eu-repo/grantAgreement/EC/H2020/645452;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 4;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8d2b1d76-469d-5de7-8446-c2d4f9af5eda",
-    "notes": [
-        "CsEnVi Pairwise Parallel Corpora consist of Vietnamese-Czech parallel corpus and Vietnamese-English parallel corpus. The corpora were assembled from the following sources:\r\n\r\n- OPUS, the open parallel corpus is a growing multilingual corpus of translated open source documents.\r\nThe majority of Vi-En and Vi-Cs bitexts are subtitles from movies and television series. \r\nThe nature of the bitexts are paraphrasing of each other's meaning, rather than translations. \r\n\r\n- TED talks, a collection of short talks on various topics, given primarily in English, transcribed and with transcripts translated to other languages. In our corpus, we use 1198 talks which had English and Vietnamese transcripts available and 784 talks which had Czech and Vietnamese transcripts available in January 2015.\r\n\r\nThe size of the original corpora collected from OPUS and TED talks is as follows:\r\n\r\n                  \tCS/VI                       \tEN/VI\r\nSentence   \t1337199/1337199   \t2035624/2035624\r\nWord          \t9128897/12073975  \t16638364/17565580\t\t\r\nUnique word\t224416/68237         \t91905/78333\r\n\r\nWe improve the quality of the corpora in two steps: normalizing and filtering.\r\n\r\nIn the normalizing step, the corpora are cleaned based on the general format of subtitles and transcripts. For instance, sequences of dots indicate explicit continuation of subtitles across multiple time frames. The sequences of dots are distributed differently in the source and the target side. Removing the sequence of dots, along with a number of other normalization rules, improves the quality of the alignment significantly.\r\nIn the filtering step, we adapt the CzEng filtering tool [1] to filter out bad sentence pairs.\r\n\r\nThe size of cleaned corpora as published is as follows:\r\n\r\n                   \tCS/VI                       \tEN/VI\r\nSentence  \t1091058/1091058    \t1113177/1091058\r\nWord         \t6718184/7646701   \t8518711/8140876\r\nUnique word\t195446/59737         \t69513/58286\r\n\r\nThe corpora are used as training data in [2].\r\n\r\nReferences:\r\n[1] Ond\u0159ej Bojar, Zden\u011bk \u017dabokrtsk\u00fd, et al. 2012. The Joy of Parallelism with CzEng 1.0. Proceedings of LREC2012. ELRA. Istanbul, Turkey.\r\n[2] Duc Tam Hoang and Ond\u0159ej Bojar, The Prague Bulletin of Mathematical Linguistics. Volume 104, Issue 1, Pages 75\u201386, ISSN 1804-0462. 9/2015"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1595"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "Vietnamese"
-        },
-        {
-            "name": "parallel corpus"
-        },
-        {
-            "name": "Czech-Vietnamese corpus"
-        },
-        {
-            "name": "English-Vietnamese corpus"
-        }
-    ],
-    "title": [
-        "CsEnVi Pairwise Parallel Corpora"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8d327714-3801-5114-9cbb-42f257eaff92.json b/oaitestdata/clarin-oai_dc/SET_1/json/8d327714-3801-5114-9cbb-42f257eaff92.json
deleted file mode 100644
index 52346d50..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8d327714-3801-5114-9cbb-42f257eaff92.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Jan Koco\u0144"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/454",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/454"
-    ],
-    "PID": "http://hdl.handle.net/11321/454",
-    "PublicationTimestamp": "2018-01-15T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Jan Koco\u0144"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Koco\u0144, Jan"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/454;2018-01-15T18:41:09Z;hdl_11321_3;hdl_11321_4;BlogReader;Koco\u0144, Jan;BlogReader;HTML parser;metadata extraction;BlogReader - corpus acquisition from structured web sources;2018-01-15;toolService;http://hdl.handle.net/11321/454;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;Jan Koco\u0144",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8d327714-3801-5114-9cbb-42f257eaff92",
-    "notes": [
-        "BlogReader - corpus acquisition from structured web sources"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/454"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "BlogReader"
-        },
-        {
-            "name": "HTML parser"
-        },
-        {
-            "name": "metadata extraction"
-        }
-    ],
-    "title": [
-        "BlogReader"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8d7fe8da-6460-5f22-b0c5-3c6060e6bb1b.json b/oaitestdata/clarin-oai_dc/SET_1/json/8d7fe8da-6460-5f22-b0c5-3c6060e6bb1b.json
deleted file mode 100644
index 54d8ff7e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8d7fe8da-6460-5f22-b0c5-3c6060e6bb1b.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Asmussen, J\u00f6rg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Danish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-246",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-246"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-246",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Denmark"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-246;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Korpus 2000;Asmussen, J\u00f6rg;written, general language;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-246;dan;downloadable_files_count: 0;Denmark;http://ordnet.dk/korpusdk",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8d7fe8da-6460-5f22-b0c5-3c6060e6bb1b",
-    "notes": [
-        "written, general language"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-246"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Korpus 2000"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8d921cf3-682e-59ec-8de3-7cca12f3ab4b.json b/oaitestdata/clarin-oai_dc/SET_1/json/8d921cf3-682e-59ec-8de3-7cca12f3ab4b.json
deleted file mode 100644
index 043bf223..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8d921cf3-682e-59ec-8de3-7cca12f3ab4b.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Masaryk University, NLP Centre"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Oromo"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2588",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2588"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2588",
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Masaryk University, NLP Centre"
-    ],
-    "RelatedIdentifier": [
-        "https://www.sketchengine.co.uk/wp-content/uploads/2015/05/Corpus_Factory_2010.pdf",
-        "http://habit-project.eu/wiki/OromoCorpus"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "NLP Centre Web Corpus License",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/license-NLPC-WeC",
-        "ACA"
-    ],
-    "author": [
-        "Suchomel, V\u00edt",
-        "Rychl\u00fd, Pavel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2588;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Oromo web corpus;Suchomel, V\u00edt;Rychl\u00fd, Pavel;text corpora;Ethiopian languages;Oromo;web corpus;under-resourced language;Oromo web corpus. Crawled by SpiderLing in January 2016. Encoded in UTF-8, cleaned, deduplicated.;2016;corpus;http://hdl.handle.net/11234/1-2588;orm;https://www.sketchengine.co.uk/wp-content/uploads/2015/05/Corpus_Factory_2010.pdf;http://habit-project.eu/wiki/OromoCorpus;NLP Centre Web Corpus License;https://lindat.mff.cuni.cz/repository/xmlui/page/license-NLPC-WeC;ACA;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Masaryk University, NLP Centre;http://habit-project.eu/wiki/HabitSystemFinal",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8d921cf3-682e-59ec-8de3-7cca12f3ab4b",
-    "notes": [
-        "Oromo web corpus. Crawled by SpiderLing in January 2016. Encoded in UTF-8, cleaned, deduplicated."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2588"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "text corpora"
-        },
-        {
-            "name": "Ethiopian languages"
-        },
-        {
-            "name": "Oromo"
-        },
-        {
-            "name": "web corpus"
-        },
-        {
-            "name": "under-resourced language"
-        }
-    ],
-    "title": [
-        "Oromo web corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8d982ef7-ca54-54fb-bfc6-7de31ca45c51.json b/oaitestdata/clarin-oai_dc/SET_1/json/8d982ef7-ca54-54fb-bfc6-7de31ca45c51.json
deleted file mode 100644
index 38d2c2b8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8d982ef7-ca54-54fb-bfc6-7de31ca45c51.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3800",
-    "MetadataAccess": [
-        "oai:ota:oucs:3800"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Boswell, James, 1740-1795."
-    ],
-    "fulltext": "oai:ota:oucs:3800;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3800.xml;A letter to the people of Scotland, on the present state of the nation. By James Boswell, Esq;Boswell, James, 1740-1795.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8d982ef7-ca54-54fb-bfc6-7de31ca45c51",
-    "oai_identifier": [
-        "oai:ota:oucs:3800"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A letter to the people of Scotland, on the present state of the nation. By James Boswell, Esq"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3800.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8d9a147b-d1e4-5909-a1a5-685ca16d526e.json b/oaitestdata/clarin-oai_dc/SET_1/json/8d9a147b-d1e4-5909-a1a5-685ca16d526e.json
deleted file mode 100644
index 300b587d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8d9a147b-d1e4-5909-a1a5-685ca16d526e.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contributor": [
-        "Paskaleva, Elena",
-        "Piperidis, Stelios"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Bulgarian",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-228",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-228"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-228",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Bulgaria"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-228;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;English-Bulgarian INTERA;Paskaleva, Elena;Piperidis, Stelios;Alignment \u2013 TMX, structural \u2013 XCES, morphosyntactic \u2013 XCES, MTE tagset;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-228;bul;eng;downloadable_files_count: 0;Bulgaria;http://www.elda.org/article177.html#production",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8d9a147b-d1e4-5909-a1a5-685ca16d526e",
-    "notes": [
-        "Alignment \u2013 TMX, structural \u2013 XCES, morphosyntactic \u2013 XCES, MTE tagset"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-228"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "English-Bulgarian INTERA"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8d9a74a1-edd0-58ab-ad93-c7ec48c1acb4.json b/oaitestdata/clarin-oai_dc/SET_1/json/8d9a74a1-edd0-58ab-ad93-c7ec48c1acb4.json
deleted file mode 100644
index c9e7895b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8d9a74a1-edd0-58ab-ad93-c7ec48c1acb4.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Matteo Grella"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2894",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2894"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2894",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Matteo Grella"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11372/LRT-2630"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Grella, Matteo"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2894;2018-11-14T15:34:46Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Italian Content Words v3;Grella, Matteo;morphological dictionary;This resource is the third version of the Italian morphological dictionary for content words (http://hdl.handle.net/11372/LRT-2630), encoded in a JSON Lines format. Compared to the previous version, it contains some minor improvements.;2018;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-2894;ita;http://hdl.handle.net/11372/LRT-2630;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Matteo Grella",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8d9a74a1-edd0-58ab-ad93-c7ec48c1acb4",
-    "notes": [
-        "This resource is the third version of the Italian morphological dictionary for content words (http://hdl.handle.net/11372/LRT-2630), encoded in a JSON Lines format. Compared to the previous version, it contains some minor improvements."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2894"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphological dictionary"
-        }
-    ],
-    "title": [
-        "Italian Content Words v3"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8db24d9b-0ae8-571a-828e-198daaf905b5.json b/oaitestdata/clarin-oai_dc/SET_1/json/8db24d9b-0ae8-571a-828e-198daaf905b5.json
deleted file mode 100644
index 1c4ebe01..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8db24d9b-0ae8-571a-828e-198daaf905b5.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "less than 512 KB"
-    ],
-    "Language": [
-        "Middle English (1100-1500)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0581",
-    "MetadataAccess": [
-        "oai:ota:oucs:0581"
-    ],
-    "PublicationTimestamp": "1350-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1350"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Unknown"
-    ],
-    "fulltext": "oai:ota:oucs:0581;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0581.xml; Pearl / compiled by Lou Burnard;Unknown;1350-1399;text_and_corpus_linguistics;Poems -- England -- 14th century;enm;Oxford Text Archive, University of Oxford;less than 512 KB;Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8db24d9b-0ae8-571a-828e-198daaf905b5",
-    "oai_identifier": [
-        "oai:ota:oucs:0581"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- England -- th century"
-        }
-    ],
-    "title": [
-        " Pearl / compiled by Lou Burnard"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0581.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8dc9f173-6d79-59eb-9805-5ddb47041ee2.json b/oaitestdata/clarin-oai_dc/SET_1/json/8dc9f173-6d79-59eb-9805-5ddb47041ee2.json
deleted file mode 100644
index f80319e9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8dc9f173-6d79-59eb-9805-5ddb47041ee2.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "UW"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/462",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/462"
-    ],
-    "PID": "http://hdl.handle.net/11321/462",
-    "PublicationTimestamp": "2018-04-12T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "UW"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "PDT 2.0 License",
-        "http://ufal.mff.cuni.cz/pdt2.0/doc/pdt-guide/en/html/ch07.html",
-        "ACA"
-    ],
-    "author": [
-        "Ochma\u0144ski, Miko\u0142aj"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/462;2018-04-12T13:30:22Z;hdl_11321_3;hdl_11321_4;Blogi_zip;Ochma\u0144ski, Miko\u0142aj;blogi;ZIp blogowy;2018-04-12;corpus;http://hdl.handle.net/11321/462;pol;PDT 2.0 License;http://ufal.mff.cuni.cz/pdt2.0/doc/pdt-guide/en/html/ch07.html;ACA;text/plain; charset=utf-8;application/zip;application/zip;downloadable_files_count: 2;UW",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8dc9f173-6d79-59eb-9805-5ddb47041ee2",
-    "notes": [
-        "ZIp blogowy"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/462"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "blogi"
-        }
-    ],
-    "title": [
-        "Blogi_zip"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8e0c75e8-cf37-5679-b9ad-e7773bc6c05f.json b/oaitestdata/clarin-oai_dc/SET_1/json/8e0c75e8-cf37-5679-b9ad-e7773bc6c05f.json
deleted file mode 100644
index a3ef3067..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8e0c75e8-cf37-5679-b9ad-e7773bc6c05f.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "IPI PAN"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "downloadable_files_count: 10",
-        "application/vnd.oasis.opendocument.text",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/400",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/400"
-    ],
-    "PID": "http://hdl.handle.net/11321/400",
-    "PublicationTimestamp": "2017-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "IPI PAN"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Ludmila, Januszewska"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/400;2017-05-30T11:56:19Z;hdl_11321_3;hdl_11321_4;exerc corp;Ludmila, Januszewska;korpus;j\u0119zyk polski;warsztaty;Tworzenie korpusu na potrzeby warsztat\u00f3w DSpace;2017-05-30;corpus;http://hdl.handle.net/11321/400;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;text/plain;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;application/vnd.oasis.opendocument.text;text/plain;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;downloadable_files_count: 10;IPI PAN",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8e0c75e8-cf37-5679-b9ad-e7773bc6c05f",
-    "notes": [
-        "Tworzenie korpusu na potrzeby warsztat\u00f3w DSpace"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/400"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "korpus"
-        },
-        {
-            "name": "korpus"
-        },
-        {
-            "name": "warsztaty"
-        }
-    ],
-    "title": [
-        "exerc corp"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8e19bfe4-17a9-55d2-868c-7fc1bbbbbc4a.json b/oaitestdata/clarin-oai_dc/SET_1/json/8e19bfe4-17a9-55d2-868c-7fc1bbbbbc4a.json
deleted file mode 100644
index 606ec7a5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8e19bfe4-17a9-55d2-868c-7fc1bbbbbc4a.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3956",
-    "MetadataAccess": [
-        "oai:ota:oucs:3956"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pinkerton, John, 1758-1826."
-    ],
-    "fulltext": "oai:ota:oucs:3956;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3956.xml;Craigmillar Castle: An elegy.;Pinkerton, John, 1758-1826.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8e19bfe4-17a9-55d2-868c-7fc1bbbbbc4a",
-    "oai_identifier": [
-        "oai:ota:oucs:3956"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Craigmillar Castle: An elegy."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3956.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8e3aef92-1ecc-5f44-a50c-2ec755adb4e7.json b/oaitestdata/clarin-oai_dc/SET_1/json/8e3aef92-1ecc-5f44-a50c-2ec755adb4e7.json
deleted file mode 100644
index 72aad21b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8e3aef92-1ecc-5f44-a50c-2ec755adb4e7.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contributor": [
-        "Andersen, Gisle"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English",
-        "French",
-        "Norwegian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-373",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-373"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-373",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Norway"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-373;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;KIAP - Cultural Identity in Academic Prose;Andersen, Gisle;Comparable corpus, written, academic prose; 450 reviewed scientific papers; 3,2 million words; POS;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-373;eng;fra;nor;downloadable_files_count: 0;Norway;http://www.uib.no/kiap/index-e.htm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8e3aef92-1ecc-5f44-a50c-2ec755adb4e7",
-    "notes": [
-        "Comparable corpus, written, academic prose; 450 reviewed scientific papers; 3,2 million words; POS"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-373"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "KIAP - Cultural Identity in Academic Prose"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8e47115b-f33d-5165-87a5-9dd1d6e88e23.json b/oaitestdata/clarin-oai_dc/SET_1/json/8e47115b-f33d-5165-87a5-9dd1d6e88e23.json
deleted file mode 100644
index 8e4e4f6a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8e47115b-f33d-5165-87a5-9dd1d6e88e23.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=f28ca110617011e2a2aa782bcb074135f64c19719cc74120858255b6b81c3a17",
-    "MetadataAccess": [
-        "f28ca110617011e2a2aa782bcb074135f64c19719cc74120858255b6b81c3a17"
-    ],
-    "PublicationTimestamp": "2012-11-23T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "fulltext": "f28ca110617011e2a2aa782bcb074135f64c19719cc74120858255b6b81c3a17;2019-02-27T12:09:32Z;corpus;corpus:text;LogicalFormBankPT;The LogicalFormBankPT (Branco, 2009, and Branco et al., 2011) is a corpus of semantic dependencies of translated texts composed of 3,406 sentences and 44,598 tokens taken from the Wall Street Journal.\n\nThe LogicalFormBankPT is composed of MRS representations of each sentence\u00e2\u0080\u0099s semantic relations resulting from a previous semi-automatic analysis with a double-blind annotation followed by adjudication (see Branco and Costa, 2008, with a full description of the process). The resulting dataset contains one information level: semantic relations.\n\nThe main motivation behind the creation of this resource was to build a high quality data set with syntactic information that could support the development of a large set of automatic resources and tools for Portuguese for NLP studies.\n\nThe development of this resource started under the METANET4U project (at: http://metanet4u.eu/) whose main goal is to contribute to the establishment of a pan-European digital platform that makes available language resources and services, encompassing both datasets and software tools, for speech and language processing, and supports a new generation of exchange facilities for them. \n;2012-11-23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8e47115b-f33d-5165-87a5-9dd1d6e88e23",
-    "notes": [
-        "The LogicalFormBankPT (Branco, 2009, and Branco et al., 2011) is a corpus of semantic dependencies of translated texts composed of 3,406 sentences and 44,598 tokens taken from the Wall Street Journal.\n\nThe LogicalFormBankPT is composed of MRS representations of each sentence\u00e2\u0080\u0099s semantic relations resulting from a previous semi-automatic analysis with a double-blind annotation followed by adjudication (see Branco and Costa, 2008, with a full description of the process). The resulting dataset contains one information level: semantic relations.\n\nThe main motivation behind the creation of this resource was to build a high quality data set with syntactic information that could support the development of a large set of automatic resources and tools for Portuguese for NLP studies.\n\nThe development of this resource started under the METANET4U project (at: http://metanet4u.eu/) whose main goal is to contribute to the establishment of a pan-European digital platform that makes available language resources and services, encompassing both datasets and software tools, for speech and language processing, and supports a new generation of exchange facilities for them. \n"
-    ],
-    "oai_identifier": [
-        "f28ca110617011e2a2aa782bcb074135f64c19719cc74120858255b6b81c3a17"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "LogicalFormBankPT"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8e49565a-04dd-5b4f-97b1-bd079bc61c6c.json b/oaitestdata/clarin-oai_dc/SET_1/json/8e49565a-04dd-5b4f-97b1-bd079bc61c6c.json
deleted file mode 100644
index 12aabaf9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8e49565a-04dd-5b4f-97b1-bd079bc61c6c.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia J.K.Mci XX. Bazylian\u00f3w"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-578",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-578"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D28-3",
-    "PublicationTimestamp": "1793-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1793"
-    ],
-    "Publisher": [
-        "Drukarnia J.K.Mci XX. Bazylian\u00f3w"
-    ],
-    "RelatedIdentifier": [
-        "http://pbc.biaman.pl/Content/578"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "author": [
-        "Lachowski, Sebastian (1731-1794)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-578;2019-03-01T15:49:57Z;Kazania niedzielne. T. 1.;Lachowski, Sebastian (1731-1794);Kazania polskie 18 w.;ilo\u015b\u0107 skan\u00f3w: 377 ; sygn. St- 18;Drukarnia J.K.Mci XX. Bazylian\u00f3w;1793;starodruk;application/xml;clarind-uds:poldilemma-578;hdl:11858/00-246C-0000-0023-8D28-3;pol;lat;http://pbc.biaman.pl/Content/578;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8e49565a-04dd-5b4f-97b1-bd079bc61c6c",
-    "notes": [
-        "ilo\u015b\u0107 skan\u00f3w: 377 ; sygn. St- 18"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-578"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Kazania polskie w."
-        }
-    ],
-    "title": [
-        "Kazania niedzielne. T. 1."
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8e5b2651-68cb-5f85-bdde-5cdca5127f69.json b/oaitestdata/clarin-oai_dc/SET_1/json/8e5b2651-68cb-5f85-bdde-5cdca5127f69.json
deleted file mode 100644
index baaebcdc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8e5b2651-68cb-5f85-bdde-5cdca5127f69.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3112",
-    "MetadataAccess": [
-        "oai:ota:oucs:3112"
-    ],
-    "PublicationTimestamp": "1855-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1855"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gaskell, Elizabeth Cleghorn, 1810-1865"
-    ],
-    "fulltext": "oai:ota:oucs:3112;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3112.xml;The squire's story;Gaskell, Elizabeth Cleghorn, 1810-1865;not after: 1855;text_and_corpus_linguistics;Fiction -- Great Britain -- 19th century;Short stories -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8e5b2651-68cb-5f85-bdde-5cdca5127f69",
-    "oai_identifier": [
-        "oai:ota:oucs:3112"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- Great Britain -- th century"
-        },
-        {
-            "name": "Short stories -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "The squire's story"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3112.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8e88c916-dfff-58b6-aeca-f3ebee4b7da4.json b/oaitestdata/clarin-oai_dc/SET_1/json/8e88c916-dfff-58b6-aeca-f3ebee4b7da4.json
deleted file mode 100644
index 8f651edc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8e88c916-dfff-58b6-aeca-f3ebee4b7da4.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Czech",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1452",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1452"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1452",
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU General Public License, version 2",
-        "http://www.gnu.org/licenses/gpl-2.0.html",
-        "PUB"
-    ],
-    "author": [
-        "Jos\u00edfko, Michal"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1452;2018-07-02T22:05:53Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;KonText Web Demo;Jos\u00edfko, Michal;web service;corpus;parallel corpus;demo;An interactive web demo for querying selected \u00daFAL and LINDAT corpora. LINDAT/CLARIN KonText is a fork of \u00da\u010cNK KonText (https://github.com/czcorpus/kontext, maintained by Tom\u00e1\u0161 Mach\u00e1lek) that contains some modifications and additional features. Kontext, in turn, is a fork of the Bonito 2.68 python web interface to the corpus management tool Manatee (http://nlp.fi.muni.cz/trac/noske, created by Pavel Rychl\u00fd).;2014;toolService;http://hdl.handle.net/11234/1-1452;ces;eng;GNU General Public License, version 2;http://www.gnu.org/licenses/gpl-2.0.html;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://github.com/czcorpus/kontext",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8e88c916-dfff-58b6-aeca-f3ebee4b7da4",
-    "notes": [
-        "An interactive web demo for querying selected \u00daFAL and LINDAT corpora. LINDAT/CLARIN KonText is a fork of \u00da\u010cNK KonText (https://github.com/czcorpus/kontext, maintained by Tom\u00e1\u0161 Mach\u00e1lek) that contains some modifications and additional features. Kontext, in turn, is a fork of the Bonito 2.68 python web interface to the corpus management tool Manatee (http://nlp.fi.muni.cz/trac/noske, created by Pavel Rychl\u00fd)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1452"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "web service"
-        },
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "parallel corpus"
-        },
-        {
-            "name": "demo"
-        }
-    ],
-    "title": [
-        "KonText Web Demo"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8ebf26dd-961c-55b1-95e8-04d0c38f61eb.json b/oaitestdata/clarin-oai_dc/SET_1/json/8ebf26dd-961c-55b1-95e8-04d0c38f61eb.json
deleted file mode 100644
index d27d8d5c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8ebf26dd-961c-55b1-95e8-04d0c38f61eb.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Raf"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/vnd.oasis.opendocument.text",
-        "downloadable_files_count: 10",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/473",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/473"
-    ],
-    "PID": "http://hdl.handle.net/11321/473",
-    "PublicationTimestamp": "2018-05-18T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Raf"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "Raf, Raf"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/473;2018-05-19T08:42:30Z;hdl_11321_3;hdl_11321_4;Raf;Raf, Raf;polish;Lol;2018-05-18;corpus;http://hdl.handle.net/11321/473;Polish;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/vnd.oasis.opendocument.text;text/plain;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;downloadable_files_count: 10;Raf",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8ebf26dd-961c-55b1-95e8-04d0c38f61eb",
-    "notes": [
-        "Lol"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/473"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "polish"
-        }
-    ],
-    "title": [
-        "Raf"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8ec7165a-1485-51bf-bfce-612f535cb1d0.json b/oaitestdata/clarin-oai_dc/SET_1/json/8ec7165a-1485-51bf-bfce-612f535cb1d0.json
deleted file mode 100644
index 368bfb28..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8ec7165a-1485-51bf-bfce-612f535cb1d0.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5624",
-    "MetadataAccess": [
-        "oai:ota:oucs:5624"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Brooke, Henry, 1703?-1783."
-    ],
-    "fulltext": "oai:ota:oucs:5624;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5624.xml;The fool of quality: or, the history of Henry Earl of Moreland. In four volumes. By Mr. Brooke. [pt.4];Brooke, Henry, 1703?-1783.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8ec7165a-1485-51bf-bfce-612f535cb1d0",
-    "oai_identifier": [
-        "oai:ota:oucs:5624"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The fool of quality: or, the history of Henry Earl of Moreland. In four volumes. By Mr. Brooke. [pt.4]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5624.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8ecd1b5b-ee5d-584b-b454-ab8a5d67ec09.json b/oaitestdata/clarin-oai_dc/SET_1/json/8ecd1b5b-ee5d-584b-b454-ab8a5d67ec09.json
deleted file mode 100644
index f3ca86ca..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8ecd1b5b-ee5d-584b-b454-ab8a5d67ec09.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3440",
-    "MetadataAccess": [
-        "oai:ota:oucs:3440"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Macklin, Charles, 1697?-1797."
-    ],
-    "fulltext": "oai:ota:oucs:3440;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3440.xml;The true-born Irishman: or, Irish fine lady. A comedy of two acts. By Charles Macklin.;Macklin, Charles, 1697?-1797.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8ecd1b5b-ee5d-584b-b454-ab8a5d67ec09",
-    "oai_identifier": [
-        "oai:ota:oucs:3440"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The true-born Irishman: or, Irish fine lady. A comedy of two acts. By Charles Macklin."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3440.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8edec7e4-6edc-5c51-bc9f-10a5765e30ec.json b/oaitestdata/clarin-oai_dc/SET_1/json/8edec7e4-6edc-5c51-bc9f-10a5765e30ec.json
deleted file mode 100644
index 9e1ec530..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8edec7e4-6edc-5c51-bc9f-10a5765e30ec.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1030",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1030"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1030",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1030;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;L1 Acquisition Anke Jolink;Language Acquisition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1030;nld;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI14321%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8edec7e4-6edc-5c51-bc9f-10a5765e30ec",
-    "notes": [
-        "Language Acquisition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1030"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "L1 Acquisition Anke Jolink"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8ef1a92f-ec47-570a-9ee6-1664f5163cd1.json b/oaitestdata/clarin-oai_dc/SET_1/json/8ef1a92f-ec47-570a-9ee6-1664f5163cd1.json
deleted file mode 100644
index 9483377e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8ef1a92f-ec47-570a-9ee6-1664f5163cd1.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1405",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1405"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1405",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1405;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;calcular_p_cue_class;Statistical analysis service: It calculates P(cue|class): probability of seeing a linguistic cue given a lexical class. This probability is computed given the occurrences of cues in a corpus (codified in the signatures file) and the information of belonging or not belonging of these words to different classes (codified in indicators file).\nThe probability is computed for each studied cue in the signatures file and for each class in the indicators file.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1405;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8ef1a92f-ec47-570a-9ee6-1664f5163cd1",
-    "notes": [
-        "Statistical analysis service: It calculates P(cue|class): probability of seeing a linguistic cue given a lexical class. This probability is computed given the occurrences of cues in a corpus (codified in the signatures file) and the information of belonging or not belonging of these words to different classes (codified in indicators file).\nThe probability is computed for each studied cue in the signatures file and for each class in the indicators file."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1405"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "calcular_p_cue_class"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8f182706-134a-5cf5-a032-b6f59e6fbb0b.json b/oaitestdata/clarin-oai_dc/SET_1/json/8f182706-134a-5cf5-a032-b6f59e6fbb0b.json
deleted file mode 100644
index 30f5335d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8f182706-134a-5cf5-a032-b6f59e6fbb0b.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "National Endowment for the Humanities",
-        "di Paolo Healey, Antonette",
-        "Social Sciences and Humanities Research Council of Canada"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(288 files : ca. 66.7 MB)"
-    ],
-    "Language": [
-        "Old English (ca. 450-1100)",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2488",
-    "MetadataAccess": [
-        "oai:ota:oucs:2488"
-    ],
-    "PublicationTimestamp": "1150-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1150"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Linguistic corpora"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:2488;2018-02-28T10:49:17Z;http://ota.ox.ac.uk/headers/2488.xml;Dictionary of Old English Corpus in Electronic Form (DOEC);Old English Corpus;600-1150;text_and_corpus_linguistics;English language--Old English, ca. 450-1100;English language--Old English, ca. 450-1100--Texts;Linguistic analysis (Linguistics);ang;lat;The Dictionary of Old English Corpus is a complete record of surviving Old English except for some variant manuscripts of individual texts. There are 3037 texts in the corpus, represented in two formats on the CD-ROM: Standard Generalized Markup Language (SGML) and Hyper Text Markup Language (HTML). ;Oxford Text Archive, University of Oxford;di Paolo Healey, Antonette;Social Sciences and Humanities Research Council of Canada;National Endowment for the Humanities;di Paolo Healey, Antonette;text/sgml;(288 files : ca. 66.7 MB);Text;Linguistic corpora;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8f182706-134a-5cf5-a032-b6f59e6fbb0b",
-    "notes": [
-        "The Dictionary of Old English Corpus is a complete record of surviving Old English except for some variant manuscripts of individual texts. There are 3037 texts in the corpus, represented in two formats on the CD-ROM: Standard Generalized Markup Language (SGML) and Hyper Text Markup Language (HTML). "
-    ],
-    "oai_identifier": [
-        "oai:ota:oucs:2488"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English language--Old English"
-        },
-        {
-            "name": "ca. -"
-        },
-        {
-            "name": "English language--Old English"
-        },
-        {
-            "name": "ca. ---Texts"
-        },
-        {
-            "name": "Linguistic analysis Linguistics"
-        }
-    ],
-    "title": [
-        "Dictionary of Old English Corpus in Electronic Form (DOEC)",
-        "Old English Corpus"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2488.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8f2c427c-17cc-5495-8163-4ad5529c0c34.json b/oaitestdata/clarin-oai_dc/SET_1/json/8f2c427c-17cc-5495-8163-4ad5529c0c34.json
deleted file mode 100644
index faee607a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8f2c427c-17cc-5495-8163-4ad5529c0c34.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Matteo Grella"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2893",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2893"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2893",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Matteo Grella"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11372/LRT-2629"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Grella, Matteo"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2893;2018-11-14T15:34:38Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Italian Function Words v3;Grella, Matteo;morphological dictionary;function words;This dictionary is the third version of 11372/LRT-2288, a curated list of Italian function words in a JSON Lines format text file, particularly useful for tasks such as part of speech tagging or syntactic parsing. Compared to the previous release, this version includes some minor improvements.;2018;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-2893;ita;http://hdl.handle.net/11372/LRT-2629;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 1;Matteo Grella",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8f2c427c-17cc-5495-8163-4ad5529c0c34",
-    "notes": [
-        "This dictionary is the third version of 11372/LRT-2288, a curated list of Italian function words in a JSON Lines format text file, particularly useful for tasks such as part of speech tagging or syntactic parsing. Compared to the previous release, this version includes some minor improvements."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2893"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphological dictionary"
-        },
-        {
-            "name": "function words"
-        }
-    ],
-    "title": [
-        "Italian Function Words v3"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8f468dd4-9ef7-5ca7-92f6-52f45a85598b.json b/oaitestdata/clarin-oai_dc/SET_1/json/8f468dd4-9ef7-5ca7-92f6-52f45a85598b.json
deleted file mode 100644
index bde98146..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8f468dd4-9ef7-5ca7-92f6-52f45a85598b.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "Fondazione Bruno Kessler, Trento, Italy"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 3",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "English",
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1632",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1632"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1632",
-    "PublicationTimestamp": "2016-02-21T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Fondazione Bruno Kessler, Trento, Italy"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/H2020/645452"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "AGREEMENT ON THE USE OF DATA IN QT21 APE Task",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21",
-        "PUB"
-    ],
-    "author": [
-        "Turchi, Marco",
-        "Chatterjee, Rajen",
-        "Negri, Matteo"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1632;2017-09-04T10:29:30Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;WMT16 APE Shared Task Data;Turchi, Marco;Chatterjee, Rajen;Negri, Matteo;machine translation;machine learning;automatic postediting;shared task;Training, development and text data (the same used for the Sentence-level Quality Estimation task) consist in English-German triplets (source, target and post-edit) belonging to the IT domain and already tokenized.\r\nTraining and development respectively contain 12,000 and 1,000 triplets, while the test set 2,000 instances. All data is provided by the EU project QT21 (http://www.qt21.eu/).;2016-02-21;corpus;http://hdl.handle.net/11372/LRT-1632;eng;deu;info:eu-repo/grantAgreement/EC/H2020/645452;AGREEMENT ON THE USE OF DATA IN QT21 APE Task;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21;PUB;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 3;Fondazione Bruno Kessler, Trento, Italy;http://www.statmt.org/wmt16/ape-task.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8f468dd4-9ef7-5ca7-92f6-52f45a85598b",
-    "notes": [
-        "Training, development and text data (the same used for the Sentence-level Quality Estimation task) consist in English-German triplets (source, target and post-edit) belonging to the IT domain and already tokenized.\r\nTraining and development respectively contain 12,000 and 1,000 triplets, while the test set 2,000 instances. All data is provided by the EU project QT21 (http://www.qt21.eu/)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1632"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "machine learning"
-        },
-        {
-            "name": "automatic postediting"
-        },
-        {
-            "name": "shared task"
-        }
-    ],
-    "title": [
-        "WMT16 APE Shared Task Data"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8f5935a8-c30d-517a-a479-950c76a47374.json b/oaitestdata/clarin-oai_dc/SET_1/json/8f5935a8-c30d-517a-a479-950c76a47374.json
deleted file mode 100644
index 16f3fb2c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8f5935a8-c30d-517a-a479-950c76a47374.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 988 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2116",
-    "MetadataAccess": [
-        "oai:ota:oucs:2116"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Bront\u00c3\u00ab, Anne, 1820-1849"
-    ],
-    "fulltext": "oai:ota:oucs:2116;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/2116.xml;The tenant of Wildfell Hall / by Anne Bront\u00c3\u00ab;Bront\u00c3\u00ab, Anne, 1820-1849;text_and_corpus_linguistics;Novels -- Great Britain -- 19th century;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 988 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8f5935a8-c30d-517a-a479-950c76a47374",
-    "oai_identifier": [
-        "oai:ota:oucs:2116"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Novels -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "The tenant of Wildfell Hall / by Anne Bront\u00c3\u00ab"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2116.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8f712b0c-f79f-5004-944e-7d4c9ab6d44d.json b/oaitestdata/clarin-oai_dc/SET_1/json/8f712b0c-f79f-5004-944e-7d4c9ab6d44d.json
deleted file mode 100644
index b090a18a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8f712b0c-f79f-5004-944e-7d4c9ab6d44d.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=2a17d622abcd11e1a404080027e73ea242399e2114844f63896f2f92dd31233e",
-    "MetadataAccess": [
-        "2a17d622abcd11e1a404080027e73ea242399e2114844f63896f2f92dd31233e"
-    ],
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "2a17d622abcd11e1a404080027e73ea242399e2114844f63896f2f92dd31233e;2019-02-27T12:08:46Z;corpus;corpus:text;CINTIL-TreeBank;The CINTIL-TreeBank (Branco et al., 2011) is a corpus of syntactic constituency trees of Portuguese texts composed of 10,039 sentences and 110,166 tokens taken from different sources and domains: news (8,861 sentences; 101,430 tokens), novels (399 sentences; 3,082 tokens). In addition, there are 779 sentences (5,654 tokens) that are used for regression testing of the computational grammar that supported the annotation of the corpus.\nFor the creation of this TreeBank we adopted a semi-automatic analysis with a double-blind annotation followed by adjudication. The resulting dataset contains one information level: phrase constituency.\nThe main motivation behind the creation of this resource was to build a high quality data set with syntactic information that could support the development of a large set of automatic resources and tools for Portuguese for NLP studies.;2015-12-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8f712b0c-f79f-5004-944e-7d4c9ab6d44d",
-    "notes": [
-        "The CINTIL-TreeBank (Branco et al., 2011) is a corpus of syntactic constituency trees of Portuguese texts composed of 10,039 sentences and 110,166 tokens taken from different sources and domains: news (8,861 sentences; 101,430 tokens), novels (399 sentences; 3,082 tokens). In addition, there are 779 sentences (5,654 tokens) that are used for regression testing of the computational grammar that supported the annotation of the corpus.\nFor the creation of this TreeBank we adopted a semi-automatic analysis with a double-blind annotation followed by adjudication. The resulting dataset contains one information level: phrase constituency.\nThe main motivation behind the creation of this resource was to build a high quality data set with syntactic information that could support the development of a large set of automatic resources and tools for Portuguese for NLP studies."
-    ],
-    "oai_identifier": [
-        "2a17d622abcd11e1a404080027e73ea242399e2114844f63896f2f92dd31233e"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "CINTIL-TreeBank"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8f7f0632-edc7-514f-a053-08fb12b7b220.json b/oaitestdata/clarin-oai_dc/SET_1/json/8f7f0632-edc7-514f-a053-08fb12b7b220.json
deleted file mode 100644
index e8e9000c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8f7f0632-edc7-514f-a053-08fb12b7b220.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5288",
-    "MetadataAccess": [
-        "oai:ota:oucs:5288"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Bickerstaff, Isaac."
-    ],
-    "fulltext": "oai:ota:oucs:5288;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5288.xml;The famous prophesie of the white king and the dead man explain'd to the present times ... By Isaac Bickerstaffe, esq;Bickerstaff, Isaac.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8f7f0632-edc7-514f-a053-08fb12b7b220",
-    "oai_identifier": [
-        "oai:ota:oucs:5288"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The famous prophesie of the white king and the dead man explain'd to the present times ... By Isaac Bickerstaffe, esq"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5288.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8f971db9-ec86-596b-88e9-507ec823c28c.json b/oaitestdata/clarin-oai_dc/SET_1/json/8f971db9-ec86-596b-88e9-507ec823c28c.json
deleted file mode 100644
index 139cf601..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8f971db9-ec86-596b-88e9-507ec823c28c.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, Dept. of Swedish Language, G\u00f6teborg University"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1304",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1304"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1304",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, Dept. of Swedish Language, G\u00f6teborg University"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Sweden"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Forsberg, Markus",
-        "Ranta, Aarne"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1304;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Extract;Forsberg, Markus;Ranta, Aarne;morphology extraction;Extract is a tool for supervised morphological lexicon extraction from raw text data.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1304;downloadable_files_count: 0;Sweden;Spr\u00e5kbanken, Dept. of Swedish Language, G\u00f6teborg University;http://www.cs.chalmers.se/~markus/extract/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8f971db9-ec86-596b-88e9-507ec823c28c",
-    "notes": [
-        "Extract is a tool for supervised morphological lexicon extraction from raw text data."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1304"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphology extraction"
-        }
-    ],
-    "title": [
-        "Extract"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8f9c2869-6d78-5caa-9cd6-da48e9f766a8.json b/oaitestdata/clarin-oai_dc/SET_1/json/8f9c2869-6d78-5caa-9cd6-da48e9f766a8.json
deleted file mode 100644
index 8afa016d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8f9c2869-6d78-5caa-9cd6-da48e9f766a8.json
+++ /dev/null
@@ -1,102 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Arabic",
-        "Bulgarian",
-        "Bengali",
-        "Catalan",
-        "Czech",
-        "Danish",
-        "German",
-        "Modern Greek (1453-)",
-        "English",
-        "Spanish",
-        "Estonian",
-        "Basque",
-        "Persian",
-        "Finnish",
-        "Ancient Greek (to 1453)",
-        "Hebrew",
-        "Hindi",
-        "Croatian",
-        "Japanese",
-        "Multiple languages",
-        "Portuguese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1465",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1465"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1465",
-    "PublicationTimestamp": "2014-12-05T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/610516"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Artistic License (Perl) 1.0",
-        "http://opensource.org/licenses/Artistic-Perl-1.0",
-        "PUB"
-    ],
-    "author": [
-        "Zeman, Daniel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1465;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Lingua::Interset 2.026;Zeman, Daniel;morphology;part of speech;conversion;tagset;Lingua::Interset is a universal morphosyntactic feature set to which all tagsets of all corpora/languages can be mapped. Version 2.026 covers 37 different tagsets of 21 languages. Limited support of the older drivers for other languages (which are not included in this package but are available for download elsewhere) is also available; these will be fully ported to Interset 2 in future.\r\n\r\nInterset is implemented as Perl libraries. It is also available via CPAN.;2014-12-05;toolService;http://hdl.handle.net/11234/1-1465;ara;bul;ben;cat;ces;dan;deu;ell;eng;spa;est;eus;fas;fin;grc;heb;hin;hrv;jpn;mul;por;info:eu-repo/grantAgreement/EC/FP7/610516;Artistic License (Perl) 1.0;http://opensource.org/licenses/Artistic-Perl-1.0;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics;http://metacpan.org/release/ZEMAN/Lingua-Interset-2.026",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8f9c2869-6d78-5caa-9cd6-da48e9f766a8",
-    "notes": [
-        "Lingua::Interset is a universal morphosyntactic feature set to which all tagsets of all corpora/languages can be mapped. Version 2.026 covers 37 different tagsets of 21 languages. Limited support of the older drivers for other languages (which are not included in this package but are available for download elsewhere) is also available; these will be fully ported to Interset 2 in future.\r\n\r\nInterset is implemented as Perl libraries. It is also available via CPAN."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1465"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "part speech"
-        },
-        {
-            "name": "conversion"
-        },
-        {
-            "name": "tagset"
-        }
-    ],
-    "title": [
-        "Lingua::Interset 2.026"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8fb54bf6-f9fe-5ab7-acc0-b79d2809ccb2.json b/oaitestdata/clarin-oai_dc/SET_1/json/8fb54bf6-f9fe-5ab7-acc0-b79d2809ccb2.json
deleted file mode 100644
index 119d093a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8fb54bf6-f9fe-5ab7-acc0-b79d2809ccb2.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2820",
-    "MetadataAccess": [
-        "oai:ota:oucs:2820"
-    ],
-    "PublicationTimestamp": "1735-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1735"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2820;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2820.xml;Drapier's Letters VI, To the Lord Chancellor Middleton;Swift, Jonathan, 1667-1745;1735;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8fb54bf6-f9fe-5ab7-acc0-b79d2809ccb2",
-    "oai_identifier": [
-        "oai:ota:oucs:2820"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Drapier's Letters VI, To the Lord Chancellor Middleton"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2820.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8fc2dd86-4d25-5252-8d52-3bdcce8890fd.json b/oaitestdata/clarin-oai_dc/SET_1/json/8fc2dd86-4d25-5252-8d52-3bdcce8890fd.json
deleted file mode 100644
index 2b48f776..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8fc2dd86-4d25-5252-8d52-3bdcce8890fd.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "text/xml",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Lule Sami"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/111",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/111"
-    ],
-    "PID": "http://hdl.handle.net/11509/111",
-    "PublicationTimestamp": "2015-10-17T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "The Divvun group at UiT The Arctic University of Norway",
-        "Giellatekno - Saami Language Technology, UiT The Arctic University of Norway"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/111;2016-09-06T12:57:08Z;hdl_11509_1;hdl_11509_2;Lule Saami N-grams;Giellatekno - Saami Language Technology, UiT The Arctic University of Norway;The Divvun group at UiT The Arctic University of Norway;Lule Saami;1-gram;2-gram;3-gram;Language Model;The Lule Saami N-gram data set is work done by the Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language community. In particular, Ciprian-Virgil Gerstenberger compiled the data set from the entire SIKOR Lule Saami corpus version 2015-10-10. The length of the N-grams ranges from unigrams (single words) to tri-grams (112877 unigrams, 552639 bigrams, 164286 trigrams). Only N-grams within sentences have been counted. The data format follows the ARPA backoff N-gram models and has been generated using SRILM, the SRI Language Modeling Toolkit (http://www.speech.sri.com/projects/srilm/). Since the N-grams have been derived automatically, they may contain wrong values. In case you find any errors the creators would appreciate your feedback sent to giellatekno@uit.no and feedback@divvun.no. Please note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata).;2015-10-17;corpus;http://hdl.handle.net/11509/111;smj;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;application/zip;text/plain; charset=utf-8;text/xml;downloadable_files_count: 1;Giellatekno - Saami Language Technology;http://giellatekno.uit.no/index.eng.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8fc2dd86-4d25-5252-8d52-3bdcce8890fd",
-    "notes": [
-        "The Lule Saami N-gram data set is work done by the Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language community. In particular, Ciprian-Virgil Gerstenberger compiled the data set from the entire SIKOR Lule Saami corpus version 2015-10-10. The length of the N-grams ranges from unigrams (single words) to tri-grams (112877 unigrams, 552639 bigrams, 164286 trigrams). Only N-grams within sentences have been counted. The data format follows the ARPA backoff N-gram models and has been generated using SRILM, the SRI Language Modeling Toolkit (http://www.speech.sri.com/projects/srilm/). Since the N-grams have been derived automatically, they may contain wrong values. In case you find any errors the creators would appreciate your feedback sent to giellatekno@uit.no and feedback@divvun.no. Please note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata)."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/111"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Lule Saami"
-        },
-        {
-            "name": "-gram"
-        },
-        {
-            "name": "-gram"
-        },
-        {
-            "name": "-gram"
-        },
-        {
-            "name": "Language Model"
-        }
-    ],
-    "title": [
-        "Lule Saami N-grams"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/8fc9d3f8-9dae-5c28-b22e-876b74eaf55a.json b/oaitestdata/clarin-oai_dc/SET_1/json/8fc9d3f8-9dae-5c28-b22e-876b74eaf55a.json
deleted file mode 100644
index aa563c3b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/8fc9d3f8-9dae-5c28-b22e-876b74eaf55a.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "A"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1636",
-    "MetadataAccess": [
-        "oai:ota:oucs:1636"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Scott, Walter"
-    ],
-    "fulltext": "oai:ota:oucs:1636;2018-04-16T15:30:51Z;http://ota.ox.ac.uk/headers/1636.xml;The antiquary;Scott, Walter;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;A;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8fc9d3f8-9dae-5c28-b22e-876b74eaf55a",
-    "oai_identifier": [
-        "oai:ota:oucs:1636"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The antiquary"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1636.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9013a359-5317-5687-ab16-3f2b2a78000a.json b/oaitestdata/clarin-oai_dc/SET_1/json/9013a359-5317-5687-ab16-3f2b2a78000a.json
deleted file mode 100644
index 6ce129e5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9013a359-5317-5687-ab16-3f2b2a78000a.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5307",
-    "MetadataAccess": [
-        "oai:ota:oucs:5307"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Beilby, Ralph, 1743-1817."
-    ],
-    "fulltext": "oai:ota:oucs:5307;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5307.xml;History of British birds: The figures engraved on wood by T. Bewick. Vol. I. Containing the history and description of land birds. [pt.1];Beilby, Ralph, 1743-1817.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9013a359-5317-5687-ab16-3f2b2a78000a",
-    "oai_identifier": [
-        "oai:ota:oucs:5307"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "History of British birds: The figures engraved on wood by T. Bewick. Vol. I. Containing the history and description of land birds. [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5307.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9020bdfa-9357-5530-8c3a-65eee6b512cb.json b/oaitestdata/clarin-oai_dc/SET_1/json/9020bdfa-9357-5530-8c3a-65eee6b512cb.json
deleted file mode 100644
index 3d15daaa..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9020bdfa-9357-5530-8c3a-65eee6b512cb.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Burnard, Lou"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 158 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1205",
-    "MetadataAccess": [
-        "oai:ota:oucs:1205"
-    ],
-    "PublicationTimestamp": "1606-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1606"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Marston, John, 1575?-1634"
-    ],
-    "fulltext": "oai:ota:oucs:1205;2018-03-05T13:22:36Z;http://ota.ox.ac.uk/headers/1205.xml;The fawn / John Marston;Marston, John, 1575?-1634;1606;text_and_corpus_linguistics;English drama -- 17th century;eng;Oxford Text Archive, University of Oxford;Burnard, Lou;(1 file : ca. 158 KB);Text;Plays;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9020bdfa-9357-5530-8c3a-65eee6b512cb",
-    "oai_identifier": [
-        "oai:ota:oucs:1205"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- th century"
-        }
-    ],
-    "title": [
-        "The fawn / John Marston"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1205.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/902800bb-a7d4-529a-a086-daff51bdb8c3.json b/oaitestdata/clarin-oai_dc/SET_1/json/902800bb-a7d4-529a-a086-daff51bdb8c3.json
deleted file mode 100644
index 701ba58a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/902800bb-a7d4-529a-a086-daff51bdb8c3.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "text/xml",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Northern Sami"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/100",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/100"
-    ],
-    "PID": "http://hdl.handle.net/11509/100",
-    "PublicationTimestamp": "2015-10-10T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "CC",
-        "http://creativecommons.org/licenses/by/3.0/"
-    ],
-    "author": [
-        "The Divvun group at UiT The Arctic University of Norway",
-        "Giellatekno - Saami Language Technology, UiT The Arctic University of Norway"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/100;2016-09-06T12:49:24Z;hdl_11509_1;hdl_11509_2;SIKOR North Saami free corpus;Giellatekno - Saami Language Technology, UiT The Arctic University of Norway;The Divvun group at UiT The Arctic University of Norway;Monolingual Corpus;Text Corpus;North Saami;Dependency Tree Bank;The SIKOR North Saami free corpus is a monolingual text corpus of North Saami that contains administrative, law, religious, non-fiction, fiction, and science texts. It is work done by the Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language community. In particular, the following colleagues have contributed to the creation of the ressource: Ciprian Gerstenberger, B\u00f8rre Gaup, Lene Antonsen, Thomas Omma, and Trond Trosterud. Linguistically, the data set (746,329 sentences; 8,936,437 tokens) features word form, lemma, morphosyntactic analysis, and dependency relations between tokens. The corpus has been automatically processed and linguistically analyzed with the Giellatekno/Divvun tools. Therefore, it may contain wrong annotations. In case you find any errors the creators would appreciate your feedback sent to giellatekno@uit.no and feedback@divvun.no.\r\nPlease note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata).;2015-10-10;corpus;http://hdl.handle.net/11509/100;sme;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);CC;http://creativecommons.org/licenses/by/3.0/;application/zip;text/plain; charset=utf-8;text/xml;downloadable_files_count: 1;Giellatekno - Saami Language Technology;http://giellatekno.uit.no/index.eng.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "902800bb-a7d4-529a-a086-daff51bdb8c3",
-    "notes": [
-        "The SIKOR North Saami free corpus is a monolingual text corpus of North Saami that contains administrative, law, religious, non-fiction, fiction, and science texts. It is work done by the Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language community. In particular, the following colleagues have contributed to the creation of the ressource: Ciprian Gerstenberger, B\u00f8rre Gaup, Lene Antonsen, Thomas Omma, and Trond Trosterud. Linguistically, the data set (746,329 sentences; 8,936,437 tokens) features word form, lemma, morphosyntactic analysis, and dependency relations between tokens. The corpus has been automatically processed and linguistically analyzed with the Giellatekno/Divvun tools. Therefore, it may contain wrong annotations. In case you find any errors the creators would appreciate your feedback sent to giellatekno@uit.no and feedback@divvun.no.\r\nPlease note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata)."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/100"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Monolingual Corpus"
-        },
-        {
-            "name": "Text Corpus"
-        },
-        {
-            "name": "North Saami"
-        },
-        {
-            "name": "Dependency Tree Bank"
-        }
-    ],
-    "title": [
-        "SIKOR North Saami free corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/90386835-cdd9-5458-b7de-27a3d39dd5d5.json b/oaitestdata/clarin-oai_dc/SET_1/json/90386835-cdd9-5458-b7de-27a3d39dd5d5.json
deleted file mode 100644
index f6eff990..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/90386835-cdd9-5458-b7de-27a3d39dd5d5.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/97",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/97"
-    ],
-    "PID": "http://hdl.handle.net/10794/97",
-    "PublicationTimestamp": "2013-03-06T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/97;2017-10-25T11:41:44Z;hdl_10794_1;hdl_10794_2;Blog mix 2003 (2017-02-17);Bloggmix 2003 (2017-02-17);n/a, n/a;Swedish;Blog;The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.;Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat.;2013-03-06;corpus;http://hdl.handle.net/10794/97;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/bloggmix2003",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "90386835-cdd9-5458-b7de-27a3d39dd5d5",
-    "notes": [
-        "The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.",
-        "Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/97"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Blog"
-        }
-    ],
-    "title": [
-        "Blog mix 2003 (2017-02-17)",
-        "Bloggmix 2003 (2017-02-17)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/90398404-7d50-54c1-806e-b1bba9d04704.json b/oaitestdata/clarin-oai_dc/SET_1/json/90398404-7d50-54c1-806e-b1bba9d04704.json
deleted file mode 100644
index 1858ef86..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/90398404-7d50-54c1-806e-b1bba9d04704.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Burnard, Lou"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 256 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1049",
-    "MetadataAccess": [
-        "oai:ota:oucs:1049"
-    ],
-    "PublicationTimestamp": "1675-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1675"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Wycherley, William, 1640-1716"
-    ],
-    "fulltext": "oai:ota:oucs:1049;2018-03-05T10:56:22Z;http://ota.ox.ac.uk/headers/1049.xml;The country\u00e2\u0080\u0093wife : a comedy, acted at the Theatre Royal, 1675 / written by Mr. Wycherley;Wycherley, William, 1640-1716;1675;text_and_corpus_linguistics;English drama -- Restoration, 1660-1700;English drama (Comedy);Oxford Text Archive, University of Oxford;Burnard, Lou;text/sgml;(1 file : ca. 256 KB);Text;Plays;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "90398404-7d50-54c1-806e-b1bba9d04704",
-    "oai_identifier": [
-        "oai:ota:oucs:1049"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- Restoration"
-        },
-        {
-            "name": "English drama Comedy"
-        }
-    ],
-    "title": [
-        "The country\u00e2\u0080\u0093wife : a comedy, acted at the Theatre Royal, 1675 / written by Mr. Wycherley"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1049.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/903ea7b2-27ff-547d-9b8d-c47625570527.json b/oaitestdata/clarin-oai_dc/SET_1/json/903ea7b2-27ff-547d-9b8d-c47625570527.json
deleted file mode 100644
index 63b7ad70..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/903ea7b2-27ff-547d-9b8d-c47625570527.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Mniszek"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/105",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/105"
-    ],
-    "PID": "http://hdl.handle.net/11321/105",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Mniszek"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Mniszek, Mniszek"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/105;2015-04-08T14:08:10Z;hdl_11321_3;hdl_11321_4;MWE Mniszek, Gehenna czyli dzieje nieszcz\u0119\u015bliwej mi\u0142o\u015bci, Cz\u0119\u015b\u0107 pierwsza, Na szynach;Mniszek, Mniszek;Mniszek;2015-04-08;corpus;http://hdl.handle.net/11321/105;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain; charset=utf-8;downloadable_files_count: 1;Mniszek",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "903ea7b2-27ff-547d-9b8d-c47625570527",
-    "notes": [
-        "Mniszek"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/105"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Mniszek, Gehenna czyli dzieje nieszcz\u0119\u015bliwej mi\u0142o\u015bci, Cz\u0119\u015b\u0107 pierwsza, Na szynach"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9040b7e5-dacd-501f-b417-8283131ea4cd.json b/oaitestdata/clarin-oai_dc/SET_1/json/9040b7e5-dacd-501f-b417-8283131ea4cd.json
deleted file mode 100644
index 530eabb7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9040b7e5-dacd-501f-b417-8283131ea4cd.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Amsterdam Centre for Language and Communication, University of Amsterdam"
-    ],
-    "Contributor": [
-        "Weenink, David",
-        "Boersma, Paul"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-289",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-289"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-289",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Amsterdam Centre for Language and Communication, University of Amsterdam"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-289;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Praat;Boersma, Paul;Weenink, David;a program for doing phonetics by computer;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-289;downloadable_files_count: 0;Netherlands (the);Amsterdam Centre for Language and Communication, University of Amsterdam;http://www.praat.org",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9040b7e5-dacd-501f-b417-8283131ea4cd",
-    "notes": [
-        "a program for doing phonetics by computer"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-289"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Praat"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9058f0ff-c914-5505-8861-e632f51fa9d9.json b/oaitestdata/clarin-oai_dc/SET_1/json/9058f0ff-c914-5505-8861-e632f51fa9d9.json
deleted file mode 100644
index b355b53e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9058f0ff-c914-5505-8861-e632f51fa9d9.json
+++ /dev/null
@@ -1,95 +0,0 @@
-{
-    "Contact": [
-        "ZRC SAZU"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1122",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1122"
-    ],
-    "PID": "http://hdl.handle.net/11356/1122",
-    "PublicationTimestamp": "2015-06-12T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "ZRC SAZU"
-    ],
-    "RelatedIdentifier": [
-        "http://centerslo.si/wp-content/uploads/2015/11/34_1-_Ahacic.pdf"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Legan Ravnikar, Andreja",
-        "Jelov\u0161ek, Alenka",
-        "Trojar, Mitja",
-        "Aha\u010di\u010d, Kozma",
-        "Narat, Jo\u017eica",
-        "\u017daucer, Rok",
-        "Furlan, Metka",
-        "\u010cepar, Metod",
-        "Maru\u0161i\u010d, Franc",
-        "Dobrovoljc, Helena",
-        "Mer\u0161e, Majda"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1122;2017-06-17T20:43:45Z;hdl_11356_1023;hdl_11356_1024;Slovene Grammars and Orthographic Dictionaries;Aha\u010di\u010d, Kozma;Dobrovoljc, Helena;Legan Ravnikar, Andreja;Mer\u0161e, Majda;Furlan, Metka;Narat, Jo\u017eica;Maru\u0161i\u010d, Franc;\u017daucer, Rok;Jelov\u0161ek, Alenka;\u010cepar, Metod;Trojar, Mitja;Slovene grammars;Slovene orthography;historical grammars;history of linguistics;syntactic description;The database contains 25 comprehensive and 25 basic descriptions of 139 Slovene grammars and orthographic dictionaries in book or web format in the period from 1584 to 2015.;2015-06-12;lexicalConceptualResource;http://hdl.handle.net/11356/1122;slv;http://centerslo.si/wp-content/uploads/2015/11/34_1-_Ahacic.pdf;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;ZRC SAZU;http://www.fran.si/slovnice-in-pravopisi",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9058f0ff-c914-5505-8861-e632f51fa9d9",
-    "notes": [
-        "The database contains 25 comprehensive and 25 basic descriptions of 139 Slovene grammars and orthographic dictionaries in book or web format in the period from 1584 to 2015."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1122"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Slovene grammars"
-        },
-        {
-            "name": "Slovene orthography"
-        },
-        {
-            "name": "historical grammars"
-        },
-        {
-            "name": "history linguistics"
-        },
-        {
-            "name": "syntactic description"
-        }
-    ],
-    "title": [
-        "Slovene Grammars and Orthographic Dictionaries"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/906f467c-b50e-5381-af4e-32311d192323.json b/oaitestdata/clarin-oai_dc/SET_1/json/906f467c-b50e-5381-af4e-32311d192323.json
deleted file mode 100644
index b71b333c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/906f467c-b50e-5381-af4e-32311d192323.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "No linguistic content"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2372",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2372"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2372",
-    "PublicationTimestamp": "2017-08-25T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "https://ufal.mff.cuni.cz/~hajicj/2017/docs/icdar2017_CAMERA.pdf"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Haji\u010d jr., Jan"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2372;2018-04-03T17:20:02Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;MUSCIMA++;Haji\u010d jr., Jan;Optical Music Recognition;Music Notation;Graph-Based Representation;Symbol Detection;MUSCIMA++ is a dataset of handwritten music notation for musical symbol detection. It contains 91255 symbols, consisting of both notation primitives and higher-level notation objects, such as key signatures or time signatures. There are 23352 notes in the dataset, of which 21356 have a full notehead, 1648 have an empty notehead, and 348 are grace notes. For each annotated object in an image, we provide both the bounding box, and a pixel mask that defines exactly which pixels within the bounding box belong to the given object. Composite constructions, such as notes, are captured through explicitly annotated relationships of the notation primitives (noteheads, stems, beams...). This way, the annotation provides an explicit bridge between the low-level and high-level symbols described in Optical Music Recognition literature.\r\n\r\nMUSCIMA++ has annotations for 140 images from the CVC-MUSCIMA dataset [2], used for handwritten music notation writer identification and staff removal. CVC-MUSCIMA consists of 1000 binary images: 20 pages of music were each re-written by 50 musicians, binarized, and staves were removed. We had 7 different annotators marking musical symbols: each annotator marked one of each 20 CVC-MUSCIMA pages, with the writers selected so that the 140 images cover 2-3 images from each of the 50 CVC-MUSCIMA writers. This setup ensures maximal variability of handwriting, given the limitations in annotation resources.\r\n\r\nThe MUSCIMA++ dataset is intended for musical symbol detection and classification, and for music notation reconstruction. A thorough description of its design is published on arXiv [2]: https://arxiv.org/abs/1703.04824 The full definition of the ground truth is given in the form of annotator instructions.;2017-08-25;corpus;http://hdl.handle.net/11372/LRT-2372;zxx;https://ufal.mff.cuni.cz/~hajicj/2017/docs/icdar2017_CAMERA.pdf;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://ufal.mff.cuni.cz/muscima/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "906f467c-b50e-5381-af4e-32311d192323",
-    "notes": [
-        "MUSCIMA++ is a dataset of handwritten music notation for musical symbol detection. It contains 91255 symbols, consisting of both notation primitives and higher-level notation objects, such as key signatures or time signatures. There are 23352 notes in the dataset, of which 21356 have a full notehead, 1648 have an empty notehead, and 348 are grace notes. For each annotated object in an image, we provide both the bounding box, and a pixel mask that defines exactly which pixels within the bounding box belong to the given object. Composite constructions, such as notes, are captured through explicitly annotated relationships of the notation primitives (noteheads, stems, beams...). This way, the annotation provides an explicit bridge between the low-level and high-level symbols described in Optical Music Recognition literature.\r\n\r\nMUSCIMA++ has annotations for 140 images from the CVC-MUSCIMA dataset [2], used for handwritten music notation writer identification and staff removal. CVC-MUSCIMA consists of 1000 binary images: 20 pages of music were each re-written by 50 musicians, binarized, and staves were removed. We had 7 different annotators marking musical symbols: each annotator marked one of each 20 CVC-MUSCIMA pages, with the writers selected so that the 140 images cover 2-3 images from each of the 50 CVC-MUSCIMA writers. This setup ensures maximal variability of handwriting, given the limitations in annotation resources.\r\n\r\nThe MUSCIMA++ dataset is intended for musical symbol detection and classification, and for music notation reconstruction. A thorough description of its design is published on arXiv [2]: https://arxiv.org/abs/1703.04824 The full definition of the ground truth is given in the form of annotator instructions."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2372"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Optical Music Recognition"
-        },
-        {
-            "name": "Music Notation"
-        },
-        {
-            "name": "Graph-Based Representation"
-        },
-        {
-            "name": "Symbol Detection"
-        }
-    ],
-    "title": [
-        "MUSCIMA++"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/90718076-b86b-5430-a3e3-085945811a0b.json b/oaitestdata/clarin-oai_dc/SET_1/json/90718076-b86b-5430-a3e3-085945811a0b.json
deleted file mode 100644
index 8cd52e79..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/90718076-b86b-5430-a3e3-085945811a0b.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=c68fe73834da11e2a2aa782bcb074135136b7883f83142e5b3925eebef708c0e",
-    "MetadataAccess": [
-        "c68fe73834da11e2a2aa782bcb074135136b7883f83142e5b3925eebef708c0e"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "c68fe73834da11e2a2aa782bcb074135136b7883f83142e5b3925eebef708c0e;2018-11-15T16:39:52Z;toolService;toolService:tool;UIMA/U-Compare Stanford Parser ;Syntactic parser for English. Outputs dependency relations. Also outputs parts-of-speech for each token.\n\nThe tool is provided as a UIMA  component, specifically as Java archive (jar) file, which can be incorporated within any UIMA workflow. However, it is particularly designed use in the U-Compare text mining platform (see separate META-SHARE record), since the types of annotations it produces are compliant with the U-Compare type system.;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "90718076-b86b-5430-a3e3-085945811a0b",
-    "notes": [
-        "Syntactic parser for English. Outputs dependency relations. Also outputs parts-of-speech for each token.\n\nThe tool is provided as a UIMA  component, specifically as Java archive (jar) file, which can be incorporated within any UIMA workflow. However, it is particularly designed use in the U-Compare text mining platform (see separate META-SHARE record), since the types of annotations it produces are compliant with the U-Compare type system."
-    ],
-    "oai_identifier": [
-        "c68fe73834da11e2a2aa782bcb074135136b7883f83142e5b3925eebef708c0e"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "UIMA/U-Compare Stanford Parser "
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9087fd03-af79-509a-8aea-cfa627364f4c.json b/oaitestdata/clarin-oai_dc/SET_1/json/9087fd03-af79-509a-8aea-cfa627364f4c.json
deleted file mode 100644
index 87b811fd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9087fd03-af79-509a-8aea-cfa627364f4c.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4449",
-    "MetadataAccess": [
-        "oai:ota:oucs:4449"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Holcroft, Thomas, 1745-1809."
-    ],
-    "fulltext": "oai:ota:oucs:4449;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4449.xml;The adventures of Hugh Trevor: By Thomas Holcroft. ... [pt.1];Holcroft, Thomas, 1745-1809.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9087fd03-af79-509a-8aea-cfa627364f4c",
-    "oai_identifier": [
-        "oai:ota:oucs:4449"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The adventures of Hugh Trevor: By Thomas Holcroft. ... [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4449.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/90b4e9ae-81a9-535c-922a-c9c54397a02a.json b/oaitestdata/clarin-oai_dc/SET_1/json/90b4e9ae-81a9-535c-922a-c9c54397a02a.json
deleted file mode 100644
index c3b54a1c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/90b4e9ae-81a9-535c-922a-c9c54397a02a.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "text/xml",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Southern Sami"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/102",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/102"
-    ],
-    "PID": "http://hdl.handle.net/11509/102",
-    "PublicationTimestamp": "2015-10-10T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "CC",
-        "http://creativecommons.org/licenses/by/3.0/"
-    ],
-    "author": [
-        "The Divvun group at UiT The Arctic University of Norway",
-        "Giellatekno - Saami Language Technology, UiT The Arctic University of Norway"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/102;2016-09-06T12:34:54Z;hdl_11509_1;hdl_11509_2;SIKOR South Saami free corpus;Giellatekno - Saami Language Technology, UiT The Arctic University of Norway;The Divvun group at UiT The Arctic University of Norway;Monolingual Corpus;Text Corpus;South Saami;Dependency Tree Bank;The SIKOR South Saami free corpus is a monolingual text corpus of South Saami that contains administrative, law, religious, non-fiction, and fiction texts. It is work done by the Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language community. In particular, the following colleagues have contributed to the creation of the ressource: Ciprian Gerstenberger, B\u00f8rre Gaup, Risten-Birje Steinfjell, Lene Antonsen, Trond Trosterud, and Maja Kappfjell. Linguistically, the data set (58,407 sentences; 646,273 tokens) features word form, lemma, morphosyntactic analysis, and dependency relations between tokens. The corpus has been automatically processed and linguistically analyzed with the Giellatekno/Divvun tools. Therefore, it may contain wrong annotations. In case you find any errors the creators would appreciate your feedback sent to giellatekno@uit.no and feedback@divvun.no.\r\nPlease note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata).;2015-10-10;corpus;http://hdl.handle.net/11509/102;sma;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);CC;http://creativecommons.org/licenses/by/3.0/;application/zip;text/plain; charset=utf-8;text/xml;downloadable_files_count: 1;Giellatekno - Saami Language Technology;http://giellatekno.uit.no/index.eng.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "90b4e9ae-81a9-535c-922a-c9c54397a02a",
-    "notes": [
-        "The SIKOR South Saami free corpus is a monolingual text corpus of South Saami that contains administrative, law, religious, non-fiction, and fiction texts. It is work done by the Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language community. In particular, the following colleagues have contributed to the creation of the ressource: Ciprian Gerstenberger, B\u00f8rre Gaup, Risten-Birje Steinfjell, Lene Antonsen, Trond Trosterud, and Maja Kappfjell. Linguistically, the data set (58,407 sentences; 646,273 tokens) features word form, lemma, morphosyntactic analysis, and dependency relations between tokens. The corpus has been automatically processed and linguistically analyzed with the Giellatekno/Divvun tools. Therefore, it may contain wrong annotations. In case you find any errors the creators would appreciate your feedback sent to giellatekno@uit.no and feedback@divvun.no.\r\nPlease note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata)."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/102"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Monolingual Corpus"
-        },
-        {
-            "name": "Text Corpus"
-        },
-        {
-            "name": "South Saami"
-        },
-        {
-            "name": "Dependency Tree Bank"
-        }
-    ],
-    "title": [
-        "SIKOR South Saami free corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/90c352db-b942-5b9a-84fb-b650dd62c2eb.json b/oaitestdata/clarin-oai_dc/SET_1/json/90c352db-b942-5b9a-84fb-b650dd62c2eb.json
deleted file mode 100644
index 4f2520f6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/90c352db-b942-5b9a-84fb-b650dd62c2eb.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 5",
-        "text/plain; charset=utf-8",
-        "application/gzip",
-        "application/octet-stream"
-    ],
-    "Language": [],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/262",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/262"
-    ],
-    "PID": "http://hdl.handle.net/11321/262",
-    "PublicationTimestamp": "2016-04-11T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "Zab\u0142ocki, Aleksander",
-        "Zaborowski, Bartosz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/262;2016-05-19T20:37:05Z;hdl_11321_3;hdl_11321_4;Poliqarp2;Zaborowski, Bartosz;Zab\u0142ocki, Aleksander;linguistic search engine;corpus;treebank;structure bank;Poliqarp2 is a linguistic search engine, capable of searching through large corpora annotated on multiple levels. It is not an     upgraded version of Poliqarp, it is a completely new software developed from scratch.;2016-04-11;toolService;http://hdl.handle.net/11321/262;N/A;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;downloadable_files_count: 5;Institute of Computer Science, Polish Academy of Sciences;https://sourceforge.net/projects/poliqarp2/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "90c352db-b942-5b9a-84fb-b650dd62c2eb",
-    "notes": [
-        "Poliqarp2 is a linguistic search engine, capable of searching through large corpora annotated on multiple levels. It is not an     upgraded version of Poliqarp, it is a completely new software developed from scratch."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/262"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "linguistic search engine"
-        },
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "structure bank"
-        }
-    ],
-    "title": [
-        "Poliqarp2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/90e8438a-1b37-5b1a-a5a2-6ccd0697ddf6.json b/oaitestdata/clarin-oai_dc/SET_1/json/90e8438a-1b37-5b1a-a5a2-6ccd0697ddf6.json
deleted file mode 100644
index e7f64fdf..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/90e8438a-1b37-5b1a-a5a2-6ccd0697ddf6.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=ffc1c2b0357f11e2a2aa782bcb074135a0708b33105c49d4b11cab77c30d5c75",
-    "MetadataAccess": [
-        "ffc1c2b0357f11e2a2aa782bcb074135a0708b33105c49d4b11cab77c30d5c75"
-    ],
-    "PublicationTimestamp": "2012-11-23T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "fulltext": "ffc1c2b0357f11e2a2aa782bcb074135a0708b33105c49d4b11cab77c30d5c75;2018-11-15T16:39:53Z;toolService;toolService:tool;LX-Tokenizer;The present tool, that was built to deal with Portuguese-specific issues concerning a few non-trivial cases that involve tokenization-ambigous strings, segments text into lexically relevant tokens, using whitespace as the separator. Note that, in these examples, the | (vertical bar) symbol is used to mark the token boundaries clearier:\n\t\n\tum exemplo \u00e2\u0086\u0092 |um|exemplo|\n\nExpands contractions. Note that the first element of an expanded contraction is marked with an _ (underscore) symbol:\n\n\tdo \u00e2\u0086\u0092 |de_|o|\n\nMarks spacing around punctuation or symbols. The \\* and the */ symbols indicate a space to the left and a space to the right, respectively:\n\num, dois e tr\u00c3\u00aas \u00e2\u0086\u0092 |um|,*/|dois|e|tr\u00c3\u00aas|\n 5.3 \u00e2\u0086\u0092 |5|.|3|\n 1. 2 \u00e2\u0086\u0092 |1|.*/|2|\n 8 . 6 \u00e2\u0086\u0092 |8|\\*.*/|6|\n\nDetaches clitic pronouns from the verb. The detached pronoun is marked with a - (hyphen) symbol. When in mesoclisis, a -CL- mark is used to signal the original position of the detached clitic. Additionally, possible vocalic alterations of the verb form are marked with a # (hash) symbol:\n\n\td\u00c3\u00a1-se-lho \u00e2\u0086\u0092 |d\u00c3\u00a1|-se|-lhe|-o|\n\tafirmar-se-ia \u00e2\u0086\u0092 |afirmar-CL-ia|-se|\n\tv\u00c3\u00aa-las \u00e2\u0086\u0092 |v\u00c3\u00aa#|-las|\n\nThis tool also handles ambiguous strings. These are words that, depending on their particular occurrence, can be tokenized in different ways. For instance:\n\ndeste \u00e2\u0086\u0092 |deste| when occurring as a Verb\ndeste \u00e2\u0086\u0092 |de|este| when occurring as a contraction (Preposition + Demonstrative)\nThis tool achieves a f-score of 99.72%.\n\nLX-Tokenizer was developed and is maintained at University of Lisbon by the NLX-Natural Language and Speech Group of the Department of Informatics.\n;2012-11-23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "90e8438a-1b37-5b1a-a5a2-6ccd0697ddf6",
-    "notes": [
-        "The present tool, that was built to deal with Portuguese-specific issues concerning a few non-trivial cases that involve tokenization-ambigous strings, segments text into lexically relevant tokens, using whitespace as the separator. Note that, in these examples, the | (vertical bar) symbol is used to mark the token boundaries clearier:\n\t\n\tum exemplo \u00e2\u0086\u0092 |um|exemplo|\n\nExpands contractions. Note that the first element of an expanded contraction is marked with an _ (underscore) symbol:\n\n\tdo \u00e2\u0086\u0092 |de_|o|\n\nMarks spacing around punctuation or symbols. The \\* and the */ symbols indicate a space to the left and a space to the right, respectively:\n\num, dois e tr\u00c3\u00aas \u00e2\u0086\u0092 |um|,*/|dois|e|tr\u00c3\u00aas|\n 5.3 \u00e2\u0086\u0092 |5|.|3|\n 1. 2 \u00e2\u0086\u0092 |1|.*/|2|\n 8 . 6 \u00e2\u0086\u0092 |8|\\*.*/|6|\n\nDetaches clitic pronouns from the verb. The detached pronoun is marked with a - (hyphen) symbol. When in mesoclisis, a -CL- mark is used to signal the original position of the detached clitic. Additionally, possible vocalic alterations of the verb form are marked with a # (hash) symbol:\n\n\td\u00c3\u00a1-se-lho \u00e2\u0086\u0092 |d\u00c3\u00a1|-se|-lhe|-o|\n\tafirmar-se-ia \u00e2\u0086\u0092 |afirmar-CL-ia|-se|\n\tv\u00c3\u00aa-las \u00e2\u0086\u0092 |v\u00c3\u00aa#|-las|\n\nThis tool also handles ambiguous strings. These are words that, depending on their particular occurrence, can be tokenized in different ways. For instance:\n\ndeste \u00e2\u0086\u0092 |deste| when occurring as a Verb\ndeste \u00e2\u0086\u0092 |de|este| when occurring as a contraction (Preposition + Demonstrative)\nThis tool achieves a f-score of 99.72%.\n\nLX-Tokenizer was developed and is maintained at University of Lisbon by the NLX-Natural Language and Speech Group of the Department of Informatics.\n"
-    ],
-    "oai_identifier": [
-        "ffc1c2b0357f11e2a2aa782bcb074135a0708b33105c49d4b11cab77c30d5c75"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "LX-Tokenizer"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/90fc6dff-2041-58f6-b5e0-61cc778fc72c.json b/oaitestdata/clarin-oai_dc/SET_1/json/90fc6dff-2041-58f6-b5e0-61cc778fc72c.json
deleted file mode 100644
index 7c597585..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/90fc6dff-2041-58f6-b5e0-61cc778fc72c.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "Wroclaw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/22",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/22"
-    ],
-    "PID": "http://hdl.handle.net/11321/22",
-    "PublicationTimestamp": "2012-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Wroclaw University of Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "author": [
-        "Marci\u0144czuk, Micha\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/22;2016-01-19T09:31:41Z;hdl_11321_3;hdl_11321_4;NELexicon;Marci\u0144czuk, Micha\u0142;NELexicon to gazetteer nazw w\u0142asnych, kt\u00f3ry zawiera ponad 1.4 miliona unikalnych nazw w\u0142asnych przypisanych do kategorii (par kategoria; nazwa), w tym ponad 1.37 miliona unikalnych napis\u00f3w (z pomini\u0119ciem powt\u00f3rze\u0144 nazw w\u0142asnych przypisanych do kilku kategorii).;2012;corpus;http://hdl.handle.net/11321/22;pol;downloadable_files_count: 0;Wroclaw University of Technology;http://nlp.pwr.wroc.pl/pl/narzedzia-i-zasoby/nelexicon",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "90fc6dff-2041-58f6-b5e0-61cc778fc72c",
-    "notes": [
-        "NELexicon to gazetteer nazw w\u0142asnych, kt\u00f3ry zawiera ponad 1.4 miliona unikalnych nazw w\u0142asnych przypisanych do kategorii (par kategoria; nazwa), w tym ponad 1.37 miliona unikalnych napis\u00f3w (z pomini\u0119ciem powt\u00f3rze\u0144 nazw w\u0142asnych przypisanych do kilku kategorii)."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/22"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "NELexicon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/91110e02-abea-5ce8-abb1-ed232fc0d4eb.json b/oaitestdata/clarin-oai_dc/SET_1/json/91110e02-abea-5ce8-abb1-ed232fc0d4eb.json
deleted file mode 100644
index b7114271..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/91110e02-abea-5ce8-abb1-ed232fc0d4eb.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Wynne, Martin"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-215",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-215"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-215",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-215;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Oxford Text Archive;Wynne, Martin;Electronic texts, corpora, lexicons. other;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-215;eng;downloadable_files_count: 0;United Kingdom;http://www.ahds.ac.uk/litlangling",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "91110e02-abea-5ce8-abb1-ed232fc0d4eb",
-    "notes": [
-        "Electronic texts, corpora, lexicons. other"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-215"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Oxford Text Archive"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/91117cac-c661-5255-ac0d-768782af8536.json b/oaitestdata/clarin-oai_dc/SET_1/json/91117cac-c661-5255-ac0d-768782af8536.json
deleted file mode 100644
index 4683e026..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/91117cac-c661-5255-ac0d-768782af8536.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Doma\u0144ska"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 5",
-        "application/zip",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/72",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/72"
-    ],
-    "PID": "http://hdl.handle.net/11321/72",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Doma\u0144ska"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Doma\u0144ska, Doma\u0144ska"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/72;2015-04-14T12:55:08Z;hdl_11321_3;hdl_11321_4;MWE Doma\u0144ska;Doma\u0144ska, Doma\u0144ska;Doma\u0144ska;2015-04-08;corpus;http://hdl.handle.net/11321/72;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 5;Doma\u0144ska",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "91117cac-c661-5255-ac0d-768782af8536",
-    "notes": [
-        "Doma\u0144ska"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/72"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Doma\u0144ska"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/911d62b9-7742-5298-9914-5c5f2f367cd7.json b/oaitestdata/clarin-oai_dc/SET_1/json/911d62b9-7742-5298-9914-5c5f2f367cd7.json
deleted file mode 100644
index 30990cd9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/911d62b9-7742-5298-9914-5c5f2f367cd7.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/327",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/327"
-    ],
-    "PID": "http://hdl.handle.net/11321/327",
-    "PublicationTimestamp": "2016-11-07T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "author": [
-        "K\u0119dzia, Pawe\u0142",
-        "Czachor, Gabriela",
-        "Piasecki, Maciej",
-        "Koco\u0144, Jan"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/327;2017-04-26T10:55:04Z;hdl_11321_3;hdl_11321_4;Vector representations of polish words (Word2Vec method);K\u0119dzia, Pawe\u0142;Czachor, Gabriela;Piasecki, Maciej;Koco\u0144, Jan;Vector space;Word2Vec;Model skip gram with vectors of length 100. Trained on kgr 10, a corpora with over 4 billion tokens. Data preprocessing involved segmentation, lemmatization and mophosyntactic disambiguation with MWE annotation.;2016-11-07;lexicalConceptualResource;http://hdl.handle.net/11321/327;pol;application/zip;downloadable_files_count: 1;Wroc\u0142aw University of Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "911d62b9-7742-5298-9914-5c5f2f367cd7",
-    "notes": [
-        "Model skip gram with vectors of length 100. Trained on kgr 10, a corpora with over 4 billion tokens. Data preprocessing involved segmentation, lemmatization and mophosyntactic disambiguation with MWE annotation."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/327"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Vector space"
-        },
-        {
-            "name": "WordVec"
-        }
-    ],
-    "title": [
-        "Vector representations of polish words (Word2Vec method)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/91330cc2-e6e4-5f75-be5f-ba3b738a621a.json b/oaitestdata/clarin-oai_dc/SET_1/json/91330cc2-e6e4-5f75-be5f-ba3b738a621a.json
deleted file mode 100644
index bada5aea..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/91330cc2-e6e4-5f75-be5f-ba3b738a621a.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "185 KB"
-    ],
-    "Language": [
-        "Old French (842-ca. 1400)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0893",
-    "MetadataAccess": [
-        "oai:ota:oucs:0893"
-    ],
-    "PublicationTimestamp": "1129-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1129"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Gesta"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:0893;2018-02-28T15:16:32Z;http://ota.ox.ac.uk/headers/0893.xml; La Chanson de Roland / compiled by John Dawson;1129-1165;text_and_corpus_linguistics;Gesta -- France -- 12th century;fro;Oxford Text Archive, University of Oxford;185 KB;Text;Gesta;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "91330cc2-e6e4-5f75-be5f-ba3b738a621a",
-    "oai_identifier": [
-        "oai:ota:oucs:0893"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Gesta -- France -- th century"
-        }
-    ],
-    "title": [
-        " La Chanson de Roland / compiled by John Dawson"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0893.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9136f046-fcc7-502f-aac5-4b5d6ca10e79.json b/oaitestdata/clarin-oai_dc/SET_1/json/9136f046-fcc7-502f-aac5-4b5d6ca10e79.json
deleted file mode 100644
index 72f1a04e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9136f046-fcc7-502f-aac5-4b5d6ca10e79.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1410",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1410"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1410",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1410;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;freeling_parsed;Freeling-based shallow parser.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1410;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9136f046-fcc7-502f-aac5-4b5d6ca10e79",
-    "notes": [
-        "Freeling-based shallow parser."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1410"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "freeling_parsed"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/91604bee-b509-5a21-bfd7-33383827f73e.json b/oaitestdata/clarin-oai_dc/SET_1/json/91604bee-b509-5a21-bfd7-33383827f73e.json
deleted file mode 100644
index 90dcc3d9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/91604bee-b509-5a21-bfd7-33383827f73e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3426",
-    "MetadataAccess": [
-        "oai:ota:oucs:3426"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Radcliffe, Ann Ward, 1764-1823."
-    ],
-    "fulltext": "oai:ota:oucs:3426;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3426.xml;The romance of the forest: interspersed with some pieces of poetry. By the authoress of \"A Sicilian romance,\" &c. In two volumes. ... [pt.1];Radcliffe, Ann Ward, 1764-1823.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "91604bee-b509-5a21-bfd7-33383827f73e",
-    "oai_identifier": [
-        "oai:ota:oucs:3426"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The romance of the forest: interspersed with some pieces of poetry. By the authoress of \"A Sicilian romance,\" &c. In two volumes. ... [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3426.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9170eb09-5707-5364-90c2-cf062db00b3f.json b/oaitestdata/clarin-oai_dc/SET_1/json/9170eb09-5707-5364-90c2-cf062db00b3f.json
deleted file mode 100644
index aed23474..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9170eb09-5707-5364-90c2-cf062db00b3f.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Department of Linguistics and Nordic Studies, University of Oslo"
-    ],
-    "Contributor": [
-        "N\u00f8klestad, Anders"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1448",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1448"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1448",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Department of Linguistics and Nordic Studies, University of Oslo"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Norway"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "N\u00f8klestad, Anders"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1448;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Glossa corpus search system;N\u00f8klestad, Anders;N\u00f8klestad, Anders;Glossa is a web-based system for corpus search and results management. It comes with built-in support for CLARIN federated content search as well as corpora encoded with the IMS Corpus Workbench. It also has a plugin architecture that enables other search engines to be used once a wrapper has been created.Glossa can be freely downloaded and installed on the user's server. It currently supports only monolignual written corpora, but support for multilingual corpora is under development, as well as support for  spoken corpora with audio, video and maps.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1448;downloadable_files_count: 0;Norway;Department of Linguistics and Nordic Studies, University of Oslo;https://github.com/textlab/rglossa",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9170eb09-5707-5364-90c2-cf062db00b3f",
-    "notes": [
-        "Glossa is a web-based system for corpus search and results management. It comes with built-in support for CLARIN federated content search as well as corpora encoded with the IMS Corpus Workbench. It also has a plugin architecture that enables other search engines to be used once a wrapper has been created.Glossa can be freely downloaded and installed on the user's server. It currently supports only monolignual written corpora, but support for multilingual corpora is under development, as well as support for  spoken corpora with audio, video and maps."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1448"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Glossa corpus search system"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/917b4734-1352-5971-8ae2-88bc830a3402.json b/oaitestdata/clarin-oai_dc/SET_1/json/917b4734-1352-5971-8ae2-88bc830a3402.json
deleted file mode 100644
index b7a18809..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/917b4734-1352-5971-8ae2-88bc830a3402.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=1092896e5f0f11e6a2aa782bcb074135086ed39db4bc44fe84f544af288d6aed",
-    "MetadataAccess": [
-        "1092896e5f0f11e6a2aa782bcb074135086ed39db4bc44fe84f544af288d6aed"
-    ],
-    "PublicationTimestamp": "2016-08-10T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "fulltext": "1092896e5f0f11e6a2aa782bcb074135086ed39db4bc44fe84f544af288d6aed;2018-11-15T16:40:23Z;corpus;corpus:text;PhenoCHF Corpus;PhenoCHF is an annotated corpus consisting of documents belonging to two different text types (i.e., narrative reports from electronic health records (EHRs) and literature articles). It is manually annotated by medical doctors with detailed information relating to mentions of phenotype concepts and disease-phenotype relations. \n\nThe documents in PhenoCHF focus on a specific medical condition, i.e., congestive heart failure (CHF). This focus is motivated by CHF's current standing as the world's most deadly disease. However, our experiments using the corpus have demonstrated that it can be used to develop systems that can recognise information relating to a wider range of diseases in a broader variety of text types than those included in PhenoCHF. ;2016-08-10",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "917b4734-1352-5971-8ae2-88bc830a3402",
-    "notes": [
-        "PhenoCHF is an annotated corpus consisting of documents belonging to two different text types (i.e., narrative reports from electronic health records (EHRs) and literature articles). It is manually annotated by medical doctors with detailed information relating to mentions of phenotype concepts and disease-phenotype relations. \n\nThe documents in PhenoCHF focus on a specific medical condition, i.e., congestive heart failure (CHF). This focus is motivated by CHF's current standing as the world's most deadly disease. However, our experiments using the corpus have demonstrated that it can be used to develop systems that can recognise information relating to a wider range of diseases in a broader variety of text types than those included in PhenoCHF. "
-    ],
-    "oai_identifier": [
-        "1092896e5f0f11e6a2aa782bcb074135086ed39db4bc44fe84f544af288d6aed"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "PhenoCHF Corpus"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/917fa228-bfe6-5e0b-b010-438bf1a840f8.json b/oaitestdata/clarin-oai_dc/SET_1/json/917fa228-bfe6-5e0b-b010-438bf1a840f8.json
deleted file mode 100644
index 2bbd86e4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/917fa228-bfe6-5e0b-b010-438bf1a840f8.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Jenkyns, Joy"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "625 files: ca. 24.4 MB"
-    ],
-    "Language": [
-        "English",
-        "Latin",
-        "Old English (ca. 450-1100)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2480",
-    "MetadataAccess": [
-        "oai:ota:oucs:2480"
-    ],
-    "PublicationTimestamp": "1988-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1988"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Electronic publications"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Jenkyns, Joy"
-    ],
-    "fulltext": "oai:ota:oucs:2480;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/2480.xml;Anglo-Saxon Charter Boundaries material;Language of Landscape: Reading the Anglo-Saxon Countryside;Jenkyns, Joy;1988;text_and_corpus_linguistics;Great Britain--History--Anglo Saxon period, 449-1066;Boundaries;eng;lat;ang;The resource consists of files made at different times and on different machines during the time of compilation. It is useful from an historical perspective only, since the material is now being set up as the AHRB-funded 'Language of Landscape: Reading the Anglo-Saxon Countryside' project (started in October 2004), which will render all these archived materials obsolete. The materials do, however, show the development of the resource from the Oxford mainframe 2988, with Famulus and Search Text as database and concordancing programs, and Ecce, Edt and Spitbol as editors. This development is traced through the move to the Vax system and the use of Ingres, OCP, Gimms and SasGraph. ;Oxford Text Archive, University of Oxford;Jenkyns, Joy;625 files: ca. 24.4 MB;Text;Electronic publications;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "917fa228-bfe6-5e0b-b010-438bf1a840f8",
-    "notes": [
-        "The resource consists of files made at different times and on different machines during the time of compilation. It is useful from an historical perspective only, since the material is now being set up as the AHRB-funded 'Language of Landscape: Reading the Anglo-Saxon Countryside' project (started in October 2004), which will render all these archived materials obsolete. The materials do, however, show the development of the resource from the Oxford mainframe 2988, with Famulus and Search Text as database and concordancing programs, and Ecce, Edt and Spitbol as editors. This development is traced through the move to the Vax system and the use of Ingres, OCP, Gimms and SasGraph. "
-    ],
-    "oai_identifier": [
-        "oai:ota:oucs:2480"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Great Britain--History--Anglo Saxon period"
-        },
-        {
-            "name": "Boundaries"
-        }
-    ],
-    "title": [
-        "Anglo-Saxon Charter Boundaries material",
-        "Language of Landscape: Reading the Anglo-Saxon Countryside"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2480.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9182a531-0220-5298-a3cb-8b297ad77a5b.json b/oaitestdata/clarin-oai_dc/SET_1/json/9182a531-0220-5298-a3cb-8b297ad77a5b.json
deleted file mode 100644
index 9a2f88b0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9182a531-0220-5298-a3cb-8b297ad77a5b.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "Persian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-916",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-916"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-916",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-916;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Middle Persian (Pahlavi);relational database;corpus;ca. 200.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-916;fas;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#mpers",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9182a531-0220-5298-a3cb-8b297ad77a5b",
-    "notes": [
-        "ca. 200.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-916"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "relational database"
-        },
-        {
-            "name": "corpus"
-        }
-    ],
-    "title": [
-        "TITUS Middle Persian (Pahlavi)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/919e7b69-81df-5a7b-9125-2f49b1ca19f5.json b/oaitestdata/clarin-oai_dc/SET_1/json/919e7b69-81df-5a7b-9125-2f49b1ca19f5.json
deleted file mode 100644
index 8f1035e3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/919e7b69-81df-5a7b-9125-2f49b1ca19f5.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Franciszka Cezarego"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-148514",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-148514"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CDE-4",
-    "PublicationTimestamp": "1642-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1642"
-    ],
-    "Publisher": [
-        "Drukarnia Franciszka Cezarego"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/148514",
-        "oai:jbc.bj.uj.edu.pl:publication:156737"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1601/1700"
-    ],
-    "TempCoverageBegin": 50506804799,
-    "TempCoverageEnd": 50506804799,
-    "TemporalCoverage": " point in time : 1601-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1601-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1601-07-01T11:59:59Z",
-    "author": [
-        "Damalewicz, Stefan (ca 1600-1673)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-148514;2019-02-28T18:15:24Z;Ro\u017ca Z opatrzno\u015bci Boskiey now\u0105 szat\u0105 odziana Abo Kazanie Przy Po\u015bwi\u0105caniu [!] Przewielebnego w Chrystusie Oyca, Ie[g]o M. X. Alexandra Bvcendorfa K\u0119ssowskiego, Opata Oliwskiego W Ko\u015bciele Kathedralnym W\u0142oc\u0142awskim;Damalewicz, Stefan (ca 1600-1673);starodruki 17\u00a0w.;K\u0119sowski, Aleksander (1590-1667). [Adr. ded.];Drukarnia Franciszka Cezarego;1642;starodruk;application/xml;clarind-uds:poldilemma-148514;hdl:11858/00-246C-0000-0023-8CDE-4;Biblioteka Jagiello\u0144ska, BJ St. Dr. 36825 I;pol;lat;http://jbc.bj.uj.edu.pl/Content/148514;oai:jbc.bj.uj.edu.pl:publication:156737;1601/1700;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "919e7b69-81df-5a7b-9125-2f49b1ca19f5",
-    "notes": [
-        "K\u0119sowski, Aleksander (1590-1667). [Adr. ded.]"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-148514"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Ro\u017ca Z opatrzno\u015bci Boskiey now\u0105 szat\u0105 odziana Abo Kazanie Przy Po\u015bwi\u0105caniu [!] Przewielebnego w Chrystusie Oyca, Ie[g]o M. X. Alexandra Bvcendorfa K\u0119ssowskiego, Opata Oliwskiego W Ko\u015bciele Kathedralnym W\u0142oc\u0142awskim"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/91d17190-5a37-5150-86cc-a4fec48d4ead.json b/oaitestdata/clarin-oai_dc/SET_1/json/91d17190-5a37-5150-86cc-a4fec48d4ead.json
deleted file mode 100644
index 05aacbda..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/91d17190-5a37-5150-86cc-a4fec48d4ead.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/85",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/85"
-    ],
-    "PID": "http://hdl.handle.net/10794/85",
-    "PublicationTimestamp": "2015-04-28T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/85;2017-10-25T14:54:26Z;hdl_10794_1;hdl_10794_2;Swedish Bible 1873 (2015-05-20);Bibeln 1873 (2015-05-20);n/a, n/a;Swedish;Bible;Swedish Bible 1873.;Svenska bibeln 1873.;2015-04-28;corpus;http://hdl.handle.net/10794/85;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/bibel1873dalin",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "91d17190-5a37-5150-86cc-a4fec48d4ead",
-    "notes": [
-        "Swedish Bible 1873.",
-        "Svenska bibeln 1873."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/85"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Bible"
-        }
-    ],
-    "title": [
-        "Swedish Bible 1873 (2015-05-20)",
-        "Bibeln 1873 (2015-05-20)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/91fa198f-6549-5f37-880c-6918dc827ac3.json b/oaitestdata/clarin-oai_dc/SET_1/json/91fa198f-6549-5f37-880c-6918dc827ac3.json
deleted file mode 100644
index 145497f8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/91fa198f-6549-5f37-880c-6918dc827ac3.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Institute of Slavic Studies, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 70",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish",
-        "Bulgarian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/536",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/536"
-    ],
-    "PID": "http://hdl.handle.net/11321/536",
-    "PublicationTimestamp": "2018-07-21T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Institute of Slavic Studies, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "IS PAS corpora license",
-        "http://clarin-pl.eu/en/licenses/is-pas-corpora-license/",
-        "CC"
-    ],
-    "author": [
-        "Sato\u0142a-Sta\u015bkowiak, Joanna",
-        "Roszko, Danuta",
-        "Roszko, Roman",
-        "Sosnowski, Wojciech"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/536;2018-07-21T21:39:15Z;hdl_11321_3;hdl_11321_4;Polish-Bulgarian Parallel Corpus;Roszko, Roman;Roszko, Danuta;Sosnowski, Wojciech;Sato\u0142a-Sta\u015bkowiak, Joanna;Polish;Bulgarian;Parallel Corpora;Polish-Bulgarian Parallel Corpus;2018-07-21;corpus;http://hdl.handle.net/11321/536;pol;bul;IS PAS corpora license;http://clarin-pl.eu/en/licenses/is-pas-corpora-license/;CC;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 70;Institute of Slavic Studies, Polish Academy of Sciences",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "91fa198f-6549-5f37-880c-6918dc827ac3",
-    "notes": [
-        "Polish-Bulgarian Parallel Corpus"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/536"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Polish"
-        },
-        {
-            "name": "Bulgarian"
-        },
-        {
-            "name": "Parallel Corpora"
-        }
-    ],
-    "title": [
-        "Polish-Bulgarian Parallel Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/91ff5a2d-cde6-5182-a71a-407fa2dc740d.json b/oaitestdata/clarin-oai_dc/SET_1/json/91ff5a2d-cde6-5182-a71a-407fa2dc740d.json
deleted file mode 100644
index 371ae81f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/91ff5a2d-cde6-5182-a71a-407fa2dc740d.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/86",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/86"
-    ],
-    "PID": "http://hdl.handle.net/10794/86",
-    "PublicationTimestamp": "2015-04-28T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/86;2017-10-25T14:51:16Z;hdl_10794_1;hdl_10794_2;Swedish Bible 1917 (2015-05-19);Bibeln 1917 (2015-05-19);n/a, n/a;Swedish;Bible;Swedish Bible 1917.;Svenska bibeln 1917.;2015-04-28;corpus;http://hdl.handle.net/10794/86;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/bibel1917",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "91ff5a2d-cde6-5182-a71a-407fa2dc740d",
-    "notes": [
-        "Swedish Bible 1917.",
-        "Svenska bibeln 1917."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/86"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Bible"
-        }
-    ],
-    "title": [
-        "Swedish Bible 1917 (2015-05-19)",
-        "Bibeln 1917 (2015-05-19)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/921161d1-472e-52e0-9b5a-52f786e83f21.json b/oaitestdata/clarin-oai_dc/SET_1/json/921161d1-472e-52e0-9b5a-52f786e83f21.json
deleted file mode 100644
index b7d5cd75..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/921161d1-472e-52e0-9b5a-52f786e83f21.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-92",
-    "MetadataAccess": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-92"
-    ],
-    "PID": "http://hdl.handle.net/20.500.11752/ILC-92",
-    "PublicationTimestamp": "2012-05-22T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/248064",
-        "http://www.lrec-conf.org/proceedings/lrec2012/workshops/06.LREC%202012%20Merging%20Proceedings.pdf"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Rubino, Francesco",
-        "Abrate, Matteo",
-        "Frontini, Francesca",
-        "Quochi, Valeria",
-        "Del Gratta, Riccardo",
-        "Lo Duca, Angelica",
-        "Monachini, Monica"
-    ],
-    "fulltext": "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-92;2018-12-05T08:43:07Z;hdl_000-c0-111_38;hdl_000-c0-111_49;LMF ML Merger;Del Gratta, Riccardo;Frontini, Francesca;Monachini, Monica;Quochi, Valeria;Rubino, Francesco;Abrate, Matteo;Lo Duca, Angelica;LFM Standard;(semi-)automatic Lexicon Merging;Similarity Score;This is a LMF Lexical Multi level Merger web-service for the automatic merging of Lexical Entries, Syntactic Behaviours and Subcategorization Frames  from two distinct LMF lexicons. The web-service takes two LMF lexicons, A and B, and a set of directives in input and outputs one or more LMF merged lexicon(s) according to different merging scenarios. Further details can be found in: Riccardo Del Gratta & Francesca Frontini & Monica Monachini &Valeria Quochi & Francesco Rubino& Matteo Abrate & Angelica Lo Duca. 2012. L-LEME: an Automatic Lexical Merger based on the LMF Standard. In Proceedings of the Workshop on Language Resource Merging (Colocated wiyh LREC 2012), May, 22 2012, Istanbul, Turkey;2012-05-22;toolService;http://hdl.handle.net/20.500.11752/ILC-92;ita;info:eu-repo/grantAgreement/EC/FP7/248064;http://www.lrec-conf.org/proceedings/lrec2012/workshops/06.LREC%202012%20Merging%20Proceedings.pdf;downloadable_files_count: 0;Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR);http://www.panacea-lr.eu",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "921161d1-472e-52e0-9b5a-52f786e83f21",
-    "notes": [
-        "This is a LMF Lexical Multi level Merger web-service for the automatic merging of Lexical Entries, Syntactic Behaviours and Subcategorization Frames  from two distinct LMF lexicons. The web-service takes two LMF lexicons, A and B, and a set of directives in input and outputs one or more LMF merged lexicon(s) according to different merging scenarios. Further details can be found in: Riccardo Del Gratta & Francesca Frontini & Monica Monachini &Valeria Quochi & Francesco Rubino& Matteo Abrate & Angelica Lo Duca. 2012. L-LEME: an Automatic Lexical Merger based on the LMF Standard. In Proceedings of the Workshop on Language Resource Merging (Colocated wiyh LREC 2012), May, 22 2012, Istanbul, Turkey"
-    ],
-    "oai_identifier": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-92"
-    ],
-    "oai_set": [
-        "hdl_000-c0-111_38",
-        "hdl_000-c0-111_49"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "LFM Standard"
-        },
-        {
-            "name": "semi-automatic Lexicon Merging"
-        },
-        {
-            "name": "Similarity Score"
-        }
-    ],
-    "title": [
-        "LMF ML Merger"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/92220db6-b99f-5bbe-a152-2f05fb24c4ed.json b/oaitestdata/clarin-oai_dc/SET_1/json/92220db6-b99f-5bbe-a152-2f05fb24c4ed.json
deleted file mode 100644
index e81c14d5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/92220db6-b99f-5bbe-a152-2f05fb24c4ed.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3164",
-    "MetadataAccess": [
-        "oai:ota:oucs:3164"
-    ],
-    "PublicationTimestamp": "1846-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1846"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dickens, Charles, 1812-1870"
-    ],
-    "fulltext": "oai:ota:oucs:3164;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3164.xml;Dombey and Son;Dickens, Charles, 1812-1870;not after: 1846;text_and_corpus_linguistics;Fiction -- Great Britain -- 19th century;Novels -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "92220db6-b99f-5bbe-a152-2f05fb24c4ed",
-    "oai_identifier": [
-        "oai:ota:oucs:3164"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- Great Britain -- th century"
-        },
-        {
-            "name": "Novels -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Dombey and Son"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3164.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9242d0f6-4aa0-5373-9f3e-ddb2d5b5a481.json b/oaitestdata/clarin-oai_dc/SET_1/json/9242d0f6-4aa0-5373-9f3e-ddb2d5b5a481.json
deleted file mode 100644
index 4bbcbd41..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9242d0f6-4aa0-5373-9f3e-ddb2d5b5a481.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Andrzeja Piotrkowczyka"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-105794",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-105794"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CD6-3",
-    "PublicationTimestamp": "1623-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1623"
-    ],
-    "Publisher": [
-        "Drukarnia Andrzeja Piotrkowczyka"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/105794",
-        "oai:jbc.bj.uj.edu.pl:publication:113146"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1601/1700"
-    ],
-    "TempCoverageBegin": 50506804799,
-    "TempCoverageEnd": 50506804799,
-    "TemporalCoverage": " point in time : 1601-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1601-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1601-07-01T11:59:59Z",
-    "author": [
-        "Piekarski, Adam (15..-1625)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-105794;2019-02-28T17:59:10Z;Sm\u0119tny Wyiazd Z Po\u0142onnego Ja\u015bnie Wielmo\u017cney Iey M\u015bci Paniey Zofiey Z Ostroga Lvbomierzkiey; Podczaszyney Koronney, S\u0119domierskiey, Spiskiey [...] Staro\u015b\u0107iney : Ktor\u0105 Ludzi zacnych wielki Orszak dnia 16. Stycznia z Ukrainy wyiachawszy a\u017c do Wi\u015bnicza nie bez serdecznego \u017calu prowadzi\u0142;Piekarski, Adam (15..-1625);starodruki 17\u00a0w.;Lubomirska, Anna ( -1639). Adr. ded.;Drukarnia Andrzeja Piotrkowczyka;1623;starodruk;application/xml;clarind-uds:poldilemma-105794;hdl:11858/00-246C-0000-0023-8CD6-3;Biblioteka Jagiello\u0144ska, BJ St. Dr. 53545 I;pol;http://jbc.bj.uj.edu.pl/Content/105794;oai:jbc.bj.uj.edu.pl:publication:113146;1601/1700;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9242d0f6-4aa0-5373-9f3e-ddb2d5b5a481",
-    "notes": [
-        "Lubomirska, Anna ( -1639). Adr. ded."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-105794"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Sm\u0119tny Wyiazd Z Po\u0142onnego Ja\u015bnie Wielmo\u017cney Iey M\u015bci Paniey Zofiey Z Ostroga Lvbomierzkiey; Podczaszyney Koronney, S\u0119domierskiey, Spiskiey [...] Staro\u015b\u0107iney : Ktor\u0105 Ludzi zacnych wielki Orszak dnia 16. Stycznia z Ukrainy wyiachawszy a\u017c do Wi\u015bnicza nie bez serdecznego \u017calu prowadzi\u0142"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9254a03e-c523-583f-a9d5-e512d5832cc8.json b/oaitestdata/clarin-oai_dc/SET_1/json/9254a03e-c523-583f-a9d5-e512d5832cc8.json
deleted file mode 100644
index dfa3b453..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9254a03e-c523-583f-a9d5-e512d5832cc8.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "[S. n.]"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-592",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-592"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D29-1",
-    "PublicationTimestamp": "1661-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1661"
-    ],
-    "Publisher": [
-        "[S. n.]"
-    ],
-    "RelatedIdentifier": [
-        "http://pbc.biaman.pl/Content/592"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-592;2019-03-01T15:51:59Z;Chleb niezdrowy: Stacye Zo\u0142nierskie z Dobr Koscielnych, to jest Dyskurs, kt\u00f3rym si\u0119 pokazuje, \u017ce Stacyi, abo chleba zo\u0142nierz wyci\u0105ga\u0107 z Dobr Ko\u015bcielnych nie ma, y nie mo\u017ce.;Ko\u015bci\u00f3\u0142 katolicki - Polska -17 w.;Maj\u0105tek ko\u015bcielny;Prawo kanoniczne;ilo\u015b\u0107 skan\u00f3w: 65 ; sygn. St-341;[S. n.];1661;starodruk;application/xml;clarind-uds:poldilemma-592;hdl:11858/00-246C-0000-0023-8D29-1;pol;lat;http://pbc.biaman.pl/Content/592;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9254a03e-c523-583f-a9d5-e512d5832cc8",
-    "notes": [
-        "ilo\u015b\u0107 skan\u00f3w: 65 ; sygn. St-341"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-592"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Prawo kanoniczne"
-        }
-    ],
-    "title": [
-        "Chleb niezdrowy: Stacye Zo\u0142nierskie z Dobr Koscielnych, to jest Dyskurs, kt\u00f3rym si\u0119 pokazuje, \u017ce Stacyi, abo chleba zo\u0142nierz wyci\u0105ga\u0107 z Dobr Ko\u015bcielnych nie ma, y nie mo\u017ce."
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/926cd0fc-9c81-5d1a-9fc6-fc6a92494594.json b/oaitestdata/clarin-oai_dc/SET_1/json/926cd0fc-9c81-5d1a-9fc6-fc6a92494594.json
deleted file mode 100644
index 52585154..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/926cd0fc-9c81-5d1a-9fc6-fc6a92494594.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4393",
-    "MetadataAccess": [
-        "oai:ota:oucs:4393"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "MacNally, Leonard, 1752-1820."
-    ],
-    "fulltext": "oai:ota:oucs:4393;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4393.xml;Richard Coeur de Lion: A comic opera, as performed at the Theatre Royal Covent Garden. Taken from a French comedy of the same name, written by Monsieur Sedaine; by Leonard Macnally, Esq.;MacNally, Leonard, 1752-1820.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "926cd0fc-9c81-5d1a-9fc6-fc6a92494594",
-    "oai_identifier": [
-        "oai:ota:oucs:4393"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Richard Coeur de Lion: A comic opera, as performed at the Theatre Royal Covent Garden. Taken from a French comedy of the same name, written by Monsieur Sedaine; by Leonard Macnally, Esq."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4393.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/92a1acab-0778-5804-9924-97571cb1dcc5.json b/oaitestdata/clarin-oai_dc/SET_1/json/92a1acab-0778-5804-9924-97571cb1dcc5.json
deleted file mode 100644
index 0a333c84..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/92a1acab-0778-5804-9924-97571cb1dcc5.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Wroclaw University of Science and Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/gzip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/626",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/626"
-    ],
-    "PID": "http://hdl.handle.net/11321/626",
-    "PublicationTimestamp": "2019-02-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Wroclaw University of Science and Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Marci\u0144czuk, Micha\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/626;2019-02-07T15:28:19Z;hdl_11321_3;hdl_11321_4;PolEval 2019 Task 1: Lemmatization of proper names and multi-word phrases \u2014 training data;Marci\u0144czuk, Micha\u0142;named entities;multi-word units;lemmatization;The task consists in developing a tool for lemmatization of proper names and multi-word phrases. The generated lemmas should follow the KPWr guidelines [https://clarin-pl.eu/dspace/handle/11321/625]. \r\n\r\nThe training dataset contains XX documents from the KPWr corpus and an index of phrases with lemmas.;2019-02-07;corpus;http://hdl.handle.net/11321/626;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;application/gzip;downloadable_files_count: 1;Wroclaw University of Science and Technology;http://poleval.pl/tasks/task2",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "92a1acab-0778-5804-9924-97571cb1dcc5",
-    "notes": [
-        "The task consists in developing a tool for lemmatization of proper names and multi-word phrases. The generated lemmas should follow the KPWr guidelines [https://clarin-pl.eu/dspace/handle/11321/625]. \r\n\r\nThe training dataset contains XX documents from the KPWr corpus and an index of phrases with lemmas."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/626"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "named entities"
-        },
-        {
-            "name": "multi-word units"
-        },
-        {
-            "name": "lemmatization"
-        }
-    ],
-    "title": [
-        "PolEval 2019 Task 1: Lemmatization of proper names and multi-word phrases \u2014 training data"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/92a6d268-aae4-5c9f-9cca-7b1fd6e0616d.json b/oaitestdata/clarin-oai_dc/SET_1/json/92a6d268-aae4-5c9f-9cca-7b1fd6e0616d.json
deleted file mode 100644
index 0f5c9f6e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/92a6d268-aae4-5c9f-9cca-7b1fd6e0616d.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Delbecque, Nicole"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 105 KB)",
-        "text/plain"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0446",
-    "MetadataAccess": [
-        "oai:ota:oucs:0446"
-    ],
-    "PublicationTimestamp": "1975-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1975"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "O'Neill, Michael, 1953-"
-    ],
-    "fulltext": "oai:ota:oucs:0446;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0446.xml;The bosom of the family / Michael O'Neill;O'Neill, Michael, 1953-;1975;text_and_corpus_linguistics;English drama -- 20th century;Oxford Text Archive, University of Oxford;Delbecque, Nicole;text/plain;(1 file : ca. 105 KB);Text;Plays;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "92a6d268-aae4-5c9f-9cca-7b1fd6e0616d",
-    "oai_identifier": [
-        "oai:ota:oucs:0446"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- th century"
-        }
-    ],
-    "title": [
-        "The bosom of the family / Michael O'Neill"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0446.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/92b3f764-aa34-5962-a5bc-859a80fd53ff.json b/oaitestdata/clarin-oai_dc/SET_1/json/92b3f764-aa34-5962-a5bc-859a80fd53ff.json
deleted file mode 100644
index b90f6d08..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/92b3f764-aa34-5962-a5bc-859a80fd53ff.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "University of Stuttgart"
-    ],
-    "Contributor": [
-        "Schmid, Helmut"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-330",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-330"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-330",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Stuttgart"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-330;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;VPF parse forest browser;Schmid, Helmut;VPF is a graphical parse forest browser.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-330;downloadable_files_count: 0;Germany;University of Stuttgart;http://www.ims.uni-stuttgart.de/projekte/gramotron/SOFTWARE/VPF.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "92b3f764-aa34-5962-a5bc-859a80fd53ff",
-    "notes": [
-        "VPF is a graphical parse forest browser."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-330"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "VPF parse forest browser"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/92be2bf1-a74c-5b3f-80b2-c0e683cfecce.json b/oaitestdata/clarin-oai_dc/SET_1/json/92be2bf1-a74c-5b3f-80b2-c0e683cfecce.json
deleted file mode 100644
index 6610e42d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/92be2bf1-a74c-5b3f-80b2-c0e683cfecce.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5084",
-    "MetadataAccess": [
-        "oai:ota:oucs:5084"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pratt, Mr. (Samuel Jackson), 1749-1814."
-    ],
-    "fulltext": "oai:ota:oucs:5084;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5084.xml;Travels for the heart: Written in France, by Courtney Melmoth. In two volumes. ... [pt.2];Pratt, Mr. (Samuel Jackson), 1749-1814.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "92be2bf1-a74c-5b3f-80b2-c0e683cfecce",
-    "oai_identifier": [
-        "oai:ota:oucs:5084"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Travels for the heart: Written in France, by Courtney Melmoth. In two volumes. ... [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5084.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/92d133c2-91aa-5bc8-8f66-313453723f0c.json b/oaitestdata/clarin-oai_dc/SET_1/json/92d133c2-91aa-5bc8-8f66-313453723f0c.json
deleted file mode 100644
index 2498bc4e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/92d133c2-91aa-5bc8-8f66-313453723f0c.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/114",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/114"
-    ],
-    "PID": "http://hdl.handle.net/10794/114",
-    "PublicationTimestamp": "2017-10-26T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/114;2017-11-01T13:39:07Z;hdl_10794_1;hdl_10794_2;Blog mix 2017 (2017-10-26);Bloggmix 2017 (2017-10-26);n/a, n/a;Swedish;Blog;The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled. It currently covers January\u2013February 2017 only.;Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat. Materialet t\u00e4cker i dagsl\u00e4get endast januari och februari 2017.;2017-10-26;corpus;http://hdl.handle.net/10794/114;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/bloggmix2017",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "92d133c2-91aa-5bc8-8f66-313453723f0c",
-    "notes": [
-        "The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled. It currently covers January\u2013February 2017 only.",
-        "Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat. Materialet t\u00e4cker i dagsl\u00e4get endast januari och februari 2017."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/114"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Blog"
-        }
-    ],
-    "title": [
-        "Blog mix 2017 (2017-10-26)",
-        "Bloggmix 2017 (2017-10-26)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/92edcb8b-2ef3-5c77-a76e-24ea925c5d9c.json b/oaitestdata/clarin-oai_dc/SET_1/json/92edcb8b-2ef3-5c77-a76e-24ea925c5d9c.json
deleted file mode 100644
index 00f2a591..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/92edcb8b-2ef3-5c77-a76e-24ea925c5d9c.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Institute of Contemporary History"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 3",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1167",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1167"
-    ],
-    "PID": "http://hdl.handle.net/11356/1167",
-    "PublicationTimestamp": "2017-11-24T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Institute of Contemporary History"
-    ],
-    "RelatedIdentifier": [
-        "http://www.sdjt.si/wp/wp-content/uploads/2016/09/JTDH-2016_Pancur_Oznacevanje-zbirke-zapisnikov-sej-slovenskega-parlamenta.pdf",
-        "http://lrec-conf.org/workshops/lrec2018/W2/summaries/4_W2.html",
-        "http://hdl.handle.net/11356/1075"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u0160orn, Mojca",
-        "Erjavec, Toma\u017e",
-        "Pan\u010dur, Andrej"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1167;2018-11-14T11:24:37Z;hdl_11356_1023;hdl_11356_1024;Slovenian parliamentary corpus SlovParl 2.0;Pan\u010dur, Andrej;\u0160orn, Mojca;Erjavec, Toma\u017e;Slovenian Parliament;parliamentary debates;TEI;The SlovParl corpus contains minutes of the Assembly of the Republic of Slovenia for the legislative period 1990-1992, i.e. it covers the period before, during, and after Slovenia became an independent country in 1991. The corpus comprises 232 sessions, 58,813 speeches and 10.8 million words. The corpus contains extensive meta-data about the speakers, a typology of sessions etc. and structural and editorial annotations.\r\n\r\nThis item comprises three datasets:\r\n- the corpus in TEI (module Transcriptions of speech);\r\n- the corpus in TEI with added automatic linguistic annotation: tokenisation, MSD tagging and lemmatisation; \r\n- the corpus in vertical format used by various concordancers, e.g. CWB and Sketch Engine; this format is simpler and smaller but does not contain all the information from the source TEI.\r\n\r\nThe SlovParl data originally come from https://github.com/SIstory/SlovParl, but have been converted to use TEI elements for speech. \r\n\r\nThe first version of this resource is presented in the paper:\r\nPan\u010dur, Andrej. \"Ozna\u010devanje zbirke zapisnikov sej slovenskega parlamenta s smernicami TEI.\" In the Proceedings of the Conference on Language Technologies & Digital Humanities (Toma\u017e Erjavec and Darja Fi\u0161er, eds.) 142-148. Ljubljana: Znanstvena zalo\u017eba Filozofske fakultete v Ljubljani, 2016.;2017-11-24;corpus;http://hdl.handle.net/11356/1167;slv;http://www.sdjt.si/wp/wp-content/uploads/2016/09/JTDH-2016_Pancur_Oznacevanje-zbirke-zapisnikov-sej-slovenskega-parlamenta.pdf;http://lrec-conf.org/workshops/lrec2018/W2/summaries/4_W2.html;http://hdl.handle.net/11356/1075;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;PUB;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 3;Institute of Contemporary History;https://github.com/DARIAH-SI/CLARIN.SI/commit/1cbe75c2ae8c90fba40c167786b6c548a852944c",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "92edcb8b-2ef3-5c77-a76e-24ea925c5d9c",
-    "notes": [
-        "The SlovParl corpus contains minutes of the Assembly of the Republic of Slovenia for the legislative period 1990-1992, i.e. it covers the period before, during, and after Slovenia became an independent country in 1991. The corpus comprises 232 sessions, 58,813 speeches and 10.8 million words. The corpus contains extensive meta-data about the speakers, a typology of sessions etc. and structural and editorial annotations.\r\n\r\nThis item comprises three datasets:\r\n- the corpus in TEI (module Transcriptions of speech);\r\n- the corpus in TEI with added automatic linguistic annotation: tokenisation, MSD tagging and lemmatisation; \r\n- the corpus in vertical format used by various concordancers, e.g. CWB and Sketch Engine; this format is simpler and smaller but does not contain all the information from the source TEI.\r\n\r\nThe SlovParl data originally come from https://github.com/SIstory/SlovParl, but have been converted to use TEI elements for speech. \r\n\r\nThe first version of this resource is presented in the paper:\r\nPan\u010dur, Andrej. \"Ozna\u010devanje zbirke zapisnikov sej slovenskega parlamenta s smernicami TEI.\" In the Proceedings of the Conference on Language Technologies & Digital Humanities (Toma\u017e Erjavec and Darja Fi\u0161er, eds.) 142-148. Ljubljana: Znanstvena zalo\u017eba Filozofske fakultete v Ljubljani, 2016."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1167"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Slovenian Parliament"
-        },
-        {
-            "name": "parliamentary debates"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "Slovenian parliamentary corpus SlovParl 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/930b231b-9546-5e5c-85af-7f0a71124058.json b/oaitestdata/clarin-oai_dc/SET_1/json/930b231b-9546-5e5c-85af-7f0a71124058.json
deleted file mode 100644
index a985312d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/930b231b-9546-5e5c-85af-7f0a71124058.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1406",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1406"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1406",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1406;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;ngrams;Ted Pedersen's Ngram Statistics Package (used to identify word Ngrams that appear in large corpora using standard tests of association such as Fisher's exact test, the log likelihood ratio, Pearson's chi-squared test, the Dice Coefficient, etc.).;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1406;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "930b231b-9546-5e5c-85af-7f0a71124058",
-    "notes": [
-        "Ted Pedersen's Ngram Statistics Package (used to identify word Ngrams that appear in large corpora using standard tests of association such as Fisher's exact test, the log likelihood ratio, Pearson's chi-squared test, the Dice Coefficient, etc.)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1406"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "ngrams"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9325f73e-b5e8-5a1b-ad80-10070db5b90a.json b/oaitestdata/clarin-oai_dc/SET_1/json/9325f73e-b5e8-5a1b-ad80-10070db5b90a.json
deleted file mode 100644
index bf38738f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9325f73e-b5e8-5a1b-ad80-10070db5b90a.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "E"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2223",
-    "MetadataAccess": [
-        "oai:ota:oucs:2223"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Collections, corpora etc"
-    ],
-    "fulltext": "oai:ota:oucs:2223;2018-04-16T15:30:51Z;http://ota.ox.ac.uk/headers/2223.xml;Summer Institute of Linguistics language material;Collections, corpora etc;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;E;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9325f73e-b5e8-5a1b-ad80-10070db5b90a",
-    "oai_identifier": [
-        "oai:ota:oucs:2223"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Summer Institute of Linguistics language material"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2223.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/93664f15-19a6-58e4-807b-11d59d96e64b.json b/oaitestdata/clarin-oai_dc/SET_1/json/93664f15-19a6-58e4-807b-11d59d96e64b.json
deleted file mode 100644
index fb004bda..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/93664f15-19a6-58e4-807b-11d59d96e64b.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4636",
-    "MetadataAccess": [
-        "oai:ota:oucs:4636"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Berkeley, George, 1685-1753."
-    ],
-    "fulltext": "oai:ota:oucs:4636;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4636.xml;An essay towards a new theory of vision. By George Berkeley,;Berkeley, George, 1685-1753.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "93664f15-19a6-58e4-807b-11d59d96e64b",
-    "oai_identifier": [
-        "oai:ota:oucs:4636"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An essay towards a new theory of vision. By George Berkeley,"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4636.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/937130aa-87a7-5fb0-a9e9-bc5269819bbd.json b/oaitestdata/clarin-oai_dc/SET_1/json/937130aa-87a7-5fb0-a9e9-bc5269819bbd.json
deleted file mode 100644
index 352eeef1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/937130aa-87a7-5fb0-a9e9-bc5269819bbd.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3635",
-    "MetadataAccess": [
-        "oai:ota:oucs:3635"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hume, David, 1711-1776."
-    ],
-    "fulltext": "oai:ota:oucs:3635;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3635.xml;An enquiry concerning the principles of morals: By David Hume, Esq;.;Hume, David, 1711-1776.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "937130aa-87a7-5fb0-a9e9-bc5269819bbd",
-    "oai_identifier": [
-        "oai:ota:oucs:3635"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An enquiry concerning the principles of morals: By David Hume, Esq;."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3635.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/93744ce8-34c8-50f2-b1a3-1359f90b3984.json b/oaitestdata/clarin-oai_dc/SET_1/json/93744ce8-34c8-50f2-b1a3-1359f90b3984.json
deleted file mode 100644
index 046e7945..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/93744ce8-34c8-50f2-b1a3-1359f90b3984.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5141",
-    "MetadataAccess": [
-        "oai:ota:oucs:5141"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Jephson, Robert, 1736-1803."
-    ],
-    "fulltext": "oai:ota:oucs:5141;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5141.xml;The confessions of James Baptiste Couteau: citizen of France, written by himself: and translated from the original French, by Robert Jephson, Esq. Illustrated with nine engravings. ... [pt.1];Jephson, Robert, 1736-1803.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "93744ce8-34c8-50f2-b1a3-1359f90b3984",
-    "oai_identifier": [
-        "oai:ota:oucs:5141"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The confessions of James Baptiste Couteau: citizen of France, written by himself: and translated from the original French, by Robert Jephson, Esq. Illustrated with nine engravings. ... [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5141.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/937501af-bb5a-516b-b9ba-3280c601a762.json b/oaitestdata/clarin-oai_dc/SET_1/json/937501af-bb5a-516b-b9ba-3280c601a762.json
deleted file mode 100644
index bc658ea5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/937501af-bb5a-516b-b9ba-3280c601a762.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia J.K.M. XX Trynitarzy"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-232108",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-232108"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D10-8",
-    "PublicationTimestamp": "1787-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1787"
-    ],
-    "Publisher": [
-        "Drukarnia J.K.M. XX Trynitarzy"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/232108",
-        "oai:jbc.bj.uj.edu.pl:publication:243787"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1701/1800"
-    ],
-    "TempCoverageBegin": 53662478399,
-    "TempCoverageEnd": 53662478399,
-    "TemporalCoverage": " point in time : 1701-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1701-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1701-07-01T11:59:59Z",
-    "author": [
-        "M\u0119ci\u0144ski, J\u00f3zef (1748-1814)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-232108;2019-03-01T13:18:53Z;Kazanie na pogrzeb Wielmoznego sp. Jozefa Skarbka Kie\u0142czewskiego, starosty kachorlickiego miane przez J\u00f3zefa M\u0119ci\u0144skiego [...] w kosciele kie\u0142czewickim dnia 17 lipca roku1787 [...] Kazanie na pogrzeb Wielmoznego sp. Jozefa Skarbka Kie\u0142czewskiego, starosty kachorlickiego miane przez J\u00f3zefa M\u0119ci\u0144skiego [...] w kosciele kie\u0142czewickim dnia 17 lipca roku1787 [...];M\u0119ci\u0144ski, J\u00f3zef (1748-1814);starodruki 18\u00a0w.;Drukarnia J.K.M. XX Trynitarzy;1787;starodruk;application/xml;clarind-uds:poldilemma-232108;hdl:11858/00-246C-0000-0023-8D10-8;Biblioteka Jagiello\u0144ska, BJ St. Dr. 588010 I;pol;http://jbc.bj.uj.edu.pl/Content/232108;oai:jbc.bj.uj.edu.pl:publication:243787;1701/1800;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "937501af-bb5a-516b-b9ba-3280c601a762",
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-232108"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Kazanie na pogrzeb Wielmoznego sp. Jozefa Skarbka Kie\u0142czewskiego, starosty kachorlickiego miane przez J\u00f3zefa M\u0119ci\u0144skiego [...] w kosciele kie\u0142czewickim dnia 17 lipca roku1787 [...] Kazanie na pogrzeb Wielmoznego sp. Jozefa Skarbka Kie\u0142czewskiego, starosty kachorlickiego miane przez J\u00f3zefa M\u0119ci\u0144skiego [...] w kosciele kie\u0142czewickim dnia 17 lipca roku1787 [...]"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/937b445a-cb7e-5eab-ba94-8cf28dc9c421.json b/oaitestdata/clarin-oai_dc/SET_1/json/937b445a-cb7e-5eab-ba94-8cf28dc9c421.json
deleted file mode 100644
index d5550d03..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/937b445a-cb7e-5eab-ba94-8cf28dc9c421.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=0ef80efc2f3a11e2a2aa782bcb074135bd52a102c7af43b9a4e45fe7971e92b3",
-    "MetadataAccess": [
-        "0ef80efc2f3a11e2a2aa782bcb074135bd52a102c7af43b9a4e45fe7971e92b3"
-    ],
-    "PublicationTimestamp": "2012-11-15T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "fulltext": "0ef80efc2f3a11e2a2aa782bcb074135bd52a102c7af43b9a4e45fe7971e92b3;2018-11-15T16:39:48Z;toolService;toolService:tool;OntoLP Plugin;The OntoLP system is a plug-in for the construction environment of the ontologies Prot\u00c3\u00a9g\u00c3\u00a9. The plug-in intents to be an assistant for the engineer of ontologies for Portuguese during the execution of initial steps concerning the ontologies construction: extraction of terms which are candidates for concepts; and their organization in a hierarchical way. The system uses methods of ontologies construction from texts based on statistical measures and linguistic information. Therefore, in order to run, it's necessary a corpus as input in a XCES format and a syntactic parser, that should be PALAVRAS (available at: http://visl.sdu.dk/visl/pt/) , which gives a linguistic analysis.\n\nThe plug-in is organized in three steps: (1) tab for loading the corpus; (2) tab for the extraction of the terms; and (3) tab for the hierarchical organization of the terms (see Junior 2012).\n\nThe OntoLP tool was implemented as a plug-in for the Prot\u00c3\u00a9g\u00c3\u00a9 (available at http://protege.stanford.edu), an editor for ontologies and an environment widely used in the scientific community that supports the constructions of ontologies based on Semantic Web Technologies, as the construction of Web Ontology Language (OWL) ontologies, in accordance with the pattern defined by the World Wide Web Consortium (W3C).\n;2012-11-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "937b445a-cb7e-5eab-ba94-8cf28dc9c421",
-    "notes": [
-        "The OntoLP system is a plug-in for the construction environment of the ontologies Prot\u00c3\u00a9g\u00c3\u00a9. The plug-in intents to be an assistant for the engineer of ontologies for Portuguese during the execution of initial steps concerning the ontologies construction: extraction of terms which are candidates for concepts; and their organization in a hierarchical way. The system uses methods of ontologies construction from texts based on statistical measures and linguistic information. Therefore, in order to run, it's necessary a corpus as input in a XCES format and a syntactic parser, that should be PALAVRAS (available at: http://visl.sdu.dk/visl/pt/) , which gives a linguistic analysis.\n\nThe plug-in is organized in three steps: (1) tab for loading the corpus; (2) tab for the extraction of the terms; and (3) tab for the hierarchical organization of the terms (see Junior 2012).\n\nThe OntoLP tool was implemented as a plug-in for the Prot\u00c3\u00a9g\u00c3\u00a9 (available at http://protege.stanford.edu), an editor for ontologies and an environment widely used in the scientific community that supports the constructions of ontologies based on Semantic Web Technologies, as the construction of Web Ontology Language (OWL) ontologies, in accordance with the pattern defined by the World Wide Web Consortium (W3C).\n"
-    ],
-    "oai_identifier": [
-        "0ef80efc2f3a11e2a2aa782bcb074135bd52a102c7af43b9a4e45fe7971e92b3"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "OntoLP Plugin"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/939e7d76-533e-560c-ba01-2f31c7cf10f1.json b/oaitestdata/clarin-oai_dc/SET_1/json/939e7d76-533e-560c-ba01-2f31c7cf10f1.json
deleted file mode 100644
index d1474e39..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/939e7d76-533e-560c-ba01-2f31c7cf10f1.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Divvun - Saami Language Technology",
-        "Giellatekno - Saami Language Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "application/octet-stream",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Northern Sami",
-        "Norwegian Bokm\u00e5l"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/88",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/88"
-    ],
-    "PID": "http://hdl.handle.net/11509/88",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Divvun - Saami Language Technology",
-        "Giellatekno - Saami Language Technology"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Gerstenberger, Ciprian-Virgil"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/88;2015-10-28T10:02:47Z;hdl_11509_1;hdl_11509_2;North Saami-Norwegian Bokm\u00e5l dictionary;Gerstenberger, Ciprian-Virgil;North Saami-Norwegian Bokm\u00e5l dictionary;Bilingual Lexicon;The Saami-Norwegian Bokm\u00e5l dictionary is the work by Nils Jernsletten, Giellatekno at UiT, Divvun at the Norwegian Saami Parliament, and members of the language communities. It contains 33440 entries in Giellatekno's dictionary xml format. It may contain entries with objectionable translations, etc. If you find any errors or want to add more words, download the file, edit it, and send it back to giellatekno@uit.no and feedback@divvun.no.;2015;lexicalConceptualResource;http://hdl.handle.net/11509/88;sme;nob;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;application/zip;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;Giellatekno - Saami Language Technology;Divvun - Saami Language Technology;http://giellatekno.uit.no/index.eng.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "939e7d76-533e-560c-ba01-2f31c7cf10f1",
-    "notes": [
-        "The Saami-Norwegian Bokm\u00e5l dictionary is the work by Nils Jernsletten, Giellatekno at UiT, Divvun at the Norwegian Saami Parliament, and members of the language communities. It contains 33440 entries in Giellatekno's dictionary xml format. It may contain entries with objectionable translations, etc. If you find any errors or want to add more words, download the file, edit it, and send it back to giellatekno@uit.no and feedback@divvun.no."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/88"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Bilingual Lexicon"
-        }
-    ],
-    "title": [
-        "North Saami-Norwegian Bokm\u00e5l dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/93a4bf13-875f-50fb-a3ce-34a1bb765572.json b/oaitestdata/clarin-oai_dc/SET_1/json/93a4bf13-875f-50fb-a3ce-34a1bb765572.json
deleted file mode 100644
index 859ccf4e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/93a4bf13-875f-50fb-a3ce-34a1bb765572.json
+++ /dev/null
@@ -1,95 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1137",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1137"
-    ],
-    "PID": "http://hdl.handle.net/11356/1137",
-    "PublicationTimestamp": "2017-08-28T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "http://slovenscina2.0.trojina.si/arhiv/2016-2/2016-2-04/",
-        "http://nl.ijs.si/janes/viri/avtomatsko-oznaceni-korpusi/#Janes-Wiki",
-        "https://doi.org/10.1007/s10579-018-9425-z"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by-sa/4.0/"
-    ],
-    "author": [
-        "Erjavec, Toma\u017e",
-        "Ljube\u0161i\u0107, Nikola",
-        "Fi\u0161er, Darja"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1137;2018-10-29T10:42:44Z;hdl_11356_1023;hdl_11356_1024;Wikipedia talk corpus Janes-Wiki 1.0;Ljube\u0161i\u0107, Nikola;Erjavec, Toma\u017e;Fi\u0161er, Darja;computer-mediated communication;Wikipedia;word normalisation;tagging;lemmatisation;named entities;TEI;Janes-Wiki is an annotated corpus of discussion pages from the Slovene Wikipedia from the period 2003-08 to 2017-06. The corpus contains page and user talks and is structured into individual pages and their comments, together with their metadata. The texts in the corpus are tokenised, sentence segmented, word normalised, morphosyntactically tagged, lemmatised and annotated with named entities.;2017-08-28;corpus;http://hdl.handle.net/11356/1137;slv;http://slovenscina2.0.trojina.si/arhiv/2016-2/2016-2-04/;http://nl.ijs.si/janes/viri/avtomatsko-oznaceni-korpusi/#Janes-Wiki;https://doi.org/10.1007/s10579-018-9425-z;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);PUB;https://creativecommons.org/licenses/by-sa/4.0/;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 2;Jo\u017eef Stefan Institute;http://nl.ijs.si/janes/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "93a4bf13-875f-50fb-a3ce-34a1bb765572",
-    "notes": [
-        "Janes-Wiki is an annotated corpus of discussion pages from the Slovene Wikipedia from the period 2003-08 to 2017-06. The corpus contains page and user talks and is structured into individual pages and their comments, together with their metadata. The texts in the corpus are tokenised, sentence segmented, word normalised, morphosyntactically tagged, lemmatised and annotated with named entities."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1137"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "computer-mediated communication"
-        },
-        {
-            "name": "Wikipedia"
-        },
-        {
-            "name": "word normalisation"
-        },
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "lemmatisation"
-        },
-        {
-            "name": "named entities"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "Wikipedia talk corpus Janes-Wiki 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/93cf899b-2e75-55a3-af65-9f05b44499b7.json b/oaitestdata/clarin-oai_dc/SET_1/json/93cf899b-2e75-55a3-af65-9f05b44499b7.json
deleted file mode 100644
index 3af0b40e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/93cf899b-2e75-55a3-af65-9f05b44499b7.json
+++ /dev/null
@@ -1,49 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5651",
-    "MetadataAccess": [
-        "oai:ota:oucs:5651"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:5651;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5651.xml;A dissertation on the King's evil: with some account of a medicine which ... has cured many of that disorder, ... and has been found effectual in other complaints, ... To which are added, the cases of many persons who have been cured, and a proposal highly meriting the consideration of the public.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "93cf899b-2e75-55a3-af65-9f05b44499b7",
-    "oai_identifier": [
-        "oai:ota:oucs:5651"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A dissertation on the King's evil: with some account of a medicine which ... has cured many of that disorder, ... and has been found effectual in other complaints, ... To which are added, the cases of many persons who have been cured, and a proposal highly meriting the consideration of the public."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5651.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/93d90b4e-0e59-56fb-8419-15ac08156c81.json b/oaitestdata/clarin-oai_dc/SET_1/json/93d90b4e-0e59-56fb-8419-15ac08156c81.json
deleted file mode 100644
index 184265a9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/93d90b4e-0e59-56fb-8419-15ac08156c81.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "UW"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 11",
-        "text/plain; charset=utf-8",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/461",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/461"
-    ],
-    "PID": "http://hdl.handle.net/11321/461",
-    "PublicationTimestamp": "2018-04-12T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "UW"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "PDT 2.0 License",
-        "http://ufal.mff.cuni.cz/pdt2.0/doc/pdt-guide/en/html/ch07.html",
-        "ACA"
-    ],
-    "author": [
-        "Ochma\u0144ski, Miko\u0142aj"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/461;2018-04-12T09:40:01Z;hdl_11321_3;hdl_11321_4;Blogosferaksiazki2018;Ochma\u0144ski, Miko\u0142aj;blog;ksi\u0105\u017cki;blogosfera;Blogi ksi\u0105\u017ckowe;2018-04-12;corpus;http://hdl.handle.net/11321/461;pol;PDT 2.0 License;http://ufal.mff.cuni.cz/pdt2.0/doc/pdt-guide/en/html/ch07.html;ACA;text/plain; charset=utf-8;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;downloadable_files_count: 11;UW",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "93d90b4e-0e59-56fb-8419-15ac08156c81",
-    "notes": [
-        "Blogi ksi\u0105\u017ckowe"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/461"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "blog"
-        },
-        {
-            "name": "blog"
-        },
-        {
-            "name": "blogosfera"
-        }
-    ],
-    "title": [
-        "Blogosferaksiazki2018"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9422f969-1e75-53ce-bd34-f5c9178f6256.json b/oaitestdata/clarin-oai_dc/SET_1/json/9422f969-1e75-53ce-bd34-f5c9178f6256.json
deleted file mode 100644
index 90b29bb6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9422f969-1e75-53ce-bd34-f5c9178f6256.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Institute of Contemporary History"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 3",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1075",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1075"
-    ],
-    "PID": "http://hdl.handle.net/11356/1075",
-    "PublicationTimestamp": "2016-08-28T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Institute of Contemporary History"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11356/1167"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u0160orn, Mojca",
-        "Erjavec, Toma\u017e",
-        "Pan\u010dur, Andrej"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1075;2017-11-24T20:43:50Z;hdl_11356_1023;hdl_11356_1024;Slovenian parliamentary corpus SlovParl 1.0;Pan\u010dur, Andrej;\u0160orn, Mojca;Erjavec, Toma\u017e;Slovenian Parliament;parliamentary debates;TEI;The SlovParl corpus contains minutes of the Chamber of Associated Labour of the Assembly of the Republic of Slovenia for the legislative period 1990-1992, i.e. it covers the period before, during, and after Slovenia became an independent country in 1991. The corpus comprises 54 sessions, 13,894 speeches and almost 2.7 million words. The corpus contains extensive meta-data about the speakers, a typology of sessions etc. and structural and editorial annotations.\r\n\r\nThis item comprises three datasets:\r\n- the corpus in TEI P5 (module Transcriptions of speech);\r\n- the corpus in TEI P5 with added automatic linguistic annotation: tokenisation, MSD tagging and lemmatisation; \r\n- the corpus in vertical format used by various concordancers, e.g. CWB and Sketch Engine; this format is simpler and smaller but does not contain all the information from the source TEI.\r\n\r\nThe SlovParl data originally come from https://github.com/SIstory/SlovParl, but have been converted to use TEI elements for speech. This version of the corpus corresponds to commit https://github.com/DARIAH-SI/CLARIN.SI/tree/5984661e7b19e054b3fb650f4d2d5d409b3d7e3d\r\n\r\nThe resource is presented in the paper:\r\nPan\u010dur, Andrej. \"Ozna\u010devanje zbirke zapisnikov sej slovenskega parlamenta s smernicami TEI.\" In the Proceedings of the Conference on Language Technologies & Digital Humanities (Toma\u017e Erjavec and Darja Fi\u0161er, eds.) 142-148. Ljubljana: Znanstvena zalo\u017eba Filozofske fakultete v Ljubljani, 2016. http://www.sdjt.si/wp/wp-content/uploads/2016/09/JTDH-2016_Pancur_Oznacevanje-zbirke-zapisnikov-sej-slovenskega-parlamenta.pdf;2016-08-28;corpus;http://hdl.handle.net/11356/1075;slv;http://hdl.handle.net/11356/1167;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;PUB;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 3;Institute of Contemporary History;https://github.com/DARIAH-SI/CLARIN.SI/tree/master/SlovParl",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9422f969-1e75-53ce-bd34-f5c9178f6256",
-    "notes": [
-        "The SlovParl corpus contains minutes of the Chamber of Associated Labour of the Assembly of the Republic of Slovenia for the legislative period 1990-1992, i.e. it covers the period before, during, and after Slovenia became an independent country in 1991. The corpus comprises 54 sessions, 13,894 speeches and almost 2.7 million words. The corpus contains extensive meta-data about the speakers, a typology of sessions etc. and structural and editorial annotations.\r\n\r\nThis item comprises three datasets:\r\n- the corpus in TEI P5 (module Transcriptions of speech);\r\n- the corpus in TEI P5 with added automatic linguistic annotation: tokenisation, MSD tagging and lemmatisation; \r\n- the corpus in vertical format used by various concordancers, e.g. CWB and Sketch Engine; this format is simpler and smaller but does not contain all the information from the source TEI.\r\n\r\nThe SlovParl data originally come from https://github.com/SIstory/SlovParl, but have been converted to use TEI elements for speech. This version of the corpus corresponds to commit https://github.com/DARIAH-SI/CLARIN.SI/tree/5984661e7b19e054b3fb650f4d2d5d409b3d7e3d\r\n\r\nThe resource is presented in the paper:\r\nPan\u010dur, Andrej. \"Ozna\u010devanje zbirke zapisnikov sej slovenskega parlamenta s smernicami TEI.\" In the Proceedings of the Conference on Language Technologies & Digital Humanities (Toma\u017e Erjavec and Darja Fi\u0161er, eds.) 142-148. Ljubljana: Znanstvena zalo\u017eba Filozofske fakultete v Ljubljani, 2016. http://www.sdjt.si/wp/wp-content/uploads/2016/09/JTDH-2016_Pancur_Oznacevanje-zbirke-zapisnikov-sej-slovenskega-parlamenta.pdf"
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1075"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Slovenian Parliament"
-        },
-        {
-            "name": "parliamentary debates"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "Slovenian parliamentary corpus SlovParl 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/942a7e72-c55c-5c98-8dc5-a2add7609cc3.json b/oaitestdata/clarin-oai_dc/SET_1/json/942a7e72-c55c-5c98-8dc5-a2add7609cc3.json
deleted file mode 100644
index 54ce834b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/942a7e72-c55c-5c98-8dc5-a2add7609cc3.json
+++ /dev/null
@@ -1,107 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-DB11-8",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-DB11-8"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0006-DB11-8",
-    "PublicationTimestamp": "2011-12-06T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11858/00-097C-0000-0001-B098-5",
-        "http://hdl.handle.net/11858/00-097C-0000-0001-B098-5",
-        "http://hdl.handle.net/11858/00-097C-0000-0023-1AAF-3"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Spoustov\u00e1, Johanka",
-        "M\u00edrovsk\u00fd, Ji\u0159\u00ed",
-        "Klyueva, Natalia",
-        "Panevov\u00e1, Jarmila",
-        "Haji\u010d, Jan",
-        "Homola, Petr",
-        "\u0160t\u011bp\u00e1nek, Jan",
-        "\u0160id\u00e1k, Pavel",
-        "Popelka, Jan",
-        "\u0160ev\u010d\u00edkov\u00e1, Magda",
-        "Smejkalov\u00e1, Lenka",
-        "Bej\u010dek, Eduard",
-        "\u0160\u0165astn\u00e1, Eva",
-        "Lopatkov\u00e1, Mark\u00e9ta",
-        "Vimmrov\u00e1, Pavl\u00edna",
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "Stra\u0148\u00e1k, Pavel",
-        "Hrabalov\u00e1, Lucie"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-DB11-8;2018-07-02T22:05:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Prague Dependency Treebank 2.5;Bej\u010dek, Eduard;Haji\u010d, Jan;Panevov\u00e1, Jarmila;M\u00edrovsk\u00fd, Ji\u0159\u00ed;Spoustov\u00e1, Johanka;\u0160t\u011bp\u00e1nek, Jan;Stra\u0148\u00e1k, Pavel;\u0160id\u00e1k, Pavel;Vimmrov\u00e1, Pavl\u00edna;\u0160\u0165astn\u00e1, Eva;\u0160ev\u010d\u00edkov\u00e1, Magda;Smejkalov\u00e1, Lenka;Homola, Petr;Popelka, Jan;Lopatkov\u00e1, Mark\u00e9ta;Hrabalov\u00e1, Lucie;Klyueva, Natalia;\u017dabokrtsk\u00fd, Zden\u011bk;treebank;multiword expressions;clauses;tectogrammatics;dependency;PDT;The Prague Dependency Treebank 2.5 annotates the same texts as the PDT 2.0. The annotation on the original four layers was fixed or improved in various aspects (see Documentation). Moreover, new information was added to the data:\r\n\r\nAnnotation of multiword expressions\r\nPair/group meaning\r\nClause segmentation;2011-12-06;corpus;http://hdl.handle.net/11858/00-097C-0000-0006-DB11-8;ces;http://hdl.handle.net/11858/00-097C-0000-0001-B098-5;http://hdl.handle.net/11858/00-097C-0000-0001-B098-5;http://hdl.handle.net/11858/00-097C-0000-0023-1AAF-3;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/pdt2.5",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "942a7e72-c55c-5c98-8dc5-a2add7609cc3",
-    "notes": [
-        "The Prague Dependency Treebank 2.5 annotates the same texts as the PDT 2.0. The annotation on the original four layers was fixed or improved in various aspects (see Documentation). Moreover, new information was added to the data:\r\n\r\nAnnotation of multiword expressions\r\nPair/group meaning\r\nClause segmentation"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-DB11-8"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "multiword expressions"
-        },
-        {
-            "name": "clauses"
-        },
-        {
-            "name": "tectogrammatics"
-        },
-        {
-            "name": "dependency"
-        },
-        {
-            "name": "PDT"
-        }
-    ],
-    "title": [
-        "Prague Dependency Treebank 2.5"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9435e476-8dde-5e13-a222-3c58f586a6e8.json b/oaitestdata/clarin-oai_dc/SET_1/json/9435e476-8dde-5e13-a222-3c58f586a6e8.json
deleted file mode 100644
index 7a3ca2b9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9435e476-8dde-5e13-a222-3c58f586a6e8.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4790",
-    "MetadataAccess": [
-        "oai:ota:oucs:4790"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Mason, William, 1725-1797."
-    ],
-    "fulltext": "oai:ota:oucs:4790;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4790.xml;Caractacus: a dramatic poem: written on the model of the ancient Greek tragedy. By the author of Elfrida.;Mason, William, 1725-1797.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9435e476-8dde-5e13-a222-3c58f586a6e8",
-    "oai_identifier": [
-        "oai:ota:oucs:4790"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Caractacus: a dramatic poem: written on the model of the ancient Greek tragedy. By the author of Elfrida."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4790.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/943c6b1b-117a-581e-809c-74fc658ccf07.json b/oaitestdata/clarin-oai_dc/SET_1/json/943c6b1b-117a-581e-809c-74fc658ccf07.json
deleted file mode 100644
index c62587a0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/943c6b1b-117a-581e-809c-74fc658ccf07.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/43",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/43"
-    ],
-    "PID": "http://hdl.handle.net/10794/43",
-    "PublicationTimestamp": "2012-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/43;2017-10-27T11:20:55Z;hdl_10794_1;hdl_10794_2;Swedberg's Swensk Ordabok (morphology, rudimentary) (2017-10-16);Swedbergs Swensk ordabok (morfologi, f.n. rudiment\u00e4r) (2017-10-16);n/a, n/a;Swedish;Morphology;Swedberg's Swensk Ordabok (morphology, rudimentary).;Swedbergs Swensk ordabok (morfologi, f.n. rudiment\u00e4r).;2012-05-30;lexicalConceptualResource;http://hdl.handle.net/10794/43;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;http://creativecommons.org/licenses/by/4.0/;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/swedbergm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "943c6b1b-117a-581e-809c-74fc658ccf07",
-    "notes": [
-        "Swedberg's Swensk Ordabok (morphology, rudimentary).",
-        "Swedbergs Swensk ordabok (morfologi, f.n. rudiment\u00e4r)."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/43"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Morphology"
-        }
-    ],
-    "title": [
-        "Swedberg's Swensk Ordabok (morphology, rudimentary) (2017-10-16)",
-        "Swedbergs Swensk ordabok (morfologi, f.n. rudiment\u00e4r) (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/944f5b05-a81e-53d0-9d9b-77bed1eb4ff4.json b/oaitestdata/clarin-oai_dc/SET_1/json/944f5b05-a81e-53d0-9d9b-77bed1eb4ff4.json
deleted file mode 100644
index 79eddf6b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/944f5b05-a81e-53d0-9d9b-77bed1eb4ff4.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Universit\u00e4t des Saarlandes"
-    ],
-    "Contributor": [
-        "Knappen, J\u00f6rg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Catalan",
-        "Dutch",
-        "English",
-        "French",
-        "German",
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-344",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-344"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-344",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Universit\u00e4t des Saarlandes"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-344;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TeLeMaCo;Knappen, J\u00f6rg;documentation;A collection of pointers to teaching and learning materials on linguistics and linguistic tools, including quick starts, how-tos, technical documentation, short teaching modules (2h), and full courses. This resource is collaboratively built by its users.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-344;cat;nld;eng;fra;deu;ita;downloadable_files_count: 0;Germany;Universit\u00e4t des Saarlandes;https://fedora.clarin-d.uni-saarland.de/hub/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "944f5b05-a81e-53d0-9d9b-77bed1eb4ff4",
-    "notes": [
-        "A collection of pointers to teaching and learning materials on linguistics and linguistic tools, including quick starts, how-tos, technical documentation, short teaching modules (2h), and full courses. This resource is collaboratively built by its users."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-344"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "documentation"
-        }
-    ],
-    "title": [
-        "TeLeMaCo"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/94781c7d-cf55-52d5-90e3-ccfefff2d8f1.json b/oaitestdata/clarin-oai_dc/SET_1/json/94781c7d-cf55-52d5-90e3-ccfefff2d8f1.json
deleted file mode 100644
index 9475c0fa..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/94781c7d-cf55-52d5-90e3-ccfefff2d8f1.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(20 files : ca. 2.4 MB)"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0282",
-    "MetadataAccess": [
-        "oai:ota:oucs:0282"
-    ],
-    "PublicationYear": [
-        "370 BCE-354 BCE"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Local histories",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Xenophon"
-    ],
-    "fulltext": "oai:ota:oucs:0282;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0282.xml;Major works / Xenophon;Xenophon;370 BCE-354 BCE;text_and_corpus_linguistics;Greek prose literature -- Greece -- 5th century B.C.;Greek literature -- Greece -- 5th century B.C.;grc;Oxford Text Archive, University of Oxford;(20 files : ca. 2.4 MB);Text;Local histories;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "94781c7d-cf55-52d5-90e3-ccfefff2d8f1",
-    "oai_identifier": [
-        "oai:ota:oucs:0282"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Greek literature -- Greece -- th century B.C."
-        }
-    ],
-    "title": [
-        "Major works / Xenophon"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0282.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/947e0c28-69a5-598f-93b8-8ffb5d5afe2e.json b/oaitestdata/clarin-oai_dc/SET_1/json/947e0c28-69a5-598f-93b8-8ffb5d5afe2e.json
deleted file mode 100644
index ed17245c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/947e0c28-69a5-598f-93b8-8ffb5d5afe2e.json
+++ /dev/null
@@ -1,90 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1740",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1740"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1740",
-    "PublicationTimestamp": "2016-06-16T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11858/00-097C-0000-0023-4670-6"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Jur\u010d\u00ed\u010dek, Filip",
-        "Du\u0161ek, Ond\u0159ej",
-        "Pl\u00e1tek, Ond\u0159ej"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1740;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Vystadial 2016 \u2013 Czech data;Pl\u00e1tek, Ond\u0159ej;Du\u0161ek, Ond\u0159ej;Jur\u010d\u00ed\u010dek, Filip;acoustic data;speech corpus;spoken corpus;telephone speech;voip;dialogue system;This is the Czech data collected during the `VYSTADIAL` project. It is an extension of the 'Vystadial 2013' Czech part data release. The dataset comprises of telephone conversations in Czech, developed for training acoustic models for automatic speech recognition in spoken dialogue systems.;2016-06-16;corpus;http://hdl.handle.net/11234/1-1740;ces;http://hdl.handle.net/11858/00-097C-0000-0023-4670-6;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics;https://ufal.mff.cuni.cz/grants/vystadial",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "947e0c28-69a5-598f-93b8-8ffb5d5afe2e",
-    "notes": [
-        "This is the Czech data collected during the `VYSTADIAL` project. It is an extension of the 'Vystadial 2013' Czech part data release. The dataset comprises of telephone conversations in Czech, developed for training acoustic models for automatic speech recognition in spoken dialogue systems."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1740"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "acoustic data"
-        },
-        {
-            "name": "speech corpus"
-        },
-        {
-            "name": "spoken corpus"
-        },
-        {
-            "name": "telephone speech"
-        },
-        {
-            "name": "voip"
-        },
-        {
-            "name": "dialogue system"
-        }
-    ],
-    "title": [
-        "Vystadial 2016 \u2013 Czech data"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/947fa908-2675-5ebc-a04b-4dc7109d0ff5.json b/oaitestdata/clarin-oai_dc/SET_1/json/947fa908-2675-5ebc-a04b-4dc7109d0ff5.json
deleted file mode 100644
index cf6c00b0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/947fa908-2675-5ebc-a04b-4dc7109d0ff5.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5388",
-    "MetadataAccess": [
-        "oai:ota:oucs:5388"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "More, Hannah, 1745-1833."
-    ],
-    "fulltext": "oai:ota:oucs:5388;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5388.xml;John the shopkeeper turned sailor; Part III;Shopkeeper turned sailor.;More, Hannah, 1745-1833.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "947fa908-2675-5ebc-a04b-4dc7109d0ff5",
-    "oai_identifier": [
-        "oai:ota:oucs:5388"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "John the shopkeeper turned sailor; Part III",
-        "Shopkeeper turned sailor."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5388.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/94b88ae1-9d46-5c07-988b-00f79c48d991.json b/oaitestdata/clarin-oai_dc/SET_1/json/94b88ae1-9d46-5c07-988b-00f79c48d991.json
deleted file mode 100644
index 95fd2b31..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/94b88ae1-9d46-5c07-988b-00f79c48d991.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=4ab1ea58e6d311e6a2aa782bcb0741351e920e18429e4d3e9d229a58030812fe",
-    "MetadataAccess": [
-        "4ab1ea58e6d311e6a2aa782bcb0741351e920e18429e4d3e9d229a58030812fe"
-    ],
-    "PublicationTimestamp": "2017-01-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "fulltext": "4ab1ea58e6d311e6a2aa782bcb0741351e920e18429e4d3e9d229a58030812fe;2018-11-15T16:40:24Z;corpus;corpus:text;LX-SimLex-999;The LX-SimLex-999 was created from SimLex-999 (Hill et al., 2015) which, in turn, was based in the University of South Florida Free Association Database (USF) (Nelson et al., 2014).\nThere were strict guidelines to create SimLex-999. Both words in each pair have the same morphosyntactic category and the multiword expressions and named entities were excluded from that data set. Besides the morphosyntactic category criteria, the level of concreteness of each word was important. The word pairs in the USF data set had been tagged with a concreteness level that was provided by human annotators, on a scale of 1-7. In the creation of SimLex-999, this classification was taken into account and the pairs in which one of the concepts was more concrete than the other were not included.  \nThe result was 999 word pairs organized in the following way: 666 pairs of noun-noun, 222 pairs of verb-verb and 111 pairs of adjective-adjective. Each pair received a score on a scale from 0 (totally unrelated) to 6 (very similar).;2017-01-30",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "94b88ae1-9d46-5c07-988b-00f79c48d991",
-    "notes": [
-        "The LX-SimLex-999 was created from SimLex-999 (Hill et al., 2015) which, in turn, was based in the University of South Florida Free Association Database (USF) (Nelson et al., 2014).\nThere were strict guidelines to create SimLex-999. Both words in each pair have the same morphosyntactic category and the multiword expressions and named entities were excluded from that data set. Besides the morphosyntactic category criteria, the level of concreteness of each word was important. The word pairs in the USF data set had been tagged with a concreteness level that was provided by human annotators, on a scale of 1-7. In the creation of SimLex-999, this classification was taken into account and the pairs in which one of the concepts was more concrete than the other were not included.  \nThe result was 999 word pairs organized in the following way: 666 pairs of noun-noun, 222 pairs of verb-verb and 111 pairs of adjective-adjective. Each pair received a score on a scale from 0 (totally unrelated) to 6 (very similar)."
-    ],
-    "oai_identifier": [
-        "4ab1ea58e6d311e6a2aa782bcb0741351e920e18429e4d3e9d229a58030812fe"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "LX-SimLex-999"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/94c44a9d-971f-5117-80f0-7f8fd89d22f7.json b/oaitestdata/clarin-oai_dc/SET_1/json/94c44a9d-971f-5117-80f0-7f8fd89d22f7.json
deleted file mode 100644
index e58a6e22..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/94c44a9d-971f-5117-80f0-7f8fd89d22f7.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3485",
-    "MetadataAccess": [
-        "oai:ota:oucs:3485"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Defoe, Daniel, 1661?-1731."
-    ],
-    "fulltext": "oai:ota:oucs:3485;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3485.xml;Some objections humbly offered to the consideration of the Hon. House of Commons, relating to the present intended relief of prisoners;Defoe, Daniel, 1661?-1731.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "94c44a9d-971f-5117-80f0-7f8fd89d22f7",
-    "oai_identifier": [
-        "oai:ota:oucs:3485"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Some objections humbly offered to the consideration of the Hon. House of Commons, relating to the present intended relief of prisoners"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3485.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/94dd53a3-36cf-5a0f-abe4-0ae1eb3c36fb.json b/oaitestdata/clarin-oai_dc/SET_1/json/94dd53a3-36cf-5a0f-abe4-0ae1eb3c36fb.json
deleted file mode 100644
index 830f047a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/94dd53a3-36cf-5a0f-abe4-0ae1eb3c36fb.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/pdf"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/609",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/609"
-    ],
-    "PID": "http://hdl.handle.net/11321/609",
-    "PublicationTimestamp": "2018-10-30T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Koco\u0144, Jan"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/609;2018-10-30T11:04:51Z;hdl_11321_3;hdl_11321_4;KPWr annotation guidelines - normalisation of temporal expressions;Koco\u0144, Jan;TIMEX3;Timex;TimeML;normalisation;temporal expressions;KPWr annotation guidelines - local and global normalisation of temporal expressions;2018-10-30;languageDescription;http://hdl.handle.net/11321/609;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain; charset=utf-8;application/pdf;downloadable_files_count: 1;Wroc\u0142aw University of Science and Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "94dd53a3-36cf-5a0f-abe4-0ae1eb3c36fb",
-    "notes": [
-        "KPWr annotation guidelines - local and global normalisation of temporal expressions"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/609"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "TIMEX"
-        },
-        {
-            "name": "Timex"
-        },
-        {
-            "name": "TimeML"
-        },
-        {
-            "name": "normalisation"
-        },
-        {
-            "name": "temporal expressions"
-        }
-    ],
-    "title": [
-        "KPWr annotation guidelines - normalisation of temporal expressions"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/94e577cd-e1e9-5a08-bc6c-80bcca2b5c3c.json b/oaitestdata/clarin-oai_dc/SET_1/json/94e577cd-e1e9-5a08-bc6c-80bcca2b5c3c.json
deleted file mode 100644
index f602a43c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/94e577cd-e1e9-5a08-bc6c-80bcca2b5c3c.json
+++ /dev/null
@@ -1,91 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2422",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2422"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2422",
-    "PublicationTimestamp": "2017-09-26T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-1807",
-        "http://hdl.handle.net/11234/1-2873"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "Vidra, Jon\u00e1\u0161",
-        "Kalu\u017eov\u00e1, Ad\u00e9la",
-        "\u0160ev\u010d\u00edkov\u00e1, Magda",
-        "Mediankin, Nikita",
-        "Straka, Milan"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2422;2018-09-24T19:15:53Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;DeriNet 1.5;Vidra, Jon\u00e1\u0161;\u017dabokrtsk\u00fd, Zden\u011bk;\u0160ev\u010d\u00edkov\u00e1, Magda;Kalu\u017eov\u00e1, Ad\u00e9la;Mediankin, Nikita;Straka, Milan;DeriNet;derivation;derivational morphology;lexical network;MorfFlex;DeriNet is a lexical network which models derivational relations in the lexicon of Czech. Nodes of the network correspond to Czech lexemes, while edges represent derivational relations between a derived word and its base word. The present version, DeriNet 1.5, contains 1,011,965 lexemes (sampled from the MorfFlex dictionary) connected by 785,543 derivational links. Besides several rather conservative updates (such as newly identified prefix and suffix verb-to-verb derivations as well as noun-to-adjective derivations manifested by most frequent adjectival suffixes), DeriNet 1.5 is the first version that contains annotations related to compounding (compound words are distinguished by a special mark in their part-of-speech labels).;2017-09-26;lexicalConceptualResource;http://hdl.handle.net/11234/1-2422;ces;http://hdl.handle.net/11234/1-1807;http://hdl.handle.net/11234/1-2873;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://ufal.mff.cuni.cz/derinet",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "94e577cd-e1e9-5a08-bc6c-80bcca2b5c3c",
-    "notes": [
-        "DeriNet is a lexical network which models derivational relations in the lexicon of Czech. Nodes of the network correspond to Czech lexemes, while edges represent derivational relations between a derived word and its base word. The present version, DeriNet 1.5, contains 1,011,965 lexemes (sampled from the MorfFlex dictionary) connected by 785,543 derivational links. Besides several rather conservative updates (such as newly identified prefix and suffix verb-to-verb derivations as well as noun-to-adjective derivations manifested by most frequent adjectival suffixes), DeriNet 1.5 is the first version that contains annotations related to compounding (compound words are distinguished by a special mark in their part-of-speech labels)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2422"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "DeriNet"
-        },
-        {
-            "name": "derivation"
-        },
-        {
-            "name": "derivational morphology"
-        },
-        {
-            "name": "lexical network"
-        },
-        {
-            "name": "MorfFlex"
-        }
-    ],
-    "title": [
-        "DeriNet 1.5"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/94e6dc4d-6a6d-5aa2-872f-15ba09b4e0be.json b/oaitestdata/clarin-oai_dc/SET_1/json/94e6dc4d-6a6d-5aa2-872f-15ba09b4e0be.json
deleted file mode 100644
index f8df8ed9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/94e6dc4d-6a6d-5aa2-872f-15ba09b4e0be.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Asmussen, J\u00f6rg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Danish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-247",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-247"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-247",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Denmark"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-247;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Parole DK;Asmussen, J\u00f6rg;written, general language; pos, manually checked; 250000 tokens;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-247;dan;downloadable_files_count: 0;Denmark;http://ordnet.dk/korpusdk",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "94e6dc4d-6a6d-5aa2-872f-15ba09b4e0be",
-    "notes": [
-        "written, general language; pos, manually checked; 250000 tokens"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-247"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Parole DK"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/94fca87a-b46f-5489-a6e2-01e709165383.json b/oaitestdata/clarin-oai_dc/SET_1/json/94fca87a-b46f-5489-a6e2-01e709165383.json
deleted file mode 100644
index 737c9be7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/94fca87a-b46f-5489-a6e2-01e709165383.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Pawe\u0142 K\u0119dzia"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/280",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/280"
-    ],
-    "PID": "http://hdl.handle.net/11321/280",
-    "PublicationTimestamp": "2016-06-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Pawe\u0142 K\u0119dzia"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "K\u0119dzia, Pawe\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/280;2016-06-03T13:11:04Z;hdl_11321_3;hdl_11321_4;Grafon;K\u0119dzia, Pawe\u0142;Graph;Semantic graph;Representation of sentence semantic with deepened semantic graphs. Graphs are composed based on the output of saper tool https://clarin-pl.eu/dspace/handle/11321/278;2016-06-01;toolService;http://hdl.handle.net/11321/280;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 1;Pawe\u0142 K\u0119dzia",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "94fca87a-b46f-5489-a6e2-01e709165383",
-    "notes": [
-        "Representation of sentence semantic with deepened semantic graphs. Graphs are composed based on the output of saper tool https://clarin-pl.eu/dspace/handle/11321/278"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/280"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Graph"
-        },
-        {
-            "name": "Semantic graph"
-        }
-    ],
-    "title": [
-        "Grafon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/951e86c5-a13e-57c7-b1f7-8960fe6771c4.json b/oaitestdata/clarin-oai_dc/SET_1/json/951e86c5-a13e-57c7-b1f7-8960fe6771c4.json
deleted file mode 100644
index dc6aabbe..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/951e86c5-a13e-57c7-b1f7-8960fe6771c4.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3542",
-    "MetadataAccess": [
-        "oai:ota:oucs:3542"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "More, Hannah, 1745-1833."
-    ],
-    "fulltext": "oai:ota:oucs:3542;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3542.xml;The happy waterman;More, Hannah, 1745-1833.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "951e86c5-a13e-57c7-b1f7-8960fe6771c4",
-    "oai_identifier": [
-        "oai:ota:oucs:3542"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The happy waterman"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3542.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/955b77d3-6fdd-5a4e-b89e-414572011992.json b/oaitestdata/clarin-oai_dc/SET_1/json/955b77d3-6fdd-5a4e-b89e-414572011992.json
deleted file mode 100644
index 41b4b9fc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/955b77d3-6fdd-5a4e-b89e-414572011992.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3892",
-    "MetadataAccess": [
-        "oai:ota:oucs:3892"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Lillo, George, 1693-1739."
-    ],
-    "fulltext": "oai:ota:oucs:3892;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3892.xml;Britannia and Batavia: a masque. Written on the marriage of the Princess Royal with his Highness the Prince of Orange. By the late Mr. Lillo.;Lillo, George, 1693-1739.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "955b77d3-6fdd-5a4e-b89e-414572011992",
-    "oai_identifier": [
-        "oai:ota:oucs:3892"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Britannia and Batavia: a masque. Written on the marriage of the Princess Royal with his Highness the Prince of Orange. By the late Mr. Lillo."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3892.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/956db74e-902e-5beb-ae04-45c4c78b9a7a.json b/oaitestdata/clarin-oai_dc/SET_1/json/956db74e-902e-5beb-ae04-45c4c78b9a7a.json
deleted file mode 100644
index 1c385b30..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/956db74e-902e-5beb-ae04-45c4c78b9a7a.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-551",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-551"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-551",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Slovenia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-551;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;e-ZRC;Digital library of Slovenian text-critical editions;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-551;slv;downloadable_files_count: 0;Slovenia;http://nl.ijs.si/e-zrc/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "956db74e-902e-5beb-ae04-45c4c78b9a7a",
-    "notes": [
-        "Digital library of Slovenian text-critical editions"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-551"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "e-ZRC"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9570b4a4-0159-50b9-9f5c-ee789df65c1f.json b/oaitestdata/clarin-oai_dc/SET_1/json/9570b4a4-0159-50b9-9f5c-ee789df65c1f.json
deleted file mode 100644
index 7acfb3d5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9570b4a4-0159-50b9-9f5c-ee789df65c1f.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Trojina, Institute for Applied Slovene Studies",
-        "Faculty of Arts, University of Ljubljana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1046",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1046"
-    ],
-    "PID": "http://hdl.handle.net/11356/1046",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Trojina, Institute for Applied Slovene Studies",
-        "Faculty of Arts, University of Ljubljana"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11356/1195"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by-sa/4.0/"
-    ],
-    "author": [
-        "Dobrovoljc, Kaja"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1046;2018-08-03T18:53:43Z;hdl_11356_1023;hdl_11356_1024;Gos corpus n-grams 1.0;Dobrovoljc, Kaja;n-grams;wordlist;multiword expressions;This is a collection of n-grams extracted from the Gos corpus of  spoken Slovene. http://hdl.handle.net/11356/1040. In addition to the separate lists of n-grams for tokens and their attributes (normalized form, morphosyntacic tag, lemma), an adjusted frequency list with statistical substring reduction has also been added (as described in O'Donnell 2011). Only n-grams within sentences have been counted.;2015-07-01;lexicalConceptualResource;http://hdl.handle.net/11356/1046;slv;http://hdl.handle.net/11356/1195;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);PUB;https://creativecommons.org/licenses/by-sa/4.0/;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 4;Trojina, Institute for Applied Slovene Studies;Faculty of Arts, University of Ljubljana;http://eng.slovenscina.eu/korpusi/gos",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9570b4a4-0159-50b9-9f5c-ee789df65c1f",
-    "notes": [
-        "This is a collection of n-grams extracted from the Gos corpus of  spoken Slovene. http://hdl.handle.net/11356/1040. In addition to the separate lists of n-grams for tokens and their attributes (normalized form, morphosyntacic tag, lemma), an adjusted frequency list with statistical substring reduction has also been added (as described in O'Donnell 2011). Only n-grams within sentences have been counted."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1046"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "n-grams"
-        },
-        {
-            "name": "wordlist"
-        },
-        {
-            "name": "multiword expressions"
-        }
-    ],
-    "title": [
-        "Gos corpus n-grams 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/958b21b0-2d92-5652-baa7-26b46b05ccaf.json b/oaitestdata/clarin-oai_dc/SET_1/json/958b21b0-2d92-5652-baa7-26b46b05ccaf.json
deleted file mode 100644
index 3ad0168a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/958b21b0-2d92-5652-baa7-26b46b05ccaf.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Croatian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1202",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1202"
-    ],
-    "PID": "http://hdl.handle.net/11356/1202",
-    "PublicationTimestamp": "2018-10-27T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "https://drive.google.com/file/d/13m7PFn49_tnEfFjcbqk8cugG4ZTy2A5I/view"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "https://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Erjavec, Toma\u017e",
-        "Ljube\u0161i\u0107, Nikola",
-        "Fi\u0161er, Darja"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1202;2018-10-27T13:53:27Z;hdl_11356_1023;hdl_11356_1024;Dataset and baseline model of moderated content FRENK-STYRIA-24sata 1.0;Ljube\u0161i\u0107, Nikola;Erjavec, Toma\u017e;Fi\u0161er, Darja;computer-mediated communication;news comments;content moderation;FRENK-STYRIA-24sata is a dataset of moderated newspaper comments from the website 24sata.hr with metadata on the time of publishing, user identifier, thread identifier and whether the comment was deleted by the moderators or not. The full text of each comment is encrypted via a character-replacement method so that the comments are not readable by humans. Basic punctuation is not encrypted in order to enable tokenization. The main use of this dataset are experiments on automating comment moderation. For real-world usage, a fastText classification model trained on non-encrypted data is made available as well.;2018-10-27;corpus;http://hdl.handle.net/11356/1202;hrv;https://drive.google.com/file/d/13m7PFn49_tnEfFjcbqk8cugG4ZTy2A5I/view;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);https://creativecommons.org/licenses/by-sa/4.0/;PUB;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 2;Jo\u017eef Stefan Institute;http://nl.ijs.si/frenk/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "958b21b0-2d92-5652-baa7-26b46b05ccaf",
-    "notes": [
-        "FRENK-STYRIA-24sata is a dataset of moderated newspaper comments from the website 24sata.hr with metadata on the time of publishing, user identifier, thread identifier and whether the comment was deleted by the moderators or not. The full text of each comment is encrypted via a character-replacement method so that the comments are not readable by humans. Basic punctuation is not encrypted in order to enable tokenization. The main use of this dataset are experiments on automating comment moderation. For real-world usage, a fastText classification model trained on non-encrypted data is made available as well."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1202"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "computer-mediated communication"
-        },
-        {
-            "name": "news comments"
-        },
-        {
-            "name": "content moderation"
-        }
-    ],
-    "title": [
-        "Dataset and baseline model of moderated content FRENK-STYRIA-24sata 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/958e8c64-9e19-5c9e-a730-0407b5146347.json b/oaitestdata/clarin-oai_dc/SET_1/json/958e8c64-9e19-5c9e-a730-0407b5146347.json
deleted file mode 100644
index b5416fbd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/958e8c64-9e19-5c9e-a730-0407b5146347.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=e69034fa616e11e2a2aa782bcb07413563a2d5c389e04e779bf58a3b09dc588e",
-    "MetadataAccess": [
-        "e69034fa616e11e2a2aa782bcb07413563a2d5c389e04e779bf58a3b09dc588e"
-    ],
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "e69034fa616e11e2a2aa782bcb07413563a2d5c389e04e779bf58a3b09dc588e;2019-02-27T12:09:30Z;corpus;corpus:text;PropBankPT;The PropBankPT (Branco et al., 2012) is a set of sentences annotated with their constituency structure and semantic role tags, composed of 3,406 sentences and 44,598 tokens taken from the Wall Street Journal translated. \nFor the creation of this PropBank we adopted a semi-automatic analysis with a double-blind annotation followed by adjudication. The resulting dataset contains three information levels: phrase constituency, grammatical functions, and phrase semantic roles.\nThe main motivation behind the creation of this resource was to build a high quality data set with semantic information that could support the development of automatic semantic role labelers for Portuguese.\nThe development of this resource started under the METANET4U project (at: http://metanet4u.eu/) whose main goal is to contribute to the establishment of a pan-European digital platform that makes available language resources and services, encompassing both datasets and software tools, for speech and language processing, and supports a new generation of exchange facilities for them. \n;2015-12-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "958e8c64-9e19-5c9e-a730-0407b5146347",
-    "notes": [
-        "The PropBankPT (Branco et al., 2012) is a set of sentences annotated with their constituency structure and semantic role tags, composed of 3,406 sentences and 44,598 tokens taken from the Wall Street Journal translated. \nFor the creation of this PropBank we adopted a semi-automatic analysis with a double-blind annotation followed by adjudication. The resulting dataset contains three information levels: phrase constituency, grammatical functions, and phrase semantic roles.\nThe main motivation behind the creation of this resource was to build a high quality data set with semantic information that could support the development of automatic semantic role labelers for Portuguese.\nThe development of this resource started under the METANET4U project (at: http://metanet4u.eu/) whose main goal is to contribute to the establishment of a pan-European digital platform that makes available language resources and services, encompassing both datasets and software tools, for speech and language processing, and supports a new generation of exchange facilities for them. \n"
-    ],
-    "oai_identifier": [
-        "e69034fa616e11e2a2aa782bcb07413563a2d5c389e04e779bf58a3b09dc588e"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "PropBankPT"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9594a562-4751-5dad-94ef-8a3b0d2def85.json b/oaitestdata/clarin-oai_dc/SET_1/json/9594a562-4751-5dad-94ef-8a3b0d2def85.json
deleted file mode 100644
index 0e9d7ade..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9594a562-4751-5dad-94ef-8a3b0d2def85.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Information Studies Novo mesto"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/plain",
-        "downloadable_files_count: 2"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1112",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1112"
-    ],
-    "PID": "http://hdl.handle.net/11356/1112",
-    "PublicationTimestamp": "2017-05-09T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Faculty of Information Studies Novo mesto"
-    ],
-    "RelatedIdentifier": [
-        "https://doi.org/10.1007/s10579-018-9413-3"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "https://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Bu\u010dar, Jo\u017ee"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1112;2018-03-12T16:17:41Z;hdl_11356_1023;hdl_11356_1024;Slovene sentiment lexicon JOB 1.0;Bu\u010dar, Jo\u017ee;sentiment lexicon;opinion lexicon;The JOB lexicon for sentiment analysis of Slovenian texts contains a list of 25,524 headwords from the List of Slovenian headwords 1.1 (http://hdl.handle.net/11356/1038) extended with sentiment ratings based on the AFINN model with an integer between -5 (very negative) and +5 (very positive). The ratings are derived from the lemmatized version of the Manually sentiment annotated Slovenian (sentence-based) news corpus SentiNews 1.0 (http://hdl.handle.net/11356/1110).;2017-05-09;lexicalConceptualResource;http://hdl.handle.net/11356/1112;slv;https://doi.org/10.1007/s10579-018-9413-3;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);https://creativecommons.org/licenses/by-sa/4.0/;PUB;text/plain; charset=utf-8;text/plain;text/plain;downloadable_files_count: 2;Faculty of Information Studies Novo mesto;https://github.com/19Joey85/Sentiment-annotated-news-corpus-and-sentiment-lexicon-in-Slovene/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9594a562-4751-5dad-94ef-8a3b0d2def85",
-    "notes": [
-        "The JOB lexicon for sentiment analysis of Slovenian texts contains a list of 25,524 headwords from the List of Slovenian headwords 1.1 (http://hdl.handle.net/11356/1038) extended with sentiment ratings based on the AFINN model with an integer between -5 (very negative) and +5 (very positive). The ratings are derived from the lemmatized version of the Manually sentiment annotated Slovenian (sentence-based) news corpus SentiNews 1.0 (http://hdl.handle.net/11356/1110)."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1112"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "sentiment lexicon"
-        },
-        {
-            "name": "opinion lexicon"
-        }
-    ],
-    "title": [
-        "Slovene sentiment lexicon JOB 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/95ba90dd-d867-555f-be29-268a92c89ad3.json b/oaitestdata/clarin-oai_dc/SET_1/json/95ba90dd-d867-555f-be29-268a92c89ad3.json
deleted file mode 100644
index e000f363..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/95ba90dd-d867-555f-be29-268a92c89ad3.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 3",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1195",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1195"
-    ],
-    "PID": "http://hdl.handle.net/11356/1195",
-    "PublicationTimestamp": "2018-08-03T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11356/1046"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "https://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Dobrovoljc, Kaja"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1195;2018-08-03T18:46:37Z;hdl_11356_1023;hdl_11356_1024;Gos corpus n-grams 2.0;Dobrovoljc, Kaja;n-grams;wordlist;multiword expressions;spoken corpus;A collection of n-grams extracted from the Gos corpus of spoken Slovene (cf. http://eng.slovenscina.eu/korpusi/gos). Three sets of n-gram lists are provided for lowercased word n-grams of length 1 to 5:\r\n- extensive frequency lists of all extracted n-grams\r\n- filtered frequency lists of n-grams with minimum frequency 10/mil.\r\n- adjusted frequency list of all n-grams with minimum frequency 10/mil.\r\n\r\nOnly n-grams within sentences have been counted, ignoring punctuation. For the filtered and adjusted list, only n-grams occurring in at least 2 different texts have been extracted.\r\n\r\nKey references:\r\n- K. Dobrovoljc, 2018. N-gram frequency lists for reference corpora of Slovenian language. Proceedings of the Language Technologies & Digital Humanities Conference 2018.\r\n- D. Verdonik, I. Kosem, A. Zwitter Vitez, S. Krek, M. Stabej, 2013. Compilation, transcription and usage of a reference speech corpus: The case of the Slovene corpus GOS. Language resources and evaluation, 47 (4), pp. 1031-1048, doi: 10.1007/s10579-013-9216-5.\r\n- M. B. O\u2019Donnell, 2010. The adjusted frequency list: A method to produce cluster-sensitive frequency lists. ICAME Journal 35, 135\u2013169.;2018-08-03;lexicalConceptualResource;http://hdl.handle.net/11356/1195;slv;http://hdl.handle.net/11356/1046;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);https://creativecommons.org/licenses/by-sa/4.0/;PUB;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 3;Centre for Language Resources and Technologies, University of Ljubljana",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "95ba90dd-d867-555f-be29-268a92c89ad3",
-    "notes": [
-        "A collection of n-grams extracted from the Gos corpus of spoken Slovene (cf. http://eng.slovenscina.eu/korpusi/gos). Three sets of n-gram lists are provided for lowercased word n-grams of length 1 to 5:\r\n- extensive frequency lists of all extracted n-grams\r\n- filtered frequency lists of n-grams with minimum frequency 10/mil.\r\n- adjusted frequency list of all n-grams with minimum frequency 10/mil.\r\n\r\nOnly n-grams within sentences have been counted, ignoring punctuation. For the filtered and adjusted list, only n-grams occurring in at least 2 different texts have been extracted.\r\n\r\nKey references:\r\n- K. Dobrovoljc, 2018. N-gram frequency lists for reference corpora of Slovenian language. Proceedings of the Language Technologies & Digital Humanities Conference 2018.\r\n- D. Verdonik, I. Kosem, A. Zwitter Vitez, S. Krek, M. Stabej, 2013. Compilation, transcription and usage of a reference speech corpus: The case of the Slovene corpus GOS. Language resources and evaluation, 47 (4), pp. 1031-1048, doi: 10.1007/s10579-013-9216-5.\r\n- M. B. O\u2019Donnell, 2010. The adjusted frequency list: A method to produce cluster-sensitive frequency lists. ICAME Journal 35, 135\u2013169."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1195"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "n-grams"
-        },
-        {
-            "name": "wordlist"
-        },
-        {
-            "name": "multiword expressions"
-        },
-        {
-            "name": "spoken corpus"
-        }
-    ],
-    "title": [
-        "Gos corpus n-grams 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/95cd8a05-02fe-5fdb-8d5f-17d59f72c918.json b/oaitestdata/clarin-oai_dc/SET_1/json/95cd8a05-02fe-5fdb-8d5f-17d59f72c918.json
deleted file mode 100644
index 17311f62..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/95cd8a05-02fe-5fdb-8d5f-17d59f72c918.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "University of Cambridge"
-    ],
-    "Contributor": [
-        "Willis, David"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/tei+xml",
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Welsh"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-883",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-883"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-883",
-    "PublicationTimestamp": "2004-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2004"
-    ],
-    "Publisher": [
-        "University of Cambridge"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-883;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Historical Corpus of the Welsh Language 1500-1850;Willis, David;Welsh texts from the period 1500-1850. Overall the corpus contains around 420,000 words from 30 texts.;2004;corpus;http://hdl.handle.net/11372/LRT-883;cym;application/tei+xml;downloadable_files_count: 0;United Kingdom;University of Cambridge;http://people.pwf.cam.ac.uk/dwew2/hcwl/menu.htm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "95cd8a05-02fe-5fdb-8d5f-17d59f72c918",
-    "notes": [
-        "Welsh texts from the period 1500-1850. Overall the corpus contains around 420,000 words from 30 texts."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-883"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Historical Corpus of the Welsh Language 1500-1850"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/95d931dc-dbee-55b5-a10c-12e3646b62f8.json b/oaitestdata/clarin-oai_dc/SET_1/json/95d931dc-dbee-55b5-a10c-12e3646b62f8.json
deleted file mode 100644
index 25ae70b1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/95d931dc-dbee-55b5-a10c-12e3646b62f8.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5525",
-    "MetadataAccess": [
-        "oai:ota:oucs:5525"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Aitken, John, d. 1790."
-    ],
-    "fulltext": "oai:ota:oucs:5525;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5525.xml;Medical improvement: an address read to the Medical Society, by John Aitken, ...;Aitken, John, d. 1790.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "95d931dc-dbee-55b5-a10c-12e3646b62f8",
-    "oai_identifier": [
-        "oai:ota:oucs:5525"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Medical improvement: an address read to the Medical Society, by John Aitken, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5525.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/95dc3acd-df6f-5cd9-807a-cb6157e7ba88.json b/oaitestdata/clarin-oai_dc/SET_1/json/95dc3acd-df6f-5cd9-807a-cb6157e7ba88.json
deleted file mode 100644
index ef989c15..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/95dc3acd-df6f-5cd9-807a-cb6157e7ba88.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-358",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-358"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-358",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Italy"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-358;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;ALTWEB;Dialect (Tuscan); 380.000 entries; written; DBT tagset;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-358;ita;downloadable_files_count: 0;Italy;http://serverdbt.ilc.cnr.it/altweb",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "95dc3acd-df6f-5cd9-807a-cb6157e7ba88",
-    "notes": [
-        "Dialect (Tuscan); 380.000 entries; written; DBT tagset"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-358"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "ALTWEB"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/95e5e1f2-9ee7-5fe7-90ca-25ae4aac70b3.json b/oaitestdata/clarin-oai_dc/SET_1/json/95e5e1f2-9ee7-5fe7-90ca-25ae4aac70b3.json
deleted file mode 100644
index 98850db0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/95e5e1f2-9ee7-5fe7-90ca-25ae4aac70b3.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Burnard, Lou"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 241 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0035",
-    "MetadataAccess": [
-        "oai:ota:oucs:0035"
-    ],
-    "PublicationTimestamp": "1785-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1785"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Cowper, William, 1731-1800"
-    ],
-    "fulltext": "oai:ota:oucs:0035;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0035.xml;The task / William Cowper;Cowper, William, 1731-1800;1785;text_and_corpus_linguistics;English poetry -- 18th century;eng;Oxford Text Archive, University of Oxford;Burnard, Lou;(1 file : ca. 241 KB);Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "95e5e1f2-9ee7-5fe7-90ca-25ae4aac70b3",
-    "oai_identifier": [
-        "oai:ota:oucs:0035"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English poetry -- th century"
-        }
-    ],
-    "title": [
-        "The task / William Cowper"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0035.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/960b8ffa-2334-58a2-8fae-d779ea3a03a2.json b/oaitestdata/clarin-oai_dc/SET_1/json/960b8ffa-2334-58a2-8fae-d779ea3a03a2.json
deleted file mode 100644
index b23c27f1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/960b8ffa-2334-58a2-8fae-d779ea3a03a2.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Catalan",
-        "English",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-420",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-420"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-420",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-420;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Corpus T\u00e8cnic de l'IULA;domain specific corpus (Law, Economy, Computing, Medicine and Environment as well as a contrastive corpus from the press); EN 3.3 M tokens, SP 33 M tokens, CAT 19 M tokens; EAGLEs pos tagset;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-420;cat;eng;spa;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra;http://bwananet.iula.upf.edu/indexes.htm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "960b8ffa-2334-58a2-8fae-d779ea3a03a2",
-    "notes": [
-        "domain specific corpus (Law, Economy, Computing, Medicine and Environment as well as a contrastive corpus from the press); EN 3.3 M tokens, SP 33 M tokens, CAT 19 M tokens; EAGLEs pos tagset"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-420"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus T\u00e8cnic de l'IULA"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/96101676-5343-5181-8035-089ed5655748.json b/oaitestdata/clarin-oai_dc/SET_1/json/96101676-5343-5181-8035-089ed5655748.json
deleted file mode 100644
index 7e9959cc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/96101676-5343-5181-8035-089ed5655748.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 15",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Croatian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1064",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1064"
-    ],
-    "PID": "http://hdl.handle.net/11356/1064",
-    "PublicationTimestamp": "2016-05-12T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by-sa/4.0/"
-    ],
-    "author": [
-        "Klubi\u010dka, Filip",
-        "Ljube\u0161i\u0107, Nikola"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1064;2018-10-24T20:54:37Z;hdl_11356_1023;hdl_11356_1024;Croatian web corpus hrWaC 2.1;Ljube\u0161i\u0107, Nikola;Klubi\u010dka, Filip;web corpus;tagging;lemmatisation;The Croatian web corpus hrWaC was built by crawling the .hr top-level domain in 2011 and again in 2014. The corpus was near-deduplicated on paragraph level, normalised via diacritic restoration, morphosyntactically annotated and lemmatised. The corpus is shuffled by paragraphs. Each paragraph contains metadata on the URL, domain and language identification (Croatian vs. Serbian).\r\n\r\nVersion 2.0 of this corpus is described in http://www.aclweb.org/anthology/W14-0405. Version 2.1 contains newer and better linguistic annotations.;2016-05-12;corpus;http://hdl.handle.net/11356/1064;hrv;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);PUB;https://creativecommons.org/licenses/by-sa/4.0/;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 15;Jo\u017eef Stefan Institute;http://nlp.ffzg.hr/resources/corpora/hrwac/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "96101676-5343-5181-8035-089ed5655748",
-    "notes": [
-        "The Croatian web corpus hrWaC was built by crawling the .hr top-level domain in 2011 and again in 2014. The corpus was near-deduplicated on paragraph level, normalised via diacritic restoration, morphosyntactically annotated and lemmatised. The corpus is shuffled by paragraphs. Each paragraph contains metadata on the URL, domain and language identification (Croatian vs. Serbian).\r\n\r\nVersion 2.0 of this corpus is described in http://www.aclweb.org/anthology/W14-0405. Version 2.1 contains newer and better linguistic annotations."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1064"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "web corpus"
-        },
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "lemmatisation"
-        }
-    ],
-    "title": [
-        "Croatian web corpus hrWaC 2.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/961bd17b-bb53-5666-b15b-4e183c18f48a.json b/oaitestdata/clarin-oai_dc/SET_1/json/961bd17b-bb53-5666-b15b-4e183c18f48a.json
deleted file mode 100644
index c689fdcc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/961bd17b-bb53-5666-b15b-4e183c18f48a.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contributor": [
-        "Frankenberg-Garcia, Ana",
-        "Santos, Diana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English",
-        "Portuguese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-866",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-866"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-866",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Portugal"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-866;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;COMPARA : Portuguese - English parallel translation corpus;Frankenberg-Garcia, Ana;Santos, Diana;bi-directional parallel corpus based on an open-ended collection of Portuguese-English and English-Portuguese source-texts and translations. Searchable via the IMS Corpus Query Processor and the DISPARA interface;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-866;eng;por;downloadable_files_count: 0;Portugal;http://www.linguateca.pt/COMPARA/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "961bd17b-bb53-5666-b15b-4e183c18f48a",
-    "notes": [
-        "bi-directional parallel corpus based on an open-ended collection of Portuguese-English and English-Portuguese source-texts and translations. Searchable via the IMS Corpus Query Processor and the DISPARA interface"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-866"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "COMPARA : Portuguese - English parallel translation corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/961c1914-9529-562d-96cf-a3a753c5b566.json b/oaitestdata/clarin-oai_dc/SET_1/json/961c1914-9529-562d-96cf-a3a753c5b566.json
deleted file mode 100644
index b4d09b86..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/961c1914-9529-562d-96cf-a3a753c5b566.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=1c8e4d40358b11e2a2aa782bcb07413512c66c74805a4e8088649b7d128fc2e4",
-    "MetadataAccess": [
-        "1c8e4d40358b11e2a2aa782bcb07413512c66c74805a4e8088649b7d128fc2e4"
-    ],
-    "PublicationTimestamp": "2012-11-23T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "fulltext": "1c8e4d40358b11e2a2aa782bcb07413512c66c74805a4e8088649b7d128fc2e4;2018-11-15T16:39:54Z;toolService;toolService:service;LX-Service;LXService is a Web Service that consists in a range of tools for Portuguese that have been develop for the processing of Portuguese. They were selected because they satisfy a number of features that are likely to make them more suitable for initial experimentation: They are fast, robust, the linguistic information in their output is well understood, and they perform at state of the art accuracy. They include the following individual tools, covering analysis and generation procedures:\n\nConstituency Parser (see Silva et al., 2010): performs a syntactic analysis of Portuguese sentences in terms of their constituency structure. 88% f-score.\n\nDependency Parser (see Silva et al., 2010): allows the automatic parsing of sentences in Portuguese in terms of their grammatical functions. 86.8% accuracy.\n\nNamed Entity Recognizer (number-based or name-based) (see Ferreira et al., 2007): recognizes the expressions for named entities in Portuguese.\n\nPOS tagger (see Silva, 2007): assigns POS tags to tokens in context; 96.87% accuracy. \n\nSentence chunker (see Silva, 2007): detects and marks paragraph and sentence boundaries; 99.94% accuracy.\n\nTokenizer (see Silva, 2007): segments text into tokens, expands contractions, detaches clitic pronouns from verbs, etc.; 99.72% accuracy.\n\nSemantic Role Labeler: generates syntactic trees with semantic labels; f-score of 82%.\n\nThe development of these web services started in the scope of the LT4eL-Language Technology for e-Learning project (available at www.lt4el.eu). They are supported by a range of language technology tools that have been developed in the past at the University of Lisbon in the scope of a number of previous projects.\n;2012-11-23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "961c1914-9529-562d-96cf-a3a753c5b566",
-    "notes": [
-        "LXService is a Web Service that consists in a range of tools for Portuguese that have been develop for the processing of Portuguese. They were selected because they satisfy a number of features that are likely to make them more suitable for initial experimentation: They are fast, robust, the linguistic information in their output is well understood, and they perform at state of the art accuracy. They include the following individual tools, covering analysis and generation procedures:\n\nConstituency Parser (see Silva et al., 2010): performs a syntactic analysis of Portuguese sentences in terms of their constituency structure. 88% f-score.\n\nDependency Parser (see Silva et al., 2010): allows the automatic parsing of sentences in Portuguese in terms of their grammatical functions. 86.8% accuracy.\n\nNamed Entity Recognizer (number-based or name-based) (see Ferreira et al., 2007): recognizes the expressions for named entities in Portuguese.\n\nPOS tagger (see Silva, 2007): assigns POS tags to tokens in context; 96.87% accuracy. \n\nSentence chunker (see Silva, 2007): detects and marks paragraph and sentence boundaries; 99.94% accuracy.\n\nTokenizer (see Silva, 2007): segments text into tokens, expands contractions, detaches clitic pronouns from verbs, etc.; 99.72% accuracy.\n\nSemantic Role Labeler: generates syntactic trees with semantic labels; f-score of 82%.\n\nThe development of these web services started in the scope of the LT4eL-Language Technology for e-Learning project (available at www.lt4el.eu). They are supported by a range of language technology tools that have been developed in the past at the University of Lisbon in the scope of a number of previous projects.\n"
-    ],
-    "oai_identifier": [
-        "1c8e4d40358b11e2a2aa782bcb07413512c66c74805a4e8088649b7d128fc2e4"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:service"
-    ],
-    "state": "active",
-    "title": [
-        "LX-Service"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9626d301-2764-56e0-882a-1e1942a1a7ea.json b/oaitestdata/clarin-oai_dc/SET_1/json/9626d301-2764-56e0-882a-1e1942a1a7ea.json
deleted file mode 100644
index a1494857..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9626d301-2764-56e0-882a-1e1942a1a7ea.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/36",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/36"
-    ],
-    "PID": "http://hdl.handle.net/10794/36",
-    "PublicationTimestamp": "2012-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/36;2017-10-27T14:17:41Z;hdl_10794_1;hdl_10794_2;SALDO's morphology (2017-10-16);SALDOs morfologi (2017-10-16);n/a, n/a;Swedish;Morphology;Semantic and morphological lexicon for language technology.;Semantiskt och morfologiskt lexikon f\u00f6r spr\u00e5kteknologi.;2012-05-30;lexicalConceptualResource;http://hdl.handle.net/10794/36;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/saldom",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9626d301-2764-56e0-882a-1e1942a1a7ea",
-    "notes": [
-        "Semantic and morphological lexicon for language technology.",
-        "Semantiskt och morfologiskt lexikon f\u00f6r spr\u00e5kteknologi."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/36"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Morphology"
-        }
-    ],
-    "title": [
-        "SALDO's morphology (2017-10-16)",
-        "SALDOs morfologi (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/962f2114-ce7c-56e1-8c09-ae88b9226392.json b/oaitestdata/clarin-oai_dc/SET_1/json/962f2114-ce7c-56e1-8c09-ae88b9226392.json
deleted file mode 100644
index 2668776e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/962f2114-ce7c-56e1-8c09-ae88b9226392.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1397",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1397"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1397",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1397;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;catdoc;Format conversion service: Word .doc to .txt converter;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1397;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "962f2114-ce7c-56e1-8c09-ae88b9226392",
-    "notes": [
-        "Format conversion service: Word .doc to .txt converter"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1397"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "catdoc"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/964aaebc-db49-5f54-9c4e-ac525531b745.json b/oaitestdata/clarin-oai_dc/SET_1/json/964aaebc-db49-5f54-9c4e-ac525531b745.json
deleted file mode 100644
index 4d6e201c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/964aaebc-db49-5f54-9c4e-ac525531b745.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "text/xml",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Northern Sami",
-        "Norwegian Bokm\u00e5l"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/98",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/98"
-    ],
-    "PID": "http://hdl.handle.net/11509/98",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "The Divvun group at UiT The Arctic University of Norway",
-        "Giellatekno - Saami Language Technology, UiT The Arctic University of Norway"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/98;2016-09-06T12:51:25Z;hdl_11509_1;hdl_11509_2;North Saami-Norwegian Bokm\u00e5l dictionary;Giellatekno - Saami Language Technology, UiT The Arctic University of Norway;The Divvun group at UiT The Arctic University of Norway;Bilingual Lexicon;North Saami;Norwegian;Machine-readable Dictionary;The North Saami-Norwegian Bokm\u00e5l dictionary is the work done by Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language communities. In particular, the following colleagues have contributed to the creation of the ressource: Nils Jernsletten, Lene Antonsen, Trond Trosterud, Ritva Nystad, Ciprian Gerstenberger, Berit Merete Nystad Eskonsipo, Marja Eira, Siri Broch Johansen, Sjur Moshagen, and Tomi Pieski. The dictionary contains 33440 entries in Giellatekno's dictionary xml format. In spite of the extensive quality control, it may contain entries with objectionable translations. If you find any errors or want to add more words, download the file, edit it, and send it back to giellatekno@uit.no and feedback@divvun.no.\r\nPlease note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata).;2015;lexicalConceptualResource;http://hdl.handle.net/11509/98;sme;nob;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;application/zip;text/plain; charset=utf-8;text/xml;downloadable_files_count: 1;Giellatekno - Saami Language Technology;http://giellatekno.uit.no/index.eng.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "964aaebc-db49-5f54-9c4e-ac525531b745",
-    "notes": [
-        "The North Saami-Norwegian Bokm\u00e5l dictionary is the work done by Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language communities. In particular, the following colleagues have contributed to the creation of the ressource: Nils Jernsletten, Lene Antonsen, Trond Trosterud, Ritva Nystad, Ciprian Gerstenberger, Berit Merete Nystad Eskonsipo, Marja Eira, Siri Broch Johansen, Sjur Moshagen, and Tomi Pieski. The dictionary contains 33440 entries in Giellatekno's dictionary xml format. In spite of the extensive quality control, it may contain entries with objectionable translations. If you find any errors or want to add more words, download the file, edit it, and send it back to giellatekno@uit.no and feedback@divvun.no.\r\nPlease note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata)."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/98"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Bilingual Lexicon"
-        },
-        {
-            "name": "North Saami"
-        },
-        {
-            "name": "Norwegian"
-        },
-        {
-            "name": "Machine-readable Dictionary"
-        }
-    ],
-    "title": [
-        "North Saami-Norwegian Bokm\u00e5l dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9659e6e5-0de7-56e5-b77c-d3051e855eb7.json b/oaitestdata/clarin-oai_dc/SET_1/json/9659e6e5-0de7-56e5-b77c-d3051e855eb7.json
deleted file mode 100644
index e53340d2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9659e6e5-0de7-56e5-b77c-d3051e855eb7.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "McKinnon, Alastair"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 243 KB)"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0564",
-    "MetadataAccess": [
-        "oai:ota:oucs:0564"
-    ],
-    "PublicationTimestamp": "1950-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1950"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Academic dissertations"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Wittgenstein, Ludwig, 1889-1951"
-    ],
-    "fulltext": "oai:ota:oucs:0564;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0564.xml;Letze Schriften \u00c3\u00bcber die Philosophie de Psychologie / Ludwig Wittgenstein;Last writings on the philosophy of psychology;Wittgenstein, Ludwig, 1889-1951;1950-1951;text_and_corpus_linguistics;Psychology -- Philosophy -- 20th century;deu;Oxford Text Archive, University of Oxford;McKinnon, Alastair;(1 file : ca. 243 KB);Text;Academic dissertations;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9659e6e5-0de7-56e5-b77c-d3051e855eb7",
-    "oai_identifier": [
-        "oai:ota:oucs:0564"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Psychology -- Philosophy -- th century"
-        }
-    ],
-    "title": [
-        "Letze Schriften \u00c3\u00bcber die Philosophie de Psychologie / Ludwig Wittgenstein",
-        "Last writings on the philosophy of psychology"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0564.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/966deac1-e4c6-5075-92cd-80b716cdd529.json b/oaitestdata/clarin-oai_dc/SET_1/json/966deac1-e4c6-5075-92cd-80b716cdd529.json
deleted file mode 100644
index 73eefebf..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/966deac1-e4c6-5075-92cd-80b716cdd529.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3607",
-    "MetadataAccess": [
-        "oai:ota:oucs:3607"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "MacNally, Leonard, 1752-1820."
-    ],
-    "fulltext": "oai:ota:oucs:3607;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3607.xml;Retaliation, a farce, in two acts: as it is performed, with universal applause, at the Theatre Royal, Covent Garden. By Leonard MacNally, Esq.;MacNally, Leonard, 1752-1820.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "966deac1-e4c6-5075-92cd-80b716cdd529",
-    "oai_identifier": [
-        "oai:ota:oucs:3607"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Retaliation, a farce, in two acts: as it is performed, with universal applause, at the Theatre Royal, Covent Garden. By Leonard MacNally, Esq."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3607.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9675921e-ab15-554b-a598-627b982425fe.json b/oaitestdata/clarin-oai_dc/SET_1/json/9675921e-ab15-554b-a598-627b982425fe.json
deleted file mode 100644
index 770c9f43..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9675921e-ab15-554b-a598-627b982425fe.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Filosoft"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Estonian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-275",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-275"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-275",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Filosoft"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Estonia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-275;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Morphological analyzer for Estonian;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-275;est;downloadable_files_count: 0;Estonia;Filosoft;http://www.filosoft.ee/html_morf_et/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9675921e-ab15-554b-a598-627b982425fe",
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-275"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Morphological analyzer for Estonian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/968b2501-f456-51bc-ba33-893c864e5fa8.json b/oaitestdata/clarin-oai_dc/SET_1/json/968b2501-f456-51bc-ba33-893c864e5fa8.json
deleted file mode 100644
index 94461591..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/968b2501-f456-51bc-ba33-893c864e5fa8.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Przemys\u0142aw \u017bukiewicz",
-        "Rafa\u0142 Zimny",
-        "Jan Wieczorek"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 44",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/599",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/599"
-    ],
-    "PID": "http://hdl.handle.net/11321/599",
-    "PublicationTimestamp": "2018-09-11T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Przemys\u0142aw \u017bukiewicz",
-        "Rafa\u0142 Zimny",
-        "Jan Wieczorek"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11321/602"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN-EULA-ACA-v1.0",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca",
-        "ACA"
-    ],
-    "author": [
-        "Wieczorek, Jan",
-        "Zimny, Rafa\u0142",
-        "\u017bukiewicz, Przemys\u0142aw"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/599;2018-09-18T11:15:05Z;hdl_11321_3;hdl_11321_478;Korpus przem\u00f3wie\u0144 noworocznych;Zimny, Rafa\u0142;\u017bukiewicz, Przemys\u0142aw;Wieczorek, Jan;przem\u00f3wienia;polityka;Fragment korpusu polskich przem\u00f3wie\u0144 politycznych;2018-09-11;corpus;http://hdl.handle.net/11321/599;pol;http://hdl.handle.net/11321/602;CLARIN-EULA-ACA-v1.0;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca;ACA;text/plain; charset=utf-8;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;downloadable_files_count: 44;Jan Wieczorek;Rafa\u0142 Zimny;Przemys\u0142aw \u017bukiewicz",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "968b2501-f456-51bc-ba33-893c864e5fa8",
-    "notes": [
-        "Fragment korpusu polskich przem\u00f3wie\u0144 politycznych"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/599"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_478"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "polityka"
-        }
-    ],
-    "title": [
-        "Korpus przem\u00f3wie\u0144 noworocznych"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/96b5ba6a-2d3f-52fe-b3e6-2abad10b6ba1.json b/oaitestdata/clarin-oai_dc/SET_1/json/96b5ba6a-2d3f-52fe-b3e6-2abad10b6ba1.json
deleted file mode 100644
index e159f9b5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/96b5ba6a-2d3f-52fe-b3e6-2abad10b6ba1.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Department of Literature, Area Studies and European Languages, University of Oslo",
-        "Department of Linguistics and Nordic Studies, University of Oslo"
-    ],
-    "Contributor": [
-        "Gr\u00f8nn, Atle",
-        "N\u00f8klestad, Anders"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English",
-        "Norwegian",
-        "Russian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1062",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1062"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1062",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Department of Literature, Area Studies and European Languages, University of Oslo",
-        "Department of Linguistics and Nordic Studies, University of Oslo"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Norway"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1062;2016-04-06T16:39:49Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Run (Russian meets Norwegian );Gr\u00f8nn, Atle;N\u00f8klestad, Anders;The RuN corpus is a parallel corpus consisting of Norwegian, Russian and English texts. The texts are aligned at the sentence level and have been tagged for grammatical information at the word level.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1062;eng;nor;rus;downloadable_files_count: 0;Norway;Department of Literature, Area Studies and European Languages, University of Oslo;Department of Linguistics and Nordic Studies, University of Oslo;http://www.hf.uio.no/ilos/english/research/projects/run/index.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "96b5ba6a-2d3f-52fe-b3e6-2abad10b6ba1",
-    "notes": [
-        "The RuN corpus is a parallel corpus consisting of Norwegian, Russian and English texts. The texts are aligned at the sentence level and have been tagged for grammatical information at the word level."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1062"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Run (Russian meets Norwegian )"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/96c7602c-6623-50fa-a641-2082d163f9e4.json b/oaitestdata/clarin-oai_dc/SET_1/json/96c7602c-6623-50fa-a641-2082d163f9e4.json
deleted file mode 100644
index f378360c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/96c7602c-6623-50fa-a641-2082d163f9e4.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3721",
-    "MetadataAccess": [
-        "oai:ota:oucs:3721"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Paine, Thomas, 1737-1809."
-    ],
-    "fulltext": "oai:ota:oucs:3721;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3721.xml;Rights of man. Part the second. Combining principle and practice. By Thomas Paine,;Paine, Thomas, 1737-1809.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "96c7602c-6623-50fa-a641-2082d163f9e4",
-    "oai_identifier": [
-        "oai:ota:oucs:3721"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Rights of man. Part the second. Combining principle and practice. By Thomas Paine,"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3721.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/96d099eb-dfdc-5340-947d-41f66efdecd9.json b/oaitestdata/clarin-oai_dc/SET_1/json/96d099eb-dfdc-5340-947d-41f66efdecd9.json
deleted file mode 100644
index 73d2d70b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/96d099eb-dfdc-5340-947d-41f66efdecd9.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Akademicka"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-189308",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-189308"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CF6-C",
-    "PublicationTimestamp": "1746-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1746"
-    ],
-    "Publisher": [
-        "Drukarnia Akademicka"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/189308",
-        "oai:jbc.bj.uj.edu.pl:publication:200432"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1701/1800"
-    ],
-    "TempCoverageBegin": 53662478399,
-    "TempCoverageEnd": 53662478399,
-    "TemporalCoverage": " point in time : 1701-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1701-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1701-07-01T11:59:59Z",
-    "author": [
-        "Wr\u00f3blewski, Roman ( -1769)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-189308;2019-03-01T11:09:55Z;Chrystus Bolei\u0105cy od grzesznikow w Morzu Krwi Jego w\u0142asney Pogr\u0105zony : Na Herbowney Lod\u017ai [...] Miko\u0142aia Stefana z Chrz\u0105stowa Chrz\u0105stowskiego [...] Opata Koronowskiego Prze\u015bwietnego Zakonu Cystercye\u0144skiego J. K. M. Sekretarza &c. do po\u017c\u0105danego portu Wyniesiony W Postnych X. Romana Wroblewskiego Prowincyi Wielko- Polskiey Obserwanta, Kazaniach [...] Roku [...] 1746;Wr\u00f3blewski, Roman ( -1769);starodruki 18\u00a0w.;Chrz\u0105stowski, Miko\u0142aj Stefan (17..-17..). Adr. ded.;Drukarnia Akademicka;[1746];starodruk;application/xml;clarind-uds:poldilemma-189308;hdl:11858/00-246C-0000-0023-8CF6-C;Biblioteka Jagiello\u0144ska, BJ St. Dr. 38176 I;pol;lat;http://jbc.bj.uj.edu.pl/Content/189308;oai:jbc.bj.uj.edu.pl:publication:200432;1701/1800;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "96d099eb-dfdc-5340-947d-41f66efdecd9",
-    "notes": [
-        "Chrz\u0105stowski, Miko\u0142aj Stefan (17..-17..). Adr. ded."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-189308"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Chrystus Bolei\u0105cy od grzesznikow w Morzu Krwi Jego w\u0142asney Pogr\u0105zony : Na Herbowney Lod\u017ai [...] Miko\u0142aia Stefana z Chrz\u0105stowa Chrz\u0105stowskiego [...] Opata Koronowskiego Prze\u015bwietnego Zakonu Cystercye\u0144skiego J. K. M. Sekretarza &c. do po\u017c\u0105danego portu Wyniesiony W Postnych X. Romana Wroblewskiego Prowincyi Wielko- Polskiey Obserwanta, Kazaniach [...] Roku [...] 1746"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/96e90987-89e1-5957-a1f5-a733e351eeb0.json b/oaitestdata/clarin-oai_dc/SET_1/json/96e90987-89e1-5957-a1f5-a733e351eeb0.json
deleted file mode 100644
index cc24c906..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/96e90987-89e1-5957-a1f5-a733e351eeb0.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "University of Wroc\u0142aw, CLARIN-PL"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/260",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/260"
-    ],
-    "PID": "http://hdl.handle.net/11321/260",
-    "PublicationTimestamp": "2016-05-09T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "University of Wroc\u0142aw, CLARIN-PL"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Paw\u0142owski, Adam Tomasz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/260;2018-03-19T11:23:46Z;hdl_11321_3;hdl_11321_4;ChronoPress -- Chronologica Corpus;Paw\u0142owski, Adam Tomasz;chronological corpus;Polish press;media;time series;quantitative text analysis;totalitarian period;ChronoPress is a unique resource containing samples of Polish press texts from the period 1945-1954. The corpus was designed as a representative set of samples for Polish public discourse.;2016-05-09;corpus;http://hdl.handle.net/11321/260;pol;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;CC;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;University of Wroc\u0142aw, CLARIN-PL;http://chronopress.clarin-pl.eu/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "96e90987-89e1-5957-a1f5-a733e351eeb0",
-    "notes": [
-        "ChronoPress is a unique resource containing samples of Polish press texts from the period 1945-1954. The corpus was designed as a representative set of samples for Polish public discourse."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/260"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "chronological corpus"
-        },
-        {
-            "name": "Polish press"
-        },
-        {
-            "name": "media"
-        },
-        {
-            "name": "time series"
-        },
-        {
-            "name": "quantitative text analysis"
-        },
-        {
-            "name": "totalitarian period"
-        }
-    ],
-    "title": [
-        "ChronoPress -- Chronologica Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/96ea5a05-6553-5ce0-bb70-0b7e6b91e97f.json b/oaitestdata/clarin-oai_dc/SET_1/json/96ea5a05-6553-5ce0-bb70-0b7e6b91e97f.json
deleted file mode 100644
index 6570958e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/96ea5a05-6553-5ce0-bb70-0b7e6b91e97f.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-56",
-    "MetadataAccess": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-56"
-    ],
-    "PID": "http://hdl.handle.net/20.500.11752/ILC-56",
-    "PublicationTimestamp": "2016-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Diakoff, Harry",
-        "Del Gratta, Riccardo",
-        "Boschetti, Federico"
-    ],
-    "fulltext": "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-56;2018-07-23T09:13:44Z;hdl_000-c0-111_38;hdl_000-c0-111_49;Open Ancient Greek WordNet 0.5;Boschetti, Federico;Del Gratta, Riccardo;Diakoff, Harry;WordNet;Ancient Greek;Ancient Greek WordNet is a lexico-semantic resource mapped on Princeton WordNet 3.0.\r\nThe synsets provided by the current version 0.5 are filtered through Minozzi's Latin WordNet synset IDs.\r\n\r\nOpen Ancient Greek WordNet  0.5 contains \r\n7447 synsets (all of them are mapped on Minozzi\u2019s Latin WordNet);\r\n22420 lemmas (coverage based on LSJ\u2019s 120k lemmas: ~18%);\r\n76620 senses (unsupervised; estimated precision: ~56%).\r\n\r\nDISCLAIMER\r\nThis resource has been bootstrapped from Greek-English dictionaries available online (Liddell-Scott-Jones, Middle Liddell, Autenrieth) and filtered by Stefano Minozzi\u2019s Latin WordNet synset IDs (http://multiwordnet.fbk.eu).\r\nThe current version 0.5 has not yet been manually corrected; the estimated precision is low.;2016-05-30;lexicalConceptualResource;http://hdl.handle.net/20.500.11752/ILC-56;grc;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;PUB;application/octet-stream;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 2;Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "96ea5a05-6553-5ce0-bb70-0b7e6b91e97f",
-    "notes": [
-        "Ancient Greek WordNet is a lexico-semantic resource mapped on Princeton WordNet 3.0.\r\nThe synsets provided by the current version 0.5 are filtered through Minozzi's Latin WordNet synset IDs.\r\n\r\nOpen Ancient Greek WordNet  0.5 contains \r\n7447 synsets (all of them are mapped on Minozzi\u2019s Latin WordNet);\r\n22420 lemmas (coverage based on LSJ\u2019s 120k lemmas: ~18%);\r\n76620 senses (unsupervised; estimated precision: ~56%).\r\n\r\nDISCLAIMER\r\nThis resource has been bootstrapped from Greek-English dictionaries available online (Liddell-Scott-Jones, Middle Liddell, Autenrieth) and filtered by Stefano Minozzi\u2019s Latin WordNet synset IDs (http://multiwordnet.fbk.eu).\r\nThe current version 0.5 has not yet been manually corrected; the estimated precision is low."
-    ],
-    "oai_identifier": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-56"
-    ],
-    "oai_set": [
-        "hdl_000-c0-111_38",
-        "hdl_000-c0-111_49"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "WordNet"
-        },
-        {
-            "name": "Ancient Greek"
-        }
-    ],
-    "title": [
-        "Open Ancient Greek WordNet 0.5"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/96f56d7f-8ae4-5cda-9f66-8aa74da41a80.json b/oaitestdata/clarin-oai_dc/SET_1/json/96f56d7f-8ae4-5cda-9f66-8aa74da41a80.json
deleted file mode 100644
index 1a5c02c8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/96f56d7f-8ae4-5cda-9f66-8aa74da41a80.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=8ad87f6c28f411e2a2aa782bcb074135e4e77c3345c4429eb4a5a9d6d435c39b",
-    "MetadataAccess": [
-        "8ad87f6c28f411e2a2aa782bcb074135e4e77c3345c4429eb4a5a9d6d435c39b"
-    ],
-    "PublicationTimestamp": "2012-11-07T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "fulltext": "8ad87f6c28f411e2a2aa782bcb074135e4e77c3345c4429eb4a5a9d6d435c39b;2019-02-27T12:09:12Z;toolService;toolService:tool;Uplug;Uplug (see Tiedemann, 2003a) is a collection of tools and scripts for processing text-corpora, for automatic alignment and for term extraction from parallel corpora. \nSeveral tools have been integrated in Uplug. Pre-processing tools include a sentence splitter, a general tokenizer and wrappers around external part-of-speech tagger and shallow parsers. The following external tools are included in the standard package: The Grok system for English (tagging and chunking), and the morphological analyzer ChaSen for Japanese. Translated documents can be sentence aligned using the length-based approach by Gale&Church, hunalign or GMA by Melamed and others. Words and phrases can be aligned using the clue alignment approach (see Tiedemann, 2003b) and GIZA++ (a toolbox for training statistical alignment models for SMT). Other tools can easily be integrated, for example, the TreeTagger for English, French, Italian, and German, the TnT tagger for English, German and Swedish. \nUplug has been developed within the PLUG project (see Tiedemann, 2002). It also includes web-based interfaces for interactive sentence and word alignment (see Tiedemann, 2006). \n\n;2012-11-07",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "96f56d7f-8ae4-5cda-9f66-8aa74da41a80",
-    "notes": [
-        "Uplug (see Tiedemann, 2003a) is a collection of tools and scripts for processing text-corpora, for automatic alignment and for term extraction from parallel corpora. \nSeveral tools have been integrated in Uplug. Pre-processing tools include a sentence splitter, a general tokenizer and wrappers around external part-of-speech tagger and shallow parsers. The following external tools are included in the standard package: The Grok system for English (tagging and chunking), and the morphological analyzer ChaSen for Japanese. Translated documents can be sentence aligned using the length-based approach by Gale&Church, hunalign or GMA by Melamed and others. Words and phrases can be aligned using the clue alignment approach (see Tiedemann, 2003b) and GIZA++ (a toolbox for training statistical alignment models for SMT). Other tools can easily be integrated, for example, the TreeTagger for English, French, Italian, and German, the TnT tagger for English, German and Swedish. \nUplug has been developed within the PLUG project (see Tiedemann, 2002). It also includes web-based interfaces for interactive sentence and word alignment (see Tiedemann, 2006). \n\n"
-    ],
-    "oai_identifier": [
-        "8ad87f6c28f411e2a2aa782bcb074135e4e77c3345c4429eb4a5a9d6d435c39b"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "Uplug"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9706d05e-54d9-5c50-bae4-4aa87656c055.json b/oaitestdata/clarin-oai_dc/SET_1/json/9706d05e-54d9-5c50-bae4-4aa87656c055.json
deleted file mode 100644
index 298fdad3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9706d05e-54d9-5c50-bae4-4aa87656c055.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "Contributor": [
-        "Withers, Peter"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1213",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1213"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1213",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1213;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;KinOath Kinship Archiver;Withers, Peter;KinOath Kinship Archiver is a kinship application with the primary goal of connecting kinship data with archived data, such as audio, video or written resources while also being closely integrated with the archive software such as Arbil. Beyond this primary goal it is designed to be flexible and culturally nonspecific, such that culturally different social structures can equally be represented. Kin type strings are used throughout the application for constructing and searching data sets. The representation of kin terms is also integrated into the application allowing comparative diagrams of kin terms. Graphical representation of the data is an important part of the application and the diagrams produced are intended to very flexible and of publishable quality.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1213;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://tla.mpi.nl/tools/tla-tools/kinoath/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9706d05e-54d9-5c50-bae4-4aa87656c055",
-    "notes": [
-        "KinOath Kinship Archiver is a kinship application with the primary goal of connecting kinship data with archived data, such as audio, video or written resources while also being closely integrated with the archive software such as Arbil. Beyond this primary goal it is designed to be flexible and culturally nonspecific, such that culturally different social structures can equally be represented. Kin type strings are used throughout the application for constructing and searching data sets. The representation of kin terms is also integrated into the application allowing comparative diagrams of kin terms. Graphical representation of the data is an important part of the application and the diagrams produced are intended to very flexible and of publishable quality."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1213"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "KinOath Kinship Archiver"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/97112e50-bce9-551a-b305-52f4092f8af5.json b/oaitestdata/clarin-oai_dc/SET_1/json/97112e50-bce9-551a-b305-52f4092f8af5.json
deleted file mode 100644
index 8f900a2e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/97112e50-bce9-551a-b305-52f4092f8af5.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Woolley, James D."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(2 files : ca. 214, 2 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1386",
-    "MetadataAccess": [
-        "oai:ota:oucs:1386"
-    ],
-    "PublicationYear": [
-        "[198?]"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Periodicals"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745",
-        "Sheridan, Thomas, 1687-1738"
-    ],
-    "fulltext": "oai:ota:oucs:1386;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1386.xml;The Intelligencer / Jonathan Swift and Thomas Sheridan;Swift, Jonathan, 1667-1745;Sheridan, Thomas, 1687-1738;[198?];text_and_corpus_linguistics;Irish periodicals -- 18th century;eng;lat;Oxford Text Archive, University of Oxford;Woolley, James D.;text/plain;(2 files : ca. 214, 2 KB);Text;Periodicals;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "97112e50-bce9-551a-b305-52f4092f8af5",
-    "oai_identifier": [
-        "oai:ota:oucs:1386"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Irish periodicals -- th century"
-        }
-    ],
-    "title": [
-        "The Intelligencer / Jonathan Swift and Thomas Sheridan"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1386.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/97360cd1-f354-579e-9e23-1ff249dfd467.json b/oaitestdata/clarin-oai_dc/SET_1/json/97360cd1-f354-579e-9e23-1ff249dfd467.json
deleted file mode 100644
index e3a8931d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/97360cd1-f354-579e-9e23-1ff249dfd467.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Glasscoe, Marion"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain",
-        "(1 file : ca. 281 KB)"
-    ],
-    "Language": [
-        "Middle English (1100-1500)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0700",
-    "MetadataAccess": [
-        "oai:ota:oucs:0700"
-    ],
-    "PublicationTimestamp": "1395-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1395"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Devotional literature"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Julian, of Norwich, b. 1343"
-    ],
-    "fulltext": "oai:ota:oucs:0700;2018-02-28T12:41:01Z;http://ota.ox.ac.uk/headers/0700.xml;A revelation of divine love / Julian of Norwich;Revelations to one who could not read a letter, Anno Domini 1373;Julian, of Norwich, b. 1343;1395;text_and_corpus_linguistics;Devotional literature, English (Middle);enm;Oxford Text Archive, University of Oxford;Glasscoe, Marion;text/plain;(1 file : ca. 281 KB);Text;Devotional literature;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "97360cd1-f354-579e-9e23-1ff249dfd467",
-    "oai_identifier": [
-        "oai:ota:oucs:0700"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Devotional literature"
-        },
-        {
-            "name": "English Middle"
-        }
-    ],
-    "title": [
-        "A revelation of divine love / Julian of Norwich",
-        "Revelations to one who could not read a letter, Anno Domini 1373"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0700.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/97648753-b785-5ced-9826-799d6566124b.json b/oaitestdata/clarin-oai_dc/SET_1/json/97648753-b785-5ced-9826-799d6566124b.json
deleted file mode 100644
index 314b06a2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/97648753-b785-5ced-9826-799d6566124b.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "British Academy and the University of Wales, Bangor"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3022",
-    "MetadataAccess": [
-        "oai:ota:oucs:3022"
-    ],
-    "PublicationTimestamp": "1667-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1667"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Milton, John, 1608-1674"
-    ],
-    "fulltext": "oai:ota:oucs:3022;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3022.xml;Paradise Lost. A Poem in ten books. [1667];Milton, John, 1608-1674;not after: 1667;text_and_corpus_linguistics;English poetry -- 17th century;eng;Oxford Text Archive, University of Oxford;British Academy and the University of Wales, Bangor;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "97648753-b785-5ced-9826-799d6566124b",
-    "oai_identifier": [
-        "oai:ota:oucs:3022"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English poetry -- th century"
-        }
-    ],
-    "title": [
-        "Paradise Lost. A Poem in ten books. [1667]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3022.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/977136af-4234-5af1-888d-ac432ac12f24.json b/oaitestdata/clarin-oai_dc/SET_1/json/977136af-4234-5af1-888d-ac432ac12f24.json
deleted file mode 100644
index e7c7c8e7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/977136af-4234-5af1-888d-ac432ac12f24.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3953",
-    "MetadataAccess": [
-        "oai:ota:oucs:3953"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Jephson, Robert, 1736-1803."
-    ],
-    "fulltext": "oai:ota:oucs:3953;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3953.xml;The Count of Narbonne: a tragedy. As it is acted at the Theatre Royal in Covent Garden. By Robert Jephson, Esq;.;Jephson, Robert, 1736-1803.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "977136af-4234-5af1-888d-ac432ac12f24",
-    "oai_identifier": [
-        "oai:ota:oucs:3953"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The Count of Narbonne: a tragedy. As it is acted at the Theatre Royal in Covent Garden. By Robert Jephson, Esq;."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3953.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/97a20985-8841-5c9f-8a7a-09c7313c79ac.json b/oaitestdata/clarin-oai_dc/SET_1/json/97a20985-8841-5c9f-8a7a-09c7313c79ac.json
deleted file mode 100644
index c99e0784..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/97a20985-8841-5c9f-8a7a-09c7313c79ac.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-989",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-989"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-989",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-989;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LAC Mawe Corpus;Language and Cognition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-989;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI33469%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "97a20985-8841-5c9f-8a7a-09c7313c79ac",
-    "notes": [
-        "Language and Cognition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-989"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LAC Mawe Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/97deb326-60ee-5043-9629-952750fc8032.json b/oaitestdata/clarin-oai_dc/SET_1/json/97deb326-60ee-5043-9629-952750fc8032.json
deleted file mode 100644
index 9bcb66a7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/97deb326-60ee-5043-9629-952750fc8032.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Bolz, Norbert W."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 220 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0677",
-    "MetadataAccess": [
-        "oai:ota:oucs:0677"
-    ],
-    "PublicationTimestamp": "1590-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1590"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Greene, Robert, 1558?-1592"
-    ],
-    "fulltext": "oai:ota:oucs:0677;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0677.xml;The Scottish history of James the Fourth / by Robert Greene;Greene, Robert, 1558?-1592;1590;text_and_corpus_linguistics;English drama -- Early modern and Elizabethan, 1500-1600;eng;Oxford Text Archive, University of Oxford;Bolz, Norbert W.;(1 file : ca. 220 KB);Text;Plays;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "97deb326-60ee-5043-9629-952750fc8032",
-    "oai_identifier": [
-        "oai:ota:oucs:0677"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- Early modern Elizabethan"
-        }
-    ],
-    "title": [
-        "The Scottish history of James the Fourth / by Robert Greene"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0677.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/97e0b2b9-090a-5860-8972-8db0c269394d.json b/oaitestdata/clarin-oai_dc/SET_1/json/97e0b2b9-090a-5860-8972-8db0c269394d.json
deleted file mode 100644
index f9f8ab7d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/97e0b2b9-090a-5860-8972-8db0c269394d.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/533",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/533"
-    ],
-    "PID": "http://hdl.handle.net/11321/533",
-    "PublicationTimestamp": "2018-07-20T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "Janz, Arkadiusz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/533;2018-07-20T11:06:59Z;hdl_11321_3;hdl_11321_4;Corpus2MWE;Janz, Arkadiusz;CCL;MWE detection;A CCL reader (Corpus2) with MWE detection.;2018-07-20;toolService;http://hdl.handle.net/11321/533;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;Wroc\u0142aw University of Technology;http://nlp.pwr.wroc.pl/redmine/projects/corpus2/wiki",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "97e0b2b9-090a-5860-8972-8db0c269394d",
-    "notes": [
-        "A CCL reader (Corpus2) with MWE detection."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/533"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "CCL"
-        },
-        {
-            "name": "MWE detection"
-        }
-    ],
-    "title": [
-        "Corpus2MWE"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/97fc63e3-63a5-5010-ab90-b5eff4920fe5.json b/oaitestdata/clarin-oai_dc/SET_1/json/97fc63e3-63a5-5010-ab90-b5eff4920fe5.json
deleted file mode 100644
index cca052ff..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/97fc63e3-63a5-5010-ab90-b5eff4920fe5.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5639",
-    "MetadataAccess": [
-        "oai:ota:oucs:5639"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hey, Mrs."
-    ],
-    "fulltext": "oai:ota:oucs:5639;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5639.xml;A generous discovery of many curious and useful medicines and preparations, both in physic, chymistry, cookery, and stiffenry; as a drink for the small pox, ... To be had at Mrs. Hey's near the Wax-candle in St. Andrew's Norwich;Hey, Mrs.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "97fc63e3-63a5-5010-ab90-b5eff4920fe5",
-    "oai_identifier": [
-        "oai:ota:oucs:5639"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A generous discovery of many curious and useful medicines and preparations, both in physic, chymistry, cookery, and stiffenry; as a drink for the small pox, ... To be had at Mrs. Hey's near the Wax-candle in St. Andrew's Norwich"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5639.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/98008e09-c9cd-54f0-9b18-a2f30ee88897.json b/oaitestdata/clarin-oai_dc/SET_1/json/98008e09-c9cd-54f0-9b18-a2f30ee88897.json
deleted file mode 100644
index e2f08139..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/98008e09-c9cd-54f0-9b18-a2f30ee88897.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5035",
-    "MetadataAccess": [
-        "oai:ota:oucs:5035"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Trusler, John, 1735-1820."
-    ],
-    "fulltext": "oai:ota:oucs:5035;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5035.xml;The habitable world described: or the present state of the people in all parts of the globe, from north to south; shewing the situation, extent, climate, ... including all the new discoveries: ... With a great variety of maps and copper-plates, ... By the Rev. Dr. John Trusler. ... [pt.1];Trusler, John, 1735-1820.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "98008e09-c9cd-54f0-9b18-a2f30ee88897",
-    "oai_identifier": [
-        "oai:ota:oucs:5035"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The habitable world described: or the present state of the people in all parts of the globe, from north to south; shewing the situation, extent, climate, ... including all the new discoveries: ... With a great variety of maps and copper-plates, ... By the Rev. Dr. John Trusler. ... [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5035.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/98078199-78a4-5cca-9518-5c0677144201.json b/oaitestdata/clarin-oai_dc/SET_1/json/98078199-78a4-5cca-9518-5c0677144201.json
deleted file mode 100644
index 33211bff..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/98078199-78a4-5cca-9518-5c0677144201.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "between 2 and 5 MB"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0292",
-    "MetadataAccess": [
-        "oai:ota:oucs:0292"
-    ],
-    "PublicationYear": [
-        "364 BCE-322 BCE"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Addresses"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Demosthenes"
-    ],
-    "fulltext": "oai:ota:oucs:0292;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0292.xml;Orationes / compiled by Thesaurus Linguae Graecae;Demosthenes;364 BCE-322 BCE;text_and_corpus_linguistics;Addresses -- Greece -- 4th century B.C.;grc;Oxford Text Archive, University of Oxford;between 2 and 5 MB;Text;Addresses;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "98078199-78a4-5cca-9518-5c0677144201",
-    "oai_identifier": [
-        "oai:ota:oucs:0292"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Addresses -- Greece -- th century B.C."
-        }
-    ],
-    "title": [
-        "Orationes / compiled by Thesaurus Linguae Graecae"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0292.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/982655d4-06e2-57c3-861f-4d65d7f88305.json b/oaitestdata/clarin-oai_dc/SET_1/json/982655d4-06e2-57c3-861f-4d65d7f88305.json
deleted file mode 100644
index 702b050f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/982655d4-06e2-57c3-861f-4d65d7f88305.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4567",
-    "MetadataAccess": [
-        "oai:ota:oucs:4567"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Defoe, Daniel, 1661?-1731."
-    ],
-    "fulltext": "oai:ota:oucs:4567;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4567.xml;The dissenters in England vindicated from some reflections in a late pamphlet, entituled, Lawful prejudices, &c;Defoe, Daniel, 1661?-1731.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "982655d4-06e2-57c3-861f-4d65d7f88305",
-    "oai_identifier": [
-        "oai:ota:oucs:4567"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The dissenters in England vindicated from some reflections in a late pamphlet, entituled, Lawful prejudices, &c"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4567.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9844d737-a64f-54ee-b218-24ed4a126620.json b/oaitestdata/clarin-oai_dc/SET_1/json/9844d737-a64f-54ee-b218-24ed4a126620.json
deleted file mode 100644
index 35a5a3b6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9844d737-a64f-54ee-b218-24ed4a126620.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Department of Information Technology, Gauhati University, Assam, India"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Assamese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/612",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/612"
-    ],
-    "PID": "http://hdl.handle.net/11321/612",
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Department of Information Technology, Gauhati University, Assam, India"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "author": [
-        "Sarma, Jumi",
-        "Sarma, Prof. Shikhar Kr."
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/612;2019-01-08T10:37:42Z;hdl_11321_3;hdl_11321_610;Assamese WSD List;Sarma, Prof. Shikhar Kr.;Sarma, Jumi;Assamese NLP;Assamese WSD;Assamese words with multiple meanings;Assamese words with multiple senses Gauhati University;WSD is the process of identifying the proper sense of an ambiguous word depending on the particular context. Assamese WSD list comprise of more than 100 words with their multiple senses. Also English meaning of each of the senses are given.\r\n\r\n---\r\n\r\n1. These Assamese NLP resources including the Tools and Applications are developed\r\nduring Research and Development Projects as well as Masters and Ph.D. thesis\r\nworks.\r\n2. These are mainly developed or generated at Gauhati University Department of\r\nComputer Science and Department of Information Technology.\r\n3. These resources are used by students and researchers for further studies, researches, as\r\nwell as for design and development of tools and applications.\r\n4. Computational Linguistics in Assamese is not rich, and Natural Language Processing\r\nworks have mainly started during last two decades, and most of the resources are first\r\ngeneration resources, and with ample scope for upgrading, enriching, and purifying.\r\n5. These are very good and essential resources for all the researchers in Assamese NLP, as\r\nthe language requires more and more NLP works to make Assamese a rich media for\r\nthe digital world.\r\n6. Anyone interested, or in need of such resources may express their interest for the\r\nrequired resources, and the way of availability will be advised/informed accordingly.\r\n7. These are purely research materials and could only be used for further research only.\r\n8. Researchers may visit the NLP Lab of Department of Information Technology, Gauhati\r\nUniversity, Guwahati, India or contact us.\r\n9. Researchers interested in collaborative works, and also students for project works, are\r\nwelcome.\r\n10. Contact person is Professor Shikhar Kr. Sarma, Department of Information\r\nTechnology, Gauhati University, Guwahati 781014, Assam, India. Email-\r\nsks@gauhati.ac.in;2019-01-08;lexicalConceptualResource;http://hdl.handle.net/11321/612;asm;downloadable_files_count: 0;Department of Information Technology, Gauhati University, Assam, India",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9844d737-a64f-54ee-b218-24ed4a126620",
-    "notes": [
-        "WSD is the process of identifying the proper sense of an ambiguous word depending on the particular context. Assamese WSD list comprise of more than 100 words with their multiple senses. Also English meaning of each of the senses are given.\r\n\r\n---\r\n\r\n1. These Assamese NLP resources including the Tools and Applications are developed\r\nduring Research and Development Projects as well as Masters and Ph.D. thesis\r\nworks.\r\n2. These are mainly developed or generated at Gauhati University Department of\r\nComputer Science and Department of Information Technology.\r\n3. These resources are used by students and researchers for further studies, researches, as\r\nwell as for design and development of tools and applications.\r\n4. Computational Linguistics in Assamese is not rich, and Natural Language Processing\r\nworks have mainly started during last two decades, and most of the resources are first\r\ngeneration resources, and with ample scope for upgrading, enriching, and purifying.\r\n5. These are very good and essential resources for all the researchers in Assamese NLP, as\r\nthe language requires more and more NLP works to make Assamese a rich media for\r\nthe digital world.\r\n6. Anyone interested, or in need of such resources may express their interest for the\r\nrequired resources, and the way of availability will be advised/informed accordingly.\r\n7. These are purely research materials and could only be used for further research only.\r\n8. Researchers may visit the NLP Lab of Department of Information Technology, Gauhati\r\nUniversity, Guwahati, India or contact us.\r\n9. Researchers interested in collaborative works, and also students for project works, are\r\nwelcome.\r\n10. Contact person is Professor Shikhar Kr. Sarma, Department of Information\r\nTechnology, Gauhati University, Guwahati 781014, Assam, India. Email-\r\nsks@gauhati.ac.in"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/612"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_610"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Assamese NLP"
-        },
-        {
-            "name": "Assamese WSD"
-        },
-        {
-            "name": "Assamese words multiple meanings"
-        },
-        {
-            "name": "Assamese words multiple senses Gauhati University"
-        }
-    ],
-    "title": [
-        "Assamese WSD List"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9844e0fd-7af1-53e8-9b41-edf525a4c343.json b/oaitestdata/clarin-oai_dc/SET_1/json/9844e0fd-7af1-53e8-9b41-edf525a4c343.json
deleted file mode 100644
index 70418c71..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9844e0fd-7af1-53e8-9b41-edf525a4c343.json
+++ /dev/null
@@ -1,423 +0,0 @@
-{
-    "Contact": [
-        "Universal Dependencies Consortium"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 3"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)",
-        "Arabic",
-        "Basque",
-        "Bulgarian",
-        "Croatian",
-        "Czech",
-        "Danish",
-        "Dutch",
-        "English",
-        "Estonian",
-        "Finnish",
-        "French",
-        "German",
-        "Gothic",
-        "Modern Greek (1453-)",
-        "Hebrew",
-        "Hindi",
-        "Hungarian",
-        "Indonesian",
-        "Irish",
-        "Italian",
-        "Japanese",
-        "Latin",
-        "Norwegian",
-        "Church Slavic",
-        "Persian",
-        "Polish",
-        "Portuguese",
-        "Romanian",
-        "Slovenian",
-        "Spanish",
-        "Swedish",
-        "Tamil",
-        "Catalan",
-        "Chinese",
-        "Galician",
-        "Kazakh",
-        "Latvian",
-        "Russian",
-        "Turkish",
-        "Coptic",
-        "Sanskrit",
-        "Slovak",
-        "Ukrainian",
-        "Uighur",
-        "Vietnamese",
-        "Belarusian",
-        "Korean",
-        "Lithuanian",
-        "Urdu",
-        "Northern Sami",
-        "Upper Sorbian",
-        "Afrikaans",
-        "Marathi",
-        "Serbian",
-        "Telugu",
-        "Amharic",
-        "Armenian",
-        "Breton",
-        "Faroese",
-        "Old French (842-ca. 1400)",
-        "Tagalog",
-        "Thai",
-        "Yoruba"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2837",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2837"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2837",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Universal Dependencies Consortium"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-2515",
-        "http://hdl.handle.net/11234/1-2895"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Licence Universal Dependencies v2.2",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-2.2",
-        "PUB"
-    ],
-    "author": [
-        "Ion, Radu",
-        "Seraji, Mojgan",
-        "Omura, Mai",
-        "Lee, John",
-        "Manning, Christopher",
-        "Cebiro\u011flu Eryi\u011fit, G\u00fcl\u015fen",
-        "Ma\u0161ek, Jan",
-        "Trukhina, Anna",
-        "Hlav\u00e1\u010dov\u00e1, Jaroslava",
-        "Passarotti, Marco",
-        "Nguy\u1ec5n Th\u1ecb, L\u01b0\u01a1ng",
-        "Zhu, Hanzhi",
-        "Takahashi, Yuta",
-        "B\u00f6rstell, Carl",
-        "Macketanz, Vivien",
-        "Tellier, Isabelle",
-        "Agi\u0107, \u017deljko",
-        "Rosa, Rudolf",
-        "Zeldes, Amir",
-        "Muischnek, Kadri",
-        "Choi, Jinho",
-        "Washington, Jonathan North",
-        "Romanenko, Mykhailo",
-        "Montemagni, Simonetta",
-        "Davidson, Elizabeth",
-        "Ojala, Stina",
-        "Ure\u0161ov\u00e1, Zde\u0148ka",
-        "Moskalevskyi, Bohdan",
-        "Stella, Antonio",
-        "Rovati, Davide",
-        "Sawanakunanon, Yanin",
-        "Yan, Chunxiao",
-        "Bank, Sebastian",
-        "Seeker, Wolfgang",
-        "Harris, Kim",
-        "Rademaker, Alexandre",
-        "Dirix, Peter",
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "Caron, Bernard",
-        "Sanguinetti, Manuela",
-        "Navarro Hor\u00f1iacek, Juan Ignacio",
-        "Mititelu, C\u0103t\u0103lin",
-        "Cinkov\u00e1, Silvie",
-        "Burchardt, Aljoscha",
-        "Lambertino, Lorenzo",
-        "Yu, Zhuoran",
-        "G\u00f6k\u0131rmak, Memduh",
-        "Simk\u00f3, Katalin",
-        "Badmaeva, Elena",
-        "Hladk\u00e1, Barbora",
-        "Bellato, Sandra",
-        "Trosterud, Trond",
-        "Krek, Simon",
-        "Han, Na-Rae",
-        "L\u00ea H\u1ed3ng, Ph\u01b0\u01a1ng",
-        "\u00d8vrelid, Lilja",
-        "Galbraith, Daniel",
-        "Lenci, Alessandro",
-        "Seddah, Djam\u00e9",
-        "Hwang, Jena",
-        "Ginter, Filip",
-        "Erjavec, Toma\u017e",
-        "Johannsen, Anders",
-        "Bick, Eckhard",
-        "Osenova, Petya",
-        "Mart\u00ednez Alonso, H\u00e9ctor",
-        "Larasati, Septina Dian",
-        "Kettnerov\u00e1, V\u00e1clava",
-        "Kayadelen, Tolga",
-        "Vajjala, Sowmya",
-        "Kahane, Sylvain",
-        "Li, Josie",
-        "Haug, Dag",
-        "Rehm, Georg",
-        "Rinaldi, Larissa",
-        "Lynn, Teresa",
-        "Tanaka, Takaaki",
-        "Plank, Barbara",
-        "Uematsu, Sumire",
-        "Freitas, Cl\u00e1udia",
-        "Varga, Viktor",
-        "Lyashevskaya, Olga",
-        "J\u00f8rgensen, Fredrik",
-        "M\u0103r\u0103nduc, C\u0103t\u0103lina",
-        "Ka\u015f\u0131kara, H\u00fcner",
-        "Pyysalo, Sampo",
-        "Kanerva, Jenna",
-        "Arutie, Gashaw",
-        "Sz\u00e1nt\u00f3, Zsolt",
-        "Chalub, Fabricio",
-        "Collomb, Aur\u00e9lie",
-        "Marheinecke, Katrin",
-        "Lim, KyungTae",
-        "Atutxa, Aitziber",
-        "Augustinus, Liesbeth",
-        "Goldberg, Yoav",
-        "Williams, Seyi",
-        "Matsumoto, Yuji",
-        "Biagetti, Erica",
-        "Dozat, Timothy",
-        "Ateyah, Luma",
-        "Przepi\u00f3rkowski, Adam",
-        "G\u00f3mez Guinovart, Xavier",
-        "M\u00fc\u00fcrisep, Kaili",
-        "Saul\u012bte, Baiba",
-        "Caron, Gauthier",
-        "Mandl, Michael",
-        "Nivre, Joakim",
-        "Prokopidis, Prokopis",
-        "Petrov, Slav",
-        "R\u00e4\u00e4bis, Andriela",
-        "Sichinava, Dmitry",
-        "Reddy, Siva",
-        "Guillaume, Bruno",
-        "Gr\u016bz\u012btis, Normunds",
-        "Cetin, Savas",
-        "Haji\u010d jr., Jan",
-        "Ephrem, Binyam",
-        "Perrier, Guy",
-        "Schneider, Nathan",
-        "Nainwani, Pinkey",
-        "de Marneffe, Marie-Catherine",
-        "Antonsen, Lene",
-        "Rocha, Luisa",
-        "Attia, Mohammed",
-        "Schuster, Sebastian",
-        "Missil\u00e4, Anna",
-        "Rama, Taraka",
-        "Dwivedi, Puneet",
-        "Hohle, Petter",
-        "Makazhanov, Aibek",
-        "Lavrentiev, Alexei",
-        "Tyers, Francis",
-        "McDonald, Ryan",
-        "Pretkalni\u0146a, Lauma",
-        "Farkas, Rich\u00e1rd",
-        "Moreno Romero, Laura",
-        "Soares-Bastos, Isabela",
-        "Martins, Andr\u00e9",
-        "Ramasamy, Loganathan",
-        "Bosco, Cristina",
-        "Kirchner, Jesse",
-        "Uszkoreit, Hans",
-        "Simionescu, Radu",
-        "Fernandez Alcalde, Hector",
-        "Eli, Marhaba",
-        "Yavrumyan, Marat M.",
-        "Barbu Mititelu, Verginica",
-        "Patejuk, Agnieszka",
-        "Ravishankar, Vinit",
-        "de Paiva, Valeria",
-        "Grioni, Matias",
-        "Real, Livy",
-        "Lertpradit, Saran",
-        "Asahara, Masayuki",
-        "Pitler, Emily",
-        "Suhr, Alane",
-        "Miekka, Niko",
-        "Miyao, Yusuke",
-        "Vincze, Veronika",
-        "Kwak, Sookyoung",
-        "Cho, Yongseok",
-        "Blokland, Rogier",
-        "Bhat, Riyaz Ahmad",
-        "Garcia, Marcos",
-        "Loginova, Olga",
-        "Shimada, Atsuko",
-        "Straka, Milan",
-        "van Niekerk, Daniel",
-        "Murawaki, Yugo",
-        "Nguy\u1ec5n Th\u1ecb Minh, Huy\u1ec1n",
-        "Nitisaroj, Rattima",
-        "Zhang, Manying",
-        "Puolakainen, Tiina",
-        "Tsarfaty, Reut",
-        "Taji, Dima",
-        "Boyd, Adriane",
-        "Goenaga, Iakes",
-        "Rituma, Laura",
-        "H\u00e0 M\u1ef9, Linh",
-        "Habash, Nizar",
-        "Rudina, Olga",
-        "Mori, Shinsuke",
-        "Partanen, Niko",
-        "Droganova, Kira",
-        "Li, Keying",
-        "Elkahky, Ali",
-        "Connor, Miriam",
-        "Samson, Stephanie",
-        "Mare\u010dek, David",
-        "Smith, Aaron",
-        "Banerjee, Esha",
-        "Nedoluzhko, Anna",
-        "Chun, Jayeol",
-        "Strnadov\u00e1, Jana",
-        "More, Amir",
-        "Poibeau, Thierry",
-        "Mendon\u00e7a, Gustavo",
-        "\u0160imkov\u00e1, M\u00e1ria",
-        "Gajdo\u0161ov\u00e1, Katar\u00edna",
-        "Zeman, Daniel",
-        "Celano, Giuseppe G. A.",
-        "Abrams, Mitchell",
-        "Dobrovoljc, Kaja",
-        "Jel\u00ednek, Tom\u00e1\u0161",
-        "Bobicev, Victoria",
-        "Popel, Martin",
-        "Laippala, Veronika",
-        "Gojenola, Koldo",
-        "Gerdes, Kim",
-        "Lando, Tatiana",
-        "Simov, Kiril",
-        "Ballesteros, Miguel",
-        "Nurmi, Hanna",
-        "Nikolaev, Vitaly",
-        "Wir\u00e9n, Mats",
-        "Perez, Cenel-Augusto",
-        "Bauer, John",
-        "Ljube\u0161i\u0107, Nikola",
-        "Woldemariam, Tsegay",
-        "Wong, Tak-sum",
-        "Ahrenberg, Lars",
-        "Sadde, Shoval",
-        "Ne\u0161pore-B\u0113rzkalne, Gunta",
-        "Simi, Maria",
-        "Diaz de Ilarraza, Arantza",
-        "Etienne, Aline",
-        "Aranzabe, Maria Jesus",
-        "Li, Cheuk Ying",
-        "Candito, Marie",
-        "Shen, Mo",
-        "Saleh, Shadi",
-        "Irimia, Elena",
-        "Bengoetxea, Kepa",
-        "Peng, Siyao",
-        "Dickerson, Carly",
-        "Shohibussirri, Muh",
-        "Ro\u0219ca, Valentin",
-        "van Noord, Gertjan",
-        "Wallin, Lars",
-        "Pr\u00e9vost, Sophie",
-        "Guillot-Barbance, C\u00e9line",
-        "Mortensen, Bjartur",
-        "Pascual, Elena",
-        "\u00d6stling, Robert",
-        "Bouma, Gosse",
-        "Foster, Jennifer",
-        "Rie\u00dfler, Michael",
-        "G\u00e4rdenfors, Moa",
-        "\u00c7\u00f6ltekin, \u00c7a\u011fr\u0131",
-        "Piitulainen, Jussi",
-        "Ramisch, Carlos",
-        "Gonz\u00e1les Saavedra, Berta",
-        "Uria, Larraitz",
-        "Courtin, Marine",
-        "Manurung, Ruli",
-        "Leung, Herman",
-        "Kanayama, Hiroshi",
-        "Haji\u010d, Jan",
-        "Bowman, Sam",
-        "Kotsyba, Natalia",
-        "Sulubacak, Umut",
-        "Samard\u017ei\u0107, Tanja",
-        "Silveira, Natalia",
-        "Ol\u00fa\u00f2kun, Ad\u00e9day\u1ecd\u0300",
-        "Hociung, Florinel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2837;2018-11-15T10:38:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Universal Dependencies 2.2;Nivre, Joakim;Abrams, Mitchell;Agi\u0107, \u017deljko;Ahrenberg, Lars;Antonsen, Lene;Aranzabe, Maria Jesus;Arutie, Gashaw;Asahara, Masayuki;Ateyah, Luma;Attia, Mohammed;Atutxa, Aitziber;Augustinus, Liesbeth;Badmaeva, Elena;Ballesteros, Miguel;Banerjee, Esha;Bank, Sebastian;Barbu Mititelu, Verginica;Bauer, John;Bellato, Sandra;Bengoetxea, Kepa;Bhat, Riyaz Ahmad;Biagetti, Erica;Bick, Eckhard;Blokland, Rogier;Bobicev, Victoria;B\u00f6rstell, Carl;Bosco, Cristina;Bouma, Gosse;Bowman, Sam;Boyd, Adriane;Burchardt, Aljoscha;Candito, Marie;Caron, Bernard;Caron, Gauthier;Cebiro\u011flu Eryi\u011fit, G\u00fcl\u015fen;Celano, Giuseppe G. A.;Cetin, Savas;Chalub, Fabricio;Choi, Jinho;Cho, Yongseok;Chun, Jayeol;Cinkov\u00e1, Silvie;Collomb, Aur\u00e9lie;\u00c7\u00f6ltekin, \u00c7a\u011fr\u0131;Connor, Miriam;Courtin, Marine;Davidson, Elizabeth;de Marneffe, Marie-Catherine;de Paiva, Valeria;Diaz de Ilarraza, Arantza;Dickerson, Carly;Dirix, Peter;Dobrovoljc, Kaja;Dozat, Timothy;Droganova, Kira;Dwivedi, Puneet;Eli, Marhaba;Elkahky, Ali;Ephrem, Binyam;Erjavec, Toma\u017e;Etienne, Aline;Farkas, Rich\u00e1rd;Fernandez Alcalde, Hector;Foster, Jennifer;Freitas, Cl\u00e1udia;Gajdo\u0161ov\u00e1, Katar\u00edna;Galbraith, Daniel;Garcia, Marcos;G\u00e4rdenfors, Moa;Gerdes, Kim;Ginter, Filip;Goenaga, Iakes;Gojenola, Koldo;G\u00f6k\u0131rmak, Memduh;Goldberg, Yoav;G\u00f3mez Guinovart, Xavier;Gonz\u00e1les Saavedra, Berta;Grioni, Matias;Gr\u016bz\u012btis, Normunds;Guillaume, Bruno;Guillot-Barbance, C\u00e9line;Habash, Nizar;Haji\u010d, Jan;Haji\u010d jr., Jan;H\u00e0 M\u1ef9, Linh;Han, Na-Rae;Harris, Kim;Haug, Dag;Hladk\u00e1, Barbora;Hlav\u00e1\u010dov\u00e1, Jaroslava;Hociung, Florinel;Hohle, Petter;Hwang, Jena;Ion, Radu;Irimia, Elena;Jel\u00ednek, Tom\u00e1\u0161;Johannsen, Anders;J\u00f8rgensen, Fredrik;Ka\u015f\u0131kara, H\u00fcner;Kahane, Sylvain;Kanayama, Hiroshi;Kanerva, Jenna;Kayadelen, Tolga;Kettnerov\u00e1, V\u00e1clava;Kirchner, Jesse;Kotsyba, Natalia;Krek, Simon;Kwak, Sookyoung;Laippala, Veronika;Lambertino, Lorenzo;Lando, Tatiana;Larasati, Septina Dian;Lavrentiev, Alexei;Lee, John;L\u00ea H\u1ed3ng, Ph\u01b0\u01a1ng;Lenci, Alessandro;Lertpradit, Saran;Leung, Herman;Li, Cheuk Ying;Li, Josie;Li, Keying;Lim, KyungTae;Ljube\u0161i\u0107, Nikola;Loginova, Olga;Lyashevskaya, Olga;Lynn, Teresa;Macketanz, Vivien;Makazhanov, Aibek;Mandl, Michael;Manning, Christopher;Manurung, Ruli;M\u0103r\u0103nduc, C\u0103t\u0103lina;Mare\u010dek, David;Marheinecke, Katrin;Mart\u00ednez Alonso, H\u00e9ctor;Martins, Andr\u00e9;Ma\u0161ek, Jan;Matsumoto, Yuji;McDonald, Ryan;Mendon\u00e7a, Gustavo;Miekka, Niko;Missil\u00e4, Anna;Mititelu, C\u0103t\u0103lin;Miyao, Yusuke;Montemagni, Simonetta;More, Amir;Moreno Romero, Laura;Mori, Shinsuke;Mortensen, Bjartur;Moskalevskyi, Bohdan;Muischnek, Kadri;Murawaki, Yugo;M\u00fc\u00fcrisep, Kaili;Nainwani, Pinkey;Navarro Hor\u00f1iacek, Juan Ignacio;Nedoluzhko, Anna;Ne\u0161pore-B\u0113rzkalne, Gunta;Nguy\u1ec5n Th\u1ecb, L\u01b0\u01a1ng;Nguy\u1ec5n Th\u1ecb Minh, Huy\u1ec1n;Nikolaev, Vitaly;Nitisaroj, Rattima;Nurmi, Hanna;Ojala, Stina;Ol\u00fa\u00f2kun, Ad\u00e9day\u1ecd\u0300;Omura, Mai;Osenova, Petya;\u00d6stling, Robert;\u00d8vrelid, Lilja;Partanen, Niko;Pascual, Elena;Passarotti, Marco;Patejuk, Agnieszka;Peng, Siyao;Perez, Cenel-Augusto;Perrier, Guy;Petrov, Slav;Piitulainen, Jussi;Pitler, Emily;Plank, Barbara;Poibeau, Thierry;Popel, Martin;Pretkalni\u0146a, Lauma;Pr\u00e9vost, Sophie;Prokopidis, Prokopis;Przepi\u00f3rkowski, Adam;Puolakainen, Tiina;Pyysalo, Sampo;R\u00e4\u00e4bis, Andriela;Rademaker, Alexandre;Ramasamy, Loganathan;Rama, Taraka;Ramisch, Carlos;Ravishankar, Vinit;Real, Livy;Reddy, Siva;Rehm, Georg;Rie\u00dfler, Michael;Rinaldi, Larissa;Rituma, Laura;Rocha, Luisa;Romanenko, Mykhailo;Rosa, Rudolf;Rovati, Davide;Ro\u0219ca, Valentin;Rudina, Olga;Sadde, Shoval;Saleh, Shadi;Samard\u017ei\u0107, Tanja;Samson, Stephanie;Sanguinetti, Manuela;Saul\u012bte, Baiba;Sawanakunanon, Yanin;Schneider, Nathan;Schuster, Sebastian;Seddah, Djam\u00e9;Seeker, Wolfgang;Seraji, Mojgan;Shen, Mo;Shimada, Atsuko;Shohibussirri, Muh;Sichinava, Dmitry;Silveira, Natalia;Simi, Maria;Simionescu, Radu;Simk\u00f3, Katalin;\u0160imkov\u00e1, M\u00e1ria;Simov, Kiril;Smith, Aaron;Soares-Bastos, Isabela;Stella, Antonio;Straka, Milan;Strnadov\u00e1, Jana;Suhr, Alane;Sulubacak, Umut;Sz\u00e1nt\u00f3, Zsolt;Taji, Dima;Takahashi, Yuta;Tanaka, Takaaki;Tellier, Isabelle;Trosterud, Trond;Trukhina, Anna;Tsarfaty, Reut;Tyers, Francis;Uematsu, Sumire;Ure\u0161ov\u00e1, Zde\u0148ka;Uria, Larraitz;Uszkoreit, Hans;Vajjala, Sowmya;van Niekerk, Daniel;van Noord, Gertjan;Varga, Viktor;Vincze, Veronika;Wallin, Lars;Washington, Jonathan North;Williams, Seyi;Wir\u00e9n, Mats;Woldemariam, Tsegay;Wong, Tak-sum;Yan, Chunxiao;Yavrumyan, Marat M.;Yu, Zhuoran;\u017dabokrtsk\u00fd, Zden\u011bk;Zeldes, Amir;Zeman, Daniel;Zhang, Manying;Zhu, Hanzhi;treebank;dependency;syntax;morphology;harmonized annotation;interset;universal tagset;stanford dependencies;Universal Dependencies is a project that seeks to develop cross-linguistically consistent treebank annotation for many languages, with the goal of facilitating multilingual parser development, cross-lingual learning, and parsing research from a language typology perspective. The annotation scheme is based on (universal) Stanford dependencies (de Marneffe et al., 2006, 2008, 2014), Google universal part-of-speech tags (Petrov et al., 2012), and the Interset interlingua for morphosyntactic tagsets (Zeman, 2008).;2018-07-01;corpus;http://hdl.handle.net/11234/1-2837;grc;ara;eus;bul;hrv;ces;dan;nld;eng;est;fin;fra;deu;got;ell;heb;hin;hun;ind;gle;ita;jpn;lat;nor;chu;fas;pol;por;ron;slv;spa;swe;tam;cat;zho;glg;kaz;lav;rus;tur;cop;san;slk;ukr;uig;vie;bel;kor;lit;urd;bxr;kmr;sme;hsb;afr;yue;mar;srp;swl;tel;amh;hye;bre;fao;kpv;pcm;fro;tgl;tha;wbp;yor;http://hdl.handle.net/11234/1-2515;http://hdl.handle.net/11234/1-2895;Licence Universal Dependencies v2.2;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-2.2;PUB;text/plain; charset=utf-8;application/x-gzip;application/x-gzip;application/x-gzip;downloadable_files_count: 3;Universal Dependencies Consortium;http://universaldependencies.org/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9844e0fd-7af1-53e8-9b41-edf525a4c343",
-    "notes": [
-        "Universal Dependencies is a project that seeks to develop cross-linguistically consistent treebank annotation for many languages, with the goal of facilitating multilingual parser development, cross-lingual learning, and parsing research from a language typology perspective. The annotation scheme is based on (universal) Stanford dependencies (de Marneffe et al., 2006, 2008, 2014), Google universal part-of-speech tags (Petrov et al., 2012), and the Interset interlingua for morphosyntactic tagsets (Zeman, 2008)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2837"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "dependency"
-        },
-        {
-            "name": "syntax"
-        },
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "harmonized annotation"
-        },
-        {
-            "name": "interset"
-        },
-        {
-            "name": "universal tagset"
-        },
-        {
-            "name": "stanford dependencies"
-        }
-    ],
-    "title": [
-        "Universal Dependencies 2.2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9844f8bd-6da4-527c-9105-da618985cd89.json b/oaitestdata/clarin-oai_dc/SET_1/json/9844f8bd-6da4-527c-9105-da618985cd89.json
deleted file mode 100644
index 78ff3430..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9844f8bd-6da4-527c-9105-da618985cd89.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "University of Silesia"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 86",
-        "text/plain; charset=utf-8",
-        "text/plain"
-    ],
-    "Language": [],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/518",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/518"
-    ],
-    "PID": "http://hdl.handle.net/11321/518",
-    "PublicationTimestamp": "2018-07-13T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "University of Silesia"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Smiths, John"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/518;2018-07-13T13:51:18Z;hdl_11321_3;hdl_11321_4;Workshop 13.07;Smiths, John;text;xxx;2018-07-13;corpus;http://hdl.handle.net/11321/518;Polska;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;downloadable_files_count: 86;University of Silesia",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9844f8bd-6da4-527c-9105-da618985cd89",
-    "notes": [
-        "xxx"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/518"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "text"
-        }
-    ],
-    "title": [
-        "Workshop 13.07"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/98456264-75ba-5e1a-9040-58f5db4e8c28.json b/oaitestdata/clarin-oai_dc/SET_1/json/98456264-75ba-5e1a-9040-58f5db4e8c28.json
deleted file mode 100644
index a7b78a1d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/98456264-75ba-5e1a-9040-58f5db4e8c28.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "ZRC SAZU"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1127",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1127"
-    ],
-    "PID": "http://hdl.handle.net/11356/1127",
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "ZRC SAZU"
-    ],
-    "RelatedIdentifier": [
-        "http://www.fran.si/140/besedje-slovenskega-knjiznega-jezika-16-stoletja/datoteke/Besedje16_Uvod.pdf"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Novak, France",
-        "Legan Ravnikar, Andreja",
-        "Narat, Jo\u017eica",
-        "Aha\u010di\u010d, Kozma",
-        "Mer\u0161e, Majda"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1127;2017-07-01T10:51:30Z;hdl_11356_1023;hdl_11356_1024;Words of the 16th-Century Slovenian Literary Language;Aha\u010di\u010d, Kozma;Legan Ravnikar, Andreja;Mer\u0161e, Majda;Narat, Jo\u017eica;Novak, France;dictionary;historical language;lexicography;This dictionary provides comprehensive information on the vocabulary used in the Slovenian literary language during the period of the Reformation. It was written based on complete concordance from all editions of Slovenian texts from the period 1550-1603. The word entries are accompanied by grammatical information, such as the part of speech used and other grammatical data. The extent of their use is shown by the attributed sources. The features of the linguistic system of that period are also shown by numerous notices regarding written, phonological and morphological variations.\r\n\r\nThis dictionary was published as a printed book:\r\nAha\u010di\u010d, Kozma, Legan Ravnikar, Andreja, Mer\u0161e, Majda, Narat, Jo\u017eica, Novak, France. Besedje slovenskega knji\u017enega jezika 16. stoletja. Ljubljana : Zalo\u017eba ZRC, ZRC SAZU, 2011. ISBN 978-961-254-252-8.;2011;lexicalConceptualResource;http://hdl.handle.net/11356/1127;slv;http://www.fran.si/140/besedje-slovenskega-knjiznega-jezika-16-stoletja/datoteke/Besedje16_Uvod.pdf;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;ZRC SAZU;http://www.fran.si/iskanje?FilteredDictionaryIds=140&View=1&Query=%2A",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "98456264-75ba-5e1a-9040-58f5db4e8c28",
-    "notes": [
-        "This dictionary provides comprehensive information on the vocabulary used in the Slovenian literary language during the period of the Reformation. It was written based on complete concordance from all editions of Slovenian texts from the period 1550-1603. The word entries are accompanied by grammatical information, such as the part of speech used and other grammatical data. The extent of their use is shown by the attributed sources. The features of the linguistic system of that period are also shown by numerous notices regarding written, phonological and morphological variations.\r\n\r\nThis dictionary was published as a printed book:\r\nAha\u010di\u010d, Kozma, Legan Ravnikar, Andreja, Mer\u0161e, Majda, Narat, Jo\u017eica, Novak, France. Besedje slovenskega knji\u017enega jezika 16. stoletja. Ljubljana : Zalo\u017eba ZRC, ZRC SAZU, 2011. ISBN 978-961-254-252-8."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1127"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "dictionary"
-        },
-        {
-            "name": "historical language"
-        },
-        {
-            "name": "lexicography"
-        }
-    ],
-    "title": [
-        "Words of the 16th-Century Slovenian Literary Language"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/984cfc5d-00de-5d41-aaa2-98421a769973.json b/oaitestdata/clarin-oai_dc/SET_1/json/984cfc5d-00de-5d41-aaa2-98421a769973.json
deleted file mode 100644
index c9020a36..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/984cfc5d-00de-5d41-aaa2-98421a769973.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Katholieke Universiteit Leuven Campus Kortrijk, Hogeschool Gent"
-    ],
-    "Contributor": [
-        "Paulussen, Hans"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Dutch",
-        "English",
-        "French"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-631",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-631"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-631",
-    "PublicationTimestamp": "2009-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2009"
-    ],
-    "Publisher": [
-        "Katholieke Universiteit Leuven Campus Kortrijk, Hogeschool Gent"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Belgium"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-631;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;DPC (Dutch Parallel Corpus);Paulussen, Hans;Parallel corpus, with Dutch as first language, 10 M words (under construction).  DPC is a STEVIN-project.;2009;corpus;http://hdl.handle.net/11372/LRT-631;nld;eng;fra;downloadable_files_count: 0;Belgium;Katholieke Universiteit Leuven Campus Kortrijk, Hogeschool Gent;http://www.kuleuven-kortrijk.be/DPC",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "984cfc5d-00de-5d41-aaa2-98421a769973",
-    "notes": [
-        "Parallel corpus, with Dutch as first language, 10 M words (under construction).  DPC is a STEVIN-project."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-631"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "DPC (Dutch Parallel Corpus)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9868cb9a-36db-5711-8253-c6bec9555ec4.json b/oaitestdata/clarin-oai_dc/SET_1/json/9868cb9a-36db-5711-8253-c6bec9555ec4.json
deleted file mode 100644
index 03835eda..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9868cb9a-36db-5711-8253-c6bec9555ec4.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-939",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-939"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-939",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-939;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Old Saxon;ca. 40.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-939;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#asachs",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9868cb9a-36db-5711-8253-c6bec9555ec4",
-    "notes": [
-        "ca. 40.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-939"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Old Saxon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/986a285e-5bea-5d86-bb8c-f85786f26a23.json b/oaitestdata/clarin-oai_dc/SET_1/json/986a285e-5bea-5d86-bb8c-f85786f26a23.json
deleted file mode 100644
index ddb77b39..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/986a285e-5bea-5d86-bb8c-f85786f26a23.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "Contributor": [
-        "Wilk, Jakub"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-287",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-287"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-287",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Poland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-287;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Poliqarp;Wilk, Jakub;Free suite of utilities for large corpora processing.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-287;downloadable_files_count: 0;Poland;Institute of Computer Science, Polish Academy of Sciences;http://sourceforge.net/projects/poliqarp/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "986a285e-5bea-5d86-bb8c-f85786f26a23",
-    "notes": [
-        "Free suite of utilities for large corpora processing."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-287"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Poliqarp"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/986cf3d1-7b76-5fd6-9a6b-59030e0f8b7b.json b/oaitestdata/clarin-oai_dc/SET_1/json/986cf3d1-7b76-5fd6-9a6b-59030e0f8b7b.json
deleted file mode 100644
index 2b7d9041..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/986cf3d1-7b76-5fd6-9a6b-59030e0f8b7b.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "University of Zagreb, Faculty of Humanities and Social Sciences"
-    ],
-    "Contributor": [
-        "Tadi\u0107, Marko"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Croatian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1182",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1182"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1182",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Zagreb, Faculty of Humanities and Social Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Croatia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1182;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Croatian Lemmatization Server;Tadi\u0107, Marko;On line service for lemmatization, full POS or MSD tagging of Croatian texts.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1182;hrv;downloadable_files_count: 0;Croatia;University of Zagreb, Faculty of Humanities and Social Sciences;http://hml.ffzg.hr/hml/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "986cf3d1-7b76-5fd6-9a6b-59030e0f8b7b",
-    "notes": [
-        "On line service for lemmatization, full POS or MSD tagging of Croatian texts."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1182"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Croatian Lemmatization Server"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9870878b-3898-52de-8b53-5e6debe90add.json b/oaitestdata/clarin-oai_dc/SET_1/json/9870878b-3898-52de-8b53-5e6debe90add.json
deleted file mode 100644
index a1f46b15..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9870878b-3898-52de-8b53-5e6debe90add.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Masaryk University, NLP Centre"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "text/plain"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2822",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2822"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2822",
-    "PublicationTimestamp": "2018-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Masaryk University, NLP Centre"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Nev\u011b\u0159ilov\u00e1, Zuzana",
-        "Pelik\u00e1nov\u00e1, Zuzana"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2822;2018-10-04T11:50:46Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;czTenTen12 v9 subcorpus of problematic phenomena;Pelik\u00e1nov\u00e1, Zuzana;Nev\u011b\u0159ilov\u00e1, Zuzana;Non-standard language;Interlingual homographs;Text corpus;czTenTen12 v9 subcorpus containing problematic features (interlingual homographs, foreign proper names, named entities);2018-05-30;corpus;http://hdl.handle.net/11234/1-2822;ces;Creative Commons - Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0);http://creativecommons.org/licenses/by-nc-nd/4.0/;PUB;text/plain;text/plain; charset=utf-8;downloadable_files_count: 1;Masaryk University, NLP Centre",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9870878b-3898-52de-8b53-5e6debe90add",
-    "notes": [
-        "czTenTen12 v9 subcorpus containing problematic features (interlingual homographs, foreign proper names, named entities)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2822"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Non-standard language"
-        },
-        {
-            "name": "Interlingual homographs"
-        },
-        {
-            "name": "Text corpus"
-        }
-    ],
-    "title": [
-        "czTenTen12 v9 subcorpus of problematic phenomena"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9870d4f0-3766-527f-bc0f-0ad7ecd03254.json b/oaitestdata/clarin-oai_dc/SET_1/json/9870d4f0-3766-527f-bc0f-0ad7ecd03254.json
deleted file mode 100644
index f190a02b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9870d4f0-3766-527f-bc0f-0ad7ecd03254.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "MENOTA - Medieval Nordic Text Archive"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml",
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Old Norse"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/113",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/113"
-    ],
-    "PID": "http://hdl.handle.net/11509/113",
-    "PublicationTimestamp": "2016-09-06T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "MENOTA - Medieval Nordic Text Archive"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0)",
-        "CC",
-        "http://creativecommons.org/licenses/by-sa/3.0/"
-    ],
-    "author": [
-        "Horn, Anna C"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/113;2016-09-07T08:54:41Z;hdl_11509_1;hdl_11509_2;AM 305 fol (Magn\u00fass Lagab\u01fftis landsl\u01ebg and other law texts): a digital edition;Horn, Anna C;Law;Medieval;Manuscript;The text \"AM 305 fol (Magn\u00fass Lagab\u01fftis landsl\u01ebg and other law texts): a digital edition\" is part of the Medieval Nordic Text Archive (www.menota.org). The Menota catalogue has been built in the Corpuscle application at Uni Research Computing in Bergen. The texts are searchable through the Corpuscle search engine and are also downloadable from there. In the Catalogue you can also find more detailed information about each text, such as the level of analysis and linguistic annotation. All texts in the archive are listed in the first column of the Catalogue. By clicking the file names in the second column of this catalogue you will be able to read texts at up to three levels, facsimile (facs), diplomatic (dipl) and normalised (norm). The archive uses web fonts (WOFF), so no special fonts need to be installed. There is also a wide array of search facilities, especially for the texts that have been morphologically annotated.;2016-09-06;corpus;http://hdl.handle.net/11509/113;non;Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0);CC;http://creativecommons.org/licenses/by-sa/3.0/;text/xml;downloadable_files_count: 0;MENOTA - Medieval Nordic Text Archive;http://clarino.uib.no/menota/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9870d4f0-3766-527f-bc0f-0ad7ecd03254",
-    "notes": [
-        "The text \"AM 305 fol (Magn\u00fass Lagab\u01fftis landsl\u01ebg and other law texts): a digital edition\" is part of the Medieval Nordic Text Archive (www.menota.org). The Menota catalogue has been built in the Corpuscle application at Uni Research Computing in Bergen. The texts are searchable through the Corpuscle search engine and are also downloadable from there. In the Catalogue you can also find more detailed information about each text, such as the level of analysis and linguistic annotation. All texts in the archive are listed in the first column of the Catalogue. By clicking the file names in the second column of this catalogue you will be able to read texts at up to three levels, facsimile (facs), diplomatic (dipl) and normalised (norm). The archive uses web fonts (WOFF), so no special fonts need to be installed. There is also a wide array of search facilities, especially for the texts that have been morphologically annotated."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/113"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Law"
-        },
-        {
-            "name": "Medieval"
-        },
-        {
-            "name": "Manuscript"
-        }
-    ],
-    "title": [
-        "AM 305 fol (Magn\u00fass Lagab\u01fftis landsl\u01ebg and other law texts): a digital edition"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9888b06e-4574-555b-98d9-04bc4bdff5a5.json b/oaitestdata/clarin-oai_dc/SET_1/json/9888b06e-4574-555b-98d9-04bc4bdff5a5.json
deleted file mode 100644
index 0a7abaf0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9888b06e-4574-555b-98d9-04bc4bdff5a5.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 3",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1675",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1675"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1675",
-    "PublicationTimestamp": "2016-04-05T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Jur\u010d\u00ed\u010dek, Filip",
-        "Du\u0161ek, Ond\u0159ej"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1675;2018-07-02T22:05:53Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Alex Context NLG Dataset;Du\u0161ek, Ond\u0159ej;Jur\u010d\u00ed\u010dek, Filip;dialogue system;natural language generation;dialogue alignment;entrainment;A dataset intended for fully trainable natural language generation (NLG) systems in task-oriented spoken dialogue systems (SDS), covering the English public transport information domain. It includes preceding context (user utterance) along with each data instance (pair of source meaning representation and target natural language paraphrase to be generated).\r\nTaking the form of the previous user utterance into account for generating the system response allows NLG systems trained on this dataset to entrain (adapt) to the preceding utterance, i.e., reuse wording and syntactic structure. This should presumably improve the perceived naturalness of the output, and may even lead to a higher task success rate.\r\nCrowdsourcing has been used to obtain natural context user utterances as well as natural system responses to be generated.;2016-04-05;corpus;http://hdl.handle.net/11234/1-1675;eng;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;PUB;application/octet-stream;application/octet-stream;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 3;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://github.com/UFAL-DSG/alex_context_nlg_dataset",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9888b06e-4574-555b-98d9-04bc4bdff5a5",
-    "notes": [
-        "A dataset intended for fully trainable natural language generation (NLG) systems in task-oriented spoken dialogue systems (SDS), covering the English public transport information domain. It includes preceding context (user utterance) along with each data instance (pair of source meaning representation and target natural language paraphrase to be generated).\r\nTaking the form of the previous user utterance into account for generating the system response allows NLG systems trained on this dataset to entrain (adapt) to the preceding utterance, i.e., reuse wording and syntactic structure. This should presumably improve the perceived naturalness of the output, and may even lead to a higher task success rate.\r\nCrowdsourcing has been used to obtain natural context user utterances as well as natural system responses to be generated."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1675"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "dialogue system"
-        },
-        {
-            "name": "natural language generation"
-        },
-        {
-            "name": "dialogue alignment"
-        },
-        {
-            "name": "entrainment"
-        }
-    ],
-    "title": [
-        "Alex Context NLG Dataset"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/98e350fe-26b0-5e93-8c76-f02110276672.json b/oaitestdata/clarin-oai_dc/SET_1/json/98e350fe-26b0-5e93-8c76-f02110276672.json
deleted file mode 100644
index 2ea37217..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/98e350fe-26b0-5e93-8c76-f02110276672.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 852 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1649",
-    "MetadataAccess": [
-        "oai:ota:oucs:1649"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Twain, Mark, 1835-1910"
-    ],
-    "fulltext": "oai:ota:oucs:1649;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1649.xml;Life on the Mississippi;Twain, Mark, 1835-1910;default: 1976-01-01;text_and_corpus_linguistics;Biographies -- United States -- 19th century;Autobiographies -- United States -- 19th century;eng;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 852 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "98e350fe-26b0-5e93-8c76-f02110276672",
-    "oai_identifier": [
-        "oai:ota:oucs:1649"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Biographies -- United States -- th century"
-        },
-        {
-            "name": "Autobiographies -- United States -- th century"
-        }
-    ],
-    "title": [
-        "Life on the Mississippi"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1649.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/98efd6d0-3aab-50a2-ac10-f6ac2e90fa28.json b/oaitestdata/clarin-oai_dc/SET_1/json/98efd6d0-3aab-50a2-ac10-f6ac2e90fa28.json
deleted file mode 100644
index 2992336c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/98efd6d0-3aab-50a2-ac10-f6ac2e90fa28.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1035",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1035"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1035",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1035;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;L1 Acquisition Max Miller;Language Acquisition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1035;deu;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI4%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "98efd6d0-3aab-50a2-ac10-f6ac2e90fa28",
-    "notes": [
-        "Language Acquisition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1035"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "L1 Acquisition Max Miller"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/98f8f029-5a8d-5eac-afa1-6c083b406e0f.json b/oaitestdata/clarin-oai_dc/SET_1/json/98f8f029-5a8d-5eac-afa1-6c083b406e0f.json
deleted file mode 100644
index 1d162c36..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/98f8f029-5a8d-5eac-afa1-6c083b406e0f.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "B"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1562",
-    "MetadataAccess": [
-        "oai:ota:oucs:1562"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "While this resource was freely available for non-commercial use provided that this header is included in its entirety with any copy distributed, it has been removed from our catalogue for one reason or another.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Faulkner, William"
-    ],
-    "fulltext": "oai:ota:oucs:1562;2018-04-16T15:30:51Z;http://ota.ox.ac.uk/headers/1562.xml;Pylon;Faulkner, William;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;B;Text;While this resource was freely available for non-commercial use provided that this header is included in its entirety with any copy distributed, it has been removed from our catalogue for one reason or another.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "98f8f029-5a8d-5eac-afa1-6c083b406e0f",
-    "oai_identifier": [
-        "oai:ota:oucs:1562"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Pylon"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1562.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/98feda0e-e032-52b4-b7cb-99c600ab8662.json b/oaitestdata/clarin-oai_dc/SET_1/json/98feda0e-e032-52b4-b7cb-99c600ab8662.json
deleted file mode 100644
index adad5e94..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/98feda0e-e032-52b4-b7cb-99c600ab8662.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contributor": [
-        "Publishing, Leifur Eiriksson"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-868",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-868"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-868",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-868;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Complete sagas of Icelanders;Publishing, Leifur Eiriksson;New English translations of the entire corpus of the sagas of Icelanders and connected tales;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-868;eng;downloadable_files_count: 0;http://notendur.centrum.is/~vinland/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "98feda0e-e032-52b4-b7cb-99c600ab8662",
-    "notes": [
-        "New English translations of the entire corpus of the sagas of Icelanders and connected tales"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-868"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Complete sagas of Icelanders"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9903a6c7-a3e2-50ea-8998-66f7b979a041.json b/oaitestdata/clarin-oai_dc/SET_1/json/9903a6c7-a3e2-50ea-8998-66f7b979a041.json
deleted file mode 100644
index 21d33ec5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9903a6c7-a3e2-50ea-8998-66f7b979a041.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "between 512 KB and 1 MB "
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0060",
-    "MetadataAccess": [
-        "oai:ota:oucs:0060"
-    ],
-    "PublicationTimestamp": "1816-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1816"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Scott, Walter,  Sir,  1771-1832"
-    ],
-    "fulltext": "oai:ota:oucs:0060;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0060.xml; The antiquary  / compiled by Sidney Michaelson;Scott, Walter,  Sir,  1771-1832;1816;text_and_corpus_linguistics;Novels -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;between 512 KB and 1 MB ;Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9903a6c7-a3e2-50ea-8998-66f7b979a041",
-    "oai_identifier": [
-        "oai:ota:oucs:0060"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Novels -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        " The antiquary  / compiled by Sidney Michaelson"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0060.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/991c2bf6-a59b-5279-a104-eb7ada03c73c.json b/oaitestdata/clarin-oai_dc/SET_1/json/991c2bf6-a59b-5279-a104-eb7ada03c73c.json
deleted file mode 100644
index 77074e36..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/991c2bf6-a59b-5279-a104-eb7ada03c73c.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/339",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/339"
-    ],
-    "PID": "http://hdl.handle.net/11321/339",
-    "PublicationTimestamp": "2017-03-03T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "K\u0119dzia, Pawe\u0142",
-        "Ry\u015bnik, B\u0142a\u017cej",
-        "Koco\u0144, Jan",
-        "Marci\u0144czuk, Micha\u0142",
-        "Maciejewski, Henryk",
-        "Kali\u0144ski, Micha\u0142",
-        "Oleksy, Marcin",
-        "Piasecki, Maciej"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/339;2017-03-03T13:29:51Z;hdl_11321_3;hdl_11321_4;Keyword Extractor;Kali\u0144ski, Micha\u0142;Piasecki, Maciej;Oleksy, Marcin;Marci\u0144czuk, Micha\u0142;Koco\u0144, Jan;K\u0119dzia, Pawe\u0142;Ry\u015bnik, B\u0142a\u017cej;Maciejewski, Henryk;keywords;text analysis;textrank;Tool for extracting key phrases for text, using TextRank algorithm.;2017-03-03;toolService;http://hdl.handle.net/11321/339;pol;application/gzip;downloadable_files_count: 1;Wroc\u0142aw University of Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "991c2bf6-a59b-5279-a104-eb7ada03c73c",
-    "notes": [
-        "Tool for extracting key phrases for text, using TextRank algorithm."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/339"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "keywords"
-        },
-        {
-            "name": "text analysis"
-        },
-        {
-            "name": "textrank"
-        }
-    ],
-    "title": [
-        "Keyword Extractor"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9934ffda-8b83-5808-986d-6e410fa377f1.json b/oaitestdata/clarin-oai_dc/SET_1/json/9934ffda-8b83-5808-986d-6e410fa377f1.json
deleted file mode 100644
index 32100294..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9934ffda-8b83-5808-986d-6e410fa377f1.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "B"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1543",
-    "MetadataAccess": [
-        "oai:ota:oucs:1543"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Defoe, Daniel,  1661?-1731"
-    ],
-    "fulltext": "oai:ota:oucs:1543;2018-04-16T15:30:51Z;http://ota.ox.ac.uk/headers/1543.xml;Moll Flanders;Defoe, Daniel,  1661?-1731;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;B;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9934ffda-8b83-5808-986d-6e410fa377f1",
-    "oai_identifier": [
-        "oai:ota:oucs:1543"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Moll Flanders"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1543.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9956afd3-68b8-5714-ba40-1ddfda203834.json b/oaitestdata/clarin-oai_dc/SET_1/json/9956afd3-68b8-5714-ba40-1ddfda203834.json
deleted file mode 100644
index 7903ee59..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9956afd3-68b8-5714-ba40-1ddfda203834.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "NBG/DBNL/INL; Nicoline van der Sijs"
-    ],
-    "Contributor": [
-        "Agency, Dutch HLT"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-573",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-573"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-573",
-    "PublicationTimestamp": "2008-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2008"
-    ],
-    "Publisher": [
-        "NBG/DBNL/INL; Nicoline van der Sijs"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-573;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Delftse Bijbel 1477;Agency, Dutch HLT;Digitised version of the Delftse Bijbel 1477;2008;corpus;http://hdl.handle.net/11372/LRT-573;nld;downloadable_files_count: 0;Netherlands (the);NBG/DBNL/INL; Nicoline van der Sijs;http://tst.inl.nl/producten/DB1477",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9956afd3-68b8-5714-ba40-1ddfda203834",
-    "notes": [
-        "Digitised version of the Delftse Bijbel 1477"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-573"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Delftse Bijbel 1477"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9975bf84-0141-5dc4-bcb6-ee8695c82c92.json b/oaitestdata/clarin-oai_dc/SET_1/json/9975bf84-0141-5dc4-bcb6-ee8695c82c92.json
deleted file mode 100644
index 824c7998..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9975bf84-0141-5dc4-bcb6-ee8695c82c92.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3037",
-    "MetadataAccess": [
-        "oai:ota:oucs:3037"
-    ],
-    "PublicationTimestamp": "1897-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1897"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Conrad, Joseph, 1857-1924"
-    ],
-    "fulltext": "oai:ota:oucs:3037;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3037.xml;Nigger of the \u00e2\u0080\u0098Narcissus\u00e2\u0080\u0099;Conrad, Joseph, 1857-1924;not after: 1897;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9975bf84-0141-5dc4-bcb6-ee8695c82c92",
-    "oai_identifier": [
-        "oai:ota:oucs:3037"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Nigger of the \u00e2\u0080\u0098Narcissus\u00e2\u0080\u0099"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3037.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/99805ef1-bcc6-5be1-aa0b-44be5487d492.json b/oaitestdata/clarin-oai_dc/SET_1/json/99805ef1-bcc6-5be1-aa0b-44be5487d492.json
deleted file mode 100644
index fd4bb9fa..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/99805ef1-bcc6-5be1-aa0b-44be5487d492.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=ca81fa08d36211e2a2aa782bcb074135b21158a773424785864b1242809f912b",
-    "MetadataAccess": [
-        "ca81fa08d36211e2a2aa782bcb074135b21158a773424785864b1242809f912b"
-    ],
-    "PublicationTimestamp": "2013-06-12T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "ca81fa08d36211e2a2aa782bcb074135b21158a773424785864b1242809f912b;2018-11-15T16:40:13Z;corpus;corpus:text;CW Corpus;The Complex Word (CW) Corpus contains 731 sentences each with one annotated CW.  These simplifications were mined from Simple Wikipedia edit histories.  Each entry gives an example of a sentence requiring simplification by means of a single lexical edit.  This resource is primarily designed for the evaluation of CW identification systems.;2013-06-12",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "99805ef1-bcc6-5be1-aa0b-44be5487d492",
-    "notes": [
-        "The Complex Word (CW) Corpus contains 731 sentences each with one annotated CW.  These simplifications were mined from Simple Wikipedia edit histories.  Each entry gives an example of a sentence requiring simplification by means of a single lexical edit.  This resource is primarily designed for the evaluation of CW identification systems."
-    ],
-    "oai_identifier": [
-        "ca81fa08d36211e2a2aa782bcb074135b21158a773424785864b1242809f912b"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "CW Corpus"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/99904cbc-4567-5284-8e77-cdc0959e4eb3.json b/oaitestdata/clarin-oai_dc/SET_1/json/99904cbc-4567-5284-8e77-cdc0959e4eb3.json
deleted file mode 100644
index e2b2e4e1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/99904cbc-4567-5284-8e77-cdc0959e4eb3.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5432",
-    "MetadataAccess": [
-        "oai:ota:oucs:5432"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Collins, William, 1721-1759."
-    ],
-    "fulltext": "oai:ota:oucs:5432;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5432.xml;The poetical works: of Mr. William Collins. With memoirs of the author; and observations on his genius and writings. By J. Langhorne.;Collins, William, 1721-1759.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "99904cbc-4567-5284-8e77-cdc0959e4eb3",
-    "oai_identifier": [
-        "oai:ota:oucs:5432"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The poetical works: of Mr. William Collins. With memoirs of the author; and observations on his genius and writings. By J. Langhorne."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5432.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/999916fa-feea-55c2-a912-3cf359a5fc6a.json b/oaitestdata/clarin-oai_dc/SET_1/json/999916fa-feea-55c2-a912-3cf359a5fc6a.json
deleted file mode 100644
index b0ff2efe..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/999916fa-feea-55c2-a912-3cf359a5fc6a.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Marcina Horteryna"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229186",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229186"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D06-F",
-    "PublicationTimestamp": "1619-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1619"
-    ],
-    "Publisher": [
-        "Drukarnia Marcina Horteryna"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/229186",
-        "oai:jbc.bj.uj.edu.pl:publication:240826"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1601/1700"
-    ],
-    "TempCoverageBegin": 50506804799,
-    "TempCoverageEnd": 50506804799,
-    "TemporalCoverage": " point in time : 1601-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1601-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1601-07-01T11:59:59Z",
-    "author": [
-        "\u017b\u0119dzianowski, Andrzej (15..-1625)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229186;2019-03-01T12:58:36Z;Kometa Z Przestrogi Niebieskiey : W Roku od Narodzenia Bozego widziany, 1618, Miesiaca Listopada w Niedzwiadku Zodiacznym [...];\u017b\u0119dzianowski, Andrzej (15..-1625);starodruki 17\u00a0w.;Drukarnia Marcina Horteryna;1619;starodruk;application/xml;clarind-uds:poldilemma-229186;hdl:11858/00-246C-0000-0023-8D06-F;Biblioteka Jagiello\u0144ska, BJ St. Dr. 56556 I;pol;http://jbc.bj.uj.edu.pl/Content/229186;oai:jbc.bj.uj.edu.pl:publication:240826;1601/1700;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "999916fa-feea-55c2-a912-3cf359a5fc6a",
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229186"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Kometa Z Przestrogi Niebieskiey : W Roku od Narodzenia Bozego widziany, 1618, Miesiaca Listopada w Niedzwiadku Zodiacznym [...]"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/99a0081d-3c3e-54c1-b8d2-b7ed6c6d8049.json b/oaitestdata/clarin-oai_dc/SET_1/json/99a0081d-3c3e-54c1-b8d2-b7ed6c6d8049.json
deleted file mode 100644
index a3716349..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/99a0081d-3c3e-54c1-b8d2-b7ed6c6d8049.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3401",
-    "MetadataAccess": [
-        "oai:ota:oucs:3401"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Mason, William, 1725-1797."
-    ],
-    "fulltext": "oai:ota:oucs:3401;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3401.xml;Ode to Mr. Pinchbeck, upon his newly invented patent candle-snuffers: by Malcolm M'Greggor, ...;Mason, William, 1725-1797.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "99a0081d-3c3e-54c1-b8d2-b7ed6c6d8049",
-    "oai_identifier": [
-        "oai:ota:oucs:3401"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Ode to Mr. Pinchbeck, upon his newly invented patent candle-snuffers: by Malcolm M'Greggor, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3401.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/99af2c5a-e30f-5d7e-ac3d-da5307d9fa2d.json b/oaitestdata/clarin-oai_dc/SET_1/json/99af2c5a-e30f-5d7e-ac3d-da5307d9fa2d.json
deleted file mode 100644
index 336c272b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/99af2c5a-e30f-5d7e-ac3d-da5307d9fa2d.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Uniwersytet Warszawski"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 11",
-        "text/plain; charset=utf-8",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/456",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/456"
-    ],
-    "PID": "http://hdl.handle.net/11321/456",
-    "PublicationTimestamp": "2018-04-09T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Uniwersytet Warszawski"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Ochma\u0144ski, Miko\u0142aj"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/456;2018-04-11T08:26:28Z;hdl_11321_3;hdl_11321_4;Blogs_2018;Ochma\u0144ski, Miko\u0142aj;blog;books;blogosphere;social media;Teksty z blog\u00f3w ksi\u0105\u017ckowych;2018-04-09;corpus;http://hdl.handle.net/11321/456;pol;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;CC;text/plain; charset=utf-8;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;downloadable_files_count: 11;Uniwersytet Warszawski;https://mikochm.wordpress.com/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "99af2c5a-e30f-5d7e-ac3d-da5307d9fa2d",
-    "notes": [
-        "Teksty z blog\u00f3w ksi\u0105\u017ckowych"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/456"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "blog"
-        },
-        {
-            "name": "books"
-        },
-        {
-            "name": "blogosphere"
-        },
-        {
-            "name": "social media"
-        }
-    ],
-    "title": [
-        "Blogs_2018"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/99af61a9-6642-5aa9-ba62-09744a378c12.json b/oaitestdata/clarin-oai_dc/SET_1/json/99af61a9-6642-5aa9-ba62-09744a378c12.json
deleted file mode 100644
index 72927da7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/99af61a9-6642-5aa9-ba62-09744a378c12.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4874",
-    "MetadataAccess": [
-        "oai:ota:oucs:4874"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Brand, John, d. 1808."
-    ],
-    "fulltext": "oai:ota:oucs:4874;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4874.xml;Observations on some of the probable effects of Mr. Gilbert's bill; to which are added remarks deduced from Dr. Price's Account of the national debt. By the Reverend Mr. Brand, M.A;Brand, John, d. 1808.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "99af61a9-6642-5aa9-ba62-09744a378c12",
-    "oai_identifier": [
-        "oai:ota:oucs:4874"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Observations on some of the probable effects of Mr. Gilbert's bill; to which are added remarks deduced from Dr. Price's Account of the national debt. By the Reverend Mr. Brand, M.A"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4874.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/99b40c16-b075-52b5-99de-fb7cbb5568e3.json b/oaitestdata/clarin-oai_dc/SET_1/json/99b40c16-b075-52b5-99de-fb7cbb5568e3.json
deleted file mode 100644
index 3ef9e9b1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/99b40c16-b075-52b5-99de-fb7cbb5568e3.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "University of Tartu"
-    ],
-    "Contributor": [
-        "M\u00fc\u00fcrisep, Kaili"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Estonian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-313",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-313"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-313",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Tartu"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Estonia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-313;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Syntactic analyzer of Estonian;M\u00fc\u00fcrisep, Kaili;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-313;est;downloadable_files_count: 0;Estonia;University of Tartu;http://www.cs.ut.ee/~kaili/parser/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "99b40c16-b075-52b5-99de-fb7cbb5568e3",
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-313"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Syntactic analyzer of Estonian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/99c0d894-c92d-5e6d-8382-fbed7e64e0b3.json b/oaitestdata/clarin-oai_dc/SET_1/json/99c0d894-c92d-5e6d-8382-fbed7e64e0b3.json
deleted file mode 100644
index ebb0acd3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/99c0d894-c92d-5e6d-8382-fbed7e64e0b3.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Kuncewiczowa"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 7",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/82",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/82"
-    ],
-    "PID": "http://hdl.handle.net/11321/82",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Kuncewiczowa"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Kuncewiczowa, Kuncewiczowa"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/82;2015-05-19T13:38:55Z;hdl_11321_3;hdl_11321_4;MWE Kuncewiczowa;Kuncewiczowa, Kuncewiczowa;Kuncewiczowa;2015-04-08;corpus;http://hdl.handle.net/11321/82;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 7;Kuncewiczowa",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "99c0d894-c92d-5e6d-8382-fbed7e64e0b3",
-    "notes": [
-        "Kuncewiczowa"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/82"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Kuncewiczowa"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/99ca831c-09f6-596f-ac72-ef657ae11208.json b/oaitestdata/clarin-oai_dc/SET_1/json/99ca831c-09f6-596f-ac72-ef657ae11208.json
deleted file mode 100644
index 6cd82b81..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/99ca831c-09f6-596f-ac72-ef657ae11208.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5420",
-    "MetadataAccess": [
-        "oai:ota:oucs:5420"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Jephson, Robert, 1736-1803."
-    ],
-    "fulltext": "oai:ota:oucs:5420;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5420.xml;Considerations upon the augmentation of the army: Address'd to the publick.;Jephson, Robert, 1736-1803.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "99ca831c-09f6-596f-ac72-ef657ae11208",
-    "oai_identifier": [
-        "oai:ota:oucs:5420"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Considerations upon the augmentation of the army: Address'd to the publick."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5420.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/99e2876d-3674-5704-9d4d-457b9d11cdac.json b/oaitestdata/clarin-oai_dc/SET_1/json/99e2876d-3674-5704-9d4d-457b9d11cdac.json
deleted file mode 100644
index 13d50b53..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/99e2876d-3674-5704-9d4d-457b9d11cdac.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "between 1 and 2 MB"
-    ],
-    "Language": [
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0308",
-    "MetadataAccess": [
-        "oai:ota:oucs:0308"
-    ],
-    "PublicationYear": [
-        "380-389"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Local histories"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Ammianus Marcellinus"
-    ],
-    "fulltext": "oai:ota:oucs:0308;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0308.xml; Histories ;Ammianus Marcellinus;380-389;text_and_corpus_linguistics;Local histories -- Italy -- 4th century;lat;Oxford Text Archive, University of Oxford;between 1 and 2 MB;Text;Local histories;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "99e2876d-3674-5704-9d4d-457b9d11cdac",
-    "oai_identifier": [
-        "oai:ota:oucs:0308"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Local histories -- Italy -- th century"
-        }
-    ],
-    "title": [
-        " Histories "
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0308.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9a0117be-06f2-5841-8c9c-3a8c75a8b282.json b/oaitestdata/clarin-oai_dc/SET_1/json/9a0117be-06f2-5841-8c9c-3a8c75a8b282.json
deleted file mode 100644
index e93ab386..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9a0117be-06f2-5841-8c9c-3a8c75a8b282.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-90",
-    "MetadataAccess": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-90"
-    ],
-    "PID": "http://hdl.handle.net/20.500.11752/ILC-90",
-    "PublicationTimestamp": "2012-12-10T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/248064",
-        "http://www.lrec-conf.org/proceedings/lrec2012/summaries/390.html"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Rubino, Francesco",
-        "Quochi, Valeria",
-        "Caselli, Tommaso",
-        "Frontini, Francesca"
-    ],
-    "fulltext": "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-90;2018-09-28T07:47:48Z;hdl_000-c0-111_38;hdl_000-c0-111_49;SCF Extractor (language indipendent);Rubino, Francesco;Caselli, Tommaso;Frontini, Francesca;Quochi, Valeria;Subcategorisation frames extraction;Automatic lexical acquisition;CoNLL-X input format;The 'SCF Extractor (language independent)' is a service that performs inductive subcategorisation extraction from dependency parsed texts, formatted according to the CoNLL-X format. The SCF Extractor tool was developed at CNR-ILC and deployed as a soap web service within the EU-FP7-STREP PANACEA project (www.panacea-lr.eu). This version of the tool/service was not optimized for any language.; it requires 2 input data: 1) a dependency parsed text corpus the CONLL-X format; 2) a list of verb lemmas for which the subcategorization frames will be extracted.;2012-12-10;toolService;http://hdl.handle.net/20.500.11752/ILC-90;info:eu-repo/grantAgreement/EC/FP7/248064;http://www.lrec-conf.org/proceedings/lrec2012/summaries/390.html;downloadable_files_count: 0;Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR);http://www.panacea-lr.eu/system/deliverables/PANACEA_D6.2.pdf",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9a0117be-06f2-5841-8c9c-3a8c75a8b282",
-    "notes": [
-        "The 'SCF Extractor (language independent)' is a service that performs inductive subcategorisation extraction from dependency parsed texts, formatted according to the CoNLL-X format. The SCF Extractor tool was developed at CNR-ILC and deployed as a soap web service within the EU-FP7-STREP PANACEA project (www.panacea-lr.eu). This version of the tool/service was not optimized for any language.; it requires 2 input data: 1) a dependency parsed text corpus the CONLL-X format; 2) a list of verb lemmas for which the subcategorization frames will be extracted."
-    ],
-    "oai_identifier": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-90"
-    ],
-    "oai_set": [
-        "hdl_000-c0-111_38",
-        "hdl_000-c0-111_49"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Subcategorisation frames extraction"
-        },
-        {
-            "name": "Automatic lexical acquisition"
-        },
-        {
-            "name": "CoNLL-X input format"
-        }
-    ],
-    "title": [
-        "SCF Extractor (language indipendent)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9a1152c8-14a8-555d-9194-0c62dda30f32.json b/oaitestdata/clarin-oai_dc/SET_1/json/9a1152c8-14a8-555d-9194-0c62dda30f32.json
deleted file mode 100644
index ab61debe..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9a1152c8-14a8-555d-9194-0c62dda30f32.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3391",
-    "MetadataAccess": [
-        "oai:ota:oucs:3391"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Carey, George Saville, 1743-1807."
-    ],
-    "fulltext": "oai:ota:oucs:3391;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3391.xml;The noble pedlar: a burletta. As performed at Marybone-Gardens. Set to music by Mr. Barthelemon.;Carey, George Saville, 1743-1807.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9a1152c8-14a8-555d-9194-0c62dda30f32",
-    "oai_identifier": [
-        "oai:ota:oucs:3391"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The noble pedlar: a burletta. As performed at Marybone-Gardens. Set to music by Mr. Barthelemon."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3391.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9a142074-893e-56b7-abc3-62bfad926253.json b/oaitestdata/clarin-oai_dc/SET_1/json/9a142074-893e-56b7-abc3-62bfad926253.json
deleted file mode 100644
index eb40198e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9a142074-893e-56b7-abc3-62bfad926253.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 1740 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1845",
-    "MetadataAccess": [
-        "oai:ota:oucs:1845"
-    ],
-    "PublicationTimestamp": "1864-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1864"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Trollope, Anthony, 1815-1882"
-    ],
-    "fulltext": "oai:ota:oucs:1845;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/1845.xml;Can you forgive her? / by Anthony Trollope;Trollope, Anthony, 1815-1882;1864;text_and_corpus_linguistics;Novels -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 1740 KB);Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9a142074-893e-56b7-abc3-62bfad926253",
-    "oai_identifier": [
-        "oai:ota:oucs:1845"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Novels -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Can you forgive her? / by Anthony Trollope"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1845.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9a2acb18-5816-5823-b828-4d8ee2b9bcda.json b/oaitestdata/clarin-oai_dc/SET_1/json/9a2acb18-5816-5823-b828-4d8ee2b9bcda.json
deleted file mode 100644
index 4a16d7ea..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9a2acb18-5816-5823-b828-4d8ee2b9bcda.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-652",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-652"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-652",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Code of conduct"
-    ],
-    "SpatialCoverage": [
-        "Australia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-652;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Iwaidja corpus;Documentation of the Iwaidja project (DoBeS project);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-652;Code of conduct;downloadable_files_count: 0;Australia;http://corpus1.mpi.nl/ds/imdi_browser/?openpath=MPI79625%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9a2acb18-5816-5823-b828-4d8ee2b9bcda",
-    "notes": [
-        "Documentation of the Iwaidja project (DoBeS project)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-652"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Iwaidja corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9a3b7221-1585-5360-937f-432599ddb499.json b/oaitestdata/clarin-oai_dc/SET_1/json/9a3b7221-1585-5360-937f-432599ddb499.json
deleted file mode 100644
index f5840909..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9a3b7221-1585-5360-937f-432599ddb499.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Department of Informatics, Human Language Technology Group, University of Szeged"
-    ],
-    "Contributor": [
-        "Vincze, Veronika"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/xml"
-    ],
-    "Language": [
-        "Hungarian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-201",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-201"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-201",
-    "PublicationTimestamp": "2004-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2004"
-    ],
-    "Publisher": [
-        "Department of Informatics, Human Language Technology Group, University of Szeged"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Hungary"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-201;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Szeged Treebank 2.0;Vincze, Veronika;82,000 sentences with full syntactic annotation.;2004;corpus;http://hdl.handle.net/11372/LRT-201;hun;application/xml;downloadable_files_count: 0;Hungary;Department of Informatics, Human Language Technology Group, University of Szeged;http://www.inf.u-szeged.hu/projectdirs/hlt/index_en.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9a3b7221-1585-5360-937f-432599ddb499",
-    "notes": [
-        "82,000 sentences with full syntactic annotation."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-201"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Szeged Treebank 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9a4f97a1-f2e7-57b1-b903-0534047077a7.json b/oaitestdata/clarin-oai_dc/SET_1/json/9a4f97a1-f2e7-57b1-b903-0534047077a7.json
deleted file mode 100644
index e0cb935f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9a4f97a1-f2e7-57b1-b903-0534047077a7.json
+++ /dev/null
@@ -1,94 +0,0 @@
-{
-    "Contact": [
-        "Regional Linguistic Data Initiative Centre ReLDI"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 3",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Serbian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1200",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1200"
-    ],
-    "PID": "http://hdl.handle.net/11356/1200",
-    "PublicationTimestamp": "2018-08-20T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Regional Linguistic Data Initiative Centre ReLDI"
-    ],
-    "RelatedIdentifier": [
-        "http://www.aclweb.org/anthology/W17-1407"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by-sa/4.0/"
-    ],
-    "author": [
-        "Erjavec, Toma\u017e",
-        "Samard\u017ei\u0107, Tanja",
-        "Batanovi\u0107, Vuk",
-        "Ljube\u0161i\u0107, Nikola"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1200;2018-10-24T20:57:49Z;hdl_11356_1023;hdl_11356_1024;Training corpus SETimes.SR 1.0;Batanovi\u0107, Vuk;Ljube\u0161i\u0107, Nikola;Samard\u017ei\u0107, Tanja;Erjavec, Toma\u017e;tagging;dependency treebank;parsing;named entities;tokenisation;manual annotation;TEI;The SETimes.SR training corpus contains 86 726 tokens manually annotated on the levels of tokenisation, sentence segmentation, morphosyntactic tagging, lemmatisation, syntactic dependencies, and named entities.\r\n\r\nThe annotations (and other aspects) of the corpus are documented in the teiHeader and back element of the TEI encoded corpus. In short, they follow (1) the MULTEXT-East V5 morphosyntactic specifications, http://nl.ijs.si/ME/V5/msd/, (2) the UDv2 Guidelines, http://universaldependencies.org/guidelines.html, and (3) the Janes annotation guidelines for named entities, http://nl.ijs.si/janes/wp-content/uploads/2017/09/SlovenianNER-eng-v1.1.pdf.;2018-08-20;corpus;http://hdl.handle.net/11356/1200;srp;http://www.aclweb.org/anthology/W17-1407;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);PUB;https://creativecommons.org/licenses/by-sa/4.0/;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 3;Regional Linguistic Data Initiative Centre ReLDI;https://github.com/vukbatanovic/SETimes.SR",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9a4f97a1-f2e7-57b1-b903-0534047077a7",
-    "notes": [
-        "The SETimes.SR training corpus contains 86 726 tokens manually annotated on the levels of tokenisation, sentence segmentation, morphosyntactic tagging, lemmatisation, syntactic dependencies, and named entities.\r\n\r\nThe annotations (and other aspects) of the corpus are documented in the teiHeader and back element of the TEI encoded corpus. In short, they follow (1) the MULTEXT-East V5 morphosyntactic specifications, http://nl.ijs.si/ME/V5/msd/, (2) the UDv2 Guidelines, http://universaldependencies.org/guidelines.html, and (3) the Janes annotation guidelines for named entities, http://nl.ijs.si/janes/wp-content/uploads/2017/09/SlovenianNER-eng-v1.1.pdf."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1200"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "dependency treebank"
-        },
-        {
-            "name": "parsing"
-        },
-        {
-            "name": "named entities"
-        },
-        {
-            "name": "tokenisation"
-        },
-        {
-            "name": "manual annotation"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "Training corpus SETimes.SR 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9a63fbfc-8ad8-5e6e-8a1f-0075e169f446.json b/oaitestdata/clarin-oai_dc/SET_1/json/9a63fbfc-8ad8-5e6e-8a1f-0075e169f446.json
deleted file mode 100644
index ff588e42..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9a63fbfc-8ad8-5e6e-8a1f-0075e169f446.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Royster, Paul"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 264 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1652",
-    "MetadataAccess": [
-        "oai:ota:oucs:1652"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Whitman, Walt, 1819-1892"
-    ],
-    "fulltext": "oai:ota:oucs:1652;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1652.xml;Leaves of grass : [1855] / Walt Whitman;Whitman, Walt, 1819-1892;text_and_corpus_linguistics;American poetry -- 19th century;Oxford Text Archive, University of Oxford;Royster, Paul;text/sgml;(1 file : ca. 264 KB);Text;Poems;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9a63fbfc-8ad8-5e6e-8a1f-0075e169f446",
-    "oai_identifier": [
-        "oai:ota:oucs:1652"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "American poetry -- th century"
-        }
-    ],
-    "title": [
-        "Leaves of grass : [1855] / Walt Whitman"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1652.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9a95ea14-b48c-56e8-b913-9b419d3adfef.json b/oaitestdata/clarin-oai_dc/SET_1/json/9a95ea14-b48c-56e8-b913-9b419d3adfef.json
deleted file mode 100644
index eb1f9fe8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9a95ea14-b48c-56e8-b913-9b419d3adfef.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-922",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-922"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-922",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-922;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Lydian;ca. 2.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-922;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#lyd",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9a95ea14-b48c-56e8-b913-9b419d3adfef",
-    "notes": [
-        "ca. 2.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-922"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Lydian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9ab91622-7a6d-5e29-81ee-ce71c9be8570.json b/oaitestdata/clarin-oai_dc/SET_1/json/9ab91622-7a6d-5e29-81ee-ce71c9be8570.json
deleted file mode 100644
index 01fb59f9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9ab91622-7a6d-5e29-81ee-ce71c9be8570.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "text/xml",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Norwegian Bokm\u00e5l"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/89",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/89"
-    ],
-    "PID": "http://hdl.handle.net/11509/89",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "CC",
-        "http://creativecommons.org/licenses/by/3.0/"
-    ],
-    "author": [
-        "Giellatekno - Saami Language Technology, UiT The Arctic University of Norway"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/89;2016-09-06T12:34:06Z;hdl_11509_1;hdl_11509_2;Kven-Norwegian Bokm\u00e5l dictionary;Giellatekno - Saami Language Technology, UiT The Arctic University of Norway;Bilingual Lexicon;Dictionary;Machine-readable;The Kven-Norwegian Bokm\u00e5l dictionary is the work done by Giellatekno, UiT The Arctic University of Norway, Kainun institutti, as well as by members of the language communities. In particular, the following colleagues have contributed to the creation of the ressource: Terje Aronsen, Verena Schall, Eira S\u00f6derholm, Trond Trosterud, Tove Reibo, and Ciprian Gerstenberger. The dictionary contains 8468 entries in Giellatekno's dictionary xml format. In spite of the extensive quality control, it may contain entries with objectionable translations. If you find any errors or want to add more words, download the file, edit it, and send it back to giellatekno@uit.no.\r\nPlease note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata).;2015;lexicalConceptualResource;http://hdl.handle.net/11509/89;fkv;nob;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);CC;http://creativecommons.org/licenses/by/3.0/;application/zip;text/plain; charset=utf-8;text/xml;downloadable_files_count: 1;Giellatekno - Saami Language Technology;http://giellatekno.uit.no/index.eng.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9ab91622-7a6d-5e29-81ee-ce71c9be8570",
-    "notes": [
-        "The Kven-Norwegian Bokm\u00e5l dictionary is the work done by Giellatekno, UiT The Arctic University of Norway, Kainun institutti, as well as by members of the language communities. In particular, the following colleagues have contributed to the creation of the ressource: Terje Aronsen, Verena Schall, Eira S\u00f6derholm, Trond Trosterud, Tove Reibo, and Ciprian Gerstenberger. The dictionary contains 8468 entries in Giellatekno's dictionary xml format. In spite of the extensive quality control, it may contain entries with objectionable translations. If you find any errors or want to add more words, download the file, edit it, and send it back to giellatekno@uit.no.\r\nPlease note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata)."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/89"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Bilingual Lexicon"
-        },
-        {
-            "name": "Dictionary"
-        },
-        {
-            "name": "Machine-readable"
-        }
-    ],
-    "title": [
-        "Kven-Norwegian Bokm\u00e5l dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9abeda35-90b3-597c-ad27-7f0106fb0a4f.json b/oaitestdata/clarin-oai_dc/SET_1/json/9abeda35-90b3-597c-ad27-7f0106fb0a4f.json
deleted file mode 100644
index 6b240ead..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9abeda35-90b3-597c-ad27-7f0106fb0a4f.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "A"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1486",
-    "MetadataAccess": [
-        "oai:ota:oucs:1486"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Byrne, John"
-    ],
-    "fulltext": "oai:ota:oucs:1486;2018-04-16T15:30:51Z;http://ota.ox.ac.uk/headers/1486.xml;Tutti Frutti;Byrne, John;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;A;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9abeda35-90b3-597c-ad27-7f0106fb0a4f",
-    "oai_identifier": [
-        "oai:ota:oucs:1486"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Tutti Frutti"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1486.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9adcea5a-a357-56e3-8703-f2d2a7a90dc1.json b/oaitestdata/clarin-oai_dc/SET_1/json/9adcea5a-a357-56e3-8703-f2d2a7a90dc1.json
deleted file mode 100644
index 8a7a1cd0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9adcea5a-a357-56e3-8703-f2d2a7a90dc1.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=a61934366bfe11e2a2aa782bcb07413527499a2c68084f5b8ed8c0c5f849eef3",
-    "MetadataAccess": [
-        "a61934366bfe11e2a2aa782bcb07413527499a2c68084f5b8ed8c0c5f849eef3"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "a61934366bfe11e2a2aa782bcb07413527499a2c68084f5b8ed8c0c5f849eef3;2018-11-15T16:40:08Z;toolService;toolService:platform;U-Compare Part-of-Speech Tagging service;Web service created by exporting UIMA-based workflow from the U-Compare text mining system.\nFunctionality: Identifies tokens in plain text and assigns parts-of-speech\nTools in workflow: MLRS POS Tagger web service (University of Malta)\nNOTE: The licence provided covers the web service only. Tools used to create the workflow may have their own licences\n;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9adcea5a-a357-56e3-8703-f2d2a7a90dc1",
-    "notes": [
-        "Web service created by exporting UIMA-based workflow from the U-Compare text mining system.\nFunctionality: Identifies tokens in plain text and assigns parts-of-speech\nTools in workflow: MLRS POS Tagger web service (University of Malta)\nNOTE: The licence provided covers the web service only. Tools used to create the workflow may have their own licences\n"
-    ],
-    "oai_identifier": [
-        "a61934366bfe11e2a2aa782bcb07413527499a2c68084f5b8ed8c0c5f849eef3"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:platform"
-    ],
-    "state": "active",
-    "title": [
-        "U-Compare Part-of-Speech Tagging service"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9af0ef4a-8798-526d-a927-92993b4a1521.json b/oaitestdata/clarin-oai_dc/SET_1/json/9af0ef4a-8798-526d-a927-92993b4a1521.json
deleted file mode 100644
index ac7d83ac..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9af0ef4a-8798-526d-a927-92993b4a1521.json
+++ /dev/null
@@ -1,142 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Afrikaans",
-        "Arabic",
-        "Breton",
-        "Bulgarian",
-        "Catalan",
-        "Czech",
-        "Church Slavic",
-        "Danish",
-        "German",
-        "Modern Greek (1453-)",
-        "English",
-        "Estonian",
-        "Basque",
-        "Faroese",
-        "Persian",
-        "Finnish",
-        "French",
-        "Old French (842-ca. 1400)",
-        "Irish",
-        "Galician",
-        "Gothic",
-        "Ancient Greek (to 1453)",
-        "Hebrew",
-        "Hindi",
-        "Croatian",
-        "Upper Sorbian",
-        "Hungarian",
-        "Armenian",
-        "Indonesian",
-        "Italian",
-        "Japanese",
-        "Kazakh",
-        "Korean",
-        "Latin",
-        "Latvian",
-        "Dutch",
-        "Norwegian",
-        "Polish",
-        "Portuguese",
-        "Romanian",
-        "Russian",
-        "Slovak",
-        "Slovenian",
-        "Northern Sami",
-        "Spanish",
-        "Serbian",
-        "Swedish",
-        "Thai",
-        "Turkish",
-        "Uighur",
-        "Ukrainian",
-        "Urdu",
-        "Vietnamese",
-        "Chinese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2899",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2899"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2899",
-    "PublicationTimestamp": "2018-11-28T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Licence Universal Dependencies v2.2",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-2.2",
-        "PUB"
-    ],
-    "author": [
-        "Straka, Milan",
-        "Zeman, Daniel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2899;2018-11-28T13:44:33Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;CoNLL 2017 and 2018 Shared Task Blind and Preprocessed Test Data;Zeman, Daniel;Straka, Milan;tokenization;word segmentation;morphology;tagging;syntax;parsing;universal dependencies;CoNLL 2017 and 2018 shared tasks:\r\nMultilingual Parsing from Raw Text to Universal Dependencies\r\n\r\nThis package contains the test data in the form in which they ware presented\r\nto the participating systems: raw text files and files preprocessed by UDPipe.\r\nThe metadata.json files contain lists of files to process and to output;\r\nREADME files in the respective folders describe the syntax of metadata.json.\r\n\r\nFor full training, development and gold standard test data, see\r\nUniversal Dependencies 2.0 (CoNLL 2017)\r\nUniversal Dependencies 2.2 (CoNLL 2018)\r\nSee the download links at http://universaldependencies.org/.\r\n\r\nFor more information on the shared tasks, see\r\nhttp://universaldependencies.org/conll17/\r\nhttp://universaldependencies.org/conll18/\r\n\r\nContents:\r\n\r\nconll17-ud-test-2017-05-09 ... CoNLL 2017 test data\r\nconll18-ud-test-2018-05-06 ... CoNLL 2018 test data\r\nconll18-ud-test-2018-05-06-for-conll17 ... CoNLL 2018 test data with metadata\r\n    and filenames modified so that it is digestible by the 2017 systems.;2018-11-28;corpus;http://hdl.handle.net/11234/1-2899;afr;ara;bre;bul;bxr;cat;ces;chu;dan;deu;ell;eng;est;eus;fao;fas;fin;fra;fro;gle;glg;got;grc;heb;hin;hrv;hsb;hun;hye;ind;ita;jpn;kaz;kmr;kor;lat;lav;nld;nor;pcm;pol;por;ron;rus;slk;slv;sme;spa;srp;swe;tha;tur;uig;ukr;urd;vie;zho;Licence Universal Dependencies v2.2;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-2.2;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://universaldependencies.org/conll18/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9af0ef4a-8798-526d-a927-92993b4a1521",
-    "notes": [
-        "CoNLL 2017 and 2018 shared tasks:\r\nMultilingual Parsing from Raw Text to Universal Dependencies\r\n\r\nThis package contains the test data in the form in which they ware presented\r\nto the participating systems: raw text files and files preprocessed by UDPipe.\r\nThe metadata.json files contain lists of files to process and to output;\r\nREADME files in the respective folders describe the syntax of metadata.json.\r\n\r\nFor full training, development and gold standard test data, see\r\nUniversal Dependencies 2.0 (CoNLL 2017)\r\nUniversal Dependencies 2.2 (CoNLL 2018)\r\nSee the download links at http://universaldependencies.org/.\r\n\r\nFor more information on the shared tasks, see\r\nhttp://universaldependencies.org/conll17/\r\nhttp://universaldependencies.org/conll18/\r\n\r\nContents:\r\n\r\nconll17-ud-test-2017-05-09 ... CoNLL 2017 test data\r\nconll18-ud-test-2018-05-06 ... CoNLL 2018 test data\r\nconll18-ud-test-2018-05-06-for-conll17 ... CoNLL 2018 test data with metadata\r\n    and filenames modified so that it is digestible by the 2017 systems."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2899"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "tokenization"
-        },
-        {
-            "name": "word segmentation"
-        },
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "syntax"
-        },
-        {
-            "name": "parsing"
-        },
-        {
-            "name": "universal dependencies"
-        }
-    ],
-    "title": [
-        "CoNLL 2017 and 2018 Shared Task Blind and Preprocessed Test Data"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9b036ee4-ae73-55f1-9079-db870e319f70.json b/oaitestdata/clarin-oai_dc/SET_1/json/9b036ee4-ae73-55f1-9079-db870e319f70.json
deleted file mode 100644
index 0971c973..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9b036ee4-ae73-55f1-9079-db870e319f70.json
+++ /dev/null
@@ -1,91 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 4",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2514",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2514"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2514",
-    "PublicationTimestamp": "2017-11-13T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-1456"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU General Public Licence, version 3",
-        "http://opensource.org/licenses/GPL-3.0",
-        "PUB"
-    ],
-    "author": [
-        "Rosa, Rudolf"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2514;2018-09-21T08:36:37Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Terminal-based CoNLL-file viewer, v2;Rosa, Rudolf;conll;terminal;console;text-based;file-viewer;conllu;universal dependencies;A simple way of browsing CoNLL format files in your terminal. Fast and text-based.\r\n\r\nTo open a CoNLL file, simply run: ./view_conll sample.conll\r\n\r\nThe output is piped through less, so you can use less commands to navigate the\r\nfile; by default the less searches for sentence beginnings, so you can use \"n\"\r\nto go to next sentence and \"N\" to go to previous sentence. Close by \"q\". Trees\r\nwith a high number of non-projective edges may be difficult to read, as I have\r\nnot found a good way of displaying them intelligibly.\r\n\r\nIf you are on Windows and don't have less (but have Python), run like this: python view_conll.py sample.conll\r\n\r\nFor complete instructions, see the README file.\r\n\r\nYou need Python 2 to run the viewer.;2017-11-13;toolService;http://hdl.handle.net/11234/1-2514;eng;http://hdl.handle.net/11234/1-1456;GNU General Public Licence, version 3;http://opensource.org/licenses/GPL-3.0;PUB;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 4;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9b036ee4-ae73-55f1-9079-db870e319f70",
-    "notes": [
-        "A simple way of browsing CoNLL format files in your terminal. Fast and text-based.\r\n\r\nTo open a CoNLL file, simply run: ./view_conll sample.conll\r\n\r\nThe output is piped through less, so you can use less commands to navigate the\r\nfile; by default the less searches for sentence beginnings, so you can use \"n\"\r\nto go to next sentence and \"N\" to go to previous sentence. Close by \"q\". Trees\r\nwith a high number of non-projective edges may be difficult to read, as I have\r\nnot found a good way of displaying them intelligibly.\r\n\r\nIf you are on Windows and don't have less (but have Python), run like this: python view_conll.py sample.conll\r\n\r\nFor complete instructions, see the README file.\r\n\r\nYou need Python 2 to run the viewer."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2514"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "conll"
-        },
-        {
-            "name": "terminal"
-        },
-        {
-            "name": "console"
-        },
-        {
-            "name": "text-based"
-        },
-        {
-            "name": "file-viewer"
-        },
-        {
-            "name": "conllu"
-        },
-        {
-            "name": "universal dependencies"
-        }
-    ],
-    "title": [
-        "Terminal-based CoNLL-file viewer, v2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9b1ad8f5-6821-5cc5-a505-f1abe6a2cd21.json b/oaitestdata/clarin-oai_dc/SET_1/json/9b1ad8f5-6821-5cc5-a505-f1abe6a2cd21.json
deleted file mode 100644
index 089b7139..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9b1ad8f5-6821-5cc5-a505-f1abe6a2cd21.json
+++ /dev/null
@@ -1,49 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5157",
-    "MetadataAccess": [
-        "oai:ota:oucs:5157"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:5157;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5157.xml;A collection of poems in six volumes. By several hands: [pt.6];text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9b1ad8f5-6821-5cc5-a505-f1abe6a2cd21",
-    "oai_identifier": [
-        "oai:ota:oucs:5157"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A collection of poems in six volumes. By several hands: [pt.6]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5157.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9b1f61d7-c2ee-5fc5-a2c7-a55e2c76ebba.json b/oaitestdata/clarin-oai_dc/SET_1/json/9b1f61d7-c2ee-5fc5-a2c7-a55e2c76ebba.json
deleted file mode 100644
index b16e2e3b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9b1f61d7-c2ee-5fc5-a2c7-a55e2c76ebba.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4359",
-    "MetadataAccess": [
-        "oai:ota:oucs:4359"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Richardson, Samuel, 1689-1761."
-    ],
-    "fulltext": "oai:ota:oucs:4359;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4359.xml;Clarissa: Or, the history of a young lady: comprehending the most important concerns of private life. ... Published by the editor of Pamela. ... [pt.2];Richardson, Samuel, 1689-1761.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9b1f61d7-c2ee-5fc5-a2c7-a55e2c76ebba",
-    "oai_identifier": [
-        "oai:ota:oucs:4359"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Clarissa: Or, the history of a young lady: comprehending the most important concerns of private life. ... Published by the editor of Pamela. ... [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4359.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9b372e78-db5b-51de-9a00-af8cfe6e9ec9.json b/oaitestdata/clarin-oai_dc/SET_1/json/9b372e78-db5b-51de-9a00-af8cfe6e9ec9.json
deleted file mode 100644
index 10ce2686..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9b372e78-db5b-51de-9a00-af8cfe6e9ec9.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Chinese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1034",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1034"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1034",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1034;2016-04-06T16:39:56Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;L1 Acquisition Chen Jidong;Language Acquisition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1034;zho;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI11699%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9b372e78-db5b-51de-9a00-af8cfe6e9ec9",
-    "notes": [
-        "Language Acquisition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1034"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "L1 Acquisition Chen Jidong"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9b3770b9-a84e-5a26-ad1d-2cfe42625ac3.json b/oaitestdata/clarin-oai_dc/SET_1/json/9b3770b9-a84e-5a26-ad1d-2cfe42625ac3.json
deleted file mode 100644
index f9007068..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9b3770b9-a84e-5a26-ad1d-2cfe42625ac3.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Arts and Humanities Research Board (AHRB)",
-        "Simmons, R. C. (Richard C.), 1937-",
-        "Bibliographical Society (Great Britain)",
-        "Simmons, Richard C."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(65 files : total of ca. 1.18 MB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2418",
-    "MetadataAccess": [
-        "oai:ota:oucs:2418"
-    ],
-    "PublicationTimestamp": "2000-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dicey, Cluer",
-        "Marshall, Richard, printer"
-    ],
-    "fulltext": "oai:ota:oucs:2418;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/2418.xml;The Dicey and Marshall catalogue / edited by R. C. Simmons;Dicey, Cluer;Marshall, Richard, printer;2000-11;text_and_corpus_linguistics;Ephemera -- Great Britain -- 18th century;Catalogues -- Great Britain -- 18th century;Sales catalogues -- Great Britain -- 18th century;Publishers' catalogues -- Great Britain -- 18th century;Advertisements -- Great Britain -- 18th century;eng;This catalogue of 1764 was probably larger than any catalogue categorising and listing cheap maps, images and texts that had up to then appeared in the British Isles. It is an important source for the study of the lower end of the eighteenth-century book and publishing trade ;Oxford Text Archive, University of Oxford;Simmons, R. C. (Richard C.), 1937-;Arts and Humanities Research Board (AHRB);Bibliographical Society (Great Britain);Simmons, Richard C.;(65 files : total of ca. 1.18 MB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9b3770b9-a84e-5a26-ad1d-2cfe42625ac3",
-    "notes": [
-        "This catalogue of 1764 was probably larger than any catalogue categorising and listing cheap maps, images and texts that had up to then appeared in the British Isles. It is an important source for the study of the lower end of the eighteenth-century book and publishing trade "
-    ],
-    "oai_identifier": [
-        "oai:ota:oucs:2418"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Ephemera -- Great Britain -- th century"
-        },
-        {
-            "name": "Catalogues -- Great Britain -- th century"
-        },
-        {
-            "name": "Sales catalogues -- Great Britain -- th century"
-        },
-        {
-            "name": "Publishers catalogues -- Great Britain -- th century"
-        },
-        {
-            "name": "Advertisements -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "The Dicey and Marshall catalogue / edited by R. C. Simmons"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2418.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9b380498-9b36-53d8-a06b-59ad0bc882cb.json b/oaitestdata/clarin-oai_dc/SET_1/json/9b380498-9b36-53d8-a06b-59ad0bc882cb.json
deleted file mode 100644
index db7a302e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9b380498-9b36-53d8-a06b-59ad0bc882cb.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-937",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-937"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-937",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-937;2016-04-06T16:39:56Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Gothic;ca. 80.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-937;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#got",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9b380498-9b36-53d8-a06b-59ad0bc882cb",
-    "notes": [
-        "ca. 80.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-937"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Gothic"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9b3e2078-d230-5673-a7d4-08def8fe8ad4.json b/oaitestdata/clarin-oai_dc/SET_1/json/9b3e2078-d230-5673-a7d4-08def8fe8ad4.json
deleted file mode 100644
index e7e76fc6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9b3e2078-d230-5673-a7d4-08def8fe8ad4.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Kokkinakis, Dimitrios"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-537",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-537"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-537",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "SpatialCoverage": [
-        "Sweden"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-537;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Swedish NE annotator;Kokkinakis, Dimitrios;Swedish Named Entity annotator;2014-07-30;languageDescription;http://hdl.handle.net/11372/LRT-537;swe;downloadable_files_count: 0;Sweden;http://g3.spraakdata.gu.se/nn/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9b3e2078-d230-5673-a7d4-08def8fe8ad4",
-    "notes": [
-        "Swedish Named Entity annotator"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-537"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Swedish NE annotator"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9b61c1e4-0f36-510c-900c-ef5c0bf5ecc2.json b/oaitestdata/clarin-oai_dc/SET_1/json/9b61c1e4-0f36-510c-900c-ef5c0bf5ecc2.json
deleted file mode 100644
index 328276d6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9b61c1e4-0f36-510c-900c-ef5c0bf5ecc2.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Estonian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-196",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-196"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-196",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Estonia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-196;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Sophie Parallel Treebank;200 sentences, TIGER-XML;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-196;est;downloadable_files_count: 0;Estonia;http://www.hf.uio.no/iln/om/organisasjon/tekstlab/prosjekter/arkiv/sofie.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9b61c1e4-0f36-510c-900c-ef5c0bf5ecc2",
-    "notes": [
-        "200 sentences, TIGER-XML"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-196"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Sophie Parallel Treebank"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9b695783-f017-55e5-a719-62ace19d8d1d.json b/oaitestdata/clarin-oai_dc/SET_1/json/9b695783-f017-55e5-a719-62ace19d8d1d.json
deleted file mode 100644
index 5270b2de..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9b695783-f017-55e5-a719-62ace19d8d1d.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "The Research Institute for the Languages of Finland"
-    ],
-    "Contributor": [
-        "Suutari, Toni"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Finnish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-764",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-764"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-764",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "The Research Institute for the Languages of Finland"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Finland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-764;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Audio Recordings Archive;Suutari, Toni;The Audio Recordings Archive (Suomen kielen nauhoitearkisto) holds over 23,000 hours of recordings collected since 1959, providing authentic samples of Finnish dialects, languages related to Finnish, and other world languages. The collection additionally includes samples of Finnish dialects spoken in Sweden, Norway, Ingria, the United States and Australia. Digitisation of the audio bank was undertaken in 1999. Over half of its content has been digitised, totalling about 13,000 hours of recordings.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-764;fin;downloadable_files_count: 0;Finland;The Research Institute for the Languages of Finland;http://kaino.kotus.fi/naark/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9b695783-f017-55e5-a719-62ace19d8d1d",
-    "notes": [
-        "The Audio Recordings Archive (Suomen kielen nauhoitearkisto) holds over 23,000 hours of recordings collected since 1959, providing authentic samples of Finnish dialects, languages related to Finnish, and other world languages. The collection additionally includes samples of Finnish dialects spoken in Sweden, Norway, Ingria, the United States and Australia. Digitisation of the audio bank was undertaken in 1999. Over half of its content has been digitised, totalling about 13,000 hours of recordings."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-764"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Audio Recordings Archive"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9b94eb62-d26d-5d68-9f7e-f5434cae2630.json b/oaitestdata/clarin-oai_dc/SET_1/json/9b94eb62-d26d-5d68-9f7e-f5434cae2630.json
deleted file mode 100644
index 9d28d0c5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9b94eb62-d26d-5d68-9f7e-f5434cae2630.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4439",
-    "MetadataAccess": [
-        "oai:ota:oucs:4439"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Oldys, William, 1696-1761."
-    ],
-    "fulltext": "oai:ota:oucs:4439;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4439.xml;The life of Dr. George Abbot, Lord Archbishop of Canterbury, reprinted with some additions and corrections from the Biographia Britannica; with his character, ... a description of the hospital, which he erected and endowed ... To which are added the lives of his two brothers, Dr. Robert Abbot, ... and Sir Morris Abbot,;Oldys, William, 1696-1761.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9b94eb62-d26d-5d68-9f7e-f5434cae2630",
-    "oai_identifier": [
-        "oai:ota:oucs:4439"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The life of Dr. George Abbot, Lord Archbishop of Canterbury, reprinted with some additions and corrections from the Biographia Britannica; with his character, ... a description of the hospital, which he erected and endowed ... To which are added the lives of his two brothers, Dr. Robert Abbot, ... and Sir Morris Abbot,"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4439.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9b9ca160-3816-5240-9722-11a5092cc206.json b/oaitestdata/clarin-oai_dc/SET_1/json/9b9ca160-3816-5240-9722-11a5092cc206.json
deleted file mode 100644
index 62d9a67e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9b9ca160-3816-5240-9722-11a5092cc206.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Dutch",
-        "German",
-        "English",
-        "French"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1051",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1051"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1051",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1051;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Multilingualism Marianne Gullberg & Peter Indefrey;Language Acquisition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1051;nld;deu;eng;fra;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI74870%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9b9ca160-3816-5240-9722-11a5092cc206",
-    "notes": [
-        "Language Acquisition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1051"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Multilingualism Marianne Gullberg & Peter Indefrey"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9ba2a2ec-cef0-59d8-853d-b578318399c5.json b/oaitestdata/clarin-oai_dc/SET_1/json/9ba2a2ec-cef0-59d8-853d-b578318399c5.json
deleted file mode 100644
index cbda7666..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9ba2a2ec-cef0-59d8-853d-b578318399c5.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3682",
-    "MetadataAccess": [
-        "oai:ota:oucs:3682"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pope, Alexander, 1688-1744."
-    ],
-    "fulltext": "oai:ota:oucs:3682;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3682.xml;Horace his ode to Venus. Lib. IV. Ode I. Imitated by Mr. Pope;Pope, Alexander, 1688-1744.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9ba2a2ec-cef0-59d8-853d-b578318399c5",
-    "oai_identifier": [
-        "oai:ota:oucs:3682"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Horace his ode to Venus. Lib. IV. Ode I. Imitated by Mr. Pope"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3682.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9bb125f5-c159-5bd0-89d1-719a6a68498d.json b/oaitestdata/clarin-oai_dc/SET_1/json/9bb125f5-c159-5bd0-89d1-719a6a68498d.json
deleted file mode 100644
index c39178ac..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9bb125f5-c159-5bd0-89d1-719a6a68498d.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5604",
-    "MetadataAccess": [
-        "oai:ota:oucs:5604"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "General Infirmary at Leeds."
-    ],
-    "fulltext": "oai:ota:oucs:5604;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5604.xml;Rules and orders of the General Infirmary at Leeds;General Infirmary at Leeds.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9bb125f5-c159-5bd0-89d1-719a6a68498d",
-    "oai_identifier": [
-        "oai:ota:oucs:5604"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Rules and orders of the General Infirmary at Leeds"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5604.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9bb8d116-1cca-5895-8f07-94f8cf073dfc.json b/oaitestdata/clarin-oai_dc/SET_1/json/9bb8d116-1cca-5895-8f07-94f8cf073dfc.json
deleted file mode 100644
index 19972ef0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9bb8d116-1cca-5895-8f07-94f8cf073dfc.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Burnard, Lou"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 100 KB)"
-    ],
-    "Language": [
-        "English",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1027",
-    "MetadataAccess": [
-        "oai:ota:oucs:1027"
-    ],
-    "PublicationTimestamp": "1645-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1645"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Milton, John, 1608-1674"
-    ],
-    "fulltext": "oai:ota:oucs:1027;2018-03-05T10:37:10Z;http://ota.ox.ac.uk/headers/1027.xml;Poems [1645] / John Milton;Milton, John, 1608-1674;1645;text_and_corpus_linguistics;English poetry -- 17th century;eng;lat;Oxford Text Archive, University of Oxford;Burnard, Lou;(1 file : ca. 100 KB);Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9bb8d116-1cca-5895-8f07-94f8cf073dfc",
-    "oai_identifier": [
-        "oai:ota:oucs:1027"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English poetry -- th century"
-        }
-    ],
-    "title": [
-        "Poems [1645] / John Milton"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1027.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9bbba294-c985-50a5-8cea-d1d3b40def71.json b/oaitestdata/clarin-oai_dc/SET_1/json/9bbba294-c985-50a5-8cea-d1d3b40def71.json
deleted file mode 100644
index f88927de..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9bbba294-c985-50a5-8cea-d1d3b40def71.json
+++ /dev/null
@@ -1,91 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/xml",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/508",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/508"
-    ],
-    "PID": "http://hdl.handle.net/11321/508",
-    "PublicationTimestamp": "2018-06-30T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "plWordNet",
-        "http://clarin-pl.eu/en/licenses/plwordnet-2/",
-        "PUB"
-    ],
-    "author": [
-        "Szpakowicz, Stan",
-        "Maziarz, Marek",
-        "Kali\u0144ski, Micha\u0142",
-        "Radziszewski, Adam",
-        "Wendelberger, Micha\u0142",
-        "Piasecki, Maciej",
-        "Dziob, Agnieszka"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/508;2018-09-17T10:01:34Z;hdl_11321_3;hdl_11321_4;MWELexicon 1.1;Dziob, Agnieszka;Kali\u0144ski, Micha\u0142;Maziarz, Marek;Piasecki, Maciej;Radziszewski, Adam;Szpakowicz, Stan;Wendelberger, Micha\u0142;multi-word units;syntax;syntactic schema;inflection;collocations;plWordNet;Lexicon of 56,5k multi-word lexical units linked to plWordNet, together with description of their syntactic bahaviour obtained in constraint language (WCCL).;2018-06-30;lexicalConceptualResource;http://hdl.handle.net/11321/508;pol;plWordNet;http://clarin-pl.eu/en/licenses/plwordnet-2/;PUB;text/xml;text/plain; charset=utf-8;downloadable_files_count: 1;Wroc\u0142aw University of Technology;http://clarin-pl.eu/pl/strona-glowna/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9bbba294-c985-50a5-8cea-d1d3b40def71",
-    "notes": [
-        "Lexicon of 56,5k multi-word lexical units linked to plWordNet, together with description of their syntactic bahaviour obtained in constraint language (WCCL)."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/508"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "multi-word units"
-        },
-        {
-            "name": "syntax"
-        },
-        {
-            "name": "syntactic schema"
-        },
-        {
-            "name": "inflection"
-        },
-        {
-            "name": "collocations"
-        },
-        {
-            "name": "plWordNet"
-        }
-    ],
-    "title": [
-        "MWELexicon 1.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9bd0b0e4-78fa-5368-bb1b-601ffe272b11.json b/oaitestdata/clarin-oai_dc/SET_1/json/9bd0b0e4-78fa-5368-bb1b-601ffe272b11.json
deleted file mode 100644
index 6d1b4ec2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9bd0b0e4-78fa-5368-bb1b-601ffe272b11.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Jezuit\u00f3w"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-84752",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-84752"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D3B-8",
-    "PublicationTimestamp": "1652-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1652"
-    ],
-    "Publisher": [
-        "Drukarnia Jezuit\u00f3w"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/84752",
-        "oai:jbc.bj.uj.edu.pl:publication:91361"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1601/1700"
-    ],
-    "TempCoverageBegin": 50506804799,
-    "TempCoverageEnd": 50506804799,
-    "TemporalCoverage": " point in time : 1601-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1601-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1601-07-01T11:59:59Z",
-    "author": [
-        "Borkowski, Modest (16..-post 1657)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-84752;2019-03-01T17:46:52Z;Complement ozdoby Starozytney Pilawie Przez [...] Mikolaia Z Potoka Potockiego Kasztelana Krakowskiego Y Hetmana Wielkiego Koronnego [...];Borkowski, Modest (16..-post 1657);starodruki 17\u00a0w.;Potocki, Piotr (-1657). Adr. ded.;Drukarnia Jezuit\u00f3w;[1652];starodruk;application/xml;clarind-uds:poldilemma-84752;hdl:11858/00-246C-0000-0023-8D3B-8;Biblioteka Jagiello\u0144ska, BJ St. Dr. 18385 I;pol;lat;http://jbc.bj.uj.edu.pl/Content/84752;oai:jbc.bj.uj.edu.pl:publication:91361;1601/1700;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9bd0b0e4-78fa-5368-bb1b-601ffe272b11",
-    "notes": [
-        "Potocki, Piotr (-1657). Adr. ded."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-84752"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Complement ozdoby Starozytney Pilawie Przez [...] Mikolaia Z Potoka Potockiego Kasztelana Krakowskiego Y Hetmana Wielkiego Koronnego [...]"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9bef0a28-7bf3-555a-b6eb-a0e1e19d038a.json b/oaitestdata/clarin-oai_dc/SET_1/json/9bef0a28-7bf3-555a-b6eb-a0e1e19d038a.json
deleted file mode 100644
index e41c3f95..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9bef0a28-7bf3-555a-b6eb-a0e1e19d038a.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(3 files : ca. 583, 590, 4.89 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "Middle High German (ca. 1050-1500)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1989",
-    "MetadataAccess": [
-        "oai:ota:oucs:1989"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Sermons"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:1989;2018-04-16T15:30:51Z;http://ota.ox.ac.uk/headers/1989.xml;Altdeutsche Predigten und Gebete aus Handschriften;Date unknown;text_and_corpus_linguistics;Addresses -- Germany -- 13th century;Sermons -- Germany -- 13th century;gmh;Sermons in Middle High German on various topics and liturgical days ;Oxford Text Archive, University of Oxford;text/plain;(3 files : ca. 583, 590, 4.89 KB);Text;Sermons;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9bef0a28-7bf3-555a-b6eb-a0e1e19d038a",
-    "notes": [
-        "Sermons in Middle High German on various topics and liturgical days "
-    ],
-    "oai_identifier": [
-        "oai:ota:oucs:1989"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Addresses -- Germany -- th century"
-        },
-        {
-            "name": "Sermons -- Germany -- th century"
-        }
-    ],
-    "title": [
-        "Altdeutsche Predigten und Gebete aus Handschriften"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1989.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9c1968bd-b48e-5db3-aad0-658e6b653f48.json b/oaitestdata/clarin-oai_dc/SET_1/json/9c1968bd-b48e-5db3-aad0-658e6b653f48.json
deleted file mode 100644
index ca35d775..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9c1968bd-b48e-5db3-aad0-658e6b653f48.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "928 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0014",
-    "MetadataAccess": [
-        "oai:ota:oucs:0014"
-    ],
-    "PublicationTimestamp": "1817-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1817"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Austen, Jane, 1775-1817"
-    ],
-    "fulltext": "oai:ota:oucs:0014;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0014.xml;Northanger Abbey & Persuasion;Austen, Jane, 1775-1817;1817;text_and_corpus_linguistics;English fiction -- 19th century;eng;Oxford Text Archive, University of Oxford;928 KB;Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9c1968bd-b48e-5db3-aad0-658e6b653f48",
-    "oai_identifier": [
-        "oai:ota:oucs:0014"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English fiction -- th century"
-        }
-    ],
-    "title": [
-        "Northanger Abbey & Persuasion"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0014.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9c6f1cb1-86cc-5be5-98ea-8f5b103418fa.json b/oaitestdata/clarin-oai_dc/SET_1/json/9c6f1cb1-86cc-5be5-98ea-8f5b103418fa.json
deleted file mode 100644
index 270737df..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9c6f1cb1-86cc-5be5-98ea-8f5b103418fa.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=524f2f40cf3211e1a404080027e73ea25d2805d840414a7f914ac3ccfc93f364",
-    "MetadataAccess": [
-        "524f2f40cf3211e1a404080027e73ea25d2805d840414a7f914ac3ccfc93f364"
-    ],
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "524f2f40cf3211e1a404080027e73ea25d2805d840414a7f914ac3ccfc93f364;2019-02-27T12:09:05Z;corpus;corpus:text;PAROLE Portuguese Annotated Corpus;The PAROLE Portuguese Corpus \u00e2\u0080\u0093 tagged subset contains 250.000 tokens and is a subset of the PAROLE Portuguese Corpus of 3 million running words of European Portuguese. The corpus was classified and encoded according to the common core parole encoding standard. \nThe tagged subset reproduces approximately the whole Corpus distribution by Medium (Newspaper: about 65%, Book: ab. 20%, Periodical: ab. 5%, Miscellaneous: ab. 10%). It has been morpho-syntactically tagged accordingly to the parole common tagset and morpho-syntactic annotation standards. Disambiguation was manually checked.\nThe corpus was tagged under a collaboration of two Portuguese institutions: the Centre of Linguistics of the University of Lisbon and INESC-ID.;2015-12-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9c6f1cb1-86cc-5be5-98ea-8f5b103418fa",
-    "notes": [
-        "The PAROLE Portuguese Corpus \u00e2\u0080\u0093 tagged subset contains 250.000 tokens and is a subset of the PAROLE Portuguese Corpus of 3 million running words of European Portuguese. The corpus was classified and encoded according to the common core parole encoding standard. \nThe tagged subset reproduces approximately the whole Corpus distribution by Medium (Newspaper: about 65%, Book: ab. 20%, Periodical: ab. 5%, Miscellaneous: ab. 10%). It has been morpho-syntactically tagged accordingly to the parole common tagset and morpho-syntactic annotation standards. Disambiguation was manually checked.\nThe corpus was tagged under a collaboration of two Portuguese institutions: the Centre of Linguistics of the University of Lisbon and INESC-ID."
-    ],
-    "oai_identifier": [
-        "524f2f40cf3211e1a404080027e73ea25d2805d840414a7f914ac3ccfc93f364"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "PAROLE Portuguese Annotated Corpus"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9c80ab66-6e1b-5303-b3dc-c6487b854ec7.json b/oaitestdata/clarin-oai_dc/SET_1/json/9c80ab66-6e1b-5303-b3dc-c6487b854ec7.json
deleted file mode 100644
index 306b11a2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9c80ab66-6e1b-5303-b3dc-c6487b854ec7.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Center of Computational Linguistics, Vytautas Magnus University"
-    ],
-    "Contributor": [
-        "Utka, dr. Andrius"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Lithuanian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-363",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-363"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-363",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Center of Computational Linguistics, Vytautas Magnus University"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Lithuania"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-363;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Corpus of the Contemporary Lithuanian Language;Utka, dr. Andrius;140 million words; Corpus of the Contemporary Lithuanian Language which comprises 160 million words is a collection of texts designed to represent current Lithuanian. The corpus is compiled  from printed material during Lithuania's independence period (since 1990). The corpus is designed to represent as wide a range of contemporary written Lithuanian as possible. The largest part of the corpus is comprised of General Press (texts from regional and national newspapers), Popular Press, and Special Press (specialized newspapers and magazines). These texts have been intended for general readers, as well as specialists. The rest of the corpus consists of Fiction, Memoirs, other literature (scientific and popular), and various official texts. The larger part of the corpus is freely accessible for online search at http://donelaitis.vdu.lt.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-363;lit;application/octet-stream;downloadable_files_count: 0;Lithuania;Center of Computational Linguistics, Vytautas Magnus University;http://tekstynas.vdu.lt/tekstynas/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9c80ab66-6e1b-5303-b3dc-c6487b854ec7",
-    "notes": [
-        "140 million words; Corpus of the Contemporary Lithuanian Language which comprises 160 million words is a collection of texts designed to represent current Lithuanian. The corpus is compiled  from printed material during Lithuania's independence period (since 1990). The corpus is designed to represent as wide a range of contemporary written Lithuanian as possible. The largest part of the corpus is comprised of General Press (texts from regional and national newspapers), Popular Press, and Special Press (specialized newspapers and magazines). These texts have been intended for general readers, as well as specialists. The rest of the corpus consists of Fiction, Memoirs, other literature (scientific and popular), and various official texts. The larger part of the corpus is freely accessible for online search at http://donelaitis.vdu.lt."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-363"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus of the Contemporary Lithuanian Language"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9c834028-c81e-582a-8061-12c26f075b32.json b/oaitestdata/clarin-oai_dc/SET_1/json/9c834028-c81e-582a-8061-12c26f075b32.json
deleted file mode 100644
index 8d418489..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9c834028-c81e-582a-8061-12c26f075b32.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3139",
-    "MetadataAccess": [
-        "oai:ota:oucs:3139"
-    ],
-    "PublicationTimestamp": "1687-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1687"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "L'Estrange, Roger, Sir, 1616-1704"
-    ],
-    "fulltext": "oai:ota:oucs:3139;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3139.xml;The Observator: [Selections];L'Estrange, Roger, Sir, 1616-1704;not after: 1687;text_and_corpus_linguistics;Great Britain -- Politics and government -- 1660-1688;eng;Oxford Text Archive, University of Oxford;Triggs, Jeffery;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9c834028-c81e-582a-8061-12c26f075b32",
-    "oai_identifier": [
-        "oai:ota:oucs:3139"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Great Britain -- Politics government -- -"
-        }
-    ],
-    "title": [
-        "The Observator: [Selections]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3139.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9c966201-43c3-5e4c-8543-efb9c7f71f94.json b/oaitestdata/clarin-oai_dc/SET_1/json/9c966201-43c3-5e4c-8543-efb9c7f71f94.json
deleted file mode 100644
index f755e705..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9c966201-43c3-5e4c-8543-efb9c7f71f94.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=eab0e2786bfa11e2a2aa782bcb074135bb0cf0cdc6f647be98deedde5baeb546",
-    "MetadataAccess": [
-        "eab0e2786bfa11e2a2aa782bcb074135bb0cf0cdc6f647be98deedde5baeb546"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "eab0e2786bfa11e2a2aa782bcb074135bb0cf0cdc6f647be98deedde5baeb546;2018-11-15T16:40:07Z;toolService;toolService:service;U-Compare Sentence Splitting Service;Web service created by exporting UIMA-based workflow from the U-Compare text mining system.\nFunctionality: Identifies sentences in plain text\nTools in workflow: Freeling sentence splitter web service (service provided by the PANACEA project) \nNOTE: The licence provided covers the web service only. Tools used to create the workflow may have their own licences;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9c966201-43c3-5e4c-8543-efb9c7f71f94",
-    "notes": [
-        "Web service created by exporting UIMA-based workflow from the U-Compare text mining system.\nFunctionality: Identifies sentences in plain text\nTools in workflow: Freeling sentence splitter web service (service provided by the PANACEA project) \nNOTE: The licence provided covers the web service only. Tools used to create the workflow may have their own licences"
-    ],
-    "oai_identifier": [
-        "eab0e2786bfa11e2a2aa782bcb074135bb0cf0cdc6f647be98deedde5baeb546"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:service"
-    ],
-    "state": "active",
-    "title": [
-        "U-Compare Sentence Splitting Service"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9cbf5fe0-1dca-56a9-8b1b-a3e9d4a3c747.json b/oaitestdata/clarin-oai_dc/SET_1/json/9cbf5fe0-1dca-56a9-8b1b-a3e9d4a3c747.json
deleted file mode 100644
index 0958d781..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9cbf5fe0-1dca-56a9-8b1b-a3e9d4a3c747.json
+++ /dev/null
@@ -1,117 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Bulgarian",
-        "Czech",
-        "English",
-        "Estonian",
-        "Persian",
-        "Hungarian",
-        "Macedonian",
-        "Polish",
-        "Romanian",
-        "Slovak",
-        "Slovenian",
-        "Serbian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1043",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1043"
-    ],
-    "PID": "http://hdl.handle.net/11356/1043",
-    "PublicationTimestamp": "2010-05-14T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/211938",
-        "https://doi.org/10.1007/s10579-011-9174-8",
-        "http://hdl.handle.net/11372/LRT-675"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Oravecz, Csaba",
-        "Barbu, Ana-Maria",
-        "Krstev, Cvetana",
-        "Petkevi\u010d, Vladim\u00edr",
-        "Dimitrova, Ludmila",
-        "Priest-Dorman, Greg",
-        "QasemiZadeh, Behrang",
-        "Kotsyba, Natalia",
-        "Tufi\u015f, Dan",
-        "Garab\u00edk, Radovan",
-        "Erjavec, Toma\u017e",
-        "Zdravkova, Katerina",
-        "Radziszewski, Adam",
-        "Derzhanski, Ivan",
-        "Kaalep, Heiki-Jaan",
-        "Simov, Kiril",
-        "Ide, Nancy"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1043;2017-09-29T14:05:02Z;hdl_11356_1023;hdl_11356_1024;MULTEXT-East \"1984\" annotated corpus 4.0;Erjavec, Toma\u017e;Barbu, Ana-Maria;Derzhanski, Ivan;Dimitrova, Ludmila;Garab\u00edk, Radovan;Ide, Nancy;Kaalep, Heiki-Jaan;Kotsyba, Natalia;Krstev, Cvetana;Oravecz, Csaba;Petkevi\u010d, Vladim\u00edr;Priest-Dorman, Greg;QasemiZadeh, Behrang;Radziszewski, Adam;Simov, Kiril;Tufi\u015f, Dan;Zdravkova, Katerina;parallel corpus;tagging;multilingual;Slavic languages;manual annotation;TEI;The novel \"1984\" by George Orwell is the central component of the MULTEXT-East corpus. This parallel and sentence aligned corpus contains the novel in the English original (about 100,000 words in length), and its translations into a number of languages. \r\n\r\nThis version of the corpus contains the linguistically annotated texts, with each word tagged by its lemma and its MULTEXT(-East) morphosyntactic description (MSD, i.e., a fine-grained feature-structure based PoS tag).\r\n\r\nThe structurally annotated texts are a separate submission (http://hdl.handle.net/11356/1044), also with somewhat different languages.;2010-05-14;corpus;http://hdl.handle.net/11356/1043;bul;ces;eng;est;fas;hun;mkd;pol;ron;slk;slv;srp;info:eu-repo/grantAgreement/EC/FP7/211938;https://doi.org/10.1007/s10579-011-9174-8;http://hdl.handle.net/11372/LRT-675;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);https://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Jo\u017eef Stefan Institute;http://nl.ijs.si/ME/V4/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9cbf5fe0-1dca-56a9-8b1b-a3e9d4a3c747",
-    "notes": [
-        "The novel \"1984\" by George Orwell is the central component of the MULTEXT-East corpus. This parallel and sentence aligned corpus contains the novel in the English original (about 100,000 words in length), and its translations into a number of languages. \r\n\r\nThis version of the corpus contains the linguistically annotated texts, with each word tagged by its lemma and its MULTEXT(-East) morphosyntactic description (MSD, i.e., a fine-grained feature-structure based PoS tag).\r\n\r\nThe structurally annotated texts are a separate submission (http://hdl.handle.net/11356/1044), also with somewhat different languages."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1043"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parallel corpus"
-        },
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "multilingual"
-        },
-        {
-            "name": "Slavic languages"
-        },
-        {
-            "name": "manual annotation"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "MULTEXT-East \"1984\" annotated corpus 4.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9cee2a96-c25d-55c2-b749-c5a868bf51b6.json b/oaitestdata/clarin-oai_dc/SET_1/json/9cee2a96-c25d-55c2-b749-c5a868bf51b6.json
deleted file mode 100644
index bd22de76..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9cee2a96-c25d-55c2-b749-c5a868bf51b6.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Catalan",
-        "English",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1176",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1176"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1176",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1176;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Bwananet;Tool for querying the Technical Corpus of the Institut Universitari de Ling\u00fc\u00edstica Aplicada.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1176;cat;eng;spa;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra;http://bwananet.iula.upf.edu/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9cee2a96-c25d-55c2-b749-c5a868bf51b6",
-    "notes": [
-        "Tool for querying the Technical Corpus of the Institut Universitari de Ling\u00fc\u00edstica Aplicada."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1176"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Bwananet"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9cf1c669-f289-5dd1-a39c-6f4bb4a9547a.json b/oaitestdata/clarin-oai_dc/SET_1/json/9cf1c669-f289-5dd1-a39c-6f4bb4a9547a.json
deleted file mode 100644
index e7130af1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9cf1c669-f289-5dd1-a39c-6f4bb4a9547a.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4998",
-    "MetadataAccess": [
-        "oai:ota:oucs:4998"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Aikin, John, 1747-1822."
-    ],
-    "fulltext": "oai:ota:oucs:4998;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4998.xml;Evenings at home; or, the juvenile budget opened: Consisting of a variety of miscellaneous pieces, ... [pt.5];Aikin, John, 1747-1822.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9cf1c669-f289-5dd1-a39c-6f4bb4a9547a",
-    "oai_identifier": [
-        "oai:ota:oucs:4998"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Evenings at home; or, the juvenile budget opened: Consisting of a variety of miscellaneous pieces, ... [pt.5]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4998.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9d054e84-df88-5042-8319-b3e72c9b5095.json b/oaitestdata/clarin-oai_dc/SET_1/json/9d054e84-df88-5042-8319-b3e72c9b5095.json
deleted file mode 100644
index 388b3836..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9d054e84-df88-5042-8319-b3e72c9b5095.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2740",
-    "MetadataAccess": [
-        "oai:ota:oucs:2740"
-    ],
-    "PublicationTimestamp": "1712-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1712"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2740;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2740.xml;The conduct of the allies;Swift, Jonathan, 1667-1745;1712 [i.e. 1711];text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9d054e84-df88-5042-8319-b3e72c9b5095",
-    "oai_identifier": [
-        "oai:ota:oucs:2740"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The conduct of the allies"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2740.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9d05602e-f581-5785-9cc9-f13d611a3d2f.json b/oaitestdata/clarin-oai_dc/SET_1/json/9d05602e-f581-5785-9cc9-f13d611a3d2f.json
deleted file mode 100644
index d663650c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9d05602e-f581-5785-9cc9-f13d611a3d2f.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4419",
-    "MetadataAccess": [
-        "oai:ota:oucs:4419"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Brooke, Frances, 1724?-1789."
-    ],
-    "fulltext": "oai:ota:oucs:4419;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4419.xml;The history of Lady Julia Mandeville: In two volumes. By the translator of Lady Catesby's letters. [pt.2];Brooke, Frances, 1724?-1789.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9d05602e-f581-5785-9cc9-f13d611a3d2f",
-    "oai_identifier": [
-        "oai:ota:oucs:4419"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The history of Lady Julia Mandeville: In two volumes. By the translator of Lady Catesby's letters. [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4419.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9d0a1b2d-983d-554b-96c0-67f5bdbdf1c0.json b/oaitestdata/clarin-oai_dc/SET_1/json/9d0a1b2d-983d-554b-96c0-67f5bdbdf1c0.json
deleted file mode 100644
index 46f283a8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9d0a1b2d-983d-554b-96c0-67f5bdbdf1c0.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Lancashire, Ian"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 122 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1330",
-    "MetadataAccess": [
-        "oai:ota:oucs:1330"
-    ],
-    "PublicationTimestamp": "1497-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1497"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Medwall, Henry, active 1486"
-    ],
-    "fulltext": "oai:ota:oucs:1330;2018-03-07T16:12:07Z;http://ota.ox.ac.uk/headers/1330.xml;Fulgens and Lucres / Henry Medwall;Medwall, Henry, active 1486;1497;text_and_corpus_linguistics;English drama -- Early modern and Elizabethan, 1500-1600;Oxford Text Archive, University of Oxford;Lancashire, Ian;(1 file : ca. 122 KB);Text;Plays;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9d0a1b2d-983d-554b-96c0-67f5bdbdf1c0",
-    "oai_identifier": [
-        "oai:ota:oucs:1330"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- Early modern Elizabethan"
-        }
-    ],
-    "title": [
-        "Fulgens and Lucres / Henry Medwall"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1330.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9d1e7ff7-cf9b-5ef8-818e-0b324dfa8f9b.json b/oaitestdata/clarin-oai_dc/SET_1/json/9d1e7ff7-cf9b-5ef8-818e-0b324dfa8f9b.json
deleted file mode 100644
index 3144b307..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9d1e7ff7-cf9b-5ef8-818e-0b324dfa8f9b.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4105",
-    "MetadataAccess": [
-        "oai:ota:oucs:4105"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Rowe, Nicholas, 1674-1718."
-    ],
-    "fulltext": "oai:ota:oucs:4105;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4105.xml;Poems on several occasions: By N. Rowe, Esq;.;Rowe, Nicholas, 1674-1718.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9d1e7ff7-cf9b-5ef8-818e-0b324dfa8f9b",
-    "oai_identifier": [
-        "oai:ota:oucs:4105"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Poems on several occasions: By N. Rowe, Esq;."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4105.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9d354b4f-a051-5e5e-bfbc-08548d61ab29.json b/oaitestdata/clarin-oai_dc/SET_1/json/9d354b4f-a051-5e5e-bfbc-08548d61ab29.json
deleted file mode 100644
index 14a2a921..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9d354b4f-a051-5e5e-bfbc-08548d61ab29.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4108",
-    "MetadataAccess": [
-        "oai:ota:oucs:4108"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Garrick, David, 1717-1779."
-    ],
-    "fulltext": "oai:ota:oucs:4108;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4108.xml;The poetical works of David Garrick, Esq. Now first collected into two volumes. With explanatory notes.: [pt.2];Garrick, David, 1717-1779.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9d354b4f-a051-5e5e-bfbc-08548d61ab29",
-    "oai_identifier": [
-        "oai:ota:oucs:4108"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The poetical works of David Garrick, Esq. Now first collected into two volumes. With explanatory notes.: [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4108.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9d3d5c11-57c9-57b0-9f41-132da55f1322.json b/oaitestdata/clarin-oai_dc/SET_1/json/9d3d5c11-57c9-57b0-9f41-132da55f1322.json
deleted file mode 100644
index 2faac1c7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9d3d5c11-57c9-57b0-9f41-132da55f1322.json
+++ /dev/null
@@ -1,98 +0,0 @@
-{
-    "Contact": [
-        "Lehrstuhl Englische Sprach- und \u00dcbersetzungswissenschaft, Fakult\u00e4t P, Fachrichtung Sprachwissenschaft und Sprachtechnologie, Universit\u00e4t des Saarlandes, Campus A2.2, 66123 Saarbr\u00fccken, Germany"
-    ],
-    "Contributor": [
-        "Alina Karakanta",
-        "Elke Teich",
-        "Mihaela Vela"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:europarl-uds",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:europarl-uds"
-    ],
-    "PID": "http://hdl.handle.net/21.11119/0000-0000-D5EE-4",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Lehrstuhl Englische Sprach- und \u00dcbersetzungswissenschaft, Fakult\u00e4t P, Fachrichtung Sprachwissenschaft und Sprachtechnologie, Universit\u00e4t des Saarlandes, Campus A2.2, 66123 Saarbr\u00fccken, Germany"
-    ],
-    "RelatedIdentifier": [
-        "Alina Karakanta, Mihaela Vela, and Elke Teich. 2018. \u201cEuroParl-Uds: Preserving and Extending Metadata in Parliamentary Debates\u201d. Proceedings of the LREC 2018. Miyazaki, Japan."
-    ],
-    "ResourceType": [
-        "Text collection",
-        "Written Corpus",
-        "Corpus of Proceedings of the European Parliament"
-    ],
-    "Rights": [
-        "CC-BY-SA-NC-4.0"
-    ],
-    "SpatialCoverage": [
-        "1999/2016",
-        "European Union",
-        "Parliamentary Debates"
-    ],
-    "TemporalCoverage": [
-        "1999/2016",
-        "European Union",
-        "Parliamentary Debates"
-    ],
-    "author": [
-        "Elke Teich, Lehrstuhl Englische Sprach- und \u00dcbersetzungswissenschaft, Fakult\u00e4t P, Fachrichtung Sprachwissenschaft und Sprachtechnologie, Universit\u00e4t des Saarlandes, Campus A2.2, 66123 Saarbr\u00fccken, Germany"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:europarl-uds;2018-07-13T09:47:07Z;EuroParl-Uds;Elke Teich, Lehrstuhl Englische Sprach- und \u00dcbersetzungswissenschaft, Fakult\u00e4t P, Fachrichtung Sprachwissenschaft und Sprachtechnologie, Universit\u00e4t des Saarlandes, Campus A2.2, 66123 Saarbr\u00fccken, Germany;Parliamentary debates;Proceedings of the European Parliament;Parallel corpus;Properties of translations;Monolingual comparable corpora;Translationese;The **EuroParl-UdS** corpus is a parallel corpus consisting of parliamentary debates of the European Parliament containing texts filtered based of native speakers. It is presently available for English, German and Spanish and the data is in plain text format. It contains texts of the European Parliament that were produced between 1999-2017. More specifically it consists of parallel (sentence-aligned) corpora for English into German and English into Spanish, where the source side contains texts only by native English speakers, and comparable monolingual corpora for English, German and Spanish, containing texts only by native speakers of each language.;Lehrstuhl Englische Sprach- und \u00dcbersetzungswissenschaft, Fakult\u00e4t P, Fachrichtung Sprachwissenschaft und Sprachtechnologie, Universit\u00e4t des Saarlandes, Campus A2.2, 66123 Saarbr\u00fccken, Germany;Alina Karakanta;Mihaela Vela;Elke Teich;2018;Text collection;Written Corpus;Corpus of Proceedings of the European Parliament;text/plain;clarind-uds:europarl-uds;hdl:21.11119/0000-0000-D5EE-4;eng;Alina Karakanta, Mihaela Vela, and Elke Teich. 2018. \u201cEuroParl-Uds: Preserving and Extending Metadata in Parliamentary Debates\u201d. Proceedings of the LREC 2018. Miyazaki, Japan.;1999/2016;European Union;Parliamentary Debates;CC-BY-SA-NC-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9d3d5c11-57c9-57b0-9f41-132da55f1322",
-    "notes": [
-        "The **EuroParl-UdS** corpus is a parallel corpus consisting of parliamentary debates of the European Parliament containing texts filtered based of native speakers. It is presently available for English, German and Spanish and the data is in plain text format. It contains texts of the European Parliament that were produced between 1999-2017. More specifically it consists of parallel (sentence-aligned) corpora for English into German and English into Spanish, where the source side contains texts only by native English speakers, and comparable monolingual corpora for English, German and Spanish, containing texts only by native speakers of each language."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:europarl-uds"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Parliamentary debates"
-        },
-        {
-            "name": "Proceedings European Parliament"
-        },
-        {
-            "name": "Parallel corpus"
-        },
-        {
-            "name": "Properties translations"
-        },
-        {
-            "name": "Monolingual comparable corpora"
-        },
-        {
-            "name": "Translationese"
-        }
-    ],
-    "title": [
-        "EuroParl-Uds"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9d41241e-dbea-5c37-be34-37433c145bfa.json b/oaitestdata/clarin-oai_dc/SET_1/json/9d41241e-dbea-5c37-be34-37433c145bfa.json
deleted file mode 100644
index 8e41cef5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9d41241e-dbea-5c37-be34-37433c145bfa.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5675",
-    "MetadataAccess": [
-        "oai:ota:oucs:5675"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Authoress of Emeline."
-    ],
-    "fulltext": "oai:ota:oucs:5675;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5675.xml;The triumph of prudence over passion: or, the history of Miss Mortimer and Miss Fitzgerald. By the authoress of Emeline. In two volumes. ... [pt.1];Authoress of Emeline.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9d41241e-dbea-5c37-be34-37433c145bfa",
-    "oai_identifier": [
-        "oai:ota:oucs:5675"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The triumph of prudence over passion: or, the history of Miss Mortimer and Miss Fitzgerald. By the authoress of Emeline. In two volumes. ... [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5675.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9d5e79ce-3d92-591e-84ac-de562b2d1893.json b/oaitestdata/clarin-oai_dc/SET_1/json/9d5e79ce-3d92-591e-84ac-de562b2d1893.json
deleted file mode 100644
index 0e345bcc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9d5e79ce-3d92-591e-84ac-de562b2d1893.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Lemnitzer, Lothar"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-455",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-455"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-455",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-455;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Wortwarte;Lemnitzer, Lothar;25 000 entries, XML;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-455;deu;downloadable_files_count: 0;Germany;http://www.wortwarte.de",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9d5e79ce-3d92-591e-84ac-de562b2d1893",
-    "notes": [
-        "25 000 entries, XML"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-455"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Wortwarte"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9d5eb605-f8f8-5517-93f7-9a121132e5cd.json b/oaitestdata/clarin-oai_dc/SET_1/json/9d5eb605-f8f8-5517-93f7-9a121132e5cd.json
deleted file mode 100644
index 5b0d88cb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9d5eb605-f8f8-5517-93f7-9a121132e5cd.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Hart, Michael"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 23 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1505",
-    "MetadataAccess": [
-        "oai:ota:oucs:1505"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Manuals (Handbooks)"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Vatsyayana"
-    ],
-    "fulltext": "oai:ota:oucs:1505;2018-07-27T10:31:43Z;http://ota.ox.ac.uk/headers/1505.xml;Kamasutra. English;The love secrets of the Kama Sutra / Vatsyayana;Vatsyayana;Date unknown;text_and_corpus_linguistics;Sex instruction;eng;Oxford Text Archive, University of Oxford;Hart, Michael;text/plain;(1 file : ca. 23 KB);Text;Manuals (Handbooks);Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9d5eb605-f8f8-5517-93f7-9a121132e5cd",
-    "oai_identifier": [
-        "oai:ota:oucs:1505"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Sex instruction"
-        }
-    ],
-    "title": [
-        "Kamasutra. English",
-        "The love secrets of the Kama Sutra / Vatsyayana"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1505.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9d65f782-5271-5cb9-afd0-5c0f28667403.json b/oaitestdata/clarin-oai_dc/SET_1/json/9d65f782-5271-5cb9-afd0-5c0f28667403.json
deleted file mode 100644
index 78da4846..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9d65f782-5271-5cb9-afd0-5c0f28667403.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "University of West Bohemia, Department of Cybernetics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 3",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1510",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1510"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1510",
-    "PublicationTimestamp": "2015-08-31T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "University of West Bohemia, Department of Cybernetics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u0160m\u00eddl, Lubo\u0161",
-        "Stanislav, Petr",
-        "Radov\u00e1, Vlasta"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1510;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;STAZKA \u2013 Speech recordings from vehicles;\u0160m\u00eddl, Lubo\u0161;Stanislav, Petr;Radov\u00e1, Vlasta;speech corpus;noisy speech;voice activity detector;speech recognition;The database actually contains two sets of recordings, both recorded in the moving or stationary vehicles (passenger cars or trucks). All data were recorded within the project \u201cIntelligent Electronic Record of the Operation and Vehicle Performance\u201d whose aim is to develop a voice-operated software for registering the vehicle operation data. \r\nThe first part (full_noises.zip) consists of relatively long recordings from the vehicle cabin, containing spontaneous speech from the vehicle crew. The recordings are accompanied with detailed transcripts in the Transcriber XML-based format (.trs). Due to the recording settings, the audio contains many different noises, only sparsely interspersed with speech. As such, the set is suitable for robust estimation of the voice activity detector parameters.\r\nThe second set (prompts.zip) consists of short prompts that were recorded in the controlled setting \u2013 the speakers either answered simple questions or they repeated commands and short phrases. The prompts were recorded by 26 different speakers. Each speaker recorded at least two sessions (with identical set of prompts) \u2013 first in stationary vehicle, with low level of noise (those recordings are marked by \u2013A_ in the file name) and second while actually driving the car (marked by \u2013B_ or, since several speakers recorded 3 sessions, by \u2013C_). The recordings from this set are suitable mostly for training of the robust domain-specific speech recognizer and also ASR test purposes.;2015-08-31;corpus;http://hdl.handle.net/11234/1-1510;ces;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;application/zip;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain; charset=utf-8;downloadable_files_count: 3;University of West Bohemia, Department of Cybernetics",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9d65f782-5271-5cb9-afd0-5c0f28667403",
-    "notes": [
-        "The database actually contains two sets of recordings, both recorded in the moving or stationary vehicles (passenger cars or trucks). All data were recorded within the project \u201cIntelligent Electronic Record of the Operation and Vehicle Performance\u201d whose aim is to develop a voice-operated software for registering the vehicle operation data. \r\nThe first part (full_noises.zip) consists of relatively long recordings from the vehicle cabin, containing spontaneous speech from the vehicle crew. The recordings are accompanied with detailed transcripts in the Transcriber XML-based format (.trs). Due to the recording settings, the audio contains many different noises, only sparsely interspersed with speech. As such, the set is suitable for robust estimation of the voice activity detector parameters.\r\nThe second set (prompts.zip) consists of short prompts that were recorded in the controlled setting \u2013 the speakers either answered simple questions or they repeated commands and short phrases. The prompts were recorded by 26 different speakers. Each speaker recorded at least two sessions (with identical set of prompts) \u2013 first in stationary vehicle, with low level of noise (those recordings are marked by \u2013A_ in the file name) and second while actually driving the car (marked by \u2013B_ or, since several speakers recorded 3 sessions, by \u2013C_). The recordings from this set are suitable mostly for training of the robust domain-specific speech recognizer and also ASR test purposes."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1510"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech corpus"
-        },
-        {
-            "name": "noisy speech"
-        },
-        {
-            "name": "voice activity detector"
-        },
-        {
-            "name": "speech recognition"
-        }
-    ],
-    "title": [
-        "STAZKA \u2013 Speech recordings from vehicles"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9d6751ef-990b-55dc-8c82-888a2a384842.json b/oaitestdata/clarin-oai_dc/SET_1/json/9d6751ef-990b-55dc-8c82-888a2a384842.json
deleted file mode 100644
index 124950c5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9d6751ef-990b-55dc-8c82-888a2a384842.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Wroclaw University of Science and Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/529",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/529"
-    ],
-    "PID": "http://hdl.handle.net/11321/529",
-    "PublicationTimestamp": "2018-07-19T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Wroclaw University of Science and Technology"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Janz, Arkadiusz",
-        "Koco\u0144, Jan"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/529;2018-07-19T11:45:34Z;hdl_11321_3;hdl_11321_4;Extended dictionary of named entities NELexicon connected with Linked Open Data;Janz, Arkadiusz;Koco\u0144, Jan;Polish;linked open data;named entities;nelexicon;This resource contains Polish named entities connected with terminology from available resources within Linked Open Data (e.g. WordNet, DBPedia, Wikipedia, etc.).;2018-07-19;lexicalConceptualResource;http://hdl.handle.net/11321/529;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;Wroclaw University of Science and Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9d6751ef-990b-55dc-8c82-888a2a384842",
-    "notes": [
-        "This resource contains Polish named entities connected with terminology from available resources within Linked Open Data (e.g. WordNet, DBPedia, Wikipedia, etc.)."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/529"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Polish"
-        },
-        {
-            "name": "linked open data"
-        },
-        {
-            "name": "named entities"
-        },
-        {
-            "name": "nelexicon"
-        }
-    ],
-    "title": [
-        "Extended dictionary of named entities NELexicon connected with Linked Open Data"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9d6df61b-c3e7-57ef-89e3-88ba21cda619.json b/oaitestdata/clarin-oai_dc/SET_1/json/9d6df61b-c3e7-57ef-89e3-88ba21cda619.json
deleted file mode 100644
index 61579fa4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9d6df61b-c3e7-57ef-89e3-88ba21cda619.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contributor": [
-        "Simov, Kiril"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Bulgarian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-224",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-224"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-224",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-224;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Bulgarian CLEF Corpus;Simov, Kiril;Written, synchronic, general (newspapers);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-224;bul;downloadable_files_count: 0;http://www.clef-campaign.org/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9d6df61b-c3e7-57ef-89e3-88ba21cda619",
-    "notes": [
-        "Written, synchronic, general (newspapers)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-224"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Bulgarian CLEF Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9d6fb695-680c-5089-bf3b-16b1ad2b25f2.json b/oaitestdata/clarin-oai_dc/SET_1/json/9d6fb695-680c-5089-bf3b-16b1ad2b25f2.json
deleted file mode 100644
index 6d4502ae..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9d6fb695-680c-5089-bf3b-16b1ad2b25f2.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4095",
-    "MetadataAccess": [
-        "oai:ota:oucs:4095"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dennis, John, 1657-1734."
-    ],
-    "fulltext": "oai:ota:oucs:4095;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4095.xml;A poem upon the death of her late sacred majesty Queen Anne, and the most happy and most auspicious accession of his sacred majesty King George. To the imperial crowns of Great Britain, France and Ireland. ... By Mr. Dennis;Dennis, John, 1657-1734.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9d6fb695-680c-5089-bf3b-16b1ad2b25f2",
-    "oai_identifier": [
-        "oai:ota:oucs:4095"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A poem upon the death of her late sacred majesty Queen Anne, and the most happy and most auspicious accession of his sacred majesty King George. To the imperial crowns of Great Britain, France and Ireland. ... By Mr. Dennis"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4095.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9d6fcd4e-1efe-585c-af2c-65c2b022b266.json b/oaitestdata/clarin-oai_dc/SET_1/json/9d6fcd4e-1efe-585c-af2c-65c2b022b266.json
deleted file mode 100644
index f5d55439..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9d6fcd4e-1efe-585c-af2c-65c2b022b266.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3550",
-    "MetadataAccess": [
-        "oai:ota:oucs:3550"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Morton, Thomas, 1764-1838."
-    ],
-    "fulltext": "oai:ota:oucs:3550;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3550.xml;Columbus: or, a world discovered. An historical play. As it is performed at the Theatre-Royal, Covent-Garden. By Thomas Morton, ...;Morton, Thomas, 1764-1838.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9d6fcd4e-1efe-585c-af2c-65c2b022b266",
-    "oai_identifier": [
-        "oai:ota:oucs:3550"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Columbus: or, a world discovered. An historical play. As it is performed at the Theatre-Royal, Covent-Garden. By Thomas Morton, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3550.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9d7ab4ad-b13c-5fc7-9edf-21da59434371.json b/oaitestdata/clarin-oai_dc/SET_1/json/9d7ab4ad-b13c-5fc7-9edf-21da59434371.json
deleted file mode 100644
index bc9b6877..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9d7ab4ad-b13c-5fc7-9edf-21da59434371.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "The National Library of Sweden"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/111",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/111"
-    ],
-    "PID": "http://hdl.handle.net/10794/111",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "The National Library of Sweden"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/111;2017-11-01T13:50:32Z;hdl_10794_1;hdl_10794_2;Bolln\u00e4s tidning 1870's (2015-08-31);Bolln\u00e4s tidning 1870-talet (2015-08-31);n/a, n/a;Swedish;News;A corpus with texts from Bolln\u00e4s tidning in the 1870's (1876\u20131879).;En korpus med texter fr\u00e5n Bolln\u00e4s tidning p\u00e5 1870-talet (1876\u20131879).;2015-04-08;corpus;http://hdl.handle.net/10794/111;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;The National Library of Sweden;https://spraakbanken.gu.se/swe/resurs/kubhist-bollnastidning-1870",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9d7ab4ad-b13c-5fc7-9edf-21da59434371",
-    "notes": [
-        "A corpus with texts from Bolln\u00e4s tidning in the 1870's (1876\u20131879).",
-        "En korpus med texter fr\u00e5n Bolln\u00e4s tidning p\u00e5 1870-talet (1876\u20131879)."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/111"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "News"
-        }
-    ],
-    "title": [
-        "Bolln\u00e4s tidning 1870's (2015-08-31)",
-        "Bolln\u00e4s tidning 1870-talet (2015-08-31)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9d95c42f-a6dd-59c2-b10b-0e799186287b.json b/oaitestdata/clarin-oai_dc/SET_1/json/9d95c42f-a6dd-59c2-b10b-0e799186287b.json
deleted file mode 100644
index d900d9f1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9d95c42f-a6dd-59c2-b10b-0e799186287b.json
+++ /dev/null
@@ -1,94 +0,0 @@
-{
-    "Contact": [
-        "DFG Collaborative Research Centre 991, University of Duesseldorf",
-        "Department of Applied Linguistics, Translation and Interpreting, Saarland University"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1661",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1661"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1661",
-    "PublicationTimestamp": "2016-03-07T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "DFG Collaborative Research Centre 991, University of Duesseldorf",
-        "Department of Applied Linguistics, Translation and Interpreting, Saarland University"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "QasemiZadeh, Behrang",
-        "Schumann, Anne-Kathrin"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1661;2017-08-11T13:52:21Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;The ACL RD-TEC 2.0;QasemiZadeh, Behrang;Schumann, Anne-Kathrin;Terminology;Term Extraction;Term Classification;Entity Recognition;Evaluation Corpus;Language Resource;Gold Dataset;Evaluation of Automatic Terminology Construction Methods;The ACL RD-TEC 2.0 has been developed with the aim of providing a benchmark for the evaluation of methods for terminology  extraction and classification as well as entity recognition tasks based on specialised text from the computational linguistics domain.  This release of the corpus consists of 300 abstracts from articles in the ACL Anthology Reference Corpus, published between 1978--2006. In these abstracts, terms (i.e., single or multi-word lexical units with a specialised meaning)  are manually annotated. In addition to their boundaries in running text, annotated terms are classified into one of the seven categories method, tool, language resource (LR), LR product,  model, measures and measurements, and other.  To assess the quality of the annotations and to determine the difficulty of this task, more than 171 of the abstracts are annotated twice, independently, by each of the two annotators. In total, 6,818 terms are identified and annotated, resulting in a specialised vocabulary made of 3,318 lexical forms, mapped to 3,471 concepts.;2016-03-07;corpus;http://hdl.handle.net/11372/LRT-1661;eng;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;DFG Collaborative Research Centre 991, University of Duesseldorf;Department of Applied Linguistics, Translation and Interpreting, Saarland University;http://pars.ie/lr/acl_rd-tec",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9d95c42f-a6dd-59c2-b10b-0e799186287b",
-    "notes": [
-        "The ACL RD-TEC 2.0 has been developed with the aim of providing a benchmark for the evaluation of methods for terminology  extraction and classification as well as entity recognition tasks based on specialised text from the computational linguistics domain.  This release of the corpus consists of 300 abstracts from articles in the ACL Anthology Reference Corpus, published between 1978--2006. In these abstracts, terms (i.e., single or multi-word lexical units with a specialised meaning)  are manually annotated. In addition to their boundaries in running text, annotated terms are classified into one of the seven categories method, tool, language resource (LR), LR product,  model, measures and measurements, and other.  To assess the quality of the annotations and to determine the difficulty of this task, more than 171 of the abstracts are annotated twice, independently, by each of the two annotators. In total, 6,818 terms are identified and annotated, resulting in a specialised vocabulary made of 3,318 lexical forms, mapped to 3,471 concepts."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1661"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Terminology"
-        },
-        {
-            "name": "Term Extraction"
-        },
-        {
-            "name": "Term Classification"
-        },
-        {
-            "name": "Entity Recognition"
-        },
-        {
-            "name": "Evaluation Corpus"
-        },
-        {
-            "name": "Language Resource"
-        },
-        {
-            "name": "Gold Dataset"
-        },
-        {
-            "name": "Evaluation Automatic Terminology Construction Methods"
-        }
-    ],
-    "title": [
-        "The ACL RD-TEC 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9dad1a19-b82c-5a32-bb49-61de8ca8a077.json b/oaitestdata/clarin-oai_dc/SET_1/json/9dad1a19-b82c-5a32-bb49-61de8ca8a077.json
deleted file mode 100644
index b92fd93f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9dad1a19-b82c-5a32-bb49-61de8ca8a077.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "less than 512 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0169",
-    "MetadataAccess": [
-        "oai:ota:oucs:0169"
-    ],
-    "PublicationTimestamp": "1599-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1599"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Shakespeare, William,  1564-1616"
-    ],
-    "fulltext": "oai:ota:oucs:0169;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0169.xml; Julius Caesar  / compiled by Sidney Michaelson;Shakespeare, William,  1564-1616;1599;text_and_corpus_linguistics;Plays -- England -- 16th century;eng;Oxford Text Archive, University of Oxford;less than 512 KB;Text;Plays;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9dad1a19-b82c-5a32-bb49-61de8ca8a077",
-    "oai_identifier": [
-        "oai:ota:oucs:0169"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        }
-    ],
-    "title": [
-        " Julius Caesar  / compiled by Sidney Michaelson"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0169.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9db2c69f-555a-56ad-8c8d-d1afd017f138.json b/oaitestdata/clarin-oai_dc/SET_1/json/9db2c69f-555a-56ad-8c8d-d1afd017f138.json
deleted file mode 100644
index 785bb6b9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9db2c69f-555a-56ad-8c8d-d1afd017f138.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "Middle English (1100-1500)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3202",
-    "MetadataAccess": [
-        "oai:ota:oucs:3202"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Chaucer, Geoffrey, d. 1400"
-    ],
-    "fulltext": "oai:ota:oucs:3202;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3202.xml;Troilus & Criseyde;Chaucer, Geoffrey, d. 1400;default: 1976-01-01;text_and_corpus_linguistics;Poems -- England -- 14th century;enm;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9db2c69f-555a-56ad-8c8d-d1afd017f138",
-    "oai_identifier": [
-        "oai:ota:oucs:3202"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- England -- th century"
-        }
-    ],
-    "title": [
-        "Troilus & Criseyde"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3202.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9db9c309-04d1-53eb-b89f-1c330372fbdd.json b/oaitestdata/clarin-oai_dc/SET_1/json/9db9c309-04d1-53eb-b89f-1c330372fbdd.json
deleted file mode 100644
index 7fd1fc96..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9db9c309-04d1-53eb-b89f-1c330372fbdd.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 3",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/557",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/557"
-    ],
-    "PID": "http://hdl.handle.net/11321/557",
-    "PublicationTimestamp": "2018-07-26T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "plWordNet",
-        "http://clarin-pl.eu/en/licenses/plwordnet-2/",
-        "PUB"
-    ],
-    "author": [
-        "Wroclaw University of Technology"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/557;2018-07-26T07:47:30Z;hdl_11321_3;hdl_11321_4;WordnetLoom 2.0;Wroclaw University of Technology;wordnet editor;java;wildfly;docker;mysql;WordneLoom 2.0 executable files for plWordnet 4.0.\r\nSource code available at https://github.com/CLARIN-PL/WordnetLoom\r\n\r\nWordnetLoom \u2013 is an wordnet editor application built for the needs of the construction of a the largest Polish wordnet called plWordNet. WordnetLoom provides two means of interaction: a form-based, implemented initially, and a visual, graph-based introduced recently. The visual, graph-based interactive presentation of the wordnet structure enables browsing and its direct editing on the structure of lexico-semantic relations and synsets. WordnetLooms works in a distributed environment, i.e. several linguists can work simulanuously from different sites on the same central database.;2018-07-26;toolService;http://hdl.handle.net/11321/557;eng;plWordNet;http://clarin-pl.eu/en/licenses/plwordnet-2/;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 3;Wroc\u0142aw University of Technology;http://plwordnet.pwr.wroc.pl/wordnet/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9db9c309-04d1-53eb-b89f-1c330372fbdd",
-    "notes": [
-        "WordneLoom 2.0 executable files for plWordnet 4.0.\r\nSource code available at https://github.com/CLARIN-PL/WordnetLoom\r\n\r\nWordnetLoom \u2013 is an wordnet editor application built for the needs of the construction of a the largest Polish wordnet called plWordNet. WordnetLoom provides two means of interaction: a form-based, implemented initially, and a visual, graph-based introduced recently. The visual, graph-based interactive presentation of the wordnet structure enables browsing and its direct editing on the structure of lexico-semantic relations and synsets. WordnetLooms works in a distributed environment, i.e. several linguists can work simulanuously from different sites on the same central database."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/557"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "wordnet editor"
-        },
-        {
-            "name": "java"
-        },
-        {
-            "name": "wildfly"
-        },
-        {
-            "name": "docker"
-        },
-        {
-            "name": "mysql"
-        }
-    ],
-    "title": [
-        "WordnetLoom 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9dc05d61-5fc7-5c11-b686-c1fb95d9fdfa.json b/oaitestdata/clarin-oai_dc/SET_1/json/9dc05d61-5fc7-5c11-b686-c1fb95d9fdfa.json
deleted file mode 100644
index 67efdc4f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9dc05d61-5fc7-5c11-b686-c1fb95d9fdfa.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Ibtikarat team"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/xml",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Arabic"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1936",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1936"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1936",
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Ibtikarat team"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)",
-        "http://creativecommons.org/licenses/by-nc/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Jaafar, Younes"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1936;2017-01-04T17:22:59Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Arabic Morphological evaluation corpus;Jaafar, Younes;morphological analysis;benchmarking corpus;An annotated corpus dedicated to the benchmark and evaluation of Arabic morphological analyzers. It consists of 100 words with all their possible analysis. The corpus contains several morphological information such as stem, pattern, root, lemma, etc.;2014;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1936;ara;Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0);http://creativecommons.org/licenses/by-nc/4.0/;PUB;text/xml;text/plain; charset=utf-8;downloadable_files_count: 1;Ibtikarat team;http://arabic.emi.ac.ma/ibtikarat/?q=Resources",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9dc05d61-5fc7-5c11-b686-c1fb95d9fdfa",
-    "notes": [
-        "An annotated corpus dedicated to the benchmark and evaluation of Arabic morphological analyzers. It consists of 100 words with all their possible analysis. The corpus contains several morphological information such as stem, pattern, root, lemma, etc."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1936"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphological analysis"
-        },
-        {
-            "name": "benchmarking corpus"
-        }
-    ],
-    "title": [
-        "Arabic Morphological evaluation corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9de31fdc-f257-5d09-9c31-c369527bc602.json b/oaitestdata/clarin-oai_dc/SET_1/json/9de31fdc-f257-5d09-9c31-c369527bc602.json
deleted file mode 100644
index 838d352c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9de31fdc-f257-5d09-9c31-c369527bc602.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4938",
-    "MetadataAccess": [
-        "oai:ota:oucs:4938"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Burgoyne, John, 1722-1792."
-    ],
-    "fulltext": "oai:ota:oucs:4938;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4938.xml;A supplement to The State of the expedition from Canada: containing General Burgoyne's orders, respecting the principal movements, ... of the army to the raising of the siege of Ticonderoga.;State of the expedition from Canada.;Burgoyne, John, 1722-1792.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9de31fdc-f257-5d09-9c31-c369527bc602",
-    "oai_identifier": [
-        "oai:ota:oucs:4938"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A supplement to The State of the expedition from Canada: containing General Burgoyne's orders, respecting the principal movements, ... of the army to the raising of the siege of Ticonderoga.",
-        "State of the expedition from Canada."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4938.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9df234a3-0da9-576f-b173-df7800c1aa4e.json b/oaitestdata/clarin-oai_dc/SET_1/json/9df234a3-0da9-576f-b173-df7800c1aa4e.json
deleted file mode 100644
index e96eeef0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9df234a3-0da9-576f-b173-df7800c1aa4e.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Centro de Tecnolog\u00edas y Aplicaciones del Lenguaje y del Habla (TALP)"
-    ],
-    "Contributor": [
-        "Gimenez, Jesus"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Catalan",
-        "English",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-311",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-311"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-311",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Centro de Tecnolog\u00edas y Aplicaciones del Lenguaje y del Habla (TALP)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-311;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;SVMTool;Gimenez, Jesus;Generator of sequential taggers based on Support Vector Machines.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-311;cat;eng;spa;downloadable_files_count: 0;Spain;Centro de Tecnolog\u00edas y Aplicaciones del Lenguaje y del Habla (TALP);http://www.lsi.upc.edu/~nlp/SVMTool/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9df234a3-0da9-576f-b173-df7800c1aa4e",
-    "notes": [
-        "Generator of sequential taggers based on Support Vector Machines."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-311"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "SVMTool"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9e24be7e-d604-5854-a3d7-5fae346b86ff.json b/oaitestdata/clarin-oai_dc/SET_1/json/9e24be7e-d604-5854-a3d7-5fae346b86ff.json
deleted file mode 100644
index 2b83b958..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9e24be7e-d604-5854-a3d7-5fae346b86ff.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2847",
-    "MetadataAccess": [
-        "oai:ota:oucs:2847"
-    ],
-    "PublicationTimestamp": "1730-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1730"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2847;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2847.xml;A vindication of his Excellency the Lord Carteret;Swift, Jonathan, 1667-1745;1730;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9e24be7e-d604-5854-a3d7-5fae346b86ff",
-    "oai_identifier": [
-        "oai:ota:oucs:2847"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A vindication of his Excellency the Lord Carteret"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2847.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9e3141ef-ee8c-5804-a4b4-a05ab3cbd88c.json b/oaitestdata/clarin-oai_dc/SET_1/json/9e3141ef-ee8c-5804-a4b4-a05ab3cbd88c.json
deleted file mode 100644
index 7ada1bf2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9e3141ef-ee8c-5804-a4b4-a05ab3cbd88c.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 61.5 KB)"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2408",
-    "MetadataAccess": [
-        "oai:ota:oucs:2408"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Euripides"
-    ],
-    "fulltext": "oai:ota:oucs:2408;2018-07-27T14:11:29Z;http://ota.ox.ac.uk/headers/2408.xml;The Electra of Euripides;Euripides;default: 1976-01-01;text_and_corpus_linguistics;Plays -- B.C.;grc;Oxford Text Archive, University of Oxford;(1 file : ca. 61.5 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9e3141ef-ee8c-5804-a4b4-a05ab3cbd88c",
-    "oai_identifier": [
-        "oai:ota:oucs:2408"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- B.C."
-        }
-    ],
-    "title": [
-        "The Electra of Euripides"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2408.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9e31b41e-6557-5e3b-87b1-eac9e22e674a.json b/oaitestdata/clarin-oai_dc/SET_1/json/9e31b41e-6557-5e3b-87b1-eac9e22e674a.json
deleted file mode 100644
index 17959a49..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9e31b41e-6557-5e3b-87b1-eac9e22e674a.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 4",
-        "application/pdf",
-        "text/plain",
-        "application/zip"
-    ],
-    "Language": [
-        "Danish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repository.clarin.dk:20.500.12115/21",
-    "MetadataAccess": [
-        "oai:repository.clarin.dk:20.500.12115/21"
-    ],
-    "PID": "http://hdl.handle.net/20.500.12115/21",
-    "PublicationTimestamp": "2008-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2008"
-    ],
-    "Publisher": [
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Pedersen, Bolette Sandford",
-        "Braasch, Anna",
-        "Olsen, Sussi",
-        "Navarretta, Costanza"
-    ],
-    "fulltext": "oai:repository.clarin.dk:20.500.12115/21;2018-06-28T13:26:54Z;hdl_20.500.12115_1;hdl_20.500.12115_3;STO morphology (v2) - csv format;Braasch, Anna;Olsen, Sussi;Navarretta, Costanza;Pedersen, Bolette Sandford;morphology;The STO (SprogTeknologisk Ordbase) lexicon is a comprehensive computational lexicon of Danish developed for NLP/HLT applications. The morphological layer of the lexicon , presented here in csv format, contains a vocabulary of 88.067 entries.\r\nSTO is created within the framework of a national collaborational project, initiated by Center for Language Technology (CST) in 2001-2004.;2008;lexicalConceptualResource;http://hdl.handle.net/20.500.12115/21;dan;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;PUB;text/plain; charset=utf-8;application/zip;text/plain;application/pdf;text/plain;downloadable_files_count: 4;Centre for Language Technology, NorS, University of Copenhagen;https://cst.ku.dk/sto_ordbase/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9e31b41e-6557-5e3b-87b1-eac9e22e674a",
-    "notes": [
-        "The STO (SprogTeknologisk Ordbase) lexicon is a comprehensive computational lexicon of Danish developed for NLP/HLT applications. The morphological layer of the lexicon , presented here in csv format, contains a vocabulary of 88.067 entries.\r\nSTO is created within the framework of a national collaborational project, initiated by Center for Language Technology (CST) in 2001-2004."
-    ],
-    "oai_identifier": [
-        "oai:repository.clarin.dk:20.500.12115/21"
-    ],
-    "oai_set": [
-        "hdl_20.500.12115_1",
-        "hdl_20.500.12115_3"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphology"
-        }
-    ],
-    "title": [
-        "STO morphology (v2) - csv format"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9e3cbe3c-6f9b-5bd9-8344-721df32f932f.json b/oaitestdata/clarin-oai_dc/SET_1/json/9e3cbe3c-6f9b-5bd9-8344-721df32f932f.json
deleted file mode 100644
index 110773ca..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9e3cbe3c-6f9b-5bd9-8344-721df32f932f.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=ed5ef28428e411e2a2aa782bcb074135b02879c356904512a60861bd38942eae",
-    "MetadataAccess": [
-        "ed5ef28428e411e2a2aa782bcb074135b02879c356904512a60861bd38942eae"
-    ],
-    "PublicationTimestamp": "2012-11-07T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "fulltext": "ed5ef28428e411e2a2aa782bcb074135b02879c356904512a60861bd38942eae;2018-11-15T16:39:45Z;toolService;toolService:tool;MaltParser;MaltParser is a system for data-driven dependency parsing, which can be used to induce a parsing model from treebank data and to parse new data using an induced model. MaltParser is developed by Johan Hall, Jens Nilsson and Joakim Nivre at V\u00c3\u00a4xj\u00c3\u00b6 University and Uppsala University, Sweden (see Nivre et al. 2006).\n\nMaltParser 1.0.0 and later releases constitute a complete reimplementation of MaltParser in Java and are distributed with an open source license. The previous versions 0.1-0.4 of MaltParser were implemented in C. The Java implementation (version 1.0.0 and later releases) replaces the C implementation (version 0.x) and MaltParser 0.x will not be supported and updated any more. \n\nMaltParser can be characterized as a data-driven parser-generator. While a traditional parser-generator constructs a parser given a grammar, a data-driven parser-generator constructs a parser given a treebank. MaltParser is an implementation of inductive dependency parsing, where the syntactic analysis of a sentence amounts to the derivation of a dependency structure, and where inductive machine learning is used to guide the parser at nondeterministic choice points (Nivre, 2006). The parsing methodology is based on three essential components: \n\n-\tDeterministic parsing algorithms for building labeled dependency graphs (Kudo and Matsumoto, 2002; Yamada and Matsumoto, 2003; Nivre, 2003) \n-\tHistory-based models for predicting the next parser action at nondeterministic choice points (Black et al., 1992; Magerman, 1995; Ratnaparkhi, 1997; Collins, 1999) \n-\tDiscriminative learning to map histories to parser actions (Kudo and Matsumoto, 2002; Yamada and Matsumoto, 2003; Nivre et al., 2004; Hall et al., 2006) \n;2012-11-07",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9e3cbe3c-6f9b-5bd9-8344-721df32f932f",
-    "notes": [
-        "MaltParser is a system for data-driven dependency parsing, which can be used to induce a parsing model from treebank data and to parse new data using an induced model. MaltParser is developed by Johan Hall, Jens Nilsson and Joakim Nivre at V\u00c3\u00a4xj\u00c3\u00b6 University and Uppsala University, Sweden (see Nivre et al. 2006).\n\nMaltParser 1.0.0 and later releases constitute a complete reimplementation of MaltParser in Java and are distributed with an open source license. The previous versions 0.1-0.4 of MaltParser were implemented in C. The Java implementation (version 1.0.0 and later releases) replaces the C implementation (version 0.x) and MaltParser 0.x will not be supported and updated any more. \n\nMaltParser can be characterized as a data-driven parser-generator. While a traditional parser-generator constructs a parser given a grammar, a data-driven parser-generator constructs a parser given a treebank. MaltParser is an implementation of inductive dependency parsing, where the syntactic analysis of a sentence amounts to the derivation of a dependency structure, and where inductive machine learning is used to guide the parser at nondeterministic choice points (Nivre, 2006). The parsing methodology is based on three essential components: \n\n-\tDeterministic parsing algorithms for building labeled dependency graphs (Kudo and Matsumoto, 2002; Yamada and Matsumoto, 2003; Nivre, 2003) \n-\tHistory-based models for predicting the next parser action at nondeterministic choice points (Black et al., 1992; Magerman, 1995; Ratnaparkhi, 1997; Collins, 1999) \n-\tDiscriminative learning to map histories to parser actions (Kudo and Matsumoto, 2002; Yamada and Matsumoto, 2003; Nivre et al., 2004; Hall et al., 2006) \n"
-    ],
-    "oai_identifier": [
-        "ed5ef28428e411e2a2aa782bcb074135b02879c356904512a60861bd38942eae"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "MaltParser"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9e51cee6-933f-52f0-9957-9d5d808c7548.json b/oaitestdata/clarin-oai_dc/SET_1/json/9e51cee6-933f-52f0-9957-9d5d808c7548.json
deleted file mode 100644
index d82d0e53..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9e51cee6-933f-52f0-9957-9d5d808c7548.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "Fondazione Bruno Kessler, Trento, Italy"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "English",
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2613",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2613"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2613",
-    "PublicationTimestamp": "2018-02-12T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Fondazione Bruno Kessler, Trento, Italy"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/H2020/645452"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "AGREEMENT ON THE USE OF DATA IN QT21 APE Task",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21",
-        "PUB"
-    ],
-    "author": [
-        "Turchi, Marco",
-        "Chatterjee, Rajen",
-        "Negri, Matteo"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2613;2018-02-12T15:27:42Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;WMT18  APE Shared Task: En-DE NMT Train and Dev Data;Turchi, Marco;Negri, Matteo;Chatterjee, Rajen;machine translation;shared task;post-editing;automatic post-editing;Training and development data for the WMT 2018 Automatic post-editing task. They consist in English-German triplets (source, target and post-edit) belonging to the information technology domain and already tokenized. Training and development respectively contain 13,442 and 1,000 triplets. A neural machine translation system has been used to generate the target segments. All data is provided by the EU project QT21 (http://www.qt21.eu/).;2018-02-12;corpus;http://hdl.handle.net/11372/LRT-2613;eng;deu;info:eu-repo/grantAgreement/EC/H2020/645452;AGREEMENT ON THE USE OF DATA IN QT21 APE Task;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21;PUB;text/plain; charset=utf-8;application/x-gzip;downloadable_files_count: 1;Fondazione Bruno Kessler, Trento, Italy;http://www.statmt.org/wmt18/ape-task.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9e51cee6-933f-52f0-9957-9d5d808c7548",
-    "notes": [
-        "Training and development data for the WMT 2018 Automatic post-editing task. They consist in English-German triplets (source, target and post-edit) belonging to the information technology domain and already tokenized. Training and development respectively contain 13,442 and 1,000 triplets. A neural machine translation system has been used to generate the target segments. All data is provided by the EU project QT21 (http://www.qt21.eu/)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2613"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "shared task"
-        },
-        {
-            "name": "post-editing"
-        },
-        {
-            "name": "automatic post-editing"
-        }
-    ],
-    "title": [
-        "WMT18  APE Shared Task: En-DE NMT Train and Dev Data"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9e6ef0c7-3cc5-5632-bca8-a904d42e1f9f.json b/oaitestdata/clarin-oai_dc/SET_1/json/9e6ef0c7-3cc5-5632-bca8-a904d42e1f9f.json
deleted file mode 100644
index 63e445b4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9e6ef0c7-3cc5-5632-bca8-a904d42e1f9f.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "text/plain"
-    ],
-    "Language": [
-        "Slovak"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-AADB-7",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-AADB-7"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0006-AADB-7",
-    "PublicationTimestamp": "2012-05-15T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/231720"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Galu\u0161\u010d\u00e1kov\u00e1, Petra",
-        "Bojar, Ond\u0159ej"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-AADB-7;2018-07-02T22:05:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Manually Classified Errors in Cs->Sk Translation;Galu\u0161\u010d\u00e1kov\u00e1, Petra;Bojar, Ond\u0159ej;machine translation;errors classification;CS-SK translation;Manual classification of errors of Czech-Slovak translation according to the classification introduced by Vilar et al. [1]. First 50 sentences from WMT 2010 test set were translated by 5 MT systems (\u010ces\u00edlko, \u010ces\u00edlko2,  Google Translate and two Moses setups) and MT errors were manually marked and classified. Classification was applied in MT systems comparison [3]. Reference translation is included.\r\n\r\nReferences: \r\n[1] David Vilar, Jia Xu, Luis Fernando D\u2019Haro and Hermann Ney. Error Analysis of Machine Translation Output. In International Conference on Language Resources and Evaluation, pages 697-702. Genoa, Italy, May 2006.\r\n[2] http://matrix.statmt.org/test_sets/list\r\n[3] Ond\u0159ej Bojar, Petra Galu\u0161\u010d\u00e1kov\u00e1, and Miroslav T\u00fdnovsk\u00fd. Evaluating Quality of Machine Translation from Czech to Slovak. In Mark\u00e9ta Lopatkov\u00e1, editor, Information Technologies - Applications and Theory, pages 3-9, September 2011;2012-05-15;lexicalConceptualResource;http://hdl.handle.net/11858/00-097C-0000-0006-AADB-7;slk;info:eu-repo/grantAgreement/EC/FP7/231720;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;text/plain;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9e6ef0c7-3cc5-5632-bca8-a904d42e1f9f",
-    "notes": [
-        "Manual classification of errors of Czech-Slovak translation according to the classification introduced by Vilar et al. [1]. First 50 sentences from WMT 2010 test set were translated by 5 MT systems (\u010ces\u00edlko, \u010ces\u00edlko2,  Google Translate and two Moses setups) and MT errors were manually marked and classified. Classification was applied in MT systems comparison [3]. Reference translation is included.\r\n\r\nReferences: \r\n[1] David Vilar, Jia Xu, Luis Fernando D\u2019Haro and Hermann Ney. Error Analysis of Machine Translation Output. In International Conference on Language Resources and Evaluation, pages 697-702. Genoa, Italy, May 2006.\r\n[2] http://matrix.statmt.org/test_sets/list\r\n[3] Ond\u0159ej Bojar, Petra Galu\u0161\u010d\u00e1kov\u00e1, and Miroslav T\u00fdnovsk\u00fd. Evaluating Quality of Machine Translation from Czech to Slovak. In Mark\u00e9ta Lopatkov\u00e1, editor, Information Technologies - Applications and Theory, pages 3-9, September 2011"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-AADB-7"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "errors classification"
-        },
-        {
-            "name": "CS-SK translation"
-        }
-    ],
-    "title": [
-        "Manually Classified Errors in Cs->Sk Translation"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9e9d2b8f-c638-50bb-bc45-8feb69da222a.json b/oaitestdata/clarin-oai_dc/SET_1/json/9e9d2b8f-c638-50bb-bc45-8feb69da222a.json
deleted file mode 100644
index 623f8bac..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9e9d2b8f-c638-50bb-bc45-8feb69da222a.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5526",
-    "MetadataAccess": [
-        "oai:ota:oucs:5526"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Borthwick, George."
-    ],
-    "fulltext": "oai:ota:oucs:5526;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5526.xml;The method of preventing and removing the causes of infectious diseases: written in plain simple language, by George Borthwick, ...;Borthwick, George.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9e9d2b8f-c638-50bb-bc45-8feb69da222a",
-    "oai_identifier": [
-        "oai:ota:oucs:5526"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The method of preventing and removing the causes of infectious diseases: written in plain simple language, by George Borthwick, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5526.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9ea96d4b-f5f3-504a-916f-7280f2f781ef.json b/oaitestdata/clarin-oai_dc/SET_1/json/9ea96d4b-f5f3-504a-916f-7280f2f781ef.json
deleted file mode 100644
index 9035e3c0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9ea96d4b-f5f3-504a-916f-7280f2f781ef.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Universit\u00e4t Mannheim"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1135",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1135"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1135",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Universit\u00e4t Mannheim"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1135;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Mannheimer Texte Online (MATEO);Germanistik;As a sub-section of MATEO, MARABU (Mannheimer Reihe Altes Buch) includes illustrated books, (manu)scripts and texts on the history of the Electoral Palatinate. Als Unterkategorie von MATEO beinhaltet MARABU (Mannheimer Reihe Altes Buch) illustrierte B\u00fccher, Handschriften und Rarissima, Quellen zur Geschichte der Kurpfalz sowie Beitr\u00e4ge \u00fcber Frauen des Humanismus.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1135;deu;lat;downloadable_files_count: 0;Germany;Universit\u00e4t Mannheim;http://www.uni-mannheim.de/mateo/epo.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9ea96d4b-f5f3-504a-916f-7280f2f781ef",
-    "notes": [
-        "As a sub-section of MATEO, MARABU (Mannheimer Reihe Altes Buch) includes illustrated books, (manu)scripts and texts on the history of the Electoral Palatinate. Als Unterkategorie von MATEO beinhaltet MARABU (Mannheimer Reihe Altes Buch) illustrierte B\u00fccher, Handschriften und Rarissima, Quellen zur Geschichte der Kurpfalz sowie Beitr\u00e4ge \u00fcber Frauen des Humanismus."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1135"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Mannheimer Texte Online (MATEO)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9eb44325-3708-574f-a0da-4e8ccff2aa66.json b/oaitestdata/clarin-oai_dc/SET_1/json/9eb44325-3708-574f-a0da-4e8ccff2aa66.json
deleted file mode 100644
index f29df2bd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9eb44325-3708-574f-a0da-4e8ccff2aa66.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "English",
-        "Tamil"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1454",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1454"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1454",
-    "PublicationTimestamp": "2014-10-31T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "Bojar, Ond\u0159ej",
-        "Ramasamy, Loganathan"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1454;2018-07-02T22:05:53Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;EnTam: An English-Tamil Parallel Corpus (EnTam v2.0);Ramasamy, Loganathan;Bojar, Ond\u0159ej;\u017dabokrtsk\u00fd, Zden\u011bk;parallel corpus;EnTam is a sentence aligned English-Tamil bilingual corpus from some of the publicly available websites that we have collected for NLP research involving Tamil. The standard set of processing has been applied on the the raw web data before the data became available in sentence aligned English-Tamil parallel corpus suitable for various NLP tasks. The parallel corpus includes texts from bible, cinema and news domains.;2014-10-31;corpus;http://hdl.handle.net/11234/1-1454;eng;tam;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/~ramasamy/parallel/html/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9eb44325-3708-574f-a0da-4e8ccff2aa66",
-    "notes": [
-        "EnTam is a sentence aligned English-Tamil bilingual corpus from some of the publicly available websites that we have collected for NLP research involving Tamil. The standard set of processing has been applied on the the raw web data before the data became available in sentence aligned English-Tamil parallel corpus suitable for various NLP tasks. The parallel corpus includes texts from bible, cinema and news domains."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1454"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parallel corpus"
-        }
-    ],
-    "title": [
-        "EnTam: An English-Tamil Parallel Corpus (EnTam v2.0)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9f1a425d-bdb1-5171-94bf-6c77d8e70a5b.json b/oaitestdata/clarin-oai_dc/SET_1/json/9f1a425d-bdb1-5171-94bf-6c77d8e70a5b.json
deleted file mode 100644
index 251c775e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9f1a425d-bdb1-5171-94bf-6c77d8e70a5b.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Reymont"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 5",
-        "application/zip",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/90",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/90"
-    ],
-    "PID": "http://hdl.handle.net/11321/90",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Reymont"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Reymont, Reymont"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/90;2015-04-14T12:59:43Z;hdl_11321_3;hdl_11321_4;MWE Reymont;Reymont, Reymont;Reymont;2015-04-08;corpus;http://hdl.handle.net/11321/90;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 5;Reymont",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9f1a425d-bdb1-5171-94bf-6c77d8e70a5b",
-    "notes": [
-        "Reymont"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/90"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Reymont"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9f1e21ed-143b-5b8e-9c7b-2838424053b5.json b/oaitestdata/clarin-oai_dc/SET_1/json/9f1e21ed-143b-5b8e-9c7b-2838424053b5.json
deleted file mode 100644
index ef81f903..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9f1e21ed-143b-5b8e-9c7b-2838424053b5.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "application/octet-stream",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/598",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/598"
-    ],
-    "PID": "http://hdl.handle.net/11321/598",
-    "PublicationTimestamp": "2018-09-07T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "Marci\u0144czuk, Micha\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/598;2018-09-07T09:44:42Z;hdl_11321_3;hdl_11321_4;Liner2.6 model NER NKJP;Marci\u0144czuk, Micha\u0142;NER;Liner2;information extraction;named entities;Liner2.6 NER NKJP model\r\n\r\nThe package contains a pre-trained Liner2 (https://github.com/CLARIN-PL/Liner2) model for recognition named entities according to NKJP guidelines. The model was trained on the NKJP corpus (http://nkjp.pl/) and evaluated in the PolEval 2018 Task 2 (http://poleval.pl/tasks/).\r\n\r\nThe model won third place with the following results: Exact \u2014 0.778, Overlap \u2014 0.818, Final \u2014 0.810.\r\n\r\nReferences:\r\n* NKJP corpus in TEI format \u2014 http://clip.ipipan.waw.pl/NationalCorpusOfPolish?action=AttachFile&do=view&target=NKJP-PodkorpusMilionowy-1.2.tar.gz\r\n* PolEval 2018 Task 2 evaluation corpus \u2014 http://mozart.ipipan.waw.pl/~axw/poleval2018/;2018-09-07;toolService;http://hdl.handle.net/11321/598;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/zip;application/octet-stream;downloadable_files_count: 2;Wroc\u0142aw University of Science and Technology;https://github.com/CLARIN-PL/Liner2",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9f1e21ed-143b-5b8e-9c7b-2838424053b5",
-    "notes": [
-        "Liner2.6 NER NKJP model\r\n\r\nThe package contains a pre-trained Liner2 (https://github.com/CLARIN-PL/Liner2) model for recognition named entities according to NKJP guidelines. The model was trained on the NKJP corpus (http://nkjp.pl/) and evaluated in the PolEval 2018 Task 2 (http://poleval.pl/tasks/).\r\n\r\nThe model won third place with the following results: Exact \u2014 0.778, Overlap \u2014 0.818, Final \u2014 0.810.\r\n\r\nReferences:\r\n* NKJP corpus in TEI format \u2014 http://clip.ipipan.waw.pl/NationalCorpusOfPolish?action=AttachFile&do=view&target=NKJP-PodkorpusMilionowy-1.2.tar.gz\r\n* PolEval 2018 Task 2 evaluation corpus \u2014 http://mozart.ipipan.waw.pl/~axw/poleval2018/"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/598"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "NER"
-        },
-        {
-            "name": "Liner"
-        },
-        {
-            "name": "information extraction"
-        },
-        {
-            "name": "named entities"
-        }
-    ],
-    "title": [
-        "Liner2.6 model NER NKJP"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9f435c41-2c72-5484-b88f-b48ad37f3bd7.json b/oaitestdata/clarin-oai_dc/SET_1/json/9f435c41-2c72-5484-b88f-b48ad37f3bd7.json
deleted file mode 100644
index a025de0f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9f435c41-2c72-5484-b88f-b48ad37f3bd7.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5187",
-    "MetadataAccess": [
-        "oai:ota:oucs:5187"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Inchbald, Mrs., 1753-1821."
-    ],
-    "fulltext": "oai:ota:oucs:5187;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5187.xml;A simple story: In four volumes. By Mrs. Inchbald. [pt.2];Inchbald, Mrs., 1753-1821.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9f435c41-2c72-5484-b88f-b48ad37f3bd7",
-    "oai_identifier": [
-        "oai:ota:oucs:5187"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A simple story: In four volumes. By Mrs. Inchbald. [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5187.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9f46458b-b6e4-5846-9412-e4aeb45a94b1.json b/oaitestdata/clarin-oai_dc/SET_1/json/9f46458b-b6e4-5846-9412-e4aeb45a94b1.json
deleted file mode 100644
index d4d81243..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9f46458b-b6e4-5846-9412-e4aeb45a94b1.json
+++ /dev/null
@@ -1,98 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 3",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Croatian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1183",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1183"
-    ],
-    "PID": "http://hdl.handle.net/11356/1183",
-    "PublicationTimestamp": "2018-04-13T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "http://www.lrec-conf.org/proceedings/lrec2016/summaries/340.html"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by-sa/4.0/"
-    ],
-    "author": [
-        "Agi\u0107, \u017deljko",
-        "Klubi\u010dka, Filip",
-        "Ljube\u0161i\u0107, Nikola",
-        "Erjavec, Toma\u017e",
-        "Batanovi\u0107, Vuk"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1183;2018-10-24T20:55:11Z;hdl_11356_1023;hdl_11356_1024;Training corpus hr500k 1.0;Ljube\u0161i\u0107, Nikola;Agi\u0107, \u017deljko;Klubi\u010dka, Filip;Batanovi\u0107, Vuk;Erjavec, Toma\u017e;tagging;dependency treebank;parsing;named entities;tokenisation;manual annotation;TEI;semantic role labelling;The hr500k training corpus contains about 500,000 tokens manually annotated on the levels of tokenisation, sentence segmentation, morphosyntactic tagging, lemmatisation and named entities. About half of the corpus is also manually annotated with syntactic dependencies. Furthermore, about a fifth of the corpus is annotated with semantic role labels.\r\n\r\nThe annotations (and other aspects) of the hr500k corpus are documented in the teiHeader and back element of the TEI encoded corpus. In short, they follow (1) the MULTEXT-East V5 morphosyntactic specifications for Croatian, http://nl.ijs.si/ME/V5/msd/, (2) the UDv2 Guidelines, http://universaldependencies.org/guidelines.html, and (3) the Janes annotation guidelines for named entities, http://nl.ijs.si/janes/wp-content/uploads/2017/09/SlovenianNER-eng-v1.1.pdf, while (4) the semantic role labelling annotation guidelines are currently in the publication process.;2018-04-13;corpus;http://hdl.handle.net/11356/1183;hrv;http://www.lrec-conf.org/proceedings/lrec2016/summaries/340.html;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);PUB;https://creativecommons.org/licenses/by-sa/4.0/;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 3;Jo\u017eef Stefan Institute;https://github.com/nljubesi/hr500k",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9f46458b-b6e4-5846-9412-e4aeb45a94b1",
-    "notes": [
-        "The hr500k training corpus contains about 500,000 tokens manually annotated on the levels of tokenisation, sentence segmentation, morphosyntactic tagging, lemmatisation and named entities. About half of the corpus is also manually annotated with syntactic dependencies. Furthermore, about a fifth of the corpus is annotated with semantic role labels.\r\n\r\nThe annotations (and other aspects) of the hr500k corpus are documented in the teiHeader and back element of the TEI encoded corpus. In short, they follow (1) the MULTEXT-East V5 morphosyntactic specifications for Croatian, http://nl.ijs.si/ME/V5/msd/, (2) the UDv2 Guidelines, http://universaldependencies.org/guidelines.html, and (3) the Janes annotation guidelines for named entities, http://nl.ijs.si/janes/wp-content/uploads/2017/09/SlovenianNER-eng-v1.1.pdf, while (4) the semantic role labelling annotation guidelines are currently in the publication process."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1183"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "dependency treebank"
-        },
-        {
-            "name": "parsing"
-        },
-        {
-            "name": "named entities"
-        },
-        {
-            "name": "tokenisation"
-        },
-        {
-            "name": "manual annotation"
-        },
-        {
-            "name": "TEI"
-        },
-        {
-            "name": "semantic role labelling"
-        }
-    ],
-    "title": [
-        "Training corpus hr500k 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9f4b8d93-32c3-5b13-b50c-94c2464a0bdb.json b/oaitestdata/clarin-oai_dc/SET_1/json/9f4b8d93-32c3-5b13-b50c-94c2464a0bdb.json
deleted file mode 100644
index 90a39de3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9f4b8d93-32c3-5b13-b50c-94c2464a0bdb.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/278",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/278"
-    ],
-    "PID": "http://hdl.handle.net/11321/278",
-    "PublicationTimestamp": "2016-06-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "K\u0119dzia, Pawe\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/278;2016-06-03T12:25:24Z;hdl_11321_3;hdl_11321_4;Saper;K\u0119dzia, Pawe\u0142;Saper;Shallow semantic parser;Semantic parser;Shallow semantic parser for polish texts processing. Contains word sense disambiguation, mapping go SUMO concepts and semantic role labelling.;2016-06-01;toolService;http://hdl.handle.net/11321/278;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 1;Wroc\u0142aw University of Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9f4b8d93-32c3-5b13-b50c-94c2464a0bdb",
-    "notes": [
-        "Shallow semantic parser for polish texts processing. Contains word sense disambiguation, mapping go SUMO concepts and semantic role labelling."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/278"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Saper"
-        },
-        {
-            "name": "Shallow semantic parser"
-        },
-        {
-            "name": "Semantic parser"
-        }
-    ],
-    "title": [
-        "Saper"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9f780d17-9fb1-5278-af7b-0b41fa161877.json b/oaitestdata/clarin-oai_dc/SET_1/json/9f780d17-9fb1-5278-af7b-0b41fa161877.json
deleted file mode 100644
index cf752d22..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9f780d17-9fb1-5278-af7b-0b41fa161877.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3738",
-    "MetadataAccess": [
-        "oai:ota:oucs:3738"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hoadly, Benjamin, 1676-1761."
-    ],
-    "fulltext": "oai:ota:oucs:3738;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3738.xml;The nature of the kingdom, or church, of Christ: A sermon preach'd before the King, at the Royal chapel at St. James's, on Sunday March 31, 1717. By ... Benjamin Lord Bishop of Bangor. ...;Hoadly, Benjamin, 1676-1761.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9f780d17-9fb1-5278-af7b-0b41fa161877",
-    "oai_identifier": [
-        "oai:ota:oucs:3738"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The nature of the kingdom, or church, of Christ: A sermon preach'd before the King, at the Royal chapel at St. James's, on Sunday March 31, 1717. By ... Benjamin Lord Bishop of Bangor. ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3738.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9f8d7ec9-9e89-5a97-bb6c-5136b8a32ea5.json b/oaitestdata/clarin-oai_dc/SET_1/json/9f8d7ec9-9e89-5a97-bb6c-5136b8a32ea5.json
deleted file mode 100644
index 640a6aed..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9f8d7ec9-9e89-5a97-bb6c-5136b8a32ea5.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Charles University, UFAL"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "text/plain",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2864",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2864"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2864",
-    "PublicationTimestamp": "2018-10-23T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Charles University, UFAL"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-2509"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Nov\u00e1k, Michal",
-        "M\u00edrovsk\u00fd, Ji\u0159\u00ed",
-        "Haji\u010dov\u00e1, Eva",
-        "Rysov\u00e1, Magdal\u00e9na",
-        "Rysov\u00e1, Kate\u0159ina"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2864;2018-10-23T16:43:28Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;EVALD 3.0 for Foreigners \u2013 Evaluator of Discourse;M\u00edrovsk\u00fd, Ji\u0159\u00ed;Nov\u00e1k, Michal;Rysov\u00e1, Kate\u0159ina;Rysov\u00e1, Magdal\u00e9na;Haji\u010dov\u00e1, Eva;text coherence;discourse;automatic evaluation;non-native speakers;EVALD 3.0 for Foreigners is a software for automatic evaluation of surface coherence (cohesion) in Czech texts written by non-native speakers of Czech.;2018-10-23;toolService;http://hdl.handle.net/11234/1-2864;ces;http://hdl.handle.net/11234/1-2509;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;text/plain;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University, UFAL;https://ufal.mff.cuni.cz/evald",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9f8d7ec9-9e89-5a97-bb6c-5136b8a32ea5",
-    "notes": [
-        "EVALD 3.0 for Foreigners is a software for automatic evaluation of surface coherence (cohesion) in Czech texts written by non-native speakers of Czech."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2864"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "text coherence"
-        },
-        {
-            "name": "discourse"
-        },
-        {
-            "name": "automatic evaluation"
-        },
-        {
-            "name": "non-native speakers"
-        }
-    ],
-    "title": [
-        "EVALD 3.0 for Foreigners \u2013 Evaluator of Discourse"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9fa64c01-3e3a-51e8-a473-705c8d264905.json b/oaitestdata/clarin-oai_dc/SET_1/json/9fa64c01-3e3a-51e8-a473-705c8d264905.json
deleted file mode 100644
index 565ca173..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9fa64c01-3e3a-51e8-a473-705c8d264905.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 583 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2141",
-    "MetadataAccess": [
-        "oai:ota:oucs:2141"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Elyot, Thomas, Sir, 1490?-1546"
-    ],
-    "fulltext": "oai:ota:oucs:2141;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/2141.xml;The boke named The gouernour / by Thomas Elyot;Elyot, Thomas, Sir, 1490?-1546;text_and_corpus_linguistics;Academic dissertations -- England -- 16th century;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 583 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9fa64c01-3e3a-51e8-a473-705c8d264905",
-    "oai_identifier": [
-        "oai:ota:oucs:2141"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Academic dissertations -- England -- th century"
-        }
-    ],
-    "title": [
-        "The boke named The gouernour / by Thomas Elyot"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2141.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9fbb5a76-e068-5cd9-9807-2d5104909b77.json b/oaitestdata/clarin-oai_dc/SET_1/json/9fbb5a76-e068-5cd9-9807-2d5104909b77.json
deleted file mode 100644
index a0662a29..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9fbb5a76-e068-5cd9-9807-2d5104909b77.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Mostowicz"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 6",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/86",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/86"
-    ],
-    "PID": "http://hdl.handle.net/11321/86",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Mostowicz"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Mostowicz, Mostowicz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/86;2015-05-19T13:40:13Z;hdl_11321_3;hdl_11321_4;MWE Mostowicz;Mostowicz, Mostowicz;Mostowicz;2015-04-08;corpus;http://hdl.handle.net/11321/86;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 6;Mostowicz",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9fbb5a76-e068-5cd9-9807-2d5104909b77",
-    "notes": [
-        "Mostowicz"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/86"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Mostowicz"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9fc60268-802e-5be1-ad66-883e0812c759.json b/oaitestdata/clarin-oai_dc/SET_1/json/9fc60268-802e-5be1-ad66-883e0812c759.json
deleted file mode 100644
index 0304d364..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9fc60268-802e-5be1-ad66-883e0812c759.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-933",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-933"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-933",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-933;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Old Czech;ca. 50.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-933;ces;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#acech",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9fc60268-802e-5be1-ad66-883e0812c759",
-    "notes": [
-        "ca. 50.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-933"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Old Czech"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9fd0a24c-bf77-519c-b02c-4d53545aaaee.json b/oaitestdata/clarin-oai_dc/SET_1/json/9fd0a24c-bf77-519c-b02c-4d53545aaaee.json
deleted file mode 100644
index 9d08b71a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9fd0a24c-bf77-519c-b02c-4d53545aaaee.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Universit\u00e4t Basel"
-    ],
-    "Contributor": [
-        "Buhofer, Prof. Dr. Annelies H\u00e4cki"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1151",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1151"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1151",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Universit\u00e4t Basel"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Switzerland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1151;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Online-Lexikon zur diachronen Phraseologie;Buhofer, Prof. Dr. Annelies H\u00e4cki;Germanistik;Dokumentation von neuhochdeutschen Sprichw\u00f6rtern und Redewendungen;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1151;deu;downloadable_files_count: 0;Switzerland;Universit\u00e4t Basel;http://oldphras.unibas.ch/GetSimple_3.0/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9fd0a24c-bf77-519c-b02c-4d53545aaaee",
-    "notes": [
-        "Dokumentation von neuhochdeutschen Sprichw\u00f6rtern und Redewendungen"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1151"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Online-Lexikon zur diachronen Phraseologie"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9fe95a4e-9369-5606-a4ac-7752a2cb8bce.json b/oaitestdata/clarin-oai_dc/SET_1/json/9fe95a4e-9369-5606-a4ac-7752a2cb8bce.json
deleted file mode 100644
index b6a5cfb6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9fe95a4e-9369-5606-a4ac-7752a2cb8bce.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3308",
-    "MetadataAccess": [
-        "oai:ota:oucs:3308"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Jones, Henry, 1721-1770."
-    ],
-    "fulltext": "oai:ota:oucs:3308;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3308.xml;The bricklayer's poem to the Countess of Chesterfield, on Her Ladyship's saving the soldiers from being shot;Jones, Henry, 1721-1770.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9fe95a4e-9369-5606-a4ac-7752a2cb8bce",
-    "oai_identifier": [
-        "oai:ota:oucs:3308"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The bricklayer's poem to the Countess of Chesterfield, on Her Ladyship's saving the soldiers from being shot"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3308.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9fec140b-9819-5a28-a087-680148ecb4ec.json b/oaitestdata/clarin-oai_dc/SET_1/json/9fec140b-9819-5a28-a087-680148ecb4ec.json
deleted file mode 100644
index 0c662fd1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9fec140b-9819-5a28-a087-680148ecb4ec.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Wikipedia"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2952",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/217",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/217"
-    ],
-    "PID": "http://hdl.handle.net/11321/217",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Wikipedia"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Wikipedia"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/217;2015-06-16T16:07:13Z;hdl_11321_3;hdl_11321_4;Wiki test - 34 categories;Wikipedia;Wikipedia, 34 kategorie - zbi\u00f3r do test\u00f3w klasyfikatora;2015;corpus;http://hdl.handle.net/11321/217;Polish;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/p",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9fec140b-9819-5a28-a087-680148ecb4ec",
-    "notes": [
-        "Wikipedia, 34 kategorie - zbi\u00f3r do test\u00f3w klasyfikatora"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/217"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Wiki test - 34 categories"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/9fed60e7-13e2-507e-b7ba-d74d29508b4b.json b/oaitestdata/clarin-oai_dc/SET_1/json/9fed60e7-13e2-507e-b7ba-d74d29508b4b.json
deleted file mode 100644
index 41801757..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/9fed60e7-13e2-507e-b7ba-d74d29508b4b.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "Irish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-950",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-950"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-950",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-950;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Old Irish;ca. 100.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-950;gle;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#air",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9fed60e7-13e2-507e-b7ba-d74d29508b4b",
-    "notes": [
-        "ca. 100.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-950"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Old Irish"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a00cc4c5-cb07-569a-acbe-8873c990dd31.json b/oaitestdata/clarin-oai_dc/SET_1/json/a00cc4c5-cb07-569a-acbe-8873c990dd31.json
deleted file mode 100644
index 7f3e7cd1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a00cc4c5-cb07-569a-acbe-8873c990dd31.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "Lithuanian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-931",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-931"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-931",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-931;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Lithuanian;ca. 50.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-931;lit;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#lit",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a00cc4c5-cb07-569a-acbe-8873c990dd31",
-    "notes": [
-        "ca. 50.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-931"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Lithuanian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a00e8b1c-6eaa-54e6-866b-516fcccfa311.json b/oaitestdata/clarin-oai_dc/SET_1/json/a00e8b1c-6eaa-54e6-866b-516fcccfa311.json
deleted file mode 100644
index 718abc80..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a00e8b1c-6eaa-54e6-866b-516fcccfa311.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=0b1d3fb6ee8511e4a2aa782bcb0741356f1c360cc2f949fab24226b691d2b6b8",
-    "MetadataAccess": [
-        "0b1d3fb6ee8511e4a2aa782bcb0741356f1c360cc2f949fab24226b691d2b6b8"
-    ],
-    "PublicationTimestamp": "2015-04-29T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "0b1d3fb6ee8511e4a2aa782bcb0741356f1c360cc2f949fab24226b691d2b6b8;2018-11-15T16:40:15Z;corpus;corpus:text;Europarl QTLeap WSD/NED corpus;Europarl QTLeap WSD/NED corpus\n\nThis corpora is part of Deliverable 5.5 of the European Commission project QTLeap FP7-ICT-2013.4.1-610516 (http://qtleap.eu). \n\nThe texts are sentences from the Europarl parallel corpus (Koehn, 2005). We selected the monolingual sentences from parallel corpora for the following pairs: Bulgarian-English, Czech-English, Portuguese-English and Spanish-English. The English corpus is comprised by the English side of the Spanish-English corpus. \n\nBasque is not in Europarl. In addition, it contains the Basque and English sides of the GNOME corpus.\n\nThe texts have been automatically annotated with NLP tools, including Word Sense Disambiguation, Named Entity Disambiguation and Coreference resolution. Please check deliverable D5.6 in http://qtleap.eu/deliverables for more information.\n\nInstitutions involved in the annotation:\n  University of the Basque Country (UPV/EHU)\n  Faculty of Science, Univeristy of Lisbon (FCUL)\n  Charles University in Prague (CUNI)\n  Bulgarian Academy of Sciences (IICT-BAS)\n;2015-04-29",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a00e8b1c-6eaa-54e6-866b-516fcccfa311",
-    "notes": [
-        "Europarl QTLeap WSD/NED corpus\n\nThis corpora is part of Deliverable 5.5 of the European Commission project QTLeap FP7-ICT-2013.4.1-610516 (http://qtleap.eu). \n\nThe texts are sentences from the Europarl parallel corpus (Koehn, 2005). We selected the monolingual sentences from parallel corpora for the following pairs: Bulgarian-English, Czech-English, Portuguese-English and Spanish-English. The English corpus is comprised by the English side of the Spanish-English corpus. \n\nBasque is not in Europarl. In addition, it contains the Basque and English sides of the GNOME corpus.\n\nThe texts have been automatically annotated with NLP tools, including Word Sense Disambiguation, Named Entity Disambiguation and Coreference resolution. Please check deliverable D5.6 in http://qtleap.eu/deliverables for more information.\n\nInstitutions involved in the annotation:\n  University of the Basque Country (UPV/EHU)\n  Faculty of Science, Univeristy of Lisbon (FCUL)\n  Charles University in Prague (CUNI)\n  Bulgarian Academy of Sciences (IICT-BAS)\n"
-    ],
-    "oai_identifier": [
-        "0b1d3fb6ee8511e4a2aa782bcb0741356f1c360cc2f949fab24226b691d2b6b8"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "Europarl QTLeap WSD/NED corpus"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a00fa4b1-f3a6-5c9a-ac59-6d315ee2fe58.json b/oaitestdata/clarin-oai_dc/SET_1/json/a00fa4b1-f3a6-5c9a-ac59-6d315ee2fe58.json
deleted file mode 100644
index eb15bee5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a00fa4b1-f3a6-5c9a-ac59-6d315ee2fe58.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Tilde"
-    ],
-    "Contributor": [
-        "Skadins, Raivis"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Latvian",
-        "Lithuanian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-475",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-475"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-475",
-    "PublicationTimestamp": "2006-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2006"
-    ],
-    "Publisher": [
-        "Tilde"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Latvia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-475;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Latvian-Lithuanian Web dictionary;Skadins, Raivis;The dictionary is based on Latvian-Lithuanian dictionary by A. Butkus, ~43 000 entries;2006;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-475;lav;lit;application/octet-stream;downloadable_files_count: 0;Latvia;Tilde;http://www.letonika.lv/groups/default.aspx?g=2&r=10621063&q=",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a00fa4b1-f3a6-5c9a-ac59-6d315ee2fe58",
-    "notes": [
-        "The dictionary is based on Latvian-Lithuanian dictionary by A. Butkus, ~43 000 entries"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-475"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Latvian-Lithuanian Web dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a02601c1-5b94-5301-9394-1975759409b1.json b/oaitestdata/clarin-oai_dc/SET_1/json/a02601c1-5b94-5301-9394-1975759409b1.json
deleted file mode 100644
index d154621d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a02601c1-5b94-5301-9394-1975759409b1.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish",
-        "Croatian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/58",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/58"
-    ],
-    "PID": "http://hdl.handle.net/10794/58",
-    "PublicationTimestamp": "2015-04-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/58;2017-10-31T12:33:22Z;hdl_10794_1;hdl_10794_2;ASPAC \u2013 Swedish-Croatian (2017-10-16);ASPAC \u2013 svenska-kroatiska (2017-10-16);n/a, n/a;ASPAC;Parallel;Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.;Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat.;2015-04-16;corpus;http://hdl.handle.net/10794/58;swe;hrv;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/octet-stream;application/gzip;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/aspacsvhr",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a02601c1-5b94-5301-9394-1975759409b1",
-    "notes": [
-        "Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.",
-        "Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/58"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ASPAC"
-        },
-        {
-            "name": "Parallel"
-        }
-    ],
-    "title": [
-        "ASPAC \u2013 Swedish-Croatian (2017-10-16)",
-        "ASPAC \u2013 svenska-kroatiska (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a02609dc-d2ab-5a49-8577-b191d1cd5bca.json b/oaitestdata/clarin-oai_dc/SET_1/json/a02609dc-d2ab-5a49-8577-b191d1cd5bca.json
deleted file mode 100644
index 80acbf3b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a02609dc-d2ab-5a49-8577-b191d1cd5bca.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "greater than 5 MB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0288",
-    "MetadataAccess": [
-        "oai:ota:oucs:0288"
-    ],
-    "PublicationTimestamp": "1983-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1983"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Dictionaries"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:0288;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0288.xml; Oxford dictionary of idiomatic English  / compiled by J.K. Cordy;1983;text_and_corpus_linguistics;Dictionaries -- 20th century;eng;Oxford Text Archive, University of Oxford;greater than 5 MB;Text;Dictionaries;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a02609dc-d2ab-5a49-8577-b191d1cd5bca",
-    "oai_identifier": [
-        "oai:ota:oucs:0288"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Dictionaries -- th century"
-        }
-    ],
-    "title": [
-        " Oxford dictionary of idiomatic English  / compiled by J.K. Cordy"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0288.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a02991ea-e7f5-5530-9531-5485f6e18da3.json b/oaitestdata/clarin-oai_dc/SET_1/json/a02991ea-e7f5-5530-9531-5485f6e18da3.json
deleted file mode 100644
index 7fc45e05..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a02991ea-e7f5-5530-9531-5485f6e18da3.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Wroclaw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish",
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/25",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/25"
-    ],
-    "PID": "http://hdl.handle.net/11321/25",
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Wroclaw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Radziszewski, Adam"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/25;2014-09-26T13:20:24Z;hdl_11321_3;hdl_11321_4;WCRFT - Wroc\u0142aw CRF Tagger;Radziszewski, Adam;WCRFT is a morphosyntactic tagger for Polish. The tagger brings together Conditional Random Fields (CRF) and tiered tagging. The code is written in C++ and uses following components: CRF++ classifier, WCCL: formalism for morphosyntactic feature generation (and its implementation), corpus2: a library for rapid NLP application development, supporting positional tagsets.;2011;toolService;http://hdl.handle.net/11321/25;pol;pol;application/octet-stream;downloadable_files_count: 0;Wroclaw University of Technology;http://w01.clarin-pl.eu:8080/weblichtWCRFT-1.0/annotate/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a02991ea-e7f5-5530-9531-5485f6e18da3",
-    "notes": [
-        "WCRFT is a morphosyntactic tagger for Polish. The tagger brings together Conditional Random Fields (CRF) and tiered tagging. The code is written in C++ and uses following components: CRF++ classifier, WCCL: formalism for morphosyntactic feature generation (and its implementation), corpus2: a library for rapid NLP application development, supporting positional tagsets."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/25"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "WCRFT - Wroc\u0142aw CRF Tagger"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a051bc6e-ec73-5000-bfd6-ea80dc0c7679.json b/oaitestdata/clarin-oai_dc/SET_1/json/a051bc6e-ec73-5000-bfd6-ea80dc0c7679.json
deleted file mode 100644
index abfd9d81..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a051bc6e-ec73-5000-bfd6-ea80dc0c7679.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 174 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2253",
-    "MetadataAccess": [
-        "oai:ota:oucs:2253"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Overbury, Thomas, Sir, 1581-1613"
-    ],
-    "fulltext": "oai:ota:oucs:2253;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/2253.xml;New and choice characters, of some seuerall authors : together with that exquisite and vnmatcht poem, The wife, written by Syr Thomas Overbury;Overbury, Thomas, Sir, 1581-1613;default: 1976-01-01;text_and_corpus_linguistics;Caricatures -- England -- 17th century;eng;Oxford Text Archive, University of Oxford;(1 file : ca. 174 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a051bc6e-ec73-5000-bfd6-ea80dc0c7679",
-    "oai_identifier": [
-        "oai:ota:oucs:2253"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Caricatures -- England -- th century"
-        }
-    ],
-    "title": [
-        "New and choice characters, of some seuerall authors : together with that exquisite and vnmatcht poem, The wife, written by Syr Thomas Overbury"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2253.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a061b963-67bb-51b7-b071-d51a2f7e47c4.json b/oaitestdata/clarin-oai_dc/SET_1/json/a061b963-67bb-51b7-b071-d51a2f7e47c4.json
deleted file mode 100644
index 01ba357a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a061b963-67bb-51b7-b071-d51a2f7e47c4.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Academia"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "text/plain"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2546",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2546"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2546",
-    "PublicationTimestamp": "2017-12-13T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Academia"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Pognan, Patrice",
-        "Slav\u00ed\u010dkov\u00e1, Eleonora",
-        "Hlav\u00e1\u010dov\u00e1, Jaroslava"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2546;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Retrograde Morphemic Dictionary of Czech - verbs;Slav\u00ed\u010dkov\u00e1, Eleonora;Hlav\u00e1\u010dov\u00e1, Jaroslava;Pognan, Patrice;morphemes;morphology;prefix;root;The file contains all Czech verbs included in the Retrograde Morphemic Dictionary of Czech Language (Slav\u00ed\u010dkov\u00e1 Eleonora, Academia 1975).\r\nThe data was obtained by scanning a portion of the dictionary that contains words ending in -ci and -ti. Among them, there were 18 non-verbs, which were removed. Using OCR, the data was converted into the plain text format and the result was checked by two independent readers. However, if a user encounters a forgotten error, please report.;2017-12-13;lexicalConceptualResource;http://hdl.handle.net/11234/1-2546;ces;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;text/plain;text/plain; charset=utf-8;downloadable_files_count: 1;Academia",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a061b963-67bb-51b7-b071-d51a2f7e47c4",
-    "notes": [
-        "The file contains all Czech verbs included in the Retrograde Morphemic Dictionary of Czech Language (Slav\u00ed\u010dkov\u00e1 Eleonora, Academia 1975).\r\nThe data was obtained by scanning a portion of the dictionary that contains words ending in -ci and -ti. Among them, there were 18 non-verbs, which were removed. Using OCR, the data was converted into the plain text format and the result was checked by two independent readers. However, if a user encounters a forgotten error, please report."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2546"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphemes"
-        },
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "prefix"
-        },
-        {
-            "name": "root"
-        }
-    ],
-    "title": [
-        "Retrograde Morphemic Dictionary of Czech - verbs"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a0719d66-0240-5d61-a504-56c384aafd17.json b/oaitestdata/clarin-oai_dc/SET_1/json/a0719d66-0240-5d61-a504-56c384aafd17.json
deleted file mode 100644
index 1070c7e7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a0719d66-0240-5d61-a504-56c384aafd17.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "British Academy and the University of Wales, Bangor"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3024",
-    "MetadataAccess": [
-        "oai:ota:oucs:3024"
-    ],
-    "PublicationTimestamp": "1671-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1671"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Milton, John, 1608-1674"
-    ],
-    "fulltext": "oai:ota:oucs:3024;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3024.xml;Paradise Regain'd. A poem in IV books. To\n\twhich is added Samson Agonistes. [1671]\n;Milton, John, 1608-1674;not after: 1671;text_and_corpus_linguistics;English poetry -- 17th century;eng;Oxford Text Archive, University of Oxford;British Academy and the University of Wales, Bangor;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a0719d66-0240-5d61-a504-56c384aafd17",
-    "oai_identifier": [
-        "oai:ota:oucs:3024"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English poetry -- th century"
-        }
-    ],
-    "title": [
-        "Paradise Regain'd. A poem in IV books. To\n\twhich is added Samson Agonistes. [1671]\n"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3024.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a072f9fc-fc1a-54b3-af28-79eff377c432.json b/oaitestdata/clarin-oai_dc/SET_1/json/a072f9fc-fc1a-54b3-af28-79eff377c432.json
deleted file mode 100644
index d3e576dd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a072f9fc-fc1a-54b3-af28-79eff377c432.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/268",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/268"
-    ],
-    "PID": "http://hdl.handle.net/11321/268",
-    "PublicationTimestamp": "2016-05-29T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "Sikora, Piotr"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/268;2016-05-31T07:44:10Z;hdl_11321_3;hdl_11321_4;Topos\u0142aw 2;Sikora, Piotr;inflection;multi-word units;Topos\u0142aw 2 is an editor of multi-world unit inflection lexicons.;2016-05-29;toolService;http://hdl.handle.net/11321/268;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 1;Institute of Computer Science, Polish Academy of Sciences;http://zil.ipipan.waw.pl/Toposlaw",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a072f9fc-fc1a-54b3-af28-79eff377c432",
-    "notes": [
-        "Topos\u0142aw 2 is an editor of multi-world unit inflection lexicons."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/268"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "inflection"
-        },
-        {
-            "name": "multi-word units"
-        }
-    ],
-    "title": [
-        "Topos\u0142aw 2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a07bbd24-a159-5a5c-81b2-a96065e64f31.json b/oaitestdata/clarin-oai_dc/SET_1/json/a07bbd24-a159-5a5c-81b2-a96065e64f31.json
deleted file mode 100644
index 587d2124..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a07bbd24-a159-5a5c-81b2-a96065e64f31.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=9354abc60b6311e5a2aa782bcb074135436e6026c8b94c6f94670c9f41f5f187",
-    "MetadataAccess": [
-        "9354abc60b6311e5a2aa782bcb074135436e6026c8b94c6f94670c9f41f5f187"
-    ],
-    "PublicationTimestamp": "2015-06-05T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "9354abc60b6311e5a2aa782bcb074135436e6026c8b94c6f94670c9f41f5f187;2018-11-15T16:40:15Z;toolService;toolService:tool;ixa-pipe-dep-eu;ixa-pipe-dep-eu is a Basque dependency parsing tool.\n\nIt is based on MATE-tools. This tool takes a document in Natural Language Processing Annotation Format (NAF) format (http://wordpress.let.vupr.nl/naf/) and outputs a new NAF document.\n\nThis tool is partly funded by the European Commission project QTLeap FP7-ICT-2013.4.1-610516 (http://qtleap.eu). This tool is distributed under the license GPL v3.0.;2015-06-05",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a07bbd24-a159-5a5c-81b2-a96065e64f31",
-    "notes": [
-        "ixa-pipe-dep-eu is a Basque dependency parsing tool.\n\nIt is based on MATE-tools. This tool takes a document in Natural Language Processing Annotation Format (NAF) format (http://wordpress.let.vupr.nl/naf/) and outputs a new NAF document.\n\nThis tool is partly funded by the European Commission project QTLeap FP7-ICT-2013.4.1-610516 (http://qtleap.eu). This tool is distributed under the license GPL v3.0."
-    ],
-    "oai_identifier": [
-        "9354abc60b6311e5a2aa782bcb074135436e6026c8b94c6f94670c9f41f5f187"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "ixa-pipe-dep-eu"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a07ffff3-282f-58d5-ae7a-ffe74a6413d6.json b/oaitestdata/clarin-oai_dc/SET_1/json/a07ffff3-282f-58d5-ae7a-ffe74a6413d6.json
deleted file mode 100644
index e5302b04..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a07ffff3-282f-58d5-ae7a-ffe74a6413d6.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "University of West Bohemia, Department of Cybernetics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 7",
-        "text/plain",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-000D-EC92-F",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-000D-EC92-F"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-000D-EC92-F",
-    "PublicationTimestamp": "2013-01-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "University of West Bohemia, Department of Cybernetics"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0)",
-        "http://creativecommons.org/licenses/by-nc/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u0160m\u00eddl, Lubo\u0161"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-000D-EC92-F;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;ATCC: Pronunciation lexicon and n-gram counts for ASR module;\u0160m\u00eddl, Lubo\u0161;pronunciation lexicon;n-gram counts;language model;The corpus contains pronunciation lexicon and n-gram counts (unigrams, bigrams and trigrams) that can be used for constructing the language model for air traffic control communication domain. It could be used together with the Air Traffic Control Communication corpus (http://hdl.handle.net/11858/00-097C-0000-0001-CCA1-0).;2013-01-01;lexicalConceptualResource;ZCU_CZ_ ATCC-LM4ASR;http://hdl.handle.net/11858/00-097C-0000-000D-EC92-F;eng;Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0);http://creativecommons.org/licenses/by-nc/3.0/;PUB;text/plain;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 7;University of West Bohemia, Department of Cybernetics",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a07ffff3-282f-58d5-ae7a-ffe74a6413d6",
-    "notes": [
-        "The corpus contains pronunciation lexicon and n-gram counts (unigrams, bigrams and trigrams) that can be used for constructing the language model for air traffic control communication domain. It could be used together with the Air Traffic Control Communication corpus (http://hdl.handle.net/11858/00-097C-0000-0001-CCA1-0)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-000D-EC92-F"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "pronunciation lexicon"
-        },
-        {
-            "name": "n-gram counts"
-        },
-        {
-            "name": "language model"
-        }
-    ],
-    "title": [
-        "ATCC: Pronunciation lexicon and n-gram counts for ASR module"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a098a9fd-de98-5a47-b519-387c25b643f6.json b/oaitestdata/clarin-oai_dc/SET_1/json/a098a9fd-de98-5a47-b519-387c25b643f6.json
deleted file mode 100644
index bb908bdf..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a098a9fd-de98-5a47-b519-387c25b643f6.json
+++ /dev/null
@@ -1,90 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Fisher, Jane L.",
-        "Fisher, John H.",
-        "Burnley, J. D."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 567 KB)"
-    ],
-    "Language": [
-        "Middle English (1100-1500)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1676",
-    "MetadataAccess": [
-        "oai:ota:oucs:1676"
-    ],
-    "PublicationTimestamp": "1384-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1384"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Anthologies"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:1676;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/1676.xml;An anthology of Chancery English / John H. Fisher, Malcolm Richardson [and] Jane L. Fisher;1384-1462;text_and_corpus_linguistics;English language -- Middle English, 1100-1500 -- Grammar;English language -- Middle English, 1100-1500 -- Texts;Great Britain -- Court and courtiers -- Language;Great Britain -- History -- Henry V, 1413-1422 -- Sources;Great Britain -- Officials and employees -- Language;Great Britain -- Politics and government -- 1399-1485;enm;Oxford Text Archive, University of Oxford;Fisher, Jane L.;Fisher, John H.;Burnley, J. D.;(1 file : ca. 567 KB);Text;Anthologies;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a098a9fd-de98-5a47-b519-387c25b643f6",
-    "oai_identifier": [
-        "oai:ota:oucs:1676"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English language -- Middle English"
-        },
-        {
-            "name": "- -- Grammar"
-        },
-        {
-            "name": "English language -- Middle English"
-        },
-        {
-            "name": "- -- Texts"
-        },
-        {
-            "name": "Great Britain -- Court courtiers -- Language"
-        },
-        {
-            "name": "Great Britain -- History -- Henry V"
-        },
-        {
-            "name": "- -- Sources"
-        },
-        {
-            "name": "Great Britain -- Officials employees -- Language"
-        },
-        {
-            "name": "Great Britain -- Politics government -- -"
-        }
-    ],
-    "title": [
-        "An anthology of Chancery English / John H. Fisher, Malcolm Richardson [and] Jane L. Fisher"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1676.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a09930b5-5456-50c7-b492-757e9278774d.json b/oaitestdata/clarin-oai_dc/SET_1/json/a09930b5-5456-50c7-b492-757e9278774d.json
deleted file mode 100644
index 216b8f27..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a09930b5-5456-50c7-b492-757e9278774d.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Katarzyna Giere\u0142o-Klimaszewska"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/492",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/492"
-    ],
-    "PID": "http://hdl.handle.net/11321/492",
-    "PublicationTimestamp": "2018-06-19T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Katarzyna Giere\u0142o-Klimaszewska"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Super Cool License",
-        "http://www.google.com",
-        "ACA"
-    ],
-    "author": [
-        "Giere\u0142o-Klimaszewska, Katarzyna"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/492;2018-06-19T11:18:44Z;hdl_11321_3;hdl_11321_4;Warsztat korpus;Giere\u0142o-Klimaszewska, Katarzyna;test;warsztaty;PWr;test;2018-06-19;corpus;http://hdl.handle.net/11321/492;Polish;Super Cool License;http://www.google.com;ACA;text/plain; charset=utf-8;application/msword;downloadable_files_count: 1;Katarzyna Giere\u0142o-Klimaszewska",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a09930b5-5456-50c7-b492-757e9278774d",
-    "notes": [
-        "test"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/492"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "test"
-        },
-        {
-            "name": "warsztaty"
-        },
-        {
-            "name": "PWr"
-        }
-    ],
-    "title": [
-        "Warsztat korpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a0ae9a8b-56ea-5ba1-ac13-5f5a8b16e4d5.json b/oaitestdata/clarin-oai_dc/SET_1/json/a0ae9a8b-56ea-5ba1-ac13-5f5a8b16e4d5.json
deleted file mode 100644
index b959b9d8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a0ae9a8b-56ea-5ba1-ac13-5f5a8b16e4d5.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3130",
-    "MetadataAccess": [
-        "oai:ota:oucs:3130"
-    ],
-    "PublicationTimestamp": "1892-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1892"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Osbourne, Lloyd, 1868-1947",
-        "Stevenson, Robert Louis, 1850-1894"
-    ],
-    "fulltext": "oai:ota:oucs:3130;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3130.xml;The wrecker;Stevenson, Robert Louis, 1850-1894;Osbourne, Lloyd, 1868-1947;not after: 1892;text_and_corpus_linguistics;Scottish literature -- 19th century;eng;Oxford Text Archive, University of Oxford;Triggs, Jeffery;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a0ae9a8b-56ea-5ba1-ac13-5f5a8b16e4d5",
-    "oai_identifier": [
-        "oai:ota:oucs:3130"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Scottish literature -- th century"
-        }
-    ],
-    "title": [
-        "The wrecker"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3130.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a0eb90a1-9391-57c1-bb4d-b63d667a5d79.json b/oaitestdata/clarin-oai_dc/SET_1/json/a0eb90a1-9391-57c1-bb4d-b63d667a5d79.json
deleted file mode 100644
index 7d782acd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a0eb90a1-9391-57c1-bb4d-b63d667a5d79.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/gzip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/590",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/590"
-    ],
-    "PID": "http://hdl.handle.net/11321/590",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "Woli\u0144ski, Marcin"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/590;2018-07-27T09:25:12Z;hdl_11321_3;hdl_11321_4;Sk\u0142adnica frazowa \u2014 a constituency treebank of Polish;Woli\u0144ski, Marcin;treebank;constituency parsing;Sk\u0142adnica frazowa is a constituency treebank of Polish. The treebank is a result of parsing Polish sentences with the syntactic parser \u015awigra. For every sentence, the parser generates all possible syntactic parse trees predicted by the rules of its grammar. Within the Dendrarium system, a single correct parse tree has been selected for each sentence by linguists (termed \"dendrologists\"). Dendrologists have established parse trees for 13,035 sentences to be correct. Other sentences under consideration have undergone classification on the basis of their (un)grammaticality and reasons for their rejection by the parser.;2018-07;corpus;http://hdl.handle.net/11321/590;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/gzip;downloadable_files_count: 1;Institute of Computer Science, Polish Academy of Sciences;http://zil.ipipan.waw.pl/Sk%C5%82adnica",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a0eb90a1-9391-57c1-bb4d-b63d667a5d79",
-    "notes": [
-        "Sk\u0142adnica frazowa is a constituency treebank of Polish. The treebank is a result of parsing Polish sentences with the syntactic parser \u015awigra. For every sentence, the parser generates all possible syntactic parse trees predicted by the rules of its grammar. Within the Dendrarium system, a single correct parse tree has been selected for each sentence by linguists (termed \"dendrologists\"). Dendrologists have established parse trees for 13,035 sentences to be correct. Other sentences under consideration have undergone classification on the basis of their (un)grammaticality and reasons for their rejection by the parser."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/590"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "constituency parsing"
-        }
-    ],
-    "title": [
-        "Sk\u0142adnica frazowa \u2014 a constituency treebank of Polish"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a0fe94dc-1301-5a1d-8012-f8aa798e4a94.json b/oaitestdata/clarin-oai_dc/SET_1/json/a0fe94dc-1301-5a1d-8012-f8aa798e4a94.json
deleted file mode 100644
index 6bfb7d8c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a0fe94dc-1301-5a1d-8012-f8aa798e4a94.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Charles University, UFAL"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "text/plain",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2863",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2863"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2863",
-    "PublicationTimestamp": "2018-10-23T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Charles University, UFAL"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-2508"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Nov\u00e1k, Michal",
-        "M\u00edrovsk\u00fd, Ji\u0159\u00ed",
-        "Haji\u010dov\u00e1, Eva",
-        "Rysov\u00e1, Magdal\u00e9na",
-        "Rysov\u00e1, Kate\u0159ina"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2863;2018-10-23T16:41:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;EVALD 3.0 \u2013 Evaluator of Discourse;M\u00edrovsk\u00fd, Ji\u0159\u00ed;Nov\u00e1k, Michal;Rysov\u00e1, Kate\u0159ina;Rysov\u00e1, Magdal\u00e9na;Haji\u010dov\u00e1, Eva;text coherence;discourse;automatic evaluation;native speakers;EVALD 3.0 serves for automatic evaluation of surface coherence (cohesion) in Czech texts written by native speakers of Czech.;2018-10-23;toolService;http://hdl.handle.net/11234/1-2863;ces;http://hdl.handle.net/11234/1-2508;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;text/plain;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University, UFAL;https://ufal.mff.cuni.cz/evald",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a0fe94dc-1301-5a1d-8012-f8aa798e4a94",
-    "notes": [
-        "EVALD 3.0 serves for automatic evaluation of surface coherence (cohesion) in Czech texts written by native speakers of Czech."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2863"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "text coherence"
-        },
-        {
-            "name": "discourse"
-        },
-        {
-            "name": "automatic evaluation"
-        },
-        {
-            "name": "native speakers"
-        }
-    ],
-    "title": [
-        "EVALD 3.0 \u2013 Evaluator of Discourse"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a10cef20-6b88-5905-b399-424e7d6b93df.json b/oaitestdata/clarin-oai_dc/SET_1/json/a10cef20-6b88-5905-b399-424e7d6b93df.json
deleted file mode 100644
index e31399fd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a10cef20-6b88-5905-b399-424e7d6b93df.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Central Khmer"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-986",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-986"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-986",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-986;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LAC Khmer Corpus;Language and Cognition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-986;khm;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI29356%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a10cef20-6b88-5905-b399-424e7d6b93df",
-    "notes": [
-        "Language and Cognition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-986"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LAC Khmer Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a128ddff-b7d2-5149-b998-a7fcedeb852a.json b/oaitestdata/clarin-oai_dc/SET_1/json/a128ddff-b7d2-5149-b998-a7fcedeb852a.json
deleted file mode 100644
index ebcabb00..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a128ddff-b7d2-5149-b998-a7fcedeb852a.json
+++ /dev/null
@@ -1,49 +0,0 @@
-{
-    "Contributor": [
-        "Ruppel, Klaas"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-433",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-433"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-433",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-433;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;\u00c1lgu \u2013 Origins of Saami Words (\u00c1lgu \u2013 Saamen sanojen etymologinen tietokanta);Ruppel, Klaas;70,000 words, over 100,000 etymological relations, Relational database;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-433;downloadable_files_count: 0;http://kaino.kotus.fi/algu",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a128ddff-b7d2-5149-b998-a7fcedeb852a",
-    "notes": [
-        "70,000 words, over 100,000 etymological relations, Relational database"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-433"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "\u00c1lgu \u2013 Origins of Saami Words (\u00c1lgu \u2013 Saamen sanojen etymologinen tietokanta)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a13dc6a3-0f0a-597d-8661-87808835b5c7.json b/oaitestdata/clarin-oai_dc/SET_1/json/a13dc6a3-0f0a-597d-8661-87808835b5c7.json
deleted file mode 100644
index 3a2e0ea7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a13dc6a3-0f0a-597d-8661-87808835b5c7.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "[S. n.]"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-806",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-806"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D36-1",
-    "PublicationTimestamp": "1764-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1764"
-    ],
-    "Publisher": [
-        "[S. n.]"
-    ],
-    "RelatedIdentifier": [
-        "http://pbc.biaman.pl/Content/806"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-806;2019-03-01T17:36:43Z;Obiasnienie wzgl\u0119dem s\u0105d\u00f3w assessorskich, y na nich kanclerskiey w\u0142adzy z responsem na skrypt pod tytu\u0142em: Przyczyny na fundamencie praw oyczystych [...].;ilo\u015b\u0107 skan\u00f3w: 22 ; sygn. St-270;[S. n.];[ca 1764];starodruk;application/xml;clarind-uds:poldilemma-806;hdl:11858/00-246C-0000-0023-8D36-1;pol;lat;http://pbc.biaman.pl/Content/806;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a13dc6a3-0f0a-597d-8661-87808835b5c7",
-    "notes": [
-        "ilo\u015b\u0107 skan\u00f3w: 22 ; sygn. St-270"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-806"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "title": [
-        "Obiasnienie wzgl\u0119dem s\u0105d\u00f3w assessorskich, y na nich kanclerskiey w\u0142adzy z responsem na skrypt pod tytu\u0142em: Przyczyny na fundamencie praw oyczystych [...]."
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a156d41e-db1e-56bf-a479-6f79b8d0986d.json b/oaitestdata/clarin-oai_dc/SET_1/json/a156d41e-db1e-56bf-a479-6f79b8d0986d.json
deleted file mode 100644
index 7129c554..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a156d41e-db1e-56bf-a479-6f79b8d0986d.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "University of Bergen, Department of Linguistic, Literary and Aesthetic Studies"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "audio/x-wav",
-        "downloadable_files_count: 9",
-        "text/plain; charset=utf-8",
-        "application/pdf",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish",
-        "Norwegian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/127",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/127"
-    ],
-    "PID": "http://hdl.handle.net/11509/127",
-    "PublicationTimestamp": "2018-11-13T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "University of Bergen, Department of Linguistic, Literary and Aesthetic Studies"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN_ACA",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NORED=1",
-        "ACA"
-    ],
-    "author": [
-        "Kristoffersen, Gjert"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/127;2019-02-25T14:34:31Z;hdl_11509_1;hdl_11509_2;The Level Stress recordings: EastMora_90;Kristoffersen, Gjert;Phonology;Recording equipment\r\nThe recordings were done by means of a cassette recorder (Sony TC-D5M) and Sony\r\nlavaliere microphones. They were digitized in the 1990s. The recordings were made in the\r\nspeakers\u2019 homes.\r\n\r\nThe speakers\r\nThe set consists of three speakers, two women from the village of Nusn\u00e4s, born in 1925 and\r\n1966, grandmother and grandchild. The third speaker is a man from the village of Gars\u00e5s,\r\nsome kilometers further south, born in 1928. They were recruited with the help of the\r\nSwedish linguist Gunnar Nystr\u00f6m, who has a thorough knowledge of Dalarna and the Dalarna\r\ndialects. The youngest speaker did not grow up in East Mora, but in the city of Falun. Both\r\nparents were from East Mora, however, and the dialect was her home language. She also\r\nspent her summer holidays at her grandmother\u2019s home in Nusn\u00e4s.\r\n\r\nFor the full background description of this item, see the file \"EastMora_90: Background.pdf\".\r\n\r\nFor the full description of the whole project, see these files:\r\n     The Level Stress recordings.pdf\r\n     LevelStress_Glossary.pdf\r\n     Level Stress_Speaker and Sound File Codes.pdf\r\n\r\nThe data should be used only for research and development purposes.;2018-11-13;corpus;http://hdl.handle.net/11509/127;swe;nor;CLARIN_ACA;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NORED=1;ACA;audio/x-wav;audio/x-wav;audio/x-wav;application/pdf;application/pdf;application/pdf;application/pdf;application/octet-stream;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 9;University of Bergen, Department of Linguistic, Literary and Aesthetic Studies;http://terminologi.no",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a156d41e-db1e-56bf-a479-6f79b8d0986d",
-    "notes": [
-        "Recording equipment\r\nThe recordings were done by means of a cassette recorder (Sony TC-D5M) and Sony\r\nlavaliere microphones. They were digitized in the 1990s. The recordings were made in the\r\nspeakers\u2019 homes.\r\n\r\nThe speakers\r\nThe set consists of three speakers, two women from the village of Nusn\u00e4s, born in 1925 and\r\n1966, grandmother and grandchild. The third speaker is a man from the village of Gars\u00e5s,\r\nsome kilometers further south, born in 1928. They were recruited with the help of the\r\nSwedish linguist Gunnar Nystr\u00f6m, who has a thorough knowledge of Dalarna and the Dalarna\r\ndialects. The youngest speaker did not grow up in East Mora, but in the city of Falun. Both\r\nparents were from East Mora, however, and the dialect was her home language. She also\r\nspent her summer holidays at her grandmother\u2019s home in Nusn\u00e4s.\r\n\r\nFor the full background description of this item, see the file \"EastMora_90: Background.pdf\".\r\n\r\nFor the full description of the whole project, see these files:\r\n     The Level Stress recordings.pdf\r\n     LevelStress_Glossary.pdf\r\n     Level Stress_Speaker and Sound File Codes.pdf\r\n\r\nThe data should be used only for research and development purposes."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/127"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Phonology"
-        }
-    ],
-    "title": [
-        "The Level Stress recordings: EastMora_90"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a15fa9e7-3a8e-55d4-8839-8eaf196b8d28.json b/oaitestdata/clarin-oai_dc/SET_1/json/a15fa9e7-3a8e-55d4-8839-8eaf196b8d28.json
deleted file mode 100644
index 1d8d8022..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a15fa9e7-3a8e-55d4-8839-8eaf196b8d28.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=29892e16a35a11e1a404080027e73ea22e53349e39f348a7944b0b5bef6e9c41",
-    "MetadataAccess": [
-        "29892e16a35a11e1a404080027e73ea22e53349e39f348a7944b0b5bef6e9c41"
-    ],
-    "PublicationTimestamp": "2012-11-28T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "fulltext": "29892e16a35a11e1a404080027e73ea22e53349e39f348a7944b0b5bef6e9c41;2018-11-15T16:39:41Z;lexicalConceptualResource;lexicalConceptualResource:wordList;LX-Stopwords;LX-Stopwords resource is a manual list of words from Portuguese composed by 2631 words of 51 types. The words are grouped in three big classes, arranged according to their morpho-syntactic category and inflectional feature value (closed classes, open classes, and multi-word units). This list was created as a support resource to develop CRIVO/EtiFac tool (see Branco & Silva, 2001), a tool for the semiautomatic annotation of corpora. With this in mind, the list seeks to be an as exhaustive as possible repository of all word forms that belong to closed classes, items typically with high frequency and fixity.\nTaking into account the ambiguity between words of different categories, which means that some words from closed classes (1866 words) can be part of others categories, two classes were added to the list: open classes (592 words) and multi-word units (173 words), including only the words already contained in closed classes. ;2012-11-28",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a15fa9e7-3a8e-55d4-8839-8eaf196b8d28",
-    "notes": [
-        "LX-Stopwords resource is a manual list of words from Portuguese composed by 2631 words of 51 types. The words are grouped in three big classes, arranged according to their morpho-syntactic category and inflectional feature value (closed classes, open classes, and multi-word units). This list was created as a support resource to develop CRIVO/EtiFac tool (see Branco & Silva, 2001), a tool for the semiautomatic annotation of corpora. With this in mind, the list seeks to be an as exhaustive as possible repository of all word forms that belong to closed classes, items typically with high frequency and fixity.\nTaking into account the ambiguity between words of different categories, which means that some words from closed classes (1866 words) can be part of others categories, two classes were added to the list: open classes (592 words) and multi-word units (173 words), including only the words already contained in closed classes. "
-    ],
-    "oai_identifier": [
-        "29892e16a35a11e1a404080027e73ea22e53349e39f348a7944b0b5bef6e9c41"
-    ],
-    "oai_set": [
-        "lexicalConceptualResource",
-        "lexicalConceptualResource:wordList"
-    ],
-    "state": "active",
-    "title": [
-        "LX-Stopwords"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a170122b-e9c1-5ca9-8595-e5d1c3c23e7d.json b/oaitestdata/clarin-oai_dc/SET_1/json/a170122b-e9c1-5ca9-8595-e5d1c3c23e7d.json
deleted file mode 100644
index b3932079..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a170122b-e9c1-5ca9-8595-e5d1c3c23e7d.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "Sanskrit"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-905",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-905"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-905",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-905;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Vedic Sanskrit;ca. 3.000.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-905;san;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#ved",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a170122b-e9c1-5ca9-8595-e5d1c3c23e7d",
-    "notes": [
-        "ca. 3.000.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-905"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Vedic Sanskrit"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a1778ece-5ca8-5f79-9aeb-50ac14e38c8c.json b/oaitestdata/clarin-oai_dc/SET_1/json/a1778ece-5ca8-5f79-9aeb-50ac14e38c8c.json
deleted file mode 100644
index 8907537d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a1778ece-5ca8-5f79-9aeb-50ac14e38c8c.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "76 KB"
-    ],
-    "Language": [
-        "French"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1322",
-    "MetadataAccess": [
-        "oai:ota:oucs:1322"
-    ],
-    "PublicationTimestamp": "1957-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1957"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "While this resource was freely available for non-commercial use provided that this header is included in its entirety with any copy distributed, it has been removed from our catalogue for one reason or another.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Beckett, Samuel,  1906-1989"
-    ],
-    "fulltext": "oai:ota:oucs:1322;2018-03-07T12:15:11Z;http://ota.ox.ac.uk/headers/1322.xml;Fin de partie  / compiled by David Bond;Beckett, Samuel,  1906-1989;1957;text_and_corpus_linguistics;Plays -- France -- 20th century;fra;Oxford Text Archive, University of Oxford;76 KB;Text;Plays;While this resource was freely available for non-commercial use provided that this header is included in its entirety with any copy distributed, it has been removed from our catalogue for one reason or another.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a1778ece-5ca8-5f79-9aeb-50ac14e38c8c",
-    "oai_identifier": [
-        "oai:ota:oucs:1322"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- France -- th century"
-        }
-    ],
-    "title": [
-        "Fin de partie  / compiled by David Bond"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1322.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a192fb8e-4422-5d83-ac52-b9d8ac08cfb2.json b/oaitestdata/clarin-oai_dc/SET_1/json/a192fb8e-4422-5d83-ac52-b9d8ac08cfb2.json
deleted file mode 100644
index f0b051b0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a192fb8e-4422-5d83-ac52-b9d8ac08cfb2.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "English",
-        "Urdu"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2582",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2582"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2582",
-    "PublicationTimestamp": "2010-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "https://ufal.mff.cuni.cz/pbml/95/art-jawaid-zeman.pdf"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Jawaid, Bushra",
-        "Zeman, Daniel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2582;2018-10-29T12:39:24Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;English-Urdu Religious Parallel Corpus;Jawaid, Bushra;Zeman, Daniel;parallel corpus;religious text;machine translation;English-Urdu parallel corpus is a collection of religious texts (Quran, Bible) in English and Urdu language with sentence alignments. The corpus can be used for experiments with statistical machine translation. Our modifications of crawled data include but are not limited to the following:\r\n1- Manually corrected sentence alignment of the corpora.\r\n2- Our data split (training-development-test) so that our published experiments can be reproduced.\r\n3- Tokenization (optional, but needed to reproduce our experiments).\r\n4- Normalization (optional) of e.g. European vs. Urdu numerals, European vs. Urdu punctuation, removal of Urdu diacritics.;2010;corpus;http://hdl.handle.net/11234/1-2582;eng;urd;https://ufal.mff.cuni.cz/pbml/95/art-jawaid-zeman.pdf;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/umc/005-en-ur/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a192fb8e-4422-5d83-ac52-b9d8ac08cfb2",
-    "notes": [
-        "English-Urdu parallel corpus is a collection of religious texts (Quran, Bible) in English and Urdu language with sentence alignments. The corpus can be used for experiments with statistical machine translation. Our modifications of crawled data include but are not limited to the following:\r\n1- Manually corrected sentence alignment of the corpora.\r\n2- Our data split (training-development-test) so that our published experiments can be reproduced.\r\n3- Tokenization (optional, but needed to reproduce our experiments).\r\n4- Normalization (optional) of e.g. European vs. Urdu numerals, European vs. Urdu punctuation, removal of Urdu diacritics."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2582"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parallel corpus"
-        },
-        {
-            "name": "religious text"
-        },
-        {
-            "name": "machine translation"
-        }
-    ],
-    "title": [
-        "English-Urdu Religious Parallel Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a19307d1-2c66-5803-8c9b-5b536fedff4d.json b/oaitestdata/clarin-oai_dc/SET_1/json/a19307d1-2c66-5803-8c9b-5b536fedff4d.json
deleted file mode 100644
index f0b3b31e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a19307d1-2c66-5803-8c9b-5b536fedff4d.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3855",
-    "MetadataAccess": [
-        "oai:ota:oucs:3855"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Glover, Richard, 1712-1785."
-    ],
-    "fulltext": "oai:ota:oucs:3855;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3855.xml;Boadicia: A tragedy. As it is acted at the Theatre-Royal in Drury-Lane. By Mr. Glover.;Glover, Richard, 1712-1785.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a19307d1-2c66-5803-8c9b-5b536fedff4d",
-    "oai_identifier": [
-        "oai:ota:oucs:3855"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Boadicia: A tragedy. As it is acted at the Theatre-Royal in Drury-Lane. By Mr. Glover."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3855.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a1a8e97a-c2b1-5849-84e9-c986bf11d5bc.json b/oaitestdata/clarin-oai_dc/SET_1/json/a1a8e97a-c2b1-5849-84e9-c986bf11d5bc.json
deleted file mode 100644
index 606f00a6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a1a8e97a-c2b1-5849-84e9-c986bf11d5bc.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Wojciech Jaworski"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/340",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/340"
-    ],
-    "PID": "http://hdl.handle.net/11321/340",
-    "PublicationTimestamp": "2016-12-28T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wojciech Jaworski"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "Jaworski, Wojciech"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/340;2017-04-06T10:08:40Z;hdl_11321_3;hdl_11321_4;ENIAMtoolkit (2017-03-06);Jaworski, Wojciech;lemmatization;part of speech tagging;tokenization;MWE detection;sentence boundaries detection;parsing;ENIAMtoolkit is a collection of libraries that:\r\n- perform tokenization, lemmatization, part of speech tagging;\r\n- detect MWE and abbreviations;\r\n- split text into sentences;\r\n- LCG parsing.;2016-12-28;toolService;http://hdl.handle.net/11321/340;N/A;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 1;Wojciech Jaworski;http://zil.ipipan.waw.pl/ENIAM",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a1a8e97a-c2b1-5849-84e9-c986bf11d5bc",
-    "notes": [
-        "ENIAMtoolkit is a collection of libraries that:\r\n- perform tokenization, lemmatization, part of speech tagging;\r\n- detect MWE and abbreviations;\r\n- split text into sentences;\r\n- LCG parsing."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/340"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "lemmatization"
-        },
-        {
-            "name": "part speech tagging"
-        },
-        {
-            "name": "tokenization"
-        },
-        {
-            "name": "MWE detection"
-        },
-        {
-            "name": "sentence boundaries detection"
-        },
-        {
-            "name": "parsing"
-        }
-    ],
-    "title": [
-        "ENIAMtoolkit (2017-03-06)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a1abbb69-e37e-546c-b833-0836b54ad5e6.json b/oaitestdata/clarin-oai_dc/SET_1/json/a1abbb69-e37e-546c-b833-0836b54ad5e6.json
deleted file mode 100644
index b25dcf39..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a1abbb69-e37e-546c-b833-0836b54ad5e6.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "137 KB"
-    ],
-    "Language": [
-        "Middle English (1100-1500)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0109",
-    "MetadataAccess": [
-        "oai:ota:oucs:0109"
-    ],
-    "PublicationTimestamp": "1100-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1100"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Unknown"
-    ],
-    "fulltext": "oai:ota:oucs:0109;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0109.xml; Owl and the nightingale  / compiled by C. Turk;Unknown;1100-1299;text_and_corpus_linguistics;Poems -- England -- 13th century;enm;Oxford Text Archive, University of Oxford;137 KB;Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a1abbb69-e37e-546c-b833-0836b54ad5e6",
-    "oai_identifier": [
-        "oai:ota:oucs:0109"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- England -- th century"
-        }
-    ],
-    "title": [
-        " Owl and the nightingale  / compiled by C. Turk"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0109.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a1b99aaa-ef9e-5b9f-b4a4-76fa802e9052.json b/oaitestdata/clarin-oai_dc/SET_1/json/a1b99aaa-ef9e-5b9f-b4a4-76fa802e9052.json
deleted file mode 100644
index b8fd1815..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a1b99aaa-ef9e-5b9f-b4a4-76fa802e9052.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-xz",
-        "downloadable_files_count: 2"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1834",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1834"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1834",
-    "PublicationTimestamp": "2016-11-15T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Haji\u010d, Jan",
-        "Hlav\u00e1\u010dov\u00e1, Jaroslava"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1834;2018-07-02T22:05:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;MorfFlex CZ 161115;Haji\u010d, Jan;Hlav\u00e1\u010dov\u00e1, Jaroslava;morphological dictionary;morphology;Czech;Czech morphological dictionary developed originally by Jan Haji\u010d as a spelling checker and lemmatization dictionary. Currently it contains full morphological information for each covered wordform, as well as some derivational, semantic and named entity information.;2016-11-15;lexicalConceptualResource;http://hdl.handle.net/11234/1-1834;ces;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/x-xz;application/x-xz;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/morfflex",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a1b99aaa-ef9e-5b9f-b4a4-76fa802e9052",
-    "notes": [
-        "Czech morphological dictionary developed originally by Jan Haji\u010d as a spelling checker and lemmatization dictionary. Currently it contains full morphological information for each covered wordform, as well as some derivational, semantic and named entity information."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1834"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphological dictionary"
-        },
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "Czech"
-        }
-    ],
-    "title": [
-        "MorfFlex CZ 161115"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a1cb86db-303e-5986-b14e-145e29c37cb2.json b/oaitestdata/clarin-oai_dc/SET_1/json/a1cb86db-303e-5986-b14e-145e29c37cb2.json
deleted file mode 100644
index c90c30e6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a1cb86db-303e-5986-b14e-145e29c37cb2.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2639",
-    "MetadataAccess": [
-        "oai:ota:oucs:2639"
-    ],
-    "PublicationTimestamp": "1765-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1765"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2639;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2639.xml;Letter to a Member of Parliament in Ireland, upon the chusing a new Speaker there ;Swift, Jonathan, 1667-1745;1765;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a1cb86db-303e-5986-b14e-145e29c37cb2",
-    "oai_identifier": [
-        "oai:ota:oucs:2639"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Letter to a Member of Parliament in Ireland, upon the chusing a new Speaker there "
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2639.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a1d208d9-6fd0-5e4b-bf02-66037fb2b88c.json b/oaitestdata/clarin-oai_dc/SET_1/json/a1d208d9-6fd0-5e4b-bf02-66037fb2b88c.json
deleted file mode 100644
index 9ecaa10d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a1d208d9-6fd0-5e4b-bf02-66037fb2b88c.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "The Research Institute for the Languages of Finland"
-    ],
-    "Contributor": [
-        "Haapanen, Minna"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Finnish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-843",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-843"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-843",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "The Research Institute for the Languages of Finland"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Finland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-843;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Modern Finnish Lexicon;Haapanen, Minna;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-843;fin;downloadable_files_count: 0;Finland;The Research Institute for the Languages of Finland;http://kaino.kotus.fi/sanat/nykysuomi/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a1d208d9-6fd0-5e4b-bf02-66037fb2b88c",
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-843"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Modern Finnish Lexicon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a1dd6815-024f-5505-8647-ae315fa9c10e.json b/oaitestdata/clarin-oai_dc/SET_1/json/a1dd6815-024f-5505-8647-ae315fa9c10e.json
deleted file mode 100644
index 36b7012f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a1dd6815-024f-5505-8647-ae315fa9c10e.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "University of West Bohemia, Department of Cybernetics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 9",
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1461",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1461"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1461",
-    "PublicationTimestamp": "2014-12-17T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of West Bohemia, Department of Cybernetics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Tihelka, Daniel",
-        "Matou\u0161ek, Jind\u0159ich"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1461;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;English TTS speech corpus of air traffic (pilot) messages - Taiwanese accent;Matou\u0161ek, Jind\u0159ich;Tihelka, Daniel;speech corpus;text-to-speech (TTS);pitch-marks;The corpus contains recordings of male speaker, native in Taiwanese, talking in English. The sentences that were read by the speaker originate in the domain of air traffic control (ATC), specifically the messages used by plane pilots during routine flight. The text in the corpus originates from the transcripts of the real recordings, part of which has been released in LINDAT/CLARIN (http://hdl.handle.net/11858/00-097C-0000-0001-CCA1-0), and individual phrases were selected by special algorithm described in J\u016fzov\u00e1, M. and Tihelka, D.: Minimum Text Corpus Selection for Limited Domain Speech Synthesis (DOI 10.1007/978-3-319-10816-2_48). The corpus was used to create a limited domain speech synthesis system capable of simulating a pilot communication with an ATC officer.;2014-12-17;corpus;http://hdl.handle.net/11234/1-1461;eng;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/zip;application/zip;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain; charset=utf-8;downloadable_files_count: 9;University of West Bohemia, Department of Cybernetics;http://itblp.zcu.cz",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a1dd6815-024f-5505-8647-ae315fa9c10e",
-    "notes": [
-        "The corpus contains recordings of male speaker, native in Taiwanese, talking in English. The sentences that were read by the speaker originate in the domain of air traffic control (ATC), specifically the messages used by plane pilots during routine flight. The text in the corpus originates from the transcripts of the real recordings, part of which has been released in LINDAT/CLARIN (http://hdl.handle.net/11858/00-097C-0000-0001-CCA1-0), and individual phrases were selected by special algorithm described in J\u016fzov\u00e1, M. and Tihelka, D.: Minimum Text Corpus Selection for Limited Domain Speech Synthesis (DOI 10.1007/978-3-319-10816-2_48). The corpus was used to create a limited domain speech synthesis system capable of simulating a pilot communication with an ATC officer."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1461"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech corpus"
-        },
-        {
-            "name": "text-to-speech TTS"
-        },
-        {
-            "name": "pitch-marks"
-        }
-    ],
-    "title": [
-        "English TTS speech corpus of air traffic (pilot) messages - Taiwanese accent"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a1eb3dcd-5c91-5377-9498-e848b95f968f.json b/oaitestdata/clarin-oai_dc/SET_1/json/a1eb3dcd-5c91-5377-9498-e848b95f968f.json
deleted file mode 100644
index 6f41052b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a1eb3dcd-5c91-5377-9498-e848b95f968f.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Universit\u00e9 Paris 4 Sorbonne / CELTA"
-    ],
-    "Contributor": [
-        "Sauvet, Georges",
-        "Wlodarczyk, Andr\u00e9"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-297",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-297"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-297",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Universit\u00e9 Paris 4 Sorbonne / CELTA"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "France"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-297;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;SEMANA - Software for symbolic and statistical data mining;Wlodarczyk, Andr\u00e9;Sauvet, Georges;Dynamic database builder and three kinds of tools for visualizing and verifiying data with correction facilities;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-297;downloadable_files_count: 0;France;Universit\u00e9 Paris 4 Sorbonne / CELTA;http://www.celta.paris-sorbonne.fr/anasem/Semana-Corner/index.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a1eb3dcd-5c91-5377-9498-e848b95f968f",
-    "notes": [
-        "Dynamic database builder and three kinds of tools for visualizing and verifiying data with correction facilities"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-297"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "SEMANA - Software for symbolic and statistical data mining"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a1f3d777-12f5-5af5-ae02-a426966a6d34.json b/oaitestdata/clarin-oai_dc/SET_1/json/a1f3d777-12f5-5af5-ae02-a426966a6d34.json
deleted file mode 100644
index b654b12a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a1f3d777-12f5-5af5-ae02-a426966a6d34.json
+++ /dev/null
@@ -1,106 +0,0 @@
-{
-    "Contact": [
-        "ParaCrawl"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 13"
-    ],
-    "Language": [
-        "English",
-        "German",
-        "French",
-        "Spanish",
-        "Italian",
-        "Portuguese",
-        "Dutch",
-        "Polish",
-        "Czech",
-        "Romanian",
-        "Finnish",
-        "Latvian",
-        "Russian",
-        "Estonian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2610",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2610"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2610",
-    "PublicationTimestamp": "2018-01-14T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "ParaCrawl"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Public Domain Dedication (CC Zero)",
-        "http://creativecommons.org/publicdomain/zero/1.0/",
-        "PUB"
-    ],
-    "author": [
-        "Espl\u00e0-Gomis, Miquel",
-        "Cartagena, V\u00edctor M. S\u00e1nchez",
-        "Samiotou, Anna",
-        "Forcada, Mikel L.",
-        "Heafield, Kenneth",
-        "Kamran, Amir",
-        "Ortiz-Rojas, Sergio",
-        "Haddow, Barry",
-        "S\u00e1nchez, Gema Ram\u00edrez",
-        "St\u0159elec, Marek",
-        "Ba\u00f1\u00f3n, Marta",
-        "Koehn, Philipp"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2610;2018-02-12T07:41:48Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;ParaCrawl Corpus version 1.0;Koehn, Philipp;Heafield, Kenneth;Forcada, Mikel L.;Espl\u00e0-Gomis, Miquel;Ortiz-Rojas, Sergio;S\u00e1nchez, Gema Ram\u00edrez;Cartagena, V\u00edctor M. S\u00e1nchez;Haddow, Barry;Ba\u00f1\u00f3n, Marta;St\u0159elec, Marek;Samiotou, Anna;Kamran, Amir;ParaCrawl;parallel corpus;CommonCrawl;machine translation;text corpora;The January 2018 release of the ParaCrawl is the first version of the corpus. It contains parallel corpora for 11 languages paired with English, crawled from a large number of web sites. The selection of websites is based on CommonCrawl, but ParaCrawl is extracted from a brand new crawl which has much higher coverage of these selected websites than CommonCrawl. Since the data is fairly raw, it is released with two quality metrics that can be used for corpus filtering. An official \"clean\" version of each corpus uses one of the metrics. For more details and raw data download please visit: http://paracrawl.eu/releases.html;2018-01-14;corpus;http://hdl.handle.net/11372/LRT-2610;eng;deu;fra;spa;ita;por;nld;pol;ces;ron;fin;lav;rus;est;Public Domain Dedication (CC Zero);http://creativecommons.org/publicdomain/zero/1.0/;PUB;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 13;ParaCrawl;http://paracrawl.eu",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a1f3d777-12f5-5af5-ae02-a426966a6d34",
-    "notes": [
-        "The January 2018 release of the ParaCrawl is the first version of the corpus. It contains parallel corpora for 11 languages paired with English, crawled from a large number of web sites. The selection of websites is based on CommonCrawl, but ParaCrawl is extracted from a brand new crawl which has much higher coverage of these selected websites than CommonCrawl. Since the data is fairly raw, it is released with two quality metrics that can be used for corpus filtering. An official \"clean\" version of each corpus uses one of the metrics. For more details and raw data download please visit: http://paracrawl.eu/releases.html"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2610"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ParaCrawl"
-        },
-        {
-            "name": "parallel corpus"
-        },
-        {
-            "name": "CommonCrawl"
-        },
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "text corpora"
-        }
-    ],
-    "title": [
-        "ParaCrawl Corpus version 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a1f78a1f-bc5f-5dc3-a938-789f193060ba.json b/oaitestdata/clarin-oai_dc/SET_1/json/a1f78a1f-bc5f-5dc3-a938-789f193060ba.json
deleted file mode 100644
index f6d11516..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a1f78a1f-bc5f-5dc3-a938-789f193060ba.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Craig, Hugh"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 217 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1442",
-    "MetadataAccess": [
-        "oai:ota:oucs:1442"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Jonson, Ben, 1573?-1637"
-    ],
-    "fulltext": "oai:ota:oucs:1442;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1442.xml;Volpone;Volpone [1607] / Ben Jonson;The foxe;Jonson, Ben, 1573?-1637;text_and_corpus_linguistics;English drama -- 17th century;Oxford Text Archive, University of Oxford;Craig, Hugh;(1 file : ca. 217 KB);Text;Plays;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a1f78a1f-bc5f-5dc3-a938-789f193060ba",
-    "oai_identifier": [
-        "oai:ota:oucs:1442"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- th century"
-        }
-    ],
-    "title": [
-        "Volpone",
-        "Volpone [1607] / Ben Jonson",
-        "The foxe"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1442.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a1fda03a-22ec-5e2d-9968-3c74f8fc90bb.json b/oaitestdata/clarin-oai_dc/SET_1/json/a1fda03a-22ec-5e2d-9968-3c74f8fc90bb.json
deleted file mode 100644
index 6377f832..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a1fda03a-22ec-5e2d-9968-3c74f8fc90bb.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Ule, Louis"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 108 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1616",
-    "MetadataAccess": [
-        "oai:ota:oucs:1616"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Marlowe, Christopher, 1564-1593"
-    ],
-    "fulltext": "oai:ota:oucs:1616;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1616.xml;Dr. Faustus / Christopher Marlowe;Marlowe, Christopher, 1564-1593;text_and_corpus_linguistics;English drama -- Early modern and Elizabethan, 1500-1600;Oxford Text Archive, University of Oxford;Ule, Louis;text/sgml;(1 file : ca. 108 KB);Text;Plays;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a1fda03a-22ec-5e2d-9968-3c74f8fc90bb",
-    "oai_identifier": [
-        "oai:ota:oucs:1616"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- Early modern Elizabethan"
-        }
-    ],
-    "title": [
-        "Dr. Faustus / Christopher Marlowe"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1616.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a2126bca-6206-56df-8aa8-0f95b95cb38c.json b/oaitestdata/clarin-oai_dc/SET_1/json/a2126bca-6206-56df-8aa8-0f95b95cb38c.json
deleted file mode 100644
index c02a738e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a2126bca-6206-56df-8aa8-0f95b95cb38c.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Sejm RP, MSZ RP"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 6",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/159",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/159"
-    ],
-    "PID": "http://hdl.handle.net/11321/159",
-    "PublicationTimestamp": "1990-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1990"
-    ],
-    "Publisher": [
-        "Sejm RP, MSZ RP"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Skubiszewski, Krzysztof"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/159;2015-04-20T12:25:49Z;hdl_11321_3;hdl_11321_4;1990_Skubiszewski;Skubiszewski, Krzysztof;pierwsze expose MSZ III RP;1990;corpus;http://hdl.handle.net/11321/159;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;application/zip;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 6;Sejm RP, MSZ RP;C:\\Users\\media\\Dropbox\\Dropbox\\Dropbox\\!WAD\\Expose MSZ 1955-2014\\expose msz 1990-2014\\expose msz 1990-2014 txt\\1990",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a2126bca-6206-56df-8aa8-0f95b95cb38c",
-    "notes": [
-        "pierwsze expose MSZ III RP"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/159"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "1990_Skubiszewski"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a239268a-944f-577d-b125-0ec06639332c.json b/oaitestdata/clarin-oai_dc/SET_1/json/a239268a-944f-577d-b125-0ec06639332c.json
deleted file mode 100644
index 6b6f29f0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a239268a-944f-577d-b125-0ec06639332c.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "GZ"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 30",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/200",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/200"
-    ],
-    "PID": "http://hdl.handle.net/11321/200",
-    "PublicationTimestamp": "2015-05-18T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "GZ"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Bolanowski, Jeremi"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/200;2015-05-21T13:47:10Z;hdl_11321_3;hdl_11321_4;BJ;Bolanowski, Jeremi;BJ;2015-05-18;corpus;http://hdl.handle.net/11321/200;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 30;GZ",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a239268a-944f-577d-b125-0ec06639332c",
-    "notes": [
-        "BJ"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/200"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "BJ"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a23ba6fc-272e-5820-a7f2-42415eddb510.json b/oaitestdata/clarin-oai_dc/SET_1/json/a23ba6fc-272e-5820-a7f2-42415eddb510.json
deleted file mode 100644
index 759d145b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a23ba6fc-272e-5820-a7f2-42415eddb510.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Dagmara Ka\u0142kus"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/vnd.oasis.opendocument.text",
-        "downloadable_files_count: 10",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/482",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/482"
-    ],
-    "PID": "http://hdl.handle.net/11321/482",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Dagmara Ka\u0142kus"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Super Cool License",
-        "http://www.google.com",
-        "ACA"
-    ],
-    "author": [
-        "Ka\u0142kus, Dagmara"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/482;2018-06-19T11:18:05Z;hdl_11321_3;hdl_11321_4;Workshop;Ka\u0142kus, Dagmara;corpus;Korpus testowy;2018;corpus;http://hdl.handle.net/11321/482;pol;Super Cool License;http://www.google.com;ACA;text/plain; charset=utf-8;application/vnd.oasis.opendocument.text;text/plain;text/plain;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;downloadable_files_count: 10;Dagmara Ka\u0142kus",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a23ba6fc-272e-5820-a7f2-42415eddb510",
-    "notes": [
-        "Korpus testowy"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/482"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        }
-    ],
-    "title": [
-        "Workshop"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a275960d-48ae-53bc-938b-197981cd81ee.json b/oaitestdata/clarin-oai_dc/SET_1/json/a275960d-48ae-53bc-938b-197981cd81ee.json
deleted file mode 100644
index bcafcd61..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a275960d-48ae-53bc-938b-197981cd81ee.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Universit\u00e4t Wien",
-        "Universit\u00e4t Salzburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1152",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1152"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1152",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Universit\u00e4t Wien",
-        "Universit\u00e4t Salzburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Austria"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1152;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Mittelhochdeutsche Begriffsdatenbank;Germanistik;M\u00f6glichkeit der Suche nach W\u00f6rtern, Zeichenketten und Begriffen in verschiedenen mittelhochdeutschen Quellen;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1152;deu;downloadable_files_count: 0;Austria;Universit\u00e4t Salzburg;Universit\u00e4t Wien;http://mhdbdb.sbg.ac.at",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a275960d-48ae-53bc-938b-197981cd81ee",
-    "notes": [
-        "M\u00f6glichkeit der Suche nach W\u00f6rtern, Zeichenketten und Begriffen in verschiedenen mittelhochdeutschen Quellen"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1152"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Mittelhochdeutsche Begriffsdatenbank"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a27f4394-30a7-563c-a468-a4495b5da7f1.json b/oaitestdata/clarin-oai_dc/SET_1/json/a27f4394-30a7-563c-a468-a4495b5da7f1.json
deleted file mode 100644
index dbeffdbb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a27f4394-30a7-563c-a468-a4495b5da7f1.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Tamil"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1453",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1453"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1453",
-    "PublicationTimestamp": "2014-10-31T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "Ramasamy, Loganathan"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1453;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Tamil Dependency Treebank v0.1;Ramasamy, Loganathan;\u017dabokrtsk\u00fd, Zden\u011bk;treebank;corpus;Tamil Dependency Treebank version 0.1 (TamilTB.v0.1) is an attempt to develop a syntactically annotated corpora for Tamil. TamilTB.v0.1 contains 600 sentences enriched with manual annotation of morphology and dependency syntax in the style of Prague Dependency Treebank. TamilTB.v0.1 has been created at the Institute of Formal and Applied Linguistics, Charles University in Prague.;2014-10-31;corpus;http://hdl.handle.net/11234/1-1453;tam;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/~ramasamy/tamiltb/0.1/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a27f4394-30a7-563c-a468-a4495b5da7f1",
-    "notes": [
-        "Tamil Dependency Treebank version 0.1 (TamilTB.v0.1) is an attempt to develop a syntactically annotated corpora for Tamil. TamilTB.v0.1 contains 600 sentences enriched with manual annotation of morphology and dependency syntax in the style of Prague Dependency Treebank. TamilTB.v0.1 has been created at the Institute of Formal and Applied Linguistics, Charles University in Prague."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1453"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "corpus"
-        }
-    ],
-    "title": [
-        "Tamil Dependency Treebank v0.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a29a3d5c-a1a6-5072-b5d0-86175ebd790e.json b/oaitestdata/clarin-oai_dc/SET_1/json/a29a3d5c-a1a6-5072-b5d0-86175ebd790e.json
deleted file mode 100644
index df835d8f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a29a3d5c-a1a6-5072-b5d0-86175ebd790e.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "University of Tartu"
-    ],
-    "Contributor": [
-        "Lippus, P\u00e4rtel"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Estonian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1079",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1079"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1079",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Tartu"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Estonia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1079;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Phonetic Corpus of Estonian Spontaneous Speech (online search engine);Lippus, P\u00e4rtel;speech corpus;Studio recordings of spontaneous Estonian segmented phonetically on word, sound, and other linguistic levels. Current size about 22 hours of speech, 155 000 words. Online search engine lets you search from word-level segments and returns matching 2 second sequences of sound and segmentation.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1079;est;downloadable_files_count: 0;Estonia;University of Tartu;http://www.murre.ut.ee/phonetic-corpus/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a29a3d5c-a1a6-5072-b5d0-86175ebd790e",
-    "notes": [
-        "Studio recordings of spontaneous Estonian segmented phonetically on word, sound, and other linguistic levels. Current size about 22 hours of speech, 155 000 words. Online search engine lets you search from word-level segments and returns matching 2 second sequences of sound and segmentation."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1079"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech corpus"
-        }
-    ],
-    "title": [
-        "Phonetic Corpus of Estonian Spontaneous Speech (online search engine)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a2b3a986-895d-5af1-b526-feed1597d696.json b/oaitestdata/clarin-oai_dc/SET_1/json/a2b3a986-895d-5af1-b526-feed1597d696.json
deleted file mode 100644
index 0802bfe9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a2b3a986-895d-5af1-b526-feed1597d696.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=ca0843b6e99a11e4a2aa782bcb0741355f1a1ee194b045f786b85cfd4cbbd96b",
-    "MetadataAccess": [
-        "ca0843b6e99a11e4a2aa782bcb0741355f1a1ee194b045f786b85cfd4cbbd96b"
-    ],
-    "PublicationTimestamp": "2015-04-29T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "ca0843b6e99a11e4a2aa782bcb0741355f1a1ee194b045f786b85cfd4cbbd96b;2018-11-15T16:40:13Z;corpus;corpus:text;QTLeap WSD/NED corpus;QTLeap WSD/NED corpus\n\nThis corpora is part of Deliverable 5.5 of the European Commission project QTLeap FP7-ICT-2013.4.1-610516 (http://qtleap.eu). \n\nThe texts are Q&A interactions from the real-user scenario (batches 1 and 2). The interactions in this corpus are available in  Basque, Bulgarian, Czech, English, Portuguese and Spanish. \n\nThe texts have been automatically annotated with NLP tools, including Word Sense Disambiguation, Named Entity Disambiguation and Coreference resolution. Please check deliverable D5.6 in http://qtleap.eu/deliverables for more information.\n\nInstitutions involved in the annotation:\n  University of the Basque Country (UPV/EHU)\n  Faculty of Science, Univeristy of Lisbon (FCUL)\n  Charles University in Prague (CUNI)\n  Bulgarian Academy of Sciences (IICT-BAS)\n;2015-04-29",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a2b3a986-895d-5af1-b526-feed1597d696",
-    "notes": [
-        "QTLeap WSD/NED corpus\n\nThis corpora is part of Deliverable 5.5 of the European Commission project QTLeap FP7-ICT-2013.4.1-610516 (http://qtleap.eu). \n\nThe texts are Q&A interactions from the real-user scenario (batches 1 and 2). The interactions in this corpus are available in  Basque, Bulgarian, Czech, English, Portuguese and Spanish. \n\nThe texts have been automatically annotated with NLP tools, including Word Sense Disambiguation, Named Entity Disambiguation and Coreference resolution. Please check deliverable D5.6 in http://qtleap.eu/deliverables for more information.\n\nInstitutions involved in the annotation:\n  University of the Basque Country (UPV/EHU)\n  Faculty of Science, Univeristy of Lisbon (FCUL)\n  Charles University in Prague (CUNI)\n  Bulgarian Academy of Sciences (IICT-BAS)\n"
-    ],
-    "oai_identifier": [
-        "ca0843b6e99a11e4a2aa782bcb0741355f1a1ee194b045f786b85cfd4cbbd96b"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "QTLeap WSD/NED corpus"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a2b68dfe-de39-50db-82a4-452cb207fa64.json b/oaitestdata/clarin-oai_dc/SET_1/json/a2b68dfe-de39-50db-82a4-452cb207fa64.json
deleted file mode 100644
index 5ae9b4f5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a2b68dfe-de39-50db-82a4-452cb207fa64.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Polish-Japanese Academy of Information Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/octet-stream",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/237",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/237"
-    ],
-    "PID": "http://hdl.handle.net/11321/237",
-    "PublicationTimestamp": "2015-11-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Polish-Japanese Academy of Information Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Jankowska-Lorek, Kamila",
-        "Marasek, Krzysztof",
-        "Brocki, \u0141ukasz",
-        "Kor\u017einek, Danijel"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/237;2016-01-11T10:53:08Z;hdl_11321_3;hdl_11321_4;Clarin-PL Mobile Corpus (EMU);Marasek, Krzysztof;Kor\u017einek, Danijel;Brocki, \u0141ukasz;Jankowska-Lorek, Kamila;speech corpus;speech prosody;telephony;Polish speech corpus of read speech recorded over the phone. Contains many speakers, each reading a few dozen different sentences and a list of words with rare phonemes. Useful for analyzing modern Polish pronounciation in a telephony environment.;2015-11-01;corpus;http://hdl.handle.net/11321/237;pol;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;text/plain; charset=utf-8;application/zip;application/octet-stream;application/octet-stream;downloadable_files_count: 1;Polish-Japanese Academy of Information Technology;http://mowa.clarin-pl.eu/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a2b68dfe-de39-50db-82a4-452cb207fa64",
-    "notes": [
-        "Polish speech corpus of read speech recorded over the phone. Contains many speakers, each reading a few dozen different sentences and a list of words with rare phonemes. Useful for analyzing modern Polish pronounciation in a telephony environment."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/237"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech corpus"
-        },
-        {
-            "name": "speech prosody"
-        },
-        {
-            "name": "telephony"
-        }
-    ],
-    "title": [
-        "Clarin-PL Mobile Corpus (EMU)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a2b70ab7-b71e-561d-9a6d-9f1b1e5877c2.json b/oaitestdata/clarin-oai_dc/SET_1/json/a2b70ab7-b71e-561d-9a6d-9f1b1e5877c2.json
deleted file mode 100644
index 4eda95bd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a2b70ab7-b71e-561d-9a6d-9f1b1e5877c2.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4268",
-    "MetadataAccess": [
-        "oai:ota:oucs:4268"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "O'Keeffe, John, 1747-1833."
-    ],
-    "fulltext": "oai:ota:oucs:4268;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4268.xml;The little hunch-back: or, a frolic in Bagdad. A farce. In two acts. As it is performed at the Theatre Royal, Covent-Garden, with universal applause. Written by John O'Keeffe. ...;O'Keeffe, John, 1747-1833.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a2b70ab7-b71e-561d-9a6d-9f1b1e5877c2",
-    "oai_identifier": [
-        "oai:ota:oucs:4268"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The little hunch-back: or, a frolic in Bagdad. A farce. In two acts. As it is performed at the Theatre Royal, Covent-Garden, with universal applause. Written by John O'Keeffe. ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4268.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a2efcc0c-fc1d-5464-b61e-35d63684f492.json b/oaitestdata/clarin-oai_dc/SET_1/json/a2efcc0c-fc1d-5464-b61e-35d63684f492.json
deleted file mode 100644
index 30f4c18b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a2efcc0c-fc1d-5464-b61e-35d63684f492.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Mitzlerowska"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-561",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-561"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D24-B",
-    "PublicationTimestamp": "1772-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1772"
-    ],
-    "Publisher": [
-        "Drukarnia Mitzlerowska"
-    ],
-    "RelatedIdentifier": [
-        "http://pbc.biaman.pl/Content/561"
-    ],
-    "ResourceType": [
-        "gazeta"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-561;2019-03-01T15:43:51Z;Monitor na Rok Pa\u0144ski 1772: Nro. I - CV;Czasopisma polskie 18 w.;ilo\u015b\u0107 skan\u00f3w: 417 ; Sygn. St - 367;Drukarnia Mitzlerowska;1772;gazeta;application/xml;clarind-uds:poldilemma-561;hdl:11858/00-246C-0000-0023-8D24-B;pol;lat;http://pbc.biaman.pl/Content/561;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a2efcc0c-fc1d-5464-b61e-35d63684f492",
-    "notes": [
-        "ilo\u015b\u0107 skan\u00f3w: 417 ; Sygn. St - 367"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-561"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Czasopisma polskie w."
-        }
-    ],
-    "title": [
-        "Monitor na Rok Pa\u0144ski 1772: Nro. I - CV"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a2feb994-d27e-591b-a81d-1315e1b8ad8a.json b/oaitestdata/clarin-oai_dc/SET_1/json/a2feb994-d27e-591b-a81d-1315e1b8ad8a.json
deleted file mode 100644
index 9c6f1a5a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a2feb994-d27e-591b-a81d-1315e1b8ad8a.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Nagle, Chris"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(2 files : ca. 1.43, 71 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2049",
-    "MetadataAccess": [
-        "oai:ota:oucs:2049"
-    ],
-    "PublicationTimestamp": "1796-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1796"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Robinson, Mary, 1758-1800"
-    ],
-    "fulltext": "oai:ota:oucs:2049;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/2049.xml;Sappho and Phaon : in a series of legitimate sonnets, with thoughts on poetical subjects, and anecdotes of the Grecian poetess;Robinson, Mary, 1758-1800;1796;text_and_corpus_linguistics;Poems -- Great Britain -- 18th century;eng;Oxford Text Archive, University of Oxford;Nagle, Chris;text/sgml;(2 files : ca. 1.43, 71 KB);Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a2feb994-d27e-591b-a81d-1315e1b8ad8a",
-    "oai_identifier": [
-        "oai:ota:oucs:2049"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Sappho and Phaon : in a series of legitimate sonnets, with thoughts on poetical subjects, and anecdotes of the Grecian poetess"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2049.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a314fd90-01aa-59b2-98bb-8b611b118786.json b/oaitestdata/clarin-oai_dc/SET_1/json/a314fd90-01aa-59b2-98bb-8b611b118786.json
deleted file mode 100644
index a889d797..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a314fd90-01aa-59b2-98bb-8b611b118786.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Unifob AS"
-    ],
-    "Contributor": [
-        "Pichler, Alois"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-189",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-189"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-189",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Unifob AS"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Norway"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-189;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;WAB \u2013 The Wittgenstein Archives;Pichler, Alois;Wittgenstein's Nachlass;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-189;deu;downloadable_files_count: 0;Norway;Unifob AS;http://wab.aksis.uib.no/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a314fd90-01aa-59b2-98bb-8b611b118786",
-    "notes": [
-        "Wittgenstein's Nachlass"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-189"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "WAB \u2013 The Wittgenstein Archives"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a326f167-a9ae-56ce-a318-421cca38c8cb.json b/oaitestdata/clarin-oai_dc/SET_1/json/a326f167-a9ae-56ce-a318-421cca38c8cb.json
deleted file mode 100644
index 4971818f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a326f167-a9ae-56ce-a318-421cca38c8cb.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "English",
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1735",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1735"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1735",
-    "PublicationTimestamp": "2016-06-10T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/H2020/645452"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "C\u00edfka, Ond\u0159ej",
-        "Bojar, Ond\u0159ej"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1735;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;A Small Dataset for English-to-Czech Speech Translation in the Travel Domain;C\u00edfka, Ond\u0159ej;Bojar, Ond\u0159ej;speech corpus;ASR;machine translation;This small dataset contains 3 speech corpora collected using the Alex Translate telephone service (https://ufal.mff.cuni.cz/alex#alex-translate).\r\nThe \"part1\" and \"part2\" corpora contain English speech with transcriptions and Czech translations. These recordings were collected from users of the service. Part 1 contains earlier recordings, filtered to include only clean speech; Part 2 contains later recordings with no filtering applied.\r\nThe \"cstest\" corpus contains recordings of artificially created sentences, each containing one or more Czech names of places in the Czech Republic. These were recorded by a multinational group of students studying in Prague.;2016-06-10;corpus;http://hdl.handle.net/11234/1-1735;eng;ces;info:eu-repo/grantAgreement/EC/H2020/645452;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;PUB;application/octet-stream;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 4;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a326f167-a9ae-56ce-a318-421cca38c8cb",
-    "notes": [
-        "This small dataset contains 3 speech corpora collected using the Alex Translate telephone service (https://ufal.mff.cuni.cz/alex#alex-translate).\r\nThe \"part1\" and \"part2\" corpora contain English speech with transcriptions and Czech translations. These recordings were collected from users of the service. Part 1 contains earlier recordings, filtered to include only clean speech; Part 2 contains later recordings with no filtering applied.\r\nThe \"cstest\" corpus contains recordings of artificially created sentences, each containing one or more Czech names of places in the Czech Republic. These were recorded by a multinational group of students studying in Prague."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1735"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech corpus"
-        },
-        {
-            "name": "ASR"
-        },
-        {
-            "name": "machine translation"
-        }
-    ],
-    "title": [
-        "A Small Dataset for English-to-Czech Speech Translation in the Travel Domain"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a335ff4e-6560-51f5-a00b-bbcfd9c91679.json b/oaitestdata/clarin-oai_dc/SET_1/json/a335ff4e-6560-51f5-a00b-bbcfd9c91679.json
deleted file mode 100644
index 12223fa5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a335ff4e-6560-51f5-a00b-bbcfd9c91679.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4444",
-    "MetadataAccess": [
-        "oai:ota:oucs:4444"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Brand, John, 1744-1806."
-    ],
-    "fulltext": "oai:ota:oucs:4444;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4444.xml;On illicit love. Written among the ruins of Godstow nunnery, near Oxford. By John Brand,;Brand, John, 1744-1806.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a335ff4e-6560-51f5-a00b-bbcfd9c91679",
-    "oai_identifier": [
-        "oai:ota:oucs:4444"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "On illicit love. Written among the ruins of Godstow nunnery, near Oxford. By John Brand,"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4444.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a33bd2da-3400-59ad-b421-01a99328a6ab.json b/oaitestdata/clarin-oai_dc/SET_1/json/a33bd2da-3400-59ad-b421-01a99328a6ab.json
deleted file mode 100644
index d7954b0f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a33bd2da-3400-59ad-b421-01a99328a6ab.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Hindi"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-BD17-1",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-BD17-1"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-BD17-1",
-    "PublicationTimestamp": "2010-05-11T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/231720",
-        "http://hdl.handle.net/11858/00-097C-0000-0023-625F-0"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Bojar, Ond\u0159ej",
-        "Damani, Om Prakesh",
-        "Stra\u0148\u00e1k, Pavel",
-        "Jain, Gaurav",
-        "Zeman, Daniel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-BD17-1;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;English-Hindi Parallel Corpus;Bojar, Ond\u0159ej;Stra\u0148\u00e1k, Pavel;Zeman, Daniel;Jain, Gaurav;Damani, Om Prakesh;English-Hindi parallel corpus;parallel corpus;English-Hindi parallel corpus collected from several sources. Tokenized and sentence-aligned. A part of the data is our patch for the Emille parallel corpus.;2010-05-11;corpus;UMC002;http://hdl.handle.net/11858/00-097C-0000-0001-BD17-1;hin;info:eu-repo/grantAgreement/EC/FP7/231720;http://hdl.handle.net/11858/00-097C-0000-0023-625F-0;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a33bd2da-3400-59ad-b421-01a99328a6ab",
-    "notes": [
-        "English-Hindi parallel corpus collected from several sources. Tokenized and sentence-aligned. A part of the data is our patch for the Emille parallel corpus."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-BD17-1"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "English-Hindi parallel corpus"
-        },
-        {
-            "name": "parallel corpus"
-        }
-    ],
-    "title": [
-        "English-Hindi Parallel Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a340d483-7e09-5e53-beb5-fdc541df2160.json b/oaitestdata/clarin-oai_dc/SET_1/json/a340d483-7e09-5e53-beb5-fdc541df2160.json
deleted file mode 100644
index 4c06d903..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a340d483-7e09-5e53-beb5-fdc541df2160.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "uni"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/506",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/506"
-    ],
-    "PID": "http://hdl.handle.net/11321/506",
-    "PublicationTimestamp": "2018-07-09T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "uni"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Smith2, Donald jr"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/506;2018-07-09T00:27:25Z;hdl_11321_3;hdl_11321_4;eng_corp_test;Smith2, Donald jr;test_corpus;test corpus;2018-07-09;corpus;http://hdl.handle.net/11321/506;eng;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;uni",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a340d483-7e09-5e53-beb5-fdc541df2160",
-    "notes": [
-        "test corpus"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/506"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "test_corpus"
-        }
-    ],
-    "title": [
-        "eng_corp_test"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a3497554-b6dd-5829-bae9-4c475064da46.json b/oaitestdata/clarin-oai_dc/SET_1/json/a3497554-b6dd-5829-bae9-4c475064da46.json
deleted file mode 100644
index ecefe83c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a3497554-b6dd-5829-bae9-4c475064da46.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4030",
-    "MetadataAccess": [
-        "oai:ota:oucs:4030"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Bickerstaff, Isaac, 1735-1812."
-    ],
-    "fulltext": "oai:ota:oucs:4030;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4030.xml;The maid of the mill. A comic opera: As it is performed at the Theatre Royal in Covent Garden. The music compiled, and the words written by the author of Love in a village.;Bickerstaff, Isaac, 1735-1812.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a3497554-b6dd-5829-bae9-4c475064da46",
-    "oai_identifier": [
-        "oai:ota:oucs:4030"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The maid of the mill. A comic opera: As it is performed at the Theatre Royal in Covent Garden. The music compiled, and the words written by the author of Love in a village."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4030.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a34dd0e3-a417-5bff-b0a6-a06aa2021c0f.json b/oaitestdata/clarin-oai_dc/SET_1/json/a34dd0e3-a417-5bff-b0a6-a06aa2021c0f.json
deleted file mode 100644
index 2833f5f0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a34dd0e3-a417-5bff-b0a6-a06aa2021c0f.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences",
-        "Polish Scientific Publishers PWN",
-        "Shared initiative of Institute of Computer Science at Polish Academy of Sciences (IPI PAN)",
-        "Department of Computational and Corpus Linguistics at the University of \u0141\u00f3d\u017a",
-        "Institute of Polish Language at the Polish Academy of Sciences"
-    ],
-    "Contributor": [
-        "Przepi\u00f3rkowski, Adam"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-676",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-676"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-676",
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences",
-        "Polish Scientific Publishers PWN",
-        "Shared initiative of Institute of Computer Science at Polish Academy of Sciences (IPI PAN)",
-        "Department of Computational and Corpus Linguistics at the University of \u0141\u00f3d\u017a",
-        "Institute of Polish Language at the Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Poland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-676;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;National Corpus of Polish;Przepi\u00f3rkowski, Adam;In (advanced) preparation: a reference corpus of Polish language containing hundreds millions of words.;2011;corpus;http://hdl.handle.net/11372/LRT-676;pol;downloadable_files_count: 0;Poland;Shared initiative of Institute of Computer Science at Polish Academy of Sciences (IPI PAN);Institute of Computer Science, Polish Academy of Sciences;Institute of Polish Language at the Polish Academy of Sciences;Polish Scientific Publishers PWN;Department of Computational and Corpus Linguistics at the University of \u0141\u00f3d\u017a;http://nkjp.pl",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a34dd0e3-a417-5bff-b0a6-a06aa2021c0f",
-    "notes": [
-        "In (advanced) preparation: a reference corpus of Polish language containing hundreds millions of words."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-676"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "National Corpus of Polish"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a3504224-9ed4-515e-bee9-14b247e2a973.json b/oaitestdata/clarin-oai_dc/SET_1/json/a3504224-9ed4-515e-bee9-14b247e2a973.json
deleted file mode 100644
index 2c7be8b4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a3504224-9ed4-515e-bee9-14b247e2a973.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5687",
-    "MetadataAccess": [
-        "oai:ota:oucs:5687"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Logan, William, 1747-1772."
-    ],
-    "fulltext": "oai:ota:oucs:5687;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5687.xml;Observations on the effects of sea water in the scurvy and scrophula: in which a new theory of those diseases is attempted; ... By William Logan.;Logan, William, 1747-1772.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a3504224-9ed4-515e-bee9-14b247e2a973",
-    "oai_identifier": [
-        "oai:ota:oucs:5687"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Observations on the effects of sea water in the scurvy and scrophula: in which a new theory of those diseases is attempted; ... By William Logan."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5687.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a366d48e-fee3-5886-9541-e820d0124108.json b/oaitestdata/clarin-oai_dc/SET_1/json/a366d48e-fee3-5886-9541-e820d0124108.json
deleted file mode 100644
index b09e60e0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a366d48e-fee3-5886-9541-e820d0124108.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Jagiellonian University"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/zip",
-        "application/vnd.oasis.opendocument.text",
-        "downloadable_files_count: 16",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/405",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/405"
-    ],
-    "PID": "http://hdl.handle.net/11321/405",
-    "PublicationTimestamp": "2017-06-29T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Jagiellonian University"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Mazur, Rafa\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/405;2018-12-06T18:02:31Z;hdl_11321_3;hdl_11321_4;Korpus testowy;Mazur, Rafa\u0142;korpus tekstowy;Korpus testowy na warsztaty z wykorzystaniem systemu Dspace;2017-06-29;corpus;http://hdl.handle.net/11321/405;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;application/vnd.oasis.opendocument.text;text/plain;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;downloadable_files_count: 16;Jagiellonian University",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a366d48e-fee3-5886-9541-e820d0124108",
-    "notes": [
-        "Korpus testowy na warsztaty z wykorzystaniem systemu Dspace"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/405"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "korpus tekstowy"
-        }
-    ],
-    "title": [
-        "Korpus testowy"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a3941689-17a0-5b08-8e5e-a5d580fa4dc0.json b/oaitestdata/clarin-oai_dc/SET_1/json/a3941689-17a0-5b08-8e5e-a5d580fa4dc0.json
deleted file mode 100644
index 8273455d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a3941689-17a0-5b08-8e5e-a5d580fa4dc0.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/26",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/26"
-    ],
-    "PID": "http://hdl.handle.net/10794/26",
-    "PublicationTimestamp": "2015-12-09T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/26;2017-10-27T15:20:57Z;hdl_10794_1;hdl_10794_2;Hellquist's Swedish etymology (2017-10-16);Hellquists Svensk etymologisk ordbok (2017-10-16);n/a, n/a;Swedish;Etymology;Dictionary;Hellquist's Swedish etymology.;Hellquists Svensk etymologisk ordbok.;2015-12-09;lexicalConceptualResource;http://hdl.handle.net/10794/26;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/hellqvist",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a3941689-17a0-5b08-8e5e-a5d580fa4dc0",
-    "notes": [
-        "Hellquist's Swedish etymology.",
-        "Hellquists Svensk etymologisk ordbok."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/26"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Etymology"
-        },
-        {
-            "name": "Dictionary"
-        }
-    ],
-    "title": [
-        "Hellquist's Swedish etymology (2017-10-16)",
-        "Hellquists Svensk etymologisk ordbok (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a39a6b1c-bace-501e-8d38-e3ba110d79b4.json b/oaitestdata/clarin-oai_dc/SET_1/json/a39a6b1c-bace-501e-8d38-e3ba110d79b4.json
deleted file mode 100644
index 809c860e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a39a6b1c-bace-501e-8d38-e3ba110d79b4.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/271",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/271"
-    ],
-    "PID": "http://hdl.handle.net/11321/271",
-    "PublicationTimestamp": "2016-04-25T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "Piasecki, Maciej"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/271;2016-05-31T12:08:35Z;hdl_11321_3;hdl_11321_4;SuperMatrix;Piasecki, Maciej;supermatrix;sm;SuperMatrix is a system to support automatic extraction of semantic relations, based on the analysis of large text corpora. System was developed as a tool for expansion of Polish wordnet (S\u0142owosie\u0107).Expansion consist of two steps: system suggests a potential links between lexical units. Linguist verify these suggestions and decide which form will go to wordnet. This speeded up the work and preserve the integrity of data entry.;2016-04-25;toolService;http://hdl.handle.net/11321/271;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 1;Wroc\u0142aw University of Technology;http://clarin-pl.eu/en/home-page/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a39a6b1c-bace-501e-8d38-e3ba110d79b4",
-    "notes": [
-        "SuperMatrix is a system to support automatic extraction of semantic relations, based on the analysis of large text corpora. System was developed as a tool for expansion of Polish wordnet (S\u0142owosie\u0107).Expansion consist of two steps: system suggests a potential links between lexical units. Linguist verify these suggestions and decide which form will go to wordnet. This speeded up the work and preserve the integrity of data entry."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/271"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "supermatrix"
-        },
-        {
-            "name": "sm"
-        }
-    ],
-    "title": [
-        "SuperMatrix"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a39dcda5-2109-593e-b473-0ab9e83de506.json b/oaitestdata/clarin-oai_dc/SET_1/json/a39dcda5-2109-593e-b473-0ab9e83de506.json
deleted file mode 100644
index e6d8076e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a39dcda5-2109-593e-b473-0ab9e83de506.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/261",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/261"
-    ],
-    "PID": "http://hdl.handle.net/11321/261",
-    "PublicationTimestamp": "2016-04-30T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "Wr\u00f3blewska, Alina"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/261;2016-05-16T18:34:44Z;hdl_11321_3;hdl_11321_4;DG-POLFIE: POLFIE and Malt-based syntactic parser;Wr\u00f3blewska, Alina;parser;LFG;dependency parsing;DG-POLFIE is a prototypical parser that tries to merge parse fragments generated by POLFIE using Polish Dependency Parser\r\n\r\nDG-POLFIE aims to improve the coverage of the POLFIE parser (i.e. the percentage of sentences with at least one analysis). In order to increase the number of Polish sentences and constructions that could be parsed with the POLFIE-based parser, DG-POLFIE defines some rules that use depenency structure to build full parse from the FRAGMENTS provided by POLFIE.;2016-04-30;toolService;http://hdl.handle.net/11321/261;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 1;Institute of Computer Science, Polish Academy of Sciences",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a39dcda5-2109-593e-b473-0ab9e83de506",
-    "notes": [
-        "DG-POLFIE is a prototypical parser that tries to merge parse fragments generated by POLFIE using Polish Dependency Parser\r\n\r\nDG-POLFIE aims to improve the coverage of the POLFIE parser (i.e. the percentage of sentences with at least one analysis). In order to increase the number of Polish sentences and constructions that could be parsed with the POLFIE-based parser, DG-POLFIE defines some rules that use depenency structure to build full parse from the FRAGMENTS provided by POLFIE."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/261"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parser"
-        },
-        {
-            "name": "LFG"
-        },
-        {
-            "name": "dependency parsing"
-        }
-    ],
-    "title": [
-        "DG-POLFIE: POLFIE and Malt-based syntactic parser"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a3b31402-27b4-5302-abf9-e6bfceff56f8.json b/oaitestdata/clarin-oai_dc/SET_1/json/a3b31402-27b4-5302-abf9-e6bfceff56f8.json
deleted file mode 100644
index c4a0aaff..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a3b31402-27b4-5302-abf9-e6bfceff56f8.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "between 512 KB and 1 MB "
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0302",
-    "MetadataAccess": [
-        "oai:ota:oucs:0302"
-    ],
-    "PublicationTimestamp": "1528-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1528"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Courtesy books"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Castiglione, Baldassare,  conte,  1478-1529"
-    ],
-    "fulltext": "oai:ota:oucs:0302;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0302.xml; Il libro del cortegiano  / compiled by J.R. Woodhouse;Castiglione, Baldassare,  conte,  1478-1529;1528;text_and_corpus_linguistics;Courtesy books -- Italy -- 16th century;ita;Oxford Text Archive, University of Oxford;between 512 KB and 1 MB ;Text;Courtesy books;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a3b31402-27b4-5302-abf9-e6bfceff56f8",
-    "oai_identifier": [
-        "oai:ota:oucs:0302"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Courtesy books -- Italy -- th century"
-        }
-    ],
-    "title": [
-        " Il libro del cortegiano  / compiled by J.R. Woodhouse"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0302.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a3bc11cc-ba18-52bd-9c6e-8dbb7a190b47.json b/oaitestdata/clarin-oai_dc/SET_1/json/a3bc11cc-ba18-52bd-9c6e-8dbb7a190b47.json
deleted file mode 100644
index 1319bf0b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a3bc11cc-ba18-52bd-9c6e-8dbb7a190b47.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Arts, Institute of the Czech National Corpus"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2579",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2579"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2579",
-    "PublicationTimestamp": "2017-12-28T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Arts, Institute of the Czech National Corpus"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "License Agreement for Czech National Corpus Data",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/license-cnc-data",
-        "ACA"
-    ],
-    "author": [
-        "Kop\u0159ivov\u00e1, Marie",
-        "Luke\u0161, David",
-        "Poukarov\u00e1, Petra",
-        "\u0160karpov\u00e1, Marie",
-        "Komrskov\u00e1, Zuzana"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2579;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;ORTOFON v1: balanced corpus of informal spoken Czech with multi-tier transcription (transcriptions & audio);Kop\u0159ivov\u00e1, Marie;Komrskov\u00e1, Zuzana;Luke\u0161, David;Poukarov\u00e1, Petra;\u0160karpov\u00e1, Marie;balanced corpus;spoken language;informal language;Czech;ORTOFON v1 is designed as a representation of authentic spoken Czech used in informal situations (private environment, spontaneity, unpreparedness etc.) in the area of the whole Czech Republic. The corpus is composed of 332 recordings from 2012\u20132017 and contains 1 014 786 orthographic words (i.e. a total of 1 236 508 tokens including punctuation); a total of 624 different speakers appear in the probes. ORTOFON v1 is fully balanced regarding the basic sociolinguistic speaker categories (gender, age group, level of education and region of childhood residence).\r\n\r\nThe transcription is linked to the corresponding audio track. Unlike the ORAL-series corpora, the transcription was carried out on two main tiers, orthographic and phonetic, supplemented by an additional metalanguage tier. ORTOFON v1 is lemmatized and morphologically tagged. The (anonymized) transcriptions are provided in the XML Elan Annotation format, audio (with corresponding anonymization beeps) is in uncompressed 16-bit PCM WAV, mono, 16 kHz format.\r\n\r\nAnother format option of the transcriptions is also available under less restrictive CC BY-NC-SA license at http://hdl.handle.net/11234/1-2580;2017-12-28;corpus;http://hdl.handle.net/11234/1-2579;ces;License Agreement for Czech National Corpus Data;https://lindat.mff.cuni.cz/repository/xmlui/page/license-cnc-data;ACA;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Arts, Institute of the Czech National Corpus;http://wiki.korpus.cz/doku.php/en:cnk:ortofon",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a3bc11cc-ba18-52bd-9c6e-8dbb7a190b47",
-    "notes": [
-        "ORTOFON v1 is designed as a representation of authentic spoken Czech used in informal situations (private environment, spontaneity, unpreparedness etc.) in the area of the whole Czech Republic. The corpus is composed of 332 recordings from 2012\u20132017 and contains 1 014 786 orthographic words (i.e. a total of 1 236 508 tokens including punctuation); a total of 624 different speakers appear in the probes. ORTOFON v1 is fully balanced regarding the basic sociolinguistic speaker categories (gender, age group, level of education and region of childhood residence).\r\n\r\nThe transcription is linked to the corresponding audio track. Unlike the ORAL-series corpora, the transcription was carried out on two main tiers, orthographic and phonetic, supplemented by an additional metalanguage tier. ORTOFON v1 is lemmatized and morphologically tagged. The (anonymized) transcriptions are provided in the XML Elan Annotation format, audio (with corresponding anonymization beeps) is in uncompressed 16-bit PCM WAV, mono, 16 kHz format.\r\n\r\nAnother format option of the transcriptions is also available under less restrictive CC BY-NC-SA license at http://hdl.handle.net/11234/1-2580"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2579"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "balanced corpus"
-        },
-        {
-            "name": "spoken language"
-        },
-        {
-            "name": "informal language"
-        },
-        {
-            "name": "Czech"
-        }
-    ],
-    "title": [
-        "ORTOFON v1: balanced corpus of informal spoken Czech with multi-tier transcription (transcriptions & audio)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a3c2476b-ae8a-5485-90fa-d1b49f7f46c7.json b/oaitestdata/clarin-oai_dc/SET_1/json/a3c2476b-ae8a-5485-90fa-d1b49f7f46c7.json
deleted file mode 100644
index 41943d66..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a3c2476b-ae8a-5485-90fa-d1b49f7f46c7.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Royster, Paul"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 402 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1596",
-    "MetadataAccess": [
-        "oai:ota:oucs:1596"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Chronicles"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Jefferson, Thomas, 1743-1826"
-    ],
-    "fulltext": "oai:ota:oucs:1596;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/1596.xml;Notes on the state of Virginia / Thomas Jefferson;Jefferson, Thomas, 1743-1826;text_and_corpus_linguistics;History -- Virginia -- 18th century;Oxford Text Archive, University of Oxford;Royster, Paul;text/sgml;(1 file : ca. 402 KB);Text;Chronicles;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a3c2476b-ae8a-5485-90fa-d1b49f7f46c7",
-    "oai_identifier": [
-        "oai:ota:oucs:1596"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "History -- Virginia -- th century"
-        }
-    ],
-    "title": [
-        "Notes on the state of Virginia / Thomas Jefferson"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1596.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a3c8c2cc-02d6-5780-8854-1ca5a5a19b7d.json b/oaitestdata/clarin-oai_dc/SET_1/json/a3c8c2cc-02d6-5780-8854-1ca5a5a19b7d.json
deleted file mode 100644
index 2eefdc46..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a3c8c2cc-02d6-5780-8854-1ca5a5a19b7d.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Formal Linguistics Department of Warsaw University"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "image/png",
-        "downloadable_files_count: 2",
-        "application/octet-stream"
-    ],
-    "Language": [],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/469",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/469"
-    ],
-    "PID": "http://hdl.handle.net/11321/469",
-    "PublicationTimestamp": "2015-04-15T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Formal Linguistics Department of Warsaw University"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "Bie\u0144, Janusz S."
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/469;2018-05-21T08:06:08Z;hdl_11321_3;hdl_11321_4;Djview for Shapes - a demonstration (Open Virtual Appliance);Bie\u0144, Janusz S.;scans DjVu;A shape browser for DjVu documents;2015-04-15;toolService;http://hdl.handle.net/11321/469;N/A;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;image/png;application/octet-stream;downloadable_files_count: 2;Formal Linguistics Department of Warsaw University;https://bitbucket.org/jsbien/ndt",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a3c8c2cc-02d6-5780-8854-1ca5a5a19b7d",
-    "notes": [
-        "A shape browser for DjVu documents"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/469"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "scans DjVu"
-        }
-    ],
-    "title": [
-        "Djview for Shapes - a demonstration (Open Virtual Appliance)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a3cf458a-fe7a-521f-82f4-1826f76aafb6.json b/oaitestdata/clarin-oai_dc/SET_1/json/a3cf458a-fe7a-521f-82f4-1826f76aafb6.json
deleted file mode 100644
index 12266c30..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a3cf458a-fe7a-521f-82f4-1826f76aafb6.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Linguistic Data Consortium (LDC)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-602",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-602"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-602",
-    "PublicationTimestamp": "2007-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2007"
-    ],
-    "Publisher": [
-        "Linguistic Data Consortium (LDC)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United States"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-602;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;English Gigaword;3rd edition contains millions of words from 6 different news wires.;2007;corpus;http://hdl.handle.net/11372/LRT-602;eng;downloadable_files_count: 0;United States;Linguistic Data Consortium (LDC);http://www.ldc.upenn.edu/Catalog/CatalogEntry.jsp?catalogId=LDC2007T07",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a3cf458a-fe7a-521f-82f4-1826f76aafb6",
-    "notes": [
-        "3rd edition contains millions of words from 6 different news wires."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-602"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "English Gigaword"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a3d4a034-357f-5647-a82d-6abbda812b73.json b/oaitestdata/clarin-oai_dc/SET_1/json/a3d4a034-357f-5647-a82d-6abbda812b73.json
deleted file mode 100644
index 7c0f0015..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a3d4a034-357f-5647-a82d-6abbda812b73.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Politechnika Wroc\u0142awska"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 209",
-        "application/zip",
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/49",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/49"
-    ],
-    "PID": "http://hdl.handle.net/11321/49",
-    "PublicationTimestamp": "2015-01-27T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Politechnika Wroc\u0142awska"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Ba\u0144ka-Kowalczyk, Magdalena"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/49;2017-06-28T20:25:25Z;hdl_11321_3;hdl_11321_4;The 8' th of March Corpus;Ba\u0144ka-Kowalczyk, Magdalena;International Women's Day;woman;The articles are especially concerned with the International Women's Day;2015-01-27;corpus;http://hdl.handle.net/11321/49;pol;Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0);http://creativecommons.org/licenses/by-nc-nd/3.0/;CC;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/msword;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/zip;text/plain; charset=utf-8;downloadable_files_count: 209;Politechnika Wroc\u0142awska",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a3d4a034-357f-5647-a82d-6abbda812b73",
-    "notes": [
-        "The articles are especially concerned with the International Women's Day"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/49"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "International Womens Day"
-        },
-        {
-            "name": "woman"
-        }
-    ],
-    "title": [
-        "The 8' th of March Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a3fec790-02a7-5bea-9ee8-01cc548f62c0.json b/oaitestdata/clarin-oai_dc/SET_1/json/a3fec790-02a7-5bea-9ee8-01cc548f62c0.json
deleted file mode 100644
index fa33d6ac..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a3fec790-02a7-5bea-9ee8-01cc548f62c0.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/8",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/8"
-    ],
-    "PID": "http://hdl.handle.net/11321/8",
-    "PublicationTimestamp": "2011-12-30T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Piasecki, Maciej"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/8;2018-08-27T08:01:51Z;hdl_11321_3;hdl_11321_4;ChunkRel WS;Piasecki, Maciej;ChunkRel-WS is a prototype service for recognition of three syntactic relations between chunks. The service may be run against plain text (input format: text), then the necessary processing steps will be run automatically (tagger and chunker). You can also process already tagged and chunked input (input format: ccl). The output will be enriched with inter-chunk relations. The service is based on a prototype implementation, hence it works slowly. The configuration used here operates on shallow syntactic annotation scheme from the KPWr corpus.;2011-12-30;toolService;http://hdl.handle.net/11321/8;pol;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 1;Wroc\u0142aw University of Technology;http://ws.clarin-pl.eu/chunker.shtml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a3fec790-02a7-5bea-9ee8-01cc548f62c0",
-    "notes": [
-        "ChunkRel-WS is a prototype service for recognition of three syntactic relations between chunks. The service may be run against plain text (input format: text), then the necessary processing steps will be run automatically (tagger and chunker). You can also process already tagged and chunked input (input format: ccl). The output will be enriched with inter-chunk relations. The service is based on a prototype implementation, hence it works slowly. The configuration used here operates on shallow syntactic annotation scheme from the KPWr corpus."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/8"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "ChunkRel WS"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a40db21b-6e84-5b3c-9dba-bbc3a0090d40.json b/oaitestdata/clarin-oai_dc/SET_1/json/a40db21b-6e84-5b3c-9dba-bbc3a0090d40.json
deleted file mode 100644
index a619f13f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a40db21b-6e84-5b3c-9dba-bbc3a0090d40.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4087",
-    "MetadataAccess": [
-        "oai:ota:oucs:4087"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Burke, Edmund, 1729-1797."
-    ],
-    "fulltext": "oai:ota:oucs:4087;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4087.xml;A philosophical enquiry into the origin of our ideas of the sublime and beautiful;Burke, Edmund, 1729-1797.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a40db21b-6e84-5b3c-9dba-bbc3a0090d40",
-    "oai_identifier": [
-        "oai:ota:oucs:4087"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A philosophical enquiry into the origin of our ideas of the sublime and beautiful"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4087.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a42c635e-1862-5a3d-b630-ebcdf2778d3a.json b/oaitestdata/clarin-oai_dc/SET_1/json/a42c635e-1862-5a3d-b630-ebcdf2778d3a.json
deleted file mode 100644
index 1235c0df..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a42c635e-1862-5a3d-b630-ebcdf2778d3a.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/x-bzip2",
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 6"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-B847-6",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-B847-6"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0006-B847-6",
-    "PublicationTimestamp": "2012-06-21T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Spoustov\u00e1, Johanka",
-        "Spousta, Miroslav"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-B847-6;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;CWC2011;Spoustov\u00e1, Johanka;Spousta, Miroslav;corpus;Czech;web;Web corpus of Czech, created in 2011. Contains newspapers+magazines, discussions, blogs. See http://www.lrec-conf.org/proceedings/lrec2012/summaries/120.html for details.;2012-06-21;corpus;http://hdl.handle.net/11858/00-097C-0000-0006-B847-6;ces;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;PUB;application/x-bzip2;application/x-bzip2;application/x-bzip2;application/x-bzip2;application/x-bzip2;application/x-bzip2;text/plain; charset=utf-8;downloadable_files_count: 6;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a42c635e-1862-5a3d-b630-ebcdf2778d3a",
-    "notes": [
-        "Web corpus of Czech, created in 2011. Contains newspapers+magazines, discussions, blogs. See http://www.lrec-conf.org/proceedings/lrec2012/summaries/120.html for details."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-B847-6"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "Czech"
-        },
-        {
-            "name": "web"
-        }
-    ],
-    "title": [
-        "CWC2011"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a43b62d3-c514-5d51-8d3d-08afa62de925.json b/oaitestdata/clarin-oai_dc/SET_1/json/a43b62d3-c514-5d51-8d3d-08afa62de925.json
deleted file mode 100644
index 24164920..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a43b62d3-c514-5d51-8d3d-08afa62de925.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "ZRC SAZU"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1094",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1094"
-    ],
-    "PID": "http://hdl.handle.net/11356/1094",
-    "PublicationTimestamp": "1996-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1996"
-    ],
-    "Publisher": [
-        "ZRC SAZU"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Hajn\u0161ek-Holz, Milena",
-        "Jakopin, Primo\u017e"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1094;2017-04-26T11:39:25Z;hdl_11356_1023;hdl_11356_1024;Reverse dictionary of Slovenian language;Hajn\u0161ek-Holz, Milena;Jakopin, Primo\u017e;dictionary;lexicography;reverse dictionary;dictionary a tergo;Reverse dictionary of Slovenian language contains 115,355 headwords and is based on the Dictionary of the Slovenian Standard Language (DSSL). Headwords are sorted a tergo (by last-to-first letter order) and include headwords from DSSL and their variants, full subheadwords and their variants, short subheadwords and subheadwords listed as special verb forms. In addition, information on oblique forms, pronunciation, part of speech and dynamic accent is included.\r\n\r\nThis dictionary was published as a printed book:\r\nHajn\u0161ek-Holz, Milena, Jakopin, Primo\u017e. Odzadnji slovar slovenskega jezika po Slovarju slovenskega knji\u017enega jezika. Ljubljana : Znanstvenoraziskovalni center Slovenske akademije znanosti in umetnosti : Slovenska akademija znanosti in umetnosti, 1996. ISBN 961-6182-19-6.;1996;lexicalConceptualResource;http://hdl.handle.net/11356/1094;slv;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;ZRC SAZU;http://isjfr.zrc-sazu.si/en/publikacije/odzadnji-slovar-slovenskega-jezika-po-slovarju-slovenskega-knjzinega-jezika-1#v",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a43b62d3-c514-5d51-8d3d-08afa62de925",
-    "notes": [
-        "Reverse dictionary of Slovenian language contains 115,355 headwords and is based on the Dictionary of the Slovenian Standard Language (DSSL). Headwords are sorted a tergo (by last-to-first letter order) and include headwords from DSSL and their variants, full subheadwords and their variants, short subheadwords and subheadwords listed as special verb forms. In addition, information on oblique forms, pronunciation, part of speech and dynamic accent is included.\r\n\r\nThis dictionary was published as a printed book:\r\nHajn\u0161ek-Holz, Milena, Jakopin, Primo\u017e. Odzadnji slovar slovenskega jezika po Slovarju slovenskega knji\u017enega jezika. Ljubljana : Znanstvenoraziskovalni center Slovenske akademije znanosti in umetnosti : Slovenska akademija znanosti in umetnosti, 1996. ISBN 961-6182-19-6."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1094"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "dictionary"
-        },
-        {
-            "name": "lexicography"
-        },
-        {
-            "name": "reverse dictionary"
-        },
-        {
-            "name": "dictionary tergo"
-        }
-    ],
-    "title": [
-        "Reverse dictionary of Slovenian language"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a441d52e-584b-5240-8695-9de93aa76a4f.json b/oaitestdata/clarin-oai_dc/SET_1/json/a441d52e-584b-5240-8695-9de93aa76a4f.json
deleted file mode 100644
index 43f8bc4c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a441d52e-584b-5240-8695-9de93aa76a4f.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Universyty of Silesia"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 26",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/348",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/348"
-    ],
-    "PID": "http://hdl.handle.net/11321/348",
-    "PublicationTimestamp": "2017-04-25T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Universyty of Silesia"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Ficek, Ewa"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/348;2017-04-25T14:09:27Z;hdl_11321_3;hdl_11321_4;Genology;Ficek, Ewa;linguistic;Corpus;2017-04-25;corpus;http://hdl.handle.net/11321/348;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;downloadable_files_count: 26;Universyty of Silesia;http://us.edu.pl",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a441d52e-584b-5240-8695-9de93aa76a4f",
-    "notes": [
-        "Corpus"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/348"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "linguistic"
-        }
-    ],
-    "title": [
-        "Genology"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a45a9cc7-f499-5602-ba97-9d104d837ef6.json b/oaitestdata/clarin-oai_dc/SET_1/json/a45a9cc7-f499-5602-ba97-9d104d837ef6.json
deleted file mode 100644
index ffb3a430..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a45a9cc7-f499-5602-ba97-9d104d837ef6.json
+++ /dev/null
@@ -1,92 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Electrical Engineering and Computer Science, University of Maribor"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 3",
-        "application/zip"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1158",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1158"
-    ],
-    "PID": "http://hdl.handle.net/11356/1158",
-    "PublicationTimestamp": "2017-10-11T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Faculty of Electrical Engineering and Computer Science, University of Maribor"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11356/1190",
-        "http://hdl.handle.net/11356/1069"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "Sepesy Mau\u010dec, Mirjam",
-        "Erjavec, Toma\u017e",
-        "Poto\u010dnik, Toma\u017e",
-        "Verdonik, Darinka"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1158;2018-10-24T20:49:46Z;hdl_11356_1023;hdl_11356_1024;Spoken corpus Gos VideoLectures 2.0 (transcription);Verdonik, Darinka;Poto\u010dnik, Toma\u017e;Sepesy Mau\u010dec, Mirjam;Erjavec, Toma\u017e;speech database;spoken corpus;academic speech;speech transcription;speech recognition;TEI;Gos VideoLectures is an add-on to the Gos reference corpus of spoken Slovene (http://hdl.handle.net/11356/1040), and covers public academic speech. \r\nThe Gos VideoLectures corpus contains a selection of public lectures available through the web portal Videolectures.net provided by the Jo\u017eef Stefan Institute, and covers 9.8 hours of speech. \r\nThis resource contains only annotated transcriptions of the corpus \u2013 audio recordings are available at http://hdl.handle.net/11356/1159.\r\n\r\nAll transcriptions for Gos VideoLectures were done manually and carefully checked. The main guidelines for transcription were those of the Gos corpus (http://www.korpus-gos.net/Support/About). The transcription tool Transcriber 1.5.1 (http://trans.sourceforge.net/en/presentation.php) was used for making transcriptions. It can be also used for reading or exporting transcriptions (.trs files) to different formats.\r\n\r\nThe transcriptions comprise the TRS files with tabular metadata, their conversion to TEI and to the CWB vertical file format. Each recording has two TRS files, one with pronunciation-based and the other with the standardised/normalised transcription. The TEI and CWB encodings join these two transcriptions at the token level, with the normalised words being also automatically PoS tagged and lemmatised.\r\n\r\nThe corpus can be used for training continuous speech recognition for Slovene language, for phonetic research or any other research of Slovene academic speech.;2017-10-11;corpus;http://hdl.handle.net/11356/1158;slv;http://hdl.handle.net/11356/1190;http://hdl.handle.net/11356/1069;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;https://creativecommons.org/licenses/by/4.0/;text/plain; charset=utf-8;application/zip;application/zip;application/zip;downloadable_files_count: 3;Faculty of Electrical Engineering and Computer Science, University of Maribor",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a45a9cc7-f499-5602-ba97-9d104d837ef6",
-    "notes": [
-        "Gos VideoLectures is an add-on to the Gos reference corpus of spoken Slovene (http://hdl.handle.net/11356/1040), and covers public academic speech. \r\nThe Gos VideoLectures corpus contains a selection of public lectures available through the web portal Videolectures.net provided by the Jo\u017eef Stefan Institute, and covers 9.8 hours of speech. \r\nThis resource contains only annotated transcriptions of the corpus \u2013 audio recordings are available at http://hdl.handle.net/11356/1159.\r\n\r\nAll transcriptions for Gos VideoLectures were done manually and carefully checked. The main guidelines for transcription were those of the Gos corpus (http://www.korpus-gos.net/Support/About). The transcription tool Transcriber 1.5.1 (http://trans.sourceforge.net/en/presentation.php) was used for making transcriptions. It can be also used for reading or exporting transcriptions (.trs files) to different formats.\r\n\r\nThe transcriptions comprise the TRS files with tabular metadata, their conversion to TEI and to the CWB vertical file format. Each recording has two TRS files, one with pronunciation-based and the other with the standardised/normalised transcription. The TEI and CWB encodings join these two transcriptions at the token level, with the normalised words being also automatically PoS tagged and lemmatised.\r\n\r\nThe corpus can be used for training continuous speech recognition for Slovene language, for phonetic research or any other research of Slovene academic speech."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1158"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech database"
-        },
-        {
-            "name": "spoken corpus"
-        },
-        {
-            "name": "academic speech"
-        },
-        {
-            "name": "speech transcription"
-        },
-        {
-            "name": "speech recognition"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "Spoken corpus Gos VideoLectures 2.0 (transcription)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a4ae3c01-837b-5c5f-a60d-0c7eea39888d.json b/oaitestdata/clarin-oai_dc/SET_1/json/a4ae3c01-837b-5c5f-a60d-0c7eea39888d.json
deleted file mode 100644
index ed012acf..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a4ae3c01-837b-5c5f-a60d-0c7eea39888d.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-959",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-959"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-959",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-959;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Svan;ca. 1.000.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-959;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#svanica",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a4ae3c01-837b-5c5f-a60d-0c7eea39888d",
-    "notes": [
-        "ca. 1.000.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-959"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Svan"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a4bb3a21-c7b7-5fa2-ab70-4bcd5887b201.json b/oaitestdata/clarin-oai_dc/SET_1/json/a4bb3a21-c7b7-5fa2-ab70-4bcd5887b201.json
deleted file mode 100644
index b1ad9df0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a4bb3a21-c7b7-5fa2-ab70-4bcd5887b201.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4368",
-    "MetadataAccess": [
-        "oai:ota:oucs:4368"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "O'Hara, Kane, 1714?-1782."
-    ],
-    "fulltext": "oai:ota:oucs:4368;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4368.xml;April-day, a burletta, in three acts. Written by the author of Midas. As it is performed at the Theatre Royal in the Hay-Market. The music composed by Dr. Arnold;O'Hara, Kane, 1714?-1782.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a4bb3a21-c7b7-5fa2-ab70-4bcd5887b201",
-    "oai_identifier": [
-        "oai:ota:oucs:4368"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "April-day, a burletta, in three acts. Written by the author of Midas. As it is performed at the Theatre Royal in the Hay-Market. The music composed by Dr. Arnold"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4368.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a4cd7658-4fac-5d5e-a778-4bff36e9a1ba.json b/oaitestdata/clarin-oai_dc/SET_1/json/a4cd7658-4fac-5d5e-a778-4bff36e9a1ba.json
deleted file mode 100644
index ac53a037..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a4cd7658-4fac-5d5e-a778-4bff36e9a1ba.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5223",
-    "MetadataAccess": [
-        "oai:ota:oucs:5223"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dibdin, Charles, 1745-1814."
-    ],
-    "fulltext": "oai:ota:oucs:5223;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5223.xml;A complete history of the English stage: ... by Mr. Dibdin. ... [pt.3];Dibdin, Charles, 1745-1814.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a4cd7658-4fac-5d5e-a778-4bff36e9a1ba",
-    "oai_identifier": [
-        "oai:ota:oucs:5223"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A complete history of the English stage: ... by Mr. Dibdin. ... [pt.3]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5223.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a4d00a96-b7d1-5563-b739-b13894d7bb81.json b/oaitestdata/clarin-oai_dc/SET_1/json/a4d00a96-b7d1-5563-b739-b13894d7bb81.json
deleted file mode 100644
index e0663747..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a4d00a96-b7d1-5563-b739-b13894d7bb81.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "University of West Bohemia, Department of Cybernetics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "audio/x-wav",
-        "text/xml",
-        "downloadable_files_count: 37",
-        "application/pdf",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0005-CF9C-4",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0005-CF9C-4"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0005-CF9C-4",
-    "PublicationTimestamp": "2012-03-28T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "University of West Bohemia, Department of Cybernetics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Pra\u017e\u00e1k, Ale\u0161",
-        "\u0160m\u00eddl, Lubo\u0161"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0005-CF9C-4;2018-10-29T12:50:32Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Czech Parliament Meetings;Pra\u017e\u00e1k, Ale\u0161;\u0160m\u00eddl, Lubo\u0161;speech corpus;acoustic model;speaker identification;speaker verification;The corpus consists of recordings from the Chamber of Deputies of the Parliament of the Czech Republic. It currently consists of 88 hours of speech data, which corresponds roughly to 0.5 million tokens. The annotation process is semi-automatic, as we are able to perform the speech recognition on the data with high accuracy (over 90%) and consequently align the resulting automatic transcripts with the speech. The annotator\u2019s task is then to check the transcripts, correct errors, add proper punctuation and label speech sections with information about the speaker. The resulting corpus is therefore suitable for both acoustic model training for ASR purposes and training of speaker identification and/or verification systems. The archive contains 18 sound files (WAV PCM, 16-bit, 44.1 kHz, mono) and corresponding transcriptions in XML-based standard Transcriber format (http://trans.sourceforge.net)\r\n\r\nThe date of airing of a particular recording is encoded in the filename in the form SOUND_YYMMDD_*. Note that the recordings are usually aired in the early morning on the day following the actual Parliament session. If the recording is too long to fit in the broadcasting scheme, it is divided into several parts and aired on the consecutive days.;2012-03-28;corpus;ZCU_CZ_Parliament;http://hdl.handle.net/11858/00-097C-0000-0005-CF9C-4;ces;Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0);http://creativecommons.org/licenses/by-nc-nd/3.0/;PUB;text/xml;audio/x-wav;text/xml;audio/x-wav;text/xml;audio/x-wav;text/xml;audio/x-wav;text/xml;audio/x-wav;text/xml;audio/x-wav;text/xml;audio/x-wav;text/xml;audio/x-wav;text/xml;audio/x-wav;text/xml;audio/x-wav;text/xml;audio/x-wav;text/xml;audio/x-wav;text/xml;audio/x-wav;text/xml;audio/x-wav;text/xml;audio/x-wav;text/xml;audio/x-wav;text/xml;audio/x-wav;text/xml;audio/x-wav;application/pdf;text/plain; charset=utf-8;downloadable_files_count: 37;University of West Bohemia, Department of Cybernetics",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a4d00a96-b7d1-5563-b739-b13894d7bb81",
-    "notes": [
-        "The corpus consists of recordings from the Chamber of Deputies of the Parliament of the Czech Republic. It currently consists of 88 hours of speech data, which corresponds roughly to 0.5 million tokens. The annotation process is semi-automatic, as we are able to perform the speech recognition on the data with high accuracy (over 90%) and consequently align the resulting automatic transcripts with the speech. The annotator\u2019s task is then to check the transcripts, correct errors, add proper punctuation and label speech sections with information about the speaker. The resulting corpus is therefore suitable for both acoustic model training for ASR purposes and training of speaker identification and/or verification systems. The archive contains 18 sound files (WAV PCM, 16-bit, 44.1 kHz, mono) and corresponding transcriptions in XML-based standard Transcriber format (http://trans.sourceforge.net)\r\n\r\nThe date of airing of a particular recording is encoded in the filename in the form SOUND_YYMMDD_*. Note that the recordings are usually aired in the early morning on the day following the actual Parliament session. If the recording is too long to fit in the broadcasting scheme, it is divided into several parts and aired on the consecutive days."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0005-CF9C-4"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech corpus"
-        },
-        {
-            "name": "acoustic model"
-        },
-        {
-            "name": "speaker identification"
-        },
-        {
-            "name": "speaker verification"
-        }
-    ],
-    "title": [
-        "Czech Parliament Meetings"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a4fbba84-2ca8-574a-b6ce-c3997b927cc5.json b/oaitestdata/clarin-oai_dc/SET_1/json/a4fbba84-2ca8-574a-b6ce-c3997b927cc5.json
deleted file mode 100644
index df236c57..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a4fbba84-2ca8-574a-b6ce-c3997b927cc5.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3332",
-    "MetadataAccess": [
-        "oai:ota:oucs:3332"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Defoe, Daniel, 1661?-1731."
-    ],
-    "fulltext": "oai:ota:oucs:3332;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3332.xml;Advice to all parties: By the author of The true-born English-man.;Defoe, Daniel, 1661?-1731.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a4fbba84-2ca8-574a-b6ce-c3997b927cc5",
-    "oai_identifier": [
-        "oai:ota:oucs:3332"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Advice to all parties: By the author of The true-born English-man."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3332.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a5071678-d189-5d5d-9e76-94ee50fbf3f2.json b/oaitestdata/clarin-oai_dc/SET_1/json/a5071678-d189-5d5d-9e76-94ee50fbf3f2.json
deleted file mode 100644
index 188b8a03..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a5071678-d189-5d5d-9e76-94ee50fbf3f2.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1417",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1417"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1417",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1417;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Catalan Digital Press;This RESTful service accesses part of the Hemeroteca Digital de l\u2019Arxiu Municipal de Girona (digital press archive from the Girona city council), specifically Catalan press from 2003. The service uses the SRU protocol.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1417;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a5071678-d189-5d5d-9e76-94ee50fbf3f2",
-    "notes": [
-        "This RESTful service accesses part of the Hemeroteca Digital de l\u2019Arxiu Municipal de Girona (digital press archive from the Girona city council), specifically Catalan press from 2003. The service uses the SRU protocol."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1417"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Catalan Digital Press"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a50bdd14-e01b-5353-bfdb-56755ced1d11.json b/oaitestdata/clarin-oai_dc/SET_1/json/a50bdd14-e01b-5353-bfdb-56755ced1d11.json
deleted file mode 100644
index bde361e4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a50bdd14-e01b-5353-bfdb-56755ced1d11.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Department of Languages and Literatures, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/80",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/80"
-    ],
-    "PID": "http://hdl.handle.net/10794/80",
-    "PublicationTimestamp": "2012-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Department of Languages and Literatures, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/80;2017-10-26T08:14:41Z;hdl_10794_1;hdl_10794_2;Banco de Datos de Once Novelas Espa\u00f1olas 1951\u20141971 (SOL) (2014-10-08);Banco de Datos de Once Novelas Espa\u00f1olas 1951\u20141971 (SOL) (2014-10-08);n/a, n/a;SOL;Part of SOL - Spanish Online. Sentence scrambled.;Del av SOL - Spanska Online. Materialet \u00e4r meningsomkastat.;2012-05-30;corpus;http://hdl.handle.net/10794/80;spa;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Department of Languages and Literatures, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/one71",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a50bdd14-e01b-5353-bfdb-56755ced1d11",
-    "notes": [
-        "Part of SOL - Spanish Online. Sentence scrambled.",
-        "Del av SOL - Spanska Online. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/80"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "SOL"
-        }
-    ],
-    "title": [
-        "Banco de Datos de Once Novelas Espa\u00f1olas 1951\u20141971 (SOL) (2014-10-08)",
-        "Banco de Datos de Once Novelas Espa\u00f1olas 1951\u20141971 (SOL) (2014-10-08)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a529ea2c-5d86-58be-babd-1a1ffeab56f2.json b/oaitestdata/clarin-oai_dc/SET_1/json/a529ea2c-5d86-58be-babd-1a1ffeab56f2.json
deleted file mode 100644
index 7ff1aee7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a529ea2c-5d86-58be-babd-1a1ffeab56f2.json
+++ /dev/null
@@ -1,90 +0,0 @@
-{
-    "Contact": [
-        "ZRC SAZU"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1091",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1091"
-    ],
-    "PID": "http://hdl.handle.net/11356/1091",
-    "PublicationTimestamp": "2012-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "ZRC SAZU"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Mirti\u010d, Tanja",
-        "Perdih, Andrej",
-        "Krvina, Domen",
-        "Bizjak Kon\u010dar, Aleksandra",
-        "Michelizza, Mija",
-        "Gliha Komac, Nata\u0161a",
-        "\u0160ircelj \u017dnidar\u0161i\u010d, Ivanka",
-        "Klemen\u010di\u010d, Simona",
-        "Snoj, Marko",
-        "Ledinek, Nina",
-        "Petric, \u0160pela",
-        "Kostanjevec, Polona",
-        "Glo\u017ean\u010dev, Alenka",
-        "Kern, Boris",
-        "\u017dele, Andreja"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1091;2017-05-15T09:49:35Z;hdl_11356_1023;hdl_11356_1024;Dictionary of New Slovenian Words;Bizjak Kon\u010dar, Aleksandra;Glo\u017ean\u010dev, Alenka;Kern, Boris;Kostanjevec, Polona;Krvina, Domen;Ledinek, Nina;Michelizza, Mija;Perdih, Andrej;Petric, \u0160pela;Snoj, Marko;\u0160ircelj \u017dnidar\u0161i\u010d, Ivanka;\u017dele, Andreja;Mirti\u010d, Tanja;Gliha Komac, Nata\u0161a;Klemen\u010di\u010d, Simona;dictionary;neologism;lexicography;Slovar novej\u0161ega besedja slovenskega jezika (Dictionary of New Slovenian Words) represents a basic new lexical supplement to the Slovar slovenskega knji\u017enega jezika (Dictionary of the Slovenian Standard Language). It contains 6399 new words and phrases that appeared in Slovenian or gained ground after 1991 as well as new meanings of previously standardised lexis. Two important new features of the dictionary are a corpus-driven analysis of new words that are in actual language use and etymological explanations of the included words.\r\n\r\nThis dictionary was published as a printed book:\r\nBizjak Kon\u010dar, Aleksandra, Snoj, Marko, Glo\u017ean\u010dev, Alenka, Kern, Boris, Kostanjevec, Polona, Krvina, Domen, Ledinek, Nina, Michelizza, Mija, Perdih, Andrej, Petric, \u0160pela, \u0160ircelj-\u017dnidar\u0161i\u010d, Ivanka, \u017dele, Andreja, Mirti\u010d, Tanja, Gliha Komac, Nata\u0161a, Klemen\u010di\u010d, Simona. Slovar novej\u0161ega besedja slovenskega jezika. Ljubljana : Zalo\u017eba ZRC, ZRC SAZU, 2012. ISBN 978-961-254-413-3.;2012;lexicalConceptualResource;http://hdl.handle.net/11356/1091;slv;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;ZRC SAZU;http://www.fran.si/131/snb-slovar-novejsega-besedja",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a529ea2c-5d86-58be-babd-1a1ffeab56f2",
-    "notes": [
-        "Slovar novej\u0161ega besedja slovenskega jezika (Dictionary of New Slovenian Words) represents a basic new lexical supplement to the Slovar slovenskega knji\u017enega jezika (Dictionary of the Slovenian Standard Language). It contains 6399 new words and phrases that appeared in Slovenian or gained ground after 1991 as well as new meanings of previously standardised lexis. Two important new features of the dictionary are a corpus-driven analysis of new words that are in actual language use and etymological explanations of the included words.\r\n\r\nThis dictionary was published as a printed book:\r\nBizjak Kon\u010dar, Aleksandra, Snoj, Marko, Glo\u017ean\u010dev, Alenka, Kern, Boris, Kostanjevec, Polona, Krvina, Domen, Ledinek, Nina, Michelizza, Mija, Perdih, Andrej, Petric, \u0160pela, \u0160ircelj-\u017dnidar\u0161i\u010d, Ivanka, \u017dele, Andreja, Mirti\u010d, Tanja, Gliha Komac, Nata\u0161a, Klemen\u010di\u010d, Simona. Slovar novej\u0161ega besedja slovenskega jezika. Ljubljana : Zalo\u017eba ZRC, ZRC SAZU, 2012. ISBN 978-961-254-413-3."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1091"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "dictionary"
-        },
-        {
-            "name": "neologism"
-        },
-        {
-            "name": "lexicography"
-        }
-    ],
-    "title": [
-        "Dictionary of New Slovenian Words"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a566ec05-9713-5570-a5f5-767f5adb408e.json b/oaitestdata/clarin-oai_dc/SET_1/json/a566ec05-9713-5570-a5f5-767f5adb408e.json
deleted file mode 100644
index d891ea0d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a566ec05-9713-5570-a5f5-767f5adb408e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5197",
-    "MetadataAccess": [
-        "oai:ota:oucs:5197"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dennis, John, 1657-1734."
-    ],
-    "fulltext": "oai:ota:oucs:5197;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5197.xml;Original letters: familiar, moral and critical. By Mr. Dennis. In two volumes. ... [pt.2];Dennis, John, 1657-1734.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a566ec05-9713-5570-a5f5-767f5adb408e",
-    "oai_identifier": [
-        "oai:ota:oucs:5197"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Original letters: familiar, moral and critical. By Mr. Dennis. In two volumes. ... [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5197.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a56774b9-ee59-55e0-a377-c9f4961a2a25.json b/oaitestdata/clarin-oai_dc/SET_1/json/a56774b9-ee59-55e0-a377-c9f4961a2a25.json
deleted file mode 100644
index f5525e28..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a56774b9-ee59-55e0-a377-c9f4961a2a25.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3284",
-    "MetadataAccess": [
-        "oai:ota:oucs:3284"
-    ],
-    "PublicationTimestamp": "1932-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1932"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Kipling, Rudyard, 1865-1936"
-    ],
-    "fulltext": "oai:ota:oucs:3284;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3284.xml;Limits and Renewals;Kipling, Rudyard, 1865-1936;not after: 1932;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a56774b9-ee59-55e0-a377-c9f4961a2a25",
-    "oai_identifier": [
-        "oai:ota:oucs:3284"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Limits and Renewals"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3284.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a57ab635-498c-5495-8b82-950e62f35621.json b/oaitestdata/clarin-oai_dc/SET_1/json/a57ab635-498c-5495-8b82-950e62f35621.json
deleted file mode 100644
index 18286cdf..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a57ab635-498c-5495-8b82-950e62f35621.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=2c1c73c6e6e011e6a2aa782bcb0741351c33fe1f38e7431da000a4071685d7dd",
-    "MetadataAccess": [
-        "2c1c73c6e6e011e6a2aa782bcb0741351c33fe1f38e7431da000a4071685d7dd"
-    ],
-    "PublicationTimestamp": "2017-01-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "fulltext": "2c1c73c6e6e011e6a2aa782bcb0741351c33fe1f38e7431da000a4071685d7dd;2018-11-15T16:40:27Z;corpus;corpus:text;LX-AP;LX-AP was created from the translation of Almuhareb-Poesio (ap) benchmark (Almuhareb and Poesio, 2005). The original data set was created considering three aspects: POS, frequency and ambiguity.\nIt contains 402 names from 21 categories of WordNet, with 13 to 21 names from each one of those categories. Examples of some categories: feeling, game, time, tree, vehicle, chemical element or motivation (more examples are shown in Table 6).\nTo estimate the word frequency it was used the British National Corpus. Concerning frequency, \u00e2\u0085\u0093 of the words of the corpus has high frequency (1 000 occurrences or more), \u00e2\u0085\u0093 has medium frequency (between 100 to 1 000 occurrences) and \u00e2\u0085\u0093 has low frequency (5 to 100 occurrences).  \nThe evaluation of the degree of ambiguity of each word was calculated taking into account the amount of senses of each word found in the WordNet. With four or more senses, the word was considered very ambiguous; with two or three meanings, the word would have medium ambiguity; and with one meaning, the word was considered not ambiguous. Each level of frequency and ambiguity is equally represented in the set.\nWe are aware that a word that is frequent in English can be less frequent in Portuguese and that a word that is ambiguous in English can be less ambiguous in Portuguese. More than translating the original data set, it would be interesting to build a data set that, in Portuguese, would also be balanced in terms of frequency and ambiguity of words. As a possible future work, an analysis of the frequency of the words using a large Portuguese data set as a reference, and an analysis of the ambiguity of the words using the Portuguese Wordnet would improve this data set. However, because the lexicographic resources required to fulfil those tasks are not available yet, the LX-AP is made of the translation from the English words, resulting in a test set with the same size as the original.\nThe translation process of this data set from English to Portuguese involved two annotators and a third adjudicator. ;2017-01-30",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a57ab635-498c-5495-8b82-950e62f35621",
-    "notes": [
-        "LX-AP was created from the translation of Almuhareb-Poesio (ap) benchmark (Almuhareb and Poesio, 2005). The original data set was created considering three aspects: POS, frequency and ambiguity.\nIt contains 402 names from 21 categories of WordNet, with 13 to 21 names from each one of those categories. Examples of some categories: feeling, game, time, tree, vehicle, chemical element or motivation (more examples are shown in Table 6).\nTo estimate the word frequency it was used the British National Corpus. Concerning frequency, \u00e2\u0085\u0093 of the words of the corpus has high frequency (1 000 occurrences or more), \u00e2\u0085\u0093 has medium frequency (between 100 to 1 000 occurrences) and \u00e2\u0085\u0093 has low frequency (5 to 100 occurrences).  \nThe evaluation of the degree of ambiguity of each word was calculated taking into account the amount of senses of each word found in the WordNet. With four or more senses, the word was considered very ambiguous; with two or three meanings, the word would have medium ambiguity; and with one meaning, the word was considered not ambiguous. Each level of frequency and ambiguity is equally represented in the set.\nWe are aware that a word that is frequent in English can be less frequent in Portuguese and that a word that is ambiguous in English can be less ambiguous in Portuguese. More than translating the original data set, it would be interesting to build a data set that, in Portuguese, would also be balanced in terms of frequency and ambiguity of words. As a possible future work, an analysis of the frequency of the words using a large Portuguese data set as a reference, and an analysis of the ambiguity of the words using the Portuguese Wordnet would improve this data set. However, because the lexicographic resources required to fulfil those tasks are not available yet, the LX-AP is made of the translation from the English words, resulting in a test set with the same size as the original.\nThe translation process of this data set from English to Portuguese involved two annotators and a third adjudicator. "
-    ],
-    "oai_identifier": [
-        "2c1c73c6e6e011e6a2aa782bcb0741351c33fe1f38e7431da000a4071685d7dd"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "LX-AP"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a594414f-c5b5-5748-9af7-d7648c00786f.json b/oaitestdata/clarin-oai_dc/SET_1/json/a594414f-c5b5-5748-9af7-d7648c00786f.json
deleted file mode 100644
index 409e3286..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a594414f-c5b5-5748-9af7-d7648c00786f.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3438",
-    "MetadataAccess": [
-        "oai:ota:oucs:3438"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Goldsmith, Oliver, 1730?-1774."
-    ],
-    "fulltext": "oai:ota:oucs:3438;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3438.xml;Retaliation: a poem: By Doctor Goldsmith. Including epitaphs on the most distinguished wits of this metropolis.;Goldsmith, Oliver, 1730?-1774.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a594414f-c5b5-5748-9af7-d7648c00786f",
-    "oai_identifier": [
-        "oai:ota:oucs:3438"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Retaliation: a poem: By Doctor Goldsmith. Including epitaphs on the most distinguished wits of this metropolis."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3438.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a59f7b33-594d-5736-8cdc-3784c230033f.json b/oaitestdata/clarin-oai_dc/SET_1/json/a59f7b33-594d-5736-8cdc-3784c230033f.json
deleted file mode 100644
index 236238c1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a59f7b33-594d-5736-8cdc-3784c230033f.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Department of Information Technology, Gauhati University, Assam, India"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Assamese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/616",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/616"
-    ],
-    "PID": "http://hdl.handle.net/11321/616",
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Department of Information Technology, Gauhati University, Assam, India"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "author": [
-        "Sarma, Prof. Shikhar Kr."
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/616;2019-01-08T10:49:17Z;hdl_11321_3;hdl_11321_610;Assamese Multi Word Expressions;Sarma, Prof. Shikhar Kr.;Assamese NLP;Assamese MWE;Assamese Multi Word Expressions;Gauhati University;Multiword Expressions are sequence of words, separated by space delimiter (or any) which determines a unique meaning instead of words' individual meanings. A list comprising of 927 Multi-word Expressions have been identified for Assamese language. Example of the Assamese MWEs are \u201c\u09ae\u09be\u099f\u09bf\u09f0 \u09ae\u09be\u09a8\u09c1\u09b9\u201d, \u201c \u0996\u099f\u0995 \u0996\u099f\u0995 \u201d etc.;2019-01-08;lexicalConceptualResource;http://hdl.handle.net/11321/616;asm;downloadable_files_count: 0;Department of Information Technology, Gauhati University, Assam, India",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a59f7b33-594d-5736-8cdc-3784c230033f",
-    "notes": [
-        "Multiword Expressions are sequence of words, separated by space delimiter (or any) which determines a unique meaning instead of words' individual meanings. A list comprising of 927 Multi-word Expressions have been identified for Assamese language. Example of the Assamese MWEs are \u201c\u09ae\u09be\u099f\u09bf\u09f0 \u09ae\u09be\u09a8\u09c1\u09b9\u201d, \u201c \u0996\u099f\u0995 \u0996\u099f\u0995 \u201d etc."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/616"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_610"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Assamese NLP"
-        },
-        {
-            "name": "Assamese MWE"
-        },
-        {
-            "name": "Assamese Multi Word Expressions"
-        },
-        {
-            "name": "Gauhati University"
-        }
-    ],
-    "title": [
-        "Assamese Multi Word Expressions"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a5a21b56-7383-5c14-a956-7ae782f23972.json b/oaitestdata/clarin-oai_dc/SET_1/json/a5a21b56-7383-5c14-a956-7ae782f23972.json
deleted file mode 100644
index a91f7a06..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a5a21b56-7383-5c14-a956-7ae782f23972.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Polish-Japanese Academy of Information Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/zip",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/297",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/297"
-    ],
-    "PID": "http://hdl.handle.net/11321/297",
-    "PublicationTimestamp": "2016-05-12T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Polish-Japanese Academy of Information Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "BSD 2 Clause",
-        "https://opensource.org/licenses/BSD-2-Clause",
-        "PUB"
-    ],
-    "author": [
-        "Marasek, Krzysztof",
-        "Sob\u00f3tka, Pawe\u0142",
-        "Walczak, Jerzy Piotr"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/297;2016-06-06T13:43:41Z;hdl_11321_3;hdl_11321_4;Long term archive operating system source code;Walczak, Jerzy Piotr;Sob\u00f3tka, Pawe\u0142;Marasek, Krzysztof;long-term archive;This submission contains the operating system of the long-term archive, built in the Polish-Japanese Academy of Information Technology for the Clarin-PL project. Basic elements of the archive are data nodes, equipped with mass memories. The nodes are controlled by embedded low-power computers which are independently powered up only when their storage is about to be accessed. This allows not only for limiting the overall energy consumption but also lowers environmental demands (no air-condition needed). The nodes are grouped in trays. Basic and recommended configuration allows for 30 nodes in trays, but it is possible to extend this limit up to 253. Each tray contains several networks designed for data transport, devices\u2019 state control and power supply. Communication with clients is conducted through buffers that are the only parts visible from externally connected networks. Therefore, stored files are completely isolated and cannot be directly accessed. Multiple trays located at single physical site create a complete archive. It is possible to split storage space into virtual archives that are separated on logical level. The operating system of the data network allows to store from 3 to 7 copies of single digital file in different nodes. Moreover, additional copies of the resource may be stored automatically in remotely located archives. The trays are treated as local parts of wider dispersed data network structure. Software of the archive enables not only secure read and write operations data but it also automatically takes care of the stored data. It periodically regenerates physical state of saved files. In case of device failure clients are transparently redirected to local or remote redundant copies. The mechanism of \"software bots\" was implemented. Archive can be supplied with external programs for processing files stored inside the data network. This allows for data analyzes, indexation, post-data creation, statistical computations or finding associations in unstructured data sets of Big Data type. Only the output of software bot can be externally accessed what makes such operations very secure. Client programs communicate with the archive using set of simple protocols based on key-value pair strings, making it convenient to build web interfaces for archive access and administration. By automating the supervision of the resources, reduction of requirements for storage, precise energy consumption control and proposed solution significantly lowers the cost of long-term data storage.;2016-05-12;toolService;http://hdl.handle.net/11321/297;N/A;BSD 2 Clause;https://opensource.org/licenses/BSD-2-Clause;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/zip;downloadable_files_count: 1;Polish-Japanese Academy of Information Technology;http://www.clarin-pl.eu",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a5a21b56-7383-5c14-a956-7ae782f23972",
-    "notes": [
-        "This submission contains the operating system of the long-term archive, built in the Polish-Japanese Academy of Information Technology for the Clarin-PL project. Basic elements of the archive are data nodes, equipped with mass memories. The nodes are controlled by embedded low-power computers which are independently powered up only when their storage is about to be accessed. This allows not only for limiting the overall energy consumption but also lowers environmental demands (no air-condition needed). The nodes are grouped in trays. Basic and recommended configuration allows for 30 nodes in trays, but it is possible to extend this limit up to 253. Each tray contains several networks designed for data transport, devices\u2019 state control and power supply. Communication with clients is conducted through buffers that are the only parts visible from externally connected networks. Therefore, stored files are completely isolated and cannot be directly accessed. Multiple trays located at single physical site create a complete archive. It is possible to split storage space into virtual archives that are separated on logical level. The operating system of the data network allows to store from 3 to 7 copies of single digital file in different nodes. Moreover, additional copies of the resource may be stored automatically in remotely located archives. The trays are treated as local parts of wider dispersed data network structure. Software of the archive enables not only secure read and write operations data but it also automatically takes care of the stored data. It periodically regenerates physical state of saved files. In case of device failure clients are transparently redirected to local or remote redundant copies. The mechanism of \"software bots\" was implemented. Archive can be supplied with external programs for processing files stored inside the data network. This allows for data analyzes, indexation, post-data creation, statistical computations or finding associations in unstructured data sets of Big Data type. Only the output of software bot can be externally accessed what makes such operations very secure. Client programs communicate with the archive using set of simple protocols based on key-value pair strings, making it convenient to build web interfaces for archive access and administration. By automating the supervision of the resources, reduction of requirements for storage, precise energy consumption control and proposed solution significantly lowers the cost of long-term data storage."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/297"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "long-term archive"
-        }
-    ],
-    "title": [
-        "Long term archive operating system source code"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a5acb03b-8d92-5194-957c-4bfb593d3ab9.json b/oaitestdata/clarin-oai_dc/SET_1/json/a5acb03b-8d92-5194-957c-4bfb593d3ab9.json
deleted file mode 100644
index 32b2a677..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a5acb03b-8d92-5194-957c-4bfb593d3ab9.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3699",
-    "MetadataAccess": [
-        "oai:ota:oucs:3699"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pope, Alexander, 1688-1744."
-    ],
-    "fulltext": "oai:ota:oucs:3699;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3699.xml;Sober advice from Horace: to the young gentlemen about town. As deliver'd in his second sermon. Imitated in the manner of Mr. Pope. Together with the original text, as restored by the Rev'd. R. Bentley ... And some remarks on the version.;Pope, Alexander, 1688-1744.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a5acb03b-8d92-5194-957c-4bfb593d3ab9",
-    "oai_identifier": [
-        "oai:ota:oucs:3699"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Sober advice from Horace: to the young gentlemen about town. As deliver'd in his second sermon. Imitated in the manner of Mr. Pope. Together with the original text, as restored by the Rev'd. R. Bentley ... And some remarks on the version."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3699.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a5c5d5cc-ee0d-5de2-9f1b-b2a47a797a1f.json b/oaitestdata/clarin-oai_dc/SET_1/json/a5c5d5cc-ee0d-5de2-9f1b-b2a47a797a1f.json
deleted file mode 100644
index 36b32aa4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a5c5d5cc-ee0d-5de2-9f1b-b2a47a797a1f.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3328",
-    "MetadataAccess": [
-        "oai:ota:oucs:3328"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Defoe, Daniel, 1661?-1731."
-    ],
-    "fulltext": "oai:ota:oucs:3328;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3328.xml;An answer to The tale of a nettle: Written by D. D'Foe.;Defoe, Daniel, 1661?-1731.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a5c5d5cc-ee0d-5de2-9f1b-b2a47a797a1f",
-    "oai_identifier": [
-        "oai:ota:oucs:3328"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An answer to The tale of a nettle: Written by D. D'Foe."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3328.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a5f87dfe-d16e-5567-adff-1c03cf39b881.json b/oaitestdata/clarin-oai_dc/SET_1/json/a5f87dfe-d16e-5567-adff-1c03cf39b881.json
deleted file mode 100644
index f3e59d28..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a5f87dfe-d16e-5567-adff-1c03cf39b881.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5165",
-    "MetadataAccess": [
-        "oai:ota:oucs:5165"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Arbuthnot, John, 1667-1735."
-    ],
-    "fulltext": "oai:ota:oucs:5165;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5165.xml;An essay concerning the effects of air on human bodies: By John Arbuthnot, ...;Arbuthnot, John, 1667-1735.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a5f87dfe-d16e-5567-adff-1c03cf39b881",
-    "oai_identifier": [
-        "oai:ota:oucs:5165"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An essay concerning the effects of air on human bodies: By John Arbuthnot, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5165.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a5ff4cd4-2713-5509-8807-38e1a45578e7.json b/oaitestdata/clarin-oai_dc/SET_1/json/a5ff4cd4-2713-5509-8807-38e1a45578e7.json
deleted file mode 100644
index c28542a9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a5ff4cd4-2713-5509-8807-38e1a45578e7.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Center for Language and Cognition"
-    ],
-    "Contributor": [
-        "Noord, Gertjan van"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/xml"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-220",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-220"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-220",
-    "PublicationTimestamp": "2002-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2002"
-    ],
-    "Publisher": [
-        "Center for Language and Cognition"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-220;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Alpino Treebank;Noord, Gertjan van;A database of 7.000 syntactically analyzed Dutch sentences.;2002;corpus;http://hdl.handle.net/11372/LRT-220;nld;application/xml;downloadable_files_count: 0;Netherlands (the);Center for Language and Cognition;http://www.let.rug.nl/~vannoord/trees",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a5ff4cd4-2713-5509-8807-38e1a45578e7",
-    "notes": [
-        "A database of 7.000 syntactically analyzed Dutch sentences."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-220"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Alpino Treebank"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a602024a-9c4d-54ed-baab-f7f10facdbd7.json b/oaitestdata/clarin-oai_dc/SET_1/json/a602024a-9c4d-54ed-baab-f7f10facdbd7.json
deleted file mode 100644
index 2a694340..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a602024a-9c4d-54ed-baab-f7f10facdbd7.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish",
-        "Upper Sorbian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/56",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/56"
-    ],
-    "PID": "http://hdl.handle.net/10794/56",
-    "PublicationTimestamp": "2015-04-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/56;2017-10-31T12:28:28Z;hdl_10794_1;hdl_10794_2;ASPAC \u2013 Swedish-Upper Sorbian (2017-10-16);ASPAC \u2013 svenska-h\u00f6gsorbiska (2017-10-16);n/a, n/a;ASPAC;Parallel;Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.;Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat.;2015-04-16;corpus;http://hdl.handle.net/10794/56;swe;hsb;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/octet-stream;application/gzip;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/aspacsvhsb",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a602024a-9c4d-54ed-baab-f7f10facdbd7",
-    "notes": [
-        "Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.",
-        "Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/56"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ASPAC"
-        },
-        {
-            "name": "Parallel"
-        }
-    ],
-    "title": [
-        "ASPAC \u2013 Swedish-Upper Sorbian (2017-10-16)",
-        "ASPAC \u2013 svenska-h\u00f6gsorbiska (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a603ae5d-bf34-5a16-b096-05999065a958.json b/oaitestdata/clarin-oai_dc/SET_1/json/a603ae5d-bf34-5a16-b096-05999065a958.json
deleted file mode 100644
index de7f4057..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a603ae5d-bf34-5a16-b096-05999065a958.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Arts, Institute of the Czech National Corpus"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/x-xz"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1846",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1846"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1846",
-    "PublicationTimestamp": "2016-12-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Arts, Institute of the Czech National Corpus"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Czech National Corpus (Shuffled Corpus Data)",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/license-cnc",
-        "ACA"
-    ],
-    "author": [
-        "Hn\u00e1tkov\u00e1, Milena",
-        "Trune\u010dek, Petr",
-        "Petkevi\u010d, Vladim\u00edr",
-        "Chlumsk\u00e1, Lucie",
-        "\u010capka, Tom\u00e1\u0161",
-        "Vond\u0159i\u010dka, Pavel",
-        "Proch\u00e1zka, Pavel",
-        "\u010cerm\u00e1kov\u00e1, Anna",
-        "Kov\u00e1\u0159\u00edkov\u00e1, Dominika",
-        "K\u0159en, Michal",
-        "Jel\u00ednek, Tom\u00e1\u0161",
-        "Skoumalov\u00e1, Hana",
-        "Cvr\u010dek, V\u00e1clav",
-        "\u0160krabal, Michal",
-        "Zasina, Adrian"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1846;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;SYN v4: large corpus of written Czech;K\u0159en, Michal;Cvr\u010dek, V\u00e1clav;\u010capka, Tom\u00e1\u0161;\u010cerm\u00e1kov\u00e1, Anna;Hn\u00e1tkov\u00e1, Milena;Chlumsk\u00e1, Lucie;Jel\u00ednek, Tom\u00e1\u0161;Kov\u00e1\u0159\u00edkov\u00e1, Dominika;Petkevi\u010d, Vladim\u00edr;Proch\u00e1zka, Pavel;Skoumalov\u00e1, Hana;\u0160krabal, Michal;Trune\u010dek, Petr;Vond\u0159i\u010dka, Pavel;Zasina, Adrian;corpus;written language;Corpus of contemporary written (printed) Czech sized 3.6 GW (i.e. 4.3 billion tokens). It covers mostly the period of 1990\u20132014 and it is a traditional corpus (as opposed to the web-crawled corpora) with rich metadata containing bibliographical information etc. Although it contains a wide range of text types (fiction, non-fiction, newspapers), the newspapers prevail noticeably. The corpus is lemmatized and morphologically annotated by a combination of stochastic and rule-based methods.\r\n\r\nThe corpus is provided in a (semi-XML) vertical format used as an input to the Manatee query engine. The data thus correspond to the corpus available via the KonText query interface to registered users of the CNC at http://www.korpus.cz with one important exception: the corpus are shuffled, i.e. divided into blocks sized max. 100 words (respecting the sentence boundaries) with ordering randomized within the given document.;2016-12-01;corpus;http://hdl.handle.net/11234/1-1846;ces;Czech National Corpus (Shuffled Corpus Data);https://lindat.mff.cuni.cz/repository/xmlui/page/license-cnc;ACA;application/x-xz;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Arts, Institute of the Czech National Corpus;https://wiki.korpus.cz/doku.php/cnk:syn:verze4",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a603ae5d-bf34-5a16-b096-05999065a958",
-    "notes": [
-        "Corpus of contemporary written (printed) Czech sized 3.6 GW (i.e. 4.3 billion tokens). It covers mostly the period of 1990\u20132014 and it is a traditional corpus (as opposed to the web-crawled corpora) with rich metadata containing bibliographical information etc. Although it contains a wide range of text types (fiction, non-fiction, newspapers), the newspapers prevail noticeably. The corpus is lemmatized and morphologically annotated by a combination of stochastic and rule-based methods.\r\n\r\nThe corpus is provided in a (semi-XML) vertical format used as an input to the Manatee query engine. The data thus correspond to the corpus available via the KonText query interface to registered users of the CNC at http://www.korpus.cz with one important exception: the corpus are shuffled, i.e. divided into blocks sized max. 100 words (respecting the sentence boundaries) with ordering randomized within the given document."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1846"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "written language"
-        }
-    ],
-    "title": [
-        "SYN v4: large corpus of written Czech"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a607e112-e3b7-5ce0-a63b-2d4ca5b661f1.json b/oaitestdata/clarin-oai_dc/SET_1/json/a607e112-e3b7-5ce0-a63b-2d4ca5b661f1.json
deleted file mode 100644
index b3896c30..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a607e112-e3b7-5ce0-a63b-2d4ca5b661f1.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Budapest Technical University Media Research Centre"
-    ],
-    "Contributor": [
-        "L\u00e1szl\u00f3, N\u00e9meth"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1338",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1338"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1338",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Budapest Technical University Media Research Centre"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU Library or \"Lesser\" General Public License 3.0 (LGPL-3.0)",
-        "http://opensource.org/licenses/LGPL-3.0",
-        "PUB"
-    ],
-    "SpatialCoverage": [
-        "Hungary"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Hal\u00e1csy, P\u00e9ter",
-        "N\u00e9meth, L\u00e1szl\u00f3",
-        "Kornai, Andr\u00e1s"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1338;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;huntoken - tokenizer and sentence splitter;N\u00e9meth, L\u00e1szl\u00f3;Hal\u00e1csy, P\u00e9ter;Kornai, Andr\u00e1s;L\u00e1szl\u00f3, N\u00e9meth;HunToken is a rule based tokenizer and sentence boundary detector for Hungarian (and English) texts.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1338;GNU Library or \"Lesser\" General Public License 3.0 (LGPL-3.0);http://opensource.org/licenses/LGPL-3.0;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Hungary;Budapest Technical University Media Research Centre",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a607e112-e3b7-5ce0-a63b-2d4ca5b661f1",
-    "notes": [
-        "HunToken is a rule based tokenizer and sentence boundary detector for Hungarian (and English) texts."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1338"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "huntoken - tokenizer and sentence splitter"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a6136548-4dd2-5119-beac-309caf50638f.json b/oaitestdata/clarin-oai_dc/SET_1/json/a6136548-4dd2-5119-beac-309caf50638f.json
deleted file mode 100644
index 1a4b6327..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a6136548-4dd2-5119-beac-309caf50638f.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Institute of Mathematics and Computer Science, University of Latvia"
-    ],
-    "Contributor": [
-        "Skadina, Inguna"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1192",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1192"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1192",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institute of Mathematics and Computer Science, University of Latvia"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Latvia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1192;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;English-Latvian SMT system;Skadina, Inguna;English-Latvian factored SMT system uses Moses decoder, trained on JRC-Acquis and some other parallel texts;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1192;eng;downloadable_files_count: 0;Latvia;Institute of Mathematics and Computer Science, University of Latvia;http://eksperimenti.ailab.lv/smt/smtdemo_en.php",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a6136548-4dd2-5119-beac-309caf50638f",
-    "notes": [
-        "English-Latvian factored SMT system uses Moses decoder, trained on JRC-Acquis and some other parallel texts"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1192"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "English-Latvian SMT system"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a6172615-dec3-5d2f-9bdb-6ff14692ef23.json b/oaitestdata/clarin-oai_dc/SET_1/json/a6172615-dec3-5d2f-9bdb-6ff14692ef23.json
deleted file mode 100644
index 27fd6125..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a6172615-dec3-5d2f-9bdb-6ff14692ef23.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1573",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1573"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1573",
-    "PublicationTimestamp": "2015-11-22T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Straka, Milan"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1573;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Universal Dependencies 1.2 Models for Parsito;Straka, Milan;parser;dependency parser;Parsing models for all Universal Depenencies 1.2 Treebanks, created solely using UD 1.2 data (http://hdl.handle.net/11234/1-1548).\r\n\r\nTo use these models, you need Parsito binary, which you can download from http://hdl.handle.net/11234/1-1584.;2015-11-22;toolService;http://hdl.handle.net/11234/1-1573;eng;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/parsito",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a6172615-dec3-5d2f-9bdb-6ff14692ef23",
-    "notes": [
-        "Parsing models for all Universal Depenencies 1.2 Treebanks, created solely using UD 1.2 data (http://hdl.handle.net/11234/1-1548).\r\n\r\nTo use these models, you need Parsito binary, which you can download from http://hdl.handle.net/11234/1-1584."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1573"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parser"
-        },
-        {
-            "name": "dependency parser"
-        }
-    ],
-    "title": [
-        "Universal Dependencies 1.2 Models for Parsito"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a61e7926-001e-56e4-b5cc-f3dd235240ef.json b/oaitestdata/clarin-oai_dc/SET_1/json/a61e7926-001e-56e4-b5cc-f3dd235240ef.json
deleted file mode 100644
index 2b655120..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a61e7926-001e-56e4-b5cc-f3dd235240ef.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=1855927ea35a11e1a404080027e73ea23b2cd5f03a874446a01f3244ab4e9acf",
-    "MetadataAccess": [
-        "1855927ea35a11e1a404080027e73ea23b2cd5f03a874446a01f3244ab4e9acf"
-    ],
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "1855927ea35a11e1a404080027e73ea23b2cd5f03a874446a01f3244ab4e9acf;2019-02-27T12:08:59Z;corpus;corpus:text;GENIA POS & Term Corpus;A corpus of 2,000 MEDLINE abstracts, collected using the three MeSH terms human, blood cells and transcription factors. The corpus is available in three formats: 1) A text file containing part-of-speech (POS) annotation, based on the Penn Treebank format, 2) An XML file containing inline POS annotation, 3) A \u00e2\u0080\u009cmerged\u00e2\u0080\u009d XML format, containing inline annotations, corresponding to both POS and term annotations ;2015-12-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a61e7926-001e-56e4-b5cc-f3dd235240ef",
-    "notes": [
-        "A corpus of 2,000 MEDLINE abstracts, collected using the three MeSH terms human, blood cells and transcription factors. The corpus is available in three formats: 1) A text file containing part-of-speech (POS) annotation, based on the Penn Treebank format, 2) An XML file containing inline POS annotation, 3) A \u00e2\u0080\u009cmerged\u00e2\u0080\u009d XML format, containing inline annotations, corresponding to both POS and term annotations "
-    ],
-    "oai_identifier": [
-        "1855927ea35a11e1a404080027e73ea23b2cd5f03a874446a01f3244ab4e9acf"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "GENIA POS & Term Corpus"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a6289e25-e016-5be6-babf-a2e17b3b4a42.json b/oaitestdata/clarin-oai_dc/SET_1/json/a6289e25-e016-5be6-babf-a2e17b3b4a42.json
deleted file mode 100644
index c2d3bffb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a6289e25-e016-5be6-babf-a2e17b3b4a42.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "School of Languages, Linguistics and Cultures, University of Manchester"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-715",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-715"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-715",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "School of Languages, Linguistics and Cultures, University of Manchester"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Code of conduct"
-    ],
-    "SpatialCoverage": [
-        "Australia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-715;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Jaminjungan and Eastern Ngumpin corpus;Documentation of the Jaminjungan and Eastern Ngumpin project (DoBeS project);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-715;Code of conduct;downloadable_files_count: 0;Australia;School of Languages, Linguistics and Cultures, University of Manchester;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI319354%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a6289e25-e016-5be6-babf-a2e17b3b4a42",
-    "notes": [
-        "Documentation of the Jaminjungan and Eastern Ngumpin project (DoBeS project)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-715"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Jaminjungan and Eastern Ngumpin corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a62ab911-7219-55a9-99c7-808aaff84945.json b/oaitestdata/clarin-oai_dc/SET_1/json/a62ab911-7219-55a9-99c7-808aaff84945.json
deleted file mode 100644
index 6bffb317..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a62ab911-7219-55a9-99c7-808aaff84945.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5454",
-    "MetadataAccess": [
-        "oai:ota:oucs:5454"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Watts, Isaac, 1674-1748."
-    ],
-    "fulltext": "oai:ota:oucs:5454;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5454.xml;Divine songs: attempted in easy language for the use of children. By I. Watts, D.D.;Watts, Isaac, 1674-1748.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a62ab911-7219-55a9-99c7-808aaff84945",
-    "oai_identifier": [
-        "oai:ota:oucs:5454"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Divine songs: attempted in easy language for the use of children. By I. Watts, D.D."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5454.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a63207af-c2f0-5b64-a59c-c8487841777c.json b/oaitestdata/clarin-oai_dc/SET_1/json/a63207af-c2f0-5b64-a59c-c8487841777c.json
deleted file mode 100644
index b03dd4fc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a63207af-c2f0-5b64-a59c-c8487841777c.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=b8c860b66c6711e2a2aa782bcb0741357d0bd8c8d04a4101affa80b298309fa4",
-    "MetadataAccess": [
-        "b8c860b66c6711e2a2aa782bcb0741357d0bd8c8d04a4101affa80b298309fa4"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "b8c860b66c6711e2a2aa782bcb0741357d0bd8c8d04a4101affa80b298309fa4;2018-11-15T16:40:10Z;toolService;toolService:service;U-Compare Discourse Parsing Service;Web service created by exporting UIMA-based workflow from the U-Compare text mining system.\nFunctionality: Performs discourse parsing on plain text. Also identifies sentences, tokens, parts of speech, lemmas, clauses and coreference chains \nTools in workflow: UAIC-POSTagger, UAIC-NPChunker, UAIC-RARE, UAIC-Splitter, UAIC-DP  (all tools of the Alexandru Ioan Cuza University, Romania) \nNOTE: The licence provided covers the web service only. Tools used to create the workflow may have their own licences\n;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a63207af-c2f0-5b64-a59c-c8487841777c",
-    "notes": [
-        "Web service created by exporting UIMA-based workflow from the U-Compare text mining system.\nFunctionality: Performs discourse parsing on plain text. Also identifies sentences, tokens, parts of speech, lemmas, clauses and coreference chains \nTools in workflow: UAIC-POSTagger, UAIC-NPChunker, UAIC-RARE, UAIC-Splitter, UAIC-DP  (all tools of the Alexandru Ioan Cuza University, Romania) \nNOTE: The licence provided covers the web service only. Tools used to create the workflow may have their own licences\n"
-    ],
-    "oai_identifier": [
-        "b8c860b66c6711e2a2aa782bcb0741357d0bd8c8d04a4101affa80b298309fa4"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:service"
-    ],
-    "state": "active",
-    "title": [
-        "U-Compare Discourse Parsing Service"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a6346cb9-acdc-5e2a-a990-d1907b17bf89.json b/oaitestdata/clarin-oai_dc/SET_1/json/a6346cb9-acdc-5e2a-a990-d1907b17bf89.json
deleted file mode 100644
index d39dde38..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a6346cb9-acdc-5e2a-a990-d1907b17bf89.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-943",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-943"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-943",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-943;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Middle High German;ca. 2.000.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-943;deu;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#mhd",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a6346cb9-acdc-5e2a-a990-d1907b17bf89",
-    "notes": [
-        "ca. 2.000.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-943"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Middle High German"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a63902b6-2665-5101-9982-ca1e0d0d61c9.json b/oaitestdata/clarin-oai_dc/SET_1/json/a63902b6-2665-5101-9982-ca1e0d0d61c9.json
deleted file mode 100644
index 353d5e3a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a63902b6-2665-5101-9982-ca1e0d0d61c9.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4384",
-    "MetadataAccess": [
-        "oai:ota:oucs:4384"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pratt, Mr. (Samuel Jackson), 1749-1814."
-    ],
-    "fulltext": "oai:ota:oucs:4384;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4384.xml;Charles and Charlotte: In two volumes. [pt.2];Pratt, Mr. (Samuel Jackson), 1749-1814.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a63902b6-2665-5101-9982-ca1e0d0d61c9",
-    "oai_identifier": [
-        "oai:ota:oucs:4384"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Charles and Charlotte: In two volumes. [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4384.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a639e798-232c-52c2-9c6d-e365b4724c93.json b/oaitestdata/clarin-oai_dc/SET_1/json/a639e798-232c-52c2-9c6d-e365b4724c93.json
deleted file mode 100644
index 9660a4e3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a639e798-232c-52c2-9c6d-e365b4724c93.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "ILSP/R.C. \"Athena\""
-    ],
-    "Contributor": [
-        "Prokopidis, Prokopis"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1308",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1308"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1308",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "ILSP/R.C. \"Athena\""
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Greece"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Papageorgiou, Haris",
-        "Prokopidis, Prokopis"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1308;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;ILSP Feature-based multi-tiered POS Tagger;Papageorgiou, Haris;Prokopidis, Prokopis;Prokopidis, Prokopis;POS tagger;ILSP FBT Tagger is an adaptation of the Brill tagger trained on Greek text. It uses a PAROLE compatible tagset of 584 different tags which capture the morphosyntactic particularities of the Greek language. Working on the output of a sentence detection and tokenisation tool, the tagger assigns initial tags, looking up in a lexicon created from a manually annotated corpus during training. A suffix lexicon is used for initially tagging unknown words. 799 contextual rules are then applied to improve the initial phase output.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1308;downloadable_files_count: 0;Greece;ILSP/R.C. \"Athena\"",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a639e798-232c-52c2-9c6d-e365b4724c93",
-    "notes": [
-        "ILSP FBT Tagger is an adaptation of the Brill tagger trained on Greek text. It uses a PAROLE compatible tagset of 584 different tags which capture the morphosyntactic particularities of the Greek language. Working on the output of a sentence detection and tokenisation tool, the tagger assigns initial tags, looking up in a lexicon created from a manually annotated corpus during training. A suffix lexicon is used for initially tagging unknown words. 799 contextual rules are then applied to improve the initial phase output."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1308"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "POS tagger"
-        }
-    ],
-    "title": [
-        "ILSP Feature-based multi-tiered POS Tagger"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a656cf8a-1bbc-5972-bc6e-8694e110dec6.json b/oaitestdata/clarin-oai_dc/SET_1/json/a656cf8a-1bbc-5972-bc6e-8694e110dec6.json
deleted file mode 100644
index 004003c0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a656cf8a-1bbc-5972-bc6e-8694e110dec6.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Society for Danish Language and Literature (DSL)",
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 6",
-        "application/pdf",
-        "text/plain",
-        "application/zip"
-    ],
-    "Language": [
-        "Danish",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repository.clarin.dk:20.500.12115/25",
-    "MetadataAccess": [
-        "oai:repository.clarin.dk:20.500.12115/25"
-    ],
-    "PID": "http://hdl.handle.net/20.500.12115/25",
-    "PublicationTimestamp": "2013-01-03T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Society for Danish Language and Literature (DSL)",
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "RelatedIdentifier": [
-        "https://pdfs.semanticscholar.org/6891/69de00c63d58bd68229cb0b3469a617f5ab3.pdf"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "DanNet 1.0 License",
-        "https://cst.ku.dk/projekter/dannet/license.txt",
-        "PUB"
-    ],
-    "author": [
-        "S\u00f8rensen, Nicolai Hartvig",
-        "Nimb, Sanni",
-        "Lorentzen, Henrik",
-        "Asmussen, J\u00f8rg",
-        "Trap-Jensen, Lars",
-        "Pedersen, Bolette Sandford"
-    ],
-    "fulltext": "oai:repository.clarin.dk:20.500.12115/25;2018-11-19T13:44:11Z;hdl_20.500.12115_1;hdl_20.500.12115_3;DanNet, Danish Wordnet (v 2.2) - owl format;Pedersen, Bolette Sandford;Nimb, Sanni;S\u00f8rensen, Nicolai Hartvig;Trap-Jensen, Lars;Lorentzen, Henrik;Asmussen, J\u00f8rg;wordnet;DanNet is a Danish lexical semantic wordnet; i.e. a language resource where the semantic relations between words are expressed in a formal language and thereby made usable for IT systems dealing with intelligent information handling. The DanNet database contains at present 65,000 concepts described in form of so-called synsets (sets of synonyms) related to one another by hyperonyms and hypernyms and for about 50 % of the concepts by other types of relations, e.g. used_for. All concepts are furthermore related to an ontological type (e.g. Human, Artifact or Activity). About 5,000 Danish synsets are linked to the equivalent English synsets of Princeton WordNet. Through the multilingual wordnet initiative Wordties (wordties.cst.dk), DanNet is linked to the Finnish, Swedish, Estonian and Polish wordnet.;2013-01-03;lexicalConceptualResource;http://hdl.handle.net/20.500.12115/25;dan;eng;https://pdfs.semanticscholar.org/6891/69de00c63d58bd68229cb0b3469a617f5ab3.pdf;DanNet 1.0 License;https://cst.ku.dk/projekter/dannet/license.txt;PUB;text/plain; charset=utf-8;application/zip;text/plain;text/plain;text/plain;application/pdf;application/pdf;downloadable_files_count: 6;Centre for Language Technology, NorS, University of Copenhagen;Society for Danish Language and Literature (DSL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a656cf8a-1bbc-5972-bc6e-8694e110dec6",
-    "notes": [
-        "DanNet is a Danish lexical semantic wordnet; i.e. a language resource where the semantic relations between words are expressed in a formal language and thereby made usable for IT systems dealing with intelligent information handling. The DanNet database contains at present 65,000 concepts described in form of so-called synsets (sets of synonyms) related to one another by hyperonyms and hypernyms and for about 50 % of the concepts by other types of relations, e.g. used_for. All concepts are furthermore related to an ontological type (e.g. Human, Artifact or Activity). About 5,000 Danish synsets are linked to the equivalent English synsets of Princeton WordNet. Through the multilingual wordnet initiative Wordties (wordties.cst.dk), DanNet is linked to the Finnish, Swedish, Estonian and Polish wordnet."
-    ],
-    "oai_identifier": [
-        "oai:repository.clarin.dk:20.500.12115/25"
-    ],
-    "oai_set": [
-        "hdl_20.500.12115_1",
-        "hdl_20.500.12115_3"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "wordnet"
-        }
-    ],
-    "title": [
-        "DanNet, Danish Wordnet (v 2.2) - owl format"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a6639d2a-ee17-5abc-ba9c-f3fdfc8029b9.json b/oaitestdata/clarin-oai_dc/SET_1/json/a6639d2a-ee17-5abc-ba9c-f3fdfc8029b9.json
deleted file mode 100644
index 7bdf02a7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a6639d2a-ee17-5abc-ba9c-f3fdfc8029b9.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/csv",
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 6",
-        "text/plain",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Multiple languages"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1071",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1071"
-    ],
-    "PID": "http://hdl.handle.net/11356/1071",
-    "PublicationTimestamp": "2016-08-05T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/H2020/640772"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "https://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Cherepnalkoski, Darko",
-        "Karpf, Andreas",
-        "Gr\u010dar, Miha",
-        "Mozeti\u010d, Igor"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1071;2018-05-28T11:29:05Z;hdl_11356_1023;hdl_11356_1024;Dataset of European Parliament roll-call votes and Twitter activities MEP 1.0;Cherepnalkoski, Darko;Karpf, Andreas;Mozeti\u010d, Igor;Gr\u010dar, Miha;European parliament;roll-call votes;Twitter;multilingual;The resource consists of two datasets related to Members of the 8th European Parliament (MEPs). The first one is a dataset of 2,535 roll-call votes of MEPs until 2016-03-01. The second one is a dataset of 26,133 retweets between MEPs in the period between 2014-10-01 and 2016-03-01. The data can be used to examine the patterns of covoting and retweeting of MEPs and analyze the extent to which they are similar.\r\nThe resource is presented and used in the paper:\r\n\r\nDarko Cherepnalkoski, Andreas Karpf, Igor Mozeti\u010d, Miha Gr\u010dar \"Cohesion and coalition formation in the European Parliament: Roll-call votes and Twitter activities\". PLoS ONE 11(11): e0166586, 2016. http://dx.doi.org/10.1371/journal.pone.0166586\r\n\r\nThe dataset contains 5 files, of which 3 contain metadata and 2 data.\r\nThe metadata comprises information about the Members of 8th European Parliament (MEPs) until 2016-03-01, about roll-call votes (RCV) and possible actions during a RCV. The first data file contains a matrix with the votes of all MEPs during all RCVs while the second contains the retweets between the MEPs.;2016-08-05;corpus;http://hdl.handle.net/11356/1071;mul;info:eu-repo/grantAgreement/EC/H2020/640772;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);https://creativecommons.org/licenses/by-sa/4.0/;PUB;text/plain;application/octet-stream;application/octet-stream;text/csv;text/csv;text/csv;text/plain; charset=utf-8;downloadable_files_count: 6;Jo\u017eef Stefan Institute",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a6639d2a-ee17-5abc-ba9c-f3fdfc8029b9",
-    "notes": [
-        "The resource consists of two datasets related to Members of the 8th European Parliament (MEPs). The first one is a dataset of 2,535 roll-call votes of MEPs until 2016-03-01. The second one is a dataset of 26,133 retweets between MEPs in the period between 2014-10-01 and 2016-03-01. The data can be used to examine the patterns of covoting and retweeting of MEPs and analyze the extent to which they are similar.\r\nThe resource is presented and used in the paper:\r\n\r\nDarko Cherepnalkoski, Andreas Karpf, Igor Mozeti\u010d, Miha Gr\u010dar \"Cohesion and coalition formation in the European Parliament: Roll-call votes and Twitter activities\". PLoS ONE 11(11): e0166586, 2016. http://dx.doi.org/10.1371/journal.pone.0166586\r\n\r\nThe dataset contains 5 files, of which 3 contain metadata and 2 data.\r\nThe metadata comprises information about the Members of 8th European Parliament (MEPs) until 2016-03-01, about roll-call votes (RCV) and possible actions during a RCV. The first data file contains a matrix with the votes of all MEPs during all RCVs while the second contains the retweets between the MEPs."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1071"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "European parliament"
-        },
-        {
-            "name": "roll-call votes"
-        },
-        {
-            "name": "Twitter"
-        },
-        {
-            "name": "multilingual"
-        }
-    ],
-    "title": [
-        "Dataset of European Parliament roll-call votes and Twitter activities MEP 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a6752775-73a2-5f90-a29b-c2f9834df627.json b/oaitestdata/clarin-oai_dc/SET_1/json/a6752775-73a2-5f90-a29b-c2f9834df627.json
deleted file mode 100644
index 5ca6aa08..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a6752775-73a2-5f90-a29b-c2f9834df627.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Ule, Louis"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 86 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1617",
-    "MetadataAccess": [
-        "oai:ota:oucs:1617"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Marlowe, Christopher, 1564-1593"
-    ],
-    "fulltext": "oai:ota:oucs:1617;2018-02-16T10:42:06Z;http://ota.ox.ac.uk/headers/1617.xml;Dido and Anaeus : the tragedy of Dido, Queen of Carthage / Christopher Marlowe;Marlowe, Christopher, 1564-1593;text_and_corpus_linguistics;English drama -- Early modern and Elizabethan, 1500-1600;Oxford Text Archive, University of Oxford;Ule, Louis;text/sgml;(1 file : ca. 86 KB);Text;Plays;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a6752775-73a2-5f90-a29b-c2f9834df627",
-    "oai_identifier": [
-        "oai:ota:oucs:1617"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- Early modern Elizabethan"
-        }
-    ],
-    "title": [
-        "Dido and Anaeus : the tragedy of Dido, Queen of Carthage / Christopher Marlowe"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1617.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a68e94b4-9de7-5f5c-bb98-05190e734f2f.json b/oaitestdata/clarin-oai_dc/SET_1/json/a68e94b4-9de7-5f5c-bb98-05190e734f2f.json
deleted file mode 100644
index 4ba3cd4d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a68e94b4-9de7-5f5c-bb98-05190e734f2f.json
+++ /dev/null
@@ -1,93 +0,0 @@
-{
-    "Contact": [
-        "Lehrstuhl Englische Sprach- und \u00dcbersetzungswissenschaft, Fakult\u00e4t P, Fachrichtung Sprachwissenschaft und Sprachtechnologie, Universit\u00e4t des Saarlandes, Campus A2.2, 66123 Saarbr\u00fccken, Germany"
-    ],
-    "Contributor": [
-        "Ashraf Khamis",
-        "J\u00f6rg Knappen",
-        "Stefan Fischer",
-        "Stefania Degaetano-Ortlieb",
-        "Elke Teich",
-        "Hannah Kermes"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:rsc",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:rsc"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D26-7",
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Lehrstuhl Englische Sprach- und \u00dcbersetzungswissenschaft, Fakult\u00e4t P, Fachrichtung Sprachwissenschaft und Sprachtechnologie, Universit\u00e4t des Saarlandes, Campus A2.2, 66123 Saarbr\u00fccken, Germany"
-    ],
-    "RelatedIdentifier": [
-        "Kermes, Hannah, Stefania Degaetano, Ashraf Khamis, J\u00f6rg Knappen, and Elke Teich. 2016. \u201cThe Royal Society Corpus: From Uncharted Data to Corpus.\u201d In Proceedings of the LREC 2016. Portoroz, Slovenia. http://www.lrec-conf.org/proceedings/lrec2016/summaries/792.html"
-    ],
-    "ResourceType": [
-        "Collection",
-        "Written Corpus",
-        "Diachronic Corpus"
-    ],
-    "Rights": [
-        "CC-BY-SA-NC-4.0"
-    ],
-    "SpatialCoverage": [
-        "1665/1869",
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " period : ( 1665-07-01T11:59:59Z - None ) ",
-    "author": [
-        "Elke Teich, Lehrstuhl Englische Sprach- und \u00dcbersetzungswissenschaft, Fakult\u00e4t P, Fachrichtung Sprachwissenschaft und Sprachtechnologie, Universit\u00e4t des Saarlandes, Campus A2.2, 66123 Saarbr\u00fccken, Germany"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:rsc;2016-10-25T15:13:24Z;The Royal Society Corpus;Elke Teich, Lehrstuhl Englische Sprach- und \u00dcbersetzungswissenschaft, Fakult\u00e4t P, Fachrichtung Sprachwissenschaft und Sprachtechnologie, Universit\u00e4t des Saarlandes, Campus A2.2, 66123 Saarbr\u00fccken, Germany;Early Modern English;Late Modern English;Science;Scientific English;Language change;The Royal Society Corpus (RSC) is based on the first two centuries of the Philosophical Transactions of the Royal Society of London from its beginning in 1665 to 1869. It includes all publications of the journal written mainly in English and containing running text. The Philosophical Transactions was the first periodical of scientific writing in England.\n\nThe RSC consists of approximately 35 million token and is encoded for text type (abstracts, articles), author, year of publication. Information about decade and 50-year periods are also available allowing for a diachronic analysis of different granularity.\n\nThe corpus is tokenized and linguistically annotated for lemma and part-of-speech using TreeTagger (Schmid 1994, Schmid 1995). For spelling normalization we use a trained model of VARD (Baron and Rayson 2008). As a special feature, we encode with each unit (word token) its average surprisal, i.e. the average amount of information it encodes in number of bits, with words as units and trigram as contexts [cf. Genzel and Charniak 2002).;Lehrstuhl Englische Sprach- und \u00dcbersetzungswissenschaft, Fakult\u00e4t P, Fachrichtung Sprachwissenschaft und Sprachtechnologie, Universit\u00e4t des Saarlandes, Campus A2.2, 66123 Saarbr\u00fccken, Germany;Elke Teich;Stefania Degaetano-Ortlieb;Stefan Fischer;Hannah Kermes;Ashraf Khamis;J\u00f6rg Knappen;2016;Collection;Written Corpus;Diachronic Corpus;text/xml;clarind-uds:rsc;hdl:11858/00-246C-0000-0023-8D26-7;eng;Kermes, Hannah, Stefania Degaetano, Ashraf Khamis, J\u00f6rg Knappen, and Elke Teich. 2016. \u201cThe Royal Society Corpus: From Uncharted Data to Corpus.\u201d In Proceedings of the LREC 2016. Portoroz, Slovenia. http://www.lrec-conf.org/proceedings/lrec2016/summaries/792.html;1665/1869;United Kingdom;CC-BY-SA-NC-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a68e94b4-9de7-5f5c-bb98-05190e734f2f",
-    "notes": [
-        "The Royal Society Corpus (RSC) is based on the first two centuries of the Philosophical Transactions of the Royal Society of London from its beginning in 1665 to 1869. It includes all publications of the journal written mainly in English and containing running text. The Philosophical Transactions was the first periodical of scientific writing in England.\n\nThe RSC consists of approximately 35 million token and is encoded for text type (abstracts, articles), author, year of publication. Information about decade and 50-year periods are also available allowing for a diachronic analysis of different granularity.\n\nThe corpus is tokenized and linguistically annotated for lemma and part-of-speech using TreeTagger (Schmid 1994, Schmid 1995). For spelling normalization we use a trained model of VARD (Baron and Rayson 2008). As a special feature, we encode with each unit (word token) its average surprisal, i.e. the average amount of information it encodes in number of bits, with words as units and trigram as contexts [cf. Genzel and Charniak 2002)."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:rsc"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Early Modern English"
-        },
-        {
-            "name": "Late Modern English"
-        },
-        {
-            "name": "Science"
-        },
-        {
-            "name": "Scientific English"
-        },
-        {
-            "name": "Language change"
-        }
-    ],
-    "title": [
-        "The Royal Society Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a68ffe86-502f-5d75-81a0-882cc74d9c17.json b/oaitestdata/clarin-oai_dc/SET_1/json/a68ffe86-502f-5d75-81a0-882cc74d9c17.json
deleted file mode 100644
index ca6a0f0e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a68ffe86-502f-5d75-81a0-882cc74d9c17.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3997",
-    "MetadataAccess": [
-        "oai:ota:oucs:3997"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "More, Hannah, 1745-1833."
-    ],
-    "fulltext": "oai:ota:oucs:3997;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3997.xml;The history of Mr. Fantom: the new fashioned philosopher and his man William.;More, Hannah, 1745-1833.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a68ffe86-502f-5d75-81a0-882cc74d9c17",
-    "oai_identifier": [
-        "oai:ota:oucs:3997"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The history of Mr. Fantom: the new fashioned philosopher and his man William."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3997.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a6aa44d1-ecb3-5df4-ae1b-7127ed56abc4.json b/oaitestdata/clarin-oai_dc/SET_1/json/a6aa44d1-ecb3-5df4-ae1b-7127ed56abc4.json
deleted file mode 100644
index fa89d097..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a6aa44d1-ecb3-5df4-ae1b-7127ed56abc4.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "A"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1555",
-    "MetadataAccess": [
-        "oai:ota:oucs:1555"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Emerson, Ralph Waldo"
-    ],
-    "fulltext": "oai:ota:oucs:1555;2018-04-16T15:30:51Z;http://ota.ox.ac.uk/headers/1555.xml;Essays; First series;Emerson, Ralph Waldo;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;A;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a6aa44d1-ecb3-5df4-ae1b-7127ed56abc4",
-    "oai_identifier": [
-        "oai:ota:oucs:1555"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Essays; First series"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1555.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a6aeadc1-2dab-505d-9687-66f2bdc0b01f.json b/oaitestdata/clarin-oai_dc/SET_1/json/a6aeadc1-2dab-505d-9687-66f2bdc0b01f.json
deleted file mode 100644
index e686d4c0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a6aeadc1-2dab-505d-9687-66f2bdc0b01f.json
+++ /dev/null
@@ -1,96 +0,0 @@
-{
-    "Contact": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 3",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1029",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1029"
-    ],
-    "PID": "http://hdl.handle.net/11356/1029",
-    "PublicationTimestamp": "2013-09-30T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11356/1052"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Krek, Simon",
-        "Dobrovoljc, Kaja",
-        "Erjavec, Toma\u017e",
-        "Ledinek, Nina",
-        "Holz, Nanika",
-        "Mo\u017ee, Sara"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1029;2017-10-13T10:34:01Z;hdl_11356_1023;hdl_11356_1024;Training corpus ssj500k 1.3;Krek, Simon;Erjavec, Toma\u017e;Dobrovoljc, Kaja;Mo\u017ee, Sara;Ledinek, Nina;Holz, Nanika;tagging;dependency treebank;parsing;named entities;tokenisation;manual annotation;TEI;The ssj500k training corpus is based on two training corpora built within the JOS project (http://nl.ijs.si/jos/). It contains the jos100k corpus and additional material from the jos1M corpus forming a training corpus with 500,000 words, manually checked and annotated on the levels of tokenization, segmentation, morphosyntactic tagging, syntactic dependency parsing and named entities. The ssj500k corpus uses the JOS morphosyntactic tagset with 1,902 tags and dependencies with 10 labels. The part of the corpus annotated with dependency relations contains 11,411 sentences, named entities are annotated in the original jos100k part of the corpus.;2013-09-30;corpus;http://hdl.handle.net/11356/1029;slv;http://hdl.handle.net/11356/1052;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);https://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 3;Centre for Language Resources and Technologies, University of Ljubljana;http://eng.slovenscina.eu/tehnologije/ucni-korpus",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a6aeadc1-2dab-505d-9687-66f2bdc0b01f",
-    "notes": [
-        "The ssj500k training corpus is based on two training corpora built within the JOS project (http://nl.ijs.si/jos/). It contains the jos100k corpus and additional material from the jos1M corpus forming a training corpus with 500,000 words, manually checked and annotated on the levels of tokenization, segmentation, morphosyntactic tagging, syntactic dependency parsing and named entities. The ssj500k corpus uses the JOS morphosyntactic tagset with 1,902 tags and dependencies with 10 labels. The part of the corpus annotated with dependency relations contains 11,411 sentences, named entities are annotated in the original jos100k part of the corpus."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1029"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "dependency treebank"
-        },
-        {
-            "name": "parsing"
-        },
-        {
-            "name": "named entities"
-        },
-        {
-            "name": "tokenisation"
-        },
-        {
-            "name": "manual annotation"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "Training corpus ssj500k 1.3"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a6ba9d94-ad47-5ef2-a345-d5a6dd711c73.json b/oaitestdata/clarin-oai_dc/SET_1/json/a6ba9d94-ad47-5ef2-a345-d5a6dd711c73.json
deleted file mode 100644
index 6cc5840e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a6ba9d94-ad47-5ef2-a345-d5a6dd711c73.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4060",
-    "MetadataAccess": [
-        "oai:ota:oucs:4060"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Cibber, Theophilus, 1703-1758."
-    ],
-    "fulltext": "oai:ota:oucs:4060;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4060.xml;A lick at a liar: or, calumny detected. Being an occasional letter to a friend from Theophilus Cibber, comedian;Cibber, Theophilus, 1703-1758.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a6ba9d94-ad47-5ef2-a345-d5a6dd711c73",
-    "oai_identifier": [
-        "oai:ota:oucs:4060"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A lick at a liar: or, calumny detected. Being an occasional letter to a friend from Theophilus Cibber, comedian"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4060.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a6c93757-1d87-52c4-beec-3910baf0725b.json b/oaitestdata/clarin-oai_dc/SET_1/json/a6c93757-1d87-52c4-beec-3910baf0725b.json
deleted file mode 100644
index 4e439a68..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a6c93757-1d87-52c4-beec-3910baf0725b.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 36.7 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2164",
-    "MetadataAccess": [
-        "oai:ota:oucs:2164"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gaskell, Elizabeth Cleghorn, 1810-1865"
-    ],
-    "fulltext": "oai:ota:oucs:2164;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/2164.xml;The squire's story / by Elizabeth Gaskell;Gaskell, Elizabeth Cleghorn, 1810-1865;text_and_corpus_linguistics;Fiction -- Great Britain -- 19th century;Short stories -- Great Britain -- 19th century;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 36.7 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a6c93757-1d87-52c4-beec-3910baf0725b",
-    "oai_identifier": [
-        "oai:ota:oucs:2164"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- Great Britain -- th century"
-        },
-        {
-            "name": "Short stories -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "The squire's story / by Elizabeth Gaskell"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2164.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a6e20d7f-dad0-554d-8abe-7867058c9ed6.json b/oaitestdata/clarin-oai_dc/SET_1/json/a6e20d7f-dad0-554d-8abe-7867058c9ed6.json
deleted file mode 100644
index 239a7c1a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a6e20d7f-dad0-554d-8abe-7867058c9ed6.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "IJP PAN"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "downloadable_files_count: 10",
-        "application/vnd.oasis.opendocument.text",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/408",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/408"
-    ],
-    "PID": "http://hdl.handle.net/11321/408",
-    "PublicationTimestamp": "2017-06-29T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "IJP PAN"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Bugajska, Maria"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/408;2017-06-29T07:52:34Z;hdl_11321_3;hdl_11321_4;korpus testowy;Bugajska, Maria;korpus testowy;korpus testowy na warsztaty z DSpace;2017-06-29;corpus;http://hdl.handle.net/11321/408;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.oasis.opendocument.text;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;text/plain;downloadable_files_count: 10;IJP PAN",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a6e20d7f-dad0-554d-8abe-7867058c9ed6",
-    "notes": [
-        "korpus testowy na warsztaty z DSpace"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/408"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "korpus testowy"
-        }
-    ],
-    "title": [
-        "korpus testowy"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a70592a8-24df-5ef7-83b4-5952d4412f27.json b/oaitestdata/clarin-oai_dc/SET_1/json/a70592a8-24df-5ef7-83b4-5952d4412f27.json
deleted file mode 100644
index cbd44a41..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a70592a8-24df-5ef7-83b4-5952d4412f27.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Center of Computational Linguistics, Vytautas Magnus University"
-    ],
-    "Contributor": [
-        "Utka, dr. Andrius"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English",
-        "Lithuanian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-626",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-626"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-626",
-    "PublicationTimestamp": "2007-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2007"
-    ],
-    "Publisher": [
-        "Center of Computational Linguistics, Vytautas Magnus University"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Lithuania"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-626;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;English-Lithuanian Machine Translation Service;Utka, dr. Andrius;On-line freely accessible machine translation tool for translating English webpages or texts into Lithuanian.;2007;toolService;http://hdl.handle.net/11372/LRT-626;eng;lit;downloadable_files_count: 0;Lithuania;Center of Computational Linguistics, Vytautas Magnus University;http://vertimas.vdu.lt/twsas/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a70592a8-24df-5ef7-83b4-5952d4412f27",
-    "notes": [
-        "On-line freely accessible machine translation tool for translating English webpages or texts into Lithuanian."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-626"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "English-Lithuanian Machine Translation Service"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a72b96d6-01c5-5c1b-aeb2-70c5f98e8b58.json b/oaitestdata/clarin-oai_dc/SET_1/json/a72b96d6-01c5-5c1b-aeb2-70c5f98e8b58.json
deleted file mode 100644
index d0dc35b7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a72b96d6-01c5-5c1b-aeb2-70c5f98e8b58.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish",
-        "Serbian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/68",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/68"
-    ],
-    "PID": "http://hdl.handle.net/10794/68",
-    "PublicationTimestamp": "2015-04-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/68;2017-10-31T15:27:25Z;hdl_10794_1;hdl_10794_2;ASPAC \u2013 Swedish-Serbian (cyrillic) (2017-10-16);ASPAC \u2013 svenska-serbiska (kyrilliskt) (2017-10-16);n/a, n/a;ASPAC;Parallel;Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.;Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat.;2015-04-16;corpus;http://hdl.handle.net/10794/68;swe;srp;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/octet-stream;application/gzip;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/aspacsvsbc",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a72b96d6-01c5-5c1b-aeb2-70c5f98e8b58",
-    "notes": [
-        "Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.",
-        "Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/68"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ASPAC"
-        },
-        {
-            "name": "Parallel"
-        }
-    ],
-    "title": [
-        "ASPAC \u2013 Swedish-Serbian (cyrillic) (2017-10-16)",
-        "ASPAC \u2013 svenska-serbiska (kyrilliskt) (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a74e7107-a01c-55b0-ac36-342cc20b4b6a.json b/oaitestdata/clarin-oai_dc/SET_1/json/a74e7107-a01c-55b0-ac36-342cc20b4b6a.json
deleted file mode 100644
index 72c2621d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a74e7107-a01c-55b0-ac36-342cc20b4b6a.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Norwegian",
-        "Vietnamese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/22",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/22"
-    ],
-    "PID": "http://hdl.handle.net/11509/22",
-    "PublicationTimestamp": "2012-12-19T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Sk\u00e5nland, Marianne Haslev"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/22;2016-06-01T11:51:52Z;hdl_11509_1;hdl_11509_2;Norwegian-Vietnamese Dictionary;Norsk-vietnamesisk ordbok;Sk\u00e5nland, Marianne Haslev;Lexical Conceptual Resource;Text;Computational Lexicon;Norwegian;Vietnamese;The Resource Norsk-vietnamesisk ordbok (resource short name: NVO) [Norwegian-Vietnamese dictionary] results from research in the project Norsk-vietnamesisk ordbok at University of Bergen, Norway.  Each entry in the dictionary contains information about: pronunciation (phonetic), word class, conjugation forms and meanings, along with the corresponding translation into Vietnamese and Norwegian example sentences for each intended meaning. The IPR holder kindly permits the distribution of the LMF version as a downloadable resource.;2012-12-19;lexicalConceptualResource;NOT_DEFINED_FOR_V2;http://hdl.handle.net/11509/22;nor;vie;Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0);http://creativecommons.org/licenses/by-nc-nd/3.0/;CC;text/xml;text/xml;downloadable_files_count: 1;https://github.com/clarino/nvo",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a74e7107-a01c-55b0-ac36-342cc20b4b6a",
-    "notes": [
-        "The Resource Norsk-vietnamesisk ordbok (resource short name: NVO) [Norwegian-Vietnamese dictionary] results from research in the project Norsk-vietnamesisk ordbok at University of Bergen, Norway.  Each entry in the dictionary contains information about: pronunciation (phonetic), word class, conjugation forms and meanings, along with the corresponding translation into Vietnamese and Norwegian example sentences for each intended meaning. The IPR holder kindly permits the distribution of the LMF version as a downloadable resource."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/22"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Lexical Conceptual Resource"
-        },
-        {
-            "name": "Text"
-        },
-        {
-            "name": "Computational Lexicon"
-        },
-        {
-            "name": "Norwegian"
-        },
-        {
-            "name": "Vietnamese"
-        }
-    ],
-    "title": [
-        "Norwegian-Vietnamese Dictionary",
-        "Norsk-vietnamesisk ordbok"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a751666d-f222-5810-9175-a2cc3c95f78b.json b/oaitestdata/clarin-oai_dc/SET_1/json/a751666d-f222-5810-9175-a2cc3c95f78b.json
deleted file mode 100644
index effad2b5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a751666d-f222-5810-9175-a2cc3c95f78b.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "Persian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-912",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-912"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-912",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-912;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Old Persian;ca. 40.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-912;fas;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#opers",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a751666d-f222-5810-9175-a2cc3c95f78b",
-    "notes": [
-        "ca. 40.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-912"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Old Persian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a76271e4-1531-5681-b898-6c066a1e5aa8.json b/oaitestdata/clarin-oai_dc/SET_1/json/a76271e4-1531-5681-b898-6c066a1e5aa8.json
deleted file mode 100644
index 8707cb1c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a76271e4-1531-5681-b898-6c066a1e5aa8.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "unp"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/vnd.oasis.opendocument.text",
-        "downloadable_files_count: 10",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/398",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/398"
-    ],
-    "PID": "http://hdl.handle.net/11321/398",
-    "PublicationTimestamp": "2017-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "unp"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Wales, Be"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/398;2018-06-13T05:36:57Z;hdl_11321_3;hdl_11321_4;pseudotitle;Wales, Be;sociolect;mine not yours;2017-05-30;lexicalConceptualResource;http://hdl.handle.net/11321/398;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;application/vnd.oasis.opendocument.text;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;downloadable_files_count: 10;unp",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a76271e4-1531-5681-b898-6c066a1e5aa8",
-    "notes": [
-        "mine not yours"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/398"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "sociolect"
-        }
-    ],
-    "title": [
-        "pseudotitle"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a764e040-c64a-5f6d-a6ae-2bbe1026e920.json b/oaitestdata/clarin-oai_dc/SET_1/json/a764e040-c64a-5f6d-a6ae-2bbe1026e920.json
deleted file mode 100644
index caa8d696..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a764e040-c64a-5f6d-a6ae-2bbe1026e920.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5471",
-    "MetadataAccess": [
-        "oai:ota:oucs:5471"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "More, Hannah, 1745-1833."
-    ],
-    "fulltext": "oai:ota:oucs:5471;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5471.xml;The day of judgment: or, the grand reckoning.;More, Hannah, 1745-1833.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a764e040-c64a-5f6d-a6ae-2bbe1026e920",
-    "oai_identifier": [
-        "oai:ota:oucs:5471"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The day of judgment: or, the grand reckoning."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5471.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a7a5b9be-8ee5-5053-8d47-b1cd7bcf8cfa.json b/oaitestdata/clarin-oai_dc/SET_1/json/a7a5b9be-8ee5-5053-8d47-b1cd7bcf8cfa.json
deleted file mode 100644
index 67972e9f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a7a5b9be-8ee5-5053-8d47-b1cd7bcf8cfa.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4508",
-    "MetadataAccess": [
-        "oai:ota:oucs:4508"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Defoe, Daniel, 1661?-1731."
-    ],
-    "fulltext": "oai:ota:oucs:4508;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4508.xml;A system of magick; or, a history of the black art: Being an historical account of mankind's most early dealing with the Devil; and how the acquaintance on both sides first begun.;Defoe, Daniel, 1661?-1731.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a7a5b9be-8ee5-5053-8d47-b1cd7bcf8cfa",
-    "oai_identifier": [
-        "oai:ota:oucs:4508"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A system of magick; or, a history of the black art: Being an historical account of mankind's most early dealing with the Devil; and how the acquaintance on both sides first begun."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4508.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a7dfd0f7-99ad-5680-9706-ccf8823ba5b3.json b/oaitestdata/clarin-oai_dc/SET_1/json/a7dfd0f7-99ad-5680-9706-ccf8823ba5b3.json
deleted file mode 100644
index 2e202100..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a7dfd0f7-99ad-5680-9706-ccf8823ba5b3.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5441",
-    "MetadataAccess": [
-        "oai:ota:oucs:5441"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Jones, Henry, 1721-1770."
-    ],
-    "fulltext": "oai:ota:oucs:5441;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5441.xml;The patriot enterprize: or an address to Britain. A poem. Inscribed to the Right Hon. William Pitt, ... by Mr. Jones, author of The Earl of Essex. To which is added, The Prussian campaign, a poem. Celebrating the atchievements [sic] of Frederick the Great, in the years 1756-57. By William Dobson, L.L.B.;Jones, Henry, 1721-1770.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a7dfd0f7-99ad-5680-9706-ccf8823ba5b3",
-    "oai_identifier": [
-        "oai:ota:oucs:5441"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The patriot enterprize: or an address to Britain. A poem. Inscribed to the Right Hon. William Pitt, ... by Mr. Jones, author of The Earl of Essex. To which is added, The Prussian campaign, a poem. Celebrating the atchievements [sic] of Frederick the Great, in the years 1756-57. By William Dobson, L.L.B."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5441.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a7f2aa47-2563-56d9-98c8-a16aa11ebb75.json b/oaitestdata/clarin-oai_dc/SET_1/json/a7f2aa47-2563-56d9-98c8-a16aa11ebb75.json
deleted file mode 100644
index b0e4df1d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a7f2aa47-2563-56d9-98c8-a16aa11ebb75.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "text/xml",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Finnish",
-        "Northern Sami"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/91",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/91"
-    ],
-    "PID": "http://hdl.handle.net/11509/91",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "CC",
-        "http://creativecommons.org/licenses/by/3.0/"
-    ],
-    "author": [
-        "Giellatekno - Saami Language Technology, UiT The Arctic University of Norway"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/91;2016-09-06T12:38:54Z;hdl_11509_1;hdl_11509_2;Finnish-North Saami dictionary;Giellatekno - Saami Language Technology, UiT The Arctic University of Norway;Dictionary;Machine-readable Lexicon;Bilingual Dictionary;The Finnish-North Saami dictionary is the work done by Giellatekno at UiT The Arctic University of Norway, Kotus in Helsinki, and members of the language communities. In particular, the following colleagues have contributed to the creation of the ressource: Trond Trosterud and Ciprian Gerstenberger. It contains 12594 entries in Giellatekno's dictionary xml format. In spite of the extensive quality control, it may contain entries with objectionable translations. If you find any errors or want to add more words, download the file, edit it, and send it back to giellatekno@uit.no.\r\nPlease note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno.;2015;lexicalConceptualResource;http://hdl.handle.net/11509/91;fin;sme;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);CC;http://creativecommons.org/licenses/by/3.0/;application/zip;text/plain; charset=utf-8;text/xml;downloadable_files_count: 1;Giellatekno - Saami Language Technology;http://giellatekno.uit.no/index.eng.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a7f2aa47-2563-56d9-98c8-a16aa11ebb75",
-    "notes": [
-        "The Finnish-North Saami dictionary is the work done by Giellatekno at UiT The Arctic University of Norway, Kotus in Helsinki, and members of the language communities. In particular, the following colleagues have contributed to the creation of the ressource: Trond Trosterud and Ciprian Gerstenberger. It contains 12594 entries in Giellatekno's dictionary xml format. In spite of the extensive quality control, it may contain entries with objectionable translations. If you find any errors or want to add more words, download the file, edit it, and send it back to giellatekno@uit.no.\r\nPlease note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/91"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Dictionary"
-        },
-        {
-            "name": "Machine-readable Lexicon"
-        },
-        {
-            "name": "Bilingual Dictionary"
-        }
-    ],
-    "title": [
-        "Finnish-North Saami dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a80f56e1-ec4e-5fb2-af72-8a253a20226e.json b/oaitestdata/clarin-oai_dc/SET_1/json/a80f56e1-ec4e-5fb2-af72-8a253a20226e.json
deleted file mode 100644
index 5389c9e9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a80f56e1-ec4e-5fb2-af72-8a253a20226e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3675",
-    "MetadataAccess": [
-        "oai:ota:oucs:3675"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pope, Alexander, 1688-1744."
-    ],
-    "fulltext": "oai:ota:oucs:3675;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3675.xml;An essay on criticism: Written by Mr. Pope.;Pope, Alexander, 1688-1744.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a80f56e1-ec4e-5fb2-af72-8a253a20226e",
-    "oai_identifier": [
-        "oai:ota:oucs:3675"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An essay on criticism: Written by Mr. Pope."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3675.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a81f4ac8-955e-56ad-866d-9384c86f8379.json b/oaitestdata/clarin-oai_dc/SET_1/json/a81f4ac8-955e-56ad-866d-9384c86f8379.json
deleted file mode 100644
index 798b2bbc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a81f4ac8-955e-56ad-866d-9384c86f8379.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Akademicka"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-163690",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-163690"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CEA-8",
-    "PublicationTimestamp": "1800-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1800"
-    ],
-    "Publisher": [
-        "Drukarnia Akademicka"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/163690",
-        "oai:jbc.bj.uj.edu.pl:publication:172070"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1701/1800"
-    ],
-    "TempCoverageBegin": 53662478399,
-    "TempCoverageEnd": 53662478399,
-    "TemporalCoverage": " point in time : 1701-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1701-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1701-07-01T11:59:59Z",
-    "author": [
-        "\u015aniadecki, J\u0119drzej (1768-1838)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-163690;2019-02-28T18:49:50Z;Pocz\u0105tki Chemii : Stosownie Do Teraznieyszego Tey Umiei\u0119tnosci Stanu Dla Pozytku Uczniow I S\u0142uchaczow U\u0142ozone Y Za Wzor Lekcyi Akademickich S\u0142uzyc Mai\u0105ce. T. 2 Przez J\u0119drzeia Sniadeckiego Filozofii i Medycyny Doctora [...];\u015aniadecki, J\u0119drzej (1768-1838);starodruki 18\u00a0w.;Drukarnia Akademicka;1800;starodruk;application/xml;clarind-uds:poldilemma-163690;hdl:11858/00-246C-0000-0023-8CEA-8;Biblioteka Jagiello\u0144ska, BJ St. Dr. 50975 I/1;pol;lat;http://jbc.bj.uj.edu.pl/Content/163690;oai:jbc.bj.uj.edu.pl:publication:172070;1701/1800;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a81f4ac8-955e-56ad-866d-9384c86f8379",
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-163690"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Pocz\u0105tki Chemii : Stosownie Do Teraznieyszego Tey Umiei\u0119tnosci Stanu Dla Pozytku Uczniow I S\u0142uchaczow U\u0142ozone Y Za Wzor Lekcyi Akademickich S\u0142uzyc Mai\u0105ce. T. 2 Przez J\u0119drzeia Sniadeckiego Filozofii i Medycyny Doctora [...]"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a8246a5b-d177-57c2-869e-94cda2a788a6.json b/oaitestdata/clarin-oai_dc/SET_1/json/a8246a5b-d177-57c2-869e-94cda2a788a6.json
deleted file mode 100644
index 948d7b15..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a8246a5b-d177-57c2-869e-94cda2a788a6.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "less than 512 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0432",
-    "MetadataAccess": [
-        "oai:ota:oucs:0432"
-    ],
-    "PublicationTimestamp": "1971-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1971"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Cheatle, Syd,  1943-"
-    ],
-    "fulltext": "oai:ota:oucs:0432;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0432.xml; Straight up  / compiled by Dirk Geens;Cheatle, Syd,  1943-;1971;text_and_corpus_linguistics;Plays -- Great Britain -- 20th century;eng;Forms part of the Louvain corpus of modern English drama deposited in 1983. The text does not conform to modern standards of text encoding. The text is all capitals, with words broken over line boundaries, undocumented markup characters, and numeric codes for the identities of the players. ;Oxford Text Archive, University of Oxford;less than 512 KB;Text;Plays;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a8246a5b-d177-57c2-869e-94cda2a788a6",
-    "notes": [
-        "Forms part of the Louvain corpus of modern English drama deposited in 1983. The text does not conform to modern standards of text encoding. The text is all capitals, with words broken over line boundaries, undocumented markup characters, and numeric codes for the identities of the players. "
-    ],
-    "oai_identifier": [
-        "oai:ota:oucs:0432"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        " Straight up  / compiled by Dirk Geens"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0432.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a827f07a-1ec4-5b78-a70c-b07f5d83f012.json b/oaitestdata/clarin-oai_dc/SET_1/json/a827f07a-1ec4-5b78-a70c-b07f5d83f012.json
deleted file mode 100644
index 523b70cb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a827f07a-1ec4-5b78-a70c-b07f5d83f012.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1036",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1036"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1036",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1036;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;L1 Acquisition Penelope Brown Rossel;Language Acquisition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1036;eng;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI1127%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a827f07a-1ec4-5b78-a70c-b07f5d83f012",
-    "notes": [
-        "Language Acquisition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1036"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "L1 Acquisition Penelope Brown Rossel"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a85fdc1c-3ca3-50c7-9de9-c93c1af6680c.json b/oaitestdata/clarin-oai_dc/SET_1/json/a85fdc1c-3ca3-50c7-9de9-c93c1af6680c.json
deleted file mode 100644
index 3961ac33..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a85fdc1c-3ca3-50c7-9de9-c93c1af6680c.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Institute for Language and Speech Processing"
-    ],
-    "Contributor": [
-        "Gavrilidou, Maria"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Modern Greek (1453-)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-266",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-266"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-266",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institute for Language and Speech Processing"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Greece"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-266;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;HNC (Hellenic National Corpus);Gavrilidou, Maria;General language corpus of standard Modern Greek; 47 MWs;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-266;ell;application/octet-stream;downloadable_files_count: 0;Greece;Institute for Language and Speech Processing;http://hnc.ilsp.gr/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a85fdc1c-3ca3-50c7-9de9-c93c1af6680c",
-    "notes": [
-        "General language corpus of standard Modern Greek; 47 MWs"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-266"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "HNC (Hellenic National Corpus)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a8614c09-95f2-5ea9-8317-9d64556af4d1.json b/oaitestdata/clarin-oai_dc/SET_1/json/a8614c09-95f2-5ea9-8317-9d64556af4d1.json
deleted file mode 100644
index e8390aab..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a8614c09-95f2-5ea9-8317-9d64556af4d1.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/31",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/31"
-    ],
-    "PID": "http://hdl.handle.net/10794/31",
-    "PublicationTimestamp": "2015-03-31T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Borin, Lars"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/31;2017-10-27T14:35:02Z;hdl_10794_1;hdl_10794_2;LWT-PWN;LWT-PWN;Borin, Lars;Swedish;PWN;Wordnet;LWT;LWT-PWN is the IDS/LWT concept list linked to Princeton WordNet 3.0 word sense identifiers.;LWT-PWN \u00e4r IDS/LWT-begreppslistan med l\u00e4nkar till ordbetydelseidentifierare i Princeton WordNet 3.0.;2015-03-31;lexicalConceptualResource;http://hdl.handle.net/10794/31;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/lwt-pwn",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a8614c09-95f2-5ea9-8317-9d64556af4d1",
-    "notes": [
-        "LWT-PWN is the IDS/LWT concept list linked to Princeton WordNet 3.0 word sense identifiers.",
-        "LWT-PWN \u00e4r IDS/LWT-begreppslistan med l\u00e4nkar till ordbetydelseidentifierare i Princeton WordNet 3.0."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/31"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "PWN"
-        },
-        {
-            "name": "Wordnet"
-        },
-        {
-            "name": "LWT"
-        }
-    ],
-    "title": [
-        "LWT-PWN",
-        "LWT-PWN"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a8691b27-ef56-5478-a784-3b9fcfcabad5.json b/oaitestdata/clarin-oai_dc/SET_1/json/a8691b27-ef56-5478-a784-3b9fcfcabad5.json
deleted file mode 100644
index 4c9a08b6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a8691b27-ef56-5478-a784-3b9fcfcabad5.json
+++ /dev/null
@@ -1,89 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 4",
-        "application/pdf",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1080",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1080"
-    ],
-    "PID": "http://hdl.handle.net/11356/1080",
-    "PublicationTimestamp": "2016-12-22T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11356/1084"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by-sa/4.0/"
-    ],
-    "author": [
-        "\u010cibej, Jaka",
-        "Erjavec, Toma\u017e",
-        "Fi\u0161er, Darja",
-        "Arhar Holdt, \u0160pela"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1080;2018-10-18T22:28:50Z;hdl_11356_1023;hdl_11356_1024;CMC training corpus Janes-Norm 1.0;Erjavec, Toma\u017e;Fi\u0161er, Darja;\u010cibej, Jaka;Arhar Holdt, \u0160pela;computer-mediated communication;tokenisation;word normalisation;manual annotation;TEI;Janes-Norm is a manually annotated corpus of Slovene Computer-Mediated Communication (CMC). It is meant as a gold-standard training and testing dataset for tokenisation, sentence segmentation and word normalisation of non-standard Slovene. The corpus is also automatically annotated with morphosyntactic descriptions and lemmas. As the corpus has been carefully manually annotated, it is also suitable for detailed linguistic explorations which require higlhy accurate and reliable annotations.\r\n\r\nThe corpus is further described in:\r\nERJAVEC, Toma\u017e, \u010cIBEJ, Jaka, ARHAR HOLDT, \u0160pela, LJUBE\u0160I\u0106, Nikola, FI\u0160ER, Darja. Gold-standard datasets for annotation of Slovene computer-mediated communication. In Proceedings of RASLAN 2016: Recent Advances in Slavonic Natural Language Processing. Brno: Tribun EU, 2016, pp. 29-40, https://nlp.fi.muni.cz/raslan/raslan16.pdf\r\n\r\nNote that a related corpus, Janes-Tag is also available, cf. http://hdl.handle.net/11356/1079.;2016-12-22;corpus;http://hdl.handle.net/11356/1080;slv;http://hdl.handle.net/11356/1084;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);PUB;https://creativecommons.org/licenses/by-sa/4.0/;application/pdf;application/pdf;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 4;Jo\u017eef Stefan Institute;http://nl.ijs.si/janes/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a8691b27-ef56-5478-a784-3b9fcfcabad5",
-    "notes": [
-        "Janes-Norm is a manually annotated corpus of Slovene Computer-Mediated Communication (CMC). It is meant as a gold-standard training and testing dataset for tokenisation, sentence segmentation and word normalisation of non-standard Slovene. The corpus is also automatically annotated with morphosyntactic descriptions and lemmas. As the corpus has been carefully manually annotated, it is also suitable for detailed linguistic explorations which require higlhy accurate and reliable annotations.\r\n\r\nThe corpus is further described in:\r\nERJAVEC, Toma\u017e, \u010cIBEJ, Jaka, ARHAR HOLDT, \u0160pela, LJUBE\u0160I\u0106, Nikola, FI\u0160ER, Darja. Gold-standard datasets for annotation of Slovene computer-mediated communication. In Proceedings of RASLAN 2016: Recent Advances in Slavonic Natural Language Processing. Brno: Tribun EU, 2016, pp. 29-40, https://nlp.fi.muni.cz/raslan/raslan16.pdf\r\n\r\nNote that a related corpus, Janes-Tag is also available, cf. http://hdl.handle.net/11356/1079."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1080"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "computer-mediated communication"
-        },
-        {
-            "name": "tokenisation"
-        },
-        {
-            "name": "word normalisation"
-        },
-        {
-            "name": "manual annotation"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "CMC training corpus Janes-Norm 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a86bb735-b86b-5779-b23f-966ade8ae502.json b/oaitestdata/clarin-oai_dc/SET_1/json/a86bb735-b86b-5779-b23f-966ade8ae502.json
deleted file mode 100644
index ff740822..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a86bb735-b86b-5779-b23f-966ade8ae502.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4739",
-    "MetadataAccess": [
-        "oai:ota:oucs:4739"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Cowley, Mrs. (Hannah), 1743-1809."
-    ],
-    "fulltext": "oai:ota:oucs:4739;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4739.xml;The poetry of Anna Matilda;Cowley, Mrs. (Hannah), 1743-1809.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a86bb735-b86b-5779-b23f-966ade8ae502",
-    "oai_identifier": [
-        "oai:ota:oucs:4739"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The poetry of Anna Matilda"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4739.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a8745161-b2f1-5902-a5d1-72816b1bcbb4.json b/oaitestdata/clarin-oai_dc/SET_1/json/a8745161-b2f1-5902-a5d1-72816b1bcbb4.json
deleted file mode 100644
index e7b57bee..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a8745161-b2f1-5902-a5d1-72816b1bcbb4.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "text/xml",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Southern Sami"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/105",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/105"
-    ],
-    "PID": "http://hdl.handle.net/11509/105",
-    "PublicationTimestamp": "2015-10-10T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "The Divvun group at UiT The Arctic University of Norway",
-        "Giellatekno - Saami Language Technology, UiT The Arctic University of Norway"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/105;2016-09-06T13:02:06Z;hdl_11509_1;hdl_11509_2;South Saami lemma frequency list;Giellatekno - Saami Language Technology, UiT The Arctic University of Norway;The Divvun group at UiT The Arctic University of Norway;Lemma Frequencies;South Saami;The South Saami lemma frequency list is work done by the Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language community. In particular, Ciprian-Virgil Gerstenberger compiled the list from the entire SIKOR South Saami corpus version 2015-10-10. The data is in an one-lemma-per-line format with the following values: <ABS_FREQ> <LEMMA> <POS>. Since the list has been derived automatically, it may contain wrong values. In case you find any errors the creators would appreciate your feedback sent to giellatekno@uit.no and feedback@divvun.no. Please note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata).;2015-10-10;corpus;http://hdl.handle.net/11509/105;sma;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;text/xml;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Giellatekno - Saami Language Technology;http://giellatekno.uit.no/index.eng.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a8745161-b2f1-5902-a5d1-72816b1bcbb4",
-    "notes": [
-        "The South Saami lemma frequency list is work done by the Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language community. In particular, Ciprian-Virgil Gerstenberger compiled the list from the entire SIKOR South Saami corpus version 2015-10-10. The data is in an one-lemma-per-line format with the following values: <ABS_FREQ> <LEMMA> <POS>. Since the list has been derived automatically, it may contain wrong values. In case you find any errors the creators would appreciate your feedback sent to giellatekno@uit.no and feedback@divvun.no. Please note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata)."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/105"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Lemma Frequencies"
-        },
-        {
-            "name": "South Saami"
-        }
-    ],
-    "title": [
-        "South Saami lemma frequency list"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a87e9bf6-8ee6-5df4-80cc-a4cc6fe5fd77.json b/oaitestdata/clarin-oai_dc/SET_1/json/a87e9bf6-8ee6-5df4-80cc-a4cc6fe5fd77.json
deleted file mode 100644
index a623a1ba..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a87e9bf6-8ee6-5df4-80cc-a4cc6fe5fd77.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Clausen, Wendell Vernon, 1923-",
-        "Waite, Stephen V.F."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 161 KB)"
-    ],
-    "Language": [
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0337",
-    "MetadataAccess": [
-        "oai:ota:oucs:0337"
-    ],
-    "PublicationYear": [
-        "100-130"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Satires"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Juvenal"
-    ],
-    "fulltext": "oai:ota:oucs:0337;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0337.xml;Saturae;D. Iunii Iuvenalis Saturae / Juvenal;Satires;Juvenal;100-130;text_and_corpus_linguistics;Verse satire -- Italy -- B.C.;lat;Oxford Text Archive, University of Oxford;Clausen, Wendell Vernon, 1923-;Waite, Stephen V.F.;(1 file : ca. 161 KB);Text;Satires;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a87e9bf6-8ee6-5df4-80cc-a4cc6fe5fd77",
-    "oai_identifier": [
-        "oai:ota:oucs:0337"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Verse satire -- Italy -- B.C."
-        }
-    ],
-    "title": [
-        "Saturae",
-        "D. Iunii Iuvenalis Saturae / Juvenal",
-        "Satires"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0337.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a8889950-f7ec-5118-a5c2-36be3892e5b2.json b/oaitestdata/clarin-oai_dc/SET_1/json/a8889950-f7ec-5118-a5c2-36be3892e5b2.json
deleted file mode 100644
index b8101550..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a8889950-f7ec-5118-a5c2-36be3892e5b2.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Arabic",
-        "Danish",
-        "Dutch",
-        "English",
-        "German",
-        "Modern Greek (1453-)",
-        "Italian",
-        "Japanese",
-        "Korean",
-        "Portuguese",
-        "Russian",
-        "Spanish",
-        "Turkish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-173",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-173"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-173",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-173;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Amara - universal subtitles;Large set of subtitles available for download in multiple languages. Can be used as parallel corpus.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-173;ara;dan;nld;eng;deu;ell;ita;jpn;kor;por;rus;spa;tur;downloadable_files_count: 0;http://www.universalsubtitles.org/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a8889950-f7ec-5118-a5c2-36be3892e5b2",
-    "notes": [
-        "Large set of subtitles available for download in multiple languages. Can be used as parallel corpus."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-173"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Amara - universal subtitles"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a88c3e70-0ff4-5a25-ae5d-f7921c84c76a.json b/oaitestdata/clarin-oai_dc/SET_1/json/a88c3e70-0ff4-5a25-ae5d-f7921c84c76a.json
deleted file mode 100644
index f7dc5c7b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a88c3e70-0ff4-5a25-ae5d-f7921c84c76a.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4026",
-    "MetadataAccess": [
-        "oai:ota:oucs:4026"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Kenrick, W. (William), 1725?-1779."
-    ],
-    "fulltext": "oai:ota:oucs:4026;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4026.xml;Love in the Suds: a town eclogue, being the lamentation of Roscius for the loss of his Nyky ...;Kenrick, W. (William), 1725?-1779.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a88c3e70-0ff4-5a25-ae5d-f7921c84c76a",
-    "oai_identifier": [
-        "oai:ota:oucs:4026"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Love in the Suds: a town eclogue, being the lamentation of Roscius for the loss of his Nyky ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4026.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a890afeb-7657-5b00-b1bd-530ed1784f60.json b/oaitestdata/clarin-oai_dc/SET_1/json/a890afeb-7657-5b00-b1bd-530ed1784f60.json
deleted file mode 100644
index 714ee025..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a890afeb-7657-5b00-b1bd-530ed1784f60.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Oriya (macrolanguage)",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2879",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2879"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2879",
-    "PublicationTimestamp": "2018-11-26T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Bojar, Ond\u0159ej",
-        "Parida, Shantipriya"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2879;2018-11-26T14:54:22Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;OdiEnCorp 1.0;Parida, Shantipriya;Bojar, Ond\u0159ej;Odia English Parallel Corpus;Odia Monolingual Corpus;English-Odia Machine Translation;Data\r\n----\r\nWe have collected English-Odia parallel and monolingual data from the\r\navailable public websites for NLP research in Odia.\r\n\r\nThe parallel corpus consists of English-Odia parallel Bible, Odia\r\ndigital library, and Odisha Goverment websites. It covers bible,\r\nliterature, goverment of Odisha and its policies. We have processed the\r\nraw data collected from the websites, performed alignments (a mix of\r\nmanual and automatic alignments) and release the corpus in a form ready\r\nfor various NLP tasks.\r\n\r\nThe Odia monolingual data consists of Odia-Wikipedia and Odia e-magazine\r\nwebsites. Because the major portion of data is extracted from\r\nOdia-Wikipedia, it covers all kinds of domains. The e-magazines data\r\nmostly cover the literature domain. We have preprocessed the monolingual\r\ndata including de-duplication, text normalization, and sentence\r\nsegmentation to make it ready for various NLP tasks.\r\n\r\nCorpus Formats\r\n--------------\r\nBoth corpora are in simple tab-delimited plain text files.\r\n\r\nThe parallel corpus files have three columns:\r\n- the original book/source of the sentence pair\r\n- the English sentence\r\n- the corresponding Odia sentence\r\n\r\nThe monolingual corpus has a varying number of columns:\r\n- each line corresponds to one *paragraph* (or related unit) of the\r\n  original source\r\n- each tab-delimited unit corresponds to one *sentence* in the paragraph\r\n\r\n\r\nData Statistics\r\n----------------\r\nThe statistics of the current release is given below.\r\n\r\nParallel Corpus Statistics\r\n---------------------------\r\n\r\nDataset\tSentences\t#English tokens \t#Odia tokens\r\n-------\t---------\t----------------\t-------------\r\nTrain  \t    27136\t          706567\t       604147\r\nDev    \t      948\t           21912\t        19513\r\nTest   \t     1262\t           28488\t        24365\r\n-------\t---------\t----------------\t-------------\r\nTotal  \t    29346\t          756967\t       648025\r\n\r\nDomain Level Statistics\r\n------------------------\r\n\r\nDomain            \tSentences\t#English tokens \t#Odia tokens\r\n------------------\t---------\t----------------\t-------------\r\nBible             \t    29069\t          756861\t       640157\r\nLiterature        \t      424\t            7977\t         6611\r\nGoverment policies\t      204\t            1411\t         1257\r\n------------------\t---------\t----------------\t-------------\r\nTotal             \t    29697\t          766249\t       648025\r\n\r\nMonolingual Corpus Statistics\r\n-----------------------------\r\n\r\nParagraphs\tSentences\t#Odia tokens\r\n----------\t---------\t------------\r\n     71698\t   221546\t     2641308\r\n\r\nDomain Level Statistics\r\n-----------------------\r\n\r\nDomain        \tParagraphs    \tSentences\t#Odia tokens\r\n--------------\t--------------\t---------\t-------------\r\nGeneral (wiki)\t30468 (42.49%)\t   102085\t      1320367\r\nLiterature    \t41230 (57.50%)\t   119461\t      1320941\r\n--------------\t--------------\t---------\t-------------\r\nTotal         \t         71698\t   221546\t      2641308\r\n\r\n\r\nCitation\r\n--------\r\n\r\nIf you use this corpus, please cite it directly (see above), but please cite also the following paper:\r\n\r\nTitle: OdiEnCorp: Odia-English and Odia-Only Corpus for Machine Translation\r\nAuthor: Shantipriya Parida, Ondrej Bojar, and Satya Ranjan Dash\r\nProceedings of the Third International Conference on Smart Computing & Informatics (SCI) 2018\r\nSeries: Smart Innovation, Systems and Technologies (SIST)\r\nPublisher: Springer Singapore;2018-11-26;corpus;http://hdl.handle.net/11234/1-2879;ori;eng;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a890afeb-7657-5b00-b1bd-530ed1784f60",
-    "notes": [
-        "Data\r\n----\r\nWe have collected English-Odia parallel and monolingual data from the\r\navailable public websites for NLP research in Odia.\r\n\r\nThe parallel corpus consists of English-Odia parallel Bible, Odia\r\ndigital library, and Odisha Goverment websites. It covers bible,\r\nliterature, goverment of Odisha and its policies. We have processed the\r\nraw data collected from the websites, performed alignments (a mix of\r\nmanual and automatic alignments) and release the corpus in a form ready\r\nfor various NLP tasks.\r\n\r\nThe Odia monolingual data consists of Odia-Wikipedia and Odia e-magazine\r\nwebsites. Because the major portion of data is extracted from\r\nOdia-Wikipedia, it covers all kinds of domains. The e-magazines data\r\nmostly cover the literature domain. We have preprocessed the monolingual\r\ndata including de-duplication, text normalization, and sentence\r\nsegmentation to make it ready for various NLP tasks.\r\n\r\nCorpus Formats\r\n--------------\r\nBoth corpora are in simple tab-delimited plain text files.\r\n\r\nThe parallel corpus files have three columns:\r\n- the original book/source of the sentence pair\r\n- the English sentence\r\n- the corresponding Odia sentence\r\n\r\nThe monolingual corpus has a varying number of columns:\r\n- each line corresponds to one *paragraph* (or related unit) of the\r\n  original source\r\n- each tab-delimited unit corresponds to one *sentence* in the paragraph\r\n\r\n\r\nData Statistics\r\n----------------\r\nThe statistics of the current release is given below.\r\n\r\nParallel Corpus Statistics\r\n---------------------------\r\n\r\nDataset\tSentences\t#English tokens \t#Odia tokens\r\n-------\t---------\t----------------\t-------------\r\nTrain  \t    27136\t          706567\t       604147\r\nDev    \t      948\t           21912\t        19513\r\nTest   \t     1262\t           28488\t        24365\r\n-------\t---------\t----------------\t-------------\r\nTotal  \t    29346\t          756967\t       648025\r\n\r\nDomain Level Statistics\r\n------------------------\r\n\r\nDomain            \tSentences\t#English tokens \t#Odia tokens\r\n------------------\t---------\t----------------\t-------------\r\nBible             \t    29069\t          756861\t       640157\r\nLiterature        \t      424\t            7977\t         6611\r\nGoverment policies\t      204\t            1411\t         1257\r\n------------------\t---------\t----------------\t-------------\r\nTotal             \t    29697\t          766249\t       648025\r\n\r\nMonolingual Corpus Statistics\r\n-----------------------------\r\n\r\nParagraphs\tSentences\t#Odia tokens\r\n----------\t---------\t------------\r\n     71698\t   221546\t     2641308\r\n\r\nDomain Level Statistics\r\n-----------------------\r\n\r\nDomain        \tParagraphs    \tSentences\t#Odia tokens\r\n--------------\t--------------\t---------\t-------------\r\nGeneral (wiki)\t30468 (42.49%)\t   102085\t      1320367\r\nLiterature    \t41230 (57.50%)\t   119461\t      1320941\r\n--------------\t--------------\t---------\t-------------\r\nTotal         \t         71698\t   221546\t      2641308\r\n\r\n\r\nCitation\r\n--------\r\n\r\nIf you use this corpus, please cite it directly (see above), but please cite also the following paper:\r\n\r\nTitle: OdiEnCorp: Odia-English and Odia-Only Corpus for Machine Translation\r\nAuthor: Shantipriya Parida, Ondrej Bojar, and Satya Ranjan Dash\r\nProceedings of the Third International Conference on Smart Computing & Informatics (SCI) 2018\r\nSeries: Smart Innovation, Systems and Technologies (SIST)\r\nPublisher: Springer Singapore"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2879"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Odia English Parallel Corpus"
-        },
-        {
-            "name": "Odia Monolingual Corpus"
-        },
-        {
-            "name": "English-Odia Machine Translation"
-        }
-    ],
-    "title": [
-        "OdiEnCorp 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a8c31252-55de-5367-9c2d-f7f2eeb52dbb.json b/oaitestdata/clarin-oai_dc/SET_1/json/a8c31252-55de-5367-9c2d-f7f2eeb52dbb.json
deleted file mode 100644
index b10d40b1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a8c31252-55de-5367-9c2d-f7f2eeb52dbb.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/552",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/552"
-    ],
-    "PID": "http://hdl.handle.net/11321/552",
-    "PublicationTimestamp": "2018-07-23T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Wr\u00f3blewska, Alina"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/552;2018-07-23T20:22:13Z;hdl_11321_3;hdl_11321_4;Dependency parsing models for Polish;Wr\u00f3blewska, Alina;dependency parsing;Polish;PDB;PDB-based parsing models are trained on the current version of Polish Depedency Bank with the publicly available parsing systems: MaltParser, MateParser, and UDPipe.;2018-07-23;toolService;http://hdl.handle.net/11321/552;pol;downloadable_files_count: 0;Institute of Computer Science, Polish Academy of Sciences;http://zil.ipipan.waw.pl/PDB/PDBparser",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a8c31252-55de-5367-9c2d-f7f2eeb52dbb",
-    "notes": [
-        "PDB-based parsing models are trained on the current version of Polish Depedency Bank with the publicly available parsing systems: MaltParser, MateParser, and UDPipe."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/552"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "dependency parsing"
-        },
-        {
-            "name": "Polish"
-        },
-        {
-            "name": "PDB"
-        }
-    ],
-    "title": [
-        "Dependency parsing models for Polish"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a8f097ea-0ae1-569f-9a31-86ad6c93a68e.json b/oaitestdata/clarin-oai_dc/SET_1/json/a8f097ea-0ae1-569f-9a31-86ad6c93a68e.json
deleted file mode 100644
index d9aeb5c6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a8f097ea-0ae1-569f-9a31-86ad6c93a68e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4745",
-    "MetadataAccess": [
-        "oai:ota:oucs:4745"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gilpin, William, 1724-1804."
-    ],
-    "fulltext": "oai:ota:oucs:4745;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4745.xml;The lives of John Trueman, Richard Atkins, &c;Gilpin, William, 1724-1804.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a8f097ea-0ae1-569f-9a31-86ad6c93a68e",
-    "oai_identifier": [
-        "oai:ota:oucs:4745"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The lives of John Trueman, Richard Atkins, &c"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4745.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a905694d-b591-5e49-82f5-8ced2796235b.json b/oaitestdata/clarin-oai_dc/SET_1/json/a905694d-b591-5e49-82f5-8ced2796235b.json
deleted file mode 100644
index 3136121f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a905694d-b591-5e49-82f5-8ced2796235b.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "IPI PAN"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
-        "downloadable_files_count: 3",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/585",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/585"
-    ],
-    "PID": "http://hdl.handle.net/11321/585",
-    "PublicationTimestamp": "2018-07-26T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "IPI PAN"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0)",
-        "http://creativecommons.org/licenses/by-sa/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Wawer, Aleksander"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/585;2018-07-26T15:37:47Z;hdl_11321_3;hdl_11321_4;LCM-PL;Wawer, Aleksander;language abstraction;dictionary describing abstraction level of verbs;2018-07-26;lexicalConceptualResource;http://hdl.handle.net/11321/585;pol;Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0);http://creativecommons.org/licenses/by-sa/3.0/;CC;text/plain; charset=utf-8;application/vnd.openxmlformats-officedocument.spreadsheetml.sheet;application/vnd.openxmlformats-officedocument.spreadsheetml.sheet;application/octet-stream;downloadable_files_count: 3;IPI PAN;http://zil.ipipan.waw.pl/LCM-PL",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a905694d-b591-5e49-82f5-8ced2796235b",
-    "notes": [
-        "dictionary describing abstraction level of verbs"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/585"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "language abstraction"
-        }
-    ],
-    "title": [
-        "LCM-PL"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a933aa45-9b4c-5f4d-81f6-59a6480b6e35.json b/oaitestdata/clarin-oai_dc/SET_1/json/a933aa45-9b4c-5f4d-81f6-59a6480b6e35.json
deleted file mode 100644
index 0831ffdc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a933aa45-9b4c-5f4d-81f6-59a6480b6e35.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "ClarinPL"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 35",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/323",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/323"
-    ],
-    "PID": "http://hdl.handle.net/11321/323",
-    "PublicationTimestamp": "2016-10-18T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "ClarinPL"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "author": [
-        "Paw\u0142owski, Adam"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/323;2016-10-18T13:32:38Z;hdl_11321_3;hdl_11321_322;Clarin PL 2 M3 Milestone;Paw\u0142owski, Adam;M3;Clarin 2.0 - M3 Milestone files;2016-10-18;corpus;http://hdl.handle.net/11321/323;pol;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/octet-stream;downloadable_files_count: 35;ClarinPL",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a933aa45-9b4c-5f4d-81f6-59a6480b6e35",
-    "notes": [
-        "Clarin 2.0 - M3 Milestone files"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/323"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_322"
-    ],
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Clarin PL 2 M3 Milestone"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a93eb371-ebcd-52fc-bb61-bfe36db0812f.json b/oaitestdata/clarin-oai_dc/SET_1/json/a93eb371-ebcd-52fc-bb61-bfe36db0812f.json
deleted file mode 100644
index 219297da..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a93eb371-ebcd-52fc-bb61-bfe36db0812f.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Smith, John B."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(2 files : ca. 375, 369 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1657",
-    "MetadataAccess": [
-        "oai:ota:oucs:1657"
-    ],
-    "PublicationTimestamp": "1925-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1925"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Woolf, Virginia, 1882-1941"
-    ],
-    "fulltext": "oai:ota:oucs:1657;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/1657.xml;Mrs. Dalloway / Virginia Woolf;Woolf, Virginia, 1882-1941;1925;text_and_corpus_linguistics;English fiction -- 20th century;eng;Oxford Text Archive, University of Oxford;Smith, John B.;text/sgml;(2 files : ca. 375, 369 KB);Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a93eb371-ebcd-52fc-bb61-bfe36db0812f",
-    "oai_identifier": [
-        "oai:ota:oucs:1657"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English fiction -- th century"
-        }
-    ],
-    "title": [
-        "Mrs. Dalloway / Virginia Woolf"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1657.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a946f01f-d5d4-5241-bd79-340f08cd51d7.json b/oaitestdata/clarin-oai_dc/SET_1/json/a946f01f-d5d4-5241-bd79-340f08cd51d7.json
deleted file mode 100644
index f3534e8b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a946f01f-d5d4-5241-bd79-340f08cd51d7.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5456",
-    "MetadataAccess": [
-        "oai:ota:oucs:5456"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dibdin, Charles, 1745-1814."
-    ],
-    "fulltext": "oai:ota:oucs:5456;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5456.xml;The deserter. A new musical drama: as it is performed at the Theatre-Royal in Drury-Lane.;Dibdin, Charles, 1745-1814.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a946f01f-d5d4-5241-bd79-340f08cd51d7",
-    "oai_identifier": [
-        "oai:ota:oucs:5456"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The deserter. A new musical drama: as it is performed at the Theatre-Royal in Drury-Lane."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5456.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a955917a-92a9-5922-b653-1f95ae74a261.json b/oaitestdata/clarin-oai_dc/SET_1/json/a955917a-92a9-5922-b653-1f95ae74a261.json
deleted file mode 100644
index ca891dcd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a955917a-92a9-5922-b653-1f95ae74a261.json
+++ /dev/null
@@ -1,130 +0,0 @@
-{
-    "Contact": [
-        "Technische Universit\u00e4t Darmstadt"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/x-gzip",
-        "downloadable_files_count: 48",
-        "text/plain"
-    ],
-    "Language": [
-        "Afrikaans",
-        "Arabic",
-        "Bengali",
-        "Bulgarian",
-        "Czech",
-        "Danish",
-        "German",
-        "Modern Greek (1453-)",
-        "English",
-        "Estonian",
-        "Persian",
-        "Finnish",
-        "French",
-        "Gujarati",
-        "Hebrew",
-        "Hindi",
-        "Croatian",
-        "Hungarian",
-        "Indonesian",
-        "Italian",
-        "Japanese",
-        "Korean",
-        "Latvian",
-        "Lithuanian",
-        "Malayalam",
-        "Macedonian",
-        "Dutch",
-        "Norwegian",
-        "Polish",
-        "Portuguese",
-        "Romanian",
-        "Russian",
-        "Slovak",
-        "Slovenian",
-        "Somali",
-        "Spanish",
-        "Albanian",
-        "Swahili (macrolanguage)",
-        "Swedish",
-        "Tamil",
-        "Tagalog",
-        "Thai",
-        "Turkish",
-        "Ukrainian",
-        "Undetermined",
-        "Vietnamese",
-        "Chinese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2207",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2207"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2207",
-    "PublicationTimestamp": "2016-04-14T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Technische Universit\u00e4t Darmstadt"
-    ],
-    "RelatedIdentifier": [
-        "http://www.lrec-conf.org/proceedings/lrec2016/pdf/388_Paper.pdf"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NoDerivatives 4.0 International (CC BY-ND 4.0)",
-        "PUB",
-        "http://creativecommons.org/licenses/by-nc/4.0/"
-    ],
-    "author": [
-        "Habernal, Ivan",
-        "Gurevych, Iryna",
-        "Zayed, Omnia"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2207;2019-01-02T14:27:37Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;C4Corpus (CC BY-ND part);Gurevych, Iryna;Habernal, Ivan;Zayed, Omnia;CommonCrawl;Creative Commons;Web corpus;Amazon Web Services;A large web corpus (over 10 billion tokens) licensed under CreativeCommons license family in 50+ languages that has been extracted from CommonCrawl, the largest publicly available general Web crawl to date with about 2 billion crawled URLs.;2016-04-14;corpus;http://hdl.handle.net/11372/LRT-2207;afr;ara;ben;bul;ces;dan;deu;ell;eng;est;fas;fin;fra;guj;heb;hin;hrv;hun;ind;ita;jpn;kor;lav;lit;mal;mkd;nld;nor;pol;por;ron;rus;slk;slv;som;spa;sqi;swa;swe;tam;tgl;tha;tur;ukr;und;vie;zho;http://www.lrec-conf.org/proceedings/lrec2016/pdf/388_Paper.pdf;Creative Commons - Attribution-NoDerivatives 4.0 International (CC BY-ND 4.0);PUB;http://creativecommons.org/licenses/by-nc/4.0/;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;text/plain;downloadable_files_count: 48;Technische Universit\u00e4t Darmstadt;https://dkpro.github.io/dkpro-c4corpus/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a955917a-92a9-5922-b653-1f95ae74a261",
-    "notes": [
-        "A large web corpus (over 10 billion tokens) licensed under CreativeCommons license family in 50+ languages that has been extracted from CommonCrawl, the largest publicly available general Web crawl to date with about 2 billion crawled URLs."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2207"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "CommonCrawl"
-        },
-        {
-            "name": "Creative Commons"
-        },
-        {
-            "name": "Web corpus"
-        },
-        {
-            "name": "Amazon Web Services"
-        }
-    ],
-    "title": [
-        "C4Corpus (CC BY-ND part)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a96c0941-3257-5ecc-a94a-6939a51480e6.json b/oaitestdata/clarin-oai_dc/SET_1/json/a96c0941-3257-5ecc-a94a-6939a51480e6.json
deleted file mode 100644
index 43e32135..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a96c0941-3257-5ecc-a94a-6939a51480e6.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2498",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2498"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2498",
-    "PublicationTimestamp": "2017-09-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-1516"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Kr\u00ed\u017e, Vincent",
-        "Hladk\u00e1, Barbora"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2498;2018-07-02T22:05:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Czech Legal Text Treebank 2.0;Kr\u00ed\u017e, Vincent;Hladk\u00e1, Barbora;treebank;Prague dependencies;named entities;semantic relations;The Czech Legal Text Treebank 2.0 (CLTT 2.0) annotates the same texts as the CLTT 1.0. These texts come from the legal domain and they are manually syntactically annotated. The CLTT 2.0 annotation on the syntactic layer is more elaborate than in the CLTT 1.0 from various aspects. In addition, new annotation layers were added to the data: (i) the layer of accounting entities, and (ii) the layer of semantic entity relations.;2017-09-01;corpus;http://hdl.handle.net/11234/1-2498;ces;http://hdl.handle.net/11234/1-1516;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/cltt2.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a96c0941-3257-5ecc-a94a-6939a51480e6",
-    "notes": [
-        "The Czech Legal Text Treebank 2.0 (CLTT 2.0) annotates the same texts as the CLTT 1.0. These texts come from the legal domain and they are manually syntactically annotated. The CLTT 2.0 annotation on the syntactic layer is more elaborate than in the CLTT 1.0 from various aspects. In addition, new annotation layers were added to the data: (i) the layer of accounting entities, and (ii) the layer of semantic entity relations."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2498"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "Prague dependencies"
-        },
-        {
-            "name": "named entities"
-        },
-        {
-            "name": "semantic relations"
-        }
-    ],
-    "title": [
-        "Czech Legal Text Treebank 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a98d9729-2308-58b0-95cb-b9c86a70233d.json b/oaitestdata/clarin-oai_dc/SET_1/json/a98d9729-2308-58b0-95cb-b9c86a70233d.json
deleted file mode 100644
index 6b56cb83..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a98d9729-2308-58b0-95cb-b9c86a70233d.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "text/xml",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Norwegian Bokm\u00e5l",
-        "Northern Sami"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/94",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/94"
-    ],
-    "PID": "http://hdl.handle.net/11509/94",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "The Divvun group at UiT The Arctic University of Norway",
-        "Giellatekno - Saami Language Technology, UiT The Arctic University of Norway"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/94;2016-09-06T12:58:14Z;hdl_11509_1;hdl_11509_2;Norwegian Bokm\u00e5l-North Saami dictionary;Giellatekno - Saami Language Technology, UiT The Arctic University of Norway;The Divvun group at UiT The Arctic University of Norway;Bilingual Lexicon;Norwegian;North Saami;Machine-readable Dictionary;The Norwegian Bokm\u00e5l-North Saami dictionary is the work done by Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language communities. In particular, the following colleagues have contributed to the creation of the ressource: Nils Jernsletten, Lene Antonsen, Trond Trosterud, Ritva Nystad, Ciprian Gerstenberger, Berit Merete Nystad Eskonsipo, Marja Eira, Siri Broch Johansen, Sjur Moshagen, and Tomi Pieski. The dictionary contains 25902 entries in Giellatekno's dictionary xml format. In spite of the extensive quality control, it may contain entries with objectionable translations. If you find any errors or want to add more words, download the file, edit it, and send it back to giellatekno@uit.no and feedback@divvun.no.\r\nPlease note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata).;2015;lexicalConceptualResource;http://hdl.handle.net/11509/94;nob;sme;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;application/zip;text/plain; charset=utf-8;text/xml;downloadable_files_count: 1;Giellatekno - Saami Language Technology;http://giellatekno.uit.no/index.eng.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a98d9729-2308-58b0-95cb-b9c86a70233d",
-    "notes": [
-        "The Norwegian Bokm\u00e5l-North Saami dictionary is the work done by Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language communities. In particular, the following colleagues have contributed to the creation of the ressource: Nils Jernsletten, Lene Antonsen, Trond Trosterud, Ritva Nystad, Ciprian Gerstenberger, Berit Merete Nystad Eskonsipo, Marja Eira, Siri Broch Johansen, Sjur Moshagen, and Tomi Pieski. The dictionary contains 25902 entries in Giellatekno's dictionary xml format. In spite of the extensive quality control, it may contain entries with objectionable translations. If you find any errors or want to add more words, download the file, edit it, and send it back to giellatekno@uit.no and feedback@divvun.no.\r\nPlease note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata)."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/94"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Bilingual Lexicon"
-        },
-        {
-            "name": "Norwegian"
-        },
-        {
-            "name": "North Saami"
-        },
-        {
-            "name": "Machine-readable Dictionary"
-        }
-    ],
-    "title": [
-        "Norwegian Bokm\u00e5l-North Saami dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a990dd20-3d65-53d2-9396-8bea3d5c9639.json b/oaitestdata/clarin-oai_dc/SET_1/json/a990dd20-3d65-53d2-9396-8bea3d5c9639.json
deleted file mode 100644
index 18c995e5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a990dd20-3d65-53d2-9396-8bea3d5c9639.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Ibtikarat team"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/xml",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Arabic"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1939",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1939"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1939",
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Ibtikarat team"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)",
-        "http://creativecommons.org/licenses/by-nc/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Namly, Driss"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1939;2017-02-06T11:05:06Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LMF Arabic characters lexicon;Namly, Driss;alphabet;An LMF conformant XML-based file containing all Arabic characters (letters, vowels and punctuations). Each character described with a description, different displays (isolated, at the beginning, middle and the end of a word), a codification (Unicode, others could be added later), and two transliterations (Buckwalter and wiki).;2014;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1939;ara;Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0);http://creativecommons.org/licenses/by-nc/4.0/;PUB;text/xml;text/plain; charset=utf-8;downloadable_files_count: 1;Ibtikarat team;http://arabic.emi.ac.ma/ibtikarat/?q=Resources",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a990dd20-3d65-53d2-9396-8bea3d5c9639",
-    "notes": [
-        "An LMF conformant XML-based file containing all Arabic characters (letters, vowels and punctuations). Each character described with a description, different displays (isolated, at the beginning, middle and the end of a word), a codification (Unicode, others could be added later), and two transliterations (Buckwalter and wiki)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1939"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "alphabet"
-        }
-    ],
-    "title": [
-        "LMF Arabic characters lexicon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a9b530d7-4c5d-5502-babb-23d0706d51c8.json b/oaitestdata/clarin-oai_dc/SET_1/json/a9b530d7-4c5d-5502-babb-23d0706d51c8.json
deleted file mode 100644
index ae8e8790..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a9b530d7-4c5d-5502-babb-23d0706d51c8.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4610",
-    "MetadataAccess": [
-        "oai:ota:oucs:4610"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Ferguson, Adam, 1723-1816."
-    ],
-    "fulltext": "oai:ota:oucs:4610;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4610.xml;An essay on the history of civil society: By Adam Ferguson, ...;Ferguson, Adam, 1723-1816.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a9b530d7-4c5d-5502-babb-23d0706d51c8",
-    "oai_identifier": [
-        "oai:ota:oucs:4610"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An essay on the history of civil society: By Adam Ferguson, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4610.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a9bb0e20-e690-5c07-96e7-fd48742e1122.json b/oaitestdata/clarin-oai_dc/SET_1/json/a9bb0e20-e690-5c07-96e7-fd48742e1122.json
deleted file mode 100644
index 4a0f46ea..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a9bb0e20-e690-5c07-96e7-fd48742e1122.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Ibtikarat team"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/xml",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Arabic"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1940",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1940"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1940",
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Ibtikarat team"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)",
-        "http://creativecommons.org/licenses/by-nc/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Namly, Driss"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1940;2017-02-06T11:05:11Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Arabic Particles Lexicon;Namly, Driss;particles;An XML-based file containing Arabic particles;2014;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1940;ara;Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0);http://creativecommons.org/licenses/by-nc/4.0/;PUB;text/xml;text/plain; charset=utf-8;downloadable_files_count: 1;Ibtikarat team;http://arabic.emi.ac.ma/ibtikarat/?q=Resources",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a9bb0e20-e690-5c07-96e7-fd48742e1122",
-    "notes": [
-        "An XML-based file containing Arabic particles"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1940"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "particles"
-        }
-    ],
-    "title": [
-        "Arabic Particles Lexicon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a9cdb67b-4be0-544a-9f9b-683688862803.json b/oaitestdata/clarin-oai_dc/SET_1/json/a9cdb67b-4be0-544a-9f9b-683688862803.json
deleted file mode 100644
index d5a9ca00..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a9cdb67b-4be0-544a-9f9b-683688862803.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Wikipedia"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 13",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/55",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/55"
-    ],
-    "PID": "http://hdl.handle.net/11321/55",
-    "PublicationTimestamp": "2015-04-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Wikipedia"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Wikipedia, Wiki Pedia"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/55;2015-04-23T07:13:26Z;hdl_11321_3;hdl_11321_4;Tygrys i 2 W\u015a;Wikipedia, Wiki Pedia;Opis;2015-04-01;corpus;http://hdl.handle.net/11321/55;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 13;Wikipedia;www.wikipedia.pl",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a9cdb67b-4be0-544a-9f9b-683688862803",
-    "notes": [
-        "Opis"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/55"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Tygrys i 2 W\u015a"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/a9ff0ad6-2d8a-5c44-a77e-fd6f519e60e5.json b/oaitestdata/clarin-oai_dc/SET_1/json/a9ff0ad6-2d8a-5c44-a77e-fd6f519e60e5.json
deleted file mode 100644
index 80934712..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/a9ff0ad6-2d8a-5c44-a77e-fd6f519e60e5.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "nak\u0142. aut."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-84708",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-84708"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D3A-A",
-    "PublicationTimestamp": "1760-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1760"
-    ],
-    "Publisher": [
-        "nak\u0142. aut."
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/84708",
-        "oai:jbc.bj.uj.edu.pl:publication:91328"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1701/1800"
-    ],
-    "TempCoverageBegin": 53662478399,
-    "TempCoverageEnd": 53662478399,
-    "TemporalCoverage": " point in time : 1701-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1701-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1701-07-01T11:59:59Z",
-    "author": [
-        "Zatorski, Aleksander Pawe\u0142 Marian (1722-1752)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-84708;2019-03-01T17:42:49Z;Przydatek Do uwag zupe\u0142nemu stanowi\u0105cych si\u0119 szcz\u0119\u015bciu s\u0142u\u017c\u0105cych &c. Osobliwy : To iest Listow rozlicznych do delikatney o pozwolon\u0105 przyia\u017a\u0144 negocyacyi s\u0142u\u017c\u0105cych, tomikow dwa. T. 2, Kilkadziesi\u0105t Listow, dalsze wierney Konkurencyi sukcesa zawierai\u0105cych Mai\u0105cy;Zatorski, Aleksander Pawe\u0142 Marian (1722-1752);starodruki 18\u00a0w.;nak\u0142. aut.;1760;starodruk;application/xml;clarind-uds:poldilemma-84708;hdl:11858/00-246C-0000-0023-8D3A-A;Biblioteka Jagiello\u0144ska, BJ St. Dr. 6810 I;pol;http://jbc.bj.uj.edu.pl/Content/84708;oai:jbc.bj.uj.edu.pl:publication:91328;1701/1800;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a9ff0ad6-2d8a-5c44-a77e-fd6f519e60e5",
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-84708"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Przydatek Do uwag zupe\u0142nemu stanowi\u0105cych si\u0119 szcz\u0119\u015bciu s\u0142u\u017c\u0105cych &c. Osobliwy : To iest Listow rozlicznych do delikatney o pozwolon\u0105 przyia\u017a\u0144 negocyacyi s\u0142u\u017c\u0105cych, tomikow dwa. T. 2, Kilkadziesi\u0105t Listow, dalsze wierney Konkurencyi sukcesa zawierai\u0105cych Mai\u0105cy"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/aa0ffe3f-1721-52c8-b3d3-36e69601cd1c.json b/oaitestdata/clarin-oai_dc/SET_1/json/aa0ffe3f-1721-52c8-b3d3-36e69601cd1c.json
deleted file mode 100644
index a25616e9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/aa0ffe3f-1721-52c8-b3d3-36e69601cd1c.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4086",
-    "MetadataAccess": [
-        "oai:ota:oucs:4086"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pennant, Thomas, 1726-1798."
-    ],
-    "fulltext": "oai:ota:oucs:4086;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4086.xml;Of the Patagonians. Formed from the relation of Father Falkener a Jesuit who had resided among them thirty eight years. And from the different voyagers who had met with this tall race;Pennant, Thomas, 1726-1798.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "aa0ffe3f-1721-52c8-b3d3-36e69601cd1c",
-    "oai_identifier": [
-        "oai:ota:oucs:4086"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Of the Patagonians. Formed from the relation of Father Falkener a Jesuit who had resided among them thirty eight years. And from the different voyagers who had met with this tall race"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4086.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/aa15b056-be30-58e1-b137-c1e2a040f3af.json b/oaitestdata/clarin-oai_dc/SET_1/json/aa15b056-be30-58e1-b137-c1e2a040f3af.json
deleted file mode 100644
index 6f4c519c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/aa15b056-be30-58e1-b137-c1e2a040f3af.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=c251fb3ad00c11e1a404080027e73ea2948a7fff88164e4ab581ea35197bb8c4",
-    "MetadataAccess": [
-        "c251fb3ad00c11e1a404080027e73ea2948a7fff88164e4ab581ea35197bb8c4"
-    ],
-    "PublicationTimestamp": "2012-07-17T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "fulltext": "c251fb3ad00c11e1a404080027e73ea2948a7fff88164e4ab581ea35197bb8c4;2018-11-15T16:39:41Z;toolService;toolService:tool;MBT \u00e2\u0080\u0093 Memory-Based Tagger-Generator and Tagger;MBT is a memory-based tagger-generator and tagger in one. The tagger-generator part can generate a sequence tagger on the basis of a training set of tagged sequences; the tagger part can tag new sequences. MBT can, for instance, be used to generate part-of-speech taggers or chunkers for natural language processing. It has also been used for named-entity recognition, information extraction in domain-specific texts, and disfluency chunking in transcribed speech.;2012-07-17",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "aa15b056-be30-58e1-b137-c1e2a040f3af",
-    "notes": [
-        "MBT is a memory-based tagger-generator and tagger in one. The tagger-generator part can generate a sequence tagger on the basis of a training set of tagged sequences; the tagger part can tag new sequences. MBT can, for instance, be used to generate part-of-speech taggers or chunkers for natural language processing. It has also been used for named-entity recognition, information extraction in domain-specific texts, and disfluency chunking in transcribed speech."
-    ],
-    "oai_identifier": [
-        "c251fb3ad00c11e1a404080027e73ea2948a7fff88164e4ab581ea35197bb8c4"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "MBT \u00e2\u0080\u0093 Memory-Based Tagger-Generator and Tagger"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/aa44b401-ce67-54ed-bc94-2a9b95db1ae8.json b/oaitestdata/clarin-oai_dc/SET_1/json/aa44b401-ce67-54ed-bc94-2a9b95db1ae8.json
deleted file mode 100644
index a4f9f55a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/aa44b401-ce67-54ed-bc94-2a9b95db1ae8.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=824f76bcbc8d11e1a404080027e73ea2dcf6c3290e944b38a24abab77a1d53e1",
-    "MetadataAccess": [
-        "824f76bcbc8d11e1a404080027e73ea2dcf6c3290e944b38a24abab77a1d53e1"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "824f76bcbc8d11e1a404080027e73ea2dcf6c3290e944b38a24abab77a1d53e1;2018-11-15T16:39:19Z;toolService;toolService:tool;UIMA/U-Compare OpenNLP Tokenizer;This is a UIMA wrapper for the OpenNLP Tokenizer tool. It splits English sentences into individual tokens. The tool forms part of the in-built library of components provided with the U-Compare platform (see separate META-SHARE record)  for building and evaluating text mining workflows. The U-Compare Workbench (see separate META-SHARE record), provides a graphical drag-and drop interface for the rapid creation of workflows. \n;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "aa44b401-ce67-54ed-bc94-2a9b95db1ae8",
-    "notes": [
-        "This is a UIMA wrapper for the OpenNLP Tokenizer tool. It splits English sentences into individual tokens. The tool forms part of the in-built library of components provided with the U-Compare platform (see separate META-SHARE record)  for building and evaluating text mining workflows. The U-Compare Workbench (see separate META-SHARE record), provides a graphical drag-and drop interface for the rapid creation of workflows. \n"
-    ],
-    "oai_identifier": [
-        "824f76bcbc8d11e1a404080027e73ea2dcf6c3290e944b38a24abab77a1d53e1"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "UIMA/U-Compare OpenNLP Tokenizer"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/aa5bd1ff-9fb2-53aa-a4ed-e1545596d20c.json b/oaitestdata/clarin-oai_dc/SET_1/json/aa5bd1ff-9fb2-53aa-a4ed-e1545596d20c.json
deleted file mode 100644
index e782ad0f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/aa5bd1ff-9fb2-53aa-a4ed-e1545596d20c.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4916-9",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4916-9"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-4916-9",
-    "PublicationTimestamp": "2009-11-02T11:59:59Z",
-    "PublicationYear": [
-        "2009"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-1458"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "\u010ce\u0161ka, Pavel",
-        "Bojar, Ond\u0159ej",
-        "Jan\u00ed\u010dek, Miroslav",
-        "Be\u0148a, Peter"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4916-9;2018-07-02T22:05:53Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;CzEng 0.7;Bojar, Ond\u0159ej;\u017dabokrtsk\u00fd, Zden\u011bk;\u010ce\u0161ka, Pavel;Be\u0148a, Peter;Jan\u00ed\u010dek, Miroslav;parallel corpus;CzEng 0.7 is a Czech-English parallel corpus compiled at the Institute of Formal and Applied Linguistics (\u00daFAL), Charles University, Prague. The corpus contains no manual annotation. It is limited only to texts which have been already available in an electronic form and which are not protected by authors' rights in the Czech Republic. The main purpose of the corpus is to support Czech-English and English-Czech machine translation research with the necessary data. CzEng 0.7 consists of a large set of parallel textual documents mainly from the fields of European law, information technology, and fiction, all of them converted into a uniform XML-based file format and provided with automatic sentence alignment.;2009-11-02;corpus;http://hdl.handle.net/11858/00-097C-0000-0001-4916-9;ces;eng;http://hdl.handle.net/11234/1-1458;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/czeng/czeng07/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "aa5bd1ff-9fb2-53aa-a4ed-e1545596d20c",
-    "notes": [
-        "CzEng 0.7 is a Czech-English parallel corpus compiled at the Institute of Formal and Applied Linguistics (\u00daFAL), Charles University, Prague. The corpus contains no manual annotation. It is limited only to texts which have been already available in an electronic form and which are not protected by authors' rights in the Czech Republic. The main purpose of the corpus is to support Czech-English and English-Czech machine translation research with the necessary data. CzEng 0.7 consists of a large set of parallel textual documents mainly from the fields of European law, information technology, and fiction, all of them converted into a uniform XML-based file format and provided with automatic sentence alignment."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4916-9"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parallel corpus"
-        }
-    ],
-    "title": [
-        "CzEng 0.7"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/aa6f754f-89cd-5278-a072-39d08021a343.json b/oaitestdata/clarin-oai_dc/SET_1/json/aa6f754f-89cd-5278-a072-39d08021a343.json
deleted file mode 100644
index eed55056..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/aa6f754f-89cd-5278-a072-39d08021a343.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/99",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/99"
-    ],
-    "PID": "http://hdl.handle.net/10794/99",
-    "PublicationTimestamp": "2013-03-06T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/99;2017-10-25T11:35:50Z;hdl_10794_1;hdl_10794_2;Blog mix 2005 (2017-02-17);Bloggmix 2005 (2017-02-17);n/a, n/a;Swedish;Blog;The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.;Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat.;2013-03-06;corpus;http://hdl.handle.net/10794/99;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;http://creativecommons.org/licenses/by/4.0/;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/bloggmix2005",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "aa6f754f-89cd-5278-a072-39d08021a343",
-    "notes": [
-        "The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.",
-        "Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/99"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Blog"
-        }
-    ],
-    "title": [
-        "Blog mix 2005 (2017-02-17)",
-        "Bloggmix 2005 (2017-02-17)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/aa8e1820-06e7-59fc-a1b6-0389eae20686.json b/oaitestdata/clarin-oai_dc/SET_1/json/aa8e1820-06e7-59fc-a1b6-0389eae20686.json
deleted file mode 100644
index b5f3737f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/aa8e1820-06e7-59fc-a1b6-0389eae20686.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4037",
-    "MetadataAccess": [
-        "oai:ota:oucs:4037"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Francklin, Thomas, 1721-1784."
-    ],
-    "fulltext": "oai:ota:oucs:4037;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4037.xml;Matilda: a tragedy. As it is performed at the Theatre-Royal in Drury-Lane. By the author of The Earl of Warwick.;Francklin, Thomas, 1721-1784.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "aa8e1820-06e7-59fc-a1b6-0389eae20686",
-    "oai_identifier": [
-        "oai:ota:oucs:4037"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Matilda: a tragedy. As it is performed at the Theatre-Royal in Drury-Lane. By the author of The Earl of Warwick."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4037.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/aa9ff81f-22df-5eca-8f02-4f61116e1800.json b/oaitestdata/clarin-oai_dc/SET_1/json/aa9ff81f-22df-5eca-8f02-4f61116e1800.json
deleted file mode 100644
index 355a27f4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/aa9ff81f-22df-5eca-8f02-4f61116e1800.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 1.14 MB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2138",
-    "MetadataAccess": [
-        "oai:ota:oucs:2138"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Eliot, George, 1819-1880"
-    ],
-    "fulltext": "oai:ota:oucs:2138;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/2138.xml;The mill on the Floss / by George Eliot;Eliot, George, 1819-1880;text_and_corpus_linguistics;Fiction -- Great Britain -- 19th century;Novels -- Great Britain -- 19th century;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 1.14 MB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "aa9ff81f-22df-5eca-8f02-4f61116e1800",
-    "oai_identifier": [
-        "oai:ota:oucs:2138"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- Great Britain -- th century"
-        },
-        {
-            "name": "Novels -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "The mill on the Floss / by George Eliot"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2138.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/aaa65ae1-c87c-55fa-8dfa-e380a720158a.json b/oaitestdata/clarin-oai_dc/SET_1/json/aaa65ae1-c87c-55fa-8dfa-e380a720158a.json
deleted file mode 100644
index 48fc1277..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/aaa65ae1-c87c-55fa-8dfa-e380a720158a.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "University of \u0141\u00f3d\u017a"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "application/pdf",
-        "application/zip"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/276",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/276"
-    ],
-    "PID": "http://hdl.handle.net/11321/276",
-    "PublicationTimestamp": "2016-03-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "University of \u0141\u00f3d\u017a"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "CC"
-    ],
-    "author": [
-        "P\u0119zik, Piotr"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/276;2016-06-02T20:27:29Z;hdl_11321_3;hdl_11321_4;Paralela corpus and search engine;P\u0119zik, Piotr;parallel corpus;corpus search engine;Paralela is as an open-ended, opportunistic parallel corpus of Polish-English and English-Polish translations. It currently contains 262 million words in 10,877,000 translation segments. The Paralela online search engine supports the SlopeQ query syntax for bilingual Polish-English corpus queries for the full dataset. Both the full texts and query results can be accessed and exported through the online application at http://paralela.clarin-pl.eu.;2016-03-01;toolService;http://hdl.handle.net/11321/276;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;CC;text/plain; charset=utf-8;application/pdf;application/zip;downloadable_files_count: 2;University of \u0141\u00f3d\u017a;http://paralela.clarin-pl.eu",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "aaa65ae1-c87c-55fa-8dfa-e380a720158a",
-    "notes": [
-        "Paralela is as an open-ended, opportunistic parallel corpus of Polish-English and English-Polish translations. It currently contains 262 million words in 10,877,000 translation segments. The Paralela online search engine supports the SlopeQ query syntax for bilingual Polish-English corpus queries for the full dataset. Both the full texts and query results can be accessed and exported through the online application at http://paralela.clarin-pl.eu."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/276"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parallel corpus"
-        },
-        {
-            "name": "corpus search engine"
-        }
-    ],
-    "title": [
-        "Paralela corpus and search engine"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/aaa7491e-45f8-5495-8b31-497270e923e0.json b/oaitestdata/clarin-oai_dc/SET_1/json/aaa7491e-45f8-5495-8b31-497270e923e0.json
deleted file mode 100644
index baefafa7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/aaa7491e-45f8-5495-8b31-497270e923e0.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=9dfd3aa056a411e2a2aa782bcb07413577c28fa1ac15497aaf1cb44bcd326db6",
-    "MetadataAccess": [
-        "9dfd3aa056a411e2a2aa782bcb07413577c28fa1ac15497aaf1cb44bcd326db6"
-    ],
-    "PublicationTimestamp": "2013-01-04T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "9dfd3aa056a411e2a2aa782bcb07413577c28fa1ac15497aaf1cb44bcd326db6;2018-11-15T16:40:00Z;corpus;corpus:text;NPChunks;The NPChunks training corpus contains approximately 1,000 sentences, in a total of 24,243 tokens, selected randomly from the written part of the CINTIL corpus (Barreto et al, 2006). The CINTIL corpus is a linguistically interpreted corpus of Portuguese composed of 1 Million annotated tokens from both written (689,124 tokens) and spoken (502,622 tokens) registers (http://cintil.ul.pt/pt/).;2013-01-04",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "aaa7491e-45f8-5495-8b31-497270e923e0",
-    "notes": [
-        "The NPChunks training corpus contains approximately 1,000 sentences, in a total of 24,243 tokens, selected randomly from the written part of the CINTIL corpus (Barreto et al, 2006). The CINTIL corpus is a linguistically interpreted corpus of Portuguese composed of 1 Million annotated tokens from both written (689,124 tokens) and spoken (502,622 tokens) registers (http://cintil.ul.pt/pt/)."
-    ],
-    "oai_identifier": [
-        "9dfd3aa056a411e2a2aa782bcb07413577c28fa1ac15497aaf1cb44bcd326db6"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "NPChunks"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/aadb8f9e-e787-5ffe-b574-8c4aff01dc0d.json b/oaitestdata/clarin-oai_dc/SET_1/json/aadb8f9e-e787-5ffe-b574-8c4aff01dc0d.json
deleted file mode 100644
index 3dd68ead..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/aadb8f9e-e787-5ffe-b574-8c4aff01dc0d.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/98",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/98"
-    ],
-    "PID": "http://hdl.handle.net/10794/98",
-    "PublicationTimestamp": "2013-03-06T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/98;2017-10-25T11:38:14Z;hdl_10794_1;hdl_10794_2;Blog mix 2004 (2017-02-17);Bloggmix 2004 (2017-02-17);n/a, n/a;Swedish;Blog;The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.;Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat.;2013-03-06;corpus;http://hdl.handle.net/10794/98;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/bloggmix2004",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "aadb8f9e-e787-5ffe-b574-8c4aff01dc0d",
-    "notes": [
-        "The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.",
-        "Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/98"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Blog"
-        }
-    ],
-    "title": [
-        "Blog mix 2004 (2017-02-17)",
-        "Bloggmix 2004 (2017-02-17)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/aae08f4c-14ff-5215-a42e-70c33a0d0307.json b/oaitestdata/clarin-oai_dc/SET_1/json/aae08f4c-14ff-5215-a42e-70c33a0d0307.json
deleted file mode 100644
index cd0a9d7f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/aae08f4c-14ff-5215-a42e-70c33a0d0307.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "text/xml",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Southern Sami"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/109",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/109"
-    ],
-    "PID": "http://hdl.handle.net/11509/109",
-    "PublicationTimestamp": "2015-10-17T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "The Divvun group at UiT The Arctic University of Norway",
-        "Giellatekno - Saami Language Technology, UiT The Arctic University of Norway"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/109;2016-09-06T12:52:07Z;hdl_11509_1;hdl_11509_2;South Saami N-grams;Giellatekno - Saami Language Technology, UiT The Arctic University of Norway;The Divvun group at UiT The Arctic University of Norway;South Saami;Ngram;1-gram;2-gram;3-gram;Language Model;The South Saami N-gram data set is work done by the Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language community. In particular, Ciprian-Virgil Gerstenberger compiled the data set from the entire SIKOR South Saami corpus version 2015-10-10. The length of the N-grams ranges from unigrams (single words) to tri-grams (101693 unigrams, 499288 bigrams, 112879 trigrams). Only N-grams within sentences have been counted. The data format follows the ARPA backoff N-gram models and has been generated using SRILM, the SRI Language Modeling Toolkit (http://www.speech.sri.com/projects/srilm/). Since the N-grams have been derived automatically, they may contain wrong values. In case you find any errors the creators would appreciate your feedback sent to giellatekno@uit.no and feedback@divvun.no. Please note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata).;2015-10-17;corpus;http://hdl.handle.net/11509/109;sma;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;application/zip;text/plain; charset=utf-8;text/xml;downloadable_files_count: 1;Giellatekno - Saami Language Technology;http://giellatekno.uit.no/index.eng.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "aae08f4c-14ff-5215-a42e-70c33a0d0307",
-    "notes": [
-        "The South Saami N-gram data set is work done by the Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language community. In particular, Ciprian-Virgil Gerstenberger compiled the data set from the entire SIKOR South Saami corpus version 2015-10-10. The length of the N-grams ranges from unigrams (single words) to tri-grams (101693 unigrams, 499288 bigrams, 112879 trigrams). Only N-grams within sentences have been counted. The data format follows the ARPA backoff N-gram models and has been generated using SRILM, the SRI Language Modeling Toolkit (http://www.speech.sri.com/projects/srilm/). Since the N-grams have been derived automatically, they may contain wrong values. In case you find any errors the creators would appreciate your feedback sent to giellatekno@uit.no and feedback@divvun.no. Please note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata)."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/109"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "South Saami"
-        },
-        {
-            "name": "Ngram"
-        },
-        {
-            "name": "-gram"
-        },
-        {
-            "name": "-gram"
-        },
-        {
-            "name": "-gram"
-        },
-        {
-            "name": "Language Model"
-        }
-    ],
-    "title": [
-        "South Saami N-grams"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/aaee2231-e12b-5e9b-ac60-21e387038ed0.json b/oaitestdata/clarin-oai_dc/SET_1/json/aaee2231-e12b-5e9b-ac60-21e387038ed0.json
deleted file mode 100644
index b65543f6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/aaee2231-e12b-5e9b-ac60-21e387038ed0.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4446",
-    "MetadataAccess": [
-        "oai:ota:oucs:4446"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Lennox, Charlotte, ca. 1729-1804."
-    ],
-    "fulltext": "oai:ota:oucs:4446;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4446.xml;Sophia: By Mrs. Charlotte Lennox. In two volumes. ... [pt.2];Lennox, Charlotte, ca. 1729-1804.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "aaee2231-e12b-5e9b-ac60-21e387038ed0",
-    "oai_identifier": [
-        "oai:ota:oucs:4446"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Sophia: By Mrs. Charlotte Lennox. In two volumes. ... [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4446.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/aaf17e7e-a8b7-5b04-b7a4-b9369c0eae91.json b/oaitestdata/clarin-oai_dc/SET_1/json/aaf17e7e-a8b7-5b04-b7a4-b9369c0eae91.json
deleted file mode 100644
index 84c6122e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/aaf17e7e-a8b7-5b04-b7a4-b9369c0eae91.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Jones, Alan"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 287 KB)"
-    ],
-    "Language": [
-        "Turkish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0284",
-    "MetadataAccess": [
-        "oai:ota:oucs:0284"
-    ],
-    "PublicationTimestamp": "1957-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1957"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Fiction"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Makal, Mahmut"
-    ],
-    "fulltext": "oai:ota:oucs:0284;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0284.xml;Kuru Sevda / Mahmut Makal;Makal, Mahmut;1957;text_and_corpus_linguistics;Turkish fiction;tur;Oxford Text Archive, University of Oxford;Jones, Alan;(1 file : ca. 287 KB);Text;Fiction;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "aaf17e7e-a8b7-5b04-b7a4-b9369c0eae91",
-    "oai_identifier": [
-        "oai:ota:oucs:0284"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Turkish fiction"
-        }
-    ],
-    "title": [
-        "Kuru Sevda / Mahmut Makal"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0284.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/aaff3513-33d9-5a8d-9656-4806c73151c2.json b/oaitestdata/clarin-oai_dc/SET_1/json/aaff3513-33d9-5a8d-9656-4806c73151c2.json
deleted file mode 100644
index f51e56a7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/aaff3513-33d9-5a8d-9656-4806c73151c2.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4673",
-    "MetadataAccess": [
-        "oai:ota:oucs:4673"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hume, David, 1711-1776."
-    ],
-    "fulltext": "oai:ota:oucs:4673;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4673.xml;The history of England: from the invasion of Julius C\u00c3\u00a6sar to the accession of Henry VII. ... By David Hume, Esq. [pt.1];Hume, David, 1711-1776.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "aaff3513-33d9-5a8d-9656-4806c73151c2",
-    "oai_identifier": [
-        "oai:ota:oucs:4673"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The history of England: from the invasion of Julius C\u00c3\u00a6sar to the accession of Henry VII. ... By David Hume, Esq. [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4673.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ab07fad0-6634-5cde-9041-8825731ea1bb.json b/oaitestdata/clarin-oai_dc/SET_1/json/ab07fad0-6634-5cde-9041-8825731ea1bb.json
deleted file mode 100644
index 0fdff503..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ab07fad0-6634-5cde-9041-8825731ea1bb.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain",
-        "(1 file : ca. 201 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1891",
-    "MetadataAccess": [
-        "oai:ota:oucs:1891"
-    ],
-    "PublicationTimestamp": "1762-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1762"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Letters",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Montagu, Mary Wortley, Lady, 1689-1762"
-    ],
-    "fulltext": "oai:ota:oucs:1891;2018-05-01T12:53:43Z;http://ota.ox.ac.uk/headers/1891.xml;Prose and poetry of Lady Mary Wortley Montagu / transcribed by Richard Bear;Montagu, Mary Wortley, Lady, 1689-1762;1762;text_and_corpus_linguistics;Letters -- Great Britain -- 18th century;Poems -- Great Britain -- 18th century;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 201 KB);Text;Letters;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ab07fad0-6634-5cde-9041-8825731ea1bb",
-    "oai_identifier": [
-        "oai:ota:oucs:1891"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Letters -- Great Britain -- th century"
-        },
-        {
-            "name": "Poems -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Prose and poetry of Lady Mary Wortley Montagu / transcribed by Richard Bear"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1891.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ab1cd241-361d-5f39-9752-f6df6d1f2667.json b/oaitestdata/clarin-oai_dc/SET_1/json/ab1cd241-361d-5f39-9752-f6df6d1f2667.json
deleted file mode 100644
index 40b26e60..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ab1cd241-361d-5f39-9752-f6df6d1f2667.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=380fbc4ed02211e1a404080027e73ea2c172bb3ddedc497d8b9c418331a0bf3f",
-    "MetadataAccess": [
-        "380fbc4ed02211e1a404080027e73ea2c172bb3ddedc497d8b9c418331a0bf3f"
-    ],
-    "PublicationTimestamp": "2015-12-10T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "380fbc4ed02211e1a404080027e73ea2c172bb3ddedc497d8b9c418331a0bf3f;2018-11-15T16:39:20Z;toolService;toolService:tool;TinySVM: Support Vector Machines.;TinySVM is an implementation of Support Vector Machines (SVMs) (Vapnik, 1995; Vapnik, 1998) for the problem of pattern recognition. ;2015-12-10",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ab1cd241-361d-5f39-9752-f6df6d1f2667",
-    "notes": [
-        "TinySVM is an implementation of Support Vector Machines (SVMs) (Vapnik, 1995; Vapnik, 1998) for the problem of pattern recognition. "
-    ],
-    "oai_identifier": [
-        "380fbc4ed02211e1a404080027e73ea2c172bb3ddedc497d8b9c418331a0bf3f"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "TinySVM: Support Vector Machines."
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ab24a097-ad7b-522c-94b4-206b3d6126e8.json b/oaitestdata/clarin-oai_dc/SET_1/json/ab24a097-ad7b-522c-94b4-206b3d6126e8.json
deleted file mode 100644
index 37986143..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ab24a097-ad7b-522c-94b4-206b3d6126e8.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Linguistic Modeling Department, IPP, Bulgarian Academy of Sciences"
-    ],
-    "Contributor": [
-        "Simov, Kiril"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1239",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1239"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1239",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Linguistic Modeling Department, IPP, Bulgarian Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Bulgaria"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Simov, Alex",
-        "Kouylekov, Milen",
-        "Simov, Kiril"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1239;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;CLaRK System - XML-based system for Corpora Development;Simov, Kiril;Simov, Alex;Kouylekov, Milen;Simov, Kiril;The CLaRK System incorporates several technologies:\n- XML technology\n- Unicode\n- Cascaded Regular Grammars;\n- Constraints over XML Documents\nOn the basis of these technologies the following tools are implemented: XML Editor, Unicode Tokeniser, Sorting tool, Removing and Extracting tool, Concordancer, XSLT tool,\nCascaded Regular Grammar tool, etc.\n1 Unicode tokenization\nIn order to provide possibility for imposing constraints over the textual node and to segment them in meaningful way, the CLaRK System supports a user-defined hierarchy of tokenisers. At the very basic level the user can define a tokeniser in terms of a set of token types. In this basic tokeniser each token type is defined by a set of UNICODE symbols. Above this basic level tokenisers, the user can define other tokenisers, for which the token types are defined as regular expressions over the tokens of some other tokeniser, the so called parent tokeniser.\n2 Regular Grammars\nThe regular grammars are the basic mechanism for linguistic processing of the content of an XML document within the system. The regular grammar processor applies a set of rules over the content of some elements in the document and incorporates the categories of the rules back in the document as XML mark-up. The content is processed before the application of the grammar rules in the following way: textual nodes are tokenized with respect to some appropriate tokeniser, the element nodes are textualized on the basis of XPath expressions that determine the important information about the element. The recognized word is substituted by a new XML mark-up, which can or can not contain the word. \n3 Constraints\nThe constraints that we implemented in the CLaRK System are generally based on the XPath language. We use XPath expressions to determine some data within one or several XML\ndocuments and thus we evaluate some predicates over the data. There are two modes of using a constraint. In the first mode the constraint is used for validity check, similar to the validity check, which is based on DTD or XML schema. In the second mode, the constraint is used to\nsupport the change of the document in order it to satisfy the constraint.  There are three types of constraints, implemented in the system: regular expression constraints, number restriction constraints, value restriction constraints.\n4 Macro Language\nIn the CLaRK System the tools support a mechanism for describing their settings. On the basis of these descriptions (called queries) a tool can be applied only by pointing to a certain description record. Each query contains the states of all settings and options which the\ncorresponding tool has. Once having this kind of queries there is a special tool for combining and applying them in groups (macros). During application the queries are executed successively and the result from an application is an input for the next one.\nFor a better control on the process of applying several queries in one we introduce several conditional operators. These operators can determine the next query for application depending on certain conditions. When a condition for such an operator is satisfied, the execution continues from a location defined in the operator. The mechanism for addressing queries is based on user defined labels. When a condition is not satisfied the operator is ignored and the process continues from the position following the operator. In this way constructions like IF-THEN-ELSE and WHILE-DO easily can be expressed.\nThe system supports five types of control operators:\nIF (XPath): the condition is an XPath expression which is evaluated on the current working document. If the result is a non-empty node-set, non-empty string, positive number or\ntrue boolean value the condition is satisfied;\nIF NOT (XPath): the same kind of condition as the previous one but the approving result is negated;\nIF CHANGED: the condition is satisfied if the preceding operation has changed the current working document or has produced a non-empty result document (depending on the operation);\nIF NOT CHANGED: the condition is satisfied if either the previous operation did not change the working document or did not produce a non-empty result.\nGOTO: unconditional changing the execution position.\nEach macro defined in the system can have its own query and can be incorporated in another macro. In this way some limited form of subroutine can be implemented.\nThe new version of CLaRK will support server applications, calls to/from external programs.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1239;downloadable_files_count: 0;Bulgaria;Linguistic Modeling Department, IPP, Bulgarian Academy of Sciences;http://www.bultreebank.org/clark/index.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ab24a097-ad7b-522c-94b4-206b3d6126e8",
-    "notes": [
-        "The CLaRK System incorporates several technologies:\n- XML technology\n- Unicode\n- Cascaded Regular Grammars;\n- Constraints over XML Documents\nOn the basis of these technologies the following tools are implemented: XML Editor, Unicode Tokeniser, Sorting tool, Removing and Extracting tool, Concordancer, XSLT tool,\nCascaded Regular Grammar tool, etc.\n1 Unicode tokenization\nIn order to provide possibility for imposing constraints over the textual node and to segment them in meaningful way, the CLaRK System supports a user-defined hierarchy of tokenisers. At the very basic level the user can define a tokeniser in terms of a set of token types. In this basic tokeniser each token type is defined by a set of UNICODE symbols. Above this basic level tokenisers, the user can define other tokenisers, for which the token types are defined as regular expressions over the tokens of some other tokeniser, the so called parent tokeniser.\n2 Regular Grammars\nThe regular grammars are the basic mechanism for linguistic processing of the content of an XML document within the system. The regular grammar processor applies a set of rules over the content of some elements in the document and incorporates the categories of the rules back in the document as XML mark-up. The content is processed before the application of the grammar rules in the following way: textual nodes are tokenized with respect to some appropriate tokeniser, the element nodes are textualized on the basis of XPath expressions that determine the important information about the element. The recognized word is substituted by a new XML mark-up, which can or can not contain the word. \n3 Constraints\nThe constraints that we implemented in the CLaRK System are generally based on the XPath language. We use XPath expressions to determine some data within one or several XML\ndocuments and thus we evaluate some predicates over the data. There are two modes of using a constraint. In the first mode the constraint is used for validity check, similar to the validity check, which is based on DTD or XML schema. In the second mode, the constraint is used to\nsupport the change of the document in order it to satisfy the constraint.  There are three types of constraints, implemented in the system: regular expression constraints, number restriction constraints, value restriction constraints.\n4 Macro Language\nIn the CLaRK System the tools support a mechanism for describing their settings. On the basis of these descriptions (called queries) a tool can be applied only by pointing to a certain description record. Each query contains the states of all settings and options which the\ncorresponding tool has. Once having this kind of queries there is a special tool for combining and applying them in groups (macros). During application the queries are executed successively and the result from an application is an input for the next one.\nFor a better control on the process of applying several queries in one we introduce several conditional operators. These operators can determine the next query for application depending on certain conditions. When a condition for such an operator is satisfied, the execution continues from a location defined in the operator. The mechanism for addressing queries is based on user defined labels. When a condition is not satisfied the operator is ignored and the process continues from the position following the operator. In this way constructions like IF-THEN-ELSE and WHILE-DO easily can be expressed.\nThe system supports five types of control operators:\nIF (XPath): the condition is an XPath expression which is evaluated on the current working document. If the result is a non-empty node-set, non-empty string, positive number or\ntrue boolean value the condition is satisfied;\nIF NOT (XPath): the same kind of condition as the previous one but the approving result is negated;\nIF CHANGED: the condition is satisfied if the preceding operation has changed the current working document or has produced a non-empty result document (depending on the operation);\nIF NOT CHANGED: the condition is satisfied if either the previous operation did not change the working document or did not produce a non-empty result.\nGOTO: unconditional changing the execution position.\nEach macro defined in the system can have its own query and can be incorporated in another macro. In this way some limited form of subroutine can be implemented.\nThe new version of CLaRK will support server applications, calls to/from external programs."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1239"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "CLaRK System - XML-based system for Corpora Development"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ab4f9e79-5eed-5d6e-b422-2af77eb43302.json b/oaitestdata/clarin-oai_dc/SET_1/json/ab4f9e79-5eed-5d6e-b422-2af77eb43302.json
deleted file mode 100644
index 264a68df..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ab4f9e79-5eed-5d6e-b422-2af77eb43302.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Budapest University of Technology and Economics Media Research (BME MOKK)"
-    ],
-    "Contributor": [
-        "Hal\u00e1csy, P\u00e9ter",
-        "Oravecz, Csaba",
-        "Kornai, Andr\u00e1s"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1205",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1205"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1205",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Budapest University of Technology and Economics Media Research (BME MOKK)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Hungary"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1205;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;hunpos - a POS tagger;Hal\u00e1csy, P\u00e9ter;Kornai, Andr\u00e1s;Oravecz, Csaba;Hunpos is an open source reimplementation of TnT, the well known part-of-speech tagger by Thorsten Brants.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1205;downloadable_files_count: 0;Hungary;Budapest University of Technology and Economics Media Research (BME MOKK);http://code.google.com/p/hunpos/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ab4f9e79-5eed-5d6e-b422-2af77eb43302",
-    "notes": [
-        "Hunpos is an open source reimplementation of TnT, the well known part-of-speech tagger by Thorsten Brants."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1205"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "hunpos - a POS tagger"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ab61b89d-6e8c-528d-a8c5-2770a157b83f.json b/oaitestdata/clarin-oai_dc/SET_1/json/ab61b89d-6e8c-528d-a8c5-2770a157b83f.json
deleted file mode 100644
index f5f2dd3d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ab61b89d-6e8c-528d-a8c5-2770a157b83f.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 6",
-        "application/gzip"
-    ],
-    "Language": [
-        "Japanese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1047",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1047"
-    ],
-    "PID": "http://hdl.handle.net/11356/1047",
-    "PublicationTimestamp": "2008-11-14T11:59:59Z",
-    "PublicationYear": [
-        "2008"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by-sa/4.0/"
-    ],
-    "author": [
-        "Hmeljak Sangawa, Kristina",
-        "Erjavec, Toma\u017e",
-        "Kawamura, Yoshiko"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1047;2018-10-24T20:49:06Z;hdl_11356_1023;hdl_11356_1024;Japanese web corpus with difficulty levels jpWaC-L 1.0;Erjavec, Toma\u017e;Hmeljak Sangawa, Kristina;Kawamura, Yoshiko;difficulty level;teaching corpus;TEI;The corpus contains over 300 million words, with annotations of words and sentences describing their difficulty levels. Words are assigned levels of difficulty according to the Japanese Language Proficiency Test Content Specifications (2004). The difficulty level of the sentences is computed using various heuristics, based on the (difficulty level of) words, sentence length, etc. The corpus was collected from the Web using WaCkY tools, part-of-speech tagged and lemmatised with Chasen. The Japanese Chasen tags have also been converted to English language based tags.\r\n\r\nThe corpora are made available in vertical format. Structural attributes are <text> and <s> (sentence). Each text gives its @url and @domain. Sentences have the @level attribute, which describes their difficulty level. The positional attributes are: \r\n1. token, as it appears in the text\r\n2. lemma of the word\r\n3. Chasen tag, translated to English\r\n4. original Chasen tag in Japanese\r\n5. difficulty level of the word.\r\n\r\nThe complete corpus is also split into sub-corpora of sentences with the same difficulty level.;2008-11-14;corpus;http://hdl.handle.net/11356/1047;jpn;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);PUB;https://creativecommons.org/licenses/by-sa/4.0/;text/plain; charset=utf-8;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;downloadable_files_count: 6;Jo\u017eef Stefan Institute;http://nl.ijs.si/jaslo/index-en.html#jpwac",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ab61b89d-6e8c-528d-a8c5-2770a157b83f",
-    "notes": [
-        "The corpus contains over 300 million words, with annotations of words and sentences describing their difficulty levels. Words are assigned levels of difficulty according to the Japanese Language Proficiency Test Content Specifications (2004). The difficulty level of the sentences is computed using various heuristics, based on the (difficulty level of) words, sentence length, etc. The corpus was collected from the Web using WaCkY tools, part-of-speech tagged and lemmatised with Chasen. The Japanese Chasen tags have also been converted to English language based tags.\r\n\r\nThe corpora are made available in vertical format. Structural attributes are <text> and <s> (sentence). Each text gives its @url and @domain. Sentences have the @level attribute, which describes their difficulty level. The positional attributes are: \r\n1. token, as it appears in the text\r\n2. lemma of the word\r\n3. Chasen tag, translated to English\r\n4. original Chasen tag in Japanese\r\n5. difficulty level of the word.\r\n\r\nThe complete corpus is also split into sub-corpora of sentences with the same difficulty level."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1047"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "difficulty level"
-        },
-        {
-            "name": "teaching corpus"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "Japanese web corpus with difficulty levels jpWaC-L 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ab6b7a25-78c4-5d18-a6da-2660b1955d7b.json b/oaitestdata/clarin-oai_dc/SET_1/json/ab6b7a25-78c4-5d18-a6da-2660b1955d7b.json
deleted file mode 100644
index 8e3b54f4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ab6b7a25-78c4-5d18-a6da-2660b1955d7b.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2922",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2922"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2922",
-    "PublicationTimestamp": "2019-01-21T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "BSD 2-Clause \"Simplified\" or \"FreeBSD\" license",
-        "http://opensource.org/licenses/BSD-2-Clause",
-        "PUB"
-    ],
-    "author": [
-        "Vari\u0161, Du\u0161an",
-        "Popel, Martin",
-        "Ko\u0161arko, Ond\u0159ej"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2922;2019-01-25T11:42:13Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;LINDAT Translation service;Ko\u0161arko, Ond\u0159ej;Vari\u0161, Du\u0161an;Popel, Martin;machine translation;frontend;Source code of the LINDAT Translation service frontend. The service provides a UI and a simple rest api that accesses machine translation models served by tensorflow serving.\r\n\r\nThe most recent version of the code is available at https://github.com/ufal/lindat_translation.;2019-01-21;toolService;http://hdl.handle.net/11234/1-2922;BSD 2-Clause \"Simplified\" or \"FreeBSD\" license;http://opensource.org/licenses/BSD-2-Clause;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ab6b7a25-78c4-5d18-a6da-2660b1955d7b",
-    "notes": [
-        "Source code of the LINDAT Translation service frontend. The service provides a UI and a simple rest api that accesses machine translation models served by tensorflow serving.\r\n\r\nThe most recent version of the code is available at https://github.com/ufal/lindat_translation."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2922"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "frontend"
-        }
-    ],
-    "title": [
-        "LINDAT Translation service"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ab75df7d-ab60-5296-8794-86779434202e.json b/oaitestdata/clarin-oai_dc/SET_1/json/ab75df7d-ab60-5296-8794-86779434202e.json
deleted file mode 100644
index 11739e0a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ab75df7d-ab60-5296-8794-86779434202e.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "Contact": [
-        "Summer Institute of Linguistics (SIL), Inc"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-301",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-301"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-301",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Summer Institute of Linguistics (SIL), Inc"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-301;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;SIL FieldWorks;corpus management;FieldWorks consists of software tools that help you manage linguistic and cultural data. FieldWorks supports tasks ranging from the initial entry of collected data through to the preparation of data for publication:  * dictionary development  * interlinearization of texts  * cultural records, which can be categorized using the Outline of Cultural Materials  * bulk editing of many fields  * morphological analysis  * complex non-Roman scripts using Unicode and SIL-developed Graphite  * multi-user editing capability over a local area network.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-301;downloadable_files_count: 0;Summer Institute of Linguistics (SIL), Inc;http://fieldworks.sil.org/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ab75df7d-ab60-5296-8794-86779434202e",
-    "notes": [
-        "FieldWorks consists of software tools that help you manage linguistic and cultural data. FieldWorks supports tasks ranging from the initial entry of collected data through to the preparation of data for publication:  * dictionary development  * interlinearization of texts  * cultural records, which can be categorized using the Outline of Cultural Materials  * bulk editing of many fields  * morphological analysis  * complex non-Roman scripts using Unicode and SIL-developed Graphite  * multi-user editing capability over a local area network."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-301"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus management"
-        }
-    ],
-    "title": [
-        "SIL FieldWorks"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/abaf7cbf-8a63-5d3c-a61b-e2f437db8caa.json b/oaitestdata/clarin-oai_dc/SET_1/json/abaf7cbf-8a63-5d3c-a61b-e2f437db8caa.json
deleted file mode 100644
index b6e20fb1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/abaf7cbf-8a63-5d3c-a61b-e2f437db8caa.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 28.5 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1339",
-    "MetadataAccess": [
-        "oai:ota:oucs:1339"
-    ],
-    "PublicationTimestamp": "1538-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1538"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Bale, John, 1495-1563"
-    ],
-    "fulltext": "oai:ota:oucs:1339;2018-04-26T12:45:55Z;http://ota.ox.ac.uk/headers/1339.xml;A brefe comedy or enterlude concernynge the temptacyon of our lorde and sauer Jesus Christ by Sathan in the desart / compyled by Johan Bale;Bale, John, 1495-1563;1538;text_and_corpus_linguistics;Plays -- England -- 16th century;Comedies -- England -- 16th century;eng;Oxford Text Archive, University of Oxford;(1 file : ca. 28.5 KB);Text;Plays;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "abaf7cbf-8a63-5d3c-a61b-e2f437db8caa",
-    "oai_identifier": [
-        "oai:ota:oucs:1339"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        },
-        {
-            "name": "Comedies -- England -- th century"
-        }
-    ],
-    "title": [
-        "A brefe comedy or enterlude concernynge the temptacyon of our lorde and sauer Jesus Christ by Sathan in the desart / compyled by Johan Bale"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1339.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/abc9e916-09ef-5388-8a35-5b613edeef48.json b/oaitestdata/clarin-oai_dc/SET_1/json/abc9e916-09ef-5388-8a35-5b613edeef48.json
deleted file mode 100644
index bc9eb9ed..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/abc9e916-09ef-5388-8a35-5b613edeef48.json
+++ /dev/null
@@ -1,49 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5362",
-    "MetadataAccess": [
-        "oai:ota:oucs:5362"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:5362;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5362.xml;The poetical calendar: Containing a collection of scarce and valuable pieces of poetry: ... by the most eminent hands. Intended as a supplement to Mr. Dodsley's collection. Written and selected by Francis Fawkes, M. A. and William Woty. In twelve volumes. [pt.4];text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "abc9e916-09ef-5388-8a35-5b613edeef48",
-    "oai_identifier": [
-        "oai:ota:oucs:5362"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The poetical calendar: Containing a collection of scarce and valuable pieces of poetry: ... by the most eminent hands. Intended as a supplement to Mr. Dodsley's collection. Written and selected by Francis Fawkes, M. A. and William Woty. In twelve volumes. [pt.4]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5362.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/abd3d971-93a1-5525-a666-7c10bc4a2150.json b/oaitestdata/clarin-oai_dc/SET_1/json/abd3d971-93a1-5525-a666-7c10bc4a2150.json
deleted file mode 100644
index 00f1155d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/abd3d971-93a1-5525-a666-7c10bc4a2150.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "[S. n.]"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-517",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-517"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D1F-A",
-    "PublicationTimestamp": "1674-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1674"
-    ],
-    "Publisher": [
-        "[S. n.]"
-    ],
-    "RelatedIdentifier": [
-        "http://pbc.biaman.pl/Content/517"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-517;2019-03-01T15:33:42Z;Porz\u0105dek Na Seymie Walnym Elekcyey Mi\u0119dzy Warszaw\u0105 a Wol\u0105, przez opisane Artyku\u0142y do samego tylko Aktu Elekcyey nale\u017c\u0105ce, uchwalony y postanowiony, Roku Pa\u0144skiego Tysi\u0105c Szesc Set Siedmdziesiat Czwartego, dnia Dwudziestego Miesiaca Kwietnia.;Parlamenty;Polska 17 w.;ilo\u015b\u0107 skan\u00f3w: 34 ; sygn: St - 352;[S. n.];1674;starodruk;application/xml;clarind-uds:poldilemma-517;hdl:11858/00-246C-0000-0023-8D1F-A;pol;lat;http://pbc.biaman.pl/Content/517;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "abd3d971-93a1-5525-a666-7c10bc4a2150",
-    "notes": [
-        "ilo\u015b\u0107 skan\u00f3w: 34 ; sygn: St - 352"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-517"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Parlamenty"
-        },
-        {
-            "name": "Polska w."
-        }
-    ],
-    "title": [
-        "Porz\u0105dek Na Seymie Walnym Elekcyey Mi\u0119dzy Warszaw\u0105 a Wol\u0105, przez opisane Artyku\u0142y do samego tylko Aktu Elekcyey nale\u017c\u0105ce, uchwalony y postanowiony, Roku Pa\u0144skiego Tysi\u0105c Szesc Set Siedmdziesiat Czwartego, dnia Dwudziestego Miesiaca Kwietnia."
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/abeee12d-2932-5e59-a4e5-fd0ea043e2b3.json b/oaitestdata/clarin-oai_dc/SET_1/json/abeee12d-2932-5e59-a4e5-fd0ea043e2b3.json
deleted file mode 100644
index 814be58a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/abeee12d-2932-5e59-a4e5-fd0ea043e2b3.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contributor": [
-        "SALSA Project Saarbr\u00fccken"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:salto",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:salto"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0005-BD14-0",
-    "PublicationTimestamp": "2007-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2007"
-    ],
-    "RelatedIdentifier": [
-        "SALSA",
-        "clarind-uds:salsa",
-        "Documentation of SALTO http://www.coli.uni-saarland.de/projects/salsa/salto/doc/html/",
-        "A. Burchardt, K. Erk, A. Frank, A. Kowalski and S. Pad\u00f3. SALTO \u2013 A Versatile Multi-Level Annotation Tool. Proceedings of LREC 2006, Genoa, Italy. http://www.coli.uni-saarland.de/projects/salsa/papers/lrec06-tool.pdf",
-        "SALSA/TIGER XML: http://www.nlpado.de/~sebastian/pub/papers/lrec04_erk.pdf"
-    ],
-    "ResourceType": [
-        "Software"
-    ],
-    "Rights": [
-        "Copyrighted, License: http://www.coli.uni-saarland.de/projects/salsa/salto/doc/license.html"
-    ],
-    "author": [
-        "Manfred Pinkal\nUniversit\u00e4t des Saarlandes\nFachrichtung 4.7 Allgemeine Linguistik\nPostfach 15 11 50\n66041 Saarbr\u00fccken, Germany"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:salto;2014-06-03T12:55:04Z;SALTO - SALSA Tool;Manfred Pinkal\nUniversit\u00e4t des Saarlandes\nFachrichtung 4.7 Allgemeine Linguistik\nPostfach 15 11 50\n66041 Saarbr\u00fccken, Germany;annotation tool;annotation management;semantic roles;semantic classes;tag set definition;Salto is a graphical tool for manual annotation of text corpora. It supports the annotation of a second (typically semantic) layer of annotation to an existing syntactic annotation. Originally it was used in the SALSA project for the annotation of semantic roles and semantic classes (FrameNet).The main features are: selecting data sets for annotation (query-based); tag set definition; distribution of corpora to annotators; inter-annotator agreement; and quality control.;SALTO is ein graphisches Werkzeug f\u00fcr die manuelle Annotation von Textkorpora. Es unterst\u00fctzt die Annotation einer zweiten Annotationsebene (z.B. einer semantischen) auf einer existierenden syntaktischen Annotationsebene. Im SALSA Projekt entwickelt, wurde es dazu benutzt semantische Rollen und Klassen (FrameNet) zu annotieren. Die Hauptfeatures sind: die Auswahl eines Datensatzes f\u00fcr die Annotation (Anfrage gest\u00fctzt); Definition von Annotationsschemata; Verteilung von Korpora auf Annotatoren; \u00dcbereinstimmung zwischen den Annotatoren; Qualit\u00e4tskontrolle.;SALSA Project Saarbr\u00fccken;2007;Software;clarind-uds:salto;hdl:11858/00-246C-0000-0005-BD14-0;deu;SALSA;clarind-uds:salsa;Documentation of SALTO http://www.coli.uni-saarland.de/projects/salsa/salto/doc/html/;A. Burchardt, K. Erk, A. Frank, A. Kowalski and S. Pad\u00f3. SALTO \u2013 A Versatile Multi-Level Annotation Tool. Proceedings of LREC 2006, Genoa, Italy. http://www.coli.uni-saarland.de/projects/salsa/papers/lrec06-tool.pdf;SALSA/TIGER XML: http://www.nlpado.de/~sebastian/pub/papers/lrec04_erk.pdf;Copyrighted, License: http://www.coli.uni-saarland.de/projects/salsa/salto/doc/license.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "abeee12d-2932-5e59-a4e5-fd0ea043e2b3",
-    "notes": [
-        "Salto is a graphical tool for manual annotation of text corpora. It supports the annotation of a second (typically semantic) layer of annotation to an existing syntactic annotation. Originally it was used in the SALSA project for the annotation of semantic roles and semantic classes (FrameNet).The main features are: selecting data sets for annotation (query-based); tag set definition; distribution of corpora to annotators; inter-annotator agreement; and quality control.",
-        "SALTO is ein graphisches Werkzeug f\u00fcr die manuelle Annotation von Textkorpora. Es unterst\u00fctzt die Annotation einer zweiten Annotationsebene (z.B. einer semantischen) auf einer existierenden syntaktischen Annotationsebene. Im SALSA Projekt entwickelt, wurde es dazu benutzt semantische Rollen und Klassen (FrameNet) zu annotieren. Die Hauptfeatures sind: die Auswahl eines Datensatzes f\u00fcr die Annotation (Anfrage gest\u00fctzt); Definition von Annotationsschemata; Verteilung von Korpora auf Annotatoren; \u00dcbereinstimmung zwischen den Annotatoren; Qualit\u00e4tskontrolle."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:salto"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "annotation tool"
-        },
-        {
-            "name": "annotation management"
-        },
-        {
-            "name": "semantic roles"
-        },
-        {
-            "name": "semantic classes"
-        },
-        {
-            "name": "tag set definition"
-        }
-    ],
-    "title": [
-        "SALTO - SALSA Tool"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/abf057a7-7f54-5007-87a8-48607b4ea24e.json b/oaitestdata/clarin-oai_dc/SET_1/json/abf057a7-7f54-5007-87a8-48607b4ea24e.json
deleted file mode 100644
index 11efb6b7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/abf057a7-7f54-5007-87a8-48607b4ea24e.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Jan Wieczorek"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/richtext",
-        "downloadable_files_count: 2",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/422",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/422"
-    ],
-    "PID": "http://hdl.handle.net/11321/422",
-    "PublicationTimestamp": "2017-09-08T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Jan Wieczorek"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Wieczorek, Jan",
-        "Rakowska, Maria"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/422;2018-10-01T11:44:37Z;hdl_11321_3;hdl_11321_4;podr\u00f3\u017c do persyi test;Rakowska, Maria;Wieczorek, Jan;Wieczorek, Jan;podr\u00f3\u017ce;Test przed zamieszczeniem w\u0142a\u015bciwego korpusu;2017-09-08;corpus;http://hdl.handle.net/11321/422;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;text/richtext;application/zip;downloadable_files_count: 2;Jan Wieczorek",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "abf057a7-7f54-5007-87a8-48607b4ea24e",
-    "notes": [
-        "Test przed zamieszczeniem w\u0142a\u015bciwego korpusu"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/422"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [],
-    "title": [
-        "podr\u00f3\u017c do persyi test"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ac0baa70-3c46-5c5b-b480-557fe09975e5.json b/oaitestdata/clarin-oai_dc/SET_1/json/ac0baa70-3c46-5c5b-b480-557fe09975e5.json
deleted file mode 100644
index c262e569..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ac0baa70-3c46-5c5b-b480-557fe09975e5.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/10",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/10"
-    ],
-    "PID": "http://hdl.handle.net/11321/10",
-    "PublicationTimestamp": "2012-02-21T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "\u015aniatowski, Tomasz",
-        "Radziszewski, Adam"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/10;2016-01-21T14:24:10Z;hdl_11321_3;hdl_11321_4;Corpus2;Radziszewski, Adam;\u015aniatowski, Tomasz;Biblioteka programistyczna w j\u0119zyku C++ z opakowaniami pythonowymi. Czytanie i pisanie korpus\u00f3w, struktury danych. Manipulacja tagsetami i tagami. U\u0142atwia szybkie pisanie tager\u00f3w i innych aplikacji NLP.;2012-02-21;toolService;http://hdl.handle.net/11321/10;pol;downloadable_files_count: 0;Wroc\u0142aw University of Technology;http://nlp.pwr.wroc.pl/redmine/projects/corpus2/wiki",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ac0baa70-3c46-5c5b-b480-557fe09975e5",
-    "notes": [
-        "Biblioteka programistyczna w j\u0119zyku C++ z opakowaniami pythonowymi. Czytanie i pisanie korpus\u00f3w, struktury danych. Manipulacja tagsetami i tagami. U\u0142atwia szybkie pisanie tager\u00f3w i innych aplikacji NLP."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/10"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ac0eacd3-653f-599f-811e-7c6dd0976dcf.json b/oaitestdata/clarin-oai_dc/SET_1/json/ac0eacd3-653f-599f-811e-7c6dd0976dcf.json
deleted file mode 100644
index f822951f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ac0eacd3-653f-599f-811e-7c6dd0976dcf.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4103",
-    "MetadataAccess": [
-        "oai:ota:oucs:4103"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Smart, Christopher, 1722-1771."
-    ],
-    "fulltext": "oai:ota:oucs:4103;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4103.xml;Poems on several occasions: By Christopher Smart, ...;Smart, Christopher, 1722-1771.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ac0eacd3-653f-599f-811e-7c6dd0976dcf",
-    "oai_identifier": [
-        "oai:ota:oucs:4103"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Poems on several occasions: By Christopher Smart, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4103.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ac0f6abe-fdc0-514d-9b99-dbddb4af5ae0.json b/oaitestdata/clarin-oai_dc/SET_1/json/ac0f6abe-fdc0-514d-9b99-dbddb4af5ae0.json
deleted file mode 100644
index 7e67c890..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ac0f6abe-fdc0-514d-9b99-dbddb4af5ae0.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "UK Economic and Social Research Council (ESRC)",
-        "McEnery, A.M.",
-        "Xiao, Richard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml",
-        "30 files : ca. 42.8 MB"
-    ],
-    "Language": [],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2474",
-    "MetadataAccess": [
-        "oai:ota:oucs:2474"
-    ],
-    "PublicationTimestamp": "2004-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2004"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Linguistic corpora"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:2474;2018-02-21T11:45:11Z;http://ota.ox.ac.uk/headers/2474.xml;The Lancaster Corpus of Mandarin Chinese;2004;text_and_corpus_linguistics;Componential analysis (Linguistics);Linguistic analysis (Linguistics);Chinese language--Modern Chinese, 1919-;cmn;The Lancaster Corpus of Mandarin Chinese (LCMC) is designed as a Chinese match for the FLOB and FROWN corpora for modern British and American English. The corpus is suitable for use in both monolingual research into modern Mandarin Chinese and cross-linguistic contrast of Chinese and British/American English. The corpus sampled 15 written text categories including news, literary texts, academic prose and official documents etc published in P.R.China in the early 1990s. The same sampling frame and period as FLOB/FROWN were used in LCMC. The corpus is encoded in Unicode (UTF-8) and marked up in XML. ;Oxford Text Archive, University of Oxford;McEnery, A.M.;Xiao, Richard;UK Economic and Social Research Council (ESRC);McEnery, A.M.;text/xml;30 files : ca. 42.8 MB;Text;Linguistic corpora;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ac0f6abe-fdc0-514d-9b99-dbddb4af5ae0",
-    "notes": [
-        "The Lancaster Corpus of Mandarin Chinese (LCMC) is designed as a Chinese match for the FLOB and FROWN corpora for modern British and American English. The corpus is suitable for use in both monolingual research into modern Mandarin Chinese and cross-linguistic contrast of Chinese and British/American English. The corpus sampled 15 written text categories including news, literary texts, academic prose and official documents etc published in P.R.China in the early 1990s. The same sampling frame and period as FLOB/FROWN were used in LCMC. The corpus is encoded in Unicode (UTF-8) and marked up in XML. "
-    ],
-    "oai_identifier": [
-        "oai:ota:oucs:2474"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Componential analysis Linguistics"
-        },
-        {
-            "name": "Linguistic analysis Linguistics"
-        },
-        {
-            "name": "Chinese language--Modern Chinese"
-        }
-    ],
-    "title": [
-        "The Lancaster Corpus of Mandarin Chinese"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2474.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ac1e700c-82fb-5877-a49e-8d9a28c452f5.json b/oaitestdata/clarin-oai_dc/SET_1/json/ac1e700c-82fb-5877-a49e-8d9a28c452f5.json
deleted file mode 100644
index abdf619f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ac1e700c-82fb-5877-a49e-8d9a28c452f5.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5135",
-    "MetadataAccess": [
-        "oai:ota:oucs:5135"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Brown, John, 1722-1787."
-    ],
-    "fulltext": "oai:ota:oucs:5135;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5135.xml;A compendious history of the British churches in England, Scotland, Ireland, and America. By John Brown.: [pt.1];Brown, John, 1722-1787.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ac1e700c-82fb-5877-a49e-8d9a28c452f5",
-    "oai_identifier": [
-        "oai:ota:oucs:5135"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A compendious history of the British churches in England, Scotland, Ireland, and America. By John Brown.: [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5135.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ac5a3c53-04b0-54ab-8b80-add1a79b1f97.json b/oaitestdata/clarin-oai_dc/SET_1/json/ac5a3c53-04b0-54ab-8b80-add1a79b1f97.json
deleted file mode 100644
index a4bb5c3a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ac5a3c53-04b0-54ab-8b80-add1a79b1f97.json
+++ /dev/null
@@ -1,253 +0,0 @@
-{
-    "Contact": [
-        "Universal Dependencies Consortium"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 4"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)",
-        "Arabic",
-        "Basque",
-        "Bulgarian",
-        "Croatian",
-        "Czech",
-        "Danish",
-        "Dutch",
-        "English",
-        "Estonian",
-        "Finnish",
-        "French",
-        "German",
-        "Gothic",
-        "Modern Greek (1453-)",
-        "Hebrew",
-        "Hindi",
-        "Hungarian",
-        "Indonesian",
-        "Irish",
-        "Italian",
-        "Japanese",
-        "Latin",
-        "Norwegian",
-        "Church Slavic",
-        "Persian",
-        "Polish",
-        "Portuguese",
-        "Romanian",
-        "Slovenian",
-        "Spanish",
-        "Swedish",
-        "Tamil",
-        "Catalan",
-        "Chinese",
-        "Galician",
-        "Kazakh",
-        "Latvian",
-        "Russian",
-        "Turkish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1699",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1699"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1699",
-    "PublicationTimestamp": "2016-05-15T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Universal Dependencies Consortium"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-1548",
-        "http://hdl.handle.net/11234/1-1827"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Licence Universal Dependencies v1.3",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-1.3",
-        "PUB"
-    ],
-    "author": [
-        "Ion, Radu",
-        "Seraji, Mojgan",
-        "Manning, Christopher",
-        "Cebiro\u011flu Eryi\u011fit, G\u00fcl\u015fen",
-        "Passarotti, Marco",
-        "Zhu, Hanzhi",
-        "Osenova, Petya",
-        "Agi\u0107, \u017deljko",
-        "Simionescu, Radu",
-        "Muischnek, Kadri",
-        "Washington, Jonathan North",
-        "Montemagni, Simonetta",
-        "Wang, Jing Xian",
-        "Seeker, Wolfgang",
-        "Berzak, Yevgeni",
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "Irimia, Elena",
-        "Simk\u00f3, Katalin",
-        "Hladk\u00e1, Barbora",
-        "Krek, Simon",
-        "Suhr, Alane",
-        "Galbraith, Daniel",
-        "Lenci, Alessandro",
-        "Mititelu, Verginica",
-        "Gokirmak, Memduh",
-        "Erjavec, Toma\u017e",
-        "Mart\u00ednez Alonso, H\u00e9ctor",
-        "Schuster, Sebastian",
-        "Haug, Dag",
-        "Lynn, Teresa",
-        "Plank, Barbara",
-        "Gojenola, Koldo",
-        "Varga, Viktor",
-        "Lyashevskaya, Olga",
-        "M\u0103r\u0103nduc, C\u0103t\u0103lina",
-        "Ka\u015f\u0131kara, H\u00fcner",
-        "Pyysalo, Sampo",
-        "Kanerva, Jenna",
-        "Sz\u00e1nt\u00f3, Zsolt",
-        "Haji\u010d, Jan",
-        "Ma\u0161ek, Jan",
-        "Atutxa, Aitziber",
-        "Goldberg, Yoav",
-        "Matsumoto, Yuji",
-        "Dozat, Timothy",
-        "G\u00f3mez Guinovart, Xavier",
-        "M\u00fc\u00fcrisep, Kaili",
-        "Saul\u012bte, Baiba",
-        "Bauer, John",
-        "Piitulainen, Jussi",
-        "Nivre, Joakim",
-        "Prokopidis, Prokopis",
-        "Petrov, Slav",
-        "Guillaume, Bruno",
-        "Gr\u016bz\u012btis, Normunds",
-        "Puolakainen, Tiina",
-        "de Marneffe, Marie-Catherine",
-        "Missil\u00e4, Anna",
-        "Perez, Cenel-Augusto",
-        "Katz, Boris",
-        "Makazhanov, Aibek",
-        "McDonald, Ryan",
-        "Lam, Lucia",
-        "Pretkalni\u0146a, Lauma",
-        "Farkas, Rich\u00e1rd",
-        "Ramasamy, Loganathan",
-        "Bosco, Cristina",
-        "Kenney, Jessica",
-        "Ginter, Filip",
-        "Mori, Shunsuke",
-        "Sulubacak, Umut",
-        "Asahara, Masayuki",
-        "Mori, Keiko Sophie",
-        "Zeman, Daniel",
-        "Tanaka, Takaaki",
-        "Miyao, Yusuke",
-        "Vincze, Veronika",
-        "Bhat, Riyaz Ahmad",
-        "Mustafina, Nina",
-        "Tsarfaty, Reut",
-        "Goenaga, Iakes",
-        "Rituma, Laura",
-        "Garza, Sebastian",
-        "Johannsen, Anders",
-        "Droganova, Kira",
-        "Shen, Mo",
-        "Connor, Miriam",
-        "Mare\u010dek, David",
-        "Smith, Aaron",
-        "\u00d8vrelid, Lilja",
-        "Spadine, Carolyn",
-        "Celano, Giuseppe G. A.",
-        "Dobrovoljc, Kaja",
-        "Popel, Martin",
-        "Laippala, Veronika",
-        "Simov, Kiril",
-        "Ballesteros, Miguel",
-        "Nurmi, Hanna",
-        "Nikolaev, Vitaly",
-        "Uematsu, Sumire",
-        "Tyers, Francis",
-        "Ahrenberg, Lars",
-        "Diaz de Ilarraza, Arantza",
-        "Rosa, Rudolf",
-        "Aranzabe, Maria Jesus",
-        "Saleh, Shadi",
-        "Simi, Maria",
-        "Bengoetxea, Kepa",
-        "van Noord, Gertjan",
-        "Pascual, Elena",
-        "Bouma, Gosse",
-        "Foster, Jennifer",
-        "\u00c7\u00f6ltekin, \u00c7a\u011fr\u0131",
-        "Gonz\u00e1les Saavedra, Berta",
-        "Uria, Larraitz",
-        "Ljube\u0161i\u0107, Nikola",
-        "Kanayama, Hiroshi",
-        "Shakurova, Lena",
-        "Bowman, Sam",
-        "Silveira, Natalia"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1699;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Universal Dependencies 1.3;Nivre, Joakim;Agi\u0107, \u017deljko;Ahrenberg, Lars;Aranzabe, Maria Jesus;Asahara, Masayuki;Atutxa, Aitziber;Ballesteros, Miguel;Bauer, John;Bengoetxea, Kepa;Berzak, Yevgeni;Bhat, Riyaz Ahmad;Bosco, Cristina;Bouma, Gosse;Bowman, Sam;Cebiro\u011flu Eryi\u011fit, G\u00fcl\u015fen;Celano, Giuseppe G. A.;\u00c7\u00f6ltekin, \u00c7a\u011fr\u0131;Connor, Miriam;de Marneffe, Marie-Catherine;Diaz de Ilarraza, Arantza;Dobrovoljc, Kaja;Dozat, Timothy;Droganova, Kira;Erjavec, Toma\u017e;Farkas, Rich\u00e1rd;Foster, Jennifer;Galbraith, Daniel;Garza, Sebastian;Ginter, Filip;Goenaga, Iakes;Gojenola, Koldo;Gokirmak, Memduh;Goldberg, Yoav;G\u00f3mez Guinovart, Xavier;Gonz\u00e1les Saavedra, Berta;Gr\u016bz\u012btis, Normunds;Guillaume, Bruno;Haji\u010d, Jan;Haug, Dag;Hladk\u00e1, Barbora;Ion, Radu;Irimia, Elena;Johannsen, Anders;Ka\u015f\u0131kara, H\u00fcner;Kanayama, Hiroshi;Kanerva, Jenna;Katz, Boris;Kenney, Jessica;Krek, Simon;Laippala, Veronika;Lam, Lucia;Lenci, Alessandro;Ljube\u0161i\u0107, Nikola;Lyashevskaya, Olga;Lynn, Teresa;Makazhanov, Aibek;Manning, Christopher;M\u0103r\u0103nduc, C\u0103t\u0103lina;Mare\u010dek, David;Mart\u00ednez Alonso, H\u00e9ctor;Ma\u0161ek, Jan;Matsumoto, Yuji;McDonald, Ryan;Missil\u00e4, Anna;Mititelu, Verginica;Miyao, Yusuke;Montemagni, Simonetta;Mori, Keiko Sophie;Mori, Shunsuke;Muischnek, Kadri;Mustafina, Nina;M\u00fc\u00fcrisep, Kaili;Nikolaev, Vitaly;Nurmi, Hanna;Osenova, Petya;\u00d8vrelid, Lilja;Pascual, Elena;Passarotti, Marco;Perez, Cenel-Augusto;Petrov, Slav;Piitulainen, Jussi;Plank, Barbara;Popel, Martin;Pretkalni\u0146a, Lauma;Prokopidis, Prokopis;Puolakainen, Tiina;Pyysalo, Sampo;Ramasamy, Loganathan;Rituma, Laura;Rosa, Rudolf;Saleh, Shadi;Saul\u012bte, Baiba;Schuster, Sebastian;Seeker, Wolfgang;Seraji, Mojgan;Shakurova, Lena;Shen, Mo;Silveira, Natalia;Simi, Maria;Simionescu, Radu;Simk\u00f3, Katalin;Simov, Kiril;Smith, Aaron;Spadine, Carolyn;Suhr, Alane;Sulubacak, Umut;Sz\u00e1nt\u00f3, Zsolt;Tanaka, Takaaki;Tsarfaty, Reut;Tyers, Francis;Uematsu, Sumire;Uria, Larraitz;van Noord, Gertjan;Varga, Viktor;Vincze, Veronika;Wang, Jing Xian;Washington, Jonathan North;\u017dabokrtsk\u00fd, Zden\u011bk;Zeman, Daniel;Zhu, Hanzhi;treebank;dependency;syntax;morphology;harmonized annotation;interset;universal tagset;stanford dependencies;Universal Dependencies is a project that seeks to develop cross-linguistically consistent treebank annotation for many languages, with the goal of facilitating multilingual parser development, cross-lingual learning, and parsing research from a language typology perspective. The annotation scheme is based on (universal) Stanford dependencies (de Marneffe et al., 2006, 2008, 2014), Google universal part-of-speech tags (Petrov et al., 2012), and the Interset interlingua for morphosyntactic tagsets (Zeman, 2008).;2016-05-15;corpus;http://hdl.handle.net/11234/1-1699;grc;ara;eus;bul;hrv;ces;dan;nld;eng;est;fin;fra;deu;got;ell;heb;hin;hun;ind;gle;ita;jpn;lat;nor;chu;fas;pol;por;ron;slv;spa;swe;tam;cat;zho;glg;kaz;lav;rus;tur;http://hdl.handle.net/11234/1-1548;http://hdl.handle.net/11234/1-1827;Licence Universal Dependencies v1.3;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-1.3;PUB;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Universal Dependencies Consortium;http://universaldependencies.org/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ac5a3c53-04b0-54ab-8b80-add1a79b1f97",
-    "notes": [
-        "Universal Dependencies is a project that seeks to develop cross-linguistically consistent treebank annotation for many languages, with the goal of facilitating multilingual parser development, cross-lingual learning, and parsing research from a language typology perspective. The annotation scheme is based on (universal) Stanford dependencies (de Marneffe et al., 2006, 2008, 2014), Google universal part-of-speech tags (Petrov et al., 2012), and the Interset interlingua for morphosyntactic tagsets (Zeman, 2008)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1699"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "dependency"
-        },
-        {
-            "name": "syntax"
-        },
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "harmonized annotation"
-        },
-        {
-            "name": "interset"
-        },
-        {
-            "name": "universal tagset"
-        },
-        {
-            "name": "stanford dependencies"
-        }
-    ],
-    "title": [
-        "Universal Dependencies 1.3"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ac783616-f3fc-55d4-bc6e-8212c6a59783.json b/oaitestdata/clarin-oai_dc/SET_1/json/ac783616-f3fc-55d4-bc6e-8212c6a59783.json
deleted file mode 100644
index 22f3fdfa..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ac783616-f3fc-55d4-bc6e-8212c6a59783.json
+++ /dev/null
@@ -1,91 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2873",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2873"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2873",
-    "PublicationTimestamp": "2018-09-24T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-2422"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "Vidra, Jon\u00e1\u0161",
-        "Kalu\u017eov\u00e1, Ad\u00e9la",
-        "\u0160ev\u010d\u00edkov\u00e1, Magda",
-        "Hude\u010dek, Vojt\u011bch",
-        "Dohnalov\u00e1, \u0160\u00e1rka",
-        "Kyj\u00e1nek, Luk\u00e1\u0161"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2873;2018-09-24T19:15:53Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;DeriNet 1.6 (2018-09-24);Vidra, Jon\u00e1\u0161;Kyj\u00e1nek, Luk\u00e1\u0161;\u0160ev\u010d\u00edkov\u00e1, Magda;\u017dabokrtsk\u00fd, Zden\u011bk;Kalu\u017eov\u00e1, Ad\u00e9la;Dohnalov\u00e1, \u0160\u00e1rka;Hude\u010dek, Vojt\u011bch;DeriNet;derivation;derivational morphology;lexical network;MorfFlex;DeriNet is a lexical network which models derivational relations in the lexicon of Czech. Nodes of the network correspond to Czech lexemes, while edges represent derivational relations between a derived word and its base word. The present version, DeriNet 1.6, contains 1,027,832 lexemes (sampled from the MorfFlex dictionary) connected by 803,404 derivational links. Furthermore, starting with version 1.5, DeriNet contains annotations related to compounding (compound words are distinguished by a special mark in their part-of-speech labels).\r\nCompared to version 1.5, version 1.6 was expanded by extracting potential links from dictionaries available under suitable licences, such as Wiktionary, and by enlarging the number of marked compounds.;2018-09-24;lexicalConceptualResource;http://hdl.handle.net/11234/1-2873;ces;http://hdl.handle.net/11234/1-2422;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://ufal.mff.cuni.cz/derinet",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ac783616-f3fc-55d4-bc6e-8212c6a59783",
-    "notes": [
-        "DeriNet is a lexical network which models derivational relations in the lexicon of Czech. Nodes of the network correspond to Czech lexemes, while edges represent derivational relations between a derived word and its base word. The present version, DeriNet 1.6, contains 1,027,832 lexemes (sampled from the MorfFlex dictionary) connected by 803,404 derivational links. Furthermore, starting with version 1.5, DeriNet contains annotations related to compounding (compound words are distinguished by a special mark in their part-of-speech labels).\r\nCompared to version 1.5, version 1.6 was expanded by extracting potential links from dictionaries available under suitable licences, such as Wiktionary, and by enlarging the number of marked compounds."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2873"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "DeriNet"
-        },
-        {
-            "name": "derivation"
-        },
-        {
-            "name": "derivational morphology"
-        },
-        {
-            "name": "lexical network"
-        },
-        {
-            "name": "MorfFlex"
-        }
-    ],
-    "title": [
-        "DeriNet 1.6 (2018-09-24)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ac8c39b0-ccef-5329-a966-221536ddea19.json b/oaitestdata/clarin-oai_dc/SET_1/json/ac8c39b0-ccef-5329-a966-221536ddea19.json
deleted file mode 100644
index 6b2792d6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ac8c39b0-ccef-5329-a966-221536ddea19.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Coventry University, University of Reading, University of Warwick"
-    ],
-    "Contributor": [
-        "Nesi, Hilary"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/tei+xml",
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-858",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-858"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-858",
-    "PublicationTimestamp": "2005-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2005"
-    ],
-    "Publisher": [
-        "Coventry University, University of Reading, University of Warwick"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-858;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;British academic spoken English (BASE) corpus;Nesi, Hilary;Transcribed recordings of 160 lectures and 39 seminars held in university departments. Four broad disciplinary groups, 1,644,942 tokens in total.;2005;corpus;http://hdl.handle.net/11372/LRT-858;eng;application/tei+xml;downloadable_files_count: 0;United Kingdom;Coventry University, University of Reading, University of Warwick;http://www.coventry.ac.uk/researchnet/d/503",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ac8c39b0-ccef-5329-a966-221536ddea19",
-    "notes": [
-        "Transcribed recordings of 160 lectures and 39 seminars held in university departments. Four broad disciplinary groups, 1,644,942 tokens in total."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-858"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "British academic spoken English (BASE) corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ac989334-e1ef-5d33-bd00-680a8d4798eb.json b/oaitestdata/clarin-oai_dc/SET_1/json/ac989334-e1ef-5d33-bd00-680a8d4798eb.json
deleted file mode 100644
index 1148bbbf..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ac989334-e1ef-5d33-bd00-680a8d4798eb.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Eurotermbank consortium",
-        "Tilde"
-    ],
-    "Contributor": [
-        "Vasiljevs, Andrejs"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "English",
-        "Estonian",
-        "French",
-        "German",
-        "Hungarian",
-        "Latvian",
-        "Lithuanian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-854",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-854"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-854",
-    "PublicationTimestamp": "2006-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2006"
-    ],
-    "Publisher": [
-        "Eurotermbank consortium",
-        "Tilde"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-854;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Eurotermbank;Vasiljevs, Andrejs;EuroTermBank is single access point to European multilingual terminology resources. It contains more than 1.9 million terms over 25 languages;2006;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-854;eng;est;fra;deu;hun;lav;lit;application/octet-stream;downloadable_files_count: 0;Tilde;Eurotermbank consortium;http://www.eurotermbank.com/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ac989334-e1ef-5d33-bd00-680a8d4798eb",
-    "notes": [
-        "EuroTermBank is single access point to European multilingual terminology resources. It contains more than 1.9 million terms over 25 languages"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-854"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Eurotermbank"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ad014ed7-f926-5aef-8f3e-034044d6d7d4.json b/oaitestdata/clarin-oai_dc/SET_1/json/ad014ed7-f926-5aef-8f3e-034044d6d7d4.json
deleted file mode 100644
index a01be95c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ad014ed7-f926-5aef-8f3e-034044d6d7d4.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Computer and Information Science, University of Ljubljana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1119",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1119"
-    ],
-    "PID": "http://hdl.handle.net/11356/1119",
-    "PublicationTimestamp": "2017-05-05T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Faculty of Computer and Information Science, University of Ljubljana"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Robnik-\u0160ikonja, Marko",
-        "Kadivec, Jo\u017ee",
-        "Vintar, \u0160pela"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1119;2017-05-05T16:33:24Z;hdl_11356_1023;hdl_11356_1024;ccGigafida ARPA language model 1.0;Kadivec, Jo\u017ee;Robnik-\u0160ikonja, Marko;Vintar, \u0160pela;Moses language model;probability language model;The ccGigafida ARPA language model was created from the ccGigafida written corpus of Slovenian (https://www.clarin.si/repository/xmlui/handle/11356/1035) using the KenLM algorithm in the Moses machine translation framework. It is a general language model of contemporary standard Slovenian language that can be used as a language model in statistical machine translation systems.\r\n\r\nThe language model was created as a part of the master thesis:\r\nKadivec, Jo\u017ee. 2016. Prilagoditev statisti\u010dnega strojnega prevajalnika za specifi\u010dno domeno v slovenskem jeziku (Domain specific adaptation of a statistical machine translation engine in Slovene language). Master's thesis, Faculty of computer and information science, University of Ljubljana. https://repozitorij.uni-lj.si/IzpisGradiva.php?id=84815;2017-05-05;lexicalConceptualResource;http://hdl.handle.net/11356/1119;slv;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;PUB;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Faculty of Computer and Information Science, University of Ljubljana",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ad014ed7-f926-5aef-8f3e-034044d6d7d4",
-    "notes": [
-        "The ccGigafida ARPA language model was created from the ccGigafida written corpus of Slovenian (https://www.clarin.si/repository/xmlui/handle/11356/1035) using the KenLM algorithm in the Moses machine translation framework. It is a general language model of contemporary standard Slovenian language that can be used as a language model in statistical machine translation systems.\r\n\r\nThe language model was created as a part of the master thesis:\r\nKadivec, Jo\u017ee. 2016. Prilagoditev statisti\u010dnega strojnega prevajalnika za specifi\u010dno domeno v slovenskem jeziku (Domain specific adaptation of a statistical machine translation engine in Slovene language). Master's thesis, Faculty of computer and information science, University of Ljubljana. https://repozitorij.uni-lj.si/IzpisGradiva.php?id=84815"
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1119"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Moses language model"
-        },
-        {
-            "name": "probability language model"
-        }
-    ],
-    "title": [
-        "ccGigafida ARPA language model 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ad0cda21-77ae-5505-a042-3aaa44836b9f.json b/oaitestdata/clarin-oai_dc/SET_1/json/ad0cda21-77ae-5505-a042-3aaa44836b9f.json
deleted file mode 100644
index 86427ec6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ad0cda21-77ae-5505-a042-3aaa44836b9f.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Institut f\u00fcr Deutsche Sprache"
-    ],
-    "Contributor": [
-        "Schwinn, Horst"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-543",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-543"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-543",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut f\u00fcr Deutsche Sprache"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-543;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Prop\u00e4deutische Grammatik (ProGr@mm);Schwinn, Horst;Web Information &Learning System, contains reusable e-learning resources, XML format;2014-07-30;languageDescription;http://hdl.handle.net/11372/LRT-543;deu;downloadable_files_count: 0;Germany;Institut f\u00fcr Deutsche Sprache;http://www.ids-mannheim.de/progr@mm/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ad0cda21-77ae-5505-a042-3aaa44836b9f",
-    "notes": [
-        "Web Information &Learning System, contains reusable e-learning resources, XML format"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-543"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Prop\u00e4deutische Grammatik (ProGr@mm)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ad34299a-1788-5179-9cca-b7faef1d8f8f.json b/oaitestdata/clarin-oai_dc/SET_1/json/ad34299a-1788-5179-9cca-b7faef1d8f8f.json
deleted file mode 100644
index 0c157ce2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ad34299a-1788-5179-9cca-b7faef1d8f8f.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5124",
-    "MetadataAccess": [
-        "oai:ota:oucs:5124"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hayley, William, 1745-1820."
-    ],
-    "fulltext": "oai:ota:oucs:5124;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5124.xml;The young widow; or the history of Cornelia Sedley: in a series of letters. ... [pt.2];Hayley, William, 1745-1820.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ad34299a-1788-5179-9cca-b7faef1d8f8f",
-    "oai_identifier": [
-        "oai:ota:oucs:5124"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The young widow; or the history of Cornelia Sedley: in a series of letters. ... [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5124.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ad43beb9-dd67-5b8a-bdcf-9cf9a1ac9936.json b/oaitestdata/clarin-oai_dc/SET_1/json/ad43beb9-dd67-5b8a-bdcf-9cf9a1ac9936.json
deleted file mode 100644
index e6548876..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ad43beb9-dd67-5b8a-bdcf-9cf9a1ac9936.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5335",
-    "MetadataAccess": [
-        "oai:ota:oucs:5335"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Goldsmith, Oliver, 1730?-1774."
-    ],
-    "fulltext": "oai:ota:oucs:5335;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5335.xml;An history of the earth: and animated nature: by Oliver Goldsmith. In eight volumes. ... [pt.2];Goldsmith, Oliver, 1730?-1774.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ad43beb9-dd67-5b8a-bdcf-9cf9a1ac9936",
-    "oai_identifier": [
-        "oai:ota:oucs:5335"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An history of the earth: and animated nature: by Oliver Goldsmith. In eight volumes. ... [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5335.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ad453da6-fe8f-5284-800e-0ddd8e0c1339.json b/oaitestdata/clarin-oai_dc/SET_1/json/ad453da6-fe8f-5284-800e-0ddd8e0c1339.json
deleted file mode 100644
index 5e5a8ec5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ad453da6-fe8f-5284-800e-0ddd8e0c1339.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 19.8 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0115",
-    "MetadataAccess": [
-        "oai:ota:oucs:0115"
-    ],
-    "PublicationTimestamp": "1630-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1630"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Randolph, Thomas, 1605-1635"
-    ],
-    "fulltext": "oai:ota:oucs:0115;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0115.xml;The conceited pedlar;Randolph, Thomas, 1605-1635;1630;text_and_corpus_linguistics;Plays -- England -- 17th century;eng;Oxford Text Archive, University of Oxford;(1 file : ca. 19.8 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ad453da6-fe8f-5284-800e-0ddd8e0c1339",
-    "oai_identifier": [
-        "oai:ota:oucs:0115"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        }
-    ],
-    "title": [
-        "The conceited pedlar"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0115.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ad49173d-c1a6-55d4-bc49-a001af5c02fb.json b/oaitestdata/clarin-oai_dc/SET_1/json/ad49173d-c1a6-55d4-bc49-a001af5c02fb.json
deleted file mode 100644
index 6cd5d4df..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ad49173d-c1a6-55d4-bc49-a001af5c02fb.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish",
-        "Macedonian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/61",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/61"
-    ],
-    "PID": "http://hdl.handle.net/10794/61",
-    "PublicationTimestamp": "2015-04-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/61;2017-10-31T12:40:11Z;hdl_10794_1;hdl_10794_2;ASPAC \u2013 Swedish-Macedonian (2017-10-16);ASPAC \u2013 svenska-makedonska (2017-10-16);n/a, n/a;ASPAC;Parallel;Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.;Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat.;2015-04-16;corpus;http://hdl.handle.net/10794/61;swe;mkd;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/octet-stream;application/gzip;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/aspacsvmk",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ad49173d-c1a6-55d4-bc49-a001af5c02fb",
-    "notes": [
-        "Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.",
-        "Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/61"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ASPAC"
-        },
-        {
-            "name": "Parallel"
-        }
-    ],
-    "title": [
-        "ASPAC \u2013 Swedish-Macedonian (2017-10-16)",
-        "ASPAC \u2013 svenska-makedonska (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ad656c20-d480-5fdf-a5fa-7eea6289a0ac.json b/oaitestdata/clarin-oai_dc/SET_1/json/ad656c20-d480-5fdf-a5fa-7eea6289a0ac.json
deleted file mode 100644
index 7decd4f4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ad656c20-d480-5fdf-a5fa-7eea6289a0ac.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Matteo Grella"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2629",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2629"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2629",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Matteo Grella"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11372/LRT-2288",
-        "http://hdl.handle.net/11372/LRT-2893"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Grella, Matteo"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2629;2018-11-14T15:34:38Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Italian Function Words v2;Grella, Matteo;morphological dictionary;function words;This dictionary is the second version of 11372/LRT-2288, a curated list of Italian function words in a JSON Lines format text file, particularly useful for tasks such as POS-Tagging or Syntactic Parsing. It contains 999 single-word forms and 2501 multi-words forms. Each entry may have the following grammatical features: lemma, pos, mood, tense, person, number, gender, case, degree. Compared to the first release, this version has a more clear JSON structure.;2018;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-2629;ita;http://hdl.handle.net/11372/LRT-2288;http://hdl.handle.net/11372/LRT-2893;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 1;Matteo Grella",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ad656c20-d480-5fdf-a5fa-7eea6289a0ac",
-    "notes": [
-        "This dictionary is the second version of 11372/LRT-2288, a curated list of Italian function words in a JSON Lines format text file, particularly useful for tasks such as POS-Tagging or Syntactic Parsing. It contains 999 single-word forms and 2501 multi-words forms. Each entry may have the following grammatical features: lemma, pos, mood, tense, person, number, gender, case, degree. Compared to the first release, this version has a more clear JSON structure."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2629"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphological dictionary"
-        },
-        {
-            "name": "function words"
-        }
-    ],
-    "title": [
-        "Italian Function Words v2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ad6e7804-d1a2-5ac1-b4ed-8d2c4c22d7e8.json b/oaitestdata/clarin-oai_dc/SET_1/json/ad6e7804-d1a2-5ac1-b4ed-8d2c4c22d7e8.json
deleted file mode 100644
index 2974efe2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ad6e7804-d1a2-5ac1-b4ed-8d2c4c22d7e8.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Uniwersytet Warszawski"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 202",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/514",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/514"
-    ],
-    "PID": "http://hdl.handle.net/11321/514",
-    "PublicationTimestamp": "2018-07-13T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Uniwersytet Warszawski"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Super Cool License",
-        "http://www.google.com",
-        "ACA"
-    ],
-    "author": [
-        "Puchatek, Kubu\u015b",
-        "Puchatek, Kubu\u015b Jr"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/514;2018-07-13T13:51:08Z;hdl_11321_3;hdl_11321_4;Korpus testowy na warsztaty;Puchatek, Kubu\u015b;Puchatek, Kubu\u015b Jr;Polish;Korpus testowy;2018-07-13;corpus;http://hdl.handle.net/11321/514;pol;Super Cool License;http://www.google.com;ACA;text/plain; charset=utf-8;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;downloadable_files_count: 202;Uniwersytet Warszawski",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ad6e7804-d1a2-5ac1-b4ed-8d2c4c22d7e8",
-    "notes": [
-        "Korpus testowy"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/514"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Polish"
-        }
-    ],
-    "title": [
-        "Korpus testowy na warsztaty"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ad8d4dfa-b840-585c-8c72-e9d9ba3e479f.json b/oaitestdata/clarin-oai_dc/SET_1/json/ad8d4dfa-b840-585c-8c72-e9d9ba3e479f.json
deleted file mode 100644
index 052f93a0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ad8d4dfa-b840-585c-8c72-e9d9ba3e479f.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3089",
-    "MetadataAccess": [
-        "oai:ota:oucs:3089"
-    ],
-    "PublicationTimestamp": "1858-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1858"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Eliot, George, 1819-1880"
-    ],
-    "fulltext": "oai:ota:oucs:3089;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3089.xml;Janet's repentance;Eliot, George, 1819-1880;not after: 1858;text_and_corpus_linguistics;Fiction -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ad8d4dfa-b840-585c-8c72-e9d9ba3e479f",
-    "oai_identifier": [
-        "oai:ota:oucs:3089"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Janet's repentance"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3089.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ada25e27-de7c-5813-b63b-5311ae478322.json b/oaitestdata/clarin-oai_dc/SET_1/json/ada25e27-de7c-5813-b63b-5311ae478322.json
deleted file mode 100644
index c23a97bd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ada25e27-de7c-5813-b63b-5311ae478322.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2823",
-    "MetadataAccess": [
-        "oai:ota:oucs:2823"
-    ],
-    "PublicationTimestamp": "1735-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1735"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2823;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2823.xml;Drapier's Letters IVc, The presentment of the Grand-Jury;Swift, Jonathan, 1667-1745;1735;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ada25e27-de7c-5813-b63b-5311ae478322",
-    "oai_identifier": [
-        "oai:ota:oucs:2823"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Drapier's Letters IVc, The presentment of the Grand-Jury"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2823.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ada717e0-7c4d-5b36-9345-303b1963737b.json b/oaitestdata/clarin-oai_dc/SET_1/json/ada717e0-7c4d-5b36-9345-303b1963737b.json
deleted file mode 100644
index 9f7ed0f6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ada717e0-7c4d-5b36-9345-303b1963737b.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2867",
-    "MetadataAccess": [
-        "oai:ota:oucs:2867"
-    ],
-    "PublicationTimestamp": "1765-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1765"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2867;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2867.xml;Upon giving badges to the poor;Swift, Jonathan, 1667-1745;1765;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ada717e0-7c4d-5b36-9345-303b1963737b",
-    "oai_identifier": [
-        "oai:ota:oucs:2867"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Upon giving badges to the poor"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2867.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ade7c2fc-bae1-5c66-9f2a-a795360d8119.json b/oaitestdata/clarin-oai_dc/SET_1/json/ade7c2fc-bae1-5c66-9f2a-a795360d8119.json
deleted file mode 100644
index 29c7e68b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ade7c2fc-bae1-5c66-9f2a-a795360d8119.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "European Commission",
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/xml",
-        "downloadable_files_count: 10",
-        "application/pdf",
-        "application/zip"
-    ],
-    "Language": [
-        "Danish",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repository.clarin.dk:20.500.12115/29",
-    "MetadataAccess": [
-        "oai:repository.clarin.dk:20.500.12115/29"
-    ],
-    "PID": "http://hdl.handle.net/20.500.12115/29",
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "European Commission",
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Hansen, Dorte Haltrup",
-        "Offersgaard, Lene"
-    ],
-    "fulltext": "oai:repository.clarin.dk:20.500.12115/29;2018-06-28T13:28:29Z;hdl_20.500.12115_1;hdl_20.500.12115_3;DK-CLARIN JRC-Acquis Parallel Corpus 1958-2003 (da-en);Hansen, Dorte Haltrup;Offersgaard, Lene;legal;EU;The DK-CLARIN JRC-Acquis Parallel Corpus (da, en) is a part of the JRC-Acquis mulilingual parallel corpus, containing documents from The Acquis Communautaire (AC) which is the total body of European Union (EU) law applicable in the the EU Member States (see: https://ec.europa.eu/jrc/en/language-technologies/jrc-acquis). The data comes with one or more Eurovoc class codes added in the metadata from the European Commission. \r\nEach language corpus (English and Danish) contains app. 20 million words.\r\n\r\nAll texts are in XML TEIP5 format (TEIP5DKCLARIN-format), with tokenisation, pos-tagging, sentence and paragraph segmentation, lemmatisation and for Danish also termhood annotation. The annotations are placed in separate text external spangroups.\r\n\r\nThe corpus was collected and processed in the work package 2.6 of the Danish CLARIN project (see http://dkclarin.ku.dk/english) by University of Copenhagen, Centre for Language Technology.\r\nThe aim of the Danish CLARIN consortium was to construct a Danish research infrastructure for the humanities integrating written, spoken, and visual records into a coherent and systematic digital repository. \r\nThe project ran from January 2008 until the end of 2010.;2011;corpus;http://hdl.handle.net/20.500.12115/29;dan;eng;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;text/plain; charset=utf-8;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/pdf;application/pdf;text/xml;downloadable_files_count: 10;Centre for Language Technology, NorS, University of Copenhagen;European Commission",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ade7c2fc-bae1-5c66-9f2a-a795360d8119",
-    "notes": [
-        "The DK-CLARIN JRC-Acquis Parallel Corpus (da, en) is a part of the JRC-Acquis mulilingual parallel corpus, containing documents from The Acquis Communautaire (AC) which is the total body of European Union (EU) law applicable in the the EU Member States (see: https://ec.europa.eu/jrc/en/language-technologies/jrc-acquis). The data comes with one or more Eurovoc class codes added in the metadata from the European Commission. \r\nEach language corpus (English and Danish) contains app. 20 million words.\r\n\r\nAll texts are in XML TEIP5 format (TEIP5DKCLARIN-format), with tokenisation, pos-tagging, sentence and paragraph segmentation, lemmatisation and for Danish also termhood annotation. The annotations are placed in separate text external spangroups.\r\n\r\nThe corpus was collected and processed in the work package 2.6 of the Danish CLARIN project (see http://dkclarin.ku.dk/english) by University of Copenhagen, Centre for Language Technology.\r\nThe aim of the Danish CLARIN consortium was to construct a Danish research infrastructure for the humanities integrating written, spoken, and visual records into a coherent and systematic digital repository. \r\nThe project ran from January 2008 until the end of 2010."
-    ],
-    "oai_identifier": [
-        "oai:repository.clarin.dk:20.500.12115/29"
-    ],
-    "oai_set": [
-        "hdl_20.500.12115_1",
-        "hdl_20.500.12115_3"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "legal"
-        },
-        {
-            "name": "EU"
-        }
-    ],
-    "title": [
-        "DK-CLARIN JRC-Acquis Parallel Corpus 1958-2003 (da-en)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ae053d8c-375d-5118-bcf7-a1fdbb923859.json b/oaitestdata/clarin-oai_dc/SET_1/json/ae053d8c-375d-5118-bcf7-a1fdbb923859.json
deleted file mode 100644
index 84ad2933..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ae053d8c-375d-5118-bcf7-a1fdbb923859.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4967",
-    "MetadataAccess": [
-        "oai:ota:oucs:4967"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Cumberland, Richard, 1732-1811."
-    ],
-    "fulltext": "oai:ota:oucs:4967;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4967.xml;Henry: in four volumes. By the author of Arundel. ... [pt.3];Cumberland, Richard, 1732-1811.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ae053d8c-375d-5118-bcf7-a1fdbb923859",
-    "oai_identifier": [
-        "oai:ota:oucs:4967"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Henry: in four volumes. By the author of Arundel. ... [pt.3]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4967.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ae0da70d-5674-55f1-8f57-144b89d9e68c.json b/oaitestdata/clarin-oai_dc/SET_1/json/ae0da70d-5674-55f1-8f57-144b89d9e68c.json
deleted file mode 100644
index 07a05f52..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ae0da70d-5674-55f1-8f57-144b89d9e68c.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Catalan",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1200",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1200"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1200",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1200;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Gestor de diccionaris;Tool for terminology management;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1200;cat;spa;downloadable_files_count: 0;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra;http://obneo.iula.upf.edu/gesdic/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ae0da70d-5674-55f1-8f57-144b89d9e68c",
-    "notes": [
-        "Tool for terminology management"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1200"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Gestor de diccionaris"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ae14367a-4afe-5552-9feb-37279ba7be6b.json b/oaitestdata/clarin-oai_dc/SET_1/json/ae14367a-4afe-5552-9feb-37279ba7be6b.json
deleted file mode 100644
index 86b62956..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ae14367a-4afe-5552-9feb-37279ba7be6b.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/600",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/600"
-    ],
-    "PID": "http://hdl.handle.net/11321/600",
-    "PublicationTimestamp": "2018-09-14T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Marci\u0144czuk, Micha\u0142",
-        "Koco\u0144, Jan"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/600;2018-09-14T13:43:42Z;hdl_11321_3;hdl_11321_4;Word embeddings for Polish (KGR10, Fasttext binary) kgr10_fasttext_bin_v1;Koco\u0144, Jan;Marci\u0144czuk, Micha\u0142;word embeddings;fasttext;binary;Polish;KGR10;Distributional language model (binary) for Polish trained on KGR10 using Fasttext (vector dimension: 100).;2018-09-14;languageDescription;http://hdl.handle.net/11321/600;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;application/octet-stream;downloadable_files_count: 1;Wroc\u0142aw University of Science and Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ae14367a-4afe-5552-9feb-37279ba7be6b",
-    "notes": [
-        "Distributional language model (binary) for Polish trained on KGR10 using Fasttext (vector dimension: 100)."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/600"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "word embeddings"
-        },
-        {
-            "name": "fasttext"
-        },
-        {
-            "name": "binary"
-        },
-        {
-            "name": "Polish"
-        },
-        {
-            "name": "KGR"
-        }
-    ],
-    "title": [
-        "Word embeddings for Polish (KGR10, Fasttext binary) kgr10_fasttext_bin_v1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ae260a97-d53a-5c3e-85e9-270ccf6230f2.json b/oaitestdata/clarin-oai_dc/SET_1/json/ae260a97-d53a-5c3e-85e9-270ccf6230f2.json
deleted file mode 100644
index 08bae691..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ae260a97-d53a-5c3e-85e9-270ccf6230f2.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1413",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1413"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1413",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1413;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;iula_preprocess;Text preprocess (this preprocess service requires that the input text be in plain text format (file .txt) and UTF-8).\nBasically, it carries out: (i) text segmentation into minor structural units (titles, paragraphs, sentences, etc.); (ii) detection of entities not found in dictionaries (numbers, abbreviations, URLs, emails, proper nouns, etc.); and (iii) the keeping of sequences of two or more words in a single block (dates, phrases, proper nouns, etc.).;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1413;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ae260a97-d53a-5c3e-85e9-270ccf6230f2",
-    "notes": [
-        "Text preprocess (this preprocess service requires that the input text be in plain text format (file .txt) and UTF-8).\nBasically, it carries out: (i) text segmentation into minor structural units (titles, paragraphs, sentences, etc.); (ii) detection of entities not found in dictionaries (numbers, abbreviations, URLs, emails, proper nouns, etc.); and (iii) the keeping of sequences of two or more words in a single block (dates, phrases, proper nouns, etc.)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1413"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "iula_preprocess"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ae3a6c60-b2ca-53bd-bbd4-9f9e01b20431.json b/oaitestdata/clarin-oai_dc/SET_1/json/ae3a6c60-b2ca-53bd-bbd4-9f9e01b20431.json
deleted file mode 100644
index 389dbedd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ae3a6c60-b2ca-53bd-bbd4-9f9e01b20431.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "Contributor": [
-        "Variaci\u00f3, Iula"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Catalan"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1108",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1108"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1108",
-    "PublicationTimestamp": "2008-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2008"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1108;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Corpus de parlants catalanoparlants de La Canonja en temps real (TR);Variaci\u00f3, Iula;oral corpus;Oral corpus containing 10 sociolinguistic interviews carried out in La Canonja (Tarragona).;2008;corpus;http://hdl.handle.net/11372/LRT-1108;cat;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra;http://www.iula.upf.edu/recurs08ca.htm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ae3a6c60-b2ca-53bd-bbd4-9f9e01b20431",
-    "notes": [
-        "Oral corpus containing 10 sociolinguistic interviews carried out in La Canonja (Tarragona)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1108"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "oral corpus"
-        }
-    ],
-    "title": [
-        "Corpus de parlants catalanoparlants de La Canonja en temps real (TR)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ae4f7a3f-6835-50c0-9120-e4ed3f8f1c81.json b/oaitestdata/clarin-oai_dc/SET_1/json/ae4f7a3f-6835-50c0-9120-e4ed3f8f1c81.json
deleted file mode 100644
index 5df15a07..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ae4f7a3f-6835-50c0-9120-e4ed3f8f1c81.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Danish",
-        "Dutch",
-        "English",
-        "Finnish",
-        "French",
-        "German",
-        "Modern Greek (1453-)",
-        "Italian",
-        "Luxembourgish",
-        "Norwegian",
-        "Portuguese",
-        "Slovenian",
-        "Spanish",
-        "Swedish",
-        "Welsh"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-598",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-598"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-598",
-    "PublicationTimestamp": "1998-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1998"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-598;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;SpeechDat databases;25 fixed and mobile telephone network databases, 500-5000 speakers each; 3 speaker verification databases. Contains interesting phonetically rich material. All orthographically transcribed. Speaker information included for gender, age, accent. Including pronunciation lexicon.;1998;corpus;http://hdl.handle.net/11372/LRT-598;dan;nld;eng;fin;fra;deu;ell;ita;ltz;nor;por;slv;spa;swe;cym;downloadable_files_count: 0;http://www.speechdat.org/SpeechDat.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ae4f7a3f-6835-50c0-9120-e4ed3f8f1c81",
-    "notes": [
-        "25 fixed and mobile telephone network databases, 500-5000 speakers each; 3 speaker verification databases. Contains interesting phonetically rich material. All orthographically transcribed. Speaker information included for gender, age, accent. Including pronunciation lexicon."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-598"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "SpeechDat databases"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ae64bfac-e767-5752-b59e-c62236185829.json b/oaitestdata/clarin-oai_dc/SET_1/json/ae64bfac-e767-5752-b59e-c62236185829.json
deleted file mode 100644
index 6f3da61e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ae64bfac-e767-5752-b59e-c62236185829.json
+++ /dev/null
@@ -1,88 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Czech",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-7AEB-4",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-7AEB-4"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-7AEB-4",
-    "PublicationTimestamp": "2014-04-05T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/610516",
-        "info:eu-repo/grantAgreement/EC/FP7/247762",
-        "http://hdl.handle.net/11234/1-1480"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Artistic License 2.0",
-        "http://opensource.org/licenses/Artistic-2.0",
-        "PUB"
-    ],
-    "author": [
-        "Rosa, Rudolf"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-7AEB-4;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;MSTperl parser;Rosa, Rudolf;parser;NLP;Treex;parsing;dependency;MSTperl is a Perl reimplementation of the MST parser of Ryan McDonald (http://www.seas.upenn.edu/~strctlrn/MSTParser/MSTParser.html).\r\n\r\nMST parser (Maximum Spanning Tree parser) is a state-of-the-art natural language dependency parser -- a tool that takes a sentence and returns its dependency tree.\r\n\r\nIn MSTperl, only some functionality was implemented; the limitations include the following:\r\nthe parser is a non-projective one, curently with no possibility of enforcing the requirement of projectivity of the parse trees;\r\nonly first-order features are supported, i.e. no second-order or third-order features are possible;\r\nthe implementation of MIRA is that of a single-best MIRA, with a closed-form update instead of using quadratic programming.\r\n\r\nOn the other hand, the parser supports several advanced features:\r\nparallel features, i.e. enriching the parser input with word-aligned sentence in other language;\r\nadding large-scale information, i.e. the feature set enriched with features corresponding to pointwise mutual information of word pairs in a large corpus (CzEng).\r\n\r\nThe MSTperl parser is tuned for parsing Czech. Trained models are available for Czech, English and German. We can train the parser for other languages on demand, or you can train it yourself -- the guidelines are part of the documentation.\r\n\r\nThe parser, together with detailed documentation, is avalable on CPAN (http://search.cpan.org/~rur/Treex-Parser-MSTperl/).;2014-04-05;toolService;http://hdl.handle.net/11858/00-097C-0000-0023-7AEB-4;ces;eng;info:eu-repo/grantAgreement/EC/FP7/610516;info:eu-repo/grantAgreement/EC/FP7/247762;http://hdl.handle.net/11234/1-1480;Artistic License 2.0;http://opensource.org/licenses/Artistic-2.0;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://ufal.mff.cuni.cz/tools/mstperl-parser",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ae64bfac-e767-5752-b59e-c62236185829",
-    "notes": [
-        "MSTperl is a Perl reimplementation of the MST parser of Ryan McDonald (http://www.seas.upenn.edu/~strctlrn/MSTParser/MSTParser.html).\r\n\r\nMST parser (Maximum Spanning Tree parser) is a state-of-the-art natural language dependency parser -- a tool that takes a sentence and returns its dependency tree.\r\n\r\nIn MSTperl, only some functionality was implemented; the limitations include the following:\r\nthe parser is a non-projective one, curently with no possibility of enforcing the requirement of projectivity of the parse trees;\r\nonly first-order features are supported, i.e. no second-order or third-order features are possible;\r\nthe implementation of MIRA is that of a single-best MIRA, with a closed-form update instead of using quadratic programming.\r\n\r\nOn the other hand, the parser supports several advanced features:\r\nparallel features, i.e. enriching the parser input with word-aligned sentence in other language;\r\nadding large-scale information, i.e. the feature set enriched with features corresponding to pointwise mutual information of word pairs in a large corpus (CzEng).\r\n\r\nThe MSTperl parser is tuned for parsing Czech. Trained models are available for Czech, English and German. We can train the parser for other languages on demand, or you can train it yourself -- the guidelines are part of the documentation.\r\n\r\nThe parser, together with detailed documentation, is avalable on CPAN (http://search.cpan.org/~rur/Treex-Parser-MSTperl/)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-7AEB-4"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parser"
-        },
-        {
-            "name": "NLP"
-        },
-        {
-            "name": "Treex"
-        },
-        {
-            "name": "parsing"
-        },
-        {
-            "name": "dependency"
-        }
-    ],
-    "title": [
-        "MSTperl parser"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ae78d630-eab4-54b0-8475-e66f6f212a65.json b/oaitestdata/clarin-oai_dc/SET_1/json/ae78d630-eab4-54b0-8475-e66f6f212a65.json
deleted file mode 100644
index 42999e7c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ae78d630-eab4-54b0-8475-e66f6f212a65.json
+++ /dev/null
@@ -1,96 +0,0 @@
-{
-    "Contact": [
-        "CNR Edizioni",
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/pdf"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/OPEN-89",
-    "MetadataAccess": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/OPEN-89"
-    ],
-    "PID": "http://hdl.handle.net/20.500.11752/OPEN-89",
-    "PublicationTimestamp": "2018-04-05T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "CNR Edizioni",
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)",
-        "http://creativecommons.org/licenses/by-nc/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Boschetti, Federico"
-    ],
-    "fulltext": "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/OPEN-89;2018-07-23T09:13:44Z;hdl_000-c0-111_39;hdl_000-c0-111_43;Copisti Digitali e Filologi Computazionali;Boschetti, Federico;Filologia collaborativa e cooperativa;Filologia computazionale;Filologia digitale;Filologia classica;Classical philology;Digital philology;Collaborative and cooperative philology;Computational philology;Digital scholarly editing;Il volume \u00e8 formato da dieci capitoli e mette insieme, elaborandoli ed aggiornandoli, materiali\r\ndelle due tesi di dottorato dell\u2019autore, una in Filologia Classica (2005) e l\u2019altra in Linguistica\r\nComputazionale (2010), entrambe discusse presso l\u2019Universit\u00e0 di Trento.\r\nDopo una breve introduzione sul concetto di filologia collaborativa e cooperativa, i primi\r\ncapitoli sono dedicati all\u2019ecdotica digitale, quindi all\u2019acquisizione del testo di edizioni critiche\r\ntramite OCR e al trattamento computazionale di apparati critici e repertori di congetture.\r\nI capitoli seguenti sono dedicati ad aspetti salienti dell\u2019ermeneutica digitale, come l\u2019analisi\r\nsintattica tramite la creazione di treebanks e l\u2019analisi lessico-semantica tramite la creazione di\r\nwordnets e l\u2019esplorazione di word spaces con metodi statistici.\r\nChiudono il volume un capitolo di discussione relativa a punti critici del testo usato come\r\ncaso di studio (I Persiani di Eschilo) e un capitolo di conclusioni e prospettive di ricerca.;2018-04-05;corpus;http://hdl.handle.net/20.500.11752/OPEN-89;ita;Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0);http://creativecommons.org/licenses/by-nc/4.0/;PUB;application/pdf;text/plain; charset=utf-8;downloadable_files_count: 1;CNR Edizioni;Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ae78d630-eab4-54b0-8475-e66f6f212a65",
-    "notes": [
-        "Il volume \u00e8 formato da dieci capitoli e mette insieme, elaborandoli ed aggiornandoli, materiali\r\ndelle due tesi di dottorato dell\u2019autore, una in Filologia Classica (2005) e l\u2019altra in Linguistica\r\nComputazionale (2010), entrambe discusse presso l\u2019Universit\u00e0 di Trento.\r\nDopo una breve introduzione sul concetto di filologia collaborativa e cooperativa, i primi\r\ncapitoli sono dedicati all\u2019ecdotica digitale, quindi all\u2019acquisizione del testo di edizioni critiche\r\ntramite OCR e al trattamento computazionale di apparati critici e repertori di congetture.\r\nI capitoli seguenti sono dedicati ad aspetti salienti dell\u2019ermeneutica digitale, come l\u2019analisi\r\nsintattica tramite la creazione di treebanks e l\u2019analisi lessico-semantica tramite la creazione di\r\nwordnets e l\u2019esplorazione di word spaces con metodi statistici.\r\nChiudono il volume un capitolo di discussione relativa a punti critici del testo usato come\r\ncaso di studio (I Persiani di Eschilo) e un capitolo di conclusioni e prospettive di ricerca."
-    ],
-    "oai_identifier": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/OPEN-89"
-    ],
-    "oai_set": [
-        "hdl_000-c0-111_39",
-        "hdl_000-c0-111_43"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Filologia collaborativa e cooperativa"
-        },
-        {
-            "name": "Filologia computazionale"
-        },
-        {
-            "name": "Filologia digitale"
-        },
-        {
-            "name": "Filologia classica"
-        },
-        {
-            "name": "Classical philology"
-        },
-        {
-            "name": "Digital philology"
-        },
-        {
-            "name": "Collaborative cooperative philology"
-        },
-        {
-            "name": "Computational philology"
-        },
-        {
-            "name": "Digital scholarly editing"
-        }
-    ],
-    "title": [
-        "Copisti Digitali e Filologi Computazionali"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ae8d5c21-8adb-5721-9758-72c5087abf86.json b/oaitestdata/clarin-oai_dc/SET_1/json/ae8d5c21-8adb-5721-9758-72c5087abf86.json
deleted file mode 100644
index d9b681e4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ae8d5c21-8adb-5721-9758-72c5087abf86.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 134 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2072",
-    "MetadataAccess": [
-        "oai:ota:oucs:2072"
-    ],
-    "PublicationTimestamp": "1776-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1776"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Paine, Thomas, 1737-1809"
-    ],
-    "fulltext": "oai:ota:oucs:2072;2018-05-17T09:29:11Z;http://ota.ox.ac.uk/headers/2072.xml;Common sense / by Thomas Paine;Paine, Thomas, 1737-1809;1776;text_and_corpus_linguistics;Essays -- United States -- 18th century;Protest literature -- United States -- 18th century;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 134 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ae8d5c21-8adb-5721-9758-72c5087abf86",
-    "oai_identifier": [
-        "oai:ota:oucs:2072"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Essays -- United States -- th century"
-        },
-        {
-            "name": "Protest literature -- United States -- th century"
-        }
-    ],
-    "title": [
-        "Common sense / by Thomas Paine"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2072.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ae97338b-ca0d-5619-8015-2b3d3d969e35.json b/oaitestdata/clarin-oai_dc/SET_1/json/ae97338b-ca0d-5619-8015-2b3d3d969e35.json
deleted file mode 100644
index 71601864..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ae97338b-ca0d-5619-8015-2b3d3d969e35.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Delbecque, Nicole"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 88 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0464",
-    "MetadataAccess": [
-        "oai:ota:oucs:0464"
-    ],
-    "PublicationTimestamp": "1972-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1972"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Whitehead, E.A."
-    ],
-    "fulltext": "oai:ota:oucs:0464;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0464.xml;The foursome / E.A. Whitehead;Whitehead, E.A.;1972;text_and_corpus_linguistics;English drama -- 20th century;eng;Oxford Text Archive, University of Oxford;Delbecque, Nicole;(1 file : ca. 88 KB);Text;Plays;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ae97338b-ca0d-5619-8015-2b3d3d969e35",
-    "oai_identifier": [
-        "oai:ota:oucs:0464"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- th century"
-        }
-    ],
-    "title": [
-        "The foursome / E.A. Whitehead"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0464.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/aea743e5-431d-5ba4-ab06-15bfce38079a.json b/oaitestdata/clarin-oai_dc/SET_1/json/aea743e5-431d-5ba4-ab06-15bfce38079a.json
deleted file mode 100644
index 6830f27a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/aea743e5-431d-5ba4-ab06-15bfce38079a.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "Universit\u00e4t des Saarlandes"
-    ],
-    "Contributor": [
-        "Jos\u00e9 Manuel Mart\u00ednez Mart\u00ednez",
-        "Mercedes Garc\u00eda Ferrer",
-        "Maria Teresa Beltr\u00e1n Chabrera",
-        "Mar\u00eda Teresa Cases Fandos"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml"
-    ],
-    "Language": [
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:clarelatin",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:clarelatin"
-    ],
-    "PID": "http://hdl.handle.net/21.11119/0000-0001-614D-C",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Universit\u00e4t des Saarlandes"
-    ],
-    "RelatedIdentifier": [
-        "Tagset: http://www.cis.uni-muenchen.de/~schmid/tools/TreeTagger/data/Lamap-Tagset.pdf"
-    ],
-    "ResourceType": [
-        "Collection"
-    ],
-    "Rights": [
-        "Copyrighted"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Galatea Team"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:clarelatin;2018-10-25T13:32:07Z;CLARE;Galatea Team;corpus linguistics;linguistics;Latin;written language;This corpus offers a continuum of different text types (registers) from written discourse. More precisely, it includes Latin texts from 20 different registers of written discourse including apology, biography, comedy, didactic, doctrinal, epic, epistolary, essay, fable, history, legislative, lyric, mythology, novel, oratory, philosophy, satire, tragedy.\n  The texts are imported from different Latin libraries on the Web.\n  The whole number of words contained in the corpus comprise ca. 19,5 Mio. The corpus is pre-annotated on several levels, which include information on tokens, lemmas, morpho-syntactic features (e.g. case, number, etc.), parts-of-speech, as well as and sentence boundaries. Tokenization, lemmatization, PoS tagging with TreeTagger (Schmid, 1994, 1995) using Gabrielle Bandolini's parameters and sentence boundary detection with CLTK (Kyle P. Johnson et al., 2014-2017).\n  The corpus is encoded in the CWB format (CWB, 2010) and can be queried with Corpus Query Processor (CQP) (Evert, 2005).;Universit\u00e4t des Saarlandes;Mercedes Garc\u00eda Ferrer;Mar\u00eda Teresa Cases Fandos;Maria Teresa Beltr\u00e1n Chabrera;Jos\u00e9 Manuel Mart\u00ednez Mart\u00ednez;2018;Collection;text/xml;clarind-uds:clarelatin;hdl:21.11119/0000-0001-614D-C;Augustana: https://www.hs-augsburg.de/~harsch/a_chron.html;Bibiloteca italiana: http://ww2.bibliotecaitaliana.it/exist/bibit/;Camena; https://www2.uni-mannheim.de/mateo/camenahtdocs/camena_e.html;Corpus corporum:  http://www.mlat.uzh.ch/MLS/index.php?lang=0;DBNL: http://www.dbnl.org/;Dante on-line: http://www.danteonline.it/italiano/opere_indice.htm;Esoteric archives: http://www.esotericarchives.com/esoteric.htm;Gitenberg: https://www.gitenberg.org/;Google Books: https://books.google.es/;Iesapos: https://iessapostol.educarex.es/latin/minerva/;Intratext: http://www.intratext.com/LATINA/;MDZ: https://www.digitale-sammlungen.de/;Narpan: http://www.narpan.net/;Perseus: http://perseus.uchicago.edu/latin.html;The Latin Library: http://www.thelatinlibrary.com/;UB: http://orbita.bib.ub.edu/llull/;Vaticanus: http://www.vatican.va/holy_father/index_sp.htm;Vicifons: https://la.wikisource.org/wiki/Pagina_prima;lat;Tagset: http://www.cis.uni-muenchen.de/~schmid/tools/TreeTagger/data/Lamap-Tagset.pdf;Spain;Copyrighted",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "aea743e5-431d-5ba4-ab06-15bfce38079a",
-    "notes": [
-        "This corpus offers a continuum of different text types (registers) from written discourse. More precisely, it includes Latin texts from 20 different registers of written discourse including apology, biography, comedy, didactic, doctrinal, epic, epistolary, essay, fable, history, legislative, lyric, mythology, novel, oratory, philosophy, satire, tragedy.\n  The texts are imported from different Latin libraries on the Web.\n  The whole number of words contained in the corpus comprise ca. 19,5 Mio. The corpus is pre-annotated on several levels, which include information on tokens, lemmas, morpho-syntactic features (e.g. case, number, etc.), parts-of-speech, as well as and sentence boundaries. Tokenization, lemmatization, PoS tagging with TreeTagger (Schmid, 1994, 1995) using Gabrielle Bandolini's parameters and sentence boundary detection with CLTK (Kyle P. Johnson et al., 2014-2017).\n  The corpus is encoded in the CWB format (CWB, 2010) and can be queried with Corpus Query Processor (CQP) (Evert, 2005)."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:clarelatin"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus linguistics"
-        },
-        {
-            "name": "linguistics"
-        },
-        {
-            "name": "Latin"
-        },
-        {
-            "name": "written language"
-        }
-    ],
-    "title": [
-        "CLARE"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/aebd297e-e63d-5d13-b44c-a16c6cc7f77f.json b/oaitestdata/clarin-oai_dc/SET_1/json/aebd297e-e63d-5d13-b44c-a16c6cc7f77f.json
deleted file mode 100644
index beae66da..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/aebd297e-e63d-5d13-b44c-a16c6cc7f77f.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "The National Library of Sweden"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/91",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/91"
-    ],
-    "PID": "http://hdl.handle.net/10794/91",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "The National Library of Sweden"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/91;2017-10-25T14:29:13Z;hdl_10794_1;hdl_10794_2;Blekingsposten 1880's (2015-04-08);Blekingsposten 1880-talet (2015-04-08);n/a, n/a;Swedish;News;A corpus with texts from Blekingeposten 1880\u20131884.;En korpus med texter fr\u00e5n Blekingeposten p\u00e5 1880-talet (1880\u20131884).;2015-04-08;corpus;http://hdl.handle.net/10794/91;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;http://creativecommons.org/licenses/by/4.0/;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;The National Library of Sweden;https://spraakbanken.gu.se/swe/resurs/kubhist-blekingsposten-1880",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "aebd297e-e63d-5d13-b44c-a16c6cc7f77f",
-    "notes": [
-        "A corpus with texts from Blekingeposten 1880\u20131884.",
-        "En korpus med texter fr\u00e5n Blekingeposten p\u00e5 1880-talet (1880\u20131884)."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/91"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "News"
-        }
-    ],
-    "title": [
-        "Blekingsposten 1880's (2015-04-08)",
-        "Blekingsposten 1880-talet (2015-04-08)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/aecc08a9-0591-56bb-86a8-c8393597e691.json b/oaitestdata/clarin-oai_dc/SET_1/json/aecc08a9-0591-56bb-86a8-c8393597e691.json
deleted file mode 100644
index 9439673f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/aecc08a9-0591-56bb-86a8-c8393597e691.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1040",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1040"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1040",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1040;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;L1 Acquisition Joost van de Weijer;Language Acquisition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1040;nld;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI319397%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "aecc08a9-0591-56bb-86a8-c8393597e691",
-    "notes": [
-        "Language Acquisition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1040"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "L1 Acquisition Joost van de Weijer"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/aee9ca5d-30bd-5cee-b648-80f32bcd97c6.json b/oaitestdata/clarin-oai_dc/SET_1/json/aee9ca5d-30bd-5cee-b648-80f32bcd97c6.json
deleted file mode 100644
index ec1f0691..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/aee9ca5d-30bd-5cee-b648-80f32bcd97c6.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3003",
-    "MetadataAccess": [
-        "oai:ota:oucs:3003"
-    ],
-    "PublicationTimestamp": "1606-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1606"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Middleton, Thomas, 1580-1627"
-    ],
-    "fulltext": "oai:ota:oucs:3003;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3003.xml;The revenger's tragedy;Middleton, Thomas, 1580-1627;not after: 1606;text_and_corpus_linguistics;English drama -- 17th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "aee9ca5d-30bd-5cee-b648-80f32bcd97c6",
-    "oai_identifier": [
-        "oai:ota:oucs:3003"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- th century"
-        }
-    ],
-    "title": [
-        "The revenger's tragedy"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3003.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/af0bb25e-5de0-5db3-8263-c4de51a40bad.json b/oaitestdata/clarin-oai_dc/SET_1/json/af0bb25e-5de0-5db3-8263-c4de51a40bad.json
deleted file mode 100644
index e02c476c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/af0bb25e-5de0-5db3-8263-c4de51a40bad.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5234",
-    "MetadataAccess": [
-        "oai:ota:oucs:5234"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Lennox, Charlotte, ca. 1729-1804."
-    ],
-    "fulltext": "oai:ota:oucs:5234;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5234.xml;Shakespear illustrated: or the novels and histories, on which the plays of Shakespear are founded, collected and translated from the original authors. With critical remarks. In two volumes. By the author of The female Quixote. [pt.2];Lennox, Charlotte, ca. 1729-1804.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "af0bb25e-5de0-5db3-8263-c4de51a40bad",
-    "oai_identifier": [
-        "oai:ota:oucs:5234"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Shakespear illustrated: or the novels and histories, on which the plays of Shakespear are founded, collected and translated from the original authors. With critical remarks. In two volumes. By the author of The female Quixote. [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5234.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/af0dc5d7-4f9c-5de1-b9d7-30cfa2ecc473.json b/oaitestdata/clarin-oai_dc/SET_1/json/af0dc5d7-4f9c-5de1-b9d7-30cfa2ecc473.json
deleted file mode 100644
index 025183f2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/af0dc5d7-4f9c-5de1-b9d7-30cfa2ecc473.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3575",
-    "MetadataAccess": [
-        "oai:ota:oucs:3575"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Sharp, Granville, 1735-1813."
-    ],
-    "fulltext": "oai:ota:oucs:3575;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3575.xml;Short sketch of temporary regulations: (until better shall be proposed) for the intended settlement on the grain coast of Africa, near Sierra Leona.;Sharp, Granville, 1735-1813.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "af0dc5d7-4f9c-5de1-b9d7-30cfa2ecc473",
-    "oai_identifier": [
-        "oai:ota:oucs:3575"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Short sketch of temporary regulations: (until better shall be proposed) for the intended settlement on the grain coast of Africa, near Sierra Leona."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3575.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/af2f9e70-b077-5132-8bf8-b090f5ffafa7.json b/oaitestdata/clarin-oai_dc/SET_1/json/af2f9e70-b077-5132-8bf8-b090f5ffafa7.json
deleted file mode 100644
index 9dea6b9d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/af2f9e70-b077-5132-8bf8-b090f5ffafa7.json
+++ /dev/null
@@ -1,135 +0,0 @@
-{
-    "Contact": [
-        "Technische Universit\u00e4t Darmstadt"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/x-gzip",
-        "downloadable_files_count: 56",
-        "text/plain"
-    ],
-    "Language": [
-        "Afrikaans",
-        "Arabic",
-        "Bengali",
-        "Bulgarian",
-        "Czech",
-        "Danish",
-        "German",
-        "Modern Greek (1453-)",
-        "English",
-        "Estonian",
-        "Persian",
-        "Finnish",
-        "French",
-        "Gujarati",
-        "Hebrew",
-        "Hindi",
-        "Croatian",
-        "Hungarian",
-        "Indonesian",
-        "Italian",
-        "Japanese",
-        "Kannada",
-        "Korean",
-        "Latvian",
-        "Lithuanian",
-        "Malayalam",
-        "Marathi",
-        "Macedonian",
-        "Nepali (macrolanguage)",
-        "Dutch",
-        "Norwegian",
-        "Polish",
-        "Portuguese",
-        "Romanian",
-        "Russian",
-        "Slovak",
-        "Slovenian",
-        "Somali",
-        "Spanish",
-        "Albanian",
-        "Swahili (macrolanguage)",
-        "Swedish",
-        "Tamil",
-        "Telugu",
-        "Tagalog",
-        "Thai",
-        "Turkish",
-        "Ukrainian",
-        "Undetermined",
-        "Urdu",
-        "Vietnamese",
-        "Chinese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2205",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2205"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2205",
-    "PublicationTimestamp": "2016-04-14T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Technische Universit\u00e4t Darmstadt"
-    ],
-    "RelatedIdentifier": [
-        "http://www.lrec-conf.org/proceedings/lrec2016/pdf/388_Paper.pdf"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)",
-        "PUB",
-        "http://creativecommons.org/licenses/by-nc-nd/4.0/"
-    ],
-    "author": [
-        "Habernal, Ivan",
-        "Gurevych, Iryna",
-        "Zayed, Omnia"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2205;2019-01-02T14:29:42Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;C4Corpus (CC BY-NC-ND part);Gurevych, Iryna;Habernal, Ivan;Zayed, Omnia;CommonCrawl;Creative Commons;Web corpus;Amazon Web Services;A large web corpus (over 10 billion tokens) licensed under CreativeCommons license family in 50+ languages that has been extracted from CommonCrawl, the largest publicly available general Web crawl to date with about 2 billion crawled URLs.;2016-04-14;corpus;http://hdl.handle.net/11372/LRT-2205;afr;ara;ben;bul;ces;dan;deu;ell;eng;est;fas;fin;fra;guj;heb;hin;hrv;hun;ind;ita;jpn;kan;kor;lav;lit;mal;mar;mkd;nep;nld;nor;pol;por;ron;rus;slk;slv;som;spa;sqi;swa;swe;tam;tel;tgl;tha;tur;ukr;und;urd;vie;zho;http://www.lrec-conf.org/proceedings/lrec2016/pdf/388_Paper.pdf;Creative Commons - Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0);PUB;http://creativecommons.org/licenses/by-nc-nd/4.0/;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;text/plain;downloadable_files_count: 56;Technische Universit\u00e4t Darmstadt;https://dkpro.github.io/dkpro-c4corpus/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "af2f9e70-b077-5132-8bf8-b090f5ffafa7",
-    "notes": [
-        "A large web corpus (over 10 billion tokens) licensed under CreativeCommons license family in 50+ languages that has been extracted from CommonCrawl, the largest publicly available general Web crawl to date with about 2 billion crawled URLs."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2205"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "CommonCrawl"
-        },
-        {
-            "name": "Creative Commons"
-        },
-        {
-            "name": "Web corpus"
-        },
-        {
-            "name": "Amazon Web Services"
-        }
-    ],
-    "title": [
-        "C4Corpus (CC BY-NC-ND part)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/af34617a-0700-5d90-bbae-704138ab4b2d.json b/oaitestdata/clarin-oai_dc/SET_1/json/af34617a-0700-5d90-bbae-704138ab4b2d.json
deleted file mode 100644
index e611fe5f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/af34617a-0700-5d90-bbae-704138ab4b2d.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3213",
-    "MetadataAccess": [
-        "oai:ota:oucs:3213"
-    ],
-    "PublicationTimestamp": "1890-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1890"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Morris, William, 1834-1896"
-    ],
-    "fulltext": "oai:ota:oucs:3213;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3213.xml;News from nowhere, or, An epoch of rest : being some chapters from a utopian romance;Morris, William, 1834-1896;not after: 1890;text_and_corpus_linguistics;Fiction -- Great Britain -- 19th century;Fantasy literature -- Great Britain -- 19th century;Utopian literature -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "af34617a-0700-5d90-bbae-704138ab4b2d",
-    "oai_identifier": [
-        "oai:ota:oucs:3213"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- Great Britain -- th century"
-        },
-        {
-            "name": "Fantasy literature -- Great Britain -- th century"
-        },
-        {
-            "name": "Utopian literature -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "News from nowhere, or, An epoch of rest : being some chapters from a utopian romance"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3213.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/af49cb61-7f61-5e4e-adc2-028712ab449a.json b/oaitestdata/clarin-oai_dc/SET_1/json/af49cb61-7f61-5e4e-adc2-028712ab449a.json
deleted file mode 100644
index 9483b0f2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/af49cb61-7f61-5e4e-adc2-028712ab449a.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Burnard, Lou"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 59 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0580",
-    "MetadataAccess": [
-        "oai:ota:oucs:0580"
-    ],
-    "PublicationTimestamp": "1714-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1714"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pope, Alexander, 1688-1744"
-    ],
-    "fulltext": "oai:ota:oucs:0580;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0580.xml;The rape of the Lock : an heroi-comical poem in five canto's / Alexander Pope;Pope, Alexander, 1688-1744;1714;text_and_corpus_linguistics;English poetry -- 18th century;Oxford Text Archive, University of Oxford;Burnard, Lou;text/sgml;(1 file : ca. 59 KB);Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "af49cb61-7f61-5e4e-adc2-028712ab449a",
-    "oai_identifier": [
-        "oai:ota:oucs:0580"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English poetry -- th century"
-        }
-    ],
-    "title": [
-        "The rape of the Lock : an heroi-comical poem in five canto's / Alexander Pope"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0580.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/af54f84c-6ffa-5bec-8369-a99df3e4e629.json b/oaitestdata/clarin-oai_dc/SET_1/json/af54f84c-6ffa-5bec-8369-a99df3e4e629.json
deleted file mode 100644
index 719e5dab..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/af54f84c-6ffa-5bec-8369-a99df3e4e629.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4237",
-    "MetadataAccess": [
-        "oai:ota:oucs:4237"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Burke, Edmund, 1729-1797."
-    ],
-    "fulltext": "oai:ota:oucs:4237;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4237.xml;Two letters from Mr. Burke to gentlemen in the city of Bristol: on the bills depending in parliament relative to the trade of Ireland.;Burke, Edmund, 1729-1797.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "af54f84c-6ffa-5bec-8369-a99df3e4e629",
-    "oai_identifier": [
-        "oai:ota:oucs:4237"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Two letters from Mr. Burke to gentlemen in the city of Bristol: on the bills depending in parliament relative to the trade of Ireland."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4237.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/af8c5d5a-e7e4-5b16-94c4-87ef9df0a49b.json b/oaitestdata/clarin-oai_dc/SET_1/json/af8c5d5a-e7e4-5b16-94c4-87ef9df0a49b.json
deleted file mode 100644
index 9f389211..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/af8c5d5a-e7e4-5b16-94c4-87ef9df0a49b.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/gzip"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/33",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/33"
-    ],
-    "PID": "http://hdl.handle.net/10794/33",
-    "PublicationTimestamp": "2012-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/33;2017-10-27T14:27:08Z;hdl_10794_1;hdl_10794_2;Parole+ (2017-10-16);Parole+ (2017-10-16);n/a, n/a;Swedish;PAROLE;The Swedish PAROLE Lexicon - A language technology resource with access to syntactic information, connected to SALDO senses.;Svenskt PAROLE-lexikon - En spr\u00e5kteknologisk resurs med syntaktisk information, kopplade till betydelser i SALDO.;2012-05-30;lexicalConceptualResource;http://hdl.handle.net/10794/33;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;text/plain; charset=utf-8;application/gzip;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/parolelexplus",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "af8c5d5a-e7e4-5b16-94c4-87ef9df0a49b",
-    "notes": [
-        "The Swedish PAROLE Lexicon - A language technology resource with access to syntactic information, connected to SALDO senses.",
-        "Svenskt PAROLE-lexikon - En spr\u00e5kteknologisk resurs med syntaktisk information, kopplade till betydelser i SALDO."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/33"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "PAROLE"
-        }
-    ],
-    "title": [
-        "Parole+ (2017-10-16)",
-        "Parole+ (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/af92a84e-ef9d-567b-bdbb-d1cddce7a135.json b/oaitestdata/clarin-oai_dc/SET_1/json/af92a84e-ef9d-567b-bdbb-d1cddce7a135.json
deleted file mode 100644
index 07d26377..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/af92a84e-ef9d-567b-bdbb-d1cddce7a135.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3792",
-    "MetadataAccess": [
-        "oai:ota:oucs:3792"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Sterne, Laurence, 1713-1768."
-    ],
-    "fulltext": "oai:ota:oucs:3792;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3792.xml;The life and opinions of Tristram Shandy, gentleman: ... [pt.2];Life and opinions of Tristram Shandy, gentleman;Sterne, Laurence, 1713-1768.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "af92a84e-ef9d-567b-bdbb-d1cddce7a135",
-    "oai_identifier": [
-        "oai:ota:oucs:3792"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The life and opinions of Tristram Shandy, gentleman: ... [pt.2]",
-        "Life and opinions of Tristram Shandy, gentleman"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3792.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/af935b88-6227-5772-be8b-a4937cfd0243.json b/oaitestdata/clarin-oai_dc/SET_1/json/af935b88-6227-5772-be8b-a4937cfd0243.json
deleted file mode 100644
index 487d7ff3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/af935b88-6227-5772-be8b-a4937cfd0243.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Societatis Jesu"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-7974",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-7974"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D34-5",
-    "PublicationTimestamp": "1766-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1766"
-    ],
-    "Publisher": [
-        "Drukarnia Societatis Jesu"
-    ],
-    "RelatedIdentifier": [
-        "http://pbc.biaman.pl/Content/7947"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "author": [
-        "Stryjkowski, Maciej (ca 1547-ca 1593)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-7974;2019-03-01T17:32:39Z;Kronika Macieja Stryjkowskiego niegdy\u015b w Kr\u00f3lewcu drukowana.;Stryjkowski, Maciej (ca 1547-ca 1593);Litwa - historia;ilo\u015b\u0107 skan\u00f3w: 812 ; sygn. St- 327;Drukarnia Societatis Jesu;1766;starodruk;application/xml;clarind-uds:poldilemma-7974;hdl:11858/00-246C-0000-0023-8D34-5;pol;lat;http://pbc.biaman.pl/Content/7947;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "af935b88-6227-5772-be8b-a4937cfd0243",
-    "notes": [
-        "ilo\u015b\u0107 skan\u00f3w: 812 ; sygn. St- 327"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-7974"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Litwa - historia"
-        }
-    ],
-    "title": [
-        "Kronika Macieja Stryjkowskiego niegdy\u015b w Kr\u00f3lewcu drukowana."
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/af96b147-7128-5ca6-8a8f-69b4b9a49920.json b/oaitestdata/clarin-oai_dc/SET_1/json/af96b147-7128-5ca6-8a8f-69b4b9a49920.json
deleted file mode 100644
index 75aa197e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/af96b147-7128-5ca6-8a8f-69b4b9a49920.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contributor": [
-        "\u0160im\u0117nait\u0117, Dr. Zita"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Lithuanian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-479",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-479"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-479",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Lithuania"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-479;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;The cart file collection of Dictionary of the Lithuanian Language;\u0160im\u0117nait\u0117, Dr. Zita;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-479;lit;downloadable_files_count: 0;Lithuania;http://www.lkz.lt",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "af96b147-7128-5ca6-8a8f-69b4b9a49920",
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-479"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "The cart file collection of Dictionary of the Lithuanian Language"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/afb4fc08-94c0-511b-8b88-619de2cbd654.json b/oaitestdata/clarin-oai_dc/SET_1/json/afb4fc08-94c0-511b-8b88-619de2cbd654.json
deleted file mode 100644
index 42cb1852..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/afb4fc08-94c0-511b-8b88-619de2cbd654.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "between 512 KB and 1 MB "
-    ],
-    "Language": [
-        "French"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0196",
-    "MetadataAccess": [
-        "oai:ota:oucs:0196"
-    ],
-    "PublicationTimestamp": "1839-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1839"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Stendhal,  1783-1842"
-    ],
-    "fulltext": "oai:ota:oucs:0196;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0196.xml; La Chartreuse de Parme / compiled by Monique Jacquemin;Stendhal,  1783-1842;1839;text_and_corpus_linguistics;Novels -- France -- 19th century;fra;Oxford Text Archive, University of Oxford;between 512 KB and 1 MB ;Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "afb4fc08-94c0-511b-8b88-619de2cbd654",
-    "oai_identifier": [
-        "oai:ota:oucs:0196"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Novels -- France -- th century"
-        }
-    ],
-    "title": [
-        " La Chartreuse de Parme / compiled by Monique Jacquemin"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0196.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/afd80ff7-2ba5-5378-b7b9-e8a3a86c378e.json b/oaitestdata/clarin-oai_dc/SET_1/json/afd80ff7-2ba5-5378-b7b9-e8a3a86c378e.json
deleted file mode 100644
index 43b408a3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/afd80ff7-2ba5-5378-b7b9-e8a3a86c378e.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Andrzeja Piotrkowczyka"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-105661",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-105661"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CD4-7",
-    "PublicationTimestamp": "1639-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1639"
-    ],
-    "Publisher": [
-        "Drukarnia Andrzeja Piotrkowczyka"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/105661",
-        "oai:jbc.bj.uj.edu.pl:publication:113006"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1601/1700"
-    ],
-    "TempCoverageBegin": 50506804799,
-    "TempCoverageEnd": 50506804799,
-    "TemporalCoverage": " point in time : 1601-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1601-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1601-07-01T11:59:59Z",
-    "author": [
-        "Mijakowski, Jacek (1597-1647)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-105661;2019-02-28T17:53:04Z;Znaczna W Cnot\u0119 Matrona [...] Anna z Rv\u015bce Lvbomirska, Hrabina na Wisniczv, Kasztelanka Woynicka [...] Dnia 3. Lutego W Krakowie v \u015bwi\u0119tey Troyce schowana, A przy Pogrzebie;Mijakowski, Jacek (1597-1647);starodruki 17\u00a0w.;Lubomirski, Stanis\u0142aw (1583-1649). Adr. ded.;Koniecpolski, Stanis\u0142aw (ca 1592-1646). Adr. ded.;Koniecpolska, Krystyna ( -1645). Adr. ded.;Drukarnia Andrzeja Piotrkowczyka;[1639];starodruk;application/xml;clarind-uds:poldilemma-105661;hdl:11858/00-246C-0000-0023-8CD4-7;Biblioteka Jagiello\u0144ska, BJ St. Dr. 17404 I;pol;http://jbc.bj.uj.edu.pl/Content/105661;oai:jbc.bj.uj.edu.pl:publication:113006;1601/1700;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "afd80ff7-2ba5-5378-b7b9-e8a3a86c378e",
-    "notes": [
-        "Lubomirski, Stanis\u0142aw (1583-1649). Adr. ded.",
-        "Koniecpolski, Stanis\u0142aw (ca 1592-1646). Adr. ded.",
-        "Koniecpolska, Krystyna ( -1645). Adr. ded."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-105661"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Znaczna W Cnot\u0119 Matrona [...] Anna z Rv\u015bce Lvbomirska, Hrabina na Wisniczv, Kasztelanka Woynicka [...] Dnia 3. Lutego W Krakowie v \u015bwi\u0119tey Troyce schowana, A przy Pogrzebie"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b00f9b66-850a-5eca-b1a2-bd92153b6718.json b/oaitestdata/clarin-oai_dc/SET_1/json/b00f9b66-850a-5eca-b1a2-bd92153b6718.json
deleted file mode 100644
index d49dcabd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b00f9b66-850a-5eca-b1a2-bd92153b6718.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Polish-Japanese Academy of Information Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/317",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/317"
-    ],
-    "PID": "http://hdl.handle.net/11321/317",
-    "PublicationTimestamp": "2016-07-31T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Polish-Japanese Academy of Information Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Brocki, \u0141ukasz",
-        "Kor\u017einek, Danijel"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/317;2016-07-31T15:51:16Z;hdl_11321_3;hdl_11321_4;Cyfry;Kor\u017einek, Danijel;Brocki, \u0141ukasz;speech corpus;A small spoken digits corpus in polish. Contains 488 recordings of 25 speakers reading 20 digits (0-9) each. Amounts to around 76 minutes of recordings. Split into train (~72%), valid (~8%) and test (~20%) sets.;2016-07-31;corpus;http://hdl.handle.net/11321/317;pol;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;Polish-Japanese Academy of Information Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b00f9b66-850a-5eca-b1a2-bd92153b6718",
-    "notes": [
-        "A small spoken digits corpus in polish. Contains 488 recordings of 25 speakers reading 20 digits (0-9) each. Amounts to around 76 minutes of recordings. Split into train (~72%), valid (~8%) and test (~20%) sets."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/317"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech corpus"
-        }
-    ],
-    "title": [
-        "Cyfry"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b0361946-30c5-5d57-b2b8-a045fe6d9c67.json b/oaitestdata/clarin-oai_dc/SET_1/json/b0361946-30c5-5d57-b2b8-a045fe6d9c67.json
deleted file mode 100644
index 93cbd264..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b0361946-30c5-5d57-b2b8-a045fe6d9c67.json
+++ /dev/null
@@ -1,108 +0,0 @@
-{
-    "Contact": [
-        "Charles University"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "application/pdf",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-95B1-E",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-95B1-E"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-95B1-E",
-    "PublicationTimestamp": "2014-05-26T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-162"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0)",
-        "http://creativecommons.org/licenses/by-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Jane\u0161, Petr",
-        "\u0160tindlov\u00e1, Barbora",
-        "Rosen, Alexandr",
-        "Hrdli\u010dka, Milan",
-        "\u0160ormov\u00e1, Kate\u0159ina",
-        "Toufarov\u00e1, Dagmar",
-        "Pol\u00e1\u010dkov\u00e1, Marie",
-        "Richter, Michal",
-        "Hrdli\u010dkov\u00e1, Tereza",
-        "\u0160ebesta, Karel",
-        "Pierscieniak, Piotr",
-        "Lund\u00e1kov\u00e1, Kate\u0159ina",
-        "Bed\u0159ichov\u00e1, Zuzanna",
-        "Hana, Ji\u0159\u00ed",
-        "Jel\u00ednek, Tom\u00e1\u0161",
-        "\u0160kodov\u00e1, Svatava",
-        "Skoumalov\u00e1, Hana",
-        "Straka, Milan",
-        "Sl\u00e1dek, \u0160imon",
-        "Petkevi\u010d, Vladim\u00edr"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-95B1-E;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;AKCES 5 (CzeSL-SGT);\u0160ebesta, Karel;Bed\u0159ichov\u00e1, Zuzanna;\u0160ormov\u00e1, Kate\u0159ina;\u0160tindlov\u00e1, Barbora;Hrdli\u010dka, Milan;Hrdli\u010dkov\u00e1, Tereza;Hana, Ji\u0159\u00ed;Petkevi\u010d, Vladim\u00edr;Jel\u00ednek, Tom\u00e1\u0161;\u0160kodov\u00e1, Svatava;Pol\u00e1\u010dkov\u00e1, Marie;Jane\u0161, Petr;Lund\u00e1kov\u00e1, Kate\u0159ina;Skoumalov\u00e1, Hana;Sl\u00e1dek, \u0160imon;Pierscieniak, Piotr;Toufarov\u00e1, Dagmar;Richter, Michal;Straka, Milan;Rosen, Alexandr;learner corpus;Czech as a foreign language;Czech language acquisition corpora;AKCES;non-native speakers;second language aquisition;Essays written by non-native learners of Czech, a part of AKCES/CLAC \u2013 Czech Language Acquisition Corpora. CzeSL-SGT stands for Czech as a Second Language with Spelling, Grammar and Tags. Extends the \u201cforeign\u201d (ciz) part of AKCES 3 (CzeSL-plain) by texts collected in 2013. Original forms and automatic corrections are tagged, lemmatized and assigned erros labels. Most texts have metadata attributes (30 items) about the author and the text.;2014-05-26;corpus;http://hdl.handle.net/11858/00-097C-0000-0023-95B1-E;ces;http://hdl.handle.net/11234/1-162;Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0);http://creativecommons.org/licenses/by-sa/3.0/;PUB;application/zip;application/pdf;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University;http://utkl.ff.cuni.cz/learncorp/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b0361946-30c5-5d57-b2b8-a045fe6d9c67",
-    "notes": [
-        "Essays written by non-native learners of Czech, a part of AKCES/CLAC \u2013 Czech Language Acquisition Corpora. CzeSL-SGT stands for Czech as a Second Language with Spelling, Grammar and Tags. Extends the \u201cforeign\u201d (ciz) part of AKCES 3 (CzeSL-plain) by texts collected in 2013. Original forms and automatic corrections are tagged, lemmatized and assigned erros labels. Most texts have metadata attributes (30 items) about the author and the text."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-95B1-E"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "learner corpus"
-        },
-        {
-            "name": "Czech foreign language"
-        },
-        {
-            "name": "Czech language acquisition corpora"
-        },
-        {
-            "name": "AKCES"
-        },
-        {
-            "name": "non-native speakers"
-        },
-        {
-            "name": "second language aquisition"
-        }
-    ],
-    "title": [
-        "AKCES 5 (CzeSL-SGT)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b071df12-8806-512c-8611-b6f984bc5349.json b/oaitestdata/clarin-oai_dc/SET_1/json/b071df12-8806-512c-8611-b6f984bc5349.json
deleted file mode 100644
index bf4241d3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b071df12-8806-512c-8611-b6f984bc5349.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 44.1 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2153",
-    "MetadataAccess": [
-        "oai:ota:oucs:2153"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gaskell, Elizabeth Cleghorn, 1810-1865"
-    ],
-    "fulltext": "oai:ota:oucs:2153;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/2153.xml;Hand and heart / by Elizabeth Gaskell;Gaskell, Elizabeth Cleghorn, 1810-1865;text_and_corpus_linguistics;Fiction -- Great Britain -- 19th century;Short stories -- Great Britain -- 19th century;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 44.1 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b071df12-8806-512c-8611-b6f984bc5349",
-    "oai_identifier": [
-        "oai:ota:oucs:2153"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- Great Britain -- th century"
-        },
-        {
-            "name": "Short stories -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Hand and heart / by Elizabeth Gaskell"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2153.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b0aa8da1-e895-554f-83e4-d4ebc93db422.json b/oaitestdata/clarin-oai_dc/SET_1/json/b0aa8da1-e895-554f-83e4-d4ebc93db422.json
deleted file mode 100644
index 665fcfc6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b0aa8da1-e895-554f-83e4-d4ebc93db422.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/xml",
-        "downloadable_files_count: 3",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/580",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/580"
-    ],
-    "PID": "http://hdl.handle.net/11321/580",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Ogrodniczuk, Maciej",
-        "Nito\u0144, Bart\u0142omiej"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/580;2018-07-26T15:03:44Z;hdl_11321_3;hdl_11321_4;Knowledge base of Polish conventionalized periphrastic nominal expressions;Nito\u0144, Bart\u0142omiej;Ogrodniczuk, Maciej;knowledge base;periphrastic nominal expressions;The resource includes free Periphraser export with a knowledge base of Polish conventionalized periphrastic nominal expressions (i.e. phrases headed by a noun) together with their textually attested realizations. For instance, the database entry for the phrase ,,Robert Lewandowski'' in the referred resource will include the phrase ,,the Polish international'' while ,,pediatrics'' will be featured as ,,medical care for children''. \r\n\r\nExport is available in two formats provided by Periphraser - XML and CSV. Associated files include a free version of data (available on the CC BY-SA 4.0 License). In case you are interested in full (authenticated) export of Polish periphrastic data please contact resource contact person.;2018;lexicalConceptualResource;http://hdl.handle.net/11321/580;pol;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;text/xml;downloadable_files_count: 3;Institute of Computer Science, Polish Academy of Sciences;http://zil.ipipan.waw.pl/Periphraser",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b0aa8da1-e895-554f-83e4-d4ebc93db422",
-    "notes": [
-        "The resource includes free Periphraser export with a knowledge base of Polish conventionalized periphrastic nominal expressions (i.e. phrases headed by a noun) together with their textually attested realizations. For instance, the database entry for the phrase ,,Robert Lewandowski'' in the referred resource will include the phrase ,,the Polish international'' while ,,pediatrics'' will be featured as ,,medical care for children''. \r\n\r\nExport is available in two formats provided by Periphraser - XML and CSV. Associated files include a free version of data (available on the CC BY-SA 4.0 License). In case you are interested in full (authenticated) export of Polish periphrastic data please contact resource contact person."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/580"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "knowledge base"
-        },
-        {
-            "name": "periphrastic nominal expressions"
-        }
-    ],
-    "title": [
-        "Knowledge base of Polish conventionalized periphrastic nominal expressions"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b0ae5ef8-7168-5c9b-9ebd-285ecba75f98.json b/oaitestdata/clarin-oai_dc/SET_1/json/b0ae5ef8-7168-5c9b-9ebd-285ecba75f98.json
deleted file mode 100644
index 6f026669..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b0ae5ef8-7168-5c9b-9ebd-285ecba75f98.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Polish-Japanese Academy of Information Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 4",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/236",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/236"
-    ],
-    "PID": "http://hdl.handle.net/11321/236",
-    "PublicationTimestamp": "2015-11-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Polish-Japanese Academy of Information Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Jankowska-Lorek, Kamila",
-        "Marasek, Krzysztof",
-        "Brocki, \u0141ukasz",
-        "Kor\u017einek, Danijel"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/236;2015-12-20T13:04:41Z;hdl_11321_3;hdl_11321_4;Clarin-PL Studio Corpus (EMU);Marasek, Krzysztof;Kor\u017einek, Danijel;Brocki, \u0141ukasz;Jankowska-Lorek, Kamila;speech corpus;speech prosody;Polish speech corpus of read speech recorded in a studio. Contains many speakers, each reading a few dozen different sentences and a list of words with rare phonemes. Useful for analyzing modern Polish pronounciation.;2015-11-01;corpus;http://hdl.handle.net/11321/236;pol;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 4;Polish-Japanese Academy of Information Technology;http://mowa.clarin-pl.eu/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b0ae5ef8-7168-5c9b-9ebd-285ecba75f98",
-    "notes": [
-        "Polish speech corpus of read speech recorded in a studio. Contains many speakers, each reading a few dozen different sentences and a list of words with rare phonemes. Useful for analyzing modern Polish pronounciation."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/236"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech corpus"
-        },
-        {
-            "name": "speech prosody"
-        }
-    ],
-    "title": [
-        "Clarin-PL Studio Corpus (EMU)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b0aebc58-ebcf-56d8-b852-a1c739be720d.json b/oaitestdata/clarin-oai_dc/SET_1/json/b0aebc58-ebcf-56d8-b852-a1c739be720d.json
deleted file mode 100644
index 979266eb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b0aebc58-ebcf-56d8-b852-a1c739be720d.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4630",
-    "MetadataAccess": [
-        "oai:ota:oucs:4630"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Disraeli, Isaac, 1766-1848."
-    ],
-    "fulltext": "oai:ota:oucs:4630;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4630.xml;Vaurien: or, sketches of the times: exhibiting views of the philosophies, religions, politics, literature, and manners of the age. In two volumes. ... [pt.2];Disraeli, Isaac, 1766-1848.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b0aebc58-ebcf-56d8-b852-a1c739be720d",
-    "oai_identifier": [
-        "oai:ota:oucs:4630"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Vaurien: or, sketches of the times: exhibiting views of the philosophies, religions, politics, literature, and manners of the age. In two volumes. ... [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4630.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b0cac485-a25a-5cb8-8071-a3279baf81dc.json b/oaitestdata/clarin-oai_dc/SET_1/json/b0cac485-a25a-5cb8-8071-a3279baf81dc.json
deleted file mode 100644
index 85524722..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b0cac485-a25a-5cb8-8071-a3279baf81dc.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1001",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1001"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1001",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1001;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LAC Zapotec and Chatino Survey;Language and Cognition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1001;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI606894%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b0cac485-a25a-5cb8-8071-a3279baf81dc",
-    "notes": [
-        "Language and Cognition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1001"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LAC Zapotec and Chatino Survey"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b0eb2246-f9d2-5d2d-81b7-549eddff2651.json b/oaitestdata/clarin-oai_dc/SET_1/json/b0eb2246-f9d2-5d2d-81b7-549eddff2651.json
deleted file mode 100644
index dcf56f61..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b0eb2246-f9d2-5d2d-81b7-549eddff2651.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Eryk Cichocki"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
-    ],
-    "Language": [],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/491",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/491"
-    ],
-    "PID": "http://hdl.handle.net/11321/491",
-    "PublicationTimestamp": "2018-06-19T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Eryk Cichocki"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Super Cool License",
-        "http://www.google.com",
-        "ACA"
-    ],
-    "author": [
-        "Cichocki, Eryk"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/491;2018-06-19T11:18:43Z;hdl_11321_3;hdl_11321_4;eksperyment;Cichocki, Eryk;warsztaty politechnika uniwersytet;projekt;2018-06-19;corpus;http://hdl.handle.net/11321/491;pso;Super Cool License;http://www.google.com;ACA;text/plain; charset=utf-8;application/vnd.openxmlformats-officedocument.wordprocessingml.document;downloadable_files_count: 1;Eryk Cichocki",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b0eb2246-f9d2-5d2d-81b7-549eddff2651",
-    "notes": [
-        "projekt"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/491"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "warsztaty politechnika uniwersytet"
-        }
-    ],
-    "title": [
-        "eksperyment"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b0ef2e7f-978d-554a-a099-bd6ba310f126.json b/oaitestdata/clarin-oai_dc/SET_1/json/b0ef2e7f-978d-554a-a099-bd6ba310f126.json
deleted file mode 100644
index 1e79a691..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b0ef2e7f-978d-554a-a099-bd6ba310f126.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Center for Sprogteknologi,  University of Copenhagen"
-    ],
-    "Contributor": [
-        "Jongejan, Bart"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Danish",
-        "Dutch",
-        "English",
-        "German",
-        "Modern Greek (1453-)",
-        "Icelandic",
-        "Norwegian",
-        "Russian",
-        "Slovenian",
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1183",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1183"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1183",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Center for Sprogteknologi,  University of Copenhagen"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Denmark"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1183;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;CST's lemmatiser;Jongejan, Bart;1) Fully automatic rule based lemmatization of inflected languages 2) Fully automatic training of lemmatization rules based on full form-lemma list;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1183;dan;nld;eng;deu;ell;isl;nor;rus;slv;swe;downloadable_files_count: 0;Denmark;Center for Sprogteknologi,  University of Copenhagen;http://cst.dk/download/uk/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b0ef2e7f-978d-554a-a099-bd6ba310f126",
-    "notes": [
-        "1) Fully automatic rule based lemmatization of inflected languages 2) Fully automatic training of lemmatization rules based on full form-lemma list"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1183"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "CST's lemmatiser"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b122adb1-4c58-506e-b59a-79d5388e9ece.json b/oaitestdata/clarin-oai_dc/SET_1/json/b122adb1-4c58-506e-b59a-79d5388e9ece.json
deleted file mode 100644
index 5f2a8968..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b122adb1-4c58-506e-b59a-79d5388e9ece.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "University of West Bohemia, Department of Cybernetics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "audio/x-wav",
-        "text/xml",
-        "downloadable_files_count: 32",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-000D-EC98-3",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-000D-EC98-3"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-000D-EC98-3",
-    "PublicationTimestamp": "2013-01-04T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "University of West Bohemia, Department of Cybernetics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0)",
-        "http://creativecommons.org/licenses/by-nc/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Pra\u017e\u00e1k, Ale\u0161",
-        "\u0160m\u00eddl, Lubo\u0161"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-000D-EC98-3;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;OVM \u2013 Ot\u00e1zky V\u00e1clava Moravce;\u0160m\u00eddl, Lubo\u0161;Pra\u017e\u00e1k, Ale\u0161;speech corpus;acoustic model;speaker identification;speaker verification;The corpus consists of transcribed recordings from the Czech political discussion broadcast \u201cOt\u00e1zky V\u00e1clava Moravce\u201c. It contains 35 hours of speech and corresponding word-by-word transcriptions, including the transcription of some non-speech events. Speakers\u2019 names are also assigned to corresponding segments. The resulting corpus is suitable for both acoustic model training for ASR purposes and training of speaker identification and/or verification systems. The archive contains 16 sound files (WAV PCM, 16-bit, 48 kHz, mono) and transcriptions in XML-based standard Transcriber format (http://trans.sourceforge.net);2013-01-04;corpus;ZCU_CZ_OVM;http://hdl.handle.net/11858/00-097C-0000-000D-EC98-3;ces;Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0);http://creativecommons.org/licenses/by-nc/3.0/;PUB;text/xml;audio/x-wav;text/xml;audio/x-wav;text/xml;audio/x-wav;text/xml;audio/x-wav;text/xml;audio/x-wav;text/xml;audio/x-wav;text/xml;audio/x-wav;text/xml;audio/x-wav;text/xml;audio/x-wav;text/xml;audio/x-wav;text/xml;audio/x-wav;text/xml;audio/x-wav;text/xml;audio/x-wav;text/xml;audio/x-wav;text/xml;audio/x-wav;text/xml;audio/x-wav;text/plain; charset=utf-8;downloadable_files_count: 32;University of West Bohemia, Department of Cybernetics",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b122adb1-4c58-506e-b59a-79d5388e9ece",
-    "notes": [
-        "The corpus consists of transcribed recordings from the Czech political discussion broadcast \u201cOt\u00e1zky V\u00e1clava Moravce\u201c. It contains 35 hours of speech and corresponding word-by-word transcriptions, including the transcription of some non-speech events. Speakers\u2019 names are also assigned to corresponding segments. The resulting corpus is suitable for both acoustic model training for ASR purposes and training of speaker identification and/or verification systems. The archive contains 16 sound files (WAV PCM, 16-bit, 48 kHz, mono) and transcriptions in XML-based standard Transcriber format (http://trans.sourceforge.net)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-000D-EC98-3"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech corpus"
-        },
-        {
-            "name": "acoustic model"
-        },
-        {
-            "name": "speaker identification"
-        },
-        {
-            "name": "speaker verification"
-        }
-    ],
-    "title": [
-        "OVM \u2013 Ot\u00e1zky V\u00e1clava Moravce"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b165d658-f004-5be5-a421-6cdb271b9eef.json b/oaitestdata/clarin-oai_dc/SET_1/json/b165d658-f004-5be5-a421-6cdb271b9eef.json
deleted file mode 100644
index 1961e9ac..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b165d658-f004-5be5-a421-6cdb271b9eef.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "s.n."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-158367",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-158367"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CE4-3",
-    "PublicationTimestamp": "1605-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1605"
-    ],
-    "Publisher": [
-        "s.n."
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/158367",
-        "oai:jbc.bj.uj.edu.pl:publication:166689"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1601/1700"
-    ],
-    "TempCoverageBegin": 50506804799,
-    "TempCoverageEnd": 50506804799,
-    "TemporalCoverage": " point in time : 1601-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1601-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1601-07-01T11:59:59Z",
-    "author": [
-        "\u0141aszcz, Marcin (1551-1615)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-158367;2019-02-28T18:37:39Z;Okvlary Wtore, Na ciemne y slepe oczy Ministr\u00f3w;\u0141aszcz, Marcin (1551-1615);starodruki 17\u00a0w.;s.n.;1605;starodruk;application/xml;clarind-uds:poldilemma-158367;hdl:11858/00-246C-0000-0023-8CE4-3;Biblioteka Jagiello\u0144ska, BJ St. Dr. 36931 I;pol;lat;http://jbc.bj.uj.edu.pl/Content/158367;oai:jbc.bj.uj.edu.pl:publication:166689;1601/1700;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b165d658-f004-5be5-a421-6cdb271b9eef",
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-158367"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Okvlary Wtore, Na ciemne y slepe oczy Ministr\u00f3w"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b17094af-4bd3-50db-9271-e2729d5ecb7b.json b/oaitestdata/clarin-oai_dc/SET_1/json/b17094af-4bd3-50db-9271-e2729d5ecb7b.json
deleted file mode 100644
index be026044..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b17094af-4bd3-50db-9271-e2729d5ecb7b.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/96",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/96"
-    ],
-    "PID": "http://hdl.handle.net/10794/96",
-    "PublicationTimestamp": "2013-03-06T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/96;2017-10-25T11:44:21Z;hdl_10794_1;hdl_10794_2;Blog mix 2002 (2017-02-17);Bloggmix 2002 (2017-02-17);n/a, n/a;Swedish;Blog;The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.;Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat.;2013-03-06;corpus;http://hdl.handle.net/10794/96;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;http://creativecommons.org/licenses/by/4.0/;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/bloggmix2002",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b17094af-4bd3-50db-9271-e2729d5ecb7b",
-    "notes": [
-        "The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.",
-        "Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/96"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Blog"
-        }
-    ],
-    "title": [
-        "Blog mix 2002 (2017-02-17)",
-        "Bloggmix 2002 (2017-02-17)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b170c1f0-1bde-5181-b200-04932b69c7e9.json b/oaitestdata/clarin-oai_dc/SET_1/json/b170c1f0-1bde-5181-b200-04932b69c7e9.json
deleted file mode 100644
index d141bd9e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b170c1f0-1bde-5181-b200-04932b69c7e9.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish",
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/64",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/64"
-    ],
-    "PID": "http://hdl.handle.net/10794/64",
-    "PublicationTimestamp": "2015-04-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/64;2017-10-31T15:14:54Z;hdl_10794_1;hdl_10794_2;ASPAC \u2013 Swedish-Polish (2017-10-16);ASPAC \u2013 svenska-polska (2017-10-16);n/a, n/a;ASPAC;Parallel;Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.;Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat.;2015-04-16;corpus;http://hdl.handle.net/10794/64;swe;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/octet-stream;application/gzip;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/aspacsvpl",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b170c1f0-1bde-5181-b200-04932b69c7e9",
-    "notes": [
-        "Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.",
-        "Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/64"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ASPAC"
-        },
-        {
-            "name": "Parallel"
-        }
-    ],
-    "title": [
-        "ASPAC \u2013 Swedish-Polish (2017-10-16)",
-        "ASPAC \u2013 svenska-polska (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b170e27d-702d-5e88-aadb-8d73b47ac26b.json b/oaitestdata/clarin-oai_dc/SET_1/json/b170e27d-702d-5e88-aadb-8d73b47ac26b.json
deleted file mode 100644
index 7e31564b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b170e27d-702d-5e88-aadb-8d73b47ac26b.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4261",
-    "MetadataAccess": [
-        "oai:ota:oucs:4261"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "O'Keeffe, John, 1747-1833."
-    ],
-    "fulltext": "oai:ota:oucs:4261;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4261.xml;Sprigs of laurel: a comic opera. In two acts. As performed, with universal applause, at the Theatre-Royal, Covent-Garden. Written by John O'Keeffee [sic], ...;O'Keeffe, John, 1747-1833.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b170e27d-702d-5e88-aadb-8d73b47ac26b",
-    "oai_identifier": [
-        "oai:ota:oucs:4261"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Sprigs of laurel: a comic opera. In two acts. As performed, with universal applause, at the Theatre-Royal, Covent-Garden. Written by John O'Keeffee [sic], ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4261.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b1885888-549b-5944-a14b-31b33171cc17.json b/oaitestdata/clarin-oai_dc/SET_1/json/b1885888-549b-5944-a14b-31b33171cc17.json
deleted file mode 100644
index c08c0a5f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b1885888-549b-5944-a14b-31b33171cc17.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5623",
-    "MetadataAccess": [
-        "oai:ota:oucs:5623"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Brooke, Henry, 1703?-1783."
-    ],
-    "fulltext": "oai:ota:oucs:5623;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5623.xml;The fool of quality: or, the history of Henry Earl of Moreland. In four volumes. By Mr. Brooke. [pt.3];Brooke, Henry, 1703?-1783.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b1885888-549b-5944-a14b-31b33171cc17",
-    "oai_identifier": [
-        "oai:ota:oucs:5623"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The fool of quality: or, the history of Henry Earl of Moreland. In four volumes. By Mr. Brooke. [pt.3]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5623.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b199bda7-7176-556b-a619-b5a785a13bb4.json b/oaitestdata/clarin-oai_dc/SET_1/json/b199bda7-7176-556b-a619-b5a785a13bb4.json
deleted file mode 100644
index 6d291664..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b199bda7-7176-556b-a619-b5a785a13bb4.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish",
-        "Lower Sorbian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/60",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/60"
-    ],
-    "PID": "http://hdl.handle.net/10794/60",
-    "PublicationTimestamp": "2015-04-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/60;2017-10-31T12:37:31Z;hdl_10794_1;hdl_10794_2;ASPAC \u2013 Swedish-Lower Sorbian (2017-10-16);ASPAC \u2013 svenska-l\u00e5gsorbiska (2017-10-16);n/a, n/a;ASPAC;Parallel;Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.;Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat.;2015-04-16;corpus;http://hdl.handle.net/10794/60;swe;dsb;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/octet-stream;application/gzip;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/aspacsvdsb",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b199bda7-7176-556b-a619-b5a785a13bb4",
-    "notes": [
-        "Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.",
-        "Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/60"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ASPAC"
-        },
-        {
-            "name": "Parallel"
-        }
-    ],
-    "title": [
-        "ASPAC \u2013 Swedish-Lower Sorbian (2017-10-16)",
-        "ASPAC \u2013 svenska-l\u00e5gsorbiska (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b1aa4890-3fee-5ab0-8c6d-4fbab5d6bf36.json b/oaitestdata/clarin-oai_dc/SET_1/json/b1aa4890-3fee-5ab0-8c6d-4fbab5d6bf36.json
deleted file mode 100644
index da820fcb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b1aa4890-3fee-5ab0-8c6d-4fbab5d6bf36.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "University of Zagreb, Faculty of Humanities and Social Sciences"
-    ],
-    "Contributor": [
-        "Tadi\u0107, Marko"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Croatian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-256",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-256"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-256",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Zagreb, Faculty of Humanities and Social Sciences"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Croatia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-256;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Croatian Morphological Lexicon;Tadi\u0107, Marko;110,000+ lemmas; 3,900,000+ word-forms, MulText East lexica format;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-256;hrv;downloadable_files_count: 0;Croatia;University of Zagreb, Faculty of Humanities and Social Sciences;http://hml.ffzg.hr/hml/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b1aa4890-3fee-5ab0-8c6d-4fbab5d6bf36",
-    "notes": [
-        "110,000+ lemmas; 3,900,000+ word-forms, MulText East lexica format"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-256"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Croatian Morphological Lexicon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b1f182f8-8037-5d82-9981-3fb539ae6b23.json b/oaitestdata/clarin-oai_dc/SET_1/json/b1f182f8-8037-5d82-9981-3fb539ae6b23.json
deleted file mode 100644
index 90083d3a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b1f182f8-8037-5d82-9981-3fb539ae6b23.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=fe32ebf2485511e2a2aa782bcb074135aa0fdcd287ac45e7b67de9c36d8d2890",
-    "MetadataAccess": [
-        "fe32ebf2485511e2a2aa782bcb074135aa0fdcd287ac45e7b67de9c36d8d2890"
-    ],
-    "PublicationTimestamp": "2018-05-02T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "fulltext": "fe32ebf2485511e2a2aa782bcb074135aa0fdcd287ac45e7b67de9c36d8d2890;2018-11-15T16:39:56Z;corpus;corpus:text;CINTIL-Corpus Internacional do Portugu\u00c3\u00aas;CINTIL-Corpus Internacional do Portugu\u00c3\u00aas is a linguistically interpreted corpus of Portuguese. At present it is composed of 1 Million annotated tokens, verified by human expert annotators. The annotation comprises information on part-of-speech, open classes lemma and inflection, multi-word expressions pertaining to the class of adverbs and to the closed POS classes, and multi-word proper names (for named entity recognition). The corpus has been developed at the University of Lisbon by the NLX group at the Faculty of Sciences and the Anagrama group at the Cenro de Lingu\u00c3\u00adstica da Universidade de Lisboa.;2018-05-02",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b1f182f8-8037-5d82-9981-3fb539ae6b23",
-    "notes": [
-        "CINTIL-Corpus Internacional do Portugu\u00c3\u00aas is a linguistically interpreted corpus of Portuguese. At present it is composed of 1 Million annotated tokens, verified by human expert annotators. The annotation comprises information on part-of-speech, open classes lemma and inflection, multi-word expressions pertaining to the class of adverbs and to the closed POS classes, and multi-word proper names (for named entity recognition). The corpus has been developed at the University of Lisbon by the NLX group at the Faculty of Sciences and the Anagrama group at the Cenro de Lingu\u00c3\u00adstica da Universidade de Lisboa."
-    ],
-    "oai_identifier": [
-        "fe32ebf2485511e2a2aa782bcb074135aa0fdcd287ac45e7b67de9c36d8d2890"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "CINTIL-Corpus Internacional do Portugu\u00c3\u00aas"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b2005fc2-4f3a-5de5-b80c-c197baaf7651.json b/oaitestdata/clarin-oai_dc/SET_1/json/b2005fc2-4f3a-5de5-b80c-c197baaf7651.json
deleted file mode 100644
index 610ec954..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b2005fc2-4f3a-5de5-b80c-c197baaf7651.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "University of West Bohemia"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/x-tar",
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "downloadable_files_count: 4"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-1D76-9",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-1D76-9"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-1D76-9",
-    "PublicationTimestamp": "2014-01-10T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of West Bohemia"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Gr\u016fber, Martin"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-1D76-9;2017-08-11T13:52:23Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Czech Senior COMPANION Expressive Speech Corpus;Gr\u016fber, Martin;speech corpus;expressive;text-to-speech synthesis;The corpus contains Czech expressive speech recorded using scenario-based approach by a professional female speaker. The scenario was created on the basis of previously recorded natural dialogues between a computer and seniors.;2014-01-10;corpus;http://hdl.handle.net/11858/00-097C-0000-0023-1D76-9;ces;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/x-gzip;application/x-tar;application/x-tar;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain; charset=utf-8;downloadable_files_count: 4;University of West Bohemia;http://www.companions-project.org/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b2005fc2-4f3a-5de5-b80c-c197baaf7651",
-    "notes": [
-        "The corpus contains Czech expressive speech recorded using scenario-based approach by a professional female speaker. The scenario was created on the basis of previously recorded natural dialogues between a computer and seniors."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-1D76-9"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech corpus"
-        },
-        {
-            "name": "expressive"
-        },
-        {
-            "name": "text-to-speech synthesis"
-        }
-    ],
-    "title": [
-        "Czech Senior COMPANION Expressive Speech Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b200b85e-62bb-516b-adca-da7eab5fc5fa.json b/oaitestdata/clarin-oai_dc/SET_1/json/b200b85e-62bb-516b-adca-da7eab5fc5fa.json
deleted file mode 100644
index 31f55cd3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b200b85e-62bb-516b-adca-da7eab5fc5fa.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 385 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0046",
-    "MetadataAccess": [
-        "oai:ota:oucs:0046"
-    ],
-    "PublicationTimestamp": "1861-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1861"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Eliot, George, 1819-1880"
-    ],
-    "fulltext": "oai:ota:oucs:0046;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0046.xml;Silas Marner;Eliot, George, 1819-1880;1861;text_and_corpus_linguistics;Novels -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 385 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b200b85e-62bb-516b-adca-da7eab5fc5fa",
-    "oai_identifier": [
-        "oai:ota:oucs:0046"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Novels -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Silas Marner"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0046.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b218ee3b-1f35-525f-ba8d-3e5333fccc24.json b/oaitestdata/clarin-oai_dc/SET_1/json/b218ee3b-1f35-525f-ba8d-3e5333fccc24.json
deleted file mode 100644
index 846c154b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b218ee3b-1f35-525f-ba8d-3e5333fccc24.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "Abkhazian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-960",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-960"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-960",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-960;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Abkhazian;57 tokens;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-960;abk;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#abxaz",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b218ee3b-1f35-525f-ba8d-3e5333fccc24",
-    "notes": [
-        "57 tokens"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-960"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Abkhazian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b24677b6-d797-5c5a-be82-8d805a499655.json b/oaitestdata/clarin-oai_dc/SET_1/json/b24677b6-d797-5c5a-be82-8d805a499655.json
deleted file mode 100644
index d5932a0b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b24677b6-d797-5c5a-be82-8d805a499655.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1166",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1166"
-    ],
-    "PID": "http://hdl.handle.net/11356/1166",
-    "PublicationTimestamp": "2018-03-25T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "RelatedIdentifier": [
-        "https://elex.link/elex2017/wp-content/uploads/2017/09/paper05.pdf"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "https://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Krek, Simon",
-        "Laskowski, Cyprian",
-        "Robnik-\u0160ikonja, Marko",
-        "Gorjanc, Vojko",
-        "Kosem, Iztok",
-        "Arhar Holdt, \u0160pela",
-        "Dobrovoljc, Kaja",
-        "\u010cibej, Jaka",
-        "Klemenc, Bojan",
-        "Gantar, Polona"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1166;2018-03-25T12:07:28Z;hdl_11356_1023;hdl_11356_1024;Thesaurus of Modern Slovene 1.0;Krek, Simon;Laskowski, Cyprian;Robnik-\u0160ikonja, Marko;Kosem, Iztok;Arhar Holdt, \u0160pela;Gantar, Polona;\u010cibej, Jaka;Gorjanc, Vojko;Klemenc, Bojan;Dobrovoljc, Kaja;thesaurus;This is an automatically created Slovene thesaurus from Slovene data available in a comprehensive English\u2013Slovenian dictionary, a monolingual dictionary, and a corpus. A network analysis on the bilingual dictionary word co-occurrence graph was used, together with additional information from the distributional thesaurus data available as part of the Sketch Engine tool and extracted from the 1.2 billion word Gigafida corpus and the monolingual dictionary.;2018-03-25;lexicalConceptualResource;http://hdl.handle.net/11356/1166;slv;https://elex.link/elex2017/wp-content/uploads/2017/09/paper05.pdf;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);https://creativecommons.org/licenses/by-sa/4.0/;PUB;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;Centre for Language Resources and Technologies, University of Ljubljana;https://www.cjvt.si/en/sopomenke/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b24677b6-d797-5c5a-be82-8d805a499655",
-    "notes": [
-        "This is an automatically created Slovene thesaurus from Slovene data available in a comprehensive English\u2013Slovenian dictionary, a monolingual dictionary, and a corpus. A network analysis on the bilingual dictionary word co-occurrence graph was used, together with additional information from the distributional thesaurus data available as part of the Sketch Engine tool and extracted from the 1.2 billion word Gigafida corpus and the monolingual dictionary."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1166"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "thesaurus"
-        }
-    ],
-    "title": [
-        "Thesaurus of Modern Slovene 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b24db186-22af-5100-9cf9-603c76f26c8f.json b/oaitestdata/clarin-oai_dc/SET_1/json/b24db186-22af-5100-9cf9-603c76f26c8f.json
deleted file mode 100644
index c3b2fff1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b24db186-22af-5100-9cf9-603c76f26c8f.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "text/plain",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1820",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1820"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1820",
-    "PublicationTimestamp": "2016-11-07T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-2508"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "BSD 2-Clause \"Simplified\" or \"FreeBSD\" license",
-        "http://opensource.org/licenses/BSD-2-Clause",
-        "PUB"
-    ],
-    "author": [
-        "Nov\u00e1k, Michal",
-        "M\u00edrovsk\u00fd, Ji\u0159\u00ed",
-        "Rysov\u00e1, Magdal\u00e9na",
-        "Rysov\u00e1, Kate\u0159ina"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1820;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;EVALD 1.0;Rysov\u00e1, Kate\u0159ina;M\u00edrovsk\u00fd, Ji\u0159\u00ed;Nov\u00e1k, Michal;Rysov\u00e1, Magdal\u00e9na;text coherence;discourse;automatic evaluation;native speakers;EVALD 1.0 serves for automatic evaluation of surface coherence (cohesion) in Czech texts written by native speakers of Czech.;2016-11-07;toolService;http://hdl.handle.net/11234/1-1820;ces;http://hdl.handle.net/11234/1-2508;BSD 2-Clause \"Simplified\" or \"FreeBSD\" license;http://opensource.org/licenses/BSD-2-Clause;PUB;text/plain;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://ufal.mff.cuni.cz/evald",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b24db186-22af-5100-9cf9-603c76f26c8f",
-    "notes": [
-        "EVALD 1.0 serves for automatic evaluation of surface coherence (cohesion) in Czech texts written by native speakers of Czech."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1820"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "text coherence"
-        },
-        {
-            "name": "discourse"
-        },
-        {
-            "name": "automatic evaluation"
-        },
-        {
-            "name": "native speakers"
-        }
-    ],
-    "title": [
-        "EVALD 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b25a6fd8-3fc8-56f9-998d-440aa0c84ff5.json b/oaitestdata/clarin-oai_dc/SET_1/json/b25a6fd8-3fc8-56f9-998d-440aa0c84ff5.json
deleted file mode 100644
index 2ea3482a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b25a6fd8-3fc8-56f9-998d-440aa0c84ff5.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "J\u00f3zef Epifani Minasowicz",
-        "Drukarnia Nadworna Jego Kr\u00f3lewskiej Mo\u015bci"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-182887",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-182887"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CF2-3",
-    "PublicationTimestamp": "1779-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1779"
-    ],
-    "Publisher": [
-        "J\u00f3zef Epifani Minasowicz",
-        "Drukarnia Nadworna Jego Kr\u00f3lewskiej Mo\u015bci"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/182887",
-        "oai:jbc.bj.uj.edu.pl:publication:193789"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1701/1800"
-    ],
-    "TempCoverageBegin": 53662478399,
-    "TempCoverageEnd": 53662478399,
-    "TemporalCoverage": " point in time : 1701-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1701-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1701-07-01T11:59:59Z",
-    "author": [
-        "Ja\u015bkiewicz, Miko\u0142aj (1717-1779)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-182887;2019-03-01T11:01:48Z;Skarb W Ziemi Ukryty : Niesmiertelna w Smiertelnym Ciele Dusza Albo Szacunek Duszy Ludzkiey;Ja\u015bkiewicz, Miko\u0142aj (1717-1779);starodruki 18\u00a0w.;J\u00f3zef Epifani Minasowicz;Drukarnia Nadworna Jego Kr\u00f3lewskiej Mo\u015bci;1779;starodruk;application/xml;clarind-uds:poldilemma-182887;hdl:11858/00-246C-0000-0023-8CF2-3;Biblioteka Jagiello\u0144ska, BJ St. Dr. 2217 I;lat;http://jbc.bj.uj.edu.pl/Content/182887;oai:jbc.bj.uj.edu.pl:publication:193789;1701/1800;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b25a6fd8-3fc8-56f9-998d-440aa0c84ff5",
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-182887"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Skarb W Ziemi Ukryty : Niesmiertelna w Smiertelnym Ciele Dusza Albo Szacunek Duszy Ludzkiey"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b2829850-5e1b-5d14-9411-4e0c6b0050e9.json b/oaitestdata/clarin-oai_dc/SET_1/json/b2829850-5e1b-5d14-9411-4e0c6b0050e9.json
deleted file mode 100644
index 4ff727bd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b2829850-5e1b-5d14-9411-4e0c6b0050e9.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3045",
-    "MetadataAccess": [
-        "oai:ota:oucs:3045"
-    ],
-    "PublicationTimestamp": "1904-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1904"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "London, Jack, 1876-1916"
-    ],
-    "fulltext": "oai:ota:oucs:3045;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3045.xml;The sea wolf;London, Jack, 1876-1916;not after: 1904;text_and_corpus_linguistics;American fiction -- 20th century;eng;Oxford Text Archive, University of Oxford;Triggs, Jeffery;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b2829850-5e1b-5d14-9411-4e0c6b0050e9",
-    "oai_identifier": [
-        "oai:ota:oucs:3045"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "American fiction -- th century"
-        }
-    ],
-    "title": [
-        "The sea wolf"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3045.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b2906cac-3bc3-5df5-a69e-ded01f4438c6.json b/oaitestdata/clarin-oai_dc/SET_1/json/b2906cac-3bc3-5df5-a69e-ded01f4438c6.json
deleted file mode 100644
index 45226074..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b2906cac-3bc3-5df5-a69e-ded01f4438c6.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Malwina Hopej"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/490",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/490"
-    ],
-    "PID": "http://hdl.handle.net/11321/490",
-    "PublicationTimestamp": "2018-06-19T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Malwina Hopej"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "plWordNet",
-        "http://clarin-pl.eu/en/licenses/plwordnet-2/",
-        "PUB"
-    ],
-    "author": [
-        "Hopej, Malwina"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/490;2018-06-19T11:18:34Z;hdl_11321_3;hdl_11321_4;Corpus 1;Hopej, Malwina;Pr\u00f3bka;Pr\u00f3bka warsztatowa.;2018-06-19;corpus;http://hdl.handle.net/11321/490;pol;plWordNet;http://clarin-pl.eu/en/licenses/plwordnet-2/;PUB;text/plain; charset=utf-8;application/vnd.openxmlformats-officedocument.wordprocessingml.document;downloadable_files_count: 1;Malwina Hopej",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b2906cac-3bc3-5df5-a69e-ded01f4438c6",
-    "notes": [
-        "Pr\u00f3bka warsztatowa."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/490"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Corpus 1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b2ad0081-e9dc-527c-b128-553246917cf2.json b/oaitestdata/clarin-oai_dc/SET_1/json/b2ad0081-e9dc-527c-b128-553246917cf2.json
deleted file mode 100644
index 7565ee1c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b2ad0081-e9dc-527c-b128-553246917cf2.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4935",
-    "MetadataAccess": [
-        "oai:ota:oucs:4935"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dutton, Thomas, 18th/19th cent."
-    ],
-    "fulltext": "oai:ota:oucs:4935;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4935.xml;A vindication of The age of reason, by Thomas Paine: being an answer to the strictures of Mr. Gilbert Wakefield and Dr. Priestley, ... By Thomas Dutton.;Dutton, Thomas, 18th/19th cent.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b2ad0081-e9dc-527c-b128-553246917cf2",
-    "oai_identifier": [
-        "oai:ota:oucs:4935"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A vindication of The age of reason, by Thomas Paine: being an answer to the strictures of Mr. Gilbert Wakefield and Dr. Priestley, ... By Thomas Dutton."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4935.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b2b0f21e-64a8-5984-ba99-8ed9abdb4909.json b/oaitestdata/clarin-oai_dc/SET_1/json/b2b0f21e-64a8-5984-ba99-8ed9abdb4909.json
deleted file mode 100644
index a2b3b354..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b2b0f21e-64a8-5984-ba99-8ed9abdb4909.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "522 KB"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1099",
-    "MetadataAccess": [
-        "oai:ota:oucs:1099"
-    ],
-    "PublicationTimestamp": "1340-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1340"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Boccaccio, Giovani,  1313-1375"
-    ],
-    "fulltext": "oai:ota:oucs:1099;2018-03-05T11:21:29Z;http://ota.ox.ac.uk/headers/1099.xml;Il Teseide / compiled by Antonio Zampolli;Teseida;Boccaccio, Giovani,  1313-1375;1340-1341;text_and_corpus_linguistics;Poems -- Italy -- 14th century;ita;Oxford Text Archive, University of Oxford;522 KB;Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b2b0f21e-64a8-5984-ba99-8ed9abdb4909",
-    "oai_identifier": [
-        "oai:ota:oucs:1099"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- Italy -- th century"
-        }
-    ],
-    "title": [
-        "Il Teseide / compiled by Antonio Zampolli",
-        "Teseida"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1099.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b2b318fe-d8c9-596c-b0b3-8417ef36ac17.json b/oaitestdata/clarin-oai_dc/SET_1/json/b2b318fe-d8c9-596c-b0b3-8417ef36ac17.json
deleted file mode 100644
index 49885627..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b2b318fe-d8c9-596c-b0b3-8417ef36ac17.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4545",
-    "MetadataAccess": [
-        "oai:ota:oucs:4545"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Chetwood, W. R. (William Rufus), d. 1766."
-    ],
-    "fulltext": "oai:ota:oucs:4545;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4545.xml;The voyages, travels and adventures, of William Owen Gwin Vaughan, Esq: With the history of his brother Jonathan Vaughan, six years a slave in Tunis. Intermix'd with the histories of Clerimont, Maria, Eleanora, and others. ... [pt.2];Chetwood, W. R. (William Rufus), d. 1766.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b2b318fe-d8c9-596c-b0b3-8417ef36ac17",
-    "oai_identifier": [
-        "oai:ota:oucs:4545"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The voyages, travels and adventures, of William Owen Gwin Vaughan, Esq: With the history of his brother Jonathan Vaughan, six years a slave in Tunis. Intermix'd with the histories of Clerimont, Maria, Eleanora, and others. ... [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4545.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b2c15bea-d3d0-5da2-86f9-ff1f74c8b3bb.json b/oaitestdata/clarin-oai_dc/SET_1/json/b2c15bea-d3d0-5da2-86f9-ff1f74c8b3bb.json
deleted file mode 100644
index 88c269df..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b2c15bea-d3d0-5da2-86f9-ff1f74c8b3bb.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "University of West Bohemia, Department of Computer Science and Engineering"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1844",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1844"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1844",
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "University of West Bohemia, Department of Computer Science and Engineering"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/630786"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Konkol, Michal",
-        "Svoboda, Luk\u00e1\u0161",
-        "Brychc\u00edn, Tom\u00e1\u0161",
-        "Steinberger, Josef",
-        "Hercig, Tom\u00e1\u0161"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1844;2016-12-07T11:10:30Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Restaurant Reviews CZ ABSA corpus v2;Hercig, Tom\u00e1\u0161;Brychc\u00edn, Tom\u00e1\u0161;Svoboda, Luk\u00e1\u0161;Konkol, Michal;Steinberger, Josef;Aspect Based Sentiment Analysis;Sentiment Analysis;Restaurant Reviews CZ ABSA - 2.15k reviews with their related target and category\r\n\r\nThe work done is described in the paper: https://doi.org/10.13053/CyS-20-3-2469;2016;corpus;http://hdl.handle.net/11372/LRT-1844;ces;info:eu-repo/grantAgreement/EC/FP7/630786;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;University of West Bohemia, Department of Computer Science and Engineering;http://nlp.kiv.zcu.cz/publication/80",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b2c15bea-d3d0-5da2-86f9-ff1f74c8b3bb",
-    "notes": [
-        "Restaurant Reviews CZ ABSA - 2.15k reviews with their related target and category\r\n\r\nThe work done is described in the paper: https://doi.org/10.13053/CyS-20-3-2469"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1844"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Aspect Based Sentiment Analysis"
-        },
-        {
-            "name": "Sentiment Analysis"
-        }
-    ],
-    "title": [
-        "Restaurant Reviews CZ ABSA corpus v2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b2c9820a-6337-5639-936a-58ab931b75ee.json b/oaitestdata/clarin-oai_dc/SET_1/json/b2c9820a-6337-5639-936a-58ab931b75ee.json
deleted file mode 100644
index 76a0d1f6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b2c9820a-6337-5639-936a-58ab931b75ee.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Korzeniowski"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 7",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/78",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/78"
-    ],
-    "PID": "http://hdl.handle.net/11321/78",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Korzeniowski"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Korzeniowski, Korzeniowski"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/78;2015-05-19T13:35:20Z;hdl_11321_3;hdl_11321_4;MWE Korzeniowski;Korzeniowski, Korzeniowski;Korzeniowski;2015-04-08;corpus;http://hdl.handle.net/11321/78;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 7;Korzeniowski",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b2c9820a-6337-5639-936a-58ab931b75ee",
-    "notes": [
-        "Korzeniowski"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/78"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Korzeniowski"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b2e37a2e-48a0-577c-9933-5c887b6d1645.json b/oaitestdata/clarin-oai_dc/SET_1/json/b2e37a2e-48a0-577c-9933-5c887b6d1645.json
deleted file mode 100644
index 919d1d60..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b2e37a2e-48a0-577c-9933-5c887b6d1645.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contributor": [
-        "Manfred Pinkal",
-        "Michael Roth",
-        "Stefan Thater",
-        "Simon Ostermann",
-        "Ashutosh Modi"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:mcscript",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:mcscript"
-    ],
-    "PID": "http://hdl.handle.net/21.11119/0000-0001-D3A7-4",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "RelatedIdentifier": [
-        "Simon Ostermann, Ashutosh Modi, Michael Roth, Stefan Thater and Manfred Pinkal (2018): \"MCScript: A Novel Dataset for Assessing Machine Comprehension Using Script Knowledge\". In Proceedings of the 11th International Conference on Language Resources and Evaluation, Miyazaki, Japan. http://www.lrec-conf.org/proceedings/lrec2018/pdf/225.pdf"
-    ],
-    "ResourceType": [
-        "Collection",
-        "Dataset",
-        "Text"
-    ],
-    "Rights": [
-        "CC-BY-SA-NC-4.0"
-    ],
-    "author": [
-        "Simon Ostermann, Fachrichtung Sprachwissenschaft und Sprachtechnologie, Universit\u00e4t des Saarlandes, Campus C7.4, 66123 Saarbr\u00fccken"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:mcscript;2018-07-10T13:05:37Z;McScript: A Novel Dataset for Assessing Machine Comprehension Using Script Knowledge;Simon Ostermann, Fachrichtung Sprachwissenschaft und Sprachtechnologie, Universit\u00e4t des Saarlandes, Campus C7.4, 66123 Saarbr\u00fccken;Scripts;Script Knowledge;Narrative Texts;Commonsense Knowledge;Crowdsourcing;The MCScript corpus is a large dataset of narrative texts and questions about these texts, intended to be used in a machine comprehension task that requires reasoning using \ncommonsense knowledge. Our dataset complements similar datasets in that we focus on \nstories about everyday activities, such as going to the movies or working in the garden, and \nthat the questions require commonsense knowledge, or more specifically, script knowledge, \nto be answered. We show that our mode of data collection via crowdsourcing results in a \nsubstantial amount of such inference questions. The dataset forms the basis of a shared task \non commonsense and script knowledge organized at SemEval 2018 and provides \nchallenging test cases for the broader natural language understanding community.;Simon Ostermann;Ashutosh Modi;Michael Roth;Stefan Thater;Manfred Pinkal;2018;Collection;Dataset;Text;text/xml;clarind-uds:mcscript;hdl:21.11119/0000-0001-D3A7-4;eng;Simon Ostermann, Ashutosh Modi, Michael Roth, Stefan Thater and Manfred Pinkal (2018): \"MCScript: A Novel Dataset for Assessing Machine Comprehension Using Script Knowledge\". In Proceedings of the 11th International Conference on Language Resources and Evaluation, Miyazaki, Japan. http://www.lrec-conf.org/proceedings/lrec2018/pdf/225.pdf;CC-BY-SA-NC-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b2e37a2e-48a0-577c-9933-5c887b6d1645",
-    "notes": [
-        "The MCScript corpus is a large dataset of narrative texts and questions about these texts, intended to be used in a machine comprehension task that requires reasoning using \ncommonsense knowledge. Our dataset complements similar datasets in that we focus on \nstories about everyday activities, such as going to the movies or working in the garden, and \nthat the questions require commonsense knowledge, or more specifically, script knowledge, \nto be answered. We show that our mode of data collection via crowdsourcing results in a \nsubstantial amount of such inference questions. The dataset forms the basis of a shared task \non commonsense and script knowledge organized at SemEval 2018 and provides \nchallenging test cases for the broader natural language understanding community."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:mcscript"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Scripts"
-        },
-        {
-            "name": "Script Knowledge"
-        },
-        {
-            "name": "Narrative Texts"
-        },
-        {
-            "name": "Commonsense Knowledge"
-        },
-        {
-            "name": "Crowdsourcing"
-        }
-    ],
-    "title": [
-        "McScript: A Novel Dataset for Assessing Machine Comprehension Using Script Knowledge"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b3199b22-a94d-5ec0-a698-6fca67ff8a12.json b/oaitestdata/clarin-oai_dc/SET_1/json/b3199b22-a94d-5ec0-a698-6fca67ff8a12.json
deleted file mode 100644
index 7550b875..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b3199b22-a94d-5ec0-a698-6fca67ff8a12.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Humanities and Social Sciences, University of Zagreb"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Serbian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1066",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1066"
-    ],
-    "PID": "http://hdl.handle.net/11356/1066",
-    "PublicationTimestamp": "2016-06-23T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Faculty of Humanities and Social Sciences, University of Zagreb"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/324414",
-        "http://hdl.handle.net/11356/1057",
-        "http://hdl.handle.net/11356/1073"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "GNU General Public Licence, version 3",
-        "http://opensource.org/licenses/GPL-3.0",
-        "PUB"
-    ],
-    "author": [
-        "Ljube\u0161i\u0107, Nikola"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1066;2017-06-27T18:10:07Z;hdl_11356_1023;hdl_11356_1024;Inflectional lexicon srLex 1.1;Ljube\u0161i\u0107, Nikola;lexicon;morphology;inflection;srLex is a large inflectional lexicon of Serbian language where each entry consists of a (wordform, lemma, MSD, frequency, per-million frequency) 5-tuple. The (wordform, lemma, MSD) triple frequencies are calculated on the srWaC v1.2 corpus. The MSD tagset follows the MULTEXT-East V5 tagset for Bosnian available at http://nl.ijs.si/ME/V5/msd/html/msd-bs.html.;2016-06-23;lexicalConceptualResource;http://hdl.handle.net/11356/1066;srp;info:eu-repo/grantAgreement/EC/FP7/324414;http://hdl.handle.net/11356/1057;http://hdl.handle.net/11356/1073;GNU General Public Licence, version 3;http://opensource.org/licenses/GPL-3.0;PUB;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Faculty of Humanities and Social Sciences, University of Zagreb;http://nlp.ffzg.hr/resources/lexicons/srlex/ \u200e",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b3199b22-a94d-5ec0-a698-6fca67ff8a12",
-    "notes": [
-        "srLex is a large inflectional lexicon of Serbian language where each entry consists of a (wordform, lemma, MSD, frequency, per-million frequency) 5-tuple. The (wordform, lemma, MSD) triple frequencies are calculated on the srWaC v1.2 corpus. The MSD tagset follows the MULTEXT-East V5 tagset for Bosnian available at http://nl.ijs.si/ME/V5/msd/html/msd-bs.html."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1066"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "lexicon"
-        },
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "inflection"
-        }
-    ],
-    "title": [
-        "Inflectional lexicon srLex 1.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b32954bb-36da-50e5-973a-9576ec108ab3.json b/oaitestdata/clarin-oai_dc/SET_1/json/b32954bb-36da-50e5-973a-9576ec108ab3.json
deleted file mode 100644
index 2475ca77..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b32954bb-36da-50e5-973a-9576ec108ab3.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4024",
-    "MetadataAccess": [
-        "oai:ota:oucs:4024"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Cunningham, John, 1729-1773."
-    ],
-    "fulltext": "oai:ota:oucs:4024;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4024.xml;Love in a mist: A farce now acting at the City-Theatre in Dublin, with great applause.;Cunningham, John, 1729-1773.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b32954bb-36da-50e5-973a-9576ec108ab3",
-    "oai_identifier": [
-        "oai:ota:oucs:4024"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Love in a mist: A farce now acting at the City-Theatre in Dublin, with great applause."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4024.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b329f444-e363-57f9-965c-481fa7ce1583.json b/oaitestdata/clarin-oai_dc/SET_1/json/b329f444-e363-57f9-965c-481fa7ce1583.json
deleted file mode 100644
index 741a32b3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b329f444-e363-57f9-965c-481fa7ce1583.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Tokyo Kokusai Kenkyu Kurabu"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 1.92 MB)"
-    ],
-    "Language": [
-        "Japanese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2246",
-    "MetadataAccess": [
-        "oai:ota:oucs:2246"
-    ],
-    "PublicationTimestamp": "2000-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Murasaki Shikibu, b. 978?"
-    ],
-    "fulltext": "oai:ota:oucs:2246;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/2246.xml;Genji monogatari;Murasaki Shikibu, b. 978?;[2000];text_and_corpus_linguistics;Fiction -- Japan -- 11th century;Novels -- Japan -- 11th century;jpn;An epic novel concerning the life and intrigues of the fictitional Prince Genji, who is the son of the emperor and Kiritsubo, his concubine. The Tale is generally regarded as an accurate portrayal of aristocratic life in the middle of the Heian period (794-1195 A.D.) ;Oxford Text Archive, University of Oxford;Tokyo Kokusai Kenkyu Kurabu;(1 file : ca. 1.92 MB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b329f444-e363-57f9-965c-481fa7ce1583",
-    "notes": [
-        "An epic novel concerning the life and intrigues of the fictitional Prince Genji, who is the son of the emperor and Kiritsubo, his concubine. The Tale is generally regarded as an accurate portrayal of aristocratic life in the middle of the Heian period (794-1195 A.D.) "
-    ],
-    "oai_identifier": [
-        "oai:ota:oucs:2246"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- Japan -- th century"
-        },
-        {
-            "name": "Novels -- Japan -- th century"
-        }
-    ],
-    "title": [
-        "Genji monogatari"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2246.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b33a64a3-5dfe-5d87-bf44-220ece492e0e.json b/oaitestdata/clarin-oai_dc/SET_1/json/b33a64a3-5dfe-5d87-bf44-220ece492e0e.json
deleted file mode 100644
index 318227e0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b33a64a3-5dfe-5d87-bf44-220ece492e0e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5562",
-    "MetadataAccess": [
-        "oai:ota:oucs:5562"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Garthshore, Maxwell, 1732-1812."
-    ],
-    "fulltext": "oai:ota:oucs:5562;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5562.xml;A remarkable case of a numerous birth, with observations: By Maxwell Garthshore, ... From the Philosophical transactions.;Garthshore, Maxwell, 1732-1812.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b33a64a3-5dfe-5d87-bf44-220ece492e0e",
-    "oai_identifier": [
-        "oai:ota:oucs:5562"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A remarkable case of a numerous birth, with observations: By Maxwell Garthshore, ... From the Philosophical transactions."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5562.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b350a74d-93e5-50bb-816e-689cc1e6a90b.json b/oaitestdata/clarin-oai_dc/SET_1/json/b350a74d-93e5-50bb-816e-689cc1e6a90b.json
deleted file mode 100644
index 40b393bb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b350a74d-93e5-50bb-816e-689cc1e6a90b.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-929",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-929"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-929",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-929;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Old Prussian;ca. 40.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-929;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#apreu",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b350a74d-93e5-50bb-816e-689cc1e6a90b",
-    "notes": [
-        "ca. 40.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-929"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Old Prussian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b35223eb-a5d9-519a-b226-c287df5b74c1.json b/oaitestdata/clarin-oai_dc/SET_1/json/b35223eb-a5d9-519a-b226-c287df5b74c1.json
deleted file mode 100644
index 9b5f79cf..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b35223eb-a5d9-519a-b226-c287df5b74c1.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 206 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "Old French (842-ca. 1400)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0180",
-    "MetadataAccess": [
-        "oai:ota:oucs:0180"
-    ],
-    "PublicationTimestamp": "1176-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1176"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Chr\u00c3\u00a9tien, de Troyes, 12th cent."
-    ],
-    "fulltext": "oai:ota:oucs:0180;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0180.xml;Clig\u00c3\u00a9s;Chr\u00c3\u00a9tien, de Troyes, 12th cent.;1176;text_and_corpus_linguistics;Poems -- France -- 12th century;Romances -- France -- 12th century;fro;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 206 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b35223eb-a5d9-519a-b226-c287df5b74c1",
-    "oai_identifier": [
-        "oai:ota:oucs:0180"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- France -- th century"
-        },
-        {
-            "name": "Romances -- France -- th century"
-        }
-    ],
-    "title": [
-        "Clig\u00c3\u00a9s"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0180.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b35997b8-5c3d-5a60-abd3-4a96adda281f.json b/oaitestdata/clarin-oai_dc/SET_1/json/b35997b8-5c3d-5a60-abd3-4a96adda281f.json
deleted file mode 100644
index 7945154c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b35997b8-5c3d-5a60-abd3-4a96adda281f.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Slovak"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-AADD-3",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-AADD-3"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0006-AADD-3",
-    "PublicationTimestamp": "2012-05-15T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/231720"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Galu\u0161\u010d\u00e1kov\u00e1, Petra",
-        "Bojar, Ond\u0159ej"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-AADD-3;2018-07-02T22:05:53Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Manually Ranked Translation Outputs;Bojar, Ond\u0159ej;Galu\u0161\u010d\u00e1kov\u00e1, Petra;machine translation;evaluation;manual ranking;Manually ranked outputs of Czech-Slovak translations. Three annotators manually ranked outputs of five MT systems (\u010ces\u00edlko, \u010ces\u00edlko2,  Google Translate and two Moses setups) on three data sets (100 sentences randomly selected from books, 100 sentences randomly selected from Acquis corpus and 50 first sentences from WMT 2010 test set).  Ranking was applied in MT systems comparison in [1].\r\n\r\nReferences: \r\n[1] Ond\u0159ej Bojar, Petra Galu\u0161\u010d\u00e1kov\u00e1, and Miroslav T\u00fdnovsk\u00fd. Evaluating Quality of Machine Translation from Czech to Slovak. In Mark\u00e9ta Lopatkov\u00e1, editor, Information Technologies - Applications and Theory, pages 3-9, September 2011;2012-05-15;lexicalConceptualResource;http://hdl.handle.net/11858/00-097C-0000-0006-AADD-3;slk;info:eu-repo/grantAgreement/EC/FP7/231720;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b35997b8-5c3d-5a60-abd3-4a96adda281f",
-    "notes": [
-        "Manually ranked outputs of Czech-Slovak translations. Three annotators manually ranked outputs of five MT systems (\u010ces\u00edlko, \u010ces\u00edlko2,  Google Translate and two Moses setups) on three data sets (100 sentences randomly selected from books, 100 sentences randomly selected from Acquis corpus and 50 first sentences from WMT 2010 test set).  Ranking was applied in MT systems comparison in [1].\r\n\r\nReferences: \r\n[1] Ond\u0159ej Bojar, Petra Galu\u0161\u010d\u00e1kov\u00e1, and Miroslav T\u00fdnovsk\u00fd. Evaluating Quality of Machine Translation from Czech to Slovak. In Mark\u00e9ta Lopatkov\u00e1, editor, Information Technologies - Applications and Theory, pages 3-9, September 2011"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0006-AADD-3"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "evaluation"
-        },
-        {
-            "name": "manual ranking"
-        }
-    ],
-    "title": [
-        "Manually Ranked Translation Outputs"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b380d2fb-75b7-5563-9307-148657a45013.json b/oaitestdata/clarin-oai_dc/SET_1/json/b380d2fb-75b7-5563-9307-148657a45013.json
deleted file mode 100644
index 804295c3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b380d2fb-75b7-5563-9307-148657a45013.json
+++ /dev/null
@@ -1,100 +0,0 @@
-{
-    "Contact": [
-        "Charles University in Prague, \u00da\u010cJTK"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 4",
-        "application/pdf",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-000C-2112-B",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-000C-2112-B"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-000C-2112-B",
-    "PublicationTimestamp": "2012-12-12T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Charles University in Prague, \u00da\u010cJTK"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u0160\u0165astn\u00fd, Klement",
-        "Jane\u0161, Petr",
-        "\u0160tindlov\u00e1, Barbora",
-        "Hrdli\u010dka, Milan",
-        "\u0160ormov\u00e1, Kate\u0159ina",
-        "Sl\u00e1dek, \u0160imon",
-        "Pol\u00e1\u010dkov\u00e1, Marie",
-        "Hrdli\u010dkov\u00e1, Tereza",
-        "\u0160ebesta, Karel",
-        "Pierscieniak, Piotr",
-        "Lund\u00e1kov\u00e1, Kate\u0159ina",
-        "Bed\u0159ichov\u00e1, Zuzanna",
-        "Hana, Ji\u0159\u00ed",
-        "Jel\u00ednek, Tom\u00e1\u0161",
-        "\u0160kodov\u00e1, Svatava",
-        "Skoumalov\u00e1, Hana",
-        "Rosen, Alexandr",
-        "Petkevi\u010d, Vladim\u00edr"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-000C-2112-B;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;AKCES 3;\u0160ebesta, Karel;Bed\u0159ichov\u00e1, Zuzanna;\u0160ormov\u00e1, Kate\u0159ina;\u0160tindlov\u00e1, Barbora;Hrdli\u010dka, Milan;Hrdli\u010dkov\u00e1, Tereza;Hana, Ji\u0159\u00ed;Rosen, Alexandr;Petkevi\u010d, Vladim\u00edr;Jel\u00ednek, Tom\u00e1\u0161;\u0160kodov\u00e1, Svatava;Pol\u00e1\u010dkov\u00e1, Marie;Jane\u0161, Petr;Lund\u00e1kov\u00e1, Kate\u0159ina;Skoumalov\u00e1, Hana;\u0160\u0165astn\u00fd, Klement;Sl\u00e1dek, \u0160imon;Pierscieniak, Piotr;Czech as a foreign language;Czech language acquisition corpora;non-native speakers;AKCES;second language aquisition;Corpus AKCES 3 includes texts written in czech by non-native speakers (AKCES/CLAC - Czech Language Acquisition Corpora);2012-12-12;corpus;http://hdl.handle.net/11858/00-097C-0000-000C-2112-B;ces;Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0);http://creativecommons.org/licenses/by-nc-nd/3.0/;PUB;application/zip;application/pdf;application/pdf;application/pdf;text/plain; charset=utf-8;downloadable_files_count: 4;Charles University in Prague, \u00da\u010cJTK;http://utkl.ff.cuni.cz/learncorp/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b380d2fb-75b7-5563-9307-148657a45013",
-    "notes": [
-        "Corpus AKCES 3 includes texts written in czech by non-native speakers (AKCES/CLAC - Czech Language Acquisition Corpora)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-000C-2112-B"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Czech foreign language"
-        },
-        {
-            "name": "Czech language acquisition corpora"
-        },
-        {
-            "name": "non-native speakers"
-        },
-        {
-            "name": "AKCES"
-        },
-        {
-            "name": "second language aquisition"
-        }
-    ],
-    "title": [
-        "AKCES 3"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b38e816a-ad66-5080-9e79-07aef4ba8d4a.json b/oaitestdata/clarin-oai_dc/SET_1/json/b38e816a-ad66-5080-9e79-07aef4ba8d4a.json
deleted file mode 100644
index 3fc13cec..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b38e816a-ad66-5080-9e79-07aef4ba8d4a.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Herden"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/vnd.oasis.opendocument.text",
-        "downloadable_files_count: 10",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/496",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/496"
-    ],
-    "PID": "http://hdl.handle.net/11321/496",
-    "PublicationTimestamp": "2018-06-19T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Herden"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Super Cool License",
-        "http://www.google.com",
-        "ACA"
-    ],
-    "author": [
-        "Herden, El\u017cbieta"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/496;2018-06-19T11:25:23Z;hdl_11321_3;hdl_11321_4;bohemian architecture;Herden, El\u017cbieta;architecture;Research Project;2018-06-19;corpus;http://hdl.handle.net/11321/496;pol;Super Cool License;http://www.google.com;ACA;text/plain; charset=utf-8;text/plain;text/plain;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.oasis.opendocument.text;application/msword;application/msword;downloadable_files_count: 10;Herden",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b38e816a-ad66-5080-9e79-07aef4ba8d4a",
-    "notes": [
-        "Research Project"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/496"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "architecture"
-        }
-    ],
-    "title": [
-        "bohemian architecture"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b39137ea-c1cf-5315-83fe-d058cc92f322.json b/oaitestdata/clarin-oai_dc/SET_1/json/b39137ea-c1cf-5315-83fe-d058cc92f322.json
deleted file mode 100644
index 3715d40f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b39137ea-c1cf-5315-83fe-d058cc92f322.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Micha\u0142 Moru\u015b"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/richtext",
-        "downloadable_files_count: 192",
-        "application/pdf"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/592",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/592"
-    ],
-    "PID": "http://hdl.handle.net/11321/592",
-    "PublicationTimestamp": "2019-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Micha\u0142 Moru\u015b"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "plWordNet",
-        "http://clarin-pl.eu/en/licenses/plwordnet-2/",
-        "PUB"
-    ],
-    "author": [
-        "Moru\u015b, Micha\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/592;2018-08-21T08:55:53Z;hdl_11321_3;hdl_11321_4;SermonsEN;Moru\u015b, Micha\u0142;sermons;Sermons in English;2019;corpus;http://hdl.handle.net/11321/592;eng;plWordNet;http://clarin-pl.eu/en/licenses/plwordnet-2/;PUB;text/plain; charset=utf-8;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;text/richtext;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;application/pdf;downloadable_files_count: 192;Micha\u0142 Moru\u015b",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b39137ea-c1cf-5315-83fe-d058cc92f322",
-    "notes": [
-        "Sermons in English"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/592"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "sermons"
-        }
-    ],
-    "title": [
-        "SermonsEN"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b3959bfd-8cab-5ffd-951c-2ccb3c37b759.json b/oaitestdata/clarin-oai_dc/SET_1/json/b3959bfd-8cab-5ffd-951c-2ccb3c37b759.json
deleted file mode 100644
index 337d9095..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b3959bfd-8cab-5ffd-951c-2ccb3c37b759.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4753",
-    "MetadataAccess": [
-        "oai:ota:oucs:4753"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hull, Thomas, 1728-1808."
-    ],
-    "fulltext": "oai:ota:oucs:4753;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4753.xml;Moral tales in verse: founded on real events. Written by Thomas Hull, ... [pt.2];Hull, Thomas, 1728-1808.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b3959bfd-8cab-5ffd-951c-2ccb3c37b759",
-    "oai_identifier": [
-        "oai:ota:oucs:4753"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Moral tales in verse: founded on real events. Written by Thomas Hull, ... [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4753.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b396c98e-4dc3-5666-85d6-5dd8ccc425fd.json b/oaitestdata/clarin-oai_dc/SET_1/json/b396c98e-4dc3-5666-85d6-5dd8ccc425fd.json
deleted file mode 100644
index 5210f5ba..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b396c98e-4dc3-5666-85d6-5dd8ccc425fd.json
+++ /dev/null
@@ -1,95 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "application/zip"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1139",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1139"
-    ],
-    "PID": "http://hdl.handle.net/11356/1139",
-    "PublicationTimestamp": "2017-08-17T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "http://slovenscina2.0.trojina.si/arhiv/2016-2/2016-2-04/",
-        "http://nl.ijs.si/janes/viri/avtomatsko-oznaceni-korpusi/#Janes-Forum",
-        "https://doi.org/10.1007/s10579-018-9425-z"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "Erjavec, Toma\u017e",
-        "Ljube\u0161i\u0107, Nikola",
-        "Fi\u0161er, Darja"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1139;2018-10-29T10:41:03Z;hdl_11356_1023;hdl_11356_1024;Forum corpus Janes-Forum 1.0;Erjavec, Toma\u017e;Ljube\u0161i\u0107, Nikola;Fi\u0161er, Darja;computer-mediated communication;forums;word normalisation;tagging;lemmatisation;named entities;TEI;Janes-Forum is an annotated corpus of Slovene forums from websites med.over.net, avtomobilizem.com, and kvarkadabra.net from the period 2001-02 to 2015-01. The corpus is structured into forums, threads and posts, together with their metadata. The texts in the corpus are tokenised, sentence segmented, word normalised, morphosyntactically tagged, lemmatised and annotated with named entities. Due to protection of privacy and compliance with wishes of platform owners, usernames are not included in the metadata, and 'person', 'person derivative' and 'company name' named entities have been removed from the texts.;2017-08-17;corpus;http://hdl.handle.net/11356/1139;slv;http://slovenscina2.0.trojina.si/arhiv/2016-2/2016-2-04/;http://nl.ijs.si/janes/viri/avtomatsko-oznaceni-korpusi/#Janes-Forum;https://doi.org/10.1007/s10579-018-9425-z;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;https://creativecommons.org/licenses/by/4.0/;text/plain; charset=utf-8;application/zip;application/zip;downloadable_files_count: 2;Jo\u017eef Stefan Institute;http://nl.ijs.si/janes/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b396c98e-4dc3-5666-85d6-5dd8ccc425fd",
-    "notes": [
-        "Janes-Forum is an annotated corpus of Slovene forums from websites med.over.net, avtomobilizem.com, and kvarkadabra.net from the period 2001-02 to 2015-01. The corpus is structured into forums, threads and posts, together with their metadata. The texts in the corpus are tokenised, sentence segmented, word normalised, morphosyntactically tagged, lemmatised and annotated with named entities. Due to protection of privacy and compliance with wishes of platform owners, usernames are not included in the metadata, and 'person', 'person derivative' and 'company name' named entities have been removed from the texts."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1139"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "computer-mediated communication"
-        },
-        {
-            "name": "forums"
-        },
-        {
-            "name": "word normalisation"
-        },
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "lemmatisation"
-        },
-        {
-            "name": "named entities"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "Forum corpus Janes-Forum 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b3d8c3f8-aa21-5a70-ae74-1394fbe2c182.json b/oaitestdata/clarin-oai_dc/SET_1/json/b3d8c3f8-aa21-5a70-ae74-1394fbe2c182.json
deleted file mode 100644
index 24f076fa..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b3d8c3f8-aa21-5a70-ae74-1394fbe2c182.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=2f2a00e4b92f11e1a404080027e73ea2eccd095ad8b0407989b2adb143ab6095",
-    "MetadataAccess": [
-        "2f2a00e4b92f11e1a404080027e73ea2eccd095ad8b0407989b2adb143ab6095"
-    ],
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "2f2a00e4b92f11e1a404080027e73ea2eccd095ad8b0407989b2adb143ab6095;2019-02-27T12:08:50Z;corpus;corpus:text;CINTIL-Definitions;The corpus presented here is a collection of several tutorials and scientific papers in the field of Information Technology with 603 annotated definitions from Portuguese. The texts were collected from the Web at the beginning of the 2006 and they are organised in 32 files of three different sub-domains with 268,064 tokens: Information Society (91,825 tokens), Information Technology (80,483 tokens), and e-Learning (94,756 tokens).;2015-12-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b3d8c3f8-aa21-5a70-ae74-1394fbe2c182",
-    "notes": [
-        "The corpus presented here is a collection of several tutorials and scientific papers in the field of Information Technology with 603 annotated definitions from Portuguese. The texts were collected from the Web at the beginning of the 2006 and they are organised in 32 files of three different sub-domains with 268,064 tokens: Information Society (91,825 tokens), Information Technology (80,483 tokens), and e-Learning (94,756 tokens)."
-    ],
-    "oai_identifier": [
-        "2f2a00e4b92f11e1a404080027e73ea2eccd095ad8b0407989b2adb143ab6095"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "CINTIL-Definitions"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b4030978-df4b-5cce-975f-f765d59f29e9.json b/oaitestdata/clarin-oai_dc/SET_1/json/b4030978-df4b-5cce-975f-f765d59f29e9.json
deleted file mode 100644
index bef24886..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b4030978-df4b-5cce-975f-f765d59f29e9.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "IPI PAN"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "downloadable_files_count: 11",
-        "application/vnd.oasis.opendocument.text",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/394",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/394"
-    ],
-    "PID": "http://hdl.handle.net/11321/394",
-    "PublicationTimestamp": "2017-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "IPI PAN"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Redzimska, Joanna"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/394;2018-06-13T05:35:16Z;hdl_11321_3;hdl_11321_4;metaphors;Redzimska, Joanna;metaphors;conceptual blending;THe collection of metaphors divided into thematic groups.;2017-05-30;corpus;http://hdl.handle.net/11321/394;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;text/plain;text/plain;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;application/vnd.oasis.opendocument.text;downloadable_files_count: 11;IPI PAN",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b4030978-df4b-5cce-975f-f765d59f29e9",
-    "notes": [
-        "THe collection of metaphors divided into thematic groups."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/394"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "metaphors"
-        },
-        {
-            "name": "conceptual blending"
-        }
-    ],
-    "title": [
-        "metaphors"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b4060391-db0b-5615-9763-5b7adc9938d5.json b/oaitestdata/clarin-oai_dc/SET_1/json/b4060391-db0b-5615-9763-5b7adc9938d5.json
deleted file mode 100644
index fbfd5026..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b4060391-db0b-5615-9763-5b7adc9938d5.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Technische Universit\u00e4t, Chemnitz , Universit\u00e4t Bayreuth"
-    ],
-    "Contributor": [
-        "Hudson-Ettle, Diana",
-        "Schmied, Josef"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-886",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-886"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-886",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Technische Universit\u00e4t, Chemnitz , Universit\u00e4t Bayreuth"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-886;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;International Corpus of English: East Africa (ICE-EA);Schmied, Josef;Hudson-Ettle, Diana;corpus;One million words of spoken and written English from Kenya and Tanzania. Part of the ICE project;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-886;eng;downloadable_files_count: 0;Germany;Technische Universit\u00e4t, Chemnitz , Universit\u00e4t Bayreuth;http://www.ucl.ac.uk/english-usage/ice/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b4060391-db0b-5615-9763-5b7adc9938d5",
-    "notes": [
-        "One million words of spoken and written English from Kenya and Tanzania. Part of the ICE project"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-886"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        }
-    ],
-    "title": [
-        "International Corpus of English: East Africa (ICE-EA)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b40988fc-df44-5481-8cfb-548e0579d44c.json b/oaitestdata/clarin-oai_dc/SET_1/json/b40988fc-df44-5481-8cfb-548e0579d44c.json
deleted file mode 100644
index 01562000..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b40988fc-df44-5481-8cfb-548e0579d44c.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4224",
-    "MetadataAccess": [
-        "oai:ota:oucs:4224"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Waldron, F. G. (Francis Godolphin), 1744-1818."
-    ],
-    "fulltext": "oai:ota:oucs:4224;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4224.xml;The virgin queen, a drama in five acts; attempted as a sequel to Shakespeare's Tempest;Waldron, F. G. (Francis Godolphin), 1744-1818.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b40988fc-df44-5481-8cfb-548e0579d44c",
-    "oai_identifier": [
-        "oai:ota:oucs:4224"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The virgin queen, a drama in five acts; attempted as a sequel to Shakespeare's Tempest"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4224.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b40b3f8a-2c9f-5008-af93-ca2a495ee6a0.json b/oaitestdata/clarin-oai_dc/SET_1/json/b40b3f8a-2c9f-5008-af93-ca2a495ee6a0.json
deleted file mode 100644
index 19b000df..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b40b3f8a-2c9f-5008-af93-ca2a495ee6a0.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/octet-stream",
-        "downloadable_files_count: 1",
-        "application/gzip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/257",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/257"
-    ],
-    "PID": "http://hdl.handle.net/11321/257",
-    "PublicationTimestamp": "2016-05-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "BSD 2 Clause",
-        "https://opensource.org/licenses/BSD-2-Clause",
-        "PUB"
-    ],
-    "author": [
-        "Woli\u0144ski, Marcin",
-        "Lenart, Micha\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/257;2016-05-10T12:34:06Z;hdl_11321_3;hdl_11321_4;Morfeusz 2;Woli\u0144ski, Marcin;Lenart, Micha\u0142;morphological analysis;inflection;morphological generation;Morfeusz 2 is a dictionary based morphological analyser and generator for Polish. This version of the program is decoupled from the dictionary. Two dictionaries of Polish developed within other projects are distributed with Morfeusz 2, namely SGJP and Polimorf.;2016-05-01;toolService;http://hdl.handle.net/11321/257;pol;BSD 2 Clause;https://opensource.org/licenses/BSD-2-Clause;PUB;text/plain; charset=utf-8;application/gzip;application/octet-stream;application/octet-stream;downloadable_files_count: 1;Institute of Computer Science, Polish Academy of Sciences;http://sgjp.pl/morfeusz/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b40b3f8a-2c9f-5008-af93-ca2a495ee6a0",
-    "notes": [
-        "Morfeusz 2 is a dictionary based morphological analyser and generator for Polish. This version of the program is decoupled from the dictionary. Two dictionaries of Polish developed within other projects are distributed with Morfeusz 2, namely SGJP and Polimorf."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/257"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphological analysis"
-        },
-        {
-            "name": "inflection"
-        },
-        {
-            "name": "morphological generation"
-        }
-    ],
-    "title": [
-        "Morfeusz 2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b40f4181-efb7-5465-b88c-ab516fc4f57e.json b/oaitestdata/clarin-oai_dc/SET_1/json/b40f4181-efb7-5465-b88c-ab516fc4f57e.json
deleted file mode 100644
index 1d9d5d6b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b40f4181-efb7-5465-b88c-ab516fc4f57e.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Wroclaw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/46",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/46"
-    ],
-    "PID": "http://hdl.handle.net/11321/46",
-    "PublicationTimestamp": "2014-10-24T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Wroclaw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Walkowiak, Tomasz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/46;2014-10-24T10:04:15Z;hdl_11321_3;hdl_11321_4;WCRFT Webservice (2014-10-24);Walkowiak, Tomasz;tagger;weblicht;Webservice for Weblicht;2014-10-24;toolService;http://hdl.handle.net/11321/46;pol;application/octet-stream;downloadable_files_count: 0;Wroclaw University of Technology;http://nlp.pwr.wroc.pl/redmine/projects/wcrft/wiki",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b40f4181-efb7-5465-b88c-ab516fc4f57e",
-    "notes": [
-        "Webservice for Weblicht"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/46"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "tagger"
-        },
-        {
-            "name": "weblicht"
-        }
-    ],
-    "title": [
-        "WCRFT Webservice (2014-10-24)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b411d33d-ad65-5e1a-9d3b-92f505730bf3.json b/oaitestdata/clarin-oai_dc/SET_1/json/b411d33d-ad65-5e1a-9d3b-92f505730bf3.json
deleted file mode 100644
index fa663fed..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b411d33d-ad65-5e1a-9d3b-92f505730bf3.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4821",
-    "MetadataAccess": [
-        "oai:ota:oucs:4821"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Churchill, Charles, 1731-1764."
-    ],
-    "fulltext": "oai:ota:oucs:4821;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4821.xml;Sermons. By Charles Churchill;Churchill, Charles, 1731-1764.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b411d33d-ad65-5e1a-9d3b-92f505730bf3",
-    "oai_identifier": [
-        "oai:ota:oucs:4821"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Sermons. By Charles Churchill"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4821.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b424c27d-a029-53de-870e-78df22c7575d.json b/oaitestdata/clarin-oai_dc/SET_1/json/b424c27d-a029-53de-870e-78df22c7575d.json
deleted file mode 100644
index 83a69332..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b424c27d-a029-53de-870e-78df22c7575d.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Charles University"
-    ],
-    "Contributor": [
-        "Hladk\u00e1, Barbora Vidov\u00e1"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1061",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1061"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1061",
-    "PublicationTimestamp": "2008-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2008"
-    ],
-    "Publisher": [
-        "Charles University"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "LDC Licence",
-        "LDC Catalog No.:\tLDC2008T22"
-    ],
-    "SpatialCoverage": [
-        "Czech Republic"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1061;2017-11-09T14:21:28Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Czech Academic Corpus (CAC) 2.0;Hladk\u00e1, Barbora Vidov\u00e1;The Prague family of annotated corpora has a new member, the Czech Academic Corpus version 2.0 (CAC 2.0). CAC 2.0 consists of 650,000 words from various 1970s and 1980s newspapers, magazines and radio and television broadcast transcripts manually annotated for morphology and syntax.;2008;corpus;http://hdl.handle.net/11372/LRT-1061;ces;LDC Licence;LDC Catalog No.:\tLDC2008T22;downloadable_files_count: 0;Czech Republic;Charles University;http://ufal.mff.cuni.cz/rest/cac.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b424c27d-a029-53de-870e-78df22c7575d",
-    "notes": [
-        "The Prague family of annotated corpora has a new member, the Czech Academic Corpus version 2.0 (CAC 2.0). CAC 2.0 consists of 650,000 words from various 1970s and 1980s newspapers, magazines and radio and television broadcast transcripts manually annotated for morphology and syntax."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1061"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Czech Academic Corpus (CAC) 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b4478229-80f3-55ac-abc4-4c69d1720f26.json b/oaitestdata/clarin-oai_dc/SET_1/json/b4478229-80f3-55ac-abc4-4c69d1720f26.json
deleted file mode 100644
index 3e42133e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b4478229-80f3-55ac-abc4-4c69d1720f26.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Marek Troszy\u0144ski"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/149",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/149"
-    ],
-    "PID": "http://hdl.handle.net/11321/149",
-    "PublicationTimestamp": "2015-04-13T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Marek Troszy\u0144ski"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Troszynski, Marek"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/149;2015-04-14T12:54:13Z;hdl_11321_3;hdl_11321_4;Romowie;Troszynski, Marek;Teksty o Romach w polskim internecie;2015-04-13;corpus;http://hdl.handle.net/11321/149;pol;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;application/vnd.openxmlformats-officedocument.spreadsheetml.sheet;application/zip;text/plain; charset=utf-8;downloadable_files_count: 2;Marek Troszy\u0144ski",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b4478229-80f3-55ac-abc4-4c69d1720f26",
-    "notes": [
-        "Teksty o Romach w polskim internecie"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/149"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Romowie"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b44a9b13-b09f-533a-b6e2-bee8d3f8146c.json b/oaitestdata/clarin-oai_dc/SET_1/json/b44a9b13-b09f-533a-b6e2-bee8d3f8146c.json
deleted file mode 100644
index 582731a1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b44a9b13-b09f-533a-b6e2-bee8d3f8146c.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/402",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/402"
-    ],
-    "PID": "http://hdl.handle.net/11321/402",
-    "PublicationTimestamp": "2015-10-09T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Oleksy, Marcin",
-        "Marci\u0144czuk, Micha\u0142",
-        "Koco\u0144, Jan"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/402;2018-04-04T14:46:23Z;hdl_11321_3;hdl_11321_4;KPWr Events;Koco\u0144, Jan;Marci\u0144czuk, Micha\u0142;Oleksy, Marcin;kpwr;event;event recognition;A set of documents annotated with event mentions extracted from the KPWr corpus. Process of annotation was described in the article:  Marci\u0144czuk, M., Oleksy et al. (2015). The set of documents was used in the initial experiments on event mention recognition and categorization described by Koco\u0144 and Marci\u0144czuk (2016). The package contains two divisions of the documents into train, tune and test parts.\r\n\r\nMarci\u0144czuk, M., Oleksy, M., Berna\u015b, T., Koco\u0144, J., & Wolski, M. (2015). Towards an event annotated corpus of Polish. Cognitive Studies| \u00c9tudes cognitives, (15), 253-267.\r\n(https://ispan.waw.pl/journals/index.php/cs-ec/article/view/cs.2015.018/1778)\r\n\r\nKoco\u0144 J., Marci\u0144czuk M. (2016) Generating of Events Dictionaries from Polish WordNet for the Recognition of Events in Polish Documents. In: Sojka P., Hor\u00e1k A., Kope\u010dek I., Pala K. (eds) Text, Speech, and Dialogue. TSD 2016. Lecture Notes in Computer Science, vol 9924. Springer, Cham (https://link.springer.com/chapter/10.1007/978-3-319-45510-5_2);2015-10-09;corpus;http://hdl.handle.net/11321/402;pol;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;Wroc\u0142aw University of Science and Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b44a9b13-b09f-533a-b6e2-bee8d3f8146c",
-    "notes": [
-        "A set of documents annotated with event mentions extracted from the KPWr corpus. Process of annotation was described in the article:  Marci\u0144czuk, M., Oleksy et al. (2015). The set of documents was used in the initial experiments on event mention recognition and categorization described by Koco\u0144 and Marci\u0144czuk (2016). The package contains two divisions of the documents into train, tune and test parts.\r\n\r\nMarci\u0144czuk, M., Oleksy, M., Berna\u015b, T., Koco\u0144, J., & Wolski, M. (2015). Towards an event annotated corpus of Polish. Cognitive Studies| \u00c9tudes cognitives, (15), 253-267.\r\n(https://ispan.waw.pl/journals/index.php/cs-ec/article/view/cs.2015.018/1778)\r\n\r\nKoco\u0144 J., Marci\u0144czuk M. (2016) Generating of Events Dictionaries from Polish WordNet for the Recognition of Events in Polish Documents. In: Sojka P., Hor\u00e1k A., Kope\u010dek I., Pala K. (eds) Text, Speech, and Dialogue. TSD 2016. Lecture Notes in Computer Science, vol 9924. Springer, Cham (https://link.springer.com/chapter/10.1007/978-3-319-45510-5_2)"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/402"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "kpwr"
-        },
-        {
-            "name": "event"
-        },
-        {
-            "name": "event recognition"
-        }
-    ],
-    "title": [
-        "KPWr Events"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b463d875-f7c0-5375-8ebb-1ec41ec3afc2.json b/oaitestdata/clarin-oai_dc/SET_1/json/b463d875-f7c0-5375-8ebb-1ec41ec3afc2.json
deleted file mode 100644
index b00687a1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b463d875-f7c0-5375-8ebb-1ec41ec3afc2.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Berlin-Brandenburg Academy of Sciences and Humanities"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/tei+xml",
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-972",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-972"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-972",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Berlin-Brandenburg Academy of Sciences and Humanities"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-972;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Korpus Gesprochene Sprache;Transcribed speech from the 20th century, about 2,5 million words. 7 categories, 756 speakers. Part of the DWDS project;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-972;deu;application/tei+xml;downloadable_files_count: 0;Germany;Berlin-Brandenburg Academy of Sciences and Humanities;http://www.dwds.de/ressourcen/gesprsprache/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b463d875-f7c0-5375-8ebb-1ec41ec3afc2",
-    "notes": [
-        "Transcribed speech from the 20th century, about 2,5 million words. 7 categories, 756 speakers. Part of the DWDS project"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-972"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Korpus Gesprochene Sprache"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b49fcc49-5de8-50f7-9f28-e87ed414b92f.json b/oaitestdata/clarin-oai_dc/SET_1/json/b49fcc49-5de8-50f7-9f28-e87ed414b92f.json
deleted file mode 100644
index dde7f86b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b49fcc49-5de8-50f7-9f28-e87ed414b92f.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "CNTS - Language Technology Group, \r\n University of Antwerp",
-        "ILK, Tilburg University"
-    ],
-    "Contributor": [
-        "Bosch, Antal van den",
-        "Daelemans, Walter"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Dutch",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1237",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1237"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1237",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "CNTS - Language Technology Group, \r\n University of Antwerp",
-        "ILK, Tilburg University"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Belgium||Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1237;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Memory-Based Shallow Parser (MBSP);Daelemans, Walter;Bosch, Antal van den;MBSP is a set of linguistic tools based on the TiMBL and MBT memory based learning applications developed at CNTS and ILK. It provides tools for Part of Speech tagging, Chunking, Lemmatizing, Relation Finding, Named Entity Recognition, and (for medical language) Semantic tagging.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1237;nld;eng;downloadable_files_count: 0;Belgium||Netherlands (the);ILK, Tilburg University;CNTS - Language Technology Group, \r\n University of Antwerp;http://www.clips.ua.ac.be/pages/MBSP",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b49fcc49-5de8-50f7-9f28-e87ed414b92f",
-    "notes": [
-        "MBSP is a set of linguistic tools based on the TiMBL and MBT memory based learning applications developed at CNTS and ILK. It provides tools for Part of Speech tagging, Chunking, Lemmatizing, Relation Finding, Named Entity Recognition, and (for medical language) Semantic tagging."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1237"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Memory-Based Shallow Parser (MBSP)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b4a954e6-fd21-5d91-94a0-9a59e0218dc7.json b/oaitestdata/clarin-oai_dc/SET_1/json/b4a954e6-fd21-5d91-94a0-9a59e0218dc7.json
deleted file mode 100644
index 93b85fa5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b4a954e6-fd21-5d91-94a0-9a59e0218dc7.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Pedagogical University of Krak\u00f3w"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 35",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/204",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/204"
-    ],
-    "PID": "http://hdl.handle.net/11321/204",
-    "PublicationTimestamp": "2015-06-02T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Pedagogical University of Krak\u00f3w"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Maciej, Eder"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/204;2015-06-02T16:27:48Z;hdl_11321_3;hdl_11321_4;Late 19th- and Early 20th-Century Polish Novels;Maciej, Eder;proza;Corpus of late 19th- and early 20th-century literary texts intended as benchmark collection for text categorization. It contains 100 Polish novels written by various authors. Each text is stored as separate .txt file.;2015-06-02;corpus;http://hdl.handle.net/11321/204;Polish;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain; charset=utf-8;downloadable_files_count: 35;Pedagogical University of Krak\u00f3w",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b4a954e6-fd21-5d91-94a0-9a59e0218dc7",
-    "notes": [
-        "Corpus of late 19th- and early 20th-century literary texts intended as benchmark collection for text categorization. It contains 100 Polish novels written by various authors. Each text is stored as separate .txt file."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/204"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "proza"
-        }
-    ],
-    "title": [
-        "Late 19th- and Early 20th-Century Polish Novels"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b4b9bd30-a359-56eb-a9cf-b45101dbd6ca.json b/oaitestdata/clarin-oai_dc/SET_1/json/b4b9bd30-a359-56eb-a9cf-b45101dbd6ca.json
deleted file mode 100644
index 62fca600..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b4b9bd30-a359-56eb-a9cf-b45101dbd6ca.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 3",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1035",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1035"
-    ],
-    "PID": "http://hdl.handle.net/11356/1035",
-    "PublicationTimestamp": "2013-09-30T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Krek, Simon",
-        "Holozan, Peter",
-        "Erjavec, Toma\u017e",
-        "Gr\u010dar, Miha",
-        "Logar, Nata\u0161a"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1035;2017-09-29T13:48:01Z;hdl_11356_1023;hdl_11356_1024;Written corpus ccGigafida 1.0;Logar, Nata\u0161a;Erjavec, Toma\u017e;Krek, Simon;Gr\u010dar, Miha;Holozan, Peter;TEI;Corpus ccGigafida consists of paragraph samples from 31,722 documents, each containing information about the source (e.g. newspapers, magazines), year of publication, text type (fiction, newspaper), the title and author if they are known. The corpus is annotated with morphosyntactic descriptions (PoS-tagged) and lemmatised. It is encoded in XML TEI format (Text Encoding Initiative P5). The ccGigafida corpus contains approximately 9% of the Gigafida corpus, a reference corpus of Slovene: http://eng.slovenscina.eu/korpusi/gigafida.\r\n\r\nThe corpus is available in source TEI-like XML and in the simpler and smaller vertical format, used by various concordancers. The XML file has PoS (MSD) tags in Slovenian only, while the vertical file has tags both in Slovenian and English. The corpus is also available as plain text, on file per text.;2013-09-30;corpus;http://hdl.handle.net/11356/1035;slv;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);https://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 3;Centre for Language Resources and Technologies, University of Ljubljana;http://eng.slovenscina.eu/korpusi/proste-zbirke",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b4b9bd30-a359-56eb-a9cf-b45101dbd6ca",
-    "notes": [
-        "Corpus ccGigafida consists of paragraph samples from 31,722 documents, each containing information about the source (e.g. newspapers, magazines), year of publication, text type (fiction, newspaper), the title and author if they are known. The corpus is annotated with morphosyntactic descriptions (PoS-tagged) and lemmatised. It is encoded in XML TEI format (Text Encoding Initiative P5). The ccGigafida corpus contains approximately 9% of the Gigafida corpus, a reference corpus of Slovene: http://eng.slovenscina.eu/korpusi/gigafida.\r\n\r\nThe corpus is available in source TEI-like XML and in the simpler and smaller vertical format, used by various concordancers. The XML file has PoS (MSD) tags in Slovenian only, while the vertical file has tags both in Slovenian and English. The corpus is also available as plain text, on file per text."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1035"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "Written corpus ccGigafida 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b4bf4d8f-8676-5847-a060-f8f439c22d46.json b/oaitestdata/clarin-oai_dc/SET_1/json/b4bf4d8f-8676-5847-a060-f8f439c22d46.json
deleted file mode 100644
index ffaa7a9a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b4bf4d8f-8676-5847-a060-f8f439c22d46.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3510",
-    "MetadataAccess": [
-        "oai:ota:oucs:3510"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dibdin, Charles, 1745-1814."
-    ],
-    "fulltext": "oai:ota:oucs:3510;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3510.xml;The cestus: a serenata. Performed at the Royal Circus, in St. George's Fields.;Dibdin, Charles, 1745-1814.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b4bf4d8f-8676-5847-a060-f8f439c22d46",
-    "oai_identifier": [
-        "oai:ota:oucs:3510"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The cestus: a serenata. Performed at the Royal Circus, in St. George's Fields."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3510.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b4c7c84f-e174-51f7-a312-6077643f9349.json b/oaitestdata/clarin-oai_dc/SET_1/json/b4c7c84f-e174-51f7-a312-6077643f9349.json
deleted file mode 100644
index ad606c4d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b4c7c84f-e174-51f7-a312-6077643f9349.json
+++ /dev/null
@@ -1,100 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 3",
-        "application/pdf",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Croatian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1121",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1121"
-    ],
-    "PID": "http://hdl.handle.net/11356/1121",
-    "PublicationTimestamp": "2017-05-14T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11356/1170",
-        "http://hdl.handle.net/11356/1095"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "Filko, Matea",
-        "Erjavec, Toma\u017e",
-        "Farka\u0161, Da\u0161a",
-        "Ljube\u0161i\u0107, Nikola",
-        "Dujmi\u0107, Barbara",
-        "Klubi\u010dka, Filip",
-        "Mili\u010devi\u0107, Maja",
-        "Kranj\u010di\u0107, Denis"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1121;2018-10-24T20:58:04Z;hdl_11356_1023;hdl_11356_1024;Croatian Twitter training corpus ReLDI-NormTag-hr 1.1;Ljube\u0161i\u0107, Nikola;Farka\u0161, Da\u0161a;Klubi\u010dka, Filip;Erjavec, Toma\u017e;Mili\u010devi\u0107, Maja;Filko, Matea;Kranj\u010di\u0107, Denis;Dujmi\u0107, Barbara;computer-mediated communication;tokenisation;word normalisation;tagging;lemmatisation;manual annotation;TEI;ReLDI-NormTag-hr 1.1 is a manually annotated corpus of Croatian tweets. It is meant as a gold-standard training and testing dataset for tokenisation, sentence segmentation, word normalisation, morphosyntactic tagging and lemmatisation of non-standard Croatian. Each tweet is also annotated for its automatically assigned standardness levels (T = technical standardness, L = linguistic standardness). As an update to version 1.0, 1.1 corrects some minor errors. \r\n\r\nThe corpus construction is (partially) described in: \r\nMILI\u010cEVI\u0106, Maja, LJUBE\u0160I\u0106, Nikola. Tviterasi, tvitera\u0161i or twittera\u0161i? Producing and analysing a normalised dataset of Croatian and Serbian tweets. Sloven\u0161\u010dina 2.0: empirical, applied and interdisciplinary research, 4/2, 2016. ISSN 2335-2736. http://dx.doi.org/10.4312/slo2.0.2016.2.156-188;2017-05-14;corpus;http://hdl.handle.net/11356/1121;hrv;http://hdl.handle.net/11356/1170;http://hdl.handle.net/11356/1095;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;https://creativecommons.org/licenses/by/4.0/;application/zip;application/zip;application/pdf;text/plain; charset=utf-8;downloadable_files_count: 3;Jo\u017eef Stefan Institute;https://reldi.spur.uzh.ch/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b4c7c84f-e174-51f7-a312-6077643f9349",
-    "notes": [
-        "ReLDI-NormTag-hr 1.1 is a manually annotated corpus of Croatian tweets. It is meant as a gold-standard training and testing dataset for tokenisation, sentence segmentation, word normalisation, morphosyntactic tagging and lemmatisation of non-standard Croatian. Each tweet is also annotated for its automatically assigned standardness levels (T = technical standardness, L = linguistic standardness). As an update to version 1.0, 1.1 corrects some minor errors. \r\n\r\nThe corpus construction is (partially) described in: \r\nMILI\u010cEVI\u0106, Maja, LJUBE\u0160I\u0106, Nikola. Tviterasi, tvitera\u0161i or twittera\u0161i? Producing and analysing a normalised dataset of Croatian and Serbian tweets. Sloven\u0161\u010dina 2.0: empirical, applied and interdisciplinary research, 4/2, 2016. ISSN 2335-2736. http://dx.doi.org/10.4312/slo2.0.2016.2.156-188"
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1121"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "computer-mediated communication"
-        },
-        {
-            "name": "tokenisation"
-        },
-        {
-            "name": "word normalisation"
-        },
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "lemmatisation"
-        },
-        {
-            "name": "manual annotation"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "Croatian Twitter training corpus ReLDI-NormTag-hr 1.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b4f2c530-5df8-50b6-b839-ded02f6f4fdc.json b/oaitestdata/clarin-oai_dc/SET_1/json/b4f2c530-5df8-50b6-b839-ded02f6f4fdc.json
deleted file mode 100644
index 01cb069f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b4f2c530-5df8-50b6-b839-ded02f6f4fdc.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=b325bb8495e611e6a2aa782bcb0741356b5403f31a544dfa8a7a114182a14964",
-    "MetadataAccess": [
-        "b325bb8495e611e6a2aa782bcb0741356b5403f31a544dfa8a7a114182a14964"
-    ],
-    "PublicationTimestamp": "2016-10-19T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "fulltext": "b325bb8495e611e6a2aa782bcb0741356b5403f31a544dfa8a7a114182a14964;2018-11-15T16:40:24Z;lexicalConceptualResource;lexicalConceptualResource:computationalLexicon;LX-DSemVectors;Distributional semantic representation of Portuguese words (aka word embeddings).;2016-10-19",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b4f2c530-5df8-50b6-b839-ded02f6f4fdc",
-    "notes": [
-        "Distributional semantic representation of Portuguese words (aka word embeddings)."
-    ],
-    "oai_identifier": [
-        "b325bb8495e611e6a2aa782bcb0741356b5403f31a544dfa8a7a114182a14964"
-    ],
-    "oai_set": [
-        "lexicalConceptualResource",
-        "lexicalConceptualResource:computationalLexicon"
-    ],
-    "state": "active",
-    "title": [
-        "LX-DSemVectors"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b51d26ad-344e-5843-b193-4d9800a16b9c.json b/oaitestdata/clarin-oai_dc/SET_1/json/b51d26ad-344e-5843-b193-4d9800a16b9c.json
deleted file mode 100644
index 13209701..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b51d26ad-344e-5843-b193-4d9800a16b9c.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "UMCS"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/137",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/137"
-    ],
-    "PID": "http://hdl.handle.net/11321/137",
-    "PublicationTimestamp": "2015-04-07T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "UMCS"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Andrew, Radomski"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/137;2015-04-13T09:40:53Z;hdl_11321_3;hdl_11321_4;Text;Andrew, Radomski;Science;Humanities;about science;2015-04-07;corpus;http://hdl.handle.net/11321/137;eng;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain; charset=utf-8;downloadable_files_count: 1;UMCS",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b51d26ad-344e-5843-b193-4d9800a16b9c",
-    "notes": [
-        "about science"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/137"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Science"
-        },
-        {
-            "name": "Humanities"
-        }
-    ],
-    "title": [
-        "Text"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b5460aee-c170-5652-9f65-f820b4ad582e.json b/oaitestdata/clarin-oai_dc/SET_1/json/b5460aee-c170-5652-9f65-f820b4ad582e.json
deleted file mode 100644
index 8e741932..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b5460aee-c170-5652-9f65-f820b4ad582e.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-8F1B-4",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-8F1B-4"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-8F1B-4",
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Peterek, Nino"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-8F1B-4;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Dialogy.Org;Peterek, Nino;multimedia corpora search service;The Dialogy.Org system allows users to search in transcribed audio-visual corpora. The Dialogy.Org works on the principle of web-based interface, so installation of additional programs on your computer is not necessary. You must have Flash Player for playing audio or video recordings.;2014;toolService;http://hdl.handle.net/11858/00-097C-0000-0023-8F1B-4;downloadable_files_count: 0;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://dialogy.org",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b5460aee-c170-5652-9f65-f820b4ad582e",
-    "notes": [
-        "The Dialogy.Org system allows users to search in transcribed audio-visual corpora. The Dialogy.Org works on the principle of web-based interface, so installation of additional programs on your computer is not necessary. You must have Flash Player for playing audio or video recordings."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-8F1B-4"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "multimedia corpora search service"
-        }
-    ],
-    "title": [
-        "Dialogy.Org"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b5486a36-4d75-54e8-87c1-e395543ee43f.json b/oaitestdata/clarin-oai_dc/SET_1/json/b5486a36-4d75-54e8-87c1-e395543ee43f.json
deleted file mode 100644
index c19057d1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b5486a36-4d75-54e8-87c1-e395543ee43f.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/35",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/35"
-    ],
-    "PID": "http://hdl.handle.net/10794/35",
-    "PublicationTimestamp": "2012-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/35;2017-10-27T14:19:54Z;hdl_10794_1;hdl_10794_2;SALDO: examples (2017-10-16);SALDO: exempel (2017-10-16);n/a, n/a;Swedish;Sense examples;Example sentences for senses in SALDO.;Exempelmeningar f\u00f6r SALDO-betydelser.;2012-05-30;lexicalConceptualResource;http://hdl.handle.net/10794/35;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/saldoe",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b5486a36-4d75-54e8-87c1-e395543ee43f",
-    "notes": [
-        "Example sentences for senses in SALDO.",
-        "Exempelmeningar f\u00f6r SALDO-betydelser."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/35"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Sense examples"
-        }
-    ],
-    "title": [
-        "SALDO: examples (2017-10-16)",
-        "SALDO: exempel (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b5580889-92d8-58a5-989a-fa0fd628b7fd.json b/oaitestdata/clarin-oai_dc/SET_1/json/b5580889-92d8-58a5-989a-fa0fd628b7fd.json
deleted file mode 100644
index e2c2576d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b5580889-92d8-58a5-989a-fa0fd628b7fd.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "Modern Greek (1453-)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-947",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-947"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-947",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-947;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Classical Greek;ca. 700.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-947;ell;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#klgrie",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b5580889-92d8-58a5-989a-fa0fd628b7fd",
-    "notes": [
-        "ca. 700.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-947"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Classical Greek"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b5633112-5908-584e-9c14-941f329f0e7e.json b/oaitestdata/clarin-oai_dc/SET_1/json/b5633112-5908-584e-9c14-941f329f0e7e.json
deleted file mode 100644
index 3bfeb197..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b5633112-5908-584e-9c14-941f329f0e7e.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 3",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1192",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1192"
-    ],
-    "PID": "http://hdl.handle.net/11356/1192",
-    "PublicationTimestamp": "2018-08-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "https://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Dobrovoljc, Kaja"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1192;2018-08-01T17:32:32Z;hdl_11356_1023;hdl_11356_1024;Janes corpus n-grams 1.0;Dobrovoljc, Kaja;n-grams;wordlist;multiword expressions;A collection of n-grams extracted from the Janes corpus of Slovenian user-generated content version 1.0 (cf. http://nl.ijs.si/janes/). Three sets of n-gram lists are provided for lowercased word n-grams of length 1 to 5:\r\n- extensive frequency lists of all extracted n-grams\r\n- filtered frequency lists of n-grams with minimum frequency 10/mil.\r\n- adjusted frequency list of all n-grams with minimum frequency 10/mil.\r\n\r\nOnly n-grams within sentences have been counted, ignoring punctuation. For the filtered and adjusted list, only n-grams occurring in at least 2 different texts have been extracted.\r\n\r\nKey references:\r\n- K. Dobrovoljc, 2018. N-gram frequency lists for reference corpora of Slovenian language. Proceedings of the Language Technologies & Digital Humanities Conference 2018.\r\n- T. Erjavec, N. Ljube\u0161i\u0107, D. Fi\u0161er, 2018. Korpus slovenskih spletnih uporabni\u0161kih vsebin Janes. V: FI\u0160ER, Darja (ur.). Viri, orodja in metode za analizo spletne sloven\u0161\u010dine. Znanstvena zalo\u017eba Filozofske fakultete Univerze v Ljubljani. https://e-knjige.ff.uni-lj.si/znanstvena-zalozba/catalog/book/111\r\n- M. B. O\u2019Donnell, 2010. The adjusted frequency list: A method to produce cluster-sensitive frequency lists. ICAME Journal 35, 135\u2013169.;2018-08-01;lexicalConceptualResource;http://hdl.handle.net/11356/1192;slv;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);https://creativecommons.org/licenses/by-sa/4.0/;PUB;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 3;Centre for Language Resources and Technologies, University of Ljubljana",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b5633112-5908-584e-9c14-941f329f0e7e",
-    "notes": [
-        "A collection of n-grams extracted from the Janes corpus of Slovenian user-generated content version 1.0 (cf. http://nl.ijs.si/janes/). Three sets of n-gram lists are provided for lowercased word n-grams of length 1 to 5:\r\n- extensive frequency lists of all extracted n-grams\r\n- filtered frequency lists of n-grams with minimum frequency 10/mil.\r\n- adjusted frequency list of all n-grams with minimum frequency 10/mil.\r\n\r\nOnly n-grams within sentences have been counted, ignoring punctuation. For the filtered and adjusted list, only n-grams occurring in at least 2 different texts have been extracted.\r\n\r\nKey references:\r\n- K. Dobrovoljc, 2018. N-gram frequency lists for reference corpora of Slovenian language. Proceedings of the Language Technologies & Digital Humanities Conference 2018.\r\n- T. Erjavec, N. Ljube\u0161i\u0107, D. Fi\u0161er, 2018. Korpus slovenskih spletnih uporabni\u0161kih vsebin Janes. V: FI\u0160ER, Darja (ur.). Viri, orodja in metode za analizo spletne sloven\u0161\u010dine. Znanstvena zalo\u017eba Filozofske fakultete Univerze v Ljubljani. https://e-knjige.ff.uni-lj.si/znanstvena-zalozba/catalog/book/111\r\n- M. B. O\u2019Donnell, 2010. The adjusted frequency list: A method to produce cluster-sensitive frequency lists. ICAME Journal 35, 135\u2013169."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1192"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "n-grams"
-        },
-        {
-            "name": "wordlist"
-        },
-        {
-            "name": "multiword expressions"
-        }
-    ],
-    "title": [
-        "Janes corpus n-grams 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b56e8aa6-7e8f-51d8-99a4-85411a085370.json b/oaitestdata/clarin-oai_dc/SET_1/json/b56e8aa6-7e8f-51d8-99a4-85411a085370.json
deleted file mode 100644
index fe9029f8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b56e8aa6-7e8f-51d8-99a4-85411a085370.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English",
-        "Estonian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-252",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-252"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-252",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Estonia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-252;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Estonian-English parallel corpus;written EU legislation; 5 mio words Est, 7.8 mio words Eng; Sentence-aligned;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-252;eng;est;downloadable_files_count: 0;Estonia;http://www.cl.ut.ee/korpused/paralleel/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b56e8aa6-7e8f-51d8-99a4-85411a085370",
-    "notes": [
-        "written EU legislation; 5 mio words Est, 7.8 mio words Eng; Sentence-aligned"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-252"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Estonian-English parallel corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b5704569-6c46-579c-9f2e-a028306de1eb.json b/oaitestdata/clarin-oai_dc/SET_1/json/b5704569-6c46-579c-9f2e-a028306de1eb.json
deleted file mode 100644
index 4d2885bf..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b5704569-6c46-579c-9f2e-a028306de1eb.json
+++ /dev/null
@@ -1,119 +0,0 @@
-{
-    "Contact": [
-        "Technische Universit\u00e4t Darmstadt"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/x-gzip",
-        "downloadable_files_count: 36",
-        "text/plain"
-    ],
-    "Language": [
-        "Afrikaans",
-        "Arabic",
-        "Bulgarian",
-        "Czech",
-        "Danish",
-        "German",
-        "Modern Greek (1453-)",
-        "English",
-        "Estonian",
-        "Persian",
-        "Finnish",
-        "French",
-        "Croatian",
-        "Hungarian",
-        "Indonesian",
-        "Italian",
-        "Japanese",
-        "Korean",
-        "Latvian",
-        "Lithuanian",
-        "Dutch",
-        "Norwegian",
-        "Polish",
-        "Portuguese",
-        "Russian",
-        "Slovenian",
-        "Somali",
-        "Spanish",
-        "Swahili (macrolanguage)",
-        "Swedish",
-        "Tagalog",
-        "Thai",
-        "Turkish",
-        "Ukrainian",
-        "Undetermined",
-        "Vietnamese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2209",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2209"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2209",
-    "PublicationTimestamp": "2016-04-14T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Technische Universit\u00e4t Darmstadt"
-    ],
-    "RelatedIdentifier": [
-        "http://www.lrec-conf.org/proceedings/lrec2016/pdf/388_Paper.pdf"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Public Domain Mark (PD)",
-        "PUB",
-        "http://creativecommons.org/publicdomain/mark/1.0/"
-    ],
-    "author": [
-        "Habernal, Ivan",
-        "Gurevych, Iryna",
-        "Zayed, Omnia"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2209;2019-01-02T14:28:01Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;C4Corpus (publicdomain part);Gurevych, Iryna;Habernal, Ivan;Zayed, Omnia;CommonCrawl;Creative Commons;Web corpus;Amazon Web Services;A large web corpus (over 10 billion tokens) licensed under CreativeCommons license family in 50+ languages that has been extracted from CommonCrawl, the largest publicly available general Web crawl to date with about 2 billion crawled URLs.;2016-04-14;corpus;http://hdl.handle.net/11372/LRT-2209;afr;ara;bul;ces;dan;deu;ell;eng;est;fas;fin;fra;hrv;hun;ind;ita;jpn;kor;lav;lit;nld;nor;pol;por;rus;slv;som;spa;swa;swe;tgl;tha;tur;ukr;und;vie;http://www.lrec-conf.org/proceedings/lrec2016/pdf/388_Paper.pdf;Public Domain Mark (PD);PUB;http://creativecommons.org/publicdomain/mark/1.0/;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;text/plain;downloadable_files_count: 36;Technische Universit\u00e4t Darmstadt;https://dkpro.github.io/dkpro-c4corpus/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b5704569-6c46-579c-9f2e-a028306de1eb",
-    "notes": [
-        "A large web corpus (over 10 billion tokens) licensed under CreativeCommons license family in 50+ languages that has been extracted from CommonCrawl, the largest publicly available general Web crawl to date with about 2 billion crawled URLs."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2209"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "CommonCrawl"
-        },
-        {
-            "name": "Creative Commons"
-        },
-        {
-            "name": "Web corpus"
-        },
-        {
-            "name": "Amazon Web Services"
-        }
-    ],
-    "title": [
-        "C4Corpus (publicdomain part)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b5724834-c4fb-5ef7-b612-36945c20378c.json b/oaitestdata/clarin-oai_dc/SET_1/json/b5724834-c4fb-5ef7-b612-36945c20378c.json
deleted file mode 100644
index c2552721..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b5724834-c4fb-5ef7-b612-36945c20378c.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "ZRC SAZU"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1130",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1130"
-    ],
-    "PID": "http://hdl.handle.net/11356/1130",
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "ZRC SAZU"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Humar, Marjeta",
-        "Hajn\u0161ek-Holz, Milena",
-        "Praznik, Zvonka",
-        "Ko\u0161mrlj-Leva\u010di\u010d, Borislava",
-        "Jakopin, Franc",
-        "Keber, Janez",
-        "Nartnik, Vlado",
-        "\u0160ircelj \u017dnidar\u0161i\u010d, Ivanka",
-        "Kostanjevec, Polona",
-        "Bokal, Milka",
-        "\u017dele, Andreja"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1130;2017-08-30T08:47:18Z;hdl_11356_1023;hdl_11356_1024;Dictionary of Lesser Used Slovenian Words;Bokal, Milka;Hajn\u0161ek-Holz, Milena;Humar, Marjeta;Jakopin, Franc;Praznik, Zvonka;\u0160ircelj \u017dnidar\u0161i\u010d, Ivanka;Kostanjevec, Polona;\u017dele, Andreja;Nartnik, Vlado;Keber, Janez;Ko\u0161mrlj-Leva\u010di\u010d, Borislava;dictionary;lexicography;Dictionary of Lesser Used Slovenian Words contains 178457 headwords not included in the Dictionary of the Slovenian Standard Language. Information on inflection, part of speech and source is included in the entries.\r\n\r\nThis dictionary was published as a printed book:\r\nBokal, Ljudmila, Hajn\u0161ek-Holz, Milena, Humar, Marjeta, Jakopin, Franc, Praznik, Zvonka. Besedi\u0161\u010de slovenskega jezika : po kartoteki za slovar sodobnega knji\u017enega jezika zbrane besede, ki niso bile sprejete v Slovar slovenskega knji\u017enega jezika. 1: A-N, 2: O-\u017d. Ljubljana: ZRC SAZU, 1987. Internal edition.\r\n\r\n\u0160ircelj-\u017dnidar\u0161i\u010d, Ivanka, Hajn\u0161ek-Holz, Milena, Kostanjevec, Polona, \u017dele, Andreja, Humar, Marjeta, Nartnik, Vlado, Keber, Janez, Ko\u0161mrlj-Leva\u010di\u010d, Borislava, Jakopin, Primo\u017e. Besedi\u0161\u010de slovenskega jezika z oblikoslovnimi podatki : A - \u017d : po gradivu za slovar sodobnega knji\u017enega jezika zbrane besede, ki niso bile sprejete v Slovar slovenskega knji\u017enega jezika. Ljubljana: ZRC SAZU, Zalo\u017eba ZRC SAZU, 1998. ISBN 961-6182-62-5.;2017;lexicalConceptualResource;http://hdl.handle.net/11356/1130;slv;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;ZRC SAZU;http://bos.zrc-sazu.si/besedisc.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b5724834-c4fb-5ef7-b612-36945c20378c",
-    "notes": [
-        "Dictionary of Lesser Used Slovenian Words contains 178457 headwords not included in the Dictionary of the Slovenian Standard Language. Information on inflection, part of speech and source is included in the entries.\r\n\r\nThis dictionary was published as a printed book:\r\nBokal, Ljudmila, Hajn\u0161ek-Holz, Milena, Humar, Marjeta, Jakopin, Franc, Praznik, Zvonka. Besedi\u0161\u010de slovenskega jezika : po kartoteki za slovar sodobnega knji\u017enega jezika zbrane besede, ki niso bile sprejete v Slovar slovenskega knji\u017enega jezika. 1: A-N, 2: O-\u017d. Ljubljana: ZRC SAZU, 1987. Internal edition.\r\n\r\n\u0160ircelj-\u017dnidar\u0161i\u010d, Ivanka, Hajn\u0161ek-Holz, Milena, Kostanjevec, Polona, \u017dele, Andreja, Humar, Marjeta, Nartnik, Vlado, Keber, Janez, Ko\u0161mrlj-Leva\u010di\u010d, Borislava, Jakopin, Primo\u017e. Besedi\u0161\u010de slovenskega jezika z oblikoslovnimi podatki : A - \u017d : po gradivu za slovar sodobnega knji\u017enega jezika zbrane besede, ki niso bile sprejete v Slovar slovenskega knji\u017enega jezika. Ljubljana: ZRC SAZU, Zalo\u017eba ZRC SAZU, 1998. ISBN 961-6182-62-5."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1130"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "dictionary"
-        },
-        {
-            "name": "lexicography"
-        }
-    ],
-    "title": [
-        "Dictionary of Lesser Used Slovenian Words"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b58c49ae-85d6-5c26-855f-980056a9bcdf.json b/oaitestdata/clarin-oai_dc/SET_1/json/b58c49ae-85d6-5c26-855f-980056a9bcdf.json
deleted file mode 100644
index 91cad1cd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b58c49ae-85d6-5c26-855f-980056a9bcdf.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1135",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1135"
-    ],
-    "PID": "http://hdl.handle.net/11356/1135",
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/H2020/640772",
-        "http://dx.doi.org/10.1186/s40649-017-0042-6"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "https://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Cherepnalkoski, Darko",
-        "Kralj Novak, Petra",
-        "Gr\u010dar, Miha",
-        "Mozeti\u010d, Igor"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1135;2017-08-23T15:49:02Z;hdl_11356_1023;hdl_11356_1024;Brexit stance annotated tweets;Gr\u010dar, Miha;Cherepnalkoski, Darko;Mozeti\u010d, Igor;Kralj Novak, Petra;Twitter;Brexit;stance;computer-mediated communication;The corpus contains over 4.5 million tweets (tweet IDs) automatically labeled by a machine learning program with stance regarding Brexit: Positive (supporting Brexit), Negative (opposing Brexit), or Neutral (uncommitted).\r\n\r\nThe Brexit referendum was held on June 23, 2016, to decide whether the UK should leave or remain in the EU. In the weeks before the referendum, starting on May 12, the UK geo-located Brexit-related tweets were continuously collected resulting in a dataset of around 4.5 million (4,508,440) tweets from almost one million (998,054) users. A large sample of the collected tweets (35,000) was manually labeled for the stance of their authors regarding Brexit: Positive (supporting Brexit), Negative (opposing Brexit), or Neutral (uncommitted). The labeled tweets were used to train a classifier which then automatically labeled all the remaining tweets.\r\n\r\nThe corpus contains tweet ids and stance labels. The tweets are grouped into files one hour per file. In each file, one row represents one entry (twitter_id, sentiment_label). Lines are ordered by the tweet time.\r\n\r\nThe data collection, annotation, model training and performance estimation  is described in detail in:\r\nMiha Gr\u010dar, Darko Cherepnalkoski, Igor Mozeti\u010d, Petra Kralj Novak:\r\nStance and influence of Twitter users regarding the Brexit referendum.\r\nComputational Social Networks 4/6. 2017. http://dx.doi.org/10.1186/s40649-017-0042-6;2016;corpus;http://hdl.handle.net/11356/1135;eng;info:eu-repo/grantAgreement/EC/H2020/640772;http://dx.doi.org/10.1186/s40649-017-0042-6;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);https://creativecommons.org/licenses/by-sa/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Jo\u017eef Stefan Institute",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b58c49ae-85d6-5c26-855f-980056a9bcdf",
-    "notes": [
-        "The corpus contains over 4.5 million tweets (tweet IDs) automatically labeled by a machine learning program with stance regarding Brexit: Positive (supporting Brexit), Negative (opposing Brexit), or Neutral (uncommitted).\r\n\r\nThe Brexit referendum was held on June 23, 2016, to decide whether the UK should leave or remain in the EU. In the weeks before the referendum, starting on May 12, the UK geo-located Brexit-related tweets were continuously collected resulting in a dataset of around 4.5 million (4,508,440) tweets from almost one million (998,054) users. A large sample of the collected tweets (35,000) was manually labeled for the stance of their authors regarding Brexit: Positive (supporting Brexit), Negative (opposing Brexit), or Neutral (uncommitted). The labeled tweets were used to train a classifier which then automatically labeled all the remaining tweets.\r\n\r\nThe corpus contains tweet ids and stance labels. The tweets are grouped into files one hour per file. In each file, one row represents one entry (twitter_id, sentiment_label). Lines are ordered by the tweet time.\r\n\r\nThe data collection, annotation, model training and performance estimation  is described in detail in:\r\nMiha Gr\u010dar, Darko Cherepnalkoski, Igor Mozeti\u010d, Petra Kralj Novak:\r\nStance and influence of Twitter users regarding the Brexit referendum.\r\nComputational Social Networks 4/6. 2017. http://dx.doi.org/10.1186/s40649-017-0042-6"
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1135"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Twitter"
-        },
-        {
-            "name": "Brexit"
-        },
-        {
-            "name": "stance"
-        },
-        {
-            "name": "computer-mediated communication"
-        }
-    ],
-    "title": [
-        "Brexit stance annotated tweets"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b5a71944-fa59-58be-8b1e-36fb7928d6db.json b/oaitestdata/clarin-oai_dc/SET_1/json/b5a71944-fa59-58be-8b1e-36fb7928d6db.json
deleted file mode 100644
index ee5f5904..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b5a71944-fa59-58be-8b1e-36fb7928d6db.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/27",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/27"
-    ],
-    "PID": "http://hdl.handle.net/10794/27",
-    "PublicationTimestamp": "2015-03-24T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/27;2017-10-27T15:16:33Z;hdl_10794_1;hdl_10794_2;Idioms from the NEO lexicon DB;Idiom ur NEO-databasen;n/a, n/a;Swedish;Idioms;Idioms with explanations extracted from the database for the dictionary  Nationalencyklopediens ordbok.;Idiom med beskrivningar och alternativformer extraherade ut databasen f\u00f6r Nationalencyklopediens ordbok.;2015-03-24;lexicalConceptualResource;http://hdl.handle.net/10794/27;swe;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;PUB;application/vnd.openxmlformats-officedocument.spreadsheetml.sheet;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/neo-idiom",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b5a71944-fa59-58be-8b1e-36fb7928d6db",
-    "notes": [
-        "Idioms with explanations extracted from the database for the dictionary  Nationalencyklopediens ordbok.",
-        "Idiom med beskrivningar och alternativformer extraherade ut databasen f\u00f6r Nationalencyklopediens ordbok."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/27"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Idioms"
-        }
-    ],
-    "title": [
-        "Idioms from the NEO lexicon DB",
-        "Idiom ur NEO-databasen"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b5a76f39-b01c-5646-91d4-c952fff1ce40.json b/oaitestdata/clarin-oai_dc/SET_1/json/b5a76f39-b01c-5646-91d4-c952fff1ce40.json
deleted file mode 100644
index a961a99d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b5a76f39-b01c-5646-91d4-c952fff1ce40.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Sienkiewicz"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 87",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/110",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/110"
-    ],
-    "PID": "http://hdl.handle.net/11321/110",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Sienkiewicz"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Sienkiewicz, Sienkiewicz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/110;2017-02-04T13:29:10Z;hdl_11321_3;hdl_11321_4;MWE Sienkiewicz, Ogniem i mieczem;Sienkiewicz, Sienkiewicz;Sienkiewicz;2015-04-08;corpus;http://hdl.handle.net/11321/110;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 87;Sienkiewicz",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b5a76f39-b01c-5646-91d4-c952fff1ce40",
-    "notes": [
-        "Sienkiewicz"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/110"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Sienkiewicz, Ogniem i mieczem"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b5fa8fbc-88bc-5293-b92e-f675069d163c.json b/oaitestdata/clarin-oai_dc/SET_1/json/b5fa8fbc-88bc-5293-b92e-f675069d163c.json
deleted file mode 100644
index 886af6d2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b5fa8fbc-88bc-5293-b92e-f675069d163c.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 115 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0145",
-    "MetadataAccess": [
-        "oai:ota:oucs:0145"
-    ],
-    "PublicationTimestamp": "1606-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1606"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Tourneur, Cyril, 1575?-1626"
-    ],
-    "fulltext": "oai:ota:oucs:0145;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0145.xml;The revenger\u00e2\u0080\u0099s tragedy / Cyril Tourneur;Tourneur, Cyril, 1575?-1626;1606;text_and_corpus_linguistics;English drama -- 17th century;eng;Oxford Text Archive, University of Oxford;(1 file : ca. 115 KB);Text;Plays;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b5fa8fbc-88bc-5293-b92e-f675069d163c",
-    "oai_identifier": [
-        "oai:ota:oucs:0145"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- th century"
-        }
-    ],
-    "title": [
-        "The revenger\u00e2\u0080\u0099s tragedy / Cyril Tourneur"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0145.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b622d762-074a-5254-97ca-baebc1ba2079.json b/oaitestdata/clarin-oai_dc/SET_1/json/b622d762-074a-5254-97ca-baebc1ba2079.json
deleted file mode 100644
index 91c5f21e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b622d762-074a-5254-97ca-baebc1ba2079.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "ZRC SAZU"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1155",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1155"
-    ],
-    "PID": "http://hdl.handle.net/11356/1155",
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "ZRC SAZU"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Jakopin, Primo\u017e"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1155;2017-09-25T08:53:32Z;hdl_11356_1023;hdl_11356_1024;Nova Beseda Frequency Lexicon;Jakopin, Primo\u017e;word forms;lexicon;Nova beseda Frequency Lexicon was compiled from the Nova beseda text corpus at the Fran Ramov\u0161 Institute of Slovenian Language with hyphen characters unified and with leading and trailing non-breaking spaces deleted.\r\n\r\nUnlike most other Slovenian corpora Nova beseda texts were pre-processed before inclusion. Typos and words with supefluous hyphens, originating from false line joinings were corrected and parts of texts in foreign, non-Slovenian language were marked-up and excluded from the lexicon.\r\n\r\nThe corpus contains 318 million tokens, mostly wordforms. It is available for search through the web page http://bos.zrc-sazu.si/a_beseda.html, where wordform search is reached by selecting \"word seach\" in the right hand side \"What to do?\" column. On the mentioned web page the corpus structure is also explained.\r\n\r\nThe lexicon is UTF-8 coded, has 2,251,151 lines, each containing the following 2 data fields, tab separated:\r\n\r\n1. token, Slovenian: pojavnica.\r\n      The vast majority of tokens are wordforms, also included are numbers and selected multiword units such as URLs, e-mail addresses, place names like New York, car plates, ID numbers.\r\n\r\n2. frequency, Slovenian: pogostnost.\r\n      The sum of all frequencies is 318,170,212.;2017;lexicalConceptualResource;http://hdl.handle.net/11356/1155;slv;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;PUB;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;ZRC SAZU;http://bos.zrc-sazu.si/a_beseda.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b622d762-074a-5254-97ca-baebc1ba2079",
-    "notes": [
-        "Nova beseda Frequency Lexicon was compiled from the Nova beseda text corpus at the Fran Ramov\u0161 Institute of Slovenian Language with hyphen characters unified and with leading and trailing non-breaking spaces deleted.\r\n\r\nUnlike most other Slovenian corpora Nova beseda texts were pre-processed before inclusion. Typos and words with supefluous hyphens, originating from false line joinings were corrected and parts of texts in foreign, non-Slovenian language were marked-up and excluded from the lexicon.\r\n\r\nThe corpus contains 318 million tokens, mostly wordforms. It is available for search through the web page http://bos.zrc-sazu.si/a_beseda.html, where wordform search is reached by selecting \"word seach\" in the right hand side \"What to do?\" column. On the mentioned web page the corpus structure is also explained.\r\n\r\nThe lexicon is UTF-8 coded, has 2,251,151 lines, each containing the following 2 data fields, tab separated:\r\n\r\n1. token, Slovenian: pojavnica.\r\n      The vast majority of tokens are wordforms, also included are numbers and selected multiword units such as URLs, e-mail addresses, place names like New York, car plates, ID numbers.\r\n\r\n2. frequency, Slovenian: pogostnost.\r\n      The sum of all frequencies is 318,170,212."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1155"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "word forms"
-        },
-        {
-            "name": "lexicon"
-        }
-    ],
-    "title": [
-        "Nova Beseda Frequency Lexicon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b63e5293-f199-5f40-bcb8-581eda6474ac.json b/oaitestdata/clarin-oai_dc/SET_1/json/b63e5293-f199-5f40-bcb8-581eda6474ac.json
deleted file mode 100644
index ea83f541..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b63e5293-f199-5f40-bcb8-581eda6474ac.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3132",
-    "MetadataAccess": [
-        "oai:ota:oucs:3132"
-    ],
-    "PublicationTimestamp": "1539-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1539"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Erasmus, Desiderius, d. 1536"
-    ],
-    "fulltext": "oai:ota:oucs:3132;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3132.xml;Adagia. Selections. Lat.-Engl;Proverbes or adagies;Adagies;Chiliades;Erasmus, Desiderius, d. 1536;not after: 1539;text_and_corpus_linguistics;Proverbs, Latin -- 16th century;eng;Oxford Text Archive, University of Oxford;Triggs, Jeffery;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b63e5293-f199-5f40-bcb8-581eda6474ac",
-    "oai_identifier": [
-        "oai:ota:oucs:3132"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Proverbs"
-        },
-        {
-            "name": "Latin -- th century"
-        }
-    ],
-    "title": [
-        "Adagia. Selections. Lat.-Engl",
-        "Proverbes or adagies",
-        "Adagies",
-        "Chiliades"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3132.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b644ce30-8788-5962-bf7f-4576ef66f1e0.json b/oaitestdata/clarin-oai_dc/SET_1/json/b644ce30-8788-5962-bf7f-4576ef66f1e0.json
deleted file mode 100644
index 01e3b652..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b644ce30-8788-5962-bf7f-4576ef66f1e0.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=6ca376ae63ec11e2a2aa782bcb0741351880c46daa1a4165869725de33498c23",
-    "MetadataAccess": [
-        "6ca376ae63ec11e2a2aa782bcb0741351880c46daa1a4165869725de33498c23"
-    ],
-    "PublicationTimestamp": "2013-01-21T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "6ca376ae63ec11e2a2aa782bcb0741351880c46daa1a4165869725de33498c23;2018-11-15T16:40:06Z;corpus;corpus:text;DeepBankPT ;The DeepBankPT (Branco et. al. 2010) is a corpus of semantic dependencies of translated texts composed of 3,406 sentences and 44,598 tokens taken from the Wall Street Journal.\n\nThe DeepBankPT is composed of MRS and AVM representations, derivation tree, and syntactic tree with grammatical and semantic labels of each sentence\u00e2\u0080\u0099s. This is the result of a previous semi-automatic analysis with a double-blind annotation followed by adjudication (see Branco and Costa, 2008, with a full description of the process). The resulting dataset contains one information level: semantic relations.\n\nThe main motivation behind the creation of this resource was to build a high quality data set with syntactic information that could support the development of a large set of automatic resources and tools for Portuguese for NLP studies.\n\nThe development of this resource started under the METANET4U project (at: http://metanet4u.eu/) whose main goal is to contribute to the establishment of a pan-European digital platform that makes available language resources and services, encompassing both datasets and software tools, for speech and language processing, and supports a new generation of exchange facilities for them. \n;2013-01-21",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b644ce30-8788-5962-bf7f-4576ef66f1e0",
-    "notes": [
-        "The DeepBankPT (Branco et. al. 2010) is a corpus of semantic dependencies of translated texts composed of 3,406 sentences and 44,598 tokens taken from the Wall Street Journal.\n\nThe DeepBankPT is composed of MRS and AVM representations, derivation tree, and syntactic tree with grammatical and semantic labels of each sentence\u00e2\u0080\u0099s. This is the result of a previous semi-automatic analysis with a double-blind annotation followed by adjudication (see Branco and Costa, 2008, with a full description of the process). The resulting dataset contains one information level: semantic relations.\n\nThe main motivation behind the creation of this resource was to build a high quality data set with syntactic information that could support the development of a large set of automatic resources and tools for Portuguese for NLP studies.\n\nThe development of this resource started under the METANET4U project (at: http://metanet4u.eu/) whose main goal is to contribute to the establishment of a pan-European digital platform that makes available language resources and services, encompassing both datasets and software tools, for speech and language processing, and supports a new generation of exchange facilities for them. \n"
-    ],
-    "oai_identifier": [
-        "6ca376ae63ec11e2a2aa782bcb0741351880c46daa1a4165869725de33498c23"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "DeepBankPT "
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b64714a6-3696-5a9c-9c6d-6305aa6e25d1.json b/oaitestdata/clarin-oai_dc/SET_1/json/b64714a6-3696-5a9c-9c6d-6305aa6e25d1.json
deleted file mode 100644
index 3fb21a52..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b64714a6-3696-5a9c-9c6d-6305aa6e25d1.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 185 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2185",
-    "MetadataAccess": [
-        "oai:ota:oucs:2185"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Melville, Herman, 1819-1891"
-    ],
-    "fulltext": "oai:ota:oucs:2185;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/2185.xml;Billy Buddy, foretopman / by Herman Melville;Melville, Herman, 1819-1891;default: 1976-01-01;text_and_corpus_linguistics;Fiction -- United States -- 20th century;Novellas -- United States -- 20th century;eng;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 185 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b64714a6-3696-5a9c-9c6d-6305aa6e25d1",
-    "oai_identifier": [
-        "oai:ota:oucs:2185"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- United States -- th century"
-        },
-        {
-            "name": "Novellas -- United States -- th century"
-        }
-    ],
-    "title": [
-        "Billy Buddy, foretopman / by Herman Melville"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2185.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b6772217-39ec-500d-88be-433c6ba74ccb.json b/oaitestdata/clarin-oai_dc/SET_1/json/b6772217-39ec-500d-88be-433c6ba74ccb.json
deleted file mode 100644
index 9604d7c4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b6772217-39ec-500d-88be-433c6ba74ccb.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2391",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2391"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2391",
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Ku\u010dera, Ond\u0159ej",
-        "Kuchy\u0148ov\u00e1, Karol\u00edna",
-        "Hladk\u00e1, Barbora"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2391;2018-07-02T22:05:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;STYX 1.0;Hladk\u00e1, Barbora;Ku\u010dera, Ond\u0159ej;Kuchy\u0148ov\u00e1, Karol\u00edna;annotated corpus;syntax;sentence diagramming;STYX 1.0 is a corpus of Czech sentences selected from the Prague Dependency treebank. The criterion for including sentences into STYX was their suitability for practicing Czech morphology and syntax in elementary schools. The sentences contain both the PDT annotations and the school sentence analyses. The school sentence analyses were created by transforming the PDT annotations using handcrafted rules. Altogether the STYX 1.0 corpus contains 11 655 sentences.\r\n\r\nOriginally, the STYX 1.0 corpus was an inseparable part of the Styx system (http://hdl.handle.net/11858/00-097C-0000-0001-48FB-F);2017;corpus;http://hdl.handle.net/11234/1-2391;ces;Creative Commons - Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0);http://creativecommons.org/licenses/by-nc-nd/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/styx",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b6772217-39ec-500d-88be-433c6ba74ccb",
-    "notes": [
-        "STYX 1.0 is a corpus of Czech sentences selected from the Prague Dependency treebank. The criterion for including sentences into STYX was their suitability for practicing Czech morphology and syntax in elementary schools. The sentences contain both the PDT annotations and the school sentence analyses. The school sentence analyses were created by transforming the PDT annotations using handcrafted rules. Altogether the STYX 1.0 corpus contains 11 655 sentences.\r\n\r\nOriginally, the STYX 1.0 corpus was an inseparable part of the Styx system (http://hdl.handle.net/11858/00-097C-0000-0001-48FB-F)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2391"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "annotated corpus"
-        },
-        {
-            "name": "syntax"
-        },
-        {
-            "name": "sentence diagramming"
-        }
-    ],
-    "title": [
-        "STYX 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b6da5940-d1d3-5519-8a67-f588aa493e2e.json b/oaitestdata/clarin-oai_dc/SET_1/json/b6da5940-d1d3-5519-8a67-f588aa493e2e.json
deleted file mode 100644
index 00b4217f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b6da5940-d1d3-5519-8a67-f588aa493e2e.json
+++ /dev/null
@@ -1,88 +0,0 @@
-{
-    "Contact": [
-        "European Commission",
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 3",
-        "text/plain",
-        "application/zip"
-    ],
-    "Language": [
-        "Danish",
-        "English",
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repository.clarin.dk:20.500.12115/30",
-    "MetadataAccess": [
-        "oai:repository.clarin.dk:20.500.12115/30"
-    ],
-    "PID": "http://hdl.handle.net/20.500.12115/30",
-    "PublicationTimestamp": "2012-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "European Commission",
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN-ACA-NC",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NC=1&NORED=1",
-        "ACA"
-    ],
-    "author": [
-        "Hansen, Dorte",
-        "Offersgaard, Lene"
-    ],
-    "fulltext": "oai:repository.clarin.dk:20.500.12115/30;2018-06-28T13:28:40Z;hdl_20.500.12115_1;hdl_20.500.12115_3;DK-CLARIN Rapid Aligned Corpus 1993-2011 (da-en, da-de);Hansen, Dorte;Offersgaard, Lene;MT;EU;press relase;alignment;politics;The aligned corpus consists of press releases from the European Commission Press Relase Database (Rapid) harvested in 2009 and 2011 (http://europa.eu/rapid/search.htm).\r\n\r\nThe corpus comprises 5330 + 2200 press releases (files) for each language Danish, English and German with app. 5,000,000 words per language and 260,000 - 270,000 aligned sentences for the language pair Danish - English and Danish - German.\r\n\r\nAll documents are processed with Uplug (https://bitbucket.org/tiedemann/uplug/wiki/Home) and aligned with HunAlign.\r\nFiles with more than 10 % negative alignments have been removed and so has all 0-alignmants.\r\nThe documents are in txt-format for each language and in tmx-format for the aligned language pairs (da-en and da-de).;2012;corpus;http://hdl.handle.net/20.500.12115/30;dan;eng;deu;CLARIN-ACA-NC;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NC=1&NORED=1;ACA;text/plain; charset=utf-8;application/zip;application/zip;text/plain;downloadable_files_count: 3;Centre for Language Technology, NorS, University of Copenhagen;European Commission",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b6da5940-d1d3-5519-8a67-f588aa493e2e",
-    "notes": [
-        "The aligned corpus consists of press releases from the European Commission Press Relase Database (Rapid) harvested in 2009 and 2011 (http://europa.eu/rapid/search.htm).\r\n\r\nThe corpus comprises 5330 + 2200 press releases (files) for each language Danish, English and German with app. 5,000,000 words per language and 260,000 - 270,000 aligned sentences for the language pair Danish - English and Danish - German.\r\n\r\nAll documents are processed with Uplug (https://bitbucket.org/tiedemann/uplug/wiki/Home) and aligned with HunAlign.\r\nFiles with more than 10 % negative alignments have been removed and so has all 0-alignmants.\r\nThe documents are in txt-format for each language and in tmx-format for the aligned language pairs (da-en and da-de)."
-    ],
-    "oai_identifier": [
-        "oai:repository.clarin.dk:20.500.12115/30"
-    ],
-    "oai_set": [
-        "hdl_20.500.12115_1",
-        "hdl_20.500.12115_3"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "MT"
-        },
-        {
-            "name": "EU"
-        },
-        {
-            "name": "press relase"
-        },
-        {
-            "name": "alignment"
-        },
-        {
-            "name": "politics"
-        }
-    ],
-    "title": [
-        "DK-CLARIN Rapid Aligned Corpus 1993-2011 (da-en, da-de)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b6ed2ff5-44a9-55d3-abda-72bf568af462.json b/oaitestdata/clarin-oai_dc/SET_1/json/b6ed2ff5-44a9-55d3-abda-72bf568af462.json
deleted file mode 100644
index e607f190..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b6ed2ff5-44a9-55d3-abda-72bf568af462.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Tilde"
-    ],
-    "Contributor": [
-        "Skadi\u0146\u0161, Raivis"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Latvian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1215",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1215"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1215",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Tilde"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Latvia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1215;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Latvian language morphological analysis/generation system;Skadi\u0146\u0161, Raivis;Morphologycal analyser and form generation tool.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1215;lav;downloadable_files_count: 0;Latvia;Tilde;http://www.letonika.lv/groups/default.aspx?g=5&q=",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b6ed2ff5-44a9-55d3-abda-72bf568af462",
-    "notes": [
-        "Morphologycal analyser and form generation tool."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1215"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Latvian language morphological analysis/generation system"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b6efdf87-96f1-5b86-8c03-28b551c79365.json b/oaitestdata/clarin-oai_dc/SET_1/json/b6efdf87-96f1-5b86-8c03-28b551c79365.json
deleted file mode 100644
index dd44ac00..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b6efdf87-96f1-5b86-8c03-28b551c79365.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "The National Library of Sweden"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/20",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/20"
-    ],
-    "PID": "http://hdl.handle.net/10794/20",
-    "PublicationTimestamp": "2015-04-23T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "The National Library of Sweden"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/20;2017-10-27T16:49:48Z;hdl_10794_1;hdl_10794_2;Aftonbladet 1860's (2017-10-16);Aftonbladet 1860-talet (2017-10-16);n/a, n/a;Swedish;News;A corpus with texts from Aftonbladet in the 1860's. Only 1860\u20131862 due to copyright restrictions.;En korpus med texter fr\u00e5n Aftonbladet p\u00e5 1860-talet. Endast 1860\u20131862 p\u00e5 grund av copyright-sk\u00e4l.;2015-04-23;corpus;http://hdl.handle.net/10794/20;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;The National Library of Sweden;https://spraakbanken.gu.se/swe/resurs/kubhist-aftonbladet-1860",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b6efdf87-96f1-5b86-8c03-28b551c79365",
-    "notes": [
-        "A corpus with texts from Aftonbladet in the 1860's. Only 1860\u20131862 due to copyright restrictions.",
-        "En korpus med texter fr\u00e5n Aftonbladet p\u00e5 1860-talet. Endast 1860\u20131862 p\u00e5 grund av copyright-sk\u00e4l."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/20"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "News"
-        }
-    ],
-    "title": [
-        "Aftonbladet 1860's (2017-10-16)",
-        "Aftonbladet 1860-talet (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b7075b13-7b00-5478-a917-43d62b05f483.json b/oaitestdata/clarin-oai_dc/SET_1/json/b7075b13-7b00-5478-a917-43d62b05f483.json
deleted file mode 100644
index 3c80e12f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b7075b13-7b00-5478-a917-43d62b05f483.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "IPI PAN"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "downloadable_files_count: 10",
-        "application/vnd.oasis.opendocument.text",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/370",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/370"
-    ],
-    "PID": "http://hdl.handle.net/11321/370",
-    "PublicationTimestamp": "2017-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "IPI PAN"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "\u0141aszkiewicz, Monika"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/370;2017-05-30T07:54:14Z;hdl_11321_3;hdl_11321_4;test1;\u0141aszkiewicz, Monika;corpus;Corpus;2017-05-30;corpus;http://hdl.handle.net/11321/370;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;application/vnd.oasis.opendocument.text;text/plain;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;downloadable_files_count: 10;IPI PAN",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b7075b13-7b00-5478-a917-43d62b05f483",
-    "notes": [
-        "Corpus"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/370"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        }
-    ],
-    "title": [
-        "test1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b709aa1c-cc44-542c-af55-6b29c68177b4.json b/oaitestdata/clarin-oai_dc/SET_1/json/b709aa1c-cc44-542c-af55-6b29c68177b4.json
deleted file mode 100644
index 459d2a5a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b709aa1c-cc44-542c-af55-6b29c68177b4.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-207",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-207"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-207",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Slovenia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-207;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Slovene Dependency Treebank;3,000 sentences, analytical structure (PDT);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-207;slv;downloadable_files_count: 0;Slovenia;http://nl.ijs.si/sdt/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b709aa1c-cc44-542c-af55-6b29c68177b4",
-    "notes": [
-        "3,000 sentences, analytical structure (PDT)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-207"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Slovene Dependency Treebank"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b71e4cb9-55a6-58c3-86a9-aa4e079d0be6.json b/oaitestdata/clarin-oai_dc/SET_1/json/b71e4cb9-55a6-58c3-86a9-aa4e079d0be6.json
deleted file mode 100644
index e7d2c1c8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b71e4cb9-55a6-58c3-86a9-aa4e079d0be6.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Masaryk University, NLP Centre"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1933",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1933"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1933",
-    "PublicationTimestamp": "2016-12-02T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Masaryk University, NLP Centre"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Baisa, V\u00edt"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1933;2018-07-02T22:05:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Czech Grammar Agreement Dataset for Evaluation of Language Models;Baisa, V\u00edt;agreement;past tense verb suffix;language model;training data;AGREE is a dataset and task for evaluation of language models based on grammar agreement in Czech. The dataset consists of sentences with marked suffixes of past tense verbs. The task is to choose the right verb suffix which depends on gender, number and animacy of subject. It is challenging for language models because 1) Czech is morphologically rich, 2) it has relatively free word order, 3) high out-of-vocabulary (OOV) ratio, 4) predicate and subject can be far from each other, 5) subjects can be unexpressed and 6) various semantic rules may apply. The task provides a straightforward and easily reproducible way of evaluating language models on a morphologically rich language.;2016-12-02;corpus;http://hdl.handle.net/11234/1-1933;ces;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Masaryk University, NLP Centre;https://www.muni.cz/vyzkum/publikace/1362555",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b71e4cb9-55a6-58c3-86a9-aa4e079d0be6",
-    "notes": [
-        "AGREE is a dataset and task for evaluation of language models based on grammar agreement in Czech. The dataset consists of sentences with marked suffixes of past tense verbs. The task is to choose the right verb suffix which depends on gender, number and animacy of subject. It is challenging for language models because 1) Czech is morphologically rich, 2) it has relatively free word order, 3) high out-of-vocabulary (OOV) ratio, 4) predicate and subject can be far from each other, 5) subjects can be unexpressed and 6) various semantic rules may apply. The task provides a straightforward and easily reproducible way of evaluating language models on a morphologically rich language."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1933"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "agreement"
-        },
-        {
-            "name": "past tense verb suffix"
-        },
-        {
-            "name": "language model"
-        },
-        {
-            "name": "training data"
-        }
-    ],
-    "title": [
-        "Czech Grammar Agreement Dataset for Evaluation of Language Models"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b71ff810-e9e4-5852-ba22-940c09bcf94b.json b/oaitestdata/clarin-oai_dc/SET_1/json/b71ff810-e9e4-5852-ba22-940c09bcf94b.json
deleted file mode 100644
index 64ff9ce0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b71ff810-e9e4-5852-ba22-940c09bcf94b.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3774",
-    "MetadataAccess": [
-        "oai:ota:oucs:3774"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gerard, Alexander, 1728-1795."
-    ],
-    "fulltext": "oai:ota:oucs:3774;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3774.xml;The influence of piety on the public good. A sermon, preached in the High Church of Edinburgh, May 31. 1761, ... By Alexander Gerard,;Gerard, Alexander, 1728-1795.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b71ff810-e9e4-5852-ba22-940c09bcf94b",
-    "oai_identifier": [
-        "oai:ota:oucs:3774"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The influence of piety on the public good. A sermon, preached in the High Church of Edinburgh, May 31. 1761, ... By Alexander Gerard,"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3774.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b73f1949-2876-51a8-a0b3-f25806df94f1.json b/oaitestdata/clarin-oai_dc/SET_1/json/b73f1949-2876-51a8-a0b3-f25806df94f1.json
deleted file mode 100644
index e1044da1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b73f1949-2876-51a8-a0b3-f25806df94f1.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Masaryk University, NLP Centre"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-000D-F67A-9",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-000D-F67A-9"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-000D-F67A-9",
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Masaryk University, NLP Centre"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "BSD 3-Clause \"New\" or \"Revised\" license",
-        "http://opensource.org/licenses/BSD-3-Clause",
-        "PUB"
-    ],
-    "author": [
-        "Pomik\u00e1lek, Jan"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-000D-F67A-9;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Chared;Pomik\u00e1lek, Jan;character encoding;character encoding detection;charset;unicode;Chared is a software tool which can detect character encoding of a text document provided the language of the document is known. The language of the text has to be specified as an input parameter so that the corresponding language model can be used. The package contains models for a wide range of languages (currently 57 --- covering all major languages). Furthermore, it provides a training script to learn models for additional languages using a set of user supplied sample html pages in the given language. The detection algorithm is based on determining similarity of byte trigrams vectors. In general, chared should be more accurate than other character encoding detection tools with no language constraints. This is an important advantage allowing precise character decoding needed for building large textual corpora. The tool has been used for building corpora in American Spanish, Arabic, Czech, French, Japanese, Russian, Tajik, and six Turkic languages consisting of 70 billions tokens altogether. Chared is an open source software, licensed under New BSD License and available for download (including the source code) at http://code.google.com/p/chared/. The research leading to this piece of software was published in POMIK\u00c1LEK, Jan a V\u00edt SUCHOMEL. chared: Character Encoding Detection with a Known Language. In Ale\u0161 Hor\u00e1k, Pavel Rychl\u00fd. RASLAN 2011. 5. vyd. Brno, Czech Republic: Tribun EU, 2011. od s. 125-129, 5 s. ISBN 978-80-263-0077-9.;2011;toolService;http://hdl.handle.net/11858/00-097C-0000-000D-F67A-9;eng;BSD 3-Clause \"New\" or \"Revised\" license;http://opensource.org/licenses/BSD-3-Clause;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Masaryk University, NLP Centre;http://code.google.com/p/chared/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b73f1949-2876-51a8-a0b3-f25806df94f1",
-    "notes": [
-        "Chared is a software tool which can detect character encoding of a text document provided the language of the document is known. The language of the text has to be specified as an input parameter so that the corresponding language model can be used. The package contains models for a wide range of languages (currently 57 --- covering all major languages). Furthermore, it provides a training script to learn models for additional languages using a set of user supplied sample html pages in the given language. The detection algorithm is based on determining similarity of byte trigrams vectors. In general, chared should be more accurate than other character encoding detection tools with no language constraints. This is an important advantage allowing precise character decoding needed for building large textual corpora. The tool has been used for building corpora in American Spanish, Arabic, Czech, French, Japanese, Russian, Tajik, and six Turkic languages consisting of 70 billions tokens altogether. Chared is an open source software, licensed under New BSD License and available for download (including the source code) at http://code.google.com/p/chared/. The research leading to this piece of software was published in POMIK\u00c1LEK, Jan a V\u00edt SUCHOMEL. chared: Character Encoding Detection with a Known Language. In Ale\u0161 Hor\u00e1k, Pavel Rychl\u00fd. RASLAN 2011. 5. vyd. Brno, Czech Republic: Tribun EU, 2011. od s. 125-129, 5 s. ISBN 978-80-263-0077-9."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-000D-F67A-9"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "character encoding"
-        },
-        {
-            "name": "character encoding detection"
-        },
-        {
-            "name": "charset"
-        },
-        {
-            "name": "unicode"
-        }
-    ],
-    "title": [
-        "Chared"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b760a6e3-da53-5ba5-bb48-f308d4f4c919.json b/oaitestdata/clarin-oai_dc/SET_1/json/b760a6e3-da53-5ba5-bb48-f308d4f4c919.json
deleted file mode 100644
index 28ffb71b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b760a6e3-da53-5ba5-bb48-f308d4f4c919.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 97.5 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1337",
-    "MetadataAccess": [
-        "oai:ota:oucs:1337"
-    ],
-    "PublicationTimestamp": "1551-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1551"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:1337;2018-04-26T12:45:55Z;http://ota.ox.ac.uk/headers/1337.xml;Gammer Gurton's needle;Gammer Gvrtons Nedle;1551-1561;text_and_corpus_linguistics;Comedies -- England -- 16th century;Plays -- England -- 16th century;eng;Oxford Text Archive, University of Oxford;(1 file : ca. 97.5 KB);Text;Plays;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b760a6e3-da53-5ba5-bb48-f308d4f4c919",
-    "oai_identifier": [
-        "oai:ota:oucs:1337"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Comedies -- England -- th century"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        }
-    ],
-    "title": [
-        "Gammer Gurton's needle",
-        "Gammer Gvrtons Nedle"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1337.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b777b25a-5936-5204-842b-fef111428e5c.json b/oaitestdata/clarin-oai_dc/SET_1/json/b777b25a-5936-5204-842b-fef111428e5c.json
deleted file mode 100644
index e296ceec..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b777b25a-5936-5204-842b-fef111428e5c.json
+++ /dev/null
@@ -1,112 +0,0 @@
-{
-    "Contact": [
-        "Institute for Applied Linguistics, Eurac Research"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 10",
-        "text/html",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech",
-        "German",
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin.eurac.edu:20.500.12124/5",
-    "MetadataAccess": [
-        "oai:clarin.eurac.edu:20.500.12124/5"
-    ],
-    "PID": "http://hdl.handle.net/20.500.12124/5",
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institute for Applied Linguistics, Eurac Research"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/200250",
-        "https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-docs/tags/v1.0",
-        "https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-text/tags/v1.0",
-        "https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-metadata/tags/v1.0",
-        "https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-tasks/tags/v1.0",
-        "https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-paula/tags/v1.0",
-        "https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-annis/tags/v1.0",
-        "https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-exmaralda/tags/v1.0",
-        "https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-solr/tags/v1.0",
-        "https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-relannis/tags/v1.0",
-        "http://www.lrec-conf.org/proceedings/lrec2014/summaries/606.html",
-        "http://hdl.handle.net/20.500.12124/6"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Blaschitz, Verena",
-        "Wisniewski, Katrin",
-        "Vodi\u010dkov\u00e1, Kate\u0159ina",
-        "Pe\u010den\u00fd, Pavel",
-        "Klein, Gudrun",
-        "Hana, Jirka",
-        "Krivanek, Julia",
-        "Lyding, Verena",
-        "Abel, Andrea",
-        "Plassmann, Sybille",
-        "Lauppe, Louise",
-        "Vettori, Chiara",
-        "Nicolas, Lionel",
-        "\u0160tindlov\u00e1, Barbora",
-        "Woldt, Claudia",
-        "Bykh, Serhiy",
-        "Meurers, Detmar",
-        "\u010curdov\u00e1, Veronika",
-        "Sch\u00f6ne, Karin",
-        "Boyd, Adriane"
-    ],
-    "fulltext": "oai:clarin.eurac.edu:20.500.12124/5;2018-09-04T09:26:59Z;hdl_20.500.12124_1;hdl_20.500.12124_4;MERLIN Written Learner Corpus for Czech, German, Italian 1.0;Wisniewski, Katrin;Abel, Andrea;Vodi\u010dkov\u00e1, Kate\u0159ina;Plassmann, Sybille;Meurers, Detmar;Woldt, Claudia;Sch\u00f6ne, Karin;Blaschitz, Verena;Lyding, Verena;Nicolas, Lionel;Vettori, Chiara;Pe\u010den\u00fd, Pavel;Hana, Jirka;\u010curdov\u00e1, Veronika;\u0160tindlov\u00e1, Barbora;Klein, Gudrun;Lauppe, Louise;Boyd, Adriane;Bykh, Serhiy;Krivanek, Julia;CEFR;language learning;learner corpus;The MERLIN corpus is a written learner corpus for Czech, German, and Italian that has been designed to illustrate the Common European Framework of Reference for Languages (CEFR) with authentic learner data. The corpus contains learner texts produced in standardized language certifications covering CEFR levels A1-C1. The MERLIN annotation scheme includes a wide range of language characteristics that provide researchers with concrete examples of learner performance and progress across multiple proficiency levels.;2014-12;corpus;http://hdl.handle.net/20.500.12124/5;ces;deu;ita;info:eu-repo/grantAgreement/EC/FP7/200250;https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-docs/tags/v1.0;https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-text/tags/v1.0;https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-metadata/tags/v1.0;https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-tasks/tags/v1.0;https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-paula/tags/v1.0;https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-annis/tags/v1.0;https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-exmaralda/tags/v1.0;https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-solr/tags/v1.0;https://gitlab.inf.unibz.it/commul/merlin-platform/merlin-relannis/tags/v1.0;http://www.lrec-conf.org/proceedings/lrec2014/summaries/606.html;http://hdl.handle.net/20.500.12124/6;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;PUB;text/html;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 10;Institute for Applied Linguistics, Eurac Research;https://merlin-platform.eu",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b777b25a-5936-5204-842b-fef111428e5c",
-    "notes": [
-        "The MERLIN corpus is a written learner corpus for Czech, German, and Italian that has been designed to illustrate the Common European Framework of Reference for Languages (CEFR) with authentic learner data. The corpus contains learner texts produced in standardized language certifications covering CEFR levels A1-C1. The MERLIN annotation scheme includes a wide range of language characteristics that provide researchers with concrete examples of learner performance and progress across multiple proficiency levels."
-    ],
-    "oai_identifier": [
-        "oai:clarin.eurac.edu:20.500.12124/5"
-    ],
-    "oai_set": [
-        "hdl_20.500.12124_1",
-        "hdl_20.500.12124_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "CEFR"
-        },
-        {
-            "name": "language learning"
-        },
-        {
-            "name": "learner corpus"
-        }
-    ],
-    "title": [
-        "MERLIN Written Learner Corpus for Czech, German, Italian 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b77db064-b709-507c-9454-8d12c98c5a7f.json b/oaitestdata/clarin-oai_dc/SET_1/json/b77db064-b709-507c-9454-8d12c98c5a7f.json
deleted file mode 100644
index 828a1728..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b77db064-b709-507c-9454-8d12c98c5a7f.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3039",
-    "MetadataAccess": [
-        "oai:ota:oucs:3039"
-    ],
-    "PublicationTimestamp": "1859-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1859"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Darwin, Charles, 1809-1882"
-    ],
-    "fulltext": "oai:ota:oucs:3039;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3039.xml;On the Origin of Species by Means of Natural Selection, or the Preservation of Favoured Races in the Struggle for Life;Darwin, Charles, 1809-1882;not after: 1859;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b77db064-b709-507c-9454-8d12c98c5a7f",
-    "oai_identifier": [
-        "oai:ota:oucs:3039"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "On the Origin of Species by Means of Natural Selection, or the Preservation of Favoured Races in the Struggle for Life"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3039.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b7af4cfe-22d1-5405-adb3-ca23bbf4235f.json b/oaitestdata/clarin-oai_dc/SET_1/json/b7af4cfe-22d1-5405-adb3-ca23bbf4235f.json
deleted file mode 100644
index db418377..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b7af4cfe-22d1-5405-adb3-ca23bbf4235f.json
+++ /dev/null
@@ -1,133 +0,0 @@
-{
-    "Contact": [
-        "Technische Universit\u00e4t Darmstadt"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/x-gzip",
-        "text/plain",
-        "downloadable_files_count: 52"
-    ],
-    "Language": [
-        "Afrikaans",
-        "Arabic",
-        "Bengali",
-        "Bulgarian",
-        "Czech",
-        "Danish",
-        "German",
-        "Modern Greek (1453-)",
-        "English",
-        "Estonian",
-        "Persian",
-        "Finnish",
-        "French",
-        "Hebrew",
-        "Hindi",
-        "Croatian",
-        "Hungarian",
-        "Indonesian",
-        "Italian",
-        "Japanese",
-        "Kannada",
-        "Korean",
-        "Latvian",
-        "Lithuanian",
-        "Malayalam",
-        "Macedonian",
-        "Nepali (macrolanguage)",
-        "Dutch",
-        "Norwegian",
-        "Panjabi",
-        "Polish",
-        "Portuguese",
-        "Romanian",
-        "Russian",
-        "Slovak",
-        "Slovenian",
-        "Somali",
-        "Spanish",
-        "Albanian",
-        "Swahili (macrolanguage)",
-        "Swedish",
-        "Tamil",
-        "Telugu",
-        "Tagalog",
-        "Thai",
-        "Turkish",
-        "Ukrainian",
-        "Undetermined",
-        "Vietnamese",
-        "Chinese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2204",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2204"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2204",
-    "PublicationTimestamp": "2016-04-14T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Technische Universit\u00e4t Darmstadt"
-    ],
-    "RelatedIdentifier": [
-        "http://www.lrec-conf.org/proceedings/lrec2016/pdf/388_Paper.pdf"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)",
-        "PUB",
-        "http://creativecommons.org/licenses/by-nc/4.0/"
-    ],
-    "author": [
-        "Habernal, Ivan",
-        "Gurevych, Iryna",
-        "Zayed, Omnia"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2204;2019-01-02T14:28:58Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;C4Corpus (CC BY-NC part);Gurevych, Iryna;Habernal, Ivan;Zayed, Omnia;CommonCrawl;Creative Commons;Web corpus;Amazon Web Services;A large web corpus (over 10 billion tokens) licensed under CreativeCommons license family in 50+ languages that has been extracted from CommonCrawl, the largest publicly available general Web crawl to date with about 2 billion crawled URLs.;2016-04-14;corpus;http://hdl.handle.net/11372/LRT-2204;afr;ara;ben;bul;ces;dan;deu;ell;eng;est;fas;fin;fra;heb;hin;hrv;hun;ind;ita;jpn;kan;kor;lav;lit;mal;mkd;nep;nld;nor;pan;pol;por;ron;rus;slk;slv;som;spa;sqi;swa;swe;tam;tel;tgl;tha;tur;ukr;und;vie;zho;http://www.lrec-conf.org/proceedings/lrec2016/pdf/388_Paper.pdf;Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0);PUB;http://creativecommons.org/licenses/by-nc/4.0/;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;text/plain;downloadable_files_count: 52;Technische Universit\u00e4t Darmstadt;https://dkpro.github.io/dkpro-c4corpus/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b7af4cfe-22d1-5405-adb3-ca23bbf4235f",
-    "notes": [
-        "A large web corpus (over 10 billion tokens) licensed under CreativeCommons license family in 50+ languages that has been extracted from CommonCrawl, the largest publicly available general Web crawl to date with about 2 billion crawled URLs."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2204"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "CommonCrawl"
-        },
-        {
-            "name": "Creative Commons"
-        },
-        {
-            "name": "Web corpus"
-        },
-        {
-            "name": "Amazon Web Services"
-        }
-    ],
-    "title": [
-        "C4Corpus (CC BY-NC part)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b7b8b169-40cb-59b9-8ad8-bcf80b927a6b.json b/oaitestdata/clarin-oai_dc/SET_1/json/b7b8b169-40cb-59b9-8ad8-bcf80b927a6b.json
deleted file mode 100644
index 4c63758b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b7b8b169-40cb-59b9-8ad8-bcf80b927a6b.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "OpenTaal, Dutch Language Union (cfr. spelling hallmark)"
-    ],
-    "Contributor": [
-        "Brouwer, Simon"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/plain"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-851",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-851"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-851",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "OpenTaal, Dutch Language Union (cfr. spelling hallmark)"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "BSD or CC-BY-3.0"
-    ],
-    "SpatialCoverage": [
-        "Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-851;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;OpenTaal word list;Brouwer, Simon;Free Dutch word list, suitable for spell checkers etc. - see http://opentaal.org/english.php;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-851;nld;BSD or CC-BY-3.0;text/plain;downloadable_files_count: 0;Netherlands (the);OpenTaal, Dutch Language Union (cfr. spelling hallmark);http://opentaal.org/download.php?file=/bestanden/bronbestanden-100G.zip",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b7b8b169-40cb-59b9-8ad8-bcf80b927a6b",
-    "notes": [
-        "Free Dutch word list, suitable for spell checkers etc. - see http://opentaal.org/english.php"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-851"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "OpenTaal word list"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b7cc7bc7-2669-5eb0-8abb-49b94137c05e.json b/oaitestdata/clarin-oai_dc/SET_1/json/b7cc7bc7-2669-5eb0-8abb-49b94137c05e.json
deleted file mode 100644
index f05f7dc0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b7cc7bc7-2669-5eb0-8abb-49b94137c05e.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Miko\u0142aja Loba"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229178",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229178"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D05-2",
-    "PublicationTimestamp": "1613-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1613"
-    ],
-    "Publisher": [
-        "Drukarnia Miko\u0142aja Loba"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/229178",
-        "oai:jbc.bj.uj.edu.pl:publication:240821"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1601/1700"
-    ],
-    "TempCoverageBegin": 50506804799,
-    "TempCoverageEnd": 50506804799,
-    "TemporalCoverage": " point in time : 1601-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1601-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1601-07-01T11:59:59Z",
-    "author": [
-        "Piotrowski, Wespazjan"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229178;2019-03-01T12:56:34Z;Pociecha na \u017cal serdeczny : (Ktory odnios\u0142a z \u015bmierci, tak wiela osob, w zacnym y wielkim domu swoim), Jasnie [...] P. Annie Z Rvsca, Lvbomirskiey, Kasztelance Woynickiey Sendomirskiey, Spiskiey, Dobczyckiey &c. Staro\u015bciney / [Piotrowski Wespesian];Piotrowski, Wespazjan;starodruki 17\u00a0w.;Drukarnia Miko\u0142aja Loba;1613;starodruk;application/xml;clarind-uds:poldilemma-229178;hdl:11858/00-246C-0000-0023-8D05-2;Biblioteka Jagiello\u0144ska, BJ St. Dr. 311136 I;lat;http://jbc.bj.uj.edu.pl/Content/229178;oai:jbc.bj.uj.edu.pl:publication:240821;1601/1700;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b7cc7bc7-2669-5eb0-8abb-49b94137c05e",
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229178"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Pociecha na \u017cal serdeczny : (Ktory odnios\u0142a z \u015bmierci, tak wiela osob, w zacnym y wielkim domu swoim), Jasnie [...] P. Annie Z Rvsca, Lvbomirskiey, Kasztelance Woynickiey Sendomirskiey, Spiskiey, Dobczyckiey &c. Staro\u015bciney / [Piotrowski Wespesian]"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b8027978-9c46-5b48-953e-3e5d2a5ba2a6.json b/oaitestdata/clarin-oai_dc/SET_1/json/b8027978-9c46-5b48-953e-3e5d2a5ba2a6.json
deleted file mode 100644
index 40529cf0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b8027978-9c46-5b48-953e-3e5d2a5ba2a6.json
+++ /dev/null
@@ -1,89 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia J.K.M. Societatis Jesu"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-553",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-553"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D22-F",
-    "PublicationTimestamp": "1740-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1740"
-    ],
-    "Publisher": [
-        "Drukarnia J.K.M. Societatis Jesu"
-    ],
-    "RelatedIdentifier": [
-        "http://pbc.biaman.pl/Content/553"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "author": [
-        "Pu\u0142aski, Franciszek (-1738)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-553;2019-03-01T15:39:47Z;Kr\u00f3tka Annotacya Seym\u00f3w Warszawskich, Grodzie\u0144skich, takze Elekcyi y Koronacyi Nayiasniejszych Kr\u00f3l\u00f3w Ichmo\u015bci\u00f3w Polskich y Jana Kazimierza, Micha\u0142a, Jana III y Augusta II, tudzie\u017c za Panowania ich Kampaniy corocznie odprawionych, publicznieyszych Dziei\u00f3w y Rewolucyi ab Anno 1648 ad Annum 1733;Pu\u0142aski, Franciszek (-1738);Denhoff Stanis\u0142aw (- 1728);Jan III Sobieski (kr\u00f3l Polski ; 1629-1696);Lubomirski Hieronim (ca 1647 - 1706);Po\u0142tawa;Powstanie Chmielnickiego 1648 r.;Sieniawska Zofia;Sieniawski Adam Miko\u0142aj (1666 - 1726);Sobieski Jakub (1667 - 1737);Zwi\u0105zek Baranowskiego;ilo\u015b\u0107 skan\u00f3w: 86 ; sygn. St- 354;Drukarnia J.K.M. Societatis Jesu;1740;starodruk;application/xml;clarind-uds:poldilemma-553;hdl:11858/00-246C-0000-0023-8D22-F;pol;lat;http://pbc.biaman.pl/Content/553;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b8027978-9c46-5b48-953e-3e5d2a5ba2a6",
-    "notes": [
-        "ilo\u015b\u0107 skan\u00f3w: 86 ; sygn. St- 354"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-553"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Jan III Sobieski kr\u00f3l Polski"
-        },
-        {
-            "name": "Lubomirski Hieronim ca -"
-        },
-        {
-            "name": "Lubomirski Hieronim ca -"
-        },
-        {
-            "name": "Powstanie Chmielnickiego r."
-        },
-        {
-            "name": "Sieniawska Zofia"
-        },
-        {
-            "name": "Sieniawska Zofia"
-        },
-        {
-            "name": "Sobieski Jakub -"
-        },
-        {
-            "name": "Sobieski Jakub -"
-        }
-    ],
-    "title": [
-        "Kr\u00f3tka Annotacya Seym\u00f3w Warszawskich, Grodzie\u0144skich, takze Elekcyi y Koronacyi Nayiasniejszych Kr\u00f3l\u00f3w Ichmo\u015bci\u00f3w Polskich y Jana Kazimierza, Micha\u0142a, Jana III y Augusta II, tudzie\u017c za Panowania ich Kampaniy corocznie odprawionych, publicznieyszych Dziei\u00f3w y Rewolucyi ab Anno 1648 ad Annum 1733"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b80b84c5-e009-5017-9b18-262ca49e4014.json b/oaitestdata/clarin-oai_dc/SET_1/json/b80b84c5-e009-5017-9b18-262ca49e4014.json
deleted file mode 100644
index dbd682f0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b80b84c5-e009-5017-9b18-262ca49e4014.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4437",
-    "MetadataAccess": [
-        "oai:ota:oucs:4437"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Defoe, Daniel, 1661?-1731."
-    ],
-    "fulltext": "oai:ota:oucs:4437;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4437.xml;The double welcome. A poem to the Duke of Marlbro';Defoe, Daniel, 1661?-1731.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b80b84c5-e009-5017-9b18-262ca49e4014",
-    "oai_identifier": [
-        "oai:ota:oucs:4437"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The double welcome. A poem to the Duke of Marlbro'"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4437.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b811af4e-3079-51e5-a4ca-b8c255aae0fd.json b/oaitestdata/clarin-oai_dc/SET_1/json/b811af4e-3079-51e5-a4ca-b8c255aae0fd.json
deleted file mode 100644
index ff9c4acd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b811af4e-3079-51e5-a4ca-b8c255aae0fd.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Matteo Grella"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/x-tar",
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2630",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2630"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2630",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Matteo Grella"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11372/LRT-2476",
-        "http://hdl.handle.net/11372/LRT-2894"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Grella, Matteo"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2630;2018-11-14T15:34:46Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Italian Content Words v2;Grella, Matteo;morphological dictionary;This resource is the second version of an Italian morphological dictionary for content words, encoded in a JSON Lines format text file. It contains correspondences between surface form and lexical forms of words followed by standard grammatical properties. Compared to the first release, this version has a better JSON structure. The surface word forms have been generated algorithmically by using stable phonological and morphological rules of the Italian language. Particular attention has been given to the generation of verbs for which rules have been extracted from A.L e G. Lepschy, La Lingua Italiana. The dictionary with its remarkable coverage is particularly useful used together with the Italian Function Words v2 (http://hdl.handle.net/11372/LRT-2629) for tasks such as pos-tagging or syntactic parsing.;2018;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-2630;ita;http://hdl.handle.net/11372/LRT-2476;http://hdl.handle.net/11372/LRT-2894;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/x-tar;text/plain; charset=utf-8;downloadable_files_count: 1;Matteo Grella",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b811af4e-3079-51e5-a4ca-b8c255aae0fd",
-    "notes": [
-        "This resource is the second version of an Italian morphological dictionary for content words, encoded in a JSON Lines format text file. It contains correspondences between surface form and lexical forms of words followed by standard grammatical properties. Compared to the first release, this version has a better JSON structure. The surface word forms have been generated algorithmically by using stable phonological and morphological rules of the Italian language. Particular attention has been given to the generation of verbs for which rules have been extracted from A.L e G. Lepschy, La Lingua Italiana. The dictionary with its remarkable coverage is particularly useful used together with the Italian Function Words v2 (http://hdl.handle.net/11372/LRT-2629) for tasks such as pos-tagging or syntactic parsing."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2630"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphological dictionary"
-        }
-    ],
-    "title": [
-        "Italian Content Words v2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b81751d2-ed0b-5b2c-91fb-303577d6b53e.json b/oaitestdata/clarin-oai_dc/SET_1/json/b81751d2-ed0b-5b2c-91fb-303577d6b53e.json
deleted file mode 100644
index 57167a4c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b81751d2-ed0b-5b2c-91fb-303577d6b53e.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "The Danish Parliament",
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Danish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repository.clarin.dk:20.500.12115/8",
-    "MetadataAccess": [
-        "oai:repository.clarin.dk:20.500.12115/8"
-    ],
-    "PID": "http://hdl.handle.net/20.500.12115/8",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "The Danish Parliament",
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Hansen, Dorte Haltrup"
-    ],
-    "fulltext": "oai:repository.clarin.dk:20.500.12115/8;2018-06-28T13:21:32Z;hdl_20.500.12115_1;hdl_20.500.12115_3;The Danish Parliament Corpus 2009 - 2017, v1;Hansen, Dorte Haltrup;Parliament records;The Danish Parliament Corpus 2009 \u2013 2017 contains Hansards (transcripts of parliamentary speeches) from the sittings in the Chamber of the Danish Parliament, Folketinget. The corpus consists of xml files, one for each parliamentary year, running from October to the following June. The files are marked for meetings, item title and number, speeches, name and party of speakers, date, time etc.\r\nThe Danish Parliament Corpus 2009-2017 follows the license for Open Data stating the following:\r\n\"The Danish Parliament grants a world-wide, free, non-exclusive and otherwise unrestricted right of use of the data in the Danish Parliament's open data catalogue. The data can be freely: \r\n\uf0a7\tcopied, distributed and published, \r\n\uf0a7\tadapted and combined with other material,\r\n\uf0a7\texploited commercially and non-commercially. \"\r\nFollowing the copyright act, the speeches can be distributed without the consent of the speaker but only in a way where the author/speaker of each text/speech is clearly stated. Furthermore, the Danish Parliament must be acknowledged as the source.\r\nVersion 1 of the corpus includes meetings until May 4th, 2017, and the reports for the latest parliamentary year have not been published as the final edition. The reports of all other meetings are the final editions.;2018;corpus;http://hdl.handle.net/20.500.12115/8;dan;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;The Danish Parliament;Centre for Language Technology, NorS, University of Copenhagen",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b81751d2-ed0b-5b2c-91fb-303577d6b53e",
-    "notes": [
-        "The Danish Parliament Corpus 2009 \u2013 2017 contains Hansards (transcripts of parliamentary speeches) from the sittings in the Chamber of the Danish Parliament, Folketinget. The corpus consists of xml files, one for each parliamentary year, running from October to the following June. The files are marked for meetings, item title and number, speeches, name and party of speakers, date, time etc.\r\nThe Danish Parliament Corpus 2009-2017 follows the license for Open Data stating the following:\r\n\"The Danish Parliament grants a world-wide, free, non-exclusive and otherwise unrestricted right of use of the data in the Danish Parliament's open data catalogue. The data can be freely: \r\n\uf0a7\tcopied, distributed and published, \r\n\uf0a7\tadapted and combined with other material,\r\n\uf0a7\texploited commercially and non-commercially. \"\r\nFollowing the copyright act, the speeches can be distributed without the consent of the speaker but only in a way where the author/speaker of each text/speech is clearly stated. Furthermore, the Danish Parliament must be acknowledged as the source.\r\nVersion 1 of the corpus includes meetings until May 4th, 2017, and the reports for the latest parliamentary year have not been published as the final edition. The reports of all other meetings are the final editions."
-    ],
-    "oai_identifier": [
-        "oai:repository.clarin.dk:20.500.12115/8"
-    ],
-    "oai_set": [
-        "hdl_20.500.12115_1",
-        "hdl_20.500.12115_3"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Parliament records"
-        }
-    ],
-    "title": [
-        "The Danish Parliament Corpus 2009 - 2017, v1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b81c8b7a-1a93-5b97-b32b-e686517654ce.json b/oaitestdata/clarin-oai_dc/SET_1/json/b81c8b7a-1a93-5b97-b32b-e686517654ce.json
deleted file mode 100644
index 4a9d727d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b81c8b7a-1a93-5b97-b32b-e686517654ce.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Makuszy\u0144ski"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 10",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/83",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/83"
-    ],
-    "PID": "http://hdl.handle.net/11321/83",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Makuszy\u0144ski"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Makuszy\u0144ski, Makuszy\u0144ski"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/83;2015-05-19T13:39:35Z;hdl_11321_3;hdl_11321_4;MWE Makuszy\u0144ski;Makuszy\u0144ski, Makuszy\u0144ski;Makuszy\u0144ski;2015-04-08;corpus;http://hdl.handle.net/11321/83;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 10;Makuszy\u0144ski",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b81c8b7a-1a93-5b97-b32b-e686517654ce",
-    "notes": [
-        "Makuszy\u0144ski"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/83"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Makuszy\u0144ski"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b82b08f3-ad90-55e4-809b-f7acd4e17eb0.json b/oaitestdata/clarin-oai_dc/SET_1/json/b82b08f3-ad90-55e4-809b-f7acd4e17eb0.json
deleted file mode 100644
index 6441ffbe..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b82b08f3-ad90-55e4-809b-f7acd4e17eb0.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5381",
-    "MetadataAccess": [
-        "oai:ota:oucs:5381"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pratt, Mr. (Samuel Jackson), 1749-1814."
-    ],
-    "fulltext": "oai:ota:oucs:5381;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5381.xml;Liberal opinions, upon animals, man, and providence: In which are introduced, Anecdotes of a gentleman. ... By Courtney Melmoth. ... [pt.5];Pratt, Mr. (Samuel Jackson), 1749-1814.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b82b08f3-ad90-55e4-809b-f7acd4e17eb0",
-    "oai_identifier": [
-        "oai:ota:oucs:5381"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Liberal opinions, upon animals, man, and providence: In which are introduced, Anecdotes of a gentleman. ... By Courtney Melmoth. ... [pt.5]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5381.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b89aa0f2-7627-5d0d-8b95-f28715a47452.json b/oaitestdata/clarin-oai_dc/SET_1/json/b89aa0f2-7627-5d0d-8b95-f28715a47452.json
deleted file mode 100644
index 5ef98e3a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b89aa0f2-7627-5d0d-8b95-f28715a47452.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "HCRC"
-    ],
-    "Contributor": [
-        "Thompson, Henry S."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Portuguese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-397",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-397"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-397",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "HCRC"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-397;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;ECI Multilingual Text;Thompson, Henry S.;Parallel corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-397;por;downloadable_files_count: 0;United Kingdom;HCRC;http://xml.coverpages.org/eciHome.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b89aa0f2-7627-5d0d-8b95-f28715a47452",
-    "notes": [
-        "Parallel corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-397"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "ECI Multilingual Text"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b8d40c3f-5b70-5ff3-8268-89ee65d8ed6a.json b/oaitestdata/clarin-oai_dc/SET_1/json/b8d40c3f-5b70-5ff3-8268-89ee65d8ed6a.json
deleted file mode 100644
index 7379a94e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b8d40c3f-5b70-5ff3-8268-89ee65d8ed6a.json
+++ /dev/null
@@ -1,99 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/xml",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2307",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2307"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2307",
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "https://www.cupress.cuni.cz/ink2_stat/index.jsp?include=podrobnosti&id=17418",
-        "http://hdl.handle.net/11858/00-097C-0000-0001-4908-9"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "Bej\u010dek, Eduard",
-        "Kettnerov\u00e1, V\u00e1clava",
-        "Lopatkov\u00e1, Mark\u00e9ta",
-        "Vernerov\u00e1, Anna"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2307;2018-07-02T22:05:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;VALLEX 3.0;Lopatkov\u00e1, Mark\u00e9ta;Kettnerov\u00e1, V\u00e1clava;Bej\u010dek, Eduard;Vernerov\u00e1, Anna;\u017dabokrtsk\u00fd, Zden\u011bk;valency;diatheses;alternations;grammar rules;Czech;lexicon;semantics;syntax;VALLEX 3.0 provides information on the valency structure (combinatorial potential) of verbs in their particular senses, which are characterized by glosses and examples. VALLEX 3.0 describes almost 4 600 Czech verbs in more than 10 800 lexical units, i.e., given verbs in the given senses. \r\nVALLEX 3.0 is a is a collection of linguistically annotated data and documentation, resulting from an attempt at formal description of valency frames of Czech verbs. In order to satisfy different needs of different potential users, the lexicon is distributed (i) in a HTML version (the data allows for an easy and fast navigation through the lexicon) and (ii) in a machine-tractable form as a single XML file, so that the VALLEX data can be used in NLP applications.;2016-12;lexicalConceptualResource;http://hdl.handle.net/11234/1-2307;ces;https://www.cupress.cuni.cz/ink2_stat/index.jsp?include=podrobnosti&id=17418;http://hdl.handle.net/11858/00-097C-0000-0001-4908-9;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;text/plain; charset=utf-8;text/xml;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/vallex",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b8d40c3f-5b70-5ff3-8268-89ee65d8ed6a",
-    "notes": [
-        "VALLEX 3.0 provides information on the valency structure (combinatorial potential) of verbs in their particular senses, which are characterized by glosses and examples. VALLEX 3.0 describes almost 4 600 Czech verbs in more than 10 800 lexical units, i.e., given verbs in the given senses. \r\nVALLEX 3.0 is a is a collection of linguistically annotated data and documentation, resulting from an attempt at formal description of valency frames of Czech verbs. In order to satisfy different needs of different potential users, the lexicon is distributed (i) in a HTML version (the data allows for an easy and fast navigation through the lexicon) and (ii) in a machine-tractable form as a single XML file, so that the VALLEX data can be used in NLP applications."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2307"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "valency"
-        },
-        {
-            "name": "diatheses"
-        },
-        {
-            "name": "alternations"
-        },
-        {
-            "name": "grammar rules"
-        },
-        {
-            "name": "Czech"
-        },
-        {
-            "name": "lexicon"
-        },
-        {
-            "name": "semantics"
-        },
-        {
-            "name": "syntax"
-        }
-    ],
-    "title": [
-        "VALLEX 3.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b8f0b36e-c559-5aee-a4e6-12f136cf2b3d.json b/oaitestdata/clarin-oai_dc/SET_1/json/b8f0b36e-c559-5aee-a4e6-12f136cf2b3d.json
deleted file mode 100644
index f2d1a4aa..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b8f0b36e-c559-5aee-a4e6-12f136cf2b3d.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "application/pdf",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1507",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1507"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1507",
-    "PublicationTimestamp": "2015-07-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Fiala, Ond\u0159ej"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1507;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Aspect-Term Annotated Customer Reviews in Czech;Fiala, Ond\u0159ej;sentiment analysis;opinion target;customer review;This dataset contains a number of user product reviews which are publicly available on the website of an established Czech online shop with electronic devices. Each review consists of negative and positive aspects of the product. This setting pushes the customer to rate important characteristics.\r\n\r\nWe have selected 2000 positive and negative segments from these reviews and manually tagged their targets. Additionally, we selected 200 of the longest reviews and annotated them in the same way. The targets were either aspects of the evaluated product or some general attributes (e.g. price, ease of use).;2015-07-16;corpus;http://hdl.handle.net/11234/1-1507;ces;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/pdf;application/zip;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b8f0b36e-c559-5aee-a4e6-12f136cf2b3d",
-    "notes": [
-        "This dataset contains a number of user product reviews which are publicly available on the website of an established Czech online shop with electronic devices. Each review consists of negative and positive aspects of the product. This setting pushes the customer to rate important characteristics.\r\n\r\nWe have selected 2000 positive and negative segments from these reviews and manually tagged their targets. Additionally, we selected 200 of the longest reviews and annotated them in the same way. The targets were either aspects of the evaluated product or some general attributes (e.g. price, ease of use)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1507"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "sentiment analysis"
-        },
-        {
-            "name": "opinion target"
-        },
-        {
-            "name": "customer review"
-        }
-    ],
-    "title": [
-        "Aspect-Term Annotated Customer Reviews in Czech"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b8f134b9-4ee6-58c3-9f6d-50aa06b0e51d.json b/oaitestdata/clarin-oai_dc/SET_1/json/b8f134b9-4ee6-58c3-9f6d-50aa06b0e51d.json
deleted file mode 100644
index 5ef50c9d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b8f134b9-4ee6-58c3-9f6d-50aa06b0e51d.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4905-F",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4905-F"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-4905-F",
-    "PublicationTimestamp": "2009-11-02T09:41:19Z",
-    "PublicationYear": [
-        "2009"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU General Public Licence, version 3",
-        "http://opensource.org/licenses/GPL-3.0",
-        "PUB"
-    ],
-    "author": [
-        "M\u00edrovsk\u00fd, Ji\u0159\u00ed",
-        "Ondru\u0161ka, Roman"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4905-F;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Netgraph;M\u00edrovsk\u00fd, Ji\u0159\u00ed;Ondru\u0161ka, Roman;search;treebank;Netgraph is a graphically oriented client-server application for searching in linguistically annotated treebanks. The query language of Netgraph is simple and intuitive, yet powerful enough for treebanks with complex annotations schemes. The primary purpose of Netgraph is searching in the Prague Dependency Treebank 2.0, nevertheless it can be used for other treebanks as well.;2009-11-02T09:41:19Z;toolService;http://hdl.handle.net/11858/00-097C-0000-0001-4905-F;GNU General Public Licence, version 3;http://opensource.org/licenses/GPL-3.0;PUB;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://quest.ms.mff.cuni.cz/netgraph/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b8f134b9-4ee6-58c3-9f6d-50aa06b0e51d",
-    "notes": [
-        "Netgraph is a graphically oriented client-server application for searching in linguistically annotated treebanks. The query language of Netgraph is simple and intuitive, yet powerful enough for treebanks with complex annotations schemes. The primary purpose of Netgraph is searching in the Prague Dependency Treebank 2.0, nevertheless it can be used for other treebanks as well."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4905-F"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "search"
-        },
-        {
-            "name": "treebank"
-        }
-    ],
-    "title": [
-        "Netgraph"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b909ef6a-098f-5985-a842-d469ccc9b2d2.json b/oaitestdata/clarin-oai_dc/SET_1/json/b909ef6a-098f-5985-a842-d469ccc9b2d2.json
deleted file mode 100644
index be3d0198..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b909ef6a-098f-5985-a842-d469ccc9b2d2.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 3",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/38",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/38"
-    ],
-    "PID": "http://hdl.handle.net/10794/38",
-    "PublicationTimestamp": "2012-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/38;2017-10-27T14:02:13Z;hdl_10794_1;hdl_10794_2;Simple lexicon;Simple lexikon;n/a, n/a;Swedish;SIMPLE;The Swedish SIMPLE Lexicon - A language technology resource with access to semantic information in Swedish.;Svenskt SIMPLE-lexikon - En spr\u00e5kteknologisk resurs med semantisk information.;2012-05-30;lexicalConceptualResource;http://hdl.handle.net/10794/38;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;http://creativecommons.org/licenses/by/4.0/;application/gzip;application/gzip;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 3;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/simple",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b909ef6a-098f-5985-a842-d469ccc9b2d2",
-    "notes": [
-        "The Swedish SIMPLE Lexicon - A language technology resource with access to semantic information in Swedish.",
-        "Svenskt SIMPLE-lexikon - En spr\u00e5kteknologisk resurs med semantisk information."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/38"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "SIMPLE"
-        }
-    ],
-    "title": [
-        "Simple lexicon",
-        "Simple lexikon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b91cd1bc-20b5-5bb9-b29a-bb8fa1dbcb9d.json b/oaitestdata/clarin-oai_dc/SET_1/json/b91cd1bc-20b5-5bb9-b29a-bb8fa1dbcb9d.json
deleted file mode 100644
index 13017c31..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b91cd1bc-20b5-5bb9-b29a-bb8fa1dbcb9d.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4711",
-    "MetadataAccess": [
-        "oai:ota:oucs:4711"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "MacNally, Leonard, 1752-1820."
-    ],
-    "fulltext": "oai:ota:oucs:4711;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4711.xml;An address to the Whig Club: with an essay on the judicial discretion of judges, on fiats and on bail;MacNally, Leonard, 1752-1820.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b91cd1bc-20b5-5bb9-b29a-bb8fa1dbcb9d",
-    "oai_identifier": [
-        "oai:ota:oucs:4711"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An address to the Whig Club: with an essay on the judicial discretion of judges, on fiats and on bail"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4711.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b92597f0-26ec-502d-95bb-c06f68169a8e.json b/oaitestdata/clarin-oai_dc/SET_1/json/b92597f0-26ec-502d-95bb-c06f68169a8e.json
deleted file mode 100644
index e6d9d050..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b92597f0-26ec-502d-95bb-c06f68169a8e.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Pistol, Ionut"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Romanian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-497",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-497"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-497",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Romania"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-497;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Romanian word frequency list;Pistol, Ionut;Aprox. 2 mil words, txt;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-497;ron;downloadable_files_count: 0;Romania;http://consilr.info.uaic.ro/2014/index.php",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b92597f0-26ec-502d-95bb-c06f68169a8e",
-    "notes": [
-        "Aprox. 2 mil words, txt"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-497"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Romanian word frequency list"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b938a2f7-f650-5110-af3b-926f85bc4213.json b/oaitestdata/clarin-oai_dc/SET_1/json/b938a2f7-f650-5110-af3b-926f85bc4213.json
deleted file mode 100644
index 29b78302..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b938a2f7-f650-5110-af3b-926f85bc4213.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Masaryk University, NLP Centre"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/x-rar-compressed"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1463",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1463"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1463",
-    "PublicationTimestamp": "2014-12-06T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Masaryk University, NLP Centre"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU General Public Licence, version 3",
-        "http://opensource.org/licenses/GPL-3.0",
-        "PUB"
-    ],
-    "author": [
-        "Hor\u00e1k, Ale\u0161",
-        "Medve\u010f, Marek"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1463;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;SQAD;Medve\u010f, Marek;Hor\u00e1k, Ale\u0161;question answering;Simple Question Answering Database;SQAD;The SQAD database consists of 3301 records obtained from Czech Wikipedia articles. The record structure is following:\r\n- the original sentence(s) from Wikipedia\r\n-  a question that is directly answered in the text\r\n- the expected answer to the question as it appears in the original text\r\n- the URL of the Wikipedia web page from which the original text was extracted\r\n- name of the author of this SQAD record;2014-12-06;corpus;http://hdl.handle.net/11234/1-1463;ces;GNU General Public Licence, version 3;http://opensource.org/licenses/GPL-3.0;PUB;application/x-rar-compressed;text/plain; charset=utf-8;downloadable_files_count: 1;Masaryk University, NLP Centre;http://nlp.fi.muni.cz/projects/sqad/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b938a2f7-f650-5110-af3b-926f85bc4213",
-    "notes": [
-        "The SQAD database consists of 3301 records obtained from Czech Wikipedia articles. The record structure is following:\r\n- the original sentence(s) from Wikipedia\r\n-  a question that is directly answered in the text\r\n- the expected answer to the question as it appears in the original text\r\n- the URL of the Wikipedia web page from which the original text was extracted\r\n- name of the author of this SQAD record"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1463"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "question answering"
-        },
-        {
-            "name": "Simple Question Answering Database"
-        },
-        {
-            "name": "SQAD"
-        }
-    ],
-    "title": [
-        "SQAD"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b9570882-27c6-5ea3-b0cf-dd79e02f5c4d.json b/oaitestdata/clarin-oai_dc/SET_1/json/b9570882-27c6-5ea3-b0cf-dd79e02f5c4d.json
deleted file mode 100644
index 992291e2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b9570882-27c6-5ea3-b0cf-dd79e02f5c4d.json
+++ /dev/null
@@ -1,40 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=168f79aaa35a11e1a404080027e73ea2b09be1971aff49cbaeabfec8cc3cab7e",
-    "MetadataAccess": [
-        "168f79aaa35a11e1a404080027e73ea2b09be1971aff49cbaeabfec8cc3cab7e"
-    ],
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "168f79aaa35a11e1a404080027e73ea2b09be1971aff49cbaeabfec8cc3cab7e;2019-02-27T12:09:03Z;corpus;corpus:text;corpus:audio;corpus:text:audio;Fundamental Portuguese;This resource includes a spoken Portuguese corpus - with aligned sound and orthographic transcription -, collected among sociolinguistically diverse speakers. It consists of recordings from informal conversations.;2015-12-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b9570882-27c6-5ea3-b0cf-dd79e02f5c4d",
-    "notes": [
-        "This resource includes a spoken Portuguese corpus - with aligned sound and orthographic transcription -, collected among sociolinguistically diverse speakers. It consists of recordings from informal conversations."
-    ],
-    "oai_identifier": [
-        "168f79aaa35a11e1a404080027e73ea2b09be1971aff49cbaeabfec8cc3cab7e"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text",
-        "corpus:audio",
-        "corpus:text:audio"
-    ],
-    "state": "active",
-    "title": [
-        "Fundamental Portuguese"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b9698f5b-f3e4-5b0b-be51-e929d7205dab.json b/oaitestdata/clarin-oai_dc/SET_1/json/b9698f5b-f3e4-5b0b-be51-e929d7205dab.json
deleted file mode 100644
index dbf8a98b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b9698f5b-f3e4-5b0b-be51-e929d7205dab.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3266",
-    "MetadataAccess": [
-        "oai:ota:oucs:3266"
-    ],
-    "PublicationTimestamp": "1900-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1900"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Kipling, Rudyard, 1865-1936"
-    ],
-    "fulltext": "oai:ota:oucs:3266;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3266.xml;City of Dreadful Night;Kipling, Rudyard, 1865-1936;not after: 1900;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b9698f5b-f3e4-5b0b-be51-e929d7205dab",
-    "oai_identifier": [
-        "oai:ota:oucs:3266"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "City of Dreadful Night"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3266.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b9790be7-608d-5065-b6b5-548654e09e93.json b/oaitestdata/clarin-oai_dc/SET_1/json/b9790be7-608d-5065-b6b5-548654e09e93.json
deleted file mode 100644
index 5055a69f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b9790be7-608d-5065-b6b5-548654e09e93.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2620",
-    "MetadataAccess": [
-        "oai:ota:oucs:2620"
-    ],
-    "PublicationTimestamp": "1710-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1710"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2620;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2620.xml;Curll's Complete key to The tale of a tub;Swift, Jonathan, 1667-1745;1710;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b9790be7-608d-5065-b6b5-548654e09e93",
-    "oai_identifier": [
-        "oai:ota:oucs:2620"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Curll's Complete key to The tale of a tub"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2620.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b9843f40-ff3f-5e2e-a2dc-cbb9c9e92e6f.json b/oaitestdata/clarin-oai_dc/SET_1/json/b9843f40-ff3f-5e2e-a2dc-cbb9c9e92e6f.json
deleted file mode 100644
index 43ac8f89..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b9843f40-ff3f-5e2e-a2dc-cbb9c9e92e6f.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "FBC"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "text/plain",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/224",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/224"
-    ],
-    "PID": "http://hdl.handle.net/11321/224",
-    "PublicationTimestamp": "2015-08-10T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "FBC"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Osinska, Veslava"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/224;2015-08-10T14:37:02Z;hdl_11321_3;hdl_11321_4;Klasyfikacje reczne artyku\u0142\u00f3w;Osinska, Veslava;humanity categories;HS1 _ teo|rel 373\r\nHS1_fil|et 238\r\nHS2 _ jez 1812\r\nHS2_ art|arc 32\r\nHS2_bib_inf 1773\r\nHS2_kul 449\r\nHS2_lit 264\r\nHS3 _etn|antro 18\r\nHS3_ arche 284\r\nHS3_ his 211\r\nHS3_archi|dok 68\r\nHS6_ped 466\r\nHS6_psy 362\r\nHS6_soc 433\r\nLicznik ca\u0142kowity\t6783;2015-08-10;corpus;http://hdl.handle.net/11321/224;Polish;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;application/octet-stream;text/plain;text/plain; charset=utf-8;downloadable_files_count: 2;FBC;wizualizacjainformacji.pl/projekt",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b9843f40-ff3f-5e2e-a2dc-cbb9c9e92e6f",
-    "notes": [
-        "HS1 _ teo|rel 373\r\nHS1_fil|et 238\r\nHS2 _ jez 1812\r\nHS2_ art|arc 32\r\nHS2_bib_inf 1773\r\nHS2_kul 449\r\nHS2_lit 264\r\nHS3 _etn|antro 18\r\nHS3_ arche 284\r\nHS3_ his 211\r\nHS3_archi|dok 68\r\nHS6_ped 466\r\nHS6_psy 362\r\nHS6_soc 433\r\nLicznik ca\u0142kowity\t6783"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/224"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "humanity categories"
-        }
-    ],
-    "title": [
-        "Klasyfikacje reczne artyku\u0142\u00f3w"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b9853518-1f64-5678-8121-054b35db6a56.json b/oaitestdata/clarin-oai_dc/SET_1/json/b9853518-1f64-5678-8121-054b35db6a56.json
deleted file mode 100644
index 1976b8f2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b9853518-1f64-5678-8121-054b35db6a56.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Stanis\u0142aw Piotrkowczyk"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-5699",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-5699"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D25-9",
-    "PublicationTimestamp": "1667-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1667"
-    ],
-    "Publisher": [
-        "Stanis\u0142aw Piotrkowczyk"
-    ],
-    "RelatedIdentifier": [
-        "http://pbc.biaman.pl/Content/5699"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "author": [
-        "Rych\u0142owski, Franciszek"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-5699;2019-03-01T15:45:53Z;Kazania na swi\u0119ta ca\u0142ego roku. Z ro\u017cnych doktorow [...] zebrane y napisane przez [...];Rych\u0142owski, Franciszek;Kazania polskie 17 w.;ilo\u015b\u0107 skan\u00f3w: 725 ; sygn. St-11;Stanis\u0142aw Piotrkowczyk;1667;starodruk;application/xml;clarind-uds:poldilemma-5699;hdl:11858/00-246C-0000-0023-8D25-9;pol;lat;http://pbc.biaman.pl/Content/5699;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b9853518-1f64-5678-8121-054b35db6a56",
-    "notes": [
-        "ilo\u015b\u0107 skan\u00f3w: 725 ; sygn. St-11"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-5699"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Kazania polskie w."
-        }
-    ],
-    "title": [
-        "Kazania na swi\u0119ta ca\u0142ego roku. Z ro\u017cnych doktorow [...] zebrane y napisane przez [...]"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b991d0e7-8c73-5f18-8156-858c3a712207.json b/oaitestdata/clarin-oai_dc/SET_1/json/b991d0e7-8c73-5f18-8156-858c3a712207.json
deleted file mode 100644
index a401f447..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b991d0e7-8c73-5f18-8156-858c3a712207.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Institute of Phonetics and Speech Processing, LMU Munich"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1191",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1191"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1191",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institute of Phonetics and Speech Processing, LMU Munich"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1191;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;EMU Speech Database System;EMU is a collection of software tools for the creation, manipulation and analysis of speech databases. At the core of EMU is a database search engine which allows the researcher to find various speech segments based on the sequential and hierarchical structure of the utterances in which they occur. EMU includes an interactive labeller which can display spectrograms and other speech waveforms, and which allows the creation of hierarchical, as well as sequential, labels for a speech utterance.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1191;downloadable_files_count: 0;Germany;Institute of Phonetics and Speech Processing, LMU Munich;http://emu.sourceforge.net/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b991d0e7-8c73-5f18-8156-858c3a712207",
-    "notes": [
-        "EMU is a collection of software tools for the creation, manipulation and analysis of speech databases. At the core of EMU is a database search engine which allows the researcher to find various speech segments based on the sequential and hierarchical structure of the utterances in which they occur. EMU includes an interactive labeller which can display spectrograms and other speech waveforms, and which allows the creation of hierarchical, as well as sequential, labels for a speech utterance."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1191"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "EMU Speech Database System"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b9e9676b-1a0a-5d04-ae07-12aa094e1b1b.json b/oaitestdata/clarin-oai_dc/SET_1/json/b9e9676b-1a0a-5d04-ae07-12aa094e1b1b.json
deleted file mode 100644
index a70db009..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b9e9676b-1a0a-5d04-ae07-12aa094e1b1b.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "1393",
-        "Gross, Maurice, 1934-"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(33 files : total of ca. 296 KB)"
-    ],
-    "Language": [
-        "French"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1393",
-    "MetadataAccess": [
-        "oai:ota:oucs:1393"
-    ],
-    "PublicationTimestamp": "1990-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1990"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Academic dissertations"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gross, Maurice, 1934-"
-    ],
-    "fulltext": "oai:ota:oucs:1393;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1393.xml;Materials for construction of lexicon grammar / compiled by Maurice Gross;Gross, Maurice, 1934-;[1990];text_and_corpus_linguistics;French language -- Lexicology -- Data;fra;Oxford Text Archive, University of Oxford;1393;Gross, Maurice, 1934-;(33 files : total of ca. 296 KB);Text;Academic dissertations;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b9e9676b-1a0a-5d04-ae07-12aa094e1b1b",
-    "oai_identifier": [
-        "oai:ota:oucs:1393"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "French language -- Lexicology -- Data"
-        }
-    ],
-    "title": [
-        "Materials for construction of lexicon grammar / compiled by Maurice Gross"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1393.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/b9ed4b0a-b746-5b1b-89c2-bed01454263c.json b/oaitestdata/clarin-oai_dc/SET_1/json/b9ed4b0a-b746-5b1b-89c2-bed01454263c.json
deleted file mode 100644
index 0877d74a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/b9ed4b0a-b746-5b1b-89c2-bed01454263c.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Frisian Academy"
-    ],
-    "Contributor": [
-        "Hoekstra, Eric"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-878",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-878"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-878",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Frisian Academy"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-878;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;New Frisian language corpus;Hoekstra, Eric;A digital collection of Frisian books, scientific magazines and newspaper articles, which can be used to investigate various aspects of Frisian culture including language and literature. The corpus contains more than 25 million words;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-878;downloadable_files_count: 0;Netherlands (the);Frisian Academy;http://www.fa.knaw.nl/fa/3departments-and-disciplines/department-of-linguistics/taalkorpora_en_/frisian-language-corpus",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b9ed4b0a-b746-5b1b-89c2-bed01454263c",
-    "notes": [
-        "A digital collection of Frisian books, scientific magazines and newspaper articles, which can be used to investigate various aspects of Frisian culture including language and literature. The corpus contains more than 25 million words"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-878"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "New Frisian language corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ba04fbbb-5cfe-5797-93a0-76ca5299e2fb.json b/oaitestdata/clarin-oai_dc/SET_1/json/ba04fbbb-5cfe-5797-93a0-76ca5299e2fb.json
deleted file mode 100644
index 53726e3e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ba04fbbb-5cfe-5797-93a0-76ca5299e2fb.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=1c665572104111e5a2aa782bcb074135247c22693c2e4320891b8feca50751e7",
-    "MetadataAccess": [
-        "1c665572104111e5a2aa782bcb074135247c22693c2e4320891b8feca50751e7"
-    ],
-    "PublicationTimestamp": "2015-06-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "1c665572104111e5a2aa782bcb074135247c22693c2e4320891b8feca50751e7;2018-11-15T16:40:17Z;corpus;corpus:text;Basque-English ParDeepBank;This resource is part of Deliverable 4.6 of the QTLeap FP7 project (Contract number 610516). In its current development (15% of the intended goal of the project), it is composed of 150 sentences (1,416 English tokens and 1,275 Basque tokens). The sentences are excerpts from journalistic text from the Wall Street Journal that have been manually translated into Basque to generate a parallel corpus.\n\nIt includes several levels of linguisic information for each sentence, including lemmatization and mophological analysis as well as dependency parsing trees. This is the result of a semi-automatic annotation process by means of automatic analysis followed by a human correction phase.\n\nThe main motivation behind the creation of this resource was to build a high quality data set with rich grammatical information that could support the development of linguistically-informed translation tools.;2015-06-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ba04fbbb-5cfe-5797-93a0-76ca5299e2fb",
-    "notes": [
-        "This resource is part of Deliverable 4.6 of the QTLeap FP7 project (Contract number 610516). In its current development (15% of the intended goal of the project), it is composed of 150 sentences (1,416 English tokens and 1,275 Basque tokens). The sentences are excerpts from journalistic text from the Wall Street Journal that have been manually translated into Basque to generate a parallel corpus.\n\nIt includes several levels of linguisic information for each sentence, including lemmatization and mophological analysis as well as dependency parsing trees. This is the result of a semi-automatic annotation process by means of automatic analysis followed by a human correction phase.\n\nThe main motivation behind the creation of this resource was to build a high quality data set with rich grammatical information that could support the development of linguistically-informed translation tools."
-    ],
-    "oai_identifier": [
-        "1c665572104111e5a2aa782bcb074135247c22693c2e4320891b8feca50751e7"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "Basque-English ParDeepBank"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ba1404c8-47ed-5938-8199-09cf1f1f8224.json b/oaitestdata/clarin-oai_dc/SET_1/json/ba1404c8-47ed-5938-8199-09cf1f1f8224.json
deleted file mode 100644
index 6f567ef9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ba1404c8-47ed-5938-8199-09cf1f1f8224.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Micha\u0142 Marci\u0144czuk"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/6",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/6"
-    ],
-    "PID": "http://hdl.handle.net/11321/6",
-    "PublicationTimestamp": "2007-09-17T11:59:59Z",
-    "PublicationYear": [
-        "2007"
-    ],
-    "Publisher": [
-        "Micha\u0142 Marci\u0144czuk"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Marci\u0144czuk, Micha\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/6;2014-09-25T10:33:59Z;hdl_11321_3;hdl_11321_4;CEN;Marci\u0144czuk, Micha\u0142;Corpus of Economic News (CEN) contains 797 documents from Polish Wikipedia annotated with 65 categories of proper names in ccl format.\r\nhttp://nlp.pwr.edu.pl/inforex/?corpus=5&page=browse;2007-09-17;corpus;http://hdl.handle.net/11321/6;pol;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 1;Micha\u0142 Marci\u0144czuk;http://nlp.pwr.wroc.pl/cen",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ba1404c8-47ed-5938-8199-09cf1f1f8224",
-    "notes": [
-        "Corpus of Economic News (CEN) contains 797 documents from Polish Wikipedia annotated with 65 categories of proper names in ccl format.\r\nhttp://nlp.pwr.edu.pl/inforex/?corpus=5&page=browse"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/6"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "CEN"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ba6d591e-8448-5df9-98d6-9a673304298f.json b/oaitestdata/clarin-oai_dc/SET_1/json/ba6d591e-8448-5df9-98d6-9a673304298f.json
deleted file mode 100644
index 71f2fcd6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ba6d591e-8448-5df9-98d6-9a673304298f.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "NLX-Natural Language and Speech Group, University of Lisbon"
-    ],
-    "Contributor": [
-        "Branco, Ant\u00f3nio",
-        "Costa, Francisco"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Portuguese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1223",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1223"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1223",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "NLX-Natural Language and Speech Group, University of Lisbon"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Portugal"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1223;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LX-Conjugator;Branco, Ant\u00f3nio;Costa, Francisco;Fully fledged automatic verbal conjugator for Portuguese, including all forms of clitic conjugation.It thus handles: * Pronominal conjugation The Portuguese verbal inflection system is a most complex part of the Portuguese morphology, and of the Portuguese language, given the high number of conjugated forms for each verb (ca. 70 forms in non pronominal conjugation), the number of productive inflection rules involved and the number of non regular forms and exceptions to such rules. This complexity is further increased when the so-called pronominal conjugation is taken into account. The Portuguese language has verbal clitics, which according to some authors are to be analyzed as integrating the inflectional suffix system: o the forms of the clitics may depend on the Number (Singular vs. Plural), the Person (First, Second, Third or Second courtesy), the Gender (Masculine vs. Feminine), the grammatical function which they are in correspondence with (Subject, Direct object or Indirect object), and the anaphoric properties (Pronominal vs. Reflexive); o up to three clitics (e.g. deu-se-lho / gave-One-ToHim_It) may be associated with a verb form; o clitics may occur in so called enclisis, i.e. as a final part of the verb form (e.g. deu-o / gave-It), or in mesoclisis, i.e. as a medial part of the verb form (e.g. d\u00e1-lo-ia / give-it-CONDITIONAL). When the verb form occurs in certain syntactic or semantic contexts (e.g in the scope of negation), the clitics appear in proclisis, i.e. before the verb form (ex.: n\u00e3o o deu / NOT it gave); o clitics follow specific rules for their concatenation. With LX-Conjugator, pronominal conjugation is exhaustively handled. It is however optional, and verbs can be conjugated also in non pronominal conjugation mode only. Additionally, LX-Conjugator exhaustively handles a set of inflection cases which tend not to be supported together in verbal conjugators: * Compound tenses * Double forms for past participles (regular and irregular) * Past participle forms inflected for number and gender (with transitive and unaccusative verbs) * Negative imperative forms * Courtesy forms for second person LX-Conjugator handles both known verbs and unknown verbs. It thus conjugates: * Neologisms (with orthographic infinitival suffix) It is also worth noting the following design principles, that LX-Conjugator adopts with respect to the so called defective verbs: * Defectives Some unsubstantiated assumptions from traditional grammar were not followed, according to which many verb forms do not exist and/or should not be used because they sound awkward or because their use is semantically very restricted. Accordingly, to give an example, all conjugated forms of weather verbs are delivered, as they can be used at least non literally (with forms other than third person singular ones being presented in a distinguished font to indicate that they have generally been considered non-existent). To give another example, verbs like falir are also fully conjugated (again with some of its forms marked in a disitinguished font in order to signal that some speakers may find them phonetically awkward). * Special cases LX-Conjugator does assume that some forms are impossible though (e.g. the imperative forms of verbs such as querer / to want: *quer tu) and that some clitics do not combine with certain verb forms (e.g. second person non-courtesy clitics and second person courtesy verb forms with the same number: *voc\u00ea ama-te/you_COURTESY love-yourself_NONCOURTESY). In these cases such forms will not be produced. Other special cases, also not generated, include impersonal se and passive se, which do not occur with first or second person verb forms. LX-Conjugator handles the very few cases where there may be different forms in different variants: * Orthographic and paradigmatic differences When the same form has different orthographic representations, all such representations are presented. To give a couple of examples, both representations of '(he) dicharges', desagua (European) and des\u00e1gua (Brazilian), and both representations for '(I) argued', argui (European) and arg\u00fci (Brazilian), are delivered. * Other cases Differences in irregular forms are also handled under the same approach. One such example is the past participle of 'to accept', with aceite (European) and aceito (Brazilian), which will be both displayed. Note that in general LX-Conjugator acknowledges differences in representations of the same verb form when such representations can be predicted from the representation of the infinitive form (to be entered by the user). Accordingly, representations of the same verb differing in (the non-final part of) their roots are not automatically acknowledged by the conjugator. For instance, all conjugated forms of 'to act' will start either with act- or with at-, depending on whether the user enters actuar (European) or atuar (Brazilian) as the representation of the infinitive.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1223;por;downloadable_files_count: 0;Portugal;NLX-Natural Language and Speech Group, University of Lisbon;http://lxconjugator.di.fc.ul.pt",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ba6d591e-8448-5df9-98d6-9a673304298f",
-    "notes": [
-        "Fully fledged automatic verbal conjugator for Portuguese, including all forms of clitic conjugation.It thus handles: * Pronominal conjugation The Portuguese verbal inflection system is a most complex part of the Portuguese morphology, and of the Portuguese language, given the high number of conjugated forms for each verb (ca. 70 forms in non pronominal conjugation), the number of productive inflection rules involved and the number of non regular forms and exceptions to such rules. This complexity is further increased when the so-called pronominal conjugation is taken into account. The Portuguese language has verbal clitics, which according to some authors are to be analyzed as integrating the inflectional suffix system: o the forms of the clitics may depend on the Number (Singular vs. Plural), the Person (First, Second, Third or Second courtesy), the Gender (Masculine vs. Feminine), the grammatical function which they are in correspondence with (Subject, Direct object or Indirect object), and the anaphoric properties (Pronominal vs. Reflexive); o up to three clitics (e.g. deu-se-lho / gave-One-ToHim_It) may be associated with a verb form; o clitics may occur in so called enclisis, i.e. as a final part of the verb form (e.g. deu-o / gave-It), or in mesoclisis, i.e. as a medial part of the verb form (e.g. d\u00e1-lo-ia / give-it-CONDITIONAL). When the verb form occurs in certain syntactic or semantic contexts (e.g in the scope of negation), the clitics appear in proclisis, i.e. before the verb form (ex.: n\u00e3o o deu / NOT it gave); o clitics follow specific rules for their concatenation. With LX-Conjugator, pronominal conjugation is exhaustively handled. It is however optional, and verbs can be conjugated also in non pronominal conjugation mode only. Additionally, LX-Conjugator exhaustively handles a set of inflection cases which tend not to be supported together in verbal conjugators: * Compound tenses * Double forms for past participles (regular and irregular) * Past participle forms inflected for number and gender (with transitive and unaccusative verbs) * Negative imperative forms * Courtesy forms for second person LX-Conjugator handles both known verbs and unknown verbs. It thus conjugates: * Neologisms (with orthographic infinitival suffix) It is also worth noting the following design principles, that LX-Conjugator adopts with respect to the so called defective verbs: * Defectives Some unsubstantiated assumptions from traditional grammar were not followed, according to which many verb forms do not exist and/or should not be used because they sound awkward or because their use is semantically very restricted. Accordingly, to give an example, all conjugated forms of weather verbs are delivered, as they can be used at least non literally (with forms other than third person singular ones being presented in a distinguished font to indicate that they have generally been considered non-existent). To give another example, verbs like falir are also fully conjugated (again with some of its forms marked in a disitinguished font in order to signal that some speakers may find them phonetically awkward). * Special cases LX-Conjugator does assume that some forms are impossible though (e.g. the imperative forms of verbs such as querer / to want: *quer tu) and that some clitics do not combine with certain verb forms (e.g. second person non-courtesy clitics and second person courtesy verb forms with the same number: *voc\u00ea ama-te/you_COURTESY love-yourself_NONCOURTESY). In these cases such forms will not be produced. Other special cases, also not generated, include impersonal se and passive se, which do not occur with first or second person verb forms. LX-Conjugator handles the very few cases where there may be different forms in different variants: * Orthographic and paradigmatic differences When the same form has different orthographic representations, all such representations are presented. To give a couple of examples, both representations of '(he) dicharges', desagua (European) and des\u00e1gua (Brazilian), and both representations for '(I) argued', argui (European) and arg\u00fci (Brazilian), are delivered. * Other cases Differences in irregular forms are also handled under the same approach. One such example is the past participle of 'to accept', with aceite (European) and aceito (Brazilian), which will be both displayed. Note that in general LX-Conjugator acknowledges differences in representations of the same verb form when such representations can be predicted from the representation of the infinitive form (to be entered by the user). Accordingly, representations of the same verb differing in (the non-final part of) their roots are not automatically acknowledged by the conjugator. For instance, all conjugated forms of 'to act' will start either with act- or with at-, depending on whether the user enters actuar (European) or atuar (Brazilian) as the representation of the infinitive."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1223"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LX-Conjugator"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ba6df9b6-c1d6-5078-9049-75bda6ae0609.json b/oaitestdata/clarin-oai_dc/SET_1/json/ba6df9b6-c1d6-5078-9049-75bda6ae0609.json
deleted file mode 100644
index 012b8be3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ba6df9b6-c1d6-5078-9049-75bda6ae0609.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5051",
-    "MetadataAccess": [
-        "oai:ota:oucs:5051"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Trusler, John, 1735-1820."
-    ],
-    "fulltext": "oai:ota:oucs:5051;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5051.xml;The habitable world described: or the present state of the people in all parts of the globe, from north to south; shewing the situation, extent, climate, ... including all the new discoveries: ... With a great variety of maps and copper-plates, ... By the Rev. Dr. John Trusler. ... [pt.17];Trusler, John, 1735-1820.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ba6df9b6-c1d6-5078-9049-75bda6ae0609",
-    "oai_identifier": [
-        "oai:ota:oucs:5051"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The habitable world described: or the present state of the people in all parts of the globe, from north to south; shewing the situation, extent, climate, ... including all the new discoveries: ... With a great variety of maps and copper-plates, ... By the Rev. Dr. John Trusler. ... [pt.17]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5051.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/baa9760f-01e5-521b-b893-c61500d1985c.json b/oaitestdata/clarin-oai_dc/SET_1/json/baa9760f-01e5-521b-b893-c61500d1985c.json
deleted file mode 100644
index 5964ad6f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/baa9760f-01e5-521b-b893-c61500d1985c.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5179",
-    "MetadataAccess": [
-        "oai:ota:oucs:5179"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pennant, Thomas, 1726-1798."
-    ],
-    "fulltext": "oai:ota:oucs:5179;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5179.xml;A tour in Wales. MDCCLXX: [pt.2];Pennant, Thomas, 1726-1798.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "baa9760f-01e5-521b-b893-c61500d1985c",
-    "oai_identifier": [
-        "oai:ota:oucs:5179"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A tour in Wales. MDCCLXX: [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5179.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bab84993-fa8d-502a-bd55-d49607846210.json b/oaitestdata/clarin-oai_dc/SET_1/json/bab84993-fa8d-502a-bd55-d49607846210.json
deleted file mode 100644
index d1c7fdb1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bab84993-fa8d-502a-bd55-d49607846210.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4834",
-    "MetadataAccess": [
-        "oai:ota:oucs:4834"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hutchinson, William, 1732-1814."
-    ],
-    "fulltext": "oai:ota:oucs:4834;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4834.xml;The spirit of masonry in moral and elucidatory lectures: By Wm Hutchinson ...;Hutchinson, William, 1732-1814.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bab84993-fa8d-502a-bd55-d49607846210",
-    "oai_identifier": [
-        "oai:ota:oucs:4834"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The spirit of masonry in moral and elucidatory lectures: By Wm Hutchinson ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4834.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bacc5ae4-8de8-5999-98a2-c5f56882ef86.json b/oaitestdata/clarin-oai_dc/SET_1/json/bacc5ae4-8de8-5999-98a2-c5f56882ef86.json
deleted file mode 100644
index ac2e5b95..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bacc5ae4-8de8-5999-98a2-c5f56882ef86.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "The Research Institute for the Languages of Finland"
-    ],
-    "Contributor": [
-        "Lounela, Mikko"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Finnish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-776",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-776"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-776",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "The Research Institute for the Languages of Finland"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Finland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-776;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Corpus of Old Literary Finnish;Lounela, Mikko;period: 1543&#8211;1809;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-776;fin;downloadable_files_count: 0;Finland;The Research Institute for the Languages of Finland;http://kaino.kotus.fi/korpus/vks/meta/vks_coll_rdf.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bacc5ae4-8de8-5999-98a2-c5f56882ef86",
-    "notes": [
-        "period: 1543&#8211;1809"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-776"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus of Old Literary Finnish"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bad910eb-f771-526a-8c31-7ccdfc364876.json b/oaitestdata/clarin-oai_dc/SET_1/json/bad910eb-f771-526a-8c31-7ccdfc364876.json
deleted file mode 100644
index b6349d40..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bad910eb-f771-526a-8c31-7ccdfc364876.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4880-3",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4880-3"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-4880-3",
-    "PublicationTimestamp": "2011-01-24T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Pala, Karel",
-        "Bej\u010dek, Eduard",
-        "Haji\u010d, Jan",
-        "\u010capek, Tom\u00e1\u0161",
-        "Kulkov\u00e1, Kate\u0159ina",
-        "Bart\u016f\u0161kov\u00e1, Dita",
-        "Stra\u0148\u00e1k, Pavel",
-        "Hoffmannov\u00e1, Petra",
-        "Zaj\u00ed\u010dkov\u00e1, Barbora"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4880-3;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Czech WordNet 1.9 PDT;Pala, Karel;\u010capek, Tom\u00e1\u0161;Zaj\u00ed\u010dkov\u00e1, Barbora;Bart\u016f\u0161kov\u00e1, Dita;Kulkov\u00e1, Kate\u0159ina;Hoffmannov\u00e1, Petra;Bej\u010dek, Eduard;Stra\u0148\u00e1k, Pavel;Haji\u010d, Jan;ontology;wordnet;Czech WordNet;A slightly modified version of the Czech Wordnet. This is the version used to annotate \"The Lexico-Semantic Annotation of PDT using Czech WordNet\": http://hdl.handle.net/11858/00-097C-0000-0001-487A-4\r\n\r\nThe Czech WordNet was developed by the Centre of Natural Language Processing at the Faculty of Informatics, Masaryk University, Czech Republic. \r\n\r\nThe Czech WordNet captures nouns, verbs, adjectives, and partly adverbs, and contains 23,094 word senses (synsets). 203 of these were created or modified by UFAL during correction of annotations. This version of WordNet was used to annotate word senses in PDT: http://hdl.handle.net/11858/00-097C-0000-0001-487A-4 \r\n\r\n A more recent version of Czech WordNet is distributed by ELRA: http://catalog.elra.info/product_info.php?products_id=1089;2011-01-24;corpus;http://hdl.handle.net/11858/00-097C-0000-0001-4880-3;ces;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bad910eb-f771-526a-8c31-7ccdfc364876",
-    "notes": [
-        "A slightly modified version of the Czech Wordnet. This is the version used to annotate \"The Lexico-Semantic Annotation of PDT using Czech WordNet\": http://hdl.handle.net/11858/00-097C-0000-0001-487A-4\r\n\r\nThe Czech WordNet was developed by the Centre of Natural Language Processing at the Faculty of Informatics, Masaryk University, Czech Republic. \r\n\r\nThe Czech WordNet captures nouns, verbs, adjectives, and partly adverbs, and contains 23,094 word senses (synsets). 203 of these were created or modified by UFAL during correction of annotations. This version of WordNet was used to annotate word senses in PDT: http://hdl.handle.net/11858/00-097C-0000-0001-487A-4 \r\n\r\n A more recent version of Czech WordNet is distributed by ELRA: http://catalog.elra.info/product_info.php?products_id=1089"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4880-3"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ontology"
-        },
-        {
-            "name": "wordnet"
-        },
-        {
-            "name": "Czech WordNet"
-        }
-    ],
-    "title": [
-        "Czech WordNet 1.9 PDT"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/badc1e7b-acbf-58b2-af79-8ce6c821611e.json b/oaitestdata/clarin-oai_dc/SET_1/json/badc1e7b-acbf-58b2-af79-8ce6c821611e.json
deleted file mode 100644
index 342d2375..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/badc1e7b-acbf-58b2-af79-8ce6c821611e.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "B"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1525",
-    "MetadataAccess": [
-        "oai:ota:oucs:1525"
-    ],
-    "PublicationTimestamp": "1817-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1817"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Austen, Jane (et al)"
-    ],
-    "fulltext": "oai:ota:oucs:1525;2018-04-16T15:56:46Z;http://ota.ox.ac.uk/headers/1525.xml;Sanditon;Austen, Jane (et al);1817;text_and_corpus_linguistics;Novels -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;B;Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "badc1e7b-acbf-58b2-af79-8ce6c821611e",
-    "oai_identifier": [
-        "oai:ota:oucs:1525"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Novels -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Sanditon"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1525.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bae9e788-a1b8-56db-9088-53aeaab7306b.json b/oaitestdata/clarin-oai_dc/SET_1/json/bae9e788-a1b8-56db-9088-53aeaab7306b.json
deleted file mode 100644
index 97dd4ea7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bae9e788-a1b8-56db-9088-53aeaab7306b.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 415 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1045",
-    "MetadataAccess": [
-        "oai:ota:oucs:1045"
-    ],
-    "PublicationTimestamp": "1848-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1848"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Clough, Arthur Hugh, 1819-1861"
-    ],
-    "fulltext": "oai:ota:oucs:1045;2018-03-05T10:56:22Z;http://ota.ox.ac.uk/headers/1045.xml;Poems. Selections;Collected verse;Clough, Arthur Hugh, 1819-1861;1848-1861;text_and_corpus_linguistics;Poems -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;(1 file : ca. 415 KB);Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bae9e788-a1b8-56db-9088-53aeaab7306b",
-    "oai_identifier": [
-        "oai:ota:oucs:1045"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Poems. Selections",
-        "Collected verse"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1045.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/baf670e5-281a-56be-933c-71b11006f01f.json b/oaitestdata/clarin-oai_dc/SET_1/json/baf670e5-281a-56be-933c-71b11006f01f.json
deleted file mode 100644
index 6a762786..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/baf670e5-281a-56be-933c-71b11006f01f.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Research Institute for Artificial Intelligence, Romanian Academy of Sciences"
-    ],
-    "Contributor": [
-        "Tufi\u015f, Dan",
-        "Ion, Radu"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English",
-        "Romanian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1300",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1300"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1300",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Research Institute for Artificial Intelligence, Romanian Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1300;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;YAWA - Yet Another Word Aligner;Tufi\u015f, Dan;Ion, Radu;word aligner;YAWA is a four stage lexical aligner that uses bilingual translation lexicons produced by [[http://www.clarin.eu/tools/translation-equivalents-extractor|TREQ]] and phrase boundaries detection to align words of a given bitext. Using this alignment, in stage 2 a language dependent module takes over and produces alignments of the remaining lexical tokens within aligned chunks. Stage 3 is specialized in aligning blocks of consecutive unaligned tokens and stage 4 deletes alignments that are likely to be wrong.\r\nDeveloped in PERL, YAWA is language independent, except for the modules that realise alignments specific to the pairs of aligned languages. So far, it works just for Ro-En pair of languages. It requires a parallel corpus in [[http://www.xces.org|XCES]] format, morpho-syntactically annotated and lemmatized (using [[http://www.clarin.eu/tools/ttl-tokenizing-tagging-and-lemmatizing-free-running-texts|TTL]]), and translation dictionaries produced by [[http://www.clarin.eu/tools/translation-equivalents-extractor|TREQ]].\r\nYAWA\u2019s individual F-measure is 81.22%. Currently YAWA is a part of the [[http://www.clarin.eu/tools/cowal-combined-word-aligner|COWAL]] combined lexical alignment platform.\r\nMore detailed descriptions are available in [[http://www.racai.ro/~tufis/papers|the following papers]]: \r\n  -- Radu Ion (2007). Word Sense Disambiguation Methods Applied to English and Romanian. (in Romanian). PhD thesis. Romanian Academy, Bucharest\r\n  -- Dan Tufi\u015f (2007). Exploiting Aligned Parallel Corpora in Multilingual Studies and Applications. In Toru Ishida, Susan R. Fussell, and Piek T.J.M. Vossen (eds.), Intercultural Collaboration. First International Workshop (IWIC 2007), volume 4568 of Lecture Notes in Computer Science, pp. 103-117. Springer-Verlag, August 2007. ISBN 978-3-540-73999-9. \r\n  -- Dan Tufi\u015f, Radu Ion, Alexandru Ceau\u015fu, and Dan \u015etef\u0103nescu (2006). Improved Lexical Alignment by Combining Multiple Reified Alignments. In Toru Ishida, Susan R. Fussell, and Piek T.J.M. Vossen (eds.), Proceedings of the 11th Conference EACL2006, pp. 153-160, Trento, Italy, April 2006. Association for Computational Linguistics. ISBN 1-9324-32-61-2.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1300;eng;ron;downloadable_files_count: 0;Research Institute for Artificial Intelligence, Romanian Academy of Sciences",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "baf670e5-281a-56be-933c-71b11006f01f",
-    "notes": [
-        "YAWA is a four stage lexical aligner that uses bilingual translation lexicons produced by [[http://www.clarin.eu/tools/translation-equivalents-extractor|TREQ]] and phrase boundaries detection to align words of a given bitext. Using this alignment, in stage 2 a language dependent module takes over and produces alignments of the remaining lexical tokens within aligned chunks. Stage 3 is specialized in aligning blocks of consecutive unaligned tokens and stage 4 deletes alignments that are likely to be wrong.\r\nDeveloped in PERL, YAWA is language independent, except for the modules that realise alignments specific to the pairs of aligned languages. So far, it works just for Ro-En pair of languages. It requires a parallel corpus in [[http://www.xces.org|XCES]] format, morpho-syntactically annotated and lemmatized (using [[http://www.clarin.eu/tools/ttl-tokenizing-tagging-and-lemmatizing-free-running-texts|TTL]]), and translation dictionaries produced by [[http://www.clarin.eu/tools/translation-equivalents-extractor|TREQ]].\r\nYAWA\u2019s individual F-measure is 81.22%. Currently YAWA is a part of the [[http://www.clarin.eu/tools/cowal-combined-word-aligner|COWAL]] combined lexical alignment platform.\r\nMore detailed descriptions are available in [[http://www.racai.ro/~tufis/papers|the following papers]]: \r\n  -- Radu Ion (2007). Word Sense Disambiguation Methods Applied to English and Romanian. (in Romanian). PhD thesis. Romanian Academy, Bucharest\r\n  -- Dan Tufi\u015f (2007). Exploiting Aligned Parallel Corpora in Multilingual Studies and Applications. In Toru Ishida, Susan R. Fussell, and Piek T.J.M. Vossen (eds.), Intercultural Collaboration. First International Workshop (IWIC 2007), volume 4568 of Lecture Notes in Computer Science, pp. 103-117. Springer-Verlag, August 2007. ISBN 978-3-540-73999-9. \r\n  -- Dan Tufi\u015f, Radu Ion, Alexandru Ceau\u015fu, and Dan \u015etef\u0103nescu (2006). Improved Lexical Alignment by Combining Multiple Reified Alignments. In Toru Ishida, Susan R. Fussell, and Piek T.J.M. Vossen (eds.), Proceedings of the 11th Conference EACL2006, pp. 153-160, Trento, Italy, April 2006. Association for Computational Linguistics. ISBN 1-9324-32-61-2."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1300"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "word aligner"
-        }
-    ],
-    "title": [
-        "YAWA - Yet Another Word Aligner"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bb3ce4ef-3daa-5e36-a8a4-34443fc6e1c1.json b/oaitestdata/clarin-oai_dc/SET_1/json/bb3ce4ef-3daa-5e36-a8a4-34443fc6e1c1.json
deleted file mode 100644
index 85deb1e7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bb3ce4ef-3daa-5e36-a8a4-34443fc6e1c1.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "[s.n.]"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-8328",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-8328"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D37-0",
-    "PublicationTimestamp": "1779-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1779"
-    ],
-    "Publisher": [
-        "[s.n.]"
-    ],
-    "RelatedIdentifier": [
-        "http://www.pbc.rzeszow.pl/Content/8328",
-        "oai:www.pbc.rzeszow.pl:publication:9016"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "author": [
-        "Jab\u0142onowski, Jan Stanis\u0142aw (1669-1731)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-8328;2019-03-01T17:38:45Z;Skrupu\u0142 bez skrupu\u0142u w Polszcze, albo o\u015bwiecenie grzech\u00f3w narodowi naszemu polskiemu zwyczaynieyszych, a za grzechy niemianych : traktat po prostu te grzechy roztrz\u0105sai\u0105cy, na rozdzia\u0142y podzielony, przez pewnego Polaka temi\u017c grzechami grzesznego, ale \u017ca\u0142ui\u0105cego. Na popraw\u0119 swoi\u0105 y Ludzk\u0105;Jab\u0142onowski, Jan Stanis\u0142aw (1669-1731);Polska - polityka - 17-18 w.;publicystyka polska - 18 w.;Na s. tyt. inf.: Roku 1730. do druku podany we Lwowie a roku 1779. na \u017c\u0105danie pewnego Ministra przedrukowany;Zawiera ryciny;[s.n.];1779;starodruk;application/xml;clarind-uds:poldilemma-8328;hdl:11858/00-246C-0000-0023-8D37-0;Sygnatura orygina\u0142u: SD-845;pol;lat;http://www.pbc.rzeszow.pl/Content/8328;oai:www.pbc.rzeszow.pl:publication:9016;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bb3ce4ef-3daa-5e36-a8a4-34443fc6e1c1",
-    "notes": [
-        "Na s. tyt. inf.: Roku 1730. do druku podany we Lwowie a roku 1779. na \u017c\u0105danie pewnego Ministra przedrukowany",
-        "Zawiera ryciny"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-8328"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Polska - polityka - - w."
-        },
-        {
-            "name": "publicystyka polska - w."
-        }
-    ],
-    "title": [
-        "Skrupu\u0142 bez skrupu\u0142u w Polszcze, albo o\u015bwiecenie grzech\u00f3w narodowi naszemu polskiemu zwyczaynieyszych, a za grzechy niemianych : traktat po prostu te grzechy roztrz\u0105sai\u0105cy, na rozdzia\u0142y podzielony, przez pewnego Polaka temi\u017c grzechami grzesznego, ale \u017ca\u0142ui\u0105cego. Na popraw\u0119 swoi\u0105 y Ludzk\u0105"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bb4619c4-08ae-5941-9987-ce70f9f67c47.json b/oaitestdata/clarin-oai_dc/SET_1/json/bb4619c4-08ae-5941-9987-ce70f9f67c47.json
deleted file mode 100644
index 920efaca..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bb4619c4-08ae-5941-9987-ce70f9f67c47.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2837",
-    "MetadataAccess": [
-        "oai:ota:oucs:2837"
-    ],
-    "PublicationTimestamp": "1732-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1732"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2837;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2837.xml;A modest proposal;Swift, Jonathan, 1667-1745;1732;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bb4619c4-08ae-5941-9987-ce70f9f67c47",
-    "oai_identifier": [
-        "oai:ota:oucs:2837"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A modest proposal"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2837.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bb56b1ec-540e-5849-af3c-bac10a322182.json b/oaitestdata/clarin-oai_dc/SET_1/json/bb56b1ec-540e-5849-af3c-bac10a322182.json
deleted file mode 100644
index e0d65366..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bb56b1ec-540e-5849-af3c-bac10a322182.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4628",
-    "MetadataAccess": [
-        "oai:ota:oucs:4628"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Woolston, Thomas, 1670-1733."
-    ],
-    "fulltext": "oai:ota:oucs:4628;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4628.xml;A fifth discourse on the miracles of our Saviour: in view of the present controversy between infidels and apostates. The second edition. By Tho. Woolston, ...;Woolston, Thomas, 1670-1733.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bb56b1ec-540e-5849-af3c-bac10a322182",
-    "oai_identifier": [
-        "oai:ota:oucs:4628"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A fifth discourse on the miracles of our Saviour: in view of the present controversy between infidels and apostates. The second edition. By Tho. Woolston, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4628.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bb57b1c8-516f-5862-b459-d6120173ea7d.json b/oaitestdata/clarin-oai_dc/SET_1/json/bb57b1c8-516f-5862-b459-d6120173ea7d.json
deleted file mode 100644
index a2b149be..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bb57b1c8-516f-5862-b459-d6120173ea7d.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "University of Bergen"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English",
-        "French"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/125",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/125"
-    ],
-    "PID": "http://hdl.handle.net/11509/125",
-    "PublicationTimestamp": "2018-02-19T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "University of Bergen"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN_RES-NC-PRIV",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaRes?ID=1&PERM=1&PLAN=1&BY=1&NC=1&PRIV=1&NORED=1",
-        "RES"
-    ],
-    "author": [
-        "Trebbi, Turid"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/125;2018-02-27T09:16:53Z;hdl_11509_1;hdl_11509_2;DISPRA - Discourse and practice in the foreign language classroom in cross cultural perspective;Trebbi, Turid;Spoken Language;Second Language;Discourse;Sound files recorded in foreign language classrooms:\r\n\r\n1 Enregistrement PARTIE I P1_STE-001.wav\r\n\r\n\r\nDue to protection of informant privacy the dissemination of the recordings is restricted to the DISPRA research group, who can request a download by contacting Clarino Bergen Repository.\r\n\r\nPublicly available datasets resulting from DISPRA will be added to this repository item.;2018-02-19;corpus;http://hdl.handle.net/11509/125;eng;fra;CLARIN_RES-NC-PRIV;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaRes?ID=1&PERM=1&PLAN=1&BY=1&NC=1&PRIV=1&NORED=1;RES;text/plain; charset=utf-8;downloadable_files_count: 0;University of Bergen",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bb57b1c8-516f-5862-b459-d6120173ea7d",
-    "notes": [
-        "Sound files recorded in foreign language classrooms:\r\n\r\n1 Enregistrement PARTIE I P1_STE-001.wav\r\n\r\n\r\nDue to protection of informant privacy the dissemination of the recordings is restricted to the DISPRA research group, who can request a download by contacting Clarino Bergen Repository.\r\n\r\nPublicly available datasets resulting from DISPRA will be added to this repository item."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/125"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Spoken Language"
-        },
-        {
-            "name": "Second Language"
-        },
-        {
-            "name": "Discourse"
-        }
-    ],
-    "title": [
-        "DISPRA - Discourse and practice in the foreign language classroom in cross cultural perspective"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bb6cfbbf-517d-53c4-85d6-1f040676d066.json b/oaitestdata/clarin-oai_dc/SET_1/json/bb6cfbbf-517d-53c4-85d6-1f040676d066.json
deleted file mode 100644
index f1bc9a21..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bb6cfbbf-517d-53c4-85d6-1f040676d066.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Wilson, David"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(2 files : total of ca. 392 KB)",
-        "text/plain"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1720",
-    "MetadataAccess": [
-        "oai:ota:oucs:1720"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Short stories"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Joyce, James, 1882-1941"
-    ],
-    "fulltext": "oai:ota:oucs:1720;2018-02-16T10:42:06Z;http://ota.ox.ac.uk/headers/1720.xml;Dubliners / James Joyce;Joyce, James, 1882-1941;text_and_corpus_linguistics;Short stories, Irish -- 20th century;This resource includes the following stories: \"The Sisters\", \"An Encounter\", \"Araby\", \"Eveline\", \"After the Race\", \"Two Gallants\", \"The Boarding House\", \"A Little Cloud\", \"Counterparts\", \"Clay\", \"A Painful Case\", \"Ivy Day in the Committee Room\", \"A Mother\", \"Grace\" and \"The Dead\". ;Oxford Text Archive, University of Oxford;Wilson, David;text/plain;(2 files : total of ca. 392 KB);Text;Short stories;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bb6cfbbf-517d-53c4-85d6-1f040676d066",
-    "notes": [
-        "This resource includes the following stories: \"The Sisters\", \"An Encounter\", \"Araby\", \"Eveline\", \"After the Race\", \"Two Gallants\", \"The Boarding House\", \"A Little Cloud\", \"Counterparts\", \"Clay\", \"A Painful Case\", \"Ivy Day in the Committee Room\", \"A Mother\", \"Grace\" and \"The Dead\". "
-    ],
-    "oai_identifier": [
-        "oai:ota:oucs:1720"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Short stories"
-        },
-        {
-            "name": "Irish -- th century"
-        }
-    ],
-    "title": [
-        "Dubliners / James Joyce"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1720.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bb73c647-1dde-5068-9615-ea6a420d1c5c.json b/oaitestdata/clarin-oai_dc/SET_1/json/bb73c647-1dde-5068-9615-ea6a420d1c5c.json
deleted file mode 100644
index 3ceb047b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bb73c647-1dde-5068-9615-ea6a420d1c5c.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Wikipedia"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 6885",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/222",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/222"
-    ],
-    "PID": "http://hdl.handle.net/11321/222",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Wikipedia"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Wikipedia"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/222;2015-06-22T12:24:12Z;hdl_11321_3;hdl_11321_4;Wiki train - 34 categories;Wikipedia;Wikipedia, 34 kategorie - zbi\u00f3r do uczenia klasyfikatora;2015;corpus;http://hdl.handle.net/11321/222;Polish;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bb73c647-1dde-5068-9615-ea6a420d1c5c",
-    "notes": [
-        "Wikipedia, 34 kategorie - zbi\u00f3r do uczenia klasyfikatora"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/222"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Wiki train - 34 categories"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bb8a05d9-0e30-5e3d-a751-c7876328e6a9.json b/oaitestdata/clarin-oai_dc/SET_1/json/bb8a05d9-0e30-5e3d-a751-c7876328e6a9.json
deleted file mode 100644
index 582a4b1e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bb8a05d9-0e30-5e3d-a751-c7876328e6a9.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4589",
-    "MetadataAccess": [
-        "oai:ota:oucs:4589"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Congreve, William, 1670-1729."
-    ],
-    "fulltext": "oai:ota:oucs:4589;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4589.xml;Mr. Congreve's last will and testament: with characters of his writings. By Mr. Dryden, Sir Richard Blackmore, Mr. Addison and Major Pack. To which are added, two pieces, viz. I. Of rightly improving the present time. ... II. The game of quadrille. An allegory.;Congreve, William, 1670-1729.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bb8a05d9-0e30-5e3d-a751-c7876328e6a9",
-    "oai_identifier": [
-        "oai:ota:oucs:4589"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Mr. Congreve's last will and testament: with characters of his writings. By Mr. Dryden, Sir Richard Blackmore, Mr. Addison and Major Pack. To which are added, two pieces, viz. I. Of rightly improving the present time. ... II. The game of quadrille. An allegory."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4589.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bb90b4a2-84fa-5ef8-b101-c5b378ded537.json b/oaitestdata/clarin-oai_dc/SET_1/json/bb90b4a2-84fa-5ef8-b101-c5b378ded537.json
deleted file mode 100644
index 75f179ce..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bb90b4a2-84fa-5ef8-b101-c5b378ded537.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "University of Glasgow"
-    ],
-    "Contributor": [
-        "Mansueto, Donato"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-899",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-899"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-899",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Glasgow"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-899;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Corpus of Italian Emblem Books;Mansueto, Donato;Italian emblem books from the Stirling Maxwell Collection (University of Glasgow). Transcribed text and photographi reproducitons. Searchable and browsable online;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-899;ita;downloadable_files_count: 0;United Kingdom;University of Glasgow;http://www.italianemblems.arts.gla.ac.uk/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bb90b4a2-84fa-5ef8-b101-c5b378ded537",
-    "notes": [
-        "Italian emblem books from the Stirling Maxwell Collection (University of Glasgow). Transcribed text and photographi reproducitons. Searchable and browsable online"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-899"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus of Italian Emblem Books"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bbc5c128-e766-5443-b815-7077eb5b3e1e.json b/oaitestdata/clarin-oai_dc/SET_1/json/bbc5c128-e766-5443-b815-7077eb5b3e1e.json
deleted file mode 100644
index 4c58ceaf..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bbc5c128-e766-5443-b815-7077eb5b3e1e.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 547 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2172",
-    "MetadataAccess": [
-        "oai:ota:oucs:2172"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Politics"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hobbes, Thomas, 1588-1679"
-    ],
-    "fulltext": "oai:ota:oucs:2172;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/2172.xml;De cive : containing the elements of civill politie in the agreement which it hath both with naturall and divine lawes in which is demonstrated, both what the origine of justice is, and wherein the essence of Christian religion doth consist together with the nature, limits and qualifications both of regiment and subjection / Thomas Hobbes;The citizen;Hobbes, Thomas, 1588-1679;text_and_corpus_linguistics;Political science -- Early works to 1800;eng;Oxford Text Archive, University of Oxford;Triggs, Jeffery;text/sgml;(1 file : ca. 547 KB);Text;Politics;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bbc5c128-e766-5443-b815-7077eb5b3e1e",
-    "oai_identifier": [
-        "oai:ota:oucs:2172"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Political science -- Early works"
-        }
-    ],
-    "title": [
-        "De cive : containing the elements of civill politie in the agreement which it hath both with naturall and divine lawes in which is demonstrated, both what the origine of justice is, and wherein the essence of Christian religion doth consist together with the nature, limits and qualifications both of regiment and subjection / Thomas Hobbes",
-        "The citizen"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2172.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bbd4c65a-5364-5ece-94a9-706e1e2dc19e.json b/oaitestdata/clarin-oai_dc/SET_1/json/bbd4c65a-5364-5ece-94a9-706e1e2dc19e.json
deleted file mode 100644
index 2e93dee4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bbd4c65a-5364-5ece-94a9-706e1e2dc19e.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1807",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1807"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1807",
-    "PublicationTimestamp": "2016-10-20T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-1520",
-        "http://hdl.handle.net/11234/1-2422"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "Vidra, Jon\u00e1\u0161",
-        "\u0160ev\u010d\u00edkov\u00e1, Magda",
-        "Straka, Milan"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1807;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;DeriNet 1.2;Vidra, Jon\u00e1\u0161;\u017dabokrtsk\u00fd, Zden\u011bk;\u0160ev\u010d\u00edkov\u00e1, Magda;Straka, Milan;derivation;DeriNet;lexical network;MorfFlex;DeriNet is a lexical network which models derivational relations in the lexicon of Czech. Nodes of the network correspond to Czech lexemes (i.e. single lemmas, possibly with only a subset of their senses), edges represent derivational relations between a derived word and its base word. The present version, DeriNet 1.2, contains 1,003,590 lexemes (sampled from the MorfFlex dictionary) with 1,001,394 unique lemmas, connected by 740,750 derivational links. Both rather technical and linguistic changes were made as compared to the previous version of the data; e.g. new version of the MorfFlex dictionary was used, derived words that contain a consonant and/or vowel alternation (e.g. bo\u017e\u00ed) were connected with their base word (b\u016fh).;2016-10-20;lexicalConceptualResource;http://hdl.handle.net/11234/1-1807;ces;http://hdl.handle.net/11234/1-1520;http://hdl.handle.net/11234/1-2422;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://ufal.mff.cuni.cz/derinet",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bbd4c65a-5364-5ece-94a9-706e1e2dc19e",
-    "notes": [
-        "DeriNet is a lexical network which models derivational relations in the lexicon of Czech. Nodes of the network correspond to Czech lexemes (i.e. single lemmas, possibly with only a subset of their senses), edges represent derivational relations between a derived word and its base word. The present version, DeriNet 1.2, contains 1,003,590 lexemes (sampled from the MorfFlex dictionary) with 1,001,394 unique lemmas, connected by 740,750 derivational links. Both rather technical and linguistic changes were made as compared to the previous version of the data; e.g. new version of the MorfFlex dictionary was used, derived words that contain a consonant and/or vowel alternation (e.g. bo\u017e\u00ed) were connected with their base word (b\u016fh)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1807"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "derivation"
-        },
-        {
-            "name": "DeriNet"
-        },
-        {
-            "name": "lexical network"
-        },
-        {
-            "name": "MorfFlex"
-        }
-    ],
-    "title": [
-        "DeriNet 1.2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bbf50c44-c1be-5747-8749-47ce915fc5e5.json b/oaitestdata/clarin-oai_dc/SET_1/json/bbf50c44-c1be-5747-8749-47ce915fc5e5.json
deleted file mode 100644
index 630d1a6a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bbf50c44-c1be-5747-8749-47ce915fc5e5.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Ruhr-Universit\u00e4t Bochum"
-    ],
-    "Contributor": [
-        "Wegera, Prof. Dr. Klaus-Peter"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1131",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1131"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1131",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Ruhr-Universit\u00e4t Bochum"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1131;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Bochumer Mittelhochdeutsch-Korpus;Wegera, Prof. Dr. Klaus-Peter;Germanistik;Verses, prose and certificates from Middle High German; mittelhochdeutsche Verse, Prosast\u00fccke und Urkunden;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1131;deu;downloadable_files_count: 0;Germany;Ruhr-Universit\u00e4t Bochum;http://www.ruhr-uni-bochum.de/wegera/archiv_1.htm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bbf50c44-c1be-5747-8749-47ce915fc5e5",
-    "notes": [
-        "Verses, prose and certificates from Middle High German; mittelhochdeutsche Verse, Prosast\u00fccke und Urkunden"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1131"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Bochumer Mittelhochdeutsch-Korpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bc063b47-d32e-5839-8b57-aa484171b41c.json b/oaitestdata/clarin-oai_dc/SET_1/json/bc063b47-d32e-5839-8b57-aa484171b41c.json
deleted file mode 100644
index d9baed1e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bc063b47-d32e-5839-8b57-aa484171b41c.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/304",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/304"
-    ],
-    "PID": "http://hdl.handle.net/11321/304",
-    "PublicationTimestamp": "2016-05-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "K\u0119dzia, Pawe\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/304;2016-06-07T09:57:05Z;hdl_11321_3;hdl_11321_4;NPSemRel;K\u0119dzia, Pawe\u0142;Semantic role labelling;Semantic roles;Nominal phrase;NPSemrel is a tool for recognizing semantic roles into nominal Phrases.;2016-05-01;toolService;http://hdl.handle.net/11321/304;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 1;Wroc\u0142aw University of Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bc063b47-d32e-5839-8b57-aa484171b41c",
-    "notes": [
-        "NPSemrel is a tool for recognizing semantic roles into nominal Phrases."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/304"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Semantic role labelling"
-        },
-        {
-            "name": "Semantic roles"
-        },
-        {
-            "name": "Nominal phrase"
-        }
-    ],
-    "title": [
-        "NPSemRel"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bc1d3cc1-9606-5167-a812-b8ebea5439bc.json b/oaitestdata/clarin-oai_dc/SET_1/json/bc1d3cc1-9606-5167-a812-b8ebea5439bc.json
deleted file mode 100644
index b4c01a7c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bc1d3cc1-9606-5167-a812-b8ebea5439bc.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Waite, Stephen V.F."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 441 KB)"
-    ],
-    "Language": [
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0374",
-    "MetadataAccess": [
-        "oai:ota:oucs:0374"
-    ],
-    "PublicationYear": [
-        "29 BCE-19 BCE"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Virgil"
-    ],
-    "fulltext": "oai:ota:oucs:0374;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0374.xml;Aeneidos / Virgil;Aeneid;Aeneis;Virgil;29 BCE-19 BCE;text_and_corpus_linguistics;Epic poetry, Latin  -- 1st century B.C.;lat;Oxford Text Archive, University of Oxford;Waite, Stephen V.F.;(1 file : ca. 441 KB);Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bc1d3cc1-9606-5167-a812-b8ebea5439bc",
-    "oai_identifier": [
-        "oai:ota:oucs:0374"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Epic poetry"
-        },
-        {
-            "name": "Latin -- st century B.C."
-        }
-    ],
-    "title": [
-        "Aeneidos / Virgil",
-        "Aeneid",
-        "Aeneis"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0374.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bc27fca6-82bc-5d0a-8ffa-9dade22eb0a4.json b/oaitestdata/clarin-oai_dc/SET_1/json/bc27fca6-82bc-5d0a-8ffa-9dade22eb0a4.json
deleted file mode 100644
index 00460d89..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bc27fca6-82bc-5d0a-8ffa-9dade22eb0a4.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Institute of Mathematics and Computer Science, University of Latvia"
-    ],
-    "Contributor": [
-        "Pinnis, M\u0101rcis",
-        "Auzi\u0146a, Ilze",
-        "Gr\u016bz\u012btis, Normunds",
-        "Rostoks, Valters"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Latvian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1218",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1218"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1218",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institute of Mathematics and Computer Science, University of Latvia"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Latvia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1218;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Latvian Text-to-Speech Synthesizer;Pinnis, M\u0101rcis;Gr\u016bz\u012btis, Normunds;Rostoks, Valters;Auzi\u0146a, Ilze;Latvian Text-to-Speech Synthesizer: a RESTful web service.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1218;lav;downloadable_files_count: 0;Latvia;Institute of Mathematics and Computer Science, University of Latvia;http://valoda.ailab.lv/ws/tts.jsp",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bc27fca6-82bc-5d0a-8ffa-9dade22eb0a4",
-    "notes": [
-        "Latvian Text-to-Speech Synthesizer: a RESTful web service."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1218"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Latvian Text-to-Speech Synthesizer"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bc2c86c6-0c59-5f99-9dc8-6bfb5f53d2e2.json b/oaitestdata/clarin-oai_dc/SET_1/json/bc2c86c6-0c59-5f99-9dc8-6bfb5f53d2e2.json
deleted file mode 100644
index 1b0e9c07..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bc2c86c6-0c59-5f99-9dc8-6bfb5f53d2e2.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Ewe"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1003",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1003"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1003",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1003;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LAC Ewe Corpus;Language and Cognition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1003;ewe;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI28415%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bc2c86c6-0c59-5f99-9dc8-6bfb5f53d2e2",
-    "notes": [
-        "Language and Cognition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1003"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LAC Ewe Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bc317907-7fca-51c1-95c9-4cf24f26e563.json b/oaitestdata/clarin-oai_dc/SET_1/json/bc317907-7fca-51c1-95c9-4cf24f26e563.json
deleted file mode 100644
index b4acc2ff..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bc317907-7fca-51c1-95c9-4cf24f26e563.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5066",
-    "MetadataAccess": [
-        "oai:ota:oucs:5066"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Trusler, John, 1735-1820."
-    ],
-    "fulltext": "oai:ota:oucs:5066;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5066.xml;The way to be rich and respectable: Addressed to men of small fortune. In this pamphlet is given an estimate, shewing that a gentleman, ... may, ... live as well as, a man of 1000l. a year, and yet not expend 400l. ...;Trusler, John, 1735-1820.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bc317907-7fca-51c1-95c9-4cf24f26e563",
-    "oai_identifier": [
-        "oai:ota:oucs:5066"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The way to be rich and respectable: Addressed to men of small fortune. In this pamphlet is given an estimate, shewing that a gentleman, ... may, ... live as well as, a man of 1000l. a year, and yet not expend 400l. ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5066.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bc3f2396-d5af-5b7c-be5c-97ca7618178d.json b/oaitestdata/clarin-oai_dc/SET_1/json/bc3f2396-d5af-5b7c-be5c-97ca7618178d.json
deleted file mode 100644
index f62d86c1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bc3f2396-d5af-5b7c-be5c-97ca7618178d.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Berlin-Brandenburg Academy of Sciences and Humanities"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/tei+xml",
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1011",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1011"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1011",
-    "PublicationTimestamp": "2012-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Berlin-Brandenburg Academy of Sciences and Humanities"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1011;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Deutsches W\u00f6rterbuch (1DWB, by Jacob and Wilhelm Grimm);retro-digitized version of the first edition of the Deutsches W\u00f6rterbuch by Jacob and Wilhelm Grimm, originally published from 1854 to 1960;2012;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1011;deu;application/tei+xml;downloadable_files_count: 0;Germany;Berlin-Brandenburg Academy of Sciences and Humanities;http://www.dwds.de/ressourcen/woerterbuecher/#part_24",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bc3f2396-d5af-5b7c-be5c-97ca7618178d",
-    "notes": [
-        "retro-digitized version of the first edition of the Deutsches W\u00f6rterbuch by Jacob and Wilhelm Grimm, originally published from 1854 to 1960"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1011"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Deutsches W\u00f6rterbuch (1DWB, by Jacob and Wilhelm Grimm)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bc4af275-5b01-5b64-8932-ddefdff5f8ef.json b/oaitestdata/clarin-oai_dc/SET_1/json/bc4af275-5b01-5b64-8932-ddefdff5f8ef.json
deleted file mode 100644
index a56658d0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bc4af275-5b01-5b64-8932-ddefdff5f8ef.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Amebis, d. o. o., Kamnik"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1055",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1055"
-    ],
-    "PID": "http://hdl.handle.net/11356/1055",
-    "PublicationTimestamp": "2016-03-03T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Amebis, d. o. o., Kamnik"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11356/1185"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Holozan, Peter"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1055;2018-04-15T08:14:01Z;hdl_11356_1023;hdl_11356_1024;Corpus of comma placement Vejica 1.0;Holozan, Peter;comma placement;error annotation;manual annotation;A collection of sentences demonstrating and correcting comma usage.\r\nThe sentences come from four sources:\r\n- KUST: a Slovene learner corpus, http://nl.ijs.si/isjt06/proc/26_Stritar.pdf\r\n- \u0160olar: a corpus of student writing, http://www.slovenscina.eu/korpusi/solar\r\n- Lektor: a corpus of proof-reading corrections, http://www.slovenscina.eu/korpusi/lektor\r\n- Wikipedija: https://sl.wikipedia.org/wiki/Glavna_stran\r\nFor Lektor, the comma corrections of proof-readers were used. For other texts, the comma errors were manually marked by Peter Holozan.;2016-03-03;corpus;http://hdl.handle.net/11356/1055;slv;http://hdl.handle.net/11356/1185;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);https://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;text/plain;application/zip;text/plain; charset=utf-8;downloadable_files_count: 2;Amebis, d. o. o., Kamnik;http://peter.amebis.si/vejica.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bc4af275-5b01-5b64-8932-ddefdff5f8ef",
-    "notes": [
-        "A collection of sentences demonstrating and correcting comma usage.\r\nThe sentences come from four sources:\r\n- KUST: a Slovene learner corpus, http://nl.ijs.si/isjt06/proc/26_Stritar.pdf\r\n- \u0160olar: a corpus of student writing, http://www.slovenscina.eu/korpusi/solar\r\n- Lektor: a corpus of proof-reading corrections, http://www.slovenscina.eu/korpusi/lektor\r\n- Wikipedija: https://sl.wikipedia.org/wiki/Glavna_stran\r\nFor Lektor, the comma corrections of proof-readers were used. For other texts, the comma errors were manually marked by Peter Holozan."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1055"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "comma placement"
-        },
-        {
-            "name": "error annotation"
-        },
-        {
-            "name": "manual annotation"
-        }
-    ],
-    "title": [
-        "Corpus of comma placement Vejica 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bc4d2dd2-8716-5a58-9100-bc379af3c928.json b/oaitestdata/clarin-oai_dc/SET_1/json/bc4d2dd2-8716-5a58-9100-bc379af3c928.json
deleted file mode 100644
index ac4e916e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bc4d2dd2-8716-5a58-9100-bc379af3c928.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "64 KB"
-    ],
-    "Language": [
-        "Old High German (ca. 750-1050)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1863",
-    "MetadataAccess": [
-        "oai:ota:oucs:1863"
-    ],
-    "PublicationYear": [
-        "750-799"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Unknown"
-    ],
-    "fulltext": "oai:ota:oucs:1863;2018-04-11T16:03:39Z;http://ota.ox.ac.uk/headers/1863.xml;Der althochdeutsche Isidor;Unknown;750-799;text_and_corpus_linguistics;goh;Oxford Text Archive, University of Oxford;64 KB;Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bc4d2dd2-8716-5a58-9100-bc379af3c928",
-    "oai_identifier": [
-        "oai:ota:oucs:1863"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Der althochdeutsche Isidor"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1863.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bc6c051a-835e-5bfa-ab4c-75075fd1b6cb.json b/oaitestdata/clarin-oai_dc/SET_1/json/bc6c051a-835e-5bfa-ab4c-75075fd1b6cb.json
deleted file mode 100644
index a12ccb80..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bc6c051a-835e-5bfa-ab4c-75075fd1b6cb.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5091",
-    "MetadataAccess": [
-        "oai:ota:oucs:5091"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Carey, Henry, 1687?-1743."
-    ],
-    "fulltext": "oai:ota:oucs:5091;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5091.xml;Cupid and Hymen: or, a voyage to the isles of love and matrimony. ... Translated from the French original. To which is added, The batchelor's estimate of the expences attending a married life. The married man's answer to it : ... By John Single, ...;Carey, Henry, 1687?-1743.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bc6c051a-835e-5bfa-ab4c-75075fd1b6cb",
-    "oai_identifier": [
-        "oai:ota:oucs:5091"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Cupid and Hymen: or, a voyage to the isles of love and matrimony. ... Translated from the French original. To which is added, The batchelor's estimate of the expences attending a married life. The married man's answer to it : ... By John Single, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5091.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bc7082f4-e695-58a5-ac37-6d88979eb53e.json b/oaitestdata/clarin-oai_dc/SET_1/json/bc7082f4-e695-58a5-ac37-6d88979eb53e.json
deleted file mode 100644
index f47c4b69..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bc7082f4-e695-58a5-ac37-6d88979eb53e.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/11",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/11"
-    ],
-    "PID": "http://hdl.handle.net/11321/11",
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Radziszewski, Adam"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/11;2016-01-19T14:02:50Z;hdl_11321_3;hdl_11321_4;Disaster;Radziszewski, Adam;Disaster (DISAmbiguator and STatistical chunkER) is a Python module for chunking and morphosyntactic disambiguation.;2011;toolService;http://hdl.handle.net/11321/11;pol;downloadable_files_count: 0;Wroc\u0142aw University of Technology;http://plwordnet.pwr.wroc.pl/trac/private/disaster/wiki/SoftwareInfo",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bc7082f4-e695-58a5-ac37-6d88979eb53e",
-    "notes": [
-        "Disaster (DISAmbiguator and STatistical chunkER) is a Python module for chunking and morphosyntactic disambiguation."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/11"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Disaster"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bc728f30-4381-5557-bbbc-c9e3bef5dccf.json b/oaitestdata/clarin-oai_dc/SET_1/json/bc728f30-4381-5557-bbbc-c9e3bef5dccf.json
deleted file mode 100644
index b792e9b8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bc728f30-4381-5557-bbbc-c9e3bef5dccf.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=2ba9f1c6a35a11e1a404080027e73ea294bc886136fd4ee69244f2976ddf4c14",
-    "MetadataAccess": [
-        "2ba9f1c6a35a11e1a404080027e73ea294bc886136fd4ee69244f2976ddf4c14"
-    ],
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "2ba9f1c6a35a11e1a404080027e73ea294bc886136fd4ee69244f2976ddf4c14;2019-02-27T12:08:55Z;corpus;corpus:text;Laws of Malta - Maltese;The corpus contains the Laws of Malta in Maltese from the official government website. The unannotated raw text files were extracted from the pdf files that can be found on the website.;2015-12-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bc728f30-4381-5557-bbbc-c9e3bef5dccf",
-    "notes": [
-        "The corpus contains the Laws of Malta in Maltese from the official government website. The unannotated raw text files were extracted from the pdf files that can be found on the website."
-    ],
-    "oai_identifier": [
-        "2ba9f1c6a35a11e1a404080027e73ea294bc886136fd4ee69244f2976ddf4c14"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "Laws of Malta - Maltese"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bc742867-2543-5f45-9875-d8842bd5a4c8.json b/oaitestdata/clarin-oai_dc/SET_1/json/bc742867-2543-5f45-9875-d8842bd5a4c8.json
deleted file mode 100644
index d60c93fe..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bc742867-2543-5f45-9875-d8842bd5a4c8.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/286",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/286"
-    ],
-    "PID": "http://hdl.handle.net/11321/286",
-    "PublicationTimestamp": "2016-04-25T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Oleksy, Marcin",
-        "Wieczorek, Jan"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/286;2016-06-03T14:17:54Z;hdl_11321_3;hdl_11321_4;NE_SUMO_PLWN_mapping;Wieczorek, Jan;Oleksy, Marcin;named entities;SUMO;plWordNet;Mapping between named entities types, SUMO catagories and plWordNet synsets;2016-04-25;lexicalConceptualResource;http://hdl.handle.net/11321/286;pol;eng;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;Wroc\u0142aw University of Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bc742867-2543-5f45-9875-d8842bd5a4c8",
-    "notes": [
-        "Mapping between named entities types, SUMO catagories and plWordNet synsets"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/286"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "named entities"
-        },
-        {
-            "name": "SUMO"
-        },
-        {
-            "name": "plWordNet"
-        }
-    ],
-    "title": [
-        "NE_SUMO_PLWN_mapping"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bc8bd90f-e445-57b2-a394-240102ca8fb3.json b/oaitestdata/clarin-oai_dc/SET_1/json/bc8bd90f-e445-57b2-a394-240102ca8fb3.json
deleted file mode 100644
index 249b71ab..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bc8bd90f-e445-57b2-a394-240102ca8fb3.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Najock, Dietmar"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 487 KB)"
-    ],
-    "Language": [
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0342",
-    "MetadataAccess": [
-        "oai:ota:oucs:0342"
-    ],
-    "PublicationYear": [
-        "86-103"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Martial"
-    ],
-    "fulltext": "oai:ota:oucs:0342;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0342.xml;Epigrammata / Martial;Epigrams;Martialis Epigrammata;Martial;86-103;text_and_corpus_linguistics;Latin poetry -- 1st century;lat;Oxford Text Archive, University of Oxford;Najock, Dietmar;(1 file : ca. 487 KB);Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bc8bd90f-e445-57b2-a394-240102ca8fb3",
-    "oai_identifier": [
-        "oai:ota:oucs:0342"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Latin poetry -- st century"
-        }
-    ],
-    "title": [
-        "Epigrammata / Martial",
-        "Epigrams",
-        "Martialis Epigrammata"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0342.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bca92ea4-7cb3-5ff8-8c59-82cedfdb356e.json b/oaitestdata/clarin-oai_dc/SET_1/json/bca92ea4-7cb3-5ff8-8c59-82cedfdb356e.json
deleted file mode 100644
index 69217e6c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bca92ea4-7cb3-5ff8-8c59-82cedfdb356e.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish",
-        "French"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/54",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/54"
-    ],
-    "PID": "http://hdl.handle.net/10794/54",
-    "PublicationTimestamp": "2015-04-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/54;2017-10-31T12:24:32Z;hdl_10794_1;hdl_10794_2;ASPAC \u2013 Swedish-French (2017-10-16);ASPAC \u2013 svenska-franska (2017-10-16);n/a, n/a;ASPAC;Parallel;Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.;Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat.;2015-04-16;corpus;http://hdl.handle.net/10794/54;swe;fra;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/octet-stream;application/gzip;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/aspacsvfr",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bca92ea4-7cb3-5ff8-8c59-82cedfdb356e",
-    "notes": [
-        "Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.",
-        "Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/54"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ASPAC"
-        },
-        {
-            "name": "Parallel"
-        }
-    ],
-    "title": [
-        "ASPAC \u2013 Swedish-French (2017-10-16)",
-        "ASPAC \u2013 svenska-franska (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bccb2ab2-0677-53b3-8015-4990e0e42fc8.json b/oaitestdata/clarin-oai_dc/SET_1/json/bccb2ab2-0677-53b3-8015-4990e0e42fc8.json
deleted file mode 100644
index 0fda7dbd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bccb2ab2-0677-53b3-8015-4990e0e42fc8.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "University of Colorado"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-680",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-680"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-680",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Colorado"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Code of conduct"
-    ],
-    "SpatialCoverage": [
-        "United States"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-680;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Wichita corpus;Documentation of the Wichita project (DoBeS project);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-680;Code of conduct;downloadable_files_count: 0;United States;University of Colorado;http://corpus1.mpi.nl/ds/imdi_browser/?openpath=MPI84029%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bccb2ab2-0677-53b3-8015-4990e0e42fc8",
-    "notes": [
-        "Documentation of the Wichita project (DoBeS project)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-680"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Wichita corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bccd5368-efff-572c-bce8-cfbd07e47b0a.json b/oaitestdata/clarin-oai_dc/SET_1/json/bccd5368-efff-572c-bce8-cfbd07e47b0a.json
deleted file mode 100644
index 9df0f0f5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bccd5368-efff-572c-bce8-cfbd07e47b0a.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "Contributor": [
-        "Freixa, Judit"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Catalan",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1177",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1177"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1177",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1177;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Cercador NEOROM;Freixa, Judit;Search engine for the neologisms database of the NEOROM network. The network collects neologisms used in the press written in Romance languages from 2005 onwards.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1177;cat;spa;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra;http://obneo.iula.upf.edu/bneorom/index.php",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bccd5368-efff-572c-bce8-cfbd07e47b0a",
-    "notes": [
-        "Search engine for the neologisms database of the NEOROM network. The network collects neologisms used in the press written in Romance languages from 2005 onwards."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1177"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Cercador NEOROM"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bcd2ba1a-9d6d-5bae-baee-700cbfc1cd38.json b/oaitestdata/clarin-oai_dc/SET_1/json/bcd2ba1a-9d6d-5bae-baee-700cbfc1cd38.json
deleted file mode 100644
index c974830d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bcd2ba1a-9d6d-5bae-baee-700cbfc1cd38.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4337",
-    "MetadataAccess": [
-        "oai:ota:oucs:4337"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Defoe, Daniel, 1661?-1731."
-    ],
-    "fulltext": "oai:ota:oucs:4337;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4337.xml;The validity of the renunciations of former powers, enquired into, and the present renuncniation of the Duke of Anjou, impartially considered. With a preface, relating to the guarantee for the Protestant succession;Defoe, Daniel, 1661?-1731.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bcd2ba1a-9d6d-5bae-baee-700cbfc1cd38",
-    "oai_identifier": [
-        "oai:ota:oucs:4337"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The validity of the renunciations of former powers, enquired into, and the present renuncniation of the Duke of Anjou, impartially considered. With a preface, relating to the guarantee for the Protestant succession"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4337.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bcd2cf50-1a8b-5022-b251-5a43e9168986.json b/oaitestdata/clarin-oai_dc/SET_1/json/bcd2cf50-1a8b-5022-b251-5a43e9168986.json
deleted file mode 100644
index 1fc739e5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bcd2cf50-1a8b-5022-b251-5a43e9168986.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Frisian Academy"
-    ],
-    "Contributor": [
-        "Siebinga, Sjoerd"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-879",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-879"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-879",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Frisian Academy"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-879;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Corpus nineteenth-century Frisian;Siebinga, Sjoerd;About a million words have been scanned and corrected. In addition, some hand-written manuscripts have been typed into the computer.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-879;downloadable_files_count: 0;Netherlands (the);Frisian Academy;http://www.fa.knaw.nl/fa/3departments-and-disciplines/department-of-linguistics/taalkorpora_en_/frisian-language-corpus",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bcd2cf50-1a8b-5022-b251-5a43e9168986",
-    "notes": [
-        "About a million words have been scanned and corrected. In addition, some hand-written manuscripts have been typed into the computer."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-879"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus nineteenth-century Frisian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bce2cbf2-de5a-56ac-95cd-19fd87a09248.json b/oaitestdata/clarin-oai_dc/SET_1/json/bce2cbf2-de5a-56ac-95cd-19fd87a09248.json
deleted file mode 100644
index b8b3a985..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bce2cbf2-de5a-56ac-95cd-19fd87a09248.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Borin, Lars"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-216",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-216"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-216",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Sweden"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-216;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Syntag;Borin, Lars;appr. 100 kW, functional/dependency (one token per line plus its POS and syntactic annotation[s]);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-216;swe;downloadable_files_count: 0;Sweden;http://spraakbanken.gu.se/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bce2cbf2-de5a-56ac-95cd-19fd87a09248",
-    "notes": [
-        "appr. 100 kW, functional/dependency (one token per line plus its POS and syntactic annotation[s])"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-216"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Syntag"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bd04e9c6-85b7-5cde-92e6-bb35f8be5e83.json b/oaitestdata/clarin-oai_dc/SET_1/json/bd04e9c6-85b7-5cde-92e6-bb35f8be5e83.json
deleted file mode 100644
index ad78e7ce..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bd04e9c6-85b7-5cde-92e6-bb35f8be5e83.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Wroclaw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 30",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/316",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/316"
-    ],
-    "PID": "http://hdl.handle.net/11321/316",
-    "PublicationTimestamp": "2016-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroclaw University of Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "IS PAS corpora license",
-        "http://clarin-pl.eu/en/licenses/is-pas-corpora-license/",
-        "CC"
-    ],
-    "author": [
-        "Damurski, Lukasz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/316;2016-07-30T04:58:40Z;hdl_11321_3;hdl_11321_4;EU Territorial Policy Documents 2007-2016 (partitioned);Damurski, Lukasz;EU;territorial policy;urban planning;Corpus of the key documents of the EU territorial policy 2007-2016.;2016-07-30;corpus;http://hdl.handle.net/11321/316;eng;IS PAS corpora license;http://clarin-pl.eu/en/licenses/is-pas-corpora-license/;CC;text/plain; charset=utf-8;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;downloadable_files_count: 30;Wroclaw University of Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bd04e9c6-85b7-5cde-92e6-bb35f8be5e83",
-    "notes": [
-        "Corpus of the key documents of the EU territorial policy 2007-2016."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/316"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "EU"
-        },
-        {
-            "name": "territorial policy"
-        },
-        {
-            "name": "urban planning"
-        }
-    ],
-    "title": [
-        "EU Territorial Policy Documents 2007-2016 (partitioned)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bd28fd7e-613d-58eb-8a4f-63e6d9c8ef02.json b/oaitestdata/clarin-oai_dc/SET_1/json/bd28fd7e-613d-58eb-8a4f-63e6d9c8ef02.json
deleted file mode 100644
index e7bf1606..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bd28fd7e-613d-58eb-8a4f-63e6d9c8ef02.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5138",
-    "MetadataAccess": [
-        "oai:ota:oucs:5138"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Sheridan, Frances Chamberlaine, 1724-1766."
-    ],
-    "fulltext": "oai:ota:oucs:5138;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5138.xml;The history of Nourjahad: By the editor of Sidney Bidulph.;Sheridan, Frances Chamberlaine, 1724-1766.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bd28fd7e-613d-58eb-8a4f-63e6d9c8ef02",
-    "oai_identifier": [
-        "oai:ota:oucs:5138"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The history of Nourjahad: By the editor of Sidney Bidulph."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5138.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bd2b29d2-a725-50d2-9b3e-b4866d4d5e47.json b/oaitestdata/clarin-oai_dc/SET_1/json/bd2b29d2-a725-50d2-9b3e-b4866d4d5e47.json
deleted file mode 100644
index 5ed32f09..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bd2b29d2-a725-50d2-9b3e-b4866d4d5e47.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Informatics, Masaryk University"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2427",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2427"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2427",
-    "PublicationTimestamp": "2017-09-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Faculty of Informatics, Masaryk University"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Public Domain Mark (PD)",
-        "http://creativecommons.org/publicdomain/mark/1.0/",
-        "PUB"
-    ],
-    "author": [
-        "Nev\u011b\u0159ilov\u00e1, Zuzana"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2427;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Czech Multiword Expressions;Nev\u011b\u0159ilov\u00e1, Zuzana;multiword expressions;The dataset contains 4731 frozen continuous Czech multiword expressions. Inflectional word forms are generated for those MWEs where applicable. In total, the dataset contains 24,807 MWE forms.;2017-09-30;lexicalConceptualResource;http://hdl.handle.net/11234/1-2427;ces;Public Domain Mark (PD);http://creativecommons.org/publicdomain/mark/1.0/;PUB;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 1;Faculty of Informatics, Masaryk University;https://nlp.fi.muni.cz/projekty/mwes/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bd2b29d2-a725-50d2-9b3e-b4866d4d5e47",
-    "notes": [
-        "The dataset contains 4731 frozen continuous Czech multiword expressions. Inflectional word forms are generated for those MWEs where applicable. In total, the dataset contains 24,807 MWE forms."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2427"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "multiword expressions"
-        }
-    ],
-    "title": [
-        "Czech Multiword Expressions"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bd37794c-bee0-565d-8c72-cb85f0f59af9.json b/oaitestdata/clarin-oai_dc/SET_1/json/bd37794c-bee0-565d-8c72-cb85f0f59af9.json
deleted file mode 100644
index c44404e1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bd37794c-bee0-565d-8c72-cb85f0f59af9.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5372",
-    "MetadataAccess": [
-        "oai:ota:oucs:5372"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Goldsmith, Oliver, 1730?-1774."
-    ],
-    "fulltext": "oai:ota:oucs:5372;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5372.xml;A prospect of society;Traveller;Goldsmith, Oliver, 1730?-1774.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bd37794c-bee0-565d-8c72-cb85f0f59af9",
-    "oai_identifier": [
-        "oai:ota:oucs:5372"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A prospect of society",
-        "Traveller"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5372.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bd57b607-af73-5c42-acbb-5b72903f23b3.json b/oaitestdata/clarin-oai_dc/SET_1/json/bd57b607-af73-5c42-acbb-5b72903f23b3.json
deleted file mode 100644
index 619e62db..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bd57b607-af73-5c42-acbb-5b72903f23b3.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/pdf"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-728",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-728"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-728",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "United States"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-728;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Narrangansett dictionary;The Narrangansett corpus contains a cultural linguistic dictionary and grammatical information on the Narrangansett language, an extinct language of the USA.;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-728;application/pdf;downloadable_files_count: 0;United States;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI239094%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bd57b607-af73-5c42-acbb-5b72903f23b3",
-    "notes": [
-        "The Narrangansett corpus contains a cultural linguistic dictionary and grammatical information on the Narrangansett language, an extinct language of the USA."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-728"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Narrangansett dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bd5bef2a-d898-5764-be42-bdba283aadef.json b/oaitestdata/clarin-oai_dc/SET_1/json/bd5bef2a-d898-5764-be42-bdba283aadef.json
deleted file mode 100644
index 2915dd86..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bd5bef2a-d898-5764-be42-bdba283aadef.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish",
-        "Portuguese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/65",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/65"
-    ],
-    "PID": "http://hdl.handle.net/10794/65",
-    "PublicationTimestamp": "2015-04-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/65;2017-10-31T15:19:53Z;hdl_10794_1;hdl_10794_2;ASPAC \u2013 Swedish-Portuguese (2017-10-16);ASPAC \u2013 svenska-portugisiska (2017-10-16);n/a, n/a;ASPAC;Parallel;Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.;Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat.;2015-04-16;corpus;http://hdl.handle.net/10794/65;swe;por;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/octet-stream;application/gzip;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/aspacsvpt",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bd5bef2a-d898-5764-be42-bdba283aadef",
-    "notes": [
-        "Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.",
-        "Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/65"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ASPAC"
-        },
-        {
-            "name": "Parallel"
-        }
-    ],
-    "title": [
-        "ASPAC \u2013 Swedish-Portuguese (2017-10-16)",
-        "ASPAC \u2013 svenska-portugisiska (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bd61e47b-6049-503d-acfa-722f589bcd75.json b/oaitestdata/clarin-oai_dc/SET_1/json/bd61e47b-6049-503d-acfa-722f589bcd75.json
deleted file mode 100644
index 987f2995..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bd61e47b-6049-503d-acfa-722f589bcd75.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5721",
-    "MetadataAccess": [
-        "oai:ota:oucs:5721"
-    ],
-    "PublicationTimestamp": "1623-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1623"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Shakespeare, William, 1564-1616"
-    ],
-    "fulltext": "oai:ota:oucs:5721;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/5721.xml;THE TRAGEDIE OF ROMEO and IVLIET;Shakespeare, William, 1564-1616;not after: 1623;text_and_corpus_linguistics;Plays -- England -- 16th century;Plays -- England -- 17th century;Comedies -- England -- 16th century;Comedies -- England -- 17th century;Tragedies -- England -- 16th century;Tragedies -- England -- 17th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bd61e47b-6049-503d-acfa-722f589bcd75",
-    "oai_identifier": [
-        "oai:ota:oucs:5721"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        },
-        {
-            "name": "Comedies -- England -- th century"
-        },
-        {
-            "name": "Comedies -- England -- th century"
-        },
-        {
-            "name": "Tragedies -- England -- th century"
-        },
-        {
-            "name": "Tragedies -- England -- th century"
-        }
-    ],
-    "title": [
-        "THE TRAGEDIE OF ROMEO and IVLIET"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5721.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bd6b4a0b-c0ad-59fa-aa83-b52209e36667.json b/oaitestdata/clarin-oai_dc/SET_1/json/bd6b4a0b-c0ad-59fa-aa83-b52209e36667.json
deleted file mode 100644
index f8b6925f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bd6b4a0b-c0ad-59fa-aa83-b52209e36667.json
+++ /dev/null
@@ -1,89 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2364",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2364"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2364",
-    "PublicationTimestamp": "2017-08-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-2898"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Straka, Milan",
-        "Strakov\u00e1, Jana"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2364;2018-11-23T13:50:22Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Universal Dependencies 2.0 Models for UDPipe (2017-08-01);Straka, Milan;Strakov\u00e1, Jana;tokenizer;POS tagger;lemmatization;tagger;parser;dependency parser;Tokenizer, POS Tagger, Lemmatizer and Parser models for all 50 languages of Universal Depenencies 2.0 Treebanks, created solely using UD 2.0 data (http://hdl.handle.net/11234/1-1983). The model documentation including performance can be found at http://ufal.mff.cuni.cz/udpipe/users-manual#universal_dependencies_20_models .\r\n\r\nTo use these models, you need UDPipe binary version at least 1.2, which you can download from http://ufal.mff.cuni.cz/udpipe .\r\n\r\nIn addition to models itself, all additional data and value of hyperparameters used for training are available in the second archive, allowing reproducible training.;2017-08-01;toolService;http://hdl.handle.net/11234/1-2364;eng;http://hdl.handle.net/11234/1-2898;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/udpipe",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bd6b4a0b-c0ad-59fa-aa83-b52209e36667",
-    "notes": [
-        "Tokenizer, POS Tagger, Lemmatizer and Parser models for all 50 languages of Universal Depenencies 2.0 Treebanks, created solely using UD 2.0 data (http://hdl.handle.net/11234/1-1983). The model documentation including performance can be found at http://ufal.mff.cuni.cz/udpipe/users-manual#universal_dependencies_20_models .\r\n\r\nTo use these models, you need UDPipe binary version at least 1.2, which you can download from http://ufal.mff.cuni.cz/udpipe .\r\n\r\nIn addition to models itself, all additional data and value of hyperparameters used for training are available in the second archive, allowing reproducible training."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2364"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "tokenizer"
-        },
-        {
-            "name": "POS tagger"
-        },
-        {
-            "name": "lemmatization"
-        },
-        {
-            "name": "tagger"
-        },
-        {
-            "name": "parser"
-        },
-        {
-            "name": "dependency parser"
-        }
-    ],
-    "title": [
-        "Universal Dependencies 2.0 Models for UDPipe (2017-08-01)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bd6b6a26-50ff-5485-bf08-6355139d5b99.json b/oaitestdata/clarin-oai_dc/SET_1/json/bd6b6a26-50ff-5485-bf08-6355139d5b99.json
deleted file mode 100644
index e6018c08..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bd6b6a26-50ff-5485-bf08-6355139d5b99.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4274",
-    "MetadataAccess": [
-        "oai:ota:oucs:4274"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dudley, H. Bate, Sir (Henry Bate), 1745-1824."
-    ],
-    "fulltext": "oai:ota:oucs:4274;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4274.xml;The rival candidates: a comic opera in two acts; as it is now performing at the Theatre Royal in Drury-Lane. By the Rev. Henry Bate.;Dudley, H. Bate, Sir (Henry Bate), 1745-1824.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bd6b6a26-50ff-5485-bf08-6355139d5b99",
-    "oai_identifier": [
-        "oai:ota:oucs:4274"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The rival candidates: a comic opera in two acts; as it is now performing at the Theatre Royal in Drury-Lane. By the Rev. Henry Bate."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4274.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bd70e422-29c5-55a5-bbdc-dd2a553b227d.json b/oaitestdata/clarin-oai_dc/SET_1/json/bd70e422-29c5-55a5-bbdc-dd2a553b227d.json
deleted file mode 100644
index 61d9015e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bd70e422-29c5-55a5-bbdc-dd2a553b227d.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Freie Universit\u00e4t Berlin"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-627",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-627"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-627",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Freie Universit\u00e4t Berlin"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Code of conduct"
-    ],
-    "SpatialCoverage": [
-        "Brazil"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-627;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Awet\u00ed corpus;Documentation of the Awet\u00ed project (DoBeS project);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-627;Code of conduct;downloadable_files_count: 0;Brazil;Freie Universit\u00e4t Berlin;http://corpus1.mpi.nl/ds/imdi_browser/?openpath=MPI77916%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bd70e422-29c5-55a5-bbdc-dd2a553b227d",
-    "notes": [
-        "Documentation of the Awet\u00ed project (DoBeS project)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-627"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Awet\u00ed corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bd7ede8b-a19e-540a-8ef6-b348199a2cb3.json b/oaitestdata/clarin-oai_dc/SET_1/json/bd7ede8b-a19e-540a-8ef6-b348199a2cb3.json
deleted file mode 100644
index e5dd34aa..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bd7ede8b-a19e-540a-8ef6-b348199a2cb3.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4273",
-    "MetadataAccess": [
-        "oai:ota:oucs:4273"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dudley, H. Bate, Sir (Henry Bate), 1745-1824."
-    ],
-    "fulltext": "oai:ota:oucs:4273;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4273.xml;The flitch of bacon; a comic opera: in two acts: as it is performed at the Theatre-Royal in the Hay-Market. By the Rev. Hen. Bate.;Dudley, H. Bate, Sir (Henry Bate), 1745-1824.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bd7ede8b-a19e-540a-8ef6-b348199a2cb3",
-    "oai_identifier": [
-        "oai:ota:oucs:4273"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The flitch of bacon; a comic opera: in two acts: as it is performed at the Theatre-Royal in the Hay-Market. By the Rev. Hen. Bate."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4273.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bd8f57b9-f8ba-53f4-845d-190510996537.json b/oaitestdata/clarin-oai_dc/SET_1/json/bd8f57b9-f8ba-53f4-845d-190510996537.json
deleted file mode 100644
index 5b9332d1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bd8f57b9-f8ba-53f4-845d-190510996537.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1402",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1402"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1402",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1402;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;freeling;Web service consisting of the Freeling open source language analysis tool suite.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1402;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bd8f57b9-f8ba-53f4-845d-190510996537",
-    "notes": [
-        "Web service consisting of the Freeling open source language analysis tool suite."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1402"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "freeling"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bdaab309-ad89-5233-b60a-bd735973978b.json b/oaitestdata/clarin-oai_dc/SET_1/json/bdaab309-ad89-5233-b60a-bd735973978b.json
deleted file mode 100644
index 395216d6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bdaab309-ad89-5233-b60a-bd735973978b.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Fryske Akademy"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/pdf"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1958",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1958"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1958",
-    "PublicationTimestamp": "2017-02-03T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Fryske Akademy"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU General Public License 2 or later (GPL-2.0)",
-        "http://opensource.org/licenses/GPL-2.0",
-        "PUB"
-    ],
-    "author": [
-        "van de Velde, Hans",
-        "Heeringa, Wilbert"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1958;2017-04-10T09:19:08Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Visible Vowels;van de Velde, Hans;Heeringa, Wilbert;Phonetics;language variation;dialect variation;This program enables the user to plot vowels in the F1/F2 space for multiple points in the vowel interval, e.g. at 20%, 50% and 80%.;2017-02-03;toolService;http://hdl.handle.net/11372/LRT-1958;GNU General Public License 2 or later (GPL-2.0);http://opensource.org/licenses/GPL-2.0;PUB;application/pdf;text/plain; charset=utf-8;downloadable_files_count: 1;Fryske Akademy;https://fryske-akademy.shinyapps.io/visvow1/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bdaab309-ad89-5233-b60a-bd735973978b",
-    "notes": [
-        "This program enables the user to plot vowels in the F1/F2 space for multiple points in the vowel interval, e.g. at 20%, 50% and 80%."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1958"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Phonetics"
-        },
-        {
-            "name": "language variation"
-        },
-        {
-            "name": "dialect variation"
-        }
-    ],
-    "title": [
-        "Visible Vowels"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bdb57102-20b9-5099-9fa0-ae755c1c3ec0.json b/oaitestdata/clarin-oai_dc/SET_1/json/bdb57102-20b9-5099-9fa0-ae755c1c3ec0.json
deleted file mode 100644
index 8f50de7f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bdb57102-20b9-5099-9fa0-ae755c1c3ec0.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contributor": [
-        "Borin, Lars"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-513",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-513"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-513",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Sweden"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-513;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;S\u00f6derwall/S\u00f6derwall supplement;Borin, Lars;appr. 43,000 entries (appr. 25,000 distinct entries), various (XML version underway);2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-513;downloadable_files_count: 0;Sweden;http://spraakbanken.gu.se/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bdb57102-20b9-5099-9fa0-ae755c1c3ec0",
-    "notes": [
-        "appr. 43,000 entries (appr. 25,000 distinct entries), various (XML version underway)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-513"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "S\u00f6derwall/S\u00f6derwall supplement"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bdba2b63-26d6-51d0-959d-833a6ccde157.json b/oaitestdata/clarin-oai_dc/SET_1/json/bdba2b63-26d6-51d0-959d-833a6ccde157.json
deleted file mode 100644
index 2752e981..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bdba2b63-26d6-51d0-959d-833a6ccde157.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "Contributor": [
-        "J\u00e4nsch, Klaus",
-        "Draxler, Christoph"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-307",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-307"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-307",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-307;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;SpeechRecorder;Draxler, Christoph;J\u00e4nsch, Klaus;SpeechRecorder is a platform independent multi-channel audio recording software. Its main features are a configurable recording script, Unicode text, image and audio prompts, hardware independence and localized language interfaces.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-307;downloadable_files_count: 0;Germany;http://www.phonetik.uni-muenchen.de/forschung/Bas/software/speechrecorder/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bdba2b63-26d6-51d0-959d-833a6ccde157",
-    "notes": [
-        "SpeechRecorder is a platform independent multi-channel audio recording software. Its main features are a configurable recording script, Unicode text, image and audio prompts, hardware independence and localized language interfaces."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-307"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "SpeechRecorder"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bdbee914-79eb-512f-9a9c-16c94be285ce.json b/oaitestdata/clarin-oai_dc/SET_1/json/bdbee914-79eb-512f-9a9c-16c94be285ce.json
deleted file mode 100644
index 29aa15e4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bdbee914-79eb-512f-9a9c-16c94be285ce.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5583",
-    "MetadataAccess": [
-        "oai:ota:oucs:5583"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Apothecary."
-    ],
-    "fulltext": "oai:ota:oucs:5583;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5583.xml;Reasons: why the apothecary may be suppos'd to understand the administration of medicines in the cure of diseases, as well as the physician. In a letter from an apothecary to a physician;Apothecary.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bdbee914-79eb-512f-9a9c-16c94be285ce",
-    "oai_identifier": [
-        "oai:ota:oucs:5583"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Reasons: why the apothecary may be suppos'd to understand the administration of medicines in the cure of diseases, as well as the physician. In a letter from an apothecary to a physician"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5583.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bdc48966-6fc1-53fc-9d3d-ef1b4d0ed4ba.json b/oaitestdata/clarin-oai_dc/SET_1/json/bdc48966-6fc1-53fc-9d3d-ef1b4d0ed4ba.json
deleted file mode 100644
index dfae952e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bdc48966-6fc1-53fc-9d3d-ef1b4d0ed4ba.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48F3-0",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48F3-0"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-48F3-0",
-    "PublicationTimestamp": "2009-11-02T09:51:39Z",
-    "PublicationYear": [
-        "2009"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Artistic License (Perl) 1.0",
-        "http://opensource.org/licenses/Artistic-Perl-1.0"
-    ],
-    "author": [
-        "Pajas, Petr"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48F3-0;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;XSH;Pajas, Petr;XML processing;command-line;XSH is a powerfull command-line tool for querying, processing and editing XML documents. It features a shell-like interface with auto-completion for comfortable interactive work, but can be as well used for off-line (batch) processing of XML data.;2009-11-02T09:51:39Z;toolService;http://hdl.handle.net/11858/00-097C-0000-0001-48F3-0;Artistic License (Perl) 1.0;http://opensource.org/licenses/Artistic-Perl-1.0;text/plain; charset=utf-8;downloadable_files_count: 0;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://xsh.sourceforge.net",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bdc48966-6fc1-53fc-9d3d-ef1b4d0ed4ba",
-    "notes": [
-        "XSH is a powerfull command-line tool for querying, processing and editing XML documents. It features a shell-like interface with auto-completion for comfortable interactive work, but can be as well used for off-line (batch) processing of XML data."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48F3-0"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "XML processing"
-        },
-        {
-            "name": "command-line"
-        }
-    ],
-    "title": [
-        "XSH"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bdd966d9-43e0-59c3-9ef5-2764174a16be.json b/oaitestdata/clarin-oai_dc/SET_1/json/bdd966d9-43e0-59c3-9ef5-2764174a16be.json
deleted file mode 100644
index 1a83f122..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bdd966d9-43e0-59c3-9ef5-2764174a16be.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "NLX-Natural Language and Speech Group, University of Lisbon"
-    ],
-    "Contributor": [
-        "Branco, Ant\u00f3nio",
-        "Martins, Pedro"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Portuguese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1224",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1224"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1224",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "NLX-Natural Language and Speech Group, University of Lisbon"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Portugal"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1224;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LX-Inflector;Branco, Ant\u00f3nio;Martins, Pedro;Fully fledged automatic nominal lemmatizer for Portuguese. It takes as input: * A Portuguese nominal form A forms of a noun or an adjective, including adjectival forms of past participles, and * Inflectional feature values Intended values of inflectional features of Gender and Number for the output. It delivers: * Inflectional features The input form is returned with the corresponding values for the inflectional features of Gender and Number associated to it; * Lemmata The lemmata (singular and masculine forms when available) possibly corresponding to the input form; * Inflected forms The inflected forms (when available) of each lemmata in accordance with the values for inflectional features entered. LX-Inflector processes simple forms, both lexically known and unknown ones. It also processes compound forms. It handles nominal forms with prefixes as well. In sum, it lemmatizes and inflects: * Prefixed forms Nominal expressions integrating one or more prefixes, e.g. \"anti-constitucional\", \"super-mega-fixe\", etc; * Compounds Nominal expressions integrating more than one form, e.g. \"trabalhador-estudante\", \"surdo-mudo\", \"lan\u00e7a-m\u00edsseis\", etc; * Neologisms;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1224;por;downloadable_files_count: 0;Portugal;NLX-Natural Language and Speech Group, University of Lisbon;http://lxinflector.di.fc.ul.pt",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bdd966d9-43e0-59c3-9ef5-2764174a16be",
-    "notes": [
-        "Fully fledged automatic nominal lemmatizer for Portuguese. It takes as input: * A Portuguese nominal form A forms of a noun or an adjective, including adjectival forms of past participles, and * Inflectional feature values Intended values of inflectional features of Gender and Number for the output. It delivers: * Inflectional features The input form is returned with the corresponding values for the inflectional features of Gender and Number associated to it; * Lemmata The lemmata (singular and masculine forms when available) possibly corresponding to the input form; * Inflected forms The inflected forms (when available) of each lemmata in accordance with the values for inflectional features entered. LX-Inflector processes simple forms, both lexically known and unknown ones. It also processes compound forms. It handles nominal forms with prefixes as well. In sum, it lemmatizes and inflects: * Prefixed forms Nominal expressions integrating one or more prefixes, e.g. \"anti-constitucional\", \"super-mega-fixe\", etc; * Compounds Nominal expressions integrating more than one form, e.g. \"trabalhador-estudante\", \"surdo-mudo\", \"lan\u00e7a-m\u00edsseis\", etc; * Neologisms"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1224"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LX-Inflector"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bdda72cb-d506-5bb9-96ec-941c81ba2945.json b/oaitestdata/clarin-oai_dc/SET_1/json/bdda72cb-d506-5bb9-96ec-941c81ba2945.json
deleted file mode 100644
index cf9f1592..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bdda72cb-d506-5bb9-96ec-941c81ba2945.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "University of West Bohemia, Department of Cybernetics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "video/mp4",
-        "downloadable_files_count: 17",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2545",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2545"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2545",
-    "PublicationTimestamp": "2017-12-14T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "University of West Bohemia, Department of Cybernetics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Hr\u00faz, Marek"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2545;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Czech Television News Broadcasting Faces;Hr\u00faz, Marek;video;czech news broadcasting;faces;face tracking;The corpus contains video files of Czech Television News Broadcasts and JSON files with annotations of faces that appear in the broadcasts. The annotations are composed of frames in which a face is seen, name of the person whose face is seen, gender of the person (male/female), and the image region containing the face. The intended use of the corpus is to train models of faces for face detection, face identification, face verification, and face tracking. For convinience two different JSON files are provided. They contain the same data, but in different arrangements. One file has the identity of the person on the top, the other has the object ID on the top, where the object is a facetrack. A demo python skript is available for showing how to access the data.;2017-12-14;corpus;http://hdl.handle.net/11234/1-2545;ces;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/zip;application/octet-stream;video/mp4;video/mp4;video/mp4;video/mp4;video/mp4;video/mp4;video/mp4;video/mp4;video/mp4;video/mp4;video/mp4;video/mp4;video/mp4;video/mp4;video/mp4;text/plain; charset=utf-8;downloadable_files_count: 17;University of West Bohemia, Department of Cybernetics",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bdda72cb-d506-5bb9-96ec-941c81ba2945",
-    "notes": [
-        "The corpus contains video files of Czech Television News Broadcasts and JSON files with annotations of faces that appear in the broadcasts. The annotations are composed of frames in which a face is seen, name of the person whose face is seen, gender of the person (male/female), and the image region containing the face. The intended use of the corpus is to train models of faces for face detection, face identification, face verification, and face tracking. For convinience two different JSON files are provided. They contain the same data, but in different arrangements. One file has the identity of the person on the top, the other has the object ID on the top, where the object is a facetrack. A demo python skript is available for showing how to access the data."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2545"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "video"
-        },
-        {
-            "name": "czech news broadcasting"
-        },
-        {
-            "name": "faces"
-        },
-        {
-            "name": "face tracking"
-        }
-    ],
-    "title": [
-        "Czech Television News Broadcasting Faces"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bddee298-776a-5e13-b8ae-87ce73137ac2.json b/oaitestdata/clarin-oai_dc/SET_1/json/bddee298-776a-5e13-b8ae-87ce73137ac2.json
deleted file mode 100644
index d350153f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bddee298-776a-5e13-b8ae-87ce73137ac2.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "SentiOne"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/634",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/634"
-    ],
-    "PID": "http://hdl.handle.net/11321/634",
-    "PublicationTimestamp": "2019-03-20T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "SentiOne"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "Walentynowicz, Wiktor"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/634;2019-03-21T09:40:18Z;hdl_11321_3;hdl_11321_4;Tagger SentiOne - version 2;Walentynowicz, Wiktor;part of speech tagging;This is the second version of the morpho-syntactic tagger for the Polish language, adapted to UGC-processing. It has been enriched with some heuristics to improve its accuracy and a tokenizer.;2019-03-20;toolService;http://hdl.handle.net/11321/634;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;application/gzip;downloadable_files_count: 1;SentiOne;https://sentione.com/knowledge/eu-research-project",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bddee298-776a-5e13-b8ae-87ce73137ac2",
-    "notes": [
-        "This is the second version of the morpho-syntactic tagger for the Polish language, adapted to UGC-processing. It has been enriched with some heuristics to improve its accuracy and a tokenizer."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/634"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "part speech tagging"
-        }
-    ],
-    "title": [
-        "Tagger SentiOne - version 2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bde08827-8195-5600-932b-e06b168c3b78.json b/oaitestdata/clarin-oai_dc/SET_1/json/bde08827-8195-5600-932b-e06b168c3b78.json
deleted file mode 100644
index 0e3a36f5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bde08827-8195-5600-932b-e06b168c3b78.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Linguistic Modeling Department, IPP, Bulgarian Academy of Sciences"
-    ],
-    "Contributor": [
-        "Simov, Kiril"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1242",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1242"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1242",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Linguistic Modeling Department, IPP, Bulgarian Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Bulgaria"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Simov, Alex",
-        "Simov, Kiril",
-        "Osenova, Petya"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1242;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;BulTreeBank Morphosyntactic Disambiguator;Simov, Kiril;Osenova, Petya;Simov, Alex;Simov, Kiril;This is a hybrid system: rules, neural network, rules. First \nrules for the sure cases are applied, then a neural network \ndisambiguator is applied, then rules for repairing of the most \nfrequent errors of the neural network. The rules are implemented \nas constraints in CLaRK System. The neural network is additional \nmodule implemented in Java. It is called CLaRK. It requires the \nmorphologically annotated input.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1242;downloadable_files_count: 0;Bulgaria;Linguistic Modeling Department, IPP, Bulgarian Academy of Sciences",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bde08827-8195-5600-932b-e06b168c3b78",
-    "notes": [
-        "This is a hybrid system: rules, neural network, rules. First \nrules for the sure cases are applied, then a neural network \ndisambiguator is applied, then rules for repairing of the most \nfrequent errors of the neural network. The rules are implemented \nas constraints in CLaRK System. The neural network is additional \nmodule implemented in Java. It is called CLaRK. It requires the \nmorphologically annotated input."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1242"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "BulTreeBank Morphosyntactic Disambiguator"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bdfff33e-4521-57e2-b06d-2b540b9f9cb0.json b/oaitestdata/clarin-oai_dc/SET_1/json/bdfff33e-4521-57e2-b06d-2b540b9f9cb0.json
deleted file mode 100644
index 1ea10f69..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bdfff33e-4521-57e2-b06d-2b540b9f9cb0.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 40 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0032",
-    "MetadataAccess": [
-        "oai:ota:oucs:0032"
-    ],
-    "PublicationTimestamp": "1742-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1742"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Collins, William, 1721-1759"
-    ],
-    "fulltext": "oai:ota:oucs:0032;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0032.xml;Poems;Odes and Eclogues;Collins, William, 1721-1759;1742;text_and_corpus_linguistics;Poems -- England -- 18th century;eng;Oxford Text Archive, University of Oxford;(1 file : ca. 40 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bdfff33e-4521-57e2-b06d-2b540b9f9cb0",
-    "oai_identifier": [
-        "oai:ota:oucs:0032"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- England -- th century"
-        }
-    ],
-    "title": [
-        "Poems",
-        "Odes and Eclogues"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0032.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/be04009b-95ae-5665-bc71-66a5d55abcd7.json b/oaitestdata/clarin-oai_dc/SET_1/json/be04009b-95ae-5665-bc71-66a5d55abcd7.json
deleted file mode 100644
index 73984cf7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/be04009b-95ae-5665-bc71-66a5d55abcd7.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4892",
-    "MetadataAccess": [
-        "oai:ota:oucs:4892"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dibdin, Charles, 1745-1814."
-    ],
-    "fulltext": "oai:ota:oucs:4892;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4892.xml;Hannah Hewit: or, the female Crusoe. Being the history of a woman of uncommon, mental, and personal accomplishments; who, ... was cast away in the Grosvenor East-Indiaman: and became for three years the sole inhabitant of an island, in the South Seas. Supposed to be written by herself. [pt.1];Dibdin, Charles, 1745-1814.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "be04009b-95ae-5665-bc71-66a5d55abcd7",
-    "oai_identifier": [
-        "oai:ota:oucs:4892"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Hannah Hewit: or, the female Crusoe. Being the history of a woman of uncommon, mental, and personal accomplishments; who, ... was cast away in the Grosvenor East-Indiaman: and became for three years the sole inhabitant of an island, in the South Seas. Supposed to be written by herself. [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4892.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/be05e3d4-e9fc-59ac-82a9-6039c494fbf2.json b/oaitestdata/clarin-oai_dc/SET_1/json/be05e3d4-e9fc-59ac-82a9-6039c494fbf2.json
deleted file mode 100644
index 86e6569b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/be05e3d4-e9fc-59ac-82a9-6039c494fbf2.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=86148bb6bc9c11e1a404080027e73ea2c5962da26b75412da3455d8c2e2a8909",
-    "MetadataAccess": [
-        "86148bb6bc9c11e1a404080027e73ea2c5962da26b75412da3455d8c2e2a8909"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "86148bb6bc9c11e1a404080027e73ea2c5962da26b75412da3455d8c2e2a8909;2018-11-15T16:39:25Z;toolService;toolService:tool;UIMA/U-Compare OpenNLP Sentence Detector;This is a UIMA wrapper for the OpenNLP Sentence Detector tool. It splits English text into individual sentences. \n\nThe tool forms part of the in-built library of components provided with the U-Compare platform (see separate META-SHARE record)  for building and evaluating text mining workflows. The U-Compare Workbench (see separate META-SHARE record) provides a graphical drag-and drop interface for the rapid creation of workflows. ;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "be05e3d4-e9fc-59ac-82a9-6039c494fbf2",
-    "notes": [
-        "This is a UIMA wrapper for the OpenNLP Sentence Detector tool. It splits English text into individual sentences. \n\nThe tool forms part of the in-built library of components provided with the U-Compare platform (see separate META-SHARE record)  for building and evaluating text mining workflows. The U-Compare Workbench (see separate META-SHARE record) provides a graphical drag-and drop interface for the rapid creation of workflows. "
-    ],
-    "oai_identifier": [
-        "86148bb6bc9c11e1a404080027e73ea2c5962da26b75412da3455d8c2e2a8909"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "UIMA/U-Compare OpenNLP Sentence Detector"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/be091582-9837-591c-8e62-cbc5949517de.json b/oaitestdata/clarin-oai_dc/SET_1/json/be091582-9837-591c-8e62-cbc5949517de.json
deleted file mode 100644
index 42d964b3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/be091582-9837-591c-8e62-cbc5949517de.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "221 KB"
-    ],
-    "Language": [
-        "Danish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1200",
-    "MetadataAccess": [
-        "oai:ota:oucs:1200"
-    ],
-    "PublicationTimestamp": "1859-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1859"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Memoirs"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Kierkegaard, S\u00c3\u00b8ren, 1813-1855"
-    ],
-    "fulltext": "oai:ota:oucs:1200;2018-03-05T14:20:38Z;http://ota.ox.ac.uk/headers/1200.xml;Synspunktet for min forfatter-virksomhed  / compiled by Alistair McKinnon;Kierkegaard, S\u00c3\u00b8ren, 1813-1855;1859;text_and_corpus_linguistics;Memoirs -- Denmark -- 19th century;dan;Oxford Text Archive, University of Oxford;221 KB;Text;Memoirs;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "be091582-9837-591c-8e62-cbc5949517de",
-    "oai_identifier": [
-        "oai:ota:oucs:1200"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Memoirs -- Denmark -- th century"
-        }
-    ],
-    "title": [
-        "Synspunktet for min forfatter-virksomhed  / compiled by Alistair McKinnon"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1200.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/be28c02a-285b-56a9-929d-435ab5f5a24d.json b/oaitestdata/clarin-oai_dc/SET_1/json/be28c02a-285b-56a9-929d-435ab5f5a24d.json
deleted file mode 100644
index 72eb645e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/be28c02a-285b-56a9-929d-435ab5f5a24d.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=83a09c48e6e111e6a2aa782bcb0741352ba3590e4ae642fc8e31025d267333d6",
-    "MetadataAccess": [
-        "83a09c48e6e111e6a2aa782bcb0741352ba3590e4ae642fc8e31025d267333d6"
-    ],
-    "PublicationTimestamp": "2017-01-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "fulltext": "83a09c48e6e111e6a2aa782bcb0741352ba3590e4ae642fc8e31025d267333d6;2018-11-15T16:40:27Z;corpus;corpus:text;LX-4WAnalogies;The test set described in was used as the basis for the assessment of word embeddings. An example entry in this data set would read: \u00e2\u0080\u0098Berlin Germany Lisbon Portugal\u00e2\u0080\u0099. With these four words relations \u00e2\u0080\u0093 as in this example \u00e2\u0080\u0093 one can test semantic analogies by using any of the possible combinations of three of the four word vectors in one entry and testing whether or not the resulting vector is similar to the (fourth) word vector missing from the combination being tested. In the example above, the completed analogy should read: \u00e2\u0080\u0098Berlin is to Germany as Lisbon is to Portugal\u00e2\u0080\u0099. \nThe test set contains five types of semantic analogy: common capitals and countries, all capitals and countries, currency, cities and states, and family relations. Nine types of syntactic analogy are also represented: adjective to adverb, opposite, comparative, superlative, present participle, nationality (adjective), past tense, plural nouns and plural verbs. The test set contains a total of 8869 semantic and 10675 syntactic entries.\nFor the evaluation of the Portuguese word embeddings, the original English test set was translated into Portuguese by skilled, native Portuguese-speaking\nlanguage experts. The resulting translations, LX-4WAnalogies, and corresponding English terms are available at http://github.com/nlx-group.;2017-01-30",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "be28c02a-285b-56a9-929d-435ab5f5a24d",
-    "notes": [
-        "The test set described in was used as the basis for the assessment of word embeddings. An example entry in this data set would read: \u00e2\u0080\u0098Berlin Germany Lisbon Portugal\u00e2\u0080\u0099. With these four words relations \u00e2\u0080\u0093 as in this example \u00e2\u0080\u0093 one can test semantic analogies by using any of the possible combinations of three of the four word vectors in one entry and testing whether or not the resulting vector is similar to the (fourth) word vector missing from the combination being tested. In the example above, the completed analogy should read: \u00e2\u0080\u0098Berlin is to Germany as Lisbon is to Portugal\u00e2\u0080\u0099. \nThe test set contains five types of semantic analogy: common capitals and countries, all capitals and countries, currency, cities and states, and family relations. Nine types of syntactic analogy are also represented: adjective to adverb, opposite, comparative, superlative, present participle, nationality (adjective), past tense, plural nouns and plural verbs. The test set contains a total of 8869 semantic and 10675 syntactic entries.\nFor the evaluation of the Portuguese word embeddings, the original English test set was translated into Portuguese by skilled, native Portuguese-speaking\nlanguage experts. The resulting translations, LX-4WAnalogies, and corresponding English terms are available at http://github.com/nlx-group."
-    ],
-    "oai_identifier": [
-        "83a09c48e6e111e6a2aa782bcb0741352ba3590e4ae642fc8e31025d267333d6"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "LX-4WAnalogies"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/be2ac672-e7e2-5b1b-8738-82c5fd835721.json b/oaitestdata/clarin-oai_dc/SET_1/json/be2ac672-e7e2-5b1b-8738-82c5fd835721.json
deleted file mode 100644
index f060c843..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/be2ac672-e7e2-5b1b-8738-82c5fd835721.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2849",
-    "MetadataAccess": [
-        "oai:ota:oucs:2849"
-    ],
-    "PublicationTimestamp": "1732-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1732"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2849;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2849.xml;A vindication of his Excellency the Lord Carteret;Swift, Jonathan, 1667-1745;1732;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "be2ac672-e7e2-5b1b-8738-82c5fd835721",
-    "oai_identifier": [
-        "oai:ota:oucs:2849"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A vindication of his Excellency the Lord Carteret"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2849.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/be32b23d-a6e2-5285-97c8-a3948d05a9b5.json b/oaitestdata/clarin-oai_dc/SET_1/json/be32b23d-a6e2-5285-97c8-a3948d05a9b5.json
deleted file mode 100644
index e7d7cf5f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/be32b23d-a6e2-5285-97c8-a3948d05a9b5.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish",
-        "Modern Greek (1453-)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/55",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/55"
-    ],
-    "PID": "http://hdl.handle.net/10794/55",
-    "PublicationTimestamp": "2015-04-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/55;2017-10-31T12:26:28Z;hdl_10794_1;hdl_10794_2;ASPAC \u2013 Swedish-Greek (2017-10-16);ASPAC \u2013 svenska-grekiska (2017-10-16);n/a, n/a;ASPAC;Parallel;Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.;Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat.;2015-04-16;corpus;http://hdl.handle.net/10794/55;swe;ell;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/octet-stream;application/gzip;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/aspacsvel",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "be32b23d-a6e2-5285-97c8-a3948d05a9b5",
-    "notes": [
-        "Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.",
-        "Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/55"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ASPAC"
-        },
-        {
-            "name": "Parallel"
-        }
-    ],
-    "title": [
-        "ASPAC \u2013 Swedish-Greek (2017-10-16)",
-        "ASPAC \u2013 svenska-grekiska (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/be3306ae-2d6b-57bb-8de6-664a88ec0484.json b/oaitestdata/clarin-oai_dc/SET_1/json/be3306ae-2d6b-57bb-8de6-664a88ec0484.json
deleted file mode 100644
index cefd0e5f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/be3306ae-2d6b-57bb-8de6-664a88ec0484.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "Contributor": [
-        "Variaci\u00f3, Iula"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Catalan",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1107",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1107"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1107",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1107;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Corpus biling\u00fce de La Canonja en temps aparent (TA);Variaci\u00f3, Iula;oral corpus;bilingual;Bilingual oral corpus containing 30 life histories/sociolinguistic interviews (17 in Catalan and 13 in Spanish) carried out in La Canonja (Tarragona).;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1107;cat;spa;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra;http://www.iula.upf.edu/recurs08ca.htm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "be3306ae-2d6b-57bb-8de6-664a88ec0484",
-    "notes": [
-        "Bilingual oral corpus containing 30 life histories/sociolinguistic interviews (17 in Catalan and 13 in Spanish) carried out in La Canonja (Tarragona)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1107"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "oral corpus"
-        },
-        {
-            "name": "bilingual"
-        }
-    ],
-    "title": [
-        "Corpus biling\u00fce de La Canonja en temps aparent (TA)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/be33e703-39b8-5b5c-aba2-42099e90ab43.json b/oaitestdata/clarin-oai_dc/SET_1/json/be33e703-39b8-5b5c-aba2-42099e90ab43.json
deleted file mode 100644
index 7ed16d16..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/be33e703-39b8-5b5c-aba2-42099e90ab43.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Humanities and Social Sciences, University of Zagreb"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Croatian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1056",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1056"
-    ],
-    "PID": "http://hdl.handle.net/11356/1056",
-    "PublicationTimestamp": "2016-03-05T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Faculty of Humanities and Social Sciences, University of Zagreb"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/324414",
-        "http://hdl.handle.net/11356/1067"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "GNU General Public Licence, version 3",
-        "http://opensource.org/licenses/GPL-3.0",
-        "PUB"
-    ],
-    "author": [
-        "Klubi\u010dka, Filip",
-        "Ljube\u0161i\u0107, Nikola"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1056;2017-06-27T18:07:00Z;hdl_11356_1023;hdl_11356_1024;Inflectional lexicon hrLex 1.0;Ljube\u0161i\u0107, Nikola;Klubi\u010dka, Filip;lexicon;morphology;inflection;hrLex is an large inflectional lexicon of Croatian language where each entry consists of a (wordform, lemma, MSD) triple. The MSD tagset follows the revised MULTEXT-East V4 tagset for Croatian and Serbian, available at\r\nhttps://github.com/ffnlp/sethr/blob/master/mte4r-upos.mapping.;2016-03-05;lexicalConceptualResource;http://hdl.handle.net/11356/1056;hrv;info:eu-repo/grantAgreement/EC/FP7/324414;http://hdl.handle.net/11356/1067;GNU General Public Licence, version 3;http://opensource.org/licenses/GPL-3.0;PUB;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Faculty of Humanities and Social Sciences, University of Zagreb;http://nlp.ffzg.hr/resources/lexicons/hrlex/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "be33e703-39b8-5b5c-aba2-42099e90ab43",
-    "notes": [
-        "hrLex is an large inflectional lexicon of Croatian language where each entry consists of a (wordform, lemma, MSD) triple. The MSD tagset follows the revised MULTEXT-East V4 tagset for Croatian and Serbian, available at\r\nhttps://github.com/ffnlp/sethr/blob/master/mte4r-upos.mapping."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1056"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "lexicon"
-        },
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "inflection"
-        }
-    ],
-    "title": [
-        "Inflectional lexicon hrLex 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/be6d96c6-34b3-5104-b103-5c0af1f5eb0b.json b/oaitestdata/clarin-oai_dc/SET_1/json/be6d96c6-34b3-5104-b103-5c0af1f5eb0b.json
deleted file mode 100644
index 2ac02e85..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/be6d96c6-34b3-5104-b103-5c0af1f5eb0b.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1144",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1144"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1144",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1144;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;OpenThesaurus;Germanistik;Synonymenw\u00f6rterbuch (Angabe von Synonymen, Kategorien, Ober-/Unterbegriffen und Assoziationen);2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1144;deu;downloadable_files_count: 0;Germany;http://www.openthesaurus.de/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "be6d96c6-34b3-5104-b103-5c0af1f5eb0b",
-    "notes": [
-        "Synonymenw\u00f6rterbuch (Angabe von Synonymen, Kategorien, Ober-/Unterbegriffen und Assoziationen)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1144"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "OpenThesaurus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/be7c6f04-f55e-5159-b2a4-5ecc6d1c9740.json b/oaitestdata/clarin-oai_dc/SET_1/json/be7c6f04-f55e-5159-b2a4-5ecc6d1c9740.json
deleted file mode 100644
index 6fcb4c4c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/be7c6f04-f55e-5159-b2a4-5ecc6d1c9740.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Ruimy, Nilda"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-472",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-472"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-472",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Italy"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-472;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;PAROLE-SIMPLE-CLIPS;Ruimy, Nilda;55.000 entries, XML;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-472;ita;downloadable_files_count: 0;Italy;http://www.ilc.cnr.it/clips/CLIPS_ENGLISH.htm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "be7c6f04-f55e-5159-b2a4-5ecc6d1c9740",
-    "notes": [
-        "55.000 entries, XML"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-472"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "PAROLE-SIMPLE-CLIPS"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/be955944-8226-590d-a55d-5a7784d7ffd4.json b/oaitestdata/clarin-oai_dc/SET_1/json/be955944-8226-590d-a55d-5a7784d7ffd4.json
deleted file mode 100644
index 4c24ae80..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/be955944-8226-590d-a55d-5a7784d7ffd4.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "214 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1978",
-    "MetadataAccess": [
-        "oai:ota:oucs:1978"
-    ],
-    "PublicationTimestamp": "1915-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1915"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Buchan, John"
-    ],
-    "fulltext": "oai:ota:oucs:1978;2018-04-16T15:09:56Z;http://ota.ox.ac.uk/headers/1978.xml;The thirty-nine steps;Buchan, John;1915;text_and_corpus_linguistics;Fiction -- Great Britain -- 20th century;eng;Oxford Text Archive, University of Oxford;214 KB;Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "be955944-8226-590d-a55d-5a7784d7ffd4",
-    "oai_identifier": [
-        "oai:ota:oucs:1978"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "The thirty-nine steps"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1978.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/beaa0d3f-a828-5414-90c4-e6da9f15a352.json b/oaitestdata/clarin-oai_dc/SET_1/json/beaa0d3f-a828-5414-90c4-e6da9f15a352.json
deleted file mode 100644
index 17be27e2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/beaa0d3f-a828-5414-90c4-e6da9f15a352.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3452",
-    "MetadataAccess": [
-        "oai:ota:oucs:3452"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Carey, Henry, 1687?-1743."
-    ],
-    "fulltext": "oai:ota:oucs:3452;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3452.xml;Blundrella: [sic]: or, the impertinent. A tale. To which is added The beau monde, or, the pleasures of St. James's. A new ballad. ...;Carey, Henry, 1687?-1743.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "beaa0d3f-a828-5414-90c4-e6da9f15a352",
-    "oai_identifier": [
-        "oai:ota:oucs:3452"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Blundrella: [sic]: or, the impertinent. A tale. To which is added The beau monde, or, the pleasures of St. James's. A new ballad. ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3452.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/beac2340-a741-5b52-9370-01def91c184e.json b/oaitestdata/clarin-oai_dc/SET_1/json/beac2340-a741-5b52-9370-01def91c184e.json
deleted file mode 100644
index 7b981fc2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/beac2340-a741-5b52-9370-01def91c184e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-992",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-992"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-992",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-992;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LAC Analysis and description of the Tiriy\u00f3 language;Language and Cognition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-992;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI33801%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "beac2340-a741-5b52-9370-01def91c184e",
-    "notes": [
-        "Language and Cognition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-992"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LAC Analysis and description of the Tiriy\u00f3 language"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bece9d33-e265-5efc-bdfe-57707980a39d.json b/oaitestdata/clarin-oai_dc/SET_1/json/bece9d33-e265-5efc-bdfe-57707980a39d.json
deleted file mode 100644
index b8f15cd0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bece9d33-e265-5efc-bdfe-57707980a39d.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "Contributor": [
-        "Malm, Mats",
-        "Borin, Lars"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-212",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-212"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-212",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Sweden"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-212;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Litteraturbanken;Borin, Lars;Malm, Mats;Full literary works (e-text, pdf, facsimile) in selected editions provided with scientific commentary and additional secondary materials; both copyright-free older works (still the lion's share) and new works (by licensing agreement with IPR holders' organizations); appr. 150 titles; planned to grow by 80-100 titles annually;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-212;swe;downloadable_files_count: 0;Sweden;http://litteraturbanken.se/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bece9d33-e265-5efc-bdfe-57707980a39d",
-    "notes": [
-        "Full literary works (e-text, pdf, facsimile) in selected editions provided with scientific commentary and additional secondary materials; both copyright-free older works (still the lion's share) and new works (by licensing agreement with IPR holders' organizations); appr. 150 titles; planned to grow by 80-100 titles annually"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-212"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Litteraturbanken"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/befc1ecf-69f5-5141-9a4f-60d3b6c7bd32.json b/oaitestdata/clarin-oai_dc/SET_1/json/befc1ecf-69f5-5141-9a4f-60d3b6c7bd32.json
deleted file mode 100644
index 8ede1f74..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/befc1ecf-69f5-5141-9a4f-60d3b6c7bd32.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Deotyma"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 5",
-        "application/zip",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/70",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/70"
-    ],
-    "PID": "http://hdl.handle.net/11321/70",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Deotyma"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Deotyma, Deotyma"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/70;2015-04-14T12:56:18Z;hdl_11321_3;hdl_11321_4;MWE Deotyma;Deotyma, Deotyma;Deotyma;2015-04-08;corpus;http://hdl.handle.net/11321/70;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 5;Deotyma",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "befc1ecf-69f5-5141-9a4f-60d3b6c7bd32",
-    "notes": [
-        "Deotyma"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/70"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Deotyma"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/befe24e9-ac43-5253-9e28-280af0176d0d.json b/oaitestdata/clarin-oai_dc/SET_1/json/befe24e9-ac43-5253-9e28-280af0176d0d.json
deleted file mode 100644
index 5f4e4b5b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/befe24e9-ac43-5253-9e28-280af0176d0d.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=aff1ddc0bc8911e1a404080027e73ea259aeca28412944ea97f7b2580a41caec",
-    "MetadataAccess": [
-        "aff1ddc0bc8911e1a404080027e73ea259aeca28412944ea97f7b2580a41caec"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "aff1ddc0bc8911e1a404080027e73ea259aeca28412944ea97f7b2580a41caec;2018-11-15T16:39:36Z;toolService;toolService:tool;U-Compare Cafetiere English Sentence Detector;The purpose of the tool is to detect sentence boundaries in English text. The tool is provided as a UIMA component, specifically as Java archive (jar) file, which can be incorporated within any UIMA workflow. However, it is particularly designed use in the U-Compare text mining platform (see separate META-SHARE record), since the types of annotations it produces are compliant with the U-Compare.;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "befe24e9-ac43-5253-9e28-280af0176d0d",
-    "notes": [
-        "The purpose of the tool is to detect sentence boundaries in English text. The tool is provided as a UIMA component, specifically as Java archive (jar) file, which can be incorporated within any UIMA workflow. However, it is particularly designed use in the U-Compare text mining platform (see separate META-SHARE record), since the types of annotations it produces are compliant with the U-Compare."
-    ],
-    "oai_identifier": [
-        "aff1ddc0bc8911e1a404080027e73ea259aeca28412944ea97f7b2580a41caec"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "U-Compare Cafetiere English Sentence Detector"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bf1cc841-d86c-5d2f-986f-87635e1bb024.json b/oaitestdata/clarin-oai_dc/SET_1/json/bf1cc841-d86c-5d2f-986f-87635e1bb024.json
deleted file mode 100644
index 44ba8fd6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bf1cc841-d86c-5d2f-986f-87635e1bb024.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "A"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1515",
-    "MetadataAccess": [
-        "oai:ota:oucs:1515"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Unknown"
-    ],
-    "fulltext": "oai:ota:oucs:1515;2018-04-16T15:30:51Z;http://ota.ox.ac.uk/headers/1515.xml;Magna carta;Unknown;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;A;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bf1cc841-d86c-5d2f-986f-87635e1bb024",
-    "oai_identifier": [
-        "oai:ota:oucs:1515"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Magna carta"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1515.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bf1de596-24a1-5070-bac7-e8f631c5cc9b.json b/oaitestdata/clarin-oai_dc/SET_1/json/bf1de596-24a1-5070-bac7-e8f631c5cc9b.json
deleted file mode 100644
index eef852cb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bf1de596-24a1-5070-bac7-e8f631c5cc9b.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=13fc5802abc511e1a404080027e73ea2a210be7dd5c44a3b9dd47afb4b2a34ef",
-    "MetadataAccess": [
-        "13fc5802abc511e1a404080027e73ea2a210be7dd5c44a3b9dd47afb4b2a34ef"
-    ],
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "13fc5802abc511e1a404080027e73ea2a210be7dd5c44a3b9dd47afb4b2a34ef;2018-11-15T16:39:36Z;lexicalConceptualResource;lexicalConceptualResource:machineReadableDictionary;Basic English-Maltese Dictionary;Bilingual wordlist, consisting of alphabetically ordered English lemmas with their Maltese translation and Maltese pronunciation (transcribed in ad-hoc system by the original author).;2015-12-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bf1de596-24a1-5070-bac7-e8f631c5cc9b",
-    "notes": [
-        "Bilingual wordlist, consisting of alphabetically ordered English lemmas with their Maltese translation and Maltese pronunciation (transcribed in ad-hoc system by the original author)."
-    ],
-    "oai_identifier": [
-        "13fc5802abc511e1a404080027e73ea2a210be7dd5c44a3b9dd47afb4b2a34ef"
-    ],
-    "oai_set": [
-        "lexicalConceptualResource",
-        "lexicalConceptualResource:machineReadableDictionary"
-    ],
-    "state": "active",
-    "title": [
-        "Basic English-Maltese Dictionary"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bf49d89a-238b-510b-abcb-9a0b8ae51e87.json b/oaitestdata/clarin-oai_dc/SET_1/json/bf49d89a-238b-510b-abcb-9a0b8ae51e87.json
deleted file mode 100644
index 204acd79..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bf49d89a-238b-510b-abcb-9a0b8ae51e87.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Dawson, John A."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 846 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0872",
-    "MetadataAccess": [
-        "oai:ota:oucs:0872"
-    ],
-    "PublicationTimestamp": "1593-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1593"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Tasso, Torquato, 1544-1595"
-    ],
-    "fulltext": "oai:ota:oucs:0872;2018-02-28T15:16:32Z;http://ota.ox.ac.uk/headers/0872.xml;Gerusalemme conquistata / Torquato Tasso;Jerusalem conquered;Tasso, Torquato, 1544-1595;1593;text_and_corpus_linguistics;Italian poetry -- 16th century;Crusades -- First, 1096-1099 -- Poetry;ita;Oxford Text Archive, University of Oxford;Dawson, John A.;text/plain;(1 file : ca. 846 KB);Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bf49d89a-238b-510b-abcb-9a0b8ae51e87",
-    "oai_identifier": [
-        "oai:ota:oucs:0872"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Italian poetry -- th century"
-        },
-        {
-            "name": "Crusades -- First"
-        },
-        {
-            "name": "- -- Poetry"
-        }
-    ],
-    "title": [
-        "Gerusalemme conquistata / Torquato Tasso",
-        "Jerusalem conquered"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0872.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bf59793d-9d2d-5881-a870-e9feaff3044e.json b/oaitestdata/clarin-oai_dc/SET_1/json/bf59793d-9d2d-5881-a870-e9feaff3044e.json
deleted file mode 100644
index bc5f9448..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bf59793d-9d2d-5881-a870-e9feaff3044e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3437",
-    "MetadataAccess": [
-        "oai:ota:oucs:3437"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Brown, Charles, fl. 1797-1799."
-    ],
-    "fulltext": "oai:ota:oucs:3437;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3437.xml;A treatise on scrophulous diseases: shewing the good effects of factitious airs: ... By Charles Brown.;Brown, Charles, fl. 1797-1799.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bf59793d-9d2d-5881-a870-e9feaff3044e",
-    "oai_identifier": [
-        "oai:ota:oucs:3437"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A treatise on scrophulous diseases: shewing the good effects of factitious airs: ... By Charles Brown."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3437.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bf5f73b8-897e-522a-88fc-6f34264662eb.json b/oaitestdata/clarin-oai_dc/SET_1/json/bf5f73b8-897e-522a-88fc-6f34264662eb.json
deleted file mode 100644
index 1a096063..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bf5f73b8-897e-522a-88fc-6f34264662eb.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Olsen, Bengt"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : total of ca. 361 KB)"
-    ],
-    "Language": [
-        "Latvian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0287",
-    "MetadataAccess": [
-        "oai:ota:oucs:0287"
-    ],
-    "PublicationTimestamp": "1964-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1964"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Folklore",
-        "Anthologies"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:0287;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0287.xml;Latvian folksong corpus;1964-1974;text_and_corpus_linguistics;Folk-songs, Latvian;Folklore -- Latvia;Linguistic analysis (Linguistics);lav;Oxford Text Archive, University of Oxford;Olsen, Bengt;(1 file : total of ca. 361 KB);Text;Folklore;Anthologies;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bf5f73b8-897e-522a-88fc-6f34264662eb",
-    "oai_identifier": [
-        "oai:ota:oucs:0287"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Folk-songs"
-        },
-        {
-            "name": "Latvian"
-        },
-        {
-            "name": "Folklore -- Latvia"
-        },
-        {
-            "name": "Linguistic analysis Linguistics"
-        }
-    ],
-    "title": [
-        "Latvian folksong corpus"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0287.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bf682a7d-cf77-5baf-8af7-9fb1b69e358c.json b/oaitestdata/clarin-oai_dc/SET_1/json/bf682a7d-cf77-5baf-8af7-9fb1b69e358c.json
deleted file mode 100644
index 02400625..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bf682a7d-cf77-5baf-8af7-9fb1b69e358c.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=ebf64a38d0e111e1a404080027e73ea2229d220cc2034f7989729aae7dfd25dd",
-    "MetadataAccess": [
-        "ebf64a38d0e111e1a404080027e73ea2229d220cc2034f7989729aae7dfd25dd"
-    ],
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "ebf64a38d0e111e1a404080027e73ea2229d220cc2034f7989729aae7dfd25dd;2018-11-15T16:39:22Z;toolService;toolService:tool;YamCha: Yet Another Multipurpose CHunk Annotator ;YamCha is a generic, customizable, and open source text chunker oriented toward a lot of NLP tasks, such as POS tagging, Named Entity Recognition, base NP chunking, and Text Chunking. We used it for NP chunking.;2015-12-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bf682a7d-cf77-5baf-8af7-9fb1b69e358c",
-    "notes": [
-        "YamCha is a generic, customizable, and open source text chunker oriented toward a lot of NLP tasks, such as POS tagging, Named Entity Recognition, base NP chunking, and Text Chunking. We used it for NP chunking."
-    ],
-    "oai_identifier": [
-        "ebf64a38d0e111e1a404080027e73ea2229d220cc2034f7989729aae7dfd25dd"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "YamCha: Yet Another Multipurpose CHunk Annotator "
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bf90d1cb-1623-5d4d-b1b1-f4e5d9b38b3b.json b/oaitestdata/clarin-oai_dc/SET_1/json/bf90d1cb-1623-5d4d-b1b1-f4e5d9b38b3b.json
deleted file mode 100644
index 2ddd0820..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bf90d1cb-1623-5d4d-b1b1-f4e5d9b38b3b.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3136",
-    "MetadataAccess": [
-        "oai:ota:oucs:3136"
-    ],
-    "PublicationTimestamp": "1774-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1774"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Wilson, James, 1742-1798"
-    ],
-    "fulltext": "oai:ota:oucs:3136;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3136.xml;On the legislative authority of the British Parliament;Wilson, James, 1742-1798;not after: 1774;text_and_corpus_linguistics;Great Britiain -- Politics and government -- 1760-1820;eng;Oxford Text Archive, University of Oxford;Triggs, Jeffery;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bf90d1cb-1623-5d4d-b1b1-f4e5d9b38b3b",
-    "oai_identifier": [
-        "oai:ota:oucs:3136"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Great Britiain -- Politics government -- -"
-        }
-    ],
-    "title": [
-        "On the legislative authority of the British Parliament"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3136.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bfacf110-a0fc-51f9-9561-e375067c74ab.json b/oaitestdata/clarin-oai_dc/SET_1/json/bfacf110-a0fc-51f9-9561-e375067c74ab.json
deleted file mode 100644
index e9e164e4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bfacf110-a0fc-51f9-9561-e375067c74ab.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3998",
-    "MetadataAccess": [
-        "oai:ota:oucs:3998"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "More, Hannah, 1745-1833."
-    ],
-    "fulltext": "oai:ota:oucs:3998;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3998.xml;The history of Tom White: the postilion. Part I.;More, Hannah, 1745-1833.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bfacf110-a0fc-51f9-9561-e375067c74ab",
-    "oai_identifier": [
-        "oai:ota:oucs:3998"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The history of Tom White: the postilion. Part I."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3998.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bfafbc77-c7f3-5aec-b100-f01ad601043d.json b/oaitestdata/clarin-oai_dc/SET_1/json/bfafbc77-c7f3-5aec-b100-f01ad601043d.json
deleted file mode 100644
index a33831ba..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bfafbc77-c7f3-5aec-b100-f01ad601043d.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Department of Informatics, Human Language Technology Group, University of Szeged"
-    ],
-    "Contributor": [
-        "Vincze, Veronika"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/xml"
-    ],
-    "Language": [
-        "Hungarian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-346",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-346"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-346",
-    "PublicationTimestamp": "2002-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2002"
-    ],
-    "Publisher": [
-        "Department of Informatics, Human Language Technology Group, University of Szeged"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Hungary"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-346;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Szeged Corpus 1.0;Vincze, Veronika;monolingual corpus;annotated corpus;POS annotation;written, monolingual, general, manually POS annotated reference corpus; 1,247,546 tokens; MSD tagset, XML (TEIxLite) files;2002;corpus;http://hdl.handle.net/11372/LRT-346;hun;application/xml;downloadable_files_count: 0;Hungary;Department of Informatics, Human Language Technology Group, University of Szeged;http://www.inf.u-szeged.hu/projectdirs/hlt/index_en.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bfafbc77-c7f3-5aec-b100-f01ad601043d",
-    "notes": [
-        "written, monolingual, general, manually POS annotated reference corpus; 1,247,546 tokens; MSD tagset, XML (TEIxLite) files"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-346"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "monolingual corpus"
-        },
-        {
-            "name": "annotated corpus"
-        },
-        {
-            "name": "POS annotation"
-        }
-    ],
-    "title": [
-        "Szeged Corpus 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bff8b85b-53ee-5f3d-806c-90fc33be152a.json b/oaitestdata/clarin-oai_dc/SET_1/json/bff8b85b-53ee-5f3d-806c-90fc33be152a.json
deleted file mode 100644
index 9016b7e4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bff8b85b-53ee-5f3d-806c-90fc33be152a.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "Contributor": [
-        "Windhouwer, Menzo",
-        "Kemps-Snijders, Marc"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1210",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1210"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1210",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1210;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;ISOcat;Windhouwer, Menzo;Kemps-Snijders, Marc;ISOcat is the reference implementation of ISO 12620.2, and implements a Data Category Registry;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1210;downloadable_files_count: 0;Netherlands (the);Max Planck Institute for Psycholinguistics;http://www.isocat.org/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bff8b85b-53ee-5f3d-806c-90fc33be152a",
-    "notes": [
-        "ISOcat is the reference implementation of ISO 12620.2, and implements a Data Category Registry"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1210"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "ISOcat"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/bff958e3-1aad-5b1c-8c2e-ebfc8df3ce0a.json b/oaitestdata/clarin-oai_dc/SET_1/json/bff958e3-1aad-5b1c-8c2e-ebfc8df3ce0a.json
deleted file mode 100644
index d6ee5b9a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/bff958e3-1aad-5b1c-8c2e-ebfc8df3ce0a.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "University of Lisbon"
-    ],
-    "Contributor": [
-        "Branco, Ant\u00f3nio"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Portuguese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-656",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-656"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-656",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Lisbon"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Portugal"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-656;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LX-Service;Branco, Ant\u00f3nio;Web service providing sentence and word segmentation, and pos tagging for Portuguese.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-656;por;downloadable_files_count: 0;Portugal;University of Lisbon;http://lxsuite.di.fc.ul.pt/lxServiceClient.v1.0.zip",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bff958e3-1aad-5b1c-8c2e-ebfc8df3ce0a",
-    "notes": [
-        "Web service providing sentence and word segmentation, and pos tagging for Portuguese."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-656"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LX-Service"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c04714ea-754c-5210-95b4-503470b92e70.json b/oaitestdata/clarin-oai_dc/SET_1/json/c04714ea-754c-5210-95b4-503470b92e70.json
deleted file mode 100644
index 2912fb62..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c04714ea-754c-5210-95b4-503470b92e70.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4379",
-    "MetadataAccess": [
-        "oai:ota:oucs:4379"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Homer."
-    ],
-    "fulltext": "oai:ota:oucs:4379;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4379.xml;The Iliad: of Homer. Translated by Mr. Pope. [pt.6];Iliad. English;Homer.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c04714ea-754c-5210-95b4-503470b92e70",
-    "oai_identifier": [
-        "oai:ota:oucs:4379"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The Iliad: of Homer. Translated by Mr. Pope. [pt.6]",
-        "Iliad. English"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4379.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c0472d9e-f52a-5597-bd96-c5849a50e145.json b/oaitestdata/clarin-oai_dc/SET_1/json/c0472d9e-f52a-5597-bd96-c5849a50e145.json
deleted file mode 100644
index 12954811..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c0472d9e-f52a-5597-bd96-c5849a50e145.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Archives of Latvian Folklore, Institute of Literature, Folklore and Art, University of Latvia"
-    ],
-    "Contributor": [
-        "B\u0113rzi\u0146a-Reinsone, Sanita"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Latvian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-188",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-188"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-188",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Archives of Latvian Folklore, Institute of Literature, Folklore and Art, University of Latvia"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Latvia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-188;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Audio and video database of Latvian folklore;B\u0113rzi\u0146a-Reinsone, Sanita;The database contains audio and video material related to traditional culture - songs, folktales, legends, life stories and various collective or individual folklore related performances. The content has been either specifically contributed to the Archives of Latvian Folklore or collected by its staff members.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-188;lav;application/octet-stream;downloadable_files_count: 0;Latvia;Archives of Latvian Folklore, Institute of Literature, Folklore and Art, University of Latvia;http://www.lfk.lv/kratuve/records.jsp?lg=en",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c0472d9e-f52a-5597-bd96-c5849a50e145",
-    "notes": [
-        "The database contains audio and video material related to traditional culture - songs, folktales, legends, life stories and various collective or individual folklore related performances. The content has been either specifically contributed to the Archives of Latvian Folklore or collected by its staff members."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-188"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Audio and video database of Latvian folklore"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c04bfdb7-1819-55d5-9e99-211d30d73031.json b/oaitestdata/clarin-oai_dc/SET_1/json/c04bfdb7-1819-55d5-9e99-211d30d73031.json
deleted file mode 100644
index b3cd021f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c04bfdb7-1819-55d5-9e99-211d30d73031.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "University of Tartu"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Estonian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-645",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-645"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-645",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Tartu"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Estonia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-645;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Corpus with Disambiguated Word Senses;100000 words, word senses based on TEKsaurus (Estonian Wordnet);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-645;est;downloadable_files_count: 0;Estonia;University of Tartu;http://www.cl.ut.ee/korpused/semkorpus/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c04bfdb7-1819-55d5-9e99-211d30d73031",
-    "notes": [
-        "100000 words, word senses based on TEKsaurus (Estonian Wordnet)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-645"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus with Disambiguated Word Senses"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c06c04db-2e44-58d9-a279-6c49526c10cc.json b/oaitestdata/clarin-oai_dc/SET_1/json/c06c04db-2e44-58d9-a279-6c49526c10cc.json
deleted file mode 100644
index 7669bcc9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c06c04db-2e44-58d9-a279-6c49526c10cc.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=73b84c28fd1a11e6a2aa782bcb074135a9fd1289fd654abeb973c65280441a6d",
-    "MetadataAccess": [
-        "73b84c28fd1a11e6a2aa782bcb074135a9fd1289fd654abeb973c65280441a6d"
-    ],
-    "PublicationTimestamp": "2017-02-27T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "fulltext": "73b84c28fd1a11e6a2aa782bcb074135a9fd1289fd654abeb973c65280441a6d;2018-11-15T16:40:29Z;lexicalConceptualResource;lexicalConceptualResource:terminologicalResource;A Terminological Inventory for Biodiversity;In order to construct the inventory, we firstly compiled a species name dictionary by combining all of the names available in Catalogue of Life (CoL), Encyclopedia of Life (EoL) and Global Biodiversity Information Facility (GBIF). \nThe terms contained in this dictionary were then located within the text of English BHL documents (about 24 million pages of text) using a string matching method. \nWe then learned vector representations of the identified terms using three different approaches, namely count-based, prediction-based and compositional distributional semantic models (DSMs). \nThese approaches compute vector representations for both single and multi-word terms. \nThe cosine similarity between two vectors serves as an indicator of the corresponding terms' semantic relatedness: the higher the cosine similarity, the more related the two terms are. \nWe finally selected the top-k candidates as the terms that are most semantically related to a given term.\n\nThe inventory contains 288,562 names of species whose frequency in BHL documents is at least five. \nFor each term in the inventory, the 20 topmost semantically similar terms are provided, together with their corresponding similarity scores. \nFor further digital biodiversity processes, each term is also linked to its URI, UUID and LSID indexed by Global Names.\n\nA search interface that uses the inventory as metadata for query expansion is available at http://nactem.ac.uk/BHLQueryExpansion/.;2017-02-27",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c06c04db-2e44-58d9-a279-6c49526c10cc",
-    "notes": [
-        "In order to construct the inventory, we firstly compiled a species name dictionary by combining all of the names available in Catalogue of Life (CoL), Encyclopedia of Life (EoL) and Global Biodiversity Information Facility (GBIF). \nThe terms contained in this dictionary were then located within the text of English BHL documents (about 24 million pages of text) using a string matching method. \nWe then learned vector representations of the identified terms using three different approaches, namely count-based, prediction-based and compositional distributional semantic models (DSMs). \nThese approaches compute vector representations for both single and multi-word terms. \nThe cosine similarity between two vectors serves as an indicator of the corresponding terms' semantic relatedness: the higher the cosine similarity, the more related the two terms are. \nWe finally selected the top-k candidates as the terms that are most semantically related to a given term.\n\nThe inventory contains 288,562 names of species whose frequency in BHL documents is at least five. \nFor each term in the inventory, the 20 topmost semantically similar terms are provided, together with their corresponding similarity scores. \nFor further digital biodiversity processes, each term is also linked to its URI, UUID and LSID indexed by Global Names.\n\nA search interface that uses the inventory as metadata for query expansion is available at http://nactem.ac.uk/BHLQueryExpansion/."
-    ],
-    "oai_identifier": [
-        "73b84c28fd1a11e6a2aa782bcb074135a9fd1289fd654abeb973c65280441a6d"
-    ],
-    "oai_set": [
-        "lexicalConceptualResource",
-        "lexicalConceptualResource:terminologicalResource"
-    ],
-    "state": "active",
-    "title": [
-        "A Terminological Inventory for Biodiversity"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c083157b-06bb-59a1-bba1-31facb9d2969.json b/oaitestdata/clarin-oai_dc/SET_1/json/c083157b-06bb-59a1-bba1-31facb9d2969.json
deleted file mode 100644
index 9baea122..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c083157b-06bb-59a1-bba1-31facb9d2969.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "university of silesia"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 20",
-        "text/plain; charset=utf-8",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/359",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/359"
-    ],
-    "PID": "http://hdl.handle.net/11321/359",
-    "PublicationTimestamp": "2017-04-25T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "university of silesia"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Janowska, Aleksandra"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/359;2017-04-25T14:09:31Z;hdl_11321_3;hdl_11321_4;aleksandra;Janowska, Aleksandra;noun;corpus;2017-04-25;corpus;http://hdl.handle.net/11321/359;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;downloadable_files_count: 20;university of silesia;http/us.edu.pl",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c083157b-06bb-59a1-bba1-31facb9d2969",
-    "notes": [
-        "corpus"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/359"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "noun"
-        }
-    ],
-    "title": [
-        "aleksandra"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c0ad4383-bfba-577c-a72b-0d91f695e159.json b/oaitestdata/clarin-oai_dc/SET_1/json/c0ad4383-bfba-577c-a72b-0d91f695e159.json
deleted file mode 100644
index a6116f55..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c0ad4383-bfba-577c-a72b-0d91f695e159.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3321",
-    "MetadataAccess": [
-        "oai:ota:oucs:3321"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Cumberland, Richard, 1732-1811."
-    ],
-    "fulltext": "oai:ota:oucs:3321;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3321.xml;An elegy written on Saint Mark's eve;Cumberland, Richard, 1732-1811.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c0ad4383-bfba-577c-a72b-0d91f695e159",
-    "oai_identifier": [
-        "oai:ota:oucs:3321"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An elegy written on Saint Mark's eve"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3321.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c0ade835-4841-5ac5-b55c-b38fa6724a95.json b/oaitestdata/clarin-oai_dc/SET_1/json/c0ade835-4841-5ac5-b55c-b38fa6724a95.json
deleted file mode 100644
index b75057f6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c0ade835-4841-5ac5-b55c-b38fa6724a95.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/gzip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/577",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/577"
-    ],
-    "PID": "http://hdl.handle.net/11321/577",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "Rights": [
-        "BSD 2 Clause",
-        "https://opensource.org/licenses/BSD-2-Clause",
-        "PUB"
-    ],
-    "author": [
-        "Woli\u0144ski, Marcin"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/577;2018-07-26T14:20:02Z;hdl_11321_3;hdl_11321_4;Polimorf;Woli\u0144ski, Marcin;inflection;dictionary;PoliMorf is a morphological dictionary for Polish resulting from the standardization and merger of Morfeusz SGJP and Morfologik.  The present version includes extended information on proper names.;2018;languageDescription;http://hdl.handle.net/11321/577;pol;BSD 2 Clause;https://opensource.org/licenses/BSD-2-Clause;PUB;text/plain; charset=utf-8;application/gzip;downloadable_files_count: 1;Institute of Computer Science, Polish Academy of Sciences;http://sgjp.pl/morfeusz/dopobrania.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c0ade835-4841-5ac5-b55c-b38fa6724a95",
-    "notes": [
-        "PoliMorf is a morphological dictionary for Polish resulting from the standardization and merger of Morfeusz SGJP and Morfologik.  The present version includes extended information on proper names."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/577"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "inflection"
-        },
-        {
-            "name": "dictionary"
-        }
-    ],
-    "title": [
-        "Polimorf"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c0ca1e1d-20e0-59ae-9d16-89ba250b5ff2.json b/oaitestdata/clarin-oai_dc/SET_1/json/c0ca1e1d-20e0-59ae-9d16-89ba250b5ff2.json
deleted file mode 100644
index b1ef41f5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c0ca1e1d-20e0-59ae-9d16-89ba250b5ff2.json
+++ /dev/null
@@ -1,107 +0,0 @@
-{
-    "Contact": [
-        "Universit\u00e4t des Saarlandes"
-    ],
-    "Contributor": [
-        "Christine Foeldesi",
-        "Kerstin Kl\u00f6ckner",
-        "Wojciech Skut",
-        "Oliver Plaehn",
-        "Sabine Brants",
-        "Olaf Holz",
-        "Bernd-Paul Simon",
-        "Holger Stenzhorn",
-        "Brigitte Krenn",
-        "Marcus Pussel",
-        "Hans Uszkoreit",
-        "Thorsten Brants",
-        "Meike van Hoorn",
-        "Anne Schwartz",
-        "Roland Hendriks"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:negra",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:negra"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0005-BD11-5",
-    "PublicationTimestamp": "2006-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2006"
-    ],
-    "Publisher": [
-        "Universit\u00e4t des Saarlandes"
-    ],
-    "RelatedIdentifier": [
-        "Part-of-Speech Tags. Stuttgart-T\u00fcbingen-Tagset (STTS): http://www.coli.uni-saarland.de/projects/sfb378/negra-corpus/stts.asc",
-        "Morphological analysis (only for the first 60,000 tokens). These are the tags of the expanded STTS. The link is broken, but it could be used instead the info in ISOCAT: http://www.isocat.org/rest/dcs/376",
-        "The grammatical function in the directly dominating phrase. List of the grammatical funktions: http://www.coli.uni-saarland.de/projects/sfb378/negra-corpus/kanten.html",
-        "The category of nonterminal nodes (phrases). List of the phrasal categories: http://www.coli.uni-saarland.de/projects/sfb378/negra-corpus/knoten.html",
-        "In the project the annotation tool Annotate was used as a graphical user interface for an efficient structural annotation. It works together with parsers supporting the manual annotation and running in the background via a defined interface: http://www.coli.uni-saarland.de/projects/sfb378/negra-corpus/annotate.html"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Academics: free",
-        "Commercial: with licence: http://www.coli.uni-saarland.de/projects/sfb378/negra-corpus/corpus-license.html",
-        "Pre-condition: User must have a valid licence fo the CD \u201cMultilingual Corpus 1\u201d reselased by the European Corpus Initiative"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "NEGRA (DFG Sonderforschungsbereich 378, Projekt C3)",
-        "LINC (Universit\u00e4t des Saarlandes)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:negra;2014-06-03T12:55:04Z;NEGRA;NEGRA (DFG Sonderforschungsbereich 378, Projekt C3);LINC (Universit\u00e4t des Saarlandes);corpus linguistics;linguistics;computational linguistics;treebank;syntactic annotation;The NEGRA corpus version 2 consists of 355,096 tokens (20,602 sentences) of German newspaper text, taken from the Frankfurter Rundschau as contained in the CD \u201cMultilingual Corpus 1\u201d of the European Corpus Initiative. It is based on approx. 60,000 tokens that were tagged for part-of speech at the Institut f\u00fcr maschinelle Sprachverarbeitung, Stuttgart. This corpus was extended, tagged with part-of-speech and completely annotated with syntactic structures. The corpus was created in the projects NEGRA (DFG Sonderforschungsbereich 378, Projekt C3) and LINC (Universit\u00e4t des Saarlandes) in Saarbr\u00fccken.;Das NEGRA Korpus Version 2 besteht aus 355.096 Tokens (20.602 S\u00e4tzen) deutschen Zeitungstextes aus der Frankfurter Rundschau. Die Texte sind der CD \u201cMultilingual Corpus 1\u201d der European Corpus Initiative entnommen. Es basiert auf ca. 60.000 Tokens, die am Institut f\u00fcr maschinelle Sprachverarbeitung, Stuttgart, mit Parts-of-Speech annotiert wurden. Dieses Korpus wurde erweitert, ebenfalls mit Parts-of-Speech versehen und vollst\u00e4ndig mit syntaktischen Strukturen annotiert. Der Aufbau des Korpus wurde in den Projekten NEGRA (DFG Sonderforschungsbereich 378, Projekt C3) und LINC (Universit\u00e4t des Saarlandes) in Saarbr\u00fccken durchgef\u00fchrt.;Universit\u00e4t des Saarlandes;Hans Uszkoreit;Thorsten Brants;Sabine Brants;Christine Foeldesi;Roland Hendriks;Olaf Holz;Meike van Hoorn;Kerstin Kl\u00f6ckner;Brigitte Krenn;Oliver Plaehn;Marcus Pussel;Anne Schwartz;Bernd-Paul Simon;Wojciech Skut;Holger Stenzhorn;2006;Dataset;text/xml;clarind-uds:negra;clarind-uds:NEGRA;hdl:11858/00-246C-0000-0005-BD11-5;German newspaper text, taken from the Frankfurter Rundschau as contained in the CD \"Multilingual Corpus 1\" of the European Corpus Initiative: http://www.ldc.upenn.edu/Catalog/CatalogEntry.jsp?catalogId=LDC94T5;deu;Part-of-Speech Tags. Stuttgart-T\u00fcbingen-Tagset (STTS): http://www.coli.uni-saarland.de/projects/sfb378/negra-corpus/stts.asc;Morphological analysis (only for the first 60,000 tokens). These are the tags of the expanded STTS. The link is broken, but it could be used instead the info in ISOCAT: http://www.isocat.org/rest/dcs/376;The grammatical function in the directly dominating phrase. List of the grammatical funktions: http://www.coli.uni-saarland.de/projects/sfb378/negra-corpus/kanten.html;The category of nonterminal nodes (phrases). List of the phrasal categories: http://www.coli.uni-saarland.de/projects/sfb378/negra-corpus/knoten.html;In the project the annotation tool Annotate was used as a graphical user interface for an efficient structural annotation. It works together with parsers supporting the manual annotation and running in the background via a defined interface: http://www.coli.uni-saarland.de/projects/sfb378/negra-corpus/annotate.html;Germany;Academics: free;Commercial: with licence: http://www.coli.uni-saarland.de/projects/sfb378/negra-corpus/corpus-license.html;Pre-condition: User must have a valid licence fo the CD \u201cMultilingual Corpus 1\u201d reselased by the European Corpus Initiative",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c0ca1e1d-20e0-59ae-9d16-89ba250b5ff2",
-    "notes": [
-        "The NEGRA corpus version 2 consists of 355,096 tokens (20,602 sentences) of German newspaper text, taken from the Frankfurter Rundschau as contained in the CD \u201cMultilingual Corpus 1\u201d of the European Corpus Initiative. It is based on approx. 60,000 tokens that were tagged for part-of speech at the Institut f\u00fcr maschinelle Sprachverarbeitung, Stuttgart. This corpus was extended, tagged with part-of-speech and completely annotated with syntactic structures. The corpus was created in the projects NEGRA (DFG Sonderforschungsbereich 378, Projekt C3) and LINC (Universit\u00e4t des Saarlandes) in Saarbr\u00fccken.",
-        "Das NEGRA Korpus Version 2 besteht aus 355.096 Tokens (20.602 S\u00e4tzen) deutschen Zeitungstextes aus der Frankfurter Rundschau. Die Texte sind der CD \u201cMultilingual Corpus 1\u201d der European Corpus Initiative entnommen. Es basiert auf ca. 60.000 Tokens, die am Institut f\u00fcr maschinelle Sprachverarbeitung, Stuttgart, mit Parts-of-Speech annotiert wurden. Dieses Korpus wurde erweitert, ebenfalls mit Parts-of-Speech versehen und vollst\u00e4ndig mit syntaktischen Strukturen annotiert. Der Aufbau des Korpus wurde in den Projekten NEGRA (DFG Sonderforschungsbereich 378, Projekt C3) und LINC (Universit\u00e4t des Saarlandes) in Saarbr\u00fccken durchgef\u00fchrt."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:negra"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus linguistics"
-        },
-        {
-            "name": "linguistics"
-        },
-        {
-            "name": "computational linguistics"
-        },
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "syntactic annotation"
-        }
-    ],
-    "title": [
-        "NEGRA"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c0dd53ae-d331-553e-9f26-b928b07febc2.json b/oaitestdata/clarin-oai_dc/SET_1/json/c0dd53ae-d331-553e-9f26-b928b07febc2.json
deleted file mode 100644
index 748b586a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c0dd53ae-d331-553e-9f26-b928b07febc2.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Royster, Paul"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 820 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1653",
-    "MetadataAccess": [
-        "oai:ota:oucs:1653"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Whitman, Walt, 1819-1892"
-    ],
-    "fulltext": "oai:ota:oucs:1653;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1653.xml;Leaves of grass : [1892] / Walt Whitman;Whitman, Walt, 1819-1892;text_and_corpus_linguistics;American poetry -- 19th century;Oxford Text Archive, University of Oxford;Royster, Paul;text/sgml;(1 file : ca. 820 KB);Text;Poems;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c0dd53ae-d331-553e-9f26-b928b07febc2",
-    "oai_identifier": [
-        "oai:ota:oucs:1653"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "American poetry -- th century"
-        }
-    ],
-    "title": [
-        "Leaves of grass : [1892] / Walt Whitman"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1653.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c0fab462-f064-51b7-9a74-06b64c8d51a6.json b/oaitestdata/clarin-oai_dc/SET_1/json/c0fab462-f064-51b7-9a74-06b64c8d51a6.json
deleted file mode 100644
index 978368ca..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c0fab462-f064-51b7-9a74-06b64c8d51a6.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "University of Lisbon"
-    ],
-    "Contributor": [
-        "Mendes, Am\u00e1lia"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Portuguese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-556",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-556"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-556",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Lisbon"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Portugal"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-556;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;PAROLE Portuguese Lexicon;Mendes, Am\u00e1lia;Generic;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-556;por;downloadable_files_count: 0;Portugal;University of Lisbon;http://www.elda.fr/catalogue/text/L0035.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c0fab462-f064-51b7-9a74-06b64c8d51a6",
-    "notes": [
-        "Generic"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-556"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "PAROLE Portuguese Lexicon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c110811c-5975-5196-81e7-c5b0ba5d2a21.json b/oaitestdata/clarin-oai_dc/SET_1/json/c110811c-5975-5196-81e7-c5b0ba5d2a21.json
deleted file mode 100644
index dc45160f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c110811c-5975-5196-81e7-c5b0ba5d2a21.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "NLX-Natural Language and Speech Group, University of Lisbon"
-    ],
-    "Contributor": [
-        "Branco, Ant\u00f3nio",
-        "Silva, Jo\u00e3o"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Portuguese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1230",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1230"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1230",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "NLX-Natural Language and Speech Group, University of Lisbon"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Portugal"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1230;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LX-Tokenizer;Branco, Ant\u00f3nio;Silva, Jo\u00e3o;Automatic segmenter of lexemes of Portuguese. Segments text into lexically relevant tokens, using whitespace as the separator. Note that, in these examples, the | (vertical bar) symbol is used to mark the token boundaries more cleary. um exemplo \u2192 |um|exemplo| Expands contractions. Note that the first element of an expanded contraction is marked with an _ (underscore) symbol: do \u2192 |de_|o| Marks spacing around punctuation or symbols. The \\* and the */ symbols indicate a space to the left and a space to the right, respectively: um, dois e tr\u00eas \u2192 |um|,*/|dois|e|tr\u00eas| 5.3 \u2192 |5|.|3| 1. 2 \u2192 |1|.*/|2| 8 . 6 \u2192 |8|\\*.*/|6| Detaches clitic pronouns from the verb. The detached pronoun is marked with a - (hyphen) symbol. When in mesoclisis, a -CL- mark is used to signal the original position of the detached clitic. Additionally, possible vocalic alterations of the verb form are marked with a # (hash) symbol: d\u00e1-se-lho \u2192 |d\u00e1|-se|-lhe|-o| afirmar-se-ia \u2192 |afirmar-CL-ia|-se| v\u00ea-las \u2192 |v\u00ea#|-las| This tool also handles ambiguous strings. These are words that, depending on their particular occurrence, can be tokenized in different ways. For instance: deste \u2192 |deste| when occurring as a Verb deste \u2192 |de|este| when occurring as a contraction (Preposition + Demonstrative) This tool achieves a f-score of 99.72%.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1230;por;downloadable_files_count: 0;Portugal;NLX-Natural Language and Speech Group, University of Lisbon;http://lxsuite.di.fc.ul.pt",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c110811c-5975-5196-81e7-c5b0ba5d2a21",
-    "notes": [
-        "Automatic segmenter of lexemes of Portuguese. Segments text into lexically relevant tokens, using whitespace as the separator. Note that, in these examples, the | (vertical bar) symbol is used to mark the token boundaries more cleary. um exemplo \u2192 |um|exemplo| Expands contractions. Note that the first element of an expanded contraction is marked with an _ (underscore) symbol: do \u2192 |de_|o| Marks spacing around punctuation or symbols. The \\* and the */ symbols indicate a space to the left and a space to the right, respectively: um, dois e tr\u00eas \u2192 |um|,*/|dois|e|tr\u00eas| 5.3 \u2192 |5|.|3| 1. 2 \u2192 |1|.*/|2| 8 . 6 \u2192 |8|\\*.*/|6| Detaches clitic pronouns from the verb. The detached pronoun is marked with a - (hyphen) symbol. When in mesoclisis, a -CL- mark is used to signal the original position of the detached clitic. Additionally, possible vocalic alterations of the verb form are marked with a # (hash) symbol: d\u00e1-se-lho \u2192 |d\u00e1|-se|-lhe|-o| afirmar-se-ia \u2192 |afirmar-CL-ia|-se| v\u00ea-las \u2192 |v\u00ea#|-las| This tool also handles ambiguous strings. These are words that, depending on their particular occurrence, can be tokenized in different ways. For instance: deste \u2192 |deste| when occurring as a Verb deste \u2192 |de|este| when occurring as a contraction (Preposition + Demonstrative) This tool achieves a f-score of 99.72%."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1230"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LX-Tokenizer"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c1156e2f-99cd-51ef-b5bc-ae171053e97b.json b/oaitestdata/clarin-oai_dc/SET_1/json/c1156e2f-99cd-51ef-b5bc-ae171053e97b.json
deleted file mode 100644
index 2a6b7718..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c1156e2f-99cd-51ef-b5bc-ae171053e97b.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3527",
-    "MetadataAccess": [
-        "oai:ota:oucs:3527"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Richardson, Samuel, 1689-1761."
-    ],
-    "fulltext": "oai:ota:oucs:3527;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3527.xml;The history of Sir Charles Grandison: In a series of letters published from the originals, by the editor of Pamela and Clarissa. In seven volumes. ... [pt.6];Sir Charles Grandison;Richardson, Samuel, 1689-1761.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c1156e2f-99cd-51ef-b5bc-ae171053e97b",
-    "oai_identifier": [
-        "oai:ota:oucs:3527"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The history of Sir Charles Grandison: In a series of letters published from the originals, by the editor of Pamela and Clarissa. In seven volumes. ... [pt.6]",
-        "Sir Charles Grandison"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3527.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c1274015-3694-5bc7-8064-9ba875a49a6c.json b/oaitestdata/clarin-oai_dc/SET_1/json/c1274015-3694-5bc7-8064-9ba875a49a6c.json
deleted file mode 100644
index 5f04acd5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c1274015-3694-5bc7-8064-9ba875a49a6c.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "less than 512 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1368",
-    "MetadataAccess": [
-        "oai:ota:oucs:1368"
-    ],
-    "PublicationYear": [
-        "Unspecified"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Langland, William,  1330?-1400?"
-    ],
-    "fulltext": "oai:ota:oucs:1368;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1368.xml; Piers Plowman  / compiled by H. Duggan;Langland, William,  1330?-1400?;Unspecified;text_and_corpus_linguistics;Poems -- England -- 14th century;eng;Oxford Text Archive, University of Oxford;less than 512 KB;Text;Poems;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c1274015-3694-5bc7-8064-9ba875a49a6c",
-    "oai_identifier": [
-        "oai:ota:oucs:1368"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- England -- th century"
-        }
-    ],
-    "title": [
-        " Piers Plowman  / compiled by H. Duggan"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1368.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c13eec16-d1cb-5014-95cb-13994113727c.json b/oaitestdata/clarin-oai_dc/SET_1/json/c13eec16-d1cb-5014-95cb-13994113727c.json
deleted file mode 100644
index 4020957a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c13eec16-d1cb-5014-95cb-13994113727c.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Information Studies Novo mesto"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 6",
-        "text/plain",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1105",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1105"
-    ],
-    "PID": "http://hdl.handle.net/11356/1105",
-    "PublicationTimestamp": "2017-04-23T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Faculty of Information Studies Novo mesto"
-    ],
-    "RelatedIdentifier": [
-        "https://doi.org/10.1007/s10579-018-9413-3"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "https://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Bu\u010dar, Jo\u017ee"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1105;2018-03-12T16:18:38Z;hdl_11356_1023;hdl_11356_1024;R crawlers for five Slovenian web media 1.0;Bu\u010dar, Jo\u017ee;web crawling;R;Five web-crawlers written in the R language for retrieving Slovenian texts from the news portals 24ur, Dnevnik, Finance, Rtvslo, and \u017durnal24. These portals contain political, business, economic and financial content.;2017-04-23;toolService;http://hdl.handle.net/11356/1105;slv;https://doi.org/10.1007/s10579-018-9413-3;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);https://creativecommons.org/licenses/by-sa/4.0/;PUB;text/plain;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 6;Faculty of Information Studies Novo mesto;https://github.com/19Joey85/Sentiment-annotated-news-corpus-and-sentiment-lexicon-in-Slovene/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c13eec16-d1cb-5014-95cb-13994113727c",
-    "notes": [
-        "Five web-crawlers written in the R language for retrieving Slovenian texts from the news portals 24ur, Dnevnik, Finance, Rtvslo, and \u017durnal24. These portals contain political, business, economic and financial content."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1105"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "web crawling"
-        }
-    ],
-    "title": [
-        "R crawlers for five Slovenian web media 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c13f134b-577c-5cbb-9889-d94283daf785.json b/oaitestdata/clarin-oai_dc/SET_1/json/c13f134b-577c-5cbb-9889-d94283daf785.json
deleted file mode 100644
index 1482fbfd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c13f134b-577c-5cbb-9889-d94283daf785.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 92 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1772",
-    "MetadataAccess": [
-        "oai:ota:oucs:1772"
-    ],
-    "PublicationTimestamp": "1899-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1899"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Fiction -- Myths and legends"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Ade, George, 1866-1944"
-    ],
-    "fulltext": "oai:ota:oucs:1772;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/1772.xml;Fables in slang / by George Ade;Ade, George, 1866-1944;1899;text_and_corpus_linguistics;Fables -- United States -- 19th century;eng;Oxford Text Archive, University of Oxford;Triggs, Jeffery;text/sgml;(1 file : ca. 92 KB);Text;Fiction -- Myths and legends;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c13f134b-577c-5cbb-9889-d94283daf785",
-    "oai_identifier": [
-        "oai:ota:oucs:1772"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fables -- United States -- th century"
-        }
-    ],
-    "title": [
-        "Fables in slang / by George Ade"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1772.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c15493ee-09e3-5fb0-86aa-274fa21673e3.json b/oaitestdata/clarin-oai_dc/SET_1/json/c15493ee-09e3-5fb0-86aa-274fa21673e3.json
deleted file mode 100644
index 419b246d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c15493ee-09e3-5fb0-86aa-274fa21673e3.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "A"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1426",
-    "MetadataAccess": [
-        "oai:ota:oucs:1426"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "While this resource was freely available for non-commercial use provided that this header is included in its entirety with any copy distributed, it has been removed from our catalogue for one reason or another.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Beckett, Samuel"
-    ],
-    "fulltext": "oai:ota:oucs:1426;2018-04-16T15:30:51Z;http://ota.ox.ac.uk/headers/1426.xml;Murphy;Beckett, Samuel;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;A;Text;While this resource was freely available for non-commercial use provided that this header is included in its entirety with any copy distributed, it has been removed from our catalogue for one reason or another.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c15493ee-09e3-5fb0-86aa-274fa21673e3",
-    "oai_identifier": [
-        "oai:ota:oucs:1426"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Murphy"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1426.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c1558717-dc8b-5806-8e7a-d1e6a366bb1d.json b/oaitestdata/clarin-oai_dc/SET_1/json/c1558717-dc8b-5806-8e7a-d1e6a366bb1d.json
deleted file mode 100644
index da0174b3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c1558717-dc8b-5806-8e7a-d1e6a366bb1d.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 887 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1513",
-    "MetadataAccess": [
-        "oai:ota:oucs:1513"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Sacred texts"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:1513;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1513.xml;Koran. English;[Koran];default: 1976-01-01;text_and_corpus_linguistics;Translations;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 887 KB);Text;Sacred texts;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c1558717-dc8b-5806-8e7a-d1e6a366bb1d",
-    "oai_identifier": [
-        "oai:ota:oucs:1513"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Translations"
-        }
-    ],
-    "title": [
-        "Koran. English",
-        "[Koran]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1513.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c1590c48-fe2b-5d74-9a6b-402386573595.json b/oaitestdata/clarin-oai_dc/SET_1/json/c1590c48-fe2b-5d74-9a6b-402386573595.json
deleted file mode 100644
index 75b4b33a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c1590c48-fe2b-5d74-9a6b-402386573595.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1457",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1457"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1457",
-    "PublicationTimestamp": "2008-12-01T11:59:59Z",
-    "PublicationYear": [
-        "2008"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0)",
-        "http://creativecommons.org/licenses/by-nc/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Pecina, Pavel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1457;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Gold Standard Reference Data for Multiword Expression Extraction: Czech Dependency Bigrams from the Prague Dependency Treebank;Pecina, Pavel;multiword expressions;Annotated list of dependency bigrams occurring in the PDT more than five times and having part-of-speech patterns that can possibly form a collocation. Each bigram is assigned to one of the six MWE categories by three annotators.;2008-12-01;lexicalConceptualResource;http://hdl.handle.net/11234/1-1457;ces;Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0);http://creativecommons.org/licenses/by-nc/3.0/;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c1590c48-fe2b-5d74-9a6b-402386573595",
-    "notes": [
-        "Annotated list of dependency bigrams occurring in the PDT more than five times and having part-of-speech patterns that can possibly form a collocation. Each bigram is assigned to one of the six MWE categories by three annotators."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1457"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "multiword expressions"
-        }
-    ],
-    "title": [
-        "Gold Standard Reference Data for Multiword Expression Extraction: Czech Dependency Bigrams from the Prague Dependency Treebank"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c15de982-9ed0-51a5-bff8-30338d34f4c4.json b/oaitestdata/clarin-oai_dc/SET_1/json/c15de982-9ed0-51a5-bff8-30338d34f4c4.json
deleted file mode 100644
index 968d7f3e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c15de982-9ed0-51a5-bff8-30338d34f4c4.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "less than 512 KB"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0412",
-    "MetadataAccess": [
-        "oai:ota:oucs:0412"
-    ],
-    "PublicationYear": [
-        "100 BCE-1 BCE"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Parthenius, of Nicaea, 1st cent. B.C."
-    ],
-    "fulltext": "oai:ota:oucs:0412;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0412.xml;Collected works  / compiled by Thesaurus Linguae Graecae;Parthenius, of Nicaea, 1st cent. B.C.;100 BCE-1 BCE;text_and_corpus_linguistics;Poems -- 1st century B.C.;grc;Oxford Text Archive, University of Oxford;less than 512 KB;Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c15de982-9ed0-51a5-bff8-30338d34f4c4",
-    "oai_identifier": [
-        "oai:ota:oucs:0412"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- st century B.C."
-        }
-    ],
-    "title": [
-        "Collected works  / compiled by Thesaurus Linguae Graecae"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0412.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c1693cfe-c0d8-550f-ba8a-869b8dabb0c1.json b/oaitestdata/clarin-oai_dc/SET_1/json/c1693cfe-c0d8-550f-ba8a-869b8dabb0c1.json
deleted file mode 100644
index 8daf13bd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c1693cfe-c0d8-550f-ba8a-869b8dabb0c1.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3799",
-    "MetadataAccess": [
-        "oai:ota:oucs:3799"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Waldron, F. G. (Francis Godolphin), 1744-1818."
-    ],
-    "fulltext": "oai:ota:oucs:3799;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3799.xml;The King in the country. A dramatic piece, in two acts. Acted at the Theatres-Royal, at Richmond and Windsor, 1788;Waldron, F. G. (Francis Godolphin), 1744-1818.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c1693cfe-c0d8-550f-ba8a-869b8dabb0c1",
-    "oai_identifier": [
-        "oai:ota:oucs:3799"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The King in the country. A dramatic piece, in two acts. Acted at the Theatres-Royal, at Richmond and Windsor, 1788"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3799.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c169bd06-43d1-5fd1-b923-3911313cb249.json b/oaitestdata/clarin-oai_dc/SET_1/json/c169bd06-43d1-5fd1-b923-3911313cb249.json
deleted file mode 100644
index ed6a4283..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c169bd06-43d1-5fd1-b923-3911313cb249.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/530",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/530"
-    ],
-    "PID": "http://hdl.handle.net/11321/530",
-    "PublicationTimestamp": "2018-07-19T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Oleksy, Marcin",
-        "Koco\u0144, Jan"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/530;2018-07-23T12:53:17Z;hdl_11321_3;hdl_11321_4;KPWr EVENTS (Attributes and Relations);Oleksy, Marcin;Koco\u0144, Jan;KPWr;corpus;events recognition;events;Attributes for EVENT;Documents from Polish Corpus of Wroc\u0142aw University of Technology manually annotated with Attributes for EVENT instances and relations between EVENTS instances;2018-07-19;corpus;http://hdl.handle.net/11321/530;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;Wroc\u0142aw University of Science and Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c169bd06-43d1-5fd1-b923-3911313cb249",
-    "notes": [
-        "Documents from Polish Corpus of Wroc\u0142aw University of Technology manually annotated with Attributes for EVENT instances and relations between EVENTS instances"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/530"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "KPWr"
-        },
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "events recognition"
-        },
-        {
-            "name": "events"
-        },
-        {
-            "name": "Attributes EVENT"
-        }
-    ],
-    "title": [
-        "KPWr EVENTS (Attributes and Relations)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c171445e-b5d3-55a7-b84c-defc7735bf95.json b/oaitestdata/clarin-oai_dc/SET_1/json/c171445e-b5d3-55a7-b84c-defc7735bf95.json
deleted file mode 100644
index bec0c514..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c171445e-b5d3-55a7-b84c-defc7735bf95.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Institute of Croatian Language and Linguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Croatian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1180",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1180"
-    ],
-    "PID": "http://hdl.handle.net/11356/1180",
-    "PublicationTimestamp": "2018-03-07T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Institute of Croatian Language and Linguistics"
-    ],
-    "RelatedIdentifier": [
-        "http://riznica.ihjj.hr/CLC-Slavicorp.pdf"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/"
-    ],
-    "author": [
-        "\u0106avar, Damir",
-        "Ljube\u0161i\u0107, Nikola",
-        "Erjavec, Toma\u017e",
-        "\u0160trkalj Despot, Kristina",
-        "\u0106avar, Ma\u0142gorzata",
-        "Stojanov, Tomislav",
-        "Brozovi\u0107 Ron\u010devi\u0107, Dunja"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1180;2018-10-24T20:55:53Z;hdl_11356_1023;hdl_11356_1024;Croatian language corpus Riznica 0.1;Brozovi\u0107 Ron\u010devi\u0107, Dunja;\u0106avar, Damir;\u0106avar, Ma\u0142gorzata;Stojanov, Tomislav;\u0160trkalj Despot, Kristina;Ljube\u0161i\u0107, Nikola;Erjavec, Toma\u017e;reference corpus;The Croatian Language Corpus was built between 2007 and 2011 at the Institute of Croatian Language and Linguistics in the scope of the research programme \"Hrvatska jezi\u010dna riznica\" as a reference corpus of Croatian language to serve various lexicographic and other linguistic and language technology projects. The corpus consists of 28% of fiction texts and 72% of specialized texts. In 2017, the corpus was segmented, part-of-speech tagged and lemmatized inside the MRE\u017dNIK project to be used for the development of the first Croatian corpus-based dictionary.;2018-03-07;corpus;http://hdl.handle.net/11356/1180;hrv;http://riznica.ihjj.hr/CLC-Slavicorp.pdf;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);PUB;https://creativecommons.org/licenses/by-nc-sa/4.0/;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Institute of Croatian Language and Linguistics;http://riznica.ihjj.hr",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c171445e-b5d3-55a7-b84c-defc7735bf95",
-    "notes": [
-        "The Croatian Language Corpus was built between 2007 and 2011 at the Institute of Croatian Language and Linguistics in the scope of the research programme \"Hrvatska jezi\u010dna riznica\" as a reference corpus of Croatian language to serve various lexicographic and other linguistic and language technology projects. The corpus consists of 28% of fiction texts and 72% of specialized texts. In 2017, the corpus was segmented, part-of-speech tagged and lemmatized inside the MRE\u017dNIK project to be used for the development of the first Croatian corpus-based dictionary."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1180"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "reference corpus"
-        }
-    ],
-    "title": [
-        "Croatian language corpus Riznica 0.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c181cfcd-4e08-5ef3-b328-974f46d29add.json b/oaitestdata/clarin-oai_dc/SET_1/json/c181cfcd-4e08-5ef3-b328-974f46d29add.json
deleted file mode 100644
index b9594006..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c181cfcd-4e08-5ef3-b328-974f46d29add.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3910",
-    "MetadataAccess": [
-        "oai:ota:oucs:3910"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dennis, John, 1657-1734."
-    ],
-    "fulltext": "oai:ota:oucs:3910;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3910.xml;A defence of Sir Fopling Flutter, a comedy written by Sir George Etheridge. In which defence is shewn, that Sir Fopling, ... was rightly compos'd by the knight his father, to answer the ends of comedy;;Dennis, John, 1657-1734.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c181cfcd-4e08-5ef3-b328-974f46d29add",
-    "oai_identifier": [
-        "oai:ota:oucs:3910"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A defence of Sir Fopling Flutter, a comedy written by Sir George Etheridge. In which defence is shewn, that Sir Fopling, ... was rightly compos'd by the knight his father, to answer the ends of comedy;"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3910.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c18b46a4-08d6-5712-8666-e645c67d64ec.json b/oaitestdata/clarin-oai_dc/SET_1/json/c18b46a4-08d6-5712-8666-e645c67d64ec.json
deleted file mode 100644
index 8379422d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c18b46a4-08d6-5712-8666-e645c67d64ec.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=1d9fe90acb7811e1a404080027e73ea241d3e2b7fb3c411481d3c23b787f8072",
-    "MetadataAccess": [
-        "1d9fe90acb7811e1a404080027e73ea241d3e2b7fb3c411481d3c23b787f8072"
-    ],
-    "PublicationTimestamp": "2012-11-28T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "fulltext": "1d9fe90acb7811e1a404080027e73ea241d3e2b7fb3c411481d3c23b787f8072;2018-11-15T16:39:29Z;lexicalConceptualResource;lexicalConceptualResource:ontology;Geo-Net-PT 02;Geo-Net-PT 02 is a public Geospatial Ontology of Portugal (see Chaves et al., 2007), a computational resource (see Rodrigues et al., 2006 and Rodrigues, 2009) for applications demanding geographic information about Portugal, and contains 701,209 concepts stored in a GKB system, most of them administrative features and place names. Some of these concepts have additional types to ease the reuse in the Web of Data: 390,664 administrative and physical features and footprints are classified as geo:SpatialThing and 23,666 network features are classified as sioc:Space. Geo-Net-PT 02 identifies 22,980 owners of domains, which are classified as sioc:User instances. The administrative and physical features are classified by 81 feature types. Postal code, street layout and settlement are the most common feature types found in the geo-administrative domain. Hydrography and touristic resources, such as museums and hotels, are the most common feature types found in the geo-physical domain.\nThe Geo-Net-PT 02 is an extension to the Geo-Net-PT 01 ontology presented in Chaves et al. (2005). It respects the recommended international standards for publishing ontologies (for more about the resource, see http://dmir.inesc-id.pt/project/Geo-Net-PT_02_in_English and Lopez-Pellicer et al. (2010).\nThis resource was created by the XLDB Team of the University of Lisbon, Faculty of Sciences, under the GREASE (Geographic Reasoning for Search Engines)1 project (see Lopez-Pellicer et al., 2009), and contains all the geographic administrative data of Portugal (distritos, concelhos and ruas, among others), and domains of websites of the Portuguese Web and their geographic scopes. Currently, it is maintained by the REACTION project (http://dmir.inesc-id.pt/project/Reaction).\nThe resource also provides an alignment with Yahoo! GeoPlanet (TM) (see Ferreira et al., 2010), between features in the Administrative with \"Where On Earth Identifiers (WOEID) from GeoPlanet (TM), and 195 Portuguese news articles with each identified toponym mapped with geographic concepts. ;2012-11-28",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c18b46a4-08d6-5712-8666-e645c67d64ec",
-    "notes": [
-        "Geo-Net-PT 02 is a public Geospatial Ontology of Portugal (see Chaves et al., 2007), a computational resource (see Rodrigues et al., 2006 and Rodrigues, 2009) for applications demanding geographic information about Portugal, and contains 701,209 concepts stored in a GKB system, most of them administrative features and place names. Some of these concepts have additional types to ease the reuse in the Web of Data: 390,664 administrative and physical features and footprints are classified as geo:SpatialThing and 23,666 network features are classified as sioc:Space. Geo-Net-PT 02 identifies 22,980 owners of domains, which are classified as sioc:User instances. The administrative and physical features are classified by 81 feature types. Postal code, street layout and settlement are the most common feature types found in the geo-administrative domain. Hydrography and touristic resources, such as museums and hotels, are the most common feature types found in the geo-physical domain.\nThe Geo-Net-PT 02 is an extension to the Geo-Net-PT 01 ontology presented in Chaves et al. (2005). It respects the recommended international standards for publishing ontologies (for more about the resource, see http://dmir.inesc-id.pt/project/Geo-Net-PT_02_in_English and Lopez-Pellicer et al. (2010).\nThis resource was created by the XLDB Team of the University of Lisbon, Faculty of Sciences, under the GREASE (Geographic Reasoning for Search Engines)1 project (see Lopez-Pellicer et al., 2009), and contains all the geographic administrative data of Portugal (distritos, concelhos and ruas, among others), and domains of websites of the Portuguese Web and their geographic scopes. Currently, it is maintained by the REACTION project (http://dmir.inesc-id.pt/project/Reaction).\nThe resource also provides an alignment with Yahoo! GeoPlanet (TM) (see Ferreira et al., 2010), between features in the Administrative with \"Where On Earth Identifiers (WOEID) from GeoPlanet (TM), and 195 Portuguese news articles with each identified toponym mapped with geographic concepts. "
-    ],
-    "oai_identifier": [
-        "1d9fe90acb7811e1a404080027e73ea241d3e2b7fb3c411481d3c23b787f8072"
-    ],
-    "oai_set": [
-        "lexicalConceptualResource",
-        "lexicalConceptualResource:ontology"
-    ],
-    "state": "active",
-    "title": [
-        "Geo-Net-PT 02"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c19460c4-1819-5c39-a7e4-6c79a153d950.json b/oaitestdata/clarin-oai_dc/SET_1/json/c19460c4-1819-5c39-a7e4-6c79a153d950.json
deleted file mode 100644
index 8e44e515..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c19460c4-1819-5c39-a7e4-6c79a153d950.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=7c508aa8bea911e1a404080027e73ea2abb5e2fadb4143b2ae4c15c250af7c78",
-    "MetadataAccess": [
-        "7c508aa8bea911e1a404080027e73ea2abb5e2fadb4143b2ae4c15c250af7c78"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "7c508aa8bea911e1a404080027e73ea2abb5e2fadb4143b2ae4c15c250af7c78;2018-11-15T16:39:23Z;toolService;toolService:tool;UIMA/U-Compare Apertium POS Tagger ;This tool assigns a part-of-speech tag and base form to each token in a text. It operates on text that has previously been tokenised and morphologically analysed. The POS tagger is a module of Apertium machine translation system. The provided tool can currently operate on a subset of the languages that are supported by the Apertium system, namely:  English, Spanish, Calatan, Galician, Portuguese, Romanian and Basque. \nNOTE: The morphological analysis required prior to running the POS tagger MUST be carried out by running the Apertium morphological analyser (which also performs tokeniaation). \n\nThe tool is provided as a UIMA component, specifically as Java archive (jar) file, which can be incorporated within any UIMA workflow. However, it is particularly designed use in the U-Compare text mining plaform (Kano et al., 2009; Kano et al., 2011; see separate META-SHARE record), since the types of annotations it produces are compliant with the U-Compare. \n;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c19460c4-1819-5c39-a7e4-6c79a153d950",
-    "notes": [
-        "This tool assigns a part-of-speech tag and base form to each token in a text. It operates on text that has previously been tokenised and morphologically analysed. The POS tagger is a module of Apertium machine translation system. The provided tool can currently operate on a subset of the languages that are supported by the Apertium system, namely:  English, Spanish, Calatan, Galician, Portuguese, Romanian and Basque. \nNOTE: The morphological analysis required prior to running the POS tagger MUST be carried out by running the Apertium morphological analyser (which also performs tokeniaation). \n\nThe tool is provided as a UIMA component, specifically as Java archive (jar) file, which can be incorporated within any UIMA workflow. However, it is particularly designed use in the U-Compare text mining plaform (Kano et al., 2009; Kano et al., 2011; see separate META-SHARE record), since the types of annotations it produces are compliant with the U-Compare. \n"
-    ],
-    "oai_identifier": [
-        "7c508aa8bea911e1a404080027e73ea2abb5e2fadb4143b2ae4c15c250af7c78"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "UIMA/U-Compare Apertium POS Tagger "
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c1a93d4b-70ce-548c-8a27-25b2d353cf7d.json b/oaitestdata/clarin-oai_dc/SET_1/json/c1a93d4b-70ce-548c-8a27-25b2d353cf7d.json
deleted file mode 100644
index 4cb57c5b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c1a93d4b-70ce-548c-8a27-25b2d353cf7d.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "UW"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "downloadable_files_count: 10",
-        "application/vnd.oasis.opendocument.text",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/434",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/434"
-    ],
-    "PID": "http://hdl.handle.net/11321/434",
-    "PublicationTimestamp": "2017-10-12T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "UW"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN-EULA-ACA-v1.0",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca",
-        "ACA"
-    ],
-    "author": [
-        "Burkacka, Iwona"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/434;2017-10-12T15:09:23Z;hdl_11321_3;hdl_11321_4;Iwona_korpusiczek;Burkacka, Iwona;aaa;neoglogizmy;2017-10-12;corpus;http://hdl.handle.net/11321/434;polski;CLARIN-EULA-ACA-v1.0;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca;ACA;text/plain; charset=utf-8;text/plain;application/msword;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;text/plain;downloadable_files_count: 10;UW",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c1a93d4b-70ce-548c-8a27-25b2d353cf7d",
-    "notes": [
-        "neoglogizmy"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/434"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "aaa"
-        }
-    ],
-    "title": [
-        "Iwona_korpusiczek"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c1c337d2-e72a-5a64-9e6d-98ff8741ba98.json b/oaitestdata/clarin-oai_dc/SET_1/json/c1c337d2-e72a-5a64-9e6d-98ff8741ba98.json
deleted file mode 100644
index c57964f2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c1c337d2-e72a-5a64-9e6d-98ff8741ba98.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Uppsala University"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/x-gzip",
-        "text/html",
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 9",
-        "application/octet-stream",
-        "application/pdf"
-    ],
-    "Language": [
-        "English",
-        "French"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1611",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1611"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1611",
-    "PublicationTimestamp": "2016-01-30T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Uppsala University"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Hardmeier, Christian",
-        "Stymne, Sara",
-        "Versley, Yannick",
-        "Nakov, Preslav",
-        "Tiedemann, J\u00f6rg"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1611;2017-07-24T13:53:34Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;DiscoMT 2015 Shared Task on Pronoun Translation;Hardmeier, Christian;Tiedemann, J\u00f6rg;Nakov, Preslav;Stymne, Sara;Versley, Yannick;machine translation;coreference resolution;anaphora resolution;discourse;The data set includes training, development and test data from the shared tasks on pronoun-focused machine translation and cross-lingual pronoun prediction from the EMNLP 2015 workshop on Discourse in Machine Translation (DiscoMT2015). The release also contains the submissions to the pronoun-focused machine translation along with the manual annotations used for the official evaluation as well as gold-standard annotations of pronoun coreference for the shared task test set.;2016-01-30;corpus;http://hdl.handle.net/11372/LRT-1611;eng;fra;Creative Commons - Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0);http://creativecommons.org/licenses/by-nc-nd/4.0/;PUB;application/octet-stream;application/pdf;text/html;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 9;Uppsala University;https://www.idiap.ch/workshop/DiscoMT/shared-task",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c1c337d2-e72a-5a64-9e6d-98ff8741ba98",
-    "notes": [
-        "The data set includes training, development and test data from the shared tasks on pronoun-focused machine translation and cross-lingual pronoun prediction from the EMNLP 2015 workshop on Discourse in Machine Translation (DiscoMT2015). The release also contains the submissions to the pronoun-focused machine translation along with the manual annotations used for the official evaluation as well as gold-standard annotations of pronoun coreference for the shared task test set."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1611"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "coreference resolution"
-        },
-        {
-            "name": "anaphora resolution"
-        },
-        {
-            "name": "discourse"
-        }
-    ],
-    "title": [
-        "DiscoMT 2015 Shared Task on Pronoun Translation"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c1ea465a-b7f2-5f1b-b776-c733fdf75243.json b/oaitestdata/clarin-oai_dc/SET_1/json/c1ea465a-b7f2-5f1b-b776-c733fdf75243.json
deleted file mode 100644
index 58bbcedb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c1ea465a-b7f2-5f1b-b776-c733fdf75243.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Nadworna Jego Kr\u00f3lewskiej Mo\u015bci (Warszawa)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-22683",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-22683"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CFF-9",
-    "PublicationTimestamp": "1775-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1775"
-    ],
-    "Publisher": [
-        "Drukarnia Nadworna Jego Kr\u00f3lewskiej Mo\u015bci (Warszawa)"
-    ],
-    "RelatedIdentifier": [
-        "http://rcin.org.pl/Content/22683",
-        "oai:rcin.org.pl:publication:41549"
-    ],
-    "ResourceType": [
-        "Text",
-        "Early printed book (1501-1800)"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "author": [
-        "Poniatowski, Micha\u0142 Jerzy (1736-1794)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-22683;2019-03-01T11:18:03Z;List Pasterski Jasnie Oswieconego [...] Micha\u0142a Jerzego Cio\u0142ka Poniatowskiego Biskupa P\u0142ockiego, Xi\u0105z\u0119cia Pu\u0142tuskiego [...] Do Oboyga Stanu Tak Duchownego, Jako I Swieckiego Diecezyi Swoiey Roku Panskiego 1775. [...] Wydany;Poniatowski, Micha\u0142 Jerzy (1736-1794);Pastorals letters and charges - 18th c.;Pod tekstem data: Dan w Warszawie dnia 20. miesi\u0105ca Sierpnia roku 1775;94 s., [3] k. ; 4\u00b0;Estr. XV-XVIII, 25, 8;Przypisy w j\u0119z. \u0142ac.;Drukarnia Nadworna Jego Kr\u00f3lewskiej Mo\u015bci (Warszawa);[post 20 VIII 1775];Text;Early printed book (1501-1800);application/xml;clarind-uds:poldilemma-22683;hdl:11858/00-246C-0000-0023-8CFF-9;IBL PAN, call no. XVIII.2.175;http://katalog.pan.pl/webpac-bin/233biblitEN/wgbroker.exe?new+-access+top+search+open+NR+xx002729478;pol;lat;http://rcin.org.pl/Content/22683;oai:rcin.org.pl:publication:41549;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c1ea465a-b7f2-5f1b-b776-c733fdf75243",
-    "notes": [
-        "Pod tekstem data: Dan w Warszawie dnia 20. miesi\u0105ca Sierpnia roku 1775",
-        "94 s., [3] k. ; 4\u00b0",
-        "Estr. XV-XVIII, 25, 8",
-        "Przypisy w j\u0119z. \u0142ac."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-22683"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Pastorals letters charges - th c."
-        }
-    ],
-    "title": [
-        "List Pasterski Jasnie Oswieconego [...] Micha\u0142a Jerzego Cio\u0142ka Poniatowskiego Biskupa P\u0142ockiego, Xi\u0105z\u0119cia Pu\u0142tuskiego [...] Do Oboyga Stanu Tak Duchownego, Jako I Swieckiego Diecezyi Swoiey Roku Panskiego 1775. [...] Wydany"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c2091b1e-2322-5635-8121-d9eab59e5aac.json b/oaitestdata/clarin-oai_dc/SET_1/json/c2091b1e-2322-5635-8121-d9eab59e5aac.json
deleted file mode 100644
index b0781887..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c2091b1e-2322-5635-8121-d9eab59e5aac.json
+++ /dev/null
@@ -1,136 +0,0 @@
-{
-    "Contact": [
-        "Technische Universit\u00e4t Darmstadt"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/x-gzip",
-        "downloadable_files_count: 59",
-        "text/plain"
-    ],
-    "Language": [
-        "Afrikaans",
-        "Arabic",
-        "Bengali",
-        "Bulgarian",
-        "Czech",
-        "Danish",
-        "German",
-        "Modern Greek (1453-)",
-        "English",
-        "Estonian",
-        "Persian",
-        "Finnish",
-        "French",
-        "Gujarati",
-        "Hebrew",
-        "Hindi",
-        "Croatian",
-        "Hungarian",
-        "Indonesian",
-        "Italian",
-        "Japanese",
-        "Kannada",
-        "Korean",
-        "Latvian",
-        "Lithuanian",
-        "Malayalam",
-        "Marathi",
-        "Macedonian",
-        "Nepali (macrolanguage)",
-        "Dutch",
-        "Norwegian",
-        "Panjabi",
-        "Polish",
-        "Portuguese",
-        "Romanian",
-        "Russian",
-        "Slovak",
-        "Slovenian",
-        "Somali",
-        "Spanish",
-        "Albanian",
-        "Swahili (macrolanguage)",
-        "Swedish",
-        "Tamil",
-        "Telugu",
-        "Tagalog",
-        "Thai",
-        "Turkish",
-        "Ukrainian",
-        "Undetermined",
-        "Urdu",
-        "Vietnamese",
-        "Chinese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2203",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2203"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2203",
-    "PublicationTimestamp": "2016-04-14T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Technische Universit\u00e4t Darmstadt"
-    ],
-    "RelatedIdentifier": [
-        "http://www.lrec-conf.org/proceedings/lrec2016/pdf/388_Paper.pdf"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "Habernal, Ivan",
-        "Gurevych, Iryna",
-        "Zayed, Omnia"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2203;2019-01-02T14:30:02Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;C4Corpus (CC-BY part);Gurevych, Iryna;Habernal, Ivan;Zayed, Omnia;CommonCrawl;Creative Commons;Web corpus;Amazon Web Services;A large web corpus (over 10 billion tokens) licensed under CreativeCommons license family in 50+ languages that has been extracted from CommonCrawl, the largest publicly available general Web crawl to date with about 2 billion crawled URLs.;2016-04-14;corpus;http://hdl.handle.net/11372/LRT-2203;afr;ara;ben;bul;ces;dan;deu;ell;eng;est;fas;fin;fra;guj;heb;hin;hrv;hun;ind;ita;jpn;kan;kor;lav;lit;mal;mar;mkd;nep;nld;nor;pan;pol;por;ron;rus;slk;slv;som;spa;sqi;swa;swe;tam;tel;tgl;tha;tur;ukr;und;urd;vie;zho;http://www.lrec-conf.org/proceedings/lrec2016/pdf/388_Paper.pdf;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;http://creativecommons.org/licenses/by/4.0/;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;text/plain;downloadable_files_count: 59;Technische Universit\u00e4t Darmstadt;https://dkpro.github.io/dkpro-c4corpus/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c2091b1e-2322-5635-8121-d9eab59e5aac",
-    "notes": [
-        "A large web corpus (over 10 billion tokens) licensed under CreativeCommons license family in 50+ languages that has been extracted from CommonCrawl, the largest publicly available general Web crawl to date with about 2 billion crawled URLs."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2203"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "CommonCrawl"
-        },
-        {
-            "name": "Creative Commons"
-        },
-        {
-            "name": "Web corpus"
-        },
-        {
-            "name": "Amazon Web Services"
-        }
-    ],
-    "title": [
-        "C4Corpus (CC-BY part)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c20c913f-f20d-5ccf-accf-6ba1df1c8add.json b/oaitestdata/clarin-oai_dc/SET_1/json/c20c913f-f20d-5ccf-accf-6ba1df1c8add.json
deleted file mode 100644
index 5aeac30d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c20c913f-f20d-5ccf-accf-6ba1df1c8add.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4079",
-    "MetadataAccess": [
-        "oai:ota:oucs:4079"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gray, Thomas, 1716-1771."
-    ],
-    "fulltext": "oai:ota:oucs:4079;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4079.xml;Ode performed in the Senate-House at Cambridge, July 1, 1769: installation of His Grace Augustus-Henry Fitzroy, Duke of Grafton, Chancellor of the University. Set to music by Dr. Randal, ...;Gray, Thomas, 1716-1771.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c20c913f-f20d-5ccf-accf-6ba1df1c8add",
-    "oai_identifier": [
-        "oai:ota:oucs:4079"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Ode performed in the Senate-House at Cambridge, July 1, 1769: installation of His Grace Augustus-Henry Fitzroy, Duke of Grafton, Chancellor of the University. Set to music by Dr. Randal, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4079.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c21c41e6-f514-5f42-a812-e87d7981abf8.json b/oaitestdata/clarin-oai_dc/SET_1/json/c21c41e6-f514-5f42-a812-e87d7981abf8.json
deleted file mode 100644
index 5db46e55..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c21c41e6-f514-5f42-a812-e87d7981abf8.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1042",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1042"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1042",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1042;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;L2 Acquisition Heide Wegener;Language Acquisition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1042;deu;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI580076%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c21c41e6-f514-5f42-a812-e87d7981abf8",
-    "notes": [
-        "Language Acquisition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1042"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "L2 Acquisition Heide Wegener"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c21ffa6a-da40-55e3-a854-2046fa960567.json b/oaitestdata/clarin-oai_dc/SET_1/json/c21ffa6a-da40-55e3-a854-2046fa960567.json
deleted file mode 100644
index d1aea4ff..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c21ffa6a-da40-55e3-a854-2046fa960567.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/38",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/38"
-    ],
-    "PID": "http://hdl.handle.net/11321/38",
-    "PublicationTimestamp": "2011-04-20T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "K\u0119dzia, Pawe\u0142",
-        "Maziarz, Marek",
-        "Marci\u0144czuk, Micha\u0142",
-        "Naskr\u0119t, Tomasz",
-        "Wardy\u0144ski, Adam",
-        "Radziszewski, Adam",
-        "Ramocki, Rados\u0142aw",
-        "Piasecki, Maciej"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/38;2016-01-21T14:27:43Z;hdl_11321_3;hdl_11321_4;WordnetLoom;Piasecki, Maciej;Marci\u0144czuk, Micha\u0142;Ramocki, Rados\u0142aw;Maziarz, Marek;Radziszewski, Adam;Wardy\u0144ski, Adam;K\u0119dzia, Pawe\u0142;Naskr\u0119t, Tomasz;WordnetLoom \u2013 is an wordnet editor application built for the needs of the construction of a the largest Polish wordnet called plWordNet. WordnetLoom provides two means of interaction: a form-based, implemented initially, and a visual, graph-based introduced recently. The visual, graph-based interactive presentation of the wordnet structure enables browsing and its direct editing on the structure of lexico-semantic relations and synsets. WordnetLooms works in a distributed environment, i.e. several linguists can work simulanuously from different sites on the same central database.;2011-04-20;toolService;http://hdl.handle.net/11321/38;pol;downloadable_files_count: 0;Wroc\u0142aw University of Technology;http://nlp.pwr.wroc.pl/pl/narzedzia-i-zasoby/wordnetloom",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c21ffa6a-da40-55e3-a854-2046fa960567",
-    "notes": [
-        "WordnetLoom \u2013 is an wordnet editor application built for the needs of the construction of a the largest Polish wordnet called plWordNet. WordnetLoom provides two means of interaction: a form-based, implemented initially, and a visual, graph-based introduced recently. The visual, graph-based interactive presentation of the wordnet structure enables browsing and its direct editing on the structure of lexico-semantic relations and synsets. WordnetLooms works in a distributed environment, i.e. several linguists can work simulanuously from different sites on the same central database."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/38"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "WordnetLoom"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c231b9c4-54e4-5f41-86c0-23895cecd15f.json b/oaitestdata/clarin-oai_dc/SET_1/json/c231b9c4-54e4-5f41-86c0-23895cecd15f.json
deleted file mode 100644
index d56e8a3c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c231b9c4-54e4-5f41-86c0-23895cecd15f.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/305",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/305"
-    ],
-    "PID": "http://hdl.handle.net/11321/305",
-    "PublicationTimestamp": "2016-04-25T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0)",
-        "http://creativecommons.org/licenses/by-sa/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Podbielska, Ma\u0142gorzata",
-        "K\u0119dzia, Pawe\u0142",
-        "Turek, Agnieszka",
-        "Wolski, Micha\u0142",
-        "Oleksy, Marcin",
-        "Fikus, Dominika"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/305;2016-06-07T11:36:22Z;hdl_11321_3;hdl_11321_4;WUT Relations Between Sentences Corpus;Oleksy, Marcin;Fikus, Dominika;Wolski, Micha\u0142;Podbielska, Ma\u0142gorzata;Turek, Agnieszka;K\u0119dzia, Pawe\u0142;corpus;discourse analysis;textual entailment;semantic relations;WUT Relations Between Sentences Corpus contains 2827 pairs of related sentences. Relationships are derived from Cross-document Structure Theory (CST), which enables multi-document summarization through identification of cross-document rhetorical relationships within a cluster of related documents.  Every relation was marked by at least 3 annotators.;2016-04-25;corpus;http://hdl.handle.net/11321/305;pol;Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0);http://creativecommons.org/licenses/by-sa/3.0/;CC;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 1;Wroc\u0142aw University of Technology;http://clarin-pl.eu/en/home-page/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c231b9c4-54e4-5f41-86c0-23895cecd15f",
-    "notes": [
-        "WUT Relations Between Sentences Corpus contains 2827 pairs of related sentences. Relationships are derived from Cross-document Structure Theory (CST), which enables multi-document summarization through identification of cross-document rhetorical relationships within a cluster of related documents.  Every relation was marked by at least 3 annotators."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/305"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "discourse analysis"
-        },
-        {
-            "name": "textual entailment"
-        },
-        {
-            "name": "semantic relations"
-        }
-    ],
-    "title": [
-        "WUT Relations Between Sentences Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c274d644-5f92-588f-942b-8389fd202f91.json b/oaitestdata/clarin-oai_dc/SET_1/json/c274d644-5f92-588f-942b-8389fd202f91.json
deleted file mode 100644
index dd273b57..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c274d644-5f92-588f-942b-8389fd202f91.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contributor": [
-        "Borin, Lars"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Faroese",
-        "Icelandic",
-        "Spanish",
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-211",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-211"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-211",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Sweden"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-211;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Spr\u00e5kbanken (Swedish Language Bank);Borin, Lars;Mainly written Swedish corpora (all time periods except Runic Swedish; various genres, including learner corpora) and lexicons; some non-Swedish corpora (Faroese, Old Icelandic, Latin, Spanish); Swedish corpora (appr. 200 MW); Swedish lexicons (appr. 220,000 entries total); non-Swedish corpora (appr. 15 MW;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-211;fao;isl;spa;swe;downloadable_files_count: 0;Sweden;http://spraakbanken.gu.se/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c274d644-5f92-588f-942b-8389fd202f91",
-    "notes": [
-        "Mainly written Swedish corpora (all time periods except Runic Swedish; various genres, including learner corpora) and lexicons; some non-Swedish corpora (Faroese, Old Icelandic, Latin, Spanish); Swedish corpora (appr. 200 MW); Swedish lexicons (appr. 220,000 entries total); non-Swedish corpora (appr. 15 MW"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-211"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Spr\u00e5kbanken (Swedish Language Bank)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c2846cc9-688d-533e-a350-a58c47d80094.json b/oaitestdata/clarin-oai_dc/SET_1/json/c2846cc9-688d-533e-a350-a58c47d80094.json
deleted file mode 100644
index 302fd1c8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c2846cc9-688d-533e-a350-a58c47d80094.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5020",
-    "MetadataAccess": [
-        "oai:ota:oucs:5020"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Boreman, Thomas, fl. 1730-1743."
-    ],
-    "fulltext": "oai:ota:oucs:5020;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5020.xml;The history and description of the famous cathedral of St. Paul's, London: [pt.1];Boreman, Thomas, fl. 1730-1743.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c2846cc9-688d-533e-a350-a58c47d80094",
-    "oai_identifier": [
-        "oai:ota:oucs:5020"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The history and description of the famous cathedral of St. Paul's, London: [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5020.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c28b07d3-e51f-5e68-b4cb-fe4411455f3f.json b/oaitestdata/clarin-oai_dc/SET_1/json/c28b07d3-e51f-5e68-b4cb-fe4411455f3f.json
deleted file mode 100644
index c91fa466..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c28b07d3-e51f-5e68-b4cb-fe4411455f3f.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Horton, Tom"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 75 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1510",
-    "MetadataAccess": [
-        "oai:ota:oucs:1510"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Shakespeare, William, 1564-1616"
-    ],
-    "fulltext": "oai:ota:oucs:1510;2018-02-16T10:42:06Z;http://ota.ox.ac.uk/headers/1510.xml;Comedy of errors : [1793] / William Shakespeare;Shakespeare, William, 1564-1616;text_and_corpus_linguistics;English drama -- Early modern and Elizabethan, 1500-1600;Oxford Text Archive, University of Oxford;Horton, Tom;(1 file : ca. 75 KB);Text;Plays;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c28b07d3-e51f-5e68-b4cb-fe4411455f3f",
-    "oai_identifier": [
-        "oai:ota:oucs:1510"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- Early modern Elizabethan"
-        }
-    ],
-    "title": [
-        "Comedy of errors : [1793] / William Shakespeare"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1510.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c2920e3e-7879-5e49-a339-861124d0846a.json b/oaitestdata/clarin-oai_dc/SET_1/json/c2920e3e-7879-5e49-a339-861124d0846a.json
deleted file mode 100644
index f475f187..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c2920e3e-7879-5e49-a339-861124d0846a.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "less than 512 KB"
-    ],
-    "Language": [
-        "Middle Irish (900-1200)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0625",
-    "MetadataAccess": [
-        "oai:ota:oucs:0625"
-    ],
-    "PublicationYear": [
-        "unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Sermons"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:0625;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0625.xml;Seanm\u00c3\u00b3nta Ch\u00c3\u00baige Uladh / compiled by D.D. Devlin;unknown;text_and_corpus_linguistics;Sermons -- Ireland -- 14th century;mga;Oxford Text Archive, University of Oxford;less than 512 KB;Text;Sermons;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c2920e3e-7879-5e49-a339-861124d0846a",
-    "oai_identifier": [
-        "oai:ota:oucs:0625"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Sermons -- Ireland -- th century"
-        }
-    ],
-    "title": [
-        "Seanm\u00c3\u00b3nta Ch\u00c3\u00baige Uladh / compiled by D.D. Devlin"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0625.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c2a87178-5d0c-5acf-8d6f-2b4743067848.json b/oaitestdata/clarin-oai_dc/SET_1/json/c2a87178-5d0c-5acf-8d6f-2b4743067848.json
deleted file mode 100644
index a3a671b8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c2a87178-5d0c-5acf-8d6f-2b4743067848.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Arts, University of Ljubljana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1172",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1172"
-    ],
-    "PID": "http://hdl.handle.net/11356/1172",
-    "PublicationTimestamp": "2018-01-17T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Faculty of Arts, University of Ljubljana"
-    ],
-    "RelatedIdentifier": [
-        "http://www.sdjt.si/wp/wp-content/uploads/2016/09/JTDH-2016_Gantar-et-al_Slovar-tviterscine.pdf",
-        "http://nl.ijs.si/janes/viri/slovarcek-tviterscine/"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "https://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u0160krjanec, Iza",
-        "Erjavec, Toma\u017e",
-        "Fi\u0161er, Darja",
-        "Gantar, Polona"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1172;2018-02-16T13:58:06Z;hdl_11356_1023;hdl_11356_1024;Dictionary of Twitterese Janes-Dict 1.0;Gantar, Polona;\u0160krjanec, Iza;Fi\u0161er, Darja;Erjavec, Toma\u017e;dictionary;Twitter;The Dictionary of Twitterese 1.0 is the first attempt at a lexicographic description of non-standard Slovene as found on Twitter. Version 1.0 contains 1,002 entries, of which 499 were generated automatically, while 503 have manually added fields, in particular the definition, various labels, variant spellings, and selected examples of use.;2018-01-17;lexicalConceptualResource;http://hdl.handle.net/11356/1172;slv;http://www.sdjt.si/wp/wp-content/uploads/2016/09/JTDH-2016_Gantar-et-al_Slovar-tviterscine.pdf;http://nl.ijs.si/janes/viri/slovarcek-tviterscine/;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);https://creativecommons.org/licenses/by-sa/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Faculty of Arts, University of Ljubljana;http://nl.ijs.si/janes/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c2a87178-5d0c-5acf-8d6f-2b4743067848",
-    "notes": [
-        "The Dictionary of Twitterese 1.0 is the first attempt at a lexicographic description of non-standard Slovene as found on Twitter. Version 1.0 contains 1,002 entries, of which 499 were generated automatically, while 503 have manually added fields, in particular the definition, various labels, variant spellings, and selected examples of use."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1172"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "dictionary"
-        },
-        {
-            "name": "Twitter"
-        }
-    ],
-    "title": [
-        "Dictionary of Twitterese Janes-Dict 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c2aef578-416c-55f3-95c6-1ea57a791e16.json b/oaitestdata/clarin-oai_dc/SET_1/json/c2aef578-416c-55f3-95c6-1ea57a791e16.json
deleted file mode 100644
index 9b49ea9d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c2aef578-416c-55f3-95c6-1ea57a791e16.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "University of Western Bohemia, Pilsen",
-        "Charles University"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1364",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1364"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1364",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Western Bohemia, Pilsen",
-        "Charles University"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Czech Republic"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1364;2017-11-09T14:21:28Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TrEdVoice;The TrEdVoice module is designed to be TrEd annotation editor accessories enabling the voice control of its functions.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1364;downloadable_files_count: 0;Czech Republic;University of Western Bohemia, Pilsen;Charles University;http://ufal.mff.cuni.cz/rest/CAC/cac_20.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c2aef578-416c-55f3-95c6-1ea57a791e16",
-    "notes": [
-        "The TrEdVoice module is designed to be TrEd annotation editor accessories enabling the voice control of its functions."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1364"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TrEdVoice"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c33ceb89-e2f8-5477-bf35-59660100142c.json b/oaitestdata/clarin-oai_dc/SET_1/json/c33ceb89-e2f8-5477-bf35-59660100142c.json
deleted file mode 100644
index 6ef7a5b2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c33ceb89-e2f8-5477-bf35-59660100142c.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "French"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1033",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1033"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1033",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1033;2016-04-06T16:39:56Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;L1 Acquisition Gaby Cablitz;Language Acquisition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1033;fra;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI9850%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c33ceb89-e2f8-5477-bf35-59660100142c",
-    "notes": [
-        "Language Acquisition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1033"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "L1 Acquisition Gaby Cablitz"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c33cf55c-2036-5896-9ac3-f12aeec91733.json b/oaitestdata/clarin-oai_dc/SET_1/json/c33cf55c-2036-5896-9ac3-f12aeec91733.json
deleted file mode 100644
index e0ae5da8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c33cf55c-2036-5896-9ac3-f12aeec91733.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-655",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-655"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-655",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Code of conduct"
-    ],
-    "SpatialCoverage": [
-        "Papua New Guinea"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-655;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Teop;corpus browser;Documentation of the Teop project (DoBeS project);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-655;Code of conduct;downloadable_files_count: 0;Papua New Guinea;https://corpus1.mpi.nl/ds/asv/?1&openpath=node:318963",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c33cf55c-2036-5896-9ac3-f12aeec91733",
-    "notes": [
-        "Documentation of the Teop project (DoBeS project)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-655"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus browser"
-        }
-    ],
-    "title": [
-        "Teop"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c356f87d-a592-537e-8f89-12f84573d95c.json b/oaitestdata/clarin-oai_dc/SET_1/json/c356f87d-a592-537e-8f89-12f84573d95c.json
deleted file mode 100644
index aaea1c14..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c356f87d-a592-537e-8f89-12f84573d95c.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "PWR Test",
-        "Wro"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/239",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/239"
-    ],
-    "PID": "http://hdl.handle.net/11321/239",
-    "PublicationTimestamp": "2015-10-22T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "PWR Test",
-        "Wro"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Tomasz, Naskr\u0119t",
-        "t"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/239;2016-01-25T11:07:40Z;hdl_11321_3;hdl_11321_4;Test cmdi;Tomasz, Naskr\u0119t;t;test;test;2015-10-22;corpus;http://hdl.handle.net/11321/239;pol;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;text/plain; charset=utf-8;text/plain;downloadable_files_count: 1;PWR Test;Wro",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c356f87d-a592-537e-8f89-12f84573d95c",
-    "notes": [
-        "test"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/239"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "test"
-        }
-    ],
-    "title": [
-        "Test cmdi"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c35832a7-6b82-5909-9237-a90faf477555.json b/oaitestdata/clarin-oai_dc/SET_1/json/c35832a7-6b82-5909-9237-a90faf477555.json
deleted file mode 100644
index 7e9fe858..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c35832a7-6b82-5909-9237-a90faf477555.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain",
-        "(1 file : ca. 201 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2027",
-    "MetadataAccess": [
-        "oai:ota:oucs:2027"
-    ],
-    "PublicationTimestamp": "1759-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1759"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Voltaire, 1694-1778"
-    ],
-    "fulltext": "oai:ota:oucs:2027;2018-03-01T12:27:15Z;http://ota.ox.ac.uk/headers/2027.xml;Candide. English;Candide / by Voltaire;Voltaire, 1694-1778;1759;text_and_corpus_linguistics;Fiction;Novels;Translations;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 201 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c35832a7-6b82-5909-9237-a90faf477555",
-    "oai_identifier": [
-        "oai:ota:oucs:2027"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction"
-        },
-        {
-            "name": "Novels"
-        },
-        {
-            "name": "Translations"
-        }
-    ],
-    "title": [
-        "Candide. English",
-        "Candide / by Voltaire"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2027.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c35f634a-c6f5-5a93-a127-957f5a92aee6.json b/oaitestdata/clarin-oai_dc/SET_1/json/c35f634a-c6f5-5a93-a127-957f5a92aee6.json
deleted file mode 100644
index 95e85e69..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c35f634a-c6f5-5a93-a127-957f5a92aee6.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "Filesize uncompressed: 130 KBytes. "
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2124",
-    "MetadataAccess": [
-        "oai:ota:oucs:2124"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Crane, Stephen, 1871-1900"
-    ],
-    "fulltext": "oai:ota:oucs:2124;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/2124.xml;Maggie: A Girl of the Streets;A machine-readable transcription;Crane, Stephen, 1871-1900;text_and_corpus_linguistics;Oxford Text Archive, University of Oxford;Filesize uncompressed: 130 KBytes. ;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c35f634a-c6f5-5a93-a127-957f5a92aee6",
-    "oai_identifier": [
-        "oai:ota:oucs:2124"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Maggie: A Girl of the Streets",
-        "A machine-readable transcription"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2124.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c3c94250-75f1-572d-8b31-92bfdec50e80.json b/oaitestdata/clarin-oai_dc/SET_1/json/c3c94250-75f1-572d-8b31-92bfdec50e80.json
deleted file mode 100644
index 3ba0992d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c3c94250-75f1-572d-8b31-92bfdec50e80.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Department of Linguistics and Nordic Studies, University of Oslo"
-    ],
-    "Contributor": [
-        "N\u00f8klestad, Anders"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Norwegian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-668",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-668"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-668",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Department of Linguistics and Nordic Studies, University of Oslo"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Norway"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-668;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;NoTa tagger;N\u00f8klestad, Anders;Statistical tagger for Norwegian spoken language;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-668;nor;downloadable_files_count: 0;Norway;Department of Linguistics and Nordic Studies, University of Oslo;http://www.tekstlab.uio.no/nota/oslo/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c3c94250-75f1-572d-8b31-92bfdec50e80",
-    "notes": [
-        "Statistical tagger for Norwegian spoken language"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-668"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "NoTa tagger"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c3d0bee8-7c34-5893-887d-cff3389f87a0.json b/oaitestdata/clarin-oai_dc/SET_1/json/c3d0bee8-7c34-5893-887d-cff3389f87a0.json
deleted file mode 100644
index 44054841..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c3d0bee8-7c34-5893-887d-cff3389f87a0.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Institute of Mathematics and Computer Science, University of Latvia"
-    ],
-    "Contributor": [
-        "Pinnis, M\u0101rcis",
-        "R\u0101bante, Guna",
-        "Gr\u016bz\u012btis, Normunds",
-        "Spektors, Andrejs"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Latvian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-276",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-276"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-276",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institute of Mathematics and Computer Science, University of Latvia"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Latvia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-276;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Morphological analyzer/synthesizer of the standard Latvian language;Pinnis, M\u0101rcis;R\u0101bante, Guna;Gr\u016bz\u012btis, Normunds;Spektors, Andrejs;A standards compliant RESTful web service, based on the lexicon of the Dictionary of the Standard Latvian Language. The morphological database contains 57 613 lemmas (1 332 889 word forms).;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-276;lav;downloadable_files_count: 0;Latvia;Institute of Mathematics and Computer Science, University of Latvia;http://valoda.ailab.lv/ws/morph.jsp",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c3d0bee8-7c34-5893-887d-cff3389f87a0",
-    "notes": [
-        "A standards compliant RESTful web service, based on the lexicon of the Dictionary of the Standard Latvian Language. The morphological database contains 57 613 lemmas (1 332 889 word forms)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-276"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Morphological analyzer/synthesizer of the standard Latvian language"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c3de7cce-1db4-5ca2-b98a-fc7b15500765.json b/oaitestdata/clarin-oai_dc/SET_1/json/c3de7cce-1db4-5ca2-b98a-fc7b15500765.json
deleted file mode 100644
index 0e1c2655..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c3de7cce-1db4-5ca2-b98a-fc7b15500765.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Clarin-PL"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/plain",
-        "downloadable_files_count: 4"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/630",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/630"
-    ],
-    "PID": "http://hdl.handle.net/11321/630",
-    "PublicationTimestamp": "2019-03-11T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Clarin-PL"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "plWordNet",
-        "http://clarin-pl.eu/en/licenses/plwordnet-2/",
-        "PUB"
-    ],
-    "author": [
-        "Rauk Wojciech"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/630;2019-03-11T16:39:57Z;hdl_11321_3;hdl_11321_4;EWBST tests for english;Rauk Wojciech;ewbst;word embeddings;testing;Submission contains test generated for EWBST test of English word embedding models.\r\nTests were created with princeton wordnet and plWN english synsts.;2019-03-11;toolService;http://hdl.handle.net/11321/630;eng;plWordNet;http://clarin-pl.eu/en/licenses/plwordnet-2/;PUB;text/plain; charset=utf-8;text/plain;text/plain;text/plain;text/plain;downloadable_files_count: 4;Clarin-PL",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c3de7cce-1db4-5ca2-b98a-fc7b15500765",
-    "notes": [
-        "Submission contains test generated for EWBST test of English word embedding models.\r\nTests were created with princeton wordnet and plWN english synsts."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/630"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ewbst"
-        },
-        {
-            "name": "word embeddings"
-        },
-        {
-            "name": "testing"
-        }
-    ],
-    "title": [
-        "EWBST tests for english"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c3e9e819-159c-5652-b6bb-cf630c8e42ce.json b/oaitestdata/clarin-oai_dc/SET_1/json/c3e9e819-159c-5652-b6bb-cf630c8e42ce.json
deleted file mode 100644
index 2e991121..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c3e9e819-159c-5652-b6bb-cf630c8e42ce.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Micha\u0142 Marci\u0144czuk"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/48",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/48"
-    ],
-    "PID": "http://hdl.handle.net/11321/48",
-    "PublicationTimestamp": "2014-11-24T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Micha\u0142 Marci\u0144czuk"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Piasecki, Dominik",
-        "Janicki, Maciej",
-        "Marci\u0144czuk, Micha\u0142",
-        "Krautforst, Micha\u0142",
-        "Koco\u0144, Jan"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/48;2014-11-26T11:13:39Z;hdl_11321_3;hdl_11321_4;Liner2.4;Marci\u0144czuk, Micha\u0142;Krautforst, Micha\u0142;Koco\u0144, Jan;Piasecki, Dominik;Janicki, Maciej;named entity recognition;text processing;text annotation;A framework for multitask sequence labeling dedicated for natural language processing tasks.;2014-11-24;toolService;http://hdl.handle.net/11321/48;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 1;Micha\u0142 Marci\u0144czuk;http://nlp.pwr.wroc.pl/liner2",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c3e9e819-159c-5652-b6bb-cf630c8e42ce",
-    "notes": [
-        "A framework for multitask sequence labeling dedicated for natural language processing tasks."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/48"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "named entity recognition"
-        },
-        {
-            "name": "text processing"
-        },
-        {
-            "name": "text annotation"
-        }
-    ],
-    "title": [
-        "Liner2.4"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c3eabdf7-eb62-576d-8aaa-345b67eb3db7.json b/oaitestdata/clarin-oai_dc/SET_1/json/c3eabdf7-eb62-576d-8aaa-345b67eb3db7.json
deleted file mode 100644
index 94a27990..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c3eabdf7-eb62-576d-8aaa-345b67eb3db7.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Estonian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-195",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-195"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-195",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Estonia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-195;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Arborest;149 sentences, VISL tagset;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-195;est;downloadable_files_count: 0;Estonia;http://corp.hum.sdu.dk/arborest.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c3eabdf7-eb62-576d-8aaa-345b67eb3db7",
-    "notes": [
-        "149 sentences, VISL tagset"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-195"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Arborest"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c3fc8b3f-7cd1-53b6-8210-207c7731e153.json b/oaitestdata/clarin-oai_dc/SET_1/json/c3fc8b3f-7cd1-53b6-8210-207c7731e153.json
deleted file mode 100644
index 907f323e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c3fc8b3f-7cd1-53b6-8210-207c7731e153.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Ibis"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 37",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/604",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/604"
-    ],
-    "PID": "http://hdl.handle.net/11321/604",
-    "PublicationTimestamp": "2018-09-18T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Ibis"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "plWordNet",
-        "http://clarin-pl.eu/en/licenses/plwordnet-2/",
-        "PUB"
-    ],
-    "author": [
-        "Koz\u0142owska, Zuzanna"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/604;2018-09-21T09:47:38Z;hdl_11321_3;hdl_11321_4;POE: Microcorpus of 20th century Polish poetry;Koz\u0142owska, Zuzanna;poezja;XX wiek;polska poezja;Microcorpus of 20th century Polish poetry;2018-09-18;corpus;http://hdl.handle.net/11321/604;pol;plWordNet;http://clarin-pl.eu/en/licenses/plwordnet-2/;PUB;text/plain; charset=utf-8;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;downloadable_files_count: 37;Ibis;httpxyz",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c3fc8b3f-7cd1-53b6-8210-207c7731e153",
-    "notes": [
-        "Microcorpus of 20th century Polish poetry"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/604"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "poezja"
-        },
-        {
-            "name": "XX wiek"
-        },
-        {
-            "name": "polska poezja"
-        }
-    ],
-    "title": [
-        "POE: Microcorpus of 20th century Polish poetry"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c41cee03-e8bf-5c93-8981-8ee4ca40d3c8.json b/oaitestdata/clarin-oai_dc/SET_1/json/c41cee03-e8bf-5c93-8981-8ee4ca40d3c8.json
deleted file mode 100644
index 5c0a309a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c41cee03-e8bf-5c93-8981-8ee4ca40d3c8.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5565",
-    "MetadataAccess": [
-        "oai:ota:oucs:5565"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Lettsom, John Coakley, 1744-1815."
-    ],
-    "fulltext": "oai:ota:oucs:5565;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5565.xml;History of some of the effects of hard drinking: The sixth edition. By J. C. Lettsom, ...;Lettsom, John Coakley, 1744-1815.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c41cee03-e8bf-5c93-8981-8ee4ca40d3c8",
-    "oai_identifier": [
-        "oai:ota:oucs:5565"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "History of some of the effects of hard drinking: The sixth edition. By J. C. Lettsom, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5565.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c433c950-0d51-5507-bd1d-84a171fdd1a7.json b/oaitestdata/clarin-oai_dc/SET_1/json/c433c950-0d51-5507-bd1d-84a171fdd1a7.json
deleted file mode 100644
index 56f4453e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c433c950-0d51-5507-bd1d-84a171fdd1a7.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Arts, University of Ljubljana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Japanese",
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1050",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1050"
-    ],
-    "PID": "http://hdl.handle.net/11356/1050",
-    "PublicationTimestamp": "2016-01-30T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Faculty of Arts, University of Ljubljana"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "https://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Srdanovi\u0107, Irena",
-        "Erjavec, Toma\u017e",
-        "Hmeljak, Kristina"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1050;2018-05-28T11:30:55Z;hdl_11356_1023;hdl_11356_1024;Japanese-Slovene learner's dictionary jaSlo 3.1;Hmeljak, Kristina;Erjavec, Toma\u017e;Srdanovi\u0107, Irena;dictionary;difficulty level;TEI;multilingual;The jaSlo dictionary is primarily intended for Slovene students learning Japanese. For each entry, it contains the Japanese headword (kanji, hiragana or katakana, and romaji), its part-of-speech and difficulty level, Slovene language gloss, Slovene translation equivalents, and translated examples of use.;2016-01-30;lexicalConceptualResource;http://hdl.handle.net/11356/1050;jpn;slv;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);https://creativecommons.org/licenses/by-sa/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Faculty of Arts, University of Ljubljana;http://nl.ijs.si/jaslo/index-en.html#jaslo",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c433c950-0d51-5507-bd1d-84a171fdd1a7",
-    "notes": [
-        "The jaSlo dictionary is primarily intended for Slovene students learning Japanese. For each entry, it contains the Japanese headword (kanji, hiragana or katakana, and romaji), its part-of-speech and difficulty level, Slovene language gloss, Slovene translation equivalents, and translated examples of use."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1050"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "dictionary"
-        },
-        {
-            "name": "difficulty level"
-        },
-        {
-            "name": "TEI"
-        },
-        {
-            "name": "multilingual"
-        }
-    ],
-    "title": [
-        "Japanese-Slovene learner's dictionary jaSlo 3.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c46f9c53-ef99-564b-b5d9-26fc8f6e9bf7.json b/oaitestdata/clarin-oai_dc/SET_1/json/c46f9c53-ef99-564b-b5d9-26fc8f6e9bf7.json
deleted file mode 100644
index 5762bab9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c46f9c53-ef99-564b-b5d9-26fc8f6e9bf7.json
+++ /dev/null
@@ -1,286 +0,0 @@
-{
-    "Contact": [
-        "Universal Dependencies Consortium"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 3"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)",
-        "Arabic",
-        "Basque",
-        "Bulgarian",
-        "Croatian",
-        "Czech",
-        "Danish",
-        "Dutch",
-        "English",
-        "Estonian",
-        "Finnish",
-        "French",
-        "German",
-        "Gothic",
-        "Modern Greek (1453-)",
-        "Hebrew",
-        "Hindi",
-        "Hungarian",
-        "Indonesian",
-        "Irish",
-        "Italian",
-        "Japanese",
-        "Latin",
-        "Norwegian",
-        "Church Slavic",
-        "Persian",
-        "Polish",
-        "Portuguese",
-        "Romanian",
-        "Slovenian",
-        "Spanish",
-        "Swedish",
-        "Tamil",
-        "Catalan",
-        "Chinese",
-        "Galician",
-        "Kazakh",
-        "Latvian",
-        "Russian",
-        "Turkish",
-        "Coptic",
-        "Sanskrit",
-        "Slovak",
-        "Ukrainian",
-        "Uighur",
-        "Vietnamese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1827",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1827"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1827",
-    "PublicationTimestamp": "2016-11-15T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Universal Dependencies Consortium"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-1699",
-        "http://hdl.handle.net/11234/1-1983"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Licence Universal Dependencies v1.4",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-1.4",
-        "PUB"
-    ],
-    "author": [
-        "Ion, Radu",
-        "Seraji, Mojgan",
-        "Manning, Christopher",
-        "Cebiro\u011flu Eryi\u011fit, G\u00fcl\u015fen",
-        "Passarotti, Marco",
-        "Nguy\u1ec5n Th\u1ecb, L\u01b0\u01a1ng",
-        "Zhu, Hanzhi",
-        "B\u00f6rstell, Carl",
-        "Agi\u0107, \u017deljko",
-        "Simionescu, Radu",
-        "Muischnek, Kadri",
-        "Washington, Jonathan North",
-        "Katz, Boris",
-        "Davidson, Elizabeth",
-        "Moskalevskyi, Bohdan",
-        "Wang, Jing Xian",
-        "Seeker, Wolfgang",
-        "Berzak, Yevgeni",
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "Irimia, Elena",
-        "Simk\u00f3, Katalin",
-        "Hladk\u00e1, Barbora",
-        "Krek, Simon",
-        "G\u00f6k\u0131rmak, Memduh",
-        "L\u00ea H\u1ed3ng, Ph\u01b0\u01a1ng",
-        "Suhr, Alane",
-        "Galbraith, Daniel",
-        "Lenci, Alessandro",
-        "Martins, Andr\u00e9",
-        "Ginter, Filip",
-        "Mititelu, Verginica",
-        "Erjavec, Toma\u017e",
-        "Bick, Eckhard",
-        "Osenova, Petya",
-        "Mart\u00ednez Alonso, H\u00e9ctor",
-        "Schuster, Sebastian",
-        "Mori, Shunsuke",
-        "Haug, Dag",
-        "Lynn, Teresa",
-        "Plank, Barbara",
-        "Gojenola, Koldo",
-        "Varga, Viktor",
-        "Lyashevskaya, Olga",
-        "J\u00f8rgensen, Fredrik",
-        "M\u0103r\u0103nduc, C\u0103t\u0103lina",
-        "Ka\u015f\u0131kara, H\u00fcner",
-        "Pyysalo, Sampo",
-        "Kanerva, Jenna",
-        "Sz\u00e1nt\u00f3, Zsolt",
-        "Chalub, Fabricio",
-        "Ma\u0161ek, Jan",
-        "Atutxa, Aitziber",
-        "Goldberg, Yoav",
-        "Matsumoto, Yuji",
-        "Dozat, Timothy",
-        "G\u00f3mez Guinovart, Xavier",
-        "M\u00fc\u00fcrisep, Kaili",
-        "Saul\u012bte, Baiba",
-        "Bauer, John",
-        "Piitulainen, Jussi",
-        "Nivre, Joakim",
-        "Prokopidis, Prokopis",
-        "Petrov, Slav",
-        "Guillaume, Bruno",
-        "Gr\u016bz\u012btis, Normunds",
-        "Puolakainen, Tiina",
-        "de Marneffe, Marie-Catherine",
-        "Missil\u00e4, Anna",
-        "Dwivedi, Puneet",
-        "Montemagni, Simonetta",
-        "Makazhanov, Aibek",
-        "McDonald, Ryan",
-        "Lam, Lucia",
-        "Pretkalni\u0146a, Lauma",
-        "Farkas, Rich\u00e1rd",
-        "Ramasamy, Loganathan",
-        "Bosco, Cristina",
-        "Kenney, Jessica",
-        "Eli, Marhaba",
-        "Freitas, Claudia",
-        "Sulubacak, Umut",
-        "Grioni, Matias",
-        "Real, Livy",
-        "Asahara, Masayuki",
-        "Mori, Keiko Sophie",
-        "Zeman, Daniel",
-        "Tanaka, Takaaki",
-        "Miyao, Yusuke",
-        "Vincze, Veronika",
-        "Bhat, Riyaz Ahmad",
-        "Mustafina, Nina",
-        "Garcia, Marcos",
-        "Paiva, Valeria",
-        "Nguy\u1ec5n Th\u1ecb Minh, Huy\u1ec1n",
-        "\u0160imkov\u00e1, M\u00e1ria",
-        "Wir\u00e9n, Mats",
-        "Tsarfaty, Reut",
-        "Goenaga, Iakes",
-        "Rituma, Laura",
-        "H\u00e0 M\u1ef9, Linh",
-        "Garza, Sebastian",
-        "Johannsen, Anders",
-        "Droganova, Kira",
-        "Shen, Mo",
-        "Connor, Miriam",
-        "Mare\u010dek, David",
-        "Smith, Aaron",
-        "\u00d8vrelid, Lilja",
-        "Gajdo\u0161ov\u00e1, Katar\u00edna",
-        "Spadine, Carolyn",
-        "Celano, Giuseppe G. A.",
-        "Dobrovoljc, Kaja",
-        "Popel, Martin",
-        "Laippala, Veronika",
-        "Simov, Kiril",
-        "Ballesteros, Miguel",
-        "Nurmi, Hanna",
-        "Nikolaev, Vitaly",
-        "Perez, Cenel-Augusto",
-        "Rademaker, Alexandre",
-        "Tyers, Francis",
-        "Ahrenberg, Lars",
-        "Shakurova, Lena",
-        "Diaz de Ilarraza, Arantza",
-        "Rosa, Rudolf",
-        "Aranzabe, Maria Jesus",
-        "Saleh, Shadi",
-        "Simi, Maria",
-        "Bengoetxea, Kepa",
-        "van Noord, Gertjan",
-        "Wallin, Lars",
-        "Zeldes, Amir",
-        "Pascual, Elena",
-        "\u00d6stling, Robert",
-        "Bouma, Gosse",
-        "Foster, Jennifer",
-        "G\u00e4rdenfors, Moa",
-        "\u00c7\u00f6ltekin, \u00c7a\u011fr\u0131",
-        "Uematsu, Sumire",
-        "Gonz\u00e1les Saavedra, Berta",
-        "Uria, Larraitz",
-        "Ljube\u0161i\u0107, Nikola",
-        "Kanayama, Hiroshi",
-        "Haji\u010d, Jan",
-        "Bowman, Sam",
-        "Kotsyba, Natalia",
-        "Silveira, Natalia"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1827;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Universal Dependencies 1.4;Nivre, Joakim;Agi\u0107, \u017deljko;Ahrenberg, Lars;Aranzabe, Maria Jesus;Asahara, Masayuki;Atutxa, Aitziber;Ballesteros, Miguel;Bauer, John;Bengoetxea, Kepa;Berzak, Yevgeni;Bhat, Riyaz Ahmad;Bick, Eckhard;B\u00f6rstell, Carl;Bosco, Cristina;Bouma, Gosse;Bowman, Sam;Cebiro\u011flu Eryi\u011fit, G\u00fcl\u015fen;Celano, Giuseppe G. A.;Chalub, Fabricio;\u00c7\u00f6ltekin, \u00c7a\u011fr\u0131;Connor, Miriam;Davidson, Elizabeth;de Marneffe, Marie-Catherine;Diaz de Ilarraza, Arantza;Dobrovoljc, Kaja;Dozat, Timothy;Droganova, Kira;Dwivedi, Puneet;Eli, Marhaba;Erjavec, Toma\u017e;Farkas, Rich\u00e1rd;Foster, Jennifer;Freitas, Claudia;Gajdo\u0161ov\u00e1, Katar\u00edna;Galbraith, Daniel;Garcia, Marcos;G\u00e4rdenfors, Moa;Garza, Sebastian;Ginter, Filip;Goenaga, Iakes;Gojenola, Koldo;G\u00f6k\u0131rmak, Memduh;Goldberg, Yoav;G\u00f3mez Guinovart, Xavier;Gonz\u00e1les Saavedra, Berta;Grioni, Matias;Gr\u016bz\u012btis, Normunds;Guillaume, Bruno;Haji\u010d, Jan;H\u00e0 M\u1ef9, Linh;Haug, Dag;Hladk\u00e1, Barbora;Ion, Radu;Irimia, Elena;Johannsen, Anders;J\u00f8rgensen, Fredrik;Ka\u015f\u0131kara, H\u00fcner;Kanayama, Hiroshi;Kanerva, Jenna;Katz, Boris;Kenney, Jessica;Kotsyba, Natalia;Krek, Simon;Laippala, Veronika;Lam, Lucia;L\u00ea H\u1ed3ng, Ph\u01b0\u01a1ng;Lenci, Alessandro;Ljube\u0161i\u0107, Nikola;Lyashevskaya, Olga;Lynn, Teresa;Makazhanov, Aibek;Manning, Christopher;M\u0103r\u0103nduc, C\u0103t\u0103lina;Mare\u010dek, David;Mart\u00ednez Alonso, H\u00e9ctor;Martins, Andr\u00e9;Ma\u0161ek, Jan;Matsumoto, Yuji;McDonald, Ryan;Missil\u00e4, Anna;Mititelu, Verginica;Miyao, Yusuke;Montemagni, Simonetta;Mori, Keiko Sophie;Mori, Shunsuke;Moskalevskyi, Bohdan;Muischnek, Kadri;Mustafina, Nina;M\u00fc\u00fcrisep, Kaili;Nguy\u1ec5n Th\u1ecb, L\u01b0\u01a1ng;Nguy\u1ec5n Th\u1ecb Minh, Huy\u1ec1n;Nikolaev, Vitaly;Nurmi, Hanna;Osenova, Petya;\u00d6stling, Robert;\u00d8vrelid, Lilja;Paiva, Valeria;Pascual, Elena;Passarotti, Marco;Perez, Cenel-Augusto;Petrov, Slav;Piitulainen, Jussi;Plank, Barbara;Popel, Martin;Pretkalni\u0146a, Lauma;Prokopidis, Prokopis;Puolakainen, Tiina;Pyysalo, Sampo;Rademaker, Alexandre;Ramasamy, Loganathan;Real, Livy;Rituma, Laura;Rosa, Rudolf;Saleh, Shadi;Saul\u012bte, Baiba;Schuster, Sebastian;Seeker, Wolfgang;Seraji, Mojgan;Shakurova, Lena;Shen, Mo;Silveira, Natalia;Simi, Maria;Simionescu, Radu;Simk\u00f3, Katalin;\u0160imkov\u00e1, M\u00e1ria;Simov, Kiril;Smith, Aaron;Spadine, Carolyn;Suhr, Alane;Sulubacak, Umut;Sz\u00e1nt\u00f3, Zsolt;Tanaka, Takaaki;Tsarfaty, Reut;Tyers, Francis;Uematsu, Sumire;Uria, Larraitz;van Noord, Gertjan;Varga, Viktor;Vincze, Veronika;Wallin, Lars;Wang, Jing Xian;Washington, Jonathan North;Wir\u00e9n, Mats;\u017dabokrtsk\u00fd, Zden\u011bk;Zeldes, Amir;Zeman, Daniel;Zhu, Hanzhi;treebank;dependency;syntax;morphology;harmonized annotation;interset;universal tagset;stanford dependencies;Universal Dependencies is a project that seeks to develop cross-linguistically consistent treebank annotation for many languages, with the goal of facilitating multilingual parser development, cross-lingual learning, and parsing research from a language typology perspective. The annotation scheme is based on (universal) Stanford dependencies (de Marneffe et al., 2006, 2008, 2014), Google universal part-of-speech tags (Petrov et al., 2012), and the Interset interlingua for morphosyntactic tagsets (Zeman, 2008).;2016-11-15;corpus;http://hdl.handle.net/11234/1-1827;grc;ara;eus;bul;hrv;ces;dan;nld;eng;est;fin;fra;deu;got;ell;heb;hin;hun;ind;gle;ita;jpn;lat;nor;chu;fas;pol;por;ron;slv;spa;swe;tam;cat;zho;glg;kaz;lav;rus;tur;cop;san;slk;swl;ukr;uig;vie;http://hdl.handle.net/11234/1-1699;http://hdl.handle.net/11234/1-1983;Licence Universal Dependencies v1.4;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-1.4;PUB;application/x-gzip;application/x-gzip;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 3;Universal Dependencies Consortium;http://universaldependencies.org/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c46f9c53-ef99-564b-b5d9-26fc8f6e9bf7",
-    "notes": [
-        "Universal Dependencies is a project that seeks to develop cross-linguistically consistent treebank annotation for many languages, with the goal of facilitating multilingual parser development, cross-lingual learning, and parsing research from a language typology perspective. The annotation scheme is based on (universal) Stanford dependencies (de Marneffe et al., 2006, 2008, 2014), Google universal part-of-speech tags (Petrov et al., 2012), and the Interset interlingua for morphosyntactic tagsets (Zeman, 2008)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1827"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "dependency"
-        },
-        {
-            "name": "syntax"
-        },
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "harmonized annotation"
-        },
-        {
-            "name": "interset"
-        },
-        {
-            "name": "universal tagset"
-        },
-        {
-            "name": "stanford dependencies"
-        }
-    ],
-    "title": [
-        "Universal Dependencies 1.4"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c4734a54-62c0-571d-a774-3624bc91cc8d.json b/oaitestdata/clarin-oai_dc/SET_1/json/c4734a54-62c0-571d-a774-3624bc91cc8d.json
deleted file mode 100644
index 23745804..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c4734a54-62c0-571d-a774-3624bc91cc8d.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3580",
-    "MetadataAccess": [
-        "oai:ota:oucs:3580"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Griffith, Mrs. (Elizabeth), 1720?-1793."
-    ],
-    "fulltext": "oai:ota:oucs:3580;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3580.xml;The platonic wife: a comedy, as it is performed at the Theatre-Royal in Drury-Lane. By a lady.;Griffith, Mrs. (Elizabeth), 1720?-1793.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c4734a54-62c0-571d-a774-3624bc91cc8d",
-    "oai_identifier": [
-        "oai:ota:oucs:3580"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The platonic wife: a comedy, as it is performed at the Theatre-Royal in Drury-Lane. By a lady."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3580.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c4803a5c-8b66-5ca9-b7e8-23689aa38913.json b/oaitestdata/clarin-oai_dc/SET_1/json/c4803a5c-8b66-5ca9-b7e8-23689aa38913.json
deleted file mode 100644
index ed82e2cd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c4803a5c-8b66-5ca9-b7e8-23689aa38913.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "Georgian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-956",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-956"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-956",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-956;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Modern Georgian;ca. 600.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-956;kat;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#georgmod",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c4803a5c-8b66-5ca9-b7e8-23689aa38913",
-    "notes": [
-        "ca. 600.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-956"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Modern Georgian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c48377aa-06ab-5331-b436-e1091ce93a94.json b/oaitestdata/clarin-oai_dc/SET_1/json/c48377aa-06ab-5331-b436-e1091ce93a94.json
deleted file mode 100644
index 6ead020f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c48377aa-06ab-5331-b436-e1091ce93a94.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Jan Wieczorek"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "downloadable_files_count: 4"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/423",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/423"
-    ],
-    "PID": "http://hdl.handle.net/11321/423",
-    "PublicationTimestamp": "1842-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1842"
-    ],
-    "Publisher": [
-        "Jan Wieczorek"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0)",
-        "http://creativecommons.org/licenses/by-sa/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Kar\u015bnicki, Antoni"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/423;2017-09-14T20:56:32Z;hdl_11321_3;hdl_11321_4;Wyci\u0105g z dziennika powt\u00f3rnej podr\u00f3\u017cy do W\u0142och;Kar\u015bnicki, Antoni;podr\u00f3\u017c;relacja;W\u0142ochy;Italia;Pierwsze siedemna\u015bcie stron relacji podr\u00f3\u017cniczej Antoniego Kar\u015bnickiego - test przed ca\u0142o\u015bci\u0105;1842;corpus;http://hdl.handle.net/11321/423;pol;Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0);http://creativecommons.org/licenses/by-sa/3.0/;CC;text/plain; charset=utf-8;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;downloadable_files_count: 4;Jan Wieczorek",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c48377aa-06ab-5331-b436-e1091ce93a94",
-    "notes": [
-        "Pierwsze siedemna\u015bcie stron relacji podr\u00f3\u017cniczej Antoniego Kar\u015bnickiego - test przed ca\u0142o\u015bci\u0105"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/423"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "relacja"
-        },
-        {
-            "name": "relacja"
-        },
-        {
-            "name": "Italia"
-        }
-    ],
-    "title": [
-        "Wyci\u0105g z dziennika powt\u00f3rnej podr\u00f3\u017cy do W\u0142och"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c4bbec83-36fc-578a-b485-86ec4b573253.json b/oaitestdata/clarin-oai_dc/SET_1/json/c4bbec83-36fc-578a-b485-86ec4b573253.json
deleted file mode 100644
index c31c7b80..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c4bbec83-36fc-578a-b485-86ec4b573253.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 3",
-        "application/octet-stream"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48F7-8",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48F7-8"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-48F7-8",
-    "PublicationTimestamp": "2009-10-13T13:11:11Z",
-    "PublicationYear": [
-        "2009"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU General Public License, version 2",
-        "http://www.gnu.org/licenses/gpl-2.0.html",
-        "PUB"
-    ],
-    "author": [
-        "Pajas, Petr"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48F7-8;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;TrEd;Pajas, Petr;annotation;tree;editor;XML;PML;Tree Editor\r\n\r\nTrEd is a fully customizable and programmable graphical editor and viewer for tree-like structures. Among other projects, it was used as the main annotation tool for syntactical and tectogrammatical annotations in The Prague Dependency Treebank, as well as for decision-tree based morphological annotation of The Prague Arabic Dependency Treebank.;2009-10-13T13:11:11Z;toolService;http://hdl.handle.net/11858/00-097C-0000-0001-48F7-8;GNU General Public License, version 2;http://www.gnu.org/licenses/gpl-2.0.html;PUB;application/octet-stream;application/octet-stream;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 3;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/tred/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c4bbec83-36fc-578a-b485-86ec4b573253",
-    "notes": [
-        "Tree Editor\r\n\r\nTrEd is a fully customizable and programmable graphical editor and viewer for tree-like structures. Among other projects, it was used as the main annotation tool for syntactical and tectogrammatical annotations in The Prague Dependency Treebank, as well as for decision-tree based morphological annotation of The Prague Arabic Dependency Treebank."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48F7-8"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "annotation"
-        },
-        {
-            "name": "tree"
-        },
-        {
-            "name": "editor"
-        },
-        {
-            "name": "XML"
-        },
-        {
-            "name": "PML"
-        }
-    ],
-    "title": [
-        "TrEd"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c4cd4256-3a41-5ec2-891f-0a4351142c63.json b/oaitestdata/clarin-oai_dc/SET_1/json/c4cd4256-3a41-5ec2-891f-0a4351142c63.json
deleted file mode 100644
index 18082186..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c4cd4256-3a41-5ec2-891f-0a4351142c63.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Centro de Tecnolog\u00edas y Aplicaciones del Lenguaje y del Habla (TALP)"
-    ],
-    "Contributor": [
-        "Llu\u00eds, Xavier"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1428",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1428"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1428",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Centro de Tecnolog\u00edas y Aplicaciones del Lenguaje y del Habla (TALP)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1428;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;jointparser;Llu\u00eds, Xavier;Parser that jointly annotates syntax and semantics. It performs syntactic parsing, shallow semantic parsing and predicate identification.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1428;downloadable_files_count: 0;Spain;Centro de Tecnolog\u00edas y Aplicaciones del Lenguaje y del Habla (TALP);http://www.lsi.upc.edu/~xlluis/?x=cat:5",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c4cd4256-3a41-5ec2-891f-0a4351142c63",
-    "notes": [
-        "Parser that jointly annotates syntax and semantics. It performs syntactic parsing, shallow semantic parsing and predicate identification."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1428"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "jointparser"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c4e891f0-a941-5bd7-8ef4-7a2bd4cdd208.json b/oaitestdata/clarin-oai_dc/SET_1/json/c4e891f0-a941-5bd7-8ef4-7a2bd4cdd208.json
deleted file mode 100644
index dcb4446e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c4e891f0-a941-5bd7-8ef4-7a2bd4cdd208.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contributor": [
-        "Vera Demberg",
-        "Manfred Pinkal",
-        "Ivan Titov",
-        "Ashutosh Modi",
-        "Asad Sayeed"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:tacl-2016",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:tacl-2016"
-    ],
-    "PID": "http://hdl.handle.net/21.11119/0000-0000-5DD9-4",
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "RelatedIdentifier": [
-        "Ashutosh Modi, Ivan Titov, Vera Demberg, Asad Sayeed and Manfred Pinkal. 2016. \"Modeling Semantic Expectation: Using Script Knowledge for Referent Prediction\". In Transactions of Association for Computational Linguistics (TACL). http://www.aclweb.org/anthology/Q17-1003"
-    ],
-    "ResourceType": [
-        "Collection",
-        "Dataset",
-        "Text"
-    ],
-    "Rights": [
-        "CC-BY-SA-NC-4.0"
-    ],
-    "author": [
-        "Ashutosh Modi, Fachrichtung Sprachwissenschaft und Sprachtechnologie, Universit\u00e4t des Saarlandes, Campus C7.4, 66123 Saarbr\u00fccken"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:tacl-2016;2018-02-27T17:32:43Z;Modeling Semantic Expectations;Ashutosh Modi, Fachrichtung Sprachwissenschaft und Sprachtechnologie, Universit\u00e4t des Saarlandes, Campus C7.4, 66123 Saarbr\u00fccken;Scripts;Script Knowledge;Narrative Texts;Referent Prediction;Referring Expression;This resource contains the DR predictions (by humans) on the InScript corpus. These were collected using Amazon Mechanical Turk. For details please refer to the paper mentioned below.;Ashutosh Modi;Ivan Titov;Vera Demberg;Asad Sayeed;Manfred Pinkal;2017;Collection;Dataset;Text;text/xml;clarind-uds:tacl-2016;hdl:21.11119/0000-0000-5DD9-4;eng;Ashutosh Modi, Ivan Titov, Vera Demberg, Asad Sayeed and Manfred Pinkal. 2016. \"Modeling Semantic Expectation: Using Script Knowledge for Referent Prediction\". In Transactions of Association for Computational Linguistics (TACL). http://www.aclweb.org/anthology/Q17-1003;CC-BY-SA-NC-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c4e891f0-a941-5bd7-8ef4-7a2bd4cdd208",
-    "notes": [
-        "This resource contains the DR predictions (by humans) on the InScript corpus. These were collected using Amazon Mechanical Turk. For details please refer to the paper mentioned below."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:tacl-2016"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Scripts"
-        },
-        {
-            "name": "Script Knowledge"
-        },
-        {
-            "name": "Narrative Texts"
-        },
-        {
-            "name": "Referent Prediction"
-        },
-        {
-            "name": "Referring Expression"
-        }
-    ],
-    "title": [
-        "Modeling Semantic Expectations"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c4f7ef65-4e31-5d60-8c46-d801f9b29ce5.json b/oaitestdata/clarin-oai_dc/SET_1/json/c4f7ef65-4e31-5d60-8c46-d801f9b29ce5.json
deleted file mode 100644
index dae66689..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c4f7ef65-4e31-5d60-8c46-d801f9b29ce5.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "Contributor": [
-        "Broeder, Daan"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1214",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1214"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1214",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1214;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LAMUS;Broeder, Daan;Language Archive Management and Upload System (LAMUS) is a web-based application that allows users to organize and update the content in the extensive archive of and IMDI-based corpus;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1214;downloadable_files_count: 0;Netherlands (the);Max Planck Institute for Psycholinguistics;http://tla.mpi.nl/tools/tla-tools/lamus/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c4f7ef65-4e31-5d60-8c46-d801f9b29ce5",
-    "notes": [
-        "Language Archive Management and Upload System (LAMUS) is a web-based application that allows users to organize and update the content in the extensive archive of and IMDI-based corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1214"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LAMUS"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c5022318-a2a1-5c3f-a366-6810a6ae1d06.json b/oaitestdata/clarin-oai_dc/SET_1/json/c5022318-a2a1-5c3f-a366-6810a6ae1d06.json
deleted file mode 100644
index 196bf67c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c5022318-a2a1-5c3f-a366-6810a6ae1d06.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2778",
-    "MetadataAccess": [
-        "oai:ota:oucs:2778"
-    ],
-    "PublicationTimestamp": "1714-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1714"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2778;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2778.xml;A modest enquiry into the reasons of the joy ... upon the spreading of a report of Her Majesty\u00e2\u0080\u0099s death;Swift, Jonathan, 1667-1745;1714;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c5022318-a2a1-5c3f-a366-6810a6ae1d06",
-    "oai_identifier": [
-        "oai:ota:oucs:2778"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A modest enquiry into the reasons of the joy ... upon the spreading of a report of Her Majesty\u00e2\u0080\u0099s death"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2778.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c5079b1e-0c8a-50f8-be8e-63c415f2d2b8.json b/oaitestdata/clarin-oai_dc/SET_1/json/c5079b1e-0c8a-50f8-be8e-63c415f2d2b8.json
deleted file mode 100644
index 91988c75..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c5079b1e-0c8a-50f8-be8e-63c415f2d2b8.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "University of West Bohemia, Department of Cybernetics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/x-rar-compressed"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-CCA1-0",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-CCA1-0"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-CCA1-0",
-    "PublicationTimestamp": "2011-12-15T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "University of West Bohemia, Department of Cybernetics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u0160m\u00eddl, Lubo\u0161"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-CCA1-0;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Air Traffic Control Communication;\u0160m\u00eddl, Lubo\u0161;speech corpus;acoustic model;Corpus contains recordings of communication between air traffic controllers and pilots. The speech is manually transcribed and labeled with the information about the speaker (pilot/controller, not the full identity of the person). The corpus is currently small (20 hours) but we plan to search for additional data next year. The audio data format is: 8kHz, 16bit PCM, mono.;2011-12-15;corpus;ZCU_CZ_ATC;http://hdl.handle.net/11858/00-097C-0000-0001-CCA1-0;eng;Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0);http://creativecommons.org/licenses/by-nc-nd/3.0/;PUB;application/x-rar-compressed;text/plain; charset=utf-8;downloadable_files_count: 1;University of West Bohemia, Department of Cybernetics",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c5079b1e-0c8a-50f8-be8e-63c415f2d2b8",
-    "notes": [
-        "Corpus contains recordings of communication between air traffic controllers and pilots. The speech is manually transcribed and labeled with the information about the speaker (pilot/controller, not the full identity of the person). The corpus is currently small (20 hours) but we plan to search for additional data next year. The audio data format is: 8kHz, 16bit PCM, mono."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-CCA1-0"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech corpus"
-        },
-        {
-            "name": "acoustic model"
-        }
-    ],
-    "title": [
-        "Air Traffic Control Communication"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c512f053-cb91-5522-a048-38c2fb2cfd2e.json b/oaitestdata/clarin-oai_dc/SET_1/json/c512f053-cb91-5522-a048-38c2fb2cfd2e.json
deleted file mode 100644
index e3bc17ff..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c512f053-cb91-5522-a048-38c2fb2cfd2e.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 126 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2016",
-    "MetadataAccess": [
-        "oai:ota:oucs:2016"
-    ],
-    "PublicationTimestamp": "1921-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1921"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Virgil"
-    ],
-    "fulltext": "oai:ota:oucs:2016;2018-03-01T11:55:06Z;http://ota.ox.ac.uk/headers/2016.xml;The Georgics / Virgil;Georgicon;Virgil;1921;text_and_corpus_linguistics;Latin poetry -- 1st century B.C.;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 126 KB);Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c512f053-cb91-5522-a048-38c2fb2cfd2e",
-    "oai_identifier": [
-        "oai:ota:oucs:2016"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Latin poetry -- st century B.C."
-        }
-    ],
-    "title": [
-        "The Georgics / Virgil",
-        "Georgicon"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2016.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c52190bd-5a36-5a0e-86f2-2f2104356453.json b/oaitestdata/clarin-oai_dc/SET_1/json/c52190bd-5a36-5a0e-86f2-2f2104356453.json
deleted file mode 100644
index aa2440cc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c52190bd-5a36-5a0e-86f2-2f2104356453.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1156",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1156"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1156",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1156;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Damen Conversations Lexikon;Germanistik;Neusatz und Faksimile der zehnb\u00e4ndigen Ausgabe (Leipzig, 1834-1838); wortgenaue Seitenkonkordanz zu der gedruckten Ausgabe; Darstellung der Gegenstandsbereiche gesellschaftlicher Konversation (speziell auf eine weibliche Zielgruppe ausgerichtet);2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1156;deu;downloadable_files_count: 0;http://www.zeno.org/DamenConvLex-1834",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c52190bd-5a36-5a0e-86f2-2f2104356453",
-    "notes": [
-        "Neusatz und Faksimile der zehnb\u00e4ndigen Ausgabe (Leipzig, 1834-1838); wortgenaue Seitenkonkordanz zu der gedruckten Ausgabe; Darstellung der Gegenstandsbereiche gesellschaftlicher Konversation (speziell auf eine weibliche Zielgruppe ausgerichtet)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1156"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Damen Conversations Lexikon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c52e4dd0-3b25-5ba1-9d65-949500ac004c.json b/oaitestdata/clarin-oai_dc/SET_1/json/c52e4dd0-3b25-5ba1-9d65-949500ac004c.json
deleted file mode 100644
index af290ffe..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c52e4dd0-3b25-5ba1-9d65-949500ac004c.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3614",
-    "MetadataAccess": [
-        "oai:ota:oucs:3614"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Andrews, Miles Peter, d. 1814."
-    ],
-    "fulltext": "oai:ota:oucs:3614;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3614.xml;The mysteries of the castle: a dramatic tale, in three acts: as performed at the Theatre-Royal, Covent-Garden. Written by Miles Peter Andrews, Esq.;Andrews, Miles Peter, d. 1814.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c52e4dd0-3b25-5ba1-9d65-949500ac004c",
-    "oai_identifier": [
-        "oai:ota:oucs:3614"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The mysteries of the castle: a dramatic tale, in three acts: as performed at the Theatre-Royal, Covent-Garden. Written by Miles Peter Andrews, Esq."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3614.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c52fd250-456d-51ee-9d48-c4f0d559e40d.json b/oaitestdata/clarin-oai_dc/SET_1/json/c52fd250-456d-51ee-9d48-c4f0d559e40d.json
deleted file mode 100644
index bf9c454a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c52fd250-456d-51ee-9d48-c4f0d559e40d.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3941",
-    "MetadataAccess": [
-        "oai:ota:oucs:3941"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Brown, John, 1715-1766."
-    ],
-    "fulltext": "oai:ota:oucs:3941;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3941.xml;An essay on satire: occasion'd by the death of Mr. Pope.;Brown, John, 1715-1766.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c52fd250-456d-51ee-9d48-c4f0d559e40d",
-    "oai_identifier": [
-        "oai:ota:oucs:3941"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An essay on satire: occasion'd by the death of Mr. Pope."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3941.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c5353316-90f2-5b7b-85c6-a1e9cf3e4c9e.json b/oaitestdata/clarin-oai_dc/SET_1/json/c5353316-90f2-5b7b-85c6-a1e9cf3e4c9e.json
deleted file mode 100644
index 85026903..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c5353316-90f2-5b7b-85c6-a1e9cf3e4c9e.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "Latvian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-930",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-930"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-930",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-930;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Latvian;ca. 10.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-930;lav;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#lett",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c5353316-90f2-5b7b-85c6-a1e9cf3e4c9e",
-    "notes": [
-        "ca. 10.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-930"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Latvian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c55acbea-d3ed-5e84-ba05-4a923ef809ad.json b/oaitestdata/clarin-oai_dc/SET_1/json/c55acbea-d3ed-5e84-ba05-4a923ef809ad.json
deleted file mode 100644
index 23b8db50..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c55acbea-d3ed-5e84-ba05-4a923ef809ad.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Richardson, Brian, 1946-"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 869 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1043",
-    "MetadataAccess": [
-        "oai:ota:oucs:1043"
-    ],
-    "PublicationTimestamp": "1923-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1923"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Svevo, Italo, 1861-1928"
-    ],
-    "fulltext": "oai:ota:oucs:1043;2018-03-05T10:56:22Z;http://ota.ox.ac.uk/headers/1043.xml;La coscienza di Zeno / Italo Svevo;The confessions of Zeno;Svevo, Italo, 1861-1928;1923;text_and_corpus_linguistics;Italian fiction -- 20th century;ita;Oxford Text Archive, University of Oxford;Richardson, Brian, 1946-;text/plain;(1 file : ca. 869 KB);Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c55acbea-d3ed-5e84-ba05-4a923ef809ad",
-    "oai_identifier": [
-        "oai:ota:oucs:1043"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Italian fiction -- th century"
-        }
-    ],
-    "title": [
-        "La coscienza di Zeno / Italo Svevo",
-        "The confessions of Zeno"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1043.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c5993e6a-318d-55da-b70c-5c8010da7830.json b/oaitestdata/clarin-oai_dc/SET_1/json/c5993e6a-318d-55da-b70c-5c8010da7830.json
deleted file mode 100644
index 6e228b10..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c5993e6a-318d-55da-b70c-5c8010da7830.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "NBG/DBNL/INL; Nicoline van der Sijs"
-    ],
-    "Contributor": [
-        "Agency, Dutch HLT"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-577",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-577"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-577",
-    "PublicationTimestamp": "2008-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2008"
-    ],
-    "Publisher": [
-        "NBG/DBNL/INL; Nicoline van der Sijs"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-577;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Statenvertaling 1637;Agency, Dutch HLT;A digitised version of the Statenvertaling (Bible) of 1637;2008;corpus;http://hdl.handle.net/11372/LRT-577;nld;downloadable_files_count: 0;Netherlands (the);NBG/DBNL/INL; Nicoline van der Sijs;http://tst.inl.nl/producten/SV1637",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c5993e6a-318d-55da-b70c-5c8010da7830",
-    "notes": [
-        "A digitised version of the Statenvertaling (Bible) of 1637"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-577"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Statenvertaling 1637"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c5ab630c-baed-5bb2-9a5f-10db6a35447e.json b/oaitestdata/clarin-oai_dc/SET_1/json/c5ab630c-baed-5bb2-9a5f-10db6a35447e.json
deleted file mode 100644
index a91a0630..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c5ab630c-baed-5bb2-9a5f-10db6a35447e.json
+++ /dev/null
@@ -1,49 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3663",
-    "MetadataAccess": [
-        "oai:ota:oucs:3663"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:3663;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3663.xml;A collection of letters, never before printed: written by Alexander Pope, Esq; and other ingenious gentlemen, to the late Aaron Hill, Esq;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c5ab630c-baed-5bb2-9a5f-10db6a35447e",
-    "oai_identifier": [
-        "oai:ota:oucs:3663"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A collection of letters, never before printed: written by Alexander Pope, Esq; and other ingenious gentlemen, to the late Aaron Hill, Esq"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3663.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c5b1ced7-babc-5c68-81b1-6ec8f9225dbb.json b/oaitestdata/clarin-oai_dc/SET_1/json/c5b1ced7-babc-5c68-81b1-6ec8f9225dbb.json
deleted file mode 100644
index 3192c142..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c5b1ced7-babc-5c68-81b1-6ec8f9225dbb.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/gzip",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/256",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/256"
-    ],
-    "PID": "http://hdl.handle.net/11321/256",
-    "PublicationTimestamp": "2016-04-30T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "Patejuk, Agnieszka"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/256;2016-05-05T12:38:43Z;hdl_11321_3;hdl_11321_4;POLFIE Bank, an LFG structure bank of Polish: pol-sk\u0142adnica-pargram;Patejuk, Agnieszka;syntax;LFG;Polish;treebank;parsebank;The pol-sk\u0142adnica-pargram structure bank was created using POLFIE: an LFG grammar of Polish. This structure bank contains FULL type sentences from Sk\u0142adnica, which were in turn taken from the NKJP1M subcorpus of NKJP. The sentences were disambiguated from scratch, independently of Sk\u0142adnica.\r\n\r\nThe pol-sk\u0142adnica-pargram structure bank can be accessed via INESS treebanking system in two ways:\r\n\u2022 use the direct link: http://clarino.uib.no/iness/lfg-sentences?&treebank=pol-sk%C5%82adnica-pargram\r\n\u2022 go to http://iness.uib.no --> choose \"Treebank Selection\" in the menu on the left-hand side --> choose \"POLFIE\" in \"Treebank Collections\" --> choose pol-sk\u0142adnica-pargram;2016-04-30;corpus;http://hdl.handle.net/11321/256;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/gzip;downloadable_files_count: 1;Institute of Computer Science, Polish Academy of Sciences;http://zil.ipipan.waw.pl/LFG",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c5b1ced7-babc-5c68-81b1-6ec8f9225dbb",
-    "notes": [
-        "The pol-sk\u0142adnica-pargram structure bank was created using POLFIE: an LFG grammar of Polish. This structure bank contains FULL type sentences from Sk\u0142adnica, which were in turn taken from the NKJP1M subcorpus of NKJP. The sentences were disambiguated from scratch, independently of Sk\u0142adnica.\r\n\r\nThe pol-sk\u0142adnica-pargram structure bank can be accessed via INESS treebanking system in two ways:\r\n\u2022 use the direct link: http://clarino.uib.no/iness/lfg-sentences?&treebank=pol-sk%C5%82adnica-pargram\r\n\u2022 go to http://iness.uib.no --> choose \"Treebank Selection\" in the menu on the left-hand side --> choose \"POLFIE\" in \"Treebank Collections\" --> choose pol-sk\u0142adnica-pargram"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/256"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "syntax"
-        },
-        {
-            "name": "LFG"
-        },
-        {
-            "name": "Polish"
-        },
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "parsebank"
-        }
-    ],
-    "title": [
-        "POLFIE Bank, an LFG structure bank of Polish: pol-sk\u0142adnica-pargram"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c5b88988-022e-5392-b4b0-e7bb2ab74ce1.json b/oaitestdata/clarin-oai_dc/SET_1/json/c5b88988-022e-5392-b4b0-e7bb2ab74ce1.json
deleted file mode 100644
index 30e5ecbd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c5b88988-022e-5392-b4b0-e7bb2ab74ce1.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-91",
-    "MetadataAccess": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-91"
-    ],
-    "PID": "http://hdl.handle.net/20.500.11752/ILC-91",
-    "PublicationTimestamp": "2012-12-12T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/248064",
-        "http://www.aclweb.org/anthology/C12-1140"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Rubino, Francesco",
-        "Quochi, Valeria",
-        "Frontini, Francesca"
-    ],
-    "fulltext": "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-91;2018-12-05T08:40:42Z;hdl_000-c0-111_38;hdl_000-c0-111_49;Multiword Extractor;Rubino, Francesco;Quochi, Valeria;Frontini, Francesca;Multiword Extraction;Automatic lexical acquisition;This is a lexical acquisition web-service for the automatic extraction of multiword expressions from large corpora. The service takes in input a POS-tagged corpus in CoNLL-X format plus a pair of POS-tags for the first and last word of a MWE, and outputs a list of extracted (candidate) multiword expressions with a set of linguistic and statistical information.\r\nThe output can then be post-processed through filters that will refine and improve the accuracy of the extraction, and finally converted to an LMF-compliant XML lexical resource.\r\nThe tool code is available open-source at https://github.com/francescafrontini/MWExtractor.\r\nFurther details can be found in: \r\n    Quochi Valeria & Frontini Francesca & Rubino Francesco. 2012. A MWE Acquisition and Lexicon Builder Web Service. In Proceedings of the 24th International Conference on Computational Linguistics (COLING 2012), December 10-14 2012, IIT Bombay, Mumbai, India.\r\n    Frontini Francesca  & Rubino Francesco & Quochi Valeria. 2012. Automatic Creation of quality multi-word Lexica from noisy text data. In Proceedings of the Sixth Workshop on Analytics for Noisy Unstructured Text Data (AND2012). December 9, 2012, IIT Bombay, Mumbai, India (Co-located with COLING2012).;2012-12-12;toolService;http://hdl.handle.net/20.500.11752/ILC-91;info:eu-repo/grantAgreement/EC/FP7/248064;http://www.aclweb.org/anthology/C12-1140;downloadable_files_count: 0;Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR);http://www.panacea-lr.eu/system/deliverables/PANACEA_D6.2.pdf",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c5b88988-022e-5392-b4b0-e7bb2ab74ce1",
-    "notes": [
-        "This is a lexical acquisition web-service for the automatic extraction of multiword expressions from large corpora. The service takes in input a POS-tagged corpus in CoNLL-X format plus a pair of POS-tags for the first and last word of a MWE, and outputs a list of extracted (candidate) multiword expressions with a set of linguistic and statistical information.\r\nThe output can then be post-processed through filters that will refine and improve the accuracy of the extraction, and finally converted to an LMF-compliant XML lexical resource.\r\nThe tool code is available open-source at https://github.com/francescafrontini/MWExtractor.\r\nFurther details can be found in: \r\n    Quochi Valeria & Frontini Francesca & Rubino Francesco. 2012. A MWE Acquisition and Lexicon Builder Web Service. In Proceedings of the 24th International Conference on Computational Linguistics (COLING 2012), December 10-14 2012, IIT Bombay, Mumbai, India.\r\n    Frontini Francesca  & Rubino Francesco & Quochi Valeria. 2012. Automatic Creation of quality multi-word Lexica from noisy text data. In Proceedings of the Sixth Workshop on Analytics for Noisy Unstructured Text Data (AND2012). December 9, 2012, IIT Bombay, Mumbai, India (Co-located with COLING2012)."
-    ],
-    "oai_identifier": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-91"
-    ],
-    "oai_set": [
-        "hdl_000-c0-111_38",
-        "hdl_000-c0-111_49"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Multiword Extraction"
-        },
-        {
-            "name": "Automatic lexical acquisition"
-        }
-    ],
-    "title": [
-        "Multiword Extractor"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c5b970b8-9742-5148-b82c-7f1acdba8555.json b/oaitestdata/clarin-oai_dc/SET_1/json/c5b970b8-9742-5148-b82c-7f1acdba8555.json
deleted file mode 100644
index 223f10b9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c5b970b8-9742-5148-b82c-7f1acdba8555.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 10.8 KB)"
-    ],
-    "Language": [
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0343",
-    "MetadataAccess": [
-        "oai:ota:oucs:0343"
-    ],
-    "PublicationYear": [
-        "804-810"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Modoinus"
-    ],
-    "fulltext": "oai:ota:oucs:0343;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0343.xml;[Eclogae];Modoinus;804-810;text_and_corpus_linguistics;Poems;Eclogues;Pastoral poems;lat;Oxford Text Archive, University of Oxford;(1 file : ca. 10.8 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c5b970b8-9742-5148-b82c-7f1acdba8555",
-    "oai_identifier": [
-        "oai:ota:oucs:0343"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems"
-        },
-        {
-            "name": "Eclogues"
-        },
-        {
-            "name": "Pastoral poems"
-        }
-    ],
-    "title": [
-        "[Eclogae]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0343.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c5bbbfef-dfbb-5f31-96ad-012ac61aec94.json b/oaitestdata/clarin-oai_dc/SET_1/json/c5bbbfef-dfbb-5f31-96ad-012ac61aec94.json
deleted file mode 100644
index cf0ed028..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c5bbbfef-dfbb-5f31-96ad-012ac61aec94.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contributor": [
-        "Simov, Kiril",
-        "Tadi\u0107, Marko"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Bulgarian",
-        "Croatian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-242",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-242"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-242",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Bulgaria||Croatia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-242;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Bulgarian-Croatian Comparable Corpus;Tadi\u0107, Marko;Simov, Kiril;written; domain-specific (newspaper); diachronic; bilingual; comparable; ca 3,500,000 tokens (393 Kw Bulgarian; 3.1 Mw Croatian);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-242;bul;hrv;downloadable_files_count: 0;Bulgaria||Croatia;http://hnk.ffzg.hr",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c5bbbfef-dfbb-5f31-96ad-012ac61aec94",
-    "notes": [
-        "written; domain-specific (newspaper); diachronic; bilingual; comparable; ca 3,500,000 tokens (393 Kw Bulgarian; 3.1 Mw Croatian)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-242"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Bulgarian-Croatian Comparable Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c5d93058-52ee-5756-b914-779731e9e959.json b/oaitestdata/clarin-oai_dc/SET_1/json/c5d93058-52ee-5756-b914-779731e9e959.json
deleted file mode 100644
index 6aa8ecc5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c5d93058-52ee-5756-b914-779731e9e959.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 5 MB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1061",
-    "MetadataAccess": [
-        "oai:ota:oucs:1061"
-    ],
-    "PublicationYear": [
-        "600 BCE-70"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Sacred texts"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:1061;2018-03-02T10:10:30Z;http://ota.ox.ac.uk/headers/1061.xml;Bible. English. Revised standard;Bible : RSV;600 BCE-70;text_and_corpus_linguistics;Bible;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 5 MB);Text;Sacred texts;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c5d93058-52ee-5756-b914-779731e9e959",
-    "oai_identifier": [
-        "oai:ota:oucs:1061"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Bible"
-        }
-    ],
-    "title": [
-        "Bible. English. Revised standard",
-        "Bible : RSV"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1061.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c5dc33ac-2877-5793-8ad1-d9721ab73b60.json b/oaitestdata/clarin-oai_dc/SET_1/json/c5dc33ac-2877-5793-8ad1-d9721ab73b60.json
deleted file mode 100644
index b192705d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c5dc33ac-2877-5793-8ad1-d9721ab73b60.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 118 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1860",
-    "MetadataAccess": [
-        "oai:ota:oucs:1860"
-    ],
-    "PublicationTimestamp": "1896-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1896"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Twain, Mark, 1835-1910"
-    ],
-    "fulltext": "oai:ota:oucs:1860;2018-04-11T16:03:39Z;http://ota.ox.ac.uk/headers/1860.xml;Tom Sawyer, detective / by Mark Twain;Twain, Mark, 1835-1910;1896;text_and_corpus_linguistics;Fiction -- United States -- 19th century;Short stories -- United States -- 19th century;Juvenile literature -- United States -- 19th century;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 118 KB);Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c5dc33ac-2877-5793-8ad1-d9721ab73b60",
-    "oai_identifier": [
-        "oai:ota:oucs:1860"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- United States -- th century"
-        },
-        {
-            "name": "Short stories -- United States -- th century"
-        },
-        {
-            "name": "Juvenile literature -- United States -- th century"
-        }
-    ],
-    "title": [
-        "Tom Sawyer, detective / by Mark Twain"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1860.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c5e07fbc-2019-549c-ade9-7455bcae2b4a.json b/oaitestdata/clarin-oai_dc/SET_1/json/c5e07fbc-2019-549c-ade9-7455bcae2b4a.json
deleted file mode 100644
index 4b0fe0d6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c5e07fbc-2019-549c-ade9-7455bcae2b4a.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4042",
-    "MetadataAccess": [
-        "oai:ota:oucs:4042"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hayley, William, 1745-1820."
-    ],
-    "fulltext": "oai:ota:oucs:4042;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4042.xml;The national advocates, a poem. Affectionately inscribed to the Honourable Thomas Erskine, and Vicary Gibbs, Esquire;Hayley, William, 1745-1820.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c5e07fbc-2019-549c-ade9-7455bcae2b4a",
-    "oai_identifier": [
-        "oai:ota:oucs:4042"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The national advocates, a poem. Affectionately inscribed to the Honourable Thomas Erskine, and Vicary Gibbs, Esquire"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4042.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c5e1b8f5-b6e8-53e7-a0f8-a4726b78b310.json b/oaitestdata/clarin-oai_dc/SET_1/json/c5e1b8f5-b6e8-53e7-a0f8-a4726b78b310.json
deleted file mode 100644
index 58606006..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c5e1b8f5-b6e8-53e7-a0f8-a4726b78b310.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "Contributor": [
-        "Yzaguirre, Llu\u00eds de"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Catalan",
-        "French",
-        "Portuguese",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-283",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-283"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-283",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-283;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;PALIC;Yzaguirre, Llu\u00eds de;A package of tools for the processing of the Corpus T\u00e8cnic in Catalan and Spanish. It includes a preprocessor, a PoSTagger and a linguistic disambiguator.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-283;cat;fra;por;spa;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra;http://terminotica.upf.edu/CREL/LIC01.htm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c5e1b8f5-b6e8-53e7-a0f8-a4726b78b310",
-    "notes": [
-        "A package of tools for the processing of the Corpus T\u00e8cnic in Catalan and Spanish. It includes a preprocessor, a PoSTagger and a linguistic disambiguator."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-283"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "PALIC"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c5e313b8-683b-59b8-8792-715b2b53915b.json b/oaitestdata/clarin-oai_dc/SET_1/json/c5e313b8-683b-59b8-8792-715b2b53915b.json
deleted file mode 100644
index 4fcf0bd7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c5e313b8-683b-59b8-8792-715b2b53915b.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "A"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1533",
-    "MetadataAccess": [
-        "oai:ota:oucs:1533"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Cather, Willa"
-    ],
-    "fulltext": "oai:ota:oucs:1533;2018-04-16T15:30:51Z;http://ota.ox.ac.uk/headers/1533.xml;The troll garden;Cather, Willa;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;A;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c5e313b8-683b-59b8-8792-715b2b53915b",
-    "oai_identifier": [
-        "oai:ota:oucs:1533"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The troll garden"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1533.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c5e5d6cf-b12f-5652-89cf-6cb28b36a46b.json b/oaitestdata/clarin-oai_dc/SET_1/json/c5e5d6cf-b12f-5652-89cf-6cb28b36a46b.json
deleted file mode 100644
index 0edf23f1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c5e5d6cf-b12f-5652-89cf-6cb28b36a46b.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Dabrowska"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 6",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/69",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/69"
-    ],
-    "PID": "http://hdl.handle.net/11321/69",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Dabrowska"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Dabrowska, Dabrowska"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/69;2015-05-19T13:34:59Z;hdl_11321_3;hdl_11321_4;MWE Dabrowska;Dabrowska, Dabrowska;Dabrowska;2015-04-08;corpus;http://hdl.handle.net/11321/69;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 6;Dabrowska",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c5e5d6cf-b12f-5652-89cf-6cb28b36a46b",
-    "notes": [
-        "Dabrowska"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/69"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Dabrowska"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c5f40813-2bcb-5645-b7fb-68a4d5f5d972.json b/oaitestdata/clarin-oai_dc/SET_1/json/c5f40813-2bcb-5645-b7fb-68a4d5f5d972.json
deleted file mode 100644
index cb08bc80..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c5f40813-2bcb-5645-b7fb-68a4d5f5d972.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 157 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "Middle English (1100-1500)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0036",
-    "MetadataAccess": [
-        "oai:ota:oucs:0036"
-    ],
-    "PublicationTimestamp": "1300-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1300"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:0036;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0036.xml;Cursor mundi;Cursor mundi : ms. in the library of the College of Physicians, Edinburgh;1300;text_and_corpus_linguistics;Devotional literature -- England -- 14th century;Local histories -- England -- 14th century;enm;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 157 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c5f40813-2bcb-5645-b7fb-68a4d5f5d972",
-    "oai_identifier": [
-        "oai:ota:oucs:0036"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Devotional literature -- England -- th century"
-        },
-        {
-            "name": "Local histories -- England -- th century"
-        }
-    ],
-    "title": [
-        "Cursor mundi",
-        "Cursor mundi : ms. in the library of the College of Physicians, Edinburgh"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0036.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c624e636-83d9-57fd-bb18-1b5d34dae92f.json b/oaitestdata/clarin-oai_dc/SET_1/json/c624e636-83d9-57fd-bb18-1b5d34dae92f.json
deleted file mode 100644
index eb511b55..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c624e636-83d9-57fd-bb18-1b5d34dae92f.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4912",
-    "MetadataAccess": [
-        "oai:ota:oucs:4912"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dennis, John, 1657-1734."
-    ],
-    "fulltext": "oai:ota:oucs:4912;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4912.xml;A proposal for putting a speedy end to the war, by ruining the commerce of the French and Spaniards: and securing our own, without any additional expence to the nation.;Dennis, John, 1657-1734.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c624e636-83d9-57fd-bb18-1b5d34dae92f",
-    "oai_identifier": [
-        "oai:ota:oucs:4912"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A proposal for putting a speedy end to the war, by ruining the commerce of the French and Spaniards: and securing our own, without any additional expence to the nation."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4912.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c641c206-ec29-5be7-aabf-b41eb9c64397.json b/oaitestdata/clarin-oai_dc/SET_1/json/c641c206-ec29-5be7-aabf-b41eb9c64397.json
deleted file mode 100644
index 711e3d6e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c641c206-ec29-5be7-aabf-b41eb9c64397.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "University of Stuttgart"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1289",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1289"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1289",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Stuttgart"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Schmid, Helmut"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1289;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;BitPar;Schmid, Helmut;parser;Statistical parser;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1289;downloadable_files_count: 0;Germany;University of Stuttgart;http://www.cis.uni-muenchen.de/~schmid/tools/BitPar/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c641c206-ec29-5be7-aabf-b41eb9c64397",
-    "notes": [
-        "Statistical parser"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1289"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parser"
-        }
-    ],
-    "title": [
-        "BitPar"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c6689dbb-5497-53ff-8142-be13271ce770.json b/oaitestdata/clarin-oai_dc/SET_1/json/c6689dbb-5497-53ff-8142-be13271ce770.json
deleted file mode 100644
index 90fcdbfb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c6689dbb-5497-53ff-8142-be13271ce770.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=573aeb080b6511e5a2aa782bcb074135ace9ac8fc0274514a993f523b313f3ae",
-    "MetadataAccess": [
-        "573aeb080b6511e5a2aa782bcb074135ace9ac8fc0274514a993f523b313f3ae"
-    ],
-    "PublicationTimestamp": "2015-06-05T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "573aeb080b6511e5a2aa782bcb074135ace9ac8fc0274514a993f523b313f3ae;2018-11-15T16:40:16Z;toolService;toolService:tool;ixa-pipe-ned-ukb;ixa-pipe-ned-ukb is a multilingual Named Entity Disambiguation tool.\n\nIt is based on UKB (http://ixa2.si.ehu.es/ukb/), a graph-based Word Sense Disambiguation tool. The Wikipedia graph built from the hyperlinks between Wikipedia articles is used for the processing. \n\nThe input of the tool is text where named entity mentions have been recognized and represented using the Natural Language Processing Annotation Format (NAF) (http://wordpress.let.vupr.nl/naf/. In the output it returns the corresponding Wikipedia articles for the entities in NAF format.\n\nThis tool is partly funded by the European Commission project QTLeap FP7-ICT-2013.4.1-610516 (http://qtleap.eu). This tool is distributed under the license GPL v3.0.;2015-06-05",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c6689dbb-5497-53ff-8142-be13271ce770",
-    "notes": [
-        "ixa-pipe-ned-ukb is a multilingual Named Entity Disambiguation tool.\n\nIt is based on UKB (http://ixa2.si.ehu.es/ukb/), a graph-based Word Sense Disambiguation tool. The Wikipedia graph built from the hyperlinks between Wikipedia articles is used for the processing. \n\nThe input of the tool is text where named entity mentions have been recognized and represented using the Natural Language Processing Annotation Format (NAF) (http://wordpress.let.vupr.nl/naf/. In the output it returns the corresponding Wikipedia articles for the entities in NAF format.\n\nThis tool is partly funded by the European Commission project QTLeap FP7-ICT-2013.4.1-610516 (http://qtleap.eu). This tool is distributed under the license GPL v3.0."
-    ],
-    "oai_identifier": [
-        "573aeb080b6511e5a2aa782bcb074135ace9ac8fc0274514a993f523b313f3ae"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "ixa-pipe-ned-ukb"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c6709459-1157-5774-95c6-1fad574527ca.json b/oaitestdata/clarin-oai_dc/SET_1/json/c6709459-1157-5774-95c6-1fad574527ca.json
deleted file mode 100644
index 9bfa6b31..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c6709459-1157-5774-95c6-1fad574527ca.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "between 2 and 5 MB"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0519",
-    "MetadataAccess": [
-        "oai:ota:oucs:0519"
-    ],
-    "PublicationYear": [
-        "415-354"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Local histories"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Xenophon"
-    ],
-    "fulltext": "oai:ota:oucs:0519;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0519.xml; Opera omnia  / compiled by Thesaurus Linguae Graecae;Xenophon;415-354;text_and_corpus_linguistics;Local histories -- 5th century;Local histories -- 4th century;grc;Oxford Text Archive, University of Oxford;between 2 and 5 MB;Text;Local histories;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c6709459-1157-5774-95c6-1fad574527ca",
-    "oai_identifier": [
-        "oai:ota:oucs:0519"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Local histories -- th century"
-        },
-        {
-            "name": "Local histories -- th century"
-        }
-    ],
-    "title": [
-        " Opera omnia  / compiled by Thesaurus Linguae Graecae"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0519.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c683ebb3-7bbc-5149-b4a0-7b625e20f788.json b/oaitestdata/clarin-oai_dc/SET_1/json/c683ebb3-7bbc-5149-b4a0-7b625e20f788.json
deleted file mode 100644
index 36b0f590..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c683ebb3-7bbc-5149-b4a0-7b625e20f788.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Copenhagen Business School"
-    ],
-    "Contributor": [
-        "Buch-Kromann, Matthias"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1188",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1188"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1188",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Copenhagen Business School"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Denmark"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1188;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;DTAG dependency treebank tool;Buch-Kromann, Matthias;DTAG is a versatile annotation tool that supports manual and semi-automatic annotation of a wide range of linguistic phenomena, including the annotation of syntax, discourse, coreference, morphology, and word and phrase alignments. It includes commands for editing general labeled graphs and graph alignments, comparing annotations, managing annotation tasks, and interfacing with a revision control system. Its visualization component can display graphs and alignments for entire texts in a compact format, with a highly flexible and configurable formatting scheme. It also provides a powerful search-replace mechanism with queries based on full first-order logic, which can be used to search for linguistic constructions and automatically apply graph transformations to collections of annotated graphs. The visualization component does not currently support characters outside the ISO-latin character set.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1188;downloadable_files_count: 0;Denmark;Copenhagen Business School;http://code.google.com/p/copenhagen-dependency-treebank/wiki/DTAG",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c683ebb3-7bbc-5149-b4a0-7b625e20f788",
-    "notes": [
-        "DTAG is a versatile annotation tool that supports manual and semi-automatic annotation of a wide range of linguistic phenomena, including the annotation of syntax, discourse, coreference, morphology, and word and phrase alignments. It includes commands for editing general labeled graphs and graph alignments, comparing annotations, managing annotation tasks, and interfacing with a revision control system. Its visualization component can display graphs and alignments for entire texts in a compact format, with a highly flexible and configurable formatting scheme. It also provides a powerful search-replace mechanism with queries based on full first-order logic, which can be used to search for linguistic constructions and automatically apply graph transformations to collections of annotated graphs. The visualization component does not currently support characters outside the ISO-latin character set."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1188"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "DTAG dependency treebank tool"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c6c55958-4b10-5983-aaaa-4bf1acf0654d.json b/oaitestdata/clarin-oai_dc/SET_1/json/c6c55958-4b10-5983-aaaa-4bf1acf0654d.json
deleted file mode 100644
index 2c39b318..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c6c55958-4b10-5983-aaaa-4bf1acf0654d.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0005-BF95-B",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0005-BF95-B"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0005-BF95-B",
-    "PublicationTimestamp": "2012-03-19T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Cinkov\u00e1, Silvie",
-        "Holub, Martin",
-        "Rambousek, Adam",
-        "Smejkalov\u00e1, Lenka"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0005-BF95-B;2018-07-02T22:05:53Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;VPS-30-En;Cinkov\u00e1, Silvie;Holub, Martin;Rambousek, Adam;Smejkalov\u00e1, Lenka;corpus pattern analysis;clustering;lexical semantics;verbs;VPS-30-En is a small lexical resource that contains the following 30 English verbs: access, ally, arrive, breathe,\r\nclaim, cool, crush, cry, deny, enlarge, enlist, forge, furnish, hail, halt, part, plough, plug, pour, say, smash, smell, steer, submit, swell,\r\ntell, throw, trouble, wake and yield. We have created and have been using VPS-30-En to explore the interannotator agreement potential\r\nof the Corpus Pattern Analysis. VPS-30-En is a small snapshot of the Pattern Dictionary of English Verbs (Hanks and Pustejovsky,\r\n2005), which we revised (both the entries and the annotated concordances) and enhanced with additional annotations.;2012-03-19;lexicalConceptualResource;http://hdl.handle.net/11858/00-097C-0000-0005-BF95-B;eng;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/spr/pdev30verbs.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c6c55958-4b10-5983-aaaa-4bf1acf0654d",
-    "notes": [
-        "VPS-30-En is a small lexical resource that contains the following 30 English verbs: access, ally, arrive, breathe,\r\nclaim, cool, crush, cry, deny, enlarge, enlist, forge, furnish, hail, halt, part, plough, plug, pour, say, smash, smell, steer, submit, swell,\r\ntell, throw, trouble, wake and yield. We have created and have been using VPS-30-En to explore the interannotator agreement potential\r\nof the Corpus Pattern Analysis. VPS-30-En is a small snapshot of the Pattern Dictionary of English Verbs (Hanks and Pustejovsky,\r\n2005), which we revised (both the entries and the annotated concordances) and enhanced with additional annotations."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0005-BF95-B"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus pattern analysis"
-        },
-        {
-            "name": "clustering"
-        },
-        {
-            "name": "lexical semantics"
-        },
-        {
-            "name": "verbs"
-        }
-    ],
-    "title": [
-        "VPS-30-En"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c6dcf27d-176c-579d-bfd3-3cc23bd7b0b8.json b/oaitestdata/clarin-oai_dc/SET_1/json/c6dcf27d-176c-579d-bfd3-3cc23bd7b0b8.json
deleted file mode 100644
index 6371394e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c6dcf27d-176c-579d-bfd3-3cc23bd7b0b8.json
+++ /dev/null
@@ -1,88 +0,0 @@
-{
-    "Contact": [
-        "Fondazione Bruno Kessler, Trento, Italy"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "English",
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2726",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2726"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2726",
-    "PublicationTimestamp": "2018-05-04T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Fondazione Bruno Kessler, Trento, Italy"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/H2020/645452"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "AGREEMENT ON THE USE OF DATA IN QT21 APE Task",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21",
-        "PUB"
-    ],
-    "author": [
-        "Chatterjee, Rajen",
-        "Turchi, Marco",
-        "Negri, Matteo"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2726;2018-05-03T06:43:57Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Test Data EN-DE MT_NMT APE Shared Task WMT18;Chatterjee, Rajen;Negri, Matteo;Turchi, Marco;machine translation;shared task;automatic post-editing;post-editing;neural machine translation;Test data for the WMT 2018 Automatic post-editing task. They consist in English-German pairs (source and target) belonging to the information technology domain and already tokenized. Test set contains 1,023 pairs. A neural machine translation system has been used to generate the target segments. All data is provided by the EU project QT21 (http://www.qt21.eu/).;2018-05-04;corpus;http://hdl.handle.net/11372/LRT-2726;eng;deu;info:eu-repo/grantAgreement/EC/H2020/645452;AGREEMENT ON THE USE OF DATA IN QT21 APE Task;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Fondazione Bruno Kessler, Trento, Italy;http://www.statmt.org/wmt18/ape-task.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c6dcf27d-176c-579d-bfd3-3cc23bd7b0b8",
-    "notes": [
-        "Test data for the WMT 2018 Automatic post-editing task. They consist in English-German pairs (source and target) belonging to the information technology domain and already tokenized. Test set contains 1,023 pairs. A neural machine translation system has been used to generate the target segments. All data is provided by the EU project QT21 (http://www.qt21.eu/)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2726"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "shared task"
-        },
-        {
-            "name": "automatic post-editing"
-        },
-        {
-            "name": "post-editing"
-        },
-        {
-            "name": "neural machine translation"
-        }
-    ],
-    "title": [
-        "Test Data EN-DE MT_NMT APE Shared Task WMT18"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c721dcd4-2871-531b-9da3-34ac5da475d3.json b/oaitestdata/clarin-oai_dc/SET_1/json/c721dcd4-2871-531b-9da3-34ac5da475d3.json
deleted file mode 100644
index 39014f1b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c721dcd4-2871-531b-9da3-34ac5da475d3.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/pdf"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/591",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/591"
-    ],
-    "PID": "http://hdl.handle.net/11321/591",
-    "PublicationTimestamp": "2018-07-27T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Oleksy, Marcin",
-        "Wieczorek, Jan",
-        "Radziszewski, Adam"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/591;2018-07-27T10:12:41Z;hdl_11321_3;hdl_11321_4;KPWr annotation guidelines - phrase lemmatization;Oleksy, Marcin;Radziszewski, Adam;Wieczorek, Jan;lemmatization;annotated corpus;guidelines;Annotation guidelines for manual phrase lemmatisation in KPWr (Polish Corpus of Wroc\u0142aw University of Technology).;2018-07-27;languageDescription;http://hdl.handle.net/11321/591;pol;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;application/pdf;downloadable_files_count: 1;Wroc\u0142aw University of Science and Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c721dcd4-2871-531b-9da3-34ac5da475d3",
-    "notes": [
-        "Annotation guidelines for manual phrase lemmatisation in KPWr (Polish Corpus of Wroc\u0142aw University of Technology)."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/591"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "lemmatization"
-        },
-        {
-            "name": "annotated corpus"
-        },
-        {
-            "name": "guidelines"
-        }
-    ],
-    "title": [
-        "KPWr annotation guidelines - phrase lemmatization"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c75cbd1a-fd9a-5b47-8cbc-6416d4f855b1.json b/oaitestdata/clarin-oai_dc/SET_1/json/c75cbd1a-fd9a-5b47-8cbc-6416d4f855b1.json
deleted file mode 100644
index 12ed167f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c75cbd1a-fd9a-5b47-8cbc-6416d4f855b1.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "mamprawowiedziec"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 102",
-        "text/plain; charset=utf-8",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/512",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/512"
-    ],
-    "PID": "http://hdl.handle.net/11321/512",
-    "PublicationTimestamp": "2018-07-13T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "mamprawowiedziec"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Molek-kozakowska"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/512;2018-07-13T13:50:40Z;hdl_11321_3;hdl_11321_4;korpus testowy;Molek-kozakowska;EU;ludzie;2018-07-13;corpus;http://hdl.handle.net/11321/512;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;downloadable_files_count: 102;mamprawowiedziec",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c75cbd1a-fd9a-5b47-8cbc-6416d4f855b1",
-    "notes": [
-        "ludzie"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/512"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "EU"
-        }
-    ],
-    "title": [
-        "korpus testowy"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c763bdde-a35f-5c97-abbf-dbd7b71d6b89.json b/oaitestdata/clarin-oai_dc/SET_1/json/c763bdde-a35f-5c97-abbf-dbd7b71d6b89.json
deleted file mode 100644
index 1967de56..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c763bdde-a35f-5c97-abbf-dbd7b71d6b89.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=d4bb9c061c5e11e2a2aa782bcb0741354c05ee5991654a169d17a55e01aba9d2",
-    "MetadataAccess": [
-        "d4bb9c061c5e11e2a2aa782bcb0741354c05ee5991654a169d17a55e01aba9d2"
-    ],
-    "PublicationTimestamp": "2012-10-22T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "fulltext": "d4bb9c061c5e11e2a2aa782bcb0741354c05ee5991654a169d17a55e01aba9d2;2018-11-15T16:39:44Z;toolService;toolService:tool;CSTParser;CSTParser is a multi-document discourse parser. Based on machine learning techniques and hand-crafted rules, the system \nidentifies a set of relations predicted by CST (Cross-document Structure Theory) among sentences of different texts on the same topic.;2012-10-22",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c763bdde-a35f-5c97-abbf-dbd7b71d6b89",
-    "notes": [
-        "CSTParser is a multi-document discourse parser. Based on machine learning techniques and hand-crafted rules, the system \nidentifies a set of relations predicted by CST (Cross-document Structure Theory) among sentences of different texts on the same topic."
-    ],
-    "oai_identifier": [
-        "d4bb9c061c5e11e2a2aa782bcb0741354c05ee5991654a169d17a55e01aba9d2"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "CSTParser"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c776ec44-4f95-5d31-a4e7-ccdbec0515c0.json b/oaitestdata/clarin-oai_dc/SET_1/json/c776ec44-4f95-5d31-a4e7-ccdbec0515c0.json
deleted file mode 100644
index 2184a1c8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c776ec44-4f95-5d31-a4e7-ccdbec0515c0.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Engels, Friedrich, 1820-1895"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 83.2 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1761",
-    "MetadataAccess": [
-        "oai:ota:oucs:1761"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Marx, Karl, 1818-1883"
-    ],
-    "fulltext": "oai:ota:oucs:1761;2018-05-17T09:29:11Z;http://ota.ox.ac.uk/headers/1761.xml;Manifest der Kommunistischen Partei. English;Manifesto of the Communist Party;Marx, Karl, 1818-1883;default: 1976-01-01;text_and_corpus_linguistics;Alternative publications;Propaganda;eng;Oxford Text Archive, University of Oxford;Engels, Friedrich, 1820-1895;text/plain;(1 file : ca. 83.2 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c776ec44-4f95-5d31-a4e7-ccdbec0515c0",
-    "oai_identifier": [
-        "oai:ota:oucs:1761"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Alternative publications"
-        },
-        {
-            "name": "Propaganda"
-        }
-    ],
-    "title": [
-        "Manifest der Kommunistischen Partei. English",
-        "Manifesto of the Communist Party"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1761.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c781249f-0bef-5564-9dca-d84a68f8fd0b.json b/oaitestdata/clarin-oai_dc/SET_1/json/c781249f-0bef-5564-9dca-d84a68f8fd0b.json
deleted file mode 100644
index 3d738803..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c781249f-0bef-5564-9dca-d84a68f8fd0b.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "University of Konstanz"
-    ],
-    "Contributor": [
-        "Nikolaeva, Irina"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-697",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-697"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-697",
-    "PublicationTimestamp": "2004-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2004"
-    ],
-    "Publisher": [
-        "University of Konstanz"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-697;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Kolymar Yukaghir;Nikolaeva, Irina;\"Yukaghir texts, both as audio recordings, and in transcribed, translated and analysed form. There are also dictionaries and pictures.\" 52 texts.;2004;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-697;downloadable_files_count: 0;Germany;University of Konstanz;http://www.sgr.fi/yukaghir/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c781249f-0bef-5564-9dca-d84a68f8fd0b",
-    "notes": [
-        "\"Yukaghir texts, both as audio recordings, and in transcribed, translated and analysed form. There are also dictionaries and pictures.\" 52 texts."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-697"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Kolymar Yukaghir"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c78b9660-532b-56d0-948c-90ebf9abe4bc.json b/oaitestdata/clarin-oai_dc/SET_1/json/c78b9660-532b-56d0-948c-90ebf9abe4bc.json
deleted file mode 100644
index 7e718fc3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c78b9660-532b-56d0-948c-90ebf9abe4bc.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish",
-        "Serbian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/69",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/69"
-    ],
-    "PID": "http://hdl.handle.net/10794/69",
-    "PublicationTimestamp": "2015-04-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/69;2017-10-31T15:30:07Z;hdl_10794_1;hdl_10794_2;ASPAC \u2013 Swedish-Serbian (latin) (2017-10-16);ASPAC \u2013 svenska-serbiska (latin) (2017-10-16);n/a, n/a;ASPAC;Parallel;Latn;Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.;Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat.;2015-04-16;corpus;http://hdl.handle.net/10794/69;swe;srp;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/octet-stream;application/gzip;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/aspacsvsr",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c78b9660-532b-56d0-948c-90ebf9abe4bc",
-    "notes": [
-        "Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.",
-        "Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/69"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ASPAC"
-        },
-        {
-            "name": "Parallel"
-        },
-        {
-            "name": "Latn"
-        }
-    ],
-    "title": [
-        "ASPAC \u2013 Swedish-Serbian (latin) (2017-10-16)",
-        "ASPAC \u2013 svenska-serbiska (latin) (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c7d0671a-9b52-5026-aebd-c1f0c7703b7d.json b/oaitestdata/clarin-oai_dc/SET_1/json/c7d0671a-9b52-5026-aebd-c1f0c7703b7d.json
deleted file mode 100644
index 6b59fb06..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c7d0671a-9b52-5026-aebd-c1f0c7703b7d.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3813",
-    "MetadataAccess": [
-        "oai:ota:oucs:3813"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Cumberland, Richard, 1732-1811."
-    ],
-    "fulltext": "oai:ota:oucs:3813;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3813.xml;Calvary: or the death of Christ. A poem, in eight books. By Richard Cumberland.;Cumberland, Richard, 1732-1811.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c7d0671a-9b52-5026-aebd-c1f0c7703b7d",
-    "oai_identifier": [
-        "oai:ota:oucs:3813"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Calvary: or the death of Christ. A poem, in eight books. By Richard Cumberland."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3813.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c7dbf563-96b3-5e56-be01-5e1c7fd1ba6f.json b/oaitestdata/clarin-oai_dc/SET_1/json/c7dbf563-96b3-5e56-be01-5e1c7fd1ba6f.json
deleted file mode 100644
index 06172e94..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c7dbf563-96b3-5e56-be01-5e1c7fd1ba6f.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5634",
-    "MetadataAccess": [
-        "oai:ota:oucs:5634"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Okell, Benjamin."
-    ],
-    "fulltext": "oai:ota:oucs:5634;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5634.xml;A short treatise of the virtues of Dr. Bateman's pectoral drops: the nature of the distempers they cure, and the manner of their operation. Publish'd by the King's letters patents under the Great Seal of Great Britain.;Okell, Benjamin.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c7dbf563-96b3-5e56-be01-5e1c7fd1ba6f",
-    "oai_identifier": [
-        "oai:ota:oucs:5634"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A short treatise of the virtues of Dr. Bateman's pectoral drops: the nature of the distempers they cure, and the manner of their operation. Publish'd by the King's letters patents under the Great Seal of Great Britain."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5634.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c7f127d0-59bf-564a-9f0a-15351269b945.json b/oaitestdata/clarin-oai_dc/SET_1/json/c7f127d0-59bf-564a-9f0a-15351269b945.json
deleted file mode 100644
index 7a475b4f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c7f127d0-59bf-564a-9f0a-15351269b945.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml-dtd",
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 4",
-        "application/pdf",
-        "application/zip"
-    ],
-    "Language": [
-        "Danish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repository.clarin.dk:20.500.12115/22",
-    "MetadataAccess": [
-        "oai:repository.clarin.dk:20.500.12115/22"
-    ],
-    "PID": "http://hdl.handle.net/20.500.12115/22",
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Hansen, Dorte Haltrup",
-        "Braasch, Anna",
-        "Olsen, Sussi",
-        "Offersgaard, Lene"
-    ],
-    "fulltext": "oai:repository.clarin.dk:20.500.12115/22;2018-06-28T13:27:13Z;hdl_20.500.12115_1;hdl_20.500.12115_3;STO morphology (v2) - LMF format;Braasch, Anna;Olsen, Sussi;Hansen, Dorte Haltrup;Offersgaard, Lene;morphology;LMF;The STO (SprogTeknologisk Ordbase) lexicon is a comprehensive computational lexicon of Danish developed for NLP/HLT applications. The morphological layer of the lexicon , presented here in Lexical Markup Format (LMF), contains a vocabulary of 87.209 entries. The Lexical Markup Language is an internationally well\u2010known and accepted XML format and the ISO standard for Natural Language Processing (NLP) lexicons. See www.lexicalmarkupframework.org for more information on LMF and the attached documentation for the marke-up of STO.\r\nSTO LMF is created within the framework of the EU project MetaNord, and was carried out by Center for Language Technology (CST) in 2011 - 2013.;2013;lexicalConceptualResource;http://hdl.handle.net/20.500.12115/22;dan;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;PUB;text/plain; charset=utf-8;application/zip;application/pdf;application/pdf;application/xml-dtd;downloadable_files_count: 4;Centre for Language Technology, NorS, University of Copenhagen;https://cst.ku.dk/sto_ordbase/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c7f127d0-59bf-564a-9f0a-15351269b945",
-    "notes": [
-        "The STO (SprogTeknologisk Ordbase) lexicon is a comprehensive computational lexicon of Danish developed for NLP/HLT applications. The morphological layer of the lexicon , presented here in Lexical Markup Format (LMF), contains a vocabulary of 87.209 entries. The Lexical Markup Language is an internationally well\u2010known and accepted XML format and the ISO standard for Natural Language Processing (NLP) lexicons. See www.lexicalmarkupframework.org for more information on LMF and the attached documentation for the marke-up of STO.\r\nSTO LMF is created within the framework of the EU project MetaNord, and was carried out by Center for Language Technology (CST) in 2011 - 2013."
-    ],
-    "oai_identifier": [
-        "oai:repository.clarin.dk:20.500.12115/22"
-    ],
-    "oai_set": [
-        "hdl_20.500.12115_1",
-        "hdl_20.500.12115_3"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "LMF"
-        }
-    ],
-    "title": [
-        "STO morphology (v2) - LMF format"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c80a8936-dbad-506b-8da5-2c0f0b4a0339.json b/oaitestdata/clarin-oai_dc/SET_1/json/c80a8936-dbad-506b-8da5-2c0f0b4a0339.json
deleted file mode 100644
index c925e312..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c80a8936-dbad-506b-8da5-2c0f0b4a0339.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4448",
-    "MetadataAccess": [
-        "oai:ota:oucs:4448"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Griffith, Mrs. (Elizabeth), 1720?-1793."
-    ],
-    "fulltext": "oai:ota:oucs:4448;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4448.xml;The story of Lady Juliana Harley: A novel. In letters. By Mrs. Griffith. ... [pt.2];Griffith, Mrs. (Elizabeth), 1720?-1793.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c80a8936-dbad-506b-8da5-2c0f0b4a0339",
-    "oai_identifier": [
-        "oai:ota:oucs:4448"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The story of Lady Juliana Harley: A novel. In letters. By Mrs. Griffith. ... [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4448.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c821cdd4-0826-567b-96a5-05ab3801caa3.json b/oaitestdata/clarin-oai_dc/SET_1/json/c821cdd4-0826-567b-96a5-05ab3801caa3.json
deleted file mode 100644
index 81ee9567..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c821cdd4-0826-567b-96a5-05ab3801caa3.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2791",
-    "MetadataAccess": [
-        "oai:ota:oucs:2791"
-    ],
-    "PublicationTimestamp": "1720-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1720"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2791;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2791.xml;Swearer's bank;Swift, Jonathan, 1667-1745;1720;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c821cdd4-0826-567b-96a5-05ab3801caa3",
-    "oai_identifier": [
-        "oai:ota:oucs:2791"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Swearer's bank"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2791.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c82d0944-de80-5956-a4f1-c0120d251f60.json b/oaitestdata/clarin-oai_dc/SET_1/json/c82d0944-de80-5956-a4f1-c0120d251f60.json
deleted file mode 100644
index c416a0a3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c82d0944-de80-5956-a4f1-c0120d251f60.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-71",
-    "MetadataAccess": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-71"
-    ],
-    "PID": "http://hdl.handle.net/20.500.11752/ILC-71",
-    "PublicationTimestamp": "2017-06-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Del Gratta, Riccardo"
-    ],
-    "fulltext": "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-71;2018-07-23T09:13:43Z;hdl_000-c0-111_38;hdl_000-c0-111_49;Lre Map;Del Gratta, Riccardo;Language Resource;Lre Map;Initiated by ELRA and FlaReNet and introduced at LREC 2010, the LRE Map is a new mechanism intended to monitor the use and creation of language resources by collecting information on both existing and newly-created resources during the submission process. It is a collective enterprise of the LREC community, as a first step towards the creation of a very broad, community-built, Open Resource Infrastructure. It is meant to become an essential instrument to monitor the field and to identify shifts in shifts in the production, use, and evaluation of LRs and LTs over the years.\r\n\r\nAt LREC 2010, nearly 2,000 language resource forms have been filled in. Apart from providing a portrait of the resources behind the community, of their uses and usability, the LRE Map intends to be a measuring instrument for monitoring the field of language resources.\r\n\r\nThe feature has been so successful that it has been implemented also at COLING 2010 and EMNLP 2010, while other major conferences are in the pipeline, in addition to the LRE Journal.\r\nThe demo url contains only a part of the data.;2017-06-30;toolService;http://hdl.handle.net/20.500.11752/ILC-71;downloadable_files_count: 0;Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c82d0944-de80-5956-a4f1-c0120d251f60",
-    "notes": [
-        "Initiated by ELRA and FlaReNet and introduced at LREC 2010, the LRE Map is a new mechanism intended to monitor the use and creation of language resources by collecting information on both existing and newly-created resources during the submission process. It is a collective enterprise of the LREC community, as a first step towards the creation of a very broad, community-built, Open Resource Infrastructure. It is meant to become an essential instrument to monitor the field and to identify shifts in shifts in the production, use, and evaluation of LRs and LTs over the years.\r\n\r\nAt LREC 2010, nearly 2,000 language resource forms have been filled in. Apart from providing a portrait of the resources behind the community, of their uses and usability, the LRE Map intends to be a measuring instrument for monitoring the field of language resources.\r\n\r\nThe feature has been so successful that it has been implemented also at COLING 2010 and EMNLP 2010, while other major conferences are in the pipeline, in addition to the LRE Journal.\r\nThe demo url contains only a part of the data."
-    ],
-    "oai_identifier": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-71"
-    ],
-    "oai_set": [
-        "hdl_000-c0-111_38",
-        "hdl_000-c0-111_49"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Language Resource"
-        },
-        {
-            "name": "Lre Map"
-        }
-    ],
-    "title": [
-        "Lre Map"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c82efd30-9cf2-5496-b32c-56d0707a3c81.json b/oaitestdata/clarin-oai_dc/SET_1/json/c82efd30-9cf2-5496-b32c-56d0707a3c81.json
deleted file mode 100644
index 82c2d48d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c82efd30-9cf2-5496-b32c-56d0707a3c81.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Prus"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 13",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/107",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/107"
-    ],
-    "PID": "http://hdl.handle.net/11321/107",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Prus"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Prus, Prus"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/107;2015-05-21T14:45:25Z;hdl_11321_3;hdl_11321_4;MWE Prus, Faraon;Prus, Prus;Prus;2015-04-08;corpus;http://hdl.handle.net/11321/107;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 13;Prus",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c82efd30-9cf2-5496-b32c-56d0707a3c81",
-    "notes": [
-        "Prus"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/107"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Prus, Faraon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c834607f-41e5-5843-84df-4dc71decf083.json b/oaitestdata/clarin-oai_dc/SET_1/json/c834607f-41e5-5843-84df-4dc71decf083.json
deleted file mode 100644
index 53c0bf77..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c834607f-41e5-5843-84df-4dc71decf083.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4878",
-    "MetadataAccess": [
-        "oai:ota:oucs:4878"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Francklin, Thomas, 1721-1784."
-    ],
-    "fulltext": "oai:ota:oucs:4878;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4878.xml;Sermons on the relative duties: Preached at Queen-Street Chapel, and St. Paul's Covent-Garden. By the Revd. Tho. Francklin, ...;Francklin, Thomas, 1721-1784.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c834607f-41e5-5843-84df-4dc71decf083",
-    "oai_identifier": [
-        "oai:ota:oucs:4878"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Sermons on the relative duties: Preached at Queen-Street Chapel, and St. Paul's Covent-Garden. By the Revd. Tho. Francklin, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4878.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c8384e6a-5a62-51c7-81c3-bfcb94b3d6f4.json b/oaitestdata/clarin-oai_dc/SET_1/json/c8384e6a-5a62-51c7-81c3-bfcb94b3d6f4.json
deleted file mode 100644
index 8f986647..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c8384e6a-5a62-51c7-81c3-bfcb94b3d6f4.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/xml",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/556",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/556"
-    ],
-    "PID": "http://hdl.handle.net/11321/556",
-    "PublicationTimestamp": "2018-07-26T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "plWordNet",
-        "http://clarin-pl.eu/en/licenses/plwordnet-2/",
-        "PUB"
-    ],
-    "author": [
-        "Wroclaw University of Technology"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/556;2018-07-26T07:44:29Z;hdl_11321_3;hdl_11321_4;enWordNet 1.0;Wroclaw University of Technology;wordnet;Princeton WordNet;Open Multilingual Wordnet;ili;The extension of Princeton WordNet built within the CLARIN-PL project. The attached file also contains the mapping to Open Multilingual Wordnet.;2018-07-26;lexicalConceptualResource;http://hdl.handle.net/11321/556;eng;plWordNet;http://clarin-pl.eu/en/licenses/plwordnet-2/;PUB;text/plain; charset=utf-8;text/xml;downloadable_files_count: 1;Wroc\u0142aw University of Technology;http://plwordnet.pwr.wroc.pl/wordnet/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c8384e6a-5a62-51c7-81c3-bfcb94b3d6f4",
-    "notes": [
-        "The extension of Princeton WordNet built within the CLARIN-PL project. The attached file also contains the mapping to Open Multilingual Wordnet."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/556"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "wordnet"
-        },
-        {
-            "name": "Princeton WordNet"
-        },
-        {
-            "name": "Open Multilingual Wordnet"
-        },
-        {
-            "name": "ili"
-        }
-    ],
-    "title": [
-        "enWordNet 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c844181f-f58d-574a-8462-ad98d4909517.json b/oaitestdata/clarin-oai_dc/SET_1/json/c844181f-f58d-574a-8462-ad98d4909517.json
deleted file mode 100644
index b840784d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c844181f-f58d-574a-8462-ad98d4909517.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2824",
-    "MetadataAccess": [
-        "oai:ota:oucs:2824"
-    ],
-    "PublicationTimestamp": "1730-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1730"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2824;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2824.xml;The report of the committee of the Lords of his Majesty's most Honourable Privy-Council, in relation to Mr. Wood's half-Pence and farthings;Swift, Jonathan, 1667-1745;1730;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c844181f-f58d-574a-8462-ad98d4909517",
-    "oai_identifier": [
-        "oai:ota:oucs:2824"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The report of the committee of the Lords of his Majesty's most Honourable Privy-Council, in relation to Mr. Wood's half-Pence and farthings"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2824.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c84cc5f0-98d8-5e6b-a5e1-2d3fe39ab8de.json b/oaitestdata/clarin-oai_dc/SET_1/json/c84cc5f0-98d8-5e6b-a5e1-2d3fe39ab8de.json
deleted file mode 100644
index faad5c62..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c84cc5f0-98d8-5e6b-a5e1-2d3fe39ab8de.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 1.19 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2018",
-    "MetadataAccess": [
-        "oai:ota:oucs:2018"
-    ],
-    "PublicationTimestamp": "1881-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1881"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "James, Henry, 1843-1916"
-    ],
-    "fulltext": "oai:ota:oucs:2018;2018-03-01T12:11:48Z;http://ota.ox.ac.uk/headers/2018.xml;The portrait of a lady / by Henry James;James, Henry, 1843-1916;1881;text_and_corpus_linguistics;Fiction -- Great Britain -- 19th century;Novels -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 1.19 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c84cc5f0-98d8-5e6b-a5e1-2d3fe39ab8de",
-    "oai_identifier": [
-        "oai:ota:oucs:2018"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- Great Britain -- th century"
-        },
-        {
-            "name": "Novels -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "The portrait of a lady / by Henry James"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2018.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c868ab30-7193-5e21-9a5e-ba6cb8e69157.json b/oaitestdata/clarin-oai_dc/SET_1/json/c868ab30-7193-5e21-9a5e-ba6cb8e69157.json
deleted file mode 100644
index 87d5b4f0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c868ab30-7193-5e21-9a5e-ba6cb8e69157.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain",
-        "less than 512 KB"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0269",
-    "MetadataAccess": [
-        "oai:ota:oucs:0269"
-    ],
-    "PublicationYear": [
-        "70-99"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Devotional literature"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:0269;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0269.xml; The gospels  / compiled by A.Q. Morton;Bible. N.T. Gospels;70-99;text_and_corpus_linguistics;Devotional literature;grc;Oxford Text Archive, University of Oxford;text/plain;less than 512 KB;Text;Devotional literature;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c868ab30-7193-5e21-9a5e-ba6cb8e69157",
-    "oai_identifier": [
-        "oai:ota:oucs:0269"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Devotional literature"
-        }
-    ],
-    "title": [
-        " The gospels  / compiled by A.Q. Morton",
-        "Bible. N.T. Gospels"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0269.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c8823772-8ac8-57cb-9578-6b0655c115a0.json b/oaitestdata/clarin-oai_dc/SET_1/json/c8823772-8ac8-57cb-9578-6b0655c115a0.json
deleted file mode 100644
index b730b78e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c8823772-8ac8-57cb-9578-6b0655c115a0.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 614 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1937",
-    "MetadataAccess": [
-        "oai:ota:oucs:1937"
-    ],
-    "PublicationTimestamp": "1697-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1697"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Virgil"
-    ],
-    "fulltext": "oai:ota:oucs:1937;2018-04-16T11:31:15Z;http://ota.ox.ac.uk/headers/1937.xml;Aeneid. English;Virgil's Aeneid;Virgil;1697;text_and_corpus_linguistics;Poems;Epics;Translations;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 614 KB);Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c8823772-8ac8-57cb-9578-6b0655c115a0",
-    "oai_identifier": [
-        "oai:ota:oucs:1937"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems"
-        },
-        {
-            "name": "Epics"
-        },
-        {
-            "name": "Translations"
-        }
-    ],
-    "title": [
-        "Aeneid. English",
-        "Virgil's Aeneid"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1937.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c886dd9e-97f3-5297-ad91-1e8f54ce60f8.json b/oaitestdata/clarin-oai_dc/SET_1/json/c886dd9e-97f3-5297-ad91-1e8f54ce60f8.json
deleted file mode 100644
index d75da0d6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c886dd9e-97f3-5297-ad91-1e8f54ce60f8.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4919",
-    "MetadataAccess": [
-        "oai:ota:oucs:4919"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Berkeley, George, 1685-1753."
-    ],
-    "fulltext": "oai:ota:oucs:4919;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4919.xml;A defence of free-thinking in mathematics: In answer to a pamphlet of Philalethes Cantabrigiensis, intituled, Geometry no friend to infidelity, or a defence of Sir Isaac Newton, and the British mathematicians. Also an appendix concerning Mr. Walton's Vindication of the principles of fluxions ... By the author of The minute philosopher.;Berkeley, George, 1685-1753.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c886dd9e-97f3-5297-ad91-1e8f54ce60f8",
-    "oai_identifier": [
-        "oai:ota:oucs:4919"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A defence of free-thinking in mathematics: In answer to a pamphlet of Philalethes Cantabrigiensis, intituled, Geometry no friend to infidelity, or a defence of Sir Isaac Newton, and the British mathematicians. Also an appendix concerning Mr. Walton's Vindication of the principles of fluxions ... By the author of The minute philosopher."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4919.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c889609a-8047-56ab-9596-a78716113d78.json b/oaitestdata/clarin-oai_dc/SET_1/json/c889609a-8047-56ab-9596-a78716113d78.json
deleted file mode 100644
index 02f53aff..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c889609a-8047-56ab-9596-a78716113d78.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "Contributor": [
-        "Berck, Peter",
-        "Koller, Thomas"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1166",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1166"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1166",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1166;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Annex - Annotation Exploration tool;Berck, Peter;Koller, Thomas;tool in the MPI web-based framework for archive exploration (and enrichment);2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1166;downloadable_files_count: 0;Netherlands (the);Max Planck Institute for Psycholinguistics;http://tla.mpi.nl/tools/tla-tools/annex/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c889609a-8047-56ab-9596-a78716113d78",
-    "notes": [
-        "tool in the MPI web-based framework for archive exploration (and enrichment)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1166"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Annex - Annotation Exploration tool"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c89f779c-a0da-58d0-8576-207fdeb442e1.json b/oaitestdata/clarin-oai_dc/SET_1/json/c89f779c-a0da-58d0-8576-207fdeb442e1.json
deleted file mode 100644
index d6e8f5fc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c89f779c-a0da-58d0-8576-207fdeb442e1.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=56be21a2485f11e2a2aa782bcb0741351bb6f491e1dd44efa7cd9aea25654d94",
-    "MetadataAccess": [
-        "56be21a2485f11e2a2aa782bcb0741351bb6f491e1dd44efa7cd9aea25654d94"
-    ],
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "56be21a2485f11e2a2aa782bcb0741351bb6f491e1dd44efa7cd9aea25654d94;2018-11-15T16:39:57Z;corpus;corpus:text;PTPARL Corpus;The PTPARL Corpus contains approximately 975,806 running words of European Portuguese. It includes 1076 texts consisting of adapted transcriptions of the Portuguese parliament sessions, which were made available in 2004.;2015-12-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c89f779c-a0da-58d0-8576-207fdeb442e1",
-    "notes": [
-        "The PTPARL Corpus contains approximately 975,806 running words of European Portuguese. It includes 1076 texts consisting of adapted transcriptions of the Portuguese parliament sessions, which were made available in 2004."
-    ],
-    "oai_identifier": [
-        "56be21a2485f11e2a2aa782bcb0741351bb6f491e1dd44efa7cd9aea25654d94"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "PTPARL Corpus"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c8a3c9e1-d092-58f1-b5a6-38959aed57bb.json b/oaitestdata/clarin-oai_dc/SET_1/json/c8a3c9e1-d092-58f1-b5a6-38959aed57bb.json
deleted file mode 100644
index f3e08fae..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c8a3c9e1-d092-58f1-b5a6-38959aed57bb.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "Contributor": [
-        "Cabr\u00e9, Teresa"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Catalan",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-699",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-699"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-699",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-699;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Vocabulary on work-risks prevention;Cabr\u00e9, Teresa;An electronic version of a vocabulary that resulted from the collaboration with the Labour Department. Its nomenclature includes more than 1,000 terms; besides, it contains six thematic annexes and a Catalan-Spanish index.;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-699;cat;spa;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra;http://www.iula.upf.edu/rec/risclab/frames.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c8a3c9e1-d092-58f1-b5a6-38959aed57bb",
-    "notes": [
-        "An electronic version of a vocabulary that resulted from the collaboration with the Labour Department. Its nomenclature includes more than 1,000 terms; besides, it contains six thematic annexes and a Catalan-Spanish index."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-699"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Vocabulary on work-risks prevention"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c8b60f93-a8f9-550f-9b34-35620d86d018.json b/oaitestdata/clarin-oai_dc/SET_1/json/c8b60f93-a8f9-550f-9b34-35620d86d018.json
deleted file mode 100644
index 292fef67..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c8b60f93-a8f9-550f-9b34-35620d86d018.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Center for Information and Language Processing, University of Munich"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 36",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "English",
-        "German",
-        "Latin",
-        "Hungarian",
-        "Spanish",
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/LRT-1483",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/LRT-1483"
-    ],
-    "PID": "http://hdl.handle.net/11234/LRT-1483",
-    "PublicationTimestamp": "2015-03-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center for Information and Language Processing, University of Munich"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "M\u00fcller, Thomas",
-        "Sch\u00fctze, Hinrich"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/LRT-1483;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Word representations for multiple languages;M\u00fcller, Thomas;Sch\u00fctze, Hinrich;morphological dictionary;morphological analysis;PoS tagging;Dictionaries with different representations for various languages. Representations include brown clusters of different sizes and morphological dictionaries extracted using different morphological analyzers. All representations cover the most frequent 250,000 word types on the Wikipedia version of the respective language.\r\n\r\nAnalzers used: MAGYARLANC (Hungarian, Zsibrita et al. (2013)), FREELING (English and Spanish, Padro and Stanilovsky (2012)), SMOR (German, Schmid et al. (2004)), an MA from Charles University (Czech, Hajic (2001)) and LATMOR (Latin, Springmann et al. (2014)).;2015-03-01;corpus;http://hdl.handle.net/11234/LRT-1483;eng;deu;lat;hun;spa;ces;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;PUB;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 36;Center for Information and Language Processing, University of Munich;http://cistern.cis.lmu.de/marmot/naacl2015/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c8b60f93-a8f9-550f-9b34-35620d86d018",
-    "notes": [
-        "Dictionaries with different representations for various languages. Representations include brown clusters of different sizes and morphological dictionaries extracted using different morphological analyzers. All representations cover the most frequent 250,000 word types on the Wikipedia version of the respective language.\r\n\r\nAnalzers used: MAGYARLANC (Hungarian, Zsibrita et al. (2013)), FREELING (English and Spanish, Padro and Stanilovsky (2012)), SMOR (German, Schmid et al. (2004)), an MA from Charles University (Czech, Hajic (2001)) and LATMOR (Latin, Springmann et al. (2014))."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/LRT-1483"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphological dictionary"
-        },
-        {
-            "name": "morphological analysis"
-        },
-        {
-            "name": "PoS tagging"
-        }
-    ],
-    "title": [
-        "Word representations for multiple languages"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c8d21596-5c6e-5172-88fc-69b72a38b41b.json b/oaitestdata/clarin-oai_dc/SET_1/json/c8d21596-5c6e-5172-88fc-69b72a38b41b.json
deleted file mode 100644
index 6a2cb5ea..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c8d21596-5c6e-5172-88fc-69b72a38b41b.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Lancaster University"
-    ],
-    "Contributor": [
-        "Rayson, Paul"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-334",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-334"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-334",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Lancaster University"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-334;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Wmatrix;Rayson, Paul;Wmatrix is a corpus comparison and annotation tool. It is web based and incorporates the CLAWS POS tagger and the USAS semantic tagger for English. It also generates frequency lists, concordances, key words and key semantic domains by comparative frequency profiling.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-334;eng;downloadable_files_count: 0;United Kingdom;Lancaster University;http://ucrel.lancs.ac.uk/wmatrix/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c8d21596-5c6e-5172-88fc-69b72a38b41b",
-    "notes": [
-        "Wmatrix is a corpus comparison and annotation tool. It is web based and incorporates the CLAWS POS tagger and the USAS semantic tagger for English. It also generates frequency lists, concordances, key words and key semantic domains by comparative frequency profiling."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-334"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Wmatrix"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c8ddaa05-72f3-5a91-b511-9782edb194e6.json b/oaitestdata/clarin-oai_dc/SET_1/json/c8ddaa05-72f3-5a91-b511-9782edb194e6.json
deleted file mode 100644
index 6247a2b3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c8ddaa05-72f3-5a91-b511-9782edb194e6.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Centro de Tecnolog\u00edas y Aplicaciones del Lenguaje y del Habla (TALP)"
-    ],
-    "Contributor": [
-        "Boleda, Gemma"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Catalan",
-        "English",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1105",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1105"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1105",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Centro de Tecnolog\u00edas y Aplicaciones del Lenguaje y del Habla (TALP)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1105;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Wikicorpus;Boleda, Gemma;trilingual corpus;Trilingual corpus (Catalan, Spanish, English) that contains large portions of the Wikipedia (based on a 2006 dump) and has been automatically enriched with linguistic information. In its present version, it contains over 750 million words.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1105;cat;eng;spa;downloadable_files_count: 0;Spain;Centro de Tecnolog\u00edas y Aplicaciones del Lenguaje y del Habla (TALP);http://www.lsi.upc.edu/~nlp/wikicorpus/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c8ddaa05-72f3-5a91-b511-9782edb194e6",
-    "notes": [
-        "Trilingual corpus (Catalan, Spanish, English) that contains large portions of the Wikipedia (based on a 2006 dump) and has been automatically enriched with linguistic information. In its present version, it contains over 750 million words."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1105"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "trilingual corpus"
-        }
-    ],
-    "title": [
-        "Wikicorpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c8dfeb41-160b-527f-a2cd-cb24e64b245c.json b/oaitestdata/clarin-oai_dc/SET_1/json/c8dfeb41-160b-527f-a2cd-cb24e64b245c.json
deleted file mode 100644
index a1fd20a4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c8dfeb41-160b-527f-a2cd-cb24e64b245c.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4155",
-    "MetadataAccess": [
-        "oai:ota:oucs:4155"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Sharp, Granville, 1735-1813."
-    ],
-    "fulltext": "oai:ota:oucs:4155;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4155.xml;Remarks concerning the encroachments on the river Thames near Durham-yard. ... In two parts;Sharp, Granville, 1735-1813.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c8dfeb41-160b-527f-a2cd-cb24e64b245c",
-    "oai_identifier": [
-        "oai:ota:oucs:4155"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Remarks concerning the encroachments on the river Thames near Durham-yard. ... In two parts"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4155.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c8f97542-49da-5d42-9830-5e4530642b65.json b/oaitestdata/clarin-oai_dc/SET_1/json/c8f97542-49da-5d42-9830-5e4530642b65.json
deleted file mode 100644
index 0c6d6c5f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c8f97542-49da-5d42-9830-5e4530642b65.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "319 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1300",
-    "MetadataAccess": [
-        "oai:ota:oucs:1300"
-    ],
-    "PublicationTimestamp": "1760-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1760"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Letters"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Burney, Fanny,  1752-1840"
-    ],
-    "fulltext": "oai:ota:oucs:1300;2018-03-07T11:07:13Z;http://ota.ox.ac.uk/headers/1300.xml;Letters (selected) / compiled by Nigel Wood;Burney, Fanny,  1752-1840;1760-1784;text_and_corpus_linguistics;Letters -- Great Britain -- 18th century;eng;Oxford Text Archive, University of Oxford;319 KB;Text;Letters;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c8f97542-49da-5d42-9830-5e4530642b65",
-    "oai_identifier": [
-        "oai:ota:oucs:1300"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Letters -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Letters (selected) / compiled by Nigel Wood"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1300.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c94af378-16c3-5356-99b4-dbe16dd929cb.json b/oaitestdata/clarin-oai_dc/SET_1/json/c94af378-16c3-5356-99b4-dbe16dd929cb.json
deleted file mode 100644
index 4e8a07f7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c94af378-16c3-5356-99b4-dbe16dd929cb.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Wroclaw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/273",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/273"
-    ],
-    "PID": "http://hdl.handle.net/11321/273",
-    "PublicationTimestamp": "2016-04-26T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroclaw University of Technology"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "plWordNet",
-        "http://clarin-pl.eu/en/licenses/plwordnet-2/",
-        "PUB"
-    ],
-    "author": [
-        "Wroclaw University of Technology"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/273;2016-09-20T12:48:40Z;hdl_11321_3;hdl_11321_4;plWordNet 3.0;S\u0142owosie\u0107 3.0;Wroclaw University of Technology;lexical unit;lexico-semantic relations;mapping;Princeton WordNet;bilingual;plWordNet;plWordNet is a lexico-semantic network which reflects the lexical system of the Polish language. plWN currently contains 178 000 nouns, verbs, adjectives, and adverbs, 259 000 word senses, and over 600 000 relations and 240 000 inter-lingual relations between lexical units. It is now the largest wordnet in the world and is still growing.\r\n\r\nSenses in plWordNet are interconnected by relations. In the resulting network, each word is defined implicitly in reference to other words. For example, samoch\u00f3d 'car' is a kind of pojazd drogowy 'road vehicle'; it is a whole consisting of silnik 'engine', spryskiwacz 'windscreen washer', podwozie 'chassis' and so on; its close counterpart is the colloquial fura 'wheels'.\r\n\r\nAmong plWordNet's numerous applications there is its use as a Polish-English and English-Polish dictionary -- the effect of mapping onto Princeton WordNet (the first and for many years the largest wordnet in the world). plWordNet is also an important resource in natural language processing and in artificial intelligence research. For example, it is used by Google Translate for the purpose of machine translation.\r\n\r\nThe University has made plWordNet available free of charge for all applications, including commercial ones, on a licence modelled on the Princeton WordNet licence. Users may browse plWordNet via mobile version and via WordNetLoom-Viewer (application enabling display of plWN entries), as well as download source files. Programmers may access plWordNet via Web service.\r\n\r\nWe provide (currently only in download version) 31 000 lexical units marked with their sentiment values: positive, negative, ambiguous or neutral.;2016-04-26;lexicalConceptualResource;http://hdl.handle.net/11321/273;pol;eng;plWordNet;http://clarin-pl.eu/en/licenses/plwordnet-2/;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 2;Wroclaw University of Technology;http://plwordnet.pwr.wroc.pl/wordnet/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c94af378-16c3-5356-99b4-dbe16dd929cb",
-    "notes": [
-        "plWordNet is a lexico-semantic network which reflects the lexical system of the Polish language. plWN currently contains 178 000 nouns, verbs, adjectives, and adverbs, 259 000 word senses, and over 600 000 relations and 240 000 inter-lingual relations between lexical units. It is now the largest wordnet in the world and is still growing.\r\n\r\nSenses in plWordNet are interconnected by relations. In the resulting network, each word is defined implicitly in reference to other words. For example, samoch\u00f3d 'car' is a kind of pojazd drogowy 'road vehicle'; it is a whole consisting of silnik 'engine', spryskiwacz 'windscreen washer', podwozie 'chassis' and so on; its close counterpart is the colloquial fura 'wheels'.\r\n\r\nAmong plWordNet's numerous applications there is its use as a Polish-English and English-Polish dictionary -- the effect of mapping onto Princeton WordNet (the first and for many years the largest wordnet in the world). plWordNet is also an important resource in natural language processing and in artificial intelligence research. For example, it is used by Google Translate for the purpose of machine translation.\r\n\r\nThe University has made plWordNet available free of charge for all applications, including commercial ones, on a licence modelled on the Princeton WordNet licence. Users may browse plWordNet via mobile version and via WordNetLoom-Viewer (application enabling display of plWN entries), as well as download source files. Programmers may access plWordNet via Web service.\r\n\r\nWe provide (currently only in download version) 31 000 lexical units marked with their sentiment values: positive, negative, ambiguous or neutral."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/273"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "lexical unit"
-        },
-        {
-            "name": "lexico-semantic relations"
-        },
-        {
-            "name": "mapping"
-        },
-        {
-            "name": "Princeton WordNet"
-        },
-        {
-            "name": "bilingual"
-        },
-        {
-            "name": "plWordNet"
-        }
-    ],
-    "title": [
-        "plWordNet 3.0",
-        "S\u0142owosie\u0107 3.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c9674520-6035-5202-abfb-630c870e9b43.json b/oaitestdata/clarin-oai_dc/SET_1/json/c9674520-6035-5202-abfb-630c870e9b43.json
deleted file mode 100644
index e4af67cf..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c9674520-6035-5202-abfb-630c870e9b43.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Mihalcea, Rada"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Romanian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-410",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-410"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-410",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "United States"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-410;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Romanian-English parallel texts;Mihalcea, Rada;1 milion word; sentence annotation;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-410;ron;downloadable_files_count: 0;United States;http://www.cs.unt.edu/%7Erada/wpt/data.protected/Romanian-English.training.tar.gz",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c9674520-6035-5202-abfb-630c870e9b43",
-    "notes": [
-        "1 milion word; sentence annotation"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-410"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Romanian-English parallel texts"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c968d6c0-024f-50df-8999-6d3ebc651c78.json b/oaitestdata/clarin-oai_dc/SET_1/json/c968d6c0-024f-50df-8999-6d3ebc651c78.json
deleted file mode 100644
index de750853..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c968d6c0-024f-50df-8999-6d3ebc651c78.json
+++ /dev/null
@@ -1,88 +0,0 @@
-{
-    "Contact": [
-        "Fondazione Bruno Kessler, Trento, Italy"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2485",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2485"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2485",
-    "PublicationTimestamp": "2017-10-16T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Fondazione Bruno Kessler, Trento, Italy"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/H2020/645452",
-        "http://www.aclweb.org/anthology/W17-4717"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "AGREEMENT ON THE USE OF DATA IN QT21 APE Task",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21",
-        "PUB"
-    ],
-    "author": [
-        "Turchi, Marco",
-        "Chatterjee, Rajen",
-        "Negri, Matteo"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2485;2017-10-17T07:48:45Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;APE Shared Task WMT17: Human Post-edits Test Data DE-EN;Turchi, Marco;Chatterjee, Rajen;Negri, Matteo;Human post-edits;machine translation;shared task;automatic post-editing;post-editing;Human post-edited test sentences for the WMT 2017 Automatic post-editing task. This consists in 2,000 English sentences belonging to the IT domain and already tokenized. Source and target segments can be downloaded from: https://lindat.mff.cuni.cz/repository/xmlui/handle/11372/LRT-2132. All data is provided by the EU project QT21 (http://www.qt21.eu/).;2017-10-16;corpus;http://hdl.handle.net/11372/LRT-2485;eng;info:eu-repo/grantAgreement/EC/H2020/645452;http://www.aclweb.org/anthology/W17-4717;AGREEMENT ON THE USE OF DATA IN QT21 APE Task;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21;PUB;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 1;Fondazione Bruno Kessler, Trento, Italy;http://www.statmt.org/wmt17/ape-task.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c968d6c0-024f-50df-8999-6d3ebc651c78",
-    "notes": [
-        "Human post-edited test sentences for the WMT 2017 Automatic post-editing task. This consists in 2,000 English sentences belonging to the IT domain and already tokenized. Source and target segments can be downloaded from: https://lindat.mff.cuni.cz/repository/xmlui/handle/11372/LRT-2132. All data is provided by the EU project QT21 (http://www.qt21.eu/)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2485"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Human post-edits"
-        },
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "shared task"
-        },
-        {
-            "name": "automatic post-editing"
-        },
-        {
-            "name": "post-editing"
-        }
-    ],
-    "title": [
-        "APE Shared Task WMT17: Human Post-edits Test Data DE-EN"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c97151d4-238b-56de-9d7a-ad8da0feb7a8.json b/oaitestdata/clarin-oai_dc/SET_1/json/c97151d4-238b-56de-9d7a-ad8da0feb7a8.json
deleted file mode 100644
index e8a566f8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c97151d4-238b-56de-9d7a-ad8da0feb7a8.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3450",
-    "MetadataAccess": [
-        "oai:ota:oucs:3450"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "More, Hannah, 1745-1833."
-    ],
-    "fulltext": "oai:ota:oucs:3450;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3450.xml;Black Giles the poacher: with some account of a family who had rather live by their wits than their work. Part I.;Black Giles the poacher.;More, Hannah, 1745-1833.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c97151d4-238b-56de-9d7a-ad8da0feb7a8",
-    "oai_identifier": [
-        "oai:ota:oucs:3450"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Black Giles the poacher: with some account of a family who had rather live by their wits than their work. Part I.",
-        "Black Giles the poacher."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3450.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c98c0b60-5314-5884-8fbd-f4b5454e226a.json b/oaitestdata/clarin-oai_dc/SET_1/json/c98c0b60-5314-5884-8fbd-f4b5454e226a.json
deleted file mode 100644
index bbc4302e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c98c0b60-5314-5884-8fbd-f4b5454e226a.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Grebl Ignacy"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-558",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-558"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D23-D",
-    "PublicationTimestamp": "1785-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1785"
-    ],
-    "Publisher": [
-        "Grebl Ignacy"
-    ],
-    "RelatedIdentifier": [
-        "http://pbc.biaman.pl/Content/558"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "author": [
-        "[Heineccius, Jan Christian (1718-1791)]"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-558;2019-03-01T15:41:49Z;Ustanowienia prawa cywilnego w sposobie \u0142atwym zebrane [...].T. 1.;[Heineccius, Jan Christian (1718-1791)];Prawo cywilne- historia;ilo\u015b\u0107 skan\u00f3w: 197 ; sygn. S-635;Grebl Ignacy;1785;starodruk;application/xml;clarind-uds:poldilemma-558;hdl:11858/00-246C-0000-0023-8D23-D;pol;lat;http://pbc.biaman.pl/Content/558;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c98c0b60-5314-5884-8fbd-f4b5454e226a",
-    "notes": [
-        "ilo\u015b\u0107 skan\u00f3w: 197 ; sygn. S-635"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-558"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Prawo cywilne- historia"
-        }
-    ],
-    "title": [
-        "Ustanowienia prawa cywilnego w sposobie \u0142atwym zebrane [...].T. 1."
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c99a6a53-49c0-5564-a04f-dcd28b1af00a.json b/oaitestdata/clarin-oai_dc/SET_1/json/c99a6a53-49c0-5564-a04f-dcd28b1af00a.json
deleted file mode 100644
index c392448f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c99a6a53-49c0-5564-a04f-dcd28b1af00a.json
+++ /dev/null
@@ -1,91 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Electrical Engineering and Computer Science, University of Maribor"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 3",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1190",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1190"
-    ],
-    "PID": "http://hdl.handle.net/11356/1190",
-    "PublicationTimestamp": "2018-08-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Faculty of Electrical Engineering and Computer Science, University of Maribor"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11356/1158"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "Sepesy Mau\u010dec, Mirjam",
-        "Erjavec, Toma\u017e",
-        "Poto\u010dnik, Toma\u017e",
-        "Verdonik, Darinka"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1190;2018-10-24T20:57:33Z;hdl_11356_1023;hdl_11356_1024;Spoken corpus Gos VideoLectures 3.0 (transcription);Verdonik, Darinka;Poto\u010dnik, Toma\u017e;Sepesy Mau\u010dec, Mirjam;Erjavec, Toma\u017e;speech database;spoken corpus;academic speech;speech transcription;speech recognition;TEI;Gos VideoLectures is an add-on to the Gos reference corpus of spoken Slovene (http://hdl.handle.net/11356/1040), and covers public academic speech. \r\nThe Gos VideoLectures corpus contains a selection of public lectures available through the web portal Videolectures.net provided by the Jo\u017eef Stefan Institute, and covers 37 lectures and 16 hours of speech. \r\nThis resource contains only annotated transcriptions of the corpus \u2013 audio recordings are available at http://hdl.handle.net/11356/1189.\r\n\r\nAll transcriptions for Gos VideoLectures were done manually and carefully checked. The main guidelines for transcription were those of the Gos corpus (http://www.korpus-gos.net/Support/About). The transcription tool Transcriber 1.5.1 (http://trans.sourceforge.net/en/presentation.php) was used for making transcriptions. It can be also used for reading or exporting transcriptions (.trs files) to different formats.\r\n\r\nThe transcriptions comprise the TRS files with tabular metadata, their conversion to TEI and to the CWB vertical file format. Each recording has two TRS files, one with pronunciation-based and the other with the standardised/normalised transcription. The TEI and CWB encodings join these two transcriptions at the token level, with the normalised words being also automatically PoS tagged and lemmatised.\r\n\r\nThe corpus can be used for training continuous speech recognition for Slovene language, for phonetic research or any other research of Slovene academic speech.;2018-08-01;corpus;http://hdl.handle.net/11356/1190;slv;http://hdl.handle.net/11356/1158;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;https://creativecommons.org/licenses/by/4.0/;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 3;Faculty of Electrical Engineering and Computer Science, University of Maribor",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c99a6a53-49c0-5564-a04f-dcd28b1af00a",
-    "notes": [
-        "Gos VideoLectures is an add-on to the Gos reference corpus of spoken Slovene (http://hdl.handle.net/11356/1040), and covers public academic speech. \r\nThe Gos VideoLectures corpus contains a selection of public lectures available through the web portal Videolectures.net provided by the Jo\u017eef Stefan Institute, and covers 37 lectures and 16 hours of speech. \r\nThis resource contains only annotated transcriptions of the corpus \u2013 audio recordings are available at http://hdl.handle.net/11356/1189.\r\n\r\nAll transcriptions for Gos VideoLectures were done manually and carefully checked. The main guidelines for transcription were those of the Gos corpus (http://www.korpus-gos.net/Support/About). The transcription tool Transcriber 1.5.1 (http://trans.sourceforge.net/en/presentation.php) was used for making transcriptions. It can be also used for reading or exporting transcriptions (.trs files) to different formats.\r\n\r\nThe transcriptions comprise the TRS files with tabular metadata, their conversion to TEI and to the CWB vertical file format. Each recording has two TRS files, one with pronunciation-based and the other with the standardised/normalised transcription. The TEI and CWB encodings join these two transcriptions at the token level, with the normalised words being also automatically PoS tagged and lemmatised.\r\n\r\nThe corpus can be used for training continuous speech recognition for Slovene language, for phonetic research or any other research of Slovene academic speech."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1190"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech database"
-        },
-        {
-            "name": "spoken corpus"
-        },
-        {
-            "name": "academic speech"
-        },
-        {
-            "name": "speech transcription"
-        },
-        {
-            "name": "speech recognition"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "Spoken corpus Gos VideoLectures 3.0 (transcription)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c9a23d39-23aa-542f-9120-c9476ffdc895.json b/oaitestdata/clarin-oai_dc/SET_1/json/c9a23d39-23aa-542f-9120-c9476ffdc895.json
deleted file mode 100644
index 7d30e57d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c9a23d39-23aa-542f-9120-c9476ffdc895.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(2 files : ca. 220, 16.7 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1417",
-    "MetadataAccess": [
-        "oai:ota:oucs:1417"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Browning, Robert, 1812-1889"
-    ],
-    "fulltext": "oai:ota:oucs:1417;2018-03-05T14:20:38Z;http://ota.ox.ac.uk/headers/1417.xml;Paracelsus;Browning, Robert, 1812-1889;default: 1976-01-01;text_and_corpus_linguistics;Poems -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;text/plain;(2 files : ca. 220, 16.7 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c9a23d39-23aa-542f-9120-c9476ffdc895",
-    "oai_identifier": [
-        "oai:ota:oucs:1417"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Paracelsus"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1417.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c9a59249-a63f-5725-a373-84cc90c2e8e6.json b/oaitestdata/clarin-oai_dc/SET_1/json/c9a59249-a63f-5725-a373-84cc90c2e8e6.json
deleted file mode 100644
index 474343b4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c9a59249-a63f-5725-a373-84cc90c2e8e6.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Berlin-Brandenburg Academy of Sciences and Humanities"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/tei+xml",
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-970",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-970"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-970",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Berlin-Brandenburg Academy of Sciences and Humanities"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-970;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;DWDS Kernkorpus;Germanistik;German reference corpus. Ca 100 million words, 20th Century. Searchable online. Part of 'Digitales W\u00f6rterbuch der deutschen Sprache des 20. Jahrhunderts' project; Korpus der BBAW; Grundlage des DWDS;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-970;deu;application/tei+xml;downloadable_files_count: 0;Germany;Berlin-Brandenburg Academy of Sciences and Humanities;http://www.dwds.de/ressourcen/kernkorpus/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c9a59249-a63f-5725-a373-84cc90c2e8e6",
-    "notes": [
-        "German reference corpus. Ca 100 million words, 20th Century. Searchable online. Part of 'Digitales W\u00f6rterbuch der deutschen Sprache des 20. Jahrhunderts' project; Korpus der BBAW; Grundlage des DWDS"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-970"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "DWDS Kernkorpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c9bd1cbb-cae3-5a05-9a6a-fe3c6f09174b.json b/oaitestdata/clarin-oai_dc/SET_1/json/c9bd1cbb-cae3-5a05-9a6a-fe3c6f09174b.json
deleted file mode 100644
index 0ff4dba7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c9bd1cbb-cae3-5a05-9a6a-fe3c6f09174b.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4614",
-    "MetadataAccess": [
-        "oai:ota:oucs:4614"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Arbuthnot, John, 1667-1735."
-    ],
-    "fulltext": "oai:ota:oucs:4614;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4614.xml;Proposals for printing a very curious discourse: in two volumes in quarto, intitled, Pseudologia politik\u00c4\u0093; or, a treatise of the art of political lying, with an abstract of the first volume of the said treatise.;Arbuthnot, John, 1667-1735.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c9bd1cbb-cae3-5a05-9a6a-fe3c6f09174b",
-    "oai_identifier": [
-        "oai:ota:oucs:4614"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Proposals for printing a very curious discourse: in two volumes in quarto, intitled, Pseudologia politik\u00c4\u0093; or, a treatise of the art of political lying, with an abstract of the first volume of the said treatise."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4614.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c9cfec3e-13a8-52c7-b0e2-d20df8237f16.json b/oaitestdata/clarin-oai_dc/SET_1/json/c9cfec3e-13a8-52c7-b0e2-d20df8237f16.json
deleted file mode 100644
index 09770c2e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c9cfec3e-13a8-52c7-b0e2-d20df8237f16.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Universidad de Alicante"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Catalan"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1169",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1169"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1169",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Universidad de Alicante"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1169;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Apertium Old Catalan morphological analyzer;morphological analyzer;A RESTful morphological analyzer for Old Catalan.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1169;cat;downloadable_files_count: 0;Spain;Universidad de Alicante;http://xixona.dlsi.ua.es/~fran/oldca/index.php",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c9cfec3e-13a8-52c7-b0e2-d20df8237f16",
-    "notes": [
-        "A RESTful morphological analyzer for Old Catalan."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1169"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphological analyzer"
-        }
-    ],
-    "title": [
-        "Apertium Old Catalan morphological analyzer"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c9d8008a-6444-5f7d-ba6b-08332d5e4b8d.json b/oaitestdata/clarin-oai_dc/SET_1/json/c9d8008a-6444-5f7d-ba6b-08332d5e4b8d.json
deleted file mode 100644
index f6a89974..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c9d8008a-6444-5f7d-ba6b-08332d5e4b8d.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3895",
-    "MetadataAccess": [
-        "oai:ota:oucs:3895"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Whitehead, William, 1715-1785."
-    ],
-    "fulltext": "oai:ota:oucs:3895;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3895.xml;A charge to the poets: By William Whitehead, Esq; Poet Laureat.;Whitehead, William, 1715-1785.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c9d8008a-6444-5f7d-ba6b-08332d5e4b8d",
-    "oai_identifier": [
-        "oai:ota:oucs:3895"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A charge to the poets: By William Whitehead, Esq; Poet Laureat."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3895.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/c9e7b568-f861-5e89-b744-a1071c467b33.json b/oaitestdata/clarin-oai_dc/SET_1/json/c9e7b568-f861-5e89-b744-a1071c467b33.json
deleted file mode 100644
index 90eefa86..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/c9e7b568-f861-5e89-b744-a1071c467b33.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "University of \u0141\u00f3d\u017a"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/288",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/288"
-    ],
-    "PID": "http://hdl.handle.net/11321/288",
-    "PublicationTimestamp": "2016-03-08T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "University of \u0141\u00f3d\u017a"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Dr\u00f3\u017cd\u017c, \u0141ukasz",
-        "Kowalczyk, Pawe\u0142",
-        "P\u0119zik, Piotr",
-        "Wilk, Pawe\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/288;2016-06-03T14:42:11Z;hdl_11321_3;hdl_11321_4;SlopeQ for BNC Search Engine;P\u0119zik, Piotr;Kowalczyk, Pawe\u0142;Wilk, Pawe\u0142;Dr\u00f3\u017cd\u017c, \u0141ukasz;British National Corpus;corpus search engine;SlopeQ;The SlopeQ for BNC Search Engine provides access to the British National Corpus dataset. \r\nIn addition to linguistically motivated corpus queries, it supports a number of data exploration and \r\nvisualisation features. Most of the functionality of the search engine is available through a \r\nREST web service.;2016-03-08;toolService;http://hdl.handle.net/11321/288;eng;Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0);http://creativecommons.org/licenses/by-nc-nd/3.0/;CC;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;University of \u0141\u00f3d\u017a;http://pelcra.clarin-pl.eu/SlopeqBNC",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c9e7b568-f861-5e89-b744-a1071c467b33",
-    "notes": [
-        "The SlopeQ for BNC Search Engine provides access to the British National Corpus dataset. \r\nIn addition to linguistically motivated corpus queries, it supports a number of data exploration and \r\nvisualisation features. Most of the functionality of the search engine is available through a \r\nREST web service."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/288"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "British National Corpus"
-        },
-        {
-            "name": "corpus search engine"
-        },
-        {
-            "name": "SlopeQ"
-        }
-    ],
-    "title": [
-        "SlopeQ for BNC Search Engine"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ca119c7b-44e6-52fe-9109-ed66fd2eb6a0.json b/oaitestdata/clarin-oai_dc/SET_1/json/ca119c7b-44e6-52fe-9109-ed66fd2eb6a0.json
deleted file mode 100644
index e66018b2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ca119c7b-44e6-52fe-9109-ed66fd2eb6a0.json
+++ /dev/null
@@ -1,91 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/543",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/543"
-    ],
-    "PID": "http://hdl.handle.net/11321/543",
-    "PublicationTimestamp": "2018-07-23T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Oleksy, Marcin",
-        "Wieczorek, Jan",
-        "Marci\u0144czuk, Micha\u0142",
-        "Berna\u015b, Tomasz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/543;2018-07-25T12:32:18Z;hdl_11321_3;hdl_11321_4;Polish Spatial Texts 1.0;Oleksy, Marcin;Wieczorek, Jan;Berna\u015b, Tomasz;Marci\u0144czuk, Micha\u0142;corpora annotation;corpus;manually annotated corpus;annotated corpus;spatial expressions;spatial. Spatial Role Labellig;ISO-Space;Texts derived from polish travel blogs manually annotated with spatial expressions, A spatial expression is a text fragment which describes a relative location of two or more physical objects to each other.;2018-07-23;corpus;http://hdl.handle.net/11321/543;pol;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;Wroc\u0142aw University of Science and Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ca119c7b-44e6-52fe-9109-ed66fd2eb6a0",
-    "notes": [
-        "Texts derived from polish travel blogs manually annotated with spatial expressions, A spatial expression is a text fragment which describes a relative location of two or more physical objects to each other."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/543"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpora annotation"
-        },
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "manually annotated corpus"
-        },
-        {
-            "name": "annotated corpus"
-        },
-        {
-            "name": "spatial expressions"
-        },
-        {
-            "name": "spatial. Spatial Role Labellig"
-        },
-        {
-            "name": "ISO-Space"
-        }
-    ],
-    "title": [
-        "Polish Spatial Texts 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ca27cccf-cad7-580d-be54-5571c939a93b.json b/oaitestdata/clarin-oai_dc/SET_1/json/ca27cccf-cad7-580d-be54-5571c939a93b.json
deleted file mode 100644
index 0ad06d60..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ca27cccf-cad7-580d-be54-5571c939a93b.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Berlin-Brandenburg Academy of Sciences and Humanities"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/tei+xml",
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1057",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1057"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1057",
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Berlin-Brandenburg Academy of Sciences and Humanities"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1057;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;W\u00f6rterbuch der deutschen Gegenwartssprache (WDG);6 volume dictionary of Standard German, retro-digitization of the printed version which appeared 196\u2013-1977;2011;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1057;deu;application/tei+xml;downloadable_files_count: 0;Germany;Berlin-Brandenburg Academy of Sciences and Humanities;http://www.dwds.de/ressourcen/woerterbuecher/wdg/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ca27cccf-cad7-580d-be54-5571c939a93b",
-    "notes": [
-        "6 volume dictionary of Standard German, retro-digitization of the printed version which appeared 196\u2013-1977"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1057"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "W\u00f6rterbuch der deutschen Gegenwartssprache (WDG)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ca4d0f4a-3622-5704-bca3-a0a541c60d7f.json b/oaitestdata/clarin-oai_dc/SET_1/json/ca4d0f4a-3622-5704-bca3-a0a541c60d7f.json
deleted file mode 100644
index 2f16f27b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ca4d0f4a-3622-5704-bca3-a0a541c60d7f.json
+++ /dev/null
@@ -1,100 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1794",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1794"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1794",
-    "PublicationTimestamp": "2015-12-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Cinkov\u00e1, Silvie",
-        "Baisa, V\u00edt",
-        "Krej\u010dov\u00e1, Ema",
-        "Vernerov\u00e1, Anna"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1794;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;VPS-GradeUp (2016-10-10);Baisa, V\u00edt;Cinkov\u00e1, Silvie;Krej\u010dov\u00e1, Ema;Vernerov\u00e1, Anna;Pattern Dictionary of English Verbs;usage patterns;lexical semantics;dictionaries;clustering;Corpus Pattern Analysis;verbs;graded decisions;Likert scale;Word Sense Disambiguation;VPS-GradeUp is a collection of triple manual annotations of 29 English verbs based on the Pattern Dictionary of English Verbs (PDEV) and comprising the following lemmas: abolish, act, adjust, advance, answer, approve, bid, cancel, conceive, cultivate, cure, distinguish, embrace, execute, hire, last, manage, murder, need, pack, plan, point, praise, prescribe, sail, seal, see, talk, urge . It contains results from two different tasks:\r\n\r\n 1.   Graded decisions\r\n 2.   Best-fit pattern (WSD) .\r\n\r\nIn both tasks, the annotators were matching verb senses defined by the PDEV patterns with 50 actual uses of each verb (using concordances from the BNC [2]). The verbs were randomly selected from a list of completed PDEV lemmas with at least 3 patterns and at least 100 BNC concordances not previously annotated by PDEV\u2019s own annotators. Also, the selection excluded verbs contained in VPS-30-En[3], a data set we developed earlier. This data set was built within the project Reviving Zellig S. Harris: more linguistic information for distributional lexical analysis of English and Czech and in connection with the SemEval-2015 CPA-related task.;2015-12-01;lexicalConceptualResource;http://hdl.handle.net/11234/1-1794;eng;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://ufal.mff.cuni.cz/vpsgradeup",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ca4d0f4a-3622-5704-bca3-a0a541c60d7f",
-    "notes": [
-        "VPS-GradeUp is a collection of triple manual annotations of 29 English verbs based on the Pattern Dictionary of English Verbs (PDEV) and comprising the following lemmas: abolish, act, adjust, advance, answer, approve, bid, cancel, conceive, cultivate, cure, distinguish, embrace, execute, hire, last, manage, murder, need, pack, plan, point, praise, prescribe, sail, seal, see, talk, urge . It contains results from two different tasks:\r\n\r\n 1.   Graded decisions\r\n 2.   Best-fit pattern (WSD) .\r\n\r\nIn both tasks, the annotators were matching verb senses defined by the PDEV patterns with 50 actual uses of each verb (using concordances from the BNC [2]). The verbs were randomly selected from a list of completed PDEV lemmas with at least 3 patterns and at least 100 BNC concordances not previously annotated by PDEV\u2019s own annotators. Also, the selection excluded verbs contained in VPS-30-En[3], a data set we developed earlier. This data set was built within the project Reviving Zellig S. Harris: more linguistic information for distributional lexical analysis of English and Czech and in connection with the SemEval-2015 CPA-related task."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1794"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Pattern Dictionary English Verbs"
-        },
-        {
-            "name": "usage patterns"
-        },
-        {
-            "name": "lexical semantics"
-        },
-        {
-            "name": "dictionaries"
-        },
-        {
-            "name": "clustering"
-        },
-        {
-            "name": "Corpus Pattern Analysis"
-        },
-        {
-            "name": "verbs"
-        },
-        {
-            "name": "graded decisions"
-        },
-        {
-            "name": "Likert scale"
-        },
-        {
-            "name": "Word Sense Disambiguation"
-        }
-    ],
-    "title": [
-        "VPS-GradeUp (2016-10-10)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ca4e8788-153d-5cc6-964c-1a69bcd1e80d.json b/oaitestdata/clarin-oai_dc/SET_1/json/ca4e8788-153d-5cc6-964c-1a69bcd1e80d.json
deleted file mode 100644
index 9bd16002..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ca4e8788-153d-5cc6-964c-1a69bcd1e80d.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Duzy Pokoj"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 86",
-        "text/plain; charset=utf-8",
-        "text/plain"
-    ],
-    "Language": [],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/516",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/516"
-    ],
-    "PID": "http://hdl.handle.net/11321/516",
-    "PublicationTimestamp": "2018-07-13T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Duzy Pokoj"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Modrzejewska, Ewa"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/516;2018-07-13T13:51:12Z;hdl_11321_3;hdl_11321_4;test corpus;Modrzejewska, Ewa;Modrzejewska, Ewa;UE;Polska;Unia;wystapienia polityk\u00f3w;2018-07-13;corpus;http://hdl.handle.net/11321/516;polski;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;downloadable_files_count: 86;Duzy Pokoj",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ca4e8788-153d-5cc6-964c-1a69bcd1e80d",
-    "notes": [
-        "wystapienia polityk\u00f3w"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/516"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "UE"
-        },
-        {
-            "name": "Polska"
-        },
-        {
-            "name": "Unia"
-        }
-    ],
-    "title": [
-        "test corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ca525652-2a43-56a7-bf1b-69cd6b58b771.json b/oaitestdata/clarin-oai_dc/SET_1/json/ca525652-2a43-56a7-bf1b-69cd6b58b771.json
deleted file mode 100644
index fe7f9093..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ca525652-2a43-56a7-bf1b-69cd6b58b771.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Department of Baltic Languages, University of Latvia",
-        "Institute of Mathematics and Computer Science, University of Latvia"
-    ],
-    "Contributor": [
-        "Andronova, Everita"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Latvian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-360",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-360"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-360",
-    "PublicationTimestamp": "2009-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2009"
-    ],
-    "Publisher": [
-        "Department of Baltic Languages, University of Latvia",
-        "Institute of Mathematics and Computer Science, University of Latvia"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Latvia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-360;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;SENIE;Andronova, Everita;diachronic corpus;Diachronic Corpus of Early Written Latvian Texts (16-18th c.). > 1 mill. running words (work is on-going). The main data are ecclesiastical texts, secular texts (laws, fiction) and some first bilingual (Latvian-German) dictionaries. A KWIC-based concordancer, as well as inverse vocabulary, frequency lists and word lists are provided. Some source facsimiles are available.;2009;corpus;http://hdl.handle.net/11372/LRT-360;lav;application/octet-stream;downloadable_files_count: 0;Latvia;Department of Baltic Languages, University of Latvia;Institute of Mathematics and Computer Science, University of Latvia;http://www.korpuss.lv/senie",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ca525652-2a43-56a7-bf1b-69cd6b58b771",
-    "notes": [
-        "Diachronic Corpus of Early Written Latvian Texts (16-18th c.). > 1 mill. running words (work is on-going). The main data are ecclesiastical texts, secular texts (laws, fiction) and some first bilingual (Latvian-German) dictionaries. A KWIC-based concordancer, as well as inverse vocabulary, frequency lists and word lists are provided. Some source facsimiles are available."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-360"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "diachronic corpus"
-        }
-    ],
-    "title": [
-        "SENIE"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ca545031-3416-55e9-b87a-e337597f8cd8.json b/oaitestdata/clarin-oai_dc/SET_1/json/ca545031-3416-55e9-b87a-e337597f8cd8.json
deleted file mode 100644
index c4d2fe4b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ca545031-3416-55e9-b87a-e337597f8cd8.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "Norwegian Biodiversity Information Centre"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "application/octet-stream",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Norwegian Bokm\u00e5l",
-        "Norwegian Nynorsk",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/115",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/115"
-    ],
-    "PID": "http://hdl.handle.net/11509/115",
-    "PublicationTimestamp": "2017-01-10T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Norwegian Biodiversity Information Centre"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "CLARIN_PUB-BY",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaPub?BY=1",
-        "PUB"
-    ],
-    "author": [
-        "Norwegian Biodiversity Information Centre"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/115;2017-01-18T09:12:55Z;hdl_11509_1;hdl_11509_2;Norwegian biodiversity terminology database;Norwegian Biodiversity Information Centre;Fauna;Marine;Terminology;Terminological;Termbase;The resource Artsdatabanken is a terminological database containing terms in Norwegian, Latin and other languages designating family/genus/species of marine species in the Norwegian marine fauna.;2017-01-10;lexicalConceptualResource;http://hdl.handle.net/11509/115;nob;nno;lat;CLARIN_PUB-BY;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaPub?BY=1;PUB;application/zip;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;Norwegian Biodiversity Information Centre;http://www.terminologi.no",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ca545031-3416-55e9-b87a-e337597f8cd8",
-    "notes": [
-        "The resource Artsdatabanken is a terminological database containing terms in Norwegian, Latin and other languages designating family/genus/species of marine species in the Norwegian marine fauna."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/115"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Fauna"
-        },
-        {
-            "name": "Marine"
-        },
-        {
-            "name": "Terminology"
-        },
-        {
-            "name": "Terminological"
-        },
-        {
-            "name": "Termbase"
-        }
-    ],
-    "title": [
-        "Norwegian biodiversity terminology database"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ca7f4de1-a781-5679-844a-98f52c5776c9.json b/oaitestdata/clarin-oai_dc/SET_1/json/ca7f4de1-a781-5679-844a-98f52c5776c9.json
deleted file mode 100644
index 2f5439fd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ca7f4de1-a781-5679-844a-98f52c5776c9.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "Fondazione Bruno Kessler, Trento, Italy"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "English",
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2132",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2132"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2132",
-    "PublicationTimestamp": "2017-04-10T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Fondazione Bruno Kessler, Trento, Italy"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/H2020/645452"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "AGREEMENT ON THE USE OF DATA IN QT21 APE Task",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21",
-        "PUB"
-    ],
-    "author": [
-        "Turchi, Marco",
-        "Chatterjee, Rajen",
-        "Negri, Marco"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2132;2017-09-04T10:29:31Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Test Data DE-EN APE Shared Task WMT17;Turchi, Marco;Chatterjee, Rajen;Negri, Marco;machine translation;shared task;automatic post-editing;post-editing;Test data for the WMT 2017 Automatic post-editing task (the same used for the Sentence-level Quality Estimation task). They consist in German-English triplets (source and target) belonging to the pharmacological domain and already tokenized. Test set contains 2,000 pairs. All data is provided by the EU project QT21 (http://www.qt21.eu/).;2017-04-10;corpus;http://hdl.handle.net/11372/LRT-2132;eng;deu;info:eu-repo/grantAgreement/EC/H2020/645452;AGREEMENT ON THE USE OF DATA IN QT21 APE Task;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Fondazione Bruno Kessler, Trento, Italy;http://www.statmt.org/wmt17/ape-task.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ca7f4de1-a781-5679-844a-98f52c5776c9",
-    "notes": [
-        "Test data for the WMT 2017 Automatic post-editing task (the same used for the Sentence-level Quality Estimation task). They consist in German-English triplets (source and target) belonging to the pharmacological domain and already tokenized. Test set contains 2,000 pairs. All data is provided by the EU project QT21 (http://www.qt21.eu/)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2132"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "shared task"
-        },
-        {
-            "name": "automatic post-editing"
-        },
-        {
-            "name": "post-editing"
-        }
-    ],
-    "title": [
-        "Test Data DE-EN APE Shared Task WMT17"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ca7f82d9-21b5-5931-9934-a6cc50ebd58b.json b/oaitestdata/clarin-oai_dc/SET_1/json/ca7f82d9-21b5-5931-9934-a6cc50ebd58b.json
deleted file mode 100644
index f9030434..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ca7f82d9-21b5-5931-9934-a6cc50ebd58b.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3080",
-    "MetadataAccess": [
-        "oai:ota:oucs:3080"
-    ],
-    "PublicationTimestamp": "1837-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1837"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Quincey, Thomas de, 1785-1859"
-    ],
-    "fulltext": "oai:ota:oucs:3080;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3080.xml;Revolt of the Tartars;Quincey, Thomas de, 1785-1859;not after: 1837;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ca7f82d9-21b5-5931-9934-a6cc50ebd58b",
-    "oai_identifier": [
-        "oai:ota:oucs:3080"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Revolt of the Tartars"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3080.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ca981b90-9597-59d3-99be-47063fe812cb.json b/oaitestdata/clarin-oai_dc/SET_1/json/ca981b90-9597-59d3-99be-47063fe812cb.json
deleted file mode 100644
index 52739465..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ca981b90-9597-59d3-99be-47063fe812cb.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Laura Przybyys\u0142awska"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/msword",
-        "downloadable_files_count: 3",
-        "text/plain",
-        "application/vnd.oasis.opendocument.text"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/471",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/471"
-    ],
-    "PID": "http://hdl.handle.net/11321/471",
-    "PublicationTimestamp": "2018-05-19T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Laura Przybyys\u0142awska"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "BSD 2 Clause",
-        "https://opensource.org/licenses/BSD-2-Clause",
-        "PUB"
-    ],
-    "author": [
-        "Przybys\u0142awska, Laura"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/471;2018-05-19T08:42:10Z;hdl_11321_3;hdl_11321_4;warsztaty GDA;Przybys\u0142awska, Laura;warszaty dansk;wwarszaty gdansk calrin blabla;2018-05-19;corpus;http://hdl.handle.net/11321/471;pol;BSD 2 Clause;https://opensource.org/licenses/BSD-2-Clause;PUB;text/plain; charset=utf-8;text/plain;application/vnd.oasis.opendocument.text;application/msword;downloadable_files_count: 3;Laura Przybyys\u0142awska",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ca981b90-9597-59d3-99be-47063fe812cb",
-    "notes": [
-        "wwarszaty gdansk calrin blabla"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/471"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "warszaty dansk"
-        }
-    ],
-    "title": [
-        "warsztaty GDA"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/caa93a8e-c192-5cf2-80c8-a1ee7c18e7a3.json b/oaitestdata/clarin-oai_dc/SET_1/json/caa93a8e-c192-5cf2-80c8-a1ee7c18e7a3.json
deleted file mode 100644
index a950f9d7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/caa93a8e-c192-5cf2-80c8-a1ee7c18e7a3.json
+++ /dev/null
@@ -1,92 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2143",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2143"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2143",
-    "PublicationTimestamp": "2017-04-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0)",
-        "http://creativecommons.org/licenses/by-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Jane\u0161, Petr",
-        "\u0160tindlov\u00e1, Barbora",
-        "Rosen, Alexandr",
-        "Hrdli\u010dka, Milan",
-        "\u0160ormov\u00e1, Kate\u0159ina",
-        "Toufarov\u00e1, Dagmar",
-        "Pol\u00e1\u010dkov\u00e1, Marie",
-        "Hrdli\u010dkov\u00e1, Tereza",
-        "\u0160ebesta, Karel",
-        "N\u00e1plava, Jakub",
-        "Pierscieniak, Piotr",
-        "Lund\u00e1kov\u00e1, Kate\u0159ina",
-        "Bed\u0159ichov\u00e1, Zuzanna",
-        "Hana, Ji\u0159\u00ed",
-        "Jel\u00ednek, Tom\u00e1\u0161",
-        "\u0160kodov\u00e1, Svatava",
-        "Skoumalov\u00e1, Hana",
-        "Straka, Milan",
-        "Sl\u00e1dek, \u0160imon",
-        "Petkevi\u010d, Vladim\u00edr"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2143;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;CzeSL Grammatical Error Correction Dataset (CzeSL-GEC);\u0160ebesta, Karel;Bed\u0159ichov\u00e1, Zuzanna;\u0160ormov\u00e1, Kate\u0159ina;\u0160tindlov\u00e1, Barbora;Hrdli\u010dka, Milan;Hrdli\u010dkov\u00e1, Tereza;Hana, Ji\u0159\u00ed;Petkevi\u010d, Vladim\u00edr;Jel\u00ednek, Tom\u00e1\u0161;\u0160kodov\u00e1, Svatava;Jane\u0161, Petr;Lund\u00e1kov\u00e1, Kate\u0159ina;Skoumalov\u00e1, Hana;Sl\u00e1dek, \u0160imon;Pierscieniak, Piotr;Toufarov\u00e1, Dagmar;Straka, Milan;Rosen, Alexandr;N\u00e1plava, Jakub;Pol\u00e1\u010dkov\u00e1, Marie;natural language correction;grammatical error correction;CzeSL-GEC is a corpus containing sentence pairs of original and corrected versions of Czech sentences collected from essays written by both non-native learners of Czech and Czech pupils with Romani background. To create this corpus, unreleased CzeSL-man corpus (http://utkl.ff.cuni.cz/learncorp/) was utilized. All sentences in the corpus are word tokenized.;2017-04-30;corpus;http://hdl.handle.net/11234/1-2143;ces;Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0);http://creativecommons.org/licenses/by-sa/3.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "caa93a8e-c192-5cf2-80c8-a1ee7c18e7a3",
-    "notes": [
-        "CzeSL-GEC is a corpus containing sentence pairs of original and corrected versions of Czech sentences collected from essays written by both non-native learners of Czech and Czech pupils with Romani background. To create this corpus, unreleased CzeSL-man corpus (http://utkl.ff.cuni.cz/learncorp/) was utilized. All sentences in the corpus are word tokenized."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2143"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "natural language correction"
-        },
-        {
-            "name": "grammatical error correction"
-        }
-    ],
-    "title": [
-        "CzeSL Grammatical Error Correction Dataset (CzeSL-GEC)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/caab5669-d3ac-54d3-bb30-868beab00f12.json b/oaitestdata/clarin-oai_dc/SET_1/json/caab5669-d3ac-54d3-bb30-868beab00f12.json
deleted file mode 100644
index c51411c1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/caab5669-d3ac-54d3-bb30-868beab00f12.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=c4e08b72e6dd11e6a2aa782bcb074135a5ac38ba70a14fb3adbd5782b21dacb0",
-    "MetadataAccess": [
-        "c4e08b72e6dd11e6a2aa782bcb074135a5ac38ba70a14fb3adbd5782b21dacb0"
-    ],
-    "PublicationTimestamp": "2017-01-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "fulltext": "c4e08b72e6dd11e6a2aa782bcb074135a5ac38ba70a14fb3adbd5782b21dacb0;2018-11-15T16:40:25Z;corpus;corpus:text;LX-WordSim-353;The LX-WordSim-353 was created from WordSim-353 (Agirre et al., 2009). As the name suggests, this data set contains 353 pairs of words. Both words in each pair can have different morphosyntactic categories. The data set is made of nouns, adjectives, verbs and named entities, and has no multiwords.\nOriginally (Finkelstein, et al., 2002), each pair of words received a human judgement on a scale from 0 (totally unrelated words) to 10 (very much related or identical words).\nAgirre et al. (2009) observed that the numeric annotation did not distinguish between similar and related pairs. In an attempt to know which was the true relation between the words of each pair, they advanced with a different approach in the annotation of this data set. Thus, the annotators should classify all pairs as being synonyms, antonyms, identical, hyperonym-hyponym, sibling terms (terms with a common hyperonymy), meronym-holonym or none-of-the-above. With this annotation, they could determine which pairs had a relation of similarity among the two words and which pairs had related words. At the end, they distinguished between the pairs with related words and the pairs with similar words. In the word pairs categorized as synonyms, antonyms, identical and hyperonym-hyponym, there was a relation of similarity between both words. In the word pairs categorized as sibling terms, holonym-meronym or none-of-the-above, which had on average a similarity greater than 5, there was a relation of relatedness between both words.\nThe LX-WordSim-353 was the outcome of a) the translation of WordSim-353 into Portuguese and b) the annotation of that list with the classification established by Agirre, et al. (2009). The translation process followed the same procedures as the translation of the data sets in the sections above: two translators translated the same data and a third expert adjudicated when there were mismatches.;2017-01-30",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "caab5669-d3ac-54d3-bb30-868beab00f12",
-    "notes": [
-        "The LX-WordSim-353 was created from WordSim-353 (Agirre et al., 2009). As the name suggests, this data set contains 353 pairs of words. Both words in each pair can have different morphosyntactic categories. The data set is made of nouns, adjectives, verbs and named entities, and has no multiwords.\nOriginally (Finkelstein, et al., 2002), each pair of words received a human judgement on a scale from 0 (totally unrelated words) to 10 (very much related or identical words).\nAgirre et al. (2009) observed that the numeric annotation did not distinguish between similar and related pairs. In an attempt to know which was the true relation between the words of each pair, they advanced with a different approach in the annotation of this data set. Thus, the annotators should classify all pairs as being synonyms, antonyms, identical, hyperonym-hyponym, sibling terms (terms with a common hyperonymy), meronym-holonym or none-of-the-above. With this annotation, they could determine which pairs had a relation of similarity among the two words and which pairs had related words. At the end, they distinguished between the pairs with related words and the pairs with similar words. In the word pairs categorized as synonyms, antonyms, identical and hyperonym-hyponym, there was a relation of similarity between both words. In the word pairs categorized as sibling terms, holonym-meronym or none-of-the-above, which had on average a similarity greater than 5, there was a relation of relatedness between both words.\nThe LX-WordSim-353 was the outcome of a) the translation of WordSim-353 into Portuguese and b) the annotation of that list with the classification established by Agirre, et al. (2009). The translation process followed the same procedures as the translation of the data sets in the sections above: two translators translated the same data and a third expert adjudicated when there were mismatches."
-    ],
-    "oai_identifier": [
-        "c4e08b72e6dd11e6a2aa782bcb074135a5ac38ba70a14fb3adbd5782b21dacb0"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "LX-WordSim-353"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/caafec49-1f05-5d39-8e37-47c493e61092.json b/oaitestdata/clarin-oai_dc/SET_1/json/caafec49-1f05-5d39-8e37-47c493e61092.json
deleted file mode 100644
index f9f2780c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/caafec49-1f05-5d39-8e37-47c493e61092.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Arts, Institute of the Czech National Corpus, Charles University in Prague"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-119C-C",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-119C-C"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-119C-C",
-    "PublicationTimestamp": "2006-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2006"
-    ],
-    "Publisher": [
-        "Faculty of Arts, Institute of the Czech National Corpus, Charles University in Prague"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Kop\u0159ivov\u00e1, Marie",
-        "Waclawi\u010dov\u00e1, Martina"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-119C-C;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;ORAL2006: Corpus of informal spoken Czech;Kop\u0159ivov\u00e1, Marie;Waclawi\u010dov\u00e1, Martina;corpus;informal spoken language;Corpus of informal spoken Czech sized 1 MW. It contains transcriptions of 221 recordings made in 2002\u20132006 in the whole of Bohemia. All the recordings were made in informal situations to ensure prototypically spontaneous spoken language. This means private environment, physical presence of speakers who know each other, unscripted speech and topic not given in advance. The total number of speakers is 754, the metadata include sociolinguistic information about them.\r\n\r\nThe corpus is provided in a (semi-XML) vertical format used as an input to the Manatee query engine. The data thus exactly correspond to the corpus available via query interface to registered users of the CNC.;2006;corpus;http://hdl.handle.net/11858/00-097C-0000-0023-119C-C;ces;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Faculty of Arts, Institute of the Czech National Corpus, Charles University in Prague;https://wiki.korpus.cz/doku.php/cnk:oral2006",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "caafec49-1f05-5d39-8e37-47c493e61092",
-    "notes": [
-        "Corpus of informal spoken Czech sized 1 MW. It contains transcriptions of 221 recordings made in 2002\u20132006 in the whole of Bohemia. All the recordings were made in informal situations to ensure prototypically spontaneous spoken language. This means private environment, physical presence of speakers who know each other, unscripted speech and topic not given in advance. The total number of speakers is 754, the metadata include sociolinguistic information about them.\r\n\r\nThe corpus is provided in a (semi-XML) vertical format used as an input to the Manatee query engine. The data thus exactly correspond to the corpus available via query interface to registered users of the CNC."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-119C-C"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "informal spoken language"
-        }
-    ],
-    "title": [
-        "ORAL2006: Corpus of informal spoken Czech"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cab193ee-841d-5298-baa4-931979b3da9c.json b/oaitestdata/clarin-oai_dc/SET_1/json/cab193ee-841d-5298-baa4-931979b3da9c.json
deleted file mode 100644
index f82221d9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cab193ee-841d-5298-baa4-931979b3da9c.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3073",
-    "MetadataAccess": [
-        "oai:ota:oucs:3073"
-    ],
-    "PublicationTimestamp": "1848-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1848"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Bront\u00c3\u00ab, Anne, 1820-1849"
-    ],
-    "fulltext": "oai:ota:oucs:3073;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3073.xml;The tenant of Wildfell Hall;Bront\u00c3\u00ab, Anne, 1820-1849;not after: 1848;text_and_corpus_linguistics;Novels -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cab193ee-841d-5298-baa4-931979b3da9c",
-    "oai_identifier": [
-        "oai:ota:oucs:3073"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Novels -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "The tenant of Wildfell Hall"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3073.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cac4a561-9931-51e3-a6ef-69f1b066d8f5.json b/oaitestdata/clarin-oai_dc/SET_1/json/cac4a561-9931-51e3-a6ef-69f1b066d8f5.json
deleted file mode 100644
index a04ba06a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cac4a561-9931-51e3-a6ef-69f1b066d8f5.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Institute of Cybernetics at Tallinn University of Technology"
-    ],
-    "Contributor": [
-        "Meister, Einar"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Estonian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1075",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1075"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1075",
-    "PublicationTimestamp": "1998-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1998"
-    ],
-    "Publisher": [
-        "Institute of Cybernetics at Tallinn University of Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Estonia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1075;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;BABEL Estonian Database;Meister, Einar;The database consists of three sets: - Many Talker Set: 30 males, 30 females; each to read 50 numbers, 1-2 connected passages, 1 block of \"filler\" sentences, and 1 block of syllables. - Few Talker Set: 4 males, 4 females; each to read 50 numbers, 10 connected passages, 1 block of \"filler\" sentences, and 2-3 blocks of syllables. - Very Few Talker Set: 1 male, 1 female; each to read 2 blocks of 50 numbers, 40 connected passages, 4 blocks of \"filler\" sentences, and 9 blocks of syllables.  Total amount ca 12 hours of speech.;1998;corpus;http://hdl.handle.net/11372/LRT-1075;est;downloadable_files_count: 0;Estonia;Institute of Cybernetics at Tallinn University of Technology;http://catalog.elra.info/product_info.php?products_id=94",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cac4a561-9931-51e3-a6ef-69f1b066d8f5",
-    "notes": [
-        "The database consists of three sets: - Many Talker Set: 30 males, 30 females; each to read 50 numbers, 1-2 connected passages, 1 block of \"filler\" sentences, and 1 block of syllables. - Few Talker Set: 4 males, 4 females; each to read 50 numbers, 10 connected passages, 1 block of \"filler\" sentences, and 2-3 blocks of syllables. - Very Few Talker Set: 1 male, 1 female; each to read 2 blocks of 50 numbers, 40 connected passages, 4 blocks of \"filler\" sentences, and 9 blocks of syllables.  Total amount ca 12 hours of speech."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1075"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "BABEL Estonian Database"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cac92c57-0229-5931-994a-7c8f2a896712.json b/oaitestdata/clarin-oai_dc/SET_1/json/cac92c57-0229-5931-994a-7c8f2a896712.json
deleted file mode 100644
index 24272bf9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cac92c57-0229-5931-994a-7c8f2a896712.json
+++ /dev/null
@@ -1,40 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=18632c20617011e2a2aa782bcb074135dc7144e8826c417e9fed52e141eb4c91",
-    "MetadataAccess": [
-        "18632c20617011e2a2aa782bcb074135dc7144e8826c417e9fed52e141eb4c91"
-    ],
-    "PublicationTimestamp": "2013-02-05T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "18632c20617011e2a2aa782bcb074135dc7144e8826c417e9fed52e141eb4c91;2018-11-15T16:40:05Z;corpus;corpus:text;corpus:audio;corpus:text:audio;Maltese Speech Engine Database;Description;2013-02-05",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cac92c57-0229-5931-994a-7c8f2a896712",
-    "notes": [
-        "Description"
-    ],
-    "oai_identifier": [
-        "18632c20617011e2a2aa782bcb074135dc7144e8826c417e9fed52e141eb4c91"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text",
-        "corpus:audio",
-        "corpus:text:audio"
-    ],
-    "state": "active",
-    "title": [
-        "Maltese Speech Engine Database"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/caddf345-29da-5ad3-b5c9-46b31ad56543.json b/oaitestdata/clarin-oai_dc/SET_1/json/caddf345-29da-5ad3-b5c9-46b31ad56543.json
deleted file mode 100644
index a7bc64a3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/caddf345-29da-5ad3-b5c9-46b31ad56543.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/29",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/29"
-    ],
-    "PID": "http://hdl.handle.net/11321/29",
-    "PublicationTimestamp": "2010-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "author": [
-        "K\u0119dzia, Pawe\u0142",
-        "Maziarz, Marek",
-        "Koco\u0144, Jan",
-        "Broda, Bartosz",
-        "Marci\u0144czuk, Micha\u0142",
-        "Kali\u0144ski, Micha\u0142",
-        "Radziszewski, Adam",
-        "Piasecki, Maciej"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/29;2016-01-21T14:28:27Z;hdl_11321_3;hdl_11321_4;WordNet;Piasecki, Maciej;Maziarz, Marek;Marci\u0144czuk, Micha\u0142;Broda, Bartosz;K\u0119dzia, Pawe\u0142;Koco\u0144, Jan;Radziszewski, Adam;Kali\u0144ski, Micha\u0142;plWordNet is a lexico-semantic network which reflects the lexical system of the Polish language. There are at present ca. 144,000 nouns, verbs and adjectives in plWordNet, ca. 203,000 word senses and ca. 500,000 relations. It is already the second-largest wordnet in the world, and it keeps growing.;2010-07-01;corpus;http://hdl.handle.net/11321/29;pol;downloadable_files_count: 0;Wroc\u0142aw University of Technology;http://plwordnet.pwr.wroc.pl/wordnet",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "caddf345-29da-5ad3-b5c9-46b31ad56543",
-    "notes": [
-        "plWordNet is a lexico-semantic network which reflects the lexical system of the Polish language. There are at present ca. 144,000 nouns, verbs and adjectives in plWordNet, ca. 203,000 word senses and ca. 500,000 relations. It is already the second-largest wordnet in the world, and it keeps growing."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/29"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "WordNet"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/caf3b68a-7b43-5388-b9df-0734d80929c6.json b/oaitestdata/clarin-oai_dc/SET_1/json/caf3b68a-7b43-5388-b9df-0734d80929c6.json
deleted file mode 100644
index c99e52ac..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/caf3b68a-7b43-5388-b9df-0734d80929c6.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Latin",
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1952",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1952"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1952",
-    "PublicationTimestamp": "2018-02-28T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Galu\u0161\u010d\u00e1kov\u00e1, Petra",
-        "Neu\u017eilov\u00e1, Lucie"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1952;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Medieval Charter Sections Corpus;Galu\u0161\u010d\u00e1kov\u00e1, Petra;Neu\u017eilov\u00e1, Lucie;section detection;segmentation;information retrieval;This package provides an evaluation framework, training and test data for semi-automatic recognition of sections of historical diplomatic manuscripts. The data collection consists of 57 Latin charters issued by the Royal Chancellery of 7 different types. Documents were created in the era of John the Blind, King of Bohemia (1310\u20131346) and Count of Luxembourg. Manuscripts were digitized, transcribed, and typical sections of medieval charters ('corroboratio', 'datatio', 'dispositio', 'inscriptio', 'intitulatio', 'narratio', and 'publicatio') were manually tagged. Manuscripts also contain additional metadata, such as manually marked named entities and short Czech abstracts.\r\nRecognition models are first trained using manually marked sections in training documents and the trained model can then be used for recognition of the sections in the test data. The parsing script supports methods based on Cosine Distance, TF-IDF weighting and adapted Viterbi algorithm.;2018-02-28;corpus;http://hdl.handle.net/11234/1-1952;lat;ces;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/Medieval-Charter-Sections-Corpus",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "caf3b68a-7b43-5388-b9df-0734d80929c6",
-    "notes": [
-        "This package provides an evaluation framework, training and test data for semi-automatic recognition of sections of historical diplomatic manuscripts. The data collection consists of 57 Latin charters issued by the Royal Chancellery of 7 different types. Documents were created in the era of John the Blind, King of Bohemia (1310\u20131346) and Count of Luxembourg. Manuscripts were digitized, transcribed, and typical sections of medieval charters ('corroboratio', 'datatio', 'dispositio', 'inscriptio', 'intitulatio', 'narratio', and 'publicatio') were manually tagged. Manuscripts also contain additional metadata, such as manually marked named entities and short Czech abstracts.\r\nRecognition models are first trained using manually marked sections in training documents and the trained model can then be used for recognition of the sections in the test data. The parsing script supports methods based on Cosine Distance, TF-IDF weighting and adapted Viterbi algorithm."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1952"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "section detection"
-        },
-        {
-            "name": "segmentation"
-        },
-        {
-            "name": "information retrieval"
-        }
-    ],
-    "title": [
-        "Medieval Charter Sections Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cafb0063-5ea4-5cfa-bd84-1c7297ade314.json b/oaitestdata/clarin-oai_dc/SET_1/json/cafb0063-5ea4-5cfa-bd84-1c7297ade314.json
deleted file mode 100644
index 1b4949f6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cafb0063-5ea4-5cfa-bd84-1c7297ade314.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1058",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1058"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1058",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1058;2016-04-06T16:39:49Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Dinglers Polytechnisches Journal (Dingler-Online);Germanistik;The issues of the Polytechnic Journal are available as full texts and as digital copies. Zweifache Verf\u00fcgbarkeit der Zeitschriftenb\u00e4nde: als Bilddigitalisate sowie als Volltexte;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1058;deu;downloadable_files_count: 0;Germany;http://www.polytechnischesjournal.de/journal/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cafb0063-5ea4-5cfa-bd84-1c7297ade314",
-    "notes": [
-        "The issues of the Polytechnic Journal are available as full texts and as digital copies. Zweifache Verf\u00fcgbarkeit der Zeitschriftenb\u00e4nde: als Bilddigitalisate sowie als Volltexte"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1058"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Dinglers Polytechnisches Journal (Dingler-Online)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cb01d40a-7aab-56e1-a788-2fc9ee6c0aa5.json b/oaitestdata/clarin-oai_dc/SET_1/json/cb01d40a-7aab-56e1-a788-2fc9ee6c0aa5.json
deleted file mode 100644
index 0e8a4564..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cb01d40a-7aab-56e1-a788-2fc9ee6c0aa5.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5043",
-    "MetadataAccess": [
-        "oai:ota:oucs:5043"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Trusler, John, 1735-1820."
-    ],
-    "fulltext": "oai:ota:oucs:5043;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5043.xml;The habitable world described: or the present state of the people in all parts of the globe, from north to south; shewing the situation, extent, climate, ... including all the new discoveries: ... With a great variety of maps and copper-plates, ... By the Rev. Dr. John Trusler. ... [pt.9];Trusler, John, 1735-1820.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cb01d40a-7aab-56e1-a788-2fc9ee6c0aa5",
-    "oai_identifier": [
-        "oai:ota:oucs:5043"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The habitable world described: or the present state of the people in all parts of the globe, from north to south; shewing the situation, extent, climate, ... including all the new discoveries: ... With a great variety of maps and copper-plates, ... By the Rev. Dr. John Trusler. ... [pt.9]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5043.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cb233c99-b495-54db-a19d-ae6b22d6dc5a.json b/oaitestdata/clarin-oai_dc/SET_1/json/cb233c99-b495-54db-a19d-ae6b22d6dc5a.json
deleted file mode 100644
index 4adfd1db..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cb233c99-b495-54db-a19d-ae6b22d6dc5a.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 3",
-        "application/zip"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1193",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1193"
-    ],
-    "PID": "http://hdl.handle.net/11356/1193",
-    "PublicationTimestamp": "2018-08-03T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11356/1045",
-        "http://hdl.handle.net/11356/1045"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "https://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Dobrovoljc, Kaja"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1193;2018-08-03T18:47:51Z;hdl_11356_1023;hdl_11356_1024;Kres corpus n-grams 2.0;Dobrovoljc, Kaja;n-grams;wordlist;multiword expressions;A collection of n-grams extracted from the Kres corpus of written Slovene (cf. http://eng.slovenscina.eu/korpusi/kres). Three sets of n-gram lists are provided for lowercased word n-grams of length 1 to 5:\r\n- extensive frequency lists of all extracted n-grams\r\n- filtered frequency lists of n-grams with minimum frequency 10/mil.\r\n- adjusted frequency list of all n-grams with minimum frequency 10/mil.\r\n\r\nOnly n-grams within sentences have been counted, ignoring punctuation. For the filtered and adjusted list, only n-grams occurring in at least 2 different texts have been extracted.\r\n\r\nKey references:\r\n- K. Dobrovoljc, 2018. N-gram frequency lists for reference corpora of Slovenian language. Proceedings of the Language Technologies & Digital Humanities Conference 2018.\r\n- N. Logar Berginc, M. Gr\u010dar, M. Brakus, T. Erjavec, \u0160. Arhar Holdt in S. Krek (2012): Korpusi slovenskega jezika Gigafida, KRES, ccGigafida in ccKRES: gradnja, vsebina, uporaba. Ljubljana: Trojina, zavod za uporabno slovenistiko; Fakulteta za dru\u017ebene vede.\r\n- M. B. O\u2019Donnell, 2010. The adjusted frequency list: A method to produce cluster-sensitive frequency lists. ICAME Journal 35, 135\u2013169.;2018-08-03;lexicalConceptualResource;http://hdl.handle.net/11356/1193;slv;http://hdl.handle.net/11356/1045;http://hdl.handle.net/11356/1045;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);https://creativecommons.org/licenses/by-sa/4.0/;PUB;text/plain; charset=utf-8;application/zip;application/zip;application/zip;downloadable_files_count: 3;Centre for Language Resources and Technologies, University of Ljubljana",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cb233c99-b495-54db-a19d-ae6b22d6dc5a",
-    "notes": [
-        "A collection of n-grams extracted from the Kres corpus of written Slovene (cf. http://eng.slovenscina.eu/korpusi/kres). Three sets of n-gram lists are provided for lowercased word n-grams of length 1 to 5:\r\n- extensive frequency lists of all extracted n-grams\r\n- filtered frequency lists of n-grams with minimum frequency 10/mil.\r\n- adjusted frequency list of all n-grams with minimum frequency 10/mil.\r\n\r\nOnly n-grams within sentences have been counted, ignoring punctuation. For the filtered and adjusted list, only n-grams occurring in at least 2 different texts have been extracted.\r\n\r\nKey references:\r\n- K. Dobrovoljc, 2018. N-gram frequency lists for reference corpora of Slovenian language. Proceedings of the Language Technologies & Digital Humanities Conference 2018.\r\n- N. Logar Berginc, M. Gr\u010dar, M. Brakus, T. Erjavec, \u0160. Arhar Holdt in S. Krek (2012): Korpusi slovenskega jezika Gigafida, KRES, ccGigafida in ccKRES: gradnja, vsebina, uporaba. Ljubljana: Trojina, zavod za uporabno slovenistiko; Fakulteta za dru\u017ebene vede.\r\n- M. B. O\u2019Donnell, 2010. The adjusted frequency list: A method to produce cluster-sensitive frequency lists. ICAME Journal 35, 135\u2013169."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1193"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "n-grams"
-        },
-        {
-            "name": "wordlist"
-        },
-        {
-            "name": "multiword expressions"
-        }
-    ],
-    "title": [
-        "Kres corpus n-grams 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cb3764b9-6dbf-5456-b3e7-75a6c4063754.json b/oaitestdata/clarin-oai_dc/SET_1/json/cb3764b9-6dbf-5456-b3e7-75a6c4063754.json
deleted file mode 100644
index 87b6d71a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cb3764b9-6dbf-5456-b3e7-75a6c4063754.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "852 KB"
-    ],
-    "Language": [
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1287",
-    "MetadataAccess": [
-        "oai:ota:oucs:1287"
-    ],
-    "PublicationTimestamp": "1988-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1988"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Academic dissertations"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Esgueva, M.  (Manuel)"
-    ],
-    "fulltext": "oai:ota:oucs:1287;2018-03-06T16:27:17Z;http://ota.ox.ac.uk/headers/1287.xml;El Habla de la ciudad de Madrid : materiales para su estudio / compiled by C.S. Butler;Esgueva, M.  (Manuel);1988;text_and_corpus_linguistics;Academic dissertations -- Spain -- 20th century;spa;Oxford Text Archive, University of Oxford;852 KB;Text;Academic dissertations;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cb3764b9-6dbf-5456-b3e7-75a6c4063754",
-    "oai_identifier": [
-        "oai:ota:oucs:1287"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Academic dissertations -- Spain -- th century"
-        }
-    ],
-    "title": [
-        "El Habla de la ciudad de Madrid : materiales para su estudio / compiled by C.S. Butler"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1287.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cb3b8590-e983-5ded-b6d0-884282dc46ed.json b/oaitestdata/clarin-oai_dc/SET_1/json/cb3b8590-e983-5ded-b6d0-884282dc46ed.json
deleted file mode 100644
index c978eab8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cb3b8590-e983-5ded-b6d0-884282dc46ed.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Delbecque, Nicole"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 82 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0470",
-    "MetadataAccess": [
-        "oai:ota:oucs:0470"
-    ],
-    "PublicationTimestamp": "1970-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1970"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hare, David, 1947-"
-    ],
-    "fulltext": "oai:ota:oucs:0470;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0470.xml;Slag / David Hare;Hare, David, 1947-;1970;text_and_corpus_linguistics;English drama -- 20th century;eng;Oxford Text Archive, University of Oxford;Delbecque, Nicole;(1 file : ca. 82 KB);Text;Plays;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cb3b8590-e983-5ded-b6d0-884282dc46ed",
-    "oai_identifier": [
-        "oai:ota:oucs:0470"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- th century"
-        }
-    ],
-    "title": [
-        "Slag / David Hare"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0470.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cb503c10-2c0a-572d-aa5b-3d34f6c87a62.json b/oaitestdata/clarin-oai_dc/SET_1/json/cb503c10-2c0a-572d-aa5b-3d34f6c87a62.json
deleted file mode 100644
index 9e0d4285..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cb503c10-2c0a-572d-aa5b-3d34f6c87a62.json
+++ /dev/null
@@ -1,91 +0,0 @@
-{
-    "Contact": [
-        "Universit\u00e4t des Saarlandes"
-    ],
-    "Contributor": [
-        "Ekaterina Lapshinova-Koltunski"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml"
-    ],
-    "Language": [
-        "English",
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:vartra",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:vartra"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CDB-A",
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Universit\u00e4t des Saarlandes"
-    ],
-    "RelatedIdentifier": [
-        "Lapshinova-Koltunski, Ekaterina. 2013. VARTRA: A Comparable Corpus for Analysis of Translation Variation. In Proceedings of the Sixth Workshop on Building and Using Comparable Corpora. Sofia, Bulgaria. Association for Computational Linguistics. pp. 77-86. URL: http://aclweb.org/anthology/W13-2510",
-        "Lapshinova-Koltunski, Ekaterina. 2013. VARTRA: A Comparable Corpus for Analysis of Translation Variation. In Proceedings of the Sixth Workshop on Building and Using Comparable Corpora. Sofia, Bulgaria. Association for Computational Linguistics. pp. 77-86. URL: http://aclweb.org/anthology/W13-2510",
-        "Lapshinova-Koltunski, Ekaterina. (2013). VARTRA: A Comparable Corpus for Analysis of Translation Variation. In Proceedings of the Sixth Workshop on Building and Using Comparable Corpora. Sofia, Bulgaria. Association for Computational Linguistics. pp. 77-86. URL: http://aclweb.org/anthology/W13-2510",
-        "Lapshinova-Koltunski, E. and Santanu Pal (2014). Comparabilty of Corpora in Human and Machine Translation. In Proceedings of BUCC, 7th Workshop on Building and Using Comparable Corpora. Building Resources for Machine Translation Research, Reykjavik, May 27, 2014.",
-        "Lapshinova-Koltunski, E. (2015). Variation in Translation: Evidence from corpora. In C. Fantinuoli and F. Zanettin. New directions in corpus-based translation studies.Translation and Multilingual Natural Language Processing (TMNLP), pp. 79-99. Language Science Press.",
-        "Lapshinova-Koltunski, E. (to appear 2015). Exploratory Analysis of Dimensions Influencing Variation in Translation: The case of text register and translation method. In De Sutter, G. and Delaere, I. and Lefer, M.-A. (eds.). New Ways of Analysing Translational Behaviour in Corpus-Based Translation Studies. TILSM series. Mouton de Gruyter."
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "partly copyrighted: EO and PT are under the same copyrights as CroCo; CAT, RBMT, SMT1 and SMT2 are free for academic"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Ekaterina Lapshinova-Koltunski"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:vartra;2018-10-15T16:03:26Z;VARTRA-SMALL;Ekaterina Lapshinova-Koltunski;corpus linguistics;linguistics;computational linguistics;translation;variation in translation;VARTRA (VARiation in TRAnslation) is a comparable English-to-German translation corpus created to investigate translation variation phenomena in terms of contrasts between languages, text types and translation methods (machine vs. computer-aided vs. human). These phenomena are reflected in linguistic features of translated texts belonging to different registers and produced with different translation methods. VARTRA-SMALL contains English original texts and variants of their translations (to each text) into German which were produced by: (1) human professionals (PT), (2) human student translators with the help of computer-aided translation tools (CAT), (3) rule-based MT systems\n(RBMT) and (4) statistical MT systems (SMT). The English originals (EO), as well as the translations by profesionals (PT) were exported from the already existing corpus CroCo (cf. Hansen-Schirra et al. 2012). The CAT variant was produced by student assistents who used the CAT tool ACROSS in the translation process. The  RBMT variant was translated with SYSTRAN (RBMT). For SMT, we have compiled two versions - the one produced with Google Translate (SMT1), and the other one with a Moses system (SMT2). Each translation variant is saved as a subcorpus and covers seven registers of written language: political essays (ESSAY), fictional texts (FICTION), manuals (INSTR), popular-scientific articles (POPSCI), letters of share-holders (SHARE), prepared political speeches (SPEECH), and touristic leaflets (TOU). The total number of tokens in VARTRA-SMALL comprises 795,460. All subcorpora of VARTRA-SMALL are tokenised, lemmatised, tagged with part-of-speech information, segmented into syntactic chunks and sentences. The annotations were obtained with Tree Tagger (Schmid, 1994).\nVARTRA-SMALL is encoded in CWB and can be queried with the help of Corpus Query Processor (CQP) (Evert, 2005). In the CWB format, the corpus contains two types of annotation: structural and positional. Structural annotation is written in XML and provides a description of the textual structure, on the one hand, and metatextual information, on the other hand. We also encode a part of the meta-data, such as information on register, as well as translation method, tools used and the source language. STRUCTURAL ATTRIBUTES: metadata: id, register; structure: chunk (shallow chunks with TreeTagger), s (sentence borders based on the TreeTagger output). Positional annotation is provided at token level containing linguistic information. POSITIONAL ATTRIBUTES: word, pos (STTS Tagset, TreeTagger).\nThe metadata (e.g. information on translators and the system used) are also saved in .header-files.;Universit\u00e4t des Saarlandes;Ekaterina Lapshinova-Koltunski;2013;Dataset;text/xml;clarind-uds:vartra;hdl:11858/00-246C-0000-0023-8CDB-A;English originals from CroCo (clarind-uds:croco);German translations from English by professionals from CroCo (clarind-uds:croco);German translations from English by students of translation at FR4.6, Saarland University (within the VARTRA projects);German translations from English with the SYSTRAN machine translation system (within the VARTRA projects);German translations from English with a Moses-based machine translation system (within the VARTRA projects);German translations from English with the Google machine translation system (within the VARTRA projects);eng;deu;Lapshinova-Koltunski, Ekaterina. 2013. VARTRA: A Comparable Corpus for Analysis of Translation Variation. In Proceedings of the Sixth Workshop on Building and Using Comparable Corpora. Sofia, Bulgaria. Association for Computational Linguistics. pp. 77-86. URL: http://aclweb.org/anthology/W13-2510;Lapshinova-Koltunski, Ekaterina. 2013. VARTRA: A Comparable Corpus for Analysis of Translation Variation. In Proceedings of the Sixth Workshop on Building and Using Comparable Corpora. Sofia, Bulgaria. Association for Computational Linguistics. pp. 77-86. URL: http://aclweb.org/anthology/W13-2510;Lapshinova-Koltunski, Ekaterina. (2013). VARTRA: A Comparable Corpus for Analysis of Translation Variation. In Proceedings of the Sixth Workshop on Building and Using Comparable Corpora. Sofia, Bulgaria. Association for Computational Linguistics. pp. 77-86. URL: http://aclweb.org/anthology/W13-2510;Lapshinova-Koltunski, E. and Santanu Pal (2014). Comparabilty of Corpora in Human and Machine Translation. In Proceedings of BUCC, 7th Workshop on Building and Using Comparable Corpora. Building Resources for Machine Translation Research, Reykjavik, May 27, 2014.;Lapshinova-Koltunski, E. (2015). Variation in Translation: Evidence from corpora. In C. Fantinuoli and F. Zanettin. New directions in corpus-based translation studies.Translation and Multilingual Natural Language Processing (TMNLP), pp. 79-99. Language Science Press.;Lapshinova-Koltunski, E. (to appear 2015). Exploratory Analysis of Dimensions Influencing Variation in Translation: The case of text register and translation method. In De Sutter, G. and Delaere, I. and Lefer, M.-A. (eds.). New Ways of Analysing Translational Behaviour in Corpus-Based Translation Studies. TILSM series. Mouton de Gruyter.;Germany;partly copyrighted: EO and PT are under the same copyrights as CroCo; CAT, RBMT, SMT1 and SMT2 are free for academic",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cb503c10-2c0a-572d-aa5b-3d34f6c87a62",
-    "notes": [
-        "VARTRA (VARiation in TRAnslation) is a comparable English-to-German translation corpus created to investigate translation variation phenomena in terms of contrasts between languages, text types and translation methods (machine vs. computer-aided vs. human). These phenomena are reflected in linguistic features of translated texts belonging to different registers and produced with different translation methods. VARTRA-SMALL contains English original texts and variants of their translations (to each text) into German which were produced by: (1) human professionals (PT), (2) human student translators with the help of computer-aided translation tools (CAT), (3) rule-based MT systems\n(RBMT) and (4) statistical MT systems (SMT). The English originals (EO), as well as the translations by profesionals (PT) were exported from the already existing corpus CroCo (cf. Hansen-Schirra et al. 2012). The CAT variant was produced by student assistents who used the CAT tool ACROSS in the translation process. The  RBMT variant was translated with SYSTRAN (RBMT). For SMT, we have compiled two versions - the one produced with Google Translate (SMT1), and the other one with a Moses system (SMT2). Each translation variant is saved as a subcorpus and covers seven registers of written language: political essays (ESSAY), fictional texts (FICTION), manuals (INSTR), popular-scientific articles (POPSCI), letters of share-holders (SHARE), prepared political speeches (SPEECH), and touristic leaflets (TOU). The total number of tokens in VARTRA-SMALL comprises 795,460. All subcorpora of VARTRA-SMALL are tokenised, lemmatised, tagged with part-of-speech information, segmented into syntactic chunks and sentences. The annotations were obtained with Tree Tagger (Schmid, 1994).\nVARTRA-SMALL is encoded in CWB and can be queried with the help of Corpus Query Processor (CQP) (Evert, 2005). In the CWB format, the corpus contains two types of annotation: structural and positional. Structural annotation is written in XML and provides a description of the textual structure, on the one hand, and metatextual information, on the other hand. We also encode a part of the meta-data, such as information on register, as well as translation method, tools used and the source language. STRUCTURAL ATTRIBUTES: metadata: id, register; structure: chunk (shallow chunks with TreeTagger), s (sentence borders based on the TreeTagger output). Positional annotation is provided at token level containing linguistic information. POSITIONAL ATTRIBUTES: word, pos (STTS Tagset, TreeTagger).\nThe metadata (e.g. information on translators and the system used) are also saved in .header-files."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:vartra"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus linguistics"
-        },
-        {
-            "name": "linguistics"
-        },
-        {
-            "name": "computational linguistics"
-        },
-        {
-            "name": "translation"
-        },
-        {
-            "name": "variation translation"
-        }
-    ],
-    "title": [
-        "VARTRA-SMALL"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cb51cb6e-72f8-5f60-b4cc-97f3c45c815b.json b/oaitestdata/clarin-oai_dc/SET_1/json/cb51cb6e-72f8-5f60-b4cc-97f3c45c815b.json
deleted file mode 100644
index 2e41a7fb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cb51cb6e-72f8-5f60-b4cc-97f3c45c815b.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "University of Stuttgart"
-    ],
-    "Contributor": [
-        "Schmid, Helmut"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-303",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-303"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-303",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Stuttgart"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-303;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;SMOR - German morphology;Schmid, Helmut;SMOR is a wide-coverage German computational morphology with inflection, derivation, and compounding. The SMOR code excepted the stem lexicon are available under the GNU license. SMOR (without a stem lexicon) comes with the SFST tools.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-303;deu;downloadable_files_count: 0;Germany;University of Stuttgart;http://www.ims.uni-stuttgart.de/projekte/gramotron/SOFTWARE/SFST.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cb51cb6e-72f8-5f60-b4cc-97f3c45c815b",
-    "notes": [
-        "SMOR is a wide-coverage German computational morphology with inflection, derivation, and compounding. The SMOR code excepted the stem lexicon are available under the GNU license. SMOR (without a stem lexicon) comes with the SFST tools."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-303"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "SMOR - German morphology"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cb5f9e30-7fef-5253-9dfe-e2763bd46e7d.json b/oaitestdata/clarin-oai_dc/SET_1/json/cb5f9e30-7fef-5253-9dfe-e2763bd46e7d.json
deleted file mode 100644
index a58ee258..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cb5f9e30-7fef-5253-9dfe-e2763bd46e7d.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Fortier, Paul A."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 115 KB)"
-    ],
-    "Language": [
-        "French"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0189",
-    "MetadataAccess": [
-        "oai:ota:oucs:0189"
-    ],
-    "PublicationTimestamp": "1926-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1926"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Malraux, Andr\u00c3\u00a9, 1901-1976"
-    ],
-    "fulltext": "oai:ota:oucs:0189;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0189.xml;La tentation de l'Occident / Andr\u00c3\u00a9 Malraux;The temptation of the East;Malraux, Andr\u00c3\u00a9, 1901-1976;1926;text_and_corpus_linguistics;French fiction -- 20th century;fra;Oxford Text Archive, University of Oxford;Fortier, Paul A.;(1 file : ca. 115 KB);Text;Novels;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cb5f9e30-7fef-5253-9dfe-e2763bd46e7d",
-    "oai_identifier": [
-        "oai:ota:oucs:0189"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "French fiction -- th century"
-        }
-    ],
-    "title": [
-        "La tentation de l'Occident / Andr\u00c3\u00a9 Malraux",
-        "The temptation of the East"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0189.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cb8c1cf3-43d7-5d0f-906f-95c0ea859ccd.json b/oaitestdata/clarin-oai_dc/SET_1/json/cb8c1cf3-43d7-5d0f-906f-95c0ea859ccd.json
deleted file mode 100644
index 55240e17..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cb8c1cf3-43d7-5d0f-906f-95c0ea859ccd.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5594",
-    "MetadataAccess": [
-        "oai:ota:oucs:5594"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pringle, John, Sir, 1707-1782."
-    ],
-    "fulltext": "oai:ota:oucs:5594;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5594.xml;A discourse upon some late improvements of the means for preserving the health of mariners. Delivered at the anniversary meeting of the Royal Society, November 30, 1776. By Sir John Pringle, Baronet, President. Published by their order;Pringle, John, Sir, 1707-1782.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cb8c1cf3-43d7-5d0f-906f-95c0ea859ccd",
-    "oai_identifier": [
-        "oai:ota:oucs:5594"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A discourse upon some late improvements of the means for preserving the health of mariners. Delivered at the anniversary meeting of the Royal Society, November 30, 1776. By Sir John Pringle, Baronet, President. Published by their order"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5594.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cb975324-b823-516b-8d91-20777678b848.json b/oaitestdata/clarin-oai_dc/SET_1/json/cb975324-b823-516b-8d91-20777678b848.json
deleted file mode 100644
index b46ac415..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cb975324-b823-516b-8d91-20777678b848.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Asmussen, J\u00f6rg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Danish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-244",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-244"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-244",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Denmark"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-244;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Korpus 90;Asmussen, J\u00f6rg;written, general language; 22 million tokens;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-244;dan;downloadable_files_count: 0;Denmark;http://ordnet.dk/korpusdk",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cb975324-b823-516b-8d91-20777678b848",
-    "notes": [
-        "written, general language; 22 million tokens"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-244"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Korpus 90"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cbb2f140-b910-53a0-a1d9-e1f1931b98a5.json b/oaitestdata/clarin-oai_dc/SET_1/json/cbb2f140-b910-53a0-a1d9-e1f1931b98a5.json
deleted file mode 100644
index 20c0c817..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cbb2f140-b910-53a0-a1d9-e1f1931b98a5.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 279 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2195",
-    "MetadataAccess": [
-        "oai:ota:oucs:2195"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Rutledge, Sarah, 1782-1855"
-    ],
-    "fulltext": "oai:ota:oucs:2195;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/2195.xml;The Carolina housewife [Electronic resource], or, House and home : by a lady of Charleston / by Sarah Rutledge;Rutledge, Sarah, 1782-1855;text_and_corpus_linguistics;Cookbooks -- United States -- 19th century;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 279 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cbb2f140-b910-53a0-a1d9-e1f1931b98a5",
-    "oai_identifier": [
-        "oai:ota:oucs:2195"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Cookbooks -- United States -- th century"
-        }
-    ],
-    "title": [
-        "The Carolina housewife [Electronic resource], or, House and home : by a lady of Charleston / by Sarah Rutledge"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2195.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cbe650ce-7548-5ed2-aef9-82c2984b7040.json b/oaitestdata/clarin-oai_dc/SET_1/json/cbe650ce-7548-5ed2-aef9-82c2984b7040.json
deleted file mode 100644
index c8292e83..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cbe650ce-7548-5ed2-aef9-82c2984b7040.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "University of West Bohemia, Department of Cybernetics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/rdf+xml; charset=utf-8",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-000D-EC91-2",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-000D-EC91-2"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-000D-EC91-2",
-    "PublicationTimestamp": "2013-01-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "University of West Bohemia, Department of Cybernetics"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Ircing, Pavel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-000D-EC91-2;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Czech translation of the EBUContentGenre thesaurus;Ircing, Pavel;thesaurus;metadata annotation;topic detection;The EBUContentGenre is a thesaurus containing the hierarchical description of various genres utilized in the TV broadcasting industry. This thesaurus is a part of  a complex metadata specification called EBUCore intended for multifaceted description of audiovisual content. EBUCore (http://tech.ebu.ch/docs/tech/tech3293v1_3.pdf) is a set of descriptive and technical metadata based on the Dublin Core and adapted to media. EBUCore is the flagship metadata specification of European Broadcasting Union, the largest professional association of broadcasters around the world. It is developed and maintained by EBU's Technical Department (http://tech.ebu.ch). The translated  thesaurus can be used for effective cataloguing of (mostly TV) audiovisual content and consequent development of systems for automatic cataloguing (topic/genre detection).;2013-01-01;lexicalConceptualResource;ZCU_CZ_ ebu_ContentGenreCS_CZ;http://hdl.handle.net/11858/00-097C-0000-000D-EC91-2;ces;eng;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/rdf+xml; charset=utf-8;text/plain; charset=utf-8;downloadable_files_count: 1;University of West Bohemia, Department of Cybernetics",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cbe650ce-7548-5ed2-aef9-82c2984b7040",
-    "notes": [
-        "The EBUContentGenre is a thesaurus containing the hierarchical description of various genres utilized in the TV broadcasting industry. This thesaurus is a part of  a complex metadata specification called EBUCore intended for multifaceted description of audiovisual content. EBUCore (http://tech.ebu.ch/docs/tech/tech3293v1_3.pdf) is a set of descriptive and technical metadata based on the Dublin Core and adapted to media. EBUCore is the flagship metadata specification of European Broadcasting Union, the largest professional association of broadcasters around the world. It is developed and maintained by EBU's Technical Department (http://tech.ebu.ch). The translated  thesaurus can be used for effective cataloguing of (mostly TV) audiovisual content and consequent development of systems for automatic cataloguing (topic/genre detection)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-000D-EC91-2"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "thesaurus"
-        },
-        {
-            "name": "metadata annotation"
-        },
-        {
-            "name": "topic detection"
-        }
-    ],
-    "title": [
-        "Czech translation of the EBUContentGenre thesaurus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cbe8e243-1aa9-5029-8c75-4e31da58a303.json b/oaitestdata/clarin-oai_dc/SET_1/json/cbe8e243-1aa9-5029-8c75-4e31da58a303.json
deleted file mode 100644
index d1a23d54..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cbe8e243-1aa9-5029-8c75-4e31da58a303.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "ILSP/R.C. \"Athena\""
-    ],
-    "Contributor": [
-        "Prokopidis, Prokopis"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1311",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1311"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1311",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "ILSP/R.C. \"Athena\""
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Greece"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Prokopidis, Prokopis"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1311;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;ILSP Dependency Parser;Prokopidis, Prokopis;Prokopidis, Prokopis;dependency parser;ILSP Dependency Parser is a tool trained on the Greek Dependency Treebank, a resource which comprises data annotated at several linguistic levels. Training data at the level of syntax consisted of ~70 KWords annotated using a dependency-based syntactic scheme that includes 25 main relations.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1311;downloadable_files_count: 0;Greece;ILSP/R.C. \"Athena\"",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cbe8e243-1aa9-5029-8c75-4e31da58a303",
-    "notes": [
-        "ILSP Dependency Parser is a tool trained on the Greek Dependency Treebank, a resource which comprises data annotated at several linguistic levels. Training data at the level of syntax consisted of ~70 KWords annotated using a dependency-based syntactic scheme that includes 25 main relations."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1311"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "dependency parser"
-        }
-    ],
-    "title": [
-        "ILSP Dependency Parser"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cbf13c16-1c2a-5208-a680-7c493d532514.json b/oaitestdata/clarin-oai_dc/SET_1/json/cbf13c16-1c2a-5208-a680-7c493d532514.json
deleted file mode 100644
index 6031def8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cbf13c16-1c2a-5208-a680-7c493d532514.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "less than 512 KB"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0513",
-    "MetadataAccess": [
-        "oai:ota:oucs:0513"
-    ],
-    "PublicationYear": [
-        "290-240"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Callimachus"
-    ],
-    "fulltext": "oai:ota:oucs:0513;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0513.xml; Complete works  / compiled by Thesaurus Linguae Graecae;Callimachus;290-240;text_and_corpus_linguistics;Poems -- Egypt -- 3rd century B.C.;grc;Oxford Text Archive, University of Oxford;less than 512 KB;Text;Poems;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cbf13c16-1c2a-5208-a680-7c493d532514",
-    "oai_identifier": [
-        "oai:ota:oucs:0513"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- Egypt -- rd century B.C."
-        }
-    ],
-    "title": [
-        " Complete works  / compiled by Thesaurus Linguae Graecae"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0513.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cc1ff594-779d-572f-b182-d17bd0ddbf7e.json b/oaitestdata/clarin-oai_dc/SET_1/json/cc1ff594-779d-572f-b182-d17bd0ddbf7e.json
deleted file mode 100644
index 3f7fea4a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cc1ff594-779d-572f-b182-d17bd0ddbf7e.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=3694294cfb6311e1a2aa782bcb074135dffcbbcce20a41e4b23652e08e0bab65",
-    "MetadataAccess": [
-        "3694294cfb6311e1a2aa782bcb074135dffcbbcce20a41e4b23652e08e0bab65"
-    ],
-    "PublicationTimestamp": "2015-12-14T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "3694294cfb6311e1a2aa782bcb074135dffcbbcce20a41e4b23652e08e0bab65;2018-11-15T16:39:19Z;toolService;toolService:tool;LX-Chunker;The present tool, that was built to deal with specific issues concerning orthographic conventions adopted for Portuguese, marks sentence boundaries with <s>\u00e2\u0080\u00a6</s>, and paragraph boundaries with <p>\u00e2\u0080\u00a6</p>. Unwraps sentences split over different lines.\nA f-score of 99.94% was obtained when testing on a 12,000 sentence corpus accurately hand tagged with respect to sentence and paragraph boundaries.\nLX-Chunker was developed and is maintained at University of Lisbon by the NLX-Natural Language and Speech Group of the Department of Informatics.\n;2015-12-14",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cc1ff594-779d-572f-b182-d17bd0ddbf7e",
-    "notes": [
-        "The present tool, that was built to deal with specific issues concerning orthographic conventions adopted for Portuguese, marks sentence boundaries with <s>\u00e2\u0080\u00a6</s>, and paragraph boundaries with <p>\u00e2\u0080\u00a6</p>. Unwraps sentences split over different lines.\nA f-score of 99.94% was obtained when testing on a 12,000 sentence corpus accurately hand tagged with respect to sentence and paragraph boundaries.\nLX-Chunker was developed and is maintained at University of Lisbon by the NLX-Natural Language and Speech Group of the Department of Informatics.\n"
-    ],
-    "oai_identifier": [
-        "3694294cfb6311e1a2aa782bcb074135dffcbbcce20a41e4b23652e08e0bab65"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "LX-Chunker"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cc394b14-c5a8-51a7-b5b4-e9dedc0acf8d.json b/oaitestdata/clarin-oai_dc/SET_1/json/cc394b14-c5a8-51a7-b5b4-e9dedc0acf8d.json
deleted file mode 100644
index 1d3630b2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cc394b14-c5a8-51a7-b5b4-e9dedc0acf8d.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3231",
-    "MetadataAccess": [
-        "oai:ota:oucs:3231"
-    ],
-    "PublicationTimestamp": "1900-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1900"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Baum, L. Frank (Lyman Frank), 1856-1919"
-    ],
-    "fulltext": "oai:ota:oucs:3231;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3231.xml;The wonderful wizard of Oz;Baum, L. Frank (Lyman Frank), 1856-1919;not after: 1900;text_and_corpus_linguistics;Juvenile literature -- United States -- 20th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cc394b14-c5a8-51a7-b5b4-e9dedc0acf8d",
-    "oai_identifier": [
-        "oai:ota:oucs:3231"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Juvenile literature -- United States -- th century"
-        }
-    ],
-    "title": [
-        "The wonderful wizard of Oz"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3231.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cc3c3d72-2b32-5388-bab4-8001a5fb62c1.json b/oaitestdata/clarin-oai_dc/SET_1/json/cc3c3d72-2b32-5388-bab4-8001a5fb62c1.json
deleted file mode 100644
index e74fe060..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cc3c3d72-2b32-5388-bab4-8001a5fb62c1.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Institut f\u00fcr Deutsche Sprache"
-    ],
-    "Contributor": [
-        "Belica, Cyril"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-872",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-872"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-872",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut f\u00fcr Deutsche Sprache"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-872;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Cyril Belica : Kookkurrenzdatenbank CCDB;Belica, Cyril;A co-occurrence database, developed by the Institut fuer Deutsche Sprache, for research in the field of collocation analysis in modern German. The database holds over 200,000 analysed words that can be browsed or searched and shown in context.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-872;deu;downloadable_files_count: 0;Germany;Institut f\u00fcr Deutsche Sprache;http://corpora.ids-mannheim.de/ccdb/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cc3c3d72-2b32-5388-bab4-8001a5fb62c1",
-    "notes": [
-        "A co-occurrence database, developed by the Institut fuer Deutsche Sprache, for research in the field of collocation analysis in modern German. The database holds over 200,000 analysed words that can be browsed or searched and shown in context."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-872"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Cyril Belica : Kookkurrenzdatenbank CCDB"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cc60225d-c6ca-50a7-8cee-0b78b6912a36.json b/oaitestdata/clarin-oai_dc/SET_1/json/cc60225d-c6ca-50a7-8cee-0b78b6912a36.json
deleted file mode 100644
index 25bdc50d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cc60225d-c6ca-50a7-8cee-0b78b6912a36.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/37",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/37"
-    ],
-    "PID": "http://hdl.handle.net/10794/37",
-    "PublicationTimestamp": "2012-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/37;2017-10-27T14:01:30Z;hdl_10794_1;hdl_10794_2;Schlyter (2017-10-16);Schlyter (2017-10-16);n/a, n/a;Swedish;Dictionary;Dictionary of Old Swedish.;Svenskt SIMPLE-lexikon - En spr\u00e5kteknologisk resurs med semantisk information.;2012-05-30;lexicalConceptualResource;http://hdl.handle.net/10794/37;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/schlyter",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cc60225d-c6ca-50a7-8cee-0b78b6912a36",
-    "notes": [
-        "Dictionary of Old Swedish.",
-        "Svenskt SIMPLE-lexikon - En spr\u00e5kteknologisk resurs med semantisk information."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/37"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Dictionary"
-        }
-    ],
-    "title": [
-        "Schlyter (2017-10-16)",
-        "Schlyter (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cc62918e-e610-58e8-86a7-e9cc93ed6fd0.json b/oaitestdata/clarin-oai_dc/SET_1/json/cc62918e-e610-58e8-86a7-e9cc93ed6fd0.json
deleted file mode 100644
index 4fbb704b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cc62918e-e610-58e8-86a7-e9cc93ed6fd0.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Centre for Language and Speech Technology, Radboud University",
-        "The Netherlands Veteran Institute",
-        "Data Archiving and Networked Services"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/plain"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1163",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1163"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1163",
-    "PublicationTimestamp": "2010-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "Centre for Language and Speech Technology, Radboud University",
-        "The Netherlands Veteran Institute",
-        "Data Archiving and Networked Services"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1163;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Living Oral History Workbench: Interviewproject Nederlandse Veteranen (IPNV);The Netherlands Veterans Institute (VI) hosts about 250 interviews (audio) in which Dutch former military personel speak about their experiences during World War II (interviews about the years 1935-1945) and decolonisation in the Dutch East Indies (1945-1950) and Dutch New Guinea (1960-1962). In the project Living Oral History Workbench these interviews have been indexed by automatic speech recognition techniques. The list of interviews and their metadata are available at the CLARIN Center; researchers may apply to VI for access to the data.;2010;corpus;http://hdl.handle.net/11372/LRT-1163;nld;text/plain;downloadable_files_count: 0;Netherlands (the);The Netherlands Veteran Institute;Centre for Language and Speech Technology, Radboud University;Data Archiving and Networked Services;https://easy.dans.knaw.nl/ui/datasets/id/easy-dataset:41923",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cc62918e-e610-58e8-86a7-e9cc93ed6fd0",
-    "notes": [
-        "The Netherlands Veterans Institute (VI) hosts about 250 interviews (audio) in which Dutch former military personel speak about their experiences during World War II (interviews about the years 1935-1945) and decolonisation in the Dutch East Indies (1945-1950) and Dutch New Guinea (1960-1962). In the project Living Oral History Workbench these interviews have been indexed by automatic speech recognition techniques. The list of interviews and their metadata are available at the CLARIN Center; researchers may apply to VI for access to the data."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1163"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Living Oral History Workbench: Interviewproject Nederlandse Veteranen (IPNV)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cc63bbb3-56c4-5daa-a779-940d66619eaa.json b/oaitestdata/clarin-oai_dc/SET_1/json/cc63bbb3-56c4-5daa-a779-940d66619eaa.json
deleted file mode 100644
index 33b88304..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cc63bbb3-56c4-5daa-a779-940d66619eaa.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 13.2 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1797",
-    "MetadataAccess": [
-        "oai:ota:oucs:1797"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Henry, O., 1862-1910"
-    ],
-    "fulltext": "oai:ota:oucs:1797;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/1797.xml;The gift of the magi / by O. Henry;Henry, O., 1862-1910;default: 1976-01-01;text_and_corpus_linguistics;Fiction -- United States -- 20th century;Short stories -- United States -- 20th century;eng;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 13.2 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cc63bbb3-56c4-5daa-a779-940d66619eaa",
-    "oai_identifier": [
-        "oai:ota:oucs:1797"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- United States -- th century"
-        },
-        {
-            "name": "Short stories -- United States -- th century"
-        }
-    ],
-    "title": [
-        "The gift of the magi / by O. Henry"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1797.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cc65d7ca-d563-5e53-9997-185a9da4d7ad.json b/oaitestdata/clarin-oai_dc/SET_1/json/cc65d7ca-d563-5e53-9997-185a9da4d7ad.json
deleted file mode 100644
index 8f725383..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cc65d7ca-d563-5e53-9997-185a9da4d7ad.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 168 KB)"
-    ],
-    "Language": [
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0334",
-    "MetadataAccess": [
-        "oai:ota:oucs:0334"
-    ],
-    "PublicationYear": [
-        "20 BCE-14 BCE"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Letters"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Horace"
-    ],
-    "fulltext": "oai:ota:oucs:0334;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0334.xml;Epistulae;Epistul\u00c3\u00a6 I, II / Horace;Horace;20 BCE-14 BCE;text_and_corpus_linguistics;Latin letters -- Rome;lat;Oxford Text Archive, University of Oxford;(1 file : ca. 168 KB);Text;Letters;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cc65d7ca-d563-5e53-9997-185a9da4d7ad",
-    "oai_identifier": [
-        "oai:ota:oucs:0334"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Latin letters -- Rome"
-        }
-    ],
-    "title": [
-        "Epistulae",
-        "Epistul\u00c3\u00a6 I, II / Horace"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0334.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cc9cfce0-141c-53f8-a010-785d3683f35a.json b/oaitestdata/clarin-oai_dc/SET_1/json/cc9cfce0-141c-53f8-a010-785d3683f35a.json
deleted file mode 100644
index 5208a352..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cc9cfce0-141c-53f8-a010-785d3683f35a.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Humanities and Social Sciences, University of Zagreb"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Serbian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1057",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1057"
-    ],
-    "PID": "http://hdl.handle.net/11356/1057",
-    "PublicationTimestamp": "2016-03-05T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Faculty of Humanities and Social Sciences, University of Zagreb"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/324414",
-        "http://hdl.handle.net/11356/1066"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "GNU General Public Licence, version 3",
-        "http://opensource.org/licenses/GPL-3.0",
-        "PUB"
-    ],
-    "author": [
-        "Klubi\u010dka, Filip",
-        "Ljube\u0161i\u0107, Nikola"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1057;2017-06-27T18:07:31Z;hdl_11356_1023;hdl_11356_1024;Inflectional lexicon srLex 1.0;Ljube\u0161i\u0107, Nikola;Klubi\u010dka, Filip;lexicon;morphology;inflection;hrLex is an large inflectional lexicon of Serbian language where each entry consists of a (wordform, lemma, MSD) triple. The MSD tagset follows the revised MULTEXT-East V4 tagset for Croatian and Serbian, available at\r\nhttps://github.com/ffnlp/sethr/blob/master/mte4r-upos.mapping.;2016-03-05;lexicalConceptualResource;http://hdl.handle.net/11356/1057;srp;info:eu-repo/grantAgreement/EC/FP7/324414;http://hdl.handle.net/11356/1066;GNU General Public Licence, version 3;http://opensource.org/licenses/GPL-3.0;PUB;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Faculty of Humanities and Social Sciences, University of Zagreb;http://nlp.ffzg.hr/resources/lexicons/srlex/ \u200e",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cc9cfce0-141c-53f8-a010-785d3683f35a",
-    "notes": [
-        "hrLex is an large inflectional lexicon of Serbian language where each entry consists of a (wordform, lemma, MSD) triple. The MSD tagset follows the revised MULTEXT-East V4 tagset for Croatian and Serbian, available at\r\nhttps://github.com/ffnlp/sethr/blob/master/mte4r-upos.mapping."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1057"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "lexicon"
-        },
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "inflection"
-        }
-    ],
-    "title": [
-        "Inflectional lexicon srLex 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cc9f5dce-5500-5445-b3fe-1907e30aeeba.json b/oaitestdata/clarin-oai_dc/SET_1/json/cc9f5dce-5500-5445-b3fe-1907e30aeeba.json
deleted file mode 100644
index ba957572..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cc9f5dce-5500-5445-b3fe-1907e30aeeba.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/293",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/293"
-    ],
-    "PID": "http://hdl.handle.net/11321/293",
-    "PublicationTimestamp": "2016-04-25T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Marci\u0144czuk, Micha\u0142",
-        "Krautforst, Micha\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/293;2016-06-06T11:03:39Z;hdl_11321_3;hdl_11321_4;Wikipedia Infobox Mapping PL;Marci\u0144czuk, Micha\u0142;Krautforst, Micha\u0142;mapping;named entities;wikipedia;kpwr ne schema;Mapping between infobox attributes used in Polish Wikipedia and KPWr named entity schema.;2016-04-25;lexicalConceptualResource;http://hdl.handle.net/11321/293;pol;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;Wroc\u0142aw University of Technology;http://nlp.pwr.wroc.pl/narzedzia-i-zasoby/zasoby/nelexicon",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cc9f5dce-5500-5445-b3fe-1907e30aeeba",
-    "notes": [
-        "Mapping between infobox attributes used in Polish Wikipedia and KPWr named entity schema."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/293"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "mapping"
-        },
-        {
-            "name": "named entities"
-        },
-        {
-            "name": "wikipedia"
-        },
-        {
-            "name": "kpwr ne schema"
-        }
-    ],
-    "title": [
-        "Wikipedia Infobox Mapping PL"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ccef82df-027f-5146-82ec-346329a7b7b6.json b/oaitestdata/clarin-oai_dc/SET_1/json/ccef82df-027f-5146-82ec-346329a7b7b6.json
deleted file mode 100644
index 3cd148be..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ccef82df-027f-5146-82ec-346329a7b7b6.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4308",
-    "MetadataAccess": [
-        "oai:ota:oucs:4308"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Sheridan, Richard Brinsley, 1751-1816."
-    ],
-    "fulltext": "oai:ota:oucs:4308;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4308.xml;Speech of Richard Brinsley Sheridan: Esq. in the House of Commons of Great Britain, on Thursday, January 31st, 1799, in reply to Mr. Pitt's speech on the union with Ireland.;Sheridan, Richard Brinsley, 1751-1816.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ccef82df-027f-5146-82ec-346329a7b7b6",
-    "oai_identifier": [
-        "oai:ota:oucs:4308"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Speech of Richard Brinsley Sheridan: Esq. in the House of Commons of Great Britain, on Thursday, January 31st, 1799, in reply to Mr. Pitt's speech on the union with Ireland."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4308.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cd0479c6-52fe-5849-a830-9714afca3327.json b/oaitestdata/clarin-oai_dc/SET_1/json/cd0479c6-52fe-5849-a830-9714afca3327.json
deleted file mode 100644
index a9dd2d64..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cd0479c6-52fe-5849-a830-9714afca3327.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "Arabic"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-964",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-964"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-964",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-964;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Arabic;ca. 100.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-964;ara;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#arabica",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cd0479c6-52fe-5849-a830-9714afca3327",
-    "notes": [
-        "ca. 100.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-964"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Arabic"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cd07fc40-9d16-5cbd-93e0-739bca411e0e.json b/oaitestdata/clarin-oai_dc/SET_1/json/cd07fc40-9d16-5cbd-93e0-739bca411e0e.json
deleted file mode 100644
index bf1a6a64..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cd07fc40-9d16-5cbd-93e0-739bca411e0e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5040",
-    "MetadataAccess": [
-        "oai:ota:oucs:5040"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Trusler, John, 1735-1820."
-    ],
-    "fulltext": "oai:ota:oucs:5040;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5040.xml;The habitable world described: or the present state of the people in all parts of the globe, from north to south; shewing the situation, extent, climate, ... including all the new discoveries: ... With a great variety of maps and copper-plates, ... By the Rev. Dr. John Trusler. ... [pt.6];Trusler, John, 1735-1820.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cd07fc40-9d16-5cbd-93e0-739bca411e0e",
-    "oai_identifier": [
-        "oai:ota:oucs:5040"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The habitable world described: or the present state of the people in all parts of the globe, from north to south; shewing the situation, extent, climate, ... including all the new discoveries: ... With a great variety of maps and copper-plates, ... By the Rev. Dr. John Trusler. ... [pt.6]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5040.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cd2cde6f-f290-5057-b5b6-e605b2f95e32.json b/oaitestdata/clarin-oai_dc/SET_1/json/cd2cde6f-f290-5057-b5b6-e605b2f95e32.json
deleted file mode 100644
index 101fbe73..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cd2cde6f-f290-5057-b5b6-e605b2f95e32.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3402",
-    "MetadataAccess": [
-        "oai:ota:oucs:3402"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Latham, John, 1761-1843."
-    ],
-    "fulltext": "oai:ota:oucs:3402;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3402.xml;On rheumatism, and gout: a letter addressed to Sir George Baker, ... By John Latham, M.D. ...;Latham, John, 1761-1843.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cd2cde6f-f290-5057-b5b6-e605b2f95e32",
-    "oai_identifier": [
-        "oai:ota:oucs:3402"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "On rheumatism, and gout: a letter addressed to Sir George Baker, ... By John Latham, M.D. ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3402.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cd3181b7-d201-5824-889c-2711a9419599.json b/oaitestdata/clarin-oai_dc/SET_1/json/cd3181b7-d201-5824-889c-2711a9419599.json
deleted file mode 100644
index 2c1288f4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cd3181b7-d201-5824-889c-2711a9419599.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/gzip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/538",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/538"
-    ],
-    "PID": "http://hdl.handle.net/11321/538",
-    "PublicationTimestamp": "2018-07-20T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Pie\u0144kosz, Micha\u0142",
-        "Przetacka, Joanna",
-        "Tele\u017cy\u0144ska, Helena",
-        "Kozakoszczak, Jakub",
-        "Antonowicz, Bart\u0142omiej",
-        "Rutkowski, Szymon",
-        "Oklesi\u0144ski, Daniel",
-        "Jaworski, Wojciech",
-        "Lupa, Jan",
-        "Markiewicz, Adam",
-        "Morusiewicz, Agnieszka",
-        "Kowalewski, Jakub"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/538;2018-07-22T07:34:36Z;hdl_11321_3;hdl_11321_4;Categorial Parser;Jaworski, Wojciech;Oklesi\u0144ski, Daniel;Lupa, Jan;Rutkowski, Szymon;Kozakoszczak, Jakub;Przetacka, Joanna;Tele\u017cy\u0144ska, Helena;Antonowicz, Bart\u0142omiej;Markiewicz, Adam;Kowalewski, Jakub;Pie\u0144kosz, Micha\u0142;Morusiewicz, Agnieszka;constituency parsing;semantics;meaning representation;This resource contains Categorial Syntactic-Semantic Parser \u201eENIAM\u201d. The Github repository contains the code and information on how to use the tool.;2018-07-20;toolService;http://hdl.handle.net/11321/538;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain; charset=utf-8;application/gzip;downloadable_files_count: 1;Institute of Computer Science, Polish Academy of Sciences;http://git.nlp.ipipan.waw.pl/wojciech.jaworski/ENIAM",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cd3181b7-d201-5824-889c-2711a9419599",
-    "notes": [
-        "This resource contains Categorial Syntactic-Semantic Parser \u201eENIAM\u201d. The Github repository contains the code and information on how to use the tool."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/538"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "constituency parsing"
-        },
-        {
-            "name": "semantics"
-        },
-        {
-            "name": "meaning representation"
-        }
-    ],
-    "title": [
-        "Categorial Parser"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cd3f977c-4f30-5339-adcb-0dc51c068ce9.json b/oaitestdata/clarin-oai_dc/SET_1/json/cd3f977c-4f30-5339-adcb-0dc51c068ce9.json
deleted file mode 100644
index 74abb91a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cd3f977c-4f30-5339-adcb-0dc51c068ce9.json
+++ /dev/null
@@ -1,99 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "application/pdf",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Spanish",
-        "Italian",
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1078",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1078"
-    ],
-    "PID": "http://hdl.handle.net/11356/1078",
-    "PublicationTimestamp": "2016-11-28T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/611346"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "The MIT License (MIT)",
-        "http://opensource.org/licenses/mit-license.php",
-        "PUB"
-    ],
-    "author": [
-        "Rei, Luis",
-        "Krek, Simon",
-        "Mladeni\u0107, Dunja"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1078;2018-12-02T19:40:11Z;hdl_11356_1023;hdl_11356_1024;xLiMe Twitter Corpus XTC 1.0.1;Rei, Luis;Krek, Simon;Mladeni\u0107, Dunja;social media;computer-mediated communication;Twitter;tagging;named entities;sentiment classification;multilingual;manual annotation;The xLiMe Twitter Corpus contains tweets in German, Italian and Spanish manually annotated with part-of-speech, named entities, and message-level sentiment polarity. In total, the corpus contains almost 20K annotated messages and 350K tokens.\r\nThe corpus is described in \r\nLuis Rei, Dunja Mladeni\u0107, Simon Krek. A Multilingual Social Media Linguistic Corpus. Proceedings of the 4th Conference on CMC and Social Media Corpora for the Humanities. 27\u201328 September 2016, Ljubljana, Slovenia. http://nl.ijs.si/janes/cmc-corpora2016/proceedings/;2016-11-28;corpus;http://hdl.handle.net/11356/1078;spa;ita;deu;info:eu-repo/grantAgreement/EC/FP7/611346;The MIT License (MIT);http://opensource.org/licenses/mit-license.php;PUB;application/zip;application/pdf;text/plain; charset=utf-8;downloadable_files_count: 2;Jo\u017eef Stefan Institute;http://github.com/lrei/xlime_twitter_corpus",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cd3f977c-4f30-5339-adcb-0dc51c068ce9",
-    "notes": [
-        "The xLiMe Twitter Corpus contains tweets in German, Italian and Spanish manually annotated with part-of-speech, named entities, and message-level sentiment polarity. In total, the corpus contains almost 20K annotated messages and 350K tokens.\r\nThe corpus is described in \r\nLuis Rei, Dunja Mladeni\u0107, Simon Krek. A Multilingual Social Media Linguistic Corpus. Proceedings of the 4th Conference on CMC and Social Media Corpora for the Humanities. 27\u201328 September 2016, Ljubljana, Slovenia. http://nl.ijs.si/janes/cmc-corpora2016/proceedings/"
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1078"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "social media"
-        },
-        {
-            "name": "computer-mediated communication"
-        },
-        {
-            "name": "Twitter"
-        },
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "named entities"
-        },
-        {
-            "name": "sentiment classification"
-        },
-        {
-            "name": "multilingual"
-        },
-        {
-            "name": "manual annotation"
-        }
-    ],
-    "title": [
-        "xLiMe Twitter Corpus XTC 1.0.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cd4e6bc2-94c6-585f-b4b9-55a6a31c8efd.json b/oaitestdata/clarin-oai_dc/SET_1/json/cd4e6bc2-94c6-585f-b4b9-55a6a31c8efd.json
deleted file mode 100644
index 0c65c59b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cd4e6bc2-94c6-585f-b4b9-55a6a31c8efd.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "Contributor": [
-        "Freixa, Judit"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1109",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1109"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1109",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1109;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Diccionario de neologismos on line;Freixa, Judit;neologisms database;Lexicographic resource containing 3.530 neologisms documented in press written in Spanish between 1989 and 2007.;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1109;spa;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra;http://obneo.iula.upf.edu/spes//",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cd4e6bc2-94c6-585f-b4b9-55a6a31c8efd",
-    "notes": [
-        "Lexicographic resource containing 3.530 neologisms documented in press written in Spanish between 1989 and 2007."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1109"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "neologisms database"
-        }
-    ],
-    "title": [
-        "Diccionario de neologismos on line"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cd5d5928-9cac-5eb4-a06c-d4e6419e9479.json b/oaitestdata/clarin-oai_dc/SET_1/json/cd5d5928-9cac-5eb4-a06c-d4e6419e9479.json
deleted file mode 100644
index 999c7080..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cd5d5928-9cac-5eb4-a06c-d4e6419e9479.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5577",
-    "MetadataAccess": [
-        "oai:ota:oucs:5577"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Merande, D."
-    ],
-    "fulltext": "oai:ota:oucs:5577;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5577.xml;A succinct account of a machine, newly invented for the cure of pr\u00c3\u00a6ternatural curvatures of the spine: together with a detail of several cases, in which this machine has been tried with great success. By D. Merande, M.D;Merande, D.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cd5d5928-9cac-5eb4-a06c-d4e6419e9479",
-    "oai_identifier": [
-        "oai:ota:oucs:5577"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A succinct account of a machine, newly invented for the cure of pr\u00c3\u00a6ternatural curvatures of the spine: together with a detail of several cases, in which this machine has been tried with great success. By D. Merande, M.D"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5577.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cd990fd9-1d77-5410-af02-b8f78e311896.json b/oaitestdata/clarin-oai_dc/SET_1/json/cd990fd9-1d77-5410-af02-b8f78e311896.json
deleted file mode 100644
index 5be5ac77..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cd990fd9-1d77-5410-af02-b8f78e311896.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Society for Danish Language and Literature, DSL"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 11",
-        "application/zip",
-        "application/pdf",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Danish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repository.clarin.dk:20.500.12115/36",
-    "MetadataAccess": [
-        "oai:repository.clarin.dk:20.500.12115/36"
-    ],
-    "PID": "http://hdl.handle.net/20.500.12115/36",
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Society for Danish Language and Literature, DSL"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN-ACA-NC",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NC=1&NORED=1",
-        "ACA"
-    ],
-    "author": [
-        "Asmussen, J\u00f8rg",
-        "Halskov, Jakob"
-    ],
-    "fulltext": "oai:repository.clarin.dk:20.500.12115/36;2018-12-19T12:20:07Z;hdl_20.500.12115_1;hdl_20.500.12115_3;DK-CLARIN Reference Corpus of General Danish;Asmussen, J\u00f8rg;Halskov, Jakob;LGP - Language for General Purposes;DK-CLARIN Reference Corpus of General Danish has been collected as part of DK-CLARIN project, WP2.1, 2008 - 2011. All texts are in XML TEIP5 format (TEIP5DKCLARIN-format), with tokenisation, ePOS-tagging, sentence and paragraph segmentation, and lemmatisation. The corpus comprises 45,113,245 words.;2011;corpus;http://hdl.handle.net/20.500.12115/36;dan;CLARIN-ACA-NC;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NC=1&NORED=1;ACA;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/pdf;application/pdf;application/pdf;text/plain; charset=utf-8;downloadable_files_count: 11;Society for Danish Language and Literature, DSL;https://korpus.dsl.dk/clarin/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cd990fd9-1d77-5410-af02-b8f78e311896",
-    "notes": [
-        "DK-CLARIN Reference Corpus of General Danish has been collected as part of DK-CLARIN project, WP2.1, 2008 - 2011. All texts are in XML TEIP5 format (TEIP5DKCLARIN-format), with tokenisation, ePOS-tagging, sentence and paragraph segmentation, and lemmatisation. The corpus comprises 45,113,245 words."
-    ],
-    "oai_identifier": [
-        "oai:repository.clarin.dk:20.500.12115/36"
-    ],
-    "oai_set": [
-        "hdl_20.500.12115_1",
-        "hdl_20.500.12115_3"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "LGP - Language General Purposes"
-        }
-    ],
-    "title": [
-        "DK-CLARIN Reference Corpus of General Danish"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cdb7c7a7-9efb-52cf-a3ca-02d5b7c2a650.json b/oaitestdata/clarin-oai_dc/SET_1/json/cdb7c7a7-9efb-52cf-a3ca-02d5b7c2a650.json
deleted file mode 100644
index 01f6aead..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cdb7c7a7-9efb-52cf-a3ca-02d5b7c2a650.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Link\u00f6ping University"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Swedish",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1517",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1517"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1517",
-    "PublicationTimestamp": "2015-10-12T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Link\u00f6ping University"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11372/LRT-1513"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)",
-        "http://creativecommons.org/licenses/by-nc/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Ahrenberg, Lars",
-        "Holmqvist, Maria"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1517;2016-04-06T16:39:49Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;A Gold Standard Word Alignment for English-Swedish (2015-10-12);Ahrenberg, Lars;Holmqvist, Maria;word alignment;A Gold Standard Word Alignment for English-Swedish (GES) is a resource containing 1164 manually word aligned sentences pairs from English and Swedish versions of Europarl v. 2.;2015-10-12;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1517;swe;eng;http://hdl.handle.net/11372/LRT-1513;Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0);http://creativecommons.org/licenses/by-nc/4.0/;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Link\u00f6ping University;https://www.ida.liu.se/labs/nlplab/ges/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cdb7c7a7-9efb-52cf-a3ca-02d5b7c2a650",
-    "notes": [
-        "A Gold Standard Word Alignment for English-Swedish (GES) is a resource containing 1164 manually word aligned sentences pairs from English and Swedish versions of Europarl v. 2."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1517"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "word alignment"
-        }
-    ],
-    "title": [
-        "A Gold Standard Word Alignment for English-Swedish (2015-10-12)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cdc0717d-936f-59c9-bae9-d22a8131a1fd.json b/oaitestdata/clarin-oai_dc/SET_1/json/cdc0717d-936f-59c9-bae9-d22a8131a1fd.json
deleted file mode 100644
index 578b7dca..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cdc0717d-936f-59c9-bae9-d22a8131a1fd.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "less than 512 KB"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0487",
-    "MetadataAccess": [
-        "oai:ota:oucs:0487"
-    ],
-    "PublicationYear": [
-        "276 BCE"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Aratus,  Solensis"
-    ],
-    "fulltext": "oai:ota:oucs:0487;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0487.xml;Phaenomena / compiled by Thesaurus Linguae Graecae;Aratus,  Solensis;276 BCE;text_and_corpus_linguistics;Poems -- Greece -- 3rd century B.C.;grc;Oxford Text Archive, University of Oxford;less than 512 KB;Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cdc0717d-936f-59c9-bae9-d22a8131a1fd",
-    "oai_identifier": [
-        "oai:ota:oucs:0487"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- Greece -- rd century B.C."
-        }
-    ],
-    "title": [
-        "Phaenomena / compiled by Thesaurus Linguae Graecae"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0487.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ce1570a3-3e14-52e0-bb15-8e156cf4561d.json b/oaitestdata/clarin-oai_dc/SET_1/json/ce1570a3-3e14-52e0-bb15-8e156cf4561d.json
deleted file mode 100644
index ef9692c6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ce1570a3-3e14-52e0-bb15-8e156cf4561d.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5167",
-    "MetadataAccess": [
-        "oai:ota:oucs:5167"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Lewis, M. G. (Matthew Gregory), 1775-1818."
-    ],
-    "fulltext": "oai:ota:oucs:5167;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5167.xml;The monk: a romance. In three volumes. ... [pt.2];Lewis, M. G. (Matthew Gregory), 1775-1818.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ce1570a3-3e14-52e0-bb15-8e156cf4561d",
-    "oai_identifier": [
-        "oai:ota:oucs:5167"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The monk: a romance. In three volumes. ... [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5167.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ce19eb6f-a9c9-5c5d-aaab-ed61f86d25c0.json b/oaitestdata/clarin-oai_dc/SET_1/json/ce19eb6f-a9c9-5c5d-aaab-ed61f86d25c0.json
deleted file mode 100644
index 73bda9f7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ce19eb6f-a9c9-5c5d-aaab-ed61f86d25c0.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2903",
-    "MetadataAccess": [
-        "oai:ota:oucs:2903"
-    ],
-    "PublicationTimestamp": "1779-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1779"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2903;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2903.xml;Memorandum on Mr Grattan's walk at Belcamp;Swift, Jonathan, 1667-1745;1779;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ce19eb6f-a9c9-5c5d-aaab-ed61f86d25c0",
-    "oai_identifier": [
-        "oai:ota:oucs:2903"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Memorandum on Mr Grattan's walk at Belcamp"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2903.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ce32bfad-f5df-5903-b69d-ea656471dac3.json b/oaitestdata/clarin-oai_dc/SET_1/json/ce32bfad-f5df-5903-b69d-ea656471dac3.json
deleted file mode 100644
index 35a26a44..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ce32bfad-f5df-5903-b69d-ea656471dac3.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Palmer, Nigel F."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 175 KB)"
-    ],
-    "Language": [
-        "Middle High German (ca. 1050-1500)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1968",
-    "MetadataAccess": [
-        "oai:ota:oucs:1968"
-    ],
-    "PublicationTimestamp": "1290-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1290"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hermann, Bruder, 13th cent."
-    ],
-    "fulltext": "oai:ota:oucs:1968;2018-04-16T14:47:08Z;http://ota.ox.ac.uk/headers/1968.xml;Leben der Gr\u00c3\u00a4fin Iolande von Vianden.;Jolanda / Hermann, Bruder;Hermann, Bruder, 13th cent.;1290;text_and_corpus_linguistics;German poetry -- Middle High German, 1050-1500;gmh;Oxford Text Archive, University of Oxford;Palmer, Nigel F.;(1 file : ca. 175 KB);Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ce32bfad-f5df-5903-b69d-ea656471dac3",
-    "oai_identifier": [
-        "oai:ota:oucs:1968"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "German poetry -- Middle High German"
-        }
-    ],
-    "title": [
-        "Leben der Gr\u00c3\u00a4fin Iolande von Vianden.",
-        "Jolanda / Hermann, Bruder"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1968.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ce37ef93-8dee-57bc-8372-cab34d8b47d5.json b/oaitestdata/clarin-oai_dc/SET_1/json/ce37ef93-8dee-57bc-8372-cab34d8b47d5.json
deleted file mode 100644
index e864538b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ce37ef93-8dee-57bc-8372-cab34d8b47d5.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Universitat de Lleida"
-    ],
-    "Contributor": [
-        "V\u00e0zquez, Gl\u00f2ria"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-710",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-710"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-710",
-    "PublicationTimestamp": "2005-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2005"
-    ],
-    "Publisher": [
-        "Universitat de Lleida"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-710;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;VOLEM;V\u00e0zquez, Gl\u00f2ria;Multilingual Verbal Lexicon: Catalan , spanish (connexion with French and Basc of other groups);2005;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-710;spa;downloadable_files_count: 0;Spain;Universitat de Lleida;http://grial.uab.es/multi/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ce37ef93-8dee-57bc-8372-cab34d8b47d5",
-    "notes": [
-        "Multilingual Verbal Lexicon: Catalan , spanish (connexion with French and Basc of other groups)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-710"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "VOLEM"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ce5c8af6-74ee-5336-b91a-acb7d1f0f399.json b/oaitestdata/clarin-oai_dc/SET_1/json/ce5c8af6-74ee-5336-b91a-acb7d1f0f399.json
deleted file mode 100644
index 4cf1bab6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ce5c8af6-74ee-5336-b91a-acb7d1f0f399.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3369",
-    "MetadataAccess": [
-        "oai:ota:oucs:3369"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Blair, Hugh, 1718-1800."
-    ],
-    "fulltext": "oai:ota:oucs:3369;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3369.xml;Lectures on rhetoric and belles lettres: By Hugh Blair, ... In three volumes. ... [pt.2];Blair, Hugh, 1718-1800.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ce5c8af6-74ee-5336-b91a-acb7d1f0f399",
-    "oai_identifier": [
-        "oai:ota:oucs:3369"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Lectures on rhetoric and belles lettres: By Hugh Blair, ... In three volumes. ... [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3369.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ceaf104f-bbdf-53fd-b880-0d5fd8e48fd2.json b/oaitestdata/clarin-oai_dc/SET_1/json/ceaf104f-bbdf-53fd-b880-0d5fd8e48fd2.json
deleted file mode 100644
index 05017841..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ceaf104f-bbdf-53fd-b880-0d5fd8e48fd2.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Reymont"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/109",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/109"
-    ],
-    "PID": "http://hdl.handle.net/11321/109",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Reymont"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Reymont, Reymont"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/109;2015-04-08T14:13:31Z;hdl_11321_3;hdl_11321_4;MWE Reymont, Ch\u0142opi;Reymont, Reymont;Reymont;2015-04-08;corpus;http://hdl.handle.net/11321/109;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain; charset=utf-8;downloadable_files_count: 1;Reymont",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ceaf104f-bbdf-53fd-b880-0d5fd8e48fd2",
-    "notes": [
-        "Reymont"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/109"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Reymont, Ch\u0142opi"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cebe8994-5279-5bc7-80f3-37435efaa5ee.json b/oaitestdata/clarin-oai_dc/SET_1/json/cebe8994-5279-5bc7-80f3-37435efaa5ee.json
deleted file mode 100644
index 981e01a0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cebe8994-5279-5bc7-80f3-37435efaa5ee.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Universitat de Barcelona"
-    ],
-    "Contributor": [
-        "Castell\u00f3n, Irene"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-510",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-510"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-510",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Universitat de Barcelona"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-510;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Spanish WordNet 3.0;Castell\u00f3n, Irene;63.000 synsets, plain text;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-510;spa;downloadable_files_count: 0;Spain;Universitat de Barcelona;http://grial.uab.es/recursos.php",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cebe8994-5279-5bc7-80f3-37435efaa5ee",
-    "notes": [
-        "63.000 synsets, plain text"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-510"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Spanish WordNet 3.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cedfc6d0-a076-557d-a46f-56b2d1f82e22.json b/oaitestdata/clarin-oai_dc/SET_1/json/cedfc6d0-a076-557d-a46f-56b2d1f82e22.json
deleted file mode 100644
index cc657df2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cedfc6d0-a076-557d-a46f-56b2d1f82e22.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Prokopidis, Prokopis"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Modern Greek (1453-)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-199",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-199"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-199",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Greece"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-199;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Greek Dependency Treebank (GDT);Prokopidis, Prokopis;70K words, Non-validated sentence segmentation. Non-validated POS tagging, Manual annotation of syntactic dependencies and dependency labels, Manual annotation of semantic roles, Manual annotation of events based on a shallow domain specific ontology (only for a 31K words  subset of GDT);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-199;ell;downloadable_files_count: 0;Greece;http://www.ilsp.gr/homepages/prokopidis/documents/gdt_tlt2005.pdf",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cedfc6d0-a076-557d-a46f-56b2d1f82e22",
-    "notes": [
-        "70K words, Non-validated sentence segmentation. Non-validated POS tagging, Manual annotation of syntactic dependencies and dependency labels, Manual annotation of semantic roles, Manual annotation of events based on a shallow domain specific ontology (only for a 31K words  subset of GDT)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-199"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Greek Dependency Treebank (GDT)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cee19139-3091-5c18-90fe-4bf4eb32b8bb.json b/oaitestdata/clarin-oai_dc/SET_1/json/cee19139-3091-5c18-90fe-4bf4eb32b8bb.json
deleted file mode 100644
index a3a932a7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cee19139-3091-5c18-90fe-4bf4eb32b8bb.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Lutkemeyer, Willy"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 131 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1825",
-    "MetadataAccess": [
-        "oai:ota:oucs:1825"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Shakespeare, William, 1564-1616"
-    ],
-    "fulltext": "oai:ota:oucs:1825;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1825.xml;Macbeth : [1623 Folio] / William Shakespeare ;Shakespeare, William, 1564-1616;text_and_corpus_linguistics;English drama -- Early modern and Elizabethan, 1500-1600;Oxford Text Archive, University of Oxford;Lutkemeyer, Willy;text/sgml;(1 file : ca. 131 KB);Text;Plays;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cee19139-3091-5c18-90fe-4bf4eb32b8bb",
-    "oai_identifier": [
-        "oai:ota:oucs:1825"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- Early modern Elizabethan"
-        }
-    ],
-    "title": [
-        "Macbeth : [1623 Folio] / William Shakespeare "
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1825.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cf233eb6-8f38-50fe-87b9-97ad777843b2.json b/oaitestdata/clarin-oai_dc/SET_1/json/cf233eb6-8f38-50fe-87b9-97ad777843b2.json
deleted file mode 100644
index e54ebd1f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cf233eb6-8f38-50fe-87b9-97ad777843b2.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "application/zip"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1176",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1176"
-    ],
-    "PID": "http://hdl.handle.net/11356/1176",
-    "PublicationTimestamp": "2018-03-20T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "http://www.sdjt.si/wp/wp-content/uploads/2018/09/JTDH-2018_Bozovic-et-al_Opus-MontenegrinSubs-1-0-First-electronic-corpus-of-the-Montenegrin-language.pdf"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by-sa/4.0/"
-    ],
-    "author": [
-        "Bo\u017eovi\u0107, Petar",
-        "Erjavec, Toma\u017e",
-        "Ljube\u0161i\u0107, Nikola",
-        "Gorjanc, Vojko",
-        "Tiedemann, J\u00f6rg"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1176;2018-10-24T20:57:01Z;hdl_11356_1023;hdl_11356_1024;English-Montenegrin parallel corpus of subtitles Opus-MontenegrinSubs 1.0;Bo\u017eovi\u0107, Petar;Erjavec, Toma\u017e;Tiedemann, J\u00f6rg;Ljube\u0161i\u0107, Nikola;Gorjanc, Vojko;parallel corpus;subtitles;multilingual;This corpus contains parallel English-Montenegrin subtitles collected in the scope of conducting a linguistic and translatological research by Petar Bo\u017eovi\u0107 for his PhD thesis \"Audiovisual Translation and Elements of Culture: A Comparative Analysis of Transfer with Reception Study in Montenegro\". The data and permission to redistribute were obtained from the Radio and Television of Montenegro (http://www.rtcg.me), the public service broadcaster of Montenegro. \r\nThe corpus consists of English and Montenegrin subtitles of three TV series: House of Cards (686 minutes), Damages (2878 minutes), and Tudors (1999 minutes). The corpus covers 10 seasons, 110 episodes, and 5,563 minutes in terms of duration.\r\nSentence alignment and basic encoding were performed inside the OPUS project (http://opus.nlpl.eu/MontenegrinSubs.php), while MSD tagging, lemmatisation, and TEI conversion were performed by the CLARIN.SI infrastructure. The English texts were tagged by TreeTagger (http://www.cis.uni-muenchen.de/~schmid/tools/TreeTagger/) and the Montenegrin texts by ReLDI Tagger (https://github.com/clarinsi/reldi-tagger) using the Serbian language model. The TreeTagger (Penn Treebank) tagset was mapped to the SPOOK MSD tagset for English (http://nl.ijs.si/spook/msd/html-en/msd-en.html).\r\nThe corpus is available in TEI format and derived vertical format used by CQP and Manatee (Sketch Engine). The alignments in the vertical file are given separately as tables linking the alignment elements of the two languages.;2018-03-20;corpus;http://hdl.handle.net/11356/1176;cnr;eng;http://www.sdjt.si/wp/wp-content/uploads/2018/09/JTDH-2018_Bozovic-et-al_Opus-MontenegrinSubs-1-0-First-electronic-corpus-of-the-Montenegrin-language.pdf;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);PUB;https://creativecommons.org/licenses/by-sa/4.0/;text/plain; charset=utf-8;application/zip;application/zip;downloadable_files_count: 2;Jo\u017eef Stefan Institute;http://opus.nlpl.eu/MontenegrinSubs.php",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cf233eb6-8f38-50fe-87b9-97ad777843b2",
-    "notes": [
-        "This corpus contains parallel English-Montenegrin subtitles collected in the scope of conducting a linguistic and translatological research by Petar Bo\u017eovi\u0107 for his PhD thesis \"Audiovisual Translation and Elements of Culture: A Comparative Analysis of Transfer with Reception Study in Montenegro\". The data and permission to redistribute were obtained from the Radio and Television of Montenegro (http://www.rtcg.me), the public service broadcaster of Montenegro. \r\nThe corpus consists of English and Montenegrin subtitles of three TV series: House of Cards (686 minutes), Damages (2878 minutes), and Tudors (1999 minutes). The corpus covers 10 seasons, 110 episodes, and 5,563 minutes in terms of duration.\r\nSentence alignment and basic encoding were performed inside the OPUS project (http://opus.nlpl.eu/MontenegrinSubs.php), while MSD tagging, lemmatisation, and TEI conversion were performed by the CLARIN.SI infrastructure. The English texts were tagged by TreeTagger (http://www.cis.uni-muenchen.de/~schmid/tools/TreeTagger/) and the Montenegrin texts by ReLDI Tagger (https://github.com/clarinsi/reldi-tagger) using the Serbian language model. The TreeTagger (Penn Treebank) tagset was mapped to the SPOOK MSD tagset for English (http://nl.ijs.si/spook/msd/html-en/msd-en.html).\r\nThe corpus is available in TEI format and derived vertical format used by CQP and Manatee (Sketch Engine). The alignments in the vertical file are given separately as tables linking the alignment elements of the two languages."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1176"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parallel corpus"
-        },
-        {
-            "name": "subtitles"
-        },
-        {
-            "name": "multilingual"
-        }
-    ],
-    "title": [
-        "English-Montenegrin parallel corpus of subtitles Opus-MontenegrinSubs 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cf2d4702-05d7-58d4-826d-f77e26674163.json b/oaitestdata/clarin-oai_dc/SET_1/json/cf2d4702-05d7-58d4-826d-f77e26674163.json
deleted file mode 100644
index 949e0836..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cf2d4702-05d7-58d4-826d-f77e26674163.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "803 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0013",
-    "MetadataAccess": [
-        "oai:ota:oucs:0013"
-    ],
-    "PublicationTimestamp": "1796-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1796"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Letters"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Austen, Jane,  1775-1817"
-    ],
-    "fulltext": "oai:ota:oucs:0013;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0013.xml; Letters  / compiled by P. Barrow;Austen, Jane,  1775-1817;1796-1817;text_and_corpus_linguistics;Letters -- England -- 19th century;eng;Oxford Text Archive, University of Oxford;803 KB;Text;Letters;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cf2d4702-05d7-58d4-826d-f77e26674163",
-    "oai_identifier": [
-        "oai:ota:oucs:0013"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Letters -- England -- th century"
-        }
-    ],
-    "title": [
-        " Letters  / compiled by P. Barrow"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0013.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cf48089c-f3f6-5253-829e-0720c5916c58.json b/oaitestdata/clarin-oai_dc/SET_1/json/cf48089c-f3f6-5253-829e-0720c5916c58.json
deleted file mode 100644
index b24920a8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cf48089c-f3f6-5253-829e-0720c5916c58.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Collegium Soc. Jesu."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-44",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-44"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D1E-C",
-    "PublicationTimestamp": "1735-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1735"
-    ],
-    "Publisher": [
-        "Drukarnia Collegium Soc. Jesu."
-    ],
-    "RelatedIdentifier": [
-        "http://pbc.biaman.pl/Content/44"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "author": [
-        "Skarga, Piotr (1536 - 1612)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-44;2019-03-01T15:31:40Z;Kazania na niedziele y \u015bwi\u0119ta ca\u0142ego roku [...] \u017ca dozwoleniem Starszych. Po czwarty raz do druku podane.;Skarga, Piotr (1536 - 1612);Kazania polskie 17 w.;ilo\u015b\u0107 skan\u00f3w: 633 ; sygn, 1200;Drukarnia Collegium Soc. Jesu.;1735;starodruk;application/xml;clarind-uds:poldilemma-44;hdl:11858/00-246C-0000-0023-8D1E-C;pol;lat;http://pbc.biaman.pl/Content/44;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cf48089c-f3f6-5253-829e-0720c5916c58",
-    "notes": [
-        "ilo\u015b\u0107 skan\u00f3w: 633 ; sygn, 1200"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-44"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Kazania polskie w."
-        }
-    ],
-    "title": [
-        "Kazania na niedziele y \u015bwi\u0119ta ca\u0142ego roku [...] \u017ca dozwoleniem Starszych. Po czwarty raz do druku podane."
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cf4ae366-9d8d-52bc-a061-9379aa93851f.json b/oaitestdata/clarin-oai_dc/SET_1/json/cf4ae366-9d8d-52bc-a061-9379aa93851f.json
deleted file mode 100644
index 394a9b11..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cf4ae366-9d8d-52bc-a061-9379aa93851f.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "downloadable_files_count: 10",
-        "application/vnd.oasis.opendocument.text",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/368",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/368"
-    ],
-    "PID": "http://hdl.handle.net/11321/368",
-    "PublicationTimestamp": "2017-05-27T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Oleksy, Marcin",
-        "Marci\u0144czuk, Micha\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/368;2017-05-27T21:11:22Z;hdl_11321_3;hdl_11321_4;Warsztaty CLARIN-PL w IPI PAN;Oleksy, Marcin;Marci\u0144czuk, Micha\u0142;corpus;Korpus testowy przygotowany na warsztaty CLARIN-PL w IPI PAN.;2017-05-27;corpus;http://hdl.handle.net/11321/368;pol;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;text/plain;application/vnd.oasis.opendocument.text;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/vnd.oasis.opendocument.text;downloadable_files_count: 10;Wroc\u0142aw University of Science and Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cf4ae366-9d8d-52bc-a061-9379aa93851f",
-    "notes": [
-        "Korpus testowy przygotowany na warsztaty CLARIN-PL w IPI PAN."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/368"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        }
-    ],
-    "title": [
-        "Warsztaty CLARIN-PL w IPI PAN"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cf63d3cb-df74-5fe2-9131-2331e4a1981a.json b/oaitestdata/clarin-oai_dc/SET_1/json/cf63d3cb-df74-5fe2-9131-2331e4a1981a.json
deleted file mode 100644
index 3bd41f07..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cf63d3cb-df74-5fe2-9131-2331e4a1981a.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-8040",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-8040"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D35-3",
-    "PublicationTimestamp": "1744-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1744"
-    ],
-    "RelatedIdentifier": [
-        "http://www.pbc.rzeszow.pl/Content/8040",
-        "oai:www.pbc.rzeszow.pl:publication:8687"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "author": [
-        "Tar\u0142o, Adam (1713-1744)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-8040;2019-03-01T17:34:41Z;Manifest Ja\u015bnie Wielmo\u017cnego Imci Pana Adama na Melsztynie y Czekarzowicach Tarla Wojewody Lubelskiego na widok \u015bwiatu polskiemu wydany;Tar\u0142o, Adam (1713-1744);Polska - 18 w.;Druk czcionk\u0105 gotyck\u0105;Manifest w dw\u00f3ch jednobrzmi\u0105cych wsp\u00f3\u0142oprawnych egzemplarzach;14.03.1744;starodruk;application/xml;clarind-uds:poldilemma-8040;hdl:11858/00-246C-0000-0023-8D35-3;Sygnatura orygina\u0142u: SD-984-985;pol;lat;http://www.pbc.rzeszow.pl/Content/8040;oai:www.pbc.rzeszow.pl:publication:8687;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cf63d3cb-df74-5fe2-9131-2331e4a1981a",
-    "notes": [
-        "Druk czcionk\u0105 gotyck\u0105",
-        "Manifest w dw\u00f3ch jednobrzmi\u0105cych wsp\u00f3\u0142oprawnych egzemplarzach"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-8040"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Polska - w."
-        }
-    ],
-    "title": [
-        "Manifest Ja\u015bnie Wielmo\u017cnego Imci Pana Adama na Melsztynie y Czekarzowicach Tarla Wojewody Lubelskiego na widok \u015bwiatu polskiemu wydany"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cf694d72-75ed-5723-8e2f-93ebedd3b839.json b/oaitestdata/clarin-oai_dc/SET_1/json/cf694d72-75ed-5723-8e2f-93ebedd3b839.json
deleted file mode 100644
index fe7a1577..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cf694d72-75ed-5723-8e2f-93ebedd3b839.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Institut f\u00fcr Deutsche Sprache"
-    ],
-    "Contributor": [
-        "Schneider, Roman"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-544",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-544"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-544",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut f\u00fcr Deutsche Sprache"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-544;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Bibliografie zur deutschen Grammatik (BDG);Schneider, Roman;Online Bibliography, bibliographic database;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-544;deu;downloadable_files_count: 0;Germany;Institut f\u00fcr Deutsche Sprache;http://www.ids-mannheim.de/bdg/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cf694d72-75ed-5723-8e2f-93ebedd3b839",
-    "notes": [
-        "Online Bibliography, bibliographic database"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-544"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Bibliografie zur deutschen Grammatik (BDG)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cf6b1c09-09a2-51cf-8a0b-02f3660225b6.json b/oaitestdata/clarin-oai_dc/SET_1/json/cf6b1c09-09a2-51cf-8a0b-02f3660225b6.json
deleted file mode 100644
index db59bf93..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cf6b1c09-09a2-51cf-8a0b-02f3660225b6.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "The National Library of Sweden"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/17",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/17"
-    ],
-    "PID": "http://hdl.handle.net/10794/17",
-    "PublicationTimestamp": "2015-04-23T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "The National Library of Sweden"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/17;2017-10-27T16:42:49Z;hdl_10794_1;hdl_10794_2;Aftonbladet 1830's (2017-10-16);Aftonbladet 1830-talet (2017-10-16);n/a, n/a;Swedish;News;A corpus with texts from Aftonbladet in the 1830's.;En korpus med texter fr\u00e5n Aftonbladet p\u00e5 1830-talet.;2015-04-23;corpus;http://hdl.handle.net/10794/17;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;The National Library of Sweden;https://spraakbanken.gu.se/swe/resurs/kubhist-aftonbladet-1830",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cf6b1c09-09a2-51cf-8a0b-02f3660225b6",
-    "notes": [
-        "A corpus with texts from Aftonbladet in the 1830's.",
-        "En korpus med texter fr\u00e5n Aftonbladet p\u00e5 1830-talet."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/17"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "News"
-        }
-    ],
-    "title": [
-        "Aftonbladet 1830's (2017-10-16)",
-        "Aftonbladet 1830-talet (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cf721842-a927-556c-9ada-e1cea8b800ae.json b/oaitestdata/clarin-oai_dc/SET_1/json/cf721842-a927-556c-9ada-e1cea8b800ae.json
deleted file mode 100644
index 40cc9d6a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cf721842-a927-556c-9ada-e1cea8b800ae.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "ZRC SAZU"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1124",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1124"
-    ],
-    "PID": "http://hdl.handle.net/11356/1124",
-    "PublicationTimestamp": "2018-01-27T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "ZRC SAZU"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Jakopin, Primo\u017e",
-        "Aha\u010di\u010d, Kozma"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1124;2018-01-27T12:15:54Z;hdl_11356_1023;hdl_11356_1024;Concordances of Primo\u017e Trubar's \"Ta evangeli sv. Matev\u017ea\" (1555);Jakopin, Primo\u017e;Aha\u010di\u010d, Kozma;16th century Slovenian language;historical language;concordances;The 23603 concordances represent a transcription of the book \"Ta evangeli sv. Matev\u017ea\" (1555)  by Primo\u017e Trubar.;2018-01-27;corpus;http://hdl.handle.net/11356/1124;slv;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;ZRC SAZU",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cf721842-a927-556c-9ada-e1cea8b800ae",
-    "notes": [
-        "The 23603 concordances represent a transcription of the book \"Ta evangeli sv. Matev\u017ea\" (1555)  by Primo\u017e Trubar."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1124"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "th century Slovenian language"
-        },
-        {
-            "name": "historical language"
-        },
-        {
-            "name": "concordances"
-        }
-    ],
-    "title": [
-        "Concordances of Primo\u017e Trubar's \"Ta evangeli sv. Matev\u017ea\" (1555)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cf9bda40-b34e-5920-b69f-714eb34daca0.json b/oaitestdata/clarin-oai_dc/SET_1/json/cf9bda40-b34e-5920-b69f-714eb34daca0.json
deleted file mode 100644
index a576b544..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cf9bda40-b34e-5920-b69f-714eb34daca0.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Dabrowska"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/102",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/102"
-    ],
-    "PID": "http://hdl.handle.net/11321/102",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Dabrowska"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Dabrowska, Dabrowska"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/102;2015-04-08T14:04:43Z;hdl_11321_3;hdl_11321_4;MWE Dabrowska, Noce i dnie, Tom 3;Dabrowska, Dabrowska;Dabrowska;2015-04-08;corpus;http://hdl.handle.net/11321/102;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain; charset=utf-8;downloadable_files_count: 1;Dabrowska",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cf9bda40-b34e-5920-b69f-714eb34daca0",
-    "notes": [
-        "Dabrowska"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/102"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Dabrowska, Noce i dnie, Tom 3"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cfad663e-3b95-583e-b023-0da85eca663e.json b/oaitestdata/clarin-oai_dc/SET_1/json/cfad663e-3b95-583e-b023-0da85eca663e.json
deleted file mode 100644
index 9be4d59d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cfad663e-3b95-583e-b023-0da85eca663e.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=5b18d7363afb11e2a2aa782bcb0741352ac937eb38404449aa899e013dc55bd3",
-    "MetadataAccess": [
-        "5b18d7363afb11e2a2aa782bcb0741352ac937eb38404449aa899e013dc55bd3"
-    ],
-    "PublicationTimestamp": "2012-11-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "fulltext": "5b18d7363afb11e2a2aa782bcb0741352ac937eb38404449aa899e013dc55bd3;2018-11-15T16:39:55Z;toolService;toolService:service;MLSS Tokeniser Web Service;The web service is a tool which takes text as input and returns a list of tokens. The tokens can be orthographical words, numerals and punctuation marks. The tokeniser was designed to work on Maltese texts. The download for this resource only contains the narrative description in a Word file.\n\nThe WSDL link is http://metanet4u.research.um.edu.mt/services/MtTokeniser?wsdl.\n\nThe service has one method which can be invoked:\n\u00e2\u0080\u00a2\tString tokenise(String text, Boolean tokenTags, String separator)\n\nThe method takes has three parameters:\n\u00e2\u0080\u00a2\ttext\nThis is the text that will be tokenised\n\n\u00e2\u0080\u00a2\ttokenTags\nThis is a boolean variable. If tokenTags is true than the output tokens will be wrapped in tags\n(ex: <token> tagged_text </token>). If false, the token will have no tags.\n\n\u00e2\u0080\u00a2\tseparator\nThis is a string which will be used to separate one token from another in the output string.\n\nInput data format: text string with sentences\n\nOutput data format: a text string with the tagged sentences in the format <sentence> sentence_text </sentence> \n\nThe web service does not need any external tool.\n;2012-11-30",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cfad663e-3b95-583e-b023-0da85eca663e",
-    "notes": [
-        "The web service is a tool which takes text as input and returns a list of tokens. The tokens can be orthographical words, numerals and punctuation marks. The tokeniser was designed to work on Maltese texts. The download for this resource only contains the narrative description in a Word file.\n\nThe WSDL link is http://metanet4u.research.um.edu.mt/services/MtTokeniser?wsdl.\n\nThe service has one method which can be invoked:\n\u00e2\u0080\u00a2\tString tokenise(String text, Boolean tokenTags, String separator)\n\nThe method takes has three parameters:\n\u00e2\u0080\u00a2\ttext\nThis is the text that will be tokenised\n\n\u00e2\u0080\u00a2\ttokenTags\nThis is a boolean variable. If tokenTags is true than the output tokens will be wrapped in tags\n(ex: <token> tagged_text </token>). If false, the token will have no tags.\n\n\u00e2\u0080\u00a2\tseparator\nThis is a string which will be used to separate one token from another in the output string.\n\nInput data format: text string with sentences\n\nOutput data format: a text string with the tagged sentences in the format <sentence> sentence_text </sentence> \n\nThe web service does not need any external tool.\n"
-    ],
-    "oai_identifier": [
-        "5b18d7363afb11e2a2aa782bcb0741352ac937eb38404449aa899e013dc55bd3"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:service"
-    ],
-    "state": "active",
-    "title": [
-        "MLSS Tokeniser Web Service"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cfcdcb49-1dab-5c14-b153-510f945168c2.json b/oaitestdata/clarin-oai_dc/SET_1/json/cfcdcb49-1dab-5c14-b153-510f945168c2.json
deleted file mode 100644
index 8fd881bf..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cfcdcb49-1dab-5c14-b153-510f945168c2.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3490",
-    "MetadataAccess": [
-        "oai:ota:oucs:3490"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Cornaro, Luigi, 1475-1566."
-    ],
-    "fulltext": "oai:ota:oucs:3490;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3490.xml;Sure methods of attaining a long and healthful life: Written originally in Italian, by Lewis Cornaro, ... Translated into English by W. Jones A.B.;Discorsi della vita sobria. English;Cornaro, Luigi, 1475-1566.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cfcdcb49-1dab-5c14-b153-510f945168c2",
-    "oai_identifier": [
-        "oai:ota:oucs:3490"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Sure methods of attaining a long and healthful life: Written originally in Italian, by Lewis Cornaro, ... Translated into English by W. Jones A.B.",
-        "Discorsi della vita sobria. English"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3490.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/cff342ef-d947-5849-a844-53fa5f1d5293.json b/oaitestdata/clarin-oai_dc/SET_1/json/cff342ef-d947-5849-a844-53fa5f1d5293.json
deleted file mode 100644
index 26702781..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/cff342ef-d947-5849-a844-53fa5f1d5293.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Royster, Paul"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 0 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1810",
-    "MetadataAccess": [
-        "oai:ota:oucs:1810"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "James, Henry, 1843-1916"
-    ],
-    "fulltext": "oai:ota:oucs:1810;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1810.xml;Watch and ward / James, Henry;James, Henry, 1843-1916;text_and_corpus_linguistics;American literature -- 19th century;Oxford Text Archive, University of Oxford;Royster, Paul;text/sgml;(1 file : ca. 0 KB);Text;Novels;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cff342ef-d947-5849-a844-53fa5f1d5293",
-    "oai_identifier": [
-        "oai:ota:oucs:1810"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "American literature -- th century"
-        }
-    ],
-    "title": [
-        "Watch and ward / James, Henry"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1810.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d003d8ce-4ee8-53c7-8cc5-69de2ed77050.json b/oaitestdata/clarin-oai_dc/SET_1/json/d003d8ce-4ee8-53c7-8cc5-69de2ed77050.json
deleted file mode 100644
index a8ffebc5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d003d8ce-4ee8-53c7-8cc5-69de2ed77050.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/254",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/254"
-    ],
-    "PID": "http://hdl.handle.net/11321/254",
-    "PublicationTimestamp": "2016-04-30T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "Patejuk, Agnieszka"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/254;2016-05-05T12:20:51Z;hdl_11321_3;hdl_11321_4;POLFIE-OT: an LFG grammar of Polish with OT marks;Patejuk, Agnieszka;syntax;LFG;Polish;grammar;POLFIE-OT is a version of POLFIE, an LFG grammar of Polish implemented in the XLE system (Xerox Linguistic Environment), enriched with OT (Optimality Theory) constraints for the purpose of automatic disambiguation of resulting parses \u2013 according to defined criteria, certain parses are considered optimal, while the remaining ones are considered unoptimal (it is possible, however, to view the unoptimal parses).\r\n\r\nPOLFIE has been developed at the Institute of Computer Science, Polish Academy of Sciences (IPI PAN) within two projects: NEKST and CLARIN-PL. It provides a two-layer representation: constituent structure (c-structure, tree representation) and functional structure (f-structure, AVM representation). It is based on two previous implemented grammars of Polish: its c-structure is based on GFJP2, a DCG grammar used by the parser \u015awigra, while its f-structure is inspired by FOJP, an HPSG grammar of Polish. Lexical entries used by the grammar are created with the help of two state-of-the-art resources for Polish: Morfeusz2, a morphological analyser, and Walenty, a valence dictionary.\r\n\r\nPOLFIE-OT is available via XLE-Web (a part of INESS; it does not require a local installation of XLE):\r\n\u2022 go to http://iness.mozart.ipipan.waw.pl/iness/xle-web or http://clarino.uib.no/iness/xle-web\r\n\u2022 choose \"POLFIE-OT\" grammar from the \"Grammar\" menu\r\n\u2022 write a sentence in the relevant field\r\n\u2022 click the \"Parse sentence\" button \u2013 only optimal solutions will be presented\r\n\u2022 however, if you want to see unoptimal solutions, check the \"Show unoptimal\" checkbox and click \"Parse sentence\" button;2016-04-30;languageDescription;http://hdl.handle.net/11321/254;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 1;Institute of Computer Science, Polish Academy of Sciences;http://zil.ipipan.waw.pl/LFG",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d003d8ce-4ee8-53c7-8cc5-69de2ed77050",
-    "notes": [
-        "POLFIE-OT is a version of POLFIE, an LFG grammar of Polish implemented in the XLE system (Xerox Linguistic Environment), enriched with OT (Optimality Theory) constraints for the purpose of automatic disambiguation of resulting parses \u2013 according to defined criteria, certain parses are considered optimal, while the remaining ones are considered unoptimal (it is possible, however, to view the unoptimal parses).\r\n\r\nPOLFIE has been developed at the Institute of Computer Science, Polish Academy of Sciences (IPI PAN) within two projects: NEKST and CLARIN-PL. It provides a two-layer representation: constituent structure (c-structure, tree representation) and functional structure (f-structure, AVM representation). It is based on two previous implemented grammars of Polish: its c-structure is based on GFJP2, a DCG grammar used by the parser \u015awigra, while its f-structure is inspired by FOJP, an HPSG grammar of Polish. Lexical entries used by the grammar are created with the help of two state-of-the-art resources for Polish: Morfeusz2, a morphological analyser, and Walenty, a valence dictionary.\r\n\r\nPOLFIE-OT is available via XLE-Web (a part of INESS; it does not require a local installation of XLE):\r\n\u2022 go to http://iness.mozart.ipipan.waw.pl/iness/xle-web or http://clarino.uib.no/iness/xle-web\r\n\u2022 choose \"POLFIE-OT\" grammar from the \"Grammar\" menu\r\n\u2022 write a sentence in the relevant field\r\n\u2022 click the \"Parse sentence\" button \u2013 only optimal solutions will be presented\r\n\u2022 however, if you want to see unoptimal solutions, check the \"Show unoptimal\" checkbox and click \"Parse sentence\" button"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/254"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "syntax"
-        },
-        {
-            "name": "LFG"
-        },
-        {
-            "name": "Polish"
-        },
-        {
-            "name": "grammar"
-        }
-    ],
-    "title": [
-        "POLFIE-OT: an LFG grammar of Polish with OT marks"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d0053b6b-212b-5c48-9723-87e678d6dced.json b/oaitestdata/clarin-oai_dc/SET_1/json/d0053b6b-212b-5c48-9723-87e678d6dced.json
deleted file mode 100644
index ea15c719..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d0053b6b-212b-5c48-9723-87e678d6dced.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contributor": [
-        "Quan Nguyen",
-        "Michael Kipp",
-        "Gabriel Manolache"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:anvil",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:anvil"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0005-BD0D-2",
-    "RelatedIdentifier": [
-        "Kipp, M. (to appear) Multimedia Annotation, Querying and Analysis in ANVIL. In: M. Maybury (ed.) Multimedia Information Extraction, Chapter 19, IEEE Computer Society Press.",
-        "Kipp, M. (to appear) ANVIL: A Universal Video Research Tool. In: J. Durand, U. Gut, G. Kristofferson (Hrsg.) Handbook of Corpus Phonology, Oxford University Press.",
-        "Heloir, A., Neff, M. and Kipp, M. (2010) Exploiting Motion Capture for Virtual Human Animation: Data Collection and Annotation Visualization. In: Proc. of the LREC Workshop on \"Multimodal Corpora: Advances in Capturing, Coding and Analyzing Multimodality\", ELDA.",
-        "Kipp, M. (2008) Spatiotemporal Coding in ANVIL. Proceedings of the 6th international conference on Language Resources and Evaluation (LREC-08).",
-        "Kipp, M. (2004), Gesture Generation by Imitation - From Human Behavior to Computer Character Animation, Boca Raton, Florida: Dissertation.com. (My published PhD thesis.)",
-        "Kipp, M. (2001) Anvil - A Generic Annotation Tool for Multimodal Dialogue. Proceedings of the 7th European Conference on Speech Communication and Technology (Eurospeech), pp. 1367-1370."
-    ],
-    "ResourceType": [
-        "Software"
-    ],
-    "author": [
-        "Michael Kipp\nHochschule Augsburg\nAn der Hochschule 1\n86161 Augsburg\nmichael.kipp@hs-augsburg.de"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:anvil;2014-06-03T12:53:03Z;Anvil The video annotation research tool;Michael Kipp\nHochschule Augsburg\nAn der Hochschule 1\n86161 Augsburg\nmichael.kipp@hs-augsburg.de;gesture research;video annotation;time-alignment;multimodal corpora;phonology;ANVIL is a free video annotation tool. It offers multi-layered annotation based on a user-defined coding scheme. During coding the user can see color-coded elements on multiple tracks in time-alignment. Some special features are cross-level links, non-temporal objects, timepoint tracks, coding agreement analysis and a project tool for managing whole corpora of annotation files.;ANVIL ist ein frei erh\u00e4ltiches Annotationstool. Es bietet die M\u00f6glichkeit zur mehrdimensionalen Annotation basierend auf einem benutzerdefinierten Kodierungsschema. W\u00e4hrend des Kodierens sieht der Benutzer farbkodierte Elemente zeitlich alineiert auf mehreren Spuren. Spezielle Features des Werkzeugs sind ebenen\u00fcbergreifende Links, nicht-temporale Objekte, Zeitspuren, Analyse der \u00dcbereinstimmung der Kodierung und ein Projektwerkzeug f\u00fcr die Verwaltung von Annotationsdateien ganzer Korpora.;Michael Kipp;Quan Nguyen;Gabriel Manolache;Software;clarind-uds:anvil;hdl:11858/00-246C-0000-0005-BD0D-2;Kipp, M. (to appear) Multimedia Annotation, Querying and Analysis in ANVIL. In: M. Maybury (ed.) Multimedia Information Extraction, Chapter 19, IEEE Computer Society Press.;Kipp, M. (to appear) ANVIL: A Universal Video Research Tool. In: J. Durand, U. Gut, G. Kristofferson (Hrsg.) Handbook of Corpus Phonology, Oxford University Press.;Heloir, A., Neff, M. and Kipp, M. (2010) Exploiting Motion Capture for Virtual Human Animation: Data Collection and Annotation Visualization. In: Proc. of the LREC Workshop on \"Multimodal Corpora: Advances in Capturing, Coding and Analyzing Multimodality\", ELDA.;Kipp, M. (2008) Spatiotemporal Coding in ANVIL. Proceedings of the 6th international conference on Language Resources and Evaluation (LREC-08).;Kipp, M. (2004), Gesture Generation by Imitation - From Human Behavior to Computer Character Animation, Boca Raton, Florida: Dissertation.com. (My published PhD thesis.);Kipp, M. (2001) Anvil - A Generic Annotation Tool for Multimodal Dialogue. Proceedings of the 7th European Conference on Speech Communication and Technology (Eurospeech), pp. 1367-1370.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d0053b6b-212b-5c48-9723-87e678d6dced",
-    "notes": [
-        "ANVIL is a free video annotation tool. It offers multi-layered annotation based on a user-defined coding scheme. During coding the user can see color-coded elements on multiple tracks in time-alignment. Some special features are cross-level links, non-temporal objects, timepoint tracks, coding agreement analysis and a project tool for managing whole corpora of annotation files.",
-        "ANVIL ist ein frei erh\u00e4ltiches Annotationstool. Es bietet die M\u00f6glichkeit zur mehrdimensionalen Annotation basierend auf einem benutzerdefinierten Kodierungsschema. W\u00e4hrend des Kodierens sieht der Benutzer farbkodierte Elemente zeitlich alineiert auf mehreren Spuren. Spezielle Features des Werkzeugs sind ebenen\u00fcbergreifende Links, nicht-temporale Objekte, Zeitspuren, Analyse der \u00dcbereinstimmung der Kodierung und ein Projektwerkzeug f\u00fcr die Verwaltung von Annotationsdateien ganzer Korpora."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:anvil"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "gesture research"
-        },
-        {
-            "name": "video annotation"
-        },
-        {
-            "name": "time-alignment"
-        },
-        {
-            "name": "multimodal corpora"
-        },
-        {
-            "name": "phonology"
-        }
-    ],
-    "title": [
-        "Anvil The video annotation research tool"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d005b90a-5a4f-54a5-afe1-ec96daeca645.json b/oaitestdata/clarin-oai_dc/SET_1/json/d005b90a-5a4f-54a5-afe1-ec96daeca645.json
deleted file mode 100644
index 768aafd4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d005b90a-5a4f-54a5-afe1-ec96daeca645.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4298",
-    "MetadataAccess": [
-        "oai:ota:oucs:4298"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Defoe, Daniel, 1661?-1731."
-    ],
-    "fulltext": "oai:ota:oucs:4298;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4298.xml;The fifteen comforts of a Scotch-man. Written by Daniel D'Foe in Scotland;Defoe, Daniel, 1661?-1731.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d005b90a-5a4f-54a5-afe1-ec96daeca645",
-    "oai_identifier": [
-        "oai:ota:oucs:4298"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The fifteen comforts of a Scotch-man. Written by Daniel D'Foe in Scotland"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4298.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d01d6057-f247-51e1-bf51-56c9927aab72.json b/oaitestdata/clarin-oai_dc/SET_1/json/d01d6057-f247-51e1-bf51-56c9927aab72.json
deleted file mode 100644
index cdc6b8f7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d01d6057-f247-51e1-bf51-56c9927aab72.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2771",
-    "MetadataAccess": [
-        "oai:ota:oucs:2771"
-    ],
-    "PublicationTimestamp": "1768-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1768"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2771;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2771.xml;An answer of the Right Honourable William Pultney to the Right Honourable Robert Walpole;Swift, Jonathan, 1667-1745;1768;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d01d6057-f247-51e1-bf51-56c9927aab72",
-    "oai_identifier": [
-        "oai:ota:oucs:2771"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An answer of the Right Honourable William Pultney to the Right Honourable Robert Walpole"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2771.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d03e5a4a-5563-594b-b917-dcc9e52a8be1.json b/oaitestdata/clarin-oai_dc/SET_1/json/d03e5a4a-5563-594b-b917-dcc9e52a8be1.json
deleted file mode 100644
index 22d6f758..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d03e5a4a-5563-594b-b917-dcc9e52a8be1.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "Armenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-928",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-928"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-928",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-928;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Old Armenian;ca. 1.000.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-928;hye;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#aarmen",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d03e5a4a-5563-594b-b917-dcc9e52a8be1",
-    "notes": [
-        "ca. 1.000.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-928"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Old Armenian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d04fcc77-1dd3-554b-ae33-33dfb29177cb.json b/oaitestdata/clarin-oai_dc/SET_1/json/d04fcc77-1dd3-554b-ae33-33dfb29177cb.json
deleted file mode 100644
index a174b486..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d04fcc77-1dd3-554b-ae33-33dfb29177cb.json
+++ /dev/null
@@ -1,217 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Afrikaans",
-        "Arabic",
-        "Breton",
-        "Bulgarian",
-        "Catalan",
-        "Czech",
-        "Church Slavic",
-        "Danish",
-        "German",
-        "Modern Greek (1453-)",
-        "English",
-        "Estonian",
-        "Basque",
-        "Faroese",
-        "Persian",
-        "Finnish",
-        "French",
-        "Old French (842-ca. 1400)",
-        "Irish",
-        "Galician",
-        "Gothic",
-        "Ancient Greek (to 1453)",
-        "Hebrew",
-        "Hindi",
-        "Croatian",
-        "Upper Sorbian",
-        "Hungarian",
-        "Armenian",
-        "Indonesian",
-        "Italian",
-        "Japanese",
-        "Kazakh",
-        "Korean",
-        "Latin",
-        "Latvian",
-        "Dutch",
-        "Norwegian",
-        "Polish",
-        "Portuguese",
-        "Romanian",
-        "Russian",
-        "Slovak",
-        "Slovenian",
-        "Northern Sami",
-        "Spanish",
-        "Serbian",
-        "Swedish",
-        "Thai",
-        "Turkish",
-        "Uighur",
-        "Ukrainian",
-        "Urdu",
-        "Vietnamese",
-        "Chinese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2885",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2885"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2885",
-    "PublicationTimestamp": "2018-10-28T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://universaldependencies.org/conll18/proceedings/pdf/K18-2001.pdf"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Licence Universal Dependencies v2.2",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-2.2",
-        "PUB"
-    ],
-    "author": [
-        "Manning, Christopher",
-        "\u00d6nder, Berkay Furkan",
-        "Rappoport, Ari",
-        "Mesnard, Olivier",
-        "Verspoor, Karin",
-        "Naseem, Tahira",
-        "Sagot, Beno\u00eet",
-        "Che, Wanxiang",
-        "He, Shexia",
-        "Qiu, Xipeng",
-        "Potthast, Martin",
-        "Castelli, Vittorio",
-        "Seddah, Djam\u00e9",
-        "Wu, Yuanbin",
-        "Yuret, Deniz",
-        "G\u00fcmeli, Can",
-        "Gungor, Tunga",
-        "Ji, Tao",
-        "Jawahar, Ganesh",
-        "Abend, Omri",
-        "Martin, Louis",
-        "Wang, Yuxuan",
-        "Kanerva, Jenna",
-        "Khachatrian, Hrant",
-        "Lim, KyungTae",
-        "Fethi, Amal",
-        "de Lhoneux, Miryam",
-        "Wr\u00f3blewska, Alina",
-        "Lan, Man",
-        "Salakoski, Tapio",
-        "Dozat, Timothy",
-        "Tong, Jia-Jun",
-        "Zeman, Daniel",
-        "Nivre, Joakim",
-        "\u00d6zg\u00fcr, Arzucan",
-        "Miekka, Niko",
-        "Hershcovich, Daniel",
-        "\u00d6zt\u00fcrk, Balk\u0131z",
-        "Hu, Zhifeng",
-        "Ginter, Filip",
-        "Burtica, Ruxandra",
-        "Zhang, Yuhao",
-        "Bohnet, Bernd",
-        "Wu, Yingting",
-        "Wan, Hui",
-        "Bhat, Riyaz Ahmad",
-        "Arakelyan, Gor",
-        "Straka, Milan",
-        "Qi, Peng",
-        "Liu, Yufang",
-        "Tsarfaty, Reut",
-        "Lee, Changki",
-        "Bhat, Irshad",
-        "Villemonte de la Clergerie, Eric",
-        "Lin, Mengxiao",
-        "Mare\u010dek, David",
-        "Smith, Aaron",
-        "Leino, Akseli",
-        "More, Amir",
-        "Poibeau, Thierry",
-        "Zhao, Hai",
-        "Li, Zuchao",
-        "Wang, Yijun",
-        "Stymne, Sara",
-        "Ballesteros, Miguel",
-        "Dayan\u0131k, Erenay",
-        "Duthoo, Elie",
-        "Liu, Ting",
-        "Rybak, Piotr",
-        "Liu, Yijia",
-        "Seker, Amit",
-        "Chen, Danlu",
-        "Dumitrescu, Stefan Daniel",
-        "Muller, Benjamin",
-        "Rosa, Rudolf",
-        "Park, Cheoneum",
-        "Shao, Yan",
-        "Bangalore, Srinivas",
-        "Lee, Young-Suk",
-        "Boro\u0219, Tiberiu",
-        "Zhang, Zhuosheng",
-        "Zheng, Bo",
-        "K\u0131rnap, \u00d6mer",
-        "\u00d6zate\u015f, \u015eaziye Bet\u00fcl",
-        "Hambardzumyan, Karen",
-        "Nguyen, Dat Quoc"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2885;2018-11-28T14:09:57Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;CoNLL 2018 Shared Task System Outputs;Zeman, Daniel;Potthast, Martin;Duthoo, Elie;Mesnard, Olivier;Rybak, Piotr;Wr\u00f3blewska, Alina;Che, Wanxiang;Liu, Yijia;Wang, Yuxuan;Zheng, Bo;Liu, Ting;Li, Zuchao;He, Shexia;Zhang, Zhuosheng;Zhao, Hai;Wu, Yingting;Tong, Jia-Jun;Nguyen, Dat Quoc;Verspoor, Karin;Wan, Hui;Naseem, Tahira;Lee, Young-Suk;Castelli, Vittorio;Ballesteros, Miguel;Hershcovich, Daniel;Abend, Omri;Rappoport, Ari;Smith, Aaron;Bohnet, Bernd;de Lhoneux, Miryam;Nivre, Joakim;Shao, Yan;Stymne, Sara;K\u0131rnap, \u00d6mer;Dayan\u0131k, Erenay;Yuret, Deniz;Kanerva, Jenna;Ginter, Filip;Miekka, Niko;Leino, Akseli;Salakoski, Tapio;Lim, KyungTae;Park, Cheoneum;Lee, Changki;Poibeau, Thierry;Bhat, Riyaz Ahmad;Bhat, Irshad;Bangalore, Srinivas;Qi, Peng;Dozat, Timothy;Zhang, Yuhao;Manning, Christopher;Boro\u0219, Tiberiu;Dumitrescu, Stefan Daniel;Burtica, Ruxandra;Arakelyan, Gor;Hambardzumyan, Karen;Khachatrian, Hrant;Rosa, Rudolf;Mare\u010dek, David;Straka, Milan;Seker, Amit;More, Amir;Tsarfaty, Reut;\u00d6nder, Berkay Furkan;G\u00fcmeli, Can;Jawahar, Ganesh;Muller, Benjamin;Fethi, Amal;Martin, Louis;Villemonte de la Clergerie, Eric;Sagot, Beno\u00eet;Seddah, Djam\u00e9;\u00d6zate\u015f, \u015eaziye Bet\u00fcl;\u00d6zg\u00fcr, Arzucan;Gungor, Tunga;\u00d6zt\u00fcrk, Balk\u0131z;Ji, Tao;Liu, Yufang;Wang, Yijun;Wu, Yuanbin;Lan, Man;Chen, Danlu;Lin, Mengxiao;Hu, Zhifeng;Qiu, Xipeng;parsed data;conllu;universal dependencies;Test data parsed by systems submitted to the CoNLL 2018 UD parsing shared task.;2018-10-28;corpus;http://hdl.handle.net/11234/1-2885;afr;ara;bre;bul;bxr;cat;ces;chu;dan;deu;ell;eng;est;eus;fao;fas;fin;fra;fro;gle;glg;got;grc;heb;hin;hrv;hsb;hun;hye;ind;ita;jpn;kaz;kmr;kor;lat;lav;nld;nor;pcm;pol;por;ron;rus;slk;slv;sme;spa;srp;swe;tha;tur;uig;ukr;urd;vie;zho;http://universaldependencies.org/conll18/proceedings/pdf/K18-2001.pdf;Licence Universal Dependencies v2.2;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-2.2;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://universaldependencies.org/conll18/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d04fcc77-1dd3-554b-ae33-33dfb29177cb",
-    "notes": [
-        "Test data parsed by systems submitted to the CoNLL 2018 UD parsing shared task."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2885"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parsed data"
-        },
-        {
-            "name": "conllu"
-        },
-        {
-            "name": "universal dependencies"
-        }
-    ],
-    "title": [
-        "CoNLL 2018 Shared Task System Outputs"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d0794092-2579-5edf-96ad-ea7863fb0714.json b/oaitestdata/clarin-oai_dc/SET_1/json/d0794092-2579-5edf-96ad-ea7863fb0714.json
deleted file mode 100644
index f19163bb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d0794092-2579-5edf-96ad-ea7863fb0714.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "The Danish Language Council",
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml",
-        "text/plain; charset=utf-8",
-        "text/plain",
-        "application/zip",
-        "downloadable_files_count: 10",
-        "application/pdf"
-    ],
-    "Language": [
-        "Danish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repository.clarin.dk:20.500.12115/15",
-    "MetadataAccess": [
-        "oai:repository.clarin.dk:20.500.12115/15"
-    ],
-    "PID": "http://hdl.handle.net/20.500.12115/15",
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "The Danish Language Council",
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN-ACA-NC",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NC=1&NORED=1",
-        "ACA"
-    ],
-    "author": [
-        "Hansen, Dorte Haltrup",
-        "Braasch, Anna",
-        "Olsen, Sussi",
-        "Jakob, Halskov"
-    ],
-    "fulltext": "oai:repository.clarin.dk:20.500.12115/15;2018-06-28T13:25:36Z;hdl_20.500.12115_1;hdl_20.500.12115_3;DK-CLARIN LSP Corpus - IT domain;Olsen, Sussi;Braasch, Anna;Jakob, Halskov;Hansen, Dorte Haltrup;IT;Information Technology;Texts in the IT Domain come from Libris, Open Office, Aktuel Naturvidenskab and have been collected in the DK-CLARIN project, WP2.2, 2008 - 2011. \r\nThe corpus consists of 1,101,059 words in 66 files. \r\nCommunicative setting/Number of files: expert->advanced (5) expert->basic (61).\r\nAll texts are in XML TEIP5 format (TEIP5DKCLARIN-format), with tokenisation, sentence and paragraph segmentation, pos-tagging, lemmatisation and termhood annotation placed in separate text external spangroups. \r\n\"DK-CLARIN LSP Corpus - IT domain\" is a part of the Danish DK-CLARIN LSP corpus consisting of seven sub-corpora from following subject domains: Agriculture, Construction, Economics, Environment, Health, IT and Nanotechnology.;2011;corpus;http://hdl.handle.net/20.500.12115/15;dan;CLARIN-ACA-NC;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NC=1&NORED=1;ACA;text/plain; charset=utf-8;application/zip;application/zip;application/zip;text/plain;application/pdf;application/pdf;application/pdf;text/xml;text/xml;text/xml;downloadable_files_count: 10;Centre for Language Technology, NorS, University of Copenhagen;The Danish Language Council",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d0794092-2579-5edf-96ad-ea7863fb0714",
-    "notes": [
-        "Texts in the IT Domain come from Libris, Open Office, Aktuel Naturvidenskab and have been collected in the DK-CLARIN project, WP2.2, 2008 - 2011. \r\nThe corpus consists of 1,101,059 words in 66 files. \r\nCommunicative setting/Number of files: expert->advanced (5) expert->basic (61).\r\nAll texts are in XML TEIP5 format (TEIP5DKCLARIN-format), with tokenisation, sentence and paragraph segmentation, pos-tagging, lemmatisation and termhood annotation placed in separate text external spangroups. \r\n\"DK-CLARIN LSP Corpus - IT domain\" is a part of the Danish DK-CLARIN LSP corpus consisting of seven sub-corpora from following subject domains: Agriculture, Construction, Economics, Environment, Health, IT and Nanotechnology."
-    ],
-    "oai_identifier": [
-        "oai:repository.clarin.dk:20.500.12115/15"
-    ],
-    "oai_set": [
-        "hdl_20.500.12115_1",
-        "hdl_20.500.12115_3"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Information Technology"
-        }
-    ],
-    "title": [
-        "DK-CLARIN LSP Corpus - IT domain"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d0820389-fa82-5004-8e0a-2b24db414bb2.json b/oaitestdata/clarin-oai_dc/SET_1/json/d0820389-fa82-5004-8e0a-2b24db414bb2.json
deleted file mode 100644
index 425fb4c0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d0820389-fa82-5004-8e0a-2b24db414bb2.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Europ\u00e4ische Akademie Bozen; Freie Universit\u00e4t Bozen; Universit\u00e4t Innsbruck"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1127",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1127"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1127",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Europ\u00e4ische Akademie Bozen; Freie Universit\u00e4t Bozen; Universit\u00e4t Innsbruck"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Austria||Italy"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1127;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Korpus S\u00fcdtirol;Germanistik;Collection of South Tyrolean German texts; korpuslinguistische Erschlie\u00dfung von S\u00fcdtiroler deutschen Texten;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1127;deu;downloadable_files_count: 0;Austria||Italy;Europ\u00e4ische Akademie Bozen; Freie Universit\u00e4t Bozen; Universit\u00e4t Innsbruck;http://www.korpus-suedtirol.it/index_DE",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d0820389-fa82-5004-8e0a-2b24db414bb2",
-    "notes": [
-        "Collection of South Tyrolean German texts; korpuslinguistische Erschlie\u00dfung von S\u00fcdtiroler deutschen Texten"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1127"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Korpus S\u00fcdtirol"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d08dac8a-ce26-5585-bfbd-a3f5d42def05.json b/oaitestdata/clarin-oai_dc/SET_1/json/d08dac8a-ce26-5585-bfbd-a3f5d42def05.json
deleted file mode 100644
index 60f6531a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d08dac8a-ce26-5585-bfbd-a3f5d42def05.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Uczelnia"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/495",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/495"
-    ],
-    "PID": "http://hdl.handle.net/11321/495",
-    "PublicationTimestamp": "2018-06-19T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Uczelnia"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Super Cool License",
-        "http://www.google.com",
-        "ACA"
-    ],
-    "author": [
-        "Augustyn, Kamila"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/495;2018-06-19T11:21:11Z;hdl_11321_3;hdl_11321_4;Korpus pr\u00f3bny;Augustyn, Kamila;slowa kluczowe;Co\u015b takiego;2018-06-19;corpus;http://hdl.handle.net/11321/495;pol;Super Cool License;http://www.google.com;ACA;text/plain; charset=utf-8;application/vnd.openxmlformats-officedocument.wordprocessingml.document;downloadable_files_count: 1;Uczelnia",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d08dac8a-ce26-5585-bfbd-a3f5d42def05",
-    "notes": [
-        "Co\u015b takiego"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/495"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "slowa kluczowe"
-        }
-    ],
-    "title": [
-        "Korpus pr\u00f3bny"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d09aa3ea-ed3e-50e9-9db1-da4496b8ce56.json b/oaitestdata/clarin-oai_dc/SET_1/json/d09aa3ea-ed3e-50e9-9db1-da4496b8ce56.json
deleted file mode 100644
index 8c01b61d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d09aa3ea-ed3e-50e9-9db1-da4496b8ce56.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4497",
-    "MetadataAccess": [
-        "oai:ota:oucs:4497"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Francklin, Thomas, 1721-1784."
-    ],
-    "fulltext": "oai:ota:oucs:4497;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4497.xml;A sermon preached at the chapel in Great Queen-Street, Lincoln's-Inn-Fields, on Sunday, March 20, 1774: for the benefit of unfortunate persons confined for small debts. ... By Thomas Francklin, ...;Francklin, Thomas, 1721-1784.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d09aa3ea-ed3e-50e9-9db1-da4496b8ce56",
-    "oai_identifier": [
-        "oai:ota:oucs:4497"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A sermon preached at the chapel in Great Queen-Street, Lincoln's-Inn-Fields, on Sunday, March 20, 1774: for the benefit of unfortunate persons confined for small debts. ... By Thomas Francklin, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4497.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d0adfa7e-4760-51df-96fa-f43cc974e1e8.json b/oaitestdata/clarin-oai_dc/SET_1/json/d0adfa7e-4760-51df-96fa-f43cc974e1e8.json
deleted file mode 100644
index d3793e1a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d0adfa7e-4760-51df-96fa-f43cc974e1e8.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Arts, Institute of the Czech National Corpus"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1848",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1848"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1848",
-    "PublicationTimestamp": "2016-12-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Arts, Institute of the Czech National Corpus"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "License Agreement for Czech National Corpus Data",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/license-cnc-data",
-        "ACA"
-    ],
-    "author": [
-        "Bene\u0161ov\u00e1, Lucie",
-        "Waclawi\u010dov\u00e1, Martina",
-        "K\u0159en, Michal"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1848;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;ORAL2013: balanced corpus of informal spoken Czech (transcriptions & audio);Bene\u0161ov\u00e1, Lucie;K\u0159en, Michal;Waclawi\u010dov\u00e1, Martina;balanced corpus;spoken language;speech corpus;ORAL2013 is designed as a representation of authentic spoken Czech used in informal situations (private environment, spontaneity, unpreparedness etc.) in the area of the whole Czech Republic. The corpus comprises 835 recordings from 2008\u20132011 that contain 2 785 189 words (i.e. 3 285 508 tokens including punctuation) uttered by 2 544 speakers, out of which 1 297 speakers are unique. ORAL2013 is balanced in the main sociolinguistic categories of the speakers (gender, age group, education, region of childhood residence).\r\n\r\nThe (anonymized) transcriptions are provided in the Transcriber XML format, audio (with corresponding anonymization beeps) is in uncompressed 16-bit PCM WAV, mono, 16 kHz format.\r\n\r\nAnother format option of the transcriptions is also available under less restrictive CC BY-NC-SA license at http://hdl.handle.net/11234/1-1847;2016-12-01;corpus;http://hdl.handle.net/11234/1-1848;ces;License Agreement for Czech National Corpus Data;https://lindat.mff.cuni.cz/repository/xmlui/page/license-cnc-data;ACA;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Arts, Institute of the Czech National Corpus;http://wiki.korpus.cz/doku.php/cnk:oral2013",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d0adfa7e-4760-51df-96fa-f43cc974e1e8",
-    "notes": [
-        "ORAL2013 is designed as a representation of authentic spoken Czech used in informal situations (private environment, spontaneity, unpreparedness etc.) in the area of the whole Czech Republic. The corpus comprises 835 recordings from 2008\u20132011 that contain 2 785 189 words (i.e. 3 285 508 tokens including punctuation) uttered by 2 544 speakers, out of which 1 297 speakers are unique. ORAL2013 is balanced in the main sociolinguistic categories of the speakers (gender, age group, education, region of childhood residence).\r\n\r\nThe (anonymized) transcriptions are provided in the Transcriber XML format, audio (with corresponding anonymization beeps) is in uncompressed 16-bit PCM WAV, mono, 16 kHz format.\r\n\r\nAnother format option of the transcriptions is also available under less restrictive CC BY-NC-SA license at http://hdl.handle.net/11234/1-1847"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1848"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "balanced corpus"
-        },
-        {
-            "name": "spoken language"
-        },
-        {
-            "name": "speech corpus"
-        }
-    ],
-    "title": [
-        "ORAL2013: balanced corpus of informal spoken Czech (transcriptions & audio)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d0f20067-8c83-57d4-8044-c71b29e826ae.json b/oaitestdata/clarin-oai_dc/SET_1/json/d0f20067-8c83-57d4-8044-c71b29e826ae.json
deleted file mode 100644
index 7ffc0588..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d0f20067-8c83-57d4-8044-c71b29e826ae.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Ibtikarat team"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/xml",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Arabic"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1941",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1941"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1941",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Ibtikarat team"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)",
-        "http://creativecommons.org/licenses/by-nc/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Namly, Driss"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1941;2017-02-06T11:05:16Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Arabic Special verbs Lexicon;Namly, Driss;particles;An XML-based file containing Arabic Stop-words respecting verbs syntax;2015;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1941;ara;Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0);http://creativecommons.org/licenses/by-nc/4.0/;PUB;text/xml;text/plain; charset=utf-8;downloadable_files_count: 1;Ibtikarat team;http://arabic.emi.ac.ma/ibtikarat/?q=Resources",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d0f20067-8c83-57d4-8044-c71b29e826ae",
-    "notes": [
-        "An XML-based file containing Arabic Stop-words respecting verbs syntax"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1941"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "particles"
-        }
-    ],
-    "title": [
-        "Arabic Special verbs Lexicon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d0f5c167-bf26-5137-ab95-ba242a9b0afb.json b/oaitestdata/clarin-oai_dc/SET_1/json/d0f5c167-bf26-5137-ab95-ba242a9b0afb.json
deleted file mode 100644
index c84ba9dd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d0f5c167-bf26-5137-ab95-ba242a9b0afb.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3570",
-    "MetadataAccess": [
-        "oai:ota:oucs:3570"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Brown, John, 1715-1766."
-    ],
-    "fulltext": "oai:ota:oucs:3570;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3570.xml;Barbarossa: A tragedy. As it is perform'd at the Theatre-Royal in Drury-Lane.;Brown, John, 1715-1766.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d0f5c167-bf26-5137-ab95-ba242a9b0afb",
-    "oai_identifier": [
-        "oai:ota:oucs:3570"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Barbarossa: A tragedy. As it is perform'd at the Theatre-Royal in Drury-Lane."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3570.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d11e72af-3df5-5c8f-8d39-ce04418d7f79.json b/oaitestdata/clarin-oai_dc/SET_1/json/d11e72af-3df5-5c8f-8d39-ce04418d7f79.json
deleted file mode 100644
index e43a581d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d11e72af-3df5-5c8f-8d39-ce04418d7f79.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3886",
-    "MetadataAccess": [
-        "oai:ota:oucs:3886"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Churchill, Charles, 1731-1764."
-    ],
-    "fulltext": "oai:ota:oucs:3886;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3886.xml;The journey: A fragment. By C. Churchill.;Churchill, Charles, 1731-1764.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d11e72af-3df5-5c8f-8d39-ce04418d7f79",
-    "oai_identifier": [
-        "oai:ota:oucs:3886"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The journey: A fragment. By C. Churchill."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3886.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d1319a2f-69d8-5f80-8538-da1c07d6d825.json b/oaitestdata/clarin-oai_dc/SET_1/json/d1319a2f-69d8-5f80-8538-da1c07d6d825.json
deleted file mode 100644
index 84069b36..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d1319a2f-69d8-5f80-8538-da1c07d6d825.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=f9be5b86cf3011e1a404080027e73ea246e34a4274c54c068f14a2d622f4e4d4",
-    "MetadataAccess": [
-        "f9be5b86cf3011e1a404080027e73ea246e34a4274c54c068f14a2d622f4e4d4"
-    ],
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "f9be5b86cf3011e1a404080027e73ea246e34a4274c54c068f14a2d622f4e4d4;2019-02-27T12:09:03Z;lexicalConceptualResource;lexicalConceptualResource:lexicon;PAROLE Portuguese Lexicon;The resource is constituted by 20 thousand entries morpho-syntactically and syntactically encoded, accordingly to the parole common encoding standards. ;2015-12-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d1319a2f-69d8-5f80-8538-da1c07d6d825",
-    "notes": [
-        "The resource is constituted by 20 thousand entries morpho-syntactically and syntactically encoded, accordingly to the parole common encoding standards. "
-    ],
-    "oai_identifier": [
-        "f9be5b86cf3011e1a404080027e73ea246e34a4274c54c068f14a2d622f4e4d4"
-    ],
-    "oai_set": [
-        "lexicalConceptualResource",
-        "lexicalConceptualResource:lexicon"
-    ],
-    "state": "active",
-    "title": [
-        "PAROLE Portuguese Lexicon"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d15040d8-c91a-55ed-bc3e-8cbd3d901248.json b/oaitestdata/clarin-oai_dc/SET_1/json/d15040d8-c91a-55ed-bc3e-8cbd3d901248.json
deleted file mode 100644
index feecfea0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d15040d8-c91a-55ed-bc3e-8cbd3d901248.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5273",
-    "MetadataAccess": [
-        "oai:ota:oucs:5273"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Smith, Adam, 1723-1790."
-    ],
-    "fulltext": "oai:ota:oucs:5273;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5273.xml;The theory of moral sentiments: By Adam Smith, ...;Smith, Adam, 1723-1790.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d15040d8-c91a-55ed-bc3e-8cbd3d901248",
-    "oai_identifier": [
-        "oai:ota:oucs:5273"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The theory of moral sentiments: By Adam Smith, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5273.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d16afa26-86de-5e6e-ae40-b52f67675719.json b/oaitestdata/clarin-oai_dc/SET_1/json/d16afa26-86de-5e6e-ae40-b52f67675719.json
deleted file mode 100644
index 9c03253b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d16afa26-86de-5e6e-ae40-b52f67675719.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5282",
-    "MetadataAccess": [
-        "oai:ota:oucs:5282"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Addison, Joseph, 1672-1719."
-    ],
-    "fulltext": "oai:ota:oucs:5282;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5282.xml;Mr. Addison's fine ode to Dr. Thomas Burnet, on his sacred theory of the earth: Done into English by the author of a late tale call'd Coffee.;Ad insignissimum virum, D. Thomam Burnettum. English;Addison, Joseph, 1672-1719.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d16afa26-86de-5e6e-ae40-b52f67675719",
-    "oai_identifier": [
-        "oai:ota:oucs:5282"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Mr. Addison's fine ode to Dr. Thomas Burnet, on his sacred theory of the earth: Done into English by the author of a late tale call'd Coffee.",
-        "Ad insignissimum virum, D. Thomam Burnettum. English"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5282.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d16d1180-fdef-54b9-9036-9d0b89bfd1ed.json b/oaitestdata/clarin-oai_dc/SET_1/json/d16d1180-fdef-54b9-9036-9d0b89bfd1ed.json
deleted file mode 100644
index e9d6fff0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d16d1180-fdef-54b9-9036-9d0b89bfd1ed.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "less than 512 KB"
-    ],
-    "Language": [
-        "Welsh"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1402",
-    "MetadataAccess": [
-        "oai:ota:oucs:1402"
-    ],
-    "PublicationYear": [
-        "Unspecified"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Romances"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:1402;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1402.xml; Peredur  : [from] Llyfr Gwyn Rhydderch / compiled by Nancy H. Rose;Unspecified;text_and_corpus_linguistics;Myths and legends -- Wales;Romances -- Wales;cym;Oxford Text Archive, University of Oxford;less than 512 KB;Text;Romances;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d16d1180-fdef-54b9-9036-9d0b89bfd1ed",
-    "oai_identifier": [
-        "oai:ota:oucs:1402"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Myths legends -- Wales"
-        },
-        {
-            "name": "Romances -- Wales"
-        }
-    ],
-    "title": [
-        " Peredur  : [from] Llyfr Gwyn Rhydderch / compiled by Nancy H. Rose"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1402.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d16e6c87-deb1-5fe7-b7f9-f9ca6185fb8c.json b/oaitestdata/clarin-oai_dc/SET_1/json/d16e6c87-deb1-5fe7-b7f9-f9ca6185fb8c.json
deleted file mode 100644
index cea6dd92..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d16e6c87-deb1-5fe7-b7f9-f9ca6185fb8c.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "English",
-        "Czech",
-        "Russian",
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2683",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2683"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2683",
-    "PublicationTimestamp": "2018-05-15T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://aclweb.org/anthology/W18-0708"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "PAWS License",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/license-PAWS",
-        "RES"
-    ],
-    "author": [
-        "Nov\u00e1k, Michal",
-        "Ogrodniczuk, Maciej",
-        "Nedoluzhko, Anna"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2683;2019-01-10T19:34:25Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;PAWS;Nedoluzhko, Anna;Nov\u00e1k, Michal;Ogrodniczuk, Maciej;multilingual;parallel corpus;coreference;tectogrammatics;PAWS is a multi-lingual parallel treebank with coreference annotation. It consists of English texts from the Wall Street Journal translated into Czech, Russian and Polish. In addition, the texts are syntactically parsed and word-aligned. PAWS is based on PCEDT 2.0 and continues the tradition of multilingual treebanks with coreference annotation. PAWS offers linguistic material that can be further leveraged in cross-lingual studies, especially on coreference.;2018-05-15;corpus;http://hdl.handle.net/11234/1-2683;eng;ces;rus;pol;http://aclweb.org/anthology/W18-0708;PAWS License;https://lindat.mff.cuni.cz/repository/xmlui/page/license-PAWS;RES;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/paws",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d16e6c87-deb1-5fe7-b7f9-f9ca6185fb8c",
-    "notes": [
-        "PAWS is a multi-lingual parallel treebank with coreference annotation. It consists of English texts from the Wall Street Journal translated into Czech, Russian and Polish. In addition, the texts are syntactically parsed and word-aligned. PAWS is based on PCEDT 2.0 and continues the tradition of multilingual treebanks with coreference annotation. PAWS offers linguistic material that can be further leveraged in cross-lingual studies, especially on coreference."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2683"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "multilingual"
-        },
-        {
-            "name": "parallel corpus"
-        },
-        {
-            "name": "coreference"
-        },
-        {
-            "name": "tectogrammatics"
-        }
-    ],
-    "title": [
-        "PAWS"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d1731f65-49c5-55dd-a591-834a4fffe440.json b/oaitestdata/clarin-oai_dc/SET_1/json/d1731f65-49c5-55dd-a591-834a4fffe440.json
deleted file mode 100644
index d1a4cb62..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d1731f65-49c5-55dd-a591-834a4fffe440.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Frisian Academy"
-    ],
-    "Contributor": [
-        "Versloot, Arjen",
-        "Boersma, Piter"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-880",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-880"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-880",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Frisian Academy"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-880;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Middle Frisian corpus;Boersma, Piter;Versloot, Arjen;All existing Middle Frisian texts are contained in the Middle Frisian corpus. The texts are tagged and lemmatised; spelling variants have been brought together.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-880;downloadable_files_count: 0;Netherlands (the);Frisian Academy;http://www.fa.knaw.nl/fa/3departments-and-disciplines/department-of-linguistics/taalkorpora_en_/frisian-language-corpus",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d1731f65-49c5-55dd-a591-834a4fffe440",
-    "notes": [
-        "All existing Middle Frisian texts are contained in the Middle Frisian corpus. The texts are tagged and lemmatised; spelling variants have been brought together."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-880"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Middle Frisian corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d1b2b105-c6bb-54a6-8b61-072f8be2f4eb.json b/oaitestdata/clarin-oai_dc/SET_1/json/d1b2b105-c6bb-54a6-8b61-072f8be2f4eb.json
deleted file mode 100644
index cdbef5b5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d1b2b105-c6bb-54a6-8b61-072f8be2f4eb.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "German",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/38",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/38"
-    ],
-    "PID": "http://hdl.handle.net/11509/38",
-    "PublicationTimestamp": "2012-04-18T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Parra Escart\u00edn, Carla"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/38;2016-04-15T05:59:20Z;hdl_11509_1;hdl_11509_2;Parallel Corpus of documents from the Technical Regulations Information System for German-Spanish (v0.2);Parra Escart\u00edn, Carla;Corpus;Text;German;Spanish, Castilian;Specialized parallel corpus Spanish-German (ES-ES, DE-AT and DE-DE), texts from the European Commission between 1997-2010. The texts are technical regulations in a variety of domains. To be sentence aligned. The current version 0.2 contains the files for 1999-2010 in the domain B00: Construction (205 files; 70,648 sentences; 1,563,000 words). This version also fixed some formatting errors detected in version 0.1 of the corpus. Versions 0.1 and 0.2 are kept as individual records because they are (currently) intended to be downloaded individually. Neither version are currently available for download, as the licensing terms and the distributor is still under negotiation. The current contact person is therefore the corpus developer, Carla Parra.;2012-04-18;corpus;http://hdl.handle.net/11509/38;ger;spa;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;CC;application/zip;downloadable_files_count: 1",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d1b2b105-c6bb-54a6-8b61-072f8be2f4eb",
-    "notes": [
-        "Specialized parallel corpus Spanish-German (ES-ES, DE-AT and DE-DE), texts from the European Commission between 1997-2010. The texts are technical regulations in a variety of domains. To be sentence aligned. The current version 0.2 contains the files for 1999-2010 in the domain B00: Construction (205 files; 70,648 sentences; 1,563,000 words). This version also fixed some formatting errors detected in version 0.1 of the corpus. Versions 0.1 and 0.2 are kept as individual records because they are (currently) intended to be downloaded individually. Neither version are currently available for download, as the licensing terms and the distributor is still under negotiation. The current contact person is therefore the corpus developer, Carla Parra."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/38"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Corpus"
-        },
-        {
-            "name": "Text"
-        },
-        {
-            "name": "German"
-        },
-        {
-            "name": "Spanish"
-        },
-        {
-            "name": "Castilian"
-        }
-    ],
-    "title": [
-        "Parallel Corpus of documents from the Technical Regulations Information System for German-Spanish (v0.2)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d1b4e844-fab8-5261-83fe-575c8fe99321.json b/oaitestdata/clarin-oai_dc/SET_1/json/d1b4e844-fab8-5261-83fe-575c8fe99321.json
deleted file mode 100644
index 7f83111b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d1b4e844-fab8-5261-83fe-575c8fe99321.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3763",
-    "MetadataAccess": [
-        "oai:ota:oucs:3763"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Cumberland, Richard, 1732-1811."
-    ],
-    "fulltext": "oai:ota:oucs:3763;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3763.xml;Arundel: By the author of The observer. ... [pt.1];Cumberland, Richard, 1732-1811.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d1b4e844-fab8-5261-83fe-575c8fe99321",
-    "oai_identifier": [
-        "oai:ota:oucs:3763"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Arundel: By the author of The observer. ... [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3763.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d1bc714a-2a98-5141-8b65-93ba9a14a9ff.json b/oaitestdata/clarin-oai_dc/SET_1/json/d1bc714a-2a98-5141-8b65-93ba9a14a9ff.json
deleted file mode 100644
index 23f3d871..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d1bc714a-2a98-5141-8b65-93ba9a14a9ff.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Wells, Stanley W., 1930-"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 164 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0133",
-    "MetadataAccess": [
-        "oai:ota:oucs:0133"
-    ],
-    "PublicationTimestamp": "1598-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1598"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Shakespeare, William, 1564-1616"
-    ],
-    "fulltext": "oai:ota:oucs:0133;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0133.xml;King Henry IV. Part 1;Henry IV : part 1;Shakespeare, William, 1564-1616;1598;text_and_corpus_linguistics;Plays -- England -- 16th century;eng;Oxford Text Archive, University of Oxford;Wells, Stanley W., 1930-;(1 file : ca. 164 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d1bc714a-2a98-5141-8b65-93ba9a14a9ff",
-    "oai_identifier": [
-        "oai:ota:oucs:0133"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        }
-    ],
-    "title": [
-        "King Henry IV. Part 1",
-        "Henry IV : part 1"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0133.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d1c65401-5a68-5c80-a93d-5435d0f8bf32.json b/oaitestdata/clarin-oai_dc/SET_1/json/d1c65401-5a68-5c80-a93d-5435d0f8bf32.json
deleted file mode 100644
index 8cfc6da2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d1c65401-5a68-5c80-a93d-5435d0f8bf32.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-726",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-726"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-726",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-726;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Guanchet corpus;Guanchet is the language spoken by the canary natives in the millenia previous to the Hispanic conquest.;2014-07-30;languageDescription;http://hdl.handle.net/11372/LRT-726;downloadable_files_count: 0;Spain;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI239015%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d1c65401-5a68-5c80-a93d-5435d0f8bf32",
-    "notes": [
-        "Guanchet is the language spoken by the canary natives in the millenia previous to the Hispanic conquest."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-726"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Guanchet corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d1e136c0-8c3a-5e85-908a-7962a60ca26d.json b/oaitestdata/clarin-oai_dc/SET_1/json/d1e136c0-8c3a-5e85-908a-7962a60ca26d.json
deleted file mode 100644
index 6f1dbce1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d1e136c0-8c3a-5e85-908a-7962a60ca26d.json
+++ /dev/null
@@ -1,49 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5078",
-    "MetadataAccess": [
-        "oai:ota:oucs:5078"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:5078;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5078.xml;The lucubrations of Isaac Bickerstaff Esq: revised and corrected by the author. ... [pt.5];text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d1e136c0-8c3a-5e85-908a-7962a60ca26d",
-    "oai_identifier": [
-        "oai:ota:oucs:5078"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The lucubrations of Isaac Bickerstaff Esq: revised and corrected by the author. ... [pt.5]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5078.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d1e9bad7-4fa8-5062-be4f-6eef4e09e75b.json b/oaitestdata/clarin-oai_dc/SET_1/json/d1e9bad7-4fa8-5062-be4f-6eef4e09e75b.json
deleted file mode 100644
index 0aa2d6fb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d1e9bad7-4fa8-5062-be4f-6eef4e09e75b.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4071",
-    "MetadataAccess": [
-        "oai:ota:oucs:4071"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Arbuthnot, John, 1667-1735."
-    ],
-    "fulltext": "oai:ota:oucs:4071;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4071.xml;Mr. Maitland's account of inoculating the small pox;Arbuthnot, John, 1667-1735.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d1e9bad7-4fa8-5062-be4f-6eef4e09e75b",
-    "oai_identifier": [
-        "oai:ota:oucs:4071"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Mr. Maitland's account of inoculating the small pox"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4071.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d1edf2ab-fa74-548d-90a8-b229b566deba.json b/oaitestdata/clarin-oai_dc/SET_1/json/d1edf2ab-fa74-548d-90a8-b229b566deba.json
deleted file mode 100644
index 75dbbbfe..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d1edf2ab-fa74-548d-90a8-b229b566deba.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Ewa Dulna-Rak"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 322",
-        "text/plain; charset=utf-8",
-        "text/richtext"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/318",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/318"
-    ],
-    "PID": "http://hdl.handle.net/11321/318",
-    "PublicationTimestamp": "2016-07-24T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Ewa Dulna-Rak"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Dulna-Rak, Ewa"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/318;2016-08-11T17:43:59Z;hdl_11321_3;hdl_11321_4;Wilam Horzyca - teksty teatralne;Dulna-Rak, Ewa;theater;language;words;Teksty Wilama Horzycy.;2016-07-24;corpus;http://hdl.handle.net/11321/318;pol;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;text/plain; charset=utf-8;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;downloadable_files_count: 322;Ewa Dulna-Rak",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d1edf2ab-fa74-548d-90a8-b229b566deba",
-    "notes": [
-        "Teksty Wilama Horzycy."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/318"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "theater"
-        },
-        {
-            "name": "language"
-        },
-        {
-            "name": "words"
-        }
-    ],
-    "title": [
-        "Wilam Horzyca - teksty teatralne"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d1f16191-a02d-56ad-b571-ad31a5312e8b.json b/oaitestdata/clarin-oai_dc/SET_1/json/d1f16191-a02d-56ad-b571-ad31a5312e8b.json
deleted file mode 100644
index 6eaa3aa1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d1f16191-a02d-56ad-b571-ad31a5312e8b.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=d2de063c6c0211e2a2aa782bcb074135eff58f6a6c5a42f992529a4b21bacfc1",
-    "MetadataAccess": [
-        "d2de063c6c0211e2a2aa782bcb074135eff58f6a6c5a42f992529a4b21bacfc1"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "d2de063c6c0211e2a2aa782bcb074135eff58f6a6c5a42f992529a4b21bacfc1;2018-11-15T16:40:09Z;toolService;toolService:service;U-Compare syntactic chunking service;Web service created by exporting UIMA-based workflow from the U-Compare text mining system.\nFunctionality: Identifies and categorises syntactic chunks in plain text\nTools in workflow: Freeling shallow parser web service (service provided by the PANACEA project) \nNOTE: The licence provided covers the U-Compare web service only. Tools used to create the workflow may have their own licences;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d1f16191-a02d-56ad-b571-ad31a5312e8b",
-    "notes": [
-        "Web service created by exporting UIMA-based workflow from the U-Compare text mining system.\nFunctionality: Identifies and categorises syntactic chunks in plain text\nTools in workflow: Freeling shallow parser web service (service provided by the PANACEA project) \nNOTE: The licence provided covers the U-Compare web service only. Tools used to create the workflow may have their own licences"
-    ],
-    "oai_identifier": [
-        "d2de063c6c0211e2a2aa782bcb074135eff58f6a6c5a42f992529a4b21bacfc1"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:service"
-    ],
-    "state": "active",
-    "title": [
-        "U-Compare syntactic chunking service"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d22886a3-5964-51a2-965a-9a78acffac67.json b/oaitestdata/clarin-oai_dc/SET_1/json/d22886a3-5964-51a2-965a-9a78acffac67.json
deleted file mode 100644
index 3d01f447..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d22886a3-5964-51a2-965a-9a78acffac67.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "A"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1806",
-    "MetadataAccess": [
-        "oai:ota:oucs:1806"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Irving, Washington"
-    ],
-    "fulltext": "oai:ota:oucs:1806;2018-05-17T09:29:11Z;http://ota.ox.ac.uk/headers/1806.xml;The legend of Sleepy Hollow;Irving, Washington;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;A;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d22886a3-5964-51a2-965a-9a78acffac67",
-    "oai_identifier": [
-        "oai:ota:oucs:1806"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The legend of Sleepy Hollow"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1806.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d22bda3d-ee13-59f7-ae4e-bb452dfe27ca.json b/oaitestdata/clarin-oai_dc/SET_1/json/d22bda3d-ee13-59f7-ae4e-bb452dfe27ca.json
deleted file mode 100644
index 556d02b2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d22bda3d-ee13-59f7-ae4e-bb452dfe27ca.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "text/xml",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Northern Sami"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/110",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/110"
-    ],
-    "PID": "http://hdl.handle.net/11509/110",
-    "PublicationTimestamp": "2015-10-17T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "CC",
-        "http://creativecommons.org/licenses/by/3.0/"
-    ],
-    "author": [
-        "Giellatekno - Saami Language Technology, UiT The Arctic University of Norway"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/110;2016-09-06T13:04:48Z;hdl_11509_1;hdl_11509_2;North Saami N-grams;Giellatekno - Saami Language Technology, UiT The Arctic University of Norway;North Saami;1-gram;2-gram;3-gram;Language Model;The North Saami N-gram data set is work done by the Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language community. In particular, Ciprian-Virgil Gerstenberger compiled the data set from the entire SIKOR North Saami corpus version 2015-10-10. The length of the N-grams ranges from unigrams (single words) to tri-grams (944754 unigrams, 7161697 bigrams, 3274039 trigrams). Only N-grams within sentences have been counted. The data format follows the ARPA backoff N-gram models and has been generated using SRILM, the SRI Language Modeling Toolkit (http://www.speech.sri.com/projects/srilm/). Since the N-grams have been derived automatically, they may contain wrong values. In case you find any errors the creators would appreciate your feedback sent to giellatekno@uit.no and feedback@divvun.no. Please note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata).;2015-10-17;corpus;http://hdl.handle.net/11509/110;sme;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);CC;http://creativecommons.org/licenses/by/3.0/;application/zip;text/plain; charset=utf-8;text/xml;downloadable_files_count: 1;Giellatekno - Saami Language Technology;http://giellatekno.uit.no/index.eng.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d22bda3d-ee13-59f7-ae4e-bb452dfe27ca",
-    "notes": [
-        "The North Saami N-gram data set is work done by the Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language community. In particular, Ciprian-Virgil Gerstenberger compiled the data set from the entire SIKOR North Saami corpus version 2015-10-10. The length of the N-grams ranges from unigrams (single words) to tri-grams (944754 unigrams, 7161697 bigrams, 3274039 trigrams). Only N-grams within sentences have been counted. The data format follows the ARPA backoff N-gram models and has been generated using SRILM, the SRI Language Modeling Toolkit (http://www.speech.sri.com/projects/srilm/). Since the N-grams have been derived automatically, they may contain wrong values. In case you find any errors the creators would appreciate your feedback sent to giellatekno@uit.no and feedback@divvun.no. Please note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata)."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/110"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "North Saami"
-        },
-        {
-            "name": "-gram"
-        },
-        {
-            "name": "-gram"
-        },
-        {
-            "name": "-gram"
-        },
-        {
-            "name": "Language Model"
-        }
-    ],
-    "title": [
-        "North Saami N-grams"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d264f40a-405d-5089-950f-1c1d2a267e40.json b/oaitestdata/clarin-oai_dc/SET_1/json/d264f40a-405d-5089-950f-1c1d2a267e40.json
deleted file mode 100644
index cfd77514..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d264f40a-405d-5089-950f-1c1d2a267e40.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 435 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1848",
-    "MetadataAccess": [
-        "oai:ota:oucs:1848"
-    ],
-    "PublicationTimestamp": "1880-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1880"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Trollope, Anthony, 1815-1882"
-    ],
-    "fulltext": "oai:ota:oucs:1848;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/1848.xml;Dr. Wortle's school / by Anthony Trollope;Trollope, Anthony, 1815-1882;1880;text_and_corpus_linguistics;Novels -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 435 KB);Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d264f40a-405d-5089-950f-1c1d2a267e40",
-    "oai_identifier": [
-        "oai:ota:oucs:1848"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Novels -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Dr. Wortle's school / by Anthony Trollope"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1848.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d2753e36-69ee-5a71-adad-1bde48edbdc6.json b/oaitestdata/clarin-oai_dc/SET_1/json/d2753e36-69ee-5a71-adad-1bde48edbdc6.json
deleted file mode 100644
index 3953aea4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d2753e36-69ee-5a71-adad-1bde48edbdc6.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/9",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/9"
-    ],
-    "PID": "http://hdl.handle.net/10794/9",
-    "PublicationTimestamp": "2015-03-04T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Borin, Lars"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/9;2017-10-27T16:12:08Z;hdl_10794_1;hdl_10794_2;Blingbring (2017-10-16);Blingbring (2017-10-16);Borin, Lars;Swedish;Thesaurus;Blingbring, an enhanced and modernized version of Bring's thesaurus (1930).;Blingbring, en SALDO-l\u00e4nkad och moderniserad version av Brings \"Svenskt ordf\u00f6rr\u00e5d ordnat i begreppsklasser\" (1930).;2015-03-04;lexicalConceptualResource;http://hdl.handle.net/10794/9;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/blingbring",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d2753e36-69ee-5a71-adad-1bde48edbdc6",
-    "notes": [
-        "Blingbring, an enhanced and modernized version of Bring's thesaurus (1930).",
-        "Blingbring, en SALDO-l\u00e4nkad och moderniserad version av Brings \"Svenskt ordf\u00f6rr\u00e5d ordnat i begreppsklasser\" (1930)."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/9"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Thesaurus"
-        }
-    ],
-    "title": [
-        "Blingbring (2017-10-16)",
-        "Blingbring (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d2882a63-8362-5d98-bb00-6c2cb4e40cc1.json b/oaitestdata/clarin-oai_dc/SET_1/json/d2882a63-8362-5d98-bb00-6c2cb4e40cc1.json
deleted file mode 100644
index 81674d41..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d2882a63-8362-5d98-bb00-6c2cb4e40cc1.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Jezuit\u00f3w"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-163378",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-163378"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CE8-C",
-    "PublicationTimestamp": "1644-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1644"
-    ],
-    "Publisher": [
-        "Drukarnia Jezuit\u00f3w"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/163378",
-        "oai:jbc.bj.uj.edu.pl:publication:171752"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1601/1700"
-    ],
-    "TempCoverageBegin": 50506804799,
-    "TempCoverageEnd": 50506804799,
-    "TemporalCoverage": " point in time : 1601-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1601-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1601-07-01T11:59:59Z",
-    "author": [
-        "Okolski, Szymon (1580-1653)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-163378;2019-02-28T18:45:46Z;Chor\u0105giew Tryumphalna troiaka, Szlachecka, Chrzescianska, Swieta. : Na Pogrzebie Zacnie Vrodzonego Iego Mo\u015bci Pana, Pana Miko\u0142aia z Czertwic Cetnera. W Kosciele Podkamienieckim Naswi\u0119tszey Panny Rozanca S. Przez W. O. Symona Okolskiego [...] og\u0142oszona: a do Druku [...] Roku 1644. Martij 12. podana;Okolski, Szymon (1580-1653);starodruki 17\u00a0w.;Drukarnia Jezuit\u00f3w;[1644];starodruk;application/xml;clarind-uds:poldilemma-163378;hdl:11858/00-246C-0000-0023-8CE8-C;Biblioteka Jagiello\u0144ska, BJ St. Dr. 25280 I;pol;http://jbc.bj.uj.edu.pl/Content/163378;oai:jbc.bj.uj.edu.pl:publication:171752;1601/1700;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d2882a63-8362-5d98-bb00-6c2cb4e40cc1",
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-163378"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Chor\u0105giew Tryumphalna troiaka, Szlachecka, Chrzescianska, Swieta. : Na Pogrzebie Zacnie Vrodzonego Iego Mo\u015bci Pana, Pana Miko\u0142aia z Czertwic Cetnera. W Kosciele Podkamienieckim Naswi\u0119tszey Panny Rozanca S. Przez W. O. Symona Okolskiego [...] og\u0142oszona: a do Druku [...] Roku 1644. Martij 12. podana"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d2913607-9931-5540-a5d0-7ca9e73e731c.json b/oaitestdata/clarin-oai_dc/SET_1/json/d2913607-9931-5540-a5d0-7ca9e73e731c.json
deleted file mode 100644
index 72b64f48..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d2913607-9931-5540-a5d0-7ca9e73e731c.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Indonesian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0005-BF85-F",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0005-BF85-F"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0005-BF85-F",
-    "PublicationTimestamp": "2012-03-13T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/238405"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Larasati, Septina Dian"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0005-BF85-F;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;IDENTICv1.0;Larasati, Septina Dian;Indonesian-English parallel corpus;parallel corpus;IDENTIC is an Indonesian-English parallel corpus for research purposes. The corpus is a bilingual corpus paired with English. The aim of this work is to build and provide researchers a proper Indonesian-English textual data set and also to promote research in this language pair. The corpus contains texts coming from different sources with different genres.;2012-03-13;corpus;http://hdl.handle.net/11858/00-097C-0000-0005-BF85-F;ind;info:eu-repo/grantAgreement/EC/FP7/238405;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d2913607-9931-5540-a5d0-7ca9e73e731c",
-    "notes": [
-        "IDENTIC is an Indonesian-English parallel corpus for research purposes. The corpus is a bilingual corpus paired with English. The aim of this work is to build and provide researchers a proper Indonesian-English textual data set and also to promote research in this language pair. The corpus contains texts coming from different sources with different genres."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0005-BF85-F"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Indonesian-English parallel corpus"
-        },
-        {
-            "name": "parallel corpus"
-        }
-    ],
-    "title": [
-        "IDENTICv1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d298b0ba-d727-5ec0-b663-2b55d1be7cda.json b/oaitestdata/clarin-oai_dc/SET_1/json/d298b0ba-d727-5ec0-b663-2b55d1be7cda.json
deleted file mode 100644
index 80aa1f65..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d298b0ba-d727-5ec0-b663-2b55d1be7cda.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Budapest University of Technology and Economics Media Research (BME MOKK)"
-    ],
-    "Contributor": [
-        "Varga, D\u00e1niel"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1203",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1203"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1203",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Budapest University of Technology and Economics Media Research (BME MOKK)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Hungary"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1203;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;hunalign - sentence level aligner;Varga, D\u00e1niel;Hunalign is a powerful free sentence level aligner for building parallel corpora. Its input is tokenized and sentence-segmented text in two languages.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1203;downloadable_files_count: 0;Hungary;Budapest University of Technology and Economics Media Research (BME MOKK);http://mokk.bme.hu/resources/hunalign",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d298b0ba-d727-5ec0-b663-2b55d1be7cda",
-    "notes": [
-        "Hunalign is a powerful free sentence level aligner for building parallel corpora. Its input is tokenized and sentence-segmented text in two languages."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1203"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "hunalign - sentence level aligner"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d2a1e60c-73da-57d4-ac12-4ed356df880b.json b/oaitestdata/clarin-oai_dc/SET_1/json/d2a1e60c-73da-57d4-ac12-4ed356df880b.json
deleted file mode 100644
index 421b08dc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d2a1e60c-73da-57d4-ac12-4ed356df880b.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Arts, Institute of the Czech National Corpus"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2580",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2580"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2580",
-    "PublicationTimestamp": "2017-12-28T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Arts, Institute of the Czech National Corpus"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-2579"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Kop\u0159ivov\u00e1, Marie",
-        "Luke\u0161, David",
-        "Poukarov\u00e1, Petra",
-        "\u0160karpov\u00e1, Marie",
-        "Komrskov\u00e1, Zuzana"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2580;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;ORTOFON v1: balanced corpus of informal spoken Czech with multi-tier transcription (transcriptions);Kop\u0159ivov\u00e1, Marie;Komrskov\u00e1, Zuzana;Luke\u0161, David;Poukarov\u00e1, Petra;\u0160karpov\u00e1, Marie;balanced corpus;spoken language;informal language;Czech;ORTOFON v1 is designed as a representation of authentic spoken Czech used in informal situations (private environment, spontaneity, unpreparedness etc.) in the area of the whole Czech Republic. The corpus is composed of 332 recordings from 2012\u20132017 and contains 1 014 786 orthographic words (i.e. a total of 1 236 508 tokens including punctuation); a total of 624 different speakers appear in the probes. ORTOFON v1 is fully balanced regarding the basic sociolinguistic speaker categories (gender, age group, level of education and region of childhood residence).\r\n\r\nThe transcription is linked to the corresponding audio track. Unlike the ORAL-series corpora, the transcription was carried out on two main tiers, orthographic and phonetic, supplemented by an additional metalanguage tier. ORTOFON v1 is lemmatized and morphologically tagged. The (anonymized) corpus is provided in a (semi-XML) vertical format used as an input to the Manatee query engine. The data thus correspond to the corpus available via the KonText query engine to registered users of the CNC at http://www.korpus.cz\r\n\r\nPlease note: this item includes only the transcriptions, audio (and the transcripts in their original format) is available under more restrictive non-CC license at http://hdl.handle.net/11234/1-2579;2017-12-28;corpus;http://hdl.handle.net/11234/1-2580;ces;http://hdl.handle.net/11234/1-2579;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Arts, Institute of the Czech National Corpus;http://wiki.korpus.cz/doku.php/en:cnk:ortofon",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d2a1e60c-73da-57d4-ac12-4ed356df880b",
-    "notes": [
-        "ORTOFON v1 is designed as a representation of authentic spoken Czech used in informal situations (private environment, spontaneity, unpreparedness etc.) in the area of the whole Czech Republic. The corpus is composed of 332 recordings from 2012\u20132017 and contains 1 014 786 orthographic words (i.e. a total of 1 236 508 tokens including punctuation); a total of 624 different speakers appear in the probes. ORTOFON v1 is fully balanced regarding the basic sociolinguistic speaker categories (gender, age group, level of education and region of childhood residence).\r\n\r\nThe transcription is linked to the corresponding audio track. Unlike the ORAL-series corpora, the transcription was carried out on two main tiers, orthographic and phonetic, supplemented by an additional metalanguage tier. ORTOFON v1 is lemmatized and morphologically tagged. The (anonymized) corpus is provided in a (semi-XML) vertical format used as an input to the Manatee query engine. The data thus correspond to the corpus available via the KonText query engine to registered users of the CNC at http://www.korpus.cz\r\n\r\nPlease note: this item includes only the transcriptions, audio (and the transcripts in their original format) is available under more restrictive non-CC license at http://hdl.handle.net/11234/1-2579"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2580"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "balanced corpus"
-        },
-        {
-            "name": "spoken language"
-        },
-        {
-            "name": "informal language"
-        },
-        {
-            "name": "Czech"
-        }
-    ],
-    "title": [
-        "ORTOFON v1: balanced corpus of informal spoken Czech with multi-tier transcription (transcriptions)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d2a3caf4-325d-50f1-89d0-9e82492d93a0.json b/oaitestdata/clarin-oai_dc/SET_1/json/d2a3caf4-325d-50f1-89d0-9e82492d93a0.json
deleted file mode 100644
index fce2291f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d2a3caf4-325d-50f1-89d0-9e82492d93a0.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4132",
-    "MetadataAccess": [
-        "oai:ota:oucs:4132"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dibdin, Charles, 1745-1814."
-    ],
-    "fulltext": "oai:ota:oucs:4132;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4132.xml;Royal Circus epitomized;Dibdin, Charles, 1745-1814.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d2a3caf4-325d-50f1-89d0-9e82492d93a0",
-    "oai_identifier": [
-        "oai:ota:oucs:4132"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Royal Circus epitomized"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4132.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d2a6951b-01e1-5dd1-b910-1e9789fc707c.json b/oaitestdata/clarin-oai_dc/SET_1/json/d2a6951b-01e1-5dd1-b910-1e9789fc707c.json
deleted file mode 100644
index 38c36047..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d2a6951b-01e1-5dd1-b910-1e9789fc707c.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 105 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2107",
-    "MetadataAccess": [
-        "oai:ota:oucs:2107"
-    ],
-    "PublicationTimestamp": "1809-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1809"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Austen, Jane, 1775-1817"
-    ],
-    "fulltext": "oai:ota:oucs:2107;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/2107.xml;The Watsons / by Jane Austen;Austen, Jane, 1775-1817;1809;text_and_corpus_linguistics;Novels -- Great Britain -- 19th century;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 105 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d2a6951b-01e1-5dd1-b910-1e9789fc707c",
-    "oai_identifier": [
-        "oai:ota:oucs:2107"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Novels -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "The Watsons / by Jane Austen"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2107.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d2b15274-80cd-566c-8b3d-c2976ee53e6f.json b/oaitestdata/clarin-oai_dc/SET_1/json/d2b15274-80cd-566c-8b3d-c2976ee53e6f.json
deleted file mode 100644
index 7293ed0c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d2b15274-80cd-566c-8b3d-c2976ee53e6f.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3909",
-    "MetadataAccess": [
-        "oai:ota:oucs:3909"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Kenrick, W. (William), 1725?-1779."
-    ],
-    "fulltext": "oai:ota:oucs:3909;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3909.xml;A defence of Mr. Kenrick's review of Dr. Johnson's Shakespeare: containing a number of curious and ludicrous anecdotes of literary biography. By a friend.;Kenrick, W. (William), 1725?-1779.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d2b15274-80cd-566c-8b3d-c2976ee53e6f",
-    "oai_identifier": [
-        "oai:ota:oucs:3909"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A defence of Mr. Kenrick's review of Dr. Johnson's Shakespeare: containing a number of curious and ludicrous anecdotes of literary biography. By a friend."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3909.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d2d4f46e-6c23-5543-ac00-f94b0d72a8db.json b/oaitestdata/clarin-oai_dc/SET_1/json/d2d4f46e-6c23-5543-ac00-f94b0d72a8db.json
deleted file mode 100644
index 3ff53489..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d2d4f46e-6c23-5543-ac00-f94b0d72a8db.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=86b7544ab17011e1a404080027e73ea273a3a3cec91b403e9cb74350770942a1",
-    "MetadataAccess": [
-        "86b7544ab17011e1a404080027e73ea273a3a3cec91b403e9cb74350770942a1"
-    ],
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "86b7544ab17011e1a404080027e73ea273a3a3cec91b403e9cb74350770942a1;2019-02-27T12:08:47Z;corpus;corpus:text;CINTIL-PropBank;The CINTIL-PropBank (Branco et al., 2012) is a set of sentences annotated with their constituency structure and semantic role tags, composed of 10,039 sentences and 110,166 tokens taken from different sources and domains: news (8,861 sentences; 101,430 tokens), and novels (399 sentences; 3,082 tokens). In addition, there are 779 sentences (5,654 tokens) used for regression testing of the computational grammar that supported the annotation of the corpus.\nFor the creation of this PropBank we adopted a semi-automatic analysis with a double-blind annotation followed by adjudication. The resulting dataset contains three information levels: phrase constituency, grammatical functions, and phrase semantic roles.\nThe main motivation behind the creation of this resource was to build a high quality data set with semantic information that could support the development of automatic semantic role labelers for Portuguese.;2015-12-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d2d4f46e-6c23-5543-ac00-f94b0d72a8db",
-    "notes": [
-        "The CINTIL-PropBank (Branco et al., 2012) is a set of sentences annotated with their constituency structure and semantic role tags, composed of 10,039 sentences and 110,166 tokens taken from different sources and domains: news (8,861 sentences; 101,430 tokens), and novels (399 sentences; 3,082 tokens). In addition, there are 779 sentences (5,654 tokens) used for regression testing of the computational grammar that supported the annotation of the corpus.\nFor the creation of this PropBank we adopted a semi-automatic analysis with a double-blind annotation followed by adjudication. The resulting dataset contains three information levels: phrase constituency, grammatical functions, and phrase semantic roles.\nThe main motivation behind the creation of this resource was to build a high quality data set with semantic information that could support the development of automatic semantic role labelers for Portuguese."
-    ],
-    "oai_identifier": [
-        "86b7544ab17011e1a404080027e73ea273a3a3cec91b403e9cb74350770942a1"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "CINTIL-PropBank"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d30c3968-00c1-5f55-a722-ef494ee9ed88.json b/oaitestdata/clarin-oai_dc/SET_1/json/d30c3968-00c1-5f55-a722-ef494ee9ed88.json
deleted file mode 100644
index 9e4dd7d3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d30c3968-00c1-5f55-a722-ef494ee9ed88.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Royster, Paul"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 1.5 MB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1654",
-    "MetadataAccess": [
-        "oai:ota:oucs:1654"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Essays"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Whitman, Walt, 1819-1892"
-    ],
-    "fulltext": "oai:ota:oucs:1654;2018-02-16T10:42:06Z;http://ota.ox.ac.uk/headers/1654.xml;Complete prose works : [1892] / Walt Whitman;[Prose];Whitman, Walt, 1819-1892;text_and_corpus_linguistics;American literature -- 19th century;Oxford Text Archive, University of Oxford;Royster, Paul;text/sgml;(1 file : ca. 1.5 MB);Text;Essays;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d30c3968-00c1-5f55-a722-ef494ee9ed88",
-    "oai_identifier": [
-        "oai:ota:oucs:1654"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "American literature -- th century"
-        }
-    ],
-    "title": [
-        "Complete prose works : [1892] / Walt Whitman",
-        "[Prose]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1654.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d34b9db8-e8bf-5be0-b443-14ddd26fdd46.json b/oaitestdata/clarin-oai_dc/SET_1/json/d34b9db8-e8bf-5be0-b443-14ddd26fdd46.json
deleted file mode 100644
index fcc977ba..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d34b9db8-e8bf-5be0-b443-14ddd26fdd46.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Dominik Wojciech Siarkowski"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-5946",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-5946"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D2A-0",
-    "PublicationTimestamp": "1746-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1746"
-    ],
-    "Publisher": [
-        "Dominik Wojciech Siarkowski"
-    ],
-    "RelatedIdentifier": [
-        "http://dlibra.bibliotekaelblaska.pl/Content/5946",
-        "oai:dlibra.bibliotekaelblaska.pl:publication:6373"
-    ],
-    "ResourceType": [
-        "starodruk",
-        "alter Druck"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "author": [
-        "Wuykowski Jan Stanis\u0142aw Kostka"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-5946;2019-03-01T15:54:01Z;Chleb duchowny, wszystkim chrze\u015bcianom na posi\u0142ek w drodze, do Nieba id\u0105cym, wystawiony albo raczey katechizm\u2026;Chleb duchowny, wszystkim chrze\u015bcianom na posi\u0142ek w drodze, do Nieba id\u0105cym, wystawiony albo raczey katechizm\u2026;Wuykowski Jan Stanis\u0142aw Kostka;Wuykowski Jan Stanis\u0142aw Kostka;modlitewnik katolicki;nauki chrze\u015bcija\u0144skie - podr\u0119cznik;katholisches Gebetbuch;christliche Lehre - Handbuch;Na karcie przedtytu\u0142owej odr\u0119czne \u0142aci\u0144skie zapiski . Za kart\u0105 tytu\u0142ow\u0105 widniej\u0105 cytaty \u0142aci\u0144skie oraz pozwolenie i aprobata na wydruk owego dzie\u0142a, wystawione 20 listopada 1744 r. w Krakowie i zatwierdzaj\u0105ce druk do publikacji przez doktora, profesora, kanonika katedry krakowskiej ks. Macieja Zi\u0119tkiewicza. Podr\u0119cznik do nauk chrze\u015bcija\u0144skich (katechizm) oparty na zadawaniu pyta\u0144 oraz odpowiedziach m. in. : pytanie: Kt\u00f3ra rzecz jest najgorsza na tym \u015bwiecie ? odp. : grzech etc. Starodruk wsp\u00f3\u0142oprawny : XVIII. 146 adl. 1-2 (adl. 2 - \"Przewodnik na drog\u0119 wiecznosci dla du\u00df ludzkich\u2026\"), wydany w drukarni Dominika Wojciecha Siarkowskiego, w formacie 4\u00b0. Oprawa zniszczona.;Auf dem Vortitelblatt handgeschriebene lateinische Notizen. Auf dem n\u00e4chsten Blatt lateinische Spr\u00fcche und Zulassung des Werkes zum Druck vom Professor Dr. Kanoniker der Wawelkathedrale Maciej Zi\u0119tkiewicz. Das Handbuch zur christlichen Lehre (Katechismus) mit Fragen und Antworten (z. B. \u201e-Was ist am schlimmsten auf der ganzen Welt?\u201c \u201eS\u00fcnde\u201c. Das zusammen eingebundene Druckerzeugnis: XVIII. 146 adl. 1-2 (adl. 2 - \"Przewodnik na drog\u0119 wieczno\u015bci dla du\u00df ludzkich\u2026\"), in der Druckerei von Dominik Wojciech Siarkowski, im Buchformat 4\u00ba. Besch\u00e4digter Einband.;Dominik Wojciech Siarkowski;Dominik Wojciech Siarkowski;1746;1746;starodruk;alter Druck;application/xml;clarind-uds:poldilemma-5946;hdl:11858/00-246C-0000-0023-8D2A-0;XVIII. 146;XVIII. 146;pol;lat;http://dlibra.bibliotekaelblaska.pl/Content/5946;oai:dlibra.bibliotekaelblaska.pl:publication:6373;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d34b9db8-e8bf-5be0-b443-14ddd26fdd46",
-    "notes": [
-        "Na karcie przedtytu\u0142owej odr\u0119czne \u0142aci\u0144skie zapiski . Za kart\u0105 tytu\u0142ow\u0105 widniej\u0105 cytaty \u0142aci\u0144skie oraz pozwolenie i aprobata na wydruk owego dzie\u0142a, wystawione 20 listopada 1744 r. w Krakowie i zatwierdzaj\u0105ce druk do publikacji przez doktora, profesora, kanonika katedry krakowskiej ks. Macieja Zi\u0119tkiewicza. Podr\u0119cznik do nauk chrze\u015bcija\u0144skich (katechizm) oparty na zadawaniu pyta\u0144 oraz odpowiedziach m. in. : pytanie: Kt\u00f3ra rzecz jest najgorsza na tym \u015bwiecie ? odp. : grzech etc. Starodruk wsp\u00f3\u0142oprawny : XVIII. 146 adl. 1-2 (adl. 2 - \"Przewodnik na drog\u0119 wiecznosci dla du\u00df ludzkich\u2026\"), wydany w drukarni Dominika Wojciecha Siarkowskiego, w formacie 4\u00b0. Oprawa zniszczona.",
-        "Auf dem Vortitelblatt handgeschriebene lateinische Notizen. Auf dem n\u00e4chsten Blatt lateinische Spr\u00fcche und Zulassung des Werkes zum Druck vom Professor Dr. Kanoniker der Wawelkathedrale Maciej Zi\u0119tkiewicz. Das Handbuch zur christlichen Lehre (Katechismus) mit Fragen und Antworten (z. B. \u201e-Was ist am schlimmsten auf der ganzen Welt?\u201c \u201eS\u00fcnde\u201c. Das zusammen eingebundene Druckerzeugnis: XVIII. 146 adl. 1-2 (adl. 2 - \"Przewodnik na drog\u0119 wieczno\u015bci dla du\u00df ludzkich\u2026\"), in der Druckerei von Dominik Wojciech Siarkowski, im Buchformat 4\u00ba. Besch\u00e4digter Einband."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-5946"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "modlitewnik katolicki"
-        },
-        {
-            "name": "modlitewnik katolicki"
-        },
-        {
-            "name": "katholisches Gebetbuch"
-        },
-        {
-            "name": "christliche Lehre - Handbuch"
-        }
-    ],
-    "title": [
-        "Chleb duchowny, wszystkim chrze\u015bcianom na posi\u0142ek w drodze, do Nieba id\u0105cym, wystawiony albo raczey katechizm\u2026",
-        "Chleb duchowny, wszystkim chrze\u015bcianom na posi\u0142ek w drodze, do Nieba id\u0105cym, wystawiony albo raczey katechizm\u2026"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d3687ae9-450f-5fad-8b61-6d6c6390b1cc.json b/oaitestdata/clarin-oai_dc/SET_1/json/d3687ae9-450f-5fad-8b61-6d6c6390b1cc.json
deleted file mode 100644
index 0dd1298d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d3687ae9-450f-5fad-8b61-6d6c6390b1cc.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "less than 512 KB"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0694",
-    "MetadataAccess": [
-        "oai:ota:oucs:0694"
-    ],
-    "PublicationTimestamp": "1320-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1320"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dante Alighieri,  1265-1321"
-    ],
-    "fulltext": "oai:ota:oucs:0694;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0694.xml;Purgatorio  / compiled by Antonio Zampolli for the Istituto di linguistica computazionale, Universit\u00c3\u00a0 di Pisa.;Dante Alighieri,  1265-1321;1320;text_and_corpus_linguistics;Poems -- Italy -- 14th century;ita;Oxford Text Archive, University of Oxford;less than 512 KB;Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d3687ae9-450f-5fad-8b61-6d6c6390b1cc",
-    "oai_identifier": [
-        "oai:ota:oucs:0694"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- Italy -- th century"
-        }
-    ],
-    "title": [
-        "Purgatorio  / compiled by Antonio Zampolli for the Istituto di linguistica computazionale, Universit\u00c3\u00a0 di Pisa."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0694.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d376a814-69ab-543d-8a82-86956c718a80.json b/oaitestdata/clarin-oai_dc/SET_1/json/d376a814-69ab-543d-8a82-86956c718a80.json
deleted file mode 100644
index 6beeb201..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d376a814-69ab-543d-8a82-86956c718a80.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Institute of Philosophy and Sociology of the University of Latvia"
-    ],
-    "Contributor": [
-        "Zirn\u012bte, M\u0101ra"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Latvian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-902",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-902"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-902",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institute of Philosophy and Sociology of the University of Latvia"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Latvia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-902;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Lifestory Archive (lifestories data base);Zirn\u012bte, M\u0101ra;The lifestory is a source for qualitative research. The most basic component of the collection is the written or recorded document of personal history, a short or lengthy story of a person's life and observations. National Oral History Project (Nacion\u0101l\u0101s mutv\u0101rdu v\u0113stures projekts (NMV)) has been financed by the Science Council of Latvia (Latvijas Zin\u0101tnes Padome) since 1992. Its approach is multidisciplinary, employing sociological and philosophical theories in particular.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-902;lav;downloadable_files_count: 0;Latvia;Institute of Philosophy and Sociology of the University of Latvia;http://www.dzivesstasts.lv/en/Dzivesstasts.htm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d376a814-69ab-543d-8a82-86956c718a80",
-    "notes": [
-        "The lifestory is a source for qualitative research. The most basic component of the collection is the written or recorded document of personal history, a short or lengthy story of a person's life and observations. National Oral History Project (Nacion\u0101l\u0101s mutv\u0101rdu v\u0113stures projekts (NMV)) has been financed by the Science Council of Latvia (Latvijas Zin\u0101tnes Padome) since 1992. Its approach is multidisciplinary, employing sociological and philosophical theories in particular."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-902"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Lifestory Archive (lifestories data base)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d3817808-bf74-5104-afd4-2c2da8b0705f.json b/oaitestdata/clarin-oai_dc/SET_1/json/d3817808-bf74-5104-afd4-2c2da8b0705f.json
deleted file mode 100644
index dfbe7e03..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d3817808-bf74-5104-afd4-2c2da8b0705f.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-C6D1-9",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-C6D1-9"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-C6D1-9",
-    "PublicationTimestamp": "2009-01-19T11:59:59Z",
-    "PublicationYear": [
-        "2009"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Haji\u010d, Jan",
-        "Stra\u0148\u00e1k, Pavel",
-        "\u0160t\u011bp\u00e1nek, Jan"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-C6D1-9;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;CoNLL 2009 Shared Task - Czech Data;Haji\u010d, Jan;Stra\u0148\u00e1k, Pavel;\u0160t\u011bp\u00e1nek, Jan;conll-st;treebank;Czech data - both train and test+eval sets, as well as the valency dictionary - for the CoNLL 2009 Shared Task. Documentation is included. The data are generated from PDT 2.0. LDC catalog number: LDC2009E34B;2009-01-19;corpus;LDC2009E34B, LDC2009E35B;http://www.aclweb.org/anthology/W09-1201;http://hdl.handle.net/11858/00-097C-0000-0001-C6D1-9;ces;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d3817808-bf74-5104-afd4-2c2da8b0705f",
-    "notes": [
-        "Czech data - both train and test+eval sets, as well as the valency dictionary - for the CoNLL 2009 Shared Task. Documentation is included. The data are generated from PDT 2.0. LDC catalog number: LDC2009E34B"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-C6D1-9"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "conll-st"
-        },
-        {
-            "name": "treebank"
-        }
-    ],
-    "title": [
-        "CoNLL 2009 Shared Task - Czech Data"
-    ],
-    "url": "http://www.aclweb.org/anthology/W09-1201"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d39a8fae-15cb-5d35-bdce-786d1e946c6a.json b/oaitestdata/clarin-oai_dc/SET_1/json/d39a8fae-15cb-5d35-bdce-786d1e946c6a.json
deleted file mode 100644
index 6661b63f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d39a8fae-15cb-5d35-bdce-786d1e946c6a.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 50.1 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0579",
-    "MetadataAccess": [
-        "oai:ota:oucs:0579"
-    ],
-    "PublicationYear": [
-        "731"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Patristic texts -- England -- 6th-10th century period"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Bede, the Venerable, Saint, 673-735"
-    ],
-    "fulltext": "oai:ota:oucs:0579;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0579.xml;Vita Cuthberti / Bede;Bede, the Venerable, Saint, 673-735;731;text_and_corpus_linguistics;Biographies -- England -- 6th-10th century period;lat;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 50.1 KB);Text;Patristic texts -- England -- 6th-10th century period;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d39a8fae-15cb-5d35-bdce-786d1e946c6a",
-    "oai_identifier": [
-        "oai:ota:oucs:0579"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Biographies -- England -- th-th century period"
-        }
-    ],
-    "title": [
-        "Vita Cuthberti / Bede"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0579.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d3c5dbeb-8646-5442-9b3c-edc08012ac98.json b/oaitestdata/clarin-oai_dc/SET_1/json/d3c5dbeb-8646-5442-9b3c-edc08012ac98.json
deleted file mode 100644
index f75f8d13..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d3c5dbeb-8646-5442-9b3c-edc08012ac98.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Kaczkowski"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/103",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/103"
-    ],
-    "PID": "http://hdl.handle.net/11321/103",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Kaczkowski"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Kaczkowski, Kaczkowski"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/103;2015-04-08T14:05:57Z;hdl_11321_3;hdl_11321_4;MWE Kaczkowski, Gr\u00f3b Nieczui, Tom 1;Kaczkowski, Kaczkowski;Kaczkowski;2015-04-08;corpus;http://hdl.handle.net/11321/103;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain; charset=utf-8;downloadable_files_count: 1;Kaczkowski",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d3c5dbeb-8646-5442-9b3c-edc08012ac98",
-    "notes": [
-        "Kaczkowski"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/103"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Kaczkowski, Gr\u00f3b Nieczui, Tom 1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d3c970d0-eca4-5bdb-a299-8f91386f6f63.json b/oaitestdata/clarin-oai_dc/SET_1/json/d3c970d0-eca4-5bdb-a299-8f91386f6f63.json
deleted file mode 100644
index 2e189910..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d3c970d0-eca4-5bdb-a299-8f91386f6f63.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Serbian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1178",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1178"
-    ],
-    "PID": "http://hdl.handle.net/11356/1178",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "http://www.informatica.si/index.php/informatica/article/view/985"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Ljube\u0161i\u0107, Nikola"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1178;2018-02-14T11:39:19Z;hdl_11356_1023;hdl_11356_1024;Automatically constructed multiword lexicon srMWELex v0.5;Ljube\u0161i\u0107, Nikola;multiword expressions;collocations;The srMWELex lexicon is an automatically constructed lexicon of Serbian multiword expression candidates (mostly collocations) from the parsed srWaC 1.0 corpus by using the DepMWEx [depmueks] tool (https://github.com/nljubesi/depmwex). The tool extracts MWE candidates from parse trees by applying tree patterns and ranking by occurrence statistics.;2015;lexicalConceptualResource;http://hdl.handle.net/11356/1178;srp;http://www.informatica.si/index.php/informatica/article/view/985;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Jo\u017eef Stefan Institute;http://nlp.ffzg.hr/resources/lexicons/srmwelex/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d3c970d0-eca4-5bdb-a299-8f91386f6f63",
-    "notes": [
-        "The srMWELex lexicon is an automatically constructed lexicon of Serbian multiword expression candidates (mostly collocations) from the parsed srWaC 1.0 corpus by using the DepMWEx [depmueks] tool (https://github.com/nljubesi/depmwex). The tool extracts MWE candidates from parse trees by applying tree patterns and ranking by occurrence statistics."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1178"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "multiword expressions"
-        },
-        {
-            "name": "collocations"
-        }
-    ],
-    "title": [
-        "Automatically constructed multiword lexicon srMWELex v0.5"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d3dc1c41-6571-5075-b45d-a7eed6171173.json b/oaitestdata/clarin-oai_dc/SET_1/json/d3dc1c41-6571-5075-b45d-a7eed6171173.json
deleted file mode 100644
index 9adfef42..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d3dc1c41-6571-5075-b45d-a7eed6171173.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Humanities and Social Sciences, University of Zagreb"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Serbian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1073",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1073"
-    ],
-    "PID": "http://hdl.handle.net/11356/1073",
-    "PublicationTimestamp": "2016-09-19T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Faculty of Humanities and Social Sciences, University of Zagreb"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/324414",
-        "http://www.lrec-conf.org/proceedings/lrec2016/summaries/340.html",
-        "http://hdl.handle.net/11356/1066"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "GNU General Public Licence, version 3",
-        "PUB",
-        "http://opensource.org/licenses/GPL-3.0"
-    ],
-    "author": [
-        "Boras, Damir",
-        "Klubi\u010dka, Filip",
-        "Ljube\u0161i\u0107, Nikola"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1073;2018-08-13T20:17:40Z;hdl_11356_1023;hdl_11356_1024;Inflectional lexicon srLex 1.2;Ljube\u0161i\u0107, Nikola;Klubi\u010dka, Filip;Boras, Damir;morphology;inflection;srLex is a large inflectional lexicon of Serbian language where each entry consists of a (wordform, lemma, MSD, frequency, per-million frequency) 5-tuple. The (wordform, lemma, MSD) triple frequencies are calculated on the srWaC v1.2 corpus. The MSD tagset follows the MULTEXT-East V5 tagset for Bosnian available at http://nl.ijs.si/ME/V5/msd/html/msd-bs.html.;2016-09-19;lexicalConceptualResource;http://hdl.handle.net/11356/1073;srp;info:eu-repo/grantAgreement/EC/FP7/324414;http://www.lrec-conf.org/proceedings/lrec2016/summaries/340.html;http://hdl.handle.net/11356/1066;GNU General Public Licence, version 3;PUB;http://opensource.org/licenses/GPL-3.0;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Faculty of Humanities and Social Sciences, University of Zagreb",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d3dc1c41-6571-5075-b45d-a7eed6171173",
-    "notes": [
-        "srLex is a large inflectional lexicon of Serbian language where each entry consists of a (wordform, lemma, MSD, frequency, per-million frequency) 5-tuple. The (wordform, lemma, MSD) triple frequencies are calculated on the srWaC v1.2 corpus. The MSD tagset follows the MULTEXT-East V5 tagset for Bosnian available at http://nl.ijs.si/ME/V5/msd/html/msd-bs.html."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1073"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "inflection"
-        }
-    ],
-    "title": [
-        "Inflectional lexicon srLex 1.2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d3e2296c-8b30-5b67-b4c8-07c10864197b.json b/oaitestdata/clarin-oai_dc/SET_1/json/d3e2296c-8b30-5b67-b4c8-07c10864197b.json
deleted file mode 100644
index 2f4354ea..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d3e2296c-8b30-5b67-b4c8-07c10864197b.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Real Academia Espa\u00f1ola"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/tei+xml",
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-895",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-895"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-895",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Real Academia Espa\u00f1ola"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-895;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;El Corpus de referencia del espa\u00f1ol actual (CREA);Written and spoken (10%) material from 1975-2004. About 160 mwd;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-895;spa;application/tei+xml;downloadable_files_count: 0;Spain;Real Academia Espa\u00f1ola;http://www.rae.es/rae/gestores/gespub000019.nsf/voTodosporId/B104F9F0D0029604C1257164004032BE?OpenDocument&i=1",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d3e2296c-8b30-5b67-b4c8-07c10864197b",
-    "notes": [
-        "Written and spoken (10%) material from 1975-2004. About 160 mwd"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-895"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "El Corpus de referencia del espa\u00f1ol actual (CREA)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d3f2a343-401b-51b8-92d0-b3445f148bac.json b/oaitestdata/clarin-oai_dc/SET_1/json/d3f2a343-401b-51b8-92d0-b3445f148bac.json
deleted file mode 100644
index 7c2e3d97..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d3f2a343-401b-51b8-92d0-b3445f148bac.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "The National Library of Sweden"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/18",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/18"
-    ],
-    "PID": "http://hdl.handle.net/10794/18",
-    "PublicationTimestamp": "2015-04-23T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "The National Library of Sweden"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/18;2017-10-27T16:45:13Z;hdl_10794_1;hdl_10794_2;Aftonbladet 1840's (2017-10-16);Aftonbladet 1840-talet (2017-10-16);n/a, n/a;Swedish;News;A corpus with texts from Aftonbladet in the 1840's.;En korpus med texter fr\u00e5n Aftonbladet p\u00e5 1840-talet.;2015-04-23;corpus;http://hdl.handle.net/10794/18;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;The National Library of Sweden;https://spraakbanken.gu.se/swe/resurs/kubhist-aftonbladet-1840",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d3f2a343-401b-51b8-92d0-b3445f148bac",
-    "notes": [
-        "A corpus with texts from Aftonbladet in the 1840's.",
-        "En korpus med texter fr\u00e5n Aftonbladet p\u00e5 1840-talet."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/18"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "News"
-        }
-    ],
-    "title": [
-        "Aftonbladet 1840's (2017-10-16)",
-        "Aftonbladet 1840-talet (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d411d299-c317-5d38-96c7-cf7972f59392.json b/oaitestdata/clarin-oai_dc/SET_1/json/d411d299-c317-5d38-96c7-cf7972f59392.json
deleted file mode 100644
index 28e16107..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d411d299-c317-5d38-96c7-cf7972f59392.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "The Danish Language Council",
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml",
-        "text/plain; charset=utf-8",
-        "text/plain",
-        "application/zip",
-        "downloadable_files_count: 12",
-        "application/pdf"
-    ],
-    "Language": [
-        "Danish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repository.clarin.dk:20.500.12115/16",
-    "MetadataAccess": [
-        "oai:repository.clarin.dk:20.500.12115/16"
-    ],
-    "PID": "http://hdl.handle.net/20.500.12115/16",
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "The Danish Language Council",
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN-ACA-NC",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NC=1&NORED=1",
-        "ACA"
-    ],
-    "author": [
-        "Hansen, Dorte Haltrup",
-        "Braasch, Anna",
-        "Olsen, Sussi",
-        "Jakob, Halskov"
-    ],
-    "fulltext": "oai:repository.clarin.dk:20.500.12115/16;2018-06-28T13:25:58Z;hdl_20.500.12115_1;hdl_20.500.12115_3;DK-CLARIN LSP Corpus - Nanotechnology domain;Olsen, Sussi;Braasch, Anna;Jakob, Halskov;Hansen, Dorte Haltrup;Nanotechnology;Texts in the Nanotechnology domain come from iNano (Interdisciplinary Nanoscience Center, AU), Nano (DTU), Niels Bohr Institutet, Forskningscenter Ris\u00f8, Ministeriet for Sundhed og Forebyggelse (via DTU), Milj\u00f8styrelsen, Aktuel Naturvidenskab and have been collected in the DK-CLARIN project, WP2.2, 2008 - 2011. \r\nThe corpus consists of 358,144 words in 157 files. \r\nCommunicative setting/Number of files: expert->advanced (13) expert->basic (144)\r\nAll texts are in XML TEIP5 format (TEIP5DKCLARIN-format), with tokenisation, sentence and paragrapgsegmentation, pos-tagging, lemmatisation and termhood annotation placed in separate text external spangroups. \r\n\"DK-CLARIN LSP Corpus - Nanotechnology domain\" is a part of the Danish DK-CLARIN LSP corpus consisting of seven sub-corpora from following subject domains: Agriculture, Construction, Economics, Environment, Health, IT and Nanotechnology.;2011;corpus;http://hdl.handle.net/20.500.12115/16;dan;CLARIN-ACA-NC;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NC=1&NORED=1;ACA;text/plain; charset=utf-8;application/zip;application/zip;application/zip;application/zip;application/zip;text/plain;application/pdf;application/pdf;application/pdf;text/xml;text/xml;text/xml;downloadable_files_count: 12;Centre for Language Technology, NorS, University of Copenhagen;The Danish Language Council",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d411d299-c317-5d38-96c7-cf7972f59392",
-    "notes": [
-        "Texts in the Nanotechnology domain come from iNano (Interdisciplinary Nanoscience Center, AU), Nano (DTU), Niels Bohr Institutet, Forskningscenter Ris\u00f8, Ministeriet for Sundhed og Forebyggelse (via DTU), Milj\u00f8styrelsen, Aktuel Naturvidenskab and have been collected in the DK-CLARIN project, WP2.2, 2008 - 2011. \r\nThe corpus consists of 358,144 words in 157 files. \r\nCommunicative setting/Number of files: expert->advanced (13) expert->basic (144)\r\nAll texts are in XML TEIP5 format (TEIP5DKCLARIN-format), with tokenisation, sentence and paragrapgsegmentation, pos-tagging, lemmatisation and termhood annotation placed in separate text external spangroups. \r\n\"DK-CLARIN LSP Corpus - Nanotechnology domain\" is a part of the Danish DK-CLARIN LSP corpus consisting of seven sub-corpora from following subject domains: Agriculture, Construction, Economics, Environment, Health, IT and Nanotechnology."
-    ],
-    "oai_identifier": [
-        "oai:repository.clarin.dk:20.500.12115/16"
-    ],
-    "oai_set": [
-        "hdl_20.500.12115_1",
-        "hdl_20.500.12115_3"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Nanotechnology"
-        }
-    ],
-    "title": [
-        "DK-CLARIN LSP Corpus - Nanotechnology domain"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d42b5009-e3f8-5d13-aeda-1be3fa45274e.json b/oaitestdata/clarin-oai_dc/SET_1/json/d42b5009-e3f8-5d13-aeda-1be3fa45274e.json
deleted file mode 100644
index 96ed871e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d42b5009-e3f8-5d13-aeda-1be3fa45274e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3552",
-    "MetadataAccess": [
-        "oai:ota:oucs:3552"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Churchill, Charles, 1731-1764."
-    ],
-    "fulltext": "oai:ota:oucs:3552;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3552.xml;The ghost: By the author.;Churchill, Charles, 1731-1764.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d42b5009-e3f8-5d13-aeda-1be3fa45274e",
-    "oai_identifier": [
-        "oai:ota:oucs:3552"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The ghost: By the author."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3552.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d42efbbc-8b56-5c78-917b-1ff9783c3d13.json b/oaitestdata/clarin-oai_dc/SET_1/json/d42efbbc-8b56-5c78-917b-1ff9783c3d13.json
deleted file mode 100644
index dfa78a44..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d42efbbc-8b56-5c78-917b-1ff9783c3d13.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Fondazione Bruno Kessler, Trento, Italy"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2483",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2483"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2483",
-    "PublicationTimestamp": "2017-10-16T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Fondazione Bruno Kessler, Trento, Italy"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/H2020/645452"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "AGREEMENT ON THE USE OF DATA IN QT21 APE Task",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21",
-        "PUB"
-    ],
-    "author": [
-        "Turchi, Marco",
-        "Chatterjee, Rajen",
-        "Negri, Matteo"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2483;2017-10-17T07:48:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;APE Shared Task WMT17: Human Post-edits Test Data EN-DE;Turchi, Marco;Chatterjee, Rajen;Negri, Matteo;machine translation;human post-edits;shared task;automatic post-editing;post-editing;Human post-edited test sentences for the WMT 2017 Automatic post-editing task. This consists in 2,000 German sentences belonging to the IT domain and already tokenized. Source and target segments can be downloaded from: https://lindat.mff.cuni.cz/repository/xmlui/handle/11372/LRT-2133. All data is provided by the EU project QT21 (http://www.qt21.eu/).;2017-10-16;corpus;http://hdl.handle.net/11372/LRT-2483;deu;info:eu-repo/grantAgreement/EC/H2020/645452;AGREEMENT ON THE USE OF DATA IN QT21 APE Task;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21;PUB;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;Fondazione Bruno Kessler, Trento, Italy;http://www.statmt.org/wmt17/ape-task.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d42efbbc-8b56-5c78-917b-1ff9783c3d13",
-    "notes": [
-        "Human post-edited test sentences for the WMT 2017 Automatic post-editing task. This consists in 2,000 German sentences belonging to the IT domain and already tokenized. Source and target segments can be downloaded from: https://lindat.mff.cuni.cz/repository/xmlui/handle/11372/LRT-2133. All data is provided by the EU project QT21 (http://www.qt21.eu/)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2483"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "human post-edits"
-        },
-        {
-            "name": "shared task"
-        },
-        {
-            "name": "automatic post-editing"
-        },
-        {
-            "name": "post-editing"
-        }
-    ],
-    "title": [
-        "APE Shared Task WMT17: Human Post-edits Test Data EN-DE"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d4345dcc-816f-5a7f-a819-e57514080cba.json b/oaitestdata/clarin-oai_dc/SET_1/json/d4345dcc-816f-5a7f-a819-e57514080cba.json
deleted file mode 100644
index f353ff0e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d4345dcc-816f-5a7f-a819-e57514080cba.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4544",
-    "MetadataAccess": [
-        "oai:ota:oucs:4544"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Chetwood, W. R. (William Rufus), d. 1766."
-    ],
-    "fulltext": "oai:ota:oucs:4544;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4544.xml;The voyages, travels and adventures, of William Owen Gwin Vaughan, Esq: With the history of his brother Jonathan Vaughan, six years a slave in Tunis. Intermix'd with the histories of Clerimont, Maria, Eleanora, and others. ... [pt.1];Chetwood, W. R. (William Rufus), d. 1766.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d4345dcc-816f-5a7f-a819-e57514080cba",
-    "oai_identifier": [
-        "oai:ota:oucs:4544"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The voyages, travels and adventures, of William Owen Gwin Vaughan, Esq: With the history of his brother Jonathan Vaughan, six years a slave in Tunis. Intermix'd with the histories of Clerimont, Maria, Eleanora, and others. ... [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4544.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d43fe95f-676c-5e5b-bf29-33eecb770e51.json b/oaitestdata/clarin-oai_dc/SET_1/json/d43fe95f-676c-5e5b-bf29-33eecb770e51.json
deleted file mode 100644
index a7a962b7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d43fe95f-676c-5e5b-bf29-33eecb770e51.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5407",
-    "MetadataAccess": [
-        "oai:ota:oucs:5407"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Colman, George, 1732-1794."
-    ],
-    "fulltext": "oai:ota:oucs:5407;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5407.xml;The connoisseur: By Mr. Town, critic and censor-general. ... [pt.1];Colman, George, 1732-1794.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d43fe95f-676c-5e5b-bf29-33eecb770e51",
-    "oai_identifier": [
-        "oai:ota:oucs:5407"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The connoisseur: By Mr. Town, critic and censor-general. ... [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5407.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d443ab7f-0394-5d3a-9f6f-ff0a2e598e1b.json b/oaitestdata/clarin-oai_dc/SET_1/json/d443ab7f-0394-5d3a-9f6f-ff0a2e598e1b.json
deleted file mode 100644
index f280cd5b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d443ab7f-0394-5d3a-9f6f-ff0a2e598e1b.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Matteo Grella"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2625",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2625"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2625",
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Matteo Grella"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Grella, Matteo"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2625;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;English Dictionary;Grella, Matteo;morphological dictionary;This resource is an alpha version of an English morphological dictionary which includes content and function words, encoded in a JSON Lines format text file. It contains correspondences between surface form and lexical forms of words followed by some standard grammatical features.;2014;corpus;http://hdl.handle.net/11234/1-2625;eng;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;Matteo Grella",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d443ab7f-0394-5d3a-9f6f-ff0a2e598e1b",
-    "notes": [
-        "This resource is an alpha version of an English morphological dictionary which includes content and function words, encoded in a JSON Lines format text file. It contains correspondences between surface form and lexical forms of words followed by some standard grammatical features."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2625"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphological dictionary"
-        }
-    ],
-    "title": [
-        "English Dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d44bf097-4b34-5244-aa7e-a69ac77087de.json b/oaitestdata/clarin-oai_dc/SET_1/json/d44bf097-4b34-5244-aa7e-a69ac77087de.json
deleted file mode 100644
index 74d51263..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d44bf097-4b34-5244-aa7e-a69ac77087de.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 19",
-        "application/zip",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/62",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/62"
-    ],
-    "PID": "http://hdl.handle.net/11321/62",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Koco\u0144, Jan"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/62;2016-01-26T11:09:17Z;hdl_11321_3;hdl_11321_4;Sample workshop corpus;Koco\u0144, Jan;Sample workshop corpus.;2015-04-08;corpus;http://hdl.handle.net/11321/62;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 19;Wroc\u0142aw University of Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d44bf097-4b34-5244-aa7e-a69ac77087de",
-    "notes": [
-        "Sample workshop corpus."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/62"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Sample workshop corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d455ec1e-50b6-5fa6-9942-3b199824bc06.json b/oaitestdata/clarin-oai_dc/SET_1/json/d455ec1e-50b6-5fa6-9942-3b199824bc06.json
deleted file mode 100644
index 9e110fa4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d455ec1e-50b6-5fa6-9942-3b199824bc06.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "University of Helsinki"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-753",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-753"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-753",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Helsinki"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Finland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-753;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Parsed Corpus of Early English Correspondence (PCEEC);Linguistically annotated corpus of English correspondence between the years 1410?-1681, compiled for historical sociolinguistic research.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-753;eng;text/plain;downloadable_files_count: 0;Finland;University of Helsinki;http://ota.ahds.ac.uk/headers/2510.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d455ec1e-50b6-5fa6-9942-3b199824bc06",
-    "notes": [
-        "Linguistically annotated corpus of English correspondence between the years 1410?-1681, compiled for historical sociolinguistic research."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-753"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Parsed Corpus of Early English Correspondence (PCEEC)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d4787cb0-332d-54bd-8973-a75d8aa4a12f.json b/oaitestdata/clarin-oai_dc/SET_1/json/d4787cb0-332d-54bd-8973-a75d8aa4a12f.json
deleted file mode 100644
index 9cccfed8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d4787cb0-332d-54bd-8973-a75d8aa4a12f.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Institute of Slavic Studies, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 214",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish",
-        "Lithuanian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/539",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/539"
-    ],
-    "PID": "http://hdl.handle.net/11321/539",
-    "PublicationTimestamp": "2018-07-21T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Institute of Slavic Studies, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "IS PAS corpora license",
-        "http://clarin-pl.eu/en/licenses/is-pas-corpora-license/",
-        "CC"
-    ],
-    "author": [
-        "Roszko, Danuta",
-        "Roszko, Roman"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/539;2018-07-22T11:27:14Z;hdl_11321_3;hdl_11321_4;Polish-Lithuanian Parallel Corpus \"2\";Roszko, Roman;Roszko, Danuta;Polish;Lithuanian;Parallel Corpora;New upgraded version of the Polish-Lithuanian Parallel Corpus (http://hdl.handle.net/11321/309) with extra files and features (Including General, Medical, Technical, Legal, Business Terms \u2026 and Slang Expressions). The Polish-Lithuanian Parallel Corpus \"2\" contains 16 543 470 words (PL 8 697 956 + LT 7 845 514).;2018-07-21;corpus;http://hdl.handle.net/11321/539;pol;lit;IS PAS corpora license;http://clarin-pl.eu/en/licenses/is-pas-corpora-license/;CC;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 214;Institute of Slavic Studies, Polish Academy of Sciences",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d4787cb0-332d-54bd-8973-a75d8aa4a12f",
-    "notes": [
-        "New upgraded version of the Polish-Lithuanian Parallel Corpus (http://hdl.handle.net/11321/309) with extra files and features (Including General, Medical, Technical, Legal, Business Terms \u2026 and Slang Expressions). The Polish-Lithuanian Parallel Corpus \"2\" contains 16 543 470 words (PL 8 697 956 + LT 7 845 514)."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/539"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Polish"
-        },
-        {
-            "name": "Lithuanian"
-        },
-        {
-            "name": "Parallel Corpora"
-        }
-    ],
-    "title": [
-        "Polish-Lithuanian Parallel Corpus \"2\""
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d4822e2d-6d6c-5ec3-934c-f395fe662051.json b/oaitestdata/clarin-oai_dc/SET_1/json/d4822e2d-6d6c-5ec3-934c-f395fe662051.json
deleted file mode 100644
index 6cb509b8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d4822e2d-6d6c-5ec3-934c-f395fe662051.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1068",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1068"
-    ],
-    "PID": "http://hdl.handle.net/11356/1068",
-    "PublicationTimestamp": "2016-09-19T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "https://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Zupan, Katja",
-        "Ljube\u0161i\u0107, Nikola",
-        "Erjavec, Toma\u017e",
-        "Fi\u0161er, Darja"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1068;2017-01-20T13:58:56Z;hdl_11356_1023;hdl_11356_1024;Dataset of normalised Slovene text KonvNormSl 1.0;Ljube\u0161i\u0107, Nikola;Zupan, Katja;Fi\u0161er, Darja;Erjavec, Toma\u017e;word normalisation;historical language;computer-mediated communication;experimental data;manual annotation;Data used in the experiments described in:\r\n\r\nNikola Ljube\u0161i\u0107, Katja Zupan, Darja Fi\u0161er and Toma\u017e Erjavec: Normalising Slovene data: historical texts vs. user-generated content. Proceedings of KONVENS 2016, September 19\u201321, 2016, Bochum, Germany.\r\nhttps://www.linguistics.rub.de/konvens16/pub/19_konvensproc.pdf\r\n(https://www.linguistics.rub.de/konvens16/)\r\n\r\nData are split into the \"token\" folder (experiment on normalising individual tokens) and \"segment\" folder (experiment on normalising whole segments of text, i.e. sentences or tweets). Each experiment folder contains the \"train\", \"dev\" and \"test\" subfolders. Each subfolder contains two files for each sample, the original data (*.orig.txt) and the data with hand-normalised words (*.norm.txt). The files are aligned by lines.\r\n\r\nThere are four datasets:\r\n- goo300k-bohoric: historical Slovene, hard case (<1850)\r\n- goo300k-gaj: historical Slovene, easy case (1850 - 1900)\r\n- tweet-L3: Slovene tweets, hard case (non-standard language)\r\n- tweet-L1: Slovene tweets, easy case (mostly standard language)\r\n\r\nThe goo300k data come from http://hdl.handle.net/11356/1025, while the tweet data originate from the JANES project (http://nl.ijs.si/janes/english/).\r\n\r\nThe text in the files has been split by inserting spaces between characters, with underscore (_) substituting the space character. Tokens not relevant for normalisation (e.g. URLs, hashtags) have been substituted by the inverted question mark '\u00bf' character.;2016-09-19;corpus;http://hdl.handle.net/11356/1068;slv;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);https://creativecommons.org/licenses/by-sa/4.0/;PUB;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;Jo\u017eef Stefan Institute",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d4822e2d-6d6c-5ec3-934c-f395fe662051",
-    "notes": [
-        "Data used in the experiments described in:\r\n\r\nNikola Ljube\u0161i\u0107, Katja Zupan, Darja Fi\u0161er and Toma\u017e Erjavec: Normalising Slovene data: historical texts vs. user-generated content. Proceedings of KONVENS 2016, September 19\u201321, 2016, Bochum, Germany.\r\nhttps://www.linguistics.rub.de/konvens16/pub/19_konvensproc.pdf\r\n(https://www.linguistics.rub.de/konvens16/)\r\n\r\nData are split into the \"token\" folder (experiment on normalising individual tokens) and \"segment\" folder (experiment on normalising whole segments of text, i.e. sentences or tweets). Each experiment folder contains the \"train\", \"dev\" and \"test\" subfolders. Each subfolder contains two files for each sample, the original data (*.orig.txt) and the data with hand-normalised words (*.norm.txt). The files are aligned by lines.\r\n\r\nThere are four datasets:\r\n- goo300k-bohoric: historical Slovene, hard case (<1850)\r\n- goo300k-gaj: historical Slovene, easy case (1850 - 1900)\r\n- tweet-L3: Slovene tweets, hard case (non-standard language)\r\n- tweet-L1: Slovene tweets, easy case (mostly standard language)\r\n\r\nThe goo300k data come from http://hdl.handle.net/11356/1025, while the tweet data originate from the JANES project (http://nl.ijs.si/janes/english/).\r\n\r\nThe text in the files has been split by inserting spaces between characters, with underscore (_) substituting the space character. Tokens not relevant for normalisation (e.g. URLs, hashtags) have been substituted by the inverted question mark '\u00bf' character."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1068"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "word normalisation"
-        },
-        {
-            "name": "historical language"
-        },
-        {
-            "name": "computer-mediated communication"
-        },
-        {
-            "name": "experimental data"
-        },
-        {
-            "name": "manual annotation"
-        }
-    ],
-    "title": [
-        "Dataset of normalised Slovene text KonvNormSl 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d496abf3-6fff-500b-82f1-d3329ff10684.json b/oaitestdata/clarin-oai_dc/SET_1/json/d496abf3-6fff-500b-82f1-d3329ff10684.json
deleted file mode 100644
index 8f88efa3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d496abf3-6fff-500b-82f1-d3329ff10684.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "IPI PAN"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/vnd.oasis.opendocument.text",
-        "downloadable_files_count: 10",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/389",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/389"
-    ],
-    "PID": "http://hdl.handle.net/11321/389",
-    "PublicationTimestamp": "2017-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "IPI PAN"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "P\u0119dzich, Ewelina"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/389;2017-05-30T11:54:58Z;hdl_11321_3;hdl_11321_4;Test corpora;P\u0119dzich, Ewelina;test;zbi\u00f3r testowy;2017-05-30;corpus;http://hdl.handle.net/11321/389;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;text/plain;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;text/plain;downloadable_files_count: 10;IPI PAN",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d496abf3-6fff-500b-82f1-d3329ff10684",
-    "notes": [
-        "zbi\u00f3r testowy"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/389"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "test"
-        }
-    ],
-    "title": [
-        "Test corpora"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d4a1ded3-04b0-553b-9ce3-1f72a16847e5.json b/oaitestdata/clarin-oai_dc/SET_1/json/d4a1ded3-04b0-553b-9ce3-1f72a16847e5.json
deleted file mode 100644
index 5b8087c8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d4a1ded3-04b0-553b-9ce3-1f72a16847e5.json
+++ /dev/null
@@ -1,134 +0,0 @@
-{
-    "Contact": [
-        "Technische Universit\u00e4t Darmstadt"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 55",
-        "application/x-gzip",
-        "text/plain"
-    ],
-    "Language": [
-        "Afrikaans",
-        "Arabic",
-        "Bengali",
-        "Bulgarian",
-        "Czech",
-        "Danish",
-        "German",
-        "Modern Greek (1453-)",
-        "English",
-        "Estonian",
-        "Persian",
-        "Finnish",
-        "French",
-        "Gujarati",
-        "Hebrew",
-        "Hindi",
-        "Croatian",
-        "Hungarian",
-        "Indonesian",
-        "Italian",
-        "Japanese",
-        "Korean",
-        "Latvian",
-        "Lithuanian",
-        "Malayalam",
-        "Marathi",
-        "Macedonian",
-        "Nepali (macrolanguage)",
-        "Dutch",
-        "Norwegian",
-        "Polish",
-        "Portuguese",
-        "Romanian",
-        "Russian",
-        "Slovak",
-        "Slovenian",
-        "Somali",
-        "Spanish",
-        "Albanian",
-        "Swahili (macrolanguage)",
-        "Swedish",
-        "Tamil",
-        "Telugu",
-        "Tagalog",
-        "Thai",
-        "Turkish",
-        "Ukrainian",
-        "Undetermined",
-        "Urdu",
-        "Vietnamese",
-        "Chinese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2206",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2206"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2206",
-    "PublicationTimestamp": "2016-04-14T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Technische Universit\u00e4t Darmstadt"
-    ],
-    "RelatedIdentifier": [
-        "http://www.lrec-conf.org/proceedings/lrec2016/pdf/388_Paper.pdf"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "PUB",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/"
-    ],
-    "author": [
-        "Habernal, Ivan",
-        "Gurevych, Iryna",
-        "Zayed, Omnia"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2206;2019-01-02T14:30:26Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;C4Corpus (CC BY-NC-SA part);Gurevych, Iryna;Habernal, Ivan;Zayed, Omnia;CommonCrawl;Creative Commons;Web corpus;Amazon Web Services;A large web corpus (over 10 billion tokens) licensed under CreativeCommons license family in 50+ languages that has been extracted from CommonCrawl, the largest publicly available general Web crawl to date with about 2 billion crawled URLs.;2016-04-14;corpus;http://hdl.handle.net/11372/LRT-2206;afr;ara;ben;bul;ces;dan;deu;ell;eng;est;fas;fin;fra;guj;heb;hin;hrv;hun;ind;ita;jpn;kor;lav;lit;mal;mar;mkd;nep;nld;nor;pol;por;ron;rus;slk;slv;som;spa;sqi;swa;swe;tam;tel;tgl;tha;tur;ukr;und;urd;vie;zho;http://www.lrec-conf.org/proceedings/lrec2016/pdf/388_Paper.pdf;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);PUB;http://creativecommons.org/licenses/by-nc-sa/4.0/;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;text/plain;downloadable_files_count: 55;Technische Universit\u00e4t Darmstadt;https://dkpro.github.io/dkpro-c4corpus/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d4a1ded3-04b0-553b-9ce3-1f72a16847e5",
-    "notes": [
-        "A large web corpus (over 10 billion tokens) licensed under CreativeCommons license family in 50+ languages that has been extracted from CommonCrawl, the largest publicly available general Web crawl to date with about 2 billion crawled URLs."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2206"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "CommonCrawl"
-        },
-        {
-            "name": "Creative Commons"
-        },
-        {
-            "name": "Web corpus"
-        },
-        {
-            "name": "Amazon Web Services"
-        }
-    ],
-    "title": [
-        "C4Corpus (CC BY-NC-SA part)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d4ac176e-96a7-5c43-b5b9-a4899acbcf76.json b/oaitestdata/clarin-oai_dc/SET_1/json/d4ac176e-96a7-5c43-b5b9-a4899acbcf76.json
deleted file mode 100644
index 6b531815..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d4ac176e-96a7-5c43-b5b9-a4899acbcf76.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "A"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1728",
-    "MetadataAccess": [
-        "oai:ota:oucs:1728"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Montgomery, Lucy Maud"
-    ],
-    "fulltext": "oai:ota:oucs:1728;2018-05-17T09:29:11Z;http://ota.ox.ac.uk/headers/1728.xml;Anne of the island;Montgomery, Lucy Maud;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;A;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d4ac176e-96a7-5c43-b5b9-a4899acbcf76",
-    "oai_identifier": [
-        "oai:ota:oucs:1728"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Anne of the island"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1728.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d4aefd6e-7236-5e52-9102-5ca090f8c168.json b/oaitestdata/clarin-oai_dc/SET_1/json/d4aefd6e-7236-5e52-9102-5ca090f8c168.json
deleted file mode 100644
index 91f60346..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d4aefd6e-7236-5e52-9102-5ca090f8c168.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 42.3 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0065",
-    "MetadataAccess": [
-        "oai:ota:oucs:0065"
-    ],
-    "PublicationTimestamp": "1747-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1747"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gray, Thomas, 1716-1771"
-    ],
-    "fulltext": "oai:ota:oucs:0065;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0065.xml;Poems. Selections;Ode on the spring ; Ode on the death of a favourite cat ; Ode on a distant prospect of Eton College ...;Gray, Thomas, 1716-1771;1747-1777;text_and_corpus_linguistics;Poems -- Great Britain -- 18th century;eng;Oxford Text Archive, University of Oxford;(1 file : ca. 42.3 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d4aefd6e-7236-5e52-9102-5ca090f8c168",
-    "oai_identifier": [
-        "oai:ota:oucs:0065"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Poems. Selections",
-        "Ode on the spring ; Ode on the death of a favourite cat ; Ode on a distant prospect of Eton College ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0065.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d4cd8a60-55f3-543e-a77d-03991cf9ad55.json b/oaitestdata/clarin-oai_dc/SET_1/json/d4cd8a60-55f3-543e-a77d-03991cf9ad55.json
deleted file mode 100644
index 5ebc8843..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d4cd8a60-55f3-543e-a77d-03991cf9ad55.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "Universit\u00e4t des Saarlandes"
-    ],
-    "Contributor": [
-        "Jos\u00e9 Manuel Mart\u00ednez Mart\u00ednez",
-        "Mercedes Garc\u00eda Ferrer",
-        "Maria Teresa Beltr\u00e1n Chabrera",
-        "Mar\u00eda Teresa Cases Fandos"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml"
-    ],
-    "Language": [
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=\"\"\"oai:fedora.clarin-d.uni-saarland.de:clarind-uds:clarelatin\"\"\"",
-    "MetadataAccess": [
-        "\"\"\"oai:fedora.clarin-d.uni-saarland.de:clarind-uds:clarelatin\"\"\""
-    ],
-    "PID": "http://hdl.handle.net/21.11119/0000-0001-614D-C",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Universit\u00e4t des Saarlandes"
-    ],
-    "RelatedIdentifier": [
-        "Tagset: http://www.cis.uni-muenchen.de/~schmid/tools/TreeTagger/data/Lamap-Tagset.pdf"
-    ],
-    "ResourceType": [
-        "Collection"
-    ],
-    "Rights": [
-        "Copyrighted"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Galatea Team"
-    ],
-    "fulltext": "\"\"\"oai:fedora.clarin-d.uni-saarland.de:clarind-uds:clarelatin\"\"\";2018-04-27T13:30:15Z;CLARE;Galatea Team;corpus linguistics;linguistics;Latin;written language;This corpus offers a continuum of different text types (registers) from written discourse. More precisely, it includes Latin texts from 20 different registers of written discourse including apology, biography, comedy, didactic, doctrinal, epic, epistolary, essay, fable, history, legislative, lyric, mythology, novel, oratory, philosophy, satire, tragedy.\n  The texts are imported from different Latin libraries on the Web.\n  The whole number of words contained in the corpus comprise ca. 19,5 Mio. The corpus is pre-annotated on several levels, which include information on tokens, lemmas, morpho-syntactic features (e.g. case, number, etc.), parts-of-speech, as well as and sentence boundaries. Tokenization, lemmatization, PoS tagging with TreeTagger (Schmid, 1994, 1995) using Gabrielle Bandolini's parameters and sentence boundary detection with CLTK (Kyle P. Johnson et al., 2014-2017).\n  The corpus is encoded in the CWB format (CWB, 2010) and can be queried with Corpus Query Processor (CQP) (Evert, 2005).;Universit\u00e4t des Saarlandes;Mercedes Garc\u00eda Ferrer;Mar\u00eda Teresa Cases Fandos;Maria Teresa Beltr\u00e1n Chabrera;Jos\u00e9 Manuel Mart\u00ednez Mart\u00ednez;2018;Collection;text/xml;clarind-uds:clarelatin;hdl:21.11119/0000-0001-614D-C;Augustana: https://www.hs-augsburg.de/~harsch/a_chron.html;Bibiloteca italiana: http://ww2.bibliotecaitaliana.it/exist/bibit/;Camena; https://www2.uni-mannheim.de/mateo/camenahtdocs/camena_e.html;Corpus corporum:  http://www.mlat.uzh.ch/MLS/index.php?lang=0;DBNL: http://www.dbnl.org/;Dante on-line: http://www.danteonline.it/italiano/opere_indice.htm;Esoteric archives: http://www.esotericarchives.com/esoteric.htm;Gitenberg: https://www.gitenberg.org/;Google Books: https://books.google.es/;Iesapos: https://iessapostol.educarex.es/latin/minerva/;Intratext: http://www.intratext.com/LATINA/;MDZ: https://www.digitale-sammlungen.de/;Narpan: http://www.narpan.net/;Perseus: http://perseus.uchicago.edu/latin.html;The Latin Library: http://www.thelatinlibrary.com/;UB: http://orbita.bib.ub.edu/llull/;Vaticanus: http://www.vatican.va/holy_father/index_sp.htm;Vicifons: https://la.wikisource.org/wiki/Pagina_prima;lat;Tagset: http://www.cis.uni-muenchen.de/~schmid/tools/TreeTagger/data/Lamap-Tagset.pdf;Spain;Copyrighted",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d4cd8a60-55f3-543e-a77d-03991cf9ad55",
-    "notes": [
-        "This corpus offers a continuum of different text types (registers) from written discourse. More precisely, it includes Latin texts from 20 different registers of written discourse including apology, biography, comedy, didactic, doctrinal, epic, epistolary, essay, fable, history, legislative, lyric, mythology, novel, oratory, philosophy, satire, tragedy.\n  The texts are imported from different Latin libraries on the Web.\n  The whole number of words contained in the corpus comprise ca. 19,5 Mio. The corpus is pre-annotated on several levels, which include information on tokens, lemmas, morpho-syntactic features (e.g. case, number, etc.), parts-of-speech, as well as and sentence boundaries. Tokenization, lemmatization, PoS tagging with TreeTagger (Schmid, 1994, 1995) using Gabrielle Bandolini's parameters and sentence boundary detection with CLTK (Kyle P. Johnson et al., 2014-2017).\n  The corpus is encoded in the CWB format (CWB, 2010) and can be queried with Corpus Query Processor (CQP) (Evert, 2005)."
-    ],
-    "oai_identifier": [
-        "\"\"\"oai:fedora.clarin-d.uni-saarland.de:clarind-uds:clarelatin\"\"\""
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus linguistics"
-        },
-        {
-            "name": "linguistics"
-        },
-        {
-            "name": "Latin"
-        },
-        {
-            "name": "written language"
-        }
-    ],
-    "title": [
-        "CLARE"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d52f0430-db38-5f29-b154-e2871a73936b.json b/oaitestdata/clarin-oai_dc/SET_1/json/d52f0430-db38-5f29-b154-e2871a73936b.json
deleted file mode 100644
index 7af696a6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d52f0430-db38-5f29-b154-e2871a73936b.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1169",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1169"
-    ],
-    "PID": "http://hdl.handle.net/11356/1169",
-    "PublicationTimestamp": "2017-11-27T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Erjavec, Toma\u017e",
-        "Perov\u0161ek, Matic",
-        "Ljube\u0161i\u0107, Nikola"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1169;2018-01-22T08:51:26Z;hdl_11356_1023;hdl_11356_1077;cSMTiser: word standardisation;Ljube\u0161i\u0107, Nikola;Perov\u0161ek, Matic;Erjavec, Toma\u017e;word normalisation;Word standardisation of non-standard language as found in user-generated content, using cSMTiser (https://github.com/clarinsi/csmtiser), a tool for text normalisation via character-level machine translation. The tool has been trained on the Janes-Norm dataset (http://hdl.handle.net/11356/1084) and background resources.;2017-11-27;toolService;http://hdl.handle.net/11356/1169;slv;application/octet-stream;downloadable_files_count: 0;Jo\u017eef Stefan Institute;https://github.com/clarinsi/csmtiser",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d52f0430-db38-5f29-b154-e2871a73936b",
-    "notes": [
-        "Word standardisation of non-standard language as found in user-generated content, using cSMTiser (https://github.com/clarinsi/csmtiser), a tool for text normalisation via character-level machine translation. The tool has been trained on the Janes-Norm dataset (http://hdl.handle.net/11356/1084) and background resources."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1169"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1077"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "word normalisation"
-        }
-    ],
-    "title": [
-        "cSMTiser: word standardisation"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d52fc848-99e3-5a6a-9c45-bad39ccea1d4.json b/oaitestdata/clarin-oai_dc/SET_1/json/d52fc848-99e3-5a6a-9c45-bad39ccea1d4.json
deleted file mode 100644
index f7102300..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d52fc848-99e3-5a6a-9c45-bad39ccea1d4.json
+++ /dev/null
@@ -1,446 +0,0 @@
-{
-    "Contact": [
-        "Universal Dependencies Consortium"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 3"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)",
-        "Arabic",
-        "Basque",
-        "Bulgarian",
-        "Croatian",
-        "Czech",
-        "Danish",
-        "Dutch",
-        "English",
-        "Estonian",
-        "Finnish",
-        "French",
-        "German",
-        "Gothic",
-        "Modern Greek (1453-)",
-        "Hebrew",
-        "Hindi",
-        "Hungarian",
-        "Indonesian",
-        "Irish",
-        "Italian",
-        "Japanese",
-        "Latin",
-        "Norwegian",
-        "Church Slavic",
-        "Persian",
-        "Polish",
-        "Portuguese",
-        "Romanian",
-        "Slovenian",
-        "Spanish",
-        "Swedish",
-        "Tamil",
-        "Catalan",
-        "Chinese",
-        "Galician",
-        "Kazakh",
-        "Latvian",
-        "Russian",
-        "Turkish",
-        "Coptic",
-        "Sanskrit",
-        "Slovak",
-        "Ukrainian",
-        "Uighur",
-        "Vietnamese",
-        "Belarusian",
-        "Korean",
-        "Lithuanian",
-        "Urdu",
-        "Northern Sami",
-        "Upper Sorbian",
-        "Afrikaans",
-        "Marathi",
-        "Serbian",
-        "Telugu",
-        "Amharic",
-        "Armenian",
-        "Breton",
-        "Faroese",
-        "Old French (842-ca. 1400)",
-        "Tagalog",
-        "Thai",
-        "Yoruba",
-        "Akkadian",
-        "Bambara",
-        "Erzya",
-        "Maltese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2895",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2895"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2895",
-    "PublicationTimestamp": "2018-11-15T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Universal Dependencies Consortium"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-2837"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Licence Universal Dependencies v2.3",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-2.3",
-        "PUB"
-    ],
-    "author": [
-        "Kirchner, Jesse",
-        "Ion, Radu",
-        "Seraji, Mojgan",
-        "Omura, Mai",
-        "Lee, John",
-        "Manning, Christopher",
-        "Cebiro\u011flu Eryi\u011fit, G\u00fcl\u015fen",
-        "Ma\u0161ek, Jan",
-        "Trukhina, Anna",
-        "Hlav\u00e1\u010dov\u00e1, Jaroslava",
-        "Passarotti, Marco",
-        "Nguy\u1ec5n Th\u1ecb, L\u01b0\u01a1ng",
-        "Zhu, Hanzhi",
-        "Villemonte de la Clergerie, Eric",
-        "Takahashi, Yuta",
-        "Basmov, Victoria",
-        "B\u00f6rstell, Carl",
-        "Macketanz, Vivien",
-        "Tellier, Isabelle",
-        "Agi\u0107, \u017deljko",
-        "Rosa, Rudolf",
-        "Zeldes, Amir",
-        "Muischnek, Kadri",
-        "Choi, Jinho",
-        "Washington, Jonathan North",
-        "Romanenko, Mykhailo",
-        "Katz, Boris",
-        "Davidson, Elizabeth",
-        "Ojala, Stina",
-        "Ure\u0161ov\u00e1, Zde\u0148ka",
-        "\u0160imkov\u00e1, M\u00e1ria",
-        "Moskalevskyi, Bohdan",
-        "Stella, Antonio",
-        "Rovati, Davide",
-        "Sawanakunanon, Yanin",
-        "Yan, Chunxiao",
-        "Wang, Jing Xian",
-        "Bank, Sebastian",
-        "Seeker, Wolfgang",
-        "Berzak, Yevgeni",
-        "Rademaker, Alexandre",
-        "Dirix, Peter",
-        "Paulino-Passos, Guilherme",
-        "Caron, Bernard",
-        "Sanguinetti, Manuela",
-        "Navarro Hor\u00f1iacek, Juan Ignacio",
-        "Cecchini, Flavio Massimiliano",
-        "Cinkov\u00e1, Silvie",
-        "Burchardt, Aljoscha",
-        "Kopacewicz, Kamil",
-        "Yu, Zhuoran",
-        "Han, Na-Rae",
-        "Simk\u00f3, Katalin",
-        "Badmaeva, Elena",
-        "Hladk\u00e1, Barbora",
-        "Bellato, Sandra",
-        "Trosterud, Trond",
-        "Krek, Simon",
-        "G\u00f6k\u0131rmak, Memduh",
-        "L\u00ea H\u1ed3ng, Ph\u01b0\u01a1ng",
-        "\u00d8vrelid, Lilja",
-        "Galbraith, Daniel",
-        "Lenci, Alessandro",
-        "Seddah, Djam\u00e9",
-        "Hwang, Jena",
-        "Ginter, Filip",
-        "Erjavec, Toma\u017e",
-        "Johannsen, Anders",
-        "Bick, Eckhard",
-        "Osenova, Petya",
-        "Mart\u00ednez Alonso, H\u00e9ctor",
-        "Larasati, Septina Dian",
-        "Kettnerov\u00e1, V\u00e1clava",
-        "Kayadelen, Tolga",
-        "Vajjala, Sowmya",
-        "Kahane, Sylvain",
-        "Lambertino, Lorenzo",
-        "Li, Josie",
-        "Haug, Dag",
-        "Rehm, Georg",
-        "Rinaldi, Larissa",
-        "Lynn, Teresa",
-        "Tanaka, Takaaki",
-        "Plank, Barbara",
-        "Sagot, Beno\u00eet",
-        "Uematsu, Sumire",
-        "Freitas, Cl\u00e1udia",
-        "Varga, Viktor",
-        "Lyashevskaya, Olga",
-        "J\u00f8rgensen, Fredrik",
-        "M\u0103r\u0103nduc, C\u0103t\u0103lina",
-        "Ka\u015f\u0131kara, H\u00fcner",
-        "Pyysalo, Sampo",
-        "Kanerva, Jenna",
-        "Arutie, Gashaw",
-        "Sz\u00e1nt\u00f3, Zsolt",
-        "\u010c\u00e9pl\u00f6, Slavom\u00edr",
-        "Chalub, Fabricio",
-        "Collomb, Aur\u00e9lie",
-        "Marheinecke, Katrin",
-        "Lim, KyungTae",
-        "Atutxa, Aitziber",
-        "Augustinus, Liesbeth",
-        "Goldberg, Yoav",
-        "Williams, Seyi",
-        "Matsumoto, Yuji",
-        "Biagetti, Erica",
-        "Dozat, Timothy",
-        "Ateyah, Luma",
-        "Przepi\u00f3rkowski, Adam",
-        "G\u00f3mez Guinovart, Xavier",
-        "M\u00fc\u00fcrisep, Kaili",
-        "Saul\u012bte, Baiba",
-        "Caron, Gauthier",
-        "Mandl, Michael",
-        "Nivre, Joakim",
-        "Prokopidis, Prokopis",
-        "Petrov, Slav",
-        "R\u00e4\u00e4bis, Andriela",
-        "Sichinava, Dmitry",
-        "Reddy, Siva",
-        "Guillaume, Bruno",
-        "Gr\u016bz\u012btis, Normunds",
-        "Cetin, Savas",
-        "Haji\u010d jr., Jan",
-        "Ephrem, Binyam",
-        "Perrier, Guy",
-        "Schneider, Nathan",
-        "Misirpashayeva, Margarita",
-        "de Marneffe, Marie-Catherine",
-        "Antonsen, Lene",
-        "Rocha, Luisa",
-        "Attia, Mohammed",
-        "Schuster, Sebastian",
-        "Missil\u00e4, Anna",
-        "Rama, Taraka",
-        "Dwivedi, Puneet",
-        "Hohle, Petter",
-        "Bhat, Irshad Ahmad",
-        "Lavrentiev, Alexei",
-        "Tyers, Francis",
-        "McDonald, Ryan",
-        "Lam, Lucia",
-        "Pretkalni\u0146a, Lauma",
-        "Farkas, Rich\u00e1rd",
-        "Moreno Romero, Laura",
-        "Soares-Bastos, Isabela",
-        "Ishola, \u1eccl\u00e1j\u00edd\u00e9",
-        "Ramasamy, Loganathan",
-        "Bosco, Cristina",
-        "Kenney, Jessica",
-        "Uszkoreit, Hans",
-        "Simionescu, Radu",
-        "Fernandez Alcalde, Hector",
-        "Eli, Marhaba",
-        "Yavrumyan, Marat M.",
-        "Barbu Mititelu, Verginica",
-        "Patejuk, Agnieszka",
-        "Ravishankar, Vinit",
-        "de Paiva, Valeria",
-        "Grioni, Matias",
-        "Real, Livy",
-        "Lertpradit, Saran",
-        "Asahara, Masayuki",
-        "Pitler, Emily",
-        "Mori, Keiko Sophie",
-        "Suhr, Alane",
-        "Zeman, Daniel",
-        "Miekka, Niko",
-        "Miyao, Yusuke",
-        "Vincze, Veronika",
-        "Kwak, Sookyoung",
-        "Cho, Yongseok",
-        "Blokland, Rogier",
-        "Bhat, Riyaz Ahmad",
-        "Garcia, Marcos",
-        "Loginova, Olga",
-        "Shimada, Atsuko",
-        "Martins, Andr\u00e9",
-        "van Niekerk, Daniel",
-        "Murawaki, Yugo",
-        "Nguy\u1ec5n Th\u1ecb Minh, Huy\u1ec1n",
-        "Nitisaroj, Rattima",
-        "Zhang, Manying",
-        "Puolakainen, Tiina",
-        "Tsarfaty, Reut",
-        "Taji, Dima",
-        "Boyd, Adriane",
-        "Goenaga, Iakes",
-        "Rituma, Laura",
-        "H\u00e0 M\u1ef9, Linh",
-        "Garza, Sebastian",
-        "Habash, Nizar",
-        "Rudina, Olga",
-        "Mori, Shinsuke",
-        "Nainwani, Pinkey",
-        "Partanen, Niko",
-        "Droganova, Kira",
-        "Li, Keying",
-        "Elkahky, Ali",
-        "Connor, Miriam",
-        "Samson, Stephanie",
-        "Mare\u010dek, David",
-        "Straka, Milan",
-        "Smith, Aaron",
-        "Banerjee, Esha",
-        "Nedoluzhko, Anna",
-        "Chun, Jayeol",
-        "Strnadov\u00e1, Jana",
-        "More, Amir",
-        "Poibeau, Thierry",
-        "Mendon\u00e7a, Gustavo",
-        "Harris, Kim",
-        "Gajdo\u0161ov\u00e1, Katar\u00edna",
-        "Spadine, Carolyn",
-        "Celano, Giuseppe G. A.",
-        "Abrams, Mitchell",
-        "Dobrovoljc, Kaja",
-        "Jel\u00ednek, Tom\u00e1\u0161",
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "Bobicev, Victoria",
-        "Popel, Martin",
-        "Laippala, Veronika",
-        "Gojenola, Koldo",
-        "Gerdes, Kim",
-        "Lando, Tatiana",
-        "Simov, Kiril",
-        "Ballesteros, Miguel",
-        "Nurmi, Hanna",
-        "Nikolaev, Vitaly",
-        "Wir\u00e9n, Mats",
-        "Perez, Cenel-Augusto",
-        "Bauer, John",
-        "Ljube\u0161i\u0107, Nikola",
-        "Woldemariam, Tsegay",
-        "Montemagni, Simonetta",
-        "Wong, Tak-sum",
-        "Ahrenberg, Lars",
-        "Rueter, Jack",
-        "Sadde, Shoval",
-        "Mititelu, C\u0103t\u0103lin",
-        "Ne\u0161pore-B\u0113rzkalne, Gunta",
-        "Simi, Maria",
-        "Diaz de Ilarraza, Arantza",
-        "Etienne, Aline",
-        "Aranzabe, Maria Jesus",
-        "Li, Cheuk Ying",
-        "Makazhanov, Aibek",
-        "Candito, Marie",
-        "Shen, Mo",
-        "Saleh, Shadi",
-        "Irimia, Elena",
-        "Bengoetxea, Kepa",
-        "Peng, Siyao",
-        "Aplonova, Katya",
-        "Dickerson, Carly",
-        "Shohibussirri, Muh",
-        "Ro\u0219ca, Valentin",
-        "van Noord, Gertjan",
-        "Wallin, Lars",
-        "Pr\u00e9vost, Sophie",
-        "Guillot-Barbance, C\u00e9line",
-        "Mortensen, Bjartur",
-        "Pascual, Elena",
-        "\u00d6stling, Robert",
-        "Bouma, Gosse",
-        "Foster, Jennifer",
-        "Rie\u00dfler, Michael",
-        "G\u00e4rdenfors, Moa",
-        "\u00c7\u00f6ltekin, \u00c7a\u011fr\u0131",
-        "Piitulainen, Jussi",
-        "Ramisch, Carlos",
-        "Gonz\u00e1les Saavedra, Berta",
-        "Uria, Larraitz",
-        "Courtin, Marine",
-        "Manurung, Ruli",
-        "Leung, Herman",
-        "Kanayama, Hiroshi",
-        "Haji\u010d, Jan",
-        "Bowman, Sam",
-        "Kotsyba, Natalia",
-        "Sulubacak, Umut",
-        "Samard\u017ei\u0107, Tanja",
-        "Silveira, Natalia",
-        "Ol\u00fa\u00f2kun, Ad\u00e9day\u1ecd\u0300",
-        "Hociung, Florinel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2895;2019-01-16T17:03:48Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Universal Dependencies 2.3;Nivre, Joakim;Abrams, Mitchell;Agi\u0107, \u017deljko;Ahrenberg, Lars;Antonsen, Lene;Aplonova, Katya;Aranzabe, Maria Jesus;Arutie, Gashaw;Asahara, Masayuki;Ateyah, Luma;Attia, Mohammed;Atutxa, Aitziber;Augustinus, Liesbeth;Badmaeva, Elena;Ballesteros, Miguel;Banerjee, Esha;Bank, Sebastian;Barbu Mititelu, Verginica;Basmov, Victoria;Bauer, John;Bellato, Sandra;Bengoetxea, Kepa;Berzak, Yevgeni;Bhat, Irshad Ahmad;Bhat, Riyaz Ahmad;Biagetti, Erica;Bick, Eckhard;Blokland, Rogier;Bobicev, Victoria;B\u00f6rstell, Carl;Bosco, Cristina;Bouma, Gosse;Bowman, Sam;Boyd, Adriane;Burchardt, Aljoscha;Candito, Marie;Caron, Bernard;Caron, Gauthier;Cebiro\u011flu Eryi\u011fit, G\u00fcl\u015fen;Cecchini, Flavio Massimiliano;Celano, Giuseppe G. A.;\u010c\u00e9pl\u00f6, Slavom\u00edr;Cetin, Savas;Chalub, Fabricio;Choi, Jinho;Cho, Yongseok;Chun, Jayeol;Cinkov\u00e1, Silvie;Collomb, Aur\u00e9lie;\u00c7\u00f6ltekin, \u00c7a\u011fr\u0131;Connor, Miriam;Courtin, Marine;Davidson, Elizabeth;de Marneffe, Marie-Catherine;de Paiva, Valeria;Diaz de Ilarraza, Arantza;Dickerson, Carly;Dirix, Peter;Dobrovoljc, Kaja;Dozat, Timothy;Droganova, Kira;Dwivedi, Puneet;Eli, Marhaba;Elkahky, Ali;Ephrem, Binyam;Erjavec, Toma\u017e;Etienne, Aline;Farkas, Rich\u00e1rd;Fernandez Alcalde, Hector;Foster, Jennifer;Freitas, Cl\u00e1udia;Gajdo\u0161ov\u00e1, Katar\u00edna;Galbraith, Daniel;Garcia, Marcos;G\u00e4rdenfors, Moa;Garza, Sebastian;Gerdes, Kim;Ginter, Filip;Goenaga, Iakes;Gojenola, Koldo;G\u00f6k\u0131rmak, Memduh;Goldberg, Yoav;G\u00f3mez Guinovart, Xavier;Gonz\u00e1les Saavedra, Berta;Grioni, Matias;Gr\u016bz\u012btis, Normunds;Guillaume, Bruno;Guillot-Barbance, C\u00e9line;Habash, Nizar;Haji\u010d, Jan;Haji\u010d jr., Jan;H\u00e0 M\u1ef9, Linh;Han, Na-Rae;Harris, Kim;Haug, Dag;Hladk\u00e1, Barbora;Hlav\u00e1\u010dov\u00e1, Jaroslava;Hociung, Florinel;Hohle, Petter;Hwang, Jena;Ion, Radu;Irimia, Elena;Ishola, \u1eccl\u00e1j\u00edd\u00e9;Jel\u00ednek, Tom\u00e1\u0161;Johannsen, Anders;J\u00f8rgensen, Fredrik;Ka\u015f\u0131kara, H\u00fcner;Kahane, Sylvain;Kanayama, Hiroshi;Kanerva, Jenna;Katz, Boris;Kayadelen, Tolga;Kenney, Jessica;Kettnerov\u00e1, V\u00e1clava;Kirchner, Jesse;Kopacewicz, Kamil;Kotsyba, Natalia;Krek, Simon;Kwak, Sookyoung;Laippala, Veronika;Lambertino, Lorenzo;Lam, Lucia;Lando, Tatiana;Larasati, Septina Dian;Lavrentiev, Alexei;Lee, John;L\u00ea H\u1ed3ng, Ph\u01b0\u01a1ng;Lenci, Alessandro;Lertpradit, Saran;Leung, Herman;Li, Cheuk Ying;Li, Josie;Li, Keying;Lim, KyungTae;Ljube\u0161i\u0107, Nikola;Loginova, Olga;Lyashevskaya, Olga;Lynn, Teresa;Macketanz, Vivien;Makazhanov, Aibek;Mandl, Michael;Manning, Christopher;Manurung, Ruli;M\u0103r\u0103nduc, C\u0103t\u0103lina;Mare\u010dek, David;Marheinecke, Katrin;Mart\u00ednez Alonso, H\u00e9ctor;Martins, Andr\u00e9;Ma\u0161ek, Jan;Matsumoto, Yuji;McDonald, Ryan;Mendon\u00e7a, Gustavo;Miekka, Niko;Misirpashayeva, Margarita;Missil\u00e4, Anna;Mititelu, C\u0103t\u0103lin;Miyao, Yusuke;Montemagni, Simonetta;More, Amir;Moreno Romero, Laura;Mori, Keiko Sophie;Mori, Shinsuke;Mortensen, Bjartur;Moskalevskyi, Bohdan;Muischnek, Kadri;Murawaki, Yugo;M\u00fc\u00fcrisep, Kaili;Nainwani, Pinkey;Navarro Hor\u00f1iacek, Juan Ignacio;Nedoluzhko, Anna;Ne\u0161pore-B\u0113rzkalne, Gunta;Nguy\u1ec5n Th\u1ecb, L\u01b0\u01a1ng;Nguy\u1ec5n Th\u1ecb Minh, Huy\u1ec1n;Nikolaev, Vitaly;Nitisaroj, Rattima;Nurmi, Hanna;Ojala, Stina;Ol\u00fa\u00f2kun, Ad\u00e9day\u1ecd\u0300;Omura, Mai;Osenova, Petya;\u00d6stling, Robert;\u00d8vrelid, Lilja;Partanen, Niko;Pascual, Elena;Passarotti, Marco;Patejuk, Agnieszka;Paulino-Passos, Guilherme;Peng, Siyao;Perez, Cenel-Augusto;Perrier, Guy;Petrov, Slav;Piitulainen, Jussi;Pitler, Emily;Plank, Barbara;Poibeau, Thierry;Popel, Martin;Pretkalni\u0146a, Lauma;Pr\u00e9vost, Sophie;Prokopidis, Prokopis;Przepi\u00f3rkowski, Adam;Puolakainen, Tiina;Pyysalo, Sampo;R\u00e4\u00e4bis, Andriela;Rademaker, Alexandre;Ramasamy, Loganathan;Rama, Taraka;Ramisch, Carlos;Ravishankar, Vinit;Real, Livy;Reddy, Siva;Rehm, Georg;Rie\u00dfler, Michael;Rinaldi, Larissa;Rituma, Laura;Rocha, Luisa;Romanenko, Mykhailo;Rosa, Rudolf;Rovati, Davide;Ro\u0219ca, Valentin;Rudina, Olga;Rueter, Jack;Sadde, Shoval;Sagot, Beno\u00eet;Saleh, Shadi;Samard\u017ei\u0107, Tanja;Samson, Stephanie;Sanguinetti, Manuela;Saul\u012bte, Baiba;Sawanakunanon, Yanin;Schneider, Nathan;Schuster, Sebastian;Seddah, Djam\u00e9;Seeker, Wolfgang;Seraji, Mojgan;Shen, Mo;Shimada, Atsuko;Shohibussirri, Muh;Sichinava, Dmitry;Silveira, Natalia;Simi, Maria;Simionescu, Radu;Simk\u00f3, Katalin;\u0160imkov\u00e1, M\u00e1ria;Simov, Kiril;Smith, Aaron;Soares-Bastos, Isabela;Spadine, Carolyn;Stella, Antonio;Straka, Milan;Strnadov\u00e1, Jana;Suhr, Alane;Sulubacak, Umut;Sz\u00e1nt\u00f3, Zsolt;Taji, Dima;Takahashi, Yuta;Tanaka, Takaaki;Tellier, Isabelle;Trosterud, Trond;Trukhina, Anna;Tsarfaty, Reut;Tyers, Francis;Uematsu, Sumire;Ure\u0161ov\u00e1, Zde\u0148ka;Uria, Larraitz;Uszkoreit, Hans;Vajjala, Sowmya;van Niekerk, Daniel;van Noord, Gertjan;Varga, Viktor;Villemonte de la Clergerie, Eric;Vincze, Veronika;Wallin, Lars;Wang, Jing Xian;Washington, Jonathan North;Williams, Seyi;Wir\u00e9n, Mats;Woldemariam, Tsegay;Wong, Tak-sum;Yan, Chunxiao;Yavrumyan, Marat M.;Yu, Zhuoran;\u017dabokrtsk\u00fd, Zden\u011bk;Zeldes, Amir;Zeman, Daniel;Zhang, Manying;Zhu, Hanzhi;treebank;dependency;syntax;morphology;harmonized annotation;interset;universal tagset;stanford dependencies;Universal Dependencies is a project that seeks to develop cross-linguistically consistent treebank annotation for many languages, with the goal of facilitating multilingual parser development, cross-lingual learning, and parsing research from a language typology perspective. The annotation scheme is based on (universal) Stanford dependencies (de Marneffe et al., 2006, 2008, 2014), Google universal part-of-speech tags (Petrov et al., 2012), and the Interset interlingua for morphosyntactic tagsets (Zeman, 2008).;2018-11-15;corpus;http://hdl.handle.net/11234/1-2895;grc;ara;eus;bul;hrv;ces;dan;nld;eng;est;fin;fra;deu;got;ell;heb;hin;hun;ind;gle;ita;jpn;lat;nor;chu;fas;pol;por;ron;slv;spa;swe;tam;cat;zho;glg;kaz;lav;rus;tur;cop;san;slk;ukr;uig;vie;bel;kor;lit;urd;bxr;kmr;sme;hsb;afr;yue;mar;srp;swl;tel;amh;hye;bre;fao;kpv;pcm;fro;tgl;tha;wbp;yor;akk;bam;myv;mlt;http://hdl.handle.net/11234/1-2837;Licence Universal Dependencies v2.3;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-2.3;PUB;application/x-gzip;application/x-gzip;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 3;Universal Dependencies Consortium;http://universaldependencies.org/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d52fc848-99e3-5a6a-9c45-bad39ccea1d4",
-    "notes": [
-        "Universal Dependencies is a project that seeks to develop cross-linguistically consistent treebank annotation for many languages, with the goal of facilitating multilingual parser development, cross-lingual learning, and parsing research from a language typology perspective. The annotation scheme is based on (universal) Stanford dependencies (de Marneffe et al., 2006, 2008, 2014), Google universal part-of-speech tags (Petrov et al., 2012), and the Interset interlingua for morphosyntactic tagsets (Zeman, 2008)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2895"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "dependency"
-        },
-        {
-            "name": "syntax"
-        },
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "harmonized annotation"
-        },
-        {
-            "name": "interset"
-        },
-        {
-            "name": "universal tagset"
-        },
-        {
-            "name": "stanford dependencies"
-        }
-    ],
-    "title": [
-        "Universal Dependencies 2.3"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d59a0179-da65-59a4-9106-23e3242300e0.json b/oaitestdata/clarin-oai_dc/SET_1/json/d59a0179-da65-59a4-9106-23e3242300e0.json
deleted file mode 100644
index 1dd518e9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d59a0179-da65-59a4-9106-23e3242300e0.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "659 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1507",
-    "MetadataAccess": [
-        "oai:ota:oucs:1507"
-    ],
-    "PublicationTimestamp": "1847-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1847"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Bronte, Emily"
-    ],
-    "fulltext": "oai:ota:oucs:1507;2018-07-27T10:38:27Z;http://ota.ox.ac.uk/headers/1507.xml;Wuthering heights;Bronte, Emily;1847;text_and_corpus_linguistics;Novels -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;659 KB;Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d59a0179-da65-59a4-9106-23e3242300e0",
-    "oai_identifier": [
-        "oai:ota:oucs:1507"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Novels -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Wuthering heights"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1507.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d59f4b06-cbfe-5d2c-91ea-1f40bda65121.json b/oaitestdata/clarin-oai_dc/SET_1/json/d59f4b06-cbfe-5d2c-91ea-1f40bda65121.json
deleted file mode 100644
index 7ed8ca5b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d59f4b06-cbfe-5d2c-91ea-1f40bda65121.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 219 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2161",
-    "MetadataAccess": [
-        "oai:ota:oucs:2161"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gaskell, Elizabeth Cleghorn, 1810-1865"
-    ],
-    "fulltext": "oai:ota:oucs:2161;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/2161.xml;Cousin Phillis [Electronic resource / by Elizabeth Gaskell;Gaskell, Elizabeth Cleghorn, 1810-1865;text_and_corpus_linguistics;Fiction -- Great Britain -- 19th century;Novels -- Great Britain -- 19th century;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 219 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d59f4b06-cbfe-5d2c-91ea-1f40bda65121",
-    "oai_identifier": [
-        "oai:ota:oucs:2161"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- Great Britain -- th century"
-        },
-        {
-            "name": "Novels -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Cousin Phillis [Electronic resource / by Elizabeth Gaskell"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2161.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d5af7e3a-0576-5580-9467-699f04f2fda9.json b/oaitestdata/clarin-oai_dc/SET_1/json/d5af7e3a-0576-5580-9467-699f04f2fda9.json
deleted file mode 100644
index f667e79c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d5af7e3a-0576-5580-9467-699f04f2fda9.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5239",
-    "MetadataAccess": [
-        "oai:ota:oucs:5239"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Lennox, Charlotte, ca. 1729-1804."
-    ],
-    "fulltext": "oai:ota:oucs:5239;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5239.xml;Shakespear illustrated: or the novels and histories, on which the plays of Shakespear are founded, collected and translated from the original authors. With critical remarks. The third and last volume. By the author of The female Quixote. [pt.3];Lennox, Charlotte, ca. 1729-1804.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d5af7e3a-0576-5580-9467-699f04f2fda9",
-    "oai_identifier": [
-        "oai:ota:oucs:5239"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Shakespear illustrated: or the novels and histories, on which the plays of Shakespear are founded, collected and translated from the original authors. With critical remarks. The third and last volume. By the author of The female Quixote. [pt.3]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5239.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d5b6b142-4bb6-5a2b-93f1-eeec333b20d0.json b/oaitestdata/clarin-oai_dc/SET_1/json/d5b6b142-4bb6-5a2b-93f1-eeec333b20d0.json
deleted file mode 100644
index 614692da..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d5b6b142-4bb6-5a2b-93f1-eeec333b20d0.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5134",
-    "MetadataAccess": [
-        "oai:ota:oucs:5134"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Kelly, Hugh, 1739-1777."
-    ],
-    "fulltext": "oai:ota:oucs:5134;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5134.xml;The babler: Containing a careful selection from those entertaining and interesting essays. Which have given the public so much satisfaction under that title ... in Owen's Weekly Chronicle. ... [pt.2];Kelly, Hugh, 1739-1777.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d5b6b142-4bb6-5a2b-93f1-eeec333b20d0",
-    "oai_identifier": [
-        "oai:ota:oucs:5134"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The babler: Containing a careful selection from those entertaining and interesting essays. Which have given the public so much satisfaction under that title ... in Owen's Weekly Chronicle. ... [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5134.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d5c462c3-c8ad-5ef6-9f42-0e6f8a56c6e3.json b/oaitestdata/clarin-oai_dc/SET_1/json/d5c462c3-c8ad-5ef6-9f42-0e6f8a56c6e3.json
deleted file mode 100644
index fbcfa4cb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d5c462c3-c8ad-5ef6-9f42-0e6f8a56c6e3.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "B"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1743",
-    "MetadataAccess": [
-        "oai:ota:oucs:1743"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Trollope, Anthony"
-    ],
-    "fulltext": "oai:ota:oucs:1743;2018-04-16T15:30:51Z;http://ota.ox.ac.uk/headers/1743.xml;Rachel Ray;Trollope, Anthony;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;B;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d5c462c3-c8ad-5ef6-9f42-0e6f8a56c6e3",
-    "oai_identifier": [
-        "oai:ota:oucs:1743"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Rachel Ray"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1743.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d5e349cc-c114-531c-a267-51ef29a8d17d.json b/oaitestdata/clarin-oai_dc/SET_1/json/d5e349cc-c114-531c-a267-51ef29a8d17d.json
deleted file mode 100644
index c6e454d2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d5e349cc-c114-531c-a267-51ef29a8d17d.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-280",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-280"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-280",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-280;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Natural Language Toolkit;Open source Python modules, linguistic data and documentation for research and development in natural language processing, supporting dozens of NLP tasks. NLTK includes the following software modules (~120k lines of Python code): Corpus readers interfaces to many corpora  Tokenizers whitespace, newline, blankline, word, treebank, sexpr, regexp, Punkt sentence segmenter  Stemmers Porter, Lancaster, regexp  Taggers regexp, n-gram, backoff, Brill, HMM, TnT  Chunkers regexp, n-gram, named-entity  Parsers recursive descent, shift-reduce, chart, feature-based, probabilistic, dependency, ...  Semantic interpretation untyped lambda calculus, first-order models, DRT, glue semantics, hole semantics, parser interface  WordNet WordNet interface, lexical relations, similarity, interactive browser  Classifiers decision tree, maximum entropy, naive Bayes, Weka interface, megam  Clusterers expectation maximization, agglomerative, k-means  Metrics accuracy, precision, recall, windowdiff, distance metrics, inter-annotator agreement coefficients, word association measures, rank correlation  Estimation uniform, maximum likelihood, Lidstone, Laplace, expected likelihood, heldout, cross-validation, Good-Turing, Witten-Bell  Miscellaneous unification, chatbots, many utilities  NLTK-Contrib (less mature) categorial grammar (Lambek, CCG), finite-state automata, hadoop (MapReduce), kimmo, readability, textual entailment, timex, TnT interface, inter-annotator agreement;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-280;downloadable_files_count: 0;http://www.nltk.org",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d5e349cc-c114-531c-a267-51ef29a8d17d",
-    "notes": [
-        "Open source Python modules, linguistic data and documentation for research and development in natural language processing, supporting dozens of NLP tasks. NLTK includes the following software modules (~120k lines of Python code): Corpus readers interfaces to many corpora  Tokenizers whitespace, newline, blankline, word, treebank, sexpr, regexp, Punkt sentence segmenter  Stemmers Porter, Lancaster, regexp  Taggers regexp, n-gram, backoff, Brill, HMM, TnT  Chunkers regexp, n-gram, named-entity  Parsers recursive descent, shift-reduce, chart, feature-based, probabilistic, dependency, ...  Semantic interpretation untyped lambda calculus, first-order models, DRT, glue semantics, hole semantics, parser interface  WordNet WordNet interface, lexical relations, similarity, interactive browser  Classifiers decision tree, maximum entropy, naive Bayes, Weka interface, megam  Clusterers expectation maximization, agglomerative, k-means  Metrics accuracy, precision, recall, windowdiff, distance metrics, inter-annotator agreement coefficients, word association measures, rank correlation  Estimation uniform, maximum likelihood, Lidstone, Laplace, expected likelihood, heldout, cross-validation, Good-Turing, Witten-Bell  Miscellaneous unification, chatbots, many utilities  NLTK-Contrib (less mature) categorial grammar (Lambek, CCG), finite-state automata, hadoop (MapReduce), kimmo, readability, textual entailment, timex, TnT interface, inter-annotator agreement"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-280"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Natural Language Toolkit"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d5f69700-f2f8-5d44-aeab-f1cbdcaa42e5.json b/oaitestdata/clarin-oai_dc/SET_1/json/d5f69700-f2f8-5d44-aeab-f1cbdcaa42e5.json
deleted file mode 100644
index 3f3056fb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d5f69700-f2f8-5d44-aeab-f1cbdcaa42e5.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Hidley, Gregory Ray, 1950-"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain",
-        "(2 files : ca. 7.71, 1120 KB)"
-    ],
-    "Language": [
-        "Old English (ca. 450-1100)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1936",
-    "MetadataAccess": [
-        "oai:ota:oucs:1936"
-    ],
-    "PublicationTimestamp": "1100-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1100"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:1936;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/1936.xml;Anglo-Saxon poetic records;450-1100;text_and_corpus_linguistics;Poems;ang;Oxford Text Archive, University of Oxford;Hidley, Gregory Ray, 1950-;text/plain;(2 files : ca. 7.71, 1120 KB);Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d5f69700-f2f8-5d44-aeab-f1cbdcaa42e5",
-    "oai_identifier": [
-        "oai:ota:oucs:1936"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems"
-        }
-    ],
-    "title": [
-        "Anglo-Saxon poetic records"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1936.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d60fee92-9af7-58ad-a933-20bf0d71a201.json b/oaitestdata/clarin-oai_dc/SET_1/json/d60fee92-9af7-58ad-a933-20bf0d71a201.json
deleted file mode 100644
index 48d8e3b6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d60fee92-9af7-58ad-a933-20bf0d71a201.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/5-UDPIPE-TOKENIZER+TAGGER",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/5-UDPIPE-TOKENIZER+TAGGER"
-    ],
-    "PID": "http://hdl.handle.net/11234/5-UDPIPE-TOKENIZER+TAGGER",
-    "PublicationTimestamp": "2016-02-08T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Straka, Milan"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/5-UDPIPE-TOKENIZER+TAGGER;2019-01-02T13:52:07Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0023-8C33-2;UDPipe tokenizer+tagger Web Service for Weblicht;Straka, Milan;udpipe;UDPipe is a trainable pipeline for tokenizing, tagging, lemmatizing and parsing Universal Treebanks and other CoNLL-U files (https://lindat.mff.cuni.cz/services/udpipe/);2016-02-08;toolService;http://hdl.handle.net/11234/5-UDPIPE-TOKENIZER+TAGGER;application/octet-stream;downloadable_files_count: 0;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://hdl.handle.net/11234/5-UDPIPE-TOKENIZER+TAGGER",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d60fee92-9af7-58ad-a933-20bf0d71a201",
-    "notes": [
-        "UDPipe is a trainable pipeline for tokenizing, tagging, lemmatizing and parsing Universal Treebanks and other CoNLL-U files (https://lindat.mff.cuni.cz/services/udpipe/)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/5-UDPIPE-TOKENIZER+TAGGER"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0023-8C33-2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "udpipe"
-        }
-    ],
-    "title": [
-        "UDPipe tokenizer+tagger Web Service for Weblicht"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d61816de-7cb4-572c-a511-f77b67e67eea.json b/oaitestdata/clarin-oai_dc/SET_1/json/d61816de-7cb4-572c-a511-f77b67e67eea.json
deleted file mode 100644
index 3a147ecf..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d61816de-7cb4-572c-a511-f77b67e67eea.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "ClarinPL"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 11",
-        "application/zip",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/59",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/59"
-    ],
-    "PID": "http://hdl.handle.net/11321/59",
-    "PublicationTimestamp": "2015-04-07T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "ClarinPL"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "\u017beromski, Stefan \u017beromski"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/59;2018-04-10T14:28:42Z;hdl_11321_3;hdl_11321_4;\u017beromski;\u017beromski, Stefan \u017beromski;S\u017b;2015-04-07;corpus;http://hdl.handle.net/11321/59;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 11;ClarinPL",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d61816de-7cb4-572c-a511-f77b67e67eea",
-    "notes": [
-        "S\u017b"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/59"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "\u017beromski"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d61ea843-e1db-5f19-b0ae-e471af8ae909.json b/oaitestdata/clarin-oai_dc/SET_1/json/d61ea843-e1db-5f19-b0ae-e471af8ae909.json
deleted file mode 100644
index 8d6c60ce..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d61ea843-e1db-5f19-b0ae-e471af8ae909.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Afar"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/627",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/627"
-    ],
-    "PID": "http://hdl.handle.net/11321/627",
-    "PublicationTimestamp": "2019-02-11T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "plWordNet",
-        "JS",
-        "http://clarin-pl.eu/en/licenses/plwordnet-2/",
-        "PUB"
-    ],
-    "author": [
-        "Mcka, Anna"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/627;2019-02-11T22:23:04Z;hdl_11321_3;hdl_11321_4;JSlisty;Mcka, Anna;Js listy;prv;2019-02-11;corpus;http://hdl.handle.net/11321/627;aar;plWordNet;JS;http://clarin-pl.eu/en/licenses/plwordnet-2/;PUB;application/octet-stream;downloadable_files_count: 1",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d61ea843-e1db-5f19-b0ae-e471af8ae909",
-    "notes": [
-        "prv"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/627"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Js listy"
-        }
-    ],
-    "title": [
-        "JSlisty"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d6212c02-9fea-5ba0-9d45-52f3e17c205a.json b/oaitestdata/clarin-oai_dc/SET_1/json/d6212c02-9fea-5ba0-9d45-52f3e17c205a.json
deleted file mode 100644
index 2c1ce649..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d6212c02-9fea-5ba0-9d45-52f3e17c205a.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/45",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/45"
-    ],
-    "PID": "http://hdl.handle.net/10794/45",
-    "PublicationTimestamp": "2012-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/45;2017-10-27T08:56:47Z;hdl_10794_1;hdl_10794_2;S\u00f6derwall (2017-10-16);S\u00f6derwall (2017-10-16);n/a, n/a;Swedish;Dictionary;Dictionary of Old Swedish.;Ordbok \u00f6ver svenska medeltidsspr\u00e5ket.;2012-05-30;lexicalConceptualResource;http://hdl.handle.net/10794/45;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/soederwall",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d6212c02-9fea-5ba0-9d45-52f3e17c205a",
-    "notes": [
-        "Dictionary of Old Swedish.",
-        "Ordbok \u00f6ver svenska medeltidsspr\u00e5ket."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/45"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Dictionary"
-        }
-    ],
-    "title": [
-        "S\u00f6derwall (2017-10-16)",
-        "S\u00f6derwall (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d62df362-bb77-5eda-9ce5-6ed5781de185.json b/oaitestdata/clarin-oai_dc/SET_1/json/d62df362-bb77-5eda-9ce5-6ed5781de185.json
deleted file mode 100644
index e619b914..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d62df362-bb77-5eda-9ce5-6ed5781de185.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5481",
-    "MetadataAccess": [
-        "oai:ota:oucs:5481"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "John and William Cunningham and Company (Brewers : Glasgow, Scotland)"
-    ],
-    "fulltext": "oai:ota:oucs:5481;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5481.xml;Unto the Right Honourable, the Lords of Council and Session, the petition of John and William Cunningham and Company brewers in Glasgow, James Hotchkis and Company brewers in Edinburgh, and James Graham vintner in Glasgow, for themselves, and as trustees of William M\u00ca\u00bbGregor late tenant in Parkhall,;John and William Cunningham and Company (Brewers : Glasgow, Scotland);text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d62df362-bb77-5eda-9ce5-6ed5781de185",
-    "oai_identifier": [
-        "oai:ota:oucs:5481"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Unto the Right Honourable, the Lords of Council and Session, the petition of John and William Cunningham and Company brewers in Glasgow, James Hotchkis and Company brewers in Edinburgh, and James Graham vintner in Glasgow, for themselves, and as trustees of William M\u00ca\u00bbGregor late tenant in Parkhall,"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5481.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d62fabb3-a44c-56a9-9c9c-e7d8bd9269ed.json b/oaitestdata/clarin-oai_dc/SET_1/json/d62fabb3-a44c-56a9-9c9c-e7d8bd9269ed.json
deleted file mode 100644
index 2942f320..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d62fabb3-a44c-56a9-9c9c-e7d8bd9269ed.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "University of Warsaw"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/507",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/507"
-    ],
-    "PID": "http://hdl.handle.net/11321/507",
-    "PublicationTimestamp": "2018-07-09T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "University of Warsaw"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "IS PAS corpora license",
-        "http://clarin-pl.eu/en/licenses/is-pas-corpora-license/",
-        "CC"
-    ],
-    "author": [
-        "Twardo, Sylwia"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/507;2018-07-09T02:03:38Z;hdl_11321_3;hdl_11321_4;C1_essays;Twardo, Sylwia;C1 essays;C1 essays;2018-07-09;corpus;http://hdl.handle.net/11321/507;eng;IS PAS corpora license;http://clarin-pl.eu/en/licenses/is-pas-corpora-license/;CC;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;University of Warsaw",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d62fabb3-a44c-56a9-9c9c-e7d8bd9269ed",
-    "notes": [
-        "C1 essays"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/507"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "C essays"
-        }
-    ],
-    "title": [
-        "C1_essays"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d64fa1cb-8e33-5739-ad9f-285ecdb977d5.json b/oaitestdata/clarin-oai_dc/SET_1/json/d64fa1cb-8e33-5739-ad9f-285ecdb977d5.json
deleted file mode 100644
index f7059901..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d64fa1cb-8e33-5739-ad9f-285ecdb977d5.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "Russian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-936",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-936"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-936",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-936;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Old Russian;ca. 200.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-936;rus;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#aruss",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d64fa1cb-8e33-5739-ad9f-285ecdb977d5",
-    "notes": [
-        "ca. 200.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-936"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Old Russian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d660bde1-f358-5e4a-9694-42eb6406a3c4.json b/oaitestdata/clarin-oai_dc/SET_1/json/d660bde1-f358-5e4a-9694-42eb6406a3c4.json
deleted file mode 100644
index 0ea6a41d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d660bde1-f358-5e4a-9694-42eb6406a3c4.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5209",
-    "MetadataAccess": [
-        "oai:ota:oucs:5209"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Sharp, Granville, 1735-1813."
-    ],
-    "fulltext": "oai:ota:oucs:5209;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5209.xml;Remarks on several very important prophecies: In five parts. ... By Granville Sharp.;Sharp, Granville, 1735-1813.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d660bde1-f358-5e4a-9694-42eb6406a3c4",
-    "oai_identifier": [
-        "oai:ota:oucs:5209"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Remarks on several very important prophecies: In five parts. ... By Granville Sharp."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5209.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d67a3b1f-b39f-5e18-8cc3-cdf4a90e4f5c.json b/oaitestdata/clarin-oai_dc/SET_1/json/d67a3b1f-b39f-5e18-8cc3-cdf4a90e4f5c.json
deleted file mode 100644
index c6d20f5d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d67a3b1f-b39f-5e18-8cc3-cdf4a90e4f5c.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "ZRC SAZU"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1141",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1141"
-    ],
-    "PID": "http://hdl.handle.net/11356/1141",
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "ZRC SAZU"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Jakopin, Primo\u017e"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1141;2017-09-25T10:21:07Z;hdl_11356_1023;hdl_11356_1024;Beseda Corpus Lemmatisation Lexicon;Jakopin, Primo\u017e;morphology;inflection;word forms;lemmatisation;Beseda Corpus Lemmatisation Lexicon for Slovenian language was generated at the Fran Ramov\u0161 Institute of Slovenian Language, primarily through inflection of open class words from the Dictionary of Standard Slovenian (Slovar slovenskega knji\u017enega jezika), augmented by wordforms, their part of speech tags and their lemmas used during the PoS tagging and lemmatization of the Beseda corpus. It was initially (2000) composed of 1 million words from the following texts:\r\n\r\nCiril Kosma\u010d Opus - 408,000 words\r\nTomo Kri\u017enar: O iskanju ljubezni / On Search for Love or Around the World by Bicycle - 132,000 words\r\nGeorge Orwell: 1984 / 1984 - 91,000 words\r\nPlato: Dr\u017eava / Republic - 93,000 words\r\nSveto pismo Nove zaveze / The Bible - New Testament - 150,000 words\r\nGustave Flaubert: Bouvard in P\u00e9cuchet / Bouvard and P\u00e9cuchet - 86,000 words\r\n\u010casopis DELO na internetu (vzorec iz 6.5.1997 - 17.6.1997) / Newspaper DELO on Internet (a sample from 5/6/1997 - 6/17/1997) - 52,000 words\r\n\r\nAfter 2000 the following texts were added:\r\n\r\nMarko Ur\u0161i\u010d: \u0160tirje \u010dasi / Four Seasons - 171,000 words\r\nDr\u017eavni zbor RS 3. sklica - dobesedni zapisi sej: 29. redna seja, zasedanje 01.10.2003 / National Assembly of the Republic of Slovenia - session transcripts: 29th regular session, meeting of 10/1/2003 - 47,000 words\r\n\u010casopis DELO za 3.1.2004 / Newspaper DELO for 1/3/2004 - 75,000 words\r\n\r\nto round the corpus to 1,300,000 words.\r\n\r\nCurrent lexicon was taken from the database of the online \"Determination of Lemmas and PoS Tags for a List of Words\" service at the Institute, available through the web page: http://bos.zrc-sazu.si/dol_lem1.html Wordform frequencies were compiled from the latest update of the abovementioned corpus (version 138, 1,300,626 words, August 2017) and are therefore approximate.\r\n\r\nLexicon is UTF-8 coded, has 3,228,128 lines, each of the following 4 data fields, tab separated:\r\n\r\n1. wordform\r\n2. lemma (102,346 different lemmas)\r\n3. PoS tag (explained at http://bos.zrc-sazu.si/bibliografija/o_oznake.html - in Slovenian)\r\n4. approximate corpus frequency; wordform-lemma-PoS entries not in corpus have zero frequency;2017;lexicalConceptualResource;http://hdl.handle.net/11356/1141;slv;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;ZRC SAZU;http://bos.zrc-sazu.si/dol_lem1.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d67a3b1f-b39f-5e18-8cc3-cdf4a90e4f5c",
-    "notes": [
-        "Beseda Corpus Lemmatisation Lexicon for Slovenian language was generated at the Fran Ramov\u0161 Institute of Slovenian Language, primarily through inflection of open class words from the Dictionary of Standard Slovenian (Slovar slovenskega knji\u017enega jezika), augmented by wordforms, their part of speech tags and their lemmas used during the PoS tagging and lemmatization of the Beseda corpus. It was initially (2000) composed of 1 million words from the following texts:\r\n\r\nCiril Kosma\u010d Opus - 408,000 words\r\nTomo Kri\u017enar: O iskanju ljubezni / On Search for Love or Around the World by Bicycle - 132,000 words\r\nGeorge Orwell: 1984 / 1984 - 91,000 words\r\nPlato: Dr\u017eava / Republic - 93,000 words\r\nSveto pismo Nove zaveze / The Bible - New Testament - 150,000 words\r\nGustave Flaubert: Bouvard in P\u00e9cuchet / Bouvard and P\u00e9cuchet - 86,000 words\r\n\u010casopis DELO na internetu (vzorec iz 6.5.1997 - 17.6.1997) / Newspaper DELO on Internet (a sample from 5/6/1997 - 6/17/1997) - 52,000 words\r\n\r\nAfter 2000 the following texts were added:\r\n\r\nMarko Ur\u0161i\u010d: \u0160tirje \u010dasi / Four Seasons - 171,000 words\r\nDr\u017eavni zbor RS 3. sklica - dobesedni zapisi sej: 29. redna seja, zasedanje 01.10.2003 / National Assembly of the Republic of Slovenia - session transcripts: 29th regular session, meeting of 10/1/2003 - 47,000 words\r\n\u010casopis DELO za 3.1.2004 / Newspaper DELO for 1/3/2004 - 75,000 words\r\n\r\nto round the corpus to 1,300,000 words.\r\n\r\nCurrent lexicon was taken from the database of the online \"Determination of Lemmas and PoS Tags for a List of Words\" service at the Institute, available through the web page: http://bos.zrc-sazu.si/dol_lem1.html Wordform frequencies were compiled from the latest update of the abovementioned corpus (version 138, 1,300,626 words, August 2017) and are therefore approximate.\r\n\r\nLexicon is UTF-8 coded, has 3,228,128 lines, each of the following 4 data fields, tab separated:\r\n\r\n1. wordform\r\n2. lemma (102,346 different lemmas)\r\n3. PoS tag (explained at http://bos.zrc-sazu.si/bibliografija/o_oznake.html - in Slovenian)\r\n4. approximate corpus frequency; wordform-lemma-PoS entries not in corpus have zero frequency"
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1141"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "inflection"
-        },
-        {
-            "name": "word forms"
-        },
-        {
-            "name": "lemmatisation"
-        }
-    ],
-    "title": [
-        "Beseda Corpus Lemmatisation Lexicon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d6894c5c-58fe-5766-b337-5da9ff907b61.json b/oaitestdata/clarin-oai_dc/SET_1/json/d6894c5c-58fe-5766-b337-5da9ff907b61.json
deleted file mode 100644
index b53a00d4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d6894c5c-58fe-5766-b337-5da9ff907b61.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "ZRC SAZU"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1128",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1128"
-    ],
-    "PID": "http://hdl.handle.net/11356/1128",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "ZRC SAZU"
-    ],
-    "RelatedIdentifier": [
-        "https://kuscholarworks.ku.edu/bitstream/handle/1808/18716/02_SCN_1_2015_Zele.pdf"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u017dele, Andreja"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1128;2017-08-04T17:21:28Z;hdl_11356_1023;hdl_11356_1024;Dictionary of Slovenian Particles;\u017dele, Andreja;dictionary;lexicography;particles;The dictionary describes the particles in the Slovenian language. It contains 429 entries with information on variants, dynamic and tonal accent, particle type, the meaning and etymology.\r\n\r\nThe relation to what is being said and the circumstances of the spoken situation are expressed particularly through particles, which is why they are functionally very lively language components of everyday communication. With their semantic-contextual role they actualise what is worded and at the same time condense the message. The particle is one of those non-parts-of-speech that fulfils the textual role of the connector and is, more particularly, ranked among inter-predicate connectors or the connectors in supra-predicate texts. Since particles play primarily a textual role, they are also particularly meaningful words, which can be reasonably used in a text, especially in one\u2019s first language; they maintain a strong communicative (connective) role, and with this a well-marked role of influence. From the communicative-pragmatic perspective, particles are divided into two main categories, namely the connecting (text) particles resulting from pragmatic circumstances, and mood (interpersonal) particles resulting from communicative relationships. Mood particles focus either on the participants, the circumstances, the verbal process or the quantity, e.g. bogvaruj, kon\u010dno, dejansko, baje, nikar, while the connecting particles highlight textual coherence and cohesion, e.g. celo, kaj \u0161ele, druga\u010de, sicer pa, torej, etc. The most comprehensive and functional semantic-circumstantial evaluation of particles can be found in lexical representation.\r\n\r\nThis dictionary was published as a printed book:\r\n\u017dele, Andreja. Slovar slovenskih \u010dlenkov. Ljubljana : Zalo\u017eba ZRC, ZRC SAZU, 2014. ISBN 978-961-254-718-9.;2015;lexicalConceptualResource;http://hdl.handle.net/11356/1128;slv;https://kuscholarworks.ku.edu/bitstream/handle/1808/18716/02_SCN_1_2015_Zele.pdf;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;ZRC SAZU;http://www.termania.net/slovarji/127/slovar-slovenskih-clenkov",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d6894c5c-58fe-5766-b337-5da9ff907b61",
-    "notes": [
-        "The dictionary describes the particles in the Slovenian language. It contains 429 entries with information on variants, dynamic and tonal accent, particle type, the meaning and etymology.\r\n\r\nThe relation to what is being said and the circumstances of the spoken situation are expressed particularly through particles, which is why they are functionally very lively language components of everyday communication. With their semantic-contextual role they actualise what is worded and at the same time condense the message. The particle is one of those non-parts-of-speech that fulfils the textual role of the connector and is, more particularly, ranked among inter-predicate connectors or the connectors in supra-predicate texts. Since particles play primarily a textual role, they are also particularly meaningful words, which can be reasonably used in a text, especially in one\u2019s first language; they maintain a strong communicative (connective) role, and with this a well-marked role of influence. From the communicative-pragmatic perspective, particles are divided into two main categories, namely the connecting (text) particles resulting from pragmatic circumstances, and mood (interpersonal) particles resulting from communicative relationships. Mood particles focus either on the participants, the circumstances, the verbal process or the quantity, e.g. bogvaruj, kon\u010dno, dejansko, baje, nikar, while the connecting particles highlight textual coherence and cohesion, e.g. celo, kaj \u0161ele, druga\u010de, sicer pa, torej, etc. The most comprehensive and functional semantic-circumstantial evaluation of particles can be found in lexical representation.\r\n\r\nThis dictionary was published as a printed book:\r\n\u017dele, Andreja. Slovar slovenskih \u010dlenkov. Ljubljana : Zalo\u017eba ZRC, ZRC SAZU, 2014. ISBN 978-961-254-718-9."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1128"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "dictionary"
-        },
-        {
-            "name": "lexicography"
-        },
-        {
-            "name": "particles"
-        }
-    ],
-    "title": [
-        "Dictionary of Slovenian Particles"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d6899be8-c7da-535c-814e-2d38349ada15.json b/oaitestdata/clarin-oai_dc/SET_1/json/d6899be8-c7da-535c-814e-2d38349ada15.json
deleted file mode 100644
index 524a7c50..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d6899be8-c7da-535c-814e-2d38349ada15.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2667",
-    "MetadataAccess": [
-        "oai:ota:oucs:2667"
-    ],
-    "PublicationTimestamp": "1733-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1733"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2667;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2667.xml;The presbyterian's plea of merit ... impartially examined;Swift, Jonathan, 1667-1745;1733;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d6899be8-c7da-535c-814e-2d38349ada15",
-    "oai_identifier": [
-        "oai:ota:oucs:2667"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The presbyterian's plea of merit ... impartially examined"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2667.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d68c8617-f017-5df5-b100-675e2d9fa382.json b/oaitestdata/clarin-oai_dc/SET_1/json/d68c8617-f017-5df5-b100-675e2d9fa382.json
deleted file mode 100644
index 9a31979d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d68c8617-f017-5df5-b100-675e2d9fa382.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Kerstin Dahlb\u00e4ck"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/78",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/78"
-    ],
-    "PID": "http://hdl.handle.net/10794/78",
-    "PublicationTimestamp": "2012-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Kerstin Dahlb\u00e4ck"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Dahlb\u00e4ck, Kerstin"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/78;2017-11-01T07:59:02Z;hdl_10794_1;hdl_10794_2;August Strindberg's letters (2017-10-16);August Strindbergs brev (2017-10-16);Dahlb\u00e4ck, Kerstin;Swedish;Letters;Part of the collected works of August Strindberg.\r\n\r\nAugust Strindberg's letters were compiled by Kerstin Dahlb\u00e4ck. They include all published and unpublished letters available on 1 August 1991. The material should be considered a working material, as it has not yet been satisfactorily proof-read. Additionally, the letters from the last years have preliminary designations and need to be renumbered in accordance with parts XVII-XX of the published letters of August Strindberg. \r\n\r\nThe material is sentence scrambled.;Del av August Strindbergs samlade verk.\r\n\r\nAugust Strindbergs brev sammanst\u00e4lldes av Kerstin Dahlb\u00e4ck. De omfattar samtliga tryckta och otryckta brev som var tillg\u00e4ngliga 1 augusti 1991. Materialet \u00e4r att betrakta som ett arbetsmaterial, d\u00e5 det \u00e4nnu inte \u00e4r tillfredsst\u00e4llande kontrollerat (korrekturfel kan inte uteslutas, de brev som kodats in direkt fr\u00e5n handskrivet manuskript kan rymma feltolkningar och b\u00f6r korrigeras, felaktigheter hos Eklund har visserligen r\u00e4ttats men en systematisk genomg\u00e5ng har inte f\u00f6retagits). Vidare har breven fr\u00e5n de sista \u00e5ren prelimin\u00e4ra beteckningar och skall omnumreras i \u00f6verensst\u00e4mmelse med delarna XVII-XX i utg\u00e5van av Augusts Strindbergs brev. \r\n\r\nMaterialet \u00e4r meningsomkastat.;2012-05-30;corpus;http://hdl.handle.net/10794/78;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Kerstin Dahlb\u00e4ck;https://spraakbanken.gu.se/swe/resurs/strindbergbrev",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d68c8617-f017-5df5-b100-675e2d9fa382",
-    "notes": [
-        "Part of the collected works of August Strindberg.\r\n\r\nAugust Strindberg's letters were compiled by Kerstin Dahlb\u00e4ck. They include all published and unpublished letters available on 1 August 1991. The material should be considered a working material, as it has not yet been satisfactorily proof-read. Additionally, the letters from the last years have preliminary designations and need to be renumbered in accordance with parts XVII-XX of the published letters of August Strindberg. \r\n\r\nThe material is sentence scrambled.",
-        "Del av August Strindbergs samlade verk.\r\n\r\nAugust Strindbergs brev sammanst\u00e4lldes av Kerstin Dahlb\u00e4ck. De omfattar samtliga tryckta och otryckta brev som var tillg\u00e4ngliga 1 augusti 1991. Materialet \u00e4r att betrakta som ett arbetsmaterial, d\u00e5 det \u00e4nnu inte \u00e4r tillfredsst\u00e4llande kontrollerat (korrekturfel kan inte uteslutas, de brev som kodats in direkt fr\u00e5n handskrivet manuskript kan rymma feltolkningar och b\u00f6r korrigeras, felaktigheter hos Eklund har visserligen r\u00e4ttats men en systematisk genomg\u00e5ng har inte f\u00f6retagits). Vidare har breven fr\u00e5n de sista \u00e5ren prelimin\u00e4ra beteckningar och skall omnumreras i \u00f6verensst\u00e4mmelse med delarna XVII-XX i utg\u00e5van av Augusts Strindbergs brev. \r\n\r\nMaterialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/78"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Letters"
-        }
-    ],
-    "title": [
-        "August Strindberg's letters (2017-10-16)",
-        "August Strindbergs brev (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d6a639d7-0b37-52bb-b783-e6b8f2264a3c.json b/oaitestdata/clarin-oai_dc/SET_1/json/d6a639d7-0b37-52bb-b783-e6b8f2264a3c.json
deleted file mode 100644
index 569b8861..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d6a639d7-0b37-52bb-b783-e6b8f2264a3c.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4099",
-    "MetadataAccess": [
-        "oai:ota:oucs:4099"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hayley, William, 1745-1820."
-    ],
-    "fulltext": "oai:ota:oucs:4099;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4099.xml;Poems and plays: by William Hayley, Esq. In six volumes. ... [pt.4];Hayley, William, 1745-1820.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d6a639d7-0b37-52bb-b783-e6b8f2264a3c",
-    "oai_identifier": [
-        "oai:ota:oucs:4099"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Poems and plays: by William Hayley, Esq. In six volumes. ... [pt.4]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4099.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d6b48b96-988c-5546-91e1-3e3803a0015a.json b/oaitestdata/clarin-oai_dc/SET_1/json/d6b48b96-988c-5546-91e1-3e3803a0015a.json
deleted file mode 100644
index d4bfd03c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d6b48b96-988c-5546-91e1-3e3803a0015a.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-988",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-988"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-988",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-988;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LAC Karihona Corpus;Language and Cognition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-988;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI33453%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d6b48b96-988c-5546-91e1-3e3803a0015a",
-    "notes": [
-        "Language and Cognition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-988"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LAC Karihona Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d6db95f2-9fe9-592b-9791-754501feb82a.json b/oaitestdata/clarin-oai_dc/SET_1/json/d6db95f2-9fe9-592b-9791-754501feb82a.json
deleted file mode 100644
index 32ff192c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d6db95f2-9fe9-592b-9791-754501feb82a.json
+++ /dev/null
@@ -1,104 +0,0 @@
-{
-    "Contact": [
-        "Wolbramczyk Krzysztof"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-5971",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-5971"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D2B-E",
-    "PublicationTimestamp": "1617-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1617"
-    ],
-    "Publisher": [
-        "Wolbramczyk Krzysztof"
-    ],
-    "RelatedIdentifier": [
-        "http://dlibra.bibliotekaelblaska.pl/Content/5971",
-        "oai:dlibra.bibliotekaelblaska.pl:publication:6186"
-    ],
-    "ResourceType": [
-        "starodruk",
-        "alter Druck"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "author": [
-        "Sixtus Erazm"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-5971;2019-03-01T15:58:03Z;O cieplicach we Skle Ksi\u0105g Troie. Przez Erazma Syxta Philozophiey y Medicyny Doktora Napisanych...;O cieplicach we Skle Ksi\u0105g Troie. Przez Erazma Syxta Philozophiey y Medicyny Doktora Napisanych...;Sixtus Erazm;Sixtus Erazm;Szk\u0142o, wie\u015b;wody siarczane;Sixtus, Erazm (w\u0142a\u015bc. Mrzyg\u0142\u00f3d) (1570-1635);kurort;wodolecznictwo;Oczko W.;Kurort;Wasserheilkunde;Szk\u0142o, Dorf;Oczko, W.;Schwefelquellen;Sixtus, Erazm (eig. Mrzyg\u0142\u00f3d) (1570-1635);Sixtus Erazm (w\u0142a\u015bc. Mrzyg\u0142\u00f3d) (1570-1635) \u2013 doktor medycyny i filozofii. W swoim dziele opisuje \u017ar\u00f3d\u0142a wody siarczanej we wsi Szk\u0142o niedaleko Lwowa. Autor powo\u0142uje si\u0119 na inne \u017ar\u00f3d\u0142o o tych wodach, a mianowicie na Cieplice W. Oczki. Sixtus E. traktuje zatem swoje dzie\u0142o jako uzupe\u0142nienie do w/w pozycji. Druk wydany w Zamo\u015bciu przez Krzysztofa Wolbramczyka, w formacie 4\u00b0, zawiera piecz\u0119ci Biblioteki Gimnazjum Elbl\u0105skiego i Stadtbibliothek.Oprawa pergaminowa z jappem. W 2010 r. drukpoddano konserwacji zachowawczej w ramach projektu \u201eKonserwacjazachowawcza druk\u00f3w XV-XVII w. Biblioteki Elbl\u0105skiej\u201d.;Sixtus Erasm war Doktor der Medizin und Philosophie. Sein Werk handelt von den Schwefelquellen im Dorf Szk\u0142o bei Lemberg . Der Autor bezieht sich auch auf andere Quellen und n\u00e4mlich auf die Abhandlung von W. Oczko, der auch f\u00fcr die Erforschung der Thermalquellen war. Der Beitrag von Sixtus soll als die Erg\u00e4nzung der Abhandlung von Oczko \u00fcber hei\u00dfe Quellen angesehen werden. Das Druckerzeugnis wurde in Zamo\u015b\u0107 (Zamosch) von Krzysztof Wolbramczyk herausgegeben. Format - 4\u00ba, Siegel der Gymnasialbibliotek und Elbinger Stadtbibliothek. Der Pergamenteinband wurde an den R\u00e4ndern geknickt, um die Blattr\u00e4nder zu sch\u00fctzen.;Wolbramczyk Krzysztof;Wolbramczyk Krzysztof;1617;1617;starodruk;alter Druck;application/xml;clarind-uds:poldilemma-5971;hdl:11858/00-246C-0000-0023-8D2B-E;Pol.7.II.303;Pol. 7. II. 303;pol;http://dlibra.bibliotekaelblaska.pl/Content/5971;oai:dlibra.bibliotekaelblaska.pl:publication:6186;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d6db95f2-9fe9-592b-9791-754501feb82a",
-    "notes": [
-        "Sixtus Erazm (w\u0142a\u015bc. Mrzyg\u0142\u00f3d) (1570-1635) \u2013 doktor medycyny i filozofii. W swoim dziele opisuje \u017ar\u00f3d\u0142a wody siarczanej we wsi Szk\u0142o niedaleko Lwowa. Autor powo\u0142uje si\u0119 na inne \u017ar\u00f3d\u0142o o tych wodach, a mianowicie na Cieplice W. Oczki. Sixtus E. traktuje zatem swoje dzie\u0142o jako uzupe\u0142nienie do w/w pozycji. Druk wydany w Zamo\u015bciu przez Krzysztofa Wolbramczyka, w formacie 4\u00b0, zawiera piecz\u0119ci Biblioteki Gimnazjum Elbl\u0105skiego i Stadtbibliothek.Oprawa pergaminowa z jappem. W 2010 r. drukpoddano konserwacji zachowawczej w ramach projektu \u201eKonserwacjazachowawcza druk\u00f3w XV-XVII w. Biblioteki Elbl\u0105skiej\u201d.",
-        "Sixtus Erasm war Doktor der Medizin und Philosophie. Sein Werk handelt von den Schwefelquellen im Dorf Szk\u0142o bei Lemberg . Der Autor bezieht sich auch auf andere Quellen und n\u00e4mlich auf die Abhandlung von W. Oczko, der auch f\u00fcr die Erforschung der Thermalquellen war. Der Beitrag von Sixtus soll als die Erg\u00e4nzung der Abhandlung von Oczko \u00fcber hei\u00dfe Quellen angesehen werden. Das Druckerzeugnis wurde in Zamo\u015b\u0107 (Zamosch) von Krzysztof Wolbramczyk herausgegeben. Format - 4\u00ba, Siegel der Gymnasialbibliotek und Elbinger Stadtbibliothek. Der Pergamenteinband wurde an den R\u00e4ndern geknickt, um die Blattr\u00e4nder zu sch\u00fctzen."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-5971"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Szk\u0142o"
-        },
-        {
-            "name": "wie\u015b"
-        },
-        {
-            "name": "wody siarczane"
-        },
-        {
-            "name": "Sixtus"
-        },
-        {
-            "name": "Erazm w\u0142a\u015bc. Mrzyg\u0142\u00f3d -"
-        },
-        {
-            "name": "kurort"
-        },
-        {
-            "name": "wodolecznictwo"
-        },
-        {
-            "name": "Oczko W."
-        },
-        {
-            "name": "Kurort"
-        },
-        {
-            "name": "Wasserheilkunde"
-        },
-        {
-            "name": "Szk\u0142o"
-        },
-        {
-            "name": "Dorf"
-        }
-    ],
-    "title": [
-        "O cieplicach we Skle Ksi\u0105g Troie. Przez Erazma Syxta Philozophiey y Medicyny Doktora Napisanych...",
-        "O cieplicach we Skle Ksi\u0105g Troie. Przez Erazma Syxta Philozophiey y Medicyny Doktora Napisanych..."
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d7031fcb-4305-5765-8c6f-85e61156e806.json b/oaitestdata/clarin-oai_dc/SET_1/json/d7031fcb-4305-5765-8c6f-85e61156e806.json
deleted file mode 100644
index ed855065..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d7031fcb-4305-5765-8c6f-85e61156e806.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1208",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1208"
-    ],
-    "PID": "http://hdl.handle.net/11356/1208",
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "http://www.sdjt.si/wp/wp-content/uploads/2018/09/JTDH-2018_Ljubesic-et-al_The-Parlameter-corpus-of-contemporary-Slovene-parliamentary-proceedings.pdf"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by-sa/4.0/"
-    ],
-    "author": [
-        "Dobrani\u0107, Filip",
-        "Ljube\u0161i\u0107, Nikola",
-        "Erjavec, Toma\u017e"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1208;2019-01-05T09:03:26Z;hdl_11356_1023;hdl_11356_1024;Slovenian parliamentary corpus ParlaMeter-sl 1.0;Dobrani\u0107, Filip;Ljube\u0161i\u0107, Nikola;Erjavec, Toma\u017e;Slovenian Parliament;parliamentary debates;TEI;named entities;The ParlaMeter-sl corpus contains minutes of the National Assembly of the Republic of Slovenia and currently covers its VIIth mandate (2014-08-01 to 2018-06-22). The corpus contains speaker metadata (gender, age, education, party affiliatiation), while the transcriptions of their speeches are MSD tagged, lemmatised, and marked with named entities.;2019-01-08;corpus;http://hdl.handle.net/11356/1208;slv;http://www.sdjt.si/wp/wp-content/uploads/2018/09/JTDH-2018_Ljubesic-et-al_The-Parlameter-corpus-of-contemporary-Slovene-parliamentary-proceedings.pdf;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);PUB;https://creativecommons.org/licenses/by-sa/4.0/;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 2;Jo\u017eef Stefan Institute;https://parlameter.si/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d7031fcb-4305-5765-8c6f-85e61156e806",
-    "notes": [
-        "The ParlaMeter-sl corpus contains minutes of the National Assembly of the Republic of Slovenia and currently covers its VIIth mandate (2014-08-01 to 2018-06-22). The corpus contains speaker metadata (gender, age, education, party affiliatiation), while the transcriptions of their speeches are MSD tagged, lemmatised, and marked with named entities."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1208"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Slovenian Parliament"
-        },
-        {
-            "name": "parliamentary debates"
-        },
-        {
-            "name": "TEI"
-        },
-        {
-            "name": "named entities"
-        }
-    ],
-    "title": [
-        "Slovenian parliamentary corpus ParlaMeter-sl 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d71e9a34-5441-52db-809f-62d7faba799d.json b/oaitestdata/clarin-oai_dc/SET_1/json/d71e9a34-5441-52db-809f-62d7faba799d.json
deleted file mode 100644
index f9b80884..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d71e9a34-5441-52db-809f-62d7faba799d.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Burnard, Lou"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3025",
-    "MetadataAccess": [
-        "oai:ota:oucs:3025"
-    ],
-    "PublicationTimestamp": "1714-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1714"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pope, Alexander, 1688-1744"
-    ],
-    "fulltext": "oai:ota:oucs:3025;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3025.xml;The rape of the Lock: an heroi-comical poem in five canto's ;Pope, Alexander, 1688-1744;not after: 1714;text_and_corpus_linguistics;English poetry -- 18th century;eng;Oxford Text Archive, University of Oxford;Burnard, Lou;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d71e9a34-5441-52db-809f-62d7faba799d",
-    "oai_identifier": [
-        "oai:ota:oucs:3025"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English poetry -- th century"
-        }
-    ],
-    "title": [
-        "The rape of the Lock: an heroi-comical poem in five canto's "
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3025.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d726981f-9105-5b75-94f8-e616b4281f68.json b/oaitestdata/clarin-oai_dc/SET_1/json/d726981f-9105-5b75-94f8-e616b4281f68.json
deleted file mode 100644
index 0d75b3ab..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d726981f-9105-5b75-94f8-e616b4281f68.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4995",
-    "MetadataAccess": [
-        "oai:ota:oucs:4995"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Aikin, John, 1747-1822."
-    ],
-    "fulltext": "oai:ota:oucs:4995;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4995.xml;Evenings at home; or, the juvenile budget opened: Consisting of a variety of miscellaneous pieces, ... [pt.2];Aikin, John, 1747-1822.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d726981f-9105-5b75-94f8-e616b4281f68",
-    "oai_identifier": [
-        "oai:ota:oucs:4995"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Evenings at home; or, the juvenile budget opened: Consisting of a variety of miscellaneous pieces, ... [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4995.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d73aa3df-7187-56c2-a1ee-3d33f3a3e372.json b/oaitestdata/clarin-oai_dc/SET_1/json/d73aa3df-7187-56c2-a1ee-3d33f3a3e372.json
deleted file mode 100644
index 13ca4ffa..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d73aa3df-7187-56c2-a1ee-3d33f3a3e372.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "A"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1757",
-    "MetadataAccess": [
-        "oai:ota:oucs:1757"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Burroughs, Edgar Rice"
-    ],
-    "fulltext": "oai:ota:oucs:1757;2018-05-17T09:29:11Z;http://ota.ox.ac.uk/headers/1757.xml;A princess of Mars;Burroughs, Edgar Rice;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;A;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d73aa3df-7187-56c2-a1ee-3d33f3a3e372",
-    "oai_identifier": [
-        "oai:ota:oucs:1757"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A princess of Mars"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1757.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d73e1c9e-0caf-5e09-a87a-83d7bcf3a3d3.json b/oaitestdata/clarin-oai_dc/SET_1/json/d73e1c9e-0caf-5e09-a87a-83d7bcf3a3d3.json
deleted file mode 100644
index b6166014..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d73e1c9e-0caf-5e09-a87a-83d7bcf3a3d3.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "less than 512 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0027",
-    "MetadataAccess": [
-        "oai:ota:oucs:0027"
-    ],
-    "PublicationTimestamp": "1865-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1865"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Juvenile literature"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Carroll, Lewis,  1832-1898"
-    ],
-    "fulltext": "oai:ota:oucs:0027;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0027.xml; Alice in wonderland  / compiled by Lou Burnard;Carroll, Lewis,  1832-1898;1865;text_and_corpus_linguistics;Juvenile literature -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;less than 512 KB;Text;Juvenile literature;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d73e1c9e-0caf-5e09-a87a-83d7bcf3a3d3",
-    "oai_identifier": [
-        "oai:ota:oucs:0027"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Juvenile literature -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        " Alice in wonderland  / compiled by Lou Burnard"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0027.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d740b0b4-6f1a-5879-803d-e834e1cb6865.json b/oaitestdata/clarin-oai_dc/SET_1/json/d740b0b4-6f1a-5879-803d-e834e1cb6865.json
deleted file mode 100644
index c710fd8e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d740b0b4-6f1a-5879-803d-e834e1cb6865.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Waite, Stephen V.F."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 74 KB)"
-    ],
-    "Language": [
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0363",
-    "MetadataAccess": [
-        "oai:ota:oucs:0363"
-    ],
-    "PublicationYear": [
-        "71-113"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Letters"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pliny, the Younger"
-    ],
-    "fulltext": "oai:ota:oucs:0363;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0363.xml;C. Plini Caecili Secundi : Epistularum libri decem / Pliny the Younger;The tenth letter of Pliny the Younger;Epistulae 10;Pliny, the Younger;71-113;text_and_corpus_linguistics;Latin letters -- 1st century;lat;Oxford Text Archive, University of Oxford;Waite, Stephen V.F.;(1 file : ca. 74 KB);Text;Letters;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d740b0b4-6f1a-5879-803d-e834e1cb6865",
-    "oai_identifier": [
-        "oai:ota:oucs:0363"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Latin letters -- st century"
-        }
-    ],
-    "title": [
-        "C. Plini Caecili Secundi : Epistularum libri decem / Pliny the Younger",
-        "The tenth letter of Pliny the Younger",
-        "Epistulae 10"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0363.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d74135e7-2bde-5044-b1e4-946b30abff06.json b/oaitestdata/clarin-oai_dc/SET_1/json/d74135e7-2bde-5044-b1e4-946b30abff06.json
deleted file mode 100644
index 36dd7050..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d74135e7-2bde-5044-b1e4-946b30abff06.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3208",
-    "MetadataAccess": [
-        "oai:ota:oucs:3208"
-    ],
-    "PublicationTimestamp": "1897-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1897"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Stoker, Bram, 1847-1912"
-    ],
-    "fulltext": "oai:ota:oucs:3208;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3208.xml;Dracula;Stoker, Bram, 1847-1912;not after: 1897;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d74135e7-2bde-5044-b1e4-946b30abff06",
-    "oai_identifier": [
-        "oai:ota:oucs:3208"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Dracula"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3208.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d76803a3-493d-5ea9-bdd5-f5e417422d24.json b/oaitestdata/clarin-oai_dc/SET_1/json/d76803a3-493d-5ea9-bdd5-f5e417422d24.json
deleted file mode 100644
index ee5e6172..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d76803a3-493d-5ea9-bdd5-f5e417422d24.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2853",
-    "MetadataAccess": [
-        "oai:ota:oucs:2853"
-    ],
-    "PublicationTimestamp": "1732-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1732"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2853;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2853.xml;City cries, instrumental and vocal: or, an examination of certain abuses, corruptions, and enormities, in London and Dublin;Swift, Jonathan, 1667-1745;1732;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d76803a3-493d-5ea9-bdd5-f5e417422d24",
-    "oai_identifier": [
-        "oai:ota:oucs:2853"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "City cries, instrumental and vocal: or, an examination of certain abuses, corruptions, and enormities, in London and Dublin"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2853.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d76c5a4e-cf4d-5a60-b91d-c457bc15d97e.json b/oaitestdata/clarin-oai_dc/SET_1/json/d76c5a4e-cf4d-5a60-b91d-c457bc15d97e.json
deleted file mode 100644
index 57f5d665..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d76c5a4e-cf4d-5a60-b91d-c457bc15d97e.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Jan Wieczorek"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 3",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/427",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/427"
-    ],
-    "PID": "http://hdl.handle.net/11321/427",
-    "PublicationTimestamp": "2017-10-11T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Jan Wieczorek"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "R\u00f3\u017cni, Autorzy"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/427;2017-10-11T12:20:20Z;hdl_11321_3;hdl_11321_4;przem\u00f3wienia olsztyn;R\u00f3\u017cni, Autorzy;polityka;przem\u00f3wienie;Testo korpus przem\u00f3wie\u0144 politycznych;2017-10-11;corpus;http://hdl.handle.net/11321/427;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;text/plain;text/plain;text/plain;downloadable_files_count: 3;Jan Wieczorek",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d76c5a4e-cf4d-5a60-b91d-c457bc15d97e",
-    "notes": [
-        "Testo korpus przem\u00f3wie\u0144 politycznych"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/427"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "polityka"
-        },
-        {
-            "name": "polityka"
-        }
-    ],
-    "title": [
-        "przem\u00f3wienia olsztyn"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d794a32c-7fb6-5f2d-b3d9-c75f5d62cc8b.json b/oaitestdata/clarin-oai_dc/SET_1/json/d794a32c-7fb6-5f2d-b3d9-c75f5d62cc8b.json
deleted file mode 100644
index 78233d12..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d794a32c-7fb6-5f2d-b3d9-c75f5d62cc8b.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "TALG Research Group (University of Vigo)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English",
-        "French",
-        "Galician",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-616",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-616"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-616",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "TALG Research Group (University of Vigo)"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-616;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Termoteca;Galician terminology databank, 6,000 terms;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-616;eng;fra;glg;spa;downloadable_files_count: 0;Spain;TALG Research Group (University of Vigo);http://sli.uvigo.es/termoteca",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d794a32c-7fb6-5f2d-b3d9-c75f5d62cc8b",
-    "notes": [
-        "Galician terminology databank, 6,000 terms"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-616"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Termoteca"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d79bafa8-7542-5841-bd07-95848803c47f.json b/oaitestdata/clarin-oai_dc/SET_1/json/d79bafa8-7542-5841-bd07-95848803c47f.json
deleted file mode 100644
index fe270f74..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d79bafa8-7542-5841-bd07-95848803c47f.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/44",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/44"
-    ],
-    "PID": "http://hdl.handle.net/10794/44",
-    "PublicationTimestamp": "2012-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/44;2017-10-27T11:10:03Z;hdl_10794_1;hdl_10794_2;Swesaurus (2017-10-16);Swesaurus (2017-10-16);n/a, n/a;Swedish;A Swedish WordNet.;Ett svenskt ordn\u00e4t.;2012-05-30;lexicalConceptualResource;http://hdl.handle.net/10794/44;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/swesaurus",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d79bafa8-7542-5841-bd07-95848803c47f",
-    "notes": [
-        "A Swedish WordNet.",
-        "Ett svenskt ordn\u00e4t."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/44"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        }
-    ],
-    "title": [
-        "Swesaurus (2017-10-16)",
-        "Swesaurus (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d79db917-ef5a-5178-996e-405a0583d4ba.json b/oaitestdata/clarin-oai_dc/SET_1/json/d79db917-ef5a-5178-996e-405a0583d4ba.json
deleted file mode 100644
index 90695e4f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d79db917-ef5a-5178-996e-405a0583d4ba.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1407",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1407"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1407",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1407;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;tfidf;It calculates the Term Frequency and the Inverse Document Frequency of a word in a given corpus (a statistical measure used to evaluate how important a word is to a document in a collection or corpus).;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1407;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d79db917-ef5a-5178-996e-405a0583d4ba",
-    "notes": [
-        "It calculates the Term Frequency and the Inverse Document Frequency of a word in a given corpus (a statistical measure used to evaluate how important a word is to a document in a collection or corpus)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1407"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "tfidf"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d7b27c7e-d1b9-5801-82a7-613bc62510b2.json b/oaitestdata/clarin-oai_dc/SET_1/json/d7b27c7e-d1b9-5801-82a7-613bc62510b2.json
deleted file mode 100644
index 6bf8bcda..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d7b27c7e-d1b9-5801-82a7-613bc62510b2.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5226",
-    "MetadataAccess": [
-        "oai:ota:oucs:5226"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Farmer, Richard, 1735-1797."
-    ],
-    "fulltext": "oai:ota:oucs:5226;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5226.xml;An essay on the learning of Shakespeare: addressed to Joseph Cradock, Esq; The second edition, with large additions. By Richard Farmer, ...;Farmer, Richard, 1735-1797.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d7b27c7e-d1b9-5801-82a7-613bc62510b2",
-    "oai_identifier": [
-        "oai:ota:oucs:5226"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An essay on the learning of Shakespeare: addressed to Joseph Cradock, Esq; The second edition, with large additions. By Richard Farmer, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5226.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d7d6afef-75aa-5760-81c6-9d1d0dd068ce.json b/oaitestdata/clarin-oai_dc/SET_1/json/d7d6afef-75aa-5760-81c6-9d1d0dd068ce.json
deleted file mode 100644
index 33ade6fb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d7d6afef-75aa-5760-81c6-9d1d0dd068ce.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "project_gutenberg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/504",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/504"
-    ],
-    "PID": "http://hdl.handle.net/11321/504",
-    "PublicationTimestamp": "2018-06-20T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "project_gutenberg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN-EULA-ACA-v1.0",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca",
-        "ACA"
-    ],
-    "author": [
-        "Stolarski, \u0141ukasz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/504;2018-06-20T11:00:12Z;hdl_11321_3;hdl_11321_4;pan_tadeusz;Stolarski, \u0141ukasz;literature;These are testing materials.;2018-06-20;corpus;http://hdl.handle.net/11321/504;pol;CLARIN-EULA-ACA-v1.0;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca;ACA;text/plain; charset=utf-8;text/plain;downloadable_files_count: 1;project_gutenberg",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d7d6afef-75aa-5760-81c6-9d1d0dd068ce",
-    "notes": [
-        "These are testing materials."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/504"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "literature"
-        }
-    ],
-    "title": [
-        "pan_tadeusz"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d810baf0-db88-58d3-9b64-dd5089487ea8.json b/oaitestdata/clarin-oai_dc/SET_1/json/d810baf0-db88-58d3-9b64-dd5089487ea8.json
deleted file mode 100644
index 7c51b816..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d810baf0-db88-58d3-9b64-dd5089487ea8.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1146",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1146"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1146",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1146;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;canoonet \u2013 Deutsche W\u00f6rterb\u00fccher und Grammatik;Germanistik;Angabe von orthographischen, morphologischen (Wortformenbildung und Wortbildung) sowie semantischen Informationen (Synonymie; Hyperonymie/Hyponymie); Zuordnung der W\u00f6rter zu der jeweiligen syntaktischen Kategorie (bei Substantiven zus\u00e4tzlich Angabe des Genus);2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1146;deu;downloadable_files_count: 0;Germany;http://www.canoo.net/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d810baf0-db88-58d3-9b64-dd5089487ea8",
-    "notes": [
-        "Angabe von orthographischen, morphologischen (Wortformenbildung und Wortbildung) sowie semantischen Informationen (Synonymie; Hyperonymie/Hyponymie); Zuordnung der W\u00f6rter zu der jeweiligen syntaktischen Kategorie (bei Substantiven zus\u00e4tzlich Angabe des Genus)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1146"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "canoonet \u2013 Deutsche W\u00f6rterb\u00fccher und Grammatik"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d811d0f5-c5d1-5230-a8f5-f657048ba63d.json b/oaitestdata/clarin-oai_dc/SET_1/json/d811d0f5-c5d1-5230-a8f5-f657048ba63d.json
deleted file mode 100644
index 4c596510..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d811d0f5-c5d1-5230-a8f5-f657048ba63d.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "Contributor": [
-        "Mihov, Stoyan"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Bulgarian",
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-231",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-231"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-231",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Bulgaria"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-231;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Ocorrect  Corpus;Mihov, Stoyan;Written, synchronic, general, bilingual, text and image; 1 000 000 tokens Bulgarian2300 image files150 000 tokens Greman312 image files;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-231;bul;deu;downloadable_files_count: 0;Bulgaria;http://lml.bas.bg/~stoyan/ocorrect/index.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d811d0f5-c5d1-5230-a8f5-f657048ba63d",
-    "notes": [
-        "Written, synchronic, general, bilingual, text and image; 1 000 000 tokens Bulgarian2300 image files150 000 tokens Greman312 image files"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-231"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Ocorrect  Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d82fb72b-efb0-57f8-97c9-e0860fabd0e9.json b/oaitestdata/clarin-oai_dc/SET_1/json/d82fb72b-efb0-57f8-97c9-e0860fabd0e9.json
deleted file mode 100644
index eb38ce9f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d82fb72b-efb0-57f8-97c9-e0860fabd0e9.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 4.06 MB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2097",
-    "MetadataAccess": [
-        "oai:ota:oucs:2097"
-    ],
-    "PublicationYear": [
-        "69-120"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Biographies"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Plutarch"
-    ],
-    "fulltext": "oai:ota:oucs:2097;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/2097.xml;Lives. English;The lives of the noble Grecians and Romans / by several hands;Plutarch;69-120;text_and_corpus_linguistics;Biographies;eng;Oxford Text Archive, University of Oxford;Triggs, Jeffery;text/sgml;(1 file : ca. 4.06 MB);Text;Biographies;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d82fb72b-efb0-57f8-97c9-e0860fabd0e9",
-    "oai_identifier": [
-        "oai:ota:oucs:2097"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Biographies"
-        }
-    ],
-    "title": [
-        "Lives. English",
-        "The lives of the noble Grecians and Romans / by several hands"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2097.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d830cac5-c339-505d-9755-f1f2a03abc18.json b/oaitestdata/clarin-oai_dc/SET_1/json/d830cac5-c339-505d-9755-f1f2a03abc18.json
deleted file mode 100644
index fb77cd35..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d830cac5-c339-505d-9755-f1f2a03abc18.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "\u015awi\u0119tochowski"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 28",
-        "application/zip",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/93",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/93"
-    ],
-    "PID": "http://hdl.handle.net/11321/93",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "\u015awi\u0119tochowski"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "\u015awi\u0119tochowski, \u015awi\u0119tochowski"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/93;2015-05-19T13:44:26Z;hdl_11321_3;hdl_11321_4;MWE \u015awi\u0119tochowski;\u015awi\u0119tochowski, \u015awi\u0119tochowski;\u015awi\u0119tochowski;2015-04-08;corpus;http://hdl.handle.net/11321/93;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 28;\u015awi\u0119tochowski",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d830cac5-c339-505d-9755-f1f2a03abc18",
-    "notes": [
-        "\u015awi\u0119tochowski"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/93"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE \u015awi\u0119tochowski"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d83160ef-7e3e-5363-93c1-5548e583a0e3.json b/oaitestdata/clarin-oai_dc/SET_1/json/d83160ef-7e3e-5363-93c1-5548e583a0e3.json
deleted file mode 100644
index 40f5bd2f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d83160ef-7e3e-5363-93c1-5548e583a0e3.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "University of Wroclaw"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/vnd.oasis.opendocument.text",
-        "downloadable_files_count: 10",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/375",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/375"
-    ],
-    "PID": "http://hdl.handle.net/11321/375",
-    "PublicationTimestamp": "2017-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "University of Wroclaw"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Osoba, Druga",
-        "Reznik, Zofia"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/375;2017-05-30T07:55:19Z;hdl_11321_3;hdl_11321_4;Zas\u00f3b testowy;Reznik, Zofia;Osoba, Druga;bajki;inflection;diachronic;aaa;2017-05-30;corpus;http://hdl.handle.net/11321/375;pol;a;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;application/vnd.oasis.opendocument.text;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;text/plain;text/plain;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;downloadable_files_count: 10;University of Wroclaw",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d83160ef-7e3e-5363-93c1-5548e583a0e3",
-    "notes": [
-        "aaa"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/375"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "bajki"
-        },
-        {
-            "name": "inflection"
-        },
-        {
-            "name": "diachronic"
-        }
-    ],
-    "title": [
-        "Zas\u00f3b testowy"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d838c337-b481-5fbd-b436-0869ead80ced.json b/oaitestdata/clarin-oai_dc/SET_1/json/d838c337-b481-5fbd-b436-0869ead80ced.json
deleted file mode 100644
index 48cea5b7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d838c337-b481-5fbd-b436-0869ead80ced.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Masaryk University, NLP Centre"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-1B2E-0",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-1B2E-0"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-1B2E-0",
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Masaryk University, NLP Centre"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u010capek, Tom\u00e1\u0161",
-        "Gr\u00e1c, Marek"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-1B2E-0;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;sholva-0.6;Gr\u00e1c, Marek;\u010capek, Tom\u00e1\u0161;Semantic net `sholva' contains more than 150 000 records for which there was sufficient agreement among annotators. Indvidual words are labeled in the following categories:\r\nperson, person / individual, event and substance.;2011;lexicalConceptualResource;http://hdl.handle.net/11858/00-097C-0000-0023-1B2E-0;ces;Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0);http://creativecommons.org/licenses/by-nc-nd/3.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Masaryk University, NLP Centre;https://nlp.fi.muni.cz/projekty/sholva/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d838c337-b481-5fbd-b436-0869ead80ced",
-    "notes": [
-        "Semantic net `sholva' contains more than 150 000 records for which there was sufficient agreement among annotators. Indvidual words are labeled in the following categories:\r\nperson, person / individual, event and substance."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-1B2E-0"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "title": [
-        "sholva-0.6"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d83c5818-83d2-5998-952d-15f16e50a918.json b/oaitestdata/clarin-oai_dc/SET_1/json/d83c5818-83d2-5998-952d-15f16e50a918.json
deleted file mode 100644
index ed75c6c1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d83c5818-83d2-5998-952d-15f16e50a918.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Wojciech Jaworski"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/octet-stream",
-        "downloadable_files_count: 3",
-        "application/gzip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/264",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/264"
-    ],
-    "PID": "http://hdl.handle.net/11321/264",
-    "PublicationTimestamp": "2016-05-22T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wojciech Jaworski"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "Jaworski, Wojciech"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/264;2016-05-26T08:26:14Z;hdl_11321_3;hdl_11321_4;ENIAM;Jaworski, Wojciech;constituency parsing;semantics;meaning representation;ENIAM: Categorial Syntactic-Semantic Parser for Polish;2016-05-22;toolService;http://hdl.handle.net/11321/264;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/gzip;application/gzip;application/gzip;application/octet-stream;application/octet-stream;downloadable_files_count: 3;Wojciech Jaworski;http://zil.ipipan.waw.pl/ENIAM",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d83c5818-83d2-5998-952d-15f16e50a918",
-    "notes": [
-        "ENIAM: Categorial Syntactic-Semantic Parser for Polish"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/264"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "constituency parsing"
-        },
-        {
-            "name": "semantics"
-        },
-        {
-            "name": "meaning representation"
-        }
-    ],
-    "title": [
-        "ENIAM"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d850f445-a31e-570a-b5f6-1569a16963de.json b/oaitestdata/clarin-oai_dc/SET_1/json/d850f445-a31e-570a-b5f6-1569a16963de.json
deleted file mode 100644
index fd4fe026..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d850f445-a31e-570a-b5f6-1569a16963de.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 74.8 KB)"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0237",
-    "MetadataAccess": [
-        "oai:ota:oucs:0237"
-    ],
-    "PublicationYear": [
-        "388 BCE"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Aristophanes"
-    ],
-    "fulltext": "oai:ota:oucs:0237;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0237.xml;Plutus;The Plutus of Aristophanes;Wealth;Aristophanes;388 BCE;text_and_corpus_linguistics;Plays -- Greece -- B.C.;grc;Oxford Text Archive, University of Oxford;(1 file : ca. 74.8 KB);Text;Plays;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d850f445-a31e-570a-b5f6-1569a16963de",
-    "oai_identifier": [
-        "oai:ota:oucs:0237"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- Greece -- B.C."
-        }
-    ],
-    "title": [
-        "Plutus",
-        "The Plutus of Aristophanes",
-        "Wealth"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0237.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d85e6f54-f31f-5903-bc6c-2d34d96a0465.json b/oaitestdata/clarin-oai_dc/SET_1/json/d85e6f54-f31f-5903-bc6c-2d34d96a0465.json
deleted file mode 100644
index 405ce935..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d85e6f54-f31f-5903-bc6c-2d34d96a0465.json
+++ /dev/null
@@ -1,92 +0,0 @@
-{
-    "Contact": [
-        "Uppsala University"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "English",
-        "Spanish",
-        "German",
-        "French"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2393",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2393"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2393",
-    "PublicationTimestamp": "2017-09-20T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Uppsala University"
-    ],
-    "RelatedIdentifier": [
-        "http://aclweb.org/anthology/W/W17/W17-4801.pdf"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Hardmeier, Christian",
-        "Cettolo, Mauro",
-        "Lo\u00e1iciga, Sharid",
-        "Stymne, Sara",
-        "Nakov, Preslav",
-        "Tiedemann, J\u00f6rg",
-        "Versley, Yannick"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2393;2017-09-27T10:17:43Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;DiscoMT 2017 Shared Task on Cross-lingual Pronoun Prediction;Lo\u00e1iciga, Sharid;Stymne, Sara;Nakov, Preslav;Hardmeier, Christian;Tiedemann, J\u00f6rg;Cettolo, Mauro;Versley, Yannick;machine translation;discourse;coreference;pronouns;Data used in the 2017 shared task on cross-lingual pronoun prediction.;2017-09-20;corpus;http://hdl.handle.net/11234/1-2393;eng;spa;deu;fra;http://aclweb.org/anthology/W/W17/W17-4801.pdf;Creative Commons - Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0);http://creativecommons.org/licenses/by-nc-nd/4.0/;PUB;application/octet-stream;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 8;Uppsala University;https://tuhat.helsinki.fi/portal/en/projects/discourseoriented-s(b4bebd83-46cd-46da-8426-3628391cfc92).html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d85e6f54-f31f-5903-bc6c-2d34d96a0465",
-    "notes": [
-        "Data used in the 2017 shared task on cross-lingual pronoun prediction."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2393"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "discourse"
-        },
-        {
-            "name": "coreference"
-        },
-        {
-            "name": "pronouns"
-        }
-    ],
-    "title": [
-        "DiscoMT 2017 Shared Task on Cross-lingual Pronoun Prediction"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d88473f4-af96-5939-95ce-e8b116a4adc0.json b/oaitestdata/clarin-oai_dc/SET_1/json/d88473f4-af96-5939-95ce-e8b116a4adc0.json
deleted file mode 100644
index 60145ccd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d88473f4-af96-5939-95ce-e8b116a4adc0.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "English",
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-466F-C",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-466F-C"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-466F-C",
-    "PublicationTimestamp": "2014-02-21T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Apache License 2.0",
-        "http://opensource.org/licenses/Apache-2.0",
-        "PUB"
-    ],
-    "author": [
-        "\u017dilka, Luk\u00e1\u0161",
-        "Jur\u010d\u00ed\u010dek, Filip",
-        "Du\u0161ek, Ond\u0159ej",
-        "Pl\u00e1tek, Ond\u0159ej",
-        "Korvas, Mat\u011bj"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-466F-C;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Vystadial 2013 \u2013 scripts;Korvas, Mat\u011bj;Pl\u00e1tek, Ond\u0159ej;Du\u0161ek, Ond\u0159ej;\u017dilka, Luk\u00e1\u0161;Jur\u010d\u00ed\u010dek, Filip;ASR;HTK;Kaldi;acoustic model;Vystadial 2013 is a dataset of telephone conversations in English and Czech, developed for training acoustic models for automatic speech recognition in spoken dialogue systems. It ships in three parts: Czech data, English data, and scripts.\r\n\r\nThe data comprise over 41 hours of speech in English and over 15 hours in Czech, plus orthographic transcriptions. The scripts implement data pre-processing and building acoustic models using the HTK and Kaldi toolkits.\r\n\r\nThis is the scripts part of the dataset.;2014-02-21;toolService;http://hdl.handle.net/11858/00-097C-0000-0023-466F-C;eng;ces;Apache License 2.0;http://opensource.org/licenses/Apache-2.0;PUB;text/plain; charset=utf-8;application/x-gzip;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics;https://ufal.mff.cuni.cz/grants/vystadial",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d88473f4-af96-5939-95ce-e8b116a4adc0",
-    "notes": [
-        "Vystadial 2013 is a dataset of telephone conversations in English and Czech, developed for training acoustic models for automatic speech recognition in spoken dialogue systems. It ships in three parts: Czech data, English data, and scripts.\r\n\r\nThe data comprise over 41 hours of speech in English and over 15 hours in Czech, plus orthographic transcriptions. The scripts implement data pre-processing and building acoustic models using the HTK and Kaldi toolkits.\r\n\r\nThis is the scripts part of the dataset."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-466F-C"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ASR"
-        },
-        {
-            "name": "HTK"
-        },
-        {
-            "name": "Kaldi"
-        },
-        {
-            "name": "acoustic model"
-        }
-    ],
-    "title": [
-        "Vystadial 2013 \u2013 scripts"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d89f0ffa-054d-5b5d-ac47-051b732cfd90.json b/oaitestdata/clarin-oai_dc/SET_1/json/d89f0ffa-054d-5b5d-ac47-051b732cfd90.json
deleted file mode 100644
index f8025a38..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d89f0ffa-054d-5b5d-ac47-051b732cfd90.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3633",
-    "MetadataAccess": [
-        "oai:ota:oucs:3633"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pratt, Mr. (Samuel Jackson), 1749-1814."
-    ],
-    "fulltext": "oai:ota:oucs:3633;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3633.xml;An apology for the life and writings of David Hume, Esq: with a parallel between him and the late Lord Chesterfield: to which is added an address to one of the people called Christians. By way of reply to his letter to Adam Smith, L.L.D.;Pratt, Mr. (Samuel Jackson), 1749-1814.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d89f0ffa-054d-5b5d-ac47-051b732cfd90",
-    "oai_identifier": [
-        "oai:ota:oucs:3633"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An apology for the life and writings of David Hume, Esq: with a parallel between him and the late Lord Chesterfield: to which is added an address to one of the people called Christians. By way of reply to his letter to Adam Smith, L.L.D."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3633.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d8a65678-b781-5400-bdc6-5b3a63ff1778.json b/oaitestdata/clarin-oai_dc/SET_1/json/d8a65678-b781-5400-bdc6-5b3a63ff1778.json
deleted file mode 100644
index 40e66aba..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d8a65678-b781-5400-bdc6-5b3a63ff1778.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Fundacja nowoczesna Polska"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/pdf"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/341",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/341"
-    ],
-    "PID": "http://hdl.handle.net/11321/341",
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Fundacja nowoczesna Polska"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "plWordNet",
-        "http://clarin-pl.eu/en/licenses/plwordnet-2/",
-        "PUB"
-    ],
-    "author": [
-        "Prus, Boles\u0142aw"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/341;2017-04-01T11:09:19Z;hdl_11321_3;hdl_11321_4;Lalka;Prus, Boles\u0142aw;lalka;prus;novel;a book in Polish by Boles\u0142aw Prus;2014;corpus;http://hdl.handle.net/11321/341;pol;plWordNet;http://clarin-pl.eu/en/licenses/plwordnet-2/;PUB;text/plain; charset=utf-8;application/pdf;downloadable_files_count: 1;Fundacja nowoczesna Polska",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d8a65678-b781-5400-bdc6-5b3a63ff1778",
-    "notes": [
-        "a book in Polish by Boles\u0142aw Prus"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/341"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "lalka"
-        },
-        {
-            "name": "prus"
-        },
-        {
-            "name": "novel"
-        }
-    ],
-    "title": [
-        "Lalka"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d8c34beb-ec7c-54c4-b945-1bedb34d2fe3.json b/oaitestdata/clarin-oai_dc/SET_1/json/d8c34beb-ec7c-54c4-b945-1bedb34d2fe3.json
deleted file mode 100644
index 1a3c9898..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d8c34beb-ec7c-54c4-b945-1bedb34d2fe3.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "Dhivehi"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-910",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-910"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-910",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-910;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Divehi;ca. 100.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-910;div;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#dhiv",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d8c34beb-ec7c-54c4-b945-1bedb34d2fe3",
-    "notes": [
-        "ca. 100.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-910"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Divehi"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d8c52c4f-ea33-5187-9d10-8171e6a59f04.json b/oaitestdata/clarin-oai_dc/SET_1/json/d8c52c4f-ea33-5187-9d10-8171e6a59f04.json
deleted file mode 100644
index f0ce545b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d8c52c4f-ea33-5187-9d10-8171e6a59f04.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "1 file, 105 MB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0009",
-    "MetadataAccess": [
-        "oai:ota:oucs:0009"
-    ],
-    "PublicationTimestamp": "1605-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1605"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Unknown"
-    ],
-    "fulltext": "oai:ota:oucs:0009;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0009.xml;The True Chronicle History of King Leir and his three daughters, Gonorill, Ragan and Cordella;Unknown;1605;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;1 file, 105 MB;Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d8c52c4f-ea33-5187-9d10-8171e6a59f04",
-    "oai_identifier": [
-        "oai:ota:oucs:0009"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The True Chronicle History of King Leir and his three daughters, Gonorill, Ragan and Cordella"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0009.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d8ce141c-3f9e-5dde-9092-85c982c06f74.json b/oaitestdata/clarin-oai_dc/SET_1/json/d8ce141c-3f9e-5dde-9092-85c982c06f74.json
deleted file mode 100644
index 9a0376b9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d8ce141c-3f9e-5dde-9092-85c982c06f74.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2884",
-    "MetadataAccess": [
-        "oai:ota:oucs:2884"
-    ],
-    "PublicationTimestamp": "1711-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1711"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2884;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2884.xml;Thoughts on various subjects;Swift, Jonathan, 1667-1745;1711;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d8ce141c-3f9e-5dde-9092-85c982c06f74",
-    "oai_identifier": [
-        "oai:ota:oucs:2884"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Thoughts on various subjects"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2884.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d8f2c4cd-1754-5519-8a4c-0b61715533e6.json b/oaitestdata/clarin-oai_dc/SET_1/json/d8f2c4cd-1754-5519-8a4c-0b61715533e6.json
deleted file mode 100644
index 62d1ee3e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d8f2c4cd-1754-5519-8a4c-0b61715533e6.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1041",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1041"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1041",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1041;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;L1 & L2 Acquisition Christine Dimroth German Project;Language Acquisition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1041;deu;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI520844%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d8f2c4cd-1754-5519-8a4c-0b61715533e6",
-    "notes": [
-        "Language Acquisition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1041"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "L1 & L2 Acquisition Christine Dimroth German Project"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d911d941-154a-55e5-97aa-f430a77353da.json b/oaitestdata/clarin-oai_dc/SET_1/json/d911d941-154a-55e5-97aa-f430a77353da.json
deleted file mode 100644
index 9a713934..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d911d941-154a-55e5-97aa-f430a77353da.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Institut f\u00fcr Deutsche Sprache"
-    ],
-    "Contributor": [
-        "Kupietz, Marc"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-261",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-261"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-261",
-    "PublicationTimestamp": "1964-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1964"
-    ],
-    "Publisher": [
-        "Institut f\u00fcr Deutsche Sprache"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "non-commercial, non-download license, EULA: http://www.ids-mannheim.de/cosmas2/projekt/registrierung/",
-        "http://www.ids-mannheim.de/cosmas2/projekt/registrierung/"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-261;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Deutsches Referenzkorpus (DeReKo);Kupietz, Marc;Germanistik;written general monolingual synchronic (1959-) reference corpus archive; 5.4 billion words;  structural information down to sentence level, rich bibliographic metadata, partial layout information, fully morpho-syntactically annotated;1964-01-01;corpus;http://hdl.handle.net/11372/LRT-261;deu;non-commercial, non-download license, EULA: http://www.ids-mannheim.de/cosmas2/projekt/registrierung/;http://www.ids-mannheim.de/cosmas2/projekt/registrierung/;application/octet-stream;downloadable_files_count: 0;Germany;Institut f\u00fcr Deutsche Sprache;http://www.ids-mannheim.de/kl/projekte/korpora/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d911d941-154a-55e5-97aa-f430a77353da",
-    "notes": [
-        "written general monolingual synchronic (1959-) reference corpus archive; 5.4 billion words;  structural information down to sentence level, rich bibliographic metadata, partial layout information, fully morpho-syntactically annotated"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-261"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Deutsches Referenzkorpus (DeReKo)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d915a964-f24d-5b34-8fe9-bb9327a18aa1.json b/oaitestdata/clarin-oai_dc/SET_1/json/d915a964-f24d-5b34-8fe9-bb9327a18aa1.json
deleted file mode 100644
index 8304629c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d915a964-f24d-5b34-8fe9-bb9327a18aa1.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Masaryk University, NLP Centre"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-000D-F67B-7",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-000D-F67B-7"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-000D-F67B-7",
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Masaryk University, NLP Centre"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "BSD 3-Clause \"New\" or \"Revised\" license",
-        "http://opensource.org/licenses/BSD-3-Clause",
-        "PUB"
-    ],
-    "author": [
-        "Pomik\u00e1lek, Jan"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-000D-F67B-7;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;onion;Pomik\u00e1lek, Jan;deduplication;corpus;text deduplication;n-gram deduplication;n-gram model;onion (ONe Instance ONly) is a tool for removing duplicate parts from large collections of texts. The tool has been implemented in Python, licensed under New BSD License and made an open source software (available for download including the source code at http://code.google.com/p/onion/). It is being successfuly used for cleaning large textual corpora at Natural language processing centre at Faculty of informatics, Masaryk university Brno and it's industry partners. The research leading to this piece of software was published in author's Ph.D. thesis \"Removing Boilerplate and Duplicate Content from Web Corpora\". The deduplication algorithm is based on comparing n-grams of words of text. The author's algorithm has been shown to be more suitable for textual corpora deduplication than competing algorithms (Broder, Charikar): in addition to detection of identical or very similar (95 %) duplicates, it is able to detect even partially similar duplicates (50 %) still achieving great performace (further described in author's Ph.D. thesis). The unique deduplication capabilities and scalability of the algorithm were been demonstrated while building corpora of American Spanish, Arabic, Czech, French, Japanese, Russian, Tajik, and six Turkic languages consisting --- several TB of text documents were deduplicated resulting in corpora of 70 billions tokens altogether.;2011;toolService;http://hdl.handle.net/11858/00-097C-0000-000D-F67B-7;eng;BSD 3-Clause \"New\" or \"Revised\" license;http://opensource.org/licenses/BSD-3-Clause;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Masaryk University, NLP Centre;http://code.google.com/p/onion/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d915a964-f24d-5b34-8fe9-bb9327a18aa1",
-    "notes": [
-        "onion (ONe Instance ONly) is a tool for removing duplicate parts from large collections of texts. The tool has been implemented in Python, licensed under New BSD License and made an open source software (available for download including the source code at http://code.google.com/p/onion/). It is being successfuly used for cleaning large textual corpora at Natural language processing centre at Faculty of informatics, Masaryk university Brno and it's industry partners. The research leading to this piece of software was published in author's Ph.D. thesis \"Removing Boilerplate and Duplicate Content from Web Corpora\". The deduplication algorithm is based on comparing n-grams of words of text. The author's algorithm has been shown to be more suitable for textual corpora deduplication than competing algorithms (Broder, Charikar): in addition to detection of identical or very similar (95 %) duplicates, it is able to detect even partially similar duplicates (50 %) still achieving great performace (further described in author's Ph.D. thesis). The unique deduplication capabilities and scalability of the algorithm were been demonstrated while building corpora of American Spanish, Arabic, Czech, French, Japanese, Russian, Tajik, and six Turkic languages consisting --- several TB of text documents were deduplicated resulting in corpora of 70 billions tokens altogether."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-000D-F67B-7"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "deduplication"
-        },
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "text deduplication"
-        },
-        {
-            "name": "n-gram deduplication"
-        },
-        {
-            "name": "n-gram model"
-        }
-    ],
-    "title": [
-        "onion"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d94250f7-d8b3-533d-a2af-44862153567c.json b/oaitestdata/clarin-oai_dc/SET_1/json/d94250f7-d8b3-533d-a2af-44862153567c.json
deleted file mode 100644
index 15154b9d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d94250f7-d8b3-533d-a2af-44862153567c.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "Filesize uncompressed: 1928 KBytes. "
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2127",
-    "MetadataAccess": [
-        "oai:ota:oucs:2127"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dickens, Charles, 1812-1870"
-    ],
-    "fulltext": "oai:ota:oucs:2127;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/2127.xml;Martin Chuzzlewit;A machine-readable transcription;Dickens, Charles, 1812-1870;text_and_corpus_linguistics;Oxford Text Archive, University of Oxford;Filesize uncompressed: 1928 KBytes. ;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d94250f7-d8b3-533d-a2af-44862153567c",
-    "oai_identifier": [
-        "oai:ota:oucs:2127"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Martin Chuzzlewit",
-        "A machine-readable transcription"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2127.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d94d0c73-5b24-59e8-8bf7-f08910c802aa.json b/oaitestdata/clarin-oai_dc/SET_1/json/d94d0c73-5b24-59e8-8bf7-f08910c802aa.json
deleted file mode 100644
index 29621751..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d94d0c73-5b24-59e8-8bf7-f08910c802aa.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2658",
-    "MetadataAccess": [
-        "oai:ota:oucs:2658"
-    ],
-    "PublicationTimestamp": "1789-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1789"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2658;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2658.xml;On the bill for the clergy's residing on their livings;Swift, Jonathan, 1667-1745;1789;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d94d0c73-5b24-59e8-8bf7-f08910c802aa",
-    "oai_identifier": [
-        "oai:ota:oucs:2658"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "On the bill for the clergy's residing on their livings"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2658.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d9516ac0-0a96-5ffb-b2b5-d04c91afd992.json b/oaitestdata/clarin-oai_dc/SET_1/json/d9516ac0-0a96-5ffb-b2b5-d04c91afd992.json
deleted file mode 100644
index e3ae82a8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d9516ac0-0a96-5ffb-b2b5-d04c91afd992.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Jakub Zarzycki"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 535",
-        "image/jpeg",
-        "text/plain; charset=utf-8",
-        "text/richtext",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/octet-stream",
-        "application/vnd.oasis.opendocument.text",
-        "application/pdf",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/607",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/607"
-    ],
-    "PID": "http://hdl.handle.net/11321/607",
-    "PublicationTimestamp": "2018-10-04T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Jakub Zarzycki"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN-EULA-ACA-v1.0",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca",
-        "ACA"
-    ],
-    "author": [
-        "Wieczorek, Jan",
-        "Zarzycki, Jakub"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/607;2018-10-23T08:36:20Z;hdl_11321_3;hdl_11321_608;Siemiradzki 3.0;Zarzycki, Jakub;Wieczorek, Jan;siemiradzki;historia sztuki;history of art;Trzecia wersja korpusu materia\u0142\u00f3w;2018-10-04;corpus;http://hdl.handle.net/11321/607;pol;CLARIN-EULA-ACA-v1.0;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca;ACA;text/plain; charset=utf-8;application/msword;application/msword;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/pdf;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/pdf;application/msword;application/pdf;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/msword;application/pdf;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/pdf;application/pdf;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/pdf;application/pdf;application/msword;application/pdf;application/msword;application/msword;application/msword;application/pdf;application/pdf;application/pdf;application/msword;application/msword;application/msword;application/pdf;application/pdf;application/msword;application/pdf;application/pdf;application/pdf;application/msword;application/msword;application/pdf;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/msword;application/msword;application/msword;application/pdf;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/msword;application/msword;application/msword;application/msword;application/pdf;application/pdf;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/msword;application/msword;application/msword;application/pdf;application/pdf;application/pdf;application/msword;application/msword;application/msword;application/msword;application/msword;application/pdf;application/msword;application/pdf;application/pdf;application/msword;application/pdf;application/msword;application/pdf;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/pdf;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/pdf;application/msword;application/pdf;application/msword;application/pdf;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/pdf;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/msword;application/msword;application/msword;application/msword;application/pdf;application/pdf;application/msword;application/msword;application/msword;application/pdf;application/msword;application/msword;application/pdf;application/msword;application/pdf;application/pdf;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/pdf;application/msword;application/msword;application/pdf;application/msword;application/msword;application/msword;application/msword;application/msword;application/pdf;application/msword;application/msword;application/pdf;application/msword;application/msword;application/pdf;application/msword;application/msword;application/pdf;application/pdf;application/msword;application/msword;application/msword;application/pdf;application/msword;application/msword;application/pdf;application/msword;image/jpeg;image/jpeg;application/pdf;application/msword;application/pdf;application/pdf;application/msword;application/msword;application/pdf;application/pdf;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;image/jpeg;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/pdf;application/msword;application/pdf;application/msword;application/pdf;application/msword;application/msword;application/msword;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/msword;application/msword;application/pdf;application/pdf;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/pdf;application/msword;application/msword;application/pdf;application/pdf;application/pdf;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/pdf;application/msword;text/richtext;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/pdf;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/pdf;application/pdf;application/msword;application/octet-stream;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/vnd.oasis.opendocument.text;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/pdf;application/msword;application/msword;application/msword;application/msword;application/msword;application/pdf;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/pdf;application/pdf;application/msword;application/msword;application/msword;application/pdf;application/msword;application/msword;application/pdf;application/msword;application/pdf;application/msword;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/pdf;application/msword;application/msword;application/msword;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/pdf;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/pdf;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/pdf;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/pdf;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/pdf;application/msword;application/msword;application/msword;downloadable_files_count: 535;Jakub Zarzycki",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d9516ac0-0a96-5ffb-b2b5-d04c91afd992",
-    "notes": [
-        "Trzecia wersja korpusu materia\u0142\u00f3w"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/607"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_608"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "siemiradzki"
-        },
-        {
-            "name": "historia sztuki"
-        },
-        {
-            "name": "history art"
-        }
-    ],
-    "title": [
-        "Siemiradzki 3.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d96b5694-0001-5930-b1d6-b62dc791b9d5.json b/oaitestdata/clarin-oai_dc/SET_1/json/d96b5694-0001-5930-b1d6-b62dc791b9d5.json
deleted file mode 100644
index 752d5b61..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d96b5694-0001-5930-b1d6-b62dc791b9d5.json
+++ /dev/null
@@ -1,98 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 3",
-        "application/pdf",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Serbian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1120",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1120"
-    ],
-    "PID": "http://hdl.handle.net/11356/1120",
-    "PublicationTimestamp": "2017-05-14T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11356/1171",
-        "http://hdl.handle.net/11356/1096"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "Erjavec, Toma\u017e",
-        "Farka\u0161, Da\u0161a",
-        "Mili\u010devi\u0107, Maja",
-        "Ljube\u0161i\u0107, Nikola",
-        "Klubi\u010dka, Filip",
-        "Vukovi\u0107, Teodora"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1120;2018-10-24T20:58:21Z;hdl_11356_1023;hdl_11356_1024;Serbian Twitter training corpus ReLDI-NormTag-sr 1.1;Ljube\u0161i\u0107, Nikola;Farka\u0161, Da\u0161a;Klubi\u010dka, Filip;Erjavec, Toma\u017e;Mili\u010devi\u0107, Maja;Vukovi\u0107, Teodora;computer-mediated communication;tokenisation;word normalisation;tagging;lemmatisation;manual annotation;TEI;ReLDI-NormTag-sr 1.1 is a manually annotated corpus of Serbian tweets. It is meant as a gold-standard training and testing dataset for tokenisation, sentence segmentation, word normalisation, morphosyntactic tagging and lemmatisation of non-standard Serbian. Each tweet is also annotated for its automatically assigned standardness levels (T = technical standardness, L = linguistic standardness). As an update to version 1.0, 1.1 corrects some minor errors. \r\n\r\nThe corpus construction is (partially) described in: \r\nMILI\u010cEVI\u0106, Maja, LJUBE\u0160I\u0106, Nikola. Tviterasi, tvitera\u0161i or twittera\u0161i? Producing and analysing a normalised dataset of Croatian and Serbian tweets. Sloven\u0161\u010dina 2.0: empirical, applied and interdisciplinary research, 4/2, 2016. ISSN 2335-2736. http://dx.doi.org/10.4312/slo2.0.2016.2.156-188;2017-05-14;corpus;http://hdl.handle.net/11356/1120;srp;http://hdl.handle.net/11356/1171;http://hdl.handle.net/11356/1096;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;https://creativecommons.org/licenses/by/4.0/;application/zip;application/zip;application/pdf;text/plain; charset=utf-8;downloadable_files_count: 3;Jo\u017eef Stefan Institute;https://reldi.spur.uzh.ch/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d96b5694-0001-5930-b1d6-b62dc791b9d5",
-    "notes": [
-        "ReLDI-NormTag-sr 1.1 is a manually annotated corpus of Serbian tweets. It is meant as a gold-standard training and testing dataset for tokenisation, sentence segmentation, word normalisation, morphosyntactic tagging and lemmatisation of non-standard Serbian. Each tweet is also annotated for its automatically assigned standardness levels (T = technical standardness, L = linguistic standardness). As an update to version 1.0, 1.1 corrects some minor errors. \r\n\r\nThe corpus construction is (partially) described in: \r\nMILI\u010cEVI\u0106, Maja, LJUBE\u0160I\u0106, Nikola. Tviterasi, tvitera\u0161i or twittera\u0161i? Producing and analysing a normalised dataset of Croatian and Serbian tweets. Sloven\u0161\u010dina 2.0: empirical, applied and interdisciplinary research, 4/2, 2016. ISSN 2335-2736. http://dx.doi.org/10.4312/slo2.0.2016.2.156-188"
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1120"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "computer-mediated communication"
-        },
-        {
-            "name": "tokenisation"
-        },
-        {
-            "name": "word normalisation"
-        },
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "lemmatisation"
-        },
-        {
-            "name": "manual annotation"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "Serbian Twitter training corpus ReLDI-NormTag-sr 1.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d9751dbf-d8d2-57cb-bd88-4e0cdf1029dc.json b/oaitestdata/clarin-oai_dc/SET_1/json/d9751dbf-d8d2-57cb-bd88-4e0cdf1029dc.json
deleted file mode 100644
index 30597882..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d9751dbf-d8d2-57cb-bd88-4e0cdf1029dc.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Akademicka"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-100676",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-100676"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CD0-F",
-    "PublicationTimestamp": "1683-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1683"
-    ],
-    "Publisher": [
-        "Drukarnia Akademicka"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/100676",
-        "oai:jbc.bj.uj.edu.pl:publication:107762"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1601/1700"
-    ],
-    "TempCoverageBegin": 50506804799,
-    "TempCoverageEnd": 50506804799,
-    "TemporalCoverage": " point in time : 1601-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1601-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1601-07-01T11:59:59Z",
-    "author": [
-        "\u017bochowski, Cyprian (1635-1693)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-100676;2019-02-28T17:47:01Z;Swi\u0119to\u0142dycz, Albo Starozytny Ia\u015bnie Wielmo\u017cnego Domu [...] Kisielow Herbowny Kleynot : Namiot Rozbity Na Gorze Witebskiey Od [...] Adama Franciszka Dorohinickiego na Brusilowie Kisiela [...] Przez Pobo\u017cn\u0105 erekcy\u0105 y Fundacy\u0105 Monastyra dla OO. Bazylianow Unitow, przy Cerkwi Kathedralney Episkopskiey;\u017bochowski, Cyprian (1635-1693);starodruki 17\u00a0w.;Kisiel, Adam Franciszek ( -1719). [Adr. ded.];Drukarnia Akademicka;1683;starodruk;application/xml;clarind-uds:poldilemma-100676;hdl:11858/00-246C-0000-0023-8CD0-F;Biblioteka Jagiello\u0144ska, BJ St. Dr. 33914;pol;http://jbc.bj.uj.edu.pl/Content/100676;oai:jbc.bj.uj.edu.pl:publication:107762;1601/1700;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d9751dbf-d8d2-57cb-bd88-4e0cdf1029dc",
-    "notes": [
-        "Kisiel, Adam Franciszek ( -1719). [Adr. ded.]"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-100676"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Swi\u0119to\u0142dycz, Albo Starozytny Ia\u015bnie Wielmo\u017cnego Domu [...] Kisielow Herbowny Kleynot : Namiot Rozbity Na Gorze Witebskiey Od [...] Adama Franciszka Dorohinickiego na Brusilowie Kisiela [...] Przez Pobo\u017cn\u0105 erekcy\u0105 y Fundacy\u0105 Monastyra dla OO. Bazylianow Unitow, przy Cerkwi Kathedralney Episkopskiey"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d982d389-6969-5ec7-9461-842338389e27.json b/oaitestdata/clarin-oai_dc/SET_1/json/d982d389-6969-5ec7-9461-842338389e27.json
deleted file mode 100644
index f2d5058f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d982d389-6969-5ec7-9461-842338389e27.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1414",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1414"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1414",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1414;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;iula_tagger;POS tagger. (The input file must be in plain text format (file.txt) and UTF-8 encoded. The disambiguation process is done by a TreeTagger instance trained by the IULA.);2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1414;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d982d389-6969-5ec7-9461-842338389e27",
-    "notes": [
-        "POS tagger. (The input file must be in plain text format (file.txt) and UTF-8 encoded. The disambiguation process is done by a TreeTagger instance trained by the IULA.)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1414"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "iula_tagger"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d99f4c4a-4e74-5d04-bb12-2c38af159c8d.json b/oaitestdata/clarin-oai_dc/SET_1/json/d99f4c4a-4e74-5d04-bb12-2c38af159c8d.json
deleted file mode 100644
index 879470f4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d99f4c4a-4e74-5d04-bb12-2c38af159c8d.json
+++ /dev/null
@@ -1,88 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-B08B-3",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-B08B-3"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-B08B-3",
-    "PublicationTimestamp": "2010-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u0160id\u00e1k, Pavel",
-        "Haji\u010d, Jan",
-        "Klyueva, Natalia",
-        "Bej\u010dek, Eduard",
-        "\u0160\u0165astn\u00e1, Eva",
-        "Vimmrov\u00e1, Pavl\u00edna",
-        "Stra\u0148\u00e1k, Pavel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-B08B-3;2018-07-02T22:05:53Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Multiword expressions in the Prague Dependency Treebank 2.0;Bej\u010dek, Eduard;Klyueva, Natalia;Stra\u0148\u00e1k, Pavel;\u0160id\u00e1k, Pavel;\u0160\u0165astn\u00e1, Eva;Vimmrov\u00e1, Pavl\u00edna;Haji\u010d, Jan;MWE;multiword expressions;idiom;phraseme;named entity;This dataset adds annotation of multiword expressions and multiword named entities to the original PDT 2.0 data. The annotation is stand-off, stored in the same PML format as the original PDT 2.0 data. It is to be used together with the PDT 2.0.;2010;corpus;http://hdl.handle.net/11858/00-097C-0000-0001-B08B-3;ces;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d99f4c4a-4e74-5d04-bb12-2c38af159c8d",
-    "notes": [
-        "This dataset adds annotation of multiword expressions and multiword named entities to the original PDT 2.0 data. The annotation is stand-off, stored in the same PML format as the original PDT 2.0 data. It is to be used together with the PDT 2.0."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-B08B-3"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "MWE"
-        },
-        {
-            "name": "multiword expressions"
-        },
-        {
-            "name": "idiom"
-        },
-        {
-            "name": "phraseme"
-        },
-        {
-            "name": "named entity"
-        }
-    ],
-    "title": [
-        "Multiword expressions in the Prague Dependency Treebank 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d9b94fa6-4cb1-552d-8500-81a6603f06fb.json b/oaitestdata/clarin-oai_dc/SET_1/json/d9b94fa6-4cb1-552d-8500-81a6603f06fb.json
deleted file mode 100644
index 44170dce..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d9b94fa6-4cb1-552d-8500-81a6603f06fb.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-957",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-957"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-957",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-957;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Laz;ca. 900 tokens;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-957;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#lazica",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d9b94fa6-4cb1-552d-8500-81a6603f06fb",
-    "notes": [
-        "ca. 900 tokens"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-957"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Laz"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d9bf2c8e-2642-5e90-b426-f873e5e66088.json b/oaitestdata/clarin-oai_dc/SET_1/json/d9bf2c8e-2642-5e90-b426-f873e5e66088.json
deleted file mode 100644
index a24a1ff7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d9bf2c8e-2642-5e90-b426-f873e5e66088.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=6a3c46dabc7a11e1a404080027e73ea23511d611524844408d271bae470b3ed5",
-    "MetadataAccess": [
-        "6a3c46dabc7a11e1a404080027e73ea23511d611524844408d271bae470b3ed5"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "6a3c46dabc7a11e1a404080027e73ea23511d611524844408d271bae470b3ed5;2018-11-15T16:39:21Z;toolService;toolService:nlpDevelopmentEnvironment;U-Compare Workbench;The U-Compare Workbench is a graphical user interface that operates on top of the U-Compare platform. The U-Compare platform allows users to build and evaluate NLP workflows. Workflows consist of one or more components, consisting of corpus readers and tools, such as tokenisers, POS taggers, named entity recognisers, etc. Workflows can be built using any components that are compliant with the UIMA framework. The Workbench provides several facilities, including rapid construction of workflows through drag and drop, graphical display of comparison of the performance of alternative workflows and evaluation against gold standard data, import of new UIMA components into the library and xport of components/workflows. \n;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d9bf2c8e-2642-5e90-b426-f873e5e66088",
-    "notes": [
-        "The U-Compare Workbench is a graphical user interface that operates on top of the U-Compare platform. The U-Compare platform allows users to build and evaluate NLP workflows. Workflows consist of one or more components, consisting of corpus readers and tools, such as tokenisers, POS taggers, named entity recognisers, etc. Workflows can be built using any components that are compliant with the UIMA framework. The Workbench provides several facilities, including rapid construction of workflows through drag and drop, graphical display of comparison of the performance of alternative workflows and evaluation against gold standard data, import of new UIMA components into the library and xport of components/workflows. \n"
-    ],
-    "oai_identifier": [
-        "6a3c46dabc7a11e1a404080027e73ea23511d611524844408d271bae470b3ed5"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:nlpDevelopmentEnvironment"
-    ],
-    "state": "active",
-    "title": [
-        "U-Compare Workbench"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d9c49d7d-5f02-5e02-853b-a8a7037ec14c.json b/oaitestdata/clarin-oai_dc/SET_1/json/d9c49d7d-5f02-5e02-853b-a8a7037ec14c.json
deleted file mode 100644
index ff0bd4ba..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d9c49d7d-5f02-5e02-853b-a8a7037ec14c.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=8537f484718f11e5a2aa782bcb074135c257a23d06734556abb980015264985d",
-    "MetadataAccess": [
-        "8537f484718f11e5a2aa782bcb074135c257a23d06734556abb980015264985d"
-    ],
-    "PublicationTimestamp": "2015-10-13T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "8537f484718f11e5a2aa782bcb074135c257a23d06734556abb980015264985d;2019-02-27T12:09:46Z;corpus;corpus:text;HIMERA Corpus;The HIMERA annotated corpus contains a set of published historical medical documents that have been manually annotated with semantic information that is relevant to the study of medical history and public health. Specifically, annotations correspond to seven different entity types and two different event types (which encode relationships amongst entities), chosen based on extensive discussions with medical historians.;2015-10-13",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d9c49d7d-5f02-5e02-853b-a8a7037ec14c",
-    "notes": [
-        "The HIMERA annotated corpus contains a set of published historical medical documents that have been manually annotated with semantic information that is relevant to the study of medical history and public health. Specifically, annotations correspond to seven different entity types and two different event types (which encode relationships amongst entities), chosen based on extensive discussions with medical historians."
-    ],
-    "oai_identifier": [
-        "8537f484718f11e5a2aa782bcb074135c257a23d06734556abb980015264985d"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "HIMERA Corpus"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d9e358fe-19c6-510d-b4c1-0fb19af8777a.json b/oaitestdata/clarin-oai_dc/SET_1/json/d9e358fe-19c6-510d-b4c1-0fb19af8777a.json
deleted file mode 100644
index 993c4589..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d9e358fe-19c6-510d-b4c1-0fb19af8777a.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5619",
-    "MetadataAccess": [
-        "oai:ota:oucs:5619"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Wintringham, Clifton, 1689-1748."
-    ],
-    "fulltext": "oai:ota:oucs:5619;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5619.xml;An enquiry into the exility of the vessels in a human body: wherein animal identity is explained, and shewn incommunicable to any individual throughout the whole species. By Clifton Wintrinham, jun.;Wintringham, Clifton, 1689-1748.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d9e358fe-19c6-510d-b4c1-0fb19af8777a",
-    "oai_identifier": [
-        "oai:ota:oucs:5619"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An enquiry into the exility of the vessels in a human body: wherein animal identity is explained, and shewn incommunicable to any individual throughout the whole species. By Clifton Wintrinham, jun."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5619.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d9f4adc9-815e-5d68-b730-e3acf2cb515c.json b/oaitestdata/clarin-oai_dc/SET_1/json/d9f4adc9-815e-5d68-b730-e3acf2cb515c.json
deleted file mode 100644
index da06e2d5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d9f4adc9-815e-5d68-b730-e3acf2cb515c.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4802",
-    "MetadataAccess": [
-        "oai:ota:oucs:4802"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Donovan, E. (Edward), 1768-1837."
-    ],
-    "fulltext": "oai:ota:oucs:4802;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4802.xml;The natural history of British insects: explaining them in their several states, with the periods of their transformations, their food, \u00c5\u0093conomy, &c. Together with the history of such minute insects as require investigation by the microscope. The whole illustrated by coloured figures, ... By E. Donovan. [pt.2];Donovan, E. (Edward), 1768-1837.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d9f4adc9-815e-5d68-b730-e3acf2cb515c",
-    "oai_identifier": [
-        "oai:ota:oucs:4802"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The natural history of British insects: explaining them in their several states, with the periods of their transformations, their food, \u00c5\u0093conomy, &c. Together with the history of such minute insects as require investigation by the microscope. The whole illustrated by coloured figures, ... By E. Donovan. [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4802.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d9f9e0b1-675c-591e-b668-fe38d9bb7a8e.json b/oaitestdata/clarin-oai_dc/SET_1/json/d9f9e0b1-675c-591e-b668-fe38d9bb7a8e.json
deleted file mode 100644
index b306d69a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d9f9e0b1-675c-591e-b668-fe38d9bb7a8e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4868",
-    "MetadataAccess": [
-        "oai:ota:oucs:4868"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Burney, Fanny, 1752-1840."
-    ],
-    "fulltext": "oai:ota:oucs:4868;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4868.xml;Cecilia: or memoirs of an heiress. By the author of Evelina. In five volumes. ... [pt.3];Burney, Fanny, 1752-1840.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d9f9e0b1-675c-591e-b668-fe38d9bb7a8e",
-    "oai_identifier": [
-        "oai:ota:oucs:4868"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Cecilia: or memoirs of an heiress. By the author of Evelina. In five volumes. ... [pt.3]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4868.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/d9fe57ed-306d-5c21-ae36-9f35c471514a.json b/oaitestdata/clarin-oai_dc/SET_1/json/d9fe57ed-306d-5c21-ae36-9f35c471514a.json
deleted file mode 100644
index 5f7838c3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/d9fe57ed-306d-5c21-ae36-9f35c471514a.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-914",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-914"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-914",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-914;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Sogdian;ca. 200.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-914;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#sogd",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d9fe57ed-306d-5c21-ae36-9f35c471514a",
-    "notes": [
-        "ca. 200.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-914"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Sogdian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/da064b0e-67d8-56ab-96da-6c3ad9ab1bea.json b/oaitestdata/clarin-oai_dc/SET_1/json/da064b0e-67d8-56ab-96da-6c3ad9ab1bea.json
deleted file mode 100644
index 806ef469..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/da064b0e-67d8-56ab-96da-6c3ad9ab1bea.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Ingham, Patricia"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 799 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0539",
-    "MetadataAccess": [
-        "oai:ota:oucs:0539"
-    ],
-    "PublicationTimestamp": "1895-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1895"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hardy, Thomas, 1840-1928"
-    ],
-    "fulltext": "oai:ota:oucs:0539;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0539.xml;Jude the obscure / Thomas Hardy;Hardy, Thomas, 1840-1928;1895;text_and_corpus_linguistics;English fiction -- 19th century;eng;Oxford Text Archive, University of Oxford;Ingham, Patricia;Ingham, Patricia;(1 file : ca. 799 KB);Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "da064b0e-67d8-56ab-96da-6c3ad9ab1bea",
-    "oai_identifier": [
-        "oai:ota:oucs:0539"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English fiction -- th century"
-        }
-    ],
-    "title": [
-        "Jude the obscure / Thomas Hardy"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0539.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/da0afd9b-baed-58f9-9d45-64e27c392be8.json b/oaitestdata/clarin-oai_dc/SET_1/json/da0afd9b-baed-58f9-9d45-64e27c392be8.json
deleted file mode 100644
index 7598db5c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/da0afd9b-baed-58f9-9d45-64e27c392be8.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5498",
-    "MetadataAccess": [
-        "oai:ota:oucs:5498"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Thomson, James, 1700-1748."
-    ],
-    "fulltext": "oai:ota:oucs:5498;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5498.xml;The tragedy of Sophonisba: Acted at the Theatre-Royal in Drury-Lane. By His Majesty's servants. By Mr. Thomson.;Thomson, James, 1700-1748.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "da0afd9b-baed-58f9-9d45-64e27c392be8",
-    "oai_identifier": [
-        "oai:ota:oucs:5498"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The tragedy of Sophonisba: Acted at the Theatre-Royal in Drury-Lane. By His Majesty's servants. By Mr. Thomson."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5498.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/da0ff9f7-1672-5164-b924-350354227fc1.json b/oaitestdata/clarin-oai_dc/SET_1/json/da0ff9f7-1672-5164-b924-350354227fc1.json
deleted file mode 100644
index 7ce814bd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/da0ff9f7-1672-5164-b924-350354227fc1.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 3",
-        "text/plain; charset=utf-8",
-        "application/gzip"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1034",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1034"
-    ],
-    "PID": "http://hdl.handle.net/11356/1034",
-    "PublicationTimestamp": "2013-09-30T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Krek, Simon",
-        "Holozan, Peter",
-        "Erjavec, Toma\u017e",
-        "Gr\u010dar, Miha",
-        "Logar, Nata\u0161a"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1034;2017-09-29T13:48:01Z;hdl_11356_1023;hdl_11356_1024;Written corpus ccKres 1.0;Logar, Nata\u0161a;Erjavec, Toma\u017e;Krek, Simon;Gr\u010dar, Miha;Holozan, Peter;TEI;Corpus ccKres consists of 9,376 documents, each containing information about the source (e.g. newspapers, magazines), year of publication, text type (fiction, newspaper), the title and author if they are known. The corpus is POS-tagged and lemmatised, and encoded in XML TEI format (Text Encoding Initiative P5). The ccKres corpus contains approximately 9% of the Kres corpus, a balanced corpus of Slovene: http://eng.slovenscina.eu/korpusi/kres.;2013-09-30;corpus;http://hdl.handle.net/11356/1034;slv;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);https://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;application/gzip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 3;Centre for Language Resources and Technologies, University of Ljubljana;http://eng.slovenscina.eu/korpusi/proste-zbirke",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "da0ff9f7-1672-5164-b924-350354227fc1",
-    "notes": [
-        "Corpus ccKres consists of 9,376 documents, each containing information about the source (e.g. newspapers, magazines), year of publication, text type (fiction, newspaper), the title and author if they are known. The corpus is POS-tagged and lemmatised, and encoded in XML TEI format (Text Encoding Initiative P5). The ccKres corpus contains approximately 9% of the Kres corpus, a balanced corpus of Slovene: http://eng.slovenscina.eu/korpusi/kres."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1034"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "Written corpus ccKres 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/da251d4d-ffe0-5974-8e3c-dbdf42121016.json b/oaitestdata/clarin-oai_dc/SET_1/json/da251d4d-ffe0-5974-8e3c-dbdf42121016.json
deleted file mode 100644
index cded2d00..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/da251d4d-ffe0-5974-8e3c-dbdf42121016.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "NLX-Natural Language and Speech Group, University of Lisbon"
-    ],
-    "Contributor": [
-        "Nunes, Filipe",
-        "Branco, Ant\u00f3nio"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Portuguese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1225",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1225"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1225",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "NLX-Natural Language and Speech Group, University of Lisbon"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Portugal"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1225;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LX-Lemmatizer;Branco, Ant\u00f3nio;Nunes, Filipe;Fully fledged automatic verbal lemmatizer for Portuguese. LX-Lemmatizer takes a Portuguese verb form and delivers all the corresponding lemmata (infinitive forms) together with the inflectional feature values. Lemmata that are less likely, but still orthographically possible, are grouped together in a last section under the header \"Other possible lemmata\". It handles: * Pronominal conjugation The Portuguese verbal inflection system is a most complex part of the Portuguese morphology, and of the Portuguese language, given the high number of conjugated forms for each verb (ca. 70 forms in non pronominal conjugation), the number of productive inflection rules involved and the number of non regular forms and exceptions to such rules. This complexity is further increased when the so-called pronominal conjugation is taken into account. The Portuguese language has verbal clitics, which according to some authors are to be analyzed as integrating the inflectional suffix system: o the forms of the clitics may depend on the Number (Singular vs. Plural), the Person (First, Second, Third or Second courtesy), the Gender (Masculine vs. Feminine), the grammatical function which they are in correspondence with (Subject, Direct object or Indirect object), and the anaphoric properties (Pronominal vs. Reflexive); o up to three clitics (e.g. deu-se-lho / gave-One-ToHim_It) may be associated with a verb form; o clitics may occur in so called enclisis, i.e. as a final part of the verb form (e.g. deu-o / gave-It), or in mesoclisis, i.e. as a medial part of the verb form (e.g. d\u00e1-lo-ia / give-it-CONDITIONAL). In some variants, when the verb form occurs in certain syntactic or semantic contexts (e.g in the scope of negation), the clitics appear in proclisis, i.e. before the verb form (ex.: n\u00e3o o deu / NOT it gave); o clitics follow specific rules for their concatenation. With LX-Lemmatizer, pronominal conjugation is exhaustively handled. Verbs can be lemmatized also in non pronominal forms. Additionally, LX-Lemmatizer exhaustively handles a set of inflection cases which tend not to be supported together in verbal lemmatizers: * Compound tenses * Double forms for past participles (regular and irregular) * Past participle forms inflected for number and gender * Negative imperative forms * Courtesy forms for second person LX-Lemmatizer handles both known verbs and unknown verbs. It thus lemmatizes: * Neologisms (with orthographic suffix) It is also worth noting the following design principles, that LX-Lemmatizer adopts with respect to the so called defective verbs: * Defectives Some unsubstantiated assumptions from traditional grammar were not followed, according to which many verb forms do not exist and/or should not be used because they sound awkward or because their use is semantically very restricted. Accordingly, to give an example, all conjugated forms of weather verbs are lemmatized, as they can be used at least non literally. To give another example, all verb forms of verbs like falir are also lemmatized. * Special cases LX-Lemmatizer does assume that some forms are impossible though (e.g. the imperative forms of verbs such as querer / to want: *quer tu) and that some clitics do not combine with certain verb forms (e.g. second person non-courtesy clitics and second person courtesy verb forms with the same number: *voc\u00ea ama-te/you_COURTESY love-yourself_NONCOURTESY). Other special cases, also not lemmatized, include impersonal se and passive se, which do not occur with first or second person verb forms. LX-Lemmatizer handles the very few cases where there may be different forms in different variants: * Orthographic and paradigmatic differences When a given verb, inflected with a given set of feature values, has different orthographic representations, all such representations can be lemmatized. To give an example, both representations for '(I) argued', argui (European) and arg\u00fci (Brazilian), are lemmatized. * Other cases Differences in irregular forms are also handled under the same approach. One such example is the past participle of 'to accept', with aceite (European) and aceito (Brazilian), which will be both lemmatized. Note that in general LX-Lemmatizer acknowledges different lemmata for different verb forms both with the same semantics and the same set of inflectional feature values when such representations can be predicted from the representation of the form (to be entered by the user). For instance, all lemmata of verb forms of 'to act' will start either with act- or with at-, depending on whether the user enters act* (European) or at* (Brazilian) as the representation of the form to be lemmatized. Aiming at optimizing usability, LX-Lemmatizer adopts the following scheme concerning the position of clitics: * Clitic placement Variants of Portuguese may differ with respect to the relative order between the clitic forms and the verb forms. In some variants, e.g. Brazilian, as a rule clitics occur invariably to the left of the verb form (in so called proclisis), while in some others, e.g. European, the clitics appear to the left, to the right (enclisis) of the verb, or still in medial position (mesoclisis), depending on the context where the verb form occurs. In order to preserve usability of the verbal lemmatizer, pronominal forms can be entered according to any variant.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1225;por;downloadable_files_count: 0;Portugal;NLX-Natural Language and Speech Group, University of Lisbon;http://lxlemmatizer.di.fc.ul.pt",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "da251d4d-ffe0-5974-8e3c-dbdf42121016",
-    "notes": [
-        "Fully fledged automatic verbal lemmatizer for Portuguese. LX-Lemmatizer takes a Portuguese verb form and delivers all the corresponding lemmata (infinitive forms) together with the inflectional feature values. Lemmata that are less likely, but still orthographically possible, are grouped together in a last section under the header \"Other possible lemmata\". It handles: * Pronominal conjugation The Portuguese verbal inflection system is a most complex part of the Portuguese morphology, and of the Portuguese language, given the high number of conjugated forms for each verb (ca. 70 forms in non pronominal conjugation), the number of productive inflection rules involved and the number of non regular forms and exceptions to such rules. This complexity is further increased when the so-called pronominal conjugation is taken into account. The Portuguese language has verbal clitics, which according to some authors are to be analyzed as integrating the inflectional suffix system: o the forms of the clitics may depend on the Number (Singular vs. Plural), the Person (First, Second, Third or Second courtesy), the Gender (Masculine vs. Feminine), the grammatical function which they are in correspondence with (Subject, Direct object or Indirect object), and the anaphoric properties (Pronominal vs. Reflexive); o up to three clitics (e.g. deu-se-lho / gave-One-ToHim_It) may be associated with a verb form; o clitics may occur in so called enclisis, i.e. as a final part of the verb form (e.g. deu-o / gave-It), or in mesoclisis, i.e. as a medial part of the verb form (e.g. d\u00e1-lo-ia / give-it-CONDITIONAL). In some variants, when the verb form occurs in certain syntactic or semantic contexts (e.g in the scope of negation), the clitics appear in proclisis, i.e. before the verb form (ex.: n\u00e3o o deu / NOT it gave); o clitics follow specific rules for their concatenation. With LX-Lemmatizer, pronominal conjugation is exhaustively handled. Verbs can be lemmatized also in non pronominal forms. Additionally, LX-Lemmatizer exhaustively handles a set of inflection cases which tend not to be supported together in verbal lemmatizers: * Compound tenses * Double forms for past participles (regular and irregular) * Past participle forms inflected for number and gender * Negative imperative forms * Courtesy forms for second person LX-Lemmatizer handles both known verbs and unknown verbs. It thus lemmatizes: * Neologisms (with orthographic suffix) It is also worth noting the following design principles, that LX-Lemmatizer adopts with respect to the so called defective verbs: * Defectives Some unsubstantiated assumptions from traditional grammar were not followed, according to which many verb forms do not exist and/or should not be used because they sound awkward or because their use is semantically very restricted. Accordingly, to give an example, all conjugated forms of weather verbs are lemmatized, as they can be used at least non literally. To give another example, all verb forms of verbs like falir are also lemmatized. * Special cases LX-Lemmatizer does assume that some forms are impossible though (e.g. the imperative forms of verbs such as querer / to want: *quer tu) and that some clitics do not combine with certain verb forms (e.g. second person non-courtesy clitics and second person courtesy verb forms with the same number: *voc\u00ea ama-te/you_COURTESY love-yourself_NONCOURTESY). Other special cases, also not lemmatized, include impersonal se and passive se, which do not occur with first or second person verb forms. LX-Lemmatizer handles the very few cases where there may be different forms in different variants: * Orthographic and paradigmatic differences When a given verb, inflected with a given set of feature values, has different orthographic representations, all such representations can be lemmatized. To give an example, both representations for '(I) argued', argui (European) and arg\u00fci (Brazilian), are lemmatized. * Other cases Differences in irregular forms are also handled under the same approach. One such example is the past participle of 'to accept', with aceite (European) and aceito (Brazilian), which will be both lemmatized. Note that in general LX-Lemmatizer acknowledges different lemmata for different verb forms both with the same semantics and the same set of inflectional feature values when such representations can be predicted from the representation of the form (to be entered by the user). For instance, all lemmata of verb forms of 'to act' will start either with act- or with at-, depending on whether the user enters act* (European) or at* (Brazilian) as the representation of the form to be lemmatized. Aiming at optimizing usability, LX-Lemmatizer adopts the following scheme concerning the position of clitics: * Clitic placement Variants of Portuguese may differ with respect to the relative order between the clitic forms and the verb forms. In some variants, e.g. Brazilian, as a rule clitics occur invariably to the left of the verb form (in so called proclisis), while in some others, e.g. European, the clitics appear to the left, to the right (enclisis) of the verb, or still in medial position (mesoclisis), depending on the context where the verb form occurs. In order to preserve usability of the verbal lemmatizer, pronominal forms can be entered according to any variant."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1225"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LX-Lemmatizer"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/da2af104-5303-5117-acef-1f2138a71d0e.json b/oaitestdata/clarin-oai_dc/SET_1/json/da2af104-5303-5117-acef-1f2138a71d0e.json
deleted file mode 100644
index 0ba98d41..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/da2af104-5303-5117-acef-1f2138a71d0e.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/104",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/104"
-    ],
-    "PID": "http://hdl.handle.net/10794/104",
-    "PublicationTimestamp": "2013-03-06T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/104;2017-10-25T11:19:03Z;hdl_10794_1;hdl_10794_2;Blog mix 2010 (2017-02-24);Bloggmix 2010 (2017-02-24);n/a, n/a;Swedish;Blog;The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.;Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat.;2013-03-06;corpus;http://hdl.handle.net/10794/104;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;http://creativecommons.org/licenses/by/4.0/;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/bloggmix2010",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "da2af104-5303-5117-acef-1f2138a71d0e",
-    "notes": [
-        "The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.",
-        "Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/104"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Blog"
-        }
-    ],
-    "title": [
-        "Blog mix 2010 (2017-02-24)",
-        "Bloggmix 2010 (2017-02-24)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/da77a356-55db-5136-8088-2559199e60ef.json b/oaitestdata/clarin-oai_dc/SET_1/json/da77a356-55db-5136-8088-2559199e60ef.json
deleted file mode 100644
index 8a6bab21..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/da77a356-55db-5136-8088-2559199e60ef.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "ZRC SAZU"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Slovenian",
-        "English",
-        "Russian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1090",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1090"
-    ],
-    "PID": "http://hdl.handle.net/11356/1090",
-    "PublicationTimestamp": "2016-10-19T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "ZRC SAZU"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU General Public Licence, version 3",
-        "PUB",
-        "http://opensource.org/licenses/GPL-3.0"
-    ],
-    "author": [
-        "Amebis, d.o.o.",
-        "Je\u017eovnik, Jano\u0161",
-        "Weiss, Peter"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1090;2018-10-16T10:38:57Z;hdl_11356_1023;hdl_11356_1024;ZRCola 2;Je\u017eovnik, Jano\u0161;Weiss, Peter;Amebis, d.o.o.;character input;Unicode;input system;ZRCola is an input system designed mainly, although not exclusively, for linguistic use. It allows the user to combine basic letters with any diacritic marks and insert the resulting complex characters into the texts with ease.\r\n\r\nThe system is comprised of an input program and a font, which can also be installed separately. The font is based on the Unicode standard and includes a vastly enlarged set of Latin, Cyrillic and other characters for Slavic writing systems in the Private Use Area.;2016-10-19;toolService;http://hdl.handle.net/11356/1090;slv;eng;rus;GNU General Public Licence, version 3;PUB;http://opensource.org/licenses/GPL-3.0;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;ZRC SAZU;http://zrcola.zrc-sazu.si/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "da77a356-55db-5136-8088-2559199e60ef",
-    "notes": [
-        "ZRCola is an input system designed mainly, although not exclusively, for linguistic use. It allows the user to combine basic letters with any diacritic marks and insert the resulting complex characters into the texts with ease.\r\n\r\nThe system is comprised of an input program and a font, which can also be installed separately. The font is based on the Unicode standard and includes a vastly enlarged set of Latin, Cyrillic and other characters for Slavic writing systems in the Private Use Area."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1090"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "character input"
-        },
-        {
-            "name": "Unicode"
-        },
-        {
-            "name": "input system"
-        }
-    ],
-    "title": [
-        "ZRCola 2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dab0fee9-0b06-5e3a-a033-140e011653ac.json b/oaitestdata/clarin-oai_dc/SET_1/json/dab0fee9-0b06-5e3a-a033-140e011653ac.json
deleted file mode 100644
index dab3db78..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dab0fee9-0b06-5e3a-a033-140e011653ac.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1000",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1000"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1000",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1000;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LAC Akuriyo Corpus;Language and Cognition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1000;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI33443%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dab0fee9-0b06-5e3a-a033-140e011653ac",
-    "notes": [
-        "Language and Cognition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1000"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LAC Akuriyo Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dab6d1f7-2461-5efd-8d79-4db02ccf7d6c.json b/oaitestdata/clarin-oai_dc/SET_1/json/dab6d1f7-2461-5efd-8d79-4db02ccf7d6c.json
deleted file mode 100644
index e3484a85..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dab6d1f7-2461-5efd-8d79-4db02ccf7d6c.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2723",
-    "MetadataAccess": [
-        "oai:ota:oucs:2723"
-    ],
-    "PublicationTimestamp": "1721-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1721"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2723;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2723.xml;A letter of advice to a young poet;Swift, Jonathan, 1667-1745;1721;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dab6d1f7-2461-5efd-8d79-4db02ccf7d6c",
-    "oai_identifier": [
-        "oai:ota:oucs:2723"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A letter of advice to a young poet"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2723.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dac2a8d1-96fa-5687-8d0c-3fd4ded0914e.json b/oaitestdata/clarin-oai_dc/SET_1/json/dac2a8d1-96fa-5687-8d0c-3fd4ded0914e.json
deleted file mode 100644
index e25e00f8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dac2a8d1-96fa-5687-8d0c-3fd4ded0914e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3381",
-    "MetadataAccess": [
-        "oai:ota:oucs:3381"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gerard, Alexander, 1728-1795."
-    ],
-    "fulltext": "oai:ota:oucs:3381;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3381.xml;The influence of the pastoral office on the character examined: with a view, especially, to Mr. Hume's representation of the spirit of that office. A sermon preached before the Synod of Aberdeen, at Aberdeen, April 8. 1760. By Alexander Gerard, ...;Gerard, Alexander, 1728-1795.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dac2a8d1-96fa-5687-8d0c-3fd4ded0914e",
-    "oai_identifier": [
-        "oai:ota:oucs:3381"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The influence of the pastoral office on the character examined: with a view, especially, to Mr. Hume's representation of the spirit of that office. A sermon preached before the Synod of Aberdeen, at Aberdeen, April 8. 1760. By Alexander Gerard, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3381.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dac7dc21-63dd-5357-8b09-1fd8d8e93cdf.json b/oaitestdata/clarin-oai_dc/SET_1/json/dac7dc21-63dd-5357-8b09-1fd8d8e93cdf.json
deleted file mode 100644
index 5d8e50dd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dac7dc21-63dd-5357-8b09-1fd8d8e93cdf.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Somali"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/118",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/118"
-    ],
-    "PID": "http://hdl.handle.net/10794/118",
-    "PublicationTimestamp": "2016-04-04T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/118;2017-12-15T10:40:53Z;hdl_10794_1;hdl_10794_2;Cilmiga bulshada 1971\u20131980 (2017-06-28);Cilmiga bulshada 1971\u20131980 (2017-06-28);n/a, n/a;Somali;Cilmiga bulshada 1971\u20131980. The material is sentence scrambled.;Cilmiga bulshada 1971\u20131980. Materialet \u00e4r meningsomkastat.;2016-04-04;corpus;http://hdl.handle.net/10794/118;som;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/eng/resource/somali-cb",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dac7dc21-63dd-5357-8b09-1fd8d8e93cdf",
-    "notes": [
-        "Cilmiga bulshada 1971\u20131980. The material is sentence scrambled.",
-        "Cilmiga bulshada 1971\u20131980. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/118"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Somali"
-        }
-    ],
-    "title": [
-        "Cilmiga bulshada 1971\u20131980 (2017-06-28)",
-        "Cilmiga bulshada 1971\u20131980 (2017-06-28)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dac9d0d4-ce31-5d1a-9978-f63563b7265c.json b/oaitestdata/clarin-oai_dc/SET_1/json/dac9d0d4-ce31-5d1a-9978-f63563b7265c.json
deleted file mode 100644
index 1ff42209..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dac9d0d4-ce31-5d1a-9978-f63563b7265c.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=8554d648190111e6a2aa782bcb074135d45d9a07bd204b76aa655a58c2b0e22e",
-    "MetadataAccess": [
-        "8554d648190111e6a2aa782bcb074135d45d9a07bd204b76aa655a58c2b0e22e"
-    ],
-    "PublicationTimestamp": "2016-05-13T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "fulltext": "8554d648190111e6a2aa782bcb074135d45d9a07bd204b76aa655a58c2b0e22e;2018-11-15T16:40:21Z;corpus;corpus:text;Radio Bulgaria WSD/NED corpus;Radio Bulgaria WSD/NED corpus is composed of texts from Bulgarian and English articles from the website of Radio Bulgaria.;2016-05-13",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dac9d0d4-ce31-5d1a-9978-f63563b7265c",
-    "notes": [
-        "Radio Bulgaria WSD/NED corpus is composed of texts from Bulgarian and English articles from the website of Radio Bulgaria."
-    ],
-    "oai_identifier": [
-        "8554d648190111e6a2aa782bcb074135d45d9a07bd204b76aa655a58c2b0e22e"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "Radio Bulgaria WSD/NED corpus"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dade43ce-ce97-5bc6-9db8-9dba6b5de1a5.json b/oaitestdata/clarin-oai_dc/SET_1/json/dade43ce-ce97-5bc6-9db8-9dba6b5de1a5.json
deleted file mode 100644
index 359a18a5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dade43ce-ce97-5bc6-9db8-9dba6b5de1a5.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "The PROIEL Treebank"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "text/xml",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Gothic",
-        "Ancient Greek (to 1453)",
-        "Church Slavic",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/114",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/114"
-    ],
-    "PID": "http://hdl.handle.net/11509/114",
-    "PublicationTimestamp": "2016-11-29T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "The PROIEL Treebank"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "CC",
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/"
-    ],
-    "author": [
-        "Haug, Dag",
-        "J\u00f8hndal, Marius L."
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/114;2016-12-05T13:37:31Z;hdl_11509_1;hdl_11509_2;PROIEL collection;Haug, Dag;J\u00f8hndal, Marius L.;Treebank;Morphosyntactic Annotation;The _PROIEL Treebank_ is a dependency treebank with morphosyntactic and information-structure annotation. It includes texts in several ancient Indo-European languages and is freely available under a Creative Commons CC BY-NC-SA 4.0 license.\r\n\r\nPlease cite as:\r\nDag T. T. Haug and Marius L. J\u00f8hndal. 2008. 'Creating a Parallel Treebank of the Old Indo-European Bible Translations'. In Caroline Sporleder and Kiril Ribarov (eds.). Proceedings of the Second Workshop on Language Technology for Cultural Heritage Data (LaTeCH 2008) (2008), pp. 27-34.\r\n\r\nReleases of the PROIEL Treebank are hosted on[Github](https://github.com/proiel/proiel-treebank).\r\n\r\nThe following texts are included in this release of the treebank:\r\n\r\nText       |         Language         |         Filename        |        Size\r\n\r\nThe Greek New Testament (ed. Tischendorf 1869) | Ancient Greek | greek-nt | 140,676 tokens\r\nThe Armenian New Testament (ed. K\u00fcnzle 1984) | Classical Armenian | armenian-nt | 23,513 tokens\r\nThe Gothic Bible (ed. Streitberg 1919) | Gothic | gothic-nt | 57,211 tokens\r\nCodex Marianus (ed. Jagi\u0107 1883) | Old Church Slavonic | marianus | 58,269 tokens\r\nJerome's Vulgate | Latin | latin-nt | 81,441 tokens\r\nCaesar, Commentarii belli Gallici (ed. Holmes 1914) | Latin | caes-gal | 28,608 tokens\r\nCicero, Epistulae ad Atticum (ed. Purser 1901) | Latin | cic-att | 41,901 tokens\r\nPeregrinatio Aetheriae (ed. Heraeus 1908) | Latin | per-aeth | 18,356 tokens\r\nHerodotus, Histories (ed. Godley 1920) | Ancient Greek | hdt | 81,495 tokens\r\nSphrantzes, Chronicles (post-1453) (ed. Grecu 1966) | Ancient Greek | chron | 24,612 tokens\r\n\r\n(The 'size' column in the table above shows the number of annotated tokens ina text. The number of tokens will be slightly larger than the number of words in the original printed edition as some words have been split into multiple tokens and some tokens have been inserted during annotation.)\r\n\r\nPlease see the XML files for detailed metadata and a full list of contributors.\r\n\r\nData formats: \r\n\r\nThe texts are available on two formats:\r\n\r\n1. PROIEL XML: These files are the authoritative source files and the only ones that contain all available annotation. They contain the complete morphological, syntactic and information-structure annotation, as well as the complete text, including punctuation, section headers etc. The schema is defined in [`proiel.xsd`](https://github.com/proiel/proiel-treebank/blob/master/proiel.xsd).\r\n\r\n2. [CoNLL-X format](http://nextens.uvt.nl/depparse-wiki/DataFormat);2016-11-29;corpus;http://hdl.handle.net/11509/114;got;grc;chu;lat;xcl;Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);CC;https://creativecommons.org/licenses/by-nc-sa/4.0/;application/gzip;text/plain; charset=utf-8;text/xml;downloadable_files_count: 1;The PROIEL Treebank;http://proiel.github.io/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dade43ce-ce97-5bc6-9db8-9dba6b5de1a5",
-    "notes": [
-        "The _PROIEL Treebank_ is a dependency treebank with morphosyntactic and information-structure annotation. It includes texts in several ancient Indo-European languages and is freely available under a Creative Commons CC BY-NC-SA 4.0 license.\r\n\r\nPlease cite as:\r\nDag T. T. Haug and Marius L. J\u00f8hndal. 2008. 'Creating a Parallel Treebank of the Old Indo-European Bible Translations'. In Caroline Sporleder and Kiril Ribarov (eds.). Proceedings of the Second Workshop on Language Technology for Cultural Heritage Data (LaTeCH 2008) (2008), pp. 27-34.\r\n\r\nReleases of the PROIEL Treebank are hosted on[Github](https://github.com/proiel/proiel-treebank).\r\n\r\nThe following texts are included in this release of the treebank:\r\n\r\nText       |         Language         |         Filename        |        Size\r\n\r\nThe Greek New Testament (ed. Tischendorf 1869) | Ancient Greek | greek-nt | 140,676 tokens\r\nThe Armenian New Testament (ed. K\u00fcnzle 1984) | Classical Armenian | armenian-nt | 23,513 tokens\r\nThe Gothic Bible (ed. Streitberg 1919) | Gothic | gothic-nt | 57,211 tokens\r\nCodex Marianus (ed. Jagi\u0107 1883) | Old Church Slavonic | marianus | 58,269 tokens\r\nJerome's Vulgate | Latin | latin-nt | 81,441 tokens\r\nCaesar, Commentarii belli Gallici (ed. Holmes 1914) | Latin | caes-gal | 28,608 tokens\r\nCicero, Epistulae ad Atticum (ed. Purser 1901) | Latin | cic-att | 41,901 tokens\r\nPeregrinatio Aetheriae (ed. Heraeus 1908) | Latin | per-aeth | 18,356 tokens\r\nHerodotus, Histories (ed. Godley 1920) | Ancient Greek | hdt | 81,495 tokens\r\nSphrantzes, Chronicles (post-1453) (ed. Grecu 1966) | Ancient Greek | chron | 24,612 tokens\r\n\r\n(The 'size' column in the table above shows the number of annotated tokens ina text. The number of tokens will be slightly larger than the number of words in the original printed edition as some words have been split into multiple tokens and some tokens have been inserted during annotation.)\r\n\r\nPlease see the XML files for detailed metadata and a full list of contributors.\r\n\r\nData formats: \r\n\r\nThe texts are available on two formats:\r\n\r\n1. PROIEL XML: These files are the authoritative source files and the only ones that contain all available annotation. They contain the complete morphological, syntactic and information-structure annotation, as well as the complete text, including punctuation, section headers etc. The schema is defined in [`proiel.xsd`](https://github.com/proiel/proiel-treebank/blob/master/proiel.xsd).\r\n\r\n2. [CoNLL-X format](http://nextens.uvt.nl/depparse-wiki/DataFormat)"
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/114"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Treebank"
-        },
-        {
-            "name": "Morphosyntactic Annotation"
-        }
-    ],
-    "title": [
-        "PROIEL collection"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dae1ab00-52c8-5418-94b2-d9a77fadff3b.json b/oaitestdata/clarin-oai_dc/SET_1/json/dae1ab00-52c8-5418-94b2-d9a77fadff3b.json
deleted file mode 100644
index f6ced14f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dae1ab00-52c8-5418-94b2-d9a77fadff3b.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=9e991cd0190211e6a2aa782bcb0741350bdadc6cae0a4c4587f0543810ec0865",
-    "MetadataAccess": [
-        "9e991cd0190211e6a2aa782bcb0741350bdadc6cae0a4c4587f0543810ec0865"
-    ],
-    "PublicationTimestamp": "2016-05-13T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "fulltext": "9e991cd0190211e6a2aa782bcb0741350bdadc6cae0a4c4587f0543810ec0865;2018-11-15T16:40:22Z;corpus;corpus:text;Bulgarian-English Wikipedia WSD/NED corpus;Bulgarian-English Wikipedia WSD/NED corpus is composed of articles from the Bulgarian version of Wikipedia and their English counterparts.;2016-05-13",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dae1ab00-52c8-5418-94b2-d9a77fadff3b",
-    "notes": [
-        "Bulgarian-English Wikipedia WSD/NED corpus is composed of articles from the Bulgarian version of Wikipedia and their English counterparts."
-    ],
-    "oai_identifier": [
-        "9e991cd0190211e6a2aa782bcb0741350bdadc6cae0a4c4587f0543810ec0865"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "Bulgarian-English Wikipedia WSD/NED corpus"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/daea8b2e-9574-5f50-ab6d-954275eb882f.json b/oaitestdata/clarin-oai_dc/SET_1/json/daea8b2e-9574-5f50-ab6d-954275eb882f.json
deleted file mode 100644
index a651358c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/daea8b2e-9574-5f50-ab6d-954275eb882f.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia J.K.M. Akadem: Soc: Jesu"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-545",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-545"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D21-2",
-    "PublicationTimestamp": "1753-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1753"
-    ],
-    "Publisher": [
-        "Drukarnia J.K.M. Akadem: Soc: Jesu"
-    ],
-    "RelatedIdentifier": [
-        "http://pbc.biaman.pl/Content/545"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "author": [
-        "Abramowicz, Adam (1710 - ?)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-545;2019-03-01T15:37:45Z;Kazania niedzielne JW. w Bogu Nayprzewielebnieyszemu JegoMo\u015bciX. Hrabi na Zas\u0142awiu, Bychowie, D\u0105brownie J\u00f3zefowi Sapie\u017ce Biskupowi Dyocezarye\u0144skiemu, Koadjutorowi Biskupstwa Wile\u0144skiego, Referendarzowi Wielkiemu W.X.L od autora ofiarowane. Cz. I.;Abramowicz, Adam (1710 - ?);Kazania polskie 18 w.;Sapieha, J\u00f3zef  Stanis\u0142aw (1708-1754);ilo\u015b\u0107 skan\u00f3w: 312 ; sygn. St-22;Drukarnia J.K.M. Akadem: Soc: Jesu;1753;starodruk;application/xml;clarind-uds:poldilemma-545;hdl:11858/00-246C-0000-0023-8D21-2;pol;lat;http://pbc.biaman.pl/Content/545;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "daea8b2e-9574-5f50-ab6d-954275eb882f",
-    "notes": [
-        "ilo\u015b\u0107 skan\u00f3w: 312 ; sygn. St-22"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-545"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Kazania polskie w."
-        },
-        {
-            "name": "Sapieha"
-        },
-        {
-            "name": "J\u00f3zef Stanis\u0142aw -"
-        }
-    ],
-    "title": [
-        "Kazania niedzielne JW. w Bogu Nayprzewielebnieyszemu JegoMo\u015bciX. Hrabi na Zas\u0142awiu, Bychowie, D\u0105brownie J\u00f3zefowi Sapie\u017ce Biskupowi Dyocezarye\u0144skiemu, Koadjutorowi Biskupstwa Wile\u0144skiego, Referendarzowi Wielkiemu W.X.L od autora ofiarowane. Cz. I."
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/db15c823-2c31-57f5-88fe-18f0a43531a8.json b/oaitestdata/clarin-oai_dc/SET_1/json/db15c823-2c31-57f5-88fe-18f0a43531a8.json
deleted file mode 100644
index 17ffa066..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/db15c823-2c31-57f5-88fe-18f0a43531a8.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=b1440fae6c0611e2a2aa782bcb0741356141ee9d41524cc990901ca440870f80",
-    "MetadataAccess": [
-        "b1440fae6c0611e2a2aa782bcb0741356141ee9d41524cc990901ca440870f80"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "b1440fae6c0611e2a2aa782bcb0741356141ee9d41524cc990901ca440870f80;2018-11-15T16:40:09Z;toolService;toolService:service;U-Compare NP Chunking Service;Web service created by exporting UIMA-based workflow from the U-Compare text mining system.\nFunctionality: Identifies NP chunks in plain text. Also carries out sentence splitting, tokenisation and POS tagging\nTools in workflow: MLRS Sentence Splitter (University of Malta), UAIC-POSTagger, UAIC-NP-Chunker (Alexandru Ioan Cuza University, Romania) \nNOTE: The licence provided covers the web service only. Tools used to create the workflow may have their own licences\n;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "db15c823-2c31-57f5-88fe-18f0a43531a8",
-    "notes": [
-        "Web service created by exporting UIMA-based workflow from the U-Compare text mining system.\nFunctionality: Identifies NP chunks in plain text. Also carries out sentence splitting, tokenisation and POS tagging\nTools in workflow: MLRS Sentence Splitter (University of Malta), UAIC-POSTagger, UAIC-NP-Chunker (Alexandru Ioan Cuza University, Romania) \nNOTE: The licence provided covers the web service only. Tools used to create the workflow may have their own licences\n"
-    ],
-    "oai_identifier": [
-        "b1440fae6c0611e2a2aa782bcb0741356141ee9d41524cc990901ca440870f80"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:service"
-    ],
-    "state": "active",
-    "title": [
-        "U-Compare NP Chunking Service"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/db1735c2-3d92-5943-b4f0-7c547cdfb74c.json b/oaitestdata/clarin-oai_dc/SET_1/json/db1735c2-3d92-5943-b4f0-7c547cdfb74c.json
deleted file mode 100644
index 245e2d86..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/db1735c2-3d92-5943-b4f0-7c547cdfb74c.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Charles University"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1367",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1367"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1367",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Czech Republic"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "\u017dabokrtsk\u00fd, Zden\u011bk"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1367;2017-11-09T14:21:28Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TectoMT;\u017dabokrtsk\u00fd, Zden\u011bk;TectoMT is a highly modular NLP (Natural Language Processing) software system implemented in Perl programming language under Linux. It is primarily aimed at Machine Translation, making use of the ideas and technology created during the Prague Dependency Treebank project. At the same time, it is also hoped to significantly facilitate and accelerate development of software solutions of many other NLP tasks, especially due to re-usability of the numerous integrated processing modules (called blocks), which are equipped with uniform object-oriented interfaces.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1367;downloadable_files_count: 0;Czech Republic;Charles University;http://ufal.mff.cuni.cz/tectomt/index.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "db1735c2-3d92-5943-b4f0-7c547cdfb74c",
-    "notes": [
-        "TectoMT is a highly modular NLP (Natural Language Processing) software system implemented in Perl programming language under Linux. It is primarily aimed at Machine Translation, making use of the ideas and technology created during the Prague Dependency Treebank project. At the same time, it is also hoped to significantly facilitate and accelerate development of software solutions of many other NLP tasks, especially due to re-usability of the numerous integrated processing modules (called blocks), which are equipped with uniform object-oriented interfaces."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1367"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TectoMT"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/db365f94-3c91-58bf-92d2-87f0a748cf10.json b/oaitestdata/clarin-oai_dc/SET_1/json/db365f94-3c91-58bf-92d2-87f0a748cf10.json
deleted file mode 100644
index d8cb1700..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/db365f94-3c91-58bf-92d2-87f0a748cf10.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 686 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2043",
-    "MetadataAccess": [
-        "oai:ota:oucs:2043"
-    ],
-    "PublicationTimestamp": "1903-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1903"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Norris, Frank, 1870-1902"
-    ],
-    "fulltext": "oai:ota:oucs:2043;2018-03-01T16:32:27Z;http://ota.ox.ac.uk/headers/2043.xml;The pit : a story of Chicago / by Frank Norris;Norris, Frank, 1870-1902;1903;text_and_corpus_linguistics;Fiction -- United States -- 20th century;Novels -- United States -- 20th century;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 686 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "db365f94-3c91-58bf-92d2-87f0a748cf10",
-    "oai_identifier": [
-        "oai:ota:oucs:2043"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- United States -- th century"
-        },
-        {
-            "name": "Novels -- United States -- th century"
-        }
-    ],
-    "title": [
-        "The pit : a story of Chicago / by Frank Norris"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2043.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/db36eefc-2f09-5fcf-94d7-67a6a9adaa4e.json b/oaitestdata/clarin-oai_dc/SET_1/json/db36eefc-2f09-5fcf-94d7-67a6a9adaa4e.json
deleted file mode 100644
index 0640b3fb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/db36eefc-2f09-5fcf-94d7-67a6a9adaa4e.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2676",
-    "MetadataAccess": [
-        "oai:ota:oucs:2676"
-    ],
-    "PublicationTimestamp": "1727-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1727"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2676;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2676.xml;A meditation upon a broomstick;Swift, Jonathan, 1667-1745;1727;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "db36eefc-2f09-5fcf-94d7-67a6a9adaa4e",
-    "oai_identifier": [
-        "oai:ota:oucs:2676"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A meditation upon a broomstick"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2676.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/db3efb53-aab2-52c0-877b-7e23aafe9e48.json b/oaitestdata/clarin-oai_dc/SET_1/json/db3efb53-aab2-52c0-877b-7e23aafe9e48.json
deleted file mode 100644
index 6f642f73..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/db3efb53-aab2-52c0-877b-7e23aafe9e48.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5315",
-    "MetadataAccess": [
-        "oai:ota:oucs:5315"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pennant, Thomas, 1726-1798."
-    ],
-    "fulltext": "oai:ota:oucs:5315;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5315.xml;The view of Hindoostan.: [pt.1];Outlines of the globe;Pennant, Thomas, 1726-1798.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "db3efb53-aab2-52c0-877b-7e23aafe9e48",
-    "oai_identifier": [
-        "oai:ota:oucs:5315"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The view of Hindoostan.: [pt.1]",
-        "Outlines of the globe"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5315.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/db49167b-8344-5815-bc0e-63166c32f0cd.json b/oaitestdata/clarin-oai_dc/SET_1/json/db49167b-8344-5815-bc0e-63166c32f0cd.json
deleted file mode 100644
index 8bb58bc2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/db49167b-8344-5815-bc0e-63166c32f0cd.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Centro de Tecnolog\u00edas y Aplicaciones del Lenguaje y del Habla (TALP)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Catalan",
-        "English",
-        "Galician",
-        "Italian",
-        "Portuguese",
-        "Welsh"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1199",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1199"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1199",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Centro de Tecnolog\u00edas y Aplicaciones del Lenguaje y del Habla (TALP)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1199;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;FreeLing;Open source language analysis tool suite: tokenizer, stemmer/lemmatizer, named entity recognizer, chunker/segmenter, morphosyntactic tagger, syntactic tagger, corpus processer, morphological tagger, semantic tagger, analyzer, Word Sense Disambiguator.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1199;cat;eng;glg;ita;por;cym;downloadable_files_count: 0;Spain;Centro de Tecnolog\u00edas y Aplicaciones del Lenguaje y del Habla (TALP);http://nlp.lsi.upc.edu/freeling/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "db49167b-8344-5815-bc0e-63166c32f0cd",
-    "notes": [
-        "Open source language analysis tool suite: tokenizer, stemmer/lemmatizer, named entity recognizer, chunker/segmenter, morphosyntactic tagger, syntactic tagger, corpus processer, morphological tagger, semantic tagger, analyzer, Word Sense Disambiguator."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1199"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "FreeLing"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/db8aee6f-f4bc-5055-a627-8d0e7f381f7e.json b/oaitestdata/clarin-oai_dc/SET_1/json/db8aee6f-f4bc-5055-a627-8d0e7f381f7e.json
deleted file mode 100644
index 5ff5bb77..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/db8aee6f-f4bc-5055-a627-8d0e7f381f7e.json
+++ /dev/null
@@ -1,98 +0,0 @@
-{
-    "Contact": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1033",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1033"
-    ],
-    "PID": "http://hdl.handle.net/11356/1033",
-    "PublicationTimestamp": "2013-09-30T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Centre for Language Resources and Technologies, University of Ljubljana"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11356/1039"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Krek, Simon",
-        "Holozan, Peter",
-        "Erjavec, Toma\u017e",
-        "Romih, Miro",
-        "Dobrovoljc, Kaja"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1033;2017-09-29T13:48:01Z;hdl_11356_1023;hdl_11356_1024;Morphological lexicon Sloleks 1.0;Dobrovoljc, Kaja;Krek, Simon;Holozan, Peter;Erjavec, Toma\u017e;Romih, Miro;morphology;lexicon;inflection;word forms;derivation;language standardization;LMF;lemmatisation;Sloleks is the reference morphological lexicon for Slovenian language, developed to be used in NLP applications and language manuals. Encoded in LMF XML, the lexicon contains approx. 100.000 most frequent Slovenian lemmas, their inflected or derivative word forms and the corresponding grammatical description. Lemmatization rules, part-of-speech categorization and the set of feature-value pairs follow the JOS morphosyntactic specifications. In addition to grammatical information, each word form is also given the information on its absolute corpus frequency and its compliance with the reference language standard.;2013-09-30;lexicalConceptualResource;http://hdl.handle.net/11356/1033;slv;http://hdl.handle.net/11356/1039;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);https://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 4;Centre for Language Resources and Technologies, University of Ljubljana;http://eng.slovenscina.eu/sloleks/opis",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "db8aee6f-f4bc-5055-a627-8d0e7f381f7e",
-    "notes": [
-        "Sloleks is the reference morphological lexicon for Slovenian language, developed to be used in NLP applications and language manuals. Encoded in LMF XML, the lexicon contains approx. 100.000 most frequent Slovenian lemmas, their inflected or derivative word forms and the corresponding grammatical description. Lemmatization rules, part-of-speech categorization and the set of feature-value pairs follow the JOS morphosyntactic specifications. In addition to grammatical information, each word form is also given the information on its absolute corpus frequency and its compliance with the reference language standard."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1033"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphology"
-        },
-        {
-            "name": "lexicon"
-        },
-        {
-            "name": "inflection"
-        },
-        {
-            "name": "word forms"
-        },
-        {
-            "name": "derivation"
-        },
-        {
-            "name": "language standardization"
-        },
-        {
-            "name": "LMF"
-        },
-        {
-            "name": "lemmatisation"
-        }
-    ],
-    "title": [
-        "Morphological lexicon Sloleks 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/db9b8441-2210-58f0-839f-82d370e14463.json b/oaitestdata/clarin-oai_dc/SET_1/json/db9b8441-2210-58f0-839f-82d370e14463.json
deleted file mode 100644
index dde51fa8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/db9b8441-2210-58f0-839f-82d370e14463.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/253",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/253"
-    ],
-    "PID": "http://hdl.handle.net/11321/253",
-    "PublicationTimestamp": "2016-04-30T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "Patejuk, Agnieszka"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/253;2016-05-05T12:20:18Z;hdl_11321_3;hdl_11321_4;POLFIE: an LFG grammar of Polish;Patejuk, Agnieszka;syntax;LFG;Polish;grammar;POLFIE is an LFG grammar of Polish implemented in the XLE system (Xerox Linguistic Environment).\r\n\r\nPOLFIE has been developed at the Institute of Computer Science, Polish Academy of Sciences (IPI PAN) within two projects: NEKST and CLARIN-PL. It provides a two-layer representation: constituent structure (c-structure, tree representation) and functional structure (f-structure, AVM representation). It is based on two previous implemented grammars of Polish: its c-structure is based on GFJP2, a DCG grammar used by the parser \u015awigra, while its f-structure is inspired by FOJP, an HPSG grammar of Polish. Lexical entries used by the grammar are created with the help of two state-of-the-art resources for Polish: Morfeusz2, a morphological analyser, and Walenty, a valence dictionary.\r\n\r\nPOLFIE is available via XLE-Web (a part of INESS; it does not require a local installation of XLE):\r\n\u2022 go to http://iness.mozart.ipipan.waw.pl/iness/xle-web or http://clarino.uib.no/iness/xle-web\r\n\u2022 choose \"POLFIE\" grammar from the \"Grammar\" menu\r\n\u2022 write a sentence in the relevant field\r\n\u2022 click the \"Parse sentence\" button;2016-04-30;languageDescription;http://hdl.handle.net/11321/253;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 1;Institute of Computer Science, Polish Academy of Sciences;http://zil.ipipan.waw.pl/LFG",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "db9b8441-2210-58f0-839f-82d370e14463",
-    "notes": [
-        "POLFIE is an LFG grammar of Polish implemented in the XLE system (Xerox Linguistic Environment).\r\n\r\nPOLFIE has been developed at the Institute of Computer Science, Polish Academy of Sciences (IPI PAN) within two projects: NEKST and CLARIN-PL. It provides a two-layer representation: constituent structure (c-structure, tree representation) and functional structure (f-structure, AVM representation). It is based on two previous implemented grammars of Polish: its c-structure is based on GFJP2, a DCG grammar used by the parser \u015awigra, while its f-structure is inspired by FOJP, an HPSG grammar of Polish. Lexical entries used by the grammar are created with the help of two state-of-the-art resources for Polish: Morfeusz2, a morphological analyser, and Walenty, a valence dictionary.\r\n\r\nPOLFIE is available via XLE-Web (a part of INESS; it does not require a local installation of XLE):\r\n\u2022 go to http://iness.mozart.ipipan.waw.pl/iness/xle-web or http://clarino.uib.no/iness/xle-web\r\n\u2022 choose \"POLFIE\" grammar from the \"Grammar\" menu\r\n\u2022 write a sentence in the relevant field\r\n\u2022 click the \"Parse sentence\" button"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/253"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "syntax"
-        },
-        {
-            "name": "LFG"
-        },
-        {
-            "name": "Polish"
-        },
-        {
-            "name": "grammar"
-        }
-    ],
-    "title": [
-        "POLFIE: an LFG grammar of Polish"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dba86af3-385f-55c9-a4e5-bf2fd8fa8bdc.json b/oaitestdata/clarin-oai_dc/SET_1/json/dba86af3-385f-55c9-a4e5-bf2fd8fa8bdc.json
deleted file mode 100644
index 39b88e41..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dba86af3-385f-55c9-a4e5-bf2fd8fa8bdc.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contributor": [
-        "Wambacq, Patrick",
-        "Roelens, Jan",
-        "Demuynck, Kris"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-306",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-306"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-306",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Belgium"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-306;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Speech Processing, Recognition and Automatic Annotation Kit (SPRAAK);Demuynck, Kris;Roelens, Jan;Wambacq, Patrick;speech recognition;SPRAAK (also Dutch for 'speech') is a speech recognition package. As such it is useful for transcription of speech, alignment of spoken and written language, annotation of corpora, etc. It is an efficient and flexible tool that combines many of the recent advancements in automatic speech recognition with a very efficient decoder in a proven HMM architecture. SPRAAK can be adapted for all languages, except tonal ones.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-306;downloadable_files_count: 0;Belgium;http://www.spraak.org",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dba86af3-385f-55c9-a4e5-bf2fd8fa8bdc",
-    "notes": [
-        "SPRAAK (also Dutch for 'speech') is a speech recognition package. As such it is useful for transcription of speech, alignment of spoken and written language, annotation of corpora, etc. It is an efficient and flexible tool that combines many of the recent advancements in automatic speech recognition with a very efficient decoder in a proven HMM architecture. SPRAAK can be adapted for all languages, except tonal ones."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-306"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech recognition"
-        }
-    ],
-    "title": [
-        "Speech Processing, Recognition and Automatic Annotation Kit (SPRAAK)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dbcae301-70f7-5b86-bbf5-1c6ca002a4a8.json b/oaitestdata/clarin-oai_dc/SET_1/json/dbcae301-70f7-5b86-bbf5-1c6ca002a4a8.json
deleted file mode 100644
index c7c035fa..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dbcae301-70f7-5b86-bbf5-1c6ca002a4a8.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "s.n."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229191",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229191"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D09-9",
-    "PublicationTimestamp": "1791-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1791"
-    ],
-    "Publisher": [
-        "s.n."
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/229191",
-        "oai:jbc.bj.uj.edu.pl:publication:240831"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1701/1800"
-    ],
-    "TempCoverageBegin": 53662478399,
-    "TempCoverageEnd": 53662478399,
-    "TemporalCoverage": " point in time : 1701-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1701-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1701-07-01T11:59:59Z",
-    "author": [
-        "Perzyna, Ludwik (1742-1800)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229191;2019-03-01T13:02:40Z;Mysli y Uwagi nad Farmazonami;Perzyna, Ludwik (1742-1800);starodruki 18\u00a0w.;s.n.;[1791];starodruk;application/xml;clarind-uds:poldilemma-229191;hdl:11858/00-246C-0000-0023-8D09-9;Biblioteka Jagiello\u0144ska, BJ St. Dr. 35833 I;pol;http://jbc.bj.uj.edu.pl/Content/229191;oai:jbc.bj.uj.edu.pl:publication:240831;1701/1800;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dbcae301-70f7-5b86-bbf5-1c6ca002a4a8",
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229191"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Mysli y Uwagi nad Farmazonami"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dbe5d377-1d3b-5edc-904d-72df3d6acad0.json b/oaitestdata/clarin-oai_dc/SET_1/json/dbe5d377-1d3b-5edc-904d-72df3d6acad0.json
deleted file mode 100644
index 3f371c07..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dbe5d377-1d3b-5edc-904d-72df3d6acad0.json
+++ /dev/null
@@ -1,49 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4862",
-    "MetadataAccess": [
-        "oai:ota:oucs:4862"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:4862;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4862.xml;Select letters between the late Duchess of Somerset, Lady Luxborough, ... and others; including a sketch of the manners, laws, &c. of the republic of Venice, ... The whole now first published from original copies, by Mr. Hull. In two volumes: [pt.1];text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dbe5d377-1d3b-5edc-904d-72df3d6acad0",
-    "oai_identifier": [
-        "oai:ota:oucs:4862"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Select letters between the late Duchess of Somerset, Lady Luxborough, ... and others; including a sketch of the manners, laws, &c. of the republic of Venice, ... The whole now first published from original copies, by Mr. Hull. In two volumes: [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4862.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dc07d2a2-b244-5216-83fd-a0d1f993c7a7.json b/oaitestdata/clarin-oai_dc/SET_1/json/dc07d2a2-b244-5216-83fd-a0d1f993c7a7.json
deleted file mode 100644
index 641865e3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dc07d2a2-b244-5216-83fd-a0d1f993c7a7.json
+++ /dev/null
@@ -1,94 +0,0 @@
-{
-    "Contact": [
-        "Universit\u00e4t des Saarlandes"
-    ],
-    "Contributor": [
-        "Andrea Wurm"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:sacoco",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:sacoco"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-001F-7C43-1",
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Universit\u00e4t des Saarlandes"
-    ],
-    "RelatedIdentifier": [
-        "Wurm, A. (2008). Translatorische Wirkung: ein Beitrag zum Verst\u00e4ndnis von \u00dcbersetzungsgeschichte als Kulturgeschichte am Beispiel deutscher \u00dcbersetzungen franz\u00f6sischer Kochb\u00fccher in der Fr\u00fchen Neuzeit. (A. Gil, J. Haller, & E. Steiner, Eds.) (p. 228). Frankfurt am Main, Berlin, Bern, Bruxelles, New York, Oxford, Wien: Peter Lang.",
-        "Amoia, M., Mart\u00ednez Mart\u00ednez, J. M., Teich, E., Kermes, H., Knappen, J. & A. Wurm (2013). A Diachronic Comparable Corpus of German Recipes. In Proceedings of the Conference on Corpora and Tools in Linguistics, Languages, and Speech, July 2013, Strasbourg, France.",
-        "Amoia, M. & Mart\u00ednez Mart\u00ednez, J. M. (2013). Using Comparable Collections of Historical Texts for Building a Diachronic Dictionary for Spelling Normalization. In Proceedings of the ACL 2013 workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities (LaTeCH 2013), August 2013, Sofia, Bulgaria.",
-        "Schmid, H. (1994). Probabilistic Part-of-Speech Tagging Using Decision Trees. Proceedings of International Conference on New Methods in Language Processing. Manchester.",
-        "STTS tagset http://www.ims.uni-stuttgart.de/forschung/ressourcen/lexika/TagSets/stts-table.html",
-        "CLARIN-D/SfS-Uni. T\u00fcbingen. 2012. WebLicht: Web-Based Linguistic Chaining Tool. Online. Date Accessed: 18 Jun 2013. URL https://weblicht.sfs.uni-tuebingen.de"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "The SaCoCo Diachronic Corpus as a whole is released under a Creative Commons Attribution - Non Commercial - Share Alike 3.0 Unported License. (CC BY NC SA 3.0) http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "The recipes belonging to Knopf 1800, Franckfurt 1789 and Gr\u00e4z 1686 contained in the SaCoCo Historical Corpus are released under a Creative Commons Attribution - Non Commercial - Share Alike 3.0 Unported License. (CC BY NC SA 3.0) http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "The SaCoCo Contemporary Corpus is released under a Creative Commons Attribution - Share Alike 3.0 Unported License. (CC BY SA 3.0) http://creativecommons.org/licenses/by-sa/3.0/",
-        "All the recipes of the SaCoCo Historical Corpus (but Knopf 1800, Franckfurt 1789 and Gr\u00e4z 1686) are released under a Creative Commons Attribution 3.0 Unported License. (CC BY 3.0) http://creativecommons.org/licenses/by/3.0/"
-    ],
-    "SpatialCoverage": [
-        "Germany, Austria and Switzerland."
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Jos\u00e9 Manuel Mart\u00ednez Mart\u00ednez",
-        "Marilisa Amoia"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:sacoco;2014-06-03T13:01:09Z;SaCoCo Saarbr\u00fccken Cookbook Corpora;Marilisa Amoia;Jos\u00e9 Manuel Mart\u00ednez Mart\u00ednez;corpus linguistics;historical linguistics;early modern age;cooking recipe;cookbook;The Saarbr\u00fccken Cookbook Corpus is a diachronic corpus made up of cooking recipes organized into two different collections: historical and contemporary.\nThe historical component contains a selection of recipes from different works. The full nomina of sources can be found listed as sources in the metadata. These recipes were collected and transcribed by Andrea Wurm as part of her PhD. For more information see Wurm 2007.\nThe contemporary component contains cooking recipes from rezeptewiki.org. The selection criteria were temporal (only the last version of the recipe) and geographical (only recipes belonging to German speaking regions). The address of the wiki dump is provided in sources.\n\nANNOTATION:\nThe corpus contains two types of annotation: structural and positional.\n\nStructural annotation is written in XML and provides a description of the textual structure, on the one hand, and metatextual information and shallow semantics, on the other hand.\n\nSTRUCTURAL ATTRIBUTES:\nmetadata: id, collection, source, url, year, decade, period, language, ref;\nshallow semantics: type, course, cuisine, ingredient, method;\nstructure: title, body, segment, paragraph, sentence.\n\nPositional annotation is provided at token level containing linguistic information.\n\nPOSITIONAL ATTRIBUTES:\nword form;\nPOS (TreeTagger, STTS tagset);\nlemma (TreeTagger);\nnormalized form (automatic normalization using the algorithm described in Amoia and Mart\u00ednez Mart\u00ednez 2013).;Universit\u00e4t des Saarlandes;Andrea Wurm;2013;Dataset;text/xml;clarind-uds:sacoco;hdl:11858/00-246C-0000-001F-7C43-1;Staindl 1569.\n    Author: Staindl, Balthasar.\n    Title: Ein sehr K\u00fcnstlichs vnd nutzlichs Kochbuoch / vormals nye in so leicht / Mannen vnnd Frawen personen / von jnen selbst zu lernen / in Truck verfast vnd au\u00dfgangen ist / Artlich in acht B\u00fccher getheilt / sampt etlichen fast nutzen bewehrten Hau\u00dfnotturfften oder k\u00fcnsten. Auch wie man Essig macht / vnd Wein guot behelt. Balthasar Staindl von Dillingen. M.D.LXVIIII. [1569 Augsburg: Matth\u00e4us Franck].\nFirst edition: 1544 Augsburg: H. Steiner (Weiss 1996:511, Nr. 3683).\nFurther editions: 1547 Augsburg: Valentin Ottmar, 1549 Frankfurt: Herman G\u00fclfferich; 1552 Augsburg: Valentin Ottmar; 1575 Augsburg: M. Manger; 1575 Augsburg: Francke; 1582 Augsburg; 1586 Augsburg: Manger; 1596 Augsburg: Manger; 1608 Francke (Weiss 1996:511f., Nr. 3684f.); Ruf (1993:69) refers two editions in 1548 and 1589, probably Kudriaffsky.\nComments: the edition used for this corpus is a reprint of the 1569 edition 1569 published in 1979 by Josef Stocker in Dietikon-Z\u00fcrich.;Koch vnd Kellermeisterey 1574.\nAuthor: anon.\nTitle: Koch vnd Kellermeisterey. Von allen Speisen vnd Getr\u00e4ncken / viel guter heimlicher k\u00fcnst / Auch wie man Latwergen / Salsen / Confect / Conseruen / vnnd Einbeytzung machen sol / Von mancherley Fr\u00fcchten / Bl\u00fcmen / Kr\u00e4utern / vnd Wurtzelen / Einem jeden im Hau\u00df sehr notwendig vn[-] n\u00fctzlich zugebrauchen. Jetzund von neuwem wider ersehen / vnd mit lustigen Figuren durchau\u00df geziret. Getruckt zu Franckfort am Mayn / M. D. LXXIIII.\nFirst edition: ca. 1485.\nFurther editions: 1547 Frankfurt a. M.: Hermann G\u00fclfferich, 1551 ibid., 1554 ibid., ca. 1556 Frankfurt a. M.: Han Weygand, 1557 ibid., 1559 Stra\u00dfburg: Christian M\u00fcller, ca. 1562 Frankfurt a. M.: Han Weygand und Georg Raben, 1564 Frankfurt a. M.: Egenolffs Erben, 1566 Frankfurt a. M.: Thomas Rebart, 1566 [Frankfurt a. M.: Egenolffs Erben], 1570 [Frankfurt a. M.: Thomas Rebart?], 1571 Frankfurt a. M.: Catherine Rebart f\u00fcr Kil. Han, 1574 Frankfurt a. M.: Egenolffs Erben, 1576 Frankfurt a. M.: Nicholas Basse, 1581 Frankfurt a. M.: Egenolffs Erben, 1581 Stra\u00dfburg: Christian M\u00fcllers Erben, 1587 Frankfurt a. M.: Nicholas Basse, 1660 Erfurt, 1581 Frankfurt a. M.: Feyerabend (= Meister Sebastian, s. dort), 1674 Basel: E. K\u00f6nig und Sohn (= Neu wolzugerichtetes Kochb\u00fcchlein...), 1684 Magdeburg.\nComments: the edition used for this corpus is the copy at Herzog August Bibliothek of 1574.;Colerus 1602.\nAuthor: Coler(us), Johannes.\nTitle: OECONOMIA. Oder Hauszbuch. M: IOHANNIS COLERI. Erste Theil. Zum Calendario Oeconomico & perpetuo geh\u00f6rig. Darinnen begriffen vnnd au\u00dff\u00fchrlichen erkleret ist / Wie ein Hauswirth nach dem jhn Gott der Allmechtige gesegnet / ferner seine Nahrung nechst Gott anstellen sol / auch fruchtbarlichen geniessen vnd gebrauchen: Aldieweil in solchem angezeigt wird / wie ein Hauswirth erstlich sein Gesinde wol regieren sol / hernach / von allerley sachen zur Hau\u00dfhaltung geh\u00f6rig / Als von Brawen / Backen / Bleichen / Wein-bergen / G\u00e4rten / H\u00f6ltzung / Ackerbaw / Viehzucht / Jagten / Fisch vnd Vogelfang / Endlich von einer Hau\u00dfartzney oder Hau\u00dfapotecken vor den gemeinen Man. Jetzd auffs New vbersehen / corrigirt vnd verbessert in Druck gegeben. Mit R\u00f6m. Key. May. Freyheit nicht nachzudrucken. Wittemberg / In vorlegung Paul Helwigs Buchf\u00fchrers daselbst. Anno 1602.\nFirst edition: Kalender 1593, the three parts of the Oeconomia 1596, 1598 und 1600.\nFurther editions: it is difficult to keep track of them. Numerous editions during S. XVI and XVII with variations regarding to title, place and editor: 1602, 1604\u201307, 1620, 1645\u201356, 1665, 1672, 1680, 1692, 1711.\nComments: the edition for this corpus is the 1602 one, which contains a cookbook with 200 recipes.;Deckhardt 1611.\nAuthor: Deckhardt, Johann.\nTitle: New / Kunstreich vnd N\u00fctzliches Kochbuch Darinn allerley n\u00fctzliche vnd seltzame Speisen vnd Trachten / nicht allein von Wildpret / Vogeln / Fischen vnd Fleisch / sondern auch gebackener / al\u00df M\u00fcrtzepanen / Dortten / Pastetten / Kuchen vnd dergleichen / f\u00fcr allerley Stands personen / Auch in allerley Hau\u00dfhaltungen / vnd nach gelegenheit der zeit / Gasterey vnd Pancketen / oder sonsten / wie dergleichen vffn nohtfall f\u00fcr krancke Leute schnell vnd balde / mit geringen vnd leichten Vnkosten zuvorfertigen / Beschrieben durch Johan[-] Deckhardt / weiland Churf: S\u00e4ch\u00df: K\u00fcchenschreiben zu Dre\u00dfden. Gedruckt / in verlegung Henning Gro\u00dfen des \u00e4ltern / Buchh\u00e4ndlers zu Leipzig. Anno M. DC. XI.\nFirst edition: unknown.\nFurther editions: unknown.\nComments: the edition for this corpus is the copy at NLB Hannover.;Stockholm 1647.\nAuthor: D[ietlev] M[ajus].\nTitle: D. M. Stockholmisch Koch Gespreches Vortrab / zwischen zweyen K\u00fcchinnen / von vnterscheidt / Ahrt / Natur vnd eigenschaft / zu auffenthalt Leibes vnd Lebendes / der Victualien, Vegetabilien Gew\u00fcrtzen / Perselen vnd Accidentalien, hiesiger vnd Au\u00dfl\u00e4ndischer / wie dieselbige recht Ihrer Natur nach / zubereite[-] / Das geringe f\u00fcr dem guten zuerkennen vnd zuvnterzuscheiden. Auff guthertziger Leute Begeren zum andern mahl Gedruckt / vnd verleget Durch Peter Van Selow Stockholm Anno 1647.\n[auf der R\u00fcckseite des Titelblattes handschriftlich erg\u00e4nzt (modern, Bleistift): \u201eD[ietlev] M[ajus]\u201c].\nFirst edition: unknown.\nFurther editions: unknown.\nComments: the edition for this corpus is the copy at Herzog August Bibliothek.;Prasmofsky 1671.\nAuthor: Prasmofsky, Stanislaus.\nTitle: Neu=verfertigtes vollst\u00e4ndiges Koch=Buch / Das ist : Gr\u00fcndliche Beschreibung / oder deutliche Anweisung / wie man allerley herrlich= und geringe Fleisch= Fisch= Gefl\u00fcgel= Wildbrett= gesottene= gebratene= gebachene= auch Pasteten=Speisen / sambt mancherley Zugem\u00fcsen oder Zwischen=Gerichten / k\u00f6stlich / delicat, und k\u00fcnstlich bey Hochzeiten / Kind=Tauffen / Gastereyen / auch sonsten ins gemein f\u00fcr Gesunde und Krancke / auf ein-heimische und frembde Manier kochen und zubereiten kan. Mit beygef\u00fcgtem Unterricht / Allerhand Confect / Latwergen / S\u00e4fft und andere eingemachte Sachen zuzurichten. Darbey auch ein vollst\u00e4ndiges und n\u00fctzliches Register zu finden / Durch Stanislaum Prasmofsky, E. H. J. gewesnen Mund=Koch. N\u00fcrnberg / Gedruckt und verlegt bey Johan[-] Philip Milten-berger / 1671.\nFirst edition: 1671.\nFurther editions: 1685 N\u00fcrnberg: Joh. Hofmann.\nComments: the edition for this corpus is the copy at Herzog August Bibliothek of the 1671.;Wecker 1679.\nAuthor: Wecker, Anna.\nTitle: Neu / k\u00f6stlich vnd nutzliches Koch=Buch / Jn welchem kurtzlich begriffen / Wie aller-hand k\u00fcnstliche Speisen / so wol von zahmen als wilden Thieren: V\u00f6gel vnd Federwildbr\u00e4t ... [2. Teil mit neuem Titelblatt]: Parisische K\u00fcchenmeister / Das ist: Jetziger Zeit verleckerte Franz\u00f6sische Art un[-] Manier / Allerhand Speisen bey k\u00f6stlichen Pancketen und Haus-haltungen zu kochen und zuzurichten. [1679 Basel: Emanuel K\u00f6nig und S\u00f6hne].\nFirst edition: in this form 1667 ibid., originally 1597 Amberg: Forster.\nFurther editions: in this form 1697 Hamburg, originally see Wecker 1598.\nComments: the edition for this corpus is the copy at Herzog August Bibliothek of the 1679. Moreover, was analyzed Wecker 1598.;Thieme 1682.\nAuthor: Thieme, Johann Christoph.\nTitle: Haus= Feld= Arzney= Koch= Kunst= und Wunder=Buch. Das ist: Ausf\u00fchrliche Beschreib= und Vorstellung / Wie ein kluger Hausvatter und sorgf\u00e4ltige Hausmutter / wes Standes und W\u00fcrden sie auch immermehr seyn m\u00f6gen / mit vortrefflichem Nutzen und er-sprie\u00dflichem Nahrungs=Aufnehmen / ihr Haus=Wesen f\u00fchren / und / durch Gottes reichen Segen / auf ihre Nachkommen h\u00f6chst=gl\u00fccklich fortpflanzen m\u00f6gen. Alles / um richtiger Ordnung willen / in zwanzig Abtheilungen enthalten / Darinn folgende Sachen abgehandelt werden: I. Von der Haushaltung insgemein. II. Vom Feld= und Ackerbau. III. Vom Gartenbau. IV. Vom Weinbau. V. Vom Haus= Feld= und Garten=Kalender. VI. Vom Bierbrauen. VII. Vom Kochen. IIX. Vom Trinchiren. IX. Vom Confitiren / Candiren und Zuckerbachen. X. Von den Bienen. XI. Vom Wild= und Waidwerk. XII. Von Pfleg= und Wartung der Pferde. XIII. Von der Viehzucht. XIV. Vom Vogelfang. XV. Von der Fischerey. XVI. Von be-w\u00e4hrten Arzneyen / sowol f\u00fcr Manns= als Weibspersonen. XVII. Vom Distilliren. XIIX. Von heilsamen Kr\u00e4utern. XIX. Von Rarit\u00e4ten und Wunder=K\u00fcnsten. XX. Von zierlicher Brief-stellung. Wo [ein Wort unleserlich] zusamm getragen / und mit sch\u00f6nen hierzu dienlichen Kupfern gezieret / von Johann Christoph Thiemen. Mit R\u00f6m. K\u00e4iserl. Majest\u00e4t Gn\u00e4digstem Privilegio. N\u00fcrnberg / In Verlegung Johann Hofmanns / Buch= und Kunsth\u00e4ndlers. Daselbst gedruckt bey Andreas Knorzen. Im Jahr Christi 1682.\n[Title of the cookbook:] De\u00df Haus= Feld= Arzney= Koch= Kunst= und Wunder= Buchs Siebender Theil / Vom Kochen. Wie man nemlich auf unterschiedliche Art und Weise allerhand Fleisch / Wildpret / Gefl\u00fcgel / Fisch / Eyer / und Garten=Speisen wolgeschmacklich zubereiten solle.\nFirst edition: 1682.\nFurther editions: 1687, 1690, 1694, 1700.\nComments: the edition for this corpus is the copy at the Herzog August Bibliothek of 1682.;Gr\u00e4tz 1686.\nAuthor: anon.\nTitle: Ein Koch= Und Artzney=Buch. Gedruckt zu Gr\u00e4tz / Bey denen Widmanstetterischen Erben. 1686.\nFirst edition: 1686 (Weiss 1996:271, Nr. 1982).\nFurther editions: 1688, 1696 (gleicher Verlag); die 3. Aufl. 1696 unter dem Titel \u201aEin sehr nutzbares Koch- und Arzneybuch\u2018 (Weiss 1996:271, Nr. 1982).\nComments: the edition for this corpus is the version of 1789 as transcribed and published by Thomas Gloning. http://www.uni-giessen.de/gloning/tx/graz2.htm;Osnabr\u00fcck 1687.\nAuthor: anon.\nTitle: Gantz neu=vermehrter Sorgf\u00e4ltiger Hau\u00df=Halter/ Begreiffend einen Nutz= und Lust= bringenden Baum= K\u00fcchen= und Blumen=Garten Welcher gestalt solcher nach bester Form gegr\u00fcndet / getheilet / ged\u00fcnget / bes\u00e4et / bepflantzet / rc. mit sch\u00f6nem Teutsch= und Frantz\u00f6sischen Laubwerck / Blumen=Feldern / Lust=G\u00e4ngen und H\u00fctten / Pyramiden und Sonnen Uhren gezieret / auch was sonsten im Hau\u00dfwesen durchs gantze Jahr Monatlich be-obachtet und n\u00fctzlichst gebraucht werden k\u00f6nne; Sambt einem Dreyfachen (1) Dessen Abtheilung= (2) Benahmung= und (3) Medicinischen Gebrauch in sich enthaltendem Register; Deme beygef\u00fcgt ein sch\u00f6nes nach Teutsch= und Frantz\u00f6sischer Manier eingerichttes Koch= Condir- und Distillir-Buch / Nebst Noch einem zwar kleinen doch auserlesnen Artzney= B\u00fcch-lein Dessen man / sonderlich auff dem Lande / in Ermanglung eines Medici, oder anderer grosser Kosten / f\u00fcr sich und sein unterhabendes Vieh / als Pferde / K\u00fche / Schaf und Schwein / rc. allen falls heilsamlich zu bedienen; Allen vielf\u00e4ltig=hiernach verlangten Lieb-habern Zu sonderbarem n\u00fctzlichen Vergn\u00fcgen mit grossem Flei\u00df durch und durch verbessert / und mit vielen neuen deutlichern Figuren vermehrt herau\u00df gegeben. Osnabr\u00fcck / Druckt und verlegt von J. Wolffg. Distner / 16[?]7. \nFirst edition: unknown, but probably 1674 Osnabr\u00fcck: Schw\u00e4nder.\nFurther editions: 1677, 1678 (Osnabr\u00fcck: Schw\u00e4nder), 1696 (Osnabr\u00fcck: Krum-bein/Schorlemer).\nComments: the edition for this corpus is the copy at the Herzog August Bibliothek of 1687.;Schuppe 1698.\nAuthor: Schuppe, Hans.\nTitle: Traiteur \u00e0 la mode, Welcher der delicaten und neu begierigen Welt zu sonderbaren Nutzen darleget. Ein neu woleingerichtetes oder zusammen=getragenes Koch=Buch / Worinn mit h\u00f6chster Lust zu finden / Wie man / so wol Hoch=F\u00fcrstlich= als anderer vornehmer H\u00f6fe Taffeln / nach bester Manier des heutigen Etats / mit wolschmeckenden Speisen galant be-stellen und versehen k\u00f6nne / Als: Mit Potagen von allerhand Wildpret und zahmen Fleisch / Wild und zahmen Gefl\u00fcgel=Werck / Fisch und Garten=Gew\u00e4chsen / wie auch Tarten / Past\u00e4ten / und ander Gebackens; imgleichen Milch=Speisen / Gallerten / Fricass\u00e9en, Ragoun, Mandeln / Eyer / Morcheln und Champignons und also bi\u00df 374 Species, welche im Register aufzuschlagen sind; Item: Von allerhand Braten / Wie dieselben ordinirt und angerichtet werden sollen / Worbey ein und zwantzig curieuse Taffeln / in guten Form= und Ordnungen / darauff die angerichtete Speisen schicklich in ein=ander zu setzen / zu finden / Auf viel-f\u00e4ltiges Ansuchen / jederm\u00e4nniglich / absonderlich der Koch=Kunst Liebhabern / mitgetheilet von Hans Schuppen [/ der Hochf\u00fcrstl [sic, ohne Punkt] Durch. zu Holstein Pl\u00f6en / itziger Zeit bestalten Mund=Koch. L\u00fcbeck und Leiptzig / bey Peter B\u00f6ckmann. PLOEN / Gedruckt durch Tobias Schmidt / F\u00fcrstl. Buchdr. 1698.].\nFirst edition: 1698.\nFurther editions: 1702 L\u00fcbeck und Leipzig: Peter B\u00f6ckmann, 1709 ibid., 1729 ibid.\nComments: the edition for this corpus is the copy at the Herzog August Bibliothek of 1698.;Buchinger 1700.\nAuthor: [Buchinger, Bernardin (Bernhard)].\nTitle: Koch=buch So wol F\u00fcr Geistliche als auch Weltliche grosse und geringe Hau\u00dfhaltungen / wie bey denen t\u00e4glich vil Leut am f\u00fcglichsten abgespeiset werden. Darinn \u00dcber die achthunderterley Fleisch / Wildprett / Gefl\u00fcgel / Fisch // Eyer / und Garten=Speisen / auch die Manier und Wei\u00df selbige zubereiten / Neben anderen nutzlichen Hau\u00dfhaltung= St\u00fccklein / zu finden und begriffen sind. Durch Einen geistlichen Kuchen=Meister de\u00df Gottshauses L\u00fctzel beschriben und practicirt. Zum dritten mal auffgelegt und vermehrt. Lautterbach. Basel / bey Johann Conrad von Mechel / Im Jahr 1700.\nFirst edition: 1671, Molsheim: Straubhaar.\nFurther editions: 1672 M\u00fchlhausen: Meyer; 1700 Lautterbach; 1706 Basel.\nComments: the edition for this corpus is the copy at the Herzog August Bibliothek of 1700.;Keyl 1705.\nAuthor: Blancard, Stephan; translated by Georg von Keyl, called Cunaeus.\nTitle: STEPH. BLANCARDI, Med. Doct. H\u00f6chst=n\u00fctzliches und zu einem langwierigen Leben anleitendes Speise= und Tisch=B\u00fcchlein / Wie man ohne Kranckheit leben k\u00f6nne / Darinnen von jeder Speise und Tranck insonderheit gehandelt wird / und nach Teutschlandes Gelegen-heit mit Flei\u00df eingerichtet / und aus der Niederl\u00e4ndischen in die Hochteutsche Sprache \u00fcber-setzet von Georg von Keyl / genandt CUN\u00c6US, Med. Doct. deme noch beygef\u00fcget / Der allzeitfertige Koch / und perfecte Speisemeister / Handelt / wie und auf was Art und Weise so wohl Teutsch= Englisch= Polnisch= als Frantz\u00f6sische Spei[mit Signatur \u00fcberklebt] niedlich und wohl zuzurichten / [..., siehe Titelblatt Koch und Speisemeister] Franckfurth und Leipzig / [???] Gottfried Freytag / Buchh\u00e4ndler Hannover und Wolffenb\u00fcttel / 1705.\n[Mit eigenem Titelblatt nach S. 80 des Werkes von Blancard:] Der allzeit fertige Koch / und Perfecte Speise= Meister / Auf was Art und Weise / so wohl Teutsche / Englische / Polen /als Frantzosen ihre Speisen niedlich und wohl zurichten. Allen Hau\u00df=V\u00e4tern und M\u00fcttern h\u00f6chst=n\u00f6thig und diensam.\nFirst edition: 1659, 1689.\nFurther editions: 1695 in Frankfurt and Leipzig.\nComments: the edition for this corpus is the copy at the Herzog August Bibliothek of 1705.;Hohberg 1715.\nAuthor: Hohberg, Wolf Helmhard von.\nTitle: Herrn von Hohbergs GEORGICA CURIOSA AUCTA. Oder: Adelichen Land= und Feld=Lebens Auf alle in Teutschland \u00fcbliche Land= und Haus=Wirthschafften / in Zw\u00f6lff B\u00fcchern wohleingericht=Neuerfundener Dritter Theil / In welchem / gantz besondere zu diesem Zweck / sehr curiose Materien / deren man sich / mit grossem Nutzen / und seiner Vergn\u00fcgung bedienen kan / enthalten; auch was / bevorab in den beeden Theilen / kurtz oder gar nicht ber\u00fchrt / nunmehro vollst\u00e4ndig / deutlich / und aufs accurateste elaborirt; Nebenst allerhand raren Erfindungen und Experimentis, auch mit m\u00f6glichstem Flei\u00df ausgef\u00fchret worden. Deme zum Beschlu\u00df / Ein bew\u00e4hrtes / meistens aus eigener Erfahrenheit / und unter-schiedlich=practicirten Manuscriptis, wohleingericht=sehr nutzliches Koch=Buch beygef\u00fcget ist. Alles / mit hierzu beh\u00f6rigen vollkommenen Registern / auch dienlichen Kupffern bestens versehen. Cum Gratia & Privilegio Sacr\u00e6 C\u00e6sare\u00e6 & Catholic\u00e6 Majestatis. N\u00fcrnberg / Jn Verlegung Martin Endters. Jm Jahr Christi 1715.\n[Das Kochbuch hat ein eigenes Titelblatt:] Bew\u00e4hrtes wohleingerichtetes Koch=Buch / Welches Von einer sorgf\u00e4ltigen Liebhaberin dieser sch\u00f6nen Wissenschaft / meistens selbst practicirt / mit ohnerm\u00fcdetem Flei\u00df zusammen getragen / und in 16. Capiteln eingetheilet worden. Ingleichen ist aus denen Kupffern / wie eine Tafel / auf unterschiedliche Arten / mit Speissen / Pyramiden / rc. zierlich und ordentlich zu rangiren / aufzutragen / auch zu changiren / klar und deutlich zu ersehen: Nicht weniger befindet sich am Ende ein voll-kommenes Register / alles Innhalts beygef\u00fcgt.\nFirst edition: 1682.\nFurther editions: 1687, 1695, 1701\u201305; 1749, N\u00fcrnberg.\nComments: the edition for this corpus is the copy at the Herzog August Bibliothek of 1715.;Danckwerth 1729.\nAuthor: Danckwerth, Christian Heinrich.\nTitle: Wohleingerichtetes Koch=Buch, Oder: Gr\u00fcndliche Anweisung.\nI. Die Speisen auf mancherley Art und Weise angenehm und wohlschmeckend, nicht weniger zur Gesundheit dienlich zuzurichten.\nII. Ferner von Conservation der in der Hau\u00df=//haltung und K\u00fcchen v\u00f6thigen Speisen und Victualien.\nIII. Zur Wissenschaft der Candier- und Confitier-Kunst.\nIV. Unterricht, Wolle und leinen Garn, Tuch und Zeuge nach allerhand Couleuren zu f\u00e4rben, zum Druck bef\u00f6rdert durch Christian Heinrich Danckwerth.\nHANOVER Verlegts Nicolaus F\u00f6rster und Sohn, 1729.\nFirst edition: probably 1729.\nFurther editions: 1769.\nComments: the edition for this corpus is the copy at the Herzog August Bibliothek of 1729.;Franckfurt 1789.\nAuthor: anon.\nTitle: Das kleine jedermann n\u00fctzliche und wohleingerichtete Franckfurter Koch=Buch, worinnen ganz leicht zu erlernen, wie allerley Speisen gut und schmackhaft zuzubereiten sind, Ehedem von einer in der Koch=Kunst erfahrnen angesehenen hiesigen Haus=Frau zum eigenen Gebrauch in Druck gegeben, Nunmehro aber wegen dessen allgemeinen Nutzen \u00f6ffentlich und in etwas vermehrt auch von Fehlern gereinigt herausgegeben. Vierte Auflage. Franckfurt am Mayn, in der J\u00e4gernschen Buchhandlung, 1789.\nFirst edition: unknown.\nFurther editions: 1804 Frankfurt.\nComments: the edition for this corpus is the version of 1789 as transcribed and published by Silvia Micha, Christina Muth, Mascha Schacht and Thomas Gloning. http://www.uni-giessen.de/gloning/tx/1789ffkb.htm;Knopf 1800.\nAuthor: J.D. Knopf\nTitle: Neues / Hann\u00f6verisches / Kochbuch. / Jn zwey Theilen. / Verbessert und vermehret / von / einem praktischen Koche. / Neueste Ausgabe. / Hannover, / bey den Gebr\u00fcdern Hahn. / 1800. \nFirst edition: unknown.\nFurther editions: unknown.\nComments: the edition for this corpus is the version of 1800 as transcribed and published by Katrin Leppert, Kristin L\u00fcckel and Thomas Gloning. http://www.uni-giessen.de/gloning/tx/1800hakb.htm;rezeptewiki\nTitle: Rezepte-Wiki\nComments: the edition for this corpus is the XML dump (06/11/2012) provided at http://www.rezeptewiki.org/wiki/Rezepte-Wiki:Offline#XML-Dump;deu;Wurm, A. (2008). Translatorische Wirkung: ein Beitrag zum Verst\u00e4ndnis von \u00dcbersetzungsgeschichte als Kulturgeschichte am Beispiel deutscher \u00dcbersetzungen franz\u00f6sischer Kochb\u00fccher in der Fr\u00fchen Neuzeit. (A. Gil, J. Haller, & E. Steiner, Eds.) (p. 228). Frankfurt am Main, Berlin, Bern, Bruxelles, New York, Oxford, Wien: Peter Lang.;Amoia, M., Mart\u00ednez Mart\u00ednez, J. M., Teich, E., Kermes, H., Knappen, J. & A. Wurm (2013). A Diachronic Comparable Corpus of German Recipes. In Proceedings of the Conference on Corpora and Tools in Linguistics, Languages, and Speech, July 2013, Strasbourg, France.;Amoia, M. & Mart\u00ednez Mart\u00ednez, J. M. (2013). Using Comparable Collections of Historical Texts for Building a Diachronic Dictionary for Spelling Normalization. In Proceedings of the ACL 2013 workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities (LaTeCH 2013), August 2013, Sofia, Bulgaria.;Schmid, H. (1994). Probabilistic Part-of-Speech Tagging Using Decision Trees. Proceedings of International Conference on New Methods in Language Processing. Manchester.;STTS tagset http://www.ims.uni-stuttgart.de/forschung/ressourcen/lexika/TagSets/stts-table.html;CLARIN-D/SfS-Uni. T\u00fcbingen. 2012. WebLicht: Web-Based Linguistic Chaining Tool. Online. Date Accessed: 18 Jun 2013. URL https://weblicht.sfs.uni-tuebingen.de;Germany, Austria and Switzerland.;The SaCoCo Diachronic Corpus as a whole is released under a Creative Commons Attribution - Non Commercial - Share Alike 3.0 Unported License. (CC BY NC SA 3.0) http://creativecommons.org/licenses/by-nc-sa/3.0/;The recipes belonging to Knopf 1800, Franckfurt 1789 and Gr\u00e4z 1686 contained in the SaCoCo Historical Corpus are released under a Creative Commons Attribution - Non Commercial - Share Alike 3.0 Unported License. (CC BY NC SA 3.0) http://creativecommons.org/licenses/by-nc-sa/3.0/;The SaCoCo Contemporary Corpus is released under a Creative Commons Attribution - Share Alike 3.0 Unported License. (CC BY SA 3.0) http://creativecommons.org/licenses/by-sa/3.0/;All the recipes of the SaCoCo Historical Corpus (but Knopf 1800, Franckfurt 1789 and Gr\u00e4z 1686) are released under a Creative Commons Attribution 3.0 Unported License. (CC BY 3.0) http://creativecommons.org/licenses/by/3.0/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dc07d2a2-b244-5216-83fd-a0d1f993c7a7",
-    "notes": [
-        "The Saarbr\u00fccken Cookbook Corpus is a diachronic corpus made up of cooking recipes organized into two different collections: historical and contemporary.\nThe historical component contains a selection of recipes from different works. The full nomina of sources can be found listed as sources in the metadata. These recipes were collected and transcribed by Andrea Wurm as part of her PhD. For more information see Wurm 2007.\nThe contemporary component contains cooking recipes from rezeptewiki.org. The selection criteria were temporal (only the last version of the recipe) and geographical (only recipes belonging to German speaking regions). The address of the wiki dump is provided in sources.\n\nANNOTATION:\nThe corpus contains two types of annotation: structural and positional.\n\nStructural annotation is written in XML and provides a description of the textual structure, on the one hand, and metatextual information and shallow semantics, on the other hand.\n\nSTRUCTURAL ATTRIBUTES:\nmetadata: id, collection, source, url, year, decade, period, language, ref;\nshallow semantics: type, course, cuisine, ingredient, method;\nstructure: title, body, segment, paragraph, sentence.\n\nPositional annotation is provided at token level containing linguistic information.\n\nPOSITIONAL ATTRIBUTES:\nword form;\nPOS (TreeTagger, STTS tagset);\nlemma (TreeTagger);\nnormalized form (automatic normalization using the algorithm described in Amoia and Mart\u00ednez Mart\u00ednez 2013)."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:sacoco"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus linguistics"
-        },
-        {
-            "name": "historical linguistics"
-        },
-        {
-            "name": "early modern age"
-        },
-        {
-            "name": "cooking recipe"
-        },
-        {
-            "name": "cookbook"
-        }
-    ],
-    "title": [
-        "SaCoCo Saarbr\u00fccken Cookbook Corpora"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dc0b3065-d461-5ba9-8975-60fc0d7f0a2f.json b/oaitestdata/clarin-oai_dc/SET_1/json/dc0b3065-d461-5ba9-8975-60fc0d7f0a2f.json
deleted file mode 100644
index ac152411..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dc0b3065-d461-5ba9-8975-60fc0d7f0a2f.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/45",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/45"
-    ],
-    "PID": "http://hdl.handle.net/11321/45",
-    "PublicationTimestamp": "2014-10-24T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Walkowiak, Tomasz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/45;2016-01-21T14:38:16Z;hdl_11321_3;hdl_11321_4;WCRFT Webservice (2014-10-24);Walkowiak, Tomasz;tagger;weblicht;Webservice for Weblicht;2014-10-24;toolService;http://hdl.handle.net/11321/45;pol;application/octet-stream;downloadable_files_count: 1;Wroc\u0142aw University of Technology;http://nlp.pwr.wroc.pl/redmine/projects/wcrft/wiki",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dc0b3065-d461-5ba9-8975-60fc0d7f0a2f",
-    "notes": [
-        "Webservice for Weblicht"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/45"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "tagger"
-        },
-        {
-            "name": "weblicht"
-        }
-    ],
-    "title": [
-        "WCRFT Webservice (2014-10-24)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dc0e114b-0604-56b8-944b-f4ee9e473614.json b/oaitestdata/clarin-oai_dc/SET_1/json/dc0e114b-0604-56b8-944b-f4ee9e473614.json
deleted file mode 100644
index 7f164624..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dc0e114b-0604-56b8-944b-f4ee9e473614.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2821",
-    "MetadataAccess": [
-        "oai:ota:oucs:2821"
-    ],
-    "PublicationTimestamp": "1735-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1735"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2821;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2821.xml;Drapier's Letters VII, An humble address to both Houses of Parliament;Swift, Jonathan, 1667-1745;1735;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dc0e114b-0604-56b8-944b-f4ee9e473614",
-    "oai_identifier": [
-        "oai:ota:oucs:2821"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Drapier's Letters VII, An humble address to both Houses of Parliament"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2821.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dc4549a3-c8e5-57e0-a05a-681ab91f7339.json b/oaitestdata/clarin-oai_dc/SET_1/json/dc4549a3-c8e5-57e0-a05a-681ab91f7339.json
deleted file mode 100644
index 21bc8db4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dc4549a3-c8e5-57e0-a05a-681ab91f7339.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5385",
-    "MetadataAccess": [
-        "oai:ota:oucs:5385"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Brown, John, 1715-1766."
-    ],
-    "fulltext": "oai:ota:oucs:5385;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5385.xml;An estimate of the manners and principles of the times: By the author of Essays on the characteristics, &c.;Brown, John, 1715-1766.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dc4549a3-c8e5-57e0-a05a-681ab91f7339",
-    "oai_identifier": [
-        "oai:ota:oucs:5385"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An estimate of the manners and principles of the times: By the author of Essays on the characteristics, &c."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5385.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dc967bac-85f4-57d6-8094-db4132e12622.json b/oaitestdata/clarin-oai_dc/SET_1/json/dc967bac-85f4-57d6-8094-db4132e12622.json
deleted file mode 100644
index 5b63c6c2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dc967bac-85f4-57d6-8094-db4132e12622.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "M. Gr\u00f6ll"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-149591",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-149591"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CE1-9",
-    "PublicationTimestamp": "1791-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1791"
-    ],
-    "Publisher": [
-        "M. Gr\u00f6ll"
-    ],
-    "RelatedIdentifier": [
-        "http://pbc.biaman.pl/Content/4505"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "author": [
-        "Jezierski, Franciszek Salezy"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-149591;2019-02-28T18:33:35Z;Niektore wyrazy porz\u0105dkiem abecad\u0142a zebrane y stosowanemi do rzeczy uwagami obia\u015bnione [...] Dzie\u0142o pogrobowe przez [...] napisane [...].;Jezierski, Franciszek Salezy;ilo\u015b\u0107 skan\u00f3w: 157 ; sygn. St-120;M. Gr\u00f6ll;1791;starodruk;application/xml;clarind-uds:poldilemma-149591;hdl:11858/00-246C-0000-0023-8CE1-9;pol;http://pbc.biaman.pl/Content/4505;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dc967bac-85f4-57d6-8094-db4132e12622",
-    "notes": [
-        "ilo\u015b\u0107 skan\u00f3w: 157 ; sygn. St-120"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-149591"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "title": [
-        "Niektore wyrazy porz\u0105dkiem abecad\u0142a zebrane y stosowanemi do rzeczy uwagami obia\u015bnione [...] Dzie\u0142o pogrobowe przez [...] napisane [...]."
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dc9e62fd-5267-5c27-856d-3b929a2c5684.json b/oaitestdata/clarin-oai_dc/SET_1/json/dc9e62fd-5267-5c27-856d-3b929a2c5684.json
deleted file mode 100644
index 45a0526b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dc9e62fd-5267-5c27-856d-3b929a2c5684.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3618",
-    "MetadataAccess": [
-        "oai:ota:oucs:3618"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Defoe, Daniel, 1661?-1731."
-    ],
-    "fulltext": "oai:ota:oucs:3618;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3618.xml;Arguments about the alteration of triennial elections of Parliament. In a letter to a friend in the country;Defoe, Daniel, 1661?-1731.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dc9e62fd-5267-5c27-856d-3b929a2c5684",
-    "oai_identifier": [
-        "oai:ota:oucs:3618"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Arguments about the alteration of triennial elections of Parliament. In a letter to a friend in the country"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3618.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dca0efbd-342c-5548-aad0-88f6027149ef.json b/oaitestdata/clarin-oai_dc/SET_1/json/dca0efbd-342c-5548-aad0-88f6027149ef.json
deleted file mode 100644
index 5cd3cd7d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dca0efbd-342c-5548-aad0-88f6027149ef.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2542",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2542"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2542",
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Bej\u010dek, Eduard",
-        "Mikulov\u00e1, Marie"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2542;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;ForFun 1.0;Mikulov\u00e1, Marie;Bej\u010dek, Eduard;form;function;database;syntax;ForFun is a database of linguistic forms and their syntactic functions built with the use of the multi-layer annotated corpora of Czech, the Prague Dependency Treebanks. The purpose of the Prague Database of Forms and Functions (ForFun) is to help the linguists to study the form-function relation, which we assume to be one of the principal tasks of both theoretical linguistics and natural language processing.\r\n\r\nA prototypical question to be asked is \"What purposes does a preposition 'po' serve for\" or \"What are the linguistic means in the sentence that can express the meaning 'a destination of an action'?\". There are almost 1500 distinct forms (besides the 'po' preposition) and 65 distinct functions (besides the 'destination').;2017-12;toolService;http://hdl.handle.net/11234/1-2542;ces;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://ufal.mff.cuni.cz/ForFun",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dca0efbd-342c-5548-aad0-88f6027149ef",
-    "notes": [
-        "ForFun is a database of linguistic forms and their syntactic functions built with the use of the multi-layer annotated corpora of Czech, the Prague Dependency Treebanks. The purpose of the Prague Database of Forms and Functions (ForFun) is to help the linguists to study the form-function relation, which we assume to be one of the principal tasks of both theoretical linguistics and natural language processing.\r\n\r\nA prototypical question to be asked is \"What purposes does a preposition 'po' serve for\" or \"What are the linguistic means in the sentence that can express the meaning 'a destination of an action'?\". There are almost 1500 distinct forms (besides the 'po' preposition) and 65 distinct functions (besides the 'destination')."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2542"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "form"
-        },
-        {
-            "name": "function"
-        },
-        {
-            "name": "database"
-        },
-        {
-            "name": "syntax"
-        }
-    ],
-    "title": [
-        "ForFun 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dd0904ba-538e-5a9b-9eca-fd7adf8a21a3.json b/oaitestdata/clarin-oai_dc/SET_1/json/dd0904ba-538e-5a9b-9eca-fd7adf8a21a3.json
deleted file mode 100644
index 323dc399..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dd0904ba-538e-5a9b-9eca-fd7adf8a21a3.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "between 512 KB and 1 MB "
-    ],
-    "Language": [
-        "French"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0185",
-    "MetadataAccess": [
-        "oai:ota:oucs:0185"
-    ],
-    "PublicationTimestamp": "1775-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1775"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Letters"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Constant, Benjamin,  1767-1830"
-    ],
-    "fulltext": "oai:ota:oucs:0185;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0185.xml; Lettres  / compiled by Cecil Courtney;Constant, Benjamin,  1767-1830;1775-1830;text_and_corpus_linguistics;Letters -- France -- 18th century;Letters -- France -- 19th century;fra;Oxford Text Archive, University of Oxford;between 512 KB and 1 MB ;Text;Letters;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dd0904ba-538e-5a9b-9eca-fd7adf8a21a3",
-    "oai_identifier": [
-        "oai:ota:oucs:0185"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Letters -- France -- th century"
-        },
-        {
-            "name": "Letters -- France -- th century"
-        }
-    ],
-    "title": [
-        " Lettres  / compiled by Cecil Courtney"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0185.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dd13319f-835b-5186-872f-d239b5969291.json b/oaitestdata/clarin-oai_dc/SET_1/json/dd13319f-835b-5186-872f-d239b5969291.json
deleted file mode 100644
index 2ccb2f73..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dd13319f-835b-5186-872f-d239b5969291.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/23",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/23"
-    ],
-    "PID": "http://hdl.handle.net/10794/23",
-    "PublicationTimestamp": "2012-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/23;2017-10-27T15:27:49Z;hdl_10794_1;hdl_10794_2;Diachronic pivot (2017-10-16);Diakronisk pivot (2017-10-16);n/a, n/a;Swedish;Diachronic;Pivot;Diachronic pivot resource.;En diakronisk pivotresurs.;2012-05-30;lexicalConceptualResource;http://hdl.handle.net/10794/23;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/diapivot",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dd13319f-835b-5186-872f-d239b5969291",
-    "notes": [
-        "Diachronic pivot resource.",
-        "En diakronisk pivotresurs."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/23"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Diachronic"
-        },
-        {
-            "name": "Pivot"
-        }
-    ],
-    "title": [
-        "Diachronic pivot (2017-10-16)",
-        "Diakronisk pivot (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dd16d96a-c08f-5a95-98e5-511b622b63c9.json b/oaitestdata/clarin-oai_dc/SET_1/json/dd16d96a-c08f-5a95-98e5-511b622b63c9.json
deleted file mode 100644
index 4280e9d1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dd16d96a-c08f-5a95-98e5-511b622b63c9.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=06cd0a6acab411e1a404080027e73ea2a136f2f220ad4ec89ac5e485765b73c8",
-    "MetadataAccess": [
-        "06cd0a6acab411e1a404080027e73ea2a136f2f220ad4ec89ac5e485765b73c8"
-    ],
-    "PublicationTimestamp": "2012-11-28T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "fulltext": "06cd0a6acab411e1a404080027e73ea2a136f2f220ad4ec89ac5e485765b73c8;2018-11-15T16:39:34Z;corpus;corpus:text;Summ-it;The corpus was developed as a linguistic resource for Automatic Summarization research and his relation with different issues to engage studies on the discourse treatment. \nSumm-it consists of fifty texts from Science domain extracted from Science section of Brazilian daily newspaper Folha de S\u00c3\u00a3o Paulo (FSP), compose by:\nI. Human summaries produced by experts in summarization (Coelho, 2007), rewriting the original texts in a compressed format.\nII. Automatic summaries, obtained by GistSumm (Pardo et al., 2002, and Pardo et al., 2003) and SuPor-2 (Leite and Rino, 2006a, Leite and Rino, 2006c, and Leite and Rino, 2006b). All summaries were generated with a 70% compression rate, which means that the summaries correspond to roughly 30% of the original texts.\nIII. Manual underline sentences which contain relevant informations from the original texts (see 3.2). \nIV. Texts semi-automatically annotated with morpho-syntactic informations, assisted by the syntactic parser PALAVRAS (available at: http://visl.sdu.dk/visl/pt/) and Xtractor converter (available at: http://abc.di.uevora.pt/xtractor/).\nV. Texts semi-automatically annotated with co-reference informations (MMAX) and with rhetorical relations (RST) (cf. Carbonel et al., 2007, Fuchs, 2008, and Collovini et al., 2007) of noun phrases. The first process intents the identification of the entities in the discourse (e.g. noun phrases) referred or recovered in the text and, the second one, permits to structure a text by relating their discursive units through RST relations. ;2012-11-28",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dd16d96a-c08f-5a95-98e5-511b622b63c9",
-    "notes": [
-        "The corpus was developed as a linguistic resource for Automatic Summarization research and his relation with different issues to engage studies on the discourse treatment. \nSumm-it consists of fifty texts from Science domain extracted from Science section of Brazilian daily newspaper Folha de S\u00c3\u00a3o Paulo (FSP), compose by:\nI. Human summaries produced by experts in summarization (Coelho, 2007), rewriting the original texts in a compressed format.\nII. Automatic summaries, obtained by GistSumm (Pardo et al., 2002, and Pardo et al., 2003) and SuPor-2 (Leite and Rino, 2006a, Leite and Rino, 2006c, and Leite and Rino, 2006b). All summaries were generated with a 70% compression rate, which means that the summaries correspond to roughly 30% of the original texts.\nIII. Manual underline sentences which contain relevant informations from the original texts (see 3.2). \nIV. Texts semi-automatically annotated with morpho-syntactic informations, assisted by the syntactic parser PALAVRAS (available at: http://visl.sdu.dk/visl/pt/) and Xtractor converter (available at: http://abc.di.uevora.pt/xtractor/).\nV. Texts semi-automatically annotated with co-reference informations (MMAX) and with rhetorical relations (RST) (cf. Carbonel et al., 2007, Fuchs, 2008, and Collovini et al., 2007) of noun phrases. The first process intents the identification of the entities in the discourse (e.g. noun phrases) referred or recovered in the text and, the second one, permits to structure a text by relating their discursive units through RST relations. "
-    ],
-    "oai_identifier": [
-        "06cd0a6acab411e1a404080027e73ea2a136f2f220ad4ec89ac5e485765b73c8"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "Summ-it"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dd3c5ac5-b469-5def-9110-b183d26a3ef1.json b/oaitestdata/clarin-oai_dc/SET_1/json/dd3c5ac5-b469-5def-9110-b183d26a3ef1.json
deleted file mode 100644
index 7ec27a07..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dd3c5ac5-b469-5def-9110-b183d26a3ef1.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Ule, Louis"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3027",
-    "MetadataAccess": [
-        "oai:ota:oucs:3027"
-    ],
-    "PublicationTimestamp": "1587-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1587"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Ovid",
-        "Marlowe, Christopher, 1564-1593"
-    ],
-    "fulltext": "oai:ota:oucs:3027;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3027.xml;Ovid's elegies;Marlowe, Christopher, 1564-1593;Ovid;not after: 1587;text_and_corpus_linguistics;English poetry -- Early modern, 1500-1700;eng;Oxford Text Archive, University of Oxford;Ule, Louis;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dd3c5ac5-b469-5def-9110-b183d26a3ef1",
-    "oai_identifier": [
-        "oai:ota:oucs:3027"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English poetry -- Early modern"
-        }
-    ],
-    "title": [
-        "Ovid's elegies"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3027.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dd3f71b5-815f-50de-b160-00b5b906338f.json b/oaitestdata/clarin-oai_dc/SET_1/json/dd3f71b5-815f-50de-b160-00b5b906338f.json
deleted file mode 100644
index ac254494..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dd3f71b5-815f-50de-b160-00b5b906338f.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "text/xml",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1520",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1520"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1520",
-    "PublicationTimestamp": "2015-07-31T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-1807"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "Vidra, Jon\u00e1\u0161",
-        "\u0160ev\u010d\u00edkov\u00e1, Magda",
-        "Straka, Milan"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1520;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;DeriNet 1.0;Vidra, Jon\u00e1\u0161;\u017dabokrtsk\u00fd, Zden\u011bk;\u0160ev\u010d\u00edkov\u00e1, Magda;Straka, Milan;derivation;DeriNet;lexical network;MorfFlex;DeriNet is a lexical network which contains derivational relations in Czech modeled as an oriented graph. Nodes correspond to Czech lexemes (a lexeme is a single lemma, possibly with only a subset of its senses \u2013 homonyms may have different derivations and are thus represented by several lexemes) and edges represent derivations between them. DeriNet 1.0 contains 968,967 lexemes with 965,535 unique lemmas; connected by 715,729 derivational links. Lexemes in DeriNet 1.0 are sampled from the MorfFlex dictionary.;2015-07-31;lexicalConceptualResource;http://hdl.handle.net/11234/1-1520;ces;http://hdl.handle.net/11234/1-1807;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/octet-stream;text/xml;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://ufal.mff.cuni.cz/derinet",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dd3f71b5-815f-50de-b160-00b5b906338f",
-    "notes": [
-        "DeriNet is a lexical network which contains derivational relations in Czech modeled as an oriented graph. Nodes correspond to Czech lexemes (a lexeme is a single lemma, possibly with only a subset of its senses \u2013 homonyms may have different derivations and are thus represented by several lexemes) and edges represent derivations between them. DeriNet 1.0 contains 968,967 lexemes with 965,535 unique lemmas; connected by 715,729 derivational links. Lexemes in DeriNet 1.0 are sampled from the MorfFlex dictionary."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1520"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "derivation"
-        },
-        {
-            "name": "DeriNet"
-        },
-        {
-            "name": "lexical network"
-        },
-        {
-            "name": "MorfFlex"
-        }
-    ],
-    "title": [
-        "DeriNet 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dd4ffc91-07b5-52a0-b3f5-6973b41e555e.json b/oaitestdata/clarin-oai_dc/SET_1/json/dd4ffc91-07b5-52a0-b3f5-6973b41e555e.json
deleted file mode 100644
index 98601104..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dd4ffc91-07b5-52a0-b3f5-6973b41e555e.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "University of Dundee"
-    ],
-    "Contributor": [
-        "Skretkowicz, Victor"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-980",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-980"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-980",
-    "PublicationTimestamp": "2004-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2004"
-    ],
-    "Publisher": [
-        "University of Dundee"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-980;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Dictionary of the Scots language;Skretkowicz, Victor;Historical dictionary of the Scottish language as written and spoken by lowland Scots in Scotland and Ulster from the 12th century onward. Over eighty thousand full-word entries.;2004;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-980;eng;downloadable_files_count: 0;United Kingdom;University of Dundee;http://www.dsl.ac.uk/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dd4ffc91-07b5-52a0-b3f5-6973b41e555e",
-    "notes": [
-        "Historical dictionary of the Scottish language as written and spoken by lowland Scots in Scotland and Ulster from the 12th century onward. Over eighty thousand full-word entries."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-980"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Dictionary of the Scots language"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dd516e79-675c-55eb-8ec7-0c614f3bb1ad.json b/oaitestdata/clarin-oai_dc/SET_1/json/dd516e79-675c-55eb-8ec7-0c614f3bb1ad.json
deleted file mode 100644
index b9baaf9e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dd516e79-675c-55eb-8ec7-0c614f3bb1ad.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Simov, Kiril"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Bulgarian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-240",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-240"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-240",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Bulgaria"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-240;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;BulTreeBank Stopword List;Simov, Kiril;805 prepositions, pronouns, etc stop words, UTF-16 list of wordforms;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-240;bul;downloadable_files_count: 0;Bulgaria;http://www.bultreebank.org/resources/BTB-StopWordList.zip",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dd516e79-675c-55eb-8ec7-0c614f3bb1ad",
-    "notes": [
-        "805 prepositions, pronouns, etc stop words, UTF-16 list of wordforms"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-240"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "BulTreeBank Stopword List"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dd55c108-c5d3-510a-97e7-c69663592584.json b/oaitestdata/clarin-oai_dc/SET_1/json/dd55c108-c5d3-510a-97e7-c69663592584.json
deleted file mode 100644
index e359ec9e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dd55c108-c5d3-510a-97e7-c69663592584.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3256",
-    "MetadataAccess": [
-        "oai:ota:oucs:3256"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dickens, Charles, 1812-1870"
-    ],
-    "fulltext": "oai:ota:oucs:3256;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3256.xml;A Christmas carol in prose: being a ghost story of Christmas;Dickens, Charles, 1812-1870;default: 1976-01-01;text_and_corpus_linguistics;Fiction -- Great Britain -- 19th century;Ghost stories -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dd55c108-c5d3-510a-97e7-c69663592584",
-    "oai_identifier": [
-        "oai:ota:oucs:3256"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- Great Britain -- th century"
-        },
-        {
-            "name": "Ghost stories -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "A Christmas carol in prose: being a ghost story of Christmas"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3256.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dd9f8c51-850a-57b7-b4b7-c42ff6d5095c.json b/oaitestdata/clarin-oai_dc/SET_1/json/dd9f8c51-850a-57b7-b4b7-c42ff6d5095c.json
deleted file mode 100644
index 0cf6f31d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dd9f8c51-850a-57b7-b4b7-c42ff6d5095c.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4372",
-    "MetadataAccess": [
-        "oai:ota:oucs:4372"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "O'Keeffe, John, 1747-1833."
-    ],
-    "fulltext": "oai:ota:oucs:4372;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4372.xml;The she gallant: or, square-toes outwitted: A new comedy of two acts. As now performing, with great applause, at the Theatre in Smock-Alley, Dublin.;O'Keeffe, John, 1747-1833.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dd9f8c51-850a-57b7-b4b7-c42ff6d5095c",
-    "oai_identifier": [
-        "oai:ota:oucs:4372"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The she gallant: or, square-toes outwitted: A new comedy of two acts. As now performing, with great applause, at the Theatre in Smock-Alley, Dublin."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4372.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ddbc6e1f-c1f4-51d5-8186-6c7ac58588e7.json b/oaitestdata/clarin-oai_dc/SET_1/json/ddbc6e1f-c1f4-51d5-8186-6c7ac58588e7.json
deleted file mode 100644
index 9d0d8855..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ddbc6e1f-c1f4-51d5-8186-6c7ac58588e7.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Jazykovedn\u00fd \u00fastav \u013d. \u0160t\u00fara Slovenskej akad\u00e9mie vied"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Slovak"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1822",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1822"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1822",
-    "PublicationTimestamp": "2016-11-07T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Jazykovedn\u00fd \u00fastav \u013d. \u0160t\u00fara Slovenskej akad\u00e9mie vied"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Gajdo\u0161ov\u00e1, Katar\u00edna",
-        "\u0160imkov\u00e1, M\u00e1ria",
-        "et al."
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1822;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Slovak Dependency Treebank;Gajdo\u0161ov\u00e1, Katar\u00edna;\u0160imkov\u00e1, M\u00e1ria;et al.;dependency;treebank;syntax;morphology;Slovak Dependency Treebank (Slovensk\u00fd z\u00e1vislostn\u00fd korpus) was created as part of the Slovak National Corpus at the \u013d. \u0160t\u00far Institute of the Slovak Academy of Sciences. The annotation follows the guidelines of the Prague Dependency Treebank (Czech), slightly modified in the spirit of Slovak grammatical tradition. Morphological tags, lemmas and dependency relations have been assigned manually to every word.\r\n\r\nThe present dataset is a subset of the original treebank. We automatically selected the sentences where the two human annotators 100% agreed on the analysis. This increases the quality and trustworthiness of the data but it also results in selecting short sentences most of the time. An extended version may be published in the future when manually merged and checked annotation is available.\r\n\r\nThe selected sentences have been converted to the CoNLL-X file format (original token IDs are preserved in the FEATS column). This PDT-style annotation will serve as the source for the first Slovak dataset in the Universal Dependencies (to be published separately).;2016-11-07;corpus;http://hdl.handle.net/11234/1-1822;slk;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Jazykovedn\u00fd \u00fastav \u013d. \u0160t\u00fara Slovenskej akad\u00e9mie vied;http://korpus.juls.savba.sk/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ddbc6e1f-c1f4-51d5-8186-6c7ac58588e7",
-    "notes": [
-        "Slovak Dependency Treebank (Slovensk\u00fd z\u00e1vislostn\u00fd korpus) was created as part of the Slovak National Corpus at the \u013d. \u0160t\u00far Institute of the Slovak Academy of Sciences. The annotation follows the guidelines of the Prague Dependency Treebank (Czech), slightly modified in the spirit of Slovak grammatical tradition. Morphological tags, lemmas and dependency relations have been assigned manually to every word.\r\n\r\nThe present dataset is a subset of the original treebank. We automatically selected the sentences where the two human annotators 100% agreed on the analysis. This increases the quality and trustworthiness of the data but it also results in selecting short sentences most of the time. An extended version may be published in the future when manually merged and checked annotation is available.\r\n\r\nThe selected sentences have been converted to the CoNLL-X file format (original token IDs are preserved in the FEATS column). This PDT-style annotation will serve as the source for the first Slovak dataset in the Universal Dependencies (to be published separately)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1822"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "dependency"
-        },
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "syntax"
-        },
-        {
-            "name": "morphology"
-        }
-    ],
-    "title": [
-        "Slovak Dependency Treebank"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ddc6ab4a-cbce-581b-b30d-a65915c4c2a8.json b/oaitestdata/clarin-oai_dc/SET_1/json/ddc6ab4a-cbce-581b-b30d-a65915c4c2a8.json
deleted file mode 100644
index e7047c54..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ddc6ab4a-cbce-581b-b30d-a65915c4c2a8.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4049",
-    "MetadataAccess": [
-        "oai:ota:oucs:4049"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Addison, Joseph, 1672-1719."
-    ],
-    "fulltext": "oai:ota:oucs:4049;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4049.xml;The free-holder: or political essays.;Addison, Joseph, 1672-1719.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ddc6ab4a-cbce-581b-b30d-a65915c4c2a8",
-    "oai_identifier": [
-        "oai:ota:oucs:4049"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The free-holder: or political essays."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4049.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ddd0caaa-b754-5249-9151-8fdcaf6b6a89.json b/oaitestdata/clarin-oai_dc/SET_1/json/ddd0caaa-b754-5249-9151-8fdcaf6b6a89.json
deleted file mode 100644
index 95e7710b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ddd0caaa-b754-5249-9151-8fdcaf6b6a89.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3081",
-    "MetadataAccess": [
-        "oai:ota:oucs:3081"
-    ],
-    "PublicationTimestamp": "1844-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1844"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dickens, Charles, 1812-1870"
-    ],
-    "fulltext": "oai:ota:oucs:3081;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3081.xml;Martin Chuzzlewit;Dickens, Charles, 1812-1870;not after: 1844;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ddd0caaa-b754-5249-9151-8fdcaf6b6a89",
-    "oai_identifier": [
-        "oai:ota:oucs:3081"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Martin Chuzzlewit"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3081.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dde63a4a-0f6f-503c-9c4e-cd16de5d0f68.json b/oaitestdata/clarin-oai_dc/SET_1/json/dde63a4a-0f6f-503c-9c4e-cd16de5d0f68.json
deleted file mode 100644
index a459f79f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dde63a4a-0f6f-503c-9c4e-cd16de5d0f68.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Prymasowska"
-    ],
-    "Contributor": [
-        "Perzyna, Ludwik (1742-1800). T\u0142."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229190",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229190"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D08-B",
-    "PublicationTimestamp": "1796-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1796"
-    ],
-    "Publisher": [
-        "Drukarnia Prymasowska"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/229190",
-        "oai:jbc.bj.uj.edu.pl:publication:240830"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1701/1800"
-    ],
-    "TempCoverageBegin": 53662478399,
-    "TempCoverageEnd": 53662478399,
-    "TemporalCoverage": " point in time : 1701-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1701-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1701-07-01T11:59:59Z",
-    "author": [
-        "Tissot, Samuel Auguste Andr\u00e9 David (1728-1797)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229190;2019-03-01T13:00:39Z;Porzadek Zycia w Czerstwosci Zdrowia W D\u0142ugie Prowadz\u0105cy Lata;Tissot, Samuel Auguste Andr\u00e9 David (1728-1797);starodruki 18\u00a0w.;Drukarnia Prymasowska;Perzyna, Ludwik (1742-1800). T\u0142.;[1796];starodruk;application/xml;clarind-uds:poldilemma-229190;hdl:11858/00-246C-0000-0023-8D08-B;Biblioteka Jagiello\u0144ska, BJ St. Dr. 42675 I;pol;http://jbc.bj.uj.edu.pl/Content/229190;oai:jbc.bj.uj.edu.pl:publication:240830;1701/1800;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dde63a4a-0f6f-503c-9c4e-cd16de5d0f68",
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229190"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Porzadek Zycia w Czerstwosci Zdrowia W D\u0142ugie Prowadz\u0105cy Lata"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ddf1767b-3909-5224-8322-d6e49a1790f9.json b/oaitestdata/clarin-oai_dc/SET_1/json/ddf1767b-3909-5224-8322-d6e49a1790f9.json
deleted file mode 100644
index 73f5184a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ddf1767b-3909-5224-8322-d6e49a1790f9.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3639",
-    "MetadataAccess": [
-        "oai:ota:oucs:3639"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dodington, George Bubb, Baron of Melcombe Regis, 1691-1762."
-    ],
-    "fulltext": "oai:ota:oucs:3639;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3639.xml;A poetical epistle from the late Lord Melcombe to the Earl of Bute: with corrections, by the author of the Night thoughts;Dodington, George Bubb, Baron of Melcombe Regis, 1691-1762.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ddf1767b-3909-5224-8322-d6e49a1790f9",
-    "oai_identifier": [
-        "oai:ota:oucs:3639"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A poetical epistle from the late Lord Melcombe to the Earl of Bute: with corrections, by the author of the Night thoughts"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3639.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/de00e0fc-92ed-5f69-a6a8-906cf721c814.json b/oaitestdata/clarin-oai_dc/SET_1/json/de00e0fc-92ed-5f69-a6a8-906cf721c814.json
deleted file mode 100644
index d2af63e0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/de00e0fc-92ed-5f69-a6a8-906cf721c814.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3516",
-    "MetadataAccess": [
-        "oai:ota:oucs:3516"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Goldsmith, Oliver, 1730?-1774."
-    ],
-    "fulltext": "oai:ota:oucs:3516;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3516.xml;Edwin and Angelina: A ballad. By Mr. Goldsmith. Printed for the amusement of the Countess of Northumberland.;Goldsmith, Oliver, 1730?-1774.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "de00e0fc-92ed-5f69-a6a8-906cf721c814",
-    "oai_identifier": [
-        "oai:ota:oucs:3516"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Edwin and Angelina: A ballad. By Mr. Goldsmith. Printed for the amusement of the Countess of Northumberland."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3516.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/de010b14-125e-5ace-b86a-e87b4333cde9.json b/oaitestdata/clarin-oai_dc/SET_1/json/de010b14-125e-5ace-b86a-e87b4333cde9.json
deleted file mode 100644
index 43053527..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/de010b14-125e-5ace-b86a-e87b4333cde9.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3780",
-    "MetadataAccess": [
-        "oai:ota:oucs:3780"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Macklin, Charles, 1697?-1797."
-    ],
-    "fulltext": "oai:ota:oucs:3780;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3780.xml;Proposals for publishing by subscription The man of the world, a comedy, in five acts; and, Love a la mode, a comedy, in two acts, written by Mr. Charles Macklin.;Man of the world.;Macklin, Charles, 1697?-1797.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "de010b14-125e-5ace-b86a-e87b4333cde9",
-    "oai_identifier": [
-        "oai:ota:oucs:3780"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Proposals for publishing by subscription The man of the world, a comedy, in five acts; and, Love a la mode, a comedy, in two acts, written by Mr. Charles Macklin.",
-        "Man of the world."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3780.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/de13283a-9e7c-56a6-8e94-f01211a08655.json b/oaitestdata/clarin-oai_dc/SET_1/json/de13283a-9e7c-56a6-8e94-f01211a08655.json
deleted file mode 100644
index 48867c4f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/de13283a-9e7c-56a6-8e94-f01211a08655.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 186 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "Old Proven\u00e7al (to 1500)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0379",
-    "MetadataAccess": [
-        "oai:ota:oucs:0379"
-    ],
-    "PublicationTimestamp": "1295-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1295"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Jofre de Foix\u00c3\u00a0, 13th cent."
-    ],
-    "fulltext": "oai:ota:oucs:0379;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0379.xml;The Regles de Trobar of Jofre de Foixa;Jofre de Foix\u00c3\u00a0, 13th cent.;1295;text_and_corpus_linguistics;Poems -- France -- 13th century;pro;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 186 KB);Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "de13283a-9e7c-56a6-8e94-f01211a08655",
-    "oai_identifier": [
-        "oai:ota:oucs:0379"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- France -- th century"
-        }
-    ],
-    "title": [
-        "The Regles de Trobar of Jofre de Foixa"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0379.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/de24232f-aa4a-5d84-9673-2be35aa1fdd0.json b/oaitestdata/clarin-oai_dc/SET_1/json/de24232f-aa4a-5d84-9673-2be35aa1fdd0.json
deleted file mode 100644
index 739a5cc6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/de24232f-aa4a-5d84-9673-2be35aa1fdd0.json
+++ /dev/null
@@ -1,101 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "text/html",
-        "application/octet-stream"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2380",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2380"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2380",
-    "PublicationTimestamp": "2017-01-10T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Mozilla Public License 2.0",
-        "http://opensource.org/licenses/MPL-2.0",
-        "PUB"
-    ],
-    "author": [
-        "Klus\u00e1\u010dek, David"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2380;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;EFCL Channelizer;Klus\u00e1\u010dek, David;Fast Channelizer;Filterbank;ASR Front End;Software   Defined Radio;Polyphase Filter;Frequency Multiplexing;Audio Denoising;High Performance Computing;HPC;SDR;FFT;FFTW;SIMD;AVX;SSE;NEON;Extremely fast digital audio channelizer implementation, usable as a building block for experimental ASR front-ends or signal denoising applications. Also applicable in software defined radios, due to its high throughput. It comes in a form of a C/C++ library and an executable example program which reads input stream, splitting it into equidistant frequency channels, emitting their data to the output.\r\n\r\nFeatures:\r\n\r\n(1) Hand tuned SIMD-aware assembly for x86 (SSE) and IA64 (AVX) as well as for ARM (NEON) processors.\r\n(2) Generic non-SIMD C++ implementation for other architectures.\r\n(3) Capable of taking advantage of multicore CPUs.\r\n(4) Fully configurable number of channels and the output decimation rate.\r\n(5) User supplied FIR of the channel separation filter, which allows to specify the width of the channels, whether they should overlap or be separated.\r\n(6) Input and output signal samples are treated as complex numbers.\r\n(7) Speed over 750 complex MS/s achieved on Core i7 4710HQ @ 2.5GHz, when channelizing into 72 output channels with a FIR length of 1152 samples, using 3 computing threads.\r\n(8) Runs under Linux OS.;2017-01-10;toolService;http://hdl.handle.net/11234/1-2380;Mozilla Public License 2.0;http://opensource.org/licenses/MPL-2.0;PUB;application/octet-stream;text/html;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://atrey.karlin.mff.cuni.cz/~klusacek/EFCL.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "de24232f-aa4a-5d84-9673-2be35aa1fdd0",
-    "notes": [
-        "Extremely fast digital audio channelizer implementation, usable as a building block for experimental ASR front-ends or signal denoising applications. Also applicable in software defined radios, due to its high throughput. It comes in a form of a C/C++ library and an executable example program which reads input stream, splitting it into equidistant frequency channels, emitting their data to the output.\r\n\r\nFeatures:\r\n\r\n(1) Hand tuned SIMD-aware assembly for x86 (SSE) and IA64 (AVX) as well as for ARM (NEON) processors.\r\n(2) Generic non-SIMD C++ implementation for other architectures.\r\n(3) Capable of taking advantage of multicore CPUs.\r\n(4) Fully configurable number of channels and the output decimation rate.\r\n(5) User supplied FIR of the channel separation filter, which allows to specify the width of the channels, whether they should overlap or be separated.\r\n(6) Input and output signal samples are treated as complex numbers.\r\n(7) Speed over 750 complex MS/s achieved on Core i7 4710HQ @ 2.5GHz, when channelizing into 72 output channels with a FIR length of 1152 samples, using 3 computing threads.\r\n(8) Runs under Linux OS."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2380"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Fast Channelizer"
-        },
-        {
-            "name": "Filterbank"
-        },
-        {
-            "name": "ASR Front End"
-        },
-        {
-            "name": "Software Defined Radio"
-        },
-        {
-            "name": "Polyphase Filter"
-        },
-        {
-            "name": "Frequency Multiplexing"
-        },
-        {
-            "name": "Audio Denoising"
-        },
-        {
-            "name": "High Performance Computing"
-        },
-        {
-            "name": "HPC"
-        },
-        {
-            "name": "SDR"
-        },
-        {
-            "name": "FFT"
-        },
-        {
-            "name": "FFTW"
-        }
-    ],
-    "title": [
-        "EFCL Channelizer"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/de3f1501-0f22-5bf5-a936-c20c165016d1.json b/oaitestdata/clarin-oai_dc/SET_1/json/de3f1501-0f22-5bf5-a936-c20c165016d1.json
deleted file mode 100644
index 7e9bbfc7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/de3f1501-0f22-5bf5-a936-c20c165016d1.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5500",
-    "MetadataAccess": [
-        "oai:ota:oucs:5500"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Glover, Richard, 1712-1785."
-    ],
-    "fulltext": "oai:ota:oucs:5500;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5500.xml;The substance of the evidence on the petition presented by the West-India planters and merchants, to the Hon. House of Commons: as it was introduced at the bar, and summ'd up by Mr. Glover, on Thursday the 16th of March, 1775.;Glover, Richard, 1712-1785.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "de3f1501-0f22-5bf5-a936-c20c165016d1",
-    "oai_identifier": [
-        "oai:ota:oucs:5500"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The substance of the evidence on the petition presented by the West-India planters and merchants, to the Hon. House of Commons: as it was introduced at the bar, and summ'd up by Mr. Glover, on Thursday the 16th of March, 1775."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5500.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/de486d6c-3904-5be4-becb-c2c90aec0563.json b/oaitestdata/clarin-oai_dc/SET_1/json/de486d6c-3904-5be4-becb-c2c90aec0563.json
deleted file mode 100644
index 21d44e53..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/de486d6c-3904-5be4-becb-c2c90aec0563.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4447",
-    "MetadataAccess": [
-        "oai:ota:oucs:4447"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Griffith, Mrs. (Elizabeth), 1720?-1793."
-    ],
-    "fulltext": "oai:ota:oucs:4447;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4447.xml;The story of Lady Juliana Harley: A novel. In letters. By Mrs. Griffith. ... [pt.1];Griffith, Mrs. (Elizabeth), 1720?-1793.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "de486d6c-3904-5be4-becb-c2c90aec0563",
-    "oai_identifier": [
-        "oai:ota:oucs:4447"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The story of Lady Juliana Harley: A novel. In letters. By Mrs. Griffith. ... [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4447.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/de5a89d4-ed72-591d-b8d5-85653a1a7707.json b/oaitestdata/clarin-oai_dc/SET_1/json/de5a89d4-ed72-591d-b8d5-85653a1a7707.json
deleted file mode 100644
index 16b2d858..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/de5a89d4-ed72-591d-b8d5-85653a1a7707.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3072",
-    "MetadataAccess": [
-        "oai:ota:oucs:3072"
-    ],
-    "PublicationTimestamp": "1847-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1847"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Bront\u00c3\u00ab, Anne, 1820-1849"
-    ],
-    "fulltext": "oai:ota:oucs:3072;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3072.xml;Agnes Grey;Bront\u00c3\u00ab, Anne, 1820-1849;not after: 1847;text_and_corpus_linguistics;Novels -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "de5a89d4-ed72-591d-b8d5-85653a1a7707",
-    "oai_identifier": [
-        "oai:ota:oucs:3072"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Novels -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Agnes Grey"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3072.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/deaa0479-176f-5940-920a-3a463dc18a23.json b/oaitestdata/clarin-oai_dc/SET_1/json/deaa0479-176f-5940-920a-3a463dc18a23.json
deleted file mode 100644
index 1709ecde..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/deaa0479-176f-5940-920a-3a463dc18a23.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3012",
-    "MetadataAccess": [
-        "oai:ota:oucs:3012"
-    ],
-    "PublicationTimestamp": "1909-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1909"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Kipling, Rudyard, 1865-1936"
-    ],
-    "fulltext": "oai:ota:oucs:3012;2018-05-25T10:13:59Z;http://ota.ox.ac.uk/headers/3012.xml;Actions and Reactions;Kipling, Rudyard, 1865-1936;not after: 1909;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "deaa0479-176f-5940-920a-3a463dc18a23",
-    "oai_identifier": [
-        "oai:ota:oucs:3012"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Actions and Reactions"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3012.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/deca9dac-f465-5e65-9ebd-2b722bf2d60c.json b/oaitestdata/clarin-oai_dc/SET_1/json/deca9dac-f465-5e65-9ebd-2b722bf2d60c.json
deleted file mode 100644
index 4df2eb4f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/deca9dac-f465-5e65-9ebd-2b722bf2d60c.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4715",
-    "MetadataAccess": [
-        "oai:ota:oucs:4715"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Coxe, William, 1747-1828."
-    ],
-    "fulltext": "oai:ota:oucs:4715;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4715.xml;Sketches of the natural, civil, and political state of Swisserland: in a series of letters to William Melmoth, Esq; from William Coxe, ...;Coxe, William, 1747-1828.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "deca9dac-f465-5e65-9ebd-2b722bf2d60c",
-    "oai_identifier": [
-        "oai:ota:oucs:4715"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Sketches of the natural, civil, and political state of Swisserland: in a series of letters to William Melmoth, Esq; from William Coxe, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4715.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/decfcba7-f797-5b1b-afb8-f1fe634da4fb.json b/oaitestdata/clarin-oai_dc/SET_1/json/decfcba7-f797-5b1b-afb8-f1fe634da4fb.json
deleted file mode 100644
index 347d1c24..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/decfcba7-f797-5b1b-afb8-f1fe634da4fb.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Nadworna Jego Kr\u00f3lewskiej Mo\u015bci i Komisji Edukacji Narodowej"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-150201",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-150201"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CE2-7",
-    "PublicationTimestamp": "1782-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1782"
-    ],
-    "Publisher": [
-        "Drukarnia Nadworna Jego Kr\u00f3lewskiej Mo\u015bci i Komisji Edukacji Narodowej"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/150201",
-        "oai:jbc.bj.uj.edu.pl:publication:158450"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1701/1800"
-    ],
-    "TempCoverageBegin": 53662478399,
-    "TempCoverageEnd": 53662478399,
-    "TemporalCoverage": " point in time : 1701-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1701-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1701-07-01T11:59:59Z",
-    "author": [
-        "Krasicki, Ignacy (1735-1801)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-150201;2019-02-28T18:35:37Z;Opisanie Podro\u017cy Z Warszawy Do Bi\u0142goraia W Liscie Do Jasnie Oswieconego Xi\u0105\u017c\u0119cia Jmci Stanis\u0142awa Poniatowskiego;Krasicki, Ignacy (1735-1801);starodruki 18\u00a0w.;Drukarnia Nadworna Jego Kr\u00f3lewskiej Mo\u015bci i Komisji Edukacji Narodowej;[1782];starodruk;application/xml;clarind-uds:poldilemma-150201;hdl:11858/00-246C-0000-0023-8CE2-7;Biblioteka Jagiello\u0144ska, BJ St. Dr. 29970 I;pol;http://jbc.bj.uj.edu.pl/Content/150201;oai:jbc.bj.uj.edu.pl:publication:158450;1701/1800;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "decfcba7-f797-5b1b-afb8-f1fe634da4fb",
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-150201"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Opisanie Podro\u017cy Z Warszawy Do Bi\u0142goraia W Liscie Do Jasnie Oswieconego Xi\u0105\u017c\u0119cia Jmci Stanis\u0142awa Poniatowskiego"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/deea928e-4920-5a48-ab67-8729f44eb560.json b/oaitestdata/clarin-oai_dc/SET_1/json/deea928e-4920-5a48-ab67-8729f44eb560.json
deleted file mode 100644
index bcd78b00..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/deea928e-4920-5a48-ab67-8729f44eb560.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2645",
-    "MetadataAccess": [
-        "oai:ota:oucs:2645"
-    ],
-    "PublicationTimestamp": "1712-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1712"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2645;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2645.xml;A Letter of thanks from my Lord W*****n to the Lord Bp of S. Asaph, In the name of the Kit-Cat-Club;Swift, Jonathan, 1667-1745;1712;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "deea928e-4920-5a48-ab67-8729f44eb560",
-    "oai_identifier": [
-        "oai:ota:oucs:2645"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A Letter of thanks from my Lord W*****n to the Lord Bp of S. Asaph, In the name of the Kit-Cat-Club"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2645.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/df136b4a-fc8b-5d9f-b1b0-ef5a95e424d3.json b/oaitestdata/clarin-oai_dc/SET_1/json/df136b4a-fc8b-5d9f-b1b0-ef5a95e424d3.json
deleted file mode 100644
index 34b8b580..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/df136b4a-fc8b-5d9f-b1b0-ef5a95e424d3.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "C"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1459",
-    "MetadataAccess": [
-        "oai:ota:oucs:1459"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dictionaries, etc."
-    ],
-    "fulltext": "oai:ota:oucs:1459;2018-04-16T15:30:51Z;http://ota.ox.ac.uk/headers/1459.xml;Roget\"s Thesaurus;Dictionaries, etc.;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;C;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "df136b4a-fc8b-5d9f-b1b0-ef5a95e424d3",
-    "oai_identifier": [
-        "oai:ota:oucs:1459"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Roget\"s Thesaurus"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1459.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/df186de2-868c-5699-8517-0dc86d3e2e75.json b/oaitestdata/clarin-oai_dc/SET_1/json/df186de2-868c-5699-8517-0dc86d3e2e75.json
deleted file mode 100644
index 1e65071f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/df186de2-868c-5699-8517-0dc86d3e2e75.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Natural Language Processing Group, Computer Science Department, Istanbul Technical University"
-    ],
-    "Contributor": [
-        "Eryi\u011fit, G\u00fcl\u015fen"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Turkish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-712",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-712"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-712",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Natural Language Processing Group, Computer Science Department, Istanbul Technical University"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Turkey"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-712;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Turkish Natural Language Processing Pipeline;Eryi\u011fit, G\u00fcl\u015fen;the state of the art Turkish NLP tools: preprocessing/normalization for social media, morphology, syntax and entity recognition.;2015;toolService;http://hdl.handle.net/11372/LRT-712;tur;downloadable_files_count: 0;Turkey;Natural Language Processing Group, Computer Science Department, Istanbul Technical University;http://tools.nlp.itu.edu.tr/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "df186de2-868c-5699-8517-0dc86d3e2e75",
-    "notes": [
-        "the state of the art Turkish NLP tools: preprocessing/normalization for social media, morphology, syntax and entity recognition."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-712"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Turkish Natural Language Processing Pipeline"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/df1d737f-3886-5c15-b044-2d6db3869908.json b/oaitestdata/clarin-oai_dc/SET_1/json/df1d737f-3886-5c15-b044-2d6db3869908.json
deleted file mode 100644
index e432af48..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/df1d737f-3886-5c15-b044-2d6db3869908.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Indonesian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-CCD2-2",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-CCD2-2"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-CCD2-2",
-    "PublicationTimestamp": "2011-12-16T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Larasati, Septina Dian"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-CCD2-2;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;IDENTICv1.0-raw;Larasati, Septina Dian;Indonesian-English parallel corpus;parallel corpus;Raw Text;2011-12-16;corpus;http://hdl.handle.net/11858/00-097C-0000-0001-CCD2-2;ind;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "df1d737f-3886-5c15-b044-2d6db3869908",
-    "notes": [
-        "Raw Text"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-CCD2-2"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Indonesian-English parallel corpus"
-        },
-        {
-            "name": "parallel corpus"
-        }
-    ],
-    "title": [
-        "IDENTICv1.0-raw"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/df47bb05-a404-5833-8117-a4b79a44e384.json b/oaitestdata/clarin-oai_dc/SET_1/json/df47bb05-a404-5833-8117-a4b79a44e384.json
deleted file mode 100644
index 91773479..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/df47bb05-a404-5833-8117-a4b79a44e384.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish",
-        "Albanian",
-        "Bosnian",
-        "English",
-        "Finnish",
-        "Modern Greek (1453-)",
-        "Croatian",
-        "Kurdish",
-        "Russian",
-        "Serbian",
-        "Somali",
-        "Spanish",
-        "Turkish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/40",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/40"
-    ],
-    "PID": "http://hdl.handle.net/10794/40",
-    "PublicationTimestamp": "2012-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/40;2017-10-27T12:38:00Z;hdl_10794_1;hdl_10794_2;Swedish words, LEXIN;Svenska ord, LEXIN;n/a, n/a;Multilingual;Lexicon for immigrants. Second edition.;Lexikon f\u00f6r invandrare. Andra upplagan.;2012-05-30;lexicalConceptualResource;http://hdl.handle.net/10794/40;swe;sqi;bos;eng;fin;ell;hrv;Kur;pes;rus;srp;som;spa;tur;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/lexin",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "df47bb05-a404-5833-8117-a4b79a44e384",
-    "notes": [
-        "Lexicon for immigrants. Second edition.",
-        "Lexikon f\u00f6r invandrare. Andra upplagan."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/40"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Multilingual"
-        }
-    ],
-    "title": [
-        "Swedish words, LEXIN",
-        "Svenska ord, LEXIN"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/df4a8b15-35b0-5094-aac4-6f5e3938edea.json b/oaitestdata/clarin-oai_dc/SET_1/json/df4a8b15-35b0-5094-aac4-6f5e3938edea.json
deleted file mode 100644
index 313f5245..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/df4a8b15-35b0-5094-aac4-6f5e3938edea.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Lake, Kirsopp, 1872-1946"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(15 files : ca. 97, 29, 17, 10, 9, 10, 10, 11, 8, 15, 22, 60, 252, 25, 26 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0222",
-    "MetadataAccess": [
-        "oai:ota:oucs:0222"
-    ],
-    "PublicationYear": [
-        "1-199"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Patristic texts -- 1st-5th century period"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:0222;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0222.xml;Apostolic Fathers (Early Christian collection);The Apostolic Fathers;1-199;text_and_corpus_linguistics;grc;Oxford Text Archive, University of Oxford;Lake, Kirsopp, 1872-1946;text/plain;(15 files : ca. 97, 29, 17, 10, 9, 10, 10, 11, 8, 15, 22, 60, 252, 25, 26 KB);Text;Patristic texts -- 1st-5th century period;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "df4a8b15-35b0-5094-aac4-6f5e3938edea",
-    "oai_identifier": [
-        "oai:ota:oucs:0222"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Apostolic Fathers (Early Christian collection)",
-        "The Apostolic Fathers"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0222.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/df5623bd-e754-5732-a24f-db865012ee75.json b/oaitestdata/clarin-oai_dc/SET_1/json/df5623bd-e754-5732-a24f-db865012ee75.json
deleted file mode 100644
index 47092aef..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/df5623bd-e754-5732-a24f-db865012ee75.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Borin, Lars"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-421",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-421"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-421",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Sweden"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-421;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;The Swedish Parole corpus;Borin, Lars;mixed-genre (press, fiction, pop science, public information); appr. 19 MW; POS tags (in CWB format);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-421;swe;downloadable_files_count: 0;Sweden;http://spraakbanken.gu.se/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "df5623bd-e754-5732-a24f-db865012ee75",
-    "notes": [
-        "mixed-genre (press, fiction, pop science, public information); appr. 19 MW; POS tags (in CWB format)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-421"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "The Swedish Parole corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/df6ac73b-e3f2-5207-9356-14dc9500901c.json b/oaitestdata/clarin-oai_dc/SET_1/json/df6ac73b-e3f2-5207-9356-14dc9500901c.json
deleted file mode 100644
index 9947e2bc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/df6ac73b-e3f2-5207-9356-14dc9500901c.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Institute of Slavic Studies, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 136",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish",
-        "Lithuanian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/309",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/309"
-    ],
-    "PID": "http://hdl.handle.net/11321/309",
-    "PublicationTimestamp": "2016-06-07T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Institute of Slavic Studies, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "IS PAS corpora license",
-        "http://clarin-pl.eu/en/licenses/is-pas-corpora-license/",
-        "CC"
-    ],
-    "author": [
-        "Roszko, Danuta",
-        "Roszko, Roman"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/309;2016-06-07T14:35:06Z;hdl_11321_3;hdl_11321_4;Polish-Lithuanian Parallel Corpus;Roszko, Danuta;Roszko, Roman;Polish;Lithuanian;corpora;Database;2016-06-07;corpus;http://hdl.handle.net/11321/309;pol;lit;IS PAS corpora license;http://clarin-pl.eu/en/licenses/is-pas-corpora-license/;CC;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 136;Institute of Slavic Studies, Polish Academy of Sciences",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "df6ac73b-e3f2-5207-9356-14dc9500901c",
-    "notes": [
-        "Database"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/309"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Polish"
-        },
-        {
-            "name": "Lithuanian"
-        },
-        {
-            "name": "corpora"
-        }
-    ],
-    "title": [
-        "Polish-Lithuanian Parallel Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/df6eb6e6-f6d9-5b71-89c4-3c528ed1711a.json b/oaitestdata/clarin-oai_dc/SET_1/json/df6eb6e6-f6d9-5b71-89c4-3c528ed1711a.json
deleted file mode 100644
index e16d92e2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/df6eb6e6-f6d9-5b71-89c4-3c528ed1711a.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4914-D",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4914-D"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-4914-D",
-    "PublicationTimestamp": "2009-11-02T10:40:55Z",
-    "PublicationYear": [
-        "2009"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "PDTSL",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-pdtsl",
-        "ACA"
-    ],
-    "author": [
-        "Mikulov\u00e1, Marie",
-        "Haji\u010d, Jan",
-        "Ure\u0161ov\u00e1, Zde\u0148ka",
-        "Podvesk\u00fd, Petr",
-        "Pajas, Petr",
-        "Mare\u010dek, David"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4914-D;2017-11-09T14:20:35Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Prague Dependency Treebank of Spoken Language (PDTSL) 0.5;Haji\u010d, Jan;Pajas, Petr;Mare\u010dek, David;Mikulov\u00e1, Marie;Ure\u0161ov\u00e1, Zde\u0148ka;Podvesk\u00fd, Petr;corpus;spoken language;The first edition of a speech corpus with a speech reconstruction layer (edited transcript).\r\n\r\nThe project of speech reconstruction of Czech and English has been started at UFAL together with the PIRE project in 2005, and has gradually grown from ideas to (first) annotation specification, annotation software and actual annotation. It is part of the Prague Dependency Treebank family of annotated corpus resources and tools, to which it adds the spoken language layer(s).;2009-11-02T10:40:55Z;corpus;http://hdl.handle.net/11858/00-097C-0000-0001-4914-D;ces;eng;PDTSL;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-pdtsl;ACA;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/pdtsl",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "df6eb6e6-f6d9-5b71-89c4-3c528ed1711a",
-    "notes": [
-        "The first edition of a speech corpus with a speech reconstruction layer (edited transcript).\r\n\r\nThe project of speech reconstruction of Czech and English has been started at UFAL together with the PIRE project in 2005, and has gradually grown from ideas to (first) annotation specification, annotation software and actual annotation. It is part of the Prague Dependency Treebank family of annotated corpus resources and tools, to which it adds the spoken language layer(s)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4914-D"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "spoken language"
-        }
-    ],
-    "title": [
-        "Prague Dependency Treebank of Spoken Language (PDTSL) 0.5"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/df7beaef-2237-50d4-9ad3-b26735b698bf.json b/oaitestdata/clarin-oai_dc/SET_1/json/df7beaef-2237-50d4-9ad3-b26735b698bf.json
deleted file mode 100644
index f5ca880f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/df7beaef-2237-50d4-9ad3-b26735b698bf.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Formal Linguistics Department of Warsaw University"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "image/png",
-        "downloadable_files_count: 2",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "En"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/468",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/468"
-    ],
-    "PID": "http://hdl.handle.net/11321/468",
-    "PublicationTimestamp": "2015-04-14T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Formal Linguistics Department of Warsaw University"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "Bie\u0144, Janusz S."
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/468;2018-05-16T10:03:48Z;hdl_11321_3;hdl_11321_4;Poliqarp for DjVu  -a demonstration (open Virtual Appliance);Bie\u0144, Janusz S.;corpus scans DjVu;a server for DjVu corpora;2015-04-14;toolService;http://hdl.handle.net/11321/468;en,pl;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;image/png;application/octet-stream;downloadable_files_count: 2;Formal Linguistics Department of Warsaw University;https://bitbucket.org/jsbien/ndt",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "df7beaef-2237-50d4-9ad3-b26735b698bf",
-    "notes": [
-        "a server for DjVu corpora"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/468"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus scans DjVu"
-        }
-    ],
-    "title": [
-        "Poliqarp for DjVu  -a demonstration (open Virtual Appliance)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/df95f2af-fcea-5fa7-a268-b6b61b09bb92.json b/oaitestdata/clarin-oai_dc/SET_1/json/df95f2af-fcea-5fa7-a268-b6b61b09bb92.json
deleted file mode 100644
index 51c07c8d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/df95f2af-fcea-5fa7-a268-b6b61b09bb92.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Prof. R. A. Lodge",
-        "Lodge, R. Anthony",
-        "Leverhulme Trust"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 900 KB)"
-    ],
-    "Language": [
-        "Middle French (ca. 1400-1600)",
-        "French"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2423",
-    "MetadataAccess": [
-        "oai:ota:oucs:2423"
-    ],
-    "PublicationTimestamp": "2000-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Linguistic corpora"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:2423;2018-02-21T11:37:02Z;http://ota.ox.ac.uk/headers/2423.xml;Paris speech in the past;2000-07;text_and_corpus_linguistics;Electronic publications -- Great Britain -- 20th century;Corpora -- Great Britain -- 20th century;Linguistic corpora -- Great Britain -- 20th century;frm;fra;A collection of semi-literary representations of vernacular (French) speech from the 16th to 19th centuries which is preceeded by a set of tax-rolls from late 17th century Paris ;Oxford Text Archive, University of Oxford;Lodge, R. Anthony;Leverhulme Trust;Prof. R. A. Lodge;text/sgml;(1 file : ca. 900 KB);Text;Linguistic corpora;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "df95f2af-fcea-5fa7-a268-b6b61b09bb92",
-    "notes": [
-        "A collection of semi-literary representations of vernacular (French) speech from the 16th to 19th centuries which is preceeded by a set of tax-rolls from late 17th century Paris "
-    ],
-    "oai_identifier": [
-        "oai:ota:oucs:2423"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Electronic publications -- Great Britain -- th century"
-        },
-        {
-            "name": "Corpora -- Great Britain -- th century"
-        },
-        {
-            "name": "Linguistic corpora -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Paris speech in the past"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2423.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dfba005e-a58a-5ef3-aa6f-27f2e3fa9b0b.json b/oaitestdata/clarin-oai_dc/SET_1/json/dfba005e-a58a-5ef3-aa6f-27f2e3fa9b0b.json
deleted file mode 100644
index 78bcf090..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dfba005e-a58a-5ef3-aa6f-27f2e3fa9b0b.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 93.8 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0608",
-    "MetadataAccess": [
-        "oai:ota:oucs:0608"
-    ],
-    "PublicationTimestamp": "1633-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1633"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Rowley, William, 1585?-1642?"
-    ],
-    "fulltext": "oai:ota:oucs:0608;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0608.xml;All's lost by lust;Rowley, William, 1585?-1642?;1633;text_and_corpus_linguistics;Plays -- England -- 17th century;Tragedies -- England -- 17th century;eng;Oxford Text Archive, University of Oxford;(1 file : ca. 93.8 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dfba005e-a58a-5ef3-aa6f-27f2e3fa9b0b",
-    "oai_identifier": [
-        "oai:ota:oucs:0608"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        },
-        {
-            "name": "Tragedies -- England -- th century"
-        }
-    ],
-    "title": [
-        "All's lost by lust"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0608.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dfc1a42c-4eae-54a1-9a1e-d9315041ff34.json b/oaitestdata/clarin-oai_dc/SET_1/json/dfc1a42c-4eae-54a1-9a1e-d9315041ff34.json
deleted file mode 100644
index 3fd6bc5b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dfc1a42c-4eae-54a1-9a1e-d9315041ff34.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3475",
-    "MetadataAccess": [
-        "oai:ota:oucs:3475"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Mendez, Moses, d. 1758."
-    ],
-    "fulltext": "oai:ota:oucs:3475;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3475.xml;The seasons. In imitation of Spenser;Mendez, Moses, d. 1758.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dfc1a42c-4eae-54a1-9a1e-d9315041ff34",
-    "oai_identifier": [
-        "oai:ota:oucs:3475"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The seasons. In imitation of Spenser"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3475.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dfcb291d-4446-50ec-ae59-c3ee477c3b1c.json b/oaitestdata/clarin-oai_dc/SET_1/json/dfcb291d-4446-50ec-ae59-c3ee477c3b1c.json
deleted file mode 100644
index d9aa0310..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dfcb291d-4446-50ec-ae59-c3ee477c3b1c.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "Contributor": [
-        "Gippert, Jost"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-967",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-967"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-967",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-967;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Old Frisian;Gippert, Jost;ca. 60.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-967;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#afries",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dfcb291d-4446-50ec-ae59-c3ee477c3b1c",
-    "notes": [
-        "ca. 60.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-967"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Old Frisian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dfe03246-6792-5790-bfeb-91cf61f4b20d.json b/oaitestdata/clarin-oai_dc/SET_1/json/dfe03246-6792-5790-bfeb-91cf61f4b20d.json
deleted file mode 100644
index e8174f1b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dfe03246-6792-5790-bfeb-91cf61f4b20d.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5215",
-    "MetadataAccess": [
-        "oai:ota:oucs:5215"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Sharp, Granville, 1735-1813."
-    ],
-    "fulltext": "oai:ota:oucs:5215;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5215.xml;The law of passive obedience: or Christian submission to personal injuries: ... By Granville Sharp.;Sharp, Granville, 1735-1813.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dfe03246-6792-5790-bfeb-91cf61f4b20d",
-    "oai_identifier": [
-        "oai:ota:oucs:5215"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The law of passive obedience: or Christian submission to personal injuries: ... By Granville Sharp."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5215.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dfe328dc-ae8d-5ca2-bef4-7e30e5270270.json b/oaitestdata/clarin-oai_dc/SET_1/json/dfe328dc-ae8d-5ca2-bef4-7e30e5270270.json
deleted file mode 100644
index d196bdcc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dfe328dc-ae8d-5ca2-bef4-7e30e5270270.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3654",
-    "MetadataAccess": [
-        "oai:ota:oucs:3654"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pope, Alexander, 1688-1744."
-    ],
-    "fulltext": "oai:ota:oucs:3654;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3654.xml;Epistles to several persons;Pope, Alexander, 1688-1744.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dfe328dc-ae8d-5ca2-bef4-7e30e5270270",
-    "oai_identifier": [
-        "oai:ota:oucs:3654"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Epistles to several persons"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3654.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dff1ff9f-b0e3-55e1-baf1-55e3c8fd61d8.json b/oaitestdata/clarin-oai_dc/SET_1/json/dff1ff9f-b0e3-55e1-baf1-55e3c8fd61d8.json
deleted file mode 100644
index 53d3c5a9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dff1ff9f-b0e3-55e1-baf1-55e3c8fd61d8.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3722",
-    "MetadataAccess": [
-        "oai:ota:oucs:3722"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Paine, Thomas, 1737-1809."
-    ],
-    "fulltext": "oai:ota:oucs:3722;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3722.xml;Thoughts on the peace, and the probable advantages thereof to the United States of America: By Thomas Paine, ...;Paine, Thomas, 1737-1809.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dff1ff9f-b0e3-55e1-baf1-55e3c8fd61d8",
-    "oai_identifier": [
-        "oai:ota:oucs:3722"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Thoughts on the peace, and the probable advantages thereof to the United States of America: By Thomas Paine, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3722.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/dffde549-26ba-514d-8ec0-48c5f4c25508.json b/oaitestdata/clarin-oai_dc/SET_1/json/dffde549-26ba-514d-8ec0-48c5f4c25508.json
deleted file mode 100644
index 981249a3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/dffde549-26ba-514d-8ec0-48c5f4c25508.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5129",
-    "MetadataAccess": [
-        "oai:ota:oucs:5129"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Sterne, Laurence, 1713-1768."
-    ],
-    "fulltext": "oai:ota:oucs:5129;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5129.xml;Yorick's meditations: upon various interesting and important subjects. Viz. Upon nothing. Upon something. Upon the thing. ...;Sterne, Laurence, 1713-1768.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dffde549-26ba-514d-8ec0-48c5f4c25508",
-    "oai_identifier": [
-        "oai:ota:oucs:5129"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Yorick's meditations: upon various interesting and important subjects. Viz. Upon nothing. Upon something. Upon the thing. ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5129.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e0046e9b-80b6-5c5d-b6d3-dae66bce7316.json b/oaitestdata/clarin-oai_dc/SET_1/json/e0046e9b-80b6-5c5d-b6d3-dae66bce7316.json
deleted file mode 100644
index 0ef1d5b3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e0046e9b-80b6-5c5d-b6d3-dae66bce7316.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-653",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-653"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-653",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Code of conduct"
-    ],
-    "SpatialCoverage": [
-        "Brazil"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-653;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Kuikuro;Documentation of the kuikuro project (DoBeS project);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-653;Code of conduct;downloadable_files_count: 0;Brazil;http://corpus1.mpi.nl/ds/imdi_browser/?openpath=MPI79774%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e0046e9b-80b6-5c5d-b6d3-dae66bce7316",
-    "notes": [
-        "Documentation of the kuikuro project (DoBeS project)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-653"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Kuikuro"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e017e37f-bc4c-5bf8-93d6-2a507d7a8c56.json b/oaitestdata/clarin-oai_dc/SET_1/json/e017e37f-bc4c-5bf8-93d6-2a507d7a8c56.json
deleted file mode 100644
index f1a5f91e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e017e37f-bc4c-5bf8-93d6-2a507d7a8c56.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 7",
-        "application/pdf",
-        "text/plain"
-    ],
-    "Language": [
-        "Arabic"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-94",
-    "MetadataAccess": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-94"
-    ],
-    "PID": "http://hdl.handle.net/20.500.11752/ILC-94",
-    "PublicationTimestamp": "2018-09-28T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "RelatedIdentifier": [
-        "http://www.aaccademia.it/scheda-libro?aaref=63"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "Rights": [
-        "GNU General Public License, version 2",
-        "http://www.gnu.org/licenses/gpl-2.0.html",
-        "PUB"
-    ],
-    "author": [
-        "Nahli, Ouafae"
-    ],
-    "fulltext": "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-94;2018-10-18T08:42:41Z;hdl_000-c0-111_38;hdl_000-c0-111_49;AraMorph Data Plus;Nahli, Ouafae;Aramorph;Arabic-English lexicon files;Morphology;The AraMorph's original engine (https://sourceforge.net/projects/aramorph/files/aramorph/1.2.1) uses six linguistic files. Three Arabic-English lexicon files: prefixes (299 entries), suffixes (618 entries), and stems (82158 entries representing 38600 lemmas). Other three files consist of morphological compatibility tables used for controlling prefix-stem combinations (1648 entries), stem-suffix combinations (1285 entries), and prefix-suffix combinations (598 entries).\r\nThe present data consists of the updated lexical resources used by the Aramorph' engine. The updates take advantage of a number of orthographic, morpho-syntactic and semantic constraints that operate at the word level. Therefore, the Arabic-English lexicon files contain: prefixes (335 entries), suffixes (876 entries), and stems (35475 entries). Note that the number of stems is smaller in Plus than in Original, due to the removal of obsolete entries and of a number of foreign names that are unlikely to be found in Arabic texts. The morphological compatibility tables used for controlling prefix-stem combinations (2698 entries), stem-suffix combinations (2161 entries), and prefix-suffix combinations (1295 entries).;2018-09-28;languageDescription;http://hdl.handle.net/20.500.11752/ILC-94;ara;http://www.aaccademia.it/scheda-libro?aaref=63;GNU General Public License, version 2;http://www.gnu.org/licenses/gpl-2.0.html;PUB;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;application/pdf;text/plain; charset=utf-8;downloadable_files_count: 7;Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e017e37f-bc4c-5bf8-93d6-2a507d7a8c56",
-    "notes": [
-        "The AraMorph's original engine (https://sourceforge.net/projects/aramorph/files/aramorph/1.2.1) uses six linguistic files. Three Arabic-English lexicon files: prefixes (299 entries), suffixes (618 entries), and stems (82158 entries representing 38600 lemmas). Other three files consist of morphological compatibility tables used for controlling prefix-stem combinations (1648 entries), stem-suffix combinations (1285 entries), and prefix-suffix combinations (598 entries).\r\nThe present data consists of the updated lexical resources used by the Aramorph' engine. The updates take advantage of a number of orthographic, morpho-syntactic and semantic constraints that operate at the word level. Therefore, the Arabic-English lexicon files contain: prefixes (335 entries), suffixes (876 entries), and stems (35475 entries). Note that the number of stems is smaller in Plus than in Original, due to the removal of obsolete entries and of a number of foreign names that are unlikely to be found in Arabic texts. The morphological compatibility tables used for controlling prefix-stem combinations (2698 entries), stem-suffix combinations (2161 entries), and prefix-suffix combinations (1295 entries)."
-    ],
-    "oai_identifier": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-94"
-    ],
-    "oai_set": [
-        "hdl_000-c0-111_38",
-        "hdl_000-c0-111_49"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Aramorph"
-        },
-        {
-            "name": "Arabic-English lexicon files"
-        },
-        {
-            "name": "Morphology"
-        }
-    ],
-    "title": [
-        "AraMorph Data Plus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e030b20e-3c94-5c4f-9d6a-c74bd153476e.json b/oaitestdata/clarin-oai_dc/SET_1/json/e030b20e-3c94-5c4f-9d6a-c74bd153476e.json
deleted file mode 100644
index 8fcb75f9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e030b20e-3c94-5c4f-9d6a-c74bd153476e.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "University of Stuttgart"
-    ],
-    "Contributor": [
-        "Schmid, Helmut"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Bulgarian",
-        "Dutch",
-        "English",
-        "French",
-        "German",
-        "Modern Greek (1453-)",
-        "Italian",
-        "Portuguese",
-        "Russian",
-        "Spanish",
-        "Swahili (macrolanguage)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-323",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-323"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-323",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Stuttgart"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-323;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TreeTagger;Schmid, Helmut;POS tagger;A part-of-speech tagger and lemmatizer for several languages.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-323;bul;nld;eng;fra;deu;ell;ita;por;rus;spa;swa;downloadable_files_count: 0;Germany;University of Stuttgart;http://www.ims.uni-stuttgart.de/projekte/corplex/TreeTagger/DecisionTreeTagger.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e030b20e-3c94-5c4f-9d6a-c74bd153476e",
-    "notes": [
-        "A part-of-speech tagger and lemmatizer for several languages."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-323"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "POS tagger"
-        }
-    ],
-    "title": [
-        "TreeTagger"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e034d129-4c39-5054-8db0-67e6a0197817.json b/oaitestdata/clarin-oai_dc/SET_1/json/e034d129-4c39-5054-8db0-67e6a0197817.json
deleted file mode 100644
index a4340c59..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e034d129-4c39-5054-8db0-67e6a0197817.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Universitat de Barcelona"
-    ],
-    "Contributor": [
-        "Castell\u00f3n, Irene"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Catalan",
-        "English",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1116",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1116"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1116",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Universitat de Barcelona"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1116;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Dependency Grammars;Castell\u00f3n, Irene;dependency grammar;Dependency grammars;2014-07-30;languageDescription;http://hdl.handle.net/11372/LRT-1116;cat;eng;spa;downloadable_files_count: 0;Spain;Universitat de Barcelona;http://grial.uab.es/recursos.php",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e034d129-4c39-5054-8db0-67e6a0197817",
-    "notes": [
-        "Dependency grammars"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1116"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "dependency grammar"
-        }
-    ],
-    "title": [
-        "Dependency Grammars"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e0369e1f-ecb3-588b-ab70-f7a7675b0077.json b/oaitestdata/clarin-oai_dc/SET_1/json/e0369e1f-ecb3-588b-ab70-f7a7675b0077.json
deleted file mode 100644
index 5c041a15..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e0369e1f-ecb3-588b-ab70-f7a7675b0077.json
+++ /dev/null
@@ -1,124 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/x-tar",
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Arabic",
-        "Bulgarian",
-        "Bengali",
-        "Catalan",
-        "Czech",
-        "Danish",
-        "German",
-        "Modern Greek (1453-)",
-        "English",
-        "Spanish",
-        "Estonian",
-        "Basque",
-        "Persian",
-        "Finnish",
-        "Ancient Greek (to 1453)",
-        "Hindi",
-        "Hungarian",
-        "Italian",
-        "Japanese",
-        "Latin",
-        "Dutch",
-        "Portuguese",
-        "Romanian",
-        "Russian",
-        "Slovak",
-        "Slovenian",
-        "Swedish",
-        "Tamil",
-        "Telugu",
-        "Turkish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-9551-4",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-9551-4"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-9551-4",
-    "PublicationTimestamp": "2014-05-24T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-1508"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "HamleDT 1.0  Licence Agreement",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-hamledt",
-        "ACA"
-    ],
-    "author": [
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "Popel, Martin",
-        "Ramasamy, Loganathan",
-        "\u0160t\u011bp\u00e1nek, Jan",
-        "Ma\u0161ek, Jan",
-        "Zeman, Daniel",
-        "Rosa, Rudolf",
-        "Mare\u010dek, David"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-9551-4;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;HamleDT 2.0;Zeman, Daniel;Mare\u010dek, David;Ma\u0161ek, Jan;Popel, Martin;Ramasamy, Loganathan;Rosa, Rudolf;\u0160t\u011bp\u00e1nek, Jan;\u017dabokrtsk\u00fd, Zden\u011bk;treebank;Stanford dependencies;Prague dependencies;harmonization;common annotation style;Interset;HamleDT 2.0 is a collection of 30 existing treebanks harmonized into a common annotation style, the Prague Dependencies, and further transformed into Stanford Dependencies, a treebank annotation style that became popular recently. We use the newest basic Universal Stanford Dependencies, without added language-specific subtypes.;2014-05-24;corpus;http://hdl.handle.net/11858/00-097C-0000-0023-9551-4;ara;bul;ben;cat;ces;dan;deu;ell;eng;spa;est;eus;fas;fin;grc;hin;hun;ita;jpn;lat;nld;por;ron;rus;slk;slv;swe;tam;tel;tur;http://hdl.handle.net/11234/1-1508;HamleDT 1.0  Licence Agreement;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-hamledt;ACA;text/plain; charset=utf-8;application/x-tar;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/hamledt",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e0369e1f-ecb3-588b-ab70-f7a7675b0077",
-    "notes": [
-        "HamleDT 2.0 is a collection of 30 existing treebanks harmonized into a common annotation style, the Prague Dependencies, and further transformed into Stanford Dependencies, a treebank annotation style that became popular recently. We use the newest basic Universal Stanford Dependencies, without added language-specific subtypes."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-9551-4"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "Stanford dependencies"
-        },
-        {
-            "name": "Prague dependencies"
-        },
-        {
-            "name": "harmonization"
-        },
-        {
-            "name": "common annotation style"
-        },
-        {
-            "name": "Interset"
-        }
-    ],
-    "title": [
-        "HamleDT 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e0388a78-7352-524b-9cb0-6090922e2c10.json b/oaitestdata/clarin-oai_dc/SET_1/json/e0388a78-7352-524b-9cb0-6090922e2c10.json
deleted file mode 100644
index e686dd7e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e0388a78-7352-524b-9cb0-6090922e2c10.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3725",
-    "MetadataAccess": [
-        "oai:ota:oucs:3725"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Paine, Thomas, 1737-1809."
-    ],
-    "fulltext": "oai:ota:oucs:3725;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3725.xml;The whole proceedings on the trial of an information exhibited ex officio by the King's Attorney-General against Thomas Paine: for a libel upon the Revolution and settlement of the Crown and regal government as by law established; ... Tried by a special jury in the Court of King's Bench, Guildhall, on Tuesday, the 18th of December, 1792. ... Taken in short-hand by Joseph Gurney.;Paine, Thomas, 1737-1809.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e0388a78-7352-524b-9cb0-6090922e2c10",
-    "oai_identifier": [
-        "oai:ota:oucs:3725"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The whole proceedings on the trial of an information exhibited ex officio by the King's Attorney-General against Thomas Paine: for a libel upon the Revolution and settlement of the Crown and regal government as by law established; ... Tried by a special jury in the Court of King's Bench, Guildhall, on Tuesday, the 18th of December, 1792. ... Taken in short-hand by Joseph Gurney."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3725.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e04ab04b-6f0c-571f-8667-aa01d7c073e7.json b/oaitestdata/clarin-oai_dc/SET_1/json/e04ab04b-6f0c-571f-8667-aa01d7c073e7.json
deleted file mode 100644
index 69a3a1b7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e04ab04b-6f0c-571f-8667-aa01d7c073e7.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Arts and Humanities Research Board (AHRB)",
-        "British Academy",
-        "Modern Humanities Research Association",
-        "Magner, Carol",
-        "Yeandle, David N."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : tbc)"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2459",
-    "MetadataAccess": [
-        "oai:ota:oucs:2459"
-    ],
-    "PublicationTimestamp": "2002-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2002"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Myths and legends--13th century"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Eschenbach, Wolfram von, 12th century"
-    ],
-    "fulltext": "oai:ota:oucs:2459;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/2459.xml;Stellenbibliographie zum \"Parzifal\" Wolframs von Eschenbach f\u00c3\u00bcr die Jahrg\u00c3\u00a4nge 1984-1996;Eschenbach, Wolfram von, 12th century;2002;text_and_corpus_linguistics;German literature--Bibliography;German literature--Middle High German, 1050-1500;deu;This database provides the complete text of the Middle High German Arthurian Romance Parzival by Wolfram von Eschenbach (ca. 1200-1210), together with a complete bibliography of literature referring to individual lines of his work for the period 1984-1996. Future editions will increase the period covered. The text of Parzival is accompanied by line-by-line bibliographical references. These are groups thematically and thereafter chronologically. From this display, hyperlinks lead to full bibliographical details of works and to a complete listing of individual topics. From the main index, there are links to the following additional indices: topics (enabling hierarchical and alphabetic thematic searching), authors (where all line references are grouped thematically for a given author's work), words in secondary literature titles (enabling specific searches for individual concepts), work types (enabling the user to search e.g.for books, articles, translations, commentaries), work languages (enabling the user to search e.g. just for works in English), and work dates (enabling the user to refine the search for a specific year or years). In every index, extensive hyperlinks lead the user to further related information. Extensive online help is available at every point. ;Oxford Text Archive, University of Oxford;Yeandle, David N.;Magner, Carol;Arts and Humanities Research Board (AHRB);British Academy;Modern Humanities Research Association;Yeandle, David N.;(1 file : tbc);Text;Myths and legends--13th century;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e04ab04b-6f0c-571f-8667-aa01d7c073e7",
-    "notes": [
-        "This database provides the complete text of the Middle High German Arthurian Romance Parzival by Wolfram von Eschenbach (ca. 1200-1210), together with a complete bibliography of literature referring to individual lines of his work for the period 1984-1996. Future editions will increase the period covered. The text of Parzival is accompanied by line-by-line bibliographical references. These are groups thematically and thereafter chronologically. From this display, hyperlinks lead to full bibliographical details of works and to a complete listing of individual topics. From the main index, there are links to the following additional indices: topics (enabling hierarchical and alphabetic thematic searching), authors (where all line references are grouped thematically for a given author's work), words in secondary literature titles (enabling specific searches for individual concepts), work types (enabling the user to search e.g.for books, articles, translations, commentaries), work languages (enabling the user to search e.g. just for works in English), and work dates (enabling the user to refine the search for a specific year or years). In every index, extensive hyperlinks lead the user to further related information. Extensive online help is available at every point. "
-    ],
-    "oai_identifier": [
-        "oai:ota:oucs:2459"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "German literature--Bibliography"
-        },
-        {
-            "name": "German literature--Middle High German"
-        }
-    ],
-    "title": [
-        "Stellenbibliographie zum \"Parzifal\" Wolframs von Eschenbach f\u00c3\u00bcr die Jahrg\u00c3\u00a4nge 1984-1996"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2459.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e04eea71-467a-5b65-9fed-5cb95c9185f9.json b/oaitestdata/clarin-oai_dc/SET_1/json/e04eea71-467a-5b65-9fed-5cb95c9185f9.json
deleted file mode 100644
index 3124062d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e04eea71-467a-5b65-9fed-5cb95c9185f9.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Ewa Dulna-Rak"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "text/richtext",
-        "downloadable_files_count: 3",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/219",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/219"
-    ],
-    "PID": "http://hdl.handle.net/11321/219",
-    "PublicationTimestamp": "2015-06-18T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Ewa Dulna-Rak"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Ewa Dulna-Rak"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/219;2015-06-18T09:41:28Z;hdl_11321_3;hdl_11321_4;korpo;Ewa Dulna-Rak;teatr;2015-06-18;corpus;http://hdl.handle.net/11321/219;PL;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/richtext;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 3;Ewa Dulna-Rak",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e04eea71-467a-5b65-9fed-5cb95c9185f9",
-    "notes": [
-        "teatr"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/219"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "korpo"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e0512501-9343-5700-b395-9ddf938ae9c4.json b/oaitestdata/clarin-oai_dc/SET_1/json/e0512501-9343-5700-b395-9ddf938ae9c4.json
deleted file mode 100644
index 076460cb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e0512501-9343-5700-b395-9ddf938ae9c4.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5111",
-    "MetadataAccess": [
-        "oai:ota:oucs:5111"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Jerningham, Mr. (Edward), 1737?-1812."
-    ],
-    "fulltext": "oai:ota:oucs:5111;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5111.xml;The Peckham frolic: or Nell Gwyn. A comedy: in three acts.;Jerningham, Mr. (Edward), 1737?-1812.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e0512501-9343-5700-b395-9ddf938ae9c4",
-    "oai_identifier": [
-        "oai:ota:oucs:5111"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The Peckham frolic: or Nell Gwyn. A comedy: in three acts."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5111.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e07a466e-6b63-5d43-9cc8-223cd178563e.json b/oaitestdata/clarin-oai_dc/SET_1/json/e07a466e-6b63-5d43-9cc8-223cd178563e.json
deleted file mode 100644
index cc3e77b2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e07a466e-6b63-5d43-9cc8-223cd178563e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3441",
-    "MetadataAccess": [
-        "oai:ota:oucs:3441"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Late Member of the Continental Congress."
-    ],
-    "fulltext": "oai:ota:oucs:3441;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3441.xml;The true merits of a late treatise, printed in America, intitled, Common sense: clearly pointed out. Addressed to the inhabitants of America. By a late member of the Continental Congress, a native of a republican state.;Late Member of the Continental Congress.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e07a466e-6b63-5d43-9cc8-223cd178563e",
-    "oai_identifier": [
-        "oai:ota:oucs:3441"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The true merits of a late treatise, printed in America, intitled, Common sense: clearly pointed out. Addressed to the inhabitants of America. By a late member of the Continental Congress, a native of a republican state."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3441.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e0a87849-d8b3-5a5c-81b3-f08171428814.json b/oaitestdata/clarin-oai_dc/SET_1/json/e0a87849-d8b3-5a5c-81b3-f08171428814.json
deleted file mode 100644
index d977dcc3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e0a87849-d8b3-5a5c-81b3-f08171428814.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/22",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/22"
-    ],
-    "PID": "http://hdl.handle.net/10794/22",
-    "PublicationTimestamp": "2012-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/22;2017-10-27T15:30:01Z;hdl_10794_1;hdl_10794_2;Dalin's morphology (2017-10-16);Dalins morfologi (2017-10-16);n/a, n/a;Swedish;Dictionary;Morphology;A morphology from Dalin's Dictionary of 19th century Swedish.;En morfologi fr\u00e5n Dalins ordbok - Ordbok \u00f6ver 1800-talsspr\u00e5ket.;2012-05-30;lexicalConceptualResource;http://hdl.handle.net/10794/22;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/dalinm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e0a87849-d8b3-5a5c-81b3-f08171428814",
-    "notes": [
-        "A morphology from Dalin's Dictionary of 19th century Swedish.",
-        "En morfologi fr\u00e5n Dalins ordbok - Ordbok \u00f6ver 1800-talsspr\u00e5ket."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/22"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Dictionary"
-        },
-        {
-            "name": "Morphology"
-        }
-    ],
-    "title": [
-        "Dalin's morphology (2017-10-16)",
-        "Dalins morfologi (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e0cf701b-8b67-56b7-906d-8243bd6d3b5a.json b/oaitestdata/clarin-oai_dc/SET_1/json/e0cf701b-8b67-56b7-906d-8243bd6d3b5a.json
deleted file mode 100644
index c029fd58..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e0cf701b-8b67-56b7-906d-8243bd6d3b5a.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Arts, Institute of the Czech National Corpus, Charles University in Prague"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-1358-3",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-1358-3"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-1358-3",
-    "PublicationTimestamp": "2006-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2006"
-    ],
-    "Publisher": [
-        "Faculty of Arts, Institute of the Czech National Corpus, Charles University in Prague"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Czech National Corpus (Shuffled Corpus Data)",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/license-cnc",
-        "ACA"
-    ],
-    "author": [
-        "Hn\u00e1tkov\u00e1, Milena",
-        "Kop\u0159ivov\u00e1, Marie",
-        "Petkevi\u010d, Vladim\u00edr",
-        "Kocek, Jan",
-        "Spoustov\u00e1, Johanka",
-        "\u010cerm\u00e1k, Franti\u0161ek",
-        "Hlav\u00e1\u010dov\u00e1, Jaroslava",
-        "Vel\u00ed\u0161ek, Zden\u011bk",
-        "Schmiedtov\u00e1, V\u011bra",
-        "K\u0159en, Michal",
-        "Jel\u00ednek, Tom\u00e1\u0161",
-        "Novotn\u00e1, Renata",
-        "Skoumalov\u00e1, Hana",
-        "\u0160ulc, Michal"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-1358-3;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;SYN2006PUB: corpus of Czech newspapers;\u010cerm\u00e1k, Franti\u0161ek;Hlav\u00e1\u010dov\u00e1, Jaroslava;Hn\u00e1tkov\u00e1, Milena;Jel\u00ednek, Tom\u00e1\u0161;Kocek, Jan;Kop\u0159ivov\u00e1, Marie;K\u0159en, Michal;Novotn\u00e1, Renata;Petkevi\u010d, Vladim\u00edr;Schmiedtov\u00e1, V\u011bra;Skoumalov\u00e1, Hana;Spoustov\u00e1, Johanka;\u0160ulc, Michal;Vel\u00ed\u0161ek, Zden\u011bk;corpus;written language;Corpus of contemporary Czech newspapers and magazines sized 300 MW. It contains various titles published between the end of 1989 and 2004. The corpus is lemmatized and morphologically tagged by a combination of stochastic and rule-based methods.\r\nThe corpus is provided in a (semi-XML) vertical format used as an input to the Manatee query engine. The data thus correspond to the corpus available via query interface to registered users of the CNC with one important exception: they are shuffled, i.e. divided into blocks sized max. 100 words (respecting the sentence boundaries) whose ordering was randomized within the given document.;2006;corpus;http://hdl.handle.net/11858/00-097C-0000-0023-1358-3;ces;Czech National Corpus (Shuffled Corpus Data);https://lindat.mff.cuni.cz/repository/xmlui/page/license-cnc;ACA;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Faculty of Arts, Institute of the Czech National Corpus, Charles University in Prague;https://wiki.korpus.cz/doku.php/cnk:syn2006pub",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e0cf701b-8b67-56b7-906d-8243bd6d3b5a",
-    "notes": [
-        "Corpus of contemporary Czech newspapers and magazines sized 300 MW. It contains various titles published between the end of 1989 and 2004. The corpus is lemmatized and morphologically tagged by a combination of stochastic and rule-based methods.\r\nThe corpus is provided in a (semi-XML) vertical format used as an input to the Manatee query engine. The data thus correspond to the corpus available via query interface to registered users of the CNC with one important exception: they are shuffled, i.e. divided into blocks sized max. 100 words (respecting the sentence boundaries) whose ordering was randomized within the given document."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-1358-3"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "written language"
-        }
-    ],
-    "title": [
-        "SYN2006PUB: corpus of Czech newspapers"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e0d086a9-990e-52b0-adf4-e97bd17ecf60.json b/oaitestdata/clarin-oai_dc/SET_1/json/e0d086a9-990e-52b0-adf4-e97bd17ecf60.json
deleted file mode 100644
index 5a794431..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e0d086a9-990e-52b0-adf4-e97bd17ecf60.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=f8dd0332e6d911e6a2aa782bcb074135a226cf379cf746a8976dd3420f5a2813",
-    "MetadataAccess": [
-        "f8dd0332e6d911e6a2aa782bcb074135a226cf379cf746a8976dd3420f5a2813"
-    ],
-    "PublicationTimestamp": "2017-01-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "fulltext": "f8dd0332e6d911e6a2aa782bcb074135a226cf379cf746a8976dd3420f5a2813;2018-11-15T16:40:25Z;corpus;corpus:text;LX-Rare Word Similarity Dataset;The LX-Rare Word Similarity Data set was created from Stanford Rare Word (RW) Similarity data set (Luong et al., 2013). This list contains 2 034 words (1 017 pairs of words). All the words were extracted from Wikipedia and from WordNet (Miller, 1995), a lexical database where the concepts are grouped into sets of synonyms.\nThe construction of this list followed this procedure: a) firstly, a list of rare words was selected from Wikipedia, b) after that, each rare word was paired with a related word picked from WordNet. Rare words are those words that have between 5 000 to 10 000 occurrences in Wikipedia.\nIn the end, the result was a set of word pairs in which one of the words is rare and the other one, which can be rare or not, is related to the first word by some WordNet relation - it can be an hyponym, hyperonym, meronym, holonym or attribute of the former.;2017-01-30",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e0d086a9-990e-52b0-adf4-e97bd17ecf60",
-    "notes": [
-        "The LX-Rare Word Similarity Data set was created from Stanford Rare Word (RW) Similarity data set (Luong et al., 2013). This list contains 2 034 words (1 017 pairs of words). All the words were extracted from Wikipedia and from WordNet (Miller, 1995), a lexical database where the concepts are grouped into sets of synonyms.\nThe construction of this list followed this procedure: a) firstly, a list of rare words was selected from Wikipedia, b) after that, each rare word was paired with a related word picked from WordNet. Rare words are those words that have between 5 000 to 10 000 occurrences in Wikipedia.\nIn the end, the result was a set of word pairs in which one of the words is rare and the other one, which can be rare or not, is related to the first word by some WordNet relation - it can be an hyponym, hyperonym, meronym, holonym or attribute of the former."
-    ],
-    "oai_identifier": [
-        "f8dd0332e6d911e6a2aa782bcb074135a226cf379cf746a8976dd3420f5a2813"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "LX-Rare Word Similarity Dataset"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e0d11c3f-1e40-5994-9c1d-635ad6e95606.json b/oaitestdata/clarin-oai_dc/SET_1/json/e0d11c3f-1e40-5994-9c1d-635ad6e95606.json
deleted file mode 100644
index 676db3d2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e0d11c3f-1e40-5994-9c1d-635ad6e95606.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1180",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1180"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1180",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1180;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Corpus Work Bench CWB (CQP);This SOAP service implements the IMS Open Corpus Workbench (CWB), a collection of open-source tools for managing and querying large text corpora (ranging from 10 million to 2 billion words) with linguistic annotations. Its central component is the flexible and efficient query processor CQP. The service makes it possible to index a new corpus and query it.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1180;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra;http://gilmere.upf.edu/cqp_invoker/queries",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e0d11c3f-1e40-5994-9c1d-635ad6e95606",
-    "notes": [
-        "This SOAP service implements the IMS Open Corpus Workbench (CWB), a collection of open-source tools for managing and querying large text corpora (ranging from 10 million to 2 billion words) with linguistic annotations. Its central component is the flexible and efficient query processor CQP. The service makes it possible to index a new corpus and query it."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1180"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus Work Bench CWB (CQP)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e0d3f2fa-64b4-5e34-90f8-1ea1b0cec7cd.json b/oaitestdata/clarin-oai_dc/SET_1/json/e0d3f2fa-64b4-5e34-90f8-1ea1b0cec7cd.json
deleted file mode 100644
index c7d28f90..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e0d3f2fa-64b4-5e34-90f8-1ea1b0cec7cd.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3899",
-    "MetadataAccess": [
-        "oai:ota:oucs:3899"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hoole, John, 1727-1803."
-    ],
-    "fulltext": "oai:ota:oucs:3899;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3899.xml;Cleonice, Princess of Bithynia: a tragedy. As it is performed at the Theatre Royal in Covent-Garden. By John Hoole.;Hoole, John, 1727-1803.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e0d3f2fa-64b4-5e34-90f8-1ea1b0cec7cd",
-    "oai_identifier": [
-        "oai:ota:oucs:3899"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Cleonice, Princess of Bithynia: a tragedy. As it is performed at the Theatre Royal in Covent-Garden. By John Hoole."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3899.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e0d66d1d-4d9b-5eb4-b048-72295f4b0953.json b/oaitestdata/clarin-oai_dc/SET_1/json/e0d66d1d-4d9b-5eb4-b048-72295f4b0953.json
deleted file mode 100644
index 4ebf120b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e0d66d1d-4d9b-5eb4-b048-72295f4b0953.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "41 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1350",
-    "MetadataAccess": [
-        "oai:ota:oucs:1350"
-    ],
-    "PublicationTimestamp": "1521-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1521"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Unknown"
-    ],
-    "fulltext": "oai:ota:oucs:1350;2018-04-26T12:36:48Z;http://ota.ox.ac.uk/headers/1350.xml;Everyman;Unknown;1521-1537;text_and_corpus_linguistics;English drama -- 16th century;eng;Oxford Text Archive, University of Oxford;41 KB;Text;Plays;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e0d66d1d-4d9b-5eb4-b048-72295f4b0953",
-    "oai_identifier": [
-        "oai:ota:oucs:1350"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- th century"
-        }
-    ],
-    "title": [
-        "Everyman"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1350.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e0d929c2-6af6-5297-b012-35924c5ace94.json b/oaitestdata/clarin-oai_dc/SET_1/json/e0d929c2-6af6-5297-b012-35924c5ace94.json
deleted file mode 100644
index e47b1a69..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e0d929c2-6af6-5297-b012-35924c5ace94.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "ClarinPL"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 11",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/338",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/338"
-    ],
-    "PID": "http://hdl.handle.net/11321/338",
-    "PublicationTimestamp": "2017-02-28T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "ClarinPL"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "author": [
-        "Paw\u0142owski, Adam"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/338;2017-03-03T13:08:56Z;hdl_11321_3;hdl_11321_322;Clarin PL 2 M6 Milestone;Paw\u0142owski, Adam;M6;Clarin 2.0 - M6 Milestone files;2017-02-28;corpus;http://hdl.handle.net/11321/338;pol;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 11;ClarinPL",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e0d929c2-6af6-5297-b012-35924c5ace94",
-    "notes": [
-        "Clarin 2.0 - M6 Milestone files"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/338"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_322"
-    ],
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Clarin PL 2 M6 Milestone"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e0ddf0b6-0f01-54cf-b49e-b626b767c0bf.json b/oaitestdata/clarin-oai_dc/SET_1/json/e0ddf0b6-0f01-54cf-b49e-b626b767c0bf.json
deleted file mode 100644
index 76cfdc8c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e0ddf0b6-0f01-54cf-b49e-b626b767c0bf.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1039",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1039"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1039",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1039;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;L1 Acquisition Christine Dimroth & Bhuvana Narasimhan;Language Acquisition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1039;deu;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI566280%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e0ddf0b6-0f01-54cf-b49e-b626b767c0bf",
-    "notes": [
-        "Language Acquisition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1039"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "L1 Acquisition Christine Dimroth & Bhuvana Narasimhan"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e0ec22d5-5b9c-52c6-b0c5-a529305a4d3c.json b/oaitestdata/clarin-oai_dc/SET_1/json/e0ec22d5-5b9c-52c6-b0c5-a529305a4d3c.json
deleted file mode 100644
index 88504ea2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e0ec22d5-5b9c-52c6-b0c5-a529305a4d3c.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3831",
-    "MetadataAccess": [
-        "oai:ota:oucs:3831"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Lee, Sophia, 1750-1824."
-    ],
-    "fulltext": "oai:ota:oucs:3831;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3831.xml;Almeyda, Queen of Granada: A tragedy, in five acts. By Sophia Lee. As performed at the Theatre Royal, Drury-Lane.;Lee, Sophia, 1750-1824.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e0ec22d5-5b9c-52c6-b0c5-a529305a4d3c",
-    "oai_identifier": [
-        "oai:ota:oucs:3831"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Almeyda, Queen of Granada: A tragedy, in five acts. By Sophia Lee. As performed at the Theatre Royal, Drury-Lane."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3831.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e114380b-b56a-5a7f-bfdc-23b28891e923.json b/oaitestdata/clarin-oai_dc/SET_1/json/e114380b-b56a-5a7f-bfdc-23b28891e923.json
deleted file mode 100644
index 53f56fb7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e114380b-b56a-5a7f-bfdc-23b28891e923.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5478",
-    "MetadataAccess": [
-        "oai:ota:oucs:5478"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Lennox, Charlotte, ca. 1729-1804."
-    ],
-    "fulltext": "oai:ota:oucs:5478;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5478.xml;The history of Sir George Warrington: or the political Quixote. By the author of The female Quixote. In three volumes. ... [pt.3];Lennox, Charlotte, ca. 1729-1804.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e114380b-b56a-5a7f-bfdc-23b28891e923",
-    "oai_identifier": [
-        "oai:ota:oucs:5478"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The history of Sir George Warrington: or the political Quixote. By the author of The female Quixote. In three volumes. ... [pt.3]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5478.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e114da08-d0a1-5a3d-9d22-8bca2465e010.json b/oaitestdata/clarin-oai_dc/SET_1/json/e114da08-d0a1-5a3d-9d22-8bca2465e010.json
deleted file mode 100644
index 824bea20..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e114da08-d0a1-5a3d-9d22-8bca2465e010.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3135",
-    "MetadataAccess": [
-        "oai:ota:oucs:3135"
-    ],
-    "PublicationTimestamp": "1917-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1917"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Wharton, Edith, 1862-1937"
-    ],
-    "fulltext": "oai:ota:oucs:3135;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3135.xml;Summer;Wharton, Edith, 1862-1937;not after: 1917;text_and_corpus_linguistics;American fiction -- 20th century;eng;Oxford Text Archive, University of Oxford;Triggs, Jeffery;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e114da08-d0a1-5a3d-9d22-8bca2465e010",
-    "oai_identifier": [
-        "oai:ota:oucs:3135"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "American fiction -- th century"
-        }
-    ],
-    "title": [
-        "Summer"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3135.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e1566636-84fc-5e80-89ef-93ba3c9026d1.json b/oaitestdata/clarin-oai_dc/SET_1/json/e1566636-84fc-5e80-89ef-93ba3c9026d1.json
deleted file mode 100644
index 3d71a5f2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e1566636-84fc-5e80-89ef-93ba3c9026d1.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Akademii Krakowskiej"
-    ],
-    "Contributor": [
-        "Brzezi\u0144ski, Andrzej. T\u0142."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-216027",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-216027"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CFE-B",
-    "PublicationTimestamp": "1693-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1693"
-    ],
-    "Publisher": [
-        "Drukarnia Akademii Krakowskiej"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/216027",
-        "oai:jbc.bj.uj.edu.pl:publication:227514"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1601/1700"
-    ],
-    "TempCoverageBegin": 50506804799,
-    "TempCoverageEnd": 50506804799,
-    "TemporalCoverage": " point in time : 1601-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1601-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1601-07-01T11:59:59Z",
-    "author": [
-        "Bie\u017canowski, Stanis\u0142aw J\u00f3zef (1628-1693)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-216027;2019-03-01T11:16:01Z;Zabawa Duchowna, Na Solenn\u0105 Oktaw\u0119, Niepokalanego Pocz\u0119cia [...] Bogarodzice Maryey Panny [...];Bie\u017canowski, Stanis\u0142aw J\u00f3zef (1628-1693);starodruki 17\u00a0w.;Piaseczy\u0144ska, Zofia Barbara (16..- ). Adr. ded.;Drukarnia Akademii Krakowskiej;Brzezi\u0144ski, Andrzej. T\u0142.;[1693];starodruk;application/xml;clarind-uds:poldilemma-216027;hdl:11858/00-246C-0000-0023-8CFE-B;Biblioteka Jagiello\u0144ska, BJ St. Dr. 5563 I;pol;lat;http://jbc.bj.uj.edu.pl/Content/216027;oai:jbc.bj.uj.edu.pl:publication:227514;1601/1700;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e1566636-84fc-5e80-89ef-93ba3c9026d1",
-    "notes": [
-        "Piaseczy\u0144ska, Zofia Barbara (16..- ). Adr. ded."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-216027"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Zabawa Duchowna, Na Solenn\u0105 Oktaw\u0119, Niepokalanego Pocz\u0119cia [...] Bogarodzice Maryey Panny [...]"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e1567d27-1664-5d9b-9e3c-3d8bc11fe030.json b/oaitestdata/clarin-oai_dc/SET_1/json/e1567d27-1664-5d9b-9e3c-3d8bc11fe030.json
deleted file mode 100644
index ec8ebda7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e1567d27-1664-5d9b-9e3c-3d8bc11fe030.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "less than 512 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1234",
-    "MetadataAccess": [
-        "oai:ota:oucs:1234"
-    ],
-    "PublicationTimestamp": "1600-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1600"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Shakespeare, William,  1564-1616"
-    ],
-    "fulltext": "oai:ota:oucs:1234;2018-05-17T10:12:54Z;http://ota.ox.ac.uk/headers/1234.xml;Henry the Fifth, 1600  / compiled by Lou Burnard;Shakespeare, William,  1564-1616;1600;text_and_corpus_linguistics;Plays -- England -- 16th century;eng;Oxford Text Archive, University of Oxford;less than 512 KB;Text;Plays;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e1567d27-1664-5d9b-9e3c-3d8bc11fe030",
-    "oai_identifier": [
-        "oai:ota:oucs:1234"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        }
-    ],
-    "title": [
-        "Henry the Fifth, 1600  / compiled by Lou Burnard"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1234.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e15c4885-1bcc-592b-bc95-46ff71350028.json b/oaitestdata/clarin-oai_dc/SET_1/json/e15c4885-1bcc-592b-bc95-46ff71350028.json
deleted file mode 100644
index fc44dec7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e15c4885-1bcc-592b-bc95-46ff71350028.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3389",
-    "MetadataAccess": [
-        "oai:ota:oucs:3389"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Janeway, James, 1636?-1674."
-    ],
-    "fulltext": "oai:ota:oucs:3389;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3389.xml;An extract of the life and death of Mr. John Janeway: ... By James Wheatley.;Invisibles, realities.;Janeway, James, 1636?-1674.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e15c4885-1bcc-592b-bc95-46ff71350028",
-    "oai_identifier": [
-        "oai:ota:oucs:3389"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An extract of the life and death of Mr. John Janeway: ... By James Wheatley.",
-        "Invisibles, realities."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3389.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e1868b23-f87e-5d61-95a4-fb1133ea1a3e.json b/oaitestdata/clarin-oai_dc/SET_1/json/e1868b23-f87e-5d61-95a4-fb1133ea1a3e.json
deleted file mode 100644
index e64b9c24..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e1868b23-f87e-5d61-95a4-fb1133ea1a3e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3667",
-    "MetadataAccess": [
-        "oai:ota:oucs:3667"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pope, Alexander, 1688-1744."
-    ],
-    "fulltext": "oai:ota:oucs:3667;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3667.xml;A clue to the comedy of the Non-juror: With some hints of consequence relating to that play. In a letter to N. Rowe, Esq; ...;Pope, Alexander, 1688-1744.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e1868b23-f87e-5d61-95a4-fb1133ea1a3e",
-    "oai_identifier": [
-        "oai:ota:oucs:3667"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A clue to the comedy of the Non-juror: With some hints of consequence relating to that play. In a letter to N. Rowe, Esq; ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3667.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e189a711-4486-5bf7-b644-802d9e8d4012.json b/oaitestdata/clarin-oai_dc/SET_1/json/e189a711-4486-5bf7-b644-802d9e8d4012.json
deleted file mode 100644
index ccfa13fe..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e189a711-4486-5bf7-b644-802d9e8d4012.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=b649dff00b6011e5a2aa782bcb0741354ad5521a324743f892e77177bc67fc6a",
-    "MetadataAccess": [
-        "b649dff00b6011e5a2aa782bcb0741354ad5521a324743f892e77177bc67fc6a"
-    ],
-    "PublicationTimestamp": "2015-06-05T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "b649dff00b6011e5a2aa782bcb0741354ad5521a324743f892e77177bc67fc6a;2018-11-15T16:40:15Z;toolService;toolService:tool;ixa-pipe-pos-eu;ixa-pipe-pos-eu is a robust and wide-coverage morphological analyser and a Part-of-Speech tagger for Basque.\n\nThe analyser is based on the two-level formalism and has been designed in an incremental way with three main modules: the standard analyser, the analyser of linguistic variants, and the analyser without lexicon which can recognize word-forms without having their lemmas in the lexicon. ixa-pipe-pos-eu provides the lemma, PoS and morphological information for each token.\n\nThis tool reads raw text and outputs a file in Natural Language Processing Annotation Format (NAF) (http://wordpress.let.vupr.nl/naf/).\n\nThis tool is partly funded by the European Commission project QTLeap FP7-ICT-2013.4.1-610516 (http://qtleap.eu). This tool is distributed under the license GPL v3.0.\n;2015-06-05",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e189a711-4486-5bf7-b644-802d9e8d4012",
-    "notes": [
-        "ixa-pipe-pos-eu is a robust and wide-coverage morphological analyser and a Part-of-Speech tagger for Basque.\n\nThe analyser is based on the two-level formalism and has been designed in an incremental way with three main modules: the standard analyser, the analyser of linguistic variants, and the analyser without lexicon which can recognize word-forms without having their lemmas in the lexicon. ixa-pipe-pos-eu provides the lemma, PoS and morphological information for each token.\n\nThis tool reads raw text and outputs a file in Natural Language Processing Annotation Format (NAF) (http://wordpress.let.vupr.nl/naf/).\n\nThis tool is partly funded by the European Commission project QTLeap FP7-ICT-2013.4.1-610516 (http://qtleap.eu). This tool is distributed under the license GPL v3.0.\n"
-    ],
-    "oai_identifier": [
-        "b649dff00b6011e5a2aa782bcb0741354ad5521a324743f892e77177bc67fc6a"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "ixa-pipe-pos-eu"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e1af1aa3-2acd-5eba-99f3-e2dec2734f39.json b/oaitestdata/clarin-oai_dc/SET_1/json/e1af1aa3-2acd-5eba-99f3-e2dec2734f39.json
deleted file mode 100644
index af173217..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e1af1aa3-2acd-5eba-99f3-e2dec2734f39.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Jan Koco\u0144"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 3",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/343",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/343"
-    ],
-    "PID": "http://hdl.handle.net/11321/343",
-    "PublicationTimestamp": "2017-04-19T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Jan Koco\u0144"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN-EULA-ACA-v1.0",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca",
-        "ACA"
-    ],
-    "author": [
-        "Koco\u0144, Jan"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/343;2017-04-25T11:08:36Z;hdl_11321_3;hdl_11321_4;Diachrono - sample;Koco\u0144, Jan;diachronic;Sample of diachronic corpus;2017-04-19;corpus;http://hdl.handle.net/11321/343;pol;CLARIN-EULA-ACA-v1.0;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca;ACA;text/plain; charset=utf-8;application/msword;application/msword;application/msword;downloadable_files_count: 3;Jan Koco\u0144",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e1af1aa3-2acd-5eba-99f3-e2dec2734f39",
-    "notes": [
-        "Sample of diachronic corpus"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/343"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "diachronic"
-        }
-    ],
-    "title": [
-        "Diachrono - sample"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e1cdbecd-9e7c-5bde-926c-abb5983972ce.json b/oaitestdata/clarin-oai_dc/SET_1/json/e1cdbecd-9e7c-5bde-926c-abb5983972ce.json
deleted file mode 100644
index 663f063b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e1cdbecd-9e7c-5bde-926c-abb5983972ce.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Akademicka"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-149590",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-149590"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CE0-B",
-    "PublicationTimestamp": "1750-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1750"
-    ],
-    "Publisher": [
-        "Drukarnia Akademicka"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/149590",
-        "oai:jbc.bj.uj.edu.pl:publication:157832"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1701/1800"
-    ],
-    "TempCoverageBegin": 53662478399,
-    "TempCoverageEnd": 53662478399,
-    "TemporalCoverage": " point in time : 1701-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1701-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1701-07-01T11:59:59Z",
-    "author": [
-        "Hylzen, Jan August (1702-1767)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-149590;2019-02-28T18:29:31Z;Inflanty W dawnych swych, y wielorakich a\u017c do wieku naszego dziejach y rewolucyach; z wywodem godno\u015bci y staro\u017cytno\u015bci Szlachty tameczney, tudziesz praw, y wolno\u015bci z dawna, y teraz jey s\u0142u\u017c\u0105cych Zebrane y Polskiemu \u015bwiatu do wiadomo\u015bci w Oyczystyni j\u0119zyku Podane;Hylzen, Jan August (1702-1767);starodruki 18\u00a0w.;Drukarnia Akademicka;1750;starodruk;application/xml;clarind-uds:poldilemma-149590;hdl:11858/00-246C-0000-0023-8CE0-B;Biblioteka Jagiello\u0144ska, BJ St. Dr. 18994 I;pol;lat;http://jbc.bj.uj.edu.pl/Content/149590;oai:jbc.bj.uj.edu.pl:publication:157832;1701/1800;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e1cdbecd-9e7c-5bde-926c-abb5983972ce",
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-149590"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Inflanty W dawnych swych, y wielorakich a\u017c do wieku naszego dziejach y rewolucyach; z wywodem godno\u015bci y staro\u017cytno\u015bci Szlachty tameczney, tudziesz praw, y wolno\u015bci z dawna, y teraz jey s\u0142u\u017c\u0105cych Zebrane y Polskiemu \u015bwiatu do wiadomo\u015bci w Oyczystyni j\u0119zyku Podane"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e1d55628-626e-5b2a-afc2-f5c1d16c34a4.json b/oaitestdata/clarin-oai_dc/SET_1/json/e1d55628-626e-5b2a-afc2-f5c1d16c34a4.json
deleted file mode 100644
index b3eb0b7a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e1d55628-626e-5b2a-afc2-f5c1d16c34a4.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=0f94b4e2328611e2a2aa782bcb0741355355eba16ed6440a81ceac5365c725e7",
-    "MetadataAccess": [
-        "0f94b4e2328611e2a2aa782bcb0741355355eba16ed6440a81ceac5365c725e7"
-    ],
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "0f94b4e2328611e2a2aa782bcb0741355355eba16ed6440a81ceac5365c725e7;2018-11-15T16:39:51Z;toolService;toolService:tool;UIMA/U-Compare GENIA Tagger;The GENIA tagger analyzes English sentences and outputs the base forms, part-of-speech tags, chunk tags, and named entity tags. The tagger is specifically tuned for biomedical text such as MEDLINE abstracts. \n\nThe tool is provided as a UIMA component, which forms part of the in-built library of components provided with the U-Compare platform (see separate META-SHARE record)  for building and evaluating text mining workflows. The U-Compare Workbench (see separate META-SHARE record) provides a graphical drag-and drop interface for the rapid creation of workflows. \n;2015-12-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e1d55628-626e-5b2a-afc2-f5c1d16c34a4",
-    "notes": [
-        "The GENIA tagger analyzes English sentences and outputs the base forms, part-of-speech tags, chunk tags, and named entity tags. The tagger is specifically tuned for biomedical text such as MEDLINE abstracts. \n\nThe tool is provided as a UIMA component, which forms part of the in-built library of components provided with the U-Compare platform (see separate META-SHARE record)  for building and evaluating text mining workflows. The U-Compare Workbench (see separate META-SHARE record) provides a graphical drag-and drop interface for the rapid creation of workflows. \n"
-    ],
-    "oai_identifier": [
-        "0f94b4e2328611e2a2aa782bcb0741355355eba16ed6440a81ceac5365c725e7"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "UIMA/U-Compare GENIA Tagger"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e1e4bc53-93b5-5f3c-932c-b286b80beb81.json b/oaitestdata/clarin-oai_dc/SET_1/json/e1e4bc53-93b5-5f3c-932c-b286b80beb81.json
deleted file mode 100644
index 13702960..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e1e4bc53-93b5-5f3c-932c-b286b80beb81.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Arts, Institute of the Czech National Corpus, Charles University in Prague"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-1359-1",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-1359-1"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-1359-1",
-    "PublicationTimestamp": "2010-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "Faculty of Arts, Institute of the Czech National Corpus, Charles University in Prague"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Czech National Corpus (Shuffled Corpus Data)",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/license-cnc",
-        "ACA"
-    ],
-    "author": [
-        "Hn\u00e1tkov\u00e1, Milena",
-        "Petkevi\u010d, Vladim\u00edr",
-        "Barto\u0148, Tom\u00e1\u0161",
-        "K\u0159en, Michal",
-        "Jel\u00ednek, Tom\u00e1\u0161",
-        "Skoumalov\u00e1, Hana",
-        "Proch\u00e1zka, Pavel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-1359-1;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;SYN2009PUB: corpus of Czech newspapers;K\u0159en, Michal;Barto\u0148, Tom\u00e1\u0161;Hn\u00e1tkov\u00e1, Milena;Jel\u00ednek, Tom\u00e1\u0161;Petkevi\u010d, Vladim\u00edr;Proch\u00e1zka, Pavel;Skoumalov\u00e1, Hana;corpus;written language;Corpus of contemporary Czech newspapers and magazines sized 700 MW. It contains various titles published between 1995\u20132007. The corpus is lemmatized and morphologically tagged by a combination of stochastic and rule-based methods.\r\nThe corpus is provided in a (semi-XML) vertical format used as an input to the Manatee query engine. The data thus correspond to the corpus available via query interface to registered users of the CNC with one important exception: they are shuffled, i.e. divided into blocks sized max. 100 words (respecting the sentence boundaries) whose ordering was randomized within the given document.;2010;corpus;http://hdl.handle.net/11858/00-097C-0000-0023-1359-1;ces;Czech National Corpus (Shuffled Corpus Data);https://lindat.mff.cuni.cz/repository/xmlui/page/license-cnc;ACA;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Faculty of Arts, Institute of the Czech National Corpus, Charles University in Prague;https://wiki.korpus.cz/doku.php/cnk:syn2009pub",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e1e4bc53-93b5-5f3c-932c-b286b80beb81",
-    "notes": [
-        "Corpus of contemporary Czech newspapers and magazines sized 700 MW. It contains various titles published between 1995\u20132007. The corpus is lemmatized and morphologically tagged by a combination of stochastic and rule-based methods.\r\nThe corpus is provided in a (semi-XML) vertical format used as an input to the Manatee query engine. The data thus correspond to the corpus available via query interface to registered users of the CNC with one important exception: they are shuffled, i.e. divided into blocks sized max. 100 words (respecting the sentence boundaries) whose ordering was randomized within the given document."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-1359-1"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "written language"
-        }
-    ],
-    "title": [
-        "SYN2009PUB: corpus of Czech newspapers"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e21b6bfe-f827-51fb-b1f6-a2213b6b43d8.json b/oaitestdata/clarin-oai_dc/SET_1/json/e21b6bfe-f827-51fb-b1f6-a2213b6b43d8.json
deleted file mode 100644
index 4abe566b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e21b6bfe-f827-51fb-b1f6-a2213b6b43d8.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4348",
-    "MetadataAccess": [
-        "oai:ota:oucs:4348"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pratt, Mr. (Samuel Jackson), 1749-1814."
-    ],
-    "fulltext": "oai:ota:oucs:4348;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4348.xml;Shenstone-Green: or, the new Paradise lost. Being a history of human nature. In three volumes. ... Written by the proprietor of the Green. The editor Courtney Melmoth. [pt.2];Pratt, Mr. (Samuel Jackson), 1749-1814.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e21b6bfe-f827-51fb-b1f6-a2213b6b43d8",
-    "oai_identifier": [
-        "oai:ota:oucs:4348"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Shenstone-Green: or, the new Paradise lost. Being a history of human nature. In three volumes. ... Written by the proprietor of the Green. The editor Courtney Melmoth. [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4348.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e229bd89-020e-5560-8226-a17d4a484d01.json b/oaitestdata/clarin-oai_dc/SET_1/json/e229bd89-020e-5560-8226-a17d4a484d01.json
deleted file mode 100644
index ffcf376e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e229bd89-020e-5560-8226-a17d4a484d01.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Ewa Dulna-Rak"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/richtext",
-        "downloadable_files_count: 50",
-        "application/zip"
-    ],
-    "Language": [],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/246",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/246"
-    ],
-    "PID": "http://hdl.handle.net/11321/246",
-    "PublicationTimestamp": "2016-02-11T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Ewa Dulna-Rak"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Dulna-Rak, Ewa"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/246;2017-04-04T10:15:07Z;hdl_11321_3;hdl_11321_4;Iwo Gall -teksty teatralne;Dulna-Rak, Ewa;teatr;Teksty teatralne Iwona Galla;2016-02-11;corpus;http://hdl.handle.net/11321/246;POLSKI;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;text/plain; charset=utf-8;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;text/richtext;application/zip;application/zip;downloadable_files_count: 50;Ewa Dulna-Rak",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e229bd89-020e-5560-8226-a17d4a484d01",
-    "notes": [
-        "Teksty teatralne Iwona Galla"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/246"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "teatr"
-        }
-    ],
-    "title": [
-        "Iwo Gall -teksty teatralne"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e22f609a-6b67-5963-9434-99a6e3c67c2c.json b/oaitestdata/clarin-oai_dc/SET_1/json/e22f609a-6b67-5963-9434-99a6e3c67c2c.json
deleted file mode 100644
index bebdae81..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e22f609a-6b67-5963-9434-99a6e3c67c2c.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "McKinnon, Alistair"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(4 files : ca. 434, 257, 4 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0563",
-    "MetadataAccess": [
-        "oai:ota:oucs:0563"
-    ],
-    "PublicationTimestamp": "1946-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1946"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Academic dissertations"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Wittgenstein, Ludwig, 1889-1951"
-    ],
-    "fulltext": "oai:ota:oucs:0563;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0563.xml;Bemerkungen \u00c3\u00bcber die Philosophie der Psychologie / Ludwig Wittgenstein / Ludwig Wittgenstein;Remarks on the philosophy of psychology;Wittgenstein, Ludwig, 1889-1951;1946-1949;text_and_corpus_linguistics;Psychology -- Philosophy -- 20th century;deu;Oxford Text Archive, University of Oxford;McKinnon, Alistair;text/plain;(4 files : ca. 434, 257, 4 KB);Text;Academic dissertations;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e22f609a-6b67-5963-9434-99a6e3c67c2c",
-    "oai_identifier": [
-        "oai:ota:oucs:0563"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Psychology -- Philosophy -- th century"
-        }
-    ],
-    "title": [
-        "Bemerkungen \u00c3\u00bcber die Philosophie der Psychologie / Ludwig Wittgenstein / Ludwig Wittgenstein",
-        "Remarks on the philosophy of psychology"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0563.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e2370598-dd5c-53f3-839b-dbbf7afd3a37.json b/oaitestdata/clarin-oai_dc/SET_1/json/e2370598-dd5c-53f3-839b-dbbf7afd3a37.json
deleted file mode 100644
index 39056f39..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e2370598-dd5c-53f3-839b-dbbf7afd3a37.json
+++ /dev/null
@@ -1,88 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-487A-4",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-487A-4"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-487A-4",
-    "PublicationTimestamp": "2011-01-23T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11858/00-097C-0000-0001-B098-5",
-        "http://hdl.handle.net/11858/00-097C-0000-0001-B098-5",
-        "http://hdl.handle.net/11858/00-097C-0000-0001-4880-3"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u0160id\u00e1k, Pavel",
-        "Holub, Martin",
-        "Haji\u010d, Jan",
-        "Hu\u010d\u00ednov\u00e1, Marie",
-        "Bej\u010dek, Eduard",
-        "Pecina, Pavel",
-        "Stra\u0148\u00e1k, Pavel",
-        "Hoffmannov\u00e1, Petra"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-487A-4;2018-07-02T22:05:53Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Lexico-Semantic Annotation of PDT using Czech WordNet;Bej\u010dek, Eduard;Hoffmannov\u00e1, Petra;Holub, Martin;Hu\u010d\u00ednov\u00e1, Marie;Pecina, Pavel;Stra\u0148\u00e1k, Pavel;\u0160id\u00e1k, Pavel;Haji\u010d, Jan;PDT;Czech WordNet;PDT;This dataset contains annotation of PDT using Czech WordNet ontology: http://hdl.handle.net/11858/00-097C-0000-0001-4880-3\r\n\r\nData is stored in PML format. This is a stand-off annotation and for most use cases it requires PDT 2.0 and the Czech WordNet 1.9 PDT that we have used for annotation.;2011-01-23;corpus;http://hdl.handle.net/11858/00-097C-0000-0001-487A-4;ces;http://hdl.handle.net/11858/00-097C-0000-0001-B098-5;http://hdl.handle.net/11858/00-097C-0000-0001-B098-5;http://hdl.handle.net/11858/00-097C-0000-0001-4880-3;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e2370598-dd5c-53f3-839b-dbbf7afd3a37",
-    "notes": [
-        "This dataset contains annotation of PDT using Czech WordNet ontology: http://hdl.handle.net/11858/00-097C-0000-0001-4880-3\r\n\r\nData is stored in PML format. This is a stand-off annotation and for most use cases it requires PDT 2.0 and the Czech WordNet 1.9 PDT that we have used for annotation."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-487A-4"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "PDT"
-        },
-        {
-            "name": "Czech WordNet"
-        },
-        {
-            "name": "PDT"
-        }
-    ],
-    "title": [
-        "Lexico-Semantic Annotation of PDT using Czech WordNet"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e23bfaa9-4085-5150-b46e-c25fb50a988d.json b/oaitestdata/clarin-oai_dc/SET_1/json/e23bfaa9-4085-5150-b46e-c25fb50a988d.json
deleted file mode 100644
index 3c1d5650..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e23bfaa9-4085-5150-b46e-c25fb50a988d.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3379",
-    "MetadataAccess": [
-        "oai:ota:oucs:3379"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hawkins, William, 1722-1801."
-    ],
-    "fulltext": "oai:ota:oucs:3379;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3379.xml;Henry and Rosamond: A tragedy. Dedicated to Sir John Philipps, Bart. By William Hawkins, ...;Hawkins, William, 1722-1801.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e23bfaa9-4085-5150-b46e-c25fb50a988d",
-    "oai_identifier": [
-        "oai:ota:oucs:3379"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Henry and Rosamond: A tragedy. Dedicated to Sir John Philipps, Bart. By William Hawkins, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3379.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e258d668-88b2-5252-98ea-75db110b64eb.json b/oaitestdata/clarin-oai_dc/SET_1/json/e258d668-88b2-5252-98ea-75db110b64eb.json
deleted file mode 100644
index c0a0056e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e258d668-88b2-5252-98ea-75db110b64eb.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/35",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/35"
-    ],
-    "PID": "http://hdl.handle.net/11321/35",
-    "PublicationTimestamp": "2012-06-20T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Radziszewski, Adam"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/35;2016-01-21T14:15:26Z;hdl_11321_3;hdl_11321_4;WCRFT;Radziszewski, Adam;WCRFT (Wroc\u0142aw CRF Tagger) is a simple morpho-syntactic tagger for Polish producing state-of-the-art results.\r\n\r\nThe tagger combines tiered tagging, conditional random fields (CRF) and features tailored for inflective languages written in WCCL.\r\nThe algorithm and code are inspired by Wroc\u0142aw Memory-Based Tagger.;2012-06-20;toolService;http://hdl.handle.net/11321/35;pol;downloadable_files_count: 0;Wroc\u0142aw University of Technology;http://nlp.pwr.wroc.pl/redmine/projects/wcrft/wiki/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e258d668-88b2-5252-98ea-75db110b64eb",
-    "notes": [
-        "WCRFT (Wroc\u0142aw CRF Tagger) is a simple morpho-syntactic tagger for Polish producing state-of-the-art results.\r\n\r\nThe tagger combines tiered tagging, conditional random fields (CRF) and features tailored for inflective languages written in WCCL.\r\nThe algorithm and code are inspired by Wroc\u0142aw Memory-Based Tagger."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/35"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "WCRFT"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e2595776-1006-5365-869c-ba13dcc6d73b.json b/oaitestdata/clarin-oai_dc/SET_1/json/e2595776-1006-5365-869c-ba13dcc6d73b.json
deleted file mode 100644
index be0ffcd2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e2595776-1006-5365-869c-ba13dcc6d73b.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 110 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2235",
-    "MetadataAccess": [
-        "oai:ota:oucs:2235"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Ovid, 43 B.C.-17 or 18 A.D."
-    ],
-    "fulltext": "oai:ota:oucs:2235;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/2235.xml;Amores. English;All Ovid's Elegies : 3 books / [translated] by Christopher Marlowe;Poetae Ovidii Nasonis Amorum;Ovid, 43 B.C.-17 or 18 A.D.;default: 1976-01-01;text_and_corpus_linguistics;Poems;Lyric poems;Elegies;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 110 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e2595776-1006-5365-869c-ba13dcc6d73b",
-    "oai_identifier": [
-        "oai:ota:oucs:2235"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems"
-        },
-        {
-            "name": "Lyric poems"
-        },
-        {
-            "name": "Elegies"
-        }
-    ],
-    "title": [
-        "Amores. English",
-        "All Ovid's Elegies : 3 books / [translated] by Christopher Marlowe",
-        "Poetae Ovidii Nasonis Amorum"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2235.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e26e23d8-d820-5a72-be62-d96f4e260a27.json b/oaitestdata/clarin-oai_dc/SET_1/json/e26e23d8-d820-5a72-be62-d96f4e260a27.json
deleted file mode 100644
index 6589e7c9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e26e23d8-d820-5a72-be62-d96f4e260a27.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Jan Trelpi\u0144ski"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229071",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229071"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D01-A",
-    "PublicationTimestamp": "1640-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1640"
-    ],
-    "Publisher": [
-        "Jan Trelpi\u0144ski"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/229071",
-        "oai:jbc.bj.uj.edu.pl:publication:240714"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1601/1700"
-    ],
-    "TempCoverageBegin": 50506804799,
-    "TempCoverageEnd": 50506804799,
-    "TemporalCoverage": " point in time : 1601-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1601-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1601-07-01T11:59:59Z",
-    "author": [
-        "Kuncewicz, Micha\u0142"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229071;2019-03-01T11:26:07Z;Dobry A Pobo\u017cny Ziemianin, Przy Pogrzebnym oddaniu ziemi, cia\u0142a zmar\u0142ego S\u0142awney Pami\u0119ci P. Stanis\u0142awa Z Wypych Wypyskiego, Wyra\u017cony Kazaniem;Kuncewicz, Micha\u0142;starodruki 17\u00a0w.;Wypyski, Jan. Adr. ded.;Jan Trelpi\u0144ski;[1640];starodruk;application/xml;clarind-uds:poldilemma-229071;hdl:11858/00-246C-0000-0023-8D01-A;Biblioteka Jagiello\u0144ska, BJ St. Dr. 17231 I;pol;http://jbc.bj.uj.edu.pl/Content/229071;oai:jbc.bj.uj.edu.pl:publication:240714;1601/1700;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e26e23d8-d820-5a72-be62-d96f4e260a27",
-    "notes": [
-        "Wypyski, Jan. Adr. ded."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-229071"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Dobry A Pobo\u017cny Ziemianin, Przy Pogrzebnym oddaniu ziemi, cia\u0142a zmar\u0142ego S\u0142awney Pami\u0119ci P. Stanis\u0142awa Z Wypych Wypyskiego, Wyra\u017cony Kazaniem"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e2af487b-ebcd-51de-b982-ec80ebdbc54c.json b/oaitestdata/clarin-oai_dc/SET_1/json/e2af487b-ebcd-51de-b982-ec80ebdbc54c.json
deleted file mode 100644
index be9da03c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e2af487b-ebcd-51de-b982-ec80ebdbc54c.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/19",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/19"
-    ],
-    "PID": "http://hdl.handle.net/11321/19",
-    "PublicationTimestamp": "2014-01-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "author": [
-        "Piasecki, Maciej",
-        "Szpakowicz, Stanis\u0142aw",
-        "Broda, Bartosz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/19;2016-01-21T14:36:25Z;hdl_11321_3;hdl_11321_4;Lists of semantic relatedness;Piasecki, Maciej;Broda, Bartosz;Szpakowicz, Stanis\u0142aw;Dystrybucyjne Podobie\u0144stwo Semantyczne (DPS, ang. Measure of Semantic Relatedness) obrazuje podobie\u0144stwo pomi\u0119dzy parami wyraz\u00f3w na podstawie  analizy ich wsp\u00f3\u0142wyst\u0119powania w korpusach tekst\u00f3w. Og\u00f3ln\u0105 spos\u00f3b wydobywania podobie\u0144stwa mo\u017cna przedstawi\u0107 nast\u0119puj\u0105co. W pierwszej kolejno\u015bci wszystkie konkteksty interesuj\u0105cych s\u0142\u00f3w s\u0105 analizowane pod k\u0105tem wsp\u00f3\u0142wyst\u0119powania z innymi s\u0142owami.;2014-01-01;corpus;http://hdl.handle.net/11321/19;pol;downloadable_files_count: 0;Wroc\u0142aw University of Technology;http://nlp.pwr.wroc.pl/pl/narzedzia-i-zasoby/lista-podobienstwa-semantycznego",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e2af487b-ebcd-51de-b982-ec80ebdbc54c",
-    "notes": [
-        "Dystrybucyjne Podobie\u0144stwo Semantyczne (DPS, ang. Measure of Semantic Relatedness) obrazuje podobie\u0144stwo pomi\u0119dzy parami wyraz\u00f3w na podstawie  analizy ich wsp\u00f3\u0142wyst\u0119powania w korpusach tekst\u00f3w. Og\u00f3ln\u0105 spos\u00f3b wydobywania podobie\u0144stwa mo\u017cna przedstawi\u0107 nast\u0119puj\u0105co. W pierwszej kolejno\u015bci wszystkie konkteksty interesuj\u0105cych s\u0142\u00f3w s\u0105 analizowane pod k\u0105tem wsp\u00f3\u0142wyst\u0119powania z innymi s\u0142owami."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/19"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Lists of semantic relatedness"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e2af5170-126a-548e-8477-83142e5bc6c4.json b/oaitestdata/clarin-oai_dc/SET_1/json/e2af5170-126a-548e-8477-83142e5bc6c4.json
deleted file mode 100644
index 3043317f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e2af5170-126a-548e-8477-83142e5bc6c4.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 38",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Finnish",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1074",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1074"
-    ],
-    "PID": "http://hdl.handle.net/11356/1074",
-    "PublicationTimestamp": "2016-09-20T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/324414"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "https://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Ljube\u0161i\u0107, Nikola",
-        "Toral, Antonio",
-        "Pirinen, Tommi"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1074;2017-06-27T18:12:39Z;hdl_11356_1023;hdl_11356_1024;Finnish web corpus fiWaC 1.0;Ljube\u0161i\u0107, Nikola;Pirinen, Tommi;Toral, Antonio;web corpus;The Finnish web corpus fiWaC was built by crawling the .fi top-level domain in 2015 for both Finnish and English documents. The corpus was naively tokenised (via spaces), near-deduplicated on paragraph level and paragraph-shuffled. Each paragraph contains metadata on the URL and language identification. The Finnish (~1.7B tokens) and English (~2B tokens) parts of the corpus are organised in separate files.;2016-09-20;corpus;http://hdl.handle.net/11356/1074;fin;eng;info:eu-repo/grantAgreement/EC/FP7/324414;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);https://creativecommons.org/licenses/by-sa/4.0/;PUB;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 38;Jo\u017eef Stefan Institute;http://www.abumatran.eu",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e2af5170-126a-548e-8477-83142e5bc6c4",
-    "notes": [
-        "The Finnish web corpus fiWaC was built by crawling the .fi top-level domain in 2015 for both Finnish and English documents. The corpus was naively tokenised (via spaces), near-deduplicated on paragraph level and paragraph-shuffled. Each paragraph contains metadata on the URL and language identification. The Finnish (~1.7B tokens) and English (~2B tokens) parts of the corpus are organised in separate files."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1074"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "web corpus"
-        }
-    ],
-    "title": [
-        "Finnish web corpus fiWaC 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e2cc38cb-2676-51d7-b5ae-db8a39ef431f.json b/oaitestdata/clarin-oai_dc/SET_1/json/e2cc38cb-2676-51d7-b5ae-db8a39ef431f.json
deleted file mode 100644
index 3674aa9c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e2cc38cb-2676-51d7-b5ae-db8a39ef431f.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Krusch, Barry"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(2 files : ca. 683, 778 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2064",
-    "MetadataAccess": [
-        "oai:ota:oucs:2064"
-    ],
-    "PublicationTimestamp": "1992-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1992"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Constitutions"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Krusch, Barry, 1958-"
-    ],
-    "fulltext": "oai:ota:oucs:2064;2018-03-02T11:01:50Z;http://ota.ox.ac.uk/headers/2064.xml;The 21st century Constitution : a new America for a new millennium / Barry Krusch;Krusch, Barry, 1958-;1992;text_and_corpus_linguistics;Constitutional law--United States;Oxford Text Archive, University of Oxford;Krusch, Barry;(2 files : ca. 683, 778 KB);Text;Constitutions;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e2cc38cb-2676-51d7-b5ae-db8a39ef431f",
-    "oai_identifier": [
-        "oai:ota:oucs:2064"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Constitutional law--United States"
-        }
-    ],
-    "title": [
-        "The 21st century Constitution : a new America for a new millennium / Barry Krusch"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2064.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e30c73b5-6a09-57ee-a197-e08633dfd7fe.json b/oaitestdata/clarin-oai_dc/SET_1/json/e30c73b5-6a09-57ee-a197-e08633dfd7fe.json
deleted file mode 100644
index ac6b1a95..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e30c73b5-6a09-57ee-a197-e08633dfd7fe.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Anna Kie\u0142biewska"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 171",
-        "text/plain"
-    ],
-    "Language": [],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/523",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/523"
-    ],
-    "PID": "http://hdl.handle.net/11321/523",
-    "PublicationTimestamp": "2018-07-13T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Anna Kie\u0142biewska"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "plWordNet",
-        "http://clarin-pl.eu/en/licenses/plwordnet-2/",
-        "PUB"
-    ],
-    "author": [
-        "Kie\u0142biewska, Anna",
-        "Modrzejewska, Ewa"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/523;2018-07-13T13:54:08Z;hdl_11321_3;hdl_11321_4;Korpus testowy - ludzie;Kie\u0142biewska, Anna;Modrzejewska, Ewa;Kie\u0142biewska, Anna;ludzie;retoryka;politycy;Korpus os\u00f3b testowy;2018-07-13;corpus;http://hdl.handle.net/11321/523;polski;plWordNet;http://clarin-pl.eu/en/licenses/plwordnet-2/;PUB;text/plain; charset=utf-8;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;downloadable_files_count: 171;Anna Kie\u0142biewska",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e30c73b5-6a09-57ee-a197-e08633dfd7fe",
-    "notes": [
-        "Korpus os\u00f3b testowy"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/523"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ludzie"
-        },
-        {
-            "name": "retoryka"
-        },
-        {
-            "name": "politycy"
-        }
-    ],
-    "title": [
-        "Korpus testowy - ludzie"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e31c516e-b1ed-5182-91c7-36544859a2b0.json b/oaitestdata/clarin-oai_dc/SET_1/json/e31c516e-b1ed-5182-91c7-36544859a2b0.json
deleted file mode 100644
index ba638516..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e31c516e-b1ed-5182-91c7-36544859a2b0.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3172",
-    "MetadataAccess": [
-        "oai:ota:oucs:3172"
-    ],
-    "PublicationTimestamp": "1534-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1534"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:3172;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3172.xml;Bible. German. trans. Luther.;Die Bibel ;not after: 1534;text_and_corpus_linguistics;Bible. German;deu;Oxford Text Archive, University of Oxford;Triggs, Jeffery;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e31c516e-b1ed-5182-91c7-36544859a2b0",
-    "oai_identifier": [
-        "oai:ota:oucs:3172"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Bible. German"
-        }
-    ],
-    "title": [
-        "Bible. German. trans. Luther.",
-        "Die Bibel "
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3172.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e360d046-b08b-5230-9084-f5e41160171e.json b/oaitestdata/clarin-oai_dc/SET_1/json/e360d046-b08b-5230-9084-f5e41160171e.json
deleted file mode 100644
index 7f13ec89..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e360d046-b08b-5230-9084-f5e41160171e.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Catalan"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-273",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-273"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-273",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-273;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Mercedes;A tool for contrasting terminological vocabularies and textual corpora. It allows controlling the presence and location of reference vocabularies in textual corpora.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-273;cat;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra;http://brangaene.upf.edu/proves/mercedes/indexNetcedes.htm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e360d046-b08b-5230-9084-f5e41160171e",
-    "notes": [
-        "A tool for contrasting terminological vocabularies and textual corpora. It allows controlling the presence and location of reference vocabularies in textual corpora."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-273"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Mercedes"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e364d89a-8971-57c3-a661-2cb7c3e0d21d.json b/oaitestdata/clarin-oai_dc/SET_1/json/e364d89a-8971-57c3-a661-2cb7c3e0d21d.json
deleted file mode 100644
index a797373f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e364d89a-8971-57c3-a661-2cb7c3e0d21d.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/5-UDPIPE-TAGGER",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/5-UDPIPE-TAGGER"
-    ],
-    "PID": "http://hdl.handle.net/11234/5-UDPIPE-TAGGER",
-    "PublicationTimestamp": "2016-02-08T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Straka, Milan"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/5-UDPIPE-TAGGER;2019-01-02T13:45:47Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0023-8C33-2;UDPipe tagger Web Service for Weblicht;Straka, Milan;udpipe;UDPipe is a trainable pipeline for tokenizing, tagging, lemmatizing and parsing Universal Treebanks and other CoNLL-U files (https://lindat.mff.cuni.cz/services/udpipe/);2016-02-08;toolService;http://hdl.handle.net/11234/5-UDPIPE-TAGGER;application/octet-stream;downloadable_files_count: 0;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://hdl.handle.net/11234/5-UDPIPE-TAGGER",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e364d89a-8971-57c3-a661-2cb7c3e0d21d",
-    "notes": [
-        "UDPipe is a trainable pipeline for tokenizing, tagging, lemmatizing and parsing Universal Treebanks and other CoNLL-U files (https://lindat.mff.cuni.cz/services/udpipe/)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/5-UDPIPE-TAGGER"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0023-8C33-2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "udpipe"
-        }
-    ],
-    "title": [
-        "UDPipe tagger Web Service for Weblicht"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e390997e-17ef-5df7-bd43-819e7ddaad67.json b/oaitestdata/clarin-oai_dc/SET_1/json/e390997e-17ef-5df7-bd43-819e7ddaad67.json
deleted file mode 100644
index 5c86ce40..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e390997e-17ef-5df7-bd43-819e7ddaad67.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(3 files : ca. 431, 434, 4.88 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "Middle High German (ca. 1050-1500)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1987",
-    "MetadataAccess": [
-        "oai:ota:oucs:1987"
-    ],
-    "PublicationTimestamp": "1100-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1100"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Sermons"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:1987;2018-04-16T15:24:51Z;http://ota.ox.ac.uk/headers/1987.xml;Altdeutsche Predigten II [Electronic resource]: Die Oberaltaicher Sammlung;1100-1299;text_and_corpus_linguistics;Addresses -- Germany -- 14th century;Sermons -- Germany -- 14th century;gmh;Sermons in Middle High German for the Sundays and solemn feasts of all the liturgical cycles of the year ;Oxford Text Archive, University of Oxford;text/plain;(3 files : ca. 431, 434, 4.88 KB);Text;Sermons;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e390997e-17ef-5df7-bd43-819e7ddaad67",
-    "notes": [
-        "Sermons in Middle High German for the Sundays and solemn feasts of all the liturgical cycles of the year "
-    ],
-    "oai_identifier": [
-        "oai:ota:oucs:1987"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Addresses -- Germany -- th century"
-        },
-        {
-            "name": "Sermons -- Germany -- th century"
-        }
-    ],
-    "title": [
-        "Altdeutsche Predigten II [Electronic resource]: Die Oberaltaicher Sammlung"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1987.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e3a901b2-f24f-522d-a054-0d11771deb72.json b/oaitestdata/clarin-oai_dc/SET_1/json/e3a901b2-f24f-522d-a054-0d11771deb72.json
deleted file mode 100644
index 6dc6fad5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e3a901b2-f24f-522d-a054-0d11771deb72.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Delbecque, Nicole"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 106 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0438",
-    "MetadataAccess": [
-        "oai:ota:oucs:0438"
-    ],
-    "PublicationTimestamp": "1970-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1970"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hampton, Christopher, 1946-"
-    ],
-    "fulltext": "oai:ota:oucs:0438;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0438.xml;The philanthropist. English;The philanthropist : a bourgeois comedy / by Christopher Hampton;Der Menschenfreund;Hampton, Christopher, 1946-;1970;text_and_corpus_linguistics;English drama -- 20th century;Oxford Text Archive, University of Oxford;Delbecque, Nicole;(1 file : ca. 106 KB);Text;Plays;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e3a901b2-f24f-522d-a054-0d11771deb72",
-    "oai_identifier": [
-        "oai:ota:oucs:0438"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- th century"
-        }
-    ],
-    "title": [
-        "The philanthropist. English",
-        "The philanthropist : a bourgeois comedy / by Christopher Hampton",
-        "Der Menschenfreund"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0438.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e3d75dff-2741-5721-9eaf-3d0c968118e9.json b/oaitestdata/clarin-oai_dc/SET_1/json/e3d75dff-2741-5721-9eaf-3d0c968118e9.json
deleted file mode 100644
index be4e5a63..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e3d75dff-2741-5721-9eaf-3d0c968118e9.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "University of West Bohemia, Department of Cybernetics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/xml",
-        "text/plain",
-        "downloadable_files_count: 2"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2585",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2585"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2585",
-    "PublicationTimestamp": "2017-12-12T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "University of West Bohemia, Department of Cybernetics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Tihelka, Daniel",
-        "Matou\u0161ek, Jind\u0159ich",
-        "J\u016fzov\u00e1, Mark\u00e9ta"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2585;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;High-Coverage Multi-Level Text Corpus for Non-Professional Voice Conservation;J\u016fzov\u00e1, Mark\u00e9ta;Tihelka, Daniel;Matou\u0161ek, Jind\u0159ich;text-to-speech (TTS);voice conservation;voice banking;text corpus;This text corpus contains a carefully optimized set of sentences that could be used in the process of preparing a speech corpus for the development of personalized text-to-speech system. It was designed primarily for the voice conservation procedure that must be performed in a relatively short period before a person loses his/her own voice, typically because of the total laryngectomy.\r\n\r\nTotal laryngectomy is a radical treatment procedure which is often unavoidable to save life of patients who were diagnosed with severe laryngeal cancer. In spite of being very effective with respect to the primary treatment, it significantly handicaps the patients due to the permanent loss of their ability to use voice and produce speech. Luckily, the modern methods of computer text-to-speech (TTS) synthesis offer a possibility for \"digital conservation\" of patient's original voice for his/her future speech communication -- a procedure called voice banking or voice conservation. Moreover, the banking procedure can be undertaken by any person facing voice degradation or loss in farther future, or who is simply is willing to keep his/her voice-print.;2017-12-12;corpus;http://hdl.handle.net/11234/1-2585;ces;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;text/plain;text/xml;text/plain; charset=utf-8;downloadable_files_count: 2;University of West Bohemia, Department of Cybernetics",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e3d75dff-2741-5721-9eaf-3d0c968118e9",
-    "notes": [
-        "This text corpus contains a carefully optimized set of sentences that could be used in the process of preparing a speech corpus for the development of personalized text-to-speech system. It was designed primarily for the voice conservation procedure that must be performed in a relatively short period before a person loses his/her own voice, typically because of the total laryngectomy.\r\n\r\nTotal laryngectomy is a radical treatment procedure which is often unavoidable to save life of patients who were diagnosed with severe laryngeal cancer. In spite of being very effective with respect to the primary treatment, it significantly handicaps the patients due to the permanent loss of their ability to use voice and produce speech. Luckily, the modern methods of computer text-to-speech (TTS) synthesis offer a possibility for \"digital conservation\" of patient's original voice for his/her future speech communication -- a procedure called voice banking or voice conservation. Moreover, the banking procedure can be undertaken by any person facing voice degradation or loss in farther future, or who is simply is willing to keep his/her voice-print."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2585"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "text-to-speech TTS"
-        },
-        {
-            "name": "voice conservation"
-        },
-        {
-            "name": "voice banking"
-        },
-        {
-            "name": "text corpus"
-        }
-    ],
-    "title": [
-        "High-Coverage Multi-Level Text Corpus for Non-Professional Voice Conservation"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e3e2615a-0760-5418-a3c2-65be18ec0703.json b/oaitestdata/clarin-oai_dc/SET_1/json/e3e2615a-0760-5418-a3c2-65be18ec0703.json
deleted file mode 100644
index 6d5b18f5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e3e2615a-0760-5418-a3c2-65be18ec0703.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/csv",
-        "text/plain; charset=utf-8",
-        "text/plain",
-        "downloadable_files_count: 2"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1188",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1188"
-    ],
-    "PID": "http://hdl.handle.net/11356/1188",
-    "PublicationTimestamp": "2018-06-15T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/H2020/640772"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "https://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Mozeti\u010d, Igor",
-        "de Amicis, Luisa",
-        "Kralj Novak, Petra"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1188;2018-07-05T06:46:55Z;hdl_11356_1023;hdl_11356_1024;Tweets about impact investing;Kralj Novak, Petra;de Amicis, Luisa;Mozeti\u010d, Igor;Twitter;impact investing;social finance;The corpus contains 668,529 tweets (tweet IDs) relevant to \"impact investing\", accompanied by sentiment labels given by an automated sentiment classifier.\r\n\r\nImpact investing involves investments made into companies, organizations, and funds with the intention to generate social and environmental impact alongside a financial return. The tweets relevant to impact investing were collected in the period from March 28, 2017, to January 28, 2018, through the Twitter Search API, and annotated for sentiment labels \"Negative\", \"Neutral\" or \"Positive\" by a general-purpose English language sentiment classifier.\r\n\r\nThe tweets were collected based on a list of known impact investing Twitter users, relevant keywords and impact investing related events. In particular, the queries include relevant users (@YF_Academy, @esmeefairbairn, @resonanceltd, @Big PotentialSI, etc.), single hashtags (#socfin, #impinv #socialfinance, #impactinvestment, etc.),\r\ncombined hashtags (#social & #finance, #social & #investment, #impact & #assessment, etc.), and hashtags of major impact investing events (#impact2, #socap17, #OxfordIIP, #skollwf, etc.).;2018-06-15;corpus;http://hdl.handle.net/11356/1188;eng;info:eu-repo/grantAgreement/EC/H2020/640772;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);https://creativecommons.org/licenses/by-sa/4.0/;PUB;text/csv;text/plain;text/plain; charset=utf-8;downloadable_files_count: 2;Jo\u017eef Stefan Institute",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e3e2615a-0760-5418-a3c2-65be18ec0703",
-    "notes": [
-        "The corpus contains 668,529 tweets (tweet IDs) relevant to \"impact investing\", accompanied by sentiment labels given by an automated sentiment classifier.\r\n\r\nImpact investing involves investments made into companies, organizations, and funds with the intention to generate social and environmental impact alongside a financial return. The tweets relevant to impact investing were collected in the period from March 28, 2017, to January 28, 2018, through the Twitter Search API, and annotated for sentiment labels \"Negative\", \"Neutral\" or \"Positive\" by a general-purpose English language sentiment classifier.\r\n\r\nThe tweets were collected based on a list of known impact investing Twitter users, relevant keywords and impact investing related events. In particular, the queries include relevant users (@YF_Academy, @esmeefairbairn, @resonanceltd, @Big PotentialSI, etc.), single hashtags (#socfin, #impinv #socialfinance, #impactinvestment, etc.),\r\ncombined hashtags (#social & #finance, #social & #investment, #impact & #assessment, etc.), and hashtags of major impact investing events (#impact2, #socap17, #OxfordIIP, #skollwf, etc.)."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1188"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Twitter"
-        },
-        {
-            "name": "impact investing"
-        },
-        {
-            "name": "social finance"
-        }
-    ],
-    "title": [
-        "Tweets about impact investing"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e3ecc07c-381e-5caf-ab53-167755357de5.json b/oaitestdata/clarin-oai_dc/SET_1/json/e3ecc07c-381e-5caf-ab53-167755357de5.json
deleted file mode 100644
index 296c9451..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e3ecc07c-381e-5caf-ab53-167755357de5.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 174 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2284",
-    "MetadataAccess": [
-        "oai:ota:oucs:2284"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Beaumont, Francis, 1584-1616",
-        "Fletcher, John, 1579-1625"
-    ],
-    "fulltext": "oai:ota:oucs:2284;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/2284.xml;Demetrius and Enanthe;Fletcher, John, 1579-1625;Beaumont, Francis, 1584-1616;default: 1976-01-01;text_and_corpus_linguistics;Plays -- England -- 17th century;Comedies -- England -- 17th century;eng;Oxford Text Archive, University of Oxford;(1 file : ca. 174 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e3ecc07c-381e-5caf-ab53-167755357de5",
-    "oai_identifier": [
-        "oai:ota:oucs:2284"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        },
-        {
-            "name": "Comedies -- England -- th century"
-        }
-    ],
-    "title": [
-        "Demetrius and Enanthe"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2284.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e3fb5617-6666-53a2-a75c-7e9c44ff0e69.json b/oaitestdata/clarin-oai_dc/SET_1/json/e3fb5617-6666-53a2-a75c-7e9c44ff0e69.json
deleted file mode 100644
index a571e08c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e3fb5617-6666-53a2-a75c-7e9c44ff0e69.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, Dept. of Swedish Language, G\u00f6teborg University"
-    ],
-    "Contributor": [
-        "Forsberg, Markus"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1172",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1172"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1172",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, Dept. of Swedish Language, G\u00f6teborg University"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Sweden"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1172;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;BNF Converter;Forsberg, Markus;compiler construction;grammar;The BNF Converter is a compiler construction tool generating a compiler front-end from a Labelled BNF grammar.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1172;downloadable_files_count: 0;Sweden;Spr\u00e5kbanken, Dept. of Swedish Language, G\u00f6teborg University;http://bnfc.digitalgrammars.com/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e3fb5617-6666-53a2-a75c-7e9c44ff0e69",
-    "notes": [
-        "The BNF Converter is a compiler construction tool generating a compiler front-end from a Labelled BNF grammar."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1172"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "compiler construction"
-        },
-        {
-            "name": "grammar"
-        }
-    ],
-    "title": [
-        "BNF Converter"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e4126ecd-adbc-5286-b790-9af8b4778f1a.json b/oaitestdata/clarin-oai_dc/SET_1/json/e4126ecd-adbc-5286-b790-9af8b4778f1a.json
deleted file mode 100644
index 43be39e5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e4126ecd-adbc-5286-b790-9af8b4778f1a.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=f94c95eccf2a11e1a404080027e73ea21c554786f12a4d30b7bb752af7f8a917",
-    "MetadataAccess": [
-        "f94c95eccf2a11e1a404080027e73ea21c554786f12a4d30b7bb752af7f8a917"
-    ],
-    "PublicationTimestamp": "2012-07-25T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "fulltext": "f94c95eccf2a11e1a404080027e73ea21c554786f12a4d30b7bb752af7f8a917;2019-02-27T12:09:06Z;lexicalConceptualResource;lexicalConceptualResource:lexicon;MWN.PT - MultiWordnet du portugais \n;MWN.PT - MultiWordnet du portugais (version 1) contient plus de 17200 concepts valid\u00c3\u00a9s manuellement (synsets), reli\u00c3\u00a9s par relations s\u00c3\u00a9mantiques d\u00e2\u0080\u0099hyponymie ou d\u00e2\u0080\u0099hyperonymie. Ces concepts sont constitu\u00c3\u00a9s de plus de 21000 sens/formes de mots et 16000 lemmes de variantes europ\u00c3\u00a9ennes et am\u00c3\u00a9ricaines du portugais. Ils sont align\u00c3\u00a9s de fa\u00c3\u00a7on translationnelle aux concepts \u00c3\u00a9quivalents du WordNet anglais de Princeton et de fa\u00c3\u00a7on transitive aux concepts des MultiWordNets italien, espagnol, h\u00c3\u00a9breu, roumain et latin. Il peut \u00c3\u00aatre consult\u00c3\u00a9 en ligne sur : http://mwnpt.di.fc.ul.pt.MWN.PT comprend les sous-ontologies d\u00c3\u00a9finies sous les concepts de Personne, Organisation, Ev\u00c3\u00a9nement, Lieux et Art, qui sont couverts par l\u00e2\u0080\u0099ontologie sup\u00c3\u00a9rieure constitu\u00c3\u00a9e des \u00c3\u00a9quivalents portugais de tous les concepts pr\u00c3\u00a9sents dans les 4 niveaux sup\u00c3\u00a9rieurs du WordNet anglais de Princeton et des 98 concepts de base propos\u00c3\u00a9s par la Global Wordnet Association, ainsi que des 164 concepts de base (Core Base Concepts) d\u00c3\u00a9finis dans le projet EuroWordNet.\n;2012-07-25",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e4126ecd-adbc-5286-b790-9af8b4778f1a",
-    "notes": [
-        "MWN.PT - MultiWordnet du portugais (version 1) contient plus de 17200 concepts valid\u00c3\u00a9s manuellement (synsets), reli\u00c3\u00a9s par relations s\u00c3\u00a9mantiques d\u00e2\u0080\u0099hyponymie ou d\u00e2\u0080\u0099hyperonymie. Ces concepts sont constitu\u00c3\u00a9s de plus de 21000 sens/formes de mots et 16000 lemmes de variantes europ\u00c3\u00a9ennes et am\u00c3\u00a9ricaines du portugais. Ils sont align\u00c3\u00a9s de fa\u00c3\u00a7on translationnelle aux concepts \u00c3\u00a9quivalents du WordNet anglais de Princeton et de fa\u00c3\u00a7on transitive aux concepts des MultiWordNets italien, espagnol, h\u00c3\u00a9breu, roumain et latin. Il peut \u00c3\u00aatre consult\u00c3\u00a9 en ligne sur : http://mwnpt.di.fc.ul.pt.MWN.PT comprend les sous-ontologies d\u00c3\u00a9finies sous les concepts de Personne, Organisation, Ev\u00c3\u00a9nement, Lieux et Art, qui sont couverts par l\u00e2\u0080\u0099ontologie sup\u00c3\u00a9rieure constitu\u00c3\u00a9e des \u00c3\u00a9quivalents portugais de tous les concepts pr\u00c3\u00a9sents dans les 4 niveaux sup\u00c3\u00a9rieurs du WordNet anglais de Princeton et des 98 concepts de base propos\u00c3\u00a9s par la Global Wordnet Association, ainsi que des 164 concepts de base (Core Base Concepts) d\u00c3\u00a9finis dans le projet EuroWordNet.\n"
-    ],
-    "oai_identifier": [
-        "f94c95eccf2a11e1a404080027e73ea21c554786f12a4d30b7bb752af7f8a917"
-    ],
-    "oai_set": [
-        "lexicalConceptualResource",
-        "lexicalConceptualResource:lexicon"
-    ],
-    "state": "active",
-    "title": [
-        "MWN.PT - MultiWordnet du portugais \n"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e45f5abf-c846-5910-9f98-05e3e7faf6a0.json b/oaitestdata/clarin-oai_dc/SET_1/json/e45f5abf-c846-5910-9f98-05e3e7faf6a0.json
deleted file mode 100644
index d9132170..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e45f5abf-c846-5910-9f98-05e3e7faf6a0.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "SentiOne"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/gzip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/633",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/633"
-    ],
-    "PID": "http://hdl.handle.net/11321/633",
-    "PublicationTimestamp": "2018-09-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "SentiOne"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Oleksy, Marcin",
-        "Walentynowicz, Wiktor"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/633;2019-03-20T10:26:21Z;hdl_11321_3;hdl_11321_4;Tagger SentiOne - version 1;Walentynowicz, Wiktor;Oleksy, Marcin;morpho-syntactic tagging;The SentiOne tagger is a tagger for the Polish language adapted to processing of user-generated content. It was trained on the Polish UGC-corpus (prepared within the same research project and soon to become available in the CLARIN repository).;2018-09-01;toolService;http://hdl.handle.net/11321/633;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain; charset=utf-8;application/gzip;downloadable_files_count: 1;SentiOne;https://sentione.com/knowledge/eu-research-project",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e45f5abf-c846-5910-9f98-05e3e7faf6a0",
-    "notes": [
-        "The SentiOne tagger is a tagger for the Polish language adapted to processing of user-generated content. It was trained on the Polish UGC-corpus (prepared within the same research project and soon to become available in the CLARIN repository)."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/633"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morpho-syntactic tagging"
-        }
-    ],
-    "title": [
-        "Tagger SentiOne - version 1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e476a2f0-5405-5dc4-bf57-9a20bd4ca1b2.json b/oaitestdata/clarin-oai_dc/SET_1/json/e476a2f0-5405-5dc4-bf57-9a20bd4ca1b2.json
deleted file mode 100644
index 73b33a85..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e476a2f0-5405-5dc4-bf57-9a20bd4ca1b2.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Dygasi\u0144ski"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 4",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/73",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/73"
-    ],
-    "PID": "http://hdl.handle.net/11321/73",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Dygasi\u0144ski"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Dygasi\u0144ski, Dygasi\u0144ski"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/73;2015-04-14T12:55:36Z;hdl_11321_3;hdl_11321_4;MWE Dygasi\u0144ski;Dygasi\u0144ski, Dygasi\u0144ski;Dygasi\u0144ski;2015-04-08;corpus;http://hdl.handle.net/11321/73;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;application/zip;text/plain; charset=utf-8;downloadable_files_count: 4;Dygasi\u0144ski",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e476a2f0-5405-5dc4-bf57-9a20bd4ca1b2",
-    "notes": [
-        "Dygasi\u0144ski"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/73"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Dygasi\u0144ski"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e47cd7e2-58e2-5fe7-96e8-bf9dedeb8e7f.json b/oaitestdata/clarin-oai_dc/SET_1/json/e47cd7e2-58e2-5fe7-96e8-bf9dedeb8e7f.json
deleted file mode 100644
index 7e4ede6e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e47cd7e2-58e2-5fe7-96e8-bf9dedeb8e7f.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Jezuit\u00f3w"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-163686",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-163686"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CE9-A",
-    "PublicationTimestamp": "1721-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1721"
-    ],
-    "Publisher": [
-        "Drukarnia Jezuit\u00f3w"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/163686",
-        "oai:jbc.bj.uj.edu.pl:publication:172065"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1701/1800"
-    ],
-    "TempCoverageBegin": 53662478399,
-    "TempCoverageEnd": 53662478399,
-    "TemporalCoverage": " point in time : 1701-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1701-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1701-07-01T11:59:59Z",
-    "author": [
-        "Kowalicki, Franciszek (1668-1730)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-163686;2019-02-28T18:47:48Z;Kaznodzieia Odswi\u0119tny Abo Kazania Doroczne Na Dni Swi\u0119tych Bozych Uroczyste Krolowy Wszystkich Swi\u0119tych Posw\u0119cone. Roku Panskiego 1721. Od X. Franciszka Kowalickiego Soc: Jesu.;Kowalicki, Franciszek (1668-1730);starodruki 18\u00a0w.;Sulimirski, Piotr (16..-17..). [Adr. ded.];Drukarnia Jezuit\u00f3w;[1721];starodruk;application/xml;clarind-uds:poldilemma-163686;hdl:11858/00-246C-0000-0023-8CE9-A;Biblioteka Jagiello\u0144ska, BJ St. Dr. 586841 I;pol;lat;http://jbc.bj.uj.edu.pl/Content/163686;oai:jbc.bj.uj.edu.pl:publication:172065;1701/1800;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e47cd7e2-58e2-5fe7-96e8-bf9dedeb8e7f",
-    "notes": [
-        "Sulimirski, Piotr (16..-17..). [Adr. ded.]"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-163686"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Kaznodzieia Odswi\u0119tny Abo Kazania Doroczne Na Dni Swi\u0119tych Bozych Uroczyste Krolowy Wszystkich Swi\u0119tych Posw\u0119cone. Roku Panskiego 1721. Od X. Franciszka Kowalickiego Soc: Jesu."
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e48886f1-166e-5d7b-b9ce-92e1559de631.json b/oaitestdata/clarin-oai_dc/SET_1/json/e48886f1-166e-5d7b-b9ce-92e1559de631.json
deleted file mode 100644
index 654f0bf5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e48886f1-166e-5d7b-b9ce-92e1559de631.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "MPW"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 86",
-        "text/plain; charset=utf-8",
-        "text/plain"
-    ],
-    "Language": [],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/521",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/521"
-    ],
-    "PID": "http://hdl.handle.net/11321/521",
-    "PublicationTimestamp": "2018-07-07T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "MPW"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "BSD 2 Clause",
-        "https://opensource.org/licenses/BSD-2-Clause",
-        "PUB"
-    ],
-    "author": [
-        "Modrzejewska, Ewa"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/521;2018-07-13T13:52:00Z;hdl_11321_3;hdl_11321_4;Testowy MPW;Modrzejewska, Ewa;political discourse;polityka;europarlament;Wypowiedzi europos\u0142\u00f3w;2018-07-07;corpus;http://hdl.handle.net/11321/521;polski;BSD 2 Clause;https://opensource.org/licenses/BSD-2-Clause;PUB;text/plain; charset=utf-8;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;downloadable_files_count: 86;MPW",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e48886f1-166e-5d7b-b9ce-92e1559de631",
-    "notes": [
-        "Wypowiedzi europos\u0142\u00f3w"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/521"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "political discourse"
-        },
-        {
-            "name": "polityka"
-        },
-        {
-            "name": "europarlament"
-        }
-    ],
-    "title": [
-        "Testowy MPW"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e493bf37-fd70-5bf8-94e5-e68fd850cb90.json b/oaitestdata/clarin-oai_dc/SET_1/json/e493bf37-fd70-5bf8-94e5-e68fd850cb90.json
deleted file mode 100644
index 32df01a1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e493bf37-fd70-5bf8-94e5-e68fd850cb90.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5386",
-    "MetadataAccess": [
-        "oai:ota:oucs:5386"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Whiston, William, 1667-1752."
-    ],
-    "fulltext": "oai:ota:oucs:5386;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5386.xml;The cause of the deluge demonstrated;Whiston, William, 1667-1752.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e493bf37-fd70-5bf8-94e5-e68fd850cb90",
-    "oai_identifier": [
-        "oai:ota:oucs:5386"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The cause of the deluge demonstrated"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5386.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e4eef863-47d6-523b-8247-073baad59304.json b/oaitestdata/clarin-oai_dc/SET_1/json/e4eef863-47d6-523b-8247-073baad59304.json
deleted file mode 100644
index f7ac1830..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e4eef863-47d6-523b-8247-073baad59304.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "s.n."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-85903",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-85903"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D3D-4",
-    "PublicationTimestamp": "1786-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1786"
-    ],
-    "Publisher": [
-        "s.n."
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/85903",
-        "oai:jbc.bj.uj.edu.pl:publication:92549"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-85903;2019-03-01T17:50:56Z;Kamie\u0144 W\u0119gielny Na Ko\u015bcio\u0142 Staraniem Y Nak\u0142adem JJ. W. W. Stanis\u0142awa Y Rozalii M\u0119ci\u0144skich Starostwa Wielu\u0144skich Zak\u0142adany w Dzia\u0142oszynie 1786;starodruki 18\u00a0w.;s.n.;[1786];starodruk;application/xml;clarind-uds:poldilemma-85903;hdl:11858/00-246C-0000-0023-8D3D-4;Biblioteka Jagiello\u0144ska, BJ St. Dr. 3196 II;pol;lat;http://jbc.bj.uj.edu.pl/Content/85903;oai:jbc.bj.uj.edu.pl:publication:92549;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e4eef863-47d6-523b-8247-073baad59304",
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-85903"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Kamie\u0144 W\u0119gielny Na Ko\u015bcio\u0142 Staraniem Y Nak\u0142adem JJ. W. W. Stanis\u0142awa Y Rozalii M\u0119ci\u0144skich Starostwa Wielu\u0144skich Zak\u0142adany w Dzia\u0142oszynie 1786"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e4f45d29-4c72-577e-9b5f-8d738e11401a.json b/oaitestdata/clarin-oai_dc/SET_1/json/e4f45d29-4c72-577e-9b5f-8d738e11401a.json
deleted file mode 100644
index 627b5f09..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e4f45d29-4c72-577e-9b5f-8d738e11401a.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4909-7",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4909-7"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-4909-7",
-    "PublicationTimestamp": "2008-10-02T11:59:59Z",
-    "PublicationYear": [
-        "2008"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Klyueva, Natalia",
-        "Bojar, Ond\u0159ej"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4909-7;2017-11-09T14:20:27Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;UMC 0.1: Czech-Russian-English Multilingual Corpus;Klyueva, Natalia;Bojar, Ond\u0159ej;multi-language corpus;UMC 0.1 Czech-English-Russian is a multilingual parallel corpus of texts in Czech, Russian and English languages with automatic pairwise sentence alignments. The primary aim of UMC is to extend the set of languages covered by the corpus CzEng mainly for the purposes of machine translation.\r\n\r\nAll the texts were downloaded from a single source \u2014 The Project Syndicate (Copyright: Project Syndicate 1995-2008), which contains a huge collection of high-quality news articles and commentaries. We were given the permission to use the texts for research and non-commercial purposes.;2008-10-02;corpus;http://hdl.handle.net/11858/00-097C-0000-0001-4909-7;ces;Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0);http://creativecommons.org/licenses/by-nc-nd/3.0/;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/umc/cer",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e4f45d29-4c72-577e-9b5f-8d738e11401a",
-    "notes": [
-        "UMC 0.1 Czech-English-Russian is a multilingual parallel corpus of texts in Czech, Russian and English languages with automatic pairwise sentence alignments. The primary aim of UMC is to extend the set of languages covered by the corpus CzEng mainly for the purposes of machine translation.\r\n\r\nAll the texts were downloaded from a single source \u2014 The Project Syndicate (Copyright: Project Syndicate 1995-2008), which contains a huge collection of high-quality news articles and commentaries. We were given the permission to use the texts for research and non-commercial purposes."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-4909-7"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "multi-language corpus"
-        }
-    ],
-    "title": [
-        "UMC 0.1: Czech-Russian-English Multilingual Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e5014212-de74-526d-853e-c96e97b1f7d8.json b/oaitestdata/clarin-oai_dc/SET_1/json/e5014212-de74-526d-853e-c96e97b1f7d8.json
deleted file mode 100644
index 0021b5e3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e5014212-de74-526d-853e-c96e97b1f7d8.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "text/plain",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/324",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/324"
-    ],
-    "PID": "http://hdl.handle.net/11321/324",
-    "PublicationTimestamp": "2014-02-26T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0)",
-        "http://creativecommons.org/licenses/by-sa/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Jakubaszek, Maja",
-        "Piasecki, Dominik",
-        "Pilarska, Aleksandra",
-        "Radziszewski, Adam",
-        "Marci\u0144czuk, Micha\u0142",
-        "Tokarczyk, Barbara",
-        "Rychlikowski, Pawe\u0142",
-        "Burdka, \u0141ukasz",
-        "Juros, Agata",
-        "Zi\u0119ba, Tomasz",
-        "Piasecki, Maciej",
-        "Hry\u0144czak, Justyna",
-        "Ptak, Marcin"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/324;2016-10-20T10:13:13Z;hdl_11321_3;hdl_11321_4;Pytania i odpowiedzi z serwisu wikipedyjnego \"Czy wiesz\", wersja 2.0;Burdka, \u0141ukasz;Hry\u0144czak, Justyna;Jakubaszek, Maja;Juros, Agata;Marci\u0144czuk, Micha\u0142;Piasecki, Dominik;Piasecki, Maciej;Pilarska, Aleksandra;Ptak, Marcin;Radziszewski, Adam;Rychlikowski, Pawe\u0142;Tokarczyk, Barbara;Zi\u0119ba, Tomasz;question answering;QA;Zbi\u00f3r wzbogacono o oznaczenie konkretnych fragment\u00f3w zawieraj\u0105cych odpowied\u017a na wskazane pytania.\r\nWszystkie wskazane fragmenty zosta\u0142y zweryfikowane przez cz\u0142owieka. Niekt\u00f3rym pytaniom przypisano wiele fragment\u00f3w.\r\n\r\nCelem zbioru jest testowanie i rozw\u00f3j system\u00f3w typu Question Answering dla j\u0119zyka polskiego.\r\nLiczymy na to, \u017ce dzi\u0119ki udost\u0119pnieniu zar\u00f3wno pyta\u0144, jak i ca\u0142ej kolekcji testowej (ca\u0142ej Wikipedii z wybranego zrzutu), mo\u017cliwe b\u0119dzie przeprowadzenie r\u00f3\u017cnych eksperyment\u00f3w w tych samych warunkach, dzi\u0119ki czemu wyniki b\u0119d\u0105 ze sob\u0105 bezpo\u015brednio por\u00f3wnywalne.\r\n\r\nZbi\u00f3r udost\u0119pniany jest na licencji Creative Commons Uznanie Autorstwa, na tych samych warunkach 3.0 (CC-BY-SA 3.0).;2014-02-26;corpus;http://hdl.handle.net/11321/324;pol;Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0);http://creativecommons.org/licenses/by-sa/3.0/;CC;text/plain; charset=utf-8;application/zip;text/plain;downloadable_files_count: 2;Wroc\u0142aw University of Science and Technology;http://nlp.pwr.wroc.pl/narzedzia-i-zasoby/zasoby/zbior-pytan-i-odpowiedzi-czy-wiesz",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e5014212-de74-526d-853e-c96e97b1f7d8",
-    "notes": [
-        "Zbi\u00f3r wzbogacono o oznaczenie konkretnych fragment\u00f3w zawieraj\u0105cych odpowied\u017a na wskazane pytania.\r\nWszystkie wskazane fragmenty zosta\u0142y zweryfikowane przez cz\u0142owieka. Niekt\u00f3rym pytaniom przypisano wiele fragment\u00f3w.\r\n\r\nCelem zbioru jest testowanie i rozw\u00f3j system\u00f3w typu Question Answering dla j\u0119zyka polskiego.\r\nLiczymy na to, \u017ce dzi\u0119ki udost\u0119pnieniu zar\u00f3wno pyta\u0144, jak i ca\u0142ej kolekcji testowej (ca\u0142ej Wikipedii z wybranego zrzutu), mo\u017cliwe b\u0119dzie przeprowadzenie r\u00f3\u017cnych eksperyment\u00f3w w tych samych warunkach, dzi\u0119ki czemu wyniki b\u0119d\u0105 ze sob\u0105 bezpo\u015brednio por\u00f3wnywalne.\r\n\r\nZbi\u00f3r udost\u0119pniany jest na licencji Creative Commons Uznanie Autorstwa, na tych samych warunkach 3.0 (CC-BY-SA 3.0)."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/324"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "question answering"
-        },
-        {
-            "name": "QA"
-        }
-    ],
-    "title": [
-        "Pytania i odpowiedzi z serwisu wikipedyjnego \"Czy wiesz\", wersja 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e510eb62-6183-52f4-9925-31e1a4433875.json b/oaitestdata/clarin-oai_dc/SET_1/json/e510eb62-6183-52f4-9925-31e1a4433875.json
deleted file mode 100644
index ef007d75..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e510eb62-6183-52f4-9925-31e1a4433875.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 143 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1897",
-    "MetadataAccess": [
-        "oai:ota:oucs:1897"
-    ],
-    "PublicationTimestamp": "1910-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1910"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:1897;2018-04-16T11:05:16Z;http://ota.ox.ac.uk/headers/1897.xml;Beowulf;1910;text_and_corpus_linguistics;Poems -- England -- 6th-10th century period;Romances -- England -- 6th-10th century period;Gesta -- England -- 6th-10th century period;Translations -- United States -- 20th century;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 143 KB);Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e510eb62-6183-52f4-9925-31e1a4433875",
-    "oai_identifier": [
-        "oai:ota:oucs:1897"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- England -- th-th century period"
-        },
-        {
-            "name": "Romances -- England -- th-th century period"
-        },
-        {
-            "name": "Gesta -- England -- th-th century period"
-        },
-        {
-            "name": "Translations -- United States -- th century"
-        }
-    ],
-    "title": [
-        "Beowulf"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1897.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e51cbf25-1d41-556b-ba2e-64564cb9e463.json b/oaitestdata/clarin-oai_dc/SET_1/json/e51cbf25-1d41-556b-ba2e-64564cb9e463.json
deleted file mode 100644
index 096987b9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e51cbf25-1d41-556b-ba2e-64564cb9e463.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/gzip",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/255",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/255"
-    ],
-    "PID": "http://hdl.handle.net/11321/255",
-    "PublicationTimestamp": "2016-04-30T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "Patejuk, Agnieszka"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/255;2016-05-05T12:22:01Z;hdl_11321_3;hdl_11321_4;POLFIE Bank, an LFG structure bank of Polish: pol-nkjp1m-pargram-dev;Patejuk, Agnieszka;syntax;LFG;Polish;treebank;parsebank;The pol-nkjp1m-pargram-dev structure bank was created using POLFIE: an LFG grammar of Polish. This structure bank contains sentences from the NKJP1M subcorpus of NKJP which were not included in Sk\u0142adnica treebank.\r\n\r\nThe pol-nkjp1m-pargram-dev structure bank can be accessed via INESS treebanking system in two ways:\r\n\u2022 use the direct link: http://clarino.uib.no/iness/lfg-sentences?&treebank=pol-nkjp1m-pargram-dev\r\n\u2022 go to http://iness.uib.no --> choose \"Treebank Selection\" in the menu on the left-hand side --> choose \"POLFIE\" in \"Treebank Collections\" --> choose pol-nkjp1m-pargram-dev;2016-04-30;corpus;http://hdl.handle.net/11321/255;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;application/gzip;downloadable_files_count: 1;Institute of Computer Science, Polish Academy of Sciences;http://zil.ipipan.waw.pl/LFG",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e51cbf25-1d41-556b-ba2e-64564cb9e463",
-    "notes": [
-        "The pol-nkjp1m-pargram-dev structure bank was created using POLFIE: an LFG grammar of Polish. This structure bank contains sentences from the NKJP1M subcorpus of NKJP which were not included in Sk\u0142adnica treebank.\r\n\r\nThe pol-nkjp1m-pargram-dev structure bank can be accessed via INESS treebanking system in two ways:\r\n\u2022 use the direct link: http://clarino.uib.no/iness/lfg-sentences?&treebank=pol-nkjp1m-pargram-dev\r\n\u2022 go to http://iness.uib.no --> choose \"Treebank Selection\" in the menu on the left-hand side --> choose \"POLFIE\" in \"Treebank Collections\" --> choose pol-nkjp1m-pargram-dev"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/255"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "syntax"
-        },
-        {
-            "name": "LFG"
-        },
-        {
-            "name": "Polish"
-        },
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "parsebank"
-        }
-    ],
-    "title": [
-        "POLFIE Bank, an LFG structure bank of Polish: pol-nkjp1m-pargram-dev"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e53b2f21-b62f-5d35-928d-4ace48025d73.json b/oaitestdata/clarin-oai_dc/SET_1/json/e53b2f21-b62f-5d35-928d-4ace48025d73.json
deleted file mode 100644
index 9df38c43..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e53b2f21-b62f-5d35-928d-4ace48025d73.json
+++ /dev/null
@@ -1,94 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-4337-2",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-4337-2"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-4337-2",
-    "PublicationTimestamp": "2014-02-13T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11858/00-097C-0000-0015-8DAF-4"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Cinkov\u00e1, Silvie",
-        "\u0160indlerov\u00e1, Jana",
-        "Haji\u010d, Jan",
-        "Fu\u010d\u00edkov\u00e1, Eva"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-4337-2;2018-05-24T09:46:59Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;EngVallex - English Valency Lexicon;Cinkov\u00e1, Silvie;Fu\u010d\u00edkov\u00e1, Eva;\u0160indlerov\u00e1, Jana;Haji\u010d, Jan;Annotations;Corpora;Data;Lexicons;Monolingual;Semantics;Valency;EngVallex is the English counterpart of the PDT-Vallex valency lexicon, using the same view of valency, valency frames and the description of a surface form of verbal arguments. EngVallex contains links also to PropBank and Verbnet, two existing English predicate-argument lexicons used, i.a., for the PropBank project. The EngVallex lexicon is fully linked to the English side of the PCEDT parallel treebank, which is in fact the PTB re-annotated using the Prague Dependency Treebank style of annotation. The EngVallex is available in an XML format in our repository, and also in a searchable form with examples from the PCEDT.;2014-02-13;lexicalConceptualResource;http://hdl.handle.net/11858/00-097C-0000-0023-4337-2;eng;http://hdl.handle.net/11858/00-097C-0000-0015-8DAF-4;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://lindat.mff.cuni.cz/services/EngVallex/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e53b2f21-b62f-5d35-928d-4ace48025d73",
-    "notes": [
-        "EngVallex is the English counterpart of the PDT-Vallex valency lexicon, using the same view of valency, valency frames and the description of a surface form of verbal arguments. EngVallex contains links also to PropBank and Verbnet, two existing English predicate-argument lexicons used, i.a., for the PropBank project. The EngVallex lexicon is fully linked to the English side of the PCEDT parallel treebank, which is in fact the PTB re-annotated using the Prague Dependency Treebank style of annotation. The EngVallex is available in an XML format in our repository, and also in a searchable form with examples from the PCEDT."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-4337-2"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Annotations"
-        },
-        {
-            "name": "Corpora"
-        },
-        {
-            "name": "Data"
-        },
-        {
-            "name": "Lexicons"
-        },
-        {
-            "name": "Monolingual"
-        },
-        {
-            "name": "Semantics"
-        },
-        {
-            "name": "Valency"
-        }
-    ],
-    "title": [
-        "EngVallex - English Valency Lexicon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e5b38333-c78f-506a-9d7e-52b4c6ddec2f.json b/oaitestdata/clarin-oai_dc/SET_1/json/e5b38333-c78f-506a-9d7e-52b4c6ddec2f.json
deleted file mode 100644
index b177ae61..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e5b38333-c78f-506a-9d7e-52b4c6ddec2f.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1005",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1005"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1005",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1005;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LAC Jalonke Corpus;Language and Cognition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1005;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI28418%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e5b38333-c78f-506a-9d7e-52b4c6ddec2f",
-    "notes": [
-        "Language and Cognition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1005"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LAC Jalonke Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e5b5d5f0-acc3-544a-9fc5-73d97ba4d6df.json b/oaitestdata/clarin-oai_dc/SET_1/json/e5b5d5f0-acc3-544a-9fc5-73d97ba4d6df.json
deleted file mode 100644
index f9144fd9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e5b5d5f0-acc3-544a-9fc5-73d97ba4d6df.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Czech",
-        "English",
-        "Russian",
-        "Ukrainian",
-        "French",
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1451",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1451"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1451",
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/288487"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "C\u00edfka, Ond\u0159ej",
-        "Bojar, Ond\u0159ej",
-        "Tamchyna, Ale\u0161",
-        "Pecina, Pavel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1451;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Moses Web Demo;Bojar, Ond\u0159ej;C\u00edfka, Ond\u0159ej;Pecina, Pavel;Tamchyna, Ale\u0161;machine translation;web service;demo;An interactive web demo of selected \u00daFAL MT systems.;2014;toolService;http://hdl.handle.net/11234/1-1451;ces;eng;rus;ukr;fra;deu;info:eu-repo/grantAgreement/EC/FP7/288487;downloadable_files_count: 0;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://lindat.mff.cuni.cz/services/moses/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e5b5d5f0-acc3-544a-9fc5-73d97ba4d6df",
-    "notes": [
-        "An interactive web demo of selected \u00daFAL MT systems."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1451"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "web service"
-        },
-        {
-            "name": "demo"
-        }
-    ],
-    "title": [
-        "Moses Web Demo"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e5c506a7-9513-5160-a58f-8cf74ce1f20d.json b/oaitestdata/clarin-oai_dc/SET_1/json/e5c506a7-9513-5160-a58f-8cf74ce1f20d.json
deleted file mode 100644
index 0dd9b386..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e5c506a7-9513-5160-a58f-8cf74ce1f20d.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "University of Leipzig"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-686",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-686"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-686",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Leipzig"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Code of conduct"
-    ],
-    "SpatialCoverage": [
-        "Nepal"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-686;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Chintang / Puma corpus;Documentation of the Chintang / Puma project (DoBeS project);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-686;Code of conduct;downloadable_files_count: 0;Nepal;University of Leipzig;http://corpus1.mpi.nl/ds/imdi_browser/?openpath=MPI337085%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e5c506a7-9513-5160-a58f-8cf74ce1f20d",
-    "notes": [
-        "Documentation of the Chintang / Puma project (DoBeS project)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-686"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Chintang / Puma corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e5cab928-cf14-5515-a504-a84d36ea9b33.json b/oaitestdata/clarin-oai_dc/SET_1/json/e5cab928-cf14-5515-a504-a84d36ea9b33.json
deleted file mode 100644
index 000fac52..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e5cab928-cf14-5515-a504-a84d36ea9b33.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5098",
-    "MetadataAccess": [
-        "oai:ota:oucs:5098"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "More, Hannah, 1745-1833."
-    ],
-    "fulltext": "oai:ota:oucs:5098;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5098.xml;A search after happiness: a pastoral. In three dialogues. By a young lady.;More, Hannah, 1745-1833.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e5cab928-cf14-5515-a504-a84d36ea9b33",
-    "oai_identifier": [
-        "oai:ota:oucs:5098"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A search after happiness: a pastoral. In three dialogues. By a young lady."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5098.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e5cd28fa-dd0d-51fc-a7e6-12d4fba38f4b.json b/oaitestdata/clarin-oai_dc/SET_1/json/e5cd28fa-dd0d-51fc-a7e6-12d4fba38f4b.json
deleted file mode 100644
index f4feea62..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e5cd28fa-dd0d-51fc-a7e6-12d4fba38f4b.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Andrzeja Piotrkowczyka"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-105688",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-105688"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CD5-5",
-    "PublicationTimestamp": "1644-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1644"
-    ],
-    "Publisher": [
-        "Drukarnia Andrzeja Piotrkowczyka"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/105688",
-        "oai:jbc.bj.uj.edu.pl:publication:113037"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1601/1700"
-    ],
-    "TempCoverageBegin": 50506804799,
-    "TempCoverageEnd": 50506804799,
-    "TemporalCoverage": " point in time : 1601-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1601-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1601-07-01T11:59:59Z",
-    "author": [
-        "Mijakowski, Jacek (1597-1647)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-105688;2019-02-28T17:55:06Z;Zbozny Pobyt Po \u015bmierci Swi\u0105tobliwie Zmar\u0142ey Matrony [...] Helzbiety Myszkowskiey Marsza\u0142kowey Koronney w Pi\u0144czowie Przy Pogrzebie cia\u0142a iey, do wiadomo\u015bci wszystkich podany;Mijakowski, Jacek (1597-1647);starodruki 17\u00a0w.;Myszkowski, Ferdynand ( -1647). Adr. ded.;Drukarnia Andrzeja Piotrkowczyka;[1644];starodruk;application/xml;clarind-uds:poldilemma-105688;hdl:11858/00-246C-0000-0023-8CD5-5;Biblioteka Jagiello\u0144ska, BJ St. Dr. 17411 I;pol;http://jbc.bj.uj.edu.pl/Content/105688;oai:jbc.bj.uj.edu.pl:publication:113037;1601/1700;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e5cd28fa-dd0d-51fc-a7e6-12d4fba38f4b",
-    "notes": [
-        "Myszkowski, Ferdynand ( -1647). Adr. ded."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-105688"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Zbozny Pobyt Po \u015bmierci Swi\u0105tobliwie Zmar\u0142ey Matrony [...] Helzbiety Myszkowskiey Marsza\u0142kowey Koronney w Pi\u0144czowie Przy Pogrzebie cia\u0142a iey, do wiadomo\u015bci wszystkich podany"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e5f26741-75d4-5ca4-a140-24543fa50e9b.json b/oaitestdata/clarin-oai_dc/SET_1/json/e5f26741-75d4-5ca4-a140-24543fa50e9b.json
deleted file mode 100644
index 62a41dae..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e5f26741-75d4-5ca4-a140-24543fa50e9b.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "University od \u0141\u00f3d\u017a"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Polish",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/277",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/277"
-    ],
-    "PID": "http://hdl.handle.net/11321/277",
-    "PublicationTimestamp": "2016-03-03T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "University od \u0141\u00f3d\u017a"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "P\u0119zik, Piotr"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/277;2016-06-02T20:11:14Z;hdl_11321_3;hdl_11321_4;WiKNN Text Classifier;P\u0119zik, Piotr;text classification;Polish;English;WiKNN is an online text classifier service for Polish and English texts. It supports hierarchical labelled classification of user-submitted texts with Wikipedia categories. WiKNN is available through a web-based interface (http://pelcra.clarin-pl.eu/tools/classifier/) and as a  REST service with interactive documentation available at http://clarin.pelcra.pl/apidocs/wiknn.;2016-03-03;toolService;http://hdl.handle.net/11321/277;pol;eng;application/zip;downloadable_files_count: 1;University od \u0141\u00f3d\u017a;http://pelcra.clarin-pl.eu/tools/classifier/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e5f26741-75d4-5ca4-a140-24543fa50e9b",
-    "notes": [
-        "WiKNN is an online text classifier service for Polish and English texts. It supports hierarchical labelled classification of user-submitted texts with Wikipedia categories. WiKNN is available through a web-based interface (http://pelcra.clarin-pl.eu/tools/classifier/) and as a  REST service with interactive documentation available at http://clarin.pelcra.pl/apidocs/wiknn."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/277"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "text classification"
-        },
-        {
-            "name": "Polish"
-        },
-        {
-            "name": "English"
-        }
-    ],
-    "title": [
-        "WiKNN Text Classifier"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e6410de8-b5c8-57fc-aa01-42eae1854b75.json b/oaitestdata/clarin-oai_dc/SET_1/json/e6410de8-b5c8-57fc-aa01-42eae1854b75.json
deleted file mode 100644
index 27711e56..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e6410de8-b5c8-57fc-aa01-42eae1854b75.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4522",
-    "MetadataAccess": [
-        "oai:ota:oucs:4522"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Trusler, John, 1735-1820."
-    ],
-    "fulltext": "oai:ota:oucs:4522;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4522.xml;Life; or, the adventures of William Ramble, Esq. With three frontispieces, designed by Ibbetson, ... and two new and beautiful songs, with the music by Pleyel and Sterkel. By the author of Modern times; or, the adventures of Gabriel Outcast. In three volumes.: [pt.3];Trusler, John, 1735-1820.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e6410de8-b5c8-57fc-aa01-42eae1854b75",
-    "oai_identifier": [
-        "oai:ota:oucs:4522"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Life; or, the adventures of William Ramble, Esq. With three frontispieces, designed by Ibbetson, ... and two new and beautiful songs, with the music by Pleyel and Sterkel. By the author of Modern times; or, the adventures of Gabriel Outcast. In three volumes.: [pt.3]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4522.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e65a01e4-bc9f-533f-807e-5b17bfda999c.json b/oaitestdata/clarin-oai_dc/SET_1/json/e65a01e4-bc9f-533f-807e-5b17bfda999c.json
deleted file mode 100644
index e5e714d3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e65a01e4-bc9f-533f-807e-5b17bfda999c.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-72",
-    "MetadataAccess": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-72"
-    ],
-    "PID": "http://hdl.handle.net/20.500.11752/ILC-72",
-    "PublicationTimestamp": "2017-03-17T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/327146"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Rubino, Francesco"
-    ],
-    "fulltext": "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-72;2018-09-06T13:37:17Z;hdl_000-c0-111_38;hdl_000-c0-111_49;Freeling IT;Rubino, Francesco;Wsdl;Soap webservice;Text analysis;Sentence splitting;Tokenization;POS tagging;Morphological analysis;Freeling IT is a web service that performs sentence splitting, tokenization, part-of-speech tagging, morphological analysis and lemmatization on Italian texts only. It was originally deployed within the EU-FP7-STREP PANACEA project (www.panacea-lr.eu) and implements the Freeling 2.1 libraries with no modification of the original code (which is available at http://devel.cpl.upc.edu/freeling/downloads?order=time&desc=1).\r\nFor a description of the Freeling tool see Llu\u00eds Padr\u00f3 and Miquel Collado and Samuel Reese and Marina Lloberes and Irene Castell\u00f3n. FreeLing 2.1: Five Years of Open-Source Language Processing Tools Proceedings of 7th Language Resources and Evaluation Conference (LREC 2010), ELRA La Valletta, Malta. May, 2010.;2017-03-17;toolService;http://hdl.handle.net/20.500.11752/ILC-72;ita;info:eu-repo/grantAgreement/EC/FP7/327146;downloadable_files_count: 0;Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR);http://www.panacea-lr.eu",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e65a01e4-bc9f-533f-807e-5b17bfda999c",
-    "notes": [
-        "Freeling IT is a web service that performs sentence splitting, tokenization, part-of-speech tagging, morphological analysis and lemmatization on Italian texts only. It was originally deployed within the EU-FP7-STREP PANACEA project (www.panacea-lr.eu) and implements the Freeling 2.1 libraries with no modification of the original code (which is available at http://devel.cpl.upc.edu/freeling/downloads?order=time&desc=1).\r\nFor a description of the Freeling tool see Llu\u00eds Padr\u00f3 and Miquel Collado and Samuel Reese and Marina Lloberes and Irene Castell\u00f3n. FreeLing 2.1: Five Years of Open-Source Language Processing Tools Proceedings of 7th Language Resources and Evaluation Conference (LREC 2010), ELRA La Valletta, Malta. May, 2010."
-    ],
-    "oai_identifier": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-72"
-    ],
-    "oai_set": [
-        "hdl_000-c0-111_38",
-        "hdl_000-c0-111_49"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Wsdl"
-        },
-        {
-            "name": "Soap webservice"
-        },
-        {
-            "name": "Text analysis"
-        },
-        {
-            "name": "Sentence splitting"
-        },
-        {
-            "name": "Tokenization"
-        },
-        {
-            "name": "POS tagging"
-        },
-        {
-            "name": "Morphological analysis"
-        }
-    ],
-    "title": [
-        "Freeling IT"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e65e2024-ee9e-5d89-899c-8e0df6e47c1c.json b/oaitestdata/clarin-oai_dc/SET_1/json/e65e2024-ee9e-5d89-899c-8e0df6e47c1c.json
deleted file mode 100644
index a64ef708..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e65e2024-ee9e-5d89-899c-8e0df6e47c1c.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia J.K.M. Akademickiey Soc: Jesu"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-5709",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-5709"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D27-5",
-    "PublicationTimestamp": "1752-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1752"
-    ],
-    "Publisher": [
-        "Drukarnia J.K.M. Akademickiey Soc: Jesu"
-    ],
-    "RelatedIdentifier": [
-        "http://pbc.biaman.pl/Content/5709"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "author": [
-        "Kurzeniecki, Marcin (1705-1771)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-5709;2019-03-01T15:47:55Z;Rozmowy kapelana albo teologa nadwornego z oyczystym Panem Chrze\u015bcia\u0144skim s\u0142u\u017c\u0105ce do zasi\u0105gnienia wiadomo\u015bci zbawienney, y do rezolucyi rzeczy do sumienia nale\u017c\u0105cych;Kurzeniecki, Marcin (1705-1771);ilo\u015b\u0107 skan\u00f3w: 252 ; sygn. St-359;Drukarnia J.K.M. Akademickiey Soc: Jesu;1752;starodruk;application/xml;clarind-uds:poldilemma-5709;hdl:11858/00-246C-0000-0023-8D27-5;pol;lat;http://pbc.biaman.pl/Content/5709;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e65e2024-ee9e-5d89-899c-8e0df6e47c1c",
-    "notes": [
-        "ilo\u015b\u0107 skan\u00f3w: 252 ; sygn. St-359"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-5709"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "title": [
-        "Rozmowy kapelana albo teologa nadwornego z oyczystym Panem Chrze\u015bcia\u0144skim s\u0142u\u017c\u0105ce do zasi\u0105gnienia wiadomo\u015bci zbawienney, y do rezolucyi rzeczy do sumienia nale\u017c\u0105cych"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e68dae2e-3f26-50a8-b249-4115091f2132.json b/oaitestdata/clarin-oai_dc/SET_1/json/e68dae2e-3f26-50a8-b249-4115091f2132.json
deleted file mode 100644
index 1ba9d38d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e68dae2e-3f26-50a8-b249-4115091f2132.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2377",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2377"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2377",
-    "PublicationTimestamp": "2017-08-28T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-2605"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Baran\u010d\u00edkov\u00e1, Petra",
-        "Kettnerov\u00e1, V\u00e1clava"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2377;2018-07-02T22:05:54Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;ParaDi 2.0;Baran\u010d\u00edkov\u00e1, Petra;Kettnerov\u00e1, V\u00e1clava;multiword expressions;light verb construction;paraphrases;idioms;ParaDi 2.0. is a dictionary of single verb paraphrases of Czech verbal multiword expressions - light verb constructions and idiomatic verb constructions.  Moreover, it provides an elaborated set of morphological, syntactic and semantic features, including information on aspectual counterparts of verbs or paraphrasability conditions of given verbs.\r\n\r\nThe format of ParaDi has been designed with respect to both human and machine readability - the dictionary is  represented as a plain table in  TSV format, as it is a flexible and language-independent data format.;2017-08-28;lexicalConceptualResource;http://hdl.handle.net/11234/1-2377;ces;http://hdl.handle.net/11234/1-2605;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e68dae2e-3f26-50a8-b249-4115091f2132",
-    "notes": [
-        "ParaDi 2.0. is a dictionary of single verb paraphrases of Czech verbal multiword expressions - light verb constructions and idiomatic verb constructions.  Moreover, it provides an elaborated set of morphological, syntactic and semantic features, including information on aspectual counterparts of verbs or paraphrasability conditions of given verbs.\r\n\r\nThe format of ParaDi has been designed with respect to both human and machine readability - the dictionary is  represented as a plain table in  TSV format, as it is a flexible and language-independent data format."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2377"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "multiword expressions"
-        },
-        {
-            "name": "light verb construction"
-        },
-        {
-            "name": "paraphrases"
-        },
-        {
-            "name": "idioms"
-        }
-    ],
-    "title": [
-        "ParaDi 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e691ec73-070b-5ea1-b4e6-29c52ec16740.json b/oaitestdata/clarin-oai_dc/SET_1/json/e691ec73-070b-5ea1-b4e6-29c52ec16740.json
deleted file mode 100644
index 41728247..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e691ec73-070b-5ea1-b4e6-29c52ec16740.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 15.3 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2271",
-    "MetadataAccess": [
-        "oai:ota:oucs:2271"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Demosthenes"
-    ],
-    "fulltext": "oai:ota:oucs:2271;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/2271.xml;Olynthiacs I. English;The first Olynthiac of Demosthenes;Demosthenes;default: 1976-01-01;text_and_corpus_linguistics;Addresses;Translations -- Great Britain -- 18th century;eng;Oxford Text Archive, University of Oxford;(1 file : ca. 15.3 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e691ec73-070b-5ea1-b4e6-29c52ec16740",
-    "oai_identifier": [
-        "oai:ota:oucs:2271"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Addresses"
-        },
-        {
-            "name": "Translations -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Olynthiacs I. English",
-        "The first Olynthiac of Demosthenes"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2271.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e698d38c-9250-5bcf-a329-e0b7de58de47.json b/oaitestdata/clarin-oai_dc/SET_1/json/e698d38c-9250-5bcf-a329-e0b7de58de47.json
deleted file mode 100644
index 2a6632ba..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e698d38c-9250-5bcf-a329-e0b7de58de47.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Wells, Stanley W., 1930-"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 138 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0129",
-    "MetadataAccess": [
-        "oai:ota:oucs:0129"
-    ],
-    "PublicationTimestamp": "1597-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1597"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Shakespeare, William, 1564-1616"
-    ],
-    "fulltext": "oai:ota:oucs:0129;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0129.xml;King Richard II;Richard II;Shakespeare, William, 1564-1616;1597;text_and_corpus_linguistics;Plays -- England -- 16th century;Tragedies -- England -- 16th century;eng;Oxford Text Archive, University of Oxford;Wells, Stanley W., 1930-;(1 file : ca. 138 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e698d38c-9250-5bcf-a329-e0b7de58de47",
-    "oai_identifier": [
-        "oai:ota:oucs:0129"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        },
-        {
-            "name": "Tragedies -- England -- th century"
-        }
-    ],
-    "title": [
-        "King Richard II",
-        "Richard II"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0129.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e69bf3c7-4c41-5ff3-843a-8c0129d47154.json b/oaitestdata/clarin-oai_dc/SET_1/json/e69bf3c7-4c41-5ff3-843a-8c0129d47154.json
deleted file mode 100644
index 1b3c4fd0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e69bf3c7-4c41-5ff3-843a-8c0129d47154.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4597",
-    "MetadataAccess": [
-        "oai:ota:oucs:4597"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Pilon, Frederick, 1750-1788."
-    ],
-    "fulltext": "oai:ota:oucs:4597;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4597.xml;An essay on the character of Hamlet: As performed by Mr. Henderson, at the Theatre Royal in the Hay-Market.;Pilon, Frederick, 1750-1788.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e69bf3c7-4c41-5ff3-843a-8c0129d47154",
-    "oai_identifier": [
-        "oai:ota:oucs:4597"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An essay on the character of Hamlet: As performed by Mr. Henderson, at the Theatre Royal in the Hay-Market."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4597.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e6d14ec2-86da-5888-8b7d-729bd0afe213.json b/oaitestdata/clarin-oai_dc/SET_1/json/e6d14ec2-86da-5888-8b7d-729bd0afe213.json
deleted file mode 100644
index 65e61456..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e6d14ec2-86da-5888-8b7d-729bd0afe213.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-B43E-6",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-B43E-6"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-B43E-6",
-    "PublicationTimestamp": "2006-06-21T11:59:59Z",
-    "PublicationYear": [
-        "2006"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11858/00-097C-0000-0001-B098-5"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "Panevov\u00e1, Jarmila",
-        "Haji\u010d, Jan",
-        "\u0160ev\u010d\u00edkov\u00e1-Raz\u00edmov\u00e1, Magda",
-        "\u0160t\u011bp\u00e1nek, Jan",
-        "Mikulov\u00e1, Marie",
-        "Sgall, Petr",
-        "Pajas, Petr",
-        "Havelka, Ji\u0159\u00ed"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-B43E-6;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Prague Dependency Treebank 2.0 - sample data;Haji\u010d, Jan;Panevov\u00e1, Jarmila;Sgall, Petr;Pajas, Petr;\u0160t\u011bp\u00e1nek, Jan;Havelka, Ji\u0159\u00ed;Mikulov\u00e1, Marie;\u017dabokrtsk\u00fd, Zden\u011bk;\u0160ev\u010d\u00edkov\u00e1-Raz\u00edmov\u00e1, Magda;treebank;dependency;PDT;A small subset of PDT 2.0 made available under a permissive license.\r\n\r\nPrague Dependency Treebank 2.0 (PDT 2.0) contains a large amount of Czech texts with complex and interlinked morphological (2 million words), syntactic (1.5 MW) and complex semantic annotation (0.8 MW); in addition, certain properties of sentence information structure and coreference relations are annotated at the semantic level.\r\n\r\nPDT 2.0 is based on the long-standing Praguian linguistic tradition, adapted for the current Computational Linguistics research needs. The corpus itself uses the latest annotation technology. Software tools for corpus search, annotation and language analysis are included. Extensive documentation (in English) is provided as well.;2006-06-21;corpus;http://hdl.handle.net/11858/00-097C-0000-0001-B43E-6;ces;http://hdl.handle.net/11858/00-097C-0000-0001-B098-5;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/pdt2.0/doc/pdt-guide/en/html/ch03.html#a-data-sample",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e6d14ec2-86da-5888-8b7d-729bd0afe213",
-    "notes": [
-        "A small subset of PDT 2.0 made available under a permissive license.\r\n\r\nPrague Dependency Treebank 2.0 (PDT 2.0) contains a large amount of Czech texts with complex and interlinked morphological (2 million words), syntactic (1.5 MW) and complex semantic annotation (0.8 MW); in addition, certain properties of sentence information structure and coreference relations are annotated at the semantic level.\r\n\r\nPDT 2.0 is based on the long-standing Praguian linguistic tradition, adapted for the current Computational Linguistics research needs. The corpus itself uses the latest annotation technology. Software tools for corpus search, annotation and language analysis are included. Extensive documentation (in English) is provided as well."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-B43E-6"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "dependency"
-        },
-        {
-            "name": "PDT"
-        }
-    ],
-    "title": [
-        "Prague Dependency Treebank 2.0 - sample data"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e70cf73b-8b7b-5408-b064-a5261fcdf6e3.json b/oaitestdata/clarin-oai_dc/SET_1/json/e70cf73b-8b7b-5408-b064-a5261fcdf6e3.json
deleted file mode 100644
index cee6d814..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e70cf73b-8b7b-5408-b064-a5261fcdf6e3.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Pisarze"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/plain",
-        "downloadable_files_count: 45"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/100",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/100"
-    ],
-    "PID": "http://hdl.handle.net/11321/100",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Pisarze"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Pisarze, Pisarze"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/100;2015-04-08T13:57:45Z;hdl_11321_3;hdl_11321_4;MWE Wiek XIX;Pisarze, Pisarze;balucki_burmistrz_1887.txt\r\nbalucki_murzyn_1875.txt\r\nbalucki_przebudzeni_1864.txt\r\nbeczkowska_bedzie_1897.txt\r\nbeczkowska_droga_1898.txt\r\nbeczkowska_gniezdzie_1899.txt\r\ndeotyma_panienka_1893.txt\r\ndeotyma_rozdrozu_1877.txt\r\ndeotyma_zagadka_1879.txt\r\ndygasinski_as_1896.txt\r\ndygasinski_piszczalski_1890.txt\r\ndygasinski_wilk_1883.txt\r\ngodlewska_kato_1897.txt\r\ngodlewska_kwiat_1897.txt\r\ngodlewska_ninka_1897.txt\r\nkaczkowski_grob_1857.txt\r\nkaczkowski_murdelio_1853.txt\r\nkaczkowski_olbrachtowi_1889.txt\r\nkorzeniowski_emeryt_1851.txt\r\nkorzeniowski_garbaty_1853.txt\r\nkorzeniowski_krewni_1856.txt\r\nkraszewski_kordecki_1850.txt\r\nkraszewski_lalki_1874.txt\r\nkraszewski_piast_1888.txt\r\nmarrene_bozek_1871.txt\r\nmarrene_mezowie_1875.txt\r\nmarrene_roza_1872.txt\r\norzeszkowa_meir_1878.txt\r\norzeszkowa_niemnem_1888.txt\r\nprus_emancypantki_1894.txt\r\nprus_faraon_1897.txt\r\nprus_lalka_1890.txt\r\nreymont_komediantka_1896.txt\r\nreymont_obiecana_1899.txt\r\nrodziewicz_miedzy_1890.txt\r\nrodziewicz_straszny_1887.txt\r\nsienkiewicz_ogniem_1884.txt\r\nsienkiewicz_quo_1896.txt\r\nsienkiewicz_rodzina_1894.txt\r\nswietochowski_prawdy_1888.txt\r\nsygietynski_calvados_1884.txt\r\nsygietynski_wysadzony_1891.txt\r\nzapolska_kaska_1888.txt\r\nzeromski_bezdomni_1899.txt\r\nzeromski_syzyfowe_1897.txt;2015-04-08;corpus;http://hdl.handle.net/11321/100;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain; charset=utf-8;downloadable_files_count: 45;Pisarze",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e70cf73b-8b7b-5408-b064-a5261fcdf6e3",
-    "notes": [
-        "balucki_burmistrz_1887.txt\r\nbalucki_murzyn_1875.txt\r\nbalucki_przebudzeni_1864.txt\r\nbeczkowska_bedzie_1897.txt\r\nbeczkowska_droga_1898.txt\r\nbeczkowska_gniezdzie_1899.txt\r\ndeotyma_panienka_1893.txt\r\ndeotyma_rozdrozu_1877.txt\r\ndeotyma_zagadka_1879.txt\r\ndygasinski_as_1896.txt\r\ndygasinski_piszczalski_1890.txt\r\ndygasinski_wilk_1883.txt\r\ngodlewska_kato_1897.txt\r\ngodlewska_kwiat_1897.txt\r\ngodlewska_ninka_1897.txt\r\nkaczkowski_grob_1857.txt\r\nkaczkowski_murdelio_1853.txt\r\nkaczkowski_olbrachtowi_1889.txt\r\nkorzeniowski_emeryt_1851.txt\r\nkorzeniowski_garbaty_1853.txt\r\nkorzeniowski_krewni_1856.txt\r\nkraszewski_kordecki_1850.txt\r\nkraszewski_lalki_1874.txt\r\nkraszewski_piast_1888.txt\r\nmarrene_bozek_1871.txt\r\nmarrene_mezowie_1875.txt\r\nmarrene_roza_1872.txt\r\norzeszkowa_meir_1878.txt\r\norzeszkowa_niemnem_1888.txt\r\nprus_emancypantki_1894.txt\r\nprus_faraon_1897.txt\r\nprus_lalka_1890.txt\r\nreymont_komediantka_1896.txt\r\nreymont_obiecana_1899.txt\r\nrodziewicz_miedzy_1890.txt\r\nrodziewicz_straszny_1887.txt\r\nsienkiewicz_ogniem_1884.txt\r\nsienkiewicz_quo_1896.txt\r\nsienkiewicz_rodzina_1894.txt\r\nswietochowski_prawdy_1888.txt\r\nsygietynski_calvados_1884.txt\r\nsygietynski_wysadzony_1891.txt\r\nzapolska_kaska_1888.txt\r\nzeromski_bezdomni_1899.txt\r\nzeromski_syzyfowe_1897.txt"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/100"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Wiek XIX"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e728ca26-ccf2-51e1-964a-c9d282893492.json b/oaitestdata/clarin-oai_dc/SET_1/json/e728ca26-ccf2-51e1-964a-c9d282893492.json
deleted file mode 100644
index c41761c2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e728ca26-ccf2-51e1-964a-c9d282893492.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5399",
-    "MetadataAccess": [
-        "oai:ota:oucs:5399"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Arbuthnot, John, 1667-1735."
-    ],
-    "fulltext": "oai:ota:oucs:5399;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5399.xml;A letter to the Reverend Mr. Dean Swift, occasion'd by a satire said to be written by him, entitled, A dedication to a great man, ... By a sparkish pamphleteer of Button's Coffee-house;Arbuthnot, John, 1667-1735.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e728ca26-ccf2-51e1-964a-c9d282893492",
-    "oai_identifier": [
-        "oai:ota:oucs:5399"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A letter to the Reverend Mr. Dean Swift, occasion'd by a satire said to be written by him, entitled, A dedication to a great man, ... By a sparkish pamphleteer of Button's Coffee-house"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5399.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e7552752-c1f4-5ffe-98b8-843e4695576e.json b/oaitestdata/clarin-oai_dc/SET_1/json/e7552752-c1f4-5ffe-98b8-843e4695576e.json
deleted file mode 100644
index c777f60e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e7552752-c1f4-5ffe-98b8-843e4695576e.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain",
-        "(1 file : ca. 97.4 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0665",
-    "MetadataAccess": [
-        "oai:ota:oucs:0665"
-    ],
-    "PublicationTimestamp": "1590-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1590"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Tarlton, Richard, d. 1588"
-    ],
-    "fulltext": "oai:ota:oucs:0665;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0665.xml; Tarlton's Newes out of Purgatorie;Tarlton, Richard, d. 1588;1590;text_and_corpus_linguistics;Satires -- England -- 16th century;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 97.4 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e7552752-c1f4-5ffe-98b8-843e4695576e",
-    "oai_identifier": [
-        "oai:ota:oucs:0665"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Satires -- England -- th century"
-        }
-    ],
-    "title": [
-        " Tarlton's Newes out of Purgatorie"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0665.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e794fb3e-a075-544e-ab8e-796ab7e0d0f7.json b/oaitestdata/clarin-oai_dc/SET_1/json/e794fb3e-a075-544e-ab8e-796ab7e0d0f7.json
deleted file mode 100644
index 0de20cd4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e794fb3e-a075-544e-ab8e-796ab7e0d0f7.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology",
-        "University of Lodz"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/pdf"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/546",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/546"
-    ],
-    "PID": "http://hdl.handle.net/11321/546",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology",
-        "University of Lodz"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "P\u0119zik, Piotr"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/546;2018-07-23T11:53:24Z;hdl_11321_3;hdl_11321_4;PELCRA LUZ corpus;P\u0119zik, Piotr;spoken data;semi-scripted interviews;everyday topics;mixed register;The corpus comprises 25 semi-scripted interviews (15 hours, ca. 165000 word tokens) with speakers of Polish on a range of topics.;2018;corpus;http://hdl.handle.net/11321/546;Polish;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;application/pdf;downloadable_files_count: 1;University of Lodz;Wroc\u0142aw University of Technology;http://spokes.clarin-pl.eu/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e794fb3e-a075-544e-ab8e-796ab7e0d0f7",
-    "notes": [
-        "The corpus comprises 25 semi-scripted interviews (15 hours, ca. 165000 word tokens) with speakers of Polish on a range of topics."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/546"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "spoken data"
-        },
-        {
-            "name": "semi-scripted interviews"
-        },
-        {
-            "name": "everyday topics"
-        },
-        {
-            "name": "mixed register"
-        }
-    ],
-    "title": [
-        "PELCRA LUZ corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e7af3aaa-80c7-584f-ac2f-bb3fe786c1cd.json b/oaitestdata/clarin-oai_dc/SET_1/json/e7af3aaa-80c7-584f-ac2f-bb3fe786c1cd.json
deleted file mode 100644
index 536a213e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e7af3aaa-80c7-584f-ac2f-bb3fe786c1cd.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Przeglad Wszechpolski"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 10",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/153",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/153"
-    ],
-    "PID": "http://hdl.handle.net/11321/153",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Przeglad Wszechpolski"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Super Cool License",
-        "http://www.google.com",
-        "ACA"
-    ],
-    "author": [
-        "przeglad, wszech"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/153;2015-04-13T20:49:29Z;hdl_11321_3;hdl_11321_4;Przeg Wszech, 1900;przeglad, wszech;gazeta 1900 r.;2015;corpus;http://hdl.handle.net/11321/153;pol;Super Cool License;http://www.google.com;ACA;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 10;Przeglad Wszechpolski",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e7af3aaa-80c7-584f-ac2f-bb3fe786c1cd",
-    "notes": [
-        "gazeta 1900 r."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/153"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Przeg Wszech, 1900"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e7c3b1cc-56f4-56bb-b30f-f6ee7be05bb2.json b/oaitestdata/clarin-oai_dc/SET_1/json/e7c3b1cc-56f4-56bb-b30f-f6ee7be05bb2.json
deleted file mode 100644
index 594b78b3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e7c3b1cc-56f4-56bb-b30f-f6ee7be05bb2.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3448",
-    "MetadataAccess": [
-        "oai:ota:oucs:3448"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hume, David, 1711-1776."
-    ],
-    "fulltext": "oai:ota:oucs:3448;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3448.xml;An abstract of a book lately published; entituled, A treatise of human nature, &c. Wherein the chief argument of that book is farther illustrated and explained;Treatise of human nature.;Hume, David, 1711-1776.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e7c3b1cc-56f4-56bb-b30f-f6ee7be05bb2",
-    "oai_identifier": [
-        "oai:ota:oucs:3448"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An abstract of a book lately published; entituled, A treatise of human nature, &c. Wherein the chief argument of that book is farther illustrated and explained",
-        "Treatise of human nature."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3448.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e7c50dce-f06a-5531-9d44-d4184d0e72bb.json b/oaitestdata/clarin-oai_dc/SET_1/json/e7c50dce-f06a-5531-9d44-d4184d0e72bb.json
deleted file mode 100644
index 58f9441d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e7c50dce-f06a-5531-9d44-d4184d0e72bb.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Ibtikarat team"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/xml",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Arabic"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1947",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1947"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1947",
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Ibtikarat team"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)",
-        "http://creativecommons.org/licenses/by-nc/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Namly, Driss"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1947;2017-02-06T11:05:42Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;\"Al wassit\" Arabic dictionary;Namly, Driss;lexical semantics;An XML-based file containing the electronic version of al wassit dictionary. An Arabic monolingual dictionary accomplished by the Academy of the Arabic Language in Cairo;2014;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1947;ara;Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0);http://creativecommons.org/licenses/by-nc/4.0/;PUB;text/xml;text/plain; charset=utf-8;downloadable_files_count: 1;Ibtikarat team;http://arabic.emi.ac.ma/ibtikarat/?q=Resources",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e7c50dce-f06a-5531-9d44-d4184d0e72bb",
-    "notes": [
-        "An XML-based file containing the electronic version of al wassit dictionary. An Arabic monolingual dictionary accomplished by the Academy of the Arabic Language in Cairo"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1947"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "lexical semantics"
-        }
-    ],
-    "title": [
-        "\"Al wassit\" Arabic dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e7cc7309-c43e-5e90-84dc-839cd88d6957.json b/oaitestdata/clarin-oai_dc/SET_1/json/e7cc7309-c43e-5e90-84dc-839cd88d6957.json
deleted file mode 100644
index c941dd03..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e7cc7309-c43e-5e90-84dc-839cd88d6957.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "less than 512 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1029",
-    "MetadataAccess": [
-        "oai:ota:oucs:1029"
-    ],
-    "PublicationTimestamp": "1611-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1611"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Donne, John,  1572-1631"
-    ],
-    "fulltext": "oai:ota:oucs:1029;2018-08-01T15:50:45Z;http://ota.ox.ac.uk/headers/1029.xml;The anatomie of the world  : the first anniversary / compiled by Ian Lancashire;Donne, John,  1572-1631;1611;text_and_corpus_linguistics;Poems -- England -- 17th century;eng;Oxford Text Archive, University of Oxford;less than 512 KB;Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e7cc7309-c43e-5e90-84dc-839cd88d6957",
-    "oai_identifier": [
-        "oai:ota:oucs:1029"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- England -- th century"
-        }
-    ],
-    "title": [
-        "The anatomie of the world  : the first anniversary / compiled by Ian Lancashire"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1029.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e7f4a116-0959-58ae-8754-500034a017a7.json b/oaitestdata/clarin-oai_dc/SET_1/json/e7f4a116-0959-58ae-8754-500034a017a7.json
deleted file mode 100644
index dbd1f23d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e7f4a116-0959-58ae-8754-500034a017a7.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1190",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1190"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1190",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1190;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Ellogon;Ellogon is a multi-lingual, cross-platform, general-purpose language engineering environment, developed in order to aid both researchers who are doing research in computational linguistics, as well as companies who produce and deliver language engineering systems. Ellogon as a language engineering platform offers an extensive set of facilities, including tools for processing and visualising textual/HTML/XML data and associated linguistic information, support for lexical resources (like creating and embedding lexicons), tools for creating annotated corpora, accessing databases, comparing annotated data, or transforming linguistic information into vectors for use with various machine learning algorithms.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1190;downloadable_files_count: 0;http://www.ellogon.org/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e7f4a116-0959-58ae-8754-500034a017a7",
-    "notes": [
-        "Ellogon is a multi-lingual, cross-platform, general-purpose language engineering environment, developed in order to aid both researchers who are doing research in computational linguistics, as well as companies who produce and deliver language engineering systems. Ellogon as a language engineering platform offers an extensive set of facilities, including tools for processing and visualising textual/HTML/XML data and associated linguistic information, support for lexical resources (like creating and embedding lexicons), tools for creating annotated corpora, accessing databases, comparing annotated data, or transforming linguistic information into vectors for use with various machine learning algorithms."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1190"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Ellogon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e7f9569d-d96d-5d2b-8b52-4e6de3ae8da7.json b/oaitestdata/clarin-oai_dc/SET_1/json/e7f9569d-d96d-5d2b-8b52-4e6de3ae8da7.json
deleted file mode 100644
index 257464a5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e7f9569d-d96d-5d2b-8b52-4e6de3ae8da7.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/583",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/583"
-    ],
-    "PID": "http://hdl.handle.net/11321/583",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "BSD 2 Clause",
-        "https://opensource.org/licenses/BSD-2-Clause",
-        "PUB"
-    ],
-    "author": [
-        "Nito\u0144, Bart\u0142omiej",
-        "Bartosiak, Tomasz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/583;2018-07-26T15:26:20Z;hdl_11321_3;hdl_11321_4;Slowal (2018-06-29);Nito\u0144, Bart\u0142omiej;Bartosiak, Tomasz;syntactic schema;valence dictionary editor;semantic frame;valence dictionary browser;Slowal is a web tool designed for creating, editing and browsing valence dictionaries. So far, it has mainly been used for creating The Polish Valence Dictionary (Walenty).\r\n\r\nSlowal supports the process of creating the dictionary; it also facilitates access by making it possible to browse the dictionary using an advanced built-in filtering system, covering both syntactic and semantic phenomena. Slowal also gives control over the work of lexicographers involved in creating dictionary, for instance by using predefined lists of values, which prevents spelling errors and enforces consistency, as well as by imposing strict validation rules.\r\n\r\nLast but not least, the created dictionary can be exported from Slowal in various formats: plain text, TeX, PDF, and TEI XML.\r\n\r\nThis version was adapted for creating semantics of nouns and adjectives.;2018;toolService;http://hdl.handle.net/11321/583;pol;BSD 2 Clause;https://opensource.org/licenses/BSD-2-Clause;PUB;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;Institute of Computer Science, Polish Academy of Sciences;http://zil.ipipan.waw.pl/Slowal",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e7f9569d-d96d-5d2b-8b52-4e6de3ae8da7",
-    "notes": [
-        "Slowal is a web tool designed for creating, editing and browsing valence dictionaries. So far, it has mainly been used for creating The Polish Valence Dictionary (Walenty).\r\n\r\nSlowal supports the process of creating the dictionary; it also facilitates access by making it possible to browse the dictionary using an advanced built-in filtering system, covering both syntactic and semantic phenomena. Slowal also gives control over the work of lexicographers involved in creating dictionary, for instance by using predefined lists of values, which prevents spelling errors and enforces consistency, as well as by imposing strict validation rules.\r\n\r\nLast but not least, the created dictionary can be exported from Slowal in various formats: plain text, TeX, PDF, and TEI XML.\r\n\r\nThis version was adapted for creating semantics of nouns and adjectives."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/583"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "syntactic schema"
-        },
-        {
-            "name": "valence dictionary editor"
-        },
-        {
-            "name": "semantic frame"
-        },
-        {
-            "name": "valence dictionary browser"
-        }
-    ],
-    "title": [
-        "Slowal (2018-06-29)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e8025b2d-aff0-5eca-9b1a-d072283120f2.json b/oaitestdata/clarin-oai_dc/SET_1/json/e8025b2d-aff0-5eca-9b1a-d072283120f2.json
deleted file mode 100644
index 022d0707..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e8025b2d-aff0-5eca-9b1a-d072283120f2.json
+++ /dev/null
@@ -1,104 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "English",
-        "French",
-        "German",
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-D9BF-5",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-D9BF-5"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0022-D9BF-5",
-    "PublicationTimestamp": "2013-10-10T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/257528",
-        "http://hdl.handle.net/11234/1-2121"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0)",
-        "http://creativecommons.org/licenses/by-nc/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Haji\u010d, Jan",
-        "Ure\u0161ov\u00e1, Zde\u0148ka",
-        "Du\u0161ek, Ond\u0159ej",
-        "Pecina, Pavel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-D9BF-5;2018-07-02T22:05:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Khresmoi Query Translation Test Data 1.0;Pecina, Pavel;Du\u0161ek, Ond\u0159ej;Haji\u010d, Jan;Ure\u0161ov\u00e1, Zde\u0148ka;corpus;test data;medical;health;machine translation;Czech;French;German;English;This package contains data sets for development and testing of machine translation of medical search short queries between Czech, English, French, and German.  The queries come from general public and medical experts.;2013-10-10;corpus;Khresmoi-Query-MT-Test-Data-1.0;http://hdl.handle.net/11858/00-097C-0000-0022-D9BF-5;eng;fra;deu;ces;info:eu-repo/grantAgreement/EC/FP7/257528;http://hdl.handle.net/11234/1-2121;Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0);http://creativecommons.org/licenses/by-nc/3.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://khresmoi.eu",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e8025b2d-aff0-5eca-9b1a-d072283120f2",
-    "notes": [
-        "This package contains data sets for development and testing of machine translation of medical search short queries between Czech, English, French, and German.  The queries come from general public and medical experts."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0022-D9BF-5"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "test data"
-        },
-        {
-            "name": "medical"
-        },
-        {
-            "name": "health"
-        },
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "Czech"
-        },
-        {
-            "name": "French"
-        },
-        {
-            "name": "German"
-        },
-        {
-            "name": "English"
-        }
-    ],
-    "title": [
-        "Khresmoi Query Translation Test Data 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e802ed6f-7151-519f-ae35-2fa4f21da301.json b/oaitestdata/clarin-oai_dc/SET_1/json/e802ed6f-7151-519f-ae35-2fa4f21da301.json
deleted file mode 100644
index f03d0da8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e802ed6f-7151-519f-ae35-2fa4f21da301.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Dutch",
-        "English",
-        "French",
-        "German",
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-426",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-426"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-426",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "France||Germany||Netherlands (the)||Sweden||United Kingdom"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-426;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;MPI ESF Corpus;Corpus of the ESF Foreign Language Speakers project; almost perfect structurefor IEI; completely metadata described; lots of annotated audio recordings containing multimodal interaction;;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-426;nld;eng;fra;deu;swe;downloadable_files_count: 0;France||Germany||Netherlands (the)||Sweden||United Kingdom;http://corpus1.mpi.nl/ds/imdi_browser/?openpath=MPI556280%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e802ed6f-7151-519f-ae35-2fa4f21da301",
-    "notes": [
-        "Corpus of the ESF Foreign Language Speakers project; almost perfect structurefor IEI; completely metadata described; lots of annotated audio recordings containing multimodal interaction;"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-426"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "MPI ESF Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e8078d90-9db0-5a4d-9edd-eca5a3498164.json b/oaitestdata/clarin-oai_dc/SET_1/json/e8078d90-9db0-5a4d-9edd-eca5a3498164.json
deleted file mode 100644
index 69e9ef51..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e8078d90-9db0-5a4d-9edd-eca5a3498164.json
+++ /dev/null
@@ -1,91 +0,0 @@
-{
-    "Contact": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-88",
-    "MetadataAccess": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-88"
-    ],
-    "PID": "http://hdl.handle.net/20.500.11752/ILC-88",
-    "PublicationTimestamp": "2016-11-21T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "AA. VV."
-    ],
-    "fulltext": "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-88;2018-07-23T09:13:44Z;hdl_000-c0-111_38;hdl_000-c0-111_49;PAROLE-SIMPLE-CLIPS;AA. VV.;Database lessicale;Morfologia;Semantica lessicale;Fonologia;Lessico computazionale;Sintassi;Lexical database;Morphology;PAROLE-SIMPLE-CLIPS is a four-level general purpose lexicon that has been elaborated over three different projects. The kernel of the morphological and syntactic lexicons was built in the framework of the European project \"Preparatory Action for Linguistic Resources Organisation for Language Engineering\" (LE-PAROLE). The linguistic model and the core of the semantic lexicon were elaborated within the European project \"Semantic Information for Multifunctional Plurilingual Lexica\" (LE-SIMPLE). The phonological level of the description and the extension of the lexical coverage were produced in the context of the Italian project \"Corpora e Lessici dell'Italiano Parlato e Scritto\" (CLIPS). It comprises a total of 387,267 phonetic units, 53,044 morphological units (53,044 lemmas), 37,406 syntactic units (28,111 lemmas) and 28,346 semantic units (19,216 lemmas). It was encoded at the semantic level, in full accordance with the international standards set out in the PAROLE-SIMPLE model and based on EAGLES. Syntactic and semantic encodings were performed jointly with Thamus (Consortium for Multilingual Documentary Engineering), which is responsible for 25,000 extra entries. PAROLE-SIMPLE-CLIPS was created incrementally between the end of the 1990s and 2003.;2016-11-21;lexicalConceptualResource;http://hdl.handle.net/20.500.11752/ILC-88;ita;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;PUB;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR);http://www.ilc.cnr.it/en/content/clips",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e8078d90-9db0-5a4d-9edd-eca5a3498164",
-    "notes": [
-        "PAROLE-SIMPLE-CLIPS is a four-level general purpose lexicon that has been elaborated over three different projects. The kernel of the morphological and syntactic lexicons was built in the framework of the European project \"Preparatory Action for Linguistic Resources Organisation for Language Engineering\" (LE-PAROLE). The linguistic model and the core of the semantic lexicon were elaborated within the European project \"Semantic Information for Multifunctional Plurilingual Lexica\" (LE-SIMPLE). The phonological level of the description and the extension of the lexical coverage were produced in the context of the Italian project \"Corpora e Lessici dell'Italiano Parlato e Scritto\" (CLIPS). It comprises a total of 387,267 phonetic units, 53,044 morphological units (53,044 lemmas), 37,406 syntactic units (28,111 lemmas) and 28,346 semantic units (19,216 lemmas). It was encoded at the semantic level, in full accordance with the international standards set out in the PAROLE-SIMPLE model and based on EAGLES. Syntactic and semantic encodings were performed jointly with Thamus (Consortium for Multilingual Documentary Engineering), which is responsible for 25,000 extra entries. PAROLE-SIMPLE-CLIPS was created incrementally between the end of the 1990s and 2003."
-    ],
-    "oai_identifier": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-88"
-    ],
-    "oai_set": [
-        "hdl_000-c0-111_38",
-        "hdl_000-c0-111_49"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Database lessicale"
-        },
-        {
-            "name": "Morfologia"
-        },
-        {
-            "name": "Semantica lessicale"
-        },
-        {
-            "name": "Fonologia"
-        },
-        {
-            "name": "Lessico computazionale"
-        },
-        {
-            "name": "Sintassi"
-        },
-        {
-            "name": "Lexical database"
-        },
-        {
-            "name": "Morphology"
-        }
-    ],
-    "title": [
-        "PAROLE-SIMPLE-CLIPS"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e831063f-523a-54e4-a420-b228b41b25ed.json b/oaitestdata/clarin-oai_dc/SET_1/json/e831063f-523a-54e4-a420-b228b41b25ed.json
deleted file mode 100644
index 763d60d5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e831063f-523a-54e4-a420-b228b41b25ed.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3747",
-    "MetadataAccess": [
-        "oai:ota:oucs:3747"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Jerningham, Mr. (Edward), 1737?-1812."
-    ],
-    "fulltext": "oai:ota:oucs:3747;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3747.xml;The fall of Mexico, a poem. By Mr. Jerningham;Jerningham, Mr. (Edward), 1737?-1812.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e831063f-523a-54e4-a420-b228b41b25ed",
-    "oai_identifier": [
-        "oai:ota:oucs:3747"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The fall of Mexico, a poem. By Mr. Jerningham"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3747.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e8375588-bed3-5754-9c86-3b552b9f7542.json b/oaitestdata/clarin-oai_dc/SET_1/json/e8375588-bed3-5754-9c86-3b552b9f7542.json
deleted file mode 100644
index e0dbfc2d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e8375588-bed3-5754-9c86-3b552b9f7542.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4644",
-    "MetadataAccess": [
-        "oai:ota:oucs:4644"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gibbon, Edward, 1737-1794."
-    ],
-    "fulltext": "oai:ota:oucs:4644;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4644.xml;The history of the decline and fall of the Roman Empire: By Edward Gibbon, Esq; ... [pt.6];Gibbon, Edward, 1737-1794.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e8375588-bed3-5754-9c86-3b552b9f7542",
-    "oai_identifier": [
-        "oai:ota:oucs:4644"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The history of the decline and fall of the Roman Empire: By Edward Gibbon, Esq; ... [pt.6]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4644.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e83c69a1-d0d5-5b2c-a043-301d5f22fc51.json b/oaitestdata/clarin-oai_dc/SET_1/json/e83c69a1-d0d5-5b2c-a043-301d5f22fc51.json
deleted file mode 100644
index 721cd0b7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e83c69a1-d0d5-5b2c-a043-301d5f22fc51.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1006",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1006"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1006",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1006;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LAC Guugu Yimithirr;Language and Cognition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1006;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI29016%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e83c69a1-d0d5-5b2c-a043-301d5f22fc51",
-    "notes": [
-        "Language and Cognition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1006"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LAC Guugu Yimithirr"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e84469a5-e396-547b-ab7b-e6f49cdfcb1a.json b/oaitestdata/clarin-oai_dc/SET_1/json/e84469a5-e396-547b-ab7b-e6f49cdfcb1a.json
deleted file mode 100644
index 90d77966..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e84469a5-e396-547b-ab7b-e6f49cdfcb1a.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Katholieke Universiteit Leuven Campus Kortrijk"
-    ],
-    "Contributor": [
-        "Paulussen, Hans"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Dutch",
-        "English",
-        "French"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-628",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-628"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-628",
-    "PublicationTimestamp": "1999-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1999"
-    ],
-    "Publisher": [
-        "Katholieke Universiteit Leuven Campus Kortrijk"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Belgium"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-628;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Namur Corpus;Paulussen, Hans;Trilingual parallel corpus, with Dutch as first language. 2M words, aligned at paragraph level. It includes fiction and non-fiction texts.;1999;corpus;http://hdl.handle.net/11372/LRT-628;nld;eng;fra;downloadable_files_count: 0;Belgium;Katholieke Universiteit Leuven Campus Kortrijk;https://www.kuleuven-kulak.be/~hpauluss/NamurCorpus.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e84469a5-e396-547b-ab7b-e6f49cdfcb1a",
-    "notes": [
-        "Trilingual parallel corpus, with Dutch as first language. 2M words, aligned at paragraph level. It includes fiction and non-fiction texts."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-628"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Namur Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e855725d-d9a5-5a3c-b46a-8065115d8b46.json b/oaitestdata/clarin-oai_dc/SET_1/json/e855725d-d9a5-5a3c-b46a-8065115d8b46.json
deleted file mode 100644
index 83035f1b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e855725d-d9a5-5a3c-b46a-8065115d8b46.json
+++ /dev/null
@@ -1,105 +0,0 @@
-{
-    "Contact": [
-        "Jan Oliver R\u00fcdiger"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German",
-        "English",
-        "French",
-        "Italian",
-        "Dutch",
-        "Spanish",
-        "Polish",
-        "Arabic",
-        "Chinese",
-        "Portuguese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2634",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2634"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2634",
-    "PublicationTimestamp": "2018-03-14T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Jan Oliver R\u00fcdiger"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "R\u00fcdiger, Jan Oliver"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2634;2018-06-25T14:14:59Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;CorpusExplorer;R\u00fcdiger, Jan Oliver;Corpus Linguisitics;NLP;conll;tei;XML;nlp;Natural Language Processing;linguistics;Linguistics;Computational Linguistics;corpus processing;tagger;POS tagger;lemmatization;text cleaning;CommonCrawl;epub;JSON;Twitter;Pandoc;Wikipedia;digital data;DTA;DSpin;MySQL;ElasticSearch;TextGrid;text corpora;TigerXML;WeblichtXML;Software for corpus linguists and text/data mining enthusiasts. The CorpusExplorer combines over 45 interactive visualizations under a user-friendly interface. Routine tasks such as text acquisition, cleaning or tagging are completely automated. The simple interface supports the use in university teaching and leads users/students to fast and substantial results. The CorpusExplorer is open for many standards (XML, CSV, JSON, R, etc.) and also offers its own software development kit (SDK).\r\n\r\nSource code available at https://github.com/notesjor/corpusexplorer2.0;2018-03-14;toolService;http://hdl.handle.net/11234/1-2634;deu;eng;fra;ita;nld;spa;pol;ara;zho;por;downloadable_files_count: 0;Jan Oliver R\u00fcdiger;http://corpusexplorer.de",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e855725d-d9a5-5a3c-b46a-8065115d8b46",
-    "notes": [
-        "Software for corpus linguists and text/data mining enthusiasts. The CorpusExplorer combines over 45 interactive visualizations under a user-friendly interface. Routine tasks such as text acquisition, cleaning or tagging are completely automated. The simple interface supports the use in university teaching and leads users/students to fast and substantial results. The CorpusExplorer is open for many standards (XML, CSV, JSON, R, etc.) and also offers its own software development kit (SDK).\r\n\r\nSource code available at https://github.com/notesjor/corpusexplorer2.0"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2634"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Corpus Linguisitics"
-        },
-        {
-            "name": "NLP"
-        },
-        {
-            "name": "conll"
-        },
-        {
-            "name": "tei"
-        },
-        {
-            "name": "XML"
-        },
-        {
-            "name": "nlp"
-        },
-        {
-            "name": "Natural Language Processing"
-        },
-        {
-            "name": "linguistics"
-        },
-        {
-            "name": "Linguistics"
-        },
-        {
-            "name": "Computational Linguistics"
-        },
-        {
-            "name": "corpus processing"
-        },
-        {
-            "name": "tagger"
-        }
-    ],
-    "title": [
-        "CorpusExplorer"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e86ecb14-b5f2-5941-8e36-edf52e2af983.json b/oaitestdata/clarin-oai_dc/SET_1/json/e86ecb14-b5f2-5941-8e36-edf52e2af983.json
deleted file mode 100644
index ccb1f74a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e86ecb14-b5f2-5941-8e36-edf52e2af983.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5603",
-    "MetadataAccess": [
-        "oai:ota:oucs:5603"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hill, John, 1714?-1775."
-    ],
-    "fulltext": "oai:ota:oucs:5603;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5603.xml;The old man's guide to health and longer life: with rules for diet, exercise, and physick; ...;Hill, John, 1714?-1775.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e86ecb14-b5f2-5941-8e36-edf52e2af983",
-    "oai_identifier": [
-        "oai:ota:oucs:5603"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The old man's guide to health and longer life: with rules for diet, exercise, and physick; ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5603.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e891628a-b1e2-5f7b-b39d-9ae53f6840a5.json b/oaitestdata/clarin-oai_dc/SET_1/json/e891628a-b1e2-5f7b-b39d-9ae53f6840a5.json
deleted file mode 100644
index 1b81dec9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e891628a-b1e2-5f7b-b39d-9ae53f6840a5.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "A"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1468",
-    "MetadataAccess": [
-        "oai:ota:oucs:1468"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Heywood, John"
-    ],
-    "fulltext": "oai:ota:oucs:1468;2018-04-16T15:30:51Z;http://ota.ox.ac.uk/headers/1468.xml;A woman killed with kindness (contractions expanded);Heywood, John;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;A;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e891628a-b1e2-5f7b-b39d-9ae53f6840a5",
-    "oai_identifier": [
-        "oai:ota:oucs:1468"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A woman killed with kindness (contractions expanded)"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1468.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e8a415d5-7fc4-5dd2-855c-d1e00aab0f2a.json b/oaitestdata/clarin-oai_dc/SET_1/json/e8a415d5-7fc4-5dd2-855c-d1e00aab0f2a.json
deleted file mode 100644
index 7c3de4f3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e8a415d5-7fc4-5dd2-855c-d1e00aab0f2a.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "The Danish Language Council",
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml",
-        "text/plain; charset=utf-8",
-        "application/pdf",
-        "downloadable_files_count: 11",
-        "application/zip",
-        "text/plain"
-    ],
-    "Language": [
-        "Danish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repository.clarin.dk:20.500.12115/11",
-    "MetadataAccess": [
-        "oai:repository.clarin.dk:20.500.12115/11"
-    ],
-    "PID": "http://hdl.handle.net/20.500.12115/11",
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "The Danish Language Council",
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN-ACA-NC",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NC=1&NORED=1",
-        "ACA"
-    ],
-    "author": [
-        "Hansen, Dorte Haltrup",
-        "Braasch, Anna",
-        "Olsen, Sussi",
-        "Jakob, Halskov"
-    ],
-    "fulltext": "oai:repository.clarin.dk:20.500.12115/11;2018-06-28T13:24:42Z;hdl_20.500.12115_1;hdl_20.500.12115_3;DK-CLARIN LSP Corpus - Economics domain;Olsen, Sussi;Braasch, Anna;Hansen, Dorte Haltrup;Jakob, Halskov;Economics;Texts in the Economics domain come from SKAT, Finanstilsynet and Erhvervs- og Selskabsstyrelsen and have been collected in the DK-CLARIN project, WP2.2, 2008 - 2011. \r\nThe corpus consists of 979,881 words in 64 files. \r\nCommunicative setting/Number of files: expert->expert (11) expert->advanced (1) expert->basic (52).\r\nAll texts are in XML TEIP5 format (TEIP5DKCLARIN-format), with tokenisation, pos-tagging, sentence and paragraph segmentation, lemmatisation and termhood annotation placed in separate text external spangroups. \r\n\"DK-CLARIN LSP Corpus - Economics domain\" is a part of the Danish DK-CLARIN LSP corpus consisting of seven sub-corpora from following subject domains: Agriculture, Construction, Economics, Environment, Health, IT and Nanotechnology.;2011;corpus;http://hdl.handle.net/20.500.12115/11;dan;CLARIN-ACA-NC;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NC=1&NORED=1;ACA;text/plain; charset=utf-8;application/zip;application/zip;application/zip;application/zip;application/pdf;application/pdf;application/pdf;text/plain;text/xml;text/xml;text/xml;downloadable_files_count: 11;Centre for Language Technology, NorS, University of Copenhagen;The Danish Language Council",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e8a415d5-7fc4-5dd2-855c-d1e00aab0f2a",
-    "notes": [
-        "Texts in the Economics domain come from SKAT, Finanstilsynet and Erhvervs- og Selskabsstyrelsen and have been collected in the DK-CLARIN project, WP2.2, 2008 - 2011. \r\nThe corpus consists of 979,881 words in 64 files. \r\nCommunicative setting/Number of files: expert->expert (11) expert->advanced (1) expert->basic (52).\r\nAll texts are in XML TEIP5 format (TEIP5DKCLARIN-format), with tokenisation, pos-tagging, sentence and paragraph segmentation, lemmatisation and termhood annotation placed in separate text external spangroups. \r\n\"DK-CLARIN LSP Corpus - Economics domain\" is a part of the Danish DK-CLARIN LSP corpus consisting of seven sub-corpora from following subject domains: Agriculture, Construction, Economics, Environment, Health, IT and Nanotechnology."
-    ],
-    "oai_identifier": [
-        "oai:repository.clarin.dk:20.500.12115/11"
-    ],
-    "oai_set": [
-        "hdl_20.500.12115_1",
-        "hdl_20.500.12115_3"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Economics"
-        }
-    ],
-    "title": [
-        "DK-CLARIN LSP Corpus - Economics domain"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e8d63f3a-838e-5489-ba15-5d4894b92191.json b/oaitestdata/clarin-oai_dc/SET_1/json/e8d63f3a-838e-5489-ba15-5d4894b92191.json
deleted file mode 100644
index d23566d1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e8d63f3a-838e-5489-ba15-5d4894b92191.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2605",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2605"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2605",
-    "PublicationTimestamp": "2017-08-28T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-2377"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Baran\u010d\u00edkov\u00e1, Petra",
-        "Kettnerov\u00e1, V\u00e1clava"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2605;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;ParaDi 2.0 (2018-01-24);Baran\u010d\u00edkov\u00e1, Petra;Kettnerov\u00e1, V\u00e1clava;multiword expressions;light verb construction;paraphrases;idioms;ParaDi 2.0. is a dictionary of single verb paraphrases of Czech verbal multiword expressions - light verb constructions and idiomatic verb constructions.  Moreover, it provides an elaborated set of morphological, syntactic and semantic features, including information on aspectual counterparts of verbs or paraphrasability conditions of given verbs.\r\n\r\nThe format of ParaDi has been designed with respect to both human and machine readability - the dictionary is  represented as a plain table in  TSV format, as it is a flexible and language-independent data format.;2017-08-28;lexicalConceptualResource;http://hdl.handle.net/11234/1-2605;ces;http://hdl.handle.net/11234/1-2377;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e8d63f3a-838e-5489-ba15-5d4894b92191",
-    "notes": [
-        "ParaDi 2.0. is a dictionary of single verb paraphrases of Czech verbal multiword expressions - light verb constructions and idiomatic verb constructions.  Moreover, it provides an elaborated set of morphological, syntactic and semantic features, including information on aspectual counterparts of verbs or paraphrasability conditions of given verbs.\r\n\r\nThe format of ParaDi has been designed with respect to both human and machine readability - the dictionary is  represented as a plain table in  TSV format, as it is a flexible and language-independent data format."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2605"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "multiword expressions"
-        },
-        {
-            "name": "light verb construction"
-        },
-        {
-            "name": "paraphrases"
-        },
-        {
-            "name": "idioms"
-        }
-    ],
-    "title": [
-        "ParaDi 2.0 (2018-01-24)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e8db6886-b0cb-5246-afd6-b437fab74e61.json b/oaitestdata/clarin-oai_dc/SET_1/json/e8db6886-b0cb-5246-afd6-b437fab74e61.json
deleted file mode 100644
index 909cb274..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e8db6886-b0cb-5246-afd6-b437fab74e61.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Piotra Dufoura"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Latin",
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-165751",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-165751"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CEC-4",
-    "PublicationTimestamp": "1790-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1790"
-    ],
-    "Publisher": [
-        "Drukarnia Piotra Dufoura"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/165751",
-        "oai:jbc.bj.uj.edu.pl:publication:174207"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1701/1800"
-    ],
-    "TempCoverageBegin": 53662478399,
-    "TempCoverageEnd": 53662478399,
-    "TemporalCoverage": " point in time : 1701-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1701-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1701-07-01T11:59:59Z",
-    "author": [
-        "Jezierski, Franciszek Salezy (1740-1791)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-165751;2019-03-01T10:49:36Z;Rzepicha Matka Krolow Zona Piasta Mi\u0119dzy Narodami Sarmackiemi S\u0142owianskiego Monarchy Tey Cz\u0119sci Ziemi Ktora si\u0119 Nazywa Polska. Cz. 1-2.;Jezierski, Franciszek Salezy (1740-1791);starodruki 18\u00a0w.;Drukarnia Piotra Dufoura;1790;starodruk;application/xml;clarind-uds:poldilemma-165751;hdl:11858/00-246C-0000-0023-8CEC-4;Biblioteka Jagiello\u0144ska, BJ St. Dr. 58242 I;lat;pol;http://jbc.bj.uj.edu.pl/Content/165751;oai:jbc.bj.uj.edu.pl:publication:174207;1701/1800;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e8db6886-b0cb-5246-afd6-b437fab74e61",
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-165751"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Rzepicha Matka Krolow Zona Piasta Mi\u0119dzy Narodami Sarmackiemi S\u0142owianskiego Monarchy Tey Cz\u0119sci Ziemi Ktora si\u0119 Nazywa Polska. Cz. 1-2."
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e927aad0-e04d-5cef-b3ef-ffa40a3c77b2.json b/oaitestdata/clarin-oai_dc/SET_1/json/e927aad0-e04d-5cef-b3ef-ffa40a3c77b2.json
deleted file mode 100644
index c54ccb7c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e927aad0-e04d-5cef-b3ef-ffa40a3c77b2.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=6acc9424059511e7a2aa782bcb074135edf97b91062c42fbbbbfef373fa944da",
-    "MetadataAccess": [
-        "6acc9424059511e7a2aa782bcb074135edf97b91062c42fbbbbfef373fa944da"
-    ],
-    "PublicationTimestamp": "2017-03-10T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "fulltext": "6acc9424059511e7a2aa782bcb074135edf97b91062c42fbbbbfef373fa944da;2018-11-15T16:40:30Z;toolService;toolService:tool;English to Czech Machine translation module;Technical Description:\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/Pilot1_technical_description.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/TechnicalDescriptionPilot2_D2.7.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2016/11/TechnicalDescriptionPilot3_D2.10.pdf;2017-03-10",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e927aad0-e04d-5cef-b3ef-ffa40a3c77b2",
-    "notes": [
-        "Technical Description:\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/Pilot1_technical_description.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/TechnicalDescriptionPilot2_D2.7.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2016/11/TechnicalDescriptionPilot3_D2.10.pdf"
-    ],
-    "oai_identifier": [
-        "6acc9424059511e7a2aa782bcb074135edf97b91062c42fbbbbfef373fa944da"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "English to Czech Machine translation module"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e9302a93-7c13-5d92-9049-034c886e6d31.json b/oaitestdata/clarin-oai_dc/SET_1/json/e9302a93-7c13-5d92-9049-034c886e6d31.json
deleted file mode 100644
index 56bcbec4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e9302a93-7c13-5d92-9049-034c886e6d31.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4113",
-    "MetadataAccess": [
-        "oai:ota:oucs:4113"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gentleman, Francis, 1728-1784."
-    ],
-    "fulltext": "oai:ota:oucs:4113;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4113.xml;Oroonoko: or the royal slave. A tragedy. Altered from Southerne, by Francis Gentleman. ...;Gentleman, Francis, 1728-1784.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e9302a93-7c13-5d92-9049-034c886e6d31",
-    "oai_identifier": [
-        "oai:ota:oucs:4113"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Oroonoko: or the royal slave. A tragedy. Altered from Southerne, by Francis Gentleman. ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4113.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e936b56c-4fdc-5df3-a726-7aceacff7198.json b/oaitestdata/clarin-oai_dc/SET_1/json/e936b56c-4fdc-5df3-a726-7aceacff7198.json
deleted file mode 100644
index b44135bd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e936b56c-4fdc-5df3-a726-7aceacff7198.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "between 1 and 2 MB"
-    ],
-    "Language": [
-        "Middle English (1100-1500)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1369",
-    "MetadataAccess": [
-        "oai:ota:oucs:1369"
-    ],
-    "PublicationYear": [
-        "Unspecified"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Chaucer, Geoffrey,  d. 1400"
-    ],
-    "fulltext": "oai:ota:oucs:1369;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1369.xml; Canterbury tales  / compiled by J.D. Burnley;Chaucer, Geoffrey,  d. 1400;Unspecified;text_and_corpus_linguistics;Poems -- England -- 14th century;enm;Oxford Text Archive, University of Oxford;between 1 and 2 MB;Text;Poems;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e936b56c-4fdc-5df3-a726-7aceacff7198",
-    "oai_identifier": [
-        "oai:ota:oucs:1369"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- England -- th century"
-        }
-    ],
-    "title": [
-        " Canterbury tales  / compiled by J.D. Burnley"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1369.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e93af506-e1e6-5079-a474-97f7d6387623.json b/oaitestdata/clarin-oai_dc/SET_1/json/e93af506-e1e6-5079-a474-97f7d6387623.json
deleted file mode 100644
index e89391d2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e93af506-e1e6-5079-a474-97f7d6387623.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "172 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1303",
-    "MetadataAccess": [
-        "oai:ota:oucs:1303"
-    ],
-    "PublicationYear": [
-        "472 BCE"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Aeschylus"
-    ],
-    "fulltext": "oai:ota:oucs:1303;2018-03-07T11:07:13Z;http://ota.ox.ac.uk/headers/1303.xml;The Persians  / compiled by Anthony J. Podlecki;Aeschylus;472 BCE;text_and_corpus_linguistics;Plays -- 5th century B.C.;eng;Oxford Text Archive, University of Oxford;172 KB;Text;Plays;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e93af506-e1e6-5079-a474-97f7d6387623",
-    "oai_identifier": [
-        "oai:ota:oucs:1303"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- th century B.C."
-        }
-    ],
-    "title": [
-        "The Persians  / compiled by Anthony J. Podlecki"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1303.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e93ee43f-cede-578a-84e7-e8fd91b4b291.json b/oaitestdata/clarin-oai_dc/SET_1/json/e93ee43f-cede-578a-84e7-e8fd91b4b291.json
deleted file mode 100644
index d2fb8173..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e93ee43f-cede-578a-84e7-e8fd91b4b291.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "French",
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1045",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1045"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1045",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1045;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;L1 & L2 Acquisition Marzena Watorek French Project;language acquisition corpus;Language Acquisition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1045;fra;pol;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;https://corpus1.mpi.nl/ds/asv/?2&openpath=node:559716",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e93ee43f-cede-578a-84e7-e8fd91b4b291",
-    "notes": [
-        "Language Acquisition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1045"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "language acquisition corpus"
-        }
-    ],
-    "title": [
-        "L1 & L2 Acquisition Marzena Watorek French Project"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e9408f0e-17f7-536a-b99a-7112c50f28a4.json b/oaitestdata/clarin-oai_dc/SET_1/json/e9408f0e-17f7-536a-b99a-7112c50f28a4.json
deleted file mode 100644
index 565ce829..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e9408f0e-17f7-536a-b99a-7112c50f28a4.json
+++ /dev/null
@@ -1,95 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 4",
-        "application/pdf",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1079",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1079"
-    ],
-    "PID": "http://hdl.handle.net/11356/1079",
-    "PublicationTimestamp": "2016-12-22T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11356/1081"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by-sa/4.0/"
-    ],
-    "author": [
-        "\u010cibej, Jaka",
-        "Erjavec, Toma\u017e",
-        "Fi\u0161er, Darja",
-        "Arhar Holdt, \u0160pela"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1079;2018-10-18T22:29:33Z;hdl_11356_1023;hdl_11356_1024;CMC training corpus Janes-Tag 1.0;Erjavec, Toma\u017e;Fi\u0161er, Darja;\u010cibej, Jaka;Arhar Holdt, \u0160pela;computer-mediated communication;tokenisation;word normalisation;tagging;lemmatisation;manual annotation;TEI;Janes-Tag is a manually annotated corpus of Slovene Computer-Mediated Communication (CMC). It is meant as a gold-standard training and testing dataset for tokenisation, sentence segmentation, word normalisation, morphosyntactic tagging and lemmatisation of non-standard Slovene. As the corpus has been carefully manually annotated, it is also suitable for detailed linguistic explorations which require higlhy accurate and reliable annotations.\r\n\r\nThe corpus is further described in:\r\nERJAVEC, Toma\u017e, \u010cIBEJ, Jaka, ARHAR HOLDT, \u0160pela, LJUBE\u0160I\u0106, Nikola, FI\u0160ER, Darja. Gold-standard datasets for annotation of Slovene computer-mediated communication. In Proceedings of RASLAN 2016: Recent Advances in Slavonic Natural Language Processing. Brno: Tribun EU, 2016, pp. 29-40, https://nlp.fi.muni.cz/raslan/raslan16.pdf\r\n\r\nNote that a related corpus, Janes-Norm is also available, cf. http://hdl.handle.net/11356/1080.;2016-12-22;corpus;http://hdl.handle.net/11356/1079;slv;http://hdl.handle.net/11356/1081;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);PUB;https://creativecommons.org/licenses/by-sa/4.0/;application/pdf;application/pdf;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 4;Jo\u017eef Stefan Institute;http://nl.ijs.si/janes/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e9408f0e-17f7-536a-b99a-7112c50f28a4",
-    "notes": [
-        "Janes-Tag is a manually annotated corpus of Slovene Computer-Mediated Communication (CMC). It is meant as a gold-standard training and testing dataset for tokenisation, sentence segmentation, word normalisation, morphosyntactic tagging and lemmatisation of non-standard Slovene. As the corpus has been carefully manually annotated, it is also suitable for detailed linguistic explorations which require higlhy accurate and reliable annotations.\r\n\r\nThe corpus is further described in:\r\nERJAVEC, Toma\u017e, \u010cIBEJ, Jaka, ARHAR HOLDT, \u0160pela, LJUBE\u0160I\u0106, Nikola, FI\u0160ER, Darja. Gold-standard datasets for annotation of Slovene computer-mediated communication. In Proceedings of RASLAN 2016: Recent Advances in Slavonic Natural Language Processing. Brno: Tribun EU, 2016, pp. 29-40, https://nlp.fi.muni.cz/raslan/raslan16.pdf\r\n\r\nNote that a related corpus, Janes-Norm is also available, cf. http://hdl.handle.net/11356/1080."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1079"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "computer-mediated communication"
-        },
-        {
-            "name": "tokenisation"
-        },
-        {
-            "name": "word normalisation"
-        },
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "lemmatisation"
-        },
-        {
-            "name": "manual annotation"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "CMC training corpus Janes-Tag 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e94e1758-8458-5173-ac28-2e156f59b95a.json b/oaitestdata/clarin-oai_dc/SET_1/json/e94e1758-8458-5173-ac28-2e156f59b95a.json
deleted file mode 100644
index e9f4eb44..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e94e1758-8458-5173-ac28-2e156f59b95a.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48FC-D",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48FC-D"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-48FC-D",
-    "PublicationTimestamp": "2009-11-02T09:34:32Z",
-    "PublicationYear": [
-        "2009"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU General Public License, version 2",
-        "http://www.gnu.org/licenses/gpl-2.0.html",
-        "PUB"
-    ],
-    "author": [
-        "Klus\u00e1\u010dek, David"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48FC-D;2018-07-02T22:05:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;MMI_clustering;Klus\u00e1\u010dek, David;clustering;MMI_clustering is a set of command line tools implementing Mercer's maximum mutual information-based clustering technique.;2009-11-02T09:34:32Z;toolService;http://hdl.handle.net/11858/00-097C-0000-0001-48FC-D;GNU General Public License, version 2;http://www.gnu.org/licenses/gpl-2.0.html;PUB;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/tools/mmic",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e94e1758-8458-5173-ac28-2e156f59b95a",
-    "notes": [
-        "MMI_clustering is a set of command line tools implementing Mercer's maximum mutual information-based clustering technique."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48FC-D"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "clustering"
-        }
-    ],
-    "title": [
-        "MMI_clustering"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e96296c8-27f9-5c8a-904c-a331510579f6.json b/oaitestdata/clarin-oai_dc/SET_1/json/e96296c8-27f9-5c8a-904c-a331510579f6.json
deleted file mode 100644
index 97e40b13..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e96296c8-27f9-5c8a-904c-a331510579f6.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3408",
-    "MetadataAccess": [
-        "oai:ota:oucs:3408"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Duck, Stephen, 1705-1756."
-    ],
-    "fulltext": "oai:ota:oucs:3408;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3408.xml;A poem on the marriage of His serene Highness the Prince of Orange: with Ann Princess-Royal of Great Britain. By Stephen Duck. To which are added, Verses to the author, by a divine. With the author's answer.;Duck, Stephen, 1705-1756.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e96296c8-27f9-5c8a-904c-a331510579f6",
-    "oai_identifier": [
-        "oai:ota:oucs:3408"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A poem on the marriage of His serene Highness the Prince of Orange: with Ann Princess-Royal of Great Britain. By Stephen Duck. To which are added, Verses to the author, by a divine. With the author's answer."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3408.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e9738266-8703-5f3f-b9e6-b11bf535d2f1.json b/oaitestdata/clarin-oai_dc/SET_1/json/e9738266-8703-5f3f-b9e6-b11bf535d2f1.json
deleted file mode 100644
index 026e59a7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e9738266-8703-5f3f-b9e6-b11bf535d2f1.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "less than 512 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0591",
-    "MetadataAccess": [
-        "oai:ota:oucs:0591"
-    ],
-    "PublicationTimestamp": "1931-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1931"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Textbooks"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Zimmerman, Carle Clark,  1897-"
-    ],
-    "fulltext": "oai:ota:oucs:0591;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0591.xml; Siam  : rural economic survey, 1930-31 / compiled by C.J. Howgego;Zimmerman, Carle Clark,  1897-;1931;text_and_corpus_linguistics;Textbooks -- Thailand -- 20th century;eng;Oxford Text Archive, University of Oxford;less than 512 KB;Text;Textbooks;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e9738266-8703-5f3f-b9e6-b11bf535d2f1",
-    "oai_identifier": [
-        "oai:ota:oucs:0591"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Textbooks -- Thailand -- th century"
-        }
-    ],
-    "title": [
-        " Siam  : rural economic survey, 1930-31 / compiled by C.J. Howgego"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0591.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e9749975-7148-5236-a43a-ead31cc04e26.json b/oaitestdata/clarin-oai_dc/SET_1/json/e9749975-7148-5236-a43a-ead31cc04e26.json
deleted file mode 100644
index 88585eac..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e9749975-7148-5236-a43a-ead31cc04e26.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Abeill\u00e9, Anne"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "French"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-197",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-197"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-197",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "France"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-197;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Corpus arbor\u00e9e du fran\u00e7ais;Abeill\u00e9, Anne;800.000 words, POS and syntax, proprietary XML;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-197;fra;downloadable_files_count: 0;France;http://www.llf.cnrs.fr/Gens/Abeille/French-Treebank-fr.php",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e9749975-7148-5236-a43a-ead31cc04e26",
-    "notes": [
-        "800.000 words, POS and syntax, proprietary XML"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-197"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus arbor\u00e9e du fran\u00e7ais"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e98ece44-0ac7-5332-8357-0c49e6fd7cbe.json b/oaitestdata/clarin-oai_dc/SET_1/json/e98ece44-0ac7-5332-8357-0c49e6fd7cbe.json
deleted file mode 100644
index 8e524572..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e98ece44-0ac7-5332-8357-0c49e6fd7cbe.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Ainiala, Terhi"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Finnish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-179",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-179"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-179",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Finland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-179;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;The Atlas of Place Names (Paikannimikartasto);Ainiala, Terhi;Finnish place names;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-179;fin;downloadable_files_count: 0;Finland;http://kaino.kotus.fi",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e98ece44-0ac7-5332-8357-0c49e6fd7cbe",
-    "notes": [
-        "Finnish place names"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-179"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "The Atlas of Place Names (Paikannimikartasto)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e990172f-b596-55b5-bea3-2f937127b708.json b/oaitestdata/clarin-oai_dc/SET_1/json/e990172f-b596-55b5-bea3-2f937127b708.json
deleted file mode 100644
index 90cd77e6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e990172f-b596-55b5-bea3-2f937127b708.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "between 512 KB and 1 MB "
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0684",
-    "MetadataAccess": [
-        "oai:ota:oucs:0684"
-    ],
-    "PublicationTimestamp": "1984-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1984"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Local histories"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Berton, Pierre,  1920-"
-    ],
-    "fulltext": "oai:ota:oucs:0684;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0684.xml;The promised land  settling the West 1896-1914 / compiled by W.C. Lougheed for the Strathy Language Unit;Berton, Pierre,  1920-;1984;text_and_corpus_linguistics;Local histories -- Canada -- 20th century;eng;Oxford Text Archive, University of Oxford;between 512 KB and 1 MB ;Text;Local histories;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e990172f-b596-55b5-bea3-2f937127b708",
-    "oai_identifier": [
-        "oai:ota:oucs:0684"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Local histories -- Canada -- th century"
-        }
-    ],
-    "title": [
-        "The promised land  settling the West 1896-1914 / compiled by W.C. Lougheed for the Strathy Language Unit"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0684.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e998d029-c45a-5fdf-990a-6ef642c33fa5.json b/oaitestdata/clarin-oai_dc/SET_1/json/e998d029-c45a-5fdf-990a-6ef642c33fa5.json
deleted file mode 100644
index 44b5dc8a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e998d029-c45a-5fdf-990a-6ef642c33fa5.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/plain",
-        "application/octet-stream",
-        "downloadable_files_count: 5",
-        "application/zip",
-        "application/pdf"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/266",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/266"
-    ],
-    "PID": "http://hdl.handle.net/11321/266",
-    "PublicationTimestamp": "2016-05-29T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "BSD 2 Clause",
-        "https://opensource.org/licenses/BSD-2-Clause",
-        "PUB"
-    ],
-    "author": [
-        "Rychlik, Piotr"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/266;2016-05-29T12:15:19Z;hdl_11321_3;hdl_11321_4;TermoPL;Rychlik, Piotr;terminology extraction;domain corpora;C-value;TermoPL is a tool for terminology extraction from domain corpora in Polish.;2016-05-29;toolService;http://hdl.handle.net/11321/266;pol;BSD 2 Clause;https://opensource.org/licenses/BSD-2-Clause;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/zip;text/plain;application/zip;application/zip;application/pdf;downloadable_files_count: 5;Institute of Computer Science, Polish Academy of Sciences",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e998d029-c45a-5fdf-990a-6ef642c33fa5",
-    "notes": [
-        "TermoPL is a tool for terminology extraction from domain corpora in Polish."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/266"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "terminology extraction"
-        },
-        {
-            "name": "domain corpora"
-        },
-        {
-            "name": "C-value"
-        }
-    ],
-    "title": [
-        "TermoPL"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e9be345f-837b-5834-bcac-e6033f04a494.json b/oaitestdata/clarin-oai_dc/SET_1/json/e9be345f-837b-5834-bcac-e6033f04a494.json
deleted file mode 100644
index 16e711ba..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e9be345f-837b-5834-bcac-e6033f04a494.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "[Franciszek Cezary]"
-    ],
-    "Contributor": [
-        "Bia\u0142ecki, Piotr Jan (ca 1640-post 1686). Aut. ded.",
-        "Cezary, Franciszek (ca 1660-1724). Druk."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-107563",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-107563"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CD7-1",
-    "PublicationTimestamp": "1678-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1678"
-    ],
-    "Publisher": [
-        "[Franciszek Cezary]"
-    ],
-    "RelatedIdentifier": [
-        "http://ebuw.uw.edu.pl/Content/107563",
-        "oai:ebuw.uw.edu.pl:publication:104552"
-    ],
-    "ResourceType": [
-        "early book"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "author": [
-        "Klonowic, Sebastian Fabian (1545-1602)."
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-107563;2019-02-28T18:01:12Z;Pami\u0119tnik Xi\u0105z\u0105t Y Krolow Polskich Sebastiana Fabiana Klonowica.;Klonowic, Sebastian Fabian (1545-1602).;Poland -- Kings and rulers -- Early works to 1800.;Inscription: \"Przewielebnemv I. Mci. Xiedzv Woyciechowi Szczerskiemv Zakonu Pr\u00e6monstrate\u0144skiego S. Norberta Proboszczowi P\u0142ockiemu [...] / Piotr Ian z Bia\u0142ocina Bia\u0142ecki, Pisarz Grodzki Siewierski\".;Place of Publication: Cracow - Poland.;Adresat dedykacji: Szczerski, Wojciech ( -post 1685).;Dedykacja: \"Przewielebnemv I. Mci. Xiedzv Woyciechowi Szczerskiemv Zakonu Pr\u00e6monstrate\u0144skiego S. Norberta Proboszczowi P\u0142ockiemu [...] / Piotr Ian z Bia\u0142ocina Bia\u0142ecki, Pisarz Grodzki Siewierski\".;Na drugiej karcie nieliczbowanej drzeworytowy herb Ogo\u0144czyk Szczerskiego oraz wiersz na herb.;Na stronie tytu\u0142owej data wydania w chronogramie: \"Anno QVo poLonI De tVrCis fVgatIs triVMphant, Sev Posteriori post eum QVo aD HoCIM poLonI eos fortIter fVgaVerVnt.\" [i.e. 1678].;Wsp\u00f3\u0142czesna nazwa miejsca wydania: Krak\u00f3w - Polska.;[Wydanie:] Znowu z Przydatkiem y wyliczeniem Monosticorvm Piotra Iana z Bia\u0142ocina Bia\u0142eckiego [...] Do Druku podany [...].;Zapowied\u017a wsp\u00f3\u0142wydanego \"Monostica\" z tytu\u0142em nag\u0142\u00f3wka (karta B3).;[Franciszek Cezary];Bia\u0142ecki, Piotr Jan (ca 1640-post 1686). Aut. ded.;Cezary, Franciszek (ca 1660-1724). Druk.;1678;early book;application/xml;clarind-uds:poldilemma-107563;hdl:11858/00-246C-0000-0023-8CD7-1;Sd.713.2653;pol;lat;http://ebuw.uw.edu.pl/Content/107563;oai:ebuw.uw.edu.pl:publication:104552;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e9be345f-837b-5834-bcac-e6033f04a494",
-    "notes": [
-        "Inscription: \"Przewielebnemv I. Mci. Xiedzv Woyciechowi Szczerskiemv Zakonu Pr\u00e6monstrate\u0144skiego S. Norberta Proboszczowi P\u0142ockiemu [...] / Piotr Ian z Bia\u0142ocina Bia\u0142ecki, Pisarz Grodzki Siewierski\".",
-        "Place of Publication: Cracow - Poland.",
-        "Adresat dedykacji: Szczerski, Wojciech ( -post 1685).",
-        "Dedykacja: \"Przewielebnemv I. Mci. Xiedzv Woyciechowi Szczerskiemv Zakonu Pr\u00e6monstrate\u0144skiego S. Norberta Proboszczowi P\u0142ockiemu [...] / Piotr Ian z Bia\u0142ocina Bia\u0142ecki, Pisarz Grodzki Siewierski\".",
-        "Na drugiej karcie nieliczbowanej drzeworytowy herb Ogo\u0144czyk Szczerskiego oraz wiersz na herb.",
-        "Na stronie tytu\u0142owej data wydania w chronogramie: \"Anno QVo poLonI De tVrCis fVgatIs triVMphant, Sev Posteriori post eum QVo aD HoCIM poLonI eos fortIter fVgaVerVnt.\" [i.e. 1678].",
-        "Wsp\u00f3\u0142czesna nazwa miejsca wydania: Krak\u00f3w - Polska.",
-        "[Wydanie:] Znowu z Przydatkiem y wyliczeniem Monosticorvm Piotra Iana z Bia\u0142ocina Bia\u0142eckiego [...] Do Druku podany [...].",
-        "Zapowied\u017a wsp\u00f3\u0142wydanego \"Monostica\" z tytu\u0142em nag\u0142\u00f3wka (karta B3)."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-107563"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Pami\u0119tnik Xi\u0105z\u0105t Y Krolow Polskich Sebastiana Fabiana Klonowica."
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/e9f8e7c7-a286-500b-913b-785b454587de.json b/oaitestdata/clarin-oai_dc/SET_1/json/e9f8e7c7-a286-500b-913b-785b454587de.json
deleted file mode 100644
index fd3c597d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/e9f8e7c7-a286-500b-913b-785b454587de.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1836",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1836"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1836",
-    "PublicationTimestamp": "2016-11-15T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-1674"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Straka, Milan",
-        "Strakov\u00e1, Jana"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1836;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Czech Models (MorfFlex CZ 161115 + PDT 3.0) for MorphoDiTa 161115;Straka, Milan;Strakov\u00e1, Jana;MorphoDiTa;Czech;morphological analysis;morphological generation;PoS tagging;Czech models for MorphoDiTa, providing morphological analysis, morphological generation and part-of-speech tagging.\r\n\r\nThe morphological dictionary is created from MorfFlex CZ 161115 and DeriNet 1.2 and the PoS tagger is trained on Prague Dependency Treebank 3.0 (PDT).;2016-11-15;languageDescription;http://hdl.handle.net/11234/1-1836;ces;http://hdl.handle.net/11234/1-1674;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/morphodita/users-manual#czech-morfflex-pdt",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e9f8e7c7-a286-500b-913b-785b454587de",
-    "notes": [
-        "Czech models for MorphoDiTa, providing morphological analysis, morphological generation and part-of-speech tagging.\r\n\r\nThe morphological dictionary is created from MorfFlex CZ 161115 and DeriNet 1.2 and the PoS tagger is trained on Prague Dependency Treebank 3.0 (PDT)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1836"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "MorphoDiTa"
-        },
-        {
-            "name": "Czech"
-        },
-        {
-            "name": "morphological analysis"
-        },
-        {
-            "name": "morphological generation"
-        },
-        {
-            "name": "PoS tagging"
-        }
-    ],
-    "title": [
-        "Czech Models (MorfFlex CZ 161115 + PDT 3.0) for MorphoDiTa 161115"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ea08f609-ae8e-52ad-aaf9-fa377de8c198.json b/oaitestdata/clarin-oai_dc/SET_1/json/ea08f609-ae8e-52ad-aaf9-fa377de8c198.json
deleted file mode 100644
index 73b283d1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ea08f609-ae8e-52ad-aaf9-fa377de8c198.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "IFIS PAN"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "downloadable_files_count: 10",
-        "application/vnd.oasis.opendocument.text",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/409",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/409"
-    ],
-    "PID": "http://hdl.handle.net/11321/409",
-    "PublicationTimestamp": "2017-06-29T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "IFIS PAN"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Szulc, B.J",
-        "Kowallski, Jan, Jr"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/409;2017-06-29T07:52:35Z;hdl_11321_3;hdl_11321_4;Korpus testowy;Kowallski, Jan, Jr;Szulc, B.J;literatura pi\u0119kna,;literatura polska;korpus testowy na warsztaty clarin-pl;2017-06-29;corpus;http://hdl.handle.net/11321/409;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;text/plain;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.oasis.opendocument.text;text/plain;text/plain;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;downloadable_files_count: 10;IFIS PAN",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ea08f609-ae8e-52ad-aaf9-fa377de8c198",
-    "notes": [
-        "korpus testowy na warsztaty clarin-pl"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/409"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "literatura pi\u0119kna"
-        },
-        {
-            "name": "literatura polska"
-        }
-    ],
-    "title": [
-        "Korpus testowy"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ea1ddad4-f4e9-5172-8b79-6b1538fb2225.json b/oaitestdata/clarin-oai_dc/SET_1/json/ea1ddad4-f4e9-5172-8b79-6b1538fb2225.json
deleted file mode 100644
index e6dc4480..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ea1ddad4-f4e9-5172-8b79-6b1538fb2225.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 63.9 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2176",
-    "MetadataAccess": [
-        "oai:ota:oucs:2176"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "James, William, 1842-1910"
-    ],
-    "fulltext": "oai:ota:oucs:2176;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/2176.xml;Great men and their environment / by William James;James, William, 1842-1910;text_and_corpus_linguistics;Periodicals -- United States -- 19th century;Essays -- United States -- 19th century;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 63.9 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ea1ddad4-f4e9-5172-8b79-6b1538fb2225",
-    "oai_identifier": [
-        "oai:ota:oucs:2176"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Periodicals -- United States -- th century"
-        },
-        {
-            "name": "Essays -- United States -- th century"
-        }
-    ],
-    "title": [
-        "Great men and their environment / by William James"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2176.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ea4dbe42-53be-52a2-a9c2-9c6eca6e1232.json b/oaitestdata/clarin-oai_dc/SET_1/json/ea4dbe42-53be-52a2-a9c2-9c6eca6e1232.json
deleted file mode 100644
index c67953f0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ea4dbe42-53be-52a2-a9c2-9c6eca6e1232.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=49afdae26c8f11e2a2aa782bcb0741352ec66561ece64d8dbc26b09f0bead921",
-    "MetadataAccess": [
-        "49afdae26c8f11e2a2aa782bcb0741352ec66561ece64d8dbc26b09f0bead921"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "49afdae26c8f11e2a2aa782bcb0741352ec66561ece64d8dbc26b09f0bead921;2018-11-15T16:40:11Z;toolService;toolService:service;U-Compare Named Entity Recognition service;Web service created by exporting UIMA-based workflow from the U-Compare text mining system.\nFunctionality: Identifies biomedical named entities (genes and proteins) in plain text. Also identifies sentences. \nTools in workflow: Cafetiere Sentence Splitter (University of Manchester), NEMine (University of Manchester)\nNOTE: The licence provided covers the web service only. Tools used to create the workflow may have their own licences\n;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ea4dbe42-53be-52a2-a9c2-9c6eca6e1232",
-    "notes": [
-        "Web service created by exporting UIMA-based workflow from the U-Compare text mining system.\nFunctionality: Identifies biomedical named entities (genes and proteins) in plain text. Also identifies sentences. \nTools in workflow: Cafetiere Sentence Splitter (University of Manchester), NEMine (University of Manchester)\nNOTE: The licence provided covers the web service only. Tools used to create the workflow may have their own licences\n"
-    ],
-    "oai_identifier": [
-        "49afdae26c8f11e2a2aa782bcb0741352ec66561ece64d8dbc26b09f0bead921"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:service"
-    ],
-    "state": "active",
-    "title": [
-        "U-Compare Named Entity Recognition service"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ea78e398-f809-54c1-8a2c-f3381e3e0f75.json b/oaitestdata/clarin-oai_dc/SET_1/json/ea78e398-f809-54c1-8a2c-f3381e3e0f75.json
deleted file mode 100644
index 085f3324..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ea78e398-f809-54c1-8a2c-f3381e3e0f75.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/5-CESILKO",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/5-CESILKO"
-    ],
-    "PID": "http://hdl.handle.net/11234/5-CESILKO",
-    "PublicationTimestamp": "2014-05-06T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Haji\u010d, Jan",
-        "Homola, Petr",
-        "Kubo\u0148, Vladislav"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/5-CESILKO;2017-11-09T14:20:26Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0023-8C33-2;Cesilko Web Service for Weblicht;Haji\u010d, Jan;Kubo\u0148, Vladislav;Homola, Petr;machine translation;Weblicht integration of Cesilko (http://hdl.handle.net/11858/00-097C-0000-0006-AAFE-A);2014-05-06;toolService;http://hdl.handle.net/11234/5-CESILKO;application/octet-stream;application/octet-stream;downloadable_files_count: 0;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ea78e398-f809-54c1-8a2c-f3381e3e0f75",
-    "notes": [
-        "Weblicht integration of Cesilko (http://hdl.handle.net/11858/00-097C-0000-0006-AAFE-A)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/5-CESILKO"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0023-8C33-2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine translation"
-        }
-    ],
-    "title": [
-        "Cesilko Web Service for Weblicht"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ea8360d3-2cc1-515d-b36a-8f5bc7874e4b.json b/oaitestdata/clarin-oai_dc/SET_1/json/ea8360d3-2cc1-515d-b36a-8f5bc7874e4b.json
deleted file mode 100644
index 22e62c01..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ea8360d3-2cc1-515d-b36a-8f5bc7874e4b.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4755",
-    "MetadataAccess": [
-        "oai:ota:oucs:4755"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gerard, Alexander, 1728-1795."
-    ],
-    "fulltext": "oai:ota:oucs:4755;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4755.xml;Sermons, by Alexander Gerard, D.D.: [pt.2];Gerard, Alexander, 1728-1795.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ea8360d3-2cc1-515d-b36a-8f5bc7874e4b",
-    "oai_identifier": [
-        "oai:ota:oucs:4755"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Sermons, by Alexander Gerard, D.D.: [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4755.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/eaa6c2ab-4db2-5657-985f-ede7333dcfff.json b/oaitestdata/clarin-oai_dc/SET_1/json/eaa6c2ab-4db2-5657-985f-ede7333dcfff.json
deleted file mode 100644
index 935a8a8f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/eaa6c2ab-4db2-5657-985f-ede7333dcfff.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Royster, Paul"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 443 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1644",
-    "MetadataAccess": [
-        "oai:ota:oucs:1644"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Travel literature"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Thoreau, Henry David, 1817-1862"
-    ],
-    "fulltext": "oai:ota:oucs:1644;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1644.xml;Cape Cod / Henry David Thoreau;Thoreau, Henry David, 1817-1862;text_and_corpus_linguistics;Philosophy, American -- 19th century;Oxford Text Archive, University of Oxford;Royster, Paul;text/sgml;(1 file : ca. 443 KB);Text;Travel literature;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "eaa6c2ab-4db2-5657-985f-ede7333dcfff",
-    "oai_identifier": [
-        "oai:ota:oucs:1644"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Philosophy"
-        },
-        {
-            "name": "American -- th century"
-        }
-    ],
-    "title": [
-        "Cape Cod / Henry David Thoreau"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1644.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/eaa86edc-26e4-5514-b65a-f897e0acd198.json b/oaitestdata/clarin-oai_dc/SET_1/json/eaa86edc-26e4-5514-b65a-f897e0acd198.json
deleted file mode 100644
index f70c9f2d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/eaa86edc-26e4-5514-b65a-f897e0acd198.json
+++ /dev/null
@@ -1,99 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 3",
-        "application/pdf",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Croatian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1095",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1095"
-    ],
-    "PID": "http://hdl.handle.net/11356/1095",
-    "PublicationTimestamp": "2017-04-04T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11356/1121"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "Filko, Matea",
-        "Erjavec, Toma\u017e",
-        "Farka\u0161, Da\u0161a",
-        "Ljube\u0161i\u0107, Nikola",
-        "Dujmi\u0107, Barbara",
-        "Klubi\u010dka, Filip",
-        "Mili\u010devi\u0107, Maja",
-        "Kranj\u010di\u0107, Denis"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1095;2018-10-18T22:26:25Z;hdl_11356_1023;hdl_11356_1024;Croatian Twitter training corpus ReLDI-NormTag-hr 1.0;Ljube\u0161i\u0107, Nikola;Farka\u0161, Da\u0161a;Klubi\u010dka, Filip;Erjavec, Toma\u017e;Mili\u010devi\u0107, Maja;Filko, Matea;Kranj\u010di\u0107, Denis;Dujmi\u0107, Barbara;computer-mediated communication;tokenisation;word normalisation;tagging;lemmatisation;manual annotation;TEI;ReLDI-NormTag-hr 1.0 is a manually annotated corpus of Croatian tweets. It is meant as a gold-standard training and testing dataset for tokenisation, sentence segmentation, word normalisation, morphosyntactic tagging and lemmatisation of non-standard Croatian. Each tweet is also annotated for its automatically assigned standardness levels (T = technical standardness, L = linguistic standardness). \r\n\r\nThe corpus construction is (partially) described in: \r\nMILI\u010cEVI\u0106, Maja, LJUBE\u0160I\u0106, Nikola. Tviterasi, tvitera\u0161i or twittera\u0161i? Producing and analysing a normalised dataset of Croatian and Serbian tweets. Sloven\u0161\u010dina 2.0: empirical, applied and interdisciplinary research, 4/2, 2016. ISSN 2335-2736. http://dx.doi.org/10.4312/slo2.0.2016.2.156-188;2017-04-04;corpus;http://hdl.handle.net/11356/1095;hrv;http://hdl.handle.net/11356/1121;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;https://creativecommons.org/licenses/by/4.0/;application/zip;application/zip;application/pdf;text/plain; charset=utf-8;downloadable_files_count: 3;Jo\u017eef Stefan Institute;https://reldi.spur.uzh.ch/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "eaa86edc-26e4-5514-b65a-f897e0acd198",
-    "notes": [
-        "ReLDI-NormTag-hr 1.0 is a manually annotated corpus of Croatian tweets. It is meant as a gold-standard training and testing dataset for tokenisation, sentence segmentation, word normalisation, morphosyntactic tagging and lemmatisation of non-standard Croatian. Each tweet is also annotated for its automatically assigned standardness levels (T = technical standardness, L = linguistic standardness). \r\n\r\nThe corpus construction is (partially) described in: \r\nMILI\u010cEVI\u0106, Maja, LJUBE\u0160I\u0106, Nikola. Tviterasi, tvitera\u0161i or twittera\u0161i? Producing and analysing a normalised dataset of Croatian and Serbian tweets. Sloven\u0161\u010dina 2.0: empirical, applied and interdisciplinary research, 4/2, 2016. ISSN 2335-2736. http://dx.doi.org/10.4312/slo2.0.2016.2.156-188"
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1095"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "computer-mediated communication"
-        },
-        {
-            "name": "tokenisation"
-        },
-        {
-            "name": "word normalisation"
-        },
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "lemmatisation"
-        },
-        {
-            "name": "manual annotation"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "Croatian Twitter training corpus ReLDI-NormTag-hr 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/eac005e4-e958-5211-9568-f611692e3c07.json b/oaitestdata/clarin-oai_dc/SET_1/json/eac005e4-e958-5211-9568-f611692e3c07.json
deleted file mode 100644
index 29c230f2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/eac005e4-e958-5211-9568-f611692e3c07.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/106",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/106"
-    ],
-    "PID": "http://hdl.handle.net/10794/106",
-    "PublicationTimestamp": "2013-03-06T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/106;2017-10-25T06:36:30Z;hdl_10794_1;hdl_10794_2;Blog mix 2012 (2017-02-24);Bloggmix 2012 (2017-02-24);n/a, n/a;Swedish;Blog;The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.;Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat.;2013-03-06;corpus;http://hdl.handle.net/10794/106;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/bloggmix2012",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "eac005e4-e958-5211-9568-f611692e3c07",
-    "notes": [
-        "The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.",
-        "Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/106"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Blog"
-        }
-    ],
-    "title": [
-        "Blog mix 2012 (2017-02-24)",
-        "Bloggmix 2012 (2017-02-24)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/eac5f7bc-e371-5ac9-89e2-ac9fc9705571.json b/oaitestdata/clarin-oai_dc/SET_1/json/eac5f7bc-e371-5ac9-89e2-ac9fc9705571.json
deleted file mode 100644
index 79d4bcfd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/eac5f7bc-e371-5ac9-89e2-ac9fc9705571.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "University of Tampere"
-    ],
-    "Contributor": [
-        "Mikhailov, Mikhail",
-        "Isolahti, Nina"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "English",
-        "German",
-        "Russian",
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1078",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1078"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1078",
-    "PublicationTimestamp": "2007-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2007"
-    ],
-    "Publisher": [
-        "University of Tampere"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Finland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1078;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Multilingual corpus of juridical texts;Mikhailov, Mikhail;Isolahti, Nina;parallel corpus;multilingual;International conventions and treaties arranged as a paralell corpus aligned on paragraph level;2007;corpus;http://hdl.handle.net/11372/LRT-1078;eng;deu;rus;swe;application/octet-stream;downloadable_files_count: 0;Finland;University of Tampere;https://mustikka.uta.fi/corpora",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "eac5f7bc-e371-5ac9-89e2-ac9fc9705571",
-    "notes": [
-        "International conventions and treaties arranged as a paralell corpus aligned on paragraph level"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1078"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parallel corpus"
-        },
-        {
-            "name": "multilingual"
-        }
-    ],
-    "title": [
-        "Multilingual corpus of juridical texts"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/eafcb5c4-e0b9-568d-91bd-d32753e25dd6.json b/oaitestdata/clarin-oai_dc/SET_1/json/eafcb5c4-e0b9-568d-91bd-d32753e25dd6.json
deleted file mode 100644
index eb22266b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/eafcb5c4-e0b9-568d-91bd-d32753e25dd6.json
+++ /dev/null
@@ -1,40 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=362a2020cf5711e1a404080027e73ea28eaaf998e9aa47739841451ea4e16f51",
-    "MetadataAccess": [
-        "362a2020cf5711e1a404080027e73ea28eaaf998e9aa47739841451ea4e16f51"
-    ],
-    "PublicationTimestamp": "2015-12-14T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "362a2020cf5711e1a404080027e73ea28eaaf998e9aa47739841451ea4e16f51;2019-02-27T12:08:52Z;corpus;corpus:text;corpus:audio;corpus:text:audio;C-ORAL-ROM_EXM;This resource includes a spoken corpus with approximately 300.000 words, covering both formal (152.755 words) and informal (165.838 words) speech, with aligned sound and orthographic transcription and POS-tag information.;2015-12-14",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "eafcb5c4-e0b9-568d-91bd-d32753e25dd6",
-    "notes": [
-        "This resource includes a spoken corpus with approximately 300.000 words, covering both formal (152.755 words) and informal (165.838 words) speech, with aligned sound and orthographic transcription and POS-tag information."
-    ],
-    "oai_identifier": [
-        "362a2020cf5711e1a404080027e73ea28eaaf998e9aa47739841451ea4e16f51"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text",
-        "corpus:audio",
-        "corpus:text:audio"
-    ],
-    "state": "active",
-    "title": [
-        "C-ORAL-ROM_EXM"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/eaffc980-87d6-5fc5-8dfe-e2f1e82479c7.json b/oaitestdata/clarin-oai_dc/SET_1/json/eaffc980-87d6-5fc5-8dfe-e2f1e82479c7.json
deleted file mode 100644
index b2cedee0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/eaffc980-87d6-5fc5-8dfe-e2f1e82479c7.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4519",
-    "MetadataAccess": [
-        "oai:ota:oucs:4519"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Defoe, Daniel, 1661?-1731."
-    ],
-    "fulltext": "oai:ota:oucs:4519;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4519.xml;Every-body's business, is no-body's business: or, private abuses, publick grievances: exemplified in the pride, insolence, and exorbitant wages of our women-servants, footmen, &c. With a proposal for amendment of the same; ... By Andrew Moreton, Esq;.;Defoe, Daniel, 1661?-1731.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "eaffc980-87d6-5fc5-8dfe-e2f1e82479c7",
-    "oai_identifier": [
-        "oai:ota:oucs:4519"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Every-body's business, is no-body's business: or, private abuses, publick grievances: exemplified in the pride, insolence, and exorbitant wages of our women-servants, footmen, &c. With a proposal for amendment of the same; ... By Andrew Moreton, Esq;."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4519.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/eb2b85df-deb8-5a26-82a3-7966ea6af390.json b/oaitestdata/clarin-oai_dc/SET_1/json/eb2b85df-deb8-5a26-82a3-7966ea6af390.json
deleted file mode 100644
index e2273c58..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/eb2b85df-deb8-5a26-82a3-7966ea6af390.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Arts, Institute of the Czech National Corpus"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1847",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1847"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1847",
-    "PublicationTimestamp": "2016-12-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Arts, Institute of the Czech National Corpus"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Bene\u0161ov\u00e1, Lucie",
-        "Waclawi\u010dov\u00e1, Martina",
-        "K\u0159en, Michal"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1847;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;ORAL2013: balanced corpus of informal spoken Czech (transcriptions);Bene\u0161ov\u00e1, Lucie;K\u0159en, Michal;Waclawi\u010dov\u00e1, Martina;balanced corpus;spoken language;ORAL2013 is designed as a representation of authentic spoken Czech used in informal situations (private environment, spontaneity, unpreparedness etc.) in the area of the whole Czech Republic. The corpus comprises 835 recordings from 2008\u20132011 that contain 2 785 189 words (i.e. 3 285 508 tokens including punctuation) uttered by 2 544 speakers, out of which 1 297 speakers are unique. ORAL2013 is balanced in the main sociolinguistic categories of speakers (gender, age group, education, region of childhood residence).\r\n\r\nThe corpus is provided in a (semi-XML) vertical format used as an input to the Manatee query engine. The data thus correspond to the corpus available via the KonText query engine to registered users of the CNC at http://www.korpus.cz\r\n\r\nPlease note: this item includes only the transcriptions, audio is available under more restrictive non-CC license at http://hdl.handle.net/11234/1-1848;2016-12-01;corpus;http://hdl.handle.net/11234/1-1847;ces;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;text/plain; charset=utf-8;application/x-gzip;downloadable_files_count: 1;Charles University, Faculty of Arts, Institute of the Czech National Corpus;http://wiki.korpus.cz/doku.php/cnk:oral2013",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "eb2b85df-deb8-5a26-82a3-7966ea6af390",
-    "notes": [
-        "ORAL2013 is designed as a representation of authentic spoken Czech used in informal situations (private environment, spontaneity, unpreparedness etc.) in the area of the whole Czech Republic. The corpus comprises 835 recordings from 2008\u20132011 that contain 2 785 189 words (i.e. 3 285 508 tokens including punctuation) uttered by 2 544 speakers, out of which 1 297 speakers are unique. ORAL2013 is balanced in the main sociolinguistic categories of speakers (gender, age group, education, region of childhood residence).\r\n\r\nThe corpus is provided in a (semi-XML) vertical format used as an input to the Manatee query engine. The data thus correspond to the corpus available via the KonText query engine to registered users of the CNC at http://www.korpus.cz\r\n\r\nPlease note: this item includes only the transcriptions, audio is available under more restrictive non-CC license at http://hdl.handle.net/11234/1-1848"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1847"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "balanced corpus"
-        },
-        {
-            "name": "spoken language"
-        }
-    ],
-    "title": [
-        "ORAL2013: balanced corpus of informal spoken Czech (transcriptions)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/eb433b9d-7bfd-547d-b8d5-a6ede319def8.json b/oaitestdata/clarin-oai_dc/SET_1/json/eb433b9d-7bfd-547d-b8d5-a6ede319def8.json
deleted file mode 100644
index 27248b5a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/eb433b9d-7bfd-547d-b8d5-a6ede319def8.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3476",
-    "MetadataAccess": [
-        "oai:ota:oucs:3476"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "More, Hannah, 1745-1833."
-    ],
-    "fulltext": "oai:ota:oucs:3476;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3476.xml;Sacred dramas: chiefly intended for young persons: the subjects taken from the Bible. To which is added, Sensibility, a poem.;More, Hannah, 1745-1833.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "eb433b9d-7bfd-547d-b8d5-a6ede319def8",
-    "oai_identifier": [
-        "oai:ota:oucs:3476"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Sacred dramas: chiefly intended for young persons: the subjects taken from the Bible. To which is added, Sensibility, a poem."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3476.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/eb490991-24f0-5959-816e-6f680563eef0.json b/oaitestdata/clarin-oai_dc/SET_1/json/eb490991-24f0-5959-816e-6f680563eef0.json
deleted file mode 100644
index 5d9d2460..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/eb490991-24f0-5959-816e-6f680563eef0.json
+++ /dev/null
@@ -1,121 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech",
-        "English",
-        "French",
-        "German",
-        "Hungarian",
-        "Polish",
-        "Spanish",
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2122",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2122"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2122",
-    "PublicationTimestamp": "2017-04-03T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/257528",
-        "info:eu-repo/grantAgreement/EC/H2020/644753",
-        "http://hdl.handle.net/11858/00-097C-0000-0023-866E-1"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)",
-        "http://creativecommons.org/licenses/by-nc/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Libovick\u00fd, Jind\u0159ich",
-        "Haji\u010d, Jan",
-        "Du\u0161ek, Ond\u0159ej",
-        "Ure\u0161ov\u00e1, Zde\u0148ka",
-        "Hlav\u00e1\u010dov\u00e1, Jaroslava",
-        "Pecina, Pavel",
-        "Tamchyna, Ale\u0161"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2122;2017-11-09T14:20:29Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Khresmoi Summary Translation Test Data 2.0;Du\u0161ek, Ond\u0159ej;Haji\u010d, Jan;Hlav\u00e1\u010dov\u00e1, Jaroslava;Libovick\u00fd, Jind\u0159ich;Pecina, Pavel;Tamchyna, Ale\u0161;Ure\u0161ov\u00e1, Zde\u0148ka;corpus;test data;medical;health;machine translation;Czech;English;French;German;Hungarian;Polish;Spanish;Swedish;This package contains data sets for development (Section dev) and testing (Section test) of machine translation of sentences from summaries of medical articles between Czech, English, French, German, Hungarian, Polish, Spanish\r\nand Swedish. Version 2.0 extends the previous version by adding Hungarian, Polish, Spanish, and Swedish translations.;2017-04-03;corpus;http://hdl.handle.net/11234/1-2122;ces;eng;fra;deu;hun;pol;spa;swe;info:eu-repo/grantAgreement/EC/FP7/257528;info:eu-repo/grantAgreement/EC/H2020/644753;http://hdl.handle.net/11858/00-097C-0000-0023-866E-1;Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0);http://creativecommons.org/licenses/by-nc/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://khresmoi.eu http://kconnect.eu",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "eb490991-24f0-5959-816e-6f680563eef0",
-    "notes": [
-        "This package contains data sets for development (Section dev) and testing (Section test) of machine translation of sentences from summaries of medical articles between Czech, English, French, German, Hungarian, Polish, Spanish\r\nand Swedish. Version 2.0 extends the previous version by adding Hungarian, Polish, Spanish, and Swedish translations."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2122"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "test data"
-        },
-        {
-            "name": "medical"
-        },
-        {
-            "name": "health"
-        },
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "Czech"
-        },
-        {
-            "name": "English"
-        },
-        {
-            "name": "French"
-        },
-        {
-            "name": "German"
-        },
-        {
-            "name": "Hungarian"
-        },
-        {
-            "name": "Polish"
-        },
-        {
-            "name": "Spanish"
-        }
-    ],
-    "title": [
-        "Khresmoi Summary Translation Test Data 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/eb7c67c4-d1cf-5b8c-b6f3-1c9a30a40f63.json b/oaitestdata/clarin-oai_dc/SET_1/json/eb7c67c4-d1cf-5b8c-b6f3-1c9a30a40f63.json
deleted file mode 100644
index 88f64690..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/eb7c67c4-d1cf-5b8c-b6f3-1c9a30a40f63.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "Contact": [
-        "Center for Reading Research, Ghent University"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Chinese",
-        "Dutch",
-        "English",
-        "German",
-        "Modern Greek (1453-)",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1065",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1065"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1065",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Center for Reading Research, Ghent University"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1065;2016-04-06T16:39:49Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Subtitle Word Frequencies;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1065;zho;nld;eng;deu;ell;spa;downloadable_files_count: 0;Center for Reading Research, Ghent University;http://crr.ugent.be/programs-data/subtitle-frequencies",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "eb7c67c4-d1cf-5b8c-b6f3-1c9a30a40f63",
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1065"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Subtitle Word Frequencies"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/eb7c91c1-569c-5df0-8cd4-476f7e396582.json b/oaitestdata/clarin-oai_dc/SET_1/json/eb7c91c1-569c-5df0-8cd4-476f7e396582.json
deleted file mode 100644
index e04ac250..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/eb7c91c1-569c-5df0-8cd4-476f7e396582.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "The Norwegian Association of Higher Education Institutions",
-        "Universitets- og h\u00f8gskoler\u00e5det"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 2",
-        "text/xml",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "English",
-        "Norwegian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/4",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/4"
-    ],
-    "PID": "http://hdl.handle.net/11509/4",
-    "PublicationTimestamp": "2012-06-13T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "The Norwegian Association of Higher Education Institutions",
-        "Universitets- og h\u00f8gskoler\u00e5det"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11509/122"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "CC"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/4;2017-01-10T15:54:41Z;hdl_11509_1;hdl_11509_2;UHR's Termbase for Norwegian higher education institutions;UHRs termbase for universitets- og h\u00f8gskolesektoren;Lexical Conceptual Resource;Text;Terminological Resource;English;Norwegian;This is a collection of 2000 administrative terms with English - Norwegian bokm\u00e5l/Norwegian bokm\u00e5l - English and English - Norwegian nynorsk/Norwegian nynorsk - English translations, from the Norwegian Institutions of Higher Education (UHR).\r\n        The termbase translates from Norwegian bokm\u00e5l/Norwegian nynorsk to British English and the other way around.\r\n        \r\n        The term base is owned by the Norwegian Association of Higher Education Institutions (UHR) in Oslo (cf. web page: http://www.uhr.no/ressurser/temasider/terminologi).\r\n        The term base has been made downloadable in TBX format by the META-NORD group at University of Bergen, with the kind permission of UHR.\r\n        META-NORD has also assisted UHR in providing a license for the downloadable version as well as for the online, browsable version.;2012-06-13;lexicalConceptualResource;http://hdl.handle.net/11509/4;eng;nor;http://hdl.handle.net/11509/122;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;CC;application/octet-stream;application/octet-stream;text/xml;downloadable_files_count: 2;The Norwegian Association of Higher Education Institutions;Universitets- og h\u00f8gskoler\u00e5det;http://github.com/clarino/uhrtermlists/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "eb7c91c1-569c-5df0-8cd4-476f7e396582",
-    "notes": [
-        "This is a collection of 2000 administrative terms with English - Norwegian bokm\u00e5l/Norwegian bokm\u00e5l - English and English - Norwegian nynorsk/Norwegian nynorsk - English translations, from the Norwegian Institutions of Higher Education (UHR).\r\n        The termbase translates from Norwegian bokm\u00e5l/Norwegian nynorsk to British English and the other way around.\r\n        \r\n        The term base is owned by the Norwegian Association of Higher Education Institutions (UHR) in Oslo (cf. web page: http://www.uhr.no/ressurser/temasider/terminologi).\r\n        The term base has been made downloadable in TBX format by the META-NORD group at University of Bergen, with the kind permission of UHR.\r\n        META-NORD has also assisted UHR in providing a license for the downloadable version as well as for the online, browsable version."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/4"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Lexical Conceptual Resource"
-        },
-        {
-            "name": "Text"
-        },
-        {
-            "name": "Terminological Resource"
-        },
-        {
-            "name": "English"
-        },
-        {
-            "name": "Norwegian"
-        }
-    ],
-    "title": [
-        "UHR's Termbase for Norwegian higher education institutions",
-        "UHRs termbase for universitets- og h\u00f8gskolesektoren"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/eb8a8101-2b1e-5437-bab8-c5dfc6131b59.json b/oaitestdata/clarin-oai_dc/SET_1/json/eb8a8101-2b1e-5437-bab8-c5dfc6131b59.json
deleted file mode 100644
index 86d9be97..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/eb8a8101-2b1e-5437-bab8-c5dfc6131b59.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4399",
-    "MetadataAccess": [
-        "oai:ota:oucs:4399"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Radcliffe, Ann Ward, 1764-1823."
-    ],
-    "fulltext": "oai:ota:oucs:4399;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4399.xml;A Sicilian romance: By the authoress of the castles of Athlin and Dunbayne. In two volumes. ... [pt.1];Radcliffe, Ann Ward, 1764-1823.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "eb8a8101-2b1e-5437-bab8-c5dfc6131b59",
-    "oai_identifier": [
-        "oai:ota:oucs:4399"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A Sicilian romance: By the authoress of the castles of Athlin and Dunbayne. In two volumes. ... [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4399.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/eb9dc8f0-fba9-5ae0-8e69-4197529c274c.json b/oaitestdata/clarin-oai_dc/SET_1/json/eb9dc8f0-fba9-5ae0-8e69-4197529c274c.json
deleted file mode 100644
index f9b473bf..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/eb9dc8f0-fba9-5ae0-8e69-4197529c274c.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "CELGA (Centro de Esudos de Lingu\u00edstica Geral e Aplicada), University of Coimbra"
-    ],
-    "Contributor": [
-        "Martins, Cristina"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Portuguese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-393",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-393"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-393",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "CELGA (Centro de Esudos de Lingu\u00edstica Geral e Aplicada), University of Coimbra"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Portugal"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-393;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;CEC-PPC;Martins, Cristina;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-393;por;downloadable_files_count: 0;Portugal;CELGA (Centro de Esudos de Lingu\u00edstica Geral e Aplicada), University of Coimbra;http://www1.ci.uc.pt/celga/servicos/sec-ppc.htm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "eb9dc8f0-fba9-5ae0-8e69-4197529c274c",
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-393"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "CEC-PPC"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/eba982bd-9577-5c99-b453-a12c63688218.json b/oaitestdata/clarin-oai_dc/SET_1/json/eba982bd-9577-5c99-b453-a12c63688218.json
deleted file mode 100644
index b65bb60a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/eba982bd-9577-5c99-b453-a12c63688218.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "ILK, Tilburg University"
-    ],
-    "Contributor": [
-        "Bosch, Antal van den"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1293",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1293"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1293",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "ILK, Tilburg University"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Bosch, Antal van den",
-        "Sloot, Ko van der",
-        "Buchholz, Sabine",
-        "Daelemans, Walter",
-        "Canisius, Sander",
-        "Zavrel, Jakub"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1293;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Tadpole;Sloot, Ko van der;Daelemans, Walter;Bosch, Antal van den;Zavrel, Jakub;Canisius, Sander;Buchholz, Sabine;Bosch, Antal van den;dependency parser;An integrated tokenizer, tagger-lemmatizer, morphological analyzer, and dependency parser for Dutch;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1293;nld;downloadable_files_count: 0;Netherlands (the);ILK, Tilburg University;http://ilk.uvt.nl/tadpole",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "eba982bd-9577-5c99-b453-a12c63688218",
-    "notes": [
-        "An integrated tokenizer, tagger-lemmatizer, morphological analyzer, and dependency parser for Dutch"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1293"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "dependency parser"
-        }
-    ],
-    "title": [
-        "Tadpole"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ebae78c0-1f9b-5c79-820e-b337885ea3e8.json b/oaitestdata/clarin-oai_dc/SET_1/json/ebae78c0-1f9b-5c79-820e-b337885ea3e8.json
deleted file mode 100644
index 936dcc3f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ebae78c0-1f9b-5c79-820e-b337885ea3e8.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia J.K.Mci XX. Bazylian\u00f3w"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-636",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-636"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D31-B",
-    "PublicationTimestamp": "1793-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1793"
-    ],
-    "Publisher": [
-        "Drukarnia J.K.Mci XX. Bazylian\u00f3w"
-    ],
-    "RelatedIdentifier": [
-        "http://pbc.biaman.pl/Content/636"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "author": [
-        "Lachowski, Sebastian (1731-1794)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-636;2019-03-01T17:30:37Z;Kazania niedzielne. T.2.;Lachowski, Sebastian (1731-1794);Kazania polskie 18 w.;ilo\u015b\u0107 skan\u00f3w: 327; sygn. S-761;Drukarnia J.K.Mci XX. Bazylian\u00f3w;1793;starodruk;application/xml;clarind-uds:poldilemma-636;hdl:11858/00-246C-0000-0023-8D31-B;pol;lat;http://pbc.biaman.pl/Content/636;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ebae78c0-1f9b-5c79-820e-b337885ea3e8",
-    "notes": [
-        "ilo\u015b\u0107 skan\u00f3w: 327; sygn. S-761"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-636"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Kazania polskie w."
-        }
-    ],
-    "title": [
-        "Kazania niedzielne. T.2."
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ebcd5760-4562-58bb-9f46-bcc189195257.json b/oaitestdata/clarin-oai_dc/SET_1/json/ebcd5760-4562-58bb-9f46-bcc189195257.json
deleted file mode 100644
index d501f866..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ebcd5760-4562-58bb-9f46-bcc189195257.json
+++ /dev/null
@@ -1,91 +0,0 @@
-{
-    "Contributor": [
-        "Jukka Tyrkk\u00f6",
-        "Hendrik De Smet",
-        "Susanne Flach",
-        "Hans-J\u00fcrgen Diller"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:clmet-31",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:clmet-31"
-    ],
-    "PID": "http://hdl.handle.net/21.11119/0000-0002-43F3-0",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "RelatedIdentifier": [
-        "Diller, H., De Smet, H., Tyrkk\u00f6, J. (2011). A European database of descriptors of English electronic texts. The European English Messenger 19, 21-35."
-    ],
-    "ResourceType": [
-        "Collection",
-        "Written Corpus",
-        "Diachronic Corpus"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "Great Britain",
-        "Ireland",
-        "1710/1920"
-    ],
-    "TemporalCoverage": [
-        "Great Britain",
-        "Ireland",
-        "1710/1920"
-    ],
-    "author": [
-        "KU Leuven"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:clmet-31;2018-10-25T13:28:05Z;The Corpus of Late Modern English Texts, version 3.1;KU Leuven;Late Modern English;corpus linguistics;language change;written language;genre classification;CLMET3.1 is a principled collection of public domain texts drawn from various online archiving projects. In total, the corpus contains some 34 million words of running text. It incorporates CLMET, CLMETEV, and CLMET3.0, and has been compiled following roughly the same principles, that is:\n\n    The corpus covers the period 1710-1920, divided into three 70-year sub-periods.\n    The texts making up the corpus have all been written by British and Irish authors who are native speakers of English.\n    The corpus never contains more than three texts by the same author.\n    The texts within each sub-period have been written by authors born within a correspondingly restricted sub-period. \n\nHowever, compared to the earlier versions, it comes with a number of important improvements (in addition to being substantially bigger):\n\n    CLMET3.1 comes with an explicit genre classification.\n    It is approximately genre-balanced.\n    It is part-of-speech tagged.\n    The corpus files have standardized text headers containing descriptive meta-data.\n    For each text, explicit information is provided on text provenance.\n    The corpus architecture allows subsequent expansions. \n    The corpus is CWB compatible.;Hendrik De Smet;Susanne Flach;Hans-J\u00fcrgen Diller;Jukka Tyrkk\u00f6;2018;Collection;Written Corpus;Diachronic Corpus;application/zip;clarind-uds:clmet-31;hdl:21.11119/0000-0002-43F3-0;See corpus files;eng;Diller, H., De Smet, H., Tyrkk\u00f6, J. (2011). A European database of descriptors of English electronic texts. The European English Messenger 19, 21-35.;Great Britain;Ireland;1710/1920;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ebcd5760-4562-58bb-9f46-bcc189195257",
-    "notes": [
-        "CLMET3.1 is a principled collection of public domain texts drawn from various online archiving projects. In total, the corpus contains some 34 million words of running text. It incorporates CLMET, CLMETEV, and CLMET3.0, and has been compiled following roughly the same principles, that is:\n\n    The corpus covers the period 1710-1920, divided into three 70-year sub-periods.\n    The texts making up the corpus have all been written by British and Irish authors who are native speakers of English.\n    The corpus never contains more than three texts by the same author.\n    The texts within each sub-period have been written by authors born within a correspondingly restricted sub-period. \n\nHowever, compared to the earlier versions, it comes with a number of important improvements (in addition to being substantially bigger):\n\n    CLMET3.1 comes with an explicit genre classification.\n    It is approximately genre-balanced.\n    It is part-of-speech tagged.\n    The corpus files have standardized text headers containing descriptive meta-data.\n    For each text, explicit information is provided on text provenance.\n    The corpus architecture allows subsequent expansions. \n    The corpus is CWB compatible."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:clmet-31"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Late Modern English"
-        },
-        {
-            "name": "corpus linguistics"
-        },
-        {
-            "name": "language change"
-        },
-        {
-            "name": "written language"
-        },
-        {
-            "name": "genre classification"
-        }
-    ],
-    "title": [
-        "The Corpus of Late Modern English Texts, version 3.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ebe9a007-7b95-53e9-9ee0-ba119525d86b.json b/oaitestdata/clarin-oai_dc/SET_1/json/ebe9a007-7b95-53e9-9ee0-ba119525d86b.json
deleted file mode 100644
index 753399eb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ebe9a007-7b95-53e9-9ee0-ba119525d86b.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5198",
-    "MetadataAccess": [
-        "oai:ota:oucs:5198"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Boreman, Thomas, fl. 1730-1743."
-    ],
-    "fulltext": "oai:ota:oucs:5198;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5198.xml;A description of a great variety of animals and vegetables: viz. beasts, birds, fishes, insects, plants, fruits, and flowers. Extracted from the most considerable writers of natural history; ... Being a supplement to A description of three hundred animals. Illustrated with above ninety copper plates, ...;Boreman, Thomas, fl. 1730-1743.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ebe9a007-7b95-53e9-9ee0-ba119525d86b",
-    "oai_identifier": [
-        "oai:ota:oucs:5198"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A description of a great variety of animals and vegetables: viz. beasts, birds, fishes, insects, plants, fruits, and flowers. Extracted from the most considerable writers of natural history; ... Being a supplement to A description of three hundred animals. Illustrated with above ninety copper plates, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5198.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ebea92ce-e66d-5fe2-98e3-7f089a969f36.json b/oaitestdata/clarin-oai_dc/SET_1/json/ebea92ce-e66d-5fe2-98e3-7f089a969f36.json
deleted file mode 100644
index abd2310d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ebea92ce-e66d-5fe2-98e3-7f089a969f36.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 3",
-        "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
-        "text/plain",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/442",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/442"
-    ],
-    "PID": "http://hdl.handle.net/11321/442",
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "Czachor, Gabriela",
-        "Piasecki, Maciej",
-        "Janz, Arkadiusz",
-        "Kaszewski, Dominik"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/442;2017-11-29T20:18:20Z;hdl_11321_3;hdl_11321_4;Word Embeddings for Polish;Piasecki, Maciej;Janz, Arkadiusz;Kaszewski, Dominik;Czachor, Gabriela;Word2Vec;FastText;Distributional language models for Polish trained on different corpora (KGR10, NKJP, Wikipedia).;2017;languageDescription;http://hdl.handle.net/11321/442;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;text/plain;application/vnd.openxmlformats-officedocument.spreadsheetml.sheet;application/octet-stream;downloadable_files_count: 3;Wroc\u0142aw University of Science and Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ebea92ce-e66d-5fe2-98e3-7f089a969f36",
-    "notes": [
-        "Distributional language models for Polish trained on different corpora (KGR10, NKJP, Wikipedia)."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/442"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "WordVec"
-        },
-        {
-            "name": "FastText"
-        }
-    ],
-    "title": [
-        "Word Embeddings for Polish"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ebfbf909-d444-54b8-a0ba-fa62e2df71aa.json b/oaitestdata/clarin-oai_dc/SET_1/json/ebfbf909-d444-54b8-a0ba-fa62e2df71aa.json
deleted file mode 100644
index 480ecb90..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ebfbf909-d444-54b8-a0ba-fa62e2df71aa.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5231",
-    "MetadataAccess": [
-        "oai:ota:oucs:5231"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dudley, H. Bate, Sir (Henry Bate), 1745-1824."
-    ],
-    "fulltext": "oai:ota:oucs:5231;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5231.xml;Passages selected by distinguished personages: on the great literary trial of Vortigern and Rowena; a comi-tragedy. ... [pt.3];Dudley, H. Bate, Sir (Henry Bate), 1745-1824.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ebfbf909-d444-54b8-a0ba-fa62e2df71aa",
-    "oai_identifier": [
-        "oai:ota:oucs:5231"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Passages selected by distinguished personages: on the great literary trial of Vortigern and Rowena; a comi-tragedy. ... [pt.3]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5231.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ec2b001e-280c-54d0-8c59-a91c36c00e11.json b/oaitestdata/clarin-oai_dc/SET_1/json/ec2b001e-280c-54d0-8c59-a91c36c00e11.json
deleted file mode 100644
index ce886aa7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ec2b001e-280c-54d0-8c59-a91c36c00e11.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Masaryk University, Brno"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "application/octet-stream",
-        "application/zip"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2647",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2647"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2647",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Masaryk University, Brno"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Loutock\u00fd, Pavel",
-        "\u0160ejnov\u00e1, Tamara",
-        "Kotkov\u00e1, Ad\u00e9la",
-        "Zibner, Jan",
-        "\u0160avelka, Jarom\u00edr",
-        "Pullmannov\u00e1, Helena",
-        "\u0160imkov\u00e1, Nikola",
-        "Hara\u0161ta, Jakub",
-        "Proch\u00e1zkov\u00e1, Daniela",
-        "Vosinek, Michal",
-        "Zavadilov\u00e1, Lucie",
-        "Kasl, Franti\u0161ek",
-        "M\u00ed\u0161ek, Jakub",
-        "Semeni\u0161\u00edn, Petr"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2647;2018-07-02T22:05:54Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Annotated Corpus of Czech Case Law for Reference Recognition Tasks;Hara\u0161ta, Jakub;\u0160avelka, Jarom\u00edr;Kasl, Franti\u0161ek;Kotkov\u00e1, Ad\u00e9la;Loutock\u00fd, Pavel;M\u00ed\u0161ek, Jakub;Proch\u00e1zkov\u00e1, Daniela;Pullmannov\u00e1, Helena;Semeni\u0161\u00edn, Petr;\u0160ejnov\u00e1, Tamara;\u0160imkov\u00e1, Nikola;Vosinek, Michal;Zavadilov\u00e1, Lucie;Zibner, Jan;reference recognition;legal texts;Annotated corpus of 350 decision of Czech top-tier courts (Supreme Court, Supreme Administrative Court, Constitutional Court).\r\n\r\nEvery decision is annotated by two trained annotators and then manually adjudicated by one trained curator to solve possible disagreements between annotators. Adjudication was conducted non-destructively, therefore dataset contains all original annotations.\r\n\r\nCorpus was developed as training and testing material for reference recognition tasks. Dataset contains references to other court decisions and literature. All references consist of basic units (identifier of court decision, identification of court issuing referred decision, author of book or article, title of book or article, point of interest in referred document etc.), values (polarity, depth of discussion etc.).;2018;corpus;http://hdl.handle.net/11234/1-2647;ces;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;text/plain; charset=utf-8;application/zip;application/octet-stream;downloadable_files_count: 2;Masaryk University, Brno;https://www.muni.cz/vyzkum/projekty/36467",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ec2b001e-280c-54d0-8c59-a91c36c00e11",
-    "notes": [
-        "Annotated corpus of 350 decision of Czech top-tier courts (Supreme Court, Supreme Administrative Court, Constitutional Court).\r\n\r\nEvery decision is annotated by two trained annotators and then manually adjudicated by one trained curator to solve possible disagreements between annotators. Adjudication was conducted non-destructively, therefore dataset contains all original annotations.\r\n\r\nCorpus was developed as training and testing material for reference recognition tasks. Dataset contains references to other court decisions and literature. All references consist of basic units (identifier of court decision, identification of court issuing referred decision, author of book or article, title of book or article, point of interest in referred document etc.), values (polarity, depth of discussion etc.)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2647"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "reference recognition"
-        },
-        {
-            "name": "legal texts"
-        }
-    ],
-    "title": [
-        "Annotated Corpus of Czech Case Law for Reference Recognition Tasks"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ec326d1f-1bba-59ea-86a7-cac041c9568d.json b/oaitestdata/clarin-oai_dc/SET_1/json/ec326d1f-1bba-59ea-86a7-cac041c9568d.json
deleted file mode 100644
index f8df14af..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ec326d1f-1bba-59ea-86a7-cac041c9568d.json
+++ /dev/null
@@ -1,113 +0,0 @@
-{
-    "Contact": [
-        "Universit\u00e4t des Saarlandes"
-    ],
-    "Contributor": [
-        "Prof. Elke Teich"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:dascitex",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:dascitex"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0005-BD0F-D",
-    "PublicationTimestamp": "2006-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2006"
-    ],
-    "Publisher": [
-        "Universit\u00e4t des Saarlandes"
-    ],
-    "RelatedIdentifier": [
-        "Publications: http://www.linglit.tu-darmstadt.de/index.php?id=lingpro_pubs",
-        "RegiCo, the follow up: https://www.uni-saarland.de/lehrstuhl/teich/projekte/abgeschlossene-projekte/register-im-kontakt.html",
-        "DaSciTex Tools and Deliverables: http://www.linglit.tu-darmstadt.de/index.php?id=lingpro_deliverable"
-    ],
-    "ResourceType": [
-        "Collection",
-        "Corpus"
-    ],
-    "Rights": [
-        "Copyrighted"
-    ],
-    "SpatialCoverage": [
-        "Germany",
-        "2003/2007"
-    ],
-    "TemporalCoverage": " period : ( None - 2003-07-01T11:59:59Z ) ",
-    "author": [
-        "Institut f\u00fcr Sprach- und Literaturwissenschaft, TU Darmstadt",
-        "LingPro DFG-Projekt"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:dascitex;2018-02-02T14:45:08Z;DaSciTex;Institut f\u00fcr Sprach- und Literaturwissenschaft, TU Darmstadt;LingPro DFG-Projekt;corpus linguistics;linguistics;register;scientific discourse;computer science;computational linguistics;biology;bioinformatics;electrical engineering;micro-electronics;mechanical engineering;computer-aided design;functional variation;Synchronic corpus of scientific texts from 9 different disciplines.;The Darmstadt Corpus of Scientific Texts (DaSciTex) contains full English scientific journal articles compiled from 23 sources covering nine scientific domains. The corpus has a three-way partition: a center discipline (computer science) four 'pure' contact disciplines (linguistics, biology, mechanical engineering, electrical engineering) and four corresponding 'mixed' disciplines (computational linguistics, bio-informatics, computer-aided design, micro-electronics). The corpus comes in two versions  a small manually checked corpus (approx. one million words) a large corpus (17 million words.);Das Darmstadt Corpus of Scientific Texts (DaSciTex) besteht aus Vollversionen Englischer wissenschaftlicher Zeitschriftenartikel aus 23 Quellen und umfa\u00dft 9 verschiedene wissenschaftliche Dom\u00e4nen. Der Aufbau des Korpus ist dreigliedrig: eine zentrale Disziplin (Informatik),vier 'reine' Kontaktdisziplinen (Linguistik, Biologie, Maschinen Bau, Elektrotechnik), vier dazugeh\u00f6rige Mischdisziplinen (Computerlinguistik, Bio-Informatik, CAD, Mikroelektronik). Es gibt zwei Versionen des Korpus: ein kleines manuell korrigiertes Korpus (ca. eine Million W\u00f6rter), ein gro\u00dfes Korpus (17 Millionen W\u00f6rter).;Universit\u00e4t des Saarlandes;Prof. Elke Teich;2006-10/2009-09;Collection;Corpus;text/xml;clarind-uds:dascitex;hdl:11858/00-246C-0000-0005-BD0F-D;eng;Publications: http://www.linglit.tu-darmstadt.de/index.php?id=lingpro_pubs;RegiCo, the follow up: https://www.uni-saarland.de/lehrstuhl/teich/projekte/abgeschlossene-projekte/register-im-kontakt.html;DaSciTex Tools and Deliverables: http://www.linglit.tu-darmstadt.de/index.php?id=lingpro_deliverable;Germany;2003/2007;Copyrighted",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ec326d1f-1bba-59ea-86a7-cac041c9568d",
-    "notes": [
-        "Synchronic corpus of scientific texts from 9 different disciplines.",
-        "The Darmstadt Corpus of Scientific Texts (DaSciTex) contains full English scientific journal articles compiled from 23 sources covering nine scientific domains. The corpus has a three-way partition: a center discipline (computer science) four 'pure' contact disciplines (linguistics, biology, mechanical engineering, electrical engineering) and four corresponding 'mixed' disciplines (computational linguistics, bio-informatics, computer-aided design, micro-electronics). The corpus comes in two versions  a small manually checked corpus (approx. one million words) a large corpus (17 million words.)",
-        "Das Darmstadt Corpus of Scientific Texts (DaSciTex) besteht aus Vollversionen Englischer wissenschaftlicher Zeitschriftenartikel aus 23 Quellen und umfa\u00dft 9 verschiedene wissenschaftliche Dom\u00e4nen. Der Aufbau des Korpus ist dreigliedrig: eine zentrale Disziplin (Informatik),vier 'reine' Kontaktdisziplinen (Linguistik, Biologie, Maschinen Bau, Elektrotechnik), vier dazugeh\u00f6rige Mischdisziplinen (Computerlinguistik, Bio-Informatik, CAD, Mikroelektronik). Es gibt zwei Versionen des Korpus: ein kleines manuell korrigiertes Korpus (ca. eine Million W\u00f6rter), ein gro\u00dfes Korpus (17 Millionen W\u00f6rter)."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:dascitex"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus linguistics"
-        },
-        {
-            "name": "linguistics"
-        },
-        {
-            "name": "register"
-        },
-        {
-            "name": "scientific discourse"
-        },
-        {
-            "name": "computer science"
-        },
-        {
-            "name": "computational linguistics"
-        },
-        {
-            "name": "biology"
-        },
-        {
-            "name": "bioinformatics"
-        },
-        {
-            "name": "electrical engineering"
-        },
-        {
-            "name": "micro-electronics"
-        },
-        {
-            "name": "mechanical engineering"
-        },
-        {
-            "name": "computer-aided design"
-        }
-    ],
-    "title": [
-        "DaSciTex"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ec595bd0-1112-53a9-900f-a8ca75395b46.json b/oaitestdata/clarin-oai_dc/SET_1/json/ec595bd0-1112-53a9-900f-a8ca75395b46.json
deleted file mode 100644
index 6887df79..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ec595bd0-1112-53a9-900f-a8ca75395b46.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "text/xml",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish",
-        "Southern Sami"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/99",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/99"
-    ],
-    "PID": "http://hdl.handle.net/11509/99",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "The Divvun group at UiT The Arctic University of Norway",
-        "Giellatekno - Saami Language Technology, UiT The Arctic University of Norway"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/99;2016-09-06T13:00:12Z;hdl_11509_1;hdl_11509_2;Swedish-South Saami dictionary;Giellatekno - Saami Language Technology, UiT The Arctic University of Norway;The Divvun group at UiT The Arctic University of Norway;Bilingual Lexicon;Swedish;South Saami;Machine-readable Dictionary;The Swedish-South Saami dictionary is the work done by Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language communities, based on the book \"Verbh - en sydsamisk verbhandbok\" by M\u00e4rit Fr\u00e4nd\u00e9n, Bj\u00f6rn Lundqvist, and Karin Wilson. The dictionary contains 3351 entries in Giellatekno's dictionary xml format. In spite of the extensive quality control, it may contain entries with objectionable translations. If you find any errors or want to add more words, download the file, edit it, and send it back to giellatekno@uit.no and feedback@divvun.no.\r\nPlease note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata).;2015;lexicalConceptualResource;http://hdl.handle.net/11509/99;swe;sma;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;text/xml;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Giellatekno - Saami Language Technology;http://giellatekno.uit.no/index.eng.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ec595bd0-1112-53a9-900f-a8ca75395b46",
-    "notes": [
-        "The Swedish-South Saami dictionary is the work done by Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language communities, based on the book \"Verbh - en sydsamisk verbhandbok\" by M\u00e4rit Fr\u00e4nd\u00e9n, Bj\u00f6rn Lundqvist, and Karin Wilson. The dictionary contains 3351 entries in Giellatekno's dictionary xml format. In spite of the extensive quality control, it may contain entries with objectionable translations. If you find any errors or want to add more words, download the file, edit it, and send it back to giellatekno@uit.no and feedback@divvun.no.\r\nPlease note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata)."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/99"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Bilingual Lexicon"
-        },
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "South Saami"
-        },
-        {
-            "name": "Machine-readable Dictionary"
-        }
-    ],
-    "title": [
-        "Swedish-South Saami dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ec641197-59d6-599c-832c-3346c8eab42a.json b/oaitestdata/clarin-oai_dc/SET_1/json/ec641197-59d6-599c-832c-3346c8eab42a.json
deleted file mode 100644
index a0372fb3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ec641197-59d6-599c-832c-3346c8eab42a.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Instituto de Lingu\u00edstica Te\u00f3rica e Computacional"
-    ],
-    "Contributor": [
-        "Santos, Fab\u00edola"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Portuguese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-613",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-613"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-613",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Instituto de Lingu\u00edstica Te\u00f3rica e Computacional"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Portugal"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-613;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;CORP-ORAL Spontaneous Speech Corpus;Santos, Fab\u00edola;The aim of the CORP-ORAL project is to build a corpus of spontaneous European Portuguese speech available for the training of speech synthesis and recognition systems as well as phonetic, phonological, lexical, morphological and syntactic studies. The corpus contains the recording of 60 hours of conversations between two European Portuguese speakers per conversation (at a time). The entire corpus will be completed with orthographic transcription and the prosodic marking of speech breaks/boundaries as well as phonetic transcription of a selection of chunks. CORP-ORAL is built from scratch with the explicit goal of becoming entirely available on the internet to the scientific community and the public in general.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-613;por;downloadable_files_count: 0;Portugal;Instituto de Lingu\u00edstica Te\u00f3rica e Computacional;http://corpus1.mpi.nl/ds/imdi_browser/?openpath=MPI556279%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ec641197-59d6-599c-832c-3346c8eab42a",
-    "notes": [
-        "The aim of the CORP-ORAL project is to build a corpus of spontaneous European Portuguese speech available for the training of speech synthesis and recognition systems as well as phonetic, phonological, lexical, morphological and syntactic studies. The corpus contains the recording of 60 hours of conversations between two European Portuguese speakers per conversation (at a time). The entire corpus will be completed with orthographic transcription and the prosodic marking of speech breaks/boundaries as well as phonetic transcription of a selection of chunks. CORP-ORAL is built from scratch with the explicit goal of becoming entirely available on the internet to the scientific community and the public in general."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-613"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "CORP-ORAL Spontaneous Speech Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ec66be0b-e9b8-57cc-8388-8781265d1cf6.json b/oaitestdata/clarin-oai_dc/SET_1/json/ec66be0b-e9b8-57cc-8388-8781265d1cf6.json
deleted file mode 100644
index b50fedab..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ec66be0b-e9b8-57cc-8388-8781265d1cf6.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "University of Silesia"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 20",
-        "text/plain; charset=utf-8",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/349",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/349"
-    ],
-    "PID": "http://hdl.handle.net/11321/349",
-    "PublicationTimestamp": "2017-04-25T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "University of Silesia"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "W\u00f3jciuk, Anna"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/349;2017-04-25T14:09:27Z;hdl_11321_3;hdl_11321_4;Linguistic;W\u00f3jciuk, Anna;language;Corpus;2017-04-25;corpus;http://hdl.handle.net/11321/349;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;application/msword;downloadable_files_count: 20;University of Silesia;http://www.us.edu.pl",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ec66be0b-e9b8-57cc-8388-8781265d1cf6",
-    "notes": [
-        "Corpus"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/349"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "language"
-        }
-    ],
-    "title": [
-        "Linguistic"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ec744f39-a11b-5e2f-907a-3e7271d13acf.json b/oaitestdata/clarin-oai_dc/SET_1/json/ec744f39-a11b-5e2f-907a-3e7271d13acf.json
deleted file mode 100644
index be08fdff..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ec744f39-a11b-5e2f-907a-3e7271d13acf.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Parlament Europejski"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 94",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/515",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/515"
-    ],
-    "PID": "http://hdl.handle.net/11321/515",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Parlament Europejski"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Szczepa\u0144ski, Maciej",
-        "Wnuk, Magda"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/515;2018-07-13T13:51:08Z;hdl_11321_3;hdl_11321_4;Wnuk;Wnuk, Magda;Szczepa\u0144ski, Maciej;opis;opis;2018;corpus;http://hdl.handle.net/11321/515;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;downloadable_files_count: 94;Parlament Europejski",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ec744f39-a11b-5e2f-907a-3e7271d13acf",
-    "notes": [
-        "opis"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/515"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "opis"
-        }
-    ],
-    "title": [
-        "Wnuk"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ec86ffc0-6573-5240-b7b5-d3dbf568f161.json b/oaitestdata/clarin-oai_dc/SET_1/json/ec86ffc0-6573-5240-b7b5-d3dbf568f161.json
deleted file mode 100644
index 13e1eabd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ec86ffc0-6573-5240-b7b5-d3dbf568f161.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "text/xml",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Northern Sami",
-        "Finnish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/97",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/97"
-    ],
-    "PID": "http://hdl.handle.net/11509/97",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "CC",
-        "http://creativecommons.org/licenses/by/3.0/"
-    ],
-    "author": [
-        "Giellatekno - Saami Language Technology, UiT The Arctic University of Norway"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/97;2016-09-06T12:39:26Z;hdl_11509_1;hdl_11509_2;North Saami-Finnish dictionary;Giellatekno - Saami Language Technology, UiT The Arctic University of Norway;Bilingual Lexicon;Swedish;South Saami;Machine-readable Dictionary;The North Saami-Finnish dictionary is the work done by Giellatekno at UiT The Arctic University of Norway, Kotus in Helsinki, and members of the language communities. In particular, the following colleagues have contributed to the creation of the ressource: Trond Trosterud and Ciprian Gerstenberger. It contains 11297 entries in Giellatekno's dictionary xml format. In spite of the extensive quality control, it may contain entries with objectionable translations. If you find any errors or want to add more words, download the file, edit it, and send it back to giellatekno@uit.no.\r\nPlease note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata).;2015;lexicalConceptualResource;http://hdl.handle.net/11509/97;sme;fin;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);CC;http://creativecommons.org/licenses/by/3.0/;text/xml;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Giellatekno - Saami Language Technology;http://giellatekno.uit.no/index.eng.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ec86ffc0-6573-5240-b7b5-d3dbf568f161",
-    "notes": [
-        "The North Saami-Finnish dictionary is the work done by Giellatekno at UiT The Arctic University of Norway, Kotus in Helsinki, and members of the language communities. In particular, the following colleagues have contributed to the creation of the ressource: Trond Trosterud and Ciprian Gerstenberger. It contains 11297 entries in Giellatekno's dictionary xml format. In spite of the extensive quality control, it may contain entries with objectionable translations. If you find any errors or want to add more words, download the file, edit it, and send it back to giellatekno@uit.no.\r\nPlease note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata)."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/97"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Bilingual Lexicon"
-        },
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "South Saami"
-        },
-        {
-            "name": "Machine-readable Dictionary"
-        }
-    ],
-    "title": [
-        "North Saami-Finnish dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ecac481e-1362-5f29-86c6-35b3852ae10e.json b/oaitestdata/clarin-oai_dc/SET_1/json/ecac481e-1362-5f29-86c6-35b3852ae10e.json
deleted file mode 100644
index 631bbfa1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ecac481e-1362-5f29-86c6-35b3852ae10e.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3286",
-    "MetadataAccess": [
-        "oai:ota:oucs:3286"
-    ],
-    "PublicationTimestamp": "1888-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1888"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Kipling, Rudyard, 1865-1936"
-    ],
-    "fulltext": "oai:ota:oucs:3286;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3286.xml;Letters of Marque;Kipling, Rudyard, 1865-1936;not after: 1888;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ecac481e-1362-5f29-86c6-35b3852ae10e",
-    "oai_identifier": [
-        "oai:ota:oucs:3286"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Letters of Marque"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3286.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ecb72c0f-c7b7-557c-999e-7b6bb092f7f6.json b/oaitestdata/clarin-oai_dc/SET_1/json/ecb72c0f-c7b7-557c-999e-7b6bb092f7f6.json
deleted file mode 100644
index e5bee2db..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ecb72c0f-c7b7-557c-999e-7b6bb092f7f6.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4572",
-    "MetadataAccess": [
-        "oai:ota:oucs:4572"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hutchinson, William, 1732-1814."
-    ],
-    "fulltext": "oai:ota:oucs:4572;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4572.xml;The Princess of Zanfara: a dramatic poem.;Hutchinson, William, 1732-1814.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ecb72c0f-c7b7-557c-999e-7b6bb092f7f6",
-    "oai_identifier": [
-        "oai:ota:oucs:4572"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The Princess of Zanfara: a dramatic poem."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4572.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ecbc4f62-d941-5765-a038-ff914e3c6067.json b/oaitestdata/clarin-oai_dc/SET_1/json/ecbc4f62-d941-5765-a038-ff914e3c6067.json
deleted file mode 100644
index 185ab5dc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ecbc4f62-d941-5765-a038-ff914e3c6067.json
+++ /dev/null
@@ -1,89 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/xml",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/274",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/274"
-    ],
-    "PID": "http://hdl.handle.net/11321/274",
-    "PublicationTimestamp": "2016-04-26T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "plWordNet",
-        "http://clarin-pl.eu/en/licenses/plwordnet-2/",
-        "PUB"
-    ],
-    "author": [
-        "Szpakowicz, Stan",
-        "Maziarz, Marek",
-        "Kali\u0144ski, Micha\u0142",
-        "Radziszewski, Adam",
-        "Wendelberger, Micha\u0142",
-        "Piasecki, Maciej",
-        "Dziob, Agnieszka"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/274;2016-06-02T11:08:21Z;hdl_11321_3;hdl_11321_4;MWELexicon;Dziob, Agnieszka;Kali\u0144ski, Micha\u0142;Maziarz, Marek;Piasecki, Maciej;Radziszewski, Adam;Szpakowicz, Stan;Wendelberger, Micha\u0142;multi-word lexical units;syntax;inflection;collocations;plWordNet;Lexicon of 55k multi-word lexical units linked to plWordNet, together with description of their syntactic bahaviour obtained in constraint language (WCCL).;2016-04-26;lexicalConceptualResource;http://hdl.handle.net/11321/274;pol;plWordNet;http://clarin-pl.eu/en/licenses/plwordnet-2/;PUB;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;text/xml;downloadable_files_count: 1;Wroc\u0142aw University of Technology;http://clarin-pl.eu/pl/o-projekcie/clarin-pl/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ecbc4f62-d941-5765-a038-ff914e3c6067",
-    "notes": [
-        "Lexicon of 55k multi-word lexical units linked to plWordNet, together with description of their syntactic bahaviour obtained in constraint language (WCCL)."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/274"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "multi-word lexical units"
-        },
-        {
-            "name": "syntax"
-        },
-        {
-            "name": "inflection"
-        },
-        {
-            "name": "collocations"
-        },
-        {
-            "name": "plWordNet"
-        }
-    ],
-    "title": [
-        "MWELexicon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ecbeaa90-c552-55df-a2dd-9f5096d280dc.json b/oaitestdata/clarin-oai_dc/SET_1/json/ecbeaa90-c552-55df-a2dd-9f5096d280dc.json
deleted file mode 100644
index 4ab89a28..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ecbeaa90-c552-55df-a2dd-9f5096d280dc.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "The Research Institute for the Languages of Finland"
-    ],
-    "Contributor": [
-        "Lounela, Mikko"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Finnish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-807",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-807"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-807",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "The Research Institute for the Languages of Finland"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Finland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-807;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;New Year Speechs of the President of the Republic of Finland;Lounela, Mikko;text corpus, period 1935&#8211;2007;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-807;fin;downloadable_files_count: 0;Finland;The Research Institute for the Languages of Finland;http://kaino.kotus.fi/korpus/teko/meta/presidentti/presidentti_coll_rdf.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ecbeaa90-c552-55df-a2dd-9f5096d280dc",
-    "notes": [
-        "text corpus, period 1935&#8211;2007"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-807"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "New Year Speechs of the President of the Republic of Finland"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ecdb93d8-e0b7-57b2-9d8c-e990151fcbdf.json b/oaitestdata/clarin-oai_dc/SET_1/json/ecdb93d8-e0b7-57b2-9d8c-e990151fcbdf.json
deleted file mode 100644
index fedfe5c5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ecdb93d8-e0b7-57b2-9d8c-e990151fcbdf.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Mniszek"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 4",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/85",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/85"
-    ],
-    "PID": "http://hdl.handle.net/11321/85",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Mniszek"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Mniszek, Mniszek"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/85;2015-05-19T13:28:54Z;hdl_11321_3;hdl_11321_4;MWE Mniszek;Mniszek, Mniszek;Mniszek;2015-04-08;corpus;http://hdl.handle.net/11321/85;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;application/zip;text/plain; charset=utf-8;downloadable_files_count: 4;Mniszek",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ecdb93d8-e0b7-57b2-9d8c-e990151fcbdf",
-    "notes": [
-        "Mniszek"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/85"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Mniszek"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ecec18c1-d444-5bd4-b2b9-df3b08135a5f.json b/oaitestdata/clarin-oai_dc/SET_1/json/ecec18c1-d444-5bd4-b2b9-df3b08135a5f.json
deleted file mode 100644
index 01614d32..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ecec18c1-d444-5bd4-b2b9-df3b08135a5f.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Pedagogical University of Krak\u00f3w"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "downloadable_files_count: 10",
-        "application/vnd.oasis.opendocument.text",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/410",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/410"
-    ],
-    "PID": "http://hdl.handle.net/11321/410",
-    "PublicationTimestamp": "2017-06-03T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Pedagogical University of Krak\u00f3w"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Gajda, Joanna"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/410;2017-06-29T07:52:35Z;hdl_11321_3;hdl_11321_4;Korpus tekstowy;Gajda, Joanna;Gajda, Joanna;warsztaty;Korpus testowy na warsztaty z korzystania z dspace;2017-06-03;corpus;http://hdl.handle.net/11321/410;pol;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;text/plain;application/msword;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.oasis.opendocument.text;text/plain;application/msword;downloadable_files_count: 10;Pedagogical University of Krak\u00f3w",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ecec18c1-d444-5bd4-b2b9-df3b08135a5f",
-    "notes": [
-        "Korpus testowy na warsztaty z korzystania z dspace"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/410"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "warsztaty"
-        }
-    ],
-    "title": [
-        "Korpus tekstowy"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ecef1cee-2440-5281-8962-25837bb53313.json b/oaitestdata/clarin-oai_dc/SET_1/json/ecef1cee-2440-5281-8962-25837bb53313.json
deleted file mode 100644
index fa928c52..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ecef1cee-2440-5281-8962-25837bb53313.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "IJP UW"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 86",
-        "text/plain; charset=utf-8",
-        "text/plain"
-    ],
-    "Language": [],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/520",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/520"
-    ],
-    "PID": "http://hdl.handle.net/11321/520",
-    "PublicationTimestamp": "2018-07-13T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "IJP UW"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Kwiecie\u0144, Monika"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/520;2018-07-13T13:51:36Z;hdl_11321_3;hdl_11321_4;warsztaty clar;Kwiecie\u0144, Monika;pose\u0142;warsztaty;2018-07-13;corpus;http://hdl.handle.net/11321/520;Polska;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;downloadable_files_count: 86;IJP UW",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ecef1cee-2440-5281-8962-25837bb53313",
-    "notes": [
-        "warsztaty"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/520"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [],
-    "title": [
-        "warsztaty clar"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ed2df7d5-dfba-51ae-ab59-1874ff888d42.json b/oaitestdata/clarin-oai_dc/SET_1/json/ed2df7d5-dfba-51ae-ab59-1874ff888d42.json
deleted file mode 100644
index c9b7a38d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ed2df7d5-dfba-51ae-ab59-1874ff888d42.json
+++ /dev/null
@@ -1,49 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4306",
-    "MetadataAccess": [
-        "oai:ota:oucs:4306"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:4306;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4306.xml;The black art detected and expos'd: or, a demonstration of the hellish impiety, of being, or desiring to be a wizzard, conjurer, or witch. ... In a letter to a country gentleman;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ed2df7d5-dfba-51ae-ab59-1874ff888d42",
-    "oai_identifier": [
-        "oai:ota:oucs:4306"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The black art detected and expos'd: or, a demonstration of the hellish impiety, of being, or desiring to be a wizzard, conjurer, or witch. ... In a letter to a country gentleman"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4306.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ed31016f-de94-594e-b21e-b72f844afb6e.json b/oaitestdata/clarin-oai_dc/SET_1/json/ed31016f-de94-594e-b21e-b72f844afb6e.json
deleted file mode 100644
index de7992a7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ed31016f-de94-594e-b21e-b72f844afb6e.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences",
-        "Institute of Applied Informatics, Wroc\u0142aw University of Technology"
-    ],
-    "Contributor": [
-        "Piasecki, Maciej",
-        "Przepi\u00f3rkowski, Adam"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1284",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1284"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1284",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences",
-        "Institute of Applied Informatics, Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Poland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Godlewski, Grzegorz",
-        "Piasecki, Maciej",
-        "Broda, Bartosz",
-        "Wardy\u0144ski, Adam",
-        "Radziszewski, Adam"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1284;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TaKIPI;Piasecki, Maciej;Godlewski, Grzegorz;Radziszewski, Adam;Broda, Bartosz;Wardy\u0144ski, Adam;Piasecki, Maciej;Przepi\u00f3rkowski, Adam;morphosyntactic tagger;morphosyntactic tagger working on the IPI PAN Corpus tagset;;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1284;downloadable_files_count: 0;Poland;Institute of Computer Science, Polish Academy of Sciences;Institute of Applied Informatics, Wroc\u0142aw University of Technology;http://plwordnet.pwr.wroc.pl/takipi",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ed31016f-de94-594e-b21e-b72f844afb6e",
-    "notes": [
-        "morphosyntactic tagger working on the IPI PAN Corpus tagset;"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1284"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "morphosyntactic tagger"
-        }
-    ],
-    "title": [
-        "TaKIPI"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ed43a45e-7fc5-51c8-ac96-0b2f815db6ab.json b/oaitestdata/clarin-oai_dc/SET_1/json/ed43a45e-7fc5-51c8-ac96-0b2f815db6ab.json
deleted file mode 100644
index ea470775..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ed43a45e-7fc5-51c8-ac96-0b2f815db6ab.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "between 1 and 2 MB"
-    ],
-    "Language": [
-        "Old French (842-ca. 1400)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0587",
-    "MetadataAccess": [
-        "oai:ota:oucs:0587"
-    ],
-    "PublicationTimestamp": "1150-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1150"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Gesta"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Unknown"
-    ],
-    "fulltext": "oai:ota:oucs:0587;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0587.xml; Le roman de Tristan en prose  : troisi\u00c3\u00a8me partie (674-940) / compiled by Janet Hillier Caukins;Unknown;1150-1190;text_and_corpus_linguistics;Gesta -- France -- 13th century;fro;Oxford Text Archive, University of Oxford;between 1 and 2 MB;Text;Gesta;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ed43a45e-7fc5-51c8-ac96-0b2f815db6ab",
-    "oai_identifier": [
-        "oai:ota:oucs:0587"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Gesta -- France -- th century"
-        }
-    ],
-    "title": [
-        " Le roman de Tristan en prose  : troisi\u00c3\u00a8me partie (674-940) / compiled by Janet Hillier Caukins"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0587.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ed4a67e6-0eab-57eb-b54d-7f9c57eaa8e3.json b/oaitestdata/clarin-oai_dc/SET_1/json/ed4a67e6-0eab-57eb-b54d-7f9c57eaa8e3.json
deleted file mode 100644
index 4b573124..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ed4a67e6-0eab-57eb-b54d-7f9c57eaa8e3.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Research Institute for Artificial Intelligence, Romanian Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1271",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1271"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1271",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Research Institute for Artificial Intelligence, Romanian Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Romania"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Tufi\u015f, Dan",
-        "Ion, Radu",
-        "Barbu, Ana-Maria"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1271;2016-04-06T16:39:49Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Translation Equivalents Extractor;Tufi\u015f, Dan;Ion, Radu;Barbu, Ana-Maria;TREQ exploits the knowledge embedded in the parallel corpora and produces a set of\r\ntranslation equivalents (a translation lexicon), based on a 1:1 mapping\r\nhypothesis. The program uses almost no linguistic knowledge, relying on statistical evidence and some simplifying assumptions. \r\nThe extraction process is based on a testing approach. It generates first a list of translation equivalent candidates and then successively extracts the most likely translation equivalence pairs. It does not require a pre-existing bilingual lexicon for the considered languages. Yet, if such a lexicon exists, it can be used to eliminate spurious candidate translation equivalence pairs and thus to speed up the process and increase its accuracy. The algorithm relies on some pre-processing of the bitext: sentence aligner, tokeniser (using [[(http://www.lpl.univaix.fr/projects/multext/MtSeg|MtSeg]]), a collocation extractor (unaware of translation equivalence), POS-tagger, lemmatiser. \r\nMore detailed descriptions are available in the following paper (http://www.racai.ro/~tufis/papers/): \r\n  -- Dan  Tufi\u015f and Ana-Maria Barbu (2002). Revealing translators knowledge: statistical methods in constructing practical translation lexicons for language and speech processing. In International Journal of Speech Technology, volume 5, pp. 199-209. Kluwer Academic Publishers, November 2002. ISSN 1381-2416. \r\n  -- Dan Tufi\u015f (2002). A cheap and fast way to build useful translation lexicons. In Proceedings of the 19th International Conference on Computational Linguistics (COLING 2002), pp. 1030-1036, Taipei, Taiwan, August 2002. ISBN 1-55860-894. \r\n  -- Dan Tufi\u015f and Ana Maria Barbu (2001). Automatic Construction of Translation Lexicons. In V.V.Kluew, C.E. D'Attellis, and N.E. Mastorakis (eds.), Advances in Automation, Multimedia and Video Systems, and Modern Computer Science, pp. 156-161. WSES Press, December 2001. ISSN 1790-5117. \r\n  -- Dan  Tufi\u015f and Ana Maria Barbu (2001). Extracting Multilingual Lexicons from Parallel Corpora. In Proceedings of the ACH-ALLC conference (ACH-ALLC 2001), New York, USA, June 2001. \r\n  -- Dan  Tufi\u015f and Ana Maria Barbu (2001). Accurate Automatic Extraction of Translation Equivalents from Parallel Corpora. In Paul Rayson, Andrew Wilson, Tony McEnery, Andrew Hardie, and Shereen Khoja., editors, Proceedings of the Corpus Linguistics 2001 Conference (CL 2001), pp. 581-586, Lancaster, UK, March 2001. Lancaster University, Computing Department. ISBN 1-86220-107-2.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1271;downloadable_files_count: 0;Romania;Research Institute for Artificial Intelligence, Romanian Academy of Sciences",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ed4a67e6-0eab-57eb-b54d-7f9c57eaa8e3",
-    "notes": [
-        "TREQ exploits the knowledge embedded in the parallel corpora and produces a set of\r\ntranslation equivalents (a translation lexicon), based on a 1:1 mapping\r\nhypothesis. The program uses almost no linguistic knowledge, relying on statistical evidence and some simplifying assumptions. \r\nThe extraction process is based on a testing approach. It generates first a list of translation equivalent candidates and then successively extracts the most likely translation equivalence pairs. It does not require a pre-existing bilingual lexicon for the considered languages. Yet, if such a lexicon exists, it can be used to eliminate spurious candidate translation equivalence pairs and thus to speed up the process and increase its accuracy. The algorithm relies on some pre-processing of the bitext: sentence aligner, tokeniser (using [[(http://www.lpl.univaix.fr/projects/multext/MtSeg|MtSeg]]), a collocation extractor (unaware of translation equivalence), POS-tagger, lemmatiser. \r\nMore detailed descriptions are available in the following paper (http://www.racai.ro/~tufis/papers/): \r\n  -- Dan  Tufi\u015f and Ana-Maria Barbu (2002). Revealing translators knowledge: statistical methods in constructing practical translation lexicons for language and speech processing. In International Journal of Speech Technology, volume 5, pp. 199-209. Kluwer Academic Publishers, November 2002. ISSN 1381-2416. \r\n  -- Dan Tufi\u015f (2002). A cheap and fast way to build useful translation lexicons. In Proceedings of the 19th International Conference on Computational Linguistics (COLING 2002), pp. 1030-1036, Taipei, Taiwan, August 2002. ISBN 1-55860-894. \r\n  -- Dan Tufi\u015f and Ana Maria Barbu (2001). Automatic Construction of Translation Lexicons. In V.V.Kluew, C.E. D'Attellis, and N.E. Mastorakis (eds.), Advances in Automation, Multimedia and Video Systems, and Modern Computer Science, pp. 156-161. WSES Press, December 2001. ISSN 1790-5117. \r\n  -- Dan  Tufi\u015f and Ana Maria Barbu (2001). Extracting Multilingual Lexicons from Parallel Corpora. In Proceedings of the ACH-ALLC conference (ACH-ALLC 2001), New York, USA, June 2001. \r\n  -- Dan  Tufi\u015f and Ana Maria Barbu (2001). Accurate Automatic Extraction of Translation Equivalents from Parallel Corpora. In Paul Rayson, Andrew Wilson, Tony McEnery, Andrew Hardie, and Shereen Khoja., editors, Proceedings of the Corpus Linguistics 2001 Conference (CL 2001), pp. 581-586, Lancaster, UK, March 2001. Lancaster University, Computing Department. ISBN 1-86220-107-2."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1271"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Translation Equivalents Extractor"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ed4ffb32-5676-5f7f-9c6c-07ac88a1301f.json b/oaitestdata/clarin-oai_dc/SET_1/json/ed4ffb32-5676-5f7f-9c6c-07ac88a1301f.json
deleted file mode 100644
index a291290e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ed4ffb32-5676-5f7f-9c6c-07ac88a1301f.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Arts, Institute of Theoretical and Computational Linguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2517",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2517"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2517",
-    "PublicationTimestamp": "2017-11-15T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Arts, Institute of Theoretical and Computational Linguistics"
-    ],
-    "RelatedIdentifier": [
-        "http://ceur-ws.org/Vol-1885/181.pdf"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Jel\u00ednek, Tom\u00e1\u0161",
-        "Hn\u00e1tkov\u00e1, Milena",
-        "Skoumalov\u00e1, Hana"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2517;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;FicTree 1.0;Jel\u00ednek, Tom\u00e1\u0161;Hn\u00e1tkov\u00e1, Milena;Skoumalov\u00e1, Hana;treebank;FicTree is a dependency treebank of Czech fiction manually annotated in the format of the analytical layer of the Prague Dependency Trebank. The treebank consists of 12,760 sentences (166,432 tokens). The texts come from eight literary works published in the Czech Republic between 1991 and 2007. The syntactic annotation of the treebank was first performed by two distinct parsers (MSTParser and MaltParser) trained on the PDT training data, then manually corrected. Any differences between the two versions were resolved manually (by another annotator).\r\n\r\nThe corpus is provided in a vertical format, where sentence boundaries are marked with a blank line. Every word form is written on a separate line, followed by five tab-separated attributes: lemma, tag, ID (word index in the sentence), head and deprel (analytical function, afun in the PDT formalism). The texts are shuffled in random chunks of maximum 100 words (respecting sentence boundaries). Each chunk is provided as a separate file, with the suggested division into train, dev and test sets written as file prefix.;2017-11-15;corpus;http://hdl.handle.net/11234/1-2517;ces;http://ceur-ws.org/Vol-1885/181.pdf;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Arts, Institute of Theoretical and Computational Linguistics;https://wiki.korpus.cz/doku.php/cnk:fictree",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ed4ffb32-5676-5f7f-9c6c-07ac88a1301f",
-    "notes": [
-        "FicTree is a dependency treebank of Czech fiction manually annotated in the format of the analytical layer of the Prague Dependency Trebank. The treebank consists of 12,760 sentences (166,432 tokens). The texts come from eight literary works published in the Czech Republic between 1991 and 2007. The syntactic annotation of the treebank was first performed by two distinct parsers (MSTParser and MaltParser) trained on the PDT training data, then manually corrected. Any differences between the two versions were resolved manually (by another annotator).\r\n\r\nThe corpus is provided in a vertical format, where sentence boundaries are marked with a blank line. Every word form is written on a separate line, followed by five tab-separated attributes: lemma, tag, ID (word index in the sentence), head and deprel (analytical function, afun in the PDT formalism). The texts are shuffled in random chunks of maximum 100 words (respecting sentence boundaries). Each chunk is provided as a separate file, with the suggested division into train, dev and test sets written as file prefix."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2517"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "treebank"
-        }
-    ],
-    "title": [
-        "FicTree 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ed628800-327b-5f13-9895-0914d9cd02ff.json b/oaitestdata/clarin-oai_dc/SET_1/json/ed628800-327b-5f13-9895-0914d9cd02ff.json
deleted file mode 100644
index 0043cd45..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ed628800-327b-5f13-9895-0914d9cd02ff.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "83 KB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0924",
-    "MetadataAccess": [
-        "oai:ota:oucs:0924"
-    ],
-    "PublicationTimestamp": "1594-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1594"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Shakespeare, William"
-    ],
-    "fulltext": "oai:ota:oucs:0924;2018-02-28T17:09:17Z;http://ota.ox.ac.uk/headers/0924.xml;Comedy of errors;Shakespeare, William;1594;text_and_corpus_linguistics;English drama -- Early modern and Elizabethan, 1500-1600;eng;Oxford Text Archive, University of Oxford;83 KB;Text;Plays;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ed628800-327b-5f13-9895-0914d9cd02ff",
-    "oai_identifier": [
-        "oai:ota:oucs:0924"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- Early modern Elizabethan"
-        }
-    ],
-    "title": [
-        "Comedy of errors"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0924.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ed884529-157c-5955-a0be-39eeab2867df.json b/oaitestdata/clarin-oai_dc/SET_1/json/ed884529-157c-5955-a0be-39eeab2867df.json
deleted file mode 100644
index 96852756..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ed884529-157c-5955-a0be-39eeab2867df.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4067",
-    "MetadataAccess": [
-        "oai:ota:oucs:4067"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Carey, George Saville, 1743-1807."
-    ],
-    "fulltext": "oai:ota:oucs:4067;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4067.xml;Momus, a poem; or a critical examination into the merits of the performers, and comic pieces, at the Theatre-Royal in the Hay-Market;Carey, George Saville, 1743-1807.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ed884529-157c-5955-a0be-39eeab2867df",
-    "oai_identifier": [
-        "oai:ota:oucs:4067"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Momus, a poem; or a critical examination into the merits of the performers, and comic pieces, at the Theatre-Royal in the Hay-Market"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4067.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ed892357-0083-5933-b986-00ffae6f1c38.json b/oaitestdata/clarin-oai_dc/SET_1/json/ed892357-0083-5933-b986-00ffae6f1c38.json
deleted file mode 100644
index ec306b6a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ed892357-0083-5933-b986-00ffae6f1c38.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4524",
-    "MetadataAccess": [
-        "oai:ota:oucs:4524"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Defoe, Daniel, 1661?-1731."
-    ],
-    "fulltext": "oai:ota:oucs:4524;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4524.xml;An essay on the history and reality of apparitions: Being an account of what they are, and what they are not; whence they come, and whence they come not. ...;Defoe, Daniel, 1661?-1731.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ed892357-0083-5933-b986-00ffae6f1c38",
-    "oai_identifier": [
-        "oai:ota:oucs:4524"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An essay on the history and reality of apparitions: Being an account of what they are, and what they are not; whence they come, and whence they come not. ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4524.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/edd81bc9-bcab-537b-a214-40f3c3f419a2.json b/oaitestdata/clarin-oai_dc/SET_1/json/edd81bc9-bcab-537b-a214-40f3c3f419a2.json
deleted file mode 100644
index b0924048..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/edd81bc9-bcab-537b-a214-40f3c3f419a2.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "Masaryk University, NLP Centre"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-000E-011B-8",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-000E-011B-8"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-000E-011B-8",
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Masaryk University, NLP Centre"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Gr\u00e1c, Marek"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-000E-011B-8;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Corpus of contemporary blogs;Gr\u00e1c, Marek;corpus;blogs;annotation;annotators;sentences;machine learning;In NLP Centre, dividing text into sentences is currently done with \r\na tool which uses rule-based system. In order to make enough training \r\ndata for machine learning, annotators manually split the corpus of contemporary text \r\nCBB.blog (1 million tokens) into sentences.\r\nEach file contains one hundredth of the whole corpus and all data were \r\nprocessed in parallel by two annotators.\r\n\r\nThe corpus was created from ten contemporary blogs:\r\nhintzu.otaku.cz\r\nmodnipeklo.cz\r\nbloc.cz\r\naleneprokopova.blogspot.com\r\nblog.aktualne.cz\r\nfuchsova.blog.onaidnes.cz\r\nhavlik.blog.idnes.cz\r\nblog.aktualne.centrum.cz\r\nklusak.blogspot.cz\r\nmyego.cz/welldone;2011;corpus;http://hdl.handle.net/11858/00-097C-0000-000E-011B-8;ces;Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0);http://creativecommons.org/licenses/by-nc-nd/3.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Masaryk University, NLP Centre;http://nlp.fi.muni.cz/projekty/cocb/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "edd81bc9-bcab-537b-a214-40f3c3f419a2",
-    "notes": [
-        "In NLP Centre, dividing text into sentences is currently done with \r\na tool which uses rule-based system. In order to make enough training \r\ndata for machine learning, annotators manually split the corpus of contemporary text \r\nCBB.blog (1 million tokens) into sentences.\r\nEach file contains one hundredth of the whole corpus and all data were \r\nprocessed in parallel by two annotators.\r\n\r\nThe corpus was created from ten contemporary blogs:\r\nhintzu.otaku.cz\r\nmodnipeklo.cz\r\nbloc.cz\r\naleneprokopova.blogspot.com\r\nblog.aktualne.cz\r\nfuchsova.blog.onaidnes.cz\r\nhavlik.blog.idnes.cz\r\nblog.aktualne.centrum.cz\r\nklusak.blogspot.cz\r\nmyego.cz/welldone"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-000E-011B-8"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "blogs"
-        },
-        {
-            "name": "annotation"
-        },
-        {
-            "name": "annotators"
-        },
-        {
-            "name": "sentences"
-        },
-        {
-            "name": "machine learning"
-        }
-    ],
-    "title": [
-        "Corpus of contemporary blogs"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/eddce55c-6015-54bb-8a00-5bbfc869117b.json b/oaitestdata/clarin-oai_dc/SET_1/json/eddce55c-6015-54bb-8a00-5bbfc869117b.json
deleted file mode 100644
index 7856077c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/eddce55c-6015-54bb-8a00-5bbfc869117b.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4793",
-    "MetadataAccess": [
-        "oai:ota:oucs:4793"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Donaldson, J. (John), 1737-1801."
-    ],
-    "fulltext": "oai:ota:oucs:4793;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4793.xml;The elements of beauty: Also, reflections on the harmony of sensibility and reason. By J. Donaldson.;Donaldson, J. (John), 1737-1801.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "eddce55c-6015-54bb-8a00-5bbfc869117b",
-    "oai_identifier": [
-        "oai:ota:oucs:4793"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The elements of beauty: Also, reflections on the harmony of sensibility and reason. By J. Donaldson."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4793.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ede762c4-7ec4-534d-a002-5bb3e655d00e.json b/oaitestdata/clarin-oai_dc/SET_1/json/ede762c4-7ec4-534d-a002-5bb3e655d00e.json
deleted file mode 100644
index 70959be2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ede762c4-7ec4-534d-a002-5bb3e655d00e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3825",
-    "MetadataAccess": [
-        "oai:ota:oucs:3825"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Inchbald, Mrs., 1753-1821."
-    ],
-    "fulltext": "oai:ota:oucs:3825;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3825.xml;Wives as they were: and maids as they are, a comedy, in five acts. Performed at the Theatre Royal, Covent-Garden. By Mrs. Inchbald.;Inchbald, Mrs., 1753-1821.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ede762c4-7ec4-534d-a002-5bb3e655d00e",
-    "oai_identifier": [
-        "oai:ota:oucs:3825"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Wives as they were: and maids as they are, a comedy, in five acts. Performed at the Theatre Royal, Covent-Garden. By Mrs. Inchbald."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3825.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/edfbd449-118c-5244-a7de-cb9dfda0aa79.json b/oaitestdata/clarin-oai_dc/SET_1/json/edfbd449-118c-5244-a7de-cb9dfda0aa79.json
deleted file mode 100644
index a69ab9c3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/edfbd449-118c-5244-a7de-cb9dfda0aa79.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3291",
-    "MetadataAccess": [
-        "oai:ota:oucs:3291"
-    ],
-    "PublicationTimestamp": "1888-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1888"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Kipling, Rudyard, 1865-1936"
-    ],
-    "fulltext": "oai:ota:oucs:3291;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3291.xml;Plain Tales from the Hills;Kipling, Rudyard, 1865-1936;not after: 1888;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "edfbd449-118c-5244-a7de-cb9dfda0aa79",
-    "oai_identifier": [
-        "oai:ota:oucs:3291"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Plain Tales from the Hills"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3291.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ee072fcc-72e2-5fb6-9315-ce363e9e2062.json b/oaitestdata/clarin-oai_dc/SET_1/json/ee072fcc-72e2-5fb6-9315-ce363e9e2062.json
deleted file mode 100644
index 0fb33042..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ee072fcc-72e2-5fb6-9315-ce363e9e2062.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4765",
-    "MetadataAccess": [
-        "oai:ota:oucs:4765"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Sheridan, Richard Brinsley, 1751-1816."
-    ],
-    "fulltext": "oai:ota:oucs:4765;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4765.xml;The speech of R. B. Sheridan: ... on Wednesday, the 7th of February, 1787, in bringing forward the fourth charge against Warren Hastings, Esq. relative to the Begums of Oude.;Sheridan, Richard Brinsley, 1751-1816.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ee072fcc-72e2-5fb6-9315-ce363e9e2062",
-    "oai_identifier": [
-        "oai:ota:oucs:4765"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The speech of R. B. Sheridan: ... on Wednesday, the 7th of February, 1787, in bringing forward the fourth charge against Warren Hastings, Esq. relative to the Begums of Oude."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4765.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ee22c070-83a3-563e-bef5-52a49b7a0c53.json b/oaitestdata/clarin-oai_dc/SET_1/json/ee22c070-83a3-563e-bef5-52a49b7a0c53.json
deleted file mode 100644
index fb59b16b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ee22c070-83a3-563e-bef5-52a49b7a0c53.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4137",
-    "MetadataAccess": [
-        "oai:ota:oucs:4137"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Murphy, Arthur, 1727-1805."
-    ],
-    "fulltext": "oai:ota:oucs:4137;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4137.xml;The orphan of China: a tragedy, as it is perform'd at the Theatre-Royal, in Drury-Lane.;Murphy, Arthur, 1727-1805.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ee22c070-83a3-563e-bef5-52a49b7a0c53",
-    "oai_identifier": [
-        "oai:ota:oucs:4137"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The orphan of China: a tragedy, as it is perform'd at the Theatre-Royal, in Drury-Lane."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4137.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ee266fcd-20c6-57d5-af1c-e27c5df42737.json b/oaitestdata/clarin-oai_dc/SET_1/json/ee266fcd-20c6-57d5-af1c-e27c5df42737.json
deleted file mode 100644
index a3901a72..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ee266fcd-20c6-57d5-af1c-e27c5df42737.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4305",
-    "MetadataAccess": [
-        "oai:ota:oucs:4305"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Cheyne, George, 1673-1743."
-    ],
-    "fulltext": "oai:ota:oucs:4305;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4305.xml;A new theory of continual fevers: Wherein, besides the appearances of such fevers, and the method of their cure; occasionally, the structure of the glands, ... are mechanically explan'd.;Cheyne, George, 1673-1743.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ee266fcd-20c6-57d5-af1c-e27c5df42737",
-    "oai_identifier": [
-        "oai:ota:oucs:4305"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A new theory of continual fevers: Wherein, besides the appearances of such fevers, and the method of their cure; occasionally, the structure of the glands, ... are mechanically explan'd."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4305.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ee300706-eb59-5a3c-a801-8345455061b8.json b/oaitestdata/clarin-oai_dc/SET_1/json/ee300706-eb59-5a3c-a801-8345455061b8.json
deleted file mode 100644
index 1e654ded..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ee300706-eb59-5a3c-a801-8345455061b8.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "wolnelektury.pl"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/465",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/465"
-    ],
-    "PID": "http://hdl.handle.net/11321/465",
-    "PublicationTimestamp": "2018-04-13T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "wolnelektury.pl"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0)",
-        "http://creativecommons.org/licenses/by-sa/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Verne, Jules"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/465;2018-04-13T08:41:01Z;hdl_11321_3;hdl_11321_4;Tajemnicza Wyspa;Verne, Jules;websty;Wolnelektury tajemnicza wyspa - cz\u0119\u015b\u0107 1;2018-04-13;corpus;http://hdl.handle.net/11321/465;pol;Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0);http://creativecommons.org/licenses/by-sa/3.0/;CC;text/plain; charset=utf-8;text/plain;downloadable_files_count: 1;wolnelektury.pl;https://wolnelektury.pl",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ee300706-eb59-5a3c-a801-8345455061b8",
-    "notes": [
-        "Wolnelektury tajemnicza wyspa - cz\u0119\u015b\u0107 1"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/465"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "websty"
-        }
-    ],
-    "title": [
-        "Tajemnicza Wyspa"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ee359eff-b9a6-5c4a-9a6f-0f2a39604ffc.json b/oaitestdata/clarin-oai_dc/SET_1/json/ee359eff-b9a6-5c4a-9a6f-0f2a39604ffc.json
deleted file mode 100644
index f8f73ef4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ee359eff-b9a6-5c4a-9a6f-0f2a39604ffc.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=78d16a9028f911e2a2aa782bcb0741356973cd9bfc4046eca30a7df7b832cf99",
-    "MetadataAccess": [
-        "78d16a9028f911e2a2aa782bcb0741356973cd9bfc4046eca30a7df7b832cf99"
-    ],
-    "PublicationTimestamp": "2012-11-07T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "fulltext": "78d16a9028f911e2a2aa782bcb0741356973cd9bfc4046eca30a7df7b832cf99;2018-11-15T16:39:46Z;toolService;toolService:tool;LX-Tagger;The present tool, that was built to deal with Portuguese-specific issues concerning syntactic categorization, assigns a single morpho-syntactic tag, from the tagset below, to every token. The tag is attached to the token, using a / (slash) symbol as separator:\n\num exemplo \u00e2\u0086\u0092 um/IA exemplo/CN\n \nEach individual token in multi-token expressions gets the tag of that expression prefixed by \"L\" and followed by the number of its position within the expression:\n\nde maneira a que \u00e2\u0086\u0092 de/LCJ1 maneira/LCJ2 a/LCJ3 que/LCJ4\n\nThis tagger was developed with TnT software over 90% of a small, 260 Ktoken, accurately hand tagged corpus. Accuracy of 96.87% was obtained with the tagger being trained over 90% of the 260 Ktokens and evaluated over the held out 10%, this being repeated over 10 different test runs and the results averaged.\nLX-Tokenizer was developed and is maintained at University of Lisbon by the NLX-Natural Language and Speech Group of the Department of Informatics.;2012-11-07",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ee359eff-b9a6-5c4a-9a6f-0f2a39604ffc",
-    "notes": [
-        "The present tool, that was built to deal with Portuguese-specific issues concerning syntactic categorization, assigns a single morpho-syntactic tag, from the tagset below, to every token. The tag is attached to the token, using a / (slash) symbol as separator:\n\num exemplo \u00e2\u0086\u0092 um/IA exemplo/CN\n \nEach individual token in multi-token expressions gets the tag of that expression prefixed by \"L\" and followed by the number of its position within the expression:\n\nde maneira a que \u00e2\u0086\u0092 de/LCJ1 maneira/LCJ2 a/LCJ3 que/LCJ4\n\nThis tagger was developed with TnT software over 90% of a small, 260 Ktoken, accurately hand tagged corpus. Accuracy of 96.87% was obtained with the tagger being trained over 90% of the 260 Ktokens and evaluated over the held out 10%, this being repeated over 10 different test runs and the results averaged.\nLX-Tokenizer was developed and is maintained at University of Lisbon by the NLX-Natural Language and Speech Group of the Department of Informatics."
-    ],
-    "oai_identifier": [
-        "78d16a9028f911e2a2aa782bcb0741356973cd9bfc4046eca30a7df7b832cf99"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "LX-Tagger"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ee3cf720-040a-57cd-afba-2e40f3ec9146.json b/oaitestdata/clarin-oai_dc/SET_1/json/ee3cf720-040a-57cd-afba-2e40f3ec9146.json
deleted file mode 100644
index bb9e3af9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ee3cf720-040a-57cd-afba-2e40f3ec9146.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "The Royal Library",
-        "University of Bergen",
-        "Spr\u00e5kbanken, Dept. of Swedish Language, G\u00f6teborg University",
-        "Department of Linguistics and Nordic Studies, University of Oslo",
-        "The National Library of Norway"
-    ],
-    "Contributor": [
-        "lle.uib.no, odd.haugen",
-        "Haugen, Odd Einar"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Old Norse"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-187",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-187"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-187",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "The Royal Library",
-        "University of Bergen",
-        "Spr\u00e5kbanken, Dept. of Swedish Language, G\u00f6teborg University",
-        "Department of Linguistics and Nordic Studies, University of Oslo",
-        "The National Library of Norway"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Norway"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-187;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Menota \u2013 Medieval Nordic Text Archive;Haugen, Odd Einar;lle.uib.no, odd.haugen;Facsimiles and richly TEI-encoded texts, diplomatic and normalised transcriptions;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-187;non;downloadable_files_count: 0;Norway;Department of Linguistics and Nordic Studies, University of Oslo;University of Bergen;The National Library of Norway;The Royal Library;Spr\u00e5kbanken, Dept. of Swedish Language, G\u00f6teborg University;http://www.menota.org",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ee3cf720-040a-57cd-afba-2e40f3ec9146",
-    "notes": [
-        "Facsimiles and richly TEI-encoded texts, diplomatic and normalised transcriptions"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-187"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Menota \u2013 Medieval Nordic Text Archive"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ee3fa144-c651-537e-b0d2-74dc6926095f.json b/oaitestdata/clarin-oai_dc/SET_1/json/ee3fa144-c651-537e-b0d2-74dc6926095f.json
deleted file mode 100644
index 5fc9c55c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ee3fa144-c651-537e-b0d2-74dc6926095f.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 418 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1922",
-    "MetadataAccess": [
-        "oai:ota:oucs:1922"
-    ],
-    "PublicationTimestamp": "1823-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1823"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Shelley, Mary Wollstonecraft, 1797-1851"
-    ],
-    "fulltext": "oai:ota:oucs:1922;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/1922.xml;Frankenstein [Electronic resource], or, The modern Prometheus / by Mary Wollestonecraft Shelley;Shelley, Mary Wollstonecraft, 1797-1851;1823;text_and_corpus_linguistics;Fiction -- Great Britain -- 19th century;Novels -- Great Britain -- 19th century;Epistolary novels -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 418 KB);Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ee3fa144-c651-537e-b0d2-74dc6926095f",
-    "oai_identifier": [
-        "oai:ota:oucs:1922"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- Great Britain -- th century"
-        },
-        {
-            "name": "Novels -- Great Britain -- th century"
-        },
-        {
-            "name": "Epistolary novels -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Frankenstein [Electronic resource], or, The modern Prometheus / by Mary Wollestonecraft Shelley"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1922.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ee5cf395-03bc-5029-8ea2-f509d28821d5.json b/oaitestdata/clarin-oai_dc/SET_1/json/ee5cf395-03bc-5029-8ea2-f509d28821d5.json
deleted file mode 100644
index 8d86b558..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ee5cf395-03bc-5029-8ea2-f509d28821d5.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Dutch",
-        "English",
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-707",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-707"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-707",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-707;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;CELEX (web version);2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-707;nld;eng;deu;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://celex.mpi.nl/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ee5cf395-03bc-5029-8ea2-f509d28821d5",
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-707"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "CELEX (web version)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ee67caf7-0686-5baf-a344-66b11e498299.json b/oaitestdata/clarin-oai_dc/SET_1/json/ee67caf7-0686-5baf-a344-66b11e498299.json
deleted file mode 100644
index dbf11100..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ee67caf7-0686-5baf-a344-66b11e498299.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "text/html",
-        "application/zip"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1469",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1469"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1469",
-    "PublicationTimestamp": "2015-03-13T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11858/00-097C-0000-000D-F67C-5"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "BSD 2-Clause \"Simplified\" or \"FreeBSD\" license",
-        "http://opensource.org/licenses/BSD-2-Clause",
-        "PUB"
-    ],
-    "author": [
-        "Straka, Milan",
-        "Richter, Michal"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1469;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Korektor 2;Straka, Milan;Richter, Michal;Korektor;spellchecker;spellchecking;grammar checker;diacritical marks generation;Korektor is a statistical spell-checker and (occasionally) grammar-checker.  It is released under 2-Clause BSD license http://opensource.org/licenses/BSD-2-Clause.\r\n\r\nKorektor started with Michal Richter's diploma thesis Advanced Czech Spellchecker https://redmine.ms.mff.cuni.cz/documents/1, but it is being developed further. There are two versions: a command line utility (tested on Linux, Windows and OS X) and a REST service with publicly available API http://lindat.mff.cuni.cz/services/korektor/api-reference.php and HTML front end https://lindat.mff.cuni.cz/services/korektor/.;2015-03-13;toolService;http://hdl.handle.net/11234/1-1469;eng;http://hdl.handle.net/11858/00-097C-0000-000D-F67C-5;BSD 2-Clause \"Simplified\" or \"FreeBSD\" license;http://opensource.org/licenses/BSD-2-Clause;PUB;text/plain; charset=utf-8;application/zip;text/html;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/korektor",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ee67caf7-0686-5baf-a344-66b11e498299",
-    "notes": [
-        "Korektor is a statistical spell-checker and (occasionally) grammar-checker.  It is released under 2-Clause BSD license http://opensource.org/licenses/BSD-2-Clause.\r\n\r\nKorektor started with Michal Richter's diploma thesis Advanced Czech Spellchecker https://redmine.ms.mff.cuni.cz/documents/1, but it is being developed further. There are two versions: a command line utility (tested on Linux, Windows and OS X) and a REST service with publicly available API http://lindat.mff.cuni.cz/services/korektor/api-reference.php and HTML front end https://lindat.mff.cuni.cz/services/korektor/."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1469"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Korektor"
-        },
-        {
-            "name": "spellchecker"
-        },
-        {
-            "name": "spellchecking"
-        },
-        {
-            "name": "grammar checker"
-        },
-        {
-            "name": "diacritical marks generation"
-        }
-    ],
-    "title": [
-        "Korektor 2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ee6def86-703d-5802-a3bc-831ede451609.json b/oaitestdata/clarin-oai_dc/SET_1/json/ee6def86-703d-5802-a3bc-831ede451609.json
deleted file mode 100644
index f15c1bc0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ee6def86-703d-5802-a3bc-831ede451609.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2616",
-    "MetadataAccess": [
-        "oai:ota:oucs:2616"
-    ],
-    "PublicationTimestamp": "1701-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1701"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2616;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2616.xml;The publisher to the reader in Sir William Temple's Miscellanea;Swift, Jonathan, 1667-1745;1701;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ee6def86-703d-5802-a3bc-831ede451609",
-    "oai_identifier": [
-        "oai:ota:oucs:2616"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The publisher to the reader in Sir William Temple's Miscellanea"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2616.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/eec1770a-2d3a-53fc-872a-bc30c1d9e666.json b/oaitestdata/clarin-oai_dc/SET_1/json/eec1770a-2d3a-53fc-872a-bc30c1d9e666.json
deleted file mode 100644
index ba13d6ab..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/eec1770a-2d3a-53fc-872a-bc30c1d9e666.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "A"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1755",
-    "MetadataAccess": [
-        "oai:ota:oucs:1755"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Conrad, Joseph"
-    ],
-    "fulltext": "oai:ota:oucs:1755;2018-04-16T15:30:51Z;http://ota.ox.ac.uk/headers/1755.xml;The secret sharer;Conrad, Joseph;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;A;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "eec1770a-2d3a-53fc-872a-bc30c1d9e666",
-    "oai_identifier": [
-        "oai:ota:oucs:1755"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The secret sharer"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1755.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/eec91f1b-871f-5b99-bef2-2715a1564060.json b/oaitestdata/clarin-oai_dc/SET_1/json/eec91f1b-871f-5b99-bef2-2715a1564060.json
deleted file mode 100644
index a015a839..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/eec91f1b-871f-5b99-bef2-2715a1564060.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "Contributor": [
-        "Murzynowski, Grzegorz"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1168",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1168"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1168",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Poland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1168;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Anotatornia;Murzynowski, Grzegorz;Tool for manual on-line annotation of corpora at various linguistic levels. The levels currently implemented are: word-level and sentence-level segmentation, morphosyntax, word sense disambiguation. Anotatornia implements sophisticated mechanisms of the management of texts, annotators and conflicts.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1168;downloadable_files_count: 0;Poland;Institute of Computer Science, Polish Academy of Sciences;http://zil.ipipan.waw.pl/Anotatornia",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "eec91f1b-871f-5b99-bef2-2715a1564060",
-    "notes": [
-        "Tool for manual on-line annotation of corpora at various linguistic levels. The levels currently implemented are: word-level and sentence-level segmentation, morphosyntax, word sense disambiguation. Anotatornia implements sophisticated mechanisms of the management of texts, annotators and conflicts."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1168"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Anotatornia"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/eee655c5-4677-5a65-a536-b810800448e4.json b/oaitestdata/clarin-oai_dc/SET_1/json/eee655c5-4677-5a65-a536-b810800448e4.json
deleted file mode 100644
index 4f1ee9e8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/eee655c5-4677-5a65-a536-b810800448e4.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "Contributor": [
-        "N\u00e1zar, Rogelio"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1211",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1211"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1211",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1211;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Jaguar;N\u00e1zar, Rogelio;A tool for statistical corpus exploitation. It offers concordances, counts ngrams, extracts collocations and gives association, distribution and similarity measures.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1211;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra;http://melot.upf.edu/cgi-bin/jaguar/jaguar.pl",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "eee655c5-4677-5a65-a536-b810800448e4",
-    "notes": [
-        "A tool for statistical corpus exploitation. It offers concordances, counts ngrams, extracts collocations and gives association, distribution and similarity measures."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1211"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Jaguar"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/eeeb563e-791e-54fc-a8c7-258d56c1b2b3.json b/oaitestdata/clarin-oai_dc/SET_1/json/eeeb563e-791e-54fc-a8c7-258d56c1b2b3.json
deleted file mode 100644
index 87ab42fa..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/eeeb563e-791e-54fc-a8c7-258d56c1b2b3.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1031",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1031"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1031",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1031;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;L1 Acquisition Barbara Schmiedtova;Language Acquisition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1031;deu;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI12464%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "eeeb563e-791e-54fc-a8c7-258d56c1b2b3",
-    "notes": [
-        "Language Acquisition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1031"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "L1 Acquisition Barbara Schmiedtova"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/eeedf5b7-6be5-5715-b2dd-8b3b7c6cb99d.json b/oaitestdata/clarin-oai_dc/SET_1/json/eeedf5b7-6be5-5715-b2dd-8b3b7c6cb99d.json
deleted file mode 100644
index 9bf4474e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/eeedf5b7-6be5-5715-b2dd-8b3b7c6cb99d.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "KUL"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 86",
-        "text/plain; charset=utf-8",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/513",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/513"
-    ],
-    "PID": "http://hdl.handle.net/11321/513",
-    "PublicationTimestamp": "2018-07-13T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "KUL"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Super Cool License",
-        "http://www.google.com",
-        "ACA"
-    ],
-    "author": [
-        "Kaczor, Donald",
-        "Myszka, Miki"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/513;2018-07-13T13:51:08Z;hdl_11321_3;hdl_11321_4;corpus warsztatowy;Myszka, Miki;Kaczor, Donald;Polish;corpus;2018-07-13;corpus;http://hdl.handle.net/11321/513;pol;Super Cool License;http://www.google.com;ACA;text/plain; charset=utf-8;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;downloadable_files_count: 86;KUL",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "eeedf5b7-6be5-5715-b2dd-8b3b7c6cb99d",
-    "notes": [
-        "corpus"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/513"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Polish"
-        }
-    ],
-    "title": [
-        "corpus warsztatowy"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/eeff4281-7823-5972-ac09-5d3b7f8416a1.json b/oaitestdata/clarin-oai_dc/SET_1/json/eeff4281-7823-5972-ac09-5d3b7f8416a1.json
deleted file mode 100644
index 1ebe6cc0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/eeff4281-7823-5972-ac09-5d3b7f8416a1.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Lancashire, Ian"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 159 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1331",
-    "MetadataAccess": [
-        "oai:ota:oucs:1331"
-    ],
-    "PublicationTimestamp": "1486-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1486"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Medwall, Henry, active 1486"
-    ],
-    "fulltext": "oai:ota:oucs:1331;2018-03-07T16:12:07Z;http://ota.ox.ac.uk/headers/1331.xml;Nature / Henry Medwall;Medwall, Henry, active 1486;1486;text_and_corpus_linguistics;English drama -- Early modern and Elizabethan, 1500-1600;Oxford Text Archive, University of Oxford;Lancashire, Ian;(1 file : ca. 159 KB);Text;Plays;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "eeff4281-7823-5972-ac09-5d3b7f8416a1",
-    "oai_identifier": [
-        "oai:ota:oucs:1331"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- Early modern Elizabethan"
-        }
-    ],
-    "title": [
-        "Nature / Henry Medwall"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1331.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ef16414d-fdde-5e53-99a0-49fb40c09d68.json b/oaitestdata/clarin-oai_dc/SET_1/json/ef16414d-fdde-5e53-99a0-49fb40c09d68.json
deleted file mode 100644
index 7005edae..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ef16414d-fdde-5e53-99a0-49fb40c09d68.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Masaryk University, Brno"
-    ],
-    "Contributor": [
-        "Rambousek, Jiri"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Czech",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-891",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-891"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-891",
-    "PublicationTimestamp": "1997-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1997"
-    ],
-    "Publisher": [
-        "Masaryk University, Brno"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Czech Republic"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-891;2018-10-29T16:30:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Kacenka : parallel corpus of English and Czech texts;Rambousek, Jiri;Parallel corpus, 3,297,283 words.\r\n\r\nThe idea was to create a small parallel corpus which would enable to work with entire texts in translation analysis rather then short extracts. At the same time it aimed at acquiring experience that could be used in creating a larger parallel corpus of English and Czech in the future.\r\nAlthough the main part of work has been completed -- and the aims of the KACENKA grant met -- we keep improving and enlarging KACENKA gradually. Currently, it has the size of 3,297,283 words (out of which, 1,689,513 have been acquired by means of scanning).\r\n\r\nMost of the English texts for KACENKA have been retrieved from the Internet resources. The rest -- and nearly all the Czech texts -- had to be scanned with the use of an OCR programme.\r\n\r\nKACENKA is stored on a single CD-ROM; its use is limited by copyright restrictions.;1997;corpus;http://hdl.handle.net/11372/LRT-891;ces;eng;downloadable_files_count: 0;Czech Republic;Masaryk University, Brno;http://www.phil.muni.cz/angl/kacenka/kachna.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ef16414d-fdde-5e53-99a0-49fb40c09d68",
-    "notes": [
-        "Parallel corpus, 3,297,283 words.\r\n\r\nThe idea was to create a small parallel corpus which would enable to work with entire texts in translation analysis rather then short extracts. At the same time it aimed at acquiring experience that could be used in creating a larger parallel corpus of English and Czech in the future.\r\nAlthough the main part of work has been completed -- and the aims of the KACENKA grant met -- we keep improving and enlarging KACENKA gradually. Currently, it has the size of 3,297,283 words (out of which, 1,689,513 have been acquired by means of scanning).\r\n\r\nMost of the English texts for KACENKA have been retrieved from the Internet resources. The rest -- and nearly all the Czech texts -- had to be scanned with the use of an OCR programme.\r\n\r\nKACENKA is stored on a single CD-ROM; its use is limited by copyright restrictions."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-891"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Kacenka : parallel corpus of English and Czech texts"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ef300bf8-2c6d-58d8-ae00-105060943448.json b/oaitestdata/clarin-oai_dc/SET_1/json/ef300bf8-2c6d-58d8-ae00-105060943448.json
deleted file mode 100644
index 7bf3f8d0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ef300bf8-2c6d-58d8-ae00-105060943448.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Berlin-Brandenburg Academy of Sciences and Humanities"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/tei+xml",
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-973",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-973"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-973",
-    "PublicationTimestamp": "2006-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2006"
-    ],
-    "Publisher": [
-        "Berlin-Brandenburg Academy of Sciences and Humanities"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-973;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Berliner Wendekorpus;Transcribed narrative interviews with people from East and West Berlin about the events of November 9. 282,000 tokens. TEI XML, lemma and POS. Normalized version also available.;2006;corpus;http://hdl.handle.net/11372/LRT-973;deu;application/tei+xml;downloadable_files_count: 0;Germany;Berlin-Brandenburg Academy of Sciences and Humanities;http://www.dwds.de/ressourcen/wendekorpus/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ef300bf8-2c6d-58d8-ae00-105060943448",
-    "notes": [
-        "Transcribed narrative interviews with people from East and West Berlin about the events of November 9. 282,000 tokens. TEI XML, lemma and POS. Normalized version also available."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-973"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Berliner Wendekorpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ef37979d-aeee-5350-afd3-970c6b3554bc.json b/oaitestdata/clarin-oai_dc/SET_1/json/ef37979d-aeee-5350-afd3-970c6b3554bc.json
deleted file mode 100644
index f3919d73..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ef37979d-aeee-5350-afd3-970c6b3554bc.json
+++ /dev/null
@@ -1,100 +0,0 @@
-{
-    "Contact": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 5",
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
-        "application/pdf"
-    ],
-    "Language": [
-        "Basque",
-        "Karelian",
-        "Breton",
-        "Sardinian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-77",
-    "MetadataAccess": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-77"
-    ],
-    "PID": "http://hdl.handle.net/20.500.11752/ILC-77",
-    "PublicationTimestamp": "2017-09-04T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0",
-        "PUB"
-    ],
-    "author": [
-        "Gurrutxaga Hernaiz, Antton",
-        "Ceberio Berger, Klara",
-        "Russo, Irene",
-        "Kruse, Eleonore",
-        "Soria, Claudia",
-        "Quochi, Valeria",
-        "Sarhimaa, Anneli",
-        "Salonen, Tuomo",
-        "Hicks, Davyth"
-    ],
-    "fulltext": "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-77;2018-04-06T07:31:29Z;hdl_000-c0-111_38;hdl_000-c0-111_49;Digital Language Diversity Project Survey Data;Soria, Claudia;Quochi, Valeria;Russo, Irene;Sarhimaa, Anneli;Kruse, Eleonore;Hicks, Davyth;Salonen, Tuomo;Gurrutxaga Hernaiz, Antton;Ceberio Berger, Klara;Linguistic diversity;Minority languages;Digital language diversity;Language vitality;Regional languages;Survey data;Sociolinguistics;This dataset contains the original responses to a questionaire run in 2016 within the DLDP project about the use and usability of 4 European regional and minority languages on digital media and devices: namely Basque, Breton, Karelian and Sardinian (See http://www.dldp.eu/content/survey-digital-fitness). \r\n\r\nThe majority of questions were closed questions where respondents had to tick a box, occasionally multiple choice was allowed.  A few questions required free text provision. \r\nThe questionnaire was designed using 'Google Forms' and was run on the same platform in the summer 2016.\r\n\r\nThe results of the survey are brielfly presented in the DLDP reports available here: http://www.dldp.eu/content/reports-digital-language-diversity-europe;2017-09-04;corpus;http://hdl.handle.net/20.500.11752/ILC-77;eus;krl;bre;srd;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0;PUB;application/vnd.openxmlformats-officedocument.spreadsheetml.sheet;application/vnd.openxmlformats-officedocument.spreadsheetml.sheet;application/vnd.openxmlformats-officedocument.spreadsheetml.sheet;application/vnd.openxmlformats-officedocument.spreadsheetml.sheet;application/pdf;text/plain; charset=utf-8;downloadable_files_count: 5;Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR);http://www.dldp.eu",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ef37979d-aeee-5350-afd3-970c6b3554bc",
-    "notes": [
-        "This dataset contains the original responses to a questionaire run in 2016 within the DLDP project about the use and usability of 4 European regional and minority languages on digital media and devices: namely Basque, Breton, Karelian and Sardinian (See http://www.dldp.eu/content/survey-digital-fitness). \r\n\r\nThe majority of questions were closed questions where respondents had to tick a box, occasionally multiple choice was allowed.  A few questions required free text provision. \r\nThe questionnaire was designed using 'Google Forms' and was run on the same platform in the summer 2016.\r\n\r\nThe results of the survey are brielfly presented in the DLDP reports available here: http://www.dldp.eu/content/reports-digital-language-diversity-europe"
-    ],
-    "oai_identifier": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-77"
-    ],
-    "oai_set": [
-        "hdl_000-c0-111_38",
-        "hdl_000-c0-111_49"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Linguistic diversity"
-        },
-        {
-            "name": "Minority languages"
-        },
-        {
-            "name": "Digital language diversity"
-        },
-        {
-            "name": "Language vitality"
-        },
-        {
-            "name": "Regional languages"
-        },
-        {
-            "name": "Survey data"
-        },
-        {
-            "name": "Sociolinguistics"
-        }
-    ],
-    "title": [
-        "Digital Language Diversity Project Survey Data"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ef430707-b97c-5cc4-9fe8-61ecdeb94707.json b/oaitestdata/clarin-oai_dc/SET_1/json/ef430707-b97c-5cc4-9fe8-61ecdeb94707.json
deleted file mode 100644
index 55135e0a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ef430707-b97c-5cc4-9fe8-61ecdeb94707.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4920",
-    "MetadataAccess": [
-        "oai:ota:oucs:4920"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Whiston, William, 1667-1752."
-    ],
-    "fulltext": "oai:ota:oucs:4920;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4920.xml;The Copernicus explain'd: or a brief account of the nature and use of an universal astronomical instrument, for the calculation and exhibition of new and full moons, and of eclipses, ... By William Whiston, ...;Whiston, William, 1667-1752.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ef430707-b97c-5cc4-9fe8-61ecdeb94707",
-    "oai_identifier": [
-        "oai:ota:oucs:4920"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The Copernicus explain'd: or a brief account of the nature and use of an universal astronomical instrument, for the calculation and exhibition of new and full moons, and of eclipses, ... By William Whiston, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4920.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ef43c7b3-dcb0-5299-b241-b3d0f2f8eea1.json b/oaitestdata/clarin-oai_dc/SET_1/json/ef43c7b3-dcb0-5299-b241-b3d0f2f8eea1.json
deleted file mode 100644
index fc49ac93..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ef43c7b3-dcb0-5299-b241-b3d0f2f8eea1.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/39",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/39"
-    ],
-    "PID": "http://hdl.handle.net/10794/39",
-    "PublicationTimestamp": "2012-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/39;2017-10-27T13:46:47Z;hdl_10794_1;hdl_10794_2;Simple+ (2017-10-16);Simple+ (2017-10-16);n/a, n/a;Swedish;SIMPLE;The Swedish SIMPLE Lexicon - A language technology resource with access to semantic information in Swedish, connected to SALDO senses.;Svenskt SIMPLE lexikon - En spr\u00e5kteknologisk resurs med semantisk information, kopplade till betydelser i SALDO.;2012-05-30;lexicalConceptualResource;http://hdl.handle.net/10794/39;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;http://creativecommons.org/licenses/by/4.0/;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/simpleplus",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ef43c7b3-dcb0-5299-b241-b3d0f2f8eea1",
-    "notes": [
-        "The Swedish SIMPLE Lexicon - A language technology resource with access to semantic information in Swedish, connected to SALDO senses.",
-        "Svenskt SIMPLE lexikon - En spr\u00e5kteknologisk resurs med semantisk information, kopplade till betydelser i SALDO."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/39"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "SIMPLE"
-        }
-    ],
-    "title": [
-        "Simple+ (2017-10-16)",
-        "Simple+ (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ef4da460-51b5-5ae9-805d-75735c07b7d3.json b/oaitestdata/clarin-oai_dc/SET_1/json/ef4da460-51b5-5ae9-805d-75735c07b7d3.json
deleted file mode 100644
index a5908d50..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ef4da460-51b5-5ae9-805d-75735c07b7d3.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=2ba8b83c059911e7a2aa782bcb074135c22b4b7e1aed475fa8b7689e0f8a731f",
-    "MetadataAccess": [
-        "2ba8b83c059911e7a2aa782bcb074135c22b4b7e1aed475fa8b7689e0f8a731f"
-    ],
-    "PublicationTimestamp": "2017-03-10T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "fulltext": "2ba8b83c059911e7a2aa782bcb074135c22b4b7e1aed475fa8b7689e0f8a731f;2018-11-15T16:40:32Z;toolService;toolService:tool;Basque to English Machine translation module;Technical Description:\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/Pilot1_technical_description.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/TechnicalDescriptionPilot2_D2.7.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2016/11/TechnicalDescriptionPilot3_D2.10.pdf;2017-03-10",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ef4da460-51b5-5ae9-805d-75735c07b7d3",
-    "notes": [
-        "Technical Description:\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/Pilot1_technical_description.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2015/05/TechnicalDescriptionPilot2_D2.7.pdf\n\nhttp://qtleap.eu/wp-content/uploads/2016/11/TechnicalDescriptionPilot3_D2.10.pdf"
-    ],
-    "oai_identifier": [
-        "2ba8b83c059911e7a2aa782bcb074135c22b4b7e1aed475fa8b7689e0f8a731f"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "Basque to English Machine translation module"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ef53dab6-c492-50bc-b83a-979fd75ae6e3.json b/oaitestdata/clarin-oai_dc/SET_1/json/ef53dab6-c492-50bc-b83a-979fd75ae6e3.json
deleted file mode 100644
index 2b204cdb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ef53dab6-c492-50bc-b83a-979fd75ae6e3.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5673",
-    "MetadataAccess": [
-        "oai:ota:oucs:5673"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Edgeworth, Maria, 1767-1849."
-    ],
-    "fulltext": "oai:ota:oucs:5673;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5673.xml;The parent's assistant; or, stories for children. Part I. Containing, The Little Dog Trusty; OR, The Liar And Boy Of Truth. The Orange Man; OR, The Honest Boy And The Thief. Tarlton. Lazy Lawrence. The False Key: and Barring-Out. To which is prefixed, an address to parents.;Parent's assistant [pt.1].;Edgeworth, Maria, 1767-1849.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ef53dab6-c492-50bc-b83a-979fd75ae6e3",
-    "oai_identifier": [
-        "oai:ota:oucs:5673"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The parent's assistant; or, stories for children. Part I. Containing, The Little Dog Trusty; OR, The Liar And Boy Of Truth. The Orange Man; OR, The Honest Boy And The Thief. Tarlton. Lazy Lawrence. The False Key: and Barring-Out. To which is prefixed, an address to parents.",
-        "Parent's assistant [pt.1]."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5673.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ef63b4e3-5d50-52e0-b781-07d95abe75fc.json b/oaitestdata/clarin-oai_dc/SET_1/json/ef63b4e3-5d50-52e0-b781-07d95abe75fc.json
deleted file mode 100644
index 35e06ca8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ef63b4e3-5d50-52e0-b781-07d95abe75fc.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 142 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1534",
-    "MetadataAccess": [
-        "oai:ota:oucs:1534"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Chapman, George"
-    ],
-    "fulltext": "oai:ota:oucs:1534;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1534.xml;Bussy d'Ambois;Chapman, George;default: 1976-01-01;text_and_corpus_linguistics;Plays -- England -- 17th century;Tragedies -- England -- 17th century;eng;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 142 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ef63b4e3-5d50-52e0-b781-07d95abe75fc",
-    "oai_identifier": [
-        "oai:ota:oucs:1534"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        },
-        {
-            "name": "Tragedies -- England -- th century"
-        }
-    ],
-    "title": [
-        "Bussy d'Ambois"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1534.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ef8226e5-bb61-5850-8c9f-e596b7cb52b7.json b/oaitestdata/clarin-oai_dc/SET_1/json/ef8226e5-bb61-5850-8c9f-e596b7cb52b7.json
deleted file mode 100644
index 060d2ed9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ef8226e5-bb61-5850-8c9f-e596b7cb52b7.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2714",
-    "MetadataAccess": [
-        "oai:ota:oucs:2714"
-    ],
-    "PublicationTimestamp": "1720-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1720"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2714;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2714.xml;The last farewell of Ebenezor Elliston to this transitory world;Swift, Jonathan, 1667-1745;[1720?];text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ef8226e5-bb61-5850-8c9f-e596b7cb52b7",
-    "oai_identifier": [
-        "oai:ota:oucs:2714"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The last farewell of Ebenezor Elliston to this transitory world"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2714.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ef92104c-0950-5bed-83ca-9a3fa7dccf19.json b/oaitestdata/clarin-oai_dc/SET_1/json/ef92104c-0950-5bed-83ca-9a3fa7dccf19.json
deleted file mode 100644
index fe33e9f8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ef92104c-0950-5bed-83ca-9a3fa7dccf19.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2888",
-    "MetadataAccess": [
-        "oai:ota:oucs:2888"
-    ],
-    "PublicationTimestamp": "1755-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1755"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2888;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2888.xml;Thoughts on various subjects (Further thoughts on various subjects);Swift, Jonathan, 1667-1745;1755;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ef92104c-0950-5bed-83ca-9a3fa7dccf19",
-    "oai_identifier": [
-        "oai:ota:oucs:2888"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Thoughts on various subjects (Further thoughts on various subjects)"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2888.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ef9c5bf6-c822-5b9f-b937-807bc6733c86.json b/oaitestdata/clarin-oai_dc/SET_1/json/ef9c5bf6-c822-5b9f-b937-807bc6733c86.json
deleted file mode 100644
index 665088f7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ef9c5bf6-c822-5b9f-b937-807bc6733c86.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/16",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/16"
-    ],
-    "PID": "http://hdl.handle.net/10794/16",
-    "PublicationTimestamp": "2012-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/16;2017-10-27T15:49:35Z;hdl_10794_1;hdl_10794_2;Dalin's Dictionary (2017-10-16);Dalin Ordbok \u00d6fver Svenska Spr\u00e5ket (2017-10-16);n/a, n/a;Swedish;Dictionary;Dalin's Dictionary of 19th century Swedish.;Dalins ordbok - Ordbok \u00f6ver 1800-talsspr\u00e5ket.;2012-05-30;lexicalConceptualResource;http://hdl.handle.net/10794/16;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/dalin",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ef9c5bf6-c822-5b9f-b937-807bc6733c86",
-    "notes": [
-        "Dalin's Dictionary of 19th century Swedish.",
-        "Dalins ordbok - Ordbok \u00f6ver 1800-talsspr\u00e5ket."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/16"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Dictionary"
-        }
-    ],
-    "title": [
-        "Dalin's Dictionary (2017-10-16)",
-        "Dalin Ordbok \u00d6fver Svenska Spr\u00e5ket (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/efa6f842-9b79-56ba-9332-85719f8dd3df.json b/oaitestdata/clarin-oai_dc/SET_1/json/efa6f842-9b79-56ba-9332-85719f8dd3df.json
deleted file mode 100644
index b906714e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/efa6f842-9b79-56ba-9332-85719f8dd3df.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contributor": [
-        "Manfred Pinkal",
-        "Alessandra Zarcone",
-        "Stefan Thater",
-        "Lilian Wanzare"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:descript",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:descript"
-    ],
-    "PID": "http://hdl.handle.net/21.11119/0000-0000-5DCF-0",
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "RelatedIdentifier": [
-        "Lilian Wanzare, Alessandra Zarcone, Stefan Thater and Manfred Pinkal. 2016. \"DeScript: A Crowdsourced Corpus for the Acquisition of High-Quality Script Knowledge\". In Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC 16), Portoro\u017e, Slovenia. http://www.lrec-conf.org/proceedings/lrec2016/pdf/913_Paper.pdf"
-    ],
-    "ResourceType": [
-        "Collection",
-        "Dataset",
-        "Text"
-    ],
-    "Rights": [
-        "CC-BY-SA-NC-4.0"
-    ],
-    "author": [
-        "Lilian Wanzare, Fachrichtung Sprachwissenschaft und Sprachtechnologie, Universit\u00e4t des Saarlandes, Campus C7.4, 66123 Saarbr\u00fccken"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:descript;2018-01-31T16:10:04Z;DeScript: A Crowdsourced Corpus for the Acquisition of High-Quality Script Knowledge;Lilian Wanzare, Fachrichtung Sprachwissenschaft und Sprachtechnologie, Universit\u00e4t des Saarlandes, Campus C7.4, 66123 Saarbr\u00fccken;Scripts;Events;Crowdsourcing;Paraphrases;DeScript is a crowdsourced corpus of event sequence descriptions (ESDs) for different scenarios crowdsourced via Amazon Mechanical Turk. It has 40 scenarios with approximately 100 ESDs each. The corpus also has partial alignments of event descriptions that are semantically similar with respect to the given scenario.;Lilian Wanzare;Alessandra Zarcone;Stefan Thater;Manfred Pinkal;2016;Collection;Dataset;Text;text/xml;clarind-uds:descript;hdl:21.11119/0000-0000-5DCF-0;eng;Lilian Wanzare, Alessandra Zarcone, Stefan Thater and Manfred Pinkal. 2016. \"DeScript: A Crowdsourced Corpus for the Acquisition of High-Quality Script Knowledge\". In Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC 16), Portoro\u017e, Slovenia. http://www.lrec-conf.org/proceedings/lrec2016/pdf/913_Paper.pdf;CC-BY-SA-NC-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "efa6f842-9b79-56ba-9332-85719f8dd3df",
-    "notes": [
-        "DeScript is a crowdsourced corpus of event sequence descriptions (ESDs) for different scenarios crowdsourced via Amazon Mechanical Turk. It has 40 scenarios with approximately 100 ESDs each. The corpus also has partial alignments of event descriptions that are semantically similar with respect to the given scenario."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:descript"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Scripts"
-        },
-        {
-            "name": "Events"
-        },
-        {
-            "name": "Crowdsourcing"
-        },
-        {
-            "name": "Paraphrases"
-        }
-    ],
-    "title": [
-        "DeScript: A Crowdsourced Corpus for the Acquisition of High-Quality Script Knowledge"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/efac1ba9-b216-5d53-a284-37543f67b473.json b/oaitestdata/clarin-oai_dc/SET_1/json/efac1ba9-b216-5d53-a284-37543f67b473.json
deleted file mode 100644
index f1087b35..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/efac1ba9-b216-5d53-a284-37543f67b473.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "greater than 5 MB"
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0696",
-    "MetadataAccess": [
-        "oai:ota:oucs:0696"
-    ],
-    "PublicationYear": [
-        "unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Local histories"
-    ],
-    "Rights": [
-        "No data.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:0696;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0696.xml;Duke data bank of documentary papyri  / compiled by W.H. Willis;unknown;text_and_corpus_linguistics;Local histories;grc;Oxford Text Archive, University of Oxford;greater than 5 MB;Text;Local histories;No data.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "efac1ba9-b216-5d53-a284-37543f67b473",
-    "oai_identifier": [
-        "oai:ota:oucs:0696"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Local histories"
-        }
-    ],
-    "title": [
-        "Duke data bank of documentary papyri  / compiled by W.H. Willis"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0696.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/efada2f0-be70-5a65-ad66-ebe59cc95da1.json b/oaitestdata/clarin-oai_dc/SET_1/json/efada2f0-be70-5a65-ad66-ebe59cc95da1.json
deleted file mode 100644
index 48ee9359..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/efada2f0-be70-5a65-ad66-ebe59cc95da1.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Computer and Information Science, University of Ljubljana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1156",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1156"
-    ],
-    "PID": "http://hdl.handle.net/11356/1156",
-    "PublicationTimestamp": "2017-09-26T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Faculty of Computer and Information Science, University of Ljubljana"
-    ],
-    "RelatedIdentifier": [
-        "http://videolectures.net/jota_krsnik_napovedovanje_naglasa/",
-        "https://repozitorij.uni-lj.si/IzpisGradiva.php?id=98276",
-        "http://hdl.handle.net/11356/1186"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u0160ef, Toma\u017e",
-        "Krsnik, Luka",
-        "Robnik-\u0160ikonja, Marko"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1156;2018-05-08T02:03:44Z;hdl_11356_1023;hdl_11356_1024;Automatically stress labelled morphological lexicon Sloleks 1.2;Krsnik, Luka;Robnik-\u0160ikonja, Marko;\u0160ef, Toma\u017e;word stress;This lexicon is an extended version of Sloleks 1.2  (http://hdl.handle.net/11356/1039). It contains all the original data from Sloleks with added information about the stress of each word form, which is included two ways: information about stress location only, and information about stress location and type. The stress assignment was performed automatically, with algorithms based on deep neural networks which correctly predicted accent location in around 90 % and combined accent type and location in about 87.5 % of test data. Therefore all accents are not correct.;2017-09-26;lexicalConceptualResource;http://hdl.handle.net/11356/1156;slv;http://videolectures.net/jota_krsnik_napovedovanje_naglasa/;https://repozitorij.uni-lj.si/IzpisGradiva.php?id=98276;http://hdl.handle.net/11356/1186;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);https://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;Faculty of Computer and Information Science, University of Ljubljana;https://github.com/lkrsnik/simple_accentuation",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "efada2f0-be70-5a65-ad66-ebe59cc95da1",
-    "notes": [
-        "This lexicon is an extended version of Sloleks 1.2  (http://hdl.handle.net/11356/1039). It contains all the original data from Sloleks with added information about the stress of each word form, which is included two ways: information about stress location only, and information about stress location and type. The stress assignment was performed automatically, with algorithms based on deep neural networks which correctly predicted accent location in around 90 % and combined accent type and location in about 87.5 % of test data. Therefore all accents are not correct."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1156"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "word stress"
-        }
-    ],
-    "title": [
-        "Automatically stress labelled morphological lexicon Sloleks 1.2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/efaf940d-cd3b-5cd9-8201-3ab4d19338eb.json b/oaitestdata/clarin-oai_dc/SET_1/json/efaf940d-cd3b-5cd9-8201-3ab4d19338eb.json
deleted file mode 100644
index e52da4aa..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/efaf940d-cd3b-5cd9-8201-3ab4d19338eb.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Department of Information Technology, Gauhati University, Assam, India"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Assamese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/621",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/621"
-    ],
-    "PID": "http://hdl.handle.net/11321/621",
-    "PublicationTimestamp": "2019-01-15T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Department of Information Technology, Gauhati University, Assam, India"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "author": [
-        "Sarma, Prof. Shikhar Kr."
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/621;2019-01-15T10:13:41Z;hdl_11321_3;hdl_11321_610;Assamese POS-Tagged Text;Sarma, Prof. Shikhar Kr.;Assamese NLP;Assamese POS Tagged text;Assamese Part of Speech tagged text;Assamese CRF++;Gauhati University;Assamese POS tagger is a CRF++ based POS Tagger. Raw text is given to this CRF++ based POS tagger to get POS tagged data. Standard POS tagset is used.\r\n\r\n---\r\n\r\n1. These Assamese NLP resources including the Tools and Applications are developed\r\nduring Research and Development Projects as well as Masters and Ph.D. thesis\r\nworks.\r\n2. These are mainly developed or generated at Gauhati University Department of\r\nComputer Science and Department of Information Technology.\r\n3. These resources are used by students and researchers for further studies, researches, as\r\nwell as for design and development of tools and applications.\r\n4. Computational Linguistics in Assamese is not rich, and Natural Language Processing\r\nworks have mainly started during last two decades, and most of the resources are first\r\ngeneration resources, and with ample scope for upgrading, enriching, and purifying.\r\n5. These are very good and essential resources for all the researchers in Assamese NLP, as\r\nthe language requires more and more NLP works to make Assamese a rich media for\r\nthe digital world.\r\n6. Anyone interested, or in need of such resources may express their interest for the\r\nrequired resources, and the way of availability will be advised/informed accordingly.\r\n7. These are purely research materials and could only be used for further research only.\r\n8. Researchers may visit the NLP Lab of Department of Information Technology, Gauhati\r\nUniversity, Guwahati, India or contact us.\r\n9. Researchers interested in collaborative works, and also students for project works, are\r\nwelcome.\r\n10. Contact person is Professor Shikhar Kr. Sarma, Department of Information\r\nTechnology, Gauhati University, Guwahati 781014, Assam, India. Email-\r\nsks@gauhati.ac.in;2019-01-15;corpus;http://hdl.handle.net/11321/621;asm;downloadable_files_count: 0;Department of Information Technology, Gauhati University, Assam, India",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "efaf940d-cd3b-5cd9-8201-3ab4d19338eb",
-    "notes": [
-        "Assamese POS tagger is a CRF++ based POS Tagger. Raw text is given to this CRF++ based POS tagger to get POS tagged data. Standard POS tagset is used.\r\n\r\n---\r\n\r\n1. These Assamese NLP resources including the Tools and Applications are developed\r\nduring Research and Development Projects as well as Masters and Ph.D. thesis\r\nworks.\r\n2. These are mainly developed or generated at Gauhati University Department of\r\nComputer Science and Department of Information Technology.\r\n3. These resources are used by students and researchers for further studies, researches, as\r\nwell as for design and development of tools and applications.\r\n4. Computational Linguistics in Assamese is not rich, and Natural Language Processing\r\nworks have mainly started during last two decades, and most of the resources are first\r\ngeneration resources, and with ample scope for upgrading, enriching, and purifying.\r\n5. These are very good and essential resources for all the researchers in Assamese NLP, as\r\nthe language requires more and more NLP works to make Assamese a rich media for\r\nthe digital world.\r\n6. Anyone interested, or in need of such resources may express their interest for the\r\nrequired resources, and the way of availability will be advised/informed accordingly.\r\n7. These are purely research materials and could only be used for further research only.\r\n8. Researchers may visit the NLP Lab of Department of Information Technology, Gauhati\r\nUniversity, Guwahati, India or contact us.\r\n9. Researchers interested in collaborative works, and also students for project works, are\r\nwelcome.\r\n10. Contact person is Professor Shikhar Kr. Sarma, Department of Information\r\nTechnology, Gauhati University, Guwahati 781014, Assam, India. Email-\r\nsks@gauhati.ac.in"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/621"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_610"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Assamese NLP"
-        },
-        {
-            "name": "Assamese POS Tagged text"
-        },
-        {
-            "name": "Assamese Part Speech tagged text"
-        },
-        {
-            "name": "Assamese CRF"
-        },
-        {
-            "name": "Gauhati University"
-        }
-    ],
-    "title": [
-        "Assamese POS-Tagged Text"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/efb1c3cd-3033-5d07-bf42-3fde93b5ed19.json b/oaitestdata/clarin-oai_dc/SET_1/json/efb1c3cd-3033-5d07-bf42-3fde93b5ed19.json
deleted file mode 100644
index af83af15..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/efb1c3cd-3033-5d07-bf42-3fde93b5ed19.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 889 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1576",
-    "MetadataAccess": [
-        "oai:ota:oucs:1576"
-    ],
-    "PublicationTimestamp": "1976-01-01T11:59:59Z",
-    "PublicationYear": [
-        "1976"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Franklin, Benjamin, 1706-1790"
-    ],
-    "fulltext": "oai:ota:oucs:1576;2018-02-16T10:42:06Z;http://ota.ox.ac.uk/headers/1576.xml;London 1757-1775;Franklin, Benjamin, 1706-1790;default: 1976-01-01;text_and_corpus_linguistics;Letters -- United States -- 18th century;eng;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 889 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "efb1c3cd-3033-5d07-bf42-3fde93b5ed19",
-    "oai_identifier": [
-        "oai:ota:oucs:1576"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Letters -- United States -- th century"
-        }
-    ],
-    "title": [
-        "London 1757-1775"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1576.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/efce315f-7fbc-5936-8791-764adfdf59b3.json b/oaitestdata/clarin-oai_dc/SET_1/json/efce315f-7fbc-5936-8791-764adfdf59b3.json
deleted file mode 100644
index 1b8b402f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/efce315f-7fbc-5936-8791-764adfdf59b3.json
+++ /dev/null
@@ -1,96 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 4",
-        "application/pdf",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1081",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1081"
-    ],
-    "PID": "http://hdl.handle.net/11356/1081",
-    "PublicationTimestamp": "2016-12-28T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11356/1085",
-        "http://hdl.handle.net/11356/1079"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by-sa/4.0/"
-    ],
-    "author": [
-        "\u010cibej, Jaka",
-        "Erjavec, Toma\u017e",
-        "Fi\u0161er, Darja",
-        "Arhar Holdt, \u0160pela"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1081;2018-10-18T22:28:20Z;hdl_11356_1023;hdl_11356_1024;CMC training corpus Janes-Tag 1.1;Erjavec, Toma\u017e;Fi\u0161er, Darja;\u010cibej, Jaka;Arhar Holdt, \u0160pela;computer-mediated communication;tokenisation;word normalisation;tagging;lemmatisation;manual annotation;TEI;Janes-Tag is a manually annotated corpus of Slovene Computer-Mediated Communication (CMC). It is meant as a gold-standard training and testing dataset for tokenisation, sentence segmentation, word normalisation, morphosyntactic tagging and lemmatisation of non-standard Slovene. As the corpus has been carefully manually annotated, it is also suitable for detailed linguistic explorations which require highly accurate and reliable annotations.\r\n\r\nThe corpus is further described in:\r\nERJAVEC, Toma\u017e, \u010cIBEJ, Jaka, ARHAR HOLDT, \u0160pela, LJUBE\u0160I\u0106, Nikola, FI\u0160ER, Darja. Gold-standard datasets for annotation of Slovene computer-mediated communication. In Proceedings of RASLAN 2016: Recent Advances in Slavonic Natural Language Processing. Brno: Tribun EU, 2016, pp. 29-40, https://nlp.fi.muni.cz/raslan/raslan16.pdf\r\n\r\nNote that a related corpus, Janes-Norm is also available, cf. http://hdl.handle.net/11356/1083.;2016-12-28;corpus;http://hdl.handle.net/11356/1081;slv;http://hdl.handle.net/11356/1085;http://hdl.handle.net/11356/1079;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);PUB;https://creativecommons.org/licenses/by-sa/4.0/;application/pdf;application/pdf;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 4;Jo\u017eef Stefan Institute;http://nl.ijs.si/janes/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "efce315f-7fbc-5936-8791-764adfdf59b3",
-    "notes": [
-        "Janes-Tag is a manually annotated corpus of Slovene Computer-Mediated Communication (CMC). It is meant as a gold-standard training and testing dataset for tokenisation, sentence segmentation, word normalisation, morphosyntactic tagging and lemmatisation of non-standard Slovene. As the corpus has been carefully manually annotated, it is also suitable for detailed linguistic explorations which require highly accurate and reliable annotations.\r\n\r\nThe corpus is further described in:\r\nERJAVEC, Toma\u017e, \u010cIBEJ, Jaka, ARHAR HOLDT, \u0160pela, LJUBE\u0160I\u0106, Nikola, FI\u0160ER, Darja. Gold-standard datasets for annotation of Slovene computer-mediated communication. In Proceedings of RASLAN 2016: Recent Advances in Slavonic Natural Language Processing. Brno: Tribun EU, 2016, pp. 29-40, https://nlp.fi.muni.cz/raslan/raslan16.pdf\r\n\r\nNote that a related corpus, Janes-Norm is also available, cf. http://hdl.handle.net/11356/1083."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1081"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "computer-mediated communication"
-        },
-        {
-            "name": "tokenisation"
-        },
-        {
-            "name": "word normalisation"
-        },
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "lemmatisation"
-        },
-        {
-            "name": "manual annotation"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "CMC training corpus Janes-Tag 1.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/efd59ee2-0f3a-5612-80a1-d47694a761f5.json b/oaitestdata/clarin-oai_dc/SET_1/json/efd59ee2-0f3a-5612-80a1-d47694a761f5.json
deleted file mode 100644
index 405fef1b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/efd59ee2-0f3a-5612-80a1-d47694a761f5.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5507",
-    "MetadataAccess": [
-        "oai:ota:oucs:5507"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Parnell, Thomas, 1679-1718."
-    ],
-    "fulltext": "oai:ota:oucs:5507;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5507.xml;The hermit. A poem;Parnell, Thomas, 1679-1718.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "efd59ee2-0f3a-5612-80a1-d47694a761f5",
-    "oai_identifier": [
-        "oai:ota:oucs:5507"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The hermit. A poem"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5507.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/efda26ca-324b-56d7-b3be-7e3911dbcce5.json b/oaitestdata/clarin-oai_dc/SET_1/json/efda26ca-324b-56d7-b3be-7e3911dbcce5.json
deleted file mode 100644
index 4e4778b6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/efda26ca-324b-56d7-b3be-7e3911dbcce5.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "Contributor": [
-        "Freixa, Judit"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Catalan",
-        "French",
-        "Galician",
-        "Italian",
-        "Portuguese",
-        "Romanian",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1111",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1111"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1111",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1111;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Neologismos econ\u00f3micos en las lenguas rom\u00e1nicas a trav\u00e9s de la prensa;Freixa, Judit;terminology database;Multilingual terminological resource containing 3.875 entries from the Economics, Finance and Banking domains.;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1111;cat;fra;glg;ita;por;ron;spa;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra;http://obneo.iula.upf.edu/economia/esp/frames.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "efda26ca-324b-56d7-b3be-7e3911dbcce5",
-    "notes": [
-        "Multilingual terminological resource containing 3.875 entries from the Economics, Finance and Banking domains."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1111"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "terminology database"
-        }
-    ],
-    "title": [
-        "Neologismos econ\u00f3micos en las lenguas rom\u00e1nicas a trav\u00e9s de la prensa"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/efe915bc-029a-5c45-9819-11b47f83001d.json b/oaitestdata/clarin-oai_dc/SET_1/json/efe915bc-029a-5c45-9819-11b47f83001d.json
deleted file mode 100644
index f2549d8e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/efe915bc-029a-5c45-9819-11b47f83001d.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "Contributor": [
-        "Woli\u0144ski, Marcin",
-        "Badowski, Tomasz",
-        "Pawlik, Dominika",
-        "Achinger, Piotr",
-        "So\u0142tys, Karolina"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1184",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1184"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1184",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Poland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1184;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Dendrarium;Woli\u0144ski, Marcin;Pawlik, Dominika;So\u0142tys, Karolina;Achinger, Piotr;Badowski, Tomasz;Coordinates work of a group of linguists selecting appropriate parse trees from many generated ones. Assigns parts of the task, signalling differences in annotation and allowing them to be corrected by a supervisor.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1184;downloadable_files_count: 0;Poland;Institute of Computer Science, Polish Academy of Sciences;http://sourceforge.net/projects/dendrarium/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "efe915bc-029a-5c45-9819-11b47f83001d",
-    "notes": [
-        "Coordinates work of a group of linguists selecting appropriate parse trees from many generated ones. Assigns parts of the task, signalling differences in annotation and allowing them to be corrected by a supervisor."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1184"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Dendrarium"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/eff864bd-4a2f-5fd7-baa7-15c2217ec3ef.json b/oaitestdata/clarin-oai_dc/SET_1/json/eff864bd-4a2f-5fd7-baa7-15c2217ec3ef.json
deleted file mode 100644
index ca9460ad..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/eff864bd-4a2f-5fd7-baa7-15c2217ec3ef.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Akademicka"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-121734",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-121734"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CD9-E",
-    "PublicationTimestamp": "1637-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1637"
-    ],
-    "Publisher": [
-        "Drukarnia Akademicka"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/121734",
-        "oai:jbc.bj.uj.edu.pl:publication:129465"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1601/1700"
-    ],
-    "TempCoverageBegin": 50506804799,
-    "TempCoverageEnd": 50506804799,
-    "TemporalCoverage": " point in time : 1601-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1601-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1601-07-01T11:59:59Z",
-    "author": [
-        "Gi\u017cycki, Stefan ( -1644)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-121734;2019-02-28T18:05:14Z;Alchimia W Raiv Przesadzona Z Zyw\u0105 Y Vmar\u0142\u0105 Smierci\u0105 Przed Bramami Pierwszego Y Ostatniego Dni, Jego Mo\u015bci P. Stephana Jacynicza S\u0142onimskiego Powiatv Marsza\u0142ka. : Na pogrzebie Roku 1637. Dnia 3. Februarij [...] wyprawiona;Gi\u017cycki, Stefan ( -1644);starodruki 17\u00a0w.;Piasecki, Piotr (15..-16..). Adr. ded.;Drukarnia Akademicka;1637;starodruk;application/xml;clarind-uds:poldilemma-121734;hdl:11858/00-246C-0000-0023-8CD9-E;Biblioteka Jagiello\u0144ska, BJ St. Dr. 25499 I;pol;lat;http://jbc.bj.uj.edu.pl/Content/121734;oai:jbc.bj.uj.edu.pl:publication:129465;1601/1700;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "eff864bd-4a2f-5fd7-baa7-15c2217ec3ef",
-    "notes": [
-        "Piasecki, Piotr (15..-16..). Adr. ded."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-121734"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Alchimia W Raiv Przesadzona Z Zyw\u0105 Y Vmar\u0142\u0105 Smierci\u0105 Przed Bramami Pierwszego Y Ostatniego Dni, Jego Mo\u015bci P. Stephana Jacynicza S\u0142onimskiego Powiatv Marsza\u0142ka. : Na pogrzebie Roku 1637. Dnia 3. Februarij [...] wyprawiona"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f05901fd-fda5-555e-9875-a59d838b39f6.json b/oaitestdata/clarin-oai_dc/SET_1/json/f05901fd-fda5-555e-9875-a59d838b39f6.json
deleted file mode 100644
index f290e481..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f05901fd-fda5-555e-9875-a59d838b39f6.json
+++ /dev/null
@@ -1,96 +0,0 @@
-{
-    "Contact": [
-        "Universit\u00e4t des Saarlandes"
-    ],
-    "Contributor": [
-        "Prof. Erich Steiner",
-        "Silvia Hansen-Schirra",
-        "Kerstin Kunz",
-        "Mihaela Vela",
-        "Oliver \u010culo",
-        "Stella Neumann"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/xml"
-    ],
-    "Language": [
-        "German",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:croco",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:croco"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0005-BD0E-F",
-    "PublicationTimestamp": "2006-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2006"
-    ],
-    "Publisher": [
-        "Universit\u00e4t des Saarlandes"
-    ],
-    "RelatedIdentifier": [
-        "Hansen-Schirra, Silvia, Neumann, Stella and Steiner, Erich. 2012. Cross-linguistic Corpora for the Study of Translations. Insights from the language pair English -- German. Series Text, Translation, Computational Processing. Berlin, New York: Mouton de Gruyter",
-        "CroCo-Meta is an user-friendly annotation tool to edit and storage meta information for a file header. http://fedora.clarin-d.uni-saarland.de/croco-gecco/croco/CroCoMeta_en.html",
-        "Deliverable No. 1 \"Corpus Design\": http://hdl.handle.net/21.11119/0000-0000-8138-F",
-        "Deliverable No. 2 \"Encoding of Metainformation\": http://hdl.handle.net/21.11119/0000-0000-8148-D",
-        "Deliverable No. 3 \"Multidimensional Corpus Alignment\": http://hdl.handle.net/21.11119/0000-0000-814E-7",
-        "Deliverable No. 4 \"Categories for the Annotation\": http://hdl.handle.net/21.11119/0000-0000-8159-A",
-        "Deliverable No. 5 \"Types of contrasts, linguistic levels, their relationship to explicitation and explicitness, and possible explanations\": http://hdl.handle.net/21.11119/0000-0000-815F-4",
-        "Publications: http://fedora.clarin-d.uni-saarland.de/croco-gecco/croco/publication_en.html"
-    ],
-    "ResourceType": [
-        "Collection"
-    ],
-    "Rights": [
-        "Copyrighted"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Universit\u00e4t des Saarlandes Fachrichtung 4.6 Englische Sprach- und \u00dcbersetzungswissenschaft"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:croco;2018-02-01T15:24:37Z;CroCo;Universit\u00e4t des Saarlandes Fachrichtung 4.6 Englische Sprach- und \u00dcbersetzungswissenschaft;corpus linguistics;linguistics;translation;explicitation;The CroCo corpus is a bidirectional corpus of German (GO) and English (EO) texts from 8 registers (popular-scientific texts, tourism leaflets, prepared speeches, political essays on economics, fictional texts, corporate communication, instruction manuals, websites) with the respective English (ETrans) and German (GTrans) translation.\nThus we have: multilingual comparable subcorpora (EO and GO, ETrans and GTrans), monolingual comparable subcorpora (EO and ETrans, GO and GTrans) and parallel subcorpora (EO and GTrans, GO and ETrans).\nThe corpus is annotated with lemma, POS, morphological information, phrasal chunks and grammatical functions. The parallel corpora are aligned on different levels: word, chunk, clause and sentence.;Das CroCo-Korpus ist ein bidirektionales Korpus bestehend aus deutschen (GO) und englischen (EO) Texten aus 8 Registern (popul\u00e4rwissenschaftliche Texte, Tourismus-Flyer, Reden, politische Essays \u00fcber Wirtschaft, fiktionale Texte, Firmenkommunikation, Handb\u00fccher, Webseiten) mit den jeweiligen Englischen (ETrans) und Deutschen (GTrans) \u00dcbersetzungen.\nDemnach gibt es multilinguale vergleichbare Subkorpora (EO und GO, ETrans und GTrans), monolinguale vergleichbare Subkorpora (EO und ETrans, GO und GTrans) und parallele Subkorpora (EO und GTrans, GO und ETrans).\nDas Korpus ist mit Lemma, POS, morphologischer Information, phrasalen Chunks und grammatischen Funktionen annotiert. Die parallelen Subkorpora sind auf verschiedenen Ebenen alligniert: Wort, Chunk, Clause, Satz.;Universit\u00e4t des Saarlandes;Oliver \u010culo;Silvia Hansen-Schirra;Kerstin Kunz;Stella Neumann;Prof. Erich Steiner;Mihaela Vela;2006;Collection;text/xml;clarind-uds:croco;hdl:11858/00-246C-0000-0005-BD0E-F;deu;eng;Hansen-Schirra, Silvia, Neumann, Stella and Steiner, Erich. 2012. Cross-linguistic Corpora for the Study of Translations. Insights from the language pair English -- German. Series Text, Translation, Computational Processing. Berlin, New York: Mouton de Gruyter;CroCo-Meta is an user-friendly annotation tool to edit and storage meta information for a file header. http://fedora.clarin-d.uni-saarland.de/croco-gecco/croco/CroCoMeta_en.html;Deliverable No. 1 \"Corpus Design\": http://hdl.handle.net/21.11119/0000-0000-8138-F;Deliverable No. 2 \"Encoding of Metainformation\": http://hdl.handle.net/21.11119/0000-0000-8148-D;Deliverable No. 3 \"Multidimensional Corpus Alignment\": http://hdl.handle.net/21.11119/0000-0000-814E-7;Deliverable No. 4 \"Categories for the Annotation\": http://hdl.handle.net/21.11119/0000-0000-8159-A;Deliverable No. 5 \"Types of contrasts, linguistic levels, their relationship to explicitation and explicitness, and possible explanations\": http://hdl.handle.net/21.11119/0000-0000-815F-4;Publications: http://fedora.clarin-d.uni-saarland.de/croco-gecco/croco/publication_en.html;Germany;Copyrighted",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f05901fd-fda5-555e-9875-a59d838b39f6",
-    "notes": [
-        "The CroCo corpus is a bidirectional corpus of German (GO) and English (EO) texts from 8 registers (popular-scientific texts, tourism leaflets, prepared speeches, political essays on economics, fictional texts, corporate communication, instruction manuals, websites) with the respective English (ETrans) and German (GTrans) translation.\nThus we have: multilingual comparable subcorpora (EO and GO, ETrans and GTrans), monolingual comparable subcorpora (EO and ETrans, GO and GTrans) and parallel subcorpora (EO and GTrans, GO and ETrans).\nThe corpus is annotated with lemma, POS, morphological information, phrasal chunks and grammatical functions. The parallel corpora are aligned on different levels: word, chunk, clause and sentence.",
-        "Das CroCo-Korpus ist ein bidirektionales Korpus bestehend aus deutschen (GO) und englischen (EO) Texten aus 8 Registern (popul\u00e4rwissenschaftliche Texte, Tourismus-Flyer, Reden, politische Essays \u00fcber Wirtschaft, fiktionale Texte, Firmenkommunikation, Handb\u00fccher, Webseiten) mit den jeweiligen Englischen (ETrans) und Deutschen (GTrans) \u00dcbersetzungen.\nDemnach gibt es multilinguale vergleichbare Subkorpora (EO und GO, ETrans und GTrans), monolinguale vergleichbare Subkorpora (EO und ETrans, GO und GTrans) und parallele Subkorpora (EO und GTrans, GO und ETrans).\nDas Korpus ist mit Lemma, POS, morphologischer Information, phrasalen Chunks und grammatischen Funktionen annotiert. Die parallelen Subkorpora sind auf verschiedenen Ebenen alligniert: Wort, Chunk, Clause, Satz."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:croco"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus linguistics"
-        },
-        {
-            "name": "linguistics"
-        },
-        {
-            "name": "translation"
-        },
-        {
-            "name": "explicitation"
-        }
-    ],
-    "title": [
-        "CroCo"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f05b92cb-f361-5d5e-ad3f-98775c50c44d.json b/oaitestdata/clarin-oai_dc/SET_1/json/f05b92cb-f361-5d5e-ad3f-98775c50c44d.json
deleted file mode 100644
index 5fa318ef..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f05b92cb-f361-5d5e-ad3f-98775c50c44d.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Centro de Tecnolog\u00edas y Aplicaciones del Lenguaje y del Habla (TALP)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Basque",
-        "Catalan",
-        "English",
-        "Galician",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1094",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1094"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1094",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Centro de Tecnolog\u00edas y Aplicaciones del Lenguaje y del Habla (TALP)"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1094;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Multilingual Central Repository;lexical database;Multilingual lexical database that follows the model proposed by the EuroWordNet project.  The MCR integrates into the same EuroWordNet framework wordnets from five different languages (together with four English WordNet versions). It also integrates WordNet Domains and new versions of the Base Concepts and Top Concept Ontology.  Overall, it contains 1,642,389 semantic relations between synsets, most of them acquired by automatic means.  Information contained: semantics, synonyms, antonyms, definition, equivalents, example of use, morphology.;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1094;eus;cat;eng;glg;spa;downloadable_files_count: 0;Spain;Centro de Tecnolog\u00edas y Aplicaciones del Lenguaje y del Habla (TALP);http://nlp.lsi.upc.edu/web/index.php?option=com_content&task=view&id=53",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f05b92cb-f361-5d5e-ad3f-98775c50c44d",
-    "notes": [
-        "Multilingual lexical database that follows the model proposed by the EuroWordNet project.  The MCR integrates into the same EuroWordNet framework wordnets from five different languages (together with four English WordNet versions). It also integrates WordNet Domains and new versions of the Base Concepts and Top Concept Ontology.  Overall, it contains 1,642,389 semantic relations between synsets, most of them acquired by automatic means.  Information contained: semantics, synonyms, antonyms, definition, equivalents, example of use, morphology."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1094"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "lexical database"
-        }
-    ],
-    "title": [
-        "Multilingual Central Repository"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f0c55b35-dbd1-55e4-a6be-952d3c5e0512.json b/oaitestdata/clarin-oai_dc/SET_1/json/f0c55b35-dbd1-55e4-a6be-952d3c5e0512.json
deleted file mode 100644
index eb238c24..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f0c55b35-dbd1-55e4-a6be-952d3c5e0512.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/12",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/12"
-    ],
-    "PID": "http://hdl.handle.net/10794/12",
-    "PublicationTimestamp": "2015-12-09T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/12;2017-10-27T16:01:40Z;hdl_10794_1;hdl_10794_2;Academic wordlist (2017-10-16);Akademisk ordlista (2017-10-16);n/a, n/a;Swedish;Academic;Academic wordlist.;Akademisk ordlista.;2015-12-09;lexicalConceptualResource;http://hdl.handle.net/10794/12;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/ao",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f0c55b35-dbd1-55e4-a6be-952d3c5e0512",
-    "notes": [
-        "Academic wordlist.",
-        "Akademisk ordlista."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/12"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Academic"
-        }
-    ],
-    "title": [
-        "Academic wordlist (2017-10-16)",
-        "Akademisk ordlista (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f0cb5a74-3e5e-5b07-a396-cc2b64bfb94a.json b/oaitestdata/clarin-oai_dc/SET_1/json/f0cb5a74-3e5e-5b07-a396-cc2b64bfb94a.json
deleted file mode 100644
index 141b8579..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f0cb5a74-3e5e-5b07-a396-cc2b64bfb94a.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Andersen, Gisle"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-368",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-368"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-368",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Norway"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-368;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;COLT \u2013 The Bergen Corpus of London Teenage Language;Andersen, Gisle;British English (London); Spoken, general, age-specific dialect corpus; 500 000 words, 55 hrs of recording; POS, speaker/conversation metainfo;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-368;eng;downloadable_files_count: 0;Norway;http://torvald.aksis.uib.no/colt/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f0cb5a74-3e5e-5b07-a396-cc2b64bfb94a",
-    "notes": [
-        "British English (London); Spoken, general, age-specific dialect corpus; 500 000 words, 55 hrs of recording; POS, speaker/conversation metainfo"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-368"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "COLT \u2013 The Bergen Corpus of London Teenage Language"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f0cfc452-dc8c-5aa7-baab-accbeb4f80e4.json b/oaitestdata/clarin-oai_dc/SET_1/json/f0cfc452-dc8c-5aa7-baab-accbeb4f80e4.json
deleted file mode 100644
index b87e0bd0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f0cfc452-dc8c-5aa7-baab-accbeb4f80e4.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Masaryk University, NLP Centre"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/xml",
-        "downloadable_files_count: 4",
-        "text/plain",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Russian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-CCCE-E",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-CCCE-E"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-CCCE-E",
-    "PublicationTimestamp": "2011-12-15T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Masaryk University, NLP Centre"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Rambousek, Adam"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-CCCE-E;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Integrated lexicographic platform for Russian;Rambousek, Adam;lexicography platform;russian;web dictionary;Integrated lexicographic platform for Russian.;2011-12-15;toolService;http://hdl.handle.net/11858/00-097C-0000-0001-CCCE-E;rus;Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0);http://creativecommons.org/licenses/by-nc-nd/3.0/;PUB;application/octet-stream;application/octet-stream;text/xml;text/plain;text/plain; charset=utf-8;downloadable_files_count: 4;Masaryk University, NLP Centre",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f0cfc452-dc8c-5aa7-baab-accbeb4f80e4",
-    "notes": [
-        "Integrated lexicographic platform for Russian."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-CCCE-E"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "lexicography platform"
-        },
-        {
-            "name": "russian"
-        },
-        {
-            "name": "web dictionary"
-        }
-    ],
-    "title": [
-        "Integrated lexicographic platform for Russian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f0df9706-aa7f-5fbe-999f-16af33cc8d6f.json b/oaitestdata/clarin-oai_dc/SET_1/json/f0df9706-aa7f-5fbe-999f-16af33cc8d6f.json
deleted file mode 100644
index 79c6c121..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f0df9706-aa7f-5fbe-999f-16af33cc8d6f.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Jakopin, Primoz"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-418",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-418"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-418",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Slovenia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-418;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Nova beseda;Jakopin, Primoz;written/spoken (formal speech)/monolingual/general/monitor corpus; 162 mil. words; XML-compatible, to sentence level;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-418;slv;downloadable_files_count: 0;Slovenia;http://bos.zrc-sazu.si/a_beseda.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f0df9706-aa7f-5fbe-999f-16af33cc8d6f",
-    "notes": [
-        "written/spoken (formal speech)/monolingual/general/monitor corpus; 162 mil. words; XML-compatible, to sentence level"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-418"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Nova beseda"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f100c41d-4b8a-54de-9fb3-900f132061d3.json b/oaitestdata/clarin-oai_dc/SET_1/json/f100c41d-4b8a-54de-9fb3-900f132061d3.json
deleted file mode 100644
index cbb473e0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f100c41d-4b8a-54de-9fb3-900f132061d3.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=9729e1dabc8811e1a404080027e73ea2bfa28a7f771f4cb6a5fb901e346734a2",
-    "MetadataAccess": [
-        "9729e1dabc8811e1a404080027e73ea2bfa28a7f771f4cb6a5fb901e346734a2"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "9729e1dabc8811e1a404080027e73ea2bfa28a7f771f4cb6a5fb901e346734a2;2018-11-15T16:39:40Z;languageDescription;languageDescription:other;U-Compare Type system;The resource constitues of a hierarchically-structured system of data types, which is intended to be suitable for describing the inputs and output annotation types of a wide range of natural language processing applications which operate within the UIMA Framework. It is being developed in conjunction with the U-Compare Workbench, but can be used as the base type system for other UIMA components and workflows, to help to ensure greater interoperability. ;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f100c41d-4b8a-54de-9fb3-900f132061d3",
-    "notes": [
-        "The resource constitues of a hierarchically-structured system of data types, which is intended to be suitable for describing the inputs and output annotation types of a wide range of natural language processing applications which operate within the UIMA Framework. It is being developed in conjunction with the U-Compare Workbench, but can be used as the base type system for other UIMA components and workflows, to help to ensure greater interoperability. "
-    ],
-    "oai_identifier": [
-        "9729e1dabc8811e1a404080027e73ea2bfa28a7f771f4cb6a5fb901e346734a2"
-    ],
-    "oai_set": [
-        "languageDescription",
-        "languageDescription:other"
-    ],
-    "state": "active",
-    "title": [
-        "U-Compare Type system"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f104e1e6-26fa-50ee-ba97-8ceb93e0cfab.json b/oaitestdata/clarin-oai_dc/SET_1/json/f104e1e6-26fa-50ee-ba97-8ceb93e0cfab.json
deleted file mode 100644
index e0385471..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f104e1e6-26fa-50ee-ba97-8ceb93e0cfab.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3412",
-    "MetadataAccess": [
-        "oai:ota:oucs:3412"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hoare, Prince, 1755-1834."
-    ],
-    "fulltext": "oai:ota:oucs:3412;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3412.xml;The prize: or, 2, 5, 3, 8, a musical farce in two acts, as performed by His Majesty's company. Written by Prince Hoare, Esq. The music by Storace. Correctly taken from the manager's book.;Hoare, Prince, 1755-1834.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f104e1e6-26fa-50ee-ba97-8ceb93e0cfab",
-    "oai_identifier": [
-        "oai:ota:oucs:3412"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The prize: or, 2, 5, 3, 8, a musical farce in two acts, as performed by His Majesty's company. Written by Prince Hoare, Esq. The music by Storace. Correctly taken from the manager's book."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3412.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f11b60fb-939c-5a71-98db-325b7d3d36c8.json b/oaitestdata/clarin-oai_dc/SET_1/json/f11b60fb-939c-5a71-98db-325b7d3d36c8.json
deleted file mode 100644
index 0c59cb32..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f11b60fb-939c-5a71-98db-325b7d3d36c8.json
+++ /dev/null
@@ -1,90 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 4",
-        "application/pdf",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1154",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1154"
-    ],
-    "PID": "http://hdl.handle.net/11356/1154",
-    "PublicationTimestamp": "2017-10-13T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "http://nl.ijs.si/janes/wp-content/uploads/2017/09/Magistrsko-delo_%C5%A0pela-Reher_final.pdf",
-        "http://nl.ijs.si/janes/viri/rocno-oznaceni-korpusi/#Janes-Preklop",
-        "https://doi.org/10.1007/s10579-018-9425-z"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "https://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Reher, \u0160pela",
-        "Erjavec, Toma\u017e",
-        "Fi\u0161er, Darja"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1154;2018-12-04T16:11:02Z;hdl_11356_1023;hdl_11356_1024;Tweet code-switching corpus Janes-Preklop 1.0;Reher, \u0160pela;Erjavec, Toma\u017e;Fi\u0161er, Darja;computer-mediated communication;Twitter;code-switching;TEI;manual annotation;Janes-Preklop is a corpus of Slovene tweets that is manually annotated for code-switching (the use of words from two or more languages within one sentence or utterance), according to the supplied typology. Words in the corpus are also automatically tagged with MSDs and lemmas.;2017-10-13;corpus;http://hdl.handle.net/11356/1154;slv;http://nl.ijs.si/janes/wp-content/uploads/2017/09/Magistrsko-delo_%C5%A0pela-Reher_final.pdf;http://nl.ijs.si/janes/viri/rocno-oznaceni-korpusi/#Janes-Preklop;https://doi.org/10.1007/s10579-018-9425-z;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);https://creativecommons.org/licenses/by-sa/4.0/;PUB;application/pdf;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 4;Jo\u017eef Stefan Institute;http://nl.ijs.si/janes/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f11b60fb-939c-5a71-98db-325b7d3d36c8",
-    "notes": [
-        "Janes-Preklop is a corpus of Slovene tweets that is manually annotated for code-switching (the use of words from two or more languages within one sentence or utterance), according to the supplied typology. Words in the corpus are also automatically tagged with MSDs and lemmas."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1154"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "computer-mediated communication"
-        },
-        {
-            "name": "Twitter"
-        },
-        {
-            "name": "code-switching"
-        },
-        {
-            "name": "TEI"
-        },
-        {
-            "name": "manual annotation"
-        }
-    ],
-    "title": [
-        "Tweet code-switching corpus Janes-Preklop 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f11f5f1a-fdb4-5e37-9dd4-d610f91f6fc3.json b/oaitestdata/clarin-oai_dc/SET_1/json/f11f5f1a-fdb4-5e37-9dd4-d610f91f6fc3.json
deleted file mode 100644
index c92437bd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f11f5f1a-fdb4-5e37-9dd4-d610f91f6fc3.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/5-UDPIPE-PARSER",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/5-UDPIPE-PARSER"
-    ],
-    "PID": "http://hdl.handle.net/11234/5-UDPIPE-PARSER",
-    "PublicationTimestamp": "2016-02-08T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Straka, Milan"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/5-UDPIPE-PARSER;2019-01-02T13:47:41Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0023-8C33-2;UDPipe parser Web Service for Weblicht;Straka, Milan;udpipe;UDPipe is a trainable pipeline for tokenizing, tagging, lemmatizing and parsing Universal Treebanks and other CoNLL-U files (https://lindat.mff.cuni.cz/services/udpipe/);2016-02-08;toolService;http://hdl.handle.net/11234/5-UDPIPE-PARSER;application/octet-stream;downloadable_files_count: 0;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://hdl.handle.net/11234/5-UDPIPE-PARSER",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f11f5f1a-fdb4-5e37-9dd4-d610f91f6fc3",
-    "notes": [
-        "UDPipe is a trainable pipeline for tokenizing, tagging, lemmatizing and parsing Universal Treebanks and other CoNLL-U files (https://lindat.mff.cuni.cz/services/udpipe/)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/5-UDPIPE-PARSER"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0023-8C33-2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "udpipe"
-        }
-    ],
-    "title": [
-        "UDPipe parser Web Service for Weblicht"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f12dfb52-3ada-5857-9462-b96f62d171da.json b/oaitestdata/clarin-oai_dc/SET_1/json/f12dfb52-3ada-5857-9462-b96f62d171da.json
deleted file mode 100644
index 30bed65d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f12dfb52-3ada-5857-9462-b96f62d171da.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Italian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-63",
-    "MetadataAccess": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-63"
-    ],
-    "PID": "http://hdl.handle.net/20.500.11752/ILC-63",
-    "PublicationTimestamp": "2016-09-21T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Maria Maddalena, Lombardi"
-    ],
-    "fulltext": "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-63;2018-07-23T09:13:44Z;hdl_000-c0-111_38;hdl_000-c0-111_49;Vittorio Alfieri's tragedies;Maria Maddalena, Lombardi;Alfieri Lexicon;Drama;Philosophy;Mythology;Texts of Vittorio Alfieri  were provided partly by the Accademia della Crusca and partly of the University of Pavia, Department of Science and Literature of Medieval and Modern Art. The tragedies listed below refer to the edition edited by Giovanna Zuradelli, Torino, UTET, 1978:\r\nAgamennone\r\nAntigone\r\nLa Congiura de' pazzi\r\nMerope\r\nMaria Stuarda\r\nOreste\r\nPolinice\r\nVirginia\r\nFilippo\r\nAgide \r\nBruto I\r\nBruto II\r\nDon Garzia\r\nMirra\r\nOttavia\r\nRosmunda\r\nSaul\r\nSofonisba\r\nTimoleone;2016-09-21;toolService;http://hdl.handle.net/20.500.11752/ILC-63;ita;downloadable_files_count: 0;Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f12dfb52-3ada-5857-9462-b96f62d171da",
-    "notes": [
-        "Texts of Vittorio Alfieri  were provided partly by the Accademia della Crusca and partly of the University of Pavia, Department of Science and Literature of Medieval and Modern Art. The tragedies listed below refer to the edition edited by Giovanna Zuradelli, Torino, UTET, 1978:\r\nAgamennone\r\nAntigone\r\nLa Congiura de' pazzi\r\nMerope\r\nMaria Stuarda\r\nOreste\r\nPolinice\r\nVirginia\r\nFilippo\r\nAgide \r\nBruto I\r\nBruto II\r\nDon Garzia\r\nMirra\r\nOttavia\r\nRosmunda\r\nSaul\r\nSofonisba\r\nTimoleone"
-    ],
-    "oai_identifier": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-63"
-    ],
-    "oai_set": [
-        "hdl_000-c0-111_38",
-        "hdl_000-c0-111_49"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Alfieri Lexicon"
-        },
-        {
-            "name": "Drama"
-        },
-        {
-            "name": "Philosophy"
-        },
-        {
-            "name": "Mythology"
-        }
-    ],
-    "title": [
-        "Vittorio Alfieri's tragedies"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f143dce2-0e08-5307-b5df-80c3d4d174c5.json b/oaitestdata/clarin-oai_dc/SET_1/json/f143dce2-0e08-5307-b5df-80c3d4d174c5.json
deleted file mode 100644
index 0fc5ee41..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f143dce2-0e08-5307-b5df-80c3d4d174c5.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4525",
-    "MetadataAccess": [
-        "oai:ota:oucs:4525"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Defoe, Daniel, 1661?-1731."
-    ],
-    "fulltext": "oai:ota:oucs:4525;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4525.xml;An essay upon publick credit: being an enquiry how the publick credit comes to depend upon the change of the ministry, or the dissolutions of Parliaments; and whether it does so or no. ...;Defoe, Daniel, 1661?-1731.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f143dce2-0e08-5307-b5df-80c3d4d174c5",
-    "oai_identifier": [
-        "oai:ota:oucs:4525"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An essay upon publick credit: being an enquiry how the publick credit comes to depend upon the change of the ministry, or the dissolutions of Parliaments; and whether it does so or no. ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4525.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f159bf8d-a1d9-58f8-bc1d-8468a6bab892.json b/oaitestdata/clarin-oai_dc/SET_1/json/f159bf8d-a1d9-58f8-bc1d-8468a6bab892.json
deleted file mode 100644
index 75ad2e83..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f159bf8d-a1d9-58f8-bc1d-8468a6bab892.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-1B04-C",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-1B04-C"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-1B04-C",
-    "PublicationTimestamp": "2014-01-09T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11858/00-097C-0000-0022-C73C-7"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u017dabokrtsk\u00fd, Zden\u011bk",
-        "Straka, Milan",
-        "Strakov\u00e1, Jana",
-        "\u0160ev\u010d\u00edkov\u00e1, Magda"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-1B04-C;2018-07-02T22:05:53Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Czech Named Entity Corpus 1.1;\u0160ev\u010d\u00edkov\u00e1, Magda;\u017dabokrtsk\u00fd, Zden\u011bk;Strakov\u00e1, Jana;Straka, Milan;named entity recognition;corpus;Czech Named Entity Corpus 1.1 fixes some issues of the Czech Named Entity Corpus 1.0: misannotated entities are fixed, all formats contain the same data, tmt format is replaced with treex format, all formats contain splitting into training, development and testing portion of the data.;2014-01-09;corpus;http://hdl.handle.net/11858/00-097C-0000-0023-1B04-C;ces;http://hdl.handle.net/11858/00-097C-0000-0022-C73C-7;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/cnec/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f159bf8d-a1d9-58f8-bc1d-8468a6bab892",
-    "notes": [
-        "Czech Named Entity Corpus 1.1 fixes some issues of the Czech Named Entity Corpus 1.0: misannotated entities are fixed, all formats contain the same data, tmt format is replaced with treex format, all formats contain splitting into training, development and testing portion of the data."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-1B04-C"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "named entity recognition"
-        },
-        {
-            "name": "corpus"
-        }
-    ],
-    "title": [
-        "Czech Named Entity Corpus 1.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f17bfdbd-d137-56f7-b28f-5ee225479970.json b/oaitestdata/clarin-oai_dc/SET_1/json/f17bfdbd-d137-56f7-b28f-5ee225479970.json
deleted file mode 100644
index 1e5716e7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f17bfdbd-d137-56f7-b28f-5ee225479970.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 462 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2009",
-    "MetadataAccess": [
-        "oai:ota:oucs:2009"
-    ],
-    "PublicationTimestamp": "1863-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1863"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Bulfinch, Thomas, 1796-1867"
-    ],
-    "fulltext": "oai:ota:oucs:2009;2018-03-01T11:33:23Z;http://ota.ox.ac.uk/headers/2009.xml;Bulfinch's Mythology: legends of Charlemagne, or, Romance of the middle ages ;Bulfinch, Thomas, 1796-1867;1863;text_and_corpus_linguistics;Romances -- United States -- 19th century;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 462 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f17bfdbd-d137-56f7-b28f-5ee225479970",
-    "oai_identifier": [
-        "oai:ota:oucs:2009"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Romances -- United States -- th century"
-        }
-    ],
-    "title": [
-        "Bulfinch's Mythology: legends of Charlemagne, or, Romance of the middle ages "
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2009.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f182a307-7f01-5ce7-9720-745bb8f63ea4.json b/oaitestdata/clarin-oai_dc/SET_1/json/f182a307-7f01-5ce7-9720-745bb8f63ea4.json
deleted file mode 100644
index d1b8002f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f182a307-7f01-5ce7-9720-745bb8f63ea4.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra",
-        "Instituto Cervantes"
-    ],
-    "Contributor": [
-        "secretaria, Iula"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Catalan"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1115",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1115"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1115",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra",
-        "Instituto Cervantes"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1115;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Banco de neologismos 2004-2007;secretaria, Iula;neologisms database;Repository of neologisms (15.375 entries);2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1115;cat;downloadable_files_count: 0;Spain;Instituto Cervantes;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra;http://cvc.cervantes.es/obref/banco_neologismos/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f182a307-7f01-5ce7-9720-745bb8f63ea4",
-    "notes": [
-        "Repository of neologisms (15.375 entries)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1115"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "neologisms database"
-        }
-    ],
-    "title": [
-        "Banco de neologismos 2004-2007"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f1ab1882-ceef-5b85-b95f-09190ab5390c.json b/oaitestdata/clarin-oai_dc/SET_1/json/f1ab1882-ceef-5b85-b95f-09190ab5390c.json
deleted file mode 100644
index 059b354a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f1ab1882-ceef-5b85-b95f-09190ab5390c.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "2 MB"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1035",
-    "MetadataAccess": [
-        "oai:ota:oucs:1035"
-    ],
-    "PublicationTimestamp": "1984-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1984"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Emeny, R. and H.M. Wilks"
-    ],
-    "fulltext": "oai:ota:oucs:1035;2018-03-05T10:37:10Z;http://ota.ox.ac.uk/headers/1035.xml;Principles and practice of rating valuations;Emeny, R. and H.M. Wilks;1984;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;2 MB;Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f1ab1882-ceef-5b85-b95f-09190ab5390c",
-    "oai_identifier": [
-        "oai:ota:oucs:1035"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Principles and practice of rating valuations"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1035.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f1b3fa26-e813-552b-a0f6-dd77f9d9b40e.json b/oaitestdata/clarin-oai_dc/SET_1/json/f1b3fa26-e813-552b-a0f6-dd77f9d9b40e.json
deleted file mode 100644
index 110d5095..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f1b3fa26-e813-552b-a0f6-dd77f9d9b40e.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "Contributor": [
-        "Sloetjes, Han"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1189",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1189"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1189",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1189;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;ELAN;Sloetjes, Han;Multimodal annotation tool;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1189;downloadable_files_count: 0;Netherlands (the);Max Planck Institute for Psycholinguistics;http://tla.mpi.nl/tools/tla-tools/elan/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f1b3fa26-e813-552b-a0f6-dd77f9d9b40e",
-    "notes": [
-        "Multimodal annotation tool"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1189"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "ELAN"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f1bf9cab-27b7-53bd-82f2-73ee0506ef96.json b/oaitestdata/clarin-oai_dc/SET_1/json/f1bf9cab-27b7-53bd-82f2-73ee0506ef96.json
deleted file mode 100644
index 2c81dca2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f1bf9cab-27b7-53bd-82f2-73ee0506ef96.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "CC"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 86",
-        "text/plain; charset=utf-8",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/511",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/511"
-    ],
-    "PID": "http://hdl.handle.net/11321/511",
-    "PublicationTimestamp": "2018-07-13T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "CC"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Super Cool License",
-        "http://www.google.com",
-        "ACA"
-    ],
-    "author": [
-        "BB, BB",
-        "AA, AA"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/511;2018-07-13T13:50:35Z;hdl_11321_3;hdl_11321_4;korpus testowy;AA, AA;BB, BB;test;testowy;2018-07-13;corpus;http://hdl.handle.net/11321/511;pol;Super Cool License;http://www.google.com;ACA;text/plain; charset=utf-8;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;downloadable_files_count: 86;CC",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f1bf9cab-27b7-53bd-82f2-73ee0506ef96",
-    "notes": [
-        "testowy"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/511"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "test"
-        }
-    ],
-    "title": [
-        "korpus testowy"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f1dab622-d32f-575b-8a0b-14fa8b8af254.json b/oaitestdata/clarin-oai_dc/SET_1/json/f1dab622-d32f-575b-8a0b-14fa8b8af254.json
deleted file mode 100644
index 13f7b4d9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f1dab622-d32f-575b-8a0b-14fa8b8af254.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Preston, M.J., (Michael James), 1943-"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(7 files : total of ca. 611 KB)"
-    ],
-    "Language": [
-        "Middle English (1100-1500)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1392",
-    "MetadataAccess": [
-        "oai:ota:oucs:1392"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Anthologies"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:1392;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1392.xml;York miracle play cycle;text_and_corpus_linguistics;Mysteries and miracle-plays, English;English drama -- To 1500;Plays -- England -- 14th century;Plays -- England -- 15th century;Linguistic analysis (Linguistics);enm;Oxford Text Archive, University of Oxford;Preston, M.J., (Michael James), 1943-;(7 files : total of ca. 611 KB);Text;Anthologies;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f1dab622-d32f-575b-8a0b-14fa8b8af254",
-    "oai_identifier": [
-        "oai:ota:oucs:1392"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Mysteries miracle-plays"
-        },
-        {
-            "name": "English"
-        },
-        {
-            "name": "English drama --"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        },
-        {
-            "name": "Linguistic analysis Linguistics"
-        }
-    ],
-    "title": [
-        "York miracle play cycle"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1392.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f1dd95df-734b-58f3-9ed7-1a358113407b.json b/oaitestdata/clarin-oai_dc/SET_1/json/f1dd95df-734b-58f3-9ed7-1a358113407b.json
deleted file mode 100644
index 153f2830..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f1dd95df-734b-58f3-9ed7-1a358113407b.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish",
-        "Ukrainian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/76",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/76"
-    ],
-    "PID": "http://hdl.handle.net/10794/76",
-    "PublicationTimestamp": "2015-04-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/76;2017-11-01T07:55:26Z;hdl_10794_1;hdl_10794_2;ASPAC \u2013 Swedish-Ukrainian (2017-10-16);ASPAC \u2013 svenska-ukrainska (2017-10-16);n/a, n/a;ASPAC;Parallel;Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.;Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat.;2015-04-16;corpus;http://hdl.handle.net/10794/76;swe;ukr;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/octet-stream;application/gzip;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/aspacsvuk",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f1dd95df-734b-58f3-9ed7-1a358113407b",
-    "notes": [
-        "Part of The Amsterdam Slavic Parallel Aligned Corpus. The material is sentence scrambled.",
-        "Del av The Amsterdam Slavic Parallel Aligned Corpus. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/76"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ASPAC"
-        },
-        {
-            "name": "Parallel"
-        }
-    ],
-    "title": [
-        "ASPAC \u2013 Swedish-Ukrainian (2017-10-16)",
-        "ASPAC \u2013 svenska-ukrainska (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f1e310e2-f09e-5754-b986-ea9c94ee7e02.json b/oaitestdata/clarin-oai_dc/SET_1/json/f1e310e2-f09e-5754-b986-ea9c94ee7e02.json
deleted file mode 100644
index 9a138392..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f1e310e2-f09e-5754-b986-ea9c94ee7e02.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Rzeczypospolitey w Collegium Xi\u0119\u017cy Scholarum Piarum"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-4404",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-4404"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D1D-E",
-    "PublicationTimestamp": "1764-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1764"
-    ],
-    "Publisher": [
-        "Drukarnia Rzeczypospolitey w Collegium Xi\u0119\u017cy Scholarum Piarum"
-    ],
-    "RelatedIdentifier": [
-        "http://pbc.biaman.pl/Content/4404"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-4404;2019-03-01T15:29:38Z;Konfederacya generalna omnium ordinum Regni et Magni Ducatus Lithuaniae na Konwokacyi G\u0142owney Warszawskiey uchwalona, dnia 7 [s\u0142.] miesi\u0105ca maja [...] Roku Pa\u0144skiego 1764 [s\u0142.].;ilo\u015b\u0107 skan\u00f3w: 193 ; sygn. St-304;Drukarnia Rzeczypospolitey w Collegium Xi\u0119\u017cy Scholarum Piarum;[ca 1764];starodruk;application/xml;clarind-uds:poldilemma-4404;hdl:11858/00-246C-0000-0023-8D1D-E;pol;lat;http://pbc.biaman.pl/Content/4404;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f1e310e2-f09e-5754-b986-ea9c94ee7e02",
-    "notes": [
-        "ilo\u015b\u0107 skan\u00f3w: 193 ; sygn. St-304"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-4404"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "title": [
-        "Konfederacya generalna omnium ordinum Regni et Magni Ducatus Lithuaniae na Konwokacyi G\u0142owney Warszawskiey uchwalona, dnia 7 [s\u0142.] miesi\u0105ca maja [...] Roku Pa\u0144skiego 1764 [s\u0142.]."
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f206324e-eb83-5659-8c59-12641f574025.json b/oaitestdata/clarin-oai_dc/SET_1/json/f206324e-eb83-5659-8c59-12641f574025.json
deleted file mode 100644
index a97f4750..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f206324e-eb83-5659-8c59-12641f574025.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3388",
-    "MetadataAccess": [
-        "oai:ota:oucs:3388"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hazlitt, William, 1737-1820."
-    ],
-    "fulltext": "oai:ota:oucs:3388;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3388.xml;Human authority, in matters of faith, repugnant to Christianity: illustrated in two discourses on Matth. xxiii. 8. With a prefatory address, ... By the author of An essay on the justice of God.;Hazlitt, William, 1737-1820.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f206324e-eb83-5659-8c59-12641f574025",
-    "oai_identifier": [
-        "oai:ota:oucs:3388"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Human authority, in matters of faith, repugnant to Christianity: illustrated in two discourses on Matth. xxiii. 8. With a prefatory address, ... By the author of An essay on the justice of God."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3388.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f2377b19-8476-56a5-a89b-7c971742e32c.json b/oaitestdata/clarin-oai_dc/SET_1/json/f2377b19-8476-56a5-a89b-7c971742e32c.json
deleted file mode 100644
index cc64a259..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f2377b19-8476-56a5-a89b-7c971742e32c.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Center for Dutch Language and Speech, University of Antwerp"
-    ],
-    "Contributor": [
-        "Daelemans, Walter"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-637",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-637"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-637",
-    "PublicationTimestamp": "2008-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2008"
-    ],
-    "Publisher": [
-        "Center for Dutch Language and Speech, University of Antwerp"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Belgium"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-637;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Swahili (audio);Daelemans, Walter;audio of Swahili syllables and phonemes;2008;corpus;http://hdl.handle.net/11372/LRT-637;downloadable_files_count: 0;Belgium;Center for Dutch Language and Speech, University of Antwerp;http://aflat.org",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f2377b19-8476-56a5-a89b-7c971742e32c",
-    "notes": [
-        "audio of Swahili syllables and phonemes"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-637"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Swahili (audio)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f2481b9c-e219-5078-bba8-86ce74c0a94f.json b/oaitestdata/clarin-oai_dc/SET_1/json/f2481b9c-e219-5078-bba8-86ce74c0a94f.json
deleted file mode 100644
index 0b3a3a85..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f2481b9c-e219-5078-bba8-86ce74c0a94f.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 3",
-        "text/plain"
-    ],
-    "Language": [
-        "Hindi"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-6260-A",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-6260-A"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-6260-A",
-    "PublicationTimestamp": "2014-03-21T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11858/00-097C-0000-0001-CC1E-B"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Rychl\u00fd, Pavel",
-        "Zeman, Daniel",
-        "Stra\u0148\u00e1k, Pavel",
-        "Suchomel, V\u00edt",
-        "Bojar, Ond\u0159ej",
-        "Tamchyna, Ale\u0161",
-        "Diatka, Vojt\u011bch"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-6260-A;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;HindMonoCorp 0.5;Bojar, Ond\u0159ej;Diatka, Vojt\u011bch;Rychl\u00fd, Pavel;Stra\u0148\u00e1k, Pavel;Suchomel, V\u00edt;Tamchyna, Ale\u0161;Zeman, Daniel;corpus;Hindi monolingual corpus. It is based primarily on web crawls performed using various tools and at various times. Since the web is a living data source, we treat these crawls as completely separate sources, despite they may overlap. To estimate the magnitude of this overlap, we compared the total number of segments if we concatenate the individual sources (each source being deduplicated on its own) with the number of segments if we de-duplicate all sources to- gether. The difference is just around 1%, confirming, that various web crawls (or their subsequent processings) differ significantly.\r\n\r\nHindMonoCorp contains data from:\r\nHindi web texts, a monolingual corpus containing mainly Hindi news articles has already been collected and released by Bojar et al. (2008). We use the HTML files as crawled for this corpus in 2010 and we add a small crawl performed in 2013 and re-process them with the current pipeline. These sources are denoted HWT 2010 and HWT 2013 in the following.\r\n\r\nHindi corpora in W2C have been collected by Martin Majli\u0161 during his project to automatically collect corpora in many languages (Majli\u0161 and \u017dabokrtsk\u00fd, 2012). There are in fact two corpora of Hindi available\u2014one from web harvest (W2C Web) and one from the Wikipedia (W2C Wiki).\r\n\r\nSpiderLing is a web crawl carried out during November and December 2013 using SpiderLing (Suchomel and Pomik\u00e1lek, 2012). The pipeline includes extraction of plain texts and deduplication at the level of documents, see below.\r\n\r\nCommonCrawl is a non-profit organization that regu- larly crawls the web and provides anyone with the data. We are grateful to Christian Buck for extracting plain text Hindi segments from the 2012 and 2013-fall crawls for us.\r\n\r\nIntercorp \u2013 7 books with their translations scanned and manually alligned per paragraph\r\n\r\nRSS Feeds from Webdunia.com and the Hindi version of BBC International followed by our custom crawler from September 2013 till January 2014.;2014-03-21;corpus;http://hdl.handle.net/11858/00-097C-0000-0023-6260-A;hin;http://hdl.handle.net/11858/00-097C-0000-0001-CC1E-B;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;text/plain;application/x-gzip;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 3;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f2481b9c-e219-5078-bba8-86ce74c0a94f",
-    "notes": [
-        "Hindi monolingual corpus. It is based primarily on web crawls performed using various tools and at various times. Since the web is a living data source, we treat these crawls as completely separate sources, despite they may overlap. To estimate the magnitude of this overlap, we compared the total number of segments if we concatenate the individual sources (each source being deduplicated on its own) with the number of segments if we de-duplicate all sources to- gether. The difference is just around 1%, confirming, that various web crawls (or their subsequent processings) differ significantly.\r\n\r\nHindMonoCorp contains data from:\r\nHindi web texts, a monolingual corpus containing mainly Hindi news articles has already been collected and released by Bojar et al. (2008). We use the HTML files as crawled for this corpus in 2010 and we add a small crawl performed in 2013 and re-process them with the current pipeline. These sources are denoted HWT 2010 and HWT 2013 in the following.\r\n\r\nHindi corpora in W2C have been collected by Martin Majli\u0161 during his project to automatically collect corpora in many languages (Majli\u0161 and \u017dabokrtsk\u00fd, 2012). There are in fact two corpora of Hindi available\u2014one from web harvest (W2C Web) and one from the Wikipedia (W2C Wiki).\r\n\r\nSpiderLing is a web crawl carried out during November and December 2013 using SpiderLing (Suchomel and Pomik\u00e1lek, 2012). The pipeline includes extraction of plain texts and deduplication at the level of documents, see below.\r\n\r\nCommonCrawl is a non-profit organization that regu- larly crawls the web and provides anyone with the data. We are grateful to Christian Buck for extracting plain text Hindi segments from the 2012 and 2013-fall crawls for us.\r\n\r\nIntercorp \u2013 7 books with their translations scanned and manually alligned per paragraph\r\n\r\nRSS Feeds from Webdunia.com and the Hindi version of BBC International followed by our custom crawler from September 2013 till January 2014."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-6260-A"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        }
-    ],
-    "title": [
-        "HindMonoCorp 0.5"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f24e1dd4-2c6f-5e91-a73b-0c5a9ad1377b.json b/oaitestdata/clarin-oai_dc/SET_1/json/f24e1dd4-2c6f-5e91-a73b-0c5a9ad1377b.json
deleted file mode 100644
index 1397259e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f24e1dd4-2c6f-5e91-a73b-0c5a9ad1377b.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Black, Jeremy A.",
-        "Cunningham, Graham"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(2373 files : total of ca. 16.1 MB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2424",
-    "MetadataAccess": [
-        "oai:ota:oucs:2424"
-    ],
-    "PublicationTimestamp": "2000-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Anthologies"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:2424;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/2424.xml;The Electronic Text Corpus of Sumerian Literature. First edition. / Jeremy Black et al.;ETCSL;2000 BCE-1600 BCE;text_and_corpus_linguistics;Linguistic analysis (Linguistics);Oxford Text Archive, University of Oxford;Black, Jeremy A.;Cunningham, Graham;Black, Jeremy A.;text/sgml;(2373 files : total of ca. 16.1 MB);Text;Anthologies;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f24e1dd4-2c6f-5e91-a73b-0c5a9ad1377b",
-    "oai_identifier": [
-        "oai:ota:oucs:2424"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Linguistic analysis Linguistics"
-        }
-    ],
-    "title": [
-        "The Electronic Text Corpus of Sumerian Literature. First edition. / Jeremy Black et al.",
-        "ETCSL"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2424.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f26bc9ad-9a36-5666-bfdd-33ca88faffad.json b/oaitestdata/clarin-oai_dc/SET_1/json/f26bc9ad-9a36-5666-bfdd-33ca88faffad.json
deleted file mode 100644
index 4b2a39a3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f26bc9ad-9a36-5666-bfdd-33ca88faffad.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3513",
-    "MetadataAccess": [
-        "oai:ota:oucs:3513"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Paine, Thomas, 1737-1809."
-    ],
-    "fulltext": "oai:ota:oucs:3513;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3513.xml;The age of reason: being an investigation of true and fabulous theology, by Thomas Paine. ...;Age of reason.;Paine, Thomas, 1737-1809.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f26bc9ad-9a36-5666-bfdd-33ca88faffad",
-    "oai_identifier": [
-        "oai:ota:oucs:3513"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The age of reason: being an investigation of true and fabulous theology, by Thomas Paine. ...",
-        "Age of reason."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3513.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f27ad80c-5c33-5bdd-b80a-329249166d40.json b/oaitestdata/clarin-oai_dc/SET_1/json/f27ad80c-5c33-5bdd-b80a-329249166d40.json
deleted file mode 100644
index fd9e195f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f27ad80c-5c33-5bdd-b80a-329249166d40.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4370",
-    "MetadataAccess": [
-        "oai:ota:oucs:4370"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Janeway, James, 1636?-1674."
-    ],
-    "fulltext": "oai:ota:oucs:4370;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4370.xml;Invisibles, realities: demonstrated in the holy life and triumphant death of Mr. John Janeway, ... By James Janeway, ...;Janeway, James, 1636?-1674.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f27ad80c-5c33-5bdd-b80a-329249166d40",
-    "oai_identifier": [
-        "oai:ota:oucs:4370"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Invisibles, realities: demonstrated in the holy life and triumphant death of Mr. John Janeway, ... By James Janeway, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4370.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f27eb3fd-45ed-5a42-b14f-35c195e43e8f.json b/oaitestdata/clarin-oai_dc/SET_1/json/f27eb3fd-45ed-5a42-b14f-35c195e43e8f.json
deleted file mode 100644
index d148265b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f27eb3fd-45ed-5a42-b14f-35c195e43e8f.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Croatian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1209",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1209"
-    ],
-    "PID": "http://hdl.handle.net/11356/1209",
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "https://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Dobrani\u0107, Filip",
-        "Ljube\u0161i\u0107, Nikola",
-        "Erjavec, Toma\u017e"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1209;2019-01-05T09:05:24Z;hdl_11356_1023;hdl_11356_1024;Croatian parliamentary corpus ParlaMeter-hr 1.0;Dobrani\u0107, Filip;Ljube\u0161i\u0107, Nikola;Erjavec, Toma\u017e;Croatian Parliament;parliamentary debates;TEI;named entities;The ParlaMeter-hr corpus contains minutes of the National Assembly of the Republic of Croatia and currently covers its VIth mandate (2016-11-15 - 2018-11-21). The corpus contains speaker metadata (gender, age, education, party affiliatiation), while the transcriptions of their speeches are MSD tagged, lemmatised, and marked with named entities.;2019-01-08;corpus;http://hdl.handle.net/11356/1209;hrv;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);https://creativecommons.org/licenses/by-sa/4.0/;PUB;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 2;Jo\u017eef Stefan Institute;https://parlametar.hr/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f27eb3fd-45ed-5a42-b14f-35c195e43e8f",
-    "notes": [
-        "The ParlaMeter-hr corpus contains minutes of the National Assembly of the Republic of Croatia and currently covers its VIth mandate (2016-11-15 - 2018-11-21). The corpus contains speaker metadata (gender, age, education, party affiliatiation), while the transcriptions of their speeches are MSD tagged, lemmatised, and marked with named entities."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1209"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Croatian Parliament"
-        },
-        {
-            "name": "parliamentary debates"
-        },
-        {
-            "name": "TEI"
-        },
-        {
-            "name": "named entities"
-        }
-    ],
-    "title": [
-        "Croatian parliamentary corpus ParlaMeter-hr 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f2a4735e-e371-57ec-87cd-64d300a15233.json b/oaitestdata/clarin-oai_dc/SET_1/json/f2a4735e-e371-57ec-87cd-64d300a15233.json
deleted file mode 100644
index bfe0e1c5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f2a4735e-e371-57ec-87cd-64d300a15233.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "Contributor": [
-        "Riera, Marc Poch"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-538",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-538"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-538",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-538;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;panacea_conversor;Riera, Marc Poch;Format conversion service: Panacea conversion tool;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-538;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra;http://www.panacea-lr.eu/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f2a4735e-e371-57ec-87cd-64d300a15233",
-    "notes": [
-        "Format conversion service: Panacea conversion tool"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-538"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "panacea_conversor"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f2c903bb-d9db-5386-afd0-c59277a03fb6.json b/oaitestdata/clarin-oai_dc/SET_1/json/f2c903bb-d9db-5386-afd0-c59277a03fb6.json
deleted file mode 100644
index 4e3938d8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f2c903bb-d9db-5386-afd0-c59277a03fb6.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "A"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1461",
-    "MetadataAccess": [
-        "oai:ota:oucs:1461"
-    ],
-    "PublicationYear": [
-        "Date unknown"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Day, John"
-    ],
-    "fulltext": "oai:ota:oucs:1461;2018-04-16T15:30:51Z;http://ota.ox.ac.uk/headers/1461.xml;Humour out of breath (contractions expanded);Day, John;Date unknown;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;A;Text;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f2c903bb-d9db-5386-afd0-c59277a03fb6",
-    "oai_identifier": [
-        "oai:ota:oucs:1461"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Humour out of breath (contractions expanded)"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1461.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f2ded9db-a3cf-59e0-8e96-c74cd5426508.json b/oaitestdata/clarin-oai_dc/SET_1/json/f2ded9db-a3cf-59e0-8e96-c74cd5426508.json
deleted file mode 100644
index 54860749..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f2ded9db-a3cf-59e0-8e96-c74cd5426508.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=dd3d5a0849dc11e2a2aa782bcb074135d9cb4fe73e884aa3b771fd0a7a11a2b7",
-    "MetadataAccess": [
-        "dd3d5a0849dc11e2a2aa782bcb074135d9cb4fe73e884aa3b771fd0a7a11a2b7"
-    ],
-    "PublicationTimestamp": "2013-02-05T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "dd3d5a0849dc11e2a2aa782bcb074135d9cb4fe73e884aa3b771fd0a7a11a2b7;2018-11-15T16:39:59Z;lexicalConceptualResource;lexicalConceptualResource:wordList;Maltese Fiction Wordlist;This is a wordlist which was created from 32 Maltese fiction books. These texts were originally in PDF file format and were converted to txt format. In the next step, the text file was tokenized and a frequency count was performed on the separate tokens. The resulting list (with about 50,000 entries) was cleaned up semi-automatically. \n\nThe original list contained 46,828 tokens. After the clean-up, the list contains 41,251 tokens. The tokens were either deleted or updated (with regards to their frequencies).\n\nGiven the conversion from PDF to txt format, the list will most likely contain spelling errors that were not detected in the semi-automatic clean-up process.\n\nThe file is in txt format, with each line containing a token, followed by frequency (separated by comma or, in case of entries ending in hyphen or apostrophe, by six tab stops).\n\nGenerally the lexicon covers the literal register. The orate register appears where speech is reproduced. All in all, the books contained:\n   - correctly written Maltese (standard literate register)\n   - badly written Maltese (e.g. to mimic chat conversations)\n   - dialact Maltese\n   - English words\n   - Italian words\n   - French words\n\nThe word list is not (yet) very reliable, since it was converted from PDF to txt format and cleaned up only semi-automatically. It is, however, a first version, and more refine updates should be done in the future.\n\n;2013-02-05",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f2ded9db-a3cf-59e0-8e96-c74cd5426508",
-    "notes": [
-        "This is a wordlist which was created from 32 Maltese fiction books. These texts were originally in PDF file format and were converted to txt format. In the next step, the text file was tokenized and a frequency count was performed on the separate tokens. The resulting list (with about 50,000 entries) was cleaned up semi-automatically. \n\nThe original list contained 46,828 tokens. After the clean-up, the list contains 41,251 tokens. The tokens were either deleted or updated (with regards to their frequencies).\n\nGiven the conversion from PDF to txt format, the list will most likely contain spelling errors that were not detected in the semi-automatic clean-up process.\n\nThe file is in txt format, with each line containing a token, followed by frequency (separated by comma or, in case of entries ending in hyphen or apostrophe, by six tab stops).\n\nGenerally the lexicon covers the literal register. The orate register appears where speech is reproduced. All in all, the books contained:\n   - correctly written Maltese (standard literate register)\n   - badly written Maltese (e.g. to mimic chat conversations)\n   - dialact Maltese\n   - English words\n   - Italian words\n   - French words\n\nThe word list is not (yet) very reliable, since it was converted from PDF to txt format and cleaned up only semi-automatically. It is, however, a first version, and more refine updates should be done in the future.\n\n"
-    ],
-    "oai_identifier": [
-        "dd3d5a0849dc11e2a2aa782bcb074135d9cb4fe73e884aa3b771fd0a7a11a2b7"
-    ],
-    "oai_set": [
-        "lexicalConceptualResource",
-        "lexicalConceptualResource:wordList"
-    ],
-    "state": "active",
-    "title": [
-        "Maltese Fiction Wordlist"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f3071418-c16c-5f64-8c2c-9ad38813ea93.json b/oaitestdata/clarin-oai_dc/SET_1/json/f3071418-c16c-5f64-8c2c-9ad38813ea93.json
deleted file mode 100644
index 5ae0d8db..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f3071418-c16c-5f64-8c2c-9ad38813ea93.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4741",
-    "MetadataAccess": [
-        "oai:ota:oucs:4741"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Duck, Stephen, 1705-1756."
-    ],
-    "fulltext": "oai:ota:oucs:4741;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4741.xml;Poems on several occasions: By Stephen Duck.;Duck, Stephen, 1705-1756.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f3071418-c16c-5f64-8c2c-9ad38813ea93",
-    "oai_identifier": [
-        "oai:ota:oucs:4741"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Poems on several occasions: By Stephen Duck."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4741.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f30d90fc-fea3-55fc-9b08-cc3362af1464.json b/oaitestdata/clarin-oai_dc/SET_1/json/f30d90fc-fea3-55fc-9b08-cc3362af1464.json
deleted file mode 100644
index 182ccbb6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f30d90fc-fea3-55fc-9b08-cc3362af1464.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48F2-1",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48F2-1"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-48F2-1",
-    "PublicationTimestamp": "2010-01-13T15:06:26Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11858/00-097C-0000-0023-4087-6"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "BSD 2-Clause \"Simplified\" or \"FreeBSD\" license",
-        "http://opensource.org/licenses/BSD-2-Clause",
-        "PUB"
-    ],
-    "author": [
-        "Pajas, Petr"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48F2-1;2018-07-02T22:05:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Dspace modifications for use of EPIC handles;Pajas, Petr;DSpace;handle;EPIC;Modifications to DSpace made by Petr Pajas in order to support pidconsortium.eu PID handle system instead of the default handle.com system used by DSpace.;2010-01-13T15:06:26Z;toolService;http://hdl.handle.net/11858/00-097C-0000-0001-48F2-1;http://hdl.handle.net/11858/00-097C-0000-0023-4087-6;BSD 2-Clause \"Simplified\" or \"FreeBSD\" license;http://opensource.org/licenses/BSD-2-Clause;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://svn.ms.mff.cuni.cz/redmine/projects/dspace-modifications",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f30d90fc-fea3-55fc-9b08-cc3362af1464",
-    "notes": [
-        "Modifications to DSpace made by Petr Pajas in order to support pidconsortium.eu PID handle system instead of the default handle.com system used by DSpace."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48F2-1"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "DSpace"
-        },
-        {
-            "name": "handle"
-        },
-        {
-            "name": "EPIC"
-        }
-    ],
-    "title": [
-        "Dspace modifications for use of EPIC handles"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f317dd89-7892-5784-8c89-d7265e793f9e.json b/oaitestdata/clarin-oai_dc/SET_1/json/f317dd89-7892-5784-8c89-d7265e793f9e.json
deleted file mode 100644
index 455026bf..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f317dd89-7892-5784-8c89-d7265e793f9e.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Italian",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-68",
-    "MetadataAccess": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-68"
-    ],
-    "PID": "http://hdl.handle.net/20.500.11752/ILC-68",
-    "PublicationTimestamp": "2016-10-18T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR)"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0",
-        "PUB"
-    ],
-    "author": [
-        "Del Gratta, Riccardo",
-        "Frontini, Francesca",
-        "Monachini, Monica"
-    ],
-    "fulltext": "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-68;2018-07-23T09:13:44Z;hdl_000-c0-111_38;hdl_000-c0-111_49;Geodomain WordNet ITA ENG V 1.0;Frontini, Francesca;Del Gratta, Riccardo;Monachini, Monica;Geographical Names;Named Entity;Concepts;Wordnet Structure;Two domain wordnets containing a manual mapping  between the concepts of the Geonames ontology (version 3.0) and two existing wordnets.\r\nGeodomain WordNet ENG V 1.0 maps the Geonames concepts onto Princeton WordNet 3.0\r\nGeodomain WordNet ITA V 1.0 maps the Geonames concepts onto ItalWordnet; moreover the Geonames concept glosses are translated into Italian.;2016-10-18;lexicalConceptualResource;http://hdl.handle.net/20.500.11752/ILC-68;ita;eng;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Istituto di Linguistica Computazionale \u201cA. Zampolli\u201d - Consiglio Nazionale delle Ricerche (ILC-CNR);http://www.ilc.cnr.it/en/content/resources",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f317dd89-7892-5784-8c89-d7265e793f9e",
-    "notes": [
-        "Two domain wordnets containing a manual mapping  between the concepts of the Geonames ontology (version 3.0) and two existing wordnets.\r\nGeodomain WordNet ENG V 1.0 maps the Geonames concepts onto Princeton WordNet 3.0\r\nGeodomain WordNet ITA V 1.0 maps the Geonames concepts onto ItalWordnet; moreover the Geonames concept glosses are translated into Italian."
-    ],
-    "oai_identifier": [
-        "oai:dspace-clarin-it.ilc.cnr.it:20.500.11752/ILC-68"
-    ],
-    "oai_set": [
-        "hdl_000-c0-111_38",
-        "hdl_000-c0-111_49"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Geographical Names"
-        },
-        {
-            "name": "Named Entity"
-        },
-        {
-            "name": "Concepts"
-        },
-        {
-            "name": "Wordnet Structure"
-        }
-    ],
-    "title": [
-        "Geodomain WordNet ITA ENG V 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f369700e-c47d-5494-aa2f-87571bf9059e.json b/oaitestdata/clarin-oai_dc/SET_1/json/f369700e-c47d-5494-aa2f-87571bf9059e.json
deleted file mode 100644
index 8b421568..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f369700e-c47d-5494-aa2f-87571bf9059e.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "Oslo University",
-        "Charles University"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "English",
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1742",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1742"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1742",
-    "PublicationTimestamp": "2016-06-25T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Oslo University",
-        "Charles University"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-1956"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Kuhlmann, Marco",
-        "Haji\u010d, Jan",
-        "Ivanova, Angelina",
-        "Zeman, Daniel",
-        "Miyao, Yusuke",
-        "Flickinger, Dan",
-        "Oepen, Stephan"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1742;2018-07-02T22:05:49Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Open SDP;Flickinger, Dan;Haji\u010d, Jan;Ivanova, Angelina;Kuhlmann, Marco;Miyao, Yusuke;Oepen, Stephan;Zeman, Daniel;semantic dependency;parsing;The original SDP 2014 and 2015 data collections were made available under task-specific \u2018evaluation\u2019 licenses to registered SemEval participants. In mid-2016, all original data has been bundled with system submissions, supporting software, an additional SDP-style collection of semantic dependency graphs, and additional background material (from which some of the SDP target representations were derived) for release through the Linguistic Data Consortium (with LDC catalogue number LDC2016\u2009T10).\r\n\r\nOne of the four English target representations (viz. DM) and the entire Czech data (in the PSD target representation) are not derivative of LDC-licensed annotations and, thus, can be made available for direct download (Open SDP; version 1.1; April 2016) under a more permissive licensing scheme, viz. the Creative Common Attribution-NonCommercial-ShareAlike license. This package also includes some \u2018richer\u2019 meaning representations from which the English bi-lexical DM graphs derive, viz. scope-underspecified logical forms and more abstract, non-lexicalized \u2018semantic networks\u2019. The latter of these are formally (if not linguistically) similar to Abstract Meaning Representation (AMR) and are available in a range of serializations, including in AMR-like syntax.\r\n\r\nPlease use the following bibliographic reference for the SDP 2016 data:\r\n\r\n  @string{C:LREC = {{I}nternational {C}onference on\r\n                    {L}anguage {R}esources and {E}valuation}}\r\n  @string{LREC:16 = {Proceedings of the 10th } # C:LREC}\r\n  @string{L:LREC:16 = {Portoro\\v{z}, Slovenia}}\r\n\r\n  @inproceedings{Oep:Kuh:Miy:16,\r\n    author = {Oepen, Stephan  and  Kuhlmann, Marco  and  Miyao, Yusuke  \r\n              and  Zeman, Daniel  and  Cinkov{\\'a}, Silvie  \r\n              and  Flickinger, Dan  and  Haji\\v{c}, Jan  \r\n              and  Ivanova, Angelina and Ure\\v{s}ov{\\'a}, Zde\\v{n}ka},\r\n    title = {Towards Comparability of Linguistic Graph Banks for Semantic Parsing},\r\n    booktitle = LREC:16\r\n    year = 2016,\r\n    address = L:LREC:16,\r\n    pages = {3991--3995}\r\n  };2016-06-25;corpus;http://hdl.handle.net/11234/1-1742;eng;ces;http://hdl.handle.net/11234/1-1956;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Oslo University;Charles University;http://sdp.delph-in.net/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f369700e-c47d-5494-aa2f-87571bf9059e",
-    "notes": [
-        "The original SDP 2014 and 2015 data collections were made available under task-specific \u2018evaluation\u2019 licenses to registered SemEval participants. In mid-2016, all original data has been bundled with system submissions, supporting software, an additional SDP-style collection of semantic dependency graphs, and additional background material (from which some of the SDP target representations were derived) for release through the Linguistic Data Consortium (with LDC catalogue number LDC2016\u2009T10).\r\n\r\nOne of the four English target representations (viz. DM) and the entire Czech data (in the PSD target representation) are not derivative of LDC-licensed annotations and, thus, can be made available for direct download (Open SDP; version 1.1; April 2016) under a more permissive licensing scheme, viz. the Creative Common Attribution-NonCommercial-ShareAlike license. This package also includes some \u2018richer\u2019 meaning representations from which the English bi-lexical DM graphs derive, viz. scope-underspecified logical forms and more abstract, non-lexicalized \u2018semantic networks\u2019. The latter of these are formally (if not linguistically) similar to Abstract Meaning Representation (AMR) and are available in a range of serializations, including in AMR-like syntax.\r\n\r\nPlease use the following bibliographic reference for the SDP 2016 data:\r\n\r\n  @string{C:LREC = {{I}nternational {C}onference on\r\n                    {L}anguage {R}esources and {E}valuation}}\r\n  @string{LREC:16 = {Proceedings of the 10th } # C:LREC}\r\n  @string{L:LREC:16 = {Portoro\\v{z}, Slovenia}}\r\n\r\n  @inproceedings{Oep:Kuh:Miy:16,\r\n    author = {Oepen, Stephan  and  Kuhlmann, Marco  and  Miyao, Yusuke  \r\n              and  Zeman, Daniel  and  Cinkov{\\'a}, Silvie  \r\n              and  Flickinger, Dan  and  Haji\\v{c}, Jan  \r\n              and  Ivanova, Angelina and Ure\\v{s}ov{\\'a}, Zde\\v{n}ka},\r\n    title = {Towards Comparability of Linguistic Graph Banks for Semantic Parsing},\r\n    booktitle = LREC:16\r\n    year = 2016,\r\n    address = L:LREC:16,\r\n    pages = {3991--3995}\r\n  }"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1742"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "semantic dependency"
-        },
-        {
-            "name": "parsing"
-        }
-    ],
-    "title": [
-        "Open SDP"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f398733c-c667-5e8f-801e-4943e192c8a7.json b/oaitestdata/clarin-oai_dc/SET_1/json/f398733c-c667-5e8f-801e-4943e192c8a7.json
deleted file mode 100644
index f087933b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f398733c-c667-5e8f-801e-4943e192c8a7.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/540",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/540"
-    ],
-    "PID": "http://hdl.handle.net/11321/540",
-    "PublicationTimestamp": "2018-07-23T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "K\u0119dzia, Pawe\u0142",
-        "Janz, Arkadiusz",
-        "Kaszewski, Dominik"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/540;2018-07-23T10:12:34Z;hdl_11321_3;hdl_11321_4;Word Sense Disambiguation tool WoSeDon;Janz, Arkadiusz;K\u0119dzia, Pawe\u0142;Kaszewski, Dominik;wsd;WoSeDon;plWordNet;Word sense disambiguation tool using rich, semantic resources.;2018-07-23;toolService;http://hdl.handle.net/11321/540;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;Wroc\u0142aw University of Science and Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f398733c-c667-5e8f-801e-4943e192c8a7",
-    "notes": [
-        "Word sense disambiguation tool using rich, semantic resources."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/540"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "wsd"
-        },
-        {
-            "name": "WoSeDon"
-        },
-        {
-            "name": "plWordNet"
-        }
-    ],
-    "title": [
-        "Word Sense Disambiguation tool WoSeDon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f3a535df-8033-506c-9b99-23e388ca9e55.json b/oaitestdata/clarin-oai_dc/SET_1/json/f3a535df-8033-506c-9b99-23e388ca9e55.json
deleted file mode 100644
index 763b9f77..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f3a535df-8033-506c-9b99-23e388ca9e55.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 3"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48FE-9",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48FE-9"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-48FE-9",
-    "PublicationTimestamp": "2009-11-02T09:36:29Z",
-    "PublicationYear": [
-        "2009"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11858/00-097C-0000-0023-43CD-0"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU General Public License, version 2",
-        "http://www.gnu.org/licenses/gpl-2.0.html",
-        "PUB"
-    ],
-    "author": [
-        "Raab, Jan"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48FE-9;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Mor\u010de;Raab, Jan;tagger;morphology;The MOR\u010cE tagger is a software for morphological disambiguation (part-of-speech tagging) of Czech text. The algorithm is statistical, based on an idea of so-called \"Averaged Perceptron\" published by Michael Collins in 2002.;2009-11-02T09:36:29Z;toolService;http://hdl.handle.net/11858/00-097C-0000-0001-48FE-9;ces;http://hdl.handle.net/11858/00-097C-0000-0023-43CD-0;GNU General Public License, version 2;http://www.gnu.org/licenses/gpl-2.0.html;PUB;application/x-gzip;application/x-gzip;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 3;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f3a535df-8033-506c-9b99-23e388ca9e55",
-    "notes": [
-        "The MOR\u010cE tagger is a software for morphological disambiguation (part-of-speech tagging) of Czech text. The algorithm is statistical, based on an idea of so-called \"Averaged Perceptron\" published by Michael Collins in 2002."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48FE-9"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "tagger"
-        },
-        {
-            "name": "morphology"
-        }
-    ],
-    "title": [
-        "Mor\u010de"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f3ac2b62-5ff1-5a64-902a-ca42d48b138d.json b/oaitestdata/clarin-oai_dc/SET_1/json/f3ac2b62-5ff1-5a64-902a-ca42d48b138d.json
deleted file mode 100644
index aa6018be..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f3ac2b62-5ff1-5a64-902a-ca42d48b138d.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2637",
-    "MetadataAccess": [
-        "oai:ota:oucs:2637"
-    ],
-    "PublicationTimestamp": "1727-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1727"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2637;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2637.xml;A letter concerning the sacramental test;Swift, Jonathan, 1667-1745;1727;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f3ac2b62-5ff1-5a64-902a-ca42d48b138d",
-    "oai_identifier": [
-        "oai:ota:oucs:2637"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A letter concerning the sacramental test"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2637.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f3c25fa8-0151-5e73-be22-67118700fae9.json b/oaitestdata/clarin-oai_dc/SET_1/json/f3c25fa8-0151-5e73-be22-67118700fae9.json
deleted file mode 100644
index c3ba26ce..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f3c25fa8-0151-5e73-be22-67118700fae9.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "Fondazione Bruno Kessler, Trento, Italy"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 3",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2334",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2334"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2334",
-    "PublicationTimestamp": "2017-07-12T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Fondazione Bruno Kessler, Trento, Italy"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/H2020/645452"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "AGREEMENT ON THE USE OF DATA IN QT21 APE Task",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21",
-        "PUB"
-    ],
-    "author": [
-        "Turchi, Marco",
-        "Chatterjee, Rajen",
-        "Negri, Matteo"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2334;2018-07-02T22:05:53Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;WMT16 APE Shared Task Data - Reference sentences;Turchi, Marco;Negri, Matteo;Chatterjee, Rajen;machine translation;machine learning;automatic post-editing;shared task;Training, development and test data consist in German sentences belonging to the IT domain and already tokenized. These sentences are the references of the data released for the 2016 edition of the WMT APE shared task. Differently from the data previously released, these sentences are obtained by manually translating the source sentence without leveraging the raw mt outputs. Training and development respectively contain 12,000 and 1,000 segments, while the test set 2,000 items. All data is provided by the EU project QT21 (http://www.qt21.eu/).;2017-07-12;corpus;http://hdl.handle.net/11234/1-2334;deu;info:eu-repo/grantAgreement/EC/H2020/645452;AGREEMENT ON THE USE OF DATA IN QT21 APE Task;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21;PUB;application/octet-stream;application/octet-stream;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 3;Fondazione Bruno Kessler, Trento, Italy;http://www.statmt.org/wmt16/ape-task.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f3c25fa8-0151-5e73-be22-67118700fae9",
-    "notes": [
-        "Training, development and test data consist in German sentences belonging to the IT domain and already tokenized. These sentences are the references of the data released for the 2016 edition of the WMT APE shared task. Differently from the data previously released, these sentences are obtained by manually translating the source sentence without leveraging the raw mt outputs. Training and development respectively contain 12,000 and 1,000 segments, while the test set 2,000 items. All data is provided by the EU project QT21 (http://www.qt21.eu/)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2334"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "machine learning"
-        },
-        {
-            "name": "automatic post-editing"
-        },
-        {
-            "name": "shared task"
-        }
-    ],
-    "title": [
-        "WMT16 APE Shared Task Data - Reference sentences"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f3cba932-fc24-5030-b7c4-86bbf1f16b8f.json b/oaitestdata/clarin-oai_dc/SET_1/json/f3cba932-fc24-5030-b7c4-86bbf1f16b8f.json
deleted file mode 100644
index c4015f1f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f3cba932-fc24-5030-b7c4-86bbf1f16b8f.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Meertens Institute KNAW The Netherlands"
-    ],
-    "Contributor": [
-        "Bloothooft, Gerrit"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-738",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-738"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-738",
-    "PublicationTimestamp": "2010-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "Meertens Institute KNAW The Netherlands"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "Meertens Institute KNAW The Netherlands"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-738;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Nederlandse Familienamen Databank (Dutch Database of Family Names);Bloothooft, Gerrit;Enriched database of  (mainly) Dutch family names, based on 1947 census (in progress; currently 90.000 entries from 140.000 max);2010;toolService;http://hdl.handle.net/11372/LRT-738;nld;Meertens Institute KNAW The Netherlands;application/octet-stream;downloadable_files_count: 0;Meertens Institute KNAW The Netherlands;http://www.meertens.knaw.nl/nfd/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f3cba932-fc24-5030-b7c4-86bbf1f16b8f",
-    "notes": [
-        "Enriched database of  (mainly) Dutch family names, based on 1947 census (in progress; currently 90.000 entries from 140.000 max)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-738"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Nederlandse Familienamen Databank (Dutch Database of Family Names)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f3e60d95-f18e-5df4-8d2a-6b2af3d6cbb9.json b/oaitestdata/clarin-oai_dc/SET_1/json/f3e60d95-f18e-5df4-8d2a-6b2af3d6cbb9.json
deleted file mode 100644
index b6d90cae..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f3e60d95-f18e-5df4-8d2a-6b2af3d6cbb9.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "text/plain",
-        "downloadable_files_count: 2"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1665",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1665"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1665",
-    "PublicationTimestamp": "2016-03-10T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Baran\u010d\u00edkov\u00e1, Petra",
-        "Tamchyna, Ale\u0161"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1665;2018-07-02T22:05:52Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Automatic Paraphrases of Czech Reference Sentences for WMT11, 13 and 14;Baran\u010d\u00edkov\u00e1, Petra;Tamchyna, Ale\u0161;machine translation;automatic evaluation;paraphrasing;This dataset contains automatic paraphrases of Czech official reference translations for the Workshop on Statistical Machine Translation shared task. The data covers the years 2011, 2013 and 2014.\r\n\r\nFor each sentence, at most 10000 paraphrases were included (randomly selected from the full set).\r\n\r\nThe goal of using this dataset is to improve automatic evaluation of machine translation outputs.\r\n\r\nIf you use this work, please cite the following paper:\r\n\r\nTamchyna Ale\u0161, Baran\u010d\u00edkov\u00e1 Petra: Automatic and Manual Paraphrases for MT Evaluation. In proceedings of LREC, 2016.;2016-03-10;corpus;http://hdl.handle.net/11234/1-1665;ces;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;PUB;application/x-gzip;text/plain;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/grants/deprefset",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f3e60d95-f18e-5df4-8d2a-6b2af3d6cbb9",
-    "notes": [
-        "This dataset contains automatic paraphrases of Czech official reference translations for the Workshop on Statistical Machine Translation shared task. The data covers the years 2011, 2013 and 2014.\r\n\r\nFor each sentence, at most 10000 paraphrases were included (randomly selected from the full set).\r\n\r\nThe goal of using this dataset is to improve automatic evaluation of machine translation outputs.\r\n\r\nIf you use this work, please cite the following paper:\r\n\r\nTamchyna Ale\u0161, Baran\u010d\u00edkov\u00e1 Petra: Automatic and Manual Paraphrases for MT Evaluation. In proceedings of LREC, 2016."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1665"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "automatic evaluation"
-        },
-        {
-            "name": "paraphrasing"
-        }
-    ],
-    "title": [
-        "Automatic Paraphrases of Czech Reference Sentences for WMT11, 13 and 14"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f3fa044f-52e4-5716-a3f2-0fadb9498b1b.json b/oaitestdata/clarin-oai_dc/SET_1/json/f3fa044f-52e4-5716-a3f2-0fadb9498b1b.json
deleted file mode 100644
index 9bd394de..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f3fa044f-52e4-5716-a3f2-0fadb9498b1b.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5691",
-    "MetadataAccess": [
-        "oai:ota:oucs:5691"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Royal College of Surgeons of England."
-    ],
-    "fulltext": "oai:ota:oucs:5691;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5691.xml;The case of the surgeons of London;Royal College of Surgeons of England.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f3fa044f-52e4-5716-a3f2-0fadb9498b1b",
-    "oai_identifier": [
-        "oai:ota:oucs:5691"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The case of the surgeons of London"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5691.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f409e1a8-59cd-5ca7-9982-86c32ace0791.json b/oaitestdata/clarin-oai_dc/SET_1/json/f409e1a8-59cd-5ca7-9982-86c32ace0791.json
deleted file mode 100644
index 60790167..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f409e1a8-59cd-5ca7-9982-86c32ace0791.json
+++ /dev/null
@@ -1,92 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1142",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1142"
-    ],
-    "PID": "http://hdl.handle.net/11356/1142",
-    "PublicationTimestamp": "2017-09-05T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "http://slovenscina2.0.trojina.si/arhiv/2016-2/2016-2-04/",
-        "http://nl.ijs.si/janes/viri/avtomatsko-oznaceni-korpusi/#Janes-Tweet",
-        "https://doi.org/10.1007/s10579-018-9425-z"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by-nc/4.0/"
-    ],
-    "author": [
-        "Erjavec, Toma\u017e",
-        "Ljube\u0161i\u0107, Nikola",
-        "Fi\u0161er, Darja"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1142;2018-10-24T20:53:07Z;hdl_11356_1023;hdl_11356_1024;Twitter corpus Janes-Tweet 1.0;Ljube\u0161i\u0107, Nikola;Erjavec, Toma\u017e;Fi\u0161er, Darja;computer-mediated communication;Twitter;word normalisation;tagging;lemmatisation;named entities;Janes-Tweet is an annotated corpus of almost 10 million tweets posted from 2013-06 to 2017-06 by approx. 9,000 users that tweet mostly in Slovene. The corpus is structured into individual tweets, together with their metadata. The tweets in the corpus are tokenised, sentence segmented, word normalised, morphosyntactically tagged, lemmatised and annotated with named entities. \r\nDue to Twitter terms-of-service, the corpus is distributed in an encoded version. The included tweetpub program (also available and documented on https://github.com/clarinsi/tweetpub) should be used to decode it, which it does by fetching the original tweets and applying a diff operation on the distributed corpus. Note that the retrieved corpus can have fewer tweets than the distributed version if some have been removed from Twitter by their authors in the meantime.;2017-09-05;corpus;http://hdl.handle.net/11356/1142;slv;http://slovenscina2.0.trojina.si/arhiv/2016-2/2016-2-04/;http://nl.ijs.si/janes/viri/avtomatsko-oznaceni-korpusi/#Janes-Tweet;https://doi.org/10.1007/s10579-018-9425-z;Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0);PUB;https://creativecommons.org/licenses/by-nc/4.0/;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 2;Jo\u017eef Stefan Institute;http://nl.ijs.si/janes/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f409e1a8-59cd-5ca7-9982-86c32ace0791",
-    "notes": [
-        "Janes-Tweet is an annotated corpus of almost 10 million tweets posted from 2013-06 to 2017-06 by approx. 9,000 users that tweet mostly in Slovene. The corpus is structured into individual tweets, together with their metadata. The tweets in the corpus are tokenised, sentence segmented, word normalised, morphosyntactically tagged, lemmatised and annotated with named entities. \r\nDue to Twitter terms-of-service, the corpus is distributed in an encoded version. The included tweetpub program (also available and documented on https://github.com/clarinsi/tweetpub) should be used to decode it, which it does by fetching the original tweets and applying a diff operation on the distributed corpus. Note that the retrieved corpus can have fewer tweets than the distributed version if some have been removed from Twitter by their authors in the meantime."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1142"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "computer-mediated communication"
-        },
-        {
-            "name": "Twitter"
-        },
-        {
-            "name": "word normalisation"
-        },
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "lemmatisation"
-        },
-        {
-            "name": "named entities"
-        }
-    ],
-    "title": [
-        "Twitter corpus Janes-Tweet 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f411ee0b-94ec-5b52-8e3e-e96863d6b28a.json b/oaitestdata/clarin-oai_dc/SET_1/json/f411ee0b-94ec-5b52-8e3e-e96863d6b28a.json
deleted file mode 100644
index 5423d222..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f411ee0b-94ec-5b52-8e3e-e96863d6b28a.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 71 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2155",
-    "MetadataAccess": [
-        "oai:ota:oucs:2155"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Novels"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gaskell, Elizabeth Cleghorn, 1810-1865"
-    ],
-    "fulltext": "oai:ota:oucs:2155;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/2155.xml;Lizzie Leigh / Elizabeth Gaskell;Gaskell, Elizabeth Cleghorn, 1810-1865;text_and_corpus_linguistics;English fiction -- 19th century;Oxford Text Archive, University of Oxford;Triggs, Jeffery;text/sgml;(1 file : ca. 71 KB);Text;Novels;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f411ee0b-94ec-5b52-8e3e-e96863d6b28a",
-    "oai_identifier": [
-        "oai:ota:oucs:2155"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English fiction -- th century"
-        }
-    ],
-    "title": [
-        "Lizzie Leigh / Elizabeth Gaskell"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2155.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f4276e7b-de9c-5f15-b4ea-ca75382489bb.json b/oaitestdata/clarin-oai_dc/SET_1/json/f4276e7b-de9c-5f15-b4ea-ca75382489bb.json
deleted file mode 100644
index 9bc73769..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f4276e7b-de9c-5f15-b4ea-ca75382489bb.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "text/xml",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Southern Sami",
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/96",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/96"
-    ],
-    "PID": "http://hdl.handle.net/11509/96",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Giellatekno - Saami Language Technology"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "The Divvun group at UiT The Arctic University of Norway",
-        "Giellatekno - Saami Language Technology, UiT The Arctic University of Norway"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/96;2016-09-06T13:01:21Z;hdl_11509_1;hdl_11509_2;South Saami-Swedish dictionary;Giellatekno - Saami Language Technology, UiT The Arctic University of Norway;The Divvun group at UiT The Arctic University of Norway;Bilingual Lexicon;Swedish;South Saami;Machine-readable Dictionary;The South Saami-Swedish dictionary is the work done by Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language communities. The dictionary contains 7133 entries in Giellatekno's dictionary xml format. In spite of the extensive quality control, it may contain entries with objectionable translations. If you find any errors or want to add more words, download the file, edit it, and send it back to giellatekno@uit.no and feedback@divvun.no.\r\nPlease note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata).;2015;lexicalConceptualResource;http://hdl.handle.net/11509/96;sma;swe;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;text/xml;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Giellatekno - Saami Language Technology;http://giellatekno.uit.no/index.eng.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f4276e7b-de9c-5f15-b4ea-ca75382489bb",
-    "notes": [
-        "The South Saami-Swedish dictionary is the work done by Giellatekno and Divvun research groups, Department of Linguistics, UiT The Arctic University of Norway, as well as by members of the language communities. The dictionary contains 7133 entries in Giellatekno's dictionary xml format. In spite of the extensive quality control, it may contain entries with objectionable translations. If you find any errors or want to add more words, download the file, edit it, and send it back to giellatekno@uit.no and feedback@divvun.no.\r\nPlease note that the Giellatekno resources are dynamic in nature. To ensure that you have a completely updated version, please contact Giellatekno (see Contact Info in metadata)."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/96"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Bilingual Lexicon"
-        },
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "South Saami"
-        },
-        {
-            "name": "Machine-readable Dictionary"
-        }
-    ],
-    "title": [
-        "South Saami-Swedish dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f46b641f-67ee-53d0-adf3-a2542cd82c3c.json b/oaitestdata/clarin-oai_dc/SET_1/json/f46b641f-67ee-53d0-adf3-a2542cd82c3c.json
deleted file mode 100644
index 39df17a6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f46b641f-67ee-53d0-adf3-a2542cd82c3c.json
+++ /dev/null
@@ -1,106 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "text/html",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1905",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1905"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1905",
-    "PublicationTimestamp": "2016-12-22T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11858/00-097C-0000-0023-1AAF-3",
-        "http://hdl.handle.net/11234/1-2621"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "M\u00edrovsk\u00fd, Ji\u0159\u00ed",
-        "Rysov\u00e1, Magdal\u00e9na",
-        "Pergler, Ji\u0159\u00ed",
-        "Zik\u00e1nov\u00e1, \u0160\u00e1rka",
-        "Haji\u010dov\u00e1, Eva",
-        "Scheller, Veronika",
-        "Zde\u0148kov\u00e1, Jana",
-        "Nedoluzhko, Anna",
-        "Pol\u00e1kov\u00e1, Lucie",
-        "Synkov\u00e1, Pavl\u00edna",
-        "Ocel\u00e1k, Radek"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1905;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Prague Discourse Treebank 2.0;Rysov\u00e1, Magdal\u00e9na;Synkov\u00e1, Pavl\u00edna;M\u00edrovsk\u00fd, Ji\u0159\u00ed;Haji\u010dov\u00e1, Eva;Nedoluzhko, Anna;Ocel\u00e1k, Radek;Pergler, Ji\u0159\u00ed;Pol\u00e1kov\u00e1, Lucie;Scheller, Veronika;Zde\u0148kov\u00e1, Jana;Zik\u00e1nov\u00e1, \u0160\u00e1rka;discourse;bridging relations;coreference;topic-focus articulation;treebank;dependency;tectogrammatics;PDT;PDiT 2.0 is a new version of the Prague Discourse Treebank. It contains a complex annotation of discourse phenomena enriched by the annotation of secondary connectives.;2016-12-22;corpus;http://hdl.handle.net/11234/1-1905;ces;http://hdl.handle.net/11858/00-097C-0000-0023-1AAF-3;http://hdl.handle.net/11234/1-2621;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;text/html;application/zip;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://ufal.mff.cuni.cz/pdit2.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f46b641f-67ee-53d0-adf3-a2542cd82c3c",
-    "notes": [
-        "PDiT 2.0 is a new version of the Prague Discourse Treebank. It contains a complex annotation of discourse phenomena enriched by the annotation of secondary connectives."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1905"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "discourse"
-        },
-        {
-            "name": "bridging relations"
-        },
-        {
-            "name": "coreference"
-        },
-        {
-            "name": "topic-focus articulation"
-        },
-        {
-            "name": "treebank"
-        },
-        {
-            "name": "dependency"
-        },
-        {
-            "name": "tectogrammatics"
-        },
-        {
-            "name": "PDT"
-        }
-    ],
-    "title": [
-        "Prague Discourse Treebank 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f483af46-c366-51a2-a585-00d392ed00fd.json b/oaitestdata/clarin-oai_dc/SET_1/json/f483af46-c366-51a2-a585-00d392ed00fd.json
deleted file mode 100644
index c3f249f7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f483af46-c366-51a2-a585-00d392ed00fd.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 3",
-        "application/gzip"
-    ],
-    "Language": [
-        "Bosnian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1062",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1062"
-    ],
-    "PID": "http://hdl.handle.net/11356/1062",
-    "PublicationTimestamp": "2016-05-12T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by-sa/4.0/"
-    ],
-    "author": [
-        "Klubi\u010dka, Filip",
-        "Ljube\u0161i\u0107, Nikola"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1062;2018-10-24T20:54:53Z;hdl_11356_1023;hdl_11356_1024;Bosnian web corpus bsWaC 1.1;Ljube\u0161i\u0107, Nikola;Klubi\u010dka, Filip;web corpus;tagging;lemmatisation;The Bosnian web corpus bsWaC was built by crawling the .ba top-level domain in 2014. The corpus was near-deduplicated on paragraph level, normalised via diacritic restoration, morphosyntactically annotated and lemmatised. The corpus is shuffled by paragraphs. Each paragraph contains metadata on the URL, domain and language identification (Bosnian vs. Croatian vs. Serbian).\r\n\r\nVersion 1.0 of this corpus is described in http://www.aclweb.org/anthology/W14-0405. Version 1.1 contains newer and better linguistic annotations.;2016-05-12;corpus;http://hdl.handle.net/11356/1062;bos;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);PUB;https://creativecommons.org/licenses/by-sa/4.0/;text/plain; charset=utf-8;application/gzip;application/gzip;application/gzip;downloadable_files_count: 3;Jo\u017eef Stefan Institute;http://nlp.ffzg.hr/resources/corpora/bswac/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f483af46-c366-51a2-a585-00d392ed00fd",
-    "notes": [
-        "The Bosnian web corpus bsWaC was built by crawling the .ba top-level domain in 2014. The corpus was near-deduplicated on paragraph level, normalised via diacritic restoration, morphosyntactically annotated and lemmatised. The corpus is shuffled by paragraphs. Each paragraph contains metadata on the URL, domain and language identification (Bosnian vs. Croatian vs. Serbian).\r\n\r\nVersion 1.0 of this corpus is described in http://www.aclweb.org/anthology/W14-0405. Version 1.1 contains newer and better linguistic annotations."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1062"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "web corpus"
-        },
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "lemmatisation"
-        }
-    ],
-    "title": [
-        "Bosnian web corpus bsWaC 1.1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f4870fa7-bc97-579b-97b9-930574fc08d5.json b/oaitestdata/clarin-oai_dc/SET_1/json/f4870fa7-bc97-579b-97b9-930574fc08d5.json
deleted file mode 100644
index 388f327e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f4870fa7-bc97-579b-97b9-930574fc08d5.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1399",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1399"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1399",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1399;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;pdftotext;Format conversion service: .pdf to .txt converter;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1399;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f4870fa7-bc97-579b-97b9-930574fc08d5",
-    "notes": [
-        "Format conversion service: .pdf to .txt converter"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1399"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "pdftotext"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f4a2dc0d-2b09-5922-88dc-d735248fb26f.json b/oaitestdata/clarin-oai_dc/SET_1/json/f4a2dc0d-2b09-5922-88dc-d735248fb26f.json
deleted file mode 100644
index 32e89e7b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f4a2dc0d-2b09-5922-88dc-d735248fb26f.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4406",
-    "MetadataAccess": [
-        "oai:ota:oucs:4406"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Walpole, Horace, 1717-1797."
-    ],
-    "fulltext": "oai:ota:oucs:4406;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4406.xml;The castle of Otranto: a story. Translated by William Marshal, Gent. from the original Italian of Onuphrio Muralto, ...;Walpole, Horace, 1717-1797.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f4a2dc0d-2b09-5922-88dc-d735248fb26f",
-    "oai_identifier": [
-        "oai:ota:oucs:4406"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The castle of Otranto: a story. Translated by William Marshal, Gent. from the original Italian of Onuphrio Muralto, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4406.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f4dd2c91-f9d8-5882-aa07-2c66fd497af0.json b/oaitestdata/clarin-oai_dc/SET_1/json/f4dd2c91-f9d8-5882-aa07-2c66fd497af0.json
deleted file mode 100644
index af6678d5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f4dd2c91-f9d8-5882-aa07-2c66fd497af0.json
+++ /dev/null
@@ -1,49 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4925",
-    "MetadataAccess": [
-        "oai:ota:oucs:4925"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:4925;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4925.xml;The hive of modern literature: a collection of essays, narratives, allegories, and instructive compositions; ...;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f4dd2c91-f9d8-5882-aa07-2c66fd497af0",
-    "oai_identifier": [
-        "oai:ota:oucs:4925"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The hive of modern literature: a collection of essays, narratives, allegories, and instructive compositions; ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4925.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f514e0ab-7bc3-5384-9b5c-9966e3e773ed.json b/oaitestdata/clarin-oai_dc/SET_1/json/f514e0ab-7bc3-5384-9b5c-9966e3e773ed.json
deleted file mode 100644
index 6a45beed..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f514e0ab-7bc3-5384-9b5c-9966e3e773ed.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4939",
-    "MetadataAccess": [
-        "oai:ota:oucs:4939"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Sidney, Algernon, 1622-1683."
-    ],
-    "fulltext": "oai:ota:oucs:4939;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4939.xml;Discourses concerning government: by Algernon Sidney, ... Publish'd from an original manuscript. The second edition carefully corrected. To which is added, the paper he deliver'd to the Sheriffs immediately before his death. And an alphabetical table.;Sidney, Algernon, 1622-1683.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f514e0ab-7bc3-5384-9b5c-9966e3e773ed",
-    "oai_identifier": [
-        "oai:ota:oucs:4939"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Discourses concerning government: by Algernon Sidney, ... Publish'd from an original manuscript. The second edition carefully corrected. To which is added, the paper he deliver'd to the Sheriffs immediately before his death. And an alphabetical table."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4939.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f514e73d-a0bb-580b-8ddd-96c9a17a8646.json b/oaitestdata/clarin-oai_dc/SET_1/json/f514e73d-a0bb-580b-8ddd-96c9a17a8646.json
deleted file mode 100644
index 9b3ec453..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f514e73d-a0bb-580b-8ddd-96c9a17a8646.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English",
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-44AF-C",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-44AF-C"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-44AF-C",
-    "PublicationTimestamp": "2014-02-17T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Sedl\u00e1k, Michal"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-44AF-C;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Treex::Web;Sedl\u00e1k, Michal;Treex;Perl;REST;web service;machine translation;Treex::Web is a web frontend for running Treex applications from your browser.\r\n\r\nTreex (formerly TectoMT) is a highly modular NLP framework implemented in Perl programming language. It is primarily aimed at Machine Translation, making use of the ideas and technology created during the Prague Dependency Treebank project.;2014-02-17;toolService;http://hdl.handle.net/11858/00-097C-0000-0023-44AF-C;eng;ces;downloadable_files_count: 0;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://lindat.mff.cuni.cz/services/treex-web/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f514e73d-a0bb-580b-8ddd-96c9a17a8646",
-    "notes": [
-        "Treex::Web is a web frontend for running Treex applications from your browser.\r\n\r\nTreex (formerly TectoMT) is a highly modular NLP framework implemented in Perl programming language. It is primarily aimed at Machine Translation, making use of the ideas and technology created during the Prague Dependency Treebank project."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-44AF-C"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Treex"
-        },
-        {
-            "name": "Perl"
-        },
-        {
-            "name": "REST"
-        },
-        {
-            "name": "web service"
-        },
-        {
-            "name": "machine translation"
-        }
-    ],
-    "title": [
-        "Treex::Web"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f515b7f2-ffda-55d4-a774-c23959680f93.json b/oaitestdata/clarin-oai_dc/SET_1/json/f515b7f2-ffda-55d4-a774-c23959680f93.json
deleted file mode 100644
index 723b4a18..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f515b7f2-ffda-55d4-a774-c23959680f93.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-940",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-940"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-940",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-940;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Middle Low German;ca. 100.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-940;deu;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#mndt",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f515b7f2-ffda-55d4-a774-c23959680f93",
-    "notes": [
-        "ca. 100.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-940"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Middle Low German"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f525d7f2-ce04-5b40-b49b-514547369253.json b/oaitestdata/clarin-oai_dc/SET_1/json/f525d7f2-ce04-5b40-b49b-514547369253.json
deleted file mode 100644
index e0ba9722..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f525d7f2-ce04-5b40-b49b-514547369253.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3820",
-    "MetadataAccess": [
-        "oai:ota:oucs:3820"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Kenrick, W. (William), 1725?-1779."
-    ],
-    "fulltext": "oai:ota:oucs:3820;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3820.xml;An address to the artists and manufacturers of Great Britain; respecting an application to Parliament for the farther encouragement of new discoveries and inventions in the useful arts; ... By W. Kenrick, LL.D;Kenrick, W. (William), 1725?-1779.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f525d7f2-ce04-5b40-b49b-514547369253",
-    "oai_identifier": [
-        "oai:ota:oucs:3820"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An address to the artists and manufacturers of Great Britain; respecting an application to Parliament for the farther encouragement of new discoveries and inventions in the useful arts; ... By W. Kenrick, LL.D"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3820.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f52918b5-df09-5a30-8489-dd0d41c219b1.json b/oaitestdata/clarin-oai_dc/SET_1/json/f52918b5-df09-5a30-8489-dd0d41c219b1.json
deleted file mode 100644
index d771c4a1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f52918b5-df09-5a30-8489-dd0d41c219b1.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/119",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/119"
-    ],
-    "PID": "http://hdl.handle.net/10794/119",
-    "PublicationTimestamp": "2018-09-10T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "Olsson, Leif-J\u00f6ran",
-        "Dann\u00e9lls, Dana"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/119;2018-09-12T16:57:42Z;hdl_10794_1;hdl_10794_2;Swedish Blackletter OCR Evaluation Material 2018;Svensk frakturtext f\u00f6r OCR-utv\u00e4rdering 2018;Dann\u00e9lls, Dana;Olsson, Leif-J\u00f6ran;Swedish;OCR;Blackletter;transcription;Swedish Blackletter OCR Evaluation Material 2018. Images by GUB, transcriptions by authors.;Svensk frakturtext f\u00f6r OCR-utv\u00e4rdering 2018. Bilder fr\u00e5n GUB, transkription av f\u00f6rfattarna.;2018-09-10;corpus;http://hdl.handle.net/10794/119;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;http://creativecommons.org/licenses/by/4.0/;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Spr\u00e5kbanken, University of Gothenburg",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f52918b5-df09-5a30-8489-dd0d41c219b1",
-    "notes": [
-        "Swedish Blackletter OCR Evaluation Material 2018. Images by GUB, transcriptions by authors.",
-        "Svensk frakturtext f\u00f6r OCR-utv\u00e4rdering 2018. Bilder fr\u00e5n GUB, transkription av f\u00f6rfattarna."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/119"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "OCR"
-        },
-        {
-            "name": "Blackletter"
-        },
-        {
-            "name": "transcription"
-        }
-    ],
-    "title": [
-        "Swedish Blackletter OCR Evaluation Material 2018",
-        "Svensk frakturtext f\u00f6r OCR-utv\u00e4rdering 2018"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f53031b9-5c3a-5917-86ad-952954b31be8.json b/oaitestdata/clarin-oai_dc/SET_1/json/f53031b9-5c3a-5917-86ad-952954b31be8.json
deleted file mode 100644
index 673058f5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f53031b9-5c3a-5917-86ad-952954b31be8.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Center of Computational Linguistics, Vytautas Magnus University"
-    ],
-    "Contributor": [
-        "Utka, dr. Andrius"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/xml"
-    ],
-    "Language": [
-        "Czech",
-        "English",
-        "Lithuanian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-624",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-624"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-624",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Center of Computational Linguistics, Vytautas Magnus University"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Lithuania"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-624;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Bilingual English-Lithuanian, Lithuanian-English, Czech-Lithuanian, Lithuanian-Czech corpora;Utka, dr. Andrius;A collection of parallel corpora: English-Lithuanian (2m words), Lithuanian-English (0,06m words), Czech-Lithuanian (0,8m words), Lithuanian-Czech (0,02m words). All the corpora are online-searcheable via one interface at http://donelaitis.vdu.lt/main_en.php?id=4&nr=1_2. The corpus is still being updated with new texts.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-624;ces;eng;lit;application/xml;downloadable_files_count: 0;Lithuania;Center of Computational Linguistics, Vytautas Magnus University;http://tekstynas.vdu.lt/page.xhtml;?id=parallelCorpus",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f53031b9-5c3a-5917-86ad-952954b31be8",
-    "notes": [
-        "A collection of parallel corpora: English-Lithuanian (2m words), Lithuanian-English (0,06m words), Czech-Lithuanian (0,8m words), Lithuanian-Czech (0,02m words). All the corpora are online-searcheable via one interface at http://donelaitis.vdu.lt/main_en.php?id=4&nr=1_2. The corpus is still being updated with new texts."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-624"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Bilingual English-Lithuanian, Lithuanian-English, Czech-Lithuanian, Lithuanian-Czech corpora"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f535f84a-f442-5d8d-9b08-993365482fd0.json b/oaitestdata/clarin-oai_dc/SET_1/json/f535f84a-f442-5d8d-9b08-993365482fd0.json
deleted file mode 100644
index 7e6fb428..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f535f84a-f442-5d8d-9b08-993365482fd0.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Anna Niepytalska-Osiecka"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 53",
-        "text/plain",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/439",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/439"
-    ],
-    "PID": "http://hdl.handle.net/11321/439",
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Anna Niepytalska-Osiecka"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Niepytalska-Osiecka, Anna"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/439;2017-11-14T19:36:44Z;hdl_11321_3;hdl_11321_4;Feminism;Niepytalska-Osiecka, Anna;feminist;feminism;How do Poles understand the concepts of feminism and feminist and how do they use these terms? Reconnaissance.;2017;corpus;http://hdl.handle.net/11321/439;Polish;Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0);http://creativecommons.org/licenses/by-nc-nd/3.0/;CC;text/plain; charset=utf-8;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;application/zip;application/zip;downloadable_files_count: 53;Anna Niepytalska-Osiecka;https://www.researchgate.net/project/How-do-Poles-understand-the-concepts-of-feminism-and-feminist-and-how-do-they-use-these-terms-Reconnaissance",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f535f84a-f442-5d8d-9b08-993365482fd0",
-    "notes": [
-        "How do Poles understand the concepts of feminism and feminist and how do they use these terms? Reconnaissance."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/439"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "feminist"
-        },
-        {
-            "name": "feminism"
-        }
-    ],
-    "title": [
-        "Feminism"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f541ea56-dda6-5e2c-b0da-804fa0b71522.json b/oaitestdata/clarin-oai_dc/SET_1/json/f541ea56-dda6-5e2c-b0da-804fa0b71522.json
deleted file mode 100644
index 19997f72..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f541ea56-dda6-5e2c-b0da-804fa0b71522.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Piotra Dufoura"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-159646",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-159646"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CE5-1",
-    "PublicationTimestamp": "1776-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1776"
-    ],
-    "Publisher": [
-        "Drukarnia Piotra Dufoura"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/159646",
-        "oai:jbc.bj.uj.edu.pl:publication:167980"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1701/1800"
-    ],
-    "TempCoverageBegin": 53662478399,
-    "TempCoverageEnd": 53662478399,
-    "TemporalCoverage": " point in time : 1701-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1701-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1701-07-01T11:59:59Z",
-    "author": [
-        "Lipski, Tadeusz (1725-1796)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-159646;2019-02-28T18:39:41Z;Mowa J. W. Jmci Pana Lipskiego, Kasztelana \u0141\u0119czyckiego Na Sessyi Seymowey Dnia 28. Sierpnia 1776. Miana. : [Inc.:] Przypadek bez przyk\u0142adu Rzpltey naszey daie nam s\u0142ysze\u0107 [...];Lipski, Tadeusz (1725-1796);starodruki 18\u00a0w.;Drukarnia Piotra Dufoura;1776;starodruk;application/xml;clarind-uds:poldilemma-159646;hdl:11858/00-246C-0000-0023-8CE5-1;Biblioteka Jagiello\u0144ska, BJ St. Dr. 9096 III/3;pol;http://jbc.bj.uj.edu.pl/Content/159646;oai:jbc.bj.uj.edu.pl:publication:167980;1701/1800;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f541ea56-dda6-5e2c-b0da-804fa0b71522",
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-159646"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Mowa J. W. Jmci Pana Lipskiego, Kasztelana \u0141\u0119czyckiego Na Sessyi Seymowey Dnia 28. Sierpnia 1776. Miana. : [Inc.:] Przypadek bez przyk\u0142adu Rzpltey naszey daie nam s\u0142ysze\u0107 [...]"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f545e4ff-e0ee-53d7-ab98-eb9ebd5238a1.json b/oaitestdata/clarin-oai_dc/SET_1/json/f545e4ff-e0ee-53d7-ab98-eb9ebd5238a1.json
deleted file mode 100644
index 6d8bfba6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f545e4ff-e0ee-53d7-ab98-eb9ebd5238a1.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2709",
-    "MetadataAccess": [
-        "oai:ota:oucs:2709"
-    ],
-    "PublicationTimestamp": "1765-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1765"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2709;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2709.xml;Hints on good manners;Swift, Jonathan, 1667-1745;1765;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f545e4ff-e0ee-53d7-ab98-eb9ebd5238a1",
-    "oai_identifier": [
-        "oai:ota:oucs:2709"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Hints on good manners"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2709.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f55dfba2-a098-5f4c-9316-34cdb0c20de3.json b/oaitestdata/clarin-oai_dc/SET_1/json/f55dfba2-a098-5f4c-9316-34cdb0c20de3.json
deleted file mode 100644
index 24b20981..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f55dfba2-a098-5f4c-9316-34cdb0c20de3.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Department of Trade and Industry"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "185 files: ca. 62.1 MB",
-        "text/xml"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2551",
-    "MetadataAccess": [
-        "oai:ota:oucs:2551"
-    ],
-    "PublicationTimestamp": "1991-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1991"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Linguistic corpora"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under the BNC User Licence. Clicking to download implies acceptance of the licence conditions.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "BNC Consortium"
-    ],
-    "fulltext": "oai:ota:oucs:2551;2018-12-04T13:04:33Z;http://ota.ox.ac.uk/headers/2551.xml;British National Corpus Sampler;BNC Sampler;BNC Consortium;1991-1994;text_and_corpus_linguistics;Linguistics;Linguistics analysis (Linguistics);eng; The BNC Sampler is a subset of the full BNC. It comprises two samples of written and spoken material of one million words each, compiled to mirror the composition of the full BNC as far as possible. The word-class annotation of the BNC Sampler texts has been carefully checked and manually corrected. The Sampler was first created at Lancaster University during the creation of the BNC. More information about the Sampler can be found in the users reference guide for the BNC Sampler: XML Edition [.pdf file]  British National Corpus is a snapshot of British English in the early 1990s. The British National Corpus is: a sample corpus: composed of text samples generally no longer than 45,000 words.a synchronic corpus: the corpus includes imaginative texts from 1960, informative texts from 1975.a general corpus: not specifically restricted to any particular subject field, register or genre.a monolingual British English corpus: it comprises text samples which are substantially the product of speakers of British English.a mixed corpus: it contains examples of both spoken and written language.  The corpus is described in full in the Users Reference Guide at BNC User Reference Guide.  ;Oxford Text Archive, University of Oxford;Department of Trade and Industry;text/xml;185 files: ca. 62.1 MB;Text;Linguistic corpora;Distributed by the University of Oxford under the BNC User Licence. Clicking to download implies acceptance of the licence conditions.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f55dfba2-a098-5f4c-9316-34cdb0c20de3",
-    "notes": [
-        " The BNC Sampler is a subset of the full BNC. It comprises two samples of written and spoken material of one million words each, compiled to mirror the composition of the full BNC as far as possible. The word-class annotation of the BNC Sampler texts has been carefully checked and manually corrected. The Sampler was first created at Lancaster University during the creation of the BNC. More information about the Sampler can be found in the users reference guide for the BNC Sampler: XML Edition [.pdf file]  British National Corpus is a snapshot of British English in the early 1990s. The British National Corpus is: a sample corpus: composed of text samples generally no longer than 45,000 words.a synchronic corpus: the corpus includes imaginative texts from 1960, informative texts from 1975.a general corpus: not specifically restricted to any particular subject field, register or genre.a monolingual British English corpus: it comprises text samples which are substantially the product of speakers of British English.a mixed corpus: it contains examples of both spoken and written language.  The corpus is described in full in the Users Reference Guide at BNC User Reference Guide.  "
-    ],
-    "oai_identifier": [
-        "oai:ota:oucs:2551"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Linguistics"
-        },
-        {
-            "name": "Linguistics analysis Linguistics"
-        }
-    ],
-    "title": [
-        "British National Corpus Sampler",
-        "BNC Sampler"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2551.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f5694dfa-89ba-5ba0-8362-87094c62deb7.json b/oaitestdata/clarin-oai_dc/SET_1/json/f5694dfa-89ba-5ba0-8362-87094c62deb7.json
deleted file mode 100644
index 407db68b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f5694dfa-89ba-5ba0-8362-87094c62deb7.json
+++ /dev/null
@@ -1,101 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 4",
-        "application/pdf",
-        "application/zip"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1086",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1086"
-    ],
-    "PID": "http://hdl.handle.net/11356/1086",
-    "PublicationTimestamp": "2017-01-03T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "http://nl.ijs.si/janes/viri/rocno-oznaceni-korpusi/#Janes-Syn",
-        "https://doi.org/10.1007/s10579-018-9425-z"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by-sa/4.0/"
-    ],
-    "author": [
-        "Arhar Holdt, \u0160pela",
-        "Fi\u0161er, Darja",
-        "Erjavec, Toma\u017e"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1086;2018-10-24T20:52:29Z;hdl_11356_1023;hdl_11356_1024;CMC training corpus Janes-Syn 1.0;Arhar Holdt, \u0160pela;Erjavec, Toma\u017e;Fi\u0161er, Darja;computer-mediated communication;tokenisation;word normalisation;tagging;lemmatisation;dependency treebank;syntactic annotation;manual annotation;TEI;Janes-Syn is a syntactically annotated corpus of Slovene tweets and is meant as a gold-standard training and testing dataset for syntactic annotation of Slovene computer-mediated communication and for detailed linguistic explorations which require highly accurate and reliable annotations. Words in the dataset are normalised, lemmatised, PoS-tagged and syntactically annotated with the JOS dependency model (http://eng.slovenscina.eu/tehnologije/razclenjevalnik). The annotations on all levels were manually corrected. \r\n\r\nThe corpus creation and structure are described in:\r\nARHAR HOLDT, \u0160pela, FI\u0160ER, Darja, ERJAVEC, Toma\u017e, KREK, Simon. Syntactic annotation of Slovene CMC : first steps. Proceedings of the 4th Conference on CMC and Social Media Corpora for the Humanities, 27-28 September 2016, Ljubljana, Slovenia, 2016, pp. 3-6. http://nl.ijs.si/janes/cmc-corpora2016/proceedings/\r\n\r\nJanes-Syn was created from two larger corpora that are also available in the repository: Janes-Norm (http://hdl.handle.net/11356/1084) and Janes-Tag (http://hdl.handle.net/11356/1123).;2017-01-03;corpus;http://hdl.handle.net/11356/1086;slv;http://nl.ijs.si/janes/viri/rocno-oznaceni-korpusi/#Janes-Syn;https://doi.org/10.1007/s10579-018-9425-z;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);PUB;https://creativecommons.org/licenses/by-sa/4.0/;text/plain; charset=utf-8;application/pdf;application/pdf;application/zip;application/zip;downloadable_files_count: 4;Jo\u017eef Stefan Institute;http://nl.ijs.si/janes/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f5694dfa-89ba-5ba0-8362-87094c62deb7",
-    "notes": [
-        "Janes-Syn is a syntactically annotated corpus of Slovene tweets and is meant as a gold-standard training and testing dataset for syntactic annotation of Slovene computer-mediated communication and for detailed linguistic explorations which require highly accurate and reliable annotations. Words in the dataset are normalised, lemmatised, PoS-tagged and syntactically annotated with the JOS dependency model (http://eng.slovenscina.eu/tehnologije/razclenjevalnik). The annotations on all levels were manually corrected. \r\n\r\nThe corpus creation and structure are described in:\r\nARHAR HOLDT, \u0160pela, FI\u0160ER, Darja, ERJAVEC, Toma\u017e, KREK, Simon. Syntactic annotation of Slovene CMC : first steps. Proceedings of the 4th Conference on CMC and Social Media Corpora for the Humanities, 27-28 September 2016, Ljubljana, Slovenia, 2016, pp. 3-6. http://nl.ijs.si/janes/cmc-corpora2016/proceedings/\r\n\r\nJanes-Syn was created from two larger corpora that are also available in the repository: Janes-Norm (http://hdl.handle.net/11356/1084) and Janes-Tag (http://hdl.handle.net/11356/1123)."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1086"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "computer-mediated communication"
-        },
-        {
-            "name": "tokenisation"
-        },
-        {
-            "name": "word normalisation"
-        },
-        {
-            "name": "tagging"
-        },
-        {
-            "name": "lemmatisation"
-        },
-        {
-            "name": "dependency treebank"
-        },
-        {
-            "name": "syntactic annotation"
-        },
-        {
-            "name": "manual annotation"
-        },
-        {
-            "name": "TEI"
-        }
-    ],
-    "title": [
-        "CMC training corpus Janes-Syn 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f5729a07-d6dc-5226-9e32-10a3a1fff21c.json b/oaitestdata/clarin-oai_dc/SET_1/json/f5729a07-d6dc-5226-9e32-10a3a1fff21c.json
deleted file mode 100644
index 1303e22b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f5729a07-d6dc-5226-9e32-10a3a1fff21c.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3538",
-    "MetadataAccess": [
-        "oai:ota:oucs:3538"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Goldsmith, Oliver, 1730?-1774."
-    ],
-    "fulltext": "oai:ota:oucs:3538;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3538.xml;The good natur'd man: a comedy. As performed at the Theatre-Royal in Covent-Garden. By Mr. Goldsmith.;Goldsmith, Oliver, 1730?-1774.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f5729a07-d6dc-5226-9e32-10a3a1fff21c",
-    "oai_identifier": [
-        "oai:ota:oucs:3538"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The good natur'd man: a comedy. As performed at the Theatre-Royal in Covent-Garden. By Mr. Goldsmith."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3538.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f5a040a9-bcd0-5419-b786-004974bdc9ad.json b/oaitestdata/clarin-oai_dc/SET_1/json/f5a040a9-bcd0-5419-b786-004974bdc9ad.json
deleted file mode 100644
index ff23ade6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f5a040a9-bcd0-5419-b786-004974bdc9ad.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2642",
-    "MetadataAccess": [
-        "oai:ota:oucs:2642"
-    ],
-    "PublicationTimestamp": "1713-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1713"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2642;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2642.xml;A preface to the Bishop of Sarum's introduction;Swift, Jonathan, 1667-1745;1713;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f5a040a9-bcd0-5419-b786-004974bdc9ad",
-    "oai_identifier": [
-        "oai:ota:oucs:2642"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A preface to the Bishop of Sarum's introduction"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2642.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f5b9aad9-7b8f-5d6a-b4d5-f929acba0642.json b/oaitestdata/clarin-oai_dc/SET_1/json/f5b9aad9-7b8f-5d6a-b4d5-f929acba0642.json
deleted file mode 100644
index eccdafec..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f5b9aad9-7b8f-5d6a-b4d5-f929acba0642.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=e43e1e786c0011e2a2aa782bcb0741354f6d3f05c0974effa8d92ddf1f26f25d",
-    "MetadataAccess": [
-        "e43e1e786c0011e2a2aa782bcb0741354f6d3f05c0974effa8d92ddf1f26f25d"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "e43e1e786c0011e2a2aa782bcb0741354f6d3f05c0974effa8d92ddf1f26f25d;2018-11-15T16:40:08Z;toolService;toolService:service;U-Compare Lemmatisation service;Web service created by exporting UIMA-based workflow from the U-Compare text mining system.\nFunctionality: Identifies sentences and tokens in plain text. Parts of speech and lemmas are assigned to tokens. Language is automatically identified amongst the supported languages and language-specific processing is carried out. \nTools in workflow: Language Identifier, TTL-Tokenizer, TTL-Tagger, TTL-Lemmmatizer (all provided by the Research Institute for Artificial Intelligence (RACAI), Romania)\nNOTE: The licence provided covers the web service only. Tools used to create the workflow may have their own licences\n;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f5b9aad9-7b8f-5d6a-b4d5-f929acba0642",
-    "notes": [
-        "Web service created by exporting UIMA-based workflow from the U-Compare text mining system.\nFunctionality: Identifies sentences and tokens in plain text. Parts of speech and lemmas are assigned to tokens. Language is automatically identified amongst the supported languages and language-specific processing is carried out. \nTools in workflow: Language Identifier, TTL-Tokenizer, TTL-Tagger, TTL-Lemmmatizer (all provided by the Research Institute for Artificial Intelligence (RACAI), Romania)\nNOTE: The licence provided covers the web service only. Tools used to create the workflow may have their own licences\n"
-    ],
-    "oai_identifier": [
-        "e43e1e786c0011e2a2aa782bcb0741354f6d3f05c0974effa8d92ddf1f26f25d"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:service"
-    ],
-    "state": "active",
-    "title": [
-        "U-Compare Lemmatisation service"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f5bf93a5-842d-5b44-840d-645095410ff9.json b/oaitestdata/clarin-oai_dc/SET_1/json/f5bf93a5-842d-5b44-840d-645095410ff9.json
deleted file mode 100644
index e7123f53..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f5bf93a5-842d-5b44-840d-645095410ff9.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia Collegium Kaliskiego"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/pdf"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-184",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-184"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CF4-0",
-    "PublicationTimestamp": "1718-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1718"
-    ],
-    "Publisher": [
-        "Drukarnia Collegium Kaliskiego"
-    ],
-    "RelatedIdentifier": [
-        "http://pbc.biaman.pl/Content/184"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "author": [
-        "Za\u0142uski, Andrzej Chryzostom (ca 1648 - 1711)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-184;2019-03-01T11:03:49Z;Mowy seymowe Ja\u015bnie O\u015bwieconego Xi\u0105z\u0119cia biskupa warminskiego Andrzeja Chryzostoma , na Za\u0142uskach y B\u0142\u0119dowie Za\u0142uskiego kanclerza wielkiego koronnego przy publicznych Oyczyzny obradach miane.;Za\u0142uski, Andrzej Chryzostom (ca 1648 - 1711);Mowy polskie 18 w.;ilo\u015b\u0107 skan\u00f3w: 238 ; sygn. St-297;Drukarnia Collegium Kaliskiego;1718;starodruk;application/pdf;clarind-uds:poldilemma-184;hdl:11858/00-246C-0000-0023-8CF4-0;pol;lat;http://pbc.biaman.pl/Content/184;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f5bf93a5-842d-5b44-840d-645095410ff9",
-    "notes": [
-        "ilo\u015b\u0107 skan\u00f3w: 238 ; sygn. St-297"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-184"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Mowy polskie w."
-        }
-    ],
-    "title": [
-        "Mowy seymowe Ja\u015bnie O\u015bwieconego Xi\u0105z\u0119cia biskupa warminskiego Andrzeja Chryzostoma , na Za\u0142uskach y B\u0142\u0119dowie Za\u0142uskiego kanclerza wielkiego koronnego przy publicznych Oyczyzny obradach miane."
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f5c32124-ae88-52d8-82d9-8acec7e15c59.json b/oaitestdata/clarin-oai_dc/SET_1/json/f5c32124-ae88-52d8-82d9-8acec7e15c59.json
deleted file mode 100644
index 155a9aa2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f5c32124-ae88-52d8-82d9-8acec7e15c59.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Budapest University of Technology and Economics Media Research (BME MOKK)"
-    ],
-    "Contributor": [
-        "Halacsy, Peter"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Hungarian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-467",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-467"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-467",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Budapest University of Technology and Economics Media Research (BME MOKK)"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Hungary"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-467;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Morphdb.hu;Halacsy, Peter;100,000 lemmas;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-467;hun;downloadable_files_count: 0;Hungary;Budapest University of Technology and Economics Media Research (BME MOKK);http://mokk.bme.hu/resources/morphdb.hu",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f5c32124-ae88-52d8-82d9-8acec7e15c59",
-    "notes": [
-        "100,000 lemmas"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-467"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Morphdb.hu"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f5cc4dbc-b5d4-5749-8b19-5b58613b816a.json b/oaitestdata/clarin-oai_dc/SET_1/json/f5cc4dbc-b5d4-5749-8b19-5b58613b816a.json
deleted file mode 100644
index cedf6bf4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f5cc4dbc-b5d4-5749-8b19-5b58613b816a.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "asd"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/vnd.oasis.opendocument.text",
-        "application/zip",
-        "downloadable_files_count: 12",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/401",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/401"
-    ],
-    "PID": "http://hdl.handle.net/11321/401",
-    "PublicationTimestamp": "2017-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "asd"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "asd, asd"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/401;2017-06-29T14:00:00Z;hdl_11321_3;hdl_11321_4;Corpus IPI PAN;asd, asd;corpus;opis;2017-05-30;corpus;http://hdl.handle.net/11321/401;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;application/vnd.oasis.opendocument.text;application/msword;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;application/vnd.oasis.opendocument.text;application/zip;application/zip;downloadable_files_count: 12;asd",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f5cc4dbc-b5d4-5749-8b19-5b58613b816a",
-    "notes": [
-        "opis"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/401"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        }
-    ],
-    "title": [
-        "Corpus IPI PAN"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f5cc8398-1afd-5bdb-aa10-d9652a17770a.json b/oaitestdata/clarin-oai_dc/SET_1/json/f5cc8398-1afd-5bdb-aa10-d9652a17770a.json
deleted file mode 100644
index e04c3d2c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f5cc8398-1afd-5bdb-aa10-d9652a17770a.json
+++ /dev/null
@@ -1,92 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/270",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/270"
-    ],
-    "PID": "http://hdl.handle.net/11321/270",
-    "PublicationTimestamp": "2016-04-25T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0)",
-        "http://creativecommons.org/licenses/by-sa/3.0/",
-        "CC"
-    ],
-    "author": [
-        "K\u0119dzia, Pawe\u0142",
-        "Maziarz, Marek",
-        "Koco\u0144, Jan",
-        "Wieczorek, Jan",
-        "Marci\u0144czuk, Micha\u0142",
-        "Turek, Agnieszka",
-        "Wolski, Micha\u0142",
-        "Oleksy, Marcin",
-        "Berna\u015b, Tomasz",
-        "Fikus, Dominika"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/270;2019-02-20T11:58:21Z;hdl_11321_3;hdl_11321_4;Polish Corpus of Wroc\u0142aw University of Technology 1.2;Korpus J\u0119zyka Polskiego Politechniki Wroc\u0142awskiej (KPWr) 1.2;Marci\u0144czuk, Micha\u0142;Oleksy, Marcin;Maziarz, Marek;Wieczorek, Jan;Fikus, Dominika;Turek, Agnieszka;Wolski, Micha\u0142;Berna\u015b, Tomasz;Koco\u0144, Jan;K\u0119dzia, Pawe\u0142;corpora;corpus;KPWr;text corpus;manually annotated corpus;KPWr (Polish Corpus of Wroc\u0142aw University of Technology, pol. Korpus J\u0119zyka Polskiego Politechniki Wroc\u0142awskiej) is a corpus of written and spoken documents available on the Creative Common license. The texts are divided into 15 subcorpuses (blogs, science, stenographic recordings, etc.). The documents are annotated on the level of chunks and selected predicate-argument relations, named entities, relations between named entities, anaphora relations, word senses, events, temporal expressions, spatial relations between entities, keywords and semantic roles within nominal and adjective phrases;2016-04-25;corpus;http://hdl.handle.net/11321/270;pol;Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0);http://creativecommons.org/licenses/by-sa/3.0/;CC;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 1;Wroc\u0142aw University of Technology;http://nlp.pwr.wroc.pl/en/tools-and-resources/resources/kpwr",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f5cc8398-1afd-5bdb-aa10-d9652a17770a",
-    "notes": [
-        "KPWr (Polish Corpus of Wroc\u0142aw University of Technology, pol. Korpus J\u0119zyka Polskiego Politechniki Wroc\u0142awskiej) is a corpus of written and spoken documents available on the Creative Common license. The texts are divided into 15 subcorpuses (blogs, science, stenographic recordings, etc.). The documents are annotated on the level of chunks and selected predicate-argument relations, named entities, relations between named entities, anaphora relations, word senses, events, temporal expressions, spatial relations between entities, keywords and semantic roles within nominal and adjective phrases"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/270"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpora"
-        },
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "KPWr"
-        },
-        {
-            "name": "text corpus"
-        },
-        {
-            "name": "manually annotated corpus"
-        }
-    ],
-    "title": [
-        "Polish Corpus of Wroc\u0142aw University of Technology 1.2",
-        "Korpus J\u0119zyka Polskiego Politechniki Wroc\u0142awskiej (KPWr) 1.2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f5d0f97d-5042-5ba8-924d-295f6f88540c.json b/oaitestdata/clarin-oai_dc/SET_1/json/f5d0f97d-5042-5ba8-924d-295f6f88540c.json
deleted file mode 100644
index 21d4b55a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f5d0f97d-5042-5ba8-924d-295f6f88540c.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "Contributor": [
-        "Torner, Sergi"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-700",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-700"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-700",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-700;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Corpus PAAU 92;Torner, Sergi;The electronic version of the book \u201cCorpus PAAU 1992: Descriptive Studies, Texts and Vocabulary\u201d includes the texts that have been object of analysis in this project as well as the vocabulary lists that make up the Corpus 92.;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-700;spa;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra;http://www.iula.upf.edu/rec/corpus92/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f5d0f97d-5042-5ba8-924d-295f6f88540c",
-    "notes": [
-        "The electronic version of the book \u201cCorpus PAAU 1992: Descriptive Studies, Texts and Vocabulary\u201d includes the texts that have been object of analysis in this project as well as the vocabulary lists that make up the Corpus 92."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-700"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus PAAU 92"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f5d42741-7ed2-5f8c-b1bf-1e8937c38fff.json b/oaitestdata/clarin-oai_dc/SET_1/json/f5d42741-7ed2-5f8c-b1bf-1e8937c38fff.json
deleted file mode 100644
index 2f868bb5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f5d42741-7ed2-5f8c-b1bf-1e8937c38fff.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Centre for Language and Speech Technology, Radboud University"
-    ],
-    "Contributor": [
-        "Scharenborg, Odette"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1197",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1197"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1197",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Centre for Language and Speech Technology, Radboud University"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1197;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Fine-Tracker;Scharenborg, Odette;Computational model of human word recognition; Fine-phonetic detail;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1197;downloadable_files_count: 0;Netherlands (the);Centre for Language and Speech Technology, Radboud University;http://www.finetracker.org/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f5d42741-7ed2-5f8c-b1bf-1e8937c38fff",
-    "notes": [
-        "Computational model of human word recognition; Fine-phonetic detail"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1197"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Fine-Tracker"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f5e6a630-d855-598e-a94e-4d5f180f748d.json b/oaitestdata/clarin-oai_dc/SET_1/json/f5e6a630-d855-598e-a94e-4d5f180f748d.json
deleted file mode 100644
index a699ee8d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f5e6a630-d855-598e-a94e-4d5f180f748d.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/27",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/27"
-    ],
-    "PID": "http://hdl.handle.net/11321/27",
-    "PublicationTimestamp": "2011-11-02T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Janicki, Maciej",
-        "Krautforst, Micha\u0142",
-        "Marci\u0144czuk, Micha\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/27;2016-01-19T13:31:50Z;hdl_11321_3;hdl_11321_4;NER WS;Janicki, Maciej;Krautforst, Micha\u0142;Marci\u0144czuk, Micha\u0142;Web service for Liner2;2011-11-02;toolService;http://hdl.handle.net/11321/27;pol;downloadable_files_count: 0;Wroc\u0142aw University of Technology;http://www.clarin-pl.eu/demo/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f5e6a630-d855-598e-a94e-4d5f180f748d",
-    "notes": [
-        "Web service for Liner2"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/27"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "NER WS"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f6396551-bec0-50ef-a56b-e47fa70a0305.json b/oaitestdata/clarin-oai_dc/SET_1/json/f6396551-bec0-50ef-a56b-e47fa70a0305.json
deleted file mode 100644
index d8c62a83..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f6396551-bec0-50ef-a56b-e47fa70a0305.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/231",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/231"
-    ],
-    "PID": "http://hdl.handle.net/11321/231",
-    "PublicationTimestamp": "2015-10-30T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Janicki, Maciej",
-        "Koco\u0144, Jan",
-        "Marci\u0144czuk, Micha\u0142",
-        "Piasecki, Dominik",
-        "Kaczmarek, Adam",
-        "Krautforst, Micha\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/231;2016-06-06T11:03:16Z;hdl_11321_3;hdl_11321_4;Liner2.5 rc3;Marci\u0144czuk, Micha\u0142;Koco\u0144, Jan;Krautforst, Micha\u0142;Kaczmarek, Adam;Janicki, Maciej;Piasecki, Dominik;NER;Timex;A framework for multitask sequence labeling dedicated for natural language processing tasks.;2015-10-30;toolService;http://hdl.handle.net/11321/231;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;Wroc\u0142aw University of Technology;http://nlp.pwr.wroc.pl/liner2",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f6396551-bec0-50ef-a56b-e47fa70a0305",
-    "notes": [
-        "A framework for multitask sequence labeling dedicated for natural language processing tasks."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/231"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "NER"
-        },
-        {
-            "name": "Timex"
-        }
-    ],
-    "title": [
-        "Liner2.5 rc3"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f67dafe2-5827-553a-9020-9cf93637db6f.json b/oaitestdata/clarin-oai_dc/SET_1/json/f67dafe2-5827-553a-9020-9cf93637db6f.json
deleted file mode 100644
index b55e125c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f67dafe2-5827-553a-9020-9cf93637db6f.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 68.8 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2268",
-    "MetadataAccess": [
-        "oai:ota:oucs:2268"
-    ],
-    "PublicationTimestamp": "1739-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1739"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Hanmer, Thomas, Sir, 1677-1746",
-        "Hervey, Thomas, 1699-1775",
-        "Hanmer, Elizabeth Folkes, Lady, d. 1741"
-    ],
-    "fulltext": "oai:ota:oucs:2268;2018-10-16T10:41:13Z;http://ota.ox.ac.uk/headers/2268.xml;A letter from the Hon. Thomas Hervey to Sir Thomas Hanmer : containing a letter from Lady Hanmer to Sir Thomas;Hervey, Thomas, 1699-1775;Hanmer, Thomas, Sir, 1677-1746;Hanmer, Elizabeth Folkes, Lady, d. 1741;1739;text_and_corpus_linguistics;Letters -- Great Britain -- 18th century;eng;Oxford Text Archive, University of Oxford;(1 file : ca. 68.8 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f67dafe2-5827-553a-9020-9cf93637db6f",
-    "oai_identifier": [
-        "oai:ota:oucs:2268"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Letters -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "A letter from the Hon. Thomas Hervey to Sir Thomas Hanmer : containing a letter from Lady Hanmer to Sir Thomas"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2268.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f6917af8-1ffa-560a-af1a-690caf4ca849.json b/oaitestdata/clarin-oai_dc/SET_1/json/f6917af8-1ffa-560a-af1a-690caf4ca849.json
deleted file mode 100644
index edf0c2e3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f6917af8-1ffa-560a-af1a-690caf4ca849.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Wikipedia"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 500",
-        "text/plain"
-    ],
-    "Language": [],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/215",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/215"
-    ],
-    "PID": "http://hdl.handle.net/11321/215",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Wikipedia"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Wikipedia"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/215;2015-06-10T14:27:12Z;hdl_11321_3;hdl_11321_4;Wiki train;Wikipedia;Wikipedia, kategorie Szachy i Samochody do uczenia klasyfikatora;2015;corpus;http://hdl.handle.net/11321/215;polski;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain; charset=utf-8;downloadable_files_count: 500;Wikipedia",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f6917af8-1ffa-560a-af1a-690caf4ca849",
-    "notes": [
-        "Wikipedia, kategorie Szachy i Samochody do uczenia klasyfikatora"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/215"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Wiki train"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f69ddf9e-dc65-58db-90e4-087930b53238.json b/oaitestdata/clarin-oai_dc/SET_1/json/f69ddf9e-dc65-58db-90e4-087930b53238.json
deleted file mode 100644
index b665c924..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f69ddf9e-dc65-58db-90e4-087930b53238.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/321",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/321"
-    ],
-    "PID": "http://hdl.handle.net/11321/321",
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Maziarz, Marek",
-        "Wendelberger, Micha\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/321;2016-10-14T14:37:58Z;hdl_11321_3;hdl_11321_4;S\u0142ownik kolokacji rzeczownikowo-przymiotnikowych bez uzgodnienia;Wendelberger, Micha\u0142;Maziarz, Marek;kolokacje;korpus;uzgodnienie;S\u0142ownik nieuzgodnionych kolokacji rzeczownikowo-przymiotnikowych z korpusu S\u0142owosieci. W nag\u0142\u00f3wku mamy\r\n\r\nbase 0\tbase 1\trelacja\tczesto\u015b\u0107\tAgrAdjSubstP0\tAgrAdjSubstH1P0\tAgrSubstAdjP0\tAgrSubstAdjH1P0\r\n\r\ngdzie base 0 - to lemat pierwszego wyrazu, base 1 - lemat drugiego wyrazu, relacja - rodzaj operatora, kt\u00f3ry wykry\u0142 po\u0142\u0105czenie, cz\u0119sto\u015b\u0107 - frekwencja po\u0142\u0105czenia w korpusie, AgrAdjSubstP0 - szyk AN (przymiotnik - rzeczownik) bez uzgodnienia, nieprzedzielony przez 3 wyraz, AgrAdjSubstH1P0 - szyk A_N (z przerw\u0105 na 1 separuj\u0105cy po\u0142\u0105czenie wyraz), AgrSubstAdjP0 - szyk NA bez uzgodnienia, bez separuj\u0105cego wyrazu, \tAgrSubstAdjH1P0 - szyk NA z przerw\u0105 na 1 separuj\u0105cy wyraz, bez uzgodnienia.\r\n\r\nPrzyk\u0142ad:\r\nbase 0\tbase 1\trelacja\tczesto\u015b\u0107\tAgrAdjSubstP0\tAgrAdjSubstH1P0\tAgrSubstAdjP0\tAgrSubstAdjH1P0\r\nger:uzyska\u0107\tadj:bezc\u0142owy\tAgrSubstAdjH1P0\t3\t0\t0\t1\t2\r\nsubst:misja\tadj:kotlarski\tAgrSubstAdjH1P0\t1\t0\t0\t0\t1;2016;lexicalConceptualResource;http://hdl.handle.net/11321/321;polski;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;Wroc\u0142aw University of Technology;http://clarin-pl.eu",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f69ddf9e-dc65-58db-90e4-087930b53238",
-    "notes": [
-        "S\u0142ownik nieuzgodnionych kolokacji rzeczownikowo-przymiotnikowych z korpusu S\u0142owosieci. W nag\u0142\u00f3wku mamy\r\n\r\nbase 0\tbase 1\trelacja\tczesto\u015b\u0107\tAgrAdjSubstP0\tAgrAdjSubstH1P0\tAgrSubstAdjP0\tAgrSubstAdjH1P0\r\n\r\ngdzie base 0 - to lemat pierwszego wyrazu, base 1 - lemat drugiego wyrazu, relacja - rodzaj operatora, kt\u00f3ry wykry\u0142 po\u0142\u0105czenie, cz\u0119sto\u015b\u0107 - frekwencja po\u0142\u0105czenia w korpusie, AgrAdjSubstP0 - szyk AN (przymiotnik - rzeczownik) bez uzgodnienia, nieprzedzielony przez 3 wyraz, AgrAdjSubstH1P0 - szyk A_N (z przerw\u0105 na 1 separuj\u0105cy po\u0142\u0105czenie wyraz), AgrSubstAdjP0 - szyk NA bez uzgodnienia, bez separuj\u0105cego wyrazu, \tAgrSubstAdjH1P0 - szyk NA z przerw\u0105 na 1 separuj\u0105cy wyraz, bez uzgodnienia.\r\n\r\nPrzyk\u0142ad:\r\nbase 0\tbase 1\trelacja\tczesto\u015b\u0107\tAgrAdjSubstP0\tAgrAdjSubstH1P0\tAgrSubstAdjP0\tAgrSubstAdjH1P0\r\nger:uzyska\u0107\tadj:bezc\u0142owy\tAgrSubstAdjH1P0\t3\t0\t0\t1\t2\r\nsubst:misja\tadj:kotlarski\tAgrSubstAdjH1P0\t1\t0\t0\t0\t1"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/321"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "kolokacje"
-        },
-        {
-            "name": "korpus"
-        },
-        {
-            "name": "uzgodnienie"
-        }
-    ],
-    "title": [
-        "S\u0142ownik kolokacji rzeczownikowo-przymiotnikowych bez uzgodnienia"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f6d13341-c754-5c0c-bcc9-c2ed21985ecd.json b/oaitestdata/clarin-oai_dc/SET_1/json/f6d13341-c754-5c0c-bcc9-c2ed21985ecd.json
deleted file mode 100644
index a60b3225..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f6d13341-c754-5c0c-bcc9-c2ed21985ecd.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1157",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1157"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1157",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1157;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Herders Conversations-Lexikon;Germanistik;1. Aufl. 1854-1857; disziplin\u00fcbergreifende Darstellung von Gegenstandsbereichen gesellschaftlicher Konversation;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1157;deu;downloadable_files_count: 0;http://www.zeno.org/Herder-1854",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f6d13341-c754-5c0c-bcc9-c2ed21985ecd",
-    "notes": [
-        "1. Aufl. 1854-1857; disziplin\u00fcbergreifende Darstellung von Gegenstandsbereichen gesellschaftlicher Konversation"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1157"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Herders Conversations-Lexikon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f6e0a67d-faca-5ff2-9f0d-d1eb23394c85.json b/oaitestdata/clarin-oai_dc/SET_1/json/f6e0a67d-faca-5ff2-9f0d-d1eb23394c85.json
deleted file mode 100644
index affda5bd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f6e0a67d-faca-5ff2-9f0d-d1eb23394c85.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-934",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-934"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-934",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-934;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Old Polish;ca. 5.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-934;pol;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#apoln",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f6e0a67d-faca-5ff2-9f0d-d1eb23394c85",
-    "notes": [
-        "ca. 5.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-934"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Old Polish"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f6e4c0df-52c6-5e20-ade2-2e54d70008ef.json b/oaitestdata/clarin-oai_dc/SET_1/json/f6e4c0df-52c6-5e20-ade2-2e54d70008ef.json
deleted file mode 100644
index 9aee9c2a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f6e4c0df-52c6-5e20-ade2-2e54d70008ef.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "Language": [
-        "Albanian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-952",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-952"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-952",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-952;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Albanian;ca. 100.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-952;sqi;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#alban",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f6e4c0df-52c6-5e20-ade2-2e54d70008ef",
-    "notes": [
-        "ca. 100.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-952"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Albanian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f6fb2e6c-5308-56b5-9ea2-676fc7b4a1ac.json b/oaitestdata/clarin-oai_dc/SET_1/json/f6fb2e6c-5308-56b5-9ea2-676fc7b4a1ac.json
deleted file mode 100644
index 535c1dcd..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f6fb2e6c-5308-56b5-9ea2-676fc7b4a1ac.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Shivaji University , Freie Universitat Berlin"
-    ],
-    "Contributor": [
-        "Leitner, Gerhard",
-        "Shastri, S.v."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-888",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-888"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-888",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Shivaji University , Freie Universitat Berlin"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Germany||India"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-888;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;International Corpus of English: India (ICE-Ind);Shastri, S.v.;Leitner, Gerhard;One million words of spoken and written English from India. Part of the ICE project;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-888;eng;downloadable_files_count: 0;Germany||India;Shivaji University , Freie Universitat Berlin;http://www.ucl.ac.uk/english-usage/ice/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f6fb2e6c-5308-56b5-9ea2-676fc7b4a1ac",
-    "notes": [
-        "One million words of spoken and written English from India. Part of the ICE project"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-888"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "International Corpus of English: India (ICE-Ind)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f707547d-8f89-580a-b3f1-9a1403f3144a.json b/oaitestdata/clarin-oai_dc/SET_1/json/f707547d-8f89-580a-b3f1-9a1403f3144a.json
deleted file mode 100644
index 5a9d89e7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f707547d-8f89-580a-b3f1-9a1403f3144a.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1160",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1160"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1160",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1160;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Meyers Gro\u00dfes Konversations-Lexikon;Germanistik;6. Aufl. 1905-1909; Fokus auf technische, naturwissenschaftliche und soziale Entwicklungen im 19. Jahrhundert;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1160;deu;downloadable_files_count: 0;http://www.zeno.org/Meyers-1905",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f707547d-8f89-580a-b3f1-9a1403f3144a",
-    "notes": [
-        "6. Aufl. 1905-1909; Fokus auf technische, naturwissenschaftliche und soziale Entwicklungen im 19. Jahrhundert"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1160"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Meyers Gro\u00dfes Konversations-Lexikon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f716c2c9-6bec-5eb3-ad7b-b00b12d878ba.json b/oaitestdata/clarin-oai_dc/SET_1/json/f716c2c9-6bec-5eb3-ad7b-b00b12d878ba.json
deleted file mode 100644
index d6cf1f04..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f716c2c9-6bec-5eb3-ad7b-b00b12d878ba.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=20a042daa35a11e1a404080027e73ea2da6b535b387a48609d6daa922e1b996d",
-    "MetadataAccess": [
-        "20a042daa35a11e1a404080027e73ea2da6b535b387a48609d6daa922e1b996d"
-    ],
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "20a042daa35a11e1a404080027e73ea2da6b535b387a48609d6daa922e1b996d;2019-02-27T12:08:49Z;corpus;corpus:text;Illum Corpus;The full editions of ILLUM from 12/11/2006 to 30/05/2010 (185 issues).;2015-12-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f716c2c9-6bec-5eb3-ad7b-b00b12d878ba",
-    "notes": [
-        "The full editions of ILLUM from 12/11/2006 to 30/05/2010 (185 issues)."
-    ],
-    "oai_identifier": [
-        "20a042daa35a11e1a404080027e73ea2da6b535b387a48609d6daa922e1b996d"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:text"
-    ],
-    "state": "active",
-    "title": [
-        "Illum Corpus"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f73885d9-256d-52f3-a46a-93aaef1f1eea.json b/oaitestdata/clarin-oai_dc/SET_1/json/f73885d9-256d-52f3-a46a-93aaef1f1eea.json
deleted file mode 100644
index d6296a2f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f73885d9-256d-52f3-a46a-93aaef1f1eea.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Department of Music, University of Jyv\u00e4skyl\u00e4"
-    ],
-    "Contributor": [
-        "Toiviainen, Petri"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Finnish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-823",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-823"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-823",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Department of Music, University of Jyv\u00e4skyl\u00e4"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Finland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-823;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Digital archive of Finnish Folk Tunes;Toiviainen, Petri;Digitalized versions of Finnish folk tunes and their relevant details (notation, key, meter, place of collection, lyrics, collector), 8613 Finnish folk tunes (including part of the lyrics);2014-07-30;toolService;http://hdl.handle.net/11372/LRT-823;fin;downloadable_files_count: 0;Finland;Department of Music, University of Jyv\u00e4skyl\u00e4;http://esavelmat.jyu.fi//",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f73885d9-256d-52f3-a46a-93aaef1f1eea",
-    "notes": [
-        "Digitalized versions of Finnish folk tunes and their relevant details (notation, key, meter, place of collection, lyrics, collector), 8613 Finnish folk tunes (including part of the lyrics)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-823"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Digital archive of Finnish Folk Tunes"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f74fca7c-415d-531c-9db8-cf53ba7c14ea.json b/oaitestdata/clarin-oai_dc/SET_1/json/f74fca7c-415d-531c-9db8-cf53ba7c14ea.json
deleted file mode 100644
index 897752bf..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f74fca7c-415d-531c-9db8-cf53ba7c14ea.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3416",
-    "MetadataAccess": [
-        "oai:ota:oucs:3416"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Shenstone, William, 1714-1763."
-    ],
-    "fulltext": "oai:ota:oucs:3416;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3416.xml;Poems upon various occasions: Written for the entertainment of the author, and printed for the amusement of a few friends, prejudic'd in his favour. By William Shenstone, gent.;Shenstone, William, 1714-1763.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f74fca7c-415d-531c-9db8-cf53ba7c14ea",
-    "oai_identifier": [
-        "oai:ota:oucs:3416"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Poems upon various occasions: Written for the entertainment of the author, and printed for the amusement of a few friends, prejudic'd in his favour. By William Shenstone, gent."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3416.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f76175b4-ad87-5bbb-b10a-b2a260dbf9c5.json b/oaitestdata/clarin-oai_dc/SET_1/json/f76175b4-ad87-5bbb-b10a-b2a260dbf9c5.json
deleted file mode 100644
index 7d901945..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f76175b4-ad87-5bbb-b10a-b2a260dbf9c5.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "NO2014, University of Oslo"
-    ],
-    "Contributor": [
-        "Wet\u00e5s, \u00c5se"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Norwegian Nynorsk"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-672",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-672"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-672",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "NO2014, University of Oslo"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-672;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;NO2014 Nynorsk Corpus;Wet\u00e5s, \u00c5se;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-672;nno;downloadable_files_count: 0;NO2014, University of Oslo;http://no2014.uio.no/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f76175b4-ad87-5bbb-b10a-b2a260dbf9c5",
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-672"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "NO2014 Nynorsk Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f778d0c4-26b5-5c9c-a571-15f613d1d6c9.json b/oaitestdata/clarin-oai_dc/SET_1/json/f778d0c4-26b5-5c9c-a571-15f613d1d6c9.json
deleted file mode 100644
index 7d26bcde..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f778d0c4-26b5-5c9c-a571-15f613d1d6c9.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "IPIPAN"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/387",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/387"
-    ],
-    "PID": "http://hdl.handle.net/11321/387",
-    "PublicationTimestamp": "2017-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "IPIPAN"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Cyrklaff, Magdalena"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/387;2017-05-30T11:54:55Z;hdl_11321_3;hdl_11321_4;Novels_Dabrowska_Dzikie_ziele;Cyrklaff, Magdalena;Maria D\u0105browska;Wild herb;stories;Body of Maria D\u0105browska \"Wild herb\" from the collection of the Scriptures selected. Stories, passages, dramas, songs for children.;2017-05-30;corpus;http://hdl.handle.net/11321/387;eng;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;application/vnd.openxmlformats-officedocument.wordprocessingml.document;downloadable_files_count: 1;IPIPAN",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f778d0c4-26b5-5c9c-a571-15f613d1d6c9",
-    "notes": [
-        "Body of Maria D\u0105browska \"Wild herb\" from the collection of the Scriptures selected. Stories, passages, dramas, songs for children."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/387"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Wild herb"
-        },
-        {
-            "name": "stories"
-        }
-    ],
-    "title": [
-        "Novels_Dabrowska_Dzikie_ziele"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f79ab6b6-3f11-5f1d-b43f-ac7a248abe73.json b/oaitestdata/clarin-oai_dc/SET_1/json/f79ab6b6-3f11-5f1d-b43f-ac7a248abe73.json
deleted file mode 100644
index f7f74e25..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f79ab6b6-3f11-5f1d-b43f-ac7a248abe73.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4168",
-    "MetadataAccess": [
-        "oai:ota:oucs:4168"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Philadelphos, Theophilos."
-    ],
-    "fulltext": "oai:ota:oucs:4168;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4168.xml;A sequel to Common sense: or, the American controversy considered in two points of view hitherto unnoticed. ... By Theophilus Philadelphus.;Philadelphos, Theophilos.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f79ab6b6-3f11-5f1d-b43f-ac7a248abe73",
-    "oai_identifier": [
-        "oai:ota:oucs:4168"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A sequel to Common sense: or, the American controversy considered in two points of view hitherto unnoticed. ... By Theophilus Philadelphus."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4168.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f79b390e-2a47-5f44-b166-c174afe144c8.json b/oaitestdata/clarin-oai_dc/SET_1/json/f79b390e-2a47-5f44-b166-c174afe144c8.json
deleted file mode 100644
index 7acf41b2..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f79b390e-2a47-5f44-b166-c174afe144c8.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "MTA-SZTE Research Group on Artificial Intelligence"
-    ],
-    "Contributor": [
-        "T\u00f3th, L\u00e1szl\u00f3"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Hungarian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-546",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-546"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-546",
-    "PublicationTimestamp": "2002-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2002"
-    ],
-    "Publisher": [
-        "MTA-SZTE Research Group on Artificial Intelligence"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Hungary"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-546;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Oasis Numbers;T\u00f3th, L\u00e1szl\u00f3;speech corpus;spoken, monolingual, manually segmented domain-specific corpus of numbers, 5857 recorded words;2002;corpus;http://hdl.handle.net/11372/LRT-546;hun;downloadable_files_count: 0;Hungary;MTA-SZTE Research Group on Artificial Intelligence;http://www.inf.u-szeged.hu/rgai/?lang=en&page=oasisnumbers",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f79b390e-2a47-5f44-b166-c174afe144c8",
-    "notes": [
-        "spoken, monolingual, manually segmented domain-specific corpus of numbers, 5857 recorded words"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-546"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech corpus"
-        }
-    ],
-    "title": [
-        "Oasis Numbers"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f7a01e62-6926-5fb2-aa45-0f42aac852cf.json b/oaitestdata/clarin-oai_dc/SET_1/json/f7a01e62-6926-5fb2-aa45-0f42aac852cf.json
deleted file mode 100644
index 8a70b683..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f7a01e62-6926-5fb2-aa45-0f42aac852cf.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=ff52704e327411e2a2aa782bcb07413549e00495edb64d11868a3cb95816da0e",
-    "MetadataAccess": [
-        "ff52704e327411e2a2aa782bcb07413549e00495edb64d11868a3cb95816da0e"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "ff52704e327411e2a2aa782bcb07413549e00495edb64d11868a3cb95816da0e;2019-02-27T12:10:03Z;toolService;toolService:tool;STEPP Tagger;Part-of-speech tagger tuned to biomedical text, provided as a web service. ;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f7a01e62-6926-5fb2-aa45-0f42aac852cf",
-    "notes": [
-        "Part-of-speech tagger tuned to biomedical text, provided as a web service. "
-    ],
-    "oai_identifier": [
-        "ff52704e327411e2a2aa782bcb07413549e00495edb64d11868a3cb95816da0e"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "STEPP Tagger"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f7a2caab-8f92-5bf5-84dd-b5887c12cc58.json b/oaitestdata/clarin-oai_dc/SET_1/json/f7a2caab-8f92-5bf5-84dd-b5887c12cc58.json
deleted file mode 100644
index be8e9387..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f7a2caab-8f92-5bf5-84dd-b5887c12cc58.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Bazyli Skalski"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-214298",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-214298"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CFC-F",
-    "PublicationTimestamp": "1610-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1610"
-    ],
-    "Publisher": [
-        "Bazyli Skalski"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/214298",
-        "oai:jbc.bj.uj.edu.pl:publication:225778"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1601/1700"
-    ],
-    "TempCoverageBegin": 50506804799,
-    "TempCoverageEnd": 50506804799,
-    "TemporalCoverage": " point in time : 1601-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1601-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1601-07-01T11:59:59Z",
-    "author": [
-        "Grochowski, Stanis\u0142aw (1542-1612)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-214298;2019-03-01T11:13:59Z;Torvnskie Nocy Roku Panskiego 1609 X. Stanislawa Grochowskiego, Kustosza Kruszwickiego;Grochowski, Stanis\u0142aw (1542-1612);starodruki 17\u00a0w.;Skarga, Piotr (1536-1612). [Adr. ded.];Bazyli Skalski;1610;starodruk;application/xml;clarind-uds:poldilemma-214298;hdl:11858/00-246C-0000-0023-8CFC-F;Biblioteka Jagiello\u0144ska, BJ St. Dr. 1471 I;pol;http://jbc.bj.uj.edu.pl/Content/214298;oai:jbc.bj.uj.edu.pl:publication:225778;1601/1700;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f7a2caab-8f92-5bf5-84dd-b5887c12cc58",
-    "notes": [
-        "Skarga, Piotr (1536-1612). [Adr. ded.]"
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-214298"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Torvnskie Nocy Roku Panskiego 1609 X. Stanislawa Grochowskiego, Kustosza Kruszwickiego"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f7b932aa-be00-505b-813f-bfd3f3eaf29b.json b/oaitestdata/clarin-oai_dc/SET_1/json/f7b932aa-be00-505b-813f-bfd3f3eaf29b.json
deleted file mode 100644
index 47d2dc83..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f7b932aa-be00-505b-813f-bfd3f3eaf29b.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1145",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1145"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1145",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1145;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Duden online;Germanistik;Angabe von Rechtschreibung, Bedeutungs\u00fcbersicht, Synonymen, Aussprache (Audio-Datei), Herkunft, Grammatik, typischen Verbindungen (computergeneriert) sowie Bedeutungen, Beispielen und Wendungen (zus\u00e4tzlich: Angabe der W\u00f6rter, die im Alphabet vorhergehen und nachfolgen);2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1145;deu;downloadable_files_count: 0;Germany;http://www.duden.de/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f7b932aa-be00-505b-813f-bfd3f3eaf29b",
-    "notes": [
-        "Angabe von Rechtschreibung, Bedeutungs\u00fcbersicht, Synonymen, Aussprache (Audio-Datei), Herkunft, Grammatik, typischen Verbindungen (computergeneriert) sowie Bedeutungen, Beispielen und Wendungen (zus\u00e4tzlich: Angabe der W\u00f6rter, die im Alphabet vorhergehen und nachfolgen)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1145"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "Duden online"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f7bd9b22-7fe7-5d27-9ca6-0648ca442632.json b/oaitestdata/clarin-oai_dc/SET_1/json/f7bd9b22-7fe7-5d27-9ca6-0648ca442632.json
deleted file mode 100644
index b234eccb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f7bd9b22-7fe7-5d27-9ca6-0648ca442632.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Natural Language Processing Centre, Faculty of Informatics, Masaryk University"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2595",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2595"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2595",
-    "PublicationTimestamp": "2017-12-02T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Natural Language Processing Centre, Faculty of Informatics, Masaryk University"
-    ],
-    "RelatedIdentifier": [
-        "https://nlp.fi.muni.cz/raslan/2017/paper12-Sulganova_Medved_Horak.pdf"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU General Public Licence, version 3",
-        "http://opensource.org/licenses/GPL-3.0",
-        "PUB"
-    ],
-    "author": [
-        "Hor\u00e1k, Ale\u0161",
-        "\u0160ulganov\u00e1, Ter\u00e9zia",
-        "Medve\u010f, Marek"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2595;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;SQAD v2;Medve\u010f, Marek;Hor\u00e1k, Ale\u0161;\u0160ulganov\u00e1, Ter\u00e9zia;question answering;Czech;Simple Question Answering Database;Simple question answering database (SQAD) created from Czech Wikipedia. Each record of SQAD consist of four files (in vertical form provided with lemmatization and POS tagging)  and two metadata files.;2017-12-02;corpus;http://hdl.handle.net/11234/1-2595;ces;https://nlp.fi.muni.cz/raslan/2017/paper12-Sulganova_Medved_Horak.pdf;GNU General Public Licence, version 3;http://opensource.org/licenses/GPL-3.0;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Natural Language Processing Centre, Faculty of Informatics, Masaryk University;https://www.muni.cz/vyzkum/projekty/31445",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f7bd9b22-7fe7-5d27-9ca6-0648ca442632",
-    "notes": [
-        "Simple question answering database (SQAD) created from Czech Wikipedia. Each record of SQAD consist of four files (in vertical form provided with lemmatization and POS tagging)  and two metadata files."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2595"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "question answering"
-        },
-        {
-            "name": "Czech"
-        },
-        {
-            "name": "Simple Question Answering Database"
-        }
-    ],
-    "title": [
-        "SQAD v2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f7c0f624-4940-5cd3-960f-a050fc52656c.json b/oaitestdata/clarin-oai_dc/SET_1/json/f7c0f624-4940-5cd3-960f-a050fc52656c.json
deleted file mode 100644
index b9f12194..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f7c0f624-4940-5cd3-960f-a050fc52656c.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Hindi"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-CC1E-B",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-CC1E-B"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-CC1E-B",
-    "PublicationTimestamp": "2011-11-23T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/231720",
-        "http://hdl.handle.net/11858/00-097C-0000-0023-6260-A"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0)",
-        "http://creativecommons.org/licenses/by-nc/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Bojar, Ond\u0159ej",
-        "Stra\u0148\u00e1k, Pavel",
-        "Zeman, Daniel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-CC1E-B;2018-07-02T22:05:54Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Hindi Web Texts;Bojar, Ond\u0159ej;Stra\u0148\u00e1k, Pavel;Zeman, Daniel;news;web texts;A Hindi corpus of texts downloaded mostly from news sites. Contains both the original raw texts and an extensively cleaned-up and tokenized version suitable for language modeling. 18M sentences, 308M tokens;2011-11-23;corpus;UMC004;http://hdl.handle.net/11858/00-097C-0000-0001-CC1E-B;hin;info:eu-repo/grantAgreement/EC/FP7/231720;http://hdl.handle.net/11858/00-097C-0000-0023-6260-A;Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0);http://creativecommons.org/licenses/by-nc/3.0/;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f7c0f624-4940-5cd3-960f-a050fc52656c",
-    "notes": [
-        "A Hindi corpus of texts downloaded mostly from news sites. Contains both the original raw texts and an extensively cleaned-up and tokenized version suitable for language modeling. 18M sentences, 308M tokens"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-CC1E-B"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "news"
-        },
-        {
-            "name": "web texts"
-        }
-    ],
-    "title": [
-        "Hindi Web Texts"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f7c7f999-f948-511d-b5b8-59e86c8f4d00.json b/oaitestdata/clarin-oai_dc/SET_1/json/f7c7f999-f948-511d-b5b8-59e86c8f4d00.json
deleted file mode 100644
index aed10848..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f7c7f999-f948-511d-b5b8-59e86c8f4d00.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Arts, Institute of the Czech National Corpus, Charles University in Prague"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-119D-A",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-119D-A"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-119D-A",
-    "PublicationTimestamp": "2008-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2008"
-    ],
-    "Publisher": [
-        "Faculty of Arts, Institute of the Czech National Corpus, Charles University in Prague"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Kop\u0159ivov\u00e1, Marie",
-        "Waclawi\u010dov\u00e1, Martina",
-        "K\u0159en, Michal",
-        "V\u00e1lkov\u00e1, Lucie"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-119D-A;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;ORAL2008: Balanced corpus of informal spoken Czech;Waclawi\u010dov\u00e1, Martina;Kop\u0159ivov\u00e1, Marie;K\u0159en, Michal;V\u00e1lkov\u00e1, Lucie;informal spoken language;balanced corpus;Balanced corpus of informal spoken Czech sized 1 MW. It contains transcriptions of 297 recordings made in 2002\u20132007 in the whole of Bohemia. All the recordings were made in informal situations to ensure prototypically spontaneous spoken language. This means private environment, physical presence of speakers who know each other, unscripted speech and topic not given in advance. The total number of speakers is 995, the corpus is balanced in their main sociolinguistic categories (gender, age group, education, region of childhood residence).\r\n\r\nThe corpus is provided in a (semi-XML) vertical format used as an input to the Manatee query engine. The data thus exactly correspond to the corpus available via query interface to registered users of the CNC.;2008;corpus;http://hdl.handle.net/11858/00-097C-0000-0023-119D-A;ces;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Faculty of Arts, Institute of the Czech National Corpus, Charles University in Prague;https://wiki.korpus.cz/doku.php/cnk:oral2008",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f7c7f999-f948-511d-b5b8-59e86c8f4d00",
-    "notes": [
-        "Balanced corpus of informal spoken Czech sized 1 MW. It contains transcriptions of 297 recordings made in 2002\u20132007 in the whole of Bohemia. All the recordings were made in informal situations to ensure prototypically spontaneous spoken language. This means private environment, physical presence of speakers who know each other, unscripted speech and topic not given in advance. The total number of speakers is 995, the corpus is balanced in their main sociolinguistic categories (gender, age group, education, region of childhood residence).\r\n\r\nThe corpus is provided in a (semi-XML) vertical format used as an input to the Manatee query engine. The data thus exactly correspond to the corpus available via query interface to registered users of the CNC."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-119D-A"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "informal spoken language"
-        },
-        {
-            "name": "balanced corpus"
-        }
-    ],
-    "title": [
-        "ORAL2008: Balanced corpus of informal spoken Czech"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f7dd150b-e4e0-52a9-8b6f-25923ae42f39.json b/oaitestdata/clarin-oai_dc/SET_1/json/f7dd150b-e4e0-52a9-8b6f-25923ae42f39.json
deleted file mode 100644
index 9d31896d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f7dd150b-e4e0-52a9-8b6f-25923ae42f39.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "IULA, Universitat Pompeu Fabra"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1285",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1285"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1285",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "IULA, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1285;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Tools for Catalan and Spanish corpus processing;corpus processing;A package of tools for Catalan and Spanish corpus processing. It includes a text handling module and a probabilistic POS tagger. It also allows consulting POS tagger dictionary data.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1285;downloadable_files_count: 0;Spain;IULA, Universitat Pompeu Fabra",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f7dd150b-e4e0-52a9-8b6f-25923ae42f39",
-    "notes": [
-        "A package of tools for Catalan and Spanish corpus processing. It includes a text handling module and a probabilistic POS tagger. It also allows consulting POS tagger dictionary data."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1285"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus processing"
-        }
-    ],
-    "title": [
-        "Tools for Catalan and Spanish corpus processing"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f7ea55ad-70b2-5b97-95a2-269428dd8c58.json b/oaitestdata/clarin-oai_dc/SET_1/json/f7ea55ad-70b2-5b97-95a2-269428dd8c58.json
deleted file mode 100644
index 6144a334..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f7ea55ad-70b2-5b97-95a2-269428dd8c58.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/x-bzip2",
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48FF-7",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48FF-7"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0001-48FF-7",
-    "PublicationTimestamp": "2009-11-02T09:50:15Z",
-    "PublicationYear": [
-        "2009"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU General Public License, version 2",
-        "http://www.gnu.org/licenses/gpl-2.0.html",
-        "PUB"
-    ],
-    "author": [
-        "Spousta, Miroslav"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48FF-7;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Victoria;Spousta, Miroslav;web page processing;Victoria is an on-line HTML web page annotation tool suitable for selecting texts on the web pages. It can be used to mark important/interesting parts of web pages for further processing.;2009-11-02T09:50:15Z;toolService;http://hdl.handle.net/11858/00-097C-0000-0001-48FF-7;GNU General Public License, version 2;http://www.gnu.org/licenses/gpl-2.0.html;PUB;application/x-bzip2;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/victor/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f7ea55ad-70b2-5b97-95a2-269428dd8c58",
-    "notes": [
-        "Victoria is an on-line HTML web page annotation tool suitable for selecting texts on the web pages. It can be used to mark important/interesting parts of web pages for further processing."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0001-48FF-7"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "web page processing"
-        }
-    ],
-    "title": [
-        "Victoria"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f80531c6-ea74-5c7d-a313-c0df45578659.json b/oaitestdata/clarin-oai_dc/SET_1/json/f80531c6-ea74-5c7d-a313-c0df45578659.json
deleted file mode 100644
index 4a580146..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f80531c6-ea74-5c7d-a313-c0df45578659.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/octet-stream",
-        "downloadable_files_count: 1",
-        "application/vnd.oasis.opendocument.spreadsheet"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/307",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/307"
-    ],
-    "PID": "http://hdl.handle.net/11321/307",
-    "PublicationTimestamp": "2016-06-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "CC"
-    ],
-    "author": [
-        "K\u0119dzia, Pawe\u0142"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/307;2016-06-07T13:45:54Z;hdl_11321_3;hdl_11321_4;PLWordNet to Sumo mapping;K\u0119dzia, Pawe\u0142;SUMO;Ontology;mapping;plWordNet;Resul of mapping plWordNet onto SUMO ontology.;2016-06-01;lexicalConceptualResource;http://hdl.handle.net/11321/307;pol;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;CC;text/plain; charset=utf-8;application/vnd.oasis.opendocument.spreadsheet;application/octet-stream;application/octet-stream;downloadable_files_count: 1;Wroc\u0142aw University of Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f80531c6-ea74-5c7d-a313-c0df45578659",
-    "notes": [
-        "Resul of mapping plWordNet onto SUMO ontology."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/307"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "SUMO"
-        },
-        {
-            "name": "Ontology"
-        },
-        {
-            "name": "mapping"
-        },
-        {
-            "name": "plWordNet"
-        }
-    ],
-    "title": [
-        "PLWordNet to Sumo mapping"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f8173d6e-6347-5e35-bb50-a5b3222c7fc1.json b/oaitestdata/clarin-oai_dc/SET_1/json/f8173d6e-6347-5e35-bb50-a5b3222c7fc1.json
deleted file mode 100644
index d0bb9f5a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f8173d6e-6347-5e35-bb50-a5b3222c7fc1.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "IPI PAN"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "downloadable_files_count: 10",
-        "application/vnd.oasis.opendocument.text",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/373",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/373"
-    ],
-    "PID": "http://hdl.handle.net/11321/373",
-    "PublicationTimestamp": "2017-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "IPI PAN"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Opali\u0144ski, Krzysztof"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/373;2017-05-30T07:54:35Z;hdl_11321_3;hdl_11321_4;korpus-materia\u0142y-CLARIN;Opali\u0144ski, Krzysztof;teksty;korpus;2017-05-30;corpus;http://hdl.handle.net/11321/373;pol;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;text/plain;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.oasis.opendocument.text;text/plain;text/plain;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;downloadable_files_count: 10;IPI PAN",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f8173d6e-6347-5e35-bb50-a5b3222c7fc1",
-    "notes": [
-        "korpus"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/373"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "teksty"
-        }
-    ],
-    "title": [
-        "korpus-materia\u0142y-CLARIN"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f82db3c2-20f7-5df2-9eb6-d0dba7825f2b.json b/oaitestdata/clarin-oai_dc/SET_1/json/f82db3c2-20f7-5df2-9eb6-d0dba7825f2b.json
deleted file mode 100644
index fdbb8fb4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f82db3c2-20f7-5df2-9eb6-d0dba7825f2b.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 3.06 MB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2026",
-    "MetadataAccess": [
-        "oai:ota:oucs:2026"
-    ],
-    "PublicationTimestamp": "1867-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1867"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Tolstoy, Leo, graf, 1828-1910"
-    ],
-    "fulltext": "oai:ota:oucs:2026;2018-03-01T12:27:15Z;http://ota.ox.ac.uk/headers/2026.xml;Voina i mir. English;War and peace / by Leo Tolstoy;Tolstoy, Leo, graf, 1828-1910;1867;text_and_corpus_linguistics;Fiction;Novels;Translations;eng;Oxford Text Archive, University of Oxford;text/plain;(1 file : ca. 3.06 MB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f82db3c2-20f7-5df2-9eb6-d0dba7825f2b",
-    "oai_identifier": [
-        "oai:ota:oucs:2026"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction"
-        },
-        {
-            "name": "Novels"
-        },
-        {
-            "name": "Translations"
-        }
-    ],
-    "title": [
-        "Voina i mir. English",
-        "War and peace / by Leo Tolstoy"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2026.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f84cfcd2-d763-5147-adff-63dfcae0780e.json b/oaitestdata/clarin-oai_dc/SET_1/json/f84cfcd2-d763-5147-adff-63dfcae0780e.json
deleted file mode 100644
index aaab91aa..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f84cfcd2-d763-5147-adff-63dfcae0780e.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Electrical Engineering and Computer Science, University of Maribor"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 4",
-        "application/pdf",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1051",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1051"
-    ],
-    "PID": "http://hdl.handle.net/11356/1051",
-    "PublicationTimestamp": "2002-03-02T11:59:59Z",
-    "PublicationYear": [
-        "2002"
-    ],
-    "Publisher": [
-        "Faculty of Electrical Engineering and Computer Science, University of Maribor"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Rotovnik, Toma\u017e",
-        "Veronik, Robert",
-        "Sepesy Mau\u010dec, Mirjam",
-        "Z\u00f6gling Marku\u0161, Aleksandra",
-        "Horvat, Bogomir",
-        "\u017dgank, Andrej",
-        "Ka\u010di\u010d, Zdravko",
-        "Rojc, Matej"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1051;2017-01-20T14:00:23Z;hdl_11356_1023;hdl_11356_1024;SNABI database for continuous speech recognition 1.2;Ka\u010di\u010d, Zdravko;Horvat, Bogomir;Z\u00f6gling Marku\u0161, Aleksandra;Veronik, Robert;Rojc, Matej;\u017dgank, Andrej;Sepesy Mau\u010dec, Mirjam;Rotovnik, Toma\u017e;speech recognition;speech database;speech recordings;spoken corpus;The SNABI speech database can be used to train continuous speech recognition for Slovene language. The database comprises 1530 sentences, 150 words and the alphabet. 132 speakers were recorded, each reading 200 sentences or more. This resulted in more than 15,000 recordings of speech signal contained in the database. The recordings were done in studio (SNABI SI_SSQ) and through a telephone line (SNABI SI_SFN).;2002-03-02;corpus;http://hdl.handle.net/11356/1051;slv;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);https://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/pdf;application/zip;application/pdf;application/zip;text/plain; charset=utf-8;downloadable_files_count: 4;Faculty of Electrical Engineering and Computer Science, University of Maribor",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f84cfcd2-d763-5147-adff-63dfcae0780e",
-    "notes": [
-        "The SNABI speech database can be used to train continuous speech recognition for Slovene language. The database comprises 1530 sentences, 150 words and the alphabet. 132 speakers were recorded, each reading 200 sentences or more. This resulted in more than 15,000 recordings of speech signal contained in the database. The recordings were done in studio (SNABI SI_SSQ) and through a telephone line (SNABI SI_SFN)."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1051"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech recognition"
-        },
-        {
-            "name": "speech database"
-        },
-        {
-            "name": "speech recordings"
-        },
-        {
-            "name": "spoken corpus"
-        }
-    ],
-    "title": [
-        "SNABI database for continuous speech recognition 1.2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f851a60d-f4e7-51ba-9d88-36d311eb354f.json b/oaitestdata/clarin-oai_dc/SET_1/json/f851a60d-f4e7-51ba-9d88-36d311eb354f.json
deleted file mode 100644
index a2e6955e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f851a60d-f4e7-51ba-9d88-36d311eb354f.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4489",
-    "MetadataAccess": [
-        "oai:ota:oucs:4489"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Defoe, Daniel, 1661?-1731."
-    ],
-    "fulltext": "oai:ota:oucs:4489;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4489.xml;The conduct of Christians made the sport of infidels: In a letter from a Turkish merchant at Amsterdam to the Grand Mufti at Constantinople: ...;Defoe, Daniel, 1661?-1731.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f851a60d-f4e7-51ba-9d88-36d311eb354f",
-    "oai_identifier": [
-        "oai:ota:oucs:4489"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The conduct of Christians made the sport of infidels: In a letter from a Turkish merchant at Amsterdam to the Grand Mufti at Constantinople: ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4489.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f85dae88-8ea4-51ac-b791-c01f2a4bab66.json b/oaitestdata/clarin-oai_dc/SET_1/json/f85dae88-8ea4-51ac-b791-c01f2a4bab66.json
deleted file mode 100644
index 086927fb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f85dae88-8ea4-51ac-b791-c01f2a4bab66.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5491",
-    "MetadataAccess": [
-        "oai:ota:oucs:5491"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Murphy, Arthur, 1727-1805."
-    ],
-    "fulltext": "oai:ota:oucs:5491;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/5491.xml;Three weeks after marriage: a comedy, in two acts, as performed at the Theatre-Royal in Covent Garden.;What we must all come to;Murphy, Arthur, 1727-1805.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f85dae88-8ea4-51ac-b791-c01f2a4bab66",
-    "oai_identifier": [
-        "oai:ota:oucs:5491"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Three weeks after marriage: a comedy, in two acts, as performed at the Theatre-Royal in Covent Garden.",
-        "What we must all come to"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5491.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f87a6b34-7de0-556d-b803-13b418da4bea.json b/oaitestdata/clarin-oai_dc/SET_1/json/f87a6b34-7de0-556d-b803-13b418da4bea.json
deleted file mode 100644
index d791b0f3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f87a6b34-7de0-556d-b803-13b418da4bea.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-938",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-938"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-938",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-938;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Proto- and Old Norse;ca. 40.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-938;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#nord",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f87a6b34-7de0-556d-b803-13b418da4bea",
-    "notes": [
-        "ca. 40.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-938"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Proto- and Old Norse"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f8892735-e0d4-517c-ab1b-f8374c4087d9.json b/oaitestdata/clarin-oai_dc/SET_1/json/f8892735-e0d4-517c-ab1b-f8374c4087d9.json
deleted file mode 100644
index 77ecb3ce..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f8892735-e0d4-517c-ab1b-f8374c4087d9.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2755",
-    "MetadataAccess": [
-        "oai:ota:oucs:2755"
-    ],
-    "PublicationTimestamp": "1779-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1779"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2755;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2755.xml;Letter from the pretender, to a whig-lord;Swift, Jonathan, 1667-1745;1779;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f8892735-e0d4-517c-ab1b-f8374c4087d9",
-    "oai_identifier": [
-        "oai:ota:oucs:2755"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Letter from the pretender, to a whig-lord"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2755.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f8959080-f12f-5b05-ab0f-52da064fe445.json b/oaitestdata/clarin-oai_dc/SET_1/json/f8959080-f12f-5b05-ab0f-52da064fe445.json
deleted file mode 100644
index f962db8b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f8959080-f12f-5b05-ab0f-52da064fe445.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 287 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1834",
-    "MetadataAccess": [
-        "oai:ota:oucs:1834"
-    ],
-    "PublicationTimestamp": "1913-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1913"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Autobiographies"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Muir, John, 1838-1914"
-    ],
-    "fulltext": "oai:ota:oucs:1834;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/1834.xml;The story of my boyhood and youth / by John Muir;Muir, John, 1838-1914;1913;text_and_corpus_linguistics;Autobiographies -- United States -- 20th century;eng;Oxford Text Archive, University of Oxford;Triggs, Jeffery;text/sgml;(1 file : ca. 287 KB);Text;Autobiographies;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f8959080-f12f-5b05-ab0f-52da064fe445",
-    "oai_identifier": [
-        "oai:ota:oucs:1834"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Autobiographies -- United States -- th century"
-        }
-    ],
-    "title": [
-        "The story of my boyhood and youth / by John Muir"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1834.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f8987834-3186-5818-8624-171538bdc21d.json b/oaitestdata/clarin-oai_dc/SET_1/json/f8987834-3186-5818-8624-171538bdc21d.json
deleted file mode 100644
index eff0072f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f8987834-3186-5818-8624-171538bdc21d.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Drukarnia J.K.M. XX Trynitarzy"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-230786",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-230786"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D0D-1",
-    "PublicationTimestamp": "1784-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1784"
-    ],
-    "Publisher": [
-        "Drukarnia J.K.M. XX Trynitarzy"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/230786",
-        "oai:jbc.bj.uj.edu.pl:publication:242450"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1701/1800"
-    ],
-    "TempCoverageBegin": 53662478399,
-    "TempCoverageEnd": 53662478399,
-    "TemporalCoverage": " point in time : 1701-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1701-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1701-07-01T11:59:59Z",
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-230786;2019-03-01T13:08:46Z;List w materyi religii niegdys do jednego p. dyssydenta pisany, a dzi\u015b wszystkim tym\u017ce ichmo\u015bciom, zacnym Korony Polskiey, i W. X. Litew. obywatelom, naymilszym bli\u017anim i braci zbawienie duszy kochai\u0105cym na uwag\u0119 podany;starodruki 18\u00a0w.;Drukarnia J.K.M. XX Trynitarzy;1784;starodruk;application/xml;application/xml;clarind-uds:poldilemma-230786;hdl:11858/00-246C-0000-0023-8D0D-1;Biblioteka Jagiello\u0144ska, BJ St. Dr. 35724;http://jbc.bj.uj.edu.pl/Content/230786;oai:jbc.bj.uj.edu.pl:publication:242450;1701/1800;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f8987834-3186-5818-8624-171538bdc21d",
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-230786"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "List w materyi religii niegdys do jednego p. dyssydenta pisany, a dzi\u015b wszystkim tym\u017ce ichmo\u015bciom, zacnym Korony Polskiey, i W. X. Litew. obywatelom, naymilszym bli\u017anim i braci zbawienie duszy kochai\u0105cym na uwag\u0119 podany"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f8a376c2-5bad-5acf-a91a-d3be7dac99d5.json b/oaitestdata/clarin-oai_dc/SET_1/json/f8a376c2-5bad-5acf-a91a-d3be7dac99d5.json
deleted file mode 100644
index 8523ac40..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f8a376c2-5bad-5acf-a91a-d3be7dac99d5.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=8ca121046bf811e2a2aa782bcb0741353301ccfceaa743e5b5ebccec22daf26a",
-    "MetadataAccess": [
-        "8ca121046bf811e2a2aa782bcb0741353301ccfceaa743e5b5ebccec22daf26a"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "8ca121046bf811e2a2aa782bcb0741353301ccfceaa743e5b5ebccec22daf26a;2018-11-15T16:40:07Z;toolService;toolService:service;U-Compare Paragraph-Breaking Service;Web service created by exporting UIMA-based workflow from the U-Compare text mining system.\nFunctionality: Identifies paragraphs in plain text\nTools in workflow: MLRS Paragraph Splitter (University of Malta)\nNOTE: The licence provided covers the web service only. Tools used to create the workflow may have their own licences;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f8a376c2-5bad-5acf-a91a-d3be7dac99d5",
-    "notes": [
-        "Web service created by exporting UIMA-based workflow from the U-Compare text mining system.\nFunctionality: Identifies paragraphs in plain text\nTools in workflow: MLRS Paragraph Splitter (University of Malta)\nNOTE: The licence provided covers the web service only. Tools used to create the workflow may have their own licences"
-    ],
-    "oai_identifier": [
-        "8ca121046bf811e2a2aa782bcb0741353301ccfceaa743e5b5ebccec22daf26a"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:service"
-    ],
-    "state": "active",
-    "title": [
-        "U-Compare Paragraph-Breaking Service"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f8a578be-b9ad-5da8-b09c-3b1a14178e5f.json b/oaitestdata/clarin-oai_dc/SET_1/json/f8a578be-b9ad-5da8-b09c-3b1a14178e5f.json
deleted file mode 100644
index b14696b1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f8a578be-b9ad-5da8-b09c-3b1a14178e5f.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Wroclaw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/zip",
-        "downloadable_files_count: 4",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/275",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/275"
-    ],
-    "PID": "http://hdl.handle.net/11321/275",
-    "PublicationTimestamp": "2016-06-02T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroclaw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "plWordNet",
-        "http://clarin-pl.eu/en/licenses/plwordnet-2/",
-        "PUB"
-    ],
-    "author": [
-        "Wroclaw University of Technology"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/275;2018-07-25T12:26:57Z;hdl_11321_3;hdl_11321_4;WordnetLoom 1.68.2;Wroclaw University of Technology;wordnet;lexical units;lexico-semantic relations;mapping;Princeton WordNet;bilingual;WordnetLoom \u2013 is an wordnet editor application built for the needs of the construction of a the largest Polish wordnet called plWordNet. WordnetLoom provides two means of interaction: a form-based, implemented initially, and a visual, graph-based introduced recently. The visual, graph-based interactive presentation of the wordnet structure enables browsing and its direct editing on the structure of lexico-semantic relations and synsets. WordnetLooms works in a distributed environment, i.e. several linguists can work simulanuously from different sites on the same central database.;2016-06-02;toolService;http://hdl.handle.net/11321/275;pol;eng;plWordNet;http://clarin-pl.eu/en/licenses/plwordnet-2/;PUB;text/plain; charset=utf-8;application/octet-stream;application/zip;application/zip;application/zip;downloadable_files_count: 4;Wroclaw University of Technology;http://nlp.pwr.wroc.pl/en/tools-and-resources/tools/wordnetloom",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f8a578be-b9ad-5da8-b09c-3b1a14178e5f",
-    "notes": [
-        "WordnetLoom \u2013 is an wordnet editor application built for the needs of the construction of a the largest Polish wordnet called plWordNet. WordnetLoom provides two means of interaction: a form-based, implemented initially, and a visual, graph-based introduced recently. The visual, graph-based interactive presentation of the wordnet structure enables browsing and its direct editing on the structure of lexico-semantic relations and synsets. WordnetLooms works in a distributed environment, i.e. several linguists can work simulanuously from different sites on the same central database."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/275"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "wordnet"
-        },
-        {
-            "name": "lexical units"
-        },
-        {
-            "name": "lexico-semantic relations"
-        },
-        {
-            "name": "mapping"
-        },
-        {
-            "name": "Princeton WordNet"
-        },
-        {
-            "name": "bilingual"
-        }
-    ],
-    "title": [
-        "WordnetLoom 1.68.2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f8b806dc-15a8-56ff-bcf1-b9034e8e8734.json b/oaitestdata/clarin-oai_dc/SET_1/json/f8b806dc-15a8-56ff-bcf1-b9034e8e8734.json
deleted file mode 100644
index 35eabd44..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f8b806dc-15a8-56ff-bcf1-b9034e8e8734.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-678",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-678"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-678",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Code of conduct"
-    ],
-    "SpatialCoverage": [
-        "United States"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-678;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Hocank corpus;Documentation of the Hocank project (DoBeS project);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-678;Code of conduct;downloadable_files_count: 0;United States;http://corpus1.mpi.nl/ds/imdi_browser/?openpath=MPI79487%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f8b806dc-15a8-56ff-bcf1-b9034e8e8734",
-    "notes": [
-        "Documentation of the Hocank project (DoBeS project)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-678"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Hocank corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f8c03c29-a3b5-52af-8b0c-7860b793cb1b.json b/oaitestdata/clarin-oai_dc/SET_1/json/f8c03c29-a3b5-52af-8b0c-7860b793cb1b.json
deleted file mode 100644
index 80d1bda1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f8c03c29-a3b5-52af-8b0c-7860b793cb1b.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "University of Ja\u00e9n (Spain)",
-        "European Organization for Nuclear Research (CERN)"
-    ],
-    "Contributor": [
-        "Montejo-R\u00e1ez, Arturo"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1312",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1312"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1312",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Ja\u00e9n (Spain)",
-        "European Organization for Nuclear Research (CERN)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain||Switzerland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Montejo-R\u00e1ez, Arturo"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1312;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Text Categorization Toolkit;Montejo-R\u00e1ez, Arturo;Montejo-R\u00e1ez, Arturo;text categorization;TECAT is a command-line tool for multi-label text categorization and evaluation. It is capable of combining multiple bases binary classifiers (built-in and external ones).;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1312;downloadable_files_count: 0;Spain||Switzerland;European Organization for Nuclear Research (CERN);University of Ja\u00e9n (Spain);http://sinai.ujaen.es/wiki/index.php/TeCat",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f8c03c29-a3b5-52af-8b0c-7860b793cb1b",
-    "notes": [
-        "TECAT is a command-line tool for multi-label text categorization and evaluation. It is capable of combining multiple bases binary classifiers (built-in and external ones)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1312"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "text categorization"
-        }
-    ],
-    "title": [
-        "Text Categorization Toolkit"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f8d20981-c4bb-5dd5-804b-81f7aae0d86a.json b/oaitestdata/clarin-oai_dc/SET_1/json/f8d20981-c4bb-5dd5-804b-81f7aae0d86a.json
deleted file mode 100644
index 6fe63598..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f8d20981-c4bb-5dd5-804b-81f7aae0d86a.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2800",
-    "MetadataAccess": [
-        "oai:ota:oucs:2800"
-    ],
-    "PublicationTimestamp": "1730-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1730"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2800;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2800.xml;Drapier's Letters II, To Mr. Harding;Swift, Jonathan, 1667-1745;1730;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f8d20981-c4bb-5dd5-804b-81f7aae0d86a",
-    "oai_identifier": [
-        "oai:ota:oucs:2800"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Drapier's Letters II, To Mr. Harding"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2800.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f8d3905c-b03f-5a2b-9160-de1a7259cf05.json b/oaitestdata/clarin-oai_dc/SET_1/json/f8d3905c-b03f-5a2b-9160-de1a7259cf05.json
deleted file mode 100644
index f21a1162..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f8d3905c-b03f-5a2b-9160-de1a7259cf05.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3110",
-    "MetadataAccess": [
-        "oai:ota:oucs:3110"
-    ],
-    "PublicationTimestamp": "1858-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1858"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gaskell, Elizabeth Cleghorn, 1810-1865"
-    ],
-    "fulltext": "oai:ota:oucs:3110;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3110.xml;Right at last;Gaskell, Elizabeth Cleghorn, 1810-1865;not after: 1858;text_and_corpus_linguistics;Fiction -- Great Britain -- 19th century;Short stories -- Great Britain -- 19th century;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f8d3905c-b03f-5a2b-9160-de1a7259cf05",
-    "oai_identifier": [
-        "oai:ota:oucs:3110"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Fiction -- Great Britain -- th century"
-        },
-        {
-            "name": "Short stories -- Great Britain -- th century"
-        }
-    ],
-    "title": [
-        "Right at last"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3110.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f8d6c495-b933-5379-8a22-9bf20ae180ec.json b/oaitestdata/clarin-oai_dc/SET_1/json/f8d6c495-b933-5379-8a22-9bf20ae180ec.json
deleted file mode 100644
index 51a5dbc7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f8d6c495-b933-5379-8a22-9bf20ae180ec.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4963",
-    "MetadataAccess": [
-        "oai:ota:oucs:4963"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Berkeley, George Monck, 1763-1793."
-    ],
-    "fulltext": "oai:ota:oucs:4963;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/4963.xml;Spanish memoirs: in a series of original letters. Containing the history of Donna Isabella della Villarea, ... Published by the author of Maria, or the generous rustic. In two volumes. ... [pt.2];Berkeley, George Monck, 1763-1793.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f8d6c495-b933-5379-8a22-9bf20ae180ec",
-    "oai_identifier": [
-        "oai:ota:oucs:4963"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Spanish memoirs: in a series of original letters. Containing the history of Donna Isabella della Villarea, ... Published by the author of Maria, or the generous rustic. In two volumes. ... [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4963.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f8eb7d76-340d-5798-b251-57ebda2df14e.json b/oaitestdata/clarin-oai_dc/SET_1/json/f8eb7d76-340d-5798-b251-57ebda2df14e.json
deleted file mode 100644
index 607c7ba3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f8eb7d76-340d-5798-b251-57ebda2df14e.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "VideoLectures.NET"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1070",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1070"
-    ],
-    "PID": "http://hdl.handle.net/11356/1070",
-    "PublicationTimestamp": "2016-08-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "VideoLectures.NET"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11356/1159"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by-nc-nd/4.0/"
-    ],
-    "author": [
-        "VideoLectures.NET"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1070;2018-10-18T22:25:50Z;hdl_11356_1023;hdl_11356_1024;Spoken corpus Gos VideoLectures 1.0 (audio);VideoLectures.NET;speech database;spoken corpus;academic speech;speech recognition;speech recordings;Gos VideoLectures is an add-on to the Gos reference speech corpus of Slovene (http://hdl.handle.net/11356/1040), and covers public academic speech. The Gos Videolectures recordings are a selection of public lectures available through web-portal Videolectures.net provided by the Jo\u017eef Stefan Institute, and covers in its first release 4.5 hours of speech. \r\nThis resource contains only the audio recordings of the corpus - the transcriptions are avaiable at CLARIN.SI handle http://hdl.handle.net/11356/1069.;2016-08-01;corpus;http://hdl.handle.net/11356/1070;slv;http://hdl.handle.net/11356/1159;Creative Commons - Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0);PUB;https://creativecommons.org/licenses/by-nc-nd/4.0/;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;VideoLectures.NET",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f8eb7d76-340d-5798-b251-57ebda2df14e",
-    "notes": [
-        "Gos VideoLectures is an add-on to the Gos reference speech corpus of Slovene (http://hdl.handle.net/11356/1040), and covers public academic speech. The Gos Videolectures recordings are a selection of public lectures available through web-portal Videolectures.net provided by the Jo\u017eef Stefan Institute, and covers in its first release 4.5 hours of speech. \r\nThis resource contains only the audio recordings of the corpus - the transcriptions are avaiable at CLARIN.SI handle http://hdl.handle.net/11356/1069."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1070"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech database"
-        },
-        {
-            "name": "spoken corpus"
-        },
-        {
-            "name": "academic speech"
-        },
-        {
-            "name": "speech recognition"
-        },
-        {
-            "name": "speech recordings"
-        }
-    ],
-    "title": [
-        "Spoken corpus Gos VideoLectures 1.0 (audio)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f8ebd7d1-ec94-5356-bfdf-9f6760181bd0.json b/oaitestdata/clarin-oai_dc/SET_1/json/f8ebd7d1-ec94-5356-bfdf-9f6760181bd0.json
deleted file mode 100644
index 74ed3ae7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f8ebd7d1-ec94-5356-bfdf-9f6760181bd0.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Croatian",
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1058",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1058"
-    ],
-    "PID": "http://hdl.handle.net/11356/1058",
-    "PublicationTimestamp": "2016-03-09T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/324414"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN.SI User Licence for Internet Corpora",
-        "http://www.clarin.si/info/wp-content/uploads/2016/01/CLARIN.SI-WAC-2016-01.pdf",
-        "ACA"
-    ],
-    "author": [
-        "Espl\u00e0-Gomis, Miquel",
-        "Klubi\u010dka, Filip",
-        "Ortiz Rojas, Sergio",
-        "Ljube\u0161i\u0107, Nikola",
-        "Toral, Antonio"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1058;2017-06-27T18:08:06Z;hdl_11356_1023;hdl_11356_1024;Croatian-English parallel corpus hrenWaC 2.0;Ljube\u0161i\u0107, Nikola;Espl\u00e0-Gomis, Miquel;Ortiz Rojas, Sergio;Klubi\u010dka, Filip;Toral, Antonio;parallel corpus;web corpus;multilingual;The hrenWaC corpus version 2.0 consists of parallel Croatian-English texts crawled from the .hr top-level domain for Croatia. The corpus was built with Spidextor (https://github.com/abumatran/spidextor), a tool that glues together the output of SpiderLing used for crawling and Bitextor used for bitext extraction. The accuracy of the extracted bitext on the segment level is around 80% and on the word level around 84%.;2016-03-09;corpus;http://hdl.handle.net/11356/1058;hrv;eng;info:eu-repo/grantAgreement/EC/FP7/324414;CLARIN.SI User Licence for Internet Corpora;http://www.clarin.si/info/wp-content/uploads/2016/01/CLARIN.SI-WAC-2016-01.pdf;ACA;application/octet-stream;text/plain; charset=utf-8;downloadable_files_count: 1;Jo\u017eef Stefan Institute;http://nlp.ffzg.hr/resources/corpora/hrenwac/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f8ebd7d1-ec94-5356-bfdf-9f6760181bd0",
-    "notes": [
-        "The hrenWaC corpus version 2.0 consists of parallel Croatian-English texts crawled from the .hr top-level domain for Croatia. The corpus was built with Spidextor (https://github.com/abumatran/spidextor), a tool that glues together the output of SpiderLing used for crawling and Bitextor used for bitext extraction. The accuracy of the extracted bitext on the segment level is around 80% and on the word level around 84%."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1058"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "parallel corpus"
-        },
-        {
-            "name": "web corpus"
-        },
-        {
-            "name": "multilingual"
-        }
-    ],
-    "title": [
-        "Croatian-English parallel corpus hrenWaC 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f91a612c-89d6-5a63-a1f1-0de7981959bc.json b/oaitestdata/clarin-oai_dc/SET_1/json/f91a612c-89d6-5a63-a1f1-0de7981959bc.json
deleted file mode 100644
index 94675bd7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f91a612c-89d6-5a63-a1f1-0de7981959bc.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Catalan",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1175",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1175"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1175",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1175;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;B\u00fastia Neol\u00f2gica Escolar;Terminology management;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1175;cat;spa;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra;http://obneo.iula.upf.edu/bustiaInfantil/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f91a612c-89d6-5a63-a1f1-0de7981959bc",
-    "notes": [
-        "Terminology management"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1175"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "B\u00fastia Neol\u00f2gica Escolar"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f926671e-3536-5e7e-a8da-57a48ada9111.json b/oaitestdata/clarin-oai_dc/SET_1/json/f926671e-3536-5e7e-a8da-57a48ada9111.json
deleted file mode 100644
index 33feaa15..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f926671e-3536-5e7e-a8da-57a48ada9111.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/300",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/300"
-    ],
-    "PID": "http://hdl.handle.net/11321/300",
-    "PublicationTimestamp": "2016-02-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU GPL3",
-        "http://www.gnu.org/licenses/gpl-3.0.en.html",
-        "PUB"
-    ],
-    "author": [
-        "Eder, Maciej",
-        "Piasecki, Maciej",
-        "Walkowiak, Tomasz"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/300;2016-06-06T15:17:09Z;hdl_11321_3;hdl_11321_4;WebStylo;Piasecki, Maciej;Eder, Maciej;Walkowiak, Tomasz;stylometry;text clustering;NLP;Web based, open stylometry system based on Multilevel Text Analysis. Runs cluto and stylo (R system) clusterisation  methods. Based on Natural Language Processing Workflow engine (included in the distribution).;2016-02-01;toolService;http://hdl.handle.net/11321/300;pol;GNU GPL3;http://www.gnu.org/licenses/gpl-3.0.en.html;PUB;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;Wroc\u0142aw University of Science and Technology;http://clarin-pl.eu",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f926671e-3536-5e7e-a8da-57a48ada9111",
-    "notes": [
-        "Web based, open stylometry system based on Multilevel Text Analysis. Runs cluto and stylo (R system) clusterisation  methods. Based on Natural Language Processing Workflow engine (included in the distribution)."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/300"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "stylometry"
-        },
-        {
-            "name": "text clustering"
-        },
-        {
-            "name": "NLP"
-        }
-    ],
-    "title": [
-        "WebStylo"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f936244b-70f3-5ce8-9a3c-4318116e1648.json b/oaitestdata/clarin-oai_dc/SET_1/json/f936244b-70f3-5ce8-9a3c-4318116e1648.json
deleted file mode 100644
index c6c90b46..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f936244b-70f3-5ce8-9a3c-4318116e1648.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5674",
-    "MetadataAccess": [
-        "oai:ota:oucs:5674"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Turner, Matthew, d. ca. 1788."
-    ],
-    "fulltext": "oai:ota:oucs:5674;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5674.xml;An account of the extraordinary medicinal fluid, called \u00c3\u00a6ther: By M. Turner, ...;Turner, Matthew, d. ca. 1788.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f936244b-70f3-5ce8-9a3c-4318116e1648",
-    "oai_identifier": [
-        "oai:ota:oucs:5674"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An account of the extraordinary medicinal fluid, called \u00c3\u00a6ther: By M. Turner, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5674.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f94a8bdf-0efa-51b2-a8e5-0f2f63ced5b2.json b/oaitestdata/clarin-oai_dc/SET_1/json/f94a8bdf-0efa-51b2-a8e5-0f2f63ced5b2.json
deleted file mode 100644
index 3176f3fc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f94a8bdf-0efa-51b2-a8e5-0f2f63ced5b2.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1416",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1416"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1416",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1416;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;iula_tokenizer;Text tokenizer (the text tokenizer requires that the input text be in plain text format (file.txt) and UTF-8 encoded).;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1416;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f94a8bdf-0efa-51b2-a8e5-0f2f63ced5b2",
-    "notes": [
-        "Text tokenizer (the text tokenizer requires that the input text be in plain text format (file.txt) and UTF-8 encoded)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1416"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "iula_tokenizer"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f95e9584-d1ba-5357-bc51-5bf89f4b8520.json b/oaitestdata/clarin-oai_dc/SET_1/json/f95e9584-d1ba-5357-bc51-5bf89f4b8520.json
deleted file mode 100644
index 0e48e288..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f95e9584-d1ba-5357-bc51-5bf89f4b8520.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "text/html"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-948",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-948"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-948",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "http://titus.uni-frankfurt.de/texte/texte2.htm#Estart"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-948;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TITUS Oscan and Umbrian;ca. 30.000 tokens; linked with relational database; XML-encoding in progress;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-948;http://titus.uni-frankfurt.de/texte/texte2.htm#Estart;text/html;downloadable_files_count: 0;Germany;http://titus.uni-frankfurt.de/texte/texte2.htm#osk",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f95e9584-d1ba-5357-bc51-5bf89f4b8520",
-    "notes": [
-        "ca. 30.000 tokens; linked with relational database; XML-encoding in progress"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-948"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "TITUS Oscan and Umbrian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f96df0c4-d053-5236-97c4-9ef555873f9f.json b/oaitestdata/clarin-oai_dc/SET_1/json/f96df0c4-d053-5236-97c4-9ef555873f9f.json
deleted file mode 100644
index 2c2ba1b9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f96df0c4-d053-5236-97c4-9ef555873f9f.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 2",
-        "text/html",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2906",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2906"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2906",
-    "PublicationTimestamp": "2018-12-20T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "M\u00edrovsk\u00fd, Ji\u0159\u00ed",
-        "Zik\u00e1nov\u00e1, \u0160\u00e1rka",
-        "Synkov\u00e1, Pavl\u00edna"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2906;2018-12-19T11:19:55Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Enriched Discourse Annotation of PDiT Subset 1.0 (PDiT-EDA 1.0);Zik\u00e1nov\u00e1, \u0160\u00e1rka;Synkov\u00e1, Pavl\u00edna;M\u00edrovsk\u00fd, Ji\u0159\u00ed;discourse annotation;implicit discourse relations;Enriched discourse annotation of a subset of the Prague Discourse Treebank, adding implicit relations, entity based relations, question-answer relations and other discourse structuring phenomena.;2018-12-20;corpus;http://hdl.handle.net/11234/1-2906;ces;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;text/html;application/zip;text/plain; charset=utf-8;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://ufal.mff.cuni.cz/pdit-eda1.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f96df0c4-d053-5236-97c4-9ef555873f9f",
-    "notes": [
-        "Enriched discourse annotation of a subset of the Prague Discourse Treebank, adding implicit relations, entity based relations, question-answer relations and other discourse structuring phenomena."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2906"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "discourse annotation"
-        },
-        {
-            "name": "implicit discourse relations"
-        }
-    ],
-    "title": [
-        "Enriched Discourse Annotation of PDiT Subset 1.0 (PDiT-EDA 1.0)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f985f2b7-0453-52e8-ac4e-e05c7d7b39f5.json b/oaitestdata/clarin-oai_dc/SET_1/json/f985f2b7-0453-52e8-ac4e-e05c7d7b39f5.json
deleted file mode 100644
index 7f92ba84..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f985f2b7-0453-52e8-ac4e-e05c7d7b39f5.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Centro de Tecnolog\u00edas y Aplicaciones del Lenguaje y del Habla (TALP)"
-    ],
-    "Contributor": [
-        "Rodriguez, Horacio"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Catalan",
-        "English",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1219",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1219"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1219",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Centro de Tecnolog\u00edas y Aplicaciones del Lenguaje y del Habla (TALP)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1219;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LCsum (Document Summarizer);Rodriguez, Horacio;Document summarizer.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1219;cat;eng;spa;downloadable_files_count: 0;Spain;Centro de Tecnolog\u00edas y Aplicaciones del Lenguaje y del Habla (TALP);http://nlp.lsi.upc.edu/lcsum/demo",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f985f2b7-0453-52e8-ac4e-e05c7d7b39f5",
-    "notes": [
-        "Document summarizer."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1219"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LCsum (Document Summarizer)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f99cbf07-c055-56e5-94f2-ddd1be27080e.json b/oaitestdata/clarin-oai_dc/SET_1/json/f99cbf07-c055-56e5-94f2-ddd1be27080e.json
deleted file mode 100644
index 08ad7a5a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f99cbf07-c055-56e5-94f2-ddd1be27080e.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "Contributor": [
-        "Variaci\u00f3, Iula"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Catalan",
-        "English",
-        "Spanish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1113",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1113"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1113",
-    "PublicationTimestamp": "1993-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1993"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1113;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Corpus biling\u00fce d\u2019alternan\u00e7a de lleng\u00fces (codeswitching);Variaci\u00f3, Iula;speech corpus;8 interactive recordings of group dynamics. Bilingual speakers (L1 -> English; L1 -> Catalan/Spanish).;1993;corpus;http://hdl.handle.net/11372/LRT-1113;cat;eng;spa;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra;http://www.iula.upf.edu/recurs08ca.htm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f99cbf07-c055-56e5-94f2-ddd1be27080e",
-    "notes": [
-        "8 interactive recordings of group dynamics. Bilingual speakers (L1 -> English; L1 -> Catalan/Spanish)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1113"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "speech corpus"
-        }
-    ],
-    "title": [
-        "Corpus biling\u00fce d\u2019alternan\u00e7a de lleng\u00fces (codeswitching)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f99e0912-4d8a-54a8-8c66-f02f1b175d56.json b/oaitestdata/clarin-oai_dc/SET_1/json/f99e0912-4d8a-54a8-8c66-f02f1b175d56.json
deleted file mode 100644
index 7804f116..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f99e0912-4d8a-54a8-8c66-f02f1b175d56.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Norges Handelsh\u00f8yskole"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Norwegian Bokm\u00e5l",
-        "Norwegian Nynorsk",
-        "English",
-        "German",
-        "French"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.clarino.uib.no:11509/75",
-    "MetadataAccess": [
-        "oai:repo.clarino.uib.no:11509/75"
-    ],
-    "PID": "http://hdl.handle.net/11509/75",
-    "PublicationTimestamp": "2013-09-20T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Norges Handelsh\u00f8yskole"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "CLARIN-ACA-NC",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NC=1&NORED=1",
-        "ACA"
-    ],
-    "author": [
-        "Olstad, Vemund"
-    ],
-    "fulltext": "oai:repo.clarino.uib.no:11509/75;2016-04-15T05:59:20Z;hdl_11509_1;hdl_11509_2;NOT-basen;Olstad, Vemund;Termbase;Nhh;Not;Norsk Termbank;NOT-basen is a TBX-export of a terminology database developed by Norsk termbank. This termbase is to be considered an historical resource, and has not been updated for a while.;2013-09-20;lexicalConceptualResource;http://hdl.handle.net/11509/75;nob;nno;eng;deu;fra;CLARIN-ACA-NC;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NC=1&NORED=1;ACA;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Norges Handelsh\u00f8yskole;http://www.terminologi.no",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f99e0912-4d8a-54a8-8c66-f02f1b175d56",
-    "notes": [
-        "NOT-basen is a TBX-export of a terminology database developed by Norsk termbank. This termbase is to be considered an historical resource, and has not been updated for a while."
-    ],
-    "oai_identifier": [
-        "oai:repo.clarino.uib.no:11509/75"
-    ],
-    "oai_set": [
-        "hdl_11509_1",
-        "hdl_11509_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Termbase"
-        },
-        {
-            "name": "Nhh"
-        },
-        {
-            "name": "Norsk Termbank"
-        }
-    ],
-    "title": [
-        "NOT-basen"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f9a95a82-dd13-5103-93cc-731ca10b539e.json b/oaitestdata/clarin-oai_dc/SET_1/json/f9a95a82-dd13-5103-93cc-731ca10b539e.json
deleted file mode 100644
index 8d3ee3ec..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f9a95a82-dd13-5103-93cc-731ca10b539e.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Dedenbach-Salazar, Dr Sabine"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-682",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-682"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-682",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Code of conduct"
-    ],
-    "SpatialCoverage": [
-        "Bolivia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-682;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Chipaya;Dedenbach-Salazar, Dr Sabine;Documentation of the Chipaya project (DoBeS project);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-682;Code of conduct;downloadable_files_count: 0;Bolivia;http://corpus1.mpi.nl/ds/imdi_browser/?openpath=MPI533706%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f9a95a82-dd13-5103-93cc-731ca10b539e",
-    "notes": [
-        "Documentation of the Chipaya project (DoBeS project)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-682"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Chipaya"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f9c08bf4-1622-5b65-a04e-4245670928c4.json b/oaitestdata/clarin-oai_dc/SET_1/json/f9c08bf4-1622-5b65-a04e-4245670928c4.json
deleted file mode 100644
index f20e1140..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f9c08bf4-1622-5b65-a04e-4245670928c4.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2635",
-    "MetadataAccess": [
-        "oai:ota:oucs:2635"
-    ],
-    "PublicationTimestamp": "1709-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1709"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2635;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2635.xml;A letter concerning the sacramental test;Swift, Jonathan, 1667-1745;1709;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f9c08bf4-1622-5b65-a04e-4245670928c4",
-    "oai_identifier": [
-        "oai:ota:oucs:2635"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A letter concerning the sacramental test"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2635.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f9ec8b1b-1197-596c-b9f6-1dbcc54fbb75.json b/oaitestdata/clarin-oai_dc/SET_1/json/f9ec8b1b-1197-596c-b9f6-1dbcc54fbb75.json
deleted file mode 100644
index 7e966326..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f9ec8b1b-1197-596c-b9f6-1dbcc54fbb75.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=9a410010830e11e5a2aa782bcb0741357950092357fd4b7c97f39c12ea6a81cc",
-    "MetadataAccess": [
-        "9a410010830e11e5a2aa782bcb0741357950092357fd4b7c97f39c12ea6a81cc"
-    ],
-    "PublicationTimestamp": "2015-11-04T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "9a410010830e11e5a2aa782bcb0741357950092357fd4b7c97f39c12ea6a81cc;2018-11-15T16:40:18Z;lexicalConceptualResource;lexicalConceptualResource:lexicon;QTLeap specialized lexicons;This  resource  is  part  of  Deliverable  5.7  of  the  European  Comission  project QTLeap  FP7-ICT-2013.4.1-610516  (http://qtleap.eu).\n\nThis gazetteer comprises multilingual lexicon entries used for the translation of specific IT domain expressions for Basque, Bulgarian, Czech, Dutch, English, Portuguese and Spanish. The expressions were collected, on the one hand, from the freely available software localization files, such as VLC, Libre Office and KDE, and on the other hand, from IT-related Wikipedia articles. \n;2015-11-04",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f9ec8b1b-1197-596c-b9f6-1dbcc54fbb75",
-    "notes": [
-        "This  resource  is  part  of  Deliverable  5.7  of  the  European  Comission  project QTLeap  FP7-ICT-2013.4.1-610516  (http://qtleap.eu).\n\nThis gazetteer comprises multilingual lexicon entries used for the translation of specific IT domain expressions for Basque, Bulgarian, Czech, Dutch, English, Portuguese and Spanish. The expressions were collected, on the one hand, from the freely available software localization files, such as VLC, Libre Office and KDE, and on the other hand, from IT-related Wikipedia articles. \n"
-    ],
-    "oai_identifier": [
-        "9a410010830e11e5a2aa782bcb0741357950092357fd4b7c97f39c12ea6a81cc"
-    ],
-    "oai_set": [
-        "lexicalConceptualResource",
-        "lexicalConceptualResource:lexicon"
-    ],
-    "state": "active",
-    "title": [
-        "QTLeap specialized lexicons"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/f9f97061-fe8c-5197-8b69-72c829dc136b.json b/oaitestdata/clarin-oai_dc/SET_1/json/f9f97061-fe8c-5197-8b69-72c829dc136b.json
deleted file mode 100644
index e266e7a7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/f9f97061-fe8c-5197-8b69-72c829dc136b.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=64a9ea62ab2a11e1a404080027e73ea20629cdaa8f7f48bc9b6bd79589d1c250",
-    "MetadataAccess": [
-        "64a9ea62ab2a11e1a404080027e73ea20629cdaa8f7f48bc9b6bd79589d1c250"
-    ],
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "64a9ea62ab2a11e1a404080027e73ea20629cdaa8f7f48bc9b6bd79589d1c250;2018-11-15T16:39:42Z;corpus;corpus:audio;F_Mona_1/ Spoken Newspaper;108 WAV files of spoken Maltese newspaper texts, subdivided into 12 directories with a variable number of sentences (sometimes: clauses) each. They come together with transcriptions and tables of phoneme durations.;2015-12-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f9f97061-fe8c-5197-8b69-72c829dc136b",
-    "notes": [
-        "108 WAV files of spoken Maltese newspaper texts, subdivided into 12 directories with a variable number of sentences (sometimes: clauses) each. They come together with transcriptions and tables of phoneme durations."
-    ],
-    "oai_identifier": [
-        "64a9ea62ab2a11e1a404080027e73ea20629cdaa8f7f48bc9b6bd79589d1c250"
-    ],
-    "oai_set": [
-        "corpus",
-        "corpus:audio"
-    ],
-    "state": "active",
-    "title": [
-        "F_Mona_1/ Spoken Newspaper"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fa33e9b6-08ec-5b6e-bbb0-bb9fe9a6cae2.json b/oaitestdata/clarin-oai_dc/SET_1/json/fa33e9b6-08ec-5b6e-bbb0-bb9fe9a6cae2.json
deleted file mode 100644
index 9597d99a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fa33e9b6-08ec-5b6e-bbb0-bb9fe9a6cae2.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=8c1eb5e05e5e11e2a2aa782bcb0741354078b3f879454f1995c6c93c8897b00f",
-    "MetadataAccess": [
-        "8c1eb5e05e5e11e2a2aa782bcb0741354078b3f879454f1995c6c93c8897b00f"
-    ],
-    "PublicationTimestamp": "2015-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "8c1eb5e05e5e11e2a2aa782bcb0741354078b3f879454f1995c6c93c8897b00f;2018-11-15T16:40:01Z;toolService;toolService:tool;MLSS Chunker;The MLSS (Maltese Language Software Services) Chunker is an online tool which looks for sequences of part-of-speech tags in a tagged text, using one or more patterns that capture the typical members of, say, a noun phrase, and returning a list of chunks from the text that match the searched patterns. \n\nThe download for this resource only contains the narrative description in a Word file. The tool itself is delivered as a GUI, which features:\n- a panel of buttons representing the POS tags, showing the corresponding description on mouse over.\n- a text box which allows the user to enter the pattern of the chunks, and\n- a text area where the user inputs the text\n\nThe user types or pastes text into the large text box on the bottom of the page and then enters a search pattern into the smaller text box above:\n\nThe user can specify patterns of:\n- POS; these being preceded by '_'. Example, _DDC _NN\n- words; string containing no '_'. Example, 'il- ?' (where the '?' represents anything which follows that word)\n- tagged words; being the most specific. Example, 'il-_DDC ?'\n\nInstead of typing in the search patterns, the user can also click on the buttons in the panel on the left-hand side of the page.\n\nAfterwards, the user clicks on \u00e2\u0080\u009cProcess\u00e2\u0080\u009d to start the chunking process. The user is then directed to a page \u00e2\u0080\u009cChunker Result\u00e2\u0080\u009d, which shows the tagged and extracted chunks in a text box. \n\nThe input data format is text string typed or copied into an input text box, and search patterns typed or copied into a search box.\nThe output data format consists of text sub-strings (i.e. tagged text chunks) of the input string, with one chunk per line. \n\nThis is the first version of the chunker. Therefore, there may be bugs and room for improvement.;2015-12-11",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fa33e9b6-08ec-5b6e-bbb0-bb9fe9a6cae2",
-    "notes": [
-        "The MLSS (Maltese Language Software Services) Chunker is an online tool which looks for sequences of part-of-speech tags in a tagged text, using one or more patterns that capture the typical members of, say, a noun phrase, and returning a list of chunks from the text that match the searched patterns. \n\nThe download for this resource only contains the narrative description in a Word file. The tool itself is delivered as a GUI, which features:\n- a panel of buttons representing the POS tags, showing the corresponding description on mouse over.\n- a text box which allows the user to enter the pattern of the chunks, and\n- a text area where the user inputs the text\n\nThe user types or pastes text into the large text box on the bottom of the page and then enters a search pattern into the smaller text box above:\n\nThe user can specify patterns of:\n- POS; these being preceded by '_'. Example, _DDC _NN\n- words; string containing no '_'. Example, 'il- ?' (where the '?' represents anything which follows that word)\n- tagged words; being the most specific. Example, 'il-_DDC ?'\n\nInstead of typing in the search patterns, the user can also click on the buttons in the panel on the left-hand side of the page.\n\nAfterwards, the user clicks on \u00e2\u0080\u009cProcess\u00e2\u0080\u009d to start the chunking process. The user is then directed to a page \u00e2\u0080\u009cChunker Result\u00e2\u0080\u009d, which shows the tagged and extracted chunks in a text box. \n\nThe input data format is text string typed or copied into an input text box, and search patterns typed or copied into a search box.\nThe output data format consists of text sub-strings (i.e. tagged text chunks) of the input string, with one chunk per line. \n\nThis is the first version of the chunker. Therefore, there may be bugs and room for improvement."
-    ],
-    "oai_identifier": [
-        "8c1eb5e05e5e11e2a2aa782bcb0741354078b3f879454f1995c6c93c8897b00f"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "MLSS Chunker"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fa48a591-8ee1-58c1-9e2f-aa2e328441ad.json b/oaitestdata/clarin-oai_dc/SET_1/json/fa48a591-8ee1-58c1-9e2f-aa2e328441ad.json
deleted file mode 100644
index aed5aa26..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fa48a591-8ee1-58c1-9e2f-aa2e328441ad.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2686",
-    "MetadataAccess": [
-        "oai:ota:oucs:2686"
-    ],
-    "PublicationTimestamp": "1727-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1727"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2686;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2686.xml;The accomplishment of the first of Mr. Bickerstaff's predictions;Swift, Jonathan, 1667-1745;1727;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fa48a591-8ee1-58c1-9e2f-aa2e328441ad",
-    "oai_identifier": [
-        "oai:ota:oucs:2686"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The accomplishment of the first of Mr. Bickerstaff's predictions"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2686.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fa5d977f-0f31-55a6-9b38-4bfe996d8066.json b/oaitestdata/clarin-oai_dc/SET_1/json/fa5d977f-0f31-55a6-9b38-4bfe996d8066.json
deleted file mode 100644
index 626d7c38..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fa5d977f-0f31-55a6-9b38-4bfe996d8066.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "between 512 KB and 1 MB "
-    ],
-    "Language": [
-        "Ancient Greek (to 1453)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0517",
-    "MetadataAccess": [
-        "oai:ota:oucs:0517"
-    ],
-    "PublicationYear": [
-        "468 BCE-405 BCE"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Although this resource has been deposited with us, it is not currently available for re-use by others.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Sophocles"
-    ],
-    "fulltext": "oai:ota:oucs:0517;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0517.xml; Collected works  / compiled by Thesaurus Linguae Graecae;Sophocles;468 BCE-405 BCE;text_and_corpus_linguistics;Plays -- Greece -- 5th century BC;grc;Oxford Text Archive, University of Oxford;between 512 KB and 1 MB ;Text;Plays;Although this resource has been deposited with us, it is not currently available for re-use by others.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fa5d977f-0f31-55a6-9b38-4bfe996d8066",
-    "oai_identifier": [
-        "oai:ota:oucs:0517"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- Greece -- th century BC"
-        }
-    ],
-    "title": [
-        " Collected works  / compiled by Thesaurus Linguae Graecae"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0517.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fa5ed0eb-2fd1-5211-947d-3c6de1e3c791.json b/oaitestdata/clarin-oai_dc/SET_1/json/fa5ed0eb-2fd1-5211-947d-3c6de1e3c791.json
deleted file mode 100644
index d1e85df6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fa5ed0eb-2fd1-5211-947d-3c6de1e3c791.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-332",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-332"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-332",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-332;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Wikipedia Geocoding and Reverse Geocoding;REST-alike (normal and reverse) geocoding based on names or languages.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-332;downloadable_files_count: 0;http://www.geonames.org/export/wikipedia-webservice.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fa5ed0eb-2fd1-5211-947d-3c6de1e3c791",
-    "notes": [
-        "REST-alike (normal and reverse) geocoding based on names or languages."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-332"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Wikipedia Geocoding and Reverse Geocoding"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fa6380e1-0159-5b69-b3e5-910fcd400fee.json b/oaitestdata/clarin-oai_dc/SET_1/json/fa6380e1-0159-5b69-b3e5-910fcd400fee.json
deleted file mode 100644
index faf8a47b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fa6380e1-0159-5b69-b3e5-910fcd400fee.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-43CE-E",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-43CE-E"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-43CE-E",
-    "PublicationTimestamp": "2014-02-14T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Straka, Milan",
-        "Strakov\u00e1, Jana"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-43CE-E;2018-07-02T22:05:51Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;NameTag;Straka, Milan;Strakov\u00e1, Jana;named entity recognizer;NameTag is an open-source tool for named entity recognition (NER). NameTag identifies proper names in text and classifies them into predefined categories, such as names of persons, locations, organizations, etc. NameTag is distributed as a standalone tool or a library, along with trained linguistic models. In the Czech language, NameTag achieves state-of-the-art performance (Strakov\u00e1 et al. 2013). NameTag is a free software under LGPL license and the linguistic models are free for non-commercial use and distributed under CC BY-NC-SA license, although for some models the original data used to create the model may impose additional licensing conditions.;2014-02-14;toolService;http://hdl.handle.net/11858/00-097C-0000-0023-43CE-E;eng;downloadable_files_count: 0;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/nametag",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fa6380e1-0159-5b69-b3e5-910fcd400fee",
-    "notes": [
-        "NameTag is an open-source tool for named entity recognition (NER). NameTag identifies proper names in text and classifies them into predefined categories, such as names of persons, locations, organizations, etc. NameTag is distributed as a standalone tool or a library, along with trained linguistic models. In the Czech language, NameTag achieves state-of-the-art performance (Strakov\u00e1 et al. 2013). NameTag is a free software under LGPL license and the linguistic models are free for non-commercial use and distributed under CC BY-NC-SA license, although for some models the original data used to create the model may impose additional licensing conditions."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-43CE-E"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "named entity recognizer"
-        }
-    ],
-    "title": [
-        "NameTag"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fa7682fa-ba35-52c7-aab4-c3a971d23fec.json b/oaitestdata/clarin-oai_dc/SET_1/json/fa7682fa-ba35-52c7-aab4-c3a971d23fec.json
deleted file mode 100644
index 5b0316be..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fa7682fa-ba35-52c7-aab4-c3a971d23fec.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "Contributor": [
-        "Moreira, Andre",
-        "Windhouwer, Menzo"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1221",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1221"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1221",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1221;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LEXUS;Windhouwer, Menzo;Moreira, Andre;LEXUS is the web based lexicon tool currently being developed by The Language Archive at the MPI;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1221;downloadable_files_count: 0;Netherlands (the);Max Planck Institute for Psycholinguistics;http://tla.mpi.nl/tools/tla-tools/lexus/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fa7682fa-ba35-52c7-aab4-c3a971d23fec",
-    "notes": [
-        "LEXUS is the web based lexicon tool currently being developed by The Language Archive at the MPI"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1221"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LEXUS"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fa798a71-599d-51bf-9ca9-df87439c4753.json b/oaitestdata/clarin-oai_dc/SET_1/json/fa798a71-599d-51bf-9ca9-df87439c4753.json
deleted file mode 100644
index c2018d42..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fa798a71-599d-51bf-9ca9-df87439c4753.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "IFA-groep, University of Amsterdam"
-    ],
-    "Contributor": [
-        "Son, R.J.J.H. van"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-576",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-576"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-576",
-    "PublicationTimestamp": "2008-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2008"
-    ],
-    "Publisher": [
-        "IFA-groep, University of Amsterdam"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU GPL"
-    ],
-    "SpatialCoverage": [
-        "Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-576;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;IFA dialog video corpus;Son, R.J.J.H. van;A video collection of spontaneous speech dialogues of 42 participants (14m, 28f);2008;corpus;http://hdl.handle.net/11372/LRT-576;nld;GNU GPL;downloadable_files_count: 0;Netherlands (the);IFA-groep, University of Amsterdam;http://www.fon.hum.uva.nl/IFA-SpokenLanguageCorpora/IFADVcorpus/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fa798a71-599d-51bf-9ca9-df87439c4753",
-    "notes": [
-        "A video collection of spontaneous speech dialogues of 42 participants (14m, 28f)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-576"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "IFA dialog video corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/faa87352-4ecd-5c0e-924a-8e4eb1f68079.json b/oaitestdata/clarin-oai_dc/SET_1/json/faa87352-4ecd-5c0e-924a-8e4eb1f68079.json
deleted file mode 100644
index 2f8529fb..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/faa87352-4ecd-5c0e-924a-8e4eb1f68079.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "between 1 and 2 MB"
-    ],
-    "Language": [
-        "Old English (ca. 450-1100)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0586",
-    "MetadataAccess": [
-        "oai:ota:oucs:0586"
-    ],
-    "PublicationTimestamp": "1100-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1100"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:0586;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0586.xml;The Anglo-Saxon poetic records / compiled by Gregory Hidley;450-1100;text_and_corpus_linguistics;Poems -- England;ang;Oxford Text Archive, University of Oxford;between 1 and 2 MB;Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "faa87352-4ecd-5c0e-924a-8e4eb1f68079",
-    "oai_identifier": [
-        "oai:ota:oucs:0586"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- England"
-        }
-    ],
-    "title": [
-        "The Anglo-Saxon poetic records / compiled by Gregory Hidley"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0586.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fab35ff5-1130-5458-91ac-d83c02209f42.json b/oaitestdata/clarin-oai_dc/SET_1/json/fab35ff5-1130-5458-91ac-d83c02209f42.json
deleted file mode 100644
index 4aa56e24..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fab35ff5-1130-5458-91ac-d83c02209f42.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Marek Troszy\u0144ski"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 4",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/156",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/156"
-    ],
-    "PID": "http://hdl.handle.net/11321/156",
-    "PublicationTimestamp": "2015-04-14T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Marek Troszy\u0144ski"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 3.0 Unported (CC BY 3.0)",
-        "http://creativecommons.org/licenses/by/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Troszynski, Marek"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/156;2015-04-14T12:52:47Z;hdl_11321_3;hdl_11321_4;romowie_01;Troszynski, Marek;maly plik;2015-04-14;corpus;http://hdl.handle.net/11321/156;pol;Creative Commons - Attribution 3.0 Unported (CC BY 3.0);http://creativecommons.org/licenses/by/3.0/;CC;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/zip;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 4;Marek Troszy\u0144ski",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fab35ff5-1130-5458-91ac-d83c02209f42",
-    "notes": [
-        "maly plik"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/156"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "romowie_01"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fab5c6da-f732-527c-8440-ee712450f658.json b/oaitestdata/clarin-oai_dc/SET_1/json/fab5c6da-f732-527c-8440-ee712450f658.json
deleted file mode 100644
index af34a3b4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fab5c6da-f732-527c-8440-ee712450f658.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "NLX-Natural Language and Speech Group, University of Lisbon"
-    ],
-    "Contributor": [
-        "Branco, Ant\u00f3nio"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Portuguese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1232",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1232"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1232",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "NLX-Natural Language and Speech Group, University of Lisbon"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Portugal"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1232;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;LXService;Branco, Ant\u00f3nio;LXService is a webservice of language technology for Portuguese providing authenticated access to the functionalities offered by the tools LX-Splitter, LX-Tokenizer and LX-Tagger.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1232;por;downloadable_files_count: 0;Portugal;NLX-Natural Language and Speech Group, University of Lisbon;http://lxsuite.di.fc.ul.pt/lxServiceClient.v1.0.zip",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fab5c6da-f732-527c-8440-ee712450f658",
-    "notes": [
-        "LXService is a webservice of language technology for Portuguese providing authenticated access to the functionalities offered by the tools LX-Splitter, LX-Tokenizer and LX-Tagger."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1232"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "LXService"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fabd446b-5673-538f-a5f6-92323fd4df50.json b/oaitestdata/clarin-oai_dc/SET_1/json/fabd446b-5673-538f-a5f6-92323fd4df50.json
deleted file mode 100644
index 5fc62da8..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fabd446b-5673-538f-a5f6-92323fd4df50.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contributor": [
-        "Teodorescu, Prof. Horia Nicolai"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Romanian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-190",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-190"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-190",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Romania"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-190;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Voiced Sounds of Romanian Language;Teodorescu, Prof. Horia Nicolai;Recordings of vowels, consonants, diphthongs, sentences;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-190;ron;downloadable_files_count: 0;Romania;http://www.etc.tuiasi.ro/sibm/romanian_spoken_language/index.htm",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fabd446b-5673-538f-a5f6-92323fd4df50",
-    "notes": [
-        "Recordings of vowels, consonants, diphthongs, sentences"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-190"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Voiced Sounds of Romanian Language"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/facd916f-0e99-5462-ba0d-220003861c2c.json b/oaitestdata/clarin-oai_dc/SET_1/json/facd916f-0e99-5462-ba0d-220003861c2c.json
deleted file mode 100644
index 21e791f0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/facd916f-0e99-5462-ba0d-220003861c2c.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2853",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2853"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2853",
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "https://link.springer.com/chapter/10.1007/978-3-319-13647-9_6"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Kr\u00ed\u017e, Vincent",
-        "Hladk\u00e1, Barbora"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2853;2018-09-03T20:20:38Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Czech Court Decisions Dataset;Kr\u00ed\u017e, Vincent;Hladk\u00e1, Barbora;named entities;annotation;corpus;We present the Czech Court Decisions Dataset (CCDD) -- a dataset of 300 manually annotated court decisions published by The Supreme Court of the Czech Republic and the Constitutional Court of the Czech Republic.;2014;corpus;http://hdl.handle.net/11234/1-2853;ces;https://link.springer.com/chapter/10.1007/978-3-319-13647-9_6;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);http://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);https://ufal.mff.cuni.cz/ccdd",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "facd916f-0e99-5462-ba0d-220003861c2c",
-    "notes": [
-        "We present the Czech Court Decisions Dataset (CCDD) -- a dataset of 300 manually annotated court decisions published by The Supreme Court of the Czech Republic and the Constitutional Court of the Czech Republic."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2853"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "named entities"
-        },
-        {
-            "name": "annotation"
-        },
-        {
-            "name": "corpus"
-        }
-    ],
-    "title": [
-        "Czech Court Decisions Dataset"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fb040622-ba65-59a7-a316-27c2ce1bf7d0.json b/oaitestdata/clarin-oai_dc/SET_1/json/fb040622-ba65-59a7-a316-27c2ce1bf7d0.json
deleted file mode 100644
index a9ae9e60..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fb040622-ba65-59a7-a316-27c2ce1bf7d0.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 19.9 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2112",
-    "MetadataAccess": [
-        "oai:ota:oucs:2112"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Blake, William, 1757-1827"
-    ],
-    "fulltext": "oai:ota:oucs:2112;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/2112.xml;Poems. Selections;Selected poems / by William Blake;Blake, William, 1757-1827;text_and_corpus_linguistics;Poems -- Great Britain;Oxford Text Archive, University of Oxford;text/sgml;(1 file : ca. 19.9 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fb040622-ba65-59a7-a316-27c2ce1bf7d0",
-    "oai_identifier": [
-        "oai:ota:oucs:2112"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poems -- Great Britain"
-        }
-    ],
-    "title": [
-        "Poems. Selections",
-        "Selected poems / by William Blake"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2112.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fb0a026c-a2c5-576a-885a-80d510865d86.json b/oaitestdata/clarin-oai_dc/SET_1/json/fb0a026c-a2c5-576a-885a-80d510865d86.json
deleted file mode 100644
index 941a8b0f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fb0a026c-a2c5-576a-885a-80d510865d86.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/pdf",
-        "downloadable_files_count: 4"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/558",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/558"
-    ],
-    "PID": "http://hdl.handle.net/11321/558",
-    "PublicationTimestamp": "2018-07-26T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Science and Technology"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Za\u015bko-Zieli\u0144ska, Monika"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/558;2018-07-26T08:57:58Z;hdl_11321_3;hdl_11321_4;Guidelines for Emotive Annotation in plWordNet 4.0;Za\u015bko-Zieli\u0144ska, Monika;emotive annotation;sentiment;wordnet;plWordNet;S\u0142owosie\u0107;Guidelines for emotive annotation in plWordNet 4.0. The set consists of four documents dedicated to emotive annotation of four parts of speech - verb, adverb, noun and adjective.;2018-07-26;languageDescription;http://hdl.handle.net/11321/558;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;application/pdf;application/pdf;application/pdf;application/pdf;downloadable_files_count: 4;Wroc\u0142aw University of Science and Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fb0a026c-a2c5-576a-885a-80d510865d86",
-    "notes": [
-        "Guidelines for emotive annotation in plWordNet 4.0. The set consists of four documents dedicated to emotive annotation of four parts of speech - verb, adverb, noun and adjective."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/558"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "emotive annotation"
-        },
-        {
-            "name": "sentiment"
-        },
-        {
-            "name": "wordnet"
-        },
-        {
-            "name": "plWordNet"
-        },
-        {
-            "name": "plWordNet"
-        }
-    ],
-    "title": [
-        "Guidelines for Emotive Annotation in plWordNet 4.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fb0ad2e5-028c-5d99-8fb8-4553ff3a1799.json b/oaitestdata/clarin-oai_dc/SET_1/json/fb0ad2e5-028c-5d99-8fb8-4553ff3a1799.json
deleted file mode 100644
index 08322117..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fb0ad2e5-028c-5d99-8fb8-4553ff3a1799.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Universitas"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "downloadable_files_count: 10",
-        "application/vnd.oasis.opendocument.text",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/413",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/413"
-    ],
-    "PID": "http://hdl.handle.net/11321/413",
-    "PublicationTimestamp": "2017-06-29T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Universitas"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Szabat 2, Marta"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/413;2017-06-29T08:14:25Z;hdl_11321_3;hdl_11321_4;Korpus testowy 2;Szabat 2, Marta;korpus;korpus tekstowy;2017-06-29;corpus;http://hdl.handle.net/11321/413;pol;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;text/plain;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/msword;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.oasis.opendocument.text;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;text/plain;application/vnd.oasis.opendocument.text;downloadable_files_count: 10;Universitas",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fb0ad2e5-028c-5d99-8fb8-4553ff3a1799",
-    "notes": [
-        "korpus tekstowy"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/413"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "korpus"
-        }
-    ],
-    "title": [
-        "Korpus testowy 2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fb1dbc7b-fafa-5f35-bd12-9be74cad8135.json b/oaitestdata/clarin-oai_dc/SET_1/json/fb1dbc7b-fafa-5f35-bd12-9be74cad8135.json
deleted file mode 100644
index 3d5ed6f5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fb1dbc7b-fafa-5f35-bd12-9be74cad8135.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Jan Wieczorek"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/629",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/629"
-    ],
-    "PID": "http://hdl.handle.net/11321/629",
-    "PublicationTimestamp": "2019-02-28T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Jan Wieczorek"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Lewandowski, Robert"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/629;2019-02-28T21:35:10Z;hdl_11321_3;hdl_11321_4;Potchefstroom demo 2.0;Lewandowski, Robert;literature;Potchefstroom (North-West University);2019-02-28;corpus;http://hdl.handle.net/11321/629;eng;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;Jan Wieczorek",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fb1dbc7b-fafa-5f35-bd12-9be74cad8135",
-    "notes": [
-        "Potchefstroom (North-West University)"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/629"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "literature"
-        }
-    ],
-    "title": [
-        "Potchefstroom demo 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fb220dfc-8e8a-5237-a550-c37c25d5001a.json b/oaitestdata/clarin-oai_dc/SET_1/json/fb220dfc-8e8a-5237-a550-c37c25d5001a.json
deleted file mode 100644
index bde14f9b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fb220dfc-8e8a-5237-a550-c37c25d5001a.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1000",
-        "text/plain",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/312",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/312"
-    ],
-    "PID": "http://hdl.handle.net/11321/312",
-    "PublicationTimestamp": "2016-04-25T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Maryl, Maciej",
-        "Borys, Robert",
-        "Rybicki, Jan",
-        "Eder, Maciej",
-        "M\u0142ynarczyk, Ksenia",
-        "Oleksy, Marcin",
-        "Piasecki, Maciej"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/312;2016-07-07T09:43:14Z;hdl_11321_3;hdl_11321_4;1000 Novels Corpus;Eder, Maciej;Rybicki, Jan;M\u0142ynarczyk, Ksenia;Oleksy, Marcin;Borys, Robert;Maryl, Maciej;Piasecki, Maciej;corpus;literature;Corpus of literary texts intended as benchmark collection for text categorization. It contains 1000 novels written in polish or translated to polish by various authors. Each text is stored as separate .txt file.;2016-04-25;corpus;http://hdl.handle.net/11321/312;pol;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;text/plain;application/octet-stream;application/octet-stream;downloadable_files_count: 1000;Wroc\u0142aw University of Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fb220dfc-8e8a-5237-a550-c37c25d5001a",
-    "notes": [
-        "Corpus of literary texts intended as benchmark collection for text categorization. It contains 1000 novels written in polish or translated to polish by various authors. Each text is stored as separate .txt file."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/312"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "literature"
-        }
-    ],
-    "title": [
-        "1000 Novels Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fb2d0f92-292b-50d6-a04c-32652637e3ca.json b/oaitestdata/clarin-oai_dc/SET_1/json/fb2d0f92-292b-50d6-a04c-32652637e3ca.json
deleted file mode 100644
index 8b22f5f6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fb2d0f92-292b-50d6-a04c-32652637e3ca.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Center for Dutch Language and Speech, University of Antwerp"
-    ],
-    "Contributor": [
-        "Daelemans, Walter"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-560",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-560"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-560",
-    "PublicationTimestamp": "2006-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2006"
-    ],
-    "Publisher": [
-        "Center for Dutch Language and Speech, University of Antwerp"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Belgium"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-560;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;English-Luganda Parallel Corpus;Daelemans, Walter;Bible. Word-alligned corpus;2006;corpus;http://hdl.handle.net/11372/LRT-560;eng;downloadable_files_count: 0;Belgium;Center for Dutch Language and Speech, University of Antwerp;http://aflat.org/?q=node/86",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fb2d0f92-292b-50d6-a04c-32652637e3ca",
-    "notes": [
-        "Bible. Word-alligned corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-560"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "English-Luganda Parallel Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fb2e714e-81bf-58bc-bbe6-2873dcd20c45.json b/oaitestdata/clarin-oai_dc/SET_1/json/fb2e714e-81bf-58bc-bbe6-2873dcd20c45.json
deleted file mode 100644
index 88f5bf19..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fb2e714e-81bf-58bc-bbe6-2873dcd20c45.json
+++ /dev/null
@@ -1,49 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4327",
-    "MetadataAccess": [
-        "oai:ota:oucs:4327"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:4327;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4327.xml;A dialogue betwixt Whig and Tory. Wherein the principles and practices of each party are fairly and impartially stated;;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fb2e714e-81bf-58bc-bbe6-2873dcd20c45",
-    "oai_identifier": [
-        "oai:ota:oucs:4327"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A dialogue betwixt Whig and Tory. Wherein the principles and practices of each party are fairly and impartially stated;"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4327.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fb3d08e8-88b0-5c72-b527-29c330b645d9.json b/oaitestdata/clarin-oai_dc/SET_1/json/fb3d08e8-88b0-5c72-b527-29c330b645d9.json
deleted file mode 100644
index b52b1cd3..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fb3d08e8-88b0-5c72-b527-29c330b645d9.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1403",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1403"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1403",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1403;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;freeling_morpho;Freeling-based morphological analyzer.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1403;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fb3d08e8-88b0-5c72-b527-29c330b645d9",
-    "notes": [
-        "Freeling-based morphological analyzer."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1403"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "freeling_morpho"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fb536ce9-888d-524f-8985-b96320c254bf.json b/oaitestdata/clarin-oai_dc/SET_1/json/fb536ce9-888d-524f-8985-b96320c254bf.json
deleted file mode 100644
index 46411656..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fb536ce9-888d-524f-8985-b96320c254bf.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Societatis Jesu"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish",
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-29538",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-29538"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8D17-9",
-    "PublicationTimestamp": "1770-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1770"
-    ],
-    "Publisher": [
-        "Societatis Jesu"
-    ],
-    "RelatedIdentifier": [
-        "http://dlibra.bibliotekaelblaska.pl/Content/29538",
-        "oai:dlibra.bibliotekaelblaska.pl:publication:30889"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-29538;2019-03-01T13:35:06Z;Kazania niedzielne X. Wawrzy\u0144ca Rydzewskiego. Edycya druga. T. 2.;modlitewnik;kazania ko\u015bcielne - 18 w.;Starodruk w j\u0119zyku polskim, zawieraj\u0105cy kazania na r\u00f3\u017cne okazje (pogrzeby, niedziele i \u015bwi\u0119ta) wybitnego jezuity na Litwie ksi\u0119dza Wawrzy\u0144ca Rydzewskiego. Na stronie tytu\u0142owej modlitewnika odr\u0119czne zapiski po \u0142acinie.;Societatis Jesu;1770;starodruk;application/xml;clarind-uds:poldilemma-29538;hdl:11858/00-246C-0000-0023-8D17-9;L-64801;pol;lat;http://dlibra.bibliotekaelblaska.pl/Content/29538;oai:dlibra.bibliotekaelblaska.pl:publication:30889;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fb536ce9-888d-524f-8985-b96320c254bf",
-    "notes": [
-        "Starodruk w j\u0119zyku polskim, zawieraj\u0105cy kazania na r\u00f3\u017cne okazje (pogrzeby, niedziele i \u015bwi\u0119ta) wybitnego jezuity na Litwie ksi\u0119dza Wawrzy\u0144ca Rydzewskiego. Na stronie tytu\u0142owej modlitewnika odr\u0119czne zapiski po \u0142acinie."
-    ],
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-29538"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "modlitewnik"
-        },
-        {
-            "name": "modlitewnik"
-        }
-    ],
-    "title": [
-        "Kazania niedzielne X. Wawrzy\u0144ca Rydzewskiego. Edycya druga. T. 2."
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fb5ef240-67a9-5909-bd8e-5378f79ed714.json b/oaitestdata/clarin-oai_dc/SET_1/json/fb5ef240-67a9-5909-bd8e-5378f79ed714.json
deleted file mode 100644
index cdd7aaad..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fb5ef240-67a9-5909-bd8e-5378f79ed714.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Przemys\u0142aw \u017bukiewicz",
-        "Rafa\u0142 Zimny",
-        "Jan Wieczorek"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 44",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/603",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/603"
-    ],
-    "PID": "http://hdl.handle.net/11321/603",
-    "PublicationTimestamp": "2018-09-11T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Przemys\u0142aw \u017bukiewicz",
-        "Rafa\u0142 Zimny",
-        "Jan Wieczorek"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11321/599",
-        "http://hdl.handle.net/11321/605"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "CLARIN-EULA-ACA-v1.0",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca",
-        "ACA"
-    ],
-    "author": [
-        "Wieczorek, Jan",
-        "Zimny, Rafa\u0142",
-        "\u017bukiewicz, Przemys\u0142aw"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/603;2018-09-24T12:11:13Z;hdl_11321_3;hdl_11321_478;Korpus przem\u00f3wie\u0144 noworocznych (2018-09-18) 2.0;Zimny, Rafa\u0142;\u017bukiewicz, Przemys\u0142aw;Wieczorek, Jan;przem\u00f3wienia;polityka;Fragment korpusu polskich przem\u00f3wie\u0144 politycznych;2018-09-11;corpus;http://hdl.handle.net/11321/603;pol;http://hdl.handle.net/11321/599;http://hdl.handle.net/11321/605;CLARIN-EULA-ACA-v1.0;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEULA#aca;ACA;text/plain; charset=utf-8;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;application/vnd.openxmlformats-officedocument.wordprocessingml.document;downloadable_files_count: 44;Jan Wieczorek;Rafa\u0142 Zimny;Przemys\u0142aw \u017bukiewicz",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fb5ef240-67a9-5909-bd8e-5378f79ed714",
-    "notes": [
-        "Fragment korpusu polskich przem\u00f3wie\u0144 politycznych"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/603"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_478"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "polityka"
-        }
-    ],
-    "title": [
-        "Korpus przem\u00f3wie\u0144 noworocznych (2018-09-18) 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fb8d2063-2862-5d1c-97c0-8e363c2061a0.json b/oaitestdata/clarin-oai_dc/SET_1/json/fb8d2063-2862-5d1c-97c0-8e363c2061a0.json
deleted file mode 100644
index 1233c8d0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fb8d2063-2862-5d1c-97c0-8e363c2061a0.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "University of Luxembourg"
-    ],
-    "Contributor": [
-        "Gilles, Peter"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Luxembourgish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1125",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1125"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1125",
-    "PublicationTimestamp": "2010-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "University of Luxembourg"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "SpatialCoverage": [
-        "Luxembourg"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1125;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Luxogramm - Grammatisches Informationssystem zum Luxemburgischen;Gilles, Peter;Luxogramm provides grammatical information (paradigms, rules, categories) for all Luxembourgish verbs;2010;languageDescription;http://hdl.handle.net/11372/LRT-1125;ltz;application/octet-stream;downloadable_files_count: 0;Luxembourg;University of Luxembourg;http://luxogramm.uni.lu",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fb8d2063-2862-5d1c-97c0-8e363c2061a0",
-    "notes": [
-        "Luxogramm provides grammatical information (paradigms, rules, categories) for all Luxembourgish verbs"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1125"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Luxogramm - Grammatisches Informationssystem zum Luxemburgischen"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fb8e8530-1163-52f8-a271-ae75c20ecc1f.json b/oaitestdata/clarin-oai_dc/SET_1/json/fb8e8530-1163-52f8-a271-ae75c20ecc1f.json
deleted file mode 100644
index 7802310e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fb8e8530-1163-52f8-a271-ae75c20ecc1f.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3733",
-    "MetadataAccess": [
-        "oai:ota:oucs:3733"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Kenrick, W. (William), 1725?-1779."
-    ],
-    "fulltext": "oai:ota:oucs:3733;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3733.xml;Introduction to the school of Shakespeare; held, on Wednesday evenings, in the Apollo, at the Devil Tavern, Temple Bar. To which is added a retort courteous on the criticks, as delivered at the second and third lectures;Kenrick, W. (William), 1725?-1779.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fb8e8530-1163-52f8-a271-ae75c20ecc1f",
-    "oai_identifier": [
-        "oai:ota:oucs:3733"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Introduction to the school of Shakespeare; held, on Wednesday evenings, in the Apollo, at the Devil Tavern, Temple Bar. To which is added a retort courteous on the criticks, as delivered at the second and third lectures"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3733.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fb98165a-4800-5efc-9780-8d10d124101a.json b/oaitestdata/clarin-oai_dc/SET_1/json/fb98165a-4800-5efc-9780-8d10d124101a.json
deleted file mode 100644
index 8aff14fc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fb98165a-4800-5efc-9780-8d10d124101a.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Tilde"
-    ],
-    "Contributor": [
-        "Skadins, Raivis"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Latvian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-548",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-548"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-548",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Tilde"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Latvia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-548;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Latvian language morphological analysis/generation reference system;Skadins, Raivis;Web service;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-548;lav;downloadable_files_count: 0;Latvia;Tilde;http://www.letonika.lv/groups/default.aspx?g=5&q=",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fb98165a-4800-5efc-9780-8d10d124101a",
-    "notes": [
-        "Web service"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-548"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Latvian language morphological analysis/generation reference system"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fbaf2c3b-e802-5760-bd8f-90124f5d4005.json b/oaitestdata/clarin-oai_dc/SET_1/json/fbaf2c3b-e802-5760-bd8f-90124f5d4005.json
deleted file mode 100644
index 70b879c6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fbaf2c3b-e802-5760-bd8f-90124f5d4005.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contributor": [
-        "Tropf, Herbert"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Czech",
-        "Danish",
-        "Dutch",
-        "English",
-        "Finnish",
-        "French",
-        "German",
-        "Hungarian",
-        "Italian",
-        "Polish",
-        "Portuguese",
-        "Russian",
-        "Spanish",
-        "Swedish",
-        "Turkish",
-        "Chinese",
-        "Hebrew",
-        "Japanese",
-        "Korean",
-        "Thai"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-600",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-600"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-600",
-    "PublicationTimestamp": "2002-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2002"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-600;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Speecon databases;Tropf, Herbert;28 speech databases containing broadband recordings from 550 adults and 50 children per language. Contains interesting phonetically rich material. All orthographically transcribed. Speaker information included for gender, age, accent. Including pronunciation lexicon.;2002;corpus;http://hdl.handle.net/11372/LRT-600;ces;dan;nld;eng;fin;fra;deu;hun;ita;pol;por;rus;spa;swe;tur;zho;heb;jpn;kor;tha;downloadable_files_count: 0;http://www.speechdat.org/speecon/index.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fbaf2c3b-e802-5760-bd8f-90124f5d4005",
-    "notes": [
-        "28 speech databases containing broadband recordings from 550 adults and 50 children per language. Contains interesting phonetically rich material. All orthographically transcribed. Speaker information included for gender, age, accent. Including pronunciation lexicon."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-600"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Speecon databases"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fbb4a813-c72b-5b0a-bd16-262b22f8e3e8.json b/oaitestdata/clarin-oai_dc/SET_1/json/fbb4a813-c72b-5b0a-bd16-262b22f8e3e8.json
deleted file mode 100644
index 02dfc099..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fbb4a813-c72b-5b0a-bd16-262b22f8e3e8.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=1eb37910a35a11e1a404080027e73ea2dbdb15cf3d18412b943f9db788f20d5c",
-    "MetadataAccess": [
-        "1eb37910a35a11e1a404080027e73ea2dbdb15cf3d18412b943f9db788f20d5c"
-    ],
-    "PublicationTimestamp": "2015-12-14T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "fulltext": "1eb37910a35a11e1a404080027e73ea2dbdb15cf3d18412b943f9db788f20d5c;2019-02-27T12:08:53Z;lexicalConceptualResource;lexicalConceptualResource:wordList;Maltese Wordlist;Wordlist for spell-checking;2015-12-14",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fbb4a813-c72b-5b0a-bd16-262b22f8e3e8",
-    "notes": [
-        "Wordlist for spell-checking"
-    ],
-    "oai_identifier": [
-        "1eb37910a35a11e1a404080027e73ea2dbdb15cf3d18412b943f9db788f20d5c"
-    ],
-    "oai_set": [
-        "lexicalConceptualResource",
-        "lexicalConceptualResource:wordList"
-    ],
-    "state": "active",
-    "title": [
-        "Maltese Wordlist"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fbde655c-7ec5-50b8-824a-eb84b2e8b10a.json b/oaitestdata/clarin-oai_dc/SET_1/json/fbde655c-7ec5-50b8-824a-eb84b2e8b10a.json
deleted file mode 100644
index 0caddc7f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fbde655c-7ec5-50b8-824a-eb84b2e8b10a.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Burnard, Lou",
-        "Corns, Thomas N."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 582 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2225",
-    "MetadataAccess": [
-        "oai:ota:oucs:2225"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Milton, John, 1608-1674"
-    ],
-    "fulltext": "oai:ota:oucs:2225;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/2225.xml;Paradise lost : a poem in twelve books [1674] / John Milton;Milton, John, 1608-1674;text_and_corpus_linguistics;Epic poetry, English -- 17th century;eng;Oxford Text Archive, University of Oxford;Corns, Thomas N.;Burnard, Lou;Burnard, Lou;text/sgml;(1 file : ca. 582 KB);Text;Poems;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fbde655c-7ec5-50b8-824a-eb84b2e8b10a",
-    "oai_identifier": [
-        "oai:ota:oucs:2225"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Epic poetry"
-        },
-        {
-            "name": "English -- th century"
-        }
-    ],
-    "title": [
-        "Paradise lost : a poem in twelve books [1674] / John Milton"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2225.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fbe20fb7-ab26-5b59-8521-3b5f3ae488fd.json b/oaitestdata/clarin-oai_dc/SET_1/json/fbe20fb7-ab26-5b59-8521-3b5f3ae488fd.json
deleted file mode 100644
index a2d975f6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fbe20fb7-ab26-5b59-8521-3b5f3ae488fd.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/105",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/105"
-    ],
-    "PID": "http://hdl.handle.net/10794/105",
-    "PublicationTimestamp": "2013-03-06T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/105;2017-10-25T06:38:23Z;hdl_10794_1;hdl_10794_2;Blog mix 2011 (2017-02-24);Bloggmix 2011 (2017-02-24);n/a, n/a;Swedish;Blog;The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.;Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat.;2013-03-06;corpus;http://hdl.handle.net/10794/105;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/bloggmix2011",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fbe20fb7-ab26-5b59-8521-3b5f3ae488fd",
-    "notes": [
-        "The blogs in the blogmix are selected through the lists Most visited private blogs, Most visited professional blogs, and the local lists for different regions, at bloggportalen.se.\r\n\r\nMore information, such as the location and age of the blogger is also retrieved from Bloggportalen. The material has not been manually checked, which means that spam may occur. Some English blogs have been removed when discovered, and some blogs have not been added for technical reasons.\r\n\r\nThe time of the blogs ranges from the first to the latest entries of the selected blogs, and the corpus is continually updated.\r\n\r\nThe material is sentence scrambled.",
-        "Urvalet av bloggar f\u00f6r bloggmixen g\u00f6rs med hj\u00e4lp av topplistorna p\u00e5 bloggportalen.se, b\u00e5de Mest bes\u00f6kta privata bloggar, Mest bes\u00f6kta proffsbloggar och de lokala topplistorna f\u00f6r olika regioner.\r\n\r\nN\u00e4rmare information, som bloggarens ort och \u00e5lder, h\u00e4mtas ocks\u00e5 fr\u00e5n Bloggportalen. Materialet har inte kontrollerats manuellt, vilket betyder att det kan f\u00f6rekomma spam. N\u00e5gra engelskspr\u00e5kiga bloggar har plockats bort d\u00e5 de uppt\u00e4ckts, och vissa bloggar har inte kunnat l\u00e4sas in av tekniska sk\u00e4l.\r\n\r\nTidsperioden str\u00e4cker sig fr\u00e5n de f\u00f6rsta inl\u00e4ggen i de utvalda bloggarna till de senaste inl\u00e4ggen. Korpusen uppdateras regelbundet.\r\n\r\nMaterialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/105"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Blog"
-        }
-    ],
-    "title": [
-        "Blog mix 2011 (2017-02-24)",
-        "Bloggmix 2011 (2017-02-24)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fc107609-1d9e-54be-bbab-c6a10afb67dc.json b/oaitestdata/clarin-oai_dc/SET_1/json/fc107609-1d9e-54be-bbab-c6a10afb67dc.json
deleted file mode 100644
index 4ec67bfc..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fc107609-1d9e-54be-bbab-c6a10afb67dc.json
+++ /dev/null
@@ -1,89 +0,0 @@
-{
-    "Contact": [
-        "ENS de Lyon - CNRS, ICAR Laboratory",
-        "Universit\u00e9 de Franche-Compt\u00e9, laboratoire ELLIADD (Edition, Litt\u00e9ratures, Langages, Informatique, Arts, Didactique, Discours)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-2382",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2382"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-2382",
-    "PublicationTimestamp": "2016-06-21T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "ENS de Lyon - CNRS, ICAR Laboratory",
-        "Universit\u00e9 de Franche-Compt\u00e9, laboratoire ELLIADD (Edition, Litt\u00e9ratures, Langages, Informatique, Arts, Didactique, Discours)"
-    ],
-    "RelatedIdentifier": [
-        "https://halshs.archives-ouvertes.fr/halshs-00549764/en"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Heiden, Serge"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-2382;2017-09-11T13:58:37Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TXM;Heiden, Serge;textometry;xml;tei;nlp;cqp;r;textual data analysis;statistical text analysis;text mining;concordance;TXM is a free and open-source cross-platform Unicode & XML based text/corpus analysis environment and graphical client, supporting Windows, Linux and Mac OS X. It can also be used online as a J2EE standard compliant web portal (GWT based) with access control built in.;2016-06-21;toolService;http://hdl.handle.net/11372/LRT-2382;https://halshs.archives-ouvertes.fr/halshs-00549764/en;downloadable_files_count: 0;ENS de Lyon - CNRS, ICAR Laboratory;Universit\u00e9 de Franche-Compt\u00e9, laboratoire ELLIADD (Edition, Litt\u00e9ratures, Langages, Informatique, Arts, Didactique, Discours);http://textometrie.ens-lyon.fr/?lang=en",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fc107609-1d9e-54be-bbab-c6a10afb67dc",
-    "notes": [
-        "TXM is a free and open-source cross-platform Unicode & XML based text/corpus analysis environment and graphical client, supporting Windows, Linux and Mac OS X. It can also be used online as a J2EE standard compliant web portal (GWT based) with access control built in."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-2382"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "textometry"
-        },
-        {
-            "name": "xml"
-        },
-        {
-            "name": "tei"
-        },
-        {
-            "name": "nlp"
-        },
-        {
-            "name": "cqp"
-        },
-        {
-            "name": "textual data analysis"
-        },
-        {
-            "name": "statistical text analysis"
-        },
-        {
-            "name": "text mining"
-        },
-        {
-            "name": "concordance"
-        }
-    ],
-    "title": [
-        "TXM"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fc2ede37-0197-5d0a-b8b3-446ecd2cd980.json b/oaitestdata/clarin-oai_dc/SET_1/json/fc2ede37-0197-5d0a-b8b3-446ecd2cd980.json
deleted file mode 100644
index bb1a9057..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fc2ede37-0197-5d0a-b8b3-446ecd2cd980.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "The Research Institute for the Languages of Finland"
-    ],
-    "Contributor": [
-        "Ruppel, Klaas"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Northern Sami"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-828",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-828"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-828",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "The Research Institute for the Languages of Finland"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "SpatialCoverage": [
-        "Finland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-828;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;\u00c1lgu \u2013 Origins of Saami Words;Ruppel, Klaas;The database will contain an etymological lexicon of Saami languages complete with detailed source citations. The database will be open to the public in November 2006 and will be updated regularly.;2014-07-30;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-828;sme;downloadable_files_count: 0;Finland;The Research Institute for the Languages of Finland;http://kaino.kotus.fi/algu/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fc2ede37-0197-5d0a-b8b3-446ecd2cd980",
-    "notes": [
-        "The database will contain an etymological lexicon of Saami languages complete with detailed source citations. The database will be open to the public in November 2006 and will be updated regularly."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-828"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "\u00c1lgu \u2013 Origins of Saami Words"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fc300b75-0c9d-56fb-9e2c-ff4d3399c0b2.json b/oaitestdata/clarin-oai_dc/SET_1/json/fc300b75-0c9d-56fb-9e2c-ff4d3399c0b2.json
deleted file mode 100644
index 586325f6..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fc300b75-0c9d-56fb-9e2c-ff4d3399c0b2.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Computer and Information Science, University of Ljubljana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1182",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1182"
-    ],
-    "PID": "http://hdl.handle.net/11356/1182",
-    "PublicationTimestamp": "2018-03-19T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Faculty of Computer and Information Science, University of Ljubljana"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)",
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "\u017ditnik, Slavko"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1182;2018-04-15T17:56:57Z;hdl_11356_1023;hdl_11356_1024;Slovene coreference resolution corpus coref149;\u017ditnik, Slavko;coreference resolution;This corpus contains a subset of the ssj500k v1.4 corpus, http://hdl.handle.net/11356/1052. Each of 149 documents contains a paragraph from ssj500k that contains at least 100 words and at least 6 named entities. The data is in TCF format, exported from the WebAnno tool, https://webanno.github.io/webanno/.\r\n\r\nThe annotated entities are of type person, organization or location. Mentions are annotated as coreference chains without additional classifications of different coreference types. Annotations also include implicit mentions that are specific for the Slovene language - in this case, a verb is tagged. The corpus consists of 1277 entities, 2329 mentions, 831 singleton entities, 40 appositions and 215 overlapping mentions. We also annotated overlapping mentions of the same entity - for example in text [strokovnega direktorja KC [Zorana Arne\u017ea]] we annotate two overlapping mentions that refer to the same entity. There are 97 such mentions in the corpus.\r\n\r\nIn the public source code repository https://bitbucket.org/szitnik/nutie-core class TEIP5Importer contains an additional function to read the dataset and merge it together with the ssj500k dataset.;2018-03-19;corpus;http://hdl.handle.net/11356/1182;slv;Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0);https://creativecommons.org/licenses/by-nc-sa/4.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Faculty of Computer and Information Science, University of Ljubljana",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fc300b75-0c9d-56fb-9e2c-ff4d3399c0b2",
-    "notes": [
-        "This corpus contains a subset of the ssj500k v1.4 corpus, http://hdl.handle.net/11356/1052. Each of 149 documents contains a paragraph from ssj500k that contains at least 100 words and at least 6 named entities. The data is in TCF format, exported from the WebAnno tool, https://webanno.github.io/webanno/.\r\n\r\nThe annotated entities are of type person, organization or location. Mentions are annotated as coreference chains without additional classifications of different coreference types. Annotations also include implicit mentions that are specific for the Slovene language - in this case, a verb is tagged. The corpus consists of 1277 entities, 2329 mentions, 831 singleton entities, 40 appositions and 215 overlapping mentions. We also annotated overlapping mentions of the same entity - for example in text [strokovnega direktorja KC [Zorana Arne\u017ea]] we annotate two overlapping mentions that refer to the same entity. There are 97 such mentions in the corpus.\r\n\r\nIn the public source code repository https://bitbucket.org/szitnik/nutie-core class TEIP5Importer contains an additional function to read the dataset and merge it together with the ssj500k dataset."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1182"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "coreference resolution"
-        }
-    ],
-    "title": [
-        "Slovene coreference resolution corpus coref149"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fc509de5-d10d-5de4-af33-d92fd008edda.json b/oaitestdata/clarin-oai_dc/SET_1/json/fc509de5-d10d-5de4-af33-d92fd008edda.json
deleted file mode 100644
index 27191cec..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fc509de5-d10d-5de4-af33-d92fd008edda.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "Contributor": [
-        "M\u0142odzki, Rafa\u0142"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1384",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1384"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1384",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Poland"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Przepi\u00f3rkowski, Adam",
-        "M\u0142odzki, Rafa\u0142"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1384;2016-04-06T16:39:50Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;WSD Development Environment;M\u0142odzki, Rafa\u0142;Przepi\u00f3rkowski, Adam;M\u0142odzki, Rafa\u0142;Tool for designing and performing Word Sense Disambiguation (WSD) experiments. Current version (prototype) facilitates the construction and evaluation of WSD methods in the supervised Machine Learning paradigm.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1384;downloadable_files_count: 0;Poland;Institute of Computer Science, Polish Academy of Sciences",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fc509de5-d10d-5de4-af33-d92fd008edda",
-    "notes": [
-        "Tool for designing and performing Word Sense Disambiguation (WSD) experiments. Current version (prototype) facilitates the construction and evaluation of WSD methods in the supervised Machine Learning paradigm."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1384"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "WSD Development Environment"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fc59b368-6477-5d23-80a0-e3839b8846ed.json b/oaitestdata/clarin-oai_dc/SET_1/json/fc59b368-6477-5d23-80a0-e3839b8846ed.json
deleted file mode 100644
index 85747048..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fc59b368-6477-5d23-80a0-e3839b8846ed.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3893",
-    "MetadataAccess": [
-        "oai:ota:oucs:3893"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Dennis, John, 1657-1734."
-    ],
-    "fulltext": "oai:ota:oucs:3893;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3893.xml;Britannia triumphans: or the Empire sav'd: and Europe deliver'd. By the success of her Majesty's forces under the wise and heroick conduct of his Grace the Duke of Marlborough. A poem, by Mr. Dennis.;Dennis, John, 1657-1734.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fc59b368-6477-5d23-80a0-e3839b8846ed",
-    "oai_identifier": [
-        "oai:ota:oucs:3893"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Britannia triumphans: or the Empire sav'd: and Europe deliver'd. By the success of her Majesty's forces under the wise and heroick conduct of his Grace the Duke of Marlborough. A poem, by Mr. Dennis."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3893.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fc5b44a7-1190-5ddb-a1b2-615fce0d346c.json b/oaitestdata/clarin-oai_dc/SET_1/json/fc5b44a7-1190-5ddb-a1b2-615fce0d346c.json
deleted file mode 100644
index 3c12c4f7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fc5b44a7-1190-5ddb-a1b2-615fce0d346c.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5160",
-    "MetadataAccess": [
-        "oai:ota:oucs:5160"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Culley, George, 1735-1813."
-    ],
-    "fulltext": "oai:ota:oucs:5160;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5160.xml;Observations on live stock: containing hints for choosing and improving the best breeds of the most useful kinds of domestic animals, by George Culley, ...;Culley, George, 1735-1813.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fc5b44a7-1190-5ddb-a1b2-615fce0d346c",
-    "oai_identifier": [
-        "oai:ota:oucs:5160"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Observations on live stock: containing hints for choosing and improving the best breeds of the most useful kinds of domestic animals, by George Culley, ..."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5160.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fca138c5-0638-57f2-b0aa-fe59b3cb46a1.json b/oaitestdata/clarin-oai_dc/SET_1/json/fca138c5-0638-57f2-b0aa-fe59b3cb46a1.json
deleted file mode 100644
index 43157200..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fca138c5-0638-57f2-b0aa-fe59b3cb46a1.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 6.48 KB)"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0116",
-    "MetadataAccess": [
-        "oai:ota:oucs:0116"
-    ],
-    "PublicationTimestamp": "1630-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1630"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Randolph, Thomas, 1605-1635"
-    ],
-    "fulltext": "oai:ota:oucs:0116;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0116.xml;Praeludium;Randolph, Thomas, 1605-1635;1630;text_and_corpus_linguistics;Plays -- England -- 17th century;eng;Oxford Text Archive, University of Oxford;(1 file : ca. 6.48 KB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fca138c5-0638-57f2-b0aa-fe59b3cb46a1",
-    "oai_identifier": [
-        "oai:ota:oucs:0116"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Plays -- England -- th century"
-        }
-    ],
-    "title": [
-        "Praeludium"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0116.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fcacc3af-ec31-570f-8f40-1463af7620a1.json b/oaitestdata/clarin-oai_dc/SET_1/json/fcacc3af-ec31-570f-8f40-1463af7620a1.json
deleted file mode 100644
index 6bf7cf80..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fcacc3af-ec31-570f-8f40-1463af7620a1.json
+++ /dev/null
@@ -1,89 +0,0 @@
-{
-    "Contact": [
-        "Faculty of Social Sciences,  University of Ljubljana"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Slovenian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1196",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1196"
-    ],
-    "PID": "http://hdl.handle.net/11356/1196",
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Faculty of Social Sciences,  University of Ljubljana"
-    ],
-    "RelatedIdentifier": [
-        "https://doi.org/10.1016/j.pubrev.2013.07.022",
-        "http://eki.ee/elex2013/proceedings/eLex2013_12_Logar+Kosem.pdf",
-        "http://slovenscina2.0.trojina.si/arhiv/2014/1/Slo2.0_2014_1_03.pdf",
-        "http://dk.fdv.uni-lj.si/db/pdfs/tip20086_Golob_Logar.pdf"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "PUB",
-        "https://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "Ver\u010di\u010d, Dejan",
-        "Logar, Nata\u0161a"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1196;2018-10-17T08:41:28Z;hdl_11356_1023;hdl_11356_1024;Lexical database of Slovene PR terminology TERMIS;Logar, Nata\u0161a;Ver\u010di\u010d, Dejan;terminology;collocations;examples of use;public relations;explanations;TERMIS is a terminology database with 2,000 entries from the field of public relations. The terms in Slovene are explained and translated into English, with typical context examples (collocations and examples of use) taken from the KoRP corpus, a corpus of Slovene PR texts (a morphosyntactically tagged synchronous and monolingual corpus, containing 1.8 million words).;2017;lexicalConceptualResource;http://hdl.handle.net/11356/1196;slv;https://doi.org/10.1016/j.pubrev.2013.07.022;http://eki.ee/elex2013/proceedings/eLex2013_12_Logar+Kosem.pdf;http://slovenscina2.0.trojina.si/arhiv/2014/1/Slo2.0_2014_1_03.pdf;http://dk.fdv.uni-lj.si/db/pdfs/tip20086_Golob_Logar.pdf;Creative Commons - Attribution 4.0 International (CC BY 4.0);PUB;https://creativecommons.org/licenses/by/4.0/;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Faculty of Social Sciences,  University of Ljubljana;http://www.termis.fdv.uni-lj.si/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fcacc3af-ec31-570f-8f40-1463af7620a1",
-    "notes": [
-        "TERMIS is a terminology database with 2,000 entries from the field of public relations. The terms in Slovene are explained and translated into English, with typical context examples (collocations and examples of use) taken from the KoRP corpus, a corpus of Slovene PR texts (a morphosyntactically tagged synchronous and monolingual corpus, containing 1.8 million words)."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1196"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "terminology"
-        },
-        {
-            "name": "collocations"
-        },
-        {
-            "name": "examples use"
-        },
-        {
-            "name": "public relations"
-        },
-        {
-            "name": "explanations"
-        }
-    ],
-    "title": [
-        "Lexical database of Slovene PR terminology TERMIS"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fcbb3003-fc62-5fbb-9db9-c3291b5cddaf.json b/oaitestdata/clarin-oai_dc/SET_1/json/fcbb3003-fc62-5fbb-9db9-c3291b5cddaf.json
deleted file mode 100644
index 174b7be4..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fcbb3003-fc62-5fbb-9db9-c3291b5cddaf.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "University of Navarra, Spain"
-    ],
-    "Contributor": [
-        "Alarc\u00f3n, Enrique"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-871",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-871"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-871",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Navarra, Spain"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-871;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Corpus Thomisticum;Alarc\u00f3n, Enrique;\"A scholarly edition of Aquinas's Opera omnia, with a lexical database, a dictionary, two collection of historical sources, and an extensive bibliography.\";2014-07-30;corpus;http://hdl.handle.net/11372/LRT-871;lat;downloadable_files_count: 0;Spain;University of Navarra, Spain;http://www.corpusthomisticum.org/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fcbb3003-fc62-5fbb-9db9-c3291b5cddaf",
-    "notes": [
-        "\"A scholarly edition of Aquinas's Opera omnia, with a lexical database, a dictionary, two collection of historical sources, and an extensive bibliography.\""
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-871"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus Thomisticum"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fcbd713a-26c0-5ef5-af2e-94e3d58fe67a.json b/oaitestdata/clarin-oai_dc/SET_1/json/fcbd713a-26c0-5ef5-af2e-94e3d58fe67a.json
deleted file mode 100644
index 9ae80c0c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fcbd713a-26c0-5ef5-af2e-94e3d58fe67a.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Wojciech Jastrz\u0119bski"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 4",
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/485",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/485"
-    ],
-    "PID": "http://hdl.handle.net/11321/485",
-    "PublicationTimestamp": "2016-02-16T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wojciech Jastrz\u0119bski"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)",
-        "http://creativecommons.org/licenses/by-nc-nd/3.0/",
-        "CC"
-    ],
-    "author": [
-        "Jastrz\u0119bski, Wojciech"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/485;2018-06-19T11:18:09Z;hdl_11321_3;hdl_11321_4;Cz\u0119\u015b\u0107 komentarzy internetowych d\u0142u\u017cszych ni\u017c 500 znak\u00f3w do filmu YT: Mazurek Kapeli - Polacy witaj\u0105 uchod\u017ac\u00f3w;Jastrz\u0119bski, Wojciech;komentarze internetowe;Testowy, pr\u00f3bny korpus komentarzy internetowych opublikowanych do filmu \"Mazurek Kapeli - Polacy witaj\u0105 uchod\u017ac\u00f3w! - YouTube\"\r\nhttps://www.youtube.com/watch?v=dAX4vJiO9Aw\r\n\r\nkomentarze d\u0142u\u017csze ni\u017c 500 znak\u00f3w;2016-02-16;corpus;http://hdl.handle.net/11321/485;pol;Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0);http://creativecommons.org/licenses/by-nc-nd/3.0/;CC;text/plain; charset=utf-8;application/msword;text/plain;application/vnd.openxmlformats-officedocument.wordprocessingml.document;text/plain;downloadable_files_count: 4;Wojciech Jastrz\u0119bski",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fcbd713a-26c0-5ef5-af2e-94e3d58fe67a",
-    "notes": [
-        "Testowy, pr\u00f3bny korpus komentarzy internetowych opublikowanych do filmu \"Mazurek Kapeli - Polacy witaj\u0105 uchod\u017ac\u00f3w! - YouTube\"\r\nhttps://www.youtube.com/watch?v=dAX4vJiO9Aw\r\n\r\nkomentarze d\u0142u\u017csze ni\u017c 500 znak\u00f3w"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/485"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "komentarze internetowe"
-        }
-    ],
-    "title": [
-        "Cz\u0119\u015b\u0107 komentarzy internetowych d\u0142u\u017cszych ni\u017c 500 znak\u00f3w do filmu YT: Mazurek Kapeli - Polacy witaj\u0105 uchod\u017ac\u00f3w"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fcf6789e-d150-5360-b372-e0e9cbefe189.json b/oaitestdata/clarin-oai_dc/SET_1/json/fcf6789e-d150-5360-b372-e0e9cbefe189.json
deleted file mode 100644
index 7475faae..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fcf6789e-d150-5360-b372-e0e9cbefe189.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3835",
-    "MetadataAccess": [
-        "oai:ota:oucs:3835"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Burke, Edmund, 1729-1797."
-    ],
-    "fulltext": "oai:ota:oucs:3835;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3835.xml;The beauties of the late Right Hon. Edmund Burke, selected from the writings, &c. of that extraordinary man, ... To which is prefixed, a sketch of the life, with some original anecdotes of Mr. Burke. In two volumes.: [pt.1];Burke, Edmund, 1729-1797.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fcf6789e-d150-5360-b372-e0e9cbefe189",
-    "oai_identifier": [
-        "oai:ota:oucs:3835"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The beauties of the late Right Hon. Edmund Burke, selected from the writings, &c. of that extraordinary man, ... To which is prefixed, a sketch of the life, with some original anecdotes of Mr. Burke. In two volumes.: [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3835.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fcfa17e8-5e15-55a9-8a4b-4bdbc6f10a97.json b/oaitestdata/clarin-oai_dc/SET_1/json/fcfa17e8-5e15-55a9-8a4b-4bdbc6f10a97.json
deleted file mode 100644
index 3c84d6a0..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fcfa17e8-5e15-55a9-8a4b-4bdbc6f10a97.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2861",
-    "MetadataAccess": [
-        "oai:ota:oucs:2861"
-    ],
-    "PublicationTimestamp": "1746-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1746"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2861;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2861.xml;Advice to the free-men of the city of Dublin, in the choice of a member to represent them in Parliament;Swift, Jonathan, 1667-1745;1746;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fcfa17e8-5e15-55a9-8a4b-4bdbc6f10a97",
-    "oai_identifier": [
-        "oai:ota:oucs:2861"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Advice to the free-men of the city of Dublin, in the choice of a member to represent them in Parliament"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2861.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fd003325-ee61-5c47-b265-6824c5881732.json b/oaitestdata/clarin-oai_dc/SET_1/json/fd003325-ee61-5c47-b265-6824c5881732.json
deleted file mode 100644
index 86c82769..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fd003325-ee61-5c47-b265-6824c5881732.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "University of Lodz"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/pdf"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/548",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/548"
-    ],
-    "PID": "http://hdl.handle.net/11321/548",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "University of Lodz"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "CC"
-    ],
-    "author": [
-        "P\u0119zik, Piotr"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/548;2018-07-23T11:54:38Z;hdl_11321_3;hdl_11321_4;Mowa Wroc\u0142awia lat 80-tych - corpus;P\u0119zik, Piotr;spoken data;1980s;Wroc\u0142aw;The corpus comprises spoken data collected in the 1980s in Wroc\u0142aw. The data were retrieved from tapes and digitalised.;2018;corpus;http://hdl.handle.net/11321/548;Polish;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;CC;text/plain; charset=utf-8;application/pdf;downloadable_files_count: 1;University of Lodz;http://spokes.clarin-pl.eu/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fd003325-ee61-5c47-b265-6824c5881732",
-    "notes": [
-        "The corpus comprises spoken data collected in the 1980s in Wroc\u0142aw. The data were retrieved from tapes and digitalised."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/548"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "spoken data"
-        }
-    ],
-    "title": [
-        "Mowa Wroc\u0142awia lat 80-tych - corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fd0b23ca-e1d8-5461-a0da-72a9ae088f87.json b/oaitestdata/clarin-oai_dc/SET_1/json/fd0b23ca-e1d8-5461-a0da-72a9ae088f87.json
deleted file mode 100644
index 6bf3394b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fd0b23ca-e1d8-5461-a0da-72a9ae088f87.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4754",
-    "MetadataAccess": [
-        "oai:ota:oucs:4754"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gerard, Alexander, 1728-1795."
-    ],
-    "fulltext": "oai:ota:oucs:4754;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4754.xml;Sermons, by Alexander Gerard, D.D.: [pt.1];Gerard, Alexander, 1728-1795.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fd0b23ca-e1d8-5461-a0da-72a9ae088f87",
-    "oai_identifier": [
-        "oai:ota:oucs:4754"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Sermons, by Alexander Gerard, D.D.: [pt.1]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4754.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fd12b75d-a6ec-5ef1-9aa1-9373105cf3f6.json b/oaitestdata/clarin-oai_dc/SET_1/json/fd12b75d-a6ec-5ef1-9aa1-9373105cf3f6.json
deleted file mode 100644
index 95a1b938..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fd12b75d-a6ec-5ef1-9aa1-9373105cf3f6.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3811",
-    "MetadataAccess": [
-        "oai:ota:oucs:3811"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Lloyd, Robert, 1733-1764."
-    ],
-    "fulltext": "oai:ota:oucs:3811;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3811.xml;The actor: A poetical epistle to Bonnell Thornton, Esq.;Lloyd, Robert, 1733-1764.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fd12b75d-a6ec-5ef1-9aa1-9373105cf3f6",
-    "oai_identifier": [
-        "oai:ota:oucs:3811"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The actor: A poetical epistle to Bonnell Thornton, Esq."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3811.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fd24853b-2a9a-5c7d-8e19-c99dc4752e4f.json b/oaitestdata/clarin-oai_dc/SET_1/json/fd24853b-2a9a-5c7d-8e19-c99dc4752e4f.json
deleted file mode 100644
index 655d639e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fd24853b-2a9a-5c7d-8e19-c99dc4752e4f.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3019",
-    "MetadataAccess": [
-        "oai:ota:oucs:3019"
-    ],
-    "PublicationTimestamp": "1903-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1903"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Yeats, W.B. (William Butler), 1865-1939"
-    ],
-    "fulltext": "oai:ota:oucs:3019;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3019.xml;The Collected Poems;Yeats, W.B. (William Butler), 1865-1939;1903;text_and_corpus_linguistics;Irish poetry -- 20th century;eng;Oxford Text Archive, University of Oxford;Text;Poems;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fd24853b-2a9a-5c7d-8e19-c99dc4752e4f",
-    "oai_identifier": [
-        "oai:ota:oucs:3019"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Irish poetry -- th century"
-        }
-    ],
-    "title": [
-        "The Collected Poems"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3019.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fd2aa820-4874-5174-8c25-ed20f73283f5.json b/oaitestdata/clarin-oai_dc/SET_1/json/fd2aa820-4874-5174-8c25-ed20f73283f5.json
deleted file mode 100644
index 89cafa04..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fd2aa820-4874-5174-8c25-ed20f73283f5.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Institute of Slavic Studies, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 152",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish",
-        "Russian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/534",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/534"
-    ],
-    "PID": "http://hdl.handle.net/11321/534",
-    "PublicationTimestamp": "2018-07-21T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Institute of Slavic Studies, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "IS PAS corpora license",
-        "http://clarin-pl.eu/en/licenses/is-pas-corpora-license/",
-        "CC"
-    ],
-    "author": [
-        "Tymoshuk, Roman",
-        "Sosnowski, Wojciech",
-        "Roszko, Danuta",
-        "Roszko, Roman",
-        "Duszkin, Maksim"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/534;2018-07-21T20:35:07Z;hdl_11321_3;hdl_11321_4;Polish-Russian Parallel Corpus;Roszko, Roman;Sosnowski, Wojciech;Duszkin, Maksim;Roszko, Danuta;Tymoshuk, Roman;Polish;Russian;Parallel Corpora;Polish-Russian Parallel Corpus;2018-07-21;corpus;http://hdl.handle.net/11321/534;pol;rus;IS PAS corpora license;http://clarin-pl.eu/en/licenses/is-pas-corpora-license/;CC;text/plain; charset=utf-8;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;downloadable_files_count: 152;Institute of Slavic Studies, Polish Academy of Sciences",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fd2aa820-4874-5174-8c25-ed20f73283f5",
-    "notes": [
-        "Polish-Russian Parallel Corpus"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/534"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Polish"
-        },
-        {
-            "name": "Russian"
-        },
-        {
-            "name": "Parallel Corpora"
-        }
-    ],
-    "title": [
-        "Polish-Russian Parallel Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fd2da9d3-f258-595a-9dd6-397d739d9aad.json b/oaitestdata/clarin-oai_dc/SET_1/json/fd2da9d3-f258-595a-9dd6-397d739d9aad.json
deleted file mode 100644
index 0f47e52d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fd2da9d3-f258-595a-9dd6-397d739d9aad.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:4504",
-    "MetadataAccess": [
-        "oai:ota:oucs:4504"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Williams, Helen Maria, 1762-1827."
-    ],
-    "fulltext": "oai:ota:oucs:4504;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/4504.xml;Julia, a novel; interspersed with some poetical pieces. By Helen Maria Williams. In two volumes.: [pt.2];Williams, Helen Maria, 1762-1827.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fd2da9d3-f258-595a-9dd6-397d739d9aad",
-    "oai_identifier": [
-        "oai:ota:oucs:4504"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Julia, a novel; interspersed with some poetical pieces. By Helen Maria Williams. In two volumes.: [pt.2]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/4504.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fd3ee36b-5fcb-5cf3-b903-92f04aa02040.json b/oaitestdata/clarin-oai_dc/SET_1/json/fd3ee36b-5fcb-5cf3-b903-92f04aa02040.json
deleted file mode 100644
index f93a7b80..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fd3ee36b-5fcb-5cf3-b903-92f04aa02040.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 3",
-        "text/plain",
-        "application/pdf",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Danish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repository.clarin.dk:20.500.12115/19",
-    "MetadataAccess": [
-        "oai:repository.clarin.dk:20.500.12115/19"
-    ],
-    "PID": "http://hdl.handle.net/20.500.12115/19",
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Centre for Language Technology, NorS, University of Copenhagen"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "CLARIN-ACA-NC",
-        "https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NC=1&NORED=1",
-        "ACA"
-    ],
-    "author": [
-        "Jongejan, Bart"
-    ],
-    "fulltext": "oai:repository.clarin.dk:20.500.12115/19;2018-06-28T13:26:33Z;hdl_20.500.12115_1;hdl_20.500.12115_3;Dictionary for the CST Lemmatizer;Jongejan, Bart;lemmatizer;Binary wordlists for the CST lemmatizer as suplement to the rules of the lemmatizer. Works with both tagged and untagged input.\r\nUse: cstlemma -d NAME-OF-WORDLIST;2013;lexicalConceptualResource;http://hdl.handle.net/20.500.12115/19;dan;CLARIN-ACA-NC;https://kitwiki.csc.fi/twiki/bin/view/FinCLARIN/ClarinEulaAca?ID=1&AFFIL=EDU&BY=1&NC=1&NORED=1;ACA;application/zip;application/pdf;text/plain;text/plain; charset=utf-8;downloadable_files_count: 3;Centre for Language Technology, NorS, University of Copenhagen",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fd3ee36b-5fcb-5cf3-b903-92f04aa02040",
-    "notes": [
-        "Binary wordlists for the CST lemmatizer as suplement to the rules of the lemmatizer. Works with both tagged and untagged input.\r\nUse: cstlemma -d NAME-OF-WORDLIST"
-    ],
-    "oai_identifier": [
-        "oai:repository.clarin.dk:20.500.12115/19"
-    ],
-    "oai_set": [
-        "hdl_20.500.12115_1",
-        "hdl_20.500.12115_3"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "lemmatizer"
-        }
-    ],
-    "title": [
-        "Dictionary for the CST Lemmatizer"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fd479a87-66fb-512c-8c59-e81c3e07999e.json b/oaitestdata/clarin-oai_dc/SET_1/json/fd479a87-66fb-512c-8c59-e81c3e07999e.json
deleted file mode 100644
index 8adc11af..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fd479a87-66fb-512c-8c59-e81c3e07999e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5188",
-    "MetadataAccess": [
-        "oai:ota:oucs:5188"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Inchbald, Mrs., 1753-1821."
-    ],
-    "fulltext": "oai:ota:oucs:5188;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5188.xml;A simple story: In four volumes. By Mrs. Inchbald. [pt.3];Inchbald, Mrs., 1753-1821.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fd479a87-66fb-512c-8c59-e81c3e07999e",
-    "oai_identifier": [
-        "oai:ota:oucs:5188"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "A simple story: In four volumes. By Mrs. Inchbald. [pt.3]"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5188.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fd5d4bf5-9692-5bcc-928e-af48911751e4.json b/oaitestdata/clarin-oai_dc/SET_1/json/fd5d4bf5-9692-5bcc-928e-af48911751e4.json
deleted file mode 100644
index 76033e8a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fd5d4bf5-9692-5bcc-928e-af48911751e4.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Somali"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/8",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/8"
-    ],
-    "PID": "http://hdl.handle.net/10794/8",
-    "PublicationTimestamp": "2015-11-20T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Spr\u00e5kbanken, University of Gothenburg"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/8;2017-10-27T16:38:40Z;hdl_10794_1;hdl_10794_2;Af Soomaali 1971-79 (2017-10-16);Af Soomaali 1971-79 (2017-10-16);n/a, n/a;Somali;Corpus;Af Soomaali 1971-79. The material is sentence scrambled.;Af Soomaali 1971-79. Materialet \u00e4r meningsomkastat.;2015-11-20;corpus;http://hdl.handle.net/10794/8;som;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Spr\u00e5kbanken, University of Gothenburg;https://spraakbanken.gu.se/swe/resurs/somali-1971-79",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fd5d4bf5-9692-5bcc-928e-af48911751e4",
-    "notes": [
-        "Af Soomaali 1971-79. The material is sentence scrambled.",
-        "Af Soomaali 1971-79. Materialet \u00e4r meningsomkastat."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/8"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Somali"
-        },
-        {
-            "name": "Corpus"
-        }
-    ],
-    "title": [
-        "Af Soomaali 1971-79 (2017-10-16)",
-        "Af Soomaali 1971-79 (2017-10-16)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fd6e8bd8-9666-569e-9c0a-298d3ade8b96.json b/oaitestdata/clarin-oai_dc/SET_1/json/fd6e8bd8-9666-569e-9c0a-298d3ade8b96.json
deleted file mode 100644
index 5ecbfb34..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fd6e8bd8-9666-569e-9c0a-298d3ade8b96.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Paddy Bullard"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2759",
-    "MetadataAccess": [
-        "oai:ota:oucs:2759"
-    ],
-    "PublicationTimestamp": "1713-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1713"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Jonathan Swift Archive"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Swift, Jonathan, 1667-1745"
-    ],
-    "fulltext": "oai:ota:oucs:2759;2018-08-02T14:11:37Z;http://ota.ox.ac.uk/headers/2759.xml;The importance of The guardian considered;Swift, Jonathan, 1667-1745;1713;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Paddy Bullard;Text;Jonathan Swift Archive;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fd6e8bd8-9666-569e-9c0a-298d3ade8b96",
-    "oai_identifier": [
-        "oai:ota:oucs:2759"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The importance of The guardian considered"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2759.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fd94827b-8d3f-559a-8f80-20186fa4188b.json b/oaitestdata/clarin-oai_dc/SET_1/json/fd94827b-8d3f-559a-8f80-20186fa4188b.json
deleted file mode 100644
index eaa8ad3a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fd94827b-8d3f-559a-8f80-20186fa4188b.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Czech"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-68D8-1",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-68D8-1"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-68D8-1",
-    "PublicationTimestamp": "2013-11-12T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "RelatedIdentifier": [
-        "http://hdl.handle.net/11234/1-1674"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Straka, Milan",
-        "Strakov\u00e1, Jana"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-68D8-1;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Czech Models (MorfFlex CZ + PDT) for MorphoDiTa;Straka, Milan;Strakov\u00e1, Jana;MorphoDiTa;Czech;morphological analysis;morphological generation;PoS tagging;Czech models for MorphoDiTa, providing morphological analysis, morphological generation and part-of-speech tagging.\r\n\r\nThe morphological dictionary is created from MorfFlex CZ and the PoS tagger is trained on PDT (Prague Dependency Treebank).;2013-11-12;languageDescription;http://hdl.handle.net/11858/00-097C-0000-0023-68D8-1;ces;http://hdl.handle.net/11234/1-1674;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/morphodita/users-manual#czech-morfflex-pdt",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fd94827b-8d3f-559a-8f80-20186fa4188b",
-    "notes": [
-        "Czech models for MorphoDiTa, providing morphological analysis, morphological generation and part-of-speech tagging.\r\n\r\nThe morphological dictionary is created from MorfFlex CZ and the PoS tagger is trained on PDT (Prague Dependency Treebank)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-68D8-1"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "MorphoDiTa"
-        },
-        {
-            "name": "Czech"
-        },
-        {
-            "name": "morphological analysis"
-        },
-        {
-            "name": "morphological generation"
-        },
-        {
-            "name": "PoS tagging"
-        }
-    ],
-    "title": [
-        "Czech Models (MorfFlex CZ + PDT) for MorphoDiTa"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fd9af609-902f-5078-b0a8-fcaa5f2e3305.json b/oaitestdata/clarin-oai_dc/SET_1/json/fd9af609-902f-5078-b0a8-fcaa5f2e3305.json
deleted file mode 100644
index f8bc25ef..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fd9af609-902f-5078-b0a8-fcaa5f2e3305.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Institute of Mathematics and Computer Science, University of Latvia"
-    ],
-    "Contributor": [
-        "B\u0113rzi\u0146a-Reinsone, Sanita"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Latvian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-620",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-620"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-620",
-    "PublicationTimestamp": "1999-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1999"
-    ],
-    "Publisher": [
-        "Institute of Mathematics and Computer Science, University of Latvia"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Latvia"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-620;2016-04-06T16:39:55Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Latvian Folktales and Legends;B\u0113rzi\u0146a-Reinsone, Sanita;Latvian fairytales and legends collected by Latvian folklorist P\u0113teris \u0160mits, published 1927-1938 (15 volumes). It is the largest published collection of Latvian folktales and legends.;1999;corpus;http://hdl.handle.net/11372/LRT-620;lav;downloadable_files_count: 0;Latvia;Institute of Mathematics and Computer Science, University of Latvia;http://valoda.ailab.lv/folklora/pasakas/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fd9af609-902f-5078-b0a8-fcaa5f2e3305",
-    "notes": [
-        "Latvian fairytales and legends collected by Latvian folklorist P\u0113teris \u0160mits, published 1927-1938 (15 volumes). It is the largest published collection of Latvian folktales and legends."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-620"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Latvian Folktales and Legends"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fdc74244-ba1d-599c-bb16-43be38466e99.json b/oaitestdata/clarin-oai_dc/SET_1/json/fdc74244-ba1d-599c-bb16-43be38466e99.json
deleted file mode 100644
index 97470086..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fdc74244-ba1d-599c-bb16-43be38466e99.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "Contributor": [
-        "Broeder, Daan"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1208",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1208"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1208",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1208;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;IMDI browser;Broeder, Daan;The Imdi Browser enables users to navigate and search swiftly through an IMDI metadata repository. It has two incarnations: a standalone application and a web application.;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1208;downloadable_files_count: 0;Netherlands (the);Max Planck Institute for Psycholinguistics;http://tla.mpi.nl/tools/tla-tools/imdi_browser/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fdc74244-ba1d-599c-bb16-43be38466e99",
-    "notes": [
-        "The Imdi Browser enables users to navigate and search swiftly through an IMDI metadata repository. It has two incarnations: a standalone application and a web application."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1208"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "IMDI browser"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fddab289-2c55-5e6a-8526-d72faa3b14b7.json b/oaitestdata/clarin-oai_dc/SET_1/json/fddab289-2c55-5e6a-8526-d72faa3b14b7.json
deleted file mode 100644
index 7d2174f7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fddab289-2c55-5e6a-8526-d72faa3b14b7.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Bellmanss\u00e4llskapet"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 2",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Swedish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:repo.spraakbanken.gu.se:10794/82",
-    "MetadataAccess": [
-        "oai:repo.spraakbanken.gu.se:10794/82"
-    ],
-    "PID": "http://hdl.handle.net/10794/82",
-    "PublicationTimestamp": "2012-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Bellmanss\u00e4llskapet"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "http://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "n/a, n/a"
-    ],
-    "fulltext": "oai:repo.spraakbanken.gu.se:10794/82;2017-10-26T08:04:20Z;hdl_10794_1;hdl_10794_2;Bellman (2015-11-09);Bellman (2015-11-09);n/a, n/a;Swedish;Collected works;Collected works of C.M. Bellman.;C.M. Bellmans samlade verk.;2012-05-30;corpus;http://hdl.handle.net/10794/82;swe;Creative Commons - Attribution 4.0 International (CC BY 4.0);http://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 2;Bellmanss\u00e4llskapet;https://spraakbanken.gu.se/swe/resurs/bellman",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fddab289-2c55-5e6a-8526-d72faa3b14b7",
-    "notes": [
-        "Collected works of C.M. Bellman.",
-        "C.M. Bellmans samlade verk."
-    ],
-    "oai_identifier": [
-        "oai:repo.spraakbanken.gu.se:10794/82"
-    ],
-    "oai_set": [
-        "hdl_10794_1",
-        "hdl_10794_2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Swedish"
-        },
-        {
-            "name": "Collected works"
-        }
-    ],
-    "title": [
-        "Bellman (2015-11-09)",
-        "Bellman (2015-11-09)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fe2e6b60-b330-56a1-bf74-24c200ac8282.json b/oaitestdata/clarin-oai_dc/SET_1/json/fe2e6b60-b330-56a1-bf74-24c200ac8282.json
deleted file mode 100644
index 3c108ace..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fe2e6b60-b330-56a1-bf74-24c200ac8282.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Department of Information Technology, Gauhati University, Assam, India"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Assamese"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/615",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/615"
-    ],
-    "PID": "http://hdl.handle.net/11321/615",
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Department of Information Technology, Gauhati University, Assam, India"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "author": [
-        "Sarma, Prof. Shikhar Kr."
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/615;2019-01-08T10:47:46Z;hdl_11321_3;hdl_11321_610;Assamese Named Entities;Sarma, Prof. Shikhar Kr.;Assamese NLP;Assamese NEs;Assamese Named entities;Gauhati University;A list comprising of 104138 Assamese named entities was developed. The list also comprises of NEs which are categorized as Organization(\u09b8\u09a6\u09cc \u0985\u09b8\u09ae \u099b\u09be\u09a4\u09cd\u09f0 \u09b8\u09a8\u09cd\u09a5\u09be), Person Names(\u09aa\u0999\u09cd\u0995\u099c), Festival(\u09a6\u09c1\u09f0\u09cd\u0997\u09be \u09aa\u09c2\u099c\u09be), Flower(\u0997\u09cb\u09b2\u09be\u09aa\u09ab\u09c1\u09b2), Folk Instruments(\u09ac\u09be\u0981\u09b9\u09c0), Food habits(\u09ad\u09be\u09a4), Games(\u09a2\u09cb\u09aa \u0996\u09c7\u09b2), Honorific title(\u099c\u09df\u09be\u09b2), Measurement(\u09af\u09cb\u0997), Place Name(\u09a4\u09c7\u099c\u09aa\u09c1\u09f0), Plants(\u0986\u0981\u09b9\u09a4 \u0997\u099b), Birds(\u09ad\u09be\u099f\u09cc), Religious Places(\u09aa\u09cb\u09f1\u09be \u09ae\u0995\u09cd\u0995\u09be), Tourist Places(\u0995\u09be\u099c\u09bf\u09f0\u0999\u09be), Institution name(\u0997\u09c1\u09f1\u09be\u09b9\u09be\u099f\u09c0 \u09ac\u09bf\u09b6\u09cd\u09ac\u09ac\u09bf\u09a6\u09cd\u09af\u09be\u09b2\u09df)\r\n\r\n---\r\n\r\n1. These Assamese NLP resources including the Tools and Applications are developed\r\nduring Research and Development Projects as well as Masters and Ph.D. thesis\r\nworks.\r\n2. These are mainly developed or generated at Gauhati University Department of\r\nComputer Science and Department of Information Technology.\r\n3. These resources are used by students and researchers for further studies, researches, as\r\nwell as for design and development of tools and applications.\r\n4. Computational Linguistics in Assamese is not rich, and Natural Language Processing\r\nworks have mainly started during last two decades, and most of the resources are first\r\ngeneration resources, and with ample scope for upgrading, enriching, and purifying.\r\n5. These are very good and essential resources for all the researchers in Assamese NLP, as\r\nthe language requires more and more NLP works to make Assamese a rich media for\r\nthe digital world.\r\n6. Anyone interested, or in need of such resources may express their interest for the\r\nrequired resources, and the way of availability will be advised/informed accordingly.\r\n7. These are purely research materials and could only be used for further research only.\r\n8. Researchers may visit the NLP Lab of Department of Information Technology, Gauhati\r\nUniversity, Guwahati, India or contact us.\r\n9. Researchers interested in collaborative works, and also students for project works, are\r\nwelcome.\r\n10. Contact person is Professor Shikhar Kr. Sarma, Department of Information\r\nTechnology, Gauhati University, Guwahati 781014, Assam, India. Email-\r\nsks@gauhati.ac.in;2019-01-08;lexicalConceptualResource;http://hdl.handle.net/11321/615;asm;downloadable_files_count: 0;Department of Information Technology, Gauhati University, Assam, India",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fe2e6b60-b330-56a1-bf74-24c200ac8282",
-    "notes": [
-        "A list comprising of 104138 Assamese named entities was developed. The list also comprises of NEs which are categorized as Organization(\u09b8\u09a6\u09cc \u0985\u09b8\u09ae \u099b\u09be\u09a4\u09cd\u09f0 \u09b8\u09a8\u09cd\u09a5\u09be), Person Names(\u09aa\u0999\u09cd\u0995\u099c), Festival(\u09a6\u09c1\u09f0\u09cd\u0997\u09be \u09aa\u09c2\u099c\u09be), Flower(\u0997\u09cb\u09b2\u09be\u09aa\u09ab\u09c1\u09b2), Folk Instruments(\u09ac\u09be\u0981\u09b9\u09c0), Food habits(\u09ad\u09be\u09a4), Games(\u09a2\u09cb\u09aa \u0996\u09c7\u09b2), Honorific title(\u099c\u09df\u09be\u09b2), Measurement(\u09af\u09cb\u0997), Place Name(\u09a4\u09c7\u099c\u09aa\u09c1\u09f0), Plants(\u0986\u0981\u09b9\u09a4 \u0997\u099b), Birds(\u09ad\u09be\u099f\u09cc), Religious Places(\u09aa\u09cb\u09f1\u09be \u09ae\u0995\u09cd\u0995\u09be), Tourist Places(\u0995\u09be\u099c\u09bf\u09f0\u0999\u09be), Institution name(\u0997\u09c1\u09f1\u09be\u09b9\u09be\u099f\u09c0 \u09ac\u09bf\u09b6\u09cd\u09ac\u09ac\u09bf\u09a6\u09cd\u09af\u09be\u09b2\u09df)\r\n\r\n---\r\n\r\n1. These Assamese NLP resources including the Tools and Applications are developed\r\nduring Research and Development Projects as well as Masters and Ph.D. thesis\r\nworks.\r\n2. These are mainly developed or generated at Gauhati University Department of\r\nComputer Science and Department of Information Technology.\r\n3. These resources are used by students and researchers for further studies, researches, as\r\nwell as for design and development of tools and applications.\r\n4. Computational Linguistics in Assamese is not rich, and Natural Language Processing\r\nworks have mainly started during last two decades, and most of the resources are first\r\ngeneration resources, and with ample scope for upgrading, enriching, and purifying.\r\n5. These are very good and essential resources for all the researchers in Assamese NLP, as\r\nthe language requires more and more NLP works to make Assamese a rich media for\r\nthe digital world.\r\n6. Anyone interested, or in need of such resources may express their interest for the\r\nrequired resources, and the way of availability will be advised/informed accordingly.\r\n7. These are purely research materials and could only be used for further research only.\r\n8. Researchers may visit the NLP Lab of Department of Information Technology, Gauhati\r\nUniversity, Guwahati, India or contact us.\r\n9. Researchers interested in collaborative works, and also students for project works, are\r\nwelcome.\r\n10. Contact person is Professor Shikhar Kr. Sarma, Department of Information\r\nTechnology, Gauhati University, Guwahati 781014, Assam, India. Email-\r\nsks@gauhati.ac.in"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/615"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_610"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Assamese NLP"
-        },
-        {
-            "name": "Assamese NEs"
-        },
-        {
-            "name": "Assamese Named entities"
-        },
-        {
-            "name": "Gauhati University"
-        }
-    ],
-    "title": [
-        "Assamese Named Entities"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fe3cbb68-cb60-5c40-9639-9972aa7da658.json b/oaitestdata/clarin-oai_dc/SET_1/json/fe3cbb68-cb60-5c40-9639-9972aa7da658.json
deleted file mode 100644
index 71f124ff..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fe3cbb68-cb60-5c40-9639-9972aa7da658.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1415",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1415"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1415",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "SpatialCoverage": [
-        "Spain"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1415;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;iula_lexicon_lookup;Lexicon lookup (given a word form, the webservice returns the information in the lexicon).;2014-07-30;toolService;http://hdl.handle.net/11372/LRT-1415;downloadable_files_count: 0;Spain;Institut Universitari de Ling\u00fc\u00edstica Aplicada, Universitat Pompeu Fabra",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fe3cbb68-cb60-5c40-9639-9972aa7da658",
-    "notes": [
-        "Lexicon lookup (given a word form, the webservice returns the information in the lexicon)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1415"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "iula_lexicon_lookup"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fe461bd3-8a12-52ba-9360-e413262bfc65.json b/oaitestdata/clarin-oai_dc/SET_1/json/fe461bd3-8a12-52ba-9360-e413262bfc65.json
deleted file mode 100644
index a6166e85..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fe461bd3-8a12-52ba-9360-e413262bfc65.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "Berlin-Brandenburg Academy of Sciences and Humanities"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/tei+xml",
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-971",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-971"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-971",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Berlin-Brandenburg Academy of Sciences and Humanities"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-971;2016-04-06T16:39:53Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Juilland-D-Korpus;Written German from 1920-39. 500,000 tokens, 392 texts. POS and lemma, TEI XML. Part of Das digitale W\u00f6rterbuch der deutschen Sprache der 20. Jahrhunderts;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-971;deu;application/tei+xml;downloadable_files_count: 0;Germany;Berlin-Brandenburg Academy of Sciences and Humanities;http://www.dwds.de/ressourcen/juilland",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fe461bd3-8a12-52ba-9360-e413262bfc65",
-    "notes": [
-        "Written German from 1920-39. 500,000 tokens, 392 texts. POS and lemma, TEI XML. Part of Das digitale W\u00f6rterbuch der deutschen Sprache der 20. Jahrhunderts"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-971"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Juilland-D-Korpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fe565f34-44af-5e21-99af-d9737a713da1.json b/oaitestdata/clarin-oai_dc/SET_1/json/fe565f34-44af-5e21-99af-d9737a713da1.json
deleted file mode 100644
index 830d892d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fe565f34-44af-5e21-99af-d9737a713da1.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "Fondazione Bruno Kessler, Trento, Italy"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/zip",
-        "downloadable_files_count: 1",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "English",
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1966",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-1966"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-1966",
-    "PublicationTimestamp": "2017-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Fondazione Bruno Kessler, Trento, Italy"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/H2020/645452"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "AGREEMENT ON THE USE OF DATA IN QT21 APE Task",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21",
-        "PUB"
-    ],
-    "author": [
-        "Turchi, Marco",
-        "Chatterjee, Rajen",
-        "Negri, Matteo"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-1966;2018-07-02T22:05:53Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;WMT17 En-De APE Shared Task Data;Turchi, Marco;Chatterjee, Rajen;Negri, Matteo;machine translation;shared task;post-editing;automatic post-editing;Training data for the WMT 2017 Automatic post-editing task (the same used for the Sentence-level Quality Estimation task). They consist in 11,000 English-German triplets (source, target and post-edit) belonging to the IT domain and already tokenized. All data is provided by the EU project QT21 (http://www.qt21.eu/).;2017-02-15;corpus;http://hdl.handle.net/11234/1-1966;eng;deu;info:eu-repo/grantAgreement/EC/H2020/645452;AGREEMENT ON THE USE OF DATA IN QT21 APE Task;https://lindat.mff.cuni.cz/repository/xmlui/page/licence-TAUS_QT21;PUB;application/zip;text/plain; charset=utf-8;downloadable_files_count: 1;Fondazione Bruno Kessler, Trento, Italy;http://www.statmt.org/wmt17/ape-task.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fe565f34-44af-5e21-99af-d9737a713da1",
-    "notes": [
-        "Training data for the WMT 2017 Automatic post-editing task (the same used for the Sentence-level Quality Estimation task). They consist in 11,000 English-German triplets (source, target and post-edit) belonging to the IT domain and already tokenized. All data is provided by the EU project QT21 (http://www.qt21.eu/)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-1966"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine translation"
-        },
-        {
-            "name": "shared task"
-        },
-        {
-            "name": "post-editing"
-        },
-        {
-            "name": "automatic post-editing"
-        }
-    ],
-    "title": [
-        "WMT17 En-De APE Shared Task Data"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fe584936-064b-5105-a6fb-9f3ee790a37b.json b/oaitestdata/clarin-oai_dc/SET_1/json/fe584936-064b-5105-a6fb-9f3ee790a37b.json
deleted file mode 100644
index 1be6ac9c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fe584936-064b-5105-a6fb-9f3ee790a37b.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Masaryk University, NLP Centre"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "application/x-gzip",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Tigrinya"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-2592",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11234/1-2592"
-    ],
-    "PID": "http://hdl.handle.net/11234/1-2592",
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Masaryk University, NLP Centre"
-    ],
-    "RelatedIdentifier": [
-        "https://www.sketchengine.co.uk/wp-content/uploads/2015/05/Corpus_Factory_2010.pdf",
-        "http://habit-project.eu/wiki/TigrinyaCorpus"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "NLP Centre Web Corpus License",
-        "https://lindat.mff.cuni.cz/repository/xmlui/page/license-NLPC-WeC",
-        "ACA"
-    ],
-    "author": [
-        "Suchomel, V\u00edt",
-        "Rychl\u00fd, Pavel"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11234/1-2592;2018-07-02T22:05:50Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;Tigrinya Web Corpus;Suchomel, V\u00edt;Rychl\u00fd, Pavel;text corpora;Ethiopian languages;web corpora;under-resourced languages;Tigrinya;Tigrinya web corpus. Crawled by SpiderLing in January 2016. Encoded in UTF-8, cleaned, deduplicated.;2016;corpus;http://hdl.handle.net/11234/1-2592;tir;https://www.sketchengine.co.uk/wp-content/uploads/2015/05/Corpus_Factory_2010.pdf;http://habit-project.eu/wiki/TigrinyaCorpus;NLP Centre Web Corpus License;https://lindat.mff.cuni.cz/repository/xmlui/page/license-NLPC-WeC;ACA;application/x-gzip;text/plain; charset=utf-8;downloadable_files_count: 1;Masaryk University, NLP Centre;http://habit-project.eu/wiki/HabitSystemFinal",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fe584936-064b-5105-a6fb-9f3ee790a37b",
-    "notes": [
-        "Tigrinya web corpus. Crawled by SpiderLing in January 2016. Encoded in UTF-8, cleaned, deduplicated."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11234/1-2592"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "text corpora"
-        },
-        {
-            "name": "Ethiopian languages"
-        },
-        {
-            "name": "web corpora"
-        },
-        {
-            "name": "under-resourced languages"
-        },
-        {
-            "name": "Tigrinya"
-        }
-    ],
-    "title": [
-        "Tigrinya Web Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fe5988ee-e2f2-5be1-b7fa-43b2a9d0686c.json b/oaitestdata/clarin-oai_dc/SET_1/json/fe5988ee-e2f2-5be1-b7fa-43b2a9d0686c.json
deleted file mode 100644
index 8b3ca297..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fe5988ee-e2f2-5be1-b7fa-43b2a9d0686c.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5150",
-    "MetadataAccess": [
-        "oai:ota:oucs:5150"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Lennox, Charlotte, ca. 1729-1804."
-    ],
-    "fulltext": "oai:ota:oucs:5150;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5150.xml;The memoirs of the Countess of Berci. Taken from the French by the author of the Female Quixote. In two volumes.: [pt.1];Histoire trage-comique de nostre temps, sous les noms de Lysandre et de Caliste. English;Lennox, Charlotte, ca. 1729-1804.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fe5988ee-e2f2-5be1-b7fa-43b2a9d0686c",
-    "oai_identifier": [
-        "oai:ota:oucs:5150"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The memoirs of the Countess of Berci. Taken from the French by the author of the Female Quixote. In two volumes.: [pt.1]",
-        "Histoire trage-comique de nostre temps, sous les noms de Lysandre et de Caliste. English"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5150.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fe62a914-678f-5dc3-a6cd-d1df2f60727e.json b/oaitestdata/clarin-oai_dc/SET_1/json/fe62a914-678f-5dc3-a6cd-d1df2f60727e.json
deleted file mode 100644
index 9e5f1744..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fe62a914-678f-5dc3-a6cd-d1df2f60727e.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-651",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-651"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-651",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "Code of conduct"
-    ],
-    "SpatialCoverage": [
-        "Mexico"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-651;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Chontal corpus;Documentation of the Chontal project (DoBeS project);2014-07-30;corpus;http://hdl.handle.net/11372/LRT-651;Code of conduct;downloadable_files_count: 0;Mexico;http://corpus1.mpi.nl/ds/imdi_browser/?openpath=MPI361244%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fe62a914-678f-5dc3-a6cd-d1df2f60727e",
-    "notes": [
-        "Documentation of the Chontal project (DoBeS project)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-651"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "Chontal corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fe6361c7-fc02-5b71-8941-6a0b7082673f.json b/oaitestdata/clarin-oai_dc/SET_1/json/fe6361c7-fc02-5b71-8941-6a0b7082673f.json
deleted file mode 100644
index 042b969d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fe6361c7-fc02-5b71-8941-6a0b7082673f.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "A"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2057",
-    "MetadataAccess": [
-        "oai:ota:oucs:2057"
-    ],
-    "PublicationYear": [
-        "475 BCE-221 BCE"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Confucius (translations)"
-    ],
-    "fulltext": "oai:ota:oucs:2057;2018-05-17T09:22:11Z;http://ota.ox.ac.uk/headers/2057.xml;Analects;Confucius (translations);475 BCE-221 BCE;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;A;Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fe6361c7-fc02-5b71-8941-6a0b7082673f",
-    "oai_identifier": [
-        "oai:ota:oucs:2057"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "Analects"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2057.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fe795821-8177-5c2a-9a94-98e01e31340a.json b/oaitestdata/clarin-oai_dc/SET_1/json/fe795821-8177-5c2a-9a94-98e01e31340a.json
deleted file mode 100644
index 187e2737..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fe795821-8177-5c2a-9a94-98e01e31340a.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Triggs, Jeffery"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3094",
-    "MetadataAccess": [
-        "oai:ota:oucs:3094"
-    ],
-    "PublicationTimestamp": "1857-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1857"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gaskell, Elizabeth Cleghorn, 1810-1865"
-    ],
-    "fulltext": "oai:ota:oucs:3094;2018-07-02T14:44:52Z;http://ota.ox.ac.uk/headers/3094.xml;The Life of Charlotte Bront\u00c3\u00ab;Gaskell, Elizabeth Cleghorn, 1810-1865;not after: 1857;text_and_corpus_linguistics;English fiction -- 19th century;eng;Oxford Text Archive, University of Oxford;Triggs, Jeffery;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fe795821-8177-5c2a-9a94-98e01e31340a",
-    "oai_identifier": [
-        "oai:ota:oucs:3094"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English fiction -- th century"
-        }
-    ],
-    "title": [
-        "The Life of Charlotte Bront\u00c3\u00ab"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3094.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fe79ce6c-0e88-5c2e-b6ab-27f422d94752.json b/oaitestdata/clarin-oai_dc/SET_1/json/fe79ce6c-0e88-5c2e-b6ab-27f422d94752.json
deleted file mode 100644
index bb7f69b7..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fe79ce6c-0e88-5c2e-b6ab-27f422d94752.json
+++ /dev/null
@@ -1,49 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:5530",
-    "MetadataAccess": [
-        "oai:ota:oucs:5530"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "fulltext": "oai:ota:oucs:5530;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/5530.xml;An enquiry into the advantage received by the first eight years inoculation;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fe79ce6c-0e88-5c2e-b6ab-27f422d94752",
-    "oai_identifier": [
-        "oai:ota:oucs:5530"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "An enquiry into the advantage received by the first eight years inoculation"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/5530.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fe80d7ca-8a4b-53af-8bbf-f391b2fda7e4.json b/oaitestdata/clarin-oai_dc/SET_1/json/fe80d7ca-8a4b-53af-8bbf-f391b2fda7e4.json
deleted file mode 100644
index d722e588..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fe80d7ca-8a4b-53af-8bbf-f391b2fda7e4.json
+++ /dev/null
@@ -1,115 +0,0 @@
-{
-    "Contact": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "application/zip"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/586",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/586"
-    ],
-    "PID": "http://hdl.handle.net/11321/586",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Institute of Computer Science, Polish Academy of Sciences"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Andrejewicz, Urszula",
-        "Skubida, Natalia",
-        "Kocyba, Natalia",
-        "Wi\u015bniakowska, Lidia",
-        "Patejuk, Agnieszka",
-        "Filipczak, Joanna",
-        "\u017bochowska, Natalia",
-        "Itoya, Bo\u017cena",
-        "Maciejewska, Ma\u0142gorzata",
-        "Szczyszek, Micha\u0142",
-        "Kaczmarska, El\u017cbieta",
-        "Batko, Piotr",
-        "Zgondek, Maciej",
-        "Zagajewska, Anna",
-        "Drabik, Lidia",
-        "Sulich, Adrian",
-        "Grzeszak, Anna",
-        "Bukowiecka, Halina",
-        "\u015awidzi\u0144ski, Marek",
-        "Norwa, Agnieszka",
-        "Andrzejczuk, Anna",
-        "Przepi\u00f3rkowski, Adam",
-        "Stankiewicz, Anna",
-        "Andrejewicz, J\u0119drzej",
-        "Szymczak, Jakub",
-        "Rosalska, Paulina",
-        "Zawis\u0142awska, Magdalena",
-        "Skwarski, Filip",
-        "\u0141odzi\u0144ska, Agnieszka",
-        "Opacki, Marcin",
-        "Alberski, Bart\u0142omiej",
-        "Woli\u0144ski, Marcin",
-        "W\u00f3jcicka, Alicja",
-        "Rabiega-Wi\u015bniewska, Joanna",
-        "Hajnicz, El\u017cbieta",
-        "Brodzi\u0144ska, Magdalena",
-        "Linsztet, Barbara",
-        "Kalu\u017cna-Go\u0142\u0105b, Marta",
-        "\u017burowski, Sebastian",
-        "Koz\u0142owska, Matylda"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/586;2018-07-26T15:53:43Z;hdl_11321_3;hdl_11321_4;Walenty (2018-06-29);Alberski, Bart\u0142omiej;Andrejewicz, J\u0119drzej;Andrejewicz, Urszula;Andrzejczuk, Anna;Batko, Piotr;Brodzi\u0144ska, Magdalena;Bukowiecka, Halina;Drabik, Lidia;Filipczak, Joanna;Grzeszak, Anna;Hajnicz, El\u017cbieta;Itoya, Bo\u017cena;Kaczmarska, El\u017cbieta;Kalu\u017cna-Go\u0142\u0105b, Marta;Kocyba, Natalia;Koz\u0142owska, Matylda;Linsztet, Barbara;\u0141odzi\u0144ska, Agnieszka;Maciejewska, Ma\u0142gorzata;Norwa, Agnieszka;Opacki, Marcin;Patejuk, Agnieszka;Przepi\u00f3rkowski, Adam;Rabiega-Wi\u015bniewska, Joanna;Rosalska, Paulina;Skubida, Natalia;Skwarski, Filip;Stankiewicz, Anna;Sulich, Adrian;Szczyszek, Micha\u0142;Szymczak, Jakub;\u015awidzi\u0144ski, Marek;Wi\u015bniakowska, Lidia;Woli\u0144ski, Marcin;W\u00f3jcicka, Alicja;Zagajewska, Anna;Zawis\u0142awska, Magdalena;Zgondek, Maciej;\u017bochowska, Natalia;\u017burowski, Sebastian;valence dictionary;syntactic schema;semantic frame;Walenty is a valence dictionary of Polish developed at the Institute of Computer Science, Polish Academy of Sciences (IPI PAN).\r\n\r\nThe original formalism of Walenty was established by Filip Skwarski, El\u017cbieta Hajnicz, Agnieszka Patejuk, Adam Przepi\u00f3rkowski, Marcin Woli\u0144ski, Marek \u015awidzi\u0144ski, and Magdalena Zawis\u0142awska. It has been further developed by El\u017cbieta Hajnicz, Agnieszka Patejuk, Adam Przepi\u00f3rkowski, and Marcin Woli\u0144ski. The semantic layer has been developed by El\u017cbieta Hajnicz and Anna Andrzejczuk.\r\n\r\nThe original seed of Walenty was provided by the automatic conversion, manually reviewed by Filip Skwarski, of the verbal valence dictionary used by the \u015awigra2 parser (6396 schemata for 1462 lemmata), which was in turn based on SDPV, the Syntactic Dictionary of Polish Verbs by Marek \u015awidzi\u0144ski (4148 schemata for 1064 lemmata). Afterwards, Walenty has been developed independently by adding new entries, syntactic schemata, in particular phraseological ones, and semantic frames.\r\n\r\nWalenty has been edited and compiled using the Slowal tool (http://zil.ipipan.waw.pl/Slowal) created by Bart\u0142omiej Nito\u0144 and Tomasz Bartosiak.\r\n\r\nThe version of Walenty from 2018.06.29 contains  101 047 syntactic schemata and 28 321 semantic frames of 13022 verbs 4070 nouns, 950 adjectives and 200 nouns.;2018;lexicalConceptualResource;http://hdl.handle.net/11321/586;pol;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;application/zip;application/zip;downloadable_files_count: 2;Institute of Computer Science, Polish Academy of Sciences;http://zil.ipipan.waw.pl/Walenty",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fe80d7ca-8a4b-53af-8bbf-f391b2fda7e4",
-    "notes": [
-        "Walenty is a valence dictionary of Polish developed at the Institute of Computer Science, Polish Academy of Sciences (IPI PAN).\r\n\r\nThe original formalism of Walenty was established by Filip Skwarski, El\u017cbieta Hajnicz, Agnieszka Patejuk, Adam Przepi\u00f3rkowski, Marcin Woli\u0144ski, Marek \u015awidzi\u0144ski, and Magdalena Zawis\u0142awska. It has been further developed by El\u017cbieta Hajnicz, Agnieszka Patejuk, Adam Przepi\u00f3rkowski, and Marcin Woli\u0144ski. The semantic layer has been developed by El\u017cbieta Hajnicz and Anna Andrzejczuk.\r\n\r\nThe original seed of Walenty was provided by the automatic conversion, manually reviewed by Filip Skwarski, of the verbal valence dictionary used by the \u015awigra2 parser (6396 schemata for 1462 lemmata), which was in turn based on SDPV, the Syntactic Dictionary of Polish Verbs by Marek \u015awidzi\u0144ski (4148 schemata for 1064 lemmata). Afterwards, Walenty has been developed independently by adding new entries, syntactic schemata, in particular phraseological ones, and semantic frames.\r\n\r\nWalenty has been edited and compiled using the Slowal tool (http://zil.ipipan.waw.pl/Slowal) created by Bart\u0142omiej Nito\u0144 and Tomasz Bartosiak.\r\n\r\nThe version of Walenty from 2018.06.29 contains  101 047 syntactic schemata and 28 321 semantic frames of 13022 verbs 4070 nouns, 950 adjectives and 200 nouns."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/586"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "valence dictionary"
-        },
-        {
-            "name": "syntactic schema"
-        },
-        {
-            "name": "semantic frame"
-        }
-    ],
-    "title": [
-        "Walenty (2018-06-29)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fe8b8345-2727-5dd1-9da5-08a854c2505c.json b/oaitestdata/clarin-oai_dc/SET_1/json/fe8b8345-2727-5dd1-9da5-08a854c2505c.json
deleted file mode 100644
index 001d3365..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fe8b8345-2727-5dd1-9da5-08a854c2505c.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=6999c3ca328011e2a2aa782bcb07413549c1bda35a744cecabaf17f115501fb1",
-    "MetadataAccess": [
-        "6999c3ca328011e2a2aa782bcb07413549c1bda35a744cecabaf17f115501fb1"
-    ],
-    "PublicationTimestamp": "2013-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "fulltext": "6999c3ca328011e2a2aa782bcb07413549c1bda35a744cecabaf17f115501fb1;2018-11-15T16:39:50Z;toolService;toolService:tool;UIMA/U-Compare STEPP Tagger;Part-of-speech tagger tuned to biomedical text.\n\nThe tool is provided as a UIMA component, which forms part of the in-built library of components provided with the U-Compare platform (see separate META-SHARE record)  for building and evaluating text mining workflows. The U-Compare Workbench (see separate META-SHARE record) provides a graphical drag-and drop interface for the rapid creation of workflows. \n;2013-02-15",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fe8b8345-2727-5dd1-9da5-08a854c2505c",
-    "notes": [
-        "Part-of-speech tagger tuned to biomedical text.\n\nThe tool is provided as a UIMA component, which forms part of the in-built library of components provided with the U-Compare platform (see separate META-SHARE record)  for building and evaluating text mining workflows. The U-Compare Workbench (see separate META-SHARE record) provides a graphical drag-and drop interface for the rapid creation of workflows. \n"
-    ],
-    "oai_identifier": [
-        "6999c3ca328011e2a2aa782bcb07413549c1bda35a744cecabaf17f115501fb1"
-    ],
-    "oai_set": [
-        "toolService",
-        "toolService:tool"
-    ],
-    "state": "active",
-    "title": [
-        "UIMA/U-Compare STEPP Tagger"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fe8bf454-30a3-53ae-a479-54ef75cc706f.json b/oaitestdata/clarin-oai_dc/SET_1/json/fe8bf454-30a3-53ae-a479-54ef75cc706f.json
deleted file mode 100644
index 4948e4b1..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fe8bf454-30a3-53ae-a479-54ef75cc706f.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "University of Stuttgart"
-    ],
-    "Contributor": [
-        "Uszkoreit, Prof. Dr. Hans"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1129",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1129"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1129",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "University of Stuttgart"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "SpatialCoverage": [
-        "Germany"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1129;2016-04-06T16:39:51Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;TIGER-Korpus;Uszkoreit, Prof. Dr. Hans;Germanistik;Treebank of German newspaper texts (taken from \"Frankfurter Rundschau\"); Grundlage: Zeitungstexte aus der \"Frankfurter Rundschau\";2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1129;deu;downloadable_files_count: 0;Germany;University of Stuttgart;http://www.ims.uni-stuttgart.de/forschung/ressourcen/korpora/tiger.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fe8bf454-30a3-53ae-a479-54ef75cc706f",
-    "notes": [
-        "Treebank of German newspaper texts (taken from \"Frankfurter Rundschau\"); Grundlage: Zeitungstexte aus der \"Frankfurter Rundschau\""
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1129"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Germanistik"
-        }
-    ],
-    "title": [
-        "TIGER-Korpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fe8ce38f-c21e-549b-9641-f2b4ee8a1209.json b/oaitestdata/clarin-oai_dc/SET_1/json/fe8ce38f-c21e-549b-9641-f2b4ee8a1209.json
deleted file mode 100644
index cb8ad278..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fe8ce38f-c21e-549b-9641-f2b4ee8a1209.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Oliver, S."
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "3 files : 1.4 MB",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:2476",
-    "MetadataAccess": [
-        "oai:ota:oucs:2476"
-    ],
-    "PublicationTimestamp": "1999-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1999"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Poems"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Oliver, Stephen, 1950-"
-    ],
-    "fulltext": "oai:ota:oucs:2476;2018-02-16T10:42:06Z;http://ota.ox.ac.uk/headers/2476.xml;Poetry Collections;Unmanned;Night of Warehouses : Poems 1978-2000;Deadly Pollen;Oliver, Stephen, 1950-;1999-2003;text_and_corpus_linguistics;Poetry;Australian poetry;New Zealand poetry--20th century;eng;Three poetry publications representing a resource for students and academics as reference texts; for the purpose of education and cultural diversity in the fields of literature and English poetics. ;Oxford Text Archive, University of Oxford;Oliver, S.;text/plain;3 files : 1.4 MB;Text;Poems;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fe8ce38f-c21e-549b-9641-f2b4ee8a1209",
-    "notes": [
-        "Three poetry publications representing a resource for students and academics as reference texts; for the purpose of education and cultural diversity in the fields of literature and English poetics. "
-    ],
-    "oai_identifier": [
-        "oai:ota:oucs:2476"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Poetry"
-        },
-        {
-            "name": "Australian poetry"
-        },
-        {
-            "name": "New Zealand poetry--th century"
-        }
-    ],
-    "title": [
-        "Poetry Collections",
-        "Unmanned",
-        "Night of Warehouses : Poems 1978-2000",
-        "Deadly Pollen"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/2476.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fea5fbdd-874b-52ba-8d1f-3f56f05cd475.json b/oaitestdata/clarin-oai_dc/SET_1/json/fea5fbdd-874b-52ba-8d1f-3f56f05cd475.json
deleted file mode 100644
index 1f741f02..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fea5fbdd-874b-52ba-8d1f-3f56f05cd475.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Zapolska"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 3",
-        "text/plain"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/95",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/95"
-    ],
-    "PID": "http://hdl.handle.net/11321/95",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Zapolska"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Zapolska, Zapolska"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/95;2015-04-08T13:38:48Z;hdl_11321_3;hdl_11321_4;MWE Zapolska;Zapolska, Zapolska;Zapolska;2015-04-08;corpus;http://hdl.handle.net/11321/95;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;text/plain; charset=utf-8;downloadable_files_count: 3;Zapolska",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fea5fbdd-874b-52ba-8d1f-3f56f05cd475",
-    "notes": [
-        "Zapolska"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/95"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Zapolska"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fef457c0-62a1-5a09-8983-e42a4630d025.json b/oaitestdata/clarin-oai_dc/SET_1/json/fef457c0-62a1-5a09-8983-e42a4630d025.json
deleted file mode 100644
index 9b0517e5..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fef457c0-62a1-5a09-8983-e42a4630d025.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3341",
-    "MetadataAccess": [
-        "oai:ota:oucs:3341"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Carey, George Saville, 1743-1807."
-    ],
-    "fulltext": "oai:ota:oucs:3341;2017-06-15T11:47:02Z;http://ota.ox.ac.uk/headers/3341.xml;The flights of fancy: being a collection of original pieces, in verse and prose, never before publish'd.;Carey, George Saville, 1743-1807.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fef457c0-62a1-5a09-8983-e42a4630d025",
-    "oai_identifier": [
-        "oai:ota:oucs:3341"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "The flights of fancy: being a collection of original pieces, in verse and prose, never before publish'd."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3341.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ff02b3a1-3bd4-5346-97d5-35953950ac0c.json b/oaitestdata/clarin-oai_dc/SET_1/json/ff02b3a1-3bd4-5346-97d5-35953950ac0c.json
deleted file mode 100644
index 650fa618..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ff02b3a1-3bd4-5346-97d5-35953950ac0c.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/302",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/302"
-    ],
-    "PID": "http://hdl.handle.net/11321/302",
-    "PublicationTimestamp": "2016-04-25T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)",
-        "http://creativecommons.org/licenses/by-sa/4.0/",
-        "CC"
-    ],
-    "author": [
-        "Marci\u0144czuk, Micha\u0142",
-        "Koco\u0144, Jan"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/302;2016-06-07T05:03:52Z;hdl_11321_3;hdl_11321_4;Liner2.5 model Timex;Koco\u0144, Jan;Marci\u0144czuk, Micha\u0142;information extraction;Timex;temporal expressions;A model for Liner2 to recognize and normalize temporal expressions.;2016-04-25;languageDescription;http://hdl.handle.net/11321/302;pol;Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0);http://creativecommons.org/licenses/by-sa/4.0/;CC;text/plain; charset=utf-8;application/octet-stream;downloadable_files_count: 1;Wroc\u0142aw University of Technology",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ff02b3a1-3bd4-5346-97d5-35953950ac0c",
-    "notes": [
-        "A model for Liner2 to recognize and normalize temporal expressions."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/302"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "information extraction"
-        },
-        {
-            "name": "Timex"
-        },
-        {
-            "name": "temporal expressions"
-        }
-    ],
-    "title": [
-        "Liner2.5 model Timex"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ff037a04-ef22-51c4-9834-0d1e8565fa7a.json b/oaitestdata/clarin-oai_dc/SET_1/json/ff037a04-ef22-51c4-9834-0d1e8565fa7a.json
deleted file mode 100644
index b3bcc04c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ff037a04-ef22-51c4-9834-0d1e8565fa7a.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Gombrich, Richard Francis"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(1 file : ca. 749 KB)",
-        "text/plain"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1304",
-    "MetadataAccess": [
-        "oai:ota:oucs:1304"
-    ],
-    "PublicationTimestamp": "1971-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1971"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Buddhism"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Gombrich, Richard Francis"
-    ],
-    "fulltext": "oai:ota:oucs:1304;2018-03-07T11:07:13Z;http://ota.ox.ac.uk/headers/1304.xml;Precept and practise : traditional Buddhism in the rural highlands of Ceylon / by Richard F. Gombrich;Gombrich, Richard Francis;1971;text_and_corpus_linguistics;Buddhism -- Sri Lanka;eng;Oxford Text Archive, University of Oxford;Gombrich, Richard Francis;text/plain;(1 file : ca. 749 KB);Text;Buddhism;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ff037a04-ef22-51c4-9834-0d1e8565fa7a",
-    "oai_identifier": [
-        "oai:ota:oucs:1304"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Buddhism -- Sri Lanka"
-        }
-    ],
-    "title": [
-        "Precept and practise : traditional Buddhism in the rural highlands of Ceylon / by Richard F. Gombrich"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1304.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ff0e843a-3190-53bf-a9fe-675c6711fc7c.json b/oaitestdata/clarin-oai_dc/SET_1/json/ff0e843a-3190-53bf-a9fe-675c6711fc7c.json
deleted file mode 100644
index 65babf1d..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ff0e843a-3190-53bf-a9fe-675c6711fc7c.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Jan Koco\u0144"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 1",
-        "application/zip"
-    ],
-    "Language": [],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/403",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/403"
-    ],
-    "PID": "http://hdl.handle.net/11321/403",
-    "PublicationTimestamp": "2017-06-28T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Jan Koco\u0144"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Koco\u0144, Jan"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/403;2017-06-28T09:14:07Z;hdl_11321_3;hdl_11321_4;CorpoGrabber;Koco\u0144, Jan;CorpoGrabber;corpus;acquiring;web scraping;corpora builder;CorpoGrabber: The Toolchain to Automatic Acquiring and Extraction of the Website Content\r\nJan Koco\u0144, Wroclaw University of Technology\r\n\r\nCorpoGrabber is a pipeline of tools to get the most relevant content of the website, including all subsites (up to the user-defined depth). The proposed toolchain can be used to build a big Web corpora of text documents. It requires only the list of the root websites as the input. Tools composing CorpoGrabber are adapted to Polish, but most subtasks are language independent. The whole process can be run in parallel on a single machine and includes the following tasks: downloading of the HTML subpages of each input page URL [1], extracting of plain text from each subpage by removing boilerplate content (such as navigation links, headers, footers, advertisements from HTML pages) [2], deduplication of plain text [2], removing of bad quality documents utilizing Morphological Analysis Converter and Aggregator (MACA) [3], tagging of documents using Wroc\u0142aw CRF Tagger (WCRFT) [4]. Last two steps are available only for Polish. The result is a corpora as a set of tagged documents for each website. \r\n\r\nReferences\r\n[1] https://www.httrack.com/html/faq.html\r\n[2] J. Pomikalek. 2011. Removing Boilerplate and Duplicate Content from Web Corpora. Ph.D. Thesis. Masaryk University, Faculcy of Informatics. Brno.\r\n[3] A. Radziszewski, T. Sniatowski. 2011. Maca \u2013 a configurable tool to integrate Polish morphological data. Proceedings of the Second International Workshop on Free/Open-Source Rule-Based Machine Translation. Barcelona, Spain.\r\n[4] A. Radziszewski. 2013. A tiered CRF tagger for Polish. Intelligent Tools for Building a Scientific Information Platform: Advanced Architectures and Solutions. Springer Verlag.;2017-06-28;toolService;http://hdl.handle.net/11321/403;N/A;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain; charset=utf-8;application/zip;downloadable_files_count: 1;Jan Koco\u0144",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ff0e843a-3190-53bf-a9fe-675c6711fc7c",
-    "notes": [
-        "CorpoGrabber: The Toolchain to Automatic Acquiring and Extraction of the Website Content\r\nJan Koco\u0144, Wroclaw University of Technology\r\n\r\nCorpoGrabber is a pipeline of tools to get the most relevant content of the website, including all subsites (up to the user-defined depth). The proposed toolchain can be used to build a big Web corpora of text documents. It requires only the list of the root websites as the input. Tools composing CorpoGrabber are adapted to Polish, but most subtasks are language independent. The whole process can be run in parallel on a single machine and includes the following tasks: downloading of the HTML subpages of each input page URL [1], extracting of plain text from each subpage by removing boilerplate content (such as navigation links, headers, footers, advertisements from HTML pages) [2], deduplication of plain text [2], removing of bad quality documents utilizing Morphological Analysis Converter and Aggregator (MACA) [3], tagging of documents using Wroc\u0142aw CRF Tagger (WCRFT) [4]. Last two steps are available only for Polish. The result is a corpora as a set of tagged documents for each website. \r\n\r\nReferences\r\n[1] https://www.httrack.com/html/faq.html\r\n[2] J. Pomikalek. 2011. Removing Boilerplate and Duplicate Content from Web Corpora. Ph.D. Thesis. Masaryk University, Faculcy of Informatics. Brno.\r\n[3] A. Radziszewski, T. Sniatowski. 2011. Maca \u2013 a configurable tool to integrate Polish morphological data. Proceedings of the Second International Workshop on Free/Open-Source Rule-Based Machine Translation. Barcelona, Spain.\r\n[4] A. Radziszewski. 2013. A tiered CRF tagger for Polish. Intelligent Tools for Building a Scientific Information Platform: Advanced Architectures and Solutions. Springer Verlag."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/403"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "CorpoGrabber"
-        },
-        {
-            "name": "corpus"
-        },
-        {
-            "name": "acquiring"
-        },
-        {
-            "name": "web scraping"
-        },
-        {
-            "name": "corpora builder"
-        }
-    ],
-    "title": [
-        "CorpoGrabber"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ff227238-5e68-5535-8819-f30418ba0adb.json b/oaitestdata/clarin-oai_dc/SET_1/json/ff227238-5e68-5535-8819-f30418ba0adb.json
deleted file mode 100644
index 6c7eee88..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ff227238-5e68-5535-8819-f30418ba0adb.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "Dmochowska"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 5",
-        "application/zip",
-        "text/plain",
-        "text/plain; charset=utf-8"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/71",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/71"
-    ],
-    "PID": "http://hdl.handle.net/11321/71",
-    "PublicationTimestamp": "2015-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Dmochowska"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU LGPL 3.0",
-        "http://www.gnu.org/licenses/lgpl.html",
-        "PUB"
-    ],
-    "author": [
-        "Dmochowska, Dmochowska"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/71;2015-04-14T19:36:39Z;hdl_11321_3;hdl_11321_4;MWE Dmochowska;Dmochowska, Dmochowska;Dmochowska;2015-04-08;corpus;http://hdl.handle.net/11321/71;pol;GNU LGPL 3.0;http://www.gnu.org/licenses/lgpl.html;PUB;text/plain;text/plain;text/plain;application/zip;application/zip;text/plain; charset=utf-8;downloadable_files_count: 5;Dmochowska",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ff227238-5e68-5535-8819-f30418ba0adb",
-    "notes": [
-        "Dmochowska"
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/71"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "MWE Dmochowska"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ff27c15d-1005-5b64-8e5e-daa2e87715ce.json b/oaitestdata/clarin-oai_dc/SET_1/json/ff27c15d-1005-5b64-8e5e-daa2e87715ce.json
deleted file mode 100644
index 15ad0aca..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ff27c15d-1005-5b64-8e5e-daa2e87715ce.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/gzip",
-        "downloadable_files_count: 4",
-        "text/plain; charset=utf-8",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "Croatian"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:www.clarin.si:11356/1205",
-    "MetadataAccess": [
-        "oai:www.clarin.si:11356/1205"
-    ],
-    "PID": "http://hdl.handle.net/11356/1205",
-    "PublicationTimestamp": "2018-12-10T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Jo\u017eef Stefan Institute"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution 4.0 International (CC BY 4.0)",
-        "https://creativecommons.org/licenses/by/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Ljube\u0161i\u0107, Nikola"
-    ],
-    "fulltext": "oai:www.clarin.si:11356/1205;2018-12-10T12:48:49Z;hdl_11356_1023;hdl_11356_1024;Word embeddings CLARIN.SI-embed.hr 1.0;Ljube\u0161i\u0107, Nikola;word embeddings;lemmatisation;tagging;CLARIN.SI-embed.hr contains word embeddings induced from a large collection of Croatian texts composed of the Croatian web corpus hrWaC and a 400-million-token-heavy collection of newspaper texts. The embeddings are based on the skip-gram model of fastText trained on 1,852,631,924 tokens of running text for (1) 1,742,837 lowercased surface forms (e.g., \"hrvatske\") and (2) 1,404,515 lowercased lemmas with added part-of-speech information (e.g., \"hrvatska#Np\").;2018-12-10;lexicalConceptualResource;http://hdl.handle.net/11356/1205;hrv;Creative Commons - Attribution 4.0 International (CC BY 4.0);https://creativecommons.org/licenses/by/4.0/;PUB;application/octet-stream;application/gzip;application/octet-stream;application/gzip;text/plain; charset=utf-8;downloadable_files_count: 4;Jo\u017eef Stefan Institute",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ff27c15d-1005-5b64-8e5e-daa2e87715ce",
-    "notes": [
-        "CLARIN.SI-embed.hr contains word embeddings induced from a large collection of Croatian texts composed of the Croatian web corpus hrWaC and a 400-million-token-heavy collection of newspaper texts. The embeddings are based on the skip-gram model of fastText trained on 1,852,631,924 tokens of running text for (1) 1,742,837 lowercased surface forms (e.g., \"hrvatske\") and (2) 1,404,515 lowercased lemmas with added part-of-speech information (e.g., \"hrvatska#Np\")."
-    ],
-    "oai_identifier": [
-        "oai:www.clarin.si:11356/1205"
-    ],
-    "oai_set": [
-        "hdl_11356_1023",
-        "hdl_11356_1024"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "word embeddings"
-        },
-        {
-            "name": "lemmatisation"
-        },
-        {
-            "name": "tagging"
-        }
-    ],
-    "title": [
-        "Word embeddings CLARIN.SI-embed.hr 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ff6a0b95-d43a-5f0b-b060-785bd22b8943.json b/oaitestdata/clarin-oai_dc/SET_1/json/ff6a0b95-d43a-5f0b-b060-785bd22b8943.json
deleted file mode 100644
index e9b9d83c..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ff6a0b95-d43a-5f0b-b060-785bd22b8943.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "Contributor": [
-        "O'Shannessy, Carmel"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1052",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1052"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1052",
-    "PublicationTimestamp": "2014-07-30T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Max Planck Institute for Psycholinguistics"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1052;2016-04-06T16:39:54Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;L1 Acquisition Carmel O'Shannessy;O'Shannessy, Carmel;Language Acquisition corpus;2014-07-30;corpus;http://hdl.handle.net/11372/LRT-1052;downloadable_files_count: 0;Max Planck Institute for Psycholinguistics;http://corpus1.mpi.nl/ds/imdi_browser?openpath=MPI337272%23",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ff6a0b95-d43a-5f0b-b060-785bd22b8943",
-    "notes": [
-        "Language Acquisition corpus"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1052"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "L1 Acquisition Carmel O'Shannessy"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ff93c820-91eb-577f-9d70-d1674d68ae00.json b/oaitestdata/clarin-oai_dc/SET_1/json/ff93c820-91eb-577f-9d70-d1674d68ae00.json
deleted file mode 100644
index f74b4e30..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ff93c820-91eb-577f-9d70-d1674d68ae00.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Instituut Fonetische Wetenschappen (IFA-groep) UvA"
-    ],
-    "Contributor": [
-        "Son, R.J.J.H. van"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-575",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-575"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-575",
-    "PublicationTimestamp": "2006-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2006"
-    ],
-    "Publisher": [
-        "Instituut Fonetische Wetenschappen (IFA-groep) UvA"
-    ],
-    "ResourceType": [
-        "corpus"
-    ],
-    "Rights": [
-        "GNU GPL"
-    ],
-    "SpatialCoverage": [
-        "Netherlands (the)"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-575;2016-04-06T16:39:52Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;IFA speech corpus;Son, R.J.J.H. van;Spoken corpus containing speech of 4 male and 4 female speakers. 50,000 words segmented at phoneme level;2006;corpus;http://hdl.handle.net/11372/LRT-575;nld;GNU GPL;downloadable_files_count: 0;Netherlands (the);Instituut Fonetische Wetenschappen (IFA-groep) UvA;http://www.fon.hum.uva.nl/Service/IFAcorpus/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ff93c820-91eb-577f-9d70-d1674d68ae00",
-    "notes": [
-        "Spoken corpus containing speech of 4 male and 4 female speakers. 50,000 words segmented at phoneme level"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-575"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "title": [
-        "IFA speech corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ffa41370-e249-5536-9141-bfad9fa68416.json b/oaitestdata/clarin-oai_dc/SET_1/json/ffa41370-e249-5536-9141-bfad9fa68416.json
deleted file mode 100644
index 63e3003e..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ffa41370-e249-5536-9141-bfad9fa68416.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "downloadable_files_count: 2",
-        "application/zip"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-68D9-0",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-68D9-0"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-097C-0000-0023-68D9-0",
-    "PublicationTimestamp": "2014-03-04T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)"
-    ],
-    "ResourceType": [
-        "languageDescription"
-    ],
-    "Rights": [
-        "Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)",
-        "http://creativecommons.org/licenses/by-nc-sa/3.0/",
-        "PUB"
-    ],
-    "author": [
-        "Straka, Milan",
-        "Strakov\u00e1, Jana"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-68D9-0;2018-07-02T22:05:53Z;hdl_11858_00-097C-0000-0001-486F-D;hdl_11858_00-097C-0000-0001-4877-A;English Models (Morphium + WSJ) for MorphoDiTa;Straka, Milan;Strakov\u00e1, Jana;MorphoDiTa;English;morphological analysis;morphological generation;PoS tagging;English models for MorphoDiTa, providing morphological analysis, morphological generation and part-of-speech tagging.\r\n\r\nThe morphological dictionary is created from Morphium and SCOWL (Spell Checker Oriented Word Lists), the PoS tagger is trained on WSJ (Wall Street Journal).;2014-03-04;languageDescription;http://hdl.handle.net/11858/00-097C-0000-0023-68D9-0;eng;Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0);http://creativecommons.org/licenses/by-nc-sa/3.0/;PUB;text/plain; charset=utf-8;application/zip;application/zip;downloadable_files_count: 2;Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL);http://ufal.mff.cuni.cz/morphodita/users-manual#english-morphium-wsj",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ffa41370-e249-5536-9141-bfad9fa68416",
-    "notes": [
-        "English models for MorphoDiTa, providing morphological analysis, morphological generation and part-of-speech tagging.\r\n\r\nThe morphological dictionary is created from Morphium and SCOWL (Spell Checker Oriented Word Lists), the PoS tagger is trained on WSJ (Wall Street Journal)."
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11858/00-097C-0000-0023-68D9-0"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0001-486F-D",
-        "hdl_11858_00-097C-0000-0001-4877-A"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "MorphoDiTa"
-        },
-        {
-            "name": "English"
-        },
-        {
-            "name": "morphological analysis"
-        },
-        {
-            "name": "morphological generation"
-        },
-        {
-            "name": "PoS tagging"
-        }
-    ],
-    "title": [
-        "English Models (Morphium + WSJ) for MorphoDiTa"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ffaad600-aaac-5836-bbb7-23eb7c11140e.json b/oaitestdata/clarin-oai_dc/SET_1/json/ffaad600-aaac-5836-bbb7-23eb7c11140e.json
deleted file mode 100644
index 1c0cda0b..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ffaad600-aaac-5836-bbb7-23eb7c11140e.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "Micha\u0142 Gr\u00f6ll"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "application/xml"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-165853",
-    "MetadataAccess": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-165853"
-    ],
-    "PID": "http://hdl.handle.net/11858/00-246C-0000-0023-8CEE-F",
-    "PublicationTimestamp": "1789-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1789"
-    ],
-    "Publisher": [
-        "Micha\u0142 Gr\u00f6ll"
-    ],
-    "RelatedIdentifier": [
-        "http://jbc.bj.uj.edu.pl/Content/165853",
-        "oai:jbc.bj.uj.edu.pl:publication:174261"
-    ],
-    "ResourceType": [
-        "starodruk"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-sa/4.0/",
-        "CC-BY-NC-SA-4.0"
-    ],
-    "SpatialCoverage": [
-        "1701/1800"
-    ],
-    "TempCoverageBegin": 53662478399,
-    "TempCoverageEnd": 53662478399,
-    "TemporalCoverage": " point in time : 1701-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1701-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1701-07-01T11:59:59Z",
-    "author": [
-        "Jezierski, Franciszek Salezy (1740-1791)"
-    ],
-    "fulltext": "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-165853;2019-03-01T10:53:40Z;Gow\u00f3rek herbu Rawicz woiewoda sandomierski : Powie\u015b\u0107 z widoku we \u015bnie;Jezierski, Franciszek Salezy (1740-1791);starodruki 18\u00a0w.;Micha\u0142 Gr\u00f6ll;1789;starodruk;application/xml;clarind-uds:poldilemma-165853;hdl:11858/00-246C-0000-0023-8CEE-F;Biblioteka Jagiello\u0144ska, BJ St. Dr. 56637 I;pol;http://jbc.bj.uj.edu.pl/Content/165853;oai:jbc.bj.uj.edu.pl:publication:174261;1701/1800;https://creativecommons.org/licenses/by-nc-sa/4.0/;CC-BY-NC-SA-4.0",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ffaad600-aaac-5836-bbb7-23eb7c11140e",
-    "oai_identifier": [
-        "oai:fedora.clarin-d.uni-saarland.de:clarind-uds:poldilemma-165853"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Gow\u00f3rek herbu Rawicz woiewoda sandomierski : Powie\u015b\u0107 z widoku we \u015bnie"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ffad133a-f9fe-57c3-8701-f2c8994ba8b8.json b/oaitestdata/clarin-oai_dc/SET_1/json/ffad133a-f9fe-57c3-8701-f2c8994ba8b8.json
deleted file mode 100644
index 9c6ea682..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ffad133a-f9fe-57c3-8701-f2c8994ba8b8.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:3992",
-    "MetadataAccess": [
-        "oai:ota:oucs:3992"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Holcroft, Thomas, 1745-1809."
-    ],
-    "fulltext": "oai:ota:oucs:3992;2017-06-15T11:47:03Z;http://ota.ox.ac.uk/headers/3992.xml;He's much to blame: a comedy: in five acts. As performed at the Theatre Royal, Covent Garden.;Holcroft, Thomas, 1745-1809.;text_and_corpus_linguistics;eng;Oxford Text Archive, University of Oxford;Text;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ffad133a-f9fe-57c3-8701-f2c8994ba8b8",
-    "oai_identifier": [
-        "oai:ota:oucs:3992"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        }
-    ],
-    "title": [
-        "He's much to blame: a comedy: in five acts. As performed at the Theatre Royal, Covent Garden."
-    ],
-    "url": "http://ota.ox.ac.uk/headers/3992.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ffda680a-d99c-545f-ae56-aee52c844d93.json b/oaitestdata/clarin-oai_dc/SET_1/json/ffda680a-d99c-545f-ae56-aee52c844d93.json
deleted file mode 100644
index dd16a966..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ffda680a-d99c-545f-ae56-aee52c844d93.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "Contributor": [
-        "Smith, Mary Regina"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/sgml",
-        "(1 file : ca. 233 KB)"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:1628",
-    "MetadataAccess": [
-        "oai:ota:oucs:1628"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text",
-        "Plays"
-    ],
-    "Rights": [
-        "Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Marlowe, Christopher, 1564-1593"
-    ],
-    "fulltext": "oai:ota:oucs:1628;2018-02-16T10:42:05Z;http://ota.ox.ac.uk/headers/1628.xml;Tamburlaine the Great : Parts one and two / Christopher Marlowe;Marlowe, Christopher, 1564-1593;text_and_corpus_linguistics;English drama -- Early modern and Elizabethan, 1500-1600;Oxford Text Archive, University of Oxford;Smith, Mary Regina;text/sgml;(1 file : ca. 233 KB);Text;Plays;Use of this resource is restricted in some manner. Usually this means that it is available for non-commercial use only with prior permission of the depositor and on condition that this header is included in its entirety with any copy distributed.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ffda680a-d99c-545f-ae56-aee52c844d93",
-    "oai_identifier": [
-        "oai:ota:oucs:1628"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "English drama -- Early modern Elizabethan"
-        }
-    ],
-    "title": [
-        "Tamburlaine the Great : Parts one and two / Christopher Marlowe"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/1628.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/ffdcc685-aacd-5920-900e-9ad692f48ed1.json b/oaitestdata/clarin-oai_dc/SET_1/json/ffdcc685-aacd-5920-900e-9ad692f48ed1.json
deleted file mode 100644
index a5956be9..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/ffdcc685-aacd-5920-900e-9ad692f48ed1.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=d6786e9a191511e6a2aa782bcb07413522f6924729e44b1aa307157a31a13ff9",
-    "MetadataAccess": [
-        "d6786e9a191511e6a2aa782bcb07413522f6924729e44b1aa307157a31a13ff9"
-    ],
-    "PublicationTimestamp": "2016-05-13T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "fulltext": "d6786e9a191511e6a2aa782bcb07413522f6924729e44b1aa307157a31a13ff9;2018-11-15T16:40:22Z;lexicalConceptualResource;lexicalConceptualResource:lexicon;QTLeap Specialized lexicons;This resource comprises multilingual lexicon entries used for the translation of specific IT domain expressions. This gazetteer has been collected from four different sources: VLC,\n LibreOffice and KDE localization projects and IT domain Wikipedia articles.;2016-05-13",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ffdcc685-aacd-5920-900e-9ad692f48ed1",
-    "notes": [
-        "This resource comprises multilingual lexicon entries used for the translation of specific IT domain expressions. This gazetteer has been collected from four different sources: VLC,\n LibreOffice and KDE localization projects and IT domain Wikipedia articles."
-    ],
-    "oai_identifier": [
-        "d6786e9a191511e6a2aa782bcb07413522f6924729e44b1aa307157a31a13ff9"
-    ],
-    "oai_set": [
-        "lexicalConceptualResource",
-        "lexicalConceptualResource:lexicon"
-    ],
-    "state": "active",
-    "title": [
-        "QTLeap Specialized lexicons"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fff2c7f1-6178-560e-be36-bd97ed5520fd.json b/oaitestdata/clarin-oai_dc/SET_1/json/fff2c7f1-6178-560e-be36-bd97ed5520fd.json
deleted file mode 100644
index ebcd562a..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fff2c7f1-6178-560e-be36-bd97ed5520fd.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "downloadable_files_count: 0"
-    ],
-    "Language": [
-        "Polish"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:clarin-pl.eu:11321/30",
-    "MetadataAccess": [
-        "oai:clarin-pl.eu:11321/30"
-    ],
-    "PID": "http://hdl.handle.net/11321/30",
-    "PublicationTimestamp": "2010-08-09T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "Wroc\u0142aw University of Technology"
-    ],
-    "ResourceType": [
-        "toolService"
-    ],
-    "author": [
-        "Zawadzki, Maciej"
-    ],
-    "fulltext": "oai:clarin-pl.eu:11321/30;2016-01-19T13:52:47Z;hdl_11321_3;hdl_11321_4;Tagger WS;Zawadzki, Maciej;Tagger-WS is a web service that reads Polish text and outputs sentences divided into tokens where each token is labelled with a morphosyntactic tag and a lemma. The tagger uses NKJP tagset and Morfeusz SGJP analyser. The service is based on WCRFT.;2010-08-09;toolService;http://hdl.handle.net/11321/30;pol;downloadable_files_count: 0;Wroc\u0142aw University of Technology;http://clarin-pl.eu/synat/ws/tagger/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fff2c7f1-6178-560e-be36-bd97ed5520fd",
-    "notes": [
-        "Tagger-WS is a web service that reads Polish text and outputs sentences divided into tokens where each token is labelled with a morphosyntactic tag and a lemma. The tagger uses NKJP tagset and Morfeusz SGJP analyser. The service is based on WCRFT."
-    ],
-    "oai_identifier": [
-        "oai:clarin-pl.eu:11321/30"
-    ],
-    "oai_set": [
-        "hdl_11321_3",
-        "hdl_11321_4"
-    ],
-    "state": "active",
-    "title": [
-        "Tagger WS"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fff52f2e-bfeb-55e2-a72b-5c8afba39b43.json b/oaitestdata/clarin-oai_dc/SET_1/json/fff52f2e-bfeb-55e2-a72b-5c8afba39b43.json
deleted file mode 100644
index ae801a4f..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fff52f2e-bfeb-55e2-a72b-5c8afba39b43.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "(17 files : 3.8 MB)"
-    ],
-    "Language": [
-        "Latin"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:ota:oucs:0327",
-    "MetadataAccess": [
-        "oai:ota:oucs:0327"
-    ],
-    "PublicationYear": [
-        "81 BCE-43 BCE"
-    ],
-    "Publisher": [
-        "Oxford Text Archive, University of Oxford"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.",
-        "http://www.ota.ox.ac.uk/documents/user_agreement.xml"
-    ],
-    "author": [
-        "Cicero, Marcus Tullius"
-    ],
-    "fulltext": "oai:ota:oucs:0327;2018-07-27T14:11:31Z;http://ota.ox.ac.uk/headers/0327.xml;Major works;Cicero, Marcus Tullius;81 BCE-43 BCE;text_and_corpus_linguistics;Letters -- Italy -- B.C.;Addresses -- Italy -- B.C.;lat;Oxford Text Archive, University of Oxford;(17 files : 3.8 MB);Text;Distributed by the University of Oxford under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.;http://www.ota.ox.ac.uk/documents/user_agreement.xml",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fff52f2e-bfeb-55e2-a72b-5c8afba39b43",
-    "oai_identifier": [
-        "oai:ota:oucs:0327"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "text_and_corpus_linguistics"
-        },
-        {
-            "name": "Letters -- Italy -- B.C."
-        },
-        {
-            "name": "Addresses -- Italy -- B.C."
-        }
-    ],
-    "title": [
-        "Major works"
-    ],
-    "url": "http://ota.ox.ac.uk/headers/0327.xml"
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/SET_1/json/fffb353b-19f7-5a5d-a227-9db30461e49a.json b/oaitestdata/clarin-oai_dc/SET_1/json/fffb353b-19f7-5a5d-a227-9db30461e49a.json
deleted file mode 100644
index 6f583747..00000000
--- a/oaitestdata/clarin-oai_dc/SET_1/json/fffb353b-19f7-5a5d-a227-9db30461e49a.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Ibtikarat team"
-    ],
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "Format": [
-        "text/plain; charset=utf-8",
-        "text/xml",
-        "downloadable_files_count: 1"
-    ],
-    "Language": [
-        "Arabic"
-    ],
-    "MetaDataAccess": "https://clarin-pl.eu/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11372/LRT-1945",
-    "MetadataAccess": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1945"
-    ],
-    "PID": "http://hdl.handle.net/11372/LRT-1945",
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Ibtikarat team"
-    ],
-    "ResourceType": [
-        "lexicalConceptualResource"
-    ],
-    "Rights": [
-        "Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)",
-        "http://creativecommons.org/licenses/by-nc/4.0/",
-        "PUB"
-    ],
-    "author": [
-        "Namly, Driss"
-    ],
-    "fulltext": "oai:lindat.mff.cuni.cz:11372/LRT-1945;2017-02-06T11:05:33Z;hdl_11858_00-097C-0000-0007-710A-A;hdl_11858_00-097C-0000-0007-710B-8;Arabic characters lexicon;Namly, Driss;alphabets;A XML-based file containing all Arabic characters (letters, vowels and punctuations). Each character described with a description, different displays (isolated, at the beginning, middle and the end of a word), a codification (Unicode, others could be added later), and two transliterations (Buckwalter and wiki);2014;lexicalConceptualResource;http://hdl.handle.net/11372/LRT-1945;ara;Creative Commons - Attribution-NonCommercial 4.0 International (CC BY-NC 4.0);http://creativecommons.org/licenses/by-nc/4.0/;PUB;text/xml;text/plain; charset=utf-8;downloadable_files_count: 1;Ibtikarat team;http://arabic.emi.ac.ma/ibtikarat/?q=Resources",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fffb353b-19f7-5a5d-a227-9db30461e49a",
-    "notes": [
-        "A XML-based file containing all Arabic characters (letters, vowels and punctuations). Each character described with a description, different displays (isolated, at the beginning, middle and the end of a word), a codification (Unicode, others could be added later), and two transliterations (Buckwalter and wiki)"
-    ],
-    "oai_identifier": [
-        "oai:lindat.mff.cuni.cz:11372/LRT-1945"
-    ],
-    "oai_set": [
-        "hdl_11858_00-097C-0000-0007-710A-A",
-        "hdl_11858_00-097C-0000-0007-710B-8"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "alphabets"
-        }
-    ],
-    "title": [
-        "Arabic characters lexicon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/00abd129-9675-547c-a4ab-19cd29ef998a.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/00abd129-9675-547c-a4ab-19cd29ef998a.json
deleted file mode 100644
index cb835937..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/00abd129-9675-547c-a4ab-19cd29ef998a.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06347L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10304239",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10304239"
-    ],
-    "PublicationTimestamp": "2017-01-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Nurk, T\u00f5nis"
-    ],
-    "fulltext": "oai:oai.datacite.org:10304239;2018-10-24T00:10:09Z;ESTDOI;ESTDOI.KEEL;Terminibaaside s\u00fcsteem Termeki ;Nurk, T\u00f5nis;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2017-01-31;doi:10.15155/3-00-0000-0000-0000-06347L;Abstract;Eesti Keele Instituudi tasuta pakutav tarkvara terminoloogia haldamiseks.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "00abd129-9675-547c-a4ab-19cd29ef998a",
-    "notes": [
-        "Abstract",
-        "Eesti Keele Instituudi tasuta pakutav tarkvara terminoloogia haldamiseks."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10304239"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Terminibaaside s\u00fcsteem Termeki "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/00ac88c0-028e-596d-a60d-249291001f35.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/00ac88c0-028e-596d-a60d-249291001f35.json
deleted file mode 100644
index 89377400..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/00ac88c0-028e-596d-a60d-249291001f35.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-07023L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14432584",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14432584"
-    ],
-    "PublicationTimestamp": "2018-03-14T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Soon, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:14432584;2018-03-14T11:35:20Z;ESTDOI;ESTDOI.KEEL;Militerm v20180801;Militerm v20180801;Soon, Tiina;Center of Estonian Language Resources;2018;Issued: 2018-03-14;Updated: 2018-03-14;doi:10.15155/3-00-0000-0000-0000-07023L;Abstract;Militerm on s\u00f5janduse, julgeoleku- ja kaitsepoliitika terminite andmebaas, kus saab m\u00e4rks\u00f5nu otsida eesti, inglise, prantsuse ja saksa keeles. Eesti- ja ingliskeelsete terminite juures on ka oskuss\u00f5nade definitsioonid.;Abstract;MILITERM is a multilingual termbase of military, security and defense terms, enabling search by Estonian, English, French and German keywords. The Estonian and English terms are provided with definitions.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "00ac88c0-028e-596d-a60d-249291001f35",
-    "notes": [
-        "Abstract",
-        "Militerm on s\u00f5janduse, julgeoleku- ja kaitsepoliitika terminite andmebaas, kus saab m\u00e4rks\u00f5nu otsida eesti, inglise, prantsuse ja saksa keeles. Eesti- ja ingliskeelsete terminite juures on ka oskuss\u00f5nade definitsioonid.",
-        "Abstract",
-        "MILITERM is a multilingual termbase of military, security and defense terms, enabling search by Estonian, English, French and German keywords. The Estonian and English terms are provided with definitions."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14432584"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Militerm v20180801",
-        "Militerm v20180801"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/00ba1770-f044-5ac6-8518-09db0d98b696.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/00ba1770-f044-5ac6-8518-09db0d98b696.json
deleted file mode 100644
index abf4212a..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/00ba1770-f044-5ac6-8518-09db0d98b696.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05AF4L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9310575",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9310575"
-    ],
-    "PublicationTimestamp": "2016-10-19T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Paet, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:9310575;2019-02-02T13:01:42Z;ESTDOI;ESTDOI.KEEL;Ametniku soovituss\u00f5nastik;Paet, Tiina;Center of Estonian Language Resources;2016;Issued: 2016-10-19;Updated: 2016-10-19;doi:10.15155/3-00-0000-0000-0000-05AF4L;Abstract;S\u00f5nastik k\u00f5igile neile, kellel on vaja kirjutada ametliku sisuga kirjakeelset teksti. S\u00f5nastik pakub n\u00f5uandeid ja soovitusi, kuidas v\u00e4ljenduda lihtsamalt, selgemalt ja t\u00e4psemalt.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "00ba1770-f044-5ac6-8518-09db0d98b696",
-    "notes": [
-        "Abstract",
-        "S\u00f5nastik k\u00f5igile neile, kellel on vaja kirjutada ametliku sisuga kirjakeelset teksti. S\u00f5nastik pakub n\u00f5uandeid ja soovitusi, kuidas v\u00e4ljenduda lihtsamalt, selgemalt ja t\u00e4psemalt."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9310575"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Ametniku soovituss\u00f5nastik"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/01781bc4-fad7-579d-9269-ca452394dbef.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/01781bc4-fad7-579d-9269-ca452394dbef.json
deleted file mode 100644
index 240dc7bf..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/01781bc4-fad7-579d-9269-ca452394dbef.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-0006DL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:6895481",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:6895481"
-    ],
-    "PublicationTimestamp": "2015-08-25T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Meister, Einar"
-    ],
-    "fulltext": "oai:oai.datacite.org:6895481;2019-04-06T06:33:13Z;ESTDOI;ESTDOI.KEEL;Corpus of Adolescent Speech;Meister, Einar;Center of Estonian Language Resources;2015;Issued: 2015-08-25;Updated: 2015-08-25;doi:10.15155/9-00-0000-0000-0000-0006DL;Abstract;Includes speech recordings of 300 native Estonian subjects in the age range from 9 to 18 years",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "01781bc4-fad7-579d-9269-ca452394dbef",
-    "notes": [
-        "Abstract",
-        "Includes speech recordings of 300 native Estonian subjects in the age range from 9 to 18 years"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:6895481"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus of Adolescent Speech"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/01be521d-6fe4-5e58-9e75-3babcb033c71.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/01be521d-6fe4-5e58-9e75-3babcb033c71.json
deleted file mode 100644
index 702f95a7..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/01be521d-6fe4-5e58-9e75-3babcb033c71.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0013AL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:12052516",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:12052516"
-    ],
-    "PublicationTimestamp": "2017-09-13T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Vare, Kadri",
-        "Orav, Heili"
-    ],
-    "fulltext": "oai:oai.datacite.org:12052516;2018-12-25T18:36:58Z;ESTDOI;ESTDOI.KEEL;Eesti Wordnet (2.1);Estonian Wordnet (2.1);Orav, Heili;Vare, Kadri;Center of Estonian Language Resources;2014;Issued: 2014-03-21;Updated: 2017-09-13;doi:10.15155/1-00-0000-0000-0000-0013AL;Abstract;XML versioon Eesti Wordnetist.;Abstract;EstWN in XML format.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "01be521d-6fe4-5e58-9e75-3babcb033c71",
-    "notes": [
-        "Abstract",
-        "XML versioon Eesti Wordnetist.",
-        "Abstract",
-        "EstWN in XML format."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:12052516"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti Wordnet (2.1)",
-        "Estonian Wordnet (2.1)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/02f997a8-86d9-5e6a-9a0d-9fde9b71a680.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/02f997a8-86d9-5e6a-9a0d-9fde9b71a680.json
deleted file mode 100644
index 507d7b3c..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/02f997a8-86d9-5e6a-9a0d-9fde9b71a680.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06BA1L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:13359316",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:13359316"
-    ],
-    "PublicationTimestamp": "2017-11-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek",
-        "Langemets, Margit"
-    ],
-    "fulltext": "oai:oai.datacite.org:13359316;2019-04-05T07:30:59Z;ESTDOI;ESTDOI.KEEL;Soome-eesti s\u00f5naraamat / Suomi\u2013viro-suursanakirja;Finnish-Estonian dictionary;Hein, Indrek;Langemets, Margit;Center of Estonian Language Resources;2017;Issued: 2017-11-30;Updated: 2017-11-30;doi:10.15155/3-00-0000-0000-0000-06BA1L;Abstract;Kahek\u00f6itelise soome-eesti suurs\u00f5naraamatu (2003) veebiversioon. Sisaldab \u00fcle 90 000 m\u00e4rks\u00f5na. S\u00f5naraamatus on rohkelt n\u00e4iteid koos t\u00f5lgetega (nii eritermineid kui ka k\u00f5nekeele v\u00e4ljendeid), lisaks valik kohanimesid. P\u00e4ringuid on v\u00f5imalik teha soome ja eesti keeles.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "02f997a8-86d9-5e6a-9a0d-9fde9b71a680",
-    "notes": [
-        "Abstract",
-        "Kahek\u00f6itelise soome-eesti suurs\u00f5naraamatu (2003) veebiversioon. Sisaldab \u00fcle 90 000 m\u00e4rks\u00f5na. S\u00f5naraamatus on rohkelt n\u00e4iteid koos t\u00f5lgetega (nii eritermineid kui ka k\u00f5nekeele v\u00e4ljendeid), lisaks valik kohanimesid. P\u00e4ringuid on v\u00f5imalik teha soome ja eesti keeles."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:13359316"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Soome-eesti s\u00f5naraamat / Suomi\u2013viro-suursanakirja",
-        "Finnish-Estonian dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/03405299-a850-59a8-b995-67b448b5cf9a.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/03405299-a850-59a8-b995-67b448b5cf9a.json
deleted file mode 100644
index 45d96869..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/03405299-a850-59a8-b995-67b448b5cf9a.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06338L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10303970",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10303970"
-    ],
-    "PublicationTimestamp": "2017-06-21T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laansalu, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:10303970;2019-04-12T21:32:38Z;ESTDOI;ESTDOI.KEEL;Eesti murrete s\u00f5naraamat (2013\u2013...; l\u00f5petis\u2013nisu); The Dictionary of Estonian Dialects (2013\u2013...; l\u00f5petis\u2013nisu);Laansalu, Tiina;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2017-06-21;doi:10.15155/3-00-0000-0000-0000-06338L;Abstract;Eesti murrete s\u00f5naraamat haarab v\u00f5imalikult kogu murdes\u00f5navara. S\u00f5nu saadab h\u00e4\u00e4likuline ja grammatiline iseloomustus, levik ning selgub s\u00f5nade t\u00e4hendus. N\u00e4itelaused toovad esile murdes\u00f5nadega seotud t\u00e4henduslikke ja grammatilisi n\u00e4htusi.;Abstract;The aim of this dictionary is to possibly cover the whole vocabulary of Estonian dialects. The entry words are accompanied by phonetic and grammatical data, their area of distribution, and meaning. Sentence examples demonstrate additional grammatical and semantic specifics of the words.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "03405299-a850-59a8-b995-67b448b5cf9a",
-    "notes": [
-        "Abstract",
-        "Eesti murrete s\u00f5naraamat haarab v\u00f5imalikult kogu murdes\u00f5navara. S\u00f5nu saadab h\u00e4\u00e4likuline ja grammatiline iseloomustus, levik ning selgub s\u00f5nade t\u00e4hendus. N\u00e4itelaused toovad esile murdes\u00f5nadega seotud t\u00e4henduslikke ja grammatilisi n\u00e4htusi.",
-        "Abstract",
-        "The aim of this dictionary is to possibly cover the whole vocabulary of Estonian dialects. The entry words are accompanied by phonetic and grammatical data, their area of distribution, and meaning. Sentence examples demonstrate additional grammatical and semantic specifics of the words."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10303970"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti murrete s\u00f5naraamat (2013\u2013...; l\u00f5petis\u2013nisu)",
-        " The Dictionary of Estonian Dialects (2013\u2013...; l\u00f5petis\u2013nisu)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/03cd539c-f718-5521-b17d-141ec6d60915.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/03cd539c-f718-5521-b17d-141ec6d60915.json
deleted file mode 100644
index 071ab2fd..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/03cd539c-f718-5521-b17d-141ec6d60915.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05B4CL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9352870",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9352870"
-    ],
-    "PublicationTimestamp": "2016-10-31T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Leemets, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:9352870;2019-03-29T21:02:55Z;ESTDOI;ESTDOI.KEEL;Eesti-vene \u00f5pilase \u00d5S;Leemets, Tiina;Center of Estonian Language Resources;2016;Issued: 2016-10-31;Updated: 2016-10-31;doi:10.15155/3-00-0000-0000-0000-05B4CL;Abstract;Eesti-vene \u00f5pilase \u00d5S on m\u00f5eldud eelk\u00f5ige vene emakeelega v\u00f5i vene keele p\u00f5hjal eesti keele \u00f5ppijale. S\u00f5nu saab otsida nii eesti kui ka vene keele kaudu.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "03cd539c-f718-5521-b17d-141ec6d60915",
-    "notes": [
-        "Abstract",
-        "Eesti-vene \u00f5pilase \u00d5S on m\u00f5eldud eelk\u00f5ige vene emakeelega v\u00f5i vene keele p\u00f5hjal eesti keele \u00f5ppijale. S\u00f5nu saab otsida nii eesti kui ka vene keele kaudu."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9352870"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti-vene \u00f5pilase \u00d5S"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0425c334-e5d5-5d80-9260-d96b669ef855.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0425c334-e5d5-5d80-9260-d96b669ef855.json
deleted file mode 100644
index be14faf9..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0425c334-e5d5-5d80-9260-d96b669ef855.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06334L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10303931",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10303931"
-    ],
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Mihkla, Meelis"
-    ],
-    "fulltext": "oai:oai.datacite.org:10303931;2019-04-17T17:26:41Z;ESTDOI;ESTDOI.KEEL;Tekstide helindaja ja heliraamatute genereerija;Audio Interface for Texts and Ebook Generator;Mihkla, Meelis;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2019-01-08;doi:10.15155/3-00-0000-0000-0000-06334L;Abstract;Teisendab txt- ja html-formaadis tekstid helifailideks ja lisab ePub3 formaadis e-raamatule s\u00fcnteesk\u00f5nes kuulatavad audiofailid. Helindaja ja genereerija Vox Populi koosneb kahest komponendist \u2013 tekstide helindajast ja h\u00e4\u00e4lduss\u00f5nastikust. Nende kahe koost\u00f6\u00f6s ja Eest Keele Instituudi k\u00f5nes\u00fcnteesi kaasates saab kasutaja saadetud tekstifailist s\u00fcnteesh\u00e4\u00e4lega audiofail.\n\n\n;Abstract;Converts texts in txt or html format to audio files and provides ebooks in ePub3 format with audio files to be listened to in synthetic speech. The audio interface and ebook generator Vox Populi consists of two components \u2013 an audio interface for texts and a pronunciation glossary. A joint application of those two and the system of speech synthesis of the Institute of the Estonian Language will convert a user\u00b4s text file into a synthetic audio file.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0425c334-e5d5-5d80-9260-d96b669ef855",
-    "notes": [
-        "Abstract",
-        "Teisendab txt- ja html-formaadis tekstid helifailideks ja lisab ePub3 formaadis e-raamatule s\u00fcnteesk\u00f5nes kuulatavad audiofailid. Helindaja ja genereerija Vox Populi koosneb kahest komponendist \u2013 tekstide helindajast ja h\u00e4\u00e4lduss\u00f5nastikust. Nende kahe koost\u00f6\u00f6s ja Eest Keele Instituudi k\u00f5nes\u00fcnteesi kaasates saab kasutaja saadetud tekstifailist s\u00fcnteesh\u00e4\u00e4lega audiofail.\n\n\n",
-        "Abstract",
-        "Converts texts in txt or html format to audio files and provides ebooks in ePub3 format with audio files to be listened to in synthetic speech. The audio interface and ebook generator Vox Populi consists of two components \u2013 an audio interface for texts and a pronunciation glossary. A joint application of those two and the system of speech synthesis of the Institute of the Estonian Language will convert a user\u00b4s text file into a synthetic audio file."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10303931"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Tekstide helindaja ja heliraamatute genereerija",
-        "Audio Interface for Texts and Ebook Generator"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/042d0316-3c42-5662-bfc8-7fd102e0b43c.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/042d0316-3c42-5662-bfc8-7fd102e0b43c.json
deleted file mode 100644
index 038e5c25..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/042d0316-3c42-5662-bfc8-7fd102e0b43c.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-001A1L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:18199542",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:18199542"
-    ],
-    "PublicationTimestamp": "2013-01-07T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:18199542;2019-03-17T18:37:25Z;ESTDOI;ESTDOI.KEEL;Corpus of Estonian law texts D;Muischnek, Kadri;Center of Estonian Language Resources;2013;Issued: 2013-01-07;Updated: 2013-01-07;doi:10.15155/1-00-0000-0000-0000-001A1L;Abstract;Corpus of law texts in Estonian, contains Estonian legislation and European legislation in Estonian. 11 million words. \nMarkup: TEI P5 XML\nEncoding: UTF8",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "042d0316-3c42-5662-bfc8-7fd102e0b43c",
-    "notes": [
-        "Abstract",
-        "Corpus of law texts in Estonian, contains Estonian legislation and European legislation in Estonian. 11 million words. \nMarkup: TEI P5 XML\nEncoding: UTF8"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:18199542"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus of Estonian law texts D"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/047d9dd2-f4ac-5675-970e-fb780864f3f8.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/047d9dd2-f4ac-5675-970e-fb780864f3f8.json
deleted file mode 100644
index 9ee8ffa2..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/047d9dd2-f4ac-5675-970e-fb780864f3f8.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-079D0L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17841061",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17841061"
-    ],
-    "PublicationTimestamp": "2018-12-18T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Paet, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:17841061;2019-04-23T09:01:12Z;ESTDOI;ESTDOI.KEEL;\u00d5S 1918. \u201eEesti keele \u00f5igekirjutuse-s\u00f5naraamatu\u201c kommenteeritud v\u00e4ljaanne (veebiversioon);\u201eThe Spelling Dictionary of Estonian 1918\u201c. Commented online dictionary;Paet, Tiina;Center of Estonian Language Resources;2018;Issued: 2018-12-18;Updated: 2018-12-18;doi:10.15155/3-00-0000-0000-0000-079D0L;Abstract;S\u00f5nastik v\u00f5imaldab linkide kaudu v\u00f5rrelda 1918. aasta \u201eEesti keele \u00f5igekirjutuse-s\u00f5naraamatu\u201c m\u00e4rks\u00f5nastikku \u201eEesti \u00f5igekeelsuss\u00f5naraamat \u00d5S 2018\u201c m\u00e4rks\u00f5nastikuga ja n\u00e4ha, kuidas eesti kirjakeele norm on saja aastaga muutunud.;Abstract;There are links enabling one to compare the entry list of the 1918 dictionary with that of the Standard Estonian Dictionary published in 2018, which reveals how the standard has changed over the century.\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "047d9dd2-f4ac-5675-970e-fb780864f3f8",
-    "notes": [
-        "Abstract",
-        "S\u00f5nastik v\u00f5imaldab linkide kaudu v\u00f5rrelda 1918. aasta \u201eEesti keele \u00f5igekirjutuse-s\u00f5naraamatu\u201c m\u00e4rks\u00f5nastikku \u201eEesti \u00f5igekeelsuss\u00f5naraamat \u00d5S 2018\u201c m\u00e4rks\u00f5nastikuga ja n\u00e4ha, kuidas eesti kirjakeele norm on saja aastaga muutunud.",
-        "Abstract",
-        "There are links enabling one to compare the entry list of the 1918 dictionary with that of the Standard Estonian Dictionary published in 2018, which reveals how the standard has changed over the century.\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17841061"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "\u00d5S 1918. \u201eEesti keele \u00f5igekirjutuse-s\u00f5naraamatu\u201c kommenteeritud v\u00e4ljaanne (veebiversioon)",
-        "\u201eThe Spelling Dictionary of Estonian 1918\u201c. Commented online dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/054f10e9-915c-523b-b04d-4fe1d8fb9238.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/054f10e9-915c-523b-b04d-4fe1d8fb9238.json
deleted file mode 100644
index ba9b7447..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/054f10e9-915c-523b-b04d-4fe1d8fb9238.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00197L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17979318",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17979318"
-    ],
-    "PublicationTimestamp": "2019-01-10T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laur, Sven"
-    ],
-    "fulltext": "oai:oai.datacite.org:17979318;2019-01-23T22:00:57Z;ESTDOI;ESTDOI.KEEL;Mallip\u00f5hine faktituletaja;Laur, Sven;Center of Estonian Language Resources;2019;Issued: 2019-01-10;Updated: 2019-01-10;doi:10.15155/1-00-0000-0000-0000-00197L;Abstract;Tarkvarakomponent suudab vabatekstidest \u00f5ppida erinevaid seoseid ning nende abil eraldada struktureeritud infot. Seosed v\u00f5ivad olla lihtsad nagu isikunimed ja organisatsioonid v\u00f5i keerulisemad nagu firmade peakontorite asukohad.\n\nMeetod vajab sisendiks korpust, milles on meid huvitav seos m\u00e4rgendatud. Seej\u00e4rel leitakse automaatselt sobivad mallid ja koostatakse mudel, mis antud seost v\u00f5imalikult h\u00e4sti tuvastaksid. Tulemusena saame m\u00e4rgendamata vabatekstidest leida uusi seosele vastavaid n\u00e4iteid.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "054f10e9-915c-523b-b04d-4fe1d8fb9238",
-    "notes": [
-        "Abstract",
-        "Tarkvarakomponent suudab vabatekstidest \u00f5ppida erinevaid seoseid ning nende abil eraldada struktureeritud infot. Seosed v\u00f5ivad olla lihtsad nagu isikunimed ja organisatsioonid v\u00f5i keerulisemad nagu firmade peakontorite asukohad.\n\nMeetod vajab sisendiks korpust, milles on meid huvitav seos m\u00e4rgendatud. Seej\u00e4rel leitakse automaatselt sobivad mallid ja koostatakse mudel, mis antud seost v\u00f5imalikult h\u00e4sti tuvastaksid. Tulemusena saame m\u00e4rgendamata vabatekstidest leida uusi seosele vastavaid n\u00e4iteid."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17979318"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Mallip\u00f5hine faktituletaja"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/077c4792-3230-52eb-8e0c-5c8ef003312c.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/077c4792-3230-52eb-8e0c-5c8ef003312c.json
deleted file mode 100644
index a2a74a12..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/077c4792-3230-52eb-8e0c-5c8ef003312c.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00083L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5757520",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5757520"
-    ],
-    "PublicationTimestamp": "2015-05-22T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:5757520;2019-03-28T16:30:56Z;ESTDOI;ESTDOI.KEEL;The database of Estonian multi-word expressions;Muischnek, Kadri;Center of Estonian Language Resources;2011;Issued: 2011-11-18;Updated: 2015-05-22;doi:10.15155/1-00-0000-0000-0000-00083L;Abstract;This database contains a subtype of multi-word expressions, namely those consisting of a verb and a particle or a verb and its complements.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "077c4792-3230-52eb-8e0c-5c8ef003312c",
-    "notes": [
-        "Abstract",
-        "This database contains a subtype of multi-word expressions, namely those consisting of a verb and a particle or a verb and its complements."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5757520"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "The database of Estonian multi-word expressions"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/08ac834d-2917-545f-9ac4-21976e86b85f.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/08ac834d-2917-545f-9ac4-21976e86b85f.json
deleted file mode 100644
index 64ecd11f..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/08ac834d-2917-545f-9ac4-21976e86b85f.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-079DEL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17960243",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17960243"
-    ],
-    "PublicationTimestamp": "2019-01-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Mihkla, Meelis",
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:17960243;2019-02-26T06:02:06Z;ESTDOI;ESTDOI.KEEL;Tekstide helindaja;Hein, Indrek;Mihkla, Meelis;Center of Estonian Language Resources;2019;Issued: 2019-01-07;Updated: 2019-01-07;doi:10.15155/3-00-0000-0000-0000-079DEL;Abstract;Heliraamatute genereerija Vox Populi, mis kasutab EKI k\u00f5nes\u00fcnteesi ja h\u00e4\u00e4ldusbaasi, et pikemaid tekste helindada.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "08ac834d-2917-545f-9ac4-21976e86b85f",
-    "notes": [
-        "Abstract",
-        "Heliraamatute genereerija Vox Populi, mis kasutab EKI k\u00f5nes\u00fcnteesi ja h\u00e4\u00e4ldusbaasi, et pikemaid tekste helindada."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17960243"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Tekstide helindaja"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/096d8474-a2e5-5824-aff4-abebfffa905c.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/096d8474-a2e5-5824-aff4-abebfffa905c.json
deleted file mode 100644
index c49c3a1f..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/096d8474-a2e5-5824-aff4-abebfffa905c.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0014CL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14066265",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14066265"
-    ],
-    "PublicationTimestamp": "2018-01-26T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Lippus, P\u00e4rtel"
-    ],
-    "fulltext": "oai:oai.datacite.org:14066265;2019-04-22T17:25:41Z;ESTDOI;ESTDOI.KEEL;Pikad s\u00f5nad;Long words in Estonian;Lippus, P\u00e4rtel;Center of Estonian Language Resources;2018;Issued: 2018-01-26;Updated: 2018-01-26;doi:10.15155/1-00-0000-0000-0000-0014CL;Abstract;140 eri silbistruktuuriga 4-6 silbilist s\u00f5na. Salvestatud s\u00f5naloendina 2 keelejuhilt ning raamlauses 6 V\u00f5ru ja 7 Saaremaa keelejuhilt.\n40 l\u00fchikeste lahtiste silpidega 5-6 silbilist s\u00f5na. Salvestatud raamlauses 6 \u00fchiskeelselt keelejuhilt.\n\nMaterjali on kasutatud siin:\nPajusalu, K., Help, T., Lippus, P., Niit, E., Teras, P., & Viitso, T.-R. (2005). On the temporal structure of Estonian secondary-stressed feet. Linguistica Uralica, 41(2), 98\u2013106.\nLippus, P., Pajusalu, K., & Teras, P. (2006). The Temporal Structure of Penta- and Hexasyllabic Words in Estonian. In R. Hoffmann & H. Mixdorff (Eds.), Proceedings of the 3rd International Conference Speech Prosody (pp. 759\u2013762). Dresden: TUDpress. Retrieved from http://www.isca-speech.org/archive/sp2006/papers/sp06_103.pdf\n;Abstract;A list of 140 words with 4-6 syllables with different syllable structure. Read by 2 speakers in word list and by 6 V\u00f5ru dialect speakers and 7 Saaremaa dialect speakers in carrier sentences.\nA list of 40 words with 5-6 syllables with short open syllables. Read by 6 Standard Estonian speakers in carrier sentences.\n\nThe data was collected for:\nPajusalu, K., Help, T., Lippus, P., Niit, E., Teras, P., & Viitso, T.-R. (2005). On the temporal structure of Estonian secondary-stressed feet. Linguistica Uralica, 41(2), 98\u2013106.\nLippus, P., Pajusalu, K., & Teras, P. (2006). The Temporal Structure of Penta- and Hexasyllabic Words in Estonian. In R. Hoffmann & H. Mixdorff (Eds.), Proceedings of the 3rd International Conference Speech Prosody (pp. 759\u2013762). Dresden: TUDpress. Retrieved from http://www.isca-speech.org/archive/sp2006/papers/sp06_103.pdf\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "096d8474-a2e5-5824-aff4-abebfffa905c",
-    "notes": [
-        "Abstract",
-        "140 eri silbistruktuuriga 4-6 silbilist s\u00f5na. Salvestatud s\u00f5naloendina 2 keelejuhilt ning raamlauses 6 V\u00f5ru ja 7 Saaremaa keelejuhilt.\n40 l\u00fchikeste lahtiste silpidega 5-6 silbilist s\u00f5na. Salvestatud raamlauses 6 \u00fchiskeelselt keelejuhilt.\n\nMaterjali on kasutatud siin:\nPajusalu, K., Help, T., Lippus, P., Niit, E., Teras, P., & Viitso, T.-R. (2005). On the temporal structure of Estonian secondary-stressed feet. Linguistica Uralica, 41(2), 98\u2013106.\nLippus, P., Pajusalu, K., & Teras, P. (2006). The Temporal Structure of Penta- and Hexasyllabic Words in Estonian. In R. Hoffmann & H. Mixdorff (Eds.), Proceedings of the 3rd International Conference Speech Prosody (pp. 759\u2013762). Dresden: TUDpress. Retrieved from http://www.isca-speech.org/archive/sp2006/papers/sp06_103.pdf\n",
-        "Abstract",
-        "A list of 140 words with 4-6 syllables with different syllable structure. Read by 2 speakers in word list and by 6 V\u00f5ru dialect speakers and 7 Saaremaa dialect speakers in carrier sentences.\nA list of 40 words with 5-6 syllables with short open syllables. Read by 6 Standard Estonian speakers in carrier sentences.\n\nThe data was collected for:\nPajusalu, K., Help, T., Lippus, P., Niit, E., Teras, P., & Viitso, T.-R. (2005). On the temporal structure of Estonian secondary-stressed feet. Linguistica Uralica, 41(2), 98\u2013106.\nLippus, P., Pajusalu, K., & Teras, P. (2006). The Temporal Structure of Penta- and Hexasyllabic Words in Estonian. In R. Hoffmann & H. Mixdorff (Eds.), Proceedings of the 3rd International Conference Speech Prosody (pp. 759\u2013762). Dresden: TUDpress. Retrieved from http://www.isca-speech.org/archive/sp2006/papers/sp06_103.pdf\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14066265"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Pikad s\u00f5nad",
-        "Long words in Estonian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0a25b5e2-7582-5dad-bc8d-371ab4f883b7.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0a25b5e2-7582-5dad-bc8d-371ab4f883b7.json
deleted file mode 100644
index 8c38f91c..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0a25b5e2-7582-5dad-bc8d-371ab4f883b7.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0007DL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5756959",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5756959"
-    ],
-    "PublicationTimestamp": "2015-03-02T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:5756959;2019-03-22T18:25:40Z;ESTDOI;ESTDOI.KEEL;Segakorpus: Doktorit\u00f6\u00f6d;Corpus of Estonian scientific texts;Muischnek, Kadri;Center of Estonian Language Resources;2013;Issued: 2013-01-07;Updated: 2015-03-02;doi:10.15155/1-00-0000-0000-0000-0007DL;Abstract;Korpus sisaldab 5 miljonit s\u00f5na eestikeelset teaduskirjandust: doktorit\u00f6\u00f6d (2,3 miljonit s\u00f5na) ja teadusartiklid. TEI P5 XML m\u00e4rgendus, UTF8 kodeering.;Abstract;A text corpus containing 5 million words of Estonian scientific texts: \nPhD dissertations (2.3 million words) and scientific articles.\nMarkup: TEI P5 XML\nencoding: UTF8",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0a25b5e2-7582-5dad-bc8d-371ab4f883b7",
-    "notes": [
-        "Abstract",
-        "Korpus sisaldab 5 miljonit s\u00f5na eestikeelset teaduskirjandust: doktorit\u00f6\u00f6d (2,3 miljonit s\u00f5na) ja teadusartiklid. TEI P5 XML m\u00e4rgendus, UTF8 kodeering.",
-        "Abstract",
-        "A text corpus containing 5 million words of Estonian scientific texts: \nPhD dissertations (2.3 million words) and scientific articles.\nMarkup: TEI P5 XML\nencoding: UTF8"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5756959"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Segakorpus: Doktorit\u00f6\u00f6d",
-        "Corpus of Estonian scientific texts"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0a3fd74b-7125-516a-8717-2d25c28f6195.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0a3fd74b-7125-516a-8717-2d25c28f6195.json
deleted file mode 100644
index c21e0e15..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0a3fd74b-7125-516a-8717-2d25c28f6195.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00146L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:13446397",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:13446397"
-    ],
-    "PublicationTimestamp": "2018-04-04T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laur, Sven"
-    ],
-    "fulltext": "oai:oai.datacite.org:13446397;2019-04-22T17:25:45Z;ESTDOI;ESTDOI.KEEL;EstNLTK sentence splitting;Laur, Sven;Center of Estonian Language Resources;2017;Issued: 2017-12-11;Updated: 2018-04-04;doi:10.15155/1-00-0000-0000-0000-00146L;Abstract;Estonian NLTK toolkit - detecting sentence boundaries",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0a3fd74b-7125-516a-8717-2d25c28f6195",
-    "notes": [
-        "Abstract",
-        "Estonian NLTK toolkit - detecting sentence boundaries"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:13446397"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "EstNLTK sentence splitting"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0b52d029-1768-5e9a-986f-cb541a446c87.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0b52d029-1768-5e9a-986f-cb541a446c87.json
deleted file mode 100644
index 01fce8b7..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0b52d029-1768-5e9a-986f-cb541a446c87.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/TY.0005",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:4597348",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:4597348"
-    ],
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Prillop, K\u00fclli"
-    ],
-    "fulltext": "oai:oai.datacite.org:4597348;2019-02-02T11:01:50Z;ESTDOI;ESTDOI.KEEL;Corpus of Old Written Estonian;Prillop, K\u00fclli;Center of Estonian Language Resources;2013;doi:10.15155/TY.0005",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0b52d029-1768-5e9a-986f-cb541a446c87",
-    "oai_identifier": [
-        "oai:oai.datacite.org:4597348"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus of Old Written Estonian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0bc80291-8b84-5712-9a48-057ee1101dac.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0bc80291-8b84-5712-9a48-057ee1101dac.json
deleted file mode 100644
index 1f60a203..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0bc80291-8b84-5712-9a48-057ee1101dac.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0014DL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14085942",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14085942"
-    ],
-    "PublicationTimestamp": "2018-01-29T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Lippus, P\u00e4rtel"
-    ],
-    "fulltext": "oai:oai.datacite.org:14085942;2019-03-05T05:31:32Z;ESTDOI;ESTDOI.KEEL;Liivi prosoodia korpus;Livonian prosody corpus;Lippus, P\u00e4rtel;Center of Estonian Language Resources;2018;Issued: 2018-01-29;Updated: 2018-01-29;doi:10.15155/1-00-0000-0000-0000-0014DL;Abstract;Korpus koosneb 12 keelejuhi salvestustest, kes loevad liivikeelseid lauseid. Loend koosneb 102st lausest, kus igas lauses on \u00fcks tests\u00f5na osalause l\u00f5pus ja teine tests\u00f5na lause l\u00f5pus. Osa keelejuhte loeb sarnast l\u00e4tikeelset s\u00f5naloendit.\nMaterjal kasutati liivi s\u00f5narposoodia uurimiseks, uurimus on avaldatud: Lehiste, I., Teras, P., Ern\u0161treits, V., Lippus, P., Pajusalu, K., Tuisk, T., & Viitso, T.-R. (2008). Livonian prosody. Helsinki: Suomalais-ugrilainen Seura.\n;Abstract;Recordings from 12 speakers reading 102 Livonian test words embedded in carrier sentences. Most of the speakers read a similar sentence list in Latvian.\nThe data is collected for: Lehiste, I., Teras, P., Ern\u0161treits, V., Lippus, P., Pajusalu, K., Tuisk, T., & Viitso, T.-R. (2008). Livonian prosody. Helsinki: Suomalais-ugrilainen Seura.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0bc80291-8b84-5712-9a48-057ee1101dac",
-    "notes": [
-        "Abstract",
-        "Korpus koosneb 12 keelejuhi salvestustest, kes loevad liivikeelseid lauseid. Loend koosneb 102st lausest, kus igas lauses on \u00fcks tests\u00f5na osalause l\u00f5pus ja teine tests\u00f5na lause l\u00f5pus. Osa keelejuhte loeb sarnast l\u00e4tikeelset s\u00f5naloendit.\nMaterjal kasutati liivi s\u00f5narposoodia uurimiseks, uurimus on avaldatud: Lehiste, I., Teras, P., Ern\u0161treits, V., Lippus, P., Pajusalu, K., Tuisk, T., & Viitso, T.-R. (2008). Livonian prosody. Helsinki: Suomalais-ugrilainen Seura.\n",
-        "Abstract",
-        "Recordings from 12 speakers reading 102 Livonian test words embedded in carrier sentences. Most of the speakers read a similar sentence list in Latvian.\nThe data is collected for: Lehiste, I., Teras, P., Ern\u0161treits, V., Lippus, P., Pajusalu, K., Tuisk, T., & Viitso, T.-R. (2008). Livonian prosody. Helsinki: Suomalais-ugrilainen Seura."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14085942"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Liivi prosoodia korpus",
-        "Livonian prosody corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0bce5a0d-c2f2-563e-aafe-c4c4488429b1.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0bce5a0d-c2f2-563e-aafe-c4c4488429b1.json
deleted file mode 100644
index 2ae4e676..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0bce5a0d-c2f2-563e-aafe-c4c4488429b1.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-071EDL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14560213",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14560213"
-    ],
-    "PublicationTimestamp": "2018-04-23T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Koppel, Kristina",
-        "Kallas, Jelena"
-    ],
-    "fulltext": "oai:oai.datacite.org:14560213;2019-04-17T17:27:01Z;ESTDOI;ESTDOI.KEEL;Eesti keele \u00f5ppekorpus 2018 (etSkELL)  2018-01;Estonian Corpus for Learners 2018 (etSkELL)  2018-01;Kallas, Jelena;Koppel, Kristina;Center of Estonian Language Resources;2018;Issued: 2018-03-26;Updated: 2018-04-23;doi:10.15155/3-00-0000-0000-0000-071EDL;Abstract;Eesti keele \u00f5ppekorpus 2018 (etSkELL) on spetsiaalne tekstikorpus, mis sisaldab ainult keele\u00f5ppijale sobivaid lauseid. Laused p\u00e4rinevad Eesti keele \u00fchendkorpusest 2017 ja Eesti keele A1-C1 \u00f5pikute korpusest 2018. Keele\u00f5ppijale sobivate lausete tuvastamiseks kasutati Kristina Koppeli v\u00e4lja t\u00f6\u00f6tatud eesti keele GDEXi  (Good Dictionary Example) moodulit, mis v\u00f5imaldab lausete filtreerimist vastavalt etteantud parameetritele (nt lause pikkus, kirjavahem\u00e4rkide arv \u00fche lause piires jmt).\nEesti keele \u00f5ppekorpuse 2018 (etSkELL) suurus on u 250 000 s\u00f5na ja u 25 miljonit lauset. \nKorpus on lemmatiseeritud, m\u00e4rgendatud ja \u00fchestatud anal\u00fcsaatori EstNLTK abil.\nKorpus on loodud Eesti Keele Instituudi ja Lexical Computing Ltd. koost\u00f6\u00f6 raames. \n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0bce5a0d-c2f2-563e-aafe-c4c4488429b1",
-    "notes": [
-        "Abstract",
-        "Eesti keele \u00f5ppekorpus 2018 (etSkELL) on spetsiaalne tekstikorpus, mis sisaldab ainult keele\u00f5ppijale sobivaid lauseid. Laused p\u00e4rinevad Eesti keele \u00fchendkorpusest 2017 ja Eesti keele A1-C1 \u00f5pikute korpusest 2018. Keele\u00f5ppijale sobivate lausete tuvastamiseks kasutati Kristina Koppeli v\u00e4lja t\u00f6\u00f6tatud eesti keele GDEXi  (Good Dictionary Example) moodulit, mis v\u00f5imaldab lausete filtreerimist vastavalt etteantud parameetritele (nt lause pikkus, kirjavahem\u00e4rkide arv \u00fche lause piires jmt).\nEesti keele \u00f5ppekorpuse 2018 (etSkELL) suurus on u 250 000 s\u00f5na ja u 25 miljonit lauset. \nKorpus on lemmatiseeritud, m\u00e4rgendatud ja \u00fchestatud anal\u00fcsaatori EstNLTK abil.\nKorpus on loodud Eesti Keele Instituudi ja Lexical Computing Ltd. koost\u00f6\u00f6 raames. \n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14560213"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele \u00f5ppekorpus 2018 (etSkELL)  2018-01",
-        "Estonian Corpus for Learners 2018 (etSkELL)  2018-01"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0d12d477-d598-57b7-bc35-863edf2da63e.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0d12d477-d598-57b7-bc35-863edf2da63e.json
deleted file mode 100644
index 882a5b19..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0d12d477-d598-57b7-bc35-863edf2da63e.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/TY.0008",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:4597356",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:4597356"
-    ],
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "M\u00fc\u00fcrisep, Kaili"
-    ],
-    "fulltext": "oai:oai.datacite.org:4597356;2019-02-21T01:31:34Z;ESTDOI;ESTDOI.KEEL;Estonian Treebank;M\u00fc\u00fcrisep, Kaili;Center of Estonian Language Resources;2011;doi:10.15155/TY.0008",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0d12d477-d598-57b7-bc35-863edf2da63e",
-    "oai_identifier": [
-        "oai:oai.datacite.org:4597356"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Estonian Treebank"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0dbcd95b-7434-5e56-aebc-c8f388ea5b05.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0dbcd95b-7434-5e56-aebc-c8f388ea5b05.json
deleted file mode 100644
index fe116f5a..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0dbcd95b-7434-5e56-aebc-c8f388ea5b05.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00181L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17950796",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17950796"
-    ],
-    "PublicationTimestamp": "2019-01-04T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Iva, Sulev"
-    ],
-    "fulltext": "oai:oai.datacite.org:17950796;2019-02-03T02:30:40Z;ESTDOI;ESTDOI.KEEL;Uma Lehe korpuse otsing;Iva, Sulev;Center of Estonian Language Resources;2019;Issued: 2019-01-04;Updated: 2019-01-04;doi:10.15155/1-00-0000-0000-0000-00181L;Abstract;V\u00f5ru ja seto ajakirjanduskorpuse mahuks on\n1 269 000 s\u00f5na, sellest: Uma Lehe korpus \u2013 ca 762 000 s\u00f5na, Ajalehe Setomaa korpus \u2013 seto keeles 279 000, eesti keeles 228 000 s\u00f5na. V\u00f5ru ja seto kirjakeele ajakirjanduse allkorpuste vaba juurdep\u00e4\u00e4suga otsingumootorid asuvad: \n- Uma Leht: http://www.murre.ut.ee/otsing/voru.php\n- Setomaa: http://synaq.org/seto",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0dbcd95b-7434-5e56-aebc-c8f388ea5b05",
-    "notes": [
-        "Abstract",
-        "V\u00f5ru ja seto ajakirjanduskorpuse mahuks on\n1 269 000 s\u00f5na, sellest: Uma Lehe korpus \u2013 ca 762 000 s\u00f5na, Ajalehe Setomaa korpus \u2013 seto keeles 279 000, eesti keeles 228 000 s\u00f5na. V\u00f5ru ja seto kirjakeele ajakirjanduse allkorpuste vaba juurdep\u00e4\u00e4suga otsingumootorid asuvad: \n- Uma Leht: http://www.murre.ut.ee/otsing/voru.php\n- Setomaa: http://synaq.org/seto"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17950796"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Uma Lehe korpuse otsing"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0e0ff0eb-fd56-525f-814e-1b7c18f6064b.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0e0ff0eb-fd56-525f-814e-1b7c18f6064b.json
deleted file mode 100644
index 815c3309..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0e0ff0eb-fd56-525f-814e-1b7c18f6064b.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05BDEL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9474544",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9474544"
-    ],
-    "PublicationTimestamp": "2017-03-03T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:9474544;2019-04-17T17:26:21Z;ESTDOI;ESTDOI.KEEL;Hariduss\u00f5nastik;The Dictionary of Education ;Hein, Indrek;Center of Estonian Language Resources;2016;Issued: 2016-11-09;Updated: 2017-03-03;doi:10.15155/3-00-0000-0000-0000-05BDEL;Abstract;Sisaldab 4850 terminit mitmesugustelt hariduse ja kasvatuse aladelt: kasvatus ja areng, alusharidus, p\u00f5hi- ja keskharidus, kutse- ja k\u00f5rgharidus, andragoogika, eripedagoogika jne. Igale eesti terminile on antud inglise, saksa, soome ja vene vaste ning enamasti ka seletus.;Abstract;Contains 4850 special terms from several fields, such as education, didactics, pre-school (kindergarten) education, basic and secondary education, vocational and higher education, andragogy, and special education. Every term is provided with an equivalent in English, German, Finnish and Russian; in most cases, an Estonian explanation is added.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0e0ff0eb-fd56-525f-814e-1b7c18f6064b",
-    "notes": [
-        "Abstract",
-        "Sisaldab 4850 terminit mitmesugustelt hariduse ja kasvatuse aladelt: kasvatus ja areng, alusharidus, p\u00f5hi- ja keskharidus, kutse- ja k\u00f5rgharidus, andragoogika, eripedagoogika jne. Igale eesti terminile on antud inglise, saksa, soome ja vene vaste ning enamasti ka seletus.",
-        "Abstract",
-        "Contains 4850 special terms from several fields, such as education, didactics, pre-school (kindergarten) education, basic and secondary education, vocational and higher education, andragogy, and special education. Every term is provided with an equivalent in English, German, Finnish and Russian; in most cases, an Estonian explanation is added."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9474544"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Hariduss\u00f5nastik",
-        "The Dictionary of Education "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0e8f67bd-b3a5-5e0d-9a2c-40aa9139132b.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0e8f67bd-b3a5-5e0d-9a2c-40aa9139132b.json
deleted file mode 100644
index 53d0851a..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0e8f67bd-b3a5-5e0d-9a2c-40aa9139132b.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00156L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14614709",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14614709"
-    ],
-    "PublicationTimestamp": "2018-04-13T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laur, Sven"
-    ],
-    "fulltext": "oai:oai.datacite.org:14614709;2019-03-07T18:25:42Z;ESTDOI;ESTDOI.KEEL;Eesti keele koondkorpus anal\u00fc\u00fcsitud EstNLTK v1.6.b abil;Estonian Reference Corpus analysed with EstNLTK v1.6.b;Laur, Sven;Center of Estonian Language Resources;2018;Issued: 2018-04-05;Updated: 2018-04-13;doi:10.15155/1-00-0000-0000-0000-00156L;Abstract;Estonian Reference Corpus analysed with EstNLTK ver.1.6_b\n\nThis resource contains texts from the Estonian Reference Corpus (Eesti keele koondkorpus) that have been converted into JSON format, and linguistically analysed with EstNLTK ver 1.6_b. The corpus contains 705,259 text files in EstNLTK's JSON format.\n\nSource of the corpus\n\nXML files of the Estonian Reference Corpus, which are available from here:\nhttp://www.cl.ut.ee/korpused/segakorpus/\n\nProcessing\n\nTexts were first converted into EstNLTK JSON format (metadata of the text documents was also preserved), and then automatically processed. Processing involved tokenizing texts into words, sentences and paragraphs, and morphological analysis and disambiguation. Results of the processing were recorded as annotation layers.\nThere are two layers of morphological annotations: \n1) the layer that uses Vabamorf's category system[1], \n2) the layer that uses Giellatekno's category system[2].\n\nThe processing was done at 2017-12-28, using the latest EstNLTK version available at that time (the version 1.6.0_beta).\nScripts that were used for processing (along with the instructions) are available here:\nhttps://github.com/estnltk/estnltk/tree/aed554e15e7f9e0f854d7a49bb2e2674e274cabc/estnltk/corpus_processing\n\nLoading JSON files with EstNLTK\nSee the tutorial:\n https://github.com/estnltk/estnltk/blob/aed554e15e7f9e0f854d7a49bb2e2674e274cabc/tutorials/json_exporter_importer.ipynb\n (Import from file)\n\n\n[1] -- Vabamorf's tagset -- Estonian description is available here: https://github.com/Filosoft/vabamorf/blob/master/doc/tagset.html\n[2] -- Giellatekno's tagset -- Estonian description is available here: http://www2.keeleveeb.ee/dict/corpus/shared/categories.html\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0e8f67bd-b3a5-5e0d-9a2c-40aa9139132b",
-    "notes": [
-        "Abstract",
-        "Estonian Reference Corpus analysed with EstNLTK ver.1.6_b\n\nThis resource contains texts from the Estonian Reference Corpus (Eesti keele koondkorpus) that have been converted into JSON format, and linguistically analysed with EstNLTK ver 1.6_b. The corpus contains 705,259 text files in EstNLTK's JSON format.\n\nSource of the corpus\n\nXML files of the Estonian Reference Corpus, which are available from here:\nhttp://www.cl.ut.ee/korpused/segakorpus/\n\nProcessing\n\nTexts were first converted into EstNLTK JSON format (metadata of the text documents was also preserved), and then automatically processed. Processing involved tokenizing texts into words, sentences and paragraphs, and morphological analysis and disambiguation. Results of the processing were recorded as annotation layers.\nThere are two layers of morphological annotations: \n1) the layer that uses Vabamorf's category system[1], \n2) the layer that uses Giellatekno's category system[2].\n\nThe processing was done at 2017-12-28, using the latest EstNLTK version available at that time (the version 1.6.0_beta).\nScripts that were used for processing (along with the instructions) are available here:\nhttps://github.com/estnltk/estnltk/tree/aed554e15e7f9e0f854d7a49bb2e2674e274cabc/estnltk/corpus_processing\n\nLoading JSON files with EstNLTK\nSee the tutorial:\n https://github.com/estnltk/estnltk/blob/aed554e15e7f9e0f854d7a49bb2e2674e274cabc/tutorials/json_exporter_importer.ipynb\n (Import from file)\n\n\n[1] -- Vabamorf's tagset -- Estonian description is available here: https://github.com/Filosoft/vabamorf/blob/master/doc/tagset.html\n[2] -- Giellatekno's tagset -- Estonian description is available here: http://www2.keeleveeb.ee/dict/corpus/shared/categories.html\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14614709"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele koondkorpus anal\u00fc\u00fcsitud EstNLTK v1.6.b abil",
-        "Estonian Reference Corpus analysed with EstNLTK v1.6.b"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0f84263b-af02-5bc1-8d5f-9a8c7ffcb674.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0f84263b-af02-5bc1-8d5f-9a8c7ffcb674.json
deleted file mode 100644
index 3ffffe4d..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0f84263b-af02-5bc1-8d5f-9a8c7ffcb674.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00188L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17960605",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17960605"
-    ],
-    "PublicationTimestamp": "2019-01-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "M\u00fc\u00fcrisep, Kaili"
-    ],
-    "fulltext": "oai:oai.datacite.org:17960605;2019-04-12T17:25:42Z;ESTDOI;ESTDOI.KEEL;Maltparseri treenitud mudel (UD);MaltParser model for Estonian UD format;M\u00fc\u00fcrisep, Kaili;Center of Estonian Language Resources;2019;Issued: 2019-01-07;Updated: 2019-01-07;doi:10.15155/1-00-0000-0000-0000-00188L;Abstract;Eesti keele s\u00fcntaksianal\u00fc\u00fcsi mudel MaltParserile (http://www.maltparser.org/), treenitud EstUD v2.2 puudepangal.;Abstract;Syntax parsing model for Estonian, trained on the Estonian Universal Dependencies treebank v2.2. To be used with MaltParser (http://www.maltparser.org/).",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0f84263b-af02-5bc1-8d5f-9a8c7ffcb674",
-    "notes": [
-        "Abstract",
-        "Eesti keele s\u00fcntaksianal\u00fc\u00fcsi mudel MaltParserile (http://www.maltparser.org/), treenitud EstUD v2.2 puudepangal.",
-        "Abstract",
-        "Syntax parsing model for Estonian, trained on the Estonian Universal Dependencies treebank v2.2. To be used with MaltParser (http://www.maltparser.org/)."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17960605"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Maltparseri treenitud mudel (UD)",
-        "MaltParser model for Estonian UD format"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0f9d94e0-2b36-5781-9eed-6697e7c43084.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0f9d94e0-2b36-5781-9eed-6697e7c43084.json
deleted file mode 100644
index 70f4bb3a..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0f9d94e0-2b36-5781-9eed-6697e7c43084.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00077L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5757204",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5757204"
-    ],
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "R\u00e4\u00e4bis, Andriela"
-    ],
-    "fulltext": "oai:oai.datacite.org:5757204;2019-03-12T18:25:42Z;ESTDOI;ESTDOI.KEEL;Suulise keele korpus;Corpus of Spoken Estonian;R\u00e4\u00e4bis, Andriela;Center of Estonian Language Resources;2013;Issued: 2013-01-09;Updated: 2019-01-08;doi:10.15155/1-00-0000-0000-0000-00077L;Abstract;The Department of Estonian Language initiated the corpus of spoken Estonian in 1997. The corpus is compiled by the research group of Spoken Estonian (Tiit Hennoste, Airi Jansons, Liina Lindstr\u00f6m, Andriela R\u00e4\u00e4bis, Olga Gerassimenko, Krista Strandson, Piret Toomet, Riina Vellerind). \nThe corpus is transcribed by the transcription of conversational analysis (CA). Each tape is provided with a header that lists in all 44 situational factors that have been found to affect language use in the analysis of various languages. For each concrete tape the number of possible factors is as high as possible. \nThe corpus is planned as an open corpus, i.e. no limits have been set. Our intention is to collect various types of oral speech, the usage of both everyday and institutional conversation, spontaneous and planned speech, monologues and dialogues, face-to-face interaction and media texts. The speakers are inhabitants of the largest towns of Estonia: Tallinn, Tartu and P\u00e4rnu. \nAs of April 2018, the corpus consists of 3761 audio  and 166 video records (703 hours, 3927 conversations alltogether) and 2337 transliterated texts (2 206 810 words according to Microsoft Word statistics). \nRecordings divide to:  \n1345 face-to-face conversations \n1924 phone conversations \n456 radio and TV broadcasts \n7 skype conversations \n\n195 undefined conversations (partially transcribed or fully transcribed extinct recordings). \n\nOn the institutionality scale, conversations divide to: \n824 everyday conversations;\n2796 institutional conversations;\n84 other conversations, \n223 non-defined. \n\nThe institutional situations include a large number of shop dialogues, dialogues at service institutions and government offices. \nThe corpus is a data bank in the Word format and simple txt-format (ISO-8859-1). In order to access the corpus, a contract with the research group of Spoken Estonian is required. ",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0f9d94e0-2b36-5781-9eed-6697e7c43084",
-    "notes": [
-        "Abstract",
-        "The Department of Estonian Language initiated the corpus of spoken Estonian in 1997. The corpus is compiled by the research group of Spoken Estonian (Tiit Hennoste, Airi Jansons, Liina Lindstr\u00f6m, Andriela R\u00e4\u00e4bis, Olga Gerassimenko, Krista Strandson, Piret Toomet, Riina Vellerind). \nThe corpus is transcribed by the transcription of conversational analysis (CA). Each tape is provided with a header that lists in all 44 situational factors that have been found to affect language use in the analysis of various languages. For each concrete tape the number of possible factors is as high as possible. \nThe corpus is planned as an open corpus, i.e. no limits have been set. Our intention is to collect various types of oral speech, the usage of both everyday and institutional conversation, spontaneous and planned speech, monologues and dialogues, face-to-face interaction and media texts. The speakers are inhabitants of the largest towns of Estonia: Tallinn, Tartu and P\u00e4rnu. \nAs of April 2018, the corpus consists of 3761 audio  and 166 video records (703 hours, 3927 conversations alltogether) and 2337 transliterated texts (2 206 810 words according to Microsoft Word statistics). \nRecordings divide to:  \n1345 face-to-face conversations \n1924 phone conversations \n456 radio and TV broadcasts \n7 skype conversations \n\n195 undefined conversations (partially transcribed or fully transcribed extinct recordings). \n\nOn the institutionality scale, conversations divide to: \n824 everyday conversations;\n2796 institutional conversations;\n84 other conversations, \n223 non-defined. \n\nThe institutional situations include a large number of shop dialogues, dialogues at service institutions and government offices. \nThe corpus is a data bank in the Word format and simple txt-format (ISO-8859-1). In order to access the corpus, a contract with the research group of Spoken Estonian is required. "
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5757204"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Suulise keele korpus",
-        "Corpus of Spoken Estonian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0fe07a68-f0c5-58bd-8eb9-823fc73f7343.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0fe07a68-f0c5-58bd-8eb9-823fc73f7343.json
deleted file mode 100644
index 2d43aa81..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/0fe07a68-f0c5-58bd-8eb9-823fc73f7343.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06BA2L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:13359318",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:13359318"
-    ],
-    "PublicationTimestamp": "2017-11-30T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek",
-        "Langemets, Margit"
-    ],
-    "fulltext": "oai:oai.datacite.org:13359318;2019-03-29T18:25:41Z;ESTDOI;ESTDOI.KEEL;Soome-eesti s\u00f5naraamat / Suomi\u2013viro-suursanakirja;Finnish-Estonian dictionary;Hein, Indrek;Langemets, Margit;Center of Estonian Language Resources;2017;Issued: 2017-11-30;Updated: 2017-11-30;doi:10.15155/3-00-0000-0000-0000-06BA2L;Abstract;Kahek\u00f6itelise soome-eesti suurs\u00f5naraamatu (2003) veebiversioon. Sisaldab \u00fcle 90 000 m\u00e4rks\u00f5na. S\u00f5naraamatus on rohkelt n\u00e4iteid koos t\u00f5lgetega (nii eritermineid kui ka k\u00f5nekeele v\u00e4ljendeid), lisaks valik kohanimesid. P\u00e4ringuid on v\u00f5imalik teha soome ja eesti keeles.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "0fe07a68-f0c5-58bd-8eb9-823fc73f7343",
-    "notes": [
-        "Abstract",
-        "Kahek\u00f6itelise soome-eesti suurs\u00f5naraamatu (2003) veebiversioon. Sisaldab \u00fcle 90 000 m\u00e4rks\u00f5na. S\u00f5naraamatus on rohkelt n\u00e4iteid koos t\u00f5lgetega (nii eritermineid kui ka k\u00f5nekeele v\u00e4ljendeid), lisaks valik kohanimesid. P\u00e4ringuid on v\u00f5imalik teha soome ja eesti keeles."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:13359318"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Soome-eesti s\u00f5naraamat / Suomi\u2013viro-suursanakirja",
-        "Finnish-Estonian dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/101b9b57-455f-54a8-9e45-002732feb738.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/101b9b57-455f-54a8-9e45-002732feb738.json
deleted file mode 100644
index 40f3f3a4..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/101b9b57-455f-54a8-9e45-002732feb738.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00176L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17944560",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17944560"
-    ],
-    "PublicationTimestamp": "2019-01-03T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Orasmaa, Siim"
-    ],
-    "fulltext": "oai:oai.datacite.org:17944560;2019-04-21T18:30:54Z;ESTDOI;ESTDOI.KEEL;Osalausestaja;Clause Segmenter for Estonian;Orasmaa, Siim;Center of Estonian Language Resources;2019;Issued: 2019-01-03;Updated: 2019-01-03;doi:10.15155/1-00-0000-0000-0000-00176L;Abstract;Osalausepiiride tuvastaja;Abstract;Clause Segmenter is a program that splits long and complex natural \n language sentences into smaller segments (clauses). For example, the \n sentence \"Mees, keda seal kohtasime, oli tuttav ja teretas meid.\" \n will be split into following clauses:\n\n     \"[Mees, [keda seal kohtasime,] oli tuttav ja] [teretas meid.]\"\n     (in the example, clauses are surrounded by brackets)\n\n   The algorithm mainly relies on punctuation, conjunction words, and\n  finite verb forms on identifying the clause boundaries.\n  For linguistic details/motivations behind the algorithm, see (Kaalep, \n  Muischnek 2012).",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "101b9b57-455f-54a8-9e45-002732feb738",
-    "notes": [
-        "Abstract",
-        "Osalausepiiride tuvastaja",
-        "Abstract",
-        "Clause Segmenter is a program that splits long and complex natural \n language sentences into smaller segments (clauses). For example, the \n sentence \"Mees, keda seal kohtasime, oli tuttav ja teretas meid.\" \n will be split into following clauses:\n\n     \"[Mees, [keda seal kohtasime,] oli tuttav ja] [teretas meid.]\"\n     (in the example, clauses are surrounded by brackets)\n\n   The algorithm mainly relies on punctuation, conjunction words, and\n  finite verb forms on identifying the clause boundaries.\n  For linguistic details/motivations behind the algorithm, see (Kaalep, \n  Muischnek 2012)."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17944560"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Osalausestaja",
-        "Clause Segmenter for Estonian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/10b47491-8d8e-50f0-a82d-09aad058843f.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/10b47491-8d8e-50f0-a82d-09aad058843f.json
deleted file mode 100644
index 7324ca0d..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/10b47491-8d8e-50f0-a82d-09aad058843f.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0016AL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17926658",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17926658"
-    ],
-    "PublicationTimestamp": "2019-01-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "M\u00fc\u00fcrisep, Kaili"
-    ],
-    "fulltext": "oai:oai.datacite.org:17926658;2019-04-12T17:25:43Z;ESTDOI;ESTDOI.KEEL;Anafooride suhtes m\u00e4rgendatud Eesti s\u00f5ltuvuspuude pank;Estonian Treebank annotated with coreference relations;M\u00fc\u00fcrisep, Kaili;Center of Estonian Language Resources;2018;Issued: 2018-12-21;Updated: 2019-01-07;doi:10.15155/1-00-0000-0000-0000-0016AL;Abstract;Anafooride suhtes m\u00e4rgendatud korpuses on praegu ca 107000 s\u00f5na mahus tekste, milles on u 4200 m\u00e4rgendatud ases\u00f5na, millest u 3200 on \u00fchendatud oma viitealusega, \u00fclej\u00e4\u00e4nud tuhandel ases\u00f5nal viitealus tekstis puudub. Tekstideks on ajalehetekstid ning \u00fcks teadustekst (ajakirja Eesti Arst 2004. aasta aastak\u00e4ik). M\u00e4rgendatud on j\u00e4rgmised ases\u00f5nad k\u00f5igis k\u00e4\u00e4ndevormides ja nende viitealused:\n\nisikulised ases\u00f5nad (mina/ma, sina/sa, tema/ta, meie/me, teie/te, nemad/nad). Kokku on korpuses 1734 isikulist ases\u00f5na, neist 1320 on \u00fchendatud viitealustega.\nn\u00e4itav ases\u00f5na see esineb korpuses 1489 korral, neist 1084 korral on tal tekstis olemas viitealus.\nsiduvad ases\u00f5nad kes ja mis esinevad tekstis kokku 1053 korda, neist 851 juhul on neil olemas viitealus tekstis.\nProgrammid, mis teisendavad puudepanga formaadis faili brati m\u00e4rgendajale sobivaks ja tagasi (pronoomentykeldaja.pl ja brat2inforem) on kataloogis tools. Programmide autorid on Kaili M\u00fc\u00fcrisep ja Katrin Tsepelina.;Abstract;This corpus containing ca 107,000 words of running text, is annotated for pronouns and their antecendents. There are 4200 annotated pronouns, among them 3200 are linked with their antecendents. The remaining 1000 pronouns have no clearly identifiable antecendent in text. Majority of the texts come from Estonian newspapers plus one scientific (medical) text, namely an issue of journal \u201eEesti Arst\u201d (Estonian Doctor).\n\nPrograms to convert Estonian dependency trees (VISLCG format) to brat annotations and back (pronoomentykeldaja.pl and brat2inforem) are in the tools folder, authors Kaili M\u00fc\u00fcrisep and Katrin Tsepelina.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "10b47491-8d8e-50f0-a82d-09aad058843f",
-    "notes": [
-        "Abstract",
-        "Anafooride suhtes m\u00e4rgendatud korpuses on praegu ca 107000 s\u00f5na mahus tekste, milles on u 4200 m\u00e4rgendatud ases\u00f5na, millest u 3200 on \u00fchendatud oma viitealusega, \u00fclej\u00e4\u00e4nud tuhandel ases\u00f5nal viitealus tekstis puudub. Tekstideks on ajalehetekstid ning \u00fcks teadustekst (ajakirja Eesti Arst 2004. aasta aastak\u00e4ik). M\u00e4rgendatud on j\u00e4rgmised ases\u00f5nad k\u00f5igis k\u00e4\u00e4ndevormides ja nende viitealused:\n\nisikulised ases\u00f5nad (mina/ma, sina/sa, tema/ta, meie/me, teie/te, nemad/nad). Kokku on korpuses 1734 isikulist ases\u00f5na, neist 1320 on \u00fchendatud viitealustega.\nn\u00e4itav ases\u00f5na see esineb korpuses 1489 korral, neist 1084 korral on tal tekstis olemas viitealus.\nsiduvad ases\u00f5nad kes ja mis esinevad tekstis kokku 1053 korda, neist 851 juhul on neil olemas viitealus tekstis.\nProgrammid, mis teisendavad puudepanga formaadis faili brati m\u00e4rgendajale sobivaks ja tagasi (pronoomentykeldaja.pl ja brat2inforem) on kataloogis tools. Programmide autorid on Kaili M\u00fc\u00fcrisep ja Katrin Tsepelina.",
-        "Abstract",
-        "This corpus containing ca 107,000 words of running text, is annotated for pronouns and their antecendents. There are 4200 annotated pronouns, among them 3200 are linked with their antecendents. The remaining 1000 pronouns have no clearly identifiable antecendent in text. Majority of the texts come from Estonian newspapers plus one scientific (medical) text, namely an issue of journal \u201eEesti Arst\u201d (Estonian Doctor).\n\nPrograms to convert Estonian dependency trees (VISLCG format) to brat annotations and back (pronoomentykeldaja.pl and brat2inforem) are in the tools folder, authors Kaili M\u00fc\u00fcrisep and Katrin Tsepelina."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17926658"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Anafooride suhtes m\u00e4rgendatud Eesti s\u00f5ltuvuspuude pank",
-        "Estonian Treebank annotated with coreference relations"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/10e1d895-d502-55df-bcdf-ed4b514ccd0d.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/10e1d895-d502-55df-bcdf-ed4b514ccd0d.json
deleted file mode 100644
index 4ca12984..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/10e1d895-d502-55df-bcdf-ed4b514ccd0d.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00178L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17944984",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17944984"
-    ],
-    "PublicationTimestamp": "2019-01-03T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:17944984;2019-02-05T18:25:41Z;ESTDOI;ESTDOI.KEEL;Nime- ja numbri\u00fcksuste tuvastaja;Muischnek, Kadri;Center of Estonian Language Resources;2019;Issued: 2019-01-03;Updated: 2019-01-03;doi:10.15155/1-00-0000-0000-0000-00178L;Abstract;Semantilise anal\u00fc\u00fcsi moodul leiab tekstis nime- ja numbri\u00fcksused",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "10e1d895-d502-55df-bcdf-ed4b514ccd0d",
-    "notes": [
-        "Abstract",
-        "Semantilise anal\u00fc\u00fcsi moodul leiab tekstis nime- ja numbri\u00fcksused"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17944984"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Nime- ja numbri\u00fcksuste tuvastaja"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/11100006-f5a0-57b1-8b56-02dba8cd0f25.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/11100006-f5a0-57b1-8b56-02dba8cd0f25.json
deleted file mode 100644
index 228443cd..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/11100006-f5a0-57b1-8b56-02dba8cd0f25.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00196L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17979317",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17979317"
-    ],
-    "PublicationTimestamp": "2019-01-10T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laur, Sven"
-    ],
-    "fulltext": "oai:oai.datacite.org:17979317;2019-04-22T09:32:22Z;ESTDOI;ESTDOI.KEEL;Faktituletaja Pythonis;Laur, Sven;Center of Estonian Language Resources;2019;Issued: 2019-01-10;Updated: 2019-01-10;doi:10.15155/1-00-0000-0000-0000-00196L;Abstract;Faktituletaja Pythoni komponent 7. m\u00e4rtsi 2013 seisuga. Integreeritud morfoanal\u00fc\u00fcsi kasutamiseks tuleb lisada bin kataloogi t3mesta binaar",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "11100006-f5a0-57b1-8b56-02dba8cd0f25",
-    "notes": [
-        "Abstract",
-        "Faktituletaja Pythoni komponent 7. m\u00e4rtsi 2013 seisuga. Integreeritud morfoanal\u00fc\u00fcsi kasutamiseks tuleb lisada bin kataloogi t3mesta binaar"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17979317"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Faktituletaja Pythonis"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/114226f5-25b7-5788-9238-7d36e235b545.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/114226f5-25b7-5788-9238-7d36e235b545.json
deleted file mode 100644
index 6bd97aeb..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/114226f5-25b7-5788-9238-7d36e235b545.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-00097L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17951390",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17951390"
-    ],
-    "PublicationTimestamp": "2019-01-04T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Meister, Einar"
-    ],
-    "fulltext": "oai:oai.datacite.org:17951390;2019-04-19T23:02:50Z;ESTDOI;ESTDOI.KEEL;Audiovisuaalse k\u00f5nes\u00fcnteesi rakendus Linuxile;Meister, Einar;Center of Estonian Language Resources;2019;Issued: 2019-01-04;Updated: 2019-01-04;doi:10.15155/9-00-0000-0000-0000-00097L;Abstract;\"K\u00f5neleva pea\" protot\u00fc\u00fcp T\u00f5nu.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "114226f5-25b7-5788-9238-7d36e235b545",
-    "notes": [
-        "Abstract",
-        "\"K\u00f5neleva pea\" protot\u00fc\u00fcp T\u00f5nu."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17951390"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Audiovisuaalse k\u00f5nes\u00fcnteesi rakendus Linuxile"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/115cc026-de84-56ce-9e04-9a014c2664ed.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/115cc026-de84-56ce-9e04-9a014c2664ed.json
deleted file mode 100644
index b32e2ec5..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/115cc026-de84-56ce-9e04-9a014c2664ed.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-079D3L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17926653",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17926653"
-    ],
-    "PublicationTimestamp": "2018-12-27T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Pajupuu, Hille"
-    ],
-    "fulltext": "oai:oai.datacite.org:17926653;2019-04-03T20:33:01Z;ESTDOI;ESTDOI.KEEL;Valence;Pajupuu, Hille;Center of Estonian Language Resources;2018;Issued: 2018-12-22;Updated: 2018-12-27;doi:10.15155/3-00-0000-0000-0000-079D3L;Abstract;This is a program classifying an Estonian text as positive, neutral or negative. It is running on server http://peeter.eki.ee:5000/valence\n\nThis code is optimized for server environment but can be run also as a standalone program:\n\npython valencecolor.py textfile.txt\nThis will produce a file textfile.txt.html where all emotionally relevant word are marked with CSS style. The limitation is that it does not print out the summary information. As a prerequisite the NLTK must be installed on the computer.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "115cc026-de84-56ce-9e04-9a014c2664ed",
-    "notes": [
-        "Abstract",
-        "This is a program classifying an Estonian text as positive, neutral or negative. It is running on server http://peeter.eki.ee:5000/valence\n\nThis code is optimized for server environment but can be run also as a standalone program:\n\npython valencecolor.py textfile.txt\nThis will produce a file textfile.txt.html where all emotionally relevant word are marked with CSS style. The limitation is that it does not print out the summary information. As a prerequisite the NLTK must be installed on the computer."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17926653"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Valence"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/11689b0c-43bd-5c2a-bcd7-7d1212072c92.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/11689b0c-43bd-5c2a-bcd7-7d1212072c92.json
deleted file mode 100644
index 8cb91700..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/11689b0c-43bd-5c2a-bcd7-7d1212072c92.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-00018L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5756974",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5756974"
-    ],
-    "PublicationTimestamp": "2017-03-03T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:5756974;2019-04-17T17:27:28Z;ESTDOI;ESTDOI.KEEL;Eesti Keele Instituudi tekstikorpus;The Text Corpus of the Institute of the Estonian Language;Hein, Indrek;Center of Estonian Language Resources;2012;Issued: 2012-06-12;Updated: 2017-03-03;doi:10.15155/3-00-0000-0000-0000-00018L;Abstract;EKI tekstikorpus on koostatud juhuslikult kogutud materjalist (10,4 miljonit s\u00f5navormi; u 80% ulatuses ajalehetekstid) ja pole seega 'representatiivne'. Ka ei ole korpus m\u00e4rgendatud, sobides eelk\u00f5ige leksikaalse materjali otsinguks.;Abstract;The material for the text corpus has been collected haphazardly, (10.4 million word forms; ca 80% of the texts come from newspapers), which is why the corpus is not representative. Nor is the corpus tagged, thus being suited for lexical search mainly.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "11689b0c-43bd-5c2a-bcd7-7d1212072c92",
-    "notes": [
-        "Abstract",
-        "EKI tekstikorpus on koostatud juhuslikult kogutud materjalist (10,4 miljonit s\u00f5navormi; u 80% ulatuses ajalehetekstid) ja pole seega 'representatiivne'. Ka ei ole korpus m\u00e4rgendatud, sobides eelk\u00f5ige leksikaalse materjali otsinguks.",
-        "Abstract",
-        "The material for the text corpus has been collected haphazardly, (10.4 million word forms; ca 80% of the texts come from newspapers), which is why the corpus is not representative. Nor is the corpus tagged, thus being suited for lexical search mainly."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5756974"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti Keele Instituudi tekstikorpus",
-        "The Text Corpus of the Institute of the Estonian Language"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/116be959-407b-5122-a399-e329d473033d.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/116be959-407b-5122-a399-e329d473033d.json
deleted file mode 100644
index a2a3c6d2..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/116be959-407b-5122-a399-e329d473033d.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0011AL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:6919407",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:6919407"
-    ],
-    "PublicationTimestamp": "2015-10-29T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Tuisk, Tuuli"
-    ],
-    "fulltext": "oai:oai.datacite.org:6919407;2019-01-30T09:38:24Z;ESTDOI;ESTDOI.KEEL;Tartu \u00dclikooli eesti murrete ja sugulaskeelte arhiiv;University of Tartu Archives of Estonian Dialects and Kindred Languages;Tuisk, Tuuli;Center of Estonian Language Resources;2015;Issued: 2015-10-29;Updated: 2015-10-29;doi:10.15155/1-00-0000-0000-0000-0011AL;Abstract;his collection of linguistic material is managed by the University of Tartu, Institute of Estonian and General Linguistics. The archives contain four types of materials: \n1) Sound recordings of Estonian dialects and Finno-Ugric languages, \n2) Unpublished manuscripts, including \n  - student report papers and thesis written at the Institute of Estonian and General Linguistics, \n  - transcriptions and written notes on Estonian and Finno-Ugric languages, \n3) Photos from field-work expedition and linguistic events, \n4) Video recordings.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "116be959-407b-5122-a399-e329d473033d",
-    "notes": [
-        "Abstract",
-        "his collection of linguistic material is managed by the University of Tartu, Institute of Estonian and General Linguistics. The archives contain four types of materials: \n1) Sound recordings of Estonian dialects and Finno-Ugric languages, \n2) Unpublished manuscripts, including \n  - student report papers and thesis written at the Institute of Estonian and General Linguistics, \n  - transcriptions and written notes on Estonian and Finno-Ugric languages, \n3) Photos from field-work expedition and linguistic events, \n4) Video recordings."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:6919407"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Tartu \u00dclikooli eesti murrete ja sugulaskeelte arhiiv",
-        "University of Tartu Archives of Estonian Dialects and Kindred Languages"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/119bdc83-cac0-5480-b8aa-a92e0a690651.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/119bdc83-cac0-5480-b8aa-a92e0a690651.json
deleted file mode 100644
index a9007cf6..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/119bdc83-cac0-5480-b8aa-a92e0a690651.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05BDDL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9474543",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9474543"
-    ],
-    "PublicationTimestamp": "2016-11-09T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:9474543;2019-03-30T10:32:40Z;ESTDOI;ESTDOI.KEEL;Hariduse ja kasvatuse s\u00f5naraamat;Hein, Indrek;Center of Estonian Language Resources;2016;Issued: 2016-11-09;Updated: 2016-11-09;doi:10.15155/3-00-0000-0000-0000-05BDDL;Abstract;Sisaldab 4850 terminit mitmesugustelt hariduse ja kasvatuse aladelt: kasvatus ja areng, alusharidus, p\u00f5hi- ja keskharidus, kutse- ja k\u00f5rgharidus, andragoogika, eripedagoogika jne. Igale eesti terminile on antud inglise, saksa, soome ja vene vaste ning enamasti ka seletus.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "119bdc83-cac0-5480-b8aa-a92e0a690651",
-    "notes": [
-        "Abstract",
-        "Sisaldab 4850 terminit mitmesugustelt hariduse ja kasvatuse aladelt: kasvatus ja areng, alusharidus, p\u00f5hi- ja keskharidus, kutse- ja k\u00f5rgharidus, andragoogika, eripedagoogika jne. Igale eesti terminile on antud inglise, saksa, soome ja vene vaste ning enamasti ka seletus."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9474543"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Hariduse ja kasvatuse s\u00f5naraamat"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/11a2bcca-9fc8-59fd-b7ca-9531dffa373c.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/11a2bcca-9fc8-59fd-b7ca-9531dffa373c.json
deleted file mode 100644
index cdffd0a0..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/11a2bcca-9fc8-59fd-b7ca-9531dffa373c.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0019DL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17986398",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17986398"
-    ],
-    "PublicationTimestamp": "2019-01-11T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Iva, Sulev"
-    ],
-    "fulltext": "oai:oai.datacite.org:17986398;2019-04-21T06:32:28Z;ESTDOI;ESTDOI.KEEL;V\u00f5ru-eesti paralleelkorpuse kasutajaliides;Iva, Sulev;Center of Estonian Language Resources;2019;Issued: 2019-01-11;Updated: 2019-01-11;doi:10.15155/1-00-0000-0000-0000-0019DL;Abstract;Otsida saab mitu s\u00f5na korraga, hetkel miinusm\u00e4rki v\u00e4ljaj\u00e4ttena ei toetata.Vaikimisi otsitakse mitte terveid s\u00f5nu vaid s\u00f5nesid pikemate s\u00f5nede sees. ",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "11a2bcca-9fc8-59fd-b7ca-9531dffa373c",
-    "notes": [
-        "Abstract",
-        "Otsida saab mitu s\u00f5na korraga, hetkel miinusm\u00e4rki v\u00e4ljaj\u00e4ttena ei toetata.Vaikimisi otsitakse mitte terveid s\u00f5nu vaid s\u00f5nesid pikemate s\u00f5nede sees. "
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17986398"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "V\u00f5ru-eesti paralleelkorpuse kasutajaliides"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/11f01313-92f3-5dc0-9d74-4c4ddb626304.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/11f01313-92f3-5dc0-9d74-4c4ddb626304.json
deleted file mode 100644
index 947c8fb4..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/11f01313-92f3-5dc0-9d74-4c4ddb626304.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05BECL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9474558",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9474558"
-    ],
-    "PublicationTimestamp": "2016-10-31T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:9474558;2019-02-02T18:01:49Z;ESTDOI;ESTDOI.KEEL;Eesti-udmurdi s\u00f5naraamat;Hein, Indrek;Center of Estonian Language Resources;2016;Issued: 2016-10-31;Updated: 2016-10-31;doi:10.15155/3-00-0000-0000-0000-05BECL;Abstract;Esimene eesti-udmurdi s\u00f5naraamat. Sisaldab u 10 000 m\u00e4rks\u00f5na ja on keeleuuenduslik: udmurdikeelsete vastete puudumisel pakuvad autorid eestikeelsele s\u00f5nale omapoolse v\u00f5imaliku vaste. S\u00f5naraamatu erip\u00e4raks on ka udmurdi murdes\u00f5nade rohkus.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "11f01313-92f3-5dc0-9d74-4c4ddb626304",
-    "notes": [
-        "Abstract",
-        "Esimene eesti-udmurdi s\u00f5naraamat. Sisaldab u 10 000 m\u00e4rks\u00f5na ja on keeleuuenduslik: udmurdikeelsete vastete puudumisel pakuvad autorid eestikeelsele s\u00f5nale omapoolse v\u00f5imaliku vaste. S\u00f5naraamatu erip\u00e4raks on ka udmurdi murdes\u00f5nade rohkus."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9474558"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti-udmurdi s\u00f5naraamat"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/138ecb55-4b38-574d-91cc-ad6a004d8de7.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/138ecb55-4b38-574d-91cc-ad6a004d8de7.json
deleted file mode 100644
index fff8d653..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/138ecb55-4b38-574d-91cc-ad6a004d8de7.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05BE4L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9474550",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9474550"
-    ],
-    "PublicationTimestamp": "2016-11-09T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Pajupuu, Hille"
-    ],
-    "fulltext": "oai:oai.datacite.org:9474550;2018-10-23T13:40:42Z;ESTDOI;ESTDOI.KEEL;Valentsikorpus;Pajupuu, Hille;Center of Estonian Language Resources;2016;Issued: 2016-11-09;Updated: 2016-11-09;doi:10.15155/3-00-0000-0000-0000-05BE4L;Abstract;Valentsikorpus koosneb \"Postimehe\" artiklite ortograafilistest l\u00f5ikudest, mille emotsionaalsuse (positiivne, negatiivne, vastuoluline, neutraalne) on m\u00e4\u00e4ranud lugejad. Kasutatud on domineeriva arvamuse meetodit (Pennebaker jt 1997).\nValentsikorpus on m\u00f5eldud eesk\u00e4tt statistiliste mudelite treenimiseks, kuid seda saab kasutada ka muudel eesm\u00e4rkidel. P\u00e4ringuid on v\u00f5imalik teha nii rubriike (Arvamus, Eesti, Kultuur, Sport, V\u00e4lismaa, Krimi) kui ka emotsionaalsust (positiivne, negatiivne, vastuoluline, neutraalne) arvesse v\u00f5ttes.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "138ecb55-4b38-574d-91cc-ad6a004d8de7",
-    "notes": [
-        "Abstract",
-        "Valentsikorpus koosneb \"Postimehe\" artiklite ortograafilistest l\u00f5ikudest, mille emotsionaalsuse (positiivne, negatiivne, vastuoluline, neutraalne) on m\u00e4\u00e4ranud lugejad. Kasutatud on domineeriva arvamuse meetodit (Pennebaker jt 1997).\nValentsikorpus on m\u00f5eldud eesk\u00e4tt statistiliste mudelite treenimiseks, kuid seda saab kasutada ka muudel eesm\u00e4rkidel. P\u00e4ringuid on v\u00f5imalik teha nii rubriike (Arvamus, Eesti, Kultuur, Sport, V\u00e4lismaa, Krimi) kui ka emotsionaalsust (positiivne, negatiivne, vastuoluline, neutraalne) arvesse v\u00f5ttes."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9474550"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Valentsikorpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/14aa38c8-d605-56f9-9c93-967833933499.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/14aa38c8-d605-56f9-9c93-967833933499.json
deleted file mode 100644
index 9eea9786..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/14aa38c8-d605-56f9-9c93-967833933499.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05B52L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9352876",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9352876"
-    ],
-    "PublicationTimestamp": "2016-10-31T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Niit, Ellen",
-        "Laansalu, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:9352876;2018-12-22T15:32:17Z;ESTDOI;ESTDOI.KEEL;Idamurde s\u00f5nastik;Laansalu, Tiina;Niit, Ellen;Center of Estonian Language Resources;2016;Issued: 2016-10-31;Updated: 2016-10-31;doi:10.15155/3-00-0000-0000-0000-05B52L;Abstract;S\u00f5nastik kuulub Eesti Keele Instituudi v\u00e4ikeste murdes\u00f5nastike sarja. S\u00f5nastik sisaldab 7000 m\u00e4rks\u00f5na ning on m\u00f5eldud k\u00f5igile, kes kasutavad oma t\u00f6\u00f6s v\u00f5i \u00f5pingutes murdekeelt v\u00f5i kes on p\u00e4rit Ida-Eestist ja keda paelub esivanemate k\u00f5nepruuk.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "14aa38c8-d605-56f9-9c93-967833933499",
-    "notes": [
-        "Abstract",
-        "S\u00f5nastik kuulub Eesti Keele Instituudi v\u00e4ikeste murdes\u00f5nastike sarja. S\u00f5nastik sisaldab 7000 m\u00e4rks\u00f5na ning on m\u00f5eldud k\u00f5igile, kes kasutavad oma t\u00f6\u00f6s v\u00f5i \u00f5pingutes murdekeelt v\u00f5i kes on p\u00e4rit Ida-Eestist ja keda paelub esivanemate k\u00f5nepruuk."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9352876"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Idamurde s\u00f5nastik"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/156ffeb7-90dd-515a-9a24-effcba5f41bb.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/156ffeb7-90dd-515a-9a24-effcba5f41bb.json
deleted file mode 100644
index ff83e8c0..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/156ffeb7-90dd-515a-9a24-effcba5f41bb.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-0002BL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5757365",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5757365"
-    ],
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Meister, Einar"
-    ],
-    "fulltext": "oai:oai.datacite.org:5757365;2019-04-23T14:31:19Z;ESTDOI;ESTDOI.KEEL;Aktsendikorpus;Estonian Foreign Accent Corpus;Meister, Einar;Center of Estonian Language Resources;2013;Issued: 2013-01-09;Updated: 2019-01-08;doi:10.15155/9-00-0000-0000-0000-0002BL;Abstract;salvestati 10 leedu emakeelega keelejuhti,  segmenteeriti k\u00e4sitsi 6 jaapani, 7 rootsi ja 20 l\u00e4ti keelejuhi v\u00e4ltevastandustega s\u00f5nu sisaldavad laused, kokku 1566 lauset;Abstract;Estonian Foreign Accent Corpus includes speech recordings of non-native Estonian speech. Among speakers different first language backgrounds are represented: Russian (50 speakers), Finnish (30), Latvian (20), German (15), Lithuanian (13), French (13), Japanese (6), Swedish (6), Spanish (5), English (5), Italian (5), Hindi (3), Danish (2), Dutch (2), Slovak (2), Polish (1), Portuguese (1), Azerbaijani (1). For the reference material a subset of native Estonian speakers (10 male, 10 female) has been recorded, as well. The corpus includes some spontaneous speech (subject\u2019s self-introduction and description of three pictures), 136 isolated sentences (including main phonological features of Estonian - all vowels and consonants in different quantity oppositions, palatalisation, etc), and two short passages; ca 25 minutes of speech per speaker. ",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "156ffeb7-90dd-515a-9a24-effcba5f41bb",
-    "notes": [
-        "Abstract",
-        "salvestati 10 leedu emakeelega keelejuhti,  segmenteeriti k\u00e4sitsi 6 jaapani, 7 rootsi ja 20 l\u00e4ti keelejuhi v\u00e4ltevastandustega s\u00f5nu sisaldavad laused, kokku 1566 lauset",
-        "Abstract",
-        "Estonian Foreign Accent Corpus includes speech recordings of non-native Estonian speech. Among speakers different first language backgrounds are represented: Russian (50 speakers), Finnish (30), Latvian (20), German (15), Lithuanian (13), French (13), Japanese (6), Swedish (6), Spanish (5), English (5), Italian (5), Hindi (3), Danish (2), Dutch (2), Slovak (2), Polish (1), Portuguese (1), Azerbaijani (1). For the reference material a subset of native Estonian speakers (10 male, 10 female) has been recorded, as well. The corpus includes some spontaneous speech (subject\u2019s self-introduction and description of three pictures), 136 isolated sentences (including main phonological features of Estonian - all vowels and consonants in different quantity oppositions, palatalisation, etc), and two short passages; ca 25 minutes of speech per speaker. "
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5757365"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Aktsendikorpus",
-        "Estonian Foreign Accent Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/160423ac-49e2-5f48-b6bb-d2caaf25b82c.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/160423ac-49e2-5f48-b6bb-d2caaf25b82c.json
deleted file mode 100644
index a147c309..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/160423ac-49e2-5f48-b6bb-d2caaf25b82c.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-00021L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5755417",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5755417"
-    ],
-    "PublicationTimestamp": "2015-12-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Meister, Einar"
-    ],
-    "fulltext": "oai:oai.datacite.org:5755417;2019-04-18T17:36:35Z;ESTDOI;ESTDOI.KEEL;Corpus of Radio News;Meister, Einar;Center of Estonian Language Resources;2014;Issued: 2014-12-30;Updated: 2015-12-16;doi:10.15155/9-00-0000-0000-0000-00021L;Abstract;Radio News of Estonian Public Broadcasting",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "160423ac-49e2-5f48-b6bb-d2caaf25b82c",
-    "notes": [
-        "Abstract",
-        "Radio News of Estonian Public Broadcasting"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5755417"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus of Radio News"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/16c710c1-8af6-5355-a0e2-25bde6b9dd3c.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/16c710c1-8af6-5355-a0e2-25bde6b9dd3c.json
deleted file mode 100644
index df79796d..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/16c710c1-8af6-5355-a0e2-25bde6b9dd3c.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0018CL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17961504",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17961504"
-    ],
-    "PublicationTimestamp": "2019-01-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Vaik, Kristiina",
-        "M\u00fc\u00fcrisep, Kaili"
-    ],
-    "fulltext": "oai:oai.datacite.org:17961504;2019-04-08T03:32:45Z;ESTDOI;ESTDOI.KEEL;S\u00fcntaksi eelt\u00f6\u00f6tlusmoodulid (EtTenTen formaadile);Preprocessing module for parsing (for EtTenTen format);M\u00fc\u00fcrisep, Kaili;Vaik, Kristiina;Center of Estonian Language Resources;2019;Issued: 2019-01-07;Updated: 2019-01-07;doi:10.15155/1-00-0000-0000-0000-0018CL;Abstract;Selle s\u00fcntaksianal\u00fc\u00fcsi-eelse eelt\u00f6\u00f6tlusmooduli versioon on m\u00f5eldud etTenTeni korpuse tekstit\u00fc\u00fcpide (perioodika, valitsus, religioon, informatiivne, unknown, foorum ja blogi) jaoks. Moodulist on kaks versiooni. Esimene versioon on m\u00f5eldud perioodika, valitsuse, religiooni, informatiivse ja tundmatu tekstit\u00fc\u00fcbile (eeltootlus_ettenten.py, ettenten_patterns.py), teine versioon on m\u00f5eldud foorumi ja blogi tekstit\u00fc\u00fcbile (eeltootlus_ettenten_blg_frm.py, ettenten_patterns_blg_frm.py).;Abstract;Preprocessing module, to be used before parsing. This version includes two modules for preprocessing EtTenTen corpus text types: the first one for newspaper, government, religious, informative and unknown texts (eeltootlus_ettenten.py, ettenten_patterns.py) and the other for forums and blogs (eeltootlus_ettenten_blg_frm.py, ettenten_patterns_blg_frm.py).",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "16c710c1-8af6-5355-a0e2-25bde6b9dd3c",
-    "notes": [
-        "Abstract",
-        "Selle s\u00fcntaksianal\u00fc\u00fcsi-eelse eelt\u00f6\u00f6tlusmooduli versioon on m\u00f5eldud etTenTeni korpuse tekstit\u00fc\u00fcpide (perioodika, valitsus, religioon, informatiivne, unknown, foorum ja blogi) jaoks. Moodulist on kaks versiooni. Esimene versioon on m\u00f5eldud perioodika, valitsuse, religiooni, informatiivse ja tundmatu tekstit\u00fc\u00fcbile (eeltootlus_ettenten.py, ettenten_patterns.py), teine versioon on m\u00f5eldud foorumi ja blogi tekstit\u00fc\u00fcbile (eeltootlus_ettenten_blg_frm.py, ettenten_patterns_blg_frm.py).",
-        "Abstract",
-        "Preprocessing module, to be used before parsing. This version includes two modules for preprocessing EtTenTen corpus text types: the first one for newspaper, government, religious, informative and unknown texts (eeltootlus_ettenten.py, ettenten_patterns.py) and the other for forums and blogs (eeltootlus_ettenten_blg_frm.py, ettenten_patterns_blg_frm.py)."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17961504"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "S\u00fcntaksi eelt\u00f6\u00f6tlusmoodulid (EtTenTen formaadile)",
-        "Preprocessing module for parsing (for EtTenTen format)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/1870d55e-d7c4-5573-93a7-091e6fc59ae0.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/1870d55e-d7c4-5573-93a7-091e6fc59ae0.json
deleted file mode 100644
index 7a32b69f..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/1870d55e-d7c4-5573-93a7-091e6fc59ae0.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-00091L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17594756",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17594756"
-    ],
-    "PublicationTimestamp": "2018-11-26T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "J\u00e4rv, Risto"
-    ],
-    "fulltext": "oai:oai.datacite.org:17594756;2019-03-02T21:01:45Z;ESTDOI;ESTDOI.KEEL;Kodavere pajatused;Folk tales in Kodavere Parish;J\u00e4rv, Risto;Center of Estonian Language Resources;2018;Issued: 2018-01-22;Updated: 2018-11-26;doi:10.15155/9-00-0000-0000-0000-00091L;Abstract;Kodavere on tuntud oma rahvajututraditsiooni poolest ning pajatused on Kodaverele vast k\u00f5ige iseloomulikum rahvajutuliik. Need on humoristlikud lood, mille aluseks on m\u00f5ni kohalik s\u00fcndmus, m\u00f5ni t\u00e4helepanu \u00e4ratanud isik v\u00f5i m\u00f5ni huvitav endisaegne elupilt. Ka laiemalt levinud jutumotiivid v\u00f5i -s\u00fc\u017eeed v\u00f5isid saada tegelasteks t\u00e4itsa kohalikud inimesed. Konkreetsele olustikule keskendumise t\u00f5ttu j\u00e4i pajatuste levik ajas ja ruumis suhteliselt piiratuks. Vaimukamad lood v\u00f5isid repertuaari j\u00e4\u00e4da kauemaks, levida p\u00f5lvest p\u00f5lve ning koguda populaarsust k\u00fcla piirest v\u00e4ljapoolgi. Pajatuste jutustajad kasutasid tavalisi rahvajuttude vormiv\u00f5tteid: liiasust, kordust, dialoogi, kujundlikke \u00fctlusi.\nKodavere pajatusi on kirja pandud alates 1932. aastast. Nende \"avastamine\" ja kogumise \"kuldaeg\" oli 1950.-1960. aastatel, mil toimusid mitmed kogumisretked Kodavere kihelkonda, korraldajaiks Riiklik Kirjandusmuuseum ja Eesti Raadio. Kodavere juttude uurimist alustas Selma L\u00e4tt, j\u00e4tkas Mall Hiiem\u00e4e.\nSiit lehelt leiab pajatuste helisalvestusi, millele on lisatud ka tekstistus.\n;Abstract;Kodavere parish in Central-East Estonia is well-known for its distinctive folktale tradition. A unique genre of personal narratives of everyday experiences (pajatused) is especially characteristic of the area. These are humoristic stories based on true life events, remarkable persons of local fame or recollections of life in the past. Also, traditional folktale motifs or plots may have been adapted to local settings and related to local characters. The spread of such tales is relatively limited in time and space, usually not exceeding the range of the knowledge of the concrete context. But the wittiest tales spread more widely and were greatly esteemed outside the village itself and by different generations. Kodavere story-tellers used traditional stylistic devices such as exaggeration, repetition, dialogue, expressive sayings. \n\nThe first tales of this type were recorded in Kodavere parish in 1932. They attracted more attention in the 1950s and 1960s, which were the Golden Years of folklore expeditions in Kodavere area, organized by Estonian Literary Museum and Estonian Radio. The most prominent folklorists focussing on this narrative tradition include Selma L\u00e4tt and more recently Mall Hiiem\u00e4e.  \n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1870d55e-d7c4-5573-93a7-091e6fc59ae0",
-    "notes": [
-        "Abstract",
-        "Kodavere on tuntud oma rahvajututraditsiooni poolest ning pajatused on Kodaverele vast k\u00f5ige iseloomulikum rahvajutuliik. Need on humoristlikud lood, mille aluseks on m\u00f5ni kohalik s\u00fcndmus, m\u00f5ni t\u00e4helepanu \u00e4ratanud isik v\u00f5i m\u00f5ni huvitav endisaegne elupilt. Ka laiemalt levinud jutumotiivid v\u00f5i -s\u00fc\u017eeed v\u00f5isid saada tegelasteks t\u00e4itsa kohalikud inimesed. Konkreetsele olustikule keskendumise t\u00f5ttu j\u00e4i pajatuste levik ajas ja ruumis suhteliselt piiratuks. Vaimukamad lood v\u00f5isid repertuaari j\u00e4\u00e4da kauemaks, levida p\u00f5lvest p\u00f5lve ning koguda populaarsust k\u00fcla piirest v\u00e4ljapoolgi. Pajatuste jutustajad kasutasid tavalisi rahvajuttude vormiv\u00f5tteid: liiasust, kordust, dialoogi, kujundlikke \u00fctlusi.\nKodavere pajatusi on kirja pandud alates 1932. aastast. Nende \"avastamine\" ja kogumise \"kuldaeg\" oli 1950.-1960. aastatel, mil toimusid mitmed kogumisretked Kodavere kihelkonda, korraldajaiks Riiklik Kirjandusmuuseum ja Eesti Raadio. Kodavere juttude uurimist alustas Selma L\u00e4tt, j\u00e4tkas Mall Hiiem\u00e4e.\nSiit lehelt leiab pajatuste helisalvestusi, millele on lisatud ka tekstistus.\n",
-        "Abstract",
-        "Kodavere parish in Central-East Estonia is well-known for its distinctive folktale tradition. A unique genre of personal narratives of everyday experiences (pajatused) is especially characteristic of the area. These are humoristic stories based on true life events, remarkable persons of local fame or recollections of life in the past. Also, traditional folktale motifs or plots may have been adapted to local settings and related to local characters. The spread of such tales is relatively limited in time and space, usually not exceeding the range of the knowledge of the concrete context. But the wittiest tales spread more widely and were greatly esteemed outside the village itself and by different generations. Kodavere story-tellers used traditional stylistic devices such as exaggeration, repetition, dialogue, expressive sayings. \n\nThe first tales of this type were recorded in Kodavere parish in 1932. They attracted more attention in the 1950s and 1960s, which were the Golden Years of folklore expeditions in Kodavere area, organized by Estonian Literary Museum and Estonian Radio. The most prominent folklorists focussing on this narrative tradition include Selma L\u00e4tt and more recently Mall Hiiem\u00e4e.  \n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17594756"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Kodavere pajatused",
-        "Folk tales in Kodavere Parish"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/191a82c5-3634-5858-87aa-1ed48618e989.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/191a82c5-3634-5858-87aa-1ed48618e989.json
deleted file mode 100644
index d61f8f66..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/191a82c5-3634-5858-87aa-1ed48618e989.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0016DL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17940190",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17940190"
-    ],
-    "PublicationTimestamp": "2019-01-02T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:17940190;2019-02-14T05:33:01Z;ESTDOI;ESTDOI.KEEL;Maltparseri anal\u00fc\u00fcsitud koondkorpus 1.0;Muischnek, Kadri;Center of Estonian Language Resources;2019;Issued: 2019-01-02;Updated: 2019-01-02;doi:10.15155/1-00-0000-0000-0000-0016DL;Abstract;MaltParser, treenitud kasutades eesti keele s\u00f5ltuvuspuude panga allosa (14 114 lauset, 197 508 s\u00f5na ja kirjavahem\u00e4rki, 164 637 s\u00f5na (ilma kirjavahem\u00e4rkideta); 4/5 kasutatud korpusest), testitud (1764 lauset, 24208 tekstis\u00f5na koos kirjavahem\u00e4rkidega (1/10)), MaltParseri treenitud mudel.\n\nTulemused morfoloogiliselt \u00fchese testkorpuse korral:\nLA (s\u00fcntaktilise m\u00e4rgendi korrektsus) 90.2%,\nLAS (s\u00f5ltuvusseose ja s\u00fcntaktilise m\u00e4rgendi korrektsus) 83.8%,\nUAS (s\u00f5ltuvusseose m\u00e4\u00e4ramise korrektsus) 86.5%\n\nMaltParseri tulemused, kasutades automaatselt morfoloogiliselt \u00fchestatud sisendit:\n\nLA (s\u00fcntaktilise m\u00e4rgendi korrektsus) 84.6%,\nLAS (s\u00f5ltuvusseose ja s\u00fcntaktilise m\u00e4rgendi korrektsus) 76.6%,\nUAS (s\u00f5ltuvusseose m\u00e4\u00e4ramise korrektsus) 81.0%.\n\nAnal\u00fc\u00fcsides m\u00f5lema parseri tugevaid k\u00fclgi ja kombineerides neid omavahel, paranes LAS veel u \u00fche protsendi v\u00f5rra.\n\nMaltParseri anal\u00fc\u00fcsitud koondkorpus (ajakirjandus, ilukirjandus, teaduskirjandus).",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "191a82c5-3634-5858-87aa-1ed48618e989",
-    "notes": [
-        "Abstract",
-        "MaltParser, treenitud kasutades eesti keele s\u00f5ltuvuspuude panga allosa (14 114 lauset, 197 508 s\u00f5na ja kirjavahem\u00e4rki, 164 637 s\u00f5na (ilma kirjavahem\u00e4rkideta); 4/5 kasutatud korpusest), testitud (1764 lauset, 24208 tekstis\u00f5na koos kirjavahem\u00e4rkidega (1/10)), MaltParseri treenitud mudel.\n\nTulemused morfoloogiliselt \u00fchese testkorpuse korral:\nLA (s\u00fcntaktilise m\u00e4rgendi korrektsus) 90.2%,\nLAS (s\u00f5ltuvusseose ja s\u00fcntaktilise m\u00e4rgendi korrektsus) 83.8%,\nUAS (s\u00f5ltuvusseose m\u00e4\u00e4ramise korrektsus) 86.5%\n\nMaltParseri tulemused, kasutades automaatselt morfoloogiliselt \u00fchestatud sisendit:\n\nLA (s\u00fcntaktilise m\u00e4rgendi korrektsus) 84.6%,\nLAS (s\u00f5ltuvusseose ja s\u00fcntaktilise m\u00e4rgendi korrektsus) 76.6%,\nUAS (s\u00f5ltuvusseose m\u00e4\u00e4ramise korrektsus) 81.0%.\n\nAnal\u00fc\u00fcsides m\u00f5lema parseri tugevaid k\u00fclgi ja kombineerides neid omavahel, paranes LAS veel u \u00fche protsendi v\u00f5rra.\n\nMaltParseri anal\u00fc\u00fcsitud koondkorpus (ajakirjandus, ilukirjandus, teaduskirjandus)."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17940190"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Maltparseri anal\u00fc\u00fcsitud koondkorpus 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/1a0b2c70-7095-51f3-b3be-9c3bfe376cef.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/1a0b2c70-7095-51f3-b3be-9c3bfe376cef.json
deleted file mode 100644
index b2025696..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/1a0b2c70-7095-51f3-b3be-9c3bfe376cef.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-000ABL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17986392",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17986392"
-    ],
-    "PublicationTimestamp": "2019-01-11T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Iva, Sulev"
-    ],
-    "fulltext": "oai:oai.datacite.org:17986392;2019-04-17T17:27:45Z;ESTDOI;ESTDOI.KEEL;W\u00f5ru Instituudi T\u00f5lkeMasin;Iva, Sulev;Center of Estonian Language Resources;2019;Issued: 2019-01-11;Updated: 2019-01-11;doi:10.15155/9-00-0000-0000-0000-000ABL;Abstract;Reeglip\u00f5hine masint\u00f5lge eesti ja v\u00f5ru keele vahel.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1a0b2c70-7095-51f3-b3be-9c3bfe376cef",
-    "notes": [
-        "Abstract",
-        "Reeglip\u00f5hine masint\u00f5lge eesti ja v\u00f5ru keele vahel."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17986392"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "W\u00f5ru Instituudi T\u00f5lkeMasin"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/1b29fc94-2af8-5e53-9422-f6a17221437b.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/1b29fc94-2af8-5e53-9422-f6a17221437b.json
deleted file mode 100644
index 29e93780..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/1b29fc94-2af8-5e53-9422-f6a17221437b.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-0632AL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10303604",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10303604"
-    ],
-    "PublicationTimestamp": "2017-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laansalu, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:10303604;2019-04-21T09:31:36Z;ESTDOI;ESTDOI.KEEL;Eesti Keele Instituudi m\u00f5isteline s\u00f5navarakartoteek;The Conceptual File of Estonian Lexis of the Institute of the Estonian Language;Laansalu, Tiina;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2017-02-15;doi:10.15155/3-00-0000-0000-0000-0632AL;Abstract;M\u00f5istelise s\u00f5navarakartoteegi idee p\u00e4rineb Andrus Saarestelt. Kogumist\u00f6\u00f6 algas 1920ndatel ja kestis 1930ndate keskpaigani. M\u00f5istelises kogus on s\u00f5navara jaotatud mitte kihelkondade, vaid m\u00f5istete j\u00e4rgi. Materjali on kogutud j\u00e4rgmiste valdkondade kohta: abielu, aeg, aiandus, armuelu, ehitused, heinategu, ilmastik, inimene, kalandus, karjandus, keha, kehakatted, k\u00e4sit\u00f6\u00f6, liiklus, linat\u00f6\u00f6, loomastik, maap\u00f5uevarad, maastik, merelinnud, merendus, mesindus, metsandus, m\u00f5\u00f5dud, m\u00e4ngimine, m\u00e4rk, n\u00f5idus, n\u00f5ud, puut\u00f6\u00f6, p\u00f5llundus, suguv\u00f5sa, s\u00f5idukid, taevalaotus, tahtmine, taimestik, tervis, toitlus, tuli, tundeelu, tunnetamine, t\u00f6\u00f6, usund, veekogud, vees\u00f5idukid, viin, vill, v\u00e4rv, \u00f5igus ja \u00fchiskond.;Abstract;The idea comes from Andrus Saareste. Collection started in the 1920s and went on until mid-1930s. Unlike the geographic division typical of dialect collections, here the vocabulary is divided by conceptual affinity. Material has been collected from the following domains: Marriage, Time, Gardening, Love life, Buildings, Haymaking, Weather, Humans, Fishing, Cattle breeding, Body, Clothing, Handicrafts, Traffic, Flax works, Animals, Mineral resources, Landscapes, Seabirds, Maritime affairs, Apiculture, Forestry, Measurement, Playing, Sign, Magic, Dishes, Woodwork, Agriculture, Family, Vehicles, Firmament, Volition, Plants, Health, Nourishment, Fire, Emotional life, Cognition, Work, Religion, Waterbodies, Water vehicles, Vodka, Wool, Colour, and Justice and Society.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1b29fc94-2af8-5e53-9422-f6a17221437b",
-    "notes": [
-        "Abstract",
-        "M\u00f5istelise s\u00f5navarakartoteegi idee p\u00e4rineb Andrus Saarestelt. Kogumist\u00f6\u00f6 algas 1920ndatel ja kestis 1930ndate keskpaigani. M\u00f5istelises kogus on s\u00f5navara jaotatud mitte kihelkondade, vaid m\u00f5istete j\u00e4rgi. Materjali on kogutud j\u00e4rgmiste valdkondade kohta: abielu, aeg, aiandus, armuelu, ehitused, heinategu, ilmastik, inimene, kalandus, karjandus, keha, kehakatted, k\u00e4sit\u00f6\u00f6, liiklus, linat\u00f6\u00f6, loomastik, maap\u00f5uevarad, maastik, merelinnud, merendus, mesindus, metsandus, m\u00f5\u00f5dud, m\u00e4ngimine, m\u00e4rk, n\u00f5idus, n\u00f5ud, puut\u00f6\u00f6, p\u00f5llundus, suguv\u00f5sa, s\u00f5idukid, taevalaotus, tahtmine, taimestik, tervis, toitlus, tuli, tundeelu, tunnetamine, t\u00f6\u00f6, usund, veekogud, vees\u00f5idukid, viin, vill, v\u00e4rv, \u00f5igus ja \u00fchiskond.",
-        "Abstract",
-        "The idea comes from Andrus Saareste. Collection started in the 1920s and went on until mid-1930s. Unlike the geographic division typical of dialect collections, here the vocabulary is divided by conceptual affinity. Material has been collected from the following domains: Marriage, Time, Gardening, Love life, Buildings, Haymaking, Weather, Humans, Fishing, Cattle breeding, Body, Clothing, Handicrafts, Traffic, Flax works, Animals, Mineral resources, Landscapes, Seabirds, Maritime affairs, Apiculture, Forestry, Measurement, Playing, Sign, Magic, Dishes, Woodwork, Agriculture, Family, Vehicles, Firmament, Volition, Plants, Health, Nourishment, Fire, Emotional life, Cognition, Work, Religion, Waterbodies, Water vehicles, Vodka, Wool, Colour, and Justice and Society."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10303604"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti Keele Instituudi m\u00f5isteline s\u00f5navarakartoteek",
-        "The Conceptual File of Estonian Lexis of the Institute of the Estonian Language"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/1c18ce1b-48c9-512a-a2f2-0473cebdc0c7.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/1c18ce1b-48c9-512a-a2f2-0473cebdc0c7.json
deleted file mode 100644
index 7e7e5ac2..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/1c18ce1b-48c9-512a-a2f2-0473cebdc0c7.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05AEEL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9310568",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9310568"
-    ],
-    "PublicationTimestamp": "2016-10-19T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:9310568;2018-10-23T12:29:55Z;ESTDOI;ESTDOI.KEEL;Esimene eesti sl\u00e4ngis\u00f5naraamat;First Estonian Slang Dictionary;Hein, Indrek;Center of Estonian Language Resources;2016;Issued: 2016-10-19;Updated: 2016-10-19;doi:10.15155/3-00-0000-0000-0000-05AEEL;Abstract;The \"First Estonian Slang Dictionary\" is based on a slang vocabulary collected in Tallinn high schools in the spring of 1989. As the collection procedure was based on 152 thematic questionnaires, the dictionary's first and main half is thematic. The dictionary's second half, or register, presents all slang words in alphabetic order, with cross references by number to the relevant themes. ",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1c18ce1b-48c9-512a-a2f2-0473cebdc0c7",
-    "notes": [
-        "Abstract",
-        "The \"First Estonian Slang Dictionary\" is based on a slang vocabulary collected in Tallinn high schools in the spring of 1989. As the collection procedure was based on 152 thematic questionnaires, the dictionary's first and main half is thematic. The dictionary's second half, or register, presents all slang words in alphabetic order, with cross references by number to the relevant themes. "
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9310568"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Esimene eesti sl\u00e4ngis\u00f5naraamat",
-        "First Estonian Slang Dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/1c5797cd-9c7d-56ed-b120-2e32e78dd5db.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/1c5797cd-9c7d-56ed-b120-2e32e78dd5db.json
deleted file mode 100644
index 88a9b41d..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/1c5797cd-9c7d-56ed-b120-2e32e78dd5db.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-079DAL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17960239",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17960239"
-    ],
-    "PublicationTimestamp": "2019-01-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Mihkla, Meelis",
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:17960239;2019-03-11T18:37:22Z;ESTDOI;ESTDOI.KEEL;H\u00e4\u00e4ldusbaas;Pronunciation database;Hein, Indrek;Mihkla, Meelis;Center of Estonian Language Resources;2019;Issued: 2019-01-07;Updated: 2019-01-07;doi:10.15155/3-00-0000-0000-0000-079DAL;Abstract;V\u00f5\u00f5rnimede ja l\u00fchendite h\u00e4\u00e4lduse andmebaas;Abstract;Database of Estonian pronunciation for foreign names and abbreviations",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1c5797cd-9c7d-56ed-b120-2e32e78dd5db",
-    "notes": [
-        "Abstract",
-        "V\u00f5\u00f5rnimede ja l\u00fchendite h\u00e4\u00e4lduse andmebaas",
-        "Abstract",
-        "Database of Estonian pronunciation for foreign names and abbreviations"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17960239"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "H\u00e4\u00e4ldusbaas",
-        "Pronunciation database"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/1cd4c618-7688-5315-aa50-d3e9b1a8d0c0.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/1cd4c618-7688-5315-aa50-d3e9b1a8d0c0.json
deleted file mode 100644
index e8b2a71e..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/1cd4c618-7688-5315-aa50-d3e9b1a8d0c0.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00165L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17732799",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17732799"
-    ],
-    "PublicationTimestamp": "2018-12-07T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Barbu, Eduard"
-    ],
-    "fulltext": "oai:oai.datacite.org:17732799;2019-04-22T20:31:02Z;ESTDOI;ESTDOI.KEEL;Taxonomy Extracted from Estonian Wikipedia Text 1.0;Barbu, Eduard;Center of Estonian Language Resources;2018;Issued: 2018-11-27;Updated: 2018-12-07;doi:10.15155/1-00-0000-0000-0000-00165L;Abstract;The taxonomy is in an xml file and it has a structure compose of elements called \u201cdoc\"",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1cd4c618-7688-5315-aa50-d3e9b1a8d0c0",
-    "notes": [
-        "Abstract",
-        "The taxonomy is in an xml file and it has a structure compose of elements called \u201cdoc\""
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17732799"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Taxonomy Extracted from Estonian Wikipedia Text 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/1d6ba8db-d3a1-5f45-8225-173c07391022.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/1d6ba8db-d3a1-5f45-8225-173c07391022.json
deleted file mode 100644
index 50642529..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/1d6ba8db-d3a1-5f45-8225-173c07391022.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/4-00-0000-0000-0000-0000EL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5757484",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5757484"
-    ],
-    "PublicationTimestamp": "2015-05-22T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Kaalep, Heiki-Jaan"
-    ],
-    "fulltext": "oai:oai.datacite.org:5757484;2018-10-19T23:32:11Z;ESTDOI;ESTDOI.KEEL;Morphological analyzer for Estonian ESTMORF;Kaalep, Heiki-Jaan;Center of Estonian Language Resources;2013;Issued: 2013-01-09;Updated: 2015-05-22;doi:10.15155/4-00-0000-0000-0000-0000EL;Abstract;ESTMORF is a computer program for analysing unrestricted Estonian text. ESTMORF is implemented in a most straightforward way: it compares word forms of the running text with combinations of lexemes from its lexicon.\nESTMORF determines, for every input word form, the structure of the word (e.g. stem, derivational suffix, inflectional affix), the word class and inflectional categories (e.g. number and case). ",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1d6ba8db-d3a1-5f45-8225-173c07391022",
-    "notes": [
-        "Abstract",
-        "ESTMORF is a computer program for analysing unrestricted Estonian text. ESTMORF is implemented in a most straightforward way: it compares word forms of the running text with combinations of lexemes from its lexicon.\nESTMORF determines, for every input word form, the structure of the word (e.g. stem, derivational suffix, inflectional affix), the word class and inflectional categories (e.g. number and case). "
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5757484"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Morphological analyzer for Estonian ESTMORF"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/1def2edf-6ce7-5818-bcdf-b43fb433f124.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/1def2edf-6ce7-5818-bcdf-b43fb433f124.json
deleted file mode 100644
index 9e284568..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/1def2edf-6ce7-5818-bcdf-b43fb433f124.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-071ECL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14560211",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14560211"
-    ],
-    "PublicationTimestamp": "2018-03-26T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Koppel, Kristina",
-        "Kallas, Jelena"
-    ],
-    "fulltext": "oai:oai.datacite.org:14560211;2018-10-19T22:32:59Z;ESTDOI;ESTDOI.KEEL;Eesti keele \u00f5ppekorpus 2018 (etSkELL);Estonian Corpus for Learners 2018 (etSkELL);Kallas, Jelena;Koppel, Kristina;Center of Estonian Language Resources;2018;Issued: 2018-03-26;Updated: 2018-03-26;doi:10.15155/3-00-0000-0000-0000-071ECL;Abstract;Eesti keele \u00f5ppekorpus 2018 (etSkELL) on spetsiaalne tekstikorpus, mis sisaldab ainult keele\u00f5ppijale sobivaid lauseid. Laused p\u00e4rinevad Eesti keele \u00fchendkorpusest 2017 ja Eesti keele A1-C1 \u00f5pikute korpusest 2018. Keele\u00f5ppijale sobivate lausete tuvastamiseks kasutati Kristina Koppeli v\u00e4lja t\u00f6\u00f6tatud eesti keele GDEXi  (Good Dictionary Example) moodulit, mis v\u00f5imaldab lausete filtreerimist vastavalt etteantud parameetritele (nt lause pikkus, kirjavahem\u00e4rkide arv \u00fche lause piires jmt).\nEesti keele \u00f5ppekorpuse 2018 (etSkELL) suurus on u 250 000 s\u00f5na ja u 25 miljonit lauset. \nKorpus on lemmatiseeritud, m\u00e4rgendatud ja \u00fchestatud anal\u00fcsaatori EstNLTK abil.\nKorpus on loodud Eesti Keele Instituudi ja Lexical Computing Ltd. koost\u00f6\u00f6 raames. \n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1def2edf-6ce7-5818-bcdf-b43fb433f124",
-    "notes": [
-        "Abstract",
-        "Eesti keele \u00f5ppekorpus 2018 (etSkELL) on spetsiaalne tekstikorpus, mis sisaldab ainult keele\u00f5ppijale sobivaid lauseid. Laused p\u00e4rinevad Eesti keele \u00fchendkorpusest 2017 ja Eesti keele A1-C1 \u00f5pikute korpusest 2018. Keele\u00f5ppijale sobivate lausete tuvastamiseks kasutati Kristina Koppeli v\u00e4lja t\u00f6\u00f6tatud eesti keele GDEXi  (Good Dictionary Example) moodulit, mis v\u00f5imaldab lausete filtreerimist vastavalt etteantud parameetritele (nt lause pikkus, kirjavahem\u00e4rkide arv \u00fche lause piires jmt).\nEesti keele \u00f5ppekorpuse 2018 (etSkELL) suurus on u 250 000 s\u00f5na ja u 25 miljonit lauset. \nKorpus on lemmatiseeritud, m\u00e4rgendatud ja \u00fchestatud anal\u00fcsaatori EstNLTK abil.\nKorpus on loodud Eesti Keele Instituudi ja Lexical Computing Ltd. koost\u00f6\u00f6 raames. \n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14560211"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele \u00f5ppekorpus 2018 (etSkELL)",
-        "Estonian Corpus for Learners 2018 (etSkELL)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/1f6c1580-2bf6-584b-b55e-32a7818e79e7.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/1f6c1580-2bf6-584b-b55e-32a7818e79e7.json
deleted file mode 100644
index 5c6b6c3f..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/1f6c1580-2bf6-584b-b55e-32a7818e79e7.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06ADFL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:13042178",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:13042178"
-    ],
-    "PublicationTimestamp": "2017-11-20T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Koppel, Kristina",
-        "Kallas, Jelena"
-    ],
-    "fulltext": "oai:oai.datacite.org:13042178;2019-02-26T07:02:07Z;ESTDOI;ESTDOI.KEEL;Eesti keele \u00f5pikute lausete korpus A1\u2013C1;Corpus Of CERF-graded Coursebook Texts' Sentences;Kallas, Jelena;Koppel, Kristina;Center of Estonian Language Resources;2017;Issued: 2017-11-20;Updated: 2017-11-20;doi:10.15155/3-00-0000-0000-0000-06ADFL;Abstract;Sisaldab korpusest \u201eEesti keele \u00f5pikute korpus A1\u2013C1\" eraldatud t\u00e4islauseid. Korpus koosneb u 200 000 s\u00f5nest ja 24 000 lausest. Korpuses on m\u00e4rgendatud tekstistruktuuri \u00fcksused lause <sentence> ja osalause <clause>. Laused on morfoloogiliselt m\u00e4rgendatud. K\u00f5ik korpuse laused on keeletaseme piirides unikaalsed.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "1f6c1580-2bf6-584b-b55e-32a7818e79e7",
-    "notes": [
-        "Abstract",
-        "Sisaldab korpusest \u201eEesti keele \u00f5pikute korpus A1\u2013C1\" eraldatud t\u00e4islauseid. Korpus koosneb u 200 000 s\u00f5nest ja 24 000 lausest. Korpuses on m\u00e4rgendatud tekstistruktuuri \u00fcksused lause <sentence> ja osalause <clause>. Laused on morfoloogiliselt m\u00e4rgendatud. K\u00f5ik korpuse laused on keeletaseme piirides unikaalsed."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:13042178"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele \u00f5pikute lausete korpus A1\u2013C1",
-        "Corpus Of CERF-graded Coursebook Texts' Sentences"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/200c283a-ebb2-577b-8cb3-723cd7d1c3d0.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/200c283a-ebb2-577b-8cb3-723cd7d1c3d0.json
deleted file mode 100644
index 77792e4c..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/200c283a-ebb2-577b-8cb3-723cd7d1c3d0.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05AF6L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9310577",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9310577"
-    ],
-    "PublicationTimestamp": "2016-10-19T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Paet, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:9310577;2019-04-04T16:02:01Z;ESTDOI;ESTDOI.KEEL;V\u00f5\u00f5rs\u00f5nade leksikon;Paet, Tiina;Center of Estonian Language Resources;2016;Issued: 2016-10-19;Updated: 2016-10-19;doi:10.15155/3-00-0000-0000-0000-05AF6L;Abstract;2012. aastal raamatuna ilmunud \u201eV\u00f5\u00f5rs\u00f5nade leksikoni\u201c veebiversioon. Sisaldab 33 000 levinumat v\u00f5\u00f5rs\u00f5na, tsitaats\u00f5na, laens\u00f5na, l\u00fchendit, sententsi ja v\u00e4ljendit. See on ka esimene eestikeelne v\u00f5\u00f5rs\u00f5nakogu, mis esitab morfoloogilise info: k\u00e4\u00e4namise ja p\u00f6\u00f6ramise ning muutt\u00fc\u00fcbid. V\u00f5rreldes varasemate v\u00e4ljaannetega on lisatud on uusi s\u00f5nu, uuendatud seletusi ning t\u00e4psustatud s\u00f5nade et\u00fcmoloogiat.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "200c283a-ebb2-577b-8cb3-723cd7d1c3d0",
-    "notes": [
-        "Abstract",
-        "2012. aastal raamatuna ilmunud \u201eV\u00f5\u00f5rs\u00f5nade leksikoni\u201c veebiversioon. Sisaldab 33 000 levinumat v\u00f5\u00f5rs\u00f5na, tsitaats\u00f5na, laens\u00f5na, l\u00fchendit, sententsi ja v\u00e4ljendit. See on ka esimene eestikeelne v\u00f5\u00f5rs\u00f5nakogu, mis esitab morfoloogilise info: k\u00e4\u00e4namise ja p\u00f6\u00f6ramise ning muutt\u00fc\u00fcbid. V\u00f5rreldes varasemate v\u00e4ljaannetega on lisatud on uusi s\u00f5nu, uuendatud seletusi ning t\u00e4psustatud s\u00f5nade et\u00fcmoloogiat."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9310577"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "V\u00f5\u00f5rs\u00f5nade leksikon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/2094bc43-2a30-535f-8654-790a27d0efb7.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/2094bc43-2a30-535f-8654-790a27d0efb7.json
deleted file mode 100644
index 3f2bc76f..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/2094bc43-2a30-535f-8654-790a27d0efb7.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05BD5L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9474535",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9474535"
-    ],
-    "PublicationTimestamp": "2016-11-13T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Ermus, Liis"
-    ],
-    "fulltext": "oai:oai.datacite.org:9474535;2018-10-23T13:42:23Z;ESTDOI;ESTDOI.KEEL;Eesti Keele Instituudi eesti murrete ja soome-ugri keelte arhiiv EMSUKA;Ermus, Liis;Center of Estonian Language Resources;2016;Issued: 2016-11-13;Updated: 2016-11-13;doi:10.15155/3-00-0000-0000-0000-05BD5L;Abstract;Eesti Keele Instituudi eesti murrete ja soome-ugri keelte arhiivi (EMSUKA) on koondatud Eesti Keele Instituudi (sh Keele ja Kirjanduse Instituudi 1947\u20131993) t\u00f6\u00f6tajate ning Emakeele Seltsi korrespondentide kogutud keelematerjalid - sedel- ja vihikkogud ning helisalvestised.\n\nOlulisemad kogud on eesti murdearhiiv ning eesti murrete ja soome-ugri keelte heliarhiiv.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2094bc43-2a30-535f-8654-790a27d0efb7",
-    "notes": [
-        "Abstract",
-        "Eesti Keele Instituudi eesti murrete ja soome-ugri keelte arhiivi (EMSUKA) on koondatud Eesti Keele Instituudi (sh Keele ja Kirjanduse Instituudi 1947\u20131993) t\u00f6\u00f6tajate ning Emakeele Seltsi korrespondentide kogutud keelematerjalid - sedel- ja vihikkogud ning helisalvestised.\n\nOlulisemad kogud on eesti murdearhiiv ning eesti murrete ja soome-ugri keelte heliarhiiv."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9474535"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti Keele Instituudi eesti murrete ja soome-ugri keelte arhiiv EMSUKA"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/20db5737-3391-5e2f-b47f-368c017d6f90.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/20db5737-3391-5e2f-b47f-368c017d6f90.json
deleted file mode 100644
index 56d0241c..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/20db5737-3391-5e2f-b47f-368c017d6f90.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00199L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17986393",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17986393"
-    ],
-    "PublicationTimestamp": "2019-01-11T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Iva, Sulev"
-    ],
-    "fulltext": "oai:oai.datacite.org:17986393;2019-01-11T16:20:18Z;ESTDOI;ESTDOI.KEEL;Synaq.org;Iva, Sulev;Center of Estonian Language Resources;2019;Issued: 2019-01-11;Updated: 2019-01-11;doi:10.15155/1-00-0000-0000-0000-00199L;Abstract;V\u00f5ru-eesti s\u00f5naraamatu baasilt on \u00fcles ehitatud uus V\u00f5ru-eesti-v\u00f5ru veebis\u00f5naraamat (synaq.org). Sellega on integreeritud k\u00f5ik V\u00f5ru ja seto keelekorpuse projektiga loodud korpused (Uma Lehe ja ajalehe Setomaa korpus, ilukirjanduskorpus ja eesti-v\u00f5ru paralleelkorpus, mida k\u00f5iki on t\u00e4iendatud uute tekstidega). S\u00f5naraamatust on kujundatud keeleportaal, mis sobitub h\u00e4sti ka nutiseadmetes kasutamiseks.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "20db5737-3391-5e2f-b47f-368c017d6f90",
-    "notes": [
-        "Abstract",
-        "V\u00f5ru-eesti s\u00f5naraamatu baasilt on \u00fcles ehitatud uus V\u00f5ru-eesti-v\u00f5ru veebis\u00f5naraamat (synaq.org). Sellega on integreeritud k\u00f5ik V\u00f5ru ja seto keelekorpuse projektiga loodud korpused (Uma Lehe ja ajalehe Setomaa korpus, ilukirjanduskorpus ja eesti-v\u00f5ru paralleelkorpus, mida k\u00f5iki on t\u00e4iendatud uute tekstidega). S\u00f5naraamatust on kujundatud keeleportaal, mis sobitub h\u00e4sti ka nutiseadmetes kasutamiseks."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17986393"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Synaq.org"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/2228e6d0-9209-5cfe-bad6-0a56ca3baac4.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/2228e6d0-9209-5cfe-bad6-0a56ca3baac4.json
deleted file mode 100644
index d4b5a871..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/2228e6d0-9209-5cfe-bad6-0a56ca3baac4.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-077D0L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:15534458",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:15534458"
-    ],
-    "PublicationTimestamp": "2019-02-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Soon, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:15534458;2019-03-11T18:37:19Z;ESTDOI;ESTDOI.KEEL;Esterm v20180701;Esterm v20180701;Soon, Tiina;Center of Estonian Language Resources;2018;Issued: 2018-07-13;Updated: 2019-02-07;doi:10.15155/3-00-0000-0000-0000-077D0L;Abstract;Esterm on Eesti Keele Instituudi mitmekeelne terminibaas, mis sisaldab peamiselt Euroopa Liidu ja Eesti Vabariigi \u00f5igusaktide termineid. Terminibaas koondab \u00fcle 50 valdkonna terminoloogiat.;Abstract;Esterm is a multilingual termbase which includes terms mainly from the legal acts of the Republic of Estonia and the European Union. The termbase contains terminology from more than 50 domains.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2228e6d0-9209-5cfe-bad6-0a56ca3baac4",
-    "notes": [
-        "Abstract",
-        "Esterm on Eesti Keele Instituudi mitmekeelne terminibaas, mis sisaldab peamiselt Euroopa Liidu ja Eesti Vabariigi \u00f5igusaktide termineid. Terminibaas koondab \u00fcle 50 valdkonna terminoloogiat.",
-        "Abstract",
-        "Esterm is a multilingual termbase which includes terms mainly from the legal acts of the Republic of Estonia and the European Union. The termbase contains terminology from more than 50 domains."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:15534458"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Esterm v20180701",
-        "Esterm v20180701"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/23337b04-8035-5151-a503-6b109ddb2d10.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/23337b04-8035-5151-a503-6b109ddb2d10.json
deleted file mode 100644
index 2fef9c31..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/23337b04-8035-5151-a503-6b109ddb2d10.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0019AL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17986394",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17986394"
-    ],
-    "PublicationTimestamp": "2019-01-11T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Iva, Sulev"
-    ],
-    "fulltext": "oai:oai.datacite.org:17986394;2019-04-17T17:27:46Z;ESTDOI;ESTDOI.KEEL;Synaq.org;Iva, Sulev;Center of Estonian Language Resources;2019;Issued: 2019-01-11;Updated: 2019-01-11;doi:10.15155/1-00-0000-0000-0000-0019AL;Abstract;V\u00f5ru-eesti s\u00f5naraamatu baasilt on \u00fcles ehitatud uus V\u00f5ru-eesti-v\u00f5ru veebis\u00f5naraamat (synaq.org). Sellega on integreeritud k\u00f5ik V\u00f5ru ja seto keelekorpuse projektiga loodud korpused (Uma Lehe ja ajalehe Setomaa korpus, ilukirjanduskorpus ja eesti-v\u00f5ru paralleelkorpus, mida k\u00f5iki on t\u00e4iendatud uute tekstidega). S\u00f5naraamatust on kujundatud keeleportaal, mis sobitub h\u00e4sti ka nutiseadmetes kasutamiseks.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "23337b04-8035-5151-a503-6b109ddb2d10",
-    "notes": [
-        "Abstract",
-        "V\u00f5ru-eesti s\u00f5naraamatu baasilt on \u00fcles ehitatud uus V\u00f5ru-eesti-v\u00f5ru veebis\u00f5naraamat (synaq.org). Sellega on integreeritud k\u00f5ik V\u00f5ru ja seto keelekorpuse projektiga loodud korpused (Uma Lehe ja ajalehe Setomaa korpus, ilukirjanduskorpus ja eesti-v\u00f5ru paralleelkorpus, mida k\u00f5iki on t\u00e4iendatud uute tekstidega). S\u00f5naraamatust on kujundatud keeleportaal, mis sobitub h\u00e4sti ka nutiseadmetes kasutamiseks."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17986394"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Synaq.org"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/23f1ab0a-5ed8-5e0a-9f9f-e84f33e68a22.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/23f1ab0a-5ed8-5e0a-9f9f-e84f33e68a22.json
deleted file mode 100644
index b9838359..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/23f1ab0a-5ed8-5e0a-9f9f-e84f33e68a22.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00172L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17944457",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17944457"
-    ],
-    "PublicationTimestamp": "2019-01-03T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:17944457;2019-04-21T19:32:19Z;ESTDOI;ESTDOI.KEEL;CG s\u00fcntaksianal\u00fcsaatori anal\u00fc\u00fcsitud Tasakaalus korpus;Muischnek, Kadri;Center of Estonian Language Resources;2019;Issued: 2019-01-03;Updated: 2019-01-03;doi:10.15155/1-00-0000-0000-0000-00172L;Abstract;ajakirjandus, ilukirjandus, teaduskirjandus",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "23f1ab0a-5ed8-5e0a-9f9f-e84f33e68a22",
-    "notes": [
-        "Abstract",
-        "ajakirjandus, ilukirjandus, teaduskirjandus"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17944457"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "CG s\u00fcntaksianal\u00fcsaatori anal\u00fc\u00fcsitud Tasakaalus korpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/245d8a43-0308-5739-ba36-a453352d818c.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/245d8a43-0308-5739-ba36-a453352d818c.json
deleted file mode 100644
index 8fb55288..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/245d8a43-0308-5739-ba36-a453352d818c.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06331L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10303904",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10303904"
-    ],
-    "PublicationTimestamp": "2017-01-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Mihkla, Meelis"
-    ],
-    "fulltext": "oai:oai.datacite.org:10303904;2019-03-24T18:31:47Z;ESTDOI;ESTDOI.KEEL;Uudiste lugeja Androidis;Mihkla, Meelis;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2017-01-31;doi:10.15155/3-00-0000-0000-0000-06331L;Abstract;Rakendus loeb eesti keeles ette v\u00e4rskeid uudiseid. Kasutajal on v\u00f5imalik valida kolme s\u00fcnteesh\u00e4\u00e4le ja erinevate lugemiskiiruste vahel.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "245d8a43-0308-5739-ba36-a453352d818c",
-    "notes": [
-        "Abstract",
-        "Rakendus loeb eesti keeles ette v\u00e4rskeid uudiseid. Kasutajal on v\u00f5imalik valida kolme s\u00fcnteesh\u00e4\u00e4le ja erinevate lugemiskiiruste vahel."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10303904"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Uudiste lugeja Androidis"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/2502f74e-5e20-50bc-94e7-07ba277be0c7.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/2502f74e-5e20-50bc-94e7-07ba277be0c7.json
deleted file mode 100644
index 59b57aa5..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/2502f74e-5e20-50bc-94e7-07ba277be0c7.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06799L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10996395",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10996395"
-    ],
-    "PublicationTimestamp": "2017-05-10T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "K\u00e4si, Inge",
-        "Laansalu, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:10996395;2019-01-28T23:30:52Z;ESTDOI;ESTDOI.KEEL;Vanap\u00e4rase V\u00f5ru murde s\u00f5naraamat;Laansalu, Tiina;K\u00e4si, Inge;Center of Estonian Language Resources;2017;Issued: 2017-05-10;Updated: 2017-05-10;doi:10.15155/3-00-0000-0000-0000-06799L;Abstract;S\u00f5naraamatus kajastub arhailine V\u00f5ru murdekeel, mida k\u00f5neldi V\u00f5rumaa idaosas XIX sajandi teisel poolel ja XX sajandi esimesel poolel. S\u00f5naraamatus on ligi 10 000 m\u00e4rks\u00f5na. S\u00f5naraamat on koostatud murdekoguja ning -uurija Hella Keema peamiselt k\u00e4sikirjaliste kogude p\u00f5hjal. P\u00f5liste v\u00f5rumaalaste s\u00f5navara R\u00f5uge, Vastseliina ja Setumaa 35 k\u00fclast on kirja pandud aastatel 1963\u20131986.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2502f74e-5e20-50bc-94e7-07ba277be0c7",
-    "notes": [
-        "Abstract",
-        "S\u00f5naraamatus kajastub arhailine V\u00f5ru murdekeel, mida k\u00f5neldi V\u00f5rumaa idaosas XIX sajandi teisel poolel ja XX sajandi esimesel poolel. S\u00f5naraamatus on ligi 10 000 m\u00e4rks\u00f5na. S\u00f5naraamat on koostatud murdekoguja ning -uurija Hella Keema peamiselt k\u00e4sikirjaliste kogude p\u00f5hjal. P\u00f5liste v\u00f5rumaalaste s\u00f5navara R\u00f5uge, Vastseliina ja Setumaa 35 k\u00fclast on kirja pandud aastatel 1963\u20131986."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10996395"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Vanap\u00e4rase V\u00f5ru murde s\u00f5naraamat"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/2531d61b-9150-5f59-b605-cf4bc5832259.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/2531d61b-9150-5f59-b605-cf4bc5832259.json
deleted file mode 100644
index ca6abb16..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/2531d61b-9150-5f59-b605-cf4bc5832259.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06341L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10304163",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10304163"
-    ],
-    "PublicationTimestamp": "2017-01-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Soon, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:10304163;2019-03-20T06:01:01Z;ESTDOI;ESTDOI.KEEL;MILITERM;MILITERM;Soon, Tiina;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2017-01-31;doi:10.15155/3-00-0000-0000-0000-06341L;Abstract;MILITERM on s\u00f5janduse, julgeoleku- ja kaitsepoliitika terminite andmebaas, kus saab m\u00e4rks\u00f5nu otsida eesti, inglise, prantsuse ja saksa keeles. Eesti- ja ingliskeelsete terminite juures on ka oskuss\u00f5nade definitsioonid.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2531d61b-9150-5f59-b605-cf4bc5832259",
-    "notes": [
-        "Abstract",
-        "MILITERM on s\u00f5janduse, julgeoleku- ja kaitsepoliitika terminite andmebaas, kus saab m\u00e4rks\u00f5nu otsida eesti, inglise, prantsuse ja saksa keeles. Eesti- ja ingliskeelsete terminite juures on ka oskuss\u00f5nade definitsioonid."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10304163"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "MILITERM",
-        "MILITERM"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/25ac861d-f9d7-5bc9-b8d3-9479fba7b7a3.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/25ac861d-f9d7-5bc9-b8d3-9479fba7b7a3.json
deleted file mode 100644
index d8b0b57d..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/25ac861d-f9d7-5bc9-b8d3-9479fba7b7a3.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-00095L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17951298",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17951298"
-    ],
-    "PublicationTimestamp": "2019-01-04T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Meister, Einar"
-    ],
-    "fulltext": "oai:oai.datacite.org:17951298;2019-03-07T18:25:54Z;ESTDOI;ESTDOI.KEEL;Audiovisuaalse k\u00f5nes\u00fcnteesi veebirakendus ;Meister, Einar;Center of Estonian Language Resources;2019;Issued: 2019-01-04;Updated: 2019-01-04;doi:10.15155/9-00-0000-0000-0000-00095L;Abstract;Pea mudel t\u00f6\u00f6tab Internet Explorer veebisirvijaga ning lisaks tuleb veebisirvijale paigaldada Cortona 3D tarkvara. Seda on v\u00f5imalik saada siit.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "25ac861d-f9d7-5bc9-b8d3-9479fba7b7a3",
-    "notes": [
-        "Abstract",
-        "Pea mudel t\u00f6\u00f6tab Internet Explorer veebisirvijaga ning lisaks tuleb veebisirvijale paigaldada Cortona 3D tarkvara. Seda on v\u00f5imalik saada siit."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17951298"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Audiovisuaalse k\u00f5nes\u00fcnteesi veebirakendus "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/2618a7f6-1ea5-5376-a873-68d49a5811cf.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/2618a7f6-1ea5-5376-a873-68d49a5811cf.json
deleted file mode 100644
index 667e7da8..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/2618a7f6-1ea5-5376-a873-68d49a5811cf.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-071F0L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14560493",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14560493"
-    ],
-    "PublicationTimestamp": "2018-03-26T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Koppel, Kristina",
-        "Kallas, Jelena"
-    ],
-    "fulltext": "oai:oai.datacite.org:14560493;2018-10-22T17:03:07Z;ESTDOI;ESTDOI.KEEL;Sketch Engine eesti keele \u00f5ppijale (etSkELL);Sketch Engine for Estonian Language Learning (etSkELL);Kallas, Jelena;Koppel, Kristina;Center of Estonian Language Resources;2018;Issued: 2018-03-26;Updated: 2018-03-26;doi:10.15155/3-00-0000-0000-0000-071F0L;Abstract;etSkELL on automaatselt loodud keele\u00f5ppekeskkond, mille alus on Eesti keele \u00f5ppekorpus 2018. Korpus sisaldab umbes 25 miljonit lauset ja 250 miljonit s\u00f5na. Laused on p\u00e4rit erinevatest meedia-, ilukirjandus- ja teadustekstidest ning eestikeelsest Vikipeediast ja Eesti keele A1-C1 \u00f5pikute korpusest 2018.\netSkELL arendati v\u00e4lja Eesti Keele Instituudi ja Lexical Computing Ltd. koost\u00f6\u00f6s.\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2618a7f6-1ea5-5376-a873-68d49a5811cf",
-    "notes": [
-        "Abstract",
-        "etSkELL on automaatselt loodud keele\u00f5ppekeskkond, mille alus on Eesti keele \u00f5ppekorpus 2018. Korpus sisaldab umbes 25 miljonit lauset ja 250 miljonit s\u00f5na. Laused on p\u00e4rit erinevatest meedia-, ilukirjandus- ja teadustekstidest ning eestikeelsest Vikipeediast ja Eesti keele A1-C1 \u00f5pikute korpusest 2018.\netSkELL arendati v\u00e4lja Eesti Keele Instituudi ja Lexical Computing Ltd. koost\u00f6\u00f6s.\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14560493"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Sketch Engine eesti keele \u00f5ppijale (etSkELL)",
-        "Sketch Engine for Estonian Language Learning (etSkELL)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/26bd48e5-79b9-5a47-8cc6-3e33a2e05b22.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/26bd48e5-79b9-5a47-8cc6-3e33a2e05b22.json
deleted file mode 100644
index 512555f1..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/26bd48e5-79b9-5a47-8cc6-3e33a2e05b22.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-0633BL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10304071",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10304071"
-    ],
-    "PublicationTimestamp": "2017-01-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Langemets, Margit"
-    ],
-    "fulltext": "oai:oai.datacite.org:10304071;2018-11-23T03:01:47Z;ESTDOI;ESTDOI.KEEL;Liivi-saksa s\u00f5naraamat;Livonian-German Dictionary;Langemets, Margit;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2017-01-31;doi:10.15155/3-00-0000-0000-0000-0633BL;Abstract;Sj\u00f6gren-Wiedemanni s\u00f5naraamatu liivi-saksa veebiversioon.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "26bd48e5-79b9-5a47-8cc6-3e33a2e05b22",
-    "notes": [
-        "Abstract",
-        "Sj\u00f6gren-Wiedemanni s\u00f5naraamatu liivi-saksa veebiversioon."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10304071"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Liivi-saksa s\u00f5naraamat",
-        "Livonian-German Dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/2757e4fd-501a-5b29-b947-aeb678376994.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/2757e4fd-501a-5b29-b947-aeb678376994.json
deleted file mode 100644
index 79eb1c16..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/2757e4fd-501a-5b29-b947-aeb678376994.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06ADEL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:13041918",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:13041918"
-    ],
-    "PublicationTimestamp": "2018-03-27T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Koppel, Kristina",
-        "Kallas, Jelena"
-    ],
-    "fulltext": "oai:oai.datacite.org:13041918;2019-04-12T17:25:40Z;ESTDOI;ESTDOI.KEEL;Eesti keele A1\u2013C1 \u00f5pikute sisu korpus 2017 ;Corpus of Estonian coursebook content 2017;Kallas, Jelena;Koppel, Kristina;Center of Estonian Language Resources;2017;Issued: 2017-11-20;Updated: 2018-03-27;doi:10.15155/3-00-0000-0000-0000-06ADEL;Abstract;Sisaldab A1, A2, B1, B2 ja C1 keeleoskustasemega eesti keele \u00f5ppijatele suunatud \u00f5pikute materjali. Korpuses  on u 500 000 s\u00f5net ning korpuses on m\u00e4rgendatud teksti\u00fcksused <text> (enamasti eristatakse harjutust, s\u00f5navaraplokki ja suuremat seotud teksti), tekstil\u00f5igud <paragraph> (\u00fchel real asuv tekst), laused <sentence> ja osalaused <clause>. Korpus on morfoloogiliselt m\u00e4rgendatud. \n\nKorpuses on kaheksa \u00f5pikut:\n1.      Pesti, M., Ahi, H. (2015). E nagu Eesti: eesti keele \u00f5pik algajatele. Tallinn: Kiri-Mari Kirjastus.\n2.      Kitsnik, M., Kingisepp, L. (2002). Avatud uksed: eesti keele \u00f5ppekomplekt kesk- ja k\u00f5rgtasemele: \u00f5pperaamat. Tallinn: TEA Kirjastus.\n3.      Kitsnik, M. (2012). Eesti keele \u00f5pik: B1, B2. Tallinn: M. Kitsnik.\n4.      Pesti, M., Ahi, H. (2015). Eesti keele \u00f5pik A1. Tallinn: Justiitsministeerium.\n5.      Pesti, M., Ahi, H. (2012). Eesti keele \u00f5pik A2. Tallinn: M. Pesti.\n6.      Pesti, M., Ahi, H. (2015). Eesti keele \u00f5pik B1. Tallinn: Justiitsministeerium.\n7.      Sooneste, M. (2007). Eesti keele \u00f5pik: vene \u00f5ppekeelega g\u00fcmnaasium: kesk- ja k\u00f5rgtase. Tallinn: Varrak.\n8.      Rammo, S., Teral, M., Klaas-Lang, B., Allik, M. (2012). Keel selgeks!: eesti keele \u00f5pik t\u00e4iskasvanutele. Tallinn: Avita.\n\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2757e4fd-501a-5b29-b947-aeb678376994",
-    "notes": [
-        "Abstract",
-        "Sisaldab A1, A2, B1, B2 ja C1 keeleoskustasemega eesti keele \u00f5ppijatele suunatud \u00f5pikute materjali. Korpuses  on u 500 000 s\u00f5net ning korpuses on m\u00e4rgendatud teksti\u00fcksused <text> (enamasti eristatakse harjutust, s\u00f5navaraplokki ja suuremat seotud teksti), tekstil\u00f5igud <paragraph> (\u00fchel real asuv tekst), laused <sentence> ja osalaused <clause>. Korpus on morfoloogiliselt m\u00e4rgendatud. \n\nKorpuses on kaheksa \u00f5pikut:\n1.      Pesti, M., Ahi, H. (2015). E nagu Eesti: eesti keele \u00f5pik algajatele. Tallinn: Kiri-Mari Kirjastus.\n2.      Kitsnik, M., Kingisepp, L. (2002). Avatud uksed: eesti keele \u00f5ppekomplekt kesk- ja k\u00f5rgtasemele: \u00f5pperaamat. Tallinn: TEA Kirjastus.\n3.      Kitsnik, M. (2012). Eesti keele \u00f5pik: B1, B2. Tallinn: M. Kitsnik.\n4.      Pesti, M., Ahi, H. (2015). Eesti keele \u00f5pik A1. Tallinn: Justiitsministeerium.\n5.      Pesti, M., Ahi, H. (2012). Eesti keele \u00f5pik A2. Tallinn: M. Pesti.\n6.      Pesti, M., Ahi, H. (2015). Eesti keele \u00f5pik B1. Tallinn: Justiitsministeerium.\n7.      Sooneste, M. (2007). Eesti keele \u00f5pik: vene \u00f5ppekeelega g\u00fcmnaasium: kesk- ja k\u00f5rgtase. Tallinn: Varrak.\n8.      Rammo, S., Teral, M., Klaas-Lang, B., Allik, M. (2012). Keel selgeks!: eesti keele \u00f5pik t\u00e4iskasvanutele. Tallinn: Avita.\n\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:13041918"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele A1\u2013C1 \u00f5pikute sisu korpus 2017 ",
-        "Corpus of Estonian coursebook content 2017"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/275bec76-5830-553e-8916-7578fdf66739.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/275bec76-5830-553e-8916-7578fdf66739.json
deleted file mode 100644
index 604b50a4..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/275bec76-5830-553e-8916-7578fdf66739.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-07003L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14277525",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14277525"
-    ],
-    "PublicationTimestamp": "2018-02-22T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Kallasmaa, Marja",
-        "P\u00e4ll, Peeter"
-    ],
-    "fulltext": "oai:oai.datacite.org:14277525;2019-02-22T10:32:42Z;ESTDOI;ESTDOI.KEEL;Eesti kohanimeraamat;P\u00e4ll, Peeter;Kallasmaa, Marja;Center of Estonian Language Resources;2018;Issued: 2018-02-22;Updated: 2018-02-22;doi:10.15155/3-00-0000-0000-0000-07003L;Abstract;Dictionary of Estonian Place Names\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "275bec76-5830-553e-8916-7578fdf66739",
-    "notes": [
-        "Abstract",
-        "Dictionary of Estonian Place Names\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14277525"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti kohanimeraamat"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/27dead26-dda5-5549-9cdf-8a428e6da100.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/27dead26-dda5-5549-9cdf-8a428e6da100.json
deleted file mode 100644
index debb0a8f..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/27dead26-dda5-5549-9cdf-8a428e6da100.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0012DL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10761536",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10761536"
-    ],
-    "PublicationTimestamp": "2017-04-06T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:10761536;2019-02-21T02:31:07Z;ESTDOI;ESTDOI.KEEL;etTenTen korpus, morfoloogiliselt \u00fchestatud;Muischnek, Kadri;Center of Estonian Language Resources;2016;Issued: 2016-04-29;Updated: 2017-04-06;doi:10.15155/1-00-0000-0000-0000-0012DL;Abstract;etTenTen korpus on internetist alla laetud eestikeelsete veebilehtede korpus.\nKorpuses on 270 miljonit s\u00f5na 686 000 veebilehelt.\nvt veel http://www2.keeleveeb.ee/dict/corpus/ettenten/about.html\n\nAlgmaterjal\n\nKorpuse tekstid korjas internetist ja teisendas utf-8 kodeeringus teksti kujule Vit Suchomel.\nVeebirobotiga laeti alla 1 173 702 veebilehte, kusjuures juba olemas olevate lehtede koopiad j\u00e4eti k\u00f5rvale; k\u00f5rvale j\u00e4eti ka lehed, mis on esindatud Eesti kirjakeele koondkorpuses. (http://www.cl.ut.ee/korpused/segakorpus/). Kasutati Jan Pomikaleki doktorit\u00f6\u00f6 k\u00e4igus loodud programme  jusText ja onion (code.google.com/p/justext, code.google.com/p/onion)\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "27dead26-dda5-5549-9cdf-8a428e6da100",
-    "notes": [
-        "Abstract",
-        "etTenTen korpus on internetist alla laetud eestikeelsete veebilehtede korpus.\nKorpuses on 270 miljonit s\u00f5na 686 000 veebilehelt.\nvt veel http://www2.keeleveeb.ee/dict/corpus/ettenten/about.html\n\nAlgmaterjal\n\nKorpuse tekstid korjas internetist ja teisendas utf-8 kodeeringus teksti kujule Vit Suchomel.\nVeebirobotiga laeti alla 1 173 702 veebilehte, kusjuures juba olemas olevate lehtede koopiad j\u00e4eti k\u00f5rvale; k\u00f5rvale j\u00e4eti ka lehed, mis on esindatud Eesti kirjakeele koondkorpuses. (http://www.cl.ut.ee/korpused/segakorpus/). Kasutati Jan Pomikaleki doktorit\u00f6\u00f6 k\u00e4igus loodud programme  jusText ja onion (code.google.com/p/justext, code.google.com/p/onion)\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10761536"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "etTenTen korpus, morfoloogiliselt \u00fchestatud"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/293ab380-d26d-5fa9-9757-d8a563bd6c1d.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/293ab380-d26d-5fa9-9757-d8a563bd6c1d.json
deleted file mode 100644
index abee3cb3..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/293ab380-d26d-5fa9-9757-d8a563bd6c1d.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0014FL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14107608",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14107608"
-    ],
-    "PublicationTimestamp": "2018-01-30T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Lippus, P\u00e4rtel"
-    ],
-    "fulltext": "oai:oai.datacite.org:14107608;2019-04-04T18:00:49Z;ESTDOI;ESTDOI.KEEL;Inari saami prosoodia korpus;Inari Sami prosody corpus;Lippus, P\u00e4rtel;Center of Estonian Language Resources;2018;Issued: 2018-01-30;Updated: 2018-01-30;doi:10.15155/1-00-0000-0000-0000-0014FL;Abstract;Materjal koosneb kahesilbilistest erineva silbistruktuuriga tests\u00f5nadest, mis on paigutatud lauses fraasi keskele v\u00f5i fraasi l\u00f5ppu ja lause l\u00f5ppu. Iga lause sisaldab 2 tests\u00f5na. 72 lauset on fraasikeskse paigutusega, 120 lauset fraasil\u00f5pulise paigutusega. Salvestusi luges 4 meesk\u00f5nelejat.;Abstract;Recordings of Inari Saami disyllabic words embedded in carrier sentences read by 4 male speakers. The speakers read a list of 72 sentences where the test words occur in phrase-medial position and a list of 120 sentences where the test words occur once in phrase-final and once in sentence-final position. The test words are segmented on Praat TextGrids.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "293ab380-d26d-5fa9-9757-d8a563bd6c1d",
-    "notes": [
-        "Abstract",
-        "Materjal koosneb kahesilbilistest erineva silbistruktuuriga tests\u00f5nadest, mis on paigutatud lauses fraasi keskele v\u00f5i fraasi l\u00f5ppu ja lause l\u00f5ppu. Iga lause sisaldab 2 tests\u00f5na. 72 lauset on fraasikeskse paigutusega, 120 lauset fraasil\u00f5pulise paigutusega. Salvestusi luges 4 meesk\u00f5nelejat.",
-        "Abstract",
-        "Recordings of Inari Saami disyllabic words embedded in carrier sentences read by 4 male speakers. The speakers read a list of 72 sentences where the test words occur in phrase-medial position and a list of 120 sentences where the test words occur once in phrase-final and once in sentence-final position. The test words are segmented on Praat TextGrids."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14107608"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Inari saami prosoodia korpus",
-        "Inari Sami prosody corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/2daa70f6-abd3-5fbd-bb29-2aa6cfff3ac4.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/2daa70f6-abd3-5fbd-bb29-2aa6cfff3ac4.json
deleted file mode 100644
index b96036f0..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/2daa70f6-abd3-5fbd-bb29-2aa6cfff3ac4.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00084L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5757480",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5757480"
-    ],
-    "PublicationTimestamp": "2016-02-08T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Orav, Heili"
-    ],
-    "fulltext": "oai:oai.datacite.org:5757480;2019-04-02T17:02:44Z;ESTDOI;ESTDOI.KEEL;Estonian WordNet (kb65a-4);Orav, Heili;Center of Estonian Language Resources;2011;Issued: 2011-11-22;Updated: 2016-02-08;doi:10.15155/1-00-0000-0000-0000-00084L;Abstract;Compiled manually according to EuroWordNet project.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "2daa70f6-abd3-5fbd-bb29-2aa6cfff3ac4",
-    "notes": [
-        "Abstract",
-        "Compiled manually according to EuroWordNet project."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5757480"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Estonian WordNet (kb65a-4)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/316ff097-42b7-5915-a273-9f43cca50671.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/316ff097-42b7-5915-a273-9f43cca50671.json
deleted file mode 100644
index 591c48f8..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/316ff097-42b7-5915-a273-9f43cca50671.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-00094L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17951297",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17951297"
-    ],
-    "PublicationTimestamp": "2019-01-04T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Meister, Einar"
-    ],
-    "fulltext": "oai:oai.datacite.org:17951297;2019-01-04T13:27:55Z;ESTDOI;ESTDOI.KEEL;Audiovisuaalse k\u00f5nes\u00fcnteesi veebirakendus ;Meister, Einar;Center of Estonian Language Resources;2019;Issued: 2019-01-04;Updated: 2019-01-04;doi:10.15155/9-00-0000-0000-0000-00094L;Abstract;Pea mudel t\u00f6\u00f6tab Internet Explorer veebisirvijaga ning lisaks tuleb veebisirvijale paigaldada Cortona 3D tarkvara. Seda on v\u00f5imalik saada siit.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "316ff097-42b7-5915-a273-9f43cca50671",
-    "notes": [
-        "Abstract",
-        "Pea mudel t\u00f6\u00f6tab Internet Explorer veebisirvijaga ning lisaks tuleb veebisirvijale paigaldada Cortona 3D tarkvara. Seda on v\u00f5imalik saada siit."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17951297"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Audiovisuaalse k\u00f5nes\u00fcnteesi veebirakendus "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/31dfe8ac-9e2f-5d0a-a3b0-bdbe99f0af0b.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/31dfe8ac-9e2f-5d0a-a3b0-bdbe99f0af0b.json
deleted file mode 100644
index d3caaf91..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/31dfe8ac-9e2f-5d0a-a3b0-bdbe99f0af0b.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-000A6L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17972097",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17972097"
-    ],
-    "PublicationTimestamp": "2019-01-09T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Mellik, Andres"
-    ],
-    "fulltext": "oai:oai.datacite.org:17972097;2019-01-21T19:31:46Z;ESTDOI;ESTDOI.KEEL;K\u00f5neravi harjutuste mallid;Mellik, Andres;Center of Estonian Language Resources;2019;Issued: 2019-01-09;Updated: 2019-01-09;doi:10.15155/9-00-0000-0000-0000-000A6L;Abstract;Harjutuste\u200b \u200bmallid,\u200b \u200bmille\u200b \u200bpeale\u200b \u200bon\u200b \u200blogopeedidel\u200b \u200bv\u00f5imalik\u200b \u200bluua\u200b \u200bk\u00f5neravi.ee keskkonda\u200b \u200buusi\u200b \u200bharjutusi",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "31dfe8ac-9e2f-5d0a-a3b0-bdbe99f0af0b",
-    "notes": [
-        "Abstract",
-        "Harjutuste\u200b \u200bmallid,\u200b \u200bmille\u200b \u200bpeale\u200b \u200bon\u200b \u200blogopeedidel\u200b \u200bv\u00f5imalik\u200b \u200bluua\u200b \u200bk\u00f5neravi.ee keskkonda\u200b \u200buusi\u200b \u200bharjutusi"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17972097"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "K\u00f5neravi harjutuste mallid"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/32290448-f663-58f6-b2a4-3c4b23a52d9c.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/32290448-f663-58f6-b2a4-3c4b23a52d9c.json
deleted file mode 100644
index c22f4331..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/32290448-f663-58f6-b2a4-3c4b23a52d9c.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05924L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:8922495",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:8922495"
-    ],
-    "PublicationTimestamp": "2016-08-23T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Kallas, Jelena",
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:8922495;2019-03-26T13:32:00Z;ESTDOI;ESTDOI.KEEL;Eesti keele p\u00f5his\u00f5navara s\u00f5nastik;Basic Estonian Dictionary;Hein, Indrek;Kallas, Jelena;Center of Estonian Language Resources;2016;Issued: 2016-08-23;Updated: 2016-08-23;doi:10.15155/3-00-0000-0000-0000-05924L;Abstract;Sisaldab u 5000 eesti keele sagedasemat s\u00f5na koos kasutusn\u00e4idetega. Lisaks illustreerivad pildid, m\u00e4rks\u00f5nade h\u00e4\u00e4ldus (audiofailid). M\u00f5eldud eesk\u00e4tt A2- ja B1-keeleoskustasemega eesti keele \u00f5ppijatele.  Eraldi rakendus on eesti viipekeele - eesti \u00fcldkeele e-s\u00f5nastiku kasutajaliides (sisaldab videofaile). ",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "32290448-f663-58f6-b2a4-3c4b23a52d9c",
-    "notes": [
-        "Abstract",
-        "Sisaldab u 5000 eesti keele sagedasemat s\u00f5na koos kasutusn\u00e4idetega. Lisaks illustreerivad pildid, m\u00e4rks\u00f5nade h\u00e4\u00e4ldus (audiofailid). M\u00f5eldud eesk\u00e4tt A2- ja B1-keeleoskustasemega eesti keele \u00f5ppijatele.  Eraldi rakendus on eesti viipekeele - eesti \u00fcldkeele e-s\u00f5nastiku kasutajaliides (sisaldab videofaile). "
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:8922495"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele p\u00f5his\u00f5navara s\u00f5nastik",
-        "Basic Estonian Dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/3262045f-b6e5-5984-ab09-81f1083b4a60.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/3262045f-b6e5-5984-ab09-81f1083b4a60.json
deleted file mode 100644
index d7004d1d..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/3262045f-b6e5-5984-ab09-81f1083b4a60.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-07315L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14673670",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14673670"
-    ],
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:14673670;2019-04-15T17:25:45Z;ESTDOI;ESTDOI.KEEL;Vox populi - tekstide helindaja;Hein, Indrek;Center of Estonian Language Resources;2018;Issued: 2018-04-13;Updated: 2019-01-08;doi:10.15155/3-00-0000-0000-0000-07315L;Abstract;Vox populi e rahva h\u00e4\u00e4l koosneb kahest komponendist: tekstide helindajast (siinne leht) ja h\u00e4\u00e4lduss\u00f5nastikust koos keelereegleid realiseerivate programmikestega. Nende kahe koost\u00f6\u00f6s ja Eesti Keele Instituudi k\u00f5nes\u00fcnteesi kaasates saab teie saadetud tekstifailist l\u00f5pptulemusena s\u00fcnteesh\u00e4\u00e4lega audiofail.\nLitsents: http://www.eki.ee/eki/litsents.html.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3262045f-b6e5-5984-ab09-81f1083b4a60",
-    "notes": [
-        "Abstract",
-        "Vox populi e rahva h\u00e4\u00e4l koosneb kahest komponendist: tekstide helindajast (siinne leht) ja h\u00e4\u00e4lduss\u00f5nastikust koos keelereegleid realiseerivate programmikestega. Nende kahe koost\u00f6\u00f6s ja Eesti Keele Instituudi k\u00f5nes\u00fcnteesi kaasates saab teie saadetud tekstifailist l\u00f5pptulemusena s\u00fcnteesh\u00e4\u00e4lega audiofail.\nLitsents: http://www.eki.ee/eki/litsents.html."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14673670"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Vox populi - tekstide helindaja"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/32709700-bf0d-5526-a0be-ff88259bbe24.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/32709700-bf0d-5526-a0be-ff88259bbe24.json
deleted file mode 100644
index d951e31e..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/32709700-bf0d-5526-a0be-ff88259bbe24.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-0576DL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:8512253",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:8512253"
-    ],
-    "PublicationTimestamp": "2019-01-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Pajupuu, Hille"
-    ],
-    "fulltext": "oai:oai.datacite.org:8512253;2019-04-16T17:36:42Z;ESTDOI;ESTDOI.KEEL;Emotsioonidetektor;Emotion detector;Pajupuu, Hille;Center of Estonian Language Resources;2015;Issued: 2015-05-18;Updated: 2019-01-07;doi:10.15155/3-00-0000-0000-0000-0576DL;Abstract;Vahend kirjaliku teksti l\u00f5ikude positiivsuse, negatiivsuse ja neutraalsuse tuvastamiseks.  T\u00f6\u00f6tab teenusena EKI serveris.;Abstract;The Emotion Detector allows to identify the positivity, negativity and neutrality in paragraphs of written text.  Service at IEL.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "32709700-bf0d-5526-a0be-ff88259bbe24",
-    "notes": [
-        "Abstract",
-        "Vahend kirjaliku teksti l\u00f5ikude positiivsuse, negatiivsuse ja neutraalsuse tuvastamiseks.  T\u00f6\u00f6tab teenusena EKI serveris.",
-        "Abstract",
-        "The Emotion Detector allows to identify the positivity, negativity and neutrality in paragraphs of written text.  Service at IEL."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:8512253"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Emotsioonidetektor",
-        "Emotion detector"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/32e04ea1-0c52-50a5-a3ab-2e955535ea27.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/32e04ea1-0c52-50a5-a3ab-2e955535ea27.json
deleted file mode 100644
index f7cbf163..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/32e04ea1-0c52-50a5-a3ab-2e955535ea27.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00128L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9845129",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9845129"
-    ],
-    "PublicationTimestamp": "2016-12-02T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Lippus, P\u00e4rtel"
-    ],
-    "fulltext": "oai:oai.datacite.org:9845129;2018-12-08T02:34:43Z;ESTDOI;ESTDOI.KEEL;P\u00f5hjatuule ja p\u00e4ikese korpus v.1.0.3;Estonian North Wind and the Sun Corpus v.1.0.3;Lippus, P\u00e4rtel;Center of Estonian Language Resources;2016;Issued: 2016-12-02;Updated: 2016-12-02;doi:10.15155/1-00-0000-0000-0000-00128L;Abstract;Recordings of the tale \u201cP\u00f5hjatuul ja p\u00e4ike\u201d (North Wind and the Sun) read by the same speakers who participated in the Phonetic Corpus of Estonian Spontaneous Speech. Most of the speakers read the text two times. The text is annotated using Praat TextGrids: words in standard orthography and phonemes in SAMPA.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "32e04ea1-0c52-50a5-a3ab-2e955535ea27",
-    "notes": [
-        "Abstract",
-        "Recordings of the tale \u201cP\u00f5hjatuul ja p\u00e4ike\u201d (North Wind and the Sun) read by the same speakers who participated in the Phonetic Corpus of Estonian Spontaneous Speech. Most of the speakers read the text two times. The text is annotated using Praat TextGrids: words in standard orthography and phonemes in SAMPA."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9845129"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "P\u00f5hjatuule ja p\u00e4ikese korpus v.1.0.3",
-        "Estonian North Wind and the Sun Corpus v.1.0.3"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/32eab823-9a7a-5faf-9579-c1e5c5fe8ee7.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/32eab823-9a7a-5faf-9579-c1e5c5fe8ee7.json
deleted file mode 100644
index c648232b..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/32eab823-9a7a-5faf-9579-c1e5c5fe8ee7.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00167L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17767577",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17767577"
-    ],
-    "PublicationTimestamp": "2018-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "M\u00fc\u00fcrisep, Kaili",
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:17767577;2019-02-15T04:30:39Z;ESTDOI;ESTDOI.KEEL;UD Estonian ver.2.3;Muischnek, Kadri;M\u00fc\u00fcrisep, Kaili;Center of Estonian Language Resources;2018;Issued: 2018-12-10;Updated: 2018-12-11;doi:10.15155/1-00-0000-0000-0000-00167L;Abstract;UD Estonian is a converted version of the Estonian Dependency Treebank (EDT), originally annotated in the Constraint Grammar (CG) annotation scheme, and consisting of genres of fiction, newspaper texts and scientific texts. The treebank contains 30,723 trees, 434,245 tokens.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "32eab823-9a7a-5faf-9579-c1e5c5fe8ee7",
-    "notes": [
-        "Abstract",
-        "UD Estonian is a converted version of the Estonian Dependency Treebank (EDT), originally annotated in the Constraint Grammar (CG) annotation scheme, and consisting of genres of fiction, newspaper texts and scientific texts. The treebank contains 30,723 trees, 434,245 tokens."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17767577"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "UD Estonian ver.2.3"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/33302721-aea7-5fc9-90dc-7b42aba80a62.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/33302721-aea7-5fc9-90dc-7b42aba80a62.json
deleted file mode 100644
index 7c1207ac..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/33302721-aea7-5fc9-90dc-7b42aba80a62.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-0421AL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:6915503",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:6915503"
-    ],
-    "PublicationTimestamp": "2015-10-28T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Piits, Liisi"
-    ],
-    "fulltext": "oai:oai.datacite.org:6915503;2019-04-23T16:30:39Z;ESTDOI;ESTDOI.KEEL;K\u00f5nes\u00fcnteesi k\u00f5nekorpus Eva;Piits, Liisi;Center of Estonian Language Resources;2015;Issued: 2015-10-28;Updated: 2015-10-28;doi:10.15155/3-00-0000-0000-0000-0421AL;Abstract;Tulemust on kasutatud eestikeelsete s\u00fcnteesh\u00e4\u00e4lte loomiseks, korpus on k\u00f5nes\u00fcnteesi akustiliseks baasiks.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "33302721-aea7-5fc9-90dc-7b42aba80a62",
-    "notes": [
-        "Abstract",
-        "Tulemust on kasutatud eestikeelsete s\u00fcnteesh\u00e4\u00e4lte loomiseks, korpus on k\u00f5nes\u00fcnteesi akustiliseks baasiks."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:6915503"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "K\u00f5nes\u00fcnteesi k\u00f5nekorpus Eva"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/345a3d3b-381f-5f5c-8600-6a5096cb73f1.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/345a3d3b-381f-5f5c-8600-6a5096cb73f1.json
deleted file mode 100644
index 5951d5bf..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/345a3d3b-381f-5f5c-8600-6a5096cb73f1.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-079CDL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17602310",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17602310"
-    ],
-    "PublicationTimestamp": "2018-11-23T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Raadik, Maire"
-    ],
-    "fulltext": "oai:oai.datacite.org:17602310;2019-02-02T21:32:44Z;ESTDOI;ESTDOI.KEEL;Eesti \u00f5igekeelsuss\u00f5naraamatu \u00d5S 2018 veebiversioon;Online Dictionary of Standard Estonian \u00d5S 2018 ;Raadik, Maire;Center of Estonian Language Resources;2018;Issued: 2018-11-23;Updated: 2018-11-23;doi:10.15155/3-00-0000-0000-0000-079CDL;Abstract;Kajastab eesti kirjakeele normi.;Abstract;\u00d5S 2018 is a normative dictionary of modern standard Estonian. It shows the standardized spelling, pronunciation and inflection of words and gives recommendations on semantics and syntax. The dictionary has annexes on  abbreviations, geographical names and pronunciation of foreign names.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "345a3d3b-381f-5f5c-8600-6a5096cb73f1",
-    "notes": [
-        "Abstract",
-        "Kajastab eesti kirjakeele normi.",
-        "Abstract",
-        "\u00d5S 2018 is a normative dictionary of modern standard Estonian. It shows the standardized spelling, pronunciation and inflection of words and gives recommendations on semantics and syntax. The dictionary has annexes on  abbreviations, geographical names and pronunciation of foreign names."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17602310"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti \u00f5igekeelsuss\u00f5naraamatu \u00d5S 2018 veebiversioon",
-        "Online Dictionary of Standard Estonian \u00d5S 2018 "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/35c6d313-3a6b-5601-a98f-5c00c551abbc.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/35c6d313-3a6b-5601-a98f-5c00c551abbc.json
deleted file mode 100644
index 66e1282f..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/35c6d313-3a6b-5601-a98f-5c00c551abbc.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0011CL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:7802324",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:7802324"
-    ],
-    "PublicationTimestamp": "2016-03-10T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Vare, Kadri",
-        "Orav, Heili"
-    ],
-    "fulltext": "oai:oai.datacite.org:7802324;2019-02-14T11:32:07Z;ESTDOI;ESTDOI.KEEL;Eesti Wordnet (kb73-VIIMANE);Estonian Wordnet (kb73-LAST);Orav, Heili;Vare, Kadri;Center of Estonian Language Resources;2014;Issued: 2014-03-21;Updated: 2016-03-10;doi:10.15155/1-00-0000-0000-0000-0011CL;Abstract; Eesti Wordnetis (versioon 73) on praeguse seisuga (m\u00e4rts 2016) 77 878 m\u00f5istet, milles s\u00f5nu 106 202, semantilisi suhteid 248 996 ja seoseid Princetoni Wordnetiga (1.5) 112 283.  K\u00f5ik m\u00f5isted on varustatud v\u00e4hemalt \u00fche keelesisese suhtega ja v\u00e4hemalt \u00fche ILI-suhtega.;Abstract;The atom of a wordnet-type thesaurus is a synonym set (also called a synset), which is a set containing all the synonymous words or multi-word units that express the same concept. All words in a synset belong into the same part of speech.\n\nTHIS IS THE NEWEST VERSION",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "35c6d313-3a6b-5601-a98f-5c00c551abbc",
-    "notes": [
-        "Abstract",
-        " Eesti Wordnetis (versioon 73) on praeguse seisuga (m\u00e4rts 2016) 77 878 m\u00f5istet, milles s\u00f5nu 106 202, semantilisi suhteid 248 996 ja seoseid Princetoni Wordnetiga (1.5) 112 283.  K\u00f5ik m\u00f5isted on varustatud v\u00e4hemalt \u00fche keelesisese suhtega ja v\u00e4hemalt \u00fche ILI-suhtega.",
-        "Abstract",
-        "The atom of a wordnet-type thesaurus is a synonym set (also called a synset), which is a set containing all the synonymous words or multi-word units that express the same concept. All words in a synset belong into the same part of speech.\n\nTHIS IS THE NEWEST VERSION"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:7802324"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti Wordnet (kb73-VIIMANE)",
-        "Estonian Wordnet (kb73-LAST)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/36cbaab6-8628-55ab-a3ba-fbf961f96033.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/36cbaab6-8628-55ab-a3ba-fbf961f96033.json
deleted file mode 100644
index 826fc916..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/36cbaab6-8628-55ab-a3ba-fbf961f96033.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-0006EL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:6895482",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:6895482"
-    ],
-    "PublicationTimestamp": "2015-08-25T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Meister, Einar"
-    ],
-    "fulltext": "oai:oai.datacite.org:6895482;2019-03-29T11:01:05Z;ESTDOI;ESTDOI.KEEL;Corpus of Adolescent Speech;Meister, Einar;Center of Estonian Language Resources;2015;Issued: 2015-08-25;Updated: 2015-08-25;doi:10.15155/9-00-0000-0000-0000-0006EL;Abstract;Includes speech recordings of 300 native Estonian subjects in the age range from 9 to 18 years",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "36cbaab6-8628-55ab-a3ba-fbf961f96033",
-    "notes": [
-        "Abstract",
-        "Includes speech recordings of 300 native Estonian subjects in the age range from 9 to 18 years"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:6895482"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus of Adolescent Speech"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/376f936b-c786-5ad6-b6b2-fcc1cee0999e.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/376f936b-c786-5ad6-b6b2-fcc1cee0999e.json
deleted file mode 100644
index 8e1ec928..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/376f936b-c786-5ad6-b6b2-fcc1cee0999e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05B5AL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9352885",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9352885"
-    ],
-    "PublicationTimestamp": "2016-10-19T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Kallas, Jelena",
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:9352885;2019-02-19T05:00:44Z;ESTDOI;ESTDOI.KEEL;Vene-eesti s\u00f5naraamat;Russian-Estonian Dictionary;Hein, Indrek;Kallas, Jelena;Center of Estonian Language Resources;2016;Issued: 2016-10-19;Updated: 2016-10-19;doi:10.15155/3-00-0000-0000-0000-05B5AL;Abstract;1984\u20131994 ilmunud 4-k\u00f6itelise \u201eVene-eesti s\u00f5naraamatu\u201c parandatud versioon. Sisaldab \u00fcldkeele k\u00f5rval hulganisti oskuss\u00f5navara ja fraseoloogiat.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "376f936b-c786-5ad6-b6b2-fcc1cee0999e",
-    "notes": [
-        "Abstract",
-        "1984\u20131994 ilmunud 4-k\u00f6itelise \u201eVene-eesti s\u00f5naraamatu\u201c parandatud versioon. Sisaldab \u00fcldkeele k\u00f5rval hulganisti oskuss\u00f5navara ja fraseoloogiat."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9352885"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Vene-eesti s\u00f5naraamat",
-        "Russian-Estonian Dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/3951ffae-d802-5f2e-8b98-65bbe39eae37.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/3951ffae-d802-5f2e-8b98-65bbe39eae37.json
deleted file mode 100644
index f61c1c66..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/3951ffae-d802-5f2e-8b98-65bbe39eae37.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/TY.000E",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:4597367",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:4597367"
-    ],
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laur, Sven"
-    ],
-    "fulltext": "oai:oai.datacite.org:4597367;2019-03-23T15:02:43Z;ESTDOI;ESTDOI.KEEL;Estonian NER corpus;Laur, Sven;Center of Estonian Language Resources;2013;doi:10.15155/TY.000E",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3951ffae-d802-5f2e-8b98-65bbe39eae37",
-    "oai_identifier": [
-        "oai:oai.datacite.org:4597367"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Estonian NER corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/398c5a7f-7934-5a2f-8c4b-23b9fa4ec06f.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/398c5a7f-7934-5a2f-8c4b-23b9fa4ec06f.json
deleted file mode 100644
index 681d226b..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/398c5a7f-7934-5a2f-8c4b-23b9fa4ec06f.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-079D6L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17926656",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17926656"
-    ],
-    "PublicationTimestamp": "2019-01-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Pajupuu, Hille"
-    ],
-    "fulltext": "oai:oai.datacite.org:17926656;2019-04-12T17:25:46Z;ESTDOI;ESTDOI.KEEL;Emotsioonidetektor Google Chrome'i laiendusena;Emotion Detector as Chrome Extension;Pajupuu, Hille;Center of Estonian Language Resources;2018;Issued: 2018-12-22;Updated: 2019-01-07;doi:10.15155/3-00-0000-0000-0000-079D6L;Abstract;Emotsioonidetektoriga saab hinnata veebikirjutise emotsionaalset m\u00f5ju. Selleks tuleb esmalt emotsioonidetektor installeerida, seej\u00e4rel v\u00e4lja valida tekst ja klikata ikoonile. Detektor annab tekstile \u00fcldhinnangu: neutraalne, positiivne, negatiivne v\u00f5i vastuoluline. Tekstis m\u00e4rgitakse \u00e4ra emotsioonitaju m\u00f5jutavad v\u00f5tmes\u00f5nad ning ortograafiliste tekstil\u00f5ikude emotsionaalsus (lilla - negatiivne, roheline - positiivne, kollane - vastuoluline, hall - ekstreemne).",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "398c5a7f-7934-5a2f-8c4b-23b9fa4ec06f",
-    "notes": [
-        "Abstract",
-        "Emotsioonidetektoriga saab hinnata veebikirjutise emotsionaalset m\u00f5ju. Selleks tuleb esmalt emotsioonidetektor installeerida, seej\u00e4rel v\u00e4lja valida tekst ja klikata ikoonile. Detektor annab tekstile \u00fcldhinnangu: neutraalne, positiivne, negatiivne v\u00f5i vastuoluline. Tekstis m\u00e4rgitakse \u00e4ra emotsioonitaju m\u00f5jutavad v\u00f5tmes\u00f5nad ning ortograafiliste tekstil\u00f5ikude emotsionaalsus (lilla - negatiivne, roheline - positiivne, kollane - vastuoluline, hall - ekstreemne)."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17926656"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Emotsioonidetektor Google Chrome'i laiendusena",
-        "Emotion Detector as Chrome Extension"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/39cc2338-8d0c-5e40-919f-7a7a2c48d625.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/39cc2338-8d0c-5e40-919f-7a7a2c48d625.json
deleted file mode 100644
index 2fe1ff6e..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/39cc2338-8d0c-5e40-919f-7a7a2c48d625.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0007EL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5756862",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5756862"
-    ],
-    "PublicationTimestamp": "2015-05-22T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:5756862;2019-01-30T18:00:41Z;ESTDOI;ESTDOI.KEEL;Eesti ilukirjanduse korpus;Corpus of Estonian fiction;Muischnek, Kadri;Center of Estonian Language Resources;2013;Issued: 2013-01-07;Updated: 2015-05-22;doi:10.15155/1-00-0000-0000-0000-0007EL;Abstract;Eesti ilukirjanduse korpus alates 1990. Kokku 5,6 miljonit s\u00f5na.;Abstract;A text corpus containing Estonian fiction texts from 1990. onwards, 5.6 million words.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "39cc2338-8d0c-5e40-919f-7a7a2c48d625",
-    "notes": [
-        "Abstract",
-        "Eesti ilukirjanduse korpus alates 1990. Kokku 5,6 miljonit s\u00f5na.",
-        "Abstract",
-        "A text corpus containing Estonian fiction texts from 1990. onwards, 5.6 million words."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5756862"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti ilukirjanduse korpus",
-        "Corpus of Estonian fiction"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/3bc072cb-4c46-56fe-bd5f-e799a313be97.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/3bc072cb-4c46-56fe-bd5f-e799a313be97.json
deleted file mode 100644
index 8cce1c48..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/3bc072cb-4c46-56fe-bd5f-e799a313be97.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0016FL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17940280",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17940280"
-    ],
-    "PublicationTimestamp": "2019-01-02T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:17940280;2019-01-31T08:01:32Z;ESTDOI;ESTDOI.KEEL;Eesti keele Kitsenduste Grammatika reeglid 1.0;Muischnek, Kadri;Center of Estonian Language Resources;2019;Issued: 2019-01-02;Updated: 2019-01-02;doi:10.15155/1-00-0000-0000-0000-0016FL;Abstract;S\u00fcntaktilise anal\u00fc\u00fcsi jaoks on vajalik\n\n eesti keele morfoloogiline anal\u00fcsaator, nt Vabamorf: https://github.com/Filosoft/vabamorf/blob/master/doc/readme.html Et Vabamorfi automaatselt kasutada, on vaja failis test.sh paika panna installeeritud Vabamorfi programmi ja s\u00f5nastiku teed.\nVISL CG3 Kitsenduste Grammatika anal\u00fcsaator: http://beta.visl.sdu.dk/constraint_grammar.html. Grammatikad \u00fchilduvad VISL CG3 versiooniga 0.9.9.10379.\nReeglite failid ja skriptid moodulite \u00fchendamiseks.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3bc072cb-4c46-56fe-bd5f-e799a313be97",
-    "notes": [
-        "Abstract",
-        "S\u00fcntaktilise anal\u00fc\u00fcsi jaoks on vajalik\n\n eesti keele morfoloogiline anal\u00fcsaator, nt Vabamorf: https://github.com/Filosoft/vabamorf/blob/master/doc/readme.html Et Vabamorfi automaatselt kasutada, on vaja failis test.sh paika panna installeeritud Vabamorfi programmi ja s\u00f5nastiku teed.\nVISL CG3 Kitsenduste Grammatika anal\u00fcsaator: http://beta.visl.sdu.dk/constraint_grammar.html. Grammatikad \u00fchilduvad VISL CG3 versiooniga 0.9.9.10379.\nReeglite failid ja skriptid moodulite \u00fchendamiseks."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17940280"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele Kitsenduste Grammatika reeglid 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/3c14c307-590e-5d6a-af03-d6ad458e5658.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/3c14c307-590e-5d6a-af03-d6ad458e5658.json
deleted file mode 100644
index 4fd75a44..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/3c14c307-590e-5d6a-af03-d6ad458e5658.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00073L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5757468",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5757468"
-    ],
-    "PublicationTimestamp": "2015-05-22T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laur, Sven"
-    ],
-    "fulltext": "oai:oai.datacite.org:5757468;2019-04-17T17:27:44Z;ESTDOI;ESTDOI.KEEL;Nime\u00fcksuste korpus;Estonian NER corpus;Laur, Sven;Center of Estonian Language Resources;2013;Issued: 2013-04-24;Updated: 2015-05-22;doi:10.15155/1-00-0000-0000-0000-00073L;Abstract;Corpus containing morphologically analyzed articles with named entity annotations (persons, organizations, locations) in BOI format.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3c14c307-590e-5d6a-af03-d6ad458e5658",
-    "notes": [
-        "Abstract",
-        "Corpus containing morphologically analyzed articles with named entity annotations (persons, organizations, locations) in BOI format."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5757468"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Nime\u00fcksuste korpus",
-        "Estonian NER corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/3c21cd11-d53a-5856-a2bb-e8de1cf3ec51.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/3c21cd11-d53a-5856-a2bb-e8de1cf3ec51.json
deleted file mode 100644
index b93ba21a..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/3c21cd11-d53a-5856-a2bb-e8de1cf3ec51.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0019FL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17986401",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17986401"
-    ],
-    "PublicationTimestamp": "2019-01-11T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Iva, Sulev"
-    ],
-    "fulltext": "oai:oai.datacite.org:17986401;2019-04-01T19:32:40Z;ESTDOI;ESTDOI.KEEL;V\u00f5ru - eesti paralleelkorpus;Iva, Sulev;Center of Estonian Language Resources;2019;Issued: 2019-01-11;Updated: 2019-01-11;doi:10.15155/1-00-0000-0000-0000-0019FL;Abstract;Paralleelkorpuse tekstid on\n\trida-realt k\u00e4sitsi joondatud,\n\tiga terviktekst eraldi failis,\n\tiga keelefaili keel j\u00e4rjekorranumbri taga punktiga eraldatult,\n\t\u00fche keele liit- ja teise lihtlause puhul m\u00f5lema keele laused \u00fchel real,\n\tt\u00f5lke puudumisel rida #-ga v\u00e4lja kommenteeritult j\u00e4ttes paralleelfaili t\u00fchja #-ga algava reaga,\n\tutf8 vormingus.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3c21cd11-d53a-5856-a2bb-e8de1cf3ec51",
-    "notes": [
-        "Abstract",
-        "Paralleelkorpuse tekstid on\n\trida-realt k\u00e4sitsi joondatud,\n\tiga terviktekst eraldi failis,\n\tiga keelefaili keel j\u00e4rjekorranumbri taga punktiga eraldatult,\n\t\u00fche keele liit- ja teise lihtlause puhul m\u00f5lema keele laused \u00fchel real,\n\tt\u00f5lke puudumisel rida #-ga v\u00e4lja kommenteeritult j\u00e4ttes paralleelfaili t\u00fchja #-ga algava reaga,\n\tutf8 vormingus."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17986401"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "V\u00f5ru - eesti paralleelkorpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/3cd2a88b-1d94-5349-ac22-8d14302dd13e.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/3cd2a88b-1d94-5349-ac22-8d14302dd13e.json
deleted file mode 100644
index 67eef914..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/3cd2a88b-1d94-5349-ac22-8d14302dd13e.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-000A8L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17972099",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17972099"
-    ],
-    "PublicationTimestamp": "2019-01-09T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Mellik, Andres",
-        "K\u00fcbar, Lea"
-    ],
-    "fulltext": "oai:oai.datacite.org:17972099;2019-03-27T07:32:43Z;ESTDOI;ESTDOI.KEEL;K\u00f5nes\u00e4mplid k\u00f5neravi.ee jaoks;K\u00fcbar, Lea;Mellik, Andres;Center of Estonian Language Resources;2019;Issued: 2019-01-09;Updated: 2019-01-09;doi:10.15155/9-00-0000-0000-0000-000A8L;Abstract;Logopeedi\u200b \u200bvastuv\u00f5tul\u200b \u200bk\u00e4inud\u200b \u200bpatsientide\u200b \u200bteraapia\u200b \u200bk\u00e4igus lindistatud k\u00f5nes\u00e4mplid.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3cd2a88b-1d94-5349-ac22-8d14302dd13e",
-    "notes": [
-        "Abstract",
-        "Logopeedi\u200b \u200bvastuv\u00f5tul\u200b \u200bk\u00e4inud\u200b \u200bpatsientide\u200b \u200bteraapia\u200b \u200bk\u00e4igus lindistatud k\u00f5nes\u00e4mplid."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17972099"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "K\u00f5nes\u00e4mplid k\u00f5neravi.ee jaoks"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/3d1ae8e9-60ab-558d-905a-3c7b452f5460.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/3d1ae8e9-60ab-558d-905a-3c7b452f5460.json
deleted file mode 100644
index 944e013c..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/3d1ae8e9-60ab-558d-905a-3c7b452f5460.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-0017FL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:19659088",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:19659088"
-    ],
-    "PublicationTimestamp": "2012-07-09T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:19659088;2019-04-16T17:36:45Z;ESTDOI;ESTDOI.KEEL;Estonian Reference Corpus;Muischnek, Kadri;Center of Estonian Language Resources;2011;Issued: 2011-12-31;Updated: 2012-07-09;doi:10.15155/9-00-0000-0000-0000-0017FL;Abstract;The Estonian reference Corpus is a selection of electronic research material that contains written Estonian from 1990 onwards. Raw text corpus. The corpus represents the written language and contains 75% newspaper texts, in lesser extent also fiction, science and legislation texts.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3d1ae8e9-60ab-558d-905a-3c7b452f5460",
-    "notes": [
-        "Abstract",
-        "The Estonian reference Corpus is a selection of electronic research material that contains written Estonian from 1990 onwards. Raw text corpus. The corpus represents the written language and contains 75% newspaper texts, in lesser extent also fiction, science and legislation texts."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:19659088"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Estonian Reference Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/3d586cf3-9cb4-5114-8795-7d319bea5ba4.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/3d586cf3-9cb4-5114-8795-7d319bea5ba4.json
deleted file mode 100644
index c36a8741..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/3d586cf3-9cb4-5114-8795-7d319bea5ba4.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-0633CL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10304072",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10304072"
-    ],
-    "PublicationTimestamp": "2017-02-16T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Langemets, Margit"
-    ],
-    "fulltext": "oai:oai.datacite.org:10304072;2019-02-18T18:25:41Z;ESTDOI;ESTDOI.KEEL;Liivi-saksa s\u00f5naraamat;The Livonian-German Dictionary;Langemets, Margit;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2017-02-16;doi:10.15155/3-00-0000-0000-0000-0633CL;Abstract;Sj\u00f6gren-Wiedemanni s\u00f5naraamatu liivi-saksa veebiversioon.;Abstract;An online Livonian\u2013German version of the dictionary by Sj\u00f6gren and Wiedemann.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3d586cf3-9cb4-5114-8795-7d319bea5ba4",
-    "notes": [
-        "Abstract",
-        "Sj\u00f6gren-Wiedemanni s\u00f5naraamatu liivi-saksa veebiversioon.",
-        "Abstract",
-        "An online Livonian\u2013German version of the dictionary by Sj\u00f6gren and Wiedemann."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10304072"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Liivi-saksa s\u00f5naraamat",
-        "The Livonian-German Dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/3e228af7-7123-5b4b-a868-7e735567c339.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/3e228af7-7123-5b4b-a868-7e735567c339.json
deleted file mode 100644
index 0ff4642d..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/3e228af7-7123-5b4b-a868-7e735567c339.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/FIL.000C",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:4597365",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:4597365"
-    ],
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:4597365;2018-12-11T04:02:43Z;ESTDOI;ESTDOI.KEEL;Estonian Frequency Dictionary;Muischnek, Kadri;Center of Estonian Language Resources;2013;doi:10.15155/FIL.000C",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "3e228af7-7123-5b4b-a868-7e735567c339",
-    "oai_identifier": [
-        "oai:oai.datacite.org:4597365"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Estonian Frequency Dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/40062f13-ca28-5f0f-bf89-0842ad8109c4.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/40062f13-ca28-5f0f-bf89-0842ad8109c4.json
deleted file mode 100644
index e310297b..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/40062f13-ca28-5f0f-bf89-0842ad8109c4.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0017BL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17945633",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17945633"
-    ],
-    "PublicationTimestamp": "2019-01-03T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:17945633;2019-02-03T03:31:51Z;ESTDOI;ESTDOI.KEEL;Sageduss\u00f5nastik 2.0;Estonian Frequency Dictionary ver. 2.0;Muischnek, Kadri;Center of Estonian Language Resources;2019;Issued: 2019-01-03;Updated: 2019-01-03;doi:10.15155/1-00-0000-0000-0000-0017BL;Abstract;Sagedusloend on koostatud statistilise \u00fchestajaga t3mesta morfoloogiliselt \u00fchestatud ning seej\u00e4rel reeglip\u00f5hise meetodiga j\u00e4rel\u00fchestatud Tasakaalus korpuse p\u00f5hjal. Korpuse koostisosadeks on: 5 miljonit s\u00f5na ajalehetekste, 5 miljonit s\u00f5na ilukirjandust, 5 miljonit s\u00f5na teadustekste.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "40062f13-ca28-5f0f-bf89-0842ad8109c4",
-    "notes": [
-        "Abstract",
-        "Sagedusloend on koostatud statistilise \u00fchestajaga t3mesta morfoloogiliselt \u00fchestatud ning seej\u00e4rel reeglip\u00f5hise meetodiga j\u00e4rel\u00fchestatud Tasakaalus korpuse p\u00f5hjal. Korpuse koostisosadeks on: 5 miljonit s\u00f5na ajalehetekste, 5 miljonit s\u00f5na ilukirjandust, 5 miljonit s\u00f5na teadustekste."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17945633"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Sageduss\u00f5nastik 2.0",
-        "Estonian Frequency Dictionary ver. 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/409c2a75-a1fa-5b7a-9c14-7b2df41bd887.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/409c2a75-a1fa-5b7a-9c14-7b2df41bd887.json
deleted file mode 100644
index 0cdd3668..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/409c2a75-a1fa-5b7a-9c14-7b2df41bd887.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06325L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10283398",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10283398"
-    ],
-    "PublicationTimestamp": "2017-01-26T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Viikberg, J\u00fcri"
-    ],
-    "fulltext": "oai:oai.datacite.org:10283398;2019-04-03T22:01:59Z;ESTDOI;ESTDOI.KEEL;Kihnu s\u00f5naraamat;Viikberg, J\u00fcri;Center of Estonian Language Resources;2017;Issued: 2017-01-26;Updated: 2017-01-26;doi:10.15155/3-00-0000-0000-0000-06325L;Abstract; \u201eKihnu s\u00f5naraamat\u201c h\u00f5lmab s\u00f5navara murdekeelest, mida k\u00f5neldakse Kihnus ja Manijal. Raamatusse on mahtunud enam kui 6000 s\u00f5na, lisaks veel valik isiku- ning kohanimesid. M\u00e4rks\u00f5nade hulka on valitud nii Kihnule iseloomulikke iidseid s\u00f5nu kui ka neid, mis on murdekeelde tulnud alles viimastel k\u00fcmnenditel. S\u00f5nade tarvitamist h\u00f5lbustavad lisatud p\u00f5hivormid ja n\u00e4itelaused nii kihnu kui ka kirjakeeles.\nS\u00f5naraamatu on koostanud Reene Leas, Reti K\u00f6nninge, Silvi Murulauk ja Ellen Niit ning toimetanud Karl Pajusalu ja J\u00fcri Viikberg.\nS\u00f5naraamat on m\u00f5eldud eelk\u00f5ige kihnlastele, kihnu keele \u00f5ppijatele ja kasutajatele, aga ka k\u00f5igile neile, kes tunnevad huvi selle erip\u00e4rase keele ja kultuuri vastu.\n\u201eKihnu s\u00f5naraamat\u201c lisandub Eesti Keele Instituudi v\u00e4ikeste murdes\u00f5nastike sarja, milles on juba ilmunud \u201eVanap\u00e4rase V\u00f5ru murde s\u00f5naraamat\u201c (2011), \u201eMulgi s\u00f5nastik\u201c (2013), \u201eHiiu s\u00f5naraamat\u201c (2015) ja \u201eIdamurde s\u00f5nastik\u201c (2016).\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "409c2a75-a1fa-5b7a-9c14-7b2df41bd887",
-    "notes": [
-        "Abstract",
-        " \u201eKihnu s\u00f5naraamat\u201c h\u00f5lmab s\u00f5navara murdekeelest, mida k\u00f5neldakse Kihnus ja Manijal. Raamatusse on mahtunud enam kui 6000 s\u00f5na, lisaks veel valik isiku- ning kohanimesid. M\u00e4rks\u00f5nade hulka on valitud nii Kihnule iseloomulikke iidseid s\u00f5nu kui ka neid, mis on murdekeelde tulnud alles viimastel k\u00fcmnenditel. S\u00f5nade tarvitamist h\u00f5lbustavad lisatud p\u00f5hivormid ja n\u00e4itelaused nii kihnu kui ka kirjakeeles.\nS\u00f5naraamatu on koostanud Reene Leas, Reti K\u00f6nninge, Silvi Murulauk ja Ellen Niit ning toimetanud Karl Pajusalu ja J\u00fcri Viikberg.\nS\u00f5naraamat on m\u00f5eldud eelk\u00f5ige kihnlastele, kihnu keele \u00f5ppijatele ja kasutajatele, aga ka k\u00f5igile neile, kes tunnevad huvi selle erip\u00e4rase keele ja kultuuri vastu.\n\u201eKihnu s\u00f5naraamat\u201c lisandub Eesti Keele Instituudi v\u00e4ikeste murdes\u00f5nastike sarja, milles on juba ilmunud \u201eVanap\u00e4rase V\u00f5ru murde s\u00f5naraamat\u201c (2011), \u201eMulgi s\u00f5nastik\u201c (2013), \u201eHiiu s\u00f5naraamat\u201c (2015) ja \u201eIdamurde s\u00f5nastik\u201c (2016).\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10283398"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Kihnu s\u00f5naraamat"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/409d228c-301b-588b-9866-af1289e07546.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/409d228c-301b-588b-9866-af1289e07546.json
deleted file mode 100644
index 0152aa8f..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/409d228c-301b-588b-9866-af1289e07546.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05AF0L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9310571",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9310571"
-    ],
-    "PublicationTimestamp": "2016-10-19T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Viikberg, J\u00fcri"
-    ],
-    "fulltext": "oai:oai.datacite.org:9310571;2019-02-02T04:32:01Z;ESTDOI;ESTDOI.KEEL;Alamsaksa laenud eesti keeles;Viikberg, J\u00fcri;Center of Estonian Language Resources;2016;Issued: 2016-10-19;Updated: 2016-10-19;doi:10.15155/3-00-0000-0000-0000-05AF0L;Abstract;Veebis\u00f5nastik, kust leiab eesti keelde laenatud ja sellesse p\u00fcsima j\u00e4\u00e4nud alamsaksa laene, mis suures osas p\u00e4rinevad ajavahemikust 13.\u201317. sajand. S\u00f5nastikus on 1150 kirja- ning murdekeelset s\u00f5na.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "409d228c-301b-588b-9866-af1289e07546",
-    "notes": [
-        "Abstract",
-        "Veebis\u00f5nastik, kust leiab eesti keelde laenatud ja sellesse p\u00fcsima j\u00e4\u00e4nud alamsaksa laene, mis suures osas p\u00e4rinevad ajavahemikust 13.\u201317. sajand. S\u00f5nastikus on 1150 kirja- ning murdekeelset s\u00f5na."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9310571"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Alamsaksa laenud eesti keeles"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/416c0ea5-65ce-563b-a8b7-badedfa64f58.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/416c0ea5-65ce-563b-a8b7-badedfa64f58.json
deleted file mode 100644
index a32b3533..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/416c0ea5-65ce-563b-a8b7-badedfa64f58.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06333L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10303928",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10303928"
-    ],
-    "PublicationTimestamp": "2017-01-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Mihkla, Meelis"
-    ],
-    "fulltext": "oai:oai.datacite.org:10303928;2019-04-23T10:32:44Z;ESTDOI;ESTDOI.KEEL;Tekstide helindaja ja heliraamatute genereerija;Mihkla, Meelis;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2017-01-31;doi:10.15155/3-00-0000-0000-0000-06333L;Abstract;Teisendab txt- ja html-formaadis tekstid helifailideks ja lisab ePub3 formaadis e-raamatule s\u00fcnteesk\u00f5nes kuulatavad audiofailid. Helindaja ja genereerija Vox Populi koosneb kahest komponendist \u2013 tekstide helindajast ja h\u00e4\u00e4lduss\u00f5nastikust. Nende kahe koost\u00f6\u00f6s ja Eest Keele Instituudi k\u00f5nes\u00fcnteesi kaasates saab kasutaja saadetud tekstifailist s\u00fcnteesh\u00e4\u00e4lega audiofail.\n\n\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "416c0ea5-65ce-563b-a8b7-badedfa64f58",
-    "notes": [
-        "Abstract",
-        "Teisendab txt- ja html-formaadis tekstid helifailideks ja lisab ePub3 formaadis e-raamatule s\u00fcnteesk\u00f5nes kuulatavad audiofailid. Helindaja ja genereerija Vox Populi koosneb kahest komponendist \u2013 tekstide helindajast ja h\u00e4\u00e4lduss\u00f5nastikust. Nende kahe koost\u00f6\u00f6s ja Eest Keele Instituudi k\u00f5nes\u00fcnteesi kaasates saab kasutaja saadetud tekstifailist s\u00fcnteesh\u00e4\u00e4lega audiofail.\n\n\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10303928"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Tekstide helindaja ja heliraamatute genereerija"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/41d0d0fd-775a-5c93-9d18-263c34c228ec.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/41d0d0fd-775a-5c93-9d18-263c34c228ec.json
deleted file mode 100644
index ba9f4479..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/41d0d0fd-775a-5c93-9d18-263c34c228ec.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0018EL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17962501",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17962501"
-    ],
-    "PublicationTimestamp": "2019-01-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Sirel, Raul"
-    ],
-    "fulltext": "oai:oai.datacite.org:17962501;2019-03-10T18:25:48Z;ESTDOI;ESTDOI.KEEL;TEXTA Toolkit;Sirel, Raul;Center of Estonian Language Resources;2019;Issued: 2019-01-07;Updated: 2019-01-07;doi:10.15155/1-00-0000-0000-0000-0018EL;Abstract;TEXTA Toolkit on eraldiseisev tarkvara, mis v\u00f5imaldab tekstikorpustest ekstraheerida korpuses esindatud valdkonnale omast oskuss\u00f5navara, koostada selle alusel m\u00f5istep\u00f5hiseid terminoloogilisi ressursse, tuvastada tekstidokumentidest m\u00f5istetele viitavaid tekstifragmente ning visualiseerida tulemusi andmestikus leiduvate andmev\u00e4ljade l\u00f5ikes. Valdkondliku terminikasutuse kirjeldamiseks kasutatakse tarkvara koosseisus erinevaid juhendamata masin\u00f5ppe meetodeid, sh tehisneurov\u00f5rkudel p\u00f5hinevaid loomuliku keele vektormudeleid.;Abstract;Terminology EXtraction and Text Analytics (TEXTA) Toolkit is a program that provides resources for analysing free text datasets. It includes the tools, which are necessary for the text analytics or solutions based on the latter. TEXTA enables fast searches and analyses from texts, to classify documents and extract information from them. The content of toolkit can be configured according to the needs of the customer and is accessible as a cloud service or installed to the customer\u2019s infrastructure. The toolkit contains the following applications: searcher, multiword expression miner, base lexicon miner, conceptualizer, grammar miner, classifier.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "41d0d0fd-775a-5c93-9d18-263c34c228ec",
-    "notes": [
-        "Abstract",
-        "TEXTA Toolkit on eraldiseisev tarkvara, mis v\u00f5imaldab tekstikorpustest ekstraheerida korpuses esindatud valdkonnale omast oskuss\u00f5navara, koostada selle alusel m\u00f5istep\u00f5hiseid terminoloogilisi ressursse, tuvastada tekstidokumentidest m\u00f5istetele viitavaid tekstifragmente ning visualiseerida tulemusi andmestikus leiduvate andmev\u00e4ljade l\u00f5ikes. Valdkondliku terminikasutuse kirjeldamiseks kasutatakse tarkvara koosseisus erinevaid juhendamata masin\u00f5ppe meetodeid, sh tehisneurov\u00f5rkudel p\u00f5hinevaid loomuliku keele vektormudeleid.",
-        "Abstract",
-        "Terminology EXtraction and Text Analytics (TEXTA) Toolkit is a program that provides resources for analysing free text datasets. It includes the tools, which are necessary for the text analytics or solutions based on the latter. TEXTA enables fast searches and analyses from texts, to classify documents and extract information from them. The content of toolkit can be configured according to the needs of the customer and is accessible as a cloud service or installed to the customer\u2019s infrastructure. The toolkit contains the following applications: searcher, multiword expression miner, base lexicon miner, conceptualizer, grammar miner, classifier."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17962501"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "TEXTA Toolkit"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/429b5cf5-1e9f-5c20-ab77-31abe30f65ca.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/429b5cf5-1e9f-5c20-ab77-31abe30f65ca.json
deleted file mode 100644
index 472dae1f..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/429b5cf5-1e9f-5c20-ab77-31abe30f65ca.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-07309L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14673192",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14673192"
-    ],
-    "PublicationTimestamp": "2018-04-13T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:14673192;2019-01-25T18:01:25Z;ESTDOI;ESTDOI.KEEL;V\u00f5\u00f5rnimede ja l\u00fchendite h\u00e4\u00e4lduss\u00f5nastiku andmebaas;Hein, Indrek;Center of Estonian Language Resources;2018;Issued: 2018-04-13;Updated: 2018-04-13;doi:10.15155/3-00-0000-0000-0000-07309L;Abstract;H\u00e4\u00e4lduss\u00f5nastik on m\u00f5eldud tekstis esinevate v\u00f5\u00f5rnimede, l\u00fchendite ja tundmatute s\u00f5nede teisendamiseks eestikeelse k\u00f5nes\u00fcntesaatori sisendile sobiva h\u00e4\u00e4lduse vormi. S\u00f5nastiku andmebaas on eksporditav, lihtsalt kasutatav ja hallatav eestikeelset teksti k\u00f5neks teisendavates rakendustes. \nLitsents: http://www.eki.ee/eki/litsents.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "429b5cf5-1e9f-5c20-ab77-31abe30f65ca",
-    "notes": [
-        "Abstract",
-        "H\u00e4\u00e4lduss\u00f5nastik on m\u00f5eldud tekstis esinevate v\u00f5\u00f5rnimede, l\u00fchendite ja tundmatute s\u00f5nede teisendamiseks eestikeelse k\u00f5nes\u00fcntesaatori sisendile sobiva h\u00e4\u00e4lduse vormi. S\u00f5nastiku andmebaas on eksporditav, lihtsalt kasutatav ja hallatav eestikeelset teksti k\u00f5neks teisendavates rakendustes. \nLitsents: http://www.eki.ee/eki/litsents.html"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14673192"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "V\u00f5\u00f5rnimede ja l\u00fchendite h\u00e4\u00e4lduss\u00f5nastiku andmebaas"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/42f46693-c068-54b9-a68f-4ab2b6585c79.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/42f46693-c068-54b9-a68f-4ab2b6585c79.json
deleted file mode 100644
index 9c3ecb63..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/42f46693-c068-54b9-a68f-4ab2b6585c79.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-0592BL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:8923004",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:8923004"
-    ],
-    "PublicationTimestamp": "2016-08-30T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Nurk, T\u00f5nis"
-    ],
-    "fulltext": "oai:oai.datacite.org:8923004;2019-02-27T18:25:40Z;ESTDOI;ESTDOI.KEEL;EKI terminibaaside s\u00fcsteem;Nurk, T\u00f5nis;Center of Estonian Language Resources;2015;Issued: 2015-05-08;Updated: 2016-08-30;doi:10.15155/3-00-0000-0000-0000-0592BL;Abstract;Terminology Management Software of IEL",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "42f46693-c068-54b9-a68f-4ab2b6585c79",
-    "notes": [
-        "Abstract",
-        "Terminology Management Software of IEL"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:8923004"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "EKI terminibaaside s\u00fcsteem"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/43544715-6199-5649-8085-bfcba70f5373.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/43544715-6199-5649-8085-bfcba70f5373.json
deleted file mode 100644
index edfb5d00..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/43544715-6199-5649-8085-bfcba70f5373.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-0668BL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10749632",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10749632"
-    ],
-    "PublicationTimestamp": "2017-04-11T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Soosaar, Sven-Erik"
-    ],
-    "fulltext": "oai:oai.datacite.org:10749632;2019-04-22T17:25:40Z;ESTDOI;ESTDOI.KEEL;Eesti-mari s\u00f5naraamat;Estonian-Mari Dictionary;Soosaar, Sven-Erik;Center of Estonian Language Resources;2017;Issued: 2017-04-03;Updated: 2017-04-11;doi:10.15155/3-00-0000-0000-0000-0668BL;Abstract;S\u00f5naraamat sisaldab umbes 9800 m\u00e4rks\u00f5na. S\u00f5naraamatu sihtgrupiks on mari keelest ja kultuurist huvitatud eestlased ning eesti keelt \u00f5ppivad marid. S\u00f5nastiku n\u00e4itelaused ja -fraasid on abiks nii keele\u00f5ppijatele kui ka t\u00f5lkijatele. Kuigi mari keelel on kaks kirjakeelt \u2013 niidumari keel ja m\u00e4emari keel \u2013, sisaldab s\u00f5naraamat vaid niidumari vasteid, sest enamasti peetakse mari keelest r\u00e4\u00e4kides silmas just niidumari keelt. S\u00f5naraamat on k\u00e4ttesaadav ainult elektrooniliselt. ",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "43544715-6199-5649-8085-bfcba70f5373",
-    "notes": [
-        "Abstract",
-        "S\u00f5naraamat sisaldab umbes 9800 m\u00e4rks\u00f5na. S\u00f5naraamatu sihtgrupiks on mari keelest ja kultuurist huvitatud eestlased ning eesti keelt \u00f5ppivad marid. S\u00f5nastiku n\u00e4itelaused ja -fraasid on abiks nii keele\u00f5ppijatele kui ka t\u00f5lkijatele. Kuigi mari keelel on kaks kirjakeelt \u2013 niidumari keel ja m\u00e4emari keel \u2013, sisaldab s\u00f5naraamat vaid niidumari vasteid, sest enamasti peetakse mari keelest r\u00e4\u00e4kides silmas just niidumari keelt. S\u00f5naraamat on k\u00e4ttesaadav ainult elektrooniliselt. "
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10749632"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti-mari s\u00f5naraamat",
-        "Estonian-Mari Dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4382d031-68b9-5839-b56e-80e761d42194.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4382d031-68b9-5839-b56e-80e761d42194.json
deleted file mode 100644
index ffa7b00a..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4382d031-68b9-5839-b56e-80e761d42194.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-000BAL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:18007420",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:18007420"
-    ],
-    "PublicationTimestamp": "2013-01-07T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:18007420;2019-04-18T17:36:46Z;ESTDOI;ESTDOI.KEEL;Corpus of Estonian newspaper texts D;Muischnek, Kadri;Center of Estonian Language Resources;2013;Issued: 2013-01-07;Updated: 2013-01-07;doi:10.15155/9-00-0000-0000-0000-000BAL;Abstract;Corpus of Estonian newspaper texts, 182 million words\nMarkup: TEI P5 XML\nEncoding: UTF8",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4382d031-68b9-5839-b56e-80e761d42194",
-    "notes": [
-        "Abstract",
-        "Corpus of Estonian newspaper texts, 182 million words\nMarkup: TEI P5 XML\nEncoding: UTF8"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:18007420"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus of Estonian newspaper texts D"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/43b36140-3c69-5452-9cf1-549fd38b0ecf.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/43b36140-3c69-5452-9cf1-549fd38b0ecf.json
deleted file mode 100644
index 4e3c1ed9..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/43b36140-3c69-5452-9cf1-549fd38b0ecf.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-064DFL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10344235",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10344235"
-    ],
-    "PublicationTimestamp": "2017-10-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek",
-        "Vare, Silvi"
-    ],
-    "fulltext": "oai:oai.datacite.org:10344235;2019-02-18T18:25:41Z;ESTDOI;ESTDOI.KEEL;Eesti keele s\u00f5napered - indeks;The Dictionary of Estonian Word Families \u2013 Index;Hein, Indrek;Vare, Silvi;Center of Estonian Language Resources;2017;Issued: 2017-02-07;Updated: 2017-10-31;doi:10.15155/3-00-0000-0000-0000-064DFL;Abstract;Indeks v\u00f5imaldab teada saada, kas otsitav s\u00f5na esineb s\u00f5naperede raamatus ning millis(t)es s\u00f5napere(de)s ja millises plokis ta t\u00e4psemalt asub. Otsida on v\u00f5imalik nii elektroonilise indeksi kaudu p\u00e4ringuaknas kui ka pereliikmete loenditest pdf-formaadis. Vajadusel on v\u00f5imalik s\u00f5na olemasolu kontrollida ka perepeade pdf-loendist.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "43b36140-3c69-5452-9cf1-549fd38b0ecf",
-    "notes": [
-        "Abstract",
-        "Indeks v\u00f5imaldab teada saada, kas otsitav s\u00f5na esineb s\u00f5naperede raamatus ning millis(t)es s\u00f5napere(de)s ja millises plokis ta t\u00e4psemalt asub. Otsida on v\u00f5imalik nii elektroonilise indeksi kaudu p\u00e4ringuaknas kui ka pereliikmete loenditest pdf-formaadis. Vajadusel on v\u00f5imalik s\u00f5na olemasolu kontrollida ka perepeade pdf-loendist."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10344235"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele s\u00f5napered - indeks",
-        "The Dictionary of Estonian Word Families \u2013 Index"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4526a99d-cade-523e-a459-ecf68acd8370.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4526a99d-cade-523e-a459-ecf68acd8370.json
deleted file mode 100644
index 5fb404d2..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4526a99d-cade-523e-a459-ecf68acd8370.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05B59L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9352884",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9352884"
-    ],
-    "PublicationTimestamp": "2017-03-03T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Viks, \u00dclle"
-    ],
-    "fulltext": "oai:oai.datacite.org:9352884;2019-04-17T17:25:41Z;ESTDOI;ESTDOI.KEEL;Norra-eesti s\u00f5naraamat;The Norwegian-Estonian Dictionary;Norsk-estisk ordbok;Viks, \u00dclle;Center of Estonian Language Resources;2016;Issued: 2016-10-26;Updated: 2017-03-03;doi:10.15155/3-00-0000-0000-0000-05B59L;Abstract;Sisaldab u 19 000 eesti ja 21 000 norra m\u00e4rks\u00f5na, millele on lisatud grammatilised andmed ja hulgaliselt n\u00e4iteid s\u00f5nade kasutamise kohta. Raamatus on ka l\u00fchi\u00fclevaated eesti ja norra keelest.\n\nTurid Farbregd, Sigrid Kangur, \u00dclle Viks. Norra-eesti : eesti-norra s\u00f5naraamat. Eesti Keele Sihtasutus. Tallinn 1998, 2. tr\u00fckk 2005 (3. tr\u00fckk ilmub 2013).\n\n;Abstract;Contains ca 19,000 Estonian and 21,000 Norwegian entry words with grammatical data and numerous usage examples.;Abstract;Dette er den f\u00f8rste toveis ordboka mellom norsk og estisk.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4526a99d-cade-523e-a459-ecf68acd8370",
-    "notes": [
-        "Abstract",
-        "Sisaldab u 19 000 eesti ja 21 000 norra m\u00e4rks\u00f5na, millele on lisatud grammatilised andmed ja hulgaliselt n\u00e4iteid s\u00f5nade kasutamise kohta. Raamatus on ka l\u00fchi\u00fclevaated eesti ja norra keelest.\n\nTurid Farbregd, Sigrid Kangur, \u00dclle Viks. Norra-eesti : eesti-norra s\u00f5naraamat. Eesti Keele Sihtasutus. Tallinn 1998, 2. tr\u00fckk 2005 (3. tr\u00fckk ilmub 2013).\n\n",
-        "Abstract",
-        "Contains ca 19,000 Estonian and 21,000 Norwegian entry words with grammatical data and numerous usage examples.",
-        "Abstract",
-        "Dette er den f\u00f8rste toveis ordboka mellom norsk og estisk."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9352884"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Norra-eesti s\u00f5naraamat",
-        "The Norwegian-Estonian Dictionary",
-        "Norsk-estisk ordbok"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/456e1493-65f5-5263-b3ed-9d56856a8550.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/456e1493-65f5-5263-b3ed-9d56856a8550.json
deleted file mode 100644
index 01f1e42f..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/456e1493-65f5-5263-b3ed-9d56856a8550.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00195L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17979316",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17979316"
-    ],
-    "PublicationTimestamp": "2019-01-10T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laur, Sven"
-    ],
-    "fulltext": "oai:oai.datacite.org:17979316;2019-02-22T09:31:26Z;ESTDOI;ESTDOI.KEEL;Faktituletaja Pythonis;Laur, Sven;Center of Estonian Language Resources;2019;Issued: 2019-01-10;Updated: 2019-01-10;doi:10.15155/1-00-0000-0000-0000-00195L;Abstract;Faktituletaja Pythoni komponent 7. m\u00e4rtsi 2013 seisuga. Integreeritud morfoanal\u00fc\u00fcsi kasutamiseks tuleb lisada bin kataloogi t3mesta binaar",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "456e1493-65f5-5263-b3ed-9d56856a8550",
-    "notes": [
-        "Abstract",
-        "Faktituletaja Pythoni komponent 7. m\u00e4rtsi 2013 seisuga. Integreeritud morfoanal\u00fc\u00fcsi kasutamiseks tuleb lisada bin kataloogi t3mesta binaar"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17979316"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Faktituletaja Pythonis"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/461bb866-8289-551b-a74b-2cd5accc03e8.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/461bb866-8289-551b-a74b-2cd5accc03e8.json
deleted file mode 100644
index 8dad33c7..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/461bb866-8289-551b-a74b-2cd5accc03e8.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-07004L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14277526",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14277526"
-    ],
-    "PublicationTimestamp": "2018-02-22T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Kallasmaa, Marja",
-        "P\u00e4ll, Peeter"
-    ],
-    "fulltext": "oai:oai.datacite.org:14277526;2019-04-16T17:36:46Z;ESTDOI;ESTDOI.KEEL;Eesti kohanimeraamat;Dictionary of Estonian Place Names;P\u00e4ll, Peeter;Kallasmaa, Marja;Center of Estonian Language Resources;2018;Issued: 2018-02-22;Updated: 2018-02-22;doi:10.15155/3-00-0000-0000-0000-07004L;Abstract;Et\u00fcmoloogiline s\u00f5naraamat, mis sisaldab Eesti k\u00f5ik ametlikud k\u00fclanimed ja valikuliselt teisi Eesti kohanimesid.\n;Abstract;Etymological dictionary containing all official village names of Estonia and selected group of other Estonian place names.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "461bb866-8289-551b-a74b-2cd5accc03e8",
-    "notes": [
-        "Abstract",
-        "Et\u00fcmoloogiline s\u00f5naraamat, mis sisaldab Eesti k\u00f5ik ametlikud k\u00fclanimed ja valikuliselt teisi Eesti kohanimesid.\n",
-        "Abstract",
-        "Etymological dictionary containing all official village names of Estonia and selected group of other Estonian place names."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14277526"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti kohanimeraamat",
-        "Dictionary of Estonian Place Names"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4698e4f1-be63-5688-a246-d0f9384e9f2e.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4698e4f1-be63-5688-a246-d0f9384e9f2e.json
deleted file mode 100644
index 3ea76a1b..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4698e4f1-be63-5688-a246-d0f9384e9f2e.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00138L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:12000827",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:12000827"
-    ],
-    "PublicationTimestamp": "2017-09-13T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Vare, Kadri",
-        "Orav, Heili"
-    ],
-    "fulltext": "oai:oai.datacite.org:12000827;2019-04-17T17:26:58Z;ESTDOI;ESTDOI.KEEL;Eesti Wordnet (2.0 beeta);Estonian Wordnet (2.0 beta);Orav, Heili;Vare, Kadri;Center of Estonian Language Resources;2014;Issued: 2014-03-21;Updated: 2017-09-13;doi:10.15155/1-00-0000-0000-0000-00138L;Abstract;Esimene XML versioon Eesti Wordnetist.;Abstract;The first version of EstWN in XML format.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4698e4f1-be63-5688-a246-d0f9384e9f2e",
-    "notes": [
-        "Abstract",
-        "Esimene XML versioon Eesti Wordnetist.",
-        "Abstract",
-        "The first version of EstWN in XML format."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:12000827"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti Wordnet (2.0 beeta)",
-        "Estonian Wordnet (2.0 beta)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/46e8fb62-67b1-57c3-aff9-f3e455c9d2b2.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/46e8fb62-67b1-57c3-aff9-f3e455c9d2b2.json
deleted file mode 100644
index 67e9919d..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/46e8fb62-67b1-57c3-aff9-f3e455c9d2b2.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0011BL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:6919408",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:6919408"
-    ],
-    "PublicationTimestamp": "2015-10-29T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Tuisk, Tuuli"
-    ],
-    "fulltext": "oai:oai.datacite.org:6919408;2019-03-22T20:32:00Z;ESTDOI;ESTDOI.KEEL;Tartu \u00dclikooli eesti murrete ja sugulaskeelte arhiiv;University of Tartu Archives of Estonian Dialects and Kindred Languages;Tuisk, Tuuli;Center of Estonian Language Resources;2015;Issued: 2015-10-29;Updated: 2015-10-29;doi:10.15155/1-00-0000-0000-0000-0011BL;Abstract;his collection of linguistic material is managed by the University of Tartu, Institute of Estonian and General Linguistics. The archives contain four types of materials: \n1) Sound recordings of Estonian dialects and Finno-Ugric languages, \n2) Unpublished manuscripts, including \n  - student report papers and thesis written at the Institute of Estonian and General Linguistics, \n  - transcriptions and written notes on Estonian and Finno-Ugric languages, \n3) Photos from field-work expedition and linguistic events, \n4) Video recordings.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "46e8fb62-67b1-57c3-aff9-f3e455c9d2b2",
-    "notes": [
-        "Abstract",
-        "his collection of linguistic material is managed by the University of Tartu, Institute of Estonian and General Linguistics. The archives contain four types of materials: \n1) Sound recordings of Estonian dialects and Finno-Ugric languages, \n2) Unpublished manuscripts, including \n  - student report papers and thesis written at the Institute of Estonian and General Linguistics, \n  - transcriptions and written notes on Estonian and Finno-Ugric languages, \n3) Photos from field-work expedition and linguistic events, \n4) Video recordings."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:6919408"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Tartu \u00dclikooli eesti murrete ja sugulaskeelte arhiiv",
-        "University of Tartu Archives of Estonian Dialects and Kindred Languages"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4705e364-847d-5d94-8c6a-8018905378bf.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4705e364-847d-5d94-8c6a-8018905378bf.json
deleted file mode 100644
index 19bb0aa5..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4705e364-847d-5d94-8c6a-8018905378bf.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06327L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10303585",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10303585"
-    ],
-    "PublicationTimestamp": "2017-01-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Ross, Kristiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:10303585;2019-02-20T23:01:47Z;ESTDOI;ESTDOI.KEEL;Eesti piiblit\u00f5lke ajalooline konkordants;Ross, Kristiina;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2017-01-31;doi:10.15155/3-00-0000-0000-0000-06327L;Abstract;Andmebaasi eesm\u00e4rk on pakkuda \u00fclevaadet vaimuliku eesti keele kujunemisloost 17. sajandil ja 18. sajandi alguses. Andmebaas sisaldab t\u00f5lketekste ja nende p\u00f5hjal koostatud s\u00f5nastikku ning v\u00f5imaldab (valminud osades) otsinguid a) autorite v\u00f5i tekstide kaupa, b) kindla piiblikoha j\u00e4rgi ning c) t\u00e4nap\u00e4evastatud m\u00e4rks\u00f5na j\u00e4rgi.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4705e364-847d-5d94-8c6a-8018905378bf",
-    "notes": [
-        "Abstract",
-        "Andmebaasi eesm\u00e4rk on pakkuda \u00fclevaadet vaimuliku eesti keele kujunemisloost 17. sajandil ja 18. sajandi alguses. Andmebaas sisaldab t\u00f5lketekste ja nende p\u00f5hjal koostatud s\u00f5nastikku ning v\u00f5imaldab (valminud osades) otsinguid a) autorite v\u00f5i tekstide kaupa, b) kindla piiblikoha j\u00e4rgi ning c) t\u00e4nap\u00e4evastatud m\u00e4rks\u00f5na j\u00e4rgi."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10303585"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti piiblit\u00f5lke ajalooline konkordants"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4716aa0f-ecc4-5fec-a8d9-2fb735c42893.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4716aa0f-ecc4-5fec-a8d9-2fb735c42893.json
deleted file mode 100644
index 1f9c9941..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4716aa0f-ecc4-5fec-a8d9-2fb735c42893.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00161L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:15726756",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:15726756"
-    ],
-    "PublicationTimestamp": "2018-07-31T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Karjus, Andres",
-        "Ehala, Martin"
-    ],
-    "fulltext": "oai:oai.datacite.org:15726756;2018-10-23T15:02:07Z;ESTDOI;ESTDOI.KEEL;Keelehoiakud Eesti keelekeskkondades 2015 andmestik;Linguistic attitudes in Estonia 2015 dataset;Karjus, Andres;Ehala, Martin;Center of Estonian Language Resources;2018;Issued: 2018-07-31;Updated: 2018-07-31;doi:10.15155/1-00-0000-0000-0000-00161L;Abstract;Tartu \u00dclikooli uurimisprojekti Eesti keele kestlikkus avatud maailmas (EKKAM) tellimusel 2015. aasta kevadel Eestis l\u00e4bi viidud keelehoiakuid puudutava k\u00fcsimustiku vastused. Demograafiliselt tasakaalustatud valimis on 1006 vastajat vanuses 15-74. K\u00fcsimused h\u00f5lmavad vastajate demograafilist infot, keeleoskust, igap\u00e4evaseid keelevalikuid, keelehoiakuid, keelepoliitilisi vaateid. K\u00fcsimustikule oli v\u00f5imalik vastata nii eesti kui vene keeles, vastavalt k\u00fcsitletava valikule (ankeedi valik on andmestikus salvestatud). Andmestikus on 200 tunnust, millest suurema osa moodustavad k\u00fcsimuste vastused, lisaks m\u00f5ned k\u00fcsimuste vastustest tuletatud tunnused. Andmestikuga kaasas on meta-andmete fail, kus on kirjeldatud tunnuste t\u00fc\u00fcbid ja k\u00fcsimused, samuti algsed ankeedid. Andmed on saadaval mitmes erinevas formaadis (sh csv tekstifail). Uurimist\u00f6\u00f6 on valminud Eesti Teadusagentuuri grandi IUT20-3 toel.;Abstract;Data from a questionnaire on linguistic attitudes carried out in Estonia in the spring of 2015, ordered by the Sustainability of Estonian in the Era of Globalisation research project of the University of Tartu. The demographically balanced sample consists of 1006 respondents aged 15-74. The questions cover the respondents' basic demographic information, their language proficiencies, daily language choices, linguistic attitudes and views on language politics. The respondents could choose either an Estonian or Russian version of the questionnaire (their choices are recorded in the dataset). The dataset consists of 200 variables, most of them being responses to the questions, along with some derived variables. The dataset comes with meta-data that describes the variables and lists the questionnaire questions and their English translations; the original questionnaires are available as well. The data are available in multiple formats (including plain text csv). This research was supported by the Estonian Research Council grant IUT20-3.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4716aa0f-ecc4-5fec-a8d9-2fb735c42893",
-    "notes": [
-        "Abstract",
-        "Tartu \u00dclikooli uurimisprojekti Eesti keele kestlikkus avatud maailmas (EKKAM) tellimusel 2015. aasta kevadel Eestis l\u00e4bi viidud keelehoiakuid puudutava k\u00fcsimustiku vastused. Demograafiliselt tasakaalustatud valimis on 1006 vastajat vanuses 15-74. K\u00fcsimused h\u00f5lmavad vastajate demograafilist infot, keeleoskust, igap\u00e4evaseid keelevalikuid, keelehoiakuid, keelepoliitilisi vaateid. K\u00fcsimustikule oli v\u00f5imalik vastata nii eesti kui vene keeles, vastavalt k\u00fcsitletava valikule (ankeedi valik on andmestikus salvestatud). Andmestikus on 200 tunnust, millest suurema osa moodustavad k\u00fcsimuste vastused, lisaks m\u00f5ned k\u00fcsimuste vastustest tuletatud tunnused. Andmestikuga kaasas on meta-andmete fail, kus on kirjeldatud tunnuste t\u00fc\u00fcbid ja k\u00fcsimused, samuti algsed ankeedid. Andmed on saadaval mitmes erinevas formaadis (sh csv tekstifail). Uurimist\u00f6\u00f6 on valminud Eesti Teadusagentuuri grandi IUT20-3 toel.",
-        "Abstract",
-        "Data from a questionnaire on linguistic attitudes carried out in Estonia in the spring of 2015, ordered by the Sustainability of Estonian in the Era of Globalisation research project of the University of Tartu. The demographically balanced sample consists of 1006 respondents aged 15-74. The questions cover the respondents' basic demographic information, their language proficiencies, daily language choices, linguistic attitudes and views on language politics. The respondents could choose either an Estonian or Russian version of the questionnaire (their choices are recorded in the dataset). The dataset consists of 200 variables, most of them being responses to the questions, along with some derived variables. The dataset comes with meta-data that describes the variables and lists the questionnaire questions and their English translations; the original questionnaires are available as well. The data are available in multiple formats (including plain text csv). This research was supported by the Estonian Research Council grant IUT20-3."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:15726756"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Keelehoiakud Eesti keelekeskkondades 2015 andmestik",
-        "Linguistic attitudes in Estonia 2015 dataset"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/480e8f81-8115-5cea-9a31-0aa00d433c2c.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/480e8f81-8115-5cea-9a31-0aa00d433c2c.json
deleted file mode 100644
index 987b5914..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/480e8f81-8115-5cea-9a31-0aa00d433c2c.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00086L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5755364",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5755364"
-    ],
-    "PublicationTimestamp": "2015-05-21T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Orav, Heili"
-    ],
-    "fulltext": "oai:oai.datacite.org:5755364;2019-02-01T21:31:59Z;ESTDOI;ESTDOI.KEEL;Estonian Wordnet (kb71-LAST);Orav, Heili;Center of Estonian Language Resources;2014;Issued: 2014-03-21;Updated: 2015-05-21;doi:10.15155/1-00-0000-0000-0000-00086L;Abstract;The atom of a wordnet-type thesaurus is a synonym set (also called a synset), which is a set containing all the synonymous words or multi-word units that express the same concept. All words in a synset belong into the same part of speech.\n\nTHIS IS THE NEWEST VERSION",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "480e8f81-8115-5cea-9a31-0aa00d433c2c",
-    "notes": [
-        "Abstract",
-        "The atom of a wordnet-type thesaurus is a synonym set (also called a synset), which is a set containing all the synonymous words or multi-word units that express the same concept. All words in a synset belong into the same part of speech.\n\nTHIS IS THE NEWEST VERSION"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5755364"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Estonian Wordnet (kb71-LAST)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/482032f4-711f-5ea2-b28f-537f5067442c.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/482032f4-711f-5ea2-b28f-537f5067442c.json
deleted file mode 100644
index dc46a482..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/482032f4-711f-5ea2-b28f-537f5067442c.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0015CL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14977543",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14977543"
-    ],
-    "PublicationTimestamp": "2018-05-04T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Orasmaa, Siim"
-    ],
-    "fulltext": "oai:oai.datacite.org:14977543;2019-04-02T23:32:06Z;ESTDOI;ESTDOI.KEEL;TimeML annotated corpus of Estonian newspaper articles;Orasmaa, Siim;Center of Estonian Language Resources;2018;Issued: 2018-04-13;Updated: 2018-05-04;doi:10.15155/1-00-0000-0000-0000-0015CL;Abstract;Estonian TimeML Annotated Corpus  (ver 2.0)\n\nThe corpus consists of 80 Estonian newspaper articles (approx. 22,000 word tokens) with manually corrected morphological and dependency syntactic annotations, and with manually added temporal semantic annotations. This corpus is a subcorpus of Estonian Dependency Treebank ( https://github.com/EstSyntax/EDT ).\n\nTemporal semantic annotations are based on an adaption of the TimeML specification ( http://www.timeml.org/ ), and consist of EVENT, TIMEX and TLINK annotations. The creation process of the corpus, along with the evaluation of consistency of annotation is described by Orasmaa (2014a, 2014b).\n\nFormat of the corpus\n\nSee  https://github.com/soras/EstTimeMLCorpus/blob/master/readme.txt  for details.\n\n\nRelated publications\n\nThe creation of this corpus and its first version is described in publications:\n\nS.Orasmaa (2014a). Towards an Integration of Syntactic and Temporal Annotations in Estonian. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14).\n\nS.Orasmaa (2014b). How Availability of Explicit Temporal Cues Affects Manual Temporal Relation Annotation. Human Language Technologies - The Baltic Perspective (215 - 218). IOS Press.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "482032f4-711f-5ea2-b28f-537f5067442c",
-    "notes": [
-        "Abstract",
-        "Estonian TimeML Annotated Corpus  (ver 2.0)\n\nThe corpus consists of 80 Estonian newspaper articles (approx. 22,000 word tokens) with manually corrected morphological and dependency syntactic annotations, and with manually added temporal semantic annotations. This corpus is a subcorpus of Estonian Dependency Treebank ( https://github.com/EstSyntax/EDT ).\n\nTemporal semantic annotations are based on an adaption of the TimeML specification ( http://www.timeml.org/ ), and consist of EVENT, TIMEX and TLINK annotations. The creation process of the corpus, along with the evaluation of consistency of annotation is described by Orasmaa (2014a, 2014b).\n\nFormat of the corpus\n\nSee  https://github.com/soras/EstTimeMLCorpus/blob/master/readme.txt  for details.\n\n\nRelated publications\n\nThe creation of this corpus and its first version is described in publications:\n\nS.Orasmaa (2014a). Towards an Integration of Syntactic and Temporal Annotations in Estonian. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14).\n\nS.Orasmaa (2014b). How Availability of Explicit Temporal Cues Affects Manual Temporal Relation Annotation. Human Language Technologies - The Baltic Perspective (215 - 218). IOS Press."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14977543"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "TimeML annotated corpus of Estonian newspaper articles"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4836b028-dcf1-5714-9d0b-1f5a45493514.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4836b028-dcf1-5714-9d0b-1f5a45493514.json
deleted file mode 100644
index 943b5205..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4836b028-dcf1-5714-9d0b-1f5a45493514.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0015AL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14614864",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14614864"
-    ],
-    "PublicationTimestamp": "2018-04-12T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laur, Sven"
-    ],
-    "fulltext": "oai:oai.datacite.org:14614864;2019-04-17T17:27:08Z;ESTDOI;ESTDOI.KEEL;Koond-ner;Laur, Sven;Center of Estonian Language Resources;2018;Issued: 2018-04-05;Updated: 2018-04-12;doi:10.15155/1-00-0000-0000-0000-0015AL;Abstract;Estonian Reference Corpus* with NER annotations\n\nNER annotations were produced with Estnltk toolkit and include entities of a type person (PER), organisation (ORG), location (LOC) and timex (TIMEX). The corpus archive contains two subdirectories - tok and lbl. Tok directory contains original text files which are word and sentence tokenised, while the lbl directory contains corresponding NER annotations.\n\n* Estonian Reference Corpus http://www.cl.ut.ee/korpused/segakorpus/",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4836b028-dcf1-5714-9d0b-1f5a45493514",
-    "notes": [
-        "Abstract",
-        "Estonian Reference Corpus* with NER annotations\n\nNER annotations were produced with Estnltk toolkit and include entities of a type person (PER), organisation (ORG), location (LOC) and timex (TIMEX). The corpus archive contains two subdirectories - tok and lbl. Tok directory contains original text files which are word and sentence tokenised, while the lbl directory contains corresponding NER annotations.\n\n* Estonian Reference Corpus http://www.cl.ut.ee/korpused/segakorpus/"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14614864"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Koond-ner"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/483fbb15-c519-5c00-8e17-4a6076165c2b.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/483fbb15-c519-5c00-8e17-4a6076165c2b.json
deleted file mode 100644
index 97c1c401..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/483fbb15-c519-5c00-8e17-4a6076165c2b.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05926L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:8922509",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:8922509"
-    ],
-    "PublicationTimestamp": "2016-08-30T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "P\u00e4ll, Peeter"
-    ],
-    "fulltext": "oai:oai.datacite.org:8922509;2019-01-31T09:02:37Z;ESTDOI;ESTDOI.KEEL;Eesti Keele Instituudi kohanimeandmebaas (KNAB);P\u00e4ll, Peeter;Center of Estonian Language Resources;2015;Issued: 2015-05-06;Updated: 2016-08-30;doi:10.15155/3-00-0000-0000-0000-05926L;Abstract;Place Names Database (KNAB)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "483fbb15-c519-5c00-8e17-4a6076165c2b",
-    "notes": [
-        "Abstract",
-        "Place Names Database (KNAB)"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:8922509"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti Keele Instituudi kohanimeandmebaas (KNAB)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4996400a-3e25-5689-a8cb-9b13f12be608.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4996400a-3e25-5689-a8cb-9b13f12be608.json
deleted file mode 100644
index 2c82268e..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4996400a-3e25-5689-a8cb-9b13f12be608.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0017EL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17946160",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17946160"
-    ],
-    "PublicationTimestamp": "2019-01-03T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:17946160;2019-04-19T11:01:20Z;ESTDOI;ESTDOI.KEEL;Mitmikute sagedusloendid;Muischnek, Kadri;Center of Estonian Language Resources;2019;Issued: 2019-01-03;Updated: 2019-01-03;doi:10.15155/1-00-0000-0000-0000-0017EL;Abstract;Lemmade ja s\u00f5navormide mitmikute (n-grammide) sagedusloendid Tasakaalus korpuse p\u00f5hjal",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4996400a-3e25-5689-a8cb-9b13f12be608",
-    "notes": [
-        "Abstract",
-        "Lemmade ja s\u00f5navormide mitmikute (n-grammide) sagedusloendid Tasakaalus korpuse p\u00f5hjal"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17946160"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Mitmikute sagedusloendid"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4a537cce-ec96-577c-aafa-280c31eccb2d.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4a537cce-ec96-577c-aafa-280c31eccb2d.json
deleted file mode 100644
index 75b3dd4a..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4a537cce-ec96-577c-aafa-280c31eccb2d.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-071EEL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14560423",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14560423"
-    ],
-    "PublicationTimestamp": "2018-03-26T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Koppel, Kristina",
-        "Kallas, Jelena"
-    ],
-    "fulltext": "oai:oai.datacite.org:14560423;2019-02-04T14:07:16Z;ESTDOI;ESTDOI.KEEL;Sketch Engine eesti keele \u00f5ppijale (etSkELL);Sketch Engine for Estonian Language Learning (etSkELL);Kallas, Jelena;Koppel, Kristina;Center of Estonian Language Resources;2018;Issued: 2018-03-26;Updated: 2018-03-26;doi:10.15155/3-00-0000-0000-0000-071EEL;Abstract;etSkELL on automaatselt loodud keele\u00f5ppekeskkond, mille alus on Eesti keele \u00f5ppekorpus 2018. Korpus sisaldab umbes 25 miljonit lauset ja 250 miljonit s\u00f5na. Laused on p\u00e4rit erinevatest meedia-, ilukirjandus- ja teadustekstidest ning eestikeelsest Vikipeediast ja Eesti keele A1-C1 \u00f5pikute korpusest 2018.\netSkELL arendati v\u00e4lja Eesti Keele Instituudi ja Lexical Computing Ltd. koost\u00f6\u00f6s.\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4a537cce-ec96-577c-aafa-280c31eccb2d",
-    "notes": [
-        "Abstract",
-        "etSkELL on automaatselt loodud keele\u00f5ppekeskkond, mille alus on Eesti keele \u00f5ppekorpus 2018. Korpus sisaldab umbes 25 miljonit lauset ja 250 miljonit s\u00f5na. Laused on p\u00e4rit erinevatest meedia-, ilukirjandus- ja teadustekstidest ning eestikeelsest Vikipeediast ja Eesti keele A1-C1 \u00f5pikute korpusest 2018.\netSkELL arendati v\u00e4lja Eesti Keele Instituudi ja Lexical Computing Ltd. koost\u00f6\u00f6s.\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14560423"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Sketch Engine eesti keele \u00f5ppijale (etSkELL)",
-        "Sketch Engine for Estonian Language Learning (etSkELL)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4b6486e8-93da-54ff-94c2-4a5db0f5e18b.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4b6486e8-93da-54ff-94c2-4a5db0f5e18b.json
deleted file mode 100644
index 8cad5f7b..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4b6486e8-93da-54ff-94c2-4a5db0f5e18b.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-0008CL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:13082151",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:13082151"
-    ],
-    "PublicationTimestamp": "2017-11-25T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laineste, Liisi"
-    ],
-    "fulltext": "oai:oai.datacite.org:13082151;2019-03-05T10:02:24Z;ESTDOI;ESTDOI.KEEL;Eesti kaasaegsed anekdoodid;Laineste, Liisi;Center of Estonian Language Resources;2017;Issued: 2017-11-25;Updated: 2017-11-25;doi:10.15155/9-00-0000-0000-0000-0008CL;Abstract;Anekdoodid",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4b6486e8-93da-54ff-94c2-4a5db0f5e18b",
-    "notes": [
-        "Abstract",
-        "Anekdoodid"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:13082151"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti kaasaegsed anekdoodid"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4bd4923a-2055-5097-bfec-0aa9ca28f362.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4bd4923a-2055-5097-bfec-0aa9ca28f362.json
deleted file mode 100644
index bb8d2a47..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4bd4923a-2055-5097-bfec-0aa9ca28f362.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/TY.000D",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:4597366",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:4597366"
-    ],
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Lippus, P\u00e4rtel"
-    ],
-    "fulltext": "oai:oai.datacite.org:4597366;2019-02-22T01:31:19Z;ESTDOI;ESTDOI.KEEL;Phonetic Corpus of Estonian Spontaneous Speech;Lippus, P\u00e4rtel;Center of Estonian Language Resources;2013;doi:10.15155/TY.000D",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4bd4923a-2055-5097-bfec-0aa9ca28f362",
-    "oai_identifier": [
-        "oai:oai.datacite.org:4597366"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Phonetic Corpus of Estonian Spontaneous Speech"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4db5673c-418c-5768-8be4-31a18f66d0fb.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4db5673c-418c-5768-8be4-31a18f66d0fb.json
deleted file mode 100644
index 4416cb49..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4db5673c-418c-5768-8be4-31a18f66d0fb.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05BE3L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9474549",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9474549"
-    ],
-    "PublicationTimestamp": "2016-11-09T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Pajupuu, Hille"
-    ],
-    "fulltext": "oai:oai.datacite.org:9474549;2019-02-03T01:02:00Z;ESTDOI;ESTDOI.KEEL;Valentsikorpus;Pajupuu, Hille;Center of Estonian Language Resources;2016;Issued: 2016-11-09;Updated: 2016-11-09;doi:10.15155/3-00-0000-0000-0000-05BE3L;Abstract;Valentsikorpus koosneb \"Postimehe\" artiklite ortograafilistest l\u00f5ikudest, mille emotsionaalsuse (positiivne, negatiivne, vastuoluline, neutraalne) on m\u00e4\u00e4ranud lugejad. Kasutatud on domineeriva arvamuse meetodit (Pennebaker jt 1997).\nValentsikorpus on m\u00f5eldud eesk\u00e4tt statistiliste mudelite treenimiseks, kuid seda saab kasutada ka muudel eesm\u00e4rkidel. P\u00e4ringuid on v\u00f5imalik teha nii rubriike (Arvamus, Eesti, Kultuur, Sport, V\u00e4lismaa, Krimi) kui ka emotsionaalsust (positiivne, negatiivne, vastuoluline, neutraalne) arvesse v\u00f5ttes.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4db5673c-418c-5768-8be4-31a18f66d0fb",
-    "notes": [
-        "Abstract",
-        "Valentsikorpus koosneb \"Postimehe\" artiklite ortograafilistest l\u00f5ikudest, mille emotsionaalsuse (positiivne, negatiivne, vastuoluline, neutraalne) on m\u00e4\u00e4ranud lugejad. Kasutatud on domineeriva arvamuse meetodit (Pennebaker jt 1997).\nValentsikorpus on m\u00f5eldud eesk\u00e4tt statistiliste mudelite treenimiseks, kuid seda saab kasutada ka muudel eesm\u00e4rkidel. P\u00e4ringuid on v\u00f5imalik teha nii rubriike (Arvamus, Eesti, Kultuur, Sport, V\u00e4lismaa, Krimi) kui ka emotsionaalsust (positiivne, negatiivne, vastuoluline, neutraalne) arvesse v\u00f5ttes."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9474549"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Valentsikorpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4f7129de-219b-584e-83d3-31b2b1446fe7.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4f7129de-219b-584e-83d3-31b2b1446fe7.json
deleted file mode 100644
index af9d8891..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4f7129de-219b-584e-83d3-31b2b1446fe7.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0012BL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9845165",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9845165"
-    ],
-    "PublicationTimestamp": "2018-03-26T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Lippus, P\u00e4rtel"
-    ],
-    "fulltext": "oai:oai.datacite.org:9845165;2019-04-15T17:25:42Z;ESTDOI;ESTDOI.KEEL;Eesti keele spontaanse k\u00f5ne foneetiline korpus v.1.0.3;Phonetic Corpus of Estonian Spontaneous Speech v.1.0.3;Lippus, P\u00e4rtel;Center of Estonian Language Resources;2013;Issued: 2013-01-09;Updated: 2018-03-26;doi:10.15155/1-00-0000-0000-0000-0012BL;Abstract;The aim of the corpus is to compile a large amount of quality recordings of spontaneous Estonian and segment it phonetically on different levels. The project started in autumn 2006.\n\nThe total size of the corpus is approximately 80 hours of speech from 120 speakers with different dialectological and social background. Speakers are from different age groups. They are asked to participate with face-to-face invitation and they are aware of the purpose of the recordings.\n\nMost of the recordings are made in a recording studio, some also on fieldwork. The signal of each speaker is recorded in a separate channel. The distance between the speakers is about 3 meters to minimize the effect of overlaps. For the field-work recordings head-set microphones are used. Recordings are saved in PCM wav-format and are not compressed. Background information about the recordings is collected in a text-file.\n    Segmentation and annotation files are saved as Praat TextGrid files and get same filenames as recordings segmented.\n\nSegmentation and annotation\nSegmentation and annotation is done with the Praat program (www.praat.org). Recordings are segmented manually on different levels (automatic segmentation program is also elaborated and tested).\nFollowing tiers are used:\n    -Words (in orthographic spelling), \n    -Phonemes (SAMPA adjusted for Estonian is used for transcription), \n    -Syllables (short \u2013 long, open \u2013 closed), \n    -Prosodic feet,\n    -Intonation phrases or inter-pausal units;\n    -Changes in voice quality (e.g. creaky voice);",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4f7129de-219b-584e-83d3-31b2b1446fe7",
-    "notes": [
-        "Abstract",
-        "The aim of the corpus is to compile a large amount of quality recordings of spontaneous Estonian and segment it phonetically on different levels. The project started in autumn 2006.\n\nThe total size of the corpus is approximately 80 hours of speech from 120 speakers with different dialectological and social background. Speakers are from different age groups. They are asked to participate with face-to-face invitation and they are aware of the purpose of the recordings.\n\nMost of the recordings are made in a recording studio, some also on fieldwork. The signal of each speaker is recorded in a separate channel. The distance between the speakers is about 3 meters to minimize the effect of overlaps. For the field-work recordings head-set microphones are used. Recordings are saved in PCM wav-format and are not compressed. Background information about the recordings is collected in a text-file.\n    Segmentation and annotation files are saved as Praat TextGrid files and get same filenames as recordings segmented.\n\nSegmentation and annotation\nSegmentation and annotation is done with the Praat program (www.praat.org). Recordings are segmented manually on different levels (automatic segmentation program is also elaborated and tested).\nFollowing tiers are used:\n    -Words (in orthographic spelling), \n    -Phonemes (SAMPA adjusted for Estonian is used for transcription), \n    -Syllables (short \u2013 long, open \u2013 closed), \n    -Prosodic feet,\n    -Intonation phrases or inter-pausal units;\n    -Changes in voice quality (e.g. creaky voice);"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9845165"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele spontaanse k\u00f5ne foneetiline korpus v.1.0.3",
-        "Phonetic Corpus of Estonian Spontaneous Speech v.1.0.3"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4f8426f5-87d2-55ac-bc08-951eb9f4a9ca.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4f8426f5-87d2-55ac-bc08-951eb9f4a9ca.json
deleted file mode 100644
index 02049f13..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/4f8426f5-87d2-55ac-bc08-951eb9f4a9ca.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0019BL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17986396",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17986396"
-    ],
-    "PublicationTimestamp": "2019-01-11T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Iva, Sulev"
-    ],
-    "fulltext": "oai:oai.datacite.org:17986396;2019-02-25T10:30:48Z;ESTDOI;ESTDOI.KEEL;Ajalehe Setomaa korpus;Iva, Sulev;Center of Estonian Language Resources;2019;Issued: 2019-01-11;Updated: 2019-01-11;doi:10.15155/1-00-0000-0000-0000-0019BL;Abstract;Seo aolehe Setomaa korpus om osa V\u00f5ro instituudi V\u00f5ro ja seto keelekorpus\u00f5st. Korpus\u00f5 om kokko pandnuq M\u00e4nnamaa Kaur aolehe Setomaa lual lehe elektrooniliidsi arhiiv\u00f5 perr\u00e4 2013. aastagal. Seo v\u00f5rgolehe om kujondanu M\u00e4nnamaa Laura.\n\nKorpus\u00f5n om parhilla 1031 teksti. Tuu hulgan setokeelitsit tekste 403 (278 879 s\u00f5nna) ja eestikeelitsit tekste 628 (227 704 s\u00f5nna). Tekstiq ommaq peri aastist 2006 - 2013. Korpus\u00f5 kokkopandmist om rahaga tug\u00f5nuq riiklin\u00f5 programm Eesti keeletehnoloogia. ",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "4f8426f5-87d2-55ac-bc08-951eb9f4a9ca",
-    "notes": [
-        "Abstract",
-        "Seo aolehe Setomaa korpus om osa V\u00f5ro instituudi V\u00f5ro ja seto keelekorpus\u00f5st. Korpus\u00f5 om kokko pandnuq M\u00e4nnamaa Kaur aolehe Setomaa lual lehe elektrooniliidsi arhiiv\u00f5 perr\u00e4 2013. aastagal. Seo v\u00f5rgolehe om kujondanu M\u00e4nnamaa Laura.\n\nKorpus\u00f5n om parhilla 1031 teksti. Tuu hulgan setokeelitsit tekste 403 (278 879 s\u00f5nna) ja eestikeelitsit tekste 628 (227 704 s\u00f5nna). Tekstiq ommaq peri aastist 2006 - 2013. Korpus\u00f5 kokkopandmist om rahaga tug\u00f5nuq riiklin\u00f5 programm Eesti keeletehnoloogia. "
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17986396"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Ajalehe Setomaa korpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/50d27a81-59ba-59cc-b491-353f8460906e.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/50d27a81-59ba-59cc-b491-353f8460906e.json
deleted file mode 100644
index 9d2d0de1..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/50d27a81-59ba-59cc-b491-353f8460906e.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00124L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9832370",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9832370"
-    ],
-    "PublicationTimestamp": "2016-11-30T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Tkachenko, Alexander"
-    ],
-    "fulltext": "oai:oai.datacite.org:9832370;2019-02-02T02:02:30Z;ESTDOI;ESTDOI.KEEL;Estonian gap tests;Tkachenko, Alexander;Center of Estonian Language Resources;2016;Issued: 2016-11-30;Updated: 2016-11-30;doi:10.15155/1-00-0000-0000-0000-00124L;Abstract;Estonian gap tests corpus represents a collection of sentences, in which one word is marked as a \"gap\", accompanied with a list of candidate words. The corpus can be used as a benchmark for evaluating language models. The corpus covers both frequent and infrequent gap-words and includes candidate lists generated in different ways. Sentences originate from the Estonian Reference Corpus (http://www.cl.ut.ee/korpused/segakorpus/).\n\nAn archive contains sentence files with an extension \".gaps\" and candidate files with an extension \"*.var\". Sentence file contains one sentence per line. A line starts with an integer which indicates gap-word's offset in a sentence. The position of the first word in the sentence is zero. Based on the frequency of a gap-word, we generated four kinds of sentence files:\n\nFile name             Gap-word frequency\n--------------------------------------------------------------\ntest.all.gaps          any frequency\ntest.freq.gaps        frequent word form\ntest.inf_freq.gaps   infrequent word form, frequent word type (lemma)\ntest.inf_inf.gaps     infrequent word form, infrequent word type (lemma)\n\n\nTo each sentence file relate multiple candidate files. In a candidate file, each line contains a list of 200 candidate words, which correspond to a sentence at the same line in the related sentence file.\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "50d27a81-59ba-59cc-b491-353f8460906e",
-    "notes": [
-        "Abstract",
-        "Estonian gap tests corpus represents a collection of sentences, in which one word is marked as a \"gap\", accompanied with a list of candidate words. The corpus can be used as a benchmark for evaluating language models. The corpus covers both frequent and infrequent gap-words and includes candidate lists generated in different ways. Sentences originate from the Estonian Reference Corpus (http://www.cl.ut.ee/korpused/segakorpus/).\n\nAn archive contains sentence files with an extension \".gaps\" and candidate files with an extension \"*.var\". Sentence file contains one sentence per line. A line starts with an integer which indicates gap-word's offset in a sentence. The position of the first word in the sentence is zero. Based on the frequency of a gap-word, we generated four kinds of sentence files:\n\nFile name             Gap-word frequency\n--------------------------------------------------------------\ntest.all.gaps          any frequency\ntest.freq.gaps        frequent word form\ntest.inf_freq.gaps   infrequent word form, frequent word type (lemma)\ntest.inf_inf.gaps     infrequent word form, infrequent word type (lemma)\n\n\nTo each sentence file relate multiple candidate files. In a candidate file, each line contains a list of 200 candidate words, which correspond to a sentence at the same line in the related sentence file.\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9832370"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Estonian gap tests"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/52400e0c-75c1-559d-9550-e890a45340b7.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/52400e0c-75c1-559d-9550-e890a45340b7.json
deleted file mode 100644
index 776af53b..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/52400e0c-75c1-559d-9550-e890a45340b7.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05BDFL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9474545",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9474545"
-    ],
-    "PublicationTimestamp": "2016-11-09T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:9474545;2019-02-15T13:31:51Z;ESTDOI;ESTDOI.KEEL;Inglise-eesti meres\u00f5naraamat;Hein, Indrek;Center of Estonian Language Resources;2016;Issued: 2016-11-09;Updated: 2016-11-09;doi:10.15155/3-00-0000-0000-0000-05BDFL;Abstract;Sisaldab \u00fcle 30 000 m\u00e4rks\u00f5na. Peale merenduslike tavaterminite leiab s\u00f5naraamatust ka purjelaevu, puulaevu, merekaubandust, mere\u00f5igust, merekindlustust, konteinervedusid, kalandust, s\u00f5jalaevastikku, raadiolokatsiooni, h\u00fcdromehaanikat, okeanograafiat, purjesporti jms puutuvaid s\u00f5nu.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "52400e0c-75c1-559d-9550-e890a45340b7",
-    "notes": [
-        "Abstract",
-        "Sisaldab \u00fcle 30 000 m\u00e4rks\u00f5na. Peale merenduslike tavaterminite leiab s\u00f5naraamatust ka purjelaevu, puulaevu, merekaubandust, mere\u00f5igust, merekindlustust, konteinervedusid, kalandust, s\u00f5jalaevastikku, raadiolokatsiooni, h\u00fcdromehaanikat, okeanograafiat, purjesporti jms puutuvaid s\u00f5nu."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9474545"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Inglise-eesti meres\u00f5naraamat"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/52bbe1b9-86d6-5455-b81f-14a80de5904f.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/52bbe1b9-86d6-5455-b81f-14a80de5904f.json
deleted file mode 100644
index d9bf0c60..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/52bbe1b9-86d6-5455-b81f-14a80de5904f.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-0008BL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:12540148",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:12540148"
-    ],
-    "PublicationTimestamp": "2017-10-10T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Krikmann, Jaak",
-        "K\u00f5iva, Mare"
-    ],
-    "fulltext": "oai:oai.datacite.org:12540148;2019-03-31T20:01:10Z;ESTDOI;ESTDOI.KEEL;Eesti m\u00f5istatuste andmebaas;Estonian Riddles Database;K\u00f5iva, Mare;Krikmann, Jaak;Center of Estonian Language Resources;2017;Issued: 2017-10-10;Updated: 2017-10-10;doi:10.15155/9-00-0000-0000-0000-0008BL;Abstract;Andmebaas on rajatud Eesti Kirjandusmuuseumi folkloristika osakonnas. Baasi aluseks oli 2800 Word 7.0 formaadis andmetabelit, mille p\u00f5hjal toodeti akadeemilise v\u00e4ljaande \"Eesti m\u00f5istatused\" (EM) p\u00f5hik\u00f6idete I (2001) ja II (2002) k\u00e4sikiri. Andmebaas on kasutatav kolmes variandis, siinne versioon on xml-kujule teisendatud \"baas-lugemik\", mis esitab 95 751 eesti m\u00f5istatusteksti kirjed 20 000 kirje kaupa EM I\u2013II t\u00fc\u00fcpide ja tekstide j\u00e4rjekorras (erinevalt andmebaasi kasutajaliidesest, kus on kirjed esitatud 1000 kaupa). Andmebaasi juurde kuuluvad abimaterjalid (millest k\u00f5iki pole siinses versioonis): 1) kogu EM I\u2013II tr\u00fckiversioonis leiduv teave 2) lahendite temaatiline register 3) Eesti kihelkondade kontuurkaart kihelkonnal\u00fchenditega 4) m\u00f5istatuste andmebaasi suhtes autonoomne \u00fcldotstarbeline kartografeerimismasin.\n\nAndmebaas kasutab \u00fchist allikmaterjali eesti m\u00f5istatuste akadeemiliste v\u00e4ljaannetega:\n\nEesti m\u00f5istatused. I, [m\u00f5istatust\u00fc\u00fcbid] 1-1350 = Aenigmata Estonica. I, 1-1350 / Eesti Keele Instituut, Eesti Kirjandusmuuseum, Tartu \u00dclikool; koostanud Anne Hussar, Arvo Krikmann, Rein Saukas, Piret Voolaid; toimetanud Arvo Krikmann ja Rein Saukas, Tartu: Eesti Keele Sihtasutus, 2001 (Tallinn: Pakett), 891 lk.\n\nEesti m\u00f5istatused. II, [m\u00f5istatust\u00fc\u00fcbid] 1351-2800 = Aenigmata Estonica II, 1351-2800 / Eesti Keele Instituut, Eesti Kirjandusmuuseum, Tartu \u00dclikool; koostanud Anne Hussar, Arvo Krikmann, Rein Saukas, Piret Voolaid; toimetanud Arvo Krikmann ja Rein Saukas, Tartu: Eesti Keele Sihtasutus, 2002 (Tallinn: Pakett), 877 lk. \nElektroonilise andmebaasi koostajad: Jaak Krikmann (php), Arvo Krikmann (autor, konsultatsioon).\n;Abstract;The database was created at the Department of Folkloristics of the Estonian Literary Museum. The foundation for the database was 2,800 Word 7.0 format data tables, on the basis of which the manuscripts of the main volumes I (2001) and II (2002) of the academic publication \"Estonian Riddles\" (ER) were compiled. The database is available in three variants; this version is converted into an xml-formatted \"base reader\", which provides 95,751 entries of the texts of Estonian riddles by groups of 20,000 entries in the order of the types and texts of EM I-II (unlike the online interface of the database, in which entries are given by groups of 1000). Auxiliary materials for the database (not all included here) are: 1) all the information contained in the ER I-II paper editions; 2) thematic register of solutions; 3) a contour map of Estonian parishes with parish abbreviations; 4) an autonomous general purpose mapping machine.\n\nThe database uses source material common with academic editions of Estonian riddles:\nEstonian Riddles [Eesti m\u00f5istatused] I, [riddle types] 1\u20131350 = Aenigmata Estonica I, 1\u20131350 / Institute of the Estonian Language, Estonian Literary Museum, University of Tartu; compiled by Anne Hussar, Arvo Krikmann, Rein Saukas, Piret Voolaid; edited by Arvo Krikmann and Rein Saukas. Tartu: Estonian Language Foundation, 2001 (Tallinn: Pakett), 891 pages.\nEstonian Riddles [Eesti m\u00f5istatused] II, [riddle types] 1351\u20132800 = Aenigmata Estonica II, 1351\u20132800 / Institute of the Estonian Language, Estonian Literary Museum, University of Tartu; compiled by Anne Hussar, Arvo Krikmann, Rein Saukas, Piret Voolaid; edited by Arvo Krikmann and Rein Saukas. Tartu: Estonian Language Foundation, 2002 (Tallinn: Pakett), 877 pages.\nCompilers of the electronic database: Jaak Krikmann (php), Arvo Krikmann (author, consultant).\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "52bbe1b9-86d6-5455-b81f-14a80de5904f",
-    "notes": [
-        "Abstract",
-        "Andmebaas on rajatud Eesti Kirjandusmuuseumi folkloristika osakonnas. Baasi aluseks oli 2800 Word 7.0 formaadis andmetabelit, mille p\u00f5hjal toodeti akadeemilise v\u00e4ljaande \"Eesti m\u00f5istatused\" (EM) p\u00f5hik\u00f6idete I (2001) ja II (2002) k\u00e4sikiri. Andmebaas on kasutatav kolmes variandis, siinne versioon on xml-kujule teisendatud \"baas-lugemik\", mis esitab 95 751 eesti m\u00f5istatusteksti kirjed 20 000 kirje kaupa EM I\u2013II t\u00fc\u00fcpide ja tekstide j\u00e4rjekorras (erinevalt andmebaasi kasutajaliidesest, kus on kirjed esitatud 1000 kaupa). Andmebaasi juurde kuuluvad abimaterjalid (millest k\u00f5iki pole siinses versioonis): 1) kogu EM I\u2013II tr\u00fckiversioonis leiduv teave 2) lahendite temaatiline register 3) Eesti kihelkondade kontuurkaart kihelkonnal\u00fchenditega 4) m\u00f5istatuste andmebaasi suhtes autonoomne \u00fcldotstarbeline kartografeerimismasin.\n\nAndmebaas kasutab \u00fchist allikmaterjali eesti m\u00f5istatuste akadeemiliste v\u00e4ljaannetega:\n\nEesti m\u00f5istatused. I, [m\u00f5istatust\u00fc\u00fcbid] 1-1350 = Aenigmata Estonica. I, 1-1350 / Eesti Keele Instituut, Eesti Kirjandusmuuseum, Tartu \u00dclikool; koostanud Anne Hussar, Arvo Krikmann, Rein Saukas, Piret Voolaid; toimetanud Arvo Krikmann ja Rein Saukas, Tartu: Eesti Keele Sihtasutus, 2001 (Tallinn: Pakett), 891 lk.\n\nEesti m\u00f5istatused. II, [m\u00f5istatust\u00fc\u00fcbid] 1351-2800 = Aenigmata Estonica II, 1351-2800 / Eesti Keele Instituut, Eesti Kirjandusmuuseum, Tartu \u00dclikool; koostanud Anne Hussar, Arvo Krikmann, Rein Saukas, Piret Voolaid; toimetanud Arvo Krikmann ja Rein Saukas, Tartu: Eesti Keele Sihtasutus, 2002 (Tallinn: Pakett), 877 lk. \nElektroonilise andmebaasi koostajad: Jaak Krikmann (php), Arvo Krikmann (autor, konsultatsioon).\n",
-        "Abstract",
-        "The database was created at the Department of Folkloristics of the Estonian Literary Museum. The foundation for the database was 2,800 Word 7.0 format data tables, on the basis of which the manuscripts of the main volumes I (2001) and II (2002) of the academic publication \"Estonian Riddles\" (ER) were compiled. The database is available in three variants; this version is converted into an xml-formatted \"base reader\", which provides 95,751 entries of the texts of Estonian riddles by groups of 20,000 entries in the order of the types and texts of EM I-II (unlike the online interface of the database, in which entries are given by groups of 1000). Auxiliary materials for the database (not all included here) are: 1) all the information contained in the ER I-II paper editions; 2) thematic register of solutions; 3) a contour map of Estonian parishes with parish abbreviations; 4) an autonomous general purpose mapping machine.\n\nThe database uses source material common with academic editions of Estonian riddles:\nEstonian Riddles [Eesti m\u00f5istatused] I, [riddle types] 1\u20131350 = Aenigmata Estonica I, 1\u20131350 / Institute of the Estonian Language, Estonian Literary Museum, University of Tartu; compiled by Anne Hussar, Arvo Krikmann, Rein Saukas, Piret Voolaid; edited by Arvo Krikmann and Rein Saukas. Tartu: Estonian Language Foundation, 2001 (Tallinn: Pakett), 891 pages.\nEstonian Riddles [Eesti m\u00f5istatused] II, [riddle types] 1351\u20132800 = Aenigmata Estonica II, 1351\u20132800 / Institute of the Estonian Language, Estonian Literary Museum, University of Tartu; compiled by Anne Hussar, Arvo Krikmann, Rein Saukas, Piret Voolaid; edited by Arvo Krikmann and Rein Saukas. Tartu: Estonian Language Foundation, 2002 (Tallinn: Pakett), 877 pages.\nCompilers of the electronic database: Jaak Krikmann (php), Arvo Krikmann (author, consultant).\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:12540148"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti m\u00f5istatuste andmebaas",
-        "Estonian Riddles Database"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/52d74f3c-7b37-527c-bf25-3fe3a4fa5494.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/52d74f3c-7b37-527c-bf25-3fe3a4fa5494.json
deleted file mode 100644
index 09e50eb5..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/52d74f3c-7b37-527c-bf25-3fe3a4fa5494.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06336L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10303952",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10303952"
-    ],
-    "PublicationTimestamp": "2017-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laansalu, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:10303952;2019-04-23T05:30:49Z;ESTDOI;ESTDOI.KEEL;Mulgi s\u00f5nastik;The Dictionary of the Mulgi Dialect;Laansalu, Tiina;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2017-02-15;doi:10.15155/3-00-0000-0000-0000-06336L;Abstract;Mulgi veebis\u00f5nastikust saab s\u00f5nu otsida nii m\u00e4rks\u00f5na (murdekuju), kirjakeelse vaste (t\u00e4henduse) kui ka stiili j\u00e4rgi. M\u00e4rks\u00f5nade juurde on enamasti lisatud ka n\u00e4itelaused ning viited teistele sama v\u00f5i l\u00e4hedase t\u00e4hendusega s\u00f5nadele.;Abstract;An online dictionary searchable by keyword (in dialect spelling), standard Estonian equivalent (meaning) or style label. Most of the entry words are provided with sentence examples and references to words with the same or similar meaning.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "52d74f3c-7b37-527c-bf25-3fe3a4fa5494",
-    "notes": [
-        "Abstract",
-        "Mulgi veebis\u00f5nastikust saab s\u00f5nu otsida nii m\u00e4rks\u00f5na (murdekuju), kirjakeelse vaste (t\u00e4henduse) kui ka stiili j\u00e4rgi. M\u00e4rks\u00f5nade juurde on enamasti lisatud ka n\u00e4itelaused ning viited teistele sama v\u00f5i l\u00e4hedase t\u00e4hendusega s\u00f5nadele.",
-        "Abstract",
-        "An online dictionary searchable by keyword (in dialect spelling), standard Estonian equivalent (meaning) or style label. Most of the entry words are provided with sentence examples and references to words with the same or similar meaning."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10303952"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Mulgi s\u00f5nastik",
-        "The Dictionary of the Mulgi Dialect"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/53412fef-af05-5c8f-81e2-bfec62bdb35e.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/53412fef-af05-5c8f-81e2-bfec62bdb35e.json
deleted file mode 100644
index d87e7499..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/53412fef-af05-5c8f-81e2-bfec62bdb35e.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-079D1L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17926651",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17926651"
-    ],
-    "PublicationTimestamp": "2018-12-22T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Pajupuu, Hille"
-    ],
-    "fulltext": "oai:oai.datacite.org:17926651;2018-12-27T15:08:02Z;ESTDOI;ESTDOI.KEEL;Emotional;Pajupuu, Hille;Center of Estonian Language Resources;2018;Issued: 2018-12-22;Updated: 2018-12-22;doi:10.15155/3-00-0000-0000-0000-079D1L;Abstract;Project Statistical Models of the Emotionality of Speech and Written Text (2011-2014) was supported by the National Programme for Estonian Language Technology (2011-2017) of the Estonian Ministry of Education and Research.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "53412fef-af05-5c8f-81e2-bfec62bdb35e",
-    "notes": [
-        "Abstract",
-        "Project Statistical Models of the Emotionality of Speech and Written Text (2011-2014) was supported by the National Programme for Estonian Language Technology (2011-2017) of the Estonian Ministry of Education and Research."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17926651"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Emotional"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/54d0781a-fe64-514e-807c-aa664bc0b115.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/54d0781a-fe64-514e-807c-aa664bc0b115.json
deleted file mode 100644
index 14a23311..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/54d0781a-fe64-514e-807c-aa664bc0b115.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06AE0L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:13042179",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:13042179"
-    ],
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Koppel, Kristina",
-        "Kallas, Jelena"
-    ],
-    "fulltext": "oai:oai.datacite.org:13042179;2019-03-14T18:25:41Z;ESTDOI;ESTDOI.KEEL;Eesti keele A1-C1 \u00f5pikute korpus 2017;Estonian Coursebook Corpus 2017;Kallas, Jelena;Koppel, Kristina;Center of Estonian Language Resources;2017;Issued: 2017-11-20;Updated: 2019-01-08;doi:10.15155/3-00-0000-0000-0000-06AE0L;Abstract;Sisaldab korpusest \u201eEesti keele \u00f5pikute korpus A1\u2013C1\" eraldatud t\u00e4islauseid. Korpus koosneb u 200 000 s\u00f5nest ja 24 000 lausest. Korpuses on m\u00e4rgendatud tekstistruktuuri \u00fcksused lause <sentence> ja osalause <clause>. Laused on morfoloogiliselt m\u00e4rgendatud. K\u00f5ik korpuse laused on keeletaseme piirides unikaalsed.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "54d0781a-fe64-514e-807c-aa664bc0b115",
-    "notes": [
-        "Abstract",
-        "Sisaldab korpusest \u201eEesti keele \u00f5pikute korpus A1\u2013C1\" eraldatud t\u00e4islauseid. Korpus koosneb u 200 000 s\u00f5nest ja 24 000 lausest. Korpuses on m\u00e4rgendatud tekstistruktuuri \u00fcksused lause <sentence> ja osalause <clause>. Laused on morfoloogiliselt m\u00e4rgendatud. K\u00f5ik korpuse laused on keeletaseme piirides unikaalsed."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:13042179"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele A1-C1 \u00f5pikute korpus 2017",
-        "Estonian Coursebook Corpus 2017"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/567dabb6-e270-5e18-859e-bca0114f759e.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/567dabb6-e270-5e18-859e-bca0114f759e.json
deleted file mode 100644
index ebdd7361..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/567dabb6-e270-5e18-859e-bca0114f759e.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05BE6L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9474552",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9474552"
-    ],
-    "PublicationTimestamp": "2017-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Pajupuu, Hille"
-    ],
-    "fulltext": "oai:oai.datacite.org:9474552;2019-04-17T17:26:26Z;ESTDOI;ESTDOI.KEEL;Valentsikorpus;Valency corpus ;Pajupuu, Hille;Center of Estonian Language Resources;2016;Issued: 2016-11-09;Updated: 2017-02-15;doi:10.15155/3-00-0000-0000-0000-05BE6L;Abstract;Valentsikorpus koosneb \"Postimehe\" artiklite ortograafilistest l\u00f5ikudest, mille emotsionaalsuse (positiivne, negatiivne, vastuoluline, neutraalne) on m\u00e4\u00e4ranud lugejad. Kasutatud on domineeriva arvamuse meetodit (Pennebaker jt 1997).\nValentsikorpus on m\u00f5eldud eesk\u00e4tt statistiliste mudelite treenimiseks, kuid seda saab kasutada ka muudel eesm\u00e4rkidel. P\u00e4ringuid on v\u00f5imalik teha nii rubriike (Arvamus, Eesti, Kultuur, Sport, V\u00e4lismaa, Krimi) kui ka emotsionaalsust (positiivne, negatiivne, vastuoluline, neutraalne) arvesse v\u00f5ttes.;Abstract;The Valency Corpus consists of orthographic passages from the Postimees daily, whose emotional tone (positive, negative, ambiguous, neutral) has been identified by readers. The identification was done using the method of dominant opinion (Pennebaker et al. 1997). The corpus is mainly intended to train statistical models, but it can also be used for other purposes. Queries can be done by rubrics (\u201cOpinion\u201c, \u201cEstonia\u201c, \u201cCulture\u201c, \u201cSports\u201c, \u201cAbroad\u201c, \u201cCriminal\u201c) as well as by the emotional tone (positive, negative, ambiguous, neutral).",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "567dabb6-e270-5e18-859e-bca0114f759e",
-    "notes": [
-        "Abstract",
-        "Valentsikorpus koosneb \"Postimehe\" artiklite ortograafilistest l\u00f5ikudest, mille emotsionaalsuse (positiivne, negatiivne, vastuoluline, neutraalne) on m\u00e4\u00e4ranud lugejad. Kasutatud on domineeriva arvamuse meetodit (Pennebaker jt 1997).\nValentsikorpus on m\u00f5eldud eesk\u00e4tt statistiliste mudelite treenimiseks, kuid seda saab kasutada ka muudel eesm\u00e4rkidel. P\u00e4ringuid on v\u00f5imalik teha nii rubriike (Arvamus, Eesti, Kultuur, Sport, V\u00e4lismaa, Krimi) kui ka emotsionaalsust (positiivne, negatiivne, vastuoluline, neutraalne) arvesse v\u00f5ttes.",
-        "Abstract",
-        "The Valency Corpus consists of orthographic passages from the Postimees daily, whose emotional tone (positive, negative, ambiguous, neutral) has been identified by readers. The identification was done using the method of dominant opinion (Pennebaker et al. 1997). The corpus is mainly intended to train statistical models, but it can also be used for other purposes. Queries can be done by rubrics (\u201cOpinion\u201c, \u201cEstonia\u201c, \u201cCulture\u201c, \u201cSports\u201c, \u201cAbroad\u201c, \u201cCriminal\u201c) as well as by the emotional tone (positive, negative, ambiguous, neutral)."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9474552"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Valentsikorpus",
-        "Valency corpus "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/56ea7b3b-7641-559c-95da-4a208ebab8a2.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/56ea7b3b-7641-559c-95da-4a208ebab8a2.json
deleted file mode 100644
index 322eb506..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/56ea7b3b-7641-559c-95da-4a208ebab8a2.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00175L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17944559",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17944559"
-    ],
-    "PublicationTimestamp": "2019-01-03T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Orasmaa, Siim"
-    ],
-    "fulltext": "oai:oai.datacite.org:17944559;2019-01-03T11:49:43Z;ESTDOI;ESTDOI.KEEL;Osalausestaja;Clause Segmenter for Estonian;Orasmaa, Siim;Center of Estonian Language Resources;2019;Issued: 2019-01-03;Updated: 2019-01-03;doi:10.15155/1-00-0000-0000-0000-00175L;Abstract;Osalausepiiride tuvastaja;Abstract;Clause Segmenter is a program that splits long and complex natural \n language sentences into smaller segments (clauses). For example, the \n sentence \"Mees, keda seal kohtasime, oli tuttav ja teretas meid.\" \n will be split into following clauses:\n\n     \"[Mees, [keda seal kohtasime,] oli tuttav ja] [teretas meid.]\"\n     (in the example, clauses are surrounded by brackets)\n\n   The algorithm mainly relies on punctuation, conjunction words, and\n  finite verb forms on identifying the clause boundaries.\n  For linguistic details/motivations behind the algorithm, see (Kaalep, \n  Muischnek 2012).",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "56ea7b3b-7641-559c-95da-4a208ebab8a2",
-    "notes": [
-        "Abstract",
-        "Osalausepiiride tuvastaja",
-        "Abstract",
-        "Clause Segmenter is a program that splits long and complex natural \n language sentences into smaller segments (clauses). For example, the \n sentence \"Mees, keda seal kohtasime, oli tuttav ja teretas meid.\" \n will be split into following clauses:\n\n     \"[Mees, [keda seal kohtasime,] oli tuttav ja] [teretas meid.]\"\n     (in the example, clauses are surrounded by brackets)\n\n   The algorithm mainly relies on punctuation, conjunction words, and\n  finite verb forms on identifying the clause boundaries.\n  For linguistic details/motivations behind the algorithm, see (Kaalep, \n  Muischnek 2012)."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17944559"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Osalausestaja",
-        "Clause Segmenter for Estonian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/56f8a113-ce7a-5e5a-b1d1-e56087bcbfe2.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/56f8a113-ce7a-5e5a-b1d1-e56087bcbfe2.json
deleted file mode 100644
index 9b238308..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/56f8a113-ce7a-5e5a-b1d1-e56087bcbfe2.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00190L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17967358",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17967358"
-    ],
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Fi\u0161el, Mark"
-    ],
-    "fulltext": "oai:oai.datacite.org:17967358;2019-04-12T17:25:49Z;ESTDOI;ESTDOI.KEEL;Neurot\u00f5lge;Neuralmt;Fi\u0161el, Mark;Center of Estonian Language Resources;2019;Issued: 2019-01-08;Updated: 2019-01-08;doi:10.15155/1-00-0000-0000-0000-00190L;Abstract;Avatud l\u00e4htekoodiga masint\u00f5lke programm.;Abstract;Neuralmt is open-source demo project for text machine translation done in the Natural Language Processing research group in the University of Tartu. The project provides convenient methods of data collection, ability to comare different translators and ability to use it as a regular text translator.\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "56f8a113-ce7a-5e5a-b1d1-e56087bcbfe2",
-    "notes": [
-        "Abstract",
-        "Avatud l\u00e4htekoodiga masint\u00f5lke programm.",
-        "Abstract",
-        "Neuralmt is open-source demo project for text machine translation done in the Natural Language Processing research group in the University of Tartu. The project provides convenient methods of data collection, ability to comare different translators and ability to use it as a regular text translator.\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17967358"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Neurot\u00f5lge",
-        "Neuralmt"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/57066ae8-8c34-5181-908d-9652fb622617.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/57066ae8-8c34-5181-908d-9652fb622617.json
deleted file mode 100644
index daa763ec..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/57066ae8-8c34-5181-908d-9652fb622617.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-00029L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5756808",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5756808"
-    ],
-    "PublicationTimestamp": "2015-05-22T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Meister, Einar"
-    ],
-    "fulltext": "oai:oai.datacite.org:5756808;2019-04-18T17:36:33Z;ESTDOI;ESTDOI.KEEL;BABEL Estonian Database;Meister, Einar;Center of Estonian Language Resources;2014;Issued: 2014-11-19;Updated: 2015-05-22;doi:10.15155/9-00-0000-0000-0000-00029L;Abstract;BABEL Estonian Database",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "57066ae8-8c34-5181-908d-9652fb622617",
-    "notes": [
-        "Abstract",
-        "BABEL Estonian Database"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5756808"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "BABEL Estonian Database"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/5715f34b-4b78-5f53-94c7-dba36693b2ee.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/5715f34b-4b78-5f53-94c7-dba36693b2ee.json
deleted file mode 100644
index f0839936..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/5715f34b-4b78-5f53-94c7-dba36693b2ee.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05929L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:8922996",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:8922996"
-    ],
-    "PublicationTimestamp": "2017-03-03T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:8922996;2019-04-17T17:26:11Z;ESTDOI;ESTDOI.KEEL;Anton\u00fc\u00fcmis\u00f5nastik;The Dictionary of Estonian Antonyms;Hein, Indrek;Center of Estonian Language Resources;2015;Issued: 2015-05-08;Updated: 2017-03-03;doi:10.15155/3-00-0000-0000-0000-05929L;Abstract;S\u00f5nastikus on ligi 2000 anton\u00fc\u00fcmipaari, neist enamik kuulub \u00fcldkeele s\u00f5navarasse. M\u00e4rks\u00f5na on esitatud koos oma vastandiga (nt suur : v\u00e4ike v\u00f5i vabastama : vangistama). ;Abstract;The dictionary contains nearly 2000 antonym pairs most of which belong to general language. Each entry word is presented together with its antonym (e.g., suur : v\u00e4ike \u00b4big : small\u00b4 or vabastama : vangistama \u00b4set free : arrest\u00b4).",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5715f34b-4b78-5f53-94c7-dba36693b2ee",
-    "notes": [
-        "Abstract",
-        "S\u00f5nastikus on ligi 2000 anton\u00fc\u00fcmipaari, neist enamik kuulub \u00fcldkeele s\u00f5navarasse. M\u00e4rks\u00f5na on esitatud koos oma vastandiga (nt suur : v\u00e4ike v\u00f5i vabastama : vangistama). ",
-        "Abstract",
-        "The dictionary contains nearly 2000 antonym pairs most of which belong to general language. Each entry word is presented together with its antonym (e.g., suur : v\u00e4ike \u00b4big : small\u00b4 or vabastama : vangistama \u00b4set free : arrest\u00b4)."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:8922996"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Anton\u00fc\u00fcmis\u00f5nastik",
-        "The Dictionary of Estonian Antonyms"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/575d2400-0333-5b2a-8f4a-b8b3b9778206.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/575d2400-0333-5b2a-8f4a-b8b3b9778206.json
deleted file mode 100644
index 7d7ccc43..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/575d2400-0333-5b2a-8f4a-b8b3b9778206.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/TY.0013",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:4597372",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:4597372"
-    ],
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:4597372;2015-01-09T14:13:38Z;ESTDOI;ESTDOI.KEEL;Corpus of Estonian law texts;Muischnek, Kadri;Center of Estonian Language Resources;2013;doi:10.15155/TY.0013",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "575d2400-0333-5b2a-8f4a-b8b3b9778206",
-    "oai_identifier": [
-        "oai:oai.datacite.org:4597372"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus of Estonian law texts"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/5787ebb0-009f-583d-b867-5cff88950ccb.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/5787ebb0-009f-583d-b867-5cff88950ccb.json
deleted file mode 100644
index 0c6bef83..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/5787ebb0-009f-583d-b867-5cff88950ccb.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-0009FL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17960896",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17960896"
-    ],
-    "PublicationTimestamp": "2019-01-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Meister, Einar"
-    ],
-    "fulltext": "oai:oai.datacite.org:17960896;2019-04-08T00:32:27Z;ESTDOI;ESTDOI.KEEL;Jutusaadete korpus;Meister, Einar;Center of Estonian Language Resources;2019;Issued: 2019-01-07;Updated: 2019-01-07;doi:10.15155/9-00-0000-0000-0000-0009FL;Abstract;Jutusaated televiisorist ja raadiost.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5787ebb0-009f-583d-b867-5cff88950ccb",
-    "notes": [
-        "Abstract",
-        "Jutusaated televiisorist ja raadiost."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17960896"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Jutusaadete korpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/58d7b2bf-b0ac-5a2d-98e1-8b9db25ca59f.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/58d7b2bf-b0ac-5a2d-98e1-8b9db25ca59f.json
deleted file mode 100644
index cf01650d..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/58d7b2bf-b0ac-5a2d-98e1-8b9db25ca59f.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00187L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17960604",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17960604"
-    ],
-    "PublicationTimestamp": "2019-01-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "M\u00fc\u00fcrisep, Kaili"
-    ],
-    "fulltext": "oai:oai.datacite.org:17960604;2019-01-07T16:15:14Z;ESTDOI;ESTDOI.KEEL;Maltparseri treenitud mudel (UD);MaltParser model for Estonian UD format;M\u00fc\u00fcrisep, Kaili;Center of Estonian Language Resources;2019;Issued: 2019-01-07;Updated: 2019-01-07;doi:10.15155/1-00-0000-0000-0000-00187L;Abstract;Eesti keele s\u00fcntaksianal\u00fc\u00fcsi mudel MaltParserile (http://www.maltparser.org/), treenitud EstUD v2.2 puudepangal.;Abstract;Syntax parsing model for Estonian, trained on the Estonian Universal Dependencies treebank v2.2. To be used with MaltParser (http://www.maltparser.org/).",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "58d7b2bf-b0ac-5a2d-98e1-8b9db25ca59f",
-    "notes": [
-        "Abstract",
-        "Eesti keele s\u00fcntaksianal\u00fc\u00fcsi mudel MaltParserile (http://www.maltparser.org/), treenitud EstUD v2.2 puudepangal.",
-        "Abstract",
-        "Syntax parsing model for Estonian, trained on the Estonian Universal Dependencies treebank v2.2. To be used with MaltParser (http://www.maltparser.org/)."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17960604"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Maltparseri treenitud mudel (UD)",
-        "MaltParser model for Estonian UD format"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/5949d969-1c8f-5961-9688-6058ddb8c8cb.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/5949d969-1c8f-5961-9688-6058ddb8c8cb.json
deleted file mode 100644
index 3b5401c1..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/5949d969-1c8f-5961-9688-6058ddb8c8cb.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0011FL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:8623654",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:8623654"
-    ],
-    "PublicationTimestamp": "2018-02-14T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:8623654;2019-04-12T23:31:50Z;ESTDOI;ESTDOI.KEEL;etTenTen korpus, toortekst;Web13 corpus (etTenTen), unannotated;Muischnek, Kadri;Center of Estonian Language Resources;2016;Issued: 2016-04-29;Updated: 2018-02-14;doi:10.15155/1-00-0000-0000-0000-0011FL;Abstract;etTenTen korpus (ehk Veebikorpus13) on internetist alla laetud eestikeelsete veebilehtede korpus.\nKorpuses on 270 miljonit s\u00f5na 686 000 veebilehelt.\nvt veel http://www2.keeleveeb.ee/dict/corpus/ettenten/about.html\n\nAlgmaterjal\n\nKorpuse tekstid korjas internetist ja teisendas utf-8 kodeeringus teksti kujule Vit Suchomel.\nVeebirobotiga laeti alla 1 173 702 veebilehte, kusjuures juba olemas olevate lehtede koopiad j\u00e4eti k\u00f5rvale; k\u00f5rvale j\u00e4eti ka lehed, mis on esindatud Eesti kirjakeele koondkorpuses. (http://www.cl.ut.ee/korpused/segakorpus/). Kasutati Jan Pomikaleki doktorit\u00f6\u00f6 k\u00e4igus loodud programme  jusText ja onion (code.google.com/p/justext, code.google.com/p/onion)\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5949d969-1c8f-5961-9688-6058ddb8c8cb",
-    "notes": [
-        "Abstract",
-        "etTenTen korpus (ehk Veebikorpus13) on internetist alla laetud eestikeelsete veebilehtede korpus.\nKorpuses on 270 miljonit s\u00f5na 686 000 veebilehelt.\nvt veel http://www2.keeleveeb.ee/dict/corpus/ettenten/about.html\n\nAlgmaterjal\n\nKorpuse tekstid korjas internetist ja teisendas utf-8 kodeeringus teksti kujule Vit Suchomel.\nVeebirobotiga laeti alla 1 173 702 veebilehte, kusjuures juba olemas olevate lehtede koopiad j\u00e4eti k\u00f5rvale; k\u00f5rvale j\u00e4eti ka lehed, mis on esindatud Eesti kirjakeele koondkorpuses. (http://www.cl.ut.ee/korpused/segakorpus/). Kasutati Jan Pomikaleki doktorit\u00f6\u00f6 k\u00e4igus loodud programme  jusText ja onion (code.google.com/p/justext, code.google.com/p/onion)\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:8623654"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "etTenTen korpus, toortekst",
-        "Web13 corpus (etTenTen), unannotated"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/59dde0e1-05a0-5b58-9e5a-c01c8cce74d2.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/59dde0e1-05a0-5b58-9e5a-c01c8cce74d2.json
deleted file mode 100644
index 1be3afd2..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/59dde0e1-05a0-5b58-9e5a-c01c8cce74d2.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05932L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:8926650",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:8926650"
-    ],
-    "PublicationTimestamp": "2016-08-30T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Langemets, Margit"
-    ],
-    "fulltext": "oai:oai.datacite.org:8926650;2019-01-22T12:02:20Z;ESTDOI;ESTDOI.KEEL;Eesti \u00f5igekeelsuss\u00f5naraamat \u00d5S 2013;Dictionary of Standard Estonian \u00d5S 2013;Langemets, Margit;Center of Estonian Language Resources;2016;Issued: 2016-08-30;Updated: 2016-08-30;doi:10.15155/3-00-0000-0000-0000-05932L;Abstract;Kajastab kehtivat eesti kirjakeele normi.;Abstract;\u00d5S 2013 is a normative dictionary of modern standard Estonian, giving recommendations on correct language use. It contains recommended spellings and the morphology of words, instructions on pronunciation and semantics, also some syntactic recommendations. Abbreviations, geographical names and instruction on pronouncing foreign names are attached.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "59dde0e1-05a0-5b58-9e5a-c01c8cce74d2",
-    "notes": [
-        "Abstract",
-        "Kajastab kehtivat eesti kirjakeele normi.",
-        "Abstract",
-        "\u00d5S 2013 is a normative dictionary of modern standard Estonian, giving recommendations on correct language use. It contains recommended spellings and the morphology of words, instructions on pronunciation and semantics, also some syntactic recommendations. Abbreviations, geographical names and instruction on pronouncing foreign names are attached."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:8926650"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti \u00f5igekeelsuss\u00f5naraamat \u00d5S 2013",
-        "Dictionary of Standard Estonian \u00d5S 2013"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/5a0654c8-faa1-5d96-9408-6df893c91ea0.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/5a0654c8-faa1-5d96-9408-6df893c91ea0.json
deleted file mode 100644
index ab97fdba..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/5a0654c8-faa1-5d96-9408-6df893c91ea0.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-07BD8L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:19520868",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:19520868"
-    ],
-    "PublicationTimestamp": "2019-04-05T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Soosaar, Sven-Erik"
-    ],
-    "fulltext": "oai:oai.datacite.org:19520868;2019-04-05T10:36:47Z;ESTDOI;ESTDOI.KEEL;Eesti-ersa s\u00f5naraamat;Estonian-Erzya dictionary;Soosaar, Sven-Erik;Center of Estonian Language Resources;2019;Issued: 2019-04-05;Updated: 2019-04-05;doi:10.15155/3-00-0000-0000-0000-07BD8L;Abstract;Eesti-ersa s\u00f5naraamat umbes 6000 m\u00e4rks\u00f5naga ning n\u00e4itefraaside ja -lausetega;Abstract;Estonian-Erzya Mordvin dictionary with example phrases and sentences containing ca 6000 headwords",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5a0654c8-faa1-5d96-9408-6df893c91ea0",
-    "notes": [
-        "Abstract",
-        "Eesti-ersa s\u00f5naraamat umbes 6000 m\u00e4rks\u00f5naga ning n\u00e4itefraaside ja -lausetega",
-        "Abstract",
-        "Estonian-Erzya Mordvin dictionary with example phrases and sentences containing ca 6000 headwords"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:19520868"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti-ersa s\u00f5naraamat",
-        "Estonian-Erzya dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/5b2d8b57-4aea-5fbb-9eb3-eae7826a9e32.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/5b2d8b57-4aea-5fbb-9eb3-eae7826a9e32.json
deleted file mode 100644
index a0d2dfce..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/5b2d8b57-4aea-5fbb-9eb3-eae7826a9e32.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-0576CL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:8512252",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:8512252"
-    ],
-    "PublicationTimestamp": "2016-05-23T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Pajupuu, Hille"
-    ],
-    "fulltext": "oai:oai.datacite.org:8512252;2019-04-05T15:01:07Z;ESTDOI;ESTDOI.KEEL;Emotsioonidetektor;Emotion detector;Pajupuu, Hille;Center of Estonian Language Resources;2015;Issued: 2015-05-18;Updated: 2016-05-23;doi:10.15155/3-00-0000-0000-0000-0576CL;Abstract;Vahend kirjaliku teksti l\u00f5ikude positiivsuse, negatiivsuse ja neutraalsuse tuvastamiseks.;Abstract;The Emotion Detector allows to identify the positivity, negativity and neutrality in paragraphs of written text.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5b2d8b57-4aea-5fbb-9eb3-eae7826a9e32",
-    "notes": [
-        "Abstract",
-        "Vahend kirjaliku teksti l\u00f5ikude positiivsuse, negatiivsuse ja neutraalsuse tuvastamiseks.",
-        "Abstract",
-        "The Emotion Detector allows to identify the positivity, negativity and neutrality in paragraphs of written text."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:8512252"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Emotsioonidetektor",
-        "Emotion detector"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/5ddc421c-027e-51d9-9225-747f5c2a3126.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/5ddc421c-027e-51d9-9225-747f5c2a3126.json
deleted file mode 100644
index 93963c61..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/5ddc421c-027e-51d9-9225-747f5c2a3126.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-0632BL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10303697",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10303697"
-    ],
-    "PublicationTimestamp": "2017-01-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Ermus, Liis"
-    ],
-    "fulltext": "oai:oai.datacite.org:10303697;2018-10-29T02:36:21Z;ESTDOI;ESTDOI.KEEL;Eesti Keele Instituudi fonoteek;Ermus, Liis;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2017-01-31;doi:10.15155/3-00-0000-0000-0000-0632BL;Abstract;Eesti Keele Instituudi fonoteegi lehek\u00fcljel saab kuulata eesti murrete, soome-ugri keelte ja v\u00e4liseesti keele helin\u00e4iteid.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5ddc421c-027e-51d9-9225-747f5c2a3126",
-    "notes": [
-        "Abstract",
-        "Eesti Keele Instituudi fonoteegi lehek\u00fcljel saab kuulata eesti murrete, soome-ugri keelte ja v\u00e4liseesti keele helin\u00e4iteid."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10303697"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti Keele Instituudi fonoteek"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/5de708ad-0fef-5bae-ba36-0a5aa052f631.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/5de708ad-0fef-5bae-ba36-0a5aa052f631.json
deleted file mode 100644
index 2c37bcdd..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/5de708ad-0fef-5bae-ba36-0a5aa052f631.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/TY.0012",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:4597371",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:4597371"
-    ],
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:4597371;2019-02-02T14:30:41Z;ESTDOI;ESTDOI.KEEL;Corpus of Estonian newspaper texts;Muischnek, Kadri;Center of Estonian Language Resources;2013;doi:10.15155/TY.0012",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5de708ad-0fef-5bae-ba36-0a5aa052f631",
-    "oai_identifier": [
-        "oai:oai.datacite.org:4597371"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus of Estonian newspaper texts"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/5e63ea25-13d3-5270-aa68-bf345e98405d.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/5e63ea25-13d3-5270-aa68-bf345e98405d.json
deleted file mode 100644
index 48cbb92d..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/5e63ea25-13d3-5270-aa68-bf345e98405d.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06335L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10303951",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10303951"
-    ],
-    "PublicationTimestamp": "2017-01-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laansalu, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:10303951;2019-04-11T20:01:42Z;ESTDOI;ESTDOI.KEEL;Mulgi s\u00f5nastik;Laansalu, Tiina;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2017-01-31;doi:10.15155/3-00-0000-0000-0000-06335L;Abstract;Mulgi veebis\u00f5nastikust saab s\u00f5nu otsida nii m\u00e4rks\u00f5na (murdekuju), kirjakeelse vaste (t\u00e4henduse) kui ka stiili j\u00e4rgi. M\u00e4rks\u00f5nade juurde on enamasti lisatud ka n\u00e4itelaused ning viited teistele sama v\u00f5i l\u00e4hedase t\u00e4hendusega s\u00f5nadele.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5e63ea25-13d3-5270-aa68-bf345e98405d",
-    "notes": [
-        "Abstract",
-        "Mulgi veebis\u00f5nastikust saab s\u00f5nu otsida nii m\u00e4rks\u00f5na (murdekuju), kirjakeelse vaste (t\u00e4henduse) kui ka stiili j\u00e4rgi. M\u00e4rks\u00f5nade juurde on enamasti lisatud ka n\u00e4itelaused ning viited teistele sama v\u00f5i l\u00e4hedase t\u00e4hendusega s\u00f5nadele."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10303951"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Mulgi s\u00f5nastik"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/5f424b5b-1108-56b5-a29c-813fef4582e3.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/5f424b5b-1108-56b5-a29c-813fef4582e3.json
deleted file mode 100644
index 42bc4c39..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/5f424b5b-1108-56b5-a29c-813fef4582e3.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0016CL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17939995",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17939995"
-    ],
-    "PublicationTimestamp": "2019-01-02T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Lippus, P\u00e4rtel"
-    ],
-    "fulltext": "oai:oai.datacite.org:17939995;2019-04-11T17:37:04Z;ESTDOI;ESTDOI.KEEL;Foneetikakorpuse otsimootor;Lippus, P\u00e4rtel;Center of Estonian Language Resources;2019;Issued: 2019-01-02;Updated: 2019-01-02;doi:10.15155/1-00-0000-0000-0000-0016CL;Abstract;Veebip\u00f5hine otsingumootor v\u00f5imaldab otsida korpusest \u00fche s\u00f5na piires, vastuseks antakse 2-sekundiline helil\u00f5ik ja selle m\u00e4rgendus.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5f424b5b-1108-56b5-a29c-813fef4582e3",
-    "notes": [
-        "Abstract",
-        "Veebip\u00f5hine otsingumootor v\u00f5imaldab otsida korpusest \u00fche s\u00f5na piires, vastuseks antakse 2-sekundiline helil\u00f5ik ja selle m\u00e4rgendus."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17939995"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Foneetikakorpuse otsimootor"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/5ff73c72-0540-520a-807e-679611ab9cf3.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/5ff73c72-0540-520a-807e-679611ab9cf3.json
deleted file mode 100644
index c7534563..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/5ff73c72-0540-520a-807e-679611ab9cf3.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-07BDCL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:19520878",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:19520878"
-    ],
-    "PublicationTimestamp": "2019-02-05T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Koppel, Kristina",
-        "Kallas, Jelena"
-    ],
-    "fulltext": "oai:oai.datacite.org:19520878;2019-04-05T10:36:54Z;ESTDOI;ESTDOI.KEEL;Koolieelikute s\u00f5navara;Kallas, Jelena;Koppel, Kristina;Center of Estonian Language Resources;2019;Issued: 2019-02-05;Updated: 2019-02-05;doi:10.15155/3-00-0000-0000-0000-07BDCL;Abstract;Eesti keele kui teise keele s\u00f5navara loendit koolieelikutele. S\u00f5naloend sisaldab kokku 1147 s\u00f5na ning selle koostajad on eksperdid Tallinna \u00dclikooli professor Reili Argus, lasteaia\u00f5petaja ja eesti keele \u00f5pikute autor Lea Maiberg ning lasteaia\u00f5petaja Mariana Koho. Eksperte konsulteerisid Eesti Keele Instituudi spetsialistid Jelena Kallas ja Kristina Koppel.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "5ff73c72-0540-520a-807e-679611ab9cf3",
-    "notes": [
-        "Abstract",
-        "Eesti keele kui teise keele s\u00f5navara loendit koolieelikutele. S\u00f5naloend sisaldab kokku 1147 s\u00f5na ning selle koostajad on eksperdid Tallinna \u00dclikooli professor Reili Argus, lasteaia\u00f5petaja ja eesti keele \u00f5pikute autor Lea Maiberg ning lasteaia\u00f5petaja Mariana Koho. Eksperte konsulteerisid Eesti Keele Instituudi spetsialistid Jelena Kallas ja Kristina Koppel."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:19520878"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Koolieelikute s\u00f5navara"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/61165b93-81e2-5999-8957-81fbc6c83622.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/61165b93-81e2-5999-8957-81fbc6c83622.json
deleted file mode 100644
index 23ce1be8..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/61165b93-81e2-5999-8957-81fbc6c83622.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0014BL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14066264",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14066264"
-    ],
-    "PublicationTimestamp": "2018-01-26T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Lippus, P\u00e4rtel"
-    ],
-    "fulltext": "oai:oai.datacite.org:14066264;2019-01-29T11:01:55Z;ESTDOI;ESTDOI.KEEL;Pikad s\u00f5nad;Long words in Estonian;Lippus, P\u00e4rtel;Center of Estonian Language Resources;2018;Issued: 2018-01-26;Updated: 2018-01-26;doi:10.15155/1-00-0000-0000-0000-0014BL;Abstract;140 eri silbistruktuuriga 4-6 silbilist s\u00f5na. Salvestatud s\u00f5naloendina 2 keelejuhilt ning raamlauses 6 V\u00f5ru ja 7 Saaremaa keelejuhilt.\n40 l\u00fchikeste lahtiste silpidega 5-6 silbilist s\u00f5na. Salvestatud raamlauses 6 \u00fchiskeelselt keelejuhilt.\n\nMaterjali on kasutatud siin:\nPajusalu, K., Help, T., Lippus, P., Niit, E., Teras, P., & Viitso, T.-R. (2005). On the temporal structure of Estonian secondary-stressed feet. Linguistica Uralica, 41(2), 98\u2013106.\nLippus, P., Pajusalu, K., & Teras, P. (2006). The Temporal Structure of Penta- and Hexasyllabic Words in Estonian. In R. Hoffmann & H. Mixdorff (Eds.), Proceedings of the 3rd International Conference Speech Prosody (pp. 759\u2013762). Dresden: TUDpress. Retrieved from http://www.isca-speech.org/archive/sp2006/papers/sp06_103.pdf\n;Abstract;A list of 140 words with 4-6 syllables with different syllable structure. Read by 2 speakers in word list and by 6 V\u00f5ru dialect speakers and 7 Saaremaa dialect speakers in carrier sentences.\nA list of 40 words with 5-6 syllables with short open syllables. Read by 6 Standard Estonian speakers in carrier sentences.\n\nThe data was collected for:\nPajusalu, K., Help, T., Lippus, P., Niit, E., Teras, P., & Viitso, T.-R. (2005). On the temporal structure of Estonian secondary-stressed feet. Linguistica Uralica, 41(2), 98\u2013106.\nLippus, P., Pajusalu, K., & Teras, P. (2006). The Temporal Structure of Penta- and Hexasyllabic Words in Estonian. In R. Hoffmann & H. Mixdorff (Eds.), Proceedings of the 3rd International Conference Speech Prosody (pp. 759\u2013762). Dresden: TUDpress. Retrieved from http://www.isca-speech.org/archive/sp2006/papers/sp06_103.pdf\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "61165b93-81e2-5999-8957-81fbc6c83622",
-    "notes": [
-        "Abstract",
-        "140 eri silbistruktuuriga 4-6 silbilist s\u00f5na. Salvestatud s\u00f5naloendina 2 keelejuhilt ning raamlauses 6 V\u00f5ru ja 7 Saaremaa keelejuhilt.\n40 l\u00fchikeste lahtiste silpidega 5-6 silbilist s\u00f5na. Salvestatud raamlauses 6 \u00fchiskeelselt keelejuhilt.\n\nMaterjali on kasutatud siin:\nPajusalu, K., Help, T., Lippus, P., Niit, E., Teras, P., & Viitso, T.-R. (2005). On the temporal structure of Estonian secondary-stressed feet. Linguistica Uralica, 41(2), 98\u2013106.\nLippus, P., Pajusalu, K., & Teras, P. (2006). The Temporal Structure of Penta- and Hexasyllabic Words in Estonian. In R. Hoffmann & H. Mixdorff (Eds.), Proceedings of the 3rd International Conference Speech Prosody (pp. 759\u2013762). Dresden: TUDpress. Retrieved from http://www.isca-speech.org/archive/sp2006/papers/sp06_103.pdf\n",
-        "Abstract",
-        "A list of 140 words with 4-6 syllables with different syllable structure. Read by 2 speakers in word list and by 6 V\u00f5ru dialect speakers and 7 Saaremaa dialect speakers in carrier sentences.\nA list of 40 words with 5-6 syllables with short open syllables. Read by 6 Standard Estonian speakers in carrier sentences.\n\nThe data was collected for:\nPajusalu, K., Help, T., Lippus, P., Niit, E., Teras, P., & Viitso, T.-R. (2005). On the temporal structure of Estonian secondary-stressed feet. Linguistica Uralica, 41(2), 98\u2013106.\nLippus, P., Pajusalu, K., & Teras, P. (2006). The Temporal Structure of Penta- and Hexasyllabic Words in Estonian. In R. Hoffmann & H. Mixdorff (Eds.), Proceedings of the 3rd International Conference Speech Prosody (pp. 759\u2013762). Dresden: TUDpress. Retrieved from http://www.isca-speech.org/archive/sp2006/papers/sp06_103.pdf\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14066264"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Pikad s\u00f5nad",
-        "Long words in Estonian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/61681124-97b2-599d-818a-3549659d2af4.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/61681124-97b2-599d-818a-3549659d2af4.json
deleted file mode 100644
index a39e892b..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/61681124-97b2-599d-818a-3549659d2af4.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00186L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17950897",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17950897"
-    ],
-    "PublicationTimestamp": "2019-01-04T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Iva, Sulev"
-    ],
-    "fulltext": "oai:oai.datacite.org:17950897;2019-03-07T18:25:55Z;ESTDOI;ESTDOI.KEEL;V\u00f5ru ja Setu ilukirjanduskorpus;V\u00f5ro ja seto kir\u00e4nd\u00fcskogo;Iva, Sulev;Center of Estonian Language Resources;2019;Issued: 2019-01-04;Updated: 2019-01-04;doi:10.15155/1-00-0000-0000-0000-00186L;Abstract;Ilukirjanduse korpuse kogumahuks on ca 350 000 s\u00f5na, korpus on viimase aasta jooksul muudetud tekstiarhiivist avalikuks keelekorpuseks koos vajaliku kasutajaliidesega, mis asub aadressil http://synaq.org/ilo.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "61681124-97b2-599d-818a-3549659d2af4",
-    "notes": [
-        "Abstract",
-        "Ilukirjanduse korpuse kogumahuks on ca 350 000 s\u00f5na, korpus on viimase aasta jooksul muudetud tekstiarhiivist avalikuks keelekorpuseks koos vajaliku kasutajaliidesega, mis asub aadressil http://synaq.org/ilo."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17950897"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "V\u00f5ru ja Setu ilukirjanduskorpus",
-        "V\u00f5ro ja seto kir\u00e4nd\u00fcskogo"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/61c41c2d-3ce7-5514-bbb3-c6bb01612be6.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/61c41c2d-3ce7-5514-bbb3-c6bb01612be6.json
deleted file mode 100644
index 9ef07d18..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/61c41c2d-3ce7-5514-bbb3-c6bb01612be6.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00080L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5757477",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5757477"
-    ],
-    "PublicationTimestamp": "2015-05-22T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "M\u00fc\u00fcrisep, Kaili"
-    ],
-    "fulltext": "oai:oai.datacite.org:5757477;2019-04-18T17:36:31Z;ESTDOI;ESTDOI.KEEL;Eesti puudepanga korpus;Estonian Treebank;M\u00fc\u00fcrisep, Kaili;Center of Estonian Language Resources;2011;Issued: 2011-12-31;Updated: 2015-05-22;doi:10.15155/1-00-0000-0000-0000-00080L;Abstract;Estonian Treebank is available both in the VISL and TigerXML format. Esttre consists of ca 1400 manually annotated sentences (10600 tokens), the text classes represented in the Corpus are fiction, both translated and original, newspaper texts and 20 sentences of transcribed spoken language.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "61c41c2d-3ce7-5514-bbb3-c6bb01612be6",
-    "notes": [
-        "Abstract",
-        "Estonian Treebank is available both in the VISL and TigerXML format. Esttre consists of ca 1400 manually annotated sentences (10600 tokens), the text classes represented in the Corpus are fiction, both translated and original, newspaper texts and 20 sentences of transcribed spoken language."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5757477"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti puudepanga korpus",
-        "Estonian Treebank"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/61c528a1-e5aa-5a39-a888-c0c5bb7b0d91.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/61c528a1-e5aa-5a39-a888-c0c5bb7b0d91.json
deleted file mode 100644
index e76fb3e0..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/61c528a1-e5aa-5a39-a888-c0c5bb7b0d91.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-00016L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5757504",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5757504"
-    ],
-    "PublicationTimestamp": "2017-03-03T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Mihkla, Meelis"
-    ],
-    "fulltext": "oai:oai.datacite.org:5757504;2019-04-22T13:02:04Z;ESTDOI;ESTDOI.KEEL;Eestikeelne k\u00f5nes\u00fcntees;Text-to-Speech Synthesis for Estonian;Mihkla, Meelis;Center of Estonian Language Resources;2013;Issued: 2013-01-07;Updated: 2017-03-03;doi:10.15155/3-00-0000-0000-0000-00016L;Abstract;K\u00f5nes\u00fcnteesikeskkond koondab endas eesti keele tekst-k\u00f5ne s\u00fcnteesi erinevaid variante, rakendusi, liideseid ja muid materjale, mis s\u00fcnteesimiseks on loodud. Kuulata saab erinevaid eestikeelseid s\u00fcnteesh\u00e4\u00e4li ning neid ka alla laadida. Samuti saab alla laadida s\u00fcnteesi kasutavaid rakendusi nii nutitelefonidele kui ka arvutitele.;Abstract;TTS for Estonian is corpus based system that uses diphones, formants, unit selection and statistical parametres for various speech models.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "61c528a1-e5aa-5a39-a888-c0c5bb7b0d91",
-    "notes": [
-        "Abstract",
-        "K\u00f5nes\u00fcnteesikeskkond koondab endas eesti keele tekst-k\u00f5ne s\u00fcnteesi erinevaid variante, rakendusi, liideseid ja muid materjale, mis s\u00fcnteesimiseks on loodud. Kuulata saab erinevaid eestikeelseid s\u00fcnteesh\u00e4\u00e4li ning neid ka alla laadida. Samuti saab alla laadida s\u00fcnteesi kasutavaid rakendusi nii nutitelefonidele kui ka arvutitele.",
-        "Abstract",
-        "TTS for Estonian is corpus based system that uses diphones, formants, unit selection and statistical parametres for various speech models."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5757504"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eestikeelne k\u00f5nes\u00fcntees",
-        "Text-to-Speech Synthesis for Estonian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/63212875-4ab9-5761-b3be-9fa6cd4c7c4a.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/63212875-4ab9-5761-b3be-9fa6cd4c7c4a.json
deleted file mode 100644
index 29b0aac8..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/63212875-4ab9-5761-b3be-9fa6cd4c7c4a.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-0009AL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17957571",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17957571"
-    ],
-    "PublicationTimestamp": "2019-01-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Alum\u00e4e, Tanel"
-    ],
-    "fulltext": "oai:oai.datacite.org:17957571;2019-03-27T14:30:56Z;ESTDOI;ESTDOI.KEEL;Eestikeelse k\u00f5netuvastuss\u00fcssteemi h\u00e4\u00e4ldusleksikoni genereerija;Alum\u00e4e, Tanel;Center of Estonian Language Resources;2019;Issued: 2019-01-07;Updated: 2019-01-07;doi:10.15155/9-00-0000-0000-0000-0009AL;Abstract;Genereerib h\u00e4\u00e4ldusleksikoni",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "63212875-4ab9-5761-b3be-9fa6cd4c7c4a",
-    "notes": [
-        "Abstract",
-        "Genereerib h\u00e4\u00e4ldusleksikoni"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17957571"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eestikeelse k\u00f5netuvastuss\u00fcssteemi h\u00e4\u00e4ldusleksikoni genereerija"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6347a1bf-65ae-52bf-80ee-7685fa50cbd8.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6347a1bf-65ae-52bf-80ee-7685fa50cbd8.json
deleted file mode 100644
index 2ed2b51b..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6347a1bf-65ae-52bf-80ee-7685fa50cbd8.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-0576BL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:8512250",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:8512250"
-    ],
-    "PublicationTimestamp": "2017-04-11T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Langemets, Margit"
-    ],
-    "fulltext": "oai:oai.datacite.org:8512250;2019-04-17T23:01:37Z;ESTDOI;ESTDOI.KEEL;Eesti keele seletav s\u00f5naraamat EKSS 2009;The Explanatory Dictionary of the Estonian Language;Langemets, Margit;Center of Estonian Language Resources;2015;Issued: 2015-05-06;Updated: 2017-04-11;doi:10.15155/3-00-0000-0000-0000-0576BL;Abstract;Suurim eesti keele s\u00f5naraamat, mis h\u00f5lmab kogu eesti kirjakeelt, k.a k\u00f5nekeelt ja oskuskeelt.  Oma t\u00fc\u00fcbilt on s\u00f5naraamat kirjeldav (deskriptiivne), mitte normiv (preskriptiivne).\n\nLangemets, Margit; Tiits, Mai; Valdre, Tiia; Veskis, Leidi; Viks, \u00dclle; Voll, Piret (2009). Eesti keele seletav s\u00f5naraamat. Eesti Keele Sihtasutus.\n;Abstract;The biggest dictionary of the Estonian language, which covers Estonian standard language as a whole, including spoken language and special languages.\n\nLangemets, Margit; Tiits, Mai; Valdre, Tiia; Veskis, Leidi; Viks, \u00dclle; Voll, Piret (2009). Eesti keele seletav s\u00f5naraamat [The Explanatory Dictionary of the Estonian Language]. Eesti Keele Sihtasutus.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6347a1bf-65ae-52bf-80ee-7685fa50cbd8",
-    "notes": [
-        "Abstract",
-        "Suurim eesti keele s\u00f5naraamat, mis h\u00f5lmab kogu eesti kirjakeelt, k.a k\u00f5nekeelt ja oskuskeelt.  Oma t\u00fc\u00fcbilt on s\u00f5naraamat kirjeldav (deskriptiivne), mitte normiv (preskriptiivne).\n\nLangemets, Margit; Tiits, Mai; Valdre, Tiia; Veskis, Leidi; Viks, \u00dclle; Voll, Piret (2009). Eesti keele seletav s\u00f5naraamat. Eesti Keele Sihtasutus.\n",
-        "Abstract",
-        "The biggest dictionary of the Estonian language, which covers Estonian standard language as a whole, including spoken language and special languages.\n\nLangemets, Margit; Tiits, Mai; Valdre, Tiia; Veskis, Leidi; Viks, \u00dclle; Voll, Piret (2009). Eesti keele seletav s\u00f5naraamat [The Explanatory Dictionary of the Estonian Language]. Eesti Keele Sihtasutus."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:8512250"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele seletav s\u00f5naraamat EKSS 2009",
-        "The Explanatory Dictionary of the Estonian Language"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/63dc8fe1-619c-5572-a57f-3a5a8c4decfc.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/63dc8fe1-619c-5572-a57f-3a5a8c4decfc.json
deleted file mode 100644
index e582d9d3..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/63dc8fe1-619c-5572-a57f-3a5a8c4decfc.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0016EL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17940191",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17940191"
-    ],
-    "PublicationTimestamp": "2019-01-02T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:17940191;2019-04-11T17:37:05Z;ESTDOI;ESTDOI.KEEL;Maltparseri anal\u00fc\u00fcsitud koondkorpus 1.0;Muischnek, Kadri;Center of Estonian Language Resources;2019;Issued: 2019-01-02;Updated: 2019-01-02;doi:10.15155/1-00-0000-0000-0000-0016EL;Abstract;MaltParser, treenitud kasutades eesti keele s\u00f5ltuvuspuude panga allosa (14 114 lauset, 197 508 s\u00f5na ja kirjavahem\u00e4rki, 164 637 s\u00f5na (ilma kirjavahem\u00e4rkideta); 4/5 kasutatud korpusest), testitud (1764 lauset, 24208 tekstis\u00f5na koos kirjavahem\u00e4rkidega (1/10)), MaltParseri treenitud mudel.\n\nTulemused morfoloogiliselt \u00fchese testkorpuse korral:\nLA (s\u00fcntaktilise m\u00e4rgendi korrektsus) 90.2%,\nLAS (s\u00f5ltuvusseose ja s\u00fcntaktilise m\u00e4rgendi korrektsus) 83.8%,\nUAS (s\u00f5ltuvusseose m\u00e4\u00e4ramise korrektsus) 86.5%\n\nMaltParseri tulemused, kasutades automaatselt morfoloogiliselt \u00fchestatud sisendit:\n\nLA (s\u00fcntaktilise m\u00e4rgendi korrektsus) 84.6%,\nLAS (s\u00f5ltuvusseose ja s\u00fcntaktilise m\u00e4rgendi korrektsus) 76.6%,\nUAS (s\u00f5ltuvusseose m\u00e4\u00e4ramise korrektsus) 81.0%.\n\nAnal\u00fc\u00fcsides m\u00f5lema parseri tugevaid k\u00fclgi ja kombineerides neid omavahel, paranes LAS veel u \u00fche protsendi v\u00f5rra.\n\nMaltParseri anal\u00fc\u00fcsitud koondkorpus (ajakirjandus, ilukirjandus, teaduskirjandus).",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "63dc8fe1-619c-5572-a57f-3a5a8c4decfc",
-    "notes": [
-        "Abstract",
-        "MaltParser, treenitud kasutades eesti keele s\u00f5ltuvuspuude panga allosa (14 114 lauset, 197 508 s\u00f5na ja kirjavahem\u00e4rki, 164 637 s\u00f5na (ilma kirjavahem\u00e4rkideta); 4/5 kasutatud korpusest), testitud (1764 lauset, 24208 tekstis\u00f5na koos kirjavahem\u00e4rkidega (1/10)), MaltParseri treenitud mudel.\n\nTulemused morfoloogiliselt \u00fchese testkorpuse korral:\nLA (s\u00fcntaktilise m\u00e4rgendi korrektsus) 90.2%,\nLAS (s\u00f5ltuvusseose ja s\u00fcntaktilise m\u00e4rgendi korrektsus) 83.8%,\nUAS (s\u00f5ltuvusseose m\u00e4\u00e4ramise korrektsus) 86.5%\n\nMaltParseri tulemused, kasutades automaatselt morfoloogiliselt \u00fchestatud sisendit:\n\nLA (s\u00fcntaktilise m\u00e4rgendi korrektsus) 84.6%,\nLAS (s\u00f5ltuvusseose ja s\u00fcntaktilise m\u00e4rgendi korrektsus) 76.6%,\nUAS (s\u00f5ltuvusseose m\u00e4\u00e4ramise korrektsus) 81.0%.\n\nAnal\u00fc\u00fcsides m\u00f5lema parseri tugevaid k\u00fclgi ja kombineerides neid omavahel, paranes LAS veel u \u00fche protsendi v\u00f5rra.\n\nMaltParseri anal\u00fc\u00fcsitud koondkorpus (ajakirjandus, ilukirjandus, teaduskirjandus)."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17940191"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Maltparseri anal\u00fc\u00fcsitud koondkorpus 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6413f65a-701f-52ca-bc9c-a2bbe0c1f36c.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6413f65a-701f-52ca-bc9c-a2bbe0c1f36c.json
deleted file mode 100644
index b69b7b30..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6413f65a-701f-52ca-bc9c-a2bbe0c1f36c.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00160L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:15015402",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:15015402"
-    ],
-    "PublicationTimestamp": "2018-05-10T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laur, Sven"
-    ],
-    "fulltext": "oai:oai.datacite.org:15015402;2019-04-17T17:27:12Z;ESTDOI;ESTDOI.KEEL;EstNLTK teek Pythoni jaoks (ver.1.4);EstNLTK library for Python (ver.1.4);Laur, Sven;Center of Estonian Language Resources;2018;Issued: 2018-05-04;Updated: 2018-05-10;doi:10.15155/1-00-0000-0000-0000-00160L;Abstract;Loodud EstNLTK teek 1.4 koondab keeletehnoloogilised t\u00f6\u00f6riistad \u00fchtseks tervikuks: - olemasolevad t\u00f6\u00f6riistad liidestatud EstNLTK teegiga, - andmevahetus toimub struktureeritult l\u00e4bi Python-i klasside, - iga komponendi ja anal\u00fc\u00fcsi jaoks on loodud \u00fclevaatlikud juhendmaterjalid. Teegi kasutamine muudab k\u00e4ttesaadavaks peamised keeletehnoloogilised operatsioonid: - lausestamine ja s\u00f5nestamine, - morfoloogiline anal\u00fc\u00fcs, - osalausestamine, - ajav\u00e4ljendite tuvastus, - nimeolemite tuvastus, - verbifraaside tuvastus, - nimis\u00f5nafraaside tuvastus, - omaduss\u00f5nafraaside tuvastus, - pinds\u00fcntaktiline anal\u00fc\u00fcs.;Abstract;EstNLTK provides common natural language processing functionality such as paragraph, sentence and word tokenization, morphological analysis, named entity recognition, etc. for the Estonian language. This is the old branch, which contains full functionality of different analysis tools. Available via Anaconda package repository for Python 3.5. PyPI packages are also available for Python 3.4+ and 2.7. Python 3.6 is not supported.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6413f65a-701f-52ca-bc9c-a2bbe0c1f36c",
-    "notes": [
-        "Abstract",
-        "Loodud EstNLTK teek 1.4 koondab keeletehnoloogilised t\u00f6\u00f6riistad \u00fchtseks tervikuks: - olemasolevad t\u00f6\u00f6riistad liidestatud EstNLTK teegiga, - andmevahetus toimub struktureeritult l\u00e4bi Python-i klasside, - iga komponendi ja anal\u00fc\u00fcsi jaoks on loodud \u00fclevaatlikud juhendmaterjalid. Teegi kasutamine muudab k\u00e4ttesaadavaks peamised keeletehnoloogilised operatsioonid: - lausestamine ja s\u00f5nestamine, - morfoloogiline anal\u00fc\u00fcs, - osalausestamine, - ajav\u00e4ljendite tuvastus, - nimeolemite tuvastus, - verbifraaside tuvastus, - nimis\u00f5nafraaside tuvastus, - omaduss\u00f5nafraaside tuvastus, - pinds\u00fcntaktiline anal\u00fc\u00fcs.",
-        "Abstract",
-        "EstNLTK provides common natural language processing functionality such as paragraph, sentence and word tokenization, morphological analysis, named entity recognition, etc. for the Estonian language. This is the old branch, which contains full functionality of different analysis tools. Available via Anaconda package repository for Python 3.5. PyPI packages are also available for Python 3.4+ and 2.7. Python 3.6 is not supported."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:15015402"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "EstNLTK teek Pythoni jaoks (ver.1.4)",
-        "EstNLTK library for Python (ver.1.4)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/64e9cb18-ef33-5f23-a970-245573a3b50e.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/64e9cb18-ef33-5f23-a970-245573a3b50e.json
deleted file mode 100644
index 35d7c9cc..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/64e9cb18-ef33-5f23-a970-245573a3b50e.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00153L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14560569",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14560569"
-    ],
-    "PublicationTimestamp": "2018-02-14T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Lippus, P\u00e4rtel"
-    ],
-    "fulltext": "oai:oai.datacite.org:14560569;2019-02-02T17:00:58Z;ESTDOI;ESTDOI.KEEL;Eesti keele spontaanse k\u00f5ne foneetiline korpus v.1.0.4;Phonetic Corpus of Estonian Spontaneous Speech v.1.0.4;Lippus, P\u00e4rtel;Center of Estonian Language Resources;2018;Issued: 2018-02-14;Updated: 2018-02-14;doi:10.15155/1-00-0000-0000-0000-00153L;Abstract;The aim of the corpus is to compile a large amount of quality recordings of spontaneous Estonian and segment it phonetically on different levels. The project started in autumn 2006.\n\nThe total size of the corpus is approximately 90 hours of speech from 130 speakers with different dialectological and social background. Speakers are from different age groups. They are asked to participate with face-to-face invitation and they are aware of the purpose of the recordings.\n\nMost of the recordings are made in a recording studio, some also on fieldwork. The signal of each speaker is recorded in a separate channel. The distance between the speakers is about 3 meters to minimize the effect of overlaps. For the field-work recordings head-set microphones are used. Recordings are saved in PCM wav-format and are not compressed. Background information about the recordings is collected in a text-file.\nSegmentation and annotation files are saved as Praat TextGrid files and get same filenames as recordings segmented.\n\nSegmentation and annotation\nSegmentation and annotation is done with the Praat program (www.praat.org). Recordings are segmented manually on different levels (automatic segmentation program is also elaborated and tested).\nFollowing tiers are used:\n-Words (in orthographic spelling),\n-Phonemes (SAMPA adjusted for Estonian is used for transcription),\n-Syllables (short \u2013 long, open \u2013 closed),\n-Prosodic feet,\n-Intonation phrases or inter-pausal units;\n-Changes in voice quality (e.g. creaky voice);",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "64e9cb18-ef33-5f23-a970-245573a3b50e",
-    "notes": [
-        "Abstract",
-        "The aim of the corpus is to compile a large amount of quality recordings of spontaneous Estonian and segment it phonetically on different levels. The project started in autumn 2006.\n\nThe total size of the corpus is approximately 90 hours of speech from 130 speakers with different dialectological and social background. Speakers are from different age groups. They are asked to participate with face-to-face invitation and they are aware of the purpose of the recordings.\n\nMost of the recordings are made in a recording studio, some also on fieldwork. The signal of each speaker is recorded in a separate channel. The distance between the speakers is about 3 meters to minimize the effect of overlaps. For the field-work recordings head-set microphones are used. Recordings are saved in PCM wav-format and are not compressed. Background information about the recordings is collected in a text-file.\nSegmentation and annotation files are saved as Praat TextGrid files and get same filenames as recordings segmented.\n\nSegmentation and annotation\nSegmentation and annotation is done with the Praat program (www.praat.org). Recordings are segmented manually on different levels (automatic segmentation program is also elaborated and tested).\nFollowing tiers are used:\n-Words (in orthographic spelling),\n-Phonemes (SAMPA adjusted for Estonian is used for transcription),\n-Syllables (short \u2013 long, open \u2013 closed),\n-Prosodic feet,\n-Intonation phrases or inter-pausal units;\n-Changes in voice quality (e.g. creaky voice);"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14560569"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele spontaanse k\u00f5ne foneetiline korpus v.1.0.4",
-        "Phonetic Corpus of Estonian Spontaneous Speech v.1.0.4"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/664be363-a810-506a-bd06-3e96287b61ab.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/664be363-a810-506a-bd06-3e96287b61ab.json
deleted file mode 100644
index b53ca360..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/664be363-a810-506a-bd06-3e96287b61ab.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05B49L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9352867",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9352867"
-    ],
-    "PublicationTimestamp": "2017-02-16T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek",
-        "Langemets, Margit"
-    ],
-    "fulltext": "oai:oai.datacite.org:9352867;2018-10-21T15:46:47Z;ESTDOI;ESTDOI.KEEL;L\u00e4ti-eesti s\u00f5naraamat;The Latvian-Estonian Dictionary;Latvie\u0161u-igau\u0146u v\u0101rdn\u012bca;Hein, Indrek;Langemets, Margit;Center of Estonian Language Resources;2016;Issued: 2016-10-31;Updated: 2017-02-16;doi:10.15155/3-00-0000-0000-0000-05B49L;Abstract;Kahesuunaline l\u00e4ti-eesti s\u00f5naraamat, mis sisaldab ligi 47 000 m\u00e4rks\u00f5naartiklit. ;Abstract;A two-way Latvian-Estonian dictionary of nearly 47,000 entries.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "664be363-a810-506a-bd06-3e96287b61ab",
-    "notes": [
-        "Abstract",
-        "Kahesuunaline l\u00e4ti-eesti s\u00f5naraamat, mis sisaldab ligi 47 000 m\u00e4rks\u00f5naartiklit. ",
-        "Abstract",
-        "A two-way Latvian-Estonian dictionary of nearly 47,000 entries."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9352867"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "L\u00e4ti-eesti s\u00f5naraamat",
-        "The Latvian-Estonian Dictionary",
-        "Latvie\u0161u-igau\u0146u v\u0101rdn\u012bca"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/66cc1b09-7f40-502a-8a52-aa2a0b695f62.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/66cc1b09-7f40-502a-8a52-aa2a0b695f62.json
deleted file mode 100644
index 55f9fb64..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/66cc1b09-7f40-502a-8a52-aa2a0b695f62.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-0592AL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:8923003",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:8923003"
-    ],
-    "PublicationTimestamp": "2016-08-30T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Nurk, T\u00f5nis"
-    ],
-    "fulltext": "oai:oai.datacite.org:8923003;2018-12-10T04:02:48Z;ESTDOI;ESTDOI.KEEL;EKI terminibaaside s\u00fcsteem;Nurk, T\u00f5nis;Center of Estonian Language Resources;2015;Issued: 2015-05-08;Updated: 2016-08-30;doi:10.15155/3-00-0000-0000-0000-0592AL;Abstract;Terminology Management Software of IEL",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "66cc1b09-7f40-502a-8a52-aa2a0b695f62",
-    "notes": [
-        "Abstract",
-        "Terminology Management Software of IEL"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:8923003"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "EKI terminibaaside s\u00fcsteem"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/67e3d341-5bd4-5ca7-9155-ead5628f9988.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/67e3d341-5bd4-5ca7-9155-ead5628f9988.json
deleted file mode 100644
index 9f1ec902..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/67e3d341-5bd4-5ca7-9155-ead5628f9988.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-07024L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14432586",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14432586"
-    ],
-    "PublicationTimestamp": "2018-03-14T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Soon, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:14432586;2019-04-20T17:37:11Z;ESTDOI;ESTDOI.KEEL;Militerm v20180801;Militerm v20180801;Soon, Tiina;Center of Estonian Language Resources;2018;Issued: 2018-03-14;Updated: 2018-03-14;doi:10.15155/3-00-0000-0000-0000-07024L;Abstract;Militerm on s\u00f5janduse, julgeoleku- ja kaitsepoliitika terminite andmebaas, kus saab m\u00e4rks\u00f5nu otsida eesti, inglise, prantsuse ja saksa keeles. Eesti- ja ingliskeelsete terminite juures on ka oskuss\u00f5nade definitsioonid.;Abstract;MILITERM is a multilingual termbase of military, security and defense terms, enabling search by Estonian, English, French and German keywords. The Estonian and English terms are provided with definitions.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "67e3d341-5bd4-5ca7-9155-ead5628f9988",
-    "notes": [
-        "Abstract",
-        "Militerm on s\u00f5janduse, julgeoleku- ja kaitsepoliitika terminite andmebaas, kus saab m\u00e4rks\u00f5nu otsida eesti, inglise, prantsuse ja saksa keeles. Eesti- ja ingliskeelsete terminite juures on ka oskuss\u00f5nade definitsioonid.",
-        "Abstract",
-        "MILITERM is a multilingual termbase of military, security and defense terms, enabling search by Estonian, English, French and German keywords. The Estonian and English terms are provided with definitions."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14432586"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Militerm v20180801",
-        "Militerm v20180801"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/68424f0a-5172-5713-84ee-70524c3ac54d.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/68424f0a-5172-5713-84ee-70524c3ac54d.json
deleted file mode 100644
index 301b2368..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/68424f0a-5172-5713-84ee-70524c3ac54d.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-0633AL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10304013",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10304013"
-    ],
-    "PublicationTimestamp": "2017-04-11T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Langemets, Margit"
-    ],
-    "fulltext": "oai:oai.datacite.org:10304013;2019-04-22T14:31:07Z;ESTDOI;ESTDOI.KEEL; Eesti viipekeele - eesti keele veebis\u00f5nastik ;The Online Dictionary of the Estonian Sign Language \u2013 Estonian;Langemets, Margit;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2017-04-11;doi:10.15155/3-00-0000-0000-0000-0633AL;Abstract;S\u00f5nastik sisaldab \u00fcle 4000 m\u00e4rks\u00f5na ning v\u00f5imaldab otsingut eestikeelse s\u00f5na v\u00f5i eesti viipekeele viipe alusel. S\u00f5nastik on m\u00f5eldud nii eesti viipekeele \u00f5ppijatele kui ka eesti viipekeele kasutajatele eesti keele \u00f5ppimiseks.;Abstract;The dictionary contains over 4000 entry words, enabling search either by an Estonian word or a by a sign of Estonian sign language. The target users are learners of Estonian sign language and the users of Estonian sign language who study Estonian.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "68424f0a-5172-5713-84ee-70524c3ac54d",
-    "notes": [
-        "Abstract",
-        "S\u00f5nastik sisaldab \u00fcle 4000 m\u00e4rks\u00f5na ning v\u00f5imaldab otsingut eestikeelse s\u00f5na v\u00f5i eesti viipekeele viipe alusel. S\u00f5nastik on m\u00f5eldud nii eesti viipekeele \u00f5ppijatele kui ka eesti viipekeele kasutajatele eesti keele \u00f5ppimiseks.",
-        "Abstract",
-        "The dictionary contains over 4000 entry words, enabling search either by an Estonian word or a by a sign of Estonian sign language. The target users are learners of Estonian sign language and the users of Estonian sign language who study Estonian."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10304013"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        " Eesti viipekeele - eesti keele veebis\u00f5nastik ",
-        "The Online Dictionary of the Estonian Sign Language \u2013 Estonian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/686c710a-97c4-5f9c-a5e6-529eb6fec26b.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/686c710a-97c4-5f9c-a5e6-529eb6fec26b.json
deleted file mode 100644
index ea65522a..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/686c710a-97c4-5f9c-a5e6-529eb6fec26b.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06326L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10283400",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10283400"
-    ],
-    "PublicationTimestamp": "2017-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Viikberg, J\u00fcri"
-    ],
-    "fulltext": "oai:oai.datacite.org:10283400;2019-04-01T17:36:59Z;ESTDOI;ESTDOI.KEEL;Kihnu s\u00f5naraamat;The Dictionary of the Kihnu Dialect ;Viikberg, J\u00fcri;Center of Estonian Language Resources;2017;Issued: 2017-01-26;Updated: 2017-02-15;doi:10.15155/3-00-0000-0000-0000-06326L;Abstract; \u201eKihnu s\u00f5naraamat\u201c h\u00f5lmab s\u00f5navara murdekeelest, mida k\u00f5neldakse Kihnus ja Manijal. Raamatusse on mahtunud enam kui 6000 s\u00f5na, lisaks veel valik isiku- ning kohanimesid. M\u00e4rks\u00f5nade hulka on valitud nii Kihnule iseloomulikke iidseid s\u00f5nu kui ka neid, mis on murdekeelde tulnud alles viimastel k\u00fcmnenditel. S\u00f5nade tarvitamist h\u00f5lbustavad lisatud p\u00f5hivormid ja n\u00e4itelaused nii kihnu kui ka kirjakeeles.\nS\u00f5naraamatu on koostanud Reene Leas, Reti K\u00f6nninge, Silvi Murulauk ja Ellen Niit ning toimetanud Karl Pajusalu ja J\u00fcri Viikberg.\nS\u00f5naraamat on m\u00f5eldud eelk\u00f5ige kihnlastele, kihnu keele \u00f5ppijatele ja kasutajatele, aga ka k\u00f5igile neile, kes tunnevad huvi selle erip\u00e4rase keele ja kultuuri vastu.\n\u201eKihnu s\u00f5naraamat\u201c lisandub Eesti Keele Instituudi v\u00e4ikeste murdes\u00f5nastike sarja, milles on juba ilmunud \u201eVanap\u00e4rase V\u00f5ru murde s\u00f5naraamat\u201c (2011), \u201eMulgi s\u00f5nastik\u201c (2013), \u201eHiiu s\u00f5naraamat\u201c (2015) ja \u201eIdamurde s\u00f5nastik\u201c (2016).\n;Abstract;The dictionary presents lexical material from the vernacular actively spoken on the islands of  Kihnu and Manija. Apart from the 6000 dialect words there is a selection of personal and place names. The entry list contains quite ancient words as well as some that have arrived in the Kihnu vernacular only in the recent decades. The basic forms and sentence examples (with translations into standard Estonian) facilitate learning and use of the dialect.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "686c710a-97c4-5f9c-a5e6-529eb6fec26b",
-    "notes": [
-        "Abstract",
-        " \u201eKihnu s\u00f5naraamat\u201c h\u00f5lmab s\u00f5navara murdekeelest, mida k\u00f5neldakse Kihnus ja Manijal. Raamatusse on mahtunud enam kui 6000 s\u00f5na, lisaks veel valik isiku- ning kohanimesid. M\u00e4rks\u00f5nade hulka on valitud nii Kihnule iseloomulikke iidseid s\u00f5nu kui ka neid, mis on murdekeelde tulnud alles viimastel k\u00fcmnenditel. S\u00f5nade tarvitamist h\u00f5lbustavad lisatud p\u00f5hivormid ja n\u00e4itelaused nii kihnu kui ka kirjakeeles.\nS\u00f5naraamatu on koostanud Reene Leas, Reti K\u00f6nninge, Silvi Murulauk ja Ellen Niit ning toimetanud Karl Pajusalu ja J\u00fcri Viikberg.\nS\u00f5naraamat on m\u00f5eldud eelk\u00f5ige kihnlastele, kihnu keele \u00f5ppijatele ja kasutajatele, aga ka k\u00f5igile neile, kes tunnevad huvi selle erip\u00e4rase keele ja kultuuri vastu.\n\u201eKihnu s\u00f5naraamat\u201c lisandub Eesti Keele Instituudi v\u00e4ikeste murdes\u00f5nastike sarja, milles on juba ilmunud \u201eVanap\u00e4rase V\u00f5ru murde s\u00f5naraamat\u201c (2011), \u201eMulgi s\u00f5nastik\u201c (2013), \u201eHiiu s\u00f5naraamat\u201c (2015) ja \u201eIdamurde s\u00f5nastik\u201c (2016).\n",
-        "Abstract",
-        "The dictionary presents lexical material from the vernacular actively spoken on the islands of  Kihnu and Manija. Apart from the 6000 dialect words there is a selection of personal and place names. The entry list contains quite ancient words as well as some that have arrived in the Kihnu vernacular only in the recent decades. The basic forms and sentence examples (with translations into standard Estonian) facilitate learning and use of the dialect."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10283400"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Kihnu s\u00f5naraamat",
-        "The Dictionary of the Kihnu Dialect "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/69302d42-88c8-506c-8840-e1d3724cb7e6.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/69302d42-88c8-506c-8840-e1d3724cb7e6.json
deleted file mode 100644
index 0cc09b59..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/69302d42-88c8-506c-8840-e1d3724cb7e6.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05BDCL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9474542",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9474542"
-    ],
-    "PublicationTimestamp": "2016-11-09T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:9474542;2019-03-30T14:03:02Z;ESTDOI;ESTDOI.KEEL;Hariduse ja kasvatuse s\u00f5naraamat;Hein, Indrek;Center of Estonian Language Resources;2016;Issued: 2016-11-09;Updated: 2016-11-09;doi:10.15155/3-00-0000-0000-0000-05BDCL;Abstract;Sisaldab 4850 terminit mitmesugustelt hariduse ja kasvatuse aladelt: kasvatus ja areng, alusharidus, p\u00f5hi- ja keskharidus, kutse- ja k\u00f5rgharidus, andragoogika, eripedagoogika jne. Igale eesti terminile on antud inglise, saksa, soome ja vene vaste ning enamasti ka seletus.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "69302d42-88c8-506c-8840-e1d3724cb7e6",
-    "notes": [
-        "Abstract",
-        "Sisaldab 4850 terminit mitmesugustelt hariduse ja kasvatuse aladelt: kasvatus ja areng, alusharidus, p\u00f5hi- ja keskharidus, kutse- ja k\u00f5rgharidus, andragoogika, eripedagoogika jne. Igale eesti terminile on antud inglise, saksa, soome ja vene vaste ning enamasti ka seletus."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9474542"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Hariduse ja kasvatuse s\u00f5naraamat"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/693714c3-6974-57d9-8f76-3456b80d921f.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/693714c3-6974-57d9-8f76-3456b80d921f.json
deleted file mode 100644
index ddaba375..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/693714c3-6974-57d9-8f76-3456b80d921f.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/TY.0018",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:4597377",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:4597377"
-    ],
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:4597377;2019-04-19T09:02:06Z;ESTDOI;ESTDOI.KEEL;Estonian-English parallel corpus;Muischnek, Kadri;Center of Estonian Language Resources;2011;doi:10.15155/TY.0018",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "693714c3-6974-57d9-8f76-3456b80d921f",
-    "oai_identifier": [
-        "oai:oai.datacite.org:4597377"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Estonian-English parallel corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6ad2babe-5a4f-5d05-8e6f-80020b94c62e.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6ad2babe-5a4f-5d05-8e6f-80020b94c62e.json
deleted file mode 100644
index 398ef795..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6ad2babe-5a4f-5d05-8e6f-80020b94c62e.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-071F3L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14560528",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14560528"
-    ],
-    "PublicationTimestamp": "2019-02-05T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Koppel, Kristina",
-        "Kallas, Jelena"
-    ],
-    "fulltext": "oai:oai.datacite.org:14560528;2019-02-05T05:03:53Z;ESTDOI;ESTDOI.KEEL;etLex t\u00e4iskasvanutele: eesti keele kui teise keele eri keeleoskustasemete s\u00f5navara ja teksti tasemesobivuse hindamine;Kallas, Jelena;Koppel, Kristina;Center of Estonian Language Resources;2018;Issued: 2018-03-26;Updated: 2019-02-05;doi:10.15155/3-00-0000-0000-0000-071F3L;Abstract;EtLex on Eesti Keele Instituudis Haridus- ja Teadusministeeriumi Digip\u00f6\u00f6rde programmi (vt https://www.hm.ee/et/digipoorde-programm) toel loodud t\u00f6\u00f6riist, mis v\u00f5imaldab automaatselt anal\u00fc\u00fcsida, mis keeleoskustaseme s\u00f5navara tekst sisaldab.\nKeeleoskustasemete m\u00e4\u00e4ramisel on aluseks Euroopa keele\u00f5ppe raamdokumendis (Common European Framework of Reference for Languages: Learning, Teaching, Assessment, CEFR) kirjeldatud keeleoskustasemed, mille kohaselt eristatakse kolme \u00fcldist taset (A-, B- ja C-tase) ja kuut alajaotust (A1-, A2-, B1-, B2-, C1-, C2-tase) (RT I 2009, 4, 26).\nEtLexi t\u00f6\u00f6riist anal\u00fc\u00fcsib tekste eesti keele A1\u2012C1 aktiivse ja passiivse s\u00f5navara loendite p\u00f5hjal. Kokku on EtLexis m\u00e4\u00e4ratud ca 13 000 s\u00f5na tasemekohasust.\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6ad2babe-5a4f-5d05-8e6f-80020b94c62e",
-    "notes": [
-        "Abstract",
-        "EtLex on Eesti Keele Instituudis Haridus- ja Teadusministeeriumi Digip\u00f6\u00f6rde programmi (vt https://www.hm.ee/et/digipoorde-programm) toel loodud t\u00f6\u00f6riist, mis v\u00f5imaldab automaatselt anal\u00fc\u00fcsida, mis keeleoskustaseme s\u00f5navara tekst sisaldab.\nKeeleoskustasemete m\u00e4\u00e4ramisel on aluseks Euroopa keele\u00f5ppe raamdokumendis (Common European Framework of Reference for Languages: Learning, Teaching, Assessment, CEFR) kirjeldatud keeleoskustasemed, mille kohaselt eristatakse kolme \u00fcldist taset (A-, B- ja C-tase) ja kuut alajaotust (A1-, A2-, B1-, B2-, C1-, C2-tase) (RT I 2009, 4, 26).\nEtLexi t\u00f6\u00f6riist anal\u00fc\u00fcsib tekste eesti keele A1\u2012C1 aktiivse ja passiivse s\u00f5navara loendite p\u00f5hjal. Kokku on EtLexis m\u00e4\u00e4ratud ca 13 000 s\u00f5na tasemekohasust.\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14560528"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "etLex t\u00e4iskasvanutele: eesti keele kui teise keele eri keeleoskustasemete s\u00f5navara ja teksti tasemesobivuse hindamine"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6c5bec4b-304f-5fae-82da-e4dc765c0a37.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6c5bec4b-304f-5fae-82da-e4dc765c0a37.json
deleted file mode 100644
index 199734d0..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6c5bec4b-304f-5fae-82da-e4dc765c0a37.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-000A7L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17972098",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17972098"
-    ],
-    "PublicationTimestamp": "2019-01-09T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Taal, Hannalore"
-    ],
-    "fulltext": "oai:oai.datacite.org:17972098;2019-04-20T05:31:56Z;ESTDOI;ESTDOI.KEEL;K\u00f5neravi harjutuste mallid;Taal, Hannalore;Center of Estonian Language Resources;2019;Issued: 2019-01-09;Updated: 2019-01-09;doi:10.15155/9-00-0000-0000-0000-000A7L;Abstract;Harjutuste\u200b \u200bmallid,\u200b \u200bmille\u200b \u200bpeale\u200b \u200bon\u200b \u200blogopeedidel\u200b \u200bv\u00f5imalik\u200b \u200bluua\u200b \u200bk\u00f5neravi.ee keskkonda\u200b \u200buusi\u200b \u200bharjutusi",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6c5bec4b-304f-5fae-82da-e4dc765c0a37",
-    "notes": [
-        "Abstract",
-        "Harjutuste\u200b \u200bmallid,\u200b \u200bmille\u200b \u200bpeale\u200b \u200bon\u200b \u200blogopeedidel\u200b \u200bv\u00f5imalik\u200b \u200bluua\u200b \u200bk\u00f5neravi.ee keskkonda\u200b \u200buusi\u200b \u200bharjutusi"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17972098"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "K\u00f5neravi harjutuste mallid"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6cd6a3b3-0f4b-55cb-b43a-38cc269f2116.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6cd6a3b3-0f4b-55cb-b43a-38cc269f2116.json
deleted file mode 100644
index f2d1a1c9..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6cd6a3b3-0f4b-55cb-b43a-38cc269f2116.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-00099L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17955058",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17955058"
-    ],
-    "PublicationTimestamp": "2019-01-05T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Alum\u00e4e, Tanel"
-    ],
-    "fulltext": "oai:oai.datacite.org:17955058;2019-03-26T11:32:41Z;ESTDOI;ESTDOI.KEEL;Inimesed;Alum\u00e4e, Tanel;Center of Estonian Language Resources;2019;Issued: 2019-01-05;Updated: 2019-01-05;doi:10.15155/9-00-0000-0000-0000-00099L;Abstract;Androidi rakendus, mis v\u00f5imaldab kiiresti ja mugavalt otsida aadressiraamatus sisalduvaid kontaktandmeid, samas ka n\u00e4ide reeglip\u00f5hise keelemudeliga eestikeelsest k\u00f5netuvastusest.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6cd6a3b3-0f4b-55cb-b43a-38cc269f2116",
-    "notes": [
-        "Abstract",
-        "Androidi rakendus, mis v\u00f5imaldab kiiresti ja mugavalt otsida aadressiraamatus sisalduvaid kontaktandmeid, samas ka n\u00e4ide reeglip\u00f5hise keelemudeliga eestikeelsest k\u00f5netuvastusest."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17955058"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Inimesed"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6dfe8cbc-3de3-5ce0-820e-816592c0c792.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6dfe8cbc-3de3-5ce0-820e-816592c0c792.json
deleted file mode 100644
index 57e5d226..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6dfe8cbc-3de3-5ce0-820e-816592c0c792.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05928L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:8922995",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:8922995"
-    ],
-    "PublicationTimestamp": "2016-08-30T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:8922995;2019-01-29T21:01:49Z;ESTDOI;ESTDOI.KEEL;Anton\u00fc\u00fcmis\u00f5nastik;Dictionary of Antonyms;Hein, Indrek;Center of Estonian Language Resources;2015;Issued: 2015-05-08;Updated: 2016-08-30;doi:10.15155/3-00-0000-0000-0000-05928L;Abstract;Eesti anton\u00fc\u00fcmide s\u00f5nastik;Abstract;Dictionary of Estonian antonyms",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6dfe8cbc-3de3-5ce0-820e-816592c0c792",
-    "notes": [
-        "Abstract",
-        "Eesti anton\u00fc\u00fcmide s\u00f5nastik",
-        "Abstract",
-        "Dictionary of Estonian antonyms"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:8922995"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Anton\u00fc\u00fcmis\u00f5nastik",
-        "Dictionary of Antonyms"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6e672135-4a18-5a05-9b3e-010be14c0614.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6e672135-4a18-5a05-9b3e-010be14c0614.json
deleted file mode 100644
index ad774ee8..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6e672135-4a18-5a05-9b3e-010be14c0614.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-07BDBL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:19520876",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:19520876"
-    ],
-    "PublicationTimestamp": "2019-02-05T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Koppel, Kristina",
-        "Kallas, Jelena"
-    ],
-    "fulltext": "oai:oai.datacite.org:19520876;2019-04-05T10:36:53Z;ESTDOI;ESTDOI.KEEL;Koolieelikute s\u00f5navara;Kallas, Jelena;Koppel, Kristina;Center of Estonian Language Resources;2019;Issued: 2019-02-05;Updated: 2019-02-05;doi:10.15155/3-00-0000-0000-0000-07BDBL;Abstract;Eesti keele kui teise keele s\u00f5navara loendit koolieelikutele. S\u00f5naloend sisaldab kokku 1147 s\u00f5na ning selle koostajad on eksperdid Tallinna \u00dclikooli professor Reili Argus, lasteaia\u00f5petaja ja eesti keele \u00f5pikute autor Lea Maiberg ning lasteaia\u00f5petaja Mariana Koho. Eksperte konsulteerisid Eesti Keele Instituudi spetsialistid Jelena Kallas ja Kristina Koppel.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6e672135-4a18-5a05-9b3e-010be14c0614",
-    "notes": [
-        "Abstract",
-        "Eesti keele kui teise keele s\u00f5navara loendit koolieelikutele. S\u00f5naloend sisaldab kokku 1147 s\u00f5na ning selle koostajad on eksperdid Tallinna \u00dclikooli professor Reili Argus, lasteaia\u00f5petaja ja eesti keele \u00f5pikute autor Lea Maiberg ning lasteaia\u00f5petaja Mariana Koho. Eksperte konsulteerisid Eesti Keele Instituudi spetsialistid Jelena Kallas ja Kristina Koppel."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:19520876"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Koolieelikute s\u00f5navara"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6e83a79a-47b4-5a77-be85-8d28296ca189.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6e83a79a-47b4-5a77-be85-8d28296ca189.json
deleted file mode 100644
index 4e8462ae..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6e83a79a-47b4-5a77-be85-8d28296ca189.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-000DBL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:18050136",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:18050136"
-    ],
-    "PublicationTimestamp": "2013-01-07T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:18050136;2019-04-20T00:32:08Z;ESTDOI;ESTDOI.KEEL;Corpus of Estonian fiction D;Muischnek, Kadri;Center of Estonian Language Resources;2013;Issued: 2013-01-07;Updated: 2013-01-07;doi:10.15155/9-00-0000-0000-0000-000DBL;Abstract;A text corpus containing Estonian fiction texts from 1990. onwards, 5,6 million words.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6e83a79a-47b4-5a77-be85-8d28296ca189",
-    "notes": [
-        "Abstract",
-        "A text corpus containing Estonian fiction texts from 1990. onwards, 5,6 million words."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:18050136"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus of Estonian fiction D"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6e84db9a-4175-5595-af3b-ee5a1170db8a.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6e84db9a-4175-5595-af3b-ee5a1170db8a.json
deleted file mode 100644
index 437d8c62..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6e84db9a-4175-5595-af3b-ee5a1170db8a.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00192L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17968157",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17968157"
-    ],
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Fi\u0161el, Mark"
-    ],
-    "fulltext": "oai:oai.datacite.org:17968157;2019-04-12T17:25:51Z;ESTDOI;ESTDOI.KEEL;Statistilise masint\u00f5lke mudelid;Fi\u0161el, Mark;Center of Estonian Language Resources;2019;Issued: 2019-01-08;Updated: 2019-01-08;doi:10.15155/1-00-0000-0000-0000-00192L;Abstract;The models represented here are statistical phrase-based translation models. In parallel we are testing the various neural MT approaches, but for now the most usable baseline in terms of industrial collaborations is statistical.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6e84db9a-4175-5595-af3b-ee5a1170db8a",
-    "notes": [
-        "Abstract",
-        "The models represented here are statistical phrase-based translation models. In parallel we are testing the various neural MT approaches, but for now the most usable baseline in terms of industrial collaborations is statistical."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17968157"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Statistilise masint\u00f5lke mudelid"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6f688c2f-1b31-5754-ad71-88e15f3a902a.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6f688c2f-1b31-5754-ad71-88e15f3a902a.json
deleted file mode 100644
index 6f574a7c..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6f688c2f-1b31-5754-ad71-88e15f3a902a.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-00087L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:11264658",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:11264658"
-    ],
-    "PublicationTimestamp": "2017-06-20T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laak, Marin",
-        "Asmer, Vilve"
-    ],
-    "fulltext": "oai:oai.datacite.org:11264658;2019-04-21T15:02:20Z;ESTDOI;ESTDOI.KEEL;Vanema eestikeelse algup\u00e4rase ilukirjanduse kogu;Books of Kreutzwald's Century;Laak, Marin;Asmer, Vilve;Center of Estonian Language Resources;2017;Issued: 2017-06-01;Updated: 2017-06-20;doi:10.15155/9-00-0000-0000-0000-00087L;Abstract;Eesti vanema ilukirjanduse tekstide kogu veebikeskkonnas \"Kreutzwaldi sajand. Eesti kultuurilooline veeb.\" Kollektsioonis elektrooniliselt taasavaldatud raamatud p\u00f5hinevad olulisemate Eesti autorite aastatel 1854-1944 ilmunud esmatr\u00fckkidel. Tekstid on esitatud keeleparandusteta, kuid tehniliselt redigeeritud. \"Kreutzwaldi sajand. Eesti kultuurilooline veeb\" esitab raamatud kolmes versioonis: 1) skaneeritud pildina originaalesmatr\u00fckist, 2) html-versioonina, mille lehek\u00fcljed\nvastavad tr\u00fckitud raamatu lehek\u00fclgedele, 3) allalaetava e-pubina.\nSiinne tekstikorpus sisaldab valikut veebikeskkonnas saadaval olevatest raamatutest, mis on teisendatud tekstifailideks. Tekstifailidele on igaks juhuks lisatud ka originaalfailid. HTML-failidest teisendatud tekstifailid sisaldavad HTML-vormingust tingitud reavahetusi, mida algsetes tekstides ei olnud.;Abstract;Web collection of older Estonian literary texts \"Kreutzwald's Century: the Estonian Cultural History Web\". The electronically republished books, included in the collection, are based on the first editions of works by more important Estonian authors, published in 1854-1944. The language of the texts has not been edited, but technical corrections have been made. \"Kreutzwald's Century: the Estonian Cultural History Web\" presents books in three versions: 1) scanned images of the original first edition; 2) a html-version; 3) a downloadable e-pub. \nThe text corpus contains a selection of books accessible on the web, which have been converted into text files. Original files have also been added to the text files. The text files which were converted from the html-files contain, due to the html-formatting, additional line breaks which were not present in the original texts. The html/text versions correspond to the original printed book page layout and the page number are also included.\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6f688c2f-1b31-5754-ad71-88e15f3a902a",
-    "notes": [
-        "Abstract",
-        "Eesti vanema ilukirjanduse tekstide kogu veebikeskkonnas \"Kreutzwaldi sajand. Eesti kultuurilooline veeb.\" Kollektsioonis elektrooniliselt taasavaldatud raamatud p\u00f5hinevad olulisemate Eesti autorite aastatel 1854-1944 ilmunud esmatr\u00fckkidel. Tekstid on esitatud keeleparandusteta, kuid tehniliselt redigeeritud. \"Kreutzwaldi sajand. Eesti kultuurilooline veeb\" esitab raamatud kolmes versioonis: 1) skaneeritud pildina originaalesmatr\u00fckist, 2) html-versioonina, mille lehek\u00fcljed\nvastavad tr\u00fckitud raamatu lehek\u00fclgedele, 3) allalaetava e-pubina.\nSiinne tekstikorpus sisaldab valikut veebikeskkonnas saadaval olevatest raamatutest, mis on teisendatud tekstifailideks. Tekstifailidele on igaks juhuks lisatud ka originaalfailid. HTML-failidest teisendatud tekstifailid sisaldavad HTML-vormingust tingitud reavahetusi, mida algsetes tekstides ei olnud.",
-        "Abstract",
-        "Web collection of older Estonian literary texts \"Kreutzwald's Century: the Estonian Cultural History Web\". The electronically republished books, included in the collection, are based on the first editions of works by more important Estonian authors, published in 1854-1944. The language of the texts has not been edited, but technical corrections have been made. \"Kreutzwald's Century: the Estonian Cultural History Web\" presents books in three versions: 1) scanned images of the original first edition; 2) a html-version; 3) a downloadable e-pub. \nThe text corpus contains a selection of books accessible on the web, which have been converted into text files. Original files have also been added to the text files. The text files which were converted from the html-files contain, due to the html-formatting, additional line breaks which were not present in the original texts. The html/text versions correspond to the original printed book page layout and the page number are also included.\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:11264658"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Vanema eestikeelse algup\u00e4rase ilukirjanduse kogu",
-        "Books of Kreutzwald's Century"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6fd4a70f-9901-5b57-abe2-e20c8eef69b0.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6fd4a70f-9901-5b57-abe2-e20c8eef69b0.json
deleted file mode 100644
index b317ca00..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/6fd4a70f-9901-5b57-abe2-e20c8eef69b0.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00189L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17961011",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17961011"
-    ],
-    "PublicationTimestamp": "2019-01-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "M\u00fc\u00fcrisep, Kaili"
-    ],
-    "fulltext": "oai:oai.datacite.org:17961011;2019-04-05T16:31:53Z;ESTDOI;ESTDOI.KEEL;S\u00fcntaksi eelt\u00f6\u00f6tlusmoodulid;Preprocessing module for parsing;M\u00fc\u00fcrisep, Kaili;Center of Estonian Language Resources;2019;Issued: 2019-01-07;Updated: 2019-01-07;doi:10.15155/1-00-0000-0000-0000-00189L;Abstract;Eelt\u00f6\u00f6tlusmoodulid Eesti keele Koondkorpuse xml-m\u00e4rgendusega teadus- ja ajakirjandustekstide jaoks, teevad tekstid parserite jaoks sobivamale kujule ning (soovi korral) nummerdavad laused.;Abstract;Preprocessing module, to be used before parsing. Input: text with xml-markup, e.g. Estonian Reference Corpus texts (http://www.cl.ut.ee/korpused/segakorpus/)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "6fd4a70f-9901-5b57-abe2-e20c8eef69b0",
-    "notes": [
-        "Abstract",
-        "Eelt\u00f6\u00f6tlusmoodulid Eesti keele Koondkorpuse xml-m\u00e4rgendusega teadus- ja ajakirjandustekstide jaoks, teevad tekstid parserite jaoks sobivamale kujule ning (soovi korral) nummerdavad laused.",
-        "Abstract",
-        "Preprocessing module, to be used before parsing. Input: text with xml-markup, e.g. Estonian Reference Corpus texts (http://www.cl.ut.ee/korpused/segakorpus/)"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17961011"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "S\u00fcntaksi eelt\u00f6\u00f6tlusmoodulid",
-        "Preprocessing module for parsing"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/70ddd083-efd0-555b-b9dd-cac666d8e90e.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/70ddd083-efd0-555b-b9dd-cac666d8e90e.json
deleted file mode 100644
index 0eb4d0ac..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/70ddd083-efd0-555b-b9dd-cac666d8e90e.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00155L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14614708",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14614708"
-    ],
-    "PublicationTimestamp": "2018-04-05T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laur, Sven"
-    ],
-    "fulltext": "oai:oai.datacite.org:14614708;2019-04-23T03:31:45Z;ESTDOI;ESTDOI.KEEL;Koondkorpus anal\u00fc\u00fcsitud estnltk ver.1.6.b abil - json vormingus;Laur, Sven;Center of Estonian Language Resources;2018;Issued: 2018-04-05;Updated: 2018-04-05;doi:10.15155/1-00-0000-0000-0000-00155L;Abstract;Koondkorpus anal\u00fc\u00fcsitud estnltk ver.1.6.b abil - json vormingus",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "70ddd083-efd0-555b-b9dd-cac666d8e90e",
-    "notes": [
-        "Abstract",
-        "Koondkorpus anal\u00fc\u00fcsitud estnltk ver.1.6.b abil - json vormingus"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14614708"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Koondkorpus anal\u00fc\u00fcsitud estnltk ver.1.6.b abil - json vormingus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/714614fc-af71-5b6b-8802-8dd8a70b55e8.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/714614fc-af71-5b6b-8802-8dd8a70b55e8.json
deleted file mode 100644
index e2d2b40e..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/714614fc-af71-5b6b-8802-8dd8a70b55e8.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-00028L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5757526",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5757526"
-    ],
-    "PublicationTimestamp": "2019-01-06T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Alum\u00e4e, Tanel"
-    ],
-    "fulltext": "oai:oai.datacite.org:5757526;2019-04-17T17:25:53Z;ESTDOI;ESTDOI.KEEL;Veebip\u00f5hine k\u00f5netuvastus;Web service for transcribing long speech recordings;Alum\u00e4e, Tanel;Center of Estonian Language Resources;2014;Issued: 2014-12-30;Updated: 2019-01-06;doi:10.15155/9-00-0000-0000-0000-00028L;Abstract;Veebileht, mille abil saab lasta oma eestikeelset k\u00f6net sisaldavaid helifaile automaatselt transkribeerida. Transkribeerimisel kasutatakse TT\u00dc K\u00fcberneetika Instituudi foneetika- ja k\u00f5netehnoloogia laboris v\u00e4ljat\u00f6\u00f6tatud tehnoloogiat ja mudeleid. \n;Abstract;Web service for transcribing long speech recordings in Estonian.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "714614fc-af71-5b6b-8802-8dd8a70b55e8",
-    "notes": [
-        "Abstract",
-        "Veebileht, mille abil saab lasta oma eestikeelset k\u00f6net sisaldavaid helifaile automaatselt transkribeerida. Transkribeerimisel kasutatakse TT\u00dc K\u00fcberneetika Instituudi foneetika- ja k\u00f5netehnoloogia laboris v\u00e4ljat\u00f6\u00f6tatud tehnoloogiat ja mudeleid. \n",
-        "Abstract",
-        "Web service for transcribing long speech recordings in Estonian."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5757526"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Veebip\u00f5hine k\u00f5netuvastus",
-        "Web service for transcribing long speech recordings"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7148e9e6-5d7e-5475-812d-bdc4dec50f93.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7148e9e6-5d7e-5475-812d-bdc4dec50f93.json
deleted file mode 100644
index 47a04b71..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7148e9e6-5d7e-5475-812d-bdc4dec50f93.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-00019L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5757485",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5757485"
-    ],
-    "PublicationTimestamp": "2017-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:5757485;2019-03-20T18:37:18Z;ESTDOI;ESTDOI.KEEL;Eesti Keele Instituudi reeglip\u00f5hise morfoloogia t\u00f6\u00f6riistad;Tools of the IEL rule-based morphology;Hein, Indrek;Center of Estonian Language Resources;2012;Issued: 2012-06-14;Updated: 2017-02-15;doi:10.15155/3-00-0000-0000-0000-00019L;Abstract;Eesti Keele Instituudi reeglip\u00f5hine morfoloogiat\u00f6\u00f6riistade komplekt sisaldab endas eraldi kasutatavaid mooduleid silbitamise, t\u00fc\u00fcbituvastuse, morfoloogilise anal\u00fc\u00fcsi ja s\u00fcnteesi kohta.;Abstract;The rule-based morphology toolkit of the Estonian Language Institute consists of separate modules for syllabification, paradigm recognition, morphological analysis and synthesis.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7148e9e6-5d7e-5475-812d-bdc4dec50f93",
-    "notes": [
-        "Abstract",
-        "Eesti Keele Instituudi reeglip\u00f5hine morfoloogiat\u00f6\u00f6riistade komplekt sisaldab endas eraldi kasutatavaid mooduleid silbitamise, t\u00fc\u00fcbituvastuse, morfoloogilise anal\u00fc\u00fcsi ja s\u00fcnteesi kohta.",
-        "Abstract",
-        "The rule-based morphology toolkit of the Estonian Language Institute consists of separate modules for syllabification, paradigm recognition, morphological analysis and synthesis."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5757485"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti Keele Instituudi reeglip\u00f5hise morfoloogia t\u00f6\u00f6riistad",
-        "Tools of the IEL rule-based morphology"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/71640c94-5c5d-539e-b5cc-b8ab5bc6459b.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/71640c94-5c5d-539e-b5cc-b8ab5bc6459b.json
deleted file mode 100644
index 8fff1179..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/71640c94-5c5d-539e-b5cc-b8ab5bc6459b.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0019CL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17986397",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17986397"
-    ],
-    "PublicationTimestamp": "2019-01-11T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Iva, Sulev"
-    ],
-    "fulltext": "oai:oai.datacite.org:17986397;2019-04-17T17:27:40Z;ESTDOI;ESTDOI.KEEL;Ajalehe Setomaa korpus;Iva, Sulev;Center of Estonian Language Resources;2019;Issued: 2019-01-11;Updated: 2019-01-11;doi:10.15155/1-00-0000-0000-0000-0019CL;Abstract;Seo aolehe Setomaa korpus om osa V\u00f5ro instituudi V\u00f5ro ja seto keelekorpus\u00f5st. Korpus\u00f5 om kokko pandnuq M\u00e4nnamaa Kaur aolehe Setomaa lual lehe elektrooniliidsi arhiiv\u00f5 perr\u00e4 2013. aastagal. Seo v\u00f5rgolehe om kujondanu M\u00e4nnamaa Laura.\n\nKorpus\u00f5n om parhilla 1031 teksti. Tuu hulgan setokeelitsit tekste 403 (278 879 s\u00f5nna) ja eestikeelitsit tekste 628 (227 704 s\u00f5nna). Tekstiq ommaq peri aastist 2006 - 2013. Korpus\u00f5 kokkopandmist om rahaga tug\u00f5nuq riiklin\u00f5 programm Eesti keeletehnoloogia. ",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "71640c94-5c5d-539e-b5cc-b8ab5bc6459b",
-    "notes": [
-        "Abstract",
-        "Seo aolehe Setomaa korpus om osa V\u00f5ro instituudi V\u00f5ro ja seto keelekorpus\u00f5st. Korpus\u00f5 om kokko pandnuq M\u00e4nnamaa Kaur aolehe Setomaa lual lehe elektrooniliidsi arhiiv\u00f5 perr\u00e4 2013. aastagal. Seo v\u00f5rgolehe om kujondanu M\u00e4nnamaa Laura.\n\nKorpus\u00f5n om parhilla 1031 teksti. Tuu hulgan setokeelitsit tekste 403 (278 879 s\u00f5nna) ja eestikeelitsit tekste 628 (227 704 s\u00f5nna). Tekstiq ommaq peri aastist 2006 - 2013. Korpus\u00f5 kokkopandmist om rahaga tug\u00f5nuq riiklin\u00f5 programm Eesti keeletehnoloogia. "
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17986397"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Ajalehe Setomaa korpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/718176ac-aec7-5da5-9eef-82ebfd5ef6f1.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/718176ac-aec7-5da5-9eef-82ebfd5ef6f1.json
deleted file mode 100644
index 093a88c5..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/718176ac-aec7-5da5-9eef-82ebfd5ef6f1.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/TY.0014",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:4597373",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:4597373"
-    ],
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:4597373;2019-02-28T20:30:41Z;ESTDOI;ESTDOI.KEEL;Corpus of Estonian scientific texts;Muischnek, Kadri;Center of Estonian Language Resources;2013;doi:10.15155/TY.0014",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "718176ac-aec7-5da5-9eef-82ebfd5ef6f1",
-    "oai_identifier": [
-        "oai:oai.datacite.org:4597373"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus of Estonian scientific texts"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/71d1f321-6977-5664-832d-c4504c7d4b92.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/71d1f321-6977-5664-832d-c4504c7d4b92.json
deleted file mode 100644
index a638bec0..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/71d1f321-6977-5664-832d-c4504c7d4b92.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05BDAL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9474540",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9474540"
-    ],
-    "PublicationTimestamp": "2018-03-20T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Piits, Liisi"
-    ],
-    "fulltext": "oai:oai.datacite.org:9474540;2019-04-17T17:26:21Z;ESTDOI;ESTDOI.KEEL;Eesti Keele Instituudi k\u00f5nes\u00fcnteesikorpus;The Corpus of Speech Synthesis of the Institute of the Estonian Language;Piits, Liisi;Center of Estonian Language Resources;2016;Issued: 2016-11-09;Updated: 2018-03-20;doi:10.15155/3-00-0000-0000-0000-05BDAL;Abstract;Eestikeelse tekst-k\u00f5ne s\u00fcnteesi h\u00e4\u00e4lemudelite loomiseks kasutatud sisseloetud tekstid.;Abstract;The corpus contains sound recordings of read texts used for the creation of voice models for Estonian text-to-speech synthesis.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "71d1f321-6977-5664-832d-c4504c7d4b92",
-    "notes": [
-        "Abstract",
-        "Eestikeelse tekst-k\u00f5ne s\u00fcnteesi h\u00e4\u00e4lemudelite loomiseks kasutatud sisseloetud tekstid.",
-        "Abstract",
-        "The corpus contains sound recordings of read texts used for the creation of voice models for Estonian text-to-speech synthesis."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9474540"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti Keele Instituudi k\u00f5nes\u00fcnteesikorpus",
-        "The Corpus of Speech Synthesis of the Institute of the Estonian Language"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/726fe736-c89d-50f5-8746-92ff462b6b05.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/726fe736-c89d-50f5-8746-92ff462b6b05.json
deleted file mode 100644
index a6bfeae4..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/726fe736-c89d-50f5-8746-92ff462b6b05.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0012AL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9845162",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9845162"
-    ],
-    "PublicationTimestamp": "2016-12-02T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Lippus, P\u00e4rtel"
-    ],
-    "fulltext": "oai:oai.datacite.org:9845162;2019-01-28T16:32:56Z;ESTDOI;ESTDOI.KEEL;Eesti keele spontaanse k\u00f5ne foneetiline korpus v.1.0.3;Phonetic Corpus of Estonian Spontaneous Speech v.1.0.3;Lippus, P\u00e4rtel;Center of Estonian Language Resources;2013;Issued: 2013-01-09;Updated: 2016-12-02;doi:10.15155/1-00-0000-0000-0000-0012AL;Abstract;The aim of the corpus is to compile a large amount of quality recordings of spontaneous Estonian and segment it phonetically on different levels. The project started in autumn 2006.\n\nThe total size of the corpus is approximately 80 hours of speech from 120 speakers with different dialectological and social background. Speakers are from different age groups. They are asked to participate with face-to-face invitation and they are aware of the purpose of the recordings.\n\nMost of the recordings are made in a recording studio, some also on fieldwork. The signal of each speaker is recorded in a separate channel. The distance between the speakers is about 3 meters to minimize the effect of overlaps. For the field-work recordings head-set microphones are used. Recordings are saved in PCM wav-format and are not compressed. Background information about the recordings is collected in a text-file.\n    Segmentation and annotation files are saved as Praat TextGrid files and get same filenames as recordings segmented.\n\nSegmentation and annotation\nSegmentation and annotation is done with the Praat program (www.praat.org). Recordings are segmented manually on different levels (automatic segmentation program is also elaborated and tested).\nFollowing tiers are used:\n    -Words (in orthographic spelling), \n    -Phonemes (SAMPA adjusted for Estonian is used for transcription), \n    -Syllables (short \u2013 long, open \u2013 closed), \n    -Prosodic feet,\n    -Intonation phrases or inter-pausal units;\n    -Changes in voice quality (e.g. creaky voice);",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "726fe736-c89d-50f5-8746-92ff462b6b05",
-    "notes": [
-        "Abstract",
-        "The aim of the corpus is to compile a large amount of quality recordings of spontaneous Estonian and segment it phonetically on different levels. The project started in autumn 2006.\n\nThe total size of the corpus is approximately 80 hours of speech from 120 speakers with different dialectological and social background. Speakers are from different age groups. They are asked to participate with face-to-face invitation and they are aware of the purpose of the recordings.\n\nMost of the recordings are made in a recording studio, some also on fieldwork. The signal of each speaker is recorded in a separate channel. The distance between the speakers is about 3 meters to minimize the effect of overlaps. For the field-work recordings head-set microphones are used. Recordings are saved in PCM wav-format and are not compressed. Background information about the recordings is collected in a text-file.\n    Segmentation and annotation files are saved as Praat TextGrid files and get same filenames as recordings segmented.\n\nSegmentation and annotation\nSegmentation and annotation is done with the Praat program (www.praat.org). Recordings are segmented manually on different levels (automatic segmentation program is also elaborated and tested).\nFollowing tiers are used:\n    -Words (in orthographic spelling), \n    -Phonemes (SAMPA adjusted for Estonian is used for transcription), \n    -Syllables (short \u2013 long, open \u2013 closed), \n    -Prosodic feet,\n    -Intonation phrases or inter-pausal units;\n    -Changes in voice quality (e.g. creaky voice);"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9845162"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele spontaanse k\u00f5ne foneetiline korpus v.1.0.3",
-        "Phonetic Corpus of Estonian Spontaneous Speech v.1.0.3"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/72d6f31d-a7df-5ef0-a850-7c6e292073c6.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/72d6f31d-a7df-5ef0-a850-7c6e292073c6.json
deleted file mode 100644
index 94404b6b..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/72d6f31d-a7df-5ef0-a850-7c6e292073c6.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06340L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10304127",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10304127"
-    ],
-    "PublicationTimestamp": "2017-11-28T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Raadik, Maire"
-    ],
-    "fulltext": "oai:oai.datacite.org:10304127;2019-04-02T15:31:15Z;ESTDOI;ESTDOI.KEEL;Eesti Keele Instituudi isikunimeandmebaas;The Family Name Database of the Institute of the Estonian Language;Raadik, Maire;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2017-11-28;doi:10.15155/3-00-0000-0000-0000-06340L;Abstract;Eesti perekonnanimede andmebaasist saab vaadata, kuidas k\u00e4\u00e4nduvad eesti perekonnanimed. Iga nime puhul on peale nimetava k\u00e4\u00e4nde n\u00e4idatud omastava, osastava ja alale\u00fctleva k\u00e4\u00e4nde vorm. Kui nime saab k\u00e4\u00e4nata mitut moodi, on antud k\u00f5ik v\u00f5imalused. Lisatud on ka sada eesnime, mille k\u00e4\u00e4namist on EKI keelen\u00f5ust k\u00f5ige rohkem k\u00fcsitud.;Abstract;The Family Name Database gives information on how to decline Estonian family names. Besides the nominative form, each name is provided with its shapes in the genitive, partitive and allative cases. If a name fits more than one paradigm, all options are included.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "72d6f31d-a7df-5ef0-a850-7c6e292073c6",
-    "notes": [
-        "Abstract",
-        "Eesti perekonnanimede andmebaasist saab vaadata, kuidas k\u00e4\u00e4nduvad eesti perekonnanimed. Iga nime puhul on peale nimetava k\u00e4\u00e4nde n\u00e4idatud omastava, osastava ja alale\u00fctleva k\u00e4\u00e4nde vorm. Kui nime saab k\u00e4\u00e4nata mitut moodi, on antud k\u00f5ik v\u00f5imalused. Lisatud on ka sada eesnime, mille k\u00e4\u00e4namist on EKI keelen\u00f5ust k\u00f5ige rohkem k\u00fcsitud.",
-        "Abstract",
-        "The Family Name Database gives information on how to decline Estonian family names. Besides the nominative form, each name is provided with its shapes in the genitive, partitive and allative cases. If a name fits more than one paradigm, all options are included."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10304127"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti Keele Instituudi isikunimeandmebaas",
-        "The Family Name Database of the Institute of the Estonian Language"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/73318b22-4fb9-59ad-9a16-6a964f7b5489.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/73318b22-4fb9-59ad-9a16-6a964f7b5489.json
deleted file mode 100644
index a9f779c4..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/73318b22-4fb9-59ad-9a16-6a964f7b5489.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06332L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10303905",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10303905"
-    ],
-    "PublicationTimestamp": "2019-01-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Mihkla, Meelis"
-    ],
-    "fulltext": "oai:oai.datacite.org:10303905;2019-04-17T17:26:40Z;ESTDOI;ESTDOI.KEEL;Uudiste lugeja Androidis;Android Newsreader;Mihkla, Meelis;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2019-01-07;doi:10.15155/3-00-0000-0000-0000-06332L;Abstract;Rakendus loeb eesti keeles ette v\u00e4rskeid uudiseid. Kasutajal on v\u00f5imalik valida kolme s\u00fcnteesh\u00e4\u00e4le ja erinevate lugemiskiiruste vahel.;Abstract;Reads aloud fresh news in Estonian. User options include three synthetic voices and different speech rates.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "73318b22-4fb9-59ad-9a16-6a964f7b5489",
-    "notes": [
-        "Abstract",
-        "Rakendus loeb eesti keeles ette v\u00e4rskeid uudiseid. Kasutajal on v\u00f5imalik valida kolme s\u00fcnteesh\u00e4\u00e4le ja erinevate lugemiskiiruste vahel.",
-        "Abstract",
-        "Reads aloud fresh news in Estonian. User options include three synthetic voices and different speech rates."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10303905"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Uudiste lugeja Androidis",
-        "Android Newsreader"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/73547b36-c494-588d-977d-2001b277ce1e.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/73547b36-c494-588d-977d-2001b277ce1e.json
deleted file mode 100644
index f9bca523..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/73547b36-c494-588d-977d-2001b277ce1e.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-00092L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17926641",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17926641"
-    ],
-    "PublicationTimestamp": "2018-12-27T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Meister, Einar"
-    ],
-    "fulltext": "oai:oai.datacite.org:17926641;2018-12-27T15:07:59Z;ESTDOI;ESTDOI.KEEL;Uudistekorpus;TV News Corpus;Meister, Einar;Center of Estonian Language Resources;2018;Issued: 2018-12-27;Updated: 2018-12-27;doi:10.15155/9-00-0000-0000-0000-00092L;Abstract;Kogutud ja k\u00e4sitsi m\u00e4rgendatud 30 tundi teleuudiseid.;Abstract;30 hours of TV news annotated.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "73547b36-c494-588d-977d-2001b277ce1e",
-    "notes": [
-        "Abstract",
-        "Kogutud ja k\u00e4sitsi m\u00e4rgendatud 30 tundi teleuudiseid.",
-        "Abstract",
-        "30 hours of TV news annotated."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17926641"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Uudistekorpus",
-        "TV News Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7382332b-e510-5afb-b21d-e52591ed4abc.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7382332b-e510-5afb-b21d-e52591ed4abc.json
deleted file mode 100644
index 85817376..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7382332b-e510-5afb-b21d-e52591ed4abc.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0018BL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17961498",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17961498"
-    ],
-    "PublicationTimestamp": "2019-01-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "M\u00fc\u00fcrisep, Kaili"
-    ],
-    "fulltext": "oai:oai.datacite.org:17961498;2019-01-07T17:54:40Z;ESTDOI;ESTDOI.KEEL;S\u00fcntaksi eelt\u00f6\u00f6tlusmoodulid (EtTenTen formaadile);Preprocessing module for parsing (for EtTenTen format);M\u00fc\u00fcrisep, Kaili;Center of Estonian Language Resources;2019;Issued: 2019-01-07;Updated: 2019-01-07;doi:10.15155/1-00-0000-0000-0000-0018BL;Abstract;Selle s\u00fcntaksianal\u00fc\u00fcsi-eelse eelt\u00f6\u00f6tlusmooduli versioon on m\u00f5eldud etTenTeni korpuse tekstit\u00fc\u00fcpide (perioodika, valitsus, religioon, informatiivne, unknown, foorum ja blogi) jaoks. Moodulist on kaks versiooni. Esimene versioon on m\u00f5eldud perioodika, valitsuse, religiooni, informatiivse ja tundmatu tekstit\u00fc\u00fcbile (eeltootlus_ettenten.py, ettenten_patterns.py), teine versioon on m\u00f5eldud foorumi ja blogi tekstit\u00fc\u00fcbile (eeltootlus_ettenten_blg_frm.py, ettenten_patterns_blg_frm.py).;Abstract;Preprocessing module, to be used before parsing. This version includes two modules for preprocessing EtTenTen corpus text types: the first one for newspaper, government, religious, informative and unknown texts (eeltootlus_ettenten.py, ettenten_patterns.py) and the other for forums and blogs (eeltootlus_ettenten_blg_frm.py, ettenten_patterns_blg_frm.py).",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7382332b-e510-5afb-b21d-e52591ed4abc",
-    "notes": [
-        "Abstract",
-        "Selle s\u00fcntaksianal\u00fc\u00fcsi-eelse eelt\u00f6\u00f6tlusmooduli versioon on m\u00f5eldud etTenTeni korpuse tekstit\u00fc\u00fcpide (perioodika, valitsus, religioon, informatiivne, unknown, foorum ja blogi) jaoks. Moodulist on kaks versiooni. Esimene versioon on m\u00f5eldud perioodika, valitsuse, religiooni, informatiivse ja tundmatu tekstit\u00fc\u00fcbile (eeltootlus_ettenten.py, ettenten_patterns.py), teine versioon on m\u00f5eldud foorumi ja blogi tekstit\u00fc\u00fcbile (eeltootlus_ettenten_blg_frm.py, ettenten_patterns_blg_frm.py).",
-        "Abstract",
-        "Preprocessing module, to be used before parsing. This version includes two modules for preprocessing EtTenTen corpus text types: the first one for newspaper, government, religious, informative and unknown texts (eeltootlus_ettenten.py, ettenten_patterns.py) and the other for forums and blogs (eeltootlus_ettenten_blg_frm.py, ettenten_patterns_blg_frm.py)."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17961498"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "S\u00fcntaksi eelt\u00f6\u00f6tlusmoodulid (EtTenTen formaadile)",
-        "Preprocessing module for parsing (for EtTenTen format)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/73ddc4db-7218-5138-9582-b9b4f171bea3.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/73ddc4db-7218-5138-9582-b9b4f171bea3.json
deleted file mode 100644
index f6fa992a..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/73ddc4db-7218-5138-9582-b9b4f171bea3.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-07021L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14431628",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14431628"
-    ],
-    "PublicationTimestamp": "2018-03-14T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Soon, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:14431628;2019-04-21T08:01:24Z;ESTDOI;ESTDOI.KEEL;Esterm v20180302;Esterm v20180302;Soon, Tiina;Center of Estonian Language Resources;2018;Issued: 2018-03-14;Updated: 2018-03-14;doi:10.15155/3-00-0000-0000-0000-07021L;Abstract;Esterm on Eesti Keele Instituudi mitmekeelne terminibaas, mis sisaldab peamiselt Euroopa Liidu ja Eesti Vabariigi \u00f5igusaktide termineid. Terminibaas koondab \u00fcle 50 valdkonna terminoloogiat.;Abstract;Esterm is a multilingual termbase which includes terms mainly from the legal acts of the Republic of Estonia and the European Union. The termbase contains terminology from more than 50 domains.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "73ddc4db-7218-5138-9582-b9b4f171bea3",
-    "notes": [
-        "Abstract",
-        "Esterm on Eesti Keele Instituudi mitmekeelne terminibaas, mis sisaldab peamiselt Euroopa Liidu ja Eesti Vabariigi \u00f5igusaktide termineid. Terminibaas koondab \u00fcle 50 valdkonna terminoloogiat.",
-        "Abstract",
-        "Esterm is a multilingual termbase which includes terms mainly from the legal acts of the Republic of Estonia and the European Union. The termbase contains terminology from more than 50 domains."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14431628"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Esterm v20180302",
-        "Esterm v20180302"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/74cbac8f-47a4-51b9-9858-353501fc841a.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/74cbac8f-47a4-51b9-9858-353501fc841a.json
deleted file mode 100644
index 52112091..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/74cbac8f-47a4-51b9-9858-353501fc841a.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-07334L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14745995",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14745995"
-    ],
-    "PublicationTimestamp": "2018-04-23T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Koppel, Kristina",
-        "Kallas, Jelena"
-    ],
-    "fulltext": "oai:oai.datacite.org:14745995;2018-10-20T23:31:55Z;ESTDOI;ESTDOI.KEEL;Eesti keele \u00f5ppekorpus 2018 (etSkELL)  2018-04;Estonian Corpus for Learners 2018 (etSkELL)  2018-04;Kallas, Jelena;Koppel, Kristina;Center of Estonian Language Resources;2018;Issued: 2018-04-23;Updated: 2018-04-23;doi:10.15155/3-00-0000-0000-0000-07334L;Abstract;Eesti keele \u00f5ppekorpus 2018 (etSkELL) on spetsiaalne tekstikorpus, mis sisaldab ainult keele\u00f5ppijale sobivaid lauseid. Laused p\u00e4rinevad Eesti keele \u00fchendkorpusest 2017 ja Eesti keele A1-C1 \u00f5pikute korpusest 2018. Keele\u00f5ppijale sobivate lausete tuvastamiseks kasutati Kristina Koppeli v\u00e4lja t\u00f6\u00f6tatud eesti keele GDEXi (Good Dictionary Example) moodulit, mis v\u00f5imaldab lausete filtreerimist vastavalt etteantud parameetritele (nt lause pikkus, kirjavahem\u00e4rkide arv \u00fche lause piires jmt). GDEXi skoorid on parandatud vastavalt uuele GDEXi konfuguratsioonile.\nEesti keele \u00f5ppekorpuse 2018 (etSkELL) suurus on u 250 000 s\u00f5na ja u 25 miljonit lauset. ",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "74cbac8f-47a4-51b9-9858-353501fc841a",
-    "notes": [
-        "Abstract",
-        "Eesti keele \u00f5ppekorpus 2018 (etSkELL) on spetsiaalne tekstikorpus, mis sisaldab ainult keele\u00f5ppijale sobivaid lauseid. Laused p\u00e4rinevad Eesti keele \u00fchendkorpusest 2017 ja Eesti keele A1-C1 \u00f5pikute korpusest 2018. Keele\u00f5ppijale sobivate lausete tuvastamiseks kasutati Kristina Koppeli v\u00e4lja t\u00f6\u00f6tatud eesti keele GDEXi (Good Dictionary Example) moodulit, mis v\u00f5imaldab lausete filtreerimist vastavalt etteantud parameetritele (nt lause pikkus, kirjavahem\u00e4rkide arv \u00fche lause piires jmt). GDEXi skoorid on parandatud vastavalt uuele GDEXi konfuguratsioonile.\nEesti keele \u00f5ppekorpuse 2018 (etSkELL) suurus on u 250 000 s\u00f5na ja u 25 miljonit lauset. "
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14745995"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele \u00f5ppekorpus 2018 (etSkELL)  2018-04",
-        "Estonian Corpus for Learners 2018 (etSkELL)  2018-04"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/770490ae-07ed-50a7-b794-4c1ef96b1194.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/770490ae-07ed-50a7-b794-4c1ef96b1194.json
deleted file mode 100644
index 4ed891d9..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/770490ae-07ed-50a7-b794-4c1ef96b1194.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0017FL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17946197",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17946197"
-    ],
-    "PublicationTimestamp": "2019-01-03T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:17946197;2019-04-15T17:34:13Z;ESTDOI;ESTDOI.KEEL;Kollokatsioonid;Muischnek, Kadri;Center of Estonian Language Resources;2019;Issued: 2019-01-03;Updated: 2019-01-03;doi:10.15155/1-00-0000-0000-0000-0017FL;Abstract;Kollokatsioonide leidja abil saab leida vastavalt p\u00e4ringule \u00fcksikuid kollokatsioone, kuid selleks, et teada saada kollokatsioonide pingerida, ongi abiks siin esitatud sagedusloendid kollokatsioonide leidja alusmaterjalist. T\u00e4nu pingeridadele on v\u00f5imalik vaadelda valitud statistiku v\u00f5i lihtsalt kollokatsioonipaari sageduse alusel j\u00e4rjestatud 5000 sagedasemat/olulisemat Tasakaalus korpuses leiduvat kollokatsioonipaari, mis esinesid korpuses k\u00fcmme v\u00f5i enam korda. Esitatud on sarnaselt kollokatsioonide leidja pakutud v\u00f5imalustega teatud s\u00f5naliiki kuuluva lemma sagedasemad kollokatsioonid teise lemmaga, teatud s\u00f5naliiki kuuluva s\u00f5navormi sagedasemad kollokatsioonid teise s\u00f5navormiga ja teatud s\u00f5naliiki kuuluva lemma sagedasemad kollokatsioonid s\u00f5navormiga.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "770490ae-07ed-50a7-b794-4c1ef96b1194",
-    "notes": [
-        "Abstract",
-        "Kollokatsioonide leidja abil saab leida vastavalt p\u00e4ringule \u00fcksikuid kollokatsioone, kuid selleks, et teada saada kollokatsioonide pingerida, ongi abiks siin esitatud sagedusloendid kollokatsioonide leidja alusmaterjalist. T\u00e4nu pingeridadele on v\u00f5imalik vaadelda valitud statistiku v\u00f5i lihtsalt kollokatsioonipaari sageduse alusel j\u00e4rjestatud 5000 sagedasemat/olulisemat Tasakaalus korpuses leiduvat kollokatsioonipaari, mis esinesid korpuses k\u00fcmme v\u00f5i enam korda. Esitatud on sarnaselt kollokatsioonide leidja pakutud v\u00f5imalustega teatud s\u00f5naliiki kuuluva lemma sagedasemad kollokatsioonid teise lemmaga, teatud s\u00f5naliiki kuuluva s\u00f5navormi sagedasemad kollokatsioonid teise s\u00f5navormiga ja teatud s\u00f5naliiki kuuluva lemma sagedasemad kollokatsioonid s\u00f5navormiga."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17946197"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Kollokatsioonid"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/771a88cc-355c-5092-b3aa-d6c2e09d49f7.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/771a88cc-355c-5092-b3aa-d6c2e09d49f7.json
deleted file mode 100644
index db58a043..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/771a88cc-355c-5092-b3aa-d6c2e09d49f7.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/4-00-0000-0000-0000-0000DL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5757463",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5757463"
-    ],
-    "PublicationTimestamp": "2015-05-22T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:5757463;2019-04-17T17:27:24Z;ESTDOI;ESTDOI.KEEL;Sageduss\u00f5nastik;Estonian Frequency Dictionary;Muischnek, Kadri;Center of Estonian Language Resources;2013;Issued: 2013-01-10;Updated: 2015-05-22;doi:10.15155/4-00-0000-0000-0000-0000DL;Abstract;Sagedusloendid, mis on tehtud 0,5 miljoni s\u00f5naga ilukirjanduse korpuse baasil (aastatest 1992-1998) ja 0,5 miljoni s\u00f5naga ajakirjanduse korpuse baasil (1995-1999). Kolm sagedusloendit s\u00f5nade ja nende sagedustega alamkorpustest ning koondkorpuses 10 000 lemmat (s\u00f5naliikidega) 1000 sagedasemat s\u00f5navormi, 100 s\u00f5na, mis on iseloomulikud ainult \u00fchele allkorpusele, kuid puuduvad teises.;Abstract;Frequency lists based on 0.5 million words of fiction texts (representing years 1992-1998), and 0.5 million words newspaper texts (from years 1995-1999).\nThree frequency lists, with words and their frequencies in the sub-corpora and in the whole corpus:\n10 000 lemmas (includes also POS)\n1000 most frequent word forms\n100 words representing only one of the sub-corpora - words that counted as frequent in one of the sub-corpora, but were missing in the other. \n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "771a88cc-355c-5092-b3aa-d6c2e09d49f7",
-    "notes": [
-        "Abstract",
-        "Sagedusloendid, mis on tehtud 0,5 miljoni s\u00f5naga ilukirjanduse korpuse baasil (aastatest 1992-1998) ja 0,5 miljoni s\u00f5naga ajakirjanduse korpuse baasil (1995-1999). Kolm sagedusloendit s\u00f5nade ja nende sagedustega alamkorpustest ning koondkorpuses 10 000 lemmat (s\u00f5naliikidega) 1000 sagedasemat s\u00f5navormi, 100 s\u00f5na, mis on iseloomulikud ainult \u00fchele allkorpusele, kuid puuduvad teises.",
-        "Abstract",
-        "Frequency lists based on 0.5 million words of fiction texts (representing years 1992-1998), and 0.5 million words newspaper texts (from years 1995-1999).\nThree frequency lists, with words and their frequencies in the sub-corpora and in the whole corpus:\n10 000 lemmas (includes also POS)\n1000 most frequent word forms\n100 words representing only one of the sub-corpora - words that counted as frequent in one of the sub-corpora, but were missing in the other. \n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5757463"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Sageduss\u00f5nastik",
-        "Estonian Frequency Dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7734eadb-46a3-5dbe-804e-58bb4ace9dfc.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7734eadb-46a3-5dbe-804e-58bb4ace9dfc.json
deleted file mode 100644
index cc707800..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7734eadb-46a3-5dbe-804e-58bb4ace9dfc.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-079CEL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17602313",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17602313"
-    ],
-    "PublicationTimestamp": "2018-11-23T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Raadik, Maire"
-    ],
-    "fulltext": "oai:oai.datacite.org:17602313;2019-03-22T00:01:12Z;ESTDOI;ESTDOI.KEEL;Eesti \u00f5igekeelsuss\u00f5naraamatu \u00d5S 2018 veebiversioon;Online Dictionary of Standard Estonian \u00d5S 2018 ;Raadik, Maire;Center of Estonian Language Resources;2018;Issued: 2018-11-23;Updated: 2018-11-23;doi:10.15155/3-00-0000-0000-0000-079CEL;Abstract;Kajastab eesti kirjakeele normi.;Abstract;\u00d5S 2018 is a normative dictionary of modern standard Estonian. It shows the standardized spelling, pronunciation and inflection of words and gives recommendations on semantics and syntax. The dictionary has annexes on  abbreviations, geographical names and pronunciation of foreign names.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7734eadb-46a3-5dbe-804e-58bb4ace9dfc",
-    "notes": [
-        "Abstract",
-        "Kajastab eesti kirjakeele normi.",
-        "Abstract",
-        "\u00d5S 2018 is a normative dictionary of modern standard Estonian. It shows the standardized spelling, pronunciation and inflection of words and gives recommendations on semantics and syntax. The dictionary has annexes on  abbreviations, geographical names and pronunciation of foreign names."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17602313"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti \u00f5igekeelsuss\u00f5naraamatu \u00d5S 2018 veebiversioon",
-        "Online Dictionary of Standard Estonian \u00d5S 2018 "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/789847c2-4bba-5c74-98eb-6639d5c90a0d.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/789847c2-4bba-5c74-98eb-6639d5c90a0d.json
deleted file mode 100644
index 1f4f25f2..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/789847c2-4bba-5c74-98eb-6639d5c90a0d.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0016BL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17939994",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17939994"
-    ],
-    "PublicationTimestamp": "2019-01-02T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Lippus, P\u00e4rtel"
-    ],
-    "fulltext": "oai:oai.datacite.org:17939994;2019-01-02T11:43:46Z;ESTDOI;ESTDOI.KEEL;Foneetikakorpuse otsimootor;Lippus, P\u00e4rtel;Center of Estonian Language Resources;2019;Issued: 2019-01-02;Updated: 2019-01-02;doi:10.15155/1-00-0000-0000-0000-0016BL;Abstract;Veebip\u00f5hine otsingumootor v\u00f5imaldab otsida korpusest \u00fche s\u00f5na piires, vastuseks antakse 2-sekundiline helil\u00f5ik ja selle m\u00e4rgendus.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "789847c2-4bba-5c74-98eb-6639d5c90a0d",
-    "notes": [
-        "Abstract",
-        "Veebip\u00f5hine otsingumootor v\u00f5imaldab otsida korpusest \u00fche s\u00f5na piires, vastuseks antakse 2-sekundiline helil\u00f5ik ja selle m\u00e4rgendus."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17939994"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Foneetikakorpuse otsimootor"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/78b21385-f814-539f-b772-c4b79a12e206.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/78b21385-f814-539f-b772-c4b79a12e206.json
deleted file mode 100644
index 5efde9b4..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/78b21385-f814-539f-b772-c4b79a12e206.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00182L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17950797",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17950797"
-    ],
-    "PublicationTimestamp": "2019-01-04T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Iva, Sulev"
-    ],
-    "fulltext": "oai:oai.datacite.org:17950797;2019-03-10T18:25:47Z;ESTDOI;ESTDOI.KEEL;Uma Lehe korpuse otsing;Iva, Sulev;Center of Estonian Language Resources;2019;Issued: 2019-01-04;Updated: 2019-01-04;doi:10.15155/1-00-0000-0000-0000-00182L;Abstract;V\u00f5ru ja seto ajakirjanduskorpuse mahuks on\n1 269 000 s\u00f5na, sellest: Uma Lehe korpus \u2013 ca 762 000 s\u00f5na, Ajalehe Setomaa korpus \u2013 seto keeles 279 000, eesti keeles 228 000 s\u00f5na. V\u00f5ru ja seto kirjakeele ajakirjanduse allkorpuste vaba juurdep\u00e4\u00e4suga otsingumootorid asuvad: \n- Uma Leht: http://www.murre.ut.ee/otsing/voru.php\n- Setomaa: http://synaq.org/seto",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "78b21385-f814-539f-b772-c4b79a12e206",
-    "notes": [
-        "Abstract",
-        "V\u00f5ru ja seto ajakirjanduskorpuse mahuks on\n1 269 000 s\u00f5na, sellest: Uma Lehe korpus \u2013 ca 762 000 s\u00f5na, Ajalehe Setomaa korpus \u2013 seto keeles 279 000, eesti keeles 228 000 s\u00f5na. V\u00f5ru ja seto kirjakeele ajakirjanduse allkorpuste vaba juurdep\u00e4\u00e4suga otsingumootorid asuvad: \n- Uma Leht: http://www.murre.ut.ee/otsing/voru.php\n- Setomaa: http://synaq.org/seto"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17950797"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Uma Lehe korpuse otsing"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7935600b-1b46-526f-b74f-ad891e9306f9.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7935600b-1b46-526f-b74f-ad891e9306f9.json
deleted file mode 100644
index 2892866f..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7935600b-1b46-526f-b74f-ad891e9306f9.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-079DDL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17960242",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17960242"
-    ],
-    "PublicationTimestamp": "2019-01-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:17960242;2019-02-25T08:32:05Z;ESTDOI;ESTDOI.KEEL;Tekstide helindaja;Hein, Indrek;Center of Estonian Language Resources;2019;Issued: 2019-01-07;Updated: 2019-01-07;doi:10.15155/3-00-0000-0000-0000-079DDL;Abstract;Heliraamatute genereerija Vox Populi, mis kasutab EKI k\u00f5nes\u00fcnteesi ja h\u00e4\u00e4ldusbaasi, et pikemaid tekste helindada.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7935600b-1b46-526f-b74f-ad891e9306f9",
-    "notes": [
-        "Abstract",
-        "Heliraamatute genereerija Vox Populi, mis kasutab EKI k\u00f5nes\u00fcnteesi ja h\u00e4\u00e4ldusbaasi, et pikemaid tekste helindada."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17960242"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Tekstide helindaja"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7951725b-f65e-54c4-8b75-1ff441ada0bf.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7951725b-f65e-54c4-8b75-1ff441ada0bf.json
deleted file mode 100644
index df90e529..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7951725b-f65e-54c4-8b75-1ff441ada0bf.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05771L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:8521722",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:8521722"
-    ],
-    "PublicationTimestamp": "2015-05-06T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Langemets, Margit"
-    ],
-    "fulltext": "oai:oai.datacite.org:8521722;2019-03-31T23:30:47Z;ESTDOI;ESTDOI.KEEL;Fraseoloogias\u00f5naraamat;Dictionary of Estonian Phraseology;Langemets, Margit;Center of Estonian Language Resources;2015;Issued: 2015-05-06;Updated: 2015-05-06;doi:10.15155/3-00-0000-0000-0000-05771L;Abstract;Sisaldab \u00fcle 7500 p\u00fcsiv\u00e4ljendi, sealhulgas raamatulikke, k\u00f5nekeelseid ja vananenud ning vulgaarseid v\u00e4ljendeid, mitmesuguseid \u00fctlusi ning kantselei- ja stampvormeleid.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7951725b-f65e-54c4-8b75-1ff441ada0bf",
-    "notes": [
-        "Abstract",
-        "Sisaldab \u00fcle 7500 p\u00fcsiv\u00e4ljendi, sealhulgas raamatulikke, k\u00f5nekeelseid ja vananenud ning vulgaarseid v\u00e4ljendeid, mitmesuguseid \u00fctlusi ning kantselei- ja stampvormeleid."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:8521722"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Fraseoloogias\u00f5naraamat",
-        "Dictionary of Estonian Phraseology"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/79ec1227-f34b-5e38-8ebe-36b4191fb19a.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/79ec1227-f34b-5e38-8ebe-36b4191fb19a.json
deleted file mode 100644
index 5515e504..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/79ec1227-f34b-5e38-8ebe-36b4191fb19a.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-0002CL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5772669",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5772669"
-    ],
-    "PublicationTimestamp": "2015-05-22T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "J\u00fcrviste, Madis"
-    ],
-    "fulltext": "oai:oai.datacite.org:5772669;2019-03-29T04:02:25Z;ESTDOI;ESTDOI.KEEL;Suur eesti-prantsuse s\u00f5naraamat;Grand dictionnaire estonien-fran\u00e7ais;Comprehensive Estonian-French Dictionary;J\u00fcrviste, Madis;Center of Estonian Language Resources;2015;Issued: 2015-05-07;Updated: 2015-05-22;doi:10.15155/9-00-0000-0000-0000-0002CL;Abstract;A comprehensive bilingual general language translation dictionary.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "79ec1227-f34b-5e38-8ebe-36b4191fb19a",
-    "notes": [
-        "Abstract",
-        "A comprehensive bilingual general language translation dictionary."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5772669"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Suur eesti-prantsuse s\u00f5naraamat",
-        "Grand dictionnaire estonien-fran\u00e7ais",
-        "Comprehensive Estonian-French Dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7b4db999-19ef-5350-86a1-0602c6ecb808.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7b4db999-19ef-5350-86a1-0602c6ecb808.json
deleted file mode 100644
index b8aa6712..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7b4db999-19ef-5350-86a1-0602c6ecb808.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-071EFL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14560424",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14560424"
-    ],
-    "PublicationTimestamp": "2018-03-26T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Koppel, Kristina",
-        "Kallas, Jelena"
-    ],
-    "fulltext": "oai:oai.datacite.org:14560424;2019-04-18T16:00:47Z;ESTDOI;ESTDOI.KEEL;Sketch Engine eesti keele \u00f5ppijale (etSkELL);Sketch Engine for Estonian Language Learning (etSkELL);Kallas, Jelena;Koppel, Kristina;Center of Estonian Language Resources;2018;Issued: 2018-03-26;Updated: 2018-03-26;doi:10.15155/3-00-0000-0000-0000-071EFL;Abstract;etSkELL on automaatselt loodud keele\u00f5ppekeskkond, mille alus on Eesti keele \u00f5ppekorpus 2018. Korpus sisaldab umbes 25 miljonit lauset ja 250 miljonit s\u00f5na. Laused on p\u00e4rit erinevatest meedia-, ilukirjandus- ja teadustekstidest ning eestikeelsest Vikipeediast ja Eesti keele A1-C1 \u00f5pikute korpusest 2018.\netSkELL arendati v\u00e4lja Eesti Keele Instituudi ja Lexical Computing Ltd. koost\u00f6\u00f6s.\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7b4db999-19ef-5350-86a1-0602c6ecb808",
-    "notes": [
-        "Abstract",
-        "etSkELL on automaatselt loodud keele\u00f5ppekeskkond, mille alus on Eesti keele \u00f5ppekorpus 2018. Korpus sisaldab umbes 25 miljonit lauset ja 250 miljonit s\u00f5na. Laused on p\u00e4rit erinevatest meedia-, ilukirjandus- ja teadustekstidest ning eestikeelsest Vikipeediast ja Eesti keele A1-C1 \u00f5pikute korpusest 2018.\netSkELL arendati v\u00e4lja Eesti Keele Instituudi ja Lexical Computing Ltd. koost\u00f6\u00f6s.\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14560424"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Sketch Engine eesti keele \u00f5ppijale (etSkELL)",
-        "Sketch Engine for Estonian Language Learning (etSkELL)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7c650f6f-ef23-5d16-b78d-56e7d64c3cd3.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7c650f6f-ef23-5d16-b78d-56e7d64c3cd3.json
deleted file mode 100644
index 02b72e88..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7c650f6f-ef23-5d16-b78d-56e7d64c3cd3.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-0009BL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17957572",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17957572"
-    ],
-    "PublicationTimestamp": "2019-01-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Alum\u00e4e, Tanel"
-    ],
-    "fulltext": "oai:oai.datacite.org:17957572;2019-03-01T01:32:39Z;ESTDOI;ESTDOI.KEEL;Eestikeelse k\u00f5netuvastuss\u00fcssteemi h\u00e4\u00e4ldusleksikoni genereerija;Alum\u00e4e, Tanel;Center of Estonian Language Resources;2019;Issued: 2019-01-07;Updated: 2019-01-07;doi:10.15155/9-00-0000-0000-0000-0009BL;Abstract;Genereerib h\u00e4\u00e4ldusleksikoni",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7c650f6f-ef23-5d16-b78d-56e7d64c3cd3",
-    "notes": [
-        "Abstract",
-        "Genereerib h\u00e4\u00e4ldusleksikoni"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17957572"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eestikeelse k\u00f5netuvastuss\u00fcssteemi h\u00e4\u00e4ldusleksikoni genereerija"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7ccc5a9c-833f-54f8-8358-1d3a5b4be5cb.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7ccc5a9c-833f-54f8-8358-1d3a5b4be5cb.json
deleted file mode 100644
index 3dafc033..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7ccc5a9c-833f-54f8-8358-1d3a5b4be5cb.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-0002FL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:6073503",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:6073503"
-    ],
-    "PublicationTimestamp": "2019-01-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "J\u00fcrviste, Madis"
-    ],
-    "fulltext": "oai:oai.datacite.org:6073503;2019-04-17T21:02:38Z;ESTDOI;ESTDOI.KEEL;Eesti-prantsuse paralleelkorpus;Corpus parall\u00e8le estonien-fran\u00e7ais;Estonian-French Parallel Corpus;J\u00fcrviste, Madis;Center of Estonian Language Resources;2015;Issued: 2015-06-03;Updated: 2019-01-07;doi:10.15155/9-00-0000-0000-0000-0002FL;Abstract;Aligned parallel translation corpus containing 65 million words (including both languages).",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7ccc5a9c-833f-54f8-8358-1d3a5b4be5cb",
-    "notes": [
-        "Abstract",
-        "Aligned parallel translation corpus containing 65 million words (including both languages)."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:6073503"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti-prantsuse paralleelkorpus",
-        "Corpus parall\u00e8le estonien-fran\u00e7ais",
-        "Estonian-French Parallel Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7d690bf0-3b52-570f-93ee-98efc5b23849.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7d690bf0-3b52-570f-93ee-98efc5b23849.json
deleted file mode 100644
index 1b1bfadc..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7d690bf0-3b52-570f-93ee-98efc5b23849.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/EKI.0006",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:4597353",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:4597353"
-    ],
-    "PublicationTimestamp": "2012-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:4597353;2019-04-20T03:02:32Z;ESTDOI;ESTDOI.KEEL;Morphological Toolset for Estonian;Hein, Indrek;Center of Estonian Language Resources;2012;doi:10.15155/EKI.0006",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7d690bf0-3b52-570f-93ee-98efc5b23849",
-    "oai_identifier": [
-        "oai:oai.datacite.org:4597353"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Morphological Toolset for Estonian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7d69a6b7-77d5-5b50-a795-c2a7e524e8a5.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7d69a6b7-77d5-5b50-a795-c2a7e524e8a5.json
deleted file mode 100644
index 211d76b5..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7d69a6b7-77d5-5b50-a795-c2a7e524e8a5.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05BD9L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9474539",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9474539"
-    ],
-    "PublicationTimestamp": "2016-11-09T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Piits, Liisi"
-    ],
-    "fulltext": "oai:oai.datacite.org:9474539;2019-02-19T21:32:35Z;ESTDOI;ESTDOI.KEEL;Eesti Keele Instituudi k\u00f5nes\u00fcnteesikorpus;Piits, Liisi;Center of Estonian Language Resources;2016;Issued: 2016-11-09;Updated: 2016-11-09;doi:10.15155/3-00-0000-0000-0000-05BD9L;Abstract;Eestikeelse tekst-k\u00f5ne s\u00fcnteesi h\u00e4\u00e4lemudelite loomiseks kasutatud sisseloetud tekstid.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7d69a6b7-77d5-5b50-a795-c2a7e524e8a5",
-    "notes": [
-        "Abstract",
-        "Eestikeelse tekst-k\u00f5ne s\u00fcnteesi h\u00e4\u00e4lemudelite loomiseks kasutatud sisseloetud tekstid."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9474539"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti Keele Instituudi k\u00f5nes\u00fcnteesikorpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7da0e160-ae57-5f23-99fc-7ce42f68341c.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7da0e160-ae57-5f23-99fc-7ce42f68341c.json
deleted file mode 100644
index b7aaa641..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7da0e160-ae57-5f23-99fc-7ce42f68341c.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05AF2L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9310573",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9310573"
-    ],
-    "PublicationTimestamp": "2016-10-19T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek",
-        "\u00d5im, Asta"
-    ],
-    "fulltext": "oai:oai.datacite.org:9310573;2019-02-19T23:01:48Z;ESTDOI;ESTDOI.KEEL;S\u00fcnon\u00fc\u00fcmis\u00f5nastik;Dictionary of Estonian Synonyms;Hein, Indrek;\u00d5im, Asta;Center of Estonian Language Resources;2016;Issued: 2016-10-19;Updated: 2016-10-19;doi:10.15155/3-00-0000-0000-0000-05AF2L;Abstract;Pakub kirjas ja k\u00f5nes kasutatavaid s\u00fcnon\u00fc\u00fcme, sealhulgas valiku vanemaid, murdelisi ning k\u00f5nekeelseid s\u00f5nu v\u00f5i v\u00e4ljendeid, samuti termineid ning kantselei- ja stampkeelendeid.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7da0e160-ae57-5f23-99fc-7ce42f68341c",
-    "notes": [
-        "Abstract",
-        "Pakub kirjas ja k\u00f5nes kasutatavaid s\u00fcnon\u00fc\u00fcme, sealhulgas valiku vanemaid, murdelisi ning k\u00f5nekeelseid s\u00f5nu v\u00f5i v\u00e4ljendeid, samuti termineid ning kantselei- ja stampkeelendeid."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9310573"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "S\u00fcnon\u00fc\u00fcmis\u00f5nastik",
-        "Dictionary of Estonian Synonyms"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7ddee5a9-c532-5254-ba0c-d9f7c74ddb09.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7ddee5a9-c532-5254-ba0c-d9f7c74ddb09.json
deleted file mode 100644
index e343a10c..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7ddee5a9-c532-5254-ba0c-d9f7c74ddb09.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05B53L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9352877",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9352877"
-    ],
-    "PublicationTimestamp": "2017-03-23T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Niit, Ellen",
-        "Laansalu, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:9352877;2019-02-15T18:37:47Z;ESTDOI;ESTDOI.KEEL;Idamurde s\u00f5nastik;The Dictionary of the Eastern Dialect ;Laansalu, Tiina;Niit, Ellen;Center of Estonian Language Resources;2016;Issued: 2016-10-31;Updated: 2017-03-23;doi:10.15155/3-00-0000-0000-0000-05B53L;Abstract;S\u00f5nastik kuulub Eesti Keele Instituudi v\u00e4ikeste murdes\u00f5nastike sarja. S\u00f5nastik sisaldab 7000 m\u00e4rks\u00f5na ning on m\u00f5eldud k\u00f5igile, kes kasutavad oma t\u00f6\u00f6s v\u00f5i \u00f5pingutes murdekeelt v\u00f5i kes on p\u00e4rit Ida-Eestist ja keda paelub esivanemate k\u00f5nepruuk.;Abstract;This dictionary of 7000 entry words is intended for everyone who deals with dialects, either professionally or academically, as well as for the people with an Eastern-Estonian background who find their ancestors\u00b4 tongue fascinating.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7ddee5a9-c532-5254-ba0c-d9f7c74ddb09",
-    "notes": [
-        "Abstract",
-        "S\u00f5nastik kuulub Eesti Keele Instituudi v\u00e4ikeste murdes\u00f5nastike sarja. S\u00f5nastik sisaldab 7000 m\u00e4rks\u00f5na ning on m\u00f5eldud k\u00f5igile, kes kasutavad oma t\u00f6\u00f6s v\u00f5i \u00f5pingutes murdekeelt v\u00f5i kes on p\u00e4rit Ida-Eestist ja keda paelub esivanemate k\u00f5nepruuk.",
-        "Abstract",
-        "This dictionary of 7000 entry words is intended for everyone who deals with dialects, either professionally or academically, as well as for the people with an Eastern-Estonian background who find their ancestors\u00b4 tongue fascinating."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9352877"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Idamurde s\u00f5nastik",
-        "The Dictionary of the Eastern Dialect "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7e4c10c1-17cd-5cba-9973-5ed41360e66e.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7e4c10c1-17cd-5cba-9973-5ed41360e66e.json
deleted file mode 100644
index 90fa9623..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7e4c10c1-17cd-5cba-9973-5ed41360e66e.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/TY.0019",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:4597378",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:4597378"
-    ],
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:4597378;2019-04-03T03:01:52Z;ESTDOI;ESTDOI.KEEL;Corpus of the Proceedings of Estonian Parliament;Muischnek, Kadri;Center of Estonian Language Resources;2013;doi:10.15155/TY.0019",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7e4c10c1-17cd-5cba-9973-5ed41360e66e",
-    "oai_identifier": [
-        "oai:oai.datacite.org:4597378"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus of the Proceedings of Estonian Parliament"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7ea0d048-3dbc-5c54-a236-81fdeda293b9.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7ea0d048-3dbc-5c54-a236-81fdeda293b9.json
deleted file mode 100644
index 82c2e692..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7ea0d048-3dbc-5c54-a236-81fdeda293b9.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0018AL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17961012",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17961012"
-    ],
-    "PublicationTimestamp": "2019-01-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "M\u00fc\u00fcrisep, Kaili"
-    ],
-    "fulltext": "oai:oai.datacite.org:17961012;2019-03-31T14:01:53Z;ESTDOI;ESTDOI.KEEL;S\u00fcntaksi eelt\u00f6\u00f6tlusmoodulid;Preprocessing module for parsing;M\u00fc\u00fcrisep, Kaili;Center of Estonian Language Resources;2019;Issued: 2019-01-07;Updated: 2019-01-07;doi:10.15155/1-00-0000-0000-0000-0018AL;Abstract;Eelt\u00f6\u00f6tlusmoodulid Eesti keele Koondkorpuse xml-m\u00e4rgendusega teadus- ja ajakirjandustekstide jaoks, teevad tekstid parserite jaoks sobivamale kujule ning (soovi korral) nummerdavad laused.;Abstract;Preprocessing module, to be used before parsing. Input: text with xml-markup, e.g. Estonian Reference Corpus texts (http://www.cl.ut.ee/korpused/segakorpus/)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7ea0d048-3dbc-5c54-a236-81fdeda293b9",
-    "notes": [
-        "Abstract",
-        "Eelt\u00f6\u00f6tlusmoodulid Eesti keele Koondkorpuse xml-m\u00e4rgendusega teadus- ja ajakirjandustekstide jaoks, teevad tekstid parserite jaoks sobivamale kujule ning (soovi korral) nummerdavad laused.",
-        "Abstract",
-        "Preprocessing module, to be used before parsing. Input: text with xml-markup, e.g. Estonian Reference Corpus texts (http://www.cl.ut.ee/korpused/segakorpus/)"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17961012"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "S\u00fcntaksi eelt\u00f6\u00f6tlusmoodulid",
-        "Preprocessing module for parsing"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7f19ee3b-eb13-5b29-90ca-f86e40c46271.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7f19ee3b-eb13-5b29-90ca-f86e40c46271.json
deleted file mode 100644
index e154f54f..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7f19ee3b-eb13-5b29-90ca-f86e40c46271.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0011DL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:7802325",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:7802325"
-    ],
-    "PublicationTimestamp": "2017-09-12T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Vare, Kadri",
-        "Orav, Heili"
-    ],
-    "fulltext": "oai:oai.datacite.org:7802325;2019-03-17T18:37:58Z;ESTDOI;ESTDOI.KEEL;Eesti Wordnet (kb73-VIIMANE);Estonian Wordnet (kb73-LAST);Orav, Heili;Vare, Kadri;Center of Estonian Language Resources;2014;Issued: 2014-03-21;Updated: 2017-09-12;doi:10.15155/1-00-0000-0000-0000-0011DL;Abstract; Eesti Wordnetis (versioon 73) on praeguse seisuga (m\u00e4rts 2016) 77 878 m\u00f5istet, milles s\u00f5nu 106 202, semantilisi suhteid 248 996 ja seoseid Princetoni Wordnetiga (1.5) 112 283.  K\u00f5ik m\u00f5isted on varustatud v\u00e4hemalt \u00fche keelesisese suhtega ja v\u00e4hemalt \u00fche ILI-suhtega.;Abstract;The atom of a wordnet-type thesaurus is a synonym set (also called a synset), which is a set containing all the synonymous words or multi-word units that express the same concept. All words in a synset belong into the same part of speech.\n\nTHIS IS THE NEWEST VERSION",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7f19ee3b-eb13-5b29-90ca-f86e40c46271",
-    "notes": [
-        "Abstract",
-        " Eesti Wordnetis (versioon 73) on praeguse seisuga (m\u00e4rts 2016) 77 878 m\u00f5istet, milles s\u00f5nu 106 202, semantilisi suhteid 248 996 ja seoseid Princetoni Wordnetiga (1.5) 112 283.  K\u00f5ik m\u00f5isted on varustatud v\u00e4hemalt \u00fche keelesisese suhtega ja v\u00e4hemalt \u00fche ILI-suhtega.",
-        "Abstract",
-        "The atom of a wordnet-type thesaurus is a synonym set (also called a synset), which is a set containing all the synonymous words or multi-word units that express the same concept. All words in a synset belong into the same part of speech.\n\nTHIS IS THE NEWEST VERSION"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:7802325"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti Wordnet (kb73-VIIMANE)",
-        "Estonian Wordnet (kb73-LAST)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7f5add65-2c4a-518e-99d4-d18f1a3e817a.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7f5add65-2c4a-518e-99d4-d18f1a3e817a.json
deleted file mode 100644
index a2c842d8..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7f5add65-2c4a-518e-99d4-d18f1a3e817a.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00170L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17940281",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17940281"
-    ],
-    "PublicationTimestamp": "2019-01-02T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:17940281;2019-04-11T17:37:07Z;ESTDOI;ESTDOI.KEEL;Eesti keele Kitsenduste Grammatika reeglid 1.0;Muischnek, Kadri;Center of Estonian Language Resources;2019;Issued: 2019-01-02;Updated: 2019-01-02;doi:10.15155/1-00-0000-0000-0000-00170L;Abstract;S\u00fcntaktilise anal\u00fc\u00fcsi jaoks on vajalik\n\n eesti keele morfoloogiline anal\u00fcsaator, nt Vabamorf: https://github.com/Filosoft/vabamorf/blob/master/doc/readme.html Et Vabamorfi automaatselt kasutada, on vaja failis test.sh paika panna installeeritud Vabamorfi programmi ja s\u00f5nastiku teed.\nVISL CG3 Kitsenduste Grammatika anal\u00fcsaator: http://beta.visl.sdu.dk/constraint_grammar.html. Grammatikad \u00fchilduvad VISL CG3 versiooniga 0.9.9.10379.\nReeglite failid ja skriptid moodulite \u00fchendamiseks.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7f5add65-2c4a-518e-99d4-d18f1a3e817a",
-    "notes": [
-        "Abstract",
-        "S\u00fcntaktilise anal\u00fc\u00fcsi jaoks on vajalik\n\n eesti keele morfoloogiline anal\u00fcsaator, nt Vabamorf: https://github.com/Filosoft/vabamorf/blob/master/doc/readme.html Et Vabamorfi automaatselt kasutada, on vaja failis test.sh paika panna installeeritud Vabamorfi programmi ja s\u00f5nastiku teed.\nVISL CG3 Kitsenduste Grammatika anal\u00fcsaator: http://beta.visl.sdu.dk/constraint_grammar.html. Grammatikad \u00fchilduvad VISL CG3 versiooniga 0.9.9.10379.\nReeglite failid ja skriptid moodulite \u00fchendamiseks."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17940281"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele Kitsenduste Grammatika reeglid 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7fd07637-469b-5448-a819-87ccba395f03.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7fd07637-469b-5448-a819-87ccba395f03.json
deleted file mode 100644
index ee103ff5..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7fd07637-469b-5448-a819-87ccba395f03.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0017DL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17946159",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17946159"
-    ],
-    "PublicationTimestamp": "2019-01-03T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:17946159;2019-04-16T03:32:44Z;ESTDOI;ESTDOI.KEEL;Mitmikute sagedusloendid;Muischnek, Kadri;Center of Estonian Language Resources;2019;Issued: 2019-01-03;Updated: 2019-01-03;doi:10.15155/1-00-0000-0000-0000-0017DL;Abstract;Lemmade ja s\u00f5navormide mitmikute (n-grammide) sagedusloendid Tasakaalus korpuse p\u00f5hjal",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7fd07637-469b-5448-a819-87ccba395f03",
-    "notes": [
-        "Abstract",
-        "Lemmade ja s\u00f5navormide mitmikute (n-grammide) sagedusloendid Tasakaalus korpuse p\u00f5hjal"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17946159"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Mitmikute sagedusloendid"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7fd20d1f-aacf-55b4-ace0-8889e5fe2df9.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7fd20d1f-aacf-55b4-ace0-8889e5fe2df9.json
deleted file mode 100644
index 3d86a5fd..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7fd20d1f-aacf-55b4-ace0-8889e5fe2df9.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-079CFL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17841060",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17841060"
-    ],
-    "PublicationTimestamp": "2018-12-18T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Paet, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:17841060;2019-03-21T10:01:52Z;ESTDOI;ESTDOI.KEEL;\u00d5S 1918. \u201eEesti keele \u00f5igekirjutuse-s\u00f5naraamatu\u201c kommenteeritud v\u00e4ljaanne (veebiversioon);\u201eThe Spelling Dictionary of Estonian 1918\u201c. Commented online dictionary;Paet, Tiina;Center of Estonian Language Resources;2018;Issued: 2018-12-18;Updated: 2018-12-18;doi:10.15155/3-00-0000-0000-0000-079CFL;Abstract;S\u00f5nastik v\u00f5imaldab linkide kaudu v\u00f5rrelda 1918. aasta \u201eEesti keele \u00f5igekirjutuse-s\u00f5naraamatu\u201c m\u00e4rks\u00f5nastikku \u201eEesti \u00f5igekeelsuss\u00f5naraamat \u00d5S 2018\u201c m\u00e4rks\u00f5nastikuga ja n\u00e4ha, kuidas eesti kirjakeele norm on saja aastaga muutunud.;Abstract;There are links enabling one to compare the entry list of the 1918 dictionary with that of the Standard Estonian Dictionary published in 2018, which reveals how the standard has changed over the century.\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7fd20d1f-aacf-55b4-ace0-8889e5fe2df9",
-    "notes": [
-        "Abstract",
-        "S\u00f5nastik v\u00f5imaldab linkide kaudu v\u00f5rrelda 1918. aasta \u201eEesti keele \u00f5igekirjutuse-s\u00f5naraamatu\u201c m\u00e4rks\u00f5nastikku \u201eEesti \u00f5igekeelsuss\u00f5naraamat \u00d5S 2018\u201c m\u00e4rks\u00f5nastikuga ja n\u00e4ha, kuidas eesti kirjakeele norm on saja aastaga muutunud.",
-        "Abstract",
-        "There are links enabling one to compare the entry list of the 1918 dictionary with that of the Standard Estonian Dictionary published in 2018, which reveals how the standard has changed over the century.\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17841060"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "\u00d5S 1918. \u201eEesti keele \u00f5igekirjutuse-s\u00f5naraamatu\u201c kommenteeritud v\u00e4ljaanne (veebiversioon)",
-        "\u201eThe Spelling Dictionary of Estonian 1918\u201c. Commented online dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7ff6eb7e-b6c0-5540-84a1-d00cad1eb71e.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7ff6eb7e-b6c0-5540-84a1-d00cad1eb71e.json
deleted file mode 100644
index d36b72ad..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/7ff6eb7e-b6c0-5540-84a1-d00cad1eb71e.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-00163L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:18304740",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:18304740"
-    ],
-    "PublicationTimestamp": "2013-01-07T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:18304740;2019-03-03T18:37:37Z;ESTDOI;ESTDOI.KEEL;Corpus of Estonian scientific texts D;Muischnek, Kadri;Center of Estonian Language Resources;2013;Issued: 2013-01-07;Updated: 2013-01-07;doi:10.15155/9-00-0000-0000-0000-00163L;Abstract;A text corpus containing 5 million words of Estonian scientific texts: \nPhD dissertations (2,3 million words) and scientific articles.\nMarkup: TEI P5 XML\nencoding: UTF8",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "7ff6eb7e-b6c0-5540-84a1-d00cad1eb71e",
-    "notes": [
-        "Abstract",
-        "A text corpus containing 5 million words of Estonian scientific texts: \nPhD dissertations (2,3 million words) and scientific articles.\nMarkup: TEI P5 XML\nencoding: UTF8"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:18304740"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus of Estonian scientific texts D"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/804da2a5-8c2b-5a05-b8d0-9b82f86737e8.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/804da2a5-8c2b-5a05-b8d0-9b82f86737e8.json
deleted file mode 100644
index 61ebb6ef..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/804da2a5-8c2b-5a05-b8d0-9b82f86737e8.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-07314L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14673669",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14673669"
-    ],
-    "PublicationTimestamp": "2018-04-13T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:14673669;2019-03-23T03:31:49Z;ESTDOI;ESTDOI.KEEL;Vox populi - tekstide helindaja;Hein, Indrek;Center of Estonian Language Resources;2018;Issued: 2018-04-13;Updated: 2018-04-13;doi:10.15155/3-00-0000-0000-0000-07314L;Abstract;Vox populi e rahva h\u00e4\u00e4l koosneb kahest komponendist: tekstide helindajast (siinne leht) ja h\u00e4\u00e4lduss\u00f5nastikust koos keelereegleid realiseerivate programmikestega. Nende kahe koost\u00f6\u00f6s ja Eesti Keele Instituudi k\u00f5nes\u00fcnteesi kaasates saab teie saadetud tekstifailist l\u00f5pptulemusena s\u00fcnteesh\u00e4\u00e4lega audiofail.\nLitsents: http://www.eki.ee/eki/litsents.html.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "804da2a5-8c2b-5a05-b8d0-9b82f86737e8",
-    "notes": [
-        "Abstract",
-        "Vox populi e rahva h\u00e4\u00e4l koosneb kahest komponendist: tekstide helindajast (siinne leht) ja h\u00e4\u00e4lduss\u00f5nastikust koos keelereegleid realiseerivate programmikestega. Nende kahe koost\u00f6\u00f6s ja Eesti Keele Instituudi k\u00f5nes\u00fcnteesi kaasates saab teie saadetud tekstifailist l\u00f5pptulemusena s\u00fcnteesh\u00e4\u00e4lega audiofail.\nLitsents: http://www.eki.ee/eki/litsents.html."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14673669"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Vox populi - tekstide helindaja"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/807bc534-054d-5540-98ce-c1c140e86650.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/807bc534-054d-5540-98ce-c1c140e86650.json
deleted file mode 100644
index 787b6c18..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/807bc534-054d-5540-98ce-c1c140e86650.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05925L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:8922496",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:8922496"
-    ],
-    "PublicationTimestamp": "2017-05-10T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Kallas, Jelena",
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:8922496;2019-04-17T17:25:40Z;ESTDOI;ESTDOI.KEEL;Eesti keele p\u00f5his\u00f5navara s\u00f5nastik;The Basic Estonian Dictionary;\u0411\u0430\u0437\u043e\u0432\u044b\u0439 \u0441\u043b\u043e\u0432\u0430\u0440\u044c \u044d\u0441\u0442\u043e\u043d\u0441\u043a\u043e\u0433\u043e \u044f\u0437\u044b\u043a\u0430;Hein, Indrek;Kallas, Jelena;Center of Estonian Language Resources;2016;Issued: 2016-08-23;Updated: 2017-05-10;doi:10.15155/3-00-0000-0000-0000-05925L;Abstract;Sisaldab ca 5000 eesti keele sagedasemat s\u00f5na koos kasutusn\u00e4idetega. S\u00f5nastik sisaldab infot m\u00e4rks\u00f5nade h\u00e4\u00e4lduse, vormimoodustuse, s\u00f5namoodustuse, t\u00e4henduste, rektsiooni, kollokatsioonide, s\u00fcnon\u00fc\u00fcmine, anton\u00fc\u00fcmide ja paron\u00fc\u00fcmide kohta. Lisaks on ka illustreerivad pildid, \u00f5ppelehed, pildilehed ning lisad (\u201eMaad ja rahavad\u201c ja \u201eEesti keele grammatika tabelid\u201c). Elektroonilises versioonis on ka audiofailid. M\u00f5eldud eesk\u00e4tt A2- ja B1-keeleoskustasemega eesti keele \u00f5ppijatele.\n\nVt ka:\nKallas, Jelena; Koppel, Kristina; Tuulik, Maria (2014). Eesti keele p\u00f5his\u00f5navara s\u00f5nastik. Oma Keel, 2, 87\u221289.\nKallas, Jelena; Tuulik, Maria (2011). Eesti keele p\u00f5his\u00f5navara s\u00f5nastik: ajalooline kontekst ja koostamisp\u00f5him\u00f5tted. Eesti Rakenduslingvistika \u00dchingu aastaraamat, 7, 59\u221275.\nBasic Estonian Dictionary: the first Monolingual L2 learner\u2019s Dictionary of Estonian. In: Andrea Abel, Chiara Vettori, Natascia Ralli (Ed.). Proceedings of the XVI EURALEX Internatinoal Congress: The User in Focus, 15-19 July 2014, Bolzano/Bozen (1109\u22121119). Bolzano/Bozen: European Academy.;Abstract;The dictionary includes 5000 important Estonian words explained in a simple language.\n\nThe dictionary is an aid to correct Estonian speaking and writing, usable from beginner to advanced levels (levels \u04102 and B1). The User guide introduces how the information is presented in the dictionary. There are also some auxiliary materials to help you. Picture pages show clothing, fruits, vegetables, vehicles, animals, etc. Study pages introduce Estonian punctuation and how to write numbers, dates, time, etc. Countries and peoples is a table presenting a selection of countries with the names of major inhabiting peoples and of the languages they speak. Grammar tables help you with word conjugation and declination as well as with degrees of comparison. In addition it is shown how most of the whole inflectional paradigm can be produced knowing just a few forms. For teacher offers ideas on what kind of exercises can be made in order to develop students\u2019 linguistic and lexicographic competence.\n\nBasic Estonian Dictionary: the first Monolingual L2 learner\u2019s Dictionary of Estonian. In: Andrea Abel, Chiara Vettori, Natascia Ralli (Ed.). Proceedings of the XVI EURALEX Internatinoal Congress: The User in Focus, 15-19 July 2014, Bolzano/Bozen (1109\u22121119). Bolzano/Bozen: European Academy.;Abstract;\u0412 \u0441\u043b\u043e\u0432\u0430\u0440\u044c \u0432\u043a\u043b\u044e\u0447\u0435\u043d\u043e 5000 \u0441\u043b\u043e\u0432, \u0441\u043e\u0441\u0442\u0430\u0432\u043b\u044f\u044e\u0449\u0438\u0435 \u043e\u0441\u043d\u043e\u0432\u043d\u043e\u0439 \u0441\u043b\u043e\u0432\u0430\u0440\u043d\u044b\u0439 \u0444\u043e\u043d\u0434 \u044d\u0441\u0442\u043e\u043d\u0441\u043a\u043e\u0433\u043e \u044f\u0437\u044b\u043a\u0430.\n\u0421\u043b\u043e\u0432\u0430\u0440\u044c \u043f\u0440\u0435\u0434\u043d\u0430\u0437\u043d\u0430\u0447\u0435\u043d \u0434\u043b\u044f \u0442\u0435\u0445, \u043a\u0442\u043e \u0438\u0437\u0443\u0447\u0430\u0435\u0442 \u044d\u0441\u0442\u043e\u043d\u0441\u043a\u0438\u0439 \u044f\u0437\u044b\u043a \u043d\u0430 \u043d\u0430\u0447\u0430\u043b\u044c\u043d\u043e\u043c \u0438 \u0441\u0440\u0435\u0434\u043d\u0435\u043c \u0443\u0440\u043e\u0432\u043d\u0435 (\u0443\u0440\u043e\u0432\u043d\u0438 \u04102 \u0438 B1). \u0412 \u0440\u0430\u0437\u0434\u0435\u043b\u0435 \u041a\u0430\u043a \u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u044c\u0441\u044f \u0441\u043b\u043e\u0432\u0430\u0440\u0435\u043c \u043e\u0431\u044a\u044f\u0441\u043d\u044f\u0435\u0442\u0441\u044f, \u043a\u0430\u043a \u0432 \u043d\u0435\u043c \u043f\u043e\u0434\u0430\u0435\u0442\u0441\u044f \u0438\u043d\u0444\u043e\u0440\u043c\u0430\u0446\u0438\u044f.\n\u0412 \u043f\u043e\u043c\u043e\u0449\u044c \u0442\u0435\u043c, \u043a\u0442\u043e \u0438\u0437\u0443\u0447\u0430\u0435\u0442 \u044d\u0441\u0442\u043e\u043d\u0441\u043a\u0438\u0439 \u044f\u0437\u044b\u043a, \u043d\u0430 \u0441\u0430\u0439\u0442\u0435 \u0434\u043e\u0441\u0442\u0443\u043f\u043d\u044b \u0442\u0430\u043a\u0436\u0435 \u0434\u043e\u043f\u043e\u043b\u043d\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u0435 \u043c\u0430\u0442\u0435\u0440\u0438\u0430\u043b\u044b. \u0412 \u0440\u0430\u0437\u0434\u0435\u043b\u0435 \u0418\u043b\u043b\u044e\u0441\u0442\u0440\u0430\u0446\u0438\u0438 \u043c\u043e\u0436\u043d\u043e \u0443\u0432\u0438\u0434\u0435\u0442\u044c \u0438\u0437\u043e\u0431\u0440\u0430\u0436\u0435\u043d\u0438\u044f, \u043d\u0430\u043f\u0440\u0438\u043c\u0435\u0440, \u043f\u0440\u0435\u0434\u043c\u0435\u0442\u043e\u0432 \u043e\u0434\u0435\u0436\u0434\u044b, \u0444\u0440\u0443\u043a\u0442\u043e\u0432, \u043e\u0432\u043e\u0449\u0435\u0439, \u0442\u0440\u0430\u043d\u0441\u043f\u043e\u0440\u0442\u043d\u044b\u0445 \u0441\u0440\u0435\u0434\u0441\u0442\u0432 \u0438 \u0436\u0438\u0432\u043e\u0442\u043d\u044b\u0445. \u0412 \u0440\u0430\u0437\u0434\u0435\u043b\u0435 \u0423\u0447\u0435\u0431\u043d\u044b\u0435 \u043c\u0430\u0442\u0435\u0440\u0438\u0430\u043b\u044b \u0434\u0430\u0435\u0442\u0441\u044f \u0438\u043d\u0444\u043e\u0440\u043c\u0430\u0446\u0438\u044f \u043e \u0442\u043e\u043c, \u043a\u0430\u043a \u0432 \u044d\u0441\u0442\u043e\u043d\u0441\u043a\u043e\u043c \u044f\u0437\u044b\u043a\u0435 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u044e\u0442\u0441\u044f \u0437\u043d\u0430\u043a\u0438 \u043f\u0440\u0435\u043f\u0438\u043d\u0430\u043d\u0438\u044f, \u0437\u0430\u043f\u0438\u0441\u044b\u0432\u0430\u044e\u0442\u0441\u044f \u0446\u0438\u0444\u0440\u044b, \u0434\u0430\u0442\u044b, \u0432\u0440\u0435\u043c\u044f \u0438 \u0442.\u043f. \u0412 \u0442\u0430\u0431\u043b\u0438\u0446\u0435 \u0421\u0442\u0440\u0430\u043d\u044b \u0438 \u043d\u0430\u0440\u043e\u0434\u044b \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043b\u0435\u043d\u044b \u043d\u0430\u0437\u0432\u0430\u043d\u0438\u044f \u0441\u0442\u0440\u0430\u043d, \u0436\u0438\u0432\u0443\u0449\u0438\u0445 \u0432 \u043d\u0438\u0445 \u043d\u0430\u0440\u043e\u0434\u043e\u0432 \u0438 \u044f\u0437\u044b\u043a\u043e\u0432, \u043d\u0430 \u043a\u043e\u0442\u043e\u0440\u044b\u0445 \u0433\u043e\u0432\u043e\u0440\u044f\u0442 \u044d\u0442\u0438 \u043d\u0430\u0440\u043e\u0434\u044b. \u0418\u0437 \u0413\u0440\u0430\u043c\u043c\u0430\u0442\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u0442\u0430\u0431\u043b\u0438\u0446 \u0432\u044b \u0443\u0437\u043d\u0430\u0435\u0442\u0435, \u043a\u0430\u043a \u0441\u043a\u043b\u043e\u043d\u044f\u044e\u0442\u0441\u044f \u0438 \u0441\u043f\u0440\u044f\u0433\u0430\u044e\u0442\u0441\u044f \u0441\u043b\u043e\u0432\u0430, \u043e\u0431\u0440\u0430\u0437\u0443\u044e\u0442\u0441\u044f \u0441\u0440\u0430\u0432\u043d\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u0435 \u0444\u043e\u0440\u043c\u044b. \u041a\u0440\u043e\u043c\u0435 \u0442\u043e\u0433\u043e, \u0443\u043a\u0430\u0437\u0430\u043d\u044b \u0441\u0432\u044f\u0437\u0438 \u043c\u0435\u0436\u0434\u0443 \u0444\u043e\u0440\u043c\u0430\u043c\u0438 \u0441\u043b\u043e\u0432. \u0420\u0430\u0437\u0434\u0435\u043b \u0423\u0447\u0438\u0442\u0435\u043b\u044e \u043f\u0440\u0435\u0434\u043d\u0430\u0437\u043d\u0430\u0447\u0435\u043d \u0434\u043b\u044f \u0443\u0447\u0438\u0442\u0435\u043b\u0435\u0439 \u044d\u0441\u0442\u043e\u043d\u0441\u043a\u043e\u0433\u043e \u044f\u0437\u044b\u043a\u0430. \u041c\u0430\u0442\u0435\u0440\u0438\u0430\u043b \u0441\u043e\u0434\u0435\u0440\u0436\u0438\u0442 \u043f\u0440\u0438\u043c\u0435\u0440\u044b \u0443\u043f\u0440\u0430\u0436\u043d\u0435\u043d\u0438\u0439, \u043d\u0430\u043f\u0440\u0430\u0432\u043b\u0435\u043d\u043d\u044b\u0445 \u043d\u0430 \u0444\u043e\u0440\u043c\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u0435 \u043d\u0430\u0432\u044b\u043a\u043e\u0432 \u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u044f \u0441\u043b\u043e\u0432\u0430\u0440\u0451\u043c \u0438 \u043d\u0430 \u0440\u0430\u0437\u0432\u0438\u0442\u0438\u0435 \u044f\u0437\u044b\u043a\u043e\u0432\u043e\u0439 \u043a\u043e\u043c\u043f\u0435\u0442\u0435\u043d\u0446\u0438\u0438 (\u0433\u0440\u0430\u043c\u043c\u0430\u0442\u0438\u043a\u0430, \u0441\u043b\u043e\u0432\u0430\u0440\u043d\u044b\u0439 \u0437\u0430\u043f\u0430\u0441, \u0443\u043f\u0440\u0430\u0432\u043b\u0435\u043d\u0438\u0435, \u0441\u043e\u0447\u0435\u0442\u0430\u0435\u043c\u043e\u0441\u0442\u044c, \u043f\u0440\u043e\u0438\u0437\u043d\u043e\u0448\u0435\u043d\u0438\u0435 \u0438 \u0434\u0440.).",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "807bc534-054d-5540-98ce-c1c140e86650",
-    "notes": [
-        "Abstract",
-        "Sisaldab ca 5000 eesti keele sagedasemat s\u00f5na koos kasutusn\u00e4idetega. S\u00f5nastik sisaldab infot m\u00e4rks\u00f5nade h\u00e4\u00e4lduse, vormimoodustuse, s\u00f5namoodustuse, t\u00e4henduste, rektsiooni, kollokatsioonide, s\u00fcnon\u00fc\u00fcmine, anton\u00fc\u00fcmide ja paron\u00fc\u00fcmide kohta. Lisaks on ka illustreerivad pildid, \u00f5ppelehed, pildilehed ning lisad (\u201eMaad ja rahavad\u201c ja \u201eEesti keele grammatika tabelid\u201c). Elektroonilises versioonis on ka audiofailid. M\u00f5eldud eesk\u00e4tt A2- ja B1-keeleoskustasemega eesti keele \u00f5ppijatele.\n\nVt ka:\nKallas, Jelena; Koppel, Kristina; Tuulik, Maria (2014). Eesti keele p\u00f5his\u00f5navara s\u00f5nastik. Oma Keel, 2, 87\u221289.\nKallas, Jelena; Tuulik, Maria (2011). Eesti keele p\u00f5his\u00f5navara s\u00f5nastik: ajalooline kontekst ja koostamisp\u00f5him\u00f5tted. Eesti Rakenduslingvistika \u00dchingu aastaraamat, 7, 59\u221275.\nBasic Estonian Dictionary: the first Monolingual L2 learner\u2019s Dictionary of Estonian. In: Andrea Abel, Chiara Vettori, Natascia Ralli (Ed.). Proceedings of the XVI EURALEX Internatinoal Congress: The User in Focus, 15-19 July 2014, Bolzano/Bozen (1109\u22121119). Bolzano/Bozen: European Academy.",
-        "Abstract",
-        "The dictionary includes 5000 important Estonian words explained in a simple language.\n\nThe dictionary is an aid to correct Estonian speaking and writing, usable from beginner to advanced levels (levels \u04102 and B1). The User guide introduces how the information is presented in the dictionary. There are also some auxiliary materials to help you. Picture pages show clothing, fruits, vegetables, vehicles, animals, etc. Study pages introduce Estonian punctuation and how to write numbers, dates, time, etc. Countries and peoples is a table presenting a selection of countries with the names of major inhabiting peoples and of the languages they speak. Grammar tables help you with word conjugation and declination as well as with degrees of comparison. In addition it is shown how most of the whole inflectional paradigm can be produced knowing just a few forms. For teacher offers ideas on what kind of exercises can be made in order to develop students\u2019 linguistic and lexicographic competence.\n\nBasic Estonian Dictionary: the first Monolingual L2 learner\u2019s Dictionary of Estonian. In: Andrea Abel, Chiara Vettori, Natascia Ralli (Ed.). Proceedings of the XVI EURALEX Internatinoal Congress: The User in Focus, 15-19 July 2014, Bolzano/Bozen (1109\u22121119). Bolzano/Bozen: European Academy.",
-        "Abstract",
-        "\u0412 \u0441\u043b\u043e\u0432\u0430\u0440\u044c \u0432\u043a\u043b\u044e\u0447\u0435\u043d\u043e 5000 \u0441\u043b\u043e\u0432, \u0441\u043e\u0441\u0442\u0430\u0432\u043b\u044f\u044e\u0449\u0438\u0435 \u043e\u0441\u043d\u043e\u0432\u043d\u043e\u0439 \u0441\u043b\u043e\u0432\u0430\u0440\u043d\u044b\u0439 \u0444\u043e\u043d\u0434 \u044d\u0441\u0442\u043e\u043d\u0441\u043a\u043e\u0433\u043e \u044f\u0437\u044b\u043a\u0430.\n\u0421\u043b\u043e\u0432\u0430\u0440\u044c \u043f\u0440\u0435\u0434\u043d\u0430\u0437\u043d\u0430\u0447\u0435\u043d \u0434\u043b\u044f \u0442\u0435\u0445, \u043a\u0442\u043e \u0438\u0437\u0443\u0447\u0430\u0435\u0442 \u044d\u0441\u0442\u043e\u043d\u0441\u043a\u0438\u0439 \u044f\u0437\u044b\u043a \u043d\u0430 \u043d\u0430\u0447\u0430\u043b\u044c\u043d\u043e\u043c \u0438 \u0441\u0440\u0435\u0434\u043d\u0435\u043c \u0443\u0440\u043e\u0432\u043d\u0435 (\u0443\u0440\u043e\u0432\u043d\u0438 \u04102 \u0438 B1). \u0412 \u0440\u0430\u0437\u0434\u0435\u043b\u0435 \u041a\u0430\u043a \u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u044c\u0441\u044f \u0441\u043b\u043e\u0432\u0430\u0440\u0435\u043c \u043e\u0431\u044a\u044f\u0441\u043d\u044f\u0435\u0442\u0441\u044f, \u043a\u0430\u043a \u0432 \u043d\u0435\u043c \u043f\u043e\u0434\u0430\u0435\u0442\u0441\u044f \u0438\u043d\u0444\u043e\u0440\u043c\u0430\u0446\u0438\u044f.\n\u0412 \u043f\u043e\u043c\u043e\u0449\u044c \u0442\u0435\u043c, \u043a\u0442\u043e \u0438\u0437\u0443\u0447\u0430\u0435\u0442 \u044d\u0441\u0442\u043e\u043d\u0441\u043a\u0438\u0439 \u044f\u0437\u044b\u043a, \u043d\u0430 \u0441\u0430\u0439\u0442\u0435 \u0434\u043e\u0441\u0442\u0443\u043f\u043d\u044b \u0442\u0430\u043a\u0436\u0435 \u0434\u043e\u043f\u043e\u043b\u043d\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u0435 \u043c\u0430\u0442\u0435\u0440\u0438\u0430\u043b\u044b. \u0412 \u0440\u0430\u0437\u0434\u0435\u043b\u0435 \u0418\u043b\u043b\u044e\u0441\u0442\u0440\u0430\u0446\u0438\u0438 \u043c\u043e\u0436\u043d\u043e \u0443\u0432\u0438\u0434\u0435\u0442\u044c \u0438\u0437\u043e\u0431\u0440\u0430\u0436\u0435\u043d\u0438\u044f, \u043d\u0430\u043f\u0440\u0438\u043c\u0435\u0440, \u043f\u0440\u0435\u0434\u043c\u0435\u0442\u043e\u0432 \u043e\u0434\u0435\u0436\u0434\u044b, \u0444\u0440\u0443\u043a\u0442\u043e\u0432, \u043e\u0432\u043e\u0449\u0435\u0439, \u0442\u0440\u0430\u043d\u0441\u043f\u043e\u0440\u0442\u043d\u044b\u0445 \u0441\u0440\u0435\u0434\u0441\u0442\u0432 \u0438 \u0436\u0438\u0432\u043e\u0442\u043d\u044b\u0445. \u0412 \u0440\u0430\u0437\u0434\u0435\u043b\u0435 \u0423\u0447\u0435\u0431\u043d\u044b\u0435 \u043c\u0430\u0442\u0435\u0440\u0438\u0430\u043b\u044b \u0434\u0430\u0435\u0442\u0441\u044f \u0438\u043d\u0444\u043e\u0440\u043c\u0430\u0446\u0438\u044f \u043e \u0442\u043e\u043c, \u043a\u0430\u043a \u0432 \u044d\u0441\u0442\u043e\u043d\u0441\u043a\u043e\u043c \u044f\u0437\u044b\u043a\u0435 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u044e\u0442\u0441\u044f \u0437\u043d\u0430\u043a\u0438 \u043f\u0440\u0435\u043f\u0438\u043d\u0430\u043d\u0438\u044f, \u0437\u0430\u043f\u0438\u0441\u044b\u0432\u0430\u044e\u0442\u0441\u044f \u0446\u0438\u0444\u0440\u044b, \u0434\u0430\u0442\u044b, \u0432\u0440\u0435\u043c\u044f \u0438 \u0442.\u043f. \u0412 \u0442\u0430\u0431\u043b\u0438\u0446\u0435 \u0421\u0442\u0440\u0430\u043d\u044b \u0438 \u043d\u0430\u0440\u043e\u0434\u044b \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043b\u0435\u043d\u044b \u043d\u0430\u0437\u0432\u0430\u043d\u0438\u044f \u0441\u0442\u0440\u0430\u043d, \u0436\u0438\u0432\u0443\u0449\u0438\u0445 \u0432 \u043d\u0438\u0445 \u043d\u0430\u0440\u043e\u0434\u043e\u0432 \u0438 \u044f\u0437\u044b\u043a\u043e\u0432, \u043d\u0430 \u043a\u043e\u0442\u043e\u0440\u044b\u0445 \u0433\u043e\u0432\u043e\u0440\u044f\u0442 \u044d\u0442\u0438 \u043d\u0430\u0440\u043e\u0434\u044b. \u0418\u0437 \u0413\u0440\u0430\u043c\u043c\u0430\u0442\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u0442\u0430\u0431\u043b\u0438\u0446 \u0432\u044b \u0443\u0437\u043d\u0430\u0435\u0442\u0435, \u043a\u0430\u043a \u0441\u043a\u043b\u043e\u043d\u044f\u044e\u0442\u0441\u044f \u0438 \u0441\u043f\u0440\u044f\u0433\u0430\u044e\u0442\u0441\u044f \u0441\u043b\u043e\u0432\u0430, \u043e\u0431\u0440\u0430\u0437\u0443\u044e\u0442\u0441\u044f \u0441\u0440\u0430\u0432\u043d\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u0435 \u0444\u043e\u0440\u043c\u044b. \u041a\u0440\u043e\u043c\u0435 \u0442\u043e\u0433\u043e, \u0443\u043a\u0430\u0437\u0430\u043d\u044b \u0441\u0432\u044f\u0437\u0438 \u043c\u0435\u0436\u0434\u0443 \u0444\u043e\u0440\u043c\u0430\u043c\u0438 \u0441\u043b\u043e\u0432. \u0420\u0430\u0437\u0434\u0435\u043b \u0423\u0447\u0438\u0442\u0435\u043b\u044e \u043f\u0440\u0435\u0434\u043d\u0430\u0437\u043d\u0430\u0447\u0435\u043d \u0434\u043b\u044f \u0443\u0447\u0438\u0442\u0435\u043b\u0435\u0439 \u044d\u0441\u0442\u043e\u043d\u0441\u043a\u043e\u0433\u043e \u044f\u0437\u044b\u043a\u0430. \u041c\u0430\u0442\u0435\u0440\u0438\u0430\u043b \u0441\u043e\u0434\u0435\u0440\u0436\u0438\u0442 \u043f\u0440\u0438\u043c\u0435\u0440\u044b \u0443\u043f\u0440\u0430\u0436\u043d\u0435\u043d\u0438\u0439, \u043d\u0430\u043f\u0440\u0430\u0432\u043b\u0435\u043d\u043d\u044b\u0445 \u043d\u0430 \u0444\u043e\u0440\u043c\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u0435 \u043d\u0430\u0432\u044b\u043a\u043e\u0432 \u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u044f \u0441\u043b\u043e\u0432\u0430\u0440\u0451\u043c \u0438 \u043d\u0430 \u0440\u0430\u0437\u0432\u0438\u0442\u0438\u0435 \u044f\u0437\u044b\u043a\u043e\u0432\u043e\u0439 \u043a\u043e\u043c\u043f\u0435\u0442\u0435\u043d\u0446\u0438\u0438 (\u0433\u0440\u0430\u043c\u043c\u0430\u0442\u0438\u043a\u0430, \u0441\u043b\u043e\u0432\u0430\u0440\u043d\u044b\u0439 \u0437\u0430\u043f\u0430\u0441, \u0443\u043f\u0440\u0430\u0432\u043b\u0435\u043d\u0438\u0435, \u0441\u043e\u0447\u0435\u0442\u0430\u0435\u043c\u043e\u0441\u0442\u044c, \u043f\u0440\u043e\u0438\u0437\u043d\u043e\u0448\u0435\u043d\u0438\u0435 \u0438 \u0434\u0440.)."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:8922496"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele p\u00f5his\u00f5navara s\u00f5nastik",
-        "The Basic Estonian Dictionary",
-        "\u0411\u0430\u0437\u043e\u0432\u044b\u0439 \u0441\u043b\u043e\u0432\u0430\u0440\u044c \u044d\u0441\u0442\u043e\u043d\u0441\u043a\u043e\u0433\u043e \u044f\u0437\u044b\u043a\u0430"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8087dddb-b572-5e2f-bb36-19f90a920d4b.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8087dddb-b572-5e2f-bb36-19f90a920d4b.json
deleted file mode 100644
index 2f16226e..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8087dddb-b572-5e2f-bb36-19f90a920d4b.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00194L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17979315",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17979315"
-    ],
-    "PublicationTimestamp": "2019-01-10T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laur, Sven"
-    ],
-    "fulltext": "oai:oai.datacite.org:17979315;2019-04-17T17:27:32Z;ESTDOI;ESTDOI.KEEL;Faktituletaja visualiseerimisliides;Laur, Sven;Center of Estonian Language Resources;2019;Issued: 2019-01-10;Updated: 2019-01-10;doi:10.15155/1-00-0000-0000-0000-00194L;Abstract;Faktituletaja visualiseerimisiidese kasutamiseks k\u00e4ivatada fail \"startserver.sh\" ning avada brauseriga \"index.html\" fail. Lisaks tuleb seadistada pakendi tee \"settings.py\" failis, mis on kataloog, kuhu liides lahti pakkida. Pakendis on kaasas ka m\u00f5ned demomudelid, mida saab visualiseerijaga uurida. ",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8087dddb-b572-5e2f-bb36-19f90a920d4b",
-    "notes": [
-        "Abstract",
-        "Faktituletaja visualiseerimisiidese kasutamiseks k\u00e4ivatada fail \"startserver.sh\" ning avada brauseriga \"index.html\" fail. Lisaks tuleb seadistada pakendi tee \"settings.py\" failis, mis on kataloog, kuhu liides lahti pakkida. Pakendis on kaasas ka m\u00f5ned demomudelid, mida saab visualiseerijaga uurida. "
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17979315"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Faktituletaja visualiseerimisliides"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/80dd79bc-df4c-5254-8cdc-6baba51308fc.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/80dd79bc-df4c-5254-8cdc-6baba51308fc.json
deleted file mode 100644
index 30c4a83b..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/80dd79bc-df4c-5254-8cdc-6baba51308fc.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00193L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17979314",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17979314"
-    ],
-    "PublicationTimestamp": "2019-01-10T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laur, Sven"
-    ],
-    "fulltext": "oai:oai.datacite.org:17979314;2019-01-10T12:22:13Z;ESTDOI;ESTDOI.KEEL;Faktituletaja visualiseerimisliides;Laur, Sven;Center of Estonian Language Resources;2019;Issued: 2019-01-10;Updated: 2019-01-10;doi:10.15155/1-00-0000-0000-0000-00193L;Abstract;Faktituletaja visualiseerimisiidese kasutamiseks k\u00e4ivatada fail \"startserver.sh\" ning avada brauseriga \"index.html\" fail. Lisaks tuleb seadistada pakendi tee \"settings.py\" failis, mis on kataloog, kuhu liides lahti pakkida. Pakendis on kaasas ka m\u00f5ned demomudelid, mida saab visualiseerijaga uurida. ",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "80dd79bc-df4c-5254-8cdc-6baba51308fc",
-    "notes": [
-        "Abstract",
-        "Faktituletaja visualiseerimisiidese kasutamiseks k\u00e4ivatada fail \"startserver.sh\" ning avada brauseriga \"index.html\" fail. Lisaks tuleb seadistada pakendi tee \"settings.py\" failis, mis on kataloog, kuhu liides lahti pakkida. Pakendis on kaasas ka m\u00f5ned demomudelid, mida saab visualiseerijaga uurida. "
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17979314"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Faktituletaja visualiseerimisliides"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/81a8a9cb-c859-57a5-be6b-09acb104d4a1.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/81a8a9cb-c859-57a5-be6b-09acb104d4a1.json
deleted file mode 100644
index 435804e5..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/81a8a9cb-c859-57a5-be6b-09acb104d4a1.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-00024L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5755422",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5755422"
-    ],
-    "PublicationTimestamp": "2015-05-21T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Alum\u00e4e, Tanel"
-    ],
-    "fulltext": "oai:oai.datacite.org:5755422;2019-04-12T20:02:04Z;ESTDOI;ESTDOI.KEEL;Arvutaja;Alum\u00e4e, Tanel;Center of Estonian Language Resources;2014;Issued: 2014-12-30;Updated: 2015-05-21;doi:10.15155/9-00-0000-0000-0000-00024L;Abstract;Speech-based calculator/assistant for Android",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "81a8a9cb-c859-57a5-be6b-09acb104d4a1",
-    "notes": [
-        "Abstract",
-        "Speech-based calculator/assistant for Android"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5755422"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Arvutaja"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8265c0a1-9fb1-5766-b251-181e8f1be3c1.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8265c0a1-9fb1-5766-b251-181e8f1be3c1.json
deleted file mode 100644
index de0946ad..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8265c0a1-9fb1-5766-b251-181e8f1be3c1.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0007AL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5756896",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5756896"
-    ],
-    "PublicationTimestamp": "2015-03-02T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:5756896;2019-04-21T05:31:08Z;ESTDOI;ESTDOI.KEEL;Eesti keele segakorpus: Seadused;Corpus of Estonian law texts;Muischnek, Kadri;Center of Estonian Language Resources;2013;Issued: 2013-01-07;Updated: 2015-03-02;doi:10.15155/1-00-0000-0000-0000-0007AL;Abstract;Eesti ja Euroopa seadusetekstide korpus. TEI P5 XML m\u00e4rgendus, UTF8 kodeering.;Abstract;Corpus of law texts in Estonian, contains Estonian legislation and European legislation in Estonian. 11 million words. \nMarkup: TEI P5 XML\nEncoding: UTF8",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8265c0a1-9fb1-5766-b251-181e8f1be3c1",
-    "notes": [
-        "Abstract",
-        "Eesti ja Euroopa seadusetekstide korpus. TEI P5 XML m\u00e4rgendus, UTF8 kodeering.",
-        "Abstract",
-        "Corpus of law texts in Estonian, contains Estonian legislation and European legislation in Estonian. 11 million words. \nMarkup: TEI P5 XML\nEncoding: UTF8"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5756896"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele segakorpus: Seadused",
-        "Corpus of Estonian law texts"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/82a59d2f-cbcf-5dce-a9cd-456a00c58f71.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/82a59d2f-cbcf-5dce-a9cd-456a00c58f71.json
deleted file mode 100644
index 481fff94..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/82a59d2f-cbcf-5dce-a9cd-456a00c58f71.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-000A5L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17968030",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17968030"
-    ],
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Ross, Peeter",
-        "Valdre, Eola"
-    ],
-    "fulltext": "oai:oai.datacite.org:17968030;2019-04-22T07:31:56Z;ESTDOI;ESTDOI.KEEL;Meditsiinikeele korpus;Ross, Peeter;Valdre, Eola;Center of Estonian Language Resources;2019;Issued: 2019-01-08;Updated: 2019-01-08;doi:10.15155/9-00-0000-0000-0000-000A5L;Abstract;Meditsiinikeele korpuse koostamiseks on kasutatud autentseid isikustamata terviseandmeid, milleks on taotletud eetikaluba (Tallinna Meditsiiniuuringute Eetikakomitee otsuse nr 2169). Tuleb arvestada, et ka isikustamata terviseandmed on eriline materjal, sh ka tervishoiuturu konkurentsi tingimustes. Tegu on \u00fche tervishoiuasutuse andmetega, mis ei pruugi adekvaatselt kajastada ega olla automaatselt \u00fclekantavad k\u00f5igile teistele tervishoiuasutustele, ka ei saa nende alusel teha j\u00e4reldusi tervishoiuteenuse kui terviku kohta. K\u00f5nelause projektiga seotud eetikaloa \u00fcks osapool on olnud AS Ida-Tallinna Keskhaigla, kelle radioloogiainfos\u00fcsteemist on isikustamata p\u00e4ringuga saadud meditsiinikeele korpuse aluseks olnud algandmed. Seet\u00f5ttu AS Ida-Tallinna Keskhaigla \u00f5igus piirata nimetatud andmete kasutamist muudel eesm\u00e4rkidel kui k\u00e4esoleva projektiga seotud eetikaloaga kaetud eesm\u00e4rgid. Sel p\u00f5hjusel eeldab ka mitte\u00e4rilistel eesm\u00e4rkidel meditsiinikeele korpuse kasutamine uute eesm\u00e4rkide korral uue eetikaloa taotlemist v\u00f5i eelmise eetikaloa laiendamist, mida saab teha eetikaloas AS Ida-Tallinna Keskhaiglat esindava dr P. Rossi kaudu (peeter.ross@ttu.ee ).",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "82a59d2f-cbcf-5dce-a9cd-456a00c58f71",
-    "notes": [
-        "Abstract",
-        "Meditsiinikeele korpuse koostamiseks on kasutatud autentseid isikustamata terviseandmeid, milleks on taotletud eetikaluba (Tallinna Meditsiiniuuringute Eetikakomitee otsuse nr 2169). Tuleb arvestada, et ka isikustamata terviseandmed on eriline materjal, sh ka tervishoiuturu konkurentsi tingimustes. Tegu on \u00fche tervishoiuasutuse andmetega, mis ei pruugi adekvaatselt kajastada ega olla automaatselt \u00fclekantavad k\u00f5igile teistele tervishoiuasutustele, ka ei saa nende alusel teha j\u00e4reldusi tervishoiuteenuse kui terviku kohta. K\u00f5nelause projektiga seotud eetikaloa \u00fcks osapool on olnud AS Ida-Tallinna Keskhaigla, kelle radioloogiainfos\u00fcsteemist on isikustamata p\u00e4ringuga saadud meditsiinikeele korpuse aluseks olnud algandmed. Seet\u00f5ttu AS Ida-Tallinna Keskhaigla \u00f5igus piirata nimetatud andmete kasutamist muudel eesm\u00e4rkidel kui k\u00e4esoleva projektiga seotud eetikaloaga kaetud eesm\u00e4rgid. Sel p\u00f5hjusel eeldab ka mitte\u00e4rilistel eesm\u00e4rkidel meditsiinikeele korpuse kasutamine uute eesm\u00e4rkide korral uue eetikaloa taotlemist v\u00f5i eelmise eetikaloa laiendamist, mida saab teha eetikaloas AS Ida-Tallinna Keskhaiglat esindava dr P. Rossi kaudu (peeter.ross@ttu.ee )."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17968030"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Meditsiinikeele korpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8433294e-c3a2-51fc-bbbe-9b29a02737ad.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8433294e-c3a2-51fc-bbbe-9b29a02737ad.json
deleted file mode 100644
index fe5a2358..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8433294e-c3a2-51fc-bbbe-9b29a02737ad.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-0001AL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5757342",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5757342"
-    ],
-    "PublicationTimestamp": "2017-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Pajupuu, Hille"
-    ],
-    "fulltext": "oai:oai.datacite.org:5757342;2019-04-21T03:32:49Z;ESTDOI;ESTDOI.KEEL;Eesti emotsionaalse k\u00f5ne korpus;Estonian Emotional Speech Corpus;Pajupuu, Hille;Center of Estonian Language Resources;2012;Issued: 2012-06-12;Updated: 2017-02-15;doi:10.15155/3-00-0000-0000-0000-0001AL;Abstract;Korpus sisaldab 1234 eestikeelset  viha-, r\u00f5\u00f5mu- ja kurbuse emotsiooniga lauset ning neutraalset lauset.\n        Naish\u00e4\u00e4l,  44.1 KHz, 16Bit, Mono;\n        wav, textgrid: h\u00e4\u00e4likud, s\u00f5nad, laused.\n        Lausete heli ja teksti saab alla laadida ja salvestada. ;Abstract;The corpus contains 1,234 Estonian sentences that\n        express anger, joy and sadness, or are neutral.\n        Female voice,  44.1 KHz, 16Bit, Mono;\n        wav, textgrid: phonemes, words, sentences.\n        The audio-recordings and text of sentences can be downloaded and saved.\n      ",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8433294e-c3a2-51fc-bbbe-9b29a02737ad",
-    "notes": [
-        "Abstract",
-        "Korpus sisaldab 1234 eestikeelset  viha-, r\u00f5\u00f5mu- ja kurbuse emotsiooniga lauset ning neutraalset lauset.\n        Naish\u00e4\u00e4l,  44.1 KHz, 16Bit, Mono;\n        wav, textgrid: h\u00e4\u00e4likud, s\u00f5nad, laused.\n        Lausete heli ja teksti saab alla laadida ja salvestada. ",
-        "Abstract",
-        "The corpus contains 1,234 Estonian sentences that\n        express anger, joy and sadness, or are neutral.\n        Female voice,  44.1 KHz, 16Bit, Mono;\n        wav, textgrid: phonemes, words, sentences.\n        The audio-recordings and text of sentences can be downloaded and saved.\n      "
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5757342"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti emotsionaalse k\u00f5ne korpus",
-        "Estonian Emotional Speech Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/85010ad6-255d-544e-95c8-9d6ddba616b1.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/85010ad6-255d-544e-95c8-9d6ddba616b1.json
deleted file mode 100644
index 3b4365e2..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/85010ad6-255d-544e-95c8-9d6ddba616b1.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05BDBL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9474541",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9474541"
-    ],
-    "PublicationTimestamp": "2016-11-09T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:9474541;2019-02-17T15:02:31Z;ESTDOI;ESTDOI.KEEL;Hariduse ja kasvatuse s\u00f5naraamat;Hein, Indrek;Center of Estonian Language Resources;2016;Issued: 2016-11-09;Updated: 2016-11-09;doi:10.15155/3-00-0000-0000-0000-05BDBL;Abstract;Sisaldab 4850 terminit mitmesugustelt hariduse ja kasvatuse aladelt: kasvatus ja areng, alusharidus, p\u00f5hi- ja keskharidus, kutse- ja k\u00f5rgharidus, andragoogika, eripedagoogika jne. Igale eesti terminile on antud inglise, saksa, soome ja vene vaste ning enamasti ka seletus.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "85010ad6-255d-544e-95c8-9d6ddba616b1",
-    "notes": [
-        "Abstract",
-        "Sisaldab 4850 terminit mitmesugustelt hariduse ja kasvatuse aladelt: kasvatus ja areng, alusharidus, p\u00f5hi- ja keskharidus, kutse- ja k\u00f5rgharidus, andragoogika, eripedagoogika jne. Igale eesti terminile on antud inglise, saksa, soome ja vene vaste ning enamasti ka seletus."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9474541"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Hariduse ja kasvatuse s\u00f5naraamat"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/864b080e-a1ec-5d58-9ab5-27d05e598113.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/864b080e-a1ec-5d58-9ab5-27d05e598113.json
deleted file mode 100644
index fe2d1c32..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/864b080e-a1ec-5d58-9ab5-27d05e598113.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05BE2L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9474548",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9474548"
-    ],
-    "PublicationTimestamp": "2017-03-03T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:9474548;2019-04-17T17:26:23Z;ESTDOI;ESTDOI.KEEL;Inglise-eesti meres\u00f5naraamat;The English-Estonian Maritime Dictionary;Hein, Indrek;Center of Estonian Language Resources;2016;Issued: 2016-11-09;Updated: 2017-03-03;doi:10.15155/3-00-0000-0000-0000-05BE2L;Abstract;Sisaldab \u00fcle 30 000 m\u00e4rks\u00f5na. Peale merenduslike tavaterminite leiab s\u00f5naraamatust ka purjelaevu, puulaevu, merekaubandust, mere\u00f5igust, merekindlustust, konteinervedusid, kalandust, s\u00f5jalaevastikku, raadiolokatsiooni, h\u00fcdromehaanikat, okeanograafiat, purjesporti jms puutuvaid s\u00f5nu.;Abstract;Over 30,000 entry words. Apart from common nautical terms there are terms concerning sailing ships, wooden boats, sea trade, maritime law, marine insurance, container transport, fishery, navy, radiolocation, hydromechanics, oceanography, sailing etc.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "864b080e-a1ec-5d58-9ab5-27d05e598113",
-    "notes": [
-        "Abstract",
-        "Sisaldab \u00fcle 30 000 m\u00e4rks\u00f5na. Peale merenduslike tavaterminite leiab s\u00f5naraamatust ka purjelaevu, puulaevu, merekaubandust, mere\u00f5igust, merekindlustust, konteinervedusid, kalandust, s\u00f5jalaevastikku, raadiolokatsiooni, h\u00fcdromehaanikat, okeanograafiat, purjesporti jms puutuvaid s\u00f5nu.",
-        "Abstract",
-        "Over 30,000 entry words. Apart from common nautical terms there are terms concerning sailing ships, wooden boats, sea trade, maritime law, marine insurance, container transport, fishery, navy, radiolocation, hydromechanics, oceanography, sailing etc."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9474548"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Inglise-eesti meres\u00f5naraamat",
-        "The English-Estonian Maritime Dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/87e3ebad-e8a2-548f-8551-02bb8412d981.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/87e3ebad-e8a2-548f-8551-02bb8412d981.json
deleted file mode 100644
index e089502d..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/87e3ebad-e8a2-548f-8551-02bb8412d981.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-00086L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10978478",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10978478"
-    ],
-    "PublicationTimestamp": "2017-07-12T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "J\u00e4rv, Risto",
-        "Tuisk, Astrid"
-    ],
-    "fulltext": "oai:oai.datacite.org:10978478;2019-04-17T17:26:45Z;ESTDOI;ESTDOI.KEEL;1001 lastem\u00e4ngu aastast 1935;1,001 children\u2019s games from the year 1935;J\u00e4rv, Risto;Tuisk, Astrid;Center of Estonian Language Resources;2017;Issued: 2017-05-05;Updated: 2017-07-12;doi:10.15155/9-00-0000-0000-0000-00086L;Abstract;Andmebaasis olevate lastem\u00e4ngude kirjeldused (kirjalikud tekstid) p\u00e4rinevad Eesti Rahvaluule Arhiivi kogudest. Suurem osa veebivalimiku m\u00e4ngukirjeldustest p\u00e4rineb lastem\u00e4ngude \u00fclemaalise kogumiskonkursi (1934\u20131935) saadetistest. Kogumisv\u00f5istlus korraldati koost\u00f6\u00f6s Haridusministeeriumi koolivalitsusega, m\u00e4ngukirjeldused ja joonistused on kooli\u00f5pilastelt. M\u00e4nge on valitud k\u00f5ikidest endistest Eesti maakondadest. Valimik sisaldab p\u00f5hiosa omaaegsest populaarsest m\u00e4nguvaramust 5\u201315-aastaste laste seas, tuues \u00e4ra ka unikaalsemaid ning ainukordsemaid m\u00e4nge. Samuti leiab kogumikust nii praeguseni m\u00e4ngitavaid kui juba unustuseh\u00f5lma vajunud m\u00e4ngude kirjeldusi. Tekste on kohendatud loetavamaks, kuid siiski sisaldavad need ka ajastuomast, paiguti t\u00e4nap\u00e4eva ortograafiareeglitele mittevastavat kirjapilti. \u00dchest ja samast m\u00e4ngust v\u00f5ib olla esitatud mitu eri varianti, mis aitavad paremini m\u00f5ista m\u00e4ngureegleid ning suunavad t\u00e4helepanu eri piirkondades kasutusel olnud erisugustele m\u00e4ngunimetustele. ;Abstract;The databases consists of children's games' descriptions found in Estonian Folklore Archives collections. Most of the available game descriptions come from the materials of the nationwide children's games collecting competition of 1934-1935. Game descriptions and drawings were collected from schoolchildren. The competition was organized in co-operation with the school administration of the Ministry of Education. The games were selected in a way that all former counties of Estonia are represented. The sample contains the majority of the popular games at that time for children age 5-15, presenting also the most unique ones. Furthermore, you will find descriptions of games that are played to this day and the forgotten ones. The texts are modified to be more readable, but they still include spellings that are old-fashioned and do not comply with the contemporary orthographic rules. One game can be presented in several different variants that help to understand its rules better.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "87e3ebad-e8a2-548f-8551-02bb8412d981",
-    "notes": [
-        "Abstract",
-        "Andmebaasis olevate lastem\u00e4ngude kirjeldused (kirjalikud tekstid) p\u00e4rinevad Eesti Rahvaluule Arhiivi kogudest. Suurem osa veebivalimiku m\u00e4ngukirjeldustest p\u00e4rineb lastem\u00e4ngude \u00fclemaalise kogumiskonkursi (1934\u20131935) saadetistest. Kogumisv\u00f5istlus korraldati koost\u00f6\u00f6s Haridusministeeriumi koolivalitsusega, m\u00e4ngukirjeldused ja joonistused on kooli\u00f5pilastelt. M\u00e4nge on valitud k\u00f5ikidest endistest Eesti maakondadest. Valimik sisaldab p\u00f5hiosa omaaegsest populaarsest m\u00e4nguvaramust 5\u201315-aastaste laste seas, tuues \u00e4ra ka unikaalsemaid ning ainukordsemaid m\u00e4nge. Samuti leiab kogumikust nii praeguseni m\u00e4ngitavaid kui juba unustuseh\u00f5lma vajunud m\u00e4ngude kirjeldusi. Tekste on kohendatud loetavamaks, kuid siiski sisaldavad need ka ajastuomast, paiguti t\u00e4nap\u00e4eva ortograafiareeglitele mittevastavat kirjapilti. \u00dchest ja samast m\u00e4ngust v\u00f5ib olla esitatud mitu eri varianti, mis aitavad paremini m\u00f5ista m\u00e4ngureegleid ning suunavad t\u00e4helepanu eri piirkondades kasutusel olnud erisugustele m\u00e4ngunimetustele. ",
-        "Abstract",
-        "The databases consists of children's games' descriptions found in Estonian Folklore Archives collections. Most of the available game descriptions come from the materials of the nationwide children's games collecting competition of 1934-1935. Game descriptions and drawings were collected from schoolchildren. The competition was organized in co-operation with the school administration of the Ministry of Education. The games were selected in a way that all former counties of Estonia are represented. The sample contains the majority of the popular games at that time for children age 5-15, presenting also the most unique ones. Furthermore, you will find descriptions of games that are played to this day and the forgotten ones. The texts are modified to be more readable, but they still include spellings that are old-fashioned and do not comply with the contemporary orthographic rules. One game can be presented in several different variants that help to understand its rules better."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10978478"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "1001 lastem\u00e4ngu aastast 1935",
-        "1,001 children\u2019s games from the year 1935"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8819159c-2362-55b9-b9bd-ced2facf1dd5.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8819159c-2362-55b9-b9bd-ced2facf1dd5.json
deleted file mode 100644
index 017814a9..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8819159c-2362-55b9-b9bd-ced2facf1dd5.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-071E8L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14560061",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14560061"
-    ],
-    "PublicationTimestamp": "2018-03-26T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Koppel, Kristina",
-        "Kallas, Jelena"
-    ],
-    "fulltext": "oai:oai.datacite.org:14560061;2019-04-19T05:31:26Z;ESTDOI;ESTDOI.KEEL;Eesti keele A1-C1 \u00f5pikute korpus 2018;Estonian Coursebook Corpus 2018;Kallas, Jelena;Koppel, Kristina;Center of Estonian Language Resources;2018;Issued: 2018-03-26;Updated: 2018-03-26;doi:10.15155/3-00-0000-0000-0000-071E8L;Abstract;Korpus sisaldab A1, A2, B1, B2 ja C1 keeleoskustasemega eesti keele \u00f5ppijatele suunatud \u00f5pikute tekstidest eraldatud t\u00e4islauseid. Korpuses on m\u00e4rgendatud tekstistruktuuri \u00fcksused lause <sentence> ja osalause <clause>. K\u00f5ik korpuse laused on keeletaseme piirides unikaalsed.\nKorpuse aluseks on Eesti keele A1-C1 \u00f5pikute korpus 2017, mis koosnes ca 200 000 s\u00f5nest ja ca 24 000 lausest. Eesti keele A1-C1 \u00f5pikute korpuse 2017 sisust ekstraheeritud t\u00e4islausetest loodigi Eesti keele A1-C1 \u00f5pikute korpus 2018, millega kaasnes k\u00e4sitsi kontroll (sisse j\u00e4eti semantiliselt terviklikud laused, kontekstisidusad ja valesti tuvastatud laused j\u00e4eti v\u00e4lja). \nKorpuses on kaheksa \u00f5pikut:\nPesti, M., Ahi, H. (2015). E nagu Eesti: eesti keele \u00f5pik algajatele. Tallinn: Kiri-Mari Kirjastus.\nKitsnik, M., Kingisepp, L. (2002). Avatud uksed: eesti keele \u00f5ppekomplekt kesk- ja k\u00f5rgtasemele: \u00f5pperaamat. Tallinn: TEA Kirjastus.\nKitsnik, M. (2012). Eesti keele \u00f5pik: B1, B2. Tallinn: M. Kitsnik.\nPesti, M., Ahi, H. (2015). Eesti keele \u00f5pik A1. Tallinn: Justiitsministeerium.\nPesti, M., Ahi, H. (2012). Eesti keele \u00f5pik A2. Tallinn: M. Pesti.\nPesti, M., Ahi, H. (2015). Eesti keele \u00f5pik B1. Tallinn: Justiitsministeerium.\nSooneste, M. (2007). Eesti keele \u00f5pik: vene \u00f5ppekeelega g\u00fcmnaasium: kesk- ja k\u00f5rgtase. Tallinn: Varrak.\nRammo, S., Teral, M., Klaas-Lang, B., Allik, M. (2012). Keel selgeks!: eesti keele \u00f5pik t\u00e4iskasvanutele. Tallinn: Avita.\nSeitse esimest \u00f5pikut digitaliseeriti Eesti Rahvusraamatkogu digitaliseerimiskeskus. Sirje Rammo jt (2012) \u00f5pikust on kasutatud k\u00e4sikirja doc-faile. \nKorpus on UTF-8 kodeeringus. Korpus on lemmatiseeritud, m\u00e4rgendatud ja \u00fchestatud anal\u00fcsaatori EstNLTK abil.\nKorpus loodi Eesti Keele Instituudi ja Lexical Computing Ltd. koost\u00f6\u00f6s.\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8819159c-2362-55b9-b9bd-ced2facf1dd5",
-    "notes": [
-        "Abstract",
-        "Korpus sisaldab A1, A2, B1, B2 ja C1 keeleoskustasemega eesti keele \u00f5ppijatele suunatud \u00f5pikute tekstidest eraldatud t\u00e4islauseid. Korpuses on m\u00e4rgendatud tekstistruktuuri \u00fcksused lause <sentence> ja osalause <clause>. K\u00f5ik korpuse laused on keeletaseme piirides unikaalsed.\nKorpuse aluseks on Eesti keele A1-C1 \u00f5pikute korpus 2017, mis koosnes ca 200 000 s\u00f5nest ja ca 24 000 lausest. Eesti keele A1-C1 \u00f5pikute korpuse 2017 sisust ekstraheeritud t\u00e4islausetest loodigi Eesti keele A1-C1 \u00f5pikute korpus 2018, millega kaasnes k\u00e4sitsi kontroll (sisse j\u00e4eti semantiliselt terviklikud laused, kontekstisidusad ja valesti tuvastatud laused j\u00e4eti v\u00e4lja). \nKorpuses on kaheksa \u00f5pikut:\nPesti, M., Ahi, H. (2015). E nagu Eesti: eesti keele \u00f5pik algajatele. Tallinn: Kiri-Mari Kirjastus.\nKitsnik, M., Kingisepp, L. (2002). Avatud uksed: eesti keele \u00f5ppekomplekt kesk- ja k\u00f5rgtasemele: \u00f5pperaamat. Tallinn: TEA Kirjastus.\nKitsnik, M. (2012). Eesti keele \u00f5pik: B1, B2. Tallinn: M. Kitsnik.\nPesti, M., Ahi, H. (2015). Eesti keele \u00f5pik A1. Tallinn: Justiitsministeerium.\nPesti, M., Ahi, H. (2012). Eesti keele \u00f5pik A2. Tallinn: M. Pesti.\nPesti, M., Ahi, H. (2015). Eesti keele \u00f5pik B1. Tallinn: Justiitsministeerium.\nSooneste, M. (2007). Eesti keele \u00f5pik: vene \u00f5ppekeelega g\u00fcmnaasium: kesk- ja k\u00f5rgtase. Tallinn: Varrak.\nRammo, S., Teral, M., Klaas-Lang, B., Allik, M. (2012). Keel selgeks!: eesti keele \u00f5pik t\u00e4iskasvanutele. Tallinn: Avita.\nSeitse esimest \u00f5pikut digitaliseeriti Eesti Rahvusraamatkogu digitaliseerimiskeskus. Sirje Rammo jt (2012) \u00f5pikust on kasutatud k\u00e4sikirja doc-faile. \nKorpus on UTF-8 kodeeringus. Korpus on lemmatiseeritud, m\u00e4rgendatud ja \u00fchestatud anal\u00fcsaatori EstNLTK abil.\nKorpus loodi Eesti Keele Instituudi ja Lexical Computing Ltd. koost\u00f6\u00f6s.\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14560061"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele A1-C1 \u00f5pikute korpus 2018",
-        "Estonian Coursebook Corpus 2018"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8931d431-2590-563e-9208-77355595cdcb.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8931d431-2590-563e-9208-77355595cdcb.json
deleted file mode 100644
index 69bb4fe8..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8931d431-2590-563e-9208-77355595cdcb.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05922L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:8922453",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:8922453"
-    ],
-    "PublicationTimestamp": "2016-08-24T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:8922453;2019-03-29T18:32:25Z;ESTDOI;ESTDOI.KEEL;V\u00e4ike murdes\u00f5nastik;Dialectological dictionary of Estonian;Hein, Indrek;Center of Estonian Language Resources;2016;Issued: 2016-08-24;Updated: 2016-08-24;doi:10.15155/3-00-0000-0000-0000-05922L;Abstract;Sisaldab eesti murdes\u00f5navara.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8931d431-2590-563e-9208-77355595cdcb",
-    "notes": [
-        "Abstract",
-        "Sisaldab eesti murdes\u00f5navara."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:8922453"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "V\u00e4ike murdes\u00f5nastik",
-        "Dialectological dictionary of Estonian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/89f6eb3e-e0b9-5450-9d38-844a316ea44d.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/89f6eb3e-e0b9-5450-9d38-844a316ea44d.json
deleted file mode 100644
index ed210d3f..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/89f6eb3e-e0b9-5450-9d38-844a316ea44d.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05772L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:8521723",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:8521723"
-    ],
-    "PublicationTimestamp": "2017-03-03T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek",
-        "\u00d5im, Asta"
-    ],
-    "fulltext": "oai:oai.datacite.org:8521723;2019-03-31T02:02:10Z;ESTDOI;ESTDOI.KEEL;Fraseoloogias\u00f5naraamat;The Dictionary of Estonian Phraseology;Hein, Indrek;\u00d5im, Asta;Center of Estonian Language Resources;2015;Issued: 2015-05-06;Updated: 2017-03-03;doi:10.15155/3-00-0000-0000-0000-05772L;Abstract;Sisaldab \u00fcle 7500 p\u00fcsiv\u00e4ljendi, sealhulgas raamatulikke, k\u00f5nekeelseid ja vananenud ning vulgaarseid v\u00e4ljendeid, mitmesuguseid \u00fctlusi ning kantselei- ja stampvormeleid.;Abstract;Contains over 7500 phrasemes, including bookish, colloquial, obsolete and vulgar expressions, as well as various sayings and also some red-tape and stereotyped expressions.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "89f6eb3e-e0b9-5450-9d38-844a316ea44d",
-    "notes": [
-        "Abstract",
-        "Sisaldab \u00fcle 7500 p\u00fcsiv\u00e4ljendi, sealhulgas raamatulikke, k\u00f5nekeelseid ja vananenud ning vulgaarseid v\u00e4ljendeid, mitmesuguseid \u00fctlusi ning kantselei- ja stampvormeleid.",
-        "Abstract",
-        "Contains over 7500 phrasemes, including bookish, colloquial, obsolete and vulgar expressions, as well as various sayings and also some red-tape and stereotyped expressions."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:8521723"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Fraseoloogias\u00f5naraamat",
-        "The Dictionary of Estonian Phraseology"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8ae7e701-11f2-5e25-baee-21bc44d5cc96.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8ae7e701-11f2-5e25-baee-21bc44d5cc96.json
deleted file mode 100644
index 360267c0..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8ae7e701-11f2-5e25-baee-21bc44d5cc96.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05BEEL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9474560",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9474560"
-    ],
-    "PublicationTimestamp": "2017-03-03T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:9474560;2019-04-17T17:26:25Z;ESTDOI;ESTDOI.KEEL;Eesti-udmurdi s\u00f5naraamat;The Estonian-Udmurt Dictionary;\u042d\u0441\u0442\u043e\u043d-\u0443\u0434\u043c\u0443\u0440\u0442 \u043a\u044b\u043b\u043b\u044e\u043a\u0430\u043c;Hein, Indrek;Center of Estonian Language Resources;2016;Issued: 2016-10-31;Updated: 2017-03-03;doi:10.15155/3-00-0000-0000-0000-05BEEL;Abstract;Esimene eesti-udmurdi s\u00f5naraamat. Sisaldab u 10 000 m\u00e4rks\u00f5na ja on keeleuuenduslik: udmurdikeelsete vastete puudumisel pakuvad autorid eestikeelsele s\u00f5nale omapoolse v\u00f5imaliku vaste. S\u00f5naraamatu erip\u00e4raks on ka udmurdi murdes\u00f5nade rohkus.;Abstract;The first ever Estonian-Udmurt dictionary. It contains ca 10,000 entry words and is innovation-oriented; namely, in absence of an Udmurt equivalent, the authors suggest one of their own invention. Also, there are remarkably many words from Udmurt dialects.;Abstract;\u041a\u044b\u043b\u043b\u044e\u043a\u0430\u043c\u044b\u043d \u043e\u0433 10 000 \u043a\u044b\u043b. \u0421\u043e \u0447\u0430\u043a\u043b\u0430\u043c\u044b\u043d \u0443\u0434\u043c\u0443\u0440\u0442 \u043a\u044b\u043b\u044d\u043d \u043d\u043e \u043b\u0443\u043b\u0447\u0435\u0431\u0435\u0440\u0435\u0442\u044d\u043d \u0442\u0443\u043d\u0441\u044b\u043a\u044a\u044f\u0441\u044c\u043a\u0438\u0441\u044c \u044d\u0441\u0442\u043e\u043d\u044a\u0451\u0441\u043b\u044b \u043d\u043e \u044d\u0441\u0442\u043e\u043d \u043a\u044b\u043b\u044d\u0437 \u0434\u044b\u0448\u0435\u0442\u04e5\u0441\u044c \u0443\u0434\u043c\u0443\u0440\u0442\u044a\u0451\u0441\u043b\u044b. \u0422\u0440\u043e\u0441 \u043a\u0443\u043b\u044d\u0437\u044d \u04f5\u0435\u043a\u0442\u044d \u043a\u044b\u043b\u043b\u044e\u043a\u0430\u043c \u043a\u044b\u043b\u044b\u0441\u044c \u043a\u044b\u043b\u044d \u0431\u0435\u0440\u044b\u043a\u0442\u04e5\u0441\u044c\u0451\u0441\u043b\u044b. ",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8ae7e701-11f2-5e25-baee-21bc44d5cc96",
-    "notes": [
-        "Abstract",
-        "Esimene eesti-udmurdi s\u00f5naraamat. Sisaldab u 10 000 m\u00e4rks\u00f5na ja on keeleuuenduslik: udmurdikeelsete vastete puudumisel pakuvad autorid eestikeelsele s\u00f5nale omapoolse v\u00f5imaliku vaste. S\u00f5naraamatu erip\u00e4raks on ka udmurdi murdes\u00f5nade rohkus.",
-        "Abstract",
-        "The first ever Estonian-Udmurt dictionary. It contains ca 10,000 entry words and is innovation-oriented; namely, in absence of an Udmurt equivalent, the authors suggest one of their own invention. Also, there are remarkably many words from Udmurt dialects.",
-        "Abstract",
-        "\u041a\u044b\u043b\u043b\u044e\u043a\u0430\u043c\u044b\u043d \u043e\u0433 10 000 \u043a\u044b\u043b. \u0421\u043e \u0447\u0430\u043a\u043b\u0430\u043c\u044b\u043d \u0443\u0434\u043c\u0443\u0440\u0442 \u043a\u044b\u043b\u044d\u043d \u043d\u043e \u043b\u0443\u043b\u0447\u0435\u0431\u0435\u0440\u0435\u0442\u044d\u043d \u0442\u0443\u043d\u0441\u044b\u043a\u044a\u044f\u0441\u044c\u043a\u0438\u0441\u044c \u044d\u0441\u0442\u043e\u043d\u044a\u0451\u0441\u043b\u044b \u043d\u043e \u044d\u0441\u0442\u043e\u043d \u043a\u044b\u043b\u044d\u0437 \u0434\u044b\u0448\u0435\u0442\u04e5\u0441\u044c \u0443\u0434\u043c\u0443\u0440\u0442\u044a\u0451\u0441\u043b\u044b. \u0422\u0440\u043e\u0441 \u043a\u0443\u043b\u044d\u0437\u044d \u04f5\u0435\u043a\u0442\u044d \u043a\u044b\u043b\u043b\u044e\u043a\u0430\u043c \u043a\u044b\u043b\u044b\u0441\u044c \u043a\u044b\u043b\u044d \u0431\u0435\u0440\u044b\u043a\u0442\u04e5\u0441\u044c\u0451\u0441\u043b\u044b. "
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9474560"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti-udmurdi s\u00f5naraamat",
-        "The Estonian-Udmurt Dictionary",
-        "\u042d\u0441\u0442\u043e\u043d-\u0443\u0434\u043c\u0443\u0440\u0442 \u043a\u044b\u043b\u043b\u044e\u043a\u0430\u043c"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8af6c715-82db-5f38-b5ba-676705a0bb8c.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8af6c715-82db-5f38-b5ba-676705a0bb8c.json
deleted file mode 100644
index d1e97bf7..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8af6c715-82db-5f38-b5ba-676705a0bb8c.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-00090L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17594754",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17594754"
-    ],
-    "PublicationTimestamp": "2018-11-23T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "J\u00e4rv, Risto"
-    ],
-    "fulltext": "oai:oai.datacite.org:17594754;2019-03-10T06:00:52Z;ESTDOI;ESTDOI.KEEL;Kodavere pajatused;Folk tales in Kodavere Parish;J\u00e4rv, Risto;Center of Estonian Language Resources;2018;Issued: 2018-01-22;Updated: 2018-11-23;doi:10.15155/9-00-0000-0000-0000-00090L;Abstract;kkk",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8af6c715-82db-5f38-b5ba-676705a0bb8c",
-    "notes": [
-        "Abstract",
-        "kkk"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17594754"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Kodavere pajatused",
-        "Folk tales in Kodavere Parish"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8b080e78-9744-5fc1-b4eb-16314c386a1e.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8b080e78-9744-5fc1-b4eb-16314c386a1e.json
deleted file mode 100644
index 40524d19..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8b080e78-9744-5fc1-b4eb-16314c386a1e.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-0633EL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10304101",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10304101"
-    ],
-    "PublicationTimestamp": "2017-02-16T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laansalu, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:10304101;2019-04-19T00:31:48Z;ESTDOI;ESTDOI.KEEL;Maailma maade nimed\n;Names of Countries;Laansalu, Tiina;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2017-02-16;doi:10.15155/3-00-0000-0000-0000-0633EL;Abstract;Loendi aluseks on Emakeele Seltsi keeletoimkonna poolt 1996. aastal l\u00e4bi arutatud v\u00e4liskohanimede (sh riiginimede) kirjapilt keelekorralduss\u00f5naraamatu kohanimelisas. Loendit on hiljem pidevalt t\u00e4psustatud ja ajakohastatud. Loend on \u00fchtlustatud standardis ISO 3166-1 antud valikuga.;Abstract;The list is based on the Estonian orthography of foreign place names (including tne names of countries) agreed upon by the Language Committee at the Mother Tongue Society in 1996 and published in a special supplement of the Language Planning Dictionary. Ever since, the list has been constantly monitored and updated. The list is harmonised with the ISO 3166-1 standard.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8b080e78-9744-5fc1-b4eb-16314c386a1e",
-    "notes": [
-        "Abstract",
-        "Loendi aluseks on Emakeele Seltsi keeletoimkonna poolt 1996. aastal l\u00e4bi arutatud v\u00e4liskohanimede (sh riiginimede) kirjapilt keelekorralduss\u00f5naraamatu kohanimelisas. Loendit on hiljem pidevalt t\u00e4psustatud ja ajakohastatud. Loend on \u00fchtlustatud standardis ISO 3166-1 antud valikuga.",
-        "Abstract",
-        "The list is based on the Estonian orthography of foreign place names (including tne names of countries) agreed upon by the Language Committee at the Mother Tongue Society in 1996 and published in a special supplement of the Language Planning Dictionary. Ever since, the list has been constantly monitored and updated. The list is harmonised with the ISO 3166-1 standard."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10304101"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Maailma maade nimed\n",
-        "Names of Countries"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8b483a0a-a60d-555d-8216-004640193691.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8b483a0a-a60d-555d-8216-004640193691.json
deleted file mode 100644
index 42b12d7a..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8b483a0a-a60d-555d-8216-004640193691.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05933L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:8926651",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:8926651"
-    ],
-    "PublicationTimestamp": "2017-03-24T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Raadik, Maire"
-    ],
-    "fulltext": "oai:oai.datacite.org:8926651;2019-03-25T18:25:41Z;ESTDOI;ESTDOI.KEEL;Eesti \u00f5igekeelsuss\u00f5naraamat \u00d5S 2013\n;The Dictionary of Standard Estonian \u00d5S 2013;Raadik, Maire;Center of Estonian Language Resources;2016;Issued: 2016-08-30;Updated: 2017-03-24;doi:10.15155/3-00-0000-0000-0000-05933L;Abstract;Kajastab kehtivat eesti kirjakeele normi.\n\nRaadik, Maire; Erelt, Tiiu; Leemets, Tiina; M\u00e4earu, Sirje (2013). Eesti \u00f5igekeelsuss\u00f5naraamat \u00d5S 2013. Tallinn: Eesti Keele Sihtasutus.;Abstract;\u00d5S 2013 is a normative dictionary of modern standard Estonian, giving recommendations on correct language use. It contains recommended spellings and the morphology of words, instructions on pronunciation and semantics, also some syntactic recommendations. Abbreviations, geographical names and instruction on pronouncing foreign names are attached.\n\nRaadik, Maire; Erelt, Tiiu; Leemets, Tiina; M\u00e4earu, Sirje (2013). Eesti \u00f5igekeelsuss\u00f5naraamat \u00d5S 2013 [The Dictionary of Standard Estonian \u00d5S 2013]. Tallinn: Eesti Keele Sihtasutus.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8b483a0a-a60d-555d-8216-004640193691",
-    "notes": [
-        "Abstract",
-        "Kajastab kehtivat eesti kirjakeele normi.\n\nRaadik, Maire; Erelt, Tiiu; Leemets, Tiina; M\u00e4earu, Sirje (2013). Eesti \u00f5igekeelsuss\u00f5naraamat \u00d5S 2013. Tallinn: Eesti Keele Sihtasutus.",
-        "Abstract",
-        "\u00d5S 2013 is a normative dictionary of modern standard Estonian, giving recommendations on correct language use. It contains recommended spellings and the morphology of words, instructions on pronunciation and semantics, also some syntactic recommendations. Abbreviations, geographical names and instruction on pronouncing foreign names are attached.\n\nRaadik, Maire; Erelt, Tiiu; Leemets, Tiina; M\u00e4earu, Sirje (2013). Eesti \u00f5igekeelsuss\u00f5naraamat \u00d5S 2013 [The Dictionary of Standard Estonian \u00d5S 2013]. Tallinn: Eesti Keele Sihtasutus."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:8926651"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti \u00f5igekeelsuss\u00f5naraamat \u00d5S 2013\n",
-        "The Dictionary of Standard Estonian \u00d5S 2013"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8b6eaf11-1289-56f3-a32d-af095fac0776.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8b6eaf11-1289-56f3-a32d-af095fac0776.json
deleted file mode 100644
index 6cc2c798..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8b6eaf11-1289-56f3-a32d-af095fac0776.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0018FL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17967357",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17967357"
-    ],
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Fi\u0161el, Mark"
-    ],
-    "fulltext": "oai:oai.datacite.org:17967357;2019-02-28T17:32:37Z;ESTDOI;ESTDOI.KEEL;Neurot\u00f5lge;Neuralmt;Fi\u0161el, Mark;Center of Estonian Language Resources;2019;Issued: 2019-01-08;Updated: 2019-01-08;doi:10.15155/1-00-0000-0000-0000-0018FL;Abstract;Avatud l\u00e4htekoodiga masint\u00f5lke programm.;Abstract;Neuralmt is open-source demo project for text machine translation done in the Natural Language Processing research group in the University of Tartu. The project provides convenient methods of data collection, ability to comare different translators and ability to use it as a regular text translator.\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8b6eaf11-1289-56f3-a32d-af095fac0776",
-    "notes": [
-        "Abstract",
-        "Avatud l\u00e4htekoodiga masint\u00f5lke programm.",
-        "Abstract",
-        "Neuralmt is open-source demo project for text machine translation done in the Natural Language Processing research group in the University of Tartu. The project provides convenient methods of data collection, ability to comare different translators and ability to use it as a regular text translator.\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17967357"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Neurot\u00f5lge",
-        "Neuralmt"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8bd01cb8-29c5-553d-842b-aae8fb71522b.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8bd01cb8-29c5-553d-842b-aae8fb71522b.json
deleted file mode 100644
index 35c79a9d..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8bd01cb8-29c5-553d-842b-aae8fb71522b.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05AF1L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9310572",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9310572"
-    ],
-    "PublicationTimestamp": "2017-04-11T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Viikberg, J\u00fcri"
-    ],
-    "fulltext": "oai:oai.datacite.org:9310572;2019-03-24T18:37:16Z;ESTDOI;ESTDOI.KEEL;Niederdeutsche Lehnw\u00f6rter im Estnischen;Alamsaksa laens\u00f5nad eesti keeles;Low-German Loanwords in the Estonian Language \n;Viikberg, J\u00fcri;Center of Estonian Language Resources;2016;Issued: 2016-10-19;Updated: 2017-04-11;doi:10.15155/3-00-0000-0000-0000-05AF1L;Abstract;Bei diesem W\u00f6rterbuch handelt es sich um den ersten Versuch, alle Entlehnungen aus dem Niederdeutschen zu erfassen, die in die estnische Sprache aufgenommen wurden und in ihr bestehen blieben. Dabei handelt es sich um eine der gr\u00f6\u00dften Gruppen der Entlehnungen. Die W\u00f6rter geh\u00f6ren meist zu jenem Wortschatz, der durch kulturelle Kontakte zwischen dem 13. und dem 17. Jahrhundert entstanden ist. Die niederdeutschen Entlehnungen in der estnischen Schriftsprache umfassen nach bisherigen Untersuchungen rund 800 W\u00f6rter. In das vorliegende W\u00f6rterbuch wurden 1150 W\u00f6rter aus der Schriftsprache und aus den Dialekten aufgenommen, teilweise stellt Niederdeutsch edoch nur eine der m\u00f6glichen Erkl\u00e4rungen f\u00fcr die Herkunft des Wortes dar.;Abstract;Veebis\u00f5nastik, kust leiab eesti keelde laenatud ja sellesse p\u00fcsima j\u00e4\u00e4nud alamsaksa laene, mis suures osas p\u00e4rinevad ajavahemikust 13.\u201317. sajand. S\u00f5nastikus on 1150 kirja- ning murdekeelset s\u00f5na.;Abstract;This is an online dictionary of Low-German loanwords, most of which persist in Estonian ever since the 13th\u201317th centuries. There are 1150 words from standard Estonian and from Estonian dialects.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8bd01cb8-29c5-553d-842b-aae8fb71522b",
-    "notes": [
-        "Abstract",
-        "Bei diesem W\u00f6rterbuch handelt es sich um den ersten Versuch, alle Entlehnungen aus dem Niederdeutschen zu erfassen, die in die estnische Sprache aufgenommen wurden und in ihr bestehen blieben. Dabei handelt es sich um eine der gr\u00f6\u00dften Gruppen der Entlehnungen. Die W\u00f6rter geh\u00f6ren meist zu jenem Wortschatz, der durch kulturelle Kontakte zwischen dem 13. und dem 17. Jahrhundert entstanden ist. Die niederdeutschen Entlehnungen in der estnischen Schriftsprache umfassen nach bisherigen Untersuchungen rund 800 W\u00f6rter. In das vorliegende W\u00f6rterbuch wurden 1150 W\u00f6rter aus der Schriftsprache und aus den Dialekten aufgenommen, teilweise stellt Niederdeutsch edoch nur eine der m\u00f6glichen Erkl\u00e4rungen f\u00fcr die Herkunft des Wortes dar.",
-        "Abstract",
-        "Veebis\u00f5nastik, kust leiab eesti keelde laenatud ja sellesse p\u00fcsima j\u00e4\u00e4nud alamsaksa laene, mis suures osas p\u00e4rinevad ajavahemikust 13.\u201317. sajand. S\u00f5nastikus on 1150 kirja- ning murdekeelset s\u00f5na.",
-        "Abstract",
-        "This is an online dictionary of Low-German loanwords, most of which persist in Estonian ever since the 13th\u201317th centuries. There are 1150 words from standard Estonian and from Estonian dialects."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9310572"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Niederdeutsche Lehnw\u00f6rter im Estnischen",
-        "Alamsaksa laens\u00f5nad eesti keeles",
-        "Low-German Loanwords in the Estonian Language \n"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8d11ae35-c438-5e63-9a23-b46059085367.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8d11ae35-c438-5e63-9a23-b46059085367.json
deleted file mode 100644
index 578b85bd..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8d11ae35-c438-5e63-9a23-b46059085367.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0007FL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5757360",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5757360"
-    ],
-    "PublicationTimestamp": "2015-05-22T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:5757360;2019-04-05T00:32:49Z;ESTDOI;ESTDOI.KEEL;Eesti-inglise paralleelkorpus;Estonian-English parallel corpus;Muischnek, Kadri;Center of Estonian Language Resources;2011;Issued: 2011-12-31;Updated: 2015-05-22;doi:10.15155/1-00-0000-0000-0000-0007FL;Abstract;korpus;Abstract;Annotated and sentence-aligned parallel text corpus; contains: 1. Estonian laws and their translations into English. 2. EU legislation translated into Estonian. More information: http://www.cl.ut.ee/korpused/paralleel/index.php?lang=en ",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8d11ae35-c438-5e63-9a23-b46059085367",
-    "notes": [
-        "Abstract",
-        "korpus",
-        "Abstract",
-        "Annotated and sentence-aligned parallel text corpus; contains: 1. Estonian laws and their translations into English. 2. EU legislation translated into Estonian. More information: http://www.cl.ut.ee/korpused/paralleel/index.php?lang=en "
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5757360"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti-inglise paralleelkorpus",
-        "Estonian-English parallel corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8d2faa9a-e3a9-586b-9ff7-86fa46c8d960.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8d2faa9a-e3a9-586b-9ff7-86fa46c8d960.json
deleted file mode 100644
index 7cb12ca0..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8d2faa9a-e3a9-586b-9ff7-86fa46c8d960.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-00026L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5755425",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5755425"
-    ],
-    "PublicationTimestamp": "2015-05-21T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Alum\u00e4e, Tanel"
-    ],
-    "fulltext": "oai:oai.datacite.org:5755425;2019-02-24T18:37:42Z;ESTDOI;ESTDOI.KEEL;K\u00f5nele;Alum\u00e4e, Tanel;Center of Estonian Language Resources;2014;Issued: 2014-12-30;Updated: 2015-05-21;doi:10.15155/9-00-0000-0000-0000-00026L;Abstract;K\u00f5nele on k\u00f5netuvastusteenus Androidi rakendustele, mis v\u00f5imaldab saata e-kirju, sooritada infootsingut, kirjutada m\u00e4rkmeid, anda k\u00e4ske jne k\u00f5ne abil.;Abstract;Real-time speech recognition application for Android",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8d2faa9a-e3a9-586b-9ff7-86fa46c8d960",
-    "notes": [
-        "Abstract",
-        "K\u00f5nele on k\u00f5netuvastusteenus Androidi rakendustele, mis v\u00f5imaldab saata e-kirju, sooritada infootsingut, kirjutada m\u00e4rkmeid, anda k\u00e4ske jne k\u00f5ne abil.",
-        "Abstract",
-        "Real-time speech recognition application for Android"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5755425"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "K\u00f5nele"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8d51b9fb-96d3-5d67-a00e-4029c66fc25f.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8d51b9fb-96d3-5d67-a00e-4029c66fc25f.json
deleted file mode 100644
index 171e2e0c..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8d51b9fb-96d3-5d67-a00e-4029c66fc25f.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-0576FL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:8521720",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:8521720"
-    ],
-    "PublicationTimestamp": "2015-04-29T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Langemets, Margit"
-    ],
-    "fulltext": "oai:oai.datacite.org:8521720;2019-03-23T07:02:07Z;ESTDOI;ESTDOI.KEEL;Eesti et\u00fcmoloogias\u00f5naraamat;Estonian Etymological Dictionary;Langemets, Margit;Center of Estonian Language Resources;2015;Issued: 2015-04-29;Updated: 2015-04-29;doi:10.15155/3-00-0000-0000-0000-0576FL;Abstract;2012. aastal ilmunud \u201eEesti et\u00fcmoloogias\u00f5naraamatu\u201c elektrooniline versioon. Sisaldab teavet eesti keele s\u00f5nat\u00fcvede p\u00e4ritolu ja s\u00f5nade omavaheliste p\u00e4ritoluseoste kohta (laenud, omat\u00fcved, tehist\u00fcved jm). Sisaldab \u201e\u00d5S 2006\u201c s\u00f5nat\u00fcvede et\u00fcmoloogiaid (v.a v\u00f5\u00f5rs\u00f5nat\u00fcved).",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8d51b9fb-96d3-5d67-a00e-4029c66fc25f",
-    "notes": [
-        "Abstract",
-        "2012. aastal ilmunud \u201eEesti et\u00fcmoloogias\u00f5naraamatu\u201c elektrooniline versioon. Sisaldab teavet eesti keele s\u00f5nat\u00fcvede p\u00e4ritolu ja s\u00f5nade omavaheliste p\u00e4ritoluseoste kohta (laenud, omat\u00fcved, tehist\u00fcved jm). Sisaldab \u201e\u00d5S 2006\u201c s\u00f5nat\u00fcvede et\u00fcmoloogiaid (v.a v\u00f5\u00f5rs\u00f5nat\u00fcved)."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:8521720"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti et\u00fcmoloogias\u00f5naraamat",
-        "Estonian Etymological Dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8e229777-0113-5117-9eda-4c034b7dac18.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8e229777-0113-5117-9eda-4c034b7dac18.json
deleted file mode 100644
index 727ba9db..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8e229777-0113-5117-9eda-4c034b7dac18.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05BE7L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9474553",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9474553"
-    ],
-    "PublicationTimestamp": "2016-11-09T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Nurk, T\u00f5nis"
-    ],
-    "fulltext": "oai:oai.datacite.org:9474553;2019-04-20T11:02:09Z;ESTDOI;ESTDOI.KEEL;e-keelen\u00f5u;Nurk, T\u00f5nis;Center of Estonian Language Resources;2016;Issued: 2016-11-09;Updated: 2016-11-09;doi:10.15155/3-00-0000-0000-0000-05BE7L;Abstract;\u00dchisp\u00e4ring keeleinfot sisaldavatest allikatest. Portaali peaeesm\u00e4rgiks on pakkuda l\u00f5pptarbijale intuitiivselt lihtsal viisil vastuseid keelealastele k\u00fcsimustele, nt normingukohasus, vasted teistes keeltes, selgitused, et\u00fcmoloogia, kasutusinfo jms.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8e229777-0113-5117-9eda-4c034b7dac18",
-    "notes": [
-        "Abstract",
-        "\u00dchisp\u00e4ring keeleinfot sisaldavatest allikatest. Portaali peaeesm\u00e4rgiks on pakkuda l\u00f5pptarbijale intuitiivselt lihtsal viisil vastuseid keelealastele k\u00fcsimustele, nt normingukohasus, vasted teistes keeltes, selgitused, et\u00fcmoloogia, kasutusinfo jms."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9474553"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "e-keelen\u00f5u"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8ec31e0b-bcee-5cad-850f-9e01090f1af4.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8ec31e0b-bcee-5cad-850f-9e01090f1af4.json
deleted file mode 100644
index deecd444..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8ec31e0b-bcee-5cad-850f-9e01090f1af4.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0014AL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:13909259",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:13909259"
-    ],
-    "PublicationTimestamp": "2018-01-24T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Lippus, P\u00e4rtel"
-    ],
-    "fulltext": "oai:oai.datacite.org:13909259;2019-04-02T19:01:45Z;ESTDOI;ESTDOI.KEEL;Ersa prosoodia korpus;Erzya prosody corpus;Lippus, P\u00e4rtel;Center of Estonian Language Resources;2018;Issued: 2018-01-24;Updated: 2018-01-24;doi:10.15155/1-00-0000-0000-0000-0014AL;Abstract;Ersa s\u00f5naprosoodia uurimiseks kogutud andmestik. Sisaldab raamlauses loetud tests\u00f5nu 8 keelejuhilt. Iga keelejuht luges 100 lauset, iga lause sisaldas tests\u00f5na kord lause keskel, kord lause l\u00f5pus. Vt l\u00e4hemalt:\nLehiste, I., Aasm\u00e4e, N., Meister, E., Pajusalu, K., Teras, P., & Viitso, T.-R. (2003). Erzya prosody. Helsinki: Finno-Ugrian Society.;Abstract;The recordings collected for studying Erzya word prosody. 8 test subjects read 100 sentences. Each carrrier sentence contained a test word in phrase medial position and phrase final position. \nLehiste, I., Aasm\u00e4e, N., Meister, E., Pajusalu, K., Teras, P., & Viitso, T.-R. (2003). Erzya prosody. Helsinki: Finno-Ugrian Society.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8ec31e0b-bcee-5cad-850f-9e01090f1af4",
-    "notes": [
-        "Abstract",
-        "Ersa s\u00f5naprosoodia uurimiseks kogutud andmestik. Sisaldab raamlauses loetud tests\u00f5nu 8 keelejuhilt. Iga keelejuht luges 100 lauset, iga lause sisaldas tests\u00f5na kord lause keskel, kord lause l\u00f5pus. Vt l\u00e4hemalt:\nLehiste, I., Aasm\u00e4e, N., Meister, E., Pajusalu, K., Teras, P., & Viitso, T.-R. (2003). Erzya prosody. Helsinki: Finno-Ugrian Society.",
-        "Abstract",
-        "The recordings collected for studying Erzya word prosody. 8 test subjects read 100 sentences. Each carrrier sentence contained a test word in phrase medial position and phrase final position. \nLehiste, I., Aasm\u00e4e, N., Meister, E., Pajusalu, K., Teras, P., & Viitso, T.-R. (2003). Erzya prosody. Helsinki: Finno-Ugrian Society."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:13909259"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Ersa prosoodia korpus",
-        "Erzya prosody corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8ef2bf88-77e7-5730-8380-f75e0e466847.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8ef2bf88-77e7-5730-8380-f75e0e466847.json
deleted file mode 100644
index 8da32180..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8ef2bf88-77e7-5730-8380-f75e0e466847.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00180L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17946198",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17946198"
-    ],
-    "PublicationTimestamp": "2019-01-03T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:17946198;2019-03-09T18:36:54Z;ESTDOI;ESTDOI.KEEL;Kollokatsioonid;Muischnek, Kadri;Center of Estonian Language Resources;2019;Issued: 2019-01-03;Updated: 2019-01-03;doi:10.15155/1-00-0000-0000-0000-00180L;Abstract;Kollokatsioonide leidja abil saab leida vastavalt p\u00e4ringule \u00fcksikuid kollokatsioone, kuid selleks, et teada saada kollokatsioonide pingerida, ongi abiks siin esitatud sagedusloendid kollokatsioonide leidja alusmaterjalist. T\u00e4nu pingeridadele on v\u00f5imalik vaadelda valitud statistiku v\u00f5i lihtsalt kollokatsioonipaari sageduse alusel j\u00e4rjestatud 5000 sagedasemat/olulisemat Tasakaalus korpuses leiduvat kollokatsioonipaari, mis esinesid korpuses k\u00fcmme v\u00f5i enam korda. Esitatud on sarnaselt kollokatsioonide leidja pakutud v\u00f5imalustega teatud s\u00f5naliiki kuuluva lemma sagedasemad kollokatsioonid teise lemmaga, teatud s\u00f5naliiki kuuluva s\u00f5navormi sagedasemad kollokatsioonid teise s\u00f5navormiga ja teatud s\u00f5naliiki kuuluva lemma sagedasemad kollokatsioonid s\u00f5navormiga.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8ef2bf88-77e7-5730-8380-f75e0e466847",
-    "notes": [
-        "Abstract",
-        "Kollokatsioonide leidja abil saab leida vastavalt p\u00e4ringule \u00fcksikuid kollokatsioone, kuid selleks, et teada saada kollokatsioonide pingerida, ongi abiks siin esitatud sagedusloendid kollokatsioonide leidja alusmaterjalist. T\u00e4nu pingeridadele on v\u00f5imalik vaadelda valitud statistiku v\u00f5i lihtsalt kollokatsioonipaari sageduse alusel j\u00e4rjestatud 5000 sagedasemat/olulisemat Tasakaalus korpuses leiduvat kollokatsioonipaari, mis esinesid korpuses k\u00fcmme v\u00f5i enam korda. Esitatud on sarnaselt kollokatsioonide leidja pakutud v\u00f5imalustega teatud s\u00f5naliiki kuuluva lemma sagedasemad kollokatsioonid teise lemmaga, teatud s\u00f5naliiki kuuluva s\u00f5navormi sagedasemad kollokatsioonid teise s\u00f5navormiga ja teatud s\u00f5naliiki kuuluva lemma sagedasemad kollokatsioonid s\u00f5navormiga."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17946198"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Kollokatsioonid"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8f8f808b-989e-5ce8-a249-df6b2c6589a8.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8f8f808b-989e-5ce8-a249-df6b2c6589a8.json
deleted file mode 100644
index 24f5a429..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8f8f808b-989e-5ce8-a249-df6b2c6589a8.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-071F1L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14560494",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14560494"
-    ],
-    "PublicationTimestamp": "2018-04-23T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Koppel, Kristina",
-        "Kallas, Jelena"
-    ],
-    "fulltext": "oai:oai.datacite.org:14560494;2019-04-17T17:27:03Z;ESTDOI;ESTDOI.KEEL;Sketch Engine eesti keele \u00f5ppijale (etSkELL) ;Sketch Engine for Estonian Language Learning (etSkELL) ;Kallas, Jelena;Koppel, Kristina;Center of Estonian Language Resources;2018;Issued: 2018-03-26;Updated: 2018-04-23;doi:10.15155/3-00-0000-0000-0000-071F1L;Abstract;etSkELL on automaatselt loodud keele\u00f5ppekeskkond, mille alus on Eesti keele \u00f5ppekorpus 2018. Korpus sisaldab umbes 25 miljonit lauset ja 250 miljonit s\u00f5na. Laused on p\u00e4rit erinevatest meedia-, ilukirjandus- ja teadustekstidest ning eestikeelsest Vikipeediast ja Eesti keele A1-C1 \u00f5pikute korpusest 2018.\netSkELL arendati v\u00e4lja Eesti Keele Instituudi ja Lexical Computing Ltd. koost\u00f6\u00f6s.\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8f8f808b-989e-5ce8-a249-df6b2c6589a8",
-    "notes": [
-        "Abstract",
-        "etSkELL on automaatselt loodud keele\u00f5ppekeskkond, mille alus on Eesti keele \u00f5ppekorpus 2018. Korpus sisaldab umbes 25 miljonit lauset ja 250 miljonit s\u00f5na. Laused on p\u00e4rit erinevatest meedia-, ilukirjandus- ja teadustekstidest ning eestikeelsest Vikipeediast ja Eesti keele A1-C1 \u00f5pikute korpusest 2018.\netSkELL arendati v\u00e4lja Eesti Keele Instituudi ja Lexical Computing Ltd. koost\u00f6\u00f6s.\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14560494"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Sketch Engine eesti keele \u00f5ppijale (etSkELL) ",
-        "Sketch Engine for Estonian Language Learning (etSkELL) "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8faa0208-2947-541a-8d8a-a423bf93c212.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8faa0208-2947-541a-8d8a-a423bf93c212.json
deleted file mode 100644
index b7d387f9..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8faa0208-2947-541a-8d8a-a423bf93c212.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00139L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:12052515",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:12052515"
-    ],
-    "PublicationTimestamp": "2017-09-13T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Vare, Kadri",
-        "Orav, Heili"
-    ],
-    "fulltext": "oai:oai.datacite.org:12052515;2019-04-06T19:01:45Z;ESTDOI;ESTDOI.KEEL;Eesti Wordnet (2.1);Estonian Wordnet (2.1);Orav, Heili;Vare, Kadri;Center of Estonian Language Resources;2014;Issued: 2014-03-21;Updated: 2017-09-13;doi:10.15155/1-00-0000-0000-0000-00139L;Abstract;XML versioon Eesti Wordnetist.;Abstract;EstWN in XML format.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8faa0208-2947-541a-8d8a-a423bf93c212",
-    "notes": [
-        "Abstract",
-        "XML versioon Eesti Wordnetist.",
-        "Abstract",
-        "EstWN in XML format."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:12052515"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti Wordnet (2.1)",
-        "Estonian Wordnet (2.1)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8fda1587-7882-507c-ad3e-2bb20ad32370.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8fda1587-7882-507c-ad3e-2bb20ad32370.json
deleted file mode 100644
index 243232d1..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/8fda1587-7882-507c-ad3e-2bb20ad32370.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/TY.0010",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:4597369",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:4597369"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Orav, Heili"
-    ],
-    "fulltext": "oai:oai.datacite.org:4597369;2019-04-02T01:31:53Z;ESTDOI;ESTDOI.KEEL;Estonian Wordnet (kb69a-LAST);Orav, Heili;Center of Estonian Language Resources;2014;doi:10.15155/TY.0010",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "8fda1587-7882-507c-ad3e-2bb20ad32370",
-    "oai_identifier": [
-        "oai:oai.datacite.org:4597369"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Estonian Wordnet (kb69a-LAST)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/90de7cf5-a3c5-56ed-8b03-4054dc09e6e6.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/90de7cf5-a3c5-56ed-8b03-4054dc09e6e6.json
deleted file mode 100644
index adc58950..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/90de7cf5-a3c5-56ed-8b03-4054dc09e6e6.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05BE8L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9474554",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9474554"
-    ],
-    "PublicationTimestamp": "2016-11-09T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Nurk, T\u00f5nis"
-    ],
-    "fulltext": "oai:oai.datacite.org:9474554;2019-04-20T08:02:25Z;ESTDOI;ESTDOI.KEEL;e-keelen\u00f5u;Nurk, T\u00f5nis;Center of Estonian Language Resources;2016;Issued: 2016-11-09;Updated: 2016-11-09;doi:10.15155/3-00-0000-0000-0000-05BE8L;Abstract;\u00dchisp\u00e4ring keeleinfot sisaldavatest allikatest. Portaali peaeesm\u00e4rgiks on pakkuda l\u00f5pptarbijale intuitiivselt lihtsal viisil vastuseid keelealastele k\u00fcsimustele, nt normingukohasus, vasted teistes keeltes, selgitused, et\u00fcmoloogia, kasutusinfo jms.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "90de7cf5-a3c5-56ed-8b03-4054dc09e6e6",
-    "notes": [
-        "Abstract",
-        "\u00dchisp\u00e4ring keeleinfot sisaldavatest allikatest. Portaali peaeesm\u00e4rgiks on pakkuda l\u00f5pptarbijale intuitiivselt lihtsal viisil vastuseid keelealastele k\u00fcsimustele, nt normingukohasus, vasted teistes keeltes, selgitused, et\u00fcmoloogia, kasutusinfo jms."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9474554"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "e-keelen\u00f5u"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/919710d2-c536-532e-9ae1-b55b19b65aac.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/919710d2-c536-532e-9ae1-b55b19b65aac.json
deleted file mode 100644
index 21ffb529..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/919710d2-c536-532e-9ae1-b55b19b65aac.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-000A9L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17972100",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17972100"
-    ],
-    "PublicationTimestamp": "2019-01-09T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Taal, Hannalore"
-    ],
-    "fulltext": "oai:oai.datacite.org:17972100;2019-03-01T21:30:42Z;ESTDOI;ESTDOI.KEEL;K\u00f5nes\u00e4mplid k\u00f5neravi.ee jaoks;Taal, Hannalore;Center of Estonian Language Resources;2019;Issued: 2019-01-09;Updated: 2019-01-09;doi:10.15155/9-00-0000-0000-0000-000A9L;Abstract;Logopeedi\u200b \u200bvastuv\u00f5tul\u200b \u200bk\u00e4inud\u200b \u200bpatsientide\u200b \u200bteraapia\u200b \u200bk\u00e4igus lindistatud k\u00f5nes\u00e4mplid.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "919710d2-c536-532e-9ae1-b55b19b65aac",
-    "notes": [
-        "Abstract",
-        "Logopeedi\u200b \u200bvastuv\u00f5tul\u200b \u200bk\u00e4inud\u200b \u200bpatsientide\u200b \u200bteraapia\u200b \u200bk\u00e4igus lindistatud k\u00f5nes\u00e4mplid."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17972100"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "K\u00f5nes\u00e4mplid k\u00f5neravi.ee jaoks"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9203c17d-ad32-5c66-ac35-a97253f4421d.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9203c17d-ad32-5c66-ac35-a97253f4421d.json
deleted file mode 100644
index d08d115f..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9203c17d-ad32-5c66-ac35-a97253f4421d.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/TY.0009",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:4597358",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:4597358"
-    ],
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Gerassimenko, Olga"
-    ],
-    "fulltext": "oai:oai.datacite.org:4597358;2019-04-04T13:01:01Z;ESTDOI;ESTDOI.KEEL;Corpus of Spoken Estonian;Gerassimenko, Olga;Center of Estonian Language Resources;2013;doi:10.15155/TY.0009",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9203c17d-ad32-5c66-ac35-a97253f4421d",
-    "oai_identifier": [
-        "oai:oai.datacite.org:4597358"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus of Spoken Estonian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/92e973bb-4f62-5789-8c62-8e1b131d7119.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/92e973bb-4f62-5789-8c62-8e1b131d7119.json
deleted file mode 100644
index f26b0aff..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/92e973bb-4f62-5789-8c62-8e1b131d7119.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00168L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17767578",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17767578"
-    ],
-    "PublicationTimestamp": "2019-01-28T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "M\u00fc\u00fcrisep, Kaili",
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:17767578;2019-03-11T18:37:20Z;ESTDOI;ESTDOI.KEEL;UD Estonian ver.2.3;Muischnek, Kadri;M\u00fc\u00fcrisep, Kaili;Center of Estonian Language Resources;2018;Issued: 2018-12-10;Updated: 2019-01-28;doi:10.15155/1-00-0000-0000-0000-00168L;Abstract;UD Estonian is a converted version of the Estonian Dependency Treebank (EDT), originally annotated in the Constraint Grammar (CG) annotation scheme, and consisting of genres of fiction, newspaper texts and scientific texts. The treebank contains 30,723 trees, 434,245 tokens.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "92e973bb-4f62-5789-8c62-8e1b131d7119",
-    "notes": [
-        "Abstract",
-        "UD Estonian is a converted version of the Estonian Dependency Treebank (EDT), originally annotated in the Constraint Grammar (CG) annotation scheme, and consisting of genres of fiction, newspaper texts and scientific texts. The treebank contains 30,723 trees, 434,245 tokens."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17767578"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "UD Estonian ver.2.3"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/92f4fa15-01e3-5f8b-9754-6d63f8186cde.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/92f4fa15-01e3-5f8b-9754-6d63f8186cde.json
deleted file mode 100644
index 3feafa54..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/92f4fa15-01e3-5f8b-9754-6d63f8186cde.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00173L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17944507",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17944507"
-    ],
-    "PublicationTimestamp": "2019-01-03T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:17944507;2019-01-03T11:07:33Z;ESTDOI;ESTDOI.KEEL;Maltparseri treenitud mudel;Muischnek, Kadri;Center of Estonian Language Resources;2019;Issued: 2019-01-03;Updated: 2019-01-03;doi:10.15155/1-00-0000-0000-0000-00173L;Abstract;MaltParseri eesti keele anal\u00fc\u00fcsiks vajalik mudel model.mco, treenitud eesti keele s\u00f5ltuvupuude pangal, \u00fchildub MaltParseri versiooniga 1.8.1. Sisaldab ka teisendajat eesti keele CG morfoloogilise \u00fchestaja v\u00f5i s\u00fcntaktilise anal\u00fcsaatori v\u00e4ljundi kujult MaltParseri treenitud mudeli jaoks sobivale conll-kujule. Anal\u00fc\u00fcsiks on vajalik MaltParseri anal\u00fcsaator: http://www.maltparser.org/.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "92f4fa15-01e3-5f8b-9754-6d63f8186cde",
-    "notes": [
-        "Abstract",
-        "MaltParseri eesti keele anal\u00fc\u00fcsiks vajalik mudel model.mco, treenitud eesti keele s\u00f5ltuvupuude pangal, \u00fchildub MaltParseri versiooniga 1.8.1. Sisaldab ka teisendajat eesti keele CG morfoloogilise \u00fchestaja v\u00f5i s\u00fcntaktilise anal\u00fcsaatori v\u00e4ljundi kujult MaltParseri treenitud mudeli jaoks sobivale conll-kujule. Anal\u00fc\u00fcsiks on vajalik MaltParseri anal\u00fcsaator: http://www.maltparser.org/."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17944507"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Maltparseri treenitud mudel"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/94398cfc-a62e-5d4a-b219-8e03ebc76c57.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/94398cfc-a62e-5d4a-b219-8e03ebc76c57.json
deleted file mode 100644
index 99487d86..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/94398cfc-a62e-5d4a-b219-8e03ebc76c57.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-079D5L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17926655",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17926655"
-    ],
-    "PublicationTimestamp": "2018-12-22T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Pajupuu, Hille"
-    ],
-    "fulltext": "oai:oai.datacite.org:17926655;2019-04-20T14:37:00Z;ESTDOI;ESTDOI.KEEL;Emotsioonidetektor Google Chrome'i laiendusena;Pajupuu, Hille;Center of Estonian Language Resources;2018;Issued: 2018-12-22;Updated: 2018-12-22;doi:10.15155/3-00-0000-0000-0000-079D5L;Abstract;Emotsioonidetektoriga saab hinnata veebikirjutise emotsionaalset m\u00f5ju. Selleks tuleb esmalt emotsioonidetektor installeerida, seej\u00e4rel v\u00e4lja valida tekst ja klikata ikoonile. Detektor annab tekstile \u00fcldhinnangu: neutraalne, positiivne, negatiivne v\u00f5i vastuoluline. Tekstis m\u00e4rgitakse \u00e4ra emotsioonitaju m\u00f5jutavad v\u00f5tmes\u00f5nad ning ortograafiliste tekstil\u00f5ikude emotsionaalsus (lilla - negatiivne, roheline - positiivne, kollane - vastuoluline, hall - ekstreemne).",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "94398cfc-a62e-5d4a-b219-8e03ebc76c57",
-    "notes": [
-        "Abstract",
-        "Emotsioonidetektoriga saab hinnata veebikirjutise emotsionaalset m\u00f5ju. Selleks tuleb esmalt emotsioonidetektor installeerida, seej\u00e4rel v\u00e4lja valida tekst ja klikata ikoonile. Detektor annab tekstile \u00fcldhinnangu: neutraalne, positiivne, negatiivne v\u00f5i vastuoluline. Tekstis m\u00e4rgitakse \u00e4ra emotsioonitaju m\u00f5jutavad v\u00f5tmes\u00f5nad ning ortograafiliste tekstil\u00f5ikude emotsionaalsus (lilla - negatiivne, roheline - positiivne, kollane - vastuoluline, hall - ekstreemne)."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17926655"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Emotsioonidetektor Google Chrome'i laiendusena"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/95897677-c789-57f8-bc7b-b8e1518530d3.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/95897677-c789-57f8-bc7b-b8e1518530d3.json
deleted file mode 100644
index ddfb41fa..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/95897677-c789-57f8-bc7b-b8e1518530d3.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0019EL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17986399",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17986399"
-    ],
-    "PublicationTimestamp": "2019-01-11T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Iva, Sulev"
-    ],
-    "fulltext": "oai:oai.datacite.org:17986399;2019-04-17T17:27:39Z;ESTDOI;ESTDOI.KEEL;V\u00f5ru-eesti paralleelkorpuse kasutajaliides;Iva, Sulev;Center of Estonian Language Resources;2019;Issued: 2019-01-11;Updated: 2019-01-11;doi:10.15155/1-00-0000-0000-0000-0019EL;Abstract;Otsida saab mitu s\u00f5na korraga, hetkel miinusm\u00e4rki v\u00e4ljaj\u00e4ttena ei toetata.Vaikimisi otsitakse mitte terveid s\u00f5nu vaid s\u00f5nesid pikemate s\u00f5nede sees. ",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "95897677-c789-57f8-bc7b-b8e1518530d3",
-    "notes": [
-        "Abstract",
-        "Otsida saab mitu s\u00f5na korraga, hetkel miinusm\u00e4rki v\u00e4ljaj\u00e4ttena ei toetata.Vaikimisi otsitakse mitte terveid s\u00f5nu vaid s\u00f5nesid pikemate s\u00f5nede sees. "
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17986399"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "V\u00f5ru-eesti paralleelkorpuse kasutajaliides"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/96147211-4bc7-5314-bf25-b1bc58aa3f19.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/96147211-4bc7-5314-bf25-b1bc58aa3f19.json
deleted file mode 100644
index 67718c4e..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/96147211-4bc7-5314-bf25-b1bc58aa3f19.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/TY.000B",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:4597363",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:4597363"
-    ],
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Luts, Martin"
-    ],
-    "fulltext": "oai:oai.datacite.org:4597363;2018-10-22T16:32:35Z;ESTDOI;ESTDOI.KEEL;Estonian Open Parallel Corpus;Luts, Martin;Center of Estonian Language Resources;2013;doi:10.15155/TY.000B",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "96147211-4bc7-5314-bf25-b1bc58aa3f19",
-    "oai_identifier": [
-        "oai:oai.datacite.org:4597363"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Estonian Open Parallel Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/97143fd5-e543-50e9-ad56-8d7577ffad5c.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/97143fd5-e543-50e9-ad56-8d7577ffad5c.json
deleted file mode 100644
index 3069f93e..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/97143fd5-e543-50e9-ad56-8d7577ffad5c.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05AF3L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9310574",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9310574"
-    ],
-    "PublicationTimestamp": "2017-03-03T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek",
-        "\u00d5im, Asta"
-    ],
-    "fulltext": "oai:oai.datacite.org:9310574;2019-04-17T17:26:02Z;ESTDOI;ESTDOI.KEEL;S\u00fcnon\u00fc\u00fcmis\u00f5nastik;The Dictionary of Estonian Synonyms;Hein, Indrek;\u00d5im, Asta;Center of Estonian Language Resources;2016;Issued: 2016-10-19;Updated: 2017-03-03;doi:10.15155/3-00-0000-0000-0000-05AF3L;Abstract;Pakub kirjas ja k\u00f5nes kasutatavaid s\u00fcnon\u00fc\u00fcme, sealhulgas valiku vanemaid, murdelisi ning k\u00f5nekeelseid s\u00f5nu v\u00f5i v\u00e4ljendeid, samuti termineid ning kantselei- ja stampkeelendeid.;Abstract;This is a comprehensive dictionary of Estonian synonyms, offering words used in writing and/or speech, including a selection of older, dialectal and colloquial words or expressions, plus some special terms as well as red-tape and stereotyped expressions. ",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "97143fd5-e543-50e9-ad56-8d7577ffad5c",
-    "notes": [
-        "Abstract",
-        "Pakub kirjas ja k\u00f5nes kasutatavaid s\u00fcnon\u00fc\u00fcme, sealhulgas valiku vanemaid, murdelisi ning k\u00f5nekeelseid s\u00f5nu v\u00f5i v\u00e4ljendeid, samuti termineid ning kantselei- ja stampkeelendeid.",
-        "Abstract",
-        "This is a comprehensive dictionary of Estonian synonyms, offering words used in writing and/or speech, including a selection of older, dialectal and colloquial words or expressions, plus some special terms as well as red-tape and stereotyped expressions. "
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9310574"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "S\u00fcnon\u00fc\u00fcmis\u00f5nastik",
-        "The Dictionary of Estonian Synonyms"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/97367d86-6a39-51d8-8447-45358ea7b131.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/97367d86-6a39-51d8-8447-45358ea7b131.json
deleted file mode 100644
index 170d1418..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/97367d86-6a39-51d8-8447-45358ea7b131.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00158L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14614711",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14614711"
-    ],
-    "PublicationTimestamp": "2018-04-13T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laur, Sven"
-    ],
-    "fulltext": "oai:oai.datacite.org:14614711;2019-04-01T07:31:03Z;ESTDOI;ESTDOI.KEEL;Veebikorpus13 korpus anal\u00fc\u00fcsitud EstNLTK v1.6.b abil;Web13 corpus analysed with EstNLTK v1.6.b;Laur, Sven;Center of Estonian Language Resources;2018;Issued: 2018-04-05;Updated: 2018-04-13;doi:10.15155/1-00-0000-0000-0000-00158L;Abstract;Web13 Corpus analysed with EstNLTK ver.1.6_b\n\nThis resource contains texts from the Web13 Corpus (aka the etTenTen corpus) that have been converted into JSON format, and linguistically analysed with EstNLTK ver 1.6_b. The corpus contains 686,325 text files in EstNLTK's JSON format. \n\nSource of the corpus\n\nRaw texts of the Web13 Corpus, which are available form here:\n https://metashare.ut.ee/repository/browse/ettenten-korpus-toortekst/b564ca760de111e6a6e4005056b4002419cacec839ad4b7a93c3f7c45a97c55f\n\nProcessing\n\nTexts were first converted into EstNLTK JSON format (metadata of the text documents was also preserved), and then automatically processed. Processing involved tokenizing texts into words, sentences and paragraphs, and morphological analysis and disambiguation. Results of the processing were recorded as annotation layers.\nThere are two layers of morphological annotations: \n1) the layer that uses Vabamorf's category system[1], \n2) the layer that uses Giellatekno's category system[2].\n\nThe processing was done at 2017-12-22, using the latest EstNLTK version available at that time (the version 1.6.0_beta).\nScripts that were used for processing (along with the instructions) are available here:\nhttps://github.com/estnltk/estnltk/tree/aed554e15e7f9e0f854d7a49bb2e2674e274cabc/estnltk/corpus_processing\n\nLoading JSON files with EstNLTK\nSee the tutorial:\n https://github.com/estnltk/estnltk/blob/aed554e15e7f9e0f854d7a49bb2e2674e274cabc/tutorials/json_exporter_importer.ipynb\n (Import from file)\n\n\n[1] -- Vabamorf's tagset -- Estonian description is available here: https://github.com/Filosoft/vabamorf/blob/master/doc/tagset.html\n[2] -- Giellatekno's tagset -- Estonian description is available here: http://www2.keeleveeb.ee/dict/corpus/shared/categories.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "97367d86-6a39-51d8-8447-45358ea7b131",
-    "notes": [
-        "Abstract",
-        "Web13 Corpus analysed with EstNLTK ver.1.6_b\n\nThis resource contains texts from the Web13 Corpus (aka the etTenTen corpus) that have been converted into JSON format, and linguistically analysed with EstNLTK ver 1.6_b. The corpus contains 686,325 text files in EstNLTK's JSON format. \n\nSource of the corpus\n\nRaw texts of the Web13 Corpus, which are available form here:\n https://metashare.ut.ee/repository/browse/ettenten-korpus-toortekst/b564ca760de111e6a6e4005056b4002419cacec839ad4b7a93c3f7c45a97c55f\n\nProcessing\n\nTexts were first converted into EstNLTK JSON format (metadata of the text documents was also preserved), and then automatically processed. Processing involved tokenizing texts into words, sentences and paragraphs, and morphological analysis and disambiguation. Results of the processing were recorded as annotation layers.\nThere are two layers of morphological annotations: \n1) the layer that uses Vabamorf's category system[1], \n2) the layer that uses Giellatekno's category system[2].\n\nThe processing was done at 2017-12-22, using the latest EstNLTK version available at that time (the version 1.6.0_beta).\nScripts that were used for processing (along with the instructions) are available here:\nhttps://github.com/estnltk/estnltk/tree/aed554e15e7f9e0f854d7a49bb2e2674e274cabc/estnltk/corpus_processing\n\nLoading JSON files with EstNLTK\nSee the tutorial:\n https://github.com/estnltk/estnltk/blob/aed554e15e7f9e0f854d7a49bb2e2674e274cabc/tutorials/json_exporter_importer.ipynb\n (Import from file)\n\n\n[1] -- Vabamorf's tagset -- Estonian description is available here: https://github.com/Filosoft/vabamorf/blob/master/doc/tagset.html\n[2] -- Giellatekno's tagset -- Estonian description is available here: http://www2.keeleveeb.ee/dict/corpus/shared/categories.html"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14614711"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Veebikorpus13 korpus anal\u00fc\u00fcsitud EstNLTK v1.6.b abil",
-        "Web13 corpus analysed with EstNLTK v1.6.b"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/97743740-39c3-5a05-a63b-39c561d463a5.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/97743740-39c3-5a05-a63b-39c561d463a5.json
deleted file mode 100644
index a8a9d98e..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/97743740-39c3-5a05-a63b-39c561d463a5.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0015BL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14977542",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14977542"
-    ],
-    "PublicationTimestamp": "2018-05-04T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Orasmaa, Siim"
-    ],
-    "fulltext": "oai:oai.datacite.org:14977542;2019-04-11T18:02:32Z;ESTDOI;ESTDOI.KEEL;TimeML annotated corpus of Estonian newspaper articles;Orasmaa, Siim;Center of Estonian Language Resources;2018;Issued: 2018-04-13;Updated: 2018-05-04;doi:10.15155/1-00-0000-0000-0000-0015BL;Abstract;Estonian TimeML Annotated Corpus  (ver 2.0)\n\nThe corpus consists of 80 Estonian newspaper articles (approx. 22,000 word tokens) with manually corrected morphological and dependency syntactic annotations, and with manually added temporal semantic annotations. This corpus is a subcorpus of Estonian Dependency Treebank ( https://github.com/EstSyntax/EDT ).\n\nTemporal semantic annotations are based on an adaption of the TimeML specification ( http://www.timeml.org/ ), and consist of EVENT, TIMEX and TLINK annotations. The creation process of the corpus, along with the evaluation of consistency of annotation is described by Orasmaa (2014a, 2014b).\n\nFormat of the corpus\n\nSee  https://github.com/soras/EstTimeMLCorpus/blob/master/readme.txt  for details.\n\n\nRelated publications\n\nThe creation of this corpus and its first version is described in publications:\n\nS.Orasmaa (2014a). Towards an Integration of Syntactic and Temporal Annotations in Estonian. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14).\n\nS.Orasmaa (2014b). How Availability of Explicit Temporal Cues Affects Manual Temporal Relation Annotation. Human Language Technologies - The Baltic Perspective (215 - 218). IOS Press.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "97743740-39c3-5a05-a63b-39c561d463a5",
-    "notes": [
-        "Abstract",
-        "Estonian TimeML Annotated Corpus  (ver 2.0)\n\nThe corpus consists of 80 Estonian newspaper articles (approx. 22,000 word tokens) with manually corrected morphological and dependency syntactic annotations, and with manually added temporal semantic annotations. This corpus is a subcorpus of Estonian Dependency Treebank ( https://github.com/EstSyntax/EDT ).\n\nTemporal semantic annotations are based on an adaption of the TimeML specification ( http://www.timeml.org/ ), and consist of EVENT, TIMEX and TLINK annotations. The creation process of the corpus, along with the evaluation of consistency of annotation is described by Orasmaa (2014a, 2014b).\n\nFormat of the corpus\n\nSee  https://github.com/soras/EstTimeMLCorpus/blob/master/readme.txt  for details.\n\n\nRelated publications\n\nThe creation of this corpus and its first version is described in publications:\n\nS.Orasmaa (2014a). Towards an Integration of Syntactic and Temporal Annotations in Estonian. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14).\n\nS.Orasmaa (2014b). How Availability of Explicit Temporal Cues Affects Manual Temporal Relation Annotation. Human Language Technologies - The Baltic Perspective (215 - 218). IOS Press."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14977542"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "TimeML annotated corpus of Estonian newspaper articles"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/989915d0-4e97-5301-a89e-37f803472f6c.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/989915d0-4e97-5301-a89e-37f803472f6c.json
deleted file mode 100644
index a68bad08..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/989915d0-4e97-5301-a89e-37f803472f6c.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0014EL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14085943",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14085943"
-    ],
-    "PublicationTimestamp": "2018-01-29T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Lippus, P\u00e4rtel"
-    ],
-    "fulltext": "oai:oai.datacite.org:14085943;2019-04-22T17:25:43Z;ESTDOI;ESTDOI.KEEL;Liivi prosoodia korpus;Livonian prosody corpus;Lippus, P\u00e4rtel;Center of Estonian Language Resources;2018;Issued: 2018-01-29;Updated: 2018-01-29;doi:10.15155/1-00-0000-0000-0000-0014EL;Abstract;Korpus koosneb 12 keelejuhi salvestustest, kes loevad liivikeelseid lauseid. Loend koosneb 102st lausest, kus igas lauses on \u00fcks tests\u00f5na osalause l\u00f5pus ja teine tests\u00f5na lause l\u00f5pus. Osa keelejuhte loeb sarnast l\u00e4tikeelset s\u00f5naloendit.\nMaterjal kasutati liivi s\u00f5narposoodia uurimiseks, uurimus on avaldatud: Lehiste, I., Teras, P., Ern\u0161treits, V., Lippus, P., Pajusalu, K., Tuisk, T., & Viitso, T.-R. (2008). Livonian prosody. Helsinki: Suomalais-ugrilainen Seura.\n;Abstract;Recordings from 12 speakers reading 102 Livonian test words embedded in carrier sentences. Most of the speakers read a similar sentence list in Latvian.\nThe data is collected for: Lehiste, I., Teras, P., Ern\u0161treits, V., Lippus, P., Pajusalu, K., Tuisk, T., & Viitso, T.-R. (2008). Livonian prosody. Helsinki: Suomalais-ugrilainen Seura.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "989915d0-4e97-5301-a89e-37f803472f6c",
-    "notes": [
-        "Abstract",
-        "Korpus koosneb 12 keelejuhi salvestustest, kes loevad liivikeelseid lauseid. Loend koosneb 102st lausest, kus igas lauses on \u00fcks tests\u00f5na osalause l\u00f5pus ja teine tests\u00f5na lause l\u00f5pus. Osa keelejuhte loeb sarnast l\u00e4tikeelset s\u00f5naloendit.\nMaterjal kasutati liivi s\u00f5narposoodia uurimiseks, uurimus on avaldatud: Lehiste, I., Teras, P., Ern\u0161treits, V., Lippus, P., Pajusalu, K., Tuisk, T., & Viitso, T.-R. (2008). Livonian prosody. Helsinki: Suomalais-ugrilainen Seura.\n",
-        "Abstract",
-        "Recordings from 12 speakers reading 102 Livonian test words embedded in carrier sentences. Most of the speakers read a similar sentence list in Latvian.\nThe data is collected for: Lehiste, I., Teras, P., Ern\u0161treits, V., Lippus, P., Pajusalu, K., Tuisk, T., & Viitso, T.-R. (2008). Livonian prosody. Helsinki: Suomalais-ugrilainen Seura."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14085943"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Liivi prosoodia korpus",
-        "Livonian prosody corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/99279a6f-0fdc-58f5-9400-e26e29fc6caf.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/99279a6f-0fdc-58f5-9400-e26e29fc6caf.json
deleted file mode 100644
index d0bd7073..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/99279a6f-0fdc-58f5-9400-e26e29fc6caf.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00076L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5757315",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5757315"
-    ],
-    "PublicationTimestamp": "2015-05-22T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Lindstr\u00f6m, Liina"
-    ],
-    "fulltext": "oai:oai.datacite.org:5757315;2019-04-17T17:26:04Z;ESTDOI;ESTDOI.KEEL;Eesti murdekorpus;Estonian Dialect Corpus;Lindstr\u00f6m, Liina;Center of Estonian Language Resources;2013;Issued: 2013-01-09;Updated: 2015-05-22;doi:10.15155/1-00-0000-0000-0000-00076L;Abstract;korpus;Abstract;The dialect corpus consists of:\n\n1)      Dialect recordings. The corpus is based on dialect recordings which have mainly been made in the 1960s and 1970s. The first recordings are even earlier \u2013 they date from 1938. The recordings are traditional dialect recordings where the interview is conducted at the home of the informant.\n\n2)      Phonetically transcribed texts. The traditional Finno-Ugric phonetic transcription is used. The texts are available as Word and pdf files (by the 1st of May 2011, there are about 1,284,000 text words in the corpus).\n\n3)      Dialect texts in simplified transcription. All of the phonetically transcribed texts have been transported one-to-one into the simplified transcription (.txt), which enables the use of these texts with every program and to conduct primary analyses.\n\n4)      Morphologically tagged texts which have been read into a MySQL database. All the word classes and morphological forms are tagged;\n\n5)      Database containing information about informants and recordings;\n\n6)      Syntactically parsed texts (about 40000 text words).\n\nIn the corpus, every phonetically transcribed text is accompanied by a recording, a file in simplified transcription and a description; more than half of the texts are also accompanied by a morphologically tagged file.\n\nAlso some data from other Finnic languages which are spoken around Estonia have been added. The aim is to incorporate at least Votic, Ingrian and Livonian data to the corpus.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "99279a6f-0fdc-58f5-9400-e26e29fc6caf",
-    "notes": [
-        "Abstract",
-        "korpus",
-        "Abstract",
-        "The dialect corpus consists of:\n\n1)      Dialect recordings. The corpus is based on dialect recordings which have mainly been made in the 1960s and 1970s. The first recordings are even earlier \u2013 they date from 1938. The recordings are traditional dialect recordings where the interview is conducted at the home of the informant.\n\n2)      Phonetically transcribed texts. The traditional Finno-Ugric phonetic transcription is used. The texts are available as Word and pdf files (by the 1st of May 2011, there are about 1,284,000 text words in the corpus).\n\n3)      Dialect texts in simplified transcription. All of the phonetically transcribed texts have been transported one-to-one into the simplified transcription (.txt), which enables the use of these texts with every program and to conduct primary analyses.\n\n4)      Morphologically tagged texts which have been read into a MySQL database. All the word classes and morphological forms are tagged;\n\n5)      Database containing information about informants and recordings;\n\n6)      Syntactically parsed texts (about 40000 text words).\n\nIn the corpus, every phonetically transcribed text is accompanied by a recording, a file in simplified transcription and a description; more than half of the texts are also accompanied by a morphologically tagged file.\n\nAlso some data from other Finnic languages which are spoken around Estonia have been added. The aim is to incorporate at least Votic, Ingrian and Livonian data to the corpus."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5757315"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti murdekorpus",
-        "Estonian Dialect Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9965d567-4bec-5236-87ff-44d6442f6219.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9965d567-4bec-5236-87ff-44d6442f6219.json
deleted file mode 100644
index 097f0eb1..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9965d567-4bec-5236-87ff-44d6442f6219.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/EKI.000A",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:4597361",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:4597361"
-    ],
-    "PublicationTimestamp": "2012-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Pajupuu, Hille"
-    ],
-    "fulltext": "oai:oai.datacite.org:4597361;2015-01-09T14:04:54Z;ESTDOI;ESTDOI.KEEL;Estonian Emotional Speech Corpus;Pajupuu, Hille;Center of Estonian Language Resources;2012;doi:10.15155/EKI.000A",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9965d567-4bec-5236-87ff-44d6442f6219",
-    "oai_identifier": [
-        "oai:oai.datacite.org:4597361"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Estonian Emotional Speech Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9ac54afd-6f1f-5f39-a200-d41d43097cf8.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9ac54afd-6f1f-5f39-a200-d41d43097cf8.json
deleted file mode 100644
index 343f3f8b..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9ac54afd-6f1f-5f39-a200-d41d43097cf8.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00074L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5757487",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5757487"
-    ],
-    "PublicationTimestamp": "2019-01-02T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Lippus, P\u00e4rtel"
-    ],
-    "fulltext": "oai:oai.datacite.org:5757487;2019-03-20T07:01:33Z;ESTDOI;ESTDOI.KEEL;Eesti keele spontaanse k\u00f5ne foneetiline korpus v.1.0.0;Phonetic Corpus of Estonian Spontaneous Speech v.1.0.0;Lippus, P\u00e4rtel;Center of Estonian Language Resources;2013;Issued: 2013-01-09;Updated: 2019-01-02;doi:10.15155/1-00-0000-0000-0000-00074L;Abstract;The aim of the corpus is to compile a large amount of quality recordings of spontaneous Estonian and segment it phonetically on different levels. The project started in autumn 2006.\n\nThe total size of the corpus is approximately 60 hours of speech from 100 speakers with different dialectological and social background. Speakers are from different age groups. They are asked to participate with face-to-face invitation and they are aware of the purpose of the recordings.\n\nMost of the recordings are made in a recording studio, some also on fieldwork. The signal of each speaker is recorded in a separate channel. The distance between the speakers is about 3 meters to minimize the effect of overlaps. For the field-work recordings head-set microphones are used. Recordings are saved in PCM wav-format and are not compressed. Background information about the recordings is collected in a text-file.\n    Segmentation and annotation files are saved as Praat TextGrid files and get same filenames as recordings segmented.\n\nSegmentation and annotation\nSegmentation and annotation is done with the Praat program (www.praat.org). Recordings are segmented manually on different levels (automatic segmentation program is also elaborated and tested).\nFollowing tiers are used:\n    -Words (in orthographic spelling), \n    -Phonemes (SAMPA adjusted for Estonian is used for transcription), \n    -Syllables (short \u2013 long, open \u2013 closed), \n    -Prosodic feet,\n    -Intonation phrases or inter-pausal units;\n    -Changes in voice quality (e.g. creaky voice);",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9ac54afd-6f1f-5f39-a200-d41d43097cf8",
-    "notes": [
-        "Abstract",
-        "The aim of the corpus is to compile a large amount of quality recordings of spontaneous Estonian and segment it phonetically on different levels. The project started in autumn 2006.\n\nThe total size of the corpus is approximately 60 hours of speech from 100 speakers with different dialectological and social background. Speakers are from different age groups. They are asked to participate with face-to-face invitation and they are aware of the purpose of the recordings.\n\nMost of the recordings are made in a recording studio, some also on fieldwork. The signal of each speaker is recorded in a separate channel. The distance between the speakers is about 3 meters to minimize the effect of overlaps. For the field-work recordings head-set microphones are used. Recordings are saved in PCM wav-format and are not compressed. Background information about the recordings is collected in a text-file.\n    Segmentation and annotation files are saved as Praat TextGrid files and get same filenames as recordings segmented.\n\nSegmentation and annotation\nSegmentation and annotation is done with the Praat program (www.praat.org). Recordings are segmented manually on different levels (automatic segmentation program is also elaborated and tested).\nFollowing tiers are used:\n    -Words (in orthographic spelling), \n    -Phonemes (SAMPA adjusted for Estonian is used for transcription), \n    -Syllables (short \u2013 long, open \u2013 closed), \n    -Prosodic feet,\n    -Intonation phrases or inter-pausal units;\n    -Changes in voice quality (e.g. creaky voice);"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5757487"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele spontaanse k\u00f5ne foneetiline korpus v.1.0.0",
-        "Phonetic Corpus of Estonian Spontaneous Speech v.1.0.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9b1da1fa-d5a3-503d-8d15-f807dd8daf1b.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9b1da1fa-d5a3-503d-8d15-f807dd8daf1b.json
deleted file mode 100644
index d1aafb39..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9b1da1fa-d5a3-503d-8d15-f807dd8daf1b.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-07BD7L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:19520865",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:19520865"
-    ],
-    "PublicationTimestamp": "2019-04-05T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Soosaar, Sven-Erik"
-    ],
-    "fulltext": "oai:oai.datacite.org:19520865;2019-04-05T10:36:46Z;ESTDOI;ESTDOI.KEEL;Eesti-ersa s\u00f5naraamat;Estonian-Erzya dictionary;Soosaar, Sven-Erik;Center of Estonian Language Resources;2019;Issued: 2019-04-05;Updated: 2019-04-05;doi:10.15155/3-00-0000-0000-0000-07BD7L;Abstract;Eesti-ersa s\u00f5naraamat umbes 6000 m\u00e4rks\u00f5naga ning n\u00e4itefraaside ja -lausetega;Abstract;Estonian-Erzya Mordvin dictionary with example phrases and sentences containing ca 6000 headwords",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9b1da1fa-d5a3-503d-8d15-f807dd8daf1b",
-    "notes": [
-        "Abstract",
-        "Eesti-ersa s\u00f5naraamat umbes 6000 m\u00e4rks\u00f5naga ning n\u00e4itefraaside ja -lausetega",
-        "Abstract",
-        "Estonian-Erzya Mordvin dictionary with example phrases and sentences containing ca 6000 headwords"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:19520865"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti-ersa s\u00f5naraamat",
-        "Estonian-Erzya dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9b22136b-fe92-54e0-9761-f5d407f130e7.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9b22136b-fe92-54e0-9761-f5d407f130e7.json
deleted file mode 100644
index dd494e1d..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9b22136b-fe92-54e0-9761-f5d407f130e7.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00122L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9822136",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9822136"
-    ],
-    "PublicationTimestamp": "2016-11-30T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Tkachenko, Alexander"
-    ],
-    "fulltext": "oai:oai.datacite.org:9822136;2019-02-02T20:32:04Z;ESTDOI;ESTDOI.KEEL;NER-tagger corpus;Tkachenko, Alexander;Center of Estonian Language Resources;2016;Issued: 2016-11-29;Updated: 2016-11-30;doi:10.15155/1-00-0000-0000-0000-00122L;Abstract;NER-tagger corpus represents a collection of sentences with manually labelled named entities. The labelling is partial -- only a selected word from each sentence is labelled. As a result, the labelled entity may be only a part of a named entity and the sentence may potentially contain other named entities.  We distinguish the following types on named entities: PER: person, LOC: location, ORG: organization, FAC: facility, PRD: product, O: other. For each labelled word the label is determined by the largest named entity containing it. For instance, Eesti in the following sentence: \"Eesti \u00dchispanga Tartu kontor oli inimesi t\u00e4is\" is facility although \"Eesti\" is location and \"Eesti \u00dchispank\" is and organisation.     \n\nThe corpus has been created using nertagger web tool: https://github.com/estnltk/ner-tagger. Two human annotators have been involved in the annotation process. \n\nThe data file contains one sentence per line with the following columns:\nname           named entity token\nsentence      sentence\nstart            entity start offset in the sentence\nend             entity end position in the sentence\nlabel            assigned label\nannotator     human annotator id\ntime            number of milliseconds it took annotator to tag a word.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9b22136b-fe92-54e0-9761-f5d407f130e7",
-    "notes": [
-        "Abstract",
-        "NER-tagger corpus represents a collection of sentences with manually labelled named entities. The labelling is partial -- only a selected word from each sentence is labelled. As a result, the labelled entity may be only a part of a named entity and the sentence may potentially contain other named entities.  We distinguish the following types on named entities: PER: person, LOC: location, ORG: organization, FAC: facility, PRD: product, O: other. For each labelled word the label is determined by the largest named entity containing it. For instance, Eesti in the following sentence: \"Eesti \u00dchispanga Tartu kontor oli inimesi t\u00e4is\" is facility although \"Eesti\" is location and \"Eesti \u00dchispank\" is and organisation.     \n\nThe corpus has been created using nertagger web tool: https://github.com/estnltk/ner-tagger. Two human annotators have been involved in the annotation process. \n\nThe data file contains one sentence per line with the following columns:\nname           named entity token\nsentence      sentence\nstart            entity start offset in the sentence\nend             entity end position in the sentence\nlabel            assigned label\nannotator     human annotator id\ntime            number of milliseconds it took annotator to tag a word."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9822136"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "NER-tagger corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9b98b4f6-3dd2-57b1-8466-9c0552b89eb0.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9b98b4f6-3dd2-57b1-8466-9c0552b89eb0.json
deleted file mode 100644
index 83092aa9..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9b98b4f6-3dd2-57b1-8466-9c0552b89eb0.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-0009CL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17958874",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17958874"
-    ],
-    "PublicationTimestamp": "2018-10-10T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laak, Marin",
-        "Saluvere, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:17958874;2019-02-01T00:31:32Z;ESTDOI;ESTDOI.KEEL;Kirjandusajalooline veebikeskkond \"ERNI. Eesti kirjanduslugu tekstides 1924 \u2013 1925\";Web-environment \"ERNI: Estonian Literary History in Texts 1924\u20131925\u201d;Laak, Marin;Saluvere, Tiina;Center of Estonian Language Resources;2018;Issued: 2018-10-10;Updated: 2018-10-10;doi:10.15155/9-00-0000-0000-0000-0009CL;Abstract;ERNI on kirjandusloo \u00f5ppeprogramm, mis esitab materjale 1920. aastate kirjanduselu kohta. ERNI kujutab \u00fcht kirjandusloo peat\u00fckki, eesti kirjanduse 1920. aastaid interaktiivses keskkonnas, tervikliku kirjandusajaloolise ruumina. ERNI sisaldab raamatukogu, kriitikaantoloogiat, fotogaleriid, autorite tutvustusi, kirjanduslike terminite s\u00f5nastikku ja ajatelge. G\u00fcmnaasiumi kirjandustundideks leiab abi k\u00fcsimustikust ja kirjandi\u00f5petusest. Kriitika ajaloo kursust k\u00f5rgkoolis saab elavdada kasutades programmi intertekstuaalse ja retseptsiooniajaloolise tekstide koguna.\n\nERNIs leiduvad tr\u00fckimaterjalid p\u00e4rinevad Eesti Kirjandusmuuseumi Arhiivraamatukogust, kirjanike fotod Kultuuriloolise Arhiivi fotokogust (Vanemuise 42, Tartu). Raamatute kujundused on v\u00f5etud kirjanik Friedebert Tuglasele kuulunud raamatutest, mis asuvad Underi ja Tuglase Kirjanduskeskuse muuseumiosakonnas (V\u00e4ikese-Illimari 12, Tallinn). K\u00f5ik materjalid abimen\u00fc\u00fcdes on koostatud t\u00f6\u00f6r\u00fchma poolt.\n\nProjekti teostamisele eelnenud allikmaterjalide l\u00e4bit\u00f6\u00f6tamine ja uurimine on toimunud Underi ja Tuglase Kirjanduskeskuse Eesti Teadusfondi grantide \"Eesti kirjanduskriitilise m\u00f5tte areng\" I ja II t\u00e4itmise k\u00e4igus (1993\u20131998). \u00d5ppematerjalid on ettevalmistatud Hugo Treffneri G\u00fcmnaasiumi kirjandustundides.\n\nProjekti on teostatud Eesti Kirjandusmuuseumis (1997\u20131998, 2000\u20132001). ERNI on terviklik elektrooniline teos. K\u00f5ik detailid, lehek\u00fcljed ja ka seosed tekstide vahel on sisuliselt p\u00f5hjendatud. Antud ajaloolisele perioodile, eksperimentaalsele 1920. aastate I poolele eriomast atmosf\u00e4\u00e4ri toetab ka kujunduskontseptsioon.\n\n\u00a9 Eesti Kirjandusmuuseum, 2001\n\nProjektijuht, idee autor: Marin Laak\nKujunduskontseptsioon, teostus: Virve Sarapik\n\u00d5ppematerjalide autor: Helgi Tering\n\u00dcldtoimetaja: Piret Viires\n\nT\u00f6\u00f6grupp:\nTiina Saluvere (ajatelg, fotod), Toomas Muru (eesti autorid, v\u00e4lispersonaalia, terminid), Virve Sarapik (fotod, raamatute kujundused, graafika), Marin Laak (eesti autorid, raamatukogu, kriitika), Alo Paistik (teostus), Kristi Metste, Kristina Pai, Katrin Raid (korrektuur), Joel Ilja (arvutiladu) ja Indrek Hein (otsimootor).\nKonsultandid: Rutt Hinrikus, Sirje Olesk, Janika Kronberg ja Enn Lillemets\n\nP\u00f5hiteostaja: \u00dclo Treikelder\n\n\nERNI on k\u00e4ttesaadav:\n\u00b7 Internetis Eesti Kirjandusmuuseumi kodulehek\u00fcljelt http://galerii.kirmus.ee/erni/erni.html\n\u00b7 CD-ROMil \"ERNI. Eesti kirjanduslugu tekstides 1924-1925\" Tiigrih\u00fcppe \u00f5ppematerjalide sarjas (2002)\n\nISBN 9985-9170-7-3",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9b98b4f6-3dd2-57b1-8466-9c0552b89eb0",
-    "notes": [
-        "Abstract",
-        "ERNI on kirjandusloo \u00f5ppeprogramm, mis esitab materjale 1920. aastate kirjanduselu kohta. ERNI kujutab \u00fcht kirjandusloo peat\u00fckki, eesti kirjanduse 1920. aastaid interaktiivses keskkonnas, tervikliku kirjandusajaloolise ruumina. ERNI sisaldab raamatukogu, kriitikaantoloogiat, fotogaleriid, autorite tutvustusi, kirjanduslike terminite s\u00f5nastikku ja ajatelge. G\u00fcmnaasiumi kirjandustundideks leiab abi k\u00fcsimustikust ja kirjandi\u00f5petusest. Kriitika ajaloo kursust k\u00f5rgkoolis saab elavdada kasutades programmi intertekstuaalse ja retseptsiooniajaloolise tekstide koguna.\n\nERNIs leiduvad tr\u00fckimaterjalid p\u00e4rinevad Eesti Kirjandusmuuseumi Arhiivraamatukogust, kirjanike fotod Kultuuriloolise Arhiivi fotokogust (Vanemuise 42, Tartu). Raamatute kujundused on v\u00f5etud kirjanik Friedebert Tuglasele kuulunud raamatutest, mis asuvad Underi ja Tuglase Kirjanduskeskuse muuseumiosakonnas (V\u00e4ikese-Illimari 12, Tallinn). K\u00f5ik materjalid abimen\u00fc\u00fcdes on koostatud t\u00f6\u00f6r\u00fchma poolt.\n\nProjekti teostamisele eelnenud allikmaterjalide l\u00e4bit\u00f6\u00f6tamine ja uurimine on toimunud Underi ja Tuglase Kirjanduskeskuse Eesti Teadusfondi grantide \"Eesti kirjanduskriitilise m\u00f5tte areng\" I ja II t\u00e4itmise k\u00e4igus (1993\u20131998). \u00d5ppematerjalid on ettevalmistatud Hugo Treffneri G\u00fcmnaasiumi kirjandustundides.\n\nProjekti on teostatud Eesti Kirjandusmuuseumis (1997\u20131998, 2000\u20132001). ERNI on terviklik elektrooniline teos. K\u00f5ik detailid, lehek\u00fcljed ja ka seosed tekstide vahel on sisuliselt p\u00f5hjendatud. Antud ajaloolisele perioodile, eksperimentaalsele 1920. aastate I poolele eriomast atmosf\u00e4\u00e4ri toetab ka kujunduskontseptsioon.\n\n\u00a9 Eesti Kirjandusmuuseum, 2001\n\nProjektijuht, idee autor: Marin Laak\nKujunduskontseptsioon, teostus: Virve Sarapik\n\u00d5ppematerjalide autor: Helgi Tering\n\u00dcldtoimetaja: Piret Viires\n\nT\u00f6\u00f6grupp:\nTiina Saluvere (ajatelg, fotod), Toomas Muru (eesti autorid, v\u00e4lispersonaalia, terminid), Virve Sarapik (fotod, raamatute kujundused, graafika), Marin Laak (eesti autorid, raamatukogu, kriitika), Alo Paistik (teostus), Kristi Metste, Kristina Pai, Katrin Raid (korrektuur), Joel Ilja (arvutiladu) ja Indrek Hein (otsimootor).\nKonsultandid: Rutt Hinrikus, Sirje Olesk, Janika Kronberg ja Enn Lillemets\n\nP\u00f5hiteostaja: \u00dclo Treikelder\n\n\nERNI on k\u00e4ttesaadav:\n\u00b7 Internetis Eesti Kirjandusmuuseumi kodulehek\u00fcljelt http://galerii.kirmus.ee/erni/erni.html\n\u00b7 CD-ROMil \"ERNI. Eesti kirjanduslugu tekstides 1924-1925\" Tiigrih\u00fcppe \u00f5ppematerjalide sarjas (2002)\n\nISBN 9985-9170-7-3"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17958874"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Kirjandusajalooline veebikeskkond \"ERNI. Eesti kirjanduslugu tekstides 1924 \u2013 1925\"",
-        "Web-environment \"ERNI: Estonian Literary History in Texts 1924\u20131925\u201d"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9c858750-184f-5fbe-834d-9215361bbb86.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9c858750-184f-5fbe-834d-9215361bbb86.json
deleted file mode 100644
index 27072a62..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9c858750-184f-5fbe-834d-9215361bbb86.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05B55L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9352880",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9352880"
-    ],
-    "PublicationTimestamp": "2017-04-11T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek",
-        "Vare, Silvi"
-    ],
-    "fulltext": "oai:oai.datacite.org:9352880;2019-03-29T22:31:55Z;ESTDOI;ESTDOI.KEEL;Eesti keele s\u00f5napered;The Estonian Word Families;Hein, Indrek;Vare, Silvi;Center of Estonian Language Resources;2016;Issued: 2016-10-30;Updated: 2017-04-11;doi:10.15155/3-00-0000-0000-0000-05B55L;Abstract;Esimene eesti keele s\u00f5naperede s\u00f5naraamat, kust saab p\u00f5hjaliku \u00fclevaate eesti keele rikkalikust s\u00f5namoodustusest \u2013 kirjeldatud on ligikaudu 120 000 s\u00f5na ehitust ja s\u00f5nadevahelisi moodustusseoseid. Seoste alusel on s\u00f5nad koondatud ligi 9000 s\u00f5napereks. S\u00f5napere koondab kokku k\u00f5ik need s\u00f5nad, mis on \u00fcksteisest moodustatud, milles kordub \u00fcks \u00fchine t\u00fcvi, mis seob k\u00f5iki s\u00f5napere liikmeid.;Abstract;The first Estonian dictionary of word families; it provides a comprehensive view of the riches of Estonian word formation, describing the structure and formative relations of ca 120,000 Estonian words. Based of the formative relations, the words make up nearly 9000 word families. A word family consists of all the words that are linked by formative processes and share one and the same word stem.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9c858750-184f-5fbe-834d-9215361bbb86",
-    "notes": [
-        "Abstract",
-        "Esimene eesti keele s\u00f5naperede s\u00f5naraamat, kust saab p\u00f5hjaliku \u00fclevaate eesti keele rikkalikust s\u00f5namoodustusest \u2013 kirjeldatud on ligikaudu 120 000 s\u00f5na ehitust ja s\u00f5nadevahelisi moodustusseoseid. Seoste alusel on s\u00f5nad koondatud ligi 9000 s\u00f5napereks. S\u00f5napere koondab kokku k\u00f5ik need s\u00f5nad, mis on \u00fcksteisest moodustatud, milles kordub \u00fcks \u00fchine t\u00fcvi, mis seob k\u00f5iki s\u00f5napere liikmeid.",
-        "Abstract",
-        "The first Estonian dictionary of word families; it provides a comprehensive view of the riches of Estonian word formation, describing the structure and formative relations of ca 120,000 Estonian words. Based of the formative relations, the words make up nearly 9000 word families. A word family consists of all the words that are linked by formative processes and share one and the same word stem."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9352880"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele s\u00f5napered",
-        "The Estonian Word Families"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9d098e87-13f4-50ae-8d5b-7d0fb236a03b.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9d098e87-13f4-50ae-8d5b-7d0fb236a03b.json
deleted file mode 100644
index 023ec8f8..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9d098e87-13f4-50ae-8d5b-7d0fb236a03b.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-071F2L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14560527",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14560527"
-    ],
-    "PublicationTimestamp": "2018-03-26T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Koppel, Kristina",
-        "Kallas, Jelena"
-    ],
-    "fulltext": "oai:oai.datacite.org:14560527;2019-04-03T20:01:13Z;ESTDOI;ESTDOI.KEEL;EtLex: eesti keele eri keeleoskustasemete s\u00f5navara ja teksti leksikaalse keerukuse hindamise t\u00f6\u00f6riist;Kallas, Jelena;Koppel, Kristina;Center of Estonian Language Resources;2018;Issued: 2018-03-26;Updated: 2018-03-26;doi:10.15155/3-00-0000-0000-0000-071F2L;Abstract;EtLex on Eesti Keele Instituudis Haridus- ja Teadusministeeriumi Digip\u00f6\u00f6rde programmi (vt https://www.hm.ee/et/digipoorde-programm) toel loodud t\u00f6\u00f6riist, mis v\u00f5imaldab automaatselt anal\u00fc\u00fcsida, mis keeleoskustaseme s\u00f5navara tekst sisaldab.\nKeeleoskustasemete m\u00e4\u00e4ramisel on aluseks Euroopa keele\u00f5ppe raamdokumendis (Common European Framework of Reference for Languages: Learning, Teaching, Assessment, CEFR) kirjeldatud keeleoskustasemed, mille kohaselt eristatakse kolme \u00fcldist taset (A-, B- ja C-tase) ja kuut alajaotust (A1-, A2-, B1-, B2-, C1-, C2-tase) (RT I 2009, 4, 26).\nEtLexi t\u00f6\u00f6riist anal\u00fc\u00fcsib tekste eesti keele A1\u2012C1 aktiivse ja passiivse s\u00f5navara loendite p\u00f5hjal. Kokku on EtLexis m\u00e4\u00e4ratud ca 13 000 s\u00f5na tasemekohasust.\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9d098e87-13f4-50ae-8d5b-7d0fb236a03b",
-    "notes": [
-        "Abstract",
-        "EtLex on Eesti Keele Instituudis Haridus- ja Teadusministeeriumi Digip\u00f6\u00f6rde programmi (vt https://www.hm.ee/et/digipoorde-programm) toel loodud t\u00f6\u00f6riist, mis v\u00f5imaldab automaatselt anal\u00fc\u00fcsida, mis keeleoskustaseme s\u00f5navara tekst sisaldab.\nKeeleoskustasemete m\u00e4\u00e4ramisel on aluseks Euroopa keele\u00f5ppe raamdokumendis (Common European Framework of Reference for Languages: Learning, Teaching, Assessment, CEFR) kirjeldatud keeleoskustasemed, mille kohaselt eristatakse kolme \u00fcldist taset (A-, B- ja C-tase) ja kuut alajaotust (A1-, A2-, B1-, B2-, C1-, C2-tase) (RT I 2009, 4, 26).\nEtLexi t\u00f6\u00f6riist anal\u00fc\u00fcsib tekste eesti keele A1\u2012C1 aktiivse ja passiivse s\u00f5navara loendite p\u00f5hjal. Kokku on EtLexis m\u00e4\u00e4ratud ca 13 000 s\u00f5na tasemekohasust.\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14560527"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "EtLex: eesti keele eri keeleoskustasemete s\u00f5navara ja teksti leksikaalse keerukuse hindamise t\u00f6\u00f6riist"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9d2fc089-5df7-5459-a90e-012b30af0c38.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9d2fc089-5df7-5459-a90e-012b30af0c38.json
deleted file mode 100644
index 342ee512..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9d2fc089-5df7-5459-a90e-012b30af0c38.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05B4AL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9352868",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9352868"
-    ],
-    "PublicationTimestamp": "2016-10-31T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek",
-        "Langemets, Margit"
-    ],
-    "fulltext": "oai:oai.datacite.org:9352868;2019-04-03T23:32:19Z;ESTDOI;ESTDOI.KEEL;Eesti-l\u00e4ti s\u00f5naraamat;Hein, Indrek;Langemets, Margit;Center of Estonian Language Resources;2016;Issued: 2016-10-31;Updated: 2016-10-31;doi:10.15155/3-00-0000-0000-0000-05B4AL;Abstract;Kahesuunaline l\u00e4ti-eesti s\u00f5naraamat, mis sisaldab ligi 47 000 m\u00e4rks\u00f5naartiklit. ",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9d2fc089-5df7-5459-a90e-012b30af0c38",
-    "notes": [
-        "Abstract",
-        "Kahesuunaline l\u00e4ti-eesti s\u00f5naraamat, mis sisaldab ligi 47 000 m\u00e4rks\u00f5naartiklit. "
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9352868"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti-l\u00e4ti s\u00f5naraamat"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9dfb0139-89f6-54fd-af2b-f5b457387d7a.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9dfb0139-89f6-54fd-af2b-f5b457387d7a.json
deleted file mode 100644
index 6238b642..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9dfb0139-89f6-54fd-af2b-f5b457387d7a.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05770L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:8521721",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:8521721"
-    ],
-    "PublicationTimestamp": "2017-04-11T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Langemets, Margit"
-    ],
-    "fulltext": "oai:oai.datacite.org:8521721;2019-03-31T12:02:44Z;ESTDOI;ESTDOI.KEEL;Eesti et\u00fcmoloogias\u00f5naraamat;The Estonian Etymological Dictionary;Langemets, Margit;Center of Estonian Language Resources;2015;Issued: 2015-04-29;Updated: 2017-04-11;doi:10.15155/3-00-0000-0000-0000-05770L;Abstract;2012. aastal ilmunud \u201eEesti et\u00fcmoloogias\u00f5naraamatu\u201c elektrooniline versioon. Sisaldab teavet eesti keele s\u00f5nat\u00fcvede p\u00e4ritolu ja s\u00f5nade omavaheliste p\u00e4ritoluseoste kohta (laenud, omat\u00fcved, tehist\u00fcved jm). Sisaldab \u201e\u00d5S 2006\u201c s\u00f5nat\u00fcvede et\u00fcmoloogiaid (v.a v\u00f5\u00f5rs\u00f5nat\u00fcved).;Abstract;Contains information on the origin of Estonian word stems and the genetic links between words (loanwords, genuine stems, artificially coined stems etc).",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9dfb0139-89f6-54fd-af2b-f5b457387d7a",
-    "notes": [
-        "Abstract",
-        "2012. aastal ilmunud \u201eEesti et\u00fcmoloogias\u00f5naraamatu\u201c elektrooniline versioon. Sisaldab teavet eesti keele s\u00f5nat\u00fcvede p\u00e4ritolu ja s\u00f5nade omavaheliste p\u00e4ritoluseoste kohta (laenud, omat\u00fcved, tehist\u00fcved jm). Sisaldab \u201e\u00d5S 2006\u201c s\u00f5nat\u00fcvede et\u00fcmoloogiaid (v.a v\u00f5\u00f5rs\u00f5nat\u00fcved).",
-        "Abstract",
-        "Contains information on the origin of Estonian word stems and the genetic links between words (loanwords, genuine stems, artificially coined stems etc)."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:8521721"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti et\u00fcmoloogias\u00f5naraamat",
-        "The Estonian Etymological Dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9f564ca8-a2db-5729-8972-64d01938d7d4.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9f564ca8-a2db-5729-8972-64d01938d7d4.json
deleted file mode 100644
index 16a6bc3c..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/9f564ca8-a2db-5729-8972-64d01938d7d4.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0017CL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17945634",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17945634"
-    ],
-    "PublicationTimestamp": "2019-01-03T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:17945634;2019-02-05T18:25:43Z;ESTDOI;ESTDOI.KEEL;Sageduss\u00f5nastik 2.0;Estonian Frequency Dictionary ver. 2.0;Muischnek, Kadri;Center of Estonian Language Resources;2019;Issued: 2019-01-03;Updated: 2019-01-03;doi:10.15155/1-00-0000-0000-0000-0017CL;Abstract;Sagedusloend on koostatud statistilise \u00fchestajaga t3mesta morfoloogiliselt \u00fchestatud ning seej\u00e4rel reeglip\u00f5hise meetodiga j\u00e4rel\u00fchestatud Tasakaalus korpuse p\u00f5hjal. Korpuse koostisosadeks on: 5 miljonit s\u00f5na ajalehetekste, 5 miljonit s\u00f5na ilukirjandust, 5 miljonit s\u00f5na teadustekste.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "9f564ca8-a2db-5729-8972-64d01938d7d4",
-    "notes": [
-        "Abstract",
-        "Sagedusloend on koostatud statistilise \u00fchestajaga t3mesta morfoloogiliselt \u00fchestatud ning seej\u00e4rel reeglip\u00f5hise meetodiga j\u00e4rel\u00fchestatud Tasakaalus korpuse p\u00f5hjal. Korpuse koostisosadeks on: 5 miljonit s\u00f5na ajalehetekste, 5 miljonit s\u00f5na ilukirjandust, 5 miljonit s\u00f5na teadustekste."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17945634"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Sageduss\u00f5nastik 2.0",
-        "Estonian Frequency Dictionary ver. 2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a12f499d-6d7d-5c12-9078-fe83f1d51c7b.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a12f499d-6d7d-5c12-9078-fe83f1d51c7b.json
deleted file mode 100644
index f862e7b1..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a12f499d-6d7d-5c12-9078-fe83f1d51c7b.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0018DL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17962500",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17962500"
-    ],
-    "PublicationTimestamp": "2019-01-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Sirel, Raul"
-    ],
-    "fulltext": "oai:oai.datacite.org:17962500;2019-04-04T19:02:22Z;ESTDOI;ESTDOI.KEEL;TEXTA Toolkit;Sirel, Raul;Center of Estonian Language Resources;2019;Issued: 2019-01-07;Updated: 2019-01-07;doi:10.15155/1-00-0000-0000-0000-0018DL;Abstract;TEXTA Toolkit on eraldiseisev tarkvara, mis v\u00f5imaldab tekstikorpustest ekstraheerida korpuses esindatud valdkonnale omast oskuss\u00f5navara, koostada selle alusel m\u00f5istep\u00f5hiseid terminoloogilisi ressursse, tuvastada tekstidokumentidest m\u00f5istetele viitavaid tekstifragmente ning visualiseerida tulemusi andmestikus leiduvate andmev\u00e4ljade l\u00f5ikes. Valdkondliku terminikasutuse kirjeldamiseks kasutatakse tarkvara koosseisus erinevaid juhendamata masin\u00f5ppe meetodeid, sh tehisneurov\u00f5rkudel p\u00f5hinevaid loomuliku keele vektormudeleid.;Abstract;Terminology EXtraction and Text Analytics (TEXTA) Toolkit is a program that provides resources for analysing free text datasets. It includes the tools, which are necessary for the text analytics or solutions based on the latter. TEXTA enables fast searches and analyses from texts, to classify documents and extract information from them. The content of toolkit can be configured according to the needs of the customer and is accessible as a cloud service or installed to the customer\u2019s infrastructure. The toolkit contains the following applications: searcher, multiword expression miner, base lexicon miner, conceptualizer, grammar miner, classifier.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a12f499d-6d7d-5c12-9078-fe83f1d51c7b",
-    "notes": [
-        "Abstract",
-        "TEXTA Toolkit on eraldiseisev tarkvara, mis v\u00f5imaldab tekstikorpustest ekstraheerida korpuses esindatud valdkonnale omast oskuss\u00f5navara, koostada selle alusel m\u00f5istep\u00f5hiseid terminoloogilisi ressursse, tuvastada tekstidokumentidest m\u00f5istetele viitavaid tekstifragmente ning visualiseerida tulemusi andmestikus leiduvate andmev\u00e4ljade l\u00f5ikes. Valdkondliku terminikasutuse kirjeldamiseks kasutatakse tarkvara koosseisus erinevaid juhendamata masin\u00f5ppe meetodeid, sh tehisneurov\u00f5rkudel p\u00f5hinevaid loomuliku keele vektormudeleid.",
-        "Abstract",
-        "Terminology EXtraction and Text Analytics (TEXTA) Toolkit is a program that provides resources for analysing free text datasets. It includes the tools, which are necessary for the text analytics or solutions based on the latter. TEXTA enables fast searches and analyses from texts, to classify documents and extract information from them. The content of toolkit can be configured according to the needs of the customer and is accessible as a cloud service or installed to the customer\u2019s infrastructure. The toolkit contains the following applications: searcher, multiword expression miner, base lexicon miner, conceptualizer, grammar miner, classifier."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17962500"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "TEXTA Toolkit"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a14ee0b2-6c92-55d1-84a6-cddbd52ecfc7.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a14ee0b2-6c92-55d1-84a6-cddbd52ecfc7.json
deleted file mode 100644
index c32bb07d..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a14ee0b2-6c92-55d1-84a6-cddbd52ecfc7.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-000A0L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17968025",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17968025"
-    ],
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Valdre, Eola"
-    ],
-    "fulltext": "oai:oai.datacite.org:17968025;2019-02-02T07:01:57Z;ESTDOI;ESTDOI.KEEL;Meditsiini \u00f5ppematerjalide korpus;Valdre, Eola;Center of Estonian Language Resources;2019;Issued: 2019-01-08;Updated: 2019-01-08;doi:10.15155/9-00-0000-0000-0000-000A0L;Abstract;Korpuses on 65 719 s\u00f5net 2455 loenguslaidilt; kasutatud on T\u00dc arstiteaduskonna III kursuse radioloogialoenguid ja VI kursuse kliinilise radioloogia loenguid (\u00f5ppeained ARHO.01.033 ja ARHO.002.009), luba selleks on saadud radioloogiakliiniku juhatajalt dr P. Ilveselt.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a14ee0b2-6c92-55d1-84a6-cddbd52ecfc7",
-    "notes": [
-        "Abstract",
-        "Korpuses on 65 719 s\u00f5net 2455 loenguslaidilt; kasutatud on T\u00dc arstiteaduskonna III kursuse radioloogialoenguid ja VI kursuse kliinilise radioloogia loenguid (\u00f5ppeained ARHO.01.033 ja ARHO.002.009), luba selleks on saadud radioloogiakliiniku juhatajalt dr P. Ilveselt."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17968025"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Meditsiini \u00f5ppematerjalide korpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a1c563e5-8dec-5200-99aa-6ef6d94f95e1.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a1c563e5-8dec-5200-99aa-6ef6d94f95e1.json
deleted file mode 100644
index cdaaca3f..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a1c563e5-8dec-5200-99aa-6ef6d94f95e1.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-00027L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5757497",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5757497"
-    ],
-    "PublicationTimestamp": "2019-01-06T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Alum\u00e4e, Tanel"
-    ],
-    "fulltext": "oai:oai.datacite.org:5757497;2019-04-16T17:36:45Z;ESTDOI;ESTDOI.KEEL;Reaalajalise k\u00f5netuvastuse server;Real-time speech recognition web service;Alum\u00e4e, Tanel;Center of Estonian Language Resources;2014;Issued: 2014-12-30;Updated: 2019-01-06;doi:10.15155/9-00-0000-0000-0000-00027L;Abstract;Real-time speech recognition web service for Estonian.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a1c563e5-8dec-5200-99aa-6ef6d94f95e1",
-    "notes": [
-        "Abstract",
-        "Real-time speech recognition web service for Estonian."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5757497"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Reaalajalise k\u00f5netuvastuse server",
-        "Real-time speech recognition web service"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a1caded6-2752-55d3-ae3d-918313045648.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a1caded6-2752-55d3-ae3d-918313045648.json
deleted file mode 100644
index 5a4375b1..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a1caded6-2752-55d3-ae3d-918313045648.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05BD6L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9474536",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9474536"
-    ],
-    "PublicationTimestamp": "2017-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Ermus, Liis"
-    ],
-    "fulltext": "oai:oai.datacite.org:9474536;2019-04-17T17:26:20Z;ESTDOI;ESTDOI.KEEL;Eesti Keele Instituudi eesti murrete ja soome-ugri keelte arhiiv EMSUKA;The Archive of Estonian Dialects and Finno-Ugric Languages (EMSUKA) of the Institute of the Estonian Language;Ermus, Liis;Center of Estonian Language Resources;2016;Issued: 2016-11-13;Updated: 2017-02-15;doi:10.15155/3-00-0000-0000-0000-05BD6L;Abstract;Eesti Keele Instituudi eesti murrete ja soome-ugri keelte arhiiv on maailma suurim eesti murdekeelt kajastav kogu. Arhiivis leidub nii salvestatud kui ka kirja pandud materjale eesti murrete, soome-ugri keelte ja v\u00e4liseesti keele kohta. ;Abstract;This is the world\u00b4s biggest collection of Estonian dialect usage. It contains sound recordings as well as written records of Estonian dialects, Finno-Ugric languages and expatriate Estonian.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a1caded6-2752-55d3-ae3d-918313045648",
-    "notes": [
-        "Abstract",
-        "Eesti Keele Instituudi eesti murrete ja soome-ugri keelte arhiiv on maailma suurim eesti murdekeelt kajastav kogu. Arhiivis leidub nii salvestatud kui ka kirja pandud materjale eesti murrete, soome-ugri keelte ja v\u00e4liseesti keele kohta. ",
-        "Abstract",
-        "This is the world\u00b4s biggest collection of Estonian dialect usage. It contains sound recordings as well as written records of Estonian dialects, Finno-Ugric languages and expatriate Estonian."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9474536"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti Keele Instituudi eesti murrete ja soome-ugri keelte arhiiv EMSUKA",
-        "The Archive of Estonian Dialects and Finno-Ugric Languages (EMSUKA) of the Institute of the Estonian Language"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a404e283-2ab5-5fa6-909d-9a7aa050da75.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a404e283-2ab5-5fa6-909d-9a7aa050da75.json
deleted file mode 100644
index 1c55cfaa..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a404e283-2ab5-5fa6-909d-9a7aa050da75.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-0002DL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5772670",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5772670"
-    ],
-    "PublicationTimestamp": "2015-06-04T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "J\u00fcrviste, Madis"
-    ],
-    "fulltext": "oai:oai.datacite.org:5772670;2019-04-04T09:33:06Z;ESTDOI;ESTDOI.KEEL;Suur eesti-prantsuse s\u00f5naraamat;Grand dictionnaire estonien-fran\u00e7ais;Comprehensive Estonian-French Dictionary;J\u00fcrviste, Madis;Center of Estonian Language Resources;2015;Issued: 2015-05-07;Updated: 2015-06-04;doi:10.15155/9-00-0000-0000-0000-0002DL;Abstract;A comprehensive bilingual general language translation dictionary (work in progress).",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a404e283-2ab5-5fa6-909d-9a7aa050da75",
-    "notes": [
-        "Abstract",
-        "A comprehensive bilingual general language translation dictionary (work in progress)."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5772670"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Suur eesti-prantsuse s\u00f5naraamat",
-        "Grand dictionnaire estonien-fran\u00e7ais",
-        "Comprehensive Estonian-French Dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a524d664-4b0d-58b2-b59c-33f31219e1b3.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a524d664-4b0d-58b2-b59c-33f31219e1b3.json
deleted file mode 100644
index 910da2e1..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a524d664-4b0d-58b2-b59c-33f31219e1b3.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-0002EL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:6073497",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:6073497"
-    ],
-    "PublicationTimestamp": "2015-06-03T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "J\u00fcrviste, Madis"
-    ],
-    "fulltext": "oai:oai.datacite.org:6073497;2019-04-06T22:02:14Z;ESTDOI;ESTDOI.KEEL;Eesti-prantsuse paralleelkorpus;Corpus parallel estonien-fran\u00e7ais;Estonian-French Parallel Corpus;J\u00fcrviste, Madis;Center of Estonian Language Resources;2015;Issued: 2015-06-03;Updated: 2015-06-03;doi:10.15155/9-00-0000-0000-0000-0002EL;Abstract;Aligned parallel translation corpus containing 65 million words (including both languages).",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a524d664-4b0d-58b2-b59c-33f31219e1b3",
-    "notes": [
-        "Abstract",
-        "Aligned parallel translation corpus containing 65 million words (including both languages)."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:6073497"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti-prantsuse paralleelkorpus",
-        "Corpus parallel estonien-fran\u00e7ais",
-        "Estonian-French Parallel Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a567e44d-11b1-5e4f-97d3-2962c1219ee7.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a567e44d-11b1-5e4f-97d3-2962c1219ee7.json
deleted file mode 100644
index 0ba0777d..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a567e44d-11b1-5e4f-97d3-2962c1219ee7.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0007CL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5756923",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5756923"
-    ],
-    "PublicationTimestamp": "2015-05-22T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:5756923;2019-02-14T18:25:40Z;ESTDOI;ESTDOI.KEEL;Eesti ajakirjanduse korpus;Corpus of Estonian newspaper texts;Muischnek, Kadri;Center of Estonian Language Resources;2013;Issued: 2013-01-07;Updated: 2015-05-22;doi:10.15155/1-00-0000-0000-0000-0007CL;Abstract;Korpus sisaldab eesti ajalehti, 182 miljonit s\u00f5na. TEI P5 XML m\u00e4rgendus, UTF8 kodeering.;Abstract;Corpus of Estonian newspaper texts, 182 million words\nMarkup: TEI P5 XML\nEncoding: UTF8",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a567e44d-11b1-5e4f-97d3-2962c1219ee7",
-    "notes": [
-        "Abstract",
-        "Korpus sisaldab eesti ajalehti, 182 miljonit s\u00f5na. TEI P5 XML m\u00e4rgendus, UTF8 kodeering.",
-        "Abstract",
-        "Corpus of Estonian newspaper texts, 182 million words\nMarkup: TEI P5 XML\nEncoding: UTF8"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5756923"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti ajakirjanduse korpus",
-        "Corpus of Estonian newspaper texts"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a56a1e14-dee9-512c-985f-427f0f6c54e9.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a56a1e14-dee9-512c-985f-427f0f6c54e9.json
deleted file mode 100644
index 350b51ac..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a56a1e14-dee9-512c-985f-427f0f6c54e9.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00087L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5755365",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5755365"
-    ],
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Orav, Heili"
-    ],
-    "fulltext": "oai:oai.datacite.org:5755365;2019-04-18T17:36:43Z;ESTDOI;ESTDOI.KEEL;Estonian Wordnet (kb71-STABLE);Orav, Heili;Center of Estonian Language Resources;2014;Issued: 2014-03-21;Updated: 2019-01-08;doi:10.15155/1-00-0000-0000-0000-00087L;Abstract; Eesti Wordnetis (versioon 71) on praeguse seisuga (veebruar 2015) u 73 000 m\u00f5istet, milles s\u00f5nu u 98 700, semantilisi suhteid \u00fcle 230 000 ja ingliskeelseid suhteid \u00fcle 105 000.  K\u00f5ik m\u00f5isted on varustatud v\u00e4hemalt \u00fche keelesisese suhtega ja v\u00e4hemalt \u00fche ILI-suhtega.;Abstract;The atom of a wordnet-type thesaurus is a synonym set (also called a synset), which is a set containing all the synonymous words or multi-word units that express the same concept. All words in a synset belong into the same part of speech.\n\nTHIS IS STABLE VERSION",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a56a1e14-dee9-512c-985f-427f0f6c54e9",
-    "notes": [
-        "Abstract",
-        " Eesti Wordnetis (versioon 71) on praeguse seisuga (veebruar 2015) u 73 000 m\u00f5istet, milles s\u00f5nu u 98 700, semantilisi suhteid \u00fcle 230 000 ja ingliskeelseid suhteid \u00fcle 105 000.  K\u00f5ik m\u00f5isted on varustatud v\u00e4hemalt \u00fche keelesisese suhtega ja v\u00e4hemalt \u00fche ILI-suhtega.",
-        "Abstract",
-        "The atom of a wordnet-type thesaurus is a synonym set (also called a synset), which is a set containing all the synonymous words or multi-word units that express the same concept. All words in a synset belong into the same part of speech.\n\nTHIS IS STABLE VERSION"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5755365"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Estonian Wordnet (kb71-STABLE)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a5d87367-bda6-5d2d-bc97-db1d6e3c22ba.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a5d87367-bda6-5d2d-bc97-db1d6e3c22ba.json
deleted file mode 100644
index 5ded49fe..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a5d87367-bda6-5d2d-bc97-db1d6e3c22ba.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06343L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10304165",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10304165"
-    ],
-    "PublicationTimestamp": "2017-01-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Soon, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:10304165;2019-01-19T06:32:46Z;ESTDOI;ESTDOI.KEEL;ESTERM;ESTERM;Soon, Tiina;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2017-01-31;doi:10.15155/3-00-0000-0000-0000-06343L;Abstract;ESTERM on mitmekeelne t\u00f5lkep\u00f5hine terminibaas, mille terminid on p\u00e4rit Eesti \u00d5igust\u00f5lke Keskuses t\u00f5lgitud Euroopa Liidu ja Eesti Vabariigi \u00f5igusaktidest",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a5d87367-bda6-5d2d-bc97-db1d6e3c22ba",
-    "notes": [
-        "Abstract",
-        "ESTERM on mitmekeelne t\u00f5lkep\u00f5hine terminibaas, mille terminid on p\u00e4rit Eesti \u00d5igust\u00f5lke Keskuses t\u00f5lgitud Euroopa Liidu ja Eesti Vabariigi \u00f5igusaktidest"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10304165"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "ESTERM",
-        "ESTERM"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a5e3c71a-0591-598a-8659-0f656887093f.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a5e3c71a-0591-598a-8659-0f656887093f.json
deleted file mode 100644
index bd471ecf..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a5e3c71a-0591-598a-8659-0f656887093f.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-0632CL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10303698",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10303698"
-    ],
-    "PublicationTimestamp": "2017-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Ermus, Liis"
-    ],
-    "fulltext": "oai:oai.datacite.org:10303698;2019-01-20T07:32:20Z;ESTDOI;ESTDOI.KEEL;Eesti Keele Instituudi fonoteek;Recordings Library of the Institute of the Estonian Language;Ermus, Liis;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2017-02-15;doi:10.15155/3-00-0000-0000-0000-0632CL;Abstract;Eesti Keele Instituudi fonoteegi lehek\u00fcljel saab kuulata eesti murrete, soome-ugri keelte ja v\u00e4liseesti keele helin\u00e4iteid.;Abstract;The website of the Recordings Library offers audio samples of sound recordings of Estonian dialects, Finno-Ugric languages and expatriate Estonian.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a5e3c71a-0591-598a-8659-0f656887093f",
-    "notes": [
-        "Abstract",
-        "Eesti Keele Instituudi fonoteegi lehek\u00fcljel saab kuulata eesti murrete, soome-ugri keelte ja v\u00e4liseesti keele helin\u00e4iteid.",
-        "Abstract",
-        "The website of the Recordings Library offers audio samples of sound recordings of Estonian dialects, Finno-Ugric languages and expatriate Estonian."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10303698"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti Keele Instituudi fonoteek",
-        "Recordings Library of the Institute of the Estonian Language"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a60f4f42-ef42-5bc2-947e-86f012586e1b.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a60f4f42-ef42-5bc2-947e-86f012586e1b.json
deleted file mode 100644
index 8c210595..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a60f4f42-ef42-5bc2-947e-86f012586e1b.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00177L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17944983",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17944983"
-    ],
-    "PublicationTimestamp": "2019-01-03T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:17944983;2019-02-02T12:00:44Z;ESTDOI;ESTDOI.KEEL;Nime- ja numbri\u00fcksuste tuvastaja;Muischnek, Kadri;Center of Estonian Language Resources;2019;Issued: 2019-01-03;Updated: 2019-01-03;doi:10.15155/1-00-0000-0000-0000-00177L;Abstract;Semantilise anal\u00fc\u00fcsi moodul leiab tekstis nime- ja numbri\u00fcksused",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a60f4f42-ef42-5bc2-947e-86f012586e1b",
-    "notes": [
-        "Abstract",
-        "Semantilise anal\u00fc\u00fcsi moodul leiab tekstis nime- ja numbri\u00fcksused"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17944983"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Nime- ja numbri\u00fcksuste tuvastaja"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a6416b63-414d-5729-af19-79c4aa50956d.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a6416b63-414d-5729-af19-79c4aa50956d.json
deleted file mode 100644
index fc4940eb..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a6416b63-414d-5729-af19-79c4aa50956d.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05AF5L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9310576",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9310576"
-    ],
-    "PublicationTimestamp": "2017-04-11T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Paet, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:9310576;2019-04-22T18:00:55Z;ESTDOI;ESTDOI.KEEL;Ametniku soovituss\u00f5nastik;The Advisory Dictionary of Document Language;Paet, Tiina;Center of Estonian Language Resources;2016;Issued: 2016-10-19;Updated: 2017-04-11;doi:10.15155/3-00-0000-0000-0000-05AF5L;Abstract;S\u00f5nastik k\u00f5igile neile, kellel on vaja kirjutada ametliku sisuga kirjakeelset teksti. S\u00f5nastik pakub n\u00f5uandeid ja soovitusi, kuidas v\u00e4ljenduda lihtsamalt, selgemalt ja t\u00e4psemalt.;Abstract;A good helper for anyone who needs to write an official Estonian text. There are a lot of tips and recommendations for simple, plain and precise expression.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a6416b63-414d-5729-af19-79c4aa50956d",
-    "notes": [
-        "Abstract",
-        "S\u00f5nastik k\u00f5igile neile, kellel on vaja kirjutada ametliku sisuga kirjakeelset teksti. S\u00f5nastik pakub n\u00f5uandeid ja soovitusi, kuidas v\u00e4ljenduda lihtsamalt, selgemalt ja t\u00e4psemalt.",
-        "Abstract",
-        "A good helper for anyone who needs to write an official Estonian text. There are a lot of tips and recommendations for simple, plain and precise expression."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9310576"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Ametniku soovituss\u00f5nastik",
-        "The Advisory Dictionary of Document Language"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a64ae4ba-3a9b-5cfc-810b-490ced5a2328.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a64ae4ba-3a9b-5cfc-810b-490ced5a2328.json
deleted file mode 100644
index 71809c98..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a64ae4ba-3a9b-5cfc-810b-490ced5a2328.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05B51L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9352875",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9352875"
-    ],
-    "PublicationTimestamp": "2017-03-03T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laansalu, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:9352875;2019-02-15T18:37:49Z;ESTDOI;ESTDOI.KEEL;Hiiu s\u00f5naraamat;The Dictionary of the Hiiu Dialect;Laansalu, Tiina;Center of Estonian Language Resources;2016;Issued: 2016-10-31;Updated: 2017-03-03;doi:10.15155/3-00-0000-0000-0000-05B51L;Abstract;S\u00f5nastik kuulub Eesti Keele Instituudi v\u00e4ikeste murdes\u00f5nastike sarja ja on maailma esimene hiiu keele s\u00f5naraamat. See sisaldab 6300 m\u00e4rks\u00f5na ning esitab hiiu keele p\u00f5his\u00f5navara ja murdes\u00f5nu k\u00f5igist Hiiumaa murrakutest. Kuna hiiu keele omap\u00e4ra tuleb esile eesk\u00e4tt tema h\u00e4\u00e4likulises k\u00fcljes, siis on s\u00f5nastikus n\u00e4idatud ka \u00fcldtuntud s\u00f5nade puhul nende hiiup\u00e4rast h\u00e4\u00e4ldust. Samuti on m\u00e4rks\u00f5nade juures n\u00e4itelaused koos viitega kihelkonnale, kust n\u00e4ide on kirja pandud.;Abstract;This is the first ever dictionary of the Hiiu vernacular. Its 6300 entry words include the core vocabulary as well as dialect words from every subdialect spoken on the island of Hiiumaa. As the specifics of the Hiiu tongue are mainly manifested in its phonetics the dictionary provides the vernacular pronunciation of common words as well. The entries also give sentence examples with reference to their source parish.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a64ae4ba-3a9b-5cfc-810b-490ced5a2328",
-    "notes": [
-        "Abstract",
-        "S\u00f5nastik kuulub Eesti Keele Instituudi v\u00e4ikeste murdes\u00f5nastike sarja ja on maailma esimene hiiu keele s\u00f5naraamat. See sisaldab 6300 m\u00e4rks\u00f5na ning esitab hiiu keele p\u00f5his\u00f5navara ja murdes\u00f5nu k\u00f5igist Hiiumaa murrakutest. Kuna hiiu keele omap\u00e4ra tuleb esile eesk\u00e4tt tema h\u00e4\u00e4likulises k\u00fcljes, siis on s\u00f5nastikus n\u00e4idatud ka \u00fcldtuntud s\u00f5nade puhul nende hiiup\u00e4rast h\u00e4\u00e4ldust. Samuti on m\u00e4rks\u00f5nade juures n\u00e4itelaused koos viitega kihelkonnale, kust n\u00e4ide on kirja pandud.",
-        "Abstract",
-        "This is the first ever dictionary of the Hiiu vernacular. Its 6300 entry words include the core vocabulary as well as dialect words from every subdialect spoken on the island of Hiiumaa. As the specifics of the Hiiu tongue are mainly manifested in its phonetics the dictionary provides the vernacular pronunciation of common words as well. The entries also give sentence examples with reference to their source parish."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9352875"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Hiiu s\u00f5naraamat",
-        "The Dictionary of the Hiiu Dialect"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a6a616db-22c2-5f77-9416-dd65e427d69a.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a6a616db-22c2-5f77-9416-dd65e427d69a.json
deleted file mode 100644
index 449a1b3d..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a6a616db-22c2-5f77-9416-dd65e427d69a.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00162L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:15726757",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:15726757"
-    ],
-    "PublicationTimestamp": "2018-07-31T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Karjus, Andres",
-        "Ehala, Martin"
-    ],
-    "fulltext": "oai:oai.datacite.org:15726757;2019-04-18T17:32:02Z;ESTDOI;ESTDOI.KEEL;Keelehoiakud Eesti keelekeskkondades 2015;Linguistic attitudes in Estonia 2015;Karjus, Andres;Ehala, Martin;Center of Estonian Language Resources;2018;Issued: 2018-07-31;Updated: 2018-07-31;doi:10.15155/1-00-0000-0000-0000-00162L;Abstract;Tartu \u00dclikooli uurimisprojekti Eesti keele kestlikkus avatud maailmas (EKKAM) tellimusel 2015. aasta kevadel Eestis l\u00e4bi viidud keelehoiakuid puudutava k\u00fcsimustiku vastused. Demograafiliselt tasakaalustatud valimis on 1006 vastajat vanuses 15-74. K\u00fcsimused h\u00f5lmavad vastajate demograafilist infot, keeleoskust, igap\u00e4evaseid keelevalikuid, keelehoiakuid, keelepoliitilisi vaateid. K\u00fcsimustikule oli v\u00f5imalik vastata nii eesti kui vene keeles, vastavalt k\u00fcsitletava valikule (ankeedi valik on andmestikus salvestatud). Andmestikus on 200 tunnust, millest suurema osa moodustavad k\u00fcsimuste vastused, lisaks m\u00f5ned k\u00fcsimuste vastustest tuletatud tunnused. Andmestikuga kaasas on meta-andmete fail, kus on kirjeldatud tunnuste t\u00fc\u00fcbid ja k\u00fcsimused, samuti algsed ankeedid. Andmed on saadaval mitmes erinevas formaadis (sh csv tekstifail). Uurimist\u00f6\u00f6 on valminud Eesti Teadusagentuuri grandi IUT20-3 toel.;Abstract;Data from a survey on linguistic attitudes carried out in Estonia in the spring of 2015, ordered by the Sustainability of Estonian in the Era of Globalisation research project of the University of Tartu. The demographically balanced sample consists of 1006 respondents aged 15-74. The questions cover the respondents' basic demographic information, their language proficiencies, daily language choices, linguistic attitudes and views on language politics. The respondents could choose either an Estonian or Russian version of the questionnaire (their choices are recorded in the dataset). The dataset consists of 200 variables, most of them being responses to the questions, along with some derived variables. The dataset comes with meta-data that describes the variables and lists the questionnaire questions and their English translations; the original questionnaires are available as well. The data are available in multiple formats (including plain text csv). This research was supported by the Estonian Research Council grant IUT20-3.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a6a616db-22c2-5f77-9416-dd65e427d69a",
-    "notes": [
-        "Abstract",
-        "Tartu \u00dclikooli uurimisprojekti Eesti keele kestlikkus avatud maailmas (EKKAM) tellimusel 2015. aasta kevadel Eestis l\u00e4bi viidud keelehoiakuid puudutava k\u00fcsimustiku vastused. Demograafiliselt tasakaalustatud valimis on 1006 vastajat vanuses 15-74. K\u00fcsimused h\u00f5lmavad vastajate demograafilist infot, keeleoskust, igap\u00e4evaseid keelevalikuid, keelehoiakuid, keelepoliitilisi vaateid. K\u00fcsimustikule oli v\u00f5imalik vastata nii eesti kui vene keeles, vastavalt k\u00fcsitletava valikule (ankeedi valik on andmestikus salvestatud). Andmestikus on 200 tunnust, millest suurema osa moodustavad k\u00fcsimuste vastused, lisaks m\u00f5ned k\u00fcsimuste vastustest tuletatud tunnused. Andmestikuga kaasas on meta-andmete fail, kus on kirjeldatud tunnuste t\u00fc\u00fcbid ja k\u00fcsimused, samuti algsed ankeedid. Andmed on saadaval mitmes erinevas formaadis (sh csv tekstifail). Uurimist\u00f6\u00f6 on valminud Eesti Teadusagentuuri grandi IUT20-3 toel.",
-        "Abstract",
-        "Data from a survey on linguistic attitudes carried out in Estonia in the spring of 2015, ordered by the Sustainability of Estonian in the Era of Globalisation research project of the University of Tartu. The demographically balanced sample consists of 1006 respondents aged 15-74. The questions cover the respondents' basic demographic information, their language proficiencies, daily language choices, linguistic attitudes and views on language politics. The respondents could choose either an Estonian or Russian version of the questionnaire (their choices are recorded in the dataset). The dataset consists of 200 variables, most of them being responses to the questions, along with some derived variables. The dataset comes with meta-data that describes the variables and lists the questionnaire questions and their English translations; the original questionnaires are available as well. The data are available in multiple formats (including plain text csv). This research was supported by the Estonian Research Council grant IUT20-3."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:15726757"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Keelehoiakud Eesti keelekeskkondades 2015",
-        "Linguistic attitudes in Estonia 2015"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a6d2c788-ec08-5e7a-91c8-bdf97fa57431.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a6d2c788-ec08-5e7a-91c8-bdf97fa57431.json
deleted file mode 100644
index 15c79978..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a6d2c788-ec08-5e7a-91c8-bdf97fa57431.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-000A3L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17968028",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17968028"
-    ],
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Ross, Peeter"
-    ],
-    "fulltext": "oai:oai.datacite.org:17968028;2019-04-12T17:25:50Z;ESTDOI;ESTDOI.KEEL;Radioloogiavastuste terminikasutuse alusel koostatud l\u00fchendis\u00f5nastik;Ross, Peeter;Center of Estonian Language Resources;2019;Issued: 2019-01-08;Updated: 2019-01-08;doi:10.15155/9-00-0000-0000-0000-000A3L;Abstract;L\u00fchendis\u00f5nastik on koostatud meditsiinikeele korpuse alusel (korpuse ja l\u00fchendite tuvastamise kirjeldus: E. Valdre, P. Ross, K. Tsepelina, K. Veskis, T. Vaino, H-J. Kaalep, Radioloogiauuringute vastuste l\u00fchendite ja l\u00fchendamise korpuslingvistiline anal\u00fc\u00fcs\u201c, Eesti Arst 2014, 93(9):502 \u2013512)). S\u00f5nastik on esitaud Excel failina kujul: m\u00f5iste, k\u00f5ik sellele vastavad l\u00fchendid korpuses esinenud kujul (kuid muutel\u00f5ppudeta), l\u00fchendi esinemiskordade arv, l\u00fchendile vastava m\u00f5iste k\u00f5igi l\u00fchendivariantide esinemiskordade arv, l\u00fchendi eeldatav algup\u00e4ra keel (eesti, ladina, inglise), l\u00fchendi allkeel (\u00fcldkeel, oskuskeel), m\u00f5istega seotud valdkond ja alavaldkonnad, teadaolevad eestikeelsed s\u00fcnon\u00fc\u00fcmid ning ladina- ja ingliskeelsed vasted. M\u00e4rkusena tuleb lisada, et seoses meditsiini arengutrendidega ei oma k\u00f5ik m\u00f5isted vasteid k\u00f5igis keeltes. ",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a6d2c788-ec08-5e7a-91c8-bdf97fa57431",
-    "notes": [
-        "Abstract",
-        "L\u00fchendis\u00f5nastik on koostatud meditsiinikeele korpuse alusel (korpuse ja l\u00fchendite tuvastamise kirjeldus: E. Valdre, P. Ross, K. Tsepelina, K. Veskis, T. Vaino, H-J. Kaalep, Radioloogiauuringute vastuste l\u00fchendite ja l\u00fchendamise korpuslingvistiline anal\u00fc\u00fcs\u201c, Eesti Arst 2014, 93(9):502 \u2013512)). S\u00f5nastik on esitaud Excel failina kujul: m\u00f5iste, k\u00f5ik sellele vastavad l\u00fchendid korpuses esinenud kujul (kuid muutel\u00f5ppudeta), l\u00fchendi esinemiskordade arv, l\u00fchendile vastava m\u00f5iste k\u00f5igi l\u00fchendivariantide esinemiskordade arv, l\u00fchendi eeldatav algup\u00e4ra keel (eesti, ladina, inglise), l\u00fchendi allkeel (\u00fcldkeel, oskuskeel), m\u00f5istega seotud valdkond ja alavaldkonnad, teadaolevad eestikeelsed s\u00fcnon\u00fc\u00fcmid ning ladina- ja ingliskeelsed vasted. M\u00e4rkusena tuleb lisada, et seoses meditsiini arengutrendidega ei oma k\u00f5ik m\u00f5isted vasteid k\u00f5igis keeltes. "
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17968028"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Radioloogiavastuste terminikasutuse alusel koostatud l\u00fchendis\u00f5nastik"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a7da6146-f090-5ccd-8ca8-da13867c653a.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a7da6146-f090-5ccd-8ca8-da13867c653a.json
deleted file mode 100644
index 0ad8a2c9..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a7da6146-f090-5ccd-8ca8-da13867c653a.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-00085L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10978474",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10978474"
-    ],
-    "PublicationTimestamp": "2017-05-08T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "J\u00e4rv, Risto",
-        "Tuisk, Astrid"
-    ],
-    "fulltext": "oai:oai.datacite.org:10978474;2019-04-08T11:33:31Z;ESTDOI;ESTDOI.KEEL;1001 lastem\u00e4ngu aastast 1935;1,001 children\u2019s games from the year 1935;J\u00e4rv, Risto;Tuisk, Astrid;Center of Estonian Language Resources;2017;Issued: 2017-05-05;Updated: 2017-05-08;doi:10.15155/9-00-0000-0000-0000-00085L;Abstract;Andmebaasis olevate lastem\u00e4ngude kirjeldused p\u00e4rinevad Eesti Rahvaluule Arhiivi kogudest. Suurem osa veebivalimiku m\u00e4ngukirjeldustest p\u00e4rineb lastem\u00e4ngude \u00fclemaalise kogumiskonkursi (1934\u20131935) saadetistest. Kogumisv\u00f5istlus korraldati koost\u00f6\u00f6s Haridusministeeriumi koolivalitsusega, m\u00e4ngukirjeldused ja joonistused on kooli\u00f5pilastelt. M\u00e4nge on valitud k\u00f5ikidest endistest Eesti maakondadest. Valimik sisaldab p\u00f5hiosa omaaegsest populaarsest m\u00e4nguvaramust 5\u201315-aastaste laste seas, tuues \u00e4ra ka unikaalsemaid ning ainukordsemaid m\u00e4nge. Samuti leiab kogumikust nii praeguseni m\u00e4ngitavaid kui juba unustuseh\u00f5lma vajunud m\u00e4ngude kirjeldusi. Tekste on kohendatud loetavamaks, kuid siiski sisaldavad need ka ajastuomast, paiguti t\u00e4nap\u00e4eva ortograafiareeglitele mittevastavat kirjapilti. \u00dchest ja samast m\u00e4ngust v\u00f5ib olla esitatud mitu eri varianti, mis aitavad paremini m\u00f5ista m\u00e4ngureegleid ning suunavad t\u00e4helepanu eri piirkondades kasutusel olnud erisugustele m\u00e4ngunimetustele. ",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a7da6146-f090-5ccd-8ca8-da13867c653a",
-    "notes": [
-        "Abstract",
-        "Andmebaasis olevate lastem\u00e4ngude kirjeldused p\u00e4rinevad Eesti Rahvaluule Arhiivi kogudest. Suurem osa veebivalimiku m\u00e4ngukirjeldustest p\u00e4rineb lastem\u00e4ngude \u00fclemaalise kogumiskonkursi (1934\u20131935) saadetistest. Kogumisv\u00f5istlus korraldati koost\u00f6\u00f6s Haridusministeeriumi koolivalitsusega, m\u00e4ngukirjeldused ja joonistused on kooli\u00f5pilastelt. M\u00e4nge on valitud k\u00f5ikidest endistest Eesti maakondadest. Valimik sisaldab p\u00f5hiosa omaaegsest populaarsest m\u00e4nguvaramust 5\u201315-aastaste laste seas, tuues \u00e4ra ka unikaalsemaid ning ainukordsemaid m\u00e4nge. Samuti leiab kogumikust nii praeguseni m\u00e4ngitavaid kui juba unustuseh\u00f5lma vajunud m\u00e4ngude kirjeldusi. Tekste on kohendatud loetavamaks, kuid siiski sisaldavad need ka ajastuomast, paiguti t\u00e4nap\u00e4eva ortograafiareeglitele mittevastavat kirjapilti. \u00dchest ja samast m\u00e4ngust v\u00f5ib olla esitatud mitu eri varianti, mis aitavad paremini m\u00f5ista m\u00e4ngureegleid ning suunavad t\u00e4helepanu eri piirkondades kasutusel olnud erisugustele m\u00e4ngunimetustele. "
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10978474"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "1001 lastem\u00e4ngu aastast 1935",
-        "1,001 children\u2019s games from the year 1935"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a8fec88a-d76f-5b34-98f7-df86d4dfacb4.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a8fec88a-d76f-5b34-98f7-df86d4dfacb4.json
deleted file mode 100644
index fc587c2c..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a8fec88a-d76f-5b34-98f7-df86d4dfacb4.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-0001BL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5757474",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5757474"
-    ],
-    "PublicationTimestamp": "2017-05-10T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Kallas, Jelena"
-    ],
-    "fulltext": "oai:oai.datacite.org:5757474;2019-04-18T17:36:51Z;ESTDOI;ESTDOI.KEEL;Eesti-vene s\u00f5naraamat;The Estonian-Russian Dictionary;\u042d\u0441\u0442\u043e\u043d\u0441\u043a\u043e-\u0440\u0443\u0441\u0441\u043a\u0438\u0439 \u0441\u043b\u043e\u0432\u0430\u0440\u044c;Kallas, Jelena;Center of Estonian Language Resources;2012;Issued: 2012-06-15;Updated: 2017-05-10;doi:10.15155/3-00-0000-0000-0000-0001BL;Abstract;Eesti-vene s\u00f5naraamat sisaldab t\u00e4nap\u00e4eva eesti kirjakeele p\u00f5his\u00f5navara, hulgaliselt erialatermineid, aga ka keeles kinnistunud uut ja moodsat ainest. S\u00f5navaliku aluseks on \u00f5igekeelsuss\u00f5naraamatu m\u00e4rks\u00f5nastik ja Eesti Keele Instituudis koostatud kirjakeele seletuss\u00f5naraamat. Eesti n\u00e4itestik p\u00f5hineb paljuski kirjakeele seletuss\u00f5naraamatul.;Abstract;The biggest and most comprehensive Estonian-Russian dictionary.;Abstract;\u0411\u043e\u043b\u044c\u0448\u043e\u0439 \u044d\u0441\u0442\u043e\u043d\u0441\u043a\u043e-\u0440\u0443\u0441\u0441\u043a\u0438\u0439 \u0441\u043b\u043e\u0432\u0430\u0440\u044c \u0441\u043e\u0434\u0435\u0440\u0436\u0438\u0442 \u043e\u0441\u043d\u043e\u0432\u043d\u0443\u044e \u043b\u0435\u043a\u0441\u0438\u043a\u0443 \u044d\u0441\u0442\u043e\u043d\u0441\u043a\u043e\u0433\u043e \u043b\u0438\u0442\u0435\u0440\u0430\u0442\u0443\u0440\u043d\u043e\u0433\u043e \u044f\u0437\u044b\u043a\u0430, \u043c\u043d\u043e\u0436\u0435\u0441\u0442\u0432\u043e \u0441\u043f\u0435\u0442\u0441\u0438\u0430\u043b\u043d\u044b\u0445 \u0442\u0435\u0440\u043c\u0438\u043d\u043e\u0432, \u0430 \u0442\u0430\u043a\u0436\u0435 \u0443\u0442\u0432\u0435\u0440\u0434\u0438\u0432\u0448\u0438\u0435\u0441\u044f \u0432 \u044f\u0437\u044b\u043a\u0435 \u043d\u043e\u0432\u044b\u0435 \u044f\u0437\u044b\u043a\u043e\u0432\u044b\u0435 \u0435\u0434\u0438\u043d\u0438\u0446\u044b.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a8fec88a-d76f-5b34-98f7-df86d4dfacb4",
-    "notes": [
-        "Abstract",
-        "Eesti-vene s\u00f5naraamat sisaldab t\u00e4nap\u00e4eva eesti kirjakeele p\u00f5his\u00f5navara, hulgaliselt erialatermineid, aga ka keeles kinnistunud uut ja moodsat ainest. S\u00f5navaliku aluseks on \u00f5igekeelsuss\u00f5naraamatu m\u00e4rks\u00f5nastik ja Eesti Keele Instituudis koostatud kirjakeele seletuss\u00f5naraamat. Eesti n\u00e4itestik p\u00f5hineb paljuski kirjakeele seletuss\u00f5naraamatul.",
-        "Abstract",
-        "The biggest and most comprehensive Estonian-Russian dictionary.",
-        "Abstract",
-        "\u0411\u043e\u043b\u044c\u0448\u043e\u0439 \u044d\u0441\u0442\u043e\u043d\u0441\u043a\u043e-\u0440\u0443\u0441\u0441\u043a\u0438\u0439 \u0441\u043b\u043e\u0432\u0430\u0440\u044c \u0441\u043e\u0434\u0435\u0440\u0436\u0438\u0442 \u043e\u0441\u043d\u043e\u0432\u043d\u0443\u044e \u043b\u0435\u043a\u0441\u0438\u043a\u0443 \u044d\u0441\u0442\u043e\u043d\u0441\u043a\u043e\u0433\u043e \u043b\u0438\u0442\u0435\u0440\u0430\u0442\u0443\u0440\u043d\u043e\u0433\u043e \u044f\u0437\u044b\u043a\u0430, \u043c\u043d\u043e\u0436\u0435\u0441\u0442\u0432\u043e \u0441\u043f\u0435\u0442\u0441\u0438\u0430\u043b\u043d\u044b\u0445 \u0442\u0435\u0440\u043c\u0438\u043d\u043e\u0432, \u0430 \u0442\u0430\u043a\u0436\u0435 \u0443\u0442\u0432\u0435\u0440\u0434\u0438\u0432\u0448\u0438\u0435\u0441\u044f \u0432 \u044f\u0437\u044b\u043a\u0435 \u043d\u043e\u0432\u044b\u0435 \u044f\u0437\u044b\u043a\u043e\u0432\u044b\u0435 \u0435\u0434\u0438\u043d\u0438\u0446\u044b."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5757474"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti-vene s\u00f5naraamat",
-        "The Estonian-Russian Dictionary",
-        "\u042d\u0441\u0442\u043e\u043d\u0441\u043a\u043e-\u0440\u0443\u0441\u0441\u043a\u0438\u0439 \u0441\u043b\u043e\u0432\u0430\u0440\u044c"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a915d480-e7f0-5da0-8693-abcf1cdc27a8.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a915d480-e7f0-5da0-8693-abcf1cdc27a8.json
deleted file mode 100644
index 7a98f2ce..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a915d480-e7f0-5da0-8693-abcf1cdc27a8.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/TY.0011",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:4597370",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:4597370"
-    ],
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "M\u00fc\u00fcrisep, Kaili"
-    ],
-    "fulltext": "oai:oai.datacite.org:4597370;2019-04-22T11:30:49Z;ESTDOI;ESTDOI.KEEL;Estonian corpus with shallow syntactic annotation;M\u00fc\u00fcrisep, Kaili;Center of Estonian Language Resources;2011;doi:10.15155/TY.0011",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a915d480-e7f0-5da0-8693-abcf1cdc27a8",
-    "oai_identifier": [
-        "oai:oai.datacite.org:4597370"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Estonian corpus with shallow syntactic annotation"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a96a167f-db8d-5ef2-9d1d-f86cc571d0af.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a96a167f-db8d-5ef2-9d1d-f86cc571d0af.json
deleted file mode 100644
index 34e01074..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a96a167f-db8d-5ef2-9d1d-f86cc571d0af.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-000FCL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:6892426",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:6892426"
-    ],
-    "PublicationTimestamp": "2015-10-20T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Kahusk, Neeme"
-    ],
-    "fulltext": "oai:oai.datacite.org:6892426;2019-02-16T04:31:30Z;ESTDOI;ESTDOI.KEEL;Poetry corpus;Kahusk, Neeme;Center of Estonian Language Resources;2015;Issued: 2015-10-20;Updated: 2015-10-20;doi:10.15155/1-00-0000-0000-0000-000FCL;Abstract;Demo",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a96a167f-db8d-5ef2-9d1d-f86cc571d0af",
-    "notes": [
-        "Abstract",
-        "Demo"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:6892426"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Poetry corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a9921b58-2137-532c-97e4-742973b78d70.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a9921b58-2137-532c-97e4-742973b78d70.json
deleted file mode 100644
index d84c5e01..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/a9921b58-2137-532c-97e4-742973b78d70.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05BEDL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9474559",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9474559"
-    ],
-    "PublicationTimestamp": "2016-10-31T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:9474559;2019-03-28T09:32:18Z;ESTDOI;ESTDOI.KEEL;Eesti-udmurdi s\u00f5naraamat;Hein, Indrek;Center of Estonian Language Resources;2016;Issued: 2016-10-31;Updated: 2016-10-31;doi:10.15155/3-00-0000-0000-0000-05BEDL;Abstract;Esimene eesti-udmurdi s\u00f5naraamat. Sisaldab u 10 000 m\u00e4rks\u00f5na ja on keeleuuenduslik: udmurdikeelsete vastete puudumisel pakuvad autorid eestikeelsele s\u00f5nale omapoolse v\u00f5imaliku vaste. S\u00f5naraamatu erip\u00e4raks on ka udmurdi murdes\u00f5nade rohkus.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "a9921b58-2137-532c-97e4-742973b78d70",
-    "notes": [
-        "Abstract",
-        "Esimene eesti-udmurdi s\u00f5naraamat. Sisaldab u 10 000 m\u00e4rks\u00f5na ja on keeleuuenduslik: udmurdikeelsete vastete puudumisel pakuvad autorid eestikeelsele s\u00f5nale omapoolse v\u00f5imaliku vaste. S\u00f5naraamatu erip\u00e4raks on ka udmurdi murdes\u00f5nade rohkus."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9474559"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti-udmurdi s\u00f5naraamat"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/aa21d578-157b-580d-a58d-f2f03ce5d5ce.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/aa21d578-157b-580d-a58d-f2f03ce5d5ce.json
deleted file mode 100644
index 001675f3..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/aa21d578-157b-580d-a58d-f2f03ce5d5ce.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05BE1L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9474547",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9474547"
-    ],
-    "PublicationTimestamp": "2016-11-09T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:9474547;2019-02-15T01:32:30Z;ESTDOI;ESTDOI.KEEL;Inglise-eesti meres\u00f5naraamat;Hein, Indrek;Center of Estonian Language Resources;2016;Issued: 2016-11-09;Updated: 2016-11-09;doi:10.15155/3-00-0000-0000-0000-05BE1L;Abstract;Sisaldab \u00fcle 30 000 m\u00e4rks\u00f5na. Peale merenduslike tavaterminite leiab s\u00f5naraamatust ka purjelaevu, puulaevu, merekaubandust, mere\u00f5igust, merekindlustust, konteinervedusid, kalandust, s\u00f5jalaevastikku, raadiolokatsiooni, h\u00fcdromehaanikat, okeanograafiat, purjesporti jms puutuvaid s\u00f5nu.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "aa21d578-157b-580d-a58d-f2f03ce5d5ce",
-    "notes": [
-        "Abstract",
-        "Sisaldab \u00fcle 30 000 m\u00e4rks\u00f5na. Peale merenduslike tavaterminite leiab s\u00f5naraamatust ka purjelaevu, puulaevu, merekaubandust, mere\u00f5igust, merekindlustust, konteinervedusid, kalandust, s\u00f5jalaevastikku, raadiolokatsiooni, h\u00fcdromehaanikat, okeanograafiat, purjesporti jms puutuvaid s\u00f5nu."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9474547"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Inglise-eesti meres\u00f5naraamat"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ab4fcb08-2e58-56b3-8dd8-6679545b3ea9.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ab4fcb08-2e58-56b3-8dd8-6679545b3ea9.json
deleted file mode 100644
index 972387ba..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ab4fcb08-2e58-56b3-8dd8-6679545b3ea9.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/TY.001A",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:4597380",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:4597380"
-    ],
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:4597380;2019-04-04T10:35:07Z;ESTDOI;ESTDOI.KEEL;Corpus of morphologically disambiguated Estonian texts;Muischnek, Kadri;Center of Estonian Language Resources;2011;doi:10.15155/TY.001A",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ab4fcb08-2e58-56b3-8dd8-6679545b3ea9",
-    "oai_identifier": [
-        "oai:oai.datacite.org:4597380"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus of morphologically disambiguated Estonian texts"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ab82086b-91d4-5357-82d2-217a9f77537d.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ab82086b-91d4-5357-82d2-217a9f77537d.json
deleted file mode 100644
index 51591a05..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ab82086b-91d4-5357-82d2-217a9f77537d.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00141L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:13445136",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:13445136"
-    ],
-    "PublicationTimestamp": "2017-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laur, Sven"
-    ],
-    "fulltext": "oai:oai.datacite.org:13445136;2018-10-27T12:49:39Z;ESTDOI;ESTDOI.KEEL;EstNLTK morphological analysis;Laur, Sven;Center of Estonian Language Resources;2017;Issued: 2017-12-11;Updated: 2017-12-11;doi:10.15155/1-00-0000-0000-0000-00141L;Abstract;Estonian NLTK toolkit - morphological analysis for Estonian. Uses Vabamorf tagset. Takes unannotated text as input.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ab82086b-91d4-5357-82d2-217a9f77537d",
-    "notes": [
-        "Abstract",
-        "Estonian NLTK toolkit - morphological analysis for Estonian. Uses Vabamorf tagset. Takes unannotated text as input."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:13445136"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "EstNLTK morphological analysis"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/aba995b8-d932-53e0-82ff-3ae6b7765197.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/aba995b8-d932-53e0-82ff-3ae6b7765197.json
deleted file mode 100644
index 358eed1a..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/aba995b8-d932-53e0-82ff-3ae6b7765197.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-0008EL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:13902330",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:13902330"
-    ],
-    "PublicationTimestamp": "2018-01-24T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "J\u00e4rv, Risto",
-        "Oras, Janika"
-    ],
-    "fulltext": "oai:oai.datacite.org:13902330;2019-03-02T14:31:45Z;ESTDOI;ESTDOI.KEEL;Eesti Regilaulud;Estonian Runic Songs' Database;J\u00e4rv, Risto;Oras, Janika;Center of Estonian Language Resources;2017;Issued: 2017-05-30;Updated: 2018-01-24;doi:10.15155/9-00-0000-0000-0000-0008EL;Abstract;Regilaulude andmebaas sisaldab 85 490 regilauluteksti, ligi kaks kolmandikku Eesti Rahvaluule Arhiivis talletatud regilaulutekstidest. Andmebaasist leiab vanema osa regilaulude kirjapanekutest \u2013 19. sajandil ja 20. sajandi alguk\u00fcmnenditel kogutud tekstid. Lisaks regilauludele on andmebaasis ka u 6000 siirdevormilist ja l\u00f5ppriimilist laulu. Tekste lisatakse j\u00e4rjest juurde. Andmebaasi on v\u00f5imalik kasutada nimetatud veebilehe kaudu v\u00f5i (\u00fchtse tekstikorpusena kasutamiseks) kontakteerudes kontaktisikutega.;Abstract;Estonian Runic Songs\u2019 Database contains 85 490 texts of runic songs - nearly two thirds of all runic songs\u2019 texts from the Estonian Folklore Archives. These are the oldest text recordings of Estonian runic songs (the text recordings were created in the 19th century and in the first decades of the 20th century). In addition to the runic songs, the database also has songs of transitional form and end-rhymed songs (about 6000). Texts are being added constantly. Please send an e-mail to contactpersons for access to full text corpus.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "aba995b8-d932-53e0-82ff-3ae6b7765197",
-    "notes": [
-        "Abstract",
-        "Regilaulude andmebaas sisaldab 85 490 regilauluteksti, ligi kaks kolmandikku Eesti Rahvaluule Arhiivis talletatud regilaulutekstidest. Andmebaasist leiab vanema osa regilaulude kirjapanekutest \u2013 19. sajandil ja 20. sajandi alguk\u00fcmnenditel kogutud tekstid. Lisaks regilauludele on andmebaasis ka u 6000 siirdevormilist ja l\u00f5ppriimilist laulu. Tekste lisatakse j\u00e4rjest juurde. Andmebaasi on v\u00f5imalik kasutada nimetatud veebilehe kaudu v\u00f5i (\u00fchtse tekstikorpusena kasutamiseks) kontakteerudes kontaktisikutega.",
-        "Abstract",
-        "Estonian Runic Songs\u2019 Database contains 85 490 texts of runic songs - nearly two thirds of all runic songs\u2019 texts from the Estonian Folklore Archives. These are the oldest text recordings of Estonian runic songs (the text recordings were created in the 19th century and in the first decades of the 20th century). In addition to the runic songs, the database also has songs of transitional form and end-rhymed songs (about 6000). Texts are being added constantly. Please send an e-mail to contactpersons for access to full text corpus."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:13902330"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti Regilaulud",
-        "Estonian Runic Songs' Database"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/abc32488-4ccc-514e-a4e2-9038428cb7fc.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/abc32488-4ccc-514e-a4e2-9038428cb7fc.json
deleted file mode 100644
index aeed0457..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/abc32488-4ccc-514e-a4e2-9038428cb7fc.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00126L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9836560",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9836560"
-    ],
-    "PublicationTimestamp": "2016-12-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Tkachenko, Alexander"
-    ],
-    "fulltext": "oai:oai.datacite.org:9836560;2019-03-27T06:31:33Z;ESTDOI;ESTDOI.KEEL;Gap-tagger corpus;Tkachenko, Alexander;Center of Estonian Language Resources;2016;Issued: 2016-12-01;Updated: 2016-12-01;doi:10.15155/1-00-0000-0000-0000-00126L;Abstract;Gap-tagger corpus contains data for assessing correctness of automatically generated alternatives for filling a gap (missing word). To get clearly interpretable results, we conducted modified version of A/B testing where the user had to choose between the original word and an alternative. The user has an option either to pick one of the two proposed words, or to report both words as appropriate. Since we know the right answer, we can objectively assess the suitability of alternative answers without formally specifying what classifies as a correct answer. Experiments were run using gap-tagger tool https://github.com/estnltk/gap-tagger. \n\nIn the corpus file, each line correspond to one question. The file is in csv format with the following columns:\nsentence: sentence\ngap_start: start position of the gap word in the sentence\ngap_end: end position of the gap word in the sentence\ngap_word: correct gap word\nvariant: gap variant word\ncorrect_selected: indicates if correct word is selected\nboth_selected: indicates if user reported both words as appropriate\nannotator: user id\ntime: time in milliseconds which took user to answer a question",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "abc32488-4ccc-514e-a4e2-9038428cb7fc",
-    "notes": [
-        "Abstract",
-        "Gap-tagger corpus contains data for assessing correctness of automatically generated alternatives for filling a gap (missing word). To get clearly interpretable results, we conducted modified version of A/B testing where the user had to choose between the original word and an alternative. The user has an option either to pick one of the two proposed words, or to report both words as appropriate. Since we know the right answer, we can objectively assess the suitability of alternative answers without formally specifying what classifies as a correct answer. Experiments were run using gap-tagger tool https://github.com/estnltk/gap-tagger. \n\nIn the corpus file, each line correspond to one question. The file is in csv format with the following columns:\nsentence: sentence\ngap_start: start position of the gap word in the sentence\ngap_end: end position of the gap word in the sentence\ngap_word: correct gap word\nvariant: gap variant word\ncorrect_selected: indicates if correct word is selected\nboth_selected: indicates if user reported both words as appropriate\nannotator: user id\ntime: time in milliseconds which took user to answer a question"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9836560"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Gap-tagger corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/acc650f2-ab03-5cc6-a224-eba4279b9f6c.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/acc650f2-ab03-5cc6-a224-eba4279b9f6c.json
deleted file mode 100644
index d241c52a..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/acc650f2-ab03-5cc6-a224-eba4279b9f6c.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-0002AL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5757471",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5757471"
-    ],
-    "PublicationTimestamp": "2019-01-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Luts, Martin"
-    ],
-    "fulltext": "oai:oai.datacite.org:5757471;2019-04-17T17:25:46Z;ESTDOI;ESTDOI.KEEL;Eesti avatud paralleelkorpus;Estonian Open Parallel Corpus;Luts, Martin;Center of Estonian Language Resources;2013;Issued: 2013-01-09;Updated: 2019-01-07;doi:10.15155/9-00-0000-0000-0000-0002AL;Abstract;Projekti \u201eEesti avatud paralleelkorpus\u201d eesm\u00e4rk on luua oluline kogus keeleressursse statistiliste masint\u00f5lkes\u00fcsteemide parendamiseks. Projekt aitab kaasa olukorra saavutamisele kus: (i) Erinevad kommerts- ja kogukondlikud masint\u00f5lkes\u00fcsteemid pakuvad kvaliteetset t\u00f5lketeenust. (ii) Masint\u00f5lkes\u00fcsteemide teenused on l\u00f5ppkasutajatele v\u00f5imalikult v\u00e4heste piirangutega (tasu, maht, kasutatavad platvormid) k\u00e4ttesaadavad. (iii) S\u00f5ltuvus \u00fcksikutest masint\u00f5lketeenuste kommertsteenusepakkujatest ei ole kriitiline ja on asendatav avatud ning vabavaraliste lahendustega. Projekti m\u00f5\u00f5detavad tulemid on: (i) Kogutud ja korrastatud paralleelkorpuste maht. Projekti esimese aasta jooksul kogutud v\u00e4hemalt 2,5 miljonit \u00fchikut (s\u00f5na), projekti l\u00f5puks v\u00e4hemalt 15 miljonit \u00fchikut. (ii) Kogutud korpuste - t\u00e4iedavalt olemasolevatele korpustele - abil treenitud masint\u00f5lkes\u00fcsteemide kvaliteedin\u00e4itajate parenemine (m\u00f5\u00f5detakse koost\u00f6\u00f6s masint\u00f5lkes\u00fcsteemide omanikega). (iii) Kogutud korpused aksepteeritud ja publitseeritud META-SHARE (http://www.meta-net.eu/meta-share) ja CLARIN (http://www.clarin.eu/external/) baasides. Projekti tulemina loodava paralleelkorpuse omadused: \u2022 Lause tasandil joondatud inglise-eesti paralleelkorpus. \u2022 Korpus kirjeldatakse kasutades META-SHARE metaandmete formaati. \u2022 Korpus on k\u00e4ttesaadav tasuta ja piiranguteta kasutamiseks kommerts- ja vabavararakendustes, edasiarendusteks jm. Korpus on allalaaditav nii META-SHARE taristu kui ka CLARINi v\u00f5rgustiku kaudu. \u2022 Korpus koostatakse andmetest mida ei ole seni kasutatud paralleelkorpuste loomiseks (ei kattu olemasolevate paralleelkorpustega DGT ja JRC Aquis).\n\nM\u00e4rkus. Alamosa korpusest (sh IT aastaraamatud) ajutiselt kvaliteediparanduseks eemaldatud;Abstract;The English-Estonian parallel corpus was collected in the framework of the National Programme for Estonian Language Technology http://www.keeletehnoloogia.ee/ekt-projektid/eesti-avatud-paralleelkorpus\n\nNote. Part of the corpus temporaly removed for quality improvements",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "acc650f2-ab03-5cc6-a224-eba4279b9f6c",
-    "notes": [
-        "Abstract",
-        "Projekti \u201eEesti avatud paralleelkorpus\u201d eesm\u00e4rk on luua oluline kogus keeleressursse statistiliste masint\u00f5lkes\u00fcsteemide parendamiseks. Projekt aitab kaasa olukorra saavutamisele kus: (i) Erinevad kommerts- ja kogukondlikud masint\u00f5lkes\u00fcsteemid pakuvad kvaliteetset t\u00f5lketeenust. (ii) Masint\u00f5lkes\u00fcsteemide teenused on l\u00f5ppkasutajatele v\u00f5imalikult v\u00e4heste piirangutega (tasu, maht, kasutatavad platvormid) k\u00e4ttesaadavad. (iii) S\u00f5ltuvus \u00fcksikutest masint\u00f5lketeenuste kommertsteenusepakkujatest ei ole kriitiline ja on asendatav avatud ning vabavaraliste lahendustega. Projekti m\u00f5\u00f5detavad tulemid on: (i) Kogutud ja korrastatud paralleelkorpuste maht. Projekti esimese aasta jooksul kogutud v\u00e4hemalt 2,5 miljonit \u00fchikut (s\u00f5na), projekti l\u00f5puks v\u00e4hemalt 15 miljonit \u00fchikut. (ii) Kogutud korpuste - t\u00e4iedavalt olemasolevatele korpustele - abil treenitud masint\u00f5lkes\u00fcsteemide kvaliteedin\u00e4itajate parenemine (m\u00f5\u00f5detakse koost\u00f6\u00f6s masint\u00f5lkes\u00fcsteemide omanikega). (iii) Kogutud korpused aksepteeritud ja publitseeritud META-SHARE (http://www.meta-net.eu/meta-share) ja CLARIN (http://www.clarin.eu/external/) baasides. Projekti tulemina loodava paralleelkorpuse omadused: \u2022 Lause tasandil joondatud inglise-eesti paralleelkorpus. \u2022 Korpus kirjeldatakse kasutades META-SHARE metaandmete formaati. \u2022 Korpus on k\u00e4ttesaadav tasuta ja piiranguteta kasutamiseks kommerts- ja vabavararakendustes, edasiarendusteks jm. Korpus on allalaaditav nii META-SHARE taristu kui ka CLARINi v\u00f5rgustiku kaudu. \u2022 Korpus koostatakse andmetest mida ei ole seni kasutatud paralleelkorpuste loomiseks (ei kattu olemasolevate paralleelkorpustega DGT ja JRC Aquis).\n\nM\u00e4rkus. Alamosa korpusest (sh IT aastaraamatud) ajutiselt kvaliteediparanduseks eemaldatud",
-        "Abstract",
-        "The English-Estonian parallel corpus was collected in the framework of the National Programme for Estonian Language Technology http://www.keeletehnoloogia.ee/ekt-projektid/eesti-avatud-paralleelkorpus\n\nNote. Part of the corpus temporaly removed for quality improvements"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5757471"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti avatud paralleelkorpus",
-        "Estonian Open Parallel Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ad9447ca-1b4f-5a20-a005-c01865f2c60c.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ad9447ca-1b4f-5a20-a005-c01865f2c60c.json
deleted file mode 100644
index f59931b9..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ad9447ca-1b4f-5a20-a005-c01865f2c60c.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-079D2L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17926652",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17926652"
-    ],
-    "PublicationTimestamp": "2018-12-22T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Pajupuu, Hille"
-    ],
-    "fulltext": "oai:oai.datacite.org:17926652;2019-04-12T17:25:45Z;ESTDOI;ESTDOI.KEEL;Emotional;Pajupuu, Hille;Center of Estonian Language Resources;2018;Issued: 2018-12-22;Updated: 2018-12-22;doi:10.15155/3-00-0000-0000-0000-079D2L;Abstract;Project Statistical Models of the Emotionality of Speech and Written Text (2011-2014) was supported by the National Programme for Estonian Language Technology (2011-2017) of the Estonian Ministry of Education and Research.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ad9447ca-1b4f-5a20-a005-c01865f2c60c",
-    "notes": [
-        "Abstract",
-        "Project Statistical Models of the Emotionality of Speech and Written Text (2011-2014) was supported by the National Programme for Estonian Language Technology (2011-2017) of the Estonian Ministry of Education and Research."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17926652"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Emotional"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/adee095d-ca80-5df3-98fd-22258b953407.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/adee095d-ca80-5df3-98fd-22258b953407.json
deleted file mode 100644
index 2a4ea7fa..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/adee095d-ca80-5df3-98fd-22258b953407.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00078L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5755379",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5755379"
-    ],
-    "PublicationTimestamp": "2015-05-21T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:5755379;2019-04-17T17:26:28Z;ESTDOI;ESTDOI.KEEL;Aligned Estonian-Icelandic ICD-10;Muischnek, Kadri;Center of Estonian Language Resources;2013;Issued: 2013-01-07;Updated: 2015-05-21;doi:10.15155/1-00-0000-0000-0000-00078L;Abstract;Aligned Estonian and Icelandic versions of WHO-s International Classification of Diseases (ICD-10)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "adee095d-ca80-5df3-98fd-22258b953407",
-    "notes": [
-        "Abstract",
-        "Aligned Estonian and Icelandic versions of WHO-s International Classification of Diseases (ICD-10)"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5755379"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Aligned Estonian-Icelandic ICD-10"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/af33e86f-71df-5424-ac00-a01d588459bf.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/af33e86f-71df-5424-ac00-a01d588459bf.json
deleted file mode 100644
index a4df7ddf..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/af33e86f-71df-5424-ac00-a01d588459bf.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05B57L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9352882",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9352882"
-    ],
-    "PublicationTimestamp": "2017-03-03T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Viks, \u00dclle"
-    ],
-    "fulltext": "oai:oai.datacite.org:9352882;2019-04-01T23:32:49Z;ESTDOI;ESTDOI.KEEL;Eesti-norra s\u00f5naraamat\n;The Estonian-Norwegian Dictionary\n;Estisk-norsk ordbok;Viks, \u00dclle;Center of Estonian Language Resources;2016;Issued: 2016-10-26;Updated: 2017-03-03;doi:10.15155/3-00-0000-0000-0000-05B57L;Abstract;Sisaldab u 19 000 eesti ja 21 000 norra m\u00e4rks\u00f5na, millele on lisatud grammatilised andmed ja hulgaliselt n\u00e4iteid s\u00f5nade kasutamise kohta. Raamatus on ka l\u00fchi\u00fclevaated eesti ja norra keelest.;Abstract;Contains ca 19,000 Estonian and 21,000 Norwegian entry words with grammatical data and numerous usage examples.;Abstract;Dette er den f\u00f8rste toveis ordboka mellom norsk og estisk.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "af33e86f-71df-5424-ac00-a01d588459bf",
-    "notes": [
-        "Abstract",
-        "Sisaldab u 19 000 eesti ja 21 000 norra m\u00e4rks\u00f5na, millele on lisatud grammatilised andmed ja hulgaliselt n\u00e4iteid s\u00f5nade kasutamise kohta. Raamatus on ka l\u00fchi\u00fclevaated eesti ja norra keelest.",
-        "Abstract",
-        "Contains ca 19,000 Estonian and 21,000 Norwegian entry words with grammatical data and numerous usage examples.",
-        "Abstract",
-        "Dette er den f\u00f8rste toveis ordboka mellom norsk og estisk."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9352882"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti-norra s\u00f5naraamat\n",
-        "The Estonian-Norwegian Dictionary\n",
-        "Estisk-norsk ordbok"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b00a8f5a-b34f-5fda-b0cc-64e00d0aa0e0.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b00a8f5a-b34f-5fda-b0cc-64e00d0aa0e0.json
deleted file mode 100644
index 51e0189b..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b00a8f5a-b34f-5fda-b0cc-64e00d0aa0e0.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-0668AL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10749631",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10749631"
-    ],
-    "PublicationTimestamp": "2017-04-03T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Soosaar, Sven-Erik"
-    ],
-    "fulltext": "oai:oai.datacite.org:10749631;2019-04-05T19:31:53Z;ESTDOI;ESTDOI.KEEL;Eesti-mari s\u00f5naraamat;Estonian-Mari Dictionary;Soosaar, Sven-Erik;Center of Estonian Language Resources;2017;Issued: 2017-04-03;Updated: 2017-04-03;doi:10.15155/3-00-0000-0000-0000-0668AL;Abstract;S\u00f5naraamat sisaldab umbes 9800 m\u00e4rks\u00f5na. S\u00f5naraamatu sihtgrupiks on mari keelest ja kultuurist huvitatud eestlased ning eesti keelt \u00f5ppivad marid. S\u00f5nastiku n\u00e4itelaused ja -fraasid on abiks nii keele\u00f5ppijatele kui ka t\u00f5lkijatele. Kuigi mari keelel on kaks kirjakeelt \u2013 niidumari keel ja m\u00e4emari keel \u2013, sisaldab s\u00f5naraamat vaid niidumari vasteid, sest enamasti peetakse mari keelest r\u00e4\u00e4kides silmas just niidumari keelt. S\u00f5naraamat on k\u00e4ttesaadav ainult elektrooniliselt. ",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b00a8f5a-b34f-5fda-b0cc-64e00d0aa0e0",
-    "notes": [
-        "Abstract",
-        "S\u00f5naraamat sisaldab umbes 9800 m\u00e4rks\u00f5na. S\u00f5naraamatu sihtgrupiks on mari keelest ja kultuurist huvitatud eestlased ning eesti keelt \u00f5ppivad marid. S\u00f5nastiku n\u00e4itelaused ja -fraasid on abiks nii keele\u00f5ppijatele kui ka t\u00f5lkijatele. Kuigi mari keelel on kaks kirjakeelt \u2013 niidumari keel ja m\u00e4emari keel \u2013, sisaldab s\u00f5naraamat vaid niidumari vasteid, sest enamasti peetakse mari keelest r\u00e4\u00e4kides silmas just niidumari keelt. S\u00f5naraamat on k\u00e4ttesaadav ainult elektrooniliselt. "
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10749631"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti-mari s\u00f5naraamat",
-        "Estonian-Mari Dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b097b60f-fef4-52da-a768-2f418f402ed5.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b097b60f-fef4-52da-a768-2f418f402ed5.json
deleted file mode 100644
index ed120726..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b097b60f-fef4-52da-a768-2f418f402ed5.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05B54L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9352878",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9352878"
-    ],
-    "PublicationTimestamp": "2016-10-30T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek",
-        "Vare, Silvi"
-    ],
-    "fulltext": "oai:oai.datacite.org:9352878;2019-04-22T15:02:39Z;ESTDOI;ESTDOI.KEEL;Eesti keele s\u00f5napered;Hein, Indrek;Vare, Silvi;Center of Estonian Language Resources;2016;Issued: 2016-10-30;Updated: 2016-10-30;doi:10.15155/3-00-0000-0000-0000-05B54L;Abstract;Esimene eesti keele s\u00f5naperede s\u00f5naraamat, kust saab p\u00f5hjaliku \u00fclevaate eesti keele rikkalikust s\u00f5namoodustusest \u2013 kirjeldatud on ligikaudu 120 000 s\u00f5na ehitust ja s\u00f5nadevahelisi moodustusseoseid. Seoste alusel on s\u00f5nad koondatud ligi 9000 s\u00f5napereks. S\u00f5napere koondab kokku k\u00f5ik need s\u00f5nad, mis on \u00fcksteisest moodustatud, milles kordub \u00fcks \u00fchine t\u00fcvi, mis seob k\u00f5iki s\u00f5napere liikmeid.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b097b60f-fef4-52da-a768-2f418f402ed5",
-    "notes": [
-        "Abstract",
-        "Esimene eesti keele s\u00f5naperede s\u00f5naraamat, kust saab p\u00f5hjaliku \u00fclevaate eesti keele rikkalikust s\u00f5namoodustusest \u2013 kirjeldatud on ligikaudu 120 000 s\u00f5na ehitust ja s\u00f5nadevahelisi moodustusseoseid. Seoste alusel on s\u00f5nad koondatud ligi 9000 s\u00f5napereks. S\u00f5napere koondab kokku k\u00f5ik need s\u00f5nad, mis on \u00fcksteisest moodustatud, milles kordub \u00fcks \u00fchine t\u00fcvi, mis seob k\u00f5iki s\u00f5napere liikmeid."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9352878"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele s\u00f5napered"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b0a1d33b-8ef5-5fad-bea1-3e63acf5e9bf.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b0a1d33b-8ef5-5fad-bea1-3e63acf5e9bf.json
deleted file mode 100644
index b24a4c77..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b0a1d33b-8ef5-5fad-bea1-3e63acf5e9bf.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-000AAL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17986390",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17986390"
-    ],
-    "PublicationTimestamp": "2019-01-11T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Iva, Sulev"
-    ],
-    "fulltext": "oai:oai.datacite.org:17986390;2019-02-24T11:02:47Z;ESTDOI;ESTDOI.KEEL;W\u00f5ru Instituudi T\u00f5lkeMasin;Iva, Sulev;Center of Estonian Language Resources;2019;Issued: 2019-01-11;Updated: 2019-01-11;doi:10.15155/9-00-0000-0000-0000-000AAL;Abstract;Reeglip\u00f5hine masint\u00f5lge eesti ja v\u00f5ru keele vahel.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b0a1d33b-8ef5-5fad-bea1-3e63acf5e9bf",
-    "notes": [
-        "Abstract",
-        "Reeglip\u00f5hine masint\u00f5lge eesti ja v\u00f5ru keele vahel."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17986390"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "W\u00f5ru Instituudi T\u00f5lkeMasin"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b138178f-3543-5169-8f70-4794c2eda024.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b138178f-3543-5169-8f70-4794c2eda024.json
deleted file mode 100644
index 5cced152..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b138178f-3543-5169-8f70-4794c2eda024.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05B4DL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9352871",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9352871"
-    ],
-    "PublicationTimestamp": "2017-03-03T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Leemets, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:9352871;2019-02-15T18:37:46Z;ESTDOI;ESTDOI.KEEL;Eesti-vene \u00f5pilase \u00d5S;Estonian-Russian learner's orthographic dictionary;\u042d\u0441\u0442\u043e\u043d\u0441\u043a\u043e-\u0440\u0443\u0441\u0441\u043a\u0438\u0439 \u043e\u0440\u0444\u043e\u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u0439 \u0441\u043b\u043e\u0432\u0430\u0440\u044c \u0443\u0447\u0435\u043d\u0438\u043a\u0430;Leemets, Tiina;Center of Estonian Language Resources;2016;Issued: 2016-10-31;Updated: 2017-03-03;doi:10.15155/3-00-0000-0000-0000-05B4DL;Abstract;Eesti-vene \u00f5pilase \u00d5S on m\u00f5eldud eelk\u00f5ige vene emakeelega v\u00f5i vene keele p\u00f5hjal eesti keele \u00f5ppijale. S\u00f5nu saab otsida nii eesti kui ka vene keele kaudu. See s\u00f5nastik on kombinatsioon eesti \u00f5igekeelsuss\u00f5naraamatust, \u00f5pilase \u00f5igekeelsuss\u00f5naraamatust ja eesti-vene s\u00f5naraamatust. Teos sisaldab 23 000 eesti keele s\u00f5na ja kohanime venekeelsete vastete ja n\u00e4idetega. Lisatud on ka venekeelne eesti ortograafia \u00fclevaade ning vene-eesti register.;Abstract;The Estonian-Russian Learner\u00b4s \u00d5S is mainly meant for those learners of Estonian whose mother tongue is Russian or who learn it through Russian. Words can be searched via Estonian as well as via Russian. The dictionary is a combination of the Dictionary of Standard Estonian, A Learner\u00b4s Dictionary of Standard Estonian, and The Estonian-Russian Dictionary. It contains 23,000 Estonian words and place names with Russian equivalents and examples. There is also a Russian-language survey of Estonian orthography and a Russian-Estonian index.;Abstract;\u042d\u0441\u0442\u043e\u043d\u0441\u043a\u043e-\u0440\u0443\u0441\u0441\u043a\u0438\u0439 \u0448\u043a\u043e\u043b\u044c\u043d\u044b\u0439 \u043e\u0440\u0444\u043e\u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u0439 \u0441\u043b\u043e\u0432\u0430\u0440\u044c \u043f\u0440\u0435\u0434\u043d\u0430\u0437\u043d\u0430\u0447\u0435\u043d \u0434\u043b\u044f \u0442\u0435\u0445, \u0434\u043b\u044f \u043a\u043e\u0433\u043e \u0440\u0443\u0441\u0441\u043a\u0438\u0439 \u044f\u0437\u044b\u043a \u044f\u0432\u043b\u044f\u0435\u0442\u0441\u044f \u0440\u043e\u0434\u043d\u044b\u043c, a \u0442\u0430\u043a\u0436\u0435 \u0434\u043b\u044f \u0442\u0435\u0445 \u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u0435\u043b\u0435\u0439, \u043a\u043e\u0442\u043e\u0440\u044b\u0435 \u0438\u0437\u0443\u0447\u0430\u044e\u0442 \u044d\u0441\u0442\u043e\u043d\u0441\u043a\u0438\u0439 \u044f\u0437\u044b\u043a \u043d\u0430 \u0431\u0430\u0437\u0435 \u0440\u0443\u0441\u0441\u043a\u043e\u0433\u043e. \u041f\u043e\u0438\u0441\u043a \u0432 \u0441\u043b\u043e\u0432\u0430\u0440\u0435 \u043c\u043e\u0436\u0435\u0442 \u043e\u0441\u0443\u0449\u0435\u0441\u0442\u0432\u043b\u044f\u0442\u044c\u0441\u044f \u043a\u0430\u043a \u0447\u0435\u0440\u0435\u0437 \u044d\u0441\u0442\u043e\u043d\u0441\u043a\u043e\u0435, \u0442\u0430\u043a \u0438 \u0447\u0435\u0440\u0435\u0437 \u0440\u0443\u0441\u0441\u043a\u043e\u0435 \u0441\u043b\u043e\u0432\u043e.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b138178f-3543-5169-8f70-4794c2eda024",
-    "notes": [
-        "Abstract",
-        "Eesti-vene \u00f5pilase \u00d5S on m\u00f5eldud eelk\u00f5ige vene emakeelega v\u00f5i vene keele p\u00f5hjal eesti keele \u00f5ppijale. S\u00f5nu saab otsida nii eesti kui ka vene keele kaudu. See s\u00f5nastik on kombinatsioon eesti \u00f5igekeelsuss\u00f5naraamatust, \u00f5pilase \u00f5igekeelsuss\u00f5naraamatust ja eesti-vene s\u00f5naraamatust. Teos sisaldab 23 000 eesti keele s\u00f5na ja kohanime venekeelsete vastete ja n\u00e4idetega. Lisatud on ka venekeelne eesti ortograafia \u00fclevaade ning vene-eesti register.",
-        "Abstract",
-        "The Estonian-Russian Learner\u00b4s \u00d5S is mainly meant for those learners of Estonian whose mother tongue is Russian or who learn it through Russian. Words can be searched via Estonian as well as via Russian. The dictionary is a combination of the Dictionary of Standard Estonian, A Learner\u00b4s Dictionary of Standard Estonian, and The Estonian-Russian Dictionary. It contains 23,000 Estonian words and place names with Russian equivalents and examples. There is also a Russian-language survey of Estonian orthography and a Russian-Estonian index.",
-        "Abstract",
-        "\u042d\u0441\u0442\u043e\u043d\u0441\u043a\u043e-\u0440\u0443\u0441\u0441\u043a\u0438\u0439 \u0448\u043a\u043e\u043b\u044c\u043d\u044b\u0439 \u043e\u0440\u0444\u043e\u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u0439 \u0441\u043b\u043e\u0432\u0430\u0440\u044c \u043f\u0440\u0435\u0434\u043d\u0430\u0437\u043d\u0430\u0447\u0435\u043d \u0434\u043b\u044f \u0442\u0435\u0445, \u0434\u043b\u044f \u043a\u043e\u0433\u043e \u0440\u0443\u0441\u0441\u043a\u0438\u0439 \u044f\u0437\u044b\u043a \u044f\u0432\u043b\u044f\u0435\u0442\u0441\u044f \u0440\u043e\u0434\u043d\u044b\u043c, a \u0442\u0430\u043a\u0436\u0435 \u0434\u043b\u044f \u0442\u0435\u0445 \u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u0435\u043b\u0435\u0439, \u043a\u043e\u0442\u043e\u0440\u044b\u0435 \u0438\u0437\u0443\u0447\u0430\u044e\u0442 \u044d\u0441\u0442\u043e\u043d\u0441\u043a\u0438\u0439 \u044f\u0437\u044b\u043a \u043d\u0430 \u0431\u0430\u0437\u0435 \u0440\u0443\u0441\u0441\u043a\u043e\u0433\u043e. \u041f\u043e\u0438\u0441\u043a \u0432 \u0441\u043b\u043e\u0432\u0430\u0440\u0435 \u043c\u043e\u0436\u0435\u0442 \u043e\u0441\u0443\u0449\u0435\u0441\u0442\u0432\u043b\u044f\u0442\u044c\u0441\u044f \u043a\u0430\u043a \u0447\u0435\u0440\u0435\u0437 \u044d\u0441\u0442\u043e\u043d\u0441\u043a\u043e\u0435, \u0442\u0430\u043a \u0438 \u0447\u0435\u0440\u0435\u0437 \u0440\u0443\u0441\u0441\u043a\u043e\u0435 \u0441\u043b\u043e\u0432\u043e."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9352871"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti-vene \u00f5pilase \u00d5S",
-        "Estonian-Russian learner's orthographic dictionary",
-        "\u042d\u0441\u0442\u043e\u043d\u0441\u043a\u043e-\u0440\u0443\u0441\u0441\u043a\u0438\u0439 \u043e\u0440\u0444\u043e\u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u0439 \u0441\u043b\u043e\u0432\u0430\u0440\u044c \u0443\u0447\u0435\u043d\u0438\u043a\u0430"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b1526c15-8071-5b17-9396-77c819d93b2d.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b1526c15-8071-5b17-9396-77c819d93b2d.json
deleted file mode 100644
index 62854728..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b1526c15-8071-5b17-9396-77c819d93b2d.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06615L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10637047",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10637047"
-    ],
-    "PublicationTimestamp": "2017-03-20T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Ross, Kristiina",
-        "Erelt, Mati"
-    ],
-    "fulltext": "oai:oai.datacite.org:10637047;2019-03-23T18:25:40Z;ESTDOI;ESTDOI.KEEL;Eesti keele k\u00e4siraamat;Handbook of the Estonian Language;Ross, Kristiina;Erelt, Mati;Center of Estonian Language Resources;2017;Issued: 2017-03-20;Updated: 2017-03-20;doi:10.15155/3-00-0000-0000-0000-06615L;Abstract;Pakub \u00fcldharivaid teadmisi eesti kirjakeele grammatika ja s\u00f5navara ehituse kohta. Esitus on v\u00f5imalikult lihtne, v\u00e4lditud on tavakasutajale tarbetuid \u00fcksikasju. Praktiline abivahend kirjakeele korrektseks kasutamiseks.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b1526c15-8071-5b17-9396-77c819d93b2d",
-    "notes": [
-        "Abstract",
-        "Pakub \u00fcldharivaid teadmisi eesti kirjakeele grammatika ja s\u00f5navara ehituse kohta. Esitus on v\u00f5imalikult lihtne, v\u00e4lditud on tavakasutajale tarbetuid \u00fcksikasju. Praktiline abivahend kirjakeele korrektseks kasutamiseks."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10637047"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele k\u00e4siraamat",
-        "Handbook of the Estonian Language"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b1d9a559-c46a-526a-bf90-1cdcc19f2d9c.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b1d9a559-c46a-526a-bf90-1cdcc19f2d9c.json
deleted file mode 100644
index 5ae07d85..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b1d9a559-c46a-526a-bf90-1cdcc19f2d9c.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00191L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17968156",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17968156"
-    ],
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Fi\u0161el, Mark"
-    ],
-    "fulltext": "oai:oai.datacite.org:17968156;2019-02-01T06:32:29Z;ESTDOI;ESTDOI.KEEL;Statistilise masint\u00f5lke mudelid;Fi\u0161el, Mark;Center of Estonian Language Resources;2019;Issued: 2019-01-08;Updated: 2019-01-08;doi:10.15155/1-00-0000-0000-0000-00191L;Abstract;The models represented here are statistical phrase-based translation models. In parallel we are testing the various neural MT approaches, but for now the most usable baseline in terms of industrial collaborations is statistical.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b1d9a559-c46a-526a-bf90-1cdcc19f2d9c",
-    "notes": [
-        "Abstract",
-        "The models represented here are statistical phrase-based translation models. In parallel we are testing the various neural MT approaches, but for now the most usable baseline in terms of industrial collaborations is statistical."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17968156"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Statistilise masint\u00f5lke mudelid"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b24473e2-3399-5302-bb6c-f6ddfc1d59ab.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b24473e2-3399-5302-bb6c-f6ddfc1d59ab.json
deleted file mode 100644
index e611a77b..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b24473e2-3399-5302-bb6c-f6ddfc1d59ab.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0011EL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:8623653",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:8623653"
-    ],
-    "PublicationTimestamp": "2016-04-29T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Kaalep, Heiki-Jaan"
-    ],
-    "fulltext": "oai:oai.datacite.org:8623653;2019-04-20T05:01:28Z;ESTDOI;ESTDOI.KEEL;etTenTen korpus;Kaalep, Heiki-Jaan;Center of Estonian Language Resources;2016;Issued: 2016-04-29;Updated: 2016-04-29;doi:10.15155/1-00-0000-0000-0000-0011EL;Abstract;etTenTen korpus on internetist alla laetud eestikeelsete veebilehtede korpus.\nKorpuses on 270 miljonit s\u00f5na 686 000 veebilehelt.\nAlgmaterjal\n\nKorpuse tekstid korjas internetist ja teisendas utf-8 kodeeringus teksti kujule Vit Suchomel.\nVeebirobotiga laeti alla 1 173 702 veebilehte, kusjuures juba olemas olevate lehtede koopiad j\u00e4eti k\u00f5rvale; k\u00f5rvale j\u00e4eti ka lehed, mis on esindatud Eesti kirjakeele koondkorpuses. (http://www.cl.ut.ee/korpused/segakorpus/). Kasutati Jan Pomikaleki doktorit\u00f6\u00f6 k\u00e4igus loodud programme  jusText ja onion (code.google.com/p/justext, code.google.com/p/onion)",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b24473e2-3399-5302-bb6c-f6ddfc1d59ab",
-    "notes": [
-        "Abstract",
-        "etTenTen korpus on internetist alla laetud eestikeelsete veebilehtede korpus.\nKorpuses on 270 miljonit s\u00f5na 686 000 veebilehelt.\nAlgmaterjal\n\nKorpuse tekstid korjas internetist ja teisendas utf-8 kodeeringus teksti kujule Vit Suchomel.\nVeebirobotiga laeti alla 1 173 702 veebilehte, kusjuures juba olemas olevate lehtede koopiad j\u00e4eti k\u00f5rvale; k\u00f5rvale j\u00e4eti ka lehed, mis on esindatud Eesti kirjakeele koondkorpuses. (http://www.cl.ut.ee/korpused/segakorpus/). Kasutati Jan Pomikaleki doktorit\u00f6\u00f6 k\u00e4igus loodud programme  jusText ja onion (code.google.com/p/justext, code.google.com/p/onion)"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:8623653"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "etTenTen korpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b294efd0-a72b-53a6-8a3c-75e7bbf45ed8.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b294efd0-a72b-53a6-8a3c-75e7bbf45ed8.json
deleted file mode 100644
index 1449536c..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b294efd0-a72b-53a6-8a3c-75e7bbf45ed8.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06329L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10303603",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10303603"
-    ],
-    "PublicationTimestamp": "2017-01-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laansalu, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:10303603;2018-11-29T03:01:34Z;ESTDOI;ESTDOI.KEEL;Eesti Keele Instituudi m\u00f5isteline s\u00f5navarakartoteek;Laansalu, Tiina;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2017-01-31;doi:10.15155/3-00-0000-0000-0000-06329L;Abstract;M\u00f5istelise s\u00f5navarakartoteegi idee p\u00e4rineb Andrus Saarestelt. Kogumist\u00f6\u00f6 algas 1920ndatel ja kestis 1930ndate keskpaigani. M\u00f5istelises kogus on s\u00f5navara jaotatud mitte kihelkondade, vaid m\u00f5istete j\u00e4rgi. Materjali on kogutud j\u00e4rgmiste valdkondade kohta: abielu, aeg, aiandus, armuelu, ehitused, heinategu, ilmastik, inimene, kalandus, karjandus, keha, kehakatted, k\u00e4sit\u00f6\u00f6, liiklus, linat\u00f6\u00f6, loomastik, maap\u00f5uevarad, maastik, merelinnud, merendus, mesindus, metsandus, m\u00f5\u00f5dud, m\u00e4ngimine, m\u00e4rk, n\u00f5idus, n\u00f5ud, puut\u00f6\u00f6, p\u00f5llundus, suguv\u00f5sa, s\u00f5idukid, taevalaotus, tahtmine, taimestik, tervis, toitlus, tuli, tundeelu, tunnetamine, t\u00f6\u00f6, usund, veekogud, vees\u00f5idukid, viin, vill, v\u00e4rv, \u00f5igus ja \u00fchiskond.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b294efd0-a72b-53a6-8a3c-75e7bbf45ed8",
-    "notes": [
-        "Abstract",
-        "M\u00f5istelise s\u00f5navarakartoteegi idee p\u00e4rineb Andrus Saarestelt. Kogumist\u00f6\u00f6 algas 1920ndatel ja kestis 1930ndate keskpaigani. M\u00f5istelises kogus on s\u00f5navara jaotatud mitte kihelkondade, vaid m\u00f5istete j\u00e4rgi. Materjali on kogutud j\u00e4rgmiste valdkondade kohta: abielu, aeg, aiandus, armuelu, ehitused, heinategu, ilmastik, inimene, kalandus, karjandus, keha, kehakatted, k\u00e4sit\u00f6\u00f6, liiklus, linat\u00f6\u00f6, loomastik, maap\u00f5uevarad, maastik, merelinnud, merendus, mesindus, metsandus, m\u00f5\u00f5dud, m\u00e4ngimine, m\u00e4rk, n\u00f5idus, n\u00f5ud, puut\u00f6\u00f6, p\u00f5llundus, suguv\u00f5sa, s\u00f5idukid, taevalaotus, tahtmine, taimestik, tervis, toitlus, tuli, tundeelu, tunnetamine, t\u00f6\u00f6, usund, veekogud, vees\u00f5idukid, viin, vill, v\u00e4rv, \u00f5igus ja \u00fchiskond."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10303603"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti Keele Instituudi m\u00f5isteline s\u00f5navarakartoteek"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b2c389af-9617-52fc-af33-e44c0c8ee733.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b2c389af-9617-52fc-af33-e44c0c8ee733.json
deleted file mode 100644
index c06251c7..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b2c389af-9617-52fc-af33-e44c0c8ee733.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06328L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10303586",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10303586"
-    ],
-    "PublicationTimestamp": "2017-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Ross, Kristiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:10303586;2019-04-03T07:01:17Z;ESTDOI;ESTDOI.KEEL;Eesti piiblit\u00f5lke ajalooline konkordants;The Historical Concordance of Estonian Bible Translations;Ross, Kristiina;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2017-02-15;doi:10.15155/3-00-0000-0000-0000-06328L;Abstract;Andmebaasi eesm\u00e4rk on pakkuda \u00fclevaadet vaimuliku eesti keele kujunemisloost 17. sajandil ja 18. sajandi alguses. Andmebaas sisaldab t\u00f5lketekste ja nende p\u00f5hjal koostatud s\u00f5nastikku ning v\u00f5imaldab (valminud osades) otsinguid a) autorite v\u00f5i tekstide kaupa, b) kindla piiblikoha j\u00e4rgi ning c) t\u00e4nap\u00e4evastatud m\u00e4rks\u00f5na j\u00e4rgi.;Abstract;The aim of the database is to provide a survey of the evolution of spiritual Estonian in the 17th and beginning of the 18th centuries. The database contains text translations and glossaries to them, enabling searches (on completed parts) a) by authors or texts, b) by passage, c) by a modernised keyword.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b2c389af-9617-52fc-af33-e44c0c8ee733",
-    "notes": [
-        "Abstract",
-        "Andmebaasi eesm\u00e4rk on pakkuda \u00fclevaadet vaimuliku eesti keele kujunemisloost 17. sajandil ja 18. sajandi alguses. Andmebaas sisaldab t\u00f5lketekste ja nende p\u00f5hjal koostatud s\u00f5nastikku ning v\u00f5imaldab (valminud osades) otsinguid a) autorite v\u00f5i tekstide kaupa, b) kindla piiblikoha j\u00e4rgi ning c) t\u00e4nap\u00e4evastatud m\u00e4rks\u00f5na j\u00e4rgi.",
-        "Abstract",
-        "The aim of the database is to provide a survey of the evolution of spiritual Estonian in the 17th and beginning of the 18th centuries. The database contains text translations and glossaries to them, enabling searches (on completed parts) a) by authors or texts, b) by passage, c) by a modernised keyword."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10303586"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti piiblit\u00f5lke ajalooline konkordants",
-        "The Historical Concordance of Estonian Bible Translations"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b2edd9dd-d191-54ef-a366-757bb1098f60.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b2edd9dd-d191-54ef-a366-757bb1098f60.json
deleted file mode 100644
index 8496745a..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b2edd9dd-d191-54ef-a366-757bb1098f60.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-071E9L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14560062",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14560062"
-    ],
-    "PublicationTimestamp": "2018-03-26T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Koppel, Kristina",
-        "Kallas, Jelena"
-    ],
-    "fulltext": "oai:oai.datacite.org:14560062;2019-04-18T17:36:49Z;ESTDOI;ESTDOI.KEEL;Eesti keele A1-C1 \u00f5pikute korpus 2018;Estonian Coursebook Corpus 2018;Kallas, Jelena;Koppel, Kristina;Center of Estonian Language Resources;2018;Issued: 2018-03-26;Updated: 2018-03-26;doi:10.15155/3-00-0000-0000-0000-071E9L;Abstract;Korpus sisaldab A1, A2, B1, B2 ja C1 keeleoskustasemega eesti keele \u00f5ppijatele suunatud \u00f5pikute tekstidest eraldatud t\u00e4islauseid. Korpuses on m\u00e4rgendatud tekstistruktuuri \u00fcksused lause <sentence> ja osalause <clause>. K\u00f5ik korpuse laused on keeletaseme piirides unikaalsed.\nKorpuse aluseks on Eesti keele A1-C1 \u00f5pikute korpus 2017, mis koosnes ca 200 000 s\u00f5nest ja ca 24 000 lausest. Eesti keele A1-C1 \u00f5pikute korpuse 2017 sisust ekstraheeritud t\u00e4islausetest loodigi Eesti keele A1-C1 \u00f5pikute korpus 2018, millega kaasnes k\u00e4sitsi kontroll (sisse j\u00e4eti semantiliselt terviklikud laused, kontekstisidusad ja valesti tuvastatud laused j\u00e4eti v\u00e4lja). \nKorpuses on kaheksa \u00f5pikut:\nPesti, M., Ahi, H. (2015). E nagu Eesti: eesti keele \u00f5pik algajatele. Tallinn: Kiri-Mari Kirjastus.\nKitsnik, M., Kingisepp, L. (2002). Avatud uksed: eesti keele \u00f5ppekomplekt kesk- ja k\u00f5rgtasemele: \u00f5pperaamat. Tallinn: TEA Kirjastus.\nKitsnik, M. (2012). Eesti keele \u00f5pik: B1, B2. Tallinn: M. Kitsnik.\nPesti, M., Ahi, H. (2015). Eesti keele \u00f5pik A1. Tallinn: Justiitsministeerium.\nPesti, M., Ahi, H. (2012). Eesti keele \u00f5pik A2. Tallinn: M. Pesti.\nPesti, M., Ahi, H. (2015). Eesti keele \u00f5pik B1. Tallinn: Justiitsministeerium.\nSooneste, M. (2007). Eesti keele \u00f5pik: vene \u00f5ppekeelega g\u00fcmnaasium: kesk- ja k\u00f5rgtase. Tallinn: Varrak.\nRammo, S., Teral, M., Klaas-Lang, B., Allik, M. (2012). Keel selgeks!: eesti keele \u00f5pik t\u00e4iskasvanutele. Tallinn: Avita.\nSeitse esimest \u00f5pikut digitaliseeriti Eesti Rahvusraamatkogu digitaliseerimiskeskus. Sirje Rammo jt (2012) \u00f5pikust on kasutatud k\u00e4sikirja doc-faile. \nKorpus on UTF-8 kodeeringus. Korpus on lemmatiseeritud, m\u00e4rgendatud ja \u00fchestatud anal\u00fcsaatori EstNLTK abil.\nKorpus loodi Eesti Keele Instituudi ja Lexical Computing Ltd. koost\u00f6\u00f6s.\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b2edd9dd-d191-54ef-a366-757bb1098f60",
-    "notes": [
-        "Abstract",
-        "Korpus sisaldab A1, A2, B1, B2 ja C1 keeleoskustasemega eesti keele \u00f5ppijatele suunatud \u00f5pikute tekstidest eraldatud t\u00e4islauseid. Korpuses on m\u00e4rgendatud tekstistruktuuri \u00fcksused lause <sentence> ja osalause <clause>. K\u00f5ik korpuse laused on keeletaseme piirides unikaalsed.\nKorpuse aluseks on Eesti keele A1-C1 \u00f5pikute korpus 2017, mis koosnes ca 200 000 s\u00f5nest ja ca 24 000 lausest. Eesti keele A1-C1 \u00f5pikute korpuse 2017 sisust ekstraheeritud t\u00e4islausetest loodigi Eesti keele A1-C1 \u00f5pikute korpus 2018, millega kaasnes k\u00e4sitsi kontroll (sisse j\u00e4eti semantiliselt terviklikud laused, kontekstisidusad ja valesti tuvastatud laused j\u00e4eti v\u00e4lja). \nKorpuses on kaheksa \u00f5pikut:\nPesti, M., Ahi, H. (2015). E nagu Eesti: eesti keele \u00f5pik algajatele. Tallinn: Kiri-Mari Kirjastus.\nKitsnik, M., Kingisepp, L. (2002). Avatud uksed: eesti keele \u00f5ppekomplekt kesk- ja k\u00f5rgtasemele: \u00f5pperaamat. Tallinn: TEA Kirjastus.\nKitsnik, M. (2012). Eesti keele \u00f5pik: B1, B2. Tallinn: M. Kitsnik.\nPesti, M., Ahi, H. (2015). Eesti keele \u00f5pik A1. Tallinn: Justiitsministeerium.\nPesti, M., Ahi, H. (2012). Eesti keele \u00f5pik A2. Tallinn: M. Pesti.\nPesti, M., Ahi, H. (2015). Eesti keele \u00f5pik B1. Tallinn: Justiitsministeerium.\nSooneste, M. (2007). Eesti keele \u00f5pik: vene \u00f5ppekeelega g\u00fcmnaasium: kesk- ja k\u00f5rgtase. Tallinn: Varrak.\nRammo, S., Teral, M., Klaas-Lang, B., Allik, M. (2012). Keel selgeks!: eesti keele \u00f5pik t\u00e4iskasvanutele. Tallinn: Avita.\nSeitse esimest \u00f5pikut digitaliseeriti Eesti Rahvusraamatkogu digitaliseerimiskeskus. Sirje Rammo jt (2012) \u00f5pikust on kasutatud k\u00e4sikirja doc-faile. \nKorpus on UTF-8 kodeeringus. Korpus on lemmatiseeritud, m\u00e4rgendatud ja \u00fchestatud anal\u00fcsaatori EstNLTK abil.\nKorpus loodi Eesti Keele Instituudi ja Lexical Computing Ltd. koost\u00f6\u00f6s.\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14560062"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele A1-C1 \u00f5pikute korpus 2018",
-        "Estonian Coursebook Corpus 2018"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b37b358e-556c-5916-bf85-e991d607449f.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b37b358e-556c-5916-bf85-e991d607449f.json
deleted file mode 100644
index 305d63ae..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b37b358e-556c-5916-bf85-e991d607449f.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06337L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10303969",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10303969"
-    ],
-    "PublicationTimestamp": "2017-01-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laansalu, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:10303969;2019-04-04T14:31:06Z;ESTDOI;ESTDOI.KEEL;Eesti murrete s\u00f5naraamat (24.\u201428. vihik; l\u00f5petis\u2014nina\u00f5rs);Laansalu, Tiina;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2017-01-31;doi:10.15155/3-00-0000-0000-0000-06337L;Abstract;Eesti murrete s\u00f5naraamat haarab v\u00f5imalikult kogu murdes\u00f5navara. S\u00f5nu saadab h\u00e4\u00e4likuline ja grammatiline iseloomustus, levik ning selgub s\u00f5nade t\u00e4hendus. N\u00e4itelaused toovad esile murdes\u00f5nadega seotud t\u00e4henduslikke ja grammatilisi n\u00e4htusi.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b37b358e-556c-5916-bf85-e991d607449f",
-    "notes": [
-        "Abstract",
-        "Eesti murrete s\u00f5naraamat haarab v\u00f5imalikult kogu murdes\u00f5navara. S\u00f5nu saadab h\u00e4\u00e4likuline ja grammatiline iseloomustus, levik ning selgub s\u00f5nade t\u00e4hendus. N\u00e4itelaused toovad esile murdes\u00f5nadega seotud t\u00e4henduslikke ja grammatilisi n\u00e4htusi."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10303969"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti murrete s\u00f5naraamat (24.\u201428. vihik; l\u00f5petis\u2014nina\u00f5rs)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b42b186e-73e9-51e2-b277-74cd973ea76f.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b42b186e-73e9-51e2-b277-74cd973ea76f.json
deleted file mode 100644
index 4b051f15..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b42b186e-73e9-51e2-b277-74cd973ea76f.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-0008FL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:13902334",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:13902334"
-    ],
-    "PublicationTimestamp": "2018-01-24T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "J\u00e4rv, Risto",
-        "Oras, Janika"
-    ],
-    "fulltext": "oai:oai.datacite.org:13902334;2019-04-17T17:26:53Z;ESTDOI;ESTDOI.KEEL;Eesti regilaulud;Estonian Runic Songs' Database;J\u00e4rv, Risto;Oras, Janika;Center of Estonian Language Resources;2017;Issued: 2017-05-30;Updated: 2018-01-24;doi:10.15155/9-00-0000-0000-0000-0008FL;Abstract;Regilaulude andmebaas sisaldab 85 490 regilauluteksti, ligi kaks kolmandikku Eesti Rahvaluule Arhiivis talletatud regilaulutekstidest. Andmebaasist leiab vanema osa regilaulude kirjapanekutest \u2013 19. sajandil ja 20. sajandi alguk\u00fcmnenditel kogutud tekstid. Lisaks regilauludele on andmebaasis ka u 6000 siirdevormilist ja l\u00f5ppriimilist laulu. Tekste lisatakse j\u00e4rjest juurde. Andmebaasi on v\u00f5imalik kasutada nimetatud veebilehe kaudu v\u00f5i (\u00fchtse tekstikorpusena kasutamiseks) kontakteerudes kontaktisikutega.;Abstract;Estonian Runic Songs\u2019 Database contains 85 490 texts of runic songs - nearly two thirds of all runic songs\u2019 texts from the Estonian Folklore Archives. These are the oldest text recordings of Estonian runic songs (the text recordings were created in the 19th century and in the first decades of the 20th century). In addition to the runic songs, the database also has songs of transitional form and end-rhymed songs (about 6000). Texts are being added constantly. Please send an e-mail to contactpersons for access to full text corpus.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b42b186e-73e9-51e2-b277-74cd973ea76f",
-    "notes": [
-        "Abstract",
-        "Regilaulude andmebaas sisaldab 85 490 regilauluteksti, ligi kaks kolmandikku Eesti Rahvaluule Arhiivis talletatud regilaulutekstidest. Andmebaasist leiab vanema osa regilaulude kirjapanekutest \u2013 19. sajandil ja 20. sajandi alguk\u00fcmnenditel kogutud tekstid. Lisaks regilauludele on andmebaasis ka u 6000 siirdevormilist ja l\u00f5ppriimilist laulu. Tekste lisatakse j\u00e4rjest juurde. Andmebaasi on v\u00f5imalik kasutada nimetatud veebilehe kaudu v\u00f5i (\u00fchtse tekstikorpusena kasutamiseks) kontakteerudes kontaktisikutega.",
-        "Abstract",
-        "Estonian Runic Songs\u2019 Database contains 85 490 texts of runic songs - nearly two thirds of all runic songs\u2019 texts from the Estonian Folklore Archives. These are the oldest text recordings of Estonian runic songs (the text recordings were created in the 19th century and in the first decades of the 20th century). In addition to the runic songs, the database also has songs of transitional form and end-rhymed songs (about 6000). Texts are being added constantly. Please send an e-mail to contactpersons for access to full text corpus."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:13902334"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti regilaulud",
-        "Estonian Runic Songs' Database"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b46e7175-8051-5d95-9ca4-afdce36c6d06.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b46e7175-8051-5d95-9ca4-afdce36c6d06.json
deleted file mode 100644
index 11f5a851..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b46e7175-8051-5d95-9ca4-afdce36c6d06.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-0730AL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14673193",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14673193"
-    ],
-    "PublicationTimestamp": "2018-04-13T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:14673193;2019-03-30T00:32:56Z;ESTDOI;ESTDOI.KEEL;V\u00f5\u00f5rnimede ja l\u00fchendite h\u00e4\u00e4lduss\u00f5nastiku andmebaas;Hein, Indrek;Center of Estonian Language Resources;2018;Issued: 2018-04-13;Updated: 2018-04-13;doi:10.15155/3-00-0000-0000-0000-0730AL;Abstract;H\u00e4\u00e4lduss\u00f5nastik on m\u00f5eldud tekstis esinevate v\u00f5\u00f5rnimede, l\u00fchendite ja tundmatute s\u00f5nede teisendamiseks eestikeelse k\u00f5nes\u00fcntesaatori sisendile sobiva h\u00e4\u00e4lduse vormi. S\u00f5nastiku andmebaas on eksporditav, lihtsalt kasutatav ja hallatav eestikeelset teksti k\u00f5neks teisendavates rakendustes. \nLitsents: http://www.eki.ee/eki/litsents.html",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b46e7175-8051-5d95-9ca4-afdce36c6d06",
-    "notes": [
-        "Abstract",
-        "H\u00e4\u00e4lduss\u00f5nastik on m\u00f5eldud tekstis esinevate v\u00f5\u00f5rnimede, l\u00fchendite ja tundmatute s\u00f5nede teisendamiseks eestikeelse k\u00f5nes\u00fcntesaatori sisendile sobiva h\u00e4\u00e4lduse vormi. S\u00f5nastiku andmebaas on eksporditav, lihtsalt kasutatav ja hallatav eestikeelset teksti k\u00f5neks teisendavates rakendustes. \nLitsents: http://www.eki.ee/eki/litsents.html"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14673193"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "V\u00f5\u00f5rnimede ja l\u00fchendite h\u00e4\u00e4lduss\u00f5nastiku andmebaas"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b4c8d8f4-146b-5627-a9d8-848af5353b60.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b4c8d8f4-146b-5627-a9d8-848af5353b60.json
deleted file mode 100644
index 45810270..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b4c8d8f4-146b-5627-a9d8-848af5353b60.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-00020L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5755416",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5755416"
-    ],
-    "PublicationTimestamp": "2015-05-21T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Meister, Einar"
-    ],
-    "fulltext": "oai:oai.datacite.org:5755416;2019-04-17T17:26:05Z;ESTDOI;ESTDOI.KEEL;Eesti Speechdat andmebaas;Estonian Speechdat-like Database;Meister, Einar;Center of Estonian Language Resources;2014;Issued: 2014-12-31;Updated: 2015-05-21;doi:10.15155/9-00-0000-0000-0000-00020L;Abstract;Korpus SpeechDat formaadis.;Abstract;Estonian speech corpus based on SpeechDat format",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b4c8d8f4-146b-5627-a9d8-848af5353b60",
-    "notes": [
-        "Abstract",
-        "Korpus SpeechDat formaadis.",
-        "Abstract",
-        "Estonian speech corpus based on SpeechDat format"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5755416"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti Speechdat andmebaas",
-        "Estonian Speechdat-like Database"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b4d92479-016e-5ecc-9974-3094a4eafa7f.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b4d92479-016e-5ecc-9974-3094a4eafa7f.json
deleted file mode 100644
index 029e6597..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b4d92479-016e-5ecc-9974-3094a4eafa7f.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05BD8L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9474538",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9474538"
-    ],
-    "PublicationTimestamp": "2017-03-03T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:9474538;2019-04-17T17:25:42Z;ESTDOI;ESTDOI.KEEL;Huvihariduss\u00f5nastik;The Dictionary of Extracurricular Activities ;Hein, Indrek;Center of Estonian Language Resources;2016;Issued: 2016-11-09;Updated: 2017-03-03;doi:10.15155/3-00-0000-0000-0000-05BD8L;Abstract;S\u00f5nastik sisaldab huvidele vastava \u00f5ppet\u00f6\u00f6v\u00e4lise hariduse valdkonda kuuluvaid m\u00f5isteid koos t\u00e4henduse seletuse ning vastetega inglise, saksa, soome ja vene keeles.;Abstract;Contains special terms from the field of extracurricular activities and interests provided with Estonian explanations and English, German, Finnish and Russian equivalents.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b4d92479-016e-5ecc-9974-3094a4eafa7f",
-    "notes": [
-        "Abstract",
-        "S\u00f5nastik sisaldab huvidele vastava \u00f5ppet\u00f6\u00f6v\u00e4lise hariduse valdkonda kuuluvaid m\u00f5isteid koos t\u00e4henduse seletuse ning vastetega inglise, saksa, soome ja vene keeles.",
-        "Abstract",
-        "Contains special terms from the field of extracurricular activities and interests provided with Estonian explanations and English, German, Finnish and Russian equivalents."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9474538"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Huvihariduss\u00f5nastik",
-        "The Dictionary of Extracurricular Activities "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b54fbbbb-9f3a-57b0-8455-a6768a0d30f6.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b54fbbbb-9f3a-57b0-8455-a6768a0d30f6.json
deleted file mode 100644
index d67698b2..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b54fbbbb-9f3a-57b0-8455-a6768a0d30f6.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/FIL.000F",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:4597368",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:4597368"
-    ],
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Kaalep, Heiki-Jaan"
-    ],
-    "fulltext": "oai:oai.datacite.org:4597368;2019-01-24T12:31:07Z;ESTDOI;ESTDOI.KEEL;Morphological analyzer for Estonian ESTMORF;Kaalep, Heiki-Jaan;Center of Estonian Language Resources;2013;doi:10.15155/FIL.000F",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b54fbbbb-9f3a-57b0-8455-a6768a0d30f6",
-    "oai_identifier": [
-        "oai:oai.datacite.org:4597368"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Morphological analyzer for Estonian ESTMORF"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b56f5517-c095-5086-90a8-e04ae8fa0f8e.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b56f5517-c095-5086-90a8-e04ae8fa0f8e.json
deleted file mode 100644
index 25df6cdb..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b56f5517-c095-5086-90a8-e04ae8fa0f8e.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-079D9L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17960238",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17960238"
-    ],
-    "PublicationTimestamp": "2019-01-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:17960238;2019-03-26T01:31:52Z;ESTDOI;ESTDOI.KEEL;H\u00e4\u00e4ldusbaas;Pronunciation database;Hein, Indrek;Center of Estonian Language Resources;2019;Issued: 2019-01-07;Updated: 2019-01-07;doi:10.15155/3-00-0000-0000-0000-079D9L;Abstract;V\u00f5\u00f5rnimede ja l\u00fchendite h\u00e4\u00e4lduse andmebaas;Abstract;Database of Estonian pronunciation for foreign names and abbreviations",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b56f5517-c095-5086-90a8-e04ae8fa0f8e",
-    "notes": [
-        "Abstract",
-        "V\u00f5\u00f5rnimede ja l\u00fchendite h\u00e4\u00e4lduse andmebaas",
-        "Abstract",
-        "Database of Estonian pronunciation for foreign names and abbreviations"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17960238"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "H\u00e4\u00e4ldusbaas",
-        "Pronunciation database"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b6a0bcf4-f01f-52c1-8cc6-99eb71a2a54b.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b6a0bcf4-f01f-52c1-8cc6-99eb71a2a54b.json
deleted file mode 100644
index eb7d397e..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b6a0bcf4-f01f-52c1-8cc6-99eb71a2a54b.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00152L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14186194",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14186194"
-    ],
-    "PublicationTimestamp": "2018-02-06T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Lippus, P\u00e4rtel"
-    ],
-    "fulltext": "oai:oai.datacite.org:14186194;2019-03-20T18:37:23Z;ESTDOI;ESTDOI.KEEL;Mok\u0161a prosoodia korpus;Moksha prosody corpus;Lippus, P\u00e4rtel;Center of Estonian Language Resources;2018;Issued: 2018-02-06;Updated: 2018-02-06;doi:10.15155/1-00-0000-0000-0000-00152L;Abstract;95 loetud lausest koosnev andmestik, iga lause sisaldab kaks 1-3-silbilist tests\u00f5na. Salvestused kokku 28 keelejuhilt. Materjali kasutati raamatus: Aasm\u00e4e, N., Lippus, P., Pajusalu, K., Salveste, N., Zirnask, T., & Viitso, T.-R. (2013). Moksha prosody. Helsinki: Suomalais-Ugrilainen Seura. Retrieved from http://www.sgr.fi/sust/sust268/sust268.pdf;Abstract;The data consists of 95 test words consisting of 1-3 syllables. The word list is created by Tiit-Rein Viitso. The test words were embedded in a carrier sentence occurring once in the phrase-final position and once in the sentece final position. Recordings from 28 speakers. \n\nThe data was used for Aasm\u00e4e, N., Lippus, P., Pajusalu, K., Salveste, N., Zirnask, T., & Viitso, T.-R. (2013). Moksha prosody. Helsinki: Suomalais-Ugrilainen Seura. Retrieved from http://www.sgr.fi/sust/sust268/sust268.pdf",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b6a0bcf4-f01f-52c1-8cc6-99eb71a2a54b",
-    "notes": [
-        "Abstract",
-        "95 loetud lausest koosnev andmestik, iga lause sisaldab kaks 1-3-silbilist tests\u00f5na. Salvestused kokku 28 keelejuhilt. Materjali kasutati raamatus: Aasm\u00e4e, N., Lippus, P., Pajusalu, K., Salveste, N., Zirnask, T., & Viitso, T.-R. (2013). Moksha prosody. Helsinki: Suomalais-Ugrilainen Seura. Retrieved from http://www.sgr.fi/sust/sust268/sust268.pdf",
-        "Abstract",
-        "The data consists of 95 test words consisting of 1-3 syllables. The word list is created by Tiit-Rein Viitso. The test words were embedded in a carrier sentence occurring once in the phrase-final position and once in the sentece final position. Recordings from 28 speakers. \n\nThe data was used for Aasm\u00e4e, N., Lippus, P., Pajusalu, K., Salveste, N., Zirnask, T., & Viitso, T.-R. (2013). Moksha prosody. Helsinki: Suomalais-Ugrilainen Seura. Retrieved from http://www.sgr.fi/sust/sust268/sust268.pdf"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14186194"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Mok\u0161a prosoodia korpus",
-        "Moksha prosody corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b735062a-1146-5632-9cb4-a8290262125a.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b735062a-1146-5632-9cb4-a8290262125a.json
deleted file mode 100644
index 6ce73f23..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b735062a-1146-5632-9cb4-a8290262125a.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-07002L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14277523",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14277523"
-    ],
-    "PublicationTimestamp": "2018-02-22T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Kallasmaa, Marja",
-        "P\u00e4ll, Peeter"
-    ],
-    "fulltext": "oai:oai.datacite.org:14277523;2019-04-06T10:02:38Z;ESTDOI;ESTDOI.KEEL;Eesti kohanimeraamat;P\u00e4ll, Peeter;Kallasmaa, Marja;Center of Estonian Language Resources;2018;Issued: 2018-02-22;Updated: 2018-02-22;doi:10.15155/3-00-0000-0000-0000-07002L;Abstract;Dictionary of Estonian Place Names\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b735062a-1146-5632-9cb4-a8290262125a",
-    "notes": [
-        "Abstract",
-        "Dictionary of Estonian Place Names\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14277523"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti kohanimeraamat"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b8229c60-6e9a-58aa-bed2-e94bd4575070.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b8229c60-6e9a-58aa-bed2-e94bd4575070.json
deleted file mode 100644
index c5de0269..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b8229c60-6e9a-58aa-bed2-e94bd4575070.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-00023L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5755421",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5755421"
-    ],
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Meister, Einar"
-    ],
-    "fulltext": "oai:oai.datacite.org:5755421;2019-04-03T05:02:10Z;ESTDOI;ESTDOI.KEEL;Loengute korpus;Corpus of Lecture Speech;Meister, Einar;Center of Estonian Language Resources;2014;Issued: 2014-12-30;Updated: 2019-01-08;doi:10.15155/9-00-0000-0000-0000-00023L;Abstract;Korpus sisaldab akadeemiliste loengute ja suuliste konverentsiettekannete salvestisi.;Abstract;Corpus includes recordings of academic lectures and oral conference presentations.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b8229c60-6e9a-58aa-bed2-e94bd4575070",
-    "notes": [
-        "Abstract",
-        "Korpus sisaldab akadeemiliste loengute ja suuliste konverentsiettekannete salvestisi.",
-        "Abstract",
-        "Corpus includes recordings of academic lectures and oral conference presentations."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5755421"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Loengute korpus",
-        "Corpus of Lecture Speech"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b867f3ee-626a-5661-a7ae-e1f5990ddfd3.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b867f3ee-626a-5661-a7ae-e1f5990ddfd3.json
deleted file mode 100644
index 0fd90dc9..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b867f3ee-626a-5661-a7ae-e1f5990ddfd3.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-000A2L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17968027",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17968027"
-    ],
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Ross, Peeter"
-    ],
-    "fulltext": "oai:oai.datacite.org:17968027;2019-02-03T06:01:50Z;ESTDOI;ESTDOI.KEEL;Radioloogiavastuste terminikasutuse alusel koostatud l\u00fchendis\u00f5nastik;Ross, Peeter;Center of Estonian Language Resources;2019;Issued: 2019-01-08;Updated: 2019-01-08;doi:10.15155/9-00-0000-0000-0000-000A2L;Abstract;L\u00fchendis\u00f5nastik on koostatud meditsiinikeele korpuse alusel (korpuse ja l\u00fchendite tuvastamise kirjeldus: E. Valdre, P. Ross, K. Tsepelina, K. Veskis, T. Vaino, H-J. Kaalep, Radioloogiauuringute vastuste l\u00fchendite ja l\u00fchendamise korpuslingvistiline anal\u00fc\u00fcs\u201c, Eesti Arst 2014, 93(9):502 \u2013512)). S\u00f5nastik on esitaud Excel failina kujul: m\u00f5iste, k\u00f5ik sellele vastavad l\u00fchendid korpuses esinenud kujul (kuid muutel\u00f5ppudeta), l\u00fchendi esinemiskordade arv, l\u00fchendile vastava m\u00f5iste k\u00f5igi l\u00fchendivariantide esinemiskordade arv, l\u00fchendi eeldatav algup\u00e4ra keel (eesti, ladina, inglise), l\u00fchendi allkeel (\u00fcldkeel, oskuskeel), m\u00f5istega seotud valdkond ja alavaldkonnad, teadaolevad eestikeelsed s\u00fcnon\u00fc\u00fcmid ning ladina- ja ingliskeelsed vasted. M\u00e4rkusena tuleb lisada, et seoses meditsiini arengutrendidega ei oma k\u00f5ik m\u00f5isted vasteid k\u00f5igis keeltes. ",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b867f3ee-626a-5661-a7ae-e1f5990ddfd3",
-    "notes": [
-        "Abstract",
-        "L\u00fchendis\u00f5nastik on koostatud meditsiinikeele korpuse alusel (korpuse ja l\u00fchendite tuvastamise kirjeldus: E. Valdre, P. Ross, K. Tsepelina, K. Veskis, T. Vaino, H-J. Kaalep, Radioloogiauuringute vastuste l\u00fchendite ja l\u00fchendamise korpuslingvistiline anal\u00fc\u00fcs\u201c, Eesti Arst 2014, 93(9):502 \u2013512)). S\u00f5nastik on esitaud Excel failina kujul: m\u00f5iste, k\u00f5ik sellele vastavad l\u00fchendid korpuses esinenud kujul (kuid muutel\u00f5ppudeta), l\u00fchendi esinemiskordade arv, l\u00fchendile vastava m\u00f5iste k\u00f5igi l\u00fchendivariantide esinemiskordade arv, l\u00fchendi eeldatav algup\u00e4ra keel (eesti, ladina, inglise), l\u00fchendi allkeel (\u00fcldkeel, oskuskeel), m\u00f5istega seotud valdkond ja alavaldkonnad, teadaolevad eestikeelsed s\u00fcnon\u00fc\u00fcmid ning ladina- ja ingliskeelsed vasted. M\u00e4rkusena tuleb lisada, et seoses meditsiini arengutrendidega ei oma k\u00f5ik m\u00f5isted vasteid k\u00f5igis keeltes. "
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17968027"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Radioloogiavastuste terminikasutuse alusel koostatud l\u00fchendis\u00f5nastik"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b89d4dfe-1fda-5a9c-bc65-c79196ca1e06.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b89d4dfe-1fda-5a9c-bc65-c79196ca1e06.json
deleted file mode 100644
index 72007af7..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b89d4dfe-1fda-5a9c-bc65-c79196ca1e06.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00143L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:13446393",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:13446393"
-    ],
-    "PublicationTimestamp": "2017-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laur, Sven"
-    ],
-    "fulltext": "oai:oai.datacite.org:13446393;2019-04-22T16:31:47Z;ESTDOI;ESTDOI.KEEL;EstNLTK tokenizer;Laur, Sven;Center of Estonian Language Resources;2017;Issued: 2017-12-11;Updated: 2017-12-11;doi:10.15155/1-00-0000-0000-0000-00143L;Abstract;Word tokenizer from the Estonian NLTK toolkit",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b89d4dfe-1fda-5a9c-bc65-c79196ca1e06",
-    "notes": [
-        "Abstract",
-        "Word tokenizer from the Estonian NLTK toolkit"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:13446393"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "EstNLTK tokenizer"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b8c858bc-7485-5faa-b5a7-7b4bd9456f73.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b8c858bc-7485-5faa-b5a7-7b4bd9456f73.json
deleted file mode 100644
index e040681d..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/b8c858bc-7485-5faa-b5a7-7b4bd9456f73.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05BE0L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9474546",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9474546"
-    ],
-    "PublicationTimestamp": "2016-11-09T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:9474546;2019-02-23T19:02:00Z;ESTDOI;ESTDOI.KEEL;Inglise-eesti meres\u00f5naraamat;Hein, Indrek;Center of Estonian Language Resources;2016;Issued: 2016-11-09;Updated: 2016-11-09;doi:10.15155/3-00-0000-0000-0000-05BE0L;Abstract;Sisaldab \u00fcle 30 000 m\u00e4rks\u00f5na. Peale merenduslike tavaterminite leiab s\u00f5naraamatust ka purjelaevu, puulaevu, merekaubandust, mere\u00f5igust, merekindlustust, konteinervedusid, kalandust, s\u00f5jalaevastikku, raadiolokatsiooni, h\u00fcdromehaanikat, okeanograafiat, purjesporti jms puutuvaid s\u00f5nu.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "b8c858bc-7485-5faa-b5a7-7b4bd9456f73",
-    "notes": [
-        "Abstract",
-        "Sisaldab \u00fcle 30 000 m\u00e4rks\u00f5na. Peale merenduslike tavaterminite leiab s\u00f5naraamatust ka purjelaevu, puulaevu, merekaubandust, mere\u00f5igust, merekindlustust, konteinervedusid, kalandust, s\u00f5jalaevastikku, raadiolokatsiooni, h\u00fcdromehaanikat, okeanograafiat, purjesporti jms puutuvaid s\u00f5nu."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9474546"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Inglise-eesti meres\u00f5naraamat"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ba0bd01f-8c7d-5b3d-a954-82e37887f90a.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ba0bd01f-8c7d-5b3d-a954-82e37887f90a.json
deleted file mode 100644
index 553f3244..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ba0bd01f-8c7d-5b3d-a954-82e37887f90a.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00179L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17945049",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17945049"
-    ],
-    "PublicationTimestamp": "2019-01-03T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:17945049;2019-01-03T13:26:19Z;ESTDOI;ESTDOI.KEEL;Kollokatsioonide tuvastaja;Muischnek, Kadri;Center of Estonian Language Resources;2019;Issued: 2019-01-03;Updated: 2019-01-03;doi:10.15155/1-00-0000-0000-0000-00179L;Abstract;Kollokatsioonid on sellised s\u00f5napaarid, mille liikmed esinevad \u00fcksteise naabruses sagedamini kui v\u00f5iks eeldada nende \u00fcksikult esinemise sageduste p\u00f5hjal. T\u00fc\u00fcpilised kollokatsioonid on p\u00fcsi\u00fchendid - n\u00e4iteks \u00fchendverbid v\u00f5i idiomaatilised v\u00e4ljendid. P\u00fcsi\u00fchendid v\u00f5ivad muidugi koosneda ka rohkem kui kahest s\u00f5nast, kuid meie kollokatsioonide otsija suudab tuvastada ainult kahes\u00f5nalisi \u00fchendeid.\n\nKollokatsioonide otsimisel arvestatakse v\u00f5imalike kollokaatide kandidaatidena samas osalauses esinevaid s\u00f5navorme v\u00f5i lemmasid.\n\nKollokatsioone saab otsida kolmel viisil:\n\n1) teatud lemma olulisi kollokaate s\u00f5navormidena\n2) teatud lemma olulisi kollokaate lemmadena\n3) teatud s\u00f5navormi olulisi kollokaate s\u00f5navormidena\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ba0bd01f-8c7d-5b3d-a954-82e37887f90a",
-    "notes": [
-        "Abstract",
-        "Kollokatsioonid on sellised s\u00f5napaarid, mille liikmed esinevad \u00fcksteise naabruses sagedamini kui v\u00f5iks eeldada nende \u00fcksikult esinemise sageduste p\u00f5hjal. T\u00fc\u00fcpilised kollokatsioonid on p\u00fcsi\u00fchendid - n\u00e4iteks \u00fchendverbid v\u00f5i idiomaatilised v\u00e4ljendid. P\u00fcsi\u00fchendid v\u00f5ivad muidugi koosneda ka rohkem kui kahest s\u00f5nast, kuid meie kollokatsioonide otsija suudab tuvastada ainult kahes\u00f5nalisi \u00fchendeid.\n\nKollokatsioonide otsimisel arvestatakse v\u00f5imalike kollokaatide kandidaatidena samas osalauses esinevaid s\u00f5navorme v\u00f5i lemmasid.\n\nKollokatsioone saab otsida kolmel viisil:\n\n1) teatud lemma olulisi kollokaate s\u00f5navormidena\n2) teatud lemma olulisi kollokaate lemmadena\n3) teatud s\u00f5navormi olulisi kollokaate s\u00f5navormidena\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17945049"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Kollokatsioonide tuvastaja"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ba69018e-6aa0-5e98-8730-644f93cf8a78.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ba69018e-6aa0-5e98-8730-644f93cf8a78.json
deleted file mode 100644
index 84a06261..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ba69018e-6aa0-5e98-8730-644f93cf8a78.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05BEBL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9474557",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9474557"
-    ],
-    "PublicationTimestamp": "2016-10-31T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:9474557;2019-04-03T01:30:57Z;ESTDOI;ESTDOI.KEEL;Eesti-udmurdi s\u00f5naraamat;Hein, Indrek;Center of Estonian Language Resources;2016;Issued: 2016-10-31;Updated: 2016-10-31;doi:10.15155/3-00-0000-0000-0000-05BEBL;Abstract;Esimene eesti-udmurdi s\u00f5naraamat. Sisaldab u 10 000 m\u00e4rks\u00f5na ja on keeleuuenduslik: udmurdikeelsete vastete puudumisel pakuvad autorid eestikeelsele s\u00f5nale omapoolse v\u00f5imaliku vaste. S\u00f5naraamatu erip\u00e4raks on ka udmurdi murdes\u00f5nade rohkus.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ba69018e-6aa0-5e98-8730-644f93cf8a78",
-    "notes": [
-        "Abstract",
-        "Esimene eesti-udmurdi s\u00f5naraamat. Sisaldab u 10 000 m\u00e4rks\u00f5na ja on keeleuuenduslik: udmurdikeelsete vastete puudumisel pakuvad autorid eestikeelsele s\u00f5nale omapoolse v\u00f5imaliku vaste. S\u00f5naraamatu erip\u00e4raks on ka udmurdi murdes\u00f5nade rohkus."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9474557"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti-udmurdi s\u00f5naraamat"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/bc50638b-8239-5cf4-9caa-3a149b6fac5d.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/bc50638b-8239-5cf4-9caa-3a149b6fac5d.json
deleted file mode 100644
index 9451c916..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/bc50638b-8239-5cf4-9caa-3a149b6fac5d.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/TY.0017",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:4597376",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:4597376"
-    ],
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:4597376;2015-01-09T14:16:15Z;ESTDOI;ESTDOI.KEEL;Corpus of Estonian fiction;Muischnek, Kadri;Center of Estonian Language Resources;2013;doi:10.15155/TY.0017",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bc50638b-8239-5cf4-9caa-3a149b6fac5d",
-    "oai_identifier": [
-        "oai:oai.datacite.org:4597376"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Corpus of Estonian fiction"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/bd183555-dc86-5754-91f1-04c08bb2eb41.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/bd183555-dc86-5754-91f1-04c08bb2eb41.json
deleted file mode 100644
index 4ebe8a4e..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/bd183555-dc86-5754-91f1-04c08bb2eb41.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06339L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10304012",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10304012"
-    ],
-    "PublicationTimestamp": "2017-01-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Langemets, Margit"
-    ],
-    "fulltext": "oai:oai.datacite.org:10304012;2019-01-20T17:32:23Z;ESTDOI;ESTDOI.KEEL; Eesti viipekeele - eesti keele veebis\u00f5nastik ;Langemets, Margit;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2017-01-31;doi:10.15155/3-00-0000-0000-0000-06339L;Abstract;S\u00f5nastik sisaldab \u00fcle 4000 m\u00e4rks\u00f5na ning v\u00f5imaldab otsingut eestikeelse s\u00f5na v\u00f5i eesti viipekeele viipe alusel. S\u00f5nastik on m\u00f5eldud nii eesti viipekeele \u00f5ppijatele kui ka eesti viipekeele kasutajatele eesti keele \u00f5ppimiseks.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bd183555-dc86-5754-91f1-04c08bb2eb41",
-    "notes": [
-        "Abstract",
-        "S\u00f5nastik sisaldab \u00fcle 4000 m\u00e4rks\u00f5na ning v\u00f5imaldab otsingut eestikeelse s\u00f5na v\u00f5i eesti viipekeele viipe alusel. S\u00f5nastik on m\u00f5eldud nii eesti viipekeele \u00f5ppijatele kui ka eesti viipekeele kasutajatele eesti keele \u00f5ppimiseks."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10304012"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        " Eesti viipekeele - eesti keele veebis\u00f5nastik "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/bde283ed-533a-5852-8fe6-a90648f85693.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/bde283ed-533a-5852-8fe6-a90648f85693.json
deleted file mode 100644
index f7f4b3b3..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/bde283ed-533a-5852-8fe6-a90648f85693.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05B4BL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9352869",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9352869"
-    ],
-    "PublicationTimestamp": "2018-05-14T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek",
-        "Langemets, Margit"
-    ],
-    "fulltext": "oai:oai.datacite.org:9352869;2019-03-31T17:00:38Z;ESTDOI;ESTDOI.KEEL;Igau\u0146u-latvie\u0161u v\u0101rdn\u012bca;Eesti-l\u00e4ti s\u00f5naraamat;The Estonian-Latvian Dictionary;Hein, Indrek;Langemets, Margit;Center of Estonian Language Resources;2016;Issued: 2016-10-31;Updated: 2018-05-14;doi:10.15155/3-00-0000-0000-0000-05B4BL;Abstract;Kahesuunaline eesti-l\u00e4ti s\u00f5naraamat, mis sisaldab ligi 47 000 m\u00e4rks\u00f5naartiklit. ;Abstract;A two-way Estonian\u2013Latvian dictionary of nearly 47,000 entries.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bde283ed-533a-5852-8fe6-a90648f85693",
-    "notes": [
-        "Abstract",
-        "Kahesuunaline eesti-l\u00e4ti s\u00f5naraamat, mis sisaldab ligi 47 000 m\u00e4rks\u00f5naartiklit. ",
-        "Abstract",
-        "A two-way Estonian\u2013Latvian dictionary of nearly 47,000 entries."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9352869"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Igau\u0146u-latvie\u0161u v\u0101rdn\u012bca",
-        "Eesti-l\u00e4ti s\u00f5naraamat",
-        "The Estonian-Latvian Dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/beaa8c89-7528-502a-b103-dffb8f3adc42.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/beaa8c89-7528-502a-b103-dffb8f3adc42.json
deleted file mode 100644
index cbaea469..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/beaa8c89-7528-502a-b103-dffb8f3adc42.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0012EL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10761537",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10761537"
-    ],
-    "PublicationTimestamp": "2018-03-15T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:10761537;2019-04-17T17:26:43Z;ESTDOI;ESTDOI.KEEL;Eesti veeb 2013 (etTenTen) korpus, morfoloogiliselt \u00fchestatud;Web13 corpus (etTenTen), morphologically annotated;Muischnek, Kadri;Center of Estonian Language Resources;2016;Issued: 2016-04-29;Updated: 2018-03-15;doi:10.15155/1-00-0000-0000-0000-0012EL;Abstract;etTenTen korpus (ehk Eesti veeb13) on internetist alla laetud eestikeelsete veebilehtede korpus.\nKorpuses on 270 miljonit s\u00f5na 686 000 veebilehelt.\nvt veel http://www2.keeleveeb.ee/dict/corpus/ettenten/about.html\n\nAlgmaterjal\n\nKorpuse tekstid korjas internetist ja teisendas utf-8 kodeeringus teksti kujule Vit Suchomel.\nVeebirobotiga laeti alla 1 173 702 veebilehte, kusjuures juba olemas olevate lehtede koopiad j\u00e4eti k\u00f5rvale; k\u00f5rvale j\u00e4eti ka lehed, mis on esindatud Eesti kirjakeele koondkorpuses. (http://www.cl.ut.ee/korpused/segakorpus/). Kasutati Jan Pomikaleki doktorit\u00f6\u00f6 k\u00e4igus loodud programme  jusText ja onion (code.google.com/p/justext, code.google.com/p/onion)\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "beaa8c89-7528-502a-b103-dffb8f3adc42",
-    "notes": [
-        "Abstract",
-        "etTenTen korpus (ehk Eesti veeb13) on internetist alla laetud eestikeelsete veebilehtede korpus.\nKorpuses on 270 miljonit s\u00f5na 686 000 veebilehelt.\nvt veel http://www2.keeleveeb.ee/dict/corpus/ettenten/about.html\n\nAlgmaterjal\n\nKorpuse tekstid korjas internetist ja teisendas utf-8 kodeeringus teksti kujule Vit Suchomel.\nVeebirobotiga laeti alla 1 173 702 veebilehte, kusjuures juba olemas olevate lehtede koopiad j\u00e4eti k\u00f5rvale; k\u00f5rvale j\u00e4eti ka lehed, mis on esindatud Eesti kirjakeele koondkorpuses. (http://www.cl.ut.ee/korpused/segakorpus/). Kasutati Jan Pomikaleki doktorit\u00f6\u00f6 k\u00e4igus loodud programme  jusText ja onion (code.google.com/p/justext, code.google.com/p/onion)\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10761537"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti veeb 2013 (etTenTen) korpus, morfoloogiliselt \u00fchestatud",
-        "Web13 corpus (etTenTen), morphologically annotated"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/bf3fe308-d6e2-5d0b-93e8-528ea56dbf08.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/bf3fe308-d6e2-5d0b-93e8-528ea56dbf08.json
deleted file mode 100644
index a87e45cd..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/bf3fe308-d6e2-5d0b-93e8-528ea56dbf08.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-0009EL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17960895",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17960895"
-    ],
-    "PublicationTimestamp": "2019-01-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Meister, Einar"
-    ],
-    "fulltext": "oai:oai.datacite.org:17960895;2019-01-31T19:02:33Z;ESTDOI;ESTDOI.KEEL;Jutusaadete korpus;Meister, Einar;Center of Estonian Language Resources;2019;Issued: 2019-01-07;Updated: 2019-01-07;doi:10.15155/9-00-0000-0000-0000-0009EL;Abstract;Jutusaated televiisorist ja raadiost.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bf3fe308-d6e2-5d0b-93e8-528ea56dbf08",
-    "notes": [
-        "Abstract",
-        "Jutusaated televiisorist ja raadiost."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17960895"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Jutusaadete korpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/bfb8e7ac-e0e1-5b48-8d0b-c1894c8cf8e6.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/bfb8e7ac-e0e1-5b48-8d0b-c1894c8cf8e6.json
deleted file mode 100644
index 44a8a78a..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/bfb8e7ac-e0e1-5b48-8d0b-c1894c8cf8e6.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-0001CL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5757258",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5757258"
-    ],
-    "PublicationTimestamp": "2017-05-10T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:5757258;2019-04-17T17:27:43Z;ESTDOI;ESTDOI.KEEL;Inglise-eesti masint\u00f5lkes\u00f5nastik;English-Estonian Machine Translation Dictionary;Hein, Indrek;Center of Estonian Language Resources;2012;Issued: 2012-06-14;Updated: 2017-05-10;doi:10.15155/3-00-0000-0000-0000-0001CL;Abstract;Jooksvalt t\u00e4ienev inglise-eesti veebis\u00f5nastik, mis on abiks t\u00f5lkimisel ja toetab ka masint\u00f5lget. S\u00f5nastikus on praegu ligi 90 000 ingliskeelset s\u00f5na ja p\u00fcsi\u00fchendit S\u00f5nastik on loodud hobi korras ning ei pruugi vastata Eesti Keele Instituudi kvaliteedistandardile.;Abstract;A constantly incremented English-Estonian online dictionary, which is helpful in both human and machine translation. Currently, there are nearly 90,000 English words and phrases. Being created as a hobby, the dictionary need not meet all the quality standards of the Institute of the Estonian Language.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bfb8e7ac-e0e1-5b48-8d0b-c1894c8cf8e6",
-    "notes": [
-        "Abstract",
-        "Jooksvalt t\u00e4ienev inglise-eesti veebis\u00f5nastik, mis on abiks t\u00f5lkimisel ja toetab ka masint\u00f5lget. S\u00f5nastikus on praegu ligi 90 000 ingliskeelset s\u00f5na ja p\u00fcsi\u00fchendit S\u00f5nastik on loodud hobi korras ning ei pruugi vastata Eesti Keele Instituudi kvaliteedistandardile.",
-        "Abstract",
-        "A constantly incremented English-Estonian online dictionary, which is helpful in both human and machine translation. Currently, there are nearly 90,000 English words and phrases. Being created as a hobby, the dictionary need not meet all the quality standards of the Institute of the Estonian Language."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5757258"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Inglise-eesti masint\u00f5lkes\u00f5nastik",
-        "English-Estonian Machine Translation Dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/bfe3ffb5-acfe-5b95-be13-8e722b57a323.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/bfe3ffb5-acfe-5b95-be13-8e722b57a323.json
deleted file mode 100644
index 778eabce..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/bfe3ffb5-acfe-5b95-be13-8e722b57a323.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05BE9L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9474555",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9474555"
-    ],
-    "PublicationTimestamp": "2016-11-09T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Nurk, T\u00f5nis"
-    ],
-    "fulltext": "oai:oai.datacite.org:9474555;2019-01-30T15:00:47Z;ESTDOI;ESTDOI.KEEL;e-keelen\u00f5u;Nurk, T\u00f5nis;Center of Estonian Language Resources;2016;Issued: 2016-11-09;Updated: 2016-11-09;doi:10.15155/3-00-0000-0000-0000-05BE9L;Abstract;\u00dchisp\u00e4ring keeleinfot sisaldavatest allikatest. Portaali peaeesm\u00e4rgiks on pakkuda l\u00f5pptarbijale intuitiivselt lihtsal viisil vastuseid keelealastele k\u00fcsimustele, nt normingukohasus, vasted teistes keeltes, selgitused, et\u00fcmoloogia, kasutusinfo jms.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "bfe3ffb5-acfe-5b95-be13-8e722b57a323",
-    "notes": [
-        "Abstract",
-        "\u00dchisp\u00e4ring keeleinfot sisaldavatest allikatest. Portaali peaeesm\u00e4rgiks on pakkuda l\u00f5pptarbijale intuitiivselt lihtsal viisil vastuseid keelealastele k\u00fcsimustele, nt normingukohasus, vasted teistes keeltes, selgitused, et\u00fcmoloogia, kasutusinfo jms."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9474555"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "e-keelen\u00f5u"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c01d6a12-bf8f-5c56-8c46-3d744c3c8bd4.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c01d6a12-bf8f-5c56-8c46-3d744c3c8bd4.json
deleted file mode 100644
index 32f49a16..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c01d6a12-bf8f-5c56-8c46-3d744c3c8bd4.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00137L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:12000825",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:12000825"
-    ],
-    "PublicationTimestamp": "2017-09-11T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Vare, Kadri",
-        "Orav, Heili"
-    ],
-    "fulltext": "oai:oai.datacite.org:12000825;2019-04-16T07:01:20Z;ESTDOI;ESTDOI.KEEL;Eesti Wordnet (2.0 beeta);Estonian Wordnet (2.0 beta);Orav, Heili;Vare, Kadri;Center of Estonian Language Resources;2014;Issued: 2014-03-21;Updated: 2017-09-11;doi:10.15155/1-00-0000-0000-0000-00137L;Abstract;Esimene XML versioon Eesti Wordnetist.;Abstract;The first version of EstWN in XML format.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c01d6a12-bf8f-5c56-8c46-3d744c3c8bd4",
-    "notes": [
-        "Abstract",
-        "Esimene XML versioon Eesti Wordnetist.",
-        "Abstract",
-        "The first version of EstWN in XML format."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:12000825"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti Wordnet (2.0 beeta)",
-        "Estonian Wordnet (2.0 beta)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c13203b9-166a-523b-9600-aaccd45ec95e.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c13203b9-166a-523b-9600-aaccd45ec95e.json
deleted file mode 100644
index c68a5175..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c13203b9-166a-523b-9600-aaccd45ec95e.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-000E9L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:6813486",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:6813486"
-    ],
-    "PublicationTimestamp": "2017-06-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Vare, Kadri",
-        "Orav, Heili"
-    ],
-    "fulltext": "oai:oai.datacite.org:6813486;2019-04-19T02:30:57Z;ESTDOI;ESTDOI.KEEL;Estonian Wordnet (kb72-LAST);Orav, Heili;Vare, Kadri;Center of Estonian Language Resources;2014;Issued: 2014-03-21;Updated: 2017-06-01;doi:10.15155/1-00-0000-0000-0000-000E9L;Abstract; Eesti Wordnetis (versioon 72) on praeguse seisuga (oktoober 2015) 74 720 m\u00f5istet, milles s\u00f5nu 101 761, semantilisi suhteid 239 719 ja seoseid Princetoni Wordnetiga (1.5) 108 202.  K\u00f5ik m\u00f5isted on varustatud v\u00e4hemalt \u00fche keelesisese suhtega ja v\u00e4hemalt \u00fche ILI-suhtega.;Abstract;The atom of a wordnet-type thesaurus is a synonym set (also called a synset), which is a set containing all the synonymous words or multi-word units that express the same concept. All words in a synset belong into the same part of speech.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c13203b9-166a-523b-9600-aaccd45ec95e",
-    "notes": [
-        "Abstract",
-        " Eesti Wordnetis (versioon 72) on praeguse seisuga (oktoober 2015) 74 720 m\u00f5istet, milles s\u00f5nu 101 761, semantilisi suhteid 239 719 ja seoseid Princetoni Wordnetiga (1.5) 108 202.  K\u00f5ik m\u00f5isted on varustatud v\u00e4hemalt \u00fche keelesisese suhtega ja v\u00e4hemalt \u00fche ILI-suhtega.",
-        "Abstract",
-        "The atom of a wordnet-type thesaurus is a synonym set (also called a synset), which is a set containing all the synonymous words or multi-word units that express the same concept. All words in a synset belong into the same part of speech."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:6813486"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Estonian Wordnet (kb72-LAST)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c255306a-ba1f-5959-abc5-e462dd5e0400.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c255306a-ba1f-5959-abc5-e462dd5e0400.json
deleted file mode 100644
index c414eebd..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c255306a-ba1f-5959-abc5-e462dd5e0400.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00075L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5757024",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5757024"
-    ],
-    "PublicationTimestamp": "2018-02-12T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Prillop, K\u00fclli"
-    ],
-    "fulltext": "oai:oai.datacite.org:5757024;2019-04-18T17:36:29Z;ESTDOI;ESTDOI.KEEL;Vana kirjakeele korpus;Corpus of Old Written Estonian;Prillop, K\u00fclli;Center of Estonian Language Resources;2013;Issued: 2013-01-09;Updated: 2018-02-12;doi:10.15155/1-00-0000-0000-0000-00075L;Abstract;The Corpus is geared towards researchers of the history and development of written Estonian. The texts included are from 16.-18. century. From 16th century all known printed and hand-written texts have been included, except for lists of place and person names. For 17. and 18. century a choice of more important authors and text types has been included. Both northern and southern Estonian dialects, secular as well as religious texts are represented. Excluded from the corpus are fragments, rhymes, primers, calendars and hand-written texts. For the first half of 19. century texts from a choice of authors is included. \nThe texts are in the original written form. 16.-18. century texts have been tagged with contemporary Estonian, morphological and language information. 19. century texts are unannotated.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c255306a-ba1f-5959-abc5-e462dd5e0400",
-    "notes": [
-        "Abstract",
-        "The Corpus is geared towards researchers of the history and development of written Estonian. The texts included are from 16.-18. century. From 16th century all known printed and hand-written texts have been included, except for lists of place and person names. For 17. and 18. century a choice of more important authors and text types has been included. Both northern and southern Estonian dialects, secular as well as religious texts are represented. Excluded from the corpus are fragments, rhymes, primers, calendars and hand-written texts. For the first half of 19. century texts from a choice of authors is included. \nThe texts are in the original written form. 16.-18. century texts have been tagged with contemporary Estonian, morphological and language information. 19. century texts are unannotated."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5757024"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Vana kirjakeele korpus",
-        "Corpus of Old Written Estonian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c330d2bc-5616-5085-b307-bbc7f15596dc.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c330d2bc-5616-5085-b307-bbc7f15596dc.json
deleted file mode 100644
index 0a962e35..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c330d2bc-5616-5085-b307-bbc7f15596dc.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-0008DL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:13082155",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:13082155"
-    ],
-    "PublicationTimestamp": "2018-07-16T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "K\u00f5iva, Mare",
-        "Laineste, Liisi"
-    ],
-    "fulltext": "oai:oai.datacite.org:13082155;2019-02-24T18:37:45Z;ESTDOI;ESTDOI.KEEL;Eesti kaasaegsed anekdoodid;Estonian contemporary jokes.;K\u00f5iva, Mare;Laineste, Liisi;Center of Estonian Language Resources;2017;Issued: 2017-11-25;Updated: 2018-07-16;doi:10.15155/9-00-0000-0000-0000-0008DL;Abstract;Anekdoodikogu on koostatud Eesti kaasaegse huumori uurimise eesm\u00e4rgil Liisi Laineste poolt 2004. aastal. See sisaldab u. 37 000 eesti netinalja perioodist 1996 - 2004.  Kogu koostamise eesm\u00e4rgiks oli kaasaegsete anekdootide arhiveerimine suurematelt internetilehek\u00fclgedelt, p\u00e4evalehtedest ja tr\u00fckis ilmunud anekdoodikogudest.\nNii anekdoodiotsing kui ka andmebaas on alles konstrueerimisj\u00e4rgus, sellest tulenevalt tuleks arvestada, et:\n- Detailselt on kategoriseeritud esialgu vaid etniliste anekdootide kategooria. Teised naljad on kas kategoriseerimata (nt Jokebooki e Meie Naljaraamatu materjal, erakogud) v\u00f5i on liigitatud portaalitegijate poolt (Delfi Naljaleht). \n- Samamoodi on ka sarnased anekdoodid leitud vaid etniliste naljade puhul. Link \"Sarnased naljad\" viib sarnaste anekdootideni vaid siis, kui kategooriaks on m\u00e4rgitud \"Erinevad rahvused\". Muudel juhtudel saab tulemuseks lihtsalt sama anekdoodi.\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c330d2bc-5616-5085-b307-bbc7f15596dc",
-    "notes": [
-        "Abstract",
-        "Anekdoodikogu on koostatud Eesti kaasaegse huumori uurimise eesm\u00e4rgil Liisi Laineste poolt 2004. aastal. See sisaldab u. 37 000 eesti netinalja perioodist 1996 - 2004.  Kogu koostamise eesm\u00e4rgiks oli kaasaegsete anekdootide arhiveerimine suurematelt internetilehek\u00fclgedelt, p\u00e4evalehtedest ja tr\u00fckis ilmunud anekdoodikogudest.\nNii anekdoodiotsing kui ka andmebaas on alles konstrueerimisj\u00e4rgus, sellest tulenevalt tuleks arvestada, et:\n- Detailselt on kategoriseeritud esialgu vaid etniliste anekdootide kategooria. Teised naljad on kas kategoriseerimata (nt Jokebooki e Meie Naljaraamatu materjal, erakogud) v\u00f5i on liigitatud portaalitegijate poolt (Delfi Naljaleht). \n- Samamoodi on ka sarnased anekdoodid leitud vaid etniliste naljade puhul. Link \"Sarnased naljad\" viib sarnaste anekdootideni vaid siis, kui kategooriaks on m\u00e4rgitud \"Erinevad rahvused\". Muudel juhtudel saab tulemuseks lihtsalt sama anekdoodi.\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:13082155"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti kaasaegsed anekdoodid",
-        "Estonian contemporary jokes."
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c42f3342-09d7-58af-9d13-e6ff1f855b8d.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c42f3342-09d7-58af-9d13-e6ff1f855b8d.json
deleted file mode 100644
index cbd9e499..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c42f3342-09d7-58af-9d13-e6ff1f855b8d.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-00088L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:11264659",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:11264659"
-    ],
-    "PublicationTimestamp": "2018-02-07T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laak, Marin",
-        "Asmer, Vilve"
-    ],
-    "fulltext": "oai:oai.datacite.org:11264659;2019-04-17T17:26:55Z;ESTDOI;ESTDOI.KEEL;Vanema eestikeelse algup\u00e4rase ilukirjanduse kogu;Collection of older original Estonian-language works of fiction;Laak, Marin;Asmer, Vilve;Center of Estonian Language Resources;2017;Issued: 2017-06-01;Updated: 2018-02-07;doi:10.15155/9-00-0000-0000-0000-00088L;Abstract;Eesti vanema ilukirjanduse tekstide kogu veebikeskkonnas \"Kreutzwaldi sajand. Eesti kultuurilooline veeb.\" Kollektsioonis elektrooniliselt taasavaldatud raamatud p\u00f5hinevad olulisemate Eesti autorite aastatel 1854-1944 ilmunud esmatr\u00fckkidel. Tekstid on esitatud keeleparandusteta, kuid tehniliselt redigeeritud. \"Kreutzwaldi sajand. Eesti kultuurilooline veeb\" esitab raamatud kolmes versioonis: 1) skaneeritud pildina originaalesmatr\u00fckist, 2) html-versioonina, mille lehek\u00fcljed\nvastavad tr\u00fckitud raamatu lehek\u00fclgedele, 3) allalaetava e-pubina.\nKui kontakteerute ressursi haldajatega, siis v\u00f5ite teadusotstarveteks kasutamiseks saada tekstikorpuse. See sisaldab valikut veebikeskkonnas saadaval olevatest raamatutest, mis on teisendatud tekstifailideks. Tekstifailidele on igaks juhuks lisatud ka originaalfailid. HTML-failidest teisendatud tekstifailid sisaldavad HTML-vormingust tingitud reavahetusi, mida algsetes tekstides ei olnud.;Abstract;Web collection of older Estonian literary texts \"Kreutzwald's Century: the Estonian Cultural History Web\". The electronically republished books, included in the collection, are based on the first editions of works by more important Estonian authors, published in 1854-1944. The language of the texts has not been edited, but technical corrections have been made. \"Kreutzwald's Century: the Estonian Cultural History Web\" presents books in three versions: 1) scanned images of the original first edition; 2) a html-version; 3) a downloadable e-pub. \nThe text corpus contains a selection of books accessible on the web, which have been converted into text files. Original files have also been added to the text files. The text files which were converted from the html-files contain, due to the html-formatting, additional line breaks which were not present in the original texts. The html/text versions correspond to the original printed book page layout and the page numbers are also included. Please contact us to gain access to the text corpus.\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c42f3342-09d7-58af-9d13-e6ff1f855b8d",
-    "notes": [
-        "Abstract",
-        "Eesti vanema ilukirjanduse tekstide kogu veebikeskkonnas \"Kreutzwaldi sajand. Eesti kultuurilooline veeb.\" Kollektsioonis elektrooniliselt taasavaldatud raamatud p\u00f5hinevad olulisemate Eesti autorite aastatel 1854-1944 ilmunud esmatr\u00fckkidel. Tekstid on esitatud keeleparandusteta, kuid tehniliselt redigeeritud. \"Kreutzwaldi sajand. Eesti kultuurilooline veeb\" esitab raamatud kolmes versioonis: 1) skaneeritud pildina originaalesmatr\u00fckist, 2) html-versioonina, mille lehek\u00fcljed\nvastavad tr\u00fckitud raamatu lehek\u00fclgedele, 3) allalaetava e-pubina.\nKui kontakteerute ressursi haldajatega, siis v\u00f5ite teadusotstarveteks kasutamiseks saada tekstikorpuse. See sisaldab valikut veebikeskkonnas saadaval olevatest raamatutest, mis on teisendatud tekstifailideks. Tekstifailidele on igaks juhuks lisatud ka originaalfailid. HTML-failidest teisendatud tekstifailid sisaldavad HTML-vormingust tingitud reavahetusi, mida algsetes tekstides ei olnud.",
-        "Abstract",
-        "Web collection of older Estonian literary texts \"Kreutzwald's Century: the Estonian Cultural History Web\". The electronically republished books, included in the collection, are based on the first editions of works by more important Estonian authors, published in 1854-1944. The language of the texts has not been edited, but technical corrections have been made. \"Kreutzwald's Century: the Estonian Cultural History Web\" presents books in three versions: 1) scanned images of the original first edition; 2) a html-version; 3) a downloadable e-pub. \nThe text corpus contains a selection of books accessible on the web, which have been converted into text files. Original files have also been added to the text files. The text files which were converted from the html-files contain, due to the html-formatting, additional line breaks which were not present in the original texts. The html/text versions correspond to the original printed book page layout and the page numbers are also included. Please contact us to gain access to the text corpus.\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:11264659"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Vanema eestikeelse algup\u00e4rase ilukirjanduse kogu",
-        "Collection of older original Estonian-language works of fiction"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c45bb0ac-988d-5afa-9f17-5da1679e9bb0.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c45bb0ac-988d-5afa-9f17-5da1679e9bb0.json
deleted file mode 100644
index 6fe7ed0c..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c45bb0ac-988d-5afa-9f17-5da1679e9bb0.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-07001L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14277512",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14277512"
-    ],
-    "PublicationTimestamp": "2018-02-22T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Kallasmaa, Marja",
-        "P\u00e4ll, Peeter"
-    ],
-    "fulltext": "oai:oai.datacite.org:14277512;2018-02-22T09:31:15Z;ESTDOI;ESTDOI.KEEL;Eesti kohanimeraamat;P\u00e4ll, Peeter;Kallasmaa, Marja;Center of Estonian Language Resources;2018;Issued: 2018-02-22;Updated: 2018-02-22;doi:10.15155/3-00-0000-0000-0000-07001L;Abstract;Dictionary of Estonian Place Names\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c45bb0ac-988d-5afa-9f17-5da1679e9bb0",
-    "notes": [
-        "Abstract",
-        "Dictionary of Estonian Place Names\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14277512"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti kohanimeraamat"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c6400076-4d33-5823-a1ea-52c5df1b3f62.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c6400076-4d33-5823-a1ea-52c5df1b3f62.json
deleted file mode 100644
index 5afb47b7..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c6400076-4d33-5823-a1ea-52c5df1b3f62.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00144L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:13446394",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:13446394"
-    ],
-    "PublicationTimestamp": "2018-04-04T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laur, Sven"
-    ],
-    "fulltext": "oai:oai.datacite.org:13446394;2019-02-22T14:02:08Z;ESTDOI;ESTDOI.KEEL;EstNLTK tokenizer;Laur, Sven;Center of Estonian Language Resources;2017;Issued: 2017-12-11;Updated: 2018-04-04;doi:10.15155/1-00-0000-0000-0000-00144L;Abstract;Word tokenizer from the Estonian NLTK toolkit",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c6400076-4d33-5823-a1ea-52c5df1b3f62",
-    "notes": [
-        "Abstract",
-        "Word tokenizer from the Estonian NLTK toolkit"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:13446394"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "EstNLTK tokenizer"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c658a877-0fc4-5077-92d7-c319aafbd62b.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c658a877-0fc4-5077-92d7-c319aafbd62b.json
deleted file mode 100644
index c96a7638..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c658a877-0fc4-5077-92d7-c319aafbd62b.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00150L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14107609",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14107609"
-    ],
-    "PublicationTimestamp": "2018-01-30T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Lippus, P\u00e4rtel"
-    ],
-    "fulltext": "oai:oai.datacite.org:14107609;2019-03-16T01:31:40Z;ESTDOI;ESTDOI.KEEL;Inari saami prosoodia korpus;Inari Sami prosody corpus;Lippus, P\u00e4rtel;Center of Estonian Language Resources;2018;Issued: 2018-01-30;Updated: 2018-01-30;doi:10.15155/1-00-0000-0000-0000-00150L;Abstract;Materjal koosneb kahesilbilistest erineva silbistruktuuriga tests\u00f5nadest, mis on paigutatud lauses fraasi keskele v\u00f5i fraasi l\u00f5ppu ja lause l\u00f5ppu. Iga lause sisaldab 2 tests\u00f5na. 72 lauset on fraasikeskse paigutusega, 120 lauset fraasil\u00f5pulise paigutusega. Salvestusi luges 4 meesk\u00f5nelejat.;Abstract;Recordings of Inari Saami disyllabic words embedded in carrier sentences read by 4 male speakers. The speakers read a list of 72 sentences where the test words occur in phrase-medial position and a list of 120 sentences where the test words occur once in phrase-final and once in sentence-final position. The test words are segmented on Praat TextGrids.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c658a877-0fc4-5077-92d7-c319aafbd62b",
-    "notes": [
-        "Abstract",
-        "Materjal koosneb kahesilbilistest erineva silbistruktuuriga tests\u00f5nadest, mis on paigutatud lauses fraasi keskele v\u00f5i fraasi l\u00f5ppu ja lause l\u00f5ppu. Iga lause sisaldab 2 tests\u00f5na. 72 lauset on fraasikeskse paigutusega, 120 lauset fraasil\u00f5pulise paigutusega. Salvestusi luges 4 meesk\u00f5nelejat.",
-        "Abstract",
-        "Recordings of Inari Saami disyllabic words embedded in carrier sentences read by 4 male speakers. The speakers read a list of 72 sentences where the test words occur in phrase-medial position and a list of 120 sentences where the test words occur once in phrase-final and once in sentence-final position. The test words are segmented on Praat TextGrids."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14107609"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Inari saami prosoodia korpus",
-        "Inari Sami prosody corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c6cdc05d-7419-518a-bded-f503255e0c51.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c6cdc05d-7419-518a-bded-f503255e0c51.json
deleted file mode 100644
index b3057874..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c6cdc05d-7419-518a-bded-f503255e0c51.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-000A1L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17968026",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17968026"
-    ],
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Valdre, Eola"
-    ],
-    "fulltext": "oai:oai.datacite.org:17968026;2019-04-12T17:25:52Z;ESTDOI;ESTDOI.KEEL;Meditsiini \u00f5ppematerjalide korpus;Valdre, Eola;Center of Estonian Language Resources;2019;Issued: 2019-01-08;Updated: 2019-01-08;doi:10.15155/9-00-0000-0000-0000-000A1L;Abstract;Korpuses on 65 719 s\u00f5net 2455 loenguslaidilt; kasutatud on T\u00dc arstiteaduskonna III kursuse radioloogialoenguid ja VI kursuse kliinilise radioloogia loenguid (\u00f5ppeained ARHO.01.033 ja ARHO.002.009), luba selleks on saadud radioloogiakliiniku juhatajalt dr P. Ilveselt.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c6cdc05d-7419-518a-bded-f503255e0c51",
-    "notes": [
-        "Abstract",
-        "Korpuses on 65 719 s\u00f5net 2455 loenguslaidilt; kasutatud on T\u00dc arstiteaduskonna III kursuse radioloogialoenguid ja VI kursuse kliinilise radioloogia loenguid (\u00f5ppeained ARHO.01.033 ja ARHO.002.009), luba selleks on saadud radioloogiakliiniku juhatajalt dr P. Ilveselt."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17968026"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Meditsiini \u00f5ppematerjalide korpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c6cdf422-3d5a-5511-b105-adb09e5f8745.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c6cdf422-3d5a-5511-b105-adb09e5f8745.json
deleted file mode 100644
index fb69050a..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c6cdf422-3d5a-5511-b105-adb09e5f8745.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05923L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:8922454",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:8922454"
-    ],
-    "PublicationTimestamp": "2017-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:8922454;2019-04-17T17:25:58Z;ESTDOI;ESTDOI.KEEL;V\u00e4ike murdes\u00f5nastik;The Dialectological Dictionary of Estonian;Hein, Indrek;Center of Estonian Language Resources;2016;Issued: 2016-08-24;Updated: 2017-02-15;doi:10.15155/3-00-0000-0000-0000-05923L;Abstract;Annab \u00fclevaate eesti murdes\u00f5navarast ja s\u00f5nade levikust.;Abstract;Provides a survey of Estonian dialect vords and their areal distribution.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c6cdf422-3d5a-5511-b105-adb09e5f8745",
-    "notes": [
-        "Abstract",
-        "Annab \u00fclevaate eesti murdes\u00f5navarast ja s\u00f5nade levikust.",
-        "Abstract",
-        "Provides a survey of Estonian dialect vords and their areal distribution."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:8922454"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "V\u00e4ike murdes\u00f5nastik",
-        "The Dialectological Dictionary of Estonian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c7e1f2e2-0b15-5f80-a6c7-61374df650b0.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c7e1f2e2-0b15-5f80-a6c7-61374df650b0.json
deleted file mode 100644
index 2319464c..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c7e1f2e2-0b15-5f80-a6c7-61374df650b0.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00142L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:13445137",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:13445137"
-    ],
-    "PublicationTimestamp": "2018-04-04T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laur, Sven"
-    ],
-    "fulltext": "oai:oai.datacite.org:13445137;2019-04-21T04:02:23Z;ESTDOI;ESTDOI.KEEL;EstNLTK morphological analysis;Laur, Sven;Center of Estonian Language Resources;2017;Issued: 2017-12-11;Updated: 2018-04-04;doi:10.15155/1-00-0000-0000-0000-00142L;Abstract;Estonian NLTK toolkit - morphological analysis for Estonian. Uses Vabamorf tagset. Takes unannotated text as input.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c7e1f2e2-0b15-5f80-a6c7-61374df650b0",
-    "notes": [
-        "Abstract",
-        "Estonian NLTK toolkit - morphological analysis for Estonian. Uses Vabamorf tagset. Takes unannotated text as input."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:13445137"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "EstNLTK morphological analysis"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c84de1a4-4cdd-542b-8dc2-c10a0e93d7af.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c84de1a4-4cdd-542b-8dc2-c10a0e93d7af.json
deleted file mode 100644
index a5eee85e..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c84de1a4-4cdd-542b-8dc2-c10a0e93d7af.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00163L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17725899",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17725899"
-    ],
-    "PublicationTimestamp": "2018-12-06T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:17725899;2019-04-16T05:03:05Z;ESTDOI;ESTDOI.KEEL;Segakorpus: Riigikogu ver.2.0;Corpus of the Proceedings of Estonian Parliament ver.2.0;Muischnek, Kadri;Center of Estonian Language Resources;2013;Issued: 2013-01-07;Updated: 2018-12-06;doi:10.15155/1-00-0000-0000-0000-00163L;Abstract;Riigikogu korpus. TEI P5 XML m\u00e4rgendus, UTF8 kodeering. Morfoloogiline anal\u00fc\u00fcs ja \u00fchestamine, automaatselt tehtud.;Abstract;Corpus of the Proceedings of Estonian Parliament. Contains edited version of the Proceedings of Estonian Parliament from the years 1995-2001; Morphologically analysed and disambiguated, automatically.\nMarkup: TEI P5 XML\nEncoding: UTF8",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c84de1a4-4cdd-542b-8dc2-c10a0e93d7af",
-    "notes": [
-        "Abstract",
-        "Riigikogu korpus. TEI P5 XML m\u00e4rgendus, UTF8 kodeering. Morfoloogiline anal\u00fc\u00fcs ja \u00fchestamine, automaatselt tehtud.",
-        "Abstract",
-        "Corpus of the Proceedings of Estonian Parliament. Contains edited version of the Proceedings of Estonian Parliament from the years 1995-2001; Morphologically analysed and disambiguated, automatically.\nMarkup: TEI P5 XML\nEncoding: UTF8"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17725899"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Segakorpus: Riigikogu ver.2.0",
-        "Corpus of the Proceedings of Estonian Parliament ver.2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c8ad501d-703f-527b-95ab-ad7d702f97ed.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c8ad501d-703f-527b-95ab-ad7d702f97ed.json
deleted file mode 100644
index 5f9c2e30..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c8ad501d-703f-527b-95ab-ad7d702f97ed.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00171L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17944456",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17944456"
-    ],
-    "PublicationTimestamp": "2019-01-03T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:17944456;2019-01-03T10:39:44Z;ESTDOI;ESTDOI.KEEL;CG s\u00fcntaksianal\u00fcsaatori anal\u00fc\u00fcsitud Tasakaalus korpus;Muischnek, Kadri;Center of Estonian Language Resources;2019;Issued: 2019-01-03;Updated: 2019-01-03;doi:10.15155/1-00-0000-0000-0000-00171L;Abstract;ajakirjandus, ilukirjandus, teaduskirjandus",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c8ad501d-703f-527b-95ab-ad7d702f97ed",
-    "notes": [
-        "Abstract",
-        "ajakirjandus, ilukirjandus, teaduskirjandus"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17944456"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "CG s\u00fcntaksianal\u00fcsaatori anal\u00fc\u00fcsitud Tasakaalus korpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c9705baf-29c6-5ee9-93b2-e4c00c55b478.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c9705baf-29c6-5ee9-93b2-e4c00c55b478.json
deleted file mode 100644
index 4eec766f..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c9705baf-29c6-5ee9-93b2-e4c00c55b478.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-07022L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14431629",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14431629"
-    ],
-    "PublicationTimestamp": "2018-03-23T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Soon, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:14431629;2019-04-20T17:37:10Z;ESTDOI;ESTDOI.KEEL;Esterm v20180302;Esterm v20180302;Soon, Tiina;Center of Estonian Language Resources;2018;Issued: 2018-03-14;Updated: 2018-03-23;doi:10.15155/3-00-0000-0000-0000-07022L;Abstract;Esterm on Eesti Keele Instituudi mitmekeelne terminibaas, mis sisaldab peamiselt Euroopa Liidu ja Eesti Vabariigi \u00f5igusaktide termineid. Terminibaas koondab \u00fcle 50 valdkonna terminoloogiat.;Abstract;Esterm is a multilingual termbase which includes terms mainly from the legal acts of the Republic of Estonia and the European Union. The termbase contains terminology from more than 50 domains.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c9705baf-29c6-5ee9-93b2-e4c00c55b478",
-    "notes": [
-        "Abstract",
-        "Esterm on Eesti Keele Instituudi mitmekeelne terminibaas, mis sisaldab peamiselt Euroopa Liidu ja Eesti Vabariigi \u00f5igusaktide termineid. Terminibaas koondab \u00fcle 50 valdkonna terminoloogiat.",
-        "Abstract",
-        "Esterm is a multilingual termbase which includes terms mainly from the legal acts of the Republic of Estonia and the European Union. The termbase contains terminology from more than 50 domains."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14431629"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Esterm v20180302",
-        "Esterm v20180302"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c9a32b0a-2e16-50b6-82ac-a85b1b66177d.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c9a32b0a-2e16-50b6-82ac-a85b1b66177d.json
deleted file mode 100644
index 4f9176c2..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c9a32b0a-2e16-50b6-82ac-a85b1b66177d.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00148L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:13902971",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:13902971"
-    ],
-    "PublicationTimestamp": "2018-01-24T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Lippus, P\u00e4rtel"
-    ],
-    "fulltext": "oai:oai.datacite.org:13902971;2019-02-24T18:37:47Z;ESTDOI;ESTDOI.KEEL;Niidumari prosoodia korpus;Meadow Mari prosody corpus;Lippus, P\u00e4rtel;Center of Estonian Language Resources;2018;Issued: 2018-01-24;Updated: 2018-01-24;doi:10.15155/1-00-0000-0000-0000-00148L;Abstract;Mari s\u00f5naprosoodia uurimiseks kogutud andmestik. Sisaldab raamlauses loetud tests\u00f5nu 8 keelejuhilt. Iga keelejuht luges 100 lauset, iga lause sisaldas tests\u00f5na kord lause keskel, kord lause l\u00f5pus.\nMaterjali kasutati siin: Lehiste, I., Teras, P., Help, T., Lippus, P., Meister, E., Pajusalu, K., & Viitso, T.-R. (2005). Meadow Mari prosody. Tallinn: Teaduste Akadeemia Kirjastus. Retrieved from http://kirj.ee/public/va_lu/Meadow%20Mari%20Prosody.pdf;Abstract;The recordings collected for studying Mari word prosody. 8 test subjects read 100 sentences. Each carrrier sentence contained a test word in phrase medial position and phrase final position.\nLehiste, I., Teras, P., Help, T., Lippus, P., Meister, E., Pajusalu, K., & Viitso, T.-R. (2005). Meadow Mari prosody. Tallinn: Teaduste Akadeemia Kirjastus. Retrieved from http://kirj.ee/public/va_lu/Meadow%20Mari%20Prosody.pdf",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c9a32b0a-2e16-50b6-82ac-a85b1b66177d",
-    "notes": [
-        "Abstract",
-        "Mari s\u00f5naprosoodia uurimiseks kogutud andmestik. Sisaldab raamlauses loetud tests\u00f5nu 8 keelejuhilt. Iga keelejuht luges 100 lauset, iga lause sisaldas tests\u00f5na kord lause keskel, kord lause l\u00f5pus.\nMaterjali kasutati siin: Lehiste, I., Teras, P., Help, T., Lippus, P., Meister, E., Pajusalu, K., & Viitso, T.-R. (2005). Meadow Mari prosody. Tallinn: Teaduste Akadeemia Kirjastus. Retrieved from http://kirj.ee/public/va_lu/Meadow%20Mari%20Prosody.pdf",
-        "Abstract",
-        "The recordings collected for studying Mari word prosody. 8 test subjects read 100 sentences. Each carrrier sentence contained a test word in phrase medial position and phrase final position.\nLehiste, I., Teras, P., Help, T., Lippus, P., Meister, E., Pajusalu, K., & Viitso, T.-R. (2005). Meadow Mari prosody. Tallinn: Teaduste Akadeemia Kirjastus. Retrieved from http://kirj.ee/public/va_lu/Meadow%20Mari%20Prosody.pdf"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:13902971"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Niidumari prosoodia korpus",
-        "Meadow Mari prosody corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c9cb9cc7-d81e-5297-91ed-77bb3351e242.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c9cb9cc7-d81e-5297-91ed-77bb3351e242.json
deleted file mode 100644
index 8dc20a7e..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/c9cb9cc7-d81e-5297-91ed-77bb3351e242.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-000E8L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:6813485",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:6813485"
-    ],
-    "PublicationTimestamp": "2015-10-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Vare, Kadri",
-        "Orav, Heili"
-    ],
-    "fulltext": "oai:oai.datacite.org:6813485;2019-02-22T07:01:16Z;ESTDOI;ESTDOI.KEEL;Estonian Wordnet (kb72-LAST);Orav, Heili;Vare, Kadri;Center of Estonian Language Resources;2014;Issued: 2014-03-21;Updated: 2015-10-01;doi:10.15155/1-00-0000-0000-0000-000E8L;Abstract; Eesti Wordnetis (versioon 72) on praeguse seisuga (oktoober 2015) 74 720 m\u00f5istet, milles s\u00f5nu 101 761, semantilisi suhteid 239 719 ja seoseid Princetoni Wordnetiga (1.5) 108 202.  K\u00f5ik m\u00f5isted on varustatud v\u00e4hemalt \u00fche keelesisese suhtega ja v\u00e4hemalt \u00fche ILI-suhtega.;Abstract;The atom of a wordnet-type thesaurus is a synonym set (also called a synset), which is a set containing all the synonymous words or multi-word units that express the same concept. All words in a synset belong into the same part of speech.\n\nTHIS IS THE NEWEST VERSION",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "c9cb9cc7-d81e-5297-91ed-77bb3351e242",
-    "notes": [
-        "Abstract",
-        " Eesti Wordnetis (versioon 72) on praeguse seisuga (oktoober 2015) 74 720 m\u00f5istet, milles s\u00f5nu 101 761, semantilisi suhteid 239 719 ja seoseid Princetoni Wordnetiga (1.5) 108 202.  K\u00f5ik m\u00f5isted on varustatud v\u00e4hemalt \u00fche keelesisese suhtega ja v\u00e4hemalt \u00fche ILI-suhtega.",
-        "Abstract",
-        "The atom of a wordnet-type thesaurus is a synonym set (also called a synset), which is a set containing all the synonymous words or multi-word units that express the same concept. All words in a synset belong into the same part of speech.\n\nTHIS IS THE NEWEST VERSION"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:6813485"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Estonian Wordnet (kb72-LAST)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/cad9d39b-54b0-5c7a-ac21-874d6001521b.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/cad9d39b-54b0-5c7a-ac21-874d6001521b.json
deleted file mode 100644
index b68cd55f..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/cad9d39b-54b0-5c7a-ac21-874d6001521b.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06345L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10304199",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10304199"
-    ],
-    "PublicationTimestamp": "2017-01-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Viks, \u00dclle"
-    ],
-    "fulltext": "oai:oai.datacite.org:10304199;2019-03-25T04:32:12Z;ESTDOI;ESTDOI.KEEL;Veebip\u00f5hine s\u00f5nastikus\u00fcsteem EELex ;Viks, \u00dclle;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2017-01-31;doi:10.15155/3-00-0000-0000-0000-06345L;Abstract;Leksikograafi t\u00f6\u00f6keskkond EELex on veebip\u00f5histe t\u00f6\u00f6vahendite kompleks, mis \u00fchendab s\u00f5nastike koostajatele ja toimetajatele vajaliku tarkvara ja keeleressursid, toetab r\u00fchmat\u00f6\u00f6d ja pakub eesti keele tuge. EELexi tarkvara on s\u00f5nastike halduss\u00fcsteem, mis v\u00f5imaldab s\u00f5nastikke koostada, toimetada ja k\u00fcljendada, teha lihtsaid ja keerulisi struktuurip\u00f5hiseid p\u00e4ringuid ning p\u00e4ringutulemusi sortida. Toimetaja t\u00f6\u00f6 h\u00f5lbustamiseks on loodud mitmeid t\u00f6\u00f6riistu, nt ristviidete kontroll, hulgiparandused kogu s\u00f5nastikus, eesti morfoloogia andmete genereerimine, k\u00fcljendusvaate kujundus, s\u00f5nastikuteksti eksport Wordi jms.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cad9d39b-54b0-5c7a-ac21-874d6001521b",
-    "notes": [
-        "Abstract",
-        "Leksikograafi t\u00f6\u00f6keskkond EELex on veebip\u00f5histe t\u00f6\u00f6vahendite kompleks, mis \u00fchendab s\u00f5nastike koostajatele ja toimetajatele vajaliku tarkvara ja keeleressursid, toetab r\u00fchmat\u00f6\u00f6d ja pakub eesti keele tuge. EELexi tarkvara on s\u00f5nastike halduss\u00fcsteem, mis v\u00f5imaldab s\u00f5nastikke koostada, toimetada ja k\u00fcljendada, teha lihtsaid ja keerulisi struktuurip\u00f5hiseid p\u00e4ringuid ning p\u00e4ringutulemusi sortida. Toimetaja t\u00f6\u00f6 h\u00f5lbustamiseks on loodud mitmeid t\u00f6\u00f6riistu, nt ristviidete kontroll, hulgiparandused kogu s\u00f5nastikus, eesti morfoloogia andmete genereerimine, k\u00fcljendusvaate kujundus, s\u00f5nastikuteksti eksport Wordi jms."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10304199"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Veebip\u00f5hine s\u00f5nastikus\u00fcsteem EELex "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/cae13e58-5ebd-5a3e-9970-95a98ffa7d4e.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/cae13e58-5ebd-5a3e-9970-95a98ffa7d4e.json
deleted file mode 100644
index d1659acc..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/cae13e58-5ebd-5a3e-9970-95a98ffa7d4e.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00129L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9845130",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9845130"
-    ],
-    "PublicationTimestamp": "2016-12-02T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Lippus, P\u00e4rtel"
-    ],
-    "fulltext": "oai:oai.datacite.org:9845130;2019-02-22T03:32:52Z;ESTDOI;ESTDOI.KEEL;P\u00f5hjatuule ja p\u00e4ikese korpus v.1.0.3;Estonian North Wind and the Sun Corpus v.1.0.3;Lippus, P\u00e4rtel;Center of Estonian Language Resources;2016;Issued: 2016-12-02;Updated: 2016-12-02;doi:10.15155/1-00-0000-0000-0000-00129L;Abstract;Recordings of the tale \u201cP\u00f5hjatuul ja p\u00e4ike\u201d (North Wind and the Sun) read by the same speakers who participated in the Phonetic Corpus of Estonian Spontaneous Speech. Most of the speakers read the text two times. The text is annotated using Praat TextGrids: words in standard orthography and phonemes in SAMPA.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cae13e58-5ebd-5a3e-9970-95a98ffa7d4e",
-    "notes": [
-        "Abstract",
-        "Recordings of the tale \u201cP\u00f5hjatuul ja p\u00e4ike\u201d (North Wind and the Sun) read by the same speakers who participated in the Phonetic Corpus of Estonian Spontaneous Speech. Most of the speakers read the text two times. The text is annotated using Praat TextGrids: words in standard orthography and phonemes in SAMPA."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9845130"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "P\u00f5hjatuule ja p\u00e4ikese korpus v.1.0.3",
-        "Estonian North Wind and the Sun Corpus v.1.0.3"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/cc40a240-5750-56b1-a523-2e2de9084538.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/cc40a240-5750-56b1-a523-2e2de9084538.json
deleted file mode 100644
index 65799f3f..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/cc40a240-5750-56b1-a523-2e2de9084538.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05B4FL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9352873",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9352873"
-    ],
-    "PublicationTimestamp": "2017-03-03T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:9352873;2019-04-20T13:33:03Z;ESTDOI;ESTDOI.KEEL;Seto s\u00f5nastik;The Dictionary of the Seto Dialect;Hein, Indrek;Center of Estonian Language Resources;2016;Issued: 2016-10-31;Updated: 2017-03-03;doi:10.15155/3-00-0000-0000-0000-05B4FL;Abstract;Esimene seto veebis\u00f5nastik sisaldab \u00fcle 6000 m\u00e4rks\u00f5na, mida saab otsida nii murdekeelse kirjapildi kui ka lihtsustatud ja ilma diakriitiliste m\u00e4rkideta variandi j\u00e4rgi.;Abstract;The first online Seto dictionary contains over 6000 keywords accessible to search both in dialect orthography and in simplified spelling (without diacritical marks).",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cc40a240-5750-56b1-a523-2e2de9084538",
-    "notes": [
-        "Abstract",
-        "Esimene seto veebis\u00f5nastik sisaldab \u00fcle 6000 m\u00e4rks\u00f5na, mida saab otsida nii murdekeelse kirjapildi kui ka lihtsustatud ja ilma diakriitiliste m\u00e4rkideta variandi j\u00e4rgi.",
-        "Abstract",
-        "The first online Seto dictionary contains over 6000 keywords accessible to search both in dialect orthography and in simplified spelling (without diacritical marks)."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9352873"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Seto s\u00f5nastik",
-        "The Dictionary of the Seto Dialect"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/cd10de03-5e1c-5715-8f67-b00f4692ac92.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/cd10de03-5e1c-5715-8f67-b00f4692ac92.json
deleted file mode 100644
index 326942ba..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/cd10de03-5e1c-5715-8f67-b00f4692ac92.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00145L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:13446396",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:13446396"
-    ],
-    "PublicationTimestamp": "2017-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laur, Sven"
-    ],
-    "fulltext": "oai:oai.datacite.org:13446396;2018-12-08T04:01:44Z;ESTDOI;ESTDOI.KEEL;EstNLTK sentence splitting;Laur, Sven;Center of Estonian Language Resources;2017;Issued: 2017-12-11;Updated: 2017-12-11;doi:10.15155/1-00-0000-0000-0000-00145L;Abstract;Estonian NLTK toolkit - detecting sentence boundaries",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cd10de03-5e1c-5715-8f67-b00f4692ac92",
-    "notes": [
-        "Abstract",
-        "Estonian NLTK toolkit - detecting sentence boundaries"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:13446396"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "EstNLTK sentence splitting"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/cd962f22-d9e4-51af-9fb5-6e33681dc85e.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/cd962f22-d9e4-51af-9fb5-6e33681dc85e.json
deleted file mode 100644
index 0bb6455d..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/cd962f22-d9e4-51af-9fb5-6e33681dc85e.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-00017L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5757251",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5757251"
-    ],
-    "PublicationTimestamp": "2017-01-25T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Langemets, Margit"
-    ],
-    "fulltext": "oai:oai.datacite.org:5757251;2019-03-18T18:25:42Z;ESTDOI;ESTDOI.KEEL;Eesti \u00f5igekeelsuss\u00f5naraamat \u00d5S 2006;Dictionary of Standard Estonian \u00d5S 2006;Langemets, Margit;Center of Estonian Language Resources;2012;Issued: 2012-06-13;Updated: 2017-01-25;doi:10.15155/3-00-0000-0000-0000-00017L;Abstract;See s\u00f5naraamat on vananenud ning sobib kasutamiseks vaid teadust\u00f6\u00f6s. Kehtivat keelenormi kajastab \"Eesti \u00f5igekeelsuss\u00f5naraamat \u00d5S 2013\"\n\n\u00d5S ajakohane versioon asub aadressil http://www.eki.ee/dict/qs/.;Abstract;\u00d5S 2006 is outdated version and suitable only for research purposes. The latest version of \u00d5S is accessible at http://www.eki.ee/dict/qs/.\n\n\u00d5S 2006 is a normative dictionary of modern standard Estonian, giving recommendations on correct language use. It contains recommended spellings and the morphology of words, instructions on pronunciation and semantics, also some syntactic recommendations. Abbreviations, geographical names and instruction on pronouncing foreign names are attached. ",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cd962f22-d9e4-51af-9fb5-6e33681dc85e",
-    "notes": [
-        "Abstract",
-        "See s\u00f5naraamat on vananenud ning sobib kasutamiseks vaid teadust\u00f6\u00f6s. Kehtivat keelenormi kajastab \"Eesti \u00f5igekeelsuss\u00f5naraamat \u00d5S 2013\"\n\n\u00d5S ajakohane versioon asub aadressil http://www.eki.ee/dict/qs/.",
-        "Abstract",
-        "\u00d5S 2006 is outdated version and suitable only for research purposes. The latest version of \u00d5S is accessible at http://www.eki.ee/dict/qs/.\n\n\u00d5S 2006 is a normative dictionary of modern standard Estonian, giving recommendations on correct language use. It contains recommended spellings and the morphology of words, instructions on pronunciation and semantics, also some syntactic recommendations. Abbreviations, geographical names and instruction on pronouncing foreign names are attached. "
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5757251"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti \u00f5igekeelsuss\u00f5naraamat \u00d5S 2006",
-        "Dictionary of Standard Estonian \u00d5S 2006"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/cdbf0507-dd20-5685-9510-c598bdb5ecfc.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/cdbf0507-dd20-5685-9510-c598bdb5ecfc.json
deleted file mode 100644
index c24dad52..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/cdbf0507-dd20-5685-9510-c598bdb5ecfc.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-0632EL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10303798",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10303798"
-    ],
-    "PublicationTimestamp": "2017-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Mihkla, Meelis"
-    ],
-    "fulltext": "oai:oai.datacite.org:10303798;2019-04-08T17:03:05Z;ESTDOI;ESTDOI.KEEL;V\u00f5ru murde HTS-k\u00f5nes\u00fcntesaator;HTS Speech Synthesiser for V\u00f5ru dialect;Mihkla, Meelis;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2017-02-15;doi:10.15155/3-00-0000-0000-0000-0632EL;Abstract;Loeb ette v\u00f5rumurdelist teksti.;Abstract;Reads aloud texts written in V\u00f5ru dialect.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cdbf0507-dd20-5685-9510-c598bdb5ecfc",
-    "notes": [
-        "Abstract",
-        "Loeb ette v\u00f5rumurdelist teksti.",
-        "Abstract",
-        "Reads aloud texts written in V\u00f5ru dialect."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10303798"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "V\u00f5ru murde HTS-k\u00f5nes\u00fcntesaator",
-        "HTS Speech Synthesiser for V\u00f5ru dialect"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/cecfe9ff-09a0-5fb9-b339-a9c1a0c02af6.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/cecfe9ff-09a0-5fb9-b339-a9c1a0c02af6.json
deleted file mode 100644
index 7b4ba469..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/cecfe9ff-09a0-5fb9-b339-a9c1a0c02af6.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0012CL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10137047",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10137047"
-    ],
-    "PublicationTimestamp": "2015-05-21T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Orav, Heili"
-    ],
-    "fulltext": "oai:oai.datacite.org:10137047;2019-04-18T17:36:28Z;ESTDOI;ESTDOI.KEEL;Estonian Wordnet (kb71-LAST);Orav, Heili;Center of Estonian Language Resources;2014;Issued: 2014-03-21;Updated: 2015-05-21;doi:10.15155/1-00-0000-0000-0000-0012CL;Abstract;The atom of a wordnet-type thesaurus is a synonym set (also called a synset), which is a set containing all the synonymous words or multi-word units that express the same concept. All words in a synset belong into the same part of speech.\n\nTHIS IS THE NEWEST VERSION",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cecfe9ff-09a0-5fb9-b339-a9c1a0c02af6",
-    "notes": [
-        "Abstract",
-        "The atom of a wordnet-type thesaurus is a synonym set (also called a synset), which is a set containing all the synonymous words or multi-word units that express the same concept. All words in a synset belong into the same part of speech.\n\nTHIS IS THE NEWEST VERSION"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10137047"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Estonian Wordnet (kb71-LAST)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ced55826-214c-54ee-bdf1-5e460e9ce4cb.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ced55826-214c-54ee-bdf1-5e460e9ce4cb.json
deleted file mode 100644
index ce35b869..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ced55826-214c-54ee-bdf1-5e460e9ce4cb.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-0008AL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:12540147",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:12540147"
-    ],
-    "PublicationTimestamp": "2017-10-10T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Krikmann, Jaak",
-        "K\u00f5iva, Mare"
-    ],
-    "fulltext": "oai:oai.datacite.org:12540147;2018-10-25T20:43:33Z;ESTDOI;ESTDOI.KEEL;Eesti m\u00f5istatuste andmebaas;Estonian Riddles Database;K\u00f5iva, Mare;Krikmann, Jaak;Center of Estonian Language Resources;2017;Issued: 2017-10-10;Updated: 2017-10-10;doi:10.15155/9-00-0000-0000-0000-0008AL;Abstract;Andmebaas on rajatud Eesti Kirjandusmuuseumi folkloristika osakonnas. Baasi aluseks oli 2800 Word 7.0 formaadis andmetabelit, mille p\u00f5hjal toodeti akadeemilise v\u00e4ljaande \"Eesti m\u00f5istatused\" (EM) p\u00f5hik\u00f6idete I (2001) ja II (2002) k\u00e4sikiri. Andmebaas on kasutatav kolmes variandis (vt t\u00e4psemalt), siinne versioon on xml-kujule teisendatud \"baas-lugemik\", mis esitab 95 751 eesti m\u00f5istatusteksti kirjed 20 000 kirje kaupa EM I\u2013II t\u00fc\u00fcpide ja tekstide j\u00e4rjekorras (erinevalt andmebaasi kasutajaliidesest, kus on kirjed esitatud 1000 kaupa). Andmebaasi juurde kuuluvad abimaterjalid (millest k\u00f5iki pole siinses versioonis): 1) kogu EM I\u2013II tr\u00fckiversioonis leiduv teave 2) lahendite temaatiline register 3) Eesti kihelkondade kontuurkaart kihelkonnal\u00fchenditega 4) m\u00f5istatuste andmebaasi suhtes autonoomne \u00fcldotstarbeline kartografeerimismasin.\n\nAndmebaas kasutab \u00fchist allikmaterjali eesti m\u00f5istatuste akadeemiliste v\u00e4ljaannetega:\n\nEesti m\u00f5istatused. I, [m\u00f5istatust\u00fc\u00fcbid] 1-1350 = Aenigmata Estonica. I, 1-1350 / Eesti Keele Instituut, Eesti Kirjandusmuuseum, Tartu \u00dclikool; koostanud Anne Hussar, Arvo Krikmann, Rein Saukas, Piret Voolaid; toimetanud Arvo Krikmann ja Rein Saukas, Tartu: Eesti Keele Sihtasutus, 2001 (Tallinn: Pakett), 891 lk.\n\nEesti m\u00f5istatused. II, [m\u00f5istatust\u00fc\u00fcbid] 1351-2800 = Aenigmata Estonica II, 1351-2800 / Eesti Keele Instituut, Eesti Kirjandusmuuseum, Tartu \u00dclikool; koostanud Anne Hussar, Arvo Krikmann, Rein Saukas, Piret Voolaid; toimetanud Arvo Krikmann ja Rein Saukas, Tartu: Eesti Keele Sihtasutus, 2002 (Tallinn: Pakett), 877 lk. \nElektroonilise andmebaasi koostajad: Jaak Krikmann (php), Arvo Krikmann (autor, konsultatsioon).\n;Abstract;The database was created at the Department of Folkloristics of the Estonian Literary Museum. The foundation for the database was 2,800 Word 7.0 format data tables, on the basis of which the manuscripts of the main volumes I (2001) and II (2002) of the academic publication \"Estonian Riddles\" (ER) were compiled. The database is available in three variants (see details); this version is converted into an xml-formatted \"base reader\", which provides 95,751 entries of the texts of Estonian riddles by groups of 20,000 entries in the order of the types and texts of EM I-II (unlike the online interface of the database, in which entries are given by groups of 1000). Auxiliary materials for the database (not all included here) are: 1) all the information contained in the ER I-II paper editions; 2) thematic register of solutions; 3) a contour map of Estonian parishes with parish abbreviations; 4) an autonomous general purpose mapping machine.\n\nThe database uses source material common with academic editions of Estonian riddles:\nEstonian Riddles [Eesti m\u00f5istatused] I, [riddle types] 1\u20131350 = Aenigmata Estonica I, 1\u20131350 / Institute of the Estonian Language, Estonian Literary Museum, University of Tartu; compiled by Anne Hussar, Arvo Krikmann, Rein Saukas, Piret Voolaid; edited by Arvo Krikmann and Rein Saukas. Tartu: Estonian Language Foundation, 2001 (Tallinn: Pakett), 891 pages.\nEstonian Riddles [Eesti m\u00f5istatused] II, [riddle types] 1351\u20132800 = Aenigmata Estonica II, 1351\u20132800 / Institute of the Estonian Language, Estonian Literary Museum, University of Tartu; compiled by Anne Hussar, Arvo Krikmann, Rein Saukas, Piret Voolaid; edited by Arvo Krikmann and Rein Saukas. Tartu: Estonian Language Foundation, 2002 (Tallinn: Pakett), 877 pages.\nCompilers of the electronic database: Jaak Krikmann (php), Arvo Krikmann (author, consultant).\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ced55826-214c-54ee-bdf1-5e460e9ce4cb",
-    "notes": [
-        "Abstract",
-        "Andmebaas on rajatud Eesti Kirjandusmuuseumi folkloristika osakonnas. Baasi aluseks oli 2800 Word 7.0 formaadis andmetabelit, mille p\u00f5hjal toodeti akadeemilise v\u00e4ljaande \"Eesti m\u00f5istatused\" (EM) p\u00f5hik\u00f6idete I (2001) ja II (2002) k\u00e4sikiri. Andmebaas on kasutatav kolmes variandis (vt t\u00e4psemalt), siinne versioon on xml-kujule teisendatud \"baas-lugemik\", mis esitab 95 751 eesti m\u00f5istatusteksti kirjed 20 000 kirje kaupa EM I\u2013II t\u00fc\u00fcpide ja tekstide j\u00e4rjekorras (erinevalt andmebaasi kasutajaliidesest, kus on kirjed esitatud 1000 kaupa). Andmebaasi juurde kuuluvad abimaterjalid (millest k\u00f5iki pole siinses versioonis): 1) kogu EM I\u2013II tr\u00fckiversioonis leiduv teave 2) lahendite temaatiline register 3) Eesti kihelkondade kontuurkaart kihelkonnal\u00fchenditega 4) m\u00f5istatuste andmebaasi suhtes autonoomne \u00fcldotstarbeline kartografeerimismasin.\n\nAndmebaas kasutab \u00fchist allikmaterjali eesti m\u00f5istatuste akadeemiliste v\u00e4ljaannetega:\n\nEesti m\u00f5istatused. I, [m\u00f5istatust\u00fc\u00fcbid] 1-1350 = Aenigmata Estonica. I, 1-1350 / Eesti Keele Instituut, Eesti Kirjandusmuuseum, Tartu \u00dclikool; koostanud Anne Hussar, Arvo Krikmann, Rein Saukas, Piret Voolaid; toimetanud Arvo Krikmann ja Rein Saukas, Tartu: Eesti Keele Sihtasutus, 2001 (Tallinn: Pakett), 891 lk.\n\nEesti m\u00f5istatused. II, [m\u00f5istatust\u00fc\u00fcbid] 1351-2800 = Aenigmata Estonica II, 1351-2800 / Eesti Keele Instituut, Eesti Kirjandusmuuseum, Tartu \u00dclikool; koostanud Anne Hussar, Arvo Krikmann, Rein Saukas, Piret Voolaid; toimetanud Arvo Krikmann ja Rein Saukas, Tartu: Eesti Keele Sihtasutus, 2002 (Tallinn: Pakett), 877 lk. \nElektroonilise andmebaasi koostajad: Jaak Krikmann (php), Arvo Krikmann (autor, konsultatsioon).\n",
-        "Abstract",
-        "The database was created at the Department of Folkloristics of the Estonian Literary Museum. The foundation for the database was 2,800 Word 7.0 format data tables, on the basis of which the manuscripts of the main volumes I (2001) and II (2002) of the academic publication \"Estonian Riddles\" (ER) were compiled. The database is available in three variants (see details); this version is converted into an xml-formatted \"base reader\", which provides 95,751 entries of the texts of Estonian riddles by groups of 20,000 entries in the order of the types and texts of EM I-II (unlike the online interface of the database, in which entries are given by groups of 1000). Auxiliary materials for the database (not all included here) are: 1) all the information contained in the ER I-II paper editions; 2) thematic register of solutions; 3) a contour map of Estonian parishes with parish abbreviations; 4) an autonomous general purpose mapping machine.\n\nThe database uses source material common with academic editions of Estonian riddles:\nEstonian Riddles [Eesti m\u00f5istatused] I, [riddle types] 1\u20131350 = Aenigmata Estonica I, 1\u20131350 / Institute of the Estonian Language, Estonian Literary Museum, University of Tartu; compiled by Anne Hussar, Arvo Krikmann, Rein Saukas, Piret Voolaid; edited by Arvo Krikmann and Rein Saukas. Tartu: Estonian Language Foundation, 2001 (Tallinn: Pakett), 891 pages.\nEstonian Riddles [Eesti m\u00f5istatused] II, [riddle types] 1351\u20132800 = Aenigmata Estonica II, 1351\u20132800 / Institute of the Estonian Language, Estonian Literary Museum, University of Tartu; compiled by Anne Hussar, Arvo Krikmann, Rein Saukas, Piret Voolaid; edited by Arvo Krikmann and Rein Saukas. Tartu: Estonian Language Foundation, 2002 (Tallinn: Pakett), 877 pages.\nCompilers of the electronic database: Jaak Krikmann (php), Arvo Krikmann (author, consultant).\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:12540147"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti m\u00f5istatuste andmebaas",
-        "Estonian Riddles Database"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/cf0fbb4a-502d-5068-a03b-ab92cdf5a75e.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/cf0fbb4a-502d-5068-a03b-ab92cdf5a75e.json
deleted file mode 100644
index 30fd2229..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/cf0fbb4a-502d-5068-a03b-ab92cdf5a75e.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00127L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9836561",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9836561"
-    ],
-    "PublicationTimestamp": "2016-12-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Tkachenko, Alexander"
-    ],
-    "fulltext": "oai:oai.datacite.org:9836561;2019-04-17T17:26:37Z;ESTDOI;ESTDOI.KEEL;Gap-tagger corpus;Tkachenko, Alexander;Center of Estonian Language Resources;2016;Issued: 2016-12-01;Updated: 2016-12-01;doi:10.15155/1-00-0000-0000-0000-00127L;Abstract;Gap-tagger corpus contains data for assessing correctness of automatically generated alternatives for filling a gap (missing word). To get clearly interpretable results, we conducted modified version of A/B testing where the user had to choose between the original word and an alternative. The user has an option either to pick one of the two proposed words, or to report both words as appropriate. Since we know the right answer, we can objectively assess the suitability of alternative answers without formally specifying what classifies as a correct answer. Experiments were run using gap-tagger tool https://github.com/estnltk/gap-tagger. \n\nIn the corpus file, each line correspond to one question. The file is in csv format with the following columns:\nsentence: sentence\ngap_start: start position of the gap word in the sentence\ngap_end: end position of the gap word in the sentence\ngap_word: correct gap word\nvariant: gap variant word\ncorrect_selected: indicates if correct word is selected\nboth_selected: indicates if user reported both words as appropriate\nannotator: user id\ntime: time in milliseconds which took user to answer a question",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cf0fbb4a-502d-5068-a03b-ab92cdf5a75e",
-    "notes": [
-        "Abstract",
-        "Gap-tagger corpus contains data for assessing correctness of automatically generated alternatives for filling a gap (missing word). To get clearly interpretable results, we conducted modified version of A/B testing where the user had to choose between the original word and an alternative. The user has an option either to pick one of the two proposed words, or to report both words as appropriate. Since we know the right answer, we can objectively assess the suitability of alternative answers without formally specifying what classifies as a correct answer. Experiments were run using gap-tagger tool https://github.com/estnltk/gap-tagger. \n\nIn the corpus file, each line correspond to one question. The file is in csv format with the following columns:\nsentence: sentence\ngap_start: start position of the gap word in the sentence\ngap_end: end position of the gap word in the sentence\ngap_word: correct gap word\nvariant: gap variant word\ncorrect_selected: indicates if correct word is selected\nboth_selected: indicates if user reported both words as appropriate\nannotator: user id\ntime: time in milliseconds which took user to answer a question"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9836561"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Gap-tagger corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/cf74b7bb-de59-5b15-b3e9-cedcf2ce20cb.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/cf74b7bb-de59-5b15-b3e9-cedcf2ce20cb.json
deleted file mode 100644
index d9f2588b..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/cf74b7bb-de59-5b15-b3e9-cedcf2ce20cb.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00147L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:13902966",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:13902966"
-    ],
-    "PublicationTimestamp": "2018-01-24T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Lippus, P\u00e4rtel"
-    ],
-    "fulltext": "oai:oai.datacite.org:13902966;2019-04-06T16:30:56Z;ESTDOI;ESTDOI.KEEL;Niidumari prosoodia korpus;Meadow Mari prosody corpus;Lippus, P\u00e4rtel;Center of Estonian Language Resources;2018;Issued: 2018-01-24;Updated: 2018-01-24;doi:10.15155/1-00-0000-0000-0000-00147L;Abstract;Mari s\u00f5naprosoodia uurimiseks kogutud andmestik. Sisaldab raamlauses loetud tests\u00f5nu 8 keelejuhilt. Iga keelejuht luges 100 lauset, iga lause sisaldas tests\u00f5na kord lause keskel, kord lause l\u00f5pus.\nMaterjali kasutati siin: Lehiste, I., Teras, P., Help, T., Lippus, P., Meister, E., Pajusalu, K., & Viitso, T.-R. (2005). Meadow Mari prosody. Tallinn: Teaduste Akadeemia Kirjastus. Retrieved from http://kirj.ee/public/va_lu/Meadow%20Mari%20Prosody.pdf;Abstract;The recordings collected for studying Mari word prosody. 8 test subjects read 100 sentences. Each carrrier sentence contained a test word in phrase medial position and phrase final position.\nLehiste, I., Teras, P., Help, T., Lippus, P., Meister, E., Pajusalu, K., & Viitso, T.-R. (2005). Meadow Mari prosody. Tallinn: Teaduste Akadeemia Kirjastus. Retrieved from http://kirj.ee/public/va_lu/Meadow%20Mari%20Prosody.pdf",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cf74b7bb-de59-5b15-b3e9-cedcf2ce20cb",
-    "notes": [
-        "Abstract",
-        "Mari s\u00f5naprosoodia uurimiseks kogutud andmestik. Sisaldab raamlauses loetud tests\u00f5nu 8 keelejuhilt. Iga keelejuht luges 100 lauset, iga lause sisaldas tests\u00f5na kord lause keskel, kord lause l\u00f5pus.\nMaterjali kasutati siin: Lehiste, I., Teras, P., Help, T., Lippus, P., Meister, E., Pajusalu, K., & Viitso, T.-R. (2005). Meadow Mari prosody. Tallinn: Teaduste Akadeemia Kirjastus. Retrieved from http://kirj.ee/public/va_lu/Meadow%20Mari%20Prosody.pdf",
-        "Abstract",
-        "The recordings collected for studying Mari word prosody. 8 test subjects read 100 sentences. Each carrrier sentence contained a test word in phrase medial position and phrase final position.\nLehiste, I., Teras, P., Help, T., Lippus, P., Meister, E., Pajusalu, K., & Viitso, T.-R. (2005). Meadow Mari prosody. Tallinn: Teaduste Akadeemia Kirjastus. Retrieved from http://kirj.ee/public/va_lu/Meadow%20Mari%20Prosody.pdf"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:13902966"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Niidumari prosoodia korpus",
-        "Meadow Mari prosody corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/cfa98e20-c8d3-5424-a6f2-c537f05050c6.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/cfa98e20-c8d3-5424-a6f2-c537f05050c6.json
deleted file mode 100644
index 53ff47c4..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/cfa98e20-c8d3-5424-a6f2-c537f05050c6.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00154L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14560570",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14560570"
-    ],
-    "PublicationTimestamp": "2018-03-26T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Lippus, P\u00e4rtel"
-    ],
-    "fulltext": "oai:oai.datacite.org:14560570;2019-04-17T17:27:05Z;ESTDOI;ESTDOI.KEEL;Eesti keele spontaanse k\u00f5ne foneetiline korpus v.1.0.4;Phonetic Corpus of Estonian Spontaneous Speech v.1.0.4;Lippus, P\u00e4rtel;Center of Estonian Language Resources;2018;Issued: 2018-02-14;Updated: 2018-03-26;doi:10.15155/1-00-0000-0000-0000-00154L;Abstract;The aim of the corpus is to compile a large amount of quality recordings of spontaneous Estonian and segment it phonetically on different levels. The project started in autumn 2006.\n\nThe total size of the corpus is approximately 90 hours of speech from 130 speakers with different dialectological and social background. Speakers are from different age groups. They are asked to participate with face-to-face invitation and they are aware of the purpose of the recordings.\n\nMost of the recordings are made in a recording studio, some also on fieldwork. The signal of each speaker is recorded in a separate channel. The distance between the speakers is about 3 meters to minimize the effect of overlaps. For the field-work recordings head-set microphones are used. Recordings are saved in PCM wav-format and are not compressed. Background information about the recordings is collected in a text-file.\nSegmentation and annotation files are saved as Praat TextGrid files and get same filenames as recordings segmented.\n\nSegmentation and annotation\nSegmentation and annotation is done with the Praat program (www.praat.org). Recordings are segmented manually on different levels (automatic segmentation program is also elaborated and tested).\nFollowing tiers are used:\n-Words (in orthographic spelling),\n-Phonemes (SAMPA adjusted for Estonian is used for transcription),\n-Syllables (short \u2013 long, open \u2013 closed),\n-Prosodic feet,\n-Intonation phrases or inter-pausal units;\n-Changes in voice quality (e.g. creaky voice);",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "cfa98e20-c8d3-5424-a6f2-c537f05050c6",
-    "notes": [
-        "Abstract",
-        "The aim of the corpus is to compile a large amount of quality recordings of spontaneous Estonian and segment it phonetically on different levels. The project started in autumn 2006.\n\nThe total size of the corpus is approximately 90 hours of speech from 130 speakers with different dialectological and social background. Speakers are from different age groups. They are asked to participate with face-to-face invitation and they are aware of the purpose of the recordings.\n\nMost of the recordings are made in a recording studio, some also on fieldwork. The signal of each speaker is recorded in a separate channel. The distance between the speakers is about 3 meters to minimize the effect of overlaps. For the field-work recordings head-set microphones are used. Recordings are saved in PCM wav-format and are not compressed. Background information about the recordings is collected in a text-file.\nSegmentation and annotation files are saved as Praat TextGrid files and get same filenames as recordings segmented.\n\nSegmentation and annotation\nSegmentation and annotation is done with the Praat program (www.praat.org). Recordings are segmented manually on different levels (automatic segmentation program is also elaborated and tested).\nFollowing tiers are used:\n-Words (in orthographic spelling),\n-Phonemes (SAMPA adjusted for Estonian is used for transcription),\n-Syllables (short \u2013 long, open \u2013 closed),\n-Prosodic feet,\n-Intonation phrases or inter-pausal units;\n-Changes in voice quality (e.g. creaky voice);"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14560570"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele spontaanse k\u00f5ne foneetiline korpus v.1.0.4",
-        "Phonetic Corpus of Estonian Spontaneous Speech v.1.0.4"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d0c782df-a51e-55a3-8148-2470503544f5.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d0c782df-a51e-55a3-8148-2470503544f5.json
deleted file mode 100644
index 8cbaaf94..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d0c782df-a51e-55a3-8148-2470503544f5.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-077CFL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:15534457",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:15534457"
-    ],
-    "PublicationTimestamp": "2018-07-13T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Soon, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:15534457;2019-02-20T08:02:06Z;ESTDOI;ESTDOI.KEEL;Esterm v20180701;Esterm v20180701;Soon, Tiina;Center of Estonian Language Resources;2018;Issued: 2018-07-13;Updated: 2018-07-13;doi:10.15155/3-00-0000-0000-0000-077CFL;Abstract;Esterm on Eesti Keele Instituudi mitmekeelne terminibaas, mis sisaldab peamiselt Euroopa Liidu ja Eesti Vabariigi \u00f5igusaktide termineid. Terminibaas koondab \u00fcle 50 valdkonna terminoloogiat.;Abstract;Esterm is a multilingual termbase which includes terms mainly from the legal acts of the Republic of Estonia and the European Union. The termbase contains terminology from more than 50 domains.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d0c782df-a51e-55a3-8148-2470503544f5",
-    "notes": [
-        "Abstract",
-        "Esterm on Eesti Keele Instituudi mitmekeelne terminibaas, mis sisaldab peamiselt Euroopa Liidu ja Eesti Vabariigi \u00f5igusaktide termineid. Terminibaas koondab \u00fcle 50 valdkonna terminoloogiat.",
-        "Abstract",
-        "Esterm is a multilingual termbase which includes terms mainly from the legal acts of the Republic of Estonia and the European Union. The termbase contains terminology from more than 50 domains."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:15534457"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Esterm v20180701",
-        "Esterm v20180701"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d10f0eae-04a3-5bd5-8a76-b47eb16aa6d3.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d10f0eae-04a3-5bd5-8a76-b47eb16aa6d3.json
deleted file mode 100644
index 12d9ff88..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d10f0eae-04a3-5bd5-8a76-b47eb16aa6d3.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-0632FL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10303799",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10303799"
-    ],
-    "PublicationTimestamp": "2017-01-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Mihkla, Meelis"
-    ],
-    "fulltext": "oai:oai.datacite.org:10303799;2019-02-19T20:31:22Z;ESTDOI;ESTDOI.KEEL;Eesti keele HTS-k\u00f5nes\u00fcntesaator ;Mihkla, Meelis;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2017-01-31;doi:10.15155/3-00-0000-0000-0000-0632FL;Abstract;Eestikeelne HTS-k\u00f5nes\u00fcntesaator ",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d10f0eae-04a3-5bd5-8a76-b47eb16aa6d3",
-    "notes": [
-        "Abstract",
-        "Eestikeelne HTS-k\u00f5nes\u00fcntesaator "
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10303799"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele HTS-k\u00f5nes\u00fcntesaator "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d13f7c5a-fc3a-57e8-8cfb-f99af21926f8.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d13f7c5a-fc3a-57e8-8cfb-f99af21926f8.json
deleted file mode 100644
index c41770eb..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d13f7c5a-fc3a-57e8-8cfb-f99af21926f8.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05B50L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9352874",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9352874"
-    ],
-    "PublicationTimestamp": "2016-10-31T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laansalu, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:9352874;2019-04-23T07:02:12Z;ESTDOI;ESTDOI.KEEL;Hiiu s\u00f5naraamat;Laansalu, Tiina;Center of Estonian Language Resources;2016;Issued: 2016-10-31;Updated: 2016-10-31;doi:10.15155/3-00-0000-0000-0000-05B50L;Abstract;S\u00f5nastik kuulub Eesti Keele Instituudi v\u00e4ikeste murdes\u00f5nastike sarja ja on maailma esimene hiiu keele s\u00f5naraamat. See sisaldab 6300 m\u00e4rks\u00f5na ning esitab hiiu keele p\u00f5his\u00f5navara ja murdes\u00f5nu k\u00f5igist Hiiumaa murrakutest. Kuna hiiu keele omap\u00e4ra tuleb esile eesk\u00e4tt tema h\u00e4\u00e4likulises k\u00fcljes, siis on s\u00f5nastikus n\u00e4idatud ka \u00fcldtuntud s\u00f5nade puhul nende hiiup\u00e4rast h\u00e4\u00e4ldust. Samuti on m\u00e4rks\u00f5nade juures n\u00e4itelaused koos viitega kihelkonnale, kust n\u00e4ide on kirja pandud.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d13f7c5a-fc3a-57e8-8cfb-f99af21926f8",
-    "notes": [
-        "Abstract",
-        "S\u00f5nastik kuulub Eesti Keele Instituudi v\u00e4ikeste murdes\u00f5nastike sarja ja on maailma esimene hiiu keele s\u00f5naraamat. See sisaldab 6300 m\u00e4rks\u00f5na ning esitab hiiu keele p\u00f5his\u00f5navara ja murdes\u00f5nu k\u00f5igist Hiiumaa murrakutest. Kuna hiiu keele omap\u00e4ra tuleb esile eesk\u00e4tt tema h\u00e4\u00e4likulises k\u00fcljes, siis on s\u00f5nastikus n\u00e4idatud ka \u00fcldtuntud s\u00f5nade puhul nende hiiup\u00e4rast h\u00e4\u00e4ldust. Samuti on m\u00e4rks\u00f5nade juures n\u00e4itelaused koos viitega kihelkonnale, kust n\u00e4ide on kirja pandud."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9352874"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Hiiu s\u00f5naraamat"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d2466b33-0626-5e73-a522-6f184d7136b9.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d2466b33-0626-5e73-a522-6f184d7136b9.json
deleted file mode 100644
index 7b8eb478..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d2466b33-0626-5e73-a522-6f184d7136b9.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-00022L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5755419",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5755419"
-    ],
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Meister, Einar"
-    ],
-    "fulltext": "oai:oai.datacite.org:5755419;2019-04-17T17:25:54Z;ESTDOI;ESTDOI.KEEL;Raadiointervjuude korpus;Corpus of Radio Interviews;Meister, Einar;Center of Estonian Language Resources;2014;Issued: 2014-12-30;Updated: 2019-01-08;doi:10.15155/9-00-0000-0000-0000-00022L;Abstract;This corpus includes telepone interviews from different radio programmes.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d2466b33-0626-5e73-a522-6f184d7136b9",
-    "notes": [
-        "Abstract",
-        "This corpus includes telepone interviews from different radio programmes."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5755419"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Raadiointervjuude korpus",
-        "Corpus of Radio Interviews"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d26dcefb-3d0a-5373-91b0-e01183f4b4e9.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d26dcefb-3d0a-5373-91b0-e01183f4b4e9.json
deleted file mode 100644
index 51d93422..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d26dcefb-3d0a-5373-91b0-e01183f4b4e9.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00079L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5757467",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5757467"
-    ],
-    "PublicationTimestamp": "2015-05-22T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:5757467;2019-03-27T12:00:53Z;ESTDOI;ESTDOI.KEEL;Eesti-l\u00e4ti ehitusalane paralleelkorpus;Estonian-Latvian Parallel Corpus of building product texts;Muischnek, Kadri;Center of Estonian Language Resources;2013;Issued: 2013-01-07;Updated: 2015-05-22;doi:10.15155/1-00-0000-0000-0000-00079L;Abstract;korpus;Abstract;Parallel corpus of the info texts of building foams and sealants in Latvian and Estonian.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d26dcefb-3d0a-5373-91b0-e01183f4b4e9",
-    "notes": [
-        "Abstract",
-        "korpus",
-        "Abstract",
-        "Parallel corpus of the info texts of building foams and sealants in Latvian and Estonian."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5757467"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti-l\u00e4ti ehitusalane paralleelkorpus",
-        "Estonian-Latvian Parallel Corpus of building product texts"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d3b76939-c04d-5a8e-b2eb-ed83e6e39290.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d3b76939-c04d-5a8e-b2eb-ed83e6e39290.json
deleted file mode 100644
index 270d80eb..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d3b76939-c04d-5a8e-b2eb-ed83e6e39290.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06344L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10304167",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10304167"
-    ],
-    "PublicationTimestamp": "2018-03-23T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Soon, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:10304167;2019-04-02T14:02:22Z;ESTDOI;ESTDOI.KEEL;Esterm v20131231;Esterm v20131231;Soon, Tiina;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2018-03-23;doi:10.15155/3-00-0000-0000-0000-06344L;Abstract;ESTERM Eesti Keele Instituudi mitmekeelne terminibaas, mis sisaldab peamiselt Euroopa Liidu ja Eesti Vabariigi \u00f5igusaktide termineid. Terminibaas koondab \u00fcle 50 valdkonna terminoloogiat.;Abstract;ESTERM is a multilingual translation-based termbase; the terms come from the legal acts of the Republic of Estonia and the European Union, translated by the Estonian Legal Language Centre.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d3b76939-c04d-5a8e-b2eb-ed83e6e39290",
-    "notes": [
-        "Abstract",
-        "ESTERM Eesti Keele Instituudi mitmekeelne terminibaas, mis sisaldab peamiselt Euroopa Liidu ja Eesti Vabariigi \u00f5igusaktide termineid. Terminibaas koondab \u00fcle 50 valdkonna terminoloogiat.",
-        "Abstract",
-        "ESTERM is a multilingual translation-based termbase; the terms come from the legal acts of the Republic of Estonia and the European Union, translated by the Estonian Legal Language Centre."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10304167"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Esterm v20131231",
-        "Esterm v20131231"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d3fe51a2-0f6c-523c-a334-bbbad5b2f95a.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d3fe51a2-0f6c-523c-a334-bbbad5b2f95a.json
deleted file mode 100644
index ffe17150..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d3fe51a2-0f6c-523c-a334-bbbad5b2f95a.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-071EAL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14560137",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14560137"
-    ],
-    "PublicationTimestamp": "2018-03-26T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Koppel, Kristina",
-        "Kallas, Jelena"
-    ],
-    "fulltext": "oai:oai.datacite.org:14560137;2019-04-09T13:00:58Z;ESTDOI;ESTDOI.KEEL;Eesti keele \u00f5ppekorpus 2018 (etSkELL);Estonian Corpus for Learners 2018 (etSkELL);Kallas, Jelena;Koppel, Kristina;Center of Estonian Language Resources;2018;Issued: 2018-03-26;Updated: 2018-03-26;doi:10.15155/3-00-0000-0000-0000-071EAL;Abstract;Eesti keele \u00f5ppekorpus 2018 (etSkELL) on spetsiaalne tekstikorpus, mis sisaldab ainult keele\u00f5ppijale sobivaid lauseid. Laused p\u00e4rinevad Eesti keele \u00fchendkorpusest 2017 ja Eesti keele A1-C1 \u00f5pikute korpusest 2018. Keele\u00f5ppijale sobivate lausete tuvastamiseks kasutati Kristina Koppeli v\u00e4lja t\u00f6\u00f6tatud eesti keele GDEXi  (Good Dictionary Example) moodulit, mis v\u00f5imaldab lausete filtreerimist vastavalt etteantud parameetritele (nt lause pikkus, kirjavahem\u00e4rkide arv \u00fche lause piires jmt).\nEesti keele \u00f5ppekorpuse 2018 (etSkELL) suurus on u 248 000 s\u00f5na ja u 25 miljonit lauset. \nKorpus on lemmatiseeritud, m\u00e4rgendatud ja \u00fchestatud anal\u00fcsaatori EstNLTK abil.\nKorpus on loodud Eesti Keele Instituudi ja Lexical Computing Ltd. koost\u00f6\u00f6 raames. \n\n\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d3fe51a2-0f6c-523c-a334-bbbad5b2f95a",
-    "notes": [
-        "Abstract",
-        "Eesti keele \u00f5ppekorpus 2018 (etSkELL) on spetsiaalne tekstikorpus, mis sisaldab ainult keele\u00f5ppijale sobivaid lauseid. Laused p\u00e4rinevad Eesti keele \u00fchendkorpusest 2017 ja Eesti keele A1-C1 \u00f5pikute korpusest 2018. Keele\u00f5ppijale sobivate lausete tuvastamiseks kasutati Kristina Koppeli v\u00e4lja t\u00f6\u00f6tatud eesti keele GDEXi  (Good Dictionary Example) moodulit, mis v\u00f5imaldab lausete filtreerimist vastavalt etteantud parameetritele (nt lause pikkus, kirjavahem\u00e4rkide arv \u00fche lause piires jmt).\nEesti keele \u00f5ppekorpuse 2018 (etSkELL) suurus on u 248 000 s\u00f5na ja u 25 miljonit lauset. \nKorpus on lemmatiseeritud, m\u00e4rgendatud ja \u00fchestatud anal\u00fcsaatori EstNLTK abil.\nKorpus on loodud Eesti Keele Instituudi ja Lexical Computing Ltd. koost\u00f6\u00f6 raames. \n\n\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14560137"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele \u00f5ppekorpus 2018 (etSkELL)",
-        "Estonian Corpus for Learners 2018 (etSkELL)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d52946d0-0c15-58e9-9912-3daa4d6a85aa.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d52946d0-0c15-58e9-9912-3daa4d6a85aa.json
deleted file mode 100644
index d417459f..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d52946d0-0c15-58e9-9912-3daa4d6a85aa.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0015DL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14977739",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14977739"
-    ],
-    "PublicationTimestamp": "2018-05-04T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laur, Sven"
-    ],
-    "fulltext": "oai:oai.datacite.org:14977739;2019-04-06T14:32:13Z;ESTDOI;ESTDOI.KEEL;EstNLTK teek Pythoni jaoks;EstNLTK library for Python;Laur, Sven;Center of Estonian Language Resources;2018;Issued: 2018-05-04;Updated: 2018-05-04;doi:10.15155/1-00-0000-0000-0000-0015DL;Abstract;EstNLTK teegis on kergesti kohandatav ning robustne lingvistilise anal\u00fc\u00fcsi t\u00f6\u00f6voog, mis toimib ka\nkirjakeelest oluliselt erinevatel tekstidel. S\u00f5ltuvalt tekstide erip\u00e4rast on v\u00f5imalik kohandada s\u00f5nestamist,\nlausestamist ja morfoloogilist anal\u00fc\u00fcsi. Vaikimisi kasutatakse EKT67 projektis ja Koondkorpuse anal\u00fc\u00fcsi\nabil leitud lihtsustus- ja normaliseerimisreegleid. T\u00f6\u00f6 tulemust valideeriti l\u00e4bi Koondkorpuse ja etTenTen-\ni t\u00e4ieliku anal\u00fc\u00fcsi.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d52946d0-0c15-58e9-9912-3daa4d6a85aa",
-    "notes": [
-        "Abstract",
-        "EstNLTK teegis on kergesti kohandatav ning robustne lingvistilise anal\u00fc\u00fcsi t\u00f6\u00f6voog, mis toimib ka\nkirjakeelest oluliselt erinevatel tekstidel. S\u00f5ltuvalt tekstide erip\u00e4rast on v\u00f5imalik kohandada s\u00f5nestamist,\nlausestamist ja morfoloogilist anal\u00fc\u00fcsi. Vaikimisi kasutatakse EKT67 projektis ja Koondkorpuse anal\u00fc\u00fcsi\nabil leitud lihtsustus- ja normaliseerimisreegleid. T\u00f6\u00f6 tulemust valideeriti l\u00e4bi Koondkorpuse ja etTenTen-\ni t\u00e4ieliku anal\u00fc\u00fcsi."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14977739"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "EstNLTK teek Pythoni jaoks",
-        "EstNLTK library for Python"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d725ff24-c3f6-583a-be9d-02757785b289.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d725ff24-c3f6-583a-be9d-02757785b289.json
deleted file mode 100644
index 053950b8..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d725ff24-c3f6-583a-be9d-02757785b289.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00151L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14186193",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14186193"
-    ],
-    "PublicationTimestamp": "2018-02-06T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Lippus, P\u00e4rtel"
-    ],
-    "fulltext": "oai:oai.datacite.org:14186193;2019-04-06T18:30:54Z;ESTDOI;ESTDOI.KEEL;Mok\u0161a prosoodia korpus;Moksha prosody corpus;Lippus, P\u00e4rtel;Center of Estonian Language Resources;2018;Issued: 2018-02-06;Updated: 2018-02-06;doi:10.15155/1-00-0000-0000-0000-00151L;Abstract;95 loetud lausest koosnev andmestik, iga lause sisaldab kaks 1-3-silbilist tests\u00f5na. Salvestused kokku 28 keelejuhilt. Materjali kasutati raamatus: Aasm\u00e4e, N., Lippus, P., Pajusalu, K., Salveste, N., Zirnask, T., & Viitso, T.-R. (2013). Moksha prosody. Helsinki: Suomalais-Ugrilainen Seura. Retrieved from http://www.sgr.fi/sust/sust268/sust268.pdf;Abstract;The data consists of 95 test words consisting of 1-3 syllables. The word list is created by Tiit-Rein Viitso. The test words were embedded in a carrier sentence occurring once in the phrase-final position and once in the sentece final position. Recordings from 28 speakers. \n\nThe data was used for Aasm\u00e4e, N., Lippus, P., Pajusalu, K., Salveste, N., Zirnask, T., & Viitso, T.-R. (2013). Moksha prosody. Helsinki: Suomalais-Ugrilainen Seura. Retrieved from http://www.sgr.fi/sust/sust268/sust268.pdf",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d725ff24-c3f6-583a-be9d-02757785b289",
-    "notes": [
-        "Abstract",
-        "95 loetud lausest koosnev andmestik, iga lause sisaldab kaks 1-3-silbilist tests\u00f5na. Salvestused kokku 28 keelejuhilt. Materjali kasutati raamatus: Aasm\u00e4e, N., Lippus, P., Pajusalu, K., Salveste, N., Zirnask, T., & Viitso, T.-R. (2013). Moksha prosody. Helsinki: Suomalais-Ugrilainen Seura. Retrieved from http://www.sgr.fi/sust/sust268/sust268.pdf",
-        "Abstract",
-        "The data consists of 95 test words consisting of 1-3 syllables. The word list is created by Tiit-Rein Viitso. The test words were embedded in a carrier sentence occurring once in the phrase-final position and once in the sentece final position. Recordings from 28 speakers. \n\nThe data was used for Aasm\u00e4e, N., Lippus, P., Pajusalu, K., Salveste, N., Zirnask, T., & Viitso, T.-R. (2013). Moksha prosody. Helsinki: Suomalais-Ugrilainen Seura. Retrieved from http://www.sgr.fi/sust/sust268/sust268.pdf"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14186193"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Mok\u0161a prosoodia korpus",
-        "Moksha prosody corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d7b76f44-d3f9-5ace-b8d1-ae7856deca4e.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d7b76f44-d3f9-5ace-b8d1-ae7856deca4e.json
deleted file mode 100644
index df21906c..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d7b76f44-d3f9-5ace-b8d1-ae7856deca4e.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05927L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:8922511",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:8922511"
-    ],
-    "PublicationTimestamp": "2017-02-16T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "P\u00e4ll, Peeter"
-    ],
-    "fulltext": "oai:oai.datacite.org:8922511;2019-04-06T05:31:40Z;ESTDOI;ESTDOI.KEEL;Eesti Keele Instituudi kohanimeandmebaas (KNAB);The Place Name Database of the Institute of the Estonian language (KNAB);P\u00e4ll, Peeter;Center of Estonian Language Resources;2015;Issued: 2015-05-06;Updated: 2017-02-16;doi:10.15155/3-00-0000-0000-0000-05927L;Abstract;Sisaldab Eesti ja maailma kohanimesid.;Abstract;Place names from Estonia and the world over.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d7b76f44-d3f9-5ace-b8d1-ae7856deca4e",
-    "notes": [
-        "Abstract",
-        "Sisaldab Eesti ja maailma kohanimesid.",
-        "Abstract",
-        "Place names from Estonia and the world over."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:8922511"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti Keele Instituudi kohanimeandmebaas (KNAB)",
-        "The Place Name Database of the Institute of the Estonian language (KNAB)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d7b8b3bb-5eea-59e4-8fb3-ff233b2be692.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d7b8b3bb-5eea-59e4-8fb3-ff233b2be692.json
deleted file mode 100644
index b1ac1728..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d7b8b3bb-5eea-59e4-8fb3-ff233b2be692.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-07BDAL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:19520873",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:19520873"
-    ],
-    "PublicationTimestamp": "2019-02-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Soon, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:19520873;2019-04-05T10:36:51Z;ESTDOI;ESTDOI.KEEL;Esterm v20190101;Esterm v20190101;Soon, Tiina;Center of Estonian Language Resources;2019;Issued: 2019-02-07;Updated: 2019-02-07;doi:10.15155/3-00-0000-0000-0000-07BDAL;Abstract;Esterm on Eesti Keele Instituudi mitmekeelne terminibaas, mis sisaldab peamiselt Euroopa Liidu ja Eesti Vabariigi \u00f5igusaktide termineid. Terminibaas koondab \u00fcle 50 valdkonna terminoloogiat.;Abstract;Esterm is a multilingual termbase which includes terms mainly from the legal acts of the Republic of Estonia and the European Union. The termbase contains terminology from more than 50 domains.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d7b8b3bb-5eea-59e4-8fb3-ff233b2be692",
-    "notes": [
-        "Abstract",
-        "Esterm on Eesti Keele Instituudi mitmekeelne terminibaas, mis sisaldab peamiselt Euroopa Liidu ja Eesti Vabariigi \u00f5igusaktide termineid. Terminibaas koondab \u00fcle 50 valdkonna terminoloogiat.",
-        "Abstract",
-        "Esterm is a multilingual termbase which includes terms mainly from the legal acts of the Republic of Estonia and the European Union. The termbase contains terminology from more than 50 domains."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:19520873"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Esterm v20190101",
-        "Esterm v20190101"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d7ea0482-e240-5c10-8a3d-0c42b7c445f6.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d7ea0482-e240-5c10-8a3d-0c42b7c445f6.json
deleted file mode 100644
index a62c7423..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d7ea0482-e240-5c10-8a3d-0c42b7c445f6.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-064DEL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10344234",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10344234"
-    ],
-    "PublicationTimestamp": "2017-02-07T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek",
-        "Vare, Silvi"
-    ],
-    "fulltext": "oai:oai.datacite.org:10344234;2019-02-23T06:31:27Z;ESTDOI;ESTDOI.KEEL;Eesti keele s\u00f5napered - indeks;Hein, Indrek;Vare, Silvi;Center of Estonian Language Resources;2017;Issued: 2017-02-07;Updated: 2017-02-07;doi:10.15155/3-00-0000-0000-0000-064DEL;Abstract;Indeks v\u00f5imaldab teada saada, kas otsitav s\u00f5na esineb s\u00f5naperede raamatus ning millis(t)es s\u00f5napere(de)s ja millises plokis ta t\u00e4psemalt asub. Otsida on v\u00f5imalik nii elektroonilise indeksi kaudu p\u00e4ringuaknas kui ka pereliikmete loenditest pdf-formaadis. Vajadusel on v\u00f5imalik s\u00f5na olemasolu kontrollida ka perepeade pdf-loendist.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d7ea0482-e240-5c10-8a3d-0c42b7c445f6",
-    "notes": [
-        "Abstract",
-        "Indeks v\u00f5imaldab teada saada, kas otsitav s\u00f5na esineb s\u00f5naperede raamatus ning millis(t)es s\u00f5napere(de)s ja millises plokis ta t\u00e4psemalt asub. Otsida on v\u00f5imalik nii elektroonilise indeksi kaudu p\u00e4ringuaknas kui ka pereliikmete loenditest pdf-formaadis. Vajadusel on v\u00f5imalik s\u00f5na olemasolu kontrollida ka perepeade pdf-loendist."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10344234"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele s\u00f5napered - indeks"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d828a750-3451-51e0-8a62-8e7a29ce4b29.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d828a750-3451-51e0-8a62-8e7a29ce4b29.json
deleted file mode 100644
index 926c9941..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d828a750-3451-51e0-8a62-8e7a29ce4b29.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-0421BL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:6915504",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:6915504"
-    ],
-    "PublicationTimestamp": "2017-03-03T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Piits, Liisi"
-    ],
-    "fulltext": "oai:oai.datacite.org:6915504;2019-04-21T12:31:28Z;ESTDOI;ESTDOI.KEEL;K\u00f5nes\u00fcnteesi k\u00f5nekorpus Eva;Speech Corpus Eva for Speech Synthesis;Piits, Liisi;Center of Estonian Language Resources;2015;Issued: 2015-10-28;Updated: 2017-03-03;doi:10.15155/3-00-0000-0000-0000-0421BL;Abstract;Tulemust on kasutatud eestikeelsete s\u00fcnteesh\u00e4\u00e4lte loomiseks, korpus on k\u00f5nes\u00fcnteesi akustiliseks baasiks.;Abstract;This is an acoustic basis for speech synthesis, which has been used to create Estonian synthetic voices.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d828a750-3451-51e0-8a62-8e7a29ce4b29",
-    "notes": [
-        "Abstract",
-        "Tulemust on kasutatud eestikeelsete s\u00fcnteesh\u00e4\u00e4lte loomiseks, korpus on k\u00f5nes\u00fcnteesi akustiliseks baasiks.",
-        "Abstract",
-        "This is an acoustic basis for speech synthesis, which has been used to create Estonian synthetic voices."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:6915504"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "K\u00f5nes\u00fcnteesi k\u00f5nekorpus Eva",
-        "Speech Corpus Eva for Speech Synthesis"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d956a25e-50ea-5d4a-a13a-8f5f25167a3e.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d956a25e-50ea-5d4a-a13a-8f5f25167a3e.json
deleted file mode 100644
index e8d82756..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d956a25e-50ea-5d4a-a13a-8f5f25167a3e.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-079D4L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17926654",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17926654"
-    ],
-    "PublicationTimestamp": "2018-12-27T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Pajupuu, Hille"
-    ],
-    "fulltext": "oai:oai.datacite.org:17926654;2019-02-07T18:37:48Z;ESTDOI;ESTDOI.KEEL;Valence;Pajupuu, Hille;Center of Estonian Language Resources;2018;Issued: 2018-12-22;Updated: 2018-12-27;doi:10.15155/3-00-0000-0000-0000-079D4L;Abstract;This is a program classifying an Estonian text as positive, neutral or negative. It is running on server http://peeter.eki.ee:5000/valence\n\nThis code is optimized for server environment but can be run also as a standalone program:\n\npython valencecolor.py textfile.txt\nThis will produce a file textfile.txt.html where all emotionally relevant word are marked with CSS style. The limitation is that it does not print out the summary information. As a prerequisite the NLTK must be installed on the computer.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d956a25e-50ea-5d4a-a13a-8f5f25167a3e",
-    "notes": [
-        "Abstract",
-        "This is a program classifying an Estonian text as positive, neutral or negative. It is running on server http://peeter.eki.ee:5000/valence\n\nThis code is optimized for server environment but can be run also as a standalone program:\n\npython valencecolor.py textfile.txt\nThis will produce a file textfile.txt.html where all emotionally relevant word are marked with CSS style. The limitation is that it does not print out the summary information. As a prerequisite the NLTK must be installed on the computer."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17926654"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Valence"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d979b11c-934a-5024-b706-631a43fe167d.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d979b11c-934a-5024-b706-631a43fe167d.json
deleted file mode 100644
index 627d0271..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d979b11c-934a-5024-b706-631a43fe167d.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-00175L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:18511715",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:18511715"
-    ],
-    "PublicationTimestamp": "2019-03-18T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Krum, Margit"
-    ],
-    "fulltext": "oai:oai.datacite.org:18511715;2019-04-01T11:31:06Z;ESTDOI;ESTDOI.KEEL;Tilde masint\u00f5lge;Krum, Margit;Center of Estonian Language Resources;2019;Issued: 2019-03-18;Updated: 2019-03-18;doi:10.15155/9-00-0000-0000-0000-00175L;Abstract;L\u00f5ppkasutajatele on lihtsalt ja tasuta k\u00e4ttesaadavad (veebilehitseja kaudu http://www.masint\u00f5lge.ee ja http://www.masintolge.ee) parima kvaliteediga masint\u00f5lkeprogrammid eesti keelest kultuuriliselt, majanduslikult olulistesse keeltesse (inglise, vene, soome, saksa, prantsuse) ja tagasi eesti keelde.;Abstract;Machine translation by Tilde",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d979b11c-934a-5024-b706-631a43fe167d",
-    "notes": [
-        "Abstract",
-        "L\u00f5ppkasutajatele on lihtsalt ja tasuta k\u00e4ttesaadavad (veebilehitseja kaudu http://www.masint\u00f5lge.ee ja http://www.masintolge.ee) parima kvaliteediga masint\u00f5lkeprogrammid eesti keelest kultuuriliselt, majanduslikult olulistesse keeltesse (inglise, vene, soome, saksa, prantsuse) ja tagasi eesti keelde.",
-        "Abstract",
-        "Machine translation by Tilde"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:18511715"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Tilde masint\u00f5lge"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d9a590dc-3c38-55a4-8d7d-3c7f2002c9fa.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d9a590dc-3c38-55a4-8d7d-3c7f2002c9fa.json
deleted file mode 100644
index e08d8e02..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/d9a590dc-3c38-55a4-8d7d-3c7f2002c9fa.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-0633DL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10304100",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10304100"
-    ],
-    "PublicationTimestamp": "2017-01-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laansalu, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:10304100;2019-04-06T23:33:07Z;ESTDOI;ESTDOI.KEEL;Maailma maade nimed\n;Laansalu, Tiina;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2017-01-31;doi:10.15155/3-00-0000-0000-0000-0633DL;Abstract;Loendi aluseks on Emakeele Seltsi keeletoimkonna poolt 1996. aastal l\u00e4bi arutatud v\u00e4liskohanimede (sh riiginimede) kirjapilt keelekorralduss\u00f5naraamatu kohanimelisas. Loendit on hiljem pidevalt t\u00e4psustatud ja ajakohastatud. Loend on \u00fchtlustatud standardis ISO 3166-1 antud valikuga.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "d9a590dc-3c38-55a4-8d7d-3c7f2002c9fa",
-    "notes": [
-        "Abstract",
-        "Loendi aluseks on Emakeele Seltsi keeletoimkonna poolt 1996. aastal l\u00e4bi arutatud v\u00e4liskohanimede (sh riiginimede) kirjapilt keelekorralduss\u00f5naraamatu kohanimelisas. Loendit on hiljem pidevalt t\u00e4psustatud ja ajakohastatud. Loend on \u00fchtlustatud standardis ISO 3166-1 antud valikuga."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10304100"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Maailma maade nimed\n"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/daab472e-68db-5ff6-8cf9-8d537e44f891.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/daab472e-68db-5ff6-8cf9-8d537e44f891.json
deleted file mode 100644
index 33c0d952..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/daab472e-68db-5ff6-8cf9-8d537e44f891.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-001A0L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17986402",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17986402"
-    ],
-    "PublicationTimestamp": "2019-01-11T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Iva, Sulev"
-    ],
-    "fulltext": "oai:oai.datacite.org:17986402;2019-04-17T17:27:36Z;ESTDOI;ESTDOI.KEEL;V\u00f5ru - eesti paralleelkorpus;Iva, Sulev;Center of Estonian Language Resources;2019;Issued: 2019-01-11;Updated: 2019-01-11;doi:10.15155/1-00-0000-0000-0000-001A0L;Abstract;Paralleelkorpuse tekstid on\n\trida-realt k\u00e4sitsi joondatud,\n\tiga terviktekst eraldi failis,\n\tiga keelefaili keel j\u00e4rjekorranumbri taga punktiga eraldatult,\n\t\u00fche keele liit- ja teise lihtlause puhul m\u00f5lema keele laused \u00fchel real,\n\tt\u00f5lke puudumisel rida #-ga v\u00e4lja kommenteeritult j\u00e4ttes paralleelfaili t\u00fchja #-ga algava reaga,\n\tutf8 vormingus.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "daab472e-68db-5ff6-8cf9-8d537e44f891",
-    "notes": [
-        "Abstract",
-        "Paralleelkorpuse tekstid on\n\trida-realt k\u00e4sitsi joondatud,\n\tiga terviktekst eraldi failis,\n\tiga keelefaili keel j\u00e4rjekorranumbri taga punktiga eraldatult,\n\t\u00fche keele liit- ja teise lihtlause puhul m\u00f5lema keele laused \u00fchel real,\n\tt\u00f5lke puudumisel rida #-ga v\u00e4lja kommenteeritult j\u00e4ttes paralleelfaili t\u00fchja #-ga algava reaga,\n\tutf8 vormingus."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17986402"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "V\u00f5ru - eesti paralleelkorpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/dad04541-5502-5856-a2a7-70fbf43168e5.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/dad04541-5502-5856-a2a7-70fbf43168e5.json
deleted file mode 100644
index 949ad7b5..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/dad04541-5502-5856-a2a7-70fbf43168e5.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05B5BL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9352886",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9352886"
-    ],
-    "PublicationTimestamp": "2017-05-09T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Kallas, Jelena",
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:9352886;2019-02-15T18:37:50Z;ESTDOI;ESTDOI.KEEL;Vene-eesti s\u00f5naraamat;The Russian-Estonian Dictionary;\u0420\u0443\u0441\u0441\u043a\u043e-\u044d\u0441\u0442\u043e\u043d\u0441\u043a\u0438\u0439 \u0441\u043b\u043e\u0432\u0430\u0440\u044c;Hein, Indrek;Kallas, Jelena;Center of Estonian Language Resources;2016;Issued: 2016-10-19;Updated: 2017-05-09;doi:10.15155/3-00-0000-0000-0000-05B5BL;Abstract;1984\u20131994 ilmunud 4-k\u00f6itelise \u201eVene-eesti s\u00f5naraamatu\u201c parandatud versioon. Sisaldab \u00fcldkeele k\u00f5rval hulganisti oskuss\u00f5navara ja fraseoloogiat.;Abstract;The entry list of the dictionary contains ca 74,000 words. Most of the entries include a number of typical word combinations for the entry word, which illustrate its semantic nuances and present the user with the most widespread uses of the word in a ready-made form.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dad04541-5502-5856-a2a7-70fbf43168e5",
-    "notes": [
-        "Abstract",
-        "1984\u20131994 ilmunud 4-k\u00f6itelise \u201eVene-eesti s\u00f5naraamatu\u201c parandatud versioon. Sisaldab \u00fcldkeele k\u00f5rval hulganisti oskuss\u00f5navara ja fraseoloogiat.",
-        "Abstract",
-        "The entry list of the dictionary contains ca 74,000 words. Most of the entries include a number of typical word combinations for the entry word, which illustrate its semantic nuances and present the user with the most widespread uses of the word in a ready-made form."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9352886"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Vene-eesti s\u00f5naraamat",
-        "The Russian-Estonian Dictionary",
-        "\u0420\u0443\u0441\u0441\u043a\u043e-\u044d\u0441\u0442\u043e\u043d\u0441\u043a\u0438\u0439 \u0441\u043b\u043e\u0432\u0430\u0440\u044c"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/db64f6e6-967e-56f2-93d1-dff7c307c24e.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/db64f6e6-967e-56f2-93d1-dff7c307c24e.json
deleted file mode 100644
index 4b8b8d5c..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/db64f6e6-967e-56f2-93d1-dff7c307c24e.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-0009DL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17958875",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17958875"
-    ],
-    "PublicationTimestamp": "2018-10-10T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laak, Marin",
-        "Saluvere, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:17958875;2019-01-07T09:09:23Z;ESTDOI;ESTDOI.KEEL;Kirjandusajalooline veebikeskkond \"ERNI. Eesti kirjanduslugu tekstides 1924 \u2013 1925\";Web-environment \"ERNI: Estonian Literary History in Texts 1924\u20131925\u201d;Laak, Marin;Saluvere, Tiina;Center of Estonian Language Resources;2018;Issued: 2018-10-10;Updated: 2018-10-10;doi:10.15155/9-00-0000-0000-0000-0009DL;Abstract;ERNI on kirjandusloo \u00f5ppeprogramm, mis esitab materjale 1920. aastate kirjanduselu kohta. ERNI kujutab \u00fcht kirjandusloo peat\u00fckki, eesti kirjanduse 1920. aastaid interaktiivses keskkonnas, tervikliku kirjandusajaloolise ruumina. ERNI sisaldab raamatukogu, kriitikaantoloogiat, fotogaleriid, autorite tutvustusi, kirjanduslike terminite s\u00f5nastikku ja ajatelge. G\u00fcmnaasiumi kirjandustundideks leiab abi k\u00fcsimustikust ja kirjandi\u00f5petusest. Kriitika ajaloo kursust k\u00f5rgkoolis saab elavdada kasutades programmi intertekstuaalse ja retseptsiooniajaloolise tekstide koguna.\n\nERNIs leiduvad tr\u00fckimaterjalid p\u00e4rinevad Eesti Kirjandusmuuseumi Arhiivraamatukogust, kirjanike fotod Kultuuriloolise Arhiivi fotokogust (Vanemuise 42, Tartu). Raamatute kujundused on v\u00f5etud kirjanik Friedebert Tuglasele kuulunud raamatutest, mis asuvad Underi ja Tuglase Kirjanduskeskuse muuseumiosakonnas (V\u00e4ikese-Illimari 12, Tallinn). K\u00f5ik materjalid abimen\u00fc\u00fcdes on koostatud t\u00f6\u00f6r\u00fchma poolt.\n\nProjekti teostamisele eelnenud allikmaterjalide l\u00e4bit\u00f6\u00f6tamine ja uurimine on toimunud Underi ja Tuglase Kirjanduskeskuse Eesti Teadusfondi grantide \"Eesti kirjanduskriitilise m\u00f5tte areng\" I ja II t\u00e4itmise k\u00e4igus (1993\u20131998). \u00d5ppematerjalid on ettevalmistatud Hugo Treffneri G\u00fcmnaasiumi kirjandustundides.\n\nProjekti on teostatud Eesti Kirjandusmuuseumis (1997\u20131998, 2000\u20132001). ERNI on terviklik elektrooniline teos. K\u00f5ik detailid, lehek\u00fcljed ja ka seosed tekstide vahel on sisuliselt p\u00f5hjendatud. Antud ajaloolisele perioodile, eksperimentaalsele 1920. aastate I poolele eriomast atmosf\u00e4\u00e4ri toetab ka kujunduskontseptsioon.\n\n\u00a9 Eesti Kirjandusmuuseum, 2001\n\nProjektijuht, idee autor: Marin Laak\nKujunduskontseptsioon, teostus: Virve Sarapik\n\u00d5ppematerjalide autor: Helgi Tering\n\u00dcldtoimetaja: Piret Viires\n\nT\u00f6\u00f6grupp:\nTiina Saluvere (ajatelg, fotod), Toomas Muru (eesti autorid, v\u00e4lispersonaalia, terminid), Virve Sarapik (fotod, raamatute kujundused, graafika), Marin Laak (eesti autorid, raamatukogu, kriitika), Alo Paistik (teostus), Kristi Metste, Kristina Pai, Katrin Raid (korrektuur), Joel Ilja (arvutiladu) ja Indrek Hein (otsimootor).\nKonsultandid: Rutt Hinrikus, Sirje Olesk, Janika Kronberg ja Enn Lillemets\n\nP\u00f5hiteostaja: \u00dclo Treikelder\n\n\nERNI on k\u00e4ttesaadav:\n\u00b7 Internetis Eesti Kirjandusmuuseumi kodulehek\u00fcljelt http://galerii.kirmus.ee/erni/erni.html\n\u00b7 CD-ROMil \"ERNI. Eesti kirjanduslugu tekstides 1924-1925\" Tiigrih\u00fcppe \u00f5ppematerjalide sarjas (2002)\n\nISBN 9985-9170-7-3",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "db64f6e6-967e-56f2-93d1-dff7c307c24e",
-    "notes": [
-        "Abstract",
-        "ERNI on kirjandusloo \u00f5ppeprogramm, mis esitab materjale 1920. aastate kirjanduselu kohta. ERNI kujutab \u00fcht kirjandusloo peat\u00fckki, eesti kirjanduse 1920. aastaid interaktiivses keskkonnas, tervikliku kirjandusajaloolise ruumina. ERNI sisaldab raamatukogu, kriitikaantoloogiat, fotogaleriid, autorite tutvustusi, kirjanduslike terminite s\u00f5nastikku ja ajatelge. G\u00fcmnaasiumi kirjandustundideks leiab abi k\u00fcsimustikust ja kirjandi\u00f5petusest. Kriitika ajaloo kursust k\u00f5rgkoolis saab elavdada kasutades programmi intertekstuaalse ja retseptsiooniajaloolise tekstide koguna.\n\nERNIs leiduvad tr\u00fckimaterjalid p\u00e4rinevad Eesti Kirjandusmuuseumi Arhiivraamatukogust, kirjanike fotod Kultuuriloolise Arhiivi fotokogust (Vanemuise 42, Tartu). Raamatute kujundused on v\u00f5etud kirjanik Friedebert Tuglasele kuulunud raamatutest, mis asuvad Underi ja Tuglase Kirjanduskeskuse muuseumiosakonnas (V\u00e4ikese-Illimari 12, Tallinn). K\u00f5ik materjalid abimen\u00fc\u00fcdes on koostatud t\u00f6\u00f6r\u00fchma poolt.\n\nProjekti teostamisele eelnenud allikmaterjalide l\u00e4bit\u00f6\u00f6tamine ja uurimine on toimunud Underi ja Tuglase Kirjanduskeskuse Eesti Teadusfondi grantide \"Eesti kirjanduskriitilise m\u00f5tte areng\" I ja II t\u00e4itmise k\u00e4igus (1993\u20131998). \u00d5ppematerjalid on ettevalmistatud Hugo Treffneri G\u00fcmnaasiumi kirjandustundides.\n\nProjekti on teostatud Eesti Kirjandusmuuseumis (1997\u20131998, 2000\u20132001). ERNI on terviklik elektrooniline teos. K\u00f5ik detailid, lehek\u00fcljed ja ka seosed tekstide vahel on sisuliselt p\u00f5hjendatud. Antud ajaloolisele perioodile, eksperimentaalsele 1920. aastate I poolele eriomast atmosf\u00e4\u00e4ri toetab ka kujunduskontseptsioon.\n\n\u00a9 Eesti Kirjandusmuuseum, 2001\n\nProjektijuht, idee autor: Marin Laak\nKujunduskontseptsioon, teostus: Virve Sarapik\n\u00d5ppematerjalide autor: Helgi Tering\n\u00dcldtoimetaja: Piret Viires\n\nT\u00f6\u00f6grupp:\nTiina Saluvere (ajatelg, fotod), Toomas Muru (eesti autorid, v\u00e4lispersonaalia, terminid), Virve Sarapik (fotod, raamatute kujundused, graafika), Marin Laak (eesti autorid, raamatukogu, kriitika), Alo Paistik (teostus), Kristi Metste, Kristina Pai, Katrin Raid (korrektuur), Joel Ilja (arvutiladu) ja Indrek Hein (otsimootor).\nKonsultandid: Rutt Hinrikus, Sirje Olesk, Janika Kronberg ja Enn Lillemets\n\nP\u00f5hiteostaja: \u00dclo Treikelder\n\n\nERNI on k\u00e4ttesaadav:\n\u00b7 Internetis Eesti Kirjandusmuuseumi kodulehek\u00fcljelt http://galerii.kirmus.ee/erni/erni.html\n\u00b7 CD-ROMil \"ERNI. Eesti kirjanduslugu tekstides 1924-1925\" Tiigrih\u00fcppe \u00f5ppematerjalide sarjas (2002)\n\nISBN 9985-9170-7-3"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17958875"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Kirjandusajalooline veebikeskkond \"ERNI. Eesti kirjanduslugu tekstides 1924 \u2013 1925\"",
-        "Web-environment \"ERNI: Estonian Literary History in Texts 1924\u20131925\u201d"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/dbc0c9e4-ee0c-551c-bc51-d546ce8c8cdd.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/dbc0c9e4-ee0c-551c-bc51-d546ce8c8cdd.json
deleted file mode 100644
index e90842e9..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/dbc0c9e4-ee0c-551c-bc51-d546ce8c8cdd.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00088L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:6334552",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:6334552"
-    ],
-    "PublicationTimestamp": "2015-06-18T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:6334552;2019-02-02T15:31:46Z;ESTDOI;ESTDOI.KEEL;Eesti keele puudepank;Muischnek, Kadri;Center of Estonian Language Resources;2015;Issued: 2015-06-18;Updated: 2015-06-18;doi:10.15155/1-00-0000-0000-0000-00088L;Abstract;Morfoloogiliselt ja s\u00f5ltuvuss\u00fcntaktiliselt anal\u00fc\u00fcsitud eestikeelsed tekstid, kokku umbes 400 000 s\u00f5na 30 000 lauses. Tekstid on p\u00e4rit eesti keele Tasakaalus korpusest http://www.cl.ut.ee/korpused/grammatikakorpus/ ja Koondkorpusest http://www.cl.ut.ee/korpused/segakorpus/ ning jagunevad ilukirjanduse, ajakirjanduse, teaduse ja populaarteaduse tekstiklasside vahel. Tekstid on esmalt anal\u00fc\u00fcsitud reeglip\u00f5hise, kitsenduste grammatikal p\u00f5hineva s\u00f5ltuvuss\u00fcntaktilise anal\u00fcsaatoriga; automaatselt anal\u00fc\u00fcsitud faile on parandatud k\u00e4sitsi.\nPublikatsioon: Muischnek, Kadri; M\u00fc\u00fcrisep, Kaili; Puolakainen Tiina (2014). Dependency Parsing of Estonian : Statistical and Rule - based Approaches Human Language Technologies - The Baltic Perspective. Frontiers in Artificial Intelligence and Applications Vol 268. IOS Press, Amsterdam, pp. 111-118. \"",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dbc0c9e4-ee0c-551c-bc51-d546ce8c8cdd",
-    "notes": [
-        "Abstract",
-        "Morfoloogiliselt ja s\u00f5ltuvuss\u00fcntaktiliselt anal\u00fc\u00fcsitud eestikeelsed tekstid, kokku umbes 400 000 s\u00f5na 30 000 lauses. Tekstid on p\u00e4rit eesti keele Tasakaalus korpusest http://www.cl.ut.ee/korpused/grammatikakorpus/ ja Koondkorpusest http://www.cl.ut.ee/korpused/segakorpus/ ning jagunevad ilukirjanduse, ajakirjanduse, teaduse ja populaarteaduse tekstiklasside vahel. Tekstid on esmalt anal\u00fc\u00fcsitud reeglip\u00f5hise, kitsenduste grammatikal p\u00f5hineva s\u00f5ltuvuss\u00fcntaktilise anal\u00fcsaatoriga; automaatselt anal\u00fc\u00fcsitud faile on parandatud k\u00e4sitsi.\nPublikatsioon: Muischnek, Kadri; M\u00fc\u00fcrisep, Kaili; Puolakainen Tiina (2014). Dependency Parsing of Estonian : Statistical and Rule - based Approaches Human Language Technologies - The Baltic Perspective. Frontiers in Artificial Intelligence and Applications Vol 268. IOS Press, Amsterdam, pp. 111-118. \""
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:6334552"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele puudepank"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/dc85558b-1c19-56f7-9c2b-ff0d84769699.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/dc85558b-1c19-56f7-9c2b-ff0d84769699.json
deleted file mode 100644
index f036955b..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/dc85558b-1c19-56f7-9c2b-ff0d84769699.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05B58L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9352883",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9352883"
-    ],
-    "PublicationTimestamp": "2016-10-26T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Viks, \u00dclle"
-    ],
-    "fulltext": "oai:oai.datacite.org:9352883;2019-03-04T20:31:32Z;ESTDOI;ESTDOI.KEEL;Norra-eesti s\u00f5naraamat;Norwegian-Estonian Dictionary;Viks, \u00dclle;Center of Estonian Language Resources;2016;Issued: 2016-10-26;Updated: 2016-10-26;doi:10.15155/3-00-0000-0000-0000-05B58L;Abstract;Sisaldab u 19 000 eesti ja 21 000 norra m\u00e4rks\u00f5na, millele on lisatud grammatilised andmed ja hulgaliselt n\u00e4iteid s\u00f5nade kasutamise kohta. Raamatus on ka l\u00fchi\u00fclevaated eesti ja norra keelest.\n\nTurid Farbregd, Sigrid Kangur, \u00dclle Viks. Norra-eesti : eesti-norra s\u00f5naraamat. Eesti Keele Sihtasutus. Tallinn 1998, 2. tr\u00fckk 2005 (3. tr\u00fckk ilmub 2013).\n\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dc85558b-1c19-56f7-9c2b-ff0d84769699",
-    "notes": [
-        "Abstract",
-        "Sisaldab u 19 000 eesti ja 21 000 norra m\u00e4rks\u00f5na, millele on lisatud grammatilised andmed ja hulgaliselt n\u00e4iteid s\u00f5nade kasutamise kohta. Raamatus on ka l\u00fchi\u00fclevaated eesti ja norra keelest.\n\nTurid Farbregd, Sigrid Kangur, \u00dclle Viks. Norra-eesti : eesti-norra s\u00f5naraamat. Eesti Keele Sihtasutus. Tallinn 1998, 2. tr\u00fckk 2005 (3. tr\u00fckk ilmub 2013).\n\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9352883"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Norra-eesti s\u00f5naraamat",
-        "Norwegian-Estonian Dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/dc9da84c-ec9d-5fef-a28a-fe10bedb382c.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/dc9da84c-ec9d-5fef-a28a-fe10bedb382c.json
deleted file mode 100644
index 78aa0cce..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/dc9da84c-ec9d-5fef-a28a-fe10bedb382c.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00166L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17732800",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17732800"
-    ],
-    "PublicationTimestamp": "2018-12-07T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Barbu, Eduard"
-    ],
-    "fulltext": "oai:oai.datacite.org:17732800;2019-04-17T17:27:15Z;ESTDOI;ESTDOI.KEEL;Taxonomy Extracted from Estonian Wikipedia Text 1.0;Barbu, Eduard;Center of Estonian Language Resources;2018;Issued: 2018-11-27;Updated: 2018-12-07;doi:10.15155/1-00-0000-0000-0000-00166L;Abstract;The taxonomy is in an xml file and it has a structure compose of elements called \u201cdoc\"",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dc9da84c-ec9d-5fef-a28a-fe10bedb382c",
-    "notes": [
-        "Abstract",
-        "The taxonomy is in an xml file and it has a structure compose of elements called \u201cdoc\""
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17732800"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Taxonomy Extracted from Estonian Wikipedia Text 1.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/dca6de37-6d13-55c5-ac3b-59bf630185a0.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/dca6de37-6d13-55c5-ac3b-59bf630185a0.json
deleted file mode 100644
index d5a95269..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/dca6de37-6d13-55c5-ac3b-59bf630185a0.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-079DBL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17960240",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17960240"
-    ],
-    "PublicationTimestamp": "2019-01-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:17960240;2019-04-15T19:37:03Z;ESTDOI;ESTDOI.KEEL;Tekstide helindaja;Hein, Indrek;Center of Estonian Language Resources;2019;Issued: 2019-01-07;Updated: 2019-01-07;doi:10.15155/3-00-0000-0000-0000-079DBL;Abstract;Heliraamatute genereerija Vox Populi, mis kasutab EKI k\u00f5nes\u00fcnteesi ja h\u00e4\u00e4ldusbaasi, et pikemaid tekste helindada.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dca6de37-6d13-55c5-ac3b-59bf630185a0",
-    "notes": [
-        "Abstract",
-        "Heliraamatute genereerija Vox Populi, mis kasutab EKI k\u00f5nes\u00fcnteesi ja h\u00e4\u00e4ldusbaasi, et pikemaid tekste helindada."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17960240"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Tekstide helindaja"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/dd3bbc89-a48b-5bf2-90f5-22fc3e380135.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/dd3bbc89-a48b-5bf2-90f5-22fc3e380135.json
deleted file mode 100644
index 51ffe6dc..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/dd3bbc89-a48b-5bf2-90f5-22fc3e380135.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00149L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:13909256",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:13909256"
-    ],
-    "PublicationTimestamp": "2018-01-24T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Lippus, P\u00e4rtel"
-    ],
-    "fulltext": "oai:oai.datacite.org:13909256;2019-04-20T07:01:00Z;ESTDOI;ESTDOI.KEEL;Ersa prosoodia korpus;Erzya prosody corpus;Lippus, P\u00e4rtel;Center of Estonian Language Resources;2018;Issued: 2018-01-24;Updated: 2018-01-24;doi:10.15155/1-00-0000-0000-0000-00149L;Abstract;Ersa s\u00f5naprosoodia uurimiseks kogutud andmestik. Sisaldab raamlauses loetud tests\u00f5nu 8 keelejuhilt. Iga keelejuht luges 100 lauset, iga lause sisaldas tests\u00f5na kord lause keskel, kord lause l\u00f5pus. Vt l\u00e4hemalt:\nLehiste, I., Aasm\u00e4e, N., Meister, E., Pajusalu, K., Teras, P., & Viitso, T.-R. (2003). Erzya prosody. Helsinki: Finno-Ugrian Society.;Abstract;The recordings collected for studying Erzya word prosody. 8 test subjects read 100 sentences. Each carrrier sentence contained a test word in phrase medial position and phrase final position. \nLehiste, I., Aasm\u00e4e, N., Meister, E., Pajusalu, K., Teras, P., & Viitso, T.-R. (2003). Erzya prosody. Helsinki: Finno-Ugrian Society.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dd3bbc89-a48b-5bf2-90f5-22fc3e380135",
-    "notes": [
-        "Abstract",
-        "Ersa s\u00f5naprosoodia uurimiseks kogutud andmestik. Sisaldab raamlauses loetud tests\u00f5nu 8 keelejuhilt. Iga keelejuht luges 100 lauset, iga lause sisaldas tests\u00f5na kord lause keskel, kord lause l\u00f5pus. Vt l\u00e4hemalt:\nLehiste, I., Aasm\u00e4e, N., Meister, E., Pajusalu, K., Teras, P., & Viitso, T.-R. (2003). Erzya prosody. Helsinki: Finno-Ugrian Society.",
-        "Abstract",
-        "The recordings collected for studying Erzya word prosody. 8 test subjects read 100 sentences. Each carrrier sentence contained a test word in phrase medial position and phrase final position. \nLehiste, I., Aasm\u00e4e, N., Meister, E., Pajusalu, K., Teras, P., & Viitso, T.-R. (2003). Erzya prosody. Helsinki: Finno-Ugrian Society."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:13909256"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Ersa prosoodia korpus",
-        "Erzya prosody corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/dd73151e-2738-5357-85a1-d070e43102fd.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/dd73151e-2738-5357-85a1-d070e43102fd.json
deleted file mode 100644
index e9f7dc72..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/dd73151e-2738-5357-85a1-d070e43102fd.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-00096L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17951389",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17951389"
-    ],
-    "PublicationTimestamp": "2019-01-04T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Meister, Einar"
-    ],
-    "fulltext": "oai:oai.datacite.org:17951389;2019-01-04T13:47:03Z;ESTDOI;ESTDOI.KEEL;Audiovisuaalse k\u00f5nes\u00fcnteesi rakendus Linuxile;Meister, Einar;Center of Estonian Language Resources;2019;Issued: 2019-01-04;Updated: 2019-01-04;doi:10.15155/9-00-0000-0000-0000-00096L;Abstract;\"K\u00f5me\u00f6eva pea\" protot\u00fc\u00fcp T\u00f5nu.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dd73151e-2738-5357-85a1-d070e43102fd",
-    "notes": [
-        "Abstract",
-        "\"K\u00f5me\u00f6eva pea\" protot\u00fc\u00fcp T\u00f5nu."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17951389"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Audiovisuaalse k\u00f5nes\u00fcnteesi rakendus Linuxile"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/dd88ab40-0d47-5286-88f1-d2952d5f9b13.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/dd88ab40-0d47-5286-88f1-d2952d5f9b13.json
deleted file mode 100644
index deca1360..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/dd88ab40-0d47-5286-88f1-d2952d5f9b13.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-0679AL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10996396",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10996396"
-    ],
-    "PublicationTimestamp": "2017-10-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "K\u00e4si, Inge"
-    ],
-    "fulltext": "oai:oai.datacite.org:10996396;2019-04-17T17:26:47Z;ESTDOI;ESTDOI.KEEL;Vanap\u00e4rase V\u00f5ru murde s\u00f5naraamat;The Dictionary of Old V\u00f5ru Dialect;K\u00e4si, Inge;Center of Estonian Language Resources;2017;Issued: 2017-05-10;Updated: 2017-10-31;doi:10.15155/3-00-0000-0000-0000-0679AL;Abstract;S\u00f5naraamatus kajastub arhailine V\u00f5ru murdekeel, mida k\u00f5neldi V\u00f5rumaa idaosas XIX sajandi teisel poolel ja XX sajandi esimesel poolel. S\u00f5naraamatus on ligi 10 000 m\u00e4rks\u00f5na. S\u00f5naraamat on koostatud murdekoguja ning -uurija Hella Keema peamiselt k\u00e4sikirjaliste kogude p\u00f5hjal. P\u00f5liste v\u00f5rumaalaste s\u00f5navara R\u00f5uge, Vastseliina ja Setumaa 35 k\u00fclast on kirja pandud aastatel 1963\u20131986.;Abstract;The dictionary reveals the archaic V\u00f5ru dialect, that was spoken in the eastern part of V\u00f5ru county in the second half of the 19th and in the first half of the 20th century. The dictionary contains approximately 10,000 entries with usage examples. The dictionary has been compiled mainly on the basis of manuscript collections, compiled by Hella Keem, a dialect collector and linguist specialist in the V\u00f5ru dialect. Everyday language spoken by the indigenous V\u00f5ru people from R\u00f5uge, Vastseliina, and Setomaa parishes has been noted down in the period 1963\u20131986.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dd88ab40-0d47-5286-88f1-d2952d5f9b13",
-    "notes": [
-        "Abstract",
-        "S\u00f5naraamatus kajastub arhailine V\u00f5ru murdekeel, mida k\u00f5neldi V\u00f5rumaa idaosas XIX sajandi teisel poolel ja XX sajandi esimesel poolel. S\u00f5naraamatus on ligi 10 000 m\u00e4rks\u00f5na. S\u00f5naraamat on koostatud murdekoguja ning -uurija Hella Keema peamiselt k\u00e4sikirjaliste kogude p\u00f5hjal. P\u00f5liste v\u00f5rumaalaste s\u00f5navara R\u00f5uge, Vastseliina ja Setumaa 35 k\u00fclast on kirja pandud aastatel 1963\u20131986.",
-        "Abstract",
-        "The dictionary reveals the archaic V\u00f5ru dialect, that was spoken in the eastern part of V\u00f5ru county in the second half of the 19th and in the first half of the 20th century. The dictionary contains approximately 10,000 entries with usage examples. The dictionary has been compiled mainly on the basis of manuscript collections, compiled by Hella Keem, a dialect collector and linguist specialist in the V\u00f5ru dialect. Everyday language spoken by the indigenous V\u00f5ru people from R\u00f5uge, Vastseliina, and Setomaa parishes has been noted down in the period 1963\u20131986."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10996396"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Vanap\u00e4rase V\u00f5ru murde s\u00f5naraamat",
-        "The Dictionary of Old V\u00f5ru Dialect"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/dd985d66-cad9-57fc-9c8b-14ad23350ae2.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/dd985d66-cad9-57fc-9c8b-14ad23350ae2.json
deleted file mode 100644
index 70613c14..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/dd985d66-cad9-57fc-9c8b-14ad23350ae2.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00198L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17979320",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17979320"
-    ],
-    "PublicationTimestamp": "2019-01-10T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laur, Sven"
-    ],
-    "fulltext": "oai:oai.datacite.org:17979320;2019-04-19T04:02:16Z;ESTDOI;ESTDOI.KEEL;Mallip\u00f5hine faktituletaja;Laur, Sven;Center of Estonian Language Resources;2019;Issued: 2019-01-10;Updated: 2019-01-10;doi:10.15155/1-00-0000-0000-0000-00198L;Abstract;Tarkvarakomponent suudab vabatekstidest \u00f5ppida erinevaid seoseid ning nende abil eraldada struktureeritud infot. Seosed v\u00f5ivad olla lihtsad nagu isikunimed ja organisatsioonid v\u00f5i keerulisemad nagu firmade peakontorite asukohad.\n\nMeetod vajab sisendiks korpust, milles on meid huvitav seos m\u00e4rgendatud. Seej\u00e4rel leitakse automaatselt sobivad mallid ja koostatakse mudel, mis antud seost v\u00f5imalikult h\u00e4sti tuvastaksid. Tulemusena saame m\u00e4rgendamata vabatekstidest leida uusi seosele vastavaid n\u00e4iteid.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "dd985d66-cad9-57fc-9c8b-14ad23350ae2",
-    "notes": [
-        "Abstract",
-        "Tarkvarakomponent suudab vabatekstidest \u00f5ppida erinevaid seoseid ning nende abil eraldada struktureeritud infot. Seosed v\u00f5ivad olla lihtsad nagu isikunimed ja organisatsioonid v\u00f5i keerulisemad nagu firmade peakontorite asukohad.\n\nMeetod vajab sisendiks korpust, milles on meid huvitav seos m\u00e4rgendatud. Seej\u00e4rel leitakse automaatselt sobivad mallid ja koostatakse mudel, mis antud seost v\u00f5imalikult h\u00e4sti tuvastaksid. Tulemusena saame m\u00e4rgendamata vabatekstidest leida uusi seosele vastavaid n\u00e4iteid."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17979320"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Mallip\u00f5hine faktituletaja"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/de51ef46-548b-527e-986e-fc858bdf4004.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/de51ef46-548b-527e-986e-fc858bdf4004.json
deleted file mode 100644
index 849b4ccf..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/de51ef46-548b-527e-986e-fc858bdf4004.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06348L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10304241",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10304241"
-    ],
-    "PublicationTimestamp": "2017-02-16T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Nurk, T\u00f5nis"
-    ],
-    "fulltext": "oai:oai.datacite.org:10304241;2018-08-11T17:35:24Z;ESTDOI;ESTDOI.KEEL;Terminibaaside s\u00fcsteem Termeki ;Terminology Management Software Termeki;Nurk, T\u00f5nis;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2017-02-16;doi:10.15155/3-00-0000-0000-0000-06348L;Abstract;Eesti Keele Instituudi tasuta pakutav tarkvara terminoloogia haldamiseks.;Abstract;Software for terminology management offered by the Institute of the Estonian Language free of charge.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "de51ef46-548b-527e-986e-fc858bdf4004",
-    "notes": [
-        "Abstract",
-        "Eesti Keele Instituudi tasuta pakutav tarkvara terminoloogia haldamiseks.",
-        "Abstract",
-        "Software for terminology management offered by the Institute of the Estonian Language free of charge."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10304241"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Terminibaaside s\u00fcsteem Termeki ",
-        "Terminology Management Software Termeki"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/df4e1bbc-291c-5fed-a581-cb9316afe419.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/df4e1bbc-291c-5fed-a581-cb9316afe419.json
deleted file mode 100644
index ad826d02..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/df4e1bbc-291c-5fed-a581-cb9316afe419.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0007BL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5757240",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5757240"
-    ],
-    "PublicationTimestamp": "2018-12-07T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:5757240;2019-04-06T18:01:40Z;ESTDOI;ESTDOI.KEEL;Segakorpus: Riigikogu;Corpus of the Proceedings of Estonian Parliament;Muischnek, Kadri;Center of Estonian Language Resources;2013;Issued: 2013-01-07;Updated: 2018-12-07;doi:10.15155/1-00-0000-0000-0000-0007BL;Abstract;Riigikogu korpus. TEI P5 XML m\u00e4rgendus, UTF8 kodeering.;Abstract;Corpus of the Proceedings of Estonian Parliament. Contains edited version of the Proceedings of Estonian Parliament from the years 1995-2001; 13 million words.\nMarkup: TEI P5 XML\nEncoding: UTF8",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "df4e1bbc-291c-5fed-a581-cb9316afe419",
-    "notes": [
-        "Abstract",
-        "Riigikogu korpus. TEI P5 XML m\u00e4rgendus, UTF8 kodeering.",
-        "Abstract",
-        "Corpus of the Proceedings of Estonian Parliament. Contains edited version of the Proceedings of Estonian Parliament from the years 1995-2001; 13 million words.\nMarkup: TEI P5 XML\nEncoding: UTF8"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5757240"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Segakorpus: Riigikogu",
-        "Corpus of the Proceedings of Estonian Parliament"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/df8da476-f516-5628-ba15-2390751068dc.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/df8da476-f516-5628-ba15-2390751068dc.json
deleted file mode 100644
index cf290e5f..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/df8da476-f516-5628-ba15-2390751068dc.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/TY.0007",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:4597355",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:4597355"
-    ],
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Lindstr\u00f6m, Liina"
-    ],
-    "fulltext": "oai:oai.datacite.org:4597355;2019-01-30T22:02:03Z;ESTDOI;ESTDOI.KEEL;Estonian Dialect Corpus;Lindstr\u00f6m, Liina;Center of Estonian Language Resources;2013;doi:10.15155/TY.0007",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "df8da476-f516-5628-ba15-2390751068dc",
-    "oai_identifier": [
-        "oai:oai.datacite.org:4597355"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Estonian Dialect Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e1d98d97-e1de-5850-b531-0e9332f4a199.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e1d98d97-e1de-5850-b531-0e9332f4a199.json
deleted file mode 100644
index f6666ddf..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e1d98d97-e1de-5850-b531-0e9332f4a199.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00125L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9832371",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9832371"
-    ],
-    "PublicationTimestamp": "2016-12-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Tkachenko, Alexander"
-    ],
-    "fulltext": "oai:oai.datacite.org:9832371;2019-04-17T17:26:35Z;ESTDOI;ESTDOI.KEEL;Estonian gap tests;Tkachenko, Alexander;Center of Estonian Language Resources;2016;Issued: 2016-11-30;Updated: 2016-12-01;doi:10.15155/1-00-0000-0000-0000-00125L;Abstract;Estonian gap tests corpus represents a collection of sentences, in which one word is marked as a \"gap\", accompanied with a list of candidate words. The corpus can be used as a benchmark for evaluating language models. The corpus covers both frequent and infrequent gap-words and includes candidate lists generated in different ways. Sentences originate from the Estonian Reference Corpus (http://www.cl.ut.ee/korpused/segakorpus/). The corpus has been tokenized using Estnltk toolkit (https://github.com/estnltk/estnltk).\n\nAn archive contains sentence files with an extension \".gaps\" and candidate files with an extension \"*.var\". Sentence file contains one sentence per line. A line starts with an integer which indicates gap-word's offset in a sentence. The position of the first word in the sentence is zero. Based on the frequency of a gap-word, we generated four kinds of sentence files:\n\nFile name             Gap-word frequency\n--------------------------------------------------------------\ntest.all.gaps          any frequency\ntest.freq.gaps        frequent word form\ntest.inf_freq.gaps   infrequent word form, frequent word type (lemma)\ntest.inf_inf.gaps     infrequent word form, infrequent word type (lemma)\n\nTo each sentence file relate multiple candidate files. In a candidate file, each line contains a list of 200 candidate words, which correspond to a sentence at the same line in the related sentence file.\nCandidate files were generated using the same frequency ranges as sentence files. We also provide four kinds of candidate files:\n\nFile suffix        Explanation\n--------------------------------------------------------------------------------------\n*.pos.var        candidates with the same part of speech as a gap-word\n*.syn.var        candidates generated with a morphological generator based on the base form of a gap-word\n*.w2v.var       candidate words from word2vec's most similar query\n*.random.var  random words\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e1d98d97-e1de-5850-b531-0e9332f4a199",
-    "notes": [
-        "Abstract",
-        "Estonian gap tests corpus represents a collection of sentences, in which one word is marked as a \"gap\", accompanied with a list of candidate words. The corpus can be used as a benchmark for evaluating language models. The corpus covers both frequent and infrequent gap-words and includes candidate lists generated in different ways. Sentences originate from the Estonian Reference Corpus (http://www.cl.ut.ee/korpused/segakorpus/). The corpus has been tokenized using Estnltk toolkit (https://github.com/estnltk/estnltk).\n\nAn archive contains sentence files with an extension \".gaps\" and candidate files with an extension \"*.var\". Sentence file contains one sentence per line. A line starts with an integer which indicates gap-word's offset in a sentence. The position of the first word in the sentence is zero. Based on the frequency of a gap-word, we generated four kinds of sentence files:\n\nFile name             Gap-word frequency\n--------------------------------------------------------------\ntest.all.gaps          any frequency\ntest.freq.gaps        frequent word form\ntest.inf_freq.gaps   infrequent word form, frequent word type (lemma)\ntest.inf_inf.gaps     infrequent word form, infrequent word type (lemma)\n\nTo each sentence file relate multiple candidate files. In a candidate file, each line contains a list of 200 candidate words, which correspond to a sentence at the same line in the related sentence file.\nCandidate files were generated using the same frequency ranges as sentence files. We also provide four kinds of candidate files:\n\nFile suffix        Explanation\n--------------------------------------------------------------------------------------\n*.pos.var        candidates with the same part of speech as a gap-word\n*.syn.var        candidates generated with a morphological generator based on the base form of a gap-word\n*.w2v.var       candidate words from word2vec's most similar query\n*.random.var  random words\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9832371"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Estonian gap tests"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e4311d4b-e574-5ee1-95b8-812d2e3abd20.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e4311d4b-e574-5ee1-95b8-812d2e3abd20.json
deleted file mode 100644
index a69a13b1..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e4311d4b-e574-5ee1-95b8-812d2e3abd20.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00082L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5757280",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5757280"
-    ],
-    "PublicationTimestamp": "2015-05-22T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "M\u00fc\u00fcrisep, Kaili"
-    ],
-    "fulltext": "oai:oai.datacite.org:5757280;2018-10-21T07:00:48Z;ESTDOI;ESTDOI.KEEL;Pinds\u00fcntaktiliselt anal\u00fc\u00fcsitud korpus;Estonian corpus with shallow syntactic annotation;M\u00fc\u00fcrisep, Kaili;Center of Estonian Language Resources;2011;Issued: 2011-12-31;Updated: 2015-05-22;doi:10.15155/1-00-0000-0000-0000-00082L;Abstract;This corpus is a monolingual corpus with Constraint Grammar-style shallow syntactic annotations.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e4311d4b-e574-5ee1-95b8-812d2e3abd20",
-    "notes": [
-        "Abstract",
-        "This corpus is a monolingual corpus with Constraint Grammar-style shallow syntactic annotations."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5757280"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Pinds\u00fcntaktiliselt anal\u00fc\u00fcsitud korpus",
-        "Estonian corpus with shallow syntactic annotation"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e4ddf7a7-8871-5ab0-af91-9d345c0e88b5.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e4ddf7a7-8871-5ab0-af91-9d345c0e88b5.json
deleted file mode 100644
index 10e703b7..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e4ddf7a7-8871-5ab0-af91-9d345c0e88b5.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00164L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17725900",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17725900"
-    ],
-    "PublicationTimestamp": "2018-12-07T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:17725900;2019-04-17T17:27:06Z;ESTDOI;ESTDOI.KEEL;Segakorpus: Riigikogu ver.2.0;Corpus of the Proceedings of Estonian Parliament ver.2.0;Muischnek, Kadri;Center of Estonian Language Resources;2013;Issued: 2013-01-07;Updated: 2018-12-07;doi:10.15155/1-00-0000-0000-0000-00164L;Abstract;Riigikogu korpus. TEI P5 XML m\u00e4rgendus, UTF8 kodeering. Morfoloogiline anal\u00fc\u00fcs ja \u00fchestamine, automaatselt tehtud.;Abstract;Corpus of the Proceedings of Estonian Parliament. Contains edited version of the Proceedings of Estonian Parliament from the years 1995-2001; Morphologically analysed and disambiguated, automatically.\nMarkup: TEI P5 XML\nEncoding: UTF8",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e4ddf7a7-8871-5ab0-af91-9d345c0e88b5",
-    "notes": [
-        "Abstract",
-        "Riigikogu korpus. TEI P5 XML m\u00e4rgendus, UTF8 kodeering. Morfoloogiline anal\u00fc\u00fcs ja \u00fchestamine, automaatselt tehtud.",
-        "Abstract",
-        "Corpus of the Proceedings of Estonian Parliament. Contains edited version of the Proceedings of Estonian Parliament from the years 1995-2001; Morphologically analysed and disambiguated, automatically.\nMarkup: TEI P5 XML\nEncoding: UTF8"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17725900"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Segakorpus: Riigikogu ver.2.0",
-        "Corpus of the Proceedings of Estonian Parliament ver.2.0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e5eb024a-edca-5f7e-9314-6e37f5186917.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e5eb024a-edca-5f7e-9314-6e37f5186917.json
deleted file mode 100644
index 9f446929..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e5eb024a-edca-5f7e-9314-6e37f5186917.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00185L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17950896",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17950896"
-    ],
-    "PublicationTimestamp": "2019-01-04T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Iva, Sulev"
-    ],
-    "fulltext": "oai:oai.datacite.org:17950896;2019-01-04T12:33:06Z;ESTDOI;ESTDOI.KEEL;V\u00f5ru ja Setu ilukirjanduskorpus;Iva, Sulev;Center of Estonian Language Resources;2019;Issued: 2019-01-04;Updated: 2019-01-04;doi:10.15155/1-00-0000-0000-0000-00185L;Abstract;Ilukirjanduse korpuse kogumahuks on ca 350 000 s\u00f5na, korpus on viimase aasta jooksul muudetud tekstiarhiivist avalikuks keelekorpuseks koos vajaliku kasutajaliidesega, mis asub aadressil http://synaq.org/ilo.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e5eb024a-edca-5f7e-9314-6e37f5186917",
-    "notes": [
-        "Abstract",
-        "Ilukirjanduse korpuse kogumahuks on ca 350 000 s\u00f5na, korpus on viimase aasta jooksul muudetud tekstiarhiivist avalikuks keelekorpuseks koos vajaliku kasutajaliidesega, mis asub aadressil http://synaq.org/ilo."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17950896"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "V\u00f5ru ja Setu ilukirjanduskorpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e6d0fc7c-a937-524d-9273-56f9e23b9eaa.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e6d0fc7c-a937-524d-9273-56f9e23b9eaa.json
deleted file mode 100644
index 33e96fe3..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e6d0fc7c-a937-524d-9273-56f9e23b9eaa.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-07335L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14745997",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14745997"
-    ],
-    "PublicationTimestamp": "2018-04-23T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Koppel, Kristina",
-        "Kallas, Jelena"
-    ],
-    "fulltext": "oai:oai.datacite.org:14745997;2019-04-17T17:27:09Z;ESTDOI;ESTDOI.KEEL;Eesti keele \u00f5ppekorpus 2018 (etSkELL)  2018-04;Estonian Corpus for Learners 2018 (etSkELL)  2018-04;Kallas, Jelena;Koppel, Kristina;Center of Estonian Language Resources;2018;Issued: 2018-04-23;Updated: 2018-04-23;doi:10.15155/3-00-0000-0000-0000-07335L;Abstract;Eesti keele \u00f5ppekorpus 2018 (etSkELL) on spetsiaalne tekstikorpus, mis sisaldab ainult keele\u00f5ppijale sobivaid lauseid. Laused p\u00e4rinevad Eesti keele \u00fchendkorpusest 2017 ja Eesti keele A1-C1 \u00f5pikute korpusest 2018. Keele\u00f5ppijale sobivate lausete tuvastamiseks kasutati Kristina Koppeli v\u00e4lja t\u00f6\u00f6tatud eesti keele GDEXi (Good Dictionary Example) moodulit, mis v\u00f5imaldab lausete filtreerimist vastavalt etteantud parameetritele (nt lause pikkus, kirjavahem\u00e4rkide arv \u00fche lause piires jmt). GDEXi skoorid on parandatud vastavalt uuele GDEXi konfuguratsioonile.\nEesti keele \u00f5ppekorpuse 2018 (etSkELL) suurus on u 250 000 s\u00f5na ja u 25 miljonit lauset. ",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e6d0fc7c-a937-524d-9273-56f9e23b9eaa",
-    "notes": [
-        "Abstract",
-        "Eesti keele \u00f5ppekorpus 2018 (etSkELL) on spetsiaalne tekstikorpus, mis sisaldab ainult keele\u00f5ppijale sobivaid lauseid. Laused p\u00e4rinevad Eesti keele \u00fchendkorpusest 2017 ja Eesti keele A1-C1 \u00f5pikute korpusest 2018. Keele\u00f5ppijale sobivate lausete tuvastamiseks kasutati Kristina Koppeli v\u00e4lja t\u00f6\u00f6tatud eesti keele GDEXi (Good Dictionary Example) moodulit, mis v\u00f5imaldab lausete filtreerimist vastavalt etteantud parameetritele (nt lause pikkus, kirjavahem\u00e4rkide arv \u00fche lause piires jmt). GDEXi skoorid on parandatud vastavalt uuele GDEXi konfuguratsioonile.\nEesti keele \u00f5ppekorpuse 2018 (etSkELL) suurus on u 250 000 s\u00f5na ja u 25 miljonit lauset. "
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14745997"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele \u00f5ppekorpus 2018 (etSkELL)  2018-04",
-        "Estonian Corpus for Learners 2018 (etSkELL)  2018-04"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e6e2c5fa-12f6-57d4-99e9-5efac4838045.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e6e2c5fa-12f6-57d4-99e9-5efac4838045.json
deleted file mode 100644
index b287a3f2..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e6e2c5fa-12f6-57d4-99e9-5efac4838045.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05BD7L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9474537",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9474537"
-    ],
-    "PublicationTimestamp": "2016-11-09T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:9474537;2019-03-01T06:01:07Z;ESTDOI;ESTDOI.KEEL;Huvihariduss\u00f5nastik;Hein, Indrek;Center of Estonian Language Resources;2016;Issued: 2016-11-09;Updated: 2016-11-09;doi:10.15155/3-00-0000-0000-0000-05BD7L;Abstract;S\u00f5nastik sisaldab huvidele vastava \u00f5ppet\u00f6\u00f6v\u00e4lise hariduse valdkonda kuuluvaid m\u00f5isteid koos t\u00e4henduse seletuse ning vastetega inglise, saksa, soome ja vene keeles.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e6e2c5fa-12f6-57d4-99e9-5efac4838045",
-    "notes": [
-        "Abstract",
-        "S\u00f5nastik sisaldab huvidele vastava \u00f5ppet\u00f6\u00f6v\u00e4lise hariduse valdkonda kuuluvaid m\u00f5isteid koos t\u00e4henduse seletuse ning vastetega inglise, saksa, soome ja vene keeles."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9474537"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Huvihariduss\u00f5nastik"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e7c8d2a2-0608-58e2-9214-9e98785d70c8.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e7c8d2a2-0608-58e2-9214-9e98785d70c8.json
deleted file mode 100644
index c63af426..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e7c8d2a2-0608-58e2-9214-9e98785d70c8.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00085L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5757010",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5757010"
-    ],
-    "PublicationTimestamp": "2015-03-02T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:5757010;2019-03-12T18:25:40Z;ESTDOI;ESTDOI.KEEL;Morfoloogiliselt \u00fchestatud korpus;Corpus of morphologically disambiguated Estonian texts;Muischnek, Kadri;Center of Estonian Language Resources;2011;Issued: 2011-12-31;Updated: 2015-03-02;doi:10.15155/1-00-0000-0000-0000-00085L;Abstract;K\u00e4sitis morfoloogiliselt \u00fchestatud korpus;Abstract;Manually annotated corpus.  Available for download and via Korp query.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e7c8d2a2-0608-58e2-9214-9e98785d70c8",
-    "notes": [
-        "Abstract",
-        "K\u00e4sitis morfoloogiliselt \u00fchestatud korpus",
-        "Abstract",
-        "Manually annotated corpus.  Available for download and via Korp query."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5757010"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Morfoloogiliselt \u00fchestatud korpus",
-        "Corpus of morphologically disambiguated Estonian texts"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e7da129d-3f2e-5153-ac93-da6cb39875c4.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e7da129d-3f2e-5153-ac93-da6cb39875c4.json
deleted file mode 100644
index b68a2575..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e7da129d-3f2e-5153-ac93-da6cb39875c4.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00184L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17950840",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17950840"
-    ],
-    "PublicationTimestamp": "2019-01-04T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Iva, Sulev"
-    ],
-    "fulltext": "oai:oai.datacite.org:17950840;2019-04-09T20:02:43Z;ESTDOI;ESTDOI.KEEL;V\u00f5ro ja seto kirjanduskogu;V\u00f5ro ja seto kir\u00e4nd\u00fcskogo;Iva, Sulev;Center of Estonian Language Resources;2019;Issued: 2019-01-04;Updated: 2019-01-04;doi:10.15155/1-00-0000-0000-0000-00184L;Abstract;Ilukirjanduse korpuse kogumahuks on ca 350 000 s\u00f5na, korpus on viimase aasta jooksul muudetud tekstiarhiivist avalikuks keelekorpuseks koos vajaliku kasutajaliidesega, mis asub aadressil http://synaq.org/ilo.;Abstract;Seo v\u00f5ro ja seto kir\u00e4nd\u00fcskogo om osa V\u00f5ro Instituudi v\u00f5ro ja seto keelekorpus\u00f5st. Korpus\u00f5n om parhilla umb\u00f5s 400 teksti (ca 350 000 s\u00f5nna). Tekstiq ommaq peri aastist 1881 \u2014 2014 . P\u00e4\u00e4lt ilokir\u00e4nd\u00fcstekste om tan viil er\u00e4le latsi- ja aokir\u00e4nd\u00fcstekste, esseistikat, m\u00e4leht\u00fcisi, tarb\u00f5tekste, dokumente ja e-kirjo tekste. Naid k\u00f5iki saa tast otsiq nii \u00fcten t\u00f5isi tekstiliikega ku ka er\u00e4lde. Korpus\u00f5 kokkopandmist om rahaga tug\u00f5nuq riiklin\u00f5 programm Eesti keeletehnoloogia.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e7da129d-3f2e-5153-ac93-da6cb39875c4",
-    "notes": [
-        "Abstract",
-        "Ilukirjanduse korpuse kogumahuks on ca 350 000 s\u00f5na, korpus on viimase aasta jooksul muudetud tekstiarhiivist avalikuks keelekorpuseks koos vajaliku kasutajaliidesega, mis asub aadressil http://synaq.org/ilo.",
-        "Abstract",
-        "Seo v\u00f5ro ja seto kir\u00e4nd\u00fcskogo om osa V\u00f5ro Instituudi v\u00f5ro ja seto keelekorpus\u00f5st. Korpus\u00f5n om parhilla umb\u00f5s 400 teksti (ca 350 000 s\u00f5nna). Tekstiq ommaq peri aastist 1881 \u2014 2014 . P\u00e4\u00e4lt ilokir\u00e4nd\u00fcstekste om tan viil er\u00e4le latsi- ja aokir\u00e4nd\u00fcstekste, esseistikat, m\u00e4leht\u00fcisi, tarb\u00f5tekste, dokumente ja e-kirjo tekste. Naid k\u00f5iki saa tast otsiq nii \u00fcten t\u00f5isi tekstiliikega ku ka er\u00e4lde. Korpus\u00f5 kokkopandmist om rahaga tug\u00f5nuq riiklin\u00f5 programm Eesti keeletehnoloogia."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17950840"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "V\u00f5ro ja seto kirjanduskogu",
-        "V\u00f5ro ja seto kir\u00e4nd\u00fcskogo"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e816cecc-f6a3-5908-b776-ab223ae63b93.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e816cecc-f6a3-5908-b776-ab223ae63b93.json
deleted file mode 100644
index 56036612..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e816cecc-f6a3-5908-b776-ab223ae63b93.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05AEFL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9310569",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9310569"
-    ],
-    "PublicationTimestamp": "2017-02-16T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:9310569;2019-03-29T12:32:25Z;ESTDOI;ESTDOI.KEEL;Esimene eesti sl\u00e4ngi s\u00f5naraamat;First Estonian Slang Dictionary;Hein, Indrek;Center of Estonian Language Resources;2016;Issued: 2016-10-19;Updated: 2017-02-16;doi:10.15155/3-00-0000-0000-0000-05AEFL;Abstract;S\u00f5naraamat p\u00f5hineb 1989. aasta kevadel Tallinna eesti keskkoolidest kogutud materjalil. Sl\u00e4ngis\u00f5naraamat on m\u00f5isteline, selles on u poolteistsada teemat, mille piires on seletatud vastavaid sl\u00e4ngis\u00f5nu.;Abstract;The \"First Estonian Slang Dictionary\" is based on a slang vocabulary collected in Tallinn high schools in the spring of 1989. As the collection procedure was based on 152 thematic questionnaires, the dictionary's first and main half is thematic. The dictionary's second half, or register, presents all slang words in alphabetic order, with cross references by number to the relevant themes. ",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e816cecc-f6a3-5908-b776-ab223ae63b93",
-    "notes": [
-        "Abstract",
-        "S\u00f5naraamat p\u00f5hineb 1989. aasta kevadel Tallinna eesti keskkoolidest kogutud materjalil. Sl\u00e4ngis\u00f5naraamat on m\u00f5isteline, selles on u poolteistsada teemat, mille piires on seletatud vastavaid sl\u00e4ngis\u00f5nu.",
-        "Abstract",
-        "The \"First Estonian Slang Dictionary\" is based on a slang vocabulary collected in Tallinn high schools in the spring of 1989. As the collection procedure was based on 152 thematic questionnaires, the dictionary's first and main half is thematic. The dictionary's second half, or register, presents all slang words in alphabetic order, with cross references by number to the relevant themes. "
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9310569"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Esimene eesti sl\u00e4ngi s\u00f5naraamat",
-        "First Estonian Slang Dictionary"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e9198063-833c-586f-895b-07d8ef251572.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e9198063-833c-586f-895b-07d8ef251572.json
deleted file mode 100644
index 59b18508..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e9198063-833c-586f-895b-07d8ef251572.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-00098L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17955057",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17955057"
-    ],
-    "PublicationTimestamp": "2019-01-05T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Alum\u00e4e, Tanel"
-    ],
-    "fulltext": "oai:oai.datacite.org:17955057;2019-01-05T10:22:42Z;ESTDOI;ESTDOI.KEEL;Inimesed;Alum\u00e4e, Tanel;Center of Estonian Language Resources;2019;Issued: 2019-01-05;Updated: 2019-01-05;doi:10.15155/9-00-0000-0000-0000-00098L;Abstract;Androidi rakendus, mis v\u00f5imaldab kiiresti ja mugavalt otsida aadressiraamatus sisalduvaid kontaktandmeid, samas ka n\u00e4ide reeglip\u00f5hise keelemudeliga eestikeelsest k\u00f5netuvastusest.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e9198063-833c-586f-895b-07d8ef251572",
-    "notes": [
-        "Abstract",
-        "Androidi rakendus, mis v\u00f5imaldab kiiresti ja mugavalt otsida aadressiraamatus sisalduvaid kontaktandmeid, samas ka n\u00e4ide reeglip\u00f5hise keelemudeliga eestikeelsest k\u00f5netuvastusest."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17955057"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Inimesed"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e91c31c3-a3d5-5003-8823-03f484b1c607.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e91c31c3-a3d5-5003-8823-03f484b1c607.json
deleted file mode 100644
index a7d2f96f..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e91c31c3-a3d5-5003-8823-03f484b1c607.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0015FL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:15015401",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:15015401"
-    ],
-    "PublicationTimestamp": "2018-05-10T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laur, Sven"
-    ],
-    "fulltext": "oai:oai.datacite.org:15015401;2018-10-22T22:31:43Z;ESTDOI;ESTDOI.KEEL;EstNLTK teek Pythoni jaoks (ver.1.4);EstNLTK library for Python (ver.1.4);Laur, Sven;Center of Estonian Language Resources;2018;Issued: 2018-05-04;Updated: 2018-05-10;doi:10.15155/1-00-0000-0000-0000-0015FL;Abstract;EstNLTK provides common natural language processing functionality such as paragraph, sentence and word tokenization, morphological analysis, named entity recognition, etc. for the Estonian language.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e91c31c3-a3d5-5003-8823-03f484b1c607",
-    "notes": [
-        "Abstract",
-        "EstNLTK provides common natural language processing functionality such as paragraph, sentence and word tokenization, morphological analysis, named entity recognition, etc. for the Estonian language."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:15015401"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "EstNLTK teek Pythoni jaoks (ver.1.4)",
-        "EstNLTK library for Python (ver.1.4)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e9b1f55d-3818-5fe7-a5b2-eb469e589d41.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e9b1f55d-3818-5fe7-a5b2-eb469e589d41.json
deleted file mode 100644
index 5fd36168..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e9b1f55d-3818-5fe7-a5b2-eb469e589d41.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-079D8L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17959927",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17959927"
-    ],
-    "PublicationTimestamp": "2019-01-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Mihkla, Meelis"
-    ],
-    "fulltext": "oai:oai.datacite.org:17959927;2019-04-01T18:01:20Z;ESTDOI;ESTDOI.KEEL;Subtiitrite helindaja;Mihkla, Meelis;Center of Estonian Language Resources;2019;Issued: 2019-01-07;Updated: 2019-01-07;doi:10.15155/3-00-0000-0000-0000-079D8L;Abstract;Subtiitrite helindamise ning tele-eetrisse edastamise tarkvaralahenduse eesm\u00e4rk on ETVs kasutatavate subtiitrifailide alusel k\u00f5nes\u00fcntesaatoriga helifailide genereerimine ning eraldi helikanalis digitelevisiooni eetrisse edastamine. \u00dchisprojekti on kaasatud Eesti Keele Instituut (EKI), Eesti Rahvusringh\u00e4\u00e4ling (ERR) ja Eesti Pimedate Liit (EPL).",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e9b1f55d-3818-5fe7-a5b2-eb469e589d41",
-    "notes": [
-        "Abstract",
-        "Subtiitrite helindamise ning tele-eetrisse edastamise tarkvaralahenduse eesm\u00e4rk on ETVs kasutatavate subtiitrifailide alusel k\u00f5nes\u00fcntesaatoriga helifailide genereerimine ning eraldi helikanalis digitelevisiooni eetrisse edastamine. \u00dchisprojekti on kaasatud Eesti Keele Instituut (EKI), Eesti Rahvusringh\u00e4\u00e4ling (ERR) ja Eesti Pimedate Liit (EPL)."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17959927"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Subtiitrite helindaja"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e9b9c0a1-fc89-5ee0-81d9-f326dfb116ac.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e9b9c0a1-fc89-5ee0-81d9-f326dfb116ac.json
deleted file mode 100644
index 9a21a837..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/e9b9c0a1-fc89-5ee0-81d9-f326dfb116ac.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-00025L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5755424",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5755424"
-    ],
-    "PublicationTimestamp": "2015-05-21T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Alum\u00e4e, Tanel"
-    ],
-    "fulltext": "oai:oai.datacite.org:5755424;2019-03-20T18:37:17Z;ESTDOI;ESTDOI.KEEL;Diktofon;Alum\u00e4e, Tanel;Center of Estonian Language Resources;2014;Issued: 2014-12-30;Updated: 2015-05-21;doi:10.15155/9-00-0000-0000-0000-00025L;Abstract;Diktofon on rakendus, mis v\u00f5imaldab telefoni abil heli lindistada ning lindistatud helifaile sorteerida, sildistada ning maham\u00e4ngida. Oluliseks erinevuseks teiste sarnaste diktofonirakendustega v\u00f5rreldes on see, et lindistatud eestikeelset k\u00f5ne saab automaatselt kirjalikuks tekstiks teisendada. Kirjaliku teksti olemasolu teeb helifailist infootsimise oluliselt mugavamaks.;Abstract;Voice recorder and transcriber for Android",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "e9b9c0a1-fc89-5ee0-81d9-f326dfb116ac",
-    "notes": [
-        "Abstract",
-        "Diktofon on rakendus, mis v\u00f5imaldab telefoni abil heli lindistada ning lindistatud helifaile sorteerida, sildistada ning maham\u00e4ngida. Oluliseks erinevuseks teiste sarnaste diktofonirakendustega v\u00f5rreldes on see, et lindistatud eestikeelset k\u00f5ne saab automaatselt kirjalikuks tekstiks teisendada. Kirjaliku teksti olemasolu teeb helifailist infootsimise oluliselt mugavamaks.",
-        "Abstract",
-        "Voice recorder and transcriber for Android"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5755424"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Diktofon"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ead1513a-4f66-5916-bddd-4636a1b78c2c.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ead1513a-4f66-5916-bddd-4636a1b78c2c.json
deleted file mode 100644
index ee94b173..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ead1513a-4f66-5916-bddd-4636a1b78c2c.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-079DCL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17960241",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17960241"
-    ],
-    "PublicationTimestamp": "2019-01-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:17960241;2019-04-10T23:32:06Z;ESTDOI;ESTDOI.KEEL;Tekstide helindaja;Hein, Indrek;Center of Estonian Language Resources;2019;Issued: 2019-01-07;Updated: 2019-01-07;doi:10.15155/3-00-0000-0000-0000-079DCL;Abstract;Heliraamatute genereerija Vox Populi, mis kasutab EKI k\u00f5nes\u00fcnteesi ja h\u00e4\u00e4ldusbaasi, et pikemaid tekste helindada.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ead1513a-4f66-5916-bddd-4636a1b78c2c",
-    "notes": [
-        "Abstract",
-        "Heliraamatute genereerija Vox Populi, mis kasutab EKI k\u00f5nes\u00fcnteesi ja h\u00e4\u00e4ldusbaasi, et pikemaid tekste helindada."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17960241"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Tekstide helindaja"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/eb01903d-7602-5d90-b4d4-f6143e1adad5.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/eb01903d-7602-5d90-b4d4-f6143e1adad5.json
deleted file mode 100644
index 50c074ea..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/eb01903d-7602-5d90-b4d4-f6143e1adad5.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-00093L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17926642",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17926642"
-    ],
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Meister, Einar"
-    ],
-    "fulltext": "oai:oai.datacite.org:17926642;2019-04-13T17:37:13Z;ESTDOI;ESTDOI.KEEL;Uudistekorpus;TV News Corpus;Meister, Einar;Center of Estonian Language Resources;2018;Issued: 2018-12-27;Updated: 2019-01-08;doi:10.15155/9-00-0000-0000-0000-00093L;Abstract;Kogutud ja k\u00e4sitsi m\u00e4rgendatud 30 tundi teleuudiseid.;Abstract;30 hours of TV news annotated.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "eb01903d-7602-5d90-b4d4-f6143e1adad5",
-    "notes": [
-        "Abstract",
-        "Kogutud ja k\u00e4sitsi m\u00e4rgendatud 30 tundi teleuudiseid.",
-        "Abstract",
-        "30 hours of TV news annotated."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17926642"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Uudistekorpus",
-        "TV News Corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/eb3675a7-eec3-5921-a203-178df8cc2a9a.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/eb3675a7-eec3-5921-a203-178df8cc2a9a.json
deleted file mode 100644
index f7d98bac..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/eb3675a7-eec3-5921-a203-178df8cc2a9a.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00072L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5757482",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5757482"
-    ],
-    "PublicationTimestamp": "2016-02-08T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Orav, Heili"
-    ],
-    "fulltext": "oai:oai.datacite.org:5757482;2019-04-21T17:01:44Z;ESTDOI;ESTDOI.KEEL;Estonian Wordnet (kb69a);Orav, Heili;Center of Estonian Language Resources;2014;Issued: 2014-03-21;Updated: 2016-02-08;doi:10.15155/1-00-0000-0000-0000-00072L;Abstract;The atom of a wordnet-type thesaurus is a synonym set (also called a synset), which is a set containing all the synonymous words or multi-word units that express the same concept. All words in a synset belong into the same part of speech.\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "eb3675a7-eec3-5921-a203-178df8cc2a9a",
-    "notes": [
-        "Abstract",
-        "The atom of a wordnet-type thesaurus is a synonym set (also called a synset), which is a set containing all the synonymous words or multi-word units that express the same concept. All words in a synset belong into the same part of speech.\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5757482"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Estonian Wordnet (kb69a)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ebe449e6-3a06-5837-adf6-56205b668698.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ebe449e6-3a06-5837-adf6-56205b668698.json
deleted file mode 100644
index 56a0d6b5..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ebe449e6-3a06-5837-adf6-56205b668698.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00169L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17926657",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17926657"
-    ],
-    "PublicationTimestamp": "2018-12-21T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "M\u00fc\u00fcrisep, Kaili"
-    ],
-    "fulltext": "oai:oai.datacite.org:17926657;2019-03-24T23:02:33Z;ESTDOI;ESTDOI.KEEL;Anafooride suhtes m\u00e4rgendatud Eesti s\u00f5ltuvuspuude pank;Estonian Treebank annotated with coreference relations;M\u00fc\u00fcrisep, Kaili;Center of Estonian Language Resources;2018;Issued: 2018-12-21;Updated: 2018-12-21;doi:10.15155/1-00-0000-0000-0000-00169L;Abstract;Anafooride suhtes m\u00e4rgendatud korpuses on praegu ca 107000 s\u00f5na mahus tekste, milles on u 4200 m\u00e4rgendatud ases\u00f5na, millest u 3200 on \u00fchendatud oma viitealusega, \u00fclej\u00e4\u00e4nud tuhandel ases\u00f5nal viitealus tekstis puudub. Tekstideks on ajalehetekstid ning \u00fcks teadustekst (ajakirja Eesti Arst 2004. aasta aastak\u00e4ik). M\u00e4rgendatud on j\u00e4rgmised ases\u00f5nad k\u00f5igis k\u00e4\u00e4ndevormides ja nende viitealused:\n\nisikulised ases\u00f5nad (mina/ma, sina/sa, tema/ta, meie/me, teie/te, nemad/nad). Kokku on korpuses 1734 isikulist ases\u00f5na, neist 1320 on \u00fchendatud viitealustega.\nn\u00e4itav ases\u00f5na see esineb korpuses 1489 korral, neist 1084 korral on tal tekstis olemas viitealus.\nsiduvad ases\u00f5nad kes ja mis esinevad tekstis kokku 1053 korda, neist 851 juhul on neil olemas viitealus tekstis.\nProgrammid, mis teisendavad puudepanga formaadis faili brati m\u00e4rgendajale sobivaks ja tagasi (pronoomentykeldaja.pl ja brat2inforem) on kataloogis tools. Programmide autorid on Kaili M\u00fc\u00fcrisep ja Katrin Tsepelina.;Abstract;This corpus containing ca 107,000 words of running text, is annotated for pronouns and their antecendents. There are 4200 annotated pronouns, among them 3200 are linked with their antecendents. The remaining 1000 pronouns have no clearly identifiable antecendent in text. Majority of the texts come from Estonian newspapers plus one scientific (medical) text, namely an issue of journal \u201eEesti Arst\u201d (Estonian Doctor).\n\nPrograms to convert Estonian dependency trees (VISLCG format) to brat annotations and back (pronoomentykeldaja.pl and brat2inforem) are in the tools folder, authors Kaili M\u00fc\u00fcrisep and Katrin Tsepelina.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ebe449e6-3a06-5837-adf6-56205b668698",
-    "notes": [
-        "Abstract",
-        "Anafooride suhtes m\u00e4rgendatud korpuses on praegu ca 107000 s\u00f5na mahus tekste, milles on u 4200 m\u00e4rgendatud ases\u00f5na, millest u 3200 on \u00fchendatud oma viitealusega, \u00fclej\u00e4\u00e4nud tuhandel ases\u00f5nal viitealus tekstis puudub. Tekstideks on ajalehetekstid ning \u00fcks teadustekst (ajakirja Eesti Arst 2004. aasta aastak\u00e4ik). M\u00e4rgendatud on j\u00e4rgmised ases\u00f5nad k\u00f5igis k\u00e4\u00e4ndevormides ja nende viitealused:\n\nisikulised ases\u00f5nad (mina/ma, sina/sa, tema/ta, meie/me, teie/te, nemad/nad). Kokku on korpuses 1734 isikulist ases\u00f5na, neist 1320 on \u00fchendatud viitealustega.\nn\u00e4itav ases\u00f5na see esineb korpuses 1489 korral, neist 1084 korral on tal tekstis olemas viitealus.\nsiduvad ases\u00f5nad kes ja mis esinevad tekstis kokku 1053 korda, neist 851 juhul on neil olemas viitealus tekstis.\nProgrammid, mis teisendavad puudepanga formaadis faili brati m\u00e4rgendajale sobivaks ja tagasi (pronoomentykeldaja.pl ja brat2inforem) on kataloogis tools. Programmide autorid on Kaili M\u00fc\u00fcrisep ja Katrin Tsepelina.",
-        "Abstract",
-        "This corpus containing ca 107,000 words of running text, is annotated for pronouns and their antecendents. There are 4200 annotated pronouns, among them 3200 are linked with their antecendents. The remaining 1000 pronouns have no clearly identifiable antecendent in text. Majority of the texts come from Estonian newspapers plus one scientific (medical) text, namely an issue of journal \u201eEesti Arst\u201d (Estonian Doctor).\n\nPrograms to convert Estonian dependency trees (VISLCG format) to brat annotations and back (pronoomentykeldaja.pl and brat2inforem) are in the tools folder, authors Kaili M\u00fc\u00fcrisep and Katrin Tsepelina."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17926657"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Anafooride suhtes m\u00e4rgendatud Eesti s\u00f5ltuvuspuude pank",
-        "Estonian Treebank annotated with coreference relations"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ec524af1-1858-5d01-b7a3-064b9562035c.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ec524af1-1858-5d01-b7a3-064b9562035c.json
deleted file mode 100644
index 2c671f34..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ec524af1-1858-5d01-b7a3-064b9562035c.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0015EL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14977740",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14977740"
-    ],
-    "PublicationTimestamp": "2018-05-04T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laur, Sven"
-    ],
-    "fulltext": "oai:oai.datacite.org:14977740;2019-04-17T17:27:11Z;ESTDOI;ESTDOI.KEEL;EstNLTK teek Pythoni jaoks (ver.1.6.2b);EstNLTK library for Python (ver.1.6.2b);Laur, Sven;Center of Estonian Language Resources;2018;Issued: 2018-05-04;Updated: 2018-05-04;doi:10.15155/1-00-0000-0000-0000-0015EL;Abstract;EstNLTK teegis on kergesti kohandatav ning robustne lingvistilise anal\u00fc\u00fcsi t\u00f6\u00f6voog, mis toimib ka\nkirjakeelest oluliselt erinevatel tekstidel. S\u00f5ltuvalt tekstide erip\u00e4rast on v\u00f5imalik kohandada s\u00f5nestamist,\nlausestamist ja morfoloogilist anal\u00fc\u00fcsi. Vaikimisi kasutatakse EKT67 projektis ja Koondkorpuse anal\u00fc\u00fcsi\nabil leitud lihtsustus- ja normaliseerimisreegleid. T\u00f6\u00f6 tulemust valideeriti l\u00e4bi Koondkorpuse ja etTenTen-\ni t\u00e4ieliku anal\u00fc\u00fcsi.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ec524af1-1858-5d01-b7a3-064b9562035c",
-    "notes": [
-        "Abstract",
-        "EstNLTK teegis on kergesti kohandatav ning robustne lingvistilise anal\u00fc\u00fcsi t\u00f6\u00f6voog, mis toimib ka\nkirjakeelest oluliselt erinevatel tekstidel. S\u00f5ltuvalt tekstide erip\u00e4rast on v\u00f5imalik kohandada s\u00f5nestamist,\nlausestamist ja morfoloogilist anal\u00fc\u00fcsi. Vaikimisi kasutatakse EKT67 projektis ja Koondkorpuse anal\u00fc\u00fcsi\nabil leitud lihtsustus- ja normaliseerimisreegleid. T\u00f6\u00f6 tulemust valideeriti l\u00e4bi Koondkorpuse ja etTenTen-\ni t\u00e4ieliku anal\u00fc\u00fcsi."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14977740"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "EstNLTK teek Pythoni jaoks (ver.1.6.2b)",
-        "EstNLTK library for Python (ver.1.6.2b)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ed4d991f-23fa-5cb7-9a62-e9a147eceb97.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ed4d991f-23fa-5cb7-9a62-e9a147eceb97.json
deleted file mode 100644
index bd129fc5..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ed4d991f-23fa-5cb7-9a62-e9a147eceb97.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06614L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10637046",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10637046"
-    ],
-    "PublicationTimestamp": "2017-03-20T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Ross, Kristiina",
-        "Erelt, Mati"
-    ],
-    "fulltext": "oai:oai.datacite.org:10637046;2019-03-26T18:31:20Z;ESTDOI;ESTDOI.KEEL;Eesti keele k\u00e4siraamat;Handbook of the Estonian Language;Ross, Kristiina;Erelt, Mati;Center of Estonian Language Resources;2017;Issued: 2017-03-20;Updated: 2017-03-20;doi:10.15155/3-00-0000-0000-0000-06614L;Abstract;Pakub \u00fcldharivaid teadmisi eesti kirjakeele grammatika ja s\u00f5navara ehituse kohta. Esitus on v\u00f5imalikult lihtne, v\u00e4lditud on tavakasutajale tarbetuid \u00fcksikasju. Praktiline abivahend kirjakeele korrektseks kasutamiseks.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ed4d991f-23fa-5cb7-9a62-e9a147eceb97",
-    "notes": [
-        "Abstract",
-        "Pakub \u00fcldharivaid teadmisi eesti kirjakeele grammatika ja s\u00f5navara ehituse kohta. Esitus on v\u00f5imalikult lihtne, v\u00e4lditud on tavakasutajale tarbetuid \u00fcksikasju. Praktiline abivahend kirjakeele korrektseks kasutamiseks."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10637046"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele k\u00e4siraamat",
-        "Handbook of the Estonian Language"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/edae83db-eda2-5561-9a0b-2556116b9dd5.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/edae83db-eda2-5561-9a0b-2556116b9dd5.json
deleted file mode 100644
index 0d6a4139..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/edae83db-eda2-5561-9a0b-2556116b9dd5.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00157L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14614710",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14614710"
-    ],
-    "PublicationTimestamp": "2018-04-05T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laur, Sven"
-    ],
-    "fulltext": "oai:oai.datacite.org:14614710;2018-10-28T02:09:59Z;ESTDOI;ESTDOI.KEEL;Web13 anal\u00fc\u00fcsitud estnltk ver.1.6.b abil - json vormingus;Laur, Sven;Center of Estonian Language Resources;2018;Issued: 2018-04-05;Updated: 2018-04-05;doi:10.15155/1-00-0000-0000-0000-00157L;Abstract;Web13 anal\u00fc\u00fcsitud estnltk ver.1.6.b abil - json vormingus",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "edae83db-eda2-5561-9a0b-2556116b9dd5",
-    "notes": [
-        "Abstract",
-        "Web13 anal\u00fc\u00fcsitud estnltk ver.1.6.b abil - json vormingus"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14614710"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Web13 anal\u00fc\u00fcsitud estnltk ver.1.6.b abil - json vormingus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/edba948e-5d88-50e7-9733-d345bf502b66.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/edba948e-5d88-50e7-9733-d345bf502b66.json
deleted file mode 100644
index 02c86aba..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/edba948e-5d88-50e7-9733-d345bf502b66.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05BE5L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9474551",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9474551"
-    ],
-    "PublicationTimestamp": "2016-11-09T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Pajupuu, Hille"
-    ],
-    "fulltext": "oai:oai.datacite.org:9474551;2019-01-22T05:01:42Z;ESTDOI;ESTDOI.KEEL;Valentsikorpus;Pajupuu, Hille;Center of Estonian Language Resources;2016;Issued: 2016-11-09;Updated: 2016-11-09;doi:10.15155/3-00-0000-0000-0000-05BE5L;Abstract;Valentsikorpus koosneb \"Postimehe\" artiklite ortograafilistest l\u00f5ikudest, mille emotsionaalsuse (positiivne, negatiivne, vastuoluline, neutraalne) on m\u00e4\u00e4ranud lugejad. Kasutatud on domineeriva arvamuse meetodit (Pennebaker jt 1997).\nValentsikorpus on m\u00f5eldud eesk\u00e4tt statistiliste mudelite treenimiseks, kuid seda saab kasutada ka muudel eesm\u00e4rkidel. P\u00e4ringuid on v\u00f5imalik teha nii rubriike (Arvamus, Eesti, Kultuur, Sport, V\u00e4lismaa, Krimi) kui ka emotsionaalsust (positiivne, negatiivne, vastuoluline, neutraalne) arvesse v\u00f5ttes.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "edba948e-5d88-50e7-9733-d345bf502b66",
-    "notes": [
-        "Abstract",
-        "Valentsikorpus koosneb \"Postimehe\" artiklite ortograafilistest l\u00f5ikudest, mille emotsionaalsuse (positiivne, negatiivne, vastuoluline, neutraalne) on m\u00e4\u00e4ranud lugejad. Kasutatud on domineeriva arvamuse meetodit (Pennebaker jt 1997).\nValentsikorpus on m\u00f5eldud eesk\u00e4tt statistiliste mudelite treenimiseks, kuid seda saab kasutada ka muudel eesm\u00e4rkidel. P\u00e4ringuid on v\u00f5imalik teha nii rubriike (Arvamus, Eesti, Kultuur, Sport, V\u00e4lismaa, Krimi) kui ka emotsionaalsust (positiivne, negatiivne, vastuoluline, neutraalne) arvesse v\u00f5ttes."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9474551"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Valentsikorpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/eefbfbd4-6fc4-5162-9c14-9edca29aaebc.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/eefbfbd4-6fc4-5162-9c14-9edca29aaebc.json
deleted file mode 100644
index 6c193c36..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/eefbfbd4-6fc4-5162-9c14-9edca29aaebc.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05B56L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9352881",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9352881"
-    ],
-    "PublicationTimestamp": "2016-10-26T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Viks, \u00dclle"
-    ],
-    "fulltext": "oai:oai.datacite.org:9352881;2019-04-23T12:31:30Z;ESTDOI;ESTDOI.KEEL;Eesti-norra s\u00f5naraamat\n;Estonian-Norwegian Dictionary\n;Viks, \u00dclle;Center of Estonian Language Resources;2016;Issued: 2016-10-26;Updated: 2016-10-26;doi:10.15155/3-00-0000-0000-0000-05B56L;Abstract;Sisaldab u 19 000 eesti ja 21 000 norra m\u00e4rks\u00f5na, millele on lisatud grammatilised andmed ja hulgaliselt n\u00e4iteid s\u00f5nade kasutamise kohta. Raamatus on ka l\u00fchi\u00fclevaated eesti ja norra keelest.\n\nTurid Farbregd, Sigrid Kangur, \u00dclle Viks. Norra-eesti : eesti-norra s\u00f5naraamat. Eesti Keele Sihtasutus. Tallinn 1998, 2. tr\u00fckk 2005 (3. tr\u00fckk ilmub 2013).\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "eefbfbd4-6fc4-5162-9c14-9edca29aaebc",
-    "notes": [
-        "Abstract",
-        "Sisaldab u 19 000 eesti ja 21 000 norra m\u00e4rks\u00f5na, millele on lisatud grammatilised andmed ja hulgaliselt n\u00e4iteid s\u00f5nade kasutamise kohta. Raamatus on ka l\u00fchi\u00fclevaated eesti ja norra keelest.\n\nTurid Farbregd, Sigrid Kangur, \u00dclle Viks. Norra-eesti : eesti-norra s\u00f5naraamat. Eesti Keele Sihtasutus. Tallinn 1998, 2. tr\u00fckk 2005 (3. tr\u00fckk ilmub 2013).\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9352881"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti-norra s\u00f5naraamat\n",
-        "Estonian-Norwegian Dictionary\n"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ef51e879-7ae3-586f-8f3e-3af27c033592.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ef51e879-7ae3-586f-8f3e-3af27c033592.json
deleted file mode 100644
index 73a97002..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ef51e879-7ae3-586f-8f3e-3af27c033592.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00089L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:6334553",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:6334553"
-    ],
-    "PublicationTimestamp": "2019-01-03T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:6334553;2019-04-18T17:36:41Z;ESTDOI;ESTDOI.KEEL;Eesti keele puudepank;Muischnek, Kadri;Center of Estonian Language Resources;2015;Issued: 2015-06-18;Updated: 2019-01-03;doi:10.15155/1-00-0000-0000-0000-00089L;Abstract;Morfoloogiliselt ja s\u00f5ltuvuss\u00fcntaktiliselt anal\u00fc\u00fcsitud eestikeelsed tekstid, kokku umbes 400 000 s\u00f5na 30 000 lauses. Tekstid on p\u00e4rit eesti keele Tasakaalus korpusest http://www.cl.ut.ee/korpused/grammatikakorpus/ ja Koondkorpusest http://www.cl.ut.ee/korpused/segakorpus/ ning jagunevad ilukirjanduse, ajakirjanduse, teaduse ja populaarteaduse tekstiklasside vahel. Tekstid on esmalt anal\u00fc\u00fcsitud reeglip\u00f5hise, kitsenduste grammatikal p\u00f5hineva s\u00f5ltuvuss\u00fcntaktilise anal\u00fcsaatoriga; automaatselt anal\u00fc\u00fcsitud faile on parandatud k\u00e4sitsi.\nPublikatsioon: Muischnek, Kadri; M\u00fc\u00fcrisep, Kaili; Puolakainen Tiina (2014). Dependency Parsing of Estonian : Statistical and Rule - based Approaches Human Language Technologies - The Baltic Perspective. Frontiers in Artificial Intelligence and Applications Vol 268. IOS Press, Amsterdam, pp. 111-118. \"",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ef51e879-7ae3-586f-8f3e-3af27c033592",
-    "notes": [
-        "Abstract",
-        "Morfoloogiliselt ja s\u00f5ltuvuss\u00fcntaktiliselt anal\u00fc\u00fcsitud eestikeelsed tekstid, kokku umbes 400 000 s\u00f5na 30 000 lauses. Tekstid on p\u00e4rit eesti keele Tasakaalus korpusest http://www.cl.ut.ee/korpused/grammatikakorpus/ ja Koondkorpusest http://www.cl.ut.ee/korpused/segakorpus/ ning jagunevad ilukirjanduse, ajakirjanduse, teaduse ja populaarteaduse tekstiklasside vahel. Tekstid on esmalt anal\u00fc\u00fcsitud reeglip\u00f5hise, kitsenduste grammatikal p\u00f5hineva s\u00f5ltuvuss\u00fcntaktilise anal\u00fcsaatoriga; automaatselt anal\u00fc\u00fcsitud faile on parandatud k\u00e4sitsi.\nPublikatsioon: Muischnek, Kadri; M\u00fc\u00fcrisep, Kaili; Puolakainen Tiina (2014). Dependency Parsing of Estonian : Statistical and Rule - based Approaches Human Language Technologies - The Baltic Perspective. Frontiers in Artificial Intelligence and Applications Vol 268. IOS Press, Amsterdam, pp. 111-118. \""
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:6334553"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele puudepank"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ef7dc444-1e9b-55b0-bd75-143cc35ac7aa.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ef7dc444-1e9b-55b0-bd75-143cc35ac7aa.json
deleted file mode 100644
index 97b9c002..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/ef7dc444-1e9b-55b0-bd75-143cc35ac7aa.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-071EBL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14560138",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14560138"
-    ],
-    "PublicationTimestamp": "2018-03-26T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Koppel, Kristina",
-        "Kallas, Jelena"
-    ],
-    "fulltext": "oai:oai.datacite.org:14560138;2019-04-17T17:27:00Z;ESTDOI;ESTDOI.KEEL;Eesti keele \u00f5ppekorpus 2018 (etSkELL);Estonian Corpus for Learners 2018 (etSkELL);Kallas, Jelena;Koppel, Kristina;Center of Estonian Language Resources;2018;Issued: 2018-03-26;Updated: 2018-03-26;doi:10.15155/3-00-0000-0000-0000-071EBL;Abstract;Eesti keele \u00f5ppekorpus 2018 (etSkELL) on spetsiaalne tekstikorpus, mis sisaldab ainult keele\u00f5ppijale sobivaid lauseid. Laused p\u00e4rinevad Eesti keele \u00fchendkorpusest 2017 ja Eesti keele A1-C1 \u00f5pikute korpusest 2018. Keele\u00f5ppijale sobivate lausete tuvastamiseks kasutati Kristina Koppeli v\u00e4lja t\u00f6\u00f6tatud eesti keele GDEXi  (Good Dictionary Example) moodulit, mis v\u00f5imaldab lausete filtreerimist vastavalt etteantud parameetritele (nt lause pikkus, kirjavahem\u00e4rkide arv \u00fche lause piires jmt).\nEesti keele \u00f5ppekorpuse 2018 (etSkELL) suurus on u 248 000 s\u00f5na ja u 25 miljonit lauset. \nKorpus on lemmatiseeritud, m\u00e4rgendatud ja \u00fchestatud anal\u00fcsaatori EstNLTK abil.\nKorpus on loodud Eesti Keele Instituudi ja Lexical Computing Ltd. koost\u00f6\u00f6 raames. \n\n\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "ef7dc444-1e9b-55b0-bd75-143cc35ac7aa",
-    "notes": [
-        "Abstract",
-        "Eesti keele \u00f5ppekorpus 2018 (etSkELL) on spetsiaalne tekstikorpus, mis sisaldab ainult keele\u00f5ppijale sobivaid lauseid. Laused p\u00e4rinevad Eesti keele \u00fchendkorpusest 2017 ja Eesti keele A1-C1 \u00f5pikute korpusest 2018. Keele\u00f5ppijale sobivate lausete tuvastamiseks kasutati Kristina Koppeli v\u00e4lja t\u00f6\u00f6tatud eesti keele GDEXi  (Good Dictionary Example) moodulit, mis v\u00f5imaldab lausete filtreerimist vastavalt etteantud parameetritele (nt lause pikkus, kirjavahem\u00e4rkide arv \u00fche lause piires jmt).\nEesti keele \u00f5ppekorpuse 2018 (etSkELL) suurus on u 248 000 s\u00f5na ja u 25 miljonit lauset. \nKorpus on lemmatiseeritud, m\u00e4rgendatud ja \u00fchestatud anal\u00fcsaatori EstNLTK abil.\nKorpus on loodud Eesti Keele Instituudi ja Lexical Computing Ltd. koost\u00f6\u00f6 raames. \n\n\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14560138"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele \u00f5ppekorpus 2018 (etSkELL)",
-        "Estonian Corpus for Learners 2018 (etSkELL)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f01564d9-f9bf-5f32-8e60-afb14ee8f047.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f01564d9-f9bf-5f32-8e60-afb14ee8f047.json
deleted file mode 100644
index 82c717cd..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f01564d9-f9bf-5f32-8e60-afb14ee8f047.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-0017AL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17945050",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17945050"
-    ],
-    "PublicationTimestamp": "2019-01-03T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:17945050;2019-03-14T03:02:20Z;ESTDOI;ESTDOI.KEEL;Kollokatsioonide tuvastaja;Muischnek, Kadri;Center of Estonian Language Resources;2019;Issued: 2019-01-03;Updated: 2019-01-03;doi:10.15155/1-00-0000-0000-0000-0017AL;Abstract;Kollokatsioonid on sellised s\u00f5napaarid, mille liikmed esinevad \u00fcksteise naabruses sagedamini kui v\u00f5iks eeldada nende \u00fcksikult esinemise sageduste p\u00f5hjal. T\u00fc\u00fcpilised kollokatsioonid on p\u00fcsi\u00fchendid - n\u00e4iteks \u00fchendverbid v\u00f5i idiomaatilised v\u00e4ljendid. P\u00fcsi\u00fchendid v\u00f5ivad muidugi koosneda ka rohkem kui kahest s\u00f5nast, kuid meie kollokatsioonide otsija suudab tuvastada ainult kahes\u00f5nalisi \u00fchendeid.\n\nKollokatsioonide otsimisel arvestatakse v\u00f5imalike kollokaatide kandidaatidena samas osalauses esinevaid s\u00f5navorme v\u00f5i lemmasid.\n\nKollokatsioone saab otsida kolmel viisil:\n\n1) teatud lemma olulisi kollokaate s\u00f5navormidena\n2) teatud lemma olulisi kollokaate lemmadena\n3) teatud s\u00f5navormi olulisi kollokaate s\u00f5navormidena\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f01564d9-f9bf-5f32-8e60-afb14ee8f047",
-    "notes": [
-        "Abstract",
-        "Kollokatsioonid on sellised s\u00f5napaarid, mille liikmed esinevad \u00fcksteise naabruses sagedamini kui v\u00f5iks eeldada nende \u00fcksikult esinemise sageduste p\u00f5hjal. T\u00fc\u00fcpilised kollokatsioonid on p\u00fcsi\u00fchendid - n\u00e4iteks \u00fchendverbid v\u00f5i idiomaatilised v\u00e4ljendid. P\u00fcsi\u00fchendid v\u00f5ivad muidugi koosneda ka rohkem kui kahest s\u00f5nast, kuid meie kollokatsioonide otsija suudab tuvastada ainult kahes\u00f5nalisi \u00fchendeid.\n\nKollokatsioonide otsimisel arvestatakse v\u00f5imalike kollokaatide kandidaatidena samas osalauses esinevaid s\u00f5navorme v\u00f5i lemmasid.\n\nKollokatsioone saab otsida kolmel viisil:\n\n1) teatud lemma olulisi kollokaate s\u00f5navormidena\n2) teatud lemma olulisi kollokaate lemmadena\n3) teatud s\u00f5navormi olulisi kollokaate s\u00f5navormidena\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17945050"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Kollokatsioonide tuvastaja"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f0949816-6254-562a-bc10-76672505eb3b.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f0949816-6254-562a-bc10-76672505eb3b.json
deleted file mode 100644
index 934da383..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f0949816-6254-562a-bc10-76672505eb3b.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-07BD9L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:19520871",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:19520871"
-    ],
-    "PublicationTimestamp": "2019-02-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Soon, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:19520871;2019-04-05T10:36:49Z;ESTDOI;ESTDOI.KEEL;Esterm v20190101;Esterm v20190101;Soon, Tiina;Center of Estonian Language Resources;2019;Issued: 2019-02-07;Updated: 2019-02-07;doi:10.15155/3-00-0000-0000-0000-07BD9L;Abstract;Esterm on Eesti Keele Instituudi mitmekeelne terminibaas, mis sisaldab peamiselt Euroopa Liidu ja Eesti Vabariigi \u00f5igusaktide termineid. Terminibaas koondab \u00fcle 50 valdkonna terminoloogiat.;Abstract;Esterm is a multilingual termbase which includes terms mainly from the legal acts of the Republic of Estonia and the European Union. The termbase contains terminology from more than 50 domains.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f0949816-6254-562a-bc10-76672505eb3b",
-    "notes": [
-        "Abstract",
-        "Esterm on Eesti Keele Instituudi mitmekeelne terminibaas, mis sisaldab peamiselt Euroopa Liidu ja Eesti Vabariigi \u00f5igusaktide termineid. Terminibaas koondab \u00fcle 50 valdkonna terminoloogiat.",
-        "Abstract",
-        "Esterm is a multilingual termbase which includes terms mainly from the legal acts of the Republic of Estonia and the European Union. The termbase contains terminology from more than 50 domains."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:19520871"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Esterm v20190101",
-        "Esterm v20190101"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f0e20d46-468d-5db8-8488-e6e942dd53db.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f0e20d46-468d-5db8-8488-e6e942dd53db.json
deleted file mode 100644
index 0c4178bc..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f0e20d46-468d-5db8-8488-e6e942dd53db.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06346L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10304200",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10304200"
-    ],
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Viks, \u00dclle"
-    ],
-    "fulltext": "oai:oai.datacite.org:10304200;2019-04-17T17:26:38Z;ESTDOI;ESTDOI.KEEL;Veebip\u00f5hine s\u00f5nastikus\u00fcsteem EELex ;Viks, \u00dclle;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2019-01-08;doi:10.15155/3-00-0000-0000-0000-06346L;Abstract;Leksikograafi t\u00f6\u00f6keskkond EELex on veebip\u00f5histe t\u00f6\u00f6vahendite kompleks, mis \u00fchendab s\u00f5nastike koostajatele ja toimetajatele vajaliku tarkvara ja keeleressursid, toetab r\u00fchmat\u00f6\u00f6d ja pakub eesti keele tuge. EELexi tarkvara on s\u00f5nastike halduss\u00fcsteem, mis v\u00f5imaldab s\u00f5nastikke koostada, toimetada ja k\u00fcljendada, teha lihtsaid ja keerulisi struktuurip\u00f5hiseid p\u00e4ringuid ning p\u00e4ringutulemusi sortida. Toimetaja t\u00f6\u00f6 h\u00f5lbustamiseks on loodud mitmeid t\u00f6\u00f6riistu, nt ristviidete kontroll, hulgiparandused kogu s\u00f5nastikus, eesti morfoloogia andmete genereerimine, k\u00fcljendusvaate kujundus, s\u00f5nastikuteksti eksport Wordi jms.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f0e20d46-468d-5db8-8488-e6e942dd53db",
-    "notes": [
-        "Abstract",
-        "Leksikograafi t\u00f6\u00f6keskkond EELex on veebip\u00f5histe t\u00f6\u00f6vahendite kompleks, mis \u00fchendab s\u00f5nastike koostajatele ja toimetajatele vajaliku tarkvara ja keeleressursid, toetab r\u00fchmat\u00f6\u00f6d ja pakub eesti keele tuge. EELexi tarkvara on s\u00f5nastike halduss\u00fcsteem, mis v\u00f5imaldab s\u00f5nastikke koostada, toimetada ja k\u00fcljendada, teha lihtsaid ja keerulisi struktuurip\u00f5hiseid p\u00e4ringuid ning p\u00e4ringutulemusi sortida. Toimetaja t\u00f6\u00f6 h\u00f5lbustamiseks on loodud mitmeid t\u00f6\u00f6riistu, nt ristviidete kontroll, hulgiparandused kogu s\u00f5nastikus, eesti morfoloogia andmete genereerimine, k\u00fcljendusvaate kujundus, s\u00f5nastikuteksti eksport Wordi jms."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10304200"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Veebip\u00f5hine s\u00f5nastikus\u00fcsteem EELex "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f18b909c-c5d0-5405-8b77-a0e9a2eae51b.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f18b909c-c5d0-5405-8b77-a0e9a2eae51b.json
deleted file mode 100644
index 11581b3d..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f18b909c-c5d0-5405-8b77-a0e9a2eae51b.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06330L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10303800",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10303800"
-    ],
-    "PublicationTimestamp": "2019-01-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Kiissel, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:10303800;2019-02-23T18:25:47Z;ESTDOI;ESTDOI.KEEL;Eesti keele HTS-k\u00f5nes\u00fcntesaator ;Estonian HTS Speech Synthesiser;Kiissel, Indrek;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2019-01-07;doi:10.15155/3-00-0000-0000-0000-06330L;Abstract;Eestikeelne HTS-k\u00f5nes\u00fcntesaator ;Abstract;Reads aloud Estonian texts.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f18b909c-c5d0-5405-8b77-a0e9a2eae51b",
-    "notes": [
-        "Abstract",
-        "Eestikeelne HTS-k\u00f5nes\u00fcntesaator ",
-        "Abstract",
-        "Reads aloud Estonian texts."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10303800"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele HTS-k\u00f5nes\u00fcntesaator ",
-        "Estonian HTS Speech Synthesiser"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f2170e91-4dda-5f51-84a3-8953b6b9c5a3.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f2170e91-4dda-5f51-84a3-8953b6b9c5a3.json
deleted file mode 100644
index d202514e..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f2170e91-4dda-5f51-84a3-8953b6b9c5a3.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-079D7L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17959926",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17959926"
-    ],
-    "PublicationTimestamp": "2019-01-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Mihkla, Meelis"
-    ],
-    "fulltext": "oai:oai.datacite.org:17959926;2019-04-20T09:32:07Z;ESTDOI;ESTDOI.KEEL;Subtiitrite helindaja;Mihkla, Meelis;Center of Estonian Language Resources;2019;Issued: 2019-01-07;Updated: 2019-01-07;doi:10.15155/3-00-0000-0000-0000-079D7L;Abstract;Subtiitrite helindamise ning tele-eetrisse edastamise tarkvaralahenduse eesm\u00e4rk on ETVs kasutatavate subtiitrifailide alusel k\u00f5nes\u00fcntesaatoriga helifailide genereerimine ning eraldi helikanalis digitelevisiooni eetrisse edastamine. \u00dchisprojekti on kaasatud Eesti Keele Instituut (EKI), Eesti Rahvusringh\u00e4\u00e4ling (ERR) ja Eesti Pimedate Liit (EPL).",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f2170e91-4dda-5f51-84a3-8953b6b9c5a3",
-    "notes": [
-        "Abstract",
-        "Subtiitrite helindamise ning tele-eetrisse edastamise tarkvaralahenduse eesm\u00e4rk on ETVs kasutatavate subtiitrifailide alusel k\u00f5nes\u00fcntesaatoriga helifailide genereerimine ning eraldi helikanalis digitelevisiooni eetrisse edastamine. \u00dchisprojekti on kaasatud Eesti Keele Instituut (EKI), Eesti Rahvusringh\u00e4\u00e4ling (ERR) ja Eesti Pimedate Liit (EPL)."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17959926"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Subtiitrite helindaja"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f2c5993f-ab52-5239-9487-2bab8c4fec7b.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f2c5993f-ab52-5239-9487-2bab8c4fec7b.json
deleted file mode 100644
index 877e8532..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f2c5993f-ab52-5239-9487-2bab8c4fec7b.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00123L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9822137",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9822137"
-    ],
-    "PublicationTimestamp": "2016-11-30T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Tkachenko, Alexander"
-    ],
-    "fulltext": "oai:oai.datacite.org:9822137;2019-04-17T17:26:34Z;ESTDOI;ESTDOI.KEEL;NER-tagger corpus;Tkachenko, Alexander;Center of Estonian Language Resources;2016;Issued: 2016-11-29;Updated: 2016-11-30;doi:10.15155/1-00-0000-0000-0000-00123L;Abstract;NER-tagger corpus represents a collection of sentences with manually labelled named entities. The labelling is partial -- only a selected word from each sentence is labelled. As a result, the labelled entity may be only a part of a named entity and the sentence may potentially contain other named entities.  We distinguish the following types on named entities: PER: person, LOC: location, ORG: organization, FAC: facility, PRD: product, O: other. For each labelled word the label is determined by the largest named entity containing it. For instance, Eesti in the following sentence: \"Eesti \u00dchispanga Tartu kontor oli inimesi t\u00e4is\" is facility although \"Eesti\" is location and \"Eesti \u00dchispank\" is and organisation.     \n\nThe corpus has been created using nertagger web tool: https://github.com/estnltk/ner-tagger. Two human annotators have been involved in the annotation process. \n\nThe data file contains one sentence per line with the following columns:\nname           named entity token\nsentence      sentence\nstart            entity start offset in the sentence\nend             entity end position in the sentence\nlabel            assigned label\nannotator     human annotator id\ntime            number of milliseconds it took annotator to tag a word.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f2c5993f-ab52-5239-9487-2bab8c4fec7b",
-    "notes": [
-        "Abstract",
-        "NER-tagger corpus represents a collection of sentences with manually labelled named entities. The labelling is partial -- only a selected word from each sentence is labelled. As a result, the labelled entity may be only a part of a named entity and the sentence may potentially contain other named entities.  We distinguish the following types on named entities: PER: person, LOC: location, ORG: organization, FAC: facility, PRD: product, O: other. For each labelled word the label is determined by the largest named entity containing it. For instance, Eesti in the following sentence: \"Eesti \u00dchispanga Tartu kontor oli inimesi t\u00e4is\" is facility although \"Eesti\" is location and \"Eesti \u00dchispank\" is and organisation.     \n\nThe corpus has been created using nertagger web tool: https://github.com/estnltk/ner-tagger. Two human annotators have been involved in the annotation process. \n\nThe data file contains one sentence per line with the following columns:\nname           named entity token\nsentence      sentence\nstart            entity start offset in the sentence\nend             entity end position in the sentence\nlabel            assigned label\nannotator     human annotator id\ntime            number of milliseconds it took annotator to tag a word."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9822137"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "NER-tagger corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f2d04dde-d8d3-509e-b53f-a50950a17616.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f2d04dde-d8d3-509e-b53f-a50950a17616.json
deleted file mode 100644
index aa8f8403..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f2d04dde-d8d3-509e-b53f-a50950a17616.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-00176L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:18511716",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:18511716"
-    ],
-    "PublicationTimestamp": "2019-03-18T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Krum, Margit"
-    ],
-    "fulltext": "oai:oai.datacite.org:18511716;2019-04-18T17:36:45Z;ESTDOI;ESTDOI.KEEL;Tilde masint\u00f5lge;Krum, Margit;Center of Estonian Language Resources;2019;Issued: 2019-03-18;Updated: 2019-03-18;doi:10.15155/9-00-0000-0000-0000-00176L;Abstract;L\u00f5ppkasutajatele on lihtsalt ja tasuta k\u00e4ttesaadavad (veebilehitseja kaudu http://www.masint\u00f5lge.ee ja http://www.masintolge.ee) parima kvaliteediga masint\u00f5lkeprogrammid eesti keelest kultuuriliselt, majanduslikult olulistesse keeltesse (inglise, vene, soome, saksa, prantsuse) ja tagasi eesti keelde.;Abstract;Machine translation by Tilde",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f2d04dde-d8d3-509e-b53f-a50950a17616",
-    "notes": [
-        "Abstract",
-        "L\u00f5ppkasutajatele on lihtsalt ja tasuta k\u00e4ttesaadavad (veebilehitseja kaudu http://www.masint\u00f5lge.ee ja http://www.masintolge.ee) parima kvaliteediga masint\u00f5lkeprogrammid eesti keelest kultuuriliselt, majanduslikult olulistesse keeltesse (inglise, vene, soome, saksa, prantsuse) ja tagasi eesti keelde.",
-        "Abstract",
-        "Machine translation by Tilde"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:18511716"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Tilde masint\u00f5lge"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f3f9b148-6f08-59fc-ba84-9c0cd7ab2392.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f3f9b148-6f08-59fc-ba84-9c0cd7ab2392.json
deleted file mode 100644
index 351fc604..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f3f9b148-6f08-59fc-ba84-9c0cd7ab2392.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/9-00-0000-0000-0000-000A4L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17968029",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17968029"
-    ],
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Ross, Peeter"
-    ],
-    "fulltext": "oai:oai.datacite.org:17968029;2019-01-08T20:00:24Z;ESTDOI;ESTDOI.KEEL;Meditsiinikeele korpus;Ross, Peeter;Center of Estonian Language Resources;2019;Issued: 2019-01-08;Updated: 2019-01-08;doi:10.15155/9-00-0000-0000-0000-000A4L;Abstract;Meditsiinikeele korpuse koostamiseks on kasutatud autentseid isikustamata terviseandmeid, milleks on taotletud eetikaluba (Tallinna Meditsiiniuuringute Eetikakomitee otsuse nr 2169). Tuleb arvestada, et ka isikustamata terviseandmed on eriline materjal, sh ka tervishoiuturu konkurentsi tingimustes. Tegu on \u00fche tervishoiuasutuse andmetega, mis ei pruugi adekvaatselt kajastada ega olla automaatselt \u00fclekantavad k\u00f5igile teistele tervishoiuasutustele, ka ei saa nende alusel teha j\u00e4reldusi tervishoiuteenuse kui terviku kohta. K\u00f5nelause projektiga seotud eetikaloa \u00fcks osapool on olnud AS Ida-Tallinna Keskhaigla, kelle radioloogiainfos\u00fcsteemist on isikustamata p\u00e4ringuga saadud meditsiinikeele korpuse aluseks olnud algandmed. Seet\u00f5ttu AS Ida-Tallinna Keskhaigla \u00f5igus piirata nimetatud andmete kasutamist muudel eesm\u00e4rkidel kui k\u00e4esoleva projektiga seotud eetikaloaga kaetud eesm\u00e4rgid. Sel p\u00f5hjusel eeldab ka mitte\u00e4rilistel eesm\u00e4rkidel meditsiinikeele korpuse kasutamine uute eesm\u00e4rkide korral uue eetikaloa taotlemist v\u00f5i eelmise eetikaloa laiendamist, mida saab teha eetikaloas AS Ida-Tallinna Keskhaiglat esindava dr P. Rossi kaudu (peeter.ross@ttu.ee ).",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f3f9b148-6f08-59fc-ba84-9c0cd7ab2392",
-    "notes": [
-        "Abstract",
-        "Meditsiinikeele korpuse koostamiseks on kasutatud autentseid isikustamata terviseandmeid, milleks on taotletud eetikaluba (Tallinna Meditsiiniuuringute Eetikakomitee otsuse nr 2169). Tuleb arvestada, et ka isikustamata terviseandmed on eriline materjal, sh ka tervishoiuturu konkurentsi tingimustes. Tegu on \u00fche tervishoiuasutuse andmetega, mis ei pruugi adekvaatselt kajastada ega olla automaatselt \u00fclekantavad k\u00f5igile teistele tervishoiuasutustele, ka ei saa nende alusel teha j\u00e4reldusi tervishoiuteenuse kui terviku kohta. K\u00f5nelause projektiga seotud eetikaloa \u00fcks osapool on olnud AS Ida-Tallinna Keskhaigla, kelle radioloogiainfos\u00fcsteemist on isikustamata p\u00e4ringuga saadud meditsiinikeele korpuse aluseks olnud algandmed. Seet\u00f5ttu AS Ida-Tallinna Keskhaigla \u00f5igus piirata nimetatud andmete kasutamist muudel eesm\u00e4rkidel kui k\u00e4esoleva projektiga seotud eetikaloaga kaetud eesm\u00e4rgid. Sel p\u00f5hjusel eeldab ka mitte\u00e4rilistel eesm\u00e4rkidel meditsiinikeele korpuse kasutamine uute eesm\u00e4rkide korral uue eetikaloa taotlemist v\u00f5i eelmise eetikaloa laiendamist, mida saab teha eetikaloas AS Ida-Tallinna Keskhaiglat esindava dr P. Rossi kaudu (peeter.ross@ttu.ee )."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17968029"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Meditsiinikeele korpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f435e848-dc6f-5b95-b6eb-e8e3c1d3ef50.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f435e848-dc6f-5b95-b6eb-e8e3c1d3ef50.json
deleted file mode 100644
index 4ad7d0e5..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f435e848-dc6f-5b95-b6eb-e8e3c1d3ef50.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05B4EL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9352872",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9352872"
-    ],
-    "PublicationTimestamp": "2016-10-31T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek"
-    ],
-    "fulltext": "oai:oai.datacite.org:9352872;2018-10-23T12:48:07Z;ESTDOI;ESTDOI.KEEL;Seto s\u00f5nastik;Hein, Indrek;Center of Estonian Language Resources;2016;Issued: 2016-10-31;Updated: 2016-10-31;doi:10.15155/3-00-0000-0000-0000-05B4EL;Abstract;Esimene seto veebis\u00f5nastik sisaldab \u00fcle 6000 m\u00e4rks\u00f5na, mida saab otsida nii murdekeelse kirjapildi kui ka lihtsustatud ja ilma diakriitiliste m\u00e4rkideta variandi j\u00e4rgi.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f435e848-dc6f-5b95-b6eb-e8e3c1d3ef50",
-    "notes": [
-        "Abstract",
-        "Esimene seto veebis\u00f5nastik sisaldab \u00fcle 6000 m\u00e4rks\u00f5na, mida saab otsida nii murdekeelse kirjapildi kui ka lihtsustatud ja ilma diakriitiliste m\u00e4rkideta variandi j\u00e4rgi."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9352872"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Seto s\u00f5nastik"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f51e69c4-5327-5fa7-ac31-137a06bb5853.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f51e69c4-5327-5fa7-ac31-137a06bb5853.json
deleted file mode 100644
index 0450fcf8..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f51e69c4-5327-5fa7-ac31-137a06bb5853.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-0576AL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:8512249",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:8512249"
-    ],
-    "PublicationTimestamp": "2015-05-08T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Langemets, Margit"
-    ],
-    "fulltext": "oai:oai.datacite.org:8512249;2018-10-22T07:30:33Z;ESTDOI;ESTDOI.KEEL;Eesti keele seletav s\u00f5naraamat EKSS 2009;Explanatory Dictionary of Estonian;Langemets, Margit;Center of Estonian Language Resources;2015;Issued: 2015-05-06;Updated: 2015-05-08;doi:10.15155/3-00-0000-0000-0000-0576AL;Abstract;Suurim eesti keele s\u00f5naraamat, mis h\u00f5lmab kogu eesti kirjakeelt, k.a k\u00f5nekeelt ja oskuskeelt.  Oma t\u00fc\u00fcbilt on s\u00f5naraamat kirjeldav (deskriptiivne), mitte normiv (preskriptiivne).",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f51e69c4-5327-5fa7-ac31-137a06bb5853",
-    "notes": [
-        "Abstract",
-        "Suurim eesti keele s\u00f5naraamat, mis h\u00f5lmab kogu eesti kirjakeelt, k.a k\u00f5nekeelt ja oskuskeelt.  Oma t\u00fc\u00fcbilt on s\u00f5naraamat kirjeldav (deskriptiivne), mitte normiv (preskriptiivne)."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:8512249"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele seletav s\u00f5naraamat EKSS 2009",
-        "Explanatory Dictionary of Estonian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f54e2bba-380d-5163-b2ec-dd4999b16c93.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f54e2bba-380d-5163-b2ec-dd4999b16c93.json
deleted file mode 100644
index babd0cbb..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f54e2bba-380d-5163-b2ec-dd4999b16c93.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-071E7L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14559948",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14559948"
-    ],
-    "PublicationTimestamp": "2018-03-27T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Koppel, Kristina",
-        "Kallas, Jelena"
-    ],
-    "fulltext": "oai:oai.datacite.org:14559948;2019-04-17T17:26:59Z;ESTDOI;ESTDOI.KEEL;Eesti keele \u00fchendkorpus 2017;Estonian National Corpus 2017;Kallas, Jelena;Koppel, Kristina;Center of Estonian Language Resources;2018;Issued: 2018-03-26;Updated: 2018-03-27;doi:10.15155/3-00-0000-0000-0000-071E7L;Abstract;Korpus on loodud Eesti Keele Instituudi ja Lexical Computing Ltd. koost\u00f6\u00f6 raames. Korpuse suurus on 1,3 miljardit s\u00f5net. Korpuse alus on Eesti keele \u00fchendkorpus 2013, mida Lexical Computing Ltd. uuendas 2017. aastal Eesti Keele Instituudi tellimusel.\nAllkorpused on Eesti keele koondkorpus 1990-2008, Eesti keele veebikorpus 2013, Eesti keele veebikorpus 2017 ja Eesti Vikipeedia 2017 korpus. Veebikorpuste sisu on internetist alla laetud eestikeelsed veebilehed. Korpuse loomisel on kasutatud aadressil http://corpus.tools kirjeldatud programme: SpederLing, JustText, Chared, Onion and wiki2corpus. Korpus on lemmatiseeritud, m\u00e4rgendatud ja \u00fchestatud anal\u00fcsaatori EstNLTK abil. \n\n\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f54e2bba-380d-5163-b2ec-dd4999b16c93",
-    "notes": [
-        "Abstract",
-        "Korpus on loodud Eesti Keele Instituudi ja Lexical Computing Ltd. koost\u00f6\u00f6 raames. Korpuse suurus on 1,3 miljardit s\u00f5net. Korpuse alus on Eesti keele \u00fchendkorpus 2013, mida Lexical Computing Ltd. uuendas 2017. aastal Eesti Keele Instituudi tellimusel.\nAllkorpused on Eesti keele koondkorpus 1990-2008, Eesti keele veebikorpus 2013, Eesti keele veebikorpus 2017 ja Eesti Vikipeedia 2017 korpus. Veebikorpuste sisu on internetist alla laetud eestikeelsed veebilehed. Korpuse loomisel on kasutatud aadressil http://corpus.tools kirjeldatud programme: SpederLing, JustText, Chared, Onion and wiki2corpus. Korpus on lemmatiseeritud, m\u00e4rgendatud ja \u00fchestatud anal\u00fcsaatori EstNLTK abil. \n\n\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14559948"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele \u00fchendkorpus 2017",
-        "Estonian National Corpus 2017"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f55a60fa-383e-5ed1-aa83-7ff376229016.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f55a60fa-383e-5ed1-aa83-7ff376229016.json
deleted file mode 100644
index f6aa0758..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f55a60fa-383e-5ed1-aa83-7ff376229016.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00081L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:5757501",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:5757501"
-    ],
-    "PublicationTimestamp": "2019-01-04T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Kahusk, Neeme"
-    ],
-    "fulltext": "oai:oai.datacite.org:5757501;2019-04-17T17:25:49Z;ESTDOI;ESTDOI.KEEL;\u00dchestatud s\u00f5nat\u00e4hendustega korpus;Semantically disambiguated corpus of Estonian;Kahusk, Neeme;Center of Estonian Language Resources;2011;Issued: 2011-12-31;Updated: 2019-01-04;doi:10.15155/1-00-0000-0000-0000-00081L;Abstract;Raw text corpus. Resource for building Estonian Framenet",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f55a60fa-383e-5ed1-aa83-7ff376229016",
-    "notes": [
-        "Abstract",
-        "Raw text corpus. Resource for building Estonian Framenet"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:5757501"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "\u00dchestatud s\u00f5nat\u00e4hendustega korpus",
-        "Semantically disambiguated corpus of Estonian"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f607a2bd-0c93-5325-83a7-b927a8590b0c.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f607a2bd-0c93-5325-83a7-b927a8590b0c.json
deleted file mode 100644
index ec62789c..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f607a2bd-0c93-5325-83a7-b927a8590b0c.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05BEAL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9474556",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9474556"
-    ],
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Nurk, T\u00f5nis"
-    ],
-    "fulltext": "oai:oai.datacite.org:9474556;2019-04-17T17:26:24Z;ESTDOI;ESTDOI.KEEL;e-keelen\u00f5u;The Combined Dictionary Search and Language Helpline e-keelen\u00f5u;Nurk, T\u00f5nis;Center of Estonian Language Resources;2016;Issued: 2016-11-09;Updated: 2019-01-08;doi:10.15155/3-00-0000-0000-0000-05BEAL;Abstract;\u00dchisp\u00e4ring keeleinfot sisaldavatest allikatest. Portaali peaeesm\u00e4rgiks on pakkuda l\u00f5pptarbijale intuitiivselt lihtsal viisil vastuseid keelealastele k\u00fcsimustele, nt normingukohasus, vasted teistes keeltes, selgitused, et\u00fcmoloogia, kasutusinfo jms.;Abstract;A fine opportunity to respond to a query by retrieving information from several sources. Simple, time-saving and possibly addressing some sources the user need not even have considered.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f607a2bd-0c93-5325-83a7-b927a8590b0c",
-    "notes": [
-        "Abstract",
-        "\u00dchisp\u00e4ring keeleinfot sisaldavatest allikatest. Portaali peaeesm\u00e4rgiks on pakkuda l\u00f5pptarbijale intuitiivselt lihtsal viisil vastuseid keelealastele k\u00fcsimustele, nt normingukohasus, vasted teistes keeltes, selgitused, et\u00fcmoloogia, kasutusinfo jms.",
-        "Abstract",
-        "A fine opportunity to respond to a query by retrieving information from several sources. Simple, time-saving and possibly addressing some sources the user need not even have considered."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9474556"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "e-keelen\u00f5u",
-        "The Combined Dictionary Search and Language Helpline e-keelen\u00f5u"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f6b27ce2-543a-5d96-8e3a-472150c7e7f7.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f6b27ce2-543a-5d96-8e3a-472150c7e7f7.json
deleted file mode 100644
index 82a1ba66..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f6b27ce2-543a-5d96-8e3a-472150c7e7f7.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00174L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17944508",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17944508"
-    ],
-    "PublicationTimestamp": "2019-01-03T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:17944508;2019-04-11T17:37:08Z;ESTDOI;ESTDOI.KEEL;Maltparseri treenitud mudel;Muischnek, Kadri;Center of Estonian Language Resources;2019;Issued: 2019-01-03;Updated: 2019-01-03;doi:10.15155/1-00-0000-0000-0000-00174L;Abstract;MaltParseri eesti keele anal\u00fc\u00fcsiks vajalik mudel model.mco, treenitud eesti keele s\u00f5ltuvupuude pangal, \u00fchildub MaltParseri versiooniga 1.8.1. Sisaldab ka teisendajat eesti keele CG morfoloogilise \u00fchestaja v\u00f5i s\u00fcntaktilise anal\u00fcsaatori v\u00e4ljundi kujult MaltParseri treenitud mudeli jaoks sobivale conll-kujule. Anal\u00fc\u00fcsiks on vajalik MaltParseri anal\u00fcsaator: http://www.maltparser.org/.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f6b27ce2-543a-5d96-8e3a-472150c7e7f7",
-    "notes": [
-        "Abstract",
-        "MaltParseri eesti keele anal\u00fc\u00fcsiks vajalik mudel model.mco, treenitud eesti keele s\u00f5ltuvupuude pangal, \u00fchildub MaltParseri versiooniga 1.8.1. Sisaldab ka teisendajat eesti keele CG morfoloogilise \u00fchestaja v\u00f5i s\u00fcntaktilise anal\u00fcsaatori v\u00e4ljundi kujult MaltParseri treenitud mudeli jaoks sobivale conll-kujule. Anal\u00fc\u00fcsiks on vajalik MaltParseri anal\u00fcsaator: http://www.maltparser.org/."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17944508"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Maltparseri treenitud mudel"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f7830a62-76e4-5d52-8a03-66cc21295765.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f7830a62-76e4-5d52-8a03-66cc21295765.json
deleted file mode 100644
index 48936a18..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f7830a62-76e4-5d52-8a03-66cc21295765.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00119L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:6916097",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:6916097"
-    ],
-    "PublicationTimestamp": "2016-12-02T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Lippus, P\u00e4rtel"
-    ],
-    "fulltext": "oai:oai.datacite.org:6916097;2019-04-18T17:36:44Z;ESTDOI;ESTDOI.KEEL;P\u00f5hjatuule ja p\u00e4ikese korpus v.1.0.2;Estonian North Wind and the Sun Corpus v.1.0.2;Lippus, P\u00e4rtel;Center of Estonian Language Resources;2015;Issued: 2015-10-16;Updated: 2016-12-02;doi:10.15155/1-00-0000-0000-0000-00119L;Abstract;Recordings of the tale \u201cP\u00f5hjatuul ja p\u00e4ike\u201d (North Wind and the Sun) read by the same speakers who participated in the Phonetic Corpus of Estonian Spontaneous Speech. Most of the speakers read the text two times. The text is annotated using Praat TextGrids: words in standard orthography and phonemes in SAMPA.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f7830a62-76e4-5d52-8a03-66cc21295765",
-    "notes": [
-        "Abstract",
-        "Recordings of the tale \u201cP\u00f5hjatuul ja p\u00e4ike\u201d (North Wind and the Sun) read by the same speakers who participated in the Phonetic Corpus of Estonian Spontaneous Speech. Most of the speakers read the text two times. The text is annotated using Praat TextGrids: words in standard orthography and phonemes in SAMPA."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:6916097"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "P\u00f5hjatuule ja p\u00e4ikese korpus v.1.0.2",
-        "Estonian North Wind and the Sun Corpus v.1.0.2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f851e2fb-5560-5a60-99fd-0708c0aa24d8.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f851e2fb-5560-5a60-99fd-0708c0aa24d8.json
deleted file mode 100644
index 833fc439..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f851e2fb-5560-5a60-99fd-0708c0aa24d8.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-000FDL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:6892427",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:6892427"
-    ],
-    "PublicationTimestamp": "2015-10-20T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Kahusk, Neeme"
-    ],
-    "fulltext": "oai:oai.datacite.org:6892427;2019-01-27T02:00:46Z;ESTDOI;ESTDOI.KEEL;Poetry corpus;Kahusk, Neeme;Center of Estonian Language Resources;2015;Issued: 2015-10-20;Updated: 2015-10-20;doi:10.15155/1-00-0000-0000-0000-000FDL;Abstract;Demo",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f851e2fb-5560-5a60-99fd-0708c0aa24d8",
-    "notes": [
-        "Abstract",
-        "Demo"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:6892427"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Poetry corpus"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f90591df-c6f6-5a89-8701-878ec07adcbd.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f90591df-c6f6-5a89-8701-878ec07adcbd.json
deleted file mode 100644
index a9626ee9..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f90591df-c6f6-5a89-8701-878ec07adcbd.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00183L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:17950839",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17950839"
-    ],
-    "PublicationTimestamp": "2019-01-04T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Iva, Sulev"
-    ],
-    "fulltext": "oai:oai.datacite.org:17950839;2019-01-04T12:02:36Z;ESTDOI;ESTDOI.KEEL;V\u00f5ro ja seto kirjanduskogu;Iva, Sulev;Center of Estonian Language Resources;2019;Issued: 2019-01-04;Updated: 2019-01-04;doi:10.15155/1-00-0000-0000-0000-00183L;Abstract;Ilukirjanduse korpuse kogumahuks on ca 350 000 s\u00f5na, korpus on viimase aasta jooksul muudetud tekstiarhiivist avalikuks keelekorpuseks koos vajaliku kasutajaliidesega, mis asub aadressil http://synaq.org/ilo.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f90591df-c6f6-5a89-8701-878ec07adcbd",
-    "notes": [
-        "Abstract",
-        "Ilukirjanduse korpuse kogumahuks on ca 350 000 s\u00f5na, korpus on viimase aasta jooksul muudetud tekstiarhiivist avalikuks keelekorpuseks koos vajaliku kasutajaliidesega, mis asub aadressil http://synaq.org/ilo."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:17950839"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "V\u00f5ro ja seto kirjanduskogu"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f95b3e13-1fa1-5b6e-9b12-b93142e695d6.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f95b3e13-1fa1-5b6e-9b12-b93142e695d6.json
deleted file mode 100644
index 00a03074..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f95b3e13-1fa1-5b6e-9b12-b93142e695d6.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06342L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10304164",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10304164"
-    ],
-    "PublicationTimestamp": "2018-03-14T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Soon, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:10304164;2019-03-24T18:37:17Z;ESTDOI;ESTDOI.KEEL;Militerm;Militerm;Soon, Tiina;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2018-03-14;doi:10.15155/3-00-0000-0000-0000-06342L;Abstract;Militerm on s\u00f5janduse, julgeoleku- ja kaitsepoliitika terminite andmebaas, kus saab m\u00e4rks\u00f5nu otsida eesti, inglise, prantsuse ja saksa keeles. Eesti- ja ingliskeelsete terminite juures on ka oskuss\u00f5nade definitsioonid.;Abstract;Militerm is a database of military, security and defense terms, enabling search by Estonian, English, French and German keywords. The Estonian and English special terms are provided with definitions.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f95b3e13-1fa1-5b6e-9b12-b93142e695d6",
-    "notes": [
-        "Abstract",
-        "Militerm on s\u00f5janduse, julgeoleku- ja kaitsepoliitika terminite andmebaas, kus saab m\u00e4rks\u00f5nu otsida eesti, inglise, prantsuse ja saksa keeles. Eesti- ja ingliskeelsete terminite juures on ka oskuss\u00f5nade definitsioonid.",
-        "Abstract",
-        "Militerm is a database of military, security and defense terms, enabling search by Estonian, English, French and German keywords. The Estonian and English special terms are provided with definitions."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10304164"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Militerm",
-        "Militerm"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f9a2ba14-175a-59c1-9f8d-848cfc20da7f.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f9a2ba14-175a-59c1-9f8d-848cfc20da7f.json
deleted file mode 100644
index 2b2d4fff..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f9a2ba14-175a-59c1-9f8d-848cfc20da7f.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05AF7L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9310578",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9310578"
-    ],
-    "PublicationTimestamp": "2017-05-10T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Paet, Tiina"
-    ],
-    "fulltext": "oai:oai.datacite.org:9310578;2019-04-01T02:31:12Z;ESTDOI;ESTDOI.KEEL;V\u00f5\u00f5rs\u00f5nade leksikon;The Dictionary of Foreign Words;Paet, Tiina;Center of Estonian Language Resources;2016;Issued: 2016-10-19;Updated: 2017-05-10;doi:10.15155/3-00-0000-0000-0000-05AF7L;Abstract;Sisaldab 33 000 levinumat v\u00f5\u00f5rs\u00f5na, tsitaats\u00f5na, laens\u00f5na, l\u00fchendit, sententsi ja v\u00e4ljendit. See on esimene eestikeelne v\u00f5\u00f5rs\u00f5nakogu, mis esitab morfoloogilise info: k\u00e4\u00e4namise ja p\u00f6\u00f6ramise ning muutt\u00fc\u00fcbid. V\u00f5rreldes varasemate v\u00e4ljaannetega on lisatud uusi s\u00f5nu, uuendatud seletusi ning t\u00e4psustatud s\u00f5nade et\u00fcmoloogiat.\n\n\nV\u00e4\u00e4ri, Eduard; Kleis, Richard; Silvet, Johannes; Paet, Tiina; Rehemaa, Tuuli (2012). V\u00f5\u00f5rs\u00f5nade leksikon. Tallinn: Valgus.\n;Abstract;The lexicon contains 33,000 widespread words of plainly foreign origin, including citations, incompletely adapted loanwords, abbreviations, maxims and expressions. The  lexicon provides information on the orthography, inflection, semantics and etymology of the words; for many unadapted foreign words the pronunciation is given, both audio and written; the understanding and use of the words is facilitated by labels and cross-references.\n\n\nV\u00e4\u00e4ri, Eduard; Kleis, Richard; Silvet, Johannes; Paet, Tiina; Rehemaa, Tuuli (2012). V\u00f5\u00f5rs\u00f5nade leksikon [The Dictionary of Foreign Words]. Tallinn: Valgus.\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f9a2ba14-175a-59c1-9f8d-848cfc20da7f",
-    "notes": [
-        "Abstract",
-        "Sisaldab 33 000 levinumat v\u00f5\u00f5rs\u00f5na, tsitaats\u00f5na, laens\u00f5na, l\u00fchendit, sententsi ja v\u00e4ljendit. See on esimene eestikeelne v\u00f5\u00f5rs\u00f5nakogu, mis esitab morfoloogilise info: k\u00e4\u00e4namise ja p\u00f6\u00f6ramise ning muutt\u00fc\u00fcbid. V\u00f5rreldes varasemate v\u00e4ljaannetega on lisatud uusi s\u00f5nu, uuendatud seletusi ning t\u00e4psustatud s\u00f5nade et\u00fcmoloogiat.\n\n\nV\u00e4\u00e4ri, Eduard; Kleis, Richard; Silvet, Johannes; Paet, Tiina; Rehemaa, Tuuli (2012). V\u00f5\u00f5rs\u00f5nade leksikon. Tallinn: Valgus.\n",
-        "Abstract",
-        "The lexicon contains 33,000 widespread words of plainly foreign origin, including citations, incompletely adapted loanwords, abbreviations, maxims and expressions. The  lexicon provides information on the orthography, inflection, semantics and etymology of the words; for many unadapted foreign words the pronunciation is given, both audio and written; the understanding and use of the words is facilitated by labels and cross-references.\n\n\nV\u00e4\u00e4ri, Eduard; Kleis, Richard; Silvet, Johannes; Paet, Tiina; Rehemaa, Tuuli (2012). V\u00f5\u00f5rs\u00f5nade leksikon [The Dictionary of Foreign Words]. Tallinn: Valgus.\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9310578"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "V\u00f5\u00f5rs\u00f5nade leksikon",
-        "The Dictionary of Foreign Words"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f9da80fe-9048-5eb9-9e37-28e8ec5a939a.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f9da80fe-9048-5eb9-9e37-28e8ec5a939a.json
deleted file mode 100644
index 15683965..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/f9da80fe-9048-5eb9-9e37-28e8ec5a939a.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-06ADDL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:13041917",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:13041917"
-    ],
-    "PublicationTimestamp": "2017-11-20T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Koppel, Kristina",
-        "Kallas, Jelena"
-    ],
-    "fulltext": "oai:oai.datacite.org:13041917;2018-10-26T21:04:59Z;ESTDOI;ESTDOI.KEEL;Eesti keele \u00f5pikute korpus A1\u2013C1;Corpus of Estonian CERF-graded Coursebook Texts;Kallas, Jelena;Koppel, Kristina;Center of Estonian Language Resources;2017;Issued: 2017-11-20;Updated: 2017-11-20;doi:10.15155/3-00-0000-0000-0000-06ADDL;Abstract;Sisaldab A1, A2, B1, B2 ja C1 keeleoskustasemega eesti keele \u00f5ppijatele suunatud \u00f5pikute materjali. Korpuses  on u 500 000 s\u00f5net ning korpuses on m\u00e4rgendatud teksti\u00fcksused <text> (enamasti eristatakse harjutust, s\u00f5navaraplokki ja suuremat seotud teksti), tekstil\u00f5igud <paragraph> (\u00fchel real asuv tekst), laused <sentence> ja osalaused <clause>. Korpus on morfoloogiliselt m\u00e4rgendatud. \n\nKorpuses on kaheksa \u00f5pikut:\n1.      Pesti, M., Ahi, H. (2015). E nagu Eesti: eesti keele \u00f5pik algajatele. Tallinn: Kiri-Mari Kirjastus.\n2.      Kitsnik, M., Kingisepp, L. (2002). Avatud uksed: eesti keele \u00f5ppekomplekt kesk- ja k\u00f5rgtasemele: \u00f5pperaamat. Tallinn: TEA Kirjastus.\n3.      Kitsnik, M. (2012). Eesti keele \u00f5pik: B1, B2. Tallinn: M. Kitsnik.\n4.      Pesti, M., Ahi, H. (2015). Eesti keele \u00f5pik A1. Tallinn: Justiitsministeerium.\n5.      Pesti, M., Ahi, H. (2012). Eesti keele \u00f5pik A2. Tallinn: M. Pesti.\n6.      Pesti, M., Ahi, H. (2015). Eesti keele \u00f5pik B1. Tallinn: Justiitsministeerium.\n7.      Sooneste, M. (2007). Eesti keele \u00f5pik: vene \u00f5ppekeelega g\u00fcmnaasium: kesk- ja k\u00f5rgtase. Tallinn: Varrak.\n8.      Rammo, S., Teral, M., Klaas-Lang, B., Allik, M. (2012). Keel selgeks!: eesti keele \u00f5pik t\u00e4iskasvanutele. Tallinn: Avita\n\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "f9da80fe-9048-5eb9-9e37-28e8ec5a939a",
-    "notes": [
-        "Abstract",
-        "Sisaldab A1, A2, B1, B2 ja C1 keeleoskustasemega eesti keele \u00f5ppijatele suunatud \u00f5pikute materjali. Korpuses  on u 500 000 s\u00f5net ning korpuses on m\u00e4rgendatud teksti\u00fcksused <text> (enamasti eristatakse harjutust, s\u00f5navaraplokki ja suuremat seotud teksti), tekstil\u00f5igud <paragraph> (\u00fchel real asuv tekst), laused <sentence> ja osalaused <clause>. Korpus on morfoloogiliselt m\u00e4rgendatud. \n\nKorpuses on kaheksa \u00f5pikut:\n1.      Pesti, M., Ahi, H. (2015). E nagu Eesti: eesti keele \u00f5pik algajatele. Tallinn: Kiri-Mari Kirjastus.\n2.      Kitsnik, M., Kingisepp, L. (2002). Avatud uksed: eesti keele \u00f5ppekomplekt kesk- ja k\u00f5rgtasemele: \u00f5pperaamat. Tallinn: TEA Kirjastus.\n3.      Kitsnik, M. (2012). Eesti keele \u00f5pik: B1, B2. Tallinn: M. Kitsnik.\n4.      Pesti, M., Ahi, H. (2015). Eesti keele \u00f5pik A1. Tallinn: Justiitsministeerium.\n5.      Pesti, M., Ahi, H. (2012). Eesti keele \u00f5pik A2. Tallinn: M. Pesti.\n6.      Pesti, M., Ahi, H. (2015). Eesti keele \u00f5pik B1. Tallinn: Justiitsministeerium.\n7.      Sooneste, M. (2007). Eesti keele \u00f5pik: vene \u00f5ppekeelega g\u00fcmnaasium: kesk- ja k\u00f5rgtase. Tallinn: Varrak.\n8.      Rammo, S., Teral, M., Klaas-Lang, B., Allik, M. (2012). Keel selgeks!: eesti keele \u00f5pik t\u00e4iskasvanutele. Tallinn: Avita\n\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:13041917"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele \u00f5pikute korpus A1\u2013C1",
-        "Corpus of Estonian CERF-graded Coursebook Texts"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/fa95f461-d2f7-5416-b2a8-2d38bfbdf8df.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/fa95f461-d2f7-5416-b2a8-2d38bfbdf8df.json
deleted file mode 100644
index 6ab57bac..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/fa95f461-d2f7-5416-b2a8-2d38bfbdf8df.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/TY.0016",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:4597375",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:4597375"
-    ],
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:4597375;2019-02-01T23:31:58Z;ESTDOI;ESTDOI.KEEL;Aligned Estonian-Icelandic ICD-10;Muischnek, Kadri;Center of Estonian Language Resources;2013;doi:10.15155/TY.0016",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fa95f461-d2f7-5416-b2a8-2d38bfbdf8df",
-    "oai_identifier": [
-        "oai:oai.datacite.org:4597375"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Aligned Estonian-Icelandic ICD-10"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/fba0e7e5-00fe-5656-b96b-2d2955d084e5.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/fba0e7e5-00fe-5656-b96b-2d2955d084e5.json
deleted file mode 100644
index ae2e9a35..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/fba0e7e5-00fe-5656-b96b-2d2955d084e5.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-071E6L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14559947",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14559947"
-    ],
-    "PublicationTimestamp": "2018-03-26T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Koppel, Kristina",
-        "Kallas, Jelena"
-    ],
-    "fulltext": "oai:oai.datacite.org:14559947;2018-11-29T04:02:49Z;ESTDOI;ESTDOI.KEEL;Eesti keele \u00fchendkorpus 2017;Estonian National Corpus 2017;Kallas, Jelena;Koppel, Kristina;Center of Estonian Language Resources;2018;Issued: 2018-03-26;Updated: 2018-03-26;doi:10.15155/3-00-0000-0000-0000-071E6L;Abstract;Korpus on loodud Eesti Keele Instituudi ja Lexical Computing Ltd. koost\u00f6\u00f6 raames. Korpuse suurus on 1,3 miljardit s\u00f5net. Korpuse alus on Eesti keele \u00fchendkorpus 2013, mida Lexical Computing Ltd. uuendas 2017. aastal Eesti Keele Instituudi tellimusel.\nAllkorpused on Eesti keele koondkorpus 1990-2008, Eesti keele veebikorpus 2013, Eesti keele veebikorpus 2017 ja Eesti Vikipeedia 2017 korpus. Veebikorpused on internetist alla laetud eestikeelsete veebilehtede korpus. Korpuse loomisel on kasutatud aadressil http://corpus.tools kirjeldatud programme: SpederLing, JustText, Chared, Onion and wiki2corpus. Korpus on lemmatiseeritud, m\u00e4rgendatud ja \u00fchestatud anal\u00fcsaatori EstNLTK abil. \n\n\n",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fba0e7e5-00fe-5656-b96b-2d2955d084e5",
-    "notes": [
-        "Abstract",
-        "Korpus on loodud Eesti Keele Instituudi ja Lexical Computing Ltd. koost\u00f6\u00f6 raames. Korpuse suurus on 1,3 miljardit s\u00f5net. Korpuse alus on Eesti keele \u00fchendkorpus 2013, mida Lexical Computing Ltd. uuendas 2017. aastal Eesti Keele Instituudi tellimusel.\nAllkorpused on Eesti keele koondkorpus 1990-2008, Eesti keele veebikorpus 2013, Eesti keele veebikorpus 2017 ja Eesti Vikipeedia 2017 korpus. Veebikorpused on internetist alla laetud eestikeelsete veebilehtede korpus. Korpuse loomisel on kasutatud aadressil http://corpus.tools kirjeldatud programme: SpederLing, JustText, Chared, Onion and wiki2corpus. Korpus on lemmatiseeritud, m\u00e4rgendatud ja \u00fchestatud anal\u00fcsaatori EstNLTK abil. \n\n\n"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14559947"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti keele \u00fchendkorpus 2017",
-        "Estonian National Corpus 2017"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/fc3a74a8-0e76-5fe2-9aa5-5925b29c2fef.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/fc3a74a8-0e76-5fe2-9aa5-5925b29c2fef.json
deleted file mode 100644
index cc1f863c..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/fc3a74a8-0e76-5fe2-9aa5-5925b29c2fef.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-0633FL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10304126",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10304126"
-    ],
-    "PublicationTimestamp": "2017-01-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Raadik, Maire"
-    ],
-    "fulltext": "oai:oai.datacite.org:10304126;2018-10-24T00:10:09Z;ESTDOI;ESTDOI.KEEL;Eesti Keele Instituudi isikunimeandmebaas;Raadik, Maire;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2017-01-31;doi:10.15155/3-00-0000-0000-0000-0633FL;Abstract;Eesti perekonnanimede andmebaasist saab vaadata, kuidas k\u00e4\u00e4nduvad eesti perekonnanimed. Iga nime puhul on peale nimetava k\u00e4\u00e4nde n\u00e4idatud omastava, osastava ja alale\u00fctleva k\u00e4\u00e4nde vorm. Kui nime saab k\u00e4\u00e4nata mitut moodi, on antud k\u00f5ik v\u00f5imalused.",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fc3a74a8-0e76-5fe2-9aa5-5925b29c2fef",
-    "notes": [
-        "Abstract",
-        "Eesti perekonnanimede andmebaasist saab vaadata, kuidas k\u00e4\u00e4nduvad eesti perekonnanimed. Iga nime puhul on peale nimetava k\u00e4\u00e4nde n\u00e4idatud omastava, osastava ja alale\u00fctleva k\u00e4\u00e4nde vorm. Kui nime saab k\u00e4\u00e4nata mitut moodi, on antud k\u00f5ik v\u00f5imalused."
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10304126"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Eesti Keele Instituudi isikunimeandmebaas"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/fdc5a928-2ff6-53d9-ba44-7730bae3a087.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/fdc5a928-2ff6-53d9-ba44-7730bae3a087.json
deleted file mode 100644
index 7bf713b2..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/fdc5a928-2ff6-53d9-ba44-7730bae3a087.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/1-00-0000-0000-0000-00159L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:14614863",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14614863"
-    ],
-    "PublicationTimestamp": "2018-04-05T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Laur, Sven"
-    ],
-    "fulltext": "oai:oai.datacite.org:14614863;2019-02-23T20:30:57Z;ESTDOI;ESTDOI.KEEL;Koond-ner;Laur, Sven;Center of Estonian Language Resources;2018;Issued: 2018-04-05;Updated: 2018-04-05;doi:10.15155/1-00-0000-0000-0000-00159L;Abstract;Estonian Reference Corpus with NER annotations",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fdc5a928-2ff6-53d9-ba44-7730bae3a087",
-    "notes": [
-        "Abstract",
-        "Estonian Reference Corpus with NER annotations"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:14614863"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Koond-ner"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/fe3ad136-6293-5d25-91ef-0d02c089a41c.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/fe3ad136-6293-5d25-91ef-0d02c089a41c.json
deleted file mode 100644
index 61be41c0..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/fe3ad136-6293-5d25-91ef-0d02c089a41c.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/TY.0015",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:4597374",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:4597374"
-    ],
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Muischnek, Kadri"
-    ],
-    "fulltext": "oai:oai.datacite.org:4597374;2019-04-15T21:03:24Z;ESTDOI;ESTDOI.KEEL;Estonian-Latvian Parallel Corpus of building product texts;Muischnek, Kadri;Center of Estonian Language Resources;2013;doi:10.15155/TY.0015",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fe3ad136-6293-5d25-91ef-0d02c089a41c",
-    "oai_identifier": [
-        "oai:oai.datacite.org:4597374"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "Estonian-Latvian Parallel Corpus of building product texts"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/fe784d3d-9034-5fc4-a79a-748e220c33f3.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/fe784d3d-9034-5fc4-a79a-748e220c33f3.json
deleted file mode 100644
index 0fd0b9b0..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/fe784d3d-9034-5fc4-a79a-748e220c33f3.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-05B48L",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:9352866",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:9352866"
-    ],
-    "PublicationTimestamp": "2016-10-31T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Hein, Indrek",
-        "Langemets, Margit"
-    ],
-    "fulltext": "oai:oai.datacite.org:9352866;2019-04-04T23:01:30Z;ESTDOI;ESTDOI.KEEL;L\u00e4ti-eesti s\u00f5naraamat;Hein, Indrek;Langemets, Margit;Center of Estonian Language Resources;2016;Issued: 2016-10-31;Updated: 2016-10-31;doi:10.15155/3-00-0000-0000-0000-05B48L;Abstract;Kahesuunaline l\u00e4ti-eesti s\u00f5naraamat, mis sisaldab ligi 47 000 m\u00e4rks\u00f5naartiklit. ",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fe784d3d-9034-5fc4-a79a-748e220c33f3",
-    "notes": [
-        "Abstract",
-        "Kahesuunaline l\u00e4ti-eesti s\u00f5naraamat, mis sisaldab ligi 47 000 m\u00e4rks\u00f5naartiklit. "
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:9352866"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "L\u00e4ti-eesti s\u00f5naraamat"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/fe8676c2-208d-5912-9501-87e7ba57a061.json b/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/fe8676c2-208d-5912-9501-87e7ba57a061.json
deleted file mode 100644
index 1a44d037..00000000
--- a/oaitestdata/clarin-oai_dc/estdoi.keel_1/json/fe8676c2-208d-5912-9501-87e7ba57a061.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "Center of Estonian Language Resources"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.15155/3-00-0000-0000-0000-0632DL",
-    "DiscHierarchy": [
-        "1.4",
-        "Humanities",
-        "Linguistics"
-    ],
-    "Discipline": "Linguistics",
-    "MetaDataAccess": "https://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.datacite.org:10303797",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:10303797"
-    ],
-    "PublicationTimestamp": "2017-01-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Center of Estonian Language Resources"
-    ],
-    "author": [
-        "Mihkla, Meelis"
-    ],
-    "fulltext": "oai:oai.datacite.org:10303797;2019-03-29T14:02:31Z;ESTDOI;ESTDOI.KEEL;V\u00f5ru murde HTS-s\u00fcntesaator;Mihkla, Meelis;Center of Estonian Language Resources;2017;Issued: 2017-01-31;Updated: 2017-01-31;doi:10.15155/3-00-0000-0000-0000-0632DL;Abstract;V\u00f5ru murde HTS-s\u00fcntesaator",
-    "group": "clarin",
-    "groups": [
-        {
-            "name": "clarin"
-        }
-    ],
-    "name": "fe8676c2-208d-5912-9501-87e7ba57a061",
-    "notes": [
-        "Abstract",
-        "V\u00f5ru murde HTS-s\u00fcntesaator"
-    ],
-    "oai_identifier": [
-        "oai:oai.datacite.org:10303797"
-    ],
-    "oai_set": [
-        "ESTDOI",
-        "ESTDOI.KEEL"
-    ],
-    "state": "active",
-    "title": [
-        "V\u00f5ru murde HTS-s\u00fcntesaator"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/D10000_1/json/feb75c69-ab98-5271-95e6-b51a0dc888a2.json b/oaitestdata/danseasy-oai_datacite/D10000_1/json/feb75c69-ab98-5271-95e6-b51a0dc888a2.json
deleted file mode 100644
index 9457779a..00000000
--- a/oaitestdata/danseasy-oai_datacite/D10000_1/json/feb75c69-ab98-5271-95e6-b51a0dc888a2.json
+++ /dev/null
@@ -1,119 +0,0 @@
-{
-    "Contact": [
-        "KNMI",
-        "K\u00f6nnen, G.K."
-    ],
-    "Contributor": [
-        "K\u00f6nnen, G.K."
-    ],
-    "DOI": "http://dx.doi.org/doi:10.17026/dans-z8k-d35z",
-    "DiscHierarchy": [
-        "1.5.9",
-        "Literary Studies",
-        "Poetry"
-    ],
-    "Discipline": "History",
-    "Format": [
-        "text/csv",
-        "image/jpeg",
-        "application/vnd.ms-access"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:101879",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:101879"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Data Archiving and Networked Services (DANS)"
-    ],
-    "RelatedIdentifier": [
-        "10.17026/dans-ze8-d3c8",
-        "10.17026/dans-x7n-2y6x",
-        "10.17026/dans-2bx-dutg"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "TempCoverageBegin": 63177019199,
-    "TempCoverageEnd": 63663274799,
-    "TemporalCoverage": " period : ( 2003-01-01T11:59:59Z - 2018-05-30T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2003-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-05-30T11:59:59Z",
-    "author": [
-        "Koek, F.B.",
-        "KNMI (Koninklijk Nederlands Meteorologisch Instituut; Royal Netherlands Meteorological Institute)"
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:101879;2018-12-19T05:26:14Z;D30000:D34000:D34300;D10000:D15000:D15500;easy-collection:6;10.17026/dans-z8k-d35z;Koek, F.B.;KNMI;KNMI (Koninklijk Nederlands Meteorologisch Instituut; Royal Netherlands Meteorological Institute);KNMI (Koninklijk Nederlands Meteorologisch Instituut; Royal Netherlands Meteorological Institute);Zeeland 1786;Reis van Vlissingen naar Colombo;Reis van Vlissingen naar Colombo;Data Archiving and Networked Services (DANS);2018;Modern and contemporary\n                        history;Atmospheric sciences;meteorologie;scheepshistorie;geografie;geschiedenis van de handel;economische geschiedenis;militaire geschiedenis;transportstudies;zeilschip-logboeken;weer-observaties;nautische weer-vocabulaires;historische mariene gegevens;geografische mobiliteit;koloniale handel;Temporal coverage: 1786;K\u00f6nnen, G.K.;KNMI;2003-01-01;2018-05-30;nl;Dataset;urn:nbn:nl:ui:13-ha-t2b9;easy-dataset:101879;10.17026/dans-ze8-d3c8;10.17026/dans-x7n-2y6x;10.17026/dans-2bx-dutg;application/vnd.ms-access;text/csv;image/jpeg;info:eu-repo/semantics/openAccess;Hoofddoel van het CLIWOC-project was het benutten van klimaatgegevens uit scheepsjournaals voor het aanleggen van een database van dagelijkse weer-observaties voor oceanen uit de periode 1750 - 1850. Een van de belangrijkste resultaten van het project is een database met gegevens uit Britse, Nederlandse, Franse en Spaanse scheepsjournaals uit de pre-industri\u00eble periode (1750 - 1853).\n\nTijdens de oorspronkelijke gegevensverzameling in de periode december 2000 tot en met november 2003 werden per scheepsreis gegevens verzameld in MS Access databases. Deze dataset bevat een oorspronkelijke database samen met de afbeeldingen van het bijbehorende scheepsjournaal.;Vlissingen;Ten anker gelegen na de rhede van colombos;Colombo;Anker van boord",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "feb75c69-ab98-5271-95e6-b51a0dc888a2",
-    "notes": [
-        "Hoofddoel van het CLIWOC-project was het benutten van klimaatgegevens uit scheepsjournaals voor het aanleggen van een database van dagelijkse weer-observaties voor oceanen uit de periode 1750 - 1850. Een van de belangrijkste resultaten van het project is een database met gegevens uit Britse, Nederlandse, Franse en Spaanse scheepsjournaals uit de pre-industri\u00eble periode (1750 - 1853).\n\nTijdens de oorspronkelijke gegevensverzameling in de periode december 2000 tot en met november 2003 werden per scheepsreis gegevens verzameld in MS Access databases. Deze dataset bevat een oorspronkelijke database samen met de afbeeldingen van het bijbehorende scheepsjournaal."
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:101879"
-    ],
-    "oai_set": [
-        "D30000:D34000:D34300",
-        "D10000:D15000:D15500",
-        "easy-collection:6"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Modern contemporary"
-        },
-        {
-            "name": "history"
-        },
-        {
-            "name": "Atmospheric sciences"
-        },
-        {
-            "name": "meteorologie"
-        },
-        {
-            "name": "scheepshistorie"
-        },
-        {
-            "name": "geografie"
-        },
-        {
-            "name": "geschiedenis van de handel"
-        },
-        {
-            "name": "economische geschiedenis"
-        },
-        {
-            "name": "militaire geschiedenis"
-        },
-        {
-            "name": "transportstudies"
-        },
-        {
-            "name": "zeilschip-logboeken"
-        },
-        {
-            "name": "weer-observaties"
-        }
-    ],
-    "title": [
-        "Zeeland 1786",
-        "Reis van Vlissingen naar Colombo",
-        "Reis van Vlissingen naar Colombo"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/000a2a74-19a0-5897-9d24-2e2f3665f3b2.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/000a2a74-19a0-5897-9d24-2e2f3665f3b2.json
deleted file mode 100644
index 6cee8fd4..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/000a2a74-19a0-5897-9d24-2e2f3665f3b2.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Transect"
-    ],
-    "Contributor": [
-        "Transect"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.17026/dans-xyk-fp35",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "application/pdf"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:108036",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:108036"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Transect"
-    ],
-    "RelatedIdentifier": [
-        "https://archisarchief.cultureelerfgoed.nl/Archis2/Archeorapporten/38/AR33533"
-    ],
-    "ResourceType": [
-        "Dataset, Collection"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "SpatialCoverage": [
-        "\n            "
-    ],
-    "TempCoverageBegin": 63503002799,
-    "TempCoverageEnd": 63651182399,
-    "TemporalCoverage": " period : ( 2013-05-01T11:59:59Z - 2018-01-10T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2013-05-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-01-10T11:59:59Z",
-    "author": [
-        "Nales, T."
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:108036;2018-09-18T17:50:20Z;D30000:D37000;easy-collection:4;10.17026/dans-xyk-fp35;Nales, T.;Transect;Archeologisch bureauonderzoek en inventariserend veldonderzoek, Leidschendam, Duivenvoorde 262-396;Transect Rapport 287;Leidschendam - Duivenvoorde 286-396;Transect Rapport 287;Leidschendam - Duivenvoorde 286-396;Transect;2018;Archaeology;Transect;2013-05-01;2018-01-10;nl;Dataset;urn:nbn:nl:ui:13-hm-xhnb;easy-dataset:108036;https://archisarchief.cultureelerfgoed.nl/Archis2/Archeorapporten/38/AR33533;application/pdf;info:eu-repo/semantics/openAccess;Onderzoeksrapport;Leidschendam;Leidschendam-Voorburg;Zuid-Holland;Duivenvoorde 286-396;52.09773983;4.39327343",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "000a2a74-19a0-5897-9d24-2e2f3665f3b2",
-    "notes": [
-        "Onderzoeksrapport"
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:108036"
-    ],
-    "oai_set": [
-        "D30000:D37000",
-        "easy-collection:4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Archaeology"
-        }
-    ],
-    "title": [
-        "Archeologisch bureauonderzoek en inventariserend veldonderzoek, Leidschendam, Duivenvoorde 262-396",
-        "Transect Rapport 287",
-        "Leidschendam - Duivenvoorde 286-396",
-        "Transect Rapport 287",
-        "Leidschendam - Duivenvoorde 286-396"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/00a2c63c-fdd9-5f7c-b1ae-b66a3373c1fd.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/00a2c63c-fdd9-5f7c-b1ae-b66a3373c1fd.json
deleted file mode 100644
index 5a561cc2..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/00a2c63c-fdd9-5f7c-b1ae-b66a3373c1fd.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Periplus Archeomare",
-        "Muis, L.A."
-    ],
-    "Contributor": [
-        "Periplus Archeomare",
-        "Muis, L.A."
-    ],
-    "DOI": "http://dx.doi.org/doi:10.17026/dans-x56-3595",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "application/pdf"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:67826",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:67826"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Periplus Archeomare"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/restrictedAccess"
-    ],
-    "SpatialCoverage": [
-        "\n            ",
-        "\n            "
-    ],
-    "TempCoverageBegin": 63540413999,
-    "TempCoverageEnd": 63619559999,
-    "TemporalCoverage": " period : ( 2014-07-08T11:59:59Z - 2017-01-09T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2014-07-08T11:59:59Z",
-    "TemporalCoverage:EndDate": "2017-01-09T11:59:59Z",
-    "author": [
-        "Brenk, S. van den"
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:67826;2018-09-18T17:13:24Z;D30000:D37000;10.17026/dans-x56-3595;Brenk, S. van den;Periplus Archeomare;Vispassage en zoutwaterafvoersystemen Afsluitdijk;Inventariserend Veldonderzoek (opwaterfase);Periplus Archeomare;2017;Archaeology;Inventariserend veldonderzoek (opwaterfase);Muis, L.A.;Periplus Archeomare;Periplus Archeomare;2014-07-08;2017-01-09;nl;Dataset;urn:nbn:nl:ui:13-ciat-et;easy-dataset:67826;application/pdf;info:eu-repo/semantics/restrictedAccess;In opdracht van Van den Herik-Sliedrecht heeft Periplus Archeomare B.V. in samenwerking met DEEP B.V. een archeologisch inventariserend veldonderzoek (opwaterfase) uitgevoerd nabij de spuicomplexen van Den Oever en Kornwerderzand. Het onderzoek bestond uit een side scan sonar onderzoek van twee plangebieden van ca 22 hectare bij Kornwerderzand en 27 hectare bij Den Oever.\nTijdens het inventariserend veldonderzoek zijn binnen en rondom de plangebieden in totaal 56 side scan sonar contacten aangetroffen; 31 bij Kornwerderzand en 25 bij Den Oever. Het merendeel van deze over het algemeen kleine contacten is geclassificeerd als onbekend object en betreft waarschijnlijk recente objecten die verloren of gedumpt zijn.\nAan drie van de contacten is een archeologische verwachting toegekend. Dit betreffen drie (resten van) scheepswrakken. Deze objecten liggen in de Zuiderhaven langs de dijk van het sluiscomplex ver buiten de plangebieden en worden niet bedreigd door de voorgenomen werkzaamheden.\nTijdens het onderhavige onderzoek is alleen het bodemoppervlak van het gebied in kaart gebracht. Het is mogelijk dat zich nog archeologische resten in het gebied bevinden die geheel begraven zijn.\nDe plangebieden kunnen vanuit archeologisch oogpunt worden vrijgegeven voor de voorgenomen werkzaamheden. Als men tijdens de werkzaamheden onverwacht stuit op objecten of voorwerpen waarvan vermoed wordt dat deze een archeologische waarde kunnen vertegenwoordigen geldt een meldingsplicht conform de Monumentenwet. Het is aan te bevelen deze meldingsplicht met verwijzing naar de herziene Monumentenwet 2007 op te nemen in het uitvoeringsplan voor de geplande werkzaamheden.;Noord-Holland;Friesland;Gemeente Hollandskroon;Gemeente S\u00fbdwest-Frysl\u00e2n;Den Oever;Kornwerderzand;53.07493118;5.33309089;52.93657678;5.04723957",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "00a2c63c-fdd9-5f7c-b1ae-b66a3373c1fd",
-    "notes": [
-        "In opdracht van Van den Herik-Sliedrecht heeft Periplus Archeomare B.V. in samenwerking met DEEP B.V. een archeologisch inventariserend veldonderzoek (opwaterfase) uitgevoerd nabij de spuicomplexen van Den Oever en Kornwerderzand. Het onderzoek bestond uit een side scan sonar onderzoek van twee plangebieden van ca 22 hectare bij Kornwerderzand en 27 hectare bij Den Oever.\nTijdens het inventariserend veldonderzoek zijn binnen en rondom de plangebieden in totaal 56 side scan sonar contacten aangetroffen; 31 bij Kornwerderzand en 25 bij Den Oever. Het merendeel van deze over het algemeen kleine contacten is geclassificeerd als onbekend object en betreft waarschijnlijk recente objecten die verloren of gedumpt zijn.\nAan drie van de contacten is een archeologische verwachting toegekend. Dit betreffen drie (resten van) scheepswrakken. Deze objecten liggen in de Zuiderhaven langs de dijk van het sluiscomplex ver buiten de plangebieden en worden niet bedreigd door de voorgenomen werkzaamheden.\nTijdens het onderhavige onderzoek is alleen het bodemoppervlak van het gebied in kaart gebracht. Het is mogelijk dat zich nog archeologische resten in het gebied bevinden die geheel begraven zijn.\nDe plangebieden kunnen vanuit archeologisch oogpunt worden vrijgegeven voor de voorgenomen werkzaamheden. Als men tijdens de werkzaamheden onverwacht stuit op objecten of voorwerpen waarvan vermoed wordt dat deze een archeologische waarde kunnen vertegenwoordigen geldt een meldingsplicht conform de Monumentenwet. Het is aan te bevelen deze meldingsplicht met verwijzing naar de herziene Monumentenwet 2007 op te nemen in het uitvoeringsplan voor de geplande werkzaamheden."
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:67826"
-    ],
-    "oai_set": [
-        "D30000:D37000"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Archaeology"
-        },
-        {
-            "name": "Inventariserend veldonderzoek opwaterfase"
-        }
-    ],
-    "title": [
-        "Vispassage en zoutwaterafvoersystemen Afsluitdijk",
-        "Inventariserend Veldonderzoek (opwaterfase)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/00a6111e-4ef9-533a-8f0e-b3e5185306e2.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/00a6111e-4ef9-533a-8f0e-b3e5185306e2.json
deleted file mode 100644
index 31328ad7..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/00a6111e-4ef9-533a-8f0e-b3e5185306e2.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "VUhbs archeologie"
-    ],
-    "Contributor": [
-        "VUhbs archeologie"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.17026/dans-z7b-3f6w",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "application/pdf"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:109612",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:109612"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "VUhbs archeologie"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "SpatialCoverage": [
-        "\n            ",
-        "\n            "
-    ],
-    "TempCoverageBegin": 63667940399,
-    "TempCoverageEnd": 63667940399,
-    "TemporalCoverage": " period : ( 2018-07-23T11:59:59Z - 2018-07-23T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2018-07-23T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-07-23T11:59:59Z",
-    "author": [
-        "Hebinck, K.A."
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:109612;2018-09-18T17:52:16Z;D30000:D37000;driver;easy-collection:4;10.17026/dans-z7b-3f6w;Hebinck, K.A.;VUhbs archeologie;Archeologisch bureau- en booronderzoek voor  twee weilanddepots te Schoonrewoerd en Hei- en Boeicop,  gemeente Leerdam en Zederik;Zuidnederlandse Archeologische Notities 601;Zuidnederlandse Archeologische Notities 601;VUhbs archeologie;2018;Archaeology;VUhbs archeologie;2018-07-23;2018-07-23;nl;Dataset;urn:nbn:nl:ui:13-rh-v73e;easy-dataset:109612;application/pdf;info:eu-repo/semantics/openAccess;VUhbs archeologie heeft een archeologisch bureauonderzoek en verkennend booronderzoek uitgevoerd voor twee weilanddepots te Schoonrewoerd, gemeente Leerdam en Hei- en Boeicop, gemeente Zederik. Het voornemen is om binnen beide deelgebieden een slibdepot aan de leggen. De werkzaamheden die met deze ontwikkeling gepaard gaan, kunnen de bodem en eventueel aanwezige archeologische resten verstoren. Daarom heeft de opdrachtgever VUhbs archeologie verzocht voor het plangebied een bureauonderzoek en inventariserend veldonderzoek door middel van verkennende boringen uit te voeren, zodat meer inzicht wordt verkregen in de archeologische verwachting van het plangebied en of er aanvullend onderzoek noodzakelijk zal zijn.\nUit het bureauonderzoek en inventariserend veldonderzoek is gebleken dat de natuurlijke bodemopbouw, afgezien van de bouwvoor, nog geheel intact is. Doordat beide deelgebieden liggen op oever- en crevasseafzettingen van verschillende stroomgordels is er sprake van meerdere potenti\u00eble archeologische niveaus. Direct aan het maaiveld kunnen resten en/of sporen verwacht worden uit de periode vanaf de ontginning van het veengebied in de 11de eeuw. Doordat beide deelgebieden buiten het bebouwingslint liggen worden bewoningssporen op dit niveau niet verwacht en zullen enkel sporen van de ontginning en het latere agrarisch gebruik zoals (ontginnings)greppels e.d. aanwezig zijn. De kans hierop is echter klein. Hieronder zijn in beide deelgebieden, afgedekt door een dunne laag komafzettingen, afzettingen van de stroomgordel van Schoonrewoerd aanwezig. In deelgebied 1 gaat het om de uitloper van de oeverwal (top op 70 tot 150 cm -mv) waarop geen bewoningsresten worden verwacht. In deelgebied 2 betreft het een zandige crevasse (top op 50 tot 70 cm -mv) met nog een middelhoge archeologische verwachting. Echter, doordat deze afzettingen ook hier worden afgedekt door een laag komafzettingen, worden de mogelijk aanwezige resten niet bedreigd door de aanleg van het slibdepot. De grootste delen van beide deelgebieden waren echter gelegen in een laaggelegen komgebied met een lage archeologische verwachting. Op een lager niveau komen in beide deelgebieden binnen de komafzettingen nog twee uitlopers van een crevasse voor die mogelijk moet worden toegeschreven aan de stroomgordel van Middelkoop of een stroomgordel van vergelijkbare ouderdom. Beide uitlopers zullen echter niet aantrekkelijk geweest voor bewoning en hebben een lage archeologische verwachting. In deelgebied 1 bevindt zich hieronder nog een beddinggordel of goed ontwikkelde crevasse op het niveau van de stroomgordel van Kortenhoeven. In deelgebied 2 zijn in het uiterste noorden beddingafzettingen van deze stroomgordel aanwezig met ten zuiden daarvan de bijbehorende oeverafzettingen. In de top hiervan zijn geen archeologische indicatoren of duidelijke sporen van bodemvorming waargenomen. Hierdoor heeft dit niveau een lage tot middelhoge verwachting op resten uit het Meso- en Neolithicum. Doordat dit niveau niet bedreigd wordt door de voorgenomen werkzaamheden zal vervolgonderzoek niet noodzakelijk zijn. Geadviseerd wordt dan ook om beide deelgebieden vrij te geven voor het voorgenomen gebruik als weilanddepot.;Overheicop;Huibertweg;Schoonrewoerd;Hei- en Boeicop;Gemeente Leerdam;Gemeente Zederik;Zuid-Holland;51.92449688;5.08988389;51.92902893;5.07672515",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "00a6111e-4ef9-533a-8f0e-b3e5185306e2",
-    "notes": [
-        "VUhbs archeologie heeft een archeologisch bureauonderzoek en verkennend booronderzoek uitgevoerd voor twee weilanddepots te Schoonrewoerd, gemeente Leerdam en Hei- en Boeicop, gemeente Zederik. Het voornemen is om binnen beide deelgebieden een slibdepot aan de leggen. De werkzaamheden die met deze ontwikkeling gepaard gaan, kunnen de bodem en eventueel aanwezige archeologische resten verstoren. Daarom heeft de opdrachtgever VUhbs archeologie verzocht voor het plangebied een bureauonderzoek en inventariserend veldonderzoek door middel van verkennende boringen uit te voeren, zodat meer inzicht wordt verkregen in de archeologische verwachting van het plangebied en of er aanvullend onderzoek noodzakelijk zal zijn.\nUit het bureauonderzoek en inventariserend veldonderzoek is gebleken dat de natuurlijke bodemopbouw, afgezien van de bouwvoor, nog geheel intact is. Doordat beide deelgebieden liggen op oever- en crevasseafzettingen van verschillende stroomgordels is er sprake van meerdere potenti\u00eble archeologische niveaus. Direct aan het maaiveld kunnen resten en/of sporen verwacht worden uit de periode vanaf de ontginning van het veengebied in de 11de eeuw. Doordat beide deelgebieden buiten het bebouwingslint liggen worden bewoningssporen op dit niveau niet verwacht en zullen enkel sporen van de ontginning en het latere agrarisch gebruik zoals (ontginnings)greppels e.d. aanwezig zijn. De kans hierop is echter klein. Hieronder zijn in beide deelgebieden, afgedekt door een dunne laag komafzettingen, afzettingen van de stroomgordel van Schoonrewoerd aanwezig. In deelgebied 1 gaat het om de uitloper van de oeverwal (top op 70 tot 150 cm -mv) waarop geen bewoningsresten worden verwacht. In deelgebied 2 betreft het een zandige crevasse (top op 50 tot 70 cm -mv) met nog een middelhoge archeologische verwachting. Echter, doordat deze afzettingen ook hier worden afgedekt door een laag komafzettingen, worden de mogelijk aanwezige resten niet bedreigd door de aanleg van het slibdepot. De grootste delen van beide deelgebieden waren echter gelegen in een laaggelegen komgebied met een lage archeologische verwachting. Op een lager niveau komen in beide deelgebieden binnen de komafzettingen nog twee uitlopers van een crevasse voor die mogelijk moet worden toegeschreven aan de stroomgordel van Middelkoop of een stroomgordel van vergelijkbare ouderdom. Beide uitlopers zullen echter niet aantrekkelijk geweest voor bewoning en hebben een lage archeologische verwachting. In deelgebied 1 bevindt zich hieronder nog een beddinggordel of goed ontwikkelde crevasse op het niveau van de stroomgordel van Kortenhoeven. In deelgebied 2 zijn in het uiterste noorden beddingafzettingen van deze stroomgordel aanwezig met ten zuiden daarvan de bijbehorende oeverafzettingen. In de top hiervan zijn geen archeologische indicatoren of duidelijke sporen van bodemvorming waargenomen. Hierdoor heeft dit niveau een lage tot middelhoge verwachting op resten uit het Meso- en Neolithicum. Doordat dit niveau niet bedreigd wordt door de voorgenomen werkzaamheden zal vervolgonderzoek niet noodzakelijk zijn. Geadviseerd wordt dan ook om beide deelgebieden vrij te geven voor het voorgenomen gebruik als weilanddepot."
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:109612"
-    ],
-    "oai_set": [
-        "D30000:D37000",
-        "driver",
-        "easy-collection:4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Archaeology"
-        }
-    ],
-    "title": [
-        "Archeologisch bureau- en booronderzoek voor  twee weilanddepots te Schoonrewoerd en Hei- en Boeicop,  gemeente Leerdam en Zederik",
-        "Zuidnederlandse Archeologische Notities 601",
-        "Zuidnederlandse Archeologische Notities 601"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/00ba9a4d-5561-5145-83e9-897349bc13f9.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/00ba9a4d-5561-5145-83e9-897349bc13f9.json
deleted file mode 100644
index eefee264..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/00ba9a4d-5561-5145-83e9-897349bc13f9.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Jelsma, J.",
-        "De Steekproef bv"
-    ],
-    "Contributor": [
-        "Jelsma, J.",
-        "De Steekproef bv"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.17026/dans-zfa-kx3n",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "verschillende pagineringen"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:17410",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:17410"
-    ],
-    "PublicationTimestamp": "2009-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2009"
-    ],
-    "Publisher": [
-        "De Steekproef, archeologisch onderzoeks- en adviesbureau"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "SpatialCoverage": [
-        "\n            "
-    ],
-    "TemporalCoverage": [
-        "2009-11-05",
-        "2004",
-        "2009-11-05"
-    ],
-    "author": [
-        "Tulp, C."
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:17410;2018-09-18T16:43:12Z;D30000:D37000;driver;easy-collection:4;10.17026/dans-zfa-kx3n;Tulp, C.;Dieverbrug, bedrijventerrein;een inventariserend archeologisch veldonderzoek;STEEK 2004.04.5;een inventariserend archeologisch veldonderzoek;STEEK 2004.04.5;De Steekproef, archeologisch onderzoeks- en adviesbureau;2009;Archaeology;PROSPECTIE;Jelsma, J.;De Steekproef bv;2009-11-05;2004;2009-11-05;nl;Dataset;urn:nbn:nl:ui:13-5ql-6ih;easy-dataset:17410;twips.dans.knaw.nl-6341406837414247677-1257439560267;verschillende pagineringen;info:eu-repo/semantics/openAccess;onderzoeksrapport;Bedrijventerrein;Westerveld;Nederland;Dieverbrug;Drenthe;e-ne (MARC21);52.84683816;6.33570764",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "00ba9a4d-5561-5145-83e9-897349bc13f9",
-    "notes": [
-        "onderzoeksrapport"
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:17410"
-    ],
-    "oai_set": [
-        "D30000:D37000",
-        "driver",
-        "easy-collection:4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Archaeology"
-        },
-        {
-            "name": "PROSPECTIE"
-        }
-    ],
-    "title": [
-        "Dieverbrug, bedrijventerrein",
-        "een inventariserend archeologisch veldonderzoek",
-        "STEEK 2004.04.5",
-        "een inventariserend archeologisch veldonderzoek",
-        "STEEK 2004.04.5"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a0a1061-00cf-53f4-bf71-8c2ccc53a54d.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0a0a1061-00cf-53f4-bf71-8c2ccc53a54d.json
deleted file mode 100644
index c7750159..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a0a1061-00cf-53f4-bf71-8c2ccc53a54d.json
+++ /dev/null
@@ -1,107 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.17026/dans-zcx-hkhm",
-    "DiscHierarchy": [
-        "1.5.9",
-        "Literary Studies",
-        "Poetry"
-    ],
-    "Discipline": "Medicine;Humanities",
-    "Format": [
-        "PDF",
-        "STATA",
-        "SPSS"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:49438",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:49438"
-    ],
-    "PublicationTimestamp": "2012-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Data Archiving and Networked Services (DANS)"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/closedAccess"
-    ],
-    "TemporalCoverage": [
-        "2012-03-21",
-        "2011-03-10",
-        "2012-03-21"
-    ],
-    "author": [
-        "CentERdata - Institute for data collection and research - Tilburg University"
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:49438;2018-09-18T17:01:08Z;D40000:D42000:D42100;D60000:D67000;D60000:D61000;D50000:D52000;D30000:D33000;D20000:D24000;10.17026/dans-zcx-hkhm;CentERdata - Institute for data collection and research - Tilburg University;Recruitment Data;Data Archiving and Networked Services (DANS);2012;Behavioural and educational\n                        sciences;Educational theory;Life sciences, medicine and health care ;Health sciences;Political science;Humanities;Theology and religious\n                        studies;Social sciences;Leisure and recreation\n                        studies;Sociology;education;employment;labor;retirement;health;well-being;housing;household;income;property;investment;leisure;recreation;culture;politics;religion;Temporal coverage: 2007;Temporal coverage: 2009;2012-03-21;2011-03-10;2012-03-21;en;Dataset;urn:nbn:nl:ui:13-diy5-uv;easy-dataset:49438;SPSS;STATA;PDF;info:eu-repo/semantics/closedAccess;This project describes data of all recruitment waves for the LISS panel.\n\n-Main Recruitment Wave 2007\n-Additional Recruitment Wave 2009;The Netherlands",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0a0a1061-00cf-53f4-bf71-8c2ccc53a54d",
-    "notes": [
-        "This project describes data of all recruitment waves for the LISS panel.\n\n-Main Recruitment Wave 2007\n-Additional Recruitment Wave 2009"
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:49438"
-    ],
-    "oai_set": [
-        "D40000:D42000:D42100",
-        "D60000:D67000",
-        "D60000:D61000",
-        "D50000:D52000",
-        "D30000:D33000",
-        "D20000:D24000"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Behavioural educational"
-        },
-        {
-            "name": "sciences"
-        },
-        {
-            "name": "Educational theory"
-        },
-        {
-            "name": "Life sciences"
-        },
-        {
-            "name": "medicine health care"
-        },
-        {
-            "name": "Health sciences"
-        },
-        {
-            "name": "Political science"
-        },
-        {
-            "name": "Humanities"
-        },
-        {
-            "name": "Theology religious"
-        },
-        {
-            "name": "studies"
-        },
-        {
-            "name": "Social sciences"
-        },
-        {
-            "name": "Leisure recreation"
-        }
-    ],
-    "title": [
-        "Recruitment Data"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a0c2f7f-66c1-538e-a5c9-033c9accca43.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0a0c2f7f-66c1-538e-a5c9-033c9accca43.json
deleted file mode 100644
index aa7e20e0..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a0c2f7f-66c1-538e-a5c9-033c9accca43.json
+++ /dev/null
@@ -1,94 +0,0 @@
-{
-    "Contact": [
-        "ATRIA",
-        "drs. Josien Pieterse (interviewer)",
-        "drs. Grietje Keller (projectleider Aletta)",
-        "prof. dr. Saskia Wieringa (projectleider Aletta)"
-    ],
-    "Contributor": [
-        "ATRIA",
-        "drs. Josien Pieterse (interviewer)",
-        "drs. Grietje Keller (projectleider Aletta)",
-        "prof. dr. Saskia Wieringa (projectleider Aletta)"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.17026/dans-x4r-qtx3",
-    "DiscHierarchy": [
-        "1.2",
-        "Humanities",
-        "History"
-    ],
-    "Discipline": "History",
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:41857",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:41857"
-    ],
-    "PublicationTimestamp": "2010-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "Data Archiving and Networked Services (DANS)"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/restrictedAccess"
-    ],
-    "TempCoverageBegin": 63382042799,
-    "TempCoverageEnd": 63413578799,
-    "TemporalCoverage": " period : ( 2009-07-01T11:59:59Z - 2010-07-01T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2009-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2010-07-01T11:59:59Z",
-    "author": [
-        "Aletta, instituut voor vrouwengeschiedenis"
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:41857;2018-09-18T16:57:11Z;D30000:D34000:D34300;easy-collection:2:3;D60000;easy-collection:1;10.17026/dans-x4r-qtx3;Aletta, instituut voor vrouwengeschiedenis;Aletta, instituut voor vrouwengeschiedenis;Thematische collectie: Erfgoed van de Oorlog, Getuigen Verhalen, Project 'Vrouwen van de CPN';Data Archiving and Networked Services (DANS);2010;Modern and contemporary\n                        history;Social sciences;erfgoed van de oorlog;getuigen verhalen;oral history;drs. Josien Pieterse (interviewer);drs. Grietje Keller (projectleider Aletta);prof. dr. Saskia Wieringa (projectleider Aletta);ATRIA;2009;2010-07-01;nl;Dataset;urn:nbn:nl:ui:13-bo6-6ug;easy-dataset:41857;twips.dans.knaw.nl--4897644017937809638-1276687228409;info:eu-repo/semantics/restrictedAccess;Tijdens de oorlog hadden communisten een grote rol in de illegaliteit. Na de oorlog verdween echter hun aureool van moed en verzet al snel onder invloed van de Koude Oorlog.\n\nIn dit project zijn de persoonlijke ervaringen van een aantal CPN-vrouwen op beeld vastgelegd. Openhartig vertellen ze over hun politieke overtuiging, het lidmaatschap van de Communistische Partij Nederland, de Tweede Wereldoorlog en de jaren erna, toen de CPN in een isolement raakte.  \n\nIn veel gevallen waren de vrouwen al vroeg bewust van de opkomst van het fascisme. Vanaf 1933 maakten zij mee hoe Duitse vluchtelingen werden opgevangen door familie of bekenden. Velen raakten een paar jaar later betrokken bij de Spaanse Burgeroorlog. Verzet bieden tegen de Duitse bezetter was voor hen een vanzelfsprekende keuze.\n\nIn de interviews vertellen zij over hun ervaringen als koerierster, distributeur van bonnenkaarten of bezorger van de illegale Waarheid. In sommige gesprekken gaat het ook over het gewapend verzet, internering en onderduik. Kenmerkend is dat alle vrouwen nadrukkelijk praten over de consequenties van dit alles voor hun verdere (politieke) leven. De oorlog bleek voor vrijwel alle vrouwen richtinggevend.;Nederland",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0a0c2f7f-66c1-538e-a5c9-033c9accca43",
-    "notes": [
-        "Tijdens de oorlog hadden communisten een grote rol in de illegaliteit. Na de oorlog verdween echter hun aureool van moed en verzet al snel onder invloed van de Koude Oorlog.\n\nIn dit project zijn de persoonlijke ervaringen van een aantal CPN-vrouwen op beeld vastgelegd. Openhartig vertellen ze over hun politieke overtuiging, het lidmaatschap van de Communistische Partij Nederland, de Tweede Wereldoorlog en de jaren erna, toen de CPN in een isolement raakte.  \n\nIn veel gevallen waren de vrouwen al vroeg bewust van de opkomst van het fascisme. Vanaf 1933 maakten zij mee hoe Duitse vluchtelingen werden opgevangen door familie of bekenden. Velen raakten een paar jaar later betrokken bij de Spaanse Burgeroorlog. Verzet bieden tegen de Duitse bezetter was voor hen een vanzelfsprekende keuze.\n\nIn de interviews vertellen zij over hun ervaringen als koerierster, distributeur van bonnenkaarten of bezorger van de illegale Waarheid. In sommige gesprekken gaat het ook over het gewapend verzet, internering en onderduik. Kenmerkend is dat alle vrouwen nadrukkelijk praten over de consequenties van dit alles voor hun verdere (politieke) leven. De oorlog bleek voor vrijwel alle vrouwen richtinggevend."
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:41857"
-    ],
-    "oai_set": [
-        "D30000:D34000:D34300",
-        "easy-collection:2:3",
-        "D60000",
-        "easy-collection:1"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Modern contemporary"
-        },
-        {
-            "name": "history"
-        },
-        {
-            "name": "Social sciences"
-        },
-        {
-            "name": "erfgoed van de oorlog"
-        },
-        {
-            "name": "getuigen verhalen"
-        },
-        {
-            "name": "oral history"
-        }
-    ],
-    "title": [
-        "Thematische collectie: Erfgoed van de Oorlog, Getuigen Verhalen, Project 'Vrouwen van de CPN'"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a1c1785-c559-51f2-9742-f5ce2caa3d13.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0a1c1785-c559-51f2-9742-f5ce2caa3d13.json
deleted file mode 100644
index b8fa3bf3..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a1c1785-c559-51f2-9742-f5ce2caa3d13.json
+++ /dev/null
@@ -1,95 +0,0 @@
-{
-    "Contact": [
-        "Archeologisch Onderzoek Leiden BV"
-    ],
-    "Contributor": [
-        "Archeologisch Onderzoek Leiden BV"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.17026/dans-xfq-xcd4",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "image/jpeg",
-        "application/mdb",
-        "application/pdf",
-        "application/mapinfo (MapInfo 7.0)",
-        "text/plain",
-        "application/msword"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:40454",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:40454"
-    ],
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Archeologisch Onderzoek Leiden BV"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "SpatialCoverage": [
-        "\n            "
-    ],
-    "TemporalCoverage": [
-        "2011-06-20",
-        "2009",
-        "2009",
-        "2011-06-20"
-    ],
-    "author": [
-        "Bos, P.A. van den",
-        "Archeologisch Onderzoek Leiden BV"
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:40454;2018-09-18T16:56:06Z;D30000:D37000;10.17026/dans-xfq-xcd4;Archeologisch Onderzoek Leiden BV;Bos, P.A. van den;Verkavelingsporen uit de middeleeuwen en nieuwe tijd aan de voet van de strandwal te Oegstgeest.;Inventariserend proefsleuvenonderzoek in het kader van de uitbreiding van de begraafplaats bij het Groene Kerkje.;Archeologisch Onderzoek Leiden BV;2011;Archaeology;Archeologisch: proefputten/proefsleuven;Infrastructuur - Percelering/verkaveling (IPER);Onbekend (XXX);Middeleeuwen laat: 1050 - 1500 nC (LME);Nieuwe tijd: 1500 - heden (NT);Archeologisch Onderzoek Leiden BV;2011-06-20;2009;2009;2011-06-20;nl;Dataset;urn:nbn:nl:ui:13-gsx-e7a;easy-dataset:40454;twips.dans.knaw.nl--4244080791836446187-1308576190110;application/mapinfo (MapInfo 7.0);application/mdb;application/pdf;application/msword;text/plain;image/jpeg;info:eu-repo/semantics/openAccess;Archeologisch Onderzoek Leiden bv (Archol bv) heeft een archeologisch inventariserend onderzoek uitgevoerd bij het Groene kerkje, tussen de A44 en de Haarlemmerstraatweg, te Oegstgeest. \nDe bodemopbouw van het plangebied kenmerkt zich door een strandwal met aan de buitenzijde (westen) een pakket van afwisselend veen en klastische afzettingen met laklagen. Vooronderzoek en aanvullende informatie van luchtfoto\u00bfs en historische bronnen gaven aanleiding om bewoningssporen uit de middeleeuwen en nieuwe tijd te verwachten.\n\nTijdens het onderzoek van Archol zijn vijf proefsleuven haaks op en parallel aan de strandwal gegraven. De flank van de strandwal blijkt binnen het plangebied geen archeologische sporen te bevatten. Ook het pakket veen en klastische afzettingen aan de buitenzijde van de strandwal heeft geen bewoningssporen opgeleverd. Het plangebied bevat enkel verkavelingssloten en -greppels uit de middeleeuwen en nieuwe tijd, die zich beperken tot de drassige laagte aan de voet van de strandwal. Deze laagte blijkt eeuwenlang in gebruik te zijn geweest als wei- en hooiland. ;30F;Groene Kerkje;Oegstgeest;Zuid-Holland;52.19576891;4.46760116",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0a1c1785-c559-51f2-9742-f5ce2caa3d13",
-    "notes": [
-        "Archeologisch Onderzoek Leiden bv (Archol bv) heeft een archeologisch inventariserend onderzoek uitgevoerd bij het Groene kerkje, tussen de A44 en de Haarlemmerstraatweg, te Oegstgeest. \nDe bodemopbouw van het plangebied kenmerkt zich door een strandwal met aan de buitenzijde (westen) een pakket van afwisselend veen en klastische afzettingen met laklagen. Vooronderzoek en aanvullende informatie van luchtfoto\u00bfs en historische bronnen gaven aanleiding om bewoningssporen uit de middeleeuwen en nieuwe tijd te verwachten.\n\nTijdens het onderzoek van Archol zijn vijf proefsleuven haaks op en parallel aan de strandwal gegraven. De flank van de strandwal blijkt binnen het plangebied geen archeologische sporen te bevatten. Ook het pakket veen en klastische afzettingen aan de buitenzijde van de strandwal heeft geen bewoningssporen opgeleverd. Het plangebied bevat enkel verkavelingssloten en -greppels uit de middeleeuwen en nieuwe tijd, die zich beperken tot de drassige laagte aan de voet van de strandwal. Deze laagte blijkt eeuwenlang in gebruik te zijn geweest als wei- en hooiland. "
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:40454"
-    ],
-    "oai_set": [
-        "D30000:D37000"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Archaeology"
-        },
-        {
-            "name": "Archeologisch proefputten proefsleuven"
-        },
-        {
-            "name": "Infrastructuur - Percelering verkaveling IPER"
-        },
-        {
-            "name": "Onbekend XXX"
-        },
-        {
-            "name": "Middeleeuwen laat - nC LME"
-        },
-        {
-            "name": "Nieuwe tijd - heden NT"
-        }
-    ],
-    "title": [
-        "Verkavelingsporen uit de middeleeuwen en nieuwe tijd aan de voet van de strandwal te Oegstgeest.",
-        "Inventariserend proefsleuvenonderzoek in het kader van de uitbreiding van de begraafplaats bij het Groene Kerkje."
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a1dbc57-9ebd-5ab8-a581-b0ab36b635bd.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0a1dbc57-9ebd-5ab8-a581-b0ab36b635bd.json
deleted file mode 100644
index 7dbf2ffc..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a1dbc57-9ebd-5ab8-a581-b0ab36b635bd.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "RAAP Archeologisch Adviesbureau"
-    ],
-    "Contributor": [
-        "RAAP Archeologisch Adviesbureau"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.17026/dans-x2q-n6nt",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "application/pdf"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:107212",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:107212"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "RAAP Archeologisch Adviesbureau"
-    ],
-    "RelatedIdentifier": [
-        "https://archisarchief.cultureelerfgoed.nl/Archis2/Archeorapporten/28/AR28841"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "SpatialCoverage": [
-        "\n            "
-    ],
-    "TempCoverageBegin": 63434577599,
-    "TempCoverageEnd": 63651182399,
-    "TemporalCoverage": " period : ( 2011-03-01T11:59:59Z - 2018-01-10T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2011-03-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-01-10T11:59:59Z",
-    "author": [
-        "Timmerman, R."
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:107212;2018-09-18T17:49:04Z;D30000:D37000;easy-collection:4;10.17026/dans-x2q-n6nt;Timmerman, R.;RAAP Archeologisch Adviesbureau;Plangebied Essenstraat 9-15 te Haarlem Gemeente Haarlem Archeologisch vooronderzoek: een bureau- en inventariserend veldonderzoek;RAAP-notitie 3727;Haarlem - Essenstraat 9-15;HMES;RAAP-notitie 3727;Haarlem - Essenstraat 9-15;HMES;RAAP Archeologisch Adviesbureau;2018;Archaeology;RAAP Archeologisch Adviesbureau;2011-03-01;2018-01-10;nl;Dataset;urn:nbn:nl:ui:13-tb-u5wv;easy-dataset:107212;https://archisarchief.cultureelerfgoed.nl/Archis2/Archeorapporten/28/AR28841;application/pdf;info:eu-repo/semantics/openAccess;Onderzoeksrapport;Haarlem;Haarlem;Noord-Holland;Essenstraat 9-15;52.37746903;4.63764968",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0a1dbc57-9ebd-5ab8-a581-b0ab36b635bd",
-    "notes": [
-        "Onderzoeksrapport"
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:107212"
-    ],
-    "oai_set": [
-        "D30000:D37000",
-        "easy-collection:4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Archaeology"
-        }
-    ],
-    "title": [
-        "Plangebied Essenstraat 9-15 te Haarlem Gemeente Haarlem Archeologisch vooronderzoek: een bureau- en inventariserend veldonderzoek",
-        "RAAP-notitie 3727",
-        "Haarlem - Essenstraat 9-15",
-        "HMES",
-        "RAAP-notitie 3727",
-        "Haarlem - Essenstraat 9-15",
-        "HMES"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a2a3046-aa34-58ec-90b7-8abae17cd410.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0a2a3046-aa34-58ec-90b7-8abae17cd410.json
deleted file mode 100644
index 2848d63f..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a2a3046-aa34-58ec-90b7-8abae17cd410.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.5061/dryad.3450r",
-    "DiscHierarchy": [
-        "1.3.3",
-        "Fine Arts, Music, Theatre and Media Studies",
-        "Dance"
-    ],
-    "Discipline": "Medicine",
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:88263",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:88263"
-    ],
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Data Archiving and Networked Services (DANS)"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/closedAccess"
-    ],
-    "TempCoverageBegin": 63566679599,
-    "TempCoverageEnd": 63566679599,
-    "TemporalCoverage": " period : ( 2015-05-08T11:59:59Z - 2015-05-08T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2015-05-08T11:59:59Z",
-    "TemporalCoverage:EndDate": "2015-05-08T11:59:59Z",
-    "author": [
-        "Barber, Jesse R.",
-        "Kawahara, Akito Y."
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:88263;2018-09-18T17:31:18Z;D20000;Kawahara, Akito Y.;Barber, Jesse R.;Data from: Tempo and mode of antibat ultrasound production and sonar jamming in the diverse hawkmoth radiation;Data Archiving and Networked Services (DANS);2015;Life sciences, medicine and health care ;2015-05-08T17:03:26.000+02:00;2015-05-08T17:03:26.000+02:00;Dataset;10.5061/dryad.3450r;urn:nbn:nl:ui:13-lt-or97;easy-dataset:88263;info:eu-repo/semantics/closedAccess;The bat\u2013moth arms race has existed for over 60 million y, with moths evolving ultrasonically sensitive ears and ultrasound-producing organs to combat bat predation. The evolution of these defenses has never been thoroughly examined because of limitations in simultaneously conducting behavioral and phylogenetic analyses across an entire group. Hawkmoths include >1,500 species worldwide, some of which produce ultrasound using genital stridulatory structures. However, the function and evolution of this behavior remain largely unknown. We built a comprehensive behavioral dataset of hawkmoth hearing and ultrasonic reply to sonar attack using high-throughput field assays. Nearly half of the species tested (57 of 124 species) produced ultrasound to tactile stimulation or playback of bat echolocation attack. To test the function of ultrasound, we pitted big brown bats (Eptesicus fuscus) against hawkmoths over multiple nights and show that hawkmoths jam bat sonar. Ultrasound production was immediately and consistently effective at thwarting attack and bats regularly performed catching behavior without capturing moths. We also constructed a fossil-calibrated, multigene phylogeny to study the evolutionary history and divergence times of these antibat strategies across the entire family. We show that ultrasound production arose in multiple groups, starting in the late Oligocene (\u223c26 Ma) after the emergence of insectivorous bats. Sonar jamming and bat-detecting ears arose twice, independently, in the Miocene (18\u201314 Ma) either from earless hawkmoths that produced ultrasound in response to physical contact only, or from species that did not respond to touch or bat echolocation attack.",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0a2a3046-aa34-58ec-90b7-8abae17cd410",
-    "notes": [
-        "The bat\u2013moth arms race has existed for over 60 million y, with moths evolving ultrasonically sensitive ears and ultrasound-producing organs to combat bat predation. The evolution of these defenses has never been thoroughly examined because of limitations in simultaneously conducting behavioral and phylogenetic analyses across an entire group. Hawkmoths include >1,500 species worldwide, some of which produce ultrasound using genital stridulatory structures. However, the function and evolution of this behavior remain largely unknown. We built a comprehensive behavioral dataset of hawkmoth hearing and ultrasonic reply to sonar attack using high-throughput field assays. Nearly half of the species tested (57 of 124 species) produced ultrasound to tactile stimulation or playback of bat echolocation attack. To test the function of ultrasound, we pitted big brown bats (Eptesicus fuscus) against hawkmoths over multiple nights and show that hawkmoths jam bat sonar. Ultrasound production was immediately and consistently effective at thwarting attack and bats regularly performed catching behavior without capturing moths. We also constructed a fossil-calibrated, multigene phylogeny to study the evolutionary history and divergence times of these antibat strategies across the entire family. We show that ultrasound production arose in multiple groups, starting in the late Oligocene (\u223c26 Ma) after the emergence of insectivorous bats. Sonar jamming and bat-detecting ears arose twice, independently, in the Miocene (18\u201314 Ma) either from earless hawkmoths that produced ultrasound in response to physical contact only, or from species that did not respond to touch or bat echolocation attack."
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:88263"
-    ],
-    "oai_set": [
-        "D20000"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Life sciences"
-        },
-        {
-            "name": "medicine health care"
-        }
-    ],
-    "title": [
-        "Data from: Tempo and mode of antibat ultrasound production and sonar jamming in the diverse hawkmoth radiation"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a2b67db-1c77-5a04-83ea-bf65ba54a327.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0a2b67db-1c77-5a04-83ea-bf65ba54a327.json
deleted file mode 100644
index d24a0f39..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a2b67db-1c77-5a04-83ea-bf65ba54a327.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.5061/dryad.qt3j5",
-    "DiscHierarchy": [
-        "1.3.3",
-        "Fine Arts, Music, Theatre and Media Studies",
-        "Dance"
-    ],
-    "Discipline": "Medicine",
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:81596",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:81596"
-    ],
-    "PublicationTimestamp": "2012-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Data Archiving and Networked Services (DANS)"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/closedAccess"
-    ],
-    "TempCoverageBegin": 63477255599,
-    "TempCoverageEnd": 63477255599,
-    "TemporalCoverage": " period : ( 2012-07-07T11:59:59Z - 2012-07-07T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2012-07-07T11:59:59Z",
-    "TemporalCoverage:EndDate": "2012-07-07T11:59:59Z",
-    "author": [
-        "Jelen\u010di\u010d, Maja",
-        "Trontelj, Peter",
-        "Waits, Lisette P.",
-        "Skrbin\u0161ek, Toma\u017e",
-        "Poto\u010dnik, Hubert"
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:81596;2018-09-18T17:25:03Z;D20000;Skrbin\u0161ek, Toma\u017e;Jelen\u010di\u010d, Maja;Waits, Lisette P.;Poto\u010dnik, Hubert;Trontelj, Peter;Data from: Using a reference population yardstick to calibrate and compare genetic diversity reported in different studies: an example from the brown bear.;Data Archiving and Networked Services (DANS);2012;Life sciences, medicine and health care ;2012-07-07T00:16:49.000+02:00;2012-07-07T00:16:49.000+02:00;Dataset;10.5061/dryad.qt3j5;urn:nbn:nl:ui:13-02-js0l;easy-dataset:81596;info:eu-repo/semantics/closedAccess;In species with large geographic ranges, genetic diversity of different populations may be well studied, but differences in loci and sample sizes can make the results of different studies difficult to compare. Yet, such comparisons are important for assessing the status of populations of conservation concern. We propose a simple approach of using a single well-studied reference population as a \"yardstick\" to calibrate results of different studies to the same scale, enabling comparisons. We use a well-studied large carnivore, the brown bear (Ursus arctos), as a case study to demonstrate the approach. As a reference population, we genotyped 513 brown bears from Slovenia using 20 polymorphic microsatellite loci. We used this dataset to calibrate and compare heterozygosity and allelic richness for 30 brown bear populations from 10 different studies across the global distribution of the species. The simplicity of the reference population approach makes it useful for other species, enabling comparisons of genetic diversity estimates between previously incompatible studies and improving our understanding of how genetic diversity is distributed along a species range.",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0a2b67db-1c77-5a04-83ea-bf65ba54a327",
-    "notes": [
-        "In species with large geographic ranges, genetic diversity of different populations may be well studied, but differences in loci and sample sizes can make the results of different studies difficult to compare. Yet, such comparisons are important for assessing the status of populations of conservation concern. We propose a simple approach of using a single well-studied reference population as a \"yardstick\" to calibrate results of different studies to the same scale, enabling comparisons. We use a well-studied large carnivore, the brown bear (Ursus arctos), as a case study to demonstrate the approach. As a reference population, we genotyped 513 brown bears from Slovenia using 20 polymorphic microsatellite loci. We used this dataset to calibrate and compare heterozygosity and allelic richness for 30 brown bear populations from 10 different studies across the global distribution of the species. The simplicity of the reference population approach makes it useful for other species, enabling comparisons of genetic diversity estimates between previously incompatible studies and improving our understanding of how genetic diversity is distributed along a species range."
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:81596"
-    ],
-    "oai_set": [
-        "D20000"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Life sciences"
-        },
-        {
-            "name": "medicine health care"
-        }
-    ],
-    "title": [
-        "Data from: Using a reference population yardstick to calibrate and compare genetic diversity reported in different studies: an example from the brown bear."
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a2cb465-2bca-51ad-965f-b2dbc43ca1e1.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0a2cb465-2bca-51ad-965f-b2dbc43ca1e1.json
deleted file mode 100644
index 4f7bfb46..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a2cb465-2bca-51ad-965f-b2dbc43ca1e1.json
+++ /dev/null
@@ -1,112 +0,0 @@
-{
-    "Contact": [
-        "Drs. Monique Brinks, interviewster"
-    ],
-    "Contributor": [
-        "Drs. Monique Brinks, interviewster"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.17026/dans-xaz-5fnp",
-    "DiscHierarchy": [
-        "4.4",
-        "Natural Sciences",
-        "Geosciences"
-    ],
-    "Discipline": "History",
-    "Format": [
-        "video/quicktime",
-        "transcriptie: word",
-        "verklaring: jpg"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:41843",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:41843"
-    ],
-    "PublicationTimestamp": "2010-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "Data Archiving and Networked Services (DANS)"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess",
-        "License: http://creativecommons.org/publicdomain/zero/1.0"
-    ],
-    "TemporalCoverage": [
-        "2010-06-23",
-        "2009-11-24",
-        "2010-05-31"
-    ],
-    "author": [
-        "Stichting Oorlogs- en Verzetscentrum Groningen (OVCG)"
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:41843;2018-09-18T16:57:09Z;D30000:D34000:D34300;driver;easy-collection:2;easy-collection:1;10.17026/dans-xaz-5fnp;Stichting Oorlogs- en Verzetscentrum Groningen (OVCG);Stichting Oorlogs- en Verzetscentrum Groningen (OVCG);Groningen in Oorlogstijd, interview 06;Data Archiving and Networked Services (DANS);2010;Modern and contemporary\n                        history;Groningen;rooms-katholiek;eigen zaak;stoffenhandel;Seyss-Inquart;Rotterdam;Naber;Scholtenhuis;deken Buve;Veringa;inzamelingen van radio's;metaal en fietsen;HBS;vorderingen;tekorten;bevrijding;brand;Waagstraat;Guldenstraat;Martinuskerk;ondernemers in centrum Groningen;fotograaf Kramer;Rein Veld;Bertie Bossina;Tweede Wereldoorlog;oral history;Temporal coverage: Groningen;Drs. Monique Brinks, interviewster;2010-06-23;2009-11-24;2010-05-31;nl;Dataset;urn:nbn:nl:ui:13-uzi-4aq;easy-dataset:41843;twips.dans.knaw.nl-2635184198456718120-1275304932416;video/quicktime;transcriptie: word;verklaring: jpg;info:eu-repo/semantics/openAccess;License: http://creativecommons.org/publicdomain/zero/1.0;Mevrouw Regina Veeger Janssen groeide op in een katholiek gezin en woonde tijdens de oorlog als tiener aan de Grote Markt. Zij vertelt van het dagelijks leven in de oorlog en van de bevrijdingsstrijd, waarbij hun huis, samen met grote delen van de Grote Markt, verwoest werd.  \n  \n00:04:15 Begin van de oorlog; inzamelen radio's en metaal.  \n  \n00:06:49 Joodse kinderen op de katholieke school  \n  \n00:09:56 Kinderen uit Rotterdam in huis, en anderen.  \n  \n00:12:25 Moeder kookt extra eten voor onbekenden  \n  \n00:14:05 Naber en arrestatie van deken Buve  \n  \n00:16:00 Naar de HBS; door Duitse vorderingen twee scholen in \u00e9\u00e9n gebouw.  \n  \n00:22:18 Stelen witte kool van Duitsers; de handtastelijke Duitse soldaat.  \n  \n00:24:50 Het kanonnetje op het Scholtenhuis; Seyss-Inquart; de bevrijding  \n  \n00:27:38 Brand Waagstraat verspreidt zich; familie onder de bureau's.  \n  \n00:33:38 Familie vlucht tijdens mini-wapenstilstand naar Poststraat en de Martinuskerk.  \n  \n00:38:02 Vader en RV bekijken de schade aan de Grote Markt  \n  \n00:40:47 Foto van gestorven vriendin terug naar ouders.  \n  \n00:42:40 Gezin krijgt huis toegewezen; een nieuwe start van ondernemersactiviteiten: foto's van de verwoesting en stoffen.  \n  \n00:46:40 Een Duitse soldaat in de gang; na de oorlog;1940-1945",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0a2cb465-2bca-51ad-965f-b2dbc43ca1e1",
-    "notes": [
-        "Mevrouw Regina Veeger Janssen groeide op in een katholiek gezin en woonde tijdens de oorlog als tiener aan de Grote Markt. Zij vertelt van het dagelijks leven in de oorlog en van de bevrijdingsstrijd, waarbij hun huis, samen met grote delen van de Grote Markt, verwoest werd.  \n  \n00:04:15 Begin van de oorlog; inzamelen radio's en metaal.  \n  \n00:06:49 Joodse kinderen op de katholieke school  \n  \n00:09:56 Kinderen uit Rotterdam in huis, en anderen.  \n  \n00:12:25 Moeder kookt extra eten voor onbekenden  \n  \n00:14:05 Naber en arrestatie van deken Buve  \n  \n00:16:00 Naar de HBS; door Duitse vorderingen twee scholen in \u00e9\u00e9n gebouw.  \n  \n00:22:18 Stelen witte kool van Duitsers; de handtastelijke Duitse soldaat.  \n  \n00:24:50 Het kanonnetje op het Scholtenhuis; Seyss-Inquart; de bevrijding  \n  \n00:27:38 Brand Waagstraat verspreidt zich; familie onder de bureau's.  \n  \n00:33:38 Familie vlucht tijdens mini-wapenstilstand naar Poststraat en de Martinuskerk.  \n  \n00:38:02 Vader en RV bekijken de schade aan de Grote Markt  \n  \n00:40:47 Foto van gestorven vriendin terug naar ouders.  \n  \n00:42:40 Gezin krijgt huis toegewezen; een nieuwe start van ondernemersactiviteiten: foto's van de verwoesting en stoffen.  \n  \n00:46:40 Een Duitse soldaat in de gang; na de oorlog"
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:41843"
-    ],
-    "oai_set": [
-        "D30000:D34000:D34300",
-        "driver",
-        "easy-collection:2",
-        "easy-collection:1"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Modern contemporary"
-        },
-        {
-            "name": "history"
-        },
-        {
-            "name": "Groningen"
-        },
-        {
-            "name": "rooms-katholiek"
-        },
-        {
-            "name": "eigen zaak"
-        },
-        {
-            "name": "stoffenhandel"
-        },
-        {
-            "name": "Seyss-Inquart"
-        },
-        {
-            "name": "Rotterdam"
-        },
-        {
-            "name": "Naber"
-        },
-        {
-            "name": "Scholtenhuis"
-        },
-        {
-            "name": "deken Buve"
-        },
-        {
-            "name": "Veringa"
-        }
-    ],
-    "title": [
-        "Groningen in Oorlogstijd, interview 06"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a2f3a7f-f019-50d1-a29a-071c8805dd79.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0a2f3a7f-f019-50d1-a29a-071c8805dd79.json
deleted file mode 100644
index fb114f11..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a2f3a7f-f019-50d1-a29a-071c8805dd79.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Archeologisch Onderzoek Leiden BV"
-    ],
-    "Contributor": [
-        "Archeologisch Onderzoek Leiden BV"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.17026/dans-z3a-qs4j",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "application/pdf"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:107613",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:107613"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Archeologisch Onderzoek Leiden BV"
-    ],
-    "RelatedIdentifier": [
-        "https://archisarchief.cultureelerfgoed.nl/Archis2/Archeorapporten/35/AR31982"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "SpatialCoverage": [
-        "\n            "
-    ],
-    "TempCoverageBegin": 63492638399,
-    "TempCoverageEnd": 63651182399,
-    "TemporalCoverage": " period : ( 2013-01-01T11:59:59Z - 2018-01-10T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2013-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-01-10T11:59:59Z",
-    "author": [
-        "Zon, M. van"
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:107613;2018-09-18T17:50:42Z;D30000:D37000;easy-collection:4;10.17026/dans-z3a-qs4j;Zon, M. van;Archeologisch Onderzoek Leiden BV;Briefrapport Archeologische Begeleiding Oegstgeest. Nieuw Rhijngeest-Zuid, Kadastrale Locatie E;Archol-rapport 232;Archol-rapport 232;Archeologisch Onderzoek Leiden BV;2018;Archaeology;Archeologisch Onderzoek Leiden BV;2013-01-01;2018-01-10;nl;Dataset;urn:nbn:nl:ui:13-lx-oezc;easy-dataset:107613;https://archisarchief.cultureelerfgoed.nl/Archis2/Archeorapporten/35/AR31982;application/pdf;info:eu-repo/semantics/openAccess;Begeleiding kabelsleuf 70x1 m. Tijdens de begeleiding zijn geen vondsten en sporen aangetroffen;Oegstgeest;Oegstgeest;Zuid-Holland;52.17127721;4.45407213",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0a2f3a7f-f019-50d1-a29a-071c8805dd79",
-    "notes": [
-        "Begeleiding kabelsleuf 70x1 m. Tijdens de begeleiding zijn geen vondsten en sporen aangetroffen"
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:107613"
-    ],
-    "oai_set": [
-        "D30000:D37000",
-        "easy-collection:4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Archaeology"
-        }
-    ],
-    "title": [
-        "Briefrapport Archeologische Begeleiding Oegstgeest. Nieuw Rhijngeest-Zuid, Kadastrale Locatie E",
-        "Archol-rapport 232",
-        "Archol-rapport 232"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a38fc9a-85ad-5810-b199-7f8eb1a22646.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0a38fc9a-85ad-5810-b199-7f8eb1a22646.json
deleted file mode 100644
index 7615b732..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a38fc9a-85ad-5810-b199-7f8eb1a22646.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.5061/dryad.39309",
-    "DiscHierarchy": [
-        "1.3.3",
-        "Fine Arts, Music, Theatre and Media Studies",
-        "Dance"
-    ],
-    "Discipline": "Medicine",
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:84687",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:84687"
-    ],
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Data Archiving and Networked Services (DANS)"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/closedAccess"
-    ],
-    "TempCoverageBegin": 63518558399,
-    "TempCoverageEnd": 63518558399,
-    "TemporalCoverage": " period : ( 2013-10-28T11:59:59Z - 2013-10-28T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2013-10-28T11:59:59Z",
-    "TemporalCoverage:EndDate": "2013-10-28T11:59:59Z",
-    "author": [
-        "Antunes, Agostinho",
-        "Vasconcelos, V\u00edtor",
-        "Machado, Jo\u00e3o Paulo"
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:84687;2018-09-18T17:27:56Z;D20000;Machado, Jo\u00e3o Paulo;Vasconcelos, V\u00edtor;Antunes, Agostinho;Data from: Adaptive functional divergence of the warm temperature acclimation-related protein (WAP65) in fishes and the ortholog Hemopexin (HPX) in mammals;Data Archiving and Networked Services (DANS);2013;Life sciences, medicine and health care ;2013-10-28T16:25:23.000+01:00;2013-10-28T16:25:23.000+01:00;Dataset;10.5061/dryad.39309;urn:nbn:nl:ui:13-mz-njvl;easy-dataset:84687;info:eu-repo/semantics/closedAccess;Gene duplication is an important mechanism that leads to genetic novelty. Different, nonexclusive processes are likely involved, and many adaptive and nonadaptive events may contribute to the maintenance of duplicated genes. In some teleosts, a duplicate copy of the mammalian ortholog Hemopexin (HPX) is present, known as the warm temperature acclimation-related protein (WAP65). Both WAP65 and HPX have been associated with iron homeostasis due to the affinity to bind the toxic-free heme circulating in the blood stream. We have assessed the evolutionary dynamics of WAP65 and HPX genes to understand the adaptive role of positive selection at both nucleotide and amino acid level. Our results showed an asymmetrical evolution between the paralogs WAP65-1 and WAP65-2 after duplication with a slight acceleration of the evolutionary rate in WAP65-1, but not in WAP65-2, and few sites contributing to the functional distinction between the paralogs, whereas the majority of the protein remained under negative selection or relaxed negative selection. WAP65-1 is functionally more distinct from the ancestral protein function than WAP65-2. HPX is phylogenetically closer to WAP65-2 but even so functional divergence was detected between both proteins. In addition, HPX showed a fast rate of evolution when compared with both WAP65-1 and WAP65-2 genes. The assessed 3-dimensional (3-D) structure of WAP65-1 and WAP65-2 suggests that the functional differences detected are not causing noticeable structural changes in these proteins. However, such subtle changes between WAP65 paralogs may be important to understand the differential gene retention of both copies in 20 out of 30 teleosts species studied.",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0a38fc9a-85ad-5810-b199-7f8eb1a22646",
-    "notes": [
-        "Gene duplication is an important mechanism that leads to genetic novelty. Different, nonexclusive processes are likely involved, and many adaptive and nonadaptive events may contribute to the maintenance of duplicated genes. In some teleosts, a duplicate copy of the mammalian ortholog Hemopexin (HPX) is present, known as the warm temperature acclimation-related protein (WAP65). Both WAP65 and HPX have been associated with iron homeostasis due to the affinity to bind the toxic-free heme circulating in the blood stream. We have assessed the evolutionary dynamics of WAP65 and HPX genes to understand the adaptive role of positive selection at both nucleotide and amino acid level. Our results showed an asymmetrical evolution between the paralogs WAP65-1 and WAP65-2 after duplication with a slight acceleration of the evolutionary rate in WAP65-1, but not in WAP65-2, and few sites contributing to the functional distinction between the paralogs, whereas the majority of the protein remained under negative selection or relaxed negative selection. WAP65-1 is functionally more distinct from the ancestral protein function than WAP65-2. HPX is phylogenetically closer to WAP65-2 but even so functional divergence was detected between both proteins. In addition, HPX showed a fast rate of evolution when compared with both WAP65-1 and WAP65-2 genes. The assessed 3-dimensional (3-D) structure of WAP65-1 and WAP65-2 suggests that the functional differences detected are not causing noticeable structural changes in these proteins. However, such subtle changes between WAP65 paralogs may be important to understand the differential gene retention of both copies in 20 out of 30 teleosts species studied."
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:84687"
-    ],
-    "oai_set": [
-        "D20000"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Life sciences"
-        },
-        {
-            "name": "medicine health care"
-        }
-    ],
-    "title": [
-        "Data from: Adaptive functional divergence of the warm temperature acclimation-related protein (WAP65) in fishes and the ortholog Hemopexin (HPX) in mammals"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a44df79-0c7e-5fbe-a36a-82e3489680ba.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0a44df79-0c7e-5fbe-a36a-82e3489680ba.json
deleted file mode 100644
index 6c1dd31b..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a44df79-0c7e-5fbe-a36a-82e3489680ba.json
+++ /dev/null
@@ -1,99 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.17026/dans-xgb-45p5",
-    "DiscHierarchy": [
-        "1.5.9",
-        "Literary Studies",
-        "Poetry"
-    ],
-    "Discipline": "History",
-    "Format": [
-        "application/x-cmdi+xml"
-    ],
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:42024",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:42024"
-    ],
-    "PublicationTimestamp": "2010-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "Data Archiving and Networked Services (DANS)"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "TempCoverageBegin": 63405028799,
-    "TempCoverageEnd": 63423341999,
-    "TemporalCoverage": " period : ( 2010-03-24T11:59:59Z - 2010-10-22T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2010-03-24T11:59:59Z",
-    "TemporalCoverage:EndDate": "2010-10-22T11:59:59Z",
-    "author": [
-        "Veteranen Instituut"
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:42024;2018-09-18T16:57:18Z;D30000:D34000:D34300;driver;easy-collection:1;10.17026/dans-xgb-45p5;Veteranen Instituut;Veteranen Instituut, IPNV, interview 1016;Data Archiving and Networked Services (DANS);2010;Modern and contemporary\n                        history;KNIL;Meester Cornelis;Japanners;Baboes;Interneringskamp;Gevangenis;Ziektes;Indonesiers;Nationaliteit;Zwitsers Rode Kruis;Militaire Dienst;Opleiding;Verpleger;Paramilitair;Oorlogshandelingen;Poncke Princen;Gewonden;Politionele actie;Fort Vredenburg;Soekarno;Angst;Temporal coverage: 1945-1950;2010-03-24;2010-10-22;Dataset;urn:nbn:nl:ui:13-lic-0u6;easy-dataset:42024;twips.dans.knaw.nl-319676217982850984-1287733147044;application/x-cmdi+xml;info:eu-repo/semantics/openAccess;De geinterviewde is geboren in Nederlands-Indie. De ge\u00efnterviewde groeide hier op en ging hier naar school.  Tijdens de Japanse bezetting kwam hij onder andere in het interneringskamp Meester Cornelis terecht. De ge\u00efnterviewde beschrijft het leven in de kampen. Een keer kwam hij in de gevangenis terecht waar hij slecht werd behandeld. Ondanks dat hij heel sterk was kwam hij toch in het ziekenhuis. Veel mensen stierven. De ge\u00efnterviewde spreekt over de ontwikkelingen na de bevrijding. Hij was hier erg teleurgesteld over. Hij had het slechter onder de Indonesiers dan onder de japanners. Op een gegeven moment mocht hij zijn nationaliteit kiezen en koos voor de Nederlandse. Hij meldde zich aan voor militaire dienst in 1948. Hij vertelt over opleidingen en hoe hij uiteindelijk bij de paramilitairen kwam. De ge\u00efnterviewde vertelt over de rol van het KNIL in Java en praat over de politionele acties, verschillende oorlogshandelingen waar hij niet altijd achter stond. Later is de ge\u00efnterviewde uitgezonden naar Korea.  \n  \nMet de ge\u00efnterviewde zijn twee of meer interviews gehouden. Zie relations.;Nederlands-Indie;Batavia;Malang;Yogyakarta;Indonesie",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0a44df79-0c7e-5fbe-a36a-82e3489680ba",
-    "notes": [
-        "De geinterviewde is geboren in Nederlands-Indie. De ge\u00efnterviewde groeide hier op en ging hier naar school.  Tijdens de Japanse bezetting kwam hij onder andere in het interneringskamp Meester Cornelis terecht. De ge\u00efnterviewde beschrijft het leven in de kampen. Een keer kwam hij in de gevangenis terecht waar hij slecht werd behandeld. Ondanks dat hij heel sterk was kwam hij toch in het ziekenhuis. Veel mensen stierven. De ge\u00efnterviewde spreekt over de ontwikkelingen na de bevrijding. Hij was hier erg teleurgesteld over. Hij had het slechter onder de Indonesiers dan onder de japanners. Op een gegeven moment mocht hij zijn nationaliteit kiezen en koos voor de Nederlandse. Hij meldde zich aan voor militaire dienst in 1948. Hij vertelt over opleidingen en hoe hij uiteindelijk bij de paramilitairen kwam. De ge\u00efnterviewde vertelt over de rol van het KNIL in Java en praat over de politionele acties, verschillende oorlogshandelingen waar hij niet altijd achter stond. Later is de ge\u00efnterviewde uitgezonden naar Korea.  \n  \nMet de ge\u00efnterviewde zijn twee of meer interviews gehouden. Zie relations."
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:42024"
-    ],
-    "oai_set": [
-        "D30000:D34000:D34300",
-        "driver",
-        "easy-collection:1"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Modern contemporary"
-        },
-        {
-            "name": "history"
-        },
-        {
-            "name": "KNIL"
-        },
-        {
-            "name": "Meester Cornelis"
-        },
-        {
-            "name": "Japanners"
-        },
-        {
-            "name": "Baboes"
-        },
-        {
-            "name": "Interneringskamp"
-        },
-        {
-            "name": "Gevangenis"
-        },
-        {
-            "name": "Ziektes"
-        },
-        {
-            "name": "Indonesiers"
-        },
-        {
-            "name": "Nationaliteit"
-        },
-        {
-            "name": "Zwitsers Rode Kruis"
-        }
-    ],
-    "title": [
-        "Veteranen Instituut, IPNV, interview 1016"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a4d2dba-183f-568c-9308-a90854292b71.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0a4d2dba-183f-568c-9308-a90854292b71.json
deleted file mode 100644
index f7c0004f..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a4d2dba-183f-568c-9308-a90854292b71.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.5061/dryad.qv0sk",
-    "DiscHierarchy": [
-        "1.3.3",
-        "Fine Arts, Music, Theatre and Media Studies",
-        "Dance"
-    ],
-    "Discipline": "Medicine",
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:88581",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:88581"
-    ],
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Data Archiving and Networked Services (DANS)"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/closedAccess"
-    ],
-    "TempCoverageBegin": 63562881599,
-    "TempCoverageEnd": 63562881599,
-    "TemporalCoverage": " period : ( 2015-03-25T11:59:59Z - 2015-03-25T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2015-03-25T11:59:59Z",
-    "TemporalCoverage:EndDate": "2015-03-25T11:59:59Z",
-    "author": [
-        "Stevens, Jeffrey R."
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:88581;2018-09-18T17:31:36Z;D20000;Stevens, Jeffrey R.;Data from: Intertemporal similarity: discounting as a last resort;Data Archiving and Networked Services (DANS);2015;Life sciences, medicine and health care ;2015-03-25T17:55:04.000+01:00;2015-03-25T17:55:04.000+01:00;Dataset;10.5061/dryad.qv0sk;urn:nbn:nl:ui:13-jj-7afk;easy-dataset:88581;info:eu-repo/semantics/closedAccess;Standard models of intertemporal choice assume that individuals discount future payoffs by integrating reward amounts and time delays to generate a discounted value. Alternative models propose that, rather than integrate across them, individuals compare within attributes (amounts and delays) to determine if differences in one attribute outweigh differences in another attribute. For instance, the similarity model 1) compares the two reward amounts to determine whether they are similar, 2) compares the similarity of the two time delays, and then 3) makes a decision based on these similarity judgments. Here, I tested discounting models against attribute-based models that use similarity judgments to make choices. I collected intertemporal choices and similarity judgments for the reward amounts and time delays from participants in three experiments. All experiments tested the ability of discounting and similarity models to predict intertemporal choices. Model generalization analyses showed that the best predicting models started with similarity judgments and then, if similarity failed to make a prediction, resorted to discounting models. Similarity judgments also matched intertemporal choice data demonstrating both the magnitude and sign effects, thereby accounting for behavioral data that contradict many discounting models. These results highlight the possibility that attribute-based models such as the similarity models provide alternatives to discounting that may offer insights into the process of making intertemporal choices.",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0a4d2dba-183f-568c-9308-a90854292b71",
-    "notes": [
-        "Standard models of intertemporal choice assume that individuals discount future payoffs by integrating reward amounts and time delays to generate a discounted value. Alternative models propose that, rather than integrate across them, individuals compare within attributes (amounts and delays) to determine if differences in one attribute outweigh differences in another attribute. For instance, the similarity model 1) compares the two reward amounts to determine whether they are similar, 2) compares the similarity of the two time delays, and then 3) makes a decision based on these similarity judgments. Here, I tested discounting models against attribute-based models that use similarity judgments to make choices. I collected intertemporal choices and similarity judgments for the reward amounts and time delays from participants in three experiments. All experiments tested the ability of discounting and similarity models to predict intertemporal choices. Model generalization analyses showed that the best predicting models started with similarity judgments and then, if similarity failed to make a prediction, resorted to discounting models. Similarity judgments also matched intertemporal choice data demonstrating both the magnitude and sign effects, thereby accounting for behavioral data that contradict many discounting models. These results highlight the possibility that attribute-based models such as the similarity models provide alternatives to discounting that may offer insights into the process of making intertemporal choices."
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:88581"
-    ],
-    "oai_set": [
-        "D20000"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Life sciences"
-        },
-        {
-            "name": "medicine health care"
-        }
-    ],
-    "title": [
-        "Data from: Intertemporal similarity: discounting as a last resort"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a50daf8-ba25-5bc7-8219-f375aab6cbb4.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0a50daf8-ba25-5bc7-8219-f375aab6cbb4.json
deleted file mode 100644
index 1dab7f4b..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a50daf8-ba25-5bc7-8219-f375aab6cbb4.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.5061/dryad.1b2q0",
-    "DiscHierarchy": [
-        "1.3.3",
-        "Fine Arts, Music, Theatre and Media Studies",
-        "Dance"
-    ],
-    "Discipline": "Medicine",
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:83192",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:83192"
-    ],
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Data Archiving and Networked Services (DANS)"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/closedAccess"
-    ],
-    "TempCoverageBegin": 63497995199,
-    "TempCoverageEnd": 63497995199,
-    "TemporalCoverage": " period : ( 2013-03-04T11:59:59Z - 2013-03-04T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2013-03-04T11:59:59Z",
-    "TemporalCoverage:EndDate": "2013-03-04T11:59:59Z",
-    "author": [
-        "Stevens, Martin",
-        "Teasdale, Luisa C.",
-        "Stuart-Fox, Devi"
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:83192;2018-09-18T17:26:32Z;D20000;Teasdale, Luisa C.;Stevens, Martin;Stuart-Fox, Devi;Data from: Discrete colour polymorphism in the tawny dragon lizard (Ctenophorus decresii) and differences in signal conspicuousness among morphs;Data Archiving and Networked Services (DANS);2013;Life sciences, medicine and health care ;2013-03-04T19:57:28.000+01:00;2013-03-04T19:57:28.000+01:00;Dataset;10.5061/dryad.1b2q0;urn:nbn:nl:ui:13-uz-sza6;easy-dataset:83192;info:eu-repo/semantics/closedAccess;Intraspecific colour variation is common in nature and can vary from the coexistence of discrete colour variants in polymorphic species to continuous variation. Whether coloration is continuous or discrete is often ambiguous and many species exhibit a combination of the two. The nature of the variation (discrete or continuous) has implications for both the genetic basis of the colour variation and the evolutionary processes generating and maintaining it. Consequently, it is important to qualify the existence of discrete morphs, particularly in relation to the animal's visual system. In this study, we quantified male throat colour variation in Ctenophorus decresii tawny dragon lizard and tested for morphological and ecological correlates of the colour variants. We confirmed that discrete throat colour morphs can be defined based on colour and pattern analyses independent of the human visual system. We also found that the colour variants differed in their conspicuousness from the background, to the lizard's visual system, which has implications for signalling. However, the morphs did not differ in morphology or microhabitat use, which suggests that these characteristics are not involved in the evolutionary maintenance of the polymorphism.",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0a50daf8-ba25-5bc7-8219-f375aab6cbb4",
-    "notes": [
-        "Intraspecific colour variation is common in nature and can vary from the coexistence of discrete colour variants in polymorphic species to continuous variation. Whether coloration is continuous or discrete is often ambiguous and many species exhibit a combination of the two. The nature of the variation (discrete or continuous) has implications for both the genetic basis of the colour variation and the evolutionary processes generating and maintaining it. Consequently, it is important to qualify the existence of discrete morphs, particularly in relation to the animal's visual system. In this study, we quantified male throat colour variation in Ctenophorus decresii tawny dragon lizard and tested for morphological and ecological correlates of the colour variants. We confirmed that discrete throat colour morphs can be defined based on colour and pattern analyses independent of the human visual system. We also found that the colour variants differed in their conspicuousness from the background, to the lizard's visual system, which has implications for signalling. However, the morphs did not differ in morphology or microhabitat use, which suggests that these characteristics are not involved in the evolutionary maintenance of the polymorphism."
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:83192"
-    ],
-    "oai_set": [
-        "D20000"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Life sciences"
-        },
-        {
-            "name": "medicine health care"
-        }
-    ],
-    "title": [
-        "Data from: Discrete colour polymorphism in the tawny dragon lizard (Ctenophorus decresii) and differences in signal conspicuousness among morphs"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a72eb80-5343-5b6c-8ff3-7af7433488ff.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0a72eb80-5343-5b6c-8ff3-7af7433488ff.json
deleted file mode 100644
index 0d74f9a7..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a72eb80-5343-5b6c-8ff3-7af7433488ff.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "BAAC BV"
-    ],
-    "Contributor": [
-        "BAAC BV"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.17026/dans-xke-8dpr",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "application/pdf"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:69950",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:69950"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "BAAC BV"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "SpatialCoverage": [
-        "\n            "
-    ],
-    "TempCoverageBegin": 63571345199,
-    "TempCoverageEnd": 63626468399,
-    "TemporalCoverage": " period : ( 2015-07-01T11:59:59Z - 2017-03-30T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2015-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2017-03-30T11:59:59Z",
-    "author": [
-        "Kalisvaart, C.C."
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:69950;2018-09-18T17:14:49Z;D30000:D37000;driver;easy-collection:4;10.17026/dans-xke-8dpr;Kalisvaart, C.C.;BAAC BV;Kalisvaart, C.C.;BAAC BV;IJsselstein, Plangebied Touwlaan;BAAC-rapport V-15.0071;Touwlaan;BAAC BV;2017;Archaeology;archeologisch: boring;BAAC BV;2015;2017-03-30;nl;Dataset;urn:nbn:nl:ui:13-fxw9-ib;easy-dataset:69950;application/pdf;info:eu-repo/semantics/openAccess;BAAC bv heeft een bureauonderzoek en verkennend booronderzoek uitgevoerd in het plangebied Touwlaan te IJsselstein. De reden voor dit onderzoek is de geplande herstructurering van de Touwlaan.\nUit het bureauonderzoek is gebleken dat er resten van een Engelse\nlandschapstuin, een 17e eeuwse Hofkamp met moestuin, de buitenste\nmiddeleeuwse gracht en een mogelijk toegangspad behorende bij kasteel\nIJsselstein worden verwacht tussen de Kasteellaan en de Johan Willem Frisolaan.\nOok kunnen ter hoogte van de kruisingen met de Achtersloot, de Kasteellaan en de straat \u201cEiteren\u201d nog restanten van laatmiddeleeuwse bebouwing worden aangetroffen. Oudere resten uit de Romeinse tijd (complextype: nederzetting) worden mogelijk in het noordelijke deel van het plangebied op de oevers van de Hollandse IJssel verwacht. Resten uit de prehistorie kunnen in het centrale deel van het plangebied nog voorkomen op de afzettingen van de Buitenzorg stroomgordel. De top van deze stroomgordel ligt echter buiten de maximale verstoringsdiepte van 1 m \u2013mv. Binnen het gehele plangebied worden resten verwacht van een voormalige touwbaan uit de 19e/20e eeuw. De diepteligging van eventueel aanwezige archeologische resten is afhankelijk van de dikte van de\nrecent opgebrachte zandige ophoogpakketten.\nUit het veldonderzoek is gebleken dat het zuidelijke deel ten zuiden van boring 6 in een lager en van oorsprong nat komgebied ligt. Tussen boring 7 en boring 17 ligt een zone waar dikke ophoogpakketten en/of vullingslagen van een gracht voorkomen. De zone vanaf boring 17 ligt op een hoger gelegen oeverwal van de Hollandse IJssel waarop een antropogene ophogingslaag ligt. Ten noorden van de kruising met de straat \u201cEiteren\u201d is het plangebied opgehoogd (recent verstoord)\ntot meer dan 1 m hoogte. Uit het booronderzoek blijkt verder dat tussen de Kasteellaan en de Johan Willem Frisolaan grachtvullingen voorkomen en dat op meerdere plekken binnen het plangebied begraven leefniveaus (AC-horizonten) aanwezig zijn onder een \u00e9\u00e9n of tweefasig opgebouwd ophoogdek. De top van de aanwezige archeologische niveaus komt vrijwel overal voor binnen 1 m \u2013mv.\nRecente verstoringen reiken slechts op enkele plekken dieper dan 1 m \u2013mv. Op basis van de resultaten van het bureauonderzoek en het booronderzoek geldt een middelhoge tot hoge archeologische verwachting op het aantreffen van archeologische resten uit de Romeinse tijd tot en met de nieuwe tijd C (complextypen: nederzetting, gracht, landschapstuin, huisplaats, touwslagerij).\nHet gebied ten noorden van de kruising met de straat \u201cEiteren\u201d heeft tot een diepte van 1,2 m \u2013mv een lage verwachting toegekend gekregen vanwege de ophoging van meer dan 1 meter voor dit gedeelte van het plangebied.\n\nBAAC bv adviseert om voor het gehele plangebied, met uitzondering van het gebied ten noorden van de kruising met de straat \u201cEiteren\u201d en de zone tussen de Kasteellaan en de Johan Willem Frisolaan, de werkzaamheden archeologisch te laten begeleiden, conform het protocol proefsleuven. Voor het traject tussen de Kasteellaan en de Johan Willem Frisolaan wordt geadviseerd om deze te begeleiden, conform het protocol opgraven. In dit gedeelte kunnen zeer behoudenswaardige resten worden verwacht, waardoor hier alle geplande verstoringen die dieper reiken dan 25 cm \u2013mv allereerst opgegraven dienen te worden. Het advies voor het gebied ten noorden van de straat \u201cEiteren\u201d betreft, gezien de lage archeologische verwachting, vrijgave van archeologisch vervolgonderzoek.\n\nBovenstaand advies is op 11 juni 2015 is in grote lijnen overgenomen. Er is\nbesloten om voor het gehele plangebied de werkzaamheden archeologisch te begeleiden, indien behoud \u201cin situ\u201d niet mogelijk is. Deze archeologische begeleiding dient te worden uitgevoerd conform het KNA 3.3 protocol proefsleuven (IVO-P), indien behoudenswaardige archeologische resten worden aangetroffen dient te worden doorgestart naar het protocol Opgraven. Dit onderzoek dient te worden uitgevoerd op basis van een door de bevoegde overheid goedgekeurd Programma van Eisen (PvE). De beide hier aangegeven onderzoeksfasen mogen in hetzelfde PvE worden opgenomen.;IJsselstein;IJsselstein;Utrecht;52.02149264;5.04183305",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0a72eb80-5343-5b6c-8ff3-7af7433488ff",
-    "notes": [
-        "BAAC bv heeft een bureauonderzoek en verkennend booronderzoek uitgevoerd in het plangebied Touwlaan te IJsselstein. De reden voor dit onderzoek is de geplande herstructurering van de Touwlaan.\nUit het bureauonderzoek is gebleken dat er resten van een Engelse\nlandschapstuin, een 17e eeuwse Hofkamp met moestuin, de buitenste\nmiddeleeuwse gracht en een mogelijk toegangspad behorende bij kasteel\nIJsselstein worden verwacht tussen de Kasteellaan en de Johan Willem Frisolaan.\nOok kunnen ter hoogte van de kruisingen met de Achtersloot, de Kasteellaan en de straat \u201cEiteren\u201d nog restanten van laatmiddeleeuwse bebouwing worden aangetroffen. Oudere resten uit de Romeinse tijd (complextype: nederzetting) worden mogelijk in het noordelijke deel van het plangebied op de oevers van de Hollandse IJssel verwacht. Resten uit de prehistorie kunnen in het centrale deel van het plangebied nog voorkomen op de afzettingen van de Buitenzorg stroomgordel. De top van deze stroomgordel ligt echter buiten de maximale verstoringsdiepte van 1 m \u2013mv. Binnen het gehele plangebied worden resten verwacht van een voormalige touwbaan uit de 19e/20e eeuw. De diepteligging van eventueel aanwezige archeologische resten is afhankelijk van de dikte van de\nrecent opgebrachte zandige ophoogpakketten.\nUit het veldonderzoek is gebleken dat het zuidelijke deel ten zuiden van boring 6 in een lager en van oorsprong nat komgebied ligt. Tussen boring 7 en boring 17 ligt een zone waar dikke ophoogpakketten en/of vullingslagen van een gracht voorkomen. De zone vanaf boring 17 ligt op een hoger gelegen oeverwal van de Hollandse IJssel waarop een antropogene ophogingslaag ligt. Ten noorden van de kruising met de straat \u201cEiteren\u201d is het plangebied opgehoogd (recent verstoord)\ntot meer dan 1 m hoogte. Uit het booronderzoek blijkt verder dat tussen de Kasteellaan en de Johan Willem Frisolaan grachtvullingen voorkomen en dat op meerdere plekken binnen het plangebied begraven leefniveaus (AC-horizonten) aanwezig zijn onder een \u00e9\u00e9n of tweefasig opgebouwd ophoogdek. De top van de aanwezige archeologische niveaus komt vrijwel overal voor binnen 1 m \u2013mv.\nRecente verstoringen reiken slechts op enkele plekken dieper dan 1 m \u2013mv. Op basis van de resultaten van het bureauonderzoek en het booronderzoek geldt een middelhoge tot hoge archeologische verwachting op het aantreffen van archeologische resten uit de Romeinse tijd tot en met de nieuwe tijd C (complextypen: nederzetting, gracht, landschapstuin, huisplaats, touwslagerij).\nHet gebied ten noorden van de kruising met de straat \u201cEiteren\u201d heeft tot een diepte van 1,2 m \u2013mv een lage verwachting toegekend gekregen vanwege de ophoging van meer dan 1 meter voor dit gedeelte van het plangebied.\n\nBAAC bv adviseert om voor het gehele plangebied, met uitzondering van het gebied ten noorden van de kruising met de straat \u201cEiteren\u201d en de zone tussen de Kasteellaan en de Johan Willem Frisolaan, de werkzaamheden archeologisch te laten begeleiden, conform het protocol proefsleuven. Voor het traject tussen de Kasteellaan en de Johan Willem Frisolaan wordt geadviseerd om deze te begeleiden, conform het protocol opgraven. In dit gedeelte kunnen zeer behoudenswaardige resten worden verwacht, waardoor hier alle geplande verstoringen die dieper reiken dan 25 cm \u2013mv allereerst opgegraven dienen te worden. Het advies voor het gebied ten noorden van de straat \u201cEiteren\u201d betreft, gezien de lage archeologische verwachting, vrijgave van archeologisch vervolgonderzoek.\n\nBovenstaand advies is op 11 juni 2015 is in grote lijnen overgenomen. Er is\nbesloten om voor het gehele plangebied de werkzaamheden archeologisch te begeleiden, indien behoud \u201cin situ\u201d niet mogelijk is. Deze archeologische begeleiding dient te worden uitgevoerd conform het KNA 3.3 protocol proefsleuven (IVO-P), indien behoudenswaardige archeologische resten worden aangetroffen dient te worden doorgestart naar het protocol Opgraven. Dit onderzoek dient te worden uitgevoerd op basis van een door de bevoegde overheid goedgekeurd Programma van Eisen (PvE). De beide hier aangegeven onderzoeksfasen mogen in hetzelfde PvE worden opgenomen."
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:69950"
-    ],
-    "oai_set": [
-        "D30000:D37000",
-        "driver",
-        "easy-collection:4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Archaeology"
-        },
-        {
-            "name": "archeologisch boring"
-        }
-    ],
-    "title": [
-        "IJsselstein, Plangebied Touwlaan",
-        "BAAC-rapport V-15.0071",
-        "Touwlaan"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a7ac574-908b-5dd3-b5fc-b33285a0a07b.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0a7ac574-908b-5dd3-b5fc-b33285a0a07b.json
deleted file mode 100644
index b5f4b301..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a7ac574-908b-5dd3-b5fc-b33285a0a07b.json
+++ /dev/null
@@ -1,106 +0,0 @@
-{
-    "Contact": [
-        "RAAP Archeologisch Adviesbureau B.V."
-    ],
-    "Contributor": [
-        "RAAP Archeologisch Adviesbureau B.V."
-    ],
-    "DOI": "http://dx.doi.org/doi:10.17026/dans-2ay-5u3x",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "image/jpeg",
-        "access / mdb",
-        "mapinfo / tab",
-        "application/rtf",
-        "application/pdf",
-        "application/msword"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:37220",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:37220"
-    ],
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "RAAP Archeologisch Adviesbureau B.V."
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "SpatialCoverage": [
-        "\n            "
-    ],
-    "TemporalCoverage": [
-        "2011-04-08",
-        "2008-10-10",
-        "2011-04-08"
-    ],
-    "author": [
-        "RAAP Archeologisch Adviesbureau",
-        "Scholte Lubberink, H.B.G."
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:37220;2018-09-18T16:54:08Z;D30000:D37000;10.17026/dans-2ay-5u3x;RAAP Archeologisch Adviesbureau;Scholte Lubberink, H.B.G.;Plangebied De Veldkamp;RAAP-rapport 1700;RAAP Archeologisch Adviesbureau B.V.;2011;Archaeology;Archeologisch: booronderzoek;boerderij;Begraving - Urnenveld (GVCU);Versterking - Landweer (VLW);Mesolithicum: 8800 - 4900 vC (MESO);Neolithicum laat: 2850 - 2000 vC (NEOL);Bronstijd laat: 1100 - 800 vC (BRONSL);IJzertijd vroeg: 800 - 500 vC (IJZV);Middeleeuwen laat: 1050 - 1500 nC (LME);RAAP Archeologisch Adviesbureau B.V.;2011-04-08;2008-10-10;2011-04-08;nl;Dataset;urn:nbn:nl:ui:13-j4x-l1i;easy-dataset:37220;twips.dans.knaw.nl-1901288763170205901-1302253556110;mapinfo / tab;access / mdb;application/rtf;application/pdf;application/msword;image/jpeg;info:eu-repo/semantics/openAccess;In opdracht van de gemeente Borne heeft RAAP Archeologisch Adviesbureau in januari en februari 2008 een archeologisch onderzoek uitgevoerd in verband met de ontwikkeling van plangebied De Veldkamp in de gemeenten Borne en Hengelo. Het onderzoek bestond uit een inventariserend veldonderzoek (karterend booronderzoek en het graven van proefsleuven) op 3 vindplaatsen en uit een archeologische begeleiding van de aanleg van een DPO-leiding.\n\nHet inventariserend veldonderzoek in de vorm van een karterend booronderzoek op vindplaats 3 De Lemerij heeft geen archeologische resten opgeleverd.\n\nTijdens het inventariserend onderzoek in de vorm van een proefsleuvenonderzoek op vindplaats 4 Schild Es is op het noordelijke deel van de Schild Es een urnenveld uit de Late Bronstijd/Vroege IJzertijd aangetroffen. Binnen dit urnenveld zijn tevens artefacten uit het Mesolithicum en Laat Neolithicum gevonden. Op basis van zijn hoge fysieke en inhoudelijke kwaliteit is het gebied van het urnenveld als behoudenswaardig aangemerkt.\n\nTijdens het proefsleuvenonderzoek op vindplaats 5 is een beperkt aantal sporen gevonden die in verband gebracht kan worden met de (bewoning op de) van oorsprong laat-middeleeuwse boerderij 't Schilt of Schildman.\n\nTijdens de archeologische begeleiding van het trac\u00e9 van de DPO-leiding zijn con form de verwachting de vermoedelijke restanten van een landweer aangetroffen.;28G;De Veldkamp;Borne;Borne;Overijssel;52.28658496;6.75059999",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0a7ac574-908b-5dd3-b5fc-b33285a0a07b",
-    "notes": [
-        "In opdracht van de gemeente Borne heeft RAAP Archeologisch Adviesbureau in januari en februari 2008 een archeologisch onderzoek uitgevoerd in verband met de ontwikkeling van plangebied De Veldkamp in de gemeenten Borne en Hengelo. Het onderzoek bestond uit een inventariserend veldonderzoek (karterend booronderzoek en het graven van proefsleuven) op 3 vindplaatsen en uit een archeologische begeleiding van de aanleg van een DPO-leiding.\n\nHet inventariserend veldonderzoek in de vorm van een karterend booronderzoek op vindplaats 3 De Lemerij heeft geen archeologische resten opgeleverd.\n\nTijdens het inventariserend onderzoek in de vorm van een proefsleuvenonderzoek op vindplaats 4 Schild Es is op het noordelijke deel van de Schild Es een urnenveld uit de Late Bronstijd/Vroege IJzertijd aangetroffen. Binnen dit urnenveld zijn tevens artefacten uit het Mesolithicum en Laat Neolithicum gevonden. Op basis van zijn hoge fysieke en inhoudelijke kwaliteit is het gebied van het urnenveld als behoudenswaardig aangemerkt.\n\nTijdens het proefsleuvenonderzoek op vindplaats 5 is een beperkt aantal sporen gevonden die in verband gebracht kan worden met de (bewoning op de) van oorsprong laat-middeleeuwse boerderij 't Schilt of Schildman.\n\nTijdens de archeologische begeleiding van het trac\u00e9 van de DPO-leiding zijn con form de verwachting de vermoedelijke restanten van een landweer aangetroffen."
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:37220"
-    ],
-    "oai_set": [
-        "D30000:D37000"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Archaeology"
-        },
-        {
-            "name": "Archeologisch booronderzoek"
-        },
-        {
-            "name": "boerderij"
-        },
-        {
-            "name": "Begraving - Urnenveld GVCU"
-        },
-        {
-            "name": "Versterking - Landweer VLW"
-        },
-        {
-            "name": "Mesolithicum - vC MESO"
-        },
-        {
-            "name": "Neolithicum laat - vC NEOL"
-        },
-        {
-            "name": "Bronstijd laat - vC BRONSL"
-        },
-        {
-            "name": "IJzertijd vroeg - vC IJZV"
-        },
-        {
-            "name": "Middeleeuwen laat - nC LME"
-        }
-    ],
-    "title": [
-        "Plangebied De Veldkamp",
-        "RAAP-rapport 1700"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a7ad63c-37d2-501c-8a05-77b8bd01baef.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0a7ad63c-37d2-501c-8a05-77b8bd01baef.json
deleted file mode 100644
index 454badbe..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a7ad63c-37d2-501c-8a05-77b8bd01baef.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "SOB Research"
-    ],
-    "Contributor": [
-        "SOB Research"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.17026/dans-zcn-bhku",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:43747",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:43747"
-    ],
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "SOB Research"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "SpatialCoverage": [
-        "\n            "
-    ],
-    "TemporalCoverage": [
-        "2011-02-08",
-        "2008-11",
-        "2011-01-26"
-    ],
-    "author": [
-        "Prins, C.A.; Ras, J."
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:43747;2018-09-18T16:58:21Z;D30000:D37000;driver;easy-collection:4;10.17026/dans-zcn-bhku;Prins, C.A.; Ras, J.;Archeologisch Bureauonderzoek; Plangebied Weverseinde, Puttershoek, Gemeente Binnenmaas;SOB 2008 PRIN.620;SOB Research;2011;Archaeology;SOB Research;2011-02-08;2008-11;2011-01-26;nl;Dataset;urn:nbn:nl:ui:13-fkv-xxf;easy-dataset:43747;twips.dans.knaw.nl-6945117832535337474-1297155217247;info:eu-repo/semantics/openAccess;onderzoeksrapport;Zuid-Holland; Binnenmaas; Puttershoek; Mijnsheerenland; Postweg; Puttershoek; Rustenburgstraat; Weverseinde; Heinenoord; Kuipersveer;51.80606382;4.54257894",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0a7ad63c-37d2-501c-8a05-77b8bd01baef",
-    "notes": [
-        "onderzoeksrapport"
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:43747"
-    ],
-    "oai_set": [
-        "D30000:D37000",
-        "driver",
-        "easy-collection:4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Archaeology"
-        }
-    ],
-    "title": [
-        "Archeologisch Bureauonderzoek; Plangebied Weverseinde, Puttershoek, Gemeente Binnenmaas",
-        "SOB 2008 PRIN.620"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a7e4b4e-4c53-58d8-93a4-18ec4245a41d.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0a7e4b4e-4c53-58d8-93a4-18ec4245a41d.json
deleted file mode 100644
index 790e93a0..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a7e4b4e-4c53-58d8-93a4-18ec4245a41d.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.5061/dryad.653c9",
-    "DiscHierarchy": [
-        "1.3.3",
-        "Fine Arts, Music, Theatre and Media Studies",
-        "Dance"
-    ],
-    "Discipline": "Medicine",
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:85001",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:85001"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Data Archiving and Networked Services (DANS)"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/closedAccess"
-    ],
-    "TempCoverageBegin": 63524260799,
-    "TempCoverageEnd": 63524260799,
-    "TemporalCoverage": " period : ( 2014-01-02T11:59:59Z - 2014-01-02T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2014-01-02T11:59:59Z",
-    "TemporalCoverage:EndDate": "2014-01-02T11:59:59Z",
-    "author": [
-        "Lau, On Lee",
-        "Stutz, William E.",
-        "Bolnick, Daniel I."
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:85001;2018-09-18T17:28:12Z;D20000;Stutz, William E.;Lau, On Lee;Bolnick, Daniel I.;Data from: Contrasting patterns of phenotype-dependent parasitism within and among populations of threespine stickleback;Data Archiving and Networked Services (DANS);2014;Life sciences, medicine and health care ;2014-01-02T18:55:25.000+01:00;2014-01-02T18:55:25.000+01:00;Dataset;10.5061/dryad.653c9;urn:nbn:nl:ui:13-ws-j92v;easy-dataset:85001;info:eu-repo/semantics/closedAccess;Variation in infection rate arises from variation in host exposure and resistance to parasites both within and among populations. All things being equal, phenotypes that increase exposure risk should covary positively with infection among individuals. It might therefore be expected that populations with mean phenotypes that increase exposure might also have higher rates of infection. However, such positive covariance between exposure and infection at the population level might be undermined by other factors such as geographic variation in parasite abundance or host resistance, negating or reversing in between-population comparisons. We studied rates of infection of two parasites among 18 populations of threespine stickleback (Gasterosteus aculeatus). As predicted, within populations, trophic morphology covaries with infection of two trophically transmitted parasites: individuals with benthic (or limnetic) phenotypes were more likely to be infected with a benthic (or limnetic) parasite. However, across populations, the relationship between morphology and infection rate was absent (limnetic parasite) or reversed (benthic parasite). Our results confirm the importance of phenotype-dependent exposure, but stress different factors or processes, such as the evolution of reduced susceptibility, might shape variation in infection at larger spatial scales.",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0a7e4b4e-4c53-58d8-93a4-18ec4245a41d",
-    "notes": [
-        "Variation in infection rate arises from variation in host exposure and resistance to parasites both within and among populations. All things being equal, phenotypes that increase exposure risk should covary positively with infection among individuals. It might therefore be expected that populations with mean phenotypes that increase exposure might also have higher rates of infection. However, such positive covariance between exposure and infection at the population level might be undermined by other factors such as geographic variation in parasite abundance or host resistance, negating or reversing in between-population comparisons. We studied rates of infection of two parasites among 18 populations of threespine stickleback (Gasterosteus aculeatus). As predicted, within populations, trophic morphology covaries with infection of two trophically transmitted parasites: individuals with benthic (or limnetic) phenotypes were more likely to be infected with a benthic (or limnetic) parasite. However, across populations, the relationship between morphology and infection rate was absent (limnetic parasite) or reversed (benthic parasite). Our results confirm the importance of phenotype-dependent exposure, but stress different factors or processes, such as the evolution of reduced susceptibility, might shape variation in infection at larger spatial scales."
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:85001"
-    ],
-    "oai_set": [
-        "D20000"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Life sciences"
-        },
-        {
-            "name": "medicine health care"
-        }
-    ],
-    "title": [
-        "Data from: Contrasting patterns of phenotype-dependent parasitism within and among populations of threespine stickleback"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a7f1ab6-291f-5192-abbd-6a547e9b3a98.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0a7f1ab6-291f-5192-abbd-6a547e9b3a98.json
deleted file mode 100644
index 213ecd93..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a7f1ab6-291f-5192-abbd-6a547e9b3a98.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "IDDS Archeologie"
-    ],
-    "Contributor": [
-        "IDDS Archeologie"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.17026/dans-x5p-jrfz",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "application/pdf"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:60746",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:60746"
-    ],
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "IDDS Archeologie"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/restrictedAccess"
-    ],
-    "SpatialCoverage": [
-        "\n            "
-    ],
-    "TemporalCoverage": [
-        "2015-02-11",
-        "2014-12-08",
-        "2015-02-11",
-        "2016-02-11"
-    ],
-    "author": [
-        "Koekkelkoren, A.M.H.C."
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:60746;2018-09-18T17:08:16Z;D30000:D37000;10.17026/dans-x5p-jrfz;Koekkelkoren, A.M.H.C.;N203, Gemeenten Castricum & Uitgeest;Archeologisch bureauonderzoek;IDDS Archeologie;2016;Archaeology;Archeologisch: bureauonderzoek;IDDS Archeologie;2015-02-11;2014-12-08;2015-02-11;2016-02-11;nl;Dataset;urn:nbn:nl:ui:13-ywu4-0r;easy-dataset:60746;application/pdf;info:eu-repo/semantics/restrictedAccess;In opdracht van Advin BV heeft IDDS Archeologie in december 2014 een archeologisch bureauonderzoek uitgevoerd voor de N203 Castricum en Uitgeest, gemeenten Castricum & Uitgeest. De aanleiding voor dit onderzoek is het geplande groot onderhoud aan de N203 tussen de aansluiting met de N513 Zeeweg en de oprit naar de A9.\n\nHet bureauonderzoek heeft uitgewezen dat de N203 is aangelegd in de jaren 30 van de 20e eeuw. Daarvoor bestond het plangebied uit weilanden met enkele slootjes en op enkele plaatsen een dijk. Voor de aanleg van de N203 is het oude landschap ge\u00ebgaliseerd en opgehoogd. Het ophoogpakket bestaat voornamelijk uit zand, maar kan tevens puinresten en andere verharding bevatten. Het pakket is gemiddeld een meter dik, maar dit kan plaatselijk vari\u00ebren.\n\nDe geplande werkzaamheden zijn overwegend beperkt tot het reeds bestaande wegtrac\u00e9 en het opgebrachte pakket. Indien graafwerkzaamheden plaats vinden die dieper reiken dan het opgebrachte pakket of daarbuiten plaats vinden, is het mogelijk dat archeologische resten worden verstoord. Daarom is een verwachtingsmodel gemaakt van de oorspronkelijke ondergrond van het plangebied. Deze verwachting is opgesteld op basis van het gemeentelijke beleid van de gemeenten Castricum en Uitgeest, de natuurlijke ondergrond en bekende archeologische resten. Met de gecombineerde resultaten zijn een verwachtingskaart (bijlage 5a en 5b) en een advieskaart (bijlage 6a en 6b) opgesteld.\n\nMet de gegevens die ten tijde van het bureauonderzoek beschikbaar zijn gesteld, wordt aangenomen dat vrijwel alle geplande werkzaamheden binnen het opgebrachte pakket plaats vinden.;19C;N203;Uitgeest & Castricum;Uitgeest & Castricum;Noord-Holland;52.5434845;4.69437237",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0a7f1ab6-291f-5192-abbd-6a547e9b3a98",
-    "notes": [
-        "In opdracht van Advin BV heeft IDDS Archeologie in december 2014 een archeologisch bureauonderzoek uitgevoerd voor de N203 Castricum en Uitgeest, gemeenten Castricum & Uitgeest. De aanleiding voor dit onderzoek is het geplande groot onderhoud aan de N203 tussen de aansluiting met de N513 Zeeweg en de oprit naar de A9.\n\nHet bureauonderzoek heeft uitgewezen dat de N203 is aangelegd in de jaren 30 van de 20e eeuw. Daarvoor bestond het plangebied uit weilanden met enkele slootjes en op enkele plaatsen een dijk. Voor de aanleg van de N203 is het oude landschap ge\u00ebgaliseerd en opgehoogd. Het ophoogpakket bestaat voornamelijk uit zand, maar kan tevens puinresten en andere verharding bevatten. Het pakket is gemiddeld een meter dik, maar dit kan plaatselijk vari\u00ebren.\n\nDe geplande werkzaamheden zijn overwegend beperkt tot het reeds bestaande wegtrac\u00e9 en het opgebrachte pakket. Indien graafwerkzaamheden plaats vinden die dieper reiken dan het opgebrachte pakket of daarbuiten plaats vinden, is het mogelijk dat archeologische resten worden verstoord. Daarom is een verwachtingsmodel gemaakt van de oorspronkelijke ondergrond van het plangebied. Deze verwachting is opgesteld op basis van het gemeentelijke beleid van de gemeenten Castricum en Uitgeest, de natuurlijke ondergrond en bekende archeologische resten. Met de gecombineerde resultaten zijn een verwachtingskaart (bijlage 5a en 5b) en een advieskaart (bijlage 6a en 6b) opgesteld.\n\nMet de gegevens die ten tijde van het bureauonderzoek beschikbaar zijn gesteld, wordt aangenomen dat vrijwel alle geplande werkzaamheden binnen het opgebrachte pakket plaats vinden."
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:60746"
-    ],
-    "oai_set": [
-        "D30000:D37000"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Archaeology"
-        },
-        {
-            "name": "Archeologisch bureauonderzoek"
-        }
-    ],
-    "title": [
-        "N203, Gemeenten Castricum & Uitgeest",
-        "Archeologisch bureauonderzoek"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a7f83a8-951f-5546-86e6-8650a47a266d.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0a7f83a8-951f-5546-86e6-8650a47a266d.json
deleted file mode 100644
index 9412a89d..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a7f83a8-951f-5546-86e6-8650a47a266d.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "SOB Research"
-    ],
-    "Contributor": [
-        "SOB Research"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.17026/dans-z3m-94ma",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:42278",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:42278"
-    ],
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "SOB Research"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "SpatialCoverage": [
-        "\n            "
-    ],
-    "TemporalCoverage": [
-        "2011-02-01",
-        "2006-02",
-        "2011-01-26"
-    ],
-    "author": [
-        "Ras, J."
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:42278;2018-09-18T16:57:31Z;D30000:D37000;driver;easy-collection:4;10.17026/dans-z3m-94ma;Ras, J.;Waarderend Archeologisch Onderzoek; Archeologische Vindplaats Recreatieoord Binnenmaas, Gemeente Binnenmaas;SOB 2006 RAS.377;SOB 2006 RAS.377;SOB Research;2011;Archaeology;SOB Research;2011-02-01;2006-02;2011-01-26;nl;Dataset;urn:nbn:nl:ui:13-8r5-tu8;easy-dataset:42278;twips.dans.knaw.nl-3184349110073622934-1296594263375;info:eu-repo/semantics/openAccess;onderzoeksrapport;Zuid-Holland; Binnenmaas; Mijnsheerenland; Recreatieoord Binnenmaas;51.80048084;4.53128793",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0a7f83a8-951f-5546-86e6-8650a47a266d",
-    "notes": [
-        "onderzoeksrapport"
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:42278"
-    ],
-    "oai_set": [
-        "D30000:D37000",
-        "driver",
-        "easy-collection:4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Archaeology"
-        }
-    ],
-    "title": [
-        "Waarderend Archeologisch Onderzoek; Archeologische Vindplaats Recreatieoord Binnenmaas, Gemeente Binnenmaas",
-        "SOB 2006 RAS.377",
-        "SOB 2006 RAS.377"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a8131aa-19b9-558f-bdfd-8edacc151e81.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0a8131aa-19b9-558f-bdfd-8edacc151e81.json
deleted file mode 100644
index fc2327e3..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a8131aa-19b9-558f-bdfd-8edacc151e81.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.5061/dryad.74458",
-    "DiscHierarchy": [
-        "1.3.3",
-        "Fine Arts, Music, Theatre and Media Studies",
-        "Dance"
-    ],
-    "Discipline": "Medicine",
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:93620",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:93620"
-    ],
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Data Archiving and Networked Services (DANS)"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/closedAccess"
-    ],
-    "TempCoverageBegin": 63594417599,
-    "TempCoverageEnd": 63594417599,
-    "TemporalCoverage": " period : ( 2016-03-24T11:59:59Z - 2016-03-24T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2016-03-24T11:59:59Z",
-    "TemporalCoverage:EndDate": "2016-03-24T11:59:59Z",
-    "author": [
-        "Gattolliat, Jean-Luc",
-        "Keller, Irene",
-        "Leys, Marie Aurore",
-        "Robinson, Christopher T.",
-        "R\u00e4s\u00e4nen, Katja"
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:93620;2018-09-18T17:36:32Z;D20000;Leys, Marie Aurore;Keller, Irene;R\u00e4s\u00e4nen, Katja;Gattolliat, Jean-Luc;Robinson, Christopher T.;Data from: Distribution and population genetic variation of cryptic species of the Alpine mayfly Baetis alpinus (Ephemeroptera: Baetidae) in the Central Alps;Data Archiving and Networked Services (DANS);2016;Life sciences, medicine and health care ;2016-03-24T15:31:32.000+01:00;2016-03-24T15:31:32.000+01:00;Dataset;10.5061/dryad.74458;urn:nbn:nl:ui:13-01-npzl;easy-dataset:93620;info:eu-repo/semantics/closedAccess;Background: Many species contain evolutionarily distinct groups that are genetically highly differentiated but morphologically difficult to distinguish (i.e., cryptic species). The presence of cryptic species poses significant challenges for the accurate assessment of biodiversity and, if unrecognized, may lead to erroneous inferences in many fields of biological research and conservation. Results: We tested for cryptic genetic variation within the broadly distributed alpine mayfly Baetis alpinus across several major European drainages in the central Alps. Bayesian clustering and multivariate analyses of nuclear microsatellite loci, combined with phylogenetic analyses of mitochondrial DNA, were used to assess population genetic structure and diversity. We identified two genetically highly differentiated lineages (A and B) that had no obvious differences in regional distribution patterns, and occurred in local sympatry. Furthermore, the two lineages differed in relative abundance, overall levels of genetic diversity as well as patterns of population structure: lineage A was abundant, widely distributed and had a higher level of genetic variation, whereas lineage B was less abundant, more prevalent in spring-fed tributaries than glacier-fed streams and restricted to high elevations. Subsequent morphological analyses revealed that traits previously acknowledged as intraspecific variation of B. alpinus in fact segregated these two lineages. Conclusions: Taken together, our findings indicate that even common and apparently ecologically well-studied species may consist of reproductively isolated units, with distinct evolutionary histories and likely different ecology and evolutionary potential. These findings emphasize the need to investigate hidden diversity even in well-known species to allow for appropriate assessment of biological diversity and conservation measures.",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0a8131aa-19b9-558f-bdfd-8edacc151e81",
-    "notes": [
-        "Background: Many species contain evolutionarily distinct groups that are genetically highly differentiated but morphologically difficult to distinguish (i.e., cryptic species). The presence of cryptic species poses significant challenges for the accurate assessment of biodiversity and, if unrecognized, may lead to erroneous inferences in many fields of biological research and conservation. Results: We tested for cryptic genetic variation within the broadly distributed alpine mayfly Baetis alpinus across several major European drainages in the central Alps. Bayesian clustering and multivariate analyses of nuclear microsatellite loci, combined with phylogenetic analyses of mitochondrial DNA, were used to assess population genetic structure and diversity. We identified two genetically highly differentiated lineages (A and B) that had no obvious differences in regional distribution patterns, and occurred in local sympatry. Furthermore, the two lineages differed in relative abundance, overall levels of genetic diversity as well as patterns of population structure: lineage A was abundant, widely distributed and had a higher level of genetic variation, whereas lineage B was less abundant, more prevalent in spring-fed tributaries than glacier-fed streams and restricted to high elevations. Subsequent morphological analyses revealed that traits previously acknowledged as intraspecific variation of B. alpinus in fact segregated these two lineages. Conclusions: Taken together, our findings indicate that even common and apparently ecologically well-studied species may consist of reproductively isolated units, with distinct evolutionary histories and likely different ecology and evolutionary potential. These findings emphasize the need to investigate hidden diversity even in well-known species to allow for appropriate assessment of biological diversity and conservation measures."
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:93620"
-    ],
-    "oai_set": [
-        "D20000"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Life sciences"
-        },
-        {
-            "name": "medicine health care"
-        }
-    ],
-    "title": [
-        "Data from: Distribution and population genetic variation of cryptic species of the Alpine mayfly Baetis alpinus (Ephemeroptera: Baetidae) in the Central Alps"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a87620d-715a-5814-9637-fe7b403d5187.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0a87620d-715a-5814-9637-fe7b403d5187.json
deleted file mode 100644
index 0433c688..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a87620d-715a-5814-9637-fe7b403d5187.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Fabio Minghini"
-    ],
-    "Contributor": [
-        "Fabio Minghini"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.17632/rrvpjsrb5w.1",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:109836",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:109836"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Data Archiving and Networked Services (DANS)"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/closedAccess",
-        "License: http://creativecommons.org/licenses/by/4.0"
-    ],
-    "TempCoverageBegin": 63668199599,
-    "TempCoverageEnd": 63668199599,
-    "TemporalCoverage": " period : ( 2018-07-26T11:59:59Z - 2018-07-26T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2018-07-26T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-07-26T11:59:59Z",
-    "author": [
-        "Minghini, F"
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:109836;2018-09-18T17:52:08Z;E10000;Minghini, F;via Mendeley Data;Dataset for built-up pultruded FRP columns;Data Archiving and Networked Services (DANS);2018;Interdisciplinary sciences;Fabio Minghini;2018-07-26T18:21:20.735+02:00;2018-07-26T18:21:20.735+02:00;Dataset;10.17632/rrvpjsrb5w.1;urn:nbn:nl:ui:13-qt-e7h4;easy-dataset:109836;info:eu-repo/semantics/closedAccess;License: http://creativecommons.org/licenses/by/4.0;Reported in the .xls files are the P-delta data points obtained from geometricaly nonlinear analyses and the values of Ploc obtained from eigenvalue analyses. All these data are necessary to reproduce the plots reported in the manuscript.",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0a87620d-715a-5814-9637-fe7b403d5187",
-    "notes": [
-        "Reported in the .xls files are the P-delta data points obtained from geometricaly nonlinear analyses and the values of Ploc obtained from eigenvalue analyses. All these data are necessary to reproduce the plots reported in the manuscript."
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:109836"
-    ],
-    "oai_set": [
-        "E10000"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Interdisciplinary sciences"
-        }
-    ],
-    "title": [
-        "Dataset for built-up pultruded FRP columns"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a8f996c-ef5e-5f11-b536-50eea26da452.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0a8f996c-ef5e-5f11-b536-50eea26da452.json
deleted file mode 100644
index f9be7ef8..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a8f996c-ef5e-5f11-b536-50eea26da452.json
+++ /dev/null
@@ -1,101 +0,0 @@
-{
-    "Contact": [
-        "Archeologie West-Friesland, Hoorn"
-    ],
-    "Contributor": [
-        "Archeologie West-Friesland, Hoorn"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.17026/dans-25x-yct8",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "application/pdf"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:106907",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:106907"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Archeologie West-Friesland, Hoorn"
-    ],
-    "RelatedIdentifier": [
-        "https://archisarchief.cultureelerfgoed.nl/Archis2/Archeorapporten/37/AR32773"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "SpatialCoverage": [
-        "\n            "
-    ],
-    "TempCoverageBegin": 63492638399,
-    "TempCoverageEnd": 63651182399,
-    "TemporalCoverage": " period : ( 2013-01-01T11:59:59Z - 2018-01-10T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2013-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-01-10T11:59:59Z",
-    "author": [
-        "Schrickx, C.P."
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:106907;2018-09-18T17:50:19Z;D30000:D37000;easy-collection:4;10.17026/dans-25x-yct8;Schrickx, C.P.;Archeologie West-Friesland, Hoorn;Middeleeuwse woonterpjes in Wognum. Archeologisch onderzoek op het perceel kerkstraat 11 in Wognum, gemeente Medemblik;Rapport 55;Wognum - kerkstraat 11;Rapport 55;Wognum - kerkstraat 11;Archeologie West-Friesland, Hoorn;2018;Archaeology;Nederzetting - Huisterp (NHT);Nederzetting, onbepaald (NX);Middeleeuwen laat: 1050 - 1500 nC (LME);Middeleeuwen laat B: 1250 - 1500 nC (LMEB);Nieuwe tijd A: 1500 - 1650 nC (NTA);Nieuwe tijd B: 1650 - 1850 nC (NTB);Archeologie West-Friesland, Hoorn;2013-01-01;2018-01-10;nl;Dataset;urn:nbn:nl:ui:13-az-kb42;easy-dataset:106907;https://archisarchief.cultureelerfgoed.nl/Archis2/Archeorapporten/37/AR32773;application/pdf;info:eu-repo/semantics/openAccess;Onderzoeksrapport;Wognum;Medemblik;Noord-Holland;kerkstraat 11;52.68107126;5.02440426",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0a8f996c-ef5e-5f11-b536-50eea26da452",
-    "notes": [
-        "Onderzoeksrapport"
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:106907"
-    ],
-    "oai_set": [
-        "D30000:D37000",
-        "easy-collection:4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Archaeology"
-        },
-        {
-            "name": "Nederzetting - Huisterp NHT"
-        },
-        {
-            "name": "Nederzetting"
-        },
-        {
-            "name": "onbepaald NX"
-        },
-        {
-            "name": "Middeleeuwen laat - nC LME"
-        },
-        {
-            "name": "Middeleeuwen laat B - nC LMEB"
-        },
-        {
-            "name": "Nieuwe tijd - nC NTA"
-        },
-        {
-            "name": "Nieuwe tijd B - nC NTB"
-        }
-    ],
-    "title": [
-        "Middeleeuwse woonterpjes in Wognum. Archeologisch onderzoek op het perceel kerkstraat 11 in Wognum, gemeente Medemblik",
-        "Rapport 55",
-        "Wognum - kerkstraat 11",
-        "Rapport 55",
-        "Wognum - kerkstraat 11"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a9a01dd-1474-5355-a931-b3ea3ff3bdde.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0a9a01dd-1474-5355-a931-b3ea3ff3bdde.json
deleted file mode 100644
index a69eb883..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a9a01dd-1474-5355-a931-b3ea3ff3bdde.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Grontmij",
-        "Fijma, P."
-    ],
-    "Contributor": [
-        "Grontmij",
-        "Fijma, P."
-    ],
-    "DOI": "http://dx.doi.org/doi:10.17026/dans-273-b47b",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "12 p."
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:23218",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:23218"
-    ],
-    "PublicationTimestamp": "2010-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "Grontmij"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/restrictedAccess"
-    ],
-    "TemporalCoverage": [
-        "2010-01-20",
-        "2006",
-        "2010-01-19"
-    ],
-    "author": [
-        "Huizing-Schreur, A."
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:23218;2018-09-18T16:46:44Z;D30000:D37000;10.17026/dans-273-b47b;Huizing-Schreur, A.;Archeologisch onderzoek recreatiegebied Kievitsveld Epe;inventariserend veldonderzoek;GAR 156;Grontmij;2010;Archaeology;PROSPECTIE;Fijma, P.;Grontmij;2010-01-20;2006;2010-01-19;nl;Dataset;urn:nbn:nl:ui:13-6j4-0yk;easy-dataset:23218;twips.dans.knaw.nl-7385991802004325960-1264022376986;12 p.;info:eu-repo/semantics/restrictedAccess;onderzoeksrapport;Epe;Gelderland;Kievitsveld;Nederland;e-ne (MARC21)",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0a9a01dd-1474-5355-a931-b3ea3ff3bdde",
-    "notes": [
-        "onderzoeksrapport"
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:23218"
-    ],
-    "oai_set": [
-        "D30000:D37000"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Archaeology"
-        },
-        {
-            "name": "PROSPECTIE"
-        }
-    ],
-    "title": [
-        "Archeologisch onderzoek recreatiegebied Kievitsveld Epe",
-        "inventariserend veldonderzoek",
-        "GAR 156"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a9b0f04-6ad8-59c2-97bf-df225d737f12.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0a9b0f04-6ad8-59c2-97bf-df225d737f12.json
deleted file mode 100644
index 5ca46c45..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a9b0f04-6ad8-59c2-97bf-df225d737f12.json
+++ /dev/null
@@ -1,92 +0,0 @@
-{
-    "Contact": [
-        "ROB, Amersfoort",
-        "Zijverden, W.K. van",
-        "Haaster, H. van",
-        "Robeerst, J.M.M."
-    ],
-    "Contributor": [
-        "ROB, Amersfoort",
-        "Zijverden, W.K. van",
-        "Haaster, H. van",
-        "Robeerst, J.M.M."
-    ],
-    "DOI": "http://dx.doi.org/doi:10.17026/dans-223-vxtu",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "QuarkXpress",
-        "application/postscript"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:38739",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:38739"
-    ],
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "ROB, Amersfoort"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "SpatialCoverage": [
-        "\n            "
-    ],
-    "TemporalCoverage": [
-        "2011-05-24",
-        "1998",
-        "2011-05-24"
-    ],
-    "author": [
-        "Anscher, T.J. ten",
-        "Jongste, P.F.B."
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:38739;2018-09-18T16:55:05Z;D30000:D37000;driver;easy-collection:4;10.17026/dans-223-vxtu;Jongste, P.F.B.;Anscher, T.J. ten;Aanvullend Archeologisch Onderzoek in het trac\u00e9 van de Betuweroute, vindplaats 22, Valburg/Zettensche Plas;RAM 19;ROB, Amersfoort;2011;Archaeology;aanvullend archeologisch onderzoek (AAO);Neolithicum laat: 2850 - 2000 vC (NEOL);Bronstijd midden: 1800 - 1100 vC (BRONSM);Haaster, H. van;Robeerst, J.M.M.;Zijverden, W.K. van;ROB, Amersfoort;2011-05-24;1998;2011-05-24;nl;Dataset;urn:nbn:nl:ui:13-w84-mj5;easy-dataset:38739;twips.dans.knaw.nl--3005317610224733491-1306227028444;QuarkXpress;application/postscript;info:eu-repo/semantics/openAccess;Op verzoek van de Nederlandse Spoorwegen Railinfrabeheer Managementgroep Betuweroute heeft de Rijksdienst voor het Oudheidkundig Bodemonderzoek (ROB) een Aanvullend Archeologisch Onderzoek (AAO) uitgevoerd in de gemeente Valburg. Object van het onderzoek was een vindplaats (toponiem 'Zettensche Plas') bij Zetten, direct ten noorden van rijksweg A15 en ten oosten van de Zettensche plas. Deze vindplaats is in 1994 tijdens een boorcampagne ontdekt door de Stichting Regionaal Archeologisch Archiverings Project.\nDe vindplaats ligt in het trac\u00e9 van de Betuweroute en wordt door de aanleg van het cunet bedreigd.\nHet doel van het AAO was inzicht te verkrijgen in de datering, de aard en de kwaliteit van deze vindplaats ten behoeve van een definitieve waardering. Daartoe zijn acht putten aangelegd (tezamen 124,16 m2). In totaal is van de vondstlaag 2,85 m3 schavenderwijs onderzocht en 0,33 m3 gezeefd.\nVindplaats 22 ligt op komafzettingen boven crevasseafzettingen. De vindplaats bestaat uit twee gave, kleine vondstconcentraties, opgevat als sites, omringd door een lichte vondstruis. Een klein deel van de vondsten van site 1 dateert uit het Laat-Neolithicum (KB of eventueel WKD). De meerderheid stamt uit de Midden-Bronstijd (HVS 1, misschien ook wel HVS 2-3). Site 2 dateert eveneens uit de Midden-Bronstijd (HVS 1-2, misschien ook wel HVS 3). De sites zijn ge\u00efnterpreteerd als kortstondig gebruikte, tijdelijke kampementen voor bijzondere activiteiten. In die activiteiten hebben vee en vuur een rol gespeeld. Het aardewerk is sterk verweerd en gefragmenteeerd. Ook het botmateriaal is sterk gefragmenteerd. Behalve verbrand bot is ook onverbrand bot aanwezig. Dat laatste is matig tot slecht geconserveerd. Er zijn maar heel weinig onverbrande zaden gevonden. Of zij van prehistorische datum zijn, is onduidelijk. Verkoolde zaden zijn in de monsters afwezig. Daarom zullen zij op de vindplaats als geheel op zijn best schaars zijn. Gezien de uitkomsten van het AAO zijn de mogelijkheden op ecologisch gebied bij verder onderzoek wel aanwezig, zij het in beperkte mate.\nVindplaats 22 is behoudenswaardig op grond van gaafheid, de zeldzaamheid van het site-type en de hoge archeologische contextwaarde.;Gelderland;Valburg;Zetten;Zettensche Plas;51.91700927;5.70494278",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0a9b0f04-6ad8-59c2-97bf-df225d737f12",
-    "notes": [
-        "Op verzoek van de Nederlandse Spoorwegen Railinfrabeheer Managementgroep Betuweroute heeft de Rijksdienst voor het Oudheidkundig Bodemonderzoek (ROB) een Aanvullend Archeologisch Onderzoek (AAO) uitgevoerd in de gemeente Valburg. Object van het onderzoek was een vindplaats (toponiem 'Zettensche Plas') bij Zetten, direct ten noorden van rijksweg A15 en ten oosten van de Zettensche plas. Deze vindplaats is in 1994 tijdens een boorcampagne ontdekt door de Stichting Regionaal Archeologisch Archiverings Project.\nDe vindplaats ligt in het trac\u00e9 van de Betuweroute en wordt door de aanleg van het cunet bedreigd.\nHet doel van het AAO was inzicht te verkrijgen in de datering, de aard en de kwaliteit van deze vindplaats ten behoeve van een definitieve waardering. Daartoe zijn acht putten aangelegd (tezamen 124,16 m2). In totaal is van de vondstlaag 2,85 m3 schavenderwijs onderzocht en 0,33 m3 gezeefd.\nVindplaats 22 ligt op komafzettingen boven crevasseafzettingen. De vindplaats bestaat uit twee gave, kleine vondstconcentraties, opgevat als sites, omringd door een lichte vondstruis. Een klein deel van de vondsten van site 1 dateert uit het Laat-Neolithicum (KB of eventueel WKD). De meerderheid stamt uit de Midden-Bronstijd (HVS 1, misschien ook wel HVS 2-3). Site 2 dateert eveneens uit de Midden-Bronstijd (HVS 1-2, misschien ook wel HVS 3). De sites zijn ge\u00efnterpreteerd als kortstondig gebruikte, tijdelijke kampementen voor bijzondere activiteiten. In die activiteiten hebben vee en vuur een rol gespeeld. Het aardewerk is sterk verweerd en gefragmenteeerd. Ook het botmateriaal is sterk gefragmenteerd. Behalve verbrand bot is ook onverbrand bot aanwezig. Dat laatste is matig tot slecht geconserveerd. Er zijn maar heel weinig onverbrande zaden gevonden. Of zij van prehistorische datum zijn, is onduidelijk. Verkoolde zaden zijn in de monsters afwezig. Daarom zullen zij op de vindplaats als geheel op zijn best schaars zijn. Gezien de uitkomsten van het AAO zijn de mogelijkheden op ecologisch gebied bij verder onderzoek wel aanwezig, zij het in beperkte mate.\nVindplaats 22 is behoudenswaardig op grond van gaafheid, de zeldzaamheid van het site-type en de hoge archeologische contextwaarde."
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:38739"
-    ],
-    "oai_set": [
-        "D30000:D37000",
-        "driver",
-        "easy-collection:4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Archaeology"
-        },
-        {
-            "name": "aanvullend archeologisch onderzoek AAO"
-        },
-        {
-            "name": "Neolithicum laat - vC NEOL"
-        },
-        {
-            "name": "Bronstijd midden - vC BRONSM"
-        }
-    ],
-    "title": [
-        "Aanvullend Archeologisch Onderzoek in het trac\u00e9 van de Betuweroute, vindplaats 22, Valburg/Zettensche Plas",
-        "RAM 19"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a9f9f27-92c7-5cda-80a6-49b406a76b2b.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0a9f9f27-92c7-5cda-80a6-49b406a76b2b.json
deleted file mode 100644
index 192b2643..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0a9f9f27-92c7-5cda-80a6-49b406a76b2b.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "ADC ArcheoProjecten"
-    ],
-    "Contributor": [
-        "ADC ArcheoProjecten"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.17026/dans-xj6-pvkp",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "application/pdf"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:108007",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:108007"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "ADC ArcheoProjecten"
-    ],
-    "RelatedIdentifier": [
-        "https://archisarchief.cultureelerfgoed.nl/Archis2/Archeorapporten/24/AR26670"
-    ],
-    "ResourceType": [
-        "Dataset; datacollection"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "SpatialCoverage": [
-        "\n            "
-    ],
-    "TempCoverageBegin": 63458337599,
-    "TempCoverageEnd": 63651182399,
-    "TemporalCoverage": " period : ( 2011-12-01T11:59:59Z - 2018-01-10T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2011-12-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-01-10T11:59:59Z",
-    "author": [
-        "Rooij, J.A.G. van"
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:108007;2018-09-18T17:50:17Z;D30000:D37000;easy-collection:4;10.17026/dans-xj6-pvkp;Rooij, J.A.G. van;ADC ArcheoProjecten;Osseweg 1 te Heesch (gemeente Bernheze). Een Inventariserend Veldonderzoek in de vorm van een verkennend booronderzoek.;ADC-rapport 2950;Heesch - Osseweg 1-3;Osseweg 1-3;ADC-rapport 2950;Heesch - Osseweg 1-3;Osseweg 1-3;ADC ArcheoProjecten;2018;Archaeology;ADC ArcheoProjecten;2011-12-01;2018-01-10;nl;Dataset;urn:nbn:nl:ui:13-of-28pi;easy-dataset:108007;https://archisarchief.cultureelerfgoed.nl/Archis2/Archeorapporten/24/AR26670;application/pdf;info:eu-repo/semantics/openAccess;Onderzoeksrapport;Heesch;Bernheze;Noord-Brabant;Osseweg 1-3;51.73661796;5.53423315",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0a9f9f27-92c7-5cda-80a6-49b406a76b2b",
-    "notes": [
-        "Onderzoeksrapport"
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:108007"
-    ],
-    "oai_set": [
-        "D30000:D37000",
-        "easy-collection:4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Archaeology"
-        }
-    ],
-    "title": [
-        "Osseweg 1 te Heesch (gemeente Bernheze). Een Inventariserend Veldonderzoek in de vorm van een verkennend booronderzoek.",
-        "ADC-rapport 2950",
-        "Heesch - Osseweg 1-3",
-        "Osseweg 1-3",
-        "ADC-rapport 2950",
-        "Heesch - Osseweg 1-3",
-        "Osseweg 1-3"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0aa74459-4604-57f0-b40c-ce1e758e4e09.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0aa74459-4604-57f0-b40c-ce1e758e4e09.json
deleted file mode 100644
index 527e3725..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0aa74459-4604-57f0-b40c-ce1e758e4e09.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.5061/dryad.d63t5",
-    "DiscHierarchy": [
-        "1.3.3",
-        "Fine Arts, Music, Theatre and Media Studies",
-        "Dance"
-    ],
-    "Discipline": "Medicine",
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:93653",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:93653"
-    ],
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Data Archiving and Networked Services (DANS)"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/closedAccess"
-    ],
-    "TempCoverageBegin": 63603140399,
-    "TempCoverageEnd": 63603140399,
-    "TemporalCoverage": " period : ( 2016-07-03T11:59:59Z - 2016-07-03T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2016-07-03T11:59:59Z",
-    "TemporalCoverage:EndDate": "2016-07-03T11:59:59Z",
-    "author": [
-        "Strickler, Susan R.",
-        "Smith, Stacey D.",
-        "Mueller, Lukas A.",
-        "Gates, Daniel J.",
-        "Olson, Bradley J. S. C."
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:93653;2018-09-18T17:36:35Z;D20000;Gates, Daniel J.;Strickler, Susan R.;Mueller, Lukas A.;Olson, Bradley J. S. C.;Smith, Stacey D.;Data from: Diversification of R2R3-MYB transcription factors in the tomato family Solanaceae;Data Archiving and Networked Services (DANS);2016;Life sciences, medicine and health care ;2016-07-03T18:26:11.000+02:00;2016-07-03T18:26:11.000+02:00;Dataset;10.5061/dryad.d63t5;urn:nbn:nl:ui:13-jk-x5tu;easy-dataset:93653;info:eu-repo/semantics/closedAccess;MYB transcription factors play an important role in regulating key plant developmental processes involving defense, cell shape, pigmentation, and root formation. Within this gene family, sequences containing an R2R3 MYB domain are the most abundant type and exhibit a wide diversity of functions. In this study, we identify 559 R2R3 MYB genes using whole genome data from four species of Solanaceae and reconstruct their evolutionary relationships. We compare the Solanaceae R2R3 MYBs to the well-characterized Arabidopsis thaliana sequences to estimate functional diversity and to identify gains and losses of MYB clades in the Solanaceae. We identify numerous R2R3 MYBs that do not appear closely related to Arabidopsis MYBs, and thus may represent clades of genes that have been lost along the Arabidopsis lineage or gained after the divergence of Rosid and Asterid lineages. Despite differences in the distribution of R2R3 MYBs across functional subgroups and species, the overall size of the R2R3 subfamily has changed relatively little over the roughly 50 million-year history of Solanaceae. We added our information regarding R2R3 MYBs in Solanaceae to other data and performed a meta-analysis to trace the evolution of subfamily size across land plants. The results reveal many shifts in the number of R2R3 genes, including a 54 % increase along the angiosperm stem lineage. The variation in R2R3 subfamily size across land plants is weakly positively correlated with genome size and strongly positively correlated with total number of genes. The retention of such a large number of R2R3 copies over long evolutionary time periods suggests that they have acquired new functions and been maintained by selection. Discovering the nature of this functional diversity will require integrating forward and reverse genetic approaches on an -omics scale.",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0aa74459-4604-57f0-b40c-ce1e758e4e09",
-    "notes": [
-        "MYB transcription factors play an important role in regulating key plant developmental processes involving defense, cell shape, pigmentation, and root formation. Within this gene family, sequences containing an R2R3 MYB domain are the most abundant type and exhibit a wide diversity of functions. In this study, we identify 559 R2R3 MYB genes using whole genome data from four species of Solanaceae and reconstruct their evolutionary relationships. We compare the Solanaceae R2R3 MYBs to the well-characterized Arabidopsis thaliana sequences to estimate functional diversity and to identify gains and losses of MYB clades in the Solanaceae. We identify numerous R2R3 MYBs that do not appear closely related to Arabidopsis MYBs, and thus may represent clades of genes that have been lost along the Arabidopsis lineage or gained after the divergence of Rosid and Asterid lineages. Despite differences in the distribution of R2R3 MYBs across functional subgroups and species, the overall size of the R2R3 subfamily has changed relatively little over the roughly 50 million-year history of Solanaceae. We added our information regarding R2R3 MYBs in Solanaceae to other data and performed a meta-analysis to trace the evolution of subfamily size across land plants. The results reveal many shifts in the number of R2R3 genes, including a 54 % increase along the angiosperm stem lineage. The variation in R2R3 subfamily size across land plants is weakly positively correlated with genome size and strongly positively correlated with total number of genes. The retention of such a large number of R2R3 copies over long evolutionary time periods suggests that they have acquired new functions and been maintained by selection. Discovering the nature of this functional diversity will require integrating forward and reverse genetic approaches on an -omics scale."
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:93653"
-    ],
-    "oai_set": [
-        "D20000"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Life sciences"
-        },
-        {
-            "name": "medicine health care"
-        }
-    ],
-    "title": [
-        "Data from: Diversification of R2R3-MYB transcription factors in the tomato family Solanaceae"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0aac12b0-6dfd-51ac-8bf2-69c794cc721b.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0aac12b0-6dfd-51ac-8bf2-69c794cc721b.json
deleted file mode 100644
index 4cd9b072..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0aac12b0-6dfd-51ac-8bf2-69c794cc721b.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.5061/dryad.5c960",
-    "DiscHierarchy": [
-        "1.3.3",
-        "Fine Arts, Music, Theatre and Media Studies",
-        "Dance"
-    ],
-    "Discipline": "Medicine",
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:95385",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:95385"
-    ],
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Data Archiving and Networked Services (DANS)"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/closedAccess"
-    ],
-    "TempCoverageBegin": 63612385199,
-    "TempCoverageEnd": 63612385199,
-    "TemporalCoverage": " period : ( 2016-10-18T11:59:59Z - 2016-10-18T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2016-10-18T11:59:59Z",
-    "TemporalCoverage:EndDate": "2016-10-18T11:59:59Z",
-    "author": [
-        "Hall, Nathan E.",
-        "Murphy, Nicholas P.",
-        "Green, Bridget S.",
-        "Ilyushkina, Irina",
-        "Strugnell, Jan M.",
-        "Doyle, Stephen R.",
-        "Robinson, Andrew J.",
-        "Bell, James J.",
-        "Villacorta-Rath, Cecilia"
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:95385;2018-09-18T17:38:10Z;D20000;Villacorta-Rath, Cecilia;Ilyushkina, Irina;Strugnell, Jan M.;Green, Bridget S.;Murphy, Nicholas P.;Doyle, Stephen R.;Hall, Nathan E.;Robinson, Andrew J.;Bell, James J.;Data from: Outlier SNPs enable food traceability of the southern rock lobster, Jasus edwardsii;Data Archiving and Networked Services (DANS);2016;Life sciences, medicine and health care ;2016-10-18T14:14:09.000+02:00;2016-10-18T14:14:09.000+02:00;Dataset;10.5061/dryad.5c960;urn:nbn:nl:ui:13-mb-fzbw;easy-dataset:95385;info:eu-repo/semantics/closedAccess;Recent advances in next-generation sequencing have enhanced the resolution of population genetic studies of non-model organisms through increased marker generation and sample throughput. Using double digest restriction site-associated DNA sequencing (ddRADseq), we investigated the population structure of the commercially important southern rock lobster, Jasus edwardsii, in Australia and New Zealand with the aim of identifying a panel of SNP markers that could be used to trace country of origin. Four ddRADseq libraries comprising a total of 88 individuals were sequenced on the Illumina MiSeq platform, and demultiplexed reads were used to create a reference catalog of loci. Individual reads were then mapped to the reference catalog, and variant calling was performed. We have characterized two single-nucleotide polymorphism (SNP) panels comprised in total of 656 SNPs. The first panel contained 535 neutral SNPs and the second, 121 outlier SNPs that were characteristic of being putatively under selection. Both neutral and outlier SNP panels showed significant differentiation between the two countries, with the outlier loci demonstrating much larger FST values (FST outlier SNP panel = 0.134, P < 0.0001; FST neutral SNP panel = 0.022, P < 0.0001). Assignment tests performed with the outlier SNP panel allocated 100 % of the individuals to country of origin, demonstrating the usefulness of these markers for food traceability of J. edwardsii.",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0aac12b0-6dfd-51ac-8bf2-69c794cc721b",
-    "notes": [
-        "Recent advances in next-generation sequencing have enhanced the resolution of population genetic studies of non-model organisms through increased marker generation and sample throughput. Using double digest restriction site-associated DNA sequencing (ddRADseq), we investigated the population structure of the commercially important southern rock lobster, Jasus edwardsii, in Australia and New Zealand with the aim of identifying a panel of SNP markers that could be used to trace country of origin. Four ddRADseq libraries comprising a total of 88 individuals were sequenced on the Illumina MiSeq platform, and demultiplexed reads were used to create a reference catalog of loci. Individual reads were then mapped to the reference catalog, and variant calling was performed. We have characterized two single-nucleotide polymorphism (SNP) panels comprised in total of 656 SNPs. The first panel contained 535 neutral SNPs and the second, 121 outlier SNPs that were characteristic of being putatively under selection. Both neutral and outlier SNP panels showed significant differentiation between the two countries, with the outlier loci demonstrating much larger FST values (FST outlier SNP panel = 0.134, P < 0.0001; FST neutral SNP panel = 0.022, P < 0.0001). Assignment tests performed with the outlier SNP panel allocated 100 % of the individuals to country of origin, demonstrating the usefulness of these markers for food traceability of J. edwardsii."
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:95385"
-    ],
-    "oai_set": [
-        "D20000"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Life sciences"
-        },
-        {
-            "name": "medicine health care"
-        }
-    ],
-    "title": [
-        "Data from: Outlier SNPs enable food traceability of the southern rock lobster, Jasus edwardsii"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0ac04acf-aae4-5ef2-a89e-8e508d242815.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0ac04acf-aae4-5ef2-a89e-8e508d242815.json
deleted file mode 100644
index c8e79551..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0ac04acf-aae4-5ef2-a89e-8e508d242815.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.5061/dryad.885c4",
-    "DiscHierarchy": [
-        "1.3.3",
-        "Fine Arts, Music, Theatre and Media Studies",
-        "Dance"
-    ],
-    "Discipline": "Medicine",
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:93309",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:93309"
-    ],
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Data Archiving and Networked Services (DANS)"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/closedAccess"
-    ],
-    "TempCoverageBegin": 63599943599,
-    "TempCoverageEnd": 63599943599,
-    "TemporalCoverage": " period : ( 2016-05-27T11:59:59Z - 2016-05-27T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2016-05-27T11:59:59Z",
-    "TemporalCoverage:EndDate": "2016-05-27T11:59:59Z",
-    "author": [
-        "Rubalcaba, Juan G.",
-        "Polo, Vicente",
-        "Veiga, Jos\u00e9 P."
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:93309;2018-09-18T17:36:06Z;D20000;Rubalcaba, Juan G.;Veiga, Jos\u00e9 P.;Polo, Vicente;Data from: Is offspring dispersal related to male mating status? An experiment with the facultatively polygynous spotless starling;Data Archiving and Networked Services (DANS);2016;Life sciences, medicine and health care ;2016-05-27T19:09:20.000+02:00;2016-05-27T19:09:20.000+02:00;Dataset;10.5061/dryad.885c4;urn:nbn:nl:ui:13-cp-erx3;easy-dataset:93309;info:eu-repo/semantics/closedAccess;Patterns of natal dispersal are generally sex-biased in vertebrates, i.e. female-biased in birds and male-biased in mammals. Interphyletic comparisons in mammals suggest that male-biased dispersal occurs in polygynous and promiscuous species where local mate competition among males exceeds local resource competition among females. However, few studies have analysed sex-biased patterns of dispersal at the individual level, and facultatively polygynous species might offer this opportunity. In the spotless starling, polygynous males exhibit their mating status during courtship carrying higher amounts of green plants to nests than monogamous males. We experimentally incorporated green plants to nests during four years to analyse long-term consequences on breeding success and offspring recruitment rates. We unexpectedly found that experimental sons recruited farther than experimental daughters, while control daughters recruited farther than control sons. A similar pattern was found using observational information from eight years. We discuss this result in the context of local competition hypothesis and speculate that sons dispersed farther from nests controlled by polygynous males to avoid competition with relatives. The amount of green plants in nests affects female perception of male attractiveness and degree of polygyny, although little is known about proximate mechanisms linking this process with the offspring dispersal behaviour. Our results support the idea that male-biased dispersal is related to polygyny in a facultatively polygynous bird.",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0ac04acf-aae4-5ef2-a89e-8e508d242815",
-    "notes": [
-        "Patterns of natal dispersal are generally sex-biased in vertebrates, i.e. female-biased in birds and male-biased in mammals. Interphyletic comparisons in mammals suggest that male-biased dispersal occurs in polygynous and promiscuous species where local mate competition among males exceeds local resource competition among females. However, few studies have analysed sex-biased patterns of dispersal at the individual level, and facultatively polygynous species might offer this opportunity. In the spotless starling, polygynous males exhibit their mating status during courtship carrying higher amounts of green plants to nests than monogamous males. We experimentally incorporated green plants to nests during four years to analyse long-term consequences on breeding success and offspring recruitment rates. We unexpectedly found that experimental sons recruited farther than experimental daughters, while control daughters recruited farther than control sons. A similar pattern was found using observational information from eight years. We discuss this result in the context of local competition hypothesis and speculate that sons dispersed farther from nests controlled by polygynous males to avoid competition with relatives. The amount of green plants in nests affects female perception of male attractiveness and degree of polygyny, although little is known about proximate mechanisms linking this process with the offspring dispersal behaviour. Our results support the idea that male-biased dispersal is related to polygyny in a facultatively polygynous bird."
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:93309"
-    ],
-    "oai_set": [
-        "D20000"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Life sciences"
-        },
-        {
-            "name": "medicine health care"
-        }
-    ],
-    "title": [
-        "Data from: Is offspring dispersal related to male mating status? An experiment with the facultatively polygynous spotless starling"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0b183e9c-16fe-5cbb-aa7c-8f207d37764b.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0b183e9c-16fe-5cbb-aa7c-8f207d37764b.json
deleted file mode 100644
index 8ddb3c73..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0b183e9c-16fe-5cbb-aa7c-8f207d37764b.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "RAAP Archeologisch Adviesbureau"
-    ],
-    "Contributor": [
-        "RAAP Archeologisch Adviesbureau"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.17026/dans-zw6-fqjd",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "32 p."
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:16129",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:16129"
-    ],
-    "PublicationTimestamp": "2009-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2009"
-    ],
-    "Publisher": [
-        "RAAP Archeologisch Adviesbureau"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "SpatialCoverage": [
-        "\n            "
-    ],
-    "TemporalCoverage": [
-        "2009-06-05",
-        "1998",
-        "2009-06-04"
-    ],
-    "author": [
-        "Soonius, C.M."
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:16129;2018-09-18T16:42:31Z;D30000:D37000;driver;easy-collection:4;10.17026/dans-zw6-fqjd;Soonius, C.M.;Provincie Noord-Holland, PWN-waterleiding Bergen-Limmen;archeologisch onderzoek;RAAPRAPPORT 266;archeologisch onderzoek;RAAPRAPPORT 266;RAAP Archeologisch Adviesbureau;2009;Archaeology;PROSPECTIE;RAAP Archeologisch Adviesbureau;2009-06-05;1998;2009-06-04;nl;Dataset;urn:nbn:nl:ui:13-gt5-v0t;easy-dataset:16129;twips.dans.knaw.nl-8205266172994353198-1244205194207;32 p.;info:eu-repo/semantics/openAccess;onderzoeksrapport;Limmen;Nederland;Noord-Holland;Bergen;e-ne (MARC21);52.69158248;4.74457951;52.5855416;4.67219661",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0b183e9c-16fe-5cbb-aa7c-8f207d37764b",
-    "notes": [
-        "onderzoeksrapport"
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:16129"
-    ],
-    "oai_set": [
-        "D30000:D37000",
-        "driver",
-        "easy-collection:4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Archaeology"
-        },
-        {
-            "name": "PROSPECTIE"
-        }
-    ],
-    "title": [
-        "Provincie Noord-Holland, PWN-waterleiding Bergen-Limmen",
-        "archeologisch onderzoek",
-        "RAAPRAPPORT 266",
-        "archeologisch onderzoek",
-        "RAAPRAPPORT 266"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0b427b65-8738-52b5-8e29-95c1b28be1e2.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0b427b65-8738-52b5-8e29-95c1b28be1e2.json
deleted file mode 100644
index 7f078c56..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0b427b65-8738-52b5-8e29-95c1b28be1e2.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "BAAC bv"
-    ],
-    "Contributor": [
-        "BAAC bv"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.17026/dans-z3u-2zav",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "application/pdf"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:113722",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:113722"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "BAAC bv"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/restrictedAccess"
-    ],
-    "SpatialCoverage": [
-        "\n            "
-    ],
-    "TempCoverageBegin": 63677879999,
-    "TempCoverageEnd": 63677879999,
-    "TemporalCoverage": " period : ( 2018-11-15T11:59:59Z - 2018-11-15T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2018-11-15T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-11-15T11:59:59Z",
-    "author": [
-        "Putten, M.J. van"
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:113722;2018-11-16T15:25:20Z;D30000:D37000;10.17026/dans-z3u-2zav;Putten, M.J. van;BAAC bv;Gemeente Venray. ooijen-Wanssum Hoogwatergeul. Deelgebied W1-west, vindplaats II te Wanssum;Inventariserend veldonderzoek (karterende fase plus);BAAC Rapport V-17.0226;BAAC bv;2018;Archaeology;Nederzetting, onbepaald (NX);Paleolithicum: tot 8800 vC (PALEO);BAAC bv;2018-11-15;2018-11-15;nl;Dataset;urn:nbn:nl:ui:13-m4-qvna;easy-dataset:113722;application/pdf;info:eu-repo/semantics/restrictedAccess;Op basis van het vondstmateriaal dat ter plaatse van vindplaats II is aangetroffen, kan worden geconcludeerd dat er aanwijzingen zijn voor bewoning gedurende de steentijd. De vindplaats heeft een oppervlakte van circa 107 m2.\nVoor vindplaatsen daterend uit deze periode dient rekening gehouden te worden met resten van jachtkampen van jagers-verzamelaars met een strooiing van bewerkt vuursteen en natuursteen. Het archeologisch relevante niveau bevindt zich op een diepte vari\u00ebrend van 80 cm-mv in het westelijke deel tot 35 cm-mv in het oostelijke deel. Dit betekent dat de vindplaats bij ondiepe verstoringen geen gevaar loopt te worden verstoord. BAAC bv hanteert als uitgangspunt dat verstoringen in het westelijke deel van het plangebied, daar waar de parallelweg zal worden aangelegd, tot 30 cm-mv geen bedreiging zullen vormen voor het bodemarchief. Hiermee wordt een buffer van circa 20 tot 50 cm gecre\u00eberd, wat afdoende zou moeten zijn om de vindplaats in situ te kunnen behouden. \nVoor wat betreft de weg die verdiept zal worden aangelegd, geldt dat de verstoringsdiepte van 1,2 meter beneden maaiveld te groot is. Het archeologisch relevante niveau bevindt zich namelijk ruim binnen deze 1,2 meter. Op bijlage 6 is echter zichtbaar dat de vindplaats zoals begrensd op basis van onderhavig onderzoek zich buiten de aan te leggen weg bevindt en derhalve ook niet bedreigd zal worden.  \n\nEr wordt derhalve geen vervolgonderzoek geadviseerd indien de verstoringdiepte ter plaatse van de parallelweg zich beperkt tot een diepte van maximaal 30 cm-mv en de geplande werkzaamheden voor de verdiept aan te leggen weg niet binnen de contouren van de vindplaats zullen plaatsvinden. Mocht dit technisch niet haalbaar zijn en verstoringen dieper dan 30 cm niet kunnen worden vermeden, dan wordt geadviseerd vervolgonderzoek te laten uitvoeren. Conform de huidige standaard voor waarderend onderzoek met betrekking tot een steentijdvindplaats is een waarderend booronderzoek de meest gebruikelijke methode. Er dient geboord te worden met een 2 bij 2,5 boorgrid, waarbij het sediment uit de archeologisch relevante bodemlaag wordt verzameld om elders, bijvoorbeeld op kantoor, nat te worden gezeefd en onderzocht op de aanwezigheid van archeologische indicatoren. Het doel van een dergelijk onderzoek zal zijn het vaststellen van de exacte aard, omvang, datering, gaafheid en conserveringsgraad van de vindplaats op basis waarvan de archeologische waarde van het gebied definitief kan worden vastgesteld.;Ooijen-Wanssum Hoogwatergeul;Wanssum;Gemeente Venray;Limburg;51.53388133;6.06570168",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0b427b65-8738-52b5-8e29-95c1b28be1e2",
-    "notes": [
-        "Op basis van het vondstmateriaal dat ter plaatse van vindplaats II is aangetroffen, kan worden geconcludeerd dat er aanwijzingen zijn voor bewoning gedurende de steentijd. De vindplaats heeft een oppervlakte van circa 107 m2.\nVoor vindplaatsen daterend uit deze periode dient rekening gehouden te worden met resten van jachtkampen van jagers-verzamelaars met een strooiing van bewerkt vuursteen en natuursteen. Het archeologisch relevante niveau bevindt zich op een diepte vari\u00ebrend van 80 cm-mv in het westelijke deel tot 35 cm-mv in het oostelijke deel. Dit betekent dat de vindplaats bij ondiepe verstoringen geen gevaar loopt te worden verstoord. BAAC bv hanteert als uitgangspunt dat verstoringen in het westelijke deel van het plangebied, daar waar de parallelweg zal worden aangelegd, tot 30 cm-mv geen bedreiging zullen vormen voor het bodemarchief. Hiermee wordt een buffer van circa 20 tot 50 cm gecre\u00eberd, wat afdoende zou moeten zijn om de vindplaats in situ te kunnen behouden. \nVoor wat betreft de weg die verdiept zal worden aangelegd, geldt dat de verstoringsdiepte van 1,2 meter beneden maaiveld te groot is. Het archeologisch relevante niveau bevindt zich namelijk ruim binnen deze 1,2 meter. Op bijlage 6 is echter zichtbaar dat de vindplaats zoals begrensd op basis van onderhavig onderzoek zich buiten de aan te leggen weg bevindt en derhalve ook niet bedreigd zal worden.  \n\nEr wordt derhalve geen vervolgonderzoek geadviseerd indien de verstoringdiepte ter plaatse van de parallelweg zich beperkt tot een diepte van maximaal 30 cm-mv en de geplande werkzaamheden voor de verdiept aan te leggen weg niet binnen de contouren van de vindplaats zullen plaatsvinden. Mocht dit technisch niet haalbaar zijn en verstoringen dieper dan 30 cm niet kunnen worden vermeden, dan wordt geadviseerd vervolgonderzoek te laten uitvoeren. Conform de huidige standaard voor waarderend onderzoek met betrekking tot een steentijdvindplaats is een waarderend booronderzoek de meest gebruikelijke methode. Er dient geboord te worden met een 2 bij 2,5 boorgrid, waarbij het sediment uit de archeologisch relevante bodemlaag wordt verzameld om elders, bijvoorbeeld op kantoor, nat te worden gezeefd en onderzocht op de aanwezigheid van archeologische indicatoren. Het doel van een dergelijk onderzoek zal zijn het vaststellen van de exacte aard, omvang, datering, gaafheid en conserveringsgraad van de vindplaats op basis waarvan de archeologische waarde van het gebied definitief kan worden vastgesteld."
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:113722"
-    ],
-    "oai_set": [
-        "D30000:D37000"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Archaeology"
-        },
-        {
-            "name": "Nederzetting"
-        },
-        {
-            "name": "onbepaald NX"
-        },
-        {
-            "name": "Paleolithicum tot vC PALEO"
-        }
-    ],
-    "title": [
-        "Gemeente Venray. ooijen-Wanssum Hoogwatergeul. Deelgebied W1-west, vindplaats II te Wanssum",
-        "Inventariserend veldonderzoek (karterende fase plus)",
-        "BAAC Rapport V-17.0226"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0b6044b0-d0d5-5dcf-9c5c-03eabcd833bc.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0b6044b0-d0d5-5dcf-9c5c-03eabcd833bc.json
deleted file mode 100644
index ee67d906..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0b6044b0-d0d5-5dcf-9c5c-03eabcd833bc.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Leuvering, J.H.F.",
-        "Emaus, A.A.G.",
-        "Borsboom, A.J.",
-        "Synthegra archeologie"
-    ],
-    "Contributor": [
-        "Leuvering, J.H.F.",
-        "Emaus, A.A.G.",
-        "Borsboom, A.J.",
-        "Synthegra archeologie"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.17026/dans-ztc-mgva",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "17 p."
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:18216",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:18216"
-    ],
-    "PublicationTimestamp": "2009-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2009"
-    ],
-    "Publisher": [
-        "Synthegra"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess",
-        "License: http://creativecommons.org/publicdomain/zero/1.0"
-    ],
-    "SpatialCoverage": [
-        "\n            "
-    ],
-    "TemporalCoverage": [
-        "2009-11-27",
-        "2006",
-        "2009-11-27"
-    ],
-    "author": [
-        "Kuijl, E.E.A. van der"
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:18216;2018-12-18T10:41:17Z;D30000:D37000;easy-collection:4;10.17026/dans-ztc-mgva;Kuijl, E.E.A. van der;Bureauonderzoek, karterend en waarderend booronderzoek, M\u00f6lnmarsch Elsbeekpolder te Marienberg;SYNTHEGRA 2006 066;SYNTHEGRA 2006 066;SYNTHEGRA 2006 066;Synthegra;2009;Archaeology;PROSPECTIE;Leuvering, J.H.F.;Borsboom, A.J.;Emaus, A.A.G.;Synthegra archeologie;2009-11-27;2006;2009-11-27;nl;Dataset;urn:nbn:nl:ui:13-kpz-der;easy-dataset:18216;twips.dans.knaw.nl--1776520409317885264-1259327088476;17 p.;info:eu-repo/semantics/openAccess;License: http://creativecommons.org/publicdomain/zero/1.0;onderzoeksrapport;Overijssel;Nederland;Mari\u00ebnberg;Hardenberg;M\u00f6lnmarsch Elsbeekpolder;e-ne (MARC21);52.51957198;6.56948205",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0b6044b0-d0d5-5dcf-9c5c-03eabcd833bc",
-    "notes": [
-        "onderzoeksrapport"
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:18216"
-    ],
-    "oai_set": [
-        "D30000:D37000",
-        "easy-collection:4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Archaeology"
-        },
-        {
-            "name": "PROSPECTIE"
-        }
-    ],
-    "title": [
-        "Bureauonderzoek, karterend en waarderend booronderzoek, M\u00f6lnmarsch Elsbeekpolder te Marienberg",
-        "SYNTHEGRA 2006 066",
-        "SYNTHEGRA 2006 066",
-        "SYNTHEGRA 2006 066"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0b6fd45e-c6e4-5ff7-8cdb-1c1065273d4e.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0b6fd45e-c6e4-5ff7-8cdb-1c1065273d4e.json
deleted file mode 100644
index 6c28123d..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0b6fd45e-c6e4-5ff7-8cdb-1c1065273d4e.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "ADC ArcheoProjecten"
-    ],
-    "Contributor": [
-        "ADC ArcheoProjecten"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.17026/dans-xnv-zcdf",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "application/pdf"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:66832",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:66832"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "ADC ArcheoProjecten"
-    ],
-    "RelatedIdentifier": [
-        "10.17026/dans-z3t-ps9j"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "SpatialCoverage": [
-        "\n            "
-    ],
-    "TempCoverageBegin": 63649454399,
-    "TempCoverageEnd": 63649540799,
-    "TemporalCoverage": " period : ( 2017-12-21T11:59:59Z - 2017-12-22T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2017-12-21T11:59:59Z",
-    "TemporalCoverage:EndDate": "2017-12-22T11:59:59Z",
-    "author": [
-        "Holl, J."
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:66832;2018-09-18T17:21:40Z;D30000:D37000;driver;easy-collection:4;10.17026/dans-xnv-zcdf;Holl, J.;ADC ArcheoProjecten;Onderdijk 126, Hendrik-Ido-Ambacht;Een Bureauonderzoek en Inventariserend Veldonderzoek in de vorm van een verkennend booronderzoek;Een Bureauonderzoek en Inventariserend Veldonderzoek in de vorm van een verkennend booronderzoek;ADC ArcheoProjecten;2017;Archaeology;Booronderzoek verkennende fase;ADC ArcheoProjecten;2017-12-21;2017-12-22;nl;Dataset;urn:nbn:nl:ui:13-3fvk-p6;easy-dataset:66832;10.17026/dans-z3t-ps9j;application/pdf;info:eu-repo/semantics/openAccess;ADC ArcheoProjecten heeft in november 2016 een bureauonderzoek en inventariserend veldonderzoek uitgevoerd op de locatie Onderdijk 126 te Hendrik-Ido-Ambacht, gemeente Hendrik-Ido-Ambacht. Aanleiding is de geplande nieuwbouw van vier woningen.\nOp basis van het bureauonderzoek werden op een diepte van ca. 1 m -mv oeverafzettingen van de Merwede of Waal verwacht. Op grond van de vormingsgeschiedenis kunnen in de top archeologische resten uit de Romeinse tijd aanwezig zijn. Deze resten bestaan overwegend uit bewoningsresten, zoals aardewerkconcentraties binnen een humeuze laag, aangevuld met grondsporen. Gedurende de Vroege Middeleeuwen vernatte het plangebied waarschijnlijk en raakte het met veen bedekt. Hierdoor werd het ongeschikt voor bewoning.\nIn de 10e eeuw werd het veengebied op grote schaal ontgonnen. Dit verkavelingspatroon is echter niet meer te zien in het landschap vanwege grootschalige overstromingen in de 14e eeuw. Hierna is de Zwijndrechtse Waard opnieuw bedijkt en ontgonnen. Het plangebied lag vanaf die tijd in \u2019De Volgerlanden\u2019, de \u2018slechte\u2019 gronden waar een overslagdek aanwezig was. Reeds op 16e-eeuwse kaarten is bebouwing langs de Veersedijk te zien, maar het is niet duidelijk of ook in het plangebied sprake was van bebouwing. Vanaf het begin van de 19e eeuw bestaat echter wel zekerheid over de aanwezigheid van bebouwing. In het plangebied kunnen mogelijk bewoningsresten voorkomen uit de periode vanaf de 14e eeuw. Deze worden vanaf het maaiveld verwacht, in een archeologische laag, een humeuze laag met aardewerk, dierlijk bot en bouwresten. Hieronder kunnen grondsporen zoals waterputten,afvalkuilen en greppels/sloten voorkomen. Naar verwachting zijn eventuele archeologische resten deels verstoord als gevolg van de aanleg van de latere bebouwing.\nTeneinde deze verwachting te toetsen en waar nodig aan te vullen is in het plangebied een verkennend booronderzoek uitgevoerd.\nTijdens dit onderzoek zijn de verwachte oeverafzettingen van de Merwede en/of Waal niet aangetroffen. De aangetroffen bodemopbouw bestaat uit veen, afgedekt door een pakket komafzettingen. Hierop is in \u00e9\u00e9n boring een laag overslagafzettingen aangetroffen. De natte omstandigheden zullen niet aantrekkelijk zijn geweest voor bewoning. Tijdens het booronderzoek zijn dan ook geen veraarde veenlagen of vegetatiehorizonten aangetroffen, die kunnen duiden op een bewoonbaar oppervlak. Bovendien is de bodem recentelijk omgewerkt tot 40 \u00e0 90 cm \u2013mv. Om deze redenen worden geen archeologische resten in het plangebied verwacht.;Onderdijk 126;Hendrik-Ido-Ambacht;Zuid-Holland;51.85031309;4.64889251",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0b6fd45e-c6e4-5ff7-8cdb-1c1065273d4e",
-    "notes": [
-        "ADC ArcheoProjecten heeft in november 2016 een bureauonderzoek en inventariserend veldonderzoek uitgevoerd op de locatie Onderdijk 126 te Hendrik-Ido-Ambacht, gemeente Hendrik-Ido-Ambacht. Aanleiding is de geplande nieuwbouw van vier woningen.\nOp basis van het bureauonderzoek werden op een diepte van ca. 1 m -mv oeverafzettingen van de Merwede of Waal verwacht. Op grond van de vormingsgeschiedenis kunnen in de top archeologische resten uit de Romeinse tijd aanwezig zijn. Deze resten bestaan overwegend uit bewoningsresten, zoals aardewerkconcentraties binnen een humeuze laag, aangevuld met grondsporen. Gedurende de Vroege Middeleeuwen vernatte het plangebied waarschijnlijk en raakte het met veen bedekt. Hierdoor werd het ongeschikt voor bewoning.\nIn de 10e eeuw werd het veengebied op grote schaal ontgonnen. Dit verkavelingspatroon is echter niet meer te zien in het landschap vanwege grootschalige overstromingen in de 14e eeuw. Hierna is de Zwijndrechtse Waard opnieuw bedijkt en ontgonnen. Het plangebied lag vanaf die tijd in \u2019De Volgerlanden\u2019, de \u2018slechte\u2019 gronden waar een overslagdek aanwezig was. Reeds op 16e-eeuwse kaarten is bebouwing langs de Veersedijk te zien, maar het is niet duidelijk of ook in het plangebied sprake was van bebouwing. Vanaf het begin van de 19e eeuw bestaat echter wel zekerheid over de aanwezigheid van bebouwing. In het plangebied kunnen mogelijk bewoningsresten voorkomen uit de periode vanaf de 14e eeuw. Deze worden vanaf het maaiveld verwacht, in een archeologische laag, een humeuze laag met aardewerk, dierlijk bot en bouwresten. Hieronder kunnen grondsporen zoals waterputten,afvalkuilen en greppels/sloten voorkomen. Naar verwachting zijn eventuele archeologische resten deels verstoord als gevolg van de aanleg van de latere bebouwing.\nTeneinde deze verwachting te toetsen en waar nodig aan te vullen is in het plangebied een verkennend booronderzoek uitgevoerd.\nTijdens dit onderzoek zijn de verwachte oeverafzettingen van de Merwede en/of Waal niet aangetroffen. De aangetroffen bodemopbouw bestaat uit veen, afgedekt door een pakket komafzettingen. Hierop is in \u00e9\u00e9n boring een laag overslagafzettingen aangetroffen. De natte omstandigheden zullen niet aantrekkelijk zijn geweest voor bewoning. Tijdens het booronderzoek zijn dan ook geen veraarde veenlagen of vegetatiehorizonten aangetroffen, die kunnen duiden op een bewoonbaar oppervlak. Bovendien is de bodem recentelijk omgewerkt tot 40 \u00e0 90 cm \u2013mv. Om deze redenen worden geen archeologische resten in het plangebied verwacht."
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:66832"
-    ],
-    "oai_set": [
-        "D30000:D37000",
-        "driver",
-        "easy-collection:4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Archaeology"
-        },
-        {
-            "name": "Booronderzoek verkennende fase"
-        }
-    ],
-    "title": [
-        "Onderdijk 126, Hendrik-Ido-Ambacht",
-        "Een Bureauonderzoek en Inventariserend Veldonderzoek in de vorm van een verkennend booronderzoek",
-        "Een Bureauonderzoek en Inventariserend Veldonderzoek in de vorm van een verkennend booronderzoek"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0b792e1e-b735-5e46-8a24-82e57c8bfdcf.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0b792e1e-b735-5e46-8a24-82e57c8bfdcf.json
deleted file mode 100644
index 074c2134..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0b792e1e-b735-5e46-8a24-82e57c8bfdcf.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "De Steekproef"
-    ],
-    "Contributor": [
-        "De Steekproef"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.17026/dans-xc2-ancx",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "14 p."
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:17373",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:17373"
-    ],
-    "PublicationTimestamp": "2009-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2009"
-    ],
-    "Publisher": [
-        "De Steekproef"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "SpatialCoverage": [
-        "\n            "
-    ],
-    "TemporalCoverage": [
-        "2009-11-05",
-        "2007-02",
-        "2009-11-05"
-    ],
-    "author": [
-        "Neef, W. De"
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:17373;2018-09-18T16:43:08Z;D30000:D37000;driver;easy-collection:4;10.17026/dans-xc2-ancx;Neef, W. De;Wapserveen: Van Helomaweg (Dr.);Een Inventariserend Archeologisch Veldonderzoek;De Steekproef;2009;Archaeology;inventariserend veldonderzoek;De Steekproef;2009-11-05;2007-02;2009-11-05;nl;Dataset;urn:nbn:nl:ui:13-c86-84o;easy-dataset:17373;twips.dans.knaw.nl--7260220477179627179-1257439192886;14 p.;info:eu-repo/semantics/openAccess;Aan de Van Helomaweg te Wapserveen (Drenthe) heeft op 13 februari 2007 een inventariserend archeologisch veldonderzoek plaatsgevonden. Aanleiding voor het onderzoek was de voorgenomen bouw van een agrarisch bedrijf op het perceel. Hierbij zal de bodem verstoord worden. Doel van het onderzoek was te bepalen of mogelijke archeologische waarden in het plangebied aanwezig zijn en in hoeverre deze door de voorgenomen bodemingrepen worden bedreigd. Om de bodemopbouw te bepalen en archeologische indicatoren op te sporen zijn 15 edelmanboringen geplaatst met een diameter van 10 cm tot een diepte van tenminste 30 cm in de onverstoorde C-horizont. In vier van de 15 boringen is een BC-horizont aangetroffen, waarvan drie onder een verstoorde laag. In twee boringen werd een laag veraard veen gevonden. In negen van de 15 boringen werd een Chorizont waargenomen onder een verstoorde laag. Het bodemprofiel is dermate verstoord dat archeologisch vervolgonderzoek niet noodzakelijk wordt geacht.;16E (kaartblad);Drenthe; Westerveld; Wapserveen; Van Helomaweg;52.82480617;6.19213197",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0b792e1e-b735-5e46-8a24-82e57c8bfdcf",
-    "notes": [
-        "Aan de Van Helomaweg te Wapserveen (Drenthe) heeft op 13 februari 2007 een inventariserend archeologisch veldonderzoek plaatsgevonden. Aanleiding voor het onderzoek was de voorgenomen bouw van een agrarisch bedrijf op het perceel. Hierbij zal de bodem verstoord worden. Doel van het onderzoek was te bepalen of mogelijke archeologische waarden in het plangebied aanwezig zijn en in hoeverre deze door de voorgenomen bodemingrepen worden bedreigd. Om de bodemopbouw te bepalen en archeologische indicatoren op te sporen zijn 15 edelmanboringen geplaatst met een diameter van 10 cm tot een diepte van tenminste 30 cm in de onverstoorde C-horizont. In vier van de 15 boringen is een BC-horizont aangetroffen, waarvan drie onder een verstoorde laag. In twee boringen werd een laag veraard veen gevonden. In negen van de 15 boringen werd een Chorizont waargenomen onder een verstoorde laag. Het bodemprofiel is dermate verstoord dat archeologisch vervolgonderzoek niet noodzakelijk wordt geacht."
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:17373"
-    ],
-    "oai_set": [
-        "D30000:D37000",
-        "driver",
-        "easy-collection:4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Archaeology"
-        },
-        {
-            "name": "inventariserend veldonderzoek"
-        }
-    ],
-    "title": [
-        "Wapserveen: Van Helomaweg (Dr.)",
-        "Een Inventariserend Archeologisch Veldonderzoek"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0bb51b70-ba9a-5d0e-8d52-12289166861e.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0bb51b70-ba9a-5d0e-8d52-12289166861e.json
deleted file mode 100644
index 2fa061cf..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0bb51b70-ba9a-5d0e-8d52-12289166861e.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "KSP Archeologie"
-    ],
-    "Contributor": [
-        "KSP Archeologie"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.17026/dans-z6b-vn8q",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "application/pdf"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:76821",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:76821"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "KSP Archeologie"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/restrictedAccess"
-    ],
-    "SpatialCoverage": [
-        "\n            "
-    ],
-    "TempCoverageBegin": 63647726399,
-    "TempCoverageEnd": 63649540799,
-    "TemporalCoverage": " period : ( 2017-12-01T11:59:59Z - 2017-12-22T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2017-12-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2017-12-22T11:59:59Z",
-    "author": [
-        "Koeman, S.M."
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:76821;2018-09-18T17:22:27Z;D30000:D37000;10.17026/dans-z6b-vn8q;Koeman, S.M.;KSP Archeologie;Bureauonderzoek en Inventariserend  Veldonderzoek, verkennende fase: Berg ong. te Budel. Gemeente Cranendonck;KSP Archeologie;2017;Archaeology;Bureau- en booronderzoek;KSP Archeologie;2017-12-01;2017-12-22;nl;Dataset;urn:nbn:nl:ui:13-w4-t0tm;easy-dataset:76821;application/pdf;info:eu-repo/semantics/restrictedAccess;KSP Archeologie heeft een archeologisch bureauonderzoek en inventariserend veldonderzoek, verkennende fase uitgevoerd voor de locatie aan de Berg (ong.) Budel (gemeente Cranendonck). Het onderzoek is uitgevoerd in het kader van de ruimtelijke onderbouwing voor de nieuwbouw van een woning.\n\nOp basis van de landschappelijke ligging ter plaatse van een relatief laag gedeelte binnen het dekzandgebied in de buurt van een moerasgebied is aan het plangebied een middelhoge verwachting toegekend voor vuursteenvindplaatsen uit het Laat-Paleolithicum tot en met het Neolithicum en een lage verwachting voor nederzettingsresten uit het Neolithicum tot en met de Volle Middeleeuwen (tot in de 13e eeuw).  \n\nUit de historische ontwikkeling is gebleken dat het plangebied op de westelijke rand van het buurtschap Berg heeft gelegen. Het westelijke deel was in het begin van de 19e eeuw onderdeel van de woeste gronden (Buulderbergsche Heide), het oostelijke deel was in bezit van een bewoner van Berg en ingericht als bouwland en dennenbos. Het buurtschap is mogelijk in de 13e eeuw ontstaan maar daar zijn tot op heden nog geen archeologische sporen van gevonden die dat kunnen bevestigen. Op basis van het historisch kaartmateriaal worden de meest kansrijke zones hiervoor ten (noord)oosten van het plangebied verwacht. Op basis hiervan wordt de hoge verwachting op de gemeentelijke beleidskaart voor het plangebied naar laag bijgesteld voor een vindplaats uit de Late Middeleeuwen en de Nieuwe tijd.\n\nVervolgens is deze verwachting getoetst door middel van een inventariserend veldonderzoek, verkennende fase. Uit het booronderzoek is gebleken dat in het plangebied geen restanten van de oorspronkelijke haarpodzolbodem aanwezig zijn. De aangetroffen bodemopbouw van AC-profielen in combinatie met het AHN-kaartbeeld geeft de indruk dan ca. 0,5 \u2013 1,0 m van de bodem is afgegraven.  Daarnaast is in naar schatting tweederde van het plangebied (oostelijke deel) de bovenste 10 tot 20 cm van de C-horizont verstoord door boomwortels/omgewerkt ten tijde van het gebruik als boomkwekerij.\n\nOp basis van deze bevindingen wordt de kans dat een vindplaats binnen het plangebied aanwezig is laag ingeschat. De voorgenomen graafwerkzaamheden vormen dan ook geen bedreiging voor het archeologische bodemarchief. Op basis van deze conclusie is geen vervolgonderzoek geadviseerd.;Berg;Gemeente Cranendonck;Noord-Brabant;51.2764835;5.54576418",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0bb51b70-ba9a-5d0e-8d52-12289166861e",
-    "notes": [
-        "KSP Archeologie heeft een archeologisch bureauonderzoek en inventariserend veldonderzoek, verkennende fase uitgevoerd voor de locatie aan de Berg (ong.) Budel (gemeente Cranendonck). Het onderzoek is uitgevoerd in het kader van de ruimtelijke onderbouwing voor de nieuwbouw van een woning.\n\nOp basis van de landschappelijke ligging ter plaatse van een relatief laag gedeelte binnen het dekzandgebied in de buurt van een moerasgebied is aan het plangebied een middelhoge verwachting toegekend voor vuursteenvindplaatsen uit het Laat-Paleolithicum tot en met het Neolithicum en een lage verwachting voor nederzettingsresten uit het Neolithicum tot en met de Volle Middeleeuwen (tot in de 13e eeuw).  \n\nUit de historische ontwikkeling is gebleken dat het plangebied op de westelijke rand van het buurtschap Berg heeft gelegen. Het westelijke deel was in het begin van de 19e eeuw onderdeel van de woeste gronden (Buulderbergsche Heide), het oostelijke deel was in bezit van een bewoner van Berg en ingericht als bouwland en dennenbos. Het buurtschap is mogelijk in de 13e eeuw ontstaan maar daar zijn tot op heden nog geen archeologische sporen van gevonden die dat kunnen bevestigen. Op basis van het historisch kaartmateriaal worden de meest kansrijke zones hiervoor ten (noord)oosten van het plangebied verwacht. Op basis hiervan wordt de hoge verwachting op de gemeentelijke beleidskaart voor het plangebied naar laag bijgesteld voor een vindplaats uit de Late Middeleeuwen en de Nieuwe tijd.\n\nVervolgens is deze verwachting getoetst door middel van een inventariserend veldonderzoek, verkennende fase. Uit het booronderzoek is gebleken dat in het plangebied geen restanten van de oorspronkelijke haarpodzolbodem aanwezig zijn. De aangetroffen bodemopbouw van AC-profielen in combinatie met het AHN-kaartbeeld geeft de indruk dan ca. 0,5 \u2013 1,0 m van de bodem is afgegraven.  Daarnaast is in naar schatting tweederde van het plangebied (oostelijke deel) de bovenste 10 tot 20 cm van de C-horizont verstoord door boomwortels/omgewerkt ten tijde van het gebruik als boomkwekerij.\n\nOp basis van deze bevindingen wordt de kans dat een vindplaats binnen het plangebied aanwezig is laag ingeschat. De voorgenomen graafwerkzaamheden vormen dan ook geen bedreiging voor het archeologische bodemarchief. Op basis van deze conclusie is geen vervolgonderzoek geadviseerd."
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:76821"
-    ],
-    "oai_set": [
-        "D30000:D37000"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Archaeology"
-        },
-        {
-            "name": "Bureau- en booronderzoek"
-        }
-    ],
-    "title": [
-        "Bureauonderzoek en Inventariserend  Veldonderzoek, verkennende fase: Berg ong. te Budel. Gemeente Cranendonck"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0d667705-210f-5428-9754-0186f01de346.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0d667705-210f-5428-9754-0186f01de346.json
deleted file mode 100644
index 93f0300c..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0d667705-210f-5428-9754-0186f01de346.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Voorst, J.F. van",
-        "Bureau Archeologie, gemeente Almere"
-    ],
-    "Contributor": [
-        "Voorst, J.F. van",
-        "Bureau Archeologie, gemeente Almere"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.17026/dans-22c-uwew",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "application/pdf"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:31693",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:31693"
-    ],
-    "PublicationTimestamp": "2010-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "Bureau Archeologie, gemeente Almere"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "SpatialCoverage": [
-        "\n            "
-    ],
-    "TemporalCoverage": [
-        "2010-09-08",
-        "2009-10-01",
-        "2010-09-08"
-    ],
-    "author": [
-        "Hogestijn, W.J.H."
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:31693;2018-09-18T16:50:08Z;D30000:D37000;driver;easy-collection:4;10.17026/dans-22c-uwew;Hogestijn, W.J.H.;ARCHEOLOGISCHE RAPPORTEN ALMERE 64;Basisrapportage Bureauonderzoek. Plangebied 3G/3H/3V Buitenhoutsedreef (Almere Buiten);Bureau Archeologie, gemeente Almere;2010;Archaeology;Nederzetting, onbepaald (NX);Neolithicum: 5300 - 2000 vC (NEO);Voorst, J.F. van;Bureau Archeologie, gemeente Almere;2010-09-08;2009-10-01;2010-09-08;nl;Dataset;urn:nbn:nl:ui:13-s41-gt9;easy-dataset:31693;twips.dans.knaw.nl--9077970224482643223-1283939769180;application/pdf;info:eu-repo/semantics/openAccess;In het plangebied 3G/3H/3V Buitenhoutsedreef (Almere Buiten) vindt onderzoek plaats naar de voorgenomen verbreding van de Buitenhoutsedreef. Tevens zal een kruispunt heringericht worden. De exacte lokatie van de verbreding is momenteel nog niet bekend. Er moet rekening gehouden worden met een verbreding met 7 meter (asfalt op puingranulaat). Het oppervlak van het plangebied is circa 1,25 ha. groot.\nHet doel van het bureauonderzoek is een gespecificeerd archeologisch verwachtingsmodel voor het plangebied op te stellen door bekende en te verwachten archeologische waarden en andere voor het onderzoek relevante gegevens te inventariseren. Aan de hand hiervan wordt bepaald of en wat voor soort archeologisch vervolgonderzoek noodzakelijk is.\nHiertoe is de Archeologische Beleidskaart Almere (ABA) d.d. 0890792009 (ook wel Selectiekaart) geraadpleegd. Uit de ABA blijkt dat direct grenzend aan het plangebied bekende archeologische waarden liggen (vindplaats 3V_1) en dat circa 95% van het te verbreden wegtrac\u00e9 binnen een Selectiegebied is gelegen.\nOp basis van het voorliggende bureauonderzoek kan worden gesteld dat in het hele plangebied prehistorische nederzettingsresten aanwezig kunnen zijn op plaatsen waar de top van het dekzand intact is. Gezien de hoogteligging van het dekzand van 7 tot 10 meter min NAP en de relatieve zeespiegelstijging zullen eventueel aanwezige archeologische resten ouder zijn dan circa 8.100 9 6.300 v.Chr. Dit betekent dat zij zullen dateren uit de Midden Steentijd (Mesolithicum / circa 8.800 \u2013 5.300 voor Chr.). Daarnaast kunnen in het plangebied in de jongere afzettingen, zoals detritus, Sloef/Almere en Zuiderzeeafzettingen scheepswrakken, scheepsonderdelen en scheepsladingen of delen hiervan verwacht worden. Ook kunnen archeologische waarden uit de laatste fase van de Oude9Steentijd, het Jong Paleolithicum (circa 18.00099.600 v.Chr.), worden verwacht. Dergelijke vindplaatsen zijn te verwachten in bodemlagen die verband houden met de B\u00f8lling en Aller\u00f8d interstadialen, zoals veen (sterk samengedrukt) en de \u2018Laag van Usselo\u2019. Ook in het Jong Dekzand 1 (Vroege Dryas stadiaal) en Jong Dekzand 2 (Late Dryas stadiaal) kunnen dergelijke vindplaatsen worden verwacht.;Almere;Almere Buiten;3G/3H/3V (gebiedscode);52.37770405;5.27621122",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0d667705-210f-5428-9754-0186f01de346",
-    "notes": [
-        "In het plangebied 3G/3H/3V Buitenhoutsedreef (Almere Buiten) vindt onderzoek plaats naar de voorgenomen verbreding van de Buitenhoutsedreef. Tevens zal een kruispunt heringericht worden. De exacte lokatie van de verbreding is momenteel nog niet bekend. Er moet rekening gehouden worden met een verbreding met 7 meter (asfalt op puingranulaat). Het oppervlak van het plangebied is circa 1,25 ha. groot.\nHet doel van het bureauonderzoek is een gespecificeerd archeologisch verwachtingsmodel voor het plangebied op te stellen door bekende en te verwachten archeologische waarden en andere voor het onderzoek relevante gegevens te inventariseren. Aan de hand hiervan wordt bepaald of en wat voor soort archeologisch vervolgonderzoek noodzakelijk is.\nHiertoe is de Archeologische Beleidskaart Almere (ABA) d.d. 0890792009 (ook wel Selectiekaart) geraadpleegd. Uit de ABA blijkt dat direct grenzend aan het plangebied bekende archeologische waarden liggen (vindplaats 3V_1) en dat circa 95% van het te verbreden wegtrac\u00e9 binnen een Selectiegebied is gelegen.\nOp basis van het voorliggende bureauonderzoek kan worden gesteld dat in het hele plangebied prehistorische nederzettingsresten aanwezig kunnen zijn op plaatsen waar de top van het dekzand intact is. Gezien de hoogteligging van het dekzand van 7 tot 10 meter min NAP en de relatieve zeespiegelstijging zullen eventueel aanwezige archeologische resten ouder zijn dan circa 8.100 9 6.300 v.Chr. Dit betekent dat zij zullen dateren uit de Midden Steentijd (Mesolithicum / circa 8.800 \u2013 5.300 voor Chr.). Daarnaast kunnen in het plangebied in de jongere afzettingen, zoals detritus, Sloef/Almere en Zuiderzeeafzettingen scheepswrakken, scheepsonderdelen en scheepsladingen of delen hiervan verwacht worden. Ook kunnen archeologische waarden uit de laatste fase van de Oude9Steentijd, het Jong Paleolithicum (circa 18.00099.600 v.Chr.), worden verwacht. Dergelijke vindplaatsen zijn te verwachten in bodemlagen die verband houden met de B\u00f8lling en Aller\u00f8d interstadialen, zoals veen (sterk samengedrukt) en de \u2018Laag van Usselo\u2019. Ook in het Jong Dekzand 1 (Vroege Dryas stadiaal) en Jong Dekzand 2 (Late Dryas stadiaal) kunnen dergelijke vindplaatsen worden verwacht."
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:31693"
-    ],
-    "oai_set": [
-        "D30000:D37000",
-        "driver",
-        "easy-collection:4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Archaeology"
-        },
-        {
-            "name": "Nederzetting"
-        },
-        {
-            "name": "onbepaald NX"
-        },
-        {
-            "name": "Neolithicum - vC NEO"
-        }
-    ],
-    "title": [
-        "ARCHEOLOGISCHE RAPPORTEN ALMERE 64",
-        "Basisrapportage Bureauonderzoek. Plangebied 3G/3H/3V Buitenhoutsedreef (Almere Buiten)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0d69050d-ddc7-50b9-af0f-587c94af16f5.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0d69050d-ddc7-50b9-af0f-587c94af16f5.json
deleted file mode 100644
index 8eff0d62..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0d69050d-ddc7-50b9-af0f-587c94af16f5.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Vivek Maru"
-    ],
-    "Contributor": [
-        "Vivek Maru"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.17632/tfnp39gk3z.1",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:102391",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:102391"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Data Archiving and Networked Services (DANS)"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/closedAccess",
-        "License: http://creativecommons.org/licenses/by/4.0"
-    ],
-    "TempCoverageBegin": 63663361199,
-    "TempCoverageEnd": 63663361199,
-    "TemporalCoverage": " period : ( 2018-05-31T11:59:59Z - 2018-05-31T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2018-05-31T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-05-31T11:59:59Z",
-    "author": [
-        "Maru, V"
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:102391;2018-09-18T17:44:57Z;E10000;Maru, V;via Mendeley Data;Solar Still data set-3500TDS;Data Archiving and Networked Services (DANS);2018;Interdisciplinary sciences;Vivek Maru;2018-05-31T12:18:12.894+02:00;2018-05-31T12:18:12.894+02:00;Dataset;10.17632/tfnp39gk3z.1;urn:nbn:nl:ui:13-pu-ko8u;easy-dataset:102391;info:eu-repo/semantics/closedAccess;License: http://creativecommons.org/licenses/by/4.0;1. Description of the data\t\n1.1 Type of study\n This is a part of Dissertation work of Master Student at School of Engineering, RK University, Rajkot India\n 1.2 Types of data\n This is an experimental data collected from a three-stepped solar still (0.6m \u00d7 0.6m) constructed by the student and experiment conducted at Bhavnagar (21.74\u00b0N,72.10\u00b0E) to yield 2.5 litres/day\n 1.3 Format and scale of the data\nThe file format is excel, the number of records is presented for the month of April 22 to May 10, 2018. CAD model was used to create the drawing for Solar Still. The experiment was conducted for the same TDS of water daily.  These are the initial indicative values. Formats and software enable sharing and long-term validity of data as a part of academic work.",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0d69050d-ddc7-50b9-af0f-587c94af16f5",
-    "notes": [
-        "1. Description of the data\t\n1.1 Type of study\n This is a part of Dissertation work of Master Student at School of Engineering, RK University, Rajkot India\n 1.2 Types of data\n This is an experimental data collected from a three-stepped solar still (0.6m \u00d7 0.6m) constructed by the student and experiment conducted at Bhavnagar (21.74\u00b0N,72.10\u00b0E) to yield 2.5 litres/day\n 1.3 Format and scale of the data\nThe file format is excel, the number of records is presented for the month of April 22 to May 10, 2018. CAD model was used to create the drawing for Solar Still. The experiment was conducted for the same TDS of water daily.  These are the initial indicative values. Formats and software enable sharing and long-term validity of data as a part of academic work."
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:102391"
-    ],
-    "oai_set": [
-        "E10000"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Interdisciplinary sciences"
-        }
-    ],
-    "title": [
-        "Solar Still data set-3500TDS"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0da94acf-4017-5b19-b329-4bcc0a5a7561.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0da94acf-4017-5b19-b329-4bcc0a5a7561.json
deleted file mode 100644
index 502f636e..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0da94acf-4017-5b19-b329-4bcc0a5a7561.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "Lohof, E. ",
-        "Veer, R.H. van 't",
-        "ADC ArcheoProjecten"
-    ],
-    "Contributor": [
-        "Lohof, E. ",
-        "Veer, R.H. van 't",
-        "ADC ArcheoProjecten"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.17026/dans-x3t-asd2",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "application/pdf"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:35475",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:35475"
-    ],
-    "PublicationTimestamp": "2010-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "ADC ArcheoProjecten"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "SpatialCoverage": [
-        "\n            ",
-        "\n            "
-    ],
-    "TemporalCoverage": [
-        "2010-05-28",
-        "2010-05-28",
-        "2010-10-05"
-    ],
-    "author": [
-        "Zee, R.M. van der ",
-        "ADC ArcheoProjecten"
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:35475;2018-09-18T16:53:08Z;D30000:D37000;easy-collection:4;10.17026/dans-x3t-asd2;ADC ArcheoProjecten;Zee, R.M. van der ;Bodegraven Nieuwerbrug aan den Rijn Endelkade 2 Booronderzoek;Endelkade 2 te Nieuwerbrug aan den Rijn (gemeente Bodegraven);Een Bureauonderzoek en Inventariserend Veldonderzoek in de vorm van een verkennend en karterend booronderzoek;ADC ArcheoProjecten;2010;Archaeology;Archeologisch: booronderzoek;Lohof, E. ;Veer, R.H. van 't;ADC ArcheoProjecten;2010-05-28;2010-05-28;2010-10-05;nl;Dataset;urn:nbn:nl:ui:13-bif-rko;easy-dataset:35475;twips.dans.knaw.nl--2636177154615364937-1275033621684;application/pdf;info:eu-repo/semantics/openAccess;In opdracht van Invepro B.V. te Lopik heeft ADC ArcheoProjecten een bureauonderzoek en een inventariserend veldonderzoek uitgevoerd voor het plangebied Endelkade 2 in Nieuwerbrug aan den Rijn (gemeente Bodegraven). In het plangebied zal de uitbreiding van een veestal gerealiseerd worden. Het onderzoek is uitgevoerd in het kader van een aanvraag van een bouwvergunning en was noodzakelijk om te bepalen of bij de voorgenomen activiteiten de kans bestaat dat archeologische resten in de ondergrond worden aangetast. \n\nHoewel deze tot op heden in het gebied niet zijn aangetoond, kunnen in de diepere ondergrond oeveren beddingafzettingen van de Blokland-Snelrewaard meandergordel aanwezig zijn. Op of in de top van deze afzettingen kunnen, gezien de ouderdom van de meandergordel, archeologische resten voorkomen uit het Laat Neolithicum. De resten zullen zich naar verwachting manifesteren als een archeologische laag, bestaande uit een vermenging van onder meer kleine fragmenten aardewerk, houtskool en bot met het oorspronkelijke substraat. De meeste typen archeologische resten (bot, houtskool, aardewerk, metaal) zullen door de natte en zuurstofloze condities goed zijn geconserveerd. Bovendien zullen eventuele resten door afdekking met veen en latere komafzettingen van de Oude Rijn niet door (sub)recente bodemingrepen zijn aangetast.\n\nVanwege de hoge grondwaterspiegel en de moeilijk bewerkbare gronden werden rivierkommen tot aan de grootschalige ontginningen in de Late Middeleeuwen niet uitgekozen voor bewoning en/of landbouw.\n\nDe kans op archeologische resten in het veen en de komklei wordt daarom gering geacht. Het komgebied van de Oude Rijn wordt evenwel doorsneden door crevasses. Op basis van het AHN kan ter plaatse een dergelijke geul verwacht worden. Hoewel tot op heden op de hieraan gerelateerde afzettingen nog geen archeologische resten zijn aangetroffen, moet hier toch rekening mee worden gehouden. Eventuele resten kunnen uit de Bronstijd, IJzertijd en Romeinse tijd dateren. Ook deze resten zullen zich naar verwachting manifesteren als een archeologische laag. Echter, vanwege de ondiepe ligging moet rekening worden gehouden met een verstoring door (sub)recente bodemingrepen.\n\nIn de Middeleeuwen werden de komgebieden op grote schaal ontgonnen. Het plangebied maakt geen deel uit van een ontginningsas en was op oude kaarten onbebouwd. De huidige boerderij is gebouwd in 1996 na een ruilverkaveling. Archeologische resten uit de Middeleeuwen en Nieuwe tijd worden daarom niet verwacht.\n\nTeneinde deze verwachting te toetsen werd in het plangebied een booronderzoek (specificatie VS03) uitgevoerd. Hierbij zijn in het plangebied geen aanwijzingen voor een verstoring van de natuurlijke bodem vastgesteld. Het booronderzoek wijst uit, dat de bodem bestaat uit komafzettingen en veen (respectievelijk Formatie van Echteld en Formatie van Nieuwkoop), afgedekt door een pakket crevasseafzettingen (Formatie van Echteld) van de Oude Rijn. Archeologische resten zijn niet waargenomen. Op basis van het bureauonderzoek werden afzettingen van de stroomgordel van Blokland-Snelrewaard verwacht. Deze zijn tijdens het booronderzoek niet aangetroffen.\n\nADC ArcheoProjecten adviseert om het terrein vrij te geven voor de voorgenomen ontwikkeling. Het is echter niet volledig uit te sluiten dat binnen het onderzochte gebied toch nog archeologische resten voorkomen. Het verdient daarom aanbeveling om de uitvoerder van het grondwerk te wijzen op de plicht archeologische vondsten te melden bij het bevoegde overheid, zoals aangegeven in artikel 53 van de Monumentenwet.;Zuid-Holland;Bodegraven;Nieuwerbrug aan den Rijn;Endelkade 2;31D;52.06765382;4.80406075;52.06765382;4.80406075",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0da94acf-4017-5b19-b329-4bcc0a5a7561",
-    "notes": [
-        "In opdracht van Invepro B.V. te Lopik heeft ADC ArcheoProjecten een bureauonderzoek en een inventariserend veldonderzoek uitgevoerd voor het plangebied Endelkade 2 in Nieuwerbrug aan den Rijn (gemeente Bodegraven). In het plangebied zal de uitbreiding van een veestal gerealiseerd worden. Het onderzoek is uitgevoerd in het kader van een aanvraag van een bouwvergunning en was noodzakelijk om te bepalen of bij de voorgenomen activiteiten de kans bestaat dat archeologische resten in de ondergrond worden aangetast. \n\nHoewel deze tot op heden in het gebied niet zijn aangetoond, kunnen in de diepere ondergrond oeveren beddingafzettingen van de Blokland-Snelrewaard meandergordel aanwezig zijn. Op of in de top van deze afzettingen kunnen, gezien de ouderdom van de meandergordel, archeologische resten voorkomen uit het Laat Neolithicum. De resten zullen zich naar verwachting manifesteren als een archeologische laag, bestaande uit een vermenging van onder meer kleine fragmenten aardewerk, houtskool en bot met het oorspronkelijke substraat. De meeste typen archeologische resten (bot, houtskool, aardewerk, metaal) zullen door de natte en zuurstofloze condities goed zijn geconserveerd. Bovendien zullen eventuele resten door afdekking met veen en latere komafzettingen van de Oude Rijn niet door (sub)recente bodemingrepen zijn aangetast.\n\nVanwege de hoge grondwaterspiegel en de moeilijk bewerkbare gronden werden rivierkommen tot aan de grootschalige ontginningen in de Late Middeleeuwen niet uitgekozen voor bewoning en/of landbouw.\n\nDe kans op archeologische resten in het veen en de komklei wordt daarom gering geacht. Het komgebied van de Oude Rijn wordt evenwel doorsneden door crevasses. Op basis van het AHN kan ter plaatse een dergelijke geul verwacht worden. Hoewel tot op heden op de hieraan gerelateerde afzettingen nog geen archeologische resten zijn aangetroffen, moet hier toch rekening mee worden gehouden. Eventuele resten kunnen uit de Bronstijd, IJzertijd en Romeinse tijd dateren. Ook deze resten zullen zich naar verwachting manifesteren als een archeologische laag. Echter, vanwege de ondiepe ligging moet rekening worden gehouden met een verstoring door (sub)recente bodemingrepen.\n\nIn de Middeleeuwen werden de komgebieden op grote schaal ontgonnen. Het plangebied maakt geen deel uit van een ontginningsas en was op oude kaarten onbebouwd. De huidige boerderij is gebouwd in 1996 na een ruilverkaveling. Archeologische resten uit de Middeleeuwen en Nieuwe tijd worden daarom niet verwacht.\n\nTeneinde deze verwachting te toetsen werd in het plangebied een booronderzoek (specificatie VS03) uitgevoerd. Hierbij zijn in het plangebied geen aanwijzingen voor een verstoring van de natuurlijke bodem vastgesteld. Het booronderzoek wijst uit, dat de bodem bestaat uit komafzettingen en veen (respectievelijk Formatie van Echteld en Formatie van Nieuwkoop), afgedekt door een pakket crevasseafzettingen (Formatie van Echteld) van de Oude Rijn. Archeologische resten zijn niet waargenomen. Op basis van het bureauonderzoek werden afzettingen van de stroomgordel van Blokland-Snelrewaard verwacht. Deze zijn tijdens het booronderzoek niet aangetroffen.\n\nADC ArcheoProjecten adviseert om het terrein vrij te geven voor de voorgenomen ontwikkeling. Het is echter niet volledig uit te sluiten dat binnen het onderzochte gebied toch nog archeologische resten voorkomen. Het verdient daarom aanbeveling om de uitvoerder van het grondwerk te wijzen op de plicht archeologische vondsten te melden bij het bevoegde overheid, zoals aangegeven in artikel 53 van de Monumentenwet."
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:35475"
-    ],
-    "oai_set": [
-        "D30000:D37000",
-        "easy-collection:4"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Archaeology"
-        },
-        {
-            "name": "Archeologisch booronderzoek"
-        }
-    ],
-    "title": [
-        "Bodegraven Nieuwerbrug aan den Rijn Endelkade 2 Booronderzoek",
-        "Endelkade 2 te Nieuwerbrug aan den Rijn (gemeente Bodegraven)",
-        "Een Bureauonderzoek en Inventariserend Veldonderzoek in de vorm van een verkennend en karterend booronderzoek"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/danseasy-oai_datacite/SET_1/json/0dcce5f1-eca6-538d-aabc-4e0b0cb77cbe.json b/oaitestdata/danseasy-oai_datacite/SET_1/json/0dcce5f1-eca6-538d-aabc-4e0b0cb77cbe.json
deleted file mode 100644
index af9c3598..00000000
--- a/oaitestdata/danseasy-oai_datacite/SET_1/json/0dcce5f1-eca6-538d-aabc-4e0b0cb77cbe.json
+++ /dev/null
@@ -1,107 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.17026/dans-zaj-v79s",
-    "DiscHierarchy": [
-        "1.5.9",
-        "Literary Studies",
-        "Poetry"
-    ],
-    "Discipline": "History;Humanities;Psychology;Geography",
-    "Format": [
-        "WAV",
-        "application/x-cmdi+xml"
-    ],
-    "Language": [
-        "Dutch"
-    ],
-    "MetaDataAccess": "https://easy.dans.knaw.nl/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:easy.dans.knaw.nl:easy-dataset:35855",
-    "MetadataAccess": [
-        "oai:easy.dans.knaw.nl:easy-dataset:35855"
-    ],
-    "PublicationTimestamp": "2010-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "Data Archiving and Networked Services (DANS)"
-    ],
-    "ResourceType": [
-        "Dataset", 
-        "Data Collection"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/restrictedAccess"
-    ],
-    "TemporalCoverage": [
-        "2010-04-07",
-        "2008-02-01",
-        "2010-04-06"
-    ],
-    "author": [
-        "Veteranen Instituut"
-    ],
-    "fulltext": "oai:easy.dans.knaw.nl:easy-dataset:35855;2018-09-18T16:53:27Z;D30000:D34000:D34300;D50000:D51000;D60000:D61000;D60000:D62000;D40000:D42000;easy-collection:1;10.17026/dans-zaj-v79s;Veteranen Instituut;Veteranen Instituut, IPNV, interview 374;Data Archiving and Networked Services (DANS);2010;Social sciences;Modern and contemporary\n                        history;Humanities;Political and administrative\n                        sciences;Psychology;Social geography;Sociology;Nederlands-Indi\u00eb;KNIL;Java 1945-1950;Oorlogsvrijwilligers;Koninklijke Marine;Soevereiniteitsoverdracht;Onafhankelijkheid Indonesi\u00eb;Inlichtingen;Militaire Inlichtingen Dienst;Officieren Koninklijke Landmacht;Koninklijke Landmacht ;Militaire opleiding in Engeland;NAVO;Carri\u00e8re bij defensie;Temporal coverage: 1945-1950;2010-04-07;2008-02-01;2010-04-06;nl;Dataset;urn:nbn:nl:ui:13-u0b-igf;easy-dataset:35855;twips.dans.knaw.nl-3693036603916007988-1270639755549;WAV;application/x-cmdi+xml;info:eu-repo/semantics/restrictedAccess;Deze oorlogsvrijwilliger ging in februari 1945 al naar Engeland voor zijn militaire opleiding. Na de Infanterie-opleiding werd hij geselecteerd bij de War Office Selection Board voor 164 OCTU in Wales. De opleiding van de expeditionele macht was eerst nog gericht op de strijd tegen Japan. Leiderschap maakte een belangrijk onderdeel uit van de officiersselectie en -opleiding. Met 4-9 RI ging hij naar Nederlands-Indi\u00eb in de zomer van 1947, waar hij langs de demarcatielijn op Java werd gelegerd. Hij was Inlichtingenofficier en werkte als zodanig nauw samen met het hoofdkwartier in Batavia en een KNIL-sergeant. Later maakte deze officier verder carri\u00e8re bij de Koninklijke Landmacht. Hij ging naar het Nato Defence College in Rome en had verschillende functies in Den Haag.;Java;Batavia;Solo;Semarang ;Djokja;Tangerang",
-    "group": "danseasy",
-    "groups": [
-        {
-            "name": "danseasy"
-        }
-    ],
-    "name": "0dcce5f1-eca6-538d-aabc-4e0b0cb77cbe",
-    "notes": [
-        "Deze oorlogsvrijwilliger ging in februari 1945 al naar Engeland voor zijn militaire opleiding. Na de Infanterie-opleiding werd hij geselecteerd bij de War Office Selection Board voor 164 OCTU in Wales. De opleiding van de expeditionele macht was eerst nog gericht op de strijd tegen Japan. Leiderschap maakte een belangrijk onderdeel uit van de officiersselectie en -opleiding. Met 4-9 RI ging hij naar Nederlands-Indi\u00eb in de zomer van 1947, waar hij langs de demarcatielijn op Java werd gelegerd. Hij was Inlichtingenofficier en werkte als zodanig nauw samen met het hoofdkwartier in Batavia en een KNIL-sergeant. Later maakte deze officier verder carri\u00e8re bij de Koninklijke Landmacht. Hij ging naar het Nato Defence College in Rome en had verschillende functies in Den Haag."
-    ],
-    "oai_identifier": [
-        "oai:easy.dans.knaw.nl:easy-dataset:35855"
-    ],
-    "oai_set": [
-        "D30000:D34000:D34300",
-        "D50000:D51000",
-        "D60000:D61000",
-        "D60000:D62000",
-        "D40000:D42000",
-        "easy-collection:1"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Social sciences"
-        },
-        {
-            "name": "Modern contemporary"
-        },
-        {
-            "name": "history"
-        },
-        {
-            "name": "Humanities"
-        },
-        {
-            "name": "Political administrative"
-        },
-        {
-            "name": "sciences"
-        },
-        {
-            "name": "Psychology"
-        },
-        {
-            "name": "Social geography"
-        },
-        {
-            "name": "Sociology"
-        },
-        {
-            "name": "Sociology"
-        },
-        {
-            "name": "KNIL"
-        },
-        {
-            "name": "Java -"
-        }
-    ],
-    "title": [
-        "Veteranen Instituut, IPNV, interview 374"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/deims-iso19139/full_1/json/0a0382ce-d888-542a-9e09-1b7c9ef0ea82.json b/oaitestdata/deims-iso19139/full_1/json/0a0382ce-d888-542a-9e09-1b7c9ef0ea82.json
deleted file mode 100644
index bce9f694..00000000
--- a/oaitestdata/deims-iso19139/full_1/json/0a0382ce-d888-542a-9e09-1b7c9ef0ea82.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "jose.antonio.fernandez.bouzas@xunta.es"
-    ],
-    "Contributor": "DEIMS-SDR | Site and Dataset registry deims.org",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Format": [
-        "Research site"
-    ],
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "https://deims.org/pycsw/catalogue/csw?verb=GetRecord&metadataPrefix=iso19139&identifier=0a0382ce-d888-542a-9e09-1b7c9ef0ea82",
-    "Publisher": [
-        "LTER Europe"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "SpatialCoverage": "(42N-43N,9 W-9 W)",
-    "author": [
-        "Jose Antonio Fernandez Bouzas"
-    ],
-    "fulltext": "4240428e-0c36-47b7-bf49-666b99a4a183;English;utf8;dataset;Research site;Jose Antonio Fernandez Bouzas;LTER Europe;jose.antonio.fernandez.bouzas@xunta.es;Jose Antonio Fernandez Bouzas;LTER Europe;jose.antonio.fernandez.bouzas@xunta.es;2018-09-24;http://www.opengis.net/def/crs/EPSG/0/4326;Illas Atlanticas / Pontevedra (ES-SNE);https://deims.org/site/4240428e-0c36-47b7-bf49-666b99a4a183;The Atlantic Islands of Galicia were declared a national park in 2002 in order to protect one of the best examples of Atlantic Ocean-associated ecosystems.Although on land there are highly valuable and exceptional ecosystems relating to cliffs, dunes and scrub, it is the marine setting that hosts the greatest Situated off the R\u00edas Baixas (Lower Estuaries), the archipelagos CIES, ONS, SALVORA AND CORTEGADA, create a natural barrier to the ocean, thereby accentuating the r\u00edas\u2019 estuary influence. The terrain features dune systems, cliffs with gorse and heather scrub, while the marine environment hosts a rocky seabed with large communities of brown algae (Sacorhiza polyschides and Laminaria spp), which are home to a great variety of living things. The marine currents deposit sand in the most sheltered parts, and together with the important M\u00e4erl beds consisting of the remains of calcareous algae, create a shifting substrate to which living things must adapt. Besides being the only national park in the autonomous region, the Atlantic Islands of Galicia National Park has earned other forms of recognition. The C\u00edes Islands were declared a natural park in 1980. The other protection categories are as follows: \u2013 Special Protection Area for Birds (SPA). Directive 79/409/CEE of the Council of 2 April 1979 relating to the conservation of wild birds. C\u00edes Islands (1988) Ons Islands (2001) \u2013 Site of Community Importance (SCI). Council Directive 92/43/EEC of 21 May 1992 on the conservation of natural habitats and of wild fauna and flora. C\u00edes Islands (2004) Ons Island (within the Ons-O Grove Complex) (2004) S\u00e1lvora Island (within the Corrubedo Wetland Complex) (2004) \u2013 Special Protection Areas for Natural Values (Decree 72/2004 of 2 April). C\u00edes Islands Ons Island (within the Ons-O Grove Complex) S\u00e1lvora Island (within the Corrubedo Wetland Complex);The original metadata record was created using DEIMS-SDR, the Dynamic Ecological Information Management System - Site and dataset registry;Jose Antonio Fernandez Bouzas;LTER Europe;jose.antonio.fernandez.bouzas@xunta.es;Jose Antonio Fernandez Bouzas;LTER Europe;jose.antonio.fernandez.bouzas@xunta.es;site;emf2iso_pointer_record;atmospheric parameter;atmospheric pressure;precipitation intensity;water parameter;water level;continuousDataCollection;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;2008-06-01;English;environment;-9.07;-8.75;42.14;42.63;2002-01-01;https://deims.org/4240428e-0c36-47b7-bf49-666b99a4a183;http://www.iatlanticas.es/;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='4240428e-0c36-47b7-bf49-666b99a4a183'&outputFormat=SHAPE-ZIP;WFS GetFeature request for downloading the data set in SHP format;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='4240428e-0c36-47b7-bf49-666b99a4a183'&outputFormat=application%2Fgml%2Bxml%3B+version%3D3.2;WFS GetFeature request for downloading the data set in GML 3.2 format;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='4240428e-0c36-47b7-bf49-666b99a4a183'&outputFormat=application%2Fjson;WFS GetFeature request for downloading the data set in GeoJSON format;https://data.lter-europe.net/pycsw?service=CSW&version=3.0.0&request=GetRecordById&ElementSetName=full&outputSchema=http://www.isotc211.org/2005/gmd&outputFormat=application/json&id=cfed0679-0894-41df-86ca-82e2847d6ef3;HTTP;Catalogue Service for the Web (CSW);https://deims.org/node/227;Spain (LTER-Spain);COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;publication;This data set is conformant with the INSPIRE Implementing Rules for the interoperability of spatial data sets and services;false;Dataset has been created by data transformation from the original record collected by the site managers using DEIMS site metadata editing form.",
-    "group": "deims",
-    "groups": [
-        {
-            "name": "deims"
-        }
-    ],
-    "name": "0a0382ce-d888-542a-9e09-1b7c9ef0ea82",
-    "notes": [
-        "The Atlantic Islands of Galicia were declared a national park in 2002 in order to protect one of the best examples of Atlantic Ocean-associated ecosystems.Although on land there are highly valuable and exceptional ecosystems relating to cliffs, dunes and scrub, it is the marine setting that hosts the greatest Situated off the R\u00edas Baixas (Lower Estuaries), the archipelagos CIES, ONS, SALVORA AND CORTEGADA, create a natural barrier to the ocean, thereby accentuating the r\u00edas\u2019 estuary influence. The terrain features dune systems, cliffs with gorse and heather scrub, while the marine environment hosts a rocky seabed with large communities of brown algae (Sacorhiza polyschides and Laminaria spp), which are home to a great variety of living things. The marine currents deposit sand in the most sheltered parts, and together with the important M\u00e4erl beds consisting of the remains of calcareous algae, create a shifting substrate to which living things must adapt. Besides being the only national park in the autonomous region, the Atlantic Islands of Galicia National Park has earned other forms of recognition. The C\u00edes Islands were declared a natural park in 1980. The other protection categories are as follows: \u2013 Special Protection Area for Birds (SPA). Directive 79/409/CEE of the Council of 2 April 1979 relating to the conservation of wild birds. C\u00edes Islands (1988) Ons Islands (2001) \u2013 Site of Community Importance (SCI). Council Directive 92/43/EEC of 21 May 1992 on the conservation of natural habitats and of wild fauna and flora. C\u00edes Islands (2004) Ons Island (within the Ons-O Grove Complex) (2004) S\u00e1lvora Island (within the Corrubedo Wetland Complex) (2004) \u2013 Special Protection Areas for Natural Values (Decree 72/2004 of 2 April). C\u00edes Islands Ons Island (within the Ons-O Grove Complex) S\u00e1lvora Island (within the Corrubedo Wetland Complex)"
-    ],
-    "oai_identifier": [
-        "0a0382ce-d888-542a-9e09-1b7c9ef0ea82"
-    ],
-    "oai_set": "full",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-9.07,42.14],[-9.07,42.63],[-8.75,42.63],[-8.75,42.14],[-9.07,42.14]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "site"
-        },
-        {
-            "name": "emfiso_pointer_record"
-        },
-        {
-            "name": "atmospheric parameter"
-        },
-        {
-            "name": "atmospheric pressure"
-        },
-        {
-            "name": "precipitation intensity"
-        },
-        {
-            "name": "water parameter"
-        },
-        {
-            "name": "water level"
-        },
-        {
-            "name": "Environmental monitoring facilities"
-        }
-    ],
-    "title": [
-        "Illas Atlanticas / Pontevedra (ES-SNE)"
-    ],
-    "url": "https://deims.org/node/227"
-}
\ No newline at end of file
diff --git a/oaitestdata/deims-iso19139/full_1/json/0a052e5a-bf67-577e-af26-c806289d3f11.json b/oaitestdata/deims-iso19139/full_1/json/0a052e5a-bf67-577e-af26-c806289d3f11.json
deleted file mode 100644
index 749967ae..00000000
--- a/oaitestdata/deims-iso19139/full_1/json/0a052e5a-bf67-577e-af26-c806289d3f11.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "frido.reinstorf@hs-magdeburg.de"
-    ],
-    "Contributor": "DEIMS-SDR | Site and Dataset registry deims.org",
-    "DOI": "http://dx.doi.org/10.23728/b2share.5776373ffab843218ac096303fef080b",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "https://deims.org/pycsw/catalogue/csw?verb=GetRecord&metadataPrefix=iso19139&identifier=0a052e5a-bf67-577e-af26-c806289d3f11",
-    "PID": "http://hdl.handle.net/11304/ae923aeb-b017-485d-8c66-66220a330be1",
-    "PublicationTimestamp": "2018-09-24T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "The data provider must be offered co-authorship for publications using this dataset at least within the metadata description",
-        "Formal acknowledgement of the dataset providers"
-    ],
-    "SpatialCoverage": "(52N-52N,11E-11E)",
-    "author": [
-        "Frido Reinstorf"
-    ],
-    "fulltext": "c73acf5e-c603-48d6-ba10-f4b396dbc3bc;English;utf8;dataset;Frido Reinstorf;Magdeburg-Stendal University of Applied Sciences;Breitscheidstra\u00dfe 2;Magdeburg;39114;DE;frido.reinstorf@hs-magdeburg.de;pointOfContact;2018-09-24;ISO19115;2003/Cor.1:2006;EPSG:4326;http://www.opengis.net/def/crs/EPSG/0/4326;http://www.opengis.net/def/crs/EPSG/0/4258;Meteorological data Siptenfelde, TERENO Harz / Central German Lowlands (1996-2005)19);2018-09-24;publication;urn:ltereurope:inspire::11839:26909;TERENO - Siptenfelde - Germany;Magdeburg-Stendal University of Applied Sciences;documentDigital;Air temperature (daily mean, min, max), precipitation (cumulative per day);completed;Frido Reinstorf;Magdeburg-Stendal University of Applied Sciences;Breitscheidstra\u00dfe 2;Magdeburg;39114;DE;frido.reinstorf@hs-magdeburg.de;pointOfContact;continual;Representative area of sampling: single point Sampling frequency - sampling time span: minutes Sampling frequency - minimum sampling unit: minutes;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;2008-06-01;publication;air temperature;precipitation;eLTER VA;LTER Controlled Vocabulary;The data provider must be offered co-authorship for publications using this dataset at least within the metadata description;Formal acknowledgement of the dataset providers;The principal: Administration has granted the access and use permission: Free access and use;The principal: Research has granted the access and use permission: Free for access;The principal: Public has granted the access and use permission: Free for access;eng;environment;extended weather station close to Siptenfelde at the Schaefertal;11.049887090921;11.049425750971;51.654490845951;51.654657250475;394.00;394;urn:ogc:def:crs:EPSG;MSL height;Not specific to any location or epoch.;Hydrography.;Representative area of sampling: single point;ground condition;1996-04-16;2005-12-31;http://doi.org/10.23728/b2share.5776373ffab843218ac096303fef080b;WWW:LINK-1.0-http--link;DOI;http://hdl.handle.net/11304/ae923aeb-b017-485d-8c66-66220a330be1;WWW:LINK-1.0-http--link;B2Share Landing Page;dataset;Conformity_001;INSPIRE;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;publication;See the referenced specification;Method description: Air temperature at 200 cm, precipitation 100 cm above ground. Method URL: . Instrumentation:;Metadata Access Constraints: none Metadata Use Constraints: none;annually",
-    "group": "deims",
-    "groups": [
-        {
-            "name": "deims"
-        }
-    ],
-    "name": "0a052e5a-bf67-577e-af26-c806289d3f11",
-    "notes": [
-        "Air temperature (daily mean, min, max), precipitation (cumulative per day)"
-    ],
-    "oai_identifier": [
-        "0a052e5a-bf67-577e-af26-c806289d3f11"
-    ],
-    "oai_set": "full",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[11.049887090921,51.654490845951],[11.049887090921,51.654657250475],[11.049425750971,51.654657250475],[11.049425750971,51.654490845951],[11.049887090921,51.654490845951]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "air temperature"
-        },
-        {
-            "name": "precipitation"
-        },
-        {
-            "name": "eLTER VA"
-        }
-    ],
-    "title": [
-        "Meteorological data Siptenfelde, TERENO Harz / Central German Lowlands (1996-2005)19)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/deims-iso19139/full_1/json/0a05ffad-6881-51c5-8c9f-f53b260abf26.json b/oaitestdata/deims-iso19139/full_1/json/0a05ffad-6881-51c5-8c9f-f53b260abf26.json
deleted file mode 100644
index 85bd19e3..00000000
--- a/oaitestdata/deims-iso19139/full_1/json/0a05ffad-6881-51c5-8c9f-f53b260abf26.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "isabella.bertani@nemo.unipr.it"
-    ],
-    "Contributor": "DEIMS-SDR | Site and Dataset registry deims.org",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "https://deims.org/pycsw/catalogue/csw?verb=GetRecord&metadataPrefix=iso19139&identifier=0a05ffad-6881-51c5-8c9f-f53b260abf26",
-    "PublicationTimestamp": "2018-09-24T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "LTER Europe"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Co-authorship on publications resulting from use of the dataset"
-    ],
-    "SpatialCoverage": "(44N-44N,10E-10E)",
-    "author": [
-        "Isabella Bertani"
-    ],
-    "fulltext": "6d7efd44-81cb-11e2-b534-005056ab003f;English;utf8;dataset;Isabella Bertani;LTER Europe;isabella.bertani@nemo.unipr.it;pointOfContact;2018-09-24;ISO19115;2003/Cor.1:2006;EPSG:4326;http://www.opengis.net/def/crs/EPSG/0/4326;http://www.opengis.net/def/crs/EPSG/0/4258;IT_SI001230_Lake Scuro_SRP_20130228;2018-09-24;publication;urn:ltereurope:inspire::9101:10278;Lago Scuro Parmense - Italy;Giampaolo Rossetti;LTER Europe;Viale G.P. Usberti 11A;Parma;PR;43100;IT;giampaolo.rossetti@unipr.it;pointOfContact;documentDigital;Dataset provides soluble reactive phosphorus (SRP) concentrations measured in Lake Scuro Parmense in 2012. Water samples were collected by means of a Ruttner bottle at different depths over the whole water column at the point of maximum depth of the lake. Samples were analysed spectrophotometrically according to Valderrama (1981).;completed;Giampaolo Rossetti;LTER Europe;Viale G.P. Usberti 11A;Parma;PR;43100;IT;giampaolo.rossetti@unipr.it;pointOfContact;Isabella Bertani;LTER Europe;isabella.bertani@nemo.unipr.it;pointOfContact;continual;Sampling frequency - sampling time span: monthly Sampling frequency - minimum sampling unit: bi-weekly;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;2008-06-01;publication;soluble reactive phosphorus;Permanent oligotrophic lakes, ponds and pools;LTER Controlled Vocabulary;Co-authorship on publications resulting from use of the dataset;The principal: Research has granted the access and use permission: Free for access and use upon request;The principal: Public has granted the access and use permission: Other restrictions according to rules defined in intellectual rights;The principal: has granted the access and use permission: Research;eng;environment;10.047000000000;10.044590000000;44.381290000000;44.382520000000;1527.00;1527;urn:ogc:def:crs:EPSG;MSL height;Not specific to any location or epoch.;Hydrography.;ground condition;1986-05-21;2009-10-20;http://www.dsa.unipr.it/rossetti/metadata.htm;WWW:LINK-1.0-http--link;Northern Apennine Lakes DatasetLake Scuro Reactive phosphorus;http://www.dsa.unipr.it/rossetti/metadata.htm;WWW:LINK-1.0-http--link;Northern Apennine Lakes DatasetLake Scuro Reactive phosphorus;http://sk.ise.cnr.it/observations/sos/kvp?service=SOS&version=2.0.0&request=GetObservation&offering=offering:http://sp7.irea.cnr.it/sensors/sk.ise.cnr.it/procedure/noManufacturerDeclared/noModelDeclared/noSerialNumberDeclared/20150209122000001/observations&observedProperty=http://vocab.nerc.ac.uk/collection/P02/current/TPHS/&procedure=http://sp7.irea.cnr.it/sensors/sk.ise.cnr.it/procedure/noManufacturerDeclared/noModelDeclared/noSerialNumberDeclared/20150209122000001&featureOfInterest=http://sp7.irea.cnr.it/sensors/sk.ise.cnr.it/foi/SSF/SP/EPSG:4326/44.381805559999997/10.045638889999999&MergeObservationsIntoDataArray=true;WWW:DOWNLOAD-1.0-http--download;Northern Apennine Lakes DatasetLake Scuro Reactive phosphorus;http://sk.ise.cnr.it/observations/sos/kvp?service=SOS&version=2.0.0&request=GetObservation&offering=offering:http://sp7.irea.cnr.it/sensors/sk.ise.cnr.it/procedure/noManufacturerDeclared/noModelDeclared/noSerialNumberDeclared/20150209122000001/observations&observedProperty=http://vocab.nerc.ac.uk/collection/P02/current/TPHS/&procedure=http://sp7.irea.cnr.it/sensors/sk.ise.cnr.it/procedure/noManufacturerDeclared/noModelDeclared/noSerialNumberDeclared/20150209122000001&featureOfInterest=http://sp7.irea.cnr.it/sensors/sk.ise.cnr.it/foi/SSF/SP/EPSG:4326/44.381805559999997/10.045638889999999&MergeObservationsIntoDataArray=true;WWW:DOWNLOAD-1.0-http--download;Northern Apennine Lakes DatasetLake Scuro Reactive phosphorus;dataset;Conformity_001;INSPIRE;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;publication;See the referenced specification;Method description: Valderrama J.C., 1981. The simultaneous analysis of total nitrogen and total phosphorus in natural waters. Mar. Chem. 10: 109-122.. Method URL: . Instrumentation: Ruttner bottle;Metadata Access Constraints: none Metadata Use Constraints: none;annually",
-    "group": "deims",
-    "groups": [
-        {
-            "name": "deims"
-        }
-    ],
-    "name": "0a05ffad-6881-51c5-8c9f-f53b260abf26",
-    "notes": [
-        "Dataset provides soluble reactive phosphorus (SRP) concentrations measured in Lake Scuro Parmense in 2012. Water samples were collected by means of a Ruttner bottle at different depths over the whole water column at the point of maximum depth of the lake. Samples were analysed spectrophotometrically according to Valderrama (1981)."
-    ],
-    "oai_identifier": [
-        "0a05ffad-6881-51c5-8c9f-f53b260abf26"
-    ],
-    "oai_set": "full",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[10.047000000000,44.381290000000],[10.047000000000,44.382520000000],[10.044590000000,44.382520000000],[10.044590000000,44.381290000000],[10.047000000000,44.381290000000]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "soluble reactive phosphorus"
-        },
-        {
-            "name": "Permanent oligotrophic lakes"
-        },
-        {
-            "name": "ponds pools"
-        }
-    ],
-    "title": [
-        "IT_SI001230_Lake Scuro_SRP_20130228"
-    ],
-    "url": "http://sk.ise.cnr.it/observations/sos/kvp?service=SOS&version=2.0.0&request=GetObservation&offering=offering:http://sp7.irea.cnr.it/sensors/sk.ise.cnr.it/procedure/noManufacturerDeclared/noModelDeclared/noSerialNumberDeclared/20150209122000001/observations&observedProperty=http://vocab.nerc.ac.uk/collection/P02/current/TPHS/&procedure=http://sp7.irea.cnr.it/sensors/sk.ise.cnr.it/procedure/noManufacturerDeclared/noModelDeclared/noSerialNumberDeclared/20150209122000001&featureOfInterest=http://sp7.irea.cnr.it/sensors/sk.ise.cnr.it/foi/SSF/SP/EPSG:4326/44.381805559999997/10.045638889999999&MergeObservationsIntoDataArray=true"
-}
\ No newline at end of file
diff --git a/oaitestdata/deims-iso19139/full_1/json/0a17096e-6912-5709-99f6-ef6a163c2e97.json b/oaitestdata/deims-iso19139/full_1/json/0a17096e-6912-5709-99f6-ef6a163c2e97.json
deleted file mode 100644
index 81147eed..00000000
--- a/oaitestdata/deims-iso19139/full_1/json/0a17096e-6912-5709-99f6-ef6a163c2e97.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "stefano.minerbi@provinz.bz.it"
-    ],
-    "Contributor": "DEIMS-SDR | Site and Dataset registry deims.org",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Format": [
-        "Research site"
-    ],
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "https://deims.org/pycsw/catalogue/csw?verb=GetRecord&metadataPrefix=iso19139&identifier=0a17096e-6912-5709-99f6-ef6a163c2e97",
-    "Publisher": [
-        "Forest Departement of South Tyrol"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "SpatialCoverage": "(47N,11E)",
-    "author": [
-        "Stefano Minerbi"
-    ],
-    "fulltext": "5d32cbf8-ab7c-4acb-b29f-600fec830a1d;English;utf8;dataset;Research site;Stefano Minerbi;Forest Departement of South Tyrol;stefano.minerbi@provinz.bz.it;Brennerstra\u00dfe 6 Bozen BZ 39100 IT;Stefano Minerbi;Forest Departement of South Tyrol;stefano.minerbi@provinz.bz.it;Brennerstra\u00dfe 6 Bozen BZ 39100 IT;2018-09-24;http://www.opengis.net/def/crs/EPSG/0/4326;Renon BOL1;https://deims.org/site/5d32cbf8-ab7c-4acb-b29f-600fec830a1d;Picea abies dominated forest, since 1995 included in the ICP Forest European network and in ICP IM network code 01. This site is located in the Central Alps and it's grouped with LOM1;TRE1;FRI2 and Valbona in a cluster of sites called Forest of the Alps. The Renon-Selva Verde site is located in the municipality of Renon, at a distance of 12.2 km North-Northeast from the town of Bolzano. Eddy covariance measurements started in the year 1997. The site is placed on a porphyric plateau; the soil is classified as Haplic Podsol following F.A.O. The site vegetation, a subalpine coniferous forest, is of natural origin and is used for wood production. As a result of the traditional harvesting method, which consists of irregular cuttings of 50-80 cubic meters, overall the forest is unevenly aged, but with homogenous groups. The largest group present in the area is growing approximately since the year 1820, after Napoleon wars. The main forest species is spruce (Picea abies (L.) Karst., 85% in number) followed by cembran pine (Pinus cembra L., 12%) and larch (Larix decidua Mill., 3%). In the clearings, covering approximately 15% of the area, the dominant grass species is Deschampsia flexuosa (L.) Trin. The canopy is irregular, with maximal height of 29 m. The mean leaf area index (LAI), measured by hemispherical photographs, is 5.1 m2 m-2. The climate is strongly influenced by elevation, with cool summer and moderately cold winter. Annual average temperature 4,6\u00b0C, average annual precipitation ammount 903 mm. An increase of the annual average temperature by 0,8\u00b0C were observed during the period 1990-2014.;The original metadata record was created using DEIMS-SDR, the Dynamic Ecological Information Management System - Site and dataset registry;Stefano Minerbi;Forest Departement of South Tyrol;stefano.minerbi@provinz.bz.it;Brennerstra\u00dfe 6 Bozen BZ 39100 IT;Stefano Minerbi;Forest Departement of South Tyrol;stefano.minerbi@provinz.bz.it;Brennerstra\u00dfe 6 Bozen BZ 39100 IT;site;emf2iso_pointer_record;atmospheric parameter;biological parameter;ecosystem parameter;soil parameter;Terrestrial;continuousDataCollection;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;2008-06-01;English;environment;11.433600000000;11.433600000000;46.586800000000;46.586800000000;1992-01-01;https://deims.org/5d32cbf8-ab7c-4acb-b29f-600fec830a1d;http://www.provinz.bz.it/forst;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='5d32cbf8-ab7c-4acb-b29f-600fec830a1d'&outputFormat=SHAPE-ZIP;WFS GetFeature request for downloading the data set in SHP format;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='5d32cbf8-ab7c-4acb-b29f-600fec830a1d'&outputFormat=application%2Fgml%2Bxml%3B+version%3D3.2;WFS GetFeature request for downloading the data set in GML 3.2 format;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='5d32cbf8-ab7c-4acb-b29f-600fec830a1d'&outputFormat=application%2Fjson;WFS GetFeature request for downloading the data set in GeoJSON format;https://data.lter-europe.net/pycsw?service=CSW&version=3.0.0&request=GetRecordById&ElementSetName=full&outputSchema=http://www.isotc211.org/2005/gmd&outputFormat=application/json&id=c6db8113-9f21-4975-9d5c-c627540812b2;HTTP;Catalogue Service for the Web (CSW);Biodiversity_Lepidoptera;https://data.lter-europe.net/pycsw?service=CSW&version=3.0.0&request=GetRecordById&ElementSetName=full&outputSchema=http://www.isotc211.org/2005/gmd&outputFormat=application/json&id=6499a7cc-df94-45ac-92ed-62f43360411d;HTTP;Catalogue Service for the Web (CSW);Deposition of N-NH4 and N-NO3 Renon Bol1 1985-207;https://data.lter-europe.net/pycsw?service=CSW&version=3.0.0&request=GetRecordById&ElementSetName=full&outputSchema=http://www.isotc211.org/2005/gmd&outputFormat=application/json&id=7e56ebf6-14cd-4991-9bbd-10ccda7da90a;HTTP;Catalogue Service for the Web (CSW);Meteorology;https://deims.org/node/226;Italy (LTER-ITalia);COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;publication;This data set is conformant with the INSPIRE Implementing Rules for the interoperability of spatial data sets and services;false;Dataset has been created by data transformation from the original record collected by the site managers using DEIMS site metadata editing form.",
-    "group": "deims",
-    "groups": [
-        {
-            "name": "deims"
-        }
-    ],
-    "name": "0a17096e-6912-5709-99f6-ef6a163c2e97",
-    "notes": [
-        "Picea abies dominated forest, since 1995 included in the ICP Forest European network and in ICP IM network code 01. This site is located in the Central Alps and it's grouped with LOM1;TRE1;FRI2 and Valbona in a cluster of sites called Forest of the Alps. The Renon-Selva Verde site is located in the municipality of Renon, at a distance of 12.2 km North-Northeast from the town of Bolzano. Eddy covariance measurements started in the year 1997. The site is placed on a porphyric plateau; the soil is classified as Haplic Podsol following F.A.O. The site vegetation, a subalpine coniferous forest, is of natural origin and is used for wood production. As a result of the traditional harvesting method, which consists of irregular cuttings of 50-80 cubic meters, overall the forest is unevenly aged, but with homogenous groups. The largest group present in the area is growing approximately since the year 1820, after Napoleon wars. The main forest species is spruce (Picea abies (L.) Karst., 85% in number) followed by cembran pine (Pinus cembra L., 12%) and larch (Larix decidua Mill., 3%). In the clearings, covering approximately 15% of the area, the dominant grass species is Deschampsia flexuosa (L.) Trin. The canopy is irregular, with maximal height of 29 m. The mean leaf area index (LAI), measured by hemispherical photographs, is 5.1 m2 m-2. The climate is strongly influenced by elevation, with cool summer and moderately cold winter. Annual average temperature 4,6\u00b0C, average annual precipitation ammount 903 mm. An increase of the annual average temperature by 0,8\u00b0C were observed during the period 1990-2014."
-    ],
-    "oai_identifier": [
-        "0a17096e-6912-5709-99f6-ef6a163c2e97"
-    ],
-    "oai_set": "full",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[11.433600000000,46.586800000000],[11.433600000000,46.586800000000],[11.433600000000,46.586800000000],[11.433600000000,46.586800000000],[11.433600000000,46.586800000000]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "site"
-        },
-        {
-            "name": "emfiso_pointer_record"
-        },
-        {
-            "name": "atmospheric parameter"
-        },
-        {
-            "name": "biological parameter"
-        },
-        {
-            "name": "ecosystem parameter"
-        },
-        {
-            "name": "soil parameter"
-        },
-        {
-            "name": "Terrestrial"
-        },
-        {
-            "name": "Environmental monitoring facilities"
-        }
-    ],
-    "title": [
-        "Renon BOL1"
-    ],
-    "url": "https://deims.org/node/226"
-}
\ No newline at end of file
diff --git a/oaitestdata/deims-iso19139/full_1/json/0a2a9d66-f441-5496-b304-d5a22b7c49ea.json b/oaitestdata/deims-iso19139/full_1/json/0a2a9d66-f441-5496-b304-d5a22b7c49ea.json
deleted file mode 100644
index c9ba6ce3..00000000
--- a/oaitestdata/deims-iso19139/full_1/json/0a2a9d66-f441-5496-b304-d5a22b7c49ea.json
+++ /dev/null
@@ -1,93 +0,0 @@
-{
-    "Contact": [
-        "alex.turner@cyfoethnaturiolcymru.gov.uk",
-        "arjs@ceh.ac.uk"
-    ],
-    "Contributor": "DEIMS-SDR | Site and Dataset registry deims.org",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Format": [
-        "Research site"
-    ],
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "https://deims.org/pycsw/catalogue/csw?verb=GetRecord&metadataPrefix=iso19139&identifier=0a2a9d66-f441-5496-b304-d5a22b7c49ea",
-    "Publisher": [
-        "Centre for Ecology & Hydrology",
-        "LTER Europe",
-        "Natural Resources Wales"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "SpatialCoverage": "(53N-53N,4 W-4 W)",
-    "author": [
-        "Andrew Sier",
-        "Alex Turner"
-    ],
-    "fulltext": "8b5da977-eed8-459f-b663-f3835aa0b356;English;utf8;dataset;Research site;Alex Turner;LTER Europe;alex.turner@cyfoethnaturiolcymru.gov.uk;Natural Resources Wales;Alex Turner;LTER Europe;alex.turner@cyfoethnaturiolcymru.gov.uk;Andrew Sier;Centre for Ecology & Hydrology;arjs@ceh.ac.uk;Centre for Ecology & Hydrology Lancaster Lancashire LA1 4AP GB;Alex Turner;LTER Europe;alex.turner@cyfoethnaturiolcymru.gov.uk;2018-09-24;http://www.opengis.net/def/crs/EPSG/0/4326;Yr Wyddfa/Snowdon;https://deims.org/site/8b5da977-eed8-459f-b663-f3835aa0b356;Yr Wyddfa/Snowdon is an upland ECN site incorporating the summit of Yr Wyddfa or Snowdon, the highest mountain in England and Wales, 19km south-east of Bangor in North Wales. It is co-located with the Nant Teyrn freshwater site. The altitude ranges from 298-1085m and includes three additional summits over 800m. The bedrock is a mixture of Ordovician acidic and basic volcanic rocks, with localised igneous intrusions. Evidence of glaciation is widespread, with prominent corrie moraines. There are 5 lakes within the site, three of which form a 'staircase'. The soils are varied and include brown podzolic soil, gleys, organic peat soils and humic rankers. The dominant vegetation is acidic grassland with Festuca ovina (sheep's fescue) and Agrostis sp (bent grass) in the drier areas and Nardus stricta (mat grass) in the wetter areas. The site is part of the Yr Wyddfa/Snowdon National Nature Reserve, managed by the Natural Resources Wales under agreement with the owner. The land is unenclosed and grazed by sheep and a small herd of feral goats.;The original metadata record was created using DEIMS-SDR, the Dynamic Ecological Information Management System - Site and dataset registry;Alex Turner;LTER Europe;alex.turner@cyfoethnaturiolcymru.gov.uk;Natural Resources Wales;Alex Turner;LTER Europe;alex.turner@cyfoethnaturiolcymru.gov.uk;Andrew Sier;Centre for Ecology & Hydrology;arjs@ceh.ac.uk;Centre for Ecology & Hydrology Lancaster Lancashire LA1 4AP GB;Alex Turner;LTER Europe;alex.turner@cyfoethnaturiolcymru.gov.uk;site;emf2iso_pointer_record;agricultural parameter;atmospheric parameter;air humidity;air temperature;precipitation intensity;snow depth;net radiation irradiance;solar radiation;net solar radiation irradiance;total radiation irradiance;wind direction;wind speed;biological parameter;tree diameter;tree height;ecosystem parameter;ecosystem structure;habitat structure;diversity index;floristic diversity;species composition;plant species composition;species abundance;macrofauna abundance;species presence;birds presence;bryophytes presence;soil solute amount;species turnover;tree diameter at breast height;total carbon;total organic carbon;landscape parameter;land cover;land use;soil parameter;soil acidity;available phosphorus;bulk density;soil bulk density;carbon-to-nitrogen ratio;cation exchange capacity;inorganic carbon content;percent carbon;percent organic carbon;soil moisture field capacity;soil PH;soil temperature;soil solution concentration;dissolved organic carbon in soil;dissolved organic nitrogen in soil;dissolved organic phosphorus;thickness of soil horizon;total organic carbon in soil;water parameter;water acidity;conductivity;runoff;water level;stage height;water quality;water table;water volume;Terrestrial;continuousDataCollection;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;2008-06-01;English;environment;-4.07971;-4.0233;53.0564;53.0831;1995-01-01;https://deims.org/8b5da977-eed8-459f-b663-f3835aa0b356;http://data.ecn.ac.uk/sites/ecnsites.asp?site=T11;http://data.ecn.ac.uk/;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='8b5da977-eed8-459f-b663-f3835aa0b356'&outputFormat=SHAPE-ZIP;WFS GetFeature request for downloading the data set in SHP format;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='8b5da977-eed8-459f-b663-f3835aa0b356'&outputFormat=application%2Fgml%2Bxml%3B+version%3D3.2;WFS GetFeature request for downloading the data set in GML 3.2 format;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='8b5da977-eed8-459f-b663-f3835aa0b356'&outputFormat=application%2Fjson;WFS GetFeature request for downloading the data set in GeoJSON format;https://data.lter-europe.net/pycsw?service=CSW&version=3.0.0&request=GetRecordById&ElementSetName=full&outputSchema=http://www.isotc211.org/2005/gmd&outputFormat=application/json&id=7f3f4f08-36dc-4bbf-86e1-516ea7a7b461;HTTP;Catalogue Service for the Web (CSW);Snowdon: Ecosystem services variables from the UK Environmental Change Network (ECN);https://data.lter-europe.net/pycsw?service=CSW&version=3.0.0&request=GetRecordById&ElementSetName=full&outputSchema=http://www.isotc211.org/2005/gmd&outputFormat=application/json&id=a36a393e-cfed-4273-8a21-82af84610590;HTTP;Catalogue Service for the Web (CSW);Snowdon: UK Environmental Change Network (ECN) bat data: 1993-2015;https://data.lter-europe.net/pycsw?service=CSW&version=3.0.0&request=GetRecordById&ElementSetName=full&outputSchema=http://www.isotc211.org/2005/gmd&outputFormat=application/json&id=3b2d5dc9-a5fc-41fd-aec5-07ab5db38bcc;HTTP;Catalogue Service for the Web (CSW);Snowdon: UK Environmental Change Network (ECN) bird data: 1995-2015;https://data.lter-europe.net/pycsw?service=CSW&version=3.0.0&request=GetRecordById&ElementSetName=full&outputSchema=http://www.isotc211.org/2005/gmd&outputFormat=application/json&id=8081c7d2-08d5-46a6-bae2-6f4cea2fc8a5;HTTP;Catalogue Service for the Web (CSW);Snowdon: UK Environmental Change Network (ECN) butterfly data: 1993-2015;https://data.lter-europe.net/pycsw?service=CSW&version=3.0.0&request=GetRecordById&ElementSetName=full&outputSchema=http://www.isotc211.org/2005/gmd&outputFormat=application/json&id=5650f986-0fac-4585-ac46-8030fba77662;HTTP;Catalogue Service for the Web (CSW);Snowdon: UK Environmental Change Network (ECN) frog data: 1994-2015;https://data.lter-europe.net/pycsw?service=CSW&version=3.0.0&request=GetRecordById&ElementSetName=full&outputSchema=http://www.isotc211.org/2005/gmd&outputFormat=application/json&id=6968758e-69f5-4b48-97a3-bcbdc3e8d0bc;HTTP;Catalogue Service for the Web (CSW);Snowdon: UK Environmental Change Network (ECN) Precipitation Chemistry data: 1992-2015;https://data.lter-europe.net/pycsw?service=CSW&version=3.0.0&request=GetRecordById&ElementSetName=full&outputSchema=http://www.isotc211.org/2005/gmd&outputFormat=application/json&id=b0732973-d88d-4c62-ad07-8c07079f6f81;HTTP;Catalogue Service for the Web (CSW);Snowdon: UK Environmental Change Network (ECN) rabbit and deer data: 1993-2015;https://data.lter-europe.net/pycsw?service=CSW&version=3.0.0&request=GetRecordById&ElementSetName=full&outputSchema=http://www.isotc211.org/2005/gmd&outputFormat=application/json&id=2d99afb2-88ac-40dd-bfa6-000682fd9344;HTTP;Catalogue Service for the Web (CSW);Snowdon: UK Environmental Change Network (ECN) Soil Solution Chemistry data: 1992-2015;https://data.lter-europe.net/pycsw?service=CSW&version=3.0.0&request=GetRecordById&ElementSetName=full&outputSchema=http://www.isotc211.org/2005/gmd&outputFormat=application/json&id=e56725a0-06f0-48b0-9415-2ba8c4e261af;HTTP;Catalogue Service for the Web (CSW);Snowdon: UK Environmental Change Network (ECN) spittle bug data: 1993-2015;https://data.lter-europe.net/pycsw?service=CSW&version=3.0.0&request=GetRecordById&ElementSetName=full&outputSchema=http://www.isotc211.org/2005/gmd&outputFormat=application/json&id=f706469b-ba2f-4c2a-92a9-09abbb9ce6a0;HTTP;Catalogue Service for the Web (CSW);Snowdon: UK Environmental Change Network (ECN) Stream Water Chemistry data: 1992-2015;https://data.lter-europe.net/pycsw?service=CSW&version=3.0.0&request=GetRecordById&ElementSetName=full&outputSchema=http://www.isotc211.org/2005/gmd&outputFormat=application/json&id=80ab680d-cc59-4ab4-ac3a-86d5db433e65;HTTP;Catalogue Service for the Web (CSW);Snowdon: UK Environmental Change Network (ECN) Atmospheric Nitrogen chemistry data: 1993-2015;https://data.lter-europe.net/pycsw?service=CSW&version=3.0.0&request=GetRecordById&ElementSetName=full&outputSchema=http://www.isotc211.org/2005/gmd&outputFormat=application/json&id=a3dddee5-2a42-4871-8ae6-69ab2ffa1baa;HTTP;Catalogue Service for the Web (CSW);Snowdon: UK Environmental Change Network (ECN) baseline vegetation data: 1991-2000;https://data.lter-europe.net/pycsw?service=CSW&version=3.0.0&request=GetRecordById&ElementSetName=full&outputSchema=http://www.isotc211.org/2005/gmd&outputFormat=application/json&id=6ea09d0f-50f4-4a06-a3ce-f0ea75985bb0;HTTP;Catalogue Service for the Web (CSW);Snowdon: UK Environmental Change Network (ECN) carabid beetle data: 1992-2015;https://data.lter-europe.net/pycsw?service=CSW&version=3.0.0&request=GetRecordById&ElementSetName=full&outputSchema=http://www.isotc211.org/2005/gmd&outputFormat=application/json&id=30e1fae8-baf5-4d4e-a2e4-4ff7e8ff2bfb;HTTP;Catalogue Service for the Web (CSW);Snowdon: UK Environmental Change Network (ECN) coarse grain vegetation data: 1994-2015;https://data.lter-europe.net/pycsw?service=CSW&version=3.0.0&request=GetRecordById&ElementSetName=full&outputSchema=http://www.isotc211.org/2005/gmd&outputFormat=application/json&id=d24032a2-8c91-42b0-88cf-b144fa1096b4;HTTP;Catalogue Service for the Web (CSW);Snowdon: UK Environmental Change Network (ECN) fine grain vegetation data: 1994-2015;https://data.lter-europe.net/pycsw?service=CSW&version=3.0.0&request=GetRecordById&ElementSetName=full&outputSchema=http://www.isotc211.org/2005/gmd&outputFormat=application/json&id=c50d9276-e4b9-4cc7-aa85-93a3bf40c15b;HTTP;Catalogue Service for the Web (CSW);Snowdon: UK Environmental Change Network (ECN) meteorology data: 1991-2015;https://data.lter-europe.net/pycsw?service=CSW&version=3.0.0&request=GetRecordById&ElementSetName=full&outputSchema=http://www.isotc211.org/2005/gmd&outputFormat=application/json&id=44353843-0c0a-46ed-8166-313601e88cf8;HTTP;Catalogue Service for the Web (CSW);Snowdon: UK Environmental Change Network (ECN) moth data: 1992-2015;https://data.lter-europe.net/pycsw?service=CSW&version=3.0.0&request=GetRecordById&ElementSetName=full&outputSchema=http://www.isotc211.org/2005/gmd&outputFormat=application/json&id=aa722642-72ab-4601-8a49-62854c582853;HTTP;Catalogue Service for the Web (CSW);Snowdon: UK Environmental Change Network (ECN) Stream Water Discharge Data: 1993-2015;https://deims.org/node/240;United Kingdom (ECN);COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;publication;This data set is conformant with the INSPIRE Implementing Rules for the interoperability of spatial data sets and services;false;Dataset has been created by data transformation from the original record collected by the site managers using DEIMS site metadata editing form.",
-    "group": "deims",
-    "groups": [
-        {
-            "name": "deims"
-        }
-    ],
-    "name": "0a2a9d66-f441-5496-b304-d5a22b7c49ea",
-    "notes": [
-        "Yr Wyddfa/Snowdon is an upland ECN site incorporating the summit of Yr Wyddfa or Snowdon, the highest mountain in England and Wales, 19km south-east of Bangor in North Wales. It is co-located with the Nant Teyrn freshwater site. The altitude ranges from 298-1085m and includes three additional summits over 800m. The bedrock is a mixture of Ordovician acidic and basic volcanic rocks, with localised igneous intrusions. Evidence of glaciation is widespread, with prominent corrie moraines. There are 5 lakes within the site, three of which form a 'staircase'. The soils are varied and include brown podzolic soil, gleys, organic peat soils and humic rankers. The dominant vegetation is acidic grassland with Festuca ovina (sheep's fescue) and Agrostis sp (bent grass) in the drier areas and Nardus stricta (mat grass) in the wetter areas. The site is part of the Yr Wyddfa/Snowdon National Nature Reserve, managed by the Natural Resources Wales under agreement with the owner. The land is unenclosed and grazed by sheep and a small herd of feral goats."
-    ],
-    "oai_identifier": [
-        "0a2a9d66-f441-5496-b304-d5a22b7c49ea"
-    ],
-    "oai_set": "full",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-4.07971,53.0564],[-4.07971,53.0831],[-4.0233,53.0831],[-4.0233,53.0564],[-4.07971,53.0564]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "site"
-        },
-        {
-            "name": "emfiso_pointer_record"
-        },
-        {
-            "name": "agricultural parameter"
-        },
-        {
-            "name": "atmospheric parameter"
-        },
-        {
-            "name": "air humidity"
-        },
-        {
-            "name": "air temperature"
-        },
-        {
-            "name": "precipitation intensity"
-        },
-        {
-            "name": "snow depth"
-        },
-        {
-            "name": "net radiation irradiance"
-        },
-        {
-            "name": "solar radiation"
-        },
-        {
-            "name": "net solar radiation irradiance"
-        },
-        {
-            "name": "total radiation irradiance"
-        }
-    ],
-    "title": [
-        "Yr Wyddfa/Snowdon"
-    ],
-    "url": "https://deims.org/node/240"
-}
\ No newline at end of file
diff --git a/oaitestdata/deims-iso19139/full_1/json/0a48d7d8-120d-5397-ac5b-56f69691d825.json b/oaitestdata/deims-iso19139/full_1/json/0a48d7d8-120d-5397-ac5b-56f69691d825.json
deleted file mode 100644
index 83d05050..00000000
--- a/oaitestdata/deims-iso19139/full_1/json/0a48d7d8-120d-5397-ac5b-56f69691d825.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "g.morabito@ise.cnr.it",
-        "m.coci@ise.cnr.it"
-    ],
-    "Contributor": "DEIMS-SDR | Site and Dataset registry deims.org",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "https://deims.org/pycsw/catalogue/csw?verb=GetRecord&metadataPrefix=iso19139&identifier=0a48d7d8-120d-5397-ac5b-56f69691d825",
-    "PublicationTimestamp": "2018-09-24T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "LTER Europe"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Co-authorship on publications resulting from use of the dataset"
-    ],
-    "SpatialCoverage": "(46N-46N,9 E-8 E)",
-    "author": [
-        "Giuseppe Morabito",
-        "Manuela Coci"
-    ],
-    "fulltext": "d9e94776-e7a8-11e2-a655-005056ab003f;English;utf8;dataset;Manuela Coci;LTER Europe;Largo Tonolli, 50;Verbania Pallanza;VB;28900;IT;m.coci@ise.cnr.it;pointOfContact;Giuseppe Morabito;LTER Europe;Largo Tonolli 50;Verbania;VB;28900;IT;g.morabito@ise.cnr.it;pointOfContact;2018-09-24;ISO19115;2003/Cor.1:2006;EPSG:4326;http://www.opengis.net/def/crs/EPSG/0/4326;http://www.opengis.net/def/crs/EPSG/0/4258;Biovolume of Phytoplankton in Lake Maggiore site code IT_SI001137_within the period 1981 - 2010;2018-09-24;publication;urn:ltereurope:inspire::8932:26499;Lago Maggiore - Italy;Manuela Coci;LTER Europe;Largo Tonolli, 50;Verbania Pallanza;VB;28900;IT;m.coci@ise.cnr.it;pointOfContact;documentDigital;Dataset provides information about biovolume of phytoplankton collected in Lake Maggiore from 1981 to 2010.;completed;Manuela Coci;LTER Europe;Largo Tonolli, 50;Verbania Pallanza;VB;28900;IT;m.coci@ise.cnr.it;pointOfContact;Giuseppe Morabito;LTER Europe;Largo Tonolli 50;Verbania;VB;28900;IT;g.morabito@ise.cnr.it;pointOfContact;continual;Representative area of sampling: _unknown Sampling frequency - sampling time span: monthly Sampling frequency - minimum sampling unit: _unknown;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;2008-06-01;publication;Asterionella formosa;Tabellaria simplex;Diatoms;Biological Classification;Changes in population size over time;phytoplankton;Permanent oligotrophic lakes, ponds and pools;LTER Controlled Vocabulary;Co-authorship on publications resulting from use of the dataset;The principal: Research has granted the access and use permission: Free for access;eng;environment;8.619120000000;8.479040000000;45.837170000000;45.940410000000;194.00;194;urn:ogc:def:crs:EPSG;MSL height;Not specific to any location or epoch.;Hydrography.;Representative area of sampling: _unknown;ground condition;1980-12-31;2010-12-30;ftp://KU2253_2@ftp.umweltbundesamt.at/KnownUsers/2253_2/EnvEurope_DataCollection/;WWW:DOWNLOAD-1.0-http--download;ftp://ftp.umweltbundesamt.at/;dataset;Conformity_001;INSPIRE;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;publication;See the referenced specification;Directive 2000/60/EC of the European Parliament and of the Council of 23 October 2000 establishing a framework for Community action in the field of water policy;2000-10-23;publication;See the referenced specification;Method description: na. Method URL: . Instrumentation: Optical Microscope;Metadata Access Constraints: none Metadata Use Constraints: none;annually",
-    "group": "deims",
-    "groups": [
-        {
-            "name": "deims"
-        }
-    ],
-    "name": "0a48d7d8-120d-5397-ac5b-56f69691d825",
-    "notes": [
-        "Dataset provides information about biovolume of phytoplankton collected in Lake Maggiore from 1981 to 2010."
-    ],
-    "oai_identifier": [
-        "0a48d7d8-120d-5397-ac5b-56f69691d825"
-    ],
-    "oai_set": "full",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[8.619120000000,45.837170000000],[8.619120000000,45.940410000000],[8.479040000000,45.940410000000],[8.479040000000,45.837170000000],[8.619120000000,45.837170000000]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Asterionella formosa"
-        },
-        {
-            "name": "Tabellaria simplex"
-        },
-        {
-            "name": "Diatoms"
-        },
-        {
-            "name": "Changes population size time"
-        },
-        {
-            "name": "phytoplankton"
-        },
-        {
-            "name": "Permanent oligotrophic lakes"
-        },
-        {
-            "name": "ponds pools"
-        }
-    ],
-    "title": [
-        "Biovolume of Phytoplankton in Lake Maggiore site code IT_SI001137_within the period 1981 - 2010"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/deims-iso19139/full_1/json/0a4a8f9b-72cc-50ee-a0a3-10dec50e9e1d.json b/oaitestdata/deims-iso19139/full_1/json/0a4a8f9b-72cc-50ee-a0a3-10dec50e9e1d.json
deleted file mode 100644
index 4a966db7..00000000
--- a/oaitestdata/deims-iso19139/full_1/json/0a4a8f9b-72cc-50ee-a0a3-10dec50e9e1d.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contributor": "DEIMS-SDR | Site and Dataset registry deims.org",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Format": [
-        "Research site"
-    ],
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "https://deims.org/pycsw/catalogue/csw?verb=GetRecord&metadataPrefix=iso19139&identifier=0a4a8f9b-72cc-50ee-a0a3-10dec50e9e1d",
-    "ResourceType": [
-        "dataset"
-    ],
-    "SpatialCoverage": "(43S,147E)",
-    "fulltext": "153c699b-2237-445d-9b9c-29f8acc697ab;English;utf8;dataset;Research site;2018-09-24;http://www.opengis.net/def/crs/EPSG/0/4326;TERN Warra Tall Eucalypt SuperSite;https://deims.org/site/153c699b-2237-445d-9b9c-29f8acc697ab;Warra Tall Eucalypt SuperSite is a member of the Australian SuperSite Network (SuperSites, http://www.supersites.net.au/), a facility within the Australian Terrestrial Ecosystem Network (TERN, http://www.tern.org.au/). SuperSites aims to answer both network wide and site-specific science questions through long term monitoring using both sensor technology and classical field methods. The Warra Tall Eucalypt SuperSite is located in southern Tasmania, where tall, wet Eucalyptus obliqua forests predominate, and are part of the cool, temperate wet forest biome. These forests are among the most productive terrestrial ecosystems in the world and their management generates a disproportionately high social and political interest. The site also includes some areas of moorland, temperate rainforest, riparian and montane conifer forest and scrubs. Warra is partly within the Tasmanian Wilderness World Heritage Area, which is managed for conservation, and partly within State forest, which is managed for multiple purposes including wood production. Warra Tall Eucalypt was established as a Long-term Ecological Research (LTER) site in 1995, and is one of Australia\u2019s most scientifically productive. It is a hub for intensive, multi-disciplinary research to understand the fundamental ecological processes in E. obliqua forests and the long-term effects that management has on those processes in contrast with natural disturbance. Current research is focussing on the bio-physical processes that support the biota and how they fluctuate across scales both spatial and temporal. Detailed knowledge exists for many elements of the biota at Warra Tall Eucalypt their habitats, their distribution and their response to disturbance. Importantly, research done at Warra Tall Eucalypt has directly driven improvements in forest management more generally, e.g. the introduction of variable retention silviculture in mature tall, wet eucalypt forests. Key research objectives - What are the fundamental ecological processes in E. obliqua wet forests? - What are the current biodiversity and geodiversity of the site and how are these changing, evolving and interacting? - What are the long-term effects of different forest management and fire regimes on biodiversity, geodiversity and ecological processes? - What are the flows of water, nutrients and energy, the biota through which those flows occur, and how do they assemble, interact, and change over time? - How do disturbances, both natural and human-induced alter the biological, physical and geochemical properties of the ecosystem? In particular, what are the mechanisms through which the ecosystem recovers following disturbance, what are the feedbacks that determine or alter those responses, and what are the thresholds beyond which state changes occur?;The original metadata record was created using DEIMS-SDR, the Dynamic Ecological Information Management System - Site and dataset registry;site;emf2iso_pointer_record;atmospheric parameter;air temperature;air water vapour pressure;carbon dioxide concentration;precipitation intensity;wind direction;wind speed;biological parameter;plant height;tree diameter;tree distribution;tree height;ecosystem parameter;disturbance pattern;fire severity index;ecosystem structure;forest structure;canopy cover rate;leaf area;leaf area index;microbial diversity;species turnover;tree diameter at breast height;deadwood decaying rate;soil parameter;soil moisture field capacity;soil moisture content;soil PH;continuousDataCollection;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;2008-06-01;English;environment;146.683758000000;146.683758000000;-43.098625000000;-43.098625000000;1995-01-01;https://deims.org/153c699b-2237-445d-9b9c-29f8acc697ab;http://www.supersites.net.au/supersites/wrra;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='153c699b-2237-445d-9b9c-29f8acc697ab'&outputFormat=SHAPE-ZIP;WFS GetFeature request for downloading the data set in SHP format;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='153c699b-2237-445d-9b9c-29f8acc697ab'&outputFormat=application%2Fgml%2Bxml%3B+version%3D3.2;WFS GetFeature request for downloading the data set in GML 3.2 format;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='153c699b-2237-445d-9b9c-29f8acc697ab'&outputFormat=application%2Fjson;WFS GetFeature request for downloading the data set in GeoJSON format;https://deims.org/node/245;Australia (TERN);COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;publication;This data set is conformant with the INSPIRE Implementing Rules for the interoperability of spatial data sets and services;false;Dataset has been created by data transformation from the original record collected by the site managers using DEIMS site metadata editing form.",
-    "group": "deims",
-    "groups": [
-        {
-            "name": "deims"
-        }
-    ],
-    "name": "0a4a8f9b-72cc-50ee-a0a3-10dec50e9e1d",
-    "notes": [
-        "Warra Tall Eucalypt SuperSite is a member of the Australian SuperSite Network (SuperSites, http://www.supersites.net.au/), a facility within the Australian Terrestrial Ecosystem Network (TERN, http://www.tern.org.au/). SuperSites aims to answer both network wide and site-specific science questions through long term monitoring using both sensor technology and classical field methods. The Warra Tall Eucalypt SuperSite is located in southern Tasmania, where tall, wet Eucalyptus obliqua forests predominate, and are part of the cool, temperate wet forest biome. These forests are among the most productive terrestrial ecosystems in the world and their management generates a disproportionately high social and political interest. The site also includes some areas of moorland, temperate rainforest, riparian and montane conifer forest and scrubs. Warra is partly within the Tasmanian Wilderness World Heritage Area, which is managed for conservation, and partly within State forest, which is managed for multiple purposes including wood production. Warra Tall Eucalypt was established as a Long-term Ecological Research (LTER) site in 1995, and is one of Australia\u2019s most scientifically productive. It is a hub for intensive, multi-disciplinary research to understand the fundamental ecological processes in E. obliqua forests and the long-term effects that management has on those processes in contrast with natural disturbance. Current research is focussing on the bio-physical processes that support the biota and how they fluctuate across scales both spatial and temporal. Detailed knowledge exists for many elements of the biota at Warra Tall Eucalypt their habitats, their distribution and their response to disturbance. Importantly, research done at Warra Tall Eucalypt has directly driven improvements in forest management more generally, e.g. the introduction of variable retention silviculture in mature tall, wet eucalypt forests. Key research objectives - What are the fundamental ecological processes in E. obliqua wet forests? - What are the current biodiversity and geodiversity of the site and how are these changing, evolving and interacting? - What are the long-term effects of different forest management and fire regimes on biodiversity, geodiversity and ecological processes? - What are the flows of water, nutrients and energy, the biota through which those flows occur, and how do they assemble, interact, and change over time? - How do disturbances, both natural and human-induced alter the biological, physical and geochemical properties of the ecosystem? In particular, what are the mechanisms through which the ecosystem recovers following disturbance, what are the feedbacks that determine or alter those responses, and what are the thresholds beyond which state changes occur?"
-    ],
-    "oai_identifier": [
-        "0a4a8f9b-72cc-50ee-a0a3-10dec50e9e1d"
-    ],
-    "oai_set": "full",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[146.683758000000,-43.098625000000],[146.683758000000,-43.098625000000],[146.683758000000,-43.098625000000],[146.683758000000,-43.098625000000],[146.683758000000,-43.098625000000]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "site"
-        },
-        {
-            "name": "emfiso_pointer_record"
-        },
-        {
-            "name": "atmospheric parameter"
-        },
-        {
-            "name": "air temperature"
-        },
-        {
-            "name": "air water vapour pressure"
-        },
-        {
-            "name": "carbon dioxide concentration"
-        },
-        {
-            "name": "precipitation intensity"
-        },
-        {
-            "name": "wind direction"
-        },
-        {
-            "name": "wind speed"
-        },
-        {
-            "name": "biological parameter"
-        },
-        {
-            "name": "plant height"
-        },
-        {
-            "name": "tree diameter"
-        }
-    ],
-    "title": [
-        "TERN Warra Tall Eucalypt SuperSite"
-    ],
-    "url": "https://deims.org/node/245"
-}
\ No newline at end of file
diff --git a/oaitestdata/deims-iso19139/full_1/json/0a51954b-e2e4-51da-91a7-817ef706319d.json b/oaitestdata/deims-iso19139/full_1/json/0a51954b-e2e4-51da-91a7-817ef706319d.json
deleted file mode 100644
index 39dfcae9..00000000
--- a/oaitestdata/deims-iso19139/full_1/json/0a51954b-e2e4-51da-91a7-817ef706319d.json
+++ /dev/null
@@ -1,92 +0,0 @@
-{
-    "Contact": [
-        "arjs@ceh.ac.uk",
-        "donm@ceh.ac.uk"
-    ],
-    "Contributor": "DEIMS-SDR | Site and Dataset registry deims.org",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Format": [
-        "Research site"
-    ],
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "https://deims.org/pycsw/catalogue/csw?verb=GetRecord&metadataPrefix=iso19139&identifier=0a51954b-e2e4-51da-91a7-817ef706319d",
-    "Publisher": [
-        "Centre for Ecology & Hydrology",
-        "LTER Europe"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "SpatialCoverage": "(55N,7 W)",
-    "author": [
-        "Andrew Sier",
-        "Don Monteith"
-    ],
-    "fulltext": "4ed8c99b-cb25-4a19-96f9-fc3c72b549fc;English;utf8;dataset;Research site;Don Monteith;LTER Europe;donm@ceh.ac.uk;Andrew Sier;Centre for Ecology & Hydrology;arjs@ceh.ac.uk;Centre for Ecology & Hydrology Lancaster Lancashire LA1 4AP GB;Don Monteith;LTER Europe;donm@ceh.ac.uk;2018-09-24;http://www.opengis.net/def/crs/EPSG/0/4326;Coneyglen Burn;https://deims.org/site/4ed8c99b-cb25-4a19-96f9-fc3c72b549fc;UK Upland Waters Monitoring Network (UK UWMN) site. The Coneyglen Burn lies in the Sperrin Mountains of central Northern Ireland. The catchment area is 1264 ha and rises from 230 m at the sampling station to a maximum of 562 m at Carnanelly. The underlying geology is schists of the Mullaghcarn series, which occur in places as rocky outcrops. Catchment soils are dominated by blanket peats and peaty podsols. Adjacent to the stream the thin peat is interspersed with alluvium, sands and gravels. Originally some 4% of the catchment (the lower section) was planted with conifers but this has increased slightly since 2000 as the forested area was enlarged. Previously improved grazing land in the middle section of the catchment, adjacent to a small farm, is no longer actively managed, except by grazing, and is reverting to moorland, with a predominance of Juncus species. Old field systems and drainage patterns suggest a higher intensity of land-use in the past. Elsewhere, the vegetation is characterised by moorland species, notably Calluna. Contemporary land-use and management is confined to low-intensity sheep grazing and infrequent heather burning. The annual rainfall is c.1500 mm. Note: The area is the size of the catchment.;The original metadata record was created using DEIMS-SDR, the Dynamic Ecological Information Management System - Site and dataset registry;Don Monteith;LTER Europe;donm@ceh.ac.uk;Andrew Sier;Centre for Ecology & Hydrology;arjs@ceh.ac.uk;Centre for Ecology & Hydrology Lancaster Lancashire LA1 4AP GB;Don Monteith;LTER Europe;donm@ceh.ac.uk;site;emf2iso_pointer_record;ecosystem parameter;diversity index;floristic diversity;faunistic diversity;species composition;plant species composition;species richness;species presence;nitrogen content;ammonium content;dissolved nutrient;inorganic nutrient content;total organic carbon;water parameter;water acidity;water alkalinity;chlorophyll content of water;conductivity;dissolved organic carbon in water;water transparency;water level;stage height;water quality;suspended solids;water temperature;Fresh water rivers;continuousDataCollection;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;2008-06-01;English;environment;-7.005540000000;-7.005540000000;54.739400000000;54.739400000000;1990-01-01;https://deims.org/4ed8c99b-cb25-4a19-96f9-fc3c72b549fc;http://awmn.defra.gov.uk/sites/site_22.php;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='4ed8c99b-cb25-4a19-96f9-fc3c72b549fc'&outputFormat=SHAPE-ZIP;WFS GetFeature request for downloading the data set in SHP format;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='4ed8c99b-cb25-4a19-96f9-fc3c72b549fc'&outputFormat=application%2Fgml%2Bxml%3B+version%3D3.2;WFS GetFeature request for downloading the data set in GML 3.2 format;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='4ed8c99b-cb25-4a19-96f9-fc3c72b549fc'&outputFormat=application%2Fjson;WFS GetFeature request for downloading the data set in GeoJSON format;https://deims.org/node/240;United Kingdom (ECN);COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;publication;This data set is conformant with the INSPIRE Implementing Rules for the interoperability of spatial data sets and services;false;Dataset has been created by data transformation from the original record collected by the site managers using DEIMS site metadata editing form.",
-    "group": "deims",
-    "groups": [
-        {
-            "name": "deims"
-        }
-    ],
-    "name": "0a51954b-e2e4-51da-91a7-817ef706319d",
-    "notes": [
-        "UK Upland Waters Monitoring Network (UK UWMN) site. The Coneyglen Burn lies in the Sperrin Mountains of central Northern Ireland. The catchment area is 1264 ha and rises from 230 m at the sampling station to a maximum of 562 m at Carnanelly. The underlying geology is schists of the Mullaghcarn series, which occur in places as rocky outcrops. Catchment soils are dominated by blanket peats and peaty podsols. Adjacent to the stream the thin peat is interspersed with alluvium, sands and gravels. Originally some 4% of the catchment (the lower section) was planted with conifers but this has increased slightly since 2000 as the forested area was enlarged. Previously improved grazing land in the middle section of the catchment, adjacent to a small farm, is no longer actively managed, except by grazing, and is reverting to moorland, with a predominance of Juncus species. Old field systems and drainage patterns suggest a higher intensity of land-use in the past. Elsewhere, the vegetation is characterised by moorland species, notably Calluna. Contemporary land-use and management is confined to low-intensity sheep grazing and infrequent heather burning. The annual rainfall is c.1500 mm. Note: The area is the size of the catchment."
-    ],
-    "oai_identifier": [
-        "0a51954b-e2e4-51da-91a7-817ef706319d"
-    ],
-    "oai_set": "full",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-7.005540000000,54.739400000000],[-7.005540000000,54.739400000000],[-7.005540000000,54.739400000000],[-7.005540000000,54.739400000000],[-7.005540000000,54.739400000000]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "site"
-        },
-        {
-            "name": "emfiso_pointer_record"
-        },
-        {
-            "name": "ecosystem parameter"
-        },
-        {
-            "name": "diversity index"
-        },
-        {
-            "name": "floristic diversity"
-        },
-        {
-            "name": "faunistic diversity"
-        },
-        {
-            "name": "species composition"
-        },
-        {
-            "name": "plant species composition"
-        },
-        {
-            "name": "species richness"
-        },
-        {
-            "name": "species presence"
-        },
-        {
-            "name": "nitrogen content"
-        },
-        {
-            "name": "ammonium content"
-        }
-    ],
-    "title": [
-        "Coneyglen Burn"
-    ],
-    "url": "https://deims.org/node/240"
-}
\ No newline at end of file
diff --git a/oaitestdata/deims-iso19139/full_1/json/0a6afaad-9507-58c8-8456-1d55f568c485.json b/oaitestdata/deims-iso19139/full_1/json/0a6afaad-9507-58c8-8456-1d55f568c485.json
deleted file mode 100644
index 9038af13..00000000
--- a/oaitestdata/deims-iso19139/full_1/json/0a6afaad-9507-58c8-8456-1d55f568c485.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "giampaolo.rossetti@unipr.it",
-        "isabella.bertani@nemo.unipr.it"
-    ],
-    "Contributor": "DEIMS-SDR | Site and Dataset registry deims.org",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "https://deims.org/pycsw/catalogue/csw?verb=GetRecord&metadataPrefix=iso19139&identifier=0a6afaad-9507-58c8-8456-1d55f568c485",
-    "PublicationTimestamp": "2018-09-24T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "LTER Europe"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Co-authorship on publications resulting from use of the dataset"
-    ],
-    "SpatialCoverage": "(44N-44N,10E-10E)",
-    "author": [
-        "Giampaolo Rossetti",
-        "Isabella Bertani"
-    ],
-    "fulltext": "6b64a758-811e-11e4-a976-005056ab003f;English;utf8;dataset;Isabella Bertani;LTER Europe;isabella.bertani@nemo.unipr.it;pointOfContact;Giampaolo Rossetti;LTER Europe;Viale G.P. Usberti 11A;Parma;PR;43100;IT;giampaolo.rossetti@unipr.it;pointOfContact;2018-09-24;ISO19115;2003/Cor.1:2006;EPSG:4326;http://www.opengis.net/def/crs/EPSG/0/4326;http://www.opengis.net/def/crs/EPSG/0/4258;Dissolved oxygen in Lake Santo Parmense (2001-2003);2018-09-24;publication;urn:ltereurope:inspire::8963:10140;Lago Santo Parmense - Italy;Isabella Bertani;LTER Europe;isabella.bertani@nemo.unipr.it;pointOfContact;documentDigital;Dataset provides dissolved oxygen measured in Lake Santo Parmense during the period 2001-2003. Water samples were collected by means of a Ruttner bottle at different depths over the whole water column at the point of maximum depth of the lake. Dissolved oxygen was measured by means of the Winkler method.;completed;Isabella Bertani;LTER Europe;isabella.bertani@nemo.unipr.it;pointOfContact;Giampaolo Rossetti;LTER Europe;Viale G.P. Usberti 11A;Parma;PR;43100;IT;giampaolo.rossetti@unipr.it;pointOfContact;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;2008-06-01;publication;lakes;freshwater;system classification;LTER Controlled Vocabulary;Co-authorship on publications resulting from use of the dataset;The principal: Research has granted the access and use permission: Free for access and use upon request;The principal: has granted the access and use permission: Research;The principal: Public has granted the access and use permission: Other restrictions according to rules defined in intellectual rights;eng;environment;10.010050000000;10.004770000000;44.400800000000;44.403920000000;1507.00;1507;urn:ogc:def:crs:EPSG;MSL height;Not specific to any location or epoch.;Hydrography.;ground condition;2001-05-14;2003-10-21;http://sp7.irea.cnr.it/sensors/noSK/;WWW:LINK-1.0-http--link;http://sp7.irea.cnr.it/sensors/noSK/;dataset;Conformity_001;INSPIRE;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;publication;See the referenced specification;Method description: pH was measured in the lab by means of a pH meter (Spatial Scale Description: Water samples were collected at the point of maximum depth of the lake by means of a Ruttner bottle. Samples were collected at the following depths for each year: 1971-april 1973 and 1975: 0, -5 m, -10 m, -15 m, bottom; june 1973-1974: 0, -2 m, -5 m, -10 m, -15 m, -18 m, bottom. Winkler reagents were immediately added to samples, which were then kept refrigerated and transported to the laboratory for analysis according to the Winkler method. Sampling frequency differed among years: 1971: monthly from july to october; 1972: monthly (occasionally twice a month) from may to october; 1973: irregular frequency from january to november (ranging from monthly to three times a month); 1974: monthly from january to october (excluding june); 1975: monthly from june to october (excluding august).). Method URL: . Instrumentation: Ruttner bottle;Metadata Access Constraints: none Metadata Use Constraints: none;annually",
-    "group": "deims",
-    "groups": [
-        {
-            "name": "deims"
-        }
-    ],
-    "name": "0a6afaad-9507-58c8-8456-1d55f568c485",
-    "notes": [
-        "Dataset provides dissolved oxygen measured in Lake Santo Parmense during the period 2001-2003. Water samples were collected by means of a Ruttner bottle at different depths over the whole water column at the point of maximum depth of the lake. Dissolved oxygen was measured by means of the Winkler method."
-    ],
-    "oai_identifier": [
-        "0a6afaad-9507-58c8-8456-1d55f568c485"
-    ],
-    "oai_set": "full",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[10.010050000000,44.400800000000],[10.010050000000,44.403920000000],[10.004770000000,44.403920000000],[10.004770000000,44.400800000000],[10.010050000000,44.400800000000]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "lakes"
-        },
-        {
-            "name": "freshwater"
-        },
-        {
-            "name": "system classification"
-        }
-    ],
-    "title": [
-        "Dissolved oxygen in Lake Santo Parmense (2001-2003)"
-    ],
-    "url": "http://sp7.irea.cnr.it/sensors/noSK/"
-}
\ No newline at end of file
diff --git a/oaitestdata/deims-iso19139/full_1/json/0a9a723b-2df6-5bbc-8ffb-55126af74c3e.json b/oaitestdata/deims-iso19139/full_1/json/0a9a723b-2df6-5bbc-8ffb-55126af74c3e.json
deleted file mode 100644
index d265136c..00000000
--- a/oaitestdata/deims-iso19139/full_1/json/0a9a723b-2df6-5bbc-8ffb-55126af74c3e.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "srennie@ceh.ac.uk"
-    ],
-    "Contributor": "DEIMS-SDR | Site and Dataset registry deims.org",
-    "DOI": "http://dx.doi.org/10.5285/a2a49f47-49b3-46da-a434-bb22e524c5d2",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "https://deims.org/pycsw/catalogue/csw?verb=GetRecord&metadataPrefix=iso19139&identifier=0a9a723b-2df6-5bbc-8ffb-55126af74c3e",
-    "PublicationTimestamp": "2018-09-24T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Formal acknowledgement of the dataset providers"
-    ],
-    "SpatialCoverage": "(52N-52N,0 W-0 W)",
-    "author": [
-        "Sue Rennie"
-    ],
-    "fulltext": "d4ff106c-c00d-4df0-b0e5-90f19180684c;English;utf8;dataset;Sue Rennie;Centre for Ecology & Hydrology;+44 1524 595835;Centre for Ecology & Hydrology;Lancaster;Lancashire;LA1 4AP;GB;srennie@ceh.ac.uk;pointOfContact;2018-09-24;ISO19115;2003/Cor.1:2006;EPSG:4326;http://www.opengis.net/def/crs/EPSG/0/4326;http://www.opengis.net/def/crs/EPSG/0/4258;Rothamsted: UK Environmental Change Network (ECN) moth data: 1992-2015;2018-09-24;publication;urn:ltereurope:inspire::11775:26551;Rothamsted - United Kingdom;Centre for Ecology and Hydrology/Natural Environment Research Council;Biotechnology and Biological Sciences Research Council;Sue Rennie;Centre for Ecology & Hydrology;+44 1524 595835;Centre for Ecology & Hydrology;Lancaster;Lancashire;LA1 4AP;GB;srennie@ceh.ac.uk;pointOfContact;Rothamsted Research;documentDigital;Moth data from the UK Environmental Change Network (ECN) terrestrial sites. Counts of individual species are recorded. These data are collected by moth traps at all of ECN&#039;s terrestrial sites using a standard protocol.They represent continuous nightly records from 1992 to 2015. ECN is the UK&#039;s long-term environmental monitoring programme. It is a multi-agency programme sponsored by a consortium of fourteen government departments and agencies. These organisations contribute to the programme through funding either site monitoring and/or network co-ordination activities. These organisations are: Agri-Food and Biosciences Institute, Biotechnology and Biological Sciences Research Council, Cyfoeth Naturiol Cymru - Natural Resources Wales, Defence Science &amp; Technology Laboratory, Department for Environment, Food and Rural Affairs, Environment Agency, Forestry Commission, Llywodraeth Cymru - Welsh Government, Natural England, Natural Environment Research Council, Northern Ireland Environment Agency, Scottish Environment Protection Agency, Scottish Government and Scottish Natural Heritage.;completed;Sue Rennie;Centre for Ecology & Hydrology;+44 1524 595835;Centre for Ecology & Hydrology;Lancaster;Lancashire;LA1 4AP;GB;srennie@ceh.ac.uk;pointOfContact;continual;Representative area of sampling: single point Sampling frequency - sampling time span: daily Sampling frequency - minimum sampling unit: daily;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;2008-06-01;publication;Insect;moth;LTER Controlled Vocabulary;Formal acknowledgement of the dataset providers;The principal: Administration has granted the access and use permission: Free access and use;The principal: Research has granted the access and use permission: Free for access;The principal: Public has granted the access and use permission: Free for access;eng;environment;Rothamsted ECN site;-0.360951000000;-0.389991580000;51.803405760000;51.815193180000;134.00;94;urn:ogc:def:crs:EPSG;MSL height;Not specific to any location or epoch.;Hydrography.;Representative area of sampling: single point;ground condition;1992-01-01;2015-12-31;https://doi.org/10.5285/a2a49f47-49b3-46da-a434-bb22e524c5d2;WWW:LINK-1.0-http--link;DOI;dataset;Conformity_001;INSPIRE;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;publication;See the referenced specification;Method description: Moth data from the UK Environmental Change Network (ECN) terrestrial sites. Counts of individual species are recorded. These data are collected by moth traps at all of ECN's terrestrial sites using a standard protocol.They represent continuous nightly records from 1992 to 2015.. Method URL: http://www.ecn.ac.uk/measurements/terrestrial/i. Instrumentation:;Metadata Access Constraints: none Metadata Use Constraints: none;annually",
-    "group": "deims",
-    "groups": [
-        {
-            "name": "deims"
-        }
-    ],
-    "name": "0a9a723b-2df6-5bbc-8ffb-55126af74c3e",
-    "notes": [
-        "Moth data from the UK Environmental Change Network (ECN) terrestrial sites. Counts of individual species are recorded. These data are collected by moth traps at all of ECN&#039;s terrestrial sites using a standard protocol.They represent continuous nightly records from 1992 to 2015. ECN is the UK&#039;s long-term environmental monitoring programme. It is a multi-agency programme sponsored by a consortium of fourteen government departments and agencies. These organisations contribute to the programme through funding either site monitoring and/or network co-ordination activities. These organisations are: Agri-Food and Biosciences Institute, Biotechnology and Biological Sciences Research Council, Cyfoeth Naturiol Cymru - Natural Resources Wales, Defence Science &amp; Technology Laboratory, Department for Environment, Food and Rural Affairs, Environment Agency, Forestry Commission, Llywodraeth Cymru - Welsh Government, Natural England, Natural Environment Research Council, Northern Ireland Environment Agency, Scottish Environment Protection Agency, Scottish Government and Scottish Natural Heritage."
-    ],
-    "oai_identifier": [
-        "0a9a723b-2df6-5bbc-8ffb-55126af74c3e"
-    ],
-    "oai_set": "full",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-0.360951000000,51.803405760000],[-0.360951000000,51.815193180000],[-0.389991580000,51.815193180000],[-0.389991580000,51.803405760000],[-0.360951000000,51.803405760000]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Insect"
-        },
-        {
-            "name": "moth"
-        }
-    ],
-    "title": [
-        "Rothamsted: UK Environmental Change Network (ECN) moth data: 1992-2015"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/deims-iso19139/full_1/json/0b092590-0aa6-5bd7-84b3-436223a677e0.json b/oaitestdata/deims-iso19139/full_1/json/0b092590-0aa6-5bd7-84b3-436223a677e0.json
deleted file mode 100644
index b618e5c3..00000000
--- a/oaitestdata/deims-iso19139/full_1/json/0b092590-0aa6-5bd7-84b3-436223a677e0.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "renukaroo@gmail.com"
-    ],
-    "Contributor": "DEIMS-SDR | Site and Dataset registry deims.org",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Format": [
-        "Research site"
-    ],
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "https://deims.org/pycsw/catalogue/csw?verb=GetRecord&metadataPrefix=iso19139&identifier=0b092590-0aa6-5bd7-84b3-436223a677e0",
-    "Publisher": [
-        "South African Environmental Observation Network",
-        "Wolwekraal Conservation and Research Organisation"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "SpatialCoverage": "(33S,22E)",
-    "author": [
-        "Sue Milton-Dean",
-        "GDPR ca314889-4f17-4801-bd8e-c50c783c04ac"
-    ],
-    "fulltext": "356fac88-0041-4833-8273-b31789bc3763;English;utf8;dataset;Research site;South African Environmental Observation Network;Sue Milton-Dean;South African Environmental Observation Network;renukaroo@gmail.com;P.O. Box 47 Prince Albert 6930 ZA;GDPR ca314889-4f17-4801-bd8e-c50c783c04ac;South African Environmental Observation Network;Wolwekraal Conservation and Research Organisation;Sue Milton-Dean;South African Environmental Observation Network;renukaroo@gmail.com;P.O. Box 47 Prince Albert 6930 ZA;GDPR ca314889-4f17-4801-bd8e-c50c783c04ac;South African Environmental Observation Network;2018-09-24;http://www.opengis.net/def/crs/EPSG/0/4326;Wolwekraal Nature Reserve;https://deims.org/site/356fac88-0041-4833-8273-b31789bc3763;The field site comprises 123 ha of natural Karoo shrubland. The Dorpsrivier passes through the nature reserve. Habitats include exposed Ecca mudstone plains, a north-facing ridge, pockets of aolian sand, and quatzite pebble bed conglomerate along the levees of the Dorpsrivier. The field site has been fenced to exclude domestic livestock since the 1970s.;The original metadata record was created using DEIMS-SDR, the Dynamic Ecological Information Management System - Site and dataset registry;South African Environmental Observation Network;Sue Milton-Dean;South African Environmental Observation Network;renukaroo@gmail.com;P.O. Box 47 Prince Albert 6930 ZA;GDPR ca314889-4f17-4801-bd8e-c50c783c04ac;South African Environmental Observation Network;Wolwekraal Conservation and Research Organisation;Sue Milton-Dean;South African Environmental Observation Network;renukaroo@gmail.com;P.O. Box 47 Prince Albert 6930 ZA;GDPR ca314889-4f17-4801-bd8e-c50c783c04ac;South African Environmental Observation Network;site;emf2iso_pointer_record;ecosystem parameter;ecosystem structure;above ground net primary production;Terrestrial;continuousDataCollection;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;2008-06-01;English;environment;22.030000000000;22.030000000000;-33.190000000000;-33.190000000000;2007-01-01;https://deims.org/356fac88-0041-4833-8273-b31789bc3763;http://www.wcro.co.za;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='356fac88-0041-4833-8273-b31789bc3763'&outputFormat=SHAPE-ZIP;WFS GetFeature request for downloading the data set in SHP format;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='356fac88-0041-4833-8273-b31789bc3763'&outputFormat=application%2Fgml%2Bxml%3B+version%3D3.2;WFS GetFeature request for downloading the data set in GML 3.2 format;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='356fac88-0041-4833-8273-b31789bc3763'&outputFormat=application%2Fjson;WFS GetFeature request for downloading the data set in GeoJSON format;https://deims.org/node/219;South Africa (SAEON);COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;publication;This data set is conformant with the INSPIRE Implementing Rules for the interoperability of spatial data sets and services;false;Dataset has been created by data transformation from the original record collected by the site managers using DEIMS site metadata editing form.",
-    "group": "deims",
-    "groups": [
-        {
-            "name": "deims"
-        }
-    ],
-    "name": "0b092590-0aa6-5bd7-84b3-436223a677e0",
-    "notes": [
-        "The field site comprises 123 ha of natural Karoo shrubland. The Dorpsrivier passes through the nature reserve. Habitats include exposed Ecca mudstone plains, a north-facing ridge, pockets of aolian sand, and quatzite pebble bed conglomerate along the levees of the Dorpsrivier. The field site has been fenced to exclude domestic livestock since the 1970s."
-    ],
-    "oai_identifier": [
-        "0b092590-0aa6-5bd7-84b3-436223a677e0"
-    ],
-    "oai_set": "full",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[22.030000000000,-33.190000000000],[22.030000000000,-33.190000000000],[22.030000000000,-33.190000000000],[22.030000000000,-33.190000000000],[22.030000000000,-33.190000000000]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "site"
-        },
-        {
-            "name": "emfiso_pointer_record"
-        },
-        {
-            "name": "ecosystem parameter"
-        },
-        {
-            "name": "ecosystem structure"
-        },
-        {
-            "name": "ground net primary production"
-        },
-        {
-            "name": "Terrestrial"
-        },
-        {
-            "name": "Environmental monitoring facilities"
-        }
-    ],
-    "title": [
-        "Wolwekraal Nature Reserve"
-    ],
-    "url": "https://deims.org/node/219"
-}
\ No newline at end of file
diff --git a/oaitestdata/deims-iso19139/full_1/json/0b0ff12a-b5d6-510a-abf3-b3c6f02cd2d4.json b/oaitestdata/deims-iso19139/full_1/json/0b0ff12a-b5d6-510a-abf3-b3c6f02cd2d4.json
deleted file mode 100644
index 89573f78..00000000
--- a/oaitestdata/deims-iso19139/full_1/json/0b0ff12a-b5d6-510a-abf3-b3c6f02cd2d4.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "agrita.briede@lu.lv"
-    ],
-    "Contributor": "DEIMS-SDR | Site and Dataset registry deims.org",
-    "DOI": "http://dx.doi.org/10.23728/b2share.4bb6bc9e5f894d8ea97912ab0639e5ca",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "https://deims.org/pycsw/catalogue/csw?verb=GetRecord&metadataPrefix=iso19139&identifier=0b0ff12a-b5d6-510a-abf3-b3c6f02cd2d4",
-    "PublicationTimestamp": "2018-09-24T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "LTER Europe"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Formal acknowledgement of the dataset providers"
-    ],
-    "SpatialCoverage": "(57N-57N,24E-24E)",
-    "author": [
-        "Agrita Briede"
-    ],
-    "fulltext": "84ca47b8-2aeb-4b60-9ffd-8936b9a46796;English;utf8;dataset;Agrita Briede;LTER Europe;agrita.briede@lu.lv;pointOfContact;2018-09-24;ISO19115;2003/Cor.1:2006;EPSG:4326;http://www.opengis.net/def/crs/EPSG/0/4326;http://www.opengis.net/def/crs/EPSG/0/4258;Precipitation data Riga Hydro Power Station Reservoir on the Daugava River 1976-2015;2018-09-24;publication;urn:ltereurope:inspire::11011:27629;Reservoir of Riga Hydropower Station on the River Daugava - Latvia;Institute of Biology, University of Latvia;documentDigital;Precipitation data for aquatic LTER site Riga Hydro Power Station Reservoir on the Daugava River 1976-2015;completed;Agrita Briede;LTER Europe;agrita.briede@lu.lv;pointOfContact;continual;Representative area of sampling: single point Sampling frequency - sampling time span: daily Sampling frequency - minimum sampling unit: daily;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;2008-06-01;publication;Bulk precipitation;climate change;Latvia;river;eLTER VA;LTER Controlled Vocabulary;Formal acknowledgement of the dataset providers;The principal: Administration has granted the access and use permission: Free for access and use upon request;The principal: Research has granted the access and use permission: Free for access and use upon request;The principal: Public has granted the access and use permission: Free for access and use upon request;eng;environment;Reservoir of Riga Hydropower station (Riga Hydroelectric Power Plant). The Riga Hydroelectric Power Plant was put into operation in 1974. In order to build Riga HES, a dam was constructed across the Daugava River through the middle of Doles Sala, half of which has since been flooded to make room for Riga Reservoir. Along with Doles Sala, there have been several other smaller islands drowned in order to fill the reservoir. The dam was built in the late 1970s.;24.410247802734;24.266052246094;56.821350720626;56.863413067939;16.00;18;urn:ogc:def:crs:EPSG;MSL height;Not specific to any location or epoch.;Hydrography.;Representative area of sampling: single point;ground condition;1976-01-01;2015-12-31;http://doi.org/10.23728/b2share.4bb6bc9e5f894d8ea97912ab0639e5ca;WWW:LINK-1.0-http--link;DOI;UKST;dataset;Conformity_001;INSPIRE;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;publication;See the referenced specification;Method description: precipitation gauge, since 2002 Milos-500 weather station. Method URL: https://data.lter-europe.net/deims/site/32370e5d-9da5-4f8c-9198-875f61b9c695. Instrumentation: Tretyakov non-recording precipitation gauge, since 2002 Milos-500 weather station from Vaisala.;Metadata Access Constraints: none Metadata Use Constraints: none;annually",
-    "group": "deims",
-    "groups": [
-        {
-            "name": "deims"
-        }
-    ],
-    "name": "0b0ff12a-b5d6-510a-abf3-b3c6f02cd2d4",
-    "notes": [
-        "Precipitation data for aquatic LTER site Riga Hydro Power Station Reservoir on the Daugava River 1976-2015"
-    ],
-    "oai_identifier": [
-        "0b0ff12a-b5d6-510a-abf3-b3c6f02cd2d4"
-    ],
-    "oai_set": "full",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[24.410247802734,56.821350720626],[24.410247802734,56.863413067939],[24.266052246094,56.863413067939],[24.266052246094,56.821350720626],[24.410247802734,56.821350720626]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Bulk precipitation"
-        },
-        {
-            "name": "climate change"
-        },
-        {
-            "name": "Latvia"
-        },
-        {
-            "name": "river"
-        },
-        {
-            "name": "eLTER VA"
-        }
-    ],
-    "title": [
-        "Precipitation data Riga Hydro Power Station Reservoir on the Daugava River 1976-2015"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/deims-iso19139/full_1/json/0b428279-d320-539e-b1fd-b411ea4ff2e8.json b/oaitestdata/deims-iso19139/full_1/json/0b428279-d320-539e-b1fd-b411ea4ff2e8.json
deleted file mode 100644
index 6f2f65a7..00000000
--- a/oaitestdata/deims-iso19139/full_1/json/0b428279-d320-539e-b1fd-b411ea4ff2e8.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contributor": "DEIMS-SDR | Site and Dataset registry deims.org",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Format": [
-        "Data product"
-    ],
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "https://deims.org/pycsw/catalogue/csw?verb=GetRecord&metadataPrefix=iso19139&identifier=0b428279-d320-539e-b1fd-b411ea4ff2e8",
-    "ResourceType": [
-        "series"
-    ],
-    "fulltext": "ca3a98c7-82ac-43a5-b72d-b45ce2817bec;English;utf8;series;Data product;2018-09-24;Kalkalpen National Park (Austria) - Water;https://data.lter-europe.net/deims/activity/ca3a98c7-82ac-43a5-b72d-b45ce2817bec;Spatial layer of running water ;The original metadata record was created using DEIMS-SDR, the Dynamic Ecological Information Management System - Site and dataset registry;single measurement;data product;product2iso_pointer_record;Running water (River and streams);Open data;Digital data;Ecopotential project;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;2008-06-01;full area coverage;English;environment;2016-09-26;https://data.lter-europe.net/deims/activity/ca3a98c7-82ac-43a5-b72d-b45ce2817bec;Data product is based on requirements defined by research projects (e.g. EcoPotential) as well as target stakeholder groups (e.g. LTER) in order to allow a summarised description of a series of data.",
-    "group": "deims",
-    "groups": [
-        {
-            "name": "deims"
-        }
-    ],
-    "name": "0b428279-d320-539e-b1fd-b411ea4ff2e8",
-    "notes": [
-        "Spatial layer of running water "
-    ],
-    "oai_identifier": [
-        "0b428279-d320-539e-b1fd-b411ea4ff2e8"
-    ],
-    "oai_set": "full",
-    "state": "active",
-    "tags": [
-        {
-            "name": "data product"
-        },
-        {
-            "name": "productiso_pointer_record"
-        },
-        {
-            "name": "Running water River streams"
-        },
-        {
-            "name": "Open data"
-        },
-        {
-            "name": "Digital data"
-        },
-        {
-            "name": "Ecopotential project"
-        },
-        {
-            "name": "Environmental monitoring facilities"
-        }
-    ],
-    "title": [
-        "Kalkalpen National Park (Austria) - Water"
-    ],
-    "url": "https://data.lter-europe.net/deims/activity/ca3a98c7-82ac-43a5-b72d-b45ce2817bec"
-}
\ No newline at end of file
diff --git a/oaitestdata/deims-iso19139/full_1/json/0b7b0cc7-2639-5c71-b22c-2cb9c77e4ebf.json b/oaitestdata/deims-iso19139/full_1/json/0b7b0cc7-2639-5c71-b22c-2cb9c77e4ebf.json
deleted file mode 100644
index 83704ec8..00000000
--- a/oaitestdata/deims-iso19139/full_1/json/0b7b0cc7-2639-5c71-b22c-2cb9c77e4ebf.json
+++ /dev/null
@@ -1,89 +0,0 @@
-{
-    "Contact": [
-        "patrick.schleppi@wsl.ch"
-    ],
-    "Contributor": "DEIMS-SDR | Site and Dataset registry deims.org",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Format": [
-        "Research site"
-    ],
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "https://deims.org/pycsw/catalogue/csw?verb=GetRecord&metadataPrefix=iso19139&identifier=0b7b0cc7-2639-5c71-b22c-2cb9c77e4ebf",
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "SpatialCoverage": "(47N-47N,9 E-9 E)",
-    "author": [
-        "Patrick Schleppi"
-    ],
-    "fulltext": "a8b05bd1-2fb0-422f-8b99-4e18f180395e;English;utf8;dataset;Research site;Patrick Schleppi;Swiss Federal Research Institute WSL;patrick.schleppi@wsl.ch;Swiss Federal Research Institute WSL Birmensdorf 8903 CH;Patrick Schleppi;Swiss Federal Research Institute WSL;patrick.schleppi@wsl.ch;Swiss Federal Research Institute WSL Birmensdorf 8903 CH;2018-09-24;http://www.opengis.net/def/crs/EPSG/0/4326;Alptal-Nitrogen-addition;https://deims.org/site/a8b05bd1-2fb0-422f-8b99-4e18f180395e;Paired-catchment, long-term nitrogen-addition experiment in a subalpine Picea abies forest;The original metadata record was created using DEIMS-SDR, the Dynamic Ecological Information Management System - Site and dataset registry;Patrick Schleppi;Swiss Federal Research Institute WSL;patrick.schleppi@wsl.ch;Swiss Federal Research Institute WSL Birmensdorf 8903 CH;Patrick Schleppi;Swiss Federal Research Institute WSL;patrick.schleppi@wsl.ch;Swiss Federal Research Institute WSL Birmensdorf 8903 CH;site;emf2iso_pointer_record;atmospheric parameter;air temperature;air humidity;precipitation intensity;snow depth;snow water equivalence;wind direction;wind speed;wind speed (mean and gust);biological parameter;plant height;root density;tree height;tree age;tree diameter;tree distribution;canopy cover rate;ecosystem parameter;above ground net primary production;crop growth rate;ground water level;leaf area;leaf area index;nitrogen content;ammonium nitrate concentration;plant nitrogen concentration;dissolved nutrient;inorganic nutrient content;leaf nutrient;soil nutrient;percent carbon;percent organic carbon;plant carbon concentration;community composition;diversity index;floristic diversity;change in population size over time;vegetation layer composition;species composition;plant species composition;species abundance;plant cover;bryophytes presence;species presence;species turnover;tree diameter at breast height;total organic carbon;soil parameter;soil acidity;soil alkalinity;base saturation;bulk density;soil bulk density;carbon-to-nitrogen ratio;cation exchange capacity;cation exchange capacity;inorganic nitrogen content;redox potential of water;soil gas flux;perched water table depth;soil nitrate leaching;soil PH;soil temperature;soil respiration;soil solution concentration;dissolved organic carbon in soil;dissolved organic nitrogen in soil;soil solution concentration;soil texture;thickness of soil horizon;total organic carbon in soil;water parameter;conductivity;dissolved organic carbon in water;runoff;water quality;suspended solids;water table;perched water table;water temperature;Terrestrial;continuousDataCollection;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;2008-06-01;English;environment;8.71;8.72;47.04;47.05;1994-01-01;https://deims.org/a8b05bd1-2fb0-422f-8b99-4e18f180395e;http://www.wsl.ch/fe/boden/projekte/alptal/index_EN;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='a8b05bd1-2fb0-422f-8b99-4e18f180395e'&outputFormat=SHAPE-ZIP;WFS GetFeature request for downloading the data set in SHP format;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='a8b05bd1-2fb0-422f-8b99-4e18f180395e'&outputFormat=application%2Fgml%2Bxml%3B+version%3D3.2;WFS GetFeature request for downloading the data set in GML 3.2 format;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='a8b05bd1-2fb0-422f-8b99-4e18f180395e'&outputFormat=application%2Fjson;WFS GetFeature request for downloading the data set in GeoJSON format;https://data.lter-europe.net/pycsw?service=CSW&version=3.0.0&request=GetRecordById&ElementSetName=full&outputSchema=http://www.isotc211.org/2005/gmd&outputFormat=application/json&id=9f4625b8-b228-11e2-a655-005056ab003f;HTTP;Catalogue Service for the Web (CSW);https://deims.org/node/248;Switzerland (LTER-Switzerland);COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;publication;This data set is conformant with the INSPIRE Implementing Rules for the interoperability of spatial data sets and services;false;Dataset has been created by data transformation from the original record collected by the site managers using DEIMS site metadata editing form.",
-    "group": "deims",
-    "groups": [
-        {
-            "name": "deims"
-        }
-    ],
-    "name": "0b7b0cc7-2639-5c71-b22c-2cb9c77e4ebf",
-    "notes": [
-        "Paired-catchment, long-term nitrogen-addition experiment in a subalpine Picea abies forest"
-    ],
-    "oai_identifier": [
-        "0b7b0cc7-2639-5c71-b22c-2cb9c77e4ebf"
-    ],
-    "oai_set": "full",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[8.71,47.04],[8.71,47.05],[8.72,47.05],[8.72,47.04],[8.71,47.04]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "site"
-        },
-        {
-            "name": "emfiso_pointer_record"
-        },
-        {
-            "name": "atmospheric parameter"
-        },
-        {
-            "name": "air temperature"
-        },
-        {
-            "name": "air humidity"
-        },
-        {
-            "name": "precipitation intensity"
-        },
-        {
-            "name": "snow depth"
-        },
-        {
-            "name": "snow water equivalence"
-        },
-        {
-            "name": "wind direction"
-        },
-        {
-            "name": "wind speed"
-        },
-        {
-            "name": "wind speed mean gust"
-        },
-        {
-            "name": "biological parameter"
-        }
-    ],
-    "title": [
-        "Alptal-Nitrogen-addition"
-    ],
-    "url": "https://deims.org/node/248"
-}
\ No newline at end of file
diff --git a/oaitestdata/deims-iso19139/full_1/json/0ba051eb-9512-57f1-90b8-260ffb097140.json b/oaitestdata/deims-iso19139/full_1/json/0ba051eb-9512-57f1-90b8-260ffb097140.json
deleted file mode 100644
index 3e3f4810..00000000
--- a/oaitestdata/deims-iso19139/full_1/json/0ba051eb-9512-57f1-90b8-260ffb097140.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "alexander.harpke@ufz.de"
-    ],
-    "Contributor": "DEIMS-SDR | Site and Dataset registry deims.org",
-    "DOI": "http://dx.doi.org/10.23728/b2share.100bc12953984cd5b8b24d58fc4c4c0c",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "https://deims.org/pycsw/catalogue/csw?verb=GetRecord&metadataPrefix=iso19139&identifier=0ba051eb-9512-57f1-90b8-260ffb097140",
-    "PID": "http://hdl.handle.net/11304/93a36e3f-a214-414f-8a42-e4a1a8b0c5e2",
-    "PublicationTimestamp": "2018-09-24T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "The data provider must be offered co-authorship for publications using this dataset at least within the metadata description",
-        "The opportunity to collaborate on the project using the dataset",
-        "The opportunity to review the results based on the dataset"
-    ],
-    "SpatialCoverage": "(52N,11E)",
-    "author": [
-        "Alexander Harpke"
-    ],
-    "fulltext": "0a53c139-06db-4741-b16d-fae947fceec5;English;utf8;dataset;Alexander Harpke;UFZ Helmholtz Centre for Environmental Research;Theodor-Lieser-Str. 4;Halle;06120;DE;alexander.harpke@ufz.de;pointOfContact;2018-09-24;ISO19115;2003/Cor.1:2006;EPSG:4326;http://www.opengis.net/def/crs/EPSG/0/4326;http://www.opengis.net/def/crs/EPSG/0/4258;Meteorological data Wanzleben, TERENO Harz / Central German Lowlands (2011-18);2018-09-24;publication;urn:ltereurope:inspire::11736:26910;TERENO - Wanzleben - Germany;Alexander Harpke;UFZ Helmholtz Centre for Environmental Research;Theodor-Lieser-Str. 4;Halle;06120;DE;alexander.harpke@ufz.de;pointOfContact;UFZ Helmholtz Centre for Environmental Research;documentDigital;Air temperature (60 cm above ground) and precipitation (100 cm above ground) from 2013-2018;completed;Alexander Harpke;UFZ Helmholtz Centre for Environmental Research;Theodor-Lieser-Str. 4;Halle;06120;DE;alexander.harpke@ufz.de;pointOfContact;UFZ Helmholtz Centre for Environmental Research;continual;Representative area of sampling: single point Sampling frequency - sampling time span: minutes Sampling frequency - minimum sampling unit: minutes;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;2008-06-01;publication;air temperature;precipitation;eLTER VA;LTER Controlled Vocabulary;The data provider must be offered co-authorship for publications using this dataset at least within the metadata description;The opportunity to collaborate on the project using the dataset;The opportunity to review the results based on the dataset;The principal: Administration has granted the access and use permission: Free access and use;The principal: Research has granted the access and use permission: Free for access;The principal: Public has granted the access and use permission: Free for access;eng;environment;Weather station;11.440340280533;11.440340280533;52.067130751543;52.067130751543;102.00;102;urn:ogc:def:crs:EPSG;MSL height;Not specific to any location or epoch.;Hydrography.;Representative area of sampling: single point;ground condition;2011-11-01;2018-03-19;http://doi.org/10.23728/b2share.100bc12953984cd5b8b24d58fc4c4c0c;WWW:LINK-1.0-http--link;DOI;http://hdl.handle.net/11304/93a36e3f-a214-414f-8a42-e4a1a8b0c5e2;WWW:LINK-1.0-http--link;B2Share Landing Page;dataset;Conformity_001;INSPIRE;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;publication;See the referenced specification;Method description: air temperature at 60 cm above ground, presipitation at 100 cm above groundSoil temperature: 2 cm depth; SKTS 200 probe Soil water content: 5,10,20,50 cm depth; ML2 Theta soil probe Matrix potential (soil water tension): 5,10,20,50 cm depth; pF Meter Sensor Soil temperature: 5,10,20,50 cm depth; pF Meter Sensor List of sensors of weather station Soil temperature: 5,10,20,50,100 cm; depth; BTPR Sensor Air temperature: 5,10,60,200 cm height; HC2-S3 AirClip 3000 Air humidity: 60,200 cm height; HC2-S3 AirClip 3000 Wind direction: 250 cm height; WMT50 Ultrasonic-Anemometer Wind speed: 250 cm height; WMT50 Ultrasonic-Anemometer Precipitation: 100 cm height; Thies-Precipitation sensor (Measurement principle according to \"Guide to Meteorological Instruments No 8\" (WMO)). Method URL: . Instrumentation:;Metadata Access Constraints: none Metadata Use Constraints: none;annually",
-    "group": "deims",
-    "groups": [
-        {
-            "name": "deims"
-        }
-    ],
-    "name": "0ba051eb-9512-57f1-90b8-260ffb097140",
-    "notes": [
-        "Air temperature (60 cm above ground) and precipitation (100 cm above ground) from 2013-2018"
-    ],
-    "oai_identifier": [
-        "0ba051eb-9512-57f1-90b8-260ffb097140"
-    ],
-    "oai_set": "full",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[11.440340280533,52.067130751543],[11.440340280533,52.067130751543],[11.440340280533,52.067130751543],[11.440340280533,52.067130751543],[11.440340280533,52.067130751543]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "air temperature"
-        },
-        {
-            "name": "precipitation"
-        },
-        {
-            "name": "eLTER VA"
-        }
-    ],
-    "title": [
-        "Meteorological data Wanzleben, TERENO Harz / Central German Lowlands (2011-18)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/deims-iso19139/full_1/json/0ba7000e-14d2-58d8-8c94-9b28b19a424f.json b/oaitestdata/deims-iso19139/full_1/json/0ba7000e-14d2-58d8-8c94-9b28b19a424f.json
deleted file mode 100644
index 9850f131..00000000
--- a/oaitestdata/deims-iso19139/full_1/json/0ba7000e-14d2-58d8-8c94-9b28b19a424f.json
+++ /dev/null
@@ -1,89 +0,0 @@
-{
-    "Contributor": "DEIMS-SDR | Site and Dataset registry deims.org",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "https://deims.org/pycsw/catalogue/csw?verb=GetRecord&metadataPrefix=iso19139&identifier=0ba7000e-14d2-58d8-8c94-9b28b19a424f",
-    "PublicationTimestamp": "2018-09-24T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "The data provider must be offered co-authorship for publications using this dataset at least within the metadata description",
-        "Formal acknowledgement of the dataset providers",
-        "The opportunity to review the results based on the dataset",
-        "Reprints of articles using the dataset must be provided to the data provider",
-        "The dataset provider is given a complete list of all products that make use of the dataset",
-        "Mutual agreement on reciprocal sharing of data"
-    ],
-    "SpatialCoverage": "(47N-47N,11E-11E)",
-    "fulltext": "d72d2d32-f7f4-11e4-870c-005056ab003f;English;utf8;dataset;2018-09-24;ISO19115;2003/Cor.1:2006;EPSG:4326;http://www.opengis.net/def/crs/EPSG/0/4326;http://www.opengis.net/def/crs/EPSG/0/4258;Obergurgl, AT, vegetation skislope, 2008;2018-09-24;publication;urn:ltereurope:inspire::9050:17670;Obergurgl - Austria;Brigitta Erschbamer;LTER Europe;brigitta.erschbamer@uibk.ac.at;pointOfContact;documentDigital;Vegetation data of the Festkogel-skislope in Obergurgl compared to outside of slope-vegetation is presented. Within the project &quot;Footprints; integrative research in the Oetztal valley&quot; (2005-2009), the development of the village Obergurgl and Vent was studied. This was tied on the project Man-and-Biosphere, the model-study in the 70ies and 80ies. The project was structured in three phases. Within the last phase, the vegetation of ski slopes in Obergurgl was recorded to compare the skislope-vegetation with the surrounding, natural vegetation. Therefore, three transects were established along an altitudinal gradient from skislope-bottom (1930 m a.s.l.) to skislope-top (2893 m a.s.l.). Locality: Festkogel skislope in Obergurgl, Tyrol, Austria Vegetation-records were made from 07.08.2008 to 26.08.2008 In sum, 118 vegetation records were made (one record=one plot). Those records are distributed in 40 parallel record-points.;completed;Nikolaus Schallhart;University of Innsbruck, Alpine Research Centre Obergurgl;Sternwartestra\u00dfe 15;Innsbruck;6020;AT;klaus.schallhart@uibk.ac.at;https://www.uibk.ac.at/afo/team/;pointOfContact;continual;Representative area of sampling: plot scale Sampling frequency - sampling time span: seasonally Sampling frequency - minimum sampling unit: seasonally;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;2008-06-01;publication;Achillea millefolium;Achillea moschata;Agrostis agrostiflora;Agrostis capillaris;Agrostis rupestris;Ajuga pyramidalis;Alchemilla fissa;Alchemilla nitida;Alchemilla vulgaris agg.;Alectoria ochroleuca;Alnus alnobetula;Androsace obtusifolia;Antennaria dioica;Anthoxanthum alpinum;Anthoxanthum odoratum;Arabis alpina;Arenaria biflora;Avenella flexuosa;Avenula versicolor;Bartsia alpina;Botrychium lunaria;Calamagrostis villosa;Calluna vulgaris;Campanula barbata;Campanula cochleariifolia;Campanula scheuchzeri;Cardamine alpina;Cardamine resedifolia;Carex brunnescens ssp. brunnescens;Carex curvula;Carex nigra;Carex pilulifera;Carex sempervirens;Carum carvi;Cerastium cerastoides;Cerastium fontanum;Cerastium pedunculatum;Cerastium uniflorum;Cetraria islandica;Cetraria nivalis;Chaerophyllum hirsutum;Chenopodium bonus-henricus;Cirsium spinosissimum;Cladonia arbuscula;Coeloglossum viride;Comastoma tenellum;Crepis aurea;Dactylis glomerata;Deschampsia cespitosa;Diphasiastrum alpinum;Doronicum clusii;Dryopteris expansa;Elymus repens;Empetrum hermaphroditum;Epilobium angustifolium;Erigeron uniflorus;Euphrasia minima agg.;Euphrasia officinalis ssp. rostkoviana;Festuca halleri;Festuca pulchella;Festuca pumila;Festuca rubra agg.;Festuca varia;Fragaria vesca;Galium anisophyllon;Galium mollugo agg.;Gentiana acaulis;Gentiana orbicularis;Gentiana punctata;Gentianella anisodonta;Geranium sylvaticum;Geum montanum;Geum reptans;Gnaphalium supinum;Gymnocarpium dryopteris;Helianthemum ovatum;Hieracium alpinum;Hieracium hoppeanum;Hieracium lachenalii;Hieracium lactucella;Hieracium pilosum;Homogyne alpina;Hypochaeris uniflora;Juncus filiformis;Juncus jacquinii;Juniperus communis ssp. nana;Kobresia myosuroides;Larix decidua;Leontodon autumnalis;Leontodon helveticus;Leontodon hispidus;Leucanthemopsis alpina;Leucanthemum vulgare agg.;Ligusticum mutellina;Linaria alpina;Loiseleuria procumbens;Lolium perenne;Lotus corniculatus;Luzula alpinopilosa;Luzula lutea;Luzula luzuloides;Luzula spicata;Luzula sylvatica;Melampyrum sylvaticum;Minuartia gerardii;Moss sp.;Myosotis alpestris;Nardus stricta;Nostoc sp.;Oreochloa disticha;Oxyria digyna;Parnassia palustris;Pedicularis kerneri;Pedicularis tuberosa;Persicaria vivipara;Petasites paradoxus;Peucedanum ostruthium;Phleum commutatum;Phleum hirsutum;Phleum pratense;Phleum rhaeticum;Phyteuma betonicifolium;Phyteuma hemisphaericum;Phyteuma orbiculare;Picea abies;Pinus cembra;Plantago major;Poa alpina;Poa laxa;Poa molinerii;Poa sp.;Polytrichum sp.;Potentilla aurea;Potentilla frigida;Potentilla pusilla;Primula glutinosa;Pseudorchis albida;Pulmonaria sp.;Pulsatilla vernalis;Pyrola minor;Ranunculus acris;Ranunculus glacialis;Ranunculus montanus;Rhododendron ferrugineum;Rhododendron x intermedium;Rubus sp.;Ruderalia;Rumex acetosa;Rumex acetosella s.lat.;Rumex alpestris;Sagina saginoides;Salix hastata;Salix helvetica;Salix herbacea;Salix retusa;Salix serpillifolia;Salix sp.;Salix waldsteiniana;Saxifraga bryoides;Saxifraga exarata;Saxifraga paniculata;Sedum acre;Sedum alpestre;Sedum atratum;Selaginella selaginoides;Sempervivum montanum;Senecio carniolicus;Sesleria albicans;Sibbaldia procumbens;Silene acaulis s.lat.;Silene nutans ssp. nutans;Silene rupestris;Silene vulgaris ssp. vulgaris;Soldanella pusilla;Solidago virgaurea;Trifolium pratense ssp nivale;Stellaria graminea;Stereocaulon alpinum;Taraxacum alpestre s.str.;Taraxacum sect.;Thamnolia vermicularis;Thesium alpinum;Thymus praecox ssp. polytrichus;Thymus praecox ssp. praecox;Trifolium badium;Trifolium hybridum;Trifolium montanum;Trifolium pallescens;Trifolium pratense;Trifolium repens;Trollius europaeus;Urtica dioica;Vaccinium gaultherioides;Vaccinium myrtillus;Vaccinium vitis-idaea;Veronica alpina;Veronica bellidioides;Veronica serpyllifolia ssp. humifusa;Vicia cracca;Viola arvensis;Viola biflora;Viola sp.;Biological Classification;Constructed, industrial and other artificial habitats;biodiversity;alpine;Line transects;hillslopes;LTER Controlled Vocabulary;The data provider must be offered co-authorship for publications using this dataset at least within the metadata description;Formal acknowledgement of the dataset providers;The opportunity to review the results based on the dataset;Reprints of articles using the dataset must be provided to the data provider;The dataset provider is given a complete list of all products that make use of the dataset;Mutual agreement on reciprocal sharing of data;The principal: Research has granted the access and use permission: Free for access and use upon request;The principal: Public has granted the access and use permission: Free for access and use upon request;eng;environment;11.048430000000;11.029380000000;46.830080000000;46.874790000000;1930.00;2823;urn:ogc:def:crs:EPSG;MSL height;Not specific to any location or epoch.;Hydrography.;Representative area of sampling: plot scale;ground condition;2008-08-06;2008-08-25;http://www.uibk.ac.at/afo/publikationen/projektberichte.html;WWW:LINK-1.0-http--link;Projektberichte;dataset;Conformity_001;INSPIRE;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;publication;See the referenced specification;Method description: Vegetation-records were made from 07.08.2008 to 26.08.2008 In sum, 118 vegetation records were made (one record=one plot). Those records are distributed in 40 parallel record-points. Plot size was taken according to Braun-Blanquet (1964). Also standheight and ecological indicator-values were recorded. Indicator values were evaluated along coverage-values and given as mean value per plot. Indicator values were taken from University of Boku in Vienna (http://statedv.boku.ac.at/zeigerwerte/) and follow Ellenberg et al. (1992). vegetation coverage of species per plot (relev\u00e9-no) according to the scale of Braun-Blanquet (1964) and Wilmanns(1993) r rare, 1 individual within the plot, very small coverage ratio 50 individuals) with small coverage ratio 5-15% 2b individual-numbers optional, coverage ratio > 15-25% 3 individual-numbers optional, coverage ratio > 25-50% 4 individual-numbers optional, coverage ratio > 50-75% 5 individual-numbers optional, coverage ratio > 75%. Method URL: . Instrumentation: metal frame with 1 m\u00b2;Metadata Access Constraints: none Metadata Use Constraints: none;annually",
-    "group": "deims",
-    "groups": [
-        {
-            "name": "deims"
-        }
-    ],
-    "name": "0ba7000e-14d2-58d8-8c94-9b28b19a424f",
-    "notes": [
-        "Vegetation data of the Festkogel-skislope in Obergurgl compared to outside of slope-vegetation is presented. Within the project &quot;Footprints; integrative research in the Oetztal valley&quot; (2005-2009), the development of the village Obergurgl and Vent was studied. This was tied on the project Man-and-Biosphere, the model-study in the 70ies and 80ies. The project was structured in three phases. Within the last phase, the vegetation of ski slopes in Obergurgl was recorded to compare the skislope-vegetation with the surrounding, natural vegetation. Therefore, three transects were established along an altitudinal gradient from skislope-bottom (1930 m a.s.l.) to skislope-top (2893 m a.s.l.). Locality: Festkogel skislope in Obergurgl, Tyrol, Austria Vegetation-records were made from 07.08.2008 to 26.08.2008 In sum, 118 vegetation records were made (one record=one plot). Those records are distributed in 40 parallel record-points."
-    ],
-    "oai_identifier": [
-        "0ba7000e-14d2-58d8-8c94-9b28b19a424f"
-    ],
-    "oai_set": "full",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[11.048430000000,46.830080000000],[11.048430000000,46.874790000000],[11.029380000000,46.874790000000],[11.029380000000,46.830080000000],[11.048430000000,46.830080000000]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Achillea millefolium"
-        },
-        {
-            "name": "Achillea moschata"
-        },
-        {
-            "name": "Agrostis agrostiflora"
-        },
-        {
-            "name": "Agrostis capillaris"
-        },
-        {
-            "name": "Agrostis rupestris"
-        },
-        {
-            "name": "Ajuga pyramidalis"
-        },
-        {
-            "name": "Alchemilla fissa"
-        },
-        {
-            "name": "Alchemilla nitida"
-        },
-        {
-            "name": "Alchemilla vulgaris agg."
-        },
-        {
-            "name": "Alectoria ochroleuca"
-        },
-        {
-            "name": "Alnus alnobetula"
-        },
-        {
-            "name": "Androsace obtusifolia"
-        }
-    ],
-    "title": [
-        "Obergurgl, AT, vegetation skislope, 2008"
-    ],
-    "url": "http://www.uibk.ac.at/afo/publikationen/projektberichte.html"
-}
\ No newline at end of file
diff --git a/oaitestdata/deims-iso19139/full_1/json/0bb39e44-39c5-5c93-a5fb-9053298ae648.json b/oaitestdata/deims-iso19139/full_1/json/0bb39e44-39c5-5c93-a5fb-9053298ae648.json
deleted file mode 100644
index 21925473..00000000
--- a/oaitestdata/deims-iso19139/full_1/json/0bb39e44-39c5-5c93-a5fb-9053298ae648.json
+++ /dev/null
@@ -1,89 +0,0 @@
-{
-    "Contact": [
-        "lars.lundin@slu.se"
-    ],
-    "Contributor": "DEIMS-SDR | Site and Dataset registry deims.org",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Format": [
-        "Research site"
-    ],
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "https://deims.org/pycsw/catalogue/csw?verb=GetRecord&metadataPrefix=iso19139&identifier=0bb39e44-39c5-5c93-a5fb-9053298ae648",
-    "Publisher": [
-        "LTER Europe"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "SpatialCoverage": "(60N,15E)",
-    "author": [
-        "Lars Lundin"
-    ],
-    "fulltext": "3d5bce60-7908-4985-8484-3b06d9ba2ff8;English;utf8;dataset;Research site;Lars Lundin;LTER Europe;lars.lundin@slu.se;Lars Lundin;LTER Europe;lars.lundin@slu.se;2018-09-24;http://www.opengis.net/def/crs/EPSG/0/4326;Masby;https://deims.org/site/3d5bce60-7908-4985-8484-3b06d9ba2ff8;Coniferous forest.;The original metadata record was created using DEIMS-SDR, the Dynamic Ecological Information Management System - Site and dataset registry;Lars Lundin;LTER Europe;lars.lundin@slu.se;Lars Lundin;LTER Europe;lars.lundin@slu.se;site;emf2iso_pointer_record;ecosystem parameter;soil nutrient;soil parameter;base saturation;bulk density;carbon-to-nitrogen ratio;cation exchange capacity;cation exchange capacity;percent carbon;percent organic carbon;soil gravimetric water content;soil profile water content;soil volumetric water content;soil water content;soil water content in the root zone;soil water holding capacity;soil water retention;soil water retention curve;soil moisture field capacity;soil moisture content;soil PH;soil texture;soil wilting point;thickness of soil horizon;total organic carbon in soil;water parameter;water alkalinity;conductivity;saturated hydraulic conductivity;runoff;total organic carbon;water quality;water table;groundwater permeability;water velocity;water volume;Terrestrial;continuousDataCollection;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;2008-06-01;English;environment;15.250000000000;15.250000000000;59.916700000000;59.916700000000;1969-01-01;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='3d5bce60-7908-4985-8484-3b06d9ba2ff8'&outputFormat=SHAPE-ZIP;WFS GetFeature request for downloading the data set in SHP format;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='3d5bce60-7908-4985-8484-3b06d9ba2ff8'&outputFormat=application%2Fgml%2Bxml%3B+version%3D3.2;WFS GetFeature request for downloading the data set in GML 3.2 format;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='3d5bce60-7908-4985-8484-3b06d9ba2ff8'&outputFormat=application%2Fjson;WFS GetFeature request for downloading the data set in GeoJSON format;https://deims.org/node/239;Sweden (LTER Sweden);COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;publication;This data set is conformant with the INSPIRE Implementing Rules for the interoperability of spatial data sets and services;false;Dataset has been created by data transformation from the original record collected by the site managers using DEIMS site metadata editing form.",
-    "group": "deims",
-    "groups": [
-        {
-            "name": "deims"
-        }
-    ],
-    "name": "0bb39e44-39c5-5c93-a5fb-9053298ae648",
-    "notes": [
-        "Coniferous forest."
-    ],
-    "oai_identifier": [
-        "0bb39e44-39c5-5c93-a5fb-9053298ae648"
-    ],
-    "oai_set": "full",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[15.250000000000,59.916700000000],[15.250000000000,59.916700000000],[15.250000000000,59.916700000000],[15.250000000000,59.916700000000],[15.250000000000,59.916700000000]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "site"
-        },
-        {
-            "name": "emfiso_pointer_record"
-        },
-        {
-            "name": "ecosystem parameter"
-        },
-        {
-            "name": "soil nutrient"
-        },
-        {
-            "name": "soil parameter"
-        },
-        {
-            "name": "base saturation"
-        },
-        {
-            "name": "bulk density"
-        },
-        {
-            "name": "carbon-to-nitrogen ratio"
-        },
-        {
-            "name": "cation exchange capacity"
-        },
-        {
-            "name": "cation exchange capacity"
-        },
-        {
-            "name": "percent carbon"
-        },
-        {
-            "name": "percent organic carbon"
-        }
-    ],
-    "title": [
-        "Masby"
-    ],
-    "url": "https://deims.org/node/239"
-}
\ No newline at end of file
diff --git a/oaitestdata/deims-iso19139/full_1/json/0bb68222-2a3e-5666-9c40-558320a93745.json b/oaitestdata/deims-iso19139/full_1/json/0bb68222-2a3e-5666-9c40-558320a93745.json
deleted file mode 100644
index f3a1e393..00000000
--- a/oaitestdata/deims-iso19139/full_1/json/0bb68222-2a3e-5666-9c40-558320a93745.json
+++ /dev/null
@@ -1,89 +0,0 @@
-{
-    "Contact": [
-        "robert.jandl@bfw.gv.at"
-    ],
-    "Contributor": "DEIMS-SDR | Site and Dataset registry deims.org",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Format": [
-        "Research site"
-    ],
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "https://deims.org/pycsw/catalogue/csw?verb=GetRecord&metadataPrefix=iso19139&identifier=0bb68222-2a3e-5666-9c40-558320a93745",
-    "Publisher": [
-        "LTER Europe"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "SpatialCoverage": "(48N,12E)",
-    "author": [
-        "Robert Jandl"
-    ],
-    "fulltext": "d2e91d98-4970-4d71-8d76-d8164542b694;English;utf8;dataset;Research site;Robert Jandl;LTER Europe;robert.jandl@bfw.gv.at;Robert Jandl;LTER Europe;robert.jandl@bfw.gv.at;2018-09-24;http://www.opengis.net/def/crs/EPSG/0/4326;Achenkirch-M\u00fchleggerk\u00f6pfl (ACH-Mue);https://deims.org/site/d2e91d98-4970-4d71-8d76-d8164542b694;Norway Spruce-Fir-Red Beech Forest on Limestone The experimental site M\u00fchleggerk\u00f6pfl is located on the northern edge of the Alps and receives air pollutants that are transported over long distances, by predominant westerly winds; local emissions from rural settlements are low. The LTER site has an area of 20 hectares. It is a privately owned mature montane forest rich in Norway spruce in the Northern Limestone Alps at 920 m a.s.l. on a north\u2013north-east facing slope of a mountain (47\u00b0 34\u2019 50\u201d N; 11\u00b0 38\u2019 21\u201d E). The site on an isolated calcareous outcrop in the valley of Achenbach represents a watershedsmall catchment. Routinely measured parameters over the years have included climate (air temperature, precipitation, and air humidity), soil temperature, soil water content, soil solution chemistry, nutrient content of Norway spruce needles, air quality, deposition of N, and surface runoff. The climate is cool and mesic with maximum precipitation in summer and a snow-free period from April/May to November/December. The mean annual air temperature and precipitation from on-site measurements are 6.8\u00b0C and 1580 mm, respectively. The annual variability of the precipitation is small. Moist conditions are also evident from the high relative air humidity.;The original metadata record was created using DEIMS-SDR, the Dynamic Ecological Information Management System - Site and dataset registry;Robert Jandl;LTER Europe;robert.jandl@bfw.gv.at;Robert Jandl;LTER Europe;robert.jandl@bfw.gv.at;site;emf2iso_pointer_record;ecosystem parameter;diversity index;species composition;plant species composition;nitrogen content;percent nitrogen;microbial diversity;percent carbon;percent organic carbon;inorganic nutrient content;leaf nutrient;soil nutrient;ecosystem structure;forest structure;canopy cover rate;disturbance pattern;below ground autotrophic respiration;biological parameter;plant height;root density;root growth rate;tree height;tree age;tree diameter;atmospheric parameter;air temperature;air humidity;air water vapour concentration;precipitation intensity;interception;soil parameter;soil acidity;base saturation;bulk density;soil bulk density;soil dry bulk density;carbon-to-nitrogen ratio;cation exchange capacity;cation exchange capacity;inorganic carbon content;inorganic nitrogen content;soil gas flux;Terrestrial;continuousDataCollection;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;2008-06-01;English;environment;11.639200000000;11.639200000000;47.580600000000;47.580600000000;1901-01-01;https://deims.org/d2e91d98-4970-4d71-8d76-d8164542b694;http://bfw.ac.at/rz/bfwcms.web?dok=4391;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='d2e91d98-4970-4d71-8d76-d8164542b694'&outputFormat=SHAPE-ZIP;WFS GetFeature request for downloading the data set in SHP format;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='d2e91d98-4970-4d71-8d76-d8164542b694'&outputFormat=application%2Fgml%2Bxml%3B+version%3D3.2;WFS GetFeature request for downloading the data set in GML 3.2 format;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='d2e91d98-4970-4d71-8d76-d8164542b694'&outputFormat=application%2Fjson;WFS GetFeature request for downloading the data set in GeoJSON format;https://data.lter-europe.net/pycsw?service=CSW&version=3.0.0&request=GetRecordById&ElementSetName=full&outputSchema=http://www.isotc211.org/2005/gmd&outputFormat=application/json&id=f253f6ea-cdfd-11e2-a655-005056ab003f;HTTP;Catalogue Service for the Web (CSW);https://deims.org/node/222;Austria (LTER-Austria);COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;publication;This data set is conformant with the INSPIRE Implementing Rules for the interoperability of spatial data sets and services;false;Dataset has been created by data transformation from the original record collected by the site managers using DEIMS site metadata editing form.",
-    "group": "deims",
-    "groups": [
-        {
-            "name": "deims"
-        }
-    ],
-    "name": "0bb68222-2a3e-5666-9c40-558320a93745",
-    "notes": [
-        "Norway Spruce-Fir-Red Beech Forest on Limestone The experimental site M\u00fchleggerk\u00f6pfl is located on the northern edge of the Alps and receives air pollutants that are transported over long distances, by predominant westerly winds; local emissions from rural settlements are low. The LTER site has an area of 20 hectares. It is a privately owned mature montane forest rich in Norway spruce in the Northern Limestone Alps at 920 m a.s.l. on a north\u2013north-east facing slope of a mountain (47\u00b0 34\u2019 50\u201d N; 11\u00b0 38\u2019 21\u201d E). The site on an isolated calcareous outcrop in the valley of Achenbach represents a watershedsmall catchment. Routinely measured parameters over the years have included climate (air temperature, precipitation, and air humidity), soil temperature, soil water content, soil solution chemistry, nutrient content of Norway spruce needles, air quality, deposition of N, and surface runoff. The climate is cool and mesic with maximum precipitation in summer and a snow-free period from April/May to November/December. The mean annual air temperature and precipitation from on-site measurements are 6.8\u00b0C and 1580 mm, respectively. The annual variability of the precipitation is small. Moist conditions are also evident from the high relative air humidity."
-    ],
-    "oai_identifier": [
-        "0bb68222-2a3e-5666-9c40-558320a93745"
-    ],
-    "oai_set": "full",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[11.639200000000,47.580600000000],[11.639200000000,47.580600000000],[11.639200000000,47.580600000000],[11.639200000000,47.580600000000],[11.639200000000,47.580600000000]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "site"
-        },
-        {
-            "name": "emfiso_pointer_record"
-        },
-        {
-            "name": "ecosystem parameter"
-        },
-        {
-            "name": "diversity index"
-        },
-        {
-            "name": "species composition"
-        },
-        {
-            "name": "plant species composition"
-        },
-        {
-            "name": "nitrogen content"
-        },
-        {
-            "name": "percent nitrogen"
-        },
-        {
-            "name": "microbial diversity"
-        },
-        {
-            "name": "percent carbon"
-        },
-        {
-            "name": "percent organic carbon"
-        },
-        {
-            "name": "inorganic nutrient content"
-        }
-    ],
-    "title": [
-        "Achenkirch-M\u00fchleggerk\u00f6pfl (ACH-Mue)"
-    ],
-    "url": "https://deims.org/node/222"
-}
\ No newline at end of file
diff --git a/oaitestdata/deims-iso19139/full_1/json/0bdb6453-e5de-5bef-82ff-507b1a1aab3b.json b/oaitestdata/deims-iso19139/full_1/json/0bdb6453-e5de-5bef-82ff-507b1a1aab3b.json
deleted file mode 100644
index 4219d891..00000000
--- a/oaitestdata/deims-iso19139/full_1/json/0bdb6453-e5de-5bef-82ff-507b1a1aab3b.json
+++ /dev/null
@@ -1,91 +0,0 @@
-{
-    "Contact": [
-        "antoine.rabatel@univ-grenoble-alpes.fr"
-    ],
-    "Contributor": "DEIMS-SDR | Site and Dataset registry deims.org",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Format": [
-        "Research site"
-    ],
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "https://deims.org/pycsw/catalogue/csw?verb=GetRecord&metadataPrefix=iso19139&identifier=0bdb6453-e5de-5bef-82ff-507b1a1aab3b",
-    "Publisher": [
-        "LTER Europe"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "SpatialCoverage": "(0 S,78W)",
-    "author": [
-        "GDPR 5e58bf7c-65cb-4d9f-897f-15511d650067",
-        "GDPR 4a1e0bbf-bc83-4aac-8a1b-92b3d6ff52cb",
-        "Antoine Rabatel"
-    ],
-    "fulltext": "a4a80312-9bfd-42fc-8101-4e222c1a90ca;English;utf8;dataset;Research site;GDPR 5e58bf7c-65cb-4d9f-897f-15511d650067;LTER Europe;GDPR 4a1e0bbf-bc83-4aac-8a1b-92b3d6ff52cb;LTER Europe;Antoine Rabatel;LTER Europe;antoine.rabatel@univ-grenoble-alpes.fr;2018-09-24;http://www.opengis.net/def/crs/EPSG/0/4326;Antizana glacier;https://deims.org/site/a4a80312-9bfd-42fc-8101-4e222c1a90ca;Antizana 15 alpha Glacier is one of the 17 tongues of the Antizana volcanoe in Ecuador, from 4820 to 5760 m a.s.l..;The original metadata record was created using DEIMS-SDR, the Dynamic Ecological Information Management System - Site and dataset registry;GDPR 5e58bf7c-65cb-4d9f-897f-15511d650067;LTER Europe;GDPR 4a1e0bbf-bc83-4aac-8a1b-92b3d6ff52cb;LTER Europe;Antoine Rabatel;LTER Europe;antoine.rabatel@univ-grenoble-alpes.fr;site;emf2iso_pointer_record;atmospheric parameter;air temperature;air humidity;precipitation intensity;snow depth;global radiation irradiance;incoming radiation intensity;long wave radiation;net far infrared radiation irradiance;solar radiation;net solar radiation irradiance;reflected radiation intensity;total radiation irradiance;wind direction;wind speed;landscape parameter;Terrestrial;continuousDataCollection;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;2008-06-01;English;environment;-78.140000000000;-78.140000000000;-0.480000000000;-0.480000000000;1994-01-01;https://deims.org/a4a80312-9bfd-42fc-8101-4e222c1a90ca;http://glacioclim.osug.fr;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='a4a80312-9bfd-42fc-8101-4e222c1a90ca'&outputFormat=SHAPE-ZIP;WFS GetFeature request for downloading the data set in SHP format;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='a4a80312-9bfd-42fc-8101-4e222c1a90ca'&outputFormat=application%2Fgml%2Bxml%3B+version%3D3.2;WFS GetFeature request for downloading the data set in GML 3.2 format;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='a4a80312-9bfd-42fc-8101-4e222c1a90ca'&outputFormat=application%2Fjson;WFS GetFeature request for downloading the data set in GeoJSON format;https://deims.org/node/250;France (LTER-France);COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;publication;This data set is conformant with the INSPIRE Implementing Rules for the interoperability of spatial data sets and services;false;Dataset has been created by data transformation from the original record collected by the site managers using DEIMS site metadata editing form.",
-    "group": "deims",
-    "groups": [
-        {
-            "name": "deims"
-        }
-    ],
-    "name": "0bdb6453-e5de-5bef-82ff-507b1a1aab3b",
-    "notes": [
-        "Antizana 15 alpha Glacier is one of the 17 tongues of the Antizana volcanoe in Ecuador, from 4820 to 5760 m a.s.l.."
-    ],
-    "oai_identifier": [
-        "0bdb6453-e5de-5bef-82ff-507b1a1aab3b"
-    ],
-    "oai_set": "full",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-78.140000000000,-0.480000000000],[-78.140000000000,-0.480000000000],[-78.140000000000,-0.480000000000],[-78.140000000000,-0.480000000000],[-78.140000000000,-0.480000000000]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "site"
-        },
-        {
-            "name": "emfiso_pointer_record"
-        },
-        {
-            "name": "atmospheric parameter"
-        },
-        {
-            "name": "air temperature"
-        },
-        {
-            "name": "air humidity"
-        },
-        {
-            "name": "precipitation intensity"
-        },
-        {
-            "name": "snow depth"
-        },
-        {
-            "name": "global radiation irradiance"
-        },
-        {
-            "name": "incoming radiation intensity"
-        },
-        {
-            "name": "long wave radiation"
-        },
-        {
-            "name": "net far infrared radiation irradiance"
-        },
-        {
-            "name": "solar radiation"
-        }
-    ],
-    "title": [
-        "Antizana glacier"
-    ],
-    "url": "https://deims.org/node/250"
-}
\ No newline at end of file
diff --git a/oaitestdata/deims-iso19139/full_1/json/0bf06f83-7717-5a1b-8aea-a7c91c2f15c3.json b/oaitestdata/deims-iso19139/full_1/json/0bf06f83-7717-5a1b-8aea-a7c91c2f15c3.json
deleted file mode 100644
index 6e18e1e4..00000000
--- a/oaitestdata/deims-iso19139/full_1/json/0bf06f83-7717-5a1b-8aea-a7c91c2f15c3.json
+++ /dev/null
@@ -1,92 +0,0 @@
-{
-    "Contact": [
-        "bradfb@environment-agency.gov.uk",
-        "arjs@ceh.ac.uk"
-    ],
-    "Contributor": "DEIMS-SDR | Site and Dataset registry deims.org",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Format": [
-        "Research site"
-    ],
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "https://deims.org/pycsw/catalogue/csw?verb=GetRecord&metadataPrefix=iso19139&identifier=0bf06f83-7717-5a1b-8aea-a7c91c2f15c3",
-    "Publisher": [
-        "Centre for Ecology & Hydrology",
-        "LTER Europe"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "SpatialCoverage": "(51N,4 W)",
-    "author": [
-        "Ben Bradford",
-        "Andrew Sier"
-    ],
-    "fulltext": "b8e9402a-10bc-4892-b03d-1e85fc925c99;English;utf8;dataset;Research site;Andrew Sier;Centre for Ecology & Hydrology;arjs@ceh.ac.uk;Centre for Ecology & Hydrology Lancaster Lancashire LA1 4AP GB;Centre for Ecology & Hydrology;Ben Bradford;LTER Europe;bradfb@environment-agency.gov.uk;Andrew Sier;Centre for Ecology & Hydrology;arjs@ceh.ac.uk;Centre for Ecology & Hydrology Lancaster Lancashire LA1 4AP GB;2018-09-24;http://www.opengis.net/def/crs/EPSG/0/4326;River Exe;https://deims.org/site/b8e9402a-10bc-4892-b03d-1e85fc925c99;UK ECN site. This site at Thorverton weir on the River Exe drains the Exmoor National Park and is situated above the City of Exeter and the more industrialised sub-catchment of the River Culm. Most of the catchment is populated by isolated farmsteads, hamlets, villages and small towns. The only major urban area upstream of this site is Tiverton. The River Exe rises at a level of 450 m AOD in the wet moorland of Exmoor, then passes through steep-sided valleys with extensive broad-leaved woodland. Further east, tributaries run off the Brendon Hills with the River Haddeo drained to form the major water resource of Wimbleball Reservoir. Further south of these tributaries down towards Tiverton the floodplain opens out and rolling farmland replaces woodland. The farmland in the catchment of Thorverton weir includes sheep, cattle and dairy farming. All stretches of river above Thorverton weir, except the Riverton canal, fit into the Environment Agency's River Objective classes 1 and 2 which describe water of very good, or good quality suitable for all fish species. The majority of the Thorverton weir catchment fits into the Environment Agency's Biological Classification class A. The average rainfall for the Exe catchment as a whole 1097 mm, with a maximum of 2018 mm on Exmoor. Analysis of the flow record at Thorverton shows a mean daily flow of 15.887 cumecs with a Q95 that is 12% of the mean daily flow which indicates a relatively 'flashy' flow regime compared to the rest of England.;The original metadata record was created using DEIMS-SDR, the Dynamic Ecological Information Management System - Site and dataset registry;Andrew Sier;Centre for Ecology & Hydrology;arjs@ceh.ac.uk;Centre for Ecology & Hydrology Lancaster Lancashire LA1 4AP GB;Centre for Ecology & Hydrology;Ben Bradford;LTER Europe;bradfb@environment-agency.gov.uk;Andrew Sier;Centre for Ecology & Hydrology;arjs@ceh.ac.uk;Centre for Ecology & Hydrology Lancaster Lancashire LA1 4AP GB;site;emf2iso_pointer_record;ecosystem parameter;nitrogen content;ammonium content;dissolved nutrient;inorganic nutrient content;total organic carbon;water parameter;water acidity;water alkalinity;chlorophyll content of water;conductivity;dissolved organic carbon in water;water transparency;water level;stage height;water quality;suspended solids;water temperature;Fresh water rivers;continuousDataCollection;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;2008-06-01;English;environment;-3.500000000000;-3.500000000000;50.800000000000;50.800000000000;1994-01-01;https://deims.org/b8e9402a-10bc-4892-b03d-1e85fc925c99;http://data.ecn.ac.uk/sites/ecnsites.asp?site=R04;http://data.ecn.ac.uk/;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='b8e9402a-10bc-4892-b03d-1e85fc925c99'&outputFormat=SHAPE-ZIP;WFS GetFeature request for downloading the data set in SHP format;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='b8e9402a-10bc-4892-b03d-1e85fc925c99'&outputFormat=application%2Fgml%2Bxml%3B+version%3D3.2;WFS GetFeature request for downloading the data set in GML 3.2 format;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='b8e9402a-10bc-4892-b03d-1e85fc925c99'&outputFormat=application%2Fjson;WFS GetFeature request for downloading the data set in GeoJSON format;https://data.lter-europe.net/pycsw?service=CSW&version=3.0.0&request=GetRecordById&ElementSetName=full&outputSchema=http://www.isotc211.org/2005/gmd&outputFormat=application/json&id=f9a3608c-ffc9-48c9-86e8-bf89182565b1;HTTP;Catalogue Service for the Web (CSW);https://deims.org/node/240;United Kingdom (ECN);COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;publication;This data set is conformant with the INSPIRE Implementing Rules for the interoperability of spatial data sets and services;false;Dataset has been created by data transformation from the original record collected by the site managers using DEIMS site metadata editing form.",
-    "group": "deims",
-    "groups": [
-        {
-            "name": "deims"
-        }
-    ],
-    "name": "0bf06f83-7717-5a1b-8aea-a7c91c2f15c3",
-    "notes": [
-        "UK ECN site. This site at Thorverton weir on the River Exe drains the Exmoor National Park and is situated above the City of Exeter and the more industrialised sub-catchment of the River Culm. Most of the catchment is populated by isolated farmsteads, hamlets, villages and small towns. The only major urban area upstream of this site is Tiverton. The River Exe rises at a level of 450 m AOD in the wet moorland of Exmoor, then passes through steep-sided valleys with extensive broad-leaved woodland. Further east, tributaries run off the Brendon Hills with the River Haddeo drained to form the major water resource of Wimbleball Reservoir. Further south of these tributaries down towards Tiverton the floodplain opens out and rolling farmland replaces woodland. The farmland in the catchment of Thorverton weir includes sheep, cattle and dairy farming. All stretches of river above Thorverton weir, except the Riverton canal, fit into the Environment Agency's River Objective classes 1 and 2 which describe water of very good, or good quality suitable for all fish species. The majority of the Thorverton weir catchment fits into the Environment Agency's Biological Classification class A. The average rainfall for the Exe catchment as a whole 1097 mm, with a maximum of 2018 mm on Exmoor. Analysis of the flow record at Thorverton shows a mean daily flow of 15.887 cumecs with a Q95 that is 12% of the mean daily flow which indicates a relatively 'flashy' flow regime compared to the rest of England."
-    ],
-    "oai_identifier": [
-        "0bf06f83-7717-5a1b-8aea-a7c91c2f15c3"
-    ],
-    "oai_set": "full",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-3.500000000000,50.800000000000],[-3.500000000000,50.800000000000],[-3.500000000000,50.800000000000],[-3.500000000000,50.800000000000],[-3.500000000000,50.800000000000]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "site"
-        },
-        {
-            "name": "emfiso_pointer_record"
-        },
-        {
-            "name": "ecosystem parameter"
-        },
-        {
-            "name": "nitrogen content"
-        },
-        {
-            "name": "ammonium content"
-        },
-        {
-            "name": "dissolved nutrient"
-        },
-        {
-            "name": "inorganic nutrient content"
-        },
-        {
-            "name": "total organic carbon"
-        },
-        {
-            "name": "water parameter"
-        },
-        {
-            "name": "water acidity"
-        },
-        {
-            "name": "water alkalinity"
-        },
-        {
-            "name": "chlorophyll content water"
-        }
-    ],
-    "title": [
-        "River Exe"
-    ],
-    "url": "https://deims.org/node/240"
-}
\ No newline at end of file
diff --git a/oaitestdata/deims-iso19139/full_1/json/0c0507fb-e883-592b-921e-e6d23e7cab66.json b/oaitestdata/deims-iso19139/full_1/json/0c0507fb-e883-592b-921e-e6d23e7cab66.json
deleted file mode 100644
index e15d921a..00000000
--- a/oaitestdata/deims-iso19139/full_1/json/0c0507fb-e883-592b-921e-e6d23e7cab66.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "michele.freppaz@unito.it"
-    ],
-    "Contributor": "DEIMS-SDR | Site and Dataset registry deims.org",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "https://deims.org/pycsw/catalogue/csw?verb=GetRecord&metadataPrefix=iso19139&identifier=0c0507fb-e883-592b-921e-e6d23e7cab66",
-    "PublicationTimestamp": "2018-09-24T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Co-authorship on publications resulting from use of the dataset",
-        "Formal acknowledgement of the dataset providers",
-        "The opportunity to collaborate on the project using the dataset",
-        "Reprints of articles using the dataset must be provided to the data provider"
-    ],
-    "SpatialCoverage": "(46N-46N,8 E-8 E)",
-    "author": [
-        "Michele Freppaz"
-    ],
-    "fulltext": "665b1d0b-6a76-4c48-bd73-a40dc2c5fba2;English;utf8;dataset;Michele Freppaz;Universit\u00e0 degli Studi di Torino;+39 116708514;44, Via Leoardo da Vinci;Grugliasco;TO;10095;IT;michele.freppaz@unito.it;pointOfContact;2018-09-24;ISO19115;2003/Cor.1:2006;EPSG:4326;http://www.opengis.net/def/crs/EPSG/0/4326;http://www.opengis.net/def/crs/EPSG/0/4258;Col d'Olen, water chemistry (DOC);2018-09-24;publication;urn:ltereurope:inspire::10589:18583;Istituto Scientifico Angelo Mosso (MOSSO) - Italy;Michele Freppaz;Universit\u00e0 degli Studi di Torino;+39 116708514;44, Via Leoardo da Vinci;Grugliasco;TO;10095;IT;michele.freppaz@unito.it;pointOfContact;documentDigital;Dataset provides information about soil temperature, soil C and N dynamics at different sites in the alpine tundra, along an elevational gradient from 2500 to 2900 m asl during the period 2005-2015. The soil temperature is measured continuously while the soil and the water samples are collected during the snow free season. The ongoing studies aimed at investigating how the meteorological variables affect the biogeochemistry of seasonally snow covered areas, with a special focus on the effect of the snow cover duration on soil and water C and N dynamics during the growing season.;completed;Michele Freppaz;Universit\u00e0 degli Studi di Torino;+39 116708514;44, Via Leoardo da Vinci;Grugliasco;TO;10095;IT;michele.freppaz@unito.it;pointOfContact;continual;Representative area of sampling: catchment scale Sampling frequency - sampling time span: yearly Sampling frequency - minimum sampling unit: other temporal resolution;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;2008-06-01;publication;LTER Site;alpine;soil chemistry;water chemistry;carbon;nitrogen;alpine tundra;LTER Controlled Vocabulary;Co-authorship on publications resulting from use of the dataset;Formal acknowledgement of the dataset providers;The opportunity to collaborate on the project using the dataset;Reprints of articles using the dataset must be provided to the data provider;The principal: Administration has granted the access and use permission: Free for access and use upon request;eng;environment;7.891100000000;7.868360000000;45.866170000000;45.876560000000;2500.00;2900;urn:ogc:def:crs:EPSG;MSL height;Not specific to any location or epoch.;Hydrography.;Representative area of sampling: catchment scale;ground condition;2008-09-30;2015-01-01;http://www.natrisk.org/datapage.asp?id=9&l=1;WWW:LINK-1.0-http--link;NatRisk;dataset;Conformity_001;INSPIRE;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;publication;See the referenced specification;Method description: Dissolved organic carbon in 0.45 \u03bcm membrane filtered water samples was determined with a TOC-Analyzer. Method URL: . Instrumentation: TOC- Analyzer (Elementar, Vario TOC, Hanau, Germany);Metadata Access Constraints: none Metadata Use Constraints: none;annually",
-    "group": "deims",
-    "groups": [
-        {
-            "name": "deims"
-        }
-    ],
-    "name": "0c0507fb-e883-592b-921e-e6d23e7cab66",
-    "notes": [
-        "Dataset provides information about soil temperature, soil C and N dynamics at different sites in the alpine tundra, along an elevational gradient from 2500 to 2900 m asl during the period 2005-2015. The soil temperature is measured continuously while the soil and the water samples are collected during the snow free season. The ongoing studies aimed at investigating how the meteorological variables affect the biogeochemistry of seasonally snow covered areas, with a special focus on the effect of the snow cover duration on soil and water C and N dynamics during the growing season."
-    ],
-    "oai_identifier": [
-        "0c0507fb-e883-592b-921e-e6d23e7cab66"
-    ],
-    "oai_set": "full",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[7.891100000000,45.866170000000],[7.891100000000,45.876560000000],[7.868360000000,45.876560000000],[7.868360000000,45.866170000000],[7.891100000000,45.866170000000]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "LTER Site"
-        },
-        {
-            "name": "alpine"
-        },
-        {
-            "name": "soil chemistry"
-        },
-        {
-            "name": "water chemistry"
-        },
-        {
-            "name": "carbon"
-        },
-        {
-            "name": "nitrogen"
-        },
-        {
-            "name": "alpine tundra"
-        }
-    ],
-    "title": [
-        "Col d'Olen, water chemistry (DOC)"
-    ],
-    "url": "http://www.natrisk.org/datapage.asp?id=9&l=1"
-}
\ No newline at end of file
diff --git a/oaitestdata/deims-iso19139/full_1/json/0c163b83-26a9-50e6-913e-c2da188175a8.json b/oaitestdata/deims-iso19139/full_1/json/0c163b83-26a9-50e6-913e-c2da188175a8.json
deleted file mode 100644
index 32f80929..00000000
--- a/oaitestdata/deims-iso19139/full_1/json/0c163b83-26a9-50e6-913e-c2da188175a8.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Franziska.Poepperl@kalkalpen.at"
-    ],
-    "Contributor": "DEIMS-SDR | Site and Dataset registry deims.org",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "https://deims.org/pycsw/catalogue/csw?verb=GetRecord&metadataPrefix=iso19139&identifier=0c163b83-26a9-50e6-913e-c2da188175a8",
-    "PublicationTimestamp": "2018-09-24T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "LTER Europe"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "SpatialCoverage": "(48N-48N,15E-14E)",
-    "author": [
-        "Franziska P\u00f6pperl"
-    ],
-    "fulltext": "33ea62e4-a7b1-435d-98e7-49d2e31cb3da;English;utf8;dataset;Franziska P\u00f6pperl;LTER Europe;Franziska.Poepperl@kalkalpen.at;pointOfContact;2018-09-24;ISO19115;2003/Cor.1:2006;EPSG:4326;http://www.opengis.net/def/crs/EPSG/0/4326;http://www.opengis.net/def/crs/EPSG/0/4258;Kalkalpen National Park - Road network;2018-09-24;publication;urn:ltereurope:inspire::10334:18139;Kalkalpen National Park - Austria;Nationalpark Kalkalpen;documentDigital;GIS-layer of road network within the Kalkalpen National Park;completed;Franziska P\u00f6pperl;LTER Europe;Franziska.Poepperl@kalkalpen.at;pointOfContact;continual;Representative area of sampling: landscape scale Sampling frequency - sampling time span: single measurement Sampling frequency - minimum sampling unit: single measurement;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;2008-06-01;publication;infrastructure;LTER Controlled Vocabulary;The principal: Administration has granted the access and use permission: Free for access and use upon request;The principal: Research has granted the access and use permission: Free for access and use upon request;The principal: Public has granted the access and use permission: Free for access and use upon request;eng;environment;Area of nationl Park Kalkalpen, Austria;14.641664028168;14.099214076996;47.652177592975;47.874648383174;Representative area of sampling: landscape scale;UKST;dataset;Conformity_001;INSPIRE;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;publication;See the referenced specification;None;2000-01-01;publication;See the referenced specification;Method description: test. Method URL: . Instrumentation:;Metadata Access Constraints: none Metadata Use Constraints: none;annually",
-    "group": "deims",
-    "groups": [
-        {
-            "name": "deims"
-        }
-    ],
-    "name": "0c163b83-26a9-50e6-913e-c2da188175a8",
-    "notes": [
-        "GIS-layer of road network within the Kalkalpen National Park"
-    ],
-    "oai_identifier": [
-        "0c163b83-26a9-50e6-913e-c2da188175a8"
-    ],
-    "oai_set": "full",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[14.641664028168,47.652177592975],[14.641664028168,47.874648383174],[14.099214076996,47.874648383174],[14.099214076996,47.652177592975],[14.641664028168,47.652177592975]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "infrastructure"
-        }
-    ],
-    "title": [
-        "Kalkalpen National Park - Road network"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/deims-iso19139/full_1/json/0c18db7d-78b0-53fe-ba2a-fafbb27e923b.json b/oaitestdata/deims-iso19139/full_1/json/0c18db7d-78b0-53fe-ba2a-fafbb27e923b.json
deleted file mode 100644
index 3c84e088..00000000
--- a/oaitestdata/deims-iso19139/full_1/json/0c18db7d-78b0-53fe-ba2a-fafbb27e923b.json
+++ /dev/null
@@ -1,89 +0,0 @@
-{
-    "Contact": [
-        "cev@ceh.ac.uk"
-    ],
-    "Contributor": "DEIMS-SDR | Site and Dataset registry deims.org",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Format": [
-        "Research site"
-    ],
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "https://deims.org/pycsw/catalogue/csw?verb=GetRecord&metadataPrefix=iso19139&identifier=0c18db7d-78b0-53fe-ba2a-fafbb27e923b",
-    "Publisher": [
-        "Centre for Ecology & Hydrology"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "SpatialCoverage": "(53N-53N,4 W-4 W)",
-    "author": [
-        "Chris Evans"
-    ],
-    "fulltext": "2eac4a5e-c339-47cf-9371-8f2b0cd8f175;English;utf8;dataset;Research site;Chris Evans;Centre for Ecology & Hydrology;cev@ceh.ac.uk;CEH Bangor, Environment Centre Wales, Deiniol Road Bangor LL57 2UW GB;Chris Evans;Centre for Ecology & Hydrology;cev@ceh.ac.uk;CEH Bangor, Environment Centre Wales, Deiniol Road Bangor LL57 2UW GB;Chris Evans;Centre for Ecology & Hydrology;cev@ceh.ac.uk;CEH Bangor, Environment Centre Wales, Deiniol Road Bangor LL57 2UW GB;2018-09-24;http://www.opengis.net/def/crs/EPSG/0/4326;Conwy;https://deims.org/site/2eac4a5e-c339-47cf-9371-8f2b0cd8f175;Mixed lowland and upland catchment established as a major UK research platform for ecological research, including long-term monitoring of greenhouse has fluxes and water quality, ecosystem-scale experiments, ecological and biogeochemical process studies and modelling. The Conwy catchment incorporates a range of habitats broadly representative of Wales, comprising upland bog and heath, mountain grassland, lowland improved grassland, conifer and broadleaf woodland.;The original metadata record was created using DEIMS-SDR, the Dynamic Ecological Information Management System - Site and dataset registry;Chris Evans;Centre for Ecology & Hydrology;cev@ceh.ac.uk;CEH Bangor, Environment Centre Wales, Deiniol Road Bangor LL57 2UW GB;Chris Evans;Centre for Ecology & Hydrology;cev@ceh.ac.uk;CEH Bangor, Environment Centre Wales, Deiniol Road Bangor LL57 2UW GB;Chris Evans;Centre for Ecology & Hydrology;cev@ceh.ac.uk;CEH Bangor, Environment Centre Wales, Deiniol Road Bangor LL57 2UW GB;site;emf2iso_pointer_record;agricultural parameter;amount of nitrate leaching;dissolved organic carbon in soil;nutrient concentration;nutrient content;soil fertility;atmospheric parameter;carbon dioxide concentration;air humidity;air temperature;heat flux;maximum temperature;mean annual air temperature;mean annual precipitation;mean annual temperature;minimum temperature;methane concentration;plant carbon concentration;solar radiation;wind direction;wind speed;biological parameter;above ground biomass;annual net primary production;leaf area;leaf area index;leaf nutrient;nitrogen content;plant carbon concentration;plant nitrogen concentration;chemical parameter;acid neutralizing capacity;air methane concentration;ammonium content;amount of nitrate leaching;available phosphorus;carbon to nitrogen ratio;chemical composition of water;dissolved organic nitrogen;inorganic nutrient content;insoluble organic carbon content;pH value of water;carbon dioxide concentration;dissolved nutrient;percent organic carbon;leaf nutrient;soil acidity;nitrogen content;soil carbon storage;soil nitrogen;soil nutrient;soil organic carbon;methane concentration;plant carbon concentration;soil solution pH;dissolved organic carbon in water;plant nitrogen concentration;dissolved organic carbon in soil;percent carbon;soil PH;soil solution concentration;suspended solids;nutrient concentration;nutrient content;total organic carbon;water acidity;water alkalinity;water turbidity;ecosystem parameter;above ground biomass;above ground net primary production;ammonium content;leaf area;carbon dioxide concentration;dissolved nutrient;percent organic carbon;leaf nutrient;percent carbon;soil microbial diversity;microbial diversity;total carbon;landscape parameter;land cover;land use;land use intensity;landscape composition;landscape metrics;heat flux;solar radiation;soil parameter;acid neutralizing capacity;ammonium content;available phosphorus;carbon dioxide concentration;percent organic carbon;carbon-to-nitrogen ratio;soil volumetric water content;soil moisture field capacity;soil temperature;soil texture;thickness of soil horizon;total organic carbon in soil;dissolved organic carbon in soil;percent carbon;soil PH;soil solution concentration;total organic carbon;water parameter;ammonium content;carbon dioxide concentration;nitrogen content;water acidity;conductivity;runoff;ammonium nitrogen content;dissolved organic phosphorus;water level;stage height;water quality;suspended solids;water table;water temperature;lake temperature;water volume;dissolved organic carbon in water;percent carbon;total organic carbon;continuousDataCollection;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;2008-06-01;English;environment;-4.1748;-3.62549;53.0544;53.4292;2006-01-01;https://deims.org/2eac4a5e-c339-47cf-9371-8f2b0cd8f175;https://www.ceh.ac.uk/our-science/monitoring-site/conwy-source-sea-catchment-research-platform;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='2eac4a5e-c339-47cf-9371-8f2b0cd8f175'&outputFormat=SHAPE-ZIP;WFS GetFeature request for downloading the data set in SHP format;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='2eac4a5e-c339-47cf-9371-8f2b0cd8f175'&outputFormat=application%2Fgml%2Bxml%3B+version%3D3.2;WFS GetFeature request for downloading the data set in GML 3.2 format;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='2eac4a5e-c339-47cf-9371-8f2b0cd8f175'&outputFormat=application%2Fjson;WFS GetFeature request for downloading the data set in GeoJSON format;https://deims.org/node/240;United Kingdom (ECN);COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;publication;This data set is conformant with the INSPIRE Implementing Rules for the interoperability of spatial data sets and services;false;Dataset has been created by data transformation from the original record collected by the site managers using DEIMS site metadata editing form.",
-    "group": "deims",
-    "groups": [
-        {
-            "name": "deims"
-        }
-    ],
-    "name": "0c18db7d-78b0-53fe-ba2a-fafbb27e923b",
-    "notes": [
-        "Mixed lowland and upland catchment established as a major UK research platform for ecological research, including long-term monitoring of greenhouse has fluxes and water quality, ecosystem-scale experiments, ecological and biogeochemical process studies and modelling. The Conwy catchment incorporates a range of habitats broadly representative of Wales, comprising upland bog and heath, mountain grassland, lowland improved grassland, conifer and broadleaf woodland."
-    ],
-    "oai_identifier": [
-        "0c18db7d-78b0-53fe-ba2a-fafbb27e923b"
-    ],
-    "oai_set": "full",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-4.1748,53.0544],[-4.1748,53.4292],[-3.62549,53.4292],[-3.62549,53.0544],[-4.1748,53.0544]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "site"
-        },
-        {
-            "name": "emfiso_pointer_record"
-        },
-        {
-            "name": "agricultural parameter"
-        },
-        {
-            "name": "amount nitrate leaching"
-        },
-        {
-            "name": "dissolved organic carbon soil"
-        },
-        {
-            "name": "nutrient concentration"
-        },
-        {
-            "name": "nutrient content"
-        },
-        {
-            "name": "soil fertility"
-        },
-        {
-            "name": "atmospheric parameter"
-        },
-        {
-            "name": "carbon dioxide concentration"
-        },
-        {
-            "name": "air humidity"
-        },
-        {
-            "name": "air temperature"
-        }
-    ],
-    "title": [
-        "Conwy"
-    ],
-    "url": "https://deims.org/node/240"
-}
\ No newline at end of file
diff --git a/oaitestdata/deims-iso19139/full_1/json/0c209c97-d170-5582-9ae3-9ca88ed6623b.json b/oaitestdata/deims-iso19139/full_1/json/0c209c97-d170-5582-9ae3-9ca88ed6623b.json
deleted file mode 100644
index 9421fff4..00000000
--- a/oaitestdata/deims-iso19139/full_1/json/0c209c97-d170-5582-9ae3-9ca88ed6623b.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "srennie@ceh.ac.uk"
-    ],
-    "Contributor": "DEIMS-SDR | Site and Dataset registry deims.org",
-    "DOI": "http://dx.doi.org/10.5285/0be0aed3-f205-4f1f-a65d-84f8cfd8d50f",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "https://deims.org/pycsw/catalogue/csw?verb=GetRecord&metadataPrefix=iso19139&identifier=0c209c97-d170-5582-9ae3-9ca88ed6623b",
-    "PublicationTimestamp": "2018-09-24T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Formal acknowledgement of the dataset providers"
-    ],
-    "SpatialCoverage": "(53N-53N,4 W-4 W)",
-    "author": [
-        "Sue Rennie"
-    ],
-    "fulltext": "b0732973-d88d-4c62-ad07-8c07079f6f81;English;utf8;dataset;Sue Rennie;Centre for Ecology & Hydrology;+44 1524 595835;Centre for Ecology & Hydrology;Lancaster;Lancashire;LA1 4AP;GB;srennie@ceh.ac.uk;pointOfContact;2018-09-24;ISO19115;2003/Cor.1:2006;EPSG:4326;http://www.opengis.net/def/crs/EPSG/0/4326;http://www.opengis.net/def/crs/EPSG/0/4258;Snowdon: UK Environmental Change Network (ECN) rabbit and deer data: 1993-2015;2018-09-24;publication;urn:ltereurope:inspire::11851:26704;Yr Wyddfa/Snowdon - United Kingdom;Centre for Ecology and Hydrology/Natural Environment Research Council;Natural Resources Wales;Sue Rennie;Centre for Ecology & Hydrology;+44 1524 595835;Centre for Ecology & Hydrology;Lancaster;Lancashire;LA1 4AP;GB;srennie@ceh.ac.uk;pointOfContact;Welsh Government;documentDigital;Rabbit and deer data from the UK Environmental Change Network (ECN) terrestrial sites. These data are collected by transect at ECN&#039;s terrestrial sites using a standard protocol. The protocol uses an index method based on dropping counts (of deer, rabbits - and where appropriate sheep and Grouse) to estimate relative abundance. They represent twice-yearly continuous records from 1993 to 2015. ECN is the UK&#039;s long-term environmental monitoring programme. It is a multi-agency programme sponsored by a consortium of fourteen government departments and agencies. These organisations contribute to the programme through funding either site monitoring and/or network co-ordination activities. These organisations are: Agri-Food and Biosciences Institute, Biotechnology and Biological Sciences Research Council, Cyfoeth Naturiol Cymru - Natural Resources Wales, Defence Science &amp; Technology Laboratory, Department for Environment, Food and Rural Affairs, Environment Agency, Forestry Commission, Llywodraeth Cymru - Welsh Government, Natural England, Natural Environment Research Council, Northern Ireland Environment Agency, Scottish Environment Protection Agency, Scottish Government and Scottish Natural Heritage.;completed;Sue Rennie;Centre for Ecology & Hydrology;+44 1524 595835;Centre for Ecology & Hydrology;Lancaster;Lancashire;LA1 4AP;GB;srennie@ceh.ac.uk;pointOfContact;continual;Representative area of sampling: transect Sampling frequency - sampling time span: yearly Sampling frequency - minimum sampling unit: yearly;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;2008-06-01;publication;vertebrates;rabbits;deer;LTER Controlled Vocabulary;Formal acknowledgement of the dataset providers;The principal: Administration has granted the access and use permission: Free access and use;The principal: Research has granted the access and use permission: Free for access;The principal: Public has granted the access and use permission: Free for access;eng;environment;Snowdon ECN site;-4.023633000000;-4.079174510000;53.057216640000;53.081893920000;1085.00;298;urn:ogc:def:crs:EPSG;MSL height;Not specific to any location or epoch.;Hydrography.;Representative area of sampling: transect;ground condition;1993-01-01;2015-12-31;https://doi.org/10.5285/0be0aed3-f205-4f1f-a65d-84f8cfd8d50f;WWW:LINK-1.0-http--link;DOI;dataset;Conformity_001;INSPIRE;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;publication;See the referenced specification;Method description: Rabbit and deer data from the UK Environmental Change Network (ECN) terrestrial sites. These data are collected by transect at ECN's terrestrial sites using a standard protocol. The protocol uses an index method based on dropping counts (of deer, rabbits - and where appropriate sheep and Grouse) to estimate relative abundance. They represent twice-yearly continuous records from 1993 to 2015. . Method URL: http://www.ecn.ac.uk/measurements/terrestrial/b. Instrumentation:;Metadata Access Constraints: none Metadata Use Constraints: none;annually",
-    "group": "deims",
-    "groups": [
-        {
-            "name": "deims"
-        }
-    ],
-    "name": "0c209c97-d170-5582-9ae3-9ca88ed6623b",
-    "notes": [
-        "Rabbit and deer data from the UK Environmental Change Network (ECN) terrestrial sites. These data are collected by transect at ECN&#039;s terrestrial sites using a standard protocol. The protocol uses an index method based on dropping counts (of deer, rabbits - and where appropriate sheep and Grouse) to estimate relative abundance. They represent twice-yearly continuous records from 1993 to 2015. ECN is the UK&#039;s long-term environmental monitoring programme. It is a multi-agency programme sponsored by a consortium of fourteen government departments and agencies. These organisations contribute to the programme through funding either site monitoring and/or network co-ordination activities. These organisations are: Agri-Food and Biosciences Institute, Biotechnology and Biological Sciences Research Council, Cyfoeth Naturiol Cymru - Natural Resources Wales, Defence Science &amp; Technology Laboratory, Department for Environment, Food and Rural Affairs, Environment Agency, Forestry Commission, Llywodraeth Cymru - Welsh Government, Natural England, Natural Environment Research Council, Northern Ireland Environment Agency, Scottish Environment Protection Agency, Scottish Government and Scottish Natural Heritage."
-    ],
-    "oai_identifier": [
-        "0c209c97-d170-5582-9ae3-9ca88ed6623b"
-    ],
-    "oai_set": "full",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-4.023633000000,53.057216640000],[-4.023633000000,53.081893920000],[-4.079174510000,53.081893920000],[-4.079174510000,53.057216640000],[-4.023633000000,53.057216640000]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "vertebrates"
-        },
-        {
-            "name": "rabbits"
-        },
-        {
-            "name": "deer"
-        }
-    ],
-    "title": [
-        "Snowdon: UK Environmental Change Network (ECN) rabbit and deer data: 1993-2015"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/deims-iso19139/full_1/json/0c374790-42de-5621-a022-3d8e2bac4325.json b/oaitestdata/deims-iso19139/full_1/json/0c374790-42de-5621-a022-3d8e2bac4325.json
deleted file mode 100644
index 0c7444c7..00000000
--- a/oaitestdata/deims-iso19139/full_1/json/0c374790-42de-5621-a022-3d8e2bac4325.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "kristin.meier@zalf.de"
-    ],
-    "Contributor": "DEIMS-SDR | Site and Dataset registry deims.org",
-    "DOI": "http://dx.doi.org/10.4228/ZALF.2007.250",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "https://deims.org/pycsw/catalogue/csw?verb=GetRecord&metadataPrefix=iso19139&identifier=0c374790-42de-5621-a022-3d8e2bac4325",
-    "PublicationTimestamp": "2018-09-24T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Formal acknowledgement of the dataset providers",
-        "Legal permission for dataset use is obtained"
-    ],
-    "SpatialCoverage": "(53N,14E)",
-    "author": [
-        "Kristin Meier"
-    ],
-    "fulltext": "4d95a61b-d071-4d7a-b1de-e40e2b3dc411;English;utf8;dataset;Kristin Meier;Leibniz-Zentrum f\u00fcr Agrarlandschaftsforschung (ZALF) e.V.;Eberswalder Str. 84;M\u00fcncheberg;15374;DE;kristin.meier@zalf.de;pointOfContact;2018-09-24;ISO19115;2003/Cor.1:2006;EPSG:4326;http://www.opengis.net/def/crs/EPSG/0/4326;http://www.opengis.net/def/crs/EPSG/0/4258;Meteorological data from the Uckermark region - AgroScapeLab Quillow 2007;2018-09-24;publication;urn:ltereurope:inspire::11919:27163;AgroScapeLab Quillow (ZALF) - Germany;Gunnar Lischeid;Leibniz-Zentrum f\u00fcr Agrarlandschaftsforschung (ZALF) e.V.;Eberswalder Str. 84;M\u00fcncheberg;15374;DE;lischeid@zalf.de;pointOfContact;Kristin Meier;Leibniz-Zentrum f\u00fcr Agrarlandschaftsforschung (ZALF) e.V.;Eberswalder Str. 84;M\u00fcncheberg;15374;DE;kristin.meier@zalf.de;pointOfContact;documentDigital;The agrometeorological weather station Dedelow was installed in 1991 by the Leibniz Centre for Agricultural Landscape Research (ZALF) e.V. and is managed by the research station of ZALF in Dedelow. The station is located within the municipality Dedelow, district Uckermark, state Brandenburg, Germany. Altitude in meter: 49 NN, Geographic latitude: 53,3665 N, Geographic longitude: 13,8030 E,Type: FMA 86. In 1991, data have been collected for: soil temperature in 20cm depth (\u00b0C); global radiation (J/cm\u00b2); relative humidity (%); air temperature, 20cm above ground (\u00b0C); air temperature, 2m above ground (\u00b0C); precipitation (mm); wind velocity (m/s); evaporation (mm). Data are saved by the logger of the station and are automatically transferred onto a PC which uses the Software MeteoWare Pro 1.02.;completed;Kristin Meier;Leibniz-Zentrum f\u00fcr Agrarlandschaftsforschung (ZALF) e.V.;Eberswalder Str. 84;M\u00fcncheberg;15374;DE;kristin.meier@zalf.de;pointOfContact;continual;Representative area of sampling: _unknown Sampling frequency - sampling time span: _unknown Sampling frequency - minimum sampling unit: _unknown;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;2008-06-01;publication;LTER Site;on-site sensors;meteorology;Intensive unmixed crops;evaporation;air temperature;wind;air humidity;weather;eLTER VA;LTER Controlled Vocabulary;Formal acknowledgement of the dataset providers;Legal permission for dataset use is obtained;eng;environment;The Experimental Station Dedelow is located approximately 100 km north of Berlin (near Prenzlau). On 42 ha of experimental fields (sandy loam; average soil quality [\u201cAckerzahl\u201d] 35-45), different agricultural cultivation systems can be realised with modern experimental technology. On site, there are various technical measuring systems such as the TERENO lysimeters and the large gas chambers of &quot;CARBO-ZALF-D\u201c. Dedelow is part of the ZALF Landscape Laboratory &quot;AgroScapeLab Quillow&quot; and supports numerous projects (e.g. DFG Research Training Group BioMove) regarding the planning and implementation of measurement programs in cooperation with farmers.;13.803000000000;13.803000000000;53.366500000000;53.366500000000;Representative area of sampling: _unknown;ground condition;2007-01-01;2007-12-31;http://doi.org/10.4228/ZALF.2007.250;WWW:LINK-1.0-http--link;DOI;WWW:DOWNLOAD-1.0-http--download;dataset;Conformity_001;INSPIRE;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;publication;See the referenced specification;Method description: The data were obtained by an automatic measurement device, which is following the standards of the German Wheather Service (DWD). The basic measurement intervall for most of the parameters is 10 minutes. The data is aggregated later on to the following temperal levels (hour, day, month and year). The measurement series started in 1999. Elder values are available on request. (Spatial Scale Description: Water samples were collected at the point of maximum depth of the lake by means of a Ruttner bottle. Samples were collected at the following depths: 0, -2 m, -6 m, -10 m, -14 m, -18 m, bottom. Samples were kept refrigerated and transported to the laboratory where chlorophyll-a was determined following the method proposed by Strickland and Parsons (1968). Samples were collected monthly from june to october.). Method URL: . Instrumentation: The data were obtained by an automatic measurement device, which is following the standards of the German Wheather Service (DWD). The basic measurement intervall for most of the parameters is\u00a0 10 minutes. The data is aggregated later on to the following temperal levels (hour, day, month and year). The measurement series started in 1999. Elder values are available on request.;Metadata Access Constraints: none Metadata Use Constraints: none;annually",
-    "group": "deims",
-    "groups": [
-        {
-            "name": "deims"
-        }
-    ],
-    "name": "0c374790-42de-5621-a022-3d8e2bac4325",
-    "notes": [
-        "The agrometeorological weather station Dedelow was installed in 1991 by the Leibniz Centre for Agricultural Landscape Research (ZALF) e.V. and is managed by the research station of ZALF in Dedelow. The station is located within the municipality Dedelow, district Uckermark, state Brandenburg, Germany. Altitude in meter: 49 NN, Geographic latitude: 53,3665 N, Geographic longitude: 13,8030 E,Type: FMA 86. In 1991, data have been collected for: soil temperature in 20cm depth (\u00b0C); global radiation (J/cm\u00b2); relative humidity (%); air temperature, 20cm above ground (\u00b0C); air temperature, 2m above ground (\u00b0C); precipitation (mm); wind velocity (m/s); evaporation (mm). Data are saved by the logger of the station and are automatically transferred onto a PC which uses the Software MeteoWare Pro 1.02."
-    ],
-    "oai_identifier": [
-        "0c374790-42de-5621-a022-3d8e2bac4325"
-    ],
-    "oai_set": "full",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[13.803000000000,53.366500000000],[13.803000000000,53.366500000000],[13.803000000000,53.366500000000],[13.803000000000,53.366500000000],[13.803000000000,53.366500000000]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "LTER Site"
-        },
-        {
-            "name": "on-site sensors"
-        },
-        {
-            "name": "meteorology"
-        },
-        {
-            "name": "Intensive unmixed crops"
-        },
-        {
-            "name": "evaporation"
-        },
-        {
-            "name": "air temperature"
-        },
-        {
-            "name": "wind"
-        },
-        {
-            "name": "air humidity"
-        },
-        {
-            "name": "weather"
-        },
-        {
-            "name": "eLTER VA"
-        }
-    ],
-    "title": [
-        "Meteorological data from the Uckermark region - AgroScapeLab Quillow 2007"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/deims-iso19139/full_1/json/0c3e3207-fd7d-59d0-857c-a87f04ba2771.json b/oaitestdata/deims-iso19139/full_1/json/0c3e3207-fd7d-59d0-857c-a87f04ba2771.json
deleted file mode 100644
index d8852c77..00000000
--- a/oaitestdata/deims-iso19139/full_1/json/0c3e3207-fd7d-59d0-857c-a87f04ba2771.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "wipf@slf.ch"
-    ],
-    "Contributor": "DEIMS-SDR | Site and Dataset registry deims.org",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Format": [
-        "Research site"
-    ],
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "https://deims.org/pycsw/catalogue/csw?verb=GetRecord&metadataPrefix=iso19139&identifier=0c3e3207-fd7d-59d0-857c-a87f04ba2771",
-    "Publisher": [
-        "LTER Europe"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "SpatialCoverage": "(47N,10E)",
-    "author": [
-        "Sonja Wipf"
-    ],
-    "fulltext": "782a17c9-d0fd-4540-b86a-8149bcd5f54e;English;utf8;dataset;Research site;Sonja Wipf;LTER Europe;wipf@slf.ch;WSL Institute for Snow and Avalanche Research SLF Davos Dorf 7260 CH;Sonja Wipf;LTER Europe;wipf@slf.ch;WSL Institute for Snow and Avalanche Research SLF Davos Dorf 7260 CH;Sonja Wipf;LTER Europe;wipf@slf.ch;WSL Institute for Snow and Avalanche Research SLF Davos Dorf 7260 CH;2018-09-24;http://www.opengis.net/def/crs/EPSG/0/4326;CH-SN2-MCS;https://deims.org/site/782a17c9-d0fd-4540-b86a-8149bcd5f54e;Lowest monitoring summit of the CH-SN2 target region near the Swiss National Park.;The original metadata record was created using DEIMS-SDR, the Dynamic Ecological Information Management System - Site and dataset registry;Sonja Wipf;LTER Europe;wipf@slf.ch;WSL Institute for Snow and Avalanche Research SLF Davos Dorf 7260 CH;Sonja Wipf;LTER Europe;wipf@slf.ch;WSL Institute for Snow and Avalanche Research SLF Davos Dorf 7260 CH;Sonja Wipf;LTER Europe;wipf@slf.ch;WSL Institute for Snow and Avalanche Research SLF Davos Dorf 7260 CH;site;emf2iso_pointer_record;continuousDataCollection;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;2008-06-01;English;environment;10.428530000000;10.428530000000;46.735490000000;46.735490000000;2003-01-01;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='782a17c9-d0fd-4540-b86a-8149bcd5f54e'&outputFormat=SHAPE-ZIP;WFS GetFeature request for downloading the data set in SHP format;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='782a17c9-d0fd-4540-b86a-8149bcd5f54e'&outputFormat=application%2Fgml%2Bxml%3B+version%3D3.2;WFS GetFeature request for downloading the data set in GML 3.2 format;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='782a17c9-d0fd-4540-b86a-8149bcd5f54e'&outputFormat=application%2Fjson;WFS GetFeature request for downloading the data set in GeoJSON format;https://deims.org/node/248;Switzerland (LTER-Switzerland);COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;publication;This data set is conformant with the INSPIRE Implementing Rules for the interoperability of spatial data sets and services;false;Dataset has been created by data transformation from the original record collected by the site managers using DEIMS site metadata editing form.",
-    "group": "deims",
-    "groups": [
-        {
-            "name": "deims"
-        }
-    ],
-    "name": "0c3e3207-fd7d-59d0-857c-a87f04ba2771",
-    "notes": [
-        "Lowest monitoring summit of the CH-SN2 target region near the Swiss National Park."
-    ],
-    "oai_identifier": [
-        "0c3e3207-fd7d-59d0-857c-a87f04ba2771"
-    ],
-    "oai_set": "full",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[10.428530000000,46.735490000000],[10.428530000000,46.735490000000],[10.428530000000,46.735490000000],[10.428530000000,46.735490000000],[10.428530000000,46.735490000000]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "site"
-        },
-        {
-            "name": "emfiso_pointer_record"
-        },
-        {
-            "name": "Environmental monitoring facilities"
-        }
-    ],
-    "title": [
-        "CH-SN2-MCS"
-    ],
-    "url": "https://deims.org/node/248"
-}
\ No newline at end of file
diff --git a/oaitestdata/deims-iso19139/full_1/json/0c7c183a-dad9-5e03-8228-97ae87503ecf.json b/oaitestdata/deims-iso19139/full_1/json/0c7c183a-dad9-5e03-8228-97ae87503ecf.json
deleted file mode 100644
index 92ca7291..00000000
--- a/oaitestdata/deims-iso19139/full_1/json/0c7c183a-dad9-5e03-8228-97ae87503ecf.json
+++ /dev/null
@@ -1,94 +0,0 @@
-{
-    "Contact": [
-        "dan.metcalfe@csiro.au"
-    ],
-    "Contributor": "DEIMS-SDR | Site and Dataset registry deims.org",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Format": [
-        "Research site"
-    ],
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "https://deims.org/pycsw/catalogue/csw?verb=GetRecord&metadataPrefix=iso19139&identifier=0c7c183a-dad9-5e03-8228-97ae87503ecf",
-    "Publisher": [
-        "Australian National University",
-        "TERN Long Term Ecological Research Network (LTERN), Australia",
-        "Department of National Parks, Sport and Racing (Queensland, Australia)",
-        "Australian National Collaborative Research Infrastructure Strategy",
-        "Australian Super Science Initiative",
-        "CSIRO (Australia). Ecosystem Sciences."
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "SpatialCoverage": "(17S,145E)",
-    "author": [
-        "Daniel Metcalfe"
-    ],
-    "fulltext": "6fc31303-c4e0-4847-84e3-9abdc5531ccd;English;utf8;dataset;Research site;Daniel Metcalfe;CSIRO (Australia). Ecosystem Sciences.;dan.metcalfe@csiro.au;CSIRO Ecosystem Sciences Atherton QLD 4883 AU;Department of National Parks, Sport and Racing (Queensland, Australia);Australian National Collaborative Research Infrastructure Strategy;Australian Super Science Initiative;Australian National University;CSIRO (Australia). Ecosystem Sciences.;TERN Long Term Ecological Research Network (LTERN), Australia;2018-09-24;http://www.opengis.net/def/crs/EPSG/0/4326;TERN - LTERN - Tropical Rainforest Plot Network;https://deims.org/site/6fc31303-c4e0-4847-84e3-9abdc5531ccd;The Tropical Rainforest Plot Network is a member of Long Term Ecological Research Network (LTERN), Australia (http://www.ltern.org.au), a facility of the Australian Government's Terrestrial Ecosystem Research Network (TERN), (http://www.tern.org.au). Except for minor disturbances associated with selective logging on two plots, the plots were established in old growth forest and all plots have thereafter been protected. Plots have been regularly censused and at each census the diameter at breast height of all stems is recorded. The data collected from the 20 plots provides an insight into the floristical composition, structure and long term forest dynamics of Australian tropical rainforests and allows direct comparisons to be made with long-term monitoring plots at a global scale. Bradford, M.G., Murphy, H.T., Ford, A.J., Hogan, D. and Metcalfe, D.J. (2014) Long term stem inventory data from tropical rainforest plots in Australia. Ecology 95:2362. http://dx.doi.org/10.1890/14-0458R.1 Temporal visits were initially conducted every 2 years, then every 5 years from 1990.;The original metadata record was created using DEIMS-SDR, the Dynamic Ecological Information Management System - Site and dataset registry;Daniel Metcalfe;CSIRO (Australia). Ecosystem Sciences.;dan.metcalfe@csiro.au;CSIRO Ecosystem Sciences Atherton QLD 4883 AU;Department of National Parks, Sport and Racing (Queensland, Australia);Australian National Collaborative Research Infrastructure Strategy;Australian Super Science Initiative;Australian National University;CSIRO (Australia). Ecosystem Sciences.;TERN Long Term Ecological Research Network (LTERN), Australia;site;emf2iso_pointer_record;ecosystem parameter;diversity index;floristic diversity;change in population size over time;species list;faunistic diversity;species composition;plant species composition;species richness;species abundance;birds abundance;macrofauna abundance;plant cover;species group abundance;leaf area;species turnover;tree diameter at breast height;vegetation reflectance;tree condition;deadwood decaying rate;ecosystem structure;habitat structure;forest structure;sapwood area;canopy cover rate;canopy gap area;disturbance pattern;biological parameter;plant height;root density;root growth rate;tree height;tree age;tree diameter;tree distribution;canopy height;canopy growth rate;root length;Terrestrial;continuousDataCollection;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;2008-06-01;English;environment;145.431410036000;145.431410036000;-16.857784875800;-16.857784875800;1971-01-01;https://deims.org/6fc31303-c4e0-4847-84e3-9abdc5531ccd;http://www.ltern.org.au/ltern-plot-networks/tropical-rainforest;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='6fc31303-c4e0-4847-84e3-9abdc5531ccd'&outputFormat=SHAPE-ZIP;WFS GetFeature request for downloading the data set in SHP format;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='6fc31303-c4e0-4847-84e3-9abdc5531ccd'&outputFormat=application%2Fgml%2Bxml%3B+version%3D3.2;WFS GetFeature request for downloading the data set in GML 3.2 format;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='6fc31303-c4e0-4847-84e3-9abdc5531ccd'&outputFormat=application%2Fjson;WFS GetFeature request for downloading the data set in GeoJSON format;https://deims.org/node/245;Australia (TERN);COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;publication;This data set is conformant with the INSPIRE Implementing Rules for the interoperability of spatial data sets and services;false;Dataset has been created by data transformation from the original record collected by the site managers using DEIMS site metadata editing form.",
-    "group": "deims",
-    "groups": [
-        {
-            "name": "deims"
-        }
-    ],
-    "name": "0c7c183a-dad9-5e03-8228-97ae87503ecf",
-    "notes": [
-        "The Tropical Rainforest Plot Network is a member of Long Term Ecological Research Network (LTERN), Australia (http://www.ltern.org.au), a facility of the Australian Government's Terrestrial Ecosystem Research Network (TERN), (http://www.tern.org.au). Except for minor disturbances associated with selective logging on two plots, the plots were established in old growth forest and all plots have thereafter been protected. Plots have been regularly censused and at each census the diameter at breast height of all stems is recorded. The data collected from the 20 plots provides an insight into the floristical composition, structure and long term forest dynamics of Australian tropical rainforests and allows direct comparisons to be made with long-term monitoring plots at a global scale. Bradford, M.G., Murphy, H.T., Ford, A.J., Hogan, D. and Metcalfe, D.J. (2014) Long term stem inventory data from tropical rainforest plots in Australia. Ecology 95:2362. http://dx.doi.org/10.1890/14-0458R.1 Temporal visits were initially conducted every 2 years, then every 5 years from 1990."
-    ],
-    "oai_identifier": [
-        "0c7c183a-dad9-5e03-8228-97ae87503ecf"
-    ],
-    "oai_set": "full",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[145.431410036000,-16.857784875800],[145.431410036000,-16.857784875800],[145.431410036000,-16.857784875800],[145.431410036000,-16.857784875800],[145.431410036000,-16.857784875800]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "site"
-        },
-        {
-            "name": "emfiso_pointer_record"
-        },
-        {
-            "name": "ecosystem parameter"
-        },
-        {
-            "name": "diversity index"
-        },
-        {
-            "name": "floristic diversity"
-        },
-        {
-            "name": "change population size time"
-        },
-        {
-            "name": "species list"
-        },
-        {
-            "name": "faunistic diversity"
-        },
-        {
-            "name": "species composition"
-        },
-        {
-            "name": "plant species composition"
-        },
-        {
-            "name": "species richness"
-        },
-        {
-            "name": "species abundance"
-        }
-    ],
-    "title": [
-        "TERN - LTERN - Tropical Rainforest Plot Network"
-    ],
-    "url": "https://deims.org/node/245"
-}
\ No newline at end of file
diff --git a/oaitestdata/deims-iso19139/full_1/json/0c820dd9-e935-52a0-8d1e-cecdb814b75e.json b/oaitestdata/deims-iso19139/full_1/json/0c820dd9-e935-52a0-8d1e-cecdb814b75e.json
deleted file mode 100644
index 79e8cb10..00000000
--- a/oaitestdata/deims-iso19139/full_1/json/0c820dd9-e935-52a0-8d1e-cecdb814b75e.json
+++ /dev/null
@@ -1,90 +0,0 @@
-{
-    "Contact": [
-        "pfleischer@lesytanap.sk"
-    ],
-    "Contributor": "DEIMS-SDR | Site and Dataset registry deims.org",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Format": [
-        "Research site"
-    ],
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "https://deims.org/pycsw/catalogue/csw?verb=GetRecord&metadataPrefix=iso19139&identifier=0c820dd9-e935-52a0-8d1e-cecdb814b75e",
-    "Publisher": [
-        "State Forests of Tatra National Park",
-        "LTER Europe"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "SpatialCoverage": "(49N,20E)",
-    "author": [
-        "Peter Fleischer"
-    ],
-    "fulltext": "f7b73d7c-068f-4406-b4e8-13e5c6e212b9;English;utf8;dataset;Research site;Peter Fleischer;LTER Europe;pfleischer@lesytanap.sk;\u0160t\u00e1tne lesy TANAPu Tatransk\u00e1 Lomnica 059 60 SK;State Forests of Tatra National Park;State Forests of Tatra National Park;Peter Fleischer;LTER Europe;pfleischer@lesytanap.sk;\u0160t\u00e1tne lesy TANAPu Tatransk\u00e1 Lomnica 059 60 SK;State Forests of Tatra National Park;2018-09-24;http://www.opengis.net/def/crs/EPSG/0/4326;Tatra National Park;https://deims.org/site/f7b73d7c-068f-4406-b4e8-13e5c6e212b9;The spruce forest ecosystem has been intensively studied since 1990s (resistance to pollution, insect infestation, weather extremes). After large-scale destruction by wind (12,000 ha) in 2004, consequent bark beetle outbreak (7,000 ha) and fire, the research was focused to four research plots (min. 100 ha each). Three of them were damaged by wind disturbance: plot NEX without forestry management (no timber extraction, no afforestation); plot EXT from which timber was extracted and the plot was afforested; plot FIR damaged by fire one year after the wind disturbance. The last plot (REF) is not affected by wind disturbance (reference plot). The monitoring equipment (meteorological stations, dendrometres, transpiration flow sensors, soil lysimeters, precipitation collectors, etc.) was installed in each plot. The focus was mainly on monitoring the spatial variability of soil, vegetation and zoocenoses. Our studies confirmed permanent disturbance regime on the affected area and unexpectedly fast and successful regeneration of ecosystem after damage. The intense, but short-term increase in nutrient flows (especially nitrogen) and the renewal of carbon sequestration confirm the adaptation of ecosystems to this disturbance regime. We found increase in biodiversity (abundance and diversity of fauna and flora) caused by disturbance. Future risk poses projected warming which might dramatically change growing condition for dominant tree species and increase population of bark beetles.;The original metadata record was created using DEIMS-SDR, the Dynamic Ecological Information Management System - Site and dataset registry;Peter Fleischer;LTER Europe;pfleischer@lesytanap.sk;\u0160t\u00e1tne lesy TANAPu Tatransk\u00e1 Lomnica 059 60 SK;State Forests of Tatra National Park;State Forests of Tatra National Park;Peter Fleischer;LTER Europe;pfleischer@lesytanap.sk;\u0160t\u00e1tne lesy TANAPu Tatransk\u00e1 Lomnica 059 60 SK;State Forests of Tatra National Park;site;emf2iso_pointer_record;atmospheric parameter;precipitation intensity;wind direction;wind speed;biological parameter;plant transpiration;ecosystem parameter;above ground net primary production;fire severity index;disturbance pattern;ecosystem structure;abiotic heterogeneity;forest structure;canopy cover rate;canopy gap area;leaf area;leaf area index;nitrogen content;percent carbon;percent organic carbon;plant carbon concentration;community composition;diversity index;floristic diversity;faunistic diversity;species composition;plant species composition;species richness;species abundance;plant cover;Terrestrial;continuousDataCollection;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;2008-06-01;English;environment;20.169200000000;20.169200000000;49.144200000000;49.144200000000;2005-01-01;https://deims.org/f7b73d7c-068f-4406-b4e8-13e5c6e212b9;http://www.lesytanap.sk;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='f7b73d7c-068f-4406-b4e8-13e5c6e212b9'&outputFormat=SHAPE-ZIP;WFS GetFeature request for downloading the data set in SHP format;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='f7b73d7c-068f-4406-b4e8-13e5c6e212b9'&outputFormat=application%2Fgml%2Bxml%3B+version%3D3.2;WFS GetFeature request for downloading the data set in GML 3.2 format;https://data.lter-europe.net/geoserver/deims/ows?service=WFS&version=2.0.0&request=GetFeature&typeName=deims:lter_all_formal&CQL_FILTER=uuid='f7b73d7c-068f-4406-b4e8-13e5c6e212b9'&outputFormat=application%2Fjson;WFS GetFeature request for downloading the data set in GeoJSON format;https://deims.org/node/218;Slovakia (LTER Slovakia);COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;publication;This data set is conformant with the INSPIRE Implementing Rules for the interoperability of spatial data sets and services;false;Dataset has been created by data transformation from the original record collected by the site managers using DEIMS site metadata editing form.",
-    "group": "deims",
-    "groups": [
-        {
-            "name": "deims"
-        }
-    ],
-    "name": "0c820dd9-e935-52a0-8d1e-cecdb814b75e",
-    "notes": [
-        "The spruce forest ecosystem has been intensively studied since 1990s (resistance to pollution, insect infestation, weather extremes). After large-scale destruction by wind (12,000 ha) in 2004, consequent bark beetle outbreak (7,000 ha) and fire, the research was focused to four research plots (min. 100 ha each). Three of them were damaged by wind disturbance: plot NEX without forestry management (no timber extraction, no afforestation); plot EXT from which timber was extracted and the plot was afforested; plot FIR damaged by fire one year after the wind disturbance. The last plot (REF) is not affected by wind disturbance (reference plot). The monitoring equipment (meteorological stations, dendrometres, transpiration flow sensors, soil lysimeters, precipitation collectors, etc.) was installed in each plot. The focus was mainly on monitoring the spatial variability of soil, vegetation and zoocenoses. Our studies confirmed permanent disturbance regime on the affected area and unexpectedly fast and successful regeneration of ecosystem after damage. The intense, but short-term increase in nutrient flows (especially nitrogen) and the renewal of carbon sequestration confirm the adaptation of ecosystems to this disturbance regime. We found increase in biodiversity (abundance and diversity of fauna and flora) caused by disturbance. Future risk poses projected warming which might dramatically change growing condition for dominant tree species and increase population of bark beetles."
-    ],
-    "oai_identifier": [
-        "0c820dd9-e935-52a0-8d1e-cecdb814b75e"
-    ],
-    "oai_set": "full",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[20.169200000000,49.144200000000],[20.169200000000,49.144200000000],[20.169200000000,49.144200000000],[20.169200000000,49.144200000000],[20.169200000000,49.144200000000]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "site"
-        },
-        {
-            "name": "emfiso_pointer_record"
-        },
-        {
-            "name": "atmospheric parameter"
-        },
-        {
-            "name": "precipitation intensity"
-        },
-        {
-            "name": "wind direction"
-        },
-        {
-            "name": "wind speed"
-        },
-        {
-            "name": "biological parameter"
-        },
-        {
-            "name": "plant transpiration"
-        },
-        {
-            "name": "ecosystem parameter"
-        },
-        {
-            "name": "ground net primary production"
-        },
-        {
-            "name": "fire severity index"
-        },
-        {
-            "name": "disturbance pattern"
-        }
-    ],
-    "title": [
-        "Tatra National Park"
-    ],
-    "url": "https://deims.org/node/218"
-}
\ No newline at end of file
diff --git a/oaitestdata/deims-iso19139/full_1/json/0c9f432c-5fee-551e-9dcb-aeb383d858a1.json b/oaitestdata/deims-iso19139/full_1/json/0c9f432c-5fee-551e-9dcb-aeb383d858a1.json
deleted file mode 100644
index ffe12f5a..00000000
--- a/oaitestdata/deims-iso19139/full_1/json/0c9f432c-5fee-551e-9dcb-aeb383d858a1.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contact": [
-        "thomas.dirnboeck@umweltbundesamt.at",
-        "michael.mirtl@umweltbundesamt.at"
-    ],
-    "Contributor": "DEIMS-SDR | Site and Dataset registry deims.org",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "https://deims.org/pycsw/catalogue/csw?verb=GetRecord&metadataPrefix=iso19139&identifier=0c9f432c-5fee-551e-9dcb-aeb383d858a1",
-    "PID": "http://hdl.handle.net/11304/b1f94c36-eac3-11e5-9bb4-2b0aad496318",
-    "PublicationTimestamp": "2018-09-24T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "SpatialCoverage": "(48N-48N,14E-14E)",
-    "author": [
-        "Michael Mirtl",
-        "Thomas Dirnboeck"
-    ],
-    "fulltext": "ebde825e-7c7a-11e3-8832-005056ab003f;English;utf8;dataset;Thomas Dirnboeck;Environment Agency Austria (EAA);Spittelauer L\u00e4nde 5;Vienna;1090;AT;thomas.dirnboeck@umweltbundesamt.at;pointOfContact;Michael Mirtl;Environment Agency Austria (EAA);Spittelauer L\u00e4nde 5;Vienna;1090;AT;michael.mirtl@umweltbundesamt.at;pointOfContact;2018-09-24;ISO19115;2003/Cor.1:2006;EPSG:4326;http://www.opengis.net/def/crs/EPSG/0/4326;http://www.opengis.net/def/crs/EPSG/0/4258;LTER Z\u00f6belboden, Austria, Litterfall chemistry, 1993-2011;2018-09-24;publication;urn:ltereurope:inspire::8938:20735;LTER Z\u00f6belboden - Austria;Thomas Dirnboeck;Environment Agency Austria (EAA);Spittelauer L\u00e4nde 5;Vienna;1090;AT;thomas.dirnboeck@umweltbundesamt.at;pointOfContact;documentDigital;Litterfall chemistry data of the LTER station Z\u00f6belboden from the years 1993 to 2011;completed;Thomas Dirnboeck;Environment Agency Austria (EAA);Spittelauer L\u00e4nde 5;Vienna;1090;AT;thomas.dirnboeck@umweltbundesamt.at;pointOfContact;Michael Mirtl;Environment Agency Austria (EAA);Spittelauer L\u00e4nde 5;Vienna;1090;AT;michael.mirtl@umweltbundesamt.at;pointOfContact;continual;Representative area of sampling: plot scale Sampling frequency - sampling time span: yearly Sampling frequency - minimum sampling unit: other temporal resolution;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;2008-06-01;publication;Fagus sylvatica;Picea abies;Biological Classification;LTER Site;leaf nutrients;litterfall;LTER Controlled Vocabulary;The principal: Administration has granted the access and use permission: Free for access and use upon request;The principal: Research has granted the access and use permission: Free for access and use upon request;The principal: Public has granted the access and use permission: Free for access;The principal: Public has granted the access and use permission: Free for access and use upon request;eng;environment;14.431570000000;14.428830000000;47.859480000000;47.861200000000;Representative area of sampling: plot scale;ground condition;1992-12-31;2011-12-30;http://hdl.handle.net/11304/b1f94c36-eac3-11e5-9bb4-2b0aad496318;WWW:LINK-1.0-http--link;B2Share Download Link;dataset;Conformity_001;INSPIRE;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;publication;See the referenced specification;Method description: empty. Method URL: http://www.syke.fi/nature/icpim. Instrumentation:;Metadata Access Constraints: none Metadata Use Constraints: none;annually",
-    "group": "deims",
-    "groups": [
-        {
-            "name": "deims"
-        }
-    ],
-    "name": "0c9f432c-5fee-551e-9dcb-aeb383d858a1",
-    "notes": [
-        "Litterfall chemistry data of the LTER station Z\u00f6belboden from the years 1993 to 2011"
-    ],
-    "oai_identifier": [
-        "0c9f432c-5fee-551e-9dcb-aeb383d858a1"
-    ],
-    "oai_set": "full",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[14.431570000000,47.859480000000],[14.431570000000,47.861200000000],[14.428830000000,47.861200000000],[14.428830000000,47.859480000000],[14.431570000000,47.859480000000]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Fagus sylvatica"
-        },
-        {
-            "name": "Picea abies"
-        },
-        {
-            "name": "LTER Site"
-        },
-        {
-            "name": "leaf nutrients"
-        },
-        {
-            "name": "litterfall"
-        }
-    ],
-    "title": [
-        "LTER Z\u00f6belboden, Austria, Litterfall chemistry, 1993-2011"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/egidatahub-oai_dc/SET_1/json/028daf1b-e2be-58e0-9dcf-3fb3e6a33b33.json b/oaitestdata/egidatahub-oai_dc/SET_1/json/028daf1b-e2be-58e0-9dcf-3fb3e6a33b33.json
deleted file mode 100644
index d0e0893c..00000000
--- a/oaitestdata/egidatahub-oai_dc/SET_1/json/028daf1b-e2be-58e0-9dcf-3fb3e6a33b33.json
+++ /dev/null
@@ -1,28 +0,0 @@
-{
-    "Contributor": [
-        "EGI-DataHub"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://datahub.egi.eu/oai_pmh?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datahub.egi.eu:fe5570cb067b47dbcb2725fc47336a7d",
-    "MetadataAccess": [
-        "oai:datahub.egi.eu:fe5570cb067b47dbcb2725fc47336a7d"
-    ],
-    "PID": "http://hdl.handle.net/21.T15999/3Byz9Cw",
-    "fulltext": "oai:datahub.egi.eu:fe5570cb067b47dbcb2725fc47336a7d;2019-10-01T10:53:31Z;http://hdl.handle.net/21.T15999/3Byz9Cw;https://datahub.egi.eu/share/fd6291ddf60efa21f6202a55242a6e68",
-    "group": "egidatahub",
-    "groups": [
-        {
-            "name": "egidatahub"
-        }
-    ],
-    "name": "028daf1b-e2be-58e0-9dcf-3fb3e6a33b33",
-    "oai_identifier": [
-        "oai:datahub.egi.eu:fe5570cb067b47dbcb2725fc47336a7d"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": "Not stated",
-    "url": "https://datahub.egi.eu/share/fd6291ddf60efa21f6202a55242a6e68"
-}
\ No newline at end of file
diff --git a/oaitestdata/egidatahub-oai_dc/SET_1/json/1ab95d4a-cc36-566c-bd1a-b59eb14a657b.json b/oaitestdata/egidatahub-oai_dc/SET_1/json/1ab95d4a-cc36-566c-bd1a-b59eb14a657b.json
deleted file mode 100644
index ee0e1fc5..00000000
--- a/oaitestdata/egidatahub-oai_dc/SET_1/json/1ab95d4a-cc36-566c-bd1a-b59eb14a657b.json
+++ /dev/null
@@ -1,28 +0,0 @@
-{
-    "Contributor": [
-        "EGI-DataHub"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://datahub.egi.eu/oai_pmh?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datahub.egi.eu:75399de631f5eba551ae7b3fd66437b1",
-    "MetadataAccess": [
-        "oai:datahub.egi.eu:75399de631f5eba551ae7b3fd66437b1"
-    ],
-    "PID": "http://hdl.handle.net/21.T15999/qVk6JWQ",
-    "fulltext": "oai:datahub.egi.eu:75399de631f5eba551ae7b3fd66437b1;2019-11-29T15:15:02Z;http://hdl.handle.net/21.T15999/qVk6JWQ;https://datahub.egi.eu/share/3431fb75b0cac3df8767547706dc1755",
-    "group": "egidatahub",
-    "groups": [
-        {
-            "name": "egidatahub"
-        }
-    ],
-    "name": "1ab95d4a-cc36-566c-bd1a-b59eb14a657b",
-    "oai_identifier": [
-        "oai:datahub.egi.eu:75399de631f5eba551ae7b3fd66437b1"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": "Not stated",
-    "url": "https://datahub.egi.eu/share/3431fb75b0cac3df8767547706dc1755"
-}
\ No newline at end of file
diff --git a/oaitestdata/egidatahub-oai_dc/SET_1/json/2417fad6-3dca-5781-b8e1-9899a3794c86.json b/oaitestdata/egidatahub-oai_dc/SET_1/json/2417fad6-3dca-5781-b8e1-9899a3794c86.json
deleted file mode 100644
index 9080c594..00000000
--- a/oaitestdata/egidatahub-oai_dc/SET_1/json/2417fad6-3dca-5781-b8e1-9899a3794c86.json
+++ /dev/null
@@ -1,28 +0,0 @@
-{
-    "Contributor": [
-        "EGI-DataHub"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://datahub.egi.eu/oai_pmh?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datahub.egi.eu:7926985caa5935edad990b9bc858cea0",
-    "MetadataAccess": [
-        "oai:datahub.egi.eu:7926985caa5935edad990b9bc858cea0"
-    ],
-    "PID": "http://hdl.handle.net/21.T15999/RhrNS9I",
-    "fulltext": "oai:datahub.egi.eu:7926985caa5935edad990b9bc858cea0;2018-11-09T13:41:03Z;http://hdl.handle.net/21.T15999/RhrNS9I;https://datahub.egi.eu/share/9be5b76f58c0d9a4ceb26f23aa24b97c",
-    "group": "egidatahub",
-    "groups": [
-        {
-            "name": "egidatahub"
-        }
-    ],
-    "name": "2417fad6-3dca-5781-b8e1-9899a3794c86",
-    "oai_identifier": [
-        "oai:datahub.egi.eu:7926985caa5935edad990b9bc858cea0"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": "Not stated",
-    "url": "https://datahub.egi.eu/share/9be5b76f58c0d9a4ceb26f23aa24b97c"
-}
\ No newline at end of file
diff --git a/oaitestdata/egidatahub-oai_dc/SET_1/json/29cb9f83-e478-557b-9dba-53c274ba2af5.json b/oaitestdata/egidatahub-oai_dc/SET_1/json/29cb9f83-e478-557b-9dba-53c274ba2af5.json
deleted file mode 100644
index c85aecf8..00000000
--- a/oaitestdata/egidatahub-oai_dc/SET_1/json/29cb9f83-e478-557b-9dba-53c274ba2af5.json
+++ /dev/null
@@ -1,28 +0,0 @@
-{
-    "Contributor": [
-        "EGI-DataHub"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://datahub.egi.eu/oai_pmh?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datahub.egi.eu:df6518fa264875352101d46d0c7d708e",
-    "MetadataAccess": [
-        "oai:datahub.egi.eu:df6518fa264875352101d46d0c7d708e"
-    ],
-    "PID": "http://hdl.handle.net/21.T15999/v9WjPIo",
-    "fulltext": "oai:datahub.egi.eu:df6518fa264875352101d46d0c7d708e;2019-01-24T14:25:54Z;http://hdl.handle.net/21.T15999/v9WjPIo;https://datahub.egi.eu/share/249999f24870d87afb731e524209306c",
-    "group": "egidatahub",
-    "groups": [
-        {
-            "name": "egidatahub"
-        }
-    ],
-    "name": "29cb9f83-e478-557b-9dba-53c274ba2af5",
-    "oai_identifier": [
-        "oai:datahub.egi.eu:df6518fa264875352101d46d0c7d708e"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": "Not stated",
-    "url": "https://datahub.egi.eu/share/249999f24870d87afb731e524209306c"
-}
\ No newline at end of file
diff --git a/oaitestdata/egidatahub-oai_dc/SET_1/json/2f8c1bea-c853-5b90-93c0-3abe42431e4e.json b/oaitestdata/egidatahub-oai_dc/SET_1/json/2f8c1bea-c853-5b90-93c0-3abe42431e4e.json
deleted file mode 100644
index bbd66a5f..00000000
--- a/oaitestdata/egidatahub-oai_dc/SET_1/json/2f8c1bea-c853-5b90-93c0-3abe42431e4e.json
+++ /dev/null
@@ -1,28 +0,0 @@
-{
-    "Contributor": [
-        "EGI-DataHub"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://datahub.egi.eu/oai_pmh?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datahub.egi.eu:497232d36561c5482d75aa7187f45c1c",
-    "MetadataAccess": [
-        "oai:datahub.egi.eu:497232d36561c5482d75aa7187f45c1c"
-    ],
-    "PID": "http://hdl.handle.net/21.T15999/QBhvvs8",
-    "fulltext": "oai:datahub.egi.eu:497232d36561c5482d75aa7187f45c1c;2019-01-24T14:25:13Z;http://hdl.handle.net/21.T15999/QBhvvs8;https://datahub.egi.eu/share/249999f24870d87afb731e524209306c",
-    "group": "egidatahub",
-    "groups": [
-        {
-            "name": "egidatahub"
-        }
-    ],
-    "name": "2f8c1bea-c853-5b90-93c0-3abe42431e4e",
-    "oai_identifier": [
-        "oai:datahub.egi.eu:497232d36561c5482d75aa7187f45c1c"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": "Not stated",
-    "url": "https://datahub.egi.eu/share/249999f24870d87afb731e524209306c"
-}
\ No newline at end of file
diff --git a/oaitestdata/egidatahub-oai_dc/SET_1/json/3d0c278c-47d3-5dee-9a56-43b1a5b5d3dd.json b/oaitestdata/egidatahub-oai_dc/SET_1/json/3d0c278c-47d3-5dee-9a56-43b1a5b5d3dd.json
deleted file mode 100644
index 57085314..00000000
--- a/oaitestdata/egidatahub-oai_dc/SET_1/json/3d0c278c-47d3-5dee-9a56-43b1a5b5d3dd.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Contributor": [
-        "EGI-DataHub"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "video/quicktime"
-    ],
-    "MetaDataAccess": "http://datahub.egi.eu/oai_pmh?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datahub.egi.eu:08758f6dd71f731b262adefad1f50a51",
-    "MetadataAccess": [
-        "oai:datahub.egi.eu:08758f6dd71f731b262adefad1f50a51"
-    ],
-    "PID": "http://hdl.handle.net/21.T15999/Fw2lYnA",
-    "PublicationTimestamp": "2018-11-12T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Rights": [
-        "https://creativecommons.org/licenses/by-nc-nd/4.0/"
-    ],
-    "author": [
-        "Bartosz Kryza"
-    ],
-    "fulltext": "oai:datahub.egi.eu:08758f6dd71f731b262adefad1f50a51;2018-11-12T20:19:20Z;EGI-DataHub Open Data Publishing With PID Demo;Bartosz Kryza;Demonstration;This video contains a demonstration of open data publishing using EGI-DataHub along with automatic PID handle generation.;2018-11-12;video/quicktime;https://creativecommons.org/licenses/by-nc-nd/4.0/;http://hdl.handle.net/21.T15999/Fw2lYnA;https://datahub.egi.eu/share/dec6359cdf03b3a7405ac75b70a4cecb",
-    "group": "egidatahub",
-    "groups": [
-        {
-            "name": "egidatahub"
-        }
-    ],
-    "name": "3d0c278c-47d3-5dee-9a56-43b1a5b5d3dd",
-    "notes": [
-        "This video contains a demonstration of open data publishing using EGI-DataHub along with automatic PID handle generation."
-    ],
-    "oai_identifier": [
-        "oai:datahub.egi.eu:08758f6dd71f731b262adefad1f50a51"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "This video contains a demonstration of open data publishing using EGI-DataHub along with automatic PID handle generation."
-    ],
-    "url": "https://datahub.egi.eu/share/dec6359cdf03b3a7405ac75b70a4cecb"
-}
\ No newline at end of file
diff --git a/oaitestdata/egidatahub-oai_dc/SET_1/json/414c63b8-ef9c-5450-ae42-b90aebbcdf07.json b/oaitestdata/egidatahub-oai_dc/SET_1/json/414c63b8-ef9c-5450-ae42-b90aebbcdf07.json
deleted file mode 100644
index 5b9cb9c7..00000000
--- a/oaitestdata/egidatahub-oai_dc/SET_1/json/414c63b8-ef9c-5450-ae42-b90aebbcdf07.json
+++ /dev/null
@@ -1,28 +0,0 @@
-{
-    "Contributor": [
-        "EGI-DataHub"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://datahub.egi.eu/oai_pmh?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datahub.egi.eu:40d0da7eda2b879e41e0d0671d4f75ae",
-    "MetadataAccess": [
-        "oai:datahub.egi.eu:40d0da7eda2b879e41e0d0671d4f75ae"
-    ],
-    "PID": "http://hdl.handle.net/21.T15999/GZvKG70",
-    "fulltext": "oai:datahub.egi.eu:40d0da7eda2b879e41e0d0671d4f75ae;2019-01-24T15:16:13Z;http://hdl.handle.net/21.T15999/GZvKG70;https://datahub.egi.eu/share/1596964c6111f77835e075dcc08d5e5a",
-    "group": "egidatahub",
-    "groups": [
-        {
-            "name": "egidatahub"
-        }
-    ],
-    "name": "414c63b8-ef9c-5450-ae42-b90aebbcdf07",
-    "oai_identifier": [
-        "oai:datahub.egi.eu:40d0da7eda2b879e41e0d0671d4f75ae"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": "Not stated",
-    "url": "https://datahub.egi.eu/share/1596964c6111f77835e075dcc08d5e5a"
-}
\ No newline at end of file
diff --git a/oaitestdata/egidatahub-oai_dc/SET_1/json/44779ca9-3c22-52a4-9579-f60027fdfa08.json b/oaitestdata/egidatahub-oai_dc/SET_1/json/44779ca9-3c22-52a4-9579-f60027fdfa08.json
deleted file mode 100644
index 0a8ec9bc..00000000
--- a/oaitestdata/egidatahub-oai_dc/SET_1/json/44779ca9-3c22-52a4-9579-f60027fdfa08.json
+++ /dev/null
@@ -1,28 +0,0 @@
-{
-    "Contributor": [
-        "EGI-DataHub"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://datahub.egi.eu/oai_pmh?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datahub.egi.eu:0144124d61b9708a61c3cf386757ca61",
-    "MetadataAccess": [
-        "oai:datahub.egi.eu:0144124d61b9708a61c3cf386757ca61"
-    ],
-    "PID": "http://hdl.handle.net/21.T15999/ILJOtQQ",
-    "fulltext": "oai:datahub.egi.eu:0144124d61b9708a61c3cf386757ca61;2019-01-24T14:24:51Z;http://hdl.handle.net/21.T15999/ILJOtQQ;https://datahub.egi.eu/share/249999f24870d87afb731e524209306c",
-    "group": "egidatahub",
-    "groups": [
-        {
-            "name": "egidatahub"
-        }
-    ],
-    "name": "44779ca9-3c22-52a4-9579-f60027fdfa08",
-    "oai_identifier": [
-        "oai:datahub.egi.eu:0144124d61b9708a61c3cf386757ca61"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": "Not stated",
-    "url": "https://datahub.egi.eu/share/249999f24870d87afb731e524209306c"
-}
\ No newline at end of file
diff --git a/oaitestdata/egidatahub-oai_dc/SET_1/json/500da8c0-735a-5a4f-aa4d-da1fb1b887e7.json b/oaitestdata/egidatahub-oai_dc/SET_1/json/500da8c0-735a-5a4f-aa4d-da1fb1b887e7.json
deleted file mode 100644
index 8aa0a174..00000000
--- a/oaitestdata/egidatahub-oai_dc/SET_1/json/500da8c0-735a-5a4f-aa4d-da1fb1b887e7.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Contributor": [
-        "EGI-DataHub"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "text/plain"
-    ],
-    "MetaDataAccess": "http://datahub.egi.eu/oai_pmh?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datahub.egi.eu:58f8af99443e02334cdd289f05dd2441",
-    "MetadataAccess": [
-        "oai:datahub.egi.eu:58f8af99443e02334cdd289f05dd2441"
-    ],
-    "PID": "http://hdl.handle.net/21.T15999/kJdyEFE",
-    "PublicationTimestamp": "2018-01-17T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "author": [
-        "Baptiste Grenier"
-    ],
-    "fulltext": "oai:datahub.egi.eu:58f8af99443e02334cdd289f05dd2441;2019-01-18T09:51:25Z;CS3;Baptiste Grenier;CS3 Dataset;CS3 Dataset;2018-01-17;Text;text/plain;http://hdl.handle.net/21.T15999/kJdyEFE;https://datahub.egi.eu/share/ae2ddade147fbdb75c3343cd3cb5387e",
-    "group": "egidatahub",
-    "groups": [
-        {
-            "name": "egidatahub"
-        }
-    ],
-    "name": "500da8c0-735a-5a4f-aa4d-da1fb1b887e7",
-    "notes": [
-        "CS3 Dataset"
-    ],
-    "oai_identifier": [
-        "oai:datahub.egi.eu:58f8af99443e02334cdd289f05dd2441"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "CS3 Dataset"
-    ],
-    "url": "https://datahub.egi.eu/share/ae2ddade147fbdb75c3343cd3cb5387e"
-}
\ No newline at end of file
diff --git a/oaitestdata/egidatahub-oai_dc/SET_1/json/5185d6a0-601a-5aeb-a526-73a7ff3580cd.json b/oaitestdata/egidatahub-oai_dc/SET_1/json/5185d6a0-601a-5aeb-a526-73a7ff3580cd.json
deleted file mode 100644
index 486cf786..00000000
--- a/oaitestdata/egidatahub-oai_dc/SET_1/json/5185d6a0-601a-5aeb-a526-73a7ff3580cd.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Contributor": [
-        "EGI-DataHub"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "text/plain"
-    ],
-    "MetaDataAccess": "http://datahub.egi.eu/oai_pmh?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datahub.egi.eu:32d5920b5aa9961188d7073c2eff9a6c",
-    "MetadataAccess": [
-        "oai:datahub.egi.eu:32d5920b5aa9961188d7073c2eff9a6c"
-    ],
-    "PID": "http://hdl.handle.net/21.T15999/hxU1MO4",
-    "PublicationTimestamp": "2018-01-22T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "author": [
-        "Baptiste Grenier"
-    ],
-    "fulltext": "oai:datahub.egi.eu:32d5920b5aa9961188d7073c2eff9a6c;2019-01-22T15:11:39Z;CS3 input files;Baptiste Grenier;CS3 input files;CS3 input files to be used for the CS3 demontration;2018-01-22;Text;text/plain;http://hdl.handle.net/21.T15999/hxU1MO4;https://datahub.egi.eu/share/49519f17a052509694e4ae8bec328d52",
-    "group": "egidatahub",
-    "groups": [
-        {
-            "name": "egidatahub"
-        }
-    ],
-    "name": "5185d6a0-601a-5aeb-a526-73a7ff3580cd",
-    "notes": [
-        "CS3 input files to be used for the CS3 demontration"
-    ],
-    "oai_identifier": [
-        "oai:datahub.egi.eu:32d5920b5aa9961188d7073c2eff9a6c"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "CS3 input files to be used for the CS3 demontration"
-    ],
-    "url": "https://datahub.egi.eu/share/49519f17a052509694e4ae8bec328d52"
-}
\ No newline at end of file
diff --git a/oaitestdata/egidatahub-oai_dc/SET_1/json/5bda421b-d083-5c5e-9489-cceab366f8ff.json b/oaitestdata/egidatahub-oai_dc/SET_1/json/5bda421b-d083-5c5e-9489-cceab366f8ff.json
deleted file mode 100644
index 8d1b4594..00000000
--- a/oaitestdata/egidatahub-oai_dc/SET_1/json/5bda421b-d083-5c5e-9489-cceab366f8ff.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Contributor": [
-        "EGI-DataHub"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "text/plain"
-    ],
-    "MetaDataAccess": "http://datahub.egi.eu/oai_pmh?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datahub.egi.eu:ea11b0c59a31f959128f65d73bff9e22",
-    "MetadataAccess": [
-        "oai:datahub.egi.eu:ea11b0c59a31f959128f65d73bff9e22"
-    ],
-    "PID": "http://hdl.handle.net/21.T15999/hzXuEO4",
-    "PublicationTimestamp": "2018-01-22T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "author": [
-        "Baptiste Grenier"
-    ],
-    "fulltext": "oai:datahub.egi.eu:ea11b0c59a31f959128f65d73bff9e22;2019-01-22T15:12:55Z;CS3 input files;Baptiste Grenier;CS3 input files;CS3 input files to be used for the CS3 demontration;2018-01-22;Text;text/plain;http://hdl.handle.net/21.T15999/hzXuEO4;https://datahub.egi.eu/share/49519f17a052509694e4ae8bec328d52",
-    "group": "egidatahub",
-    "groups": [
-        {
-            "name": "egidatahub"
-        }
-    ],
-    "name": "5bda421b-d083-5c5e-9489-cceab366f8ff",
-    "notes": [
-        "CS3 input files to be used for the CS3 demontration"
-    ],
-    "oai_identifier": [
-        "oai:datahub.egi.eu:ea11b0c59a31f959128f65d73bff9e22"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "CS3 input files to be used for the CS3 demontration"
-    ],
-    "url": "https://datahub.egi.eu/share/49519f17a052509694e4ae8bec328d52"
-}
\ No newline at end of file
diff --git a/oaitestdata/egidatahub-oai_dc/SET_1/json/5d14a4dd-2be8-56de-a715-326b1402cf93.json b/oaitestdata/egidatahub-oai_dc/SET_1/json/5d14a4dd-2be8-56de-a715-326b1402cf93.json
deleted file mode 100644
index 4e230498..00000000
--- a/oaitestdata/egidatahub-oai_dc/SET_1/json/5d14a4dd-2be8-56de-a715-326b1402cf93.json
+++ /dev/null
@@ -1,28 +0,0 @@
-{
-    "Contributor": [
-        "EGI-DataHub"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://datahub.egi.eu/oai_pmh?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datahub.egi.eu:6f3757f390db5c1af2b73a18a9a70c30",
-    "MetadataAccess": [
-        "oai:datahub.egi.eu:6f3757f390db5c1af2b73a18a9a70c30"
-    ],
-    "PID": "http://hdl.handle.net/21.T15999/6uiWjLU",
-    "fulltext": "oai:datahub.egi.eu:6f3757f390db5c1af2b73a18a9a70c30;2019-12-02T14:34:35Z;http://hdl.handle.net/21.T15999/6uiWjLU;https://datahub.egi.eu/share/33798796391866ed7661f602be0e203e",
-    "group": "egidatahub",
-    "groups": [
-        {
-            "name": "egidatahub"
-        }
-    ],
-    "name": "5d14a4dd-2be8-56de-a715-326b1402cf93",
-    "oai_identifier": [
-        "oai:datahub.egi.eu:6f3757f390db5c1af2b73a18a9a70c30"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": "Not stated",
-    "url": "https://datahub.egi.eu/share/33798796391866ed7661f602be0e203e"
-}
\ No newline at end of file
diff --git a/oaitestdata/egidatahub-oai_dc/SET_1/json/74452e30-2038-52a6-a277-57d24e0722a3.json b/oaitestdata/egidatahub-oai_dc/SET_1/json/74452e30-2038-52a6-a277-57d24e0722a3.json
deleted file mode 100644
index c7baba96..00000000
--- a/oaitestdata/egidatahub-oai_dc/SET_1/json/74452e30-2038-52a6-a277-57d24e0722a3.json
+++ /dev/null
@@ -1,42 +0,0 @@
-{
-    "Contact": [
-        "Cyfronet"
-    ],
-    "Contributor": [
-        "EGI-DataHub"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://datahub.egi.eu/oai_pmh?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datahub.egi.eu:943383795cfc46e420a0205018440be5",
-    "MetadataAccess": [
-        "oai:datahub.egi.eu:943383795cfc46e420a0205018440be5"
-    ],
-    "PID": "http://hdl.handle.net/21.T15999/QBFl7Pw",
-    "Publisher": [
-        "Cyfronet"
-    ],
-    "author": [
-        "Lukasz Dutka"
-    ],
-    "fulltext": "oai:datahub.egi.eu:943383795cfc46e420a0205018440be5;2019-04-11T21:03:29Z;Test dataset;Lukasz Dutka;Demonstration;This is to show publication of PIDs.;Cyfronet;http://hdl.handle.net/21.T15999/QBFl7Pw;https://datahub.egi.eu/share/dec6359cdf03b3a7405ac75b70a4cecb",
-    "group": "egidatahub",
-    "groups": [
-        {
-            "name": "egidatahub"
-        }
-    ],
-    "name": "74452e30-2038-52a6-a277-57d24e0722a3",
-    "notes": [
-        "This is to show publication of PIDs."
-    ],
-    "oai_identifier": [
-        "oai:datahub.egi.eu:943383795cfc46e420a0205018440be5"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "This is to show publication of PIDs."
-    ],
-    "url": "https://datahub.egi.eu/share/dec6359cdf03b3a7405ac75b70a4cecb"
-}
\ No newline at end of file
diff --git a/oaitestdata/egidatahub-oai_dc/SET_1/json/76cf99bd-f9dd-5202-a7ef-9ebea8899098.json b/oaitestdata/egidatahub-oai_dc/SET_1/json/76cf99bd-f9dd-5202-a7ef-9ebea8899098.json
deleted file mode 100644
index ab83ddaf..00000000
--- a/oaitestdata/egidatahub-oai_dc/SET_1/json/76cf99bd-f9dd-5202-a7ef-9ebea8899098.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Contributor": [
-        "EGI-DataHub"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "application/x-ipynb+json"
-    ],
-    "MetaDataAccess": "http://datahub.egi.eu/oai_pmh?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datahub.egi.eu:1d328b99d5fe4fa9d258442ff4ca8969",
-    "MetadataAccess": [
-        "oai:datahub.egi.eu:1d328b99d5fe4fa9d258442ff4ca8969"
-    ],
-    "PID": "http://hdl.handle.net/21.T15999/tQAc2eo",
-    "PublicationTimestamp": "2019-01-24T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "ResourceType": [
-        "Jupyter Notebook"
-    ],
-    "author": [
-        "Baptiste Grenier"
-    ],
-    "fulltext": "oai:datahub.egi.eu:1d328b99d5fe4fa9d258442ff4ca8969;2019-01-24T15:20:21Z;CS3 notebooks;Baptiste Grenier;Notebook presented at the CS3 conference;Notebook presented at the CS3 conference: Open Data analysis with EOSC-hub services;2019-01-24;Jupyter Notebook;application/x-ipynb+json;http://hdl.handle.net/21.T15999/tQAc2eo;https://datahub.egi.eu/share/1596964c6111f77835e075dcc08d5e5a",
-    "group": "egidatahub",
-    "groups": [
-        {
-            "name": "egidatahub"
-        }
-    ],
-    "name": "76cf99bd-f9dd-5202-a7ef-9ebea8899098",
-    "notes": [
-        "Notebook presented at the CS3 conference: Open Data analysis with EOSC-hub services"
-    ],
-    "oai_identifier": [
-        "oai:datahub.egi.eu:1d328b99d5fe4fa9d258442ff4ca8969"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Notebook presented at the CS3 conference: Open Data analysis with EOSC-hub services"
-    ],
-    "url": "https://datahub.egi.eu/share/1596964c6111f77835e075dcc08d5e5a"
-}
\ No newline at end of file
diff --git a/oaitestdata/egidatahub-oai_dc/SET_1/json/9dac24f6-d801-5d9d-8de9-a4d3d7d12148.json b/oaitestdata/egidatahub-oai_dc/SET_1/json/9dac24f6-d801-5d9d-8de9-a4d3d7d12148.json
deleted file mode 100644
index 73088ec2..00000000
--- a/oaitestdata/egidatahub-oai_dc/SET_1/json/9dac24f6-d801-5d9d-8de9-a4d3d7d12148.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Contributor": [
-        "EGI-DataHub"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "PNG"
-    ],
-    "MetaDataAccess": "http://datahub.egi.eu/oai_pmh?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datahub.egi.eu:1cab8cd08e28be9bb37d47e0be1fbf2e",
-    "MetadataAccess": [
-        "oai:datahub.egi.eu:1cab8cd08e28be9bb37d47e0be1fbf2e"
-    ],
-    "PID": "http://hdl.handle.net/21.T15999/zppPvhg",
-    "PublicationTimestamp": "2018-11-12T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Rights": [
-        "CC-0"
-    ],
-    "author": [
-        "Bartosz Kryza"
-    ],
-    "fulltext": "oai:datahub.egi.eu:1cab8cd08e28be9bb37d47e0be1fbf2e;2018-11-12T20:03:55Z;White Noise Image Collection;Bartosz Kryza;Demonstration;This data set contains 10 images containing white noise, including script used to generate them.;2018-11-12;PNG;CC-0;http://hdl.handle.net/21.T15999/zppPvhg;https://datahub.egi.eu/share/d7f1f5e7090651a79699ff0301fb6fbe",
-    "group": "egidatahub",
-    "groups": [
-        {
-            "name": "egidatahub"
-        }
-    ],
-    "name": "9dac24f6-d801-5d9d-8de9-a4d3d7d12148",
-    "notes": [
-        "This data set contains 10 images containing white noise, including script used to generate them."
-    ],
-    "oai_identifier": [
-        "oai:datahub.egi.eu:1cab8cd08e28be9bb37d47e0be1fbf2e"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "This data set contains 10 images containing white noise, including script used to generate them."
-    ],
-    "url": "https://datahub.egi.eu/share/d7f1f5e7090651a79699ff0301fb6fbe"
-}
\ No newline at end of file
diff --git a/oaitestdata/egidatahub-oai_dc/SET_1/json/9fb3c2f8-86cf-5722-bdd1-b8d7c5a1f5cd.json b/oaitestdata/egidatahub-oai_dc/SET_1/json/9fb3c2f8-86cf-5722-bdd1-b8d7c5a1f5cd.json
deleted file mode 100644
index 18b21939..00000000
--- a/oaitestdata/egidatahub-oai_dc/SET_1/json/9fb3c2f8-86cf-5722-bdd1-b8d7c5a1f5cd.json
+++ /dev/null
@@ -1,28 +0,0 @@
-{
-    "Contributor": [
-        "EGI-DataHub"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://datahub.egi.eu/oai_pmh?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datahub.egi.eu:876c628c2b34b21808b9bb44f4c0b998",
-    "MetadataAccess": [
-        "oai:datahub.egi.eu:876c628c2b34b21808b9bb44f4c0b998"
-    ],
-    "PID": "http://hdl.handle.net/21.T15999/v6EAbiY",
-    "fulltext": "oai:datahub.egi.eu:876c628c2b34b21808b9bb44f4c0b998;2019-01-21T14:12:05Z;http://hdl.handle.net/21.T15999/v6EAbiY;https://datahub.egi.eu/share/33f656bb66977e714833a7371f66773b",
-    "group": "egidatahub",
-    "groups": [
-        {
-            "name": "egidatahub"
-        }
-    ],
-    "name": "9fb3c2f8-86cf-5722-bdd1-b8d7c5a1f5cd",
-    "oai_identifier": [
-        "oai:datahub.egi.eu:876c628c2b34b21808b9bb44f4c0b998"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": "Not stated",
-    "url": "https://datahub.egi.eu/share/33f656bb66977e714833a7371f66773b"
-}
\ No newline at end of file
diff --git a/oaitestdata/egidatahub-oai_dc/SET_1/json/b53a8b2d-6af6-5023-b34b-0a3feca7c046.json b/oaitestdata/egidatahub-oai_dc/SET_1/json/b53a8b2d-6af6-5023-b34b-0a3feca7c046.json
deleted file mode 100644
index 260c959c..00000000
--- a/oaitestdata/egidatahub-oai_dc/SET_1/json/b53a8b2d-6af6-5023-b34b-0a3feca7c046.json
+++ /dev/null
@@ -1,28 +0,0 @@
-{
-    "Contributor": [
-        "EGI-DataHub"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://datahub.egi.eu/oai_pmh?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datahub.egi.eu:e6fb2973d3acbc2dec3af7b98657eb4a",
-    "MetadataAccess": [
-        "oai:datahub.egi.eu:e6fb2973d3acbc2dec3af7b98657eb4a"
-    ],
-    "PID": "http://hdl.handle.net/21.T15999/u0cPEEc",
-    "fulltext": "oai:datahub.egi.eu:e6fb2973d3acbc2dec3af7b98657eb4a;2019-10-01T10:53:09Z;http://hdl.handle.net/21.T15999/u0cPEEc;https://datahub.egi.eu/share/ecf3bab9bcd82b081fa33c77af29893f",
-    "group": "egidatahub",
-    "groups": [
-        {
-            "name": "egidatahub"
-        }
-    ],
-    "name": "b53a8b2d-6af6-5023-b34b-0a3feca7c046",
-    "oai_identifier": [
-        "oai:datahub.egi.eu:e6fb2973d3acbc2dec3af7b98657eb4a"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": "Not stated",
-    "url": "https://datahub.egi.eu/share/ecf3bab9bcd82b081fa33c77af29893f"
-}
\ No newline at end of file
diff --git a/oaitestdata/egidatahub-oai_dc/SET_1/json/bccbe1ed-c6b1-5d0e-a25d-7a26d0d4abe9.json b/oaitestdata/egidatahub-oai_dc/SET_1/json/bccbe1ed-c6b1-5d0e-a25d-7a26d0d4abe9.json
deleted file mode 100644
index 74c24e27..00000000
--- a/oaitestdata/egidatahub-oai_dc/SET_1/json/bccbe1ed-c6b1-5d0e-a25d-7a26d0d4abe9.json
+++ /dev/null
@@ -1,28 +0,0 @@
-{
-    "Contributor": [
-        "EGI-DataHub"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://datahub.egi.eu/oai_pmh?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datahub.egi.eu:d8e93b8e96d2a7ee25dbb3aa3b9ff96d",
-    "MetadataAccess": [
-        "oai:datahub.egi.eu:d8e93b8e96d2a7ee25dbb3aa3b9ff96d"
-    ],
-    "PID": "http://hdl.handle.net/21.T15999/EjWFAJw",
-    "fulltext": "oai:datahub.egi.eu:d8e93b8e96d2a7ee25dbb3aa3b9ff96d;2019-01-24T14:20:04Z;http://hdl.handle.net/21.T15999/EjWFAJw;https://datahub.egi.eu/share/249999f24870d87afb731e524209306c",
-    "group": "egidatahub",
-    "groups": [
-        {
-            "name": "egidatahub"
-        }
-    ],
-    "name": "bccbe1ed-c6b1-5d0e-a25d-7a26d0d4abe9",
-    "oai_identifier": [
-        "oai:datahub.egi.eu:d8e93b8e96d2a7ee25dbb3aa3b9ff96d"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": "Not stated",
-    "url": "https://datahub.egi.eu/share/249999f24870d87afb731e524209306c"
-}
\ No newline at end of file
diff --git a/oaitestdata/egidatahub-oai_dc/SET_1/json/c0209778-14d9-5392-ad80-f07ccc47315c.json b/oaitestdata/egidatahub-oai_dc/SET_1/json/c0209778-14d9-5392-ad80-f07ccc47315c.json
deleted file mode 100644
index c20ecb09..00000000
--- a/oaitestdata/egidatahub-oai_dc/SET_1/json/c0209778-14d9-5392-ad80-f07ccc47315c.json
+++ /dev/null
@@ -1,28 +0,0 @@
-{
-    "Contributor": [
-        "EGI-DataHub"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://datahub.egi.eu/oai_pmh?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datahub.egi.eu:a394e2ef8cde67cd8e808f9809c1dadb",
-    "MetadataAccess": [
-        "oai:datahub.egi.eu:a394e2ef8cde67cd8e808f9809c1dadb"
-    ],
-    "PID": "http://hdl.handle.net/21.T15999/S1H6MFo",
-    "fulltext": "oai:datahub.egi.eu:a394e2ef8cde67cd8e808f9809c1dadb;2019-01-24T14:50:43Z;http://hdl.handle.net/21.T15999/S1H6MFo;https://datahub.egi.eu/share/1596964c6111f77835e075dcc08d5e5a",
-    "group": "egidatahub",
-    "groups": [
-        {
-            "name": "egidatahub"
-        }
-    ],
-    "name": "c0209778-14d9-5392-ad80-f07ccc47315c",
-    "oai_identifier": [
-        "oai:datahub.egi.eu:a394e2ef8cde67cd8e808f9809c1dadb"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": "Not stated",
-    "url": "https://datahub.egi.eu/share/1596964c6111f77835e075dcc08d5e5a"
-}
\ No newline at end of file
diff --git a/oaitestdata/egidatahub-oai_dc/SET_1/json/c1a3df42-00bb-5ecf-8f46-34e0e2d82461.json b/oaitestdata/egidatahub-oai_dc/SET_1/json/c1a3df42-00bb-5ecf-8f46-34e0e2d82461.json
deleted file mode 100644
index 8a37698b..00000000
--- a/oaitestdata/egidatahub-oai_dc/SET_1/json/c1a3df42-00bb-5ecf-8f46-34e0e2d82461.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Contributor": [
-        "EGI-DataHub"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "application/x-ipynb+json"
-    ],
-    "MetaDataAccess": "http://datahub.egi.eu/oai_pmh?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datahub.egi.eu:f3ed3cea53d27e590be69ea814504f55",
-    "MetadataAccess": [
-        "oai:datahub.egi.eu:f3ed3cea53d27e590be69ea814504f55"
-    ],
-    "PID": "http://hdl.handle.net/21.T15999/dXjo15U",
-    "PublicationTimestamp": "2019-01-24T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "ResourceType": [
-        "Jupyter Notebook"
-    ],
-    "author": [
-        "Baptiste Grenier"
-    ],
-    "fulltext": "oai:datahub.egi.eu:f3ed3cea53d27e590be69ea814504f55;2019-01-24T15:20:56Z;CS3 notebooks;Baptiste Grenier;Notebook presented at the CS3 conference;Notebook presented at the CS3 conference: Open Data analysis with EOSC-hub services;2019-01-24;Jupyter Notebook;application/x-ipynb+json;http://hdl.handle.net/21.T15999/dXjo15U;https://datahub.egi.eu/share/1596964c6111f77835e075dcc08d5e5a",
-    "group": "egidatahub",
-    "groups": [
-        {
-            "name": "egidatahub"
-        }
-    ],
-    "name": "c1a3df42-00bb-5ecf-8f46-34e0e2d82461",
-    "notes": [
-        "Notebook presented at the CS3 conference: Open Data analysis with EOSC-hub services"
-    ],
-    "oai_identifier": [
-        "oai:datahub.egi.eu:f3ed3cea53d27e590be69ea814504f55"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Notebook presented at the CS3 conference: Open Data analysis with EOSC-hub services"
-    ],
-    "url": "https://datahub.egi.eu/share/1596964c6111f77835e075dcc08d5e5a"
-}
\ No newline at end of file
diff --git a/oaitestdata/egidatahub-oai_dc/SET_1/json/d73fcc22-5502-564e-a9d7-cada1032d12b.json b/oaitestdata/egidatahub-oai_dc/SET_1/json/d73fcc22-5502-564e-a9d7-cada1032d12b.json
deleted file mode 100644
index a3652aa1..00000000
--- a/oaitestdata/egidatahub-oai_dc/SET_1/json/d73fcc22-5502-564e-a9d7-cada1032d12b.json
+++ /dev/null
@@ -1,28 +0,0 @@
-{
-    "Contributor": [
-        "EGI-DataHub"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://datahub.egi.eu/oai_pmh?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datahub.egi.eu:a9a181a3fef90e8c5576f5c63b287e81",
-    "MetadataAccess": [
-        "oai:datahub.egi.eu:a9a181a3fef90e8c5576f5c63b287e81"
-    ],
-    "PID": "http://hdl.handle.net/21.T15999/1QX0Ljw",
-    "fulltext": "oai:datahub.egi.eu:a9a181a3fef90e8c5576f5c63b287e81;2019-01-18T09:38:31Z;http://hdl.handle.net/21.T15999/1QX0Ljw;https://datahub.egi.eu/share/c56a69cfeab9eb11bbaa8224a60c8ebd",
-    "group": "egidatahub",
-    "groups": [
-        {
-            "name": "egidatahub"
-        }
-    ],
-    "name": "d73fcc22-5502-564e-a9d7-cada1032d12b",
-    "oai_identifier": [
-        "oai:datahub.egi.eu:a9a181a3fef90e8c5576f5c63b287e81"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": "Not stated",
-    "url": "https://datahub.egi.eu/share/c56a69cfeab9eb11bbaa8224a60c8ebd"
-}
\ No newline at end of file
diff --git a/oaitestdata/egidatahub-oai_dc/SET_1/json/db04aada-6225-5b93-9510-a4efc669964c.json b/oaitestdata/egidatahub-oai_dc/SET_1/json/db04aada-6225-5b93-9510-a4efc669964c.json
deleted file mode 100644
index efcb6ac8..00000000
--- a/oaitestdata/egidatahub-oai_dc/SET_1/json/db04aada-6225-5b93-9510-a4efc669964c.json
+++ /dev/null
@@ -1,28 +0,0 @@
-{
-    "Contributor": [
-        "EGI-DataHub"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://datahub.egi.eu/oai_pmh?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datahub.egi.eu:33ac2189db61a5a1b33d5338ee1184b4",
-    "MetadataAccess": [
-        "oai:datahub.egi.eu:33ac2189db61a5a1b33d5338ee1184b4"
-    ],
-    "PID": "http://hdl.handle.net/21.T15999/ZMxnmB0",
-    "fulltext": "oai:datahub.egi.eu:33ac2189db61a5a1b33d5338ee1184b4;2019-01-24T14:24:37Z;http://hdl.handle.net/21.T15999/ZMxnmB0;https://datahub.egi.eu/share/249999f24870d87afb731e524209306c",
-    "group": "egidatahub",
-    "groups": [
-        {
-            "name": "egidatahub"
-        }
-    ],
-    "name": "db04aada-6225-5b93-9510-a4efc669964c",
-    "oai_identifier": [
-        "oai:datahub.egi.eu:33ac2189db61a5a1b33d5338ee1184b4"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": "Not stated",
-    "url": "https://datahub.egi.eu/share/249999f24870d87afb731e524209306c"
-}
\ No newline at end of file
diff --git a/oaitestdata/egidatahub-oai_dc/SET_1/json/f4e6c5c0-0986-56e8-90c6-76e5c8c4edb7.json b/oaitestdata/egidatahub-oai_dc/SET_1/json/f4e6c5c0-0986-56e8-90c6-76e5c8c4edb7.json
deleted file mode 100644
index ef03c9d8..00000000
--- a/oaitestdata/egidatahub-oai_dc/SET_1/json/f4e6c5c0-0986-56e8-90c6-76e5c8c4edb7.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Contributor": [
-        "EGI-DataHub"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "application/x-ipynb+json"
-    ],
-    "MetaDataAccess": "http://datahub.egi.eu/oai_pmh?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datahub.egi.eu:93aaf6f32cab454824dbecaf60e03c68",
-    "MetadataAccess": [
-        "oai:datahub.egi.eu:93aaf6f32cab454824dbecaf60e03c68"
-    ],
-    "PID": "http://hdl.handle.net/21.T15999/TgAl7s0",
-    "PublicationTimestamp": "2019-01-29T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "ResourceType": [
-        "Jupyter Notebook"
-    ],
-    "author": [
-        "Baptiste Grenier"
-    ],
-    "fulltext": "oai:datahub.egi.eu:93aaf6f32cab454824dbecaf60e03c68;2019-01-29T11:03:37Z;CS3 notebooks;Baptiste Grenier;Notebook presented at the CS3 conference;Notebook presented at the CS3 conference: Open Data analysis with EOSC-hub services;2019-01-29;Jupyter Notebook;application/x-ipynb+json;http://hdl.handle.net/21.T15999/TgAl7s0;https://datahub.egi.eu/share/e61286563d8172aaac9dab3a0715b6ec",
-    "group": "egidatahub",
-    "groups": [
-        {
-            "name": "egidatahub"
-        }
-    ],
-    "name": "f4e6c5c0-0986-56e8-90c6-76e5c8c4edb7",
-    "notes": [
-        "Notebook presented at the CS3 conference: Open Data analysis with EOSC-hub services"
-    ],
-    "oai_identifier": [
-        "oai:datahub.egi.eu:93aaf6f32cab454824dbecaf60e03c68"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Notebook presented at the CS3 conference: Open Data analysis with EOSC-hub services"
-    ],
-    "url": "https://datahub.egi.eu/share/e61286563d8172aaac9dab3a0715b6ec"
-}
\ No newline at end of file
diff --git a/oaitestdata/egidatahub-oai_dc/SET_1/json/fa0515f5-b316-5dd9-be1e-66874aad4745.json b/oaitestdata/egidatahub-oai_dc/SET_1/json/fa0515f5-b316-5dd9-be1e-66874aad4745.json
deleted file mode 100644
index 63baa100..00000000
--- a/oaitestdata/egidatahub-oai_dc/SET_1/json/fa0515f5-b316-5dd9-be1e-66874aad4745.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Contributor": [
-        "EGI-DataHub"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "application/x-ipynb+json"
-    ],
-    "MetaDataAccess": "http://datahub.egi.eu/oai_pmh?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datahub.egi.eu:648744ddeae59f4f960a15a4e7a4f7cb",
-    "MetadataAccess": [
-        "oai:datahub.egi.eu:648744ddeae59f4f960a15a4e7a4f7cb"
-    ],
-    "PID": "http://hdl.handle.net/21.T15999/t4ZwK3Q",
-    "PublicationTimestamp": "2019-01-24T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "ResourceType": [
-        "Jupyter Notebook"
-    ],
-    "author": [
-        "Baptiste Grenier"
-    ],
-    "fulltext": "oai:datahub.egi.eu:648744ddeae59f4f960a15a4e7a4f7cb;2019-01-24T15:21:11Z;CS3 notebooks;Baptiste Grenier;Notebook presented at the CS3 conference;Notebook presented at the CS3 conference: Open Data analysis with EOSC-hub services;2019-01-24;Jupyter Notebook;application/x-ipynb+json;http://hdl.handle.net/21.T15999/t4ZwK3Q;https://datahub.egi.eu/share/1596964c6111f77835e075dcc08d5e5a",
-    "group": "egidatahub",
-    "groups": [
-        {
-            "name": "egidatahub"
-        }
-    ],
-    "name": "fa0515f5-b316-5dd9-be1e-66874aad4745",
-    "notes": [
-        "Notebook presented at the CS3 conference: Open Data analysis with EOSC-hub services"
-    ],
-    "oai_identifier": [
-        "oai:datahub.egi.eu:648744ddeae59f4f960a15a4e7a4f7cb"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Notebook presented at the CS3 conference: Open Data analysis with EOSC-hub services"
-    ],
-    "url": "https://datahub.egi.eu/share/1596964c6111f77835e075dcc08d5e5a"
-}
\ No newline at end of file
diff --git a/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/165a88f6-4ebd-5f17-afd5-dcb588e7ea3f.json b/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/165a88f6-4ebd-5f17-afd5-dcb588e7ea3f.json
deleted file mode 100644
index 9491a693..00000000
--- a/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/165a88f6-4ebd-5f17-afd5-dcb588e7ea3f.json
+++ /dev/null
@@ -1,29 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6236",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6236"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6236;2018-06-26T08:19:41Z;DOIDB;DOIDB.ENMAP;false;4;DOIDB.ENMAP;10.5880/enmap.2016.008;Okujeni, Akpona;Humboldt-Universit\u00e4t zu Berlin, Geography Department;van der Linden, Sebastian;Humboldt-Universit\u00e4t zu Berlin, Geography Department;Hostert, Patrick;Humboldt-Universit\u00e4t zu Berlin, Geography Department;Berlin-Urban-Gradient dataset 2009 - An EnMAP Preparatory Flight Campaign (Datasets);GFZ Data Services;2016;imaging spectrometry;hyperspectral;EnMAP;HyMap;urban land cover;unmixing;classification;regression;support vector machines;multi-scale;Okujeni, Akpona;Humboldt-Universit\u00e4t zu Berlin, Geography Department;Okujeni, Akpona;Humboldt-Universit\u00e4t zu Berlin, Geography Department;van der Linden, Sebastian;Humboldt-Universit\u00e4t zu Berlin, Geography Department;van der Linden, Sebastian;Humboldt-Universit\u00e4t zu Berlin, Geography Department;Hostert, Patrick;Humboldt-Universit\u00e4t zu Berlin, Geography Department;German Aerospace Centre;German Aerospace Centre;GFZ German Research Center for Geosciences;GFZ German Research Center for Geosciences;Foerster, Saskia;0000-0001-7752-7394;GFZ German Research Center for Geosciences;Elger, Kirsten;0000-0001-5140-8602;GFZ German Research Center for Geosciences;2016-03-10;2009-08-20T09:44:29/2009-08-20T09:49:53;2009-08-20T10:07:14/2009-08-20T10:12:07;2009-08-20;eng;Dataset;10.1016/j.rse.2014.11.009;10.3390/rs6076324;10.1016/j.rse.2013.06.007;10.3390/rs70708830;10.1109/JSTARS.2012.2188994;10.2312/enmap.2016.008;http://www.enmap.org/?q=flights;10.5880/enmap.2016.002;1.2;CC BY-SA 4.0;Berlin-Urban-Gradient is a ready-to-use imaging spectrometry dataset for multi-scale unmixing and hard classification analyses in urban environments. The dataset comprises two airborne HyMap scenes at 3.6 and 9 m resolution, a simulated spaceborne EnMAP scene at 30 m resolution, an im-age endmember spectral library and detailed land cover reference information. All images are pro-vided as geocoded reflectance products and cover the same subset along Berlin\u2019s urban-rural gradient. The variety of land cover and land use patterns captured make the dataset an ideal play-ground for testing the transfer of methods and research approaches at multiple spatial scales.;The Environmental Mapping and Analysis Program (EnMAP) is a German hyperspectral satellite mission that aims at monitoring and characterizing the Earth\u2019s environment on a global scale. EnMAP serves to measure and model key dynamic processes of the Earth\u2019s ecosystems by extracting geochemical, biochemical and biophysical parameters, which provide information on the status and evolution of various terrestrial and aquatic ecosystems. In the frame of the EnMAP preparatory phase, pre-flight campaigns including airborne and in-situ measurements in different environments and for several application fields are being conducted. The main purpose of these campaigns is to support the development of scientific applications for EnMAP. In addition, the acquired data are input in the EnMAP end-to-end simulation tool (EeteS) and are employed to test data pre-processing and calibration-validation methods. The campaign data are made freely available to the scientific community under a Creative Commons Attribution-ShareAlike 4.0 International License. An overview of all available data is provided in in the EnMAP Flight Campaigns Metadata Portal http://www.enmap.org/?q=flights.;13.2800;13.3142;52.3140;52.5183;HyMap01 Berlin-Urban-Gradient (3,6 m spatial resolution);13.2561;13.3384;52.3193;52.5243;HyMap02 Berlin-Urban-Gradient (9 m spatial resolution);13.2561;13.3384;52.3193;52.5243;EnMAP Berlin-Urban-Gradient (30 m spatial resolution);Bundesministerium f\u00fcr Bildung und Forschung;http://doi.org/10.13039/501100002347;Bundesministerium f\u00fcr Wirtschaft und Technologie;http://doi.org/10.13039/501100002765;Deutsche Forschungsgemeinschaft;http://doi.org/10.13039/501100001659",
-    "group": "enmap",
-    "groups": [
-        {
-            "name": "enmap"
-        }
-    ],
-    "name": "165a88f6-4ebd-5f17-afd5-dcb588e7ea3f",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6236"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.ENMAP"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/1a255453-1793-5a6c-a99c-c7a9c4f42050.json b/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/1a255453-1793-5a6c-a99c-c7a9c4f42050.json
deleted file mode 100644
index 4a589fdb..00000000
--- a/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/1a255453-1793-5a6c-a99c-c7a9c4f42050.json
+++ /dev/null
@@ -1,93 +0,0 @@
-{
-    "Contact": [
-        "Hank, Tobias Benedikt"
-    ],
-    "Contributor": [
-        "BMBF"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.5880/enmap.2015.002",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6149",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6149"
-    ],
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "GFZ Data Services"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "CC BY-SA 4.0"
-    ],
-    "SpatialCoverage": [
-        "48.616260 12.835615 48.743966 12.905975",
-        "48.500825 12.703778 48.637529 12.783497"
-    ],
-    "TemporalCoverage": [
-        "2010-03-11",
-        "2009-07-27T08:00:00/2009-07-27T10:00:00",
-        "2009-07-27T08:00:00/2009-07-27T10:00:00"
-    ],
-    "author": [
-        "Richter, Katja",
-        "Hank, Tobias Benedikt",
-        "Mauser, Wolfram"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6149;2016-11-25T13:57:59Z;DOIDB;DOIDB.ENMAP;false;3;DOIDB.ENMAP;10.5880/enmap.2015.002;Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Richter, Katja;F-6957-2010;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Mauser, Wolfram;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Neusling (Landau a.d. Isar) 2009 - An Agricultural EnMAP Preparatory Flight Campaign Using the HyMap Instrument (Datasets);GFZ Data Services;2015;Hyperspectral Imagery;Field Spectroscopy;Agriculture;Biomass;Canopy Water Content;LAI;Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Richter, Katja;F-6957-2010;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Richter, Katja;F-6957-2010;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Richter, Katja;F-6957-2010;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Richter, Katja;F-6957-2010;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Mauser, Wolfram;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);BMBF;DLR;Bachmann, Martin;Bachmann, Martin;Weide, Sebastian;Weide, Sebastian;Marzahn, Philip;Brandlhuber, Theresa;Scholtes, Jochen;Rittger, Annamaria;Schlenz, Florian;Fischer, Georg;Schavoir, Philipp;Dong, Lu;Friese, Malin;Seidel, Moritz;Heidbach, Katja;Eschenlohr, Inga;Leichtle, Tobias;Abdullahi, Sarah;M\u00fcller, Andreas;Foerster, Saskia;GFZ German Research Center for Geosciences;Brosinsky, Arlena;GFZ German Research Center for Geosciences;Elger, Kirsten;0000-0001-5140-8602;GFZ German Research Center for Geosciences;2010-03-11;2009-07-27T08:00:00/2009-07-27T10:00:00;2009-07-27T08:00:00/2009-07-27T10:00:00;eng;Dataset;978-92-9221-247-6;10.2312/enmap.2015.002;10.3390/rs70708830;http://www.enmap.org/?q=flights;CC BY-SA 4.0;This data collection contains airborne hyperspectral data as well as accompanying in-situ data acquired in autumn 2009 in the Neusling test area near Landau a.d. Isar in Southern Germany. The dataset is composed of a) two airborne hyperspectral image strips acquired during an overflight on July 27th, 2009 with the HyMap instrument over two areas; \u201cNeusling\u201d and \u201cSteinbeissen\u201d. The airborne data consists of 125 spectral bands, ranging from VIS to SWIR (455 - 2478 nm); b) spectral reference measurements acquired with a portable ASD FieldSpec 3 JR spectroradiometer in 2150 spectral bands (350 - 2500nm) taken parallel to the overflight; c) spatially comprehensive land use/land cover maps for both flight strips generated from in-situ observations during the days next to the overflight; d) Flight-parallel in-situ point-measurements consisting of: i) destructively measured aboveground dry biomass and canopy water content of maize, sugar beet and winter wheat (58 measurements), ii) non-destructive measurements of LAI of sugar beet and maize (52 measurements), iii) TDR soil moisture measurements covering the main land cover types in the area (250 measurements), iv) 249 measurements of canopy height, v) 199 observations of plant phenology. The dataset was intended to be used in an educational context and was collected with an agricultural focus.;The Environmental Mapping and Analysis Program (EnMAP) is a German hyperspectral satellite mission that aims at monitoring and characterizing the Earth\u2019s environment on a global scale. EnMAP serves to measure and model key dynamic processes of the Earth\u2019s ecosystems by extracting geochemical, biochemical and biophysical parameters, which provide information on the status and evolution of various terrestrial and aquatic ecosystems. In the frame of the EnMAP preparatory phase, pre-flight campaigns including airborne and in-situ measurements in different environments and for several application fields are being conducted. The main purpose of these campaigns is to support the development of scientific applications for EnMAP. In addition, the acquired data are input in the EnMAP end-to-end simulation tool (EeteS) and are employed to test data pre-processing and calibration-validation methods. The campaign data are made freely available to the scientific community under a Creative Commons Attribution-ShareAlike 4.0 International License. An overview of all available data is provided in in the EnMAP Flight Campaigns Metadata Portal http://www.enmap.org/?q=flights.;48.616260 12.835615 48.743966 12.905975;HyMap Imaging Flight Strip Neusling;48.500825 12.703778 48.637529 12.783497;HyMap Imaging Flight Strip Steinbeissen",
-    "group": "enmap",
-    "groups": [
-        {
-            "name": "enmap"
-        }
-    ],
-    "name": "1a255453-1793-5a6c-a99c-c7a9c4f42050",
-    "notes": [
-        "This data collection contains airborne hyperspectral data as well as accompanying in-situ data acquired in autumn 2009 in the Neusling test area near Landau a.d. Isar in Southern Germany. The dataset is composed of a) two airborne hyperspectral image strips acquired during an overflight on July 27th, 2009 with the HyMap instrument over two areas; \u201cNeusling\u201d and \u201cSteinbeissen\u201d. The airborne data consists of 125 spectral bands, ranging from VIS to SWIR (455 - 2478 nm); b) spectral reference measurements acquired with a portable ASD FieldSpec 3 JR spectroradiometer in 2150 spectral bands (350 - 2500nm) taken parallel to the overflight; c) spatially comprehensive land use/land cover maps for both flight strips generated from in-situ observations during the days next to the overflight; d) Flight-parallel in-situ point-measurements consisting of: i) destructively measured aboveground dry biomass and canopy water content of maize, sugar beet and winter wheat (58 measurements), ii) non-destructive measurements of LAI of sugar beet and maize (52 measurements), iii) TDR soil moisture measurements covering the main land cover types in the area (250 measurements), iv) 249 measurements of canopy height, v) 199 observations of plant phenology. The dataset was intended to be used in an educational context and was collected with an agricultural focus.",
-        "The Environmental Mapping and Analysis Program (EnMAP) is a German hyperspectral satellite mission that aims at monitoring and characterizing the Earth\u2019s environment on a global scale. EnMAP serves to measure and model key dynamic processes of the Earth\u2019s ecosystems by extracting geochemical, biochemical and biophysical parameters, which provide information on the status and evolution of various terrestrial and aquatic ecosystems. In the frame of the EnMAP preparatory phase, pre-flight campaigns including airborne and in-situ measurements in different environments and for several application fields are being conducted. The main purpose of these campaigns is to support the development of scientific applications for EnMAP. In addition, the acquired data are input in the EnMAP end-to-end simulation tool (EeteS) and are employed to test data pre-processing and calibration-validation methods. The campaign data are made freely available to the scientific community under a Creative Commons Attribution-ShareAlike 4.0 International License. An overview of all available data is provided in in the EnMAP Flight Campaigns Metadata Portal http://www.enmap.org/?q=flights."
-    ],
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6149"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.ENMAP"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Hyperspectral Imagery"
-        },
-        {
-            "name": "Field Spectroscopy"
-        },
-        {
-            "name": "Agriculture"
-        },
-        {
-            "name": "Biomass"
-        },
-        {
-            "name": "Canopy Water Content"
-        },
-        {
-            "name": "LAI"
-        }
-    ],
-    "title": [
-        "Neusling (Landau a.d. Isar) 2009 - An Agricultural EnMAP Preparatory Flight Campaign Using the HyMap Instrument (Datasets)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/20a54d14-68e3-51cc-95af-405e69d14dcd.json b/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/20a54d14-68e3-51cc-95af-405e69d14dcd.json
deleted file mode 100644
index 15228d45..00000000
--- a/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/20a54d14-68e3-51cc-95af-405e69d14dcd.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Hank, Tobias Benedikt"
-    ],
-    "Contributor": [
-        "BMWI"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.5880/enmap.2016.007",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6224",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6224"
-    ],
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "GFZ Data Services"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "CC BY-SA 4.0"
-    ],
-    "SpatialCoverage": "(49N-49N,13E-13E)",
-    "TempCoverageBegin": 63612385199,
-    "TempCoverageEnd": 63471207599,
-    "TemporalCoverage": " period : ( 2016-10-18T11:59:59Z - 2012-04-28T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2016-10-18T11:59:59Z",
-    "TemporalCoverage:EndDate": "2012-04-28T11:59:59Z",
-    "author": [
-        "Richter, Katja",
-        "Locherer, Matthias",
-        "Hank, Tobias Benedikt",
-        "Mauser, Wolfram"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6224;2016-11-25T13:58:08Z;DOIDB;DOIDB.ENMAP;false;3;DOIDB.ENMAP;10.5880/enmap.2016.007;Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Locherer, Matthias;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Richter, Katja;F-6957-2010;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Mauser, Wolfram;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Neusling (Landau a.d. Isar) 2012 - A Multitemporal and Multisensoral Agricultural EnMAP Preparatory Flight Campaign (Datasets);GFZ Data Services;2016;Hyperspectral Imagery;Field Spectroscopy;Agriculture;LAI;Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Locherer, Matthias;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Locherer, Matthias;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Locherer, Matthias;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Richter, Katja;F-6957-2010;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Richter, Katja;F-6957-2010;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Richter, Katja;F-6957-2010;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Richter, Katja;F-6957-2010;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Mauser, Wolfram;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);BMWI;DLR;Bachmann. Martin;Bachmann. Martin;Bachmann. Martin;Pinnel, Nicole;Pinnel, Nicole;Pinnel, Nicole;Itzerott, Sibylle;Akyol, Reyhan;Dotzler, Sandra;Chen, Yueli;Danner, Martin;Huber Garcia, Verena;Mitterer, Johannes;Obster, Christina;S\u00fc\u00df, Andreas;Wood, Raul;Foerster, Saskia;0000-0001-7752-7394;GFZ German Research Center for Geosciences;Brosinsky, Arlena;GFZ German Research Center for Geosciences;Elger, Kirsten;0000-0001-5140-8602;GFZ German Research Center for Geosciences;2016-10-18;2012-04-28T08:00:00/2012-09-08T10:00:00;eng;Dataset;urn:nbn:de:bvb:19-176184;10.3390/rs70810321;10.2312/enmap.2016.007;10.3390/rs70708830;http://www.enmap.org/?q=flights;10.5880/enmap.2015.004;1.2;CC BY-SA 4.0;This data collection contains a multitemporal series of six airborne hyperspectral image mosaics acquired during the growing season of 2012 over the Neusling test area near Landau a.d. Isar in Southern Germany. The airborne hyperspectral data is complemented by accompanying in-situ data acquired parallel to the overflights. The dataset is composed of a) four airborne hyperspectral image mosaics acquired during overflights on April 28th 2012, May 25th 2012, June 16th 2012 and September 8th 2012 with the AVIS-3 imaging spectrometer. The AVIS data consists of 197 spectral bands, ranging from VIS to SWIR (477 - 1704 nm); b) two airborne hyperspectral image mosaics acquired during overflights, which were conducted by the DLR user service OpAiRS (www.dlr.de/opairs) on May 8th 2012 and August 14th 2012 with a HySpex imaging spectrometer. The HySpex data consists of 332 spectral bands, ranging from VIS to SWIR (417 - 2496 nm); c) spatially comprehensive land use/land cover maps generated from in-situ observations for two time-windows during the growing season of 2012 (May and August); d) Flight-parallel in-situ point-measurements consisting of: i) non-destructively measured leaf area index of winter wheat, winter barley, sugar beet, maize and rapeseed (561 measurements incl. standard deviations), ii) SPAD chlorophyll measurements (522 measurements incl. standard deviations), iii) 557 soil moisture measurements incl. standard deviations iv) 539 phenological observations v) 499 measurements of canopy height incl. standard deviations and vi) 38 measurements of plant density. The dataset was collected in order to cover the seasonal dynamics in the development of agricultural crops in Southern Germany.;The Environmental Mapping and Analysis Program (EnMAP) is a German hyperspectral satellite mission that aims at monitoring and characterizing the Earth\u2019s environment on a global scale. EnMAP serves to measure and model key dynamic processes of the Earth\u2019s ecosystems by extracting geochemical, biochemical and biophysical parameters, which provide information on the status and evolution of various terrestrial and aquatic ecosystems. In the frame of the EnMAP preparatory phase, pre-flight campaigns including airborne and in-situ measurements in different environments and for several application fields are being conducted. The main purpose of these campaigns is to support the development of scientific applications for EnMAP. In addition, the acquired data are input in the EnMAP end-to-end simulation tool (EeteS) and are employed to test data pre-processing and calibration-validation methods. The campaign data are made freely available to the scientific community under a Creative Commons Attribution-ShareAlike 4.0 International License. An overview of all available data is provided in in the EnMAP Flight Campaigns Metadata Portal http://www.enmap.org/?q=flights.;48.678265 12.838639 48.706162 12.893916;Multitemporal and Multisensoral (AVIS-3 & HySpex) Imaging Flight Mosaic Neusling",
-    "group": "enmap",
-    "groups": [
-        {
-            "name": "enmap"
-        }
-    ],
-    "name": "20a54d14-68e3-51cc-95af-405e69d14dcd",
-    "notes": [
-        "This data collection contains a multitemporal series of six airborne hyperspectral image mosaics acquired during the growing season of 2012 over the Neusling test area near Landau a.d. Isar in Southern Germany. The airborne hyperspectral data is complemented by accompanying in-situ data acquired parallel to the overflights. The dataset is composed of a) four airborne hyperspectral image mosaics acquired during overflights on April 28th 2012, May 25th 2012, June 16th 2012 and September 8th 2012 with the AVIS-3 imaging spectrometer. The AVIS data consists of 197 spectral bands, ranging from VIS to SWIR (477 - 1704 nm); b) two airborne hyperspectral image mosaics acquired during overflights, which were conducted by the DLR user service OpAiRS (www.dlr.de/opairs) on May 8th 2012 and August 14th 2012 with a HySpex imaging spectrometer. The HySpex data consists of 332 spectral bands, ranging from VIS to SWIR (417 - 2496 nm); c) spatially comprehensive land use/land cover maps generated from in-situ observations for two time-windows during the growing season of 2012 (May and August); d) Flight-parallel in-situ point-measurements consisting of: i) non-destructively measured leaf area index of winter wheat, winter barley, sugar beet, maize and rapeseed (561 measurements incl. standard deviations), ii) SPAD chlorophyll measurements (522 measurements incl. standard deviations), iii) 557 soil moisture measurements incl. standard deviations iv) 539 phenological observations v) 499 measurements of canopy height incl. standard deviations and vi) 38 measurements of plant density. The dataset was collected in order to cover the seasonal dynamics in the development of agricultural crops in Southern Germany.",
-        "The Environmental Mapping and Analysis Program (EnMAP) is a German hyperspectral satellite mission that aims at monitoring and characterizing the Earth\u2019s environment on a global scale. EnMAP serves to measure and model key dynamic processes of the Earth\u2019s ecosystems by extracting geochemical, biochemical and biophysical parameters, which provide information on the status and evolution of various terrestrial and aquatic ecosystems. In the frame of the EnMAP preparatory phase, pre-flight campaigns including airborne and in-situ measurements in different environments and for several application fields are being conducted. The main purpose of these campaigns is to support the development of scientific applications for EnMAP. In addition, the acquired data are input in the EnMAP end-to-end simulation tool (EeteS) and are employed to test data pre-processing and calibration-validation methods. The campaign data are made freely available to the scientific community under a Creative Commons Attribution-ShareAlike 4.0 International License. An overview of all available data is provided in in the EnMAP Flight Campaigns Metadata Portal http://www.enmap.org/?q=flights."
-    ],
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6224"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.ENMAP"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[12.838639,48.678265],[12.838639,48.706162],[12.893916,48.706162],[12.893916,48.678265],[12.838639,48.678265]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Hyperspectral Imagery"
-        },
-        {
-            "name": "Field Spectroscopy"
-        },
-        {
-            "name": "Agriculture"
-        },
-        {
-            "name": "LAI"
-        }
-    ],
-    "title": [
-        "Neusling (Landau a.d. Isar) 2012 - A Multitemporal and Multisensoral Agricultural EnMAP Preparatory Flight Campaign (Datasets)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/2fcae98c-8619-5c44-9c31-98e75dbe7cf4.json b/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/2fcae98c-8619-5c44-9c31-98e75dbe7cf4.json
deleted file mode 100644
index 2a134c8c..00000000
--- a/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/2fcae98c-8619-5c44-9c31-98e75dbe7cf4.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Hank, Tobias Benedikt"
-    ],
-    "Contributor": [
-        "BMWI"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.5880/enmap.2015.004",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6146",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6146"
-    ],
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "GFZ Data Services"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "CC BY-SA 4.0"
-    ],
-    "SpatialCoverage": "(49N-49N,13E-13E)",
-    "TempCoverageBegin": 63493329599,
-    "TempCoverageEnd": 63471207599,
-    "TemporalCoverage": " period : ( 2013-01-09T11:59:59Z - 2012-04-28T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2013-01-09T11:59:59Z",
-    "TemporalCoverage:EndDate": "2012-04-28T11:59:59Z",
-    "author": [
-        "Richter, Katja",
-        "Locherer, Matthias",
-        "Hank, Tobias Benedikt",
-        "Mauser, Wolfram"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6146;2016-11-25T13:58:01Z;DOIDB;DOIDB.ENMAP;false;3;DOIDB.ENMAP;10.5880/enmap.2015.004;Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Locherer, Matthias;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Richter, Katja;F-6957-2010;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Mauser, Wolfram;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Neusling (Landau a.d. Isar) 2012 - A Multitemporal and Multisensoral Agricultural EnMAP Preparatory Flight Campaign (Datasets);GFZ Data Services;2015;Hyperspectral Imagery;Field Spectroscopy;Agriculture;LAI;Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Locherer, Matthias;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Locherer, Matthias;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Locherer, Matthias;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Richter, Katja;F-6957-2010;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Richter, Katja;F-6957-2010;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Richter, Katja;F-6957-2010;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Richter, Katja;F-6957-2010;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Mauser, Wolfram;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);BMWI;DLR;Bachmann. Martin;Bachmann. Martin;Bachmann. Martin;Pinnel, Nicole;Pinnel, Nicole;Pinnel, Nicole;Itzerott, Sibylle;Akyol, Reyhan;Dotzler, Sandra;Chen, Yueli;Danner, Martin;Huber Garcia, Verena;Mitterer, Johannes;Obster, Christina;S\u00fc\u00df, Andreas;Wood, Raul;Foerster, Saskia;0000-0001-7752-7394;GFZ German Research Center for Geosciences;Brosinsky, Arlena;GFZ German Research Center for Geosciences;Elger, Kirsten;0000-0001-5140-8602;GFZ German Research Center for Geosciences;2013-01-09;2012-04-28T08:00:00/2012-09-08T10:00:00;eng;Dataset;urn:nbn:de:bvb:19-176184;10.3390/rs70810321;10.2312/enmap.2015.004;10.3390/rs70708830;http://www.enmap.org/?q=flights;10.5880/enmap.2016.007;CC BY-SA 4.0;This data collection contains a multitemporal series of six airborne hyperspectral image mosaics acquired during the growing season of 2012 over the Neusling test area near Landau a.d. Isar in Southern Germany. The airborne hyperspectral data is complemented by accompanying in-situ data acquired parallel to the overflights. The dataset is composed of a) four airborne hyperspectral image mosaics acquired during overflights on April 28th 2012, May 25th 2012, June 16th 2012 and September 8th 2012 with the AVIS-3 imaging spectrometer. The AVIS data consists of 197 spectral bands, ranging from VIS to SWIR (477 - 1704 nm); b) two airborne hyperspectral image mosaics acquired during overflights, which were conducted by the DLR user service OpAiRS (www.dlr.de/opairs) on May 8th 2012 and August 14th 2012 with a HySpex imaging spectrometer. The HySpex data consists of 332 spectral bands, ranging from VIS to SWIR (417 - 2496 nm); c) spatially comprehensive land use/land cover maps generated from in-situ observations for two time-windows during the growing season of 2012 (May and August); d) Flight-parallel in-situ point-measurements consisting of: i) non-destructively measured leaf area index of winter wheat, winter barley, sugar beet, maize and rapeseed (561 measurements incl. standard deviations), ii) SPAD chlorophyll measurements (522 measurements incl. standard deviations), iii) 557 soil moisture measurements incl. standard deviations iv) 539 phenological observations v) 499 measurements of canopy height incl. standard deviations and vi) 38 measurements of plant density. The dataset was collected in order to cover the seasonal dynamics in the development of agricultural crops in Southern Germany.;The Environmental Mapping and Analysis Program (EnMAP) is a German hyperspectral satellite mission that aims at monitoring and characterizing the Earth\u2019s environment on a global scale. EnMAP serves to measure and model key dynamic processes of the Earth\u2019s ecosystems by extracting geochemical, biochemical and biophysical parameters, which provide information on the status and evolution of various terrestrial and aquatic ecosystems. In the frame of the EnMAP preparatory phase, pre-flight campaigns including airborne and in-situ measurements in different environments and for several application fields are being conducted. The main purpose of these campaigns is to support the development of scientific applications for EnMAP. In addition, the acquired data are input in the EnMAP end-to-end simulation tool (EeteS) and are employed to test data pre-processing and calibration-validation methods. The campaign data are made freely available to the scientific community under a Creative Commons Attribution-ShareAlike 4.0 International License. An overview of all available data is provided in in the EnMAP Flight Campaigns Metadata Portal http://www.enmap.org/?q=flights.;48.678265 12.838639 48.706162 12.893916;Multitemporal and Multisensoral (AVIS-3 & HySpex) Imaging Flight Mosaic Neusling",
-    "group": "enmap",
-    "groups": [
-        {
-            "name": "enmap"
-        }
-    ],
-    "name": "2fcae98c-8619-5c44-9c31-98e75dbe7cf4",
-    "notes": [
-        "This data collection contains a multitemporal series of six airborne hyperspectral image mosaics acquired during the growing season of 2012 over the Neusling test area near Landau a.d. Isar in Southern Germany. The airborne hyperspectral data is complemented by accompanying in-situ data acquired parallel to the overflights. The dataset is composed of a) four airborne hyperspectral image mosaics acquired during overflights on April 28th 2012, May 25th 2012, June 16th 2012 and September 8th 2012 with the AVIS-3 imaging spectrometer. The AVIS data consists of 197 spectral bands, ranging from VIS to SWIR (477 - 1704 nm); b) two airborne hyperspectral image mosaics acquired during overflights, which were conducted by the DLR user service OpAiRS (www.dlr.de/opairs) on May 8th 2012 and August 14th 2012 with a HySpex imaging spectrometer. The HySpex data consists of 332 spectral bands, ranging from VIS to SWIR (417 - 2496 nm); c) spatially comprehensive land use/land cover maps generated from in-situ observations for two time-windows during the growing season of 2012 (May and August); d) Flight-parallel in-situ point-measurements consisting of: i) non-destructively measured leaf area index of winter wheat, winter barley, sugar beet, maize and rapeseed (561 measurements incl. standard deviations), ii) SPAD chlorophyll measurements (522 measurements incl. standard deviations), iii) 557 soil moisture measurements incl. standard deviations iv) 539 phenological observations v) 499 measurements of canopy height incl. standard deviations and vi) 38 measurements of plant density. The dataset was collected in order to cover the seasonal dynamics in the development of agricultural crops in Southern Germany.",
-        "The Environmental Mapping and Analysis Program (EnMAP) is a German hyperspectral satellite mission that aims at monitoring and characterizing the Earth\u2019s environment on a global scale. EnMAP serves to measure and model key dynamic processes of the Earth\u2019s ecosystems by extracting geochemical, biochemical and biophysical parameters, which provide information on the status and evolution of various terrestrial and aquatic ecosystems. In the frame of the EnMAP preparatory phase, pre-flight campaigns including airborne and in-situ measurements in different environments and for several application fields are being conducted. The main purpose of these campaigns is to support the development of scientific applications for EnMAP. In addition, the acquired data are input in the EnMAP end-to-end simulation tool (EeteS) and are employed to test data pre-processing and calibration-validation methods. The campaign data are made freely available to the scientific community under a Creative Commons Attribution-ShareAlike 4.0 International License. An overview of all available data is provided in in the EnMAP Flight Campaigns Metadata Portal http://www.enmap.org/?q=flights."
-    ],
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6146"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.ENMAP"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[12.838639,48.678265],[12.838639,48.706162],[12.893916,48.706162],[12.893916,48.678265],[12.838639,48.678265]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Hyperspectral Imagery"
-        },
-        {
-            "name": "Field Spectroscopy"
-        },
-        {
-            "name": "Agriculture"
-        },
-        {
-            "name": "LAI"
-        }
-    ],
-    "title": [
-        "Neusling (Landau a.d. Isar) 2012 - A Multitemporal and Multisensoral Agricultural EnMAP Preparatory Flight Campaign (Datasets)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/30153ff3-61a8-5451-88ca-fdfeab173815.json b/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/30153ff3-61a8-5451-88ca-fdfeab173815.json
deleted file mode 100644
index e0efedfc..00000000
--- a/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/30153ff3-61a8-5451-88ca-fdfeab173815.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Buddenbaum, Henning"
-    ],
-    "Contributor": [
-        "Federal Ministry of Economic Affairs and Energy"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.5880/enmap.2015.006",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6132",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6132"
-    ],
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "GFZ Data Services"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "CC BY-SA 4.0"
-    ],
-    "SpatialCoverage": "(50N-50N,8 E-8 E)",
-    "TempCoverageBegin": 63571517999,
-    "TempCoverageEnd": 63571517999,
-    "TemporalCoverage": " period : ( 2015-07-03T11:59:59Z - 2015-07-03T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2015-07-03T11:59:59Z",
-    "TemporalCoverage:EndDate": "2015-07-03T11:59:59Z",
-    "author": [
-        "Dotzler, Sandra",
-        "Buddenbaum, Henning",
-        "Hill, Joachim"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6132;2016-11-25T13:58:03Z;DOIDB;DOIDB.ENMAP;false;3;DOIDB.ENMAP;10.5880/enmap.2015.006;Buddenbaum, Henning;0000-0002-0956-5628;University of Trier, Environmental Remote Sensing and Geoinformatics, Trier, Germany;Dotzler, Sandra;0000-0002-8171-2944;University of Trier, Environmental Remote Sensing and Geoinformatics, Trier, Germany;Hill, Joachim;University of Trier, Environmental Remote Sensing and Geoinformatics, Trier, Germany;Donnersberg, 2014-07-03 - An EnMAP Preparatory Flight Campaign (Datasets);GFZ Data Services;2015;Imaging Spectroscopy;Vegetation Ecology;Forest;Buddenbaum, Henning;0000-0002-0956-5628;University of Trier, Environmental Remote Sensing and Geoinformatics, Trier, Germany;Buddenbaum, Henning;0000-0002-0956-5628;University of Trier, Environmental Remote Sensing and Geoinformatics, Trier, Germany;Dotzler, Sandra;0000-0002-8171-2944;University of Trier, Environmental Remote Sensing and Geoinformatics, Trier, Germany;Dotzler, Sandra;0000-0002-8171-2944;University of Trier, Environmental Remote Sensing and Geoinformatics, Trier, Germany;Hill, Joachim;University of Trier, Environmental Remote Sensing and Geoinformatics, Trier, Germany;Federal Ministry of Economic Affairs and Energy;Federal Ministry of Economic Affairs and Energy;Foerster, Saskia;0000-0001-7752-7394;GFZ German Research Center for Geosciences;Kuester, Theres;GFZ German Research Center for Geosciences;Elger, Kirsten;0000-0001-5140-8602;GFZ German Research Center for Geosciences;2015-07-03;2015-07-03T13:32/2015-07-03T14:26;eng;Dataset;10.2312/enmap.2015.006;http://meetingorganizer.copernicus.org/ISRSE36/ISRSE36-201-2.pdf;http://www.conftool.net/earsel2015/index.php?page=browseSessions&search=dotzler;10.3390/rs70708830;http://www.enmap.org/?q=flights;CC BY-SA 4.0;The dataset contains hyperspectral imagery acquired during airplane overflights on 3rd July 2014 consisting of 242 spectral bands, ranging from VIS to SWIR (423 - 2438 nm) wavelength regions. It covers an area of about 78 km\u00b2 which is dominated by beech and oak forests. The flight campaign was part of several flight campaigns within the EnMAP project and focused on hyperspectral analysis of plant physiology in deciduous forests in the Donnersberg region in Rhineland-Palatinate, Germany.;The Environmental Mapping and Analysis Program (EnMAP) is a German hyperspectral satellite mission that aims at monitoring and characterizing the Earth\u2019s environment on a global scale. EnMAP serves to measure and model key dynamic processes of the Earth\u2019s ecosystems by extracting geochemical, biochemical and biophysical parameters, which provide information on the status and evolution of various terrestrial and aquatic ecosystems. In the frame of the EnMAP preparatory phase, pre-flight campaigns including airborne and in-situ measurements in different environments and for several application fields are being conducted. The main purpose of these campaigns is to support the development of scientific applications for EnMAP. In addition, the acquired data are input in the EnMAP end-to-end simulation tool (EeteS) and are employed to test data pre-processing and calibration-validation methods. The campaign data are made freely available to the scientific community under a Creative Commons Attribution-ShareAlike 4.0 International License. An overview of all available data is provided in in the EnMAP Flight Campaigns Metadata Portal http://www.enmap.org/?q=flights;49.579109609432095 7.853851318359375 49.64451295574021 7.9575347900390625;HySpex, 14 Flight Lines",
-    "group": "enmap",
-    "groups": [
-        {
-            "name": "enmap"
-        }
-    ],
-    "name": "30153ff3-61a8-5451-88ca-fdfeab173815",
-    "notes": [
-        "The dataset contains hyperspectral imagery acquired during airplane overflights on 3rd July 2014 consisting of 242 spectral bands, ranging from VIS to SWIR (423 - 2438 nm) wavelength regions. It covers an area of about 78 km\u00b2 which is dominated by beech and oak forests. The flight campaign was part of several flight campaigns within the EnMAP project and focused on hyperspectral analysis of plant physiology in deciduous forests in the Donnersberg region in Rhineland-Palatinate, Germany.",
-        "The Environmental Mapping and Analysis Program (EnMAP) is a German hyperspectral satellite mission that aims at monitoring and characterizing the Earth\u2019s environment on a global scale. EnMAP serves to measure and model key dynamic processes of the Earth\u2019s ecosystems by extracting geochemical, biochemical and biophysical parameters, which provide information on the status and evolution of various terrestrial and aquatic ecosystems. In the frame of the EnMAP preparatory phase, pre-flight campaigns including airborne and in-situ measurements in different environments and for several application fields are being conducted. The main purpose of these campaigns is to support the development of scientific applications for EnMAP. In addition, the acquired data are input in the EnMAP end-to-end simulation tool (EeteS) and are employed to test data pre-processing and calibration-validation methods. The campaign data are made freely available to the scientific community under a Creative Commons Attribution-ShareAlike 4.0 International License. An overview of all available data is provided in in the EnMAP Flight Campaigns Metadata Portal http://www.enmap.org/?q=flights"
-    ],
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6132"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.ENMAP"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[7.853851318359375,49.579109609432095],[7.853851318359375,49.64451295574021],[7.9575347900390625,49.64451295574021],[7.9575347900390625,49.579109609432095],[7.853851318359375,49.579109609432095]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Imaging Spectroscopy"
-        },
-        {
-            "name": "Vegetation Ecology"
-        },
-        {
-            "name": "Forest"
-        }
-    ],
-    "title": [
-        "Donnersberg, 2014-07-03 - An EnMAP Preparatory Flight Campaign (Datasets)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/ab5265b0-e2d5-5b86-a922-e02a1fb13b99.json b/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/ab5265b0-e2d5-5b86-a922-e02a1fb13b99.json
deleted file mode 100644
index 1a740a02..00000000
--- a/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/ab5265b0-e2d5-5b86-a922-e02a1fb13b99.json
+++ /dev/null
@@ -1,29 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6173",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6173"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6173;2018-06-26T08:34:55Z;DOIDB;DOIDB.ENMAP;false;4;DOIDB.ENMAP;10.5880/enmap.2016.002;Okujeni, Akpona;Humboldt-Universit\u00e4t zu Berlin, Geography Department, Berlin, Germany;van der Linden, Sebastian;Humboldt-Universit\u00e4t zu Berlin, Geography Department, Berlin, Germany;Hostert, Patrick;Humboldt-Universit\u00e4t zu Berlin, Geography Department, Berlin, Germany;Berlin-Urban-Gradient dataset 2009 - An EnMAP Preparatory Flight Campaign (Datasets);GFZ Data Services;2016;imaging spectrometry;hyperspectral;EnMAP;HyMap;urban land cover;unmixing;classification;regression;support vector machines;multi-scale;Okujeni, Akpona;Humboldt-Universit\u00e4t zu Berlin, Geography Department, Berlin, Germany;Okujeni, Akpona;Humboldt-Universit\u00e4t zu Berlin, Geography Department, Berlin, Germany;van der Linden, Sebastian;Humboldt-Universit\u00e4t zu Berlin, Geography Department, Berlin, Germany;van der Linden, Sebastian;Humboldt-Universit\u00e4t zu Berlin, Geography Department, Berlin, Germany;Hostert, Patrick;Humboldt-Universit\u00e4t zu Berlin, Geography Department, Berlin, Germany;German Aerospace Center (DLR);German Aerospace Center (DLR);GFZ German Research Center for Geosciences;GFZ German Research Centre for Geosciences, Potsdam, Germany;Foerster, Saskia;0000-0001-7752-7394;GFZ German Research Centre for Geosciences, Potsdam, Germany;Elger, Kirsten;0000-0001-5140-8602;GFZ German Research Centre for Geosciences, Potsdam, Germany;2016-03-10;2009-08-20T09:44:29/2009-08-20T09:49:53;2009-08-20T10:07:14/2009-08-20T10:12:07;2009-08-20;eng;Dataset;10.1016/j.rse.2014.11.009;10.3390/rs6076324;10.1016/j.rse.2013.06.007;10.3390/rs70708830;10.1109/JSTARS.2012.2188994;10.2312/enmap.2016.002;http://www.enmap.org/?q=flights;10.5880/enmap.2016.008;CC BY-SA 4.0;Berlin-Urban-Gradient is a ready-to-use imaging spectrometry dataset for multi-scale unmixing and hard classification analyses in urban environments. The dataset comprises two airborne HyMap scenes at 3.6 and 9 m resolution, a simulated spaceborne EnMAP scene at 30 m resolution, an im-age endmember spectral library and detailed land cover reference information. All images are pro-vided as geocoded reflectance products and cover the same subset along Berlin\u2019s urban-rural gra-dient. The variety of land cover and land use patterns captured make the dataset an ideal play-ground for testing the transfer of methods and research approaches at multiple spatial scales.;The Environmental Mapping and Analysis Program (EnMAP) is a German hyperspectral satellite mission that aims at monitoring and characterizing the Earth\u2019s environment on a global scale. EnMAP serves to measure and model key dynamic processes of the Earth\u2019s ecosystems by extracting geochemical, biochemical and biophysical parameters, which provide information on the status and evolution of various terrestrial and aquatic ecosystems. In the frame of the EnMAP preparatory phase, pre-flight campaigns including airborne and in-situ measurements in different environments and for several application fields are being conducted. The main purpose of these campaigns is to support the development of scientific applications for EnMAP. In addition, the acquired data are input in the EnMAP end-to-end simulation tool (EeteS) and are employed to test data pre-processing and calibration-validation methods. The campaign data are made freely available to the scientific community under a Creative Commons Attribution-ShareAlike 4.0 International License. An overview of all available data is provided in in the EnMAP Flight Campaigns Metadata Portal http://www.enmap.org/?q=flights.;13.2800;13.3142;52.3140;52.5183;HyMap01 Berlin-Urban-Gradient (3,6 m spatial resolution);13.2561;13.3384;52.3193;52.5243;HyMap02 Berlin-Urban-Gradient (9 m spatial resolution);13.2561;13.3384;52.3193;52.5243;EnMAP Berlin-Urban-Gradient (30 m spatial resolution);Bundesministerium f\u00fcr Bildung und Forschung;http://doi.org/10.13039/501100002347;Bundesministerium f\u00fcr Wirtschaft und Technologie;http://doi.org/10.13039/501100002765;Deutsche Forschungsgemeinschaft;http://doi.org/10.13039/501100001659",
-    "group": "enmap",
-    "groups": [
-        {
-            "name": "enmap"
-        }
-    ],
-    "name": "ab5265b0-e2d5-5b86-a922-e02a1fb13b99",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6173"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.ENMAP"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/b82929b0-3ed1-5a64-b9ec-fba2430db5da.json b/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/b82929b0-3ed1-5a64-b9ec-fba2430db5da.json
deleted file mode 100644
index 3fdaef86..00000000
--- a/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/b82929b0-3ed1-5a64-b9ec-fba2430db5da.json
+++ /dev/null
@@ -1,97 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.5880/enmap.2016.001",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "application/octet-stream"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6193",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6193"
-    ],
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "GFZ Data Services"
-    ],
-    "Rights": [
-        "CC BY-SA 4.0"
-    ],
-    "SpatialCoverage": [
-        "35.4946 -115.56907778 35.46335333 -115.50759167",
-        "36.8285917 -2.0724028 36.8897917 -2.0280639"
-    ],
-    "author": [
-        "Brell, Maximilian",
-        "Boesche, Nina K.",
-        "Guanter, Luis",
-        "Mielke, Christian",
-        "Lundeen, Sarah",
-        "Rogass, Christian",
-        "Thomson, David",
-        "Chabrillat, Sabine",
-        "Segl, Karl"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6193;2016-11-25T13:58:05Z;DOIDB;DOIDB.ENMAP;false;3;DOIDB.ENMAP;10.5880/enmap.2016.001;Boesche, Nina K.;GFZ German Research Centre for Geosciences, Potsdam, Gemany;Mielke, Christian;GFZ German Research Centre for Geosciences, Potsdam, Gemany;Segl, Karl;GFZ German Research Centre for Geosciences, Potsdam, Gemany;Chabrillat, Sabine;0000-0001-8600-5168;GFZ German Research Centre for Geosciences, Potsdam, Gemany;Rogass, Christian;GFZ German Research Centre for Geosciences, Potsdam, Gemany;Thomson, David;Jet Propulsion Laboratory (JPL), 4800 Oak Grove Drive, Pasadena, CA 91109, USA;Lundeen, Sarah;Jet Propulsion Laboratory (JPL), 4800 Oak Grove Drive, Pasadena, CA 91109, USA;Brell, Maximilian;GFZ German Research Centre for Geosciences, Potsdam, Gemany;Guanter, Luis;0000-0002-8389-5764;GFZ German Research Centre for Geosciences, Potsdam, Gemany;EnGeoMAP Test Data: Simulated EnMAP Satellite Data for Mountain Pass, USA and Rodalquilar, Spain;GFZ Data Services;2016;Imaging spectroscopy;Mineral Mapping;Rare Earth Elements;EnMAP;EnGeoMAP;Simulated Data;Rodalquilar;Mountain Pass;Hyperspectral Imagery;Foerster, Saskia;0000-0001-7752-7394;GFZ German Research Centre for Geosciences, Potsdam, Gemany;Elger, Kirsten;0000-0001-5140-8602;GFZ German Research Centre for Geosciences, Potsdam, Gemany;en;urn:nbn:de:kobv:517-opus4-85363;10.2312/enmap.2016.003;978-3941493865;http://www.earsel.org/workshops/IS_Warsaw_2005/papers/Terrestial_Ecosystems/13_Chabrillat_113_118.pdf;10.2312/enmap.2016.001;10.3390/rs70708830;10.3390/rs8020127;http://pubs.usgs.gov/pp/0261/report.pdf;10.1109/JSTARS.2012.2188994;http://www.enmap.org/?q=flights;10.1016/j.rse.2015.02.010;36514690 Bytes;4 Files;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;CC BY-SA 4.0;This data pubilcation includes EnMAP-like imaging spectroscopy data files to be used for mineral mapping with the EnMAP BOX software. It is simulated EnMAP satellite data, which is based on hyperspectral flight campaign data with the AVIRIS-NG and HyMap sensors. In preparation of the EnMAP satellite mission, an EnMAP BOX software package provides tools for visualization and scientific analysis of the data. Among many applications, the EnMAP BOX contains geological mapping tools (EnGeoMAP). Here we apply these tools to several representative test cases (Boesche, 2015; Boesche et al. 2016; Mielke et al., 2016). The test data comprise two study sites. ;The Environmental Mapping and Analysis Program (EnMAP) is a German hyperspectral satellite mission that aims at monitoring and characterizing the Earth\u2019s environment on a global scale. EnMAP serves to measure and model key dynamic processes of the Earth\u2019s ecosystems by extracting geochemical, biochemical and biophysical parameters, which provide information on the status and evolution of various terrestrial and aquatic ecosystems. In the frame of the EnMAP preparatory phase, pre-flight campaigns including airborne and in-situ measurements in different environments and for several application fields are being conducted. The main purpose of these campaigns is to support the development of scientific applications for EnMAP. In addition, the acquired data are input in the EnMAP end-to-end simulation tool (EeteS) and are employed to test data pre-processing and calibration-validation methods. The campaign data are made freely available to the scientific community under a Creative Commons Attribution-ShareAlike 4.0 International License. An overview of all available data is provided in in the EnMAP Flight Campaigns Metadata Portal http://www.enmap.org/?q=flights.;35.4946 -115.56907778 35.46335333 -115.50759167;Mountain Pass;36.8285917 -2.0724028 36.8897917 -2.0280639;Rodalquilar",
-    "group": "enmap",
-    "groups": [
-        {
-            "name": "enmap"
-        }
-    ],
-    "name": "b82929b0-3ed1-5a64-b9ec-fba2430db5da",
-    "notes": [
-        "This data pubilcation includes EnMAP-like imaging spectroscopy data files to be used for mineral mapping with the EnMAP BOX software. It is simulated EnMAP satellite data, which is based on hyperspectral flight campaign data with the AVIRIS-NG and HyMap sensors. In preparation of the EnMAP satellite mission, an EnMAP BOX software package provides tools for visualization and scientific analysis of the data. Among many applications, the EnMAP BOX contains geological mapping tools (EnGeoMAP). Here we apply these tools to several representative test cases (Boesche, 2015; Boesche et al. 2016; Mielke et al., 2016). The test data comprise two study sites. ",
-        "The Environmental Mapping and Analysis Program (EnMAP) is a German hyperspectral satellite mission that aims at monitoring and characterizing the Earth\u2019s environment on a global scale. EnMAP serves to measure and model key dynamic processes of the Earth\u2019s ecosystems by extracting geochemical, biochemical and biophysical parameters, which provide information on the status and evolution of various terrestrial and aquatic ecosystems. In the frame of the EnMAP preparatory phase, pre-flight campaigns including airborne and in-situ measurements in different environments and for several application fields are being conducted. The main purpose of these campaigns is to support the development of scientific applications for EnMAP. In addition, the acquired data are input in the EnMAP end-to-end simulation tool (EeteS) and are employed to test data pre-processing and calibration-validation methods. The campaign data are made freely available to the scientific community under a Creative Commons Attribution-ShareAlike 4.0 International License. An overview of all available data is provided in in the EnMAP Flight Campaigns Metadata Portal http://www.enmap.org/?q=flights."
-    ],
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6193"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.ENMAP"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Imaging spectroscopy"
-        },
-        {
-            "name": "Mineral Mapping"
-        },
-        {
-            "name": "Rare Earth Elements"
-        },
-        {
-            "name": "EnMAP"
-        },
-        {
-            "name": "EnGeoMAP"
-        },
-        {
-            "name": "Simulated Data"
-        },
-        {
-            "name": "Rodalquilar"
-        },
-        {
-            "name": "Mountain Pass"
-        },
-        {
-            "name": "Hyperspectral Imagery"
-        }
-    ],
-    "title": [
-        "EnGeoMAP Test Data: Simulated EnMAP Satellite Data for Mountain Pass, USA and Rodalquilar, Spain"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/b8ab6505-b010-5265-b1e4-af8a6f67260a.json b/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/b8ab6505-b010-5265-b1e4-af8a6f67260a.json
deleted file mode 100644
index 03a07bf6..00000000
--- a/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/b8ab6505-b010-5265-b1e4-af8a6f67260a.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contributor": [
-        "Federal Ministry of Economics and Technology"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.5880/enmap.2015.001",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6148",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6148"
-    ],
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "GFZ Data Services"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "CC BY-SA 4.0"
-    ],
-    "SpatialCoverage": [
-        "52.45412645595905 12.989959716796875 52.536064211791505 13.104286193847656",
-        "52.35295738060679 12.9913330078125 52.53794364304724 13.04901123046875",
-        "52.35127974891625 13.056564331054688 52.53961418106945 13.09844970703125",
-        "52.45768304654543 12.965927124023438 52.53961418106945 13.105316162109375"
-    ],
-    "TemporalCoverage": [
-        "2010-08-06",
-        "2008-08-07T11:00:51/2008-08-07T11:21:10",
-        "2009-08-20T09:14:39/2009-08-20T09:19:36",
-        "2009-08-20T09:25:16/2009-08-20T09:30:20",
-        "2007-05-01/2009-09-01"
-    ],
-    "author": [
-        "Neumann, Carsten",
-        "Itzerott, Sibylle",
-        "Weiss, Gabriele"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6148;2016-11-25T13:57:58Z;DOIDB;DOIDB.ENMAP;false;3;DOIDB.ENMAP;10.5880/enmap.2015.001;Neumann, Carsten;GFZ German Research Centre for Geosciences;Weiss, Gabriele;Ecostrat GmbH;Itzerott, Sibylle;GFZ German Research Centre for Geosciences;D\u00f6beritzer Heide 2008/2009 - An EnMAP Preparatory Flight Campaign (Datasets);GFZ Data Services;2015;Imaging Spectroscopy;Vegetation Ecology;Environmental Gradients;Federal Ministry of Economics and Technology;Federal Ministry of Economics and Technology;Klinke, Randolf;GFZ German Research Centre for Geosciences;Fuerstenow, Joerg;Sielmanns Naturlandschaften gGmbH;Foerster, Saskia;0000-0001-7752-7394;GFZ German Research Centre for Geosciences;Kuester, Theres;GFZ German Research Centre for Geosciences;Elger, Kirsten;0000-0001-5140-8602;GFZ German Research Centre for Geosciences;Brosinsky, Arlena;GFZ German Research Centre for Geosciences;2010-08-06;2008-08-07T11:00:51/2008-08-07T11:21:10;2009-08-20T09:14:39/2009-08-20T09:19:36;2009-08-20T09:25:16/2009-08-20T09:30:20;2007-05-01/2009-09-01;eng;Dataset;10.3390/rs70708830;10.1016/j.ecolind.2014.06.025 ;10.2312/GFZ.b103-13024;10.3390/rs70302871 ;10.1127/pfg/2014/0243 ;10.2312/enmap.2015.001;http://www.enmap.org/?q=flights;CC BY-SA 4.0;The dataset is composed of a) hyperspectral imagery acquired during airplane overflights on August 7th, 2008 and August 20th, 2009 consisting of 126 and 125 spectral bands, respectively, ranging from VIS to SWIR (456 - 2490 nm and 453 - 2480 nm) wavelength regions; b) spectral reference measurements acquired with an portable ASD field spectroradiometer in 2150 spectral bands (350 - 2500nm) in the same phenological periods of July/August/September 2008/09 c) plant species assemblages on 81 moist and 72 dry habitats consisting of the fractional cover of all vascular plants, mosses and lichens. ;The Environmental Mapping and Analysis Program (EnMAP) is a German hyperspectral satellite mission that aims at monitoring and characterizing the Earth\u2019s environment on a global scale. EnMAP serves to measure and model key dynamic processes of the Earth\u2019s ecosystems by extracting geochemical, biochemical and biophysical parameters, which provide information on the status and evolution of various terrestrial and aquatic ecosystems. In the frame of the EnMAP preparatory phase, pre-flight campaigns including airborne and in-situ measurements in different environments and for several application fields are being conducted. The main purpose of these campaigns is to support the development of scientific applications for EnMAP. In addition, the acquired data are input in the EnMAP end-to-end simulation tool (EeteS) and are employed to test data pre-processing and calibration-validation methods. The campaign data are made freely available to the scientific community under a Creative Commons Attribution-ShareAlike 4.0 International License. An overview of all available data is provided in in the EnMAP Flight Campaigns Metadata Portal http://www.enmap.org/?q=flights.;52.45412645595905 12.989959716796875 52.536064211791505 13.104286193847656; HyMap campaign 2008, 4 flight lines, D\u00f6beritzer Heide;52.35295738060679 12.9913330078125 52.53794364304724 13.04901123046875; HyMap campaign 2009, flight line 1, D\u00f6beritzer Heide;52.35127974891625 13.056564331054688 52.53961418106945 13.09844970703125; HyMap campaign 2009, flight line 2, D\u00f6beritzer Heide;52.45768304654543 12.965927124023438 52.53961418106945 13.105316162109375;Plant species assemblages, D\u00f6beritzer Heide",
-    "group": "enmap",
-    "groups": [
-        {
-            "name": "enmap"
-        }
-    ],
-    "name": "b8ab6505-b010-5265-b1e4-af8a6f67260a",
-    "notes": [
-        "The dataset is composed of a) hyperspectral imagery acquired during airplane overflights on August 7th, 2008 and August 20th, 2009 consisting of 126 and 125 spectral bands, respectively, ranging from VIS to SWIR (456 - 2490 nm and 453 - 2480 nm) wavelength regions; b) spectral reference measurements acquired with an portable ASD field spectroradiometer in 2150 spectral bands (350 - 2500nm) in the same phenological periods of July/August/September 2008/09 c) plant species assemblages on 81 moist and 72 dry habitats consisting of the fractional cover of all vascular plants, mosses and lichens. ",
-        "The Environmental Mapping and Analysis Program (EnMAP) is a German hyperspectral satellite mission that aims at monitoring and characterizing the Earth\u2019s environment on a global scale. EnMAP serves to measure and model key dynamic processes of the Earth\u2019s ecosystems by extracting geochemical, biochemical and biophysical parameters, which provide information on the status and evolution of various terrestrial and aquatic ecosystems. In the frame of the EnMAP preparatory phase, pre-flight campaigns including airborne and in-situ measurements in different environments and for several application fields are being conducted. The main purpose of these campaigns is to support the development of scientific applications for EnMAP. In addition, the acquired data are input in the EnMAP end-to-end simulation tool (EeteS) and are employed to test data pre-processing and calibration-validation methods. The campaign data are made freely available to the scientific community under a Creative Commons Attribution-ShareAlike 4.0 International License. An overview of all available data is provided in in the EnMAP Flight Campaigns Metadata Portal http://www.enmap.org/?q=flights."
-    ],
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6148"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.ENMAP"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Imaging Spectroscopy"
-        },
-        {
-            "name": "Vegetation Ecology"
-        },
-        {
-            "name": "Environmental Gradients"
-        }
-    ],
-    "title": [
-        "D\u00f6beritzer Heide 2008/2009 - An EnMAP Preparatory Flight Campaign (Datasets)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/c1641ba0-df5e-5da3-8462-fd232808fd8a.json b/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/c1641ba0-df5e-5da3-8462-fd232808fd8a.json
deleted file mode 100644
index 90422e49..00000000
--- a/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/c1641ba0-df5e-5da3-8462-fd232808fd8a.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contributor": [
-        "Federal Ministry for Economic Affairs and Energy"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.5880/enmap.2017.002",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6284",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6284"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "GFZ Data Services"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "CC BY-SA 4.0"
-    ],
-    "SpatialCoverage": [
-        "51.77  11.87 51.82 11.97",
-        "51.77 11.87 51.82 11.97",
-        "51.77 11.84 51.88 11.94"
-    ],
-    "TemporalCoverage": [
-        "2016-11-30",
-        "2011-05-10T09:32:18/2011-05-10T11:07:26",
-        "2011-06-27T08:35:23/2011-06-27T10:16:44",
-        "2012-05-24T09:06:57/2012-05-24T11:12:03"
-    ],
-    "author": [
-        "Siegmann, Bastian",
-        "Jarmer, Thomas"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6284;2017-09-15T09:21:28Z;DOIDB;DOIDB.ENMAP;false;3;DOIDB.ENMAP;10.5880/enmap.2017.002;Jarmer, Thomas;0000-0002-4652-1640;University of Osnabrueck;Siegmann, Bastian;University of Osnabrueck;K\u00f6then 2011/ 2012 - An EnMAP Preparatory Flight Campaign;GFZ Data Services;2017;Imaging Spectroscopy;Precision Farming;Yield Estimation;Federal Ministry for Economic Affairs and Energy;Federal Ministry of Economics and Technology;Foerster, Saskia;0000-0001-7752-7394;GFZ German Research Centre for Geosciences, Potsdam, Germany;K\u00fcster Theres;GFZ German Research Centre for Geosciences, Potsdam, Germany;Elger, Kirsten;0000-0001-5140-8602;GFZ German Research Centre for Geosciences, Potsdam, Germany;2016-11-30;2011-05-10T09:32:18/2011-05-10T11:07:26;2011-06-27T08:35:23/2011-06-27T10:16:44;2012-05-24T09:06:57/2012-05-24T11:12:03;eng;Dataset;10.2312/enmap.2017.002;10.3390/rs70708830;10.3390/rs8110927;10.3390/rs71012737;10.1080/01431161.2015.1084438;http://www.enmap.org/?q=flights;CC BY-SA 4.0;The dataset is composed of hyperspectral imagery acquired during airplane overflights on May 10th, 2011, June 27th, 2011 and May 24th, 2012 consisting of 367 and 368 spectral bands, respective-ly, ranging from VIS to SWIR (400 - 2500 nm) wavelength regions. The hyperspectral image data was acquired in the framework of the  EnMAP preparation project HyLand (Hyperspectral remote sensing for the assessment of crop and soil parameters in precision farming and yield estimation). Within the project, innovative techniques were developed to derive crop and soil parameters from hyper-spectral remote sensing and terrestrial laser scanning data, which served as input parameters for novel yield estimation models. ;The Environmental Mapping and Analysis Program (EnMAP) is a German hyperspectral satellite mission that aims at monitoring and characterizing the Earth\u2019s environment on a global scale. EnMAP serves to measure and model key dynamic processes of the Earth\u2019s ecosystems by extract-ing geochemical, biochemical and biophysical parameters, which provide information on the status and evolution of various terrestrial and aquatic ecosystems. In the frame of the EnMAP preparatory phase, pre-flight campaigns including airborne and in-situ measurements in different environments and for several application fields are being conducted. The main purpose of these campaigns is to support the development of scientific applications for EnMAP. In addition, the acquired data are input in the EnMAP end-to-end simulation tool (EeteS) and are employed to test data pre-processing and calibration-validation methods. The campaign data are made freely available to the scientific community under a Creative Commons Attribution-ShareAlike 4.0 International License. An overview of all available data is provided in in the EnMAP Flight Campaigns Metadata Portal (http://www.enmap.org/?q=flightbeta).\n;51.77  11.87 51.82 11.97;Campaign 1, K\u00f6then;51.77 11.87 51.82 11.97;Campaign 2, K\u00f6then;51.77 11.84 51.88 11.94;Campaign 3, K\u00f6then",
-    "group": "enmap",
-    "groups": [
-        {
-            "name": "enmap"
-        }
-    ],
-    "name": "c1641ba0-df5e-5da3-8462-fd232808fd8a",
-    "notes": [
-        "The dataset is composed of hyperspectral imagery acquired during airplane overflights on May 10th, 2011, June 27th, 2011 and May 24th, 2012 consisting of 367 and 368 spectral bands, respective-ly, ranging from VIS to SWIR (400 - 2500 nm) wavelength regions. The hyperspectral image data was acquired in the framework of the  EnMAP preparation project HyLand (Hyperspectral remote sensing for the assessment of crop and soil parameters in precision farming and yield estimation). Within the project, innovative techniques were developed to derive crop and soil parameters from hyper-spectral remote sensing and terrestrial laser scanning data, which served as input parameters for novel yield estimation models. ",
-        "The Environmental Mapping and Analysis Program (EnMAP) is a German hyperspectral satellite mission that aims at monitoring and characterizing the Earth\u2019s environment on a global scale. EnMAP serves to measure and model key dynamic processes of the Earth\u2019s ecosystems by extract-ing geochemical, biochemical and biophysical parameters, which provide information on the status and evolution of various terrestrial and aquatic ecosystems. In the frame of the EnMAP preparatory phase, pre-flight campaigns including airborne and in-situ measurements in different environments and for several application fields are being conducted. The main purpose of these campaigns is to support the development of scientific applications for EnMAP. In addition, the acquired data are input in the EnMAP end-to-end simulation tool (EeteS) and are employed to test data pre-processing and calibration-validation methods. The campaign data are made freely available to the scientific community under a Creative Commons Attribution-ShareAlike 4.0 International License. An overview of all available data is provided in in the EnMAP Flight Campaigns Metadata Portal (http://www.enmap.org/?q=flightbeta).\n"
-    ],
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6284"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.ENMAP"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Imaging Spectroscopy"
-        },
-        {
-            "name": "Precision Farming"
-        },
-        {
-            "name": "Yield Estimation"
-        }
-    ],
-    "title": [
-        "K\u00f6then 2011/ 2012 - An EnMAP Preparatory Flight Campaign"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/ce62baad-ecd3-564f-aa27-25f8d2136742.json b/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/ce62baad-ecd3-564f-aa27-25f8d2136742.json
deleted file mode 100644
index 542e2e27..00000000
--- a/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/ce62baad-ecd3-564f-aa27-25f8d2136742.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Hank, Tobias Benedikt"
-    ],
-    "Contributor": [
-        "BMWI"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.5880/enmap.2015.003",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6147",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6147"
-    ],
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "GFZ Data Services"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "CC BY-SA 4.0"
-    ],
-    "SpatialCoverage": "(49N-49N,13E-13E)",
-    "TemporalCoverage": [
-        "2012-03-09",
-        "2012-03-09",
-        "2011-09-10T08:00:00/2011-09-10T10:00:00"
-    ],
-    "author": [
-        "Richter, Katja",
-        "Locherer, Matthias",
-        "Hank, Tobias Benedikt",
-        "Mauser, Wolfram",
-        "Frank, Toni"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6147;2016-11-25T13:58:00Z;DOIDB;DOIDB.ENMAP;false;3;DOIDB.ENMAP;10.5880/enmap.2015.003;Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Richter, Katja;F-6957-2010;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Locherer, Matthias;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Frank, Toni;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Mauser, Wolfram;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Neusling (Landau a.d. Isar) 2011 - An Agricultural EnMAP Preparatory Flight Campaign Using the APEX Instrument (Datasets);GFZ Data Services;2015;Hyperspectral Imagery;Field Spectroscopy;Agriculture;LAI;Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Hank, Tobias Benedikt;K-5087-2012;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Richter, Katja;F-6957-2010;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Richter, Katja;F-6957-2010;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Richter, Katja;F-6957-2010;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Richter, Katja;F-6957-2010;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Locherer, Matthias;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Locherer, Matthias;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Locherer, Matthias;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Frank, Toni;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Frank, Toni;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Frank, Toni;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);Mauser, Wolfram;Dept. of Geography, Ludwig-Maximilian University Munich (Germany);BMWI;VITO;VITO;Meuleman, Koen;Meuleman, Koen;Meuleman, Koen;DLR;Hartmann, Ariane;Dotzler, Sandra;Putzenlechner, Birgitta;Foerster, Saskia;0000-0001-7752-7394;GFZ German Research Center for Geosciences;Brosinsky, Arlena;GFZ German Research Center for Geosciences;Elger, Kirsten;0000-0001-5140-8602;GFZ German Research Center for Geosciences;2012-03-09;2012-03-09;2011-09-10T08:00:00/2011-09-10T10:00:00;eng;Dataset;10.2312/enmap.2015.003;10.3390/rs70708830;http://www.enmap.org/?q=flights;CC BY-SA 4.0;This data collection contains airborne hyperspectral data as well as accompanying in-situ data acquired in autumn 2011 in the Neusling test area near Landau a.d. Isar in Southern Germany. The dataset is composed of a) three airborne hyperspectral image strips acquired during an overflight on September 10th, 2011 with the APEX instrument. The airborne data consists of 288 spectral bands, ranging from VIS to SWIR (413 - 2449 nm). A mosaic of the three image strips covering the Neusling test area is also provided; b) spectral reference and control measurements acquired with a portable ASD FieldSpec 3 JR spectroradiometer in 2150 spectral bands (350 - 2500nm) taken parallel to the overflight; c) a spatially comprehensive land use/land cover map generated from in-situ observations during the days next to the overflight; d) Flight-parallel in-situ point-measurements consisting of: i) non-destructively measured leaf area index of sugar beet, maize, grassland and legumes (105 measurements incl. standard deviations), ii) SPAD chlorophyll measurements (106 measurements incl. standard deviations), iii) 106 measurements of canopy height (incl. standard deviations). The dataset was collected with an agricultural focus.;The Environmental Mapping and Analysis Program (EnMAP) is a German hyperspectral satellite mission that aims at monitoring and characterizing the Earth\u2019s environment on a global scale. EnMAP serves to measure and model key dynamic processes of the Earth\u2019s ecosystems by extracting geochemical, biochemical and biophysical parameters, which provide information on the status and evolution of various terrestrial and aquatic ecosystems. In the frame of the EnMAP preparatory phase, pre-flight campaigns including airborne and in-situ measurements in different environments and for several application fields are being conducted. The main purpose of these campaigns is to support the development of scientific applications for EnMAP. In addition, the acquired data are input in the EnMAP end-to-end simulation tool (EeteS) and are employed to test data pre-processing and calibration-validation methods. The campaign data are made freely available to the scientific community under a Creative Commons Attribution-ShareAlike 4.0 International License. An overview of all available data is provided in in the EnMAP Flight Campaigns Metadata Portal http://www.enmap.org/?q=flights.;48.678265 12.838639 48.706162 12.893916;APEX Imaging Flight Mosaic Neusling",
-    "group": "enmap",
-    "groups": [
-        {
-            "name": "enmap"
-        }
-    ],
-    "name": "ce62baad-ecd3-564f-aa27-25f8d2136742",
-    "notes": [
-        "This data collection contains airborne hyperspectral data as well as accompanying in-situ data acquired in autumn 2011 in the Neusling test area near Landau a.d. Isar in Southern Germany. The dataset is composed of a) three airborne hyperspectral image strips acquired during an overflight on September 10th, 2011 with the APEX instrument. The airborne data consists of 288 spectral bands, ranging from VIS to SWIR (413 - 2449 nm). A mosaic of the three image strips covering the Neusling test area is also provided; b) spectral reference and control measurements acquired with a portable ASD FieldSpec 3 JR spectroradiometer in 2150 spectral bands (350 - 2500nm) taken parallel to the overflight; c) a spatially comprehensive land use/land cover map generated from in-situ observations during the days next to the overflight; d) Flight-parallel in-situ point-measurements consisting of: i) non-destructively measured leaf area index of sugar beet, maize, grassland and legumes (105 measurements incl. standard deviations), ii) SPAD chlorophyll measurements (106 measurements incl. standard deviations), iii) 106 measurements of canopy height (incl. standard deviations). The dataset was collected with an agricultural focus.",
-        "The Environmental Mapping and Analysis Program (EnMAP) is a German hyperspectral satellite mission that aims at monitoring and characterizing the Earth\u2019s environment on a global scale. EnMAP serves to measure and model key dynamic processes of the Earth\u2019s ecosystems by extracting geochemical, biochemical and biophysical parameters, which provide information on the status and evolution of various terrestrial and aquatic ecosystems. In the frame of the EnMAP preparatory phase, pre-flight campaigns including airborne and in-situ measurements in different environments and for several application fields are being conducted. The main purpose of these campaigns is to support the development of scientific applications for EnMAP. In addition, the acquired data are input in the EnMAP end-to-end simulation tool (EeteS) and are employed to test data pre-processing and calibration-validation methods. The campaign data are made freely available to the scientific community under a Creative Commons Attribution-ShareAlike 4.0 International License. An overview of all available data is provided in in the EnMAP Flight Campaigns Metadata Portal http://www.enmap.org/?q=flights."
-    ],
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6147"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.ENMAP"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[12.838639,48.678265],[12.838639,48.706162],[12.893916,48.706162],[12.893916,48.678265],[12.838639,48.678265]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Hyperspectral Imagery"
-        },
-        {
-            "name": "Field Spectroscopy"
-        },
-        {
-            "name": "Agriculture"
-        },
-        {
-            "name": "LAI"
-        }
-    ],
-    "title": [
-        "Neusling (Landau a.d. Isar) 2011 - An Agricultural EnMAP Preparatory Flight Campaign Using the APEX Instrument (Datasets)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/d71bddc0-2d29-5c77-95fb-1ad37dda327d.json b/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/d71bddc0-2d29-5c77-95fb-1ad37dda327d.json
deleted file mode 100644
index 67047c54..00000000
--- a/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/d71bddc0-2d29-5c77-95fb-1ad37dda327d.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Buddenbaum, Henning"
-    ],
-    "Contributor": [
-        "Federal Ministry of Economic Affairs and Energy"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.5880/enmap.2015.005",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6140",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6140"
-    ],
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "GFZ Data Services"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "CC BY-SA 4.0"
-    ],
-    "SpatialCoverage": "(50N-50N,7 E-7 E)",
-    "TempCoverageBegin": 63566420399,
-    "TempCoverageEnd": 63566420399,
-    "TemporalCoverage": " period : ( 2015-05-05T11:59:59Z - 2015-05-05T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2015-05-05T11:59:59Z",
-    "TemporalCoverage:EndDate": "2015-05-05T11:59:59Z",
-    "author": [
-        "Dotzler, Sandra",
-        "Buddenbaum, Henning",
-        "Hill, Joachim"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6140;2016-11-25T13:58:02Z;DOIDB;DOIDB.ENMAP;false;3;DOIDB.ENMAP;10.5880/enmap.2015.005;Buddenbaum, Henning;0000-0002-0956-5628;University of Trier, Environmental Remote Sensing and Geoinformatics, Trier, Germany;Dotzler, Sandra;0000-0002-8171-2944;University of Trier, Environmental Remote Sensing and Geoinformatics, Trier, Germany;Hill, Joachim;University of Trier, Environmental Remote Sensing and Geoinformatics, Trier, Germany;Nationalpark Hunsr\u00fcck-Hochwald, 2014-05-05 - An EnMAP Preparatory Flight Campaign (Datasets);GFZ Data Services;2015;Imaging Spectroscopy;Vegetation Ecology;Forest;Buddenbaum, Henning;0000-0002-0956-5628;University of Trier, Environmental Remote Sensing and Geoinformatics, Trier, Germany;Buddenbaum, Henning;0000-0002-0956-5628;University of Trier, Environmental Remote Sensing and Geoinformatics, Trier, Germany;Dotzler, Sandra;0000-0002-8171-2944;University of Trier, Environmental Remote Sensing and Geoinformatics, Trier, Germany;Dotzler, Sandra;0000-0002-8171-2944;University of Trier, Environmental Remote Sensing and Geoinformatics, Trier, Germany;Hill, Joachim;University of Trier, Environmental Remote Sensing and Geoinformatics, Trier, Germany;Federal Ministry of Economic Affairs and Energy;Federal Ministry of Economic Affairs and Energy;Foerster, Saskia;0000-0001-7752-7394;GFZ German Research Centre for Geosciences;Kuester, Theres;GFZ German Research Centre for Geosciences;Elger, Kirsten;0000-0001-5140-8602;GFZ German Research Centre for Geosciences;2015-05-05;2015-05-05T12:22:00/2015-05-05T14:21:00;eng;Dataset;10.2312/enmap.2015.005;10.1080/01431160500285076;10.1080/01431161.2013.776721;10.3390/rs70708830;http://www.enmap.org/?q=flights;CC BY-SA 4.0;The dataset consists of hyperspectral imagery acquired during airplane overflights on 5th May 2014 that contain 242 spectral bands, ranging from VIS to SWIR (423 - 2438 nm) wavelength regions. It covers an area of about 116 km\u00b2 which is dominated by spruce and beech forests. The flight campaign was part of several campaigns aiming at the creation of a multitemporal hyperspectral data set of the newly founded National Park Hunsr\u00fcck-Hochwald in Rhineland Palatinate, Germany. ;The Environmental Mapping and Analysis Program (EnMAP) is a German hyperspectral satellite mission that aims at monitoring and characterizing the Earth\u2019s environment on a global scale. EnMAP serves to measure and model key dynamic processes of the Earth\u2019s ecosystems by extracting geochemical, biochemical and biophysical parameters, which provide information on the status and evolution of various terrestrial and aquatic ecosystems. In the frame of the EnMAP preparatory phase, pre-flight campaigns including airborne and in-situ measurements in different environments and for several application fields are being conducted. The main purpose of these campaigns is to support the development of scientific applications for EnMAP. In addition, the acquired data are input in the EnMAP end-to-end simulation tool (EeteS) and are employed to test data pre-processing and calibration-validation methods. The campaign data are made freely available to the scientific community under a Creative Commons Attribution-ShareAlike 4.0 International License. An overview of all available data is provided in in the EnMAP Flight Campaigns Metadata Portal http://www.enmap.org/?q=flights.;49.62316641036846 6.93511962890625 49.75997752330658 7.1575927734375;HySpex, 22 Flight Lines",
-    "group": "enmap",
-    "groups": [
-        {
-            "name": "enmap"
-        }
-    ],
-    "name": "d71bddc0-2d29-5c77-95fb-1ad37dda327d",
-    "notes": [
-        "The dataset consists of hyperspectral imagery acquired during airplane overflights on 5th May 2014 that contain 242 spectral bands, ranging from VIS to SWIR (423 - 2438 nm) wavelength regions. It covers an area of about 116 km\u00b2 which is dominated by spruce and beech forests. The flight campaign was part of several campaigns aiming at the creation of a multitemporal hyperspectral data set of the newly founded National Park Hunsr\u00fcck-Hochwald in Rhineland Palatinate, Germany. ",
-        "The Environmental Mapping and Analysis Program (EnMAP) is a German hyperspectral satellite mission that aims at monitoring and characterizing the Earth\u2019s environment on a global scale. EnMAP serves to measure and model key dynamic processes of the Earth\u2019s ecosystems by extracting geochemical, biochemical and biophysical parameters, which provide information on the status and evolution of various terrestrial and aquatic ecosystems. In the frame of the EnMAP preparatory phase, pre-flight campaigns including airborne and in-situ measurements in different environments and for several application fields are being conducted. The main purpose of these campaigns is to support the development of scientific applications for EnMAP. In addition, the acquired data are input in the EnMAP end-to-end simulation tool (EeteS) and are employed to test data pre-processing and calibration-validation methods. The campaign data are made freely available to the scientific community under a Creative Commons Attribution-ShareAlike 4.0 International License. An overview of all available data is provided in in the EnMAP Flight Campaigns Metadata Portal http://www.enmap.org/?q=flights."
-    ],
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6140"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.ENMAP"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[6.93511962890625,49.62316641036846],[6.93511962890625,49.75997752330658],[7.1575927734375,49.75997752330658],[7.1575927734375,49.62316641036846],[6.93511962890625,49.62316641036846]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Imaging Spectroscopy"
-        },
-        {
-            "name": "Vegetation Ecology"
-        },
-        {
-            "name": "Forest"
-        }
-    ],
-    "title": [
-        "Nationalpark Hunsr\u00fcck-Hochwald, 2014-05-05 - An EnMAP Preparatory Flight Campaign (Datasets)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/ea3f2c5f-839a-50d2-afb9-dd91d0092860.json b/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/ea3f2c5f-839a-50d2-afb9-dd91d0092860.json
deleted file mode 100644
index ecad10fd..00000000
--- a/oaitestdata/enmap-oai_datacite/DOIDB.ENMAP_1/json/ea3f2c5f-839a-50d2-afb9-dd91d0092860.json
+++ /dev/null
@@ -1,95 +0,0 @@
-{
-    "Contact": [
-        "Foerster, Saskia"
-    ],
-    "Contributor": [
-        "EUFAR Transnational Access",
-        "BMWi"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.5880/enmap.2015.007",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6150",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6150"
-    ],
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "GFZ Data Services"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "CC BY-SA 4.0"
-    ],
-    "SpatialCoverage": [
-        "42.4379 0.4789 42.2710 0.5800",
-        "42.4361 0.4719 42.2716 0.5737",
-        "42.4361 0.4719 42.2716 0.5737",
-        "42.4379 0.4789 42.2710 0.5800",
-        "42.4361 0.4719 42.2716 0.5737"
-    ],
-    "TemporalCoverage": [
-        "2015-04",
-        "2011-04-02",
-        "2011-08-09",
-        "2011-08-09",
-        "2011-04",
-        "2011-08"
-    ],
-    "author": [
-        "Foerster, Saskia",
-        "Brosinsky, Arlena",
-        "Wilczok, Charlotte",
-        "Bauer, Marcus"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6150;2016-11-25T13:58:04Z;DOIDB;DOIDB.ENMAP;false;3;DOIDB.ENMAP;10.5880/enmap.2015.007;Foerster, Saskia;0000-0001-7752-7394;GFZ German Research Centre for Geosciences;Brosinsky, Arlena;GFZ German Research Centre for Geosciences;Wilczok, Charlotte;GFZ German Research Centre for Geosciences;Bauer, Marcus;University of Potsdam;Is\u00e1bena 2011 - An EnMAP Preparatory Flight Campaign (Datasets);GFZ Data Services;2015;Imaging Spectroscopy;Airborne Laserscanning;Mediterranean drylands;Ground fractional cover;Foerster, Saskia;0000-0001-7752-7394;GFZ German Research Centre for Geosciences;Foerster, Saskia;0000-0001-7752-7394;GFZ German Research Centre for Geosciences;Foerster, Saskia;0000-0001-7752-7394;GFZ German Research Centre for Geosciences;Brosinsky, Arlena;GFZ German Research Centre for Geosciences;Brosinsky, Arlena;GFZ German Research Centre for Geosciences;Wilczok, Charlotte;GFZ German Research Centre for Geosciences;Wilczok, Charlotte;GFZ German Research Centre for Geosciences;Bauer, Marcus;University of Potsdam;Bauer, Marcus;University of Potsdam;Bauer, Marcus;University of Potsdam;Bauer, Marcus;University of Potsdam;BMWi;Federal Ministry of Economics and Technology;EUFAR Transnational Access;EUFAR Transnational Access;Klinke, Randolf;GFZ German Research Centre for Geosciences;H\u00f6rhold, Simon;University of Potsdam;Lindenthal, Elfrun;University of Potsdam;Elger, Kirsten;0000-0001-5140-8602;GFZ German Research Centre for Geosciences;Brauer, Arne;University of Potsdam;2015-04;2011-04-02;2011-08-09;2011-08-09;2011-04;2011-08;eng;Dataset;10.3390/rs70708830;10.2312/enmap.2015.007;10.1007/s11368-014-0992-3;http://www.enmap.org/?q=flights;CC BY-SA 4.0;The dataset is composed of a) hyperspectral imagery acquired with AISA Eagle and Hawk imaging spectrometer data in the range 400 to 2500 nm on April 2 and August 9, 2011, with a ground sampling distance of 4 m in 12 and 15 flight lines, respectively; b) airborne LiDAR data acquired in single-pulse mode in August 2011 concurrent with hyperspectral data acquisition with an avarage point density of 0.7 hits per meter squared; c) spectral reference measurements acquired with a portable ASD field spectroradiometer around the days of image acquisitions d) fractional cover of green vegetation, dry vegetation, bare soil and rock were visually estimated for 60 (April) and 53 (August) transects of 20-m length. The overall goal of the study was to investigate the potential of hyperspectral and LiDAR data for assessing sediment connectivity at the hillslope to subcatchment scale. For that the fractional cover of green vegetation, dry vegetation, bare soil and rock was derived\nby applying a multiple endmember spectral mixture analysis approach to the hyperspectral image data. The LiDAR point clouds were pre-processed to generate a digital elevation map as well as a vegetation height map, both with 4-m spatial resolution.;The Environmental Mapping and Analysis Program (EnMAP) is a German hyperspectral satellite mission that aims at monitoring and characterizing the Earth\u2019s environment on a global scale. EnMAP serves to measure and model key dynamic processes of the Earth\u2019s ecosystems by extracting geochemical, biochemical and biophysical parameters, which provide information on the status and evolution of various terrestrial and aquatic ecosystems. In the frame of the EnMAP preparatory phase, pre-flight campaigns including airborne and in-situ measurements in different environments and for several application fields are being conducted. The main purpose of these campaigns is to support the development of scientific applications for EnMAP. In addition, the acquired data are input in the EnMAP end-to-end simulation tool (EeteS) and are employed to test data pre-processing and calibration-validation methods. The campaign data are made freely available to the scientific community under a Creative Commons Attribution-ShareAlike 4.0 International License. An overview of all available data is provided in in the EnMAP Flight Campaigns Metadata Portal http://www.enmap.org/?q=flights.;42.4379 0.4789 42.2710 0.5800;AISA Eagle and Hawk, Isabena, Spain;42.4361 0.4719 42.2716 0.5737;AISA Eagle and Hawk, Isabena, Spain;42.4361 0.4719 42.2716 0.5737;Airborne LiDAR, Isabena, Spain;42.4379 0.4789 42.2710 0.5800;Ground fractional cover in-situ estimation April, Isabena, Spain;42.4361 0.4719 42.2716 0.5737;Ground fractional cover in-situ estimation August, Isabena, Spain",
-    "group": "enmap",
-    "groups": [
-        {
-            "name": "enmap"
-        }
-    ],
-    "name": "ea3f2c5f-839a-50d2-afb9-dd91d0092860",
-    "notes": [
-        "The dataset is composed of a) hyperspectral imagery acquired with AISA Eagle and Hawk imaging spectrometer data in the range 400 to 2500 nm on April 2 and August 9, 2011, with a ground sampling distance of 4 m in 12 and 15 flight lines, respectively; b) airborne LiDAR data acquired in single-pulse mode in August 2011 concurrent with hyperspectral data acquisition with an avarage point density of 0.7 hits per meter squared; c) spectral reference measurements acquired with a portable ASD field spectroradiometer around the days of image acquisitions d) fractional cover of green vegetation, dry vegetation, bare soil and rock were visually estimated for 60 (April) and 53 (August) transects of 20-m length. The overall goal of the study was to investigate the potential of hyperspectral and LiDAR data for assessing sediment connectivity at the hillslope to subcatchment scale. For that the fractional cover of green vegetation, dry vegetation, bare soil and rock was derived\nby applying a multiple endmember spectral mixture analysis approach to the hyperspectral image data. The LiDAR point clouds were pre-processed to generate a digital elevation map as well as a vegetation height map, both with 4-m spatial resolution.",
-        "The Environmental Mapping and Analysis Program (EnMAP) is a German hyperspectral satellite mission that aims at monitoring and characterizing the Earth\u2019s environment on a global scale. EnMAP serves to measure and model key dynamic processes of the Earth\u2019s ecosystems by extracting geochemical, biochemical and biophysical parameters, which provide information on the status and evolution of various terrestrial and aquatic ecosystems. In the frame of the EnMAP preparatory phase, pre-flight campaigns including airborne and in-situ measurements in different environments and for several application fields are being conducted. The main purpose of these campaigns is to support the development of scientific applications for EnMAP. In addition, the acquired data are input in the EnMAP end-to-end simulation tool (EeteS) and are employed to test data pre-processing and calibration-validation methods. The campaign data are made freely available to the scientific community under a Creative Commons Attribution-ShareAlike 4.0 International License. An overview of all available data is provided in in the EnMAP Flight Campaigns Metadata Portal http://www.enmap.org/?q=flights."
-    ],
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6150"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.ENMAP"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Imaging Spectroscopy"
-        },
-        {
-            "name": "Airborne Laserscanning"
-        },
-        {
-            "name": "Mediterranean drylands"
-        },
-        {
-            "name": "Ground fractional cover"
-        }
-    ],
-    "title": [
-        "Is\u00e1bena 2011 - An EnMAP Preparatory Flight Campaign (Datasets)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/0343f106-2baa-5a03-968f-45b15f6a923c.json b/oaitestdata/envidat-datacite/SET_1/json/0343f106-2baa-5a03-968f-45b15f6a923c.json
deleted file mode 100644
index 17eced3c..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/0343f106-2baa-5a03-968f-45b15f6a923c.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Ionu\u021b Iosifescu Enescu"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "GeoTIFF",
-        "TIF",
-        "JPEG"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:a16c451d-0f31-4e3d-bbc5-6243e42c599b",
-    "MetadataAccess": [
-        "oai:envidat.ch:a16c451d-0f31-4e3d-bbc5-6243e42c599b"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/datasets-for-testing-the-repository-and-storage"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(90S-90N,180W-180E)",
-    "TempCoverageBegin": 63657230399,
-    "TempCoverageEnd": 63657230399,
-    "TemporalCoverage": " point in time : 2018-03-21T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-03-21T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-03-21T11:59:59Z",
-    "author": [
-        "Ionu\u021b Iosifescu Enescu"
-    ],
-    "fulltext": "oai:envidat.ch:a16c451d-0f31-4e3d-bbc5-6243e42c599b;2018-10-23T13:09:14Z;Ionu\u021b Iosifescu Enescu;0000-0002-1770-7833;WSL;Data set for testing the repository and file storage;2018;WSL;LARGE FILES;NATURAL EARTH;TEST;Ionu\u021b Iosifescu Enescu;0000-0002-1770-7833;WSL;2018-03-21;en;Dataset;https://www.envidat.ch/dataset/datasets-for-testing-the-repository-and-storage;482223 bytes;238021628 bytes;476043256 bytes;1190108140 bytes;1904173024 bytes;JPEG;TIF;GeoTIFF;1.0;Open Data Commons Open Database License (ODbL);This is a test dataset. The attached data are some large GIS raster files (GeoTIFFs) made with Natural Earth data. Natural Earth is a free vector and raster map data @ naturalearthdata.com. The data used for creating these large files was the \"Cross Blended Hypso with Shaded Relief and Water\". Data was concatenated to achieve larger and larger files. Internal pyramids were created, in order that the files can be opened easily in a GIS software such as QGIS or by a (future) GIS data visualisation module integrated in EnviDat.;-90.0 -180.0 90.0 180.0;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "0343f106-2baa-5a03-968f-45b15f6a923c",
-    "notes": [
-        "This is a test dataset. The attached data are some large GIS raster files (GeoTIFFs) made with Natural Earth data. Natural Earth is a free vector and raster map data @ naturalearthdata.com. The data used for creating these large files was the \"Cross Blended Hypso with Shaded Relief and Water\". Data was concatenated to achieve larger and larger files. Internal pyramids were created, in order that the files can be opened easily in a GIS software such as QGIS or by a (future) GIS data visualisation module integrated in EnviDat."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:a16c451d-0f31-4e3d-bbc5-6243e42c599b"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-180.0,-90.0],[-180.0,90.0],[180.0,90.0],[180.0,-90.0],[-180.0,-90.0]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "LARGE FILES"
-        },
-        {
-            "name": "NATURAL EARTH"
-        },
-        {
-            "name": "TEST"
-        }
-    ],
-    "title": [
-        "Data set for testing the repository and file storage"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/0540c2a7-8f0e-5b20-a08a-98e75a3f861f.json b/oaitestdata/envidat-datacite/SET_1/json/0540c2a7-8f0e-5b20-a08a-98e75a3f861f.json
deleted file mode 100644
index 296c6c9e..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/0540c2a7-8f0e-5b20-a08a-98e75a3f861f.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Marcia Phillips"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "SMET"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:7c4c3231-6903-45fc-a9a6-ddda5edb89a9",
-    "MetadataAccess": [
-        "oai:envidat.ch:7c4c3231-6903-45fc-a9a6-ddda5edb89a9"
-    ],
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/gem2"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N,9 E)",
-    "TempCoverageBegin": 63501620399,
-    "TempCoverageEnd": 63501620399,
-    "TemporalCoverage": " point in time : 2013-04-15T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2013-04-15T11:59:59Z",
-    "TemporalCoverage:EndDate": "2013-04-15T11:59:59Z",
-    "author": [
-        "Marcia Phillips"
-    ],
-    "fulltext": "oai:envidat.ch:7c4c3231-6903-45fc-a9a6-ddda5edb89a9;2018-07-06T22:13:05Z;Marcia Phillips;WSL Institute for snow and avalanche research SLF;GEM2: Meteorological and snow station at Gemsstock (3021 m asl), Canton Uri, Switzerland;2016;Swiss Federal Research Institute WSL;LONGWAVE RADIATION;METEO STATION;SHORTWAVE RADIATION;SNOW HEIGHT;Marcia Phillips;Swiss Federal Research Institute WSL;2013-04-15;en;Dataset;https://www.envidat.ch/dataset/gem2;SMET;1.0;Open Data Commons Open Database License (ODbL);Meteorological station at Gemstock (3021 m asl) in Canton Uri. The station includes in/out LW/SW and a snow height sensor.;46.60369 8.60904;Gemsstock, Uri, Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "0540c2a7-8f0e-5b20-a08a-98e75a3f861f",
-    "notes": [
-        "Meteorological station at Gemstock (3021 m asl) in Canton Uri. The station includes in/out LW/SW and a snow height sensor."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:7c4c3231-6903-45fc-a9a6-ddda5edb89a9"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[8.60904,46.60369],[8.60904,46.60369],[8.60904,46.60369],[8.60904,46.60369],[8.60904,46.60369]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "LONGWAVE RADIATION"
-        },
-        {
-            "name": "METEO STATION"
-        },
-        {
-            "name": "SHORTWAVE RADIATION"
-        },
-        {
-            "name": "SNOW HEIGHT"
-        }
-    ],
-    "title": [
-        "GEM2: Meteorological and snow station at Gemsstock (3021 m asl), Canton Uri, Switzerland"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/0b2121c1-5a3e-546b-bad1-e74a35e857d7.json b/oaitestdata/envidat-datacite/SET_1/json/0b2121c1-5a3e-546b-bad1-e74a35e857d7.json
deleted file mode 100644
index 5a2868c5..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/0b2121c1-5a3e-546b-bad1-e74a35e857d7.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Avalanche Warning Service SLF"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/13",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "CSV"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:f7160261-c98d-4d49-8966-10c1b0a32831",
-    "MetadataAccess": [
-        "oai:envidat.ch:f7160261-c98d-4d49-8966-10c1b0a32831"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avalanche Research SLF"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/fatal-avalanche-accidents-switzerland-1995"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "SLF"
-    ],
-    "fulltext": "oai:envidat.ch:f7160261-c98d-4d49-8966-10c1b0a32831;2018-12-09T00:31:45Z;10.16904/13;SLF;WSL Institute for Snow and Avalanche Research SLF;Fatal avalanche accidents in Switzerland since 1995-1996;2018;WSL Institute for Snow and Avalanche Research SLF;AVALANCHE ACCIDENT STATISTICS;AVALANCHE ACCIDENTS;AVALANCHE FATALITIES;Avalanche Warning Service SLF;WSL Institute for Snow and Avalanche Research SLF;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/fatal-avalanche-accidents-switzerland-1995;43522 bytes;CSV;1.0;Open Data Commons Open Database License (ODbL);This data collection contains information concerning all accidents by snow avalanches causing at least one fatality in Switzerland. The data set commences on 01/10/1995. After the completion of a hydrological year, the new data is added.  \n\nThe following information is provided:    \n\n * avalanche identifier   \n * date of the accident  \n * accuracy of the date in range of days before and after  \n * canton  \n * name of the locality  \n * start zone of the avalanche  \n   * coordinates (Swiss coordinate system, approximately in middle of start zone)  \n   * accuracy of the coordinates in meters\n  * elevation (in meteres above sea level, app. in middle of start zone)  \n  * slope aspect (main orientation of start zone)   \n  * slope inclination (in degree, steepest point within start zone)    \n * number of dead persons   \n * number of caught persons  \n * number of fully buried persons    \n * forecasted avalanche danger level   \n * activity/location of the accident party at the time of the incident;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "0b2121c1-5a3e-546b-bad1-e74a35e857d7",
-    "notes": [
-        "This data collection contains information concerning all accidents by snow avalanches causing at least one fatality in Switzerland. The data set commences on 01/10/1995. After the completion of a hydrological year, the new data is added.  \n\nThe following information is provided:    \n\n * avalanche identifier   \n * date of the accident  \n * accuracy of the date in range of days before and after  \n * canton  \n * name of the locality  \n * start zone of the avalanche  \n   * coordinates (Swiss coordinate system, approximately in middle of start zone)  \n   * accuracy of the coordinates in meters\n  * elevation (in meteres above sea level, app. in middle of start zone)  \n  * slope aspect (main orientation of start zone)   \n  * slope inclination (in degree, steepest point within start zone)    \n * number of dead persons   \n * number of caught persons  \n * number of fully buried persons    \n * forecasted avalanche danger level   \n * activity/location of the accident party at the time of the incident"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:f7160261-c98d-4d49-8966-10c1b0a32831"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "AVALANCHE ACCIDENT STATISTICS"
-        },
-        {
-            "name": "AVALANCHE ACCIDENTS"
-        },
-        {
-            "name": "AVALANCHE FATALITIES"
-        }
-    ],
-    "title": [
-        "Fatal avalanche accidents in Switzerland since 1995-1996"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/0b9b8142-f20c-5153-b303-0fd489408fe8.json b/oaitestdata/envidat-datacite/SET_1/json/0b9b8142-f20c-5153-b303-0fd489408fe8.json
deleted file mode 100644
index 92050562..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/0b9b8142-f20c-5153-b303-0fd489408fe8.json
+++ /dev/null
@@ -1,91 +0,0 @@
-{
-    "Contact": [
-        "Christoph Marty"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/15",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "TXT",
-        "CSV"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:213846c4-2697-4ab5-b08a-983380bf9b4e",
-    "MetadataAccess": [
-        "oai:envidat.ch:213846c4-2697-4ab5-b08a-983380bf9b4e"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avalanche Research SLF"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/gcos-swe-data"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": [
-        "46.55818213 7.890192955",
-        "46.63294615 8.591917728",
-        "46.79121008 8.395290837",
-        "46.50461379 8.308282838",
-        "46.02340309 7.751164932",
-        "46.81254897 9.848163035",
-        "46.86057949 9.895973081",
-        "46.82938238 9.8092511",
-        "46.46326154 9.184634236",
-        "46.59981095 10.41934353",
-        "46.60433181 9.962675638"
-    ],
-    "TempCoverageBegin": 61438651199,
-    "TempCoverageEnd": 61438651199,
-    "TemporalCoverage": " point in time : 1947-12-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1947-12-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1947-12-01T11:59:59Z",
-    "author": [
-        "Christoph Marty"
-    ],
-    "fulltext": "oai:envidat.ch:213846c4-2697-4ab5-b08a-983380bf9b4e;2018-07-12T09:01:15Z;10.16904/15;Christoph Marty;WSL Institute for Snow and Avalanche Research SLF;GCOS SWE data from 11 stations in Switzerland;2017;WSL Institute for Snow and Avalanche Research SLF;GCOS;SNOW HEIGHT;SNOW WATER EQUIVALENT;Christoph Marty;WSL Institute for Snow and Avalanche Research SLF;1947-12-01;en;https://www.envidat.ch/dataset/gcos-swe-data;TXT;CSV;1;Open Data Commons Open Database License (ODbL);Snowprofile from 11 observer sites in Switzerland compiled for the Global Climate Observing System (GCOS).  Height of snow (cm) and snow water equivalent (mm) are recorded every 2 weeks since the 1947 (depending on station). Attached metadata file gives details of each station.;46.55818213 7.890192955;46.63294615 8.591917728;46.79121008 8.395290837;46.50461379 8.308282838;46.02340309 7.751164932;46.81254897 9.848163035;46.86057949 9.895973081;46.82938238 9.8092511;46.46326154 9.184634236;46.59981095 10.41934353;46.60433181 9.962675638;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "0b9b8142-f20c-5153-b303-0fd489408fe8",
-    "notes": [
-        "Snowprofile from 11 observer sites in Switzerland compiled for the Global Climate Observing System (GCOS).  Height of snow (cm) and snow water equivalent (mm) are recorded every 2 weeks since the 1947 (depending on station). Attached metadata file gives details of each station."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:213846c4-2697-4ab5-b08a-983380bf9b4e"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "GCOS"
-        },
-        {
-            "name": "SNOW HEIGHT"
-        },
-        {
-            "name": "SNOW WATER EQUIVALENT"
-        }
-    ],
-    "title": [
-        "GCOS SWE data from 11 stations in Switzerland"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/0bb3520e-ac08-530e-885e-6c0e705ff769.json b/oaitestdata/envidat-datacite/SET_1/json/0bb3520e-ac08-530e-885e-6c0e705ff769.json
deleted file mode 100644
index 7dba99c2..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/0bb3520e-ac08-530e-885e-6c0e705ff769.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Nander Wever"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/2",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "DAT",
-        "TXT"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:0b294122-015c-46bf-b5c5-cc6d0a6f67c1",
-    "MetadataAccess": [
-        "oai:envidat.ch:0b294122-015c-46bf-b5c5-cc6d0a6f67c1"
-    ],
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avalanche Research SLF"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/10-16904-2"
-    ],
-    "ResourceType": [
-        "Snow Profile Measurements"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N,10E)",
-    "TempCoverageBegin": 63666471599,
-    "TempCoverageEnd": 63666471599,
-    "TemporalCoverage": " point in time : 2018-07-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-07-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-07-06T11:59:59Z",
-    "author": [
-        "WSL Institute for Snow and Avalanche Research SLF"
-    ],
-    "fulltext": "oai:envidat.ch:0b294122-015c-46bf-b5c5-cc6d0a6f67c1;2018-12-09T00:31:04Z;10.16904/2;WSL Institute for Snow and Avalanche Research SLF;SLF;Manual bi-weekly snow profiles from Weissfluhjoch, Davos, Switzerland;2015;WSL Institute for Snow and Avalanche Research SLF;SNOW DENSITY;SNOW ICE TEMPERATURE;SNOW STRATIGRAPHY;SNOW WATER EQUIVALENT;Nander Wever;SLF;2018-07-06;en;Snow Profile Measurements;https://www.envidat.ch/dataset/10-16904-2;DAT;TXT;1;Open Data Commons Open Database License (ODbL);Dataset of manual bi-weekly snow profiles from Weissfluhjoch, Davos, Switzerland. Typical snow profile measurements and observations are included (temperature, density, grain size, grain type, hardness, wetness), following the guidelines of the The International Classification for Seasonal Snow on the Ground (ICSSG) [Fierz, C., Armstrong, R.L., Durand, Y., Etchevers, P., Greene, E., McClung, D.M., Nishimura, K., Satyawali, P.K. and Sokratov, S.A. 2009. The International Classification for Seasonal Snow on the Ground. IHP-VII Technical Documents in Hydrology N\u00b083, IACS Contribution N\u00b01, UNESCO-IHP, Paris].;46.829598 9.809568;[46.829598 9.809568]",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "0bb3520e-ac08-530e-885e-6c0e705ff769",
-    "notes": [
-        "Dataset of manual bi-weekly snow profiles from Weissfluhjoch, Davos, Switzerland. Typical snow profile measurements and observations are included (temperature, density, grain size, grain type, hardness, wetness), following the guidelines of the The International Classification for Seasonal Snow on the Ground (ICSSG) [Fierz, C., Armstrong, R.L., Durand, Y., Etchevers, P., Greene, E., McClung, D.M., Nishimura, K., Satyawali, P.K. and Sokratov, S.A. 2009. The International Classification for Seasonal Snow on the Ground. IHP-VII Technical Documents in Hydrology N\u00b083, IACS Contribution N\u00b01, UNESCO-IHP, Paris]."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:0b294122-015c-46bf-b5c5-cc6d0a6f67c1"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[9.809568,46.829598],[9.809568,46.829598],[9.809568,46.829598],[9.809568,46.829598],[9.809568,46.829598]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "SNOW DENSITY"
-        },
-        {
-            "name": "SNOW ICE TEMPERATURE"
-        },
-        {
-            "name": "SNOW STRATIGRAPHY"
-        },
-        {
-            "name": "SNOW WATER EQUIVALENT"
-        }
-    ],
-    "title": [
-        "Manual bi-weekly snow profiles from Weissfluhjoch, Davos, Switzerland"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/1044c699-0fb6-5da9-aaca-edd719d9b463.json b/oaitestdata/envidat-datacite/SET_1/json/1044c699-0fb6-5da9-aaca-edd719d9b463.json
deleted file mode 100644
index 991ab310..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/1044c699-0fb6-5da9-aaca-edd719d9b463.json
+++ /dev/null
@@ -1,102 +0,0 @@
-{
-    "Contact": [
-        "Dirk Nikolaus Karger"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.5061/dryad.kd1d4",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:2adb0c83-4653-4337-af28-f75c63ab7c74",
-    "MetadataAccess": [
-        "oai:envidat.ch:2adb0c83-4653-4337-af28-f75c63ab7c74"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Dryad Digital Repository"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/chelsa-climatologies"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(90S-90N,180W-180E)",
-    "TempCoverageBegin": 63636231599,
-    "TempCoverageEnd": 63636231599,
-    "TemporalCoverage": " point in time : 2017-07-21T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2017-07-21T11:59:59Z",
-    "TemporalCoverage:EndDate": "2017-07-21T11:59:59Z",
-    "author": [
-        "Dirk Nikolaus Karger",
-        "J\u00fcrgen B\u00f6hner",
-        "Tobias Kawohl",
-        "Rodrigo Wilber Soria-Auza",
-        "H. Peter Linder",
-        "Olaf Conrad",
-        "Niklaus E. Zimmermann",
-        "Michael Kessler",
-        "Holger Kreft"
-    ],
-    "fulltext": "oai:envidat.ch:2adb0c83-4653-4337-af28-f75c63ab7c74;2018-12-09T00:23:51Z;10.5061/dryad.kd1d4;Dirk Nikolaus Karger;WSL;Olaf Conrad;University of Hamburg;J\u00fcrgen B\u00f6hner;University of Hamburg;Tobias Kawohl;University of Hamburg;Holger Kreft;University of Goettingen;Rodrigo Wilber Soria-Auza;Rodrigo Wilber Soria-Auza;Niklaus E. Zimmermann;WSL;H. Peter Linder;University of Zurich;Michael Kessler;University of Zurich;Climatologies at high resolution for the earth\u2019s land surface areas;2017;Dryad Digital Repository;BIOCLIM;CLIMATE;CLIMATE CHANGE;CLIMATE LAYERS;CLIMATOLOGY;FREE CLIMATE DATA;PRECIPITATION;TEMPERATURE;Dirk Nikolaus Karger;WSL;2017-07-21;en;Dataset;https://www.envidat.ch/dataset/chelsa-climatologies;1.2;Other (Open);High-resolution information on climatic conditions is essential to many applications in environmental and ecological sciences. Here we present the CHELSA (Climatologies at high resolution for the earth\u2019s land surface areas) data of downscaled model output temperature and precipitation estimates of the ERA-Interim climatic reanalysis to a high resolution of 30\u2009arc\u2009sec. The temperature algorithm is based on statistical downscaling of atmospheric temperatures. The precipitation algorithm incorporates orographic predictors including wind fields, valley exposition, and boundary layer height, with a subsequent bias correction. The resulting data consist of a monthly temperature and precipitation climatology for the years 1979\u20132013. We compare the data derived from the CHELSA algorithm with other standard gridded products and station data from the Global Historical Climate Network. We compare the performance of the new climatologies in species distribution modelling and show that we can increase the accuracy of species range predictions. We further show that CHELSA climatological data has a similar accuracy as other products for temperature, but that its predictions of precipitation patterns are better.\n\nData Variable Codes:\n\n- Bio1 = Annual Mean Temperature\n- Bio2 = Mean Diurnal Range\n- Bio3 = Isothermality\n- Bio4 = Temperature Seasonality\n- Bio5 = Max Temperature of Warmest Month\n- Bio6 = Min Temperature of Coldest Month\n- Bio7 = Temperature Annual Range\n- Bio8 = Mean Temperature of Wettest Quarter\n- Bio9 = Mean Temperature of Driest Quarter\n- Bio10 = Mean Temperature of Warmest Quarter\n- Bio11 = Mean Temperature of Coldest Quarter\n- Bio12 = Annual Precipitation\n- Bio13 = Precipitation of Wettest Month\n- Bio14 = Precipitation of Driest Month\n- Bio15 = Precipitation Seasonality\n- Bio16 = Precipitation of Wettest Quarter\n- Bio17 = Precipitation of Driest Quarter\n- Bio18 = Precipitation of Warmest Quarter\n- Bio19 = Precipitation of Coldest Quarter\n\n&nbsp;\n__Paper Citation:__\n > _Karger DN. et al. Climatologies at high resolution for the earth\u2019s land surface areas, Scientific Data, 4, 170122 (2017)  [doi: 10.1038/sdata.2017.122](https://doi.org/10.1038/sdata.2017.122)._;-90.0 -180.0 90.0 180.0;global",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "1044c699-0fb6-5da9-aaca-edd719d9b463",
-    "notes": [
-        "High-resolution information on climatic conditions is essential to many applications in environmental and ecological sciences. Here we present the CHELSA (Climatologies at high resolution for the earth\u2019s land surface areas) data of downscaled model output temperature and precipitation estimates of the ERA-Interim climatic reanalysis to a high resolution of 30\u2009arc\u2009sec. The temperature algorithm is based on statistical downscaling of atmospheric temperatures. The precipitation algorithm incorporates orographic predictors including wind fields, valley exposition, and boundary layer height, with a subsequent bias correction. The resulting data consist of a monthly temperature and precipitation climatology for the years 1979\u20132013. We compare the data derived from the CHELSA algorithm with other standard gridded products and station data from the Global Historical Climate Network. We compare the performance of the new climatologies in species distribution modelling and show that we can increase the accuracy of species range predictions. We further show that CHELSA climatological data has a similar accuracy as other products for temperature, but that its predictions of precipitation patterns are better.\n\nData Variable Codes:\n\n- Bio1 = Annual Mean Temperature\n- Bio2 = Mean Diurnal Range\n- Bio3 = Isothermality\n- Bio4 = Temperature Seasonality\n- Bio5 = Max Temperature of Warmest Month\n- Bio6 = Min Temperature of Coldest Month\n- Bio7 = Temperature Annual Range\n- Bio8 = Mean Temperature of Wettest Quarter\n- Bio9 = Mean Temperature of Driest Quarter\n- Bio10 = Mean Temperature of Warmest Quarter\n- Bio11 = Mean Temperature of Coldest Quarter\n- Bio12 = Annual Precipitation\n- Bio13 = Precipitation of Wettest Month\n- Bio14 = Precipitation of Driest Month\n- Bio15 = Precipitation Seasonality\n- Bio16 = Precipitation of Wettest Quarter\n- Bio17 = Precipitation of Driest Quarter\n- Bio18 = Precipitation of Warmest Quarter\n- Bio19 = Precipitation of Coldest Quarter\n\n&nbsp;\n__Paper Citation:__\n > _Karger DN. et al. Climatologies at high resolution for the earth\u2019s land surface areas, Scientific Data, 4, 170122 (2017)  [doi: 10.1038/sdata.2017.122](https://doi.org/10.1038/sdata.2017.122)._"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:2adb0c83-4653-4337-af28-f75c63ab7c74"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-180.0,-90.0],[-180.0,90.0],[180.0,90.0],[180.0,-90.0],[-180.0,-90.0]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "BIOCLIM"
-        },
-        {
-            "name": "CLIMATE"
-        },
-        {
-            "name": "CLIMATE CHANGE"
-        },
-        {
-            "name": "CLIMATE LAYERS"
-        },
-        {
-            "name": "CLIMATOLOGY"
-        },
-        {
-            "name": "FREE CLIMATE DATA"
-        },
-        {
-            "name": "PRECIPITATION"
-        },
-        {
-            "name": "TEMPERATURE"
-        }
-    ],
-    "title": [
-        "Climatologies at high resolution for the earth\u2019s land surface areas"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/10c8cae1-01ac-513b-b081-b7326d69a2f9.json b/oaitestdata/envidat-datacite/SET_1/json/10c8cae1-01ac-513b-b081-b7326d69a2f9.json
deleted file mode 100644
index b87e4d8a..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/10c8cae1-01ac-513b-b081-b7326d69a2f9.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Avalanche Warning Service SLF"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/envidat.32",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "CSV"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:b00052bc-11da-4c51-a062-ee1fa1d158d8",
-    "MetadataAccess": [
-        "oai:envidat.ch:b00052bc-11da-4c51-a062-ee1fa1d158d8"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/avalanche-fatalities-per-calendar-year-since-1936"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 61094260799,
-    "TempCoverageEnd": 61094260799,
-    "TemporalCoverage": " point in time : 1937-01-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1937-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1937-01-01T11:59:59Z",
-    "author": [
-        "SLF"
-    ],
-    "fulltext": "oai:envidat.ch:b00052bc-11da-4c51-a062-ee1fa1d158d8;2018-12-09T00:31:02Z;10.16904/envidat.32;SLF;WSL Institute for Snow and Avalanche Research SLF;Number of avalanche fatalities per calendar year in Switzerland since 1937;2018;AVALANCHE ACCIDENT STATISTICS;AVALANCHE FATALITIES;Avalanche Warning Service SLF;WSL Institute for Snow and Avalanchre Research SLF;1937-01-01;en;Dataset;https://www.envidat.ch/dataset/avalanche-fatalities-per-calendar-year-since-1936;1713 bytes;CSV;1.0;Open Data Commons Open Database License (ODbL);This dataset contains the statistics on the number of avalanche fatalities per **calendar year** in Switzerland. The data collection commences with the beginning of the year 1937. After the completion of a hydrological year, which  is the standard way avalanche fatalities are summarized in Switzerland and ends on the 30th of September, the new data is appended to the existing dataset.\nIf you require annual statistics per hydrological year, please download the data from here: [https://www.envidat.ch/dataset/avalanche-fatalities-switzerland-1936]\n\nThe following information is contained (by column and column title):  \n - year  \n - number of fatalities in the backcountry (=tour)  \n - number of fatalities in terrain close to ski areas (=offpiste, away from open and secured ski runs)  \n - number of fatalities on transportation corridors including ski runs, roads, railway lines (=transportation.corridors)  \n - number of fatalities in or around buildings or in settlements (= buildings)  \n - sum (of all four categories)\n\nThe definitions for these four categories, as described in the guidelines to the avalanche accident database are:\n\n__tour:__  \nactivities include back-country ski, snowboard or snow-shoe touring  \n\n__offpiste:__  \naccess from ski area, generally from the top of a skilift with short hiking distances  \n\n__transportation.corridors__ (Techel et al., 2016):  \npeople travelling or recreating on open or temporarily closed transportation corridors (e.g. a road user or a skier on a ski run) and people working on open or closed transportation corridors (e.g. maintenance crews on roads, professional rescue teams)  \n\n__buildings__ (Techel et al., 2016):  \npeople inside or just outside buildings, and workers on high alpine building sites;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "10c8cae1-01ac-513b-b081-b7326d69a2f9",
-    "notes": [
-        "This dataset contains the statistics on the number of avalanche fatalities per **calendar year** in Switzerland. The data collection commences with the beginning of the year 1937. After the completion of a hydrological year, which  is the standard way avalanche fatalities are summarized in Switzerland and ends on the 30th of September, the new data is appended to the existing dataset.\nIf you require annual statistics per hydrological year, please download the data from here: [https://www.envidat.ch/dataset/avalanche-fatalities-switzerland-1936]\n\nThe following information is contained (by column and column title):  \n - year  \n - number of fatalities in the backcountry (=tour)  \n - number of fatalities in terrain close to ski areas (=offpiste, away from open and secured ski runs)  \n - number of fatalities on transportation corridors including ski runs, roads, railway lines (=transportation.corridors)  \n - number of fatalities in or around buildings or in settlements (= buildings)  \n - sum (of all four categories)\n\nThe definitions for these four categories, as described in the guidelines to the avalanche accident database are:\n\n__tour:__  \nactivities include back-country ski, snowboard or snow-shoe touring  \n\n__offpiste:__  \naccess from ski area, generally from the top of a skilift with short hiking distances  \n\n__transportation.corridors__ (Techel et al., 2016):  \npeople travelling or recreating on open or temporarily closed transportation corridors (e.g. a road user or a skier on a ski run) and people working on open or closed transportation corridors (e.g. maintenance crews on roads, professional rescue teams)  \n\n__buildings__ (Techel et al., 2016):  \npeople inside or just outside buildings, and workers on high alpine building sites"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:b00052bc-11da-4c51-a062-ee1fa1d158d8"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "AVALANCHE ACCIDENT STATISTICS"
-        },
-        {
-            "name": "AVALANCHE FATALITIES"
-        }
-    ],
-    "title": [
-        "Number of avalanche fatalities per calendar year in Switzerland since 1937"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/10cd77be-9305-5b29-890d-bcdf60c3309a.json b/oaitestdata/envidat-datacite/SET_1/json/10cd77be-9305-5b29-890d-bcdf60c3309a.json
deleted file mode 100644
index ee93b349..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/10cd77be-9305-5b29-890d-bcdf60c3309a.json
+++ /dev/null
@@ -1,93 +0,0 @@
-{
-    "Contact": [
-        "Vanessa Burg"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/18",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "XLSX",
-        "DOCX"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:21599a72-b714-4d11-a748-644d0016fae9",
-    "MetadataAccess": [
-        "oai:envidat.ch:21599a72-b714-4d11-a748-644d0016fae9"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Swiss Federal Institute for Forest, Snow and Landscape Research WSL / Swiss Competence Center for Energy Research - Biomass for Swiss Energy Transition SCCER-BIOSWEET"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/swiss-biomass-potentials"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "License not specified"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Gillianne Bowman",
-        "Matthias Erni",
-        "Oliver Thees",
-        "Renato Lemm",
-        "Vanessa Burg"
-    ],
-    "fulltext": "oai:envidat.ch:21599a72-b714-4d11-a748-644d0016fae9;2018-12-09T00:33:15Z;10.16904/18;Oliver Thees;WSL;Vanessa Burg;WSL;Matthias Erni;WSL;Gillianne Bowman;WSL;Renato Lemm;WSL;Potentials of domestic biomass resources for the energy transition in Switzerland;2017;Swiss Federal Institute for Forest, Snow and Landscape Research WSL / Swiss Competence Center for Energy Research - Biomass for Swiss Energy Transition SCCER-BIOSWEET;AVAILABILITY;BIOENERGY;BIOMASS RESOURCES;POTENTIAL ASSESSMENT;SUSTAINABILITY;Vanessa Burg;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/swiss-biomass-potentials;10164033 bytes;138287 bytes;194315 bytes;XLSX;DOCX;1.0;License not specified;Switzerland has a reliable and cost efficient energy system. Due to phase  out of nuclear energy it is necessary to find new options to maintain this powerful energy system. The Swiss energy strategy 2050 aims to reduce CO2-emissions, increase efficiency and promote renewable energies. The Swiss Federal Institute for Forest, Snow and Landscape Research (WSL) examined relevant woody and non-woody biomass quantities (cubic meters, fresh-, dry weight) and their energy potentials (in Petajoules: primary energy and biomethane) with a similar methodological approach. The work was done within the frame of the Swiss Competence Centers for Energy Research (SCCER) especially in line with the SCCER Biomass for Swiss energy future (Biosweet). With a uniform and consistent approach for the current potentials ten biomass categories were estimated and aggregated for the whole of Switzerland. In this context solutions for the technical, social and political challenges are promoted. First, considering the different biomass resources characteristics and available data, appropriate methods at the finest scale possible were elaborated to estimate the annual quantities which could theoretically be collected (theoretical potential). Then, explicit and rational restrictions for sustainable bio-energy production were defined according to the current state of the art and subtracted from the theoretical potential to obtain the sustainable potential. The main restrictions are competing material utilizations, environmental factors and supply costs. Finally, the additional sustainable potential was estimated considering the current bioenergy production. Our main purpose was to provide potentials for developing conversion technologies as well as a detailed and comprehensive basis of the Swiss biomass potentials for energy use for economic and political decision makers. The complete report is available under https://www.dora.lib4ri.ch/wsl/islandora/object/wsl%3A13277/datastream/PDF/view;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "10cd77be-9305-5b29-890d-bcdf60c3309a",
-    "notes": [
-        "Switzerland has a reliable and cost efficient energy system. Due to phase  out of nuclear energy it is necessary to find new options to maintain this powerful energy system. The Swiss energy strategy 2050 aims to reduce CO2-emissions, increase efficiency and promote renewable energies. The Swiss Federal Institute for Forest, Snow and Landscape Research (WSL) examined relevant woody and non-woody biomass quantities (cubic meters, fresh-, dry weight) and their energy potentials (in Petajoules: primary energy and biomethane) with a similar methodological approach. The work was done within the frame of the Swiss Competence Centers for Energy Research (SCCER) especially in line with the SCCER Biomass for Swiss energy future (Biosweet). With a uniform and consistent approach for the current potentials ten biomass categories were estimated and aggregated for the whole of Switzerland. In this context solutions for the technical, social and political challenges are promoted. First, considering the different biomass resources characteristics and available data, appropriate methods at the finest scale possible were elaborated to estimate the annual quantities which could theoretically be collected (theoretical potential). Then, explicit and rational restrictions for sustainable bio-energy production were defined according to the current state of the art and subtracted from the theoretical potential to obtain the sustainable potential. The main restrictions are competing material utilizations, environmental factors and supply costs. Finally, the additional sustainable potential was estimated considering the current bioenergy production. Our main purpose was to provide potentials for developing conversion technologies as well as a detailed and comprehensive basis of the Swiss biomass potentials for energy use for economic and political decision makers. The complete report is available under https://www.dora.lib4ri.ch/wsl/islandora/object/wsl%3A13277/datastream/PDF/view"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:21599a72-b714-4d11-a748-644d0016fae9"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "AVAILABILITY"
-        },
-        {
-            "name": "BIOENERGY"
-        },
-        {
-            "name": "BIOMASS RESOURCES"
-        },
-        {
-            "name": "POTENTIAL ASSESSMENT"
-        },
-        {
-            "name": "SUSTAINABILITY"
-        }
-    ],
-    "title": [
-        "Potentials of domestic biomass resources for the energy transition in Switzerland"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/115874bf-d058-5857-8caf-780251e23431.json b/oaitestdata/envidat-datacite/SET_1/json/115874bf-d058-5857-8caf-780251e23431.json
deleted file mode 100644
index b0064245..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/115874bf-d058-5857-8caf-780251e23431.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:2b7c328f-f803-45d9-a45b-704e24a99c23",
-    "MetadataAccess": [
-        "oai:envidat.ch:2b7c328f-f803-45d9-a45b-704e24a99c23"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/volume-21"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:2b7c328f-f803-45d9-a45b-704e24a99c23;2018-12-09T00:33:31Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Volume;2014;Swiss Federal Research Institute WSL;14 X 14 KM GRID;56 CLASSES;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;ALTITUDINAL VEGETATION ZONE;AVALANCHES SILVAPROTECT;BIOGEOGRAPHICAL REGION;CANTON;CONIFERS-BROADLEAVES;DIAMETER CLASS SIZE 10 CM;DIAMETER CLASSES;ECONOMIC REGION;EXPOSITION 8 CLASSES;FOREST DISTRICT AS OF 2013;FOREST TYPE 12 CLASSES;FOREST TYPE AND STAGE OF DEVELOPMENT;GRID NFI4 2009-2013;LANDSLIDE-MUDFLOW SILVAPROTECT;LOWER-HIGHER ALTITUDINAL ZONES;MAIN TREE SPECIES;NFI1;NFI2;NFI3;NFI4B;OWNERSHIP;OWNERSHIP NFI4;POTENTIAL COST FOR TIMBER HARVESTING;PROCESSES IN CHANNELS SILVAPROTECT;PRODUCTION REGION;PROTECTION FOREST PERIMETER SILVAPROTECT;PROTECTION FOREST REGION;ROCKFALL SILVAPROTECT;SITE QUALITY;STAGE OF STAND DEVELOPMENT;TERRESTRIAL GRID NFI1;TERRESTRIAL GRID NFI2;TERRESTRIAL GRID NFI3;TREE SPECIES 5 CLASSES;TREE SPECIES WOODY SPECIES;VOLUME;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/volume-21;URL;1.0;Other (Open);Volume of stemwood with bark of living trees and shrubs (standing and lying)  starting at 12 cm dbh. This corresponds internationally to the \"growing stock\". The correction for bias with the sample Tarif trees may be so drastic that it results in negative values with small numbers of trees.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "115874bf-d058-5857-8caf-780251e23431",
-    "notes": [
-        "Volume of stemwood with bark of living trees and shrubs (standing and lying)  starting at 12 cm dbh. This corresponds internationally to the \"growing stock\". The correction for bias with the sample Tarif trees may be so drastic that it results in negative values with small numbers of trees.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:2b7c328f-f803-45d9-a45b-704e24a99c23"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "X KM GRID"
-        },
-        {
-            "name": "CLASSES"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "AVALANCHES SILVAPROTECT"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        }
-    ],
-    "title": [
-        "Volume"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/1187844d-f582-5576-bf58-81f02fa0aae7.json b/oaitestdata/envidat-datacite/SET_1/json/1187844d-f582-5576-bf58-81f02fa0aae7.json
deleted file mode 100644
index 56d4afa9..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/1187844d-f582-5576-bf58-81f02fa0aae7.json
+++ /dev/null
@@ -1,92 +0,0 @@
-{
-    "Contact": [
-        "Christian Sommer"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/21",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "TXT",
-        "Link",
-        "ZIP"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:9918d77c-3176-453f-b34c-062ba979144a",
-    "MetadataAccess": [
-        "oai:envidat.ch:9918d77c-3176-453f-b34c-062ba979144a"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/10-16904-21"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N,10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Charles Fierz",
-        "Michael Lehning",
-        "Christian G. Sommer"
-    ],
-    "fulltext": "oai:envidat.ch:9918d77c-3176-453f-b34c-062ba979144a;2018-12-09T00:31:05Z;10.16904/21;Christian G. Sommer;WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland and CRYOS, School of Architecture and Civil Engineering, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland;Michael Lehning;WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland and CRYOS, School of Architecture and Civil Engineering, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland;Charles Fierz;WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland;Wind crust formation: SnowMicroPen data;2017;WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland;SMP;SNOW;SNOWMICROPEN;WIND CRUST;WIND-PACKING;Christian Sommer;WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland and CRYOS, School of Architecture and Civil Engineering, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/10-16904-21;2701 bytes;12976 bytes;Link;TXT;ZIP;1.0;Open Data Commons Open Database License (ODbL);This dataset contains the SnowMicroPen (SMP) data from 38 wind tunnel experiments on wind-packing / wind crust formation. These experiments were performed in the winters 2015/16 and 2016/17 and include more than 1000 SMP measurements. \n\nThe SMPs are organized per experiment. Each experiment subfolder contains the processed SMP profiles and some additional files.\n\nPlease refer to the README for more details on the data. The processing scripts are available for download as well. The scripts are mainly provided as documentation and would need to be adjusted to be used.\n\nThis dataset is the basis of the following publication:\n\nSommer C.G., Lehning M., & Fierz C. (2017). Wind tunnel experiments: Saltation is necessary for wind-packing. Journal of Glaciology, 63(242), 950-958. doi:10.1017/jog.2017.53;46.80798 9.86752;Davos, Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "1187844d-f582-5576-bf58-81f02fa0aae7",
-    "notes": [
-        "This dataset contains the SnowMicroPen (SMP) data from 38 wind tunnel experiments on wind-packing / wind crust formation. These experiments were performed in the winters 2015/16 and 2016/17 and include more than 1000 SMP measurements. \n\nThe SMPs are organized per experiment. Each experiment subfolder contains the processed SMP profiles and some additional files.\n\nPlease refer to the README for more details on the data. The processing scripts are available for download as well. The scripts are mainly provided as documentation and would need to be adjusted to be used.\n\nThis dataset is the basis of the following publication:\n\nSommer C.G., Lehning M., & Fierz C. (2017). Wind tunnel experiments: Saltation is necessary for wind-packing. Journal of Glaciology, 63(242), 950-958. doi:10.1017/jog.2017.53"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:9918d77c-3176-453f-b34c-062ba979144a"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[9.86752,46.80798],[9.86752,46.80798],[9.86752,46.80798],[9.86752,46.80798],[9.86752,46.80798]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "SMP"
-        },
-        {
-            "name": "SNOW"
-        },
-        {
-            "name": "SNOWMICROPEN"
-        },
-        {
-            "name": "WIND CRUST"
-        },
-        {
-            "name": "WIND-PACKING"
-        }
-    ],
-    "title": [
-        "Wind crust formation: SnowMicroPen data"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/17472fc4-ef14-5ec7-8798-00b4cfb7f267.json b/oaitestdata/envidat-datacite/SET_1/json/17472fc4-ef14-5ec7-8798-00b4cfb7f267.json
deleted file mode 100644
index 5ece2459..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/17472fc4-ef14-5ec7-8798-00b4cfb7f267.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:e08a6efe-897a-4198-bf20-30beae6cca2a",
-    "MetadataAccess": [
-        "oai:envidat.ch:e08a6efe-897a-4198-bf20-30beae6cca2a"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/young_forest_with_browsing_damage-193"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:e08a6efe-897a-4198-bf20-30beae6cca2a;2018-12-09T00:33:49Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Young forest with browsing damage;2014;Swiss Federal Research Institute WSL;ACCESSIBLE FOREST WITHOUT SHRUB FOREST WITH YOUNG FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST WITH YOUNG FOREST NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST WITH YOUNG FOREST NFI3-NFI4;ALTITUDINAL VEGETATION ZONE;AVALANCHES SILVAPROTECT;BIOGEOGRAPHICAL REGION;CANTON;ECONOMIC REGION;GRID NFI4 2009-2013;LANDSLIDE-MUDFLOW SILVAPROTECT;MAIN TREE SPECIES IN YOUNG FOREST;NFI2;NFI4B;PROCESSES IN CHANNELS SILVAPROTECT;PRODUCTION REGION;PROTECTION FOREST PERIMETER SILVAPROTECT;PROTECTION FOREST REGION;ROCKFALL SILVAPROTECT;STEM COUNT OF YOUNG FOREST;TERRESTRIAL GRID NFI2;TOTAL NUMBER;YOUNG FOREST CLASSES 5 CLASSES;YOUNG FOREST WITH BROWSING DAMAGE;YOUNG PLANTS;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/young_forest_with_browsing_damage-193;URL;1.0;Other (Open);Number of regeneration trees where browsing of the shoots from the previous year was recorded in NFI\u2019s regeneration survey.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "17472fc4-ef14-5ec7-8798-00b4cfb7f267",
-    "notes": [
-        "Number of regeneration trees where browsing of the shoots from the previous year was recorded in NFI\u2019s regeneration survey.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:e08a6efe-897a-4198-bf20-30beae6cca2a"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST YOUNG FOREST"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "AVALANCHES SILVAPROTECT"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "LANDSLIDE-MUDFLOW SILVAPROTECT"
-        },
-        {
-            "name": "MAIN TREE SPECIES YOUNG FOREST"
-        },
-        {
-            "name": "NFI"
-        },
-        {
-            "name": "NFIB"
-        },
-        {
-            "name": "PROCESSES CHANNELS SILVAPROTECT"
-        }
-    ],
-    "title": [
-        "Young forest with browsing damage"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/192bc0dc-2c6c-54a4-b737-d17c6b7783c6.json b/oaitestdata/envidat-datacite/SET_1/json/192bc0dc-2c6c-54a4-b737-d17c6b7783c6.json
deleted file mode 100644
index 2d53bf59..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/192bc0dc-2c6c-54a4-b737-d17c6b7783c6.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Matthias Heck"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/envidat.29",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "ZIP"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:6b0788a9-33e8-4ea6-b958-6327167ad423",
-    "MetadataAccess": [
-        "oai:envidat.ch:6b0788a9-33e8-4ea6-b958-6327167ad423"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avalanche Research SLF"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/10-16904-envidat-29"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N,10E)",
-    "TempCoverageBegin": 63397943999,
-    "TempCoverageEnd": 63397943999,
-    "TemporalCoverage": " point in time : 2010-01-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2010-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2010-01-01T11:59:59Z",
-    "author": [
-        "Alec van Herwijnen",
-        "Matthias Heck"
-    ],
-    "fulltext": "oai:envidat.ch:6b0788a9-33e8-4ea6-b958-6327167ad423;2018-12-09T00:24:15Z;10.16904/envidat.29;Matthias Heck;WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland;Alec van Herwijnen;WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland;Automatic detection of avalanches;Machine learning approach on seismic data;2018;WSL Institute for Snow and Avalanche Research SLF;AVALANCHE ACTIVITY;HIDDEN MARKOV MODEL;MONITORING;SEISMIC;Matthias Heck;SLF;2010-01-01;en;Dataset;https://www.envidat.ch/dataset/10-16904-envidat-29;1802458 bytes;ZIP;1.0;Open Data Commons Open Database License (ODbL);This dataset contains the results obtained by an automatic classification using hidden Markov models of a continuous seismic dataset. To avoid long computational times, we reduced the seismic data using pre-processing step. The start and end times of the windows used for the classification are also included in this dataset. Furthermore, an avalanche reference data set is included and the python scripts used to perform the processing steps and the classification.;46.80616 9.78759;Steint\u00e4lli, Davos, Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "192bc0dc-2c6c-54a4-b737-d17c6b7783c6",
-    "notes": [
-        "This dataset contains the results obtained by an automatic classification using hidden Markov models of a continuous seismic dataset. To avoid long computational times, we reduced the seismic data using pre-processing step. The start and end times of the windows used for the classification are also included in this dataset. Furthermore, an avalanche reference data set is included and the python scripts used to perform the processing steps and the classification."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:6b0788a9-33e8-4ea6-b958-6327167ad423"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[9.78759,46.80616],[9.78759,46.80616],[9.78759,46.80616],[9.78759,46.80616],[9.78759,46.80616]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "AVALANCHE ACTIVITY"
-        },
-        {
-            "name": "HIDDEN MARKOV MODEL"
-        },
-        {
-            "name": "MONITORING"
-        },
-        {
-            "name": "SEISMIC"
-        }
-    ],
-    "title": [
-        "Automatic detection of avalanches",
-        "Machine learning approach on seismic data"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/1991d724-074c-53fe-a56f-3f3e31caa42d.json b/oaitestdata/envidat-datacite/SET_1/json/1991d724-074c-53fe-a56f-3f3e31caa42d.json
deleted file mode 100644
index 2adaf570..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/1991d724-074c-53fe-a56f-3f3e31caa42d.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:0870aa19-1a32-4857-9742-1bb37a050116",
-    "MetadataAccess": [
-        "oai:envidat.ch:0870aa19-1a32-4857-9742-1bb37a050116"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/yield_of_merchantable_timber-114"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:0870aa19-1a32-4857-9742-1bb37a050116;2018-12-09T00:33:46Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Yield of merchantable timber;2014;Swiss Federal Research Institute WSL;14 X 14 KM GRID;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;BIOGEOGRAPHICAL REGION;CONIFERS-BROADLEAVES;ECONOMIC REGION;GRID NFI4 2009-2013;NFI2-NFI3;NFI3-NFI4B;OWNERSHIP;PRODUCTION REGION;PROTECTION FOREST REGION;YIELD OF MERCHANTABLE TIMBER;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/yield_of_merchantable_timber-114;URL;1.0;Other (Open);Wood volume of the stem (without bark and stump) and the branches (with bark) at least 7 cm in diameter (limit for coarse wood) from trees and shrubs  starting at 12 cm dbh that were living in the pre-inventory and were cut between the two inventories.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "1991d724-074c-53fe-a56f-3f3e31caa42d",
-    "notes": [
-        "Wood volume of the stem (without bark and stump) and the branches (with bark) at least 7 cm in diameter (limit for coarse wood) from trees and shrubs  starting at 12 cm dbh that were living in the pre-inventory and were cut between the two inventories.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:0870aa19-1a32-4857-9742-1bb37a050116"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "X KM GRID"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "NFI-NFI"
-        },
-        {
-            "name": "NFI-NFIB"
-        },
-        {
-            "name": "OWNERSHIP"
-        }
-    ],
-    "title": [
-        "Yield of merchantable timber"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/1b30f043-a23a-502c-a5e5-af1b3b6cb00e.json b/oaitestdata/envidat-datacite/SET_1/json/1b30f043-a23a-502c-a5e5-af1b3b6cb00e.json
deleted file mode 100644
index 7e35cb93..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/1b30f043-a23a-502c-a5e5-af1b3b6cb00e.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:19ed6c2b-9882-465c-aafb-d068eecda734",
-    "MetadataAccess": [
-        "oai:envidat.ch:19ed6c2b-9882-465c-aafb-d068eecda734"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/yield_of_merchantable_branches-112"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:19ed6c2b-9882-465c-aafb-d068eecda734;2018-12-09T00:33:45Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Yield of merchantable branches;2014;Swiss Federal Research Institute WSL;14 X 14 KM GRID;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;BIOGEOGRAPHICAL REGION;CONIFERS-BROADLEAVES;ECONOMIC REGION;GRID NFI4 2009-2013;NFI2-NFI3;NFI3-NFI4B;OWNERSHIP;PRODUCTION REGION;PROTECTION FOREST REGION;YIELD OF MERCHANTABLE BRANCHES;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/yield_of_merchantable_branches-112;URL;1.0;Other (Open);Wood volume of branches with bark at least 7 cm in diameter (limit for coarse wood) of all living trees and shrubs  starting at 12 cm dbh that were present in the pre-inventory and cut meanwhile.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "1b30f043-a23a-502c-a5e5-af1b3b6cb00e",
-    "notes": [
-        "Wood volume of branches with bark at least 7 cm in diameter (limit for coarse wood) of all living trees and shrubs  starting at 12 cm dbh that were present in the pre-inventory and cut meanwhile.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:19ed6c2b-9882-465c-aafb-d068eecda734"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "X KM GRID"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "NFI-NFI"
-        },
-        {
-            "name": "NFI-NFIB"
-        },
-        {
-            "name": "OWNERSHIP"
-        }
-    ],
-    "title": [
-        "Yield of merchantable branches"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/1d9c4c5b-b6c3-5085-ae5c-9e921cf02520.json b/oaitestdata/envidat-datacite/SET_1/json/1d9c4c5b-b6c3-5085-ae5c-9e921cf02520.json
deleted file mode 100644
index ce26de61..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/1d9c4c5b-b6c3-5085-ae5c-9e921cf02520.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:d874e80d-f1f7-41bd-8f93-5ff99234b6d3",
-    "MetadataAccess": [
-        "oai:envidat.ch:d874e80d-f1f7-41bd-8f93-5ff99234b6d3"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/biomass_of_lying_dead_wood_lis-72"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:d874e80d-f1f7-41bd-8f93-5ff99234b6d3;2018-12-09T00:31:34Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Biomass of lying dead wood (LIS);2014;Swiss Federal Research Institute WSL;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;BIOGEOGRAPHICAL REGION;BIOMASS OF LYING DEAD WOOD LIS;CANTON;ECONOMIC REGION;GRID NFI4 2009-2013;NFI3;NFI4B;OWNERSHIP;PRODUCTION REGION;PROTECTION FOREST REGION;TERRESTRIAL GRID NFI3;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/biomass_of_lying_dead_wood_lis-72;URL;1.0;Other (Open);Dry weight (mass) of lying deadwood  starting at 7 cm in diameter that does not fulfil the criteria for a tally tree (measurement location of dbh not identifiable or the dbh is less than 12cm).\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "1d9c4c5b-b6c3-5085-ae5c-9e921cf02520",
-    "notes": [
-        "Dry weight (mass) of lying deadwood  starting at 7 cm in diameter that does not fulfil the criteria for a tally tree (measurement location of dbh not identifiable or the dbh is less than 12cm).\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:d874e80d-f1f7-41bd-8f93-5ff99234b6d3"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "BIOMASS LYING DEAD WOOD LIS"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "NFI"
-        },
-        {
-            "name": "NFIB"
-        },
-        {
-            "name": "OWNERSHIP"
-        },
-        {
-            "name": "PRODUCTION REGION"
-        },
-        {
-            "name": "PROTECTION FOREST REGION"
-        }
-    ],
-    "title": [
-        "Biomass of lying dead wood (LIS)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/20eb2598-bbf5-5d15-bb5e-01262898798b.json b/oaitestdata/envidat-datacite/SET_1/json/20eb2598-bbf5-5d15-bb5e-01262898798b.json
deleted file mode 100644
index 9150806c..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/20eb2598-bbf5-5d15-bb5e-01262898798b.json
+++ /dev/null
@@ -1,90 +0,0 @@
-{
-    "Contact": [
-        "Anita Risch"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/envidat.38",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "XLSX"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:0f23238f-4ae7-4ca6-ad8f-64308d835fc6",
-    "MetadataAccess": [
-        "oai:envidat.ch:0f23238f-4ae7-4ca6-ad8f-64308d835fc6"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/soil-respiration-exclosure-experiment"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N-47N,10E-10E)",
-    "TempCoverageBegin": 63379450799,
-    "TempCoverageEnd": 63379450799,
-    "TemporalCoverage": " point in time : 2009-06-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2009-06-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2009-06-01T11:59:59Z",
-    "author": [
-        "Martin Schuetz",
-        "Anita Risch"
-    ],
-    "fulltext": "oai:envidat.ch:0f23238f-4ae7-4ca6-ad8f-64308d835fc6;2018-12-06T17:27:51Z;10.16904/envidat.38;Anita Risch;A-9836-2012;WSL;Martin Schuetz;WSL;Soil respiration - exclosure experiment;SNF funded;2018;WSL;GRASSLAND;GRAZING;SOIL RESPIRATION;SUBALPINE;UNGULATES;Anita Risch;A-9836-2012;WSL;2009-06-01;en;Dataset;https://www.envidat.ch/dataset/soil-respiration-exclosure-experiment;15062 bytes;XLSX;1.0;Open Data Commons Open Database License (ODbL);Location of data collection\nThe Swiss National Park (SNP) is located in the southeastern part of Switzerland, and covers an area of 170 km2, 50 km2 of which is forested, 33 km2 is occupied by alpine and 3 km2 by subalpine grasslands. Elevations range from 1350 to 3170 m a.s.l., and mean annual precipitation and temperature are 871 mm and 0.6\u00b0C measured at the Park\u2019s weather station in Buffalora (1980 m a.s.l.) between 1960 and 2009 (MeteoSchweiz 2011). Founded in 1914, the SNP received minimal human disturbance for almost 100 years (no hunting, fishing, or camping, visitors are not allowed to leave the trails). Large (> 1 ha) homogeneous patches of short- and tall-grass vegetation characterize the subalpine grasslands. The average vegetation height of short-grass vegetation is 2 to 5 cm. Red fescue (Festuca rubra L.), quaking grass (Briza media L.) and common bent grass (Agrostis tenuis Sipthrob) are the predominating plant species in this vegetation type. Tussocks of evergreen sedge (Carex sempervirens Vill.) and mat grass (Nardus stricta L.) are predominant in the tall-grass vegetation, which averages 20 cm in vegetation height (Sch\u00fctz and others 2006). Short-grass vegetation developed in areas where cattle and sheep rested (high nutrient input) during agricultural land-use (from 14th century until 1914); tall-grass vegetation developed in areas where cattle and sheep used to graze, but did not rest (Sch\u00fctz and others 2003, 2006). Herbivores were shown to consume > 60% of the biomass in short-grass compared to < 20% in tall-grass vegetation (Sch\u00fctz and others 2006). The herbivore community present in the SNP can be divided into four groups based on body size/weight: large [red deer (Cervus elaphus L.) and chamois (Rupricapra rupricapra L.); 30 - 150 kg], medium [marmot (Marmota marmota L.) and snow hare (Lepus timidus L.); 3 \u2013 6 kg], and small vertebrate herbivores (small rodents: e.g. Clethrionomys spp., Microtus spp., Apodemus spp.; 30 \u2013 100 g) as well as invertebrates (e.g. grasshoppers, caterpillars, cicadas, < 5 g). \n\nExperimental design\nWe selected 18 subalpine grassland sites (9 short-grass, 9 tall-grass vegetation). The sites were spread across the entire park on dolomite parent material at altitudes of 1975 to 2300 meters. At each site we established an exclosure network (fences) in spring 2009 (early June), immediately after snowmelt. Each exclosure network consisted of a total of five 2 \u00d7 3 m sized plots that progressively excluded the different herbivores listed above (further labeled according to the herbivore guilds that had access to the respective plots \u201cAll\u201d, \u201cMarmot/Mice/Invertebrates\u201d, \u201cMice/Invertebrates\u201d, \u201cInvertebrates\u201d, \u201cNone\u201d). The \u201cAll\u201d treatment was thus accessible to all herbivores, was not fenced and was located at least 5 m away from a 2.1 m tall and 7 \u00d7 9 m main fence that enclosed the other four treatments. This fence was constructed of 10 \u00d7 10 cm wooden posts and electrical equestrian tape (AGRARO ECO, Landi, Bern, Switzerland; 20 mm width) mounted at 0.7 m, 0.95 m, 1.2 m, 1.5 m and 2.1 m above the ground that were connected to a solar charged battery (AGRARO Sunpower S250, Landi, Bern, Switzerland). We also mounted non-electrically charged equestrian tape at 0.5 m to help exclude deer and chamois, yet allow marmots and hares to enter safely. Within each main fenced area we randomly established four 2 \u00d7 3 m plots: (1) The \u201cMarmot/Mice/Invertebrates\u201d plot remained unfenced, thus, with the exception of red deer and chamois, all herbivores were able to access the plot, (2) The \u201cMice/Invertebrates\u201d plot consisted of a 90 cm high electric sheep fence (AGRARO Weidezaunnetz ECO, Landi, Bern, Switzerland; mesh size 10 \u00d7 10 cm) connected to the solar panel and excluded all medium sized mammals (marmots, hares), but provided access for small mammals and invertebrates, (3) The \u201cInvertebrates\u201d plot provided access for invertebrates only and was surrounded by 1 m high metal mesh (Hortima AG, Hausen, Schweiz; mesh size 2 \u00d7 2 cm), (4) The \u201cNone\u201d plot was surrounded by a 1 m tall mosquito net (Sala Ferramenta AG, Biasca, Switzerland; mesh size 1.5 \u00d7 2 mm) to exclude all herbivores. This plot was covered with a roof constructed of a wooden frame lined with mosquito mesh that was mounted on the wooden corner posts. We also treated this plot with a biocompatible insecticide (Clean kill original, Eco Belle GmbH, Waldshut-Tiengen, Germany) when needed to remove insects that might have entered during data collection or that hatched from the soil. \n\n!!! The here published data set only contains data for \u201cAll\u201d, and \u201cMarmot/Mice/Invertebrates\u201d (= ungulates excluded) plots !!!\n\nData collection\nIn-situ soil CO2 emissions were measured with a PP-Systems SRC-1 soil respiration chamber (closed circuit) attached to a PP-Systems EGM-4 infrared gas analyzer (PP-Systems, Amesbury, MA, USA) on two randomly selected locations on one subplot within each of the 90 plots. For each measurement the soil chamber (15 cm high; 10 cm diameter) was placed on a permanently installed PVC collar (10 cm diameter) driven five centimeters into the soil at the beginning of the study (June 2009). The measurements were conducted between 0900 and 1700 hours every two weeks from early to early September 2009, 2010, 2011 and 2013. Freshly germinated plants growing within the PVC collars were removed prior to each measurement to avoid measuring plant respiration/photosynthesis. The two measurements collected per plot every two weeks were averaged. \n\nPlease acknowledge the funding of the study: funded by the Swiss National Science Foundation, SNF grant-no 31003A_122009/1 to Anita C. Risch, Martin Sch\u00fctz and Flurin Filli;46.6073592082 10.1273345947 46.7580997708 10.3607940674;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "20eb2598-bbf5-5d15-bb5e-01262898798b",
-    "notes": [
-        "Location of data collection\nThe Swiss National Park (SNP) is located in the southeastern part of Switzerland, and covers an area of 170 km2, 50 km2 of which is forested, 33 km2 is occupied by alpine and 3 km2 by subalpine grasslands. Elevations range from 1350 to 3170 m a.s.l., and mean annual precipitation and temperature are 871 mm and 0.6\u00b0C measured at the Park\u2019s weather station in Buffalora (1980 m a.s.l.) between 1960 and 2009 (MeteoSchweiz 2011). Founded in 1914, the SNP received minimal human disturbance for almost 100 years (no hunting, fishing, or camping, visitors are not allowed to leave the trails). Large (> 1 ha) homogeneous patches of short- and tall-grass vegetation characterize the subalpine grasslands. The average vegetation height of short-grass vegetation is 2 to 5 cm. Red fescue (Festuca rubra L.), quaking grass (Briza media L.) and common bent grass (Agrostis tenuis Sipthrob) are the predominating plant species in this vegetation type. Tussocks of evergreen sedge (Carex sempervirens Vill.) and mat grass (Nardus stricta L.) are predominant in the tall-grass vegetation, which averages 20 cm in vegetation height (Sch\u00fctz and others 2006). Short-grass vegetation developed in areas where cattle and sheep rested (high nutrient input) during agricultural land-use (from 14th century until 1914); tall-grass vegetation developed in areas where cattle and sheep used to graze, but did not rest (Sch\u00fctz and others 2003, 2006). Herbivores were shown to consume > 60% of the biomass in short-grass compared to < 20% in tall-grass vegetation (Sch\u00fctz and others 2006). The herbivore community present in the SNP can be divided into four groups based on body size/weight: large [red deer (Cervus elaphus L.) and chamois (Rupricapra rupricapra L.); 30 - 150 kg], medium [marmot (Marmota marmota L.) and snow hare (Lepus timidus L.); 3 \u2013 6 kg], and small vertebrate herbivores (small rodents: e.g. Clethrionomys spp., Microtus spp., Apodemus spp.; 30 \u2013 100 g) as well as invertebrates (e.g. grasshoppers, caterpillars, cicadas, < 5 g). \n\nExperimental design\nWe selected 18 subalpine grassland sites (9 short-grass, 9 tall-grass vegetation). The sites were spread across the entire park on dolomite parent material at altitudes of 1975 to 2300 meters. At each site we established an exclosure network (fences) in spring 2009 (early June), immediately after snowmelt. Each exclosure network consisted of a total of five 2 \u00d7 3 m sized plots that progressively excluded the different herbivores listed above (further labeled according to the herbivore guilds that had access to the respective plots \u201cAll\u201d, \u201cMarmot/Mice/Invertebrates\u201d, \u201cMice/Invertebrates\u201d, \u201cInvertebrates\u201d, \u201cNone\u201d). The \u201cAll\u201d treatment was thus accessible to all herbivores, was not fenced and was located at least 5 m away from a 2.1 m tall and 7 \u00d7 9 m main fence that enclosed the other four treatments. This fence was constructed of 10 \u00d7 10 cm wooden posts and electrical equestrian tape (AGRARO ECO, Landi, Bern, Switzerland; 20 mm width) mounted at 0.7 m, 0.95 m, 1.2 m, 1.5 m and 2.1 m above the ground that were connected to a solar charged battery (AGRARO Sunpower S250, Landi, Bern, Switzerland). We also mounted non-electrically charged equestrian tape at 0.5 m to help exclude deer and chamois, yet allow marmots and hares to enter safely. Within each main fenced area we randomly established four 2 \u00d7 3 m plots: (1) The \u201cMarmot/Mice/Invertebrates\u201d plot remained unfenced, thus, with the exception of red deer and chamois, all herbivores were able to access the plot, (2) The \u201cMice/Invertebrates\u201d plot consisted of a 90 cm high electric sheep fence (AGRARO Weidezaunnetz ECO, Landi, Bern, Switzerland; mesh size 10 \u00d7 10 cm) connected to the solar panel and excluded all medium sized mammals (marmots, hares), but provided access for small mammals and invertebrates, (3) The \u201cInvertebrates\u201d plot provided access for invertebrates only and was surrounded by 1 m high metal mesh (Hortima AG, Hausen, Schweiz; mesh size 2 \u00d7 2 cm), (4) The \u201cNone\u201d plot was surrounded by a 1 m tall mosquito net (Sala Ferramenta AG, Biasca, Switzerland; mesh size 1.5 \u00d7 2 mm) to exclude all herbivores. This plot was covered with a roof constructed of a wooden frame lined with mosquito mesh that was mounted on the wooden corner posts. We also treated this plot with a biocompatible insecticide (Clean kill original, Eco Belle GmbH, Waldshut-Tiengen, Germany) when needed to remove insects that might have entered during data collection or that hatched from the soil. \n\n!!! The here published data set only contains data for \u201cAll\u201d, and \u201cMarmot/Mice/Invertebrates\u201d (= ungulates excluded) plots !!!\n\nData collection\nIn-situ soil CO2 emissions were measured with a PP-Systems SRC-1 soil respiration chamber (closed circuit) attached to a PP-Systems EGM-4 infrared gas analyzer (PP-Systems, Amesbury, MA, USA) on two randomly selected locations on one subplot within each of the 90 plots. For each measurement the soil chamber (15 cm high; 10 cm diameter) was placed on a permanently installed PVC collar (10 cm diameter) driven five centimeters into the soil at the beginning of the study (June 2009). The measurements were conducted between 0900 and 1700 hours every two weeks from early to early September 2009, 2010, 2011 and 2013. Freshly germinated plants growing within the PVC collars were removed prior to each measurement to avoid measuring plant respiration/photosynthesis. The two measurements collected per plot every two weeks were averaged. \n\nPlease acknowledge the funding of the study: funded by the Swiss National Science Foundation, SNF grant-no 31003A_122009/1 to Anita C. Risch, Martin Sch\u00fctz and Flurin Filli"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:0f23238f-4ae7-4ca6-ad8f-64308d835fc6"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[10.1273345947,46.6073592082],[10.1273345947,46.7580997708],[10.3607940674,46.7580997708],[10.3607940674,46.6073592082],[10.1273345947,46.6073592082]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "GRASSLAND"
-        },
-        {
-            "name": "GRAZING"
-        },
-        {
-            "name": "SOIL RESPIRATION"
-        },
-        {
-            "name": "SUBALPINE"
-        },
-        {
-            "name": "UNGULATES"
-        }
-    ],
-    "title": [
-        "Soil respiration - exclosure experiment",
-        "SNF funded"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/2374eb52-41ed-5725-8fa9-f7e6273ca109.json b/oaitestdata/envidat-datacite/SET_1/json/2374eb52-41ed-5725-8fa9-f7e6273ca109.json
deleted file mode 100644
index d0736c96..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/2374eb52-41ed-5725-8fa9-f7e6273ca109.json
+++ /dev/null
@@ -1,93 +0,0 @@
-{
-    "Contact": [
-        "Lisa H\u00fclsmann"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.5061/dryad.h4s6t",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "CSV"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:d2b9e7f9-c617-4e4d-9f04-c993e1e27ff7",
-    "MetadataAccess": [
-        "oai:envidat.ch:d2b9e7f9-c617-4e4d-9f04-c993e1e27ff7"
-    ],
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Dryad"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/data-for-huelsmann_et_al_ecol_appl_2016"
-    ],
-    "Rights": [
-        "License not specified"
-    ],
-    "SpatialCoverage": "(51N,7 E)",
-    "TempCoverageBegin": 63646343999,
-    "TempCoverageEnd": 63646343999,
-    "TemporalCoverage": " point in time : 2017-11-15T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2017-11-15T11:59:59Z",
-    "TemporalCoverage:EndDate": "2017-11-15T11:59:59Z",
-    "author": [
-        "Stephan Zimmermann",
-        "Brigitte Commarmot",
-        "Harald Bugmann",
-        "Peter Meyer",
-        "Peter Brang",
-        "Lisa H\u00fclsmann"
-    ],
-    "fulltext": "oai:envidat.ch:d2b9e7f9-c617-4e4d-9f04-c993e1e27ff7;2018-12-06T17:42:23Z;10.5061/dryad.h4s6t;Lisa H\u00fclsmann;0000-0003-4252-2715;WSL;Harald Bugmann;ETHZ;Brigitte Commarmot;WSL;Peter Meyer;NW-FVA;Stephan Zimmermann;WSL;Peter Brang;WSL;Data from: Does one model fit all? patterns of beech mortality in natural forests of three European regions;2016;Dryad;FAGUS SYLVATICA;FOREST INVENTORY;FOREST RESERVES;MORTALITY MODELS;PRIMEVAL FORESTS;TREE MORTALITY;Lisa H\u00fclsmann;0000-0003-4252-2715;University of Regensburg;2017-11-15;en;https://www.envidat.ch/dataset/data-for-huelsmann_et_al_ecol_appl_2016;CSV;1.0;License not specified;The datasets comprise nearly 19\u2019000 trees of European beech (_Fagus sylvatica_ L.) from unmanaged forests in Switzerland, Germany / Lower Saxony and Ukraine. Tree death was modelled as a function of size and growth, i.e., stem diameter (DBH) and relative basal area increment (relBAI). To explain the spatial and temporal variability in mortality patterns, we considered a large set of environmental and stand characteristics.\n\n## Inventory data\nThe strict forest reserves in Switzerland and Germany had been established in the period of 1961-1975 and 1971-1974, respectively. Every reserve included up to 10 permanent plots ranging from 0.09 to 1.8 ha in size, with slightly irregular re-measurement intervals. Permanent plots with pure or mixed beech stands were selected from the reserves of both networks. Reserves with considerable wind disturbance during the monitored intervals were excluded from the analysis. In addition to data from the Swiss and German reserves, data from a 10 ha plot in the primeval beech forest Uholka in Western Ukraine including three remeasurements were used. The inventory data provide diameter measurements at breast height (dbh) for revisited trees with a diameter of more than 4, 7 and 6 cm for Switzerland, Germany and Ukraine, respectively.\n\n## Mortality predictors\nA set of three consecutive inventories was used to generate records for the calibration of mortality models based on trees that were alive in the first and second inventory and either dead or alive in the third inventory. As an explanatory variable, the annual relative basal area increment (relBAI) was calculated based on the first and the second dbh measurement as the compound annual growth rate of the trees basal area. Tree dbh in the second inventory was used in addition to relBAI to model tree status (alive or dead) of the third inventory. \n\nTo increase the generality of the mortality models, we selected environmental variables that are known to have a considerable influence on growth and mortality of beech. We emphasized the effects of water availability using a large set of drought characteristics that were calculated based on the local site water balance. We also related beech mortality to soil pH, temperature, precipitation and growing degree-days. Additionally, we considered stand characteristics that reflect the development stage, competition and structure of the forests.\n\n## Further information\nFor further information, refer to H\u00fclsmann _et al_. (2016) Does one model fit all? patterns of beech mortality in natural forests of three European regions. _Ecological Applications_.;51.2344073516 6.6357421875;Switzerland, Germany, Ukraine",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "2374eb52-41ed-5725-8fa9-f7e6273ca109",
-    "notes": [
-        "The datasets comprise nearly 19\u2019000 trees of European beech (_Fagus sylvatica_ L.) from unmanaged forests in Switzerland, Germany / Lower Saxony and Ukraine. Tree death was modelled as a function of size and growth, i.e., stem diameter (DBH) and relative basal area increment (relBAI). To explain the spatial and temporal variability in mortality patterns, we considered a large set of environmental and stand characteristics.\n\n## Inventory data\nThe strict forest reserves in Switzerland and Germany had been established in the period of 1961-1975 and 1971-1974, respectively. Every reserve included up to 10 permanent plots ranging from 0.09 to 1.8 ha in size, with slightly irregular re-measurement intervals. Permanent plots with pure or mixed beech stands were selected from the reserves of both networks. Reserves with considerable wind disturbance during the monitored intervals were excluded from the analysis. In addition to data from the Swiss and German reserves, data from a 10 ha plot in the primeval beech forest Uholka in Western Ukraine including three remeasurements were used. The inventory data provide diameter measurements at breast height (dbh) for revisited trees with a diameter of more than 4, 7 and 6 cm for Switzerland, Germany and Ukraine, respectively.\n\n## Mortality predictors\nA set of three consecutive inventories was used to generate records for the calibration of mortality models based on trees that were alive in the first and second inventory and either dead or alive in the third inventory. As an explanatory variable, the annual relative basal area increment (relBAI) was calculated based on the first and the second dbh measurement as the compound annual growth rate of the trees basal area. Tree dbh in the second inventory was used in addition to relBAI to model tree status (alive or dead) of the third inventory. \n\nTo increase the generality of the mortality models, we selected environmental variables that are known to have a considerable influence on growth and mortality of beech. We emphasized the effects of water availability using a large set of drought characteristics that were calculated based on the local site water balance. We also related beech mortality to soil pH, temperature, precipitation and growing degree-days. Additionally, we considered stand characteristics that reflect the development stage, competition and structure of the forests.\n\n## Further information\nFor further information, refer to H\u00fclsmann _et al_. (2016) Does one model fit all? patterns of beech mortality in natural forests of three European regions. _Ecological Applications_."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:d2b9e7f9-c617-4e4d-9f04-c993e1e27ff7"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[6.6357421875,51.2344073516],[6.6357421875,51.2344073516],[6.6357421875,51.2344073516],[6.6357421875,51.2344073516],[6.6357421875,51.2344073516]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "FAGUS SYLVATICA"
-        },
-        {
-            "name": "FOREST INVENTORY"
-        },
-        {
-            "name": "FOREST RESERVES"
-        },
-        {
-            "name": "MORTALITY MODELS"
-        },
-        {
-            "name": "PRIMEVAL FORESTS"
-        },
-        {
-            "name": "TREE MORTALITY"
-        }
-    ],
-    "title": [
-        "Data from: Does one model fit all? patterns of beech mortality in natural forests of three European regions"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/25946757-be98-5351-ad28-0c1ab1aedd98.json b/oaitestdata/envidat-datacite/SET_1/json/25946757-be98-5351-ad28-0c1ab1aedd98.json
deleted file mode 100644
index bae561de..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/25946757-be98-5351-ad28-0c1ab1aedd98.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:7b250f8c-91c8-4cd8-9627-b84e64aac1c7",
-    "MetadataAccess": [
-        "oai:envidat.ch:7b250f8c-91c8-4cd8-9627-b84e64aac1c7"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/amount_of_dead_wood-214"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:7b250f8c-91c8-4cd8-9627-b84e64aac1c7;2018-12-09T00:31:17Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Amount of dead wood;2014;Swiss Federal Research Institute WSL;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;ALTITUDINAL VEGETATION ZONE;AMOUNT OF DEAD WOOD;BIOGEOGRAPHICAL REGION;CANTON;ECONOMIC REGION;FOREST DISTRICT AS OF 2013;GRID NFI4 2009-2013;LOWER-HIGHER ALTITUDINAL ZONES;NFI3;NFI4B;OWNERSHIP;PRODUCTION REGION;PROTECTION FOREST REGION;TERRESTRIAL GRID NFI3;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/amount_of_dead_wood-214;URL;1.0;Other (Open);Wood volume of all deadwood recorded according to the NFI3 method. For standing trees and shrubs  starting at 12 cm dbh, the volume of stemwood reduced due to stem breakage is recorded, and for lying deadwood the merchantable wood ( starting at 7 cm in diameter). Heaps of branches are not included.   The correction for bias with the sample Tarif trees may be so drastic that it results in negative values with small numbers of trees.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "25946757-be98-5351-ad28-0c1ab1aedd98",
-    "notes": [
-        "Wood volume of all deadwood recorded according to the NFI3 method. For standing trees and shrubs  starting at 12 cm dbh, the volume of stemwood reduced due to stem breakage is recorded, and for lying deadwood the merchantable wood ( starting at 7 cm in diameter). Heaps of branches are not included.   The correction for bias with the sample Tarif trees may be so drastic that it results in negative values with small numbers of trees.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:7b250f8c-91c8-4cd8-9627-b84e64aac1c7"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "AMOUNT DEAD WOOD"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "FOREST DISTRICT"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "LOWER-HIGHER ALTITUDINAL ZONES"
-        },
-        {
-            "name": "NFI"
-        },
-        {
-            "name": "NFIB"
-        }
-    ],
-    "title": [
-        "Amount of dead wood"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/274ac114-029a-5e94-98b6-758587d33be2.json b/oaitestdata/envidat-datacite/SET_1/json/274ac114-029a-5e94-98b6-758587d33be2.json
deleted file mode 100644
index f341b97b..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/274ac114-029a-5e94-98b6-758587d33be2.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:1bef0e93-5dc9-4552-bce2-a78edef34ad0",
-    "MetadataAccess": [
-        "oai:envidat.ch:1bef0e93-5dc9-4552-bce2-a78edef34ad0"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/net_increment_star-187"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:1bef0e93-5dc9-4552-bce2-a78edef34ad0;2018-12-09T00:32:41Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Net increment*;2014;Swiss Federal Research Institute WSL;14 X 14 KM GRID;56 CLASSES;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;ALTITUDE 400 M CLASSES;ALTITUDINAL VEGETATION ZONE;AVALANCHES SILVAPROTECT;CANTON;CONIFERS-BROADLEAVES;FOREST DISTRICT AS OF 2013;GRID NFI4 2009-2013;LANDSLIDE-MUDFLOW SILVAPROTECT;LOWER-HIGHER ALTITUDINAL ZONES;MAIN TREE SPECIES;NET INCREMENT STAR;NFI2-NFI3;NFI3-NFI4B;OWNERSHIP;POTENTIAL COST FOR TIMBER HARVESTING;PROCESSES IN CHANNELS SILVAPROTECT;PROTECTION FOREST PERIMETER SILVAPROTECT;ROCKFALL SILVAPROTECT;SITE QUALITY;TREE SPECIES WOODY SPECIES;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/net_increment_star-187;URL;1.0;Other (Open);Increment with ingrowth minus the mortality.  *In the calculation no D7/tree height data were used. The values calculated like this have not been corrected for bias, but allow for cantons or forest districts a more robust estimation of changes and could thus be better interpreted.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "274ac114-029a-5e94-98b6-758587d33be2",
-    "notes": [
-        "Increment with ingrowth minus the mortality.  *In the calculation no D7/tree height data were used. The values calculated like this have not been corrected for bias, but allow for cantons or forest districts a more robust estimation of changes and could thus be better interpreted.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:1bef0e93-5dc9-4552-bce2-a78edef34ad0"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "X KM GRID"
-        },
-        {
-            "name": "CLASSES"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ALTITUDE M CLASSES"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "AVALANCHES SILVAPROTECT"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        },
-        {
-            "name": "FOREST DISTRICT"
-        }
-    ],
-    "title": [
-        "Net increment*"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/28f7a1b8-5ae3-580e-b26c-e146585fb953.json b/oaitestdata/envidat-datacite/SET_1/json/28f7a1b8-5ae3-580e-b26c-e146585fb953.json
deleted file mode 100644
index 2153bd59..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/28f7a1b8-5ae3-580e-b26c-e146585fb953.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "Franziska Gerber"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/envidat.35",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "PDF",
-        "ZIP"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:30c985c3-4a14-4cd5-936e-9eb848175812",
-    "MetadataAccess": [
-        "oai:envidat.ch:30c985c3-4a14-4cd5-936e-9eb848175812"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Laboratory of Cryospheric Sciences CRYOS, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne EPFL, Lausanne, Switzerland"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/cosmo-wrf-documentation"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(45N-48N,7 E-11E)",
-    "TempCoverageBegin": 63652564799,
-    "TempCoverageEnd": 63652564799,
-    "TemporalCoverage": " point in time : 2018-01-26T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-01-26T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-01-26T11:59:59Z",
-    "author": [
-        "Franziska Gerber",
-        "Varun Sharma"
-    ],
-    "fulltext": "oai:envidat.ch:30c985c3-4a14-4cd5-936e-9eb848175812;2018-12-06T17:34:12Z;10.16904/envidat.35;Franziska Gerber;CRYOS, EPFL; WSL-SLF;Varun Sharma;CRYOS, EPFL;Running COSMO-WRF on very-high resolution over complex terrain;COSMO-WRF documentation;2018;Laboratory of Cryospheric Sciences CRYOS, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne EPFL, Lausanne, Switzerland;COMPLEX TERRAIN;COSMO-WRF;HIGH-RESOLUTION;NUMERICAL SIMULATION;Franziska Gerber;2018-01-26;en;https://www.envidat.ch/dataset/cosmo-wrf-documentation;275721 bytes;8317 bytes;28859 bytes;30162 bytes;6718 bytes;8787 bytes;3782 bytes;PDF;ZIP;1.0;Open Data Commons Open Database License (ODbL);This is a technical documentation of the procedure to run the Weather Research and Forecasting (WRF) model over complex alpine terrain using Consortium for Small-Scale Modeling (COSMO) reanalysis by the Federal Office of Meteorology and Climatology (MeteoSwiss) as initial and boundary conditions (COMSO-WRF). The setup is adapted for very high resolution simulations based on COSMO-2 (2.2 km resolution) reanalysis. This document gives an overview over steps to setup COSMO-WRF and adaptations needed to run COSMO-WRF. Additionally, the calculation of precipitation rate at a horizontal plane and remapping COSMO-WRF output on Swiss coordinates are documented.;45.4 7.31281 48.2535 10.6311",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "28f7a1b8-5ae3-580e-b26c-e146585fb953",
-    "notes": [
-        "This is a technical documentation of the procedure to run the Weather Research and Forecasting (WRF) model over complex alpine terrain using Consortium for Small-Scale Modeling (COSMO) reanalysis by the Federal Office of Meteorology and Climatology (MeteoSwiss) as initial and boundary conditions (COMSO-WRF). The setup is adapted for very high resolution simulations based on COSMO-2 (2.2 km resolution) reanalysis. This document gives an overview over steps to setup COSMO-WRF and adaptations needed to run COSMO-WRF. Additionally, the calculation of precipitation rate at a horizontal plane and remapping COSMO-WRF output on Swiss coordinates are documented."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:30c985c3-4a14-4cd5-936e-9eb848175812"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[7.31281,45.4],[7.31281,48.2535],[10.6311,48.2535],[10.6311,45.4],[7.31281,45.4]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "COMPLEX TERRAIN"
-        },
-        {
-            "name": "COSMO-WRF"
-        },
-        {
-            "name": "HIGH-RESOLUTION"
-        },
-        {
-            "name": "NUMERICAL SIMULATION"
-        }
-    ],
-    "title": [
-        "Running COSMO-WRF on very-high resolution over complex terrain",
-        "COSMO-WRF documentation"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/2a3db70e-fc2b-50fe-a30a-0f7b00bc160b.json b/oaitestdata/envidat-datacite/SET_1/json/2a3db70e-fc2b-50fe-a30a-0f7b00bc160b.json
deleted file mode 100644
index d6b10774..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/2a3db70e-fc2b-50fe-a30a-0f7b00bc160b.json
+++ /dev/null
@@ -1,97 +0,0 @@
-{
-    "Contact": [
-        "Michael Lehning"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/envidat.47",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "XLSX",
-        "ZIP"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:90e36ede-4301-43f3-b0cb-b524d8c81f6b",
-    "MetadataAccess": [
-        "oai:envidat.ch:90e36ede-4301-43f3-b0cb-b524d8c81f6b"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "EnviDat"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/pv_snow_mountain"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Annelen Kahl",
-        "J\u00e9r\u00f4me Dujardin",
-        "Michael Lehning"
-    ],
-    "fulltext": "oai:envidat.ch:90e36ede-4301-43f3-b0cb-b524d8c81f6b;2018-12-09T00:32:54Z;10.16904/envidat.47;Annelen Kahl;WSL/SLF and EPFL;J\u00e9r\u00f4me Dujardin;EPFL;Michael Lehning;0000-0002-8442-0875;WSL/SLF and EPFL;Dataset on PV Production in Snow Covered Mountains;2018;EnviDat;ALBEDO;ENERGY;IRRADIANCE;MOUNTAIN;PHOTOVOLTAIC;REFLECTION;SNOW;Michael Lehning;0000-0002-8442-0875;WSL/SLF and EPFL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/pv_snow_mountain;2654822 bytes;XLSX;ZIP;1.0;Open Data Commons Open Database License (ODbL);### Overview\nThe SUNWELL Modelling Environment is a combination of data and code that models electricity production from satellite-derived irradiance data and other spatial data sets for all of Switzerland. This ensemble accompanies the publication \"The bright side of PV production in snow-covered mountains\", published in the Proceedings of the National Academy of Science and reproduces all results and figures of. Code and resources are in their original form (with documentation). A new version with a more generalized application to PV modelling and with more flexibility in terms of input and output formats will be released in the coming months.\n\n### Format\nAll code is written and has to be executed in Matlab. The input and output data sets are also in the Matlab-specific .mat format. Whenever publicly available, the original data is provided as geotif, .xlsx or other common format. \nThis is the case for:\n\n- Digital Elevation Model (InputsFromMatlab/MSG/OriginalData/ASTERDEM), \n- Landsurface cover type (InputsFromMatlab/MSG/OriginalData/CORINE), \n- Population Density (InputsFromMatlab/MSG/OriginalData/popdensRaster, \n- Electricity production from three of our validation sites (/Validation/WSL), \n- Measured irradiance for two validation sites (/Validation/ASRB)\nThe \u2018Metadata\u2019 documents in the respective folders provide further information about the data sources and processing. Figures are produced either in .pdf or .png format. \n\n### Structure\nThe central level of the SUNWELL environment holds the 5 Mains, which run the different modelling aspects of the paper; each code is documented separately. Additional code is located in the __\u2018DataProcessing\u2019__ and the __\u2018functions\u2019__ folder. Functions are called in the different Mains.\n\n__\u2018InputsFromMatlab\u2019__ contains the radiation and albedo input data sets in separate subfolders (SIS/SISDIR/ALB). The original data is not publicly available, but can be requested for research purposes free of charge. We provide a processed subset of the data set that was used to run the SUNWELL simulations. The MSG subfolder contains additional spatial input data sets.\n\n__\u2018Outputs\u2019__ contains the output files from the different mains (matching names, Main_CHallpixels.m \uf0e0 Prod_CHallpixels)\n\n__\u2018Publication_figures\u2019__ contains all individual figures from the PNAS publication, as well as the generating code (/code_plot) and the power point figures (/ppts) that provide the combined final figures.\n\n__\u2018Validation\u2019__ contains the data sets used in the model validation:\n\n- Electricity production from three of our validation sites (/WSL), \n- Measured irradiance for two validation sites (/ASRB)\n\n__Electricity__ production from a validation site at Lac des Toules in Wallis (/LDT), this data set was provided under an NDA and cannot be made publicly available. \n\n__Paper Citation:__\n > _Annelen Kahl; J\u00e9r\u00f4me Dujardin; Michael Lehning (2018). Dataset on PV Production in Snow Covered Mountains. PNAS - Proceedings of the National Academy of Sciences. (in press)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "2a3db70e-fc2b-50fe-a30a-0f7b00bc160b",
-    "notes": [
-        "### Overview\nThe SUNWELL Modelling Environment is a combination of data and code that models electricity production from satellite-derived irradiance data and other spatial data sets for all of Switzerland. This ensemble accompanies the publication \"The bright side of PV production in snow-covered mountains\", published in the Proceedings of the National Academy of Science and reproduces all results and figures of. Code and resources are in their original form (with documentation). A new version with a more generalized application to PV modelling and with more flexibility in terms of input and output formats will be released in the coming months.\n\n### Format\nAll code is written and has to be executed in Matlab. The input and output data sets are also in the Matlab-specific .mat format. Whenever publicly available, the original data is provided as geotif, .xlsx or other common format. \nThis is the case for:\n\n- Digital Elevation Model (InputsFromMatlab/MSG/OriginalData/ASTERDEM), \n- Landsurface cover type (InputsFromMatlab/MSG/OriginalData/CORINE), \n- Population Density (InputsFromMatlab/MSG/OriginalData/popdensRaster, \n- Electricity production from three of our validation sites (/Validation/WSL), \n- Measured irradiance for two validation sites (/Validation/ASRB)\nThe \u2018Metadata\u2019 documents in the respective folders provide further information about the data sources and processing. Figures are produced either in .pdf or .png format. \n\n### Structure\nThe central level of the SUNWELL environment holds the 5 Mains, which run the different modelling aspects of the paper; each code is documented separately. Additional code is located in the __\u2018DataProcessing\u2019__ and the __\u2018functions\u2019__ folder. Functions are called in the different Mains.\n\n__\u2018InputsFromMatlab\u2019__ contains the radiation and albedo input data sets in separate subfolders (SIS/SISDIR/ALB). The original data is not publicly available, but can be requested for research purposes free of charge. We provide a processed subset of the data set that was used to run the SUNWELL simulations. The MSG subfolder contains additional spatial input data sets.\n\n__\u2018Outputs\u2019__ contains the output files from the different mains (matching names, Main_CHallpixels.m \uf0e0 Prod_CHallpixels)\n\n__\u2018Publication_figures\u2019__ contains all individual figures from the PNAS publication, as well as the generating code (/code_plot) and the power point figures (/ppts) that provide the combined final figures.\n\n__\u2018Validation\u2019__ contains the data sets used in the model validation:\n\n- Electricity production from three of our validation sites (/WSL), \n- Measured irradiance for two validation sites (/ASRB)\n\n__Electricity__ production from a validation site at Lac des Toules in Wallis (/LDT), this data set was provided under an NDA and cannot be made publicly available. \n\n__Paper Citation:__\n > _Annelen Kahl; J\u00e9r\u00f4me Dujardin; Michael Lehning (2018). Dataset on PV Production in Snow Covered Mountains. PNAS - Proceedings of the National Academy of Sciences. (in press)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:90e36ede-4301-43f3-b0cb-b524d8c81f6b"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ALBEDO"
-        },
-        {
-            "name": "ENERGY"
-        },
-        {
-            "name": "IRRADIANCE"
-        },
-        {
-            "name": "MOUNTAIN"
-        },
-        {
-            "name": "PHOTOVOLTAIC"
-        },
-        {
-            "name": "REFLECTION"
-        },
-        {
-            "name": "SNOW"
-        }
-    ],
-    "title": [
-        "Dataset on PV Production in Snow Covered Mountains"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/2ac2dafa-2dce-590a-93dd-087256701fa5.json b/oaitestdata/envidat-datacite/SET_1/json/2ac2dafa-2dce-590a-93dd-087256701fa5.json
deleted file mode 100644
index 3ec6a864..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/2ac2dafa-2dce-590a-93dd-087256701fa5.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:fb851074-a421-47bf-802f-f03493c57041",
-    "MetadataAccess": [
-        "oai:envidat.ch:fb851074-a421-47bf-802f-f03493c57041"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/total_basal_area-2"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:fb851074-a421-47bf-802f-f03493c57041;2018-12-09T00:33:17Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Total basal area;2014;Swiss Federal Research Institute WSL;7 CLASSES;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;ALTITUDINAL VEGETATION ZONE;BIOGEOGRAPHICAL REGION;CANTON;ECONOMIC REGION;FOREST COMMUNITIES K\u00dcCHLER 2008;GRID NFI4 2009-2013;MAIN TREE SPECIES;NFI2;NFI3;NFI4B;PRODUCTION REGION;PROTECTION FOREST REGION;TERRESTRIAL GRID NFI2;TERRESTRIAL GRID NFI3;TOTAL BASAL AREA;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/total_basal_area-2;URL;1.0;Other (Open);Sum of the stem cross-section areas of all living and dead trees and shrubs starting at 12 cm dbh at a height of 1.3 m (dbh measurement height).\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "2ac2dafa-2dce-590a-93dd-087256701fa5",
-    "notes": [
-        "Sum of the stem cross-section areas of all living and dead trees and shrubs starting at 12 cm dbh at a height of 1.3 m (dbh measurement height).\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:fb851074-a421-47bf-802f-f03493c57041"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "CLASSES"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "MAIN TREE SPECIES"
-        },
-        {
-            "name": "NFI"
-        }
-    ],
-    "title": [
-        "Total basal area"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/2bcf856c-e5a8-5228-966c-cfe8e62e924b.json b/oaitestdata/envidat-datacite/SET_1/json/2bcf856c-e5a8-5228-966c-cfe8e62e924b.json
deleted file mode 100644
index 182de761..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/2bcf856c-e5a8-5228-966c-cfe8e62e924b.json
+++ /dev/null
@@ -1,92 +0,0 @@
-{
-    "Contact": [
-        "Lisa H\u00fclsmann"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/envidat.27",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "CSV"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:3a492ec9-def3-4e75-9778-dc397f63264d",
-    "MetadataAccess": [
-        "oai:envidat.ch:3a492ec9-def3-4e75-9778-dc397f63264d"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "WSL, NW-FVA"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/10-16904-envidat-27"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(51N,7 E)",
-    "TempCoverageBegin": 63646343999,
-    "TempCoverageEnd": 63646343999,
-    "TemporalCoverage": " point in time : 2017-11-15T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2017-11-15T11:59:59Z",
-    "TemporalCoverage:EndDate": "2017-11-15T11:59:59Z",
-    "author": [
-        "Peter Brang",
-        "Maxime Cailleret",
-        "Lisa H\u00fclsmann",
-        "Harald Bugmann",
-        "Peter Meyer"
-    ],
-    "fulltext": "oai:envidat.ch:3a492ec9-def3-4e75-9778-dc397f63264d;2018-07-06T22:12:59Z;10.16904/envidat.27;Lisa H\u00fclsmann;0000-0003-4252-2715;WSL;Harald Bugmann;ETHZ;Maxime Cailleret;WSL;Peter Brang;WSL;Peter Meyer;NW-FVA;Calibration data for empirical mortality models of 18 European tree species;2017;WSL, NW-FVA;EMPIRICAL MORTALITY MODELS;FOREST RESERVES;INVENTORY DATA;TREE GROWTH;TREE MORTALITY;Lisa H\u00fclsmann;0000-0003-4252-2715;University of Regensburg;2017-11-15;en;Dataset;https://www.envidat.ch/dataset/10-16904-envidat-27;10706192 bytes;CSV;1.0;Open Data Commons Open Database License (ODbL);The dataset comprises > 90 000 records from inventories in 54 strict forest reserves in [Switzerland](https://www.wsl.ch/de/wald/biodiversitaet-naturschutz-urwald/naturwaldreservate.html) and [Lower Saxony / Germany](http://naturwaelder.de/) along a considerable environmental gradient. It was used to develop parsimonious, species-specific mortality models for 18 European tree species based on tree size and growth as well as additional covariates on stand structure and climate. \n\n## Inventory data\nMeasurements had been conducted repeatedly on up to 14 permanent plots per reserve for up to 60 years with re-measurement intervals of 4 - 27 years. The permanent plots vary in size between 0.03 and 3.47 ha. The inventories provide diameter measurements at breast height (DBH) and information on the species and status (alive or dead) of trees with DBH \u2265 4 cm for Switzerland and \u2265 7 cm for Germany. \n\n## Data selection\nWe excluded three permanent plots where at least 80 % of the trees died during an interval of 10 years, and mortality could be clearly assigned to a disturbance agent. Mortality in the remaining stands was rather low, with a mean annual mortality rate of 1.5 % and strong variation between plots from 0 to 6.5 % (assessed for trees of all species with DBH \u2265 7 cm).\nWe only used data from permanent plots with at least 20 trees per species to obtain reliable plot-level mortality rates even for species with low mortality rates (about 5 % during 10 years), and selected tree species occurring on at least 10 plots to cover sufficient ecological gradients. This led to a dataset of 197 permanent plots and 18 tree or shrub species: _Abies alba_ Mill., _Acer campestre_ L., _Acer pseudoplatanus_ L., _Alnus incana_ Moench., _Betula pendula_ Roth, _Carpinus betulus_ L., _Cornus mas_ L., _Corylus avellana_ L., _Fagus sylvatica_ L., _Fraxinus excelsior_ L., _Picea abies_ (L.) Karst, _Pinus mugo_ Turra, _Pinus sylvestris_ L., _Quercus pubescens_ Willd., _Quercus_ spp. (_Q. petraea_ Liebl. and _Q. robur_ L.; not properly differentiated in the Swiss inventories), _Sorbus aria_ Crantz, _Tilia cordata_ Mill. and _Ulmus glabra_ Huds.. \n\n## Predictors of tree mortality\nWe considered tree size and growth as key indicators for mortality risk. Radial stem growth between the first and second inventory and DBH at the second inventory were used to predict tree status (alive or dead) at the third inventory. To this end, the annual relative basal area increment (relBAI) was calculated as the compound annual growth rate of the trees basal area. Additional covariates on stand structure and climate comprise mean annual precipitation sum (P), mean annual air temperature (mT), the mean and the interquartile range of DBH (mDBH, iqrDBH), basal area (BA) and the number of trees (N) per hectare. \n\n## Further information\nFor further information, refer to H\u00fclsmann _et al_. (in press) How to kill a tree \u2013 Empirical mortality models for eighteen species and their performance in a dynamic forest model. _Ecological Applications_.;51.2344073516 6.6357421875;Switzerland, Germany (Lower Saxony)",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "2bcf856c-e5a8-5228-966c-cfe8e62e924b",
-    "notes": [
-        "The dataset comprises > 90 000 records from inventories in 54 strict forest reserves in [Switzerland](https://www.wsl.ch/de/wald/biodiversitaet-naturschutz-urwald/naturwaldreservate.html) and [Lower Saxony / Germany](http://naturwaelder.de/) along a considerable environmental gradient. It was used to develop parsimonious, species-specific mortality models for 18 European tree species based on tree size and growth as well as additional covariates on stand structure and climate. \n\n## Inventory data\nMeasurements had been conducted repeatedly on up to 14 permanent plots per reserve for up to 60 years with re-measurement intervals of 4 - 27 years. The permanent plots vary in size between 0.03 and 3.47 ha. The inventories provide diameter measurements at breast height (DBH) and information on the species and status (alive or dead) of trees with DBH \u2265 4 cm for Switzerland and \u2265 7 cm for Germany. \n\n## Data selection\nWe excluded three permanent plots where at least 80 % of the trees died during an interval of 10 years, and mortality could be clearly assigned to a disturbance agent. Mortality in the remaining stands was rather low, with a mean annual mortality rate of 1.5 % and strong variation between plots from 0 to 6.5 % (assessed for trees of all species with DBH \u2265 7 cm).\nWe only used data from permanent plots with at least 20 trees per species to obtain reliable plot-level mortality rates even for species with low mortality rates (about 5 % during 10 years), and selected tree species occurring on at least 10 plots to cover sufficient ecological gradients. This led to a dataset of 197 permanent plots and 18 tree or shrub species: _Abies alba_ Mill., _Acer campestre_ L., _Acer pseudoplatanus_ L., _Alnus incana_ Moench., _Betula pendula_ Roth, _Carpinus betulus_ L., _Cornus mas_ L., _Corylus avellana_ L., _Fagus sylvatica_ L., _Fraxinus excelsior_ L., _Picea abies_ (L.) Karst, _Pinus mugo_ Turra, _Pinus sylvestris_ L., _Quercus pubescens_ Willd., _Quercus_ spp. (_Q. petraea_ Liebl. and _Q. robur_ L.; not properly differentiated in the Swiss inventories), _Sorbus aria_ Crantz, _Tilia cordata_ Mill. and _Ulmus glabra_ Huds.. \n\n## Predictors of tree mortality\nWe considered tree size and growth as key indicators for mortality risk. Radial stem growth between the first and second inventory and DBH at the second inventory were used to predict tree status (alive or dead) at the third inventory. To this end, the annual relative basal area increment (relBAI) was calculated as the compound annual growth rate of the trees basal area. Additional covariates on stand structure and climate comprise mean annual precipitation sum (P), mean annual air temperature (mT), the mean and the interquartile range of DBH (mDBH, iqrDBH), basal area (BA) and the number of trees (N) per hectare. \n\n## Further information\nFor further information, refer to H\u00fclsmann _et al_. (in press) How to kill a tree \u2013 Empirical mortality models for eighteen species and their performance in a dynamic forest model. _Ecological Applications_."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:3a492ec9-def3-4e75-9778-dc397f63264d"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[6.6357421875,51.2344073516],[6.6357421875,51.2344073516],[6.6357421875,51.2344073516],[6.6357421875,51.2344073516],[6.6357421875,51.2344073516]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "EMPIRICAL MORTALITY MODELS"
-        },
-        {
-            "name": "FOREST RESERVES"
-        },
-        {
-            "name": "INVENTORY DATA"
-        },
-        {
-            "name": "TREE GROWTH"
-        },
-        {
-            "name": "TREE MORTALITY"
-        }
-    ],
-    "title": [
-        "Calibration data for empirical mortality models of 18 European tree species"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/2e6fc4dc-1ef2-5533-b25c-0ebb27ab2593.json b/oaitestdata/envidat-datacite/SET_1/json/2e6fc4dc-1ef2-5533-b25c-0ebb27ab2593.json
deleted file mode 100644
index 3187b28a..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/2e6fc4dc-1ef2-5533-b25c-0ebb27ab2593.json
+++ /dev/null
@@ -1,90 +0,0 @@
-{
-    "Contact": [
-        "Yves B\u00fchler"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/envidat.31",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "TIFF",
-        "tfw"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:84db9938-9af5-4ae1-8e30-cb45c61fc274",
-    "MetadataAccess": [
-        "oai:envidat.ch:84db9938-9af5-4ae1-8e30-cb45c61fc274"
-    ],
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "The Cryosphere"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/uas-based-snow-depth-maps-bramabuel-davos-ch"
-    ],
-    "ResourceType": [
-        "tif raster"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N-47N,10E-10E)",
-    "TempCoverageBegin": 63564605999,
-    "TempCoverageEnd": 63564605999,
-    "TemporalCoverage": " point in time : 2015-04-14T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2015-04-14T11:59:59Z",
-    "TemporalCoverage:EndDate": "2015-04-14T11:59:59Z",
-    "author": [
-        "Yves B\u00fchler"
-    ],
-    "fulltext": "oai:envidat.ch:84db9938-9af5-4ae1-8e30-cb45c61fc274;2018-12-06T17:36:41Z;10.16904/envidat.31;Yves B\u00fchler;SLF;UAS based snow depth maps Br\u00e4mab\u00fcel, Davos, CH;high spatial resolution snow depth map;2016;The Cryosphere;REMOTE SENSING;SNOW;SNOW DEPTH;SWE;UAS;Yves B\u00fchler;SLF;2015-04-14;en;tif raster;https://www.envidat.ch/dataset/uas-based-snow-depth-maps-bramabuel-davos-ch;163529181 bytes;89 bytes;TIFF;tfw;1.0;Open Data Commons Open Database License (ODbL);This snow depth map was generated 14 January 2015, close to peak of winter accumulation, applying Unmanned Aerial System digital surface models with a spatial resolution of 10 cm. The covered area is 285'000 m2 at the top of Br\u00e4mab\u00fcel, 2490 m a.s.l. covering all expositions. Coordinate system: CH1903LV03.\n\nA detailed description is given here:\n\nB\u00fchler, Y., Adams, M. S., B\u00f6sch, R., and Stoffel, A.: Mapping snow depth in alpine terrain with unmanned aerial systems (UASs): potential and limitations, The Cryosphere, 10, 1075-1088, 10.5194/tc-10-1075-2016, 2016.\n\nAbstract:\nDetailed information on the spatial and temporal distribution, and variability of snow depth (HS) is a crucial input for numerous applications in hydrology, climatology, ecology and avalanche research. Nowadays, snow depth distribution is usually estimated by combining point measurements from weather stations or observers in the field with spatial interpolation algorithms. However, even a dense measurement network is not able to capture the large spatial variability of snow depth in alpine terrain. \nRemote sensing methods, such as laser scanning or digital photogrammetry, have recently been successfully applied to map snow depth variability at local and regional scales. However, such data acquisition is costly, if manned airplanes are involved. The effectiveness of ground-based measurements on the other hand, is often hindered by occlusions, due to the complex terrain or acute viewing angles. In this paper, we investigate the application of unmanned aerial systems (UAS), in combination with structure-from-motion photogrammetry, to map snow depth distribution. Such systems have the advantage that they are comparatively cost-effective and can be applied very flexibly to cover also otherwise inaccessible terrain. In this study we map snow depth at two different locations: a) a sheltered location at the bottom of the Fl\u00fcela valley (1900 m a.s.l.) and b) an exposed location (2500 m a.s.l.) on a peak in the ski resort Jakobshorn, both in the vicinity of Davos, Switzerland. At the first test site, we monitor the ablation on three different dates. We validate the photogrammetric snow depth maps using simultaneously acquired manual snow depth measurements. The resulting snow depth values have a root mean square error (RMSE) better than 0.07 to 0.15 m on meadows and rocks and a RMSE better than 0.30 m on sections covered by bushes or tall grass. This new measurement technology opens the door for efficient, flexible, repeatable and cost effective snow depth monitoring for various applications, investigating the worlds cryosphere.;46.7827679855 9.84855651855 46.7809459618 9.8459815979;Br\u00e4mab\u00fcl, Jakobshorn, Davos, Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "2e6fc4dc-1ef2-5533-b25c-0ebb27ab2593",
-    "notes": [
-        "This snow depth map was generated 14 January 2015, close to peak of winter accumulation, applying Unmanned Aerial System digital surface models with a spatial resolution of 10 cm. The covered area is 285'000 m2 at the top of Br\u00e4mab\u00fcel, 2490 m a.s.l. covering all expositions. Coordinate system: CH1903LV03.\n\nA detailed description is given here:\n\nB\u00fchler, Y., Adams, M. S., B\u00f6sch, R., and Stoffel, A.: Mapping snow depth in alpine terrain with unmanned aerial systems (UASs): potential and limitations, The Cryosphere, 10, 1075-1088, 10.5194/tc-10-1075-2016, 2016.\n\nAbstract:\nDetailed information on the spatial and temporal distribution, and variability of snow depth (HS) is a crucial input for numerous applications in hydrology, climatology, ecology and avalanche research. Nowadays, snow depth distribution is usually estimated by combining point measurements from weather stations or observers in the field with spatial interpolation algorithms. However, even a dense measurement network is not able to capture the large spatial variability of snow depth in alpine terrain. \nRemote sensing methods, such as laser scanning or digital photogrammetry, have recently been successfully applied to map snow depth variability at local and regional scales. However, such data acquisition is costly, if manned airplanes are involved. The effectiveness of ground-based measurements on the other hand, is often hindered by occlusions, due to the complex terrain or acute viewing angles. In this paper, we investigate the application of unmanned aerial systems (UAS), in combination with structure-from-motion photogrammetry, to map snow depth distribution. Such systems have the advantage that they are comparatively cost-effective and can be applied very flexibly to cover also otherwise inaccessible terrain. In this study we map snow depth at two different locations: a) a sheltered location at the bottom of the Fl\u00fcela valley (1900 m a.s.l.) and b) an exposed location (2500 m a.s.l.) on a peak in the ski resort Jakobshorn, both in the vicinity of Davos, Switzerland. At the first test site, we monitor the ablation on three different dates. We validate the photogrammetric snow depth maps using simultaneously acquired manual snow depth measurements. The resulting snow depth values have a root mean square error (RMSE) better than 0.07 to 0.15 m on meadows and rocks and a RMSE better than 0.30 m on sections covered by bushes or tall grass. This new measurement technology opens the door for efficient, flexible, repeatable and cost effective snow depth monitoring for various applications, investigating the worlds cryosphere."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:84db9938-9af5-4ae1-8e30-cb45c61fc274"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[9.84855651855,46.7827679855],[9.84855651855,46.7809459618],[9.8459815979,46.7809459618],[9.8459815979,46.7827679855],[9.84855651855,46.7827679855]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "REMOTE SENSING"
-        },
-        {
-            "name": "SNOW"
-        },
-        {
-            "name": "SNOW DEPTH"
-        },
-        {
-            "name": "SWE"
-        },
-        {
-            "name": "UAS"
-        }
-    ],
-    "title": [
-        "UAS based snow depth maps Br\u00e4mab\u00fcel, Davos, CH",
-        "high spatial resolution snow depth map"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/2ee260b1-0051-5758-ae75-fe575f684c0a.json b/oaitestdata/envidat-datacite/SET_1/json/2ee260b1-0051-5758-ae75-fe575f684c0a.json
deleted file mode 100644
index ef8fb5db..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/2ee260b1-0051-5758-ae75-fe575f684c0a.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:71b66e5c-fc32-4997-81bc-6bc8b29680ca",
-    "MetadataAccess": [
-        "oai:envidat.ch:71b66e5c-fc32-4997-81bc-6bc8b29680ca"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/stem_count_of_young_forest-191"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:71b66e5c-fc32-4997-81bc-6bc8b29680ca;2018-12-09T00:33:09Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Stem count of young forest;2014;Swiss Federal Research Institute WSL;ACCESSIBLE FOREST WITHOUT SHRUB FOREST WITH YOUNG FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST WITH YOUNG FOREST NFI2-NFI3-NFI4;BIOGEOGRAPHICAL REGION;CANTON;ECONOMIC REGION;GRID NFI4 2009-2013;MAIN TREE SPECIES IN YOUNG FOREST;NFI2;NFI4B;PRODUCTION REGION;PROTECTION FOREST REGION;STEM COUNT OF YOUNG FOREST;TERRESTRIAL GRID NFI2;YOUNG FOREST CLASS RAW DATA;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/stem_count_of_young_forest-191;URL;1.0;Other (Open);#191#  Number of regeneration trees  starting at 10 cm tall up to 11.9 cm dbh recorded in NFI\u2019s regeneration survey.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "2ee260b1-0051-5758-ae75-fe575f684c0a",
-    "notes": [
-        "#191#  Number of regeneration trees  starting at 10 cm tall up to 11.9 cm dbh recorded in NFI\u2019s regeneration survey.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:71b66e5c-fc32-4997-81bc-6bc8b29680ca"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST YOUNG FOREST"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "MAIN TREE SPECIES YOUNG FOREST"
-        },
-        {
-            "name": "NFI"
-        },
-        {
-            "name": "NFIB"
-        },
-        {
-            "name": "PRODUCTION REGION"
-        },
-        {
-            "name": "PROTECTION FOREST REGION"
-        },
-        {
-            "name": "STEM COUNT YOUNG FOREST"
-        },
-        {
-            "name": "TERRESTRIAL GRID NFI"
-        }
-    ],
-    "title": [
-        "Stem count of young forest"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/2f03ea5e-3565-570f-8c2e-cbe103719017.json b/oaitestdata/envidat-datacite/SET_1/json/2f03ea5e-3565-570f-8c2e-cbe103719017.json
deleted file mode 100644
index 7407e33f..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/2f03ea5e-3565-570f-8c2e-cbe103719017.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:7fa34688-141f-403e-8872-f92247dfce66",
-    "MetadataAccess": [
-        "oai:envidat.ch:7fa34688-141f-403e-8872-f92247dfce66"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/length_of_forest_roads-78"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:7fa34688-141f-403e-8872-f92247dfce66;2018-12-09T00:31:58Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Length of forest roads;2014;Swiss Federal Research Institute WSL;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;BIOGEOGRAPHICAL REGION;CANTON;ECONOMIC REGION;GRID NFI4 2009-2013;LENGTH OF FOREST ROADS;LOWER-HIGHER ALTITUDINAL ZONES;NFI3;OWNERSHIP;PRODUCTION REGION;PROTECTION FOREST REGION;TERRESTRIAL GRID NFI3;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/length_of_forest_roads-78;URL;1.0;Other (Open);The length of forest roads corresponds to the length of the NFI forest roads. This length was calculated according to the method of the specific NFI concerned.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "2f03ea5e-3565-570f-8c2e-cbe103719017",
-    "notes": [
-        "The length of forest roads corresponds to the length of the NFI forest roads. This length was calculated according to the method of the specific NFI concerned.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:7fa34688-141f-403e-8872-f92247dfce66"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "LENGTH FOREST ROADS"
-        },
-        {
-            "name": "LOWER-HIGHER ALTITUDINAL ZONES"
-        },
-        {
-            "name": "NFI"
-        },
-        {
-            "name": "OWNERSHIP"
-        },
-        {
-            "name": "PRODUCTION REGION"
-        }
-    ],
-    "title": [
-        "Length of forest roads"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/3349005f-8c9a-57b8-b161-37da1c75080f.json b/oaitestdata/envidat-datacite/SET_1/json/3349005f-8c9a-57b8-b161-37da1c75080f.json
deleted file mode 100644
index e3ddf963..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/3349005f-8c9a-57b8-b161-37da1c75080f.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:98be1911-f092-442f-8156-3b0a6cf4e464",
-    "MetadataAccess": [
-        "oai:envidat.ch:98be1911-f092-442f-8156-3b0a6cf4e464"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/mass_of_merchantable_branches_of_live_trees-47"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:98be1911-f092-442f-8156-3b0a6cf4e464;2018-12-09T00:32:33Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Mass of merchantable branches of live trees;2014;Swiss Federal Research Institute WSL;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;BIOGEOGRAPHICAL REGION;CANTON;CONIFERS-BROADLEAVES;ECONOMIC REGION;GRID NFI4 2009-2013;MASS OF MERCHANTABLE BRANCHES OF LIVE TREES;NFI3;NFI4B;PRODUCTION REGION;PROTECTION FOREST REGION;TERRESTRIAL GRID NFI3;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/mass_of_merchantable_branches_of_live_trees-47;URL;1.0;Other (Open);Dry weight (mass) of branches with a diameter of at least 7 cm from living trees and shrubs  starting at 12cm dbh.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "3349005f-8c9a-57b8-b161-37da1c75080f",
-    "notes": [
-        "Dry weight (mass) of branches with a diameter of at least 7 cm from living trees and shrubs  starting at 12cm dbh.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:98be1911-f092-442f-8156-3b0a6cf4e464"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "MASS MERCHANTABLE BRANCHES LIVE TREES"
-        },
-        {
-            "name": "NFI"
-        },
-        {
-            "name": "NFIB"
-        },
-        {
-            "name": "PRODUCTION REGION"
-        },
-        {
-            "name": "PROTECTION FOREST REGION"
-        }
-    ],
-    "title": [
-        "Mass of merchantable branches of live trees"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/34de5744-e093-539f-88b3-b8ec716fa68c.json b/oaitestdata/envidat-datacite/SET_1/json/34de5744-e093-539f-88b3-b8ec716fa68c.json
deleted file mode 100644
index dcc40672..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/34de5744-e093-539f-88b3-b8ec716fa68c.json
+++ /dev/null
@@ -1,104 +0,0 @@
-{
-    "Contact": [
-        "Andrin Caviezel"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/envidat.37",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "application/x-7z-compressed",
-        "ZIP"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:5b7a47bf-cbea-42a0-879f-ea2ccd17e82f",
-    "MetadataAccess": [
-        "oai:envidat.ch:5b7a47bf-cbea-42a0-879f-ea2ccd17e82f"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avalanche Research SLF"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/experimental-rockfall-dataset-tschamut-grisons-switzerland"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N-47N,9 E-9 E)",
-    "TempCoverageBegin": 63658609199,
-    "TempCoverageEnd": 63658609199,
-    "TemporalCoverage": " point in time : 2018-04-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-04-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-04-06T11:59:59Z",
-    "author": [
-        "Andrin Caviezel",
-        "Perry Bartelt",
-        "Marc Christen",
-        "Yves B\u00fchler"
-    ],
-    "fulltext": "oai:envidat.ch:5b7a47bf-cbea-42a0-879f-ea2ccd17e82f;2018-12-09T00:23:44Z;10.16904/envidat.37;Andrin Caviezel;0000-0001-6249-4913;WSL Institute for Snow and Avalanche Research SLF;Yves B\u00fchler;WSL Institute for Snow and Avalanche Research SLF;Marc Christen;WSL Institute for Snow and Avalanche Research SLF;Perry Bartelt;WSL Institute for Snow and Avalanche Research SLF;Induced Rockfall Dataset (Small Rock Experimental Campaign), Tschamut, Grisons, Switzerland;2018;WSL Institute for Snow and Avalanche Research SLF;DEM;DEPOSITION POINTS;INDUCED ROCKFALL;ROCKFALL;ROCKFALL EXPERIMENTS;ROCKFALL RUNOUT;SENSOR STREAM;STONENODE;STONENODEDATA;Andrin Caviezel;0000-0001-6249-4913;WSL Institute for Snow and Avalanche Research SLF;2018-04-06;en;Dataset;https://www.envidat.ch/dataset/experimental-rockfall-dataset-tschamut-grisons-switzerland;83833546 bytes;6899716 bytes;ZIP;application/x-7z-compressed;1.0;Open Data Commons Open Database License (ODbL);#Dataset of an experimental campaign of induced rockfall in Tschamut, Grisons, Switzerland. \n\nThe data archive contains site specific geographical data such as DEM and orthophoto as well as the deposition points of manually induced rockfall by releasing differently shaped boulders with 30\u201380 kg of mass. Additionally available are all the StoneNode data streams for rocks equipped with a sensor. The data set consists of \n</ul>\n* Deposition points from two series (wet (27/10/2016) and frozen (08/12/2016) ground)  \n* Digital Elevation Model (grid resolution 2 m) obtained via UAV\n* Orthophoto (5 cm resolution) obtained via UAV\n* Digitized rock point clouds (.pts input files for RAMMS::ROCKFALL)\n* StoneNode v1.0 raw data stream for equipped rocks.\n\nFurther information is found in\n</ul>\n* __A. Caviezel__ et al., _Design and Evaluation of a Low-Power Sensor Device for Induced Rockfall Experiments_, IEEE Transactions on Instrumentation and Measurement, 2018, 67, 767-779, http://ieeexplore.ieee.org/document/8122020/\n* __ P. Niklaus__ et al., _StoneNode: A low-power sensor device for induced rockfall experiments_, 2017 IEEE Sensors Applications Symposium (SAS), 2017, 1-6, http://ieeexplore.ieee.org/document/7894081/;46.6518076158 8.70076417923 46.6540464071 8.70375752449;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "34de5744-e093-539f-88b3-b8ec716fa68c",
-    "notes": [
-        "#Dataset of an experimental campaign of induced rockfall in Tschamut, Grisons, Switzerland. \n\nThe data archive contains site specific geographical data such as DEM and orthophoto as well as the deposition points of manually induced rockfall by releasing differently shaped boulders with 30\u201380 kg of mass. Additionally available are all the StoneNode data streams for rocks equipped with a sensor. The data set consists of \n</ul>\n* Deposition points from two series (wet (27/10/2016) and frozen (08/12/2016) ground)  \n* Digital Elevation Model (grid resolution 2 m) obtained via UAV\n* Orthophoto (5 cm resolution) obtained via UAV\n* Digitized rock point clouds (.pts input files for RAMMS::ROCKFALL)\n* StoneNode v1.0 raw data stream for equipped rocks.\n\nFurther information is found in\n</ul>\n* __A. Caviezel__ et al., _Design and Evaluation of a Low-Power Sensor Device for Induced Rockfall Experiments_, IEEE Transactions on Instrumentation and Measurement, 2018, 67, 767-779, http://ieeexplore.ieee.org/document/8122020/\n* __ P. Niklaus__ et al., _StoneNode: A low-power sensor device for induced rockfall experiments_, 2017 IEEE Sensors Applications Symposium (SAS), 2017, 1-6, http://ieeexplore.ieee.org/document/7894081/"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:5b7a47bf-cbea-42a0-879f-ea2ccd17e82f"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[8.70076417923,46.6518076158],[8.70076417923,46.6540464071],[8.70375752449,46.6540464071],[8.70375752449,46.6518076158],[8.70076417923,46.6518076158]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "DEM"
-        },
-        {
-            "name": "DEPOSITION POINTS"
-        },
-        {
-            "name": "INDUCED ROCKFALL"
-        },
-        {
-            "name": "ROCKFALL"
-        },
-        {
-            "name": "ROCKFALL EXPERIMENTS"
-        },
-        {
-            "name": "ROCKFALL RUNOUT"
-        },
-        {
-            "name": "SENSOR STREAM"
-        },
-        {
-            "name": "STONENODE"
-        },
-        {
-            "name": "STONENODEDATA"
-        }
-    ],
-    "title": [
-        "Induced Rockfall Dataset (Small Rock Experimental Campaign), Tschamut, Grisons, Switzerland"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/350fb689-e44d-5d31-965f-e3ec6dda96b6.json b/oaitestdata/envidat-datacite/SET_1/json/350fb689-e44d-5d31-965f-e3ec6dda96b6.json
deleted file mode 100644
index 1c858e57..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/350fb689-e44d-5d31-965f-e3ec6dda96b6.json
+++ /dev/null
@@ -1,89 +0,0 @@
-{
-    "Contact": [
-        "Lars Waser"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/1000001.3",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "PDF",
-        "TXT",
-        "JPEG"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:82d763fa-123a-4648-b827-0dec02a5efbc",
-    "MetadataAccess": [
-        "oai:envidat.ch:82d763fa-123a-4648-b827-0dec02a5efbc"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "National Forest Inventory (NFI)"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/forest-type-nfi"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Not Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63655934399,
-    "TempCoverageEnd": 63655934399,
-    "TemporalCoverage": " point in time : 2018-03-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-03-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-03-06T11:59:59Z",
-    "author": [
-        "Lars Waser",
-        "Christian Ginzler"
-    ],
-    "fulltext": "oai:envidat.ch:82d763fa-123a-4648-b827-0dec02a5efbc;2018-04-03T13:06:34Z;10.16904/1000001.3;Lars Waser;D-5937-2011;Swiss Federal Institute for Forest, Snow and Landscape Research WSL;Christian Ginzler;E-9544-2012;Swiss Federal Institute for Forest, Snow and Landscape Research WSL;Forest Type NFI;Waldmischungsgrad LFI;2018;National Forest Inventory (NFI);FOREST;FOREST INVENTORY;FOREST TYPE;NFI;Lars Waser;D-5937-2011;Swiss Federal Institute for Forest, Snow and Landscape Research WSL;2018-03-06;en;Dataset;https://www.envidat.ch/dataset/forest-type-nfi;88 bytes;3072776 bytes;TXT;PDF;JPEG;2016 (current);Other (Not Open);This dataset presents an remote sensing based approach for a countrywide mapping of broadleaved and coniferous trees in Switzerland with a spatial resolution of 3 m x 3 m. The data available is a raster of 25 m x 25 m with the fraction of broadleaf trees. The classification approach incorporates a random forest classifier, explanatory variables from multispectral aerial imagery and a Digital Terrain Model (DTM) from Airborne Laser Scanning (ALS) data, digitized training polygons and independent validation data from the National Forest Inventory (NFI). Whereas high model overall accuracies (0.99)\nand kappa (0.98) were achieved, the comparison of the tree type map with independent NFI data revealed significant deviations that are related to underestimations of broadleaved trees (median of 3.17%).;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "350fb689-e44d-5d31-965f-e3ec6dda96b6",
-    "notes": [
-        "This dataset presents an remote sensing based approach for a countrywide mapping of broadleaved and coniferous trees in Switzerland with a spatial resolution of 3 m x 3 m. The data available is a raster of 25 m x 25 m with the fraction of broadleaf trees. The classification approach incorporates a random forest classifier, explanatory variables from multispectral aerial imagery and a Digital Terrain Model (DTM) from Airborne Laser Scanning (ALS) data, digitized training polygons and independent validation data from the National Forest Inventory (NFI). Whereas high model overall accuracies (0.99)\nand kappa (0.98) were achieved, the comparison of the tree type map with independent NFI data revealed significant deviations that are related to underestimations of broadleaved trees (median of 3.17%)."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:82d763fa-123a-4648-b827-0dec02a5efbc"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "FOREST"
-        },
-        {
-            "name": "FOREST INVENTORY"
-        },
-        {
-            "name": "FOREST TYPE"
-        },
-        {
-            "name": "NFI"
-        }
-    ],
-    "title": [
-        "Forest Type NFI",
-        "Waldmischungsgrad LFI"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/36c85dc1-9f93-557d-95bd-852a6b39332f.json b/oaitestdata/envidat-datacite/SET_1/json/36c85dc1-9f93-557d-95bd-852a6b39332f.json
deleted file mode 100644
index b74ff776..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/36c85dc1-9f93-557d-95bd-852a6b39332f.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:40996545-d02b-4d28-86ac-e85476608a20",
-    "MetadataAccess": [
-        "oai:envidat.ch:40996545-d02b-4d28-86ac-e85476608a20"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/basal_area_of_dead_wood-171"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:40996545-d02b-4d28-86ac-e85476608a20;2018-12-09T00:31:25Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Basal area of dead wood;2014;Swiss Federal Research Institute WSL;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;ALTITUDINAL VEGETATION ZONE;ALTITUDINAL VEGETATION ZONE 3 CLASSES;BASAL AREA OF DEAD WOOD;BIOGEOGRAPHICAL REGION;CANTON;CONIFERS-BROADLEAVES;ECONOMIC REGION;EXTENT OF AREAL DAMAGE 10 CLASSES;FOREST DISTRICT AS OF 2013;GRID NFI4 2009-2013;LOWER-HIGHER ALTITUDINAL ZONES;MAIN TREE SPECIES;MECHANICAL STRENGTH OF WOOD;NFI2;NFI3;NFI4B;OWNERSHIP;PRIMARY FOREST FUNCTION NFI4 NATURE PROTECTION;PRODUCTION REGION;PROTECTION FOREST REGION;REMAINING BARK ON DEAD WOOD 3 CLASSES;TERRESTRIAL GRID NFI2;TERRESTRIAL GRID NFI3;TREE STATE STANDING-LYING;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/basal_area_of_dead_wood-171;URL;1.0;Other (Open);Sum of the stem cross-section areas of all dead trees in a stand at a height of 1.3 m (dbh measurement height).\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "36c85dc1-9f93-557d-95bd-852a6b39332f",
-    "notes": [
-        "Sum of the stem cross-section areas of all dead trees in a stand at a height of 1.3 m (dbh measurement height).\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:40996545-d02b-4d28-86ac-e85476608a20"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE CLASSES"
-        },
-        {
-            "name": "BASAL AREA DEAD WOOD"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "EXTENT AREAL DAMAGE CLASSES"
-        },
-        {
-            "name": "FOREST DISTRICT"
-        }
-    ],
-    "title": [
-        "Basal area of dead wood"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/36f343bb-9a7e-5044-93d2-f2704007865f.json b/oaitestdata/envidat-datacite/SET_1/json/36f343bb-9a7e-5044-93d2-f2704007865f.json
deleted file mode 100644
index 529e8040..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/36f343bb-9a7e-5044-93d2-f2704007865f.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:861d05f9-6125-4540-b4d6-d454c595d70e",
-    "MetadataAccess": [
-        "oai:envidat.ch:861d05f9-6125-4540-b4d6-d454c595d70e"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/total_stem_number_by_type_of_damage-208"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:861d05f9-6125-4540-b4d6-d454c595d70e;2018-12-09T00:33:24Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Total stem number by type of damage;2014;Swiss Federal Research Institute WSL;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;ALTITUDE 200 M CLASS;BIOGEOGRAPHICAL REGION;CANTON;DAMAGE OF TREE;ECONOMIC REGION;GRID NFI4 2009-2013;NFI3;NFI4B;PRODUCTION REGION;PROTECTION FOREST REGION;SLOPE 20 CLASSES;TERRESTRIAL GRID NFI3;TOTAL STEM NUMBER;TOTAL STEM NUMBER BY TYPE OF DAMAGE;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/total_stem_number_by_type_of_damage-208;URL;1.0;Other (Open);Number of all living and dead trees and shrubs  starting at 12 cm dbh where a particular type of damage (including no damage, dead or lying) was observed. One tree may have more than one type of damage, which means it may contribute to the total number of stems for several different types of damage.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "36f343bb-9a7e-5044-93d2-f2704007865f",
-    "notes": [
-        "Number of all living and dead trees and shrubs  starting at 12 cm dbh where a particular type of damage (including no damage, dead or lying) was observed. One tree may have more than one type of damage, which means it may contribute to the total number of stems for several different types of damage.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:861d05f9-6125-4540-b4d6-d454c595d70e"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ALTITUDE M CLASS"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "DAMAGE TREE"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "NFI"
-        },
-        {
-            "name": "NFIB"
-        },
-        {
-            "name": "PRODUCTION REGION"
-        }
-    ],
-    "title": [
-        "Total stem number by type of damage"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/3acedc92-83ac-5d32-85ff-cd724037de5d.json b/oaitestdata/envidat-datacite/SET_1/json/3acedc92-83ac-5d32-85ff-cd724037de5d.json
deleted file mode 100644
index 9f83c46b..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/3acedc92-83ac-5d32-85ff-cd724037de5d.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Marcia Phillips"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.13093/permos-2016-01",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL",
-        "PDF"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:0c21a308-e1c8-488b-a410-57f31577f80d",
-    "MetadataAccess": [
-        "oai:envidat.ch:0c21a308-e1c8-488b-a410-57f31577f80d"
-    ],
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "PERMOS"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/flu-a-bh"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Non-Commercial)"
-    ],
-    "SpatialCoverage": "(47N,10E)",
-    "TempCoverageBegin": 63169066799,
-    "TempCoverageEnd": 63169066799,
-    "TemporalCoverage": " point in time : 2002-10-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2002-10-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2002-10-01T11:59:59Z",
-    "author": [
-        "Marcia Phillips"
-    ],
-    "fulltext": "oai:envidat.ch:0c21a308-e1c8-488b-a410-57f31577f80d;2017-08-11T14:08:33Z;10.13093/permos-2016-01;Marcia Phillips;Swiss Federal Research Institute WSL;Processed permafrost borehole data (2394 m asl), Fluelapass A, Switzerland;2016;PERMOS;BOREHOLE;PERMAFROST;Marcia Phillips;Swiss Federal Research Institute WSL;2002-10-01;en;Dataset;https://www.envidat.ch/dataset/flu-a-bh;URL;PDF;1.0;Other (Non-Commercial);Processed ground temperature measurements at the Fluelapass permafrost borehole A (FLU_0102) in canton Graubunden, Switzerland. The borehole is located at 2394 m asl on a moderate (26\u00b0) North-east slope (45\u00b0). The surface material is talus and borehole depth is 23 m. Thermistors used YSI 44006. Year of drilling 2002. This borehole is part of the Swiss Permafrost network, PERMOS (www.permos.ch). Contact phillips@slf.ch for details of processing applied.;46.7479 9.9451;Fluela Pass, Graubunden, Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "3acedc92-83ac-5d32-85ff-cd724037de5d",
-    "notes": [
-        "Processed ground temperature measurements at the Fluelapass permafrost borehole A (FLU_0102) in canton Graubunden, Switzerland. The borehole is located at 2394 m asl on a moderate (26\u00b0) North-east slope (45\u00b0). The surface material is talus and borehole depth is 23 m. Thermistors used YSI 44006. Year of drilling 2002. This borehole is part of the Swiss Permafrost network, PERMOS (www.permos.ch). Contact phillips@slf.ch for details of processing applied."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:0c21a308-e1c8-488b-a410-57f31577f80d"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[9.9451,46.7479],[9.9451,46.7479],[9.9451,46.7479],[9.9451,46.7479],[9.9451,46.7479]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "BOREHOLE"
-        },
-        {
-            "name": "PERMAFROST"
-        }
-    ],
-    "title": [
-        "Processed permafrost borehole data (2394 m asl), Fluelapass A, Switzerland"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/3af0bdab-341b-5a8e-8698-ea6887ab8e28.json b/oaitestdata/envidat-datacite/SET_1/json/3af0bdab-341b-5a8e-8698-ea6887ab8e28.json
deleted file mode 100644
index 05745886..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/3af0bdab-341b-5a8e-8698-ea6887ab8e28.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:b564ae5d-6c8e-4115-a4c6-1ea6fe54157c",
-    "MetadataAccess": [
-        "oai:envidat.ch:b564ae5d-6c8e-4115-a4c6-1ea6fe54157c"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/volume_of_bole_wood_hg_2010-211"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:b564ae5d-6c8e-4115-a4c6-1ea6fe54157c;2018-12-09T00:33:34Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Volume of bole wood (HG 2010);2014;Swiss Federal Research Institute WSL;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;BIOGEOGRAPHICAL REGION;CANTON;CONIFERS-BROADLEAVES;ECONOMIC REGION;GRID NFI4 2009-2013;MAIN TREE SPECIES;NFI4B;PRODUCTION REGION;PROTECTION FOREST REGION;TIMBER ASSORTMENT CLASSES HG 2010;TREE SPECIES 5 CLASSES;TYPE OF ASSORTMENT;VOLUME OF BOLE WOOD HG 2010;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/volume_of_bole_wood_hg_2010-211;URL;1.0;Other (Open);Wood volume of the trunk without bark or branches at least 7 cm in diameter (limit for coarse wool) of all trees and shrubs  starting at 12 cm dbh, based on the stem-form function according to Kaufmann (2001). The definition of the assortment is based on the 2010 edition of the Trading Practices (Handelsgebr\u00e4uchen Ausgabe 2010).\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "3af0bdab-341b-5a8e-8698-ea6887ab8e28",
-    "notes": [
-        "Wood volume of the trunk without bark or branches at least 7 cm in diameter (limit for coarse wool) of all trees and shrubs  starting at 12 cm dbh, based on the stem-form function according to Kaufmann (2001). The definition of the assortment is based on the 2010 edition of the Trading Practices (Handelsgebr\u00e4uchen Ausgabe 2010).\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:b564ae5d-6c8e-4115-a4c6-1ea6fe54157c"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "MAIN TREE SPECIES"
-        },
-        {
-            "name": "NFIB"
-        },
-        {
-            "name": "PRODUCTION REGION"
-        },
-        {
-            "name": "PROTECTION FOREST REGION"
-        }
-    ],
-    "title": [
-        "Volume of bole wood (HG 2010)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/3b59004c-b1c0-5f74-8409-75ef82ba44be.json b/oaitestdata/envidat-datacite/SET_1/json/3b59004c-b1c0-5f74-8409-75ef82ba44be.json
deleted file mode 100644
index 0a657ae5..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/3b59004c-b1c0-5f74-8409-75ef82ba44be.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:aa2c10c7-b355-4c84-9012-bd536291c67b",
-    "MetadataAccess": [
-        "oai:envidat.ch:aa2c10c7-b355-4c84-9012-bd536291c67b"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/mortality-16"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:aa2c10c7-b355-4c84-9012-bd536291c67b;2018-12-09T00:32:36Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Mortality;2014;Swiss Federal Research Institute WSL;14 X 14 KM GRID;56 CLASSES;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;ALTITUDE 400 M CLASSES;ALTITUDINAL VEGETATION ZONE;BIOGEOGRAPHICAL REGION;CONIFERS-BROADLEAVES;ECONOMIC REGION;GRID NFI4 2009-2013;LOWER-HIGHER ALTITUDINAL ZONES;MAIN TREE SPECIES;MORTALITY;NFI2-NFI3;NFI3-NFI4B;OWNERSHIP;POTENTIAL COST FOR TIMBER HARVESTING;PRODUCTION REGION;PROTECTION FOREST REGION;SITE QUALITY;TREE SPECIES WOODY SPECIES;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/mortality-16;URL;1.0;Other (Open);Volume of stemwood with bark of all trees and shrubs  starting at 12 cm dbh that died or disappeared between two inventories and that were not harvested. The correction for bias with the sample Tarif trees may be so drastic that it results in negative values with small numbers of trees.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "3b59004c-b1c0-5f74-8409-75ef82ba44be",
-    "notes": [
-        "Volume of stemwood with bark of all trees and shrubs  starting at 12 cm dbh that died or disappeared between two inventories and that were not harvested. The correction for bias with the sample Tarif trees may be so drastic that it results in negative values with small numbers of trees.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:aa2c10c7-b355-4c84-9012-bd536291c67b"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "X KM GRID"
-        },
-        {
-            "name": "CLASSES"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ALTITUDE M CLASSES"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        }
-    ],
-    "title": [
-        "Mortality"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/3b7a6421-c71c-5371-a9d0-5752e1d5a0d3.json b/oaitestdata/envidat-datacite/SET_1/json/3b7a6421-c71c-5371-a9d0-5752e1d5a0d3.json
deleted file mode 100644
index b6afe254..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/3b7a6421-c71c-5371-a9d0-5752e1d5a0d3.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:85b494ba-63d3-401c-9fb4-0a46a4a2e375",
-    "MetadataAccess": [
-        "oai:envidat.ch:85b494ba-63d3-401c-9fb4-0a46a4a2e375"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/stem_number-73"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:85b494ba-63d3-401c-9fb4-0a46a4a2e375;2018-12-09T00:33:11Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Stem number;2014;Swiss Federal Research Institute WSL;14 X 14 KM GRID;56 CLASSES;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;ALTITUDE 200 M CLASS;ALTITUDINAL VEGETATION ZONE;BIOGEOGRAPHICAL REGION;CANTON;CONIFERS-BROADLEAVES;DIAMETER CLASS SIZE 10 CM;DIAMETER CLASSES;ECONOMIC REGION;EXOTIC SPECIES NEOPHYTES;FOREST DISTRICT AS OF 2013;FOREST TYPE 12 CLASSES;FOREST TYPE AND STAGE OF DEVELOPMENT;GRID NFI4 2009-2013;IMPORTANT EXOTIC SPECIES NEOPHYTES;LOWER-HIGHER ALTITUDINAL ZONES;MAIN TREE SPECIES;NFI1;NFI2;NFI3;NFI4B;NUMBER OF DAMAGES;OWNERSHIP;OWNERSHIP NFI4;PRODUCTION REGION;PROTECTION FOREST REGION;STAGE OF STAND DEVELOPMENT;STEM NUMBER;TERRESTRIAL GRID NFI1;TERRESTRIAL GRID NFI2;TERRESTRIAL GRID NFI3;TREE SPECIES 5 CLASSES;TREE SPECIES WOODY SPECIES;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/stem_number-73;URL;1.0;Other (Open);Number of stems of living trees and shrubs (standing and lying)  starting at 12 cm dbh.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "3b7a6421-c71c-5371-a9d0-5752e1d5a0d3",
-    "notes": [
-        "Number of stems of living trees and shrubs (standing and lying)  starting at 12 cm dbh.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:85b494ba-63d3-401c-9fb4-0a46a4a2e375"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "X KM GRID"
-        },
-        {
-            "name": "CLASSES"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ALTITUDE M CLASS"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        }
-    ],
-    "title": [
-        "Stem number"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/3d95b891-c871-5471-a18b-2f856e555f84.json b/oaitestdata/envidat-datacite/SET_1/json/3d95b891-c871-5471-a18b-2f856e555f84.json
deleted file mode 100644
index 275d5a42..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/3d95b891-c871-5471-a18b-2f856e555f84.json
+++ /dev/null
@@ -1,89 +0,0 @@
-{
-    "Contact": [
-        "Tristan Brauchli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/envidat.24",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "ZIP"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:f1d3d6da-2e59-4ee3-92fe-fc4add117f61",
-    "MetadataAccess": [
-        "oai:envidat.ch:f1d3d6da-2e59-4ee3-92fe-fc4add117f61"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Water Resources Research"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/10-16904-envidat-24"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "License not specified"
-    ],
-    "SpatialCoverage": "(47N-47N,10E-10E)",
-    "TempCoverageBegin": 63648244799,
-    "TempCoverageEnd": 63648244799,
-    "TemporalCoverage": " point in time : 2017-12-07T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2017-12-07T11:59:59Z",
-    "TemporalCoverage:EndDate": "2017-12-07T11:59:59Z",
-    "author": [
-        "Tristan Brauchli"
-    ],
-    "fulltext": "oai:envidat.ch:f1d3d6da-2e59-4ee3-92fe-fc4add117f61;2018-12-09T00:23:47Z;10.16904/envidat.24;Tristan Brauchli;0000-0003-3332-4995;EPFL;Influence of slope-scale snowmelt on catchment response simulated with the Alpine3D model;The files contain Alpine3D output used to generate the graphs in the manuscript;2017;Water Resources Research;COMPLEX TOPOGRAPHY;HYDROLOGICAL RESPONSE;SNOW MODELING;SNOWMELT;SPATIAL VARIABILITY;Tristan Brauchli;0000-0003-3332-4995;EPFL;2017-12-07;en;Dataset;https://www.envidat.ch/dataset/10-16904-envidat-24;104953493 bytes;ZIP;1.0;License not specified;# Abstract\nSnow and hydrological modeling in alpine environments remains a challenge because of the complexity of the processes complexity affecting the mass and energy balance. This study examines the influence of snowmelt on the hydrological response of a high-alpine catchment of 43.2 km2 in the Swiss Alps during the water year 2014-2015. Based on recent advances in Alpine3D, we examine how modeled snow distributions, and modeled liquid water transport within the snowpack influence runoff dynamics. By combining these results with multi-scale field data (snow lysimeter data, distributed snow depths and streamflow), we demonstrate the added value of a more realistic representation of snow distribution at the onset of melt season. At the site scale, snowpack runoff is well simulated when the snowpack mass balance errors are corrected (R2 = 0.95 vs. R2 = 0.61). At the sub-basin scale, a more heterogeneous snowpack leads to a more rapid runoff pulse originated in the shallower areas while an extended melting period (by more than a month) is caused by slower snowmelt from deeper areas. This result is a marked improvement over results obtained using a less heterogeneous snow distribution (i.e., traditional precipitation interpolation method). Catchment hydrological response is also improved by the more realistic representation of snowpack heterogeneity (Nash coefficient of 0.85 vs. 0.74), even though the calibration process smoothens out the differences. \nThe added value of a more complex liquid water transport scheme is obvious at the site scale but decreases at the sub-basin and basin scales. Our results highlight not only the importance but also the difficulty of getting a realistic snowpack distribution even in a well-instrumented area and present a model validation from multi-scale experimental datasets.;46.6722920457 9.81971740723 46.8012345356 9.98931884766",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "3d95b891-c871-5471-a18b-2f856e555f84",
-    "notes": [
-        "# Abstract\nSnow and hydrological modeling in alpine environments remains a challenge because of the complexity of the processes complexity affecting the mass and energy balance. This study examines the influence of snowmelt on the hydrological response of a high-alpine catchment of 43.2 km2 in the Swiss Alps during the water year 2014-2015. Based on recent advances in Alpine3D, we examine how modeled snow distributions, and modeled liquid water transport within the snowpack influence runoff dynamics. By combining these results with multi-scale field data (snow lysimeter data, distributed snow depths and streamflow), we demonstrate the added value of a more realistic representation of snow distribution at the onset of melt season. At the site scale, snowpack runoff is well simulated when the snowpack mass balance errors are corrected (R2 = 0.95 vs. R2 = 0.61). At the sub-basin scale, a more heterogeneous snowpack leads to a more rapid runoff pulse originated in the shallower areas while an extended melting period (by more than a month) is caused by slower snowmelt from deeper areas. This result is a marked improvement over results obtained using a less heterogeneous snow distribution (i.e., traditional precipitation interpolation method). Catchment hydrological response is also improved by the more realistic representation of snowpack heterogeneity (Nash coefficient of 0.85 vs. 0.74), even though the calibration process smoothens out the differences. \nThe added value of a more complex liquid water transport scheme is obvious at the site scale but decreases at the sub-basin and basin scales. Our results highlight not only the importance but also the difficulty of getting a realistic snowpack distribution even in a well-instrumented area and present a model validation from multi-scale experimental datasets."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:f1d3d6da-2e59-4ee3-92fe-fc4add117f61"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[9.81971740723,46.6722920457],[9.81971740723,46.8012345356],[9.98931884766,46.8012345356],[9.98931884766,46.6722920457],[9.81971740723,46.6722920457]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "COMPLEX TOPOGRAPHY"
-        },
-        {
-            "name": "HYDROLOGICAL RESPONSE"
-        },
-        {
-            "name": "SNOW MODELING"
-        },
-        {
-            "name": "SNOWMELT"
-        },
-        {
-            "name": "SPATIAL VARIABILITY"
-        }
-    ],
-    "title": [
-        "Influence of slope-scale snowmelt on catchment response simulated with the Alpine3D model",
-        "The files contain Alpine3D output used to generate the graphs in the manuscript"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/3dea0629-16cb-55b4-8bdb-30d2a57a7fb9.json b/oaitestdata/envidat-datacite/SET_1/json/3dea0629-16cb-55b4-8bdb-30d2a57a7fb9.json
deleted file mode 100644
index b9797a6a..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/3dea0629-16cb-55b4-8bdb-30d2a57a7fb9.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Manfred St\u00e4hli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/5",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "XLSX",
-        "XLSM"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:5333838f-5da6-4574-8d28-ce1794c19631",
-    "MetadataAccess": [
-        "oai:envidat.ch:5333838f-5da6-4574-8d28-ce1794c19631"
-    ],
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Competence Center Environment and Sustainability, ETH Zurich"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/10-16904-5"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Attribution)"
-    ],
-    "SpatialCoverage": "(47N,9 E)",
-    "TempCoverageBegin": 63424209599,
-    "TempCoverageEnd": 63424209599,
-    "TemporalCoverage": " point in time : 2010-11-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2010-11-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2010-11-01T11:59:59Z",
-    "author": [
-        "Seraina Kauer",
-        "Manfred St\u00e4hli",
-        "Philipp Schneider",
-        "Cornelia Br\u00f6nnimann"
-    ],
-    "fulltext": "oai:envidat.ch:5333838f-5da6-4574-8d28-ce1794c19631;2018-12-09T00:24:10Z;10.16904/5;Cornelia Br\u00f6nnimann;WSL;Seraina Kauer;University of Z\u00fcrich, Department of Geography;Philipp Schneider;University of Z\u00fcrich, Department of Geography;Manfred St\u00e4hli;Swiss Federal Research Institute WSL;TRAMM project - experimental hydrological and hydrogeological dataset of a landslide prone hillslope. Rufiberg, Switzerland;2015;Competence Center Environment and Sustainability, ETH Zurich;LANDSLIDES;SOIL MOISTURE WATER CONTENT;WATER TABLE;Manfred St\u00e4hli;WSL;2010-11-01;en;Dataset;https://www.envidat.ch/dataset/10-16904-5;7866407 bytes;2033894 bytes;5593516 bytes;939397 bytes;XLSM;XLSX;1;Other (Attribution);Rufiberg is a pre-alpine meadow site in Switzerland where shallow landslides have been observed after past intense rain storms. In order to assess the triggering mechanisms of these landslides, a comprehensive investigation was conducted within the project TRAMM from Nov 2009 to Oct 2012. It included meteorological observations, soil moisture measurements, bedrock groundwater measurements. The Rufiberg is located at the NW side of the Gnipen to the north of the village Arth-Goldau in the Canton of Schwyz. In the summer months, the site is used for pasturing. Usually, from December to March a snow cover is present at the Rufiberg. The site is at an altitude between 1080 \u2013 1180 m asl, is ENE oriented, and has an average slope of 30 -35\u00b0. The Subalpine Molasse in the region is inclined with 30 - 35\u00b0 to SE. In the area of the field site, beds of conglomerate with several m of thickness alter with beds of sandstone and marlstone. A ca. 2 \u2013 5 m thick eluvium/colluvium layer composed of silty and sandy clay covers the bedrock. This site has been chosen because on one hand, during heavy rainfall events, e.g. autumn 2005, numerous landslides occur in the region of the Gnipen and the Rufiberg. On the other hand, the Rufiberg is very appropriate for experiments due its location away from infrastructures and due to its accessibility. The goal of the investigation was to understand the hydrology and hydrogeology of the slope with regard to shallow landslides. \n\nMore information: Br\u00f6nnimann, C., St\u00e4hli, M., Schneider, P., Seward, L. and Springman, S.M. 2013. Bedrock exfiltration as a triggering mechanism for shallow landslides. Water Resources Research, 49 (9): 5155\u20135167. DOI: 10.1002/wrcr.20386.;47.0889606 8.5544251;Rufiberg, Switzerland (47.0889606\u00b0 N, 8.5544251\u00b0 E)",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "3dea0629-16cb-55b4-8bdb-30d2a57a7fb9",
-    "notes": [
-        "Rufiberg is a pre-alpine meadow site in Switzerland where shallow landslides have been observed after past intense rain storms. In order to assess the triggering mechanisms of these landslides, a comprehensive investigation was conducted within the project TRAMM from Nov 2009 to Oct 2012. It included meteorological observations, soil moisture measurements, bedrock groundwater measurements. The Rufiberg is located at the NW side of the Gnipen to the north of the village Arth-Goldau in the Canton of Schwyz. In the summer months, the site is used for pasturing. Usually, from December to March a snow cover is present at the Rufiberg. The site is at an altitude between 1080 \u2013 1180 m asl, is ENE oriented, and has an average slope of 30 -35\u00b0. The Subalpine Molasse in the region is inclined with 30 - 35\u00b0 to SE. In the area of the field site, beds of conglomerate with several m of thickness alter with beds of sandstone and marlstone. A ca. 2 \u2013 5 m thick eluvium/colluvium layer composed of silty and sandy clay covers the bedrock. This site has been chosen because on one hand, during heavy rainfall events, e.g. autumn 2005, numerous landslides occur in the region of the Gnipen and the Rufiberg. On the other hand, the Rufiberg is very appropriate for experiments due its location away from infrastructures and due to its accessibility. The goal of the investigation was to understand the hydrology and hydrogeology of the slope with regard to shallow landslides. \n\nMore information: Br\u00f6nnimann, C., St\u00e4hli, M., Schneider, P., Seward, L. and Springman, S.M. 2013. Bedrock exfiltration as a triggering mechanism for shallow landslides. Water Resources Research, 49 (9): 5155\u20135167. DOI: 10.1002/wrcr.20386."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:5333838f-5da6-4574-8d28-ce1794c19631"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[8.5544251,47.0889606],[8.5544251,47.0889606],[8.5544251,47.0889606],[8.5544251,47.0889606],[8.5544251,47.0889606]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "LANDSLIDES"
-        },
-        {
-            "name": "SOIL MOISTURE WATER CONTENT"
-        },
-        {
-            "name": "WATER TABLE"
-        }
-    ],
-    "title": [
-        "TRAMM project - experimental hydrological and hydrogeological dataset of a landslide prone hillslope. Rufiberg, Switzerland"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/3eb8a197-2c53-5948-b808-a7148529013d.json b/oaitestdata/envidat-datacite/SET_1/json/3eb8a197-2c53-5948-b808-a7148529013d.json
deleted file mode 100644
index febda0d1..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/3eb8a197-2c53-5948-b808-a7148529013d.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:df9faab9-037f-4915-8604-2f8b1b791957",
-    "MetadataAccess": [
-        "oai:envidat.ch:df9faab9-037f-4915-8604-2f8b1b791957"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/biomass_of_standing_dead_trees-69"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:df9faab9-037f-4915-8604-2f8b1b791957;2018-12-09T00:31:35Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Biomass of standing dead trees;2014;Swiss Federal Research Institute WSL;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;BIOGEOGRAPHICAL REGION;BIOMASS OF STANDING DEAD TREES;CANTON;CONIFERS-BROADLEAVES;ECONOMIC REGION;GRID NFI4 2009-2013;NFI3;NFI4B;PRODUCTION REGION;PROTECTION FOREST REGION;TERRESTRIAL GRID NFI3;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/biomass_of_standing_dead_trees-69;URL;1.0;Other (Open);Dry weight (mass) of dead, standing trees and shrubs  starting at 12 cm dbh. This consists of the tree parts: roots, stemwood and also, depending on the degree of decomposition, the branch coarse wood.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "3eb8a197-2c53-5948-b808-a7148529013d",
-    "notes": [
-        "Dry weight (mass) of dead, standing trees and shrubs  starting at 12 cm dbh. This consists of the tree parts: roots, stemwood and also, depending on the degree of decomposition, the branch coarse wood.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:df9faab9-037f-4915-8604-2f8b1b791957"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "BIOMASS STANDING DEAD TREES"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "NFI"
-        },
-        {
-            "name": "NFIB"
-        },
-        {
-            "name": "PRODUCTION REGION"
-        },
-        {
-            "name": "PROTECTION FOREST REGION"
-        }
-    ],
-    "title": [
-        "Biomass of standing dead trees"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/3f8750b4-7ef0-5dc6-917c-88f88ede5471.json b/oaitestdata/envidat-datacite/SET_1/json/3f8750b4-7ef0-5dc6-917c-88f88ede5471.json
deleted file mode 100644
index 8b7b2fe6..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/3f8750b4-7ef0-5dc6-917c-88f88ede5471.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:871681c0-61cb-49d3-84ae-8fabfa6b2b2e",
-    "MetadataAccess": [
-        "oai:envidat.ch:871681c0-61cb-49d3-84ae-8fabfa6b2b2e"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/number_of_forest_edges-124"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:871681c0-61cb-49d3-84ae-8fabfa6b2b2e;2018-12-09T00:32:43Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Number of forest edges;2014;Swiss Federal Research Institute WSL;ALTITUDINAL VEGETATION ZONE;BIOGEOGRAPHICAL REGION;BOUNDARY OF FOREST EDGE;DENSITY OF FOREST EDGE;DIVERSITY OF WOODY SPECIES AT THE FOREST EDGE;ECONOMIC REGION;ECOTONE VALUE;FOREST EDGE OF ZONES FOOTHILL-SUBMONTANE-MONTANE;FOREST EDGE OF ZONES FOOTHILL-SUBMONTANE-MONTANE NFI2-NFI3-NFI4;FOREST EDGE OF ZONES FOOTHILL-SUBMONTANE-MONTANE NFI3-NFI4;GRID NFI4 2009-2013;NFI2;NFI3;NFI4B;NUMBER OF FOREST EDGES;NUMBER OF WOODY SPECIES AT THE FOREST EDGE;PRODUCTION REGION;PROTECTION FOREST REGION;SHAPE OF FOREST EDGE;STATE OF FOREST EDGE;STRUCTURAL DIVERSITY OF THE FOREST EDGE;STRUCTURE OF FOREST EDGE;SURROUNDINGS OF FOREST EDGE;TERRESTRIAL GRID NFI2;TERRESTRIAL GRID NFI3;WIDTH OF HERBACEOUS FRINGE;WIDTH OF SHELTER BELT;WIDTH OF SHRUB BELT;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/number_of_forest_edges-124;URL;1.0;Other (Open);Number of forest edges according to the NFI definition.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "3f8750b4-7ef0-5dc6-917c-88f88ede5471",
-    "notes": [
-        "Number of forest edges according to the NFI definition.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:871681c0-61cb-49d3-84ae-8fabfa6b2b2e"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "BOUNDARY FOREST EDGE"
-        },
-        {
-            "name": "DENSITY FOREST EDGE"
-        },
-        {
-            "name": "DIVERSITY WOODY SPECIES FOREST EDGE"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "ECOTONE VALUE"
-        },
-        {
-            "name": "FOREST EDGE ZONES FOOTHILL-SUBMONTANE-MONTANE"
-        },
-        {
-            "name": "FOREST EDGE ZONES FOOTHILL-SUBMONTANE-MONTANE NFI-NFI-NFI"
-        },
-        {
-            "name": "FOREST EDGE ZONES FOOTHILL-SUBMONTANE-MONTANE NFI-NFI"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "NFI"
-        }
-    ],
-    "title": [
-        "Number of forest edges"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/3fa79bab-c9bf-55dd-8108-f78978b0926f.json b/oaitestdata/envidat-datacite/SET_1/json/3fa79bab-c9bf-55dd-8108-f78978b0926f.json
deleted file mode 100644
index 24a9ad5e..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/3fa79bab-c9bf-55dd-8108-f78978b0926f.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Nander Wever"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/16",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "text/x-sh",
-        "ZIP"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:a9264e9f-ea9b-4c89-b471-464efb891826",
-    "MetadataAccess": [
-        "oai:envidat.ch:a9264e9f-ea9b-4c89-b471-464efb891826"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avalanche Research SLF"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/snowmip"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N,10E)",
-    "TempCoverageBegin": 62977172399,
-    "TempCoverageEnd": 62977172399,
-    "TemporalCoverage": " point in time : 1996-09-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1996-09-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1996-09-01T11:59:59Z",
-    "author": [
-        "WSL Institute for Snow and Avalanche Research SLF"
-    ],
-    "fulltext": "oai:envidat.ch:a9264e9f-ea9b-4c89-b471-464efb891826;2018-12-06T17:36:57Z;10.16904/16;WSL Institute for Snow and Avalanche Research SLF;SLF;Weissfluhjoch dataset for ESM-SnowMIP;2017;WSL Institute for Snow and Avalanche Research SLF;SNOW MODELS;Nander Wever;WSL Institute for Snow and Avalanche Research SLF;1996-09-01;en;https://www.envidat.ch/dataset/snowmip;11596605 bytes;900 bytes;1410 bytes;4688961 bytes;text/x-sh;ZIP;1.0;Open Data Commons Open Database License (ODbL);This Weissfluhjoch dataset is a processed version  of the Weissfluhjoch dataset version 6 from http://www.envidat.ch/dataset/10-16904-1. This dataset was specially created for the ESM-SnowMIP project. Here it is documented how this dataset has been created.;46.829598 9.809568;Weissfluhjoch (46.829598 9.809568)",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "3fa79bab-c9bf-55dd-8108-f78978b0926f",
-    "notes": [
-        "This Weissfluhjoch dataset is a processed version  of the Weissfluhjoch dataset version 6 from http://www.envidat.ch/dataset/10-16904-1. This dataset was specially created for the ESM-SnowMIP project. Here it is documented how this dataset has been created."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:a9264e9f-ea9b-4c89-b471-464efb891826"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[9.809568,46.829598],[9.809568,46.829598],[9.809568,46.829598],[9.809568,46.829598],[9.809568,46.829598]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "SNOW MODELS"
-        }
-    ],
-    "title": [
-        "Weissfluhjoch dataset for ESM-SnowMIP"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/44036157-4c4c-5860-bc39-a4a8d26733b0.json b/oaitestdata/envidat-datacite/SET_1/json/44036157-4c4c-5860-bc39-a4a8d26733b0.json
deleted file mode 100644
index e44fc066..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/44036157-4c4c-5860-bc39-a4a8d26733b0.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Marcia Phillips"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.13093/permos-2016-01",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL",
-        "PDF"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:0dd82305-a330-4e5b-975f-54f3b6fe8a81",
-    "MetadataAccess": [
-        "oai:envidat.ch:0dd82305-a330-4e5b-975f-54f3b6fe8a81"
-    ],
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "PERMOS"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/rit1"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(46N,8 E)",
-    "TempCoverageBegin": 63638045999,
-    "TempCoverageEnd": 63638045999,
-    "TemporalCoverage": " point in time : 2017-08-11T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2017-08-11T11:59:59Z",
-    "TemporalCoverage:EndDate": "2017-08-11T11:59:59Z",
-    "author": [
-        "Marcia Phillips"
-    ],
-    "fulltext": "oai:envidat.ch:0dd82305-a330-4e5b-975f-54f3b6fe8a81;2018-12-09T00:32:56Z;10.13093/permos-2016-01;Marcia Phillips;Swiss Federal Research Institute WSL;RIT1: Processed permafrost borehole data (2690  m asl), Ritigraben, Switzerland;2016;PERMOS;BOREHOLE;PERMAFROST;Marcia Phillips;WSL;2017-08-11;en;Dataset;https://www.envidat.ch/dataset/rit1;URL;PDF;1.0;Open Data Commons Open Database License (ODbL);Processed ground temperature measurements at the Ritigraben permafrost borehole (RIT_0102) in canton Valais, Switzerland. The borehole is located at 2690 m asl on a flat site. The surface material is coarse blocks and borehole depth is 30 m. Thermistors used YSI 44006. Year of drilling 2002. This borehole is part of the Swiss Permafrost network, PERMOS (www.permos.ch). Contact phillips@slf.ch for details of processing applied.;46.17467 7.84982;Ritigraben, Canton Valais, Switzerland.",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "44036157-4c4c-5860-bc39-a4a8d26733b0",
-    "notes": [
-        "Processed ground temperature measurements at the Ritigraben permafrost borehole (RIT_0102) in canton Valais, Switzerland. The borehole is located at 2690 m asl on a flat site. The surface material is coarse blocks and borehole depth is 30 m. Thermistors used YSI 44006. Year of drilling 2002. This borehole is part of the Swiss Permafrost network, PERMOS (www.permos.ch). Contact phillips@slf.ch for details of processing applied."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:0dd82305-a330-4e5b-975f-54f3b6fe8a81"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[7.84982,46.17467],[7.84982,46.17467],[7.84982,46.17467],[7.84982,46.17467],[7.84982,46.17467]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "BOREHOLE"
-        },
-        {
-            "name": "PERMAFROST"
-        }
-    ],
-    "title": [
-        "RIT1: Processed permafrost borehole data (2690  m asl), Ritigraben, Switzerland"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/443c9632-b8c7-5b50-a31f-439e0d14b373.json b/oaitestdata/envidat-datacite/SET_1/json/443c9632-b8c7-5b50-a31f-439e0d14b373.json
deleted file mode 100644
index 893fbaf0..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/443c9632-b8c7-5b50-a31f-439e0d14b373.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Peter Bebi"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/envidat.45",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "DOC",
-        "GDB",
-        "JPEG"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:b72cc62e-cf31-4f4c-b89e-eba90f27ac50",
-    "MetadataAccess": [
-        "oai:envidat.ch:b72cc62e-cf31-4f4c-b89e-eba90f27ac50"
-    ],
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/stillberg-reforestation"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N,10E)",
-    "TempCoverageBegin": 62293406399,
-    "TempCoverageEnd": 62293406399,
-    "TemporalCoverage": " point in time : 1975-01-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1975-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1975-01-01T11:59:59Z",
-    "author": [
-        "Peter Bebi"
-    ],
-    "fulltext": "oai:envidat.ch:b72cc62e-cf31-4f4c-b89e-eba90f27ac50;2018-12-09T00:30:59Z;10.16904/envidat.45;Peter Bebi;Swiss Federal Research Institute WSL;Long-term treeline research dataset at Stillberg, Davos;2016;Swiss Federal Research Institute WSL;AFFORESTATION;FORESTY;MOUNTAIN FOREST;TREELINE ECOSYSTEMS;Peter Bebi;WSL Institute for Snow and Avalanche Research SLF;1975-01-01;en;Dataset;https://www.envidat.ch/dataset/stillberg-reforestation;57344 bytes;GDB;JPEG;DOC;1.0;Open Data Commons Open Database License (ODbL);#Background\n\nA history of many centuries of seasonal livestock grazing of alpine pastures has significantly depressed the treeline in many European mountain ranges. Therefore, observations of treeline patterns are more likely to be obscured by historical land use than in regions with less human influence and might not provide relevant information about environmental factors that influence mortality and growth patterns at the natural high-elevation limit of tree existence. To overcome this, we used a large afforestation experiment in the Swiss Alps, \"Stillberg\", to address the following questions:\n\nCan trees survive above the current treeline in the European Alps? Are environmental factors that influence spatial patterns of mortality the same as those that influence height growth? Does the relative importance of these environmental variables change over the first 40 years after planting as seedlings?\n\n#Dataset\nThe 5 ha Stillberg long-term afforestation research area is located near Davos (Central Alps, Switzerland). The bottom of the afforestation is approximately at the current treeline and it covers an altitudinal gradient of more than 150 m (2075 to 2230 m a.s.l.; see picture above). Approximately 92'000 seedlings of three treeline species (Larix decidua, Pinus mugo ssp. uncinata and Pinus cembra) were systematically planted in 1975, and mortality and height growth were closely monitored during the following 40 years.\n\n__Publications__\nBarbeito, I., Dawes, M. A., Rixen, C., Senn, J. and Bebi, P. (2012), Factors driving mortality and growth at treeline: a 30-year experiment of 92\u2009000 conifers. Ecology, 93: 389\u2013401. http://dx.doi.org/10.1890/11-0384.1;46.773573 9.86716;Davos, Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "443c9632-b8c7-5b50-a31f-439e0d14b373",
-    "notes": [
-        "#Background\n\nA history of many centuries of seasonal livestock grazing of alpine pastures has significantly depressed the treeline in many European mountain ranges. Therefore, observations of treeline patterns are more likely to be obscured by historical land use than in regions with less human influence and might not provide relevant information about environmental factors that influence mortality and growth patterns at the natural high-elevation limit of tree existence. To overcome this, we used a large afforestation experiment in the Swiss Alps, \"Stillberg\", to address the following questions:\n\nCan trees survive above the current treeline in the European Alps? Are environmental factors that influence spatial patterns of mortality the same as those that influence height growth? Does the relative importance of these environmental variables change over the first 40 years after planting as seedlings?\n\n#Dataset\nThe 5 ha Stillberg long-term afforestation research area is located near Davos (Central Alps, Switzerland). The bottom of the afforestation is approximately at the current treeline and it covers an altitudinal gradient of more than 150 m (2075 to 2230 m a.s.l.; see picture above). Approximately 92'000 seedlings of three treeline species (Larix decidua, Pinus mugo ssp. uncinata and Pinus cembra) were systematically planted in 1975, and mortality and height growth were closely monitored during the following 40 years.\n\n__Publications__\nBarbeito, I., Dawes, M. A., Rixen, C., Senn, J. and Bebi, P. (2012), Factors driving mortality and growth at treeline: a 30-year experiment of 92\u2009000 conifers. Ecology, 93: 389\u2013401. http://dx.doi.org/10.1890/11-0384.1"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:b72cc62e-cf31-4f4c-b89e-eba90f27ac50"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[9.86716,46.773573],[9.86716,46.773573],[9.86716,46.773573],[9.86716,46.773573],[9.86716,46.773573]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "AFFORESTATION"
-        },
-        {
-            "name": "FORESTY"
-        },
-        {
-            "name": "MOUNTAIN FOREST"
-        },
-        {
-            "name": "TREELINE ECOSYSTEMS"
-        }
-    ],
-    "title": [
-        "Long-term treeline research dataset at Stillberg, Davos"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/4450c4d1-bf1a-5de4-9861-7ba5b8590d0a.json b/oaitestdata/envidat-datacite/SET_1/json/4450c4d1-bf1a-5de4-9861-7ba5b8590d0a.json
deleted file mode 100644
index dc3c5060..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/4450c4d1-bf1a-5de4-9861-7ba5b8590d0a.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:536fcebc-e66d-480c-9dd2-fda643dfac3d",
-    "MetadataAccess": [
-        "oai:envidat.ch:536fcebc-e66d-480c-9dd2-fda643dfac3d"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/total_stem_number_nfi1-243"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:536fcebc-e66d-480c-9dd2-fda643dfac3d;2018-12-09T00:33:25Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Total stem number NFI1;2014;Swiss Federal Research Institute WSL;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ALTITUDINAL VEGETATION ZONE;ALTITUDINAL VEGETATION ZONE 3 CLASSES;BIOGEOGRAPHICAL REGION;CANTON;CONIFERS-BROADLEAVES;DIAMETER CLASS SIZE 10 CM;ECONOMIC REGION;FOREST DISTRICT AS OF 2013;GIANTS;GRID NFI4 2009-2013;LOWER-HIGHER ALTITUDINAL ZONES;MAIN TREE SPECIES;NFI1;OWNERSHIP;PRIMARY FOREST FUNCTION NFI4 NATURE PROTECTION;PRODUCTION REGION;PROTECTION FOREST REGION;TERRESTRIAL GRID NFI1;TOTAL STEM NUMBER NFI1;TREE SPECIES 5 CLASSES;TREE STATE ALIVE-DEAD;TREE STATUS;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/total_stem_number_nfi1-243;URL;1.0;Other (Open);Number of stems of all living and dead trees and shrubs  starting at 12 cm dbh recorded according to the NFI1 method. In NFI1 only those dead trees were recorded whose wood could still be exploited. \n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "4450c4d1-bf1a-5de4-9861-7ba5b8590d0a",
-    "notes": [
-        "Number of stems of all living and dead trees and shrubs  starting at 12 cm dbh recorded according to the NFI1 method. In NFI1 only those dead trees were recorded whose wood could still be exploited. \n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:536fcebc-e66d-480c-9dd2-fda643dfac3d"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE CLASSES"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        },
-        {
-            "name": "DIAMETER CLASS SIZE CM"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "FOREST DISTRICT"
-        },
-        {
-            "name": "GIANTS"
-        },
-        {
-            "name": "GRID NFI -"
-        }
-    ],
-    "title": [
-        "Total stem number NFI1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/477b28dd-0ddd-568e-b155-88dcf31c51a4.json b/oaitestdata/envidat-datacite/SET_1/json/477b28dd-0ddd-568e-b155-88dcf31c51a4.json
deleted file mode 100644
index 68f3f354..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/477b28dd-0ddd-568e-b155-88dcf31c51a4.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Christoph Marty"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/12",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "tar.bz2"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:c8696023-5622-481d-952a-13f88c35e9fe",
-    "MetadataAccess": [
-        "oai:envidat.ch:c8696023-5622-481d-952a-13f88c35e9fe"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avanche Research SLF"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/ch2014"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N,8 E)",
-    "TempCoverageBegin": 63622065599,
-    "TempCoverageEnd": 63622065599,
-    "TemporalCoverage": " point in time : 2017-02-07T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2017-02-07T11:59:59Z",
-    "TemporalCoverage:EndDate": "2017-02-07T11:59:59Z",
-    "author": [
-        "Sebastian Schoegl",
-        "Christoph Marty",
-        "Matthias Bavay",
-        "Michael Lehning"
-    ],
-    "fulltext": "oai:envidat.ch:c8696023-5622-481d-952a-13f88c35e9fe;2018-12-20T07:40:38Z;10.16904/12;Sebastian Schoegl;WSL Institute for Snow and Avanche Research SLF;Christoph Marty;WSL Institute for Snow and Avanche Research SLF;Matthias Bavay;WSL Institute for Snow and Avanche Research SLF;Michael Lehning;WSL Institute for Snow and Avanche Research SLF;Alpine3D simulations of future climate scenarios CH2014;2014;WSL Institute for Snow and Avanche Research SLF;CLIMATE CHANGE;SNOW DEPTH;SNOW WATER EQUIVALENT;Christoph Marty;WSL Institute for Snow and Avanche Research SLF;2017-02-07;en;https://www.envidat.ch/dataset/ch2014;1208440 bytes;360212 bytes;tar.bz2;1;Open Data Commons Open Database License (ODbL);# Overview\n\nThe CH2014-Impacts initiative is a concerted national effort to describe impacts of climate change in Switzerland quantitatively, drawing on the scientific resources available in Switzerland today. The initiative links the recently developed Swiss Climate Change Scenarios CH2011 with an evolving base of quantitative impact models. The use of a common climate data set across disciplines and research groups sets a high standard of consistency and comparability of results. Impact studies explore the wide range of climatic changes in temperature and precipitation projected in CH2011 for the 21st century, which vary with the assumed global level of greenhouse gases, the time horizon, the underlying climate model, and the geographical region within Switzerland. The differences among climate projections are considered using three greenhouse gas scenarios, three future time periods in the 21st century, and three climate uncertainty levels (Figure 1). Impacts are shown with respect to the reference period 1980-2009 of CH2011, and add to any impacts that have already emerged as a result of earlier climate change.\n\n# Experimental Setup\n\nFuture snow cover changes are simulated with the physics-based model Alpine3D (Lehning et al., 2006). It is applied to two regions: The canton of Graub\u00fcnden and the Aare catchment. These domains are modeled with a Digital Elevation Model (DEM) with a resolution of 200 m \u00d7 200 m. This defines the simulation grid that has to be filled with land cover data and downscaled meteorological input data for each cell for the time period of interest at hourly resolution. The reference data set consists of automatic weather station data. All meteorological input parameters are spatially interpolated to the simulation grid. The reference period comprises only thirteen years (1999\u20132012), because the number of available high elevation weather stations for earlier times is not sufficient to achieve unbiased distribution of the observations with elevation. The model uses projected temperature and precipitation changes for all greenhouse gas scenarios (A1B, A2, and RCP3PD) and CH2011 time periods (2035, 2060, and 2085).\n\n# Data\n\nSnow cover changes are projected to be relatively small in the near term (2035) (Figure 5.1 top), in particular at higher elevations above 2000 m asl. As shown by Bavay et al. (2013) the spread in projected snow cover for this period is greater between different climate model chains (Chapter 3) than between the reference period and the model chain exhibiting the most moderate change. In the 2085 period much larger changes with the potential to fundamentally transform the snow dominated alpine area become apparent (Figure 5.1 bottom). These changes include a shortening of the snow season by 5\u20139 weeks for the A1B scenario. This is roughly equivalent to an elevation shift of 400\u2013800 m. The slight increase of winter precipitation and therefore snow fall projected in the CH2011 scenarios (with high associated uncertainty) can no longer compensate for the effect of increasing winter temperatures even at high elevations. In terms of Snow Water Equivalents (SWE), the projected reduction is up to two thirds toward the end of the century (2085). A continuous snow cover will be restricted to a shorter time period and/or to regions at increasingly high elevation. In Bern, for example, the number of days per year with at least 5 cm snow depth will decrease by 90% from now 20 days to only 2 days on average.;46.79959 8.227;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "477b28dd-0ddd-568e-b155-88dcf31c51a4",
-    "notes": [
-        "# Overview\n\nThe CH2014-Impacts initiative is a concerted national effort to describe impacts of climate change in Switzerland quantitatively, drawing on the scientific resources available in Switzerland today. The initiative links the recently developed Swiss Climate Change Scenarios CH2011 with an evolving base of quantitative impact models. The use of a common climate data set across disciplines and research groups sets a high standard of consistency and comparability of results. Impact studies explore the wide range of climatic changes in temperature and precipitation projected in CH2011 for the 21st century, which vary with the assumed global level of greenhouse gases, the time horizon, the underlying climate model, and the geographical region within Switzerland. The differences among climate projections are considered using three greenhouse gas scenarios, three future time periods in the 21st century, and three climate uncertainty levels (Figure 1). Impacts are shown with respect to the reference period 1980-2009 of CH2011, and add to any impacts that have already emerged as a result of earlier climate change.\n\n# Experimental Setup\n\nFuture snow cover changes are simulated with the physics-based model Alpine3D (Lehning et al., 2006). It is applied to two regions: The canton of Graub\u00fcnden and the Aare catchment. These domains are modeled with a Digital Elevation Model (DEM) with a resolution of 200 m \u00d7 200 m. This defines the simulation grid that has to be filled with land cover data and downscaled meteorological input data for each cell for the time period of interest at hourly resolution. The reference data set consists of automatic weather station data. All meteorological input parameters are spatially interpolated to the simulation grid. The reference period comprises only thirteen years (1999\u20132012), because the number of available high elevation weather stations for earlier times is not sufficient to achieve unbiased distribution of the observations with elevation. The model uses projected temperature and precipitation changes for all greenhouse gas scenarios (A1B, A2, and RCP3PD) and CH2011 time periods (2035, 2060, and 2085).\n\n# Data\n\nSnow cover changes are projected to be relatively small in the near term (2035) (Figure 5.1 top), in particular at higher elevations above 2000 m asl. As shown by Bavay et al. (2013) the spread in projected snow cover for this period is greater between different climate model chains (Chapter 3) than between the reference period and the model chain exhibiting the most moderate change. In the 2085 period much larger changes with the potential to fundamentally transform the snow dominated alpine area become apparent (Figure 5.1 bottom). These changes include a shortening of the snow season by 5\u20139 weeks for the A1B scenario. This is roughly equivalent to an elevation shift of 400\u2013800 m. The slight increase of winter precipitation and therefore snow fall projected in the CH2011 scenarios (with high associated uncertainty) can no longer compensate for the effect of increasing winter temperatures even at high elevations. In terms of Snow Water Equivalents (SWE), the projected reduction is up to two thirds toward the end of the century (2085). A continuous snow cover will be restricted to a shorter time period and/or to regions at increasingly high elevation. In Bern, for example, the number of days per year with at least 5 cm snow depth will decrease by 90% from now 20 days to only 2 days on average."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:c8696023-5622-481d-952a-13f88c35e9fe"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[8.227,46.79959],[8.227,46.79959],[8.227,46.79959],[8.227,46.79959],[8.227,46.79959]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "CLIMATE CHANGE"
-        },
-        {
-            "name": "SNOW DEPTH"
-        },
-        {
-            "name": "SNOW WATER EQUIVALENT"
-        }
-    ],
-    "title": [
-        "Alpine3D simulations of future climate scenarios CH2014"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/48bb409f-a5c3-5d7e-8423-a2bf049529bf.json b/oaitestdata/envidat-datacite/SET_1/json/48bb409f-a5c3-5d7e-8423-a2bf049529bf.json
deleted file mode 100644
index 35d3ff66..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/48bb409f-a5c3-5d7e-8423-a2bf049529bf.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:12a296af-a453-486c-b75b-892fa279bc9b",
-    "MetadataAccess": [
-        "oai:envidat.ch:12a296af-a453-486c-b75b-892fa279bc9b"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/basal_area-92"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:12a296af-a453-486c-b75b-892fa279bc9b;2018-12-09T00:31:23Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Basal area;2014;Swiss Federal Research Institute WSL;14 X 14 KM GRID;56 CLASSES;7 CLASSES;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;ALTITUDINAL VEGETATION ZONE;ALTITUDINAL VEGETATION ZONE 3 CLASSES;AVALANCHES SILVAPROTECT;BASAL AREA;BIOGEOGRAPHICAL REGION;CANTON;CONIFERS-BROADLEAVES;DIAMETER CLASS SIZE 10 CM;DIAMETER CLASSES;DOMINANT DIAMETER CLASS SIZE 10CM;ECONOMIC REGION;EXPOSITION 8 CLASSES;FOREST COMMUNITIES K\u00dcCHLER 2008;FOREST DISTRICT AS OF 2013;FOREST TYPE 12 CLASSES;FOREST TYPE AND STAGE OF DEVELOPMENT;GIANTS;GRID NFI4 2009-2013;LANDSLIDE-MUDFLOW SILVAPROTECT;LOWER-HIGHER ALTITUDINAL ZONES;MAIN TREE SPECIES;NFI1;NFI2;NFI3;NFI4B;OWNERSHIP;OWNERSHIP NFI4;POTENTIAL COST FOR TIMBER HARVESTING;PRIMARY FOREST FUNCTION NFI4 NATURE PROTECTION;PROCESSES IN CHANNELS SILVAPROTECT;PRODUCTION REGION;PROTECTION FOREST PERIMETER SILVAPROTECT;PROTECTION FOREST REGION;ROCKFALL SILVAPROTECT;SITE QUALITY;STAGE OF STAND DEVELOPMENT;TERRESTRIAL GRID NFI1;TERRESTRIAL GRID NFI2;TERRESTRIAL GRID NFI3;TREE SPECIES 5 CLASSES;TREE SPECIES WOODY SPECIES;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/basal_area-92;URL;1.0;Other (Open);Sum of the stem cross-section areas of all living trees and shrubs  starting at 12 cm dbh (standing and lying) at a height of 1.3 m (dbh measurement height).\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "48bb409f-a5c3-5d7e-8423-a2bf049529bf",
-    "notes": [
-        "Sum of the stem cross-section areas of all living trees and shrubs  starting at 12 cm dbh (standing and lying) at a height of 1.3 m (dbh measurement height).\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:12a296af-a453-486c-b75b-892fa279bc9b"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "X KM GRID"
-        },
-        {
-            "name": "CLASSES"
-        },
-        {
-            "name": "CLASSES"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE CLASSES"
-        },
-        {
-            "name": "AVALANCHES SILVAPROTECT"
-        }
-    ],
-    "title": [
-        "Basal area"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/4cb3e99f-9a1b-545f-87dc-51e9207d72e4.json b/oaitestdata/envidat-datacite/SET_1/json/4cb3e99f-9a1b-545f-87dc-51e9207d72e4.json
deleted file mode 100644
index b1d90b22..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/4cb3e99f-9a1b-545f-87dc-51e9207d72e4.json
+++ /dev/null
@@ -1,117 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:a67f9d30-7ca1-4770-8908-6d60bcd35f7e",
-    "MetadataAccess": [
-        "oai:envidat.ch:a67f9d30-7ca1-4770-8908-6d60bcd35f7e"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/salvage_logging_due_to_insects_star-251"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:a67f9d30-7ca1-4770-8908-6d60bcd35f7e;2018-12-09T00:33:02Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Salvage logging due to insects*;2014;Swiss Federal Research Institute WSL;14 X 14 KM GRID;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;ALTITUDINAL VEGETATION ZONE;CANTON;GRID NFI4 2009-2013;NFI2-NFI3;NFI3-NFI4B;SALVAGE LOGGING DUE TO INSECTS STAR;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/salvage_logging_due_to_insects_star-251;URL;1.0;Other (Open);Volume of stemwood with bark of all trees and shrubs  starting at 12 cm dbh removed from the forest as a result of damage occurring between two inventories, in this case insects, and not because of management planning. This feature is derived on the level of a sample plot from the cutting of the sample trees and the salvage cut proportion (according to information from the forester).  *In the calculation no D7/tree height data were used. The values calculated like this have not been corrected for bias, but allow for cantons or forest districts a more robust estimation of changes and could thus be better interpreted. \n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "4cb3e99f-9a1b-545f-87dc-51e9207d72e4",
-    "notes": [
-        "Volume of stemwood with bark of all trees and shrubs  starting at 12 cm dbh removed from the forest as a result of damage occurring between two inventories, in this case insects, and not because of management planning. This feature is derived on the level of a sample plot from the cutting of the sample trees and the salvage cut proportion (according to information from the forester).  *In the calculation no D7/tree height data were used. The values calculated like this have not been corrected for bias, but allow for cantons or forest districts a more robust estimation of changes and could thus be better interpreted. \n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:a67f9d30-7ca1-4770-8908-6d60bcd35f7e"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "X KM GRID"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "NFI-NFI"
-        },
-        {
-            "name": "NFI-NFIB"
-        },
-        {
-            "name": "SALVAGE LOGGING DUE INSECTS STAR"
-        }
-    ],
-    "title": [
-        "Salvage logging due to insects*"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/4ce1f005-dc4d-5789-8d6f-68de25c2cc2b.json b/oaitestdata/envidat-datacite/SET_1/json/4ce1f005-dc4d-5789-8d6f-68de25c2cc2b.json
deleted file mode 100644
index d11169d4..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/4ce1f005-dc4d-5789-8d6f-68de25c2cc2b.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:b3af3467-d789-4149-9613-e882fbbd6bb4",
-    "MetadataAccess": [
-        "oai:envidat.ch:b3af3467-d789-4149-9613-e882fbbd6bb4"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/total_timber_volume_nfi1-242"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:b3af3467-d789-4149-9613-e882fbbd6bb4;2018-12-09T00:33:28Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Total timber volume NFI1;2014;Swiss Federal Research Institute WSL;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ALTITUDINAL VEGETATION ZONE;BIOGEOGRAPHICAL REGION;CANTON;CONIFERS-BROADLEAVES;DIAMETER AT BREAST HEIGHT 30 CM;ECONOMIC REGION;FOREST DISTRICT AS OF 2013;GRID NFI4 2009-2013;LOWER-HIGHER ALTITUDINAL ZONES;MAIN TREE SPECIES;NFI1;OWNERSHIP;PRODUCTION REGION;PROTECTION FOREST REGION;TERRESTRIAL GRID NFI1;TOTAL TIMBER VOLUME NFI1;TREE SPECIES 5 CLASSES;TREE STATE ALIVE-DEAD;TREE STATUS;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/total_timber_volume_nfi1-242;URL;1.0;Other (Open);Volume of stemwood with bark of all living and dead trees and shrubs  starting at 12 cm dbh recorded according to the NFI1 method. In NFI1 only those dead trees were recorded whose wood could still be exploited. The correction for bias with the sample Tarif trees may be so drastic that it results in negative values with small numbers of trees.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "4ce1f005-dc4d-5789-8d6f-68de25c2cc2b",
-    "notes": [
-        "Volume of stemwood with bark of all living and dead trees and shrubs  starting at 12 cm dbh recorded according to the NFI1 method. In NFI1 only those dead trees were recorded whose wood could still be exploited. The correction for bias with the sample Tarif trees may be so drastic that it results in negative values with small numbers of trees.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:b3af3467-d789-4149-9613-e882fbbd6bb4"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        },
-        {
-            "name": "DIAMETER BREAST HEIGHT CM"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "FOREST DISTRICT"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "LOWER-HIGHER ALTITUDINAL ZONES"
-        },
-        {
-            "name": "MAIN TREE SPECIES"
-        }
-    ],
-    "title": [
-        "Total timber volume NFI1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/4f14fa08-8636-571e-a6b7-bfe8553e3319.json b/oaitestdata/envidat-datacite/SET_1/json/4f14fa08-8636-571e-a6b7-bfe8553e3319.json
deleted file mode 100644
index 050e2198..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/4f14fa08-8636-571e-a6b7-bfe8553e3319.json
+++ /dev/null
@@ -1,90 +0,0 @@
-{
-    "Contact": [
-        "Michael Lehning"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/envidat.51",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "PDF",
-        "R"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:e1d8922e-43f7-4a24-bf5f-d14d69414ff4",
-    "MetadataAccess": [
-        "oai:envidat.ch:e1d8922e-43f7-4a24-bf5f-d14d69414ff4"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Frontiers"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/dataset-on-wind-fields-and-energy-potential-in-swiss-alps"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63673642799,
-    "TempCoverageEnd": 63673642799,
-    "TemporalCoverage": " point in time : 2018-09-27T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-09-27T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-09-27T11:59:59Z",
-    "author": [
-        "Bert Kruyt",
-        "Michael Lehning"
-    ],
-    "fulltext": "oai:envidat.ch:e1d8922e-43f7-4a24-bf5f-d14d69414ff4;2018-12-09T00:22:05Z;10.16904/envidat.51;Bert Kruyt;CRYOS EPFL and WSL;Michael Lehning;0000-0002-8442-0875;WSL and CRYOS EPFL;Dataset on Cosmo-1 based Energy Potential in Swiss Alps;2018;Frontiers;COSMO-1;ES2050;MOUNTAIN WIND POTENTIAL;TOPOGRAPHY;WIND ENERGY;Michael Lehning;0000-0002-8442-0875;WSL and CRYOS EPFL;2018-09-27;en;Dataset;https://www.envidat.ch/dataset/dataset-on-wind-fields-and-energy-potential-in-swiss-alps;3144305336 bytes;255151 bytes;42299 bytes;R;PDF;1.0;Open Data Commons Open Database License (ODbL);This dataset consist of simulated hourly power production from an Enercon E82 Turbine at 100 m hub-height. It describes the hourly power output a 1MW turbine would produce in each 0.01\u00b0 grid cell for the years 2016 and 2017.\n\n100 m wind speed data was taken from the COSMO-1 model (Consortium for Small-scale Modeling 2017), which has a 0.01\u00b0 horizontal resolution. The domain covered is the whole of Switzerland, with the exclusion of lakes. As such, the number of 0.01\u25e6 pixels within Switzerland amounts to 48657. \nConversion to power output was done based on the power curve of the Enercon E82 Turbine. As power output is lower at altitude due to lower air density, we corrected for this effect as described in (Kruyt et al. 2017). \n\nPlease cite the following paper in connection with the dataset:\n\n__Paper Citation:__\n > _Bert Kruyt, J\u00e9r\u00f4me Dujardin, and Michael Lehning: Improvement of wind power assessment in complex terrain: The case of COSMO-1 in the Swiss Alps, Front. Energy Res., [doi:10.3389/fenrg.2018.00102] (https://doi.org/10.3389/fenrg.2018.00102)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "4f14fa08-8636-571e-a6b7-bfe8553e3319",
-    "notes": [
-        "This dataset consist of simulated hourly power production from an Enercon E82 Turbine at 100 m hub-height. It describes the hourly power output a 1MW turbine would produce in each 0.01\u00b0 grid cell for the years 2016 and 2017.\n\n100 m wind speed data was taken from the COSMO-1 model (Consortium for Small-scale Modeling 2017), which has a 0.01\u00b0 horizontal resolution. The domain covered is the whole of Switzerland, with the exclusion of lakes. As such, the number of 0.01\u25e6 pixels within Switzerland amounts to 48657. \nConversion to power output was done based on the power curve of the Enercon E82 Turbine. As power output is lower at altitude due to lower air density, we corrected for this effect as described in (Kruyt et al. 2017). \n\nPlease cite the following paper in connection with the dataset:\n\n__Paper Citation:__\n > _Bert Kruyt, J\u00e9r\u00f4me Dujardin, and Michael Lehning: Improvement of wind power assessment in complex terrain: The case of COSMO-1 in the Swiss Alps, Front. Energy Res., [doi:10.3389/fenrg.2018.00102] (https://doi.org/10.3389/fenrg.2018.00102)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:e1d8922e-43f7-4a24-bf5f-d14d69414ff4"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "COSMO-"
-        },
-        {
-            "name": "ES"
-        },
-        {
-            "name": "MOUNTAIN WIND POTENTIAL"
-        },
-        {
-            "name": "TOPOGRAPHY"
-        },
-        {
-            "name": "WIND ENERGY"
-        }
-    ],
-    "title": [
-        "Dataset on Cosmo-1 based Energy Potential in Swiss Alps"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/4f6a91ff-f44a-5550-9968-0c3bc0c88240.json b/oaitestdata/envidat-datacite/SET_1/json/4f6a91ff-f44a-5550-9968-0c3bc0c88240.json
deleted file mode 100644
index ae390578..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/4f6a91ff-f44a-5550-9968-0c3bc0c88240.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:833ab441-a144-4aad-98e0-17cd49353232",
-    "MetadataAccess": [
-        "oai:envidat.ch:833ab441-a144-4aad-98e0-17cd49353232"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/yield_and_mortality_star-163"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:833ab441-a144-4aad-98e0-17cd49353232;2018-12-09T00:33:43Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Yield and mortality*;2014;Swiss Federal Research Institute WSL;14 X 14 KM GRID;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;ALTITUDE 400 M CLASSES;ALTITUDINAL VEGETATION ZONE;CANTON;CONIFERS-BROADLEAVES;FOREST DISTRICT AS OF 2013;GRID NFI4 2009-2013;INCREMENT STAR;LOWER-HIGHER ALTITUDINAL ZONES;MAIN TREE SPECIES;NFI1-NFI2;NFI2-NFI3;NFI3-NFI4B;OWNERSHIP;YIELD AND MORTALITY STAR;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/yield_and_mortality_star-163;URL;1.0;Other (Open);Volume of stemwood with bark of all trees and shrubs  starting at 12 cm dbh that were used, died or disappeared between two inventories.  *In the calculation no D7/tree height data were used. The values calculated like this have not been corrected for bias, but allow for cantons or forest districts a more robust estimation of changes and could thus be better interpreted. \n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "4f6a91ff-f44a-5550-9968-0c3bc0c88240",
-    "notes": [
-        "Volume of stemwood with bark of all trees and shrubs  starting at 12 cm dbh that were used, died or disappeared between two inventories.  *In the calculation no D7/tree height data were used. The values calculated like this have not been corrected for bias, but allow for cantons or forest districts a more robust estimation of changes and could thus be better interpreted. \n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:833ab441-a144-4aad-98e0-17cd49353232"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "X KM GRID"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ALTITUDE M CLASSES"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        },
-        {
-            "name": "FOREST DISTRICT"
-        },
-        {
-            "name": "GRID NFI -"
-        }
-    ],
-    "title": [
-        "Yield and mortality*"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/50800c29-9647-533d-9fea-08705ddf403d.json b/oaitestdata/envidat-datacite/SET_1/json/50800c29-9647-533d-9fea-08705ddf403d.json
deleted file mode 100644
index dfdef2e4..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/50800c29-9647-533d-9fea-08705ddf403d.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:03568d20-52c5-462c-932d-ccb83fc49fbb",
-    "MetadataAccess": [
-        "oai:envidat.ch:03568d20-52c5-462c-932d-ccb83fc49fbb"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/total_timber_volume-23"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:03568d20-52c5-462c-932d-ccb83fc49fbb;2018-12-09T00:33:27Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Total timber volume;2014;Swiss Federal Research Institute WSL;14 X 14 KM GRID;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;ALTITUDINAL VEGETATION ZONE;BIOGEOGRAPHICAL REGION;CANTON;CONIFERS-BROADLEAVES;DIAMETER AT BREAST HEIGHT 30 CM;ECONOMIC REGION;FOREST DISTRICT AS OF 2013;GRID NFI4 2009-2013;LOWER-HIGHER ALTITUDINAL ZONES;MAIN TREE SPECIES;NFI2;NFI3;NFI4B;OWNERSHIP;OWNERSHIP NFI4;PRODUCTION REGION;PROTECTION FOREST REGION;TERRESTRIAL GRID NFI2;TERRESTRIAL GRID NFI3;TOTAL TIMBER VOLUME;TREE SPECIES 5 CLASSES;TREE STATE ALIVE-DEAD;TREE STATUS;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/total_timber_volume-23;URL;1.0;Other (Open);Volume of stemwood with bark of all living and dead trees and shrubs (standing and lying)  starting at 12 cm dbh. This corresponds to the sum of the volumes of growing stock and deadwood. The correction for bias with the sample Tarif trees may be so drastic that it results in negative values with small numbers of trees.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "50800c29-9647-533d-9fea-08705ddf403d",
-    "notes": [
-        "Volume of stemwood with bark of all living and dead trees and shrubs (standing and lying)  starting at 12 cm dbh. This corresponds to the sum of the volumes of growing stock and deadwood. The correction for bias with the sample Tarif trees may be so drastic that it results in negative values with small numbers of trees.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:03568d20-52c5-462c-932d-ccb83fc49fbb"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "X KM GRID"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        },
-        {
-            "name": "DIAMETER BREAST HEIGHT CM"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "FOREST DISTRICT"
-        }
-    ],
-    "title": [
-        "Total timber volume"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/51645b01-dfc8-5b48-8725-a32745e5dec1.json b/oaitestdata/envidat-datacite/SET_1/json/51645b01-dfc8-5b48-8725-a32745e5dec1.json
deleted file mode 100644
index f7848d28..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/51645b01-dfc8-5b48-8725-a32745e5dec1.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Nander Wever"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/17",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:df20d940-9653-4578-a32a-2d2ea7a1b347",
-    "MetadataAccess": [
-        "oai:envidat.ch:df20d940-9653-4578-a32a-2d2ea7a1b347"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "SLF"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/soil-moisture-measurements-davos"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": [
-        "46.7968286797 9.8297824141",
-        "46.8038436988 9.8940537806",
-        "46.7717421009 9.8666676384",
-        "46.8084926987 9.9034282695",
-        "46.7315544045 9.914150411",
-        "46.7897142035 9.8645693083",
-        "46.812365 9.847212"
-    ],
-    "TempCoverageBegin": 63421527599,
-    "TempCoverageEnd": 63421527599,
-    "TemporalCoverage": " point in time : 2010-10-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2010-10-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2010-10-01T11:59:59Z",
-    "author": [
-        "Nander Wever"
-    ],
-    "fulltext": "oai:envidat.ch:df20d940-9653-4578-a32a-2d2ea7a1b347;2018-12-09T00:24:13Z;10.16904/17;Nander Wever;SLF;IRKIS Soil moisture measurements Davos;2017;SLF;METEO STATION;SOIL MOISTURE;Nander Wever;SLF;2010-10-01;en;Dataset;https://www.envidat.ch/dataset/soil-moisture-measurements-davos;1.0;Open Data Commons Open Database License (ODbL);Meteorological and soil moisture measurements from soil moisture stations installed from October 2010 - October 2013 in the area surrounding Davos, in particular in the Dischma catchment.\n\nThere are in total 7 stations: 1202, 1203, 1204, 1205, 222, 333 and SLF2. For each of the stations, there is a:\n\n* vwc_[stn].smet: containing the soil moisture measurements\n\n* station_[stn].smet: in-situ measured meteorlogical parameters. Note, the quality of these measurements for stations 1202, 1203, 1204 and 1205 is very low, with data gaps. Use this data with care. For stations 222, 333 and SLF2, data quality is high and only the default cautiousness should be applied.\n\n* interpolatedmeteo_[stn].smet contains per stations a dataset derived by interpolating from several stations in the Davos area to the stations location. This dataset was generated from the output of the Alpine3D model, of which simulations are presented in the Wever et al. (2017) manuscript.\n\nAt the soil moisture measurement sites, Decagon 10HS sensors were installed, at 10, 30, 50, 80 and 120 cm depth. Per depth 2 sensors were installed, labelled A and B in the datafiles. Note that at stations 1203, 1204 and 1205, sensors were only installed at 10, 30 and 50 cm depth.\n\nThe files follow the SMET format: https://models.slf.ch/docserver/meteoio/SMET_specifications.pdf and metadata for the stations can be found in the header of the smet files.\n\nPlease cite the Wever et al. (2017) reference when using this data in publications.\n\nFor a more detailed description, please refer to: Wever, N., Comola, F., Bavay, M., and Lehning, M.: Simulating the influence of snow surface processes on soil moisture dynamics and streamflow generation in an alpine catchment, Hydrol. Earth Syst. Sci., 21, 4053-4071, https://doi.org/10.5194/hess-21-4053-2017, 2017.;46.7968286797 9.8297824141;46.8038436988 9.8940537806;46.7717421009 9.8666676384;46.8084926987 9.9034282695;46.7315544045 9.914150411;46.7897142035 9.8645693083;46.812365 9.847212;Davos, Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "51645b01-dfc8-5b48-8725-a32745e5dec1",
-    "notes": [
-        "Meteorological and soil moisture measurements from soil moisture stations installed from October 2010 - October 2013 in the area surrounding Davos, in particular in the Dischma catchment.\n\nThere are in total 7 stations: 1202, 1203, 1204, 1205, 222, 333 and SLF2. For each of the stations, there is a:\n\n* vwc_[stn].smet: containing the soil moisture measurements\n\n* station_[stn].smet: in-situ measured meteorlogical parameters. Note, the quality of these measurements for stations 1202, 1203, 1204 and 1205 is very low, with data gaps. Use this data with care. For stations 222, 333 and SLF2, data quality is high and only the default cautiousness should be applied.\n\n* interpolatedmeteo_[stn].smet contains per stations a dataset derived by interpolating from several stations in the Davos area to the stations location. This dataset was generated from the output of the Alpine3D model, of which simulations are presented in the Wever et al. (2017) manuscript.\n\nAt the soil moisture measurement sites, Decagon 10HS sensors were installed, at 10, 30, 50, 80 and 120 cm depth. Per depth 2 sensors were installed, labelled A and B in the datafiles. Note that at stations 1203, 1204 and 1205, sensors were only installed at 10, 30 and 50 cm depth.\n\nThe files follow the SMET format: https://models.slf.ch/docserver/meteoio/SMET_specifications.pdf and metadata for the stations can be found in the header of the smet files.\n\nPlease cite the Wever et al. (2017) reference when using this data in publications.\n\nFor a more detailed description, please refer to: Wever, N., Comola, F., Bavay, M., and Lehning, M.: Simulating the influence of snow surface processes on soil moisture dynamics and streamflow generation in an alpine catchment, Hydrol. Earth Syst. Sci., 21, 4053-4071, https://doi.org/10.5194/hess-21-4053-2017, 2017."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:df20d940-9653-4578-a32a-2d2ea7a1b347"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "METEO STATION"
-        },
-        {
-            "name": "SOIL MOISTURE"
-        }
-    ],
-    "title": [
-        "IRKIS Soil moisture measurements Davos"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/54d6fab8-3c37-52b3-a237-aa52ea6238af.json b/oaitestdata/envidat-datacite/SET_1/json/54d6fab8-3c37-52b3-a237-aa52ea6238af.json
deleted file mode 100644
index 47239bb3..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/54d6fab8-3c37-52b3-a237-aa52ea6238af.json
+++ /dev/null
@@ -1,100 +0,0 @@
-{
-    "Contact": [
-        "Marcus Schaub"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/11",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL",
-        "XLSX",
-        "JPEG"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:0e18a914-f2e4-47df-a86c-a44a1b0055e4",
-    "MetadataAccess": [
-        "oai:envidat.ch:0e18a914-f2e4-47df-a86c-a44a1b0055e4"
-    ],
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL / SwissForestLab"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/pfynwald"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(46N,8 E)",
-    "TempCoverageBegin": 63666471599,
-    "TempCoverageEnd": 63666471599,
-    "TemporalCoverage": " point in time : 2018-07-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-07-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-07-06T11:59:59Z",
-    "author": [
-        "Matthias Haeni",
-        "Arthur Gessler",
-        "Marcus Schaub",
-        "Christian Hug",
-        "Andreas Rigling"
-    ],
-    "fulltext": "oai:envidat.ch:0e18a914-f2e4-47df-a86c-a44a1b0055e4;2018-12-09T00:32:52Z;10.16904/11;Marcus Schaub;Swiss Federal Research Institute WSL;Matthias Haeni;Swiss Federal Research Institute WSL;Christian Hug;Swiss Federal Research Institute WSL;Arthur Gessler;Swiss Federal Research Institute WSL;Andreas Rigling;Swiss Federal Research Institute WSL;Tree\tmeasurements 2002-2016 from the long-term irrigation experiment Pfynwald, Switzerland;2016;Swiss Federal Research Institute WSL / SwissForestLab;CROWN CONDITION;DBH;DIAMETER AT BREAST HEIGHT;DROUGHT;IRRIGATION;SCOTS PINE;TREE;TREE SPECIES;Marcus Schaub;Swiss Federal Research Institute WSL;2018-07-06;en;https://www.envidat.ch/dataset/pfynwald;XLSX;JPEG;URL;2016;Open Data Commons Open Database License (ODbL);To study the performance of mature Scots pine (_Pinus sylvestris_ L.) under chronic drought conditions in comparison to their immediate physiological response to drought release, a controlled long-term and large-scale irrigation experiment has been set up in 2003. The experiment is located in a xeric mature Scots pine forest in the Pfynwald (46\u00b0 18' N, 7\u00b0 36' E, 615 m a.s.l.) in one of the driest inner-Alpine valleys of the European Alps, the Valais (mean annual temperature: 9.2\u00b0C, annual precipitation sum: 657 mm, both 1961-1990). Tree age is on average 100 years, the top height is 10.8 m and the stand density is 730 stems ha-1 with a basal area of 27.3 m2 ha-1. The forest is described as _Erico Pinetum sylvestris_ and the soil is a shallow pararendzina characterized by low water retention. The experimental site (1.2 ha; 800 trees) is split up into eight plots of 1'000 m2 each. During April-October, irrigation is applied on four randomly selected plots with sprinklers of 1 m height at night using water from an adjacent water channel. The amount of irrigation corresponds to a supplementary rainfall of 700 mm year-1. Trees in the other four plots grow under naturally dry conditions. Soil moisture has been monitored since the beginning of the project at 3 soil depths (10, 20 and 60 cm). The crown condition of each tree is being assessed each year since 2003. Tree measurement data such as diameter at breast height, tree height, and social status were assessed in 2002, 2009 and 2014. The duration of the irrigation experiment is planned for 20 years.;46.30284 7.61192;Pfynwald, Valais, Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "54d6fab8-3c37-52b3-a237-aa52ea6238af",
-    "notes": [
-        "To study the performance of mature Scots pine (_Pinus sylvestris_ L.) under chronic drought conditions in comparison to their immediate physiological response to drought release, a controlled long-term and large-scale irrigation experiment has been set up in 2003. The experiment is located in a xeric mature Scots pine forest in the Pfynwald (46\u00b0 18' N, 7\u00b0 36' E, 615 m a.s.l.) in one of the driest inner-Alpine valleys of the European Alps, the Valais (mean annual temperature: 9.2\u00b0C, annual precipitation sum: 657 mm, both 1961-1990). Tree age is on average 100 years, the top height is 10.8 m and the stand density is 730 stems ha-1 with a basal area of 27.3 m2 ha-1. The forest is described as _Erico Pinetum sylvestris_ and the soil is a shallow pararendzina characterized by low water retention. The experimental site (1.2 ha; 800 trees) is split up into eight plots of 1'000 m2 each. During April-October, irrigation is applied on four randomly selected plots with sprinklers of 1 m height at night using water from an adjacent water channel. The amount of irrigation corresponds to a supplementary rainfall of 700 mm year-1. Trees in the other four plots grow under naturally dry conditions. Soil moisture has been monitored since the beginning of the project at 3 soil depths (10, 20 and 60 cm). The crown condition of each tree is being assessed each year since 2003. Tree measurement data such as diameter at breast height, tree height, and social status were assessed in 2002, 2009 and 2014. The duration of the irrigation experiment is planned for 20 years."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:0e18a914-f2e4-47df-a86c-a44a1b0055e4"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[7.61192,46.30284],[7.61192,46.30284],[7.61192,46.30284],[7.61192,46.30284],[7.61192,46.30284]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "CROWN CONDITION"
-        },
-        {
-            "name": "DBH"
-        },
-        {
-            "name": "DIAMETER BREAST HEIGHT"
-        },
-        {
-            "name": "DROUGHT"
-        },
-        {
-            "name": "IRRIGATION"
-        },
-        {
-            "name": "SCOTS PINE"
-        },
-        {
-            "name": "TREE"
-        },
-        {
-            "name": "TREE SPECIES"
-        }
-    ],
-    "title": [
-        "Tree\tmeasurements 2002-2016 from the long-term irrigation experiment Pfynwald, Switzerland"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/54e3ee1a-0492-5905-b951-d65e227471e8.json b/oaitestdata/envidat-datacite/SET_1/json/54e3ee1a-0492-5905-b951-d65e227471e8.json
deleted file mode 100644
index 4e190367..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/54e3ee1a-0492-5905-b951-d65e227471e8.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:abea9123-a3fe-4a12-aaf1-952f97f4394c",
-    "MetadataAccess": [
-        "oai:envidat.ch:abea9123-a3fe-4a12-aaf1-952f97f4394c"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/basal_area_of_dead_wood_nfi1-247"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:abea9123-a3fe-4a12-aaf1-952f97f4394c;2018-12-09T00:31:27Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Basal area of dead wood NFI1;2014;Swiss Federal Research Institute WSL;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ALTITUDINAL VEGETATION ZONE;ALTITUDINAL VEGETATION ZONE 3 CLASSES;BASAL AREA OF DEAD WOOD NFI1;BIOGEOGRAPHICAL REGION;CANTON;CONIFERS-BROADLEAVES;ECONOMIC REGION;FOREST DISTRICT AS OF 2013;GRID NFI4 2009-2013;LOWER-HIGHER ALTITUDINAL ZONES;MAIN TREE SPECIES;NFI1;OWNERSHIP;PRIMARY FOREST FUNCTION NFI4 NATURE PROTECTION;PRODUCTION REGION;PROTECTION FOREST REGION;TERRESTRIAL GRID NFI1;TREE STATE STANDING-LYING;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/basal_area_of_dead_wood_nfi1-247;URL;1.0;Other (Open);Sum of stem cross-section areas of all dead trees in a stand at a height of 1.3 m (dbh measurement height) recorded according to the NFI1 method. \n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "54e3ee1a-0492-5905-b951-d65e227471e8",
-    "notes": [
-        "Sum of stem cross-section areas of all dead trees in a stand at a height of 1.3 m (dbh measurement height) recorded according to the NFI1 method. \n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:abea9123-a3fe-4a12-aaf1-952f97f4394c"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE CLASSES"
-        },
-        {
-            "name": "BASAL AREA DEAD WOOD NFI"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "FOREST DISTRICT"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "LOWER-HIGHER ALTITUDINAL ZONES"
-        }
-    ],
-    "title": [
-        "Basal area of dead wood NFI1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/5562a8a5-c08d-5c82-8de2-ed9baa33c4e4.json b/oaitestdata/envidat-datacite/SET_1/json/5562a8a5-c08d-5c82-8de2-ed9baa33c4e4.json
deleted file mode 100644
index 51e73353..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/5562a8a5-c08d-5c82-8de2-ed9baa33c4e4.json
+++ /dev/null
@@ -1,94 +0,0 @@
-{
-    "Contact": [
-        "Franziska Koch"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/envidat.56",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "PDF",
-        "CSV"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:cd57ac77-a276-4783-88c9-f52f51552d2c",
-    "MetadataAccess": [
-        "oai:envidat.ch:cd57ac77-a276-4783-88c9-f52f51552d2c"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "EnviDat"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/gps-derived-data-of-swe-hs-and-lwc-and-corresponding-validation-data"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N,10E)",
-    "TempCoverageBegin": 63579293999,
-    "TempCoverageEnd": 63579293999,
-    "TemporalCoverage": " point in time : 2015-10-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2015-10-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2015-10-01T11:59:59Z",
-    "author": [
-        "Wolfram Mauser",
-        "Patrick Henkel",
-        "Florian Appel",
-        "Franziska Koch",
-        "J\u00fcrg Schweizer"
-    ],
-    "fulltext": "oai:envidat.ch:cd57ac77-a276-4783-88c9-f52f51552d2c;2018-12-06T17:42:20Z;10.16904/envidat.56;Franziska Koch;0000-0001-5826-295X;University of Natural Resources and Life Sciences;Patrick Henkel;0000-0003-2934-3456;Advanced Navigation Solutions GmbH;Florian Appel;0000-0002-1907-9076;Vista Remote Sensing GmbH;Wolfram Mauser;0000-0002-2963-8759;Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen;J\u00fcrg Schweizer;0000-0001-5076-2968;WSL Institute for Snow and Avalanche Research SLF;GPS-derived data of SWE, HS and LWC and corresponding validation data;GPS-derived snow cover properties;2018;EnviDat;GPS;LIQUID WATER CONTENT;SNOW;SNOW COVER;SNOW DEPTH;Franziska Koch;0000-0001-5826-295X;University of Natural Resources and Life Sciences;2015-10-01;en;Dataset;https://www.envidat.ch/dataset/gps-derived-data-of-swe-hs-and-lwc-and-corresponding-validation-data;109310 bytes;90714 bytes;PDF;CSV;1.0;Open Data Commons Open Database License (ODbL);This dataset includes GPS-derived snow water equivalent (SWE), snow depth (HS) and liquid water content (LWC) data for three entire snow-covered seasons (2015-2016, 2016-2017, 2017-2018) at the study plot Weissfluhjoch 2540 m a.s.l. (Davos, Switzerland). The procedure to derive these snow properties is described in Koch et al. (submitted). The novel approach is based on a combination of GPS signal attenuation and time delay.\n\nThe dataset also includes corresponding validation data for SWE and HS measured at Weissfluhjoch, and some additional meteorological data used for interpretation of the snow cover evolution.\n\nPlease refer to the Read-me file for further details on the data.\n\nThese data are the basis of the following publication (and therefore the data are embargoed until the article will be accepted and published): \n > _Koch, F., Henkel, P., Appel, F., Schmid, L., Bach, H., Lamm, M., Prasch, M., Schweizer, J., and Mauser, W., 2018. Retrieval of snow water equivalent, liquid water content and snow height of dry and wet snow by combining GPS signal attenuation and time delay. Water Resources Research, submitted._;46.8295131395 9.80939626694;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "5562a8a5-c08d-5c82-8de2-ed9baa33c4e4",
-    "notes": [
-        "This dataset includes GPS-derived snow water equivalent (SWE), snow depth (HS) and liquid water content (LWC) data for three entire snow-covered seasons (2015-2016, 2016-2017, 2017-2018) at the study plot Weissfluhjoch 2540 m a.s.l. (Davos, Switzerland). The procedure to derive these snow properties is described in Koch et al. (submitted). The novel approach is based on a combination of GPS signal attenuation and time delay.\n\nThe dataset also includes corresponding validation data for SWE and HS measured at Weissfluhjoch, and some additional meteorological data used for interpretation of the snow cover evolution.\n\nPlease refer to the Read-me file for further details on the data.\n\nThese data are the basis of the following publication (and therefore the data are embargoed until the article will be accepted and published): \n > _Koch, F., Henkel, P., Appel, F., Schmid, L., Bach, H., Lamm, M., Prasch, M., Schweizer, J., and Mauser, W., 2018. Retrieval of snow water equivalent, liquid water content and snow height of dry and wet snow by combining GPS signal attenuation and time delay. Water Resources Research, submitted._"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:cd57ac77-a276-4783-88c9-f52f51552d2c"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[9.80939626694,46.8295131395],[9.80939626694,46.8295131395],[9.80939626694,46.8295131395],[9.80939626694,46.8295131395],[9.80939626694,46.8295131395]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "GPS"
-        },
-        {
-            "name": "LIQUID WATER CONTENT"
-        },
-        {
-            "name": "SNOW"
-        },
-        {
-            "name": "SNOW COVER"
-        },
-        {
-            "name": "SNOW DEPTH"
-        }
-    ],
-    "title": [
-        "GPS-derived data of SWE, HS and LWC and corresponding validation data",
-        "GPS-derived snow cover properties"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/57db07e1-95c7-5537-95f1-7f7a7a8c9cb8.json b/oaitestdata/envidat-datacite/SET_1/json/57db07e1-95c7-5537-95f1-7f7a7a8c9cb8.json
deleted file mode 100644
index 46adf7a7..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/57db07e1-95c7-5537-95f1-7f7a7a8c9cb8.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:b37fc3bb-0bbf-47b6-9dfc-d2a47629725d",
-    "MetadataAccess": [
-        "oai:envidat.ch:b37fc3bb-0bbf-47b6-9dfc-d2a47629725d"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/increment_star-162"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:b37fc3bb-0bbf-47b6-9dfc-d2a47629725d;2018-12-09T00:31:55Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Increment*;2014;Swiss Federal Research Institute WSL;14 X 14 KM GRID;56 CLASSES;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;ALTITUDE 400 M CLASSES;ALTITUDINAL VEGETATION ZONE;AVALANCHES SILVAPROTECT;CANTON;CONIFERS-BROADLEAVES;FOREST DISTRICT AS OF 2013;GRID NFI4 2009-2013;INCREMENT STAR;LANDSLIDE-MUDFLOW SILVAPROTECT;LOWER-HIGHER ALTITUDINAL ZONES;MAIN TREE SPECIES;NFI1-NFI2;NFI2-NFI3;NFI3-NFI4B;OWNERSHIP;POTENTIAL COST FOR TIMBER HARVESTING;PROCESSES IN CHANNELS SILVAPROTECT;PROTECTION FOREST PERIMETER SILVAPROTECT;ROCKFALL SILVAPROTECT;SITE QUALITY;TREE SPECIES WOODY SPECIES;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/increment_star-162;URL;1.0;Other (Open);Increase in the volume of stemwood with bark of the surviving trees and shrubs  starting at 12 cm dbh between two inventories and the losses (modelled for the half period), plus the volume of gains.  *In the calculation no D7/tree height data were used. The values calculated like this have not been corrected for bias, but allow for cantons or forest districts a more robust estimation of changes and could thus be better interpreted. \n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "57db07e1-95c7-5537-95f1-7f7a7a8c9cb8",
-    "notes": [
-        "Increase in the volume of stemwood with bark of the surviving trees and shrubs  starting at 12 cm dbh between two inventories and the losses (modelled for the half period), plus the volume of gains.  *In the calculation no D7/tree height data were used. The values calculated like this have not been corrected for bias, but allow for cantons or forest districts a more robust estimation of changes and could thus be better interpreted. \n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:b37fc3bb-0bbf-47b6-9dfc-d2a47629725d"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "X KM GRID"
-        },
-        {
-            "name": "CLASSES"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ALTITUDE M CLASSES"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "AVALANCHES SILVAPROTECT"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        }
-    ],
-    "title": [
-        "Increment*"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/580588e6-9e6c-5029-a68a-dde775838553.json b/oaitestdata/envidat-datacite/SET_1/json/580588e6-9e6c-5029-a68a-dde775838553.json
deleted file mode 100644
index 68ebec21..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/580588e6-9e6c-5029-a68a-dde775838553.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:7c8c6c9c-729b-40b6-847c-80b77f4539e6",
-    "MetadataAccess": [
-        "oai:envidat.ch:7c8c6c9c-729b-40b6-847c-80b77f4539e6"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/volume_of_dead_wood_nfi1-249"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:7c8c6c9c-729b-40b6-847c-80b77f4539e6;2018-12-09T00:33:37Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Volume of dead wood NFI1;2014;Swiss Federal Research Institute WSL;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ALTITUDINAL VEGETATION ZONE;ALTITUDINAL VEGETATION ZONE 3 CLASSES;BIOGEOGRAPHICAL REGION;CANTON;CONIFERS-BROADLEAVES;ECONOMIC REGION;FOREST DISTRICT AS OF 2013;GRID NFI4 2009-2013;LOWER-HIGHER ALTITUDINAL ZONES;MAIN TREE SPECIES;NFI1;OWNERSHIP;PRIMARY FOREST FUNCTION NFI4 NATURE PROTECTION;PRODUCTION REGION;PROTECTION FOREST REGION;TERRESTRIAL GRID NFI1;TREE STATE STANDING-LYING;VOLUME OF DEAD WOOD NFI1;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/volume_of_dead_wood_nfi1-249;URL;1.0;Other (Open);Volume of stemwood with bark of all dead trees and shrubs (standing and lying)  starting at 12 cm dbh  recorded according to the NFI1 method. In NFI1 only those dead trees were recorded whose wood could still be exploited. In addition, lying green trees were classified in NFI1 as deadwood.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "580588e6-9e6c-5029-a68a-dde775838553",
-    "notes": [
-        "Volume of stemwood with bark of all dead trees and shrubs (standing and lying)  starting at 12 cm dbh  recorded according to the NFI1 method. In NFI1 only those dead trees were recorded whose wood could still be exploited. In addition, lying green trees were classified in NFI1 as deadwood.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:7c8c6c9c-729b-40b6-847c-80b77f4539e6"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE CLASSES"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "FOREST DISTRICT"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "LOWER-HIGHER ALTITUDINAL ZONES"
-        },
-        {
-            "name": "MAIN TREE SPECIES"
-        }
-    ],
-    "title": [
-        "Volume of dead wood NFI1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/591046bc-5854-5fff-a014-71a0be729e42.json b/oaitestdata/envidat-datacite/SET_1/json/591046bc-5854-5fff-a014-71a0be729e42.json
deleted file mode 100644
index d010fc93..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/591046bc-5854-5fff-a014-71a0be729e42.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Luzi Bernhard"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "XLSX"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:4de5d4cd-f265-48b9-98a1-290d6f78fb23",
-    "MetadataAccess": [
-        "oai:envidat.ch:4de5d4cd-f265-48b9-98a1-290d6f78fb23"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/longterm-hydrological-observatory-alptal-central-switzerland"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N,9 E)",
-    "TempCoverageBegin": 62072481599,
-    "TempCoverageEnd": 62072481599,
-    "TemporalCoverage": " point in time : 1968-01-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1968-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1968-01-01T11:59:59Z",
-    "author": [
-        "Manfred St\u00e4hli"
-    ],
-    "fulltext": "oai:envidat.ch:4de5d4cd-f265-48b9-98a1-290d6f78fb23;2018-12-09T00:31:00Z;Manfred St\u00e4hli;Swiss Federal Research Institute WSL;Longterm hydrological observatory Alptal (central Switzerland);2018;ALPTAL;FIRST ORDER CATCHMENT;METEOROLOGICAL DATA;RUNOFF;SNOW;SUBALPINE;Luzi Bernhard;Swiss Federal Research Institute WSL;1968-01-01;en;Dataset;https://www.envidat.ch/dataset/longterm-hydrological-observatory-alptal-central-switzerland;1615852 bytes;2472224 bytes;1018271 bytes;XLSX;1.0;Open Data Commons Open Database License (ODbL);This data set includes 50 years of hydrometeorological measurements from small (first-order) catchments in the pre-alpine valley Alptal. Here we provide daily mean values; values in sub-daily resolution can be provided on demand.\nRunoff has been measured at the outlet of three small (first-order) catchments of approximately 1 km2 area: Erlenbach (two independent runoff measurements), Vogelbach and L\u00fcmpenenbach. The catchments are similar with regard to geology (Flysch) and soil conditions (clay soils), but differ in forest coverage (20 to 60%). A detailed description of the catchments can be found at https://www.wsl.ch/de/ueber-die-wsl/versuchsanlagen-und-labors/naturgefahren-anlagen/wildbachforschung-im-alptal/gebietsbeschreibung.html.\nRunoff in these small catchments is typically very dynamic and can temporally carry large amounts of sediment and large wood. Thus, the accuracy of the measurements at very large flow is limited. \nMeteorological variables have been measured on a meadow (Erlenh\u00f6he) located in the Erlenbach catchment at 1220 m a.s.l. using a standard meteorological station (incl. ventilated air temperature and heated rain gauges). In addition, precipitation has also been recorded at two other locations (in the Vogelbach and L\u00fcmpenenbach catchments).\nSnow measurements have been conducted weekly to monthly since 1968 at more than 15 locations (30-m transects) representing different altitudes, aspects and land uses (meadow, forest). Details on these snow measurements can be found in St\u00e4hli, M. and Gustafsson, D. 2006. Hydrol. Proc., 20, 411-428. doi: 10.1002/hyp.6058.;47.0466744008 8.70521664619;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "591046bc-5854-5fff-a014-71a0be729e42",
-    "notes": [
-        "This data set includes 50 years of hydrometeorological measurements from small (first-order) catchments in the pre-alpine valley Alptal. Here we provide daily mean values; values in sub-daily resolution can be provided on demand.\nRunoff has been measured at the outlet of three small (first-order) catchments of approximately 1 km2 area: Erlenbach (two independent runoff measurements), Vogelbach and L\u00fcmpenenbach. The catchments are similar with regard to geology (Flysch) and soil conditions (clay soils), but differ in forest coverage (20 to 60%). A detailed description of the catchments can be found at https://www.wsl.ch/de/ueber-die-wsl/versuchsanlagen-und-labors/naturgefahren-anlagen/wildbachforschung-im-alptal/gebietsbeschreibung.html.\nRunoff in these small catchments is typically very dynamic and can temporally carry large amounts of sediment and large wood. Thus, the accuracy of the measurements at very large flow is limited. \nMeteorological variables have been measured on a meadow (Erlenh\u00f6he) located in the Erlenbach catchment at 1220 m a.s.l. using a standard meteorological station (incl. ventilated air temperature and heated rain gauges). In addition, precipitation has also been recorded at two other locations (in the Vogelbach and L\u00fcmpenenbach catchments).\nSnow measurements have been conducted weekly to monthly since 1968 at more than 15 locations (30-m transects) representing different altitudes, aspects and land uses (meadow, forest). Details on these snow measurements can be found in St\u00e4hli, M. and Gustafsson, D. 2006. Hydrol. Proc., 20, 411-428. doi: 10.1002/hyp.6058."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:4de5d4cd-f265-48b9-98a1-290d6f78fb23"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[8.70521664619,47.0466744008],[8.70521664619,47.0466744008],[8.70521664619,47.0466744008],[8.70521664619,47.0466744008],[8.70521664619,47.0466744008]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ALPTAL"
-        },
-        {
-            "name": "FIRST ORDER CATCHMENT"
-        },
-        {
-            "name": "METEOROLOGICAL DATA"
-        },
-        {
-            "name": "RUNOFF"
-        },
-        {
-            "name": "SNOW"
-        },
-        {
-            "name": "SUBALPINE"
-        }
-    ],
-    "title": [
-        "Longterm hydrological observatory Alptal (central Switzerland)"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/5923c165-43d9-537a-b554-7d2c58266936.json b/oaitestdata/envidat-datacite/SET_1/json/5923c165-43d9-537a-b554-7d2c58266936.json
deleted file mode 100644
index 452176e1..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/5923c165-43d9-537a-b554-7d2c58266936.json
+++ /dev/null
@@ -1,107 +0,0 @@
-{
-    "Contact": [
-        "Markus Didion"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/envidat.52",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "PDF",
-        "XLSX"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:d92e9a5c-fc2f-4023-8f3a-b73cdf06ed9f",
-    "MetadataAccess": [
-        "oai:envidat.ch:d92e9a5c-fc2f-4023-8f3a-b73cdf06ed9f"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/herb-layer-biomass-in-swiss-forests"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": [
-        "47.0628584 7.195934012",
-        "46.79597556 7.581016377",
-        "46.66253488 7.426498306",
-        "47.51018267 8.82084427",
-        "47.39947643 9.160885554",
-        "46.9633825 8.731743039",
-        "46.18872018 8.797169613",
-        "46.08078867 8.93719123",
-        "46.35786287 9.197100398"
-    ],
-    "TempCoverageBegin": 63597697199,
-    "TempCoverageEnd": 63597697199,
-    "TemporalCoverage": " point in time : 2016-05-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2016-05-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2016-05-01T11:59:59Z",
-    "author": [
-        "Jerome Schneuwly",
-        "Marc Baume",
-        "Markus Didion",
-        "Fulvio Giudici"
-    ],
-    "fulltext": "oai:envidat.ch:d92e9a5c-fc2f-4023-8f3a-b73cdf06ed9f;2018-12-06T17:42:28Z;10.16904/envidat.52;Markus Didion;0000-0003-0346-0646;WSL;Marc Baume;WSL;Fulvio Giudici;WSL;Jerome Schneuwly;WSL;Herb layer biomass in Swiss forests;2018;Swiss Federal Research Institute WSL;BIOMASS;FERNS;GRASSES;HERBS;NATIONAL FOREST INVENTORY;SEDGES;SHRUBS;Markus Didion;0000-0003-0346-0646;WSL;2016-05-01;en;Dataset;https://www.envidat.ch/dataset/herb-layer-biomass-in-swiss-forests;2454893 bytes;146345 bytes;12554 bytes;PDF;XLSX;1.0;Open Data Commons Open Database License (ODbL);The purpose of this project was to develop a model to estimate herb layer biomass and carbon stock based on the categorical cover estimate on each NFI sample plot. To this end, biomass and cover of the six main plant groups in the herb layer were collected from 405 1x1 m subplots on 135 study sites (15 sites in 9 strata) which were selected based on a stratified sampling approach. To ensure consistency with NFI methodology, study sites corresponded to the design of regular NFI sample plots and plant cover was estimated by trained field-crew members. Based on the dry weight of the plant biomass and the cover estimate on each subplot, a linear regression model was developed and applied to estimate herb layer biomass on each NFI sample plot.;47.0628584 7.195934012;46.79597556 7.581016377;46.66253488 7.426498306;47.51018267 8.82084427;47.39947643 9.160885554;46.9633825 8.731743039;46.18872018 8.797169613;46.08078867 8.93719123;46.35786287 9.197100398;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "5923c165-43d9-537a-b554-7d2c58266936",
-    "notes": [
-        "The purpose of this project was to develop a model to estimate herb layer biomass and carbon stock based on the categorical cover estimate on each NFI sample plot. To this end, biomass and cover of the six main plant groups in the herb layer were collected from 405 1x1 m subplots on 135 study sites (15 sites in 9 strata) which were selected based on a stratified sampling approach. To ensure consistency with NFI methodology, study sites corresponded to the design of regular NFI sample plots and plant cover was estimated by trained field-crew members. Based on the dry weight of the plant biomass and the cover estimate on each subplot, a linear regression model was developed and applied to estimate herb layer biomass on each NFI sample plot."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:d92e9a5c-fc2f-4023-8f3a-b73cdf06ed9f"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "BIOMASS"
-        },
-        {
-            "name": "FERNS"
-        },
-        {
-            "name": "GRASSES"
-        },
-        {
-            "name": "HERBS"
-        },
-        {
-            "name": "NATIONAL FOREST INVENTORY"
-        },
-        {
-            "name": "SEDGES"
-        },
-        {
-            "name": "SHRUBS"
-        }
-    ],
-    "title": [
-        "Herb layer biomass in Swiss forests"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/59f9a72e-ed56-506d-8d77-74522a098e8f.json b/oaitestdata/envidat-datacite/SET_1/json/59f9a72e-ed56-506d-8d77-74522a098e8f.json
deleted file mode 100644
index f346f663..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/59f9a72e-ed56-506d-8d77-74522a098e8f.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Peter Bebi"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/envidat.46",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "PNG",
-        "ZIP"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:0d88fc12-285e-4a64-b2d6-d8a7bf0603f8",
-    "MetadataAccess": [
-        "oai:envidat.ch:0d88fc12-285e-4a64-b2d6-d8a7bf0603f8"
-    ],
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "WSL Institute for snow and avalanche research SLF"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/face-stillberg"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N,10E)",
-    "TempCoverageBegin": 63113947199,
-    "TempCoverageEnd": 63113947199,
-    "TemporalCoverage": " point in time : 2001-01-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2001-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2001-01-01T11:59:59Z",
-    "author": [
-        "Frank Hagedorn",
-        "Peter Bebi",
-        "Christian Rixen",
-        "Melissa Dawes"
-    ],
-    "fulltext": "oai:envidat.ch:0d88fc12-285e-4a64-b2d6-d8a7bf0603f8;2018-12-09T00:24:24Z;10.16904/envidat.46;Melissa Dawes;WSL Institute for snow and avalanche research SLF;Christian Rixen;WSL Institute for snow and avalanche research SLF;Frank Hagedorn;WSL;Peter Bebi;WSL Institute for snow and avalanche research SLF;FACE: Stillberg CO2 enrichment and soil warming study;2016;WSL Institute for snow and avalanche research SLF;CARBON DIOXIDE;CLIMATE CHANGE;SOIL TEMPERATURE;VEGETATION;Peter Bebi;WSL;2001-01-01;en;https://www.envidat.ch/dataset/face-stillberg;62446403 bytes;ZIP;PNG;1.0;Open Data Commons Open Database License (ODbL);# Overview\nHigh elevation ecosystems are important in research about environmental change because shifts in climate associated with anthropogenic greenhouse gas emissions are predicted to be more pronounced in these areas than in most other regions of the world. This project involves a Free Air CO2 Enrichment (FACE) and soil warming experiment located in a natural treeline environment near Davos, Switzerland (Stillberg, 2200 m a.s.l.). Elevated atmospheric CO2 concentrations (+200 ppm) were applied from 2001 to 2009, and a soil warming treatment (+4 K) was added in 2007 (ongoing). The combined CO2 enrichment and warming treatment reflects conditions expected to occur in this region in approximately 2050. A broad range of ecological and biogeochemical research is carried out as part of this environmental change project.\n\n#Experimental setup\nThe experiment consists of 40 hexagonal 1.1 m2 plots, 20 with a Pinus mugo ssp. uncinata (mountain pine, evergreen) individual in the centre and 20 with a Larix decidua (European larch, deciduous) individual in the centre. A dense cover of understorey vegetation surrounds the tree in each plot, including the dominant dwarf shrub species Vaccinium myrtillus (bilberry), Vaccinium gaultherioides (group V. uliginosum agg., northern bilberry) and Empetrum nigrum ssp. hermaphroditum (crowberry) plus several herbaceous and non-vascular species.\n\n\n\nAt the beginning of the experimental period, the 40 plots were assigned to 10 groups of four neighbouring plots (two larch and two pine trees per group) in order to facilitate the logistics of CO2 distribution and regulation. Half of these groups were randomly assigned to an elevated CO2 treatment while the remaining groups served as controls and received no additional CO2. In spring 2007, one plot of each tree species identity was randomly selected from each of the 10 CO2 treatment groups and assigned a soil warming treatment, yielding a balanced design with a replication of five individual plots for each combination of CO2 level, warming treatment and tree species.\n\n#Data\nSoil and air conditions have been monitored closely throughout the study period, with most measurements made during the combined CO2 x warming experiment (2007-2009).;46.7716544001 9.8675439656;Davos, Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "59f9a72e-ed56-506d-8d77-74522a098e8f",
-    "notes": [
-        "# Overview\nHigh elevation ecosystems are important in research about environmental change because shifts in climate associated with anthropogenic greenhouse gas emissions are predicted to be more pronounced in these areas than in most other regions of the world. This project involves a Free Air CO2 Enrichment (FACE) and soil warming experiment located in a natural treeline environment near Davos, Switzerland (Stillberg, 2200 m a.s.l.). Elevated atmospheric CO2 concentrations (+200 ppm) were applied from 2001 to 2009, and a soil warming treatment (+4 K) was added in 2007 (ongoing). The combined CO2 enrichment and warming treatment reflects conditions expected to occur in this region in approximately 2050. A broad range of ecological and biogeochemical research is carried out as part of this environmental change project.\n\n#Experimental setup\nThe experiment consists of 40 hexagonal 1.1 m2 plots, 20 with a Pinus mugo ssp. uncinata (mountain pine, evergreen) individual in the centre and 20 with a Larix decidua (European larch, deciduous) individual in the centre. A dense cover of understorey vegetation surrounds the tree in each plot, including the dominant dwarf shrub species Vaccinium myrtillus (bilberry), Vaccinium gaultherioides (group V. uliginosum agg., northern bilberry) and Empetrum nigrum ssp. hermaphroditum (crowberry) plus several herbaceous and non-vascular species.\n\n\n\nAt the beginning of the experimental period, the 40 plots were assigned to 10 groups of four neighbouring plots (two larch and two pine trees per group) in order to facilitate the logistics of CO2 distribution and regulation. Half of these groups were randomly assigned to an elevated CO2 treatment while the remaining groups served as controls and received no additional CO2. In spring 2007, one plot of each tree species identity was randomly selected from each of the 10 CO2 treatment groups and assigned a soil warming treatment, yielding a balanced design with a replication of five individual plots for each combination of CO2 level, warming treatment and tree species.\n\n#Data\nSoil and air conditions have been monitored closely throughout the study period, with most measurements made during the combined CO2 x warming experiment (2007-2009)."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:0d88fc12-285e-4a64-b2d6-d8a7bf0603f8"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[9.8675439656,46.7716544001],[9.8675439656,46.7716544001],[9.8675439656,46.7716544001],[9.8675439656,46.7716544001],[9.8675439656,46.7716544001]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "CARBON DIOXIDE"
-        },
-        {
-            "name": "CLIMATE CHANGE"
-        },
-        {
-            "name": "SOIL TEMPERATURE"
-        },
-        {
-            "name": "VEGETATION"
-        }
-    ],
-    "title": [
-        "FACE: Stillberg CO2 enrichment and soil warming study"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/5a7a057b-656c-59a2-a866-069f8be63275.json b/oaitestdata/envidat-datacite/SET_1/json/5a7a057b-656c-59a2-a866-069f8be63275.json
deleted file mode 100644
index f8af442b..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/5a7a057b-656c-59a2-a866-069f8be63275.json
+++ /dev/null
@@ -1,113 +0,0 @@
-{
-    "Contact": [
-        "M. Schaub (LTER national representative)"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/envidat.36",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "CSV"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:4039ffb0-bd4b-4e15-ab00-dca5ae5b2b37",
-    "MetadataAccess": [
-        "oai:envidat.ch:4039ffb0-bd4b-4e15-ab00-dca5ae5b2b37"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/lwf-tea-bag-sites"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": [
-        "47.274064 7.886764",
-        "47.225156 7.416653",
-        "46.302789 7.612108",
-        "46.022611 8.834161",
-        "46.700344 7.762336",
-        "47.165047 9.067072",
-        "47.361944 8.454444",
-        "46.318667 7.584333"
-    ],
-    "TempCoverageBegin": 63587678399,
-    "TempCoverageEnd": 63587678399,
-    "TemporalCoverage": " point in time : 2016-01-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2016-01-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2016-01-06T11:59:59Z",
-    "author": [
-        "Pierre Vollenweider",
-        "Arthur Gessler",
-        "Markus Didion",
-        "Marcus Schaub",
-        "Peter Waldner",
-        "Flurin Sutter"
-    ],
-    "fulltext": "oai:envidat.ch:4039ffb0-bd4b-4e15-ab00-dca5ae5b2b37;2018-12-06T17:34:20Z;10.16904/envidat.36;Markus Didion;0000-0003-0346-0646;WSL;Flurin Sutter;WSL;Pierre Vollenweider;WSL;Arthur Gessler;WSL;Peter Waldner;WSL;Marcus Schaub;WSL;LWF-Tea bag sites;2018;Swiss Federal Research Institute WSL;CARBON;DECOMPOSITION;FOREST;GREEN TEA;LITTER;MODELING;ROIBOOS;TEA BAG;VERIFICATION;M. Schaub (LTER national representative);WSL;2016-01-06;en;Dataset;https://www.envidat.ch/dataset/lwf-tea-bag-sites;4417 bytes;CSV;1.0;Open Data Commons Open Database License (ODbL);Decomposition of plant litter is a key process for the transfer of carbon and nutrients in ecosystems. Carbon contained in the decaying biomass is released to the atmosphere as respired CO2, and may contribute to global warming. Litterbag studies have been used to improve our knowledge of the drivers of litter decomposition, but they lack comparability because litter quality is plant species-specific. The use of commercial tea bags as a standard substrate was suggested in order to harmonize studies, where green tea and rooibos represent more labile and more recalcitrant C compounds as surrogates of local litter.\nThe tea bag approach was implemented on eight sites of the Swiss long-term Forest Ecosystem Research (LWF) network (https://www.wsl.ch/LWF). This allowed us to take advantage from the existing infrastructure and data from a previous litterbag study with local litter. In Beatenberg and Schaenis, additional elevation transects were established (1200-1800 m and 540-1150 m, respectively) to examine particularly the effect of temperature on decomposition. In Pfynwald (https://www.wsl.ch/de/ueber-die-wsl/versuchsanlagen-und-labors/flaechen-im-wald/pfynwald.html) and Salgesch, infrastructure of running projects was used to examine the effect of drought and understory removal, respectively. In Novaggio, tea bags were incubated in summer and winter to study the effect of seasonality particularly precipitation. Tea bags are collected after 3, 12, 24, and 36 months; for the two time-shifted experiments additionally after 6 and 9 months.\nThe study has two primary objectives. Firstly, it contributes to TeaComposition initiative (http://teacomposition.org/) which aims at investigating long-term litter decomposition and its key drivers at present as well as under different future climate scenarios using a common protocol and standard litter (tea) across nine terrestrial biomes. Secondly, the data are used to further develop decomposition models such as Yasso (http://en.ilmatieteenlaitos.fi/yasso) which is used by several countries, including Switzerland to estimate the annual carbon fluxes in dead wood, litter, and soil for reporting in National Greenhouse Gas Inventories under the United Nations Framework Convention on Climate Change and the Kyoto Protocol.;47.274064 7.886764;47.225156 7.416653;46.302789 7.612108;46.022611 8.834161;46.700344 7.762336;47.165047 9.067072;47.361944 8.454444;46.318667 7.584333;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "5a7a057b-656c-59a2-a866-069f8be63275",
-    "notes": [
-        "Decomposition of plant litter is a key process for the transfer of carbon and nutrients in ecosystems. Carbon contained in the decaying biomass is released to the atmosphere as respired CO2, and may contribute to global warming. Litterbag studies have been used to improve our knowledge of the drivers of litter decomposition, but they lack comparability because litter quality is plant species-specific. The use of commercial tea bags as a standard substrate was suggested in order to harmonize studies, where green tea and rooibos represent more labile and more recalcitrant C compounds as surrogates of local litter.\nThe tea bag approach was implemented on eight sites of the Swiss long-term Forest Ecosystem Research (LWF) network (https://www.wsl.ch/LWF). This allowed us to take advantage from the existing infrastructure and data from a previous litterbag study with local litter. In Beatenberg and Schaenis, additional elevation transects were established (1200-1800 m and 540-1150 m, respectively) to examine particularly the effect of temperature on decomposition. In Pfynwald (https://www.wsl.ch/de/ueber-die-wsl/versuchsanlagen-und-labors/flaechen-im-wald/pfynwald.html) and Salgesch, infrastructure of running projects was used to examine the effect of drought and understory removal, respectively. In Novaggio, tea bags were incubated in summer and winter to study the effect of seasonality particularly precipitation. Tea bags are collected after 3, 12, 24, and 36 months; for the two time-shifted experiments additionally after 6 and 9 months.\nThe study has two primary objectives. Firstly, it contributes to TeaComposition initiative (http://teacomposition.org/) which aims at investigating long-term litter decomposition and its key drivers at present as well as under different future climate scenarios using a common protocol and standard litter (tea) across nine terrestrial biomes. Secondly, the data are used to further develop decomposition models such as Yasso (http://en.ilmatieteenlaitos.fi/yasso) which is used by several countries, including Switzerland to estimate the annual carbon fluxes in dead wood, litter, and soil for reporting in National Greenhouse Gas Inventories under the United Nations Framework Convention on Climate Change and the Kyoto Protocol."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:4039ffb0-bd4b-4e15-ab00-dca5ae5b2b37"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "CARBON"
-        },
-        {
-            "name": "DECOMPOSITION"
-        },
-        {
-            "name": "FOREST"
-        },
-        {
-            "name": "GREEN TEA"
-        },
-        {
-            "name": "LITTER"
-        },
-        {
-            "name": "MODELING"
-        },
-        {
-            "name": "ROIBOOS"
-        },
-        {
-            "name": "TEA BAG"
-        },
-        {
-            "name": "VERIFICATION"
-        }
-    ],
-    "title": [
-        "LWF-Tea bag sites"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/5bd45143-daa5-562d-bbb7-c4d305ba0b73.json b/oaitestdata/envidat-datacite/SET_1/json/5bd45143-daa5-562d-bbb7-c4d305ba0b73.json
deleted file mode 100644
index 75a45c8c..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/5bd45143-daa5-562d-bbb7-c4d305ba0b73.json
+++ /dev/null
@@ -1,110 +0,0 @@
-{
-    "Contact": [
-        "Axel Volkwein"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/envidat.41",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "XLSX"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:2c3b41a5-0ff2-4d65-b396-19afe029df09",
-    "MetadataAccess": [
-        "oai:envidat.ch:2c3b41a5-0ff2-4d65-b396-19afe029df09"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/rockfall-gallery-testing-parde-2016"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N,9 E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Axel Volkwein"
-    ],
-    "fulltext": "oai:envidat.ch:2c3b41a5-0ff2-4d65-b396-19afe029df09;2018-12-09T00:32:57Z;10.16904/envidat.41;Axel Volkwein;0000-0003-3585-6426;WSL;Rockfall gallery testing Parde 2016;Rockfall impact testing;2018;WSL;EXPERIMENT;EXPERIMENTS;FIELD DATA;FIELD TEST;FIELD TESTS;IMPACT TESTING;MASS MOVEMENTS;NATURAL HAZARD;NATURAL HAZARDS;ROCKFALL;ROCKFALL EXPERIMENTS;ROCKFALLS;Axel Volkwein;0000-0003-3585-6426;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/rockfall-gallery-testing-parde-2016;320251100 bytes;7038602 bytes;XLSX;1.0;Open Data Commons Open Database License (ODbL);Five full-scale field tests were conducted with concrete blocks weighting between 800 and 3200 kg being dropped onto the roof of a gallery structure made from reinforced concrete. The impacts were recorded using high-speed video and acceleration measurements at the falling blocks. The dataset contains the raw data as well as the analyses of the block trajectories, i.e. kinetics and dynamics. Setup of the measurements and the analyses conducted are published in Volkwein, A. \"Durchf\u00fchrung und Auswertung von Steinschlagversuchen auf eine Stahlbetongalerie\", WSL-Berichte, Heft 68, 2018.;46.6532196367 8.69808197021;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "5bd45143-daa5-562d-bbb7-c4d305ba0b73",
-    "notes": [
-        "Five full-scale field tests were conducted with concrete blocks weighting between 800 and 3200 kg being dropped onto the roof of a gallery structure made from reinforced concrete. The impacts were recorded using high-speed video and acceleration measurements at the falling blocks. The dataset contains the raw data as well as the analyses of the block trajectories, i.e. kinetics and dynamics. Setup of the measurements and the analyses conducted are published in Volkwein, A. \"Durchf\u00fchrung und Auswertung von Steinschlagversuchen auf eine Stahlbetongalerie\", WSL-Berichte, Heft 68, 2018."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:2c3b41a5-0ff2-4d65-b396-19afe029df09"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[8.69808197021,46.6532196367],[8.69808197021,46.6532196367],[8.69808197021,46.6532196367],[8.69808197021,46.6532196367],[8.69808197021,46.6532196367]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "EXPERIMENT"
-        },
-        {
-            "name": "EXPERIMENTS"
-        },
-        {
-            "name": "FIELD DATA"
-        },
-        {
-            "name": "FIELD TEST"
-        },
-        {
-            "name": "FIELD TESTS"
-        },
-        {
-            "name": "IMPACT TESTING"
-        },
-        {
-            "name": "MASS MOVEMENTS"
-        },
-        {
-            "name": "NATURAL HAZARD"
-        },
-        {
-            "name": "NATURAL HAZARDS"
-        },
-        {
-            "name": "ROCKFALL"
-        },
-        {
-            "name": "ROCKFALL EXPERIMENTS"
-        },
-        {
-            "name": "ROCKFALLS"
-        }
-    ],
-    "title": [
-        "Rockfall gallery testing Parde 2016",
-        "Rockfall impact testing"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/5fda26ca-85c1-501d-a986-efed49e002c0.json b/oaitestdata/envidat-datacite/SET_1/json/5fda26ca-85c1-501d-a986-efed49e002c0.json
deleted file mode 100644
index ed96051c..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/5fda26ca-85c1-501d-a986-efed49e002c0.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "Martin Schneebeli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/20",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "TXT",
-        "ZIP"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:f87efc01-9914-4a75-998f-7dfc1fcef563",
-    "MetadataAccess": [
-        "oai:envidat.ch:f87efc01-9914-4a75-998f-7dfc1fcef563"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avalanche Research SLF"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/snow-deltao18-metamorphism-advection"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N,10E)",
-    "TempCoverageBegin": 63632602799,
-    "TempCoverageEnd": 63632602799,
-    "TemporalCoverage": " point in time : 2017-06-09T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2017-06-09T11:59:59Z",
-    "TemporalCoverage:EndDate": "2017-06-09T11:59:59Z",
-    "author": [
-        "Pirmin P. Ebner",
-        "Martin Schneebeli"
-    ],
-    "fulltext": "oai:envidat.ch:f87efc01-9914-4a75-998f-7dfc1fcef563;2018-12-09T00:23:53Z;10.16904/20;Pirmin P. Ebner;0000-0003-1012-5643;WSL Institute for Snow and Avalanche Research SLF;Martin Schneebeli;0000-0003-2872-4409;WSL Institute for Snow and Avalanche Research SLF;Experiments on stable water isotopes,  snow metamorphism, and advection;2017;WSL Institute for Snow and Avalanche Research SLF;ADVECTION;METAMORPHISM;SNOW;STABLE WATER ISOTOPE;Martin Schneebeli;WSL Institute for Snow and Avalanche Research;2017-06-09;en;https://www.envidat.ch/dataset/snow-deltao18-metamorphism-advection;974 bytes;8226023 bytes;TXT;ZIP;1.0;Open Data Commons Open Database License (ODbL);Stable water isotopes (\u03b418O) obtained from snow and ice samples of polar regions are used to reconstruct past climate variability, but heat and mass transport processes can affect the isotopic composition. Here we present an experimental study on the effect on the snow isotopic composition by airflow through a snow pack in controlled laboratory conditions. The influence of isothermal and controlled temperature gradient conditions on the \u03b418O content in the snow and interstitial water vapor is elucidated. The observed disequilibrium between snow and vapor isotopes led to exchange of isotopes between snow and vapor under non-equilibrium processes, significantly changing the \u03b418O content of the snow. The type of metamorphism of the snow had a significant influence on this process. \nEbner, P. P., Steen-Larsen, H. C., Stenni, B., Schneebeli, M., and Steinfeld, A.: Experimental observation of transient \u03b418O interaction between snow and advective airflow under various temperature gradient conditions, The Cryosphere Discuss., https://doi.org/10.5194/tc-2017-16, accepted, 2017.;46.812580167 9.84736561775;Davos Dorf, Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "5fda26ca-85c1-501d-a986-efed49e002c0",
-    "notes": [
-        "Stable water isotopes (\u03b418O) obtained from snow and ice samples of polar regions are used to reconstruct past climate variability, but heat and mass transport processes can affect the isotopic composition. Here we present an experimental study on the effect on the snow isotopic composition by airflow through a snow pack in controlled laboratory conditions. The influence of isothermal and controlled temperature gradient conditions on the \u03b418O content in the snow and interstitial water vapor is elucidated. The observed disequilibrium between snow and vapor isotopes led to exchange of isotopes between snow and vapor under non-equilibrium processes, significantly changing the \u03b418O content of the snow. The type of metamorphism of the snow had a significant influence on this process. \nEbner, P. P., Steen-Larsen, H. C., Stenni, B., Schneebeli, M., and Steinfeld, A.: Experimental observation of transient \u03b418O interaction between snow and advective airflow under various temperature gradient conditions, The Cryosphere Discuss., https://doi.org/10.5194/tc-2017-16, accepted, 2017."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:f87efc01-9914-4a75-998f-7dfc1fcef563"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[9.84736561775,46.812580167],[9.84736561775,46.812580167],[9.84736561775,46.812580167],[9.84736561775,46.812580167],[9.84736561775,46.812580167]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ADVECTION"
-        },
-        {
-            "name": "METAMORPHISM"
-        },
-        {
-            "name": "SNOW"
-        },
-        {
-            "name": "STABLE WATER ISOTOPE"
-        }
-    ],
-    "title": [
-        "Experiments on stable water isotopes,  snow metamorphism, and advection"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/60d985e1-c72f-54c7-964a-ff8e5ec830fc.json b/oaitestdata/envidat-datacite/SET_1/json/60d985e1-c72f-54c7-964a-ff8e5ec830fc.json
deleted file mode 100644
index 516e3b4c..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/60d985e1-c72f-54c7-964a-ff8e5ec830fc.json
+++ /dev/null
@@ -1,106 +0,0 @@
-{
-    "Contact": [
-        "Anita Risch"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/envidat.44",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "XLSX"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:6fb4c37d-16c8-48e3-a0e4-03a53a1ef45a",
-    "MetadataAccess": [
-        "oai:envidat.ch:6fb4c37d-16c8-48e3-a0e4-03a53a1ef45a"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Swiss Federal Institute for Forest, Snow and Landscape Research WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/ecosystem-coupling-and-multifunctionality-exclosure-experiment"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N-47N,10E-10E)",
-    "TempCoverageBegin": 63663879599,
-    "TempCoverageEnd": 63663879599,
-    "TemporalCoverage": " point in time : 2018-06-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-06-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-06-06T11:59:59Z",
-    "author": [
-        "Raul Ochoa-Hueso",
-        "Martin Schuetz",
-        "Anita Risch"
-    ],
-    "fulltext": "oai:envidat.ch:6fb4c37d-16c8-48e3-a0e4-03a53a1ef45a;2018-12-09T00:23:42Z;10.16904/envidat.44;Anita Risch;A-9836-2012;WSL;Martin Schuetz;WSL;Raul Ochoa-Hueso;https://www.researchgate.net/profile/Raul_Ochoa-Hueso2;Autonomous University of Madrid;Ecosystem coupling and multifunctionality - exclosure experiment;Ecosystem coupling-multifunctionality;2018;Swiss Federal Institute for Forest, Snow and Landscape Research WSL;ECOSYSTEM COUPLING;ECOSYSTEM FUNCTIONS;ECOSYSTEM MULTIFUNCTIONALITY;EXCLUSION;GRASSLAND;GRAZING;INVERTEBRATES;SUBALPINE;SWISS NATIONAL PARK;VERTEBRATES;Anita Risch;A-9836-2012;WSL;2018-06-06;en;Dataset;https://www.envidat.ch/dataset/ecosystem-coupling-and-multifunctionality-exclosure-experiment;34644 bytes;XLSX;1.0;Open Data Commons Open Database License (ODbL);This dataset contains all data on which the following publication below is based. \n__Citation:__\n > Risch AC, Ochoa-Hueso R, van der Putten WH, Bump JK, Busse MD, Frey B, Gwiazdowicz DJ, Page-Dumroese DS, Vandegehuchte ML, Zimmermann S, Sch\u00fctz M. (pending revisions). Size-dependent loss of aboveground animals differentially affects grassland ecosystem coupling and functions. 2018. Nature Communications 9: 3684. \n\nhttps://doi.org/10.1038/s41467-018-06105-4\n\n\nPlease cite this paper together with the citation for the datafile.\n\n\n#Methods\n##Study sites \nThe experimental exclosure setups were installed within the SNP (IUCN category Ia preserve; Dudley 2008), in south-eastern Switzerland. The park covers 172 km2 of forests and subalpine and alpine grasslands along with scattered rock outcrops and scree slopes. The entire area has been protected from human impact (no hunting, fishing, camping or off-trail hiking) since 1914. Large, fairly homogenous patches of short- and tall-grass vegetation, which originate from different historical management and grazing regimes, cover the park\u2019s subalpine grasslands entirely. Short-grass vegetation developed in areas where cattle used to rest (nutrient input) prior to the park\u2019s foundation (14th century to 1914) (Sch\u00fctz and others 2003, 2006) and is dominated by lawn grass species such as Festuca rubra L., Briza media L. and Agrostis capillaris L. (Sch\u00fctz and others 2003, 2006). Today, this vegetation type is intensively grazed by diverse vertebrate and invertebrate communities that inhabit the park and consume up to 60% of the available biomass (Risch and others 2013). Tall-grass vegetation developed where cattle formerly grazed, but did not rest, and is dominated by rather nutrient-poor tussocks of Carex sempervirens Vill. and Nardus stricta L. (Sch\u00fctz and others 2003, 2006). This vegetation type receives considerably less grazing, with only roughly 20% of the biomass consumed (Risch and others 2013). Consequently, the two vegetation types together represent a long-term trajectory of changes in grazing regimes. Underlying bedrock of all grasslands is dolomite, which renders these grasslands rather poor in nutrients regardless of former and current land-use regimes.\n##Experimental design\nTo progressively exclude aboveground vertebrate and invertebrate animals, we established 18 size-selective exclosure setups (nine in short-grass, nine in tall-grass vegetation) distributed over six subalpine grasslands across the SNP (Risch and others 2013, 2015). Elevation differences of exclosure locations did not exceed 350 m (between 1975 and 2300 m a.s.l.). The exclosures were established immediately after snowmelt in spring 2009 and were left in place for five consecutive growing seasons (until end of 2013). They were, however, temporarily dismantled every fall (late October after first snowfall) to protect them from avalanches. They were re-established in the same location every spring immediately after snowmelt. Each size-selective exclosure setup consisted of five plots (2 x 3 m) that progressively excluded aboveground vertebrates and invertebrates from large to small. The plots are labelled according to the guilds that had access to them \u201cL/M/S/I\u201d, \u201cM/S/I\u201d, \u201cS/I\u201d, \u201cI\u201d, \u201cNone\u201d; L = large mammals, M = medium mammals, S = small mammals, I = invertebrates, None = no animals had access. As we only had permission to have the experimental setup in place for five consecutive growing seasons, the experiment had to be completely dismantled in the late fall of 2013 and all material removed from the SNP.\nOur exclosure design was aimed at excluding mammalian herbivores, but naturally also excluded the few medium and small mammalian predators, as well as the entire aboveground invertebrate food web. A total of 26 large to small mammal species can be found in the SNP, but large apex predators are missing (wolf, bear, lynx) . Reptiles, amphibians and birds are scarce to absent in the subalpine grasslands under study. Only two reptile species occur in the park and they are confined to rocky areas that warm up enough for them to survive. One frog species spawns in an isolated pond far from our grasslands. Only three bird species occasionally feed on the subalpine grasslands. Using game cameras (Moultrie 6MP Game Spy I-60 Infrared Digital Game Camera, Moultrie Feeders, Alabaster, AL, USA), we did observe that the medium- and small-sized mammals (marmot/hares and mice) were not afraid to enter the fences and feed on their designated plots. We never spotted reptiles, amphibians or birds on camera. We distinguished between 59 higher aboveground-dwelling invertebrate taxa that our size-selective exclosures excluded (see also methods for aboveground-dwelling invertebrates below). \nThe \u201cL/M/S/I\u201d plot (not fenced) was located at least 5 m from the 2.1 m tall and 7 x 9 m large main electrical fence that enclosed the other four plots. The bottom wire of this fence was mounted at 0.5 m height and was not electrified to enable safe access for medium and small mammals, while fencing out the large ones. Within each main fence, we randomly established four 2 x 3 m plots separated by 1-m wide walkways from one another and from the main fence line: 1) the \u201cM/S/I\u201d plots were unfenced, allowing access to all but the large mammals; 2) the \u201cS/I\u201d plots (10 x 10 cm electrical mesh fence) excluded all medium-sized mammals. Note that the bottom 10 cm of this fence remained non-electrified to enable safe access for small mammals; 3) the \u201cI\u201d plots (2 x 2 cm metal mesh fence) excluded all mammals. We double-folded the mesh at the bottom 50 cm to reduce the mesh size to smaller than 1 x 1 cm openings; and 4) the \u201cNone\u201d plots were surrounded by a 1 m tall mosquito net (1.5 x 2 mm) to exclude all animals. The top of the plot was covered with a mosquito-meshed wooden frame mounted to the corner posts (roof). We treated these plots a few times with biocompatible insecticide (Clean kill original, Eco Belle GmbH, Waldshut-Tiengen, Germany) to remove insects that might have entered during data collection or that hatched from the soil, but amounts were negligible and did not impact soil moisture conditions within these plots.\nTo assess whether the design of the \u201cNone\u201d exclosure (mesh and roof) affected the response variables within the plots and, therefore, influenced the results, we established an additional six \u201cmicro-climate control\u201d exclosures (one in each of the six grasslands) (Risch and others 2013, 2015). These exclosures were built as the \u201cNone\u201d exclosures but were open at the bottom (20 cm) of the 3-m side of the fence facing away from the prevailing wind direction to allow invertebrates to enter. A 20-cm high and 3-m long strip of metal mesh was used to block access to small mammals. Thus, this construction allowed a comparable micro-climate to the \u201cNone\u201d plots, but also a comparable feeding pressure by invertebrates to the \u201cI\u201d plots. We compared various properties within these exclosures against one another to assess if our construction altered the conditions in the \u201cNone\u201d plots. We showed that differences in plant (e.g., vegetation height, aboveground biomass) and soil properties (e.g., soil temperature, moisture) found between the \u201cI\u201d and the \u201cNone\u201d treatments were not due to the construction of the \u201cNone\u201d exclosure, but a function of animal exclusions, although the amount of UV light reaching the plant canopy was significantly reduced (Risch and others 2013). \n##Aboveground invertebrate sampling\nAboveground invertebrates were sampled with two different methods to capture both ground- and plant-dwelling organisms: 1) we randomly placed two pitfall traps (67 mm in diameter, covered with a roof) filled with 20% propylene glycol in one 1 x 1 m subplot of the 2 x 3 m treatment plots in spring 2013 (May) and emptied them every two weeks until late September 2013 (Vandegehuchte and others 2017b, 2018). A pitfall trap consisted of a plastic cylinder (13 cm depth, 6.75 cm diameter). Within each cylinder we placed a 100 ml plastic vial with outer diameter 6.70 cm and on top of the cylinder we placed a plastic funnel to guide the invertebrates into the vials. Each trap was cover with a cone-shaped and transparent plastic roof to protect the trap from rain (Vandegehuchte and others 2017b, 2018). Note that in the \u201cNone\u201d plots only one trap was placed as control to check for effectiveness of the exclosure. 2) We vacuumed all invertebrates from a 60 x 60 cm area on another 1 x 1 m subplot with a suction sampler (Vortis, Burkhard manufacturing CO, Ltd., Rickmansworth, Hertfordshire, UK) every month from June to September 2013 (Vandegehuchte and others 2017b, 2018). For this purpose, we quickly placed a square plastic frame (60 x 60 x 40 cm) with a closable mosquito mesh sleeve attached to the top edge into the plot from the outside. The suction sample was then inserted into through the sleeve and operated for 45 s to collect the invertebrates (Vandegehuchte and others 2017b, 2018). \nWe sorted the \u2248100 000 individuals collected with both methods by hand and identified each individual morphologically to the lowest taxonomic level feasible (59 taxa, including orders, suborders, subfamilies, families; phylum for Mollusca). These taxa belonged to the following feeding types: 19 herbivores, 16 detritivores, 9 predators, 8 mixed feeders, 5 omnivores and 2 non-classified feeders (or not feeding as adults) (Vandegehuchte and others 2017b). We summed the numbers from the two pitfall traps and the suction sampling over the course of the 2013 season to represent the aboveground invertebrate abundance and community composition of a plot. Note: we did not specifically attempt to catch flying invertebrates with e.g., sticky traps, thus a few flying insects may have been missed with our vacuum sampling approach.\n##Sampling of plant properties \nThe vascular plant species composition was assessed at peak biomass every summer (July) by estimating the frequency of occurrence of each species with the pin count method in each plot (Frank and McNaughton 1990). A total of 172 taxa occurred within our 90 plots and we calculated plant species richness for each plot separately. We used the 2013 data in this study. Plant quality was assessed every year in July and September; here we use plant quality at the end of the experiment (September 2013). Two 10 x 100 cm wide strips of vegetation per plot were clipped, combined, dried at 65\u00b0C, and ground (Pulverisette 16, Fritsch, Idar-Oberstein, Germany) to pass through a 0.5 mm sieve. Twenty randomly selected samples across all treatments were analysed for N (Leco TruSpec Analyser, Leco, St. Joseph, Michigan, USA) (Vandegehuchte and others 2015). Nitrogen concentrations of the other samples were then estimated from models established for the experiment and the entire SNP relating Fourier transform-near infrared reflectance (FT-NIR) spectra to the measured values of N using a multi-purpose FT-NIR spectrometer (Bruker Optics, F\u00e4llanden, Switzerland) (Vandegehuchte and others 2015). Root biomass was sampled every fall by collecting five 2.2 cm diameter x 10 cm deep soil samples (Giddings Machine Company, Windsor, CO, USA) per plot (450 samples year-1). The samples were dried at 30 \u00b0C and roots were sorted from the sample by hand. We sorted each sample for 1 h which allowed to retrieve over 90% of all roots present in the samples (Risch and others 2013). The roots were then dried at 65 \u00b0C for 48 and weighed to the nearest mg. We averaged the values per plot and used the 2013 data only in this study.\n##Sampling of edaphic communities\nIn 2009, 2010, and 2011 we collected three composited soil samples (5 cm diameter x 10 cm depth; AMS Samplers, American Falls, ID, USA) and assessed bacterial community structure using T-RFLP profiling (Liu and others 1997; Blackwood and others 2003; Hodel and others 2014). We detected a total of 89 operational taxonomic units (OTUs). These values are in accordance with other studies reporting OTU richness (Wirthner and others 2011; Zumsteg and others 2012; Meola and others 2014) using T-RFLP profiling, a method that detects the most abundant, and thus likely, the most relevant, taxa. We averaged the data over the three years of collections for our calculations. Microbial biomass carbon (MBC) was determined with the substrate-induced method (Anderson and Domsch 1978) every fall (September) between 2009 and 2013 by collecting three mineral soil samples (5 cm diameter \u00d7 10 cm mineral soil core, AMS Samplers, American Falls, ID, USA). The three samples were combined (90 samples for each sampling year), immediately put on ice, taken to the laboratory, passed through a 2-mm sieve and stored at 4\u00b0C. Again, we only used the 2013 data in this study.\nSoil samples (5 cm diameter x 10 cm depth) to extract soil arthropods were collected in June, July, and August 2011 with a soil corer lined with a plastic sleeve to ensure an undisturbed sample (total of 270 samples). The plastic line core was immediately sealed on both ends using cling film and put into a cooler. All plots were sampled within three days and the extraction of arthropods started the evening of the sampling day using a high-gradient Tullgren funnel apparatus (Crossley and Blair 1991; Vandegehuchte and others 2015). Samples were kept in the extractor for four days and the soil arthropods were collected in 95% ethanol. All individuals were counted and each individual was identified morphologically to the lowest level feasible [76 taxa, including orders, suborders, subfamilies, families (Protura, Thysanoptera, Aphidina, Psylina, Coleoptera, Brachycera, Nematocera, Auchenorryncha, Heteroptera, Formicidae); sub-phylum for Myriapoda, for Acari and Collembola also including morpho-species). Note that we also included larval stages (nine of the 76 taxa) (Vandegehuchte and others 2015). All data were summed over the season. A detailed species list for mites and collembolans is published (Vandegehuchte and others 2017a) [https://doi.org/10.1371/journal.pone.0118679.s001]. Earthworms are rare in the SNP and therefore were not included. We collected eight random 2.2 cm diameter x 10 cm deep soil cores from each plot in September 2013 to determine the soil nematode community composition. The samples were mixed and the nematodes were extracted from 100 ml of fresh soil using Oostenbrink elutriators (Oostenbrink 1960). All nematodes in a 1 ml of the 10 ml extract were counted, a minimum of 150 individuals sample-1 were identified to genus or family level using (Bongers 1988), the numbers of all nematodes were extrapolated to the entire sample and expressed for a 100 g dry sample. In total we identified 63 genus or family levels (Vandegehuchte and others 2015). The list of all the nematodes found is published (Vandegehuchte and others 2015) [http://www.oikosjournal.org/appendix/oik-03341] or DOI: [doi: 10.1111/oik.03341]. \nWe are aware that sampling soil microbes from 2009 to 2011 and soil arthropods in 2011 was not ideal, but we are positive that this does not bias the results. Most of the parameters measured in our experiment either already showed a treatment response after the first growing season (e.g., plant biomass) or did not respond over the entire time experiment (e.g., microbial biomass C). The microbial community composition (2009 \u2013 2011) was highly influenced by inter-annual differences in temperature and precipitation, but did not differ between treatments or vegetation types (Hodel and others 2014). We therefore felt comfortable using the 2009 through 2011 data for describing the soil microbial community in our experimental treatments. Similarly, we are positive that our soil arthropod data are representative. We did assess soil arthropods in August 2012 and found no differences to the August 2011 data. However, we did not feel comfortable combining the 2011 June, July, August data with only August data for 2012 for our analyses. \n##Sampling of soil properties\nWe collected three soil samples (5 cm diameter x 10 cm depth) in each plot in September 2013 after removing the vegetation. First, we collected the top layer of mineral soil rich in organic matter, the surface organic layer or rhizosphere, typically 1 to 3 cm in depth with a soil corer (AMS Samples, American Falls, Idaho, USA). Second, we collected a 10 cm mineral soil core beneath this surface layer. The cores for each layer were composited, dried at 65 \u00b0C for 48 h and fine-ground to pass a 0.5 mm screen. We then analysed all samples for total C using a Leco TruSpec Analyser (Leco, St. Joseph, Michigan, USA). Mineral soil pH was measured potentiometrically in 1:2 soil:CaCl2 solution with an equilibration time of 30 min. \nSoil net N mineralisation was assessed during the 2013 growing season (Risch and others 2015). For this purpose, we randomly collected a 5 cm diameter x10 cm deep soil sample with a soil corer (AMS Samples, American Falls, Idaho, USA) after clipping the vegetation in June 2013. After weighing and sieving (4 mm mesh) the soil, we extracted a 20 g subsample in 1 mol l-1 KCl for 1.5 h on an end-over-end shaker and thereafter filtered it through ashless folded filter paper (DF 5895 150, ALBET LabScience, Hahnenm\u00fchle FineArt GmbH, Dassel, Germany). From these filtrates NO3- concentrations were measured colorimetrically (Norman and Stucki 1981) and NH4+with flow injection analysis (FIAS 300, Perkin Elmer, Waltham Massachusetts, USA) (Risch and others 2015). We dried the rest of the sample 105 \u00b0C to constant mass to determine fine,fraction bulk density. A second soil sample was collected within each plot in June 2013 with a corer lined with a 5 x 13 cm aluminium cylinder. The corer was driven 11.5 cm deep into the soil so that the top 1.5 cm of the cylinder remained empty. Into this space we placed a polyester bag (250 \u00b5m) filled an ion-exchanger resin to capture the incoming N. The bag was filled with a 1:1 mixture of acidic and alkaline exchanger resin (ion-exchanger I KA/ion exchanger IIIAA, Merck AG, Darmstadt, Germany). We then removed 1.5 cm soil at the bottom of the cylinder and placed a second resin exchanger bag into this space to capture the N leached from the soil column. To assure that the exchange resin was saturated with H+ and Cl- prior to filling the bags, the mixture was stirred with 1.2 ml l-1 HCl for 1 h and then rinsed with demineralized water until the electrical conductivity of the water reached 5 \u00b5m cm-1. The cylinder with the resin bags in place was reinserted into the soil with the top flush to the soil surface and incubated for three months. We recollected the cylinders in September 2013. Each resin bag and 20 g of sieved soil (4 mm mesh) from each cylinder were then separately extracted with KCl and NO3- and NH4+ concentrations were measured. Nitrate and NH4+ concentrations of all samples were then converted to a content basis by multiplying their values with fine fraction bulk density. Net N mineralisation was thereafter calculated as the difference between the N content of the samples collected at the end of the three-month incubation (including the N extracted from the bottom resin bag) and the N content at the beginning of the incubation (Risch and others 2015). \nSoil CO2 emissions were measured every two weeks between 0900 and 1700 hrs from early May through late September 2013 with a PP-Systems SRC-1 soil respiration chamber (15 cm high, 10 cm diameter; closed circuit) attached to a PP-Systems EGM-4 infrared gas analyser (PP-Systems, Amesbury, MA, USA) on two locations per plot (Risch and others 2013). The chamber was placed on randomly placed, permanently installed PVC collars (10 cm diameter) driven 5 cm into the soil at the beginning of the study (Risch and others 2013). Freshly germinated plants growing within the collars were removed prior to each measurement to avoid measuring plant respiration or photosynthesis. The two measurements collected per plot and sampling date were averaged. \nSoil moisture (with time domain reflectometry; Field-Scout TDR-100, Spectrum Technologies, Plainfield, Illionois, USA) and temperature (with a waterproof digital pocket thermometer; Barnstead International, Dubuque, Iowa, USA) were measured at five random locations per plot every two weeks during the growing seasons during the experiment for the 0 to 10 cm depth (Risch and others 2013, 2015). As soil moisture and soil temperature were highly negatively correlated (Risch and others 2013), we only used soil moisture for this study. We used plot-level averages of all values available to capture soil moisture variability during the five years of the experiment. The results remained unchanged when we only used soil moisture from the 2013 growing season.\n##Numeral calculations and statistical analyses\nEcosystem coupling. We conducted principal component analyses (PCAs; unscaled) at the complete dataset level using the abundances of each taxonomical entity to describe each of the five different communities used in this study: aboveground-dwelling invertebrates, vascular plants, soil microorganisms, soil arthropods and soil nematodes. We retained the first two components (PCA axis 1 and PCA axis 2) of each analysis as we found them to adequately represent the temporal and spatial variability of our 90 treatment plots in previous studies55,67. Together they explained a total of 71.70% of the variation for aboveground invertebrates, 44.36% for plants, 44.85% for soil microorganisms, 61.85% for soil arthropods and 77.19% for soil nematodes. In addition, we used soil pH and soil organic C content as a proxy for soil chemical properties, soil bulk density as a proxy for soil physical properties and soil moisture (negatively correlated with soil temperature) as a proxy for soil micro-climatic conditions for an overall total of fourteen constituents.\nWe calculated ecosystem coupling9 for each exclosure treatment within each vegetation type (i.e., 2 \uf0b4 5 treatment combinations in total) as an integrated measure of pairwise ecological interactions between ecosystem constituents representing ecological communities and the soil abiotic environment. These ecological interactions are defined by non-parametric Spearman rank correlation analyses between two constituents, excluding interactions involving two abiotic constituents (e.g., soil pH vs. soil moisture) and interactions between the first (PC1) and second (PC2) component of each community type, as these are orthogonal by definition. Interactions between abiotic constituents were excluded from the analyses because the focus of our study was on communities and how they interact with one another and their surrounding environment; therefore, including abiotic-abiotic interactions was not of interest here. Given that the effectiveness of our experimental design resulted in that no community composition data of aboveground-dwelling invertebrates was available for the \u201cNone\u201d plots (all animals excluded), only thirteen instead of fourteen constituents were included in the ecosystem coupling calculations for this treatment. The complete absence of aboveground invertebrates represents the most extreme case of disturbance between aboveground animal communities and the rest of the ecosystem constituents. This may have resulted in a slight overestimation of ecosystem coupling for these plots. \n\tAverage ecosystem coupling was calculated as follows: \nEcosystem coupling=\nwhere Xi is the absolute Coupling was calculated value of the Spearman\u2019s rho coefficient of the ith correlation for each treatment within each vegetation type (i.e., based on nine replicates each), considering and n is the number of pairwise comparisons considered (n = a total of 80;  interactions (56 in the case of the \u201cNone\u201d treatment). We considered a total of 40 biotic-biotic interactions (i.e., concerning two community-level principal components such as plants and microbes; 24 in the case of the \u201cNone\u201d treatment) and 40 abiotic-biotic (i.e., concerning one community-level principal component and one abiotic factor, e.g., plant community and soil properties; 32 in the case of the \u201cNone\u201d treatment).\tCoupling was calculated for each treatment within each vegetation type (i.e., based on nine replicates each), considering a total of 80 interactions (56 in the case of the \u201cNone\u201d treatment). We considered a total of 40 biotic-biotic interactions (i.e., concerning two community-level principal components such as plants and microbes; 24 in the case of the \u201cNone\u201d treatment) and 40 abiotic-biotic (i.e., concerning one community-level principal component and one abiotic factor, e.g., plant community and soil properties; 32 in the case of the \u201cNone\u201d treatment). \nTo establish whether constituents were significantly and positively coupled within treatments (i.e., the average of their correlation coefficients were greater than in a null model where correlation only happens by chance), we calculated one-tailed p-values based on permutation tests with 999 permutations.   \n \nWe considered six ecosystem functions and process rates commonly used to assess ecosystem functioning (Meyer and others 2015; Manning and others 2018). Plant N content represents a measure of forage quality, while plant richness has been shown to stabilise biomass production, thus allowing the system to respond to changes in herbivory. Soil net N mineralisation, soil respiration, root biomass, and microbial biomass represent fluxes or stocks of energy. For all functions and processes higher values represent higher functioning (Manning and others 2018). All these variables were measured in the last year of the experiment (2013). We then quantified ecosystem multifunctionality using the multiple threshold approach (Byrnes and others 2014; Manning and others 2018), which considers the number of functions that are above a certain threshold, over a series of threshold values (typically 10-99%) that are defined based on the maximum value of each function. We weighted all our functions equally for these calculations (Manning and others 2018). The number of functions in a plot with values higher than a given threshold value for the respective function is summed up. The sum represents ecosystem multifunctionality for that plot. Given that choosing any particular threshold as a measure of ecosystem multifunctionality is arbitrary, we calculated the average of thresholds from 10-90% (in 10% intervals) as a more integrated representation of ecosystem multifunctionality. \nWe used Pearson correlations to explore the relationships between ecosystem coupling (all interactions, biotic-biotic interactions, abiotic-biotic interactions involving above- and belowground constituents, and all interactions, biotic-biotic interactions, abiotic-biotic interactions involving belowground constituents only) and ecosystem multifunctionality by calculating the slopes of all relationships between ecosystem coupling and multifunctionality for all thresholds between 10 and 99%. We also related ecosystem coupling with the average of multifunctionality at thresholds between 30-80% as explained before and considered this correlation as a robust indication of the type of association between these two variables. In addition, we explored the relationships between ecosystem coupling (all interactions, biotic-biotic interactions, abiotic-biotic interactions involving above- and belowground constituents, and all interactions, biotic-biotic interactions, abiotic-biotic interactions involving belowground constituents only) and individual ecosystem functions. The effects of exclosures and vegetation type on individual functions and multifunctionality were evaluated using linear mixed effects models ('lme' function of the nlme package), with exclosure and vegetation type as fixed effects and fence as a random factor. All statistical analyses and numerical calculations were done in R version 3.4.0 (R Core Team 2016).\n\n#References\n\n- Anderson J, Domsch K. 1978. A physiological method for the quantitative measurement of microbial biomass in soil. Soil Biol Biochem 10:215\u201321.\n- Blackwood CB, Marsh T, Kim S-H, Paul EA. 2003. Terminal Restriction Fragment Length Polymorphism Data Analysis for Quantitative Comparison of Microbial Communities. Appl Environ Microbiol 69:926\u201332. http://www.ncbi.nlm.nih.gov/pmc/articles/PMC143601/\n- Bongers T. 1988. De nematoden von Nederland. Schoorl, The Netherlands: Pirola\n- Byrnes JEK, Gamfeldt L, Isbell F, Lefcheck JS, Griffin JN, Hector A, Cardinale BJ, Hooper DU, Dee LE, Duffy JE. 2014. Investigating the relationship between biodiversity and ecosystem multifunctionality: Challenges and solutions. Methods Ecol Evol 5:111\u201324.\n- Crossley DAJ, Blair JM. 1991. A high-efficiency low-technology Tulgren-type extractor for soil microarthopods. Agric Ecosyst Environ 34:187\u201392.\n- Dudley N. 2008. Guidelines for applying protected area managment categories. Gland: IUCN\n- Frank DA, McNaughton SJ. 1990. Aboveground biomass estimation with the canopy intercept method: A plant growth form caveat. Oikos 57:57\u201360.\n- Haynes AG, Sch\u00fctz M, Buchmann N, Page-Dumroese DS, Busse MD, Risch AC. 2014. Linkages between grazing history and herbivore exclusion on decomposition rates in mineral soils of subalpine grasslands. Plant Soil 374.\n- Hodel M, Sch\u00fctz M, Vandegehuchte ML, Frey B, Albrecht M, Busse MD, Risch AC. 2014. Does the aboveground herbivore assemblage influence soil bacterial community composition and richness in subalpine grasslands? Microb Ecol 68:584\u201395.\n- Liu WT, Marsh TL, Cheng H, Forney LJ. 1997. Characterization of microbial diversity by determining terminal restriction fragment length polymorphisms of genes encoding 16S rRNA. Appl Environ Microbiol 63:4516\u201322. http://www.ncbi.nlm.nih.gov/pmc/articles/PMC168770/\n- Manning P, van der Plas F, Soliveres S, Allan E, Maestre FT, Mace G, Whittingham MJ, Fischer M. 2018. Redefining ecosystem multifunctionality. Nat Ecol Evol 2:427\u201336. https://doi.org/10.1038/s41559-017-0461-7\n- Meola M, Lazzaro A, Zeyer J. 2014. Diversity, resistance and resilience of the bacterial communities at two alpine glacier forefields after a reciprocal soil transplantation. Environ Microbiol 16:1918\u201334. https://onlinelibrary.wiley.com/doi/abs/10.1111/1462-2920.12435\n- Meyer ST, Koch C, Weisser WW. 2015. Towards a standardized Rapid Ecosystem Function Assessment (REFA). Trends Ecol Evol 30:390\u20137. http://www.sciencedirect.com/science/article/pii/S0169534715000968\n- Norman R., Stucki JW. 1981. The determination of nitrate and nitrite in soil extracts by ultraviolet spectrophotometry. Soil Sci Soc Am J 45:347\u201353.\n- Ochoa-Hueso R. 2016. Non-linear disruption of ecological interactions in response to nitrogen deposition. Ecology 87:2802\u20132814.\n- Oostenbrink M. 1960. Estimating nematode populations by some selected methods. In: Sasser NJ, Jenkins WR, editors. Nematology. Chapel Hill, NC, USA: University of North Carolina Press. pp 85\u2013101.\n- R Core Team. 2016. R: A language and environment for statistical computing. Vienna, Austria: R Foundation for Statistical Computing\n- Risch AC, Haynes AG, Busse MD, Filli F, Sch\u00fctz M. 2013. The response",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "60d985e1-c72f-54c7-964a-ff8e5ec830fc",
-    "notes": [
-        "This dataset contains all data on which the following publication below is based. \n__Citation:__\n > Risch AC, Ochoa-Hueso R, van der Putten WH, Bump JK, Busse MD, Frey B, Gwiazdowicz DJ, Page-Dumroese DS, Vandegehuchte ML, Zimmermann S, Sch\u00fctz M. (pending revisions). Size-dependent loss of aboveground animals differentially affects grassland ecosystem coupling and functions. 2018. Nature Communications 9: 3684. \n\nhttps://doi.org/10.1038/s41467-018-06105-4\n\n\nPlease cite this paper together with the citation for the datafile.\n\n\n#Methods\n##Study sites \nThe experimental exclosure setups were installed within the SNP (IUCN category Ia preserve; Dudley 2008), in south-eastern Switzerland. The park covers 172 km2 of forests and subalpine and alpine grasslands along with scattered rock outcrops and scree slopes. The entire area has been protected from human impact (no hunting, fishing, camping or off-trail hiking) since 1914. Large, fairly homogenous patches of short- and tall-grass vegetation, which originate from different historical management and grazing regimes, cover the park\u2019s subalpine grasslands entirely. Short-grass vegetation developed in areas where cattle used to rest (nutrient input) prior to the park\u2019s foundation (14th century to 1914) (Sch\u00fctz and others 2003, 2006) and is dominated by lawn grass species such as Festuca rubra L., Briza media L. and Agrostis capillaris L. (Sch\u00fctz and others 2003, 2006). Today, this vegetation type is intensively grazed by diverse vertebrate and invertebrate communities that inhabit the park and consume up to 60% of the available biomass (Risch and others 2013). Tall-grass vegetation developed where cattle formerly grazed, but did not rest, and is dominated by rather nutrient-poor tussocks of Carex sempervirens Vill. and Nardus stricta L. (Sch\u00fctz and others 2003, 2006). This vegetation type receives considerably less grazing, with only roughly 20% of the biomass consumed (Risch and others 2013). Consequently, the two vegetation types together represent a long-term trajectory of changes in grazing regimes. Underlying bedrock of all grasslands is dolomite, which renders these grasslands rather poor in nutrients regardless of former and current land-use regimes.\n##Experimental design\nTo progressively exclude aboveground vertebrate and invertebrate animals, we established 18 size-selective exclosure setups (nine in short-grass, nine in tall-grass vegetation) distributed over six subalpine grasslands across the SNP (Risch and others 2013, 2015). Elevation differences of exclosure locations did not exceed 350 m (between 1975 and 2300 m a.s.l.). The exclosures were established immediately after snowmelt in spring 2009 and were left in place for five consecutive growing seasons (until end of 2013). They were, however, temporarily dismantled every fall (late October after first snowfall) to protect them from avalanches. They were re-established in the same location every spring immediately after snowmelt. Each size-selective exclosure setup consisted of five plots (2 x 3 m) that progressively excluded aboveground vertebrates and invertebrates from large to small. The plots are labelled according to the guilds that had access to them \u201cL/M/S/I\u201d, \u201cM/S/I\u201d, \u201cS/I\u201d, \u201cI\u201d, \u201cNone\u201d; L = large mammals, M = medium mammals, S = small mammals, I = invertebrates, None = no animals had access. As we only had permission to have the experimental setup in place for five consecutive growing seasons, the experiment had to be completely dismantled in the late fall of 2013 and all material removed from the SNP.\nOur exclosure design was aimed at excluding mammalian herbivores, but naturally also excluded the few medium and small mammalian predators, as well as the entire aboveground invertebrate food web. A total of 26 large to small mammal species can be found in the SNP, but large apex predators are missing (wolf, bear, lynx) . Reptiles, amphibians and birds are scarce to absent in the subalpine grasslands under study. Only two reptile species occur in the park and they are confined to rocky areas that warm up enough for them to survive. One frog species spawns in an isolated pond far from our grasslands. Only three bird species occasionally feed on the subalpine grasslands. Using game cameras (Moultrie 6MP Game Spy I-60 Infrared Digital Game Camera, Moultrie Feeders, Alabaster, AL, USA), we did observe that the medium- and small-sized mammals (marmot/hares and mice) were not afraid to enter the fences and feed on their designated plots. We never spotted reptiles, amphibians or birds on camera. We distinguished between 59 higher aboveground-dwelling invertebrate taxa that our size-selective exclosures excluded (see also methods for aboveground-dwelling invertebrates below). \nThe \u201cL/M/S/I\u201d plot (not fenced) was located at least 5 m from the 2.1 m tall and 7 x 9 m large main electrical fence that enclosed the other four plots. The bottom wire of this fence was mounted at 0.5 m height and was not electrified to enable safe access for medium and small mammals, while fencing out the large ones. Within each main fence, we randomly established four 2 x 3 m plots separated by 1-m wide walkways from one another and from the main fence line: 1) the \u201cM/S/I\u201d plots were unfenced, allowing access to all but the large mammals; 2) the \u201cS/I\u201d plots (10 x 10 cm electrical mesh fence) excluded all medium-sized mammals. Note that the bottom 10 cm of this fence remained non-electrified to enable safe access for small mammals; 3) the \u201cI\u201d plots (2 x 2 cm metal mesh fence) excluded all mammals. We double-folded the mesh at the bottom 50 cm to reduce the mesh size to smaller than 1 x 1 cm openings; and 4) the \u201cNone\u201d plots were surrounded by a 1 m tall mosquito net (1.5 x 2 mm) to exclude all animals. The top of the plot was covered with a mosquito-meshed wooden frame mounted to the corner posts (roof). We treated these plots a few times with biocompatible insecticide (Clean kill original, Eco Belle GmbH, Waldshut-Tiengen, Germany) to remove insects that might have entered during data collection or that hatched from the soil, but amounts were negligible and did not impact soil moisture conditions within these plots.\nTo assess whether the design of the \u201cNone\u201d exclosure (mesh and roof) affected the response variables within the plots and, therefore, influenced the results, we established an additional six \u201cmicro-climate control\u201d exclosures (one in each of the six grasslands) (Risch and others 2013, 2015). These exclosures were built as the \u201cNone\u201d exclosures but were open at the bottom (20 cm) of the 3-m side of the fence facing away from the prevailing wind direction to allow invertebrates to enter. A 20-cm high and 3-m long strip of metal mesh was used to block access to small mammals. Thus, this construction allowed a comparable micro-climate to the \u201cNone\u201d plots, but also a comparable feeding pressure by invertebrates to the \u201cI\u201d plots. We compared various properties within these exclosures against one another to assess if our construction altered the conditions in the \u201cNone\u201d plots. We showed that differences in plant (e.g., vegetation height, aboveground biomass) and soil properties (e.g., soil temperature, moisture) found between the \u201cI\u201d and the \u201cNone\u201d treatments were not due to the construction of the \u201cNone\u201d exclosure, but a function of animal exclusions, although the amount of UV light reaching the plant canopy was significantly reduced (Risch and others 2013). \n##Aboveground invertebrate sampling\nAboveground invertebrates were sampled with two different methods to capture both ground- and plant-dwelling organisms: 1) we randomly placed two pitfall traps (67 mm in diameter, covered with a roof) filled with 20% propylene glycol in one 1 x 1 m subplot of the 2 x 3 m treatment plots in spring 2013 (May) and emptied them every two weeks until late September 2013 (Vandegehuchte and others 2017b, 2018). A pitfall trap consisted of a plastic cylinder (13 cm depth, 6.75 cm diameter). Within each cylinder we placed a 100 ml plastic vial with outer diameter 6.70 cm and on top of the cylinder we placed a plastic funnel to guide the invertebrates into the vials. Each trap was cover with a cone-shaped and transparent plastic roof to protect the trap from rain (Vandegehuchte and others 2017b, 2018). Note that in the \u201cNone\u201d plots only one trap was placed as control to check for effectiveness of the exclosure. 2) We vacuumed all invertebrates from a 60 x 60 cm area on another 1 x 1 m subplot with a suction sampler (Vortis, Burkhard manufacturing CO, Ltd., Rickmansworth, Hertfordshire, UK) every month from June to September 2013 (Vandegehuchte and others 2017b, 2018). For this purpose, we quickly placed a square plastic frame (60 x 60 x 40 cm) with a closable mosquito mesh sleeve attached to the top edge into the plot from the outside. The suction sample was then inserted into through the sleeve and operated for 45 s to collect the invertebrates (Vandegehuchte and others 2017b, 2018). \nWe sorted the \u2248100 000 individuals collected with both methods by hand and identified each individual morphologically to the lowest taxonomic level feasible (59 taxa, including orders, suborders, subfamilies, families; phylum for Mollusca). These taxa belonged to the following feeding types: 19 herbivores, 16 detritivores, 9 predators, 8 mixed feeders, 5 omnivores and 2 non-classified feeders (or not feeding as adults) (Vandegehuchte and others 2017b). We summed the numbers from the two pitfall traps and the suction sampling over the course of the 2013 season to represent the aboveground invertebrate abundance and community composition of a plot. Note: we did not specifically attempt to catch flying invertebrates with e.g., sticky traps, thus a few flying insects may have been missed with our vacuum sampling approach.\n##Sampling of plant properties \nThe vascular plant species composition was assessed at peak biomass every summer (July) by estimating the frequency of occurrence of each species with the pin count method in each plot (Frank and McNaughton 1990). A total of 172 taxa occurred within our 90 plots and we calculated plant species richness for each plot separately. We used the 2013 data in this study. Plant quality was assessed every year in July and September; here we use plant quality at the end of the experiment (September 2013). Two 10 x 100 cm wide strips of vegetation per plot were clipped, combined, dried at 65\u00b0C, and ground (Pulverisette 16, Fritsch, Idar-Oberstein, Germany) to pass through a 0.5 mm sieve. Twenty randomly selected samples across all treatments were analysed for N (Leco TruSpec Analyser, Leco, St. Joseph, Michigan, USA) (Vandegehuchte and others 2015). Nitrogen concentrations of the other samples were then estimated from models established for the experiment and the entire SNP relating Fourier transform-near infrared reflectance (FT-NIR) spectra to the measured values of N using a multi-purpose FT-NIR spectrometer (Bruker Optics, F\u00e4llanden, Switzerland) (Vandegehuchte and others 2015). Root biomass was sampled every fall by collecting five 2.2 cm diameter x 10 cm deep soil samples (Giddings Machine Company, Windsor, CO, USA) per plot (450 samples year-1). The samples were dried at 30 \u00b0C and roots were sorted from the sample by hand. We sorted each sample for 1 h which allowed to retrieve over 90% of all roots present in the samples (Risch and others 2013). The roots were then dried at 65 \u00b0C for 48 and weighed to the nearest mg. We averaged the values per plot and used the 2013 data only in this study.\n##Sampling of edaphic communities\nIn 2009, 2010, and 2011 we collected three composited soil samples (5 cm diameter x 10 cm depth; AMS Samplers, American Falls, ID, USA) and assessed bacterial community structure using T-RFLP profiling (Liu and others 1997; Blackwood and others 2003; Hodel and others 2014). We detected a total of 89 operational taxonomic units (OTUs). These values are in accordance with other studies reporting OTU richness (Wirthner and others 2011; Zumsteg and others 2012; Meola and others 2014) using T-RFLP profiling, a method that detects the most abundant, and thus likely, the most relevant, taxa. We averaged the data over the three years of collections for our calculations. Microbial biomass carbon (MBC) was determined with the substrate-induced method (Anderson and Domsch 1978) every fall (September) between 2009 and 2013 by collecting three mineral soil samples (5 cm diameter \u00d7 10 cm mineral soil core, AMS Samplers, American Falls, ID, USA). The three samples were combined (90 samples for each sampling year), immediately put on ice, taken to the laboratory, passed through a 2-mm sieve and stored at 4\u00b0C. Again, we only used the 2013 data in this study.\nSoil samples (5 cm diameter x 10 cm depth) to extract soil arthropods were collected in June, July, and August 2011 with a soil corer lined with a plastic sleeve to ensure an undisturbed sample (total of 270 samples). The plastic line core was immediately sealed on both ends using cling film and put into a cooler. All plots were sampled within three days and the extraction of arthropods started the evening of the sampling day using a high-gradient Tullgren funnel apparatus (Crossley and Blair 1991; Vandegehuchte and others 2015). Samples were kept in the extractor for four days and the soil arthropods were collected in 95% ethanol. All individuals were counted and each individual was identified morphologically to the lowest level feasible [76 taxa, including orders, suborders, subfamilies, families (Protura, Thysanoptera, Aphidina, Psylina, Coleoptera, Brachycera, Nematocera, Auchenorryncha, Heteroptera, Formicidae); sub-phylum for Myriapoda, for Acari and Collembola also including morpho-species). Note that we also included larval stages (nine of the 76 taxa) (Vandegehuchte and others 2015). All data were summed over the season. A detailed species list for mites and collembolans is published (Vandegehuchte and others 2017a) [https://doi.org/10.1371/journal.pone.0118679.s001]. Earthworms are rare in the SNP and therefore were not included. We collected eight random 2.2 cm diameter x 10 cm deep soil cores from each plot in September 2013 to determine the soil nematode community composition. The samples were mixed and the nematodes were extracted from 100 ml of fresh soil using Oostenbrink elutriators (Oostenbrink 1960). All nematodes in a 1 ml of the 10 ml extract were counted, a minimum of 150 individuals sample-1 were identified to genus or family level using (Bongers 1988), the numbers of all nematodes were extrapolated to the entire sample and expressed for a 100 g dry sample. In total we identified 63 genus or family levels (Vandegehuchte and others 2015). The list of all the nematodes found is published (Vandegehuchte and others 2015) [http://www.oikosjournal.org/appendix/oik-03341] or DOI: [doi: 10.1111/oik.03341]. \nWe are aware that sampling soil microbes from 2009 to 2011 and soil arthropods in 2011 was not ideal, but we are positive that this does not bias the results. Most of the parameters measured in our experiment either already showed a treatment response after the first growing season (e.g., plant biomass) or did not respond over the entire time experiment (e.g., microbial biomass C). The microbial community composition (2009 \u2013 2011) was highly influenced by inter-annual differences in temperature and precipitation, but did not differ between treatments or vegetation types (Hodel and others 2014). We therefore felt comfortable using the 2009 through 2011 data for describing the soil microbial community in our experimental treatments. Similarly, we are positive that our soil arthropod data are representative. We did assess soil arthropods in August 2012 and found no differences to the August 2011 data. However, we did not feel comfortable combining the 2011 June, July, August data with only August data for 2012 for our analyses. \n##Sampling of soil properties\nWe collected three soil samples (5 cm diameter x 10 cm depth) in each plot in September 2013 after removing the vegetation. First, we collected the top layer of mineral soil rich in organic matter, the surface organic layer or rhizosphere, typically 1 to 3 cm in depth with a soil corer (AMS Samples, American Falls, Idaho, USA). Second, we collected a 10 cm mineral soil core beneath this surface layer. The cores for each layer were composited, dried at 65 \u00b0C for 48 h and fine-ground to pass a 0.5 mm screen. We then analysed all samples for total C using a Leco TruSpec Analyser (Leco, St. Joseph, Michigan, USA). Mineral soil pH was measured potentiometrically in 1:2 soil:CaCl2 solution with an equilibration time of 30 min. \nSoil net N mineralisation was assessed during the 2013 growing season (Risch and others 2015). For this purpose, we randomly collected a 5 cm diameter x10 cm deep soil sample with a soil corer (AMS Samples, American Falls, Idaho, USA) after clipping the vegetation in June 2013. After weighing and sieving (4 mm mesh) the soil, we extracted a 20 g subsample in 1 mol l-1 KCl for 1.5 h on an end-over-end shaker and thereafter filtered it through ashless folded filter paper (DF 5895 150, ALBET LabScience, Hahnenm\u00fchle FineArt GmbH, Dassel, Germany). From these filtrates NO3- concentrations were measured colorimetrically (Norman and Stucki 1981) and NH4+with flow injection analysis (FIAS 300, Perkin Elmer, Waltham Massachusetts, USA) (Risch and others 2015). We dried the rest of the sample 105 \u00b0C to constant mass to determine fine,fraction bulk density. A second soil sample was collected within each plot in June 2013 with a corer lined with a 5 x 13 cm aluminium cylinder. The corer was driven 11.5 cm deep into the soil so that the top 1.5 cm of the cylinder remained empty. Into this space we placed a polyester bag (250 \u00b5m) filled an ion-exchanger resin to capture the incoming N. The bag was filled with a 1:1 mixture of acidic and alkaline exchanger resin (ion-exchanger I KA/ion exchanger IIIAA, Merck AG, Darmstadt, Germany). We then removed 1.5 cm soil at the bottom of the cylinder and placed a second resin exchanger bag into this space to capture the N leached from the soil column. To assure that the exchange resin was saturated with H+ and Cl- prior to filling the bags, the mixture was stirred with 1.2 ml l-1 HCl for 1 h and then rinsed with demineralized water until the electrical conductivity of the water reached 5 \u00b5m cm-1. The cylinder with the resin bags in place was reinserted into the soil with the top flush to the soil surface and incubated for three months. We recollected the cylinders in September 2013. Each resin bag and 20 g of sieved soil (4 mm mesh) from each cylinder were then separately extracted with KCl and NO3- and NH4+ concentrations were measured. Nitrate and NH4+ concentrations of all samples were then converted to a content basis by multiplying their values with fine fraction bulk density. Net N mineralisation was thereafter calculated as the difference between the N content of the samples collected at the end of the three-month incubation (including the N extracted from the bottom resin bag) and the N content at the beginning of the incubation (Risch and others 2015). \nSoil CO2 emissions were measured every two weeks between 0900 and 1700 hrs from early May through late September 2013 with a PP-Systems SRC-1 soil respiration chamber (15 cm high, 10 cm diameter; closed circuit) attached to a PP-Systems EGM-4 infrared gas analyser (PP-Systems, Amesbury, MA, USA) on two locations per plot (Risch and others 2013). The chamber was placed on randomly placed, permanently installed PVC collars (10 cm diameter) driven 5 cm into the soil at the beginning of the study (Risch and others 2013). Freshly germinated plants growing within the collars were removed prior to each measurement to avoid measuring plant respiration or photosynthesis. The two measurements collected per plot and sampling date were averaged. \nSoil moisture (with time domain reflectometry; Field-Scout TDR-100, Spectrum Technologies, Plainfield, Illionois, USA) and temperature (with a waterproof digital pocket thermometer; Barnstead International, Dubuque, Iowa, USA) were measured at five random locations per plot every two weeks during the growing seasons during the experiment for the 0 to 10 cm depth (Risch and others 2013, 2015). As soil moisture and soil temperature were highly negatively correlated (Risch and others 2013), we only used soil moisture for this study. We used plot-level averages of all values available to capture soil moisture variability during the five years of the experiment. The results remained unchanged when we only used soil moisture from the 2013 growing season.\n##Numeral calculations and statistical analyses\nEcosystem coupling. We conducted principal component analyses (PCAs; unscaled) at the complete dataset level using the abundances of each taxonomical entity to describe each of the five different communities used in this study: aboveground-dwelling invertebrates, vascular plants, soil microorganisms, soil arthropods and soil nematodes. We retained the first two components (PCA axis 1 and PCA axis 2) of each analysis as we found them to adequately represent the temporal and spatial variability of our 90 treatment plots in previous studies55,67. Together they explained a total of 71.70% of the variation for aboveground invertebrates, 44.36% for plants, 44.85% for soil microorganisms, 61.85% for soil arthropods and 77.19% for soil nematodes. In addition, we used soil pH and soil organic C content as a proxy for soil chemical properties, soil bulk density as a proxy for soil physical properties and soil moisture (negatively correlated with soil temperature) as a proxy for soil micro-climatic conditions for an overall total of fourteen constituents.\nWe calculated ecosystem coupling9 for each exclosure treatment within each vegetation type (i.e., 2 \uf0b4 5 treatment combinations in total) as an integrated measure of pairwise ecological interactions between ecosystem constituents representing ecological communities and the soil abiotic environment. These ecological interactions are defined by non-parametric Spearman rank correlation analyses between two constituents, excluding interactions involving two abiotic constituents (e.g., soil pH vs. soil moisture) and interactions between the first (PC1) and second (PC2) component of each community type, as these are orthogonal by definition. Interactions between abiotic constituents were excluded from the analyses because the focus of our study was on communities and how they interact with one another and their surrounding environment; therefore, including abiotic-abiotic interactions was not of interest here. Given that the effectiveness of our experimental design resulted in that no community composition data of aboveground-dwelling invertebrates was available for the \u201cNone\u201d plots (all animals excluded), only thirteen instead of fourteen constituents were included in the ecosystem coupling calculations for this treatment. The complete absence of aboveground invertebrates represents the most extreme case of disturbance between aboveground animal communities and the rest of the ecosystem constituents. This may have resulted in a slight overestimation of ecosystem coupling for these plots. \n\tAverage ecosystem coupling was calculated as follows: \nEcosystem coupling=\nwhere Xi is the absolute Coupling was calculated value of the Spearman\u2019s rho coefficient of the ith correlation for each treatment within each vegetation type (i.e., based on nine replicates each), considering and n is the number of pairwise comparisons considered (n = a total of 80;  interactions (56 in the case of the \u201cNone\u201d treatment). We considered a total of 40 biotic-biotic interactions (i.e., concerning two community-level principal components such as plants and microbes; 24 in the case of the \u201cNone\u201d treatment) and 40 abiotic-biotic (i.e., concerning one community-level principal component and one abiotic factor, e.g., plant community and soil properties; 32 in the case of the \u201cNone\u201d treatment).\tCoupling was calculated for each treatment within each vegetation type (i.e., based on nine replicates each), considering a total of 80 interactions (56 in the case of the \u201cNone\u201d treatment). We considered a total of 40 biotic-biotic interactions (i.e., concerning two community-level principal components such as plants and microbes; 24 in the case of the \u201cNone\u201d treatment) and 40 abiotic-biotic (i.e., concerning one community-level principal component and one abiotic factor, e.g., plant community and soil properties; 32 in the case of the \u201cNone\u201d treatment). \nTo establish whether constituents were significantly and positively coupled within treatments (i.e., the average of their correlation coefficients were greater than in a null model where correlation only happens by chance), we calculated one-tailed p-values based on permutation tests with 999 permutations.   \n \nWe considered six ecosystem functions and process rates commonly used to assess ecosystem functioning (Meyer and others 2015; Manning and others 2018). Plant N content represents a measure of forage quality, while plant richness has been shown to stabilise biomass production, thus allowing the system to respond to changes in herbivory. Soil net N mineralisation, soil respiration, root biomass, and microbial biomass represent fluxes or stocks of energy. For all functions and processes higher values represent higher functioning (Manning and others 2018). All these variables were measured in the last year of the experiment (2013). We then quantified ecosystem multifunctionality using the multiple threshold approach (Byrnes and others 2014; Manning and others 2018), which considers the number of functions that are above a certain threshold, over a series of threshold values (typically 10-99%) that are defined based on the maximum value of each function. We weighted all our functions equally for these calculations (Manning and others 2018). The number of functions in a plot with values higher than a given threshold value for the respective function is summed up. The sum represents ecosystem multifunctionality for that plot. Given that choosing any particular threshold as a measure of ecosystem multifunctionality is arbitrary, we calculated the average of thresholds from 10-90% (in 10% intervals) as a more integrated representation of ecosystem multifunctionality. \nWe used Pearson correlations to explore the relationships between ecosystem coupling (all interactions, biotic-biotic interactions, abiotic-biotic interactions involving above- and belowground constituents, and all interactions, biotic-biotic interactions, abiotic-biotic interactions involving belowground constituents only) and ecosystem multifunctionality by calculating the slopes of all relationships between ecosystem coupling and multifunctionality for all thresholds between 10 and 99%. We also related ecosystem coupling with the average of multifunctionality at thresholds between 30-80% as explained before and considered this correlation as a robust indication of the type of association between these two variables. In addition, we explored the relationships between ecosystem coupling (all interactions, biotic-biotic interactions, abiotic-biotic interactions involving above- and belowground constituents, and all interactions, biotic-biotic interactions, abiotic-biotic interactions involving belowground constituents only) and individual ecosystem functions. The effects of exclosures and vegetation type on individual functions and multifunctionality were evaluated using linear mixed effects models ('lme' function of the nlme package), with exclosure and vegetation type as fixed effects and fence as a random factor. All statistical analyses and numerical calculations were done in R version 3.4.0 (R Core Team 2016).\n\n#References\n\n- Anderson J, Domsch K. 1978. A physiological method for the quantitative measurement of microbial biomass in soil. Soil Biol Biochem 10:215\u201321.\n- Blackwood CB, Marsh T, Kim S-H, Paul EA. 2003. Terminal Restriction Fragment Length Polymorphism Data Analysis for Quantitative Comparison of Microbial Communities. Appl Environ Microbiol 69:926\u201332. http://www.ncbi.nlm.nih.gov/pmc/articles/PMC143601/\n- Bongers T. 1988. De nematoden von Nederland. Schoorl, The Netherlands: Pirola\n- Byrnes JEK, Gamfeldt L, Isbell F, Lefcheck JS, Griffin JN, Hector A, Cardinale BJ, Hooper DU, Dee LE, Duffy JE. 2014. Investigating the relationship between biodiversity and ecosystem multifunctionality: Challenges and solutions. Methods Ecol Evol 5:111\u201324.\n- Crossley DAJ, Blair JM. 1991. A high-efficiency low-technology Tulgren-type extractor for soil microarthopods. Agric Ecosyst Environ 34:187\u201392.\n- Dudley N. 2008. Guidelines for applying protected area managment categories. Gland: IUCN\n- Frank DA, McNaughton SJ. 1990. Aboveground biomass estimation with the canopy intercept method: A plant growth form caveat. Oikos 57:57\u201360.\n- Haynes AG, Sch\u00fctz M, Buchmann N, Page-Dumroese DS, Busse MD, Risch AC. 2014. Linkages between grazing history and herbivore exclusion on decomposition rates in mineral soils of subalpine grasslands. Plant Soil 374.\n- Hodel M, Sch\u00fctz M, Vandegehuchte ML, Frey B, Albrecht M, Busse MD, Risch AC. 2014. Does the aboveground herbivore assemblage influence soil bacterial community composition and richness in subalpine grasslands? Microb Ecol 68:584\u201395.\n- Liu WT, Marsh TL, Cheng H, Forney LJ. 1997. Characterization of microbial diversity by determining terminal restriction fragment length polymorphisms of genes encoding 16S rRNA. Appl Environ Microbiol 63:4516\u201322. http://www.ncbi.nlm.nih.gov/pmc/articles/PMC168770/\n- Manning P, van der Plas F, Soliveres S, Allan E, Maestre FT, Mace G, Whittingham MJ, Fischer M. 2018. Redefining ecosystem multifunctionality. Nat Ecol Evol 2:427\u201336. https://doi.org/10.1038/s41559-017-0461-7\n- Meola M, Lazzaro A, Zeyer J. 2014. Diversity, resistance and resilience of the bacterial communities at two alpine glacier forefields after a reciprocal soil transplantation. Environ Microbiol 16:1918\u201334. https://onlinelibrary.wiley.com/doi/abs/10.1111/1462-2920.12435\n- Meyer ST, Koch C, Weisser WW. 2015. Towards a standardized Rapid Ecosystem Function Assessment (REFA). Trends Ecol Evol 30:390\u20137. http://www.sciencedirect.com/science/article/pii/S0169534715000968\n- Norman R., Stucki JW. 1981. The determination of nitrate and nitrite in soil extracts by ultraviolet spectrophotometry. Soil Sci Soc Am J 45:347\u201353.\n- Ochoa-Hueso R. 2016. Non-linear disruption of ecological interactions in response to nitrogen deposition. Ecology 87:2802\u20132814.\n- Oostenbrink M. 1960. Estimating nematode populations by some selected methods. In: Sasser NJ, Jenkins WR, editors. Nematology. Chapel Hill, NC, USA: University of North Carolina Press. pp 85\u2013101.\n- R Core Team. 2016. R: A language and environment for statistical computing. Vienna, Austria: R Foundation for Statistical Computing\n- Risch AC, Haynes AG, Busse MD, Filli F, Sch\u00fctz M. 2013. The response of soil CO2 fluxes to progressively excluding vertebrate and invertebrate herbivores depends on ecosystem type. Ecosystems 16:1192\u2013202.\n- Risch AC, Sch\u00fctz M, Vandegehuchte ML, Van Der Putten WH, Duyts H, Raschein U, Gwiazdowicz DJ, Busse MD, Page-Dumroese DS, Zimmermann S. 2015. Aboveground vertebrate and invertebrate herbivore impact on net N mineralization in subalpine grasslands. Ecology 96:3312\u201322.\n- Sch\u00fctz M, Risch AC, Achermann G, Thiel-Egenter C, Page-Dumroese DS, Jurgensen MF, Edwards PJ. 2006. Phosphorus translocation by red deer on a subalpine grassland in the Central European Alps. Ecosystems 9:624\u2013633.\n- Sch\u00fctz M, Risch AC, Leuzinger E, Kr\u00fcsi BO, Achermann G. 2003. Impact of herbivory by red deer (Cervus elaphus L.) on patterns and processes in subalpine grasslands in the Swiss National Park. For Ecol Manage 181:177\u201388.\n- Vandegehuchte ML, van der Putten WH, Duyts H, Sch\u00fctz M, Risch AC. 2017a. Aboveground mammal and invertebrate exclusions cause consistent changes in soil food webs of two subalpine grassland types, but mechanisms are system-speci\ufb01c. Oikos 126:212\u201323.\n- Vandegehuchte ML, Raschein U, Sch\u00fctz M, Gwiazdowicz DJ, Risch AC. 2015. Indirect short- and long-term effects of aboveground invertebrate and vertebrate herbivores on soil microarthropod communities. PLoS One 10:e0118679.\n- Vandegehuchte ML, Sch\u00fctz M, de Schaetzen F, Risch AC. 2017b. Mammal-induced trophic cascades in invertebrate food webs are modulated by grazing intensity in subalpine grassland. J Anim Ecol 86:1434\u201346.\n- Vandegehuchte ML, Trivellone V, Sch\u00fctz M, Firn J, de Schaetzen F, Risch AC. 2018. Mammalian herbivores affect leafhoppers associated with specific plant functional types at different timescales. Funct Ecol 32:545\u201355.\n- Wirthner S, Frey B, Busse MD, Sch\u00fctz M, Risch AC. 2011. Effects of wild boar (Sus scrofa L.) rooting on the bacterial community structure in mixed-hardwood forest soils in Switzerland. Eur J Soil Biol 47:296\u2013302. http://dx.doi.org/10.1016/j.ejsobi.2011.07.003\n- Zumsteg A, Luster J, G\u00f6ransson H, Smittenberg RH, Brunner I, Bernasconi SM, Zeyer J, Frey B. 2012. Bacterial, Archaeal and Fungal Succession in the Forefield of a Receding Glacier. Microb Ecol 63:552\u201364. https://doi.org/10.1007/s00248-011-9991-8"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:6fb4c37d-16c8-48e3-a0e4-03a53a1ef45a"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[10.0270843506,46.5948099753],[10.0270843506,46.7662842444],[10.3951263428,46.7662842444],[10.3951263428,46.5948099753],[10.0270843506,46.5948099753]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ECOSYSTEM COUPLING"
-        },
-        {
-            "name": "ECOSYSTEM FUNCTIONS"
-        },
-        {
-            "name": "ECOSYSTEM MULTIFUNCTIONALITY"
-        },
-        {
-            "name": "EXCLUSION"
-        },
-        {
-            "name": "GRASSLAND"
-        },
-        {
-            "name": "GRAZING"
-        },
-        {
-            "name": "INVERTEBRATES"
-        },
-        {
-            "name": "SUBALPINE"
-        },
-        {
-            "name": "SWISS NATIONAL PARK"
-        },
-        {
-            "name": "VERTEBRATES"
-        }
-    ],
-    "title": [
-        "Ecosystem coupling and multifunctionality - exclosure experiment",
-        "Ecosystem coupling-multifunctionality"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/610c7ef9-ff66-5d31-a5d6-863694d96ff6.json b/oaitestdata/envidat-datacite/SET_1/json/610c7ef9-ff66-5d31-a5d6-863694d96ff6.json
deleted file mode 100644
index d0773e72..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/610c7ef9-ff66-5d31-a5d6-863694d96ff6.json
+++ /dev/null
@@ -1,117 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:7e58d844-0067-40cf-8340-084f9d0e9433",
-    "MetadataAccess": [
-        "oai:envidat.ch:7e58d844-0067-40cf-8340-084f9d0e9433"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/salvage_logging_due_to_wind_star-250"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:7e58d844-0067-40cf-8340-084f9d0e9433;2018-12-09T00:33:06Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Salvage logging due to wind*;2014;Swiss Federal Research Institute WSL;14 X 14 KM GRID;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;ALTITUDINAL VEGETATION ZONE;CANTON;GRID NFI4 2009-2013;NFI2-NFI3;NFI3-NFI4B;SALVAGE LOGGING DUE TO WIND STAR;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/salvage_logging_due_to_wind_star-250;URL;1.0;Other (Open);Volume of stemwood with bark of all trees and shrubs  starting at 12 cm dbh removed from the forest as a result of damage occurring between two inventories, in this case windthrow, and not because of management planning. This theme is derived on the level of a sample plot from the cutting of the sample trees and the salvage cut proportion (according to information from the forester).  *In the calculation no D7/tree height data were used. The values calculated like this have not been corrected for bias, but allow for cantons or forest districts a more robust estimation of changes and could thus be better interpreted. \n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "610c7ef9-ff66-5d31-a5d6-863694d96ff6",
-    "notes": [
-        "Volume of stemwood with bark of all trees and shrubs  starting at 12 cm dbh removed from the forest as a result of damage occurring between two inventories, in this case windthrow, and not because of management planning. This theme is derived on the level of a sample plot from the cutting of the sample trees and the salvage cut proportion (according to information from the forester).  *In the calculation no D7/tree height data were used. The values calculated like this have not been corrected for bias, but allow for cantons or forest districts a more robust estimation of changes and could thus be better interpreted. \n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:7e58d844-0067-40cf-8340-084f9d0e9433"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "X KM GRID"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "NFI-NFI"
-        },
-        {
-            "name": "NFI-NFIB"
-        },
-        {
-            "name": "SALVAGE LOGGING DUE WIND STAR"
-        }
-    ],
-    "title": [
-        "Salvage logging due to wind*"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/61718442-77e1-5c79-9287-45860f69e19a.json b/oaitestdata/envidat-datacite/SET_1/json/61718442-77e1-5c79-9287-45860f69e19a.json
deleted file mode 100644
index 01a2e370..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/61718442-77e1-5c79-9287-45860f69e19a.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Rebecca Mott"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/envidat.25",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "PDF",
-        "ZIP"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:6b961ebc-1c86-45ec-8b6d-8efdd2e8babe",
-    "MetadataAccess": [
-        "oai:envidat.ch:6b961ebc-1c86-45ec-8b6d-8efdd2e8babe"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avalanche Research SLF"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/10-16904-envidat-25"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N,10E)",
-    "TempCoverageBegin": 63533329199,
-    "TempCoverageEnd": 63533329199,
-    "TemporalCoverage": " point in time : 2014-04-17T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2014-04-17T11:59:59Z",
-    "TemporalCoverage:EndDate": "2014-04-17T11:59:59Z",
-    "author": [
-        "Rebecca Mott",
-        "Michael Lehning",
-        "Sebastian Schl\u00f6gl"
-    ],
-    "fulltext": "oai:envidat.ch:6b961ebc-1c86-45ec-8b6d-8efdd2e8babe;2018-12-09T00:24:01Z;10.16904/envidat.25;Sebastian Schl\u00f6gl;E\u0300cole Polytechnique Fe\u0300de\u0300rale de Lausanne, Lausanne, Switzerland School of Architecture, Civil and Environmental Engineering, Laboratory of Cryospheric Sciences (CRYOS) and WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland;Michael Lehning;E\u0300cole Polytechnique Fe\u0300de\u0300rale de Lausanne, Lausanne, Switzerland School of Architecture, Civil and Environmental Engineering, Laboratory of Cryospheric Sciences (CRYOS) and WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland;Rebecca Mott;WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland;DISCHMEX - High-resolution daily snow ablation rates in an Alpine environment;High-resolution daily snow ablation rates recording with a terrestrial laserscanner;2017;WSL Institute for Snow and Avalanche Research SLF;PATCHY SNOW COVERS;SNOW ABLATION RATES;TERRESTRIAL LASER SCANNING;Rebecca Mott;E\u0300cole Polytechnique Fe\u0300de\u0300rale de Lausanne, Lausanne, Switzerland School of Architecture, Civil and Environmental Engineering, Laboratory of Cryospheric Sciences (CRYOS) and WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland,;2014-04-17;en;Dataset;https://www.envidat.ch/dataset/10-16904-envidat-25;76297946 bytes;2069460 bytes;85474333 bytes;6736562 bytes;73447711 bytes;1979860 bytes;352578 bytes;ZIP;PDF;1;Open Data Commons Open Database License (ODbL);We recorded snow ablation maps with a terrestrial laser scanner (TLS, Riegl-VZ6000) at the Gletschboden area. The TLS position is located approximately 30 vertical meters above the Gletschboden area at a northerly exposed slope. In total 44 TLS measurement sets have been conducted in three consecutive years 2014-2016 (2014: 13 measurements; 2015: 17 measurements; 2016: 14 measurements). The TLS system has a single-point measurement frequency of 300 kHz and a beam divergence of 0.007\u00b0. This set-up allows a horizontal resolution of approximately 0.01 m in 100 m distance to the TLS position. One scan of the Gletschboden area lasts approximately 15 minutes. The travel time from the laser scanner towards the surface is recorded and afterwards converted into a point cloud of distances. 5 reflectors located at the Gletschboden area and in the closer surroundings were additionally scanned during each measurement to transform the point cloud from the scanner own coordinate system into Swiss coordinates. Additionally, orthophotos have been created by using pictures recorded from the TLS in order to provide snow mask maps. Snow and bare ground can be distinguished by the RGB color information of the orthophoto. Cells with blue band information greater than 175 were categorized as snow and all cells with values smaller or equal 175 were categorized as bare ground.;46.71291 9.92665;The dataset was recorded at the Gletschboden area (2094 m asl) in the upper Dischma valley, Davos, Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "61718442-77e1-5c79-9287-45860f69e19a",
-    "notes": [
-        "We recorded snow ablation maps with a terrestrial laser scanner (TLS, Riegl-VZ6000) at the Gletschboden area. The TLS position is located approximately 30 vertical meters above the Gletschboden area at a northerly exposed slope. In total 44 TLS measurement sets have been conducted in three consecutive years 2014-2016 (2014: 13 measurements; 2015: 17 measurements; 2016: 14 measurements). The TLS system has a single-point measurement frequency of 300 kHz and a beam divergence of 0.007\u00b0. This set-up allows a horizontal resolution of approximately 0.01 m in 100 m distance to the TLS position. One scan of the Gletschboden area lasts approximately 15 minutes. The travel time from the laser scanner towards the surface is recorded and afterwards converted into a point cloud of distances. 5 reflectors located at the Gletschboden area and in the closer surroundings were additionally scanned during each measurement to transform the point cloud from the scanner own coordinate system into Swiss coordinates. Additionally, orthophotos have been created by using pictures recorded from the TLS in order to provide snow mask maps. Snow and bare ground can be distinguished by the RGB color information of the orthophoto. Cells with blue band information greater than 175 were categorized as snow and all cells with values smaller or equal 175 were categorized as bare ground."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:6b961ebc-1c86-45ec-8b6d-8efdd2e8babe"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[9.92665,46.71291],[9.92665,46.71291],[9.92665,46.71291],[9.92665,46.71291],[9.92665,46.71291]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "PATCHY SNOW COVERS"
-        },
-        {
-            "name": "SNOW ABLATION RATES"
-        },
-        {
-            "name": "TERRESTRIAL LASER SCANNING"
-        }
-    ],
-    "title": [
-        "DISCHMEX - High-resolution daily snow ablation rates in an Alpine environment",
-        "High-resolution daily snow ablation rates recording with a terrestrial laserscanner"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/61ea2c30-4fa4-5079-a8c1-f637762aa37f.json b/oaitestdata/envidat-datacite/SET_1/json/61ea2c30-4fa4-5079-a8c1-f637762aa37f.json
deleted file mode 100644
index 61e30546..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/61ea2c30-4fa4-5079-a8c1-f637762aa37f.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Ionu\u021b Iosifescu"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:035de132-2b5c-41af-8408-a4400facbe46",
-    "MetadataAccess": [
-        "oai:envidat.ch:035de132-2b5c-41af-8408-a4400facbe46"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "EnviDat"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/new-schema-test"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63680385599,
-    "TempCoverageEnd": 63680385599,
-    "TemporalCoverage": " point in time : 2018-12-14T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-14T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-14T11:59:59Z",
-    "author": [
-        "Ionu\u021b Iosifescu"
-    ],
-    "fulltext": "oai:envidat.ch:035de132-2b5c-41af-8408-a4400facbe46;2018-12-14T12:31:18Z;Ionu\u021b Iosifescu;0000-0002-1770-7833;WSL;New Schema Test;2018;EnviDat;FOREST;LANDSCAPE;SNOW;Ionu\u021b Iosifescu;0000-0002-1770-7833;WSL;2018-12-14;en;Dataset;https://www.envidat.ch/dataset/new-schema-test;1.0;Open Data Commons Open Database License (ODbL);testing the new schema in production;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "61ea2c30-4fa4-5079-a8c1-f637762aa37f",
-    "notes": [
-        "testing the new schema in production"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:035de132-2b5c-41af-8408-a4400facbe46"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "FOREST"
-        },
-        {
-            "name": "LANDSCAPE"
-        },
-        {
-            "name": "SNOW"
-        }
-    ],
-    "title": [
-        "New Schema Test"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/62778fc3-5a23-514c-b5d6-7b4b094f90bc.json b/oaitestdata/envidat-datacite/SET_1/json/62778fc3-5a23-514c-b5d6-7b4b094f90bc.json
deleted file mode 100644
index 398e72ec..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/62778fc3-5a23-514c-b5d6-7b4b094f90bc.json
+++ /dev/null
@@ -1,115 +0,0 @@
-{
-    "Contact": [
-        "F. Alexander Haumann"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/8",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL",
-        "PDF",
-        "NetCDF4 CF-1.6"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:b16a0901-3abe-4da0-b61e-cdb80c59ba63",
-    "MetadataAccess": [
-        "oai:envidat.ch:b16a0901-3abe-4da0-b61e-cdb80c59ba63"
-    ],
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "ETH Zurich"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/10-16904-8"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Non-Commercial)"
-    ],
-    "SpatialCoverage": "(90S-37S,180W-180E)",
-    "TempCoverageBegin": 62519428799,
-    "TempCoverageEnd": 62519428799,
-    "TemporalCoverage": " point in time : 1982-03-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1982-03-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1982-03-01T11:59:59Z",
-    "author": [
-        "Nicolas Gruber",
-        "Ivy Frenger",
-        "Stefan Kern",
-        "Matthias M\u00fcnnich",
-        "F. Alexander Haumann"
-    ],
-    "fulltext": "oai:envidat.ch:b16a0901-3abe-4da0-b61e-cdb80c59ba63;2018-07-10T07:48:38Z;10.16904/8;F. Alexander Haumann;0000-0002-8218-977X;ETHZ;Nicolas Gruber;ETHZ;Matthias M\u00fcnnich;ETHZ;Ivy Frenger;ETHZ, GEOMAR Helmholtz Centre for Ocean Research Kiel;Stefan Kern;ICDC  University of Hamburg;Antarctic sea-ice freshwater fluxes associated with freezing, transport, and melting;2016;ETH Zurich;ANTARTIC;CLIMATE CHANGE;CRYOSPHERIC SCIENCE;FORCING;FREEZING;FRESHWATER FLUX;MASS BALANCE;MELTING;PHYSICAL OCEANOGRAPHY;POLAR;SALINITY;SALT;SATELLITE;SEA ICE;SEA ICE DIVERGENCE;SEA ICE VOLUME;SOUTHERN OCEAN;TRANSPORT;F. Alexander Haumann;0000-0002-8218-977X;1982-03-01;en;Dataset;https://www.envidat.ch/dataset/10-16904-8;379128 bytes;1493303 bytes;260945 bytes;PDF;NetCDF4 CF-1.6;URL;1;Other (Non-Commercial);This data set provides estimates of annual fresh water fluxes related to sea-ice formation from ocean freezing and snow-ice formation, sea-ice melting, lateral transport of sea ice in the Southern Ocean over the period 1982 to 2008.It is derived from a mass balance calculation of local sea-ice volume change and divergence from satellite data and sea-ice reconstructions. The mass balance is calculated on a daily basis and fluxes are then integrated over the entire year, where a year is defined from March to February of the next year (i.e. from March 1982 to February 2009). This approach combines multiple products of sea-ice concentration (Cavalieri & Parkinson, 2008;Comiso, 1986; Meier et al., 2013), sea-ice thickness (Kurtz & Markus, 2012; Massonnet et al., 2013; Worby et al., 2008), and sea-ice drift (Fowler et al., 2013; Kwok 2005; Schwegmann et al., 2011). For a detailed description of the method see Haumann et al. (2016). The data set is derived to estimate large-scale (regional to basin-scale) fluxes on an annual basis. Our confidence is reduced on a grid cell basis, such as for single coastal polynyas, where the method and underlying data induce large, unknown uncertainties.\n\n_Disclaimer: This data set is free to use for any non-commercial purpose at the risk of the user and the authors do not take any liability on the use of the data set. The authors assembled the data set carefully and assessed accuracy, errors, and uncertainties. Please contact the authors if you find any issues._\n\n__Related publication__: http://www.nature.com/nature/journal/v537/n7618/full/nature19101.html (doi:10.1038/nature19101);-89.7 -180 -37 180;Southern Ocean",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "62778fc3-5a23-514c-b5d6-7b4b094f90bc",
-    "notes": [
-        "This data set provides estimates of annual fresh water fluxes related to sea-ice formation from ocean freezing and snow-ice formation, sea-ice melting, lateral transport of sea ice in the Southern Ocean over the period 1982 to 2008.It is derived from a mass balance calculation of local sea-ice volume change and divergence from satellite data and sea-ice reconstructions. The mass balance is calculated on a daily basis and fluxes are then integrated over the entire year, where a year is defined from March to February of the next year (i.e. from March 1982 to February 2009). This approach combines multiple products of sea-ice concentration (Cavalieri & Parkinson, 2008;Comiso, 1986; Meier et al., 2013), sea-ice thickness (Kurtz & Markus, 2012; Massonnet et al., 2013; Worby et al., 2008), and sea-ice drift (Fowler et al., 2013; Kwok 2005; Schwegmann et al., 2011). For a detailed description of the method see Haumann et al. (2016). The data set is derived to estimate large-scale (regional to basin-scale) fluxes on an annual basis. Our confidence is reduced on a grid cell basis, such as for single coastal polynyas, where the method and underlying data induce large, unknown uncertainties.\n\n_Disclaimer: This data set is free to use for any non-commercial purpose at the risk of the user and the authors do not take any liability on the use of the data set. The authors assembled the data set carefully and assessed accuracy, errors, and uncertainties. Please contact the authors if you find any issues._\n\n__Related publication__: http://www.nature.com/nature/journal/v537/n7618/full/nature19101.html (doi:10.1038/nature19101)"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:b16a0901-3abe-4da0-b61e-cdb80c59ba63"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-180,-89.7],[-180,-37],[180,-37],[180,-89.7],[-180,-89.7]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ANTARTIC"
-        },
-        {
-            "name": "CLIMATE CHANGE"
-        },
-        {
-            "name": "CRYOSPHERIC SCIENCE"
-        },
-        {
-            "name": "FORCING"
-        },
-        {
-            "name": "FREEZING"
-        },
-        {
-            "name": "FRESHWATER FLUX"
-        },
-        {
-            "name": "MASS BALANCE"
-        },
-        {
-            "name": "MELTING"
-        },
-        {
-            "name": "PHYSICAL OCEANOGRAPHY"
-        },
-        {
-            "name": "POLAR"
-        },
-        {
-            "name": "SALINITY"
-        },
-        {
-            "name": "SALT"
-        }
-    ],
-    "title": [
-        "Antarctic sea-ice freshwater fluxes associated with freezing, transport, and melting"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/6533555d-e0ff-5836-acec-fc84e0ef64f9.json b/oaitestdata/envidat-datacite/SET_1/json/6533555d-e0ff-5836-acec-fc84e0ef64f9.json
deleted file mode 100644
index 78388507..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/6533555d-e0ff-5836-acec-fc84e0ef64f9.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:0d321cd0-12f6-4f68-bb2c-30c2ea410d1f",
-    "MetadataAccess": [
-        "oai:envidat.ch:0d321cd0-12f6-4f68-bb2c-30c2ea410d1f"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/mass_of_needles_or_leaves_of_live_trees-49"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:0d321cd0-12f6-4f68-bb2c-30c2ea410d1f;2018-12-09T00:32:35Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Mass of needles or leaves of live trees;2014;Swiss Federal Research Institute WSL;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;BIOGEOGRAPHICAL REGION;CANTON;CONIFERS-BROADLEAVES;ECONOMIC REGION;GRID NFI4 2009-2013;MASS OF NEEDLES OR LEAVES OF LIVE TREES;NFI3;NFI4B;PRODUCTION REGION;PROTECTION FOREST REGION;TERRESTRIAL GRID NFI3;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/mass_of_needles_or_leaves_of_live_trees-49;URL;1.0;Other (Open);Dry weight (mass) of the needles and leaves of the living trees and shrubs  starting at 12 cm dbh.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "6533555d-e0ff-5836-acec-fc84e0ef64f9",
-    "notes": [
-        "Dry weight (mass) of the needles and leaves of the living trees and shrubs  starting at 12 cm dbh.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:0d321cd0-12f6-4f68-bb2c-30c2ea410d1f"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "MASS NEEDLES LEAVES LIVE TREES"
-        },
-        {
-            "name": "NFI"
-        },
-        {
-            "name": "NFIB"
-        },
-        {
-            "name": "PRODUCTION REGION"
-        },
-        {
-            "name": "PROTECTION FOREST REGION"
-        }
-    ],
-    "title": [
-        "Mass of needles or leaves of live trees"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/665f7851-055d-56bc-ae3c-e46a0acb6398.json b/oaitestdata/envidat-datacite/SET_1/json/665f7851-055d-56bc-ae3c-e46a0acb6398.json
deleted file mode 100644
index c0018431..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/665f7851-055d-56bc-ae3c-e46a0acb6398.json
+++ /dev/null
@@ -1,88 +0,0 @@
-{
-    "Contact": [
-        "Frank Techel"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/envidat.26",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "TXT"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:07dcd960-6197-4709-9a54-60407b4075ca",
-    "MetadataAccess": [
-        "oai:envidat.ch:07dcd960-6197-4709-9a54-60407b4075ca"
-    ],
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Geographica Helvetica"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/avalanche-fatalities-european-alps-1969-2015"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(45N-43N,5 E-6 E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Miha Pav\u0161ek",
-        "Patrick Nairz",
-        "Fr\u00e9d\u00e9ric Jarry",
-        "Mauro Valt",
-        "Susanna Mitterer",
-        "Frank Techel",
-        "Georg Kronthaler"
-    ],
-    "fulltext": "oai:envidat.ch:07dcd960-6197-4709-9a54-60407b4075ca;2018-12-09T00:31:19Z;10.16904/envidat.26;Frank Techel;0000-0001-5686-6127;WSL Institute for Snow and Avalanche Research SLF;Fr\u00e9d\u00e9ric Jarry;Association Nationale pour l'\u00c9tude de la Neige et des Avalanches, Grenoble, France;Georg Kronthaler;Lawinenwarndienst Bayern, Munich, Germany;Susanna Mitterer;\u00d6sterreichisches Kuratorium f\u00fcr alpine Sicherheit, Innsbruck, Austria;Patrick Nairz;Lawinenwarndienst Tirol, Innsbruck, Austria;Miha Pav\u0161ek;Anton Melik Geographical Institute, Research Centre of the Slovenian Academy of Sciences and Arts, Ljubljana, Slovenia;Mauro Valt;Centro Valanghe di Arabba, Arabba, Italy;Avalanche fatalities in the European Alps (1969/1970 - 2014/2015);2016;Geographica Helvetica;AVALANCHE ACCIDENT;AVALANCHE ACCIDENT STATISTICS;AVALANCHE FATALITIES;Frank Techel;0000-0001-5686-6127;WSL Institute for Snow and Avalanchre Research SLF;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/avalanche-fatalities-european-alps-1969-2015;753 bytes;TXT;1.0;Open Data Commons Open Database License (ODbL);During the last 45 years, about 100 people lost their lives in avalanches in the European Alps each year. Avalanche fatalities in settlements and on transportation corridors have considerably decreased since the 1970s. In contrast, the number of avalanche fatalities during recreational activities away from avalanche-secured terrain doubled between the 1960s and 1980s and has remained relatively stable since, despite a continuing strong increase in winter backcountry recreational activities.\n\nData complementing Figure 2 in:  \n_\"Avalanche fatalities in the European Alps: long-term trends and statistics\"_, by Techel, F., Jarry, F., Kronthaler, G., Mitterer, S., Nairz, P., Pav\u0161ek, M., Valt, M., and Darms, G.\n\nData description:  \nplease refer to section 2 (Data and Methods) in the mentioned publication;44.7779358963 5.1416015625 43.0367758576 5.888671875;European Alps",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "665f7851-055d-56bc-ae3c-e46a0acb6398",
-    "notes": [
-        "During the last 45 years, about 100 people lost their lives in avalanches in the European Alps each year. Avalanche fatalities in settlements and on transportation corridors have considerably decreased since the 1970s. In contrast, the number of avalanche fatalities during recreational activities away from avalanche-secured terrain doubled between the 1960s and 1980s and has remained relatively stable since, despite a continuing strong increase in winter backcountry recreational activities.\n\nData complementing Figure 2 in:  \n_\"Avalanche fatalities in the European Alps: long-term trends and statistics\"_, by Techel, F., Jarry, F., Kronthaler, G., Mitterer, S., Nairz, P., Pav\u0161ek, M., Valt, M., and Darms, G.\n\nData description:  \nplease refer to section 2 (Data and Methods) in the mentioned publication"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:07dcd960-6197-4709-9a54-60407b4075ca"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.1416015625,44.7779358963],[5.1416015625,43.0367758576],[5.888671875,43.0367758576],[5.888671875,44.7779358963],[5.1416015625,44.7779358963]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "AVALANCHE ACCIDENT"
-        },
-        {
-            "name": "AVALANCHE ACCIDENT STATISTICS"
-        },
-        {
-            "name": "AVALANCHE FATALITIES"
-        }
-    ],
-    "title": [
-        "Avalanche fatalities in the European Alps (1969/1970 - 2014/2015)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/6849f1ea-d016-5d74-ad2f-316013a22f9a.json b/oaitestdata/envidat-datacite/SET_1/json/6849f1ea-d016-5d74-ad2f-316013a22f9a.json
deleted file mode 100644
index 5ba2e3dd..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/6849f1ea-d016-5d74-ad2f-316013a22f9a.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:1eea4a98-b461-4396-ad65-314f6b874fc8",
-    "MetadataAccess": [
-        "oai:envidat.ch:1eea4a98-b461-4396-ad65-314f6b874fc8"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/bole_wood_mass_of_live_trees-50"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:1eea4a98-b461-4396-ad65-314f6b874fc8;2018-12-09T00:31:38Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Bole wood mass of live trees;2014;Swiss Federal Research Institute WSL;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;BIOGEOGRAPHICAL REGION;BOLE WOOD MASS OF LIVE TREES;CANTON;CONIFERS-BROADLEAVES;ECONOMIC REGION;GRID NFI4 2009-2013;NFI3;NFI4B;PRODUCTION REGION;PROTECTION FOREST REGION;TERRESTRIAL GRID NFI3;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/bole_wood_mass_of_live_trees-50;URL;1.0;Other (Open);Dry weight (mass) of the stemwood with bark of the living trees and shrubs  starting at 12 cm dbh.   The correction for bias with the sample Tarif trees may be so drastic that it results in negative values with small numbers of trees.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "6849f1ea-d016-5d74-ad2f-316013a22f9a",
-    "notes": [
-        "Dry weight (mass) of the stemwood with bark of the living trees and shrubs  starting at 12 cm dbh.   The correction for bias with the sample Tarif trees may be so drastic that it results in negative values with small numbers of trees.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:1eea4a98-b461-4396-ad65-314f6b874fc8"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "BOLE WOOD MASS LIVE TREES"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "NFI"
-        },
-        {
-            "name": "NFIB"
-        },
-        {
-            "name": "PRODUCTION REGION"
-        },
-        {
-            "name": "PROTECTION FOREST REGION"
-        }
-    ],
-    "title": [
-        "Bole wood mass of live trees"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/6a4c4127-c2fe-51d2-ba9b-c2ba9cdd8612.json b/oaitestdata/envidat-datacite/SET_1/json/6a4c4127-c2fe-51d2-ba9b-c2ba9cdd8612.json
deleted file mode 100644
index bcfdcc75..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/6a4c4127-c2fe-51d2-ba9b-c2ba9cdd8612.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:c94c4155-a05c-4520-82a5-42bb142f612c",
-    "MetadataAccess": [
-        "oai:envidat.ch:c94c4155-a05c-4520-82a5-42bb142f612c"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/total_stem_number_by_cause_of_damage-218"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:c94c4155-a05c-4520-82a5-42bb142f612c;2018-12-09T00:33:21Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Total stem number by cause of damage;2014;Swiss Federal Research Institute WSL;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;ALTITUDE 200 M CLASS;BIOGEOGRAPHICAL REGION;CANTON;CAUSE OF DAMAGE OF SINGLE TREE;ECONOMIC REGION;GRID NFI4 2009-2013;NFI3;NFI4B;PRODUCTION REGION;PROTECTION FOREST REGION;SLOPE 20 CLASSES;TERRESTRIAL GRID NFI3;TOTAL STEM NUMBER;TOTAL STEM NUMBER BY CAUSE OF DAMAGE;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/total_stem_number_by_cause_of_damage-218;URL;1.0;Other (Open);Number of all living and dead trees and shrubs  starting at 12 cm dbh where a particular cause of damage (including no damage, dead or lying) was determined. One tree may have damage with more than one type of origin, which means it may contribute to the total number of stems with damage with several different types of origin.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "6a4c4127-c2fe-51d2-ba9b-c2ba9cdd8612",
-    "notes": [
-        "Number of all living and dead trees and shrubs  starting at 12 cm dbh where a particular cause of damage (including no damage, dead or lying) was determined. One tree may have damage with more than one type of origin, which means it may contribute to the total number of stems with damage with several different types of origin.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:c94c4155-a05c-4520-82a5-42bb142f612c"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ALTITUDE M CLASS"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "CAUSE DAMAGE SINGLE TREE"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "NFI"
-        },
-        {
-            "name": "NFIB"
-        },
-        {
-            "name": "PRODUCTION REGION"
-        }
-    ],
-    "title": [
-        "Total stem number by cause of damage"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/6b8658d2-ef0b-5ba6-91cd-2855f5f941ed.json b/oaitestdata/envidat-datacite/SET_1/json/6b8658d2-ef0b-5ba6-91cd-2855f5f941ed.json
deleted file mode 100644
index f51f91c6..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/6b8658d2-ef0b-5ba6-91cd-2855f5f941ed.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:4567bd60-6047-4f07-ade5-ac2c7440d8ef",
-    "MetadataAccess": [
-        "oai:envidat.ch:4567bd60-6047-4f07-ade5-ac2c7440d8ef"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/yield_and_mortality-13"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:4567bd60-6047-4f07-ade5-ac2c7440d8ef;2018-12-09T00:33:41Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Yield and mortality;2014;Swiss Federal Research Institute WSL;14 X 14 KM GRID;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;ALTITUDE 400 M CLASSES;ALTITUDINAL VEGETATION ZONE;BIOGEOGRAPHICAL REGION;CONIFERS-BROADLEAVES;ECONOMIC REGION;FOREST TYPE 12 CLASSES;GRID NFI4 2009-2013;INCREMENT;LOWER-HIGHER ALTITUDINAL ZONES;MAIN TREE SPECIES;NFI1-NFI2;NFI2-NFI3;NFI3-NFI4B;OWNERSHIP;PRODUCTION REGION;PROTECTION FOREST REGION;STAGE OF STAND DEVELOPMENT;YIELD AND MORTALITY;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/yield_and_mortality-13;URL;1.0;Other (Open);Volume of stemwood with bark of all trees and shrubs  starting at 12 cm dbh that were felled, died or disappeared between two inventories. The correction for bias with the sample Tarif trees may be so drastic that it results in negative values with small numbers of trees.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "6b8658d2-ef0b-5ba6-91cd-2855f5f941ed",
-    "notes": [
-        "Volume of stemwood with bark of all trees and shrubs  starting at 12 cm dbh that were felled, died or disappeared between two inventories. The correction for bias with the sample Tarif trees may be so drastic that it results in negative values with small numbers of trees.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:4567bd60-6047-4f07-ade5-ac2c7440d8ef"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "X KM GRID"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ALTITUDE M CLASSES"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "FOREST TYPE CLASSES"
-        }
-    ],
-    "title": [
-        "Yield and mortality"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/6bd42527-0a4f-563f-88ed-999b1c8ded9e.json b/oaitestdata/envidat-datacite/SET_1/json/6bd42527-0a4f-563f-88ed-999b1c8ded9e.json
deleted file mode 100644
index a7ede751..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/6bd42527-0a4f-563f-88ed-999b1c8ded9e.json
+++ /dev/null
@@ -1,89 +0,0 @@
-{
-    "Contact": [
-        "Ernesto Trujillo"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/9",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "DAT",
-        "DOC",
-        "ZIP"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:c88b82ed-d54e-43e6-b4e4-7ae1ee06a014",
-    "MetadataAccess": [
-        "oai:envidat.ch:c88b82ed-d54e-43e6-b4e4-7ae1ee06a014"
-    ],
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "\u00c9cole polytechnique f\u00e9d\u00e9rale de Lausanne"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/10-16904-9"
-    ],
-    "ResourceType": [
-        "Post-processed laser scans"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(66S-63S,114E-122E)",
-    "TempCoverageBegin": 63482093999,
-    "TempCoverageEnd": 63482093999,
-    "TemporalCoverage": " point in time : 2012-09-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2012-09-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2012-09-01T11:59:59Z",
-    "author": [
-        "Michael Lehning",
-        "Rapha\u00ebl Hoesli",
-        "K. Leonard",
-        "Ernesto Trujillo",
-        "T. Maksym"
-    ],
-    "fulltext": "oai:envidat.ch:c88b82ed-d54e-43e6-b4e4-7ae1ee06a014;2018-07-06T22:08:12Z;10.16904/9;Ernesto Trujillo;EPFL, SLF;Rapha\u00ebl Hoesli;EPFL;T. Maksym;Woods Hole Oceanographic Institute;Michael Lehning;EPFL, SLF;K. Leonard;EPFL, SLF, University of Colorado, Boulder;High resolution sea ice surface topography from the SIPEX-2 expedition, East Antarctica, 2012;Post-processing of the terrestrial laser scans of Antarctic Sea Ice from the Sea Ice Physics and Ecosystems Experiment;2016;\u00c9cole polytechnique f\u00e9d\u00e9rale de Lausanne;POLAR;SEA ICE;SEA ICE ELEVATION;Ernesto Trujillo;EPFL, SLF;2012-09-01;en;Post-processed laser scans;https://www.envidat.ch/dataset/10-16904-9;DOC;DAT;ZIP;1;Open Data Commons Open Database License (ODbL);This dataset comprises of a post-processed set of terrestrial laser scans (TLS\u2019s) of Antarctic sea ice obtained during the Sea Ice Physics and Ecosystem Experiment-2 (SIPEX-2, http://seaice.acecrc.org.au/sipex2012/) in September-November 2012. The post-processing steps include the registration of the individual scans into a single 3-dimensional point cloud, the removal of unwanted noise caused by particles in the air (i.e., snow crystals), and the final generation of surface grids based on the cleaned individual point returns. The final product includes the \u2018xyz\u2019 coordinates of the individual point measurements, and gridded surfaces covering study areas of 100m x 100 m, and at resolutions of 0.01 m, 0.1 m, 0.25 m, 0.5 m and 1 m for each of the survey dates. Additionally, subgrid statistics that include the mean elevation, standard deviation, minimum and maximum elevations, range, and number of point returns in each gridcell are generated. The final product is provided in space-delimited text files, with the surface grids provided in Digital Terrain Model (DTM) format ready for visualization in any GIS software.\n\n###How to cite:\nPlease also cite the original publication when using this data set.: Trujillo, E., K. Leonard, T. Maksym, and M. Lehning (2016), Changes in snow distribution and surface topography following a snowstorm on Antarctic sea ice, J. Geophys. Res. Earth Surf., 121, doi:[10.1002/2016JF003893](https://dx.doi.org/10.1002/2016JF003893).;-66 114 -63 122;Antarctica, Southern Ocean [-66 114 -63 122]",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "6bd42527-0a4f-563f-88ed-999b1c8ded9e",
-    "notes": [
-        "This dataset comprises of a post-processed set of terrestrial laser scans (TLS\u2019s) of Antarctic sea ice obtained during the Sea Ice Physics and Ecosystem Experiment-2 (SIPEX-2, http://seaice.acecrc.org.au/sipex2012/) in September-November 2012. The post-processing steps include the registration of the individual scans into a single 3-dimensional point cloud, the removal of unwanted noise caused by particles in the air (i.e., snow crystals), and the final generation of surface grids based on the cleaned individual point returns. The final product includes the \u2018xyz\u2019 coordinates of the individual point measurements, and gridded surfaces covering study areas of 100m x 100 m, and at resolutions of 0.01 m, 0.1 m, 0.25 m, 0.5 m and 1 m for each of the survey dates. Additionally, subgrid statistics that include the mean elevation, standard deviation, minimum and maximum elevations, range, and number of point returns in each gridcell are generated. The final product is provided in space-delimited text files, with the surface grids provided in Digital Terrain Model (DTM) format ready for visualization in any GIS software.\n\n###How to cite:\nPlease also cite the original publication when using this data set.: Trujillo, E., K. Leonard, T. Maksym, and M. Lehning (2016), Changes in snow distribution and surface topography following a snowstorm on Antarctic sea ice, J. Geophys. Res. Earth Surf., 121, doi:[10.1002/2016JF003893](https://dx.doi.org/10.1002/2016JF003893)."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:c88b82ed-d54e-43e6-b4e4-7ae1ee06a014"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[114,-66],[114,-63],[122,-63],[122,-66],[114,-66]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "POLAR"
-        },
-        {
-            "name": "SEA ICE"
-        },
-        {
-            "name": "SEA ICE ELEVATION"
-        }
-    ],
-    "title": [
-        "High resolution sea ice surface topography from the SIPEX-2 expedition, East Antarctica, 2012",
-        "Post-processing of the terrestrial laser scans of Antarctic Sea Ice from the Sea Ice Physics and Ecosystems Experiment"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/6d50939c-37d0-59fd-b367-cfa96c6e89be.json b/oaitestdata/envidat-datacite/SET_1/json/6d50939c-37d0-59fd-b367-cfa96c6e89be.json
deleted file mode 100644
index 383e91b8..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/6d50939c-37d0-59fd-b367-cfa96c6e89be.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:c98e40e4-4df6-4a6f-af45-b9422ea52fc7",
-    "MetadataAccess": [
-        "oai:envidat.ch:c98e40e4-4df6-4a6f-af45-b9422ea52fc7"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/volume_of_dead_wood-24"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:c98e40e4-4df6-4a6f-af45-b9422ea52fc7;2018-12-09T00:33:36Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Volume of dead wood;2014;Swiss Federal Research Institute WSL;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;ALTITUDINAL VEGETATION ZONE;ALTITUDINAL VEGETATION ZONE 3 CLASSES;BIOGEOGRAPHICAL REGION;CANTON;CONIFERS-BROADLEAVES;ECONOMIC REGION;EXTENT OF AREAL DAMAGE 10 CLASSES;FOREST DISTRICT AS OF 2013;GRID NFI4 2009-2013;LOWER-HIGHER ALTITUDINAL ZONES;MAIN TREE SPECIES;MECHANICAL STRENGTH OF WOOD;NFI2;NFI3;NFI4B;OWNERSHIP;PRIMARY FOREST FUNCTION NFI4 NATURE PROTECTION;PRODUCTION REGION;PROTECTION FOREST REGION;REMAINING BARK ON DEAD WOOD 3 CLASSES;TERRESTRIAL GRID NFI2;TERRESTRIAL GRID NFI3;TREE STATE STANDING-LYING;VOLUME OF DEAD WOOD;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/volume_of_dead_wood-24;URL;1.0;Other (Open);Volume of stemwood with bark of all dead trees and shrubs (standing and lying)  starting at 12 cm dbh.  Unlike this theme\u00a0, the \"Amount of deadwood according to the method of NFI3\" includes all lying deadwood  starting at 7 cm in diameter.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "6d50939c-37d0-59fd-b367-cfa96c6e89be",
-    "notes": [
-        "Volume of stemwood with bark of all dead trees and shrubs (standing and lying)  starting at 12 cm dbh.  Unlike this theme\u00a0, the \"Amount of deadwood according to the method of NFI3\" includes all lying deadwood  starting at 7 cm in diameter.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:c98e40e4-4df6-4a6f-af45-b9422ea52fc7"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE CLASSES"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "EXTENT AREAL DAMAGE CLASSES"
-        },
-        {
-            "name": "FOREST DISTRICT"
-        },
-        {
-            "name": "GRID NFI -"
-        }
-    ],
-    "title": [
-        "Volume of dead wood"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/6e018c60-e0df-57c0-9730-acbbb5d476c4.json b/oaitestdata/envidat-datacite/SET_1/json/6e018c60-e0df-57c0-9730-acbbb5d476c4.json
deleted file mode 100644
index 3502c09b..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/6e018c60-e0df-57c0-9730-acbbb5d476c4.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:03379f2b-1d72-44ef-87da-52888bf849f4",
-    "MetadataAccess": [
-        "oai:envidat.ch:03379f2b-1d72-44ef-87da-52888bf849f4"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/number_of_young_forest_plants_by_damage-209"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:03379f2b-1d72-44ef-87da-52888bf849f4;2018-12-09T00:32:51Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Number of young forest plants by damage;2014;Swiss Federal Research Institute WSL;ACCESSIBLE FOREST WITHOUT SHRUB FOREST WITH YOUNG FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST WITH YOUNG FOREST NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST WITH YOUNG FOREST NFI3-NFI4;BIOGEOGRAPHICAL REGION;CANTON;DAMAGE OF YOUNG FOREST PLANT;ECONOMIC REGION;GRID NFI4 2009-2013;NFI3;NFI4B;NUMBER OF YOUNG FOREST PLANTS BY DAMAGE;PRODUCTION REGION;PROTECTION FOREST REGION;TERRESTRIAL GRID NFI3;YOUNG FOREST PLANT CLASS;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/number_of_young_forest_plants_by_damage-209;URL;1.0;Other (Open);Number of regeneration trees  starting at 10 cm height up to 11.9 cm dbh with a particular type of damage or with no damage. The attribute is recorded by targeting the next regeneration tree in the centre of the subplot during NFI\u2019s regeneration survey. A regeneration tree may have more than one type of damage, which means it may contribute to the total number of regeneration trees for several different types of damage.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "6e018c60-e0df-57c0-9730-acbbb5d476c4",
-    "notes": [
-        "Number of regeneration trees  starting at 10 cm height up to 11.9 cm dbh with a particular type of damage or with no damage. The attribute is recorded by targeting the next regeneration tree in the centre of the subplot during NFI\u2019s regeneration survey. A regeneration tree may have more than one type of damage, which means it may contribute to the total number of regeneration trees for several different types of damage.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:03379f2b-1d72-44ef-87da-52888bf849f4"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST YOUNG FOREST"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "DAMAGE YOUNG FOREST PLANT"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "NFI"
-        },
-        {
-            "name": "NFIB"
-        },
-        {
-            "name": "NUMBER YOUNG FOREST PLANTS DAMAGE"
-        },
-        {
-            "name": "PRODUCTION REGION"
-        },
-        {
-            "name": "PROTECTION FOREST REGION"
-        },
-        {
-            "name": "TERRESTRIAL GRID NFI"
-        }
-    ],
-    "title": [
-        "Number of young forest plants by damage"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/6fe93b16-13e1-5b6c-91f6-a0b06726ca20.json b/oaitestdata/envidat-datacite/SET_1/json/6fe93b16-13e1-5b6c-91f6-a0b06726ca20.json
deleted file mode 100644
index bfafeced..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/6fe93b16-13e1-5b6c-91f6-a0b06726ca20.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:0bdfc40d-73ae-48e1-b7ac-aecec9c3af87",
-    "MetadataAccess": [
-        "oai:envidat.ch:0bdfc40d-73ae-48e1-b7ac-aecec9c3af87"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/volume_of_bole_wood_hg_2000-167"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:0bdfc40d-73ae-48e1-b7ac-aecec9c3af87;2018-12-09T00:33:33Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Volume of bole wood (HG 2000);2014;Swiss Federal Research Institute WSL;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;BIOGEOGRAPHICAL REGION;CANTON;CONIFERS-BROADLEAVES;ECONOMIC REGION;GRID NFI4 2009-2013;MAIN TREE SPECIES;NFI3;PRODUCTION REGION;PROTECTION FOREST REGION;TERRESTRIAL GRID NFI3;TIMBER ASSORTMENT CLASSES HG 2000;TREE SPECIES 5 CLASSES;TYPE OF ASSORTMENT;VOLUME OF BOLE WOOD HG 2000;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/volume_of_bole_wood_hg_2000-167;URL;1.0;Other (Open);Wood volume of the stem without bark or stump at least 7 cm in diameter (limit of coarse wood) of all trees and shrubs  starting at 12 cm dbh, based on the stem-form functions according to Kaufmann (2001). The definition of the assortment is based on the 2000 edition of the Trading Practices (Handelsgebr\u00e4uchen Ausgabe 2000\u00a0).\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "6fe93b16-13e1-5b6c-91f6-a0b06726ca20",
-    "notes": [
-        "Wood volume of the stem without bark or stump at least 7 cm in diameter (limit of coarse wood) of all trees and shrubs  starting at 12 cm dbh, based on the stem-form functions according to Kaufmann (2001). The definition of the assortment is based on the 2000 edition of the Trading Practices (Handelsgebr\u00e4uchen Ausgabe 2000\u00a0).\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:0bdfc40d-73ae-48e1-b7ac-aecec9c3af87"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "MAIN TREE SPECIES"
-        },
-        {
-            "name": "NFI"
-        },
-        {
-            "name": "PRODUCTION REGION"
-        },
-        {
-            "name": "PROTECTION FOREST REGION"
-        }
-    ],
-    "title": [
-        "Volume of bole wood (HG 2000)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/70c4abb3-5678-5f35-8bb8-877e0e57bd0a.json b/oaitestdata/envidat-datacite/SET_1/json/70c4abb3-5678-5f35-8bb8-877e0e57bd0a.json
deleted file mode 100644
index 754a93fe..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/70c4abb3-5678-5f35-8bb8-877e0e57bd0a.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Christoph Marty"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "PDF",
-        "SMET",
-        "TXT"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:99a619e2-5c9e-48c5-bcc6-6d8bab8b5709",
-    "MetadataAccess": [
-        "oai:envidat.ch:99a619e2-5c9e-48c5-bcc6-6d8bab8b5709"
-    ],
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avalanche Research SLF"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/asrb-vf"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N,10E)",
-    "TempCoverageBegin": 62956094399,
-    "TempCoverageEnd": 62956094399,
-    "TemporalCoverage": " point in time : 1996-01-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1996-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1996-01-01T11:59:59Z",
-    "author": [
-        "Christoph Marty"
-    ],
-    "fulltext": "oai:envidat.ch:99a619e2-5c9e-48c5-bcc6-6d8bab8b5709;2018-12-09T00:24:29Z;Christoph Marty;WSL Institute for Snow and Avalanche Research SLF;ASRB_WFJVF: Shortwave and longwave radiation measurements (2 min) at the Weissfluhjoch research site, Davos;2016;WSL Institute for Snow and Avalanche Research SLF;LONGWAVE RADIATION;SHORTWAVE RADIATION;Christoph Marty;WSL Institute for Snow and Avalanche Research SLF;1996-01-01;en;Dataset;https://www.envidat.ch/dataset/asrb-vf;129587 bytes;1364039 bytes;1166 bytes;SMET;PDF;TXT;1.0;Open Data Commons Open Database License (ODbL);Incoming and outgoing  shortwave and longwave 2 min radiation measurements at the Weissfluhjoch research site, Davos, CH. The experimental site at the Weissfluhjoch (WFJ, 46.83 N, 9.81 E) is located at an altitude of 2540 m in the Swiss Alps near Davos. During the winter months, almost all precipitation falls as snow at this altitude. As a consequence, a continuous seasonal snow cover builds up every winter, with a maximum snow height ranging from 153\u2013366 cm over the period 1934\u20132012. The measurement site is located in an almost flat part of a southeast oriented slope.\n\n###References\n1. Marty, C., Philipona, R., Frohlich, C., Ohmura, A.. Altitude dependence of surface radiation fluxes and cloud forcing in the alps: results from the alpine surface radiation budget network. 2002. Theoretical and Applied Climatology. Volume 72. Issue 3-4. 137-155. http://dx.doi.org/10.1007/s007040200019. 10.1007/s007040200019.\n2. Christoph Marty. Surface Radiation, Cloud Forcing and Greenhouse Effect in the Alps. 2000. Institute fuer Klimaforschung ETH. Zuercher Klima-Schriften. Volume 79. http://e-collection.library.ethz.ch/eserv/eth:23491/eth-23491-01.pdf.;46.829631 9.809204",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "70c4abb3-5678-5f35-8bb8-877e0e57bd0a",
-    "notes": [
-        "Incoming and outgoing  shortwave and longwave 2 min radiation measurements at the Weissfluhjoch research site, Davos, CH. The experimental site at the Weissfluhjoch (WFJ, 46.83 N, 9.81 E) is located at an altitude of 2540 m in the Swiss Alps near Davos. During the winter months, almost all precipitation falls as snow at this altitude. As a consequence, a continuous seasonal snow cover builds up every winter, with a maximum snow height ranging from 153\u2013366 cm over the period 1934\u20132012. The measurement site is located in an almost flat part of a southeast oriented slope.\n\n###References\n1. Marty, C., Philipona, R., Frohlich, C., Ohmura, A.. Altitude dependence of surface radiation fluxes and cloud forcing in the alps: results from the alpine surface radiation budget network. 2002. Theoretical and Applied Climatology. Volume 72. Issue 3-4. 137-155. http://dx.doi.org/10.1007/s007040200019. 10.1007/s007040200019.\n2. Christoph Marty. Surface Radiation, Cloud Forcing and Greenhouse Effect in the Alps. 2000. Institute fuer Klimaforschung ETH. Zuercher Klima-Schriften. Volume 79. http://e-collection.library.ethz.ch/eserv/eth:23491/eth-23491-01.pdf."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:99a619e2-5c9e-48c5-bcc6-6d8bab8b5709"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[9.809204,46.829631],[9.809204,46.829631],[9.809204,46.829631],[9.809204,46.829631],[9.809204,46.829631]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "LONGWAVE RADIATION"
-        },
-        {
-            "name": "SHORTWAVE RADIATION"
-        }
-    ],
-    "title": [
-        "ASRB_WFJVF: Shortwave and longwave radiation measurements (2 min) at the Weissfluhjoch research site, Davos"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/77b0bf16-5cc7-5844-ad5f-e89dfd11ac29.json b/oaitestdata/envidat-datacite/SET_1/json/77b0bf16-5cc7-5844-ad5f-e89dfd11ac29.json
deleted file mode 100644
index 1b373593..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/77b0bf16-5cc7-5844-ad5f-e89dfd11ac29.json
+++ /dev/null
@@ -1,89 +0,0 @@
-{
-    "Contact": [
-        "Franziska Gerber"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/envidat.50",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "ZIP"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:68536bc6-0990-41c0-a06f-21b19c0f2ffe",
-    "MetadataAccess": [
-        "oai:envidat.ch:68536bc6-0990-41c0-a06f-21b19c0f2ffe"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Laboratory of Cryospheric Sciences, School of Architecture and Civil Engineering, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/dischmex-high-resolution-wrf-simulations-in-complex-alpine-terrain-and-station-measurements"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(46N-47N,9 E-11E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Rebecca Mott",
-        "Franziska Gerber",
-        "Varun Sharma",
-        "Michael Lehning",
-        "Megan Daniels"
-    ],
-    "fulltext": "oai:envidat.ch:68536bc6-0990-41c0-a06f-21b19c0f2ffe;2018-12-09T00:31:41Z;10.16904/envidat.50;Franziska Gerber;CRYOS, EPFL; WSL-SLF;Varun Sharma;CRYOS, EPFL;Rebecca Mott;KIT/IMK_IFU; WSL-SLF;Megan Daniels;unaffiliated;Michael Lehning;CRYOS, EPFL; WSL-SLF;DISCHMEX - High-resolution WRF simulations in complex alpine terrain and station measurements;2018;Laboratory of Cryospheric Sciences, School of Architecture and Civil Engineering, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland;COMPLEX TERRAIN;COSMO-WRF;OROGRAPHIC PRECIPITATION;PRECIPITATION VARIABILITY;Franziska Gerber;Laboratory of Cryospheric Sciences, School of Architecture and Civil Engineering, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland and WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/dischmex-high-resolution-wrf-simulations-in-complex-alpine-terrain-and-station-measurements;1161085 bytes;ZIP;1.0;Open Data Commons Open Database License (ODbL);The data presented here corresponds to the publication \"Spatial variability in snow precipitation and accumulation in COSMO-WRF simulations and radar estimations over complex terrain\" (Gerber et al., 2018a), which investigates the precipitation variability of snow precipitation in the central northern part of the Grisons (CH) and the publication \"The importance of near-surface winter precipitation processes in complex alpine terrain\" (Gerber et al., 2018b). The dataset contains:\n\n* WRFsimulations: WRF simulation output for simulations with 4x (14x) terrain smoothing with an output timestep of 30 min/5 min and horizontal grid spacings of 1350 m, 450 m, 150 m and 50 m (currently: data available upon request).\n* StationData: Meteorological station data of 18 meteorological stations in the central northern part of the Grisons with 30 minute resolution for the period 1 January 2016 till 1 May 2016.\n\nFor more details about the simulation and observation data, see Gerber et al., 2018 and Gerber and Sharma (2018).\n\n__Publications:__\n\nGerber, F., Besic, N., Sharma, V., Mott, R., Daniels, M., Gabella, M., Berne, A., Germann, U., and Lehning, M.: Spatial variability in snow precipitation and accumulation in COSMO-WRF simulations and radar estimations over complex terrain, The Cryosphere, doi:10.5194/tc-12-3137-2018, 2018.\n\nGerber, F., Mott, R. and Lehning, M.: The importance of near-surface winter precipitation processes in complex alpine terrain, Journal of Hydrometeorology, in review, 2018.\n\nGerber, F., and Sharma, V.:  Running COSMO-WRF on very-high resolution over complex terrain. Laboratory of Cryospheric Sciences CRYOS, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne EPFL, Lausanne, Switzerland. doi:10.16904/envidat.35, 2018.;46.3969575109 9.40704345703 47.1643219976 10.5661010742;central northern part of the Grisons",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "77b0bf16-5cc7-5844-ad5f-e89dfd11ac29",
-    "notes": [
-        "The data presented here corresponds to the publication \"Spatial variability in snow precipitation and accumulation in COSMO-WRF simulations and radar estimations over complex terrain\" (Gerber et al., 2018a), which investigates the precipitation variability of snow precipitation in the central northern part of the Grisons (CH) and the publication \"The importance of near-surface winter precipitation processes in complex alpine terrain\" (Gerber et al., 2018b). The dataset contains:\n\n* WRFsimulations: WRF simulation output for simulations with 4x (14x) terrain smoothing with an output timestep of 30 min/5 min and horizontal grid spacings of 1350 m, 450 m, 150 m and 50 m (currently: data available upon request).\n* StationData: Meteorological station data of 18 meteorological stations in the central northern part of the Grisons with 30 minute resolution for the period 1 January 2016 till 1 May 2016.\n\nFor more details about the simulation and observation data, see Gerber et al., 2018 and Gerber and Sharma (2018).\n\n__Publications:__\n\nGerber, F., Besic, N., Sharma, V., Mott, R., Daniels, M., Gabella, M., Berne, A., Germann, U., and Lehning, M.: Spatial variability in snow precipitation and accumulation in COSMO-WRF simulations and radar estimations over complex terrain, The Cryosphere, doi:10.5194/tc-12-3137-2018, 2018.\n\nGerber, F., Mott, R. and Lehning, M.: The importance of near-surface winter precipitation processes in complex alpine terrain, Journal of Hydrometeorology, in review, 2018.\n\nGerber, F., and Sharma, V.:  Running COSMO-WRF on very-high resolution over complex terrain. Laboratory of Cryospheric Sciences CRYOS, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne EPFL, Lausanne, Switzerland. doi:10.16904/envidat.35, 2018."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:68536bc6-0990-41c0-a06f-21b19c0f2ffe"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[9.40704345703,46.3969575109],[9.40704345703,47.1643219976],[10.5661010742,47.1643219976],[10.5661010742,46.3969575109],[9.40704345703,46.3969575109]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "COMPLEX TERRAIN"
-        },
-        {
-            "name": "COSMO-WRF"
-        },
-        {
-            "name": "OROGRAPHIC PRECIPITATION"
-        },
-        {
-            "name": "PRECIPITATION VARIABILITY"
-        }
-    ],
-    "title": [
-        "DISCHMEX - High-resolution WRF simulations in complex alpine terrain and station measurements"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/7c940496-db15-57dd-9ed6-4a1345696f7a.json b/oaitestdata/envidat-datacite/SET_1/json/7c940496-db15-57dd-9ed6-4a1345696f7a.json
deleted file mode 100644
index 22314681..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/7c940496-db15-57dd-9ed6-4a1345696f7a.json
+++ /dev/null
@@ -1,94 +0,0 @@
-{
-    "Contact": [
-        "Peter Bebi"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/envidat.43",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "JPEG",
-        "SMET",
-        "TXT",
-        "PNG"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:938e0cc0-0f75-41da-a358-679f27c254d4",
-    "MetadataAccess": [
-        "oai:envidat.ch:938e0cc0-0f75-41da-a358-679f27c254d4"
-    ],
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avalanche Research SLF"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/stillberg-climate"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N,10E)",
-    "TempCoverageBegin": 62293406399,
-    "TempCoverageEnd": 62293406399,
-    "TemporalCoverage": " point in time : 1975-01-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1975-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1975-01-01T11:59:59Z",
-    "author": [
-        "Peter Bebi"
-    ],
-    "fulltext": "oai:envidat.ch:938e0cc0-0f75-41da-a358-679f27c254d4;2018-07-18T13:33:14Z;10.16904/envidat.43;Peter Bebi;WSL Institute for Snow and Avalanche Research SLF;Long-term meteorological and snow station at 2090 m a.s.l., Stillberg, Davos, Switzerland (1975 - present);2016;WSL Institute for Snow and Avalanche Research SLF;AIR TEMPERATURE;HUMIDITY;LONGWAVE RADIATION;PRECIPITATION AMOUNT;SHORTWAVE RADIATION;SNOW DEPTH;Peter Bebi;WSL;1975-01-01;en;Dataset;https://www.envidat.ch/dataset/stillberg-climate;SMET;TXT;PNG;JPEG;1.0;Open Data Commons Open Database License (ODbL);Longterm meteorological and snow station on a steep (c. 40 degrees) North-East exposed slope at 2090 m a.s.l above  Davos, Switzerland. Established 1975 and ongoing measurements made, although instruments have changed during this period. The station is located within a experimental plantation that serves as avalanche protection to downslope communities as well as a unique site for treeline dynamics research.;46.773573 9.86716;Switzerland, Davos",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "7c940496-db15-57dd-9ed6-4a1345696f7a",
-    "notes": [
-        "Longterm meteorological and snow station on a steep (c. 40 degrees) North-East exposed slope at 2090 m a.s.l above  Davos, Switzerland. Established 1975 and ongoing measurements made, although instruments have changed during this period. The station is located within a experimental plantation that serves as avalanche protection to downslope communities as well as a unique site for treeline dynamics research."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:938e0cc0-0f75-41da-a358-679f27c254d4"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[9.86716,46.773573],[9.86716,46.773573],[9.86716,46.773573],[9.86716,46.773573],[9.86716,46.773573]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "AIR TEMPERATURE"
-        },
-        {
-            "name": "HUMIDITY"
-        },
-        {
-            "name": "LONGWAVE RADIATION"
-        },
-        {
-            "name": "PRECIPITATION AMOUNT"
-        },
-        {
-            "name": "SHORTWAVE RADIATION"
-        },
-        {
-            "name": "SNOW DEPTH"
-        }
-    ],
-    "title": [
-        "Long-term meteorological and snow station at 2090 m a.s.l., Stillberg, Davos, Switzerland (1975 - present)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/7f9c7de0-f72d-5bc3-894b-10685896719e.json b/oaitestdata/envidat-datacite/SET_1/json/7f9c7de0-f72d-5bc3-894b-10685896719e.json
deleted file mode 100644
index cca4c37b..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/7f9c7de0-f72d-5bc3-894b-10685896719e.json
+++ /dev/null
@@ -1,113 +0,0 @@
-{
-    "Contact": [
-        "Saskia Gindraux"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/envidat.48",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "PDF",
-        ".zip"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:ce722112-0768-4f79-a65b-3409af2a62e8",
-    "MetadataAccess": [
-        "oai:envidat.ch:ce722112-0768-4f79-a65b-3409af2a62e8"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Remote Sensing"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/uav-datasets-for-three-alpine-glaciers"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N,9 E)",
-    "TempCoverageBegin": 63623361599,
-    "TempCoverageEnd": 63623361599,
-    "TemporalCoverage": " point in time : 2017-02-22T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2017-02-22T11:59:59Z",
-    "TemporalCoverage:EndDate": "2017-02-22T11:59:59Z",
-    "author": [
-        "Daniel Farinotti",
-        "Saskia Gindraux",
-        "Ruedi Boesch"
-    ],
-    "fulltext": "oai:envidat.ch:ce722112-0768-4f79-a65b-3409af2a62e8;2018-12-09T00:23:54Z;10.16904/envidat.48;Saskia Gindraux;WSL;Daniel Farinotti;0000-0003-3417-4570;ETH-VAW/WSL;Ruedi Boesch;WSL;UAV-derived Digital Surface Models and orthoimages for three alpine glaciers;UAV-derived DSMs and orthoimages;2017;Remote Sensing;ALPS;DEM;DRONE;DSM;FINDELENGLETSCHER;GLACIER;GLETSCHER;GRIESGLETSCHER;ORTHOIMAGE;ORTHOPHOTO;SANKT ANNAFIRN;UAV;Saskia Gindraux;WSL;2017-02-22;en;Dataset;https://www.envidat.ch/dataset/uav-datasets-for-three-alpine-glaciers;1681404 bytes;780690371 bytes;813185979 bytes;957278925 bytes;2943574039 bytes;2465299515 bytes;2164463488 bytes;2101212707 bytes;3002624298 bytes;3185830469 bytes;3135905280 bytes;3678514763 bytes;3592468237 bytes;3793037626 bytes;3942636963 bytes;5116350 bytes;PDF;.zip;1.0;Open Data Commons Open Database License (ODbL);###UAV-derived DSMs and orthoimages\n\nUnmanned Aerial Vehicle  (UAV) surveys were conducted between 2015 and 2016 on the __Sankt Annafirn__, __Findelen-__ and __Griesgletscher__, situated in the __Swiss Alps__. Three surveys at the Sankt Annafirn allowed for a full glacier coverage,  four  surveys at Griesgletscher allowed an almost full glacier coverage and seven surveys at Findelengletscher allowed for a partial coverage of the glacier tongue (see individual datasets for exact extent). For each survey, a __high resolution orthoimage__ and a __Digital Surface Model (DSM)__ was created.\n\n###UAV surveys:\n\nPrior flight, Ground Control Points (GCPs) were deployed on the glacier surface and measured with a differential GPS (Trimble R7 or Leica GPS 1200). They allowed precise georeferencing of the UAV-derived datasets. UAV flight plans were planned with the software *eMotion 2* and a SenseFly eBee was used as surveying platform. The images were then processed with the software Agisoft Photoscan Pro 1.1.6 .\n\nThe location and dates of each survey can be found in the table together with the number of flights performed (Nflights), the number of acquired images (Nimages), the number of GCPs set (NGCPs) and the surveyed area.\n\nA folder for each dataset is available (see folder name in table), which contains:\n\n- An orthoimage  __*glacier_date_photoscan_oi_CH1903+_LV95_0.1m.tif*__\n\n- A Digital Surface Model  __*glacier_date_photoscan_dsm_CH1903+_LV95_0.1m.tif*__\n\n- The Agisoft Photoscan automatic processing report   __*glacier_date_photoscan_report.pdf*__\n\nwhere:\n\n- __*glacier*__ is the name of the surveyed glacier\n\n- __*date*__ is the date of the UAV image acquisition\n\n- __*photoscan*__ is the name of the photogrammetric software\n\n- __*oi*__ or __*dsm*__ the type of dataset\n\n- __*CH1903+_LV95*__ is the coordinate system and datum of the dataset\n\n- __*0.1m*__ is the resolution of the dataset in meter\n\n- __*.tif*__ is the extention of the dataset\n\n&nbsp;\n\nDetails about the UAV surveys, the image processing and the accuracy of the UAV-derived products can be found in this publication below.\n\n__Paper Citation:__\n > _Gindraux et al. 2017. Accuracy Assessment of Digital Surface Models from Unmanned Aerial Vehicles\u2019Imagery on Glaciers, Remote Sensing, 9, 186, 1-15,  [doi: 10.3390/rs9020186](https://doi.org/10.3390/rs9020186)._\n\nThe folder UAV_flight_paths.zip contains all UAV flights performed on the Sankt Annafirn, Findelengletscher and Griesgletscher. The flights were planned with the software eMotion2 and have the .afp extention.;46.5919326823 8.59005160693;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "7f9c7de0-f72d-5bc3-894b-10685896719e",
-    "notes": [
-        "###UAV-derived DSMs and orthoimages\n\nUnmanned Aerial Vehicle  (UAV) surveys were conducted between 2015 and 2016 on the __Sankt Annafirn__, __Findelen-__ and __Griesgletscher__, situated in the __Swiss Alps__. Three surveys at the Sankt Annafirn allowed for a full glacier coverage,  four  surveys at Griesgletscher allowed an almost full glacier coverage and seven surveys at Findelengletscher allowed for a partial coverage of the glacier tongue (see individual datasets for exact extent). For each survey, a __high resolution orthoimage__ and a __Digital Surface Model (DSM)__ was created.\n\n###UAV surveys:\n\nPrior flight, Ground Control Points (GCPs) were deployed on the glacier surface and measured with a differential GPS (Trimble R7 or Leica GPS 1200). They allowed precise georeferencing of the UAV-derived datasets. UAV flight plans were planned with the software *eMotion 2* and a SenseFly eBee was used as surveying platform. The images were then processed with the software Agisoft Photoscan Pro 1.1.6 .\n\nThe location and dates of each survey can be found in the table together with the number of flights performed (Nflights), the number of acquired images (Nimages), the number of GCPs set (NGCPs) and the surveyed area.\n\nA folder for each dataset is available (see folder name in table), which contains:\n\n- An orthoimage  __*glacier_date_photoscan_oi_CH1903+_LV95_0.1m.tif*__\n\n- A Digital Surface Model  __*glacier_date_photoscan_dsm_CH1903+_LV95_0.1m.tif*__\n\n- The Agisoft Photoscan automatic processing report   __*glacier_date_photoscan_report.pdf*__\n\nwhere:\n\n- __*glacier*__ is the name of the surveyed glacier\n\n- __*date*__ is the date of the UAV image acquisition\n\n- __*photoscan*__ is the name of the photogrammetric software\n\n- __*oi*__ or __*dsm*__ the type of dataset\n\n- __*CH1903+_LV95*__ is the coordinate system and datum of the dataset\n\n- __*0.1m*__ is the resolution of the dataset in meter\n\n- __*.tif*__ is the extention of the dataset\n\n&nbsp;\n\nDetails about the UAV surveys, the image processing and the accuracy of the UAV-derived products can be found in this publication below.\n\n__Paper Citation:__\n > _Gindraux et al. 2017. Accuracy Assessment of Digital Surface Models from Unmanned Aerial Vehicles\u2019Imagery on Glaciers, Remote Sensing, 9, 186, 1-15,  [doi: 10.3390/rs9020186](https://doi.org/10.3390/rs9020186)._\n\nThe folder UAV_flight_paths.zip contains all UAV flights performed on the Sankt Annafirn, Findelengletscher and Griesgletscher. The flights were planned with the software eMotion2 and have the .afp extention."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:ce722112-0768-4f79-a65b-3409af2a62e8"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[8.59005160693,46.5919326823],[8.59005160693,46.5919326823],[8.59005160693,46.5919326823],[8.59005160693,46.5919326823],[8.59005160693,46.5919326823]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ALPS"
-        },
-        {
-            "name": "DEM"
-        },
-        {
-            "name": "DRONE"
-        },
-        {
-            "name": "DSM"
-        },
-        {
-            "name": "FINDELENGLETSCHER"
-        },
-        {
-            "name": "GLACIER"
-        },
-        {
-            "name": "GLETSCHER"
-        },
-        {
-            "name": "GRIESGLETSCHER"
-        },
-        {
-            "name": "ORTHOIMAGE"
-        },
-        {
-            "name": "ORTHOPHOTO"
-        },
-        {
-            "name": "SANKT ANNAFIRN"
-        },
-        {
-            "name": "UAV"
-        }
-    ],
-    "title": [
-        "UAV-derived Digital Surface Models and orthoimages for three alpine glaciers",
-        "UAV-derived DSMs and orthoimages"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/80e203d7-7c64-5c00-8d1f-a91d49b0fa16.json b/oaitestdata/envidat-datacite/SET_1/json/80e203d7-7c64-5c00-8d1f-a91d49b0fa16.json
deleted file mode 100644
index 978ec696..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/80e203d7-7c64-5c00-8d1f-a91d49b0fa16.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:7872513f-ecb8-41f4-a90c-66059a09a634",
-    "MetadataAccess": [
-        "oai:envidat.ch:7872513f-ecb8-41f4-a90c-66059a09a634"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/stem_number_of_dead_wood_nfi1-248"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:7872513f-ecb8-41f4-a90c-66059a09a634;2018-12-09T00:33:14Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Stem number of dead wood NFI1;2014;Swiss Federal Research Institute WSL;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;BIOGEOGRAPHICAL REGION;CANTON;CONIFERS-BROADLEAVES;ECONOMIC REGION;GRID NFI4 2009-2013;MAIN TREE SPECIES;NFI1;PRODUCTION REGION;PROTECTION FOREST REGION;STEM NUMBER OF DEAD WOOD NFI1;TERRESTRIAL GRID NFI1;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/stem_number_of_dead_wood_nfi1-248;URL;1.0;Other (Open);Number of stems of dead trees and shrubs (standing and lying)  starting at 12 cm recorded according to the NFI1 method. In NFI1 only those dead trees were recorded whose wood could still be exploited. In addition, lying green trees were classified in NFI1 as deadwood.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "80e203d7-7c64-5c00-8d1f-a91d49b0fa16",
-    "notes": [
-        "Number of stems of dead trees and shrubs (standing and lying)  starting at 12 cm recorded according to the NFI1 method. In NFI1 only those dead trees were recorded whose wood could still be exploited. In addition, lying green trees were classified in NFI1 as deadwood.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:7872513f-ecb8-41f4-a90c-66059a09a634"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "MAIN TREE SPECIES"
-        },
-        {
-            "name": "NFI"
-        },
-        {
-            "name": "PRODUCTION REGION"
-        },
-        {
-            "name": "PROTECTION FOREST REGION"
-        },
-        {
-            "name": "STEM NUMBER DEAD WOOD NFI"
-        }
-    ],
-    "title": [
-        "Stem number of dead wood NFI1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/888153db-7c41-5c54-8b28-c54cccf61c49.json b/oaitestdata/envidat-datacite/SET_1/json/888153db-7c41-5c54-8b28-c54cccf61c49.json
deleted file mode 100644
index e3f9ab7a..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/888153db-7c41-5c54-8b28-c54cccf61c49.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "Marielle Fraefel"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/envidat.49",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "SHP",
-        "url",
-        "ipynb"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:6c16efa5-2c29-468a-916a-4a005b3bff02",
-    "MetadataAccess": [
-        "oai:envidat.ch:6c16efa5-2c29-468a-916a-4a005b3bff02"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/dataset-for-ogrs-2018-publication"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63670618799,
-    "TempCoverageEnd": 63670618799,
-    "TemporalCoverage": " point in time : 2018-08-23T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-08-23T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-08-23T11:59:59Z",
-    "author": [
-        "Marielle Fraefel"
-    ],
-    "fulltext": "oai:envidat.ch:6c16efa5-2c29-468a-916a-4a005b3bff02;2018-12-06T17:36:22Z;10.16904/envidat.49;Marielle Fraefel;WSL;Dataset for OGRS 2018 publication;2018;WSL;BUFFER;DENSITY;ROADS;Marielle Fraefel;WSL;2018-08-23;en;Dataset;https://www.envidat.ch/dataset/dataset-for-ogrs-2018-publication;394934 bytes;1719 bytes;8643 bytes;SHP;ipynb;url;1.0;Open Data Commons Open Database License (ODbL);This dataset contains the road and plot data used for the geospatial analysis example showcased in \"Fostering Open Science at WSL with the EnviDat Environmental Data Portal\", a contribution to the 5th Open Source Geospatial Research and Education Symposium (OGRS), 2018. \nThe example uses Jupyter Notebook to calculate road densities in the neighbourhood of sample plot locations with Python. Road data were extracted from OpenStreetMap, while the point data (sample plots) were generated manually.;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "888153db-7c41-5c54-8b28-c54cccf61c49",
-    "notes": [
-        "This dataset contains the road and plot data used for the geospatial analysis example showcased in \"Fostering Open Science at WSL with the EnviDat Environmental Data Portal\", a contribution to the 5th Open Source Geospatial Research and Education Symposium (OGRS), 2018. \nThe example uses Jupyter Notebook to calculate road densities in the neighbourhood of sample plot locations with Python. Road data were extracted from OpenStreetMap, while the point data (sample plots) were generated manually."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:6c16efa5-2c29-468a-916a-4a005b3bff02"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "BUFFER"
-        },
-        {
-            "name": "DENSITY"
-        },
-        {
-            "name": "ROADS"
-        }
-    ],
-    "title": [
-        "Dataset for OGRS 2018 publication"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/8e3afba6-a9e9-5f6a-9337-75d00b7d03db.json b/oaitestdata/envidat-datacite/SET_1/json/8e3afba6-a9e9-5f6a-9337-75d00b7d03db.json
deleted file mode 100644
index 8c074f5d..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/8e3afba6-a9e9-5f6a-9337-75d00b7d03db.json
+++ /dev/null
@@ -1,103 +0,0 @@
-{
-    "Contact": [
-        "Nander Wever"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/1",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "PDF",
-        "SMET"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:38112bee-f865-4b29-ba19-47a99ba78833",
-    "MetadataAccess": [
-        "oai:envidat.ch:38112bee-f865-4b29-ba19-47a99ba78833"
-    ],
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avalanche Research SLF"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/10-16904-1",
-        "http://www.envidat.ch/catalogue/10.16904/1"
-    ],
-    "ResourceType": [
-        "Measurements"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N,10E)",
-    "TempCoverageBegin": 62977172399,
-    "TempCoverageEnd": 62977172399,
-    "TemporalCoverage": " point in time : 1996-09-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1996-09-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1996-09-01T11:59:59Z",
-    "author": [
-        "WSL Institute for Snow and Avalanche Research SLF"
-    ],
-    "fulltext": "oai:envidat.ch:38112bee-f865-4b29-ba19-47a99ba78833;2018-12-09T00:24:25Z;10.16904/1;WSL Institute for Snow and Avalanche Research SLF;SLF;WFJ_MOD: Meteorological and snowpack measurements from Weissfluhjoch, Davos, Switzerland;Meteorologische und Schneedecke Messungen von Weissfluhjoch, Davos, Schweiz.;2015;WSL Institute for Snow and Avalanche Research SLF;AIR TEMPERATURE;HUMIDITY;LONGWAVE RADIATION;PRECIPITATION AMOUNT;SHORTWAVE RADIATION;SNOW DEPTH;SNOW ICE TEMPERATURE;WIND DIRECTION;WIND SPEED;Nander Wever;SLF;1996-09-01;en;Measurements;https://www.envidat.ch/dataset/10-16904-1;http://www.envidat.ch/catalogue/10.16904/1;2490 bytes;2223 bytes;1095 bytes;59121 bytes;SMET;PDF;1;Open Data Commons Open Database License (ODbL);Dataset of meteorological and snowpack measurements from the automatic weather station at Weissfluhjoch, Davos, Switzerland, suitable for driving snowpack models. The dataset contains standard meteorological measurements, and additionally snowpack runoff data from a snow lysimeter. Where possible, data is quality checked and missing data are replaced from backup sensors from the measurement site itself, or (in only a few cases) from the MeteoSwiss weather station at 470 m distance and 150 m above the measurement site. \n\n__Publication__\nWever, N., Schmid, L., Heilig, A., Eisen, O., Fierz, C., and Lehning, M. Verification of the multi-layer SNOWPACK model with different water transport schemes. 2015. The Cryosphere. Volume 9. 2271-2293. http://dx.doi.org/10.5194/tc-9-2271-2015. 10.5194/tc-9-2271-2015;46.829598 9.809568;[46.829598 9.809568]",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "8e3afba6-a9e9-5f6a-9337-75d00b7d03db",
-    "notes": [
-        "Dataset of meteorological and snowpack measurements from the automatic weather station at Weissfluhjoch, Davos, Switzerland, suitable for driving snowpack models. The dataset contains standard meteorological measurements, and additionally snowpack runoff data from a snow lysimeter. Where possible, data is quality checked and missing data are replaced from backup sensors from the measurement site itself, or (in only a few cases) from the MeteoSwiss weather station at 470 m distance and 150 m above the measurement site. \n\n__Publication__\nWever, N., Schmid, L., Heilig, A., Eisen, O., Fierz, C., and Lehning, M. Verification of the multi-layer SNOWPACK model with different water transport schemes. 2015. The Cryosphere. Volume 9. 2271-2293. http://dx.doi.org/10.5194/tc-9-2271-2015. 10.5194/tc-9-2271-2015"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:38112bee-f865-4b29-ba19-47a99ba78833"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[9.809568,46.829598],[9.809568,46.829598],[9.809568,46.829598],[9.809568,46.829598],[9.809568,46.829598]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "AIR TEMPERATURE"
-        },
-        {
-            "name": "HUMIDITY"
-        },
-        {
-            "name": "LONGWAVE RADIATION"
-        },
-        {
-            "name": "PRECIPITATION AMOUNT"
-        },
-        {
-            "name": "SHORTWAVE RADIATION"
-        },
-        {
-            "name": "SNOW DEPTH"
-        },
-        {
-            "name": "SNOW ICE TEMPERATURE"
-        },
-        {
-            "name": "WIND DIRECTION"
-        },
-        {
-            "name": "WIND SPEED"
-        }
-    ],
-    "title": [
-        "WFJ_MOD: Meteorological and snowpack measurements from Weissfluhjoch, Davos, Switzerland",
-        "Meteorologische und Schneedecke Messungen von Weissfluhjoch, Davos, Schweiz."
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/8eecbeab-40c1-5ef5-b9d1-049a785c6406.json b/oaitestdata/envidat-datacite/SET_1/json/8eecbeab-40c1-5ef5-b9d1-049a785c6406.json
deleted file mode 100644
index 74f84979..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/8eecbeab-40c1-5ef5-b9d1-049a785c6406.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Francesco Comola"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "TXT"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:467b2213-b72a-4578-8c2e-f1181b6a7742",
-    "MetadataAccess": [
-        "oai:envidat.ch:467b2213-b72a-4578-8c2e-f1181b6a7742"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Geophysical Research Letters"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/2016gl071822"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N,7 E)",
-    "TempCoverageBegin": 63620510399,
-    "TempCoverageEnd": 63620510399,
-    "TemporalCoverage": " point in time : 2017-01-20T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2017-01-20T11:59:59Z",
-    "TemporalCoverage:EndDate": "2017-01-20T11:59:59Z",
-    "author": [
-        "Francesco Comola"
-    ],
-    "fulltext": "oai:envidat.ch:467b2213-b72a-4578-8c2e-f1181b6a7742;2018-12-06T17:34:27Z;Francesco Comola;0000-0002-3867-732X;EPFL;Energy- and momentum-conserving model of splash entrainment in sand and snow saltation;2017;Geophysical Research Letters;EROSION;MARS;SEDIMENT TRANSPORT;SNOW;Francesco Comola;EPFL;2017-01-20;en;Dataset;https://www.envidat.ch/dataset/2016gl071822;3587 bytes;1434 bytes;2190 bytes;3626 bytes;2904 bytes;TXT;1.0;Open Data Commons Open Database License (ODbL);The files contain the datasets used to produce Figures 2, 3, and 4 of the manuscript ([doi: 10.1002/2016GL071822](http://dx.doi.org/10.1002/2016GL071822)).\n\n## Manuscript Abstract:\nDespite being the main sediment entrainment mechanism in aeolian transport, granular splash is still poorly understood. We provide a deeper insight into the dynamics of sand and snow ejection with a stochastic model derived from the energy and momentum conservation laws. Our analysis highlights that the ejection regime of uniform sand is inherently different from that of heterogeneous sand. Moreover, we show that cohesive snow presents a mixed ejection regime, statistically controlled either by energy or momentum conservation depending on the impact velocity. The proposed formulation can provide a solid base for granular splash simulations in saltation models, leading to more reliable assessments of aeolian transport on Earth and Mars.;46.51959 6.56689;EPFL Lausanne (VD), Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "8eecbeab-40c1-5ef5-b9d1-049a785c6406",
-    "notes": [
-        "The files contain the datasets used to produce Figures 2, 3, and 4 of the manuscript ([doi: 10.1002/2016GL071822](http://dx.doi.org/10.1002/2016GL071822)).\n\n## Manuscript Abstract:\nDespite being the main sediment entrainment mechanism in aeolian transport, granular splash is still poorly understood. We provide a deeper insight into the dynamics of sand and snow ejection with a stochastic model derived from the energy and momentum conservation laws. Our analysis highlights that the ejection regime of uniform sand is inherently different from that of heterogeneous sand. Moreover, we show that cohesive snow presents a mixed ejection regime, statistically controlled either by energy or momentum conservation depending on the impact velocity. The proposed formulation can provide a solid base for granular splash simulations in saltation models, leading to more reliable assessments of aeolian transport on Earth and Mars."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:467b2213-b72a-4578-8c2e-f1181b6a7742"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[6.56689,46.51959],[6.56689,46.51959],[6.56689,46.51959],[6.56689,46.51959],[6.56689,46.51959]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "EROSION"
-        },
-        {
-            "name": "MARS"
-        },
-        {
-            "name": "SEDIMENT TRANSPORT"
-        },
-        {
-            "name": "SNOW"
-        }
-    ],
-    "title": [
-        "Energy- and momentum-conserving model of splash entrainment in sand and snow saltation"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/91a80c53-020a-559f-9aad-ced39bba3a35.json b/oaitestdata/envidat-datacite/SET_1/json/91a80c53-020a-559f-9aad-ced39bba3a35.json
deleted file mode 100644
index 51dc62cb..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/91a80c53-020a-559f-9aad-ced39bba3a35.json
+++ /dev/null
@@ -1,91 +0,0 @@
-{
-    "Contact": [
-        "Rebecca Mott"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/10",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "XLSX",
-        "PNG",
-        "ZIP"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:7e8c6dac-80cf-49d7-bd85-2a61d3336e6f",
-    "MetadataAccess": [
-        "oai:envidat.ch:7e8c6dac-80cf-49d7-bd85-2a61d3336e6f"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avalanche Research SLF"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/10-16904-10"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N,10E)",
-    "TemporalCoverage": [
-        "2014-04-17",
-        "2015-04-15",
-        "2016-04-21"
-    ],
-    "author": [
-        "Rebecca Mott",
-        "Lisa Dirks",
-        "Michael Lehning",
-        "Sebastian Schl\u00f6gl"
-    ],
-    "fulltext": "oai:envidat.ch:7e8c6dac-80cf-49d7-bd85-2a61d3336e6f;2018-12-09T00:24:04Z;10.16904/10;Rebecca Mott;WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland;Sebastian Schl\u00f6gl;E\u0300cole Polytechnique Fe\u0300de\u0300rale de Lausanne, Lausanne, Switzerland School of Architecture, Civil and Environmental Engineering, Laboratory of Cryospheric Sciences (CRYOS) and WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland;Lisa Dirks;WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland;Michael Lehning;E\u0300cole Polytechnique Fe\u0300de\u0300rale de Lausanne, Lausanne, Switzerland School of Architecture, Civil and Environmental Engineering, Laboratory of Cryospheric Sciences (CRYOS) and WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland;DISCHMEX - Impact of extreme land-surface heterogeneity on micrometeorology over spring snow-cover;Eddy-covariance measurements;2017;WSL Institute for Snow and Avalanche Research SLF;DISCHMEX;EDDY-COVARIANCE MEASUREMENTS;PATCHY SNOW COVERS;TURBULENT SENSIBLE HEAT FLUXES;Rebecca Mott;SLF;2014-04-17;2015-04-15;2016-04-21;en;Dataset;https://www.envidat.ch/dataset/10-16904-10;725025 bytes;726971 bytes;717361 bytes;717473 bytes;212111 bytes;765677 bytes;764023 bytes;737846 bytes;735270 bytes;271399 bytes;842796 bytes;571682 bytes;860498 bytes;54602 bytes;17405 bytes;1723556 bytes;ZIP;XLSX;PNG;1.0;Open Data Commons Open Database License (ODbL);This dataset contains eddy-covariance measurements in the ablation period of 2014-2016. Measurements were taken from two turbulence towers over a long-lasting snow patch, which are 5 m apart from each other (2014 and 2015). The turbulence towers were equipped with two YOUNG ultrasonic anemometers mounted 0.7 m (in 2014) and 3.3 m (in 2015) above snow-free ground, two ultrasonic anemometers (CSAT3, Campbell Scientific, Inc.) mounted at 2.6 m (in 2014) and 2.2 m (in 2015) above snow-free ground and one anemometer (DA-600, Kaijo Denki) mounted at 0.3 m above snow surface.  \n\nThe measurement setup changed in 2016 and includes a measurement above the snow-free ground in upwind direction (Swiss coordinates: 790191/176689). The measurement tower is equipped with one ultrasonic anemometer (CSAT3, Campbell Scientific, Inc.) in 3.3 m above the snow-free ground. Additionally, one measurement tower is installed above the long-Lasting snow patch and equipped with the same setup as 2015.\n\nTurbulence data were sampled at a frequency of 20 Hz. The processing of the data to quality controlled fluxes has been done with the Biomicrometeorology flux software (Thomas et al., 2009). The program applies plausibility tests and a despiking test after Vickers and Mahrt (1997) on the measured data. The routine further applies a time-lag correction and considers the deployment (e.g.  the sonic azimuth). A frequency response correction (Moore, 1986) is done and a three-dimensional rotation is performed. Finally, quality assurance/quality control (QA/QC) flags after Foken et al., (2004) are issued and fast Fourier transform power and co-spectra are calculated.  The change in snow height is considered in the post-processing for every measurement day. The turbulence data were averaged to 30 minute intervals.;46.71291 9.92665;The dataset was recorded at the Gletschboden area (2094 m asl) in the upper Dischma valley, Davos, Switzerland. Swiss coordinates: 790211/176539",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "91a80c53-020a-559f-9aad-ced39bba3a35",
-    "notes": [
-        "This dataset contains eddy-covariance measurements in the ablation period of 2014-2016. Measurements were taken from two turbulence towers over a long-lasting snow patch, which are 5 m apart from each other (2014 and 2015). The turbulence towers were equipped with two YOUNG ultrasonic anemometers mounted 0.7 m (in 2014) and 3.3 m (in 2015) above snow-free ground, two ultrasonic anemometers (CSAT3, Campbell Scientific, Inc.) mounted at 2.6 m (in 2014) and 2.2 m (in 2015) above snow-free ground and one anemometer (DA-600, Kaijo Denki) mounted at 0.3 m above snow surface.  \n\nThe measurement setup changed in 2016 and includes a measurement above the snow-free ground in upwind direction (Swiss coordinates: 790191/176689). The measurement tower is equipped with one ultrasonic anemometer (CSAT3, Campbell Scientific, Inc.) in 3.3 m above the snow-free ground. Additionally, one measurement tower is installed above the long-Lasting snow patch and equipped with the same setup as 2015.\n\nTurbulence data were sampled at a frequency of 20 Hz. The processing of the data to quality controlled fluxes has been done with the Biomicrometeorology flux software (Thomas et al., 2009). The program applies plausibility tests and a despiking test after Vickers and Mahrt (1997) on the measured data. The routine further applies a time-lag correction and considers the deployment (e.g.  the sonic azimuth). A frequency response correction (Moore, 1986) is done and a three-dimensional rotation is performed. Finally, quality assurance/quality control (QA/QC) flags after Foken et al., (2004) are issued and fast Fourier transform power and co-spectra are calculated.  The change in snow height is considered in the post-processing for every measurement day. The turbulence data were averaged to 30 minute intervals."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:7e8c6dac-80cf-49d7-bd85-2a61d3336e6f"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[9.92665,46.71291],[9.92665,46.71291],[9.92665,46.71291],[9.92665,46.71291],[9.92665,46.71291]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "DISCHMEX"
-        },
-        {
-            "name": "EDDY-COVARIANCE MEASUREMENTS"
-        },
-        {
-            "name": "PATCHY SNOW COVERS"
-        },
-        {
-            "name": "TURBULENT SENSIBLE HEAT FLUXES"
-        }
-    ],
-    "title": [
-        "DISCHMEX - Impact of extreme land-surface heterogeneity on micrometeorology over spring snow-cover",
-        "Eddy-covariance measurements"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/92245f96-cf2f-5517-82fe-51ef789c20ca.json b/oaitestdata/envidat-datacite/SET_1/json/92245f96-cf2f-5517-82fe-51ef789c20ca.json
deleted file mode 100644
index d677b275..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/92245f96-cf2f-5517-82fe-51ef789c20ca.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:5edb2ee9-c388-463c-bb8b-fbe6922545ba",
-    "MetadataAccess": [
-        "oai:envidat.ch:5edb2ee9-c388-463c-bb8b-fbe6922545ba"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/root_mass_of_live_trees_zell_wutzler-210"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:5edb2ee9-c388-463c-bb8b-fbe6922545ba;2018-12-09T00:32:58Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Root mass of live trees (Zell, Wutzler);2014;Swiss Federal Research Institute WSL;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;BIOGEOGRAPHICAL REGION;CANTON;CONIFERS-BROADLEAVES;ECONOMIC REGION;GRID NFI4 2009-2013;NFI3;NFI4B;PRODUCTION REGION;PROTECTION FOREST REGION;ROOT MASS OF LIVE TREES ZELL;TERRESTRIAL GRID NFI3;WUTZLER;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/root_mass_of_live_trees_zell_wutzler-210;URL;1.0;Other (Open);Dry weight (mass) of the belowground part (roots) of living trees and shrubs  starting at 12 cm dbh. The dimensions of the roots are determined according to Zell and Wutzler.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "92245f96-cf2f-5517-82fe-51ef789c20ca",
-    "notes": [
-        "Dry weight (mass) of the belowground part (roots) of living trees and shrubs  starting at 12 cm dbh. The dimensions of the roots are determined according to Zell and Wutzler.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:5edb2ee9-c388-463c-bb8b-fbe6922545ba"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "NFI"
-        },
-        {
-            "name": "NFIB"
-        },
-        {
-            "name": "PRODUCTION REGION"
-        },
-        {
-            "name": "PROTECTION FOREST REGION"
-        },
-        {
-            "name": "ROOT MASS LIVE TREES ZELL"
-        }
-    ],
-    "title": [
-        "Root mass of live trees (Zell, Wutzler)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/958a24a2-cb1b-5b64-a9fa-63e7e69a0776.json b/oaitestdata/envidat-datacite/SET_1/json/958a24a2-cb1b-5b64-a9fa-63e7e69a0776.json
deleted file mode 100644
index 2ec42468..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/958a24a2-cb1b-5b64-a9fa-63e7e69a0776.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:70dcad06-3d10-48b4-a178-1c3c0ec6d9d2",
-    "MetadataAccess": [
-        "oai:envidat.ch:70dcad06-3d10-48b4-a178-1c3c0ec6d9d2"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/mortality_star-164"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:70dcad06-3d10-48b4-a178-1c3c0ec6d9d2;2018-12-09T00:32:39Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Mortality*;2014;Swiss Federal Research Institute WSL;14 X 14 KM GRID;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;ALTITUDE 400 M CLASSES;CANTON;FOREST DISTRICT AS OF 2013;GRID NFI4 2009-2013;MORTALITY STAR;NFI2-NFI3;NFI3-NFI4B;OWNERSHIP;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/mortality_star-164;URL;1.0;Other (Open);Volume of stemwood with bark of all trees and shrubs  starting at 12 cm dbh that died or disappeared between two inventories, but were not cut.  *In the calculation no D7/tree height data were used. The values calculated like this have not been corrected for bias, but allow for cantons or forest districts a more robust estimation of changes and could thus be better interpreted. \n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "958a24a2-cb1b-5b64-a9fa-63e7e69a0776",
-    "notes": [
-        "Volume of stemwood with bark of all trees and shrubs  starting at 12 cm dbh that died or disappeared between two inventories, but were not cut.  *In the calculation no D7/tree height data were used. The values calculated like this have not been corrected for bias, but allow for cantons or forest districts a more robust estimation of changes and could thus be better interpreted. \n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:70dcad06-3d10-48b4-a178-1c3c0ec6d9d2"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "X KM GRID"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ALTITUDE M CLASSES"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "FOREST DISTRICT"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "MORTALITY STAR"
-        },
-        {
-            "name": "NFI-NFI"
-        },
-        {
-            "name": "NFI-NFIB"
-        }
-    ],
-    "title": [
-        "Mortality*"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/97f70f94-342a-5b13-b691-812f4abbed79.json b/oaitestdata/envidat-datacite/SET_1/json/97f70f94-342a-5b13-b691-812f4abbed79.json
deleted file mode 100644
index 3404f16d..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/97f70f94-342a-5b13-b691-812f4abbed79.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "Frank Techel"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/envidat.53",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "SHP",
-        "CSV"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:f2dff8e3-fdff-4626-b650-a8ba5c19ef27",
-    "MetadataAccess": [
-        "oai:envidat.ch:f2dff8e3-fdff-4626-b650-a8ba5c19ef27"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Natural Hazards Earth System Sciences"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/forecast-avalanche-danger-level-european-alps-2011-2015"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(48N-48N,11E-15E)",
-    "TempCoverageBegin": 63459460799,
-    "TempCoverageEnd": 63459460799,
-    "TemporalCoverage": " point in time : 2011-12-14T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2011-12-14T11:59:59Z",
-    "TemporalCoverage:EndDate": "2011-12-14T11:59:59Z",
-    "author": [
-        "Frank Techel"
-    ],
-    "fulltext": "oai:envidat.ch:f2dff8e3-fdff-4626-b650-a8ba5c19ef27;2018-12-09T00:24:08Z;10.16904/envidat.53;Frank Techel;0000-0001-5686-6127;SLF;Forecast avalanche danger level European Alps 2011 - 2015;Spatial consistency and bias in avalanche forecasts - a case study in the European Alps;2018;Natural Hazards Earth System Sciences;AVALANCHE FORECAST;DANGER LEVEL;WARNING REGIONS;Frank Techel;0000-0001-5686-6127;SLF;2011-12-14;en;Dataset;https://www.envidat.ch/dataset/forecast-avalanche-danger-level-european-alps-2011-2015;4052358 bytes;378119 bytes;CSV;SHP;1.0;Open Data Commons Open Database License (ODbL);This dataset contains the data used in the publication by Techel et al., 2018 _Spatial consistency and bias in avalanche forecasts - a case study in the European Alps_ (Nat Haz Earth Syst Sci).\nFor details on the data please refer to this publication.\nThe dataset contains the following: \n- shape files for the warning regions in the Alps\n- highest forecast danger level for each warning region and day;47.7678840801 11.0302734375 47.9153605103 14.58984375;European Alps",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "97f70f94-342a-5b13-b691-812f4abbed79",
-    "notes": [
-        "This dataset contains the data used in the publication by Techel et al., 2018 _Spatial consistency and bias in avalanche forecasts - a case study in the European Alps_ (Nat Haz Earth Syst Sci).\nFor details on the data please refer to this publication.\nThe dataset contains the following: \n- shape files for the warning regions in the Alps\n- highest forecast danger level for each warning region and day"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:f2dff8e3-fdff-4626-b650-a8ba5c19ef27"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[11.0302734375,47.7678840801],[11.0302734375,47.9153605103],[14.58984375,47.9153605103],[14.58984375,47.7678840801],[11.0302734375,47.7678840801]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "AVALANCHE FORECAST"
-        },
-        {
-            "name": "DANGER LEVEL"
-        },
-        {
-            "name": "WARNING REGIONS"
-        }
-    ],
-    "title": [
-        "Forecast avalanche danger level European Alps 2011 - 2015",
-        "Spatial consistency and bias in avalanche forecasts - a case study in the European Alps"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/9846b79b-3ecd-5121-ad5a-dd438961ffc7.json b/oaitestdata/envidat-datacite/SET_1/json/9846b79b-3ecd-5121-ad5a-dd438961ffc7.json
deleted file mode 100644
index 572849da..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/9846b79b-3ecd-5121-ad5a-dd438961ffc7.json
+++ /dev/null
@@ -1,100 +0,0 @@
-{
-    "Contact": [
-        "Mountain Hydrology and Mass Movements"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/envidat.33",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "CSV"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:17732065-e90f-452d-838d-ba70bfd01a5e",
-    "MetadataAccess": [
-        "oai:envidat.ch:17732065-e90f-452d-838d-ba70bfd01a5e"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Swiss Federal Institute for Forest, Snow and Landscape Research WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/number-of-natural-hazard-fatalities-per-year-in-switzerland-since-1946"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-11E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "WSL"
-    ],
-    "fulltext": "oai:envidat.ch:17732065-e90f-452d-838d-ba70bfd01a5e;2018-12-09T00:32:46Z;10.16904/envidat.33;WSL;Swiss Federal Institute for Forest, Snow and Landscape Research WSL;Number of natural hazard fatalities per year in Switzerland since 1946;2018;Swiss Federal Institute for Forest, Snow and Landscape Research WSL;DEBRIS FLOW FATALITIES;EARTHQUAKE FATALITIES;FLOOD FATALITIES;ICE AVALANCHE FATALITIES;LANDSLIDE FATALITIES;LIGHTNING FATALITIES;NATURAL HAZARD FATALITIES;ROCKFALL FATALITIES;WINDSTORM FATALITIES;Mountain Hydrology and Mass Movements;Swiss Federal Institute for Forest, Snow and Landscape Research WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/number-of-natural-hazard-fatalities-per-year-in-switzerland-since-1946;1576 bytes;CSV;1.0;Open Data Commons Open Database License (ODbL);This dataset contains the number of fatalities due to flood, debris flow, landslide, rockfall, windstorm, lightning, ice avalanche, earthquake and other processes like roof avalanche or lacustrine tsunami for each year since 1946.\nThe following information is contained (by column and column title):  \n\n* year\n* total number of hazard fatalities\n* number of fatalities by flood (German: Hochwasser, \u00dcberschwemmung). Flood includes people drowned in flooded or inundated areas or carried away in streams under high-water conditions.\n* number of fatalities by debris flow (German: Murgang).\n* number of fatalities by landslide (German: Erdrutsch). Landslide includes people killed by landslides and hillslope debris flows (German: Hangmure).\n* number of fatalities by rockfall (German: Steinschlag, Fels- und Bergsturz).\n* number of fatalities by windstorm (German: Sturm). Windstorm includes people killed by falling objects or trees during very strong wind conditions and people who drowned in lakes because their boat capsized during such conditions.\n* number of fatalities by lightning (German: Blitz).\n* number of fatalities by ice avalanche (German: Eislawine).\n* number of fatalities by earthquake (German: Erdbeben).\n* number of fatalities by other processes like roof avalanche, lacustrine tsunami (German: andere Prozesse wie Dachlawine, Tsunami im See).\n\nThe data was collected based on newspaper research. For more information please refer to \n\n_Badoux, A., Andres, N., Techel, F., and Hegg, C.: Natural hazard fatalities in Switzerland from 1946 to 2015, Nat. Hazards Earth Syst. Sci., 16, 2747-2768, https://doi.org/10.5194/nhess-16-2747-2016, 2016._\n\nThe data collection is financed by the FOEN (with exception of the collection of the avalanche fatalities). The data contains the official statistics of the FOEN on fatalities due to flood, debris flow, landslide, rock fall and avalanche.\n\n__Restrictions: The data set is not complete.__ Only fatalities in or around settlements and on open transportation routes are included. More precisely, fatalities were not collected, when persons exposed themselves to a great danger on purpose. Or fatalities during leisure activities which are connected to a higher risk were not included (this includes e.g. canoeing or river surfing during flood, canyoning, mountaineering, climbing, walking or driving on a closed road).\n\nFatalities by avalanches are collected at the WSL Institute for Snow and Avalanche Research SLF. You can download the avalanche fatalities per hydrological year [here](https://www.envidat.ch/dataset/avalanche-fatalities-switzerland-1936) and per calendar year [here](https://www.envidat.ch/dataset/avalanche-fatalities-per-calendar-year-since-1936). For a direct comparison with the fatalities presented here, please download the data set with the calendar years and do not consider fatalities in the backcountry (tour) or in terrain close to ski areas (offpiste).;45.7675229621 5.64697265625 47.8647739558 10.5798339844;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "9846b79b-3ecd-5121-ad5a-dd438961ffc7",
-    "notes": [
-        "This dataset contains the number of fatalities due to flood, debris flow, landslide, rockfall, windstorm, lightning, ice avalanche, earthquake and other processes like roof avalanche or lacustrine tsunami for each year since 1946.\nThe following information is contained (by column and column title):  \n\n* year\n* total number of hazard fatalities\n* number of fatalities by flood (German: Hochwasser, \u00dcberschwemmung). Flood includes people drowned in flooded or inundated areas or carried away in streams under high-water conditions.\n* number of fatalities by debris flow (German: Murgang).\n* number of fatalities by landslide (German: Erdrutsch). Landslide includes people killed by landslides and hillslope debris flows (German: Hangmure).\n* number of fatalities by rockfall (German: Steinschlag, Fels- und Bergsturz).\n* number of fatalities by windstorm (German: Sturm). Windstorm includes people killed by falling objects or trees during very strong wind conditions and people who drowned in lakes because their boat capsized during such conditions.\n* number of fatalities by lightning (German: Blitz).\n* number of fatalities by ice avalanche (German: Eislawine).\n* number of fatalities by earthquake (German: Erdbeben).\n* number of fatalities by other processes like roof avalanche, lacustrine tsunami (German: andere Prozesse wie Dachlawine, Tsunami im See).\n\nThe data was collected based on newspaper research. For more information please refer to \n\n_Badoux, A., Andres, N., Techel, F., and Hegg, C.: Natural hazard fatalities in Switzerland from 1946 to 2015, Nat. Hazards Earth Syst. Sci., 16, 2747-2768, https://doi.org/10.5194/nhess-16-2747-2016, 2016._\n\nThe data collection is financed by the FOEN (with exception of the collection of the avalanche fatalities). The data contains the official statistics of the FOEN on fatalities due to flood, debris flow, landslide, rock fall and avalanche.\n\n__Restrictions: The data set is not complete.__ Only fatalities in or around settlements and on open transportation routes are included. More precisely, fatalities were not collected, when persons exposed themselves to a great danger on purpose. Or fatalities during leisure activities which are connected to a higher risk were not included (this includes e.g. canoeing or river surfing during flood, canyoning, mountaineering, climbing, walking or driving on a closed road).\n\nFatalities by avalanches are collected at the WSL Institute for Snow and Avalanche Research SLF. You can download the avalanche fatalities per hydrological year [here](https://www.envidat.ch/dataset/avalanche-fatalities-switzerland-1936) and per calendar year [here](https://www.envidat.ch/dataset/avalanche-fatalities-per-calendar-year-since-1936). For a direct comparison with the fatalities presented here, please download the data set with the calendar years and do not consider fatalities in the backcountry (tour) or in terrain close to ski areas (offpiste)."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:17732065-e90f-452d-838d-ba70bfd01a5e"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.64697265625,45.7675229621],[5.64697265625,47.8647739558],[10.5798339844,47.8647739558],[10.5798339844,45.7675229621],[5.64697265625,45.7675229621]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "DEBRIS FLOW FATALITIES"
-        },
-        {
-            "name": "EARTHQUAKE FATALITIES"
-        },
-        {
-            "name": "FLOOD FATALITIES"
-        },
-        {
-            "name": "ICE AVALANCHE FATALITIES"
-        },
-        {
-            "name": "LANDSLIDE FATALITIES"
-        },
-        {
-            "name": "LIGHTNING FATALITIES"
-        },
-        {
-            "name": "NATURAL HAZARD FATALITIES"
-        },
-        {
-            "name": "ROCKFALL FATALITIES"
-        },
-        {
-            "name": "WINDSTORM FATALITIES"
-        }
-    ],
-    "title": [
-        "Number of natural hazard fatalities per year in Switzerland since 1946"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/98ac0665-5bfd-54e8-8570-6c6413547549.json b/oaitestdata/envidat-datacite/SET_1/json/98ac0665-5bfd-54e8-8570-6c6413547549.json
deleted file mode 100644
index 5151ae99..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/98ac0665-5bfd-54e8-8570-6c6413547549.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Rebecca Mott"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/envidat.54",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "PDF",
-        "ZIP",
-        "XLSX"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:c4a42aa7-8b55-4f5e-8bf1-98c7b9ac2dc7",
-    "MetadataAccess": [
-        "oai:envidat.ch:c4a42aa7-8b55-4f5e-8bf1-98c7b9ac2dc7"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Frontiers to Earth Science"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/dischmex-meteorological-measurements"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N,10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Rebecca Mott",
-        "Michael Lehning",
-        "Sebastian Schl\u00f6gl"
-    ],
-    "fulltext": "oai:envidat.ch:c4a42aa7-8b55-4f5e-8bf1-98c7b9ac2dc7;2018-12-09T00:31:42Z;10.16904/envidat.54;Sebastian Schl\u00f6gl;SLF;Rebecca Mott;SLF;Michael Lehning;SLF;DISCHMEX - Meteorological measurements;2018;Frontiers to Earth Science;DISCHMEX;METEO STATION;METEOROLOGICAL DATA;Rebecca Mott;SLF;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/dischmex-meteorological-measurements;5503565 bytes;1159577 bytes;14489 bytes;34228880 bytes;1159577 bytes;13943 bytes;7715938 bytes;279067 bytes;ZIP;PDF;XLSX;1.0;Open Data Commons Open Database License (ODbL);Meteorological measurements recorded in the Dischma valley from 2014-2016. In 2014 and 2015 we used 11 mobile weather stations from sensorscope to record meteorological parameter in the upper Dischma valley in the closer surroundings of the Gletschboden area. The meteorological stations are eqiupped with at least air temperature/humidity, wind velocity and wind direction sensors. Some stations are additionally equipped with precipitation, shortwave radiation and snow surface temperature sensors.  \nThree transects were installed at different aspects and were equipped with air temperature/humidity and wind sensors. Transect 1 (stations 2-4) provides meteorological Information on an east-north-east facing slope at elevations ranging between 2100 m and 2500 m. Transect 2 (stations 5-7) provides meteorological Information on a south-west slope and transect 3 (stations 8-10) on a north-west slope. Station 1 is fully equipped with meteorological sensors (temperature/humidity, wind, IR, up and downwand shortwave radiation and precipitation).\nIn 2016, mobile stations from sensorscope were replaced with six permanent meteorological stations. Meteorological stations 1-3 are equipped with an air temperature/humidity sensor, two wind speed sensors, a wind direction sensor and an incoming and outgoing shortwave radiation sensor. Stations 4 and 6 are equipped with an air temperature/humidity sensor and a wind speed/direction sensor. Station 5 is a equipped with an air temperature/humidity sensor, a wind speed/direction sensor, a snow surface temperature sensor, an incoming and outgoing shortwave radiation sensor and an incoming longwave radiation sensor.;46.71291 9.92665;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "98ac0665-5bfd-54e8-8570-6c6413547549",
-    "notes": [
-        "Meteorological measurements recorded in the Dischma valley from 2014-2016. In 2014 and 2015 we used 11 mobile weather stations from sensorscope to record meteorological parameter in the upper Dischma valley in the closer surroundings of the Gletschboden area. The meteorological stations are eqiupped with at least air temperature/humidity, wind velocity and wind direction sensors. Some stations are additionally equipped with precipitation, shortwave radiation and snow surface temperature sensors.  \nThree transects were installed at different aspects and were equipped with air temperature/humidity and wind sensors. Transect 1 (stations 2-4) provides meteorological Information on an east-north-east facing slope at elevations ranging between 2100 m and 2500 m. Transect 2 (stations 5-7) provides meteorological Information on a south-west slope and transect 3 (stations 8-10) on a north-west slope. Station 1 is fully equipped with meteorological sensors (temperature/humidity, wind, IR, up and downwand shortwave radiation and precipitation).\nIn 2016, mobile stations from sensorscope were replaced with six permanent meteorological stations. Meteorological stations 1-3 are equipped with an air temperature/humidity sensor, two wind speed sensors, a wind direction sensor and an incoming and outgoing shortwave radiation sensor. Stations 4 and 6 are equipped with an air temperature/humidity sensor and a wind speed/direction sensor. Station 5 is a equipped with an air temperature/humidity sensor, a wind speed/direction sensor, a snow surface temperature sensor, an incoming and outgoing shortwave radiation sensor and an incoming longwave radiation sensor."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:c4a42aa7-8b55-4f5e-8bf1-98c7b9ac2dc7"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[9.92665,46.71291],[9.92665,46.71291],[9.92665,46.71291],[9.92665,46.71291],[9.92665,46.71291]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "DISCHMEX"
-        },
-        {
-            "name": "METEO STATION"
-        },
-        {
-            "name": "METEOROLOGICAL DATA"
-        }
-    ],
-    "title": [
-        "DISCHMEX - Meteorological measurements"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/99acc993-33ef-5538-8091-7f7c7ac8878f.json b/oaitestdata/envidat-datacite/SET_1/json/99acc993-33ef-5538-8091-7f7c7ac8878f.json
deleted file mode 100644
index 832afc58..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/99acc993-33ef-5538-8091-7f7c7ac8878f.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:52a3744e-10d0-4e3d-9db3-1d42efc6d06b",
-    "MetadataAccess": [
-        "oai:envidat.ch:52a3744e-10d0-4e3d-9db3-1d42efc6d06b"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/length_of_forest_edge-8"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:52a3744e-10d0-4e3d-9db3-1d42efc6d06b;2018-12-09T00:31:56Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Length of forest edge;2014;Swiss Federal Research Institute WSL;ALTITUDINAL VEGETATION ZONE;BIOGEOGRAPHICAL REGION;CANTON;ECONOMIC REGION;FOREST DISTRICT AS OF 2013;GRID NFI4 2009-2013;LENGTH OF FOREST EDGE;LOWER-HIGHER ALTITUDINAL ZONES;NFI3;NFI4B;PRODUCTION REGION;PROTECTION FOREST REGION;TERRESTRIAL GRID NFI3;TOTAL AREA;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/length_of_forest_edge-8;URL;1.0;Other (Open);Length of the forest edge calculated on the basis of the forest boundary lines determined in the aerial photo.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "99acc993-33ef-5538-8091-7f7c7ac8878f",
-    "notes": [
-        "Length of the forest edge calculated on the basis of the forest boundary lines determined in the aerial photo.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:52a3744e-10d0-4e3d-9db3-1d42efc6d06b"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "FOREST DISTRICT"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "LENGTH FOREST EDGE"
-        },
-        {
-            "name": "LOWER-HIGHER ALTITUDINAL ZONES"
-        },
-        {
-            "name": "NFI"
-        },
-        {
-            "name": "NFIB"
-        },
-        {
-            "name": "PRODUCTION REGION"
-        },
-        {
-            "name": "PROTECTION FOREST REGION"
-        }
-    ],
-    "title": [
-        "Length of forest edge"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/9cef640c-2c45-5891-b3fd-0f7449f46f46.json b/oaitestdata/envidat-datacite/SET_1/json/9cef640c-2c45-5891-b3fd-0f7449f46f46.json
deleted file mode 100644
index 2b9b0c98..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/9cef640c-2c45-5891-b3fd-0f7449f46f46.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:34dac4f8-ad13-4daa-a691-29d63e48c580",
-    "MetadataAccess": [
-        "oai:envidat.ch:34dac4f8-ad13-4daa-a691-29d63e48c580"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/yield_of_live_bole_wood-87"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:34dac4f8-ad13-4daa-a691-29d63e48c580;2018-12-09T00:33:44Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Yield of live bole wood;2014;Swiss Federal Research Institute WSL;14 X 14 KM GRID;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;BIOGEOGRAPHICAL REGION;CONIFERS-BROADLEAVES;ECONOMIC REGION;GRID NFI4 2009-2013;MAIN TYPE OF HARVEST;NFI2-NFI3;NFI3-NFI4B;OWNERSHIP;POTENTIAL COST FOR TIMBER HARVESTING;PRODUCTION REGION;PROTECTION FOREST REGION;TYPE OF LAST SILVICULTURAL TREATMENT INTERVIEW SURVEY;YIELD OF LIVE BOLE WOOD;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/yield_of_live_bole_wood-87;URL;1.0;Other (Open);Volume of stemwood at least 7 cm in diameter (limit for coarse wood) without the bark and stump that were  living trees or shrubs  starting at 12 cm dbh in the pre-inventory and were cut between two inventories.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "9cef640c-2c45-5891-b3fd-0f7449f46f46",
-    "notes": [
-        "Volume of stemwood at least 7 cm in diameter (limit for coarse wood) without the bark and stump that were  living trees or shrubs  starting at 12 cm dbh in the pre-inventory and were cut between two inventories.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:34dac4f8-ad13-4daa-a691-29d63e48c580"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "X KM GRID"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "MAIN TYPE HARVEST"
-        },
-        {
-            "name": "NFI-NFI"
-        },
-        {
-            "name": "NFI-NFIB"
-        }
-    ],
-    "title": [
-        "Yield of live bole wood"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/9d05648c-7d85-5c7f-81fa-307980ae419c.json b/oaitestdata/envidat-datacite/SET_1/json/9d05648c-7d85-5c7f-81fa-307980ae419c.json
deleted file mode 100644
index 8026aace..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/9d05648c-7d85-5c7f-81fa-307980ae419c.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:bc4de0c4-35a2-4804-8b68-f96138f3e070",
-    "MetadataAccess": [
-        "oai:envidat.ch:bc4de0c4-35a2-4804-8b68-f96138f3e070"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/stem_number_of_dead_wood-116"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:bc4de0c4-35a2-4804-8b68-f96138f3e070;2018-12-09T00:33:13Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Stem number of dead wood;2014;Swiss Federal Research Institute WSL;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;BIOGEOGRAPHICAL REGION;CANTON;CAVITY BY WOODPECKER;COLONIZATION OF DEAD WOOD BY SHRUBS 5 CLASSES;CONIFERS-BROADLEAVES;DEGREE OF COVER BY MOSSES OF DEAD WOOD 5 CLASSES;ECONOMIC REGION;GRID NFI4 2009-2013;LENGTH OF LYING DEAD SAMPLE TREE 6 CLASSES;MAIN TREE SPECIES;MECHANICAL STRENGTH OF WOOD 3 CLASSES;NFI2;NFI3;NFI4B;NUMBER OF FUNGI ON DEAD WOOD 3 CLASSES;PRODUCTION REGION;PROTECTION FOREST REGION;REGENERATION ON DEAD WOOD 3 CLASSES;STEM HEIGHT OF BROKEN SNAGS 6 CLASSES;STEM NUMBER OF DEAD WOOD;TERRESTRIAL GRID NFI2;TERRESTRIAL GRID NFI3;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/stem_number_of_dead_wood-116;URL;1.0;Other (Open);Number of stems of dead trees and shrubs (standing and lying)  starting at 12 cm dbh.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "9d05648c-7d85-5c7f-81fa-307980ae419c",
-    "notes": [
-        "Number of stems of dead trees and shrubs (standing and lying)  starting at 12 cm dbh.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:bc4de0c4-35a2-4804-8b68-f96138f3e070"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "CAVITY WOODPECKER"
-        },
-        {
-            "name": "COLONIZATION DEAD WOOD SHRUBS CLASSES"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "LENGTH LYING DEAD SAMPLE TREE CLASSES"
-        },
-        {
-            "name": "MAIN TREE SPECIES"
-        }
-    ],
-    "title": [
-        "Stem number of dead wood"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/9d490baa-18c7-569e-a393-2a5dbd63cec1.json b/oaitestdata/envidat-datacite/SET_1/json/9d490baa-18c7-569e-a393-2a5dbd63cec1.json
deleted file mode 100644
index 93b46e3a..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/9d490baa-18c7-569e-a393-2a5dbd63cec1.json
+++ /dev/null
@@ -1,101 +0,0 @@
-{
-    "Contact": [
-        "Dr. Manfred Staehli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/7",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "ZIP"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:c54a616a-4419-4ba8-840e-82f6ec5c05ff",
-    "MetadataAccess": [
-        "oai:envidat.ch:c54a616a-4419-4ba8-840e-82f6ec5c05ff"
-    ],
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Swiss Federal Institute for Forest, Snow and Landscape WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/10-16904-7"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": [
-        "47.01576 7.84273",
-        "47.0163 7.8903",
-        "47.01555 7.88684",
-        "47.02267 7.84487",
-        "47.01343 7.84105",
-        "47.01867 7.88851",
-        "47.01745 7.88764",
-        "47.01353 7.88702",
-        "47.03105 7.85199"
-    ],
-    "TempCoverageBegin": 63666471599,
-    "TempCoverageEnd": 63666471599,
-    "TemporalCoverage": " point in time : 2018-07-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-07-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-07-06T11:59:59Z",
-    "author": [
-        "Karl Steiner",
-        "Alexandre Badoux",
-        "A. Ludwig",
-        "Manfred St\u00e4hli"
-    ],
-    "fulltext": "oai:envidat.ch:c54a616a-4419-4ba8-840e-82f6ec5c05ff;2018-12-09T00:31:13Z;10.16904/7;Manfred St\u00e4hli;WSL;A. Ludwig;None;Karl Steiner;WSL;Alexandre Badoux;WSL;More than one century of hydrological monitoring in two small catchments with different forest coverage, Sperbelgraben and Rappengraben (Switzerland);Hydrologische Messungen Sperbel- und Rappengraben (1903 \u2013 2009);2016;Swiss Federal Institute for Forest, Snow and Landscape WSL;AIR TEMPERATURE;PRECIPITATION;RUNOFF;SNOW DEPTH;WATERSHED DRAINAGE BASINS;Dr. Manfred Staehli;WSL;2018-07-06;en;Dataset;https://www.envidat.ch/dataset/10-16904-7;2482693 bytes;ZIP;1;Other (Open);Long-term data on precipitation and runoff are essential to draw firm conclusions about the behavior and trends of hydrological catchments that may be influenced by land-use and climate change. Here the longest continuous runoff records (1903 - 2015) from small catchments (less than 1 km2) in Switzerland (and possibly worldwide) are provided as a data set. The history of the hydrological monitoring in the Sperbel- and Rappengraben (Emmental) is summarized in St\u00e4hli et al., Environ Monit Assess (2011). The runoff stations operated safely for more than 90% of the summer months when most of the major flood events occurred. Nevertheless, the absolute values of peak runoff during the largest flood events are subject to considerable uncertainty (also discussed in St\u00e4hli et al., 2011). This treasure trove of data can be used in various ways, eg. for analysis of the generalized extreme value distributions of the two catchments, of the mechanisms governing the runoff behavior of small catchments, as well as for testing stochastic and deterministic models.;47.01576 7.84273;47.0163 7.8903;47.01555 7.88684;47.02267 7.84487;47.01343 7.84105;47.01867 7.88851;47.01745 7.88764;47.01353 7.88702;47.03105 7.85199;Sperbelgraben and Rappengraben (Switzerland)",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "9d490baa-18c7-569e-a393-2a5dbd63cec1",
-    "notes": [
-        "Long-term data on precipitation and runoff are essential to draw firm conclusions about the behavior and trends of hydrological catchments that may be influenced by land-use and climate change. Here the longest continuous runoff records (1903 - 2015) from small catchments (less than 1 km2) in Switzerland (and possibly worldwide) are provided as a data set. The history of the hydrological monitoring in the Sperbel- and Rappengraben (Emmental) is summarized in St\u00e4hli et al., Environ Monit Assess (2011). The runoff stations operated safely for more than 90% of the summer months when most of the major flood events occurred. Nevertheless, the absolute values of peak runoff during the largest flood events are subject to considerable uncertainty (also discussed in St\u00e4hli et al., 2011). This treasure trove of data can be used in various ways, eg. for analysis of the generalized extreme value distributions of the two catchments, of the mechanisms governing the runoff behavior of small catchments, as well as for testing stochastic and deterministic models."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:c54a616a-4419-4ba8-840e-82f6ec5c05ff"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "AIR TEMPERATURE"
-        },
-        {
-            "name": "PRECIPITATION"
-        },
-        {
-            "name": "RUNOFF"
-        },
-        {
-            "name": "SNOW DEPTH"
-        },
-        {
-            "name": "WATERSHED DRAINAGE BASINS"
-        }
-    ],
-    "title": [
-        "More than one century of hydrological monitoring in two small catchments with different forest coverage, Sperbelgraben and Rappengraben (Switzerland)",
-        "Hydrologische Messungen Sperbel- und Rappengraben (1903 \u2013 2009)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/9ef2871b-20c5-59ab-924a-54a415554ada.json b/oaitestdata/envidat-datacite/SET_1/json/9ef2871b-20c5-59ab-924a-54a415554ada.json
deleted file mode 100644
index 38295c03..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/9ef2871b-20c5-59ab-924a-54a415554ada.json
+++ /dev/null
@@ -1,108 +0,0 @@
-{
-    "Contact": [
-        "Benjamin Reuter"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/envidat.40",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "PDF",
-        "CSV"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:3735a11a-34a5-4a83-b2db-ed22484589d8",
-    "MetadataAccess": [
-        "oai:envidat.ch:3735a11a-34a5-4a83-b2db-ed22484589d8"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avalanche Research SLF"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/data-snow-instability"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N-47N,10E-10E)",
-    "TempCoverageBegin": 63180820799,
-    "TempCoverageEnd": 63180820799,
-    "TemporalCoverage": " point in time : 2003-02-14T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2003-02-14T11:59:59Z",
-    "TemporalCoverage:EndDate": "2003-02-14T11:59:59Z",
-    "author": [
-        "Benjamin Reuter",
-        "Sascha Bellaire",
-        "Alec van Herwijnen",
-        "J\u00fcrg Schweizer"
-    ],
-    "fulltext": "oai:envidat.ch:3735a11a-34a5-4a83-b2db-ed22484589d8;2018-12-06T17:34:19Z;10.16904/envidat.40;Benjamin Reuter;0000-0002-7302-3858;WSL Institute for Snow and Avalanche Research SLF;Alec van Herwijnen;0000-0001-5637-6486;WSL Institute for Snow and Avalanche Research SLF;Sascha Bellaire;WSL Institute for Snow and Avalanche Research SLF;J\u00fcrg Schweizer;0000-0001-5076-2968;WSL Institute for Snow and Avalanche Research SLF;Data set on snow instability;Snow instability;2018;WSL Institute for Snow and Avalanche Research SLF;AVALANCHE FORCASTING;CRACK PROPAGATION;FAILURE INITIATION;PROPGATOIN SAW TEST;RUTSCHBLOCK;SLAB;SLAB TENSILE SUPPORT;SNOW AVALANCHE;SNOW STABILITY EVALUATION;WEAK LAYER;Benjamin Reuter;0000-0002-7302-3858;WSL Institute for Snow and Avalanche Research SLF;2003-02-14;en;Dataset;https://www.envidat.ch/dataset/data-snow-instability;10332 bytes;172308 bytes;CSV;PDF;1.0;Open Data Commons Open Database License (ODbL);These data on snow instability include three data subsets that were analyzed and the results published by Reuter and Schweizer (2018) who suggest a novel framework on how to describe snow instability by failure initiation, crack propagation and slab tensile support.\n\nPlease refer to the Read-me file for further details on the data.\n\nThese data are the basis of the following publication:\nReuter, B. and Schweizer, J., 2018. Describing snow instability by failure initiation, crack propagation and slab tensile support. Geophys. Res. Lett., 45, doi: 10.1029/2018GL078069.;46.7353429853 9.73182678223 46.8707071353 9.96528625488;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "9ef2871b-20c5-59ab-924a-54a415554ada",
-    "notes": [
-        "These data on snow instability include three data subsets that were analyzed and the results published by Reuter and Schweizer (2018) who suggest a novel framework on how to describe snow instability by failure initiation, crack propagation and slab tensile support.\n\nPlease refer to the Read-me file for further details on the data.\n\nThese data are the basis of the following publication:\nReuter, B. and Schweizer, J., 2018. Describing snow instability by failure initiation, crack propagation and slab tensile support. Geophys. Res. Lett., 45, doi: 10.1029/2018GL078069."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:3735a11a-34a5-4a83-b2db-ed22484589d8"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[9.73182678223,46.7353429853],[9.73182678223,46.8707071353],[9.96528625488,46.8707071353],[9.96528625488,46.7353429853],[9.73182678223,46.7353429853]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "AVALANCHE FORCASTING"
-        },
-        {
-            "name": "CRACK PROPAGATION"
-        },
-        {
-            "name": "FAILURE INITIATION"
-        },
-        {
-            "name": "PROPGATOIN SAW TEST"
-        },
-        {
-            "name": "RUTSCHBLOCK"
-        },
-        {
-            "name": "SLAB"
-        },
-        {
-            "name": "SLAB TENSILE SUPPORT"
-        },
-        {
-            "name": "SNOW AVALANCHE"
-        },
-        {
-            "name": "SNOW STABILITY EVALUATION"
-        },
-        {
-            "name": "WEAK LAYER"
-        }
-    ],
-    "title": [
-        "Data set on snow instability",
-        "Snow instability"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/a06d5b9f-ad90-5083-84f2-ff7aa11bf981.json b/oaitestdata/envidat-datacite/SET_1/json/a06d5b9f-ad90-5083-84f2-ff7aa11bf981.json
deleted file mode 100644
index 5896e2e7..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/a06d5b9f-ad90-5083-84f2-ff7aa11bf981.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:47696adf-552e-45d7-a08f-fd43a66c8a2c",
-    "MetadataAccess": [
-        "oai:envidat.ch:47696adf-552e-45d7-a08f-fd43a66c8a2c"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/twig_mass_of_live_trees-48"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:47696adf-552e-45d7-a08f-fd43a66c8a2c;2018-12-09T00:33:29Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Twig mass of live trees;2014;Swiss Federal Research Institute WSL;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;BIOGEOGRAPHICAL REGION;CANTON;CONIFERS-BROADLEAVES;ECONOMIC REGION;GRID NFI4 2009-2013;NFI3;NFI4B;PRODUCTION REGION;PROTECTION FOREST REGION;TERRESTRIAL GRID NFI3;TWIG MASS OF LIVE TREES;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/twig_mass_of_live_trees-48;URL;1.0;Other (Open);Dry weight (mass) of branches with a diameter under 7 cm from living trees and shrubs  starting at 12cm dbh.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "a06d5b9f-ad90-5083-84f2-ff7aa11bf981",
-    "notes": [
-        "Dry weight (mass) of branches with a diameter under 7 cm from living trees and shrubs  starting at 12cm dbh.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:47696adf-552e-45d7-a08f-fd43a66c8a2c"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "NFI"
-        },
-        {
-            "name": "NFIB"
-        },
-        {
-            "name": "PRODUCTION REGION"
-        },
-        {
-            "name": "PROTECTION FOREST REGION"
-        },
-        {
-            "name": "TERRESTRIAL GRID NFI"
-        }
-    ],
-    "title": [
-        "Twig mass of live trees"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/a1437f8d-ffa6-529c-bf0c-9edaf2997236.json b/oaitestdata/envidat-datacite/SET_1/json/a1437f8d-ffa6-529c-bf0c-9edaf2997236.json
deleted file mode 100644
index 0a977cf6..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/a1437f8d-ffa6-529c-bf0c-9edaf2997236.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:0011ce37-f55d-4169-86b7-0120ff278307",
-    "MetadataAccess": [
-        "oai:envidat.ch:0011ce37-f55d-4169-86b7-0120ff278307"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/salvage_logging_due_to_wind-88"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:0011ce37-f55d-4169-86b7-0120ff278307;2018-12-09T00:33:04Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Salvage logging due to wind;2014;Swiss Federal Research Institute WSL;14 X 14 KM GRID;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;ALTITUDINAL VEGETATION ZONE;BIOGEOGRAPHICAL REGION;ECONOMIC REGION;GRID NFI4 2009-2013;NFI2-NFI3;NFI3-NFI4B;PRODUCTION REGION;PROTECTION FOREST REGION;SALVAGE LOGGING DUE TO WIND;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/salvage_logging_due_to_wind-88;URL;1.0;Other (Open);Volume of stemwood with bark of all trees and shrubs  starting at 12 cm dbh removed from the forest between two inventories due to damage that occurred, in this case windthrow, and not due to silvicultural planning. This theme is derived on the level of a sample plot  from the cuttings of the sample trees and the salvage cut proportion (according to information from the forester).   The correction for bias with the sample Tarif trees may be so drastic that it results in negative values with small numbers of trees.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "a1437f8d-ffa6-529c-bf0c-9edaf2997236",
-    "notes": [
-        "Volume of stemwood with bark of all trees and shrubs  starting at 12 cm dbh removed from the forest between two inventories due to damage that occurred, in this case windthrow, and not due to silvicultural planning. This theme is derived on the level of a sample plot  from the cuttings of the sample trees and the salvage cut proportion (according to information from the forester).   The correction for bias with the sample Tarif trees may be so drastic that it results in negative values with small numbers of trees.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:0011ce37-f55d-4169-86b7-0120ff278307"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "X KM GRID"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "NFI-NFI"
-        },
-        {
-            "name": "NFI-NFIB"
-        },
-        {
-            "name": "PRODUCTION REGION"
-        }
-    ],
-    "title": [
-        "Salvage logging due to wind"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/a7da126e-1ac0-50ac-9e56-8543b61ae0d3.json b/oaitestdata/envidat-datacite/SET_1/json/a7da126e-1ac0-50ac-9e56-8543b61ae0d3.json
deleted file mode 100644
index eda12365..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/a7da126e-1ac0-50ac-9e56-8543b61ae0d3.json
+++ /dev/null
@@ -1,89 +0,0 @@
-{
-    "Contact": [
-        "Enrico Paterna"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/6",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "ZIP"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:78af269e-4d9d-4fc3-9039-9814a4872a07",
-    "MetadataAccess": [
-        "oai:envidat.ch:78af269e-4d9d-4fc3-9039-9814a4872a07"
-    ],
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avalanche Research SLF"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/10-16904-6"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N,10E)",
-    "TempCoverageBegin": 63666471599,
-    "TempCoverageEnd": 63666471599,
-    "TemporalCoverage": " point in time : 2018-07-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-07-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-07-06T11:59:59Z",
-    "author": [
-        "Philip Crivelli",
-        "Enrico Paterna"
-    ],
-    "fulltext": "oai:envidat.ch:78af269e-4d9d-4fc3-9039-9814a4872a07;2018-12-09T00:31:11Z;10.16904/6;Enrico Paterna;SLF;Philip Crivelli;SLF;Wind tunnel measurement data of drifting snow and turbulent wind fluctuations;2016;WSL Institute for Snow and Avalanche Research SLF;BOUNDARY LAYER WINDS;SALTATION;SNOW COVER;SNOW DEPTH;VERTICAL WIND MOTION;Enrico Paterna;SLF;2018-07-06;en;Dataset;https://www.envidat.ch/dataset/10-16904-6;ZIP;1;Open Data Commons Open Database License (ODbL);The data correspond to the experiments presented and discussed in a paper regarding the interaction between turbulent wind fluctuations and snow saltation mass-fluxes (Paterna, 2016). Each of the nine data files corresponds to a different experiment presented in the paper and conducted in the winter 2014/2015 in the WSL/SLF cold wind tunnel in Davos. For each file the five columns indicate the time from the beginning of the experiment, the streamwise (u\u2019) and the vertical (w\u2019) wind velocity fluctuations, the streamwise (qx) and the vertical (qz) snow mass-flux components. From these time-series the scales of the snow saltation and of the turbulent flow are obtained with respect to the eddy-cycles and snow saltation cycles. From spectral analysis of the time-series a decoupling of the snow saltation from the turbulence forcing reveals two regimes of interaction: a turbulence-dependent regime occurring with weak saltation, and a turbulence-independent regime with strong saltation. Further details can be found at the link below. \n\n__Publication__ http://onlinelibrary.wiley.com/doi/10.1002/2016GL068171/abstract;46.81204 9.84726;SLF Davos Dorf (GR), Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "a7da126e-1ac0-50ac-9e56-8543b61ae0d3",
-    "notes": [
-        "The data correspond to the experiments presented and discussed in a paper regarding the interaction between turbulent wind fluctuations and snow saltation mass-fluxes (Paterna, 2016). Each of the nine data files corresponds to a different experiment presented in the paper and conducted in the winter 2014/2015 in the WSL/SLF cold wind tunnel in Davos. For each file the five columns indicate the time from the beginning of the experiment, the streamwise (u\u2019) and the vertical (w\u2019) wind velocity fluctuations, the streamwise (qx) and the vertical (qz) snow mass-flux components. From these time-series the scales of the snow saltation and of the turbulent flow are obtained with respect to the eddy-cycles and snow saltation cycles. From spectral analysis of the time-series a decoupling of the snow saltation from the turbulence forcing reveals two regimes of interaction: a turbulence-dependent regime occurring with weak saltation, and a turbulence-independent regime with strong saltation. Further details can be found at the link below. \n\n__Publication__ http://onlinelibrary.wiley.com/doi/10.1002/2016GL068171/abstract"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:78af269e-4d9d-4fc3-9039-9814a4872a07"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[9.84726,46.81204],[9.84726,46.81204],[9.84726,46.81204],[9.84726,46.81204],[9.84726,46.81204]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "BOUNDARY LAYER WINDS"
-        },
-        {
-            "name": "SALTATION"
-        },
-        {
-            "name": "SNOW COVER"
-        },
-        {
-            "name": "SNOW DEPTH"
-        },
-        {
-            "name": "VERTICAL WIND MOTION"
-        }
-    ],
-    "title": [
-        "Wind tunnel measurement data of drifting snow and turbulent wind fluctuations"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/a8fe9136-473c-5250-b06f-c126f9752b5b.json b/oaitestdata/envidat-datacite/SET_1/json/a8fe9136-473c-5250-b06f-c126f9752b5b.json
deleted file mode 100644
index e7bfc656..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/a8fe9136-473c-5250-b06f-c126f9752b5b.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Christian Ginzler"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/1000001.2",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "TXT",
-        "JPEG"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:33cb02f7-7ab0-49d6-8502-906d2c502ccc",
-    "MetadataAccess": [
-        "oai:envidat.ch:33cb02f7-7ab0-49d6-8502-906d2c502ccc"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "National Forest Inventory (NFI)"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/hillshade-for-vegetation-height-model-nfi"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Not Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63647639999,
-    "TempCoverageEnd": 63647639999,
-    "TemporalCoverage": " point in time : 2017-11-30T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2017-11-30T11:59:59Z",
-    "TemporalCoverage:EndDate": "2017-11-30T11:59:59Z",
-    "author": [
-        "Christian Ginzler"
-    ],
-    "fulltext": "oai:envidat.ch:33cb02f7-7ab0-49d6-8502-906d2c502ccc;2018-04-03T13:07:32Z;10.16904/1000001.2;Christian Ginzler;E-9544-2012;Swiss Federal Institute for Forest, Snow and Landscape Research WSL;Hillshade for Vegetation Height Model NFI;Reliefschattierung zum Vegetationsh\u00f6henmodell LFI;2018;National Forest Inventory (NFI);3D;DIGITAL SURFACE MODEL;IMAGE MATCHING;PHOTOGRAMMETY;POINT CLOUD;Christian Ginzler;E-9544-2012;Swiss Federal Institute for Forest, Snow and Landscape Research WSL;2017-11-30;en;Dataset;https://www.envidat.ch/dataset/hillshade-for-vegetation-height-model-nfi;102 bytes;6054021 bytes;TXT;JPEG;2016 (current);Other (Not Open);Hillshade of the digital surface model (DSM), calculated from digital aerial stereo images. The image data was acquired by the Federal Office of Topography swisstopo. The resolution of the DSM is 1 m x 1 m.;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "a8fe9136-473c-5250-b06f-c126f9752b5b",
-    "notes": [
-        "Hillshade of the digital surface model (DSM), calculated from digital aerial stereo images. The image data was acquired by the Federal Office of Topography swisstopo. The resolution of the DSM is 1 m x 1 m."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:33cb02f7-7ab0-49d6-8502-906d2c502ccc"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "DIGITAL SURFACE MODEL"
-        },
-        {
-            "name": "IMAGE MATCHING"
-        },
-        {
-            "name": "PHOTOGRAMMETY"
-        },
-        {
-            "name": "POINT CLOUD"
-        }
-    ],
-    "title": [
-        "Hillshade for Vegetation Height Model NFI",
-        "Reliefschattierung zum Vegetationsh\u00f6henmodell LFI"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/aa4e37a7-3b2c-54df-8f60-0cdca951d0c4.json b/oaitestdata/envidat-datacite/SET_1/json/aa4e37a7-3b2c-54df-8f60-0cdca951d0c4.json
deleted file mode 100644
index 9189666f..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/aa4e37a7-3b2c-54df-8f60-0cdca951d0c4.json
+++ /dev/null
@@ -1,89 +0,0 @@
-{
-    "Contact": [
-        "Christian Sommer"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/22",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "TXT",
-        "Link",
-        "ZIP"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:d57b3332-804d-463b-bbf8-0ed38593e180",
-    "MetadataAccess": [
-        "oai:envidat.ch:d57b3332-804d-463b-bbf8-0ed38593e180"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/10-16904-22"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N,10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Charles Fierz",
-        "Michael Lehning",
-        "Christian G. Sommer"
-    ],
-    "fulltext": "oai:envidat.ch:d57b3332-804d-463b-bbf8-0ed38593e180;2018-12-09T00:31:07Z;10.16904/22;Christian G. Sommer;WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland and CRYOS, School of Architecture and Civil Engineering, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland;Michael Lehning;WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland and CRYOS, School of Architecture and Civil Engineering, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland;Charles Fierz;WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland;Wind crust formation: Microsoft Kinect data;2017;WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland;KINECT;SNOW;WIND CRUST;WIND-PACKING;Christian Sommer;WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland and CRYOS, School of Architecture and Civil Engineering, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/10-16904-22;967 bytes;35366 bytes;Link;TXT;ZIP;1.0;Open Data Commons Open Database License (ODbL);This data sets contains the Microsoft Kinect data from 15 wind tunnel experiments on wind-packing / wind crust formation. These experiments were performed in the winter 2016/17. The Kinect measures distributed snow depth.\n\nThe Kinect data is organized per experiment. Each experiment subfolder contains the processed Kinect depth images and some additional files.\n\nPlease refer to the README for more details on the data. The processing scripts are available for download as well. The scripts are mainly provided as documentation and would need to be adjusted to be used.\n\nThis dataset is the basis of the following publication:\n\nSommer C.G., Lehning M. & Fierz C. (2018). Wind Tunnel Experiments: Influence of Erosion and Deposition on Wind-Packing of New Snow. Front. Earth Sci. 6:4. doi: 10.3389/feart.2018.00004;46.80798 9.86752;Davos, Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "aa4e37a7-3b2c-54df-8f60-0cdca951d0c4",
-    "notes": [
-        "This data sets contains the Microsoft Kinect data from 15 wind tunnel experiments on wind-packing / wind crust formation. These experiments were performed in the winter 2016/17. The Kinect measures distributed snow depth.\n\nThe Kinect data is organized per experiment. Each experiment subfolder contains the processed Kinect depth images and some additional files.\n\nPlease refer to the README for more details on the data. The processing scripts are available for download as well. The scripts are mainly provided as documentation and would need to be adjusted to be used.\n\nThis dataset is the basis of the following publication:\n\nSommer C.G., Lehning M. & Fierz C. (2018). Wind Tunnel Experiments: Influence of Erosion and Deposition on Wind-Packing of New Snow. Front. Earth Sci. 6:4. doi: 10.3389/feart.2018.00004"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:d57b3332-804d-463b-bbf8-0ed38593e180"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[9.86752,46.80798],[9.86752,46.80798],[9.86752,46.80798],[9.86752,46.80798],[9.86752,46.80798]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "KINECT"
-        },
-        {
-            "name": "SNOW"
-        },
-        {
-            "name": "WIND CRUST"
-        },
-        {
-            "name": "WIND-PACKING"
-        }
-    ],
-    "title": [
-        "Wind crust formation: Microsoft Kinect data"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/ab70d864-8ea7-598e-b3b2-b2ef14e906ed.json b/oaitestdata/envidat-datacite/SET_1/json/ab70d864-8ea7-598e-b3b2-b2ef14e906ed.json
deleted file mode 100644
index 5ef52ed6..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/ab70d864-8ea7-598e-b3b2-b2ef14e906ed.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:b405bf38-a017-4888-b3b0-a25dae1ec43e",
-    "MetadataAccess": [
-        "oai:envidat.ch:b405bf38-a017-4888-b3b0-a25dae1ec43e"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/biomass_above_ground_of_live_trees-19"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:b405bf38-a017-4888-b3b0-a25dae1ec43e;2018-12-09T00:31:28Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Biomass above ground of live trees;2014;Swiss Federal Research Institute WSL;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;BIOGEOGRAPHICAL REGION;BIOMASS ABOVE GROUND OF LIVE TREES;CANTON;CONIFERS-BROADLEAVES;ECONOMIC REGION;GRID NFI4 2009-2013;NFI3;NFI4B;PRODUCTION REGION;PROTECTION FOREST REGION;TERRESTRIAL GRID NFI3;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/biomass_above_ground_of_live_trees-19;URL;1.0;Other (Open);Dry weight (mass) of the aboveground parts of living trees and shrubs  starting at 12 cm dbh. This consists of the tree parts: stemwood, branch coarse wood, brushwood/twigs and needles/leaves. The correction for bias with the sample Tarif trees may be so drastic that it results in negative values with small numbers of trees.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "ab70d864-8ea7-598e-b3b2-b2ef14e906ed",
-    "notes": [
-        "Dry weight (mass) of the aboveground parts of living trees and shrubs  starting at 12 cm dbh. This consists of the tree parts: stemwood, branch coarse wood, brushwood/twigs and needles/leaves. The correction for bias with the sample Tarif trees may be so drastic that it results in negative values with small numbers of trees.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:b405bf38-a017-4888-b3b0-a25dae1ec43e"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "BIOMASS GROUND LIVE TREES"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "NFI"
-        },
-        {
-            "name": "NFIB"
-        },
-        {
-            "name": "PRODUCTION REGION"
-        },
-        {
-            "name": "PROTECTION FOREST REGION"
-        }
-    ],
-    "title": [
-        "Biomass above ground of live trees"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/ad43a2a8-52af-5c78-8ba7-302efc04a3f7.json b/oaitestdata/envidat-datacite/SET_1/json/ad43a2a8-52af-5c78-8ba7-302efc04a3f7.json
deleted file mode 100644
index 59a1a986..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/ad43a2a8-52af-5c78-8ba7-302efc04a3f7.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "EnviDat Admin"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "XML",
-        "JPEG"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:3397f564-fb50-41ac-a8f1-b2549c9524ba",
-    "MetadataAccess": [
-        "oai:envidat.ch:3397f564-fb50-41ac-a8f1-b2549c9524ba"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/ckanext-restricted-test"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": [
-        "47.405771 8.498823",
-        "47.3811492228 8.45569610596",
-        "47.3502216389 8.45191955566",
-        "47.3444061587 8.49449157715",
-        "47.3716170889 8.51818084717"
-    ],
-    "TempCoverageBegin": 63657831599,
-    "TempCoverageEnd": 63657831599,
-    "TemporalCoverage": " point in time : 2018-03-28T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-03-28T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-03-28T11:59:59Z",
-    "author": [
-        "Lucia Espona Pernas",
-        "Ionu\u021b Iosifescu"
-    ],
-    "fulltext": "oai:envidat.ch:3397f564-fb50-41ac-a8f1-b2549c9524ba;2018-12-06T17:34:13Z;Lucia Espona Pernas;WSL;Ionu\u021b Iosifescu;WSL;Dataset for testing resource access restriction;2017;TEST;EnviDat Admin;WSL;2018-03-28;en;https://www.envidat.ch/dataset/ckanext-restricted-test;752433 bytes;1566353 bytes;1114188 bytes;85739 bytes;5358 bytes;JPEG;XML;1.0;Open Data Commons Open Database License (ODbL);# Test Record\n## Testing the markdown\n### testing 3 heading\n\nThis is a __temporary dataset for testing pourposes__. The extension ckanext-restricted (https://github.com/espona/ckanext-restricted) has been developed to allow users further access control for the data (resources) of their datasets. Feel free to give it a try and report any issue to envidat@wsl.ch.\n\n* list item 1\n* list item 2\n* list item 3;47.405771 8.498823;47.3811492228 8.45569610596;47.3502216389 8.45191955566;47.3444061587 8.49449157715;47.3716170889 8.51818084717",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "ad43a2a8-52af-5c78-8ba7-302efc04a3f7",
-    "notes": [
-        "# Test Record\n## Testing the markdown\n### testing 3 heading\n\nThis is a __temporary dataset for testing pourposes__. The extension ckanext-restricted (https://github.com/espona/ckanext-restricted) has been developed to allow users further access control for the data (resources) of their datasets. Feel free to give it a try and report any issue to envidat@wsl.ch.\n\n* list item 1\n* list item 2\n* list item 3"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:3397f564-fb50-41ac-a8f1-b2549c9524ba"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "TEST"
-        }
-    ],
-    "title": [
-        "Dataset for testing resource access restriction"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/afe2314f-2499-52e1-bf56-db2492a9840a.json b/oaitestdata/envidat-datacite/SET_1/json/afe2314f-2499-52e1-bf56-db2492a9840a.json
deleted file mode 100644
index 2776b2bd..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/afe2314f-2499-52e1-bf56-db2492a9840a.json
+++ /dev/null
@@ -1,98 +0,0 @@
-{
-    "Contact": [
-        "Michael Lehning"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/envidat.28",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "SNO",
-        "SMET",
-        "TXT"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:640b09be-3b86-492e-aba2-449329969989",
-    "MetadataAccess": [
-        "oai:envidat.ch:640b09be-3b86-492e-aba2-449329969989"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avalanche Research SLF"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/10-16904-envidat-28"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": [
-        "46.808 9.868",
-        "46.517 10.727"
-    ],
-    "TempCoverageBegin": 63565901999,
-    "TempCoverageEnd": 63565901999,
-    "TemporalCoverage": " point in time : 2015-04-29T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2015-04-29T11:59:59Z",
-    "TemporalCoverage:EndDate": "2015-04-29T11:59:59Z",
-    "author": [
-        "Fabian Wolfsperger",
-        "Michael Lehning",
-        "Thomas Gr\u00fcnewald"
-    ],
-    "fulltext": "oai:envidat.ch:640b09be-3b86-492e-aba2-449329969989;2018-12-06T17:34:44Z;10.16904/envidat.28;Thomas Gr\u00fcnewald;WSL Institute for Snow and Avalanche Research SLF;Fabian Wolfsperger;WSL Institute for Snow and Avalanche Research SLF;Michael Lehning;WSL Institute for Snow and Avalanche Research SLF;Snowfarming data set Davos and Martell 2015;TLS measurements and Meteodata;2018;WSL Institute for Snow and Avalanche Research SLF;SNOW;SNOW CONSERVATION;SNOW FARMING;SNOWPACK;TERRESTRIAL LASER SCANNING;WINTER TOURISM;Michael Lehning;SLF;2015-04-29;en;Dataset;https://www.envidat.ch/dataset/10-16904-envidat-28;1919 bytes;1761 bytes;827214 bytes;889965 bytes;1702059 bytes;1720506 bytes;2412003 bytes;2332516 bytes;SNO;SMET;TXT;1.0;Open Data Commons Open Database License (ODbL);Two data sets obtained for snow farming projects (Fluela, Davos, CH and Martell, IT) in 2015. \n\nThe data set contains for each site:\n\n* 10 cm GIS raster of snow depth calculated from terrestrial laserscanning surveys (TLS) in the end of winter season (April/May)\n\n* 10 cm GIS raster of snow depth calculated from TLS in the end of summer season (October)\n\nInput files for SNOWPACK model:\n\n* .sno: snow profile at the end of winter\n\n* .smet: meteorological data measured by weather stations in the area\n\nFor more details see  Gr\u00fcnewald, T., Lehning, M., and Wolfsperger, F.: Snow farming: Conserving snow over the summer season, The Cryosphere Discuss., https://doi.org/10.5194/tc-2017-93, in review, 2017.;46.808 9.868;46.517 10.727;Davos, Switzerland (lat: 46.808\u00b0 N, long: 9.868\u00b0 E) and Martell, South Tyrol (lat: 46.517\u00b0 N, long: 10.727\u00b0 E",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "afe2314f-2499-52e1-bf56-db2492a9840a",
-    "notes": [
-        "Two data sets obtained for snow farming projects (Fluela, Davos, CH and Martell, IT) in 2015. \n\nThe data set contains for each site:\n\n* 10 cm GIS raster of snow depth calculated from terrestrial laserscanning surveys (TLS) in the end of winter season (April/May)\n\n* 10 cm GIS raster of snow depth calculated from TLS in the end of summer season (October)\n\nInput files for SNOWPACK model:\n\n* .sno: snow profile at the end of winter\n\n* .smet: meteorological data measured by weather stations in the area\n\nFor more details see  Gr\u00fcnewald, T., Lehning, M., and Wolfsperger, F.: Snow farming: Conserving snow over the summer season, The Cryosphere Discuss., https://doi.org/10.5194/tc-2017-93, in review, 2017."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:640b09be-3b86-492e-aba2-449329969989"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "SNOW"
-        },
-        {
-            "name": "SNOW CONSERVATION"
-        },
-        {
-            "name": "SNOW FARMING"
-        },
-        {
-            "name": "SNOWPACK"
-        },
-        {
-            "name": "TERRESTRIAL LASER SCANNING"
-        },
-        {
-            "name": "WINTER TOURISM"
-        }
-    ],
-    "title": [
-        "Snowfarming data set Davos and Martell 2015",
-        "TLS measurements and Meteodata"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/b0710e18-972a-5069-9e6a-f04b106a2d20.json b/oaitestdata/envidat-datacite/SET_1/json/b0710e18-972a-5069-9e6a-f04b106a2d20.json
deleted file mode 100644
index 980820c0..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/b0710e18-972a-5069-9e6a-f04b106a2d20.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:b2b29928-8591-4689-87be-fa99fb6517bc",
-    "MetadataAccess": [
-        "oai:envidat.ch:b2b29928-8591-4689-87be-fa99fb6517bc"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/number_of_woody_species_from_40_cm_height-144"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:b2b29928-8591-4689-87be-fa99fb6517bc;2018-12-09T00:32:47Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Number of woody species (from 40 cm height);2014;Swiss Federal Research Institute WSL;7 CLASSES;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;ALTITUDINAL VEGETATION ZONE;ALTITUDINAL VEGETATION ZONE 3 CLASSES;BIOGEOGRAPHICAL REGION;CANTON;ECONOMIC REGION;FOREST COMMUNITIES K\u00dcCHLER 2008;GRID NFI4 2009-2013;NFI3;NFI4B;NUMBER OF WOODY SPECIES FROM 40 CM HEIGHT;PRIMARY FOREST FUNCTION NFI4 NATURE PROTECTION;PRODUCTION REGION;PROTECTION FOREST REGION;TERRESTRIAL GRID NFI3;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/number_of_woody_species_from_40_cm_height-144;URL;1.0;Other (Open);Number of species of living trees and shrubs  starting at 40 cm plant height that occur within a 200 m2 sample plot.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "b0710e18-972a-5069-9e6a-f04b106a2d20",
-    "notes": [
-        "Number of species of living trees and shrubs  starting at 40 cm plant height that occur within a 200 m2 sample plot.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:b2b29928-8591-4689-87be-fa99fb6517bc"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "CLASSES"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE CLASSES"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "NFI"
-        }
-    ],
-    "title": [
-        "Number of woody species (from 40 cm height)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/b4609719-90c6-5164-813f-f9d603e20f69.json b/oaitestdata/envidat-datacite/SET_1/json/b4609719-90c6-5164-813f-f9d603e20f69.json
deleted file mode 100644
index 88f921cc..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/b4609719-90c6-5164-813f-f9d603e20f69.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:2b8a752c-968d-418b-9ac2-bc9c597801d2",
-    "MetadataAccess": [
-        "oai:envidat.ch:2b8a752c-968d-418b-9ac2-bc9c597801d2"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/area_of_shrub_forest-123"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:2b8a752c-968d-418b-9ac2-bc9c597801d2;2018-12-09T00:31:18Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Area of shrub forest;2014;Swiss Federal Research Institute WSL;ACCESSIBLE SHRUB FOREST;ALTITUDE 400 M CLASSES;AREA OF SHRUB FOREST;BIOGEOGRAPHICAL REGION;ECONOMIC REGION;GRID NFI4 2009-2013;NFI3;NFI4B;PREDOMINANT WOODY SPECIES IN THE SHRUB FOREST;PRODUCTION REGION;SHRUB FOREST;TERRESTRIAL GRID NFI3;TYPE OF SHRUB FOREST AERIAL PHOTO;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/area_of_shrub_forest-123;URL;1.0;Other (Open);All plots classified as shrub forest according to the NFI forest definition.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "b4609719-90c6-5164-813f-f9d603e20f69",
-    "notes": [
-        "All plots classified as shrub forest according to the NFI forest definition.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:2b8a752c-968d-418b-9ac2-bc9c597801d2"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE SHRUB FOREST"
-        },
-        {
-            "name": "ALTITUDE M CLASSES"
-        },
-        {
-            "name": "AREA SHRUB FOREST"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "NFI"
-        },
-        {
-            "name": "NFIB"
-        },
-        {
-            "name": "PREDOMINANT WOODY SPECIES SHRUB FOREST"
-        },
-        {
-            "name": "PRODUCTION REGION"
-        },
-        {
-            "name": "SHRUB FOREST"
-        },
-        {
-            "name": "TERRESTRIAL GRID NFI"
-        }
-    ],
-    "title": [
-        "Area of shrub forest"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/b4fe40b4-1fac-5fd9-96f3-22d0c7fd8e3f.json b/oaitestdata/envidat-datacite/SET_1/json/b4fe40b4-1fac-5fd9-96f3-22d0c7fd8e3f.json
deleted file mode 100644
index d492582f..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/b4fe40b4-1fac-5fd9-96f3-22d0c7fd8e3f.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:006aefed-0e93-4168-99d6-c9a8ea76ba53",
-    "MetadataAccess": [
-        "oai:envidat.ch:006aefed-0e93-4168-99d6-c9a8ea76ba53"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/forest_area-44"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:006aefed-0e93-4168-99d6-c9a8ea76ba53;2018-12-09T00:31:46Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Forest area;2014;Swiss Federal Research Institute WSL;14 X 14 KM GRID;5 CLASSES;7 CLASSES;ACCESSIBLE FOREST NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;ALTITUDE 200 M CLASS;ALTITUDE 400 M CLASSES;ALTITUDINAL VEGETATION ZONE;ALTITUDINAL VEGETATION ZONE 3 CLASSES;AVALANCHES SILVAPROTECT;BASAL AREA OF CONIFERS CLASSIFIED;BASAL AREA STANDING LIVE TREES;BASIS FOR LOCAL PLANNING;BIOGEOGRAPHICAL REGION;BIOTOPE VALUE NFI1;BIOTOPE VALUE NFI2;CANTON;CAUSE OF SALVAGE LOGGING;CERTIFICATION LABEL;CLASSIFIED;CLOSENESS TO NATURE OF CONIFERS IN BROADLEAF AREA;CONCEPT OF TRANSPORTATION SYSTEM;CROWN CLOSURE;DEGREE OF COVER AERIAL PHOTO;DEGREE OF COVER OF ASSURED REGENERATION;DEGREE OF COVER OF REGENERATION 7 CLASSES;DEGREE OF DAMAGE OF THE STAND;DEGREE OF MIXTURE;DOMINANCE BY EXOTIC SPECIES NEOPHYTES;DOMINANT DIAMETER 5 CLASSES;DOMINANT DIAMETER CLASS SIZE 10CM;DOMINATED BY EXOTIC SPECIES 2 CLASSES;ECONOMIC REGION;EXPOSITION 4 CLASSES;EXPOSITION 8 CLASSES;FOREST;FOREST AREA;FOREST COMMUNITIES K\u00dcCHLER 2008;FOREST DISTRICT AS OF 2013;FOREST FUNCTION AGRICULTURAL USE;FOREST FUNCTION DRINKING WATER;FOREST FUNCTION GAME RESERVE;FOREST FUNCTION LANDSCAPE PROTECTION;FOREST FUNCTION MILITARY;FOREST FUNCTION NATURE PROTECTION;FOREST FUNCTION PROTECTION AGAINST NATURAL HAZARDS;FOREST FUNCTION RECREATION;FOREST FUNCTION SHELTERBELT;FOREST FUNCTION WOOD PRODUCTION;FOREST MANAGEMENT INTENSITY NFI1 MODEL;FOREST NFI3-NFI4;FOREST TYPE 12 CLASSES;FOREST TYPE 3 CLASSES;FOREST TYPE AND STAGE OF DEVELOPMENT;FOREST WITHOUT SHRUB FOREST - SHRUB FOREST;FOREST WITHOUT SHRUB FOREST-SHRUB FOREST-NONFOREST;FORESTRY PLANS;GRID NFI4 2009-2013;GROUNDWATER PROTECTION ZONES APRIL 2013;HARVEST OF TIMBER;HARVESTING SYSTEMS;HORIZONTAL DISTANCE SAMPLE PLOT-ROAD 4 CLASSES;INDICATOR OF GROUNDWATER PROTECTION ZONE 2013;LANDSLIDE-MUDFLOW SILVAPROTECT;LOWER-HIGHER ALTITUDINAL ZONES;MAIN TYPE OF HARVEST;MEANS OF TRANSPORT BY HAND;MEANS OF TRANSPORT CABLE CRANE;MEANS OF TRANSPORT CABLEWAY;MEANS OF TRANSPORT CLAMBUNK-GRAPPLE;MEANS OF TRANSPORT FORESTRY TRACTOR;MEANS OF TRANSPORT FORWARDER;MEANS OF TRANSPORT HELICOPTER;MEANS OF TRANSPORT HORSE;MEANS OF TRANSPORT MOBILE TOWER YARDER;MEANS OF TRANSPORT OTHERS;MEANS OF TRANSPORT SHIP;MEANS OF TRANSPORT SINGLE WINCH;MEANS OF TRANSPORT SKIDDER;MEANS OF TRANSPORT SLEDGE;MEANS OF TRANSPORT TRACKED SKIDDER;MEANS OF TRANSPORT TRAILER WITH BOOM;MEANS OF TRANSPORT WINCH MOUNTED;METHOD OF TIMBER HARVEST;METHOD OF TIMBER HARVEST ASSORTMENT-FULL TREE;METHOD OF TIMBER HARVEST DEGREE OF MECHANIZATION;NFI1;NFI2;NFI3;NFI4;NFI4B;NON-SPF;NONFOREST;NUMBER OF TREE SPECIES IN THE UPPER LAYER;NUMBER OF TYPES NATURAL HAZARDS SILVAPROTECT;ORIGIN OF THE FOREST;ORIGIN OF THE STAND;OWNERSHIP;PERCENTAGE OF SALVAGE LOGGING;POTENTIAL COST FOR TIMBER HARVESTING;POTENTIAL DEMAND FOR LOCAL RECREATION;PREDOMINANT TREE CLASS;PREDOMINANT TREE SPECIES;PREHAULAGE DISTANCE;PRIMARY FOREST FUNCTION NFI4;PRIMARY FOREST FUNCTION NFI4 NATURE PROTECTION;PRIMARY FOREST FUNCTION NLS;PRIMARY FUNCTION NFI3;PROCESSES IN CHANNELS SILVAPROTECT;PRODUCTION REGION;PROTECTION FOREST PERIMETER SILVAPROTECT;PROTECTION FOREST REGION;REGENERATION COVER;RELIEF;RESTRICTIONS FOR TIMBER HARVEST;ROCKFALL SILVAPROTECT;SILVICULTURAL TREATMENT BETWEEN NFI2 AND NFI3;SILVICULTURAL TREATMENT BETWEEN NFI3 AND NFI4;SITE QUALITY;SIZE OF MANAGED UNIT;SIZE OF STAND;SLOPE 20 CLASSES;SLOPE 40 CLASSES;SLOPE DISTANCE SAMPLE PLOT-ROAD 4 CLASSES;SPECIAL FOREST FUNCTION;SPECIAL FOREST FUNCTION - PROTECTION FOREST;SPF;STAGE OF STAND DEVELOPMENT;STAND AGE CLASSES OF 20 YEARS;STAND AGE CLASSES OF 40 YEARS;STAND DENSITY INDEX SDI;STAND RELEVANT TO REGENERATION;STAND STABILITY;STAND STRUCTURE;STAND WITH OLD TIMBER;STATE OF CERTIFICATION;STATUS OF REGIONAL PLANNING;STATUS OF TRANSPORTATION SYSTEM;STEM COUNT-HA DBH GTE 12CM;STEM COUNT-HA DBH GTE 24CM;STEM COUNT-HA DBH GTE 36CM;STRUCTURAL DIVERSITY OF THE STAND;TERRESTRIAL GRID NFI1;TERRESTRIAL GRID NFI2;TERRESTRIAL GRID NFI3;TIME OF LAST TREATMENT;TIME OF LAST TREATMENT CLASSES OF 10 YEARS;TOTAL AREA;TOTAL SKIDDING DISTANCE PER SAMPLE PLOT;TYPE OF INTERVENTION IN 2002;TYPE OF NEXT TREATMENT INTERVIEW SURVEY;TYPE OF OWNERSHIP;TYPE OF REGENERATION;TYPE OF SILVICULTURAL TREATMENT IN 2004;TYPE OF SILVICULTURAL TREATMENT IN 2005;TYPE OF SILVICULTURAL TREATMENT IN 2006;TYPE OF SILVICULTURAL TREATMENT IN 2007;TYPE OF SILVICULTURAL TREATMENT IN 2008;TYPE OF SILVICULTURAL TREATMENT IN 2009;TYPE OF SILVICULTURAL TREATMENT IN 2010;TYPE OF SILVICULTURAL TREATMENT IN 2011;TYPE OF SILVICULTURAL TREATMENT IN 2012;TYPE OF SILVICULTURAL TREATMENT IN 2013;TYPE OF TREATMENT IN 1996;TYPE OF TREATMENT IN 1997;TYPE OF TREATMENT IN 1998;TYPE OF TREATMENT IN 1999;TYPE OF TREATMENT IN 2000;TYPE OF TREATMENT IN 2001;TYPE OF TREATMENT IN 2003;URGENCY OF NEXT TREATMENT INTERVIEW SURVEY;WATERSHED;WITHOUT LARIX K;YEAR OF AFFORESTATION 5 CLASSES;YEAR OF AFFORESTATION CLASSES;YEAR OF AFFORESTATION DECADES;YEAR OF LOCAL FOREST PLANNING 4 CLASSES;YEAR OF REGIONAL FOREST PLANNING 6 CLASSES;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/forest_area-44;URL;1.0;Other (Open);The forest area is the total sum of all areas classified as forest according to NFI\u2019s forest definition. The forest definition includes shrub forest.  This theme is also used to assess the total area when forest and non-forest need to be distinguished.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "b4fe40b4-1fac-5fd9-96f3-22d0c7fd8e3f",
-    "notes": [
-        "The forest area is the total sum of all areas classified as forest according to NFI\u2019s forest definition. The forest definition includes shrub forest.  This theme is also used to assess the total area when forest and non-forest need to be distinguished.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:006aefed-0e93-4168-99d6-c9a8ea76ba53"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "X KM GRID"
-        },
-        {
-            "name": "CLASSES"
-        },
-        {
-            "name": "CLASSES"
-        },
-        {
-            "name": "ACCESSIBLE FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ALTITUDE M CLASS"
-        },
-        {
-            "name": "ALTITUDE M CLASSES"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE CLASSES"
-        },
-        {
-            "name": "AVALANCHES SILVAPROTECT"
-        }
-    ],
-    "title": [
-        "Forest area"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/b6138762-3250-5893-ac96-5139384f9f5b.json b/oaitestdata/envidat-datacite/SET_1/json/b6138762-3250-5893-ac96-5139384f9f5b.json
deleted file mode 100644
index b8a88b51..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/b6138762-3250-5893-ac96-5139384f9f5b.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:1fb966ed-48a2-437c-93a1-1d86a8ac8808",
-    "MetadataAccess": [
-        "oai:envidat.ch:1fb966ed-48a2-437c-93a1-1d86a8ac8808"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/yield_star-161"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:1fb966ed-48a2-437c-93a1-1d86a8ac8808;2018-12-09T00:33:47Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Yield*;2014;Swiss Federal Research Institute WSL;14 X 14 KM GRID;56 CLASSES;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;ALTITUDE 400 M CLASSES;ALTITUDINAL VEGETATION ZONE;AVALANCHES SILVAPROTECT;CANTON;CONIFERS-BROADLEAVES;FOREST DISTRICT AS OF 2013;FOREST TYPE 12 CLASSES;GRID NFI4 2009-2013;LANDSLIDE-MUDFLOW SILVAPROTECT;LOWER-HIGHER ALTITUDINAL ZONES;MAIN TREE SPECIES;NET INCREMENT STAR;NFI2-NFI3;NFI3-NFI4B;OWNERSHIP;POTENTIAL COST FOR TIMBER HARVESTING;PROCESSES IN CHANNELS SILVAPROTECT;PROTECTION FOREST PERIMETER SILVAPROTECT;ROCKFALL SILVAPROTECT;STAGE OF STAND DEVELOPMENT;TREE SPECIES WOODY SPECIES;YIELD STAR;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/yield_star-161;URL;1.0;Other (Open);Volume of stemwood with bark of all trees and shrubs  starting at 12 cm dbh cut between two inventories.  *In the calculation no D7/tree height data were used. The values calculated like this have not been corrected for bias, but allow for cantons or forest districts a more robust estimation of changes and could thus be better interpreted.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "b6138762-3250-5893-ac96-5139384f9f5b",
-    "notes": [
-        "Volume of stemwood with bark of all trees and shrubs  starting at 12 cm dbh cut between two inventories.  *In the calculation no D7/tree height data were used. The values calculated like this have not been corrected for bias, but allow for cantons or forest districts a more robust estimation of changes and could thus be better interpreted.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:1fb966ed-48a2-437c-93a1-1d86a8ac8808"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "X KM GRID"
-        },
-        {
-            "name": "CLASSES"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ALTITUDE M CLASSES"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "AVALANCHES SILVAPROTECT"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        },
-        {
-            "name": "FOREST DISTRICT"
-        }
-    ],
-    "title": [
-        "Yield*"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/b853dd1f-86eb-5e85-a461-679c0541d7e9.json b/oaitestdata/envidat-datacite/SET_1/json/b853dd1f-86eb-5e85-a461-679c0541d7e9.json
deleted file mode 100644
index 63cdc254..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/b853dd1f-86eb-5e85-a461-679c0541d7e9.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:0c06e2c9-c3b8-4f31-8254-9ec9a7d2d049",
-    "MetadataAccess": [
-        "oai:envidat.ch:0c06e2c9-c3b8-4f31-8254-9ec9a7d2d049"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/yield-15"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:0c06e2c9-c3b8-4f31-8254-9ec9a7d2d049;2018-12-09T00:33:40Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Yield;2014;Swiss Federal Research Institute WSL;14 X 14 KM GRID;56 CLASSES;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;ALTITUDE 400 M CLASSES;ALTITUDINAL VEGETATION ZONE;AVALANCHES SILVAPROTECT;BIOGEOGRAPHICAL REGION;CONIFERS-BROADLEAVES;ECONOMIC REGION;FOREST TYPE 12 CLASSES;GRID NFI4 2009-2013;LANDSLIDE-MUDFLOW SILVAPROTECT;LOWER-HIGHER ALTITUDINAL ZONES;MAIN TREE SPECIES;NET INCREMENT;NFI2-NFI3;NFI3-NFI4B;OWNERSHIP;POTENTIAL COST FOR TIMBER HARVESTING;PROCESSES IN CHANNELS SILVAPROTECT;PRODUCTION REGION;PROTECTION FOREST PERIMETER SILVAPROTECT;PROTECTION FOREST REGION;ROCKFALL SILVAPROTECT;STAGE OF STAND DEVELOPMENT;TREE SPECIES WOODY SPECIES;YIELD;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/yield-15;URL;1.0;Other (Open);Volume of stemwood with bark of all trees and shrubs  starting at 12 cm dbh that were felled between two inventories. The correction for bias with the sample Tarif trees may be so drastic that it results in negative values with small numbers of trees.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "b853dd1f-86eb-5e85-a461-679c0541d7e9",
-    "notes": [
-        "Volume of stemwood with bark of all trees and shrubs  starting at 12 cm dbh that were felled between two inventories. The correction for bias with the sample Tarif trees may be so drastic that it results in negative values with small numbers of trees.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:0c06e2c9-c3b8-4f31-8254-9ec9a7d2d049"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "X KM GRID"
-        },
-        {
-            "name": "CLASSES"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ALTITUDE M CLASSES"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "AVALANCHES SILVAPROTECT"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        }
-    ],
-    "title": [
-        "Yield"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/b8588a63-a32e-5d4f-9e3f-a0fad487e13f.json b/oaitestdata/envidat-datacite/SET_1/json/b8588a63-a32e-5d4f-9e3f-a0fad487e13f.json
deleted file mode 100644
index c58f2c86..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/b8588a63-a32e-5d4f-9e3f-a0fad487e13f.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "Christian Ginzler"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/1000001.1",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "PDF",
-        "TXT",
-        "JPEG"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:d0e70abe-cc8a-4d91-8798-fa2d9991230f",
-    "MetadataAccess": [
-        "oai:envidat.ch:d0e70abe-cc8a-4d91-8798-fa2d9991230f"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "National Forest Inventory (NFI)"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/vegetation-height-model-nfi"
-    ],
-    "Rights": [
-        "Other (Not Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-11E)",
-    "TempCoverageBegin": 63313613999,
-    "TempCoverageEnd": 63642365999,
-    "TemporalCoverage": " period : ( 2007-05-01T11:59:59Z - 2017-09-30T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2007-05-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2017-09-30T11:59:59Z",
-    "author": [
-        "Christian Ginzler"
-    ],
-    "fulltext": "oai:envidat.ch:d0e70abe-cc8a-4d91-8798-fa2d9991230f;2018-12-09T00:24:16Z;10.16904/1000001.1;Christian Ginzler;E-9544-2012;Swiss Federal Institute for Forest, Snow and Landscape Research WSL;Vegetation Height Model NFI;Vegetation height model of Switzerland based on stereo-image matching;2018;National Forest Inventory (NFI);3D;FOREST;PHOTOGRAMMETY;POINT CLOUD;VEGETATION HEIGHT MODEL;Christian Ginzler;E-9544-2012;Swiss Federal Institute for Forest, Snow and Landscape Research WSL;2007-05-01;2017-09-30;en;https://www.envidat.ch/dataset/vegetation-height-model-nfi;88 bytes;88 bytes;88 bytes;6375018 bytes;TXT;PDF;JPEG;2016 (current);Other (Not Open);A national vegetation height model was calculated for Switzerland using digital aerial images.\nWe used the stereo aerial images acquired by the Federal Office of Topography swisstopo using the ADS80 sensor to first calculate a digital\nsurface model (DSM) with a very high spatial resolution\n(1 \u00d7 1 m). The DSM was then normalized to obtain the actual\nvegetation heights using a digital terrain model (DTM)\nbased on laser data with the buildings masked out, and to\nproduce a vegetation height model (VHM). Such a model\nwill be calculated in the framework of the Swiss National\nForest Inventory (NFI) with consistent methods and a very\nhigh level of detail. For covering the whole of Switzerland,\nwe use summer aerial images from six years.;45.8402810545 5.91613769531 47.8574028947 10.5578613281;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "b8588a63-a32e-5d4f-9e3f-a0fad487e13f",
-    "notes": [
-        "A national vegetation height model was calculated for Switzerland using digital aerial images.\nWe used the stereo aerial images acquired by the Federal Office of Topography swisstopo using the ADS80 sensor to first calculate a digital\nsurface model (DSM) with a very high spatial resolution\n(1 \u00d7 1 m). The DSM was then normalized to obtain the actual\nvegetation heights using a digital terrain model (DTM)\nbased on laser data with the buildings masked out, and to\nproduce a vegetation height model (VHM). Such a model\nwill be calculated in the framework of the Swiss National\nForest Inventory (NFI) with consistent methods and a very\nhigh level of detail. For covering the whole of Switzerland,\nwe use summer aerial images from six years."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:d0e70abe-cc8a-4d91-8798-fa2d9991230f"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.91613769531,45.8402810545],[5.91613769531,47.8574028947],[10.5578613281,47.8574028947],[10.5578613281,45.8402810545],[5.91613769531,45.8402810545]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "FOREST"
-        },
-        {
-            "name": "PHOTOGRAMMETY"
-        },
-        {
-            "name": "POINT CLOUD"
-        },
-        {
-            "name": "VEGETATION HEIGHT MODEL"
-        }
-    ],
-    "title": [
-        "Vegetation Height Model NFI",
-        "Vegetation height model of Switzerland based on stereo-image matching"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/bc5f0432-2c64-5f8c-ac82-3baa0f8f72ba.json b/oaitestdata/envidat-datacite/SET_1/json/bc5f0432-2c64-5f8c-ac82-3baa0f8f72ba.json
deleted file mode 100644
index 08929e91..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/bc5f0432-2c64-5f8c-ac82-3baa0f8f72ba.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "Sebastian W\u00fcrzer"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "TXT",
-        ".ZIP"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:5e2fc5e0-dd28-4d0b-837c-aa9cf064bc3d",
-    "MetadataAccess": [
-        "oai:envidat.ch:5e2fc5e0-dd28-4d0b-837c-aa9cf064bc3d"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/ros_data"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63638564399,
-    "TempCoverageEnd": 63638564399,
-    "TemporalCoverage": " point in time : 2017-08-17T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2017-08-17T11:59:59Z",
-    "TemporalCoverage:EndDate": "2017-08-17T11:59:59Z",
-    "author": [
-        "Sebastian W\u00fcrzer"
-    ],
-    "fulltext": "oai:envidat.ch:5e2fc5e0-dd28-4d0b-837c-aa9cf064bc3d;2018-12-09T00:23:50Z;Sebastian W\u00fcrzer;WSL;Meteorological data for investigation of rain-on-snow events in 58 catchments in Switzerland;2018;CATCHMENT DATA;METEOROLOGICAL DATA;RAIN-ON-SNOW;SNOW HYDROLOGY;SNOWPACK;Sebastian W\u00fcrzer;SLF;2017-08-17;en;Dataset;https://www.envidat.ch/dataset/ros_data;1534677078 bytes;768 bytes;.ZIP;TXT;1.0;Open Data Commons Open Database License (ODbL);Meteorological data used to run SNOWPACK for 58 catchments in the Swiss Alps. The data consists of a 2 km grid of \"virtual meteorological stations\" for each catchment. It was used to simulate snow cover processes during rain-on-snow events, therefore meteorological data of each catchment contains at least one rain-on-snow event. Further information can be found in the attached readme.txt and in W\u00fcrzer & Jonas et al. (2017), currently under review in Hydrological Processes.;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "bc5f0432-2c64-5f8c-ac82-3baa0f8f72ba",
-    "notes": [
-        "Meteorological data used to run SNOWPACK for 58 catchments in the Swiss Alps. The data consists of a 2 km grid of \"virtual meteorological stations\" for each catchment. It was used to simulate snow cover processes during rain-on-snow events, therefore meteorological data of each catchment contains at least one rain-on-snow event. Further information can be found in the attached readme.txt and in W\u00fcrzer & Jonas et al. (2017), currently under review in Hydrological Processes."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:5e2fc5e0-dd28-4d0b-837c-aa9cf064bc3d"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "CATCHMENT DATA"
-        },
-        {
-            "name": "METEOROLOGICAL DATA"
-        },
-        {
-            "name": "RAIN-ON-SNOW"
-        },
-        {
-            "name": "SNOW HYDROLOGY"
-        },
-        {
-            "name": "SNOWPACK"
-        }
-    ],
-    "title": [
-        "Meteorological data for investigation of rain-on-snow events in 58 catchments in Switzerland"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/c1a6ac95-7733-5a4e-ad8a-d863c9763126.json b/oaitestdata/envidat-datacite/SET_1/json/c1a6ac95-7733-5a4e-ad8a-d863c9763126.json
deleted file mode 100644
index 5a80c0d3..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/c1a6ac95-7733-5a4e-ad8a-d863c9763126.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Ionut Iosifescu"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:295826c1-b2cb-4020-918e-6d53770ce2d1",
-    "MetadataAccess": [
-        "oai:envidat.ch:295826c1-b2cb-4020-918e-6d53770ce2d1"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/data-set-for-testing-the-repository-restrictions-and-external-links"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63663879599,
-    "TempCoverageEnd": 63663879599,
-    "TemporalCoverage": " point in time : 2018-06-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-06-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-06-06T11:59:59Z",
-    "author": [
-        "Ionut Iosifescu"
-    ],
-    "fulltext": "oai:envidat.ch:295826c1-b2cb-4020-918e-6d53770ce2d1;2018-12-06T17:34:06Z;Ionut Iosifescu;0000-0002-1770-7833;WSL;Data set for testing login tokens for external systems;2018;WSL;GIS;REPOSITORY;RESTRICTIONS;TEST;TOKEN;Ionut Iosifescu;0000-0002-1770-7833;WSL;2018-06-06;en;Dataset;https://www.envidat.ch/dataset/data-set-for-testing-the-repository-restrictions-and-external-links;URL;1.0;Open Data Commons Open Database License (ODbL);This is a __test dataset__. This dataset includes links to external URLs in other to test the creation and transmission of EnviDat login tokens to external systems. \n\nThe access to these links and files is restricted in several ways, for testing purposes.;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "c1a6ac95-7733-5a4e-ad8a-d863c9763126",
-    "notes": [
-        "This is a __test dataset__. This dataset includes links to external URLs in other to test the creation and transmission of EnviDat login tokens to external systems. \n\nThe access to these links and files is restricted in several ways, for testing purposes."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:295826c1-b2cb-4020-918e-6d53770ce2d1"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "GIS"
-        },
-        {
-            "name": "REPOSITORY"
-        },
-        {
-            "name": "RESTRICTIONS"
-        },
-        {
-            "name": "TEST"
-        },
-        {
-            "name": "TOKEN"
-        }
-    ],
-    "title": [
-        "Data set for testing login tokens for external systems"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/c3dd1031-3bf0-59a5-8cf5-d2d58ac36368.json b/oaitestdata/envidat-datacite/SET_1/json/c3dd1031-3bf0-59a5-8cf5-d2d58ac36368.json
deleted file mode 100644
index 305a2837..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/c3dd1031-3bf0-59a5-8cf5-d2d58ac36368.json
+++ /dev/null
@@ -1,89 +0,0 @@
-{
-    "Contact": [
-        "Franziska Gerber"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/19",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "ZIP"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:361a9977-c156-485a-b77f-9a7a92e15bac",
-    "MetadataAccess": [
-        "oai:envidat.ch:361a9977-c156-485a-b77f-9a7a92e15bac"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Laboratory of Cryospheric Sciences, School of Architecture and Civil Engineering, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/10-16904-19"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N-47N,10E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Rebecca Mott",
-        "Franziska Gerber",
-        "Mathias Bavay",
-        "Sebastian W. Hoch",
-        "Michael Lehning"
-    ],
-    "fulltext": "oai:envidat.ch:361a9977-c156-485a-b77f-9a7a92e15bac;2018-12-09T00:31:03Z;10.16904/19;Franziska Gerber;Laboratory of Cryospheric Sciences, School of Architecture and Civil Engineering, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland and WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland;Rebecca Mott;WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland;Sebastian W. Hoch;Department of Atmospheric Sciences, University of Utah, Salt Lake City, Utah;Mathias Bavay;WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland;Michael Lehning;Laboratory of Cryospheric Sciences, School of Architecture and Civil Engineering, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland and WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland;DISCHMEX - Observations and simulations of the close-ridge small-scale atmospheric flow field and snow accumulation at Sattelhorn, Dischma valley, Davos, Switzerland.;2017;Laboratory of Cryospheric Sciences, School of Architecture and Civil Engineering, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland;LEE-SIDE FLOW FIELD;LIDAR;PREFERENTIAL DEPOSITION;TLS;Franziska Gerber;Laboratory of Cryospheric Sciences, School of Architecture and Civil Engineering, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland and WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/10-16904-19;ZIP;1.0;Open Data Commons Open Database License (ODbL);The data presented here corresponds to the publication \"A Close-Ridge Small-Scale Atmospheric Flow Field and its Influence on Snow Accumulation\" (Gerber et al., 2017), which investigates an eddy-like structure in the vicinity of the Sattelhorn in the Dischma valley (Davos Switzerland)  and its influence on snow accumulation. The dataset contains:\n\n* Alpine3D: Alpine3D snow depth grids (25 m resolution) for two simulations with and without snow redistribution.\n* ARPS: 10 ARPS simulations (25 m horizontal resolution) with different model setups (wind direction, wind speed, stability).\n* LiDAR: Processed LiDAR PPI (D2_PPI_1h) and RHI (D2_cross_1h) across the valley with a hourly resolution for the period 27 October 2015 01:00 - 29 October 2015c 21:00 (spatial resolution: 25 m).\n* meteostations-dischma: Meteorological station data of two meteorological stations in the Dischma valley with 10 minute resolution for the period 28 October 2015 - 30 October 2015.\n* TLS: Snow depth change data (m) between 28 October 2015 and 30 October 2015 based on terrestrial laser scans.\n\nFor more details about the simulation and observation data, see Gerber et al., 2017.\n\n__Publication__: Gerber et al., 2017: A Close-Ridge Small-Scale Atmospheric Flow Field and its Influence on Snow Accumulation, submitted to JGR - Atmospheres.;46.700152853 9.852357673 46.739303111 9.935928682;Dischma Valley, Davos, Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "c3dd1031-3bf0-59a5-8cf5-d2d58ac36368",
-    "notes": [
-        "The data presented here corresponds to the publication \"A Close-Ridge Small-Scale Atmospheric Flow Field and its Influence on Snow Accumulation\" (Gerber et al., 2017), which investigates an eddy-like structure in the vicinity of the Sattelhorn in the Dischma valley (Davos Switzerland)  and its influence on snow accumulation. The dataset contains:\n\n* Alpine3D: Alpine3D snow depth grids (25 m resolution) for two simulations with and without snow redistribution.\n* ARPS: 10 ARPS simulations (25 m horizontal resolution) with different model setups (wind direction, wind speed, stability).\n* LiDAR: Processed LiDAR PPI (D2_PPI_1h) and RHI (D2_cross_1h) across the valley with a hourly resolution for the period 27 October 2015 01:00 - 29 October 2015c 21:00 (spatial resolution: 25 m).\n* meteostations-dischma: Meteorological station data of two meteorological stations in the Dischma valley with 10 minute resolution for the period 28 October 2015 - 30 October 2015.\n* TLS: Snow depth change data (m) between 28 October 2015 and 30 October 2015 based on terrestrial laser scans.\n\nFor more details about the simulation and observation data, see Gerber et al., 2017.\n\n__Publication__: Gerber et al., 2017: A Close-Ridge Small-Scale Atmospheric Flow Field and its Influence on Snow Accumulation, submitted to JGR - Atmospheres."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:361a9977-c156-485a-b77f-9a7a92e15bac"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[9.852357673,46.700152853],[9.852357673,46.739303111],[9.935928682,46.739303111],[9.935928682,46.700152853],[9.852357673,46.700152853]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "LEE-SIDE FLOW FIELD"
-        },
-        {
-            "name": "LIDAR"
-        },
-        {
-            "name": "PREFERENTIAL DEPOSITION"
-        },
-        {
-            "name": "TLS"
-        }
-    ],
-    "title": [
-        "DISCHMEX - Observations and simulations of the close-ridge small-scale atmospheric flow field and snow accumulation at Sattelhorn, Dischma valley, Davos, Switzerland."
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/c698cc0d-c23f-5147-9787-490b67093b69.json b/oaitestdata/envidat-datacite/SET_1/json/c698cc0d-c23f-5147-9787-490b67093b69.json
deleted file mode 100644
index 6ccd1560..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/c698cc0d-c23f-5147-9787-490b67093b69.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:fd734937-cf78-4529-878b-4815a20a1bbf",
-    "MetadataAccess": [
-        "oai:envidat.ch:fd734937-cf78-4529-878b-4815a20a1bbf"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/salvage_logging_star-186"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:fd734937-cf78-4529-878b-4815a20a1bbf;2018-12-09T00:33:07Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Salvage logging*;2014;Swiss Federal Research Institute WSL;14 X 14 KM GRID;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;AVALANCHES SILVAPROTECT;CANTON;CAUSE OF SALVAGE LOGGING;COST OF TIMBER HARVEST 6 CLASSES;GRID NFI4 2009-2013;LANDSLIDE-MUDFLOW SILVAPROTECT;MAIN TYPE OF HARVEST;NFI2-NFI3;NFI3-NFI4B;POTENTIAL COST FOR TIMBER HARVESTING;PROCESSES IN CHANNELS SILVAPROTECT;PROTECTION FOREST PERIMETER SILVAPROTECT;ROCKFALL SILVAPROTECT;SALVAGE LOGGING STAR;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/salvage_logging_star-186;URL;1.0;Other (Open);Volume of stemwood with bark of all trees and shrubs  starting at 12 cm dbh that were removed from the forest as a result of damage occurring (e.g. windthrow, avalanches, insects, rockfall), and not because of management planning. This theme is derived on the level of a sample plot from the cuttings of the sample trees and the salvage cut proportion (according to information from the forester).  *In the calculation no D7/tree height data were used. The values calculated like this have not been corrected for bias, but allow for cantons or forest districts a more robust estimation of changes and could thus be better interpreted.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "c698cc0d-c23f-5147-9787-490b67093b69",
-    "notes": [
-        "Volume of stemwood with bark of all trees and shrubs  starting at 12 cm dbh that were removed from the forest as a result of damage occurring (e.g. windthrow, avalanches, insects, rockfall), and not because of management planning. This theme is derived on the level of a sample plot from the cuttings of the sample trees and the salvage cut proportion (according to information from the forester).  *In the calculation no D7/tree height data were used. The values calculated like this have not been corrected for bias, but allow for cantons or forest districts a more robust estimation of changes and could thus be better interpreted.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:fd734937-cf78-4529-878b-4815a20a1bbf"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "X KM GRID"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "AVALANCHES SILVAPROTECT"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "CAUSE SALVAGE LOGGING"
-        },
-        {
-            "name": "COST TIMBER HARVEST CLASSES"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "LANDSLIDE-MUDFLOW SILVAPROTECT"
-        },
-        {
-            "name": "MAIN TYPE HARVEST"
-        }
-    ],
-    "title": [
-        "Salvage logging*"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/ca037177-6e2d-5a88-b107-92ee725d3419.json b/oaitestdata/envidat-datacite/SET_1/json/ca037177-6e2d-5a88-b107-92ee725d3419.json
deleted file mode 100644
index 15ab59ab..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/ca037177-6e2d-5a88-b107-92ee725d3419.json
+++ /dev/null
@@ -1,88 +0,0 @@
-{
-    "Contact": [
-        "Frank Techel"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/envidat.39",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "ZIP"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:93e6820a-536e-4df0-b9d0-dc2550c89873",
-    "MetadataAccess": [
-        "oai:envidat.ch:93e6820a-536e-4df0-b9d0-dc2550c89873"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avalanche Research SLF"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/selected-wet-snow-avalanche-activity-data-davos-switzerland-2011-2014"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N-47N,10E-10E)",
-    "TempCoverageBegin": 63421527599,
-    "TempCoverageEnd": 63421527599,
-    "TemporalCoverage": " point in time : 2010-10-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2010-10-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2010-10-01T11:59:59Z",
-    "author": [
-        "Swiss Avalanche Warning Service"
-    ],
-    "fulltext": "oai:envidat.ch:93e6820a-536e-4df0-b9d0-dc2550c89873;2018-12-09T00:24:11Z;10.16904/envidat.39;Swiss Avalanche Warning Service;WSL Institute for Snow and Avalanche Research SLF;Selected wet snow avalanche activity data Davos, Switzerland (2011-2014);2018;WSL Institute for Snow and Avalanche Research SLF;ALPS;AVALANCHES;OBSERVATIONS;SHAPEFILE;SNOW;Frank Techel;WSL/SLF;2010-10-01;de;Dataset;https://www.envidat.ch/dataset/selected-wet-snow-avalanche-activity-data-davos-switzerland-2011-2014;416928 bytes;ZIP;1.0;Open Data Commons Open Database License (ODbL);Polygons of wet snow avalanches in the Davos area, as documented by the Swiss avalanche warning service. The georeferenced outlines of the avalanches contain both the release as well as the deposit area, but without separating between both.\n\nThe dataset is a subset of the total record of 1615 avalanches classified as wet snow avalanches from October 2011 - September 2014, containing those 255 avalanches exceeding 0.0125 km^2. Every polygon comes with meta data, including the date of occurrence.\n\nThis dataset is the underlying dataset to:\nWever, N., Vera Valero, C. and Techel, F. (2018) _Coupled snow cover and avalanche dynamics simulations to evaluate wet snow avalanche activity_. Submitted to J. Geophys. Res., in review.;46.6729987746 9.70848083496 46.8658249013 9.99549865723;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "ca037177-6e2d-5a88-b107-92ee725d3419",
-    "notes": [
-        "Polygons of wet snow avalanches in the Davos area, as documented by the Swiss avalanche warning service. The georeferenced outlines of the avalanches contain both the release as well as the deposit area, but without separating between both.\n\nThe dataset is a subset of the total record of 1615 avalanches classified as wet snow avalanches from October 2011 - September 2014, containing those 255 avalanches exceeding 0.0125 km^2. Every polygon comes with meta data, including the date of occurrence.\n\nThis dataset is the underlying dataset to:\nWever, N., Vera Valero, C. and Techel, F. (2018) _Coupled snow cover and avalanche dynamics simulations to evaluate wet snow avalanche activity_. Submitted to J. Geophys. Res., in review."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:93e6820a-536e-4df0-b9d0-dc2550c89873"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[9.70848083496,46.6729987746],[9.70848083496,46.8658249013],[9.99549865723,46.8658249013],[9.99549865723,46.6729987746],[9.70848083496,46.6729987746]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ALPS"
-        },
-        {
-            "name": "AVALANCHES"
-        },
-        {
-            "name": "OBSERVATIONS"
-        },
-        {
-            "name": "SHAPEFILE"
-        },
-        {
-            "name": "SNOW"
-        }
-    ],
-    "title": [
-        "Selected wet snow avalanche activity data Davos, Switzerland (2011-2014)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/ca7245bb-f953-546c-95fa-19d4f84b9565.json b/oaitestdata/envidat-datacite/SET_1/json/ca7245bb-f953-546c-95fa-19d4f84b9565.json
deleted file mode 100644
index a00ce85e..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/ca7245bb-f953-546c-95fa-19d4f84b9565.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:70614675-a828-4919-8d18-abc2fb365d4b",
-    "MetadataAccess": [
-        "oai:envidat.ch:70614675-a828-4919-8d18-abc2fb365d4b"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/diversity_of_woody_species-36"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:70614675-a828-4919-8d18-abc2fb365d4b;2018-12-09T00:31:44Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Diversity of woody species;2014;Swiss Federal Research Institute WSL;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;ALTITUDINAL VEGETATION ZONE;BIOGEOGRAPHICAL REGION;CANTON;DIVERSITY OF WOODY SPECIES;ECONOMIC REGION;GRID NFI4 2009-2013;NFI1;NFI2;NFI3;NFI4B;PRODUCTION REGION;PROTECTION FOREST REGION;TERRESTRIAL GRID NFI1;TERRESTRIAL GRID NFI2;TERRESTRIAL GRID NFI3;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/diversity_of_woody_species-36;URL;1.0;Other (Open);Index based on the number of tree and shrub species  starting at 12 cm dbh in the upper layer and the occurrence of especially ecologically valuable tree and shrub species  starting at 12 cm dbh in the upper layer.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "ca7245bb-f953-546c-95fa-19d4f84b9565",
-    "notes": [
-        "Index based on the number of tree and shrub species  starting at 12 cm dbh in the upper layer and the occurrence of especially ecologically valuable tree and shrub species  starting at 12 cm dbh in the upper layer.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:70614675-a828-4919-8d18-abc2fb365d4b"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "DIVERSITY WOODY SPECIES"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "NFI"
-        },
-        {
-            "name": "NFI"
-        },
-        {
-            "name": "NFI"
-        }
-    ],
-    "title": [
-        "Diversity of woody species"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/ccca3e0a-3093-570f-9b23-b215de129422.json b/oaitestdata/envidat-datacite/SET_1/json/ccca3e0a-3093-570f-9b23-b215de129422.json
deleted file mode 100644
index eabd42dc..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/ccca3e0a-3093-570f-9b23-b215de129422.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Christoph Marty"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "PDF",
-        "TXT"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:43775c11-11c7-418b-a559-aba0c9658120",
-    "MetadataAccess": [
-        "oai:envidat.ch:43775c11-11c7-418b-a559-aba0c9658120"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avalanche Research SLF"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/asrb-wfj"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N,10E)",
-    "TempCoverageBegin": 62956094399,
-    "TempCoverageEnd": 62956094399,
-    "TemporalCoverage": " point in time : 1996-01-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1996-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1996-01-01T11:59:59Z",
-    "author": [
-        "Christoph Marty"
-    ],
-    "fulltext": "oai:envidat.ch:43775c11-11c7-418b-a559-aba0c9658120;2018-12-09T00:24:28Z;Christoph Marty;WSL Institute for Snow and Avalanche Research SLF;ASRB_WFJ: Shortwave and longwave radiation measurements (2 min) at the Weissfluhjoch research site, Davos;2017;WSL Institute for Snow and Avalanche Research SLF;LONGWAVE RADIATION;SHORTWAVE RADIATION;Christoph Marty;WSL Institute for Snow and Avalanche Research SLF;1996-01-01;en;https://www.envidat.ch/dataset/asrb-wfj;PDF;TXT;1.0;Open Data Commons Open Database License (ODbL);Corrected incoming and outgoing  shortwave and longwave 2 min radiation measurements at the Weissfluhjoch summit, Davos, CH. \n\n###References\n1. Marty, C., Philipona, R., Frohlich, C., Ohmura, A.. Altitude dependence of surface radiation fluxes and cloud forcing in the alps: results from the alpine surface radiation budget network. 2002. Theoretical and Applied Climatology. Volume 72. Issue 3-4. 137-155. http://dx.doi.org/10.1007/s007040200019. 10.1007/s007040200019.\n2. Christoph Marty. Surface Radiation, Cloud Forcing and Greenhouse Effect in the Alps. 2000. Institute fuer Klimaforschung ETH. Zuercher Klima-Schriften. Volume 79. http://e-collection.library.ethz.ch/eserv/eth:23491/eth-23491-01.pdf.;46.829631 9.809204;Weissfluhjoch, Davos, Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "ccca3e0a-3093-570f-9b23-b215de129422",
-    "notes": [
-        "Corrected incoming and outgoing  shortwave and longwave 2 min radiation measurements at the Weissfluhjoch summit, Davos, CH. \n\n###References\n1. Marty, C., Philipona, R., Frohlich, C., Ohmura, A.. Altitude dependence of surface radiation fluxes and cloud forcing in the alps: results from the alpine surface radiation budget network. 2002. Theoretical and Applied Climatology. Volume 72. Issue 3-4. 137-155. http://dx.doi.org/10.1007/s007040200019. 10.1007/s007040200019.\n2. Christoph Marty. Surface Radiation, Cloud Forcing and Greenhouse Effect in the Alps. 2000. Institute fuer Klimaforschung ETH. Zuercher Klima-Schriften. Volume 79. http://e-collection.library.ethz.ch/eserv/eth:23491/eth-23491-01.pdf."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:43775c11-11c7-418b-a559-aba0c9658120"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[9.809204,46.829631],[9.809204,46.829631],[9.809204,46.829631],[9.809204,46.829631],[9.809204,46.829631]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "LONGWAVE RADIATION"
-        },
-        {
-            "name": "SHORTWAVE RADIATION"
-        }
-    ],
-    "title": [
-        "ASRB_WFJ: Shortwave and longwave radiation measurements (2 min) at the Weissfluhjoch research site, Davos"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/cd209f98-a3e7-52ba-8b21-5800aa1add47.json b/oaitestdata/envidat-datacite/SET_1/json/cd209f98-a3e7-52ba-8b21-5800aa1add47.json
deleted file mode 100644
index 70447556..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/cd209f98-a3e7-52ba-8b21-5800aa1add47.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:83fcb33f-6c91-4bdb-afb2-9c67d02b16bf",
-    "MetadataAccess": [
-        "oai:envidat.ch:83fcb33f-6c91-4bdb-afb2-9c67d02b16bf"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/biomass_of_live_trees-18"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:83fcb33f-6c91-4bdb-afb2-9c67d02b16bf;2018-12-09T00:31:29Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Biomass of live trees;2014;Swiss Federal Research Institute WSL;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;BIOGEOGRAPHICAL REGION;BIOMASS OF LIVE TREES;CANTON;CONIFERS-BROADLEAVES;ECONOMIC REGION;GRID NFI4 2009-2013;NFI3;NFI4B;PRODUCTION REGION;PROTECTION FOREST REGION;TERRESTRIAL GRID NFI3;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/biomass_of_live_trees-18;URL;1.0;Other (Open);Dry weight (mass) of living trees and shrubs  starting at 12 cm dbh. This consists of the tree parts: roots, stemwood, branch coarse wood, brushwood/twigs and needles/leaves. The correction for bias with the sample Tarif trees may be so drastic that it results in negative values with small numbers of trees.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "cd209f98-a3e7-52ba-8b21-5800aa1add47",
-    "notes": [
-        "Dry weight (mass) of living trees and shrubs  starting at 12 cm dbh. This consists of the tree parts: roots, stemwood, branch coarse wood, brushwood/twigs and needles/leaves. The correction for bias with the sample Tarif trees may be so drastic that it results in negative values with small numbers of trees.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:83fcb33f-6c91-4bdb-afb2-9c67d02b16bf"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "BIOMASS LIVE TREES"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "NFI"
-        },
-        {
-            "name": "NFIB"
-        },
-        {
-            "name": "PRODUCTION REGION"
-        },
-        {
-            "name": "PROTECTION FOREST REGION"
-        }
-    ],
-    "title": [
-        "Biomass of live trees"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/cf5cf6c7-f932-526b-a016-510211e8cf7d.json b/oaitestdata/envidat-datacite/SET_1/json/cf5cf6c7-f932-526b-a016-510211e8cf7d.json
deleted file mode 100644
index 6605d4aa..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/cf5cf6c7-f932-526b-a016-510211e8cf7d.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Alexandre Buttler"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "ZIP"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:044835c8-a185-4ddc-a8a0-559a1a6303c0",
-    "MetadataAccess": [
-        "oai:envidat.ch:044835c8-a185-4ddc-a8a0-559a1a6303c0"
-    ],
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/mountland-jura"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N,6 E)",
-    "TempCoverageBegin": 63397943999,
-    "TempCoverageEnd": 63397943999,
-    "TemporalCoverage": " point in time : 2010-01-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2010-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2010-01-01T11:59:59Z",
-    "author": [
-        "Alexandre Buttler",
-        "Alexander Peringer",
-        "Konstantin Gavazov",
-        "Thomas Spiegelberger"
-    ],
-    "fulltext": "oai:envidat.ch:044835c8-a185-4ddc-a8a0-559a1a6303c0;2018-07-06T22:12:56Z;Alexandre Buttler;Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne;Konstantin Gavazov;Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne;Alexander Peringer;Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne;Thomas Spiegelberger;Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne;Biogeochemical data from a transplantation experiment of monolith soil turfs along an altitudinal gradient to simulate climate change scenarios;2016;Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne;BIOGEOCHEMISTY;CLIMATE CHANGE;SILVOPASTORAL SYSTEMS;TRANSPLANTATION EXPERIMENT;Alexandre Buttler;Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne;2010-01-01;en;Dataset;https://www.envidat.ch/dataset/mountland-jura;2634855742 bytes;ZIP;1;Open Data Commons Open Database License (ODbL);Silvopastoral systems are highly productive and combine long-term wood production with annual provision of forage for livestock. In the Swiss Jura Mountains these systems are a key component of the landscape. As in other cold biomes, climate change can potentially accelerate landscape change within these historically sustainable systems.\n\nIn order to anticipate the evolution of subalpine wooded pasture ecosystems under future climate and land-use changes, this project focused on the interplay between soil, vegetation and climate. It was aimed at providing experimental evidence for chief ecosystem processes, with emphasis on the quality of the ecosystem services provided. The main interest was placed on vegetation turf resistance to climate change along an unwooded \u2013 sparsely wooded - densely wooded pasture gradient (land-use intensity), where plant productivity, diversity and succession along with rates of carbon cycling and microbial activity provided measures of ecosystem functioning at both plot and landscape level.\n\nExperimental transplantation of monolith soil turfs to lower altitudes allowed to simulate soil warming and reduced annual precipitation. In order to simulate a year-round warmer and drier climate the natural climate variation along an altitudinal gradient was used as a proxy. The aim was to simulate realistic climate change scenarios for the second half of the 21st century predicted by the IPCC report and downscaled for Switzerland providing regionalized interpolated projections integrating therein trends for temperature increase and precipitation decrease. By using permanent meteorological stations within the network of the Federal Office of Meteorology and Climatology (MeteoSwiss), we obtained high resolution regional data on the variation of mean annual temperature (MAT) and mean annual precipitation (MAP) in relation to altitude in the Swiss Jura Mountains. We observed a general increase of +0.5 K in MAT and a decrease of -20 % MAP for each 100 m decrease in altitude along the SE slope of the Swiss Jura Mountains. These relationships served for the selection of the transplantation sites such that in comparison to a control site at 1350 m a.s.l. (Combe des Amburnex, N 46\u00b054\u2019, E 6\u00b023\u2019) a +2 K MAT and -20 % MAP was achieved at 1010 m a.s.l. (Saint-George, N 46\u00b052\u2019, E 6\u00b026\u2019), a +4 K MAT and -40 % MAP at 570 m a.s.l., (Arboretum d\u2019Aubonne, N 46\u00b051\u2019, E 6\u00b037\u2019), and a +5 K MAT and -50 % MAP at 395 m a.s.l. (Les Bois Chamblard, N 46\u00b047\u2019, E 6\u00b041\u2019). The two stations at 1010 m a.s.l. and 570 m a.s.l. corresponded to the IPCC scenario A1B for a moderate increase in greenhouse gas emissions and to scenario A2 for a high increase in greenhouse gas emissions, respectively. The station at 395 m a.s.l. was chosen to represent an extreme scenario with climate variables lying at the positive tail distribution of model predictions under the A2 scenario.\n\nSoil cores were assembled into rectangular PVC boxes of 60 \uf0b4 80 cm2 size and of 35 cm height. All mesocosms were dug down to surface level into previously prepared trenches in the ground thus preventing lateral heat exchange with the atmosphere. Since at each site the mesocosms were placed in a common garden with no light interception, mesocosms with turfs from the two wooded pastures were shaded from direct sun light to simulate the natural light conditions in the corresponding habitats. Each mesocosm was equipped with a drainage system and was connected to a water tank thus representing a zero potential lysimeter collecting soil solution and precipitation/snowmelt runoff. ECH2O EC-TM sensor probes coupled to Em50 data-loggers (Decagon Devices, Inc., USA) recorded soil temperature and volumetric water content in each mesocosm at the top-soil (0 to -3 cm) every minute and data were averaged over one hour intervals. Climate parameters at each transplantation site were monitored continuously throughout the experiment by means of automated weather stations (Sensor Scope S\u00e0rl, Switzerland), measuring rain precipitation (non-heated tipping bucket gauges) and air temperature and humidity 2 m above the ground surface at one minute intervals.\n\nA list of above- and belowground variables were measured to assess the resilience of biogeochemical processes, plant productivity, tree regeneration, and carbon sequestration for each respective land-use practice. Furthermore, the experimental data were used to improve on (parameterization) the existing spatially explicit, dynamic model WoodPaM and refine the model\u02bcs climatic and land-use variables so that different scenarios of climate change and land use change could be simulated. Natural and management induced disturbance patterns were incorporated into the model. \nThe data have been made available within the project CCES Mounted. The climate stations Sensorscope are still in use within the project CLIMARBRE (Wald und Klimawandel, WSL/BAFU).\n\n#References\n\n1. Puissant, J., C\u00e9cillon, L., Mills, R.T.E., Robroek, B.J.M. Gavazov, K., De Danieli, S., Spiegelberger, T., Buttler, A., Brun, J.J. 2015. Seasonal influence of climate manipulation on microbial community structure and function in mountain soils. Soil Biology and Biochemistry 80: 296\u2013305.\n2. Mills, R., K. Gavazov, T. Spiegelberger, D. Johnson and A. Buttler 2014. Diminished soil functions occur under simulated climate change in a sup-alpine pasture, but heterotrophic temperature sensitivity indicates microbial resilience. Science of the Total Environment, vol. 473\u2013474(0): 465-472.\n3. Gavazov, K., Spiegelberger, T. and Buttler, A. 2014. Transplantation of subalpine wood-pasture turfs along a natural climatic gradient reveals lower resistance of unwooded pastures to climate change compared to wooded ones. Oecologia\u00a0(174)\u00a0: 1425-1435.\n4. Peringer A., Siehoff S., Ch\u00e9telat J., Spiegelberger T., Buttler A. & Gillet F. 2013. Past and future landscape dynamics in pasture-woodlands of the Swiss Jura Mountains under climate change. Ecology and Society, 18, 3: 11. DOI: 10.5751/ES-05600-180311. [online] URL: http://www.ecologyandsociety.org/vol18/iss3/art11/\n5. Gavazov, K. S., A. Peringer, A. Buttler, F. Gillet and T. Spiegelberger. 2013. Dynamics of Forage Production in Pasture-woodlands of the Swiss Jura Mountains under Projected Climate Change Scenarios. Ecology and Society 18 (1): 38. [online] URL: http://www.ecologyandsociety.org/vol18/iss1/art38/;46.866667 6.433333;Jura, Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "cf5cf6c7-f932-526b-a016-510211e8cf7d",
-    "notes": [
-        "Silvopastoral systems are highly productive and combine long-term wood production with annual provision of forage for livestock. In the Swiss Jura Mountains these systems are a key component of the landscape. As in other cold biomes, climate change can potentially accelerate landscape change within these historically sustainable systems.\n\nIn order to anticipate the evolution of subalpine wooded pasture ecosystems under future climate and land-use changes, this project focused on the interplay between soil, vegetation and climate. It was aimed at providing experimental evidence for chief ecosystem processes, with emphasis on the quality of the ecosystem services provided. The main interest was placed on vegetation turf resistance to climate change along an unwooded \u2013 sparsely wooded - densely wooded pasture gradient (land-use intensity), where plant productivity, diversity and succession along with rates of carbon cycling and microbial activity provided measures of ecosystem functioning at both plot and landscape level.\n\nExperimental transplantation of monolith soil turfs to lower altitudes allowed to simulate soil warming and reduced annual precipitation. In order to simulate a year-round warmer and drier climate the natural climate variation along an altitudinal gradient was used as a proxy. The aim was to simulate realistic climate change scenarios for the second half of the 21st century predicted by the IPCC report and downscaled for Switzerland providing regionalized interpolated projections integrating therein trends for temperature increase and precipitation decrease. By using permanent meteorological stations within the network of the Federal Office of Meteorology and Climatology (MeteoSwiss), we obtained high resolution regional data on the variation of mean annual temperature (MAT) and mean annual precipitation (MAP) in relation to altitude in the Swiss Jura Mountains. We observed a general increase of +0.5 K in MAT and a decrease of -20 % MAP for each 100 m decrease in altitude along the SE slope of the Swiss Jura Mountains. These relationships served for the selection of the transplantation sites such that in comparison to a control site at 1350 m a.s.l. (Combe des Amburnex, N 46\u00b054\u2019, E 6\u00b023\u2019) a +2 K MAT and -20 % MAP was achieved at 1010 m a.s.l. (Saint-George, N 46\u00b052\u2019, E 6\u00b026\u2019), a +4 K MAT and -40 % MAP at 570 m a.s.l., (Arboretum d\u2019Aubonne, N 46\u00b051\u2019, E 6\u00b037\u2019), and a +5 K MAT and -50 % MAP at 395 m a.s.l. (Les Bois Chamblard, N 46\u00b047\u2019, E 6\u00b041\u2019). The two stations at 1010 m a.s.l. and 570 m a.s.l. corresponded to the IPCC scenario A1B for a moderate increase in greenhouse gas emissions and to scenario A2 for a high increase in greenhouse gas emissions, respectively. The station at 395 m a.s.l. was chosen to represent an extreme scenario with climate variables lying at the positive tail distribution of model predictions under the A2 scenario.\n\nSoil cores were assembled into rectangular PVC boxes of 60 \uf0b4 80 cm2 size and of 35 cm height. All mesocosms were dug down to surface level into previously prepared trenches in the ground thus preventing lateral heat exchange with the atmosphere. Since at each site the mesocosms were placed in a common garden with no light interception, mesocosms with turfs from the two wooded pastures were shaded from direct sun light to simulate the natural light conditions in the corresponding habitats. Each mesocosm was equipped with a drainage system and was connected to a water tank thus representing a zero potential lysimeter collecting soil solution and precipitation/snowmelt runoff. ECH2O EC-TM sensor probes coupled to Em50 data-loggers (Decagon Devices, Inc., USA) recorded soil temperature and volumetric water content in each mesocosm at the top-soil (0 to -3 cm) every minute and data were averaged over one hour intervals. Climate parameters at each transplantation site were monitored continuously throughout the experiment by means of automated weather stations (Sensor Scope S\u00e0rl, Switzerland), measuring rain precipitation (non-heated tipping bucket gauges) and air temperature and humidity 2 m above the ground surface at one minute intervals.\n\nA list of above- and belowground variables were measured to assess the resilience of biogeochemical processes, plant productivity, tree regeneration, and carbon sequestration for each respective land-use practice. Furthermore, the experimental data were used to improve on (parameterization) the existing spatially explicit, dynamic model WoodPaM and refine the model\u02bcs climatic and land-use variables so that different scenarios of climate change and land use change could be simulated. Natural and management induced disturbance patterns were incorporated into the model. \nThe data have been made available within the project CCES Mounted. The climate stations Sensorscope are still in use within the project CLIMARBRE (Wald und Klimawandel, WSL/BAFU).\n\n#References\n\n1. Puissant, J., C\u00e9cillon, L., Mills, R.T.E., Robroek, B.J.M. Gavazov, K., De Danieli, S., Spiegelberger, T., Buttler, A., Brun, J.J. 2015. Seasonal influence of climate manipulation on microbial community structure and function in mountain soils. Soil Biology and Biochemistry 80: 296\u2013305.\n2. Mills, R., K. Gavazov, T. Spiegelberger, D. Johnson and A. Buttler 2014. Diminished soil functions occur under simulated climate change in a sup-alpine pasture, but heterotrophic temperature sensitivity indicates microbial resilience. Science of the Total Environment, vol. 473\u2013474(0): 465-472.\n3. Gavazov, K., Spiegelberger, T. and Buttler, A. 2014. Transplantation of subalpine wood-pasture turfs along a natural climatic gradient reveals lower resistance of unwooded pastures to climate change compared to wooded ones. Oecologia\u00a0(174)\u00a0: 1425-1435.\n4. Peringer A., Siehoff S., Ch\u00e9telat J., Spiegelberger T., Buttler A. & Gillet F. 2013. Past and future landscape dynamics in pasture-woodlands of the Swiss Jura Mountains under climate change. Ecology and Society, 18, 3: 11. DOI: 10.5751/ES-05600-180311. [online] URL: http://www.ecologyandsociety.org/vol18/iss3/art11/\n5. Gavazov, K. S., A. Peringer, A. Buttler, F. Gillet and T. Spiegelberger. 2013. Dynamics of Forage Production in Pasture-woodlands of the Swiss Jura Mountains under Projected Climate Change Scenarios. Ecology and Society 18 (1): 38. [online] URL: http://www.ecologyandsociety.org/vol18/iss1/art38/"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:044835c8-a185-4ddc-a8a0-559a1a6303c0"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[6.433333,46.866667],[6.433333,46.866667],[6.433333,46.866667],[6.433333,46.866667],[6.433333,46.866667]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "BIOGEOCHEMISTY"
-        },
-        {
-            "name": "CLIMATE CHANGE"
-        },
-        {
-            "name": "SILVOPASTORAL SYSTEMS"
-        },
-        {
-            "name": "TRANSPLANTATION EXPERIMENT"
-        }
-    ],
-    "title": [
-        "Biogeochemical data from a transplantation experiment of monolith soil turfs along an altitudinal gradient to simulate climate change scenarios"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/d25db36f-76fb-502c-9b01-0e010c9cd71f.json b/oaitestdata/envidat-datacite/SET_1/json/d25db36f-76fb-502c-9b01-0e010c9cd71f.json
deleted file mode 100644
index 443e4e31..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/d25db36f-76fb-502c-9b01-0e010c9cd71f.json
+++ /dev/null
@@ -1,93 +0,0 @@
-{
-    "Contact": [
-        "Leo Gallus Bont"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        ".zip"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:dc4fa7ef-8bb0-4a9d-8a52-ddc5dde48a7f",
-    "MetadataAccess": [
-        "oai:envidat.ch:dc4fa7ef-8bb0-4a9d-8a52-ddc5dde48a7f"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "EnviDat"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/seilaplan"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(48N-47N,16E-10E)",
-    "TempCoverageBegin": 63678484799,
-    "TempCoverageEnd": 63566074799,
-    "TemporalCoverage": " period : ( 2018-11-22T11:59:59Z - 2015-05-01T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2018-11-22T11:59:59Z",
-    "TemporalCoverage:EndDate": "2015-05-01T11:59:59Z",
-    "author": [
-        "Leo Gallus Bont",
-        "Patricia Edith Moll"
-    ],
-    "fulltext": "oai:envidat.ch:dc4fa7ef-8bb0-4a9d-8a52-ddc5dde48a7f;2018-12-09T00:22:01Z;Leo Gallus Bont;0000-0003-2548-7671;WSL;Patricia Edith Moll;ETH Zurich;Seilaplan;2018;EnviDat;CABLE PLANNING;CABLE YARDING;CATENARY LOAD PATH;PYTHON;QGIS;SOFTWARE;STEEP TERRAIN HARVESTING;Leo Gallus Bont;0000-0003-2548-7671;WSL;2018-11-22;2015-05-01;de;Dataset;https://www.envidat.ch/dataset/seilaplan;10177519 bytes;.zip;2.0;Other (Open);Seilaplan is a tool for cable road planning.\n- QGIS & Python Plugin\n- Describe Algorithms\n- cite Paper;48.0849294187 16.1938476562 47.2861851836 9.73388671875;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "d25db36f-76fb-502c-9b01-0e010c9cd71f",
-    "notes": [
-        "Seilaplan is a tool for cable road planning.\n- QGIS & Python Plugin\n- Describe Algorithms\n- cite Paper"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:dc4fa7ef-8bb0-4a9d-8a52-ddc5dde48a7f"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[16.1938476562,48.0849294187],[16.1938476562,47.2861851836],[9.73388671875,47.2861851836],[9.73388671875,48.0849294187],[16.1938476562,48.0849294187]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "CABLE PLANNING"
-        },
-        {
-            "name": "CABLE YARDING"
-        },
-        {
-            "name": "CATENARY LOAD PATH"
-        },
-        {
-            "name": "PYTHON"
-        },
-        {
-            "name": "QGIS"
-        },
-        {
-            "name": "SOFTWARE"
-        },
-        {
-            "name": "STEEP TERRAIN HARVESTING"
-        }
-    ],
-    "title": [
-        "Seilaplan"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/da573d40-751e-5437-a616-5818bca2a241.json b/oaitestdata/envidat-datacite/SET_1/json/da573d40-751e-5437-a616-5818bca2a241.json
deleted file mode 100644
index 8f2e8c89..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/da573d40-751e-5437-a616-5818bca2a241.json
+++ /dev/null
@@ -1,94 +0,0 @@
-{
-    "Contact": [
-        "Yves B\u00fchler"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/envidat.55",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "SHP",
-        ".tif"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:1a8ed871-a483-4900-b528-95e901b3910e",
-    "MetadataAccess": [
-        "oai:envidat.ch:1a8ed871-a483-4900-b528-95e901b3910e"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "EnviDat"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/automated-avalanche-release-area-pra-delineation-davos"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N-47N,10E-10E)",
-    "TempCoverageBegin": 63676670399,
-    "TempCoverageEnd": 63676670399,
-    "TemporalCoverage": " point in time : 2018-11-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-11-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-11-01T11:59:59Z",
-    "author": [
-        "Daniel von Rickenbach",
-        "Yves B\u00fchler"
-    ],
-    "fulltext": "oai:envidat.ch:1a8ed871-a483-4900-b528-95e901b3910e;2018-12-09T00:22:03Z;10.16904/envidat.55;Yves B\u00fchler;0000-0002-0815-2717;SLF;Daniel von Rickenbach;SLF / GIUZ;Automated Avalanche Release Area (PRA) Delineation Davos;Avalanche Release Areas (PRA);2018;EnviDat;AVALANCHE;AVALANCHE HAZARD MAPPING;HAZARD INDICATION MAPPING;RAMMS;RELEASE;SNOW;Yves B\u00fchler;0000-0002-0815-2717;SLF;2018-11-01;en;Dataset;https://www.envidat.ch/dataset/automated-avalanche-release-area-pra-delineation-davos;4379100 bytes;24222947 bytes;SHP;.tif;1.0;Open Data Commons Open Database License (ODbL);This dataset contains the output and reference data published in the paper \"Automated snow avalanche release area delineation - validation of existing algorithms and proposition of a new object-based approach for large scale hazard indication mapping\" Yves B\u00fchler, Daniel von Rickenbach, Andreas Stoffel, Stefan Margreth, Lukas Stoffel, Marc Christen (2018) Natural Hazards And Earth System Sciences.\n\nAbstract:\nSnow avalanche hazard is threatening people and infrastructure in all alpine regions with seasonal or permanent snow cover around the globe. Coping with this hazard is a big challenge and during the past centuries, different strategies were developed. Today, in Switzerland, experienced avalanche engineers produce hazard maps with a very high reliability based on avalanche cadastre information, terrain analysis, climatological datasets and numerical modelling of the flow dynamics for selected avalanche tracks that might affect settlements. However, for regions outside the considered settlement areas such area-wide hazard maps are not available mainly because of the too high cost, in Switzerland and in most mountain regions around the world. Therefore, hazard indication maps, even though they are less reliable and less detailed, are often the only spatial planning tool available. To produce meaningful and cost-effective avalanche hazard indication maps over large regions (regional to national scale), automated release area delineation has to be combined with volume estimations and state-of-the-art numerical avalanche simulations.\n\nIn this paper we validate existing potential release area (PRA) delineation algorithms, published in peer-reviewed journals, that are based on digital terrain models and their derivatives such as slope angle, aspect, roughness and curvature. For validation, we apply avalanche cadastre data from three different ski resorts in the vicinity of Davos, Switzerland, where experienced ski-patrol staff mapped most avalanches in detail since many years. After calculating the best fit input parameters for every tested algorithm, we compare their performance based on the reference datasets. Because all tested algorithms do not provide meaningful delineation between individual potential release areas (PRA), we propose a new algorithm based on object-based image analysis (OBIA). In combination with an automatic procedure to estimate the average release depth (d0), defining the avalanche release volume, this algorithm enables the numerical simulation of thousands of avalanches over large regions applying the well-established avalanche dynamics model RAMMS. We demonstrate this for the region of Davos for two hazard scenarios, frequent (10 \u2013 30 years return period) and extreme (100 \u2013 300 years return period). This approach opens the door for large scale avalanche hazard indication mapping in all regions where high quality and resolution digital terrain models and snow data are available.;46.7125608452 9.75036621094 46.8517390787 9.8876953125;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "da573d40-751e-5437-a616-5818bca2a241",
-    "notes": [
-        "This dataset contains the output and reference data published in the paper \"Automated snow avalanche release area delineation - validation of existing algorithms and proposition of a new object-based approach for large scale hazard indication mapping\" Yves B\u00fchler, Daniel von Rickenbach, Andreas Stoffel, Stefan Margreth, Lukas Stoffel, Marc Christen (2018) Natural Hazards And Earth System Sciences.\n\nAbstract:\nSnow avalanche hazard is threatening people and infrastructure in all alpine regions with seasonal or permanent snow cover around the globe. Coping with this hazard is a big challenge and during the past centuries, different strategies were developed. Today, in Switzerland, experienced avalanche engineers produce hazard maps with a very high reliability based on avalanche cadastre information, terrain analysis, climatological datasets and numerical modelling of the flow dynamics for selected avalanche tracks that might affect settlements. However, for regions outside the considered settlement areas such area-wide hazard maps are not available mainly because of the too high cost, in Switzerland and in most mountain regions around the world. Therefore, hazard indication maps, even though they are less reliable and less detailed, are often the only spatial planning tool available. To produce meaningful and cost-effective avalanche hazard indication maps over large regions (regional to national scale), automated release area delineation has to be combined with volume estimations and state-of-the-art numerical avalanche simulations.\n\nIn this paper we validate existing potential release area (PRA) delineation algorithms, published in peer-reviewed journals, that are based on digital terrain models and their derivatives such as slope angle, aspect, roughness and curvature. For validation, we apply avalanche cadastre data from three different ski resorts in the vicinity of Davos, Switzerland, where experienced ski-patrol staff mapped most avalanches in detail since many years. After calculating the best fit input parameters for every tested algorithm, we compare their performance based on the reference datasets. Because all tested algorithms do not provide meaningful delineation between individual potential release areas (PRA), we propose a new algorithm based on object-based image analysis (OBIA). In combination with an automatic procedure to estimate the average release depth (d0), defining the avalanche release volume, this algorithm enables the numerical simulation of thousands of avalanches over large regions applying the well-established avalanche dynamics model RAMMS. We demonstrate this for the region of Davos for two hazard scenarios, frequent (10 \u2013 30 years return period) and extreme (100 \u2013 300 years return period). This approach opens the door for large scale avalanche hazard indication mapping in all regions where high quality and resolution digital terrain models and snow data are available."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:1a8ed871-a483-4900-b528-95e901b3910e"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[9.75036621094,46.7125608452],[9.75036621094,46.8517390787],[9.8876953125,46.8517390787],[9.8876953125,46.7125608452],[9.75036621094,46.7125608452]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "AVALANCHE"
-        },
-        {
-            "name": "AVALANCHE HAZARD MAPPING"
-        },
-        {
-            "name": "HAZARD INDICATION MAPPING"
-        },
-        {
-            "name": "RAMMS"
-        },
-        {
-            "name": "RELEASE"
-        },
-        {
-            "name": "SNOW"
-        }
-    ],
-    "title": [
-        "Automated Avalanche Release Area (PRA) Delineation Davos",
-        "Avalanche Release Areas (PRA)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/dec26830-4cc8-5b3d-80d1-02b0a9797144.json b/oaitestdata/envidat-datacite/SET_1/json/dec26830-4cc8-5b3d-80d1-02b0a9797144.json
deleted file mode 100644
index d8709542..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/dec26830-4cc8-5b3d-80d1-02b0a9797144.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:4e606a00-e364-44fb-a93b-a7c00826c32b",
-    "MetadataAccess": [
-        "oai:envidat.ch:4e606a00-e364-44fb-a93b-a7c00826c32b"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/forest_area_by_natural_hazard-260"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:4e606a00-e364-44fb-a93b-a7c00826c32b;2018-12-09T00:31:51Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Forest area by natural hazard;2014;Swiss Federal Research Institute WSL;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;BIOGEOGRAPHICAL REGION;CANTON;ECONOMIC REGION;FOREST;FOREST AREA;FOREST AREA BY NATURAL HAZARD;GRID NFI4 2009-2013;NATURAL HAZARD;NFI1;NFI2;NFI3;NFI4B;PRODUCTION REGION;PROTECTION FOREST REGION;TERRESTRIAL GRID NFI1;TERRESTRIAL GRID NFI2;TERRESTRIAL GRID NFI3;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/forest_area_by_natural_hazard-260;URL;1.0;Other (Open);For each natural hazard process according to FOEN\u2019s SilvaProtectCH, the size of the forest area affected is given. One forest region may be affected by several different natural hazard processes and may thus contribute to the forest area affected by several different natural hazard processes.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "dec26830-4cc8-5b3d-80d1-02b0a9797144",
-    "notes": [
-        "For each natural hazard process according to FOEN\u2019s SilvaProtectCH, the size of the forest area affected is given. One forest region may be affected by several different natural hazard processes and may thus contribute to the forest area affected by several different natural hazard processes.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:4e606a00-e364-44fb-a93b-a7c00826c32b"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "FOREST"
-        },
-        {
-            "name": "FOREST AREA"
-        },
-        {
-            "name": "FOREST AREA NATURAL HAZARD"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "NATURAL HAZARD"
-        },
-        {
-            "name": "NFI"
-        },
-        {
-            "name": "NFI"
-        }
-    ],
-    "title": [
-        "Forest area by natural hazard"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/df5c7681-43fc-5868-b1c7-ed829bb91159.json b/oaitestdata/envidat-datacite/SET_1/json/df5c7681-43fc-5868-b1c7-ed829bb91159.json
deleted file mode 100644
index 9354b336..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/df5c7681-43fc-5868-b1c7-ed829bb91159.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Christoph Marty"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "PDF",
-        "SMET",
-        "TXT"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:74417a94-f434-4a7c-a05b-c1f71af4a7f4",
-    "MetadataAccess": [
-        "oai:envidat.ch:74417a94-f434-4a7c-a05b-c1f71af4a7f4"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avalanche Research SLF"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/asrb-dav"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N,10E)",
-    "TempCoverageBegin": 62956094399,
-    "TempCoverageEnd": 62956094399,
-    "TemporalCoverage": " point in time : 1996-01-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1996-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1996-01-01T11:59:59Z",
-    "author": [
-        "Christoph Marty"
-    ],
-    "fulltext": "oai:envidat.ch:74417a94-f434-4a7c-a05b-c1f71af4a7f4;2018-12-09T00:24:27Z;Christoph Marty;WSL Institute for Snow and Avalanche Research SLF;ASRB_DAV: Shortwave and longwave radiation measurements (2 min) in Davos Dorf;2017;WSL Institute for Snow and Avalanche Research SLF;LONGWAVE RADIATION;SHORTWAVE RADIATION;Christoph Marty;WSL Institute for Snow and Avalanche Research SLF;1996-01-01;en;https://www.envidat.ch/dataset/asrb-dav;SMET;PDF;TXT;1.0;Open Data Commons Open Database License (ODbL);Incoming and outgoing  shortwave and longwave 2 min radiation measurements in Davos Dorf, CH. \n\n###References\n1. Marty, C., Philipona, R., Frohlich, C., Ohmura, A.. Altitude dependence of surface radiation fluxes and cloud forcing in the alps: results from the alpine surface radiation budget network. 2002. Theoretical and Applied Climatology. Volume 72. Issue 3-4. 137-155. http://dx.doi.org/10.1007/s007040200019. 10.1007/s007040200019.\n2. Christoph Marty. Surface Radiation, Cloud Forcing and Greenhouse Effect in the Alps. 2000. Institute fuer Klimaforschung ETH. Zuercher Klima-Schriften. Volume 79. http://e-collection.library.ethz.ch/eserv/eth:23491/eth-23491-01.pdf.;46.81277 9.84827;Davos, Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "df5c7681-43fc-5868-b1c7-ed829bb91159",
-    "notes": [
-        "Incoming and outgoing  shortwave and longwave 2 min radiation measurements in Davos Dorf, CH. \n\n###References\n1. Marty, C., Philipona, R., Frohlich, C., Ohmura, A.. Altitude dependence of surface radiation fluxes and cloud forcing in the alps: results from the alpine surface radiation budget network. 2002. Theoretical and Applied Climatology. Volume 72. Issue 3-4. 137-155. http://dx.doi.org/10.1007/s007040200019. 10.1007/s007040200019.\n2. Christoph Marty. Surface Radiation, Cloud Forcing and Greenhouse Effect in the Alps. 2000. Institute fuer Klimaforschung ETH. Zuercher Klima-Schriften. Volume 79. http://e-collection.library.ethz.ch/eserv/eth:23491/eth-23491-01.pdf."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:74417a94-f434-4a7c-a05b-c1f71af4a7f4"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[9.84827,46.81277],[9.84827,46.81277],[9.84827,46.81277],[9.84827,46.81277],[9.84827,46.81277]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "LONGWAVE RADIATION"
-        },
-        {
-            "name": "SHORTWAVE RADIATION"
-        }
-    ],
-    "title": [
-        "ASRB_DAV: Shortwave and longwave radiation measurements (2 min) in Davos Dorf"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/dfac0675-a45a-54d3-8f12-9ddb22d6cc15.json b/oaitestdata/envidat-datacite/SET_1/json/dfac0675-a45a-54d3-8f12-9ddb22d6cc15.json
deleted file mode 100644
index ce654c02..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/dfac0675-a45a-54d3-8f12-9ddb22d6cc15.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:1c9e4b62-288d-4fbe-954b-a87e0aaa8288",
-    "MetadataAccess": [
-        "oai:envidat.ch:1c9e4b62-288d-4fbe-954b-a87e0aaa8288"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/increment-11"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:1c9e4b62-288d-4fbe-954b-a87e0aaa8288;2018-12-09T00:31:54Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Increment;2014;Swiss Federal Research Institute WSL;14 X 14 KM GRID;56 CLASSES;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;ALTITUDE 400 M CLASSES;ALTITUDINAL VEGETATION ZONE;AVALANCHES SILVAPROTECT;BIOGEOGRAPHICAL REGION;CONIFERS-BROADLEAVES;ECONOMIC REGION;FOREST TYPE 12 CLASSES;GRID NFI4 2009-2013;INCREMENT;LANDSLIDE-MUDFLOW SILVAPROTECT;LOWER-HIGHER ALTITUDINAL ZONES;MAIN TREE SPECIES;NFI1-NFI2;NFI2-NFI3;NFI3-NFI4B;OWNERSHIP;POTENTIAL COST FOR TIMBER HARVESTING;PROCESSES IN CHANNELS SILVAPROTECT;PRODUCTION REGION;PROTECTION FOREST PERIMETER SILVAPROTECT;PROTECTION FOREST REGION;ROCKFALL SILVAPROTECT;SITE QUALITY;STAGE OF STAND DEVELOPMENT;TREE SPECIES WOODY SPECIES;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/increment-11;URL;1.0;Other (Open);Increase in the volume of stemwood with bark of the trees and shrubs  starting at 12 cm dbh that have survived between two inventories and of the losses (modelled for the half period), plus the volume of the gains. The correction for bias with the sample Tarif trees may be so drastic that it results in negative values with small numbers of trees.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "dfac0675-a45a-54d3-8f12-9ddb22d6cc15",
-    "notes": [
-        "Increase in the volume of stemwood with bark of the trees and shrubs  starting at 12 cm dbh that have survived between two inventories and of the losses (modelled for the half period), plus the volume of the gains. The correction for bias with the sample Tarif trees may be so drastic that it results in negative values with small numbers of trees.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:1c9e4b62-288d-4fbe-954b-a87e0aaa8288"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "X KM GRID"
-        },
-        {
-            "name": "CLASSES"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ALTITUDE M CLASSES"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "AVALANCHES SILVAPROTECT"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        }
-    ],
-    "title": [
-        "Increment"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/e10d0c67-c12c-52c6-81b7-4709efe3c0b5.json b/oaitestdata/envidat-datacite/SET_1/json/e10d0c67-c12c-52c6-81b7-4709efe3c0b5.json
deleted file mode 100644
index ce39a3aa..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/e10d0c67-c12c-52c6-81b7-4709efe3c0b5.json
+++ /dev/null
@@ -1,95 +0,0 @@
-{
-    "Contact": [
-        "Christian Sommer"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/envidat.30",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "TXT",
-        "Link"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:b5c9438a-83c3-4afb-8f37-b3ec18d3db6e",
-    "MetadataAccess": [
-        "oai:envidat.ch:b5c9438a-83c3-4afb-8f37-b3ec18d3db6e"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/10-16904-envidat-30"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(72S,23E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Nander Wever",
-        "Michael Lehning",
-        "Christian Sommer",
-        "Philip Crivelli"
-    ],
-    "fulltext": "oai:envidat.ch:b5c9438a-83c3-4afb-8f37-b3ec18d3db6e;2018-12-09T00:31:15Z;10.16904/envidat.30;Nander Wever;WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland;Michael Lehning;WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland and CRYOS, School of Architecture and Civil Engineering, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland;Christian Sommer;WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland and CRYOS, School of Architecture and Civil Engineering, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland;Philip Crivelli;WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland and CRYOS, School of Architecture and Civil Engineering, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland;Expedition to Princess Elisabeth Antarctica Station, 2016/2017;2018;WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland;ANTARCTICA;DRIFTING SNOW;MASS FLUX;METEOROLOGICAL DATA;SNOWMICROPEN;TERRESTRIAL LASER SCANNING;Christian Sommer;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/10-16904-envidat-30;3534 bytes;Link;TXT;1.0;Open Data Commons Open Database License (ODbL);This dataset contains the data acquired during the expedition to Princess Elisabeth Antarctica Station in December 2016 and January 2017. The dataset consits of meterorological data, drifting snow mass flux data, SnowMicroPen data and Terrestrial Laser Scanning data.\n\nPlease refer to the README for more information about the data.\n\nThis dataset is the basis of the following publication:\n\nSommer, C. G., Wever, N., Fierz, C., and Lehning, M.: Wind-packing of snow in Antarctica, The Cryosphere Discuss., https://doi.org/10.5194/tc-2018-36, in review, 2018.;-71.95 23.35;Princess Elisabeth Antarctica Station",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "e10d0c67-c12c-52c6-81b7-4709efe3c0b5",
-    "notes": [
-        "This dataset contains the data acquired during the expedition to Princess Elisabeth Antarctica Station in December 2016 and January 2017. The dataset consits of meterorological data, drifting snow mass flux data, SnowMicroPen data and Terrestrial Laser Scanning data.\n\nPlease refer to the README for more information about the data.\n\nThis dataset is the basis of the following publication:\n\nSommer, C. G., Wever, N., Fierz, C., and Lehning, M.: Wind-packing of snow in Antarctica, The Cryosphere Discuss., https://doi.org/10.5194/tc-2018-36, in review, 2018."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:b5c9438a-83c3-4afb-8f37-b3ec18d3db6e"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[23.35,-71.95],[23.35,-71.95],[23.35,-71.95],[23.35,-71.95],[23.35,-71.95]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ANTARCTICA"
-        },
-        {
-            "name": "DRIFTING SNOW"
-        },
-        {
-            "name": "MASS FLUX"
-        },
-        {
-            "name": "METEOROLOGICAL DATA"
-        },
-        {
-            "name": "SNOWMICROPEN"
-        },
-        {
-            "name": "TERRESTRIAL LASER SCANNING"
-        }
-    ],
-    "title": [
-        "Expedition to Princess Elisabeth Antarctica Station, 2016/2017"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/e2a52d5d-9a59-56e0-b7b6-34e78af26165.json b/oaitestdata/envidat-datacite/SET_1/json/e2a52d5d-9a59-56e0-b7b6-34e78af26165.json
deleted file mode 100644
index 521bf1d8..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/e2a52d5d-9a59-56e0-b7b6-34e78af26165.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Sarah M. Springman"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/4",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "ZIP"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:65ecae0a-e309-40f2-9e44-f0ad45f3339d",
-    "MetadataAccess": [
-        "oai:envidat.ch:65ecae0a-e309-40f2-9e44-f0ad45f3339d"
-    ],
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Competence Center Environment and Sustainability, ETH Z\u00fcrich"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/10-16904-4"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(48N,9 E)",
-    "TempCoverageBegin": 63666471599,
-    "TempCoverageEnd": 63666471599,
-    "TemporalCoverage": " point in time : 2018-07-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-07-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-07-06T11:59:59Z",
-    "author": [
-        "Peter Kienzler",
-        "Francesca Casini",
-        "Sarah M. Springman",
-        "Amin Askarinejad"
-    ],
-    "fulltext": "oai:envidat.ch:65ecae0a-e309-40f2-9e44-f0ad45f3339d;2018-12-09T00:31:10Z;10.16904/4;Amin Askarinejad;ETHZ;Peter Kienzler;ETHZ;Francesca Casini;ETHZ;Sarah M. Springman;0000000041102119;ETHZ;TRAMM project Ruedlingen experimental landslide dataset, Switzerland;2015;Competence Center Environment and Sustainability, ETH Z\u00fcrich;LANDSLIDES;PORE WATER;Sarah M. Springman;0000000041102119;ETHZ;2018-07-06;en;Dataset;https://www.envidat.ch/dataset/10-16904-4;974427 bytes;ZIP;1;Open Data Commons Open Database License (ODbL);A landslide testsite dataset related to pore water pressure perturbations on the stability of unsaturated silty sand slopes leading to the initiation and propagation of the shear deformations and eventual rapid mass movements. This project was initiated and led by the Institute of Geotechnical Engineering (IGT) of the Swiss Federal Institute of Technology (ETH Zurich) and was incorporated in a Swiss national (TRAMM) and a European Union (SafeLand) multidisciplinary research project. Field site: The experimental slope is 7.5 m wide by 35 m long, located in the Swiss lowlands on an east facing slope over-looking the river Rhine, at an altitude of ~ 350 masl. Originally there were forestry covertures of circa 80%, heights of 5-20 m. Shrubs up to 1-5 m high and a free herb layer covered ~ 50% of the surface. The average gradient was determined to be from 38\u00b0 to 43\u00b0 with a slightly concave surface. The underlying rock consists mainly of Molasse, which is formed by alternate layers of sea deposits under the Tethys Sea (Seawater Molasse) and land deposits (Freshwater Molasse). Several augured samples, as well as an outcrop of the bedrock about 20 m above the selected field, revealed horizontal layering of fine grained sand- and marlstone at the test site. The sandstone was later proven to be highly permeable and fissured. Grain-size distributions were determined and the soil was classified as medium-low plasticity silty sand. Site instrumentation:Measurements of soil suction, groundwater level, soil volumetric water content, rain intensity and soil temperature were taken and combined with geophysical monitoring using Electrical Resistance Tomography (ERT) and investigations into subsurface flow by means of tracer experiments. Deformations were monitored during the experiment, both on the surface via photogrammetrical methods and within the soil mass, using a flexible probe equipped with strain gauges at different points and two axis inclinometers on the top and acoustic sensors. Instruments were installed mainly in three clusters at depths of 15, 30, 60, 90, 120, and 150 cm below the ground surface over the slope, including jet-fill tensiometers, TDRs, Decagon TDRs, piezometers, soil temperature sensors, deformation probes, earth pressure cells, acoustic sensors and rain gauges. A ring-net barrier (provided by Geobrugg AG) was set up at the foot of the slope to protect the road. Experiments: A sprinkling experiment was carried out in September 2008 to investigate the hydrological and mechanical response of the slope (Experiment 1), followed by a second one to trigger a landslide in March 2009 (Experiment 2). \n\n__Publications__\n\n1. Lehmann, P., F. Gambazzi, B. Suski, L. Baron, A. Askarinejad, S. M. Springman, K. Holliger, and D. Or (2013), Evolution of soil wetting patterns preceding a hydrologically induced landslide inferred from electrical resistivity survey and point measurements of volumetric water content and pore water pressure, Water Resour. Res., 49, 7992\u20138004, doi:[10.1002/2013WR014560](http://dx.doi.org/10.1002/2013WR014560).\n\n2. Springman, S. M., Kienzler, P., Casini, F., & Askarinejad, A. (2009). Landslide triggering experiment in a steep forested slope in Switzerland. In 17th International Conference of Soil Mechanics and Geotechnical Engineering, Alexandria, Egypt (pp. 1698-1701). doi: [10.3233/978-1-60750-031-5-1698](http://dx.doi.org/10.3233/978-1-60750-031-5-1698);47.56685 8.56659;47.56685\u00b0 N, 8.56659\u00b0 E",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "e2a52d5d-9a59-56e0-b7b6-34e78af26165",
-    "notes": [
-        "A landslide testsite dataset related to pore water pressure perturbations on the stability of unsaturated silty sand slopes leading to the initiation and propagation of the shear deformations and eventual rapid mass movements. This project was initiated and led by the Institute of Geotechnical Engineering (IGT) of the Swiss Federal Institute of Technology (ETH Zurich) and was incorporated in a Swiss national (TRAMM) and a European Union (SafeLand) multidisciplinary research project. Field site: The experimental slope is 7.5 m wide by 35 m long, located in the Swiss lowlands on an east facing slope over-looking the river Rhine, at an altitude of ~ 350 masl. Originally there were forestry covertures of circa 80%, heights of 5-20 m. Shrubs up to 1-5 m high and a free herb layer covered ~ 50% of the surface. The average gradient was determined to be from 38\u00b0 to 43\u00b0 with a slightly concave surface. The underlying rock consists mainly of Molasse, which is formed by alternate layers of sea deposits under the Tethys Sea (Seawater Molasse) and land deposits (Freshwater Molasse). Several augured samples, as well as an outcrop of the bedrock about 20 m above the selected field, revealed horizontal layering of fine grained sand- and marlstone at the test site. The sandstone was later proven to be highly permeable and fissured. Grain-size distributions were determined and the soil was classified as medium-low plasticity silty sand. Site instrumentation:Measurements of soil suction, groundwater level, soil volumetric water content, rain intensity and soil temperature were taken and combined with geophysical monitoring using Electrical Resistance Tomography (ERT) and investigations into subsurface flow by means of tracer experiments. Deformations were monitored during the experiment, both on the surface via photogrammetrical methods and within the soil mass, using a flexible probe equipped with strain gauges at different points and two axis inclinometers on the top and acoustic sensors. Instruments were installed mainly in three clusters at depths of 15, 30, 60, 90, 120, and 150 cm below the ground surface over the slope, including jet-fill tensiometers, TDRs, Decagon TDRs, piezometers, soil temperature sensors, deformation probes, earth pressure cells, acoustic sensors and rain gauges. A ring-net barrier (provided by Geobrugg AG) was set up at the foot of the slope to protect the road. Experiments: A sprinkling experiment was carried out in September 2008 to investigate the hydrological and mechanical response of the slope (Experiment 1), followed by a second one to trigger a landslide in March 2009 (Experiment 2). \n\n__Publications__\n\n1. Lehmann, P., F. Gambazzi, B. Suski, L. Baron, A. Askarinejad, S. M. Springman, K. Holliger, and D. Or (2013), Evolution of soil wetting patterns preceding a hydrologically induced landslide inferred from electrical resistivity survey and point measurements of volumetric water content and pore water pressure, Water Resour. Res., 49, 7992\u20138004, doi:[10.1002/2013WR014560](http://dx.doi.org/10.1002/2013WR014560).\n\n2. Springman, S. M., Kienzler, P., Casini, F., & Askarinejad, A. (2009). Landslide triggering experiment in a steep forested slope in Switzerland. In 17th International Conference of Soil Mechanics and Geotechnical Engineering, Alexandria, Egypt (pp. 1698-1701). doi: [10.3233/978-1-60750-031-5-1698](http://dx.doi.org/10.3233/978-1-60750-031-5-1698)"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:65ecae0a-e309-40f2-9e44-f0ad45f3339d"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[8.56659,47.56685],[8.56659,47.56685],[8.56659,47.56685],[8.56659,47.56685],[8.56659,47.56685]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "LANDSLIDES"
-        },
-        {
-            "name": "PORE WATER"
-        }
-    ],
-    "title": [
-        "TRAMM project Ruedlingen experimental landslide dataset, Switzerland"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/e4130758-21ee-5d07-b070-613bcfa2765e.json b/oaitestdata/envidat-datacite/SET_1/json/e4130758-21ee-5d07-b070-613bcfa2765e.json
deleted file mode 100644
index 1900c266..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/e4130758-21ee-5d07-b070-613bcfa2765e.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:8550b0b7-7ef2-46ff-9a28-66e98c850ddf",
-    "MetadataAccess": [
-        "oai:envidat.ch:8550b0b7-7ef2-46ff-9a28-66e98c850ddf"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/salvage_logging-27"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:8550b0b7-7ef2-46ff-9a28-66e98c850ddf;2018-12-09T00:32:59Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Salvage logging;2014;Swiss Federal Research Institute WSL;14 X 14 KM GRID;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;AVALANCHES SILVAPROTECT;BIOGEOGRAPHICAL REGION;CAUSE OF SALVAGE LOGGING;COST OF TIMBER HARVEST 6 CLASSES;ECONOMIC REGION;GRID NFI4 2009-2013;LANDSLIDE-MUDFLOW SILVAPROTECT;MAIN TYPE OF HARVEST;NFI2-NFI3;NFI3-NFI4B;POTENTIAL COST FOR TIMBER HARVESTING;PROCESSES IN CHANNELS SILVAPROTECT;PRODUCTION REGION;PROTECTION FOREST PERIMETER SILVAPROTECT;PROTECTION FOREST REGION;ROCKFALL SILVAPROTECT;SALVAGE LOGGING;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/salvage_logging-27;URL;1.0;Other (Open);Volume of stemwood with bark of all trees and shrubs  starting at 12 cm dbh removed from the forest due to damage occurring (e.g. windthrow, avalanches, insects or rockfall), and not as the result of management planning. This feature is derived on the level of a sample plot from the cuttings of the sample trees and the salvage cut proportion (according to information from the forester).   The correction for bias with the sample Tarif trees may be so drastic that it results in negative values with small numbers of trees.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "e4130758-21ee-5d07-b070-613bcfa2765e",
-    "notes": [
-        "Volume of stemwood with bark of all trees and shrubs  starting at 12 cm dbh removed from the forest due to damage occurring (e.g. windthrow, avalanches, insects or rockfall), and not as the result of management planning. This feature is derived on the level of a sample plot from the cuttings of the sample trees and the salvage cut proportion (according to information from the forester).   The correction for bias with the sample Tarif trees may be so drastic that it results in negative values with small numbers of trees.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:8550b0b7-7ef2-46ff-9a28-66e98c850ddf"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "X KM GRID"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "AVALANCHES SILVAPROTECT"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CAUSE SALVAGE LOGGING"
-        },
-        {
-            "name": "COST TIMBER HARVEST CLASSES"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "LANDSLIDE-MUDFLOW SILVAPROTECT"
-        }
-    ],
-    "title": [
-        "Salvage logging"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/e45e3d56-2779-5133-bf86-d9d544c08ca5.json b/oaitestdata/envidat-datacite/SET_1/json/e45e3d56-2779-5133-bf86-d9d544c08ca5.json
deleted file mode 100644
index a02d750d..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/e45e3d56-2779-5133-bf86-d9d544c08ca5.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Avalanche Warning Service SLF"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/14",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "CSV"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:09817bad-b6bf-424a-82a2-f233a1037a42",
-    "MetadataAccess": [
-        "oai:envidat.ch:09817bad-b6bf-424a-82a2-f233a1037a42"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avalanche Research SLF"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/avalanche-fatalities-switzerland-1936"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "SLF"
-    ],
-    "fulltext": "oai:envidat.ch:09817bad-b6bf-424a-82a2-f233a1037a42;2018-12-09T00:31:21Z;10.16904/14;SLF;WSL Institute for Snow and Avalanche Research SLF;Number of avalanche fatalities per hydrological year in Switzerland since 1936-1937;2018;WSL Institute for Snow and Avalanche Research SLF;AVALANCHE ACCIDENT STATISTICS;AVALANCHE ACCIDENTS;AVALANCHE FATALITIES;Avalanche Warning Service SLF;WSL Institute for Snow and Avalanche Research SLF;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/avalanche-fatalities-switzerland-1936;2135 bytes;CSV;1.0;Open Data Commons Open Database License (ODbL);This dataset contains the statistics on the number of avalanche fatalities per  hydrological year in Switzerland. The data set commences with the beginning of the hydrological year 1936/37 on 01/10/1936. After the completion of a hydrological year, the new data is appended to the existing dataset. \n\nThe following information is contained (by column and column title):  \n - hydrological year  \n - number of fatalities in the backcountry (=tour)  \n - number of fatalities in terrain close to ski areas (=offpiste)  \n - number of fatalities on transportation corridors including ski runs, roads, railway lines (=transportation.corridors)  \n - number of fatalities in or around buildings or in settlements (= buildings)  \n - sum (of all four categories)  \n\nThe definition for these four categories as described in the guidelines to the avalanche accident database:       \n\n**tour**:     \nactivities include back-country ski, snowboard or snow-shoe touring  \n\n**offpiste**:  \naccess from ski area, generally from the top of a skilift with short hiking distances  \n\n**transportation.corridors** ([Techel et al., 2016](http://www.geogr-helv.net/71/147/2016/ )):   \npeople travelling or recreating on open or temporarily closed\ntransportation corridors (e.g. a road user or a skier on a ski run) and people working on open or closed transportation corridors (e.g. maintenance crews on roads, professional rescue teams)   \n\n**buildings** ([Techel et al., 2016](http://www.geogr-helv.net/71/147/2016/ )):  \npeople inside or just outside buildings, and workers on high alpine building\nsites;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "e45e3d56-2779-5133-bf86-d9d544c08ca5",
-    "notes": [
-        "This dataset contains the statistics on the number of avalanche fatalities per  hydrological year in Switzerland. The data set commences with the beginning of the hydrological year 1936/37 on 01/10/1936. After the completion of a hydrological year, the new data is appended to the existing dataset. \n\nThe following information is contained (by column and column title):  \n - hydrological year  \n - number of fatalities in the backcountry (=tour)  \n - number of fatalities in terrain close to ski areas (=offpiste)  \n - number of fatalities on transportation corridors including ski runs, roads, railway lines (=transportation.corridors)  \n - number of fatalities in or around buildings or in settlements (= buildings)  \n - sum (of all four categories)  \n\nThe definition for these four categories as described in the guidelines to the avalanche accident database:       \n\n**tour**:     \nactivities include back-country ski, snowboard or snow-shoe touring  \n\n**offpiste**:  \naccess from ski area, generally from the top of a skilift with short hiking distances  \n\n**transportation.corridors** ([Techel et al., 2016](http://www.geogr-helv.net/71/147/2016/ )):   \npeople travelling or recreating on open or temporarily closed\ntransportation corridors (e.g. a road user or a skier on a ski run) and people working on open or closed transportation corridors (e.g. maintenance crews on roads, professional rescue teams)   \n\n**buildings** ([Techel et al., 2016](http://www.geogr-helv.net/71/147/2016/ )):  \npeople inside or just outside buildings, and workers on high alpine building\nsites"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:09817bad-b6bf-424a-82a2-f233a1037a42"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "AVALANCHE ACCIDENT STATISTICS"
-        },
-        {
-            "name": "AVALANCHE ACCIDENTS"
-        },
-        {
-            "name": "AVALANCHE FATALITIES"
-        }
-    ],
-    "title": [
-        "Number of avalanche fatalities per hydrological year in Switzerland since 1936-1937"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/e9ea7191-7e24-5b6f-afb4-ee1c673676ce.json b/oaitestdata/envidat-datacite/SET_1/json/e9ea7191-7e24-5b6f-afb4-ee1c673676ce.json
deleted file mode 100644
index 6f912b8a..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/e9ea7191-7e24-5b6f-afb4-ee1c673676ce.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:941f691a-0721-4012-a8eb-111bedacf51a",
-    "MetadataAccess": [
-        "oai:envidat.ch:941f691a-0721-4012-a8eb-111bedacf51a"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/total_stem_number-3"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:941f691a-0721-4012-a8eb-111bedacf51a;2018-12-09T00:33:20Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Total stem number;2014;Swiss Federal Research Institute WSL;14 X 14 KM GRID;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;ALTITUDINAL VEGETATION ZONE;ALTITUDINAL VEGETATION ZONE 3 CLASSES;BIOGEOGRAPHICAL REGION;CANTON;CONIFERS-BROADLEAVES;DEGREE OF DAMAGE;DIAMETER CLASS SIZE 10 CM;ECONOMIC REGION;FOREST DISTRICT AS OF 2013;GIANTS;GRID NFI4 2009-2013;LOWER-HIGHER ALTITUDINAL ZONES;MAIN TREE SPECIES;NFI2;NFI3;NFI4B;OWNERSHIP;OWNERSHIP NFI4;PRIMARY FOREST FUNCTION NFI4 NATURE PROTECTION;PRODUCTION REGION;PROTECTION FOREST REGION;TERRESTRIAL GRID NFI2;TERRESTRIAL GRID NFI3;TOTAL STEM NUMBER;TREE SPECIES 5 CLASSES;TREE STATE ALIVE-DEAD;TREE STATUS;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/total_stem_number-3;URL;1.0;Other (Open);Number of stems of all living and dead trees and shrubs starting at 12 cm dbh.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "e9ea7191-7e24-5b6f-afb4-ee1c673676ce",
-    "notes": [
-        "Number of stems of all living and dead trees and shrubs starting at 12 cm dbh.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:941f691a-0721-4012-a8eb-111bedacf51a"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "X KM GRID"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE CLASSES"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        },
-        {
-            "name": "DEGREE DAMAGE"
-        },
-        {
-            "name": "DIAMETER CLASS SIZE CM"
-        }
-    ],
-    "title": [
-        "Total stem number"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/ec2d5dd8-594c-58b5-b5bb-efb1573bb077.json b/oaitestdata/envidat-datacite/SET_1/json/ec2d5dd8-594c-58b5-b5bb-efb1573bb077.json
deleted file mode 100644
index 0a069ede..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/ec2d5dd8-594c-58b5-b5bb-efb1573bb077.json
+++ /dev/null
@@ -1,93 +0,0 @@
-{
-    "Contact": [
-        "Fabrizio Cioldi"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/3",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:99105534-4a3d-4062-a4f9-69933eab4d37",
-    "MetadataAccess": [
-        "oai:envidat.ch:99105534-4a3d-4062-a4f9-69933eab4d37"
-    ],
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Swiss Federal Institute for Forest, Snow and Landscape WSL /  Federal Office for the Environment FOEN"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/10-16904-3"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Non-Commercial)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63492638399,
-    "TempCoverageEnd": 63492638399,
-    "TemporalCoverage": " point in time : 2013-01-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2013-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2013-01-01T11:59:59Z",
-    "author": [
-        "Paolo Camin",
-        "Kalin M\u00fcller",
-        "Marielle Fraefel",
-        "Fabrizio Cioldi",
-        "Christoph Fischer"
-    ],
-    "fulltext": "oai:envidat.ch:99105534-4a3d-4062-a4f9-69933eab4d37;2018-08-21T08:38:35Z;10.16904/3;Kalin M\u00fcller;WSL;Marielle Fraefel;WSL;Fabrizio Cioldi;WSL;Paolo Camin;FOEN;Christoph Fischer;WSL;Forest Access Roads 2013;Walderschliessungsstrassen LFI3;2016;Swiss Federal Institute for Forest, Snow and Landscape WSL /  Federal Office for the Environment FOEN;FOREST ACCESS ROADS;FOREST TRANSPORTATION SYSTEMS;TIMBER HARVESTING;TRAFFICABILITY;TRUCKS;Fabrizio Cioldi;WSL;2013-01-01;de;Dataset;https://www.envidat.ch/dataset/10-16904-3;URL;1;Other (Non-Commercial);In 2013\u20132014, a survey was conducted in Switzerland to update the Forest Access Roads geo-dataset within the framework of the Swiss National Forest Inventory (NFI). The resulting nationwide dataset contains valuable information on truck-accessible forest roads that can be used to transport wood. The survey involved interviewing staff from the approximately 800 local forest services in Switzerland and recording the data first on paper maps and then in digitized form. The data in the NFI on the forest roads could thus be updated and additional information regarding their trafficability for specific categories of truck included. The information has now been attached to the geometries of the Roads and Tracks of the swissTLM3D (release 2012) of the Federal Office of Topography swisstopo. The resulting data are suitable for statistical analyses and modeling, but further (labour-intensive) validation work would be necessary if they are to be used as a basis for applications requiring more spatial accuracy, such as navigation systems. The data are managed at the Swiss Federal Institute for Forest, Snow and Landscape Research (WSL) and are available for third parties for non-commercial use provided they have purchased a TLM license. \n\n__Related Publication__: [doi: 10.3188/szf.2016.0136](http://dx.doi.org/10.3188/szf.2016.0136);45.81802 5.95587 47.80838 10.49203;Switzerland [45.81802 5.95587 47.80838 10.49203]",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "ec2d5dd8-594c-58b5-b5bb-efb1573bb077",
-    "notes": [
-        "In 2013\u20132014, a survey was conducted in Switzerland to update the Forest Access Roads geo-dataset within the framework of the Swiss National Forest Inventory (NFI). The resulting nationwide dataset contains valuable information on truck-accessible forest roads that can be used to transport wood. The survey involved interviewing staff from the approximately 800 local forest services in Switzerland and recording the data first on paper maps and then in digitized form. The data in the NFI on the forest roads could thus be updated and additional information regarding their trafficability for specific categories of truck included. The information has now been attached to the geometries of the Roads and Tracks of the swissTLM3D (release 2012) of the Federal Office of Topography swisstopo. The resulting data are suitable for statistical analyses and modeling, but further (labour-intensive) validation work would be necessary if they are to be used as a basis for applications requiring more spatial accuracy, such as navigation systems. The data are managed at the Swiss Federal Institute for Forest, Snow and Landscape Research (WSL) and are available for third parties for non-commercial use provided they have purchased a TLM license. \n\n__Related Publication__: [doi: 10.3188/szf.2016.0136](http://dx.doi.org/10.3188/szf.2016.0136)"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:99105534-4a3d-4062-a4f9-69933eab4d37"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "FOREST ACCESS ROADS"
-        },
-        {
-            "name": "FOREST TRANSPORTATION SYSTEMS"
-        },
-        {
-            "name": "TIMBER HARVESTING"
-        },
-        {
-            "name": "TRAFFICABILITY"
-        },
-        {
-            "name": "TRUCKS"
-        }
-    ],
-    "title": [
-        "Forest Access Roads 2013",
-        "Walderschliessungsstrassen LFI3"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/edceaa03-e96c-5885-9382-911b906fce01.json b/oaitestdata/envidat-datacite/SET_1/json/edceaa03-e96c-5885-9382-911b906fce01.json
deleted file mode 100644
index 43898fb2..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/edceaa03-e96c-5885-9382-911b906fce01.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:c6d12621-6d86-4a90-871e-beaf38a430dc",
-    "MetadataAccess": [
-        "oai:envidat.ch:c6d12621-6d86-4a90-871e-beaf38a430dc"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/forest_area_by_forest_function-262"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:c6d12621-6d86-4a90-871e-beaf38a430dc;2018-12-09T00:31:49Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Forest area by forest function;2014;Swiss Federal Research Institute WSL;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;BIOGEOGRAPHICAL REGION;CANTON;ECONOMIC REGION;FOREST;FOREST AREA;FOREST AREA BY FOREST FUNCTION;FOREST FUNCTION;GRID NFI4 2009-2013;NFI3;NFI4B;OWNERSHIP;PRODUCTION REGION;PROTECTION FOREST REGION;TERRESTRIAL GRID NFI3;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/forest_area_by_forest_function-262;URL;1.0;Other (Open);The forest area refers to all areas classified as forest according to NFI\u2019s forest definition. The forest definition includes shrub forest.   For each forest function (including no special forest function) identified in the survey of the forestry services, the size of the associated forest area is displayed. One forest region may fulfil several different forest functions and may thus contribute to the forest area for several forest functions. \n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "edceaa03-e96c-5885-9382-911b906fce01",
-    "notes": [
-        "The forest area refers to all areas classified as forest according to NFI\u2019s forest definition. The forest definition includes shrub forest.   For each forest function (including no special forest function) identified in the survey of the forestry services, the size of the associated forest area is displayed. One forest region may fulfil several different forest functions and may thus contribute to the forest area for several forest functions. \n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:c6d12621-6d86-4a90-871e-beaf38a430dc"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "FOREST"
-        },
-        {
-            "name": "FOREST AREA"
-        },
-        {
-            "name": "FOREST AREA FOREST FUNCTION"
-        },
-        {
-            "name": "FOREST FUNCTION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "NFI"
-        },
-        {
-            "name": "NFIB"
-        },
-        {
-            "name": "OWNERSHIP"
-        }
-    ],
-    "title": [
-        "Forest area by forest function"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/f060a61d-8761-5b01-9d1e-c4a9aee8a084.json b/oaitestdata/envidat-datacite/SET_1/json/f060a61d-8761-5b01-9d1e-c4a9aee8a084.json
deleted file mode 100644
index c79235da..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/f060a61d-8761-5b01-9d1e-c4a9aee8a084.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:d411ffab-053d-481b-8211-e07a14c6302f",
-    "MetadataAccess": [
-        "oai:envidat.ch:d411ffab-053d-481b-8211-e07a14c6302f"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/number_of_woody_species_gt_12_cm_dbh-41"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:d411ffab-053d-481b-8211-e07a14c6302f;2018-12-09T00:32:50Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Number of woody species (>= 12 cm DBH);2014;Swiss Federal Research Institute WSL;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;ALTITUDINAL VEGETATION ZONE;GRID NFI4 2009-2013;NFI1;NFI2;NFI3;NFI4B;NUMBER OF WOODY SPECIES GTE 12 CM DBH;PRODUCTION REGION;TERRESTRIAL GRID NFI1;TERRESTRIAL GRID NFI2;TERRESTRIAL GRID NFI3;TIME OF LAST TREATMENT;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/number_of_woody_species_gt_12_cm_dbh-41;URL;1.0;Other (Open);Number of tree and shrub species  starting at 12 cm dbh (diameter at breast height) within the 200 m2 sample plot.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "f060a61d-8761-5b01-9d1e-c4a9aee8a084",
-    "notes": [
-        "Number of tree and shrub species  starting at 12 cm dbh (diameter at breast height) within the 200 m2 sample plot.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:d411ffab-053d-481b-8211-e07a14c6302f"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "NFI"
-        },
-        {
-            "name": "NFI"
-        },
-        {
-            "name": "NFI"
-        },
-        {
-            "name": "NFIB"
-        },
-        {
-            "name": "NUMBER WOODY SPECIES GTE CM DBH"
-        },
-        {
-            "name": "PRODUCTION REGION"
-        },
-        {
-            "name": "TERRESTRIAL GRID NFI"
-        }
-    ],
-    "title": [
-        "Number of woody species (>= 12 cm DBH)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/f1aeafea-8222-5d6a-a552-344753b65b78.json b/oaitestdata/envidat-datacite/SET_1/json/f1aeafea-8222-5d6a-a552-344753b65b78.json
deleted file mode 100644
index e7f1c7d9..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/f1aeafea-8222-5d6a-a552-344753b65b78.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:14ca6820-35ff-43ab-87a9-e4787cff488a",
-    "MetadataAccess": [
-        "oai:envidat.ch:14ca6820-35ff-43ab-87a9-e4787cff488a"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/biomass_of_lying_dead_trees-70"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:14ca6820-35ff-43ab-87a9-e4787cff488a;2018-12-09T00:31:32Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Biomass of lying dead trees;2014;Swiss Federal Research Institute WSL;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;BIOGEOGRAPHICAL REGION;BIOMASS OF LYING DEAD TREES;CANTON;CONIFERS-BROADLEAVES;ECONOMIC REGION;GRID NFI4 2009-2013;NFI3;NFI4B;PRODUCTION REGION;PROTECTION FOREST REGION;TERRESTRIAL GRID NFI3;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/biomass_of_lying_dead_trees-70;URL;1.0;Other (Open);Dry weight (mass) of dead, lying trees and shrubs  starting at 12 cm dbh. This consists of the tree parts: roots, stemwood and also, depending on the degree of decomposition of the stem, the branch coarse wood. \n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "f1aeafea-8222-5d6a-a552-344753b65b78",
-    "notes": [
-        "Dry weight (mass) of dead, lying trees and shrubs  starting at 12 cm dbh. This consists of the tree parts: roots, stemwood and also, depending on the degree of decomposition of the stem, the branch coarse wood. \n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:14ca6820-35ff-43ab-87a9-e4787cff488a"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "BIOMASS LYING DEAD TREES"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "NFI"
-        },
-        {
-            "name": "NFIB"
-        },
-        {
-            "name": "PRODUCTION REGION"
-        },
-        {
-            "name": "PROTECTION FOREST REGION"
-        }
-    ],
-    "title": [
-        "Biomass of lying dead trees"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/f1ea23c0-03dd-592a-ab0b-cc7f23a3cdef.json b/oaitestdata/envidat-datacite/SET_1/json/f1ea23c0-03dd-592a-ab0b-cc7f23a3cdef.json
deleted file mode 100644
index 7f19628a..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/f1ea23c0-03dd-592a-ab0b-cc7f23a3cdef.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:03430494-9371-40ce-be19-52ca49b8fede",
-    "MetadataAccess": [
-        "oai:envidat.ch:03430494-9371-40ce-be19-52ca49b8fede"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/biomass_of_total_dead_wood-71"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:03430494-9371-40ce-be19-52ca49b8fede;2018-12-09T00:31:36Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Biomass of total dead wood;2014;Swiss Federal Research Institute WSL;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;BIOGEOGRAPHICAL REGION;BIOMASS OF TOTAL DEAD WOOD;CANTON;ECONOMIC REGION;GRID NFI4 2009-2013;NFI3;NFI4B;OWNERSHIP;PRODUCTION REGION;PROTECTION FOREST REGION;TERRESTRIAL GRID NFI3;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/biomass_of_total_dead_wood-71;URL;1.0;Other (Open);Dry weight (mass) of all deadwood. This consists of the standing dead trees and shrubs  starting at 12cm dbh and the lying deadwood  starting at 7cm in diameter.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "f1ea23c0-03dd-592a-ab0b-cc7f23a3cdef",
-    "notes": [
-        "Dry weight (mass) of all deadwood. This consists of the standing dead trees and shrubs  starting at 12cm dbh and the lying deadwood  starting at 7cm in diameter.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:03430494-9371-40ce-be19-52ca49b8fede"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "BIOMASS TOTAL DEAD WOOD"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "NFI"
-        },
-        {
-            "name": "NFIB"
-        },
-        {
-            "name": "OWNERSHIP"
-        },
-        {
-            "name": "PRODUCTION REGION"
-        },
-        {
-            "name": "PROTECTION FOREST REGION"
-        }
-    ],
-    "title": [
-        "Biomass of total dead wood"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/f25b69de-15cc-57e9-8871-1688a75fc4c0.json b/oaitestdata/envidat-datacite/SET_1/json/f25b69de-15cc-57e9-8871-1688a75fc4c0.json
deleted file mode 100644
index 8d223b3e..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/f25b69de-15cc-57e9-8871-1688a75fc4c0.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:8c42ae50-29f6-4a82-9087-5ae617990a4d",
-    "MetadataAccess": [
-        "oai:envidat.ch:8c42ae50-29f6-4a82-9087-5ae617990a4d"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/number_of_forest_plots-125"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:8c42ae50-29f6-4a82-9087-5ae617990a4d;2018-12-09T00:32:44Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Number of forest plots;2014;Swiss Federal Research Institute WSL;5 CLASSES;ACCESSIBLE FOREST NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;ALTITUDINAL VEGETATION ZONE;AREA OF LARGEST GAP AERIAL PHOTO;AVALANCHES SILVAPROTECT;BIOGEOGRAPHICAL REGION;CANTON;DIVERSITY OF WOODY SPECIES IN THE STAND;ECONOMIC REGION;FOREST;FOREST DISTRICT AS OF 2013;FOREST FUNCTION RECREATION;FOREST TYPE 12 CLASSES;FOREST TYPE 3 CLASSES;GRID NFI4 2009-2013;INFRASTRUCTURE FOR RECREATION;INNER EDGE OF STAND;INTENSITY OF PASTURING;INTENSITY OF RECREATIONAL USE;LANDSLIDE-MUDFLOW SILVAPROTECT;LOWER-HIGHER ALTITUDINAL ZONES;NFI1;NFI2;NFI3;NFI4B;NUMBER OF FOREST PLOTS;OCCURENCE OF REMNANTS OF ROOT PLATES;OCCURRENCE OF ROOT PLATES;OVERALL PRESENCE OF DEAD WOOD;OVERLOADS AND DISTURBANCES;OWNERSHIP;PILE OF BRANCHES AND LOGS;PRIMARY FOREST FUNCTION NFI4;PRIMARY FUNCTION NFI3;PROCESSES IN CHANNELS SILVAPROTECT;PRODUCTION REGION;PROTECTION FOREST PERIMETER SILVAPROTECT;PROTECTION FOREST REGION;RECREATIONAL USE SEASONALITY;ROCKFALL SILVAPROTECT;SLOPE 20 CLASSES;SNAG;SOIL TYPE OF DAMAGE;STUMPS AND LYING DEAD WOOD;SURROUNDINGS OF SOIL DAMAGE;TERRESTRIAL GRID NFI1;TERRESTRIAL GRID NFI2;TERRESTRIAL GRID NFI3;TYPE OF GAPS;TYPE OF PASTURING;TYPE OF RECREATION CAMPING;TYPE OF RECREATION CROSS-COUNTRY SKIING;TYPE OF RECREATION CYCLING;TYPE OF RECREATION HIKING;TYPE OF RECREATION HORSEBACK RIDING;TYPE OF RECREATION JOGGING;TYPE OF RECREATION MOUNTAIN BIKING;TYPE OF RECREATION OTHER ACTIVITIES;TYPE OF RECREATION SKI AND SNOWBOARD;TYPE OF RECREATION SNOWSHOEING;TYPE OF RECREATION WALK;VEHICLE TRACK;YEAR OF LAST PASTURING;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/number_of_forest_plots-125;URL;1.0;Other (Open);Number of forest sample plots (Plots).\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "f25b69de-15cc-57e9-8871-1688a75fc4c0",
-    "notes": [
-        "Number of forest sample plots (Plots).\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:8c42ae50-29f6-4a82-9087-5ae617990a4d"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "CLASSES"
-        },
-        {
-            "name": "ACCESSIBLE FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "AREA LARGEST GAP AERIAL PHOTO"
-        },
-        {
-            "name": "AVALANCHES SILVAPROTECT"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "DIVERSITY WOODY SPECIES STAND"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        }
-    ],
-    "title": [
-        "Number of forest plots"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/f78ea7f0-1c6f-5a9e-918c-afa2d498eb46.json b/oaitestdata/envidat-datacite/SET_1/json/f78ea7f0-1c6f-5a9e-918c-afa2d498eb46.json
deleted file mode 100644
index b0ebf100..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/f78ea7f0-1c6f-5a9e-918c-afa2d498eb46.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Marcia Phillips"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL",
-        "PDF"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:1e117ff0-3fd3-4f7f-8593-9313fc79e0ca",
-    "MetadataAccess": [
-        "oai:envidat.ch:1e117ff0-3fd3-4f7f-8593-9313fc79e0ca"
-    ],
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "PERMOS"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/gem-bh"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N,9 E)",
-    "TempCoverageBegin": 63295642799,
-    "TempCoverageEnd": 63295642799,
-    "TemporalCoverage": " point in time : 2006-10-05T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2006-10-05T11:59:59Z",
-    "TemporalCoverage:EndDate": "2006-10-05T11:59:59Z",
-    "author": [
-        "Marcia Phillips"
-    ],
-    "fulltext": "oai:envidat.ch:1e117ff0-3fd3-4f7f-8593-9313fc79e0ca;2018-12-09T00:24:18Z;Marcia Phillips;Swiss Federal Research Institute WSL;Processed permafrost borehole data (2940 m asl), Gemsstock, Switzerland;2016;PERMOS;BOREHOLE;PERMAFROST;Marcia Phillips;Swiss Federal Research Institute WSL;2006-10-05;en;Dataset;https://www.envidat.ch/dataset/gem-bh;URL;PDF;1.0;Open Data Commons Open Database License (ODbL);Processed ground temperature measurements at the Gemsstock permafrost borehole in canton Uri, Switzerland. The borehole is located at 2940 m asl on a steep (50&deg;) North-West slope (315&deg;). The surface material is bedrock and borehole depth is 40 m.  Thermistors used YSI 44008. Year of drilling 2006. This borehole is part of the Swiss Permafrost network, PERMOS (www.permos.ch). Contact phillips@slf.ch for details of processing applied.\n\n__Publications__\n\n1. A. Haberkorn, M. Phillips, R. Kenner, H. Rhyner, M. Bavay, S.P. Galos, M. Hoelzle. Thermal regime of rock and its relation to snow cover in steep Alpine rock walls: Gemsstock, central Swiss Alps. 2015. Geografiska Annaler: Series A, Physical Geography. Volume 97. Issue 3. 579\u2013597. http://dx.doi.org/10.1111/geoa.12101. 10.1111/geoa.12101.\n\n2. R. Kenner, M. Phillips, C. Danioth, C. Denier, P. Thee, A. Zgraggen. Investigation of rock and ice loss in a recently deglaciated mountain rock wall using terrestrial laser scanning: Gemsstock, Swiss Alps. 2011. Cold Regions Science and Technology. Volume 67. Issue 3. 157\u2013164. http://dx.doi.org/10.1016/j.coldregions.2011.04.006. 10.1016/j.coldregions.2011.04.006.;46.60097 8.61026;Gemsstock, Uri, Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "f78ea7f0-1c6f-5a9e-918c-afa2d498eb46",
-    "notes": [
-        "Processed ground temperature measurements at the Gemsstock permafrost borehole in canton Uri, Switzerland. The borehole is located at 2940 m asl on a steep (50&deg;) North-West slope (315&deg;). The surface material is bedrock and borehole depth is 40 m.  Thermistors used YSI 44008. Year of drilling 2006. This borehole is part of the Swiss Permafrost network, PERMOS (www.permos.ch). Contact phillips@slf.ch for details of processing applied.\n\n__Publications__\n\n1. A. Haberkorn, M. Phillips, R. Kenner, H. Rhyner, M. Bavay, S.P. Galos, M. Hoelzle. Thermal regime of rock and its relation to snow cover in steep Alpine rock walls: Gemsstock, central Swiss Alps. 2015. Geografiska Annaler: Series A, Physical Geography. Volume 97. Issue 3. 579\u2013597. http://dx.doi.org/10.1111/geoa.12101. 10.1111/geoa.12101.\n\n2. R. Kenner, M. Phillips, C. Danioth, C. Denier, P. Thee, A. Zgraggen. Investigation of rock and ice loss in a recently deglaciated mountain rock wall using terrestrial laser scanning: Gemsstock, Swiss Alps. 2011. Cold Regions Science and Technology. Volume 67. Issue 3. 157\u2013164. http://dx.doi.org/10.1016/j.coldregions.2011.04.006. 10.1016/j.coldregions.2011.04.006."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:1e117ff0-3fd3-4f7f-8593-9313fc79e0ca"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[8.61026,46.60097],[8.61026,46.60097],[8.61026,46.60097],[8.61026,46.60097],[8.61026,46.60097]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "BOREHOLE"
-        },
-        {
-            "name": "PERMAFROST"
-        }
-    ],
-    "title": [
-        "Processed permafrost borehole data (2940 m asl), Gemsstock, Switzerland"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/f8661cd4-f5bb-5cf4-bbd6-71c80ccfba22.json b/oaitestdata/envidat-datacite/SET_1/json/f8661cd4-f5bb-5cf4-bbd6-71c80ccfba22.json
deleted file mode 100644
index 323b385b..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/f8661cd4-f5bb-5cf4-bbd6-71c80ccfba22.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:5b8ddf61-9d87-432d-954c-314f33d0cf74",
-    "MetadataAccess": [
-        "oai:envidat.ch:5b8ddf61-9d87-432d-954c-314f33d0cf74"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/net_increment-80"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:5b8ddf61-9d87-432d-954c-314f33d0cf74;2018-12-09T00:32:40Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Net increment;2014;Swiss Federal Research Institute WSL;14 X 14 KM GRID;56 CLASSES;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;ALTITUDE 400 M CLASSES;ALTITUDINAL VEGETATION ZONE;AVALANCHES SILVAPROTECT;BIOGEOGRAPHICAL REGION;CONIFERS-BROADLEAVES;ECONOMIC REGION;FOREST TYPE 12 CLASSES;GRID NFI4 2009-2013;LANDSLIDE-MUDFLOW SILVAPROTECT;LOWER-HIGHER ALTITUDINAL ZONES;MAIN TREE SPECIES;NET INCREMENT;NFI2-NFI3;NFI3-NFI4B;OWNERSHIP;POTENTIAL COST FOR TIMBER HARVESTING;PROCESSES IN CHANNELS SILVAPROTECT;PRODUCTION REGION;PROTECTION FOREST PERIMETER SILVAPROTECT;PROTECTION FOREST REGION;ROCKFALL SILVAPROTECT;SITE QUALITY;STAGE OF STAND DEVELOPMENT;TREE SPECIES WOODY SPECIES;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/net_increment-80;URL;1.0;Other (Open);Increment including ingrowth minus the mortality.   The correction for bias with the sample Tarif trees may be so drastic that it results in negative values with small numbers of trees.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "f8661cd4-f5bb-5cf4-bbd6-71c80ccfba22",
-    "notes": [
-        "Increment including ingrowth minus the mortality.   The correction for bias with the sample Tarif trees may be so drastic that it results in negative values with small numbers of trees.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:5b8ddf61-9d87-432d-954c-314f33d0cf74"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "X KM GRID"
-        },
-        {
-            "name": "CLASSES"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ALTITUDE M CLASSES"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "AVALANCHES SILVAPROTECT"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CONIFERS-BROADLEAVES"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        }
-    ],
-    "title": [
-        "Net increment"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/f9930051-50c3-5e1a-8ed4-662b1355b033.json b/oaitestdata/envidat-datacite/SET_1/json/f9930051-50c3-5e1a-8ed4-662b1355b033.json
deleted file mode 100644
index f6674951..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/f9930051-50c3-5e1a-8ed4-662b1355b033.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:e1a66c2f-92f8-4444-94af-492a4482f5f3",
-    "MetadataAccess": [
-        "oai:envidat.ch:e1a66c2f-92f8-4444-94af-492a4482f5f3"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/salvage_logging_due_to_insects-89"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:e1a66c2f-92f8-4444-94af-492a4482f5f3;2018-12-09T00:33:01Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Salvage logging due to insects;2014;Swiss Federal Research Institute WSL;14 X 14 KM GRID;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;ALTITUDINAL VEGETATION ZONE;BIOGEOGRAPHICAL REGION;ECONOMIC REGION;GRID NFI4 2009-2013;NFI2-NFI3;NFI3-NFI4B;PRODUCTION REGION;PROTECTION FOREST REGION;SALVAGE LOGGING DUE TO INSECTS;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/salvage_logging_due_to_insects-89;URL;1.0;Other (Open);Volume of stemwood with bark of all trees and shrubs  starting at 12 cm dbh removed from the forest between two inventories due to damage that occurred, in this case insects, and not due to silvicultural planning. This theme is derived on the level of a sample plot from the cuttings of the sample trees and the salvage cut proportion (according to information from the forester).   The correction for bias with the sample Tarif trees may be so drastic that it results in negative values with small numbers of trees.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "f9930051-50c3-5e1a-8ed4-662b1355b033",
-    "notes": [
-        "Volume of stemwood with bark of all trees and shrubs  starting at 12 cm dbh removed from the forest between two inventories due to damage that occurred, in this case insects, and not due to silvicultural planning. This theme is derived on the level of a sample plot from the cuttings of the sample trees and the salvage cut proportion (according to information from the forester).   The correction for bias with the sample Tarif trees may be so drastic that it results in negative values with small numbers of trees.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:e1a66c2f-92f8-4444-94af-492a4482f5f3"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "X KM GRID"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "NFI-NFI"
-        },
-        {
-            "name": "NFI-NFIB"
-        },
-        {
-            "name": "PRODUCTION REGION"
-        }
-    ],
-    "title": [
-        "Salvage logging due to insects"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/fb2fbef1-b2e2-5c84-a33b-b391ed8855c8.json b/oaitestdata/envidat-datacite/SET_1/json/fb2fbef1-b2e2-5c84-a33b-b391ed8855c8.json
deleted file mode 100644
index a0c70099..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/fb2fbef1-b2e2-5c84-a33b-b391ed8855c8.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:685bf952-ce50-4007-ac04-0b0a76552c6f",
-    "MetadataAccess": [
-        "oai:envidat.ch:685bf952-ce50-4007-ac04-0b0a76552c6f"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/stand_density_sdi-29"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:685bf952-ce50-4007-ac04-0b0a76552c6f;2018-12-09T00:33:08Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Stand density (SDI);2014;Swiss Federal Research Institute WSL;14 X 14 KM GRID;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI2-NFI3;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI3-NFI4;ALTITUDINAL VEGETATION ZONE;ALTITUDINAL VEGETATION ZONE 3 CLASSES;BIOGEOGRAPHICAL REGION;CANTON;ECONOMIC REGION;GRID NFI4 2009-2013;NFI1;NFI2;NFI3;NFI4B;PRIMARY FOREST FUNCTION NFI4 NATURE PROTECTION;PRODUCTION REGION;PROTECTION FOREST REGION;STAND DENSITY SDI;TERRESTRIAL GRID NFI1;TERRESTRIAL GRID NFI2;TERRESTRIAL GRID NFI3;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/stand_density_sdi-29;URL;1.0;Other (Open);The Stand Density Index (SDI) is a general measure for the density of a stocking and is based on the number of stems/ha and the average diameter of the tally trees on the sample plot.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "fb2fbef1-b2e2-5c84-a33b-b391ed8855c8",
-    "notes": [
-        "The Stand Density Index (SDI) is a general measure for the density of a stocking and is based on the number of stems/ha and the average diameter of the tally trees on the sample plot.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:685bf952-ce50-4007-ac04-0b0a76552c6f"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "X KM GRID"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE CLASSES"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        }
-    ],
-    "title": [
-        "Stand density (SDI)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/fb76e829-e2a2-5f32-a855-97c5e570aac7.json b/oaitestdata/envidat-datacite/SET_1/json/fb76e829-e2a2-5f32-a855-97c5e570aac7.json
deleted file mode 100644
index 7b1b3b7d..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/fb76e829-e2a2-5f32-a855-97c5e570aac7.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "Esther R. Frei"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/envidat.42",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "ZIP"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:6078db91-18c3-411c-ba36-837b718a5897",
-    "MetadataAccess": [
-        "oai:envidat.ch:6078db91-18c3-411c-ba36-837b718a5897"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avalanche Research SLF"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/gtree"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N,10E)",
-    "TempCoverageBegin": 63416775599,
-    "TempCoverageEnd": 63416775599,
-    "TemporalCoverage": " point in time : 2010-08-07T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2010-08-07T11:59:59Z",
-    "TemporalCoverage:EndDate": "2010-08-07T11:59:59Z",
-    "author": [
-        "Peter Bebi",
-        "Esther R. Frei",
-        "Christian Rixen",
-        "Melissa A. Dawes"
-    ],
-    "fulltext": "oai:envidat.ch:6078db91-18c3-411c-ba36-837b718a5897;2018-12-09T00:24:14Z;10.16904/envidat.42;Esther R. Frei;0000-0003-1910-7900;Swiss Federal Research Institute WSL;Peter Bebi;0000-0001-8868-6569;WSL Institute for Snow and Avalanche Research SLF;Melissa A. Dawes;0000-0003-4919-0151;Swiss Federal Research Institute WSL;Christian Rixen;0000-0002-2486-9988;WSL Institute for Snow and Avalanche Research SLF;G-TREE: Global Treeline Range Expansion Experiment Davos, Switzerland;2018;WSL Institute for Snow and Avalanche Research SLF;CLIMATE CHANGE;FOREST;TREELINE;Esther R. Frei;0000-0003-1910-7900;Swiss Federal Research Institute WSL;2010-08-07;en;Dataset;https://www.envidat.ch/dataset/gtree;126 bytes;ZIP;1.0;Open Data Commons Open Database License (ODbL);G-TREE is a global research network composed of 40 arctic and alpine researchers from around the world. This summer, our field experiment will be established at numerous sites across Canada, France, Norway, Spain, the United States, and Venezuela. Other sites are being developed in Russia, Scotland, and Sweden. \n\nThe Stillberg research area is located in the Eastern Swiss Alps near Davos, Switzerland. The site has been used for several long-term monitoring as well as experimental studies for the last four decades. Our G-TREE experiment consists of a lowest site located in a subalpine Larch-Spruce forest (Larici-Picetum) dominated by Larix decidua and Picea abies (1930 m a.s.l.), a transition zone site dominated by alpine shrubs (2100 m a.s.l.), and an uppermost site in an alpine meadow with some dwarf shrubs (2390 m a.s.l.).;46.771906 9.86624;Davos, Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "fb76e829-e2a2-5f32-a855-97c5e570aac7",
-    "notes": [
-        "G-TREE is a global research network composed of 40 arctic and alpine researchers from around the world. This summer, our field experiment will be established at numerous sites across Canada, France, Norway, Spain, the United States, and Venezuela. Other sites are being developed in Russia, Scotland, and Sweden. \n\nThe Stillberg research area is located in the Eastern Swiss Alps near Davos, Switzerland. The site has been used for several long-term monitoring as well as experimental studies for the last four decades. Our G-TREE experiment consists of a lowest site located in a subalpine Larch-Spruce forest (Larici-Picetum) dominated by Larix decidua and Picea abies (1930 m a.s.l.), a transition zone site dominated by alpine shrubs (2100 m a.s.l.), and an uppermost site in an alpine meadow with some dwarf shrubs (2390 m a.s.l.)."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:6078db91-18c3-411c-ba36-837b718a5897"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[9.86624,46.771906],[9.86624,46.771906],[9.86624,46.771906],[9.86624,46.771906],[9.86624,46.771906]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "CLIMATE CHANGE"
-        },
-        {
-            "name": "FOREST"
-        },
-        {
-            "name": "TREELINE"
-        }
-    ],
-    "title": [
-        "G-TREE: Global Treeline Range Expansion Experiment Davos, Switzerland"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/fcf956ab-be1e-595f-8021-51da4d82c046.json b/oaitestdata/envidat-datacite/SET_1/json/fcf956ab-be1e-595f-8021-51da4d82c046.json
deleted file mode 100644
index 3a214c7e..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/fcf956ab-be1e-595f-8021-51da4d82c046.json
+++ /dev/null
@@ -1,120 +0,0 @@
-{
-    "Contact": [
-        "Urs-Beat Br\u00e4ndli"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.21258/1057112",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "URL"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:f4f7ed9e-de38-4205-8638-399bcc8edb87",
-    "MetadataAccess": [
-        "oai:envidat.ch:f4f7ed9e-de38-4205-8638-399bcc8edb87"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/total_basal_area_nfi1-238"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Huber M.",
-        "Herold-Bonardi, A.",
-        "Keller, M.",
-        "Traub, B.",
-        "Fischer, C.",
-        "Meile, R.",
-        "Vidondo, B.",
-        "R\u00f6sler, E.",
-        "Speich, S.",
-        "Abegg, M.",
-        "Br\u00e4ndli, U.-B.",
-        "Cioldi, F."
-    ],
-    "fulltext": "oai:envidat.ch:f4f7ed9e-de38-4205-8638-399bcc8edb87;2018-12-09T00:33:19Z;10.21258/1057112;Abegg, M.;WSL;Br\u00e4ndli, U.-B.;WSL;Cioldi, F.;WSL;Fischer, C.;WSL;Herold-Bonardi, A.;WSL;Huber M.;WSL;Keller, M.;WSL;Meile, R.;WSL;R\u00f6sler, E.;WSL;Speich, S.;WSL;Traub, B.;WSL;Vidondo, B.;WSL;Total basal area NFI1;2014;Swiss Federal Research Institute WSL;7 CLASSES;ACCESSIBLE FOREST WITHOUT SHRUB FOREST;ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI1-NFI2-NFI3-NFI4;ALTITUDINAL VEGETATION ZONE;BIOGEOGRAPHICAL REGION;CANTON;ECONOMIC REGION;FOREST COMMUNITIES K\u00dcCHLER 2008;GRID NFI4 2009-2013;MAIN TREE SPECIES;NFI1;PRODUCTION REGION;PROTECTION FOREST REGION;TERRESTRIAL GRID NFI1;TOTAL BASAL AREA NFI1;Urs-Beat Br\u00e4ndli;WSL;2018-12-06;en;Dataset;https://www.envidat.ch/dataset/total_basal_area_nfi1-238;URL;1.0;Other (Open);Sum of stem cross-section areas at a height of 1.3 m (dbh measurement height) of all living and dead trees and shrubs  starting at 12 cm dbh recorded according to the NFI1 method.  In NFI1 only those dead trees were recorded whose wood could still be exploited.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_;45.81802 5.95587 47.80838 10.49203;Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "fcf956ab-be1e-595f-8021-51da4d82c046",
-    "notes": [
-        "Sum of stem cross-section areas at a height of 1.3 m (dbh measurement height) of all living and dead trees and shrubs  starting at 12 cm dbh recorded according to the NFI1 method.  In NFI1 only those dead trees were recorded whose wood could still be exploited.\n\n__Citation:__\n > _Abegg, M.; Br\u00e4ndli, U.-B.; Cioldi, F.; Fischer, C.; Herold-Bonardi, A.; Huber M.; Keller, M.; Meile, R.; R\u00f6sler, E.; Speich, S.; Traub, B.; Vidondo, B. (2014). Fourth national forest inventory - result tables and maps on the Internet for the NFI 2009-2013 (NFI4b). [Published online 06.11.2014] Available from World Wide Web http://www.lfi.ch/resultate/ Birmensdorf, Swiss Federal Research Institute WSL. [doi:10.21258/1057112](https://doi.org/10.21258/1057112)_"
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:f4f7ed9e-de38-4205-8638-399bcc8edb87"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "CLASSES"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST"
-        },
-        {
-            "name": "ACCESSIBLE FOREST WITHOUT SHRUB FOREST NFI-NFI-NFI-NFI"
-        },
-        {
-            "name": "ALTITUDINAL VEGETATION ZONE"
-        },
-        {
-            "name": "BIOGEOGRAPHICAL REGION"
-        },
-        {
-            "name": "CANTON"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "ECONOMIC REGION"
-        },
-        {
-            "name": "GRID NFI -"
-        },
-        {
-            "name": "MAIN TREE SPECIES"
-        },
-        {
-            "name": "NFI"
-        },
-        {
-            "name": "PRODUCTION REGION"
-        }
-    ],
-    "title": [
-        "Total basal area NFI1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-datacite/SET_1/json/fe4e94a7-31ee-586d-a50c-4a310765d588.json b/oaitestdata/envidat-datacite/SET_1/json/fe4e94a7-31ee-586d-a50c-4a310765d588.json
deleted file mode 100644
index c97d695d..00000000
--- a/oaitestdata/envidat-datacite/SET_1/json/fe4e94a7-31ee-586d-a50c-4a310765d588.json
+++ /dev/null
@@ -1,93 +0,0 @@
-{
-    "Contact": [
-        "Michael Lehning"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.16904/23",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Format": [
-        "ZIP"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=datacite&identifier=oai:envidat.ch:e3176e82-1561-4df0-8830-76eb4f66166b",
-    "MetadataAccess": [
-        "oai:envidat.ch:e3176e82-1561-4df0-8830-76eb4f66166b"
-    ],
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Frontiers in Earth Science"
-    ],
-    "RelatedIdentifier": [
-        "https://www.envidat.ch/dataset/10-16904-23"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N-47N,10E-10E)",
-    "TempCoverageBegin": 63679694399,
-    "TempCoverageEnd": 63679694399,
-    "TemporalCoverage": " point in time : 2018-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-06T11:59:59Z",
-    "author": [
-        "Mathias Bavay",
-        "Michael Lehning",
-        "Christian V\u00f6geli"
-    ],
-    "fulltext": "oai:envidat.ch:e3176e82-1561-4df0-8830-76eb4f66166b;2018-12-09T00:31:09Z;10.16904/23;Christian V\u00f6geli;WSL;Michael Lehning;WSL and EPFL;Mathias Bavay;WSL;Precipitation Scaling Data Set (V\u00f6geli et al., Frontiers);2016;Frontiers in Earth Science;ALPINE PRECIPITATION;ALPINE3D;ALPINE3D SIMULATIONS;SNOW;SNOW COVER;SNOW DISTRIBUTION;SNOW HYDROLOGY;Michael Lehning;WSL;2018-12-06;en;https://www.envidat.ch/dataset/10-16904-23;99469351 bytes;ZIP;1.0;Open Data Commons Open Database License (ODbL);Dataset (Model input, snow distribution and validation) for the precipitation scaling paper, which should be cited along with the data set citation.\n\nThis data is useful for distributed hydrological modelling or other tasks that involve the study of snow distribution and precipitation in the high Alpine. \n\nThe format of the data is for Alpine3D (models.slf.ch) model runs but other models could be used, too.\n\nPlease cite:\n\n_V\u00f6geli, C., Lehning, M., Wever, N., Bavay M., 2016: Scaling Precipitation Input to Spatially Distributed Hydrological Models by Measured Snow Distribution., Front. Earth Sci. 4: 108. doi: 10.3389/feart.2016.00108._\n\nDataset is provided as a single zip file. \nThe archive contains two directories, the valuable distributed snow depth maps for the landscape Davos and the simulation input. \nThe archive also contains the file: \"ReadMeMetadataDataSetPrecipitationScaling\" which explains the data structure.;46.8606605287 9.70985412598 46.6866603841 10.0037384033;Davos, Switzerland",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "fe4e94a7-31ee-586d-a50c-4a310765d588",
-    "notes": [
-        "Dataset (Model input, snow distribution and validation) for the precipitation scaling paper, which should be cited along with the data set citation.\n\nThis data is useful for distributed hydrological modelling or other tasks that involve the study of snow distribution and precipitation in the high Alpine. \n\nThe format of the data is for Alpine3D (models.slf.ch) model runs but other models could be used, too.\n\nPlease cite:\n\n_V\u00f6geli, C., Lehning, M., Wever, N., Bavay M., 2016: Scaling Precipitation Input to Spatially Distributed Hydrological Models by Measured Snow Distribution., Front. Earth Sci. 4: 108. doi: 10.3389/feart.2016.00108._\n\nDataset is provided as a single zip file. \nThe archive contains two directories, the valuable distributed snow depth maps for the landscape Davos and the simulation input. \nThe archive also contains the file: \"ReadMeMetadataDataSetPrecipitationScaling\" which explains the data structure."
-    ],
-    "oai_identifier": [
-        "oai:envidat.ch:e3176e82-1561-4df0-8830-76eb4f66166b"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[9.70985412598,46.8606605287],[9.70985412598,46.6866603841],[10.0037384033,46.6866603841],[10.0037384033,46.8606605287],[9.70985412598,46.8606605287]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ALPINE PRECIPITATION"
-        },
-        {
-            "name": "ALPINED"
-        },
-        {
-            "name": "ALPINED SIMULATIONS"
-        },
-        {
-            "name": "SNOW"
-        },
-        {
-            "name": "SNOW COVER"
-        },
-        {
-            "name": "SNOW DISTRIBUTION"
-        },
-        {
-            "name": "SNOW HYDROLOGY"
-        }
-    ],
-    "title": [
-        "Precipitation Scaling Data Set (V\u00f6geli et al., Frontiers)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-iso19139/SET_1/json/106ad207-70ea-5689-ad66-a3a7cb7a4c62.json b/oaitestdata/envidat-iso19139/SET_1/json/106ad207-70ea-5689-ad66-a3a7cb7a4c62.json
deleted file mode 100644
index a6acd598..00000000
--- a/oaitestdata/envidat-iso19139/SET_1/json/106ad207-70ea-5689-ad66-a3a7cb7a4c62.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "manfred.staehli@wsl.ch"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "ZIP"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=iso19139&identifier=doi:10.16904/7",
-    "PublicationTimestamp": "2016-12-31T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "WSL"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "author": [
-        "Dr. Manfred Staehli"
-    ],
-    "fulltext": "oai:envidat.ch:10.16904/7;2018-07-07T00:09:39Z;doi:10.16904/7;Eng;MD_CharacterSetCode_utf8;Dr. Manfred Staehli;WSL;manfred.staehli@wsl.ch;2016-10-16T22:18:02;ISO 19115:2003/19139;1.0;EPSG:4326;More than one century of hydrological monitoring in two small catchments with different forest coverage, Sperbelgraben and Rappengraben (Switzerland);2016-12-31;Long-term data on precipitation and runoff are essential to draw firm conclusions about the behavior and trends of hydrological catchments that may be influenced by land-use and climate change. Here the longest continuous runoff records (1903 - 2015) from small catchments (less than 1 km2) in Switzerland (and possibly worldwide) are provided as a data set. The history of the hydrological monitoring in the Sperbel- and Rappengraben (Emmental) is summarized in St\u00e4hli et al., Environ Monit Assess (2011). The runoff stations operated safely for more than 90% of the summer months when most of the major flood events occurred. Nevertheless, the absolute values of peak runoff during the largest flood events are subject to considerable uncertainty (also discussed in St\u00e4hli et al., 2011). This treasure trove of data can be used in various ways, eg. for analysis of the generalized extreme value distributions of the two catchments, of the mechanisms governing the runoff behavior of small catchments, as well as for testing stochastic and deterministic models.;Dr. Manfred Staehli;WSL;manfred.staehli@wsl.ch;AIR TEMPERATURE;PRECIPITATION;RUNOFF;SNOW DEPTH;WATERSHED DRAINAGE BASINS;Other (Open);Eng;MD_CharacterSetCode_utf8;7.84273 47.01576;7.8903 47.0163;7.88684 47.01555;7.84487 47.02267;7.84105 47.01343;7.88851 47.01867;7.88764 47.01745;7.88702 47.01353;7.85199 47.03105;ZIP;https://www.envidat.ch/dataset/10-16904-7;HTTPS;DATASET METADATA;information;https://www.envidat.ch/dataset/c54a616a-4419-4ba8-840e-82f6ec5c05ff/resource/c40b6688-86b1-4c42-9ece-2ad23e19b977/download/daten-sperbel-rappengraben-for-envidat.zip;HTTPS;DATEN SPERBEL-RAPPENGRABEN;download",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "106ad207-70ea-5689-ad66-a3a7cb7a4c62",
-    "notes": [
-        "Long-term data on precipitation and runoff are essential to draw firm conclusions about the behavior and trends of hydrological catchments that may be influenced by land-use and climate change. Here the longest continuous runoff records (1903 - 2015) from small catchments (less than 1 km2) in Switzerland (and possibly worldwide) are provided as a data set. The history of the hydrological monitoring in the Sperbel- and Rappengraben (Emmental) is summarized in St\u00e4hli et al., Environ Monit Assess (2011). The runoff stations operated safely for more than 90% of the summer months when most of the major flood events occurred. Nevertheless, the absolute values of peak runoff during the largest flood events are subject to considerable uncertainty (also discussed in St\u00e4hli et al., 2011). This treasure trove of data can be used in various ways, eg. for analysis of the generalized extreme value distributions of the two catchments, of the mechanisms governing the runoff behavior of small catchments, as well as for testing stochastic and deterministic models."
-    ],
-    "oai_identifier": [
-        "doi:10.16904/7",
-        "oai:envidat.ch:10.16904/7"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "AIR TEMPERATURE"
-        },
-        {
-            "name": "PRECIPITATION"
-        },
-        {
-            "name": "RUNOFF"
-        },
-        {
-            "name": "SNOW DEPTH"
-        },
-        {
-            "name": "WATERSHED DRAINAGE BASINS"
-        }
-    ],
-    "title": [
-        "More than one century of hydrological monitoring in two small catchments with different forest coverage, Sperbelgraben and Rappengraben (Switzerland)"
-    ],
-    "url": "https://www.envidat.ch/dataset/c54a616a-4419-4ba8-840e-82f6ec5c05ff/resource/c40b6688-86b1-4c42-9ece-2ad23e19b977/download/daten-sperbel-rappengraben-for-envidat.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-iso19139/SET_1/json/25f91d90-d57b-599a-8383-43b9a71a46af.json b/oaitestdata/envidat-iso19139/SET_1/json/25f91d90-d57b-599a-8383-43b9a71a46af.json
deleted file mode 100644
index 360e7319..00000000
--- a/oaitestdata/envidat-iso19139/SET_1/json/25f91d90-d57b-599a-8383-43b9a71a46af.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "sommer@slf.ch"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "TXT",
-        "LINK",
-        "ZIP"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=iso19139&identifier=doi:10.16904/22",
-    "PublicationTimestamp": "2017-12-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland and CRYOS, School of Architecture and Civil Engineering, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "author": [
-        "Christian Sommer"
-    ],
-    "fulltext": "oai:envidat.ch:10.16904/22;2018-02-22T14:47:38Z;doi:10.16904/22;Eng;MD_CharacterSetCode_utf8;Christian Sommer;WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland and CRYOS, School of Architecture and Civil Engineering, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland;sommer@slf.ch;2017-06-22T16:13:51;ISO 19115:2003/19139;1.0;EPSG:4326;Wind crust formation: Microsoft Kinect data;2017-12-31;This data sets contains the Microsoft Kinect data from 15 wind tunnel experiments on wind-packing / wind crust formation. These experiments were performed in the winter 2016/17. The Kinect measures distributed snow depth.    The Kinect data is organized per experiment. Each experiment subfolder contains the processed Kinect depth images and some additional files.    Please refer to the README for more details on the data. The processing scripts are available for download as well. The scripts are mainly provided as documentation and would need to be adjusted to be used.    This dataset is the basis of the following publication:    Sommer C.G., Lehning M. & Fierz C. (2018). Wind Tunnel Experiments: Influence of Erosion and Deposition on Wind-Packing of New Snow. Front. Earth Sci. 6:4. doi: 10.3389/feart.2018.00004;Christian Sommer;WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland and CRYOS, School of Architecture and Civil Engineering, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland;sommer@slf.ch;KINECT;SNOW;WIND CRUST;WIND-PACKING;Open Data Commons Open Database License (ODbL);Eng;MD_CharacterSetCode_utf8;9.86752 46.80798;LINK;TXT;ZIP;https://www.envidat.ch/dataset/10-16904-22;HTTPS;DATASET METADATA;information;http://montblanc.slf.ch/owncloud/index.php/s/wb7dkWxV8x8tMtK;HTTP;KINECT DATA;download;https://www.envidat.ch/dataset/d57b3332-804d-463b-bbf8-0ed38593e180/resource/76c0e984-004d-4524-9f2f-30005a955d83/download/readme.txt;HTTPS;README;download;https://www.envidat.ch/dataset/d57b3332-804d-463b-bbf8-0ed38593e180/resource/28bfe352-df8a-423e-ae2c-d938b0c2a4c1/download/processingscripts.zip;HTTPS;PROCESSING SCRIPTS;download",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "25f91d90-d57b-599a-8383-43b9a71a46af",
-    "notes": [
-        "This data sets contains the Microsoft Kinect data from 15 wind tunnel experiments on wind-packing / wind crust formation. These experiments were performed in the winter 2016/17. The Kinect measures distributed snow depth.    The Kinect data is organized per experiment. Each experiment subfolder contains the processed Kinect depth images and some additional files.    Please refer to the README for more details on the data. The processing scripts are available for download as well. The scripts are mainly provided as documentation and would need to be adjusted to be used.    This dataset is the basis of the following publication:    Sommer C.G., Lehning M. & Fierz C. (2018). Wind Tunnel Experiments: Influence of Erosion and Deposition on Wind-Packing of New Snow. Front. Earth Sci. 6:4. doi: 10.3389/feart.2018.00004"
-    ],
-    "oai_identifier": [
-        "doi:10.16904/22",
-        "oai:envidat.ch:10.16904/22"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "KINECT"
-        },
-        {
-            "name": "SNOW"
-        },
-        {
-            "name": "WIND CRUST"
-        },
-        {
-            "name": "WIND-PACKING"
-        }
-    ],
-    "title": [
-        "Wind crust formation: Microsoft Kinect data"
-    ],
-    "url": "https://www.envidat.ch/dataset/d57b3332-804d-463b-bbf8-0ed38593e180/resource/28bfe352-df8a-423e-ae2c-d938b0c2a4c1/download/processingscripts.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-iso19139/SET_1/json/2ea750c6-4354-5f0a-9b67-2275d922d06f.json b/oaitestdata/envidat-iso19139/SET_1/json/2ea750c6-4354-5f0a-9b67-2275d922d06f.json
deleted file mode 100644
index 4f6970c4..00000000
--- a/oaitestdata/envidat-iso19139/SET_1/json/2ea750c6-4354-5f0a-9b67-2275d922d06f.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "accidents@slf.ch"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "CSV"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=iso19139&identifier=doi:10.16904/14",
-    "PublicationTimestamp": "2018-12-31T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avalanche Research SLF"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "author": [
-        "Avalanche Warning Service SLF"
-    ],
-    "fulltext": "oai:envidat.ch:10.16904/14;2018-11-12T09:04:19Z;doi:10.16904/14;Eng;MD_CharacterSetCode_utf8;Avalanche Warning Service SLF;WSL Institute for Snow and Avalanche Research SLF;accidents@slf.ch;2017-03-01T11:54:28;ISO 19115:2003/19139;1.0;EPSG:4326;Number of avalanche fatalities per hydrological year in Switzerland since 1936-1937;2018-12-31;This dataset contains the statistics on the number of avalanche fatalities per  hydrological year in Switzerland. The data set commences with the beginning of the hydrological year 1936/37 on 01/10/1936. After the completion of a hydrological year, the new data is appended to the existing dataset.     The following information is contained (by column and column title):     - hydrological year     - number of fatalities in the backcountry (=tour)     - number of fatalities in terrain close to ski areas (=offpiste)     - number of fatalities on transportation corridors including ski runs, roads, railway lines (=transportation.corridors)     - number of fatalities in or around buildings or in settlements (= buildings)     - sum (of all four categories)      The definition for these four categories as described in the guidelines to the avalanche accident database:           **tour**:       activities include back-country ski, snowboard or snow-shoe touring      **offpiste**:    access from ski area, generally from the top of a skilift with short hiking distances      **transportation.corridors** ([Techel et al., 2016](http://www.geogr-helv.net/71/147/2016/ )):     people travelling or recreating on open or temporarily closed  transportation corridors (e.g. a road user or a skier on a ski run) and people working on open or closed transportation corridors (e.g. maintenance crews on roads, professional rescue teams)       **buildings** ([Techel et al., 2016](http://www.geogr-helv.net/71/147/2016/ )):    people inside or just outside buildings, and workers on high alpine building  sites;Avalanche Warning Service SLF;WSL Institute for Snow and Avalanche Research SLF;accidents@slf.ch;AVALANCHE ACCIDENT STATISTICS;AVALANCHE ACCIDENTS;AVALANCHE FATALITIES;Open Data Commons Open Database License (ODbL);Eng;MD_CharacterSetCode_utf8;5.95587;10.49203;45.81802;47.80838;CSV;https://www.envidat.ch/dataset/avalanche-fatalities-switzerland-1936;HTTPS;DATASET METADATA;information;https://www.envidat.ch/dataset/09817bad-b6bf-424a-82a2-f233a1037a42/resource/419fadba-a176-4058-bdc6-94879f56ef29/download/avalanche_fatalities_switzerland_since_1936.csv;HTTPS;AVALANCHE FATALITIES PER YEAR IN SWITZERLAND SINCE 1936/1937;download",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "2ea750c6-4354-5f0a-9b67-2275d922d06f",
-    "notes": [
-        "This dataset contains the statistics on the number of avalanche fatalities per  hydrological year in Switzerland. The data set commences with the beginning of the hydrological year 1936/37 on 01/10/1936. After the completion of a hydrological year, the new data is appended to the existing dataset.     The following information is contained (by column and column title):     - hydrological year     - number of fatalities in the backcountry (=tour)     - number of fatalities in terrain close to ski areas (=offpiste)     - number of fatalities on transportation corridors including ski runs, roads, railway lines (=transportation.corridors)     - number of fatalities in or around buildings or in settlements (= buildings)     - sum (of all four categories)      The definition for these four categories as described in the guidelines to the avalanche accident database:           **tour**:       activities include back-country ski, snowboard or snow-shoe touring      **offpiste**:    access from ski area, generally from the top of a skilift with short hiking distances      **transportation.corridors** ([Techel et al., 2016](http://www.geogr-helv.net/71/147/2016/ )):     people travelling or recreating on open or temporarily closed  transportation corridors (e.g. a road user or a skier on a ski run) and people working on open or closed transportation corridors (e.g. maintenance crews on roads, professional rescue teams)       **buildings** ([Techel et al., 2016](http://www.geogr-helv.net/71/147/2016/ )):    people inside or just outside buildings, and workers on high alpine building  sites"
-    ],
-    "oai_identifier": [
-        "doi:10.16904/14",
-        "oai:envidat.ch:10.16904/14"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "AVALANCHE ACCIDENT STATISTICS"
-        },
-        {
-            "name": "AVALANCHE ACCIDENTS"
-        },
-        {
-            "name": "AVALANCHE FATALITIES"
-        }
-    ],
-    "title": [
-        "Number of avalanche fatalities per hydrological year in Switzerland since 1936-1937"
-    ],
-    "url": "https://www.envidat.ch/dataset/09817bad-b6bf-424a-82a2-f233a1037a42/resource/419fadba-a176-4058-bdc6-94879f56ef29/download/avalanche_fatalities_switzerland_since_1936.csv"
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-iso19139/SET_1/json/303bdc67-fdc9-5b04-9fdb-30d582d9da32.json b/oaitestdata/envidat-iso19139/SET_1/json/303bdc67-fdc9-5b04-9fdb-30d582d9da32.json
deleted file mode 100644
index d8db9fdf..00000000
--- a/oaitestdata/envidat-iso19139/SET_1/json/303bdc67-fdc9-5b04-9fdb-30d582d9da32.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "alexander.haumann@usys.ethz.ch"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "URL",
-        "PDF",
-        "NETCDF4 CF-1.6"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=iso19139&identifier=doi:10.16904/8",
-    "PublicationTimestamp": "2016-12-31T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Rights": [
-        "Other (Non-Commercial)"
-    ],
-    "SpatialCoverage": "(90S-37S,180W-180E)",
-    "author": [
-        "F. Alexander Haumann"
-    ],
-    "fulltext": "oai:envidat.ch:10.16904/8;2018-07-10T09:48:38Z;doi:10.16904/8;Eng;MD_CharacterSetCode_utf8;F. Alexander Haumann;alexander.haumann@usys.ethz.ch;2016-10-17T12:19:28;ISO 19115:2003/19139;1.0;EPSG:4326;Antarctic sea-ice freshwater fluxes associated with freezing, transport, and melting;2016-12-31;This data set provides estimates of annual fresh water fluxes related to sea-ice formation from ocean freezing and snow-ice formation, sea-ice melting, lateral transport of sea ice in the Southern Ocean over the period 1982 to 2008.It is derived from a mass balance calculation of local sea-ice volume change and divergence from satellite data and sea-ice reconstructions. The mass balance is calculated on a daily basis and fluxes are then integrated over the entire year, where a year is defined from March to February of the next year (i.e. from March 1982 to February 2009). This approach combines multiple products of sea-ice concentration (Cavalieri & Parkinson, 2008;Comiso, 1986; Meier et al., 2013), sea-ice thickness (Kurtz & Markus, 2012; Massonnet et al., 2013; Worby et al., 2008), and sea-ice drift (Fowler et al., 2013; Kwok 2005; Schwegmann et al., 2011). For a detailed description of the method see Haumann et al. (2016). The data set is derived to estimate large-scale (regional to basin-scale) fluxes on an annual basis. Our confidence is reduced on a grid cell basis, such as for single coastal polynyas, where the method and underlying data induce large, unknown uncertainties.    _Disclaimer: This data set is free to use for any non-commercial purpose at the risk of the user and the authors do not take any liability on the use of the data set. The authors assembled the data set carefully and assessed accuracy, errors, and uncertainties. Please contact the authors if you find any issues._    __Related publication__: http://www.nature.com/nature/journal/v537/n7618/full/nature19101.html (doi:10.1038/nature19101);F. Alexander Haumann;alexander.haumann@usys.ethz.ch;ANTARTIC;CLIMATE CHANGE;CRYOSPHERIC SCIENCE;FORCING;FREEZING;FRESHWATER FLUX;MASS BALANCE;MELTING;PHYSICAL OCEANOGRAPHY;POLAR;SALINITY;SALT;SATELLITE;SEA ICE;SEA ICE DIVERGENCE;SEA ICE VOLUME;SOUTHERN OCEAN;TRANSPORT;Other (Non-Commercial);Eng;MD_CharacterSetCode_utf8;-180;180;-89.7;-37;PDF;NETCDF4 CF-1.6;URL;https://www.envidat.ch/dataset/10-16904-8;HTTPS;DATASET METADATA;information;https://www.envidat.ch/dataset/b16a0901-3abe-4da0-b61e-cdb80c59ba63/resource/a2d8430f-dc92-4a03-b3d6-6661b553bdd1/download/aniceflux_v01.pdf;HTTPS;EXPLANATORY DOCUMENT;download;https://www.envidat.ch/dataset/b16a0901-3abe-4da0-b61e-cdb80c59ba63/resource/5de37dd3-e6a7-41b4-b97a-21b14734b861/download/aniceflux_v01_annual_1982-2008.nc;HTTPS;ANICEFLUX_V01_ANNUAL_1982-2008.NC;download;https://www.envidat.ch/dataset/b16a0901-3abe-4da0-b61e-cdb80c59ba63/resource/6a315e6d-4c92-4f85-b131-92fd87853b65/download/aniceflux_v01_clim_mean_1982-2008.nc;HTTPS;ANICEFLUX_V01_CLIM_MEAN_1982-2008.NC;download;http://www.nature.com/articles/nature19101.epdf?author_access_token=dtLqMQ3Ss6p16tymoagae9RgN0jAjWel9jnR3ZoTv0PH2BR1NrVw3zxcEnl7ViU5pKp8iHAlc_ntQx82EiRMqFRuGOR0VueOUVoGWzy8lSzML6YUBUMMZ5f4LYCdK8Ca;HTTP;LINK TO RELATED PUBLICATION;download",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "303bdc67-fdc9-5b04-9fdb-30d582d9da32",
-    "notes": [
-        "This data set provides estimates of annual fresh water fluxes related to sea-ice formation from ocean freezing and snow-ice formation, sea-ice melting, lateral transport of sea ice in the Southern Ocean over the period 1982 to 2008.It is derived from a mass balance calculation of local sea-ice volume change and divergence from satellite data and sea-ice reconstructions. The mass balance is calculated on a daily basis and fluxes are then integrated over the entire year, where a year is defined from March to February of the next year (i.e. from March 1982 to February 2009). This approach combines multiple products of sea-ice concentration (Cavalieri & Parkinson, 2008;Comiso, 1986; Meier et al., 2013), sea-ice thickness (Kurtz & Markus, 2012; Massonnet et al., 2013; Worby et al., 2008), and sea-ice drift (Fowler et al., 2013; Kwok 2005; Schwegmann et al., 2011). For a detailed description of the method see Haumann et al. (2016). The data set is derived to estimate large-scale (regional to basin-scale) fluxes on an annual basis. Our confidence is reduced on a grid cell basis, such as for single coastal polynyas, where the method and underlying data induce large, unknown uncertainties.    _Disclaimer: This data set is free to use for any non-commercial purpose at the risk of the user and the authors do not take any liability on the use of the data set. The authors assembled the data set carefully and assessed accuracy, errors, and uncertainties. Please contact the authors if you find any issues._    __Related publication__: http://www.nature.com/nature/journal/v537/n7618/full/nature19101.html (doi:10.1038/nature19101)"
-    ],
-    "oai_identifier": [
-        "doi:10.16904/8",
-        "oai:envidat.ch:10.16904/8"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-180,-89.7],[-180,-37],[180,-37],[180,-89.7],[-180,-89.7]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ANTARTIC"
-        },
-        {
-            "name": "CLIMATE CHANGE"
-        },
-        {
-            "name": "CRYOSPHERIC SCIENCE"
-        },
-        {
-            "name": "FORCING"
-        },
-        {
-            "name": "FREEZING"
-        },
-        {
-            "name": "FRESHWATER FLUX"
-        },
-        {
-            "name": "MASS BALANCE"
-        },
-        {
-            "name": "MELTING"
-        },
-        {
-            "name": "PHYSICAL OCEANOGRAPHY"
-        },
-        {
-            "name": "POLAR"
-        },
-        {
-            "name": "SALINITY"
-        },
-        {
-            "name": "SALT"
-        }
-    ],
-    "title": [
-        "Antarctic sea-ice freshwater fluxes associated with freezing, transport, and melting"
-    ],
-    "url": "http://www.nature.com/articles/nature19101.epdf?author_access_token=dtLqMQ3Ss6p16tymoagae9RgN0jAjWel9jnR3ZoTv0PH2BR1NrVw3zxcEnl7ViU5pKp8iHAlc_ntQx82EiRMqFRuGOR0VueOUVoGWzy8lSzML6YUBUMMZ5f4LYCdK8Ca"
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-iso19139/SET_1/json/31c606f6-0ced-5f50-a4f1-e4cfdf444583.json b/oaitestdata/envidat-iso19139/SET_1/json/31c606f6-0ced-5f50-a4f1-e4cfdf444583.json
deleted file mode 100644
index 1550f36a..00000000
--- a/oaitestdata/envidat-iso19139/SET_1/json/31c606f6-0ced-5f50-a4f1-e4cfdf444583.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "fabrizio.cioldi@wsl.ch"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "URL"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=iso19139&identifier=doi:10.16904/3",
-    "PublicationTimestamp": "2016-12-31T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "WSL"
-    ],
-    "Rights": [
-        "Other (Non-Commercial)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "author": [
-        "Fabrizio Cioldi"
-    ],
-    "fulltext": "oai:envidat.ch:10.16904/3;2018-08-21T10:38:35Z;doi:10.16904/3;Ger;MD_CharacterSetCode_utf8;Fabrizio Cioldi;WSL;fabrizio.cioldi@wsl.ch;2016-10-16T22:24:05;ISO 19115:2003/19139;1.0;EPSG:4326;Forest Access Roads 2013;2016-12-31;In 2013\u20132014, a survey was conducted in Switzerland to update the Forest Access Roads geo-dataset within the framework of the Swiss National Forest Inventory (NFI). The resulting nationwide dataset contains valuable information on truck-accessible forest roads that can be used to transport wood. The survey involved interviewing staff from the approximately 800 local forest services in Switzerland and recording the data first on paper maps and then in digitized form. The data in the NFI on the forest roads could thus be updated and additional information regarding their trafficability for specific categories of truck included. The information has now been attached to the geometries of the Roads and Tracks of the swissTLM3D (release 2012) of the Federal Office of Topography swisstopo. The resulting data are suitable for statistical analyses and modeling, but further (labour-intensive) validation work would be necessary if they are to be used as a basis for applications requiring more spatial accuracy, such as navigation systems. The data are managed at the Swiss Federal Institute for Forest, Snow and Landscape Research (WSL) and are available for third parties for non-commercial use provided they have purchased a TLM license.     __Related Publication__: [doi: 10.3188/szf.2016.0136](http://dx.doi.org/10.3188/szf.2016.0136);Fabrizio Cioldi;WSL;fabrizio.cioldi@wsl.ch;FOREST ACCESS ROADS;FOREST TRANSPORTATION SYSTEMS;TIMBER HARVESTING;TRAFFICABILITY;TRUCKS;Other (Non-Commercial);Ger;MD_CharacterSetCode_utf8;5.95587;10.49203;45.81802;47.80838;URL;https://www.envidat.ch/dataset/10-16904-3;HTTPS;DATASET METADATA;information;https://www.dora.lib4ri.ch/wsl/islandora/object/wsl:5563;HTTPS;PUBLICATION WALDERSCHLIESSUNGSSTRASSEN 2013;download",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "31c606f6-0ced-5f50-a4f1-e4cfdf444583",
-    "notes": [
-        "In 2013\u20132014, a survey was conducted in Switzerland to update the Forest Access Roads geo-dataset within the framework of the Swiss National Forest Inventory (NFI). The resulting nationwide dataset contains valuable information on truck-accessible forest roads that can be used to transport wood. The survey involved interviewing staff from the approximately 800 local forest services in Switzerland and recording the data first on paper maps and then in digitized form. The data in the NFI on the forest roads could thus be updated and additional information regarding their trafficability for specific categories of truck included. The information has now been attached to the geometries of the Roads and Tracks of the swissTLM3D (release 2012) of the Federal Office of Topography swisstopo. The resulting data are suitable for statistical analyses and modeling, but further (labour-intensive) validation work would be necessary if they are to be used as a basis for applications requiring more spatial accuracy, such as navigation systems. The data are managed at the Swiss Federal Institute for Forest, Snow and Landscape Research (WSL) and are available for third parties for non-commercial use provided they have purchased a TLM license.     __Related Publication__: [doi: 10.3188/szf.2016.0136](http://dx.doi.org/10.3188/szf.2016.0136)"
-    ],
-    "oai_identifier": [
-        "doi:10.16904/3",
-        "oai:envidat.ch:10.16904/3"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "FOREST ACCESS ROADS"
-        },
-        {
-            "name": "FOREST TRANSPORTATION SYSTEMS"
-        },
-        {
-            "name": "TIMBER HARVESTING"
-        },
-        {
-            "name": "TRAFFICABILITY"
-        },
-        {
-            "name": "TRUCKS"
-        }
-    ],
-    "title": [
-        "Forest Access Roads 2013"
-    ],
-    "url": "https://www.dora.lib4ri.ch/wsl/islandora/object/wsl:5563"
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-iso19139/SET_1/json/339fa94f-8532-5f12-8d27-01f61185ce45.json b/oaitestdata/envidat-iso19139/SET_1/json/339fa94f-8532-5f12-8d27-01f61185ce45.json
deleted file mode 100644
index 02e302ed..00000000
--- a/oaitestdata/envidat-iso19139/SET_1/json/339fa94f-8532-5f12-8d27-01f61185ce45.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "marcus.schaub@wsl.ch"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "URL",
-        "XLSX",
-        "JPEG"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=iso19139&identifier=doi:10.16904/11",
-    "PublicationTimestamp": "2016-12-31T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Swiss Federal Research Institute WSL"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "author": [
-        "Marcus Schaub"
-    ],
-    "fulltext": "oai:envidat.ch:10.16904/11;2018-07-07T00:13:04Z;doi:10.16904/11;Eng;MD_CharacterSetCode_utf8;Marcus Schaub;Swiss Federal Research Institute WSL;marcus.schaub@wsl.ch;2016-11-04T13:48:21;ISO 19115:2003/19139;1.0;EPSG:4326;Tree\tmeasurements 2002-2016 from the long-term irrigation experiment Pfynwald, Switzerland;2016-12-31;To study the performance of mature Scots pine (_Pinus sylvestris_ L.) under chronic drought conditions in comparison to their immediate physiological response to drought release, a controlled long-term and large-scale irrigation experiment has been set up in 2003. The experiment is located in a xeric mature Scots pine forest in the Pfynwald (46\u00b0 18' N, 7\u00b0 36' E, 615 m a.s.l.) in one of the driest inner-Alpine valleys of the European Alps, the Valais (mean annual temperature: 9.2\u00b0C, annual precipitation sum: 657 mm, both 1961-1990). Tree age is on average 100 years, the top height is 10.8 m and the stand density is 730 stems ha-1 with a basal area of 27.3 m2 ha-1. The forest is described as _Erico Pinetum sylvestris_ and the soil is a shallow pararendzina characterized by low water retention. The experimental site (1.2 ha; 800 trees) is split up into eight plots of 1'000 m2 each. During April-October, irrigation is applied on four randomly selected plots with sprinklers of 1 m height at night using water from an adjacent water channel. The amount of irrigation corresponds to a supplementary rainfall of 700 mm year-1. Trees in the other four plots grow under naturally dry conditions. Soil moisture has been monitored since the beginning of the project at 3 soil depths (10, 20 and 60 cm). The crown condition of each tree is being assessed each year since 2003. Tree measurement data such as diameter at breast height, tree height, and social status were assessed in 2002, 2009 and 2014. The duration of the irrigation experiment is planned for 20 years.;Marcus Schaub;Swiss Federal Research Institute WSL;marcus.schaub@wsl.ch;CROWN CONDITION;DBH;DIAMETER AT BREAST HEIGHT;DROUGHT;IRRIGATION;SCOTS PINE;TREE;TREE SPECIES;Open Data Commons Open Database License (ODbL);Eng;MD_CharacterSetCode_utf8;7.61192 46.30284;XLSX;JPEG;URL;https://www.envidat.ch/dataset/pfynwald;HTTPS;DATASET METADATA;information;https://www.envidat.ch/dataset/0e18a914-f2e4-47df-a86c-a44a1b0055e4/resource/81280262-3628-458c-8dbf-33ed80eb222a/download/envidatpfyncrowncond2016.xlsx;HTTPS;DATASET;download;https://www.envidat.ch/dataset/0e18a914-f2e4-47df-a86c-a44a1b0055e4/resource/e0eed15d-de04-44f0-8601-cb531f9fa916/download/20150709pfyn117.jpg;HTTPS;SITE PHOTO 1;download;https://www.envidat.ch/dataset/0e18a914-f2e4-47df-a86c-a44a1b0055e4/resource/fd9b4ee3-e87e-4c0b-b7a8-832fb3f019e7/download/20150709pfyn117.jpg;HTTPS;SITE PHOTO 2;download;https://www.envidat.ch/dataset/0e18a914-f2e4-47df-a86c-a44a1b0055e4/resource/e3c46133-0b7c-4d9c-a3d0-ba0e91e663b5/download/20150709pfyn218.jpg;HTTPS;SITE PHOTO 3;download;http://www.wsl.ch/fe/walddynamik/projekte/irrigationpfynwald/index_EN;HTTP;LONG-TERM IRRIGATION\tEXPERIMENT PFYNWALD HOMEPAGE;download;http://www.wsl.ch/dienstleistungen/inventare/sanasilva/index_EN;HTTP;SWISS FOREST HEALTH INVENTORY;download;https://map.geo.admin.ch/?topic=swisstopo&X=127951&Y=613350&zoom=11&lang=de&bgLay er=ch.swisstopo.pixelkarte-farbe&crosshair=marker;HTTPS;SHAPEFILE\tOF MEASUREMENT LOCATION;download",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "339fa94f-8532-5f12-8d27-01f61185ce45",
-    "notes": [
-        "To study the performance of mature Scots pine (_Pinus sylvestris_ L.) under chronic drought conditions in comparison to their immediate physiological response to drought release, a controlled long-term and large-scale irrigation experiment has been set up in 2003. The experiment is located in a xeric mature Scots pine forest in the Pfynwald (46\u00b0 18' N, 7\u00b0 36' E, 615 m a.s.l.) in one of the driest inner-Alpine valleys of the European Alps, the Valais (mean annual temperature: 9.2\u00b0C, annual precipitation sum: 657 mm, both 1961-1990). Tree age is on average 100 years, the top height is 10.8 m and the stand density is 730 stems ha-1 with a basal area of 27.3 m2 ha-1. The forest is described as _Erico Pinetum sylvestris_ and the soil is a shallow pararendzina characterized by low water retention. The experimental site (1.2 ha; 800 trees) is split up into eight plots of 1'000 m2 each. During April-October, irrigation is applied on four randomly selected plots with sprinklers of 1 m height at night using water from an adjacent water channel. The amount of irrigation corresponds to a supplementary rainfall of 700 mm year-1. Trees in the other four plots grow under naturally dry conditions. Soil moisture has been monitored since the beginning of the project at 3 soil depths (10, 20 and 60 cm). The crown condition of each tree is being assessed each year since 2003. Tree measurement data such as diameter at breast height, tree height, and social status were assessed in 2002, 2009 and 2014. The duration of the irrigation experiment is planned for 20 years."
-    ],
-    "oai_identifier": [
-        "doi:10.16904/11",
-        "oai:envidat.ch:10.16904/11"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "CROWN CONDITION"
-        },
-        {
-            "name": "DBH"
-        },
-        {
-            "name": "DIAMETER BREAST HEIGHT"
-        },
-        {
-            "name": "DROUGHT"
-        },
-        {
-            "name": "IRRIGATION"
-        },
-        {
-            "name": "SCOTS PINE"
-        },
-        {
-            "name": "TREE"
-        },
-        {
-            "name": "TREE SPECIES"
-        }
-    ],
-    "title": [
-        "Tree\tmeasurements 2002-2016 from the long-term irrigation experiment Pfynwald, Switzerland"
-    ],
-    "url": "https://map.geo.admin.ch/?topic=swisstopo&X=127951&Y=613350&zoom=11&lang=de&bgLay"
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-iso19139/SET_1/json/48314924-e38a-53ce-b26a-ac157cf158f8.json b/oaitestdata/envidat-iso19139/SET_1/json/48314924-e38a-53ce-b26a-ac157cf158f8.json
deleted file mode 100644
index a5ccb7e9..00000000
--- a/oaitestdata/envidat-iso19139/SET_1/json/48314924-e38a-53ce-b26a-ac157cf158f8.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "schneebeli@slf.ch"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "TXT",
-        "ZIP"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=iso19139&identifier=doi:10.16904/20",
-    "PublicationTimestamp": "2017-12-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avalanche Research"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "author": [
-        "Martin Schneebeli"
-    ],
-    "fulltext": "oai:envidat.ch:10.16904/20;2018-05-03T16:52:16Z;doi:10.16904/20;Eng;MD_CharacterSetCode_utf8;Martin Schneebeli;WSL Institute for Snow and Avalanche Research;schneebeli@slf.ch;2017-06-26T08:47:38;ISO 19115:2003/19139;1.0;EPSG:4326;Experiments on stable water isotopes,  snow metamorphism, and advection;2017-12-31;Stable water isotopes (\u03b418O) obtained from snow and ice samples of polar regions are used to reconstruct past climate variability, but heat and mass transport processes can affect the isotopic composition. Here we present an experimental study on the effect on the snow isotopic composition by airflow through a snow pack in controlled laboratory conditions. The influence of isothermal and controlled temperature gradient conditions on the \u03b418O content in the snow and interstitial water vapor is elucidated. The observed disequilibrium between snow and vapor isotopes led to exchange of isotopes between snow and vapor under non-equilibrium processes, significantly changing the \u03b418O content of the snow. The type of metamorphism of the snow had a significant influence on this process.   Ebner, P. P., Steen-Larsen, H. C., Stenni, B., Schneebeli, M., and Steinfeld, A.: Experimental observation of transient \u03b418O interaction between snow and advective airflow under various temperature gradient conditions, The Cryosphere Discuss., https://doi.org/10.5194/tc-2017-16, accepted, 2017.;Martin Schneebeli;WSL Institute for Snow and Avalanche Research;schneebeli@slf.ch;ADVECTION;METAMORPHISM;SNOW;STABLE WATER ISOTOPE;Open Data Commons Open Database License (ODbL);Eng;MD_CharacterSetCode_utf8;9.84736561775 46.812580167;TXT;ZIP;https://www.envidat.ch/dataset/snow-deltao18-metamorphism-advection;HTTPS;DATASET METADATA;information;https://www.envidat.ch/dataset/f87efc01-9914-4a75-998f-7dfc1fcef563/resource/92a315fd-1e17-4b9e-bce3-e69a3fac0d0a/download/readme.txt;HTTPS;READ-ME;download;https://www.envidat.ch/dataset/f87efc01-9914-4a75-998f-7dfc1fcef563/resource/e133ed87-de41-4595-87c9-b07f696c5cce/download/archive.zip;HTTPS;DATA FILES AND READ-ME;download",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "48314924-e38a-53ce-b26a-ac157cf158f8",
-    "notes": [
-        "Stable water isotopes (\u03b418O) obtained from snow and ice samples of polar regions are used to reconstruct past climate variability, but heat and mass transport processes can affect the isotopic composition. Here we present an experimental study on the effect on the snow isotopic composition by airflow through a snow pack in controlled laboratory conditions. The influence of isothermal and controlled temperature gradient conditions on the \u03b418O content in the snow and interstitial water vapor is elucidated. The observed disequilibrium between snow and vapor isotopes led to exchange of isotopes between snow and vapor under non-equilibrium processes, significantly changing the \u03b418O content of the snow. The type of metamorphism of the snow had a significant influence on this process.   Ebner, P. P., Steen-Larsen, H. C., Stenni, B., Schneebeli, M., and Steinfeld, A.: Experimental observation of transient \u03b418O interaction between snow and advective airflow under various temperature gradient conditions, The Cryosphere Discuss., https://doi.org/10.5194/tc-2017-16, accepted, 2017."
-    ],
-    "oai_identifier": [
-        "doi:10.16904/20",
-        "oai:envidat.ch:10.16904/20"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ADVECTION"
-        },
-        {
-            "name": "METAMORPHISM"
-        },
-        {
-            "name": "SNOW"
-        },
-        {
-            "name": "STABLE WATER ISOTOPE"
-        }
-    ],
-    "title": [
-        "Experiments on stable water isotopes,  snow metamorphism, and advection"
-    ],
-    "url": "https://www.envidat.ch/dataset/f87efc01-9914-4a75-998f-7dfc1fcef563/resource/e133ed87-de41-4595-87c9-b07f696c5cce/download/archive.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-iso19139/SET_1/json/4c482aac-c448-5533-be29-0a99cb495b2f.json b/oaitestdata/envidat-iso19139/SET_1/json/4c482aac-c448-5533-be29-0a99cb495b2f.json
deleted file mode 100644
index afb2b43d..00000000
--- a/oaitestdata/envidat-iso19139/SET_1/json/4c482aac-c448-5533-be29-0a99cb495b2f.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "vanessa.burg@wsl.ch"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "XLSX",
-        "DOCX"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=iso19139&identifier=doi:10.16904/18",
-    "PublicationTimestamp": "2017-12-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "WSL"
-    ],
-    "Rights": [
-        "License not specified"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "author": [
-        "Vanessa Burg"
-    ],
-    "fulltext": "oai:envidat.ch:10.16904/18;2018-07-07T00:13:06Z;doi:10.16904/18;Eng;MD_CharacterSetCode_utf8;Vanessa Burg;WSL;vanessa.burg@wsl.ch;2017-04-25T12:52:55;ISO 19115:2003/19139;1.0;EPSG:4326;Potentials of domestic biomass resources for the energy transition in Switzerland;2017-12-31;Switzerland has a reliable and cost efficient energy system. Due to phase  out of nuclear energy it is necessary to find new options to maintain this powerful energy system. The Swiss energy strategy 2050 aims to reduce CO2-emissions, increase efficiency and promote renewable energies. The Swiss Federal Institute for Forest, Snow and Landscape Research (WSL) examined relevant woody and non-woody biomass quantities (cubic meters, fresh-, dry weight) and their energy potentials (in Petajoules: primary energy and biomethane) with a similar methodological approach. The work was done within the frame of the Swiss Competence Centers for Energy Research (SCCER) especially in line with the SCCER Biomass for Swiss energy future (Biosweet). With a uniform and consistent approach for the current potentials ten biomass categories were estimated and aggregated for the whole of Switzerland. In this context solutions for the technical, social and political challenges are promoted. First, considering the different biomass resources characteristics and available data, appropriate methods at the finest scale possible were elaborated to estimate the annual quantities which could theoretically be collected (theoretical potential). Then, explicit and rational restrictions for sustainable bio-energy production were defined according to the current state of the art and subtracted from the theoretical potential to obtain the sustainable potential. The main restrictions are competing material utilizations, environmental factors and supply costs. Finally, the additional sustainable potential was estimated considering the current bioenergy production. Our main purpose was to provide potentials for developing conversion technologies as well as a detailed and comprehensive basis of the Swiss biomass potentials for energy use for economic and political decision makers. The complete report is available under https://www.dora.lib4ri.ch/wsl/islandora/object/wsl%3A13277/datastream/PDF/view;Vanessa Burg;WSL;vanessa.burg@wsl.ch;AVAILABILITY;BIOENERGY;BIOMASS RESOURCES;POTENTIAL ASSESSMENT;SUSTAINABILITY;License not specified;Eng;MD_CharacterSetCode_utf8;5.95587;10.49203;45.81802;47.80838;XLSX;DOCX;https://www.envidat.ch/dataset/swiss-biomass-potentials;HTTPS;DATASET METADATA;information;https://www.envidat.ch/dataset/21599a72-b714-4d11-a748-644d0016fae9/resource/67ecd9fa-b920-40b0-a5ed-6209360fa645/download/biomasspotentials_detailed_national-level.xlsx;HTTPS;BIOMASS POTENTIALS SWITZERLAND;download;https://www.envidat.ch/dataset/21599a72-b714-4d11-a748-644d0016fae9/resource/65b8fe6d-81ee-4b05-ab8c-c46ece1d3d25/download/biomasspotentials_cantonal-level.xlsx;HTTPS;BIOMASS POTENTIALS SWITZERLAND CANTONS;download;https://www.envidat.ch/dataset/21599a72-b714-4d11-a748-644d0016fae9/resource/d20fa98a-3fcc-4ada-ab31-c302d0c26f9f/download/biomasssupplycost.docx;HTTPS;BIOMASS SUPPLY COSTS;download",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "4c482aac-c448-5533-be29-0a99cb495b2f",
-    "notes": [
-        "Switzerland has a reliable and cost efficient energy system. Due to phase  out of nuclear energy it is necessary to find new options to maintain this powerful energy system. The Swiss energy strategy 2050 aims to reduce CO2-emissions, increase efficiency and promote renewable energies. The Swiss Federal Institute for Forest, Snow and Landscape Research (WSL) examined relevant woody and non-woody biomass quantities (cubic meters, fresh-, dry weight) and their energy potentials (in Petajoules: primary energy and biomethane) with a similar methodological approach. The work was done within the frame of the Swiss Competence Centers for Energy Research (SCCER) especially in line with the SCCER Biomass for Swiss energy future (Biosweet). With a uniform and consistent approach for the current potentials ten biomass categories were estimated and aggregated for the whole of Switzerland. In this context solutions for the technical, social and political challenges are promoted. First, considering the different biomass resources characteristics and available data, appropriate methods at the finest scale possible were elaborated to estimate the annual quantities which could theoretically be collected (theoretical potential). Then, explicit and rational restrictions for sustainable bio-energy production were defined according to the current state of the art and subtracted from the theoretical potential to obtain the sustainable potential. The main restrictions are competing material utilizations, environmental factors and supply costs. Finally, the additional sustainable potential was estimated considering the current bioenergy production. Our main purpose was to provide potentials for developing conversion technologies as well as a detailed and comprehensive basis of the Swiss biomass potentials for energy use for economic and political decision makers. The complete report is available under https://www.dora.lib4ri.ch/wsl/islandora/object/wsl%3A13277/datastream/PDF/view"
-    ],
-    "oai_identifier": [
-        "doi:10.16904/18",
-        "oai:envidat.ch:10.16904/18"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "AVAILABILITY"
-        },
-        {
-            "name": "BIOENERGY"
-        },
-        {
-            "name": "BIOMASS RESOURCES"
-        },
-        {
-            "name": "POTENTIAL ASSESSMENT"
-        },
-        {
-            "name": "SUSTAINABILITY"
-        }
-    ],
-    "title": [
-        "Potentials of domestic biomass resources for the energy transition in Switzerland"
-    ],
-    "url": "https://www.envidat.ch/dataset/21599a72-b714-4d11-a748-644d0016fae9/resource/d20fa98a-3fcc-4ada-ab31-c302d0c26f9f/download/biomasssupplycost.docx"
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-iso19139/SET_1/json/516b9369-ebb9-57df-add4-95e3b8f73f5f.json b/oaitestdata/envidat-iso19139/SET_1/json/516b9369-ebb9-57df-add4-95e3b8f73f5f.json
deleted file mode 100644
index 13663ee1..00000000
--- a/oaitestdata/envidat-iso19139/SET_1/json/516b9369-ebb9-57df-add4-95e3b8f73f5f.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "manfred.staehli@wsl.ch"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "XLSX",
-        "XLSM"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=iso19139&identifier=doi:10.16904/5",
-    "PublicationTimestamp": "2015-12-31T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "WSL"
-    ],
-    "Rights": [
-        "Other (Attribution)"
-    ],
-    "author": [
-        "Manfred St\u00e4hli"
-    ],
-    "fulltext": "oai:envidat.ch:10.16904/5;2018-07-07T00:12:51Z;doi:10.16904/5;Eng;MD_CharacterSetCode_utf8;Manfred St\u00e4hli;WSL;manfred.staehli@wsl.ch;2016-10-17T10:09:14;ISO 19115:2003/19139;1.0;EPSG:4326;TRAMM project - experimental hydrological and hydrogeological dataset of a landslide prone hillslope. Rufiberg, Switzerland;2015-12-31;Rufiberg is a pre-alpine meadow site in Switzerland where shallow landslides have been observed after past intense rain storms. In order to assess the triggering mechanisms of these landslides, a comprehensive investigation was conducted within the project TRAMM from Nov 2009 to Oct 2012. It included meteorological observations, soil moisture measurements, bedrock groundwater measurements. The Rufiberg is located at the NW side of the Gnipen to the north of the village Arth-Goldau in the Canton of Schwyz. In the summer months, the site is used for pasturing. Usually, from December to March a snow cover is present at the Rufiberg. The site is at an altitude between 1080 \u2013 1180 m asl, is ENE oriented, and has an average slope of 30 -35\u00b0. The Subalpine Molasse in the region is inclined with 30 - 35\u00b0 to SE. In the area of the field site, beds of conglomerate with several m of thickness alter with beds of sandstone and marlstone. A ca. 2 \u2013 5 m thick eluvium/colluvium layer composed of silty and sandy clay covers the bedrock. This site has been chosen because on one hand, during heavy rainfall events, e.g. autumn 2005, numerous landslides occur in the region of the Gnipen and the Rufiberg. On the other hand, the Rufiberg is very appropriate for experiments due its location away from infrastructures and due to its accessibility. The goal of the investigation was to understand the hydrology and hydrogeology of the slope with regard to shallow landslides.     More information: Br\u00f6nnimann, C., St\u00e4hli, M., Schneider, P., Seward, L. and Springman, S.M. 2013. Bedrock exfiltration as a triggering mechanism for shallow landslides. Water Resources Research, 49 (9): 5155\u20135167. DOI: 10.1002/wrcr.20386.;Manfred St\u00e4hli;WSL;manfred.staehli@wsl.ch;LANDSLIDES;SOIL MOISTURE WATER CONTENT;WATER TABLE;Other (Attribution);Eng;MD_CharacterSetCode_utf8;8.5544251 47.0889606;XLSM;XLSX;https://www.envidat.ch/dataset/10-16904-5;HTTPS;DATASET METADATA;information;https://www.envidat.ch/dataset/5333838f-5da6-4574-8d28-ce1794c19631/resource/fd31a45e-e5d0-476e-9a45-611f4d572d93/download/data-soil-water-content-tdr.xlsm;HTTPS;DATA SOIL WATER CONTENT TDR.XLSM;download;https://www.envidat.ch/dataset/5333838f-5da6-4574-8d28-ce1794c19631/resource/251578d0-3df2-44ed-9090-613a678bdbf8/download/data-lateral-subsurface-water-flow.xlsm;HTTPS;DATA LATERAL SUBSURFACE WATER FLOW.XLSM;download;https://www.envidat.ch/dataset/5333838f-5da6-4574-8d28-ce1794c19631/resource/720b044d-3ee5-4104-ba45-4b5b8ee7bf3e/download/data-groundwater-level-in-soil.xlsx;HTTPS;DATA GROUNDWATER LEVEL IN SOIL.XLSX;download;https://www.envidat.ch/dataset/5333838f-5da6-4574-8d28-ce1794c19631/resource/0e09242b-0222-4b90-b247-4fa2c34bb8ca/download/data-groundwater-level-in-bedrock.xlsx;HTTPS;DATA GROUNDWATER LEVEL IN BEDROCK.XLSX;download",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "516b9369-ebb9-57df-add4-95e3b8f73f5f",
-    "notes": [
-        "Rufiberg is a pre-alpine meadow site in Switzerland where shallow landslides have been observed after past intense rain storms. In order to assess the triggering mechanisms of these landslides, a comprehensive investigation was conducted within the project TRAMM from Nov 2009 to Oct 2012. It included meteorological observations, soil moisture measurements, bedrock groundwater measurements. The Rufiberg is located at the NW side of the Gnipen to the north of the village Arth-Goldau in the Canton of Schwyz. In the summer months, the site is used for pasturing. Usually, from December to March a snow cover is present at the Rufiberg. The site is at an altitude between 1080 \u2013 1180 m asl, is ENE oriented, and has an average slope of 30 -35\u00b0. The Subalpine Molasse in the region is inclined with 30 - 35\u00b0 to SE. In the area of the field site, beds of conglomerate with several m of thickness alter with beds of sandstone and marlstone. A ca. 2 \u2013 5 m thick eluvium/colluvium layer composed of silty and sandy clay covers the bedrock. This site has been chosen because on one hand, during heavy rainfall events, e.g. autumn 2005, numerous landslides occur in the region of the Gnipen and the Rufiberg. On the other hand, the Rufiberg is very appropriate for experiments due its location away from infrastructures and due to its accessibility. The goal of the investigation was to understand the hydrology and hydrogeology of the slope with regard to shallow landslides.     More information: Br\u00f6nnimann, C., St\u00e4hli, M., Schneider, P., Seward, L. and Springman, S.M. 2013. Bedrock exfiltration as a triggering mechanism for shallow landslides. Water Resources Research, 49 (9): 5155\u20135167. DOI: 10.1002/wrcr.20386."
-    ],
-    "oai_identifier": [
-        "doi:10.16904/5",
-        "oai:envidat.ch:10.16904/5"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "LANDSLIDES"
-        },
-        {
-            "name": "SOIL MOISTURE WATER CONTENT"
-        },
-        {
-            "name": "WATER TABLE"
-        }
-    ],
-    "title": [
-        "TRAMM project - experimental hydrological and hydrogeological dataset of a landslide prone hillslope. Rufiberg, Switzerland"
-    ],
-    "url": "https://www.envidat.ch/dataset/5333838f-5da6-4574-8d28-ce1794c19631/resource/0e09242b-0222-4b90-b247-4fa2c34bb8ca/download/data-groundwater-level-in-bedrock.xlsx"
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-iso19139/SET_1/json/53ad5ac1-ba81-57ca-86cb-e260a5ccbcc5.json b/oaitestdata/envidat-iso19139/SET_1/json/53ad5ac1-ba81-57ca-86cb-e260a5ccbcc5.json
deleted file mode 100644
index 4815b811..00000000
--- a/oaitestdata/envidat-iso19139/SET_1/json/53ad5ac1-ba81-57ca-86cb-e260a5ccbcc5.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "mott@slf.ch"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "PDF",
-        "ZIP"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=iso19139&identifier=doi:10.16904/envidat.25",
-    "PublicationTimestamp": "2017-12-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "E\u0300cole Polytechnique Fe\u0300de\u0300rale de Lausanne, Lausanne, Switzerland School of Architecture, Civil and Environmental Engineering, Laboratory of Cryospheric Sciences (CRYOS) and WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland,"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "author": [
-        "Rebecca Mott"
-    ],
-    "fulltext": "oai:envidat.ch:10.16904/envidat.25;2018-10-26T13:07:13Z;doi:10.16904/envidat.25;Eng;MD_CharacterSetCode_utf8;Rebecca Mott;E\u0300cole Polytechnique Fe\u0300de\u0300rale de Lausanne, Lausanne, Switzerland School of Architecture, Civil and Environmental Engineering, Laboratory of Cryospheric Sciences (CRYOS) and WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland,;mott@slf.ch;2017-07-19T13:16:40;ISO 19115:2003/19139;1.0;EPSG:4326;DISCHMEX - High-resolution daily snow ablation rates in an Alpine environment;2017-12-31;We recorded snow ablation maps with a terrestrial laser scanner (TLS, Riegl-VZ6000) at the Gletschboden area. The TLS position is located approximately 30 vertical meters above the Gletschboden area at a northerly exposed slope. In total 44 TLS measurement sets have been conducted in three consecutive years 2014-2016 (2014: 13 measurements; 2015: 17 measurements; 2016: 14 measurements). The TLS system has a single-point measurement frequency of 300 kHz and a beam divergence of 0.007\u00b0. This set-up allows a horizontal resolution of approximately 0.01 m in 100 m distance to the TLS position. One scan of the Gletschboden area lasts approximately 15 minutes. The travel time from the laser scanner towards the surface is recorded and afterwards converted into a point cloud of distances. 5 reflectors located at the Gletschboden area and in the closer surroundings were additionally scanned during each measurement to transform the point cloud from the scanner own coordinate system into Swiss coordinates. Additionally, orthophotos have been created by using pictures recorded from the TLS in order to provide snow mask maps. Snow and bare ground can be distinguished by the RGB color information of the orthophoto. Cells with blue band information greater than 175 were categorized as snow and all cells with values smaller or equal 175 were categorized as bare ground.;Rebecca Mott;E\u0300cole Polytechnique Fe\u0300de\u0300rale de Lausanne, Lausanne, Switzerland School of Architecture, Civil and Environmental Engineering, Laboratory of Cryospheric Sciences (CRYOS) and WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland,;mott@slf.ch;PATCHY SNOW COVERS;SNOW ABLATION RATES;TERRESTRIAL LASER SCANNING;Open Data Commons Open Database License (ODbL);Eng;MD_CharacterSetCode_utf8;9.92665 46.71291;ZIP;PDF;https://www.envidat.ch/dataset/10-16904-envidat-25;HTTPS;DATASET METADATA;information;https://www.envidat.ch/dataset/6b961ebc-1c86-45ec-8b6d-8efdd2e8babe/resource/299a98ef-94e5-4bdd-912f-24b347d20da6/download/2014dem.zip;HTTPS;DEM 2014;download;https://www.envidat.ch/dataset/6b961ebc-1c86-45ec-8b6d-8efdd2e8babe/resource/5a5b22eb-a0ae-4552-a7b3-34631c3ae998/download/2014snowmask.zip;HTTPS;SNOWMASK 2014;download;https://www.envidat.ch/dataset/6b961ebc-1c86-45ec-8b6d-8efdd2e8babe/resource/9d19c582-76ca-45df-b032-46d8346f45be/download/2015dem.zip;HTTPS;DEM 2015;download;https://www.envidat.ch/dataset/6b961ebc-1c86-45ec-8b6d-8efdd2e8babe/resource/89c08602-142c-4fdb-9c76-3993a9d0dbfc/download/2015snowmask.zip;HTTPS;SNOWMASK 2015;download;https://www.envidat.ch/dataset/6b961ebc-1c86-45ec-8b6d-8efdd2e8babe/resource/787f969b-71db-4ec9-967b-7e0198dd9d71/download/2016dem.zip;HTTPS;DEM 2016;download;https://www.envidat.ch/dataset/6b961ebc-1c86-45ec-8b6d-8efdd2e8babe/resource/2b54670d-74e9-4ea5-8fcd-4ea98ad26ed6/download/2016snowmask.zip;HTTPS;SNOWMASK 2016;download;https://www.envidat.ch/dataset/6b961ebc-1c86-45ec-8b6d-8efdd2e8babe/resource/645e45ec-fc90-432c-a29e-d1d79781d5b2/download/dischma_neu.pdf;HTTPS;GLETSCHBODEN TEST SITE;download",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "53ad5ac1-ba81-57ca-86cb-e260a5ccbcc5",
-    "notes": [
-        "We recorded snow ablation maps with a terrestrial laser scanner (TLS, Riegl-VZ6000) at the Gletschboden area. The TLS position is located approximately 30 vertical meters above the Gletschboden area at a northerly exposed slope. In total 44 TLS measurement sets have been conducted in three consecutive years 2014-2016 (2014: 13 measurements; 2015: 17 measurements; 2016: 14 measurements). The TLS system has a single-point measurement frequency of 300 kHz and a beam divergence of 0.007\u00b0. This set-up allows a horizontal resolution of approximately 0.01 m in 100 m distance to the TLS position. One scan of the Gletschboden area lasts approximately 15 minutes. The travel time from the laser scanner towards the surface is recorded and afterwards converted into a point cloud of distances. 5 reflectors located at the Gletschboden area and in the closer surroundings were additionally scanned during each measurement to transform the point cloud from the scanner own coordinate system into Swiss coordinates. Additionally, orthophotos have been created by using pictures recorded from the TLS in order to provide snow mask maps. Snow and bare ground can be distinguished by the RGB color information of the orthophoto. Cells with blue band information greater than 175 were categorized as snow and all cells with values smaller or equal 175 were categorized as bare ground."
-    ],
-    "oai_identifier": [
-        "doi:10.16904/envidat.25",
-        "oai:envidat.ch:10.16904/envidat.25"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "PATCHY SNOW COVERS"
-        },
-        {
-            "name": "SNOW ABLATION RATES"
-        },
-        {
-            "name": "TERRESTRIAL LASER SCANNING"
-        }
-    ],
-    "title": [
-        "DISCHMEX - High-resolution daily snow ablation rates in an Alpine environment"
-    ],
-    "url": "https://www.envidat.ch/dataset/6b961ebc-1c86-45ec-8b6d-8efdd2e8babe/resource/645e45ec-fc90-432c-a29e-d1d79781d5b2/download/dischma_neu.pdf"
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-iso19139/SET_1/json/6c2fc8fd-5c04-5f95-bcd8-99b39ae39d20.json b/oaitestdata/envidat-iso19139/SET_1/json/6c2fc8fd-5c04-5f95-bcd8-99b39ae39d20.json
deleted file mode 100644
index 891feef3..00000000
--- a/oaitestdata/envidat-iso19139/SET_1/json/6c2fc8fd-5c04-5f95-bcd8-99b39ae39d20.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "matthias.heck@slf.ch"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "ZIP"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=iso19139&identifier=doi:10.16904/envidat.29",
-    "PublicationTimestamp": "2018-12-31T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "SLF"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "author": [
-        "Matthias Heck"
-    ],
-    "fulltext": "oai:envidat.ch:10.16904/envidat.29;2018-01-19T12:40:45Z;doi:10.16904/envidat.29;Eng;MD_CharacterSetCode_utf8;Matthias Heck;SLF;matthias.heck@slf.ch;2018-01-16T16:12:15;ISO 19115:2003/19139;1.0;EPSG:4326;Automatic detection of avalanches;2018-12-31;This dataset contains the results obtained by an automatic classification using hidden Markov models of a continuous seismic dataset. To avoid long computational times, we reduced the seismic data using pre-processing step. The start and end times of the windows used for the classification are also included in this dataset. Furthermore, an avalanche reference data set is included and the python scripts used to perform the processing steps and the classification.;Matthias Heck;SLF;matthias.heck@slf.ch;AVALANCHE ACTIVITY;HIDDEN MARKOV MODEL;MONITORING;SEISMIC;Open Data Commons Open Database License (ODbL);Eng;MD_CharacterSetCode_utf8;9.78759 46.80616;ZIP;https://www.envidat.ch/dataset/10-16904-envidat-29;HTTPS;DATASET METADATA;information;https://www.envidat.ch/dataset/6b0788a9-33e8-4ea6-b958-6327167ad423/resource/684cb802-18de-46ee-822a-f63f2f434197/download/results_and_scripts.zip;HTTPS;RESULTS AND SCRIPTS;download",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "6c2fc8fd-5c04-5f95-bcd8-99b39ae39d20",
-    "notes": [
-        "This dataset contains the results obtained by an automatic classification using hidden Markov models of a continuous seismic dataset. To avoid long computational times, we reduced the seismic data using pre-processing step. The start and end times of the windows used for the classification are also included in this dataset. Furthermore, an avalanche reference data set is included and the python scripts used to perform the processing steps and the classification."
-    ],
-    "oai_identifier": [
-        "doi:10.16904/envidat.29",
-        "oai:envidat.ch:10.16904/envidat.29"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "AVALANCHE ACTIVITY"
-        },
-        {
-            "name": "HIDDEN MARKOV MODEL"
-        },
-        {
-            "name": "MONITORING"
-        },
-        {
-            "name": "SEISMIC"
-        }
-    ],
-    "title": [
-        "Automatic detection of avalanches"
-    ],
-    "url": "https://www.envidat.ch/dataset/6b0788a9-33e8-4ea6-b958-6327167ad423/resource/684cb802-18de-46ee-822a-f63f2f434197/download/results_and_scripts.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-iso19139/SET_1/json/7878dd08-7d7b-5ebe-98b8-e248be9e2012.json b/oaitestdata/envidat-iso19139/SET_1/json/7878dd08-7d7b-5ebe-98b8-e248be9e2012.json
deleted file mode 100644
index d8240f34..00000000
--- a/oaitestdata/envidat-iso19139/SET_1/json/7878dd08-7d7b-5ebe-98b8-e248be9e2012.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "sarah.springman@igt.baug.ethz.ch"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "ZIP"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=iso19139&identifier=doi:10.16904/4",
-    "PublicationTimestamp": "2015-12-31T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "ETHZ"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "author": [
-        "Sarah M. Springman"
-    ],
-    "fulltext": "oai:envidat.ch:10.16904/4;2018-07-07T00:12:52Z;doi:10.16904/4;Eng;MD_CharacterSetCode_utf8;Sarah M. Springman;ETHZ;sarah.springman@igt.baug.ethz.ch;2016-10-17T09:30:11;ISO 19115:2003/19139;1.0;EPSG:4326;TRAMM project Ruedlingen experimental landslide dataset, Switzerland;2015-12-31;A landslide testsite dataset related to pore water pressure perturbations on the stability of unsaturated silty sand slopes leading to the initiation and propagation of the shear deformations and eventual rapid mass movements. This project was initiated and led by the Institute of Geotechnical Engineering (IGT) of the Swiss Federal Institute of Technology (ETH Zurich) and was incorporated in a Swiss national (TRAMM) and a European Union (SafeLand) multidisciplinary research project. Field site: The experimental slope is 7.5 m wide by 35 m long, located in the Swiss lowlands on an east facing slope over-looking the river Rhine, at an altitude of ~ 350 masl. Originally there were forestry covertures of circa 80%, heights of 5-20 m. Shrubs up to 1-5 m high and a free herb layer covered ~ 50% of the surface. The average gradient was determined to be from 38\u00b0 to 43\u00b0 with a slightly concave surface. The underlying rock consists mainly of Molasse, which is formed by alternate layers of sea deposits under the Tethys Sea (Seawater Molasse) and land deposits (Freshwater Molasse). Several augured samples, as well as an outcrop of the bedrock about 20 m above the selected field, revealed horizontal layering of fine grained sand- and marlstone at the test site. The sandstone was later proven to be highly permeable and fissured. Grain-size distributions were determined and the soil was classified as medium-low plasticity silty sand. Site instrumentation:Measurements of soil suction, groundwater level, soil volumetric water content, rain intensity and soil temperature were taken and combined with geophysical monitoring using Electrical Resistance Tomography (ERT) and investigations into subsurface flow by means of tracer experiments. Deformations were monitored during the experiment, both on the surface via photogrammetrical methods and within the soil mass, using a flexible probe equipped with strain gauges at different points and two axis inclinometers on the top and acoustic sensors. Instruments were installed mainly in three clusters at depths of 15, 30, 60, 90, 120, and 150 cm below the ground surface over the slope, including jet-fill tensiometers, TDRs, Decagon TDRs, piezometers, soil temperature sensors, deformation probes, earth pressure cells, acoustic sensors and rain gauges. A ring-net barrier (provided by Geobrugg AG) was set up at the foot of the slope to protect the road. Experiments: A sprinkling experiment was carried out in September 2008 to investigate the hydrological and mechanical response of the slope (Experiment 1), followed by a second one to trigger a landslide in March 2009 (Experiment 2).     __Publications__    1. Lehmann, P., F. Gambazzi, B. Suski, L. Baron, A. Askarinejad, S. M. Springman, K. Holliger, and D. Or (2013), Evolution of soil wetting patterns preceding a hydrologically induced landslide inferred from electrical resistivity survey and point measurements of volumetric water content and pore water pressure, Water Resour. Res., 49, 7992\u20138004, doi:[10.1002/2013WR014560](http://dx.doi.org/10.1002/2013WR014560).    2. Springman, S. M., Kienzler, P., Casini, F., & Askarinejad, A. (2009). Landslide triggering experiment in a steep forested slope in Switzerland. In 17th International Conference of Soil Mechanics and Geotechnical Engineering, Alexandria, Egypt (pp. 1698-1701). doi: [10.3233/978-1-60750-031-5-1698](http://dx.doi.org/10.3233/978-1-60750-031-5-1698);Sarah M. Springman;ETHZ;sarah.springman@igt.baug.ethz.ch;LANDSLIDES;PORE WATER;Open Data Commons Open Database License (ODbL);Eng;MD_CharacterSetCode_utf8;8.56659 47.56685;ZIP;https://www.envidat.ch/dataset/10-16904-4;HTTPS;DATASET METADATA;information;https://www.envidat.ch/dataset/65ecae0a-e309-40f2-9e44-f0ad45f3339d/resource/c11c782a-45fa-46d8-981c-6ecdcdc938fa/download/trammruedlingendata.zip;HTTPS;TRAMM RUEDLINGEN DATA;download",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "7878dd08-7d7b-5ebe-98b8-e248be9e2012",
-    "notes": [
-        "A landslide testsite dataset related to pore water pressure perturbations on the stability of unsaturated silty sand slopes leading to the initiation and propagation of the shear deformations and eventual rapid mass movements. This project was initiated and led by the Institute of Geotechnical Engineering (IGT) of the Swiss Federal Institute of Technology (ETH Zurich) and was incorporated in a Swiss national (TRAMM) and a European Union (SafeLand) multidisciplinary research project. Field site: The experimental slope is 7.5 m wide by 35 m long, located in the Swiss lowlands on an east facing slope over-looking the river Rhine, at an altitude of ~ 350 masl. Originally there were forestry covertures of circa 80%, heights of 5-20 m. Shrubs up to 1-5 m high and a free herb layer covered ~ 50% of the surface. The average gradient was determined to be from 38\u00b0 to 43\u00b0 with a slightly concave surface. The underlying rock consists mainly of Molasse, which is formed by alternate layers of sea deposits under the Tethys Sea (Seawater Molasse) and land deposits (Freshwater Molasse). Several augured samples, as well as an outcrop of the bedrock about 20 m above the selected field, revealed horizontal layering of fine grained sand- and marlstone at the test site. The sandstone was later proven to be highly permeable and fissured. Grain-size distributions were determined and the soil was classified as medium-low plasticity silty sand. Site instrumentation:Measurements of soil suction, groundwater level, soil volumetric water content, rain intensity and soil temperature were taken and combined with geophysical monitoring using Electrical Resistance Tomography (ERT) and investigations into subsurface flow by means of tracer experiments. Deformations were monitored during the experiment, both on the surface via photogrammetrical methods and within the soil mass, using a flexible probe equipped with strain gauges at different points and two axis inclinometers on the top and acoustic sensors. Instruments were installed mainly in three clusters at depths of 15, 30, 60, 90, 120, and 150 cm below the ground surface over the slope, including jet-fill tensiometers, TDRs, Decagon TDRs, piezometers, soil temperature sensors, deformation probes, earth pressure cells, acoustic sensors and rain gauges. A ring-net barrier (provided by Geobrugg AG) was set up at the foot of the slope to protect the road. Experiments: A sprinkling experiment was carried out in September 2008 to investigate the hydrological and mechanical response of the slope (Experiment 1), followed by a second one to trigger a landslide in March 2009 (Experiment 2).     __Publications__    1. Lehmann, P., F. Gambazzi, B. Suski, L. Baron, A. Askarinejad, S. M. Springman, K. Holliger, and D. Or (2013), Evolution of soil wetting patterns preceding a hydrologically induced landslide inferred from electrical resistivity survey and point measurements of volumetric water content and pore water pressure, Water Resour. Res., 49, 7992\u20138004, doi:[10.1002/2013WR014560](http://dx.doi.org/10.1002/2013WR014560).    2. Springman, S. M., Kienzler, P., Casini, F., & Askarinejad, A. (2009). Landslide triggering experiment in a steep forested slope in Switzerland. In 17th International Conference of Soil Mechanics and Geotechnical Engineering, Alexandria, Egypt (pp. 1698-1701). doi: [10.3233/978-1-60750-031-5-1698](http://dx.doi.org/10.3233/978-1-60750-031-5-1698)"
-    ],
-    "oai_identifier": [
-        "doi:10.16904/4",
-        "oai:envidat.ch:10.16904/4"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "LANDSLIDES"
-        },
-        {
-            "name": "PORE WATER"
-        }
-    ],
-    "title": [
-        "TRAMM project Ruedlingen experimental landslide dataset, Switzerland"
-    ],
-    "url": "https://www.envidat.ch/dataset/65ecae0a-e309-40f2-9e44-f0ad45f3339d/resource/c11c782a-45fa-46d8-981c-6ecdcdc938fa/download/trammruedlingendata.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-iso19139/SET_1/json/7d1c728e-c7b3-5149-b290-0175a190a90c.json b/oaitestdata/envidat-iso19139/SET_1/json/7d1c728e-c7b3-5149-b290-0175a190a90c.json
deleted file mode 100644
index 88e99fb1..00000000
--- a/oaitestdata/envidat-iso19139/SET_1/json/7d1c728e-c7b3-5149-b290-0175a190a90c.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "nander.wever@slf.ch"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "DAT",
-        "TXT"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=iso19139&identifier=doi:10.16904/2",
-    "PublicationTimestamp": "2015-12-31T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "SLF"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "author": [
-        "Nander Wever"
-    ],
-    "fulltext": "oai:envidat.ch:10.16904/2;2018-07-07T00:12:53Z;doi:10.16904/2;Eng;MD_CharacterSetCode_utf8;Nander Wever;SLF;nander.wever@slf.ch;2016-10-16T21:39:20;ISO 19115:2003/19139;1.0;EPSG:4326;Manual bi-weekly snow profiles from Weissfluhjoch, Davos, Switzerland;2015-12-31;Dataset of manual bi-weekly snow profiles from Weissfluhjoch, Davos, Switzerland. Typical snow profile measurements and observations are included (temperature, density, grain size, grain type, hardness, wetness), following the guidelines of the The International Classification for Seasonal Snow on the Ground (ICSSG) [Fierz, C., Armstrong, R.L., Durand, Y., Etchevers, P., Greene, E., McClung, D.M., Nishimura, K., Satyawali, P.K. and Sokratov, S.A. 2009. The International Classification for Seasonal Snow on the Ground. IHP-VII Technical Documents in Hydrology N\u00b083, IACS Contribution N\u00b01, UNESCO-IHP, Paris].;Nander Wever;SLF;nander.wever@slf.ch;SNOW DENSITY;SNOW ICE TEMPERATURE;SNOW STRATIGRAPHY;SNOW WATER EQUIVALENT;Open Data Commons Open Database License (ODbL);Eng;MD_CharacterSetCode_utf8;9.809568 46.829598;DAT;TXT;https://www.envidat.ch/dataset/10-16904-2;HTTPS;DATASET METADATA;information;https://www.envidat.ch/dataset/0b294122-015c-46bf-b5c5-cc6d0a6f67c1/resource/f64d8a9f-36ea-40f6-9874-bc9071050d0a/download/wfjsnowprofiles19992014.zip;HTTPS;WFJ SNOW PROFILES 1999-2014;download;ftp://ftp.wsl.ch/pub/smm/readme.txt;FTP;README;download",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "7d1c728e-c7b3-5149-b290-0175a190a90c",
-    "notes": [
-        "Dataset of manual bi-weekly snow profiles from Weissfluhjoch, Davos, Switzerland. Typical snow profile measurements and observations are included (temperature, density, grain size, grain type, hardness, wetness), following the guidelines of the The International Classification for Seasonal Snow on the Ground (ICSSG) [Fierz, C., Armstrong, R.L., Durand, Y., Etchevers, P., Greene, E., McClung, D.M., Nishimura, K., Satyawali, P.K. and Sokratov, S.A. 2009. The International Classification for Seasonal Snow on the Ground. IHP-VII Technical Documents in Hydrology N\u00b083, IACS Contribution N\u00b01, UNESCO-IHP, Paris]."
-    ],
-    "oai_identifier": [
-        "doi:10.16904/2",
-        "oai:envidat.ch:10.16904/2"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "SNOW DENSITY"
-        },
-        {
-            "name": "SNOW ICE TEMPERATURE"
-        },
-        {
-            "name": "SNOW STRATIGRAPHY"
-        },
-        {
-            "name": "SNOW WATER EQUIVALENT"
-        }
-    ],
-    "title": [
-        "Manual bi-weekly snow profiles from Weissfluhjoch, Davos, Switzerland"
-    ],
-    "url": "https://www.envidat.ch/dataset/0b294122-015c-46bf-b5c5-cc6d0a6f67c1/resource/f64d8a9f-36ea-40f6-9874-bc9071050d0a/download/wfjsnowprofiles19992014.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-iso19139/SET_1/json/7fa3f05f-9abf-5ef2-80ad-d01092c05c30.json b/oaitestdata/envidat-iso19139/SET_1/json/7fa3f05f-9abf-5ef2-80ad-d01092c05c30.json
deleted file mode 100644
index a6ca5d4b..00000000
--- a/oaitestdata/envidat-iso19139/SET_1/json/7fa3f05f-9abf-5ef2-80ad-d01092c05c30.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "tristan.brauchli@alumni.epfl.ch"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "ZIP"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=iso19139&identifier=doi:10.16904/envidat.24",
-    "PublicationTimestamp": "2017-12-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "EPFL"
-    ],
-    "Rights": [
-        "License not specified"
-    ],
-    "author": [
-        "Tristan Brauchli"
-    ],
-    "fulltext": "oai:envidat.ch:10.16904/envidat.24;2017-12-15T13:04:56Z;doi:10.16904/envidat.24;Eng;MD_CharacterSetCode_utf8;Tristan Brauchli;EPFL;tristan.brauchli@alumni.epfl.ch;2017-10-26T14:33:36;ISO 19115:2003/19139;1.0;EPSG:4326;Influence of slope-scale snowmelt on catchment response simulated with the Alpine3D model;2017-12-31;# Abstract  Snow and hydrological modeling in alpine environments remains a challenge because of the complexity of the processes complexity affecting the mass and energy balance. This study examines the influence of snowmelt on the hydrological response of a high-alpine catchment of 43.2 km2 in the Swiss Alps during the water year 2014-2015. Based on recent advances in Alpine3D, we examine how modeled snow distributions, and modeled liquid water transport within the snowpack influence runoff dynamics. By combining these results with multi-scale field data (snow lysimeter data, distributed snow depths and streamflow), we demonstrate the added value of a more realistic representation of snow distribution at the onset of melt season. At the site scale, snowpack runoff is well simulated when the snowpack mass balance errors are corrected (R2 = 0.95 vs. R2 = 0.61). At the sub-basin scale, a more heterogeneous snowpack leads to a more rapid runoff pulse originated in the shallower areas while an extended melting period (by more than a month) is caused by slower snowmelt from deeper areas. This result is a marked improvement over results obtained using a less heterogeneous snow distribution (i.e., traditional precipitation interpolation method). Catchment hydrological response is also improved by the more realistic representation of snowpack heterogeneity (Nash coefficient of 0.85 vs. 0.74), even though the calibration process smoothens out the differences.   The added value of a more complex liquid water transport scheme is obvious at the site scale but decreases at the sub-basin and basin scales. Our results highlight not only the importance but also the difficulty of getting a realistic snowpack distribution even in a well-instrumented area and present a model validation from multi-scale experimental datasets.;Tristan Brauchli;EPFL;tristan.brauchli@alumni.epfl.ch;COMPLEX TOPOGRAPHY;HYDROLOGICAL RESPONSE;SNOW MODELING;SNOWMELT;SPATIAL VARIABILITY;License not specified;Eng;MD_CharacterSetCode_utf8;9.81971740723 46.6722920457;9.98931884766 46.6722920457;9.98931884766 46.8012345356;9.81971740723 46.8012345356;9.81971740723 46.6722920457;ZIP;https://www.envidat.ch/dataset/10-16904-envidat-24;HTTPS;DATASET METADATA;information;https://www.envidat.ch/dataset/f1d3d6da-2e59-4ee3-92fe-fc4add117f61/resource/b81690c4-86bf-4c6a-81d2-fd206e4afeb1/download/paperwrrbrauchli.zip;HTTPS;ALPINE3D OUTPUT DISCHMA;download",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "7fa3f05f-9abf-5ef2-80ad-d01092c05c30",
-    "notes": [
-        "# Abstract  Snow and hydrological modeling in alpine environments remains a challenge because of the complexity of the processes complexity affecting the mass and energy balance. This study examines the influence of snowmelt on the hydrological response of a high-alpine catchment of 43.2 km2 in the Swiss Alps during the water year 2014-2015. Based on recent advances in Alpine3D, we examine how modeled snow distributions, and modeled liquid water transport within the snowpack influence runoff dynamics. By combining these results with multi-scale field data (snow lysimeter data, distributed snow depths and streamflow), we demonstrate the added value of a more realistic representation of snow distribution at the onset of melt season. At the site scale, snowpack runoff is well simulated when the snowpack mass balance errors are corrected (R2 = 0.95 vs. R2 = 0.61). At the sub-basin scale, a more heterogeneous snowpack leads to a more rapid runoff pulse originated in the shallower areas while an extended melting period (by more than a month) is caused by slower snowmelt from deeper areas. This result is a marked improvement over results obtained using a less heterogeneous snow distribution (i.e., traditional precipitation interpolation method). Catchment hydrological response is also improved by the more realistic representation of snowpack heterogeneity (Nash coefficient of 0.85 vs. 0.74), even though the calibration process smoothens out the differences.   The added value of a more complex liquid water transport scheme is obvious at the site scale but decreases at the sub-basin and basin scales. Our results highlight not only the importance but also the difficulty of getting a realistic snowpack distribution even in a well-instrumented area and present a model validation from multi-scale experimental datasets."
-    ],
-    "oai_identifier": [
-        "doi:10.16904/envidat.24",
-        "oai:envidat.ch:10.16904/envidat.24"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "COMPLEX TOPOGRAPHY"
-        },
-        {
-            "name": "HYDROLOGICAL RESPONSE"
-        },
-        {
-            "name": "SNOW MODELING"
-        },
-        {
-            "name": "SNOWMELT"
-        },
-        {
-            "name": "SPATIAL VARIABILITY"
-        }
-    ],
-    "title": [
-        "Influence of slope-scale snowmelt on catchment response simulated with the Alpine3D model"
-    ],
-    "url": "https://www.envidat.ch/dataset/f1d3d6da-2e59-4ee3-92fe-fc4add117f61/resource/b81690c4-86bf-4c6a-81d2-fd206e4afeb1/download/paperwrrbrauchli.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-iso19139/SET_1/json/80cec969-c17d-5023-b99b-a16cdd3ce04d.json b/oaitestdata/envidat-iso19139/SET_1/json/80cec969-c17d-5023-b99b-a16cdd3ce04d.json
deleted file mode 100644
index d9bb8dc7..00000000
--- a/oaitestdata/envidat-iso19139/SET_1/json/80cec969-c17d-5023-b99b-a16cdd3ce04d.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "lehning@slf.ch"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "SNO",
-        "SMET",
-        "TXT"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=iso19139&identifier=doi:10.16904/envidat.28",
-    "PublicationTimestamp": "2018-12-31T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "SLF"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "author": [
-        "Michael Lehning"
-    ],
-    "fulltext": "oai:envidat.ch:10.16904/envidat.28;2018-02-22T21:21:57Z;doi:10.16904/envidat.28;Eng;MD_CharacterSetCode_utf8;Michael Lehning;SLF;lehning@slf.ch;2018-01-12T13:30:17;ISO 19115:2003/19139;1.0;EPSG:4326;Snowfarming data set Davos and Martell 2015;2018-12-31;Two data sets obtained for snow farming projects (Fluela, Davos, CH and Martell, IT) in 2015.     The data set contains for each site:    * 10 cm GIS raster of snow depth calculated from terrestrial laserscanning surveys (TLS) in the end of winter season (April/May)    * 10 cm GIS raster of snow depth calculated from TLS in the end of summer season (October)    Input files for SNOWPACK model:    * .sno: snow profile at the end of winter    * .smet: meteorological data measured by weather stations in the area    For more details see  Gr\u00fcnewald, T., Lehning, M., and Wolfsperger, F.: Snow farming: Conserving snow over the summer season, The Cryosphere Discuss., https://doi.org/10.5194/tc-2017-93, in review, 2017.;Michael Lehning;SLF;lehning@slf.ch;SNOW;SNOW CONSERVATION;SNOW FARMING;SNOWPACK;TERRESTRIAL LASER SCANNING;WINTER TOURISM;Open Data Commons Open Database License (ODbL);Eng;MD_CharacterSetCode_utf8;9.868 46.808;10.727 46.517;SNO;SMET;TXT;https://www.envidat.ch/dataset/10-16904-envidat-28;HTTPS;DATASET METADATA;information;https://www.envidat.ch/dataset/640b09be-3b86-492e-aba2-449329969989/resource/f31e7520-2624-4628-a7a9-bb0bcbeea876/download/fluela_1schicht_40cm_lwc3.sno;HTTPS;FLUELA .SNO;download;https://www.envidat.ch/dataset/640b09be-3b86-492e-aba2-449329969989/resource/bd5861f8-f17c-4133-9ff2-c8526e67804e/download/martell_1schicht_lwc3.sno;HTTPS;MARTELL .SNO;download;https://www.envidat.ch/dataset/640b09be-3b86-492e-aba2-449329969989/resource/5c4a89bc-c16a-4c37-92e6-183a50438fae/download/meteo_martell.smet;HTTPS;MARTELL .SMET;download;https://www.envidat.ch/dataset/640b09be-3b86-492e-aba2-449329969989/resource/7e360bad-ec83-4675-802e-05dc7a701a27/download/haufen_vwcor_shade.smet;HTTPS;FLUELA .SMET;download;https://www.envidat.ch/dataset/640b09be-3b86-492e-aba2-449329969989/resource/a0aef820-34e4-490a-9271-a12646f37b67/download/20150429_fluela_hs.txt;HTTPS;HS FLUELA SPRING 2015;download;https://www.envidat.ch/dataset/640b09be-3b86-492e-aba2-449329969989/resource/47f70f9b-63df-44aa-836c-02a46bbf4f6b/download/20151008_fluela_hs.txt;HTTPS;HS FLUELA AUTUMN 2015;download;https://www.envidat.ch/dataset/640b09be-3b86-492e-aba2-449329969989/resource/0d16510c-f1d4-4de2-86f7-b5ef2fb0bd0f/download/20151028_martell_hs.txt;HTTPS;HS MARTELL AUTUMN 2015;download;https://www.envidat.ch/dataset/640b09be-3b86-492e-aba2-449329969989/resource/558c33f7-ce57-45b8-a339-f617be015e96/download/20150519_martell_hs.txt;HTTPS;HS MARTELL SPRING 2015;download",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "80cec969-c17d-5023-b99b-a16cdd3ce04d",
-    "notes": [
-        "Two data sets obtained for snow farming projects (Fluela, Davos, CH and Martell, IT) in 2015.     The data set contains for each site:    * 10 cm GIS raster of snow depth calculated from terrestrial laserscanning surveys (TLS) in the end of winter season (April/May)    * 10 cm GIS raster of snow depth calculated from TLS in the end of summer season (October)    Input files for SNOWPACK model:    * .sno: snow profile at the end of winter    * .smet: meteorological data measured by weather stations in the area    For more details see  Gr\u00fcnewald, T., Lehning, M., and Wolfsperger, F.: Snow farming: Conserving snow over the summer season, The Cryosphere Discuss., https://doi.org/10.5194/tc-2017-93, in review, 2017."
-    ],
-    "oai_identifier": [
-        "doi:10.16904/envidat.28",
-        "oai:envidat.ch:10.16904/envidat.28"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "SNOW"
-        },
-        {
-            "name": "SNOW CONSERVATION"
-        },
-        {
-            "name": "SNOW FARMING"
-        },
-        {
-            "name": "SNOWPACK"
-        },
-        {
-            "name": "TERRESTRIAL LASER SCANNING"
-        },
-        {
-            "name": "WINTER TOURISM"
-        }
-    ],
-    "title": [
-        "Snowfarming data set Davos and Martell 2015"
-    ],
-    "url": "https://www.envidat.ch/dataset/640b09be-3b86-492e-aba2-449329969989/resource/558c33f7-ce57-45b8-a339-f617be015e96/download/20150519_martell_hs.txt"
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-iso19139/SET_1/json/8ab9a83b-4a08-52b2-bf87-1b3cd146a39b.json b/oaitestdata/envidat-iso19139/SET_1/json/8ab9a83b-4a08-52b2-bf87-1b3cd146a39b.json
deleted file mode 100644
index fccb5ad4..00000000
--- a/oaitestdata/envidat-iso19139/SET_1/json/8ab9a83b-4a08-52b2-bf87-1b3cd146a39b.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "lisa.huelsmann@ur.de"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "CSV"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=iso19139&identifier=doi:10.16904/envidat.27",
-    "PublicationTimestamp": "2017-12-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "University of Regensburg"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "author": [
-        "Lisa H\u00fclsmann"
-    ],
-    "fulltext": "oai:envidat.ch:10.16904/envidat.27;2018-07-07T00:12:59Z;doi:10.16904/envidat.27;Eng;MD_CharacterSetCode_utf8;Lisa H\u00fclsmann;University of Regensburg;lisa.huelsmann@ur.de;2017-11-15T16:15:30;ISO 19115:2003/19139;1.0;EPSG:4326;Calibration data for empirical mortality models of 18 European tree species;2017-12-31;The dataset comprises > 90 000 records from inventories in 54 strict forest reserves in [Switzerland](https://www.wsl.ch/de/wald/biodiversitaet-naturschutz-urwald/naturwaldreservate.html) and [Lower Saxony / Germany](http://naturwaelder.de/) along a considerable environmental gradient. It was used to develop parsimonious, species-specific mortality models for 18 European tree species based on tree size and growth as well as additional covariates on stand structure and climate.     ## Inventory data  Measurements had been conducted repeatedly on up to 14 permanent plots per reserve for up to 60 years with re-measurement intervals of 4 - 27 years. The permanent plots vary in size between 0.03 and 3.47 ha. The inventories provide diameter measurements at breast height (DBH) and information on the species and status (alive or dead) of trees with DBH \u2265 4 cm for Switzerland and \u2265 7 cm for Germany.     ## Data selection  We excluded three permanent plots where at least 80 % of the trees died during an interval of 10 years, and mortality could be clearly assigned to a disturbance agent. Mortality in the remaining stands was rather low, with a mean annual mortality rate of 1.5 % and strong variation between plots from 0 to 6.5 % (assessed for trees of all species with DBH \u2265 7 cm).  We only used data from permanent plots with at least 20 trees per species to obtain reliable plot-level mortality rates even for species with low mortality rates (about 5 % during 10 years), and selected tree species occurring on at least 10 plots to cover sufficient ecological gradients. This led to a dataset of 197 permanent plots and 18 tree or shrub species: _Abies alba_ Mill., _Acer campestre_ L., _Acer pseudoplatanus_ L., _Alnus incana_ Moench., _Betula pendula_ Roth, _Carpinus betulus_ L., _Cornus mas_ L., _Corylus avellana_ L., _Fagus sylvatica_ L., _Fraxinus excelsior_ L., _Picea abies_ (L.) Karst, _Pinus mugo_ Turra, _Pinus sylvestris_ L., _Quercus pubescens_ Willd., _Quercus_ spp. (_Q. petraea_ Liebl. and _Q. robur_ L.; not properly differentiated in the Swiss inventories), _Sorbus aria_ Crantz, _Tilia cordata_ Mill. and _Ulmus glabra_ Huds..     ## Predictors of tree mortality  We considered tree size and growth as key indicators for mortality risk. Radial stem growth between the first and second inventory and DBH at the second inventory were used to predict tree status (alive or dead) at the third inventory. To this end, the annual relative basal area increment (relBAI) was calculated as the compound annual growth rate of the trees basal area. Additional covariates on stand structure and climate comprise mean annual precipitation sum (P), mean annual air temperature (mT), the mean and the interquartile range of DBH (mDBH, iqrDBH), basal area (BA) and the number of trees (N) per hectare.     ## Further information  For further information, refer to H\u00fclsmann _et al_. (in press) How to kill a tree \u2013 Empirical mortality models for eighteen species and their performance in a dynamic forest model. _Ecological Applications_.;Lisa H\u00fclsmann;University of Regensburg;lisa.huelsmann@ur.de;EMPIRICAL MORTALITY MODELS;FOREST RESERVES;INVENTORY DATA;TREE GROWTH;TREE MORTALITY;Open Data Commons Open Database License (ODbL);Eng;MD_CharacterSetCode_utf8;[6.6357421875, 51.23440735163459] [11.77734375, 51.23440735163459];CSV;https://www.envidat.ch/dataset/10-16904-envidat-27;HTTPS;DATASET METADATA;information;https://www.envidat.ch/dataset/3a492ec9-def3-4e75-9778-dc397f63264d/resource/2a82fbff-34f5-4464-a7d4-664ef43a1303/download/mortality_calibration_data.csv;HTTPS;CALIBRATION DATA;download",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "8ab9a83b-4a08-52b2-bf87-1b3cd146a39b",
-    "notes": [
-        "The dataset comprises > 90 000 records from inventories in 54 strict forest reserves in [Switzerland](https://www.wsl.ch/de/wald/biodiversitaet-naturschutz-urwald/naturwaldreservate.html) and [Lower Saxony / Germany](http://naturwaelder.de/) along a considerable environmental gradient. It was used to develop parsimonious, species-specific mortality models for 18 European tree species based on tree size and growth as well as additional covariates on stand structure and climate.     ## Inventory data  Measurements had been conducted repeatedly on up to 14 permanent plots per reserve for up to 60 years with re-measurement intervals of 4 - 27 years. The permanent plots vary in size between 0.03 and 3.47 ha. The inventories provide diameter measurements at breast height (DBH) and information on the species and status (alive or dead) of trees with DBH \u2265 4 cm for Switzerland and \u2265 7 cm for Germany.     ## Data selection  We excluded three permanent plots where at least 80 % of the trees died during an interval of 10 years, and mortality could be clearly assigned to a disturbance agent. Mortality in the remaining stands was rather low, with a mean annual mortality rate of 1.5 % and strong variation between plots from 0 to 6.5 % (assessed for trees of all species with DBH \u2265 7 cm).  We only used data from permanent plots with at least 20 trees per species to obtain reliable plot-level mortality rates even for species with low mortality rates (about 5 % during 10 years), and selected tree species occurring on at least 10 plots to cover sufficient ecological gradients. This led to a dataset of 197 permanent plots and 18 tree or shrub species: _Abies alba_ Mill., _Acer campestre_ L., _Acer pseudoplatanus_ L., _Alnus incana_ Moench., _Betula pendula_ Roth, _Carpinus betulus_ L., _Cornus mas_ L., _Corylus avellana_ L., _Fagus sylvatica_ L., _Fraxinus excelsior_ L., _Picea abies_ (L.) Karst, _Pinus mugo_ Turra, _Pinus sylvestris_ L., _Quercus pubescens_ Willd., _Quercus_ spp. (_Q. petraea_ Liebl. and _Q. robur_ L.; not properly differentiated in the Swiss inventories), _Sorbus aria_ Crantz, _Tilia cordata_ Mill. and _Ulmus glabra_ Huds..     ## Predictors of tree mortality  We considered tree size and growth as key indicators for mortality risk. Radial stem growth between the first and second inventory and DBH at the second inventory were used to predict tree status (alive or dead) at the third inventory. To this end, the annual relative basal area increment (relBAI) was calculated as the compound annual growth rate of the trees basal area. Additional covariates on stand structure and climate comprise mean annual precipitation sum (P), mean annual air temperature (mT), the mean and the interquartile range of DBH (mDBH, iqrDBH), basal area (BA) and the number of trees (N) per hectare.     ## Further information  For further information, refer to H\u00fclsmann _et al_. (in press) How to kill a tree \u2013 Empirical mortality models for eighteen species and their performance in a dynamic forest model. _Ecological Applications_."
-    ],
-    "oai_identifier": [
-        "doi:10.16904/envidat.27",
-        "oai:envidat.ch:10.16904/envidat.27"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "EMPIRICAL MORTALITY MODELS"
-        },
-        {
-            "name": "FOREST RESERVES"
-        },
-        {
-            "name": "INVENTORY DATA"
-        },
-        {
-            "name": "TREE GROWTH"
-        },
-        {
-            "name": "TREE MORTALITY"
-        }
-    ],
-    "title": [
-        "Calibration data for empirical mortality models of 18 European tree species"
-    ],
-    "url": "https://www.envidat.ch/dataset/3a492ec9-def3-4e75-9778-dc397f63264d/resource/2a82fbff-34f5-4464-a7d4-664ef43a1303/download/mortality_calibration_data.csv"
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-iso19139/SET_1/json/9119cb6d-879b-5fcb-a1ed-019aee3cb28d.json b/oaitestdata/envidat-iso19139/SET_1/json/9119cb6d-879b-5fcb-a1ed-019aee3cb28d.json
deleted file mode 100644
index 8d14eec2..00000000
--- a/oaitestdata/envidat-iso19139/SET_1/json/9119cb6d-879b-5fcb-a1ed-019aee3cb28d.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "sommer@slf.ch"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "TXT",
-        "LINK",
-        "ZIP"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=iso19139&identifier=doi:10.16904/21",
-    "PublicationTimestamp": "2017-12-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland and CRYOS, School of Architecture and Civil Engineering, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "author": [
-        "Christian Sommer"
-    ],
-    "fulltext": "oai:envidat.ch:10.16904/21;2018-02-22T14:46:39Z;doi:10.16904/21;Eng;MD_CharacterSetCode_utf8;Christian Sommer;WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland and CRYOS, School of Architecture and Civil Engineering, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland;sommer@slf.ch;2017-06-19T15:09:33;ISO 19115:2003/19139;1.0;EPSG:4326;Wind crust formation: SnowMicroPen data;2017-12-31;This dataset contains the SnowMicroPen (SMP) data from 38 wind tunnel experiments on wind-packing / wind crust formation. These experiments were performed in the winters 2015/16 and 2016/17 and include more than 1000 SMP measurements.     The SMPs are organized per experiment. Each experiment subfolder contains the processed SMP profiles and some additional files.    Please refer to the README for more details on the data. The processing scripts are available for download as well. The scripts are mainly provided as documentation and would need to be adjusted to be used.    This dataset is the basis of the following publication:    Sommer C.G., Lehning M., & Fierz C. (2017). Wind tunnel experiments: Saltation is necessary for wind-packing. Journal of Glaciology, 63(242), 950-958. doi:10.1017/jog.2017.53;Christian Sommer;WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland and CRYOS, School of Architecture and Civil Engineering, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland;sommer@slf.ch;SMP;SNOW;SNOWMICROPEN;WIND CRUST;WIND-PACKING;Open Data Commons Open Database License (ODbL);Eng;MD_CharacterSetCode_utf8;9.86752 46.80798;LINK;TXT;ZIP;https://www.envidat.ch/dataset/10-16904-21;HTTPS;DATASET METADATA;information;http://montblanc.slf.ch/owncloud/index.php/s/mjiY348fUwdHsPW;HTTP;SMP DATA;download;https://www.envidat.ch/dataset/9918d77c-3176-453f-b34c-062ba979144a/resource/551fe7aa-af53-44a5-8d6f-615b5891a696/download/readme.txt;HTTPS;README;download;https://www.envidat.ch/dataset/9918d77c-3176-453f-b34c-062ba979144a/resource/f4d23fd3-364b-4574-bc54-5fc07aae4d35/download/processingscripts.zip;HTTPS;PROCESSING SCRIPTS;download",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "9119cb6d-879b-5fcb-a1ed-019aee3cb28d",
-    "notes": [
-        "This dataset contains the SnowMicroPen (SMP) data from 38 wind tunnel experiments on wind-packing / wind crust formation. These experiments were performed in the winters 2015/16 and 2016/17 and include more than 1000 SMP measurements.     The SMPs are organized per experiment. Each experiment subfolder contains the processed SMP profiles and some additional files.    Please refer to the README for more details on the data. The processing scripts are available for download as well. The scripts are mainly provided as documentation and would need to be adjusted to be used.    This dataset is the basis of the following publication:    Sommer C.G., Lehning M., & Fierz C. (2017). Wind tunnel experiments: Saltation is necessary for wind-packing. Journal of Glaciology, 63(242), 950-958. doi:10.1017/jog.2017.53"
-    ],
-    "oai_identifier": [
-        "doi:10.16904/21",
-        "oai:envidat.ch:10.16904/21"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "SMP"
-        },
-        {
-            "name": "SNOW"
-        },
-        {
-            "name": "SNOWMICROPEN"
-        },
-        {
-            "name": "WIND CRUST"
-        },
-        {
-            "name": "WIND-PACKING"
-        }
-    ],
-    "title": [
-        "Wind crust formation: SnowMicroPen data"
-    ],
-    "url": "https://www.envidat.ch/dataset/9918d77c-3176-453f-b34c-062ba979144a/resource/f4d23fd3-364b-4574-bc54-5fc07aae4d35/download/processingscripts.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-iso19139/SET_1/json/a71f9f2f-0102-5807-84d8-602d16646f65.json b/oaitestdata/envidat-iso19139/SET_1/json/a71f9f2f-0102-5807-84d8-602d16646f65.json
deleted file mode 100644
index a4596c54..00000000
--- a/oaitestdata/envidat-iso19139/SET_1/json/a71f9f2f-0102-5807-84d8-602d16646f65.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "Contact": [
-        "marty@slf.ch"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "TXT",
-        "CSV"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=iso19139&identifier=doi:10.16904/15",
-    "PublicationTimestamp": "2017-12-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avalanche Research SLF"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "author": [
-        "Christoph Marty"
-    ],
-    "fulltext": "oai:envidat.ch:10.16904/15;2018-07-12T11:01:15Z;doi:10.16904/15;Eng;MD_CharacterSetCode_utf8;Christoph Marty;WSL Institute for Snow and Avalanche Research SLF;marty@slf.ch;2017-03-02T08:50:47;ISO 19115:2003/19139;1.0;EPSG:4326;GCOS SWE data from 11 stations in Switzerland;2017-12-31;Snowprofile from 11 observer sites in Switzerland compiled for the Global Climate Observing System (GCOS).  Height of snow (cm) and snow water equivalent (mm) are recorded every 2 weeks since the 1947 (depending on station). Attached metadata file gives details of each station.;Christoph Marty;WSL Institute for Snow and Avalanche Research SLF;marty@slf.ch;GCOS;SNOW HEIGHT;SNOW WATER EQUIVALENT;Open Data Commons Open Database License (ODbL);Eng;MD_CharacterSetCode_utf8;7.890192955 46.55818213;8.591917728 46.63294615;8.395290837 46.79121008;8.308282838 46.50461379;7.751164932 46.02340309;9.848163035 46.81254897;9.895973081 46.86057949;9.8092511 46.82938238;9.184634236 46.46326154;10.41934353 46.59981095;9.962675638 46.60433181;TXT;CSV;https://www.envidat.ch/dataset/gcos-swe-data;HTTPS;DATASET METADATA;information;http://montblanc.slf.ch/owncloud/index.php/s/v4a9zjZRoOOr4Ss/download?path=%2F&files=metadata.txt;HTTP;STATION METADATA;download;http://montblanc.slf.ch/owncloud/index.php/s/v4a9zjZRoOOr4Ss;HTTP;DATA ACCESS;download",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "a71f9f2f-0102-5807-84d8-602d16646f65",
-    "notes": [
-        "Snowprofile from 11 observer sites in Switzerland compiled for the Global Climate Observing System (GCOS).  Height of snow (cm) and snow water equivalent (mm) are recorded every 2 weeks since the 1947 (depending on station). Attached metadata file gives details of each station."
-    ],
-    "oai_identifier": [
-        "doi:10.16904/15",
-        "oai:envidat.ch:10.16904/15"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "GCOS"
-        },
-        {
-            "name": "SNOW HEIGHT"
-        },
-        {
-            "name": "SNOW WATER EQUIVALENT"
-        }
-    ],
-    "title": [
-        "GCOS SWE data from 11 stations in Switzerland"
-    ],
-    "url": "http://montblanc.slf.ch/owncloud/index.php/s/v4a9zjZRoOOr4Ss"
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-iso19139/SET_1/json/b37b8292-cf30-5252-b3cb-ba21350e20cb.json b/oaitestdata/envidat-iso19139/SET_1/json/b37b8292-cf30-5252-b3cb-ba21350e20cb.json
deleted file mode 100644
index 7c0bd3a0..00000000
--- a/oaitestdata/envidat-iso19139/SET_1/json/b37b8292-cf30-5252-b3cb-ba21350e20cb.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "techel@slf.ch"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "TXT"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=iso19139&identifier=doi:10.16904/envidat.26",
-    "PublicationTimestamp": "2016-12-31T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avalanchre Research SLF"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "author": [
-        "Frank Techel"
-    ],
-    "fulltext": "oai:envidat.ch:10.16904/envidat.26;2018-07-07T00:20:12Z;doi:10.16904/envidat.26;Eng;MD_CharacterSetCode_utf8;Frank Techel;WSL Institute for Snow and Avalanchre Research SLF;techel@slf.ch;2017-12-01T07:13:26;ISO 19115:2003/19139;1.0;EPSG:4326;Avalanche fatalities in the European Alps (1969/1970 - 2014/2015);2016-12-31;During the last 45 years, about 100 people lost their lives in avalanches in the European Alps each year. Avalanche fatalities in settlements and on transportation corridors have considerably decreased since the 1970s. In contrast, the number of avalanche fatalities during recreational activities away from avalanche-secured terrain doubled between the 1960s and 1980s and has remained relatively stable since, despite a continuing strong increase in winter backcountry recreational activities.    Data complementing Figure 2 in:    _\"Avalanche fatalities in the European Alps: long-term trends and statistics\"_, by Techel, F., Jarry, F., Kronthaler, G., Mitterer, S., Nairz, P., Pav\u0161ek, M., Valt, M., and Darms, G.    Data description:    please refer to section 2 (Data and Methods) in the mentioned publication;Frank Techel;WSL Institute for Snow and Avalanchre Research SLF;techel@slf.ch;AVALANCHE ACCIDENT;AVALANCHE ACCIDENT STATISTICS;AVALANCHE FATALITIES;Open Data Commons Open Database License (ODbL);Eng;MD_CharacterSetCode_utf8;5.1416015625 44.7779358963;4.5703125 44.0560116958;5.888671875 43.0367758576;8.701171875 44.1191415164;7.55859375 44.7467332402;8.7451171875 45.6140374114;11.1181640625 45.182036837;13.18359375 46.1341700462;16.5673828125 46.0427356538;16.0400390625 48.4292005556;13.798828125 48.166085419;7.5146484375 47.6357835909;5.1416015625 44.7779358963;TXT;https://www.envidat.ch/dataset/avalanche-fatalities-european-alps-1969-2015;HTTPS;DATASET METADATA;information;https://www.envidat.ch/dataset/07dcd960-6197-4709-9a54-60407b4075ca/resource/d093dfb5-f72a-41c9-a444-373b1e4ffba5/download/fatalities_all_countries_envidat.txt;HTTPS;DATA AVALANCHE FATALITIES 1969/1970 - 2014/2015;download",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "b37b8292-cf30-5252-b3cb-ba21350e20cb",
-    "notes": [
-        "During the last 45 years, about 100 people lost their lives in avalanches in the European Alps each year. Avalanche fatalities in settlements and on transportation corridors have considerably decreased since the 1970s. In contrast, the number of avalanche fatalities during recreational activities away from avalanche-secured terrain doubled between the 1960s and 1980s and has remained relatively stable since, despite a continuing strong increase in winter backcountry recreational activities.    Data complementing Figure 2 in:    _\"Avalanche fatalities in the European Alps: long-term trends and statistics\"_, by Techel, F., Jarry, F., Kronthaler, G., Mitterer, S., Nairz, P., Pav\u0161ek, M., Valt, M., and Darms, G.    Data description:    please refer to section 2 (Data and Methods) in the mentioned publication"
-    ],
-    "oai_identifier": [
-        "doi:10.16904/envidat.26",
-        "oai:envidat.ch:10.16904/envidat.26"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "AVALANCHE ACCIDENT"
-        },
-        {
-            "name": "AVALANCHE ACCIDENT STATISTICS"
-        },
-        {
-            "name": "AVALANCHE FATALITIES"
-        }
-    ],
-    "title": [
-        "Avalanche fatalities in the European Alps (1969/1970 - 2014/2015)"
-    ],
-    "url": "https://www.envidat.ch/dataset/07dcd960-6197-4709-9a54-60407b4075ca/resource/d093dfb5-f72a-41c9-a444-373b1e4ffba5/download/fatalities_all_countries_envidat.txt"
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-iso19139/SET_1/json/bcc437b4-ab48-565e-84c4-ad1fac665baf.json b/oaitestdata/envidat-iso19139/SET_1/json/bcc437b4-ab48-565e-84c4-ad1fac665baf.json
deleted file mode 100644
index c9c126ee..00000000
--- a/oaitestdata/envidat-iso19139/SET_1/json/bcc437b4-ab48-565e-84c4-ad1fac665baf.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "enrico.paterna@slf.ch"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "ZIP"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=iso19139&identifier=doi:10.16904/6",
-    "PublicationTimestamp": "2016-12-31T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "SLF"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "author": [
-        "Enrico Paterna"
-    ],
-    "fulltext": "oai:envidat.ch:10.16904/6;2018-07-07T00:12:49Z;doi:10.16904/6;Eng;MD_CharacterSetCode_utf8;Enrico Paterna;SLF;enrico.paterna@slf.ch;2016-10-17T10:30:40;ISO 19115:2003/19139;1.0;EPSG:4326;Wind tunnel measurement data of drifting snow and turbulent wind fluctuations;2016-12-31;The data correspond to the experiments presented and discussed in a paper regarding the interaction between turbulent wind fluctuations and snow saltation mass-fluxes (Paterna, 2016). Each of the nine data files corresponds to a different experiment presented in the paper and conducted in the winter 2014/2015 in the WSL/SLF cold wind tunnel in Davos. For each file the five columns indicate the time from the beginning of the experiment, the streamwise (u\u2019) and the vertical (w\u2019) wind velocity fluctuations, the streamwise (qx) and the vertical (qz) snow mass-flux components. From these time-series the scales of the snow saltation and of the turbulent flow are obtained with respect to the eddy-cycles and snow saltation cycles. From spectral analysis of the time-series a decoupling of the snow saltation from the turbulence forcing reveals two regimes of interaction: a turbulence-dependent regime occurring with weak saltation, and a turbulence-independent regime with strong saltation. Further details can be found at the link below.     __Publication__ http://onlinelibrary.wiley.com/doi/10.1002/2016GL068171/abstract;Enrico Paterna;SLF;enrico.paterna@slf.ch;BOUNDARY LAYER WINDS;SALTATION;SNOW COVER;SNOW DEPTH;VERTICAL WIND MOTION;Open Data Commons Open Database License (ODbL);Eng;MD_CharacterSetCode_utf8;9.84726 46.81204;ZIP;https://www.envidat.ch/dataset/10-16904-6;HTTPS;DATASET METADATA;information;https://www.envidat.ch/dataset/78af269e-4d9d-4fc3-9039-9814a4872a07/resource/8030cd31-90dd-4d18-a1f7-fdfd7030540d/download/paterna2016.zip;HTTPS;DATA COMPILATION;download",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "bcc437b4-ab48-565e-84c4-ad1fac665baf",
-    "notes": [
-        "The data correspond to the experiments presented and discussed in a paper regarding the interaction between turbulent wind fluctuations and snow saltation mass-fluxes (Paterna, 2016). Each of the nine data files corresponds to a different experiment presented in the paper and conducted in the winter 2014/2015 in the WSL/SLF cold wind tunnel in Davos. For each file the five columns indicate the time from the beginning of the experiment, the streamwise (u\u2019) and the vertical (w\u2019) wind velocity fluctuations, the streamwise (qx) and the vertical (qz) snow mass-flux components. From these time-series the scales of the snow saltation and of the turbulent flow are obtained with respect to the eddy-cycles and snow saltation cycles. From spectral analysis of the time-series a decoupling of the snow saltation from the turbulence forcing reveals two regimes of interaction: a turbulence-dependent regime occurring with weak saltation, and a turbulence-independent regime with strong saltation. Further details can be found at the link below.     __Publication__ http://onlinelibrary.wiley.com/doi/10.1002/2016GL068171/abstract"
-    ],
-    "oai_identifier": [
-        "doi:10.16904/6",
-        "oai:envidat.ch:10.16904/6"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "BOUNDARY LAYER WINDS"
-        },
-        {
-            "name": "SALTATION"
-        },
-        {
-            "name": "SNOW COVER"
-        },
-        {
-            "name": "SNOW DEPTH"
-        },
-        {
-            "name": "VERTICAL WIND MOTION"
-        }
-    ],
-    "title": [
-        "Wind tunnel measurement data of drifting snow and turbulent wind fluctuations"
-    ],
-    "url": "https://www.envidat.ch/dataset/78af269e-4d9d-4fc3-9039-9814a4872a07/resource/8030cd31-90dd-4d18-a1f7-fdfd7030540d/download/paterna2016.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-iso19139/SET_1/json/c7798a7d-2a26-5255-a779-a7df7a337707.json b/oaitestdata/envidat-iso19139/SET_1/json/c7798a7d-2a26-5255-a779-a7df7a337707.json
deleted file mode 100644
index 3e77aee0..00000000
--- a/oaitestdata/envidat-iso19139/SET_1/json/c7798a7d-2a26-5255-a779-a7df7a337707.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "accidents@slf.ch"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "CSV"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=iso19139&identifier=doi:10.16904/13",
-    "PublicationTimestamp": "2018-12-31T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avalanche Research SLF"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(46N-48N,6 E-10E)",
-    "author": [
-        "Avalanche Warning Service SLF"
-    ],
-    "fulltext": "oai:envidat.ch:10.16904/13;2018-11-12T08:50:36Z;doi:10.16904/13;Eng;MD_CharacterSetCode_utf8;Avalanche Warning Service SLF;WSL Institute for Snow and Avalanche Research SLF;accidents@slf.ch;2017-03-01T12:20:55;ISO 19115:2003/19139;1.0;EPSG:4326;Fatal avalanche accidents in Switzerland since 1995-1996;2018-12-31;This data collection contains information concerning all accidents by snow avalanches causing at least one fatality in Switzerland. The data set commences on 01/10/1995. After the completion of a hydrological year, the new data is added.      The following information is provided:         * avalanche identifier      * date of the accident     * accuracy of the date in range of days before and after     * canton     * name of the locality     * start zone of the avalanche       * coordinates (Swiss coordinate system, approximately in middle of start zone)       * accuracy of the coordinates in meters    * elevation (in meteres above sea level, app. in middle of start zone)      * slope aspect (main orientation of start zone)       * slope inclination (in degree, steepest point within start zone)       * number of dead persons      * number of caught persons     * number of fully buried persons       * forecasted avalanche danger level      * activity/location of the accident party at the time of the incident;Avalanche Warning Service SLF;WSL Institute for Snow and Avalanche Research SLF;accidents@slf.ch;AVALANCHE ACCIDENT STATISTICS;AVALANCHE ACCIDENTS;AVALANCHE FATALITIES;Open Data Commons Open Database License (ODbL);Eng;MD_CharacterSetCode_utf8;5.95587;10.49203;45.81802;47.80838;CSV;https://www.envidat.ch/dataset/fatal-avalanche-accidents-switzerland-1995;HTTPS;DATASET METADATA;information;https://www.envidat.ch/dataset/f7160261-c98d-4d49-8966-10c1b0a32831/resource/6dd040cb-e505-4373-8f7f-e932e7d73c17/download/avalanche_accidents_switzerland_since_1995.csv;HTTPS;FATAL AVALANCHE ACCIDENTS IN SWITZERLAND SINCE 1995-1996;download",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "c7798a7d-2a26-5255-a779-a7df7a337707",
-    "notes": [
-        "This data collection contains information concerning all accidents by snow avalanches causing at least one fatality in Switzerland. The data set commences on 01/10/1995. After the completion of a hydrological year, the new data is added.      The following information is provided:         * avalanche identifier      * date of the accident     * accuracy of the date in range of days before and after     * canton     * name of the locality     * start zone of the avalanche       * coordinates (Swiss coordinate system, approximately in middle of start zone)       * accuracy of the coordinates in meters    * elevation (in meteres above sea level, app. in middle of start zone)      * slope aspect (main orientation of start zone)       * slope inclination (in degree, steepest point within start zone)       * number of dead persons      * number of caught persons     * number of fully buried persons       * forecasted avalanche danger level      * activity/location of the accident party at the time of the incident"
-    ],
-    "oai_identifier": [
-        "doi:10.16904/13",
-        "oai:envidat.ch:10.16904/13"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.95587,45.81802],[5.95587,47.80838],[10.49203,47.80838],[10.49203,45.81802],[5.95587,45.81802]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "AVALANCHE ACCIDENT STATISTICS"
-        },
-        {
-            "name": "AVALANCHE ACCIDENTS"
-        },
-        {
-            "name": "AVALANCHE FATALITIES"
-        }
-    ],
-    "title": [
-        "Fatal avalanche accidents in Switzerland since 1995-1996"
-    ],
-    "url": "https://www.envidat.ch/dataset/f7160261-c98d-4d49-8966-10c1b0a32831/resource/6dd040cb-e505-4373-8f7f-e932e7d73c17/download/avalanche_accidents_switzerland_since_1995.csv"
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-iso19139/SET_1/json/cc9c536b-e63f-5b27-92da-64f7d6736da7.json b/oaitestdata/envidat-iso19139/SET_1/json/cc9c536b-e63f-5b27-92da-64f7d6736da7.json
deleted file mode 100644
index ccbab1bd..00000000
--- a/oaitestdata/envidat-iso19139/SET_1/json/cc9c536b-e63f-5b27-92da-64f7d6736da7.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "marty@slf.ch"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=iso19139&identifier=doi:10.16904/12",
-    "PublicationTimestamp": "2014-12-31T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avanche Research SLF"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "author": [
-        "Christoph Marty"
-    ],
-    "fulltext": "oai:envidat.ch:10.16904/12;2018-10-24T13:33:02Z;doi:10.16904/12;Eng;MD_CharacterSetCode_utf8;Christoph Marty;WSL Institute for Snow and Avanche Research SLF;marty@slf.ch;2017-02-07T08:21:09;ISO 19115:2003/19139;1.0;EPSG:4326;Alpine3D simulations of future climate scenarios CH2014;2014-12-31;# Overview    The CH2014-Impacts initiative is a concerted national effort to describe impacts of climate change in Switzerland quantitatively, drawing on the scientific resources available in Switzerland today. The initiative links the recently developed Swiss Climate Change Scenarios CH2011 with an evolving base of quantitative impact models. The use of a common climate data set across disciplines and research groups sets a high standard of consistency and comparability of results. Impact studies explore the wide range of climatic changes in temperature and precipitation projected in CH2011 for the 21st century, which vary with the assumed global level of greenhouse gases, the time horizon, the underlying climate model, and the geographical region within Switzerland. The differences among climate projections are considered using three greenhouse gas scenarios, three future time periods in the 21st century, and three climate uncertainty levels (Figure 1). Impacts are shown with respect to the reference period 1980-2009 of CH2011, and add to any impacts that have already emerged as a result of earlier climate change.    # Experimental Setup    Future snow cover changes are simulated with the physics-based model Alpine3D (Lehning et al., 2006). It is applied to two regions: The canton of Graub\u00fcnden and the Aare catchment. These domains are modeled with a Digital Elevation Model (DEM) with a resolution of 200 m \u00d7 200 m. This defines the simulation grid that has to be filled with land cover data and downscaled meteorological input data for each cell for the time period of interest at hourly resolution. The reference data set consists of automatic weather station data. All meteorological input parameters are spatially interpolated to the simulation grid. The reference period comprises only thirteen years (1999\u20132012), because the number of available high elevation weather stations for earlier times is not sufficient to achieve unbiased distribution of the observations with elevation. The model uses projected temperature and precipitation changes for all greenhouse gas scenarios (A1B, A2, and RCP3PD) and CH2011 time periods (2035, 2060, and 2085).    # Data    Snow cover changes are projected to be relatively small in the near term (2035) (Figure 5.1 top), in particular at higher elevations above 2000 m asl. As shown by Bavay et al. (2013) the spread in projected snow cover for this period is greater between different climate model chains (Chapter 3) than between the reference period and the model chain exhibiting the most moderate change. In the 2085 period much larger changes with the potential to fundamentally transform the snow dominated alpine area become apparent (Figure 5.1 bottom). These changes include a shortening of the snow season by 5\u20139 weeks for the A1B scenario. This is roughly equivalent to an elevation shift of 400\u2013800 m. The slight increase of winter precipitation and therefore snow fall projected in the CH2011 scenarios (with high associated uncertainty) can no longer compensate for the effect of increasing winter temperatures even at high elevations. In terms of Snow Water Equivalents (SWE), the projected reduction is up to two thirds toward the end of the century (2085). A continuous snow cover will be restricted to a shorter time period and/or to regions at increasingly high elevation. In Bern, for example, the number of days per year with at least 5 cm snow depth will decrease by 90% from now 20 days to only 2 days on average.;Christoph Marty;WSL Institute for Snow and Avanche Research SLF;marty@slf.ch;CLIMATE CHANGE;SNOW DEPTH;SNOW WATER EQUIVALENT;Open Data Commons Open Database License (ODbL);Eng;MD_CharacterSetCode_utf8;8.227 46.79959;https://www.envidat.ch/dataset/ch2014;HTTPS;DATASET METADATA;information;http://ch2014-impacts.ch/;HTTP;CH2014 REPORT;download;http://montblanc.slf.ch/owncloud/index.php/s/aFhh3IpDJ7z0vui;HTTP;DATASET;download",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "cc9c536b-e63f-5b27-92da-64f7d6736da7",
-    "notes": [
-        "# Overview    The CH2014-Impacts initiative is a concerted national effort to describe impacts of climate change in Switzerland quantitatively, drawing on the scientific resources available in Switzerland today. The initiative links the recently developed Swiss Climate Change Scenarios CH2011 with an evolving base of quantitative impact models. The use of a common climate data set across disciplines and research groups sets a high standard of consistency and comparability of results. Impact studies explore the wide range of climatic changes in temperature and precipitation projected in CH2011 for the 21st century, which vary with the assumed global level of greenhouse gases, the time horizon, the underlying climate model, and the geographical region within Switzerland. The differences among climate projections are considered using three greenhouse gas scenarios, three future time periods in the 21st century, and three climate uncertainty levels (Figure 1). Impacts are shown with respect to the reference period 1980-2009 of CH2011, and add to any impacts that have already emerged as a result of earlier climate change.    # Experimental Setup    Future snow cover changes are simulated with the physics-based model Alpine3D (Lehning et al., 2006). It is applied to two regions: The canton of Graub\u00fcnden and the Aare catchment. These domains are modeled with a Digital Elevation Model (DEM) with a resolution of 200 m \u00d7 200 m. This defines the simulation grid that has to be filled with land cover data and downscaled meteorological input data for each cell for the time period of interest at hourly resolution. The reference data set consists of automatic weather station data. All meteorological input parameters are spatially interpolated to the simulation grid. The reference period comprises only thirteen years (1999\u20132012), because the number of available high elevation weather stations for earlier times is not sufficient to achieve unbiased distribution of the observations with elevation. The model uses projected temperature and precipitation changes for all greenhouse gas scenarios (A1B, A2, and RCP3PD) and CH2011 time periods (2035, 2060, and 2085).    # Data    Snow cover changes are projected to be relatively small in the near term (2035) (Figure 5.1 top), in particular at higher elevations above 2000 m asl. As shown by Bavay et al. (2013) the spread in projected snow cover for this period is greater between different climate model chains (Chapter 3) than between the reference period and the model chain exhibiting the most moderate change. In the 2085 period much larger changes with the potential to fundamentally transform the snow dominated alpine area become apparent (Figure 5.1 bottom). These changes include a shortening of the snow season by 5\u20139 weeks for the A1B scenario. This is roughly equivalent to an elevation shift of 400\u2013800 m. The slight increase of winter precipitation and therefore snow fall projected in the CH2011 scenarios (with high associated uncertainty) can no longer compensate for the effect of increasing winter temperatures even at high elevations. In terms of Snow Water Equivalents (SWE), the projected reduction is up to two thirds toward the end of the century (2085). A continuous snow cover will be restricted to a shorter time period and/or to regions at increasingly high elevation. In Bern, for example, the number of days per year with at least 5 cm snow depth will decrease by 90% from now 20 days to only 2 days on average."
-    ],
-    "oai_identifier": [
-        "doi:10.16904/12",
-        "oai:envidat.ch:10.16904/12"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "CLIMATE CHANGE"
-        },
-        {
-            "name": "SNOW DEPTH"
-        },
-        {
-            "name": "SNOW WATER EQUIVALENT"
-        }
-    ],
-    "title": [
-        "Alpine3D simulations of future climate scenarios CH2014"
-    ],
-    "url": "http://montblanc.slf.ch/owncloud/index.php/s/aFhh3IpDJ7z0vui"
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-iso19139/SET_1/json/df23ae2a-9502-52ad-8de0-579ad401a122.json b/oaitestdata/envidat-iso19139/SET_1/json/df23ae2a-9502-52ad-8de0-579ad401a122.json
deleted file mode 100644
index bf8e1af2..00000000
--- a/oaitestdata/envidat-iso19139/SET_1/json/df23ae2a-9502-52ad-8de0-579ad401a122.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "sommer@slf.ch"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "TXT",
-        "LINK"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=iso19139&identifier=doi:10.16904/envidat.30",
-    "PublicationTimestamp": "2018-12-31T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "author": [
-        "Christian Sommer"
-    ],
-    "fulltext": "oai:envidat.ch:10.16904/envidat.30;2018-05-05T08:24:33Z;doi:10.16904/envidat.30;Eng;MD_CharacterSetCode_utf8;Christian Sommer;sommer@slf.ch;2018-02-22T14:01:16;ISO 19115:2003/19139;1.0;EPSG:4326;Expedition to Princess Elisabeth Antarctica Station, 2016/2017;2018-12-31;This dataset contains the data acquired during the expedition to Princess Elisabeth Antarctica Station in December 2016 and January 2017. The dataset consits of meterorological data, drifting snow mass flux data, SnowMicroPen data and Terrestrial Laser Scanning data.    Please refer to the README for more information about the data.    This dataset is the basis of the following publication:    Sommer, C. G., Wever, N., Fierz, C., and Lehning, M.: Wind-packing of snow in Antarctica, The Cryosphere Discuss., https://doi.org/10.5194/tc-2018-36, in review, 2018.;Christian Sommer;sommer@slf.ch;ANTARCTICA;DRIFTING SNOW;MASS FLUX;METEOROLOGICAL DATA;SNOWMICROPEN;TERRESTRIAL LASER SCANNING;Open Data Commons Open Database License (ODbL);Eng;MD_CharacterSetCode_utf8;23.35 -71.95;LINK;TXT;https://www.envidat.ch/dataset/10-16904-envidat-30;HTTPS;DATASET METADATA;information;http://montblanc.slf.ch/owncloud/index.php/s/SUhtGSpVdgBnFrE;HTTP;DATASET;download;https://www.envidat.ch/dataset/b5c9438a-83c3-4afb-8f37-b3ec18d3db6e/resource/f5b4224d-6a68-4090-b0d6-24234f698bb5/download/readme.txt;HTTPS;README;download",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "df23ae2a-9502-52ad-8de0-579ad401a122",
-    "notes": [
-        "This dataset contains the data acquired during the expedition to Princess Elisabeth Antarctica Station in December 2016 and January 2017. The dataset consits of meterorological data, drifting snow mass flux data, SnowMicroPen data and Terrestrial Laser Scanning data.    Please refer to the README for more information about the data.    This dataset is the basis of the following publication:    Sommer, C. G., Wever, N., Fierz, C., and Lehning, M.: Wind-packing of snow in Antarctica, The Cryosphere Discuss., https://doi.org/10.5194/tc-2018-36, in review, 2018."
-    ],
-    "oai_identifier": [
-        "doi:10.16904/envidat.30",
-        "oai:envidat.ch:10.16904/envidat.30"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ANTARCTICA"
-        },
-        {
-            "name": "DRIFTING SNOW"
-        },
-        {
-            "name": "MASS FLUX"
-        },
-        {
-            "name": "METEOROLOGICAL DATA"
-        },
-        {
-            "name": "SNOWMICROPEN"
-        },
-        {
-            "name": "TERRESTRIAL LASER SCANNING"
-        }
-    ],
-    "title": [
-        "Expedition to Princess Elisabeth Antarctica Station, 2016/2017"
-    ],
-    "url": "https://www.envidat.ch/dataset/b5c9438a-83c3-4afb-8f37-b3ec18d3db6e/resource/f5b4224d-6a68-4090-b0d6-24234f698bb5/download/readme.txt"
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-iso19139/SET_1/json/dfa133d9-712a-5f49-925e-c2d35ee81cee.json b/oaitestdata/envidat-iso19139/SET_1/json/dfa133d9-712a-5f49-925e-c2d35ee81cee.json
deleted file mode 100644
index 5619cccd..00000000
--- a/oaitestdata/envidat-iso19139/SET_1/json/dfa133d9-712a-5f49-925e-c2d35ee81cee.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "mott@slf.ch"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "XLSX",
-        "PNG",
-        "ZIP"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=iso19139&identifier=doi:10.16904/10",
-    "PublicationTimestamp": "2017-12-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "SLF"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "author": [
-        "Rebecca Mott"
-    ],
-    "fulltext": "oai:envidat.ch:10.16904/10;2018-10-26T13:05:48Z;doi:10.16904/10;Eng;MD_CharacterSetCode_utf8;Rebecca Mott;SLF;mott@slf.ch;2017-07-19T07:02:01;ISO 19115:2003/19139;1.0;EPSG:4326;DISCHMEX - Impact of extreme land-surface heterogeneity on micrometeorology over spring snow-cover;2017-12-31;This dataset contains eddy-covariance measurements in the ablation period of 2014-2016. Measurements were taken from two turbulence towers over a long-lasting snow patch, which are 5 m apart from each other (2014 and 2015). The turbulence towers were equipped with two YOUNG ultrasonic anemometers mounted 0.7 m (in 2014) and 3.3 m (in 2015) above snow-free ground, two ultrasonic anemometers (CSAT3, Campbell Scientific, Inc.) mounted at 2.6 m (in 2014) and 2.2 m (in 2015) above snow-free ground and one anemometer (DA-600, Kaijo Denki) mounted at 0.3 m above snow surface.      The measurement setup changed in 2016 and includes a measurement above the snow-free ground in upwind direction (Swiss coordinates: 790191/176689). The measurement tower is equipped with one ultrasonic anemometer (CSAT3, Campbell Scientific, Inc.) in 3.3 m above the snow-free ground. Additionally, one measurement tower is installed above the long-Lasting snow patch and equipped with the same setup as 2015.    Turbulence data were sampled at a frequency of 20 Hz. The processing of the data to quality controlled fluxes has been done with the Biomicrometeorology flux software (Thomas et al., 2009). The program applies plausibility tests and a despiking test after Vickers and Mahrt (1997) on the measured data. The routine further applies a time-lag correction and considers the deployment (e.g.  the sonic azimuth). A frequency response correction (Moore, 1986) is done and a three-dimensional rotation is performed. Finally, quality assurance/quality control (QA/QC) flags after Foken et al., (2004) are issued and fast Fourier transform power and co-spectra are calculated.  The change in snow height is considered in the post-processing for every measurement day. The turbulence data were averaged to 30 minute intervals.;Rebecca Mott;SLF;mott@slf.ch;DISCHMEX;EDDY-COVARIANCE MEASUREMENTS;PATCHY SNOW COVERS;TURBULENT SENSIBLE HEAT FLUXES;Open Data Commons Open Database License (ODbL);Eng;MD_CharacterSetCode_utf8;9.92665 46.71291;ZIP;XLSX;PNG;https://www.envidat.ch/dataset/10-16904-10;HTTPS;DATASET METADATA;information;https://www.envidat.ch/dataset/7e8c6dac-80cf-49d7-bd85-2a61d3336e6f/resource/486e31a9-78e2-4736-9cad-a40c0958662c/download/s1-2014.zip;HTTPS;S1 2014;download;https://www.envidat.ch/dataset/7e8c6dac-80cf-49d7-bd85-2a61d3336e6f/resource/25ce04fb-452c-439e-b1fe-8ef2ccb1ea4e/download/s2-2014.zip;HTTPS;S2 2014;download;https://www.envidat.ch/dataset/7e8c6dac-80cf-49d7-bd85-2a61d3336e6f/resource/96640b5b-18e4-4de4-b19b-d8be3fabe9a6/download/s3-2014.zip;HTTPS;S3 2014;download;https://www.envidat.ch/dataset/7e8c6dac-80cf-49d7-bd85-2a61d3336e6f/resource/60ca7742-4ab9-49f6-9318-3dac0c4ae4bd/download/s4-2014.zip;HTTPS;S4 2014;download;https://www.envidat.ch/dataset/7e8c6dac-80cf-49d7-bd85-2a61d3336e6f/resource/fb937402-fc94-4121-9d55-809664005628/download/s5-2014.zip;HTTPS;S5 2014;download;https://www.envidat.ch/dataset/7e8c6dac-80cf-49d7-bd85-2a61d3336e6f/resource/9e551281-5120-4041-860e-8d2fc911c9dd/download/s3-2015.zip;HTTPS;S3 2015;download;https://www.envidat.ch/dataset/7e8c6dac-80cf-49d7-bd85-2a61d3336e6f/resource/3e7cd0af-60cb-4026-8e8f-7c0736c45f5b/download/s4-2015.zip;HTTPS;S4 2015;download;https://www.envidat.ch/dataset/7e8c6dac-80cf-49d7-bd85-2a61d3336e6f/resource/68c609d2-beb3-45b7-bbd4-cdf33de5f6e1/download/s1-2015.zip;HTTPS;S1 2015;download;https://www.envidat.ch/dataset/7e8c6dac-80cf-49d7-bd85-2a61d3336e6f/resource/81cb8412-b9bf-4ac8-a65b-7fdd0c597087/download/s2-2015.zip;HTTPS;S2 2015;download;https://www.envidat.ch/dataset/7e8c6dac-80cf-49d7-bd85-2a61d3336e6f/resource/d9037751-fbdf-438c-a1b0-03aa3301c065/download/s5-2015.zip;HTTPS;S5 2015;download;https://www.envidat.ch/dataset/7e8c6dac-80cf-49d7-bd85-2a61d3336e6f/resource/b5c85840-bf9f-4605-b4c7-9d05b00f2cdc/download/s1-2016.zip;HTTPS;S1 2016;download;https://www.envidat.ch/dataset/7e8c6dac-80cf-49d7-bd85-2a61d3336e6f/resource/e78a7861-5a9d-458f-b66d-d180292f6840/download/s2-2016.zip;HTTPS;S2 2016;download;https://www.envidat.ch/dataset/7e8c6dac-80cf-49d7-bd85-2a61d3336e6f/resource/0425d29f-b2cd-4092-afe6-00ca6fbd2303/download/s3-2016.zip;HTTPS;S3 2016;download;https://www.envidat.ch/dataset/7e8c6dac-80cf-49d7-bd85-2a61d3336e6f/resource/43081c3a-5d6c-4f7c-9259-b221e82f9b61/download/s5-2016.zip;HTTPS;S5 2016;download;https://www.envidat.ch/dataset/7e8c6dac-80cf-49d7-bd85-2a61d3336e6f/resource/c97df0fe-0691-4123-9d12-73909311f289/download/outputexplanation.xlsx;HTTPS;OUTPUT EXPLANATION;download;https://www.envidat.ch/dataset/7e8c6dac-80cf-49d7-bd85-2a61d3336e6f/resource/622ba326-7828-4f83-868c-94ad784c1841/download/gletschboden.png;HTTPS;GLETSCHBODEN SETUP;download",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "dfa133d9-712a-5f49-925e-c2d35ee81cee",
-    "notes": [
-        "This dataset contains eddy-covariance measurements in the ablation period of 2014-2016. Measurements were taken from two turbulence towers over a long-lasting snow patch, which are 5 m apart from each other (2014 and 2015). The turbulence towers were equipped with two YOUNG ultrasonic anemometers mounted 0.7 m (in 2014) and 3.3 m (in 2015) above snow-free ground, two ultrasonic anemometers (CSAT3, Campbell Scientific, Inc.) mounted at 2.6 m (in 2014) and 2.2 m (in 2015) above snow-free ground and one anemometer (DA-600, Kaijo Denki) mounted at 0.3 m above snow surface.      The measurement setup changed in 2016 and includes a measurement above the snow-free ground in upwind direction (Swiss coordinates: 790191/176689). The measurement tower is equipped with one ultrasonic anemometer (CSAT3, Campbell Scientific, Inc.) in 3.3 m above the snow-free ground. Additionally, one measurement tower is installed above the long-Lasting snow patch and equipped with the same setup as 2015.    Turbulence data were sampled at a frequency of 20 Hz. The processing of the data to quality controlled fluxes has been done with the Biomicrometeorology flux software (Thomas et al., 2009). The program applies plausibility tests and a despiking test after Vickers and Mahrt (1997) on the measured data. The routine further applies a time-lag correction and considers the deployment (e.g.  the sonic azimuth). A frequency response correction (Moore, 1986) is done and a three-dimensional rotation is performed. Finally, quality assurance/quality control (QA/QC) flags after Foken et al., (2004) are issued and fast Fourier transform power and co-spectra are calculated.  The change in snow height is considered in the post-processing for every measurement day. The turbulence data were averaged to 30 minute intervals."
-    ],
-    "oai_identifier": [
-        "doi:10.16904/10",
-        "oai:envidat.ch:10.16904/10"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "DISCHMEX"
-        },
-        {
-            "name": "EDDY-COVARIANCE MEASUREMENTS"
-        },
-        {
-            "name": "PATCHY SNOW COVERS"
-        },
-        {
-            "name": "TURBULENT SENSIBLE HEAT FLUXES"
-        }
-    ],
-    "title": [
-        "DISCHMEX - Impact of extreme land-surface heterogeneity on micrometeorology over spring snow-cover"
-    ],
-    "url": "https://www.envidat.ch/dataset/7e8c6dac-80cf-49d7-bd85-2a61d3336e6f/resource/622ba326-7828-4f83-868c-94ad784c1841/download/gletschboden.png"
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-iso19139/SET_1/json/eb614775-347d-5dc3-81ec-058248c18fed.json b/oaitestdata/envidat-iso19139/SET_1/json/eb614775-347d-5dc3-81ec-058248c18fed.json
deleted file mode 100644
index 9b208f40..00000000
--- a/oaitestdata/envidat-iso19139/SET_1/json/eb614775-347d-5dc3-81ec-058248c18fed.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "wever@slf.ch"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "PDF",
-        "SMET"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=iso19139&identifier=doi:10.16904/1",
-    "PublicationTimestamp": "2015-12-31T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "SLF"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "author": [
-        "Nander Wever"
-    ],
-    "fulltext": "oai:envidat.ch:10.16904/1;2018-07-07T00:12:55Z;doi:10.16904/1;Eng;MD_CharacterSetCode_utf8;Nander Wever;SLF;wever@slf.ch;2016-05-25T15:07:58;ISO 19115:2003/19139;1.0;EPSG:4326;WFJ_MOD: Meteorological and snowpack measurements from Weissfluhjoch, Davos, Switzerland;2015-12-31;Dataset of meteorological and snowpack measurements from the automatic weather station at Weissfluhjoch, Davos, Switzerland, suitable for driving snowpack models. The dataset contains standard meteorological measurements, and additionally snowpack runoff data from a snow lysimeter. Where possible, data is quality checked and missing data are replaced from backup sensors from the measurement site itself, or (in only a few cases) from the MeteoSwiss weather station at 470 m distance and 150 m above the measurement site.     __Publication__  Wever, N., Schmid, L., Heilig, A., Eisen, O., Fierz, C., and Lehning, M. Verification of the multi-layer SNOWPACK model with different water transport schemes. 2015. The Cryosphere. Volume 9. 2271-2293. http://dx.doi.org/10.5194/tc-9-2271-2015. 10.5194/tc-9-2271-2015;Nander Wever;SLF;wever@slf.ch;AIR TEMPERATURE;HUMIDITY;LONGWAVE RADIATION;PRECIPITATION AMOUNT;SHORTWAVE RADIATION;SNOW DEPTH;SNOW ICE TEMPERATURE;WIND DIRECTION;WIND SPEED;Open Data Commons Open Database License (ODbL);Eng;MD_CharacterSetCode_utf8;9.809568 46.829598;SMET;PDF;https://www.envidat.ch/dataset/10-16904-1;HTTPS;DATASET METADATA;information;http://montblanc.slf.ch/owncloud/index.php/s/Wir5VAfGpDBbq8R;HTTP;VERSION 7 (CURRENT);download;http://montblanc.slf.ch/owncloud/index.php/s/3HuhVPC8614xwGF;HTTP;VERSION 6;download;http://montblanc.slf.ch/owncloud/index.php/s/lHzKsz2oFkYfYHA;HTTP;VERSION 5;download;http://montblanc.slf.ch/owncloud/index.php/s/nnWEGFR8Z7HQTGj;HTTP;VERSION 4;download;http://montblanc.slf.ch/owncloud/index.php/s/l1ttKFAnEXwp7hc;HTTP;VERSION 3;download;http://montblanc.slf.ch/owncloud/index.php/s/93dtOq2yCH7uyZX;HTTP;VERSION 2;download;http://montblanc.slf.ch/owncloud/index.php/s/ZwaKg8kCcbK1HXG;HTTP;VERSION 1;download;http://montblanc.slf.ch/owncloud/index.php/s/csDu5ZbaQyOoBgd;HTTP;ALL VERSIONS;download;https://www.envidat.ch/dataset/38112bee-f865-4b29-ba19-47a99ba78833/resource/8d201858-fba9-449c-b41b-4e49624fa6cc/download/iowfjref.ini;HTTPS;SNOWPACK INI FILE (NEW SYNTAX);download;https://www.envidat.ch/dataset/38112bee-f865-4b29-ba19-47a99ba78833/resource/e51b83ae-99a6-42f0-add4-8da9590c6573/download/iowfjref.ini;HTTPS;SNOWPACK INI FILE (OLD SYNTAX);download;https://www.envidat.ch/dataset/38112bee-f865-4b29-ba19-47a99ba78833/resource/ec0609f1-42fa-4a20-945e-6809bb15a8a0/download/wfj2.sno;HTTPS;SNOWPACK SNO FILE;download;https://www.envidat.ch/dataset/38112bee-f865-4b29-ba19-47a99ba78833/resource/022a5232-e9a6-4972-a59a-f1aedc2697d3/download/undercatch.pdf;HTTPS;UNDERCATCH CORRECTION;download",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "eb614775-347d-5dc3-81ec-058248c18fed",
-    "notes": [
-        "Dataset of meteorological and snowpack measurements from the automatic weather station at Weissfluhjoch, Davos, Switzerland, suitable for driving snowpack models. The dataset contains standard meteorological measurements, and additionally snowpack runoff data from a snow lysimeter. Where possible, data is quality checked and missing data are replaced from backup sensors from the measurement site itself, or (in only a few cases) from the MeteoSwiss weather station at 470 m distance and 150 m above the measurement site.     __Publication__  Wever, N., Schmid, L., Heilig, A., Eisen, O., Fierz, C., and Lehning, M. Verification of the multi-layer SNOWPACK model with different water transport schemes. 2015. The Cryosphere. Volume 9. 2271-2293. http://dx.doi.org/10.5194/tc-9-2271-2015. 10.5194/tc-9-2271-2015"
-    ],
-    "oai_identifier": [
-        "doi:10.16904/1",
-        "oai:envidat.ch:10.16904/1"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "AIR TEMPERATURE"
-        },
-        {
-            "name": "HUMIDITY"
-        },
-        {
-            "name": "LONGWAVE RADIATION"
-        },
-        {
-            "name": "PRECIPITATION AMOUNT"
-        },
-        {
-            "name": "SHORTWAVE RADIATION"
-        },
-        {
-            "name": "SNOW DEPTH"
-        },
-        {
-            "name": "SNOW ICE TEMPERATURE"
-        },
-        {
-            "name": "WIND DIRECTION"
-        },
-        {
-            "name": "WIND SPEED"
-        }
-    ],
-    "title": [
-        "WFJ_MOD: Meteorological and snowpack measurements from Weissfluhjoch, Davos, Switzerland"
-    ],
-    "url": "https://www.envidat.ch/dataset/38112bee-f865-4b29-ba19-47a99ba78833/resource/022a5232-e9a6-4972-a59a-f1aedc2697d3/download/undercatch.pdf"
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-iso19139/SET_1/json/eea9a427-a09c-5204-8dc3-e1908db794cc.json b/oaitestdata/envidat-iso19139/SET_1/json/eea9a427-a09c-5204-8dc3-e1908db794cc.json
deleted file mode 100644
index eb9b9943..00000000
--- a/oaitestdata/envidat-iso19139/SET_1/json/eea9a427-a09c-5204-8dc3-e1908db794cc.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "lehning@slf.ch"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "ZIP"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=iso19139&identifier=doi:10.16904/23",
-    "PublicationTimestamp": "2016-12-31T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "WSL"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "SpatialCoverage": "(47N-47N,10E-10E)",
-    "author": [
-        "Michael Lehning"
-    ],
-    "fulltext": "oai:envidat.ch:10.16904/23;2018-10-24T13:31:41Z;doi:10.16904/23;Eng;MD_CharacterSetCode_utf8;Michael Lehning;WSL;lehning@slf.ch;2017-08-15T15:23:58;ISO 19115:2003/19139;1.0;EPSG:4326;Precipitation Scaling Data Set (V\u00f6geli et al., Frontiers);2016-12-31;Dataset (Model input, snow distribution and validation) for the precipitation scaling paper, which should be cited along with the data set citation.    This data is useful for distributed hydrological modelling or other tasks that involve the study of snow distribution and precipitation in the high Alpine.     The format of the data is for Alpine3D (models.slf.ch) model runs but other models could be used, too.    Please cite:    _V\u00f6geli, C., Lehning, M., Wever, N., Bavay M., 2016: Scaling Precipitation Input to Spatially Distributed Hydrological Models by Measured Snow Distribution., Front. Earth Sci. 4: 108. doi: 10.3389/feart.2016.00108._    Dataset is provided as a single zip file.   The archive contains two directories, the valuable distributed snow depth maps for the landscape Davos and the simulation input.   The archive also contains the file: \"ReadMeMetadataDataSetPrecipitationScaling\" which explains the data structure.;Michael Lehning;WSL;lehning@slf.ch;ALPINE PRECIPITATION;ALPINE3D;ALPINE3D SIMULATIONS;SNOW;SNOW COVER;SNOW DISTRIBUTION;SNOW HYDROLOGY;Open Data Commons Open Database License (ODbL);Eng;MD_CharacterSetCode_utf8;9.70985412598;10.0037384033;46.6866603841;46.8606605287;ZIP;https://www.envidat.ch/dataset/10-16904-23;HTTPS;DATASET METADATA;information;https://www.envidat.ch/dataset/e3176e82-1561-4df0-8830-76eb4f66166b/resource/34945680-7cb0-47a1-96cb-ee6832a2b17c/download/archivevogeliforenvidat.zip;HTTPS;ADS DATASETS AND SIMULATION INPUTS;download",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "eea9a427-a09c-5204-8dc3-e1908db794cc",
-    "notes": [
-        "Dataset (Model input, snow distribution and validation) for the precipitation scaling paper, which should be cited along with the data set citation.    This data is useful for distributed hydrological modelling or other tasks that involve the study of snow distribution and precipitation in the high Alpine.     The format of the data is for Alpine3D (models.slf.ch) model runs but other models could be used, too.    Please cite:    _V\u00f6geli, C., Lehning, M., Wever, N., Bavay M., 2016: Scaling Precipitation Input to Spatially Distributed Hydrological Models by Measured Snow Distribution., Front. Earth Sci. 4: 108. doi: 10.3389/feart.2016.00108._    Dataset is provided as a single zip file.   The archive contains two directories, the valuable distributed snow depth maps for the landscape Davos and the simulation input.   The archive also contains the file: \"ReadMeMetadataDataSetPrecipitationScaling\" which explains the data structure."
-    ],
-    "oai_identifier": [
-        "doi:10.16904/23",
-        "oai:envidat.ch:10.16904/23"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[9.70985412598,46.6866603841],[9.70985412598,46.8606605287],[10.0037384033,46.8606605287],[10.0037384033,46.6866603841],[9.70985412598,46.6866603841]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ALPINE PRECIPITATION"
-        },
-        {
-            "name": "ALPINED"
-        },
-        {
-            "name": "ALPINED SIMULATIONS"
-        },
-        {
-            "name": "SNOW"
-        },
-        {
-            "name": "SNOW COVER"
-        },
-        {
-            "name": "SNOW DISTRIBUTION"
-        },
-        {
-            "name": "SNOW HYDROLOGY"
-        }
-    ],
-    "title": [
-        "Precipitation Scaling Data Set (V\u00f6geli et al., Frontiers)"
-    ],
-    "url": "https://www.envidat.ch/dataset/e3176e82-1561-4df0-8830-76eb4f66166b/resource/34945680-7cb0-47a1-96cb-ee6832a2b17c/download/archivevogeliforenvidat.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-iso19139/SET_1/json/f0c65311-0256-5242-8996-5f4182c3ac6e.json b/oaitestdata/envidat-iso19139/SET_1/json/f0c65311-0256-5242-8996-5f4182c3ac6e.json
deleted file mode 100644
index 332f2515..00000000
--- a/oaitestdata/envidat-iso19139/SET_1/json/f0c65311-0256-5242-8996-5f4182c3ac6e.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "Contact": [
-        "wever@slf.ch"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "TEXT/X-SH",
-        "ZIP"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=iso19139&identifier=doi:10.16904/16",
-    "PublicationTimestamp": "2017-12-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "WSL Institute for Snow and Avalanche Research SLF"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "author": [
-        "Nander Wever"
-    ],
-    "fulltext": "oai:envidat.ch:10.16904/16;2018-07-07T00:20:29Z;doi:10.16904/16;Eng;MD_CharacterSetCode_utf8;Nander Wever;WSL Institute for Snow and Avalanche Research SLF;wever@slf.ch;2017-03-21T13:59:10;ISO 19115:2003/19139;1.0;EPSG:4326;Weissfluhjoch dataset for ESM-SnowMIP;2017-12-31;This Weissfluhjoch dataset is a processed version  of the Weissfluhjoch dataset version 6 from http://www.envidat.ch/dataset/10-16904-1. This dataset was specially created for the ESM-SnowMIP project. Here it is documented how this dataset has been created.;Nander Wever;WSL Institute for Snow and Avalanche Research SLF;wever@slf.ch;SNOW MODELS;Open Data Commons Open Database License (ODbL);Eng;MD_CharacterSetCode_utf8;9.809568 46.829598;TEXT/X-SH;ZIP;https://www.envidat.ch/dataset/snowmip;HTTPS;DATASET METADATA;information;https://www.envidat.ch/dataset/a9264e9f-ea9b-4c89-b471-464efb891826/resource/a5918c50-6716-4dcf-b462-e1970ae1e072/download/wfj.smet;HTTPS;DATASET WEISSFLUHJOCH FOR ESM-SNOWMIP;download;https://www.envidat.ch/dataset/a9264e9f-ea9b-4c89-b471-464efb891826/resource/aa8942dc-5fe5-4792-bf4b-1b950d9c6204/download/createwfjdataset.sh;HTTPS;CONVERSION SCRIPT;download;https://www.envidat.ch/dataset/a9264e9f-ea9b-4c89-b471-464efb891826/resource/c7f7533e-03f2-42c2-ad82-36d3c6ab8fd2/download/io.ini;HTTPS;INI FILE;download;https://www.envidat.ch/dataset/a9264e9f-ea9b-4c89-b471-464efb891826/resource/b834a645-c5e0-4bf1-bceb-17a2eb62b61a/download/wfjairpressuredata.zip;HTTPS;WFJ_AIRPRESSURE_DATA.ZIP;download",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "f0c65311-0256-5242-8996-5f4182c3ac6e",
-    "notes": [
-        "This Weissfluhjoch dataset is a processed version  of the Weissfluhjoch dataset version 6 from http://www.envidat.ch/dataset/10-16904-1. This dataset was specially created for the ESM-SnowMIP project. Here it is documented how this dataset has been created."
-    ],
-    "oai_identifier": [
-        "doi:10.16904/16",
-        "oai:envidat.ch:10.16904/16"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "SNOW MODELS"
-        }
-    ],
-    "title": [
-        "Weissfluhjoch dataset for ESM-SnowMIP"
-    ],
-    "url": "https://www.envidat.ch/dataset/a9264e9f-ea9b-4c89-b471-464efb891826/resource/b834a645-c5e0-4bf1-bceb-17a2eb62b61a/download/wfjairpressuredata.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-iso19139/SET_1/json/f2ca7dea-9bf9-5530-8c3b-34c30043883b.json b/oaitestdata/envidat-iso19139/SET_1/json/f2ca7dea-9bf9-5530-8c3b-34c30043883b.json
deleted file mode 100644
index bfacfd43..00000000
--- a/oaitestdata/envidat-iso19139/SET_1/json/f2ca7dea-9bf9-5530-8c3b-34c30043883b.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "ernesto.trujillo@epfl.ch"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "DAT",
-        "DOC",
-        "ZIP"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=iso19139&identifier=doi:10.16904/9",
-    "PublicationTimestamp": "2016-12-31T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "EPFL, SLF"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "author": [
-        "Ernesto Trujillo"
-    ],
-    "fulltext": "oai:envidat.ch:10.16904/9;2018-07-07T00:08:12Z;doi:10.16904/9;Eng;MD_CharacterSetCode_utf8;Ernesto Trujillo;EPFL, SLF;ernesto.trujillo@epfl.ch;2016-10-16T21:56:52;ISO 19115:2003/19139;1.0;EPSG:4326;High resolution sea ice surface topography from the SIPEX-2 expedition, East Antarctica, 2012;2016-12-31;This dataset comprises of a post-processed set of terrestrial laser scans (TLS\u2019s) of Antarctic sea ice obtained during the Sea Ice Physics and Ecosystem Experiment-2 (SIPEX-2, http://seaice.acecrc.org.au/sipex2012/) in September-November 2012. The post-processing steps include the registration of the individual scans into a single 3-dimensional point cloud, the removal of unwanted noise caused by particles in the air (i.e., snow crystals), and the final generation of surface grids based on the cleaned individual point returns. The final product includes the \u2018xyz\u2019 coordinates of the individual point measurements, and gridded surfaces covering study areas of 100m x 100 m, and at resolutions of 0.01 m, 0.1 m, 0.25 m, 0.5 m and 1 m for each of the survey dates. Additionally, subgrid statistics that include the mean elevation, standard deviation, minimum and maximum elevations, range, and number of point returns in each gridcell are generated. The final product is provided in space-delimited text files, with the surface grids provided in Digital Terrain Model (DTM) format ready for visualization in any GIS software.    ###How to cite:  Please also cite the original publication when using this data set.: Trujillo, E., K. Leonard, T. Maksym, and M. Lehning (2016), Changes in snow distribution and surface topography following a snowstorm on Antarctic sea ice, J. Geophys. Res. Earth Surf., 121, doi:[10.1002/2016JF003893](https://dx.doi.org/10.1002/2016JF003893).;Ernesto Trujillo;EPFL, SLF;ernesto.trujillo@epfl.ch;POLAR;SEA ICE;SEA ICE ELEVATION;Open Data Commons Open Database License (ODbL);Eng;MD_CharacterSetCode_utf8;114 -66;122 -66;122 -63;114 -63;114 -66;DOC;DAT;ZIP;https://www.envidat.ch/dataset/10-16904-9;HTTPS;DATASET METADATA;information;https://www.envidat.ch/dataset/c88b82ed-d54e-43e6-b4e4-7ae1ee06a014/resource/bb51210c-6738-41d4-b4a4-31dd08f4725e/download/tlssipex-2metadata.doc;HTTPS;DATA PROCESSING DOCUMENTATION;download;ftp://ftp.wsl.ch/pub/smm/sipex2_dat.zip;FTP;LINK TO POST-PROCESSED TLS\u2019S OF ANTARCTIC SEA ICE;download;https://www.envidat.ch/dataset/c88b82ed-d54e-43e6-b4e4-7ae1ee06a014/resource/2557ecb5-e65d-4d60-97ce-fd6696ee2d00/download/10-16904-9sipex2dat.zip;HTTPS;POST PROCESSED TLS'S;download",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "f2ca7dea-9bf9-5530-8c3b-34c30043883b",
-    "notes": [
-        "This dataset comprises of a post-processed set of terrestrial laser scans (TLS\u2019s) of Antarctic sea ice obtained during the Sea Ice Physics and Ecosystem Experiment-2 (SIPEX-2, http://seaice.acecrc.org.au/sipex2012/) in September-November 2012. The post-processing steps include the registration of the individual scans into a single 3-dimensional point cloud, the removal of unwanted noise caused by particles in the air (i.e., snow crystals), and the final generation of surface grids based on the cleaned individual point returns. The final product includes the \u2018xyz\u2019 coordinates of the individual point measurements, and gridded surfaces covering study areas of 100m x 100 m, and at resolutions of 0.01 m, 0.1 m, 0.25 m, 0.5 m and 1 m for each of the survey dates. Additionally, subgrid statistics that include the mean elevation, standard deviation, minimum and maximum elevations, range, and number of point returns in each gridcell are generated. The final product is provided in space-delimited text files, with the surface grids provided in Digital Terrain Model (DTM) format ready for visualization in any GIS software.    ###How to cite:  Please also cite the original publication when using this data set.: Trujillo, E., K. Leonard, T. Maksym, and M. Lehning (2016), Changes in snow distribution and surface topography following a snowstorm on Antarctic sea ice, J. Geophys. Res. Earth Surf., 121, doi:[10.1002/2016JF003893](https://dx.doi.org/10.1002/2016JF003893)."
-    ],
-    "oai_identifier": [
-        "doi:10.16904/9",
-        "oai:envidat.ch:10.16904/9"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "POLAR"
-        },
-        {
-            "name": "SEA ICE"
-        },
-        {
-            "name": "SEA ICE ELEVATION"
-        }
-    ],
-    "title": [
-        "High resolution sea ice surface topography from the SIPEX-2 expedition, East Antarctica, 2012"
-    ],
-    "url": "https://www.envidat.ch/dataset/c88b82ed-d54e-43e6-b4e4-7ae1ee06a014/resource/2557ecb5-e65d-4d60-97ce-fd6696ee2d00/download/10-16904-9sipex2dat.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-iso19139/SET_1/json/fa19fb75-c103-5ff4-b67b-0ee58eda23ce.json b/oaitestdata/envidat-iso19139/SET_1/json/fa19fb75-c103-5ff4-b67b-0ee58eda23ce.json
deleted file mode 100644
index b8af8eeb..00000000
--- a/oaitestdata/envidat-iso19139/SET_1/json/fa19fb75-c103-5ff4-b67b-0ee58eda23ce.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "Contact": [
-        "wever@slf.ch"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=iso19139&identifier=doi:10.16904/17",
-    "PublicationTimestamp": "2017-12-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "SLF"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "author": [
-        "Nander Wever"
-    ],
-    "fulltext": "oai:envidat.ch:10.16904/17;2017-09-18T10:49:01Z;doi:10.16904/17;Eng;MD_CharacterSetCode_utf8;Nander Wever;SLF;wever@slf.ch;2017-03-23T14:25:26;ISO 19115:2003/19139;1.0;EPSG:4326;IRKIS Soil moisture measurements Davos;2017-12-31;Meteorological and soil moisture measurements from soil moisture stations installed from October 2010 - October 2013 in the area surrounding Davos, in particular in the Dischma catchment.    There are in total 7 stations: 1202, 1203, 1204, 1205, 222, 333 and SLF2. For each of the stations, there is a:    * vwc_[stn].smet: containing the soil moisture measurements    * station_[stn].smet: in-situ measured meteorlogical parameters. Note, the quality of these measurements for stations 1202, 1203, 1204 and 1205 is very low, with data gaps. Use this data with care. For stations 222, 333 and SLF2, data quality is high and only the default cautiousness should be applied.    * interpolatedmeteo_[stn].smet contains per stations a dataset derived by interpolating from several stations in the Davos area to the stations location. This dataset was generated from the output of the Alpine3D model, of which simulations are presented in the Wever et al. (2017) manuscript.    At the soil moisture measurement sites, Decagon 10HS sensors were installed, at 10, 30, 50, 80 and 120 cm depth. Per depth 2 sensors were installed, labelled A and B in the datafiles. Note that at stations 1203, 1204 and 1205, sensors were only installed at 10, 30 and 50 cm depth.    The files follow the SMET format: https://models.slf.ch/docserver/meteoio/SMET_specifications.pdf and metadata for the stations can be found in the header of the smet files.    Please cite the Wever et al. (2017) reference when using this data in publications.    For a more detailed description, please refer to: Wever, N., Comola, F., Bavay, M., and Lehning, M.: Simulating the influence of snow surface processes on soil moisture dynamics and streamflow generation in an alpine catchment, Hydrol. Earth Syst. Sci., 21, 4053-4071, https://doi.org/10.5194/hess-21-4053-2017, 2017.;Nander Wever;SLF;wever@slf.ch;METEO STATION;SOIL MOISTURE;Open Data Commons Open Database License (ODbL);Eng;MD_CharacterSetCode_utf8;9.8297824141 46.7968286797;9.8940537806 46.8038436988;9.8666676384 46.7717421009;9.9034282695 46.8084926987;9.914150411 46.7315544045;9.8645693083 46.7897142035;9.847212 46.812365;https://www.envidat.ch/dataset/soil-moisture-measurements-davos;HTTPS;DATASET METADATA;information;http://montblanc.slf.ch/owncloud/index.php/s/THiY4GlFBL3o4rC;HTTP;IRKIS SOIL MOISTURE DATA (ZIP FILE);download",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "fa19fb75-c103-5ff4-b67b-0ee58eda23ce",
-    "notes": [
-        "Meteorological and soil moisture measurements from soil moisture stations installed from October 2010 - October 2013 in the area surrounding Davos, in particular in the Dischma catchment.    There are in total 7 stations: 1202, 1203, 1204, 1205, 222, 333 and SLF2. For each of the stations, there is a:    * vwc_[stn].smet: containing the soil moisture measurements    * station_[stn].smet: in-situ measured meteorlogical parameters. Note, the quality of these measurements for stations 1202, 1203, 1204 and 1205 is very low, with data gaps. Use this data with care. For stations 222, 333 and SLF2, data quality is high and only the default cautiousness should be applied.    * interpolatedmeteo_[stn].smet contains per stations a dataset derived by interpolating from several stations in the Davos area to the stations location. This dataset was generated from the output of the Alpine3D model, of which simulations are presented in the Wever et al. (2017) manuscript.    At the soil moisture measurement sites, Decagon 10HS sensors were installed, at 10, 30, 50, 80 and 120 cm depth. Per depth 2 sensors were installed, labelled A and B in the datafiles. Note that at stations 1203, 1204 and 1205, sensors were only installed at 10, 30 and 50 cm depth.    The files follow the SMET format: https://models.slf.ch/docserver/meteoio/SMET_specifications.pdf and metadata for the stations can be found in the header of the smet files.    Please cite the Wever et al. (2017) reference when using this data in publications.    For a more detailed description, please refer to: Wever, N., Comola, F., Bavay, M., and Lehning, M.: Simulating the influence of snow surface processes on soil moisture dynamics and streamflow generation in an alpine catchment, Hydrol. Earth Syst. Sci., 21, 4053-4071, https://doi.org/10.5194/hess-21-4053-2017, 2017."
-    ],
-    "oai_identifier": [
-        "doi:10.16904/17",
-        "oai:envidat.ch:10.16904/17"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "METEO STATION"
-        },
-        {
-            "name": "SOIL MOISTURE"
-        }
-    ],
-    "title": [
-        "IRKIS Soil moisture measurements Davos"
-    ],
-    "url": "http://montblanc.slf.ch/owncloud/index.php/s/THiY4GlFBL3o4rC"
-}
\ No newline at end of file
diff --git a/oaitestdata/envidat-iso19139/SET_1/json/fa681dd6-0f3e-5cb1-8595-16e5d7b5150f.json b/oaitestdata/envidat-iso19139/SET_1/json/fa681dd6-0f3e-5cb1-8595-16e5d7b5150f.json
deleted file mode 100644
index 4936efea..00000000
--- a/oaitestdata/envidat-iso19139/SET_1/json/fa681dd6-0f3e-5cb1-8595-16e5d7b5150f.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "gerberf@slf.ch"
-    ],
-    "Contributor": [
-        "EnviDat"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "ZIP"
-    ],
-    "MetaDataAccess": "https://www.envidat.ch/oai?verb=GetRecord&metadataPrefix=iso19139&identifier=doi:10.16904/19",
-    "PublicationTimestamp": "2017-12-31T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Laboratory of Cryospheric Sciences, School of Architecture and Civil Engineering, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland and WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland"
-    ],
-    "Rights": [
-        "Open Data Commons Open Database License (ODbL)"
-    ],
-    "author": [
-        "Franziska Gerber"
-    ],
-    "fulltext": "oai:envidat.ch:10.16904/19;2018-06-16T11:07:20Z;doi:10.16904/19;Eng;MD_CharacterSetCode_utf8;Franziska Gerber;Laboratory of Cryospheric Sciences, School of Architecture and Civil Engineering, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland and WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland;gerberf@slf.ch;2017-06-01T12:46:02;ISO 19115:2003/19139;1.0;EPSG:4326;DISCHMEX - Observations and simulations of the close-ridge small-scale atmospheric flow field and snow accumulation at Sattelhorn, Dischma valley, Davos, Switzerland.;2017-12-31;The data presented here corresponds to the publication \"A Close-Ridge Small-Scale Atmospheric Flow Field and its Influence on Snow Accumulation\" (Gerber et al., 2017), which investigates an eddy-like structure in the vicinity of the Sattelhorn in the Dischma valley (Davos Switzerland)  and its influence on snow accumulation. The dataset contains:    * Alpine3D: Alpine3D snow depth grids (25 m resolution) for two simulations with and without snow redistribution.  * ARPS: 10 ARPS simulations (25 m horizontal resolution) with different model setups (wind direction, wind speed, stability).  * LiDAR: Processed LiDAR PPI (D2_PPI_1h) and RHI (D2_cross_1h) across the valley with a hourly resolution for the period 27 October 2015 01:00 - 29 October 2015c 21:00 (spatial resolution: 25 m).  * meteostations-dischma: Meteorological station data of two meteorological stations in the Dischma valley with 10 minute resolution for the period 28 October 2015 - 30 October 2015.  * TLS: Snow depth change data (m) between 28 October 2015 and 30 October 2015 based on terrestrial laser scans.    For more details about the simulation and observation data, see Gerber et al., 2017.    __Publication__: Gerber et al., 2017: A Close-Ridge Small-Scale Atmospheric Flow Field and its Influence on Snow Accumulation, submitted to JGR - Atmospheres.;Franziska Gerber;Laboratory of Cryospheric Sciences, School of Architecture and Civil Engineering, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland and WSL Institute for Snow and Avalanche Research SLF, Davos, Switzerland;gerberf@slf.ch;LEE-SIDE FLOW FIELD;LIDAR;PREFERENTIAL DEPOSITION;TLS;Open Data Commons Open Database License (ODbL);Eng;MD_CharacterSetCode_utf8;9.852357673 46.700152853;9.935928682 46.700152853;9.935928682 46.739303111;9.852357673 46.739303111;9.852357673 46.700152853;ZIP;https://www.envidat.ch/dataset/10-16904-19;HTTPS;DATASET METADATA;information;http://montblanc.slf.ch/owncloud/index.php/s/9COZ0CRW8r255OL;HTTP;DATASET;download",
-    "group": "envidat",
-    "groups": [
-        {
-            "name": "envidat"
-        }
-    ],
-    "name": "fa681dd6-0f3e-5cb1-8595-16e5d7b5150f",
-    "notes": [
-        "The data presented here corresponds to the publication \"A Close-Ridge Small-Scale Atmospheric Flow Field and its Influence on Snow Accumulation\" (Gerber et al., 2017), which investigates an eddy-like structure in the vicinity of the Sattelhorn in the Dischma valley (Davos Switzerland)  and its influence on snow accumulation. The dataset contains:    * Alpine3D: Alpine3D snow depth grids (25 m resolution) for two simulations with and without snow redistribution.  * ARPS: 10 ARPS simulations (25 m horizontal resolution) with different model setups (wind direction, wind speed, stability).  * LiDAR: Processed LiDAR PPI (D2_PPI_1h) and RHI (D2_cross_1h) across the valley with a hourly resolution for the period 27 October 2015 01:00 - 29 October 2015c 21:00 (spatial resolution: 25 m).  * meteostations-dischma: Meteorological station data of two meteorological stations in the Dischma valley with 10 minute resolution for the period 28 October 2015 - 30 October 2015.  * TLS: Snow depth change data (m) between 28 October 2015 and 30 October 2015 based on terrestrial laser scans.    For more details about the simulation and observation data, see Gerber et al., 2017.    __Publication__: Gerber et al., 2017: A Close-Ridge Small-Scale Atmospheric Flow Field and its Influence on Snow Accumulation, submitted to JGR - Atmospheres."
-    ],
-    "oai_identifier": [
-        "doi:10.16904/19",
-        "oai:envidat.ch:10.16904/19"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "LEE-SIDE FLOW FIELD"
-        },
-        {
-            "name": "LIDAR"
-        },
-        {
-            "name": "PREFERENTIAL DEPOSITION"
-        },
-        {
-            "name": "TLS"
-        }
-    ],
-    "title": [
-        "DISCHMEX - Observations and simulations of the close-ridge small-scale atmospheric flow field and snow accumulation at Sattelhorn, Dischma valley, Davos, Switzerland."
-    ],
-    "url": "http://montblanc.slf.ch/owncloud/index.php/s/9COZ0CRW8r255OL"
-}
\ No newline at end of file
diff --git a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0a13c347-b6ce-5278-ae9f-c53154a04dbc.json b/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0a13c347-b6ce-5278-ae9f-c53154a04dbc.json
deleted file mode 100644
index c7bfe940..00000000
--- a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0a13c347-b6ce-5278-ae9f-c53154a04dbc.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15151/ESRF-ES-95282956",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:oai.datacite.org:14653900",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14653900"
-    ],
-    "PublicationTimestamp": "2021-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2021"
-    ],
-    "Publisher": [
-        "European Synchrotron Radiation Facility"
-    ],
-    "ResourceType": [
-        "Experiment Session"
-    ],
-    "TempCoverageBegin": 63659041199,
-    "TempCoverageEnd": 63659041199,
-    "TemporalCoverage": " point in time : 2018-04-11T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-04-11T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-04-11T11:59:59Z",
-    "author": [
-        "Gerlind SULZENBACHER",
-        "Alain ROUSSEL",
-        "Dehbia CHENA",
-        "Alexis DOGLIANI",
-        "Sana BEN ABDALLAH",
-        "Vincent DELAUZUN"
-    ],
-    "fulltext": "oai:oai.datacite.org:14653900;2018-04-11T13:46:19Z;INIST;INIST.ESRF;3;INIST.ESRF;10.15151/ESRF-ES-95282956;Gerlind SULZENBACHER;Alain ROUSSEL;Vincent DELAUZUN;Sana BEN ABDALLAH;Dehbia CHENA;Alexis DOGLIANI;Structural Biology in Marseille;Macromolecular Crystallography;MX-1986;id30b;European Synchrotron Radiation Facility;2018-04-11;2021;eng;Experiment Session",
-    "group": "esrf",
-    "groups": [
-        {
-            "name": "esrf"
-        }
-    ],
-    "name": "0a13c347-b6ce-5278-ae9f-c53154a04dbc",
-    "oai_identifier": [
-        "oai:oai.datacite.org:14653900"
-    ],
-    "oai_set": [
-        "INIST",
-        "INIST.ESRF"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Macromolecular Crystallography"
-        },
-        {
-            "name": "MX-"
-        },
-        {
-            "name": "idb"
-        }
-    ],
-    "title": [
-        "Structural Biology in Marseille"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0abc61f8-d85f-5d96-b49b-13c4b7ba749c.json b/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0abc61f8-d85f-5d96-b49b-13c4b7ba749c.json
deleted file mode 100644
index 4bcf60c5..00000000
--- a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0abc61f8-d85f-5d96-b49b-13c4b7ba749c.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15151/ESRF-ES-120120588",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:oai.datacite.org:16451698",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:16451698"
-    ],
-    "PublicationTimestamp": "2021-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2021"
-    ],
-    "Publisher": [
-        "European Synchrotron Radiation Facility"
-    ],
-    "ResourceType": [
-        "Experiment Session"
-    ],
-    "TempCoverageBegin": 63672433199,
-    "TempCoverageEnd": 63672433199,
-    "TemporalCoverage": " point in time : 2018-09-13T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-09-13T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-09-13T11:59:59Z",
-    "author": [
-        "Joseph BROCK",
-        "Dirk FAHRENKAMP",
-        "Tatyana SANDALOVA",
-        "Gunter SCHNEIDER",
-        "Renhua SUN"
-    ],
-    "fulltext": "oai:oai.datacite.org:16451698;2018-09-13T08:28:21Z;INIST;INIST.ESRF;3;INIST.ESRF;10.15151/ESRF-ES-120120588;Gunter SCHNEIDER;Joseph BROCK;Dirk FAHRENKAMP;Renhua SUN;Tatyana SANDALOVA;Stockholm BAG;Macromolecular Crystallography;MX-2074;id30a3;European Synchrotron Radiation Facility;2018-09-13;2021;eng;Experiment Session",
-    "group": "esrf",
-    "groups": [
-        {
-            "name": "esrf"
-        }
-    ],
-    "name": "0abc61f8-d85f-5d96-b49b-13c4b7ba749c",
-    "oai_identifier": [
-        "oai:oai.datacite.org:16451698"
-    ],
-    "oai_set": [
-        "INIST",
-        "INIST.ESRF"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Macromolecular Crystallography"
-        },
-        {
-            "name": "MX-"
-        },
-        {
-            "name": "ida"
-        }
-    ],
-    "title": [
-        "Stockholm BAG"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0ac17310-1436-5fa1-95fd-c87cf2f8e8ec.json b/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0ac17310-1436-5fa1-95fd-c87cf2f8e8ec.json
deleted file mode 100644
index 82150035..00000000
--- a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0ac17310-1436-5fa1-95fd-c87cf2f8e8ec.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15151/ESRF-ES-119994641",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:oai.datacite.org:16445558",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:16445558"
-    ],
-    "PublicationTimestamp": "2021-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2021"
-    ],
-    "Publisher": [
-        "European Synchrotron Radiation Facility"
-    ],
-    "ResourceType": [
-        "Experiment Session"
-    ],
-    "TempCoverageBegin": 63672346799,
-    "TempCoverageEnd": 63672346799,
-    "TemporalCoverage": " point in time : 2018-09-12T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-09-12T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-09-12T11:59:59Z",
-    "author": [
-        "Cecile BON"
-    ],
-    "fulltext": "oai:oai.datacite.org:16445558;2018-10-21T03:32:40Z;INIST;INIST.ESRF;3;INIST.ESRF;10.15151/ESRF-ES-119994641;Cecile BON;High-resolution 3D structure determination of Pks13, the condensase of mycolic acids, by single-particle cryo-electron microscopy.;Macromolecular Crystallography;MX-2097;cm01;European Synchrotron Radiation Facility;2018-09-12;2021;eng;Experiment Session",
-    "group": "esrf",
-    "groups": [
-        {
-            "name": "esrf"
-        }
-    ],
-    "name": "0ac17310-1436-5fa1-95fd-c87cf2f8e8ec",
-    "oai_identifier": [
-        "oai:oai.datacite.org:16445558"
-    ],
-    "oai_set": [
-        "INIST",
-        "INIST.ESRF"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Macromolecular Crystallography"
-        },
-        {
-            "name": "MX-"
-        },
-        {
-            "name": "cm"
-        }
-    ],
-    "title": [
-        "High-resolution 3D structure determination of Pks13, the condensase of mycolic acids, by single-particle cryo-electron microscopy."
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0afabeda-ad60-5041-a937-887eacd3279e.json b/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0afabeda-ad60-5041-a937-887eacd3279e.json
deleted file mode 100644
index cd39b104..00000000
--- a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0afabeda-ad60-5041-a937-887eacd3279e.json
+++ /dev/null
@@ -1,95 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15151/ESRF-ES-20306689",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:oai.datacite.org:14364932",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14364932"
-    ],
-    "PublicationTimestamp": "2021-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2021"
-    ],
-    "Publisher": [
-        "European Synchrotron Radiation Facility"
-    ],
-    "ResourceType": [
-        "Experiment Session"
-    ],
-    "TempCoverageBegin": 63622756799,
-    "TempCoverageEnd": 63622756799,
-    "TemporalCoverage": " point in time : 2017-02-15T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2017-02-15T11:59:59Z",
-    "TemporalCoverage:EndDate": "2017-02-15T11:59:59Z",
-    "author": [
-        "Koung hye SEO",
-        "Gordon LEONARD",
-        "Laurent TERRADOT-PIOT",
-        "Markus ALAHUHTA",
-        "Mirek GILSKI",
-        "Paul TUCKER",
-        "Kyriacos PETRATOS",
-        "Wojciech RYPNIEWSKI",
-        "Grzegorz BUJACZ",
-        "Rajaram VENKATESAN",
-        "Gitte MERILAINEN",
-        "St\u00e9phanie MONACO",
-        "Mats OKVIST",
-        "Daniele DE SANCTIS",
-        "Young jun AN",
-        "Olof SVENSSON",
-        "Rik WIERENGA",
-        "Renate GESSMANN",
-        "Kristian KOSKI",
-        "Sun-shin CHA",
-        "Evangelia KAPETANIOU",
-        "Raczynska JOANNA",
-        "Min-Kyu KIM",
-        "Johan TURKENBURG",
-        "Michal SIKORSKI",
-        "Mikko SALIN",
-        "Kon ho LEE",
-        "Katarzyna BANASZAK",
-        "Tatu HAATAJA",
-        "Alexander POPOV",
-        "In-kwon KIM",
-        "Andrew THOMPSON",
-        "Matias GUIJARRO",
-        "Demetres D. LEONIDAS",
-        "Pedro MATIAS"
-    ],
-    "fulltext": "oai:oai.datacite.org:14364932;2018-03-08T08:25:07Z;INIST;INIST.ESRF;3;INIST.ESRF;10.15151/ESRF-ES-20306689;St\u00e9phanie MONACO;Gordon LEONARD;Kyriacos PETRATOS;Matias GUIJARRO;Paul TUCKER;Mikko SALIN;Rik WIERENGA;Alexander POPOV;Michal SIKORSKI;Kon ho LEE;Wojciech RYPNIEWSKI;Young jun AN;Min-Kyu KIM;Koung hye SEO;Katarzyna BANASZAK;Sun-shin CHA;Gitte MERILAINEN;In-kwon KIM;Johan TURKENBURG;Kristian KOSKI;Tatu HAATAJA;Demetres D. LEONIDAS;Markus ALAHUHTA;Pedro MATIAS;Grzegorz BUJACZ;Raczynska JOANNA;Daniele DE SANCTIS;Mirek GILSKI;Laurent TERRADOT-PIOT;Mats OKVIST;Rajaram VENKATESAN;Renate GESSMANN;Andrew THOMPSON;Evangelia KAPETANIOU;Olof SVENSSON;TEST;Macromolecular Crystallography;MX-415;id30b;European Synchrotron Radiation Facility;2017-02-15;2021;eng;Experiment Session",
-    "group": "esrf",
-    "groups": [
-        {
-            "name": "esrf"
-        }
-    ],
-    "name": "0afabeda-ad60-5041-a937-887eacd3279e",
-    "oai_identifier": [
-        "oai:oai.datacite.org:14364932"
-    ],
-    "oai_set": [
-        "INIST",
-        "INIST.ESRF"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Macromolecular Crystallography"
-        },
-        {
-            "name": "MX-"
-        },
-        {
-            "name": "idb"
-        }
-    ],
-    "title": [
-        "TEST"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0b3646b0-ede6-5381-936f-e836680857cc.json b/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0b3646b0-ede6-5381-936f-e836680857cc.json
deleted file mode 100644
index 60b882ed..00000000
--- a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0b3646b0-ede6-5381-936f-e836680857cc.json
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15151/ESRF-ES-122238319",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:oai.datacite.org:16637401",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:16637401"
-    ],
-    "PublicationTimestamp": "2021-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2021"
-    ],
-    "Publisher": [
-        "European Synchrotron Radiation Facility"
-    ],
-    "ResourceType": [
-        "Experiment Session"
-    ],
-    "TempCoverageBegin": 63673210799,
-    "TempCoverageEnd": 63673210799,
-    "TemporalCoverage": " point in time : 2018-09-22T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-09-22T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-09-22T11:59:59Z",
-    "author": [
-        "Peter CLOETENS",
-        "Alexandra JOITA PACUREANU",
-        "Julio Cesar da Silva"
-    ],
-    "fulltext": "oai:oai.datacite.org:16637401;2018-09-22T09:03:18Z;INIST;INIST.ESRF;3;INIST.ESRF;10.15151/ESRF-ES-122238319;Peter CLOETENS;Alexandra JOITA PACUREANU;Julio Cesar da Silva;Holotomography of Al/Si alloys;IH-MA-52;id16a;European Synchrotron Radiation Facility;2018-09-22;2021;eng;Experiment Session",
-    "group": "esrf",
-    "groups": [
-        {
-            "name": "esrf"
-        }
-    ],
-    "name": "0b3646b0-ede6-5381-936f-e836680857cc",
-    "oai_identifier": [
-        "oai:oai.datacite.org:16637401"
-    ],
-    "oai_set": [
-        "INIST",
-        "INIST.ESRF"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "IH-MA-"
-        },
-        {
-            "name": "ida"
-        }
-    ],
-    "title": [
-        "Holotomography of Al/Si alloys"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0b7aac31-d995-5242-88db-865f4a9c9de5.json b/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0b7aac31-d995-5242-88db-865f4a9c9de5.json
deleted file mode 100644
index 35d2550a..00000000
--- a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0b7aac31-d995-5242-88db-865f4a9c9de5.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15151/ESRF-ES-113585769",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:oai.datacite.org:15673445",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:15673445"
-    ],
-    "PublicationTimestamp": "2021-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2021"
-    ],
-    "Publisher": [
-        "European Synchrotron Radiation Facility"
-    ],
-    "ResourceType": [
-        "Experiment Session"
-    ],
-    "TempCoverageBegin": 63668285999,
-    "TempCoverageEnd": 63668285999,
-    "TemporalCoverage": " point in time : 2018-07-27T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-07-27T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-07-27T11:59:59Z",
-    "author": [
-        "Steven DE MEYER",
-        "Frederik VANMEERT",
-        "Koen JANSSENS",
-        "Letizia MONICO",
-        "gert NUYTS"
-    ],
-    "fulltext": "oai:oai.datacite.org:15673445;2018-10-20T00:33:03Z;INIST;INIST.ESRF;3;INIST.ESRF;10.15151/ESRF-ES-113585769;Koen JANSSENS;gert NUYTS;Letizia MONICO;Steven DE MEYER;Frederik VANMEERT;Van Gogh's Sunflowers: The London vs. the Amsterdam version: is there evidence in both of (superficial) photo-induced reduction of Light Sen;Cultural Heritage;HG-129;id21;European Synchrotron Radiation Facility;2018-07-27;2021;eng;Experiment Session",
-    "group": "esrf",
-    "groups": [
-        {
-            "name": "esrf"
-        }
-    ],
-    "name": "0b7aac31-d995-5242-88db-865f4a9c9de5",
-    "oai_identifier": [
-        "oai:oai.datacite.org:15673445"
-    ],
-    "oai_set": [
-        "INIST",
-        "INIST.ESRF"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Cultural Heritage"
-        },
-        {
-            "name": "HG-"
-        },
-        {
-            "name": "id"
-        }
-    ],
-    "title": [
-        "Van Gogh's Sunflowers: The London vs. the Amsterdam version: is there evidence in both of (superficial) photo-induced reduction of Light Sen"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0bc610ab-7222-5f3c-921a-d0508a5367c6.json b/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0bc610ab-7222-5f3c-921a-d0508a5367c6.json
deleted file mode 100644
index 84774ce0..00000000
--- a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0bc610ab-7222-5f3c-921a-d0508a5367c6.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15151/ESRF-ES-109967489",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:oai.datacite.org:15520433",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:15520433"
-    ],
-    "PublicationTimestamp": "2021-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2021"
-    ],
-    "Publisher": [
-        "European Synchrotron Radiation Facility"
-    ],
-    "ResourceType": [
-        "Experiment Session"
-    ],
-    "TempCoverageBegin": 63666903599,
-    "TempCoverageEnd": 63666903599,
-    "TemporalCoverage": " point in time : 2018-07-11T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-07-11T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-07-11T11:59:59Z",
-    "author": [
-        "Murielle SALOME",
-        "Peter CLOETENS",
-        "Sylvain BOHIC",
-        "Alexandra JOITA PACUREANU",
-        "Julio Cesar da Silva",
-        "Yang Yang"
-    ],
-    "fulltext": "oai:oai.datacite.org:15520433;2018-07-11T07:08:00Z;INIST;INIST.ESRF;3;INIST.ESRF;10.15151/ESRF-ES-109967489;Sylvain BOHIC;Yang Yang;Murielle SALOME;Peter CLOETENS;Alexandra JOITA PACUREANU;Julio Cesar da Silva;Zinc distribution in cortical neurons;In-house Life Science;IH-LS-3123;id16a;European Synchrotron Radiation Facility;2018-07-11;2021;eng;Experiment Session",
-    "group": "esrf",
-    "groups": [
-        {
-            "name": "esrf"
-        }
-    ],
-    "name": "0bc610ab-7222-5f3c-921a-d0508a5367c6",
-    "oai_identifier": [
-        "oai:oai.datacite.org:15520433"
-    ],
-    "oai_set": [
-        "INIST",
-        "INIST.ESRF"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "In-house Life Science"
-        },
-        {
-            "name": "IH-LS-"
-        },
-        {
-            "name": "ida"
-        }
-    ],
-    "title": [
-        "Zinc distribution in cortical neurons"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0cf959c5-f3f0-586b-bb26-1732ae053142.json b/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0cf959c5-f3f0-586b-bb26-1732ae053142.json
deleted file mode 100644
index d09d5974..00000000
--- a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0cf959c5-f3f0-586b-bb26-1732ae053142.json
+++ /dev/null
@@ -1,93 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15151/ESRF-ES-95600596",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:oai.datacite.org:14660922",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14660922"
-    ],
-    "PublicationTimestamp": "2021-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2021"
-    ],
-    "Publisher": [
-        "European Synchrotron Radiation Facility"
-    ],
-    "ResourceType": [
-        "Experiment Session"
-    ],
-    "TempCoverageBegin": 63659127599,
-    "TempCoverageEnd": 63659127599,
-    "TemporalCoverage": " point in time : 2018-04-12T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-04-12T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-04-12T11:59:59Z",
-    "author": [
-        "Sigal Yoli NETZER-EL",
-        "Ron DISKIN",
-        "Reuven WIENER",
-        "HUSEIN BOUZ",
-        "Oded LIVNAH",
-        "Nimrod GOLAN",
-        "Fadi GABARA",
-        "Gabriel JAVITT",
-        "Shira COHEN",
-        "Meytal LANDAU",
-        "Adi DAYAN FRENKEL",
-        "Batel DERI",
-        "Michael SPORNY",
-        "juana BANA",
-        "Tami KHAZMA",
-        "Guy LEBEL",
-        "Moshe DESSAU",
-        "Alexander ROUVINSKI",
-        "Shalev GIHAZ",
-        "ARIEL BEN BASSAT",
-        "Dvir HARRIS",
-        "Deborah FASS",
-        "Orly AVRAHAM",
-        "Yael DOMOVICH",
-        "Yizhaq ENGELBERG",
-        "Einav TAYEB-FLIGELMAN",
-        "Barak AKABAYOV",
-        "Stefan ILIC",
-        "Nathan NELSON",
-        "Hadas COHEN-DVASHI",
-        "PRASANTH PADALA",
-        "Daniel KLAIMAN",
-        "Maayan SUISSA"
-    ],
-    "fulltext": "oai:oai.datacite.org:14660922;2018-04-12T06:57:11Z;INIST;INIST.ESRF;3;INIST.ESRF;10.15151/ESRF-ES-95600596;Oded LIVNAH;Yael DOMOVICH;Nathan NELSON;Reuven WIENER;Ron DISKIN;Deborah FASS;Moshe DESSAU;Meytal LANDAU;Tami KHAZMA;Hadas COHEN-DVASHI;Maayan SUISSA;Nimrod GOLAN;Daniel KLAIMAN;Orly AVRAHAM;PRASANTH PADALA;Alexander ROUVINSKI;Shalev GIHAZ;Batel DERI;ARIEL BEN BASSAT;Adi DAYAN FRENKEL;juana BANA;HUSEIN BOUZ;Guy LEBEL;Michael SPORNY;Shira COHEN;Fadi GABARA;Yizhaq ENGELBERG;Stefan ILIC;Sigal Yoli NETZER-EL;Barak AKABAYOV;Dvir HARRIS;Gabriel JAVITT;Einav TAYEB-FLIGELMAN;THE ISRAELI BAG;Macromolecular Crystallography;MX-1997;id30b;European Synchrotron Radiation Facility;2018-04-12;2021;eng;Experiment Session",
-    "group": "esrf",
-    "groups": [
-        {
-            "name": "esrf"
-        }
-    ],
-    "name": "0cf959c5-f3f0-586b-bb26-1732ae053142",
-    "oai_identifier": [
-        "oai:oai.datacite.org:14660922"
-    ],
-    "oai_set": [
-        "INIST",
-        "INIST.ESRF"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Macromolecular Crystallography"
-        },
-        {
-            "name": "MX-"
-        },
-        {
-            "name": "idb"
-        }
-    ],
-    "title": [
-        "THE ISRAELI BAG"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0e2875ce-1aa1-555c-9906-5ed69bb99a33.json b/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0e2875ce-1aa1-555c-9906-5ed69bb99a33.json
deleted file mode 100644
index 9da37835..00000000
--- a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0e2875ce-1aa1-555c-9906-5ed69bb99a33.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15151/ESRF-ES-130412444",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:oai.datacite.org:16866058",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:16866058"
-    ],
-    "PublicationTimestamp": "2021-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2021"
-    ],
-    "Publisher": [
-        "European Synchrotron Radiation Facility"
-    ],
-    "ResourceType": [
-        "Experiment Session"
-    ],
-    "TempCoverageBegin": 63674506799,
-    "TempCoverageEnd": 63674506799,
-    "TemporalCoverage": " point in time : 2018-10-07T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-10-07T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-10-07T11:59:59Z",
-    "author": [
-        "Asfandyar SIKANDAR",
-        "Yvonne CARIUS",
-        "Sebastian ADAM",
-        "Katja URBANSKY",
-        "Denys POGORYELOV",
-        "C. Roy D. LANCASTER",
-        "Oezkan YILDIZ",
-        "Yamila Maren BETZ",
-        "Louris FEITSMA",
-        "Andreas KLEIN",
-        "Jesko KOEHNKE",
-        "Ganna KRASNOSELSKA"
-    ],
-    "fulltext": "oai:oai.datacite.org:16866058;2018-10-07T06:34:38Z;INIST;INIST.ESRF;3;INIST.ESRF;10.15151/ESRF-ES-130412444;C. Roy D. LANCASTER;Jesko KOEHNKE;Oezkan YILDIZ;Andreas KLEIN;Louris FEITSMA;Denys POGORYELOV;Katja URBANSKY;Yamila Maren BETZ;Sebastian ADAM;Yvonne CARIUS;Asfandyar SIKANDAR;Ganna KRASNOSELSKA;FRANKFURT/SAARLAND BAG: ATOMIC MECHANISMS OF ACTION OF MEMBRANE PROTEINS;Macromolecular Crystallography;MX-2070;bm29;European Synchrotron Radiation Facility;2018-10-07;2021;eng;Experiment Session",
-    "group": "esrf",
-    "groups": [
-        {
-            "name": "esrf"
-        }
-    ],
-    "name": "0e2875ce-1aa1-555c-9906-5ed69bb99a33",
-    "oai_identifier": [
-        "oai:oai.datacite.org:16866058"
-    ],
-    "oai_set": [
-        "INIST",
-        "INIST.ESRF"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Macromolecular Crystallography"
-        },
-        {
-            "name": "MX-"
-        },
-        {
-            "name": "bm"
-        }
-    ],
-    "title": [
-        "FRANKFURT/SAARLAND BAG: ATOMIC MECHANISMS OF ACTION OF MEMBRANE PROTEINS"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0e566f45-e9fb-5258-bdec-47a2840749fd.json b/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0e566f45-e9fb-5258-bdec-47a2840749fd.json
deleted file mode 100644
index 7e15e3f2..00000000
--- a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0e566f45-e9fb-5258-bdec-47a2840749fd.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15151/ESRF-ES-118169876",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:oai.datacite.org:16224474",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:16224474"
-    ],
-    "PublicationTimestamp": "2021-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2021"
-    ],
-    "Publisher": [
-        "European Synchrotron Radiation Facility"
-    ],
-    "ResourceType": [
-        "Experiment Session"
-    ],
-    "TempCoverageBegin": 63671655599,
-    "TempCoverageEnd": 63671655599,
-    "TemporalCoverage": " point in time : 2018-09-04T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-09-04T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-09-04T11:59:59Z",
-    "author": [
-        "Jennifer BOOKER",
-        "Altin SULA",
-        "Bonnie Ann WALLACE"
-    ],
-    "fulltext": "oai:oai.datacite.org:16224474;2018-09-04T14:44:51Z;INIST;INIST.ESRF;3;INIST.ESRF;10.15151/ESRF-ES-118169876;Bonnie Ann WALLACE;Altin SULA;Jennifer BOOKER;CryoEM determination of the closed inactivated voltage-gated sodium channel to compare structure in different functional states;Macromolecular Crystallography;MX-2002;cm01;European Synchrotron Radiation Facility;2018-09-04;2021;eng;Experiment Session",
-    "group": "esrf",
-    "groups": [
-        {
-            "name": "esrf"
-        }
-    ],
-    "name": "0e566f45-e9fb-5258-bdec-47a2840749fd",
-    "oai_identifier": [
-        "oai:oai.datacite.org:16224474"
-    ],
-    "oai_set": [
-        "INIST",
-        "INIST.ESRF"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Macromolecular Crystallography"
-        },
-        {
-            "name": "MX-"
-        },
-        {
-            "name": "cm"
-        }
-    ],
-    "title": [
-        "CryoEM determination of the closed inactivated voltage-gated sodium channel to compare structure in different functional states"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0f4abac3-7332-5b20-bc82-c6c504376fa1.json b/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0f4abac3-7332-5b20-bc82-c6c504376fa1.json
deleted file mode 100644
index f91e182c..00000000
--- a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0f4abac3-7332-5b20-bc82-c6c504376fa1.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15151/ESRF-ES-91846265",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:oai.datacite.org:14419362",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14419362"
-    ],
-    "PublicationTimestamp": "2021-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2021"
-    ],
-    "Publisher": [
-        "European Synchrotron Radiation Facility"
-    ],
-    "ResourceType": [
-        "Experiment Session"
-    ],
-    "TempCoverageBegin": 63656539199,
-    "TempCoverageEnd": 63656539199,
-    "TemporalCoverage": " point in time : 2018-03-13T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-03-13T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-03-13T11:59:59Z",
-    "author": [
-        "Kristian KOSKI",
-        "Chandan THAPA",
-        "Abris BENDES",
-        "Yashwanth ASOK",
-        "Kornelia MIKULA",
-        "POOJA POOJA",
-        "Veli-Matti LEPPANEN",
-        "Tarja PARKKINEN",
-        "Johan PAAKKONEN",
-        "Tommi KAJANDER",
-        "Subhadra DALWANI",
-        "Hannes BEYER",
-        "Deborah HARRUS",
-        "Mikko METSA-KETELA",
-        "EZEOGO OBAJI",
-        "Ulla PENTIKAINEN",
-        "Mahesh Kumar TELI",
-        "Sven SOWA",
-        "Leena PENTTINEN"
-    ],
-    "fulltext": "oai:oai.datacite.org:14419362;2018-03-13T09:35:40Z;INIST;INIST.ESRF;3;INIST.ESRF;10.15151/ESRF-ES-91846265;Tommi KAJANDER;Veli-Matti LEPPANEN;Mikko METSA-KETELA;Ulla PENTIKAINEN;Mahesh Kumar TELI;Kornelia MIKULA;Kristian KOSKI;Leena PENTTINEN;POOJA POOJA;Johan PAAKKONEN;Abris BENDES;Sven SOWA;Tarja PARKKINEN;Hannes BEYER;Subhadra DALWANI;Chandan THAPA;Deborah HARRUS;Yashwanth ASOK;EZEOGO OBAJI;Finnish National Protein Crystallography Consortium (FinnProCC);Macromolecular Crystallography;MX-1933;id29;European Synchrotron Radiation Facility;2018-03-13;2021;eng;Experiment Session",
-    "group": "esrf",
-    "groups": [
-        {
-            "name": "esrf"
-        }
-    ],
-    "name": "0f4abac3-7332-5b20-bc82-c6c504376fa1",
-    "oai_identifier": [
-        "oai:oai.datacite.org:14419362"
-    ],
-    "oai_set": [
-        "INIST",
-        "INIST.ESRF"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Macromolecular Crystallography"
-        },
-        {
-            "name": "MX-"
-        },
-        {
-            "name": "id"
-        }
-    ],
-    "title": [
-        "Finnish National Protein Crystallography Consortium (FinnProCC)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0f79d477-f9ff-52a4-b7ef-193ef5d97546.json b/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0f79d477-f9ff-52a4-b7ef-193ef5d97546.json
deleted file mode 100644
index dd5b1843..00000000
--- a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0f79d477-f9ff-52a4-b7ef-193ef5d97546.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15151/ESRF-ES-67159411",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:oai.datacite.org:14699236",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14699236"
-    ],
-    "PublicationTimestamp": "2021-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2021"
-    ],
-    "Publisher": [
-        "European Synchrotron Radiation Facility"
-    ],
-    "ResourceType": [
-        "Experiment Session"
-    ],
-    "TempCoverageBegin": 63646343999,
-    "TempCoverageEnd": 63646343999,
-    "TemporalCoverage": " point in time : 2017-11-15T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2017-11-15T11:59:59Z",
-    "TemporalCoverage:EndDate": "2017-11-15T11:59:59Z",
-    "author": [
-        "Nathalie COLLOCH",
-        "stephane PLANCQUEEL",
-        "SYLVIE NESSLER",
-        "Pierre BARRAUD",
-        "Gilles PHAN",
-        "Celine CHEN",
-        "Lea KHOURY",
-        "Thierry PRANGE",
-        "Noelia BERNARDO GARCIA",
-        "Julien HENRI",
-        "Christian GALICIA",
-        "Dominique DURAND",
-        "Karim HOUSSEINI",
-        "Allegra MBOUKOU",
-        "Clement MADRU",
-        "yann FERRANDEZ",
-        "Stephanie OERUM",
-        "Simon VEYRON"
-    ],
-    "fulltext": "oai:oai.datacite.org:14699236;2018-04-18T07:19:21Z;INIST;INIST.ESRF;3;INIST.ESRF;10.15151/ESRF-ES-67159411;Gilles PHAN;SYLVIE NESSLER;Nathalie COLLOCH;Stephanie OERUM;stephane PLANCQUEEL;Allegra MBOUKOU;Celine CHEN;Thierry PRANGE;Christian GALICIA;Noelia BERNARDO GARCIA;Karim HOUSSEINI;yann FERRANDEZ;Clement MADRU;Pierre BARRAUD;Julien HENRI;Lea KHOURY;Dominique DURAND;Simon VEYRON;BAG Paris Rive-Gauche;Macromolecular Crystallography;MX-1940;id30a3;European Synchrotron Radiation Facility;2017-11-15;2021;eng;Experiment Session",
-    "group": "esrf",
-    "groups": [
-        {
-            "name": "esrf"
-        }
-    ],
-    "name": "0f79d477-f9ff-52a4-b7ef-193ef5d97546",
-    "oai_identifier": [
-        "oai:oai.datacite.org:14699236"
-    ],
-    "oai_set": [
-        "INIST",
-        "INIST.ESRF"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Macromolecular Crystallography"
-        },
-        {
-            "name": "MX-"
-        },
-        {
-            "name": "ida"
-        }
-    ],
-    "title": [
-        "BAG Paris Rive-Gauche"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0f7f1d83-6cc6-5469-99b1-bb1c3c774b78.json b/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0f7f1d83-6cc6-5469-99b1-bb1c3c774b78.json
deleted file mode 100644
index e33caf45..00000000
--- a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/0f7f1d83-6cc6-5469-99b1-bb1c3c774b78.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15151/ESRF-ES-133989980",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:oai.datacite.org:17061917",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17061917"
-    ],
-    "PublicationTimestamp": "2021-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2021"
-    ],
-    "Publisher": [
-        "European Synchrotron Radiation Facility"
-    ],
-    "ResourceType": [
-        "Experiment Session"
-    ],
-    "TempCoverageBegin": 63675975599,
-    "TempCoverageEnd": 63675975599,
-    "TemporalCoverage": " point in time : 2018-10-24T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-10-24T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-10-24T11:59:59Z",
-    "author": [
-        "Leonhard KICK",
-        "Andreas BRACHER",
-        "Florent DELHOMMEL",
-        "Krzysztof ZAK",
-        "Lopez ABRAHAM",
-        "PRADEEP MANDAL",
-        "Christopher SCHEIDLER"
-    ],
-    "fulltext": "oai:oai.datacite.org:17061917;2019-01-11T13:30:40Z;INIST;INIST.ESRF;3;INIST.ESRF;10.15151/ESRF-ES-133989980;Andreas BRACHER;PRADEEP MANDAL;Krzysztof ZAK;Leonhard KICK;Florent DELHOMMEL;Lopez ABRAHAM;Christopher SCHEIDLER;Munich Crystallography BAG;Macromolecular Crystallography;MX-2088;id30a1;European Synchrotron Radiation Facility;2018-10-24;2021;eng;Experiment Session",
-    "group": "esrf",
-    "groups": [
-        {
-            "name": "esrf"
-        }
-    ],
-    "name": "0f7f1d83-6cc6-5469-99b1-bb1c3c774b78",
-    "oai_identifier": [
-        "oai:oai.datacite.org:17061917"
-    ],
-    "oai_set": [
-        "INIST",
-        "INIST.ESRF"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Macromolecular Crystallography"
-        },
-        {
-            "name": "MX-"
-        },
-        {
-            "name": "ida"
-        }
-    ],
-    "title": [
-        "Munich Crystallography BAG"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1a349d46-fe8b-5c30-aed8-d86ee35523e3.json b/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1a349d46-fe8b-5c30-aed8-d86ee35523e3.json
deleted file mode 100644
index b0f34351..00000000
--- a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1a349d46-fe8b-5c30-aed8-d86ee35523e3.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15151/ESRF-ES-105564349",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:oai.datacite.org:15254064",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:15254064"
-    ],
-    "PublicationTimestamp": "2021-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2021"
-    ],
-    "Publisher": [
-        "European Synchrotron Radiation Facility"
-    ],
-    "ResourceType": [
-        "Experiment Session"
-    ],
-    "TempCoverageBegin": 63664657199,
-    "TempCoverageEnd": 63664657199,
-    "TemporalCoverage": " point in time : 2018-06-15T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-06-15T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-06-15T11:59:59Z",
-    "author": [
-        "Evgenii OSIPOV",
-        "Sergio MARTINEZ",
-        "Ramon VAN DEN BOS",
-        "Matthieu ZERONIAN",
-        "Gopinath MURUGANANDAM",
-        "Maru\u0161a PROLIC KALINSEK",
-        "Fredj BEN BDIRA",
-        "Sergei STRELKOV",
-        "Nikolas CAPRA",
-        "Stephen WEEKS",
-        "Bert JANSSEN",
-        "Lucas CHATAIGNER",
-        "Koen VERSCHUEREN",
-        "Luping PANG",
-        "Viviana NEVIANI",
-        "Steff DE GRAEF",
-        "GABRIELA GARCIA RODRIGUEZ",
-        "Kenneth VERSTRAETE",
-        "Wouter BEUGELINK",
-        "Anamika GAUR",
-        "Tatjana HEIDEBRECHT-LINNEMANN",
-        "Andy-Mark THUNNISSEN"
-    ],
-    "fulltext": "oai:oai.datacite.org:15254064;2018-11-02T04:02:53Z;INIST;INIST.ESRF;3;INIST.ESRF;10.15151/ESRF-ES-105564349;Andy-Mark THUNNISSEN;Sergei STRELKOV;Bert JANSSEN;Ramon VAN DEN BOS;Stephen WEEKS;Anamika GAUR;Matthieu ZERONIAN;Wouter BEUGELINK;Tatjana HEIDEBRECHT-LINNEMANN;Koen VERSCHUEREN;Kenneth VERSTRAETE;Nikolas CAPRA;Viviana NEVIANI;Steff DE GRAEF;Fredj BEN BDIRA;Maru\u0161a PROLIC KALINSEK;Gopinath MURUGANANDAM;Sergio MARTINEZ;Luping PANG;GABRIELA GARCIA RODRIGUEZ;Evgenii OSIPOV;Lucas CHATAIGNER;Holland-Belgium BAG;Macromolecular Crystallography;MX-1993;id23-2;European Synchrotron Radiation Facility;2018-06-15;2021;eng;Experiment Session",
-    "group": "esrf",
-    "groups": [
-        {
-            "name": "esrf"
-        }
-    ],
-    "name": "1a349d46-fe8b-5c30-aed8-d86ee35523e3",
-    "oai_identifier": [
-        "oai:oai.datacite.org:15254064"
-    ],
-    "oai_set": [
-        "INIST",
-        "INIST.ESRF"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Macromolecular Crystallography"
-        },
-        {
-            "name": "MX-"
-        },
-        {
-            "name": "id-"
-        }
-    ],
-    "title": [
-        "Holland-Belgium BAG"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1aafa278-18af-5ad8-b306-44a365174556.json b/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1aafa278-18af-5ad8-b306-44a365174556.json
deleted file mode 100644
index c401a586..00000000
--- a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1aafa278-18af-5ad8-b306-44a365174556.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15151/ESRF-ES-96318785",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:oai.datacite.org:14680598",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14680598"
-    ],
-    "PublicationTimestamp": "2021-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2021"
-    ],
-    "Publisher": [
-        "European Synchrotron Radiation Facility"
-    ],
-    "ResourceType": [
-        "Experiment Session"
-    ],
-    "TempCoverageBegin": 63659300399,
-    "TempCoverageEnd": 63659300399,
-    "TemporalCoverage": " point in time : 2018-04-14T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-04-14T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-04-14T11:59:59Z",
-    "author": [
-        "Lars EIDE",
-        "Hanna-Kirsti Schroder LEIROS",
-        "Ute KRENGEL",
-        "Bjorn DALHUS",
-        "Matthias AMANN",
-        "Mikkel killingmoe CHRISTENSEN",
-        "Ulli ROTHWEILER",
-        "Bastien BISSARO",
-        "bjorge WESTERENG",
-        "AASMUND ROEHR KJENDSETH",
-        "Josefine Eilsoe NIELSEN"
-    ],
-    "fulltext": "oai:oai.datacite.org:14680598;2018-04-14T07:05:32Z;INIST;INIST.ESRF;3;INIST.ESRF;10.15151/ESRF-ES-96318785;Ute KRENGEL;Bjorn DALHUS;Hanna-Kirsti Schroder LEIROS;Ulli ROTHWEILER;Matthias AMANN;Bastien BISSARO;Josefine Eilsoe NIELSEN;Mikkel killingmoe CHRISTENSEN;bjorge WESTERENG;AASMUND ROEHR KJENDSETH;Lars EIDE;NORWAY BAG;Macromolecular Crystallography;MX-1996;bm29;European Synchrotron Radiation Facility;2018-04-14;2021;eng;Experiment Session",
-    "group": "esrf",
-    "groups": [
-        {
-            "name": "esrf"
-        }
-    ],
-    "name": "1aafa278-18af-5ad8-b306-44a365174556",
-    "oai_identifier": [
-        "oai:oai.datacite.org:14680598"
-    ],
-    "oai_set": [
-        "INIST",
-        "INIST.ESRF"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Macromolecular Crystallography"
-        },
-        {
-            "name": "MX-"
-        },
-        {
-            "name": "bm"
-        }
-    ],
-    "title": [
-        "NORWAY BAG"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1b9e563c-384b-5a21-9100-18fe71700ff0.json b/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1b9e563c-384b-5a21-9100-18fe71700ff0.json
deleted file mode 100644
index a665e61d..00000000
--- a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1b9e563c-384b-5a21-9100-18fe71700ff0.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15151/ESRF-ES-107950358",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:oai.datacite.org:15396302",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:15396302"
-    ],
-    "PublicationTimestamp": "2021-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2021"
-    ],
-    "Publisher": [
-        "European Synchrotron Radiation Facility"
-    ],
-    "ResourceType": [
-        "Experiment Session"
-    ],
-    "TempCoverageBegin": 63666039599,
-    "TempCoverageEnd": 63666039599,
-    "TemporalCoverage": " point in time : 2018-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-07-01T11:59:59Z",
-    "author": [
-        "Peter CLOETENS",
-        "Yang Yang",
-        "Alexandra JOITA PACUREANU",
-        "Murielle SALOME"
-    ],
-    "fulltext": "oai:oai.datacite.org:15396302;2019-01-14T17:00:38Z;INIST;INIST.ESRF;3;INIST.ESRF;10.15151/ESRF-ES-107950358;Alexandra JOITA PACUREANU;Yang Yang;Murielle SALOME;Peter CLOETENS;Accelerating connectomics with X-ray holographic nano-tomography;In-house Life Science;IH-LS-3121;id16a;European Synchrotron Radiation Facility;2018-07-01;2021;eng;Experiment Session",
-    "group": "esrf",
-    "groups": [
-        {
-            "name": "esrf"
-        }
-    ],
-    "name": "1b9e563c-384b-5a21-9100-18fe71700ff0",
-    "oai_identifier": [
-        "oai:oai.datacite.org:15396302"
-    ],
-    "oai_set": [
-        "INIST",
-        "INIST.ESRF"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "In-house Life Science"
-        },
-        {
-            "name": "IH-LS-"
-        },
-        {
-            "name": "ida"
-        }
-    ],
-    "title": [
-        "Accelerating connectomics with X-ray holographic nano-tomography"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1c3c5b70-a8b2-5df4-964a-1481dcc33337.json b/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1c3c5b70-a8b2-5df4-964a-1481dcc33337.json
deleted file mode 100644
index 66df52cd..00000000
--- a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1c3c5b70-a8b2-5df4-964a-1481dcc33337.json
+++ /dev/null
@@ -1,95 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15151/ESRF-ES-131846968",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:oai.datacite.org:17004052",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17004052"
-    ],
-    "PublicationTimestamp": "2021-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2021"
-    ],
-    "Publisher": [
-        "European Synchrotron Radiation Facility"
-    ],
-    "ResourceType": [
-        "Experiment Session"
-    ],
-    "TempCoverageBegin": 63675543599,
-    "TempCoverageEnd": 63675543599,
-    "TemporalCoverage": " point in time : 2018-10-19T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-10-19T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-10-19T11:59:59Z",
-    "author": [
-        "Sebastien VIOLOT",
-        "Stephanie RAVAUD",
-        "Patrice GOUET",
-        "Laurent TERRADOT-PIOT",
-        "Christophe GUILLON",
-        "Thanh NGUYEN",
-        "Laurane BERNELIN",
-        "virginie GUEGUEN-CHAIGNON",
-        "lionel BALLUT",
-        "Lionel MOUREY",
-        "Sylvain VALLET",
-        "Vincent CHAPTAL",
-        "JEAN-DENIS PEDELACQ",
-        "Dhoha KORSIA",
-        "Sabine GAVALDA",
-        "Adriana Erica MIELE",
-        "Nathanael MARRIE",
-        "Samuel TRANIER",
-        "Mathieu LONG",
-        "Frank GONDELAUD",
-        "Brice KAUFFMANN",
-        "PRADEEP MANDAL",
-        "Margot NIORE",
-        "Virginie NAHOUM",
-        "Frederic GALISSON",
-        "Benjamin BOURGEY",
-        "Lea CONCHOU",
-        "Coralie CARIVENC",
-        "Valerie GUILLET",
-        "Gianluca CIOCI",
-        "Yasmina GRIMOIRE",
-        "Celia ROUX",
-        "Laurent MAVEYRAUD",
-        "Marine LOSFELT",
-        "Francesca FIORINI"
-    ],
-    "fulltext": "oai:oai.datacite.org:17004052;2018-10-23T19:32:05Z;INIST;INIST.ESRF;3;INIST.ESRF;10.15151/ESRF-ES-131846968;Sebastien VIOLOT;Vincent CHAPTAL;Patrice GOUET;Laurent TERRADOT-PIOT;Valerie GUILLET;Lionel MOUREY;Stephanie RAVAUD;Brice KAUFFMANN;JEAN-DENIS PEDELACQ;Coralie CARIVENC;Sylvain VALLET;Sabine GAVALDA;Celia ROUX;lionel BALLUT;Thanh NGUYEN;Samuel TRANIER;Virginie NAHOUM;Laurane BERNELIN;PRADEEP MANDAL;Margot NIORE;Laurent MAVEYRAUD;Yasmina GRIMOIRE;Frank GONDELAUD;Mathieu LONG;Dhoha KORSIA;Gianluca CIOCI;Nathanael MARRIE;Christophe GUILLON;virginie GUEGUEN-CHAIGNON;Adriana Erica MIELE;Francesca FIORINI;Marine LOSFELT;Lea CONCHOU;Benjamin BOURGEY;Frederic GALISSON;Macromolecular Crystallography in Lyon/Toulouse/Bordeaux\r\nIBCP-MMSB / IPBS / IECB IBGC CBMN;Macromolecular Crystallography;MX-1979;bm29;European Synchrotron Radiation Facility;2018-10-19;2021;eng;Experiment Session",
-    "group": "esrf",
-    "groups": [
-        {
-            "name": "esrf"
-        }
-    ],
-    "name": "1c3c5b70-a8b2-5df4-964a-1481dcc33337",
-    "oai_identifier": [
-        "oai:oai.datacite.org:17004052"
-    ],
-    "oai_set": [
-        "INIST",
-        "INIST.ESRF"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Macromolecular Crystallography"
-        },
-        {
-            "name": "MX-"
-        },
-        {
-            "name": "bm"
-        }
-    ],
-    "title": [
-        "Macromolecular Crystallography in Lyon/Toulouse/Bordeaux\r\nIBCP-MMSB / IPBS / IECB IBGC CBMN"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1cbbb189-c633-5596-bcab-0ff1291d271b.json b/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1cbbb189-c633-5596-bcab-0ff1291d271b.json
deleted file mode 100644
index c967c2ab..00000000
--- a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1cbbb189-c633-5596-bcab-0ff1291d271b.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15151/ESRF-ES-164574620",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:oai.datacite.org:17755800",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17755800"
-    ],
-    "PublicationTimestamp": "2021-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2021"
-    ],
-    "Publisher": [
-        "European Synchrotron Radiation Facility"
-    ],
-    "ResourceType": [
-        "Experiment Session"
-    ],
-    "TempCoverageBegin": 63679953599,
-    "TempCoverageEnd": 63679953599,
-    "TemporalCoverage": " point in time : 2018-12-09T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-12-09T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-12-09T11:59:59Z",
-    "author": [
-        "Murielle SALOME",
-        "Caroline BISSARDON",
-        "Peter CLOETENS",
-        "Sylvain BOHIC",
-        "Alexandra JOITA PACUREANU",
-        "Julio Cesar da Silva",
-        "Yang Yang"
-    ],
-    "fulltext": "oai:oai.datacite.org:17755800;2018-12-10T16:27:17Z;INIST;INIST.ESRF;3;INIST.ESRF;10.15151/ESRF-ES-164574620;Sylvain BOHIC;Caroline BISSARDON;Julio Cesar da Silva;Yang Yang;Murielle SALOME;Peter CLOETENS;Alexandra JOITA PACUREANU;Cryo-correlative light X-ray nanoimaging on PC-3 cells;In-house Life Science;IH-LS-3202;id16a;European Synchrotron Radiation Facility;2018-12-09;2021;eng;Experiment Session",
-    "group": "esrf",
-    "groups": [
-        {
-            "name": "esrf"
-        }
-    ],
-    "name": "1cbbb189-c633-5596-bcab-0ff1291d271b",
-    "oai_identifier": [
-        "oai:oai.datacite.org:17755800"
-    ],
-    "oai_set": [
-        "INIST",
-        "INIST.ESRF"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "In-house Life Science"
-        },
-        {
-            "name": "IH-LS-"
-        },
-        {
-            "name": "ida"
-        }
-    ],
-    "title": [
-        "Cryo-correlative light X-ray nanoimaging on PC-3 cells"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1de29aef-c2d6-52cd-9d38-d0e3fc6424d6.json b/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1de29aef-c2d6-52cd-9d38-d0e3fc6424d6.json
deleted file mode 100644
index 08807fce..00000000
--- a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1de29aef-c2d6-52cd-9d38-d0e3fc6424d6.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15151/ESRF-ES-74836812",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:oai.datacite.org:14625439",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14625439"
-    ],
-    "PublicationTimestamp": "2021-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2021"
-    ],
-    "Publisher": [
-        "European Synchrotron Radiation Facility"
-    ],
-    "ResourceType": [
-        "Experiment Session"
-    ],
-    "TempCoverageBegin": 63648331199,
-    "TempCoverageEnd": 63648331199,
-    "TemporalCoverage": " point in time : 2017-12-08T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2017-12-08T11:59:59Z",
-    "TemporalCoverage:EndDate": "2017-12-08T11:59:59Z",
-    "author": [
-        "Nathalie COLLOCH",
-        "stephane PLANCQUEEL",
-        "SYLVIE NESSLER",
-        "Lea KHOURY",
-        "Gilles PHAN",
-        "Celine CHEN",
-        "Thierry PRANGE",
-        "Noelia BERNARDO GARCIA",
-        "Julien HENRI",
-        "Christian GALICIA",
-        "Dominique DURAND",
-        "Karim HOUSSEINI",
-        "Allegra MBOUKOU",
-        "Pierre BARRAUD",
-        "yann FERRANDEZ",
-        "Stephanie OERUM",
-        "Simon VEYRON"
-    ],
-    "fulltext": "oai:oai.datacite.org:14625439;2018-11-26T03:01:48Z;INIST;INIST.ESRF;3;INIST.ESRF;10.15151/ESRF-ES-74836812;Gilles PHAN;Nathalie COLLOCH;SYLVIE NESSLER;Stephanie OERUM;stephane PLANCQUEEL;Celine CHEN;Allegra MBOUKOU;yann FERRANDEZ;Thierry PRANGE;Pierre BARRAUD;Christian GALICIA;Julien HENRI;Lea KHOURY;Noelia BERNARDO GARCIA;Karim HOUSSEINI;Simon VEYRON;Dominique DURAND;BAG Paris Rive-Gauche;Macromolecular Crystallography;MX-1940;bm29;European Synchrotron Radiation Facility;2017-12-08;2021;eng;Experiment Session",
-    "group": "esrf",
-    "groups": [
-        {
-            "name": "esrf"
-        }
-    ],
-    "name": "1de29aef-c2d6-52cd-9d38-d0e3fc6424d6",
-    "oai_identifier": [
-        "oai:oai.datacite.org:14625439"
-    ],
-    "oai_set": [
-        "INIST",
-        "INIST.ESRF"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Macromolecular Crystallography"
-        },
-        {
-            "name": "MX-"
-        },
-        {
-            "name": "bm"
-        }
-    ],
-    "title": [
-        "BAG Paris Rive-Gauche"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1e8472fa-ee14-5e33-9678-41b36d0076de.json b/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1e8472fa-ee14-5e33-9678-41b36d0076de.json
deleted file mode 100644
index 234d169e..00000000
--- a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1e8472fa-ee14-5e33-9678-41b36d0076de.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15151/ESRF-ES-131022975",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:oai.datacite.org:16981699",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:16981699"
-    ],
-    "PublicationTimestamp": "2021-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2021"
-    ],
-    "Publisher": [
-        "European Synchrotron Radiation Facility"
-    ],
-    "ResourceType": [
-        "Experiment Session"
-    ],
-    "TempCoverageBegin": 63675370799,
-    "TempCoverageEnd": 63675370799,
-    "TemporalCoverage": " point in time : 2018-10-17T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-10-17T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-10-17T11:59:59Z",
-    "author": [
-        "Montserrat SOLER LOPEZ",
-        "Anais CHRETIEN",
-        "Irina GUTSCHE",
-        "Matthew JESSOP",
-        "Melissa SAIDI",
-        "Gabriele GIACHIN",
-        "Michael HONS",
-        "Maria BACIA",
-        "Samira ACAJJAOUI"
-    ],
-    "fulltext": "oai:oai.datacite.org:16981699;2018-10-16T23:03:28Z;INIST;INIST.ESRF;3;INIST.ESRF;10.15151/ESRF-ES-131022975;Montserrat SOLER LOPEZ;Irina GUTSCHE;Matthew JESSOP;Gabriele GIACHIN;Melissa SAIDI;Anais CHRETIEN;Samira ACAJJAOUI;Maria BACIA;Michael HONS;3D reconstruction of the ACAD9:ECSIT complex at high resolution;Macromolecular Crystallography;MX-2142;cm01;European Synchrotron Radiation Facility;2018-10-17;2021;eng;Experiment Session",
-    "group": "esrf",
-    "groups": [
-        {
-            "name": "esrf"
-        }
-    ],
-    "name": "1e8472fa-ee14-5e33-9678-41b36d0076de",
-    "oai_identifier": [
-        "oai:oai.datacite.org:16981699"
-    ],
-    "oai_set": [
-        "INIST",
-        "INIST.ESRF"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Macromolecular Crystallography"
-        },
-        {
-            "name": "MX-"
-        },
-        {
-            "name": "cm"
-        }
-    ],
-    "title": [
-        "3D reconstruction of the ACAD9:ECSIT complex at high resolution"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1e98de60-4408-5e6b-9005-8991c076dfa8.json b/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1e98de60-4408-5e6b-9005-8991c076dfa8.json
deleted file mode 100644
index 20740f05..00000000
--- a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1e98de60-4408-5e6b-9005-8991c076dfa8.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15151/ESRF-ES-100444815",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:oai.datacite.org:15023034",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:15023034"
-    ],
-    "PublicationTimestamp": "2021-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2021"
-    ],
-    "Publisher": [
-        "European Synchrotron Radiation Facility"
-    ],
-    "ResourceType": [
-        "Experiment Session"
-    ],
-    "TempCoverageBegin": 63661633199,
-    "TempCoverageEnd": 63661633199,
-    "TemporalCoverage": " point in time : 2018-05-11T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-05-11T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-05-11T11:59:59Z",
-    "author": [
-        "Minmin YU",
-        "Christina GLADKOVA",
-        "Malte GERSCH",
-        "Marc FIEDLER",
-        "Madhanagopal ANANDAPADAMANABAN",
-        "Claire DICKSON",
-        "Roger WILLIAMS",
-        "Jonathan PRUNEDA"
-    ],
-    "fulltext": "oai:oai.datacite.org:15023034;2018-10-19T07:02:56Z;INIST;INIST.ESRF;3;INIST.ESRF;10.15151/ESRF-ES-100444815;Roger WILLIAMS;Marc FIEDLER;Minmin YU;Jonathan PRUNEDA;Christina GLADKOVA;Claire DICKSON;Malte GERSCH;Madhanagopal ANANDAPADAMANABAN;Cambridge MRC Block allocation;Macromolecular Crystallography;MX-1936;id23-1;European Synchrotron Radiation Facility;2018-05-11;2021;eng;Experiment Session",
-    "group": "esrf",
-    "groups": [
-        {
-            "name": "esrf"
-        }
-    ],
-    "name": "1e98de60-4408-5e6b-9005-8991c076dfa8",
-    "oai_identifier": [
-        "oai:oai.datacite.org:15023034"
-    ],
-    "oai_set": [
-        "INIST",
-        "INIST.ESRF"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Macromolecular Crystallography"
-        },
-        {
-            "name": "MX-"
-        },
-        {
-            "name": "id-"
-        }
-    ],
-    "title": [
-        "Cambridge MRC Block allocation"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1ec57af4-3930-56d7-b8d5-b1d7a80b3ece.json b/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1ec57af4-3930-56d7-b8d5-b1d7a80b3ece.json
deleted file mode 100644
index 23eaa0d2..00000000
--- a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1ec57af4-3930-56d7-b8d5-b1d7a80b3ece.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15151/ESRF-ES-154128138",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:oai.datacite.org:17555631",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17555631"
-    ],
-    "PublicationTimestamp": "2021-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2021"
-    ],
-    "Publisher": [
-        "European Synchrotron Radiation Facility"
-    ],
-    "ResourceType": [
-        "Experiment Session"
-    ],
-    "TempCoverageBegin": 63678225599,
-    "TempCoverageEnd": 63678225599,
-    "TemporalCoverage": " point in time : 2018-11-19T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-11-19T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-11-19T11:59:59Z",
-    "author": [
-        "Marie SKEPO",
-        "Sandeep CHAKANE",
-        "Stephanie JEPHTHAH"
-    ],
-    "fulltext": "oai:oai.datacite.org:17555631;2018-11-19T08:20:58Z;INIST;INIST.ESRF;3;INIST.ESRF;10.15151/ESRF-ES-154128138;Marie SKEPO;Stephanie JEPHTHAH;Sandeep CHAKANE;To understand the antimicrobial activity of the salivary protein Histatin 5;Macromolecular Crystallography;MX-2141;bm29;European Synchrotron Radiation Facility;2018-11-19;2021;eng;Experiment Session",
-    "group": "esrf",
-    "groups": [
-        {
-            "name": "esrf"
-        }
-    ],
-    "name": "1ec57af4-3930-56d7-b8d5-b1d7a80b3ece",
-    "oai_identifier": [
-        "oai:oai.datacite.org:17555631"
-    ],
-    "oai_set": [
-        "INIST",
-        "INIST.ESRF"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Macromolecular Crystallography"
-        },
-        {
-            "name": "MX-"
-        },
-        {
-            "name": "bm"
-        }
-    ],
-    "title": [
-        "To understand the antimicrobial activity of the salivary protein Histatin 5"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1f4f3bef-71eb-5297-bd18-a162932f3454.json b/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1f4f3bef-71eb-5297-bd18-a162932f3454.json
deleted file mode 100644
index c44997cb..00000000
--- a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1f4f3bef-71eb-5297-bd18-a162932f3454.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15151/ESRF-ES-155242587",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:oai.datacite.org:17576195",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17576195"
-    ],
-    "PublicationTimestamp": "2021-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2021"
-    ],
-    "Publisher": [
-        "European Synchrotron Radiation Facility"
-    ],
-    "ResourceType": [
-        "Experiment Session"
-    ],
-    "TempCoverageBegin": 63678398399,
-    "TempCoverageEnd": 63678398399,
-    "TemporalCoverage": " point in time : 2018-11-21T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-11-21T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-11-21T11:59:59Z",
-    "author": [
-        "Arvind Kumar GUPTA",
-        "Pankaj Kumar MADHESHIYA",
-        "PRAGYAN PARIMITA RATH",
-        "Nishant Kumar VARSHNEY",
-        "Rahul SHARMA",
-        "Ajay Kumar SAXENA",
-        "Eswar Reddy MADDI",
-        "Deepak Thankappan NAIR",
-        "Barnali CHAUDHURI",
-        "Kumari JYOTI",
-        "Vengadesan KRISHNAN",
-        "AMAR DEEP",
-        "Beena KRISHNAN",
-        "Supreeti MAHAJAN",
-        "VENKATAREDDY DADIREDDY",
-        "Yogita SHARMA",
-        "Komal CHOUKATE",
-        "RUCHIR CHANDRAKANT BOBDE",
-        "Garima VERMA",
-        "Poonam DHANKHAR",
-        "Aravind PENMATSA",
-        "Dileep VASUDEVAN",
-        "Shruti MATHUR",
-        "Rashika SINGH",
-        "NEHA SAINI"
-    ],
-    "fulltext": "oai:oai.datacite.org:17576195;2018-11-21T11:20:31Z;INIST;INIST.ESRF;3;INIST.ESRF;10.15151/ESRF-ES-155242587;Deepak Thankappan NAIR;Beena KRISHNAN;Dileep VASUDEVAN;Poonam DHANKHAR;Ajay Kumar SAXENA;Yogita SHARMA;Kumari JYOTI;Barnali CHAUDHURI;PRAGYAN PARIMITA RATH;RUCHIR CHANDRAKANT BOBDE;Pankaj Kumar MADHESHIYA;Shruti MATHUR;Vengadesan KRISHNAN;Aravind PENMATSA;Rahul SHARMA;Nishant Kumar VARSHNEY;Rashika SINGH;VENKATAREDDY DADIREDDY;Arvind Kumar GUPTA;Komal CHOUKATE;Eswar Reddy MADDI;Garima VERMA;Supreeti MAHAJAN;AMAR DEEP;NEHA SAINI;Structural Biology of Macromolecules and Macromolecular complexes from India;Macromolecular Crystallography;MX-2077;id30b;European Synchrotron Radiation Facility;2018-11-21;2021;eng;Experiment Session",
-    "group": "esrf",
-    "groups": [
-        {
-            "name": "esrf"
-        }
-    ],
-    "name": "1f4f3bef-71eb-5297-bd18-a162932f3454",
-    "oai_identifier": [
-        "oai:oai.datacite.org:17576195"
-    ],
-    "oai_set": [
-        "INIST",
-        "INIST.ESRF"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Macromolecular Crystallography"
-        },
-        {
-            "name": "MX-"
-        },
-        {
-            "name": "idb"
-        }
-    ],
-    "title": [
-        "Structural Biology of Macromolecules and Macromolecular complexes from India"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1f7d0109-08aa-5f0a-871d-9306c8f5eb54.json b/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1f7d0109-08aa-5f0a-871d-9306c8f5eb54.json
deleted file mode 100644
index 435d7790..00000000
--- a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1f7d0109-08aa-5f0a-871d-9306c8f5eb54.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15151/ESRF-ES-133417381",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:oai.datacite.org:17029860",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:17029860"
-    ],
-    "PublicationTimestamp": "2021-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2021"
-    ],
-    "Publisher": [
-        "European Synchrotron Radiation Facility"
-    ],
-    "ResourceType": [
-        "Experiment Session"
-    ],
-    "TempCoverageBegin": 63675889199,
-    "TempCoverageEnd": 63675889199,
-    "TemporalCoverage": " point in time : 2018-10-23T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-10-23T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-10-23T11:59:59Z",
-    "author": [
-        "Peter CLOETENS",
-        "Yang Yang",
-        "Sylvain BOHIC",
-        "Murielle SALOME"
-    ],
-    "fulltext": "oai:oai.datacite.org:17029860;2018-11-18T04:02:34Z;INIST;INIST.ESRF;3;INIST.ESRF;10.15151/ESRF-ES-133417381;Peter CLOETENS;Yang Yang;Murielle SALOME;Sylvain BOHIC;Zernike phase contrast projection imaging;In-house Method and Instrumentation;IH-MI-1424;id16a;European Synchrotron Radiation Facility;2018-10-23;2021;eng;Experiment Session",
-    "group": "esrf",
-    "groups": [
-        {
-            "name": "esrf"
-        }
-    ],
-    "name": "1f7d0109-08aa-5f0a-871d-9306c8f5eb54",
-    "oai_identifier": [
-        "oai:oai.datacite.org:17029860"
-    ],
-    "oai_set": [
-        "INIST",
-        "INIST.ESRF"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "In-house Method Instrumentation"
-        },
-        {
-            "name": "IH-MI-"
-        },
-        {
-            "name": "ida"
-        }
-    ],
-    "title": [
-        "Zernike phase contrast projection imaging"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1fd8e7a0-9bec-58e3-a734-8b091e102b44.json b/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1fd8e7a0-9bec-58e3-a734-8b091e102b44.json
deleted file mode 100644
index acf83bbb..00000000
--- a/oaitestdata/esrf-oai_datacite/INIST.ESRF_1/json/1fd8e7a0-9bec-58e3-a734-8b091e102b44.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15151/ESRF-ES-92162610",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://oai.datacite.org/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:oai.datacite.org:14561119",
-    "MetadataAccess": [
-        "oai:oai.datacite.org:14561119"
-    ],
-    "PublicationTimestamp": "2021-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2021"
-    ],
-    "Publisher": [
-        "European Synchrotron Radiation Facility"
-    ],
-    "ResourceType": [
-        "Experiment Session"
-    ],
-    "TempCoverageBegin": 63657658799,
-    "TempCoverageEnd": 63657658799,
-    "TemporalCoverage": " point in time : 2018-03-26T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2018-03-26T11:59:59Z",
-    "TemporalCoverage:EndDate": "2018-03-26T11:59:59Z",
-    "author": [
-        "Henri GLEYZOLLE",
-        "Carlotta GIACOBBE",
-        "Jonathan Wright",
-        "Wolfgang LUDWIG",
-        "Marta MAJKUT"
-    ],
-    "fulltext": "oai:oai.datacite.org:14561119;2018-03-26T12:25:44Z;INIST;INIST.ESRF;3;INIST.ESRF;10.15151/ESRF-ES-92162610;Jonathan Wright;Henri GLEYZOLLE;Marta MAJKUT;Carlotta GIACOBBE;Wolfgang LUDWIG;Align, radiation test and texture measurements on test samples;In-house Method and Instrumentation;IH-MI-1382;id11;European Synchrotron Radiation Facility;2018-03-26;2021;eng;Experiment Session",
-    "group": "esrf",
-    "groups": [
-        {
-            "name": "esrf"
-        }
-    ],
-    "name": "1fd8e7a0-9bec-58e3-a734-8b091e102b44",
-    "oai_identifier": [
-        "oai:oai.datacite.org:14561119"
-    ],
-    "oai_set": [
-        "INIST",
-        "INIST.ESRF"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "In-house Method Instrumentation"
-        },
-        {
-            "name": "IH-MI-"
-        },
-        {
-            "name": "id"
-        }
-    ],
-    "title": [
-        "Align, radiation test and texture measurements on test samples"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/ess-oai_datacite/full_1/json/00e953de-6c83-5d2d-b7d5-146dd6c0672a.json b/oaitestdata/ess-oai_datacite/full_1/json/00e953de-6c83-5d2d-b7d5-146dd6c0672a.json
deleted file mode 100644
index e139cc34..00000000
--- a/oaitestdata/ess-oai_datacite/full_1/json/00e953de-6c83-5d2d-b7d5-146dd6c0672a.json
+++ /dev/null
@@ -1,35 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.17199/NXMV08.DSC0001",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://scicat.esss.se/scicat/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=10.17199/NXMV08.DSC0001",
-    "MetadataAccess": [
-        "10.17199/NXMV08.DSC0001"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "ESS"
-    ],
-    "fulltext": "10.17199/NXMV08.DSC0001;openaire_data;2020-01-01;Differential scanning calorimetry (DSC) data for breast cancer cells;https://doi.org/10.17199/NXMV08.DSC0001;https://github.com/ess-dmsc/ess_file_formats/wiki/DSC;2020-01-01;2020-01-01;2018;Murillo Longo Martins;ESS;ESS;1;OpenAccess",
-    "group": "ess",
-    "groups": [
-        {
-            "name": "ess"
-        }
-    ],
-    "name": "00e953de-6c83-5d2d-b7d5-146dd6c0672a",
-    "oai_identifier": [
-        "10.17199/NXMV08.DSC0001"
-    ],
-    "oai_set": [
-        "openaire_data"
-    ],
-    "state": "active",
-    "title": [
-        "\n        "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/ess-oai_datacite/full_1/json/01f38ae3-3714-5d42-9183-09153d837a53.json b/oaitestdata/ess-oai_datacite/full_1/json/01f38ae3-3714-5d42-9183-09153d837a53.json
deleted file mode 100644
index f5e33228..00000000
--- a/oaitestdata/ess-oai_datacite/full_1/json/01f38ae3-3714-5d42-9183-09153d837a53.json
+++ /dev/null
@@ -1,35 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.17199/BRIGHTNESS/V200003",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://scicat.esss.se/scicat/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=10.17199/BRIGHTNESS/V200003",
-    "MetadataAccess": [
-        "10.17199/BRIGHTNESS/V200003"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "ESS"
-    ],
-    "fulltext": "10.17199/BRIGHTNESS/V200003;openaire_data;2020-01-01;Sample Data from V20;https://doi.org/10.17199/BRIGHTNESS/V200003;https://github.com/ess-dmsc/ess_file_formats/wiki/HDF5;2020-01-01;2020-01-01;2018;Tobias Richter;ESS;ESS;1;OpenAccess",
-    "group": "ess",
-    "groups": [
-        {
-            "name": "ess"
-        }
-    ],
-    "name": "01f38ae3-3714-5d42-9183-09153d837a53",
-    "oai_identifier": [
-        "10.17199/BRIGHTNESS/V200003"
-    ],
-    "oai_set": [
-        "openaire_data"
-    ],
-    "state": "active",
-    "title": [
-        "\n        "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/ess-oai_datacite/full_1/json/01fd8e62-d73f-5dc3-bb11-acf9fb5dcf33.json b/oaitestdata/ess-oai_datacite/full_1/json/01fd8e62-d73f-5dc3-bb11-acf9fb5dcf33.json
deleted file mode 100644
index cafe9746..00000000
--- a/oaitestdata/ess-oai_datacite/full_1/json/01fd8e62-d73f-5dc3-bb11-acf9fb5dcf33.json
+++ /dev/null
@@ -1,35 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.17199/BRIGHTNESS/V200173",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://scicat.esss.se/scicat/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=10.17199/BRIGHTNESS/V200173",
-    "MetadataAccess": [
-        "10.17199/BRIGHTNESS/V200173"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "ESS"
-    ],
-    "fulltext": "10.17199/BRIGHTNESS/V200173;openaire_data;2020-01-01;Sample Data from V20;https://doi.org/10.17199/BRIGHTNESS/V200173;https://github.com/ess-dmsc/ess_file_formats/wiki/HDF5;2020-01-01;2020-01-01;2018;Tobias Richter;ESS;ESS;1;OpenAccess",
-    "group": "ess",
-    "groups": [
-        {
-            "name": "ess"
-        }
-    ],
-    "name": "01fd8e62-d73f-5dc3-bb11-acf9fb5dcf33",
-    "oai_identifier": [
-        "10.17199/BRIGHTNESS/V200173"
-    ],
-    "oai_set": [
-        "openaire_data"
-    ],
-    "state": "active",
-    "title": [
-        "\n        "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/ess-oai_datacite/full_1/json/02ac9a2f-5e16-5915-ab32-d8adb2a0b7be.json b/oaitestdata/ess-oai_datacite/full_1/json/02ac9a2f-5e16-5915-ab32-d8adb2a0b7be.json
deleted file mode 100644
index 3c829647..00000000
--- a/oaitestdata/ess-oai_datacite/full_1/json/02ac9a2f-5e16-5915-ab32-d8adb2a0b7be.json
+++ /dev/null
@@ -1,35 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.17199/BRIGHTNESS/MB0041",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://scicat.esss.se/scicat/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=10.17199/BRIGHTNESS/MB0041",
-    "MetadataAccess": [
-        "10.17199/BRIGHTNESS/MB0041"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "ESS"
-    ],
-    "fulltext": "10.17199/BRIGHTNESS/MB0041;openaire_data;2020-01-01;Sample Data from multiblade;https://doi.org/10.17199/BRIGHTNESS/MB0041;https://github.com/ess-dmsc/ess_file_formats/wiki/Zaba;2020-01-01;2020-01-01;2018;Francesco Piscitelli;ESS;ESS;1;OpenAccess",
-    "group": "ess",
-    "groups": [
-        {
-            "name": "ess"
-        }
-    ],
-    "name": "02ac9a2f-5e16-5915-ab32-d8adb2a0b7be",
-    "oai_identifier": [
-        "10.17199/BRIGHTNESS/MB0041"
-    ],
-    "oai_set": [
-        "openaire_data"
-    ],
-    "state": "active",
-    "title": [
-        "\n        "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/ess-oai_datacite/full_1/json/0aa871e7-12c9-5283-8025-562414a73ecd.json b/oaitestdata/ess-oai_datacite/full_1/json/0aa871e7-12c9-5283-8025-562414a73ecd.json
deleted file mode 100644
index 6ce0624b..00000000
--- a/oaitestdata/ess-oai_datacite/full_1/json/0aa871e7-12c9-5283-8025-562414a73ecd.json
+++ /dev/null
@@ -1,35 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.17199/BRIGHTNESS/V200111",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://scicat.esss.se/scicat/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=10.17199/BRIGHTNESS/V200111",
-    "MetadataAccess": [
-        "10.17199/BRIGHTNESS/V200111"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "ESS"
-    ],
-    "fulltext": "10.17199/BRIGHTNESS/V200111;openaire_data;2020-01-01;Sample Data from V20;https://doi.org/10.17199/BRIGHTNESS/V200111;https://github.com/ess-dmsc/ess_file_formats/wiki/HDF5;2020-01-01;2020-01-01;2018;Tobias Richter;ESS;ESS;1;OpenAccess",
-    "group": "ess",
-    "groups": [
-        {
-            "name": "ess"
-        }
-    ],
-    "name": "0aa871e7-12c9-5283-8025-562414a73ecd",
-    "oai_identifier": [
-        "10.17199/BRIGHTNESS/V200111"
-    ],
-    "oai_set": [
-        "openaire_data"
-    ],
-    "state": "active",
-    "title": [
-        "\n        "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/ess-oai_datacite/full_1/json/0adbf2a8-c162-5d18-9e8a-a4cc725e4d47.json b/oaitestdata/ess-oai_datacite/full_1/json/0adbf2a8-c162-5d18-9e8a-a4cc725e4d47.json
deleted file mode 100644
index 1f31de31..00000000
--- a/oaitestdata/ess-oai_datacite/full_1/json/0adbf2a8-c162-5d18-9e8a-a4cc725e4d47.json
+++ /dev/null
@@ -1,35 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.17199/BRIGHTNESS/V200080",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://scicat.esss.se/scicat/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=10.17199/BRIGHTNESS/V200080",
-    "MetadataAccess": [
-        "10.17199/BRIGHTNESS/V200080"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "ESS"
-    ],
-    "fulltext": "10.17199/BRIGHTNESS/V200080;openaire_data;2020-01-01;Sample Data from V20;https://doi.org/10.17199/BRIGHTNESS/V200080;https://github.com/ess-dmsc/ess_file_formats/wiki/HDF5;2020-01-01;2020-01-01;2018;Tobias Richter;ESS;ESS;1;OpenAccess",
-    "group": "ess",
-    "groups": [
-        {
-            "name": "ess"
-        }
-    ],
-    "name": "0adbf2a8-c162-5d18-9e8a-a4cc725e4d47",
-    "oai_identifier": [
-        "10.17199/BRIGHTNESS/V200080"
-    ],
-    "oai_set": [
-        "openaire_data"
-    ],
-    "state": "active",
-    "title": [
-        "\n        "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/ess-oai_datacite/full_1/json/0bf772ac-382d-559b-95b5-aa1c392b2942.json b/oaitestdata/ess-oai_datacite/full_1/json/0bf772ac-382d-559b-95b5-aa1c392b2942.json
deleted file mode 100644
index d68e8b0e..00000000
--- a/oaitestdata/ess-oai_datacite/full_1/json/0bf772ac-382d-559b-95b5-aa1c392b2942.json
+++ /dev/null
@@ -1,35 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.17199/BRIGHTNESS/V200040",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://scicat.esss.se/scicat/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=10.17199/BRIGHTNESS/V200040",
-    "MetadataAccess": [
-        "10.17199/BRIGHTNESS/V200040"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "ESS"
-    ],
-    "fulltext": "10.17199/BRIGHTNESS/V200040;openaire_data;2020-01-01;Sample Data from V20;https://doi.org/10.17199/BRIGHTNESS/V200040;https://github.com/ess-dmsc/ess_file_formats/wiki/HDF5;2020-01-01;2020-01-01;2018;Tobias Richter;ESS;ESS;1;OpenAccess",
-    "group": "ess",
-    "groups": [
-        {
-            "name": "ess"
-        }
-    ],
-    "name": "0bf772ac-382d-559b-95b5-aa1c392b2942",
-    "oai_identifier": [
-        "10.17199/BRIGHTNESS/V200040"
-    ],
-    "oai_set": [
-        "openaire_data"
-    ],
-    "state": "active",
-    "title": [
-        "\n        "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/ess-oai_datacite/full_1/json/0c7acc20-126c-5be5-8a15-c2fed81d96c9.json b/oaitestdata/ess-oai_datacite/full_1/json/0c7acc20-126c-5be5-8a15-c2fed81d96c9.json
deleted file mode 100644
index 0486eb18..00000000
--- a/oaitestdata/ess-oai_datacite/full_1/json/0c7acc20-126c-5be5-8a15-c2fed81d96c9.json
+++ /dev/null
@@ -1,35 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.17199/BRIGHTNESS/MB0023",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://scicat.esss.se/scicat/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=10.17199/BRIGHTNESS/MB0023",
-    "MetadataAccess": [
-        "10.17199/BRIGHTNESS/MB0023"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "ESS"
-    ],
-    "fulltext": "10.17199/BRIGHTNESS/MB0023;openaire_data;2020-01-01;Sample Data from multiblade;https://doi.org/10.17199/BRIGHTNESS/MB0023;https://github.com/ess-dmsc/ess_file_formats/wiki/Zaba;2020-01-01;2020-01-01;2018;Francesco Piscitelli;ESS;ESS;1;OpenAccess",
-    "group": "ess",
-    "groups": [
-        {
-            "name": "ess"
-        }
-    ],
-    "name": "0c7acc20-126c-5be5-8a15-c2fed81d96c9",
-    "oai_identifier": [
-        "10.17199/BRIGHTNESS/MB0023"
-    ],
-    "oai_set": [
-        "openaire_data"
-    ],
-    "state": "active",
-    "title": [
-        "\n        "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/ess-oai_datacite/full_1/json/0d15276e-fa0c-5d13-94eb-95855d56a12b.json b/oaitestdata/ess-oai_datacite/full_1/json/0d15276e-fa0c-5d13-94eb-95855d56a12b.json
deleted file mode 100644
index 0bd9f9cc..00000000
--- a/oaitestdata/ess-oai_datacite/full_1/json/0d15276e-fa0c-5d13-94eb-95855d56a12b.json
+++ /dev/null
@@ -1,35 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.17199/BRIGHTNESS/MB0040",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://scicat.esss.se/scicat/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=10.17199/BRIGHTNESS/MB0040",
-    "MetadataAccess": [
-        "10.17199/BRIGHTNESS/MB0040"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "ESS"
-    ],
-    "fulltext": "10.17199/BRIGHTNESS/MB0040;openaire_data;2020-01-01;Sample Data from multiblade;https://doi.org/10.17199/BRIGHTNESS/MB0040;https://github.com/ess-dmsc/ess_file_formats/wiki/Zaba;2020-01-01;2020-01-01;2018;Francesco Piscitelli;ESS;ESS;1;OpenAccess",
-    "group": "ess",
-    "groups": [
-        {
-            "name": "ess"
-        }
-    ],
-    "name": "0d15276e-fa0c-5d13-94eb-95855d56a12b",
-    "oai_identifier": [
-        "10.17199/BRIGHTNESS/MB0040"
-    ],
-    "oai_set": [
-        "openaire_data"
-    ],
-    "state": "active",
-    "title": [
-        "\n        "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/ess-oai_datacite/full_1/json/0d9d82dd-889d-50ae-af3b-970fd3c718b3.json b/oaitestdata/ess-oai_datacite/full_1/json/0d9d82dd-889d-50ae-af3b-970fd3c718b3.json
deleted file mode 100644
index 310c6132..00000000
--- a/oaitestdata/ess-oai_datacite/full_1/json/0d9d82dd-889d-50ae-af3b-970fd3c718b3.json
+++ /dev/null
@@ -1,35 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.17199/BRIGHTNESS/NMX0125",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://scicat.esss.se/scicat/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=10.17199/BRIGHTNESS/NMX0125",
-    "MetadataAccess": [
-        "10.17199/BRIGHTNESS/NMX0125"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "ESS"
-    ],
-    "fulltext": "10.17199/BRIGHTNESS/NMX0125;openaire_data;2020-01-01;Sample Data from NMX;https://doi.org/10.17199/BRIGHTNESS/NMX0125;https://github.com/ess-dmsc/ess_file_formats/wiki/NMX;2020-01-01;2020-01-01;2018;Dorothea Pfeiffer;ESS;ESS;1;OpenAccess",
-    "group": "ess",
-    "groups": [
-        {
-            "name": "ess"
-        }
-    ],
-    "name": "0d9d82dd-889d-50ae-af3b-970fd3c718b3",
-    "oai_identifier": [
-        "10.17199/BRIGHTNESS/NMX0125"
-    ],
-    "oai_set": [
-        "openaire_data"
-    ],
-    "state": "active",
-    "title": [
-        "\n        "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/ess-oai_datacite/full_1/json/0dcb4ea0-09ce-569c-b0f0-96be04a6dcd4.json b/oaitestdata/ess-oai_datacite/full_1/json/0dcb4ea0-09ce-569c-b0f0-96be04a6dcd4.json
deleted file mode 100644
index 66996c8d..00000000
--- a/oaitestdata/ess-oai_datacite/full_1/json/0dcb4ea0-09ce-569c-b0f0-96be04a6dcd4.json
+++ /dev/null
@@ -1,35 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.17199/BRIGHTNESS/MG0004",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://scicat.esss.se/scicat/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=10.17199/BRIGHTNESS/MG0004",
-    "MetadataAccess": [
-        "10.17199/BRIGHTNESS/MG0004"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "ESS"
-    ],
-    "fulltext": "10.17199/BRIGHTNESS/MG0004;openaire_data;2020-01-01;Sample Data from multigrid;https://doi.org/10.17199/BRIGHTNESS/MG0004;https://github.com/ess-dmsc/ess_file_formats/wiki/Multigrid-Data-Format-I;2020-01-01;2020-01-01;2018;Anton Khaplanov;ESS;ESS;1;OpenAccess",
-    "group": "ess",
-    "groups": [
-        {
-            "name": "ess"
-        }
-    ],
-    "name": "0dcb4ea0-09ce-569c-b0f0-96be04a6dcd4",
-    "oai_identifier": [
-        "10.17199/BRIGHTNESS/MG0004"
-    ],
-    "oai_set": [
-        "openaire_data"
-    ],
-    "state": "active",
-    "title": [
-        "\n        "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/ess-oai_datacite/full_1/json/0dd16d8d-1a55-52ae-b37c-b1cc7a6cfe4a.json b/oaitestdata/ess-oai_datacite/full_1/json/0dd16d8d-1a55-52ae-b37c-b1cc7a6cfe4a.json
deleted file mode 100644
index af78d434..00000000
--- a/oaitestdata/ess-oai_datacite/full_1/json/0dd16d8d-1a55-52ae-b37c-b1cc7a6cfe4a.json
+++ /dev/null
@@ -1,35 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.17199/BRIGHTNESS/V200103",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://scicat.esss.se/scicat/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=10.17199/BRIGHTNESS/V200103",
-    "MetadataAccess": [
-        "10.17199/BRIGHTNESS/V200103"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "ESS"
-    ],
-    "fulltext": "10.17199/BRIGHTNESS/V200103;openaire_data;2020-01-01;Sample Data from V20;https://doi.org/10.17199/BRIGHTNESS/V200103;https://github.com/ess-dmsc/ess_file_formats/wiki/HDF5;2020-01-01;2020-01-01;2018;Tobias Richter;ESS;ESS;1;OpenAccess",
-    "group": "ess",
-    "groups": [
-        {
-            "name": "ess"
-        }
-    ],
-    "name": "0dd16d8d-1a55-52ae-b37c-b1cc7a6cfe4a",
-    "oai_identifier": [
-        "10.17199/BRIGHTNESS/V200103"
-    ],
-    "oai_set": [
-        "openaire_data"
-    ],
-    "state": "active",
-    "title": [
-        "\n        "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/ess-oai_datacite/full_1/json/0e305549-7b4f-540d-8c39-4d7b2332a614.json b/oaitestdata/ess-oai_datacite/full_1/json/0e305549-7b4f-540d-8c39-4d7b2332a614.json
deleted file mode 100644
index 82e724c9..00000000
--- a/oaitestdata/ess-oai_datacite/full_1/json/0e305549-7b4f-540d-8c39-4d7b2332a614.json
+++ /dev/null
@@ -1,35 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.17199/BRIGHTNESS/V200049",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://scicat.esss.se/scicat/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=10.17199/BRIGHTNESS/V200049",
-    "MetadataAccess": [
-        "10.17199/BRIGHTNESS/V200049"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "ESS"
-    ],
-    "fulltext": "10.17199/BRIGHTNESS/V200049;openaire_data;2020-01-01;Sample Data from V20;https://doi.org/10.17199/BRIGHTNESS/V200049;https://github.com/ess-dmsc/ess_file_formats/wiki/HDF5;2020-01-01;2020-01-01;2018;Tobias Richter;ESS;ESS;1;OpenAccess",
-    "group": "ess",
-    "groups": [
-        {
-            "name": "ess"
-        }
-    ],
-    "name": "0e305549-7b4f-540d-8c39-4d7b2332a614",
-    "oai_identifier": [
-        "10.17199/BRIGHTNESS/V200049"
-    ],
-    "oai_set": [
-        "openaire_data"
-    ],
-    "state": "active",
-    "title": [
-        "\n        "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/ess-oai_datacite/full_1/json/0e535465-293b-5e43-8037-8e880454f7a0.json b/oaitestdata/ess-oai_datacite/full_1/json/0e535465-293b-5e43-8037-8e880454f7a0.json
deleted file mode 100644
index 72963af4..00000000
--- a/oaitestdata/ess-oai_datacite/full_1/json/0e535465-293b-5e43-8037-8e880454f7a0.json
+++ /dev/null
@@ -1,35 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.17199/BRIGHTNESS/V200146",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://scicat.esss.se/scicat/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=10.17199/BRIGHTNESS/V200146",
-    "MetadataAccess": [
-        "10.17199/BRIGHTNESS/V200146"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "ESS"
-    ],
-    "fulltext": "10.17199/BRIGHTNESS/V200146;openaire_data;2020-01-01;Sample Data from V20;https://doi.org/10.17199/BRIGHTNESS/V200146;https://github.com/ess-dmsc/ess_file_formats/wiki/HDF5;2020-01-01;2020-01-01;2018;Tobias Richter;ESS;ESS;1;OpenAccess",
-    "group": "ess",
-    "groups": [
-        {
-            "name": "ess"
-        }
-    ],
-    "name": "0e535465-293b-5e43-8037-8e880454f7a0",
-    "oai_identifier": [
-        "10.17199/BRIGHTNESS/V200146"
-    ],
-    "oai_set": [
-        "openaire_data"
-    ],
-    "state": "active",
-    "title": [
-        "\n        "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/ess-oai_datacite/full_1/json/0ef70cd4-14b6-5593-9cb1-b7607c38f77c.json b/oaitestdata/ess-oai_datacite/full_1/json/0ef70cd4-14b6-5593-9cb1-b7607c38f77c.json
deleted file mode 100644
index db5164f4..00000000
--- a/oaitestdata/ess-oai_datacite/full_1/json/0ef70cd4-14b6-5593-9cb1-b7607c38f77c.json
+++ /dev/null
@@ -1,35 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.17199/BRIGHTNESS/NMX0043",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://scicat.esss.se/scicat/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=10.17199/BRIGHTNESS/NMX0043",
-    "MetadataAccess": [
-        "10.17199/BRIGHTNESS/NMX0043"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "ESS"
-    ],
-    "fulltext": "10.17199/BRIGHTNESS/NMX0043;openaire_data;2020-01-01;Sample Data from NMX;https://doi.org/10.17199/BRIGHTNESS/NMX0043;https://github.com/ess-dmsc/ess_file_formats/wiki/NMX;2020-01-01;2020-01-01;2018;Dorothea Pfeiffer;ESS;ESS;1;OpenAccess",
-    "group": "ess",
-    "groups": [
-        {
-            "name": "ess"
-        }
-    ],
-    "name": "0ef70cd4-14b6-5593-9cb1-b7607c38f77c",
-    "oai_identifier": [
-        "10.17199/BRIGHTNESS/NMX0043"
-    ],
-    "oai_set": [
-        "openaire_data"
-    ],
-    "state": "active",
-    "title": [
-        "\n        "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/ess-oai_datacite/full_1/json/0fda2e35-92cf-527b-8030-2ea58a8454be.json b/oaitestdata/ess-oai_datacite/full_1/json/0fda2e35-92cf-527b-8030-2ea58a8454be.json
deleted file mode 100644
index 996481ab..00000000
--- a/oaitestdata/ess-oai_datacite/full_1/json/0fda2e35-92cf-527b-8030-2ea58a8454be.json
+++ /dev/null
@@ -1,35 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.17199/BRIGHTNESS/NMX0062",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://scicat.esss.se/scicat/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=10.17199/BRIGHTNESS/NMX0062",
-    "MetadataAccess": [
-        "10.17199/BRIGHTNESS/NMX0062"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "ESS"
-    ],
-    "fulltext": "10.17199/BRIGHTNESS/NMX0062;openaire_data;2020-01-01;Sample Data from NMX;https://doi.org/10.17199/BRIGHTNESS/NMX0062;https://github.com/ess-dmsc/ess_file_formats/wiki/NMX;2020-01-01;2020-01-01;2018;Dorothea Pfeiffer;ESS;ESS;1;OpenAccess",
-    "group": "ess",
-    "groups": [
-        {
-            "name": "ess"
-        }
-    ],
-    "name": "0fda2e35-92cf-527b-8030-2ea58a8454be",
-    "oai_identifier": [
-        "10.17199/BRIGHTNESS/NMX0062"
-    ],
-    "oai_set": [
-        "openaire_data"
-    ],
-    "state": "active",
-    "title": [
-        "\n        "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/ess-oai_datacite/full_1/json/1a738a8e-f202-555b-94cb-acb232862a61.json b/oaitestdata/ess-oai_datacite/full_1/json/1a738a8e-f202-555b-94cb-acb232862a61.json
deleted file mode 100644
index d77bed26..00000000
--- a/oaitestdata/ess-oai_datacite/full_1/json/1a738a8e-f202-555b-94cb-acb232862a61.json
+++ /dev/null
@@ -1,35 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.17199/BRIGHTNESS/NMX0065",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://scicat.esss.se/scicat/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=10.17199/BRIGHTNESS/NMX0065",
-    "MetadataAccess": [
-        "10.17199/BRIGHTNESS/NMX0065"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "ESS"
-    ],
-    "fulltext": "10.17199/BRIGHTNESS/NMX0065;openaire_data;2020-01-01;Sample Data from NMX;https://doi.org/10.17199/BRIGHTNESS/NMX0065;https://github.com/ess-dmsc/ess_file_formats/wiki/NMX;2020-01-01;2020-01-01;2018;Dorothea Pfeiffer;ESS;ESS;1;OpenAccess",
-    "group": "ess",
-    "groups": [
-        {
-            "name": "ess"
-        }
-    ],
-    "name": "1a738a8e-f202-555b-94cb-acb232862a61",
-    "oai_identifier": [
-        "10.17199/BRIGHTNESS/NMX0065"
-    ],
-    "oai_set": [
-        "openaire_data"
-    ],
-    "state": "active",
-    "title": [
-        "\n        "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/ess-oai_datacite/full_1/json/1a7f9c7a-aebd-556d-94dd-3c511998f851.json b/oaitestdata/ess-oai_datacite/full_1/json/1a7f9c7a-aebd-556d-94dd-3c511998f851.json
deleted file mode 100644
index 2c528816..00000000
--- a/oaitestdata/ess-oai_datacite/full_1/json/1a7f9c7a-aebd-556d-94dd-3c511998f851.json
+++ /dev/null
@@ -1,35 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.17199/BRIGHTNESS/V200176",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://scicat.esss.se/scicat/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=10.17199/BRIGHTNESS/V200176",
-    "MetadataAccess": [
-        "10.17199/BRIGHTNESS/V200176"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "ESS"
-    ],
-    "fulltext": "10.17199/BRIGHTNESS/V200176;openaire_data;2020-01-01;Sample Data from V20;https://doi.org/10.17199/BRIGHTNESS/V200176;https://github.com/ess-dmsc/ess_file_formats/wiki/HDF5;2020-01-01;2020-01-01;2018;Tobias Richter;ESS;ESS;1;OpenAccess",
-    "group": "ess",
-    "groups": [
-        {
-            "name": "ess"
-        }
-    ],
-    "name": "1a7f9c7a-aebd-556d-94dd-3c511998f851",
-    "oai_identifier": [
-        "10.17199/BRIGHTNESS/V200176"
-    ],
-    "oai_set": [
-        "openaire_data"
-    ],
-    "state": "active",
-    "title": [
-        "\n        "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/ess-oai_datacite/full_1/json/1ab35a7e-f4d8-507f-b839-3aa1bc0e9bf2.json b/oaitestdata/ess-oai_datacite/full_1/json/1ab35a7e-f4d8-507f-b839-3aa1bc0e9bf2.json
deleted file mode 100644
index b457730b..00000000
--- a/oaitestdata/ess-oai_datacite/full_1/json/1ab35a7e-f4d8-507f-b839-3aa1bc0e9bf2.json
+++ /dev/null
@@ -1,35 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.17199/BRIGHTNESS/MB0019",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://scicat.esss.se/scicat/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=10.17199/BRIGHTNESS/MB0019",
-    "MetadataAccess": [
-        "10.17199/BRIGHTNESS/MB0019"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "ESS"
-    ],
-    "fulltext": "10.17199/BRIGHTNESS/MB0019;openaire_data;2020-01-01;Sample Data from multiblade;https://doi.org/10.17199/BRIGHTNESS/MB0019;https://github.com/ess-dmsc/ess_file_formats/wiki/Zaba;2020-01-01;2020-01-01;2018;Francesco Piscitelli;ESS;ESS;1;OpenAccess",
-    "group": "ess",
-    "groups": [
-        {
-            "name": "ess"
-        }
-    ],
-    "name": "1ab35a7e-f4d8-507f-b839-3aa1bc0e9bf2",
-    "oai_identifier": [
-        "10.17199/BRIGHTNESS/MB0019"
-    ],
-    "oai_set": [
-        "openaire_data"
-    ],
-    "state": "active",
-    "title": [
-        "\n        "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/ess-oai_datacite/full_1/json/1b54ad24-a193-5c69-a959-ee4b395adc03.json b/oaitestdata/ess-oai_datacite/full_1/json/1b54ad24-a193-5c69-a959-ee4b395adc03.json
deleted file mode 100644
index ec10e5f7..00000000
--- a/oaitestdata/ess-oai_datacite/full_1/json/1b54ad24-a193-5c69-a959-ee4b395adc03.json
+++ /dev/null
@@ -1,35 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.17199/BRIGHTNESS/V200125",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://scicat.esss.se/scicat/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=10.17199/BRIGHTNESS/V200125",
-    "MetadataAccess": [
-        "10.17199/BRIGHTNESS/V200125"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "ESS"
-    ],
-    "fulltext": "10.17199/BRIGHTNESS/V200125;openaire_data;2020-01-01;Sample Data from V20;https://doi.org/10.17199/BRIGHTNESS/V200125;https://github.com/ess-dmsc/ess_file_formats/wiki/HDF5;2020-01-01;2020-01-01;2018;Tobias Richter;ESS;ESS;1;OpenAccess",
-    "group": "ess",
-    "groups": [
-        {
-            "name": "ess"
-        }
-    ],
-    "name": "1b54ad24-a193-5c69-a959-ee4b395adc03",
-    "oai_identifier": [
-        "10.17199/BRIGHTNESS/V200125"
-    ],
-    "oai_set": [
-        "openaire_data"
-    ],
-    "state": "active",
-    "title": [
-        "\n        "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/ess-oai_datacite/full_1/json/1b63d5e7-a676-5c00-b718-07105b377732.json b/oaitestdata/ess-oai_datacite/full_1/json/1b63d5e7-a676-5c00-b718-07105b377732.json
deleted file mode 100644
index 198c2f09..00000000
--- a/oaitestdata/ess-oai_datacite/full_1/json/1b63d5e7-a676-5c00-b718-07105b377732.json
+++ /dev/null
@@ -1,35 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.17199/BRIGHTNESS/V200157",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://scicat.esss.se/scicat/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=10.17199/BRIGHTNESS/V200157",
-    "MetadataAccess": [
-        "10.17199/BRIGHTNESS/V200157"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "ESS"
-    ],
-    "fulltext": "10.17199/BRIGHTNESS/V200157;openaire_data;2020-01-01;Sample Data from V20;https://doi.org/10.17199/BRIGHTNESS/V200157;https://github.com/ess-dmsc/ess_file_formats/wiki/HDF5;2020-01-01;2020-01-01;2018;Tobias Richter;ESS;ESS;1;OpenAccess",
-    "group": "ess",
-    "groups": [
-        {
-            "name": "ess"
-        }
-    ],
-    "name": "1b63d5e7-a676-5c00-b718-07105b377732",
-    "oai_identifier": [
-        "10.17199/BRIGHTNESS/V200157"
-    ],
-    "oai_set": [
-        "openaire_data"
-    ],
-    "state": "active",
-    "title": [
-        "\n        "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/ess-oai_datacite/full_1/json/1b67ed58-9fbf-5357-980e-71c93ad78823.json b/oaitestdata/ess-oai_datacite/full_1/json/1b67ed58-9fbf-5357-980e-71c93ad78823.json
deleted file mode 100644
index 2ce6c51a..00000000
--- a/oaitestdata/ess-oai_datacite/full_1/json/1b67ed58-9fbf-5357-980e-71c93ad78823.json
+++ /dev/null
@@ -1,34 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/5e3c01013a45005c48e66691",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://scicat.esss.se/scicat/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=5e3c01013a45005c48e66691",
-    "MetadataAccess": [
-        "5e3c01013a45005c48e66691"
-    ],
-    "PublicationYear": [
-        "0"
-    ],
-    "Publisher": [
-        "string"
-    ],
-    "fulltext": "5e3c01013a45005c48e66691;openaire_data;2020-01-01;string;https://doi.org/5e3c01013a45005c48e66691;string;2020-01-01;2020-01-01;0;string;string;string;1;OpenAccess",
-    "group": "ess",
-    "groups": [
-        {
-            "name": "ess"
-        }
-    ],
-    "name": "1b67ed58-9fbf-5357-980e-71c93ad78823",
-    "oai_identifier": [
-        "5e3c01013a45005c48e66691"
-    ],
-    "oai_set": [
-        "openaire_data"
-    ],
-    "state": "active",
-    "title": [
-        "\n        "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/ess-oai_datacite/full_1/json/1b821870-c95c-5f28-b797-86ec1ae1ba76.json b/oaitestdata/ess-oai_datacite/full_1/json/1b821870-c95c-5f28-b797-86ec1ae1ba76.json
deleted file mode 100644
index 60d9ba3e..00000000
--- a/oaitestdata/ess-oai_datacite/full_1/json/1b821870-c95c-5f28-b797-86ec1ae1ba76.json
+++ /dev/null
@@ -1,35 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.17199/BRIGHTNESS/MB0034",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://scicat.esss.se/scicat/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=10.17199/BRIGHTNESS/MB0034",
-    "MetadataAccess": [
-        "10.17199/BRIGHTNESS/MB0034"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "ESS"
-    ],
-    "fulltext": "10.17199/BRIGHTNESS/MB0034;openaire_data;2020-01-01;Sample Data from multiblade;https://doi.org/10.17199/BRIGHTNESS/MB0034;https://github.com/ess-dmsc/ess_file_formats/wiki/Zaba;2020-01-01;2020-01-01;2018;Francesco Piscitelli;ESS;ESS;1;OpenAccess",
-    "group": "ess",
-    "groups": [
-        {
-            "name": "ess"
-        }
-    ],
-    "name": "1b821870-c95c-5f28-b797-86ec1ae1ba76",
-    "oai_identifier": [
-        "10.17199/BRIGHTNESS/MB0034"
-    ],
-    "oai_set": [
-        "openaire_data"
-    ],
-    "state": "active",
-    "title": [
-        "\n        "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/ess-oai_datacite/full_1/json/1c507bfc-fe6f-51d6-8dcb-4274529dfa8b.json b/oaitestdata/ess-oai_datacite/full_1/json/1c507bfc-fe6f-51d6-8dcb-4274529dfa8b.json
deleted file mode 100644
index 080c253c..00000000
--- a/oaitestdata/ess-oai_datacite/full_1/json/1c507bfc-fe6f-51d6-8dcb-4274529dfa8b.json
+++ /dev/null
@@ -1,35 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.17199/BRIGHTNESS/V200127",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://scicat.esss.se/scicat/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=10.17199/BRIGHTNESS/V200127",
-    "MetadataAccess": [
-        "10.17199/BRIGHTNESS/V200127"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "ESS"
-    ],
-    "fulltext": "10.17199/BRIGHTNESS/V200127;openaire_data;2020-01-01;Sample Data from V20;https://doi.org/10.17199/BRIGHTNESS/V200127;https://github.com/ess-dmsc/ess_file_formats/wiki/HDF5;2020-01-01;2020-01-01;2018;Tobias Richter;ESS;ESS;1;OpenAccess",
-    "group": "ess",
-    "groups": [
-        {
-            "name": "ess"
-        }
-    ],
-    "name": "1c507bfc-fe6f-51d6-8dcb-4274529dfa8b",
-    "oai_identifier": [
-        "10.17199/BRIGHTNESS/V200127"
-    ],
-    "oai_set": [
-        "openaire_data"
-    ],
-    "state": "active",
-    "title": [
-        "\n        "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/ess-oai_datacite/full_1/json/1cd8405f-e797-5def-bcc4-cfedd1140827.json b/oaitestdata/ess-oai_datacite/full_1/json/1cd8405f-e797-5def-bcc4-cfedd1140827.json
deleted file mode 100644
index 6a36c6a5..00000000
--- a/oaitestdata/ess-oai_datacite/full_1/json/1cd8405f-e797-5def-bcc4-cfedd1140827.json
+++ /dev/null
@@ -1,35 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.17199/BRIGHTNESS/V200037",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://scicat.esss.se/scicat/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=10.17199/BRIGHTNESS/V200037",
-    "MetadataAccess": [
-        "10.17199/BRIGHTNESS/V200037"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "ESS"
-    ],
-    "fulltext": "10.17199/BRIGHTNESS/V200037;openaire_data;2020-01-01;Sample Data from V20;https://doi.org/10.17199/BRIGHTNESS/V200037;https://github.com/ess-dmsc/ess_file_formats/wiki/HDF5;2020-01-01;2020-01-01;2018;Tobias Richter;ESS;ESS;1;OpenAccess",
-    "group": "ess",
-    "groups": [
-        {
-            "name": "ess"
-        }
-    ],
-    "name": "1cd8405f-e797-5def-bcc4-cfedd1140827",
-    "oai_identifier": [
-        "10.17199/BRIGHTNESS/V200037"
-    ],
-    "oai_set": [
-        "openaire_data"
-    ],
-    "state": "active",
-    "title": [
-        "\n        "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/ess-oai_datacite/full_1/json/1d5ac01b-ded2-56cf-8d8f-819ca5de95be.json b/oaitestdata/ess-oai_datacite/full_1/json/1d5ac01b-ded2-56cf-8d8f-819ca5de95be.json
deleted file mode 100644
index ee46692d..00000000
--- a/oaitestdata/ess-oai_datacite/full_1/json/1d5ac01b-ded2-56cf-8d8f-819ca5de95be.json
+++ /dev/null
@@ -1,35 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.17199/BRIGHTNESS/V200099",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://scicat.esss.se/scicat/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=10.17199/BRIGHTNESS/V200099",
-    "MetadataAccess": [
-        "10.17199/BRIGHTNESS/V200099"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "ESS"
-    ],
-    "fulltext": "10.17199/BRIGHTNESS/V200099;openaire_data;2020-01-01;Sample Data from V20;https://doi.org/10.17199/BRIGHTNESS/V200099;https://github.com/ess-dmsc/ess_file_formats/wiki/HDF5;2020-01-01;2020-01-01;2018;Tobias Richter;ESS;ESS;1;OpenAccess",
-    "group": "ess",
-    "groups": [
-        {
-            "name": "ess"
-        }
-    ],
-    "name": "1d5ac01b-ded2-56cf-8d8f-819ca5de95be",
-    "oai_identifier": [
-        "10.17199/BRIGHTNESS/V200099"
-    ],
-    "oai_set": [
-        "openaire_data"
-    ],
-    "state": "active",
-    "title": [
-        "\n        "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/ess-oai_datacite/full_1/json/1fd05938-ed2f-5fd1-9b97-eb0917026361.json b/oaitestdata/ess-oai_datacite/full_1/json/1fd05938-ed2f-5fd1-9b97-eb0917026361.json
deleted file mode 100644
index b90dfe82..00000000
--- a/oaitestdata/ess-oai_datacite/full_1/json/1fd05938-ed2f-5fd1-9b97-eb0917026361.json
+++ /dev/null
@@ -1,35 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.17199/BRIGHTNESS/V200060",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://scicat.esss.se/scicat/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=10.17199/BRIGHTNESS/V200060",
-    "MetadataAccess": [
-        "10.17199/BRIGHTNESS/V200060"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "ESS"
-    ],
-    "fulltext": "10.17199/BRIGHTNESS/V200060;openaire_data;2020-01-01;Sample Data from V20;https://doi.org/10.17199/BRIGHTNESS/V200060;https://github.com/ess-dmsc/ess_file_formats/wiki/HDF5;2020-01-01;2020-01-01;2018;Tobias Richter;ESS;ESS;1;OpenAccess",
-    "group": "ess",
-    "groups": [
-        {
-            "name": "ess"
-        }
-    ],
-    "name": "1fd05938-ed2f-5fd1-9b97-eb0917026361",
-    "oai_identifier": [
-        "10.17199/BRIGHTNESS/V200060"
-    ],
-    "oai_set": [
-        "openaire_data"
-    ],
-    "state": "active",
-    "title": [
-        "\n        "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/etsin-oai_dc/SET_1/json/00a47bcd-dcb6-525a-90a8-4ff023b9e0a2.json b/oaitestdata/etsin-oai_dc/SET_1/json/00a47bcd-dcb6-525a-90a8-4ff023b9e0a2.json
deleted file mode 100644
index 6076f618..00000000
--- a/oaitestdata/etsin-oai_dc/SET_1/json/00a47bcd-dcb6-525a-90a8-4ff023b9e0a2.json
+++ /dev/null
@@ -1,88 +0,0 @@
-{
-    "Contact": [
-        "Yhteiskuntatieteellinen tietoarkisto"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://etsin.avointiede.fi/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=00a47bcd-dcb6-525a-90a8-4ff023b9e0a2",
-    "PublicationTimestamp": "2016-03-10T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Yhteiskuntatieteellinen tietoarkisto"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Other (Not Open)"
-    ],
-    "SpatialCoverage": [
-        "Suomi",
-        "2004/2004"
-    ],
-    "TemporalCoverage": " period : ( None - 2004-07-01T11:59:59Z ) ",
-    "author": [
-        "Maanpuolustustiedotuksen suunnittelukunta (MTS)"
-    ],
-    "fulltext": "urn:nbn:fi:csc-kata20141222155931417387;2016-03-10T09:13:12Z;01905-2571-tampereen-yliopisto-yhteiskuntatieteellinen-tietoarkisto;Turvallisuuspolitiikka- ja maanpuolustustutkimus 2004;Finnish Opinions on Security Policy and National Defence 2004;Maanpuolustustiedotuksen suunnittelukunta (MTS);asevelvollisuus;konfliktit;kriisinhallinta;liittoutuminen;maanpuolustus;miinat;poliittinen k\u00e4ytt\u00e4ytyminen;poliittiset asenteet ja mielipiteet;puolustuspolitiikka;rauhankumppanuus;rauhanturvaaminen;terrorismi;turvallisuus;turvallisuus ja rauha;turvallisuuspolitiikka;ulkopolitiikka;yhteiskuntatieteet;Tutkimuksessa kartoitettiin vastaajien n\u00e4kemyksi\u00e4 ulko- ja turvallisuuspolitiikan sek\u00e4 kansainv\u00e4listen suhteiden hoidosta, sotilaallisesta liittoutumisesta ja sen eri vaihtoehdoista. Turvallisuuteen liittyen kysyttiin esimerkiksi, miten EU:n laajentuminen Baltiaan ja it\u00e4iseen Keski-Eurooppaan, Viron, Latvian ja Liettuan Nato-j\u00e4senyys, Ven\u00e4j\u00e4n julistama sota terrorismia vastaan sek\u00e4 Suomen sotilaallinen liittoutumattomuus vaikuttavat Suomen ja suomalaisten turvallisuuteen. Vastaajilta tiedusteltiin, luulevatko he Suomen olevan sitoutumassa Naton j\u00e4senyyteen.\r\n\r\nHaastateltujen suhtautumista Suomen ja Naton yhteisty\u00f6h\u00f6n (rauhankumppanuus, kriisinhallintaoperaatiot sek\u00e4 aseistuksen ja johtoj\u00e4rjestelmien yhteensovittaminen) kartoitettiin. Edelleen selvitettiin mielipiteit\u00e4 puolustusvoimille my\u00f6nnett\u00e4vist\u00e4 varoista, puolustusvoimien sotilaallisista teht\u00e4vist\u00e4, Suomen puolustusj\u00e4rjestelm\u00e4st\u00e4, Euroopan unionin yhteisen puolustuksen j\u00e4rjest\u00e4misest\u00e4 sek\u00e4 terrorismin syist\u00e4.\r\n\r\nVastaajat kertoivat, kuinka huolissaan he ovat nykyisest\u00e4 maailmanpoliittisesta tilanteesta. Tulevaisuuteen liittyvi\u00e4 huolenaiheita (esim. Israelin ja palestiinalaisten v\u00e4linen konflikti, ilmastonmuutos, kansainv\u00e4linen terrorismi, j\u00e4rjest\u00e4ytynyt kansainv\u00e4linen rikollisuus ja sotilaalliset selkkaukset) selvitettiin. Vastaajat arvioivat my\u00f6s, pit\u00e4isik\u00f6 Suomen liitty\u00e4 henkil\u00f6miinat kielt\u00e4v\u00e4\u00e4n niin sanottuun Ottawan sopimukseen. Taustamuuttujina olivat muun muassa vastaajan sukupuoli, ik\u00e4, ty\u00f6markkina- ja ammattiasema, koulutus, asuinl\u00e4\u00e4ni sek\u00e4 talouden tuloluokka.;Yhteiskuntatieteellinen tietoarkisto;Yhteiskuntatieteellinen tietoarkisto;2016-03-10;dataset;FSD2045;urn:nbn:fi:fsd:T-FSD2045;urn:nbn:fi:csc-kata20141222155931417387;http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20141222155931417387;Suomi;2004/2004;Other (Not Open)",
-    "group": "etsin",
-    "groups": [
-        {
-            "name": "etsin"
-        }
-    ],
-    "name": "00a47bcd-dcb6-525a-90a8-4ff023b9e0a2",
-    "notes": [
-        "Tutkimuksessa kartoitettiin vastaajien n\u00e4kemyksi\u00e4 ulko- ja turvallisuuspolitiikan sek\u00e4 kansainv\u00e4listen suhteiden hoidosta, sotilaallisesta liittoutumisesta ja sen eri vaihtoehdoista. Turvallisuuteen liittyen kysyttiin esimerkiksi, miten EU:n laajentuminen Baltiaan ja it\u00e4iseen Keski-Eurooppaan, Viron, Latvian ja Liettuan Nato-j\u00e4senyys, Ven\u00e4j\u00e4n julistama sota terrorismia vastaan sek\u00e4 Suomen sotilaallinen liittoutumattomuus vaikuttavat Suomen ja suomalaisten turvallisuuteen. Vastaajilta tiedusteltiin, luulevatko he Suomen olevan sitoutumassa Naton j\u00e4senyyteen.\r\n\r\nHaastateltujen suhtautumista Suomen ja Naton yhteisty\u00f6h\u00f6n (rauhankumppanuus, kriisinhallintaoperaatiot sek\u00e4 aseistuksen ja johtoj\u00e4rjestelmien yhteensovittaminen) kartoitettiin. Edelleen selvitettiin mielipiteit\u00e4 puolustusvoimille my\u00f6nnett\u00e4vist\u00e4 varoista, puolustusvoimien sotilaallisista teht\u00e4vist\u00e4, Suomen puolustusj\u00e4rjestelm\u00e4st\u00e4, Euroopan unionin yhteisen puolustuksen j\u00e4rjest\u00e4misest\u00e4 sek\u00e4 terrorismin syist\u00e4.\r\n\r\nVastaajat kertoivat, kuinka huolissaan he ovat nykyisest\u00e4 maailmanpoliittisesta tilanteesta. Tulevaisuuteen liittyvi\u00e4 huolenaiheita (esim. Israelin ja palestiinalaisten v\u00e4linen konflikti, ilmastonmuutos, kansainv\u00e4linen terrorismi, j\u00e4rjest\u00e4ytynyt kansainv\u00e4linen rikollisuus ja sotilaalliset selkkaukset) selvitettiin. Vastaajat arvioivat my\u00f6s, pit\u00e4isik\u00f6 Suomen liitty\u00e4 henkil\u00f6miinat kielt\u00e4v\u00e4\u00e4n niin sanottuun Ottawan sopimukseen. Taustamuuttujina olivat muun muassa vastaajan sukupuoli, ik\u00e4, ty\u00f6markkina- ja ammattiasema, koulutus, asuinl\u00e4\u00e4ni sek\u00e4 talouden tuloluokka."
-    ],
-    "oai_identifier": [
-        "00a47bcd-dcb6-525a-90a8-4ff023b9e0a2"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "asevelvollisuus"
-        },
-        {
-            "name": "konfliktit"
-        },
-        {
-            "name": "kriisinhallinta"
-        },
-        {
-            "name": "liittoutuminen"
-        },
-        {
-            "name": "maanpuolustus"
-        },
-        {
-            "name": "miinat"
-        },
-        {
-            "name": "miinat"
-        },
-        {
-            "name": "poliittiset asenteet ja mielipiteet"
-        },
-        {
-            "name": "puolustuspolitiikka"
-        },
-        {
-            "name": "rauhankumppanuus"
-        },
-        {
-            "name": "rauhanturvaaminen"
-        },
-        {
-            "name": "terrorismi"
-        }
-    ],
-    "title": [
-        "Turvallisuuspolitiikka- ja maanpuolustustutkimus 2004",
-        "Finnish Opinions on Security Policy and National Defence 2004"
-    ],
-    "url": "http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20141222155931417387"
-}
\ No newline at end of file
diff --git a/oaitestdata/etsin-oai_dc/SET_1/json/00a60eb0-a793-5700-9d0a-dce0388b5dad.json b/oaitestdata/etsin-oai_dc/SET_1/json/00a60eb0-a793-5700-9d0a-dce0388b5dad.json
deleted file mode 100644
index a4296ddb..00000000
--- a/oaitestdata/etsin-oai_dc/SET_1/json/00a60eb0-a793-5700-9d0a-dce0388b5dad.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "atm-data@helsinki.fi"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://etsin.avointiede.fi/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=00a60eb0-a793-5700-9d0a-dce0388b5dad",
-    "PublicationTimestamp": "2016-03-08T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "atm-data@helsinki.fi"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0"
-    ],
-    "SpatialCoverage": [
-        "DCMI-point: name=V\u00e4rri\u00f6; east=29.610137; north=67.755044; elevation=390;",
-        "2012-01-01T00:00:00Z/2012-12-31T23:59:59Z"
-    ],
-    "TempCoverageBegin": 192513067199,
-    "TempCoverageEnd": 63460972800,
-    "TemporalCoverage": " period : ( 6101-07-01T11:59:59Z - 2012-01-01T00:00:00Z ) ",
-    "TemporalCoverage:BeginDate": "6101-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2012-01-01T00:00:00Z",
-    "author": [
-        "Pasi Kolari"
-    ],
-    "fulltext": "urn:nbn:fi:csc-kata20160308084856246387;2016-03-08T06:48:56Z;university-of-helsinki-department-of-physics-division-of-atmospheric-sciences;V\u00e4rri\u00f6 SMEAR I tree gas exchange and diameter change - Pine shoot 2 transpiration - 2012;Pasi Kolari;http://www.yso.fi/onto/yso/p16571;Title: Pine shoot 2 transpiration \n\nDescription: Water vapour flux of pine shoot 2 per unit all-sided leaf area, positive sign = emission, data questionable at RH>75% \n\nVariable: F_H2O_tree2 \n\nUnit: mg m\u207b\u00b2 s\u207b\u00b9 \n\nSource: Automated chamber & Li-Cor Li-840 gas analyser \n\nCategory: Tree \n\n;atm-data@helsinki.fi;Pasi Kolari;2016-03-08;dataset;urn:nbn:fi:csc-ida2014011604685s;urn:nbn:fi:csc-ida-10x201703282015017315478v;urn:nbn:fi:csc-ida2014011604685v;urn:nbn:fi:csc-kata20160308084856246387;http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308084856246387;DCMI-point: name=V\u00e4rri\u00f6; east=29.610137; north=67.755044; elevation=390;;2012-01-01T00:00:00Z/2012-12-31T23:59:59Z;Creative Commons Attribution 4.0",
-    "group": "etsin",
-    "groups": [
-        {
-            "name": "etsin"
-        }
-    ],
-    "name": "00a60eb0-a793-5700-9d0a-dce0388b5dad",
-    "notes": [
-        "Title: Pine shoot 2 transpiration \n\nDescription: Water vapour flux of pine shoot 2 per unit all-sided leaf area, positive sign = emission, data questionable at RH>75% \n\nVariable: F_H2O_tree2 \n\nUnit: mg m\u207b\u00b2 s\u207b\u00b9 \n\nSource: Automated chamber & Li-Cor Li-840 gas analyser \n\nCategory: Tree \n\n"
-    ],
-    "oai_identifier": [
-        "00a60eb0-a793-5700-9d0a-dce0388b5dad"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "http www.yso.fi onto yso p"
-        }
-    ],
-    "title": [
-        "V\u00e4rri\u00f6 SMEAR I tree gas exchange and diameter change - Pine shoot 2 transpiration - 2012"
-    ],
-    "url": "http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308084856246387"
-}
\ No newline at end of file
diff --git a/oaitestdata/etsin-oai_dc/SET_1/json/00aa115d-cf02-5df4-bb1b-60df0f4b4bab.json b/oaitestdata/etsin-oai_dc/SET_1/json/00aa115d-cf02-5df4-bb1b-60df0f4b4bab.json
deleted file mode 100644
index dbec7319..00000000
--- a/oaitestdata/etsin-oai_dc/SET_1/json/00aa115d-cf02-5df4-bb1b-60df0f4b4bab.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "Tilastokeskus",
-        "CSC, Tieteen tietotekniikan keskus"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "Finnish"
-    ],
-    "MetaDataAccess": "https://etsin.avointiede.fi/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=00aa115d-cf02-5df4-bb1b-60df0f4b4bab",
-    "PublicationTimestamp": "2016-02-08T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Tilastokeskus",
-        "CSC, Tieteen tietotekniikan keskus"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Other (Open)"
-    ],
-    "SpatialCoverage": [
-        "Suomi",
-        "2014/2014"
-    ],
-    "TemporalCoverage": " period : ( None - 2014-07-01T11:59:59Z ) ",
-    "author": [
-        "Tilastokeskus, Official Statistics of Finland",
-        "Kylli Ek"
-    ],
-    "fulltext": "urn:nbn:fi:csc-kata00001000000000000559;2016-02-08T15:29:19Z;ilmatieteen-laitos-finnish-meteorological-institute;Tieliikenneonnettomuudet 2014;Road traffic accidents 2014;Tilastokeskus, Official Statistics of Finland;Kylli Ek;Paituli;http://www.yso.fi/onto/koko/p36051;http://www.yso.fi/onto/koko/p71582;Aineisto sis\u00e4lt\u00e4\u00e4 Suomessa poliisin tietoon tulleet ja Tilastokeskukselle ilmoittamat henkil\u00f6vahinkoon johtaneet tieliikenteen onnettomuudet, joilla on koordinaattitiedot. \r\n\r\nAineisto sis\u00e4lt\u00e4\u00e4 seuraavat muuttujat:\r\nonnettomuuden tapahtumavuosi (VVONN)  \r\nonnettomuuden tapahtumakuukausi (KKONN)  \r\nonnettomuuden kellonaika (KELLO)  \r\nonnettomuuden vakavuus (VAKAV):  \r\n1=kuolemaan johtanut onnettomuus  \r\n2=loukkaantumiseen johtanut onnettomuus  \r\nonnettomuustyyppi (ONNTYYPPI):  \r\n0=Samat ajosuunnat (ajo suoraan)  \r\n1=Samat ajosuunnat (ajo k\u00e4\u00e4ntyen)  \r\n2= Vastakkaiset ajosuunnat (ajo suoraan)  \r\n3=Vastakkaiset ajosuunnat (ajo k\u00e4\u00e4ntyen)  \r\n4=Riste\u00e4v\u00e4t ajosuunnat (ajo suoraan)  \r\n5=Riste\u00e4v\u00e4t ajosuunnat (ajo k\u00e4\u00e4ntyen)  \r\n6=Jalankulkijaonnettomuus (suojatiell\u00e4)  \r\n7=Jalankulkijaonnettomuus (muualla)  \r\n8=Tielt\u00e4 suistuminen  \r\n9=Muu onnettomuus,  \r\nhenkil\u00f6autojen ja pakettiautojen lukum\u00e4\u00e4r\u00e4 onnettomuudessa (LKMHAPA)  \r\nlinja-autojen ja kuorma-autojen lukum\u00e4\u00e4r\u00e4 onnettomuudessa (LKMLAKA)  \r\njalankulkijoiden lukum\u00e4\u00e4r\u00e4 onnettomuudessa (LKMJK)  \r\npolkupy\u00f6r\u00e4ilij\u00f6iden lukum\u00e4\u00e4r\u00e4 onnettomuudessa (LKMPP)  \r\nmopojen lukum\u00e4\u00e4r\u00e4 onnettomuudessa (LKMMO)  \r\nmoottoripy\u00f6rien lukum\u00e4\u00e4r\u00e4 onnettomuudessa (LKMMP)  \r\nmuiden kulkuneuvojen lukum\u00e4\u00e4r\u00e4 onnettomuudessa (LKMMUUKULK)  \r\nonnettomuuden koordinaattitiedot (ETRS-TM35FIN)\r\n\r\nLis\u00e4tietoja: [Tilastokeskus, Tieliikenneonnettomuudet](http://www.stat.fi/tup/rajapintapalvelut/tieliikenneonnettomuudet.html)\r\n\r\nMuunnos Shape formaattiin on tehty CSC:ll\u00e4.  \r\nKoordinaattij\u00e4rjestelm\u00e4: ETRS-TM35FIN (EPSG:3067);Road traffic accidents involving personal injury known to the police in Finland and reported to Statistics Finland, which have co-ordinate data. \r\n\r\nThe data cover the following information:  \r\nvvonn= year of the accident  \r\nkkonn= month of the accident  \r\nkello= time of the accident  \r\nvakav= seriousness of the accident:  \r\n    1=accident resulting in death  \r\n    2= accident resulting in injury  \r\nonntyyppi= type of accident:  \r\n    0=Same direction of travel (going straight)  \r\n    1=Same direction of travel (turning)  \r\n    2=Opposite direction of travel (going straight)  \r\n    3=Opposite direction of travel (turning)  \r\n    4=Intersecting direction of travel (going straight)  \r\n    5=Intersecting direction of travel (turning)  \r\n    6=Pedestrian accident (on pedestrian crossing)  \r\n    7=Pedestrian accident (elsewhere)  \r\n    8=Running off the road  \r\n    9=Other accident  \r\nlkmhapa= number of passenger cars and vans in the accident  \r\nlkmlaka= number of buses and lorries in the accident  \r\nlkmjk= number of pedestrians in the accident  \r\nlkmpp= number of cyclists in the accident  \r\nlkmmo= number of mopeds in the accident  \r\nlkmmp= number of motor cycles in the accident  \r\nlkmmuukulk= number of other vehicles in the accident  \r\nx= x coordinate of the accident  \r\ny= y coordinate of the accident  \r\n\r\nAdditional information: [Statistics Finland, Road traffic accidents](http://www.stat.fi/tup/rajapintapalvelut/tieliikenneonnettomuudet.html)\r\n\r\nThe data format has been changed to Shape at CSC.  \r\nCoordinate Reference System: ETRS89 / ETRS-TM35FIN (EPSG:3067);CSC, Tieteen tietotekniikan keskus;Tilastokeskus;2016-02-08;dataset;urn:nbn:fi:csc-kata00001000000000000558;urn:nbn:fi:csc-kata00001000000000000560;urn:nbn:fi:csc-kata00001000000000000559;http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata00001000000000000559;fin;Suomi;2014/2014;Other (Open)",
-    "group": "etsin",
-    "groups": [
-        {
-            "name": "etsin"
-        }
-    ],
-    "name": "00aa115d-cf02-5df4-bb1b-60df0f4b4bab",
-    "notes": [
-        "Aineisto sis\u00e4lt\u00e4\u00e4 Suomessa poliisin tietoon tulleet ja Tilastokeskukselle ilmoittamat henkil\u00f6vahinkoon johtaneet tieliikenteen onnettomuudet, joilla on koordinaattitiedot. \r\n\r\nAineisto sis\u00e4lt\u00e4\u00e4 seuraavat muuttujat:\r\nonnettomuuden tapahtumavuosi (VVONN)  \r\nonnettomuuden tapahtumakuukausi (KKONN)  \r\nonnettomuuden kellonaika (KELLO)  \r\nonnettomuuden vakavuus (VAKAV):  \r\n1=kuolemaan johtanut onnettomuus  \r\n2=loukkaantumiseen johtanut onnettomuus  \r\nonnettomuustyyppi (ONNTYYPPI):  \r\n0=Samat ajosuunnat (ajo suoraan)  \r\n1=Samat ajosuunnat (ajo k\u00e4\u00e4ntyen)  \r\n2= Vastakkaiset ajosuunnat (ajo suoraan)  \r\n3=Vastakkaiset ajosuunnat (ajo k\u00e4\u00e4ntyen)  \r\n4=Riste\u00e4v\u00e4t ajosuunnat (ajo suoraan)  \r\n5=Riste\u00e4v\u00e4t ajosuunnat (ajo k\u00e4\u00e4ntyen)  \r\n6=Jalankulkijaonnettomuus (suojatiell\u00e4)  \r\n7=Jalankulkijaonnettomuus (muualla)  \r\n8=Tielt\u00e4 suistuminen  \r\n9=Muu onnettomuus,  \r\nhenkil\u00f6autojen ja pakettiautojen lukum\u00e4\u00e4r\u00e4 onnettomuudessa (LKMHAPA)  \r\nlinja-autojen ja kuorma-autojen lukum\u00e4\u00e4r\u00e4 onnettomuudessa (LKMLAKA)  \r\njalankulkijoiden lukum\u00e4\u00e4r\u00e4 onnettomuudessa (LKMJK)  \r\npolkupy\u00f6r\u00e4ilij\u00f6iden lukum\u00e4\u00e4r\u00e4 onnettomuudessa (LKMPP)  \r\nmopojen lukum\u00e4\u00e4r\u00e4 onnettomuudessa (LKMMO)  \r\nmoottoripy\u00f6rien lukum\u00e4\u00e4r\u00e4 onnettomuudessa (LKMMP)  \r\nmuiden kulkuneuvojen lukum\u00e4\u00e4r\u00e4 onnettomuudessa (LKMMUUKULK)  \r\nonnettomuuden koordinaattitiedot (ETRS-TM35FIN)\r\n\r\nLis\u00e4tietoja: [Tilastokeskus, Tieliikenneonnettomuudet](http://www.stat.fi/tup/rajapintapalvelut/tieliikenneonnettomuudet.html)\r\n\r\nMuunnos Shape formaattiin on tehty CSC:ll\u00e4.  \r\nKoordinaattij\u00e4rjestelm\u00e4: ETRS-TM35FIN (EPSG:3067)",
-        "Road traffic accidents involving personal injury known to the police in Finland and reported to Statistics Finland, which have co-ordinate data. \r\n\r\nThe data cover the following information:  \r\nvvonn= year of the accident  \r\nkkonn= month of the accident  \r\nkello= time of the accident  \r\nvakav= seriousness of the accident:  \r\n    1=accident resulting in death  \r\n    2= accident resulting in injury  \r\nonntyyppi= type of accident:  \r\n    0=Same direction of travel (going straight)  \r\n    1=Same direction of travel (turning)  \r\n    2=Opposite direction of travel (going straight)  \r\n    3=Opposite direction of travel (turning)  \r\n    4=Intersecting direction of travel (going straight)  \r\n    5=Intersecting direction of travel (turning)  \r\n    6=Pedestrian accident (on pedestrian crossing)  \r\n    7=Pedestrian accident (elsewhere)  \r\n    8=Running off the road  \r\n    9=Other accident  \r\nlkmhapa= number of passenger cars and vans in the accident  \r\nlkmlaka= number of buses and lorries in the accident  \r\nlkmjk= number of pedestrians in the accident  \r\nlkmpp= number of cyclists in the accident  \r\nlkmmo= number of mopeds in the accident  \r\nlkmmp= number of motor cycles in the accident  \r\nlkmmuukulk= number of other vehicles in the accident  \r\nx= x coordinate of the accident  \r\ny= y coordinate of the accident  \r\n\r\nAdditional information: [Statistics Finland, Road traffic accidents](http://www.stat.fi/tup/rajapintapalvelut/tieliikenneonnettomuudet.html)\r\n\r\nThe data format has been changed to Shape at CSC.  \r\nCoordinate Reference System: ETRS89 / ETRS-TM35FIN (EPSG:3067)"
-    ],
-    "oai_identifier": [
-        "00aa115d-cf02-5df4-bb1b-60df0f4b4bab"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Paituli"
-        },
-        {
-            "name": "http www.yso.fi onto koko p"
-        },
-        {
-            "name": "http www.yso.fi onto koko p"
-        }
-    ],
-    "title": [
-        "Tieliikenneonnettomuudet 2014",
-        "Road traffic accidents 2014"
-    ],
-    "url": "http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata00001000000000000559"
-}
\ No newline at end of file
diff --git a/oaitestdata/etsin-oai_dc/SET_1/json/00ac1142-e653-5438-8465-667f6e81aff0.json b/oaitestdata/etsin-oai_dc/SET_1/json/00ac1142-e653-5438-8465-667f6e81aff0.json
deleted file mode 100644
index 6e524b2a..00000000
--- a/oaitestdata/etsin-oai_dc/SET_1/json/00ac1142-e653-5438-8465-667f6e81aff0.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "atm-data@helsinki.fi"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://etsin.avointiede.fi/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=00ac1142-e653-5438-8465-667f6e81aff0",
-    "PublicationTimestamp": "2016-03-08T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "atm-data@helsinki.fi"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0"
-    ],
-    "SpatialCoverage": [
-        "DCMI-point: name=Hyyti\u00e4l\u00e4; east=24.294795; north=61.847463 elevation=179",
-        "2012-01-01T00:00:00Z/2012-12-31T23:59:59Z"
-    ],
-    "TempCoverageBegin": 92982427199,
-    "TempCoverageEnd": 63460972800,
-    "TemporalCoverage": " period : ( 2947-07-01T11:59:59Z - 2012-01-01T00:00:00Z ) ",
-    "TemporalCoverage:BeginDate": "2947-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2012-01-01T00:00:00Z",
-    "author": [
-        "Pasi Aalto"
-    ],
-    "fulltext": "urn:nbn:fi:csc-kata20160308110328820538;2016-03-08T09:03:28Z;university-of-helsinki-department-of-physics-division-of-atmospheric-sciences;Hyyti\u00e4l\u00e4 SMEAR II eddy radiation tower - N of removed spikes (2) - 2012;Pasi Aalto;http://www.yso.fi/onto/yso/p26208;Title: N of removed spikes (2) \n\nDescription: Maximum amount of removed spikes, i.e. outliers in a 30min period, radiation tower 23 m height, secondary flux measurement \n\nVariable: err_packet_radtow \n\nUnit:  \n\nSource: Gill Solent HS1199 anemometer/thermometer & LI-COR LI-6262 gas analyzer \n\nCategory: Flux ancillary data \n\n;atm-data@helsinki.fi;2016-03-08;dataset;urn:nbn:fi:csc-ida2014010800881v;urn:nbn:fi:csc-ida2014010800881s;urn:nbn:fi:csc-kata20160308110328820538;http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308110328820538;DCMI-point: name=Hyyti\u00e4l\u00e4; east=24.294795; north=61.847463 elevation=179;2012-01-01T00:00:00Z/2012-12-31T23:59:59Z;Creative Commons Attribution 4.0",
-    "group": "etsin",
-    "groups": [
-        {
-            "name": "etsin"
-        }
-    ],
-    "name": "00ac1142-e653-5438-8465-667f6e81aff0",
-    "notes": [
-        "Title: N of removed spikes (2) \n\nDescription: Maximum amount of removed spikes, i.e. outliers in a 30min period, radiation tower 23 m height, secondary flux measurement \n\nVariable: err_packet_radtow \n\nUnit:  \n\nSource: Gill Solent HS1199 anemometer/thermometer & LI-COR LI-6262 gas analyzer \n\nCategory: Flux ancillary data \n\n"
-    ],
-    "oai_identifier": [
-        "00ac1142-e653-5438-8465-667f6e81aff0"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "http www.yso.fi onto yso p"
-        }
-    ],
-    "title": [
-        "Hyyti\u00e4l\u00e4 SMEAR II eddy radiation tower - N of removed spikes (2) - 2012"
-    ],
-    "url": "http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308110328820538"
-}
\ No newline at end of file
diff --git a/oaitestdata/etsin-oai_dc/SET_1/json/0a052e56-a04a-51f9-992e-d9391be8074a.json b/oaitestdata/etsin-oai_dc/SET_1/json/0a052e56-a04a-51f9-992e-d9391be8074a.json
deleted file mode 100644
index 3a298041..00000000
--- a/oaitestdata/etsin-oai_dc/SET_1/json/0a052e56-a04a-51f9-992e-d9391be8074a.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "atm-data@helsinki.fi"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://etsin.avointiede.fi/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=0a052e56-a04a-51f9-992e-d9391be8074a",
-    "PublicationTimestamp": "2016-03-08T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "atm-data@helsinki.fi"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0"
-    ],
-    "SpatialCoverage": [
-        "DCMI-point: name=Kumpula; east=24.961227; north=60.202887 elevation=45;",
-        "2009-01-01T00:00:00Z/2009-12-31T23:59:59Z"
-    ],
-    "TempCoverageBegin": 303309575999,
-    "TempCoverageEnd": 63366364800,
-    "TemporalCoverage": " period : ( 9612-07-01T11:59:59Z - 2009-01-01T00:00:00Z ) ",
-    "TemporalCoverage:BeginDate": "9612-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2009-01-01T00:00:00Z",
-    "author": [
-        "Pasi Aalto"
-    ],
-    "fulltext": "urn:nbn:fi:csc-kata20160308102850717672;2016-03-08T08:28:50Z;university-of-helsinki-department-of-physics-division-of-atmospheric-sciences;Helsinki Kumpula SMEAR III meteorology - Air pressure - 2009;Pasi Aalto;http://www.yso.fi/onto/ysa/Y101807;http://www.yso.fi/onto/yso/p5394;ilmanpaine;Title: Air pressure \n\nDescription: Sea level pressure, Physicum roof, (hPa) \n\nVariable: p0 \n\nUnit: hPa \n\nSource: saa \n\nCategory: Meteorology \n\n;atm-data@helsinki.fi;2016-03-08;dataset;urn:nbn:fi:csc-ida20140120144345v;urn:nbn:fi:csc-ida20140120144345s;urn:nbn:fi:csc-ida-10x201703282015017313760v;urn:nbn:fi:csc-kata20160308102850717672;http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308102850717672;DCMI-point: name=Kumpula; east=24.961227; north=60.202887 elevation=45;;2009-01-01T00:00:00Z/2009-12-31T23:59:59Z;Creative Commons Attribution 4.0",
-    "group": "etsin",
-    "groups": [
-        {
-            "name": "etsin"
-        }
-    ],
-    "name": "0a052e56-a04a-51f9-992e-d9391be8074a",
-    "notes": [
-        "Title: Air pressure \n\nDescription: Sea level pressure, Physicum roof, (hPa) \n\nVariable: p0 \n\nUnit: hPa \n\nSource: saa \n\nCategory: Meteorology \n\n"
-    ],
-    "oai_identifier": [
-        "0a052e56-a04a-51f9-992e-d9391be8074a"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "http www.yso.fi onto ysa Y"
-        },
-        {
-            "name": "http www.yso.fi onto yso p"
-        },
-        {
-            "name": "ilmanpaine"
-        }
-    ],
-    "title": [
-        "Helsinki Kumpula SMEAR III meteorology - Air pressure - 2009"
-    ],
-    "url": "http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308102850717672"
-}
\ No newline at end of file
diff --git a/oaitestdata/etsin-oai_dc/SET_1/json/0a073923-ab07-5ab4-b11f-0e7c8eb82825.json b/oaitestdata/etsin-oai_dc/SET_1/json/0a073923-ab07-5ab4-b11f-0e7c8eb82825.json
deleted file mode 100644
index 8e14014d..00000000
--- a/oaitestdata/etsin-oai_dc/SET_1/json/0a073923-ab07-5ab4-b11f-0e7c8eb82825.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "Suomen ymp\u00e4rist\u00f6keskus",
-        "CSC, Tieteen tietotekniikan keskus"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "Finnish"
-    ],
-    "MetaDataAccess": "https://etsin.avointiede.fi/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=0a073923-ab07-5ab4-b11f-0e7c8eb82825",
-    "PublicationTimestamp": "2016-10-11T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Suomen ymp\u00e4rist\u00f6keskus",
-        "CSC, Tieteen tietotekniikan keskus"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0"
-    ],
-    "SpatialCoverage": [
-        "Suomi",
-        "2006/2012"
-    ],
-    "TemporalCoverage": " period : ( None - 2006-07-01T11:59:59Z ) ",
-    "author": [
-        "Suomen ymp\u00e4rist\u00f6keskus, Finnish environment institute"
-    ],
-    "fulltext": "urn:nbn:fi:csc-kata00001000000000000733;2016-10-11T07:41:01Z;7020017-suomen-ymparistokeskus;CORINE maanpeitemuutokset, 5ha 2006-2012;CORINE land cover changes, 5ha, 2006-2012;Suomen ymp\u00e4rist\u00f6keskus, Finnish environment institute;Paituli;http://www.yso.fi/onto/koko/p36412;CORINE Land Cover 2012 kuvaa koko Suomen maank\u00e4ytt\u00f6\u00e4 ja maanpeitett\u00e4 vuonna 2012. SYKEss\u00e4 EU:n Copernicus Gioland-hankkeessa tuotettiin Suomen alueelta maanpeiteaineistot sek\u00e4 laadittiin maanpeitteen muutoksia v\u00e4lill\u00e4 2006-2012 kuvaavat aineistot. Aineistot luotiin kahdella tarkkuustasolla: EU-vaatimusten mukaisesti ja kansalliseen k\u00e4ytt\u00f6\u00f6n. Aineisto koostuu rasterimuotoisesta paikkatietokannasta (erotuskyky 20 * 20 m) ja vektorimuotoisesta paikkatietokannasta, jossa pienin maastossa erottuva alue on v\u00e4hint\u00e4\u00e4n 25 ha ja kapeimmillaan 100 metri\u00e4.\r\n\r\nKansallisen muutosaineiston 2006-2012 pienin kuvio on 0,5 ha ja eurooppalaisen 5 ha.\r\n  Suoria pikselien vertailuja vuoteen 2006 ei suositella tekem\u00e4\u00e4n vaan muutokset kannattaa hakea muutosaineistosta.   \r\n\r\nAineisto on tuotettu SYKEss\u00e4 olemassa oleviin paikkatietoaineistoihin sek\u00e4 satelliittikuvatulkintaan perustuen. Vektoriaineisto tuotettiin yleist\u00e4m\u00e4ll\u00e4 rasteriaineistoa EEA:n CORINE-s\u00e4\u00e4nt\u00f6jen mukaan.\r\n\r\nVektoriaineistoissa maank\u00e4ytt\u00f6\u00e4/maanpeitett\u00e4 kuvataan kolmitasoisella hierarkisella luokittelulla.\r\n\r\n Koordinaattij\u00e4rjestelm\u00e4: ETRS89 / ETRS-TM35FIN (EPSG:3067) ;CORINE Land Cover 2012 dataset provides information on Finnish land cover and land use on 2012, and its changes from 2006 to 2012. The data was produced as a part of the European Gioland 2012 project. \r\n\r\nDataset includes several spatial layers: \r\n\r\n* CLC raster (resolution of 20x20 m) \r\n* CLC vector (minimum mapping unit 25 hectares and minimum width 100 m). \r\n* Source raster (resolution of 20x20 m) on the source data used in the interpretation \r\n* Age raster (resolution of 20x20 m) on the year of the source information \r\n* Change vector (minimum mapping unit 5 hectares) \r\n* Change raster (minimum mapping unit 0,5 hectares)\r\n \r\nThe dataset has been produced in Finnish Environment Institute (SYKE), based on automated interpretation of satellite images and data integration with existing digital map data. The vector dataset was produced from raster data by generalization according to the CORINE 2012 project class definitions.\r\n\r\nThe nomenclature of the vector data has 3 hierarchy levels. The first level classes are: artificial surfaces, agricultural areas, forests and seminatural areas, wetlands and water. The second level has 15 classes and the third level 44 sub-classes. The raster dataset has an additional fourth, national class in some of the sub-classes.\r\n\r\nCoordinate Reference System: ETRS89 / ETRS-TM35FIN (EPSG:3067) ;CSC, Tieteen tietotekniikan keskus;Suomen ymp\u00e4rist\u00f6keskus;2016-10-11;dataset;urn:nbn:fi:csc-kata00001000000000000732;urn:nbn:fi:csc-kata00001000000000000733;http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata00001000000000000733;fin;Suomi;2006/2012;Creative Commons Attribution 4.0",
-    "group": "etsin",
-    "groups": [
-        {
-            "name": "etsin"
-        }
-    ],
-    "name": "0a073923-ab07-5ab4-b11f-0e7c8eb82825",
-    "notes": [
-        "CORINE Land Cover 2012 kuvaa koko Suomen maank\u00e4ytt\u00f6\u00e4 ja maanpeitett\u00e4 vuonna 2012. SYKEss\u00e4 EU:n Copernicus Gioland-hankkeessa tuotettiin Suomen alueelta maanpeiteaineistot sek\u00e4 laadittiin maanpeitteen muutoksia v\u00e4lill\u00e4 2006-2012 kuvaavat aineistot. Aineistot luotiin kahdella tarkkuustasolla: EU-vaatimusten mukaisesti ja kansalliseen k\u00e4ytt\u00f6\u00f6n. Aineisto koostuu rasterimuotoisesta paikkatietokannasta (erotuskyky 20 * 20 m) ja vektorimuotoisesta paikkatietokannasta, jossa pienin maastossa erottuva alue on v\u00e4hint\u00e4\u00e4n 25 ha ja kapeimmillaan 100 metri\u00e4.\r\n\r\nKansallisen muutosaineiston 2006-2012 pienin kuvio on 0,5 ha ja eurooppalaisen 5 ha.\r\n  Suoria pikselien vertailuja vuoteen 2006 ei suositella tekem\u00e4\u00e4n vaan muutokset kannattaa hakea muutosaineistosta.   \r\n\r\nAineisto on tuotettu SYKEss\u00e4 olemassa oleviin paikkatietoaineistoihin sek\u00e4 satelliittikuvatulkintaan perustuen. Vektoriaineisto tuotettiin yleist\u00e4m\u00e4ll\u00e4 rasteriaineistoa EEA:n CORINE-s\u00e4\u00e4nt\u00f6jen mukaan.\r\n\r\nVektoriaineistoissa maank\u00e4ytt\u00f6\u00e4/maanpeitett\u00e4 kuvataan kolmitasoisella hierarkisella luokittelulla.\r\n\r\n Koordinaattij\u00e4rjestelm\u00e4: ETRS89 / ETRS-TM35FIN (EPSG:3067) ",
-        "CORINE Land Cover 2012 dataset provides information on Finnish land cover and land use on 2012, and its changes from 2006 to 2012. The data was produced as a part of the European Gioland 2012 project. \r\n\r\nDataset includes several spatial layers: \r\n\r\n* CLC raster (resolution of 20x20 m) \r\n* CLC vector (minimum mapping unit 25 hectares and minimum width 100 m). \r\n* Source raster (resolution of 20x20 m) on the source data used in the interpretation \r\n* Age raster (resolution of 20x20 m) on the year of the source information \r\n* Change vector (minimum mapping unit 5 hectares) \r\n* Change raster (minimum mapping unit 0,5 hectares)\r\n \r\nThe dataset has been produced in Finnish Environment Institute (SYKE), based on automated interpretation of satellite images and data integration with existing digital map data. The vector dataset was produced from raster data by generalization according to the CORINE 2012 project class definitions.\r\n\r\nThe nomenclature of the vector data has 3 hierarchy levels. The first level classes are: artificial surfaces, agricultural areas, forests and seminatural areas, wetlands and water. The second level has 15 classes and the third level 44 sub-classes. The raster dataset has an additional fourth, national class in some of the sub-classes.\r\n\r\nCoordinate Reference System: ETRS89 / ETRS-TM35FIN (EPSG:3067) "
-    ],
-    "oai_identifier": [
-        "0a073923-ab07-5ab4-b11f-0e7c8eb82825"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Paituli"
-        },
-        {
-            "name": "http www.yso.fi onto koko p"
-        }
-    ],
-    "title": [
-        "CORINE maanpeitemuutokset, 5ha 2006-2012",
-        "CORINE land cover changes, 5ha, 2006-2012"
-    ],
-    "url": "http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata00001000000000000733"
-}
\ No newline at end of file
diff --git a/oaitestdata/etsin-oai_dc/SET_1/json/0a135963-f673-505a-bdce-12d6001245ca.json b/oaitestdata/etsin-oai_dc/SET_1/json/0a135963-f673-505a-bdce-12d6001245ca.json
deleted file mode 100644
index 2e10ab43..00000000
--- a/oaitestdata/etsin-oai_dc/SET_1/json/0a135963-f673-505a-bdce-12d6001245ca.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "atm-data@helsinki.fi"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://etsin.avointiede.fi/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=0a135963-f673-505a-bdce-12d6001245ca",
-    "PublicationTimestamp": "2016-03-08T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "atm-data@helsinki.fi"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0"
-    ],
-    "SpatialCoverage": [
-        "DCMI-point: name=V\u00e4rri\u00f6; east=29.610137; north=67.755044; elevation=390;",
-        "2002-01-01T00:00:00Z/2002-12-31T23:59:59Z"
-    ],
-    "TempCoverageBegin": 192513067199,
-    "TempCoverageEnd": 63145440000,
-    "TemporalCoverage": " period : ( 6101-07-01T11:59:59Z - 2002-01-01T00:00:00Z ) ",
-    "TemporalCoverage:BeginDate": "6101-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2002-01-01T00:00:00Z",
-    "author": [
-        "Pasi Aalto"
-    ],
-    "fulltext": "urn:nbn:fi:csc-kata20160308092807560912;2016-03-08T07:28:07Z;university-of-helsinki-department-of-physics-division-of-atmospheric-sciences;V\u00e4rri\u00f6 SMEAR I meteorology, gases and soil - Wind speed 4.4 m - 2002;Pasi Aalto;http://www.yso.fi/onto/yso/p5394;Title: Wind speed 4.4 m \n\nDescription: Wind speed 4.4 m \n\nVariable: WS3 \n\nUnit: m s\u207b\u00b9 \n\nSource: Vector A100R anemometer \n\nCategory: Meteorology \n\n;atm-data@helsinki.fi;2016-03-08;dataset;urn:nbn:fi:csc-ida2014011535518s;urn:nbn:fi:csc-ida2014011535518v;urn:nbn:fi:csc-ida-10x201703282015017315667v;urn:nbn:fi:csc-kata20160308092807560912;http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308092807560912;DCMI-point: name=V\u00e4rri\u00f6; east=29.610137; north=67.755044; elevation=390;;2002-01-01T00:00:00Z/2002-12-31T23:59:59Z;Creative Commons Attribution 4.0",
-    "group": "etsin",
-    "groups": [
-        {
-            "name": "etsin"
-        }
-    ],
-    "name": "0a135963-f673-505a-bdce-12d6001245ca",
-    "notes": [
-        "Title: Wind speed 4.4 m \n\nDescription: Wind speed 4.4 m \n\nVariable: WS3 \n\nUnit: m s\u207b\u00b9 \n\nSource: Vector A100R anemometer \n\nCategory: Meteorology \n\n"
-    ],
-    "oai_identifier": [
-        "0a135963-f673-505a-bdce-12d6001245ca"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "http www.yso.fi onto yso p"
-        }
-    ],
-    "title": [
-        "V\u00e4rri\u00f6 SMEAR I meteorology, gases and soil - Wind speed 4.4 m - 2002"
-    ],
-    "url": "http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308092807560912"
-}
\ No newline at end of file
diff --git a/oaitestdata/etsin-oai_dc/SET_1/json/0a1f47dc-eb8b-529c-afa9-80eefba2e9b5.json b/oaitestdata/etsin-oai_dc/SET_1/json/0a1f47dc-eb8b-529c-afa9-80eefba2e9b5.json
deleted file mode 100644
index 7f0dc79e..00000000
--- a/oaitestdata/etsin-oai_dc/SET_1/json/0a1f47dc-eb8b-529c-afa9-80eefba2e9b5.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "atm-data@helsinki.fi"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://etsin.avointiede.fi/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=0a1f47dc-eb8b-529c-afa9-80eefba2e9b5",
-    "PublicationTimestamp": "2016-03-08T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "atm-data@helsinki.fi"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0"
-    ],
-    "SpatialCoverage": [
-        "DCMI-point: name=V\u00e4rri\u00f6; east=29.610137; north=67.755044; elevation=390;",
-        "2007-01-01T00:00:00Z/2007-12-31T23:59:59Z"
-    ],
-    "TempCoverageBegin": 192513067199,
-    "TempCoverageEnd": 63303206400,
-    "TemporalCoverage": " period : ( 6101-07-01T11:59:59Z - 2007-01-01T00:00:00Z ) ",
-    "TemporalCoverage:BeginDate": "6101-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2007-01-01T00:00:00Z",
-    "author": [
-        "Pasi Kolari",
-        "Tapani Hopkins"
-    ],
-    "fulltext": "urn:nbn:fi:csc-kata20160308081725975460;2016-03-08T06:17:26Z;university-of-helsinki-department-of-physics-division-of-atmospheric-sciences;V\u00e4rri\u00f6 SMEAR I tree gas exchange and diameter change - Pine shoot 2 transpiration - 2007;Tapani Hopkins;Pasi Kolari;Pasi Kolari;http://www.yso.fi/onto/yso/p16571;Title: Pine shoot 2 transpiration \n\nDescription: Water vapour flux of pine shoot 2 per unit all-sided leaf area, positive sign = emission, data questionable at RH>75% \n\nVariable: F_H2O_tree2 \n\nUnit: mg m\u207b\u00b2 s\u207b\u00b9 \n\nSource: Automated chamber & Li-Cor Li-840 gas analyser \n\nCategory: Tree \n\n;atm-data@helsinki.fi;Ville Vakkari;Pasi Kolari;2016-03-08;dataset;urn:nbn:fi:csc-ida-10x201703282015017315583v;urn:nbn:fi:csc-ida-10x201512212015014127775v;urn:nbn:fi:csc-ida2014011531572s;urn:nbn:fi:csc-kata20160308081725975460;http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308081725975460;DCMI-point: name=V\u00e4rri\u00f6; east=29.610137; north=67.755044; elevation=390;;2007-01-01T00:00:00Z/2007-12-31T23:59:59Z;Creative Commons Attribution 4.0",
-    "group": "etsin",
-    "groups": [
-        {
-            "name": "etsin"
-        }
-    ],
-    "name": "0a1f47dc-eb8b-529c-afa9-80eefba2e9b5",
-    "notes": [
-        "Title: Pine shoot 2 transpiration \n\nDescription: Water vapour flux of pine shoot 2 per unit all-sided leaf area, positive sign = emission, data questionable at RH>75% \n\nVariable: F_H2O_tree2 \n\nUnit: mg m\u207b\u00b2 s\u207b\u00b9 \n\nSource: Automated chamber & Li-Cor Li-840 gas analyser \n\nCategory: Tree \n\n"
-    ],
-    "oai_identifier": [
-        "0a1f47dc-eb8b-529c-afa9-80eefba2e9b5"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "http www.yso.fi onto yso p"
-        }
-    ],
-    "title": [
-        "V\u00e4rri\u00f6 SMEAR I tree gas exchange and diameter change - Pine shoot 2 transpiration - 2007"
-    ],
-    "url": "http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308081725975460"
-}
\ No newline at end of file
diff --git a/oaitestdata/etsin-oai_dc/SET_1/json/0a29e191-dccf-518b-b317-e21ed8f924cc.json b/oaitestdata/etsin-oai_dc/SET_1/json/0a29e191-dccf-518b-b317-e21ed8f924cc.json
deleted file mode 100644
index 4b807e84..00000000
--- a/oaitestdata/etsin-oai_dc/SET_1/json/0a29e191-dccf-518b-b317-e21ed8f924cc.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "atm-data@helsinki.fi"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://etsin.avointiede.fi/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=0a29e191-dccf-518b-b317-e21ed8f924cc",
-    "PublicationTimestamp": "2016-03-08T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "atm-data@helsinki.fi"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0"
-    ],
-    "SpatialCoverage": [
-        "DCMI-point: name=V\u00e4rri\u00f6; east=29.610137; north=67.755044; elevation=390;",
-        "1995-01-01T00:00:00Z/1995-12-31T23:59:59Z"
-    ],
-    "TempCoverageBegin": 192513067199,
-    "TempCoverageEnd": 62924515200,
-    "TemporalCoverage": " period : ( 6101-07-01T11:59:59Z - 1995-01-01T00:00:00Z ) ",
-    "TemporalCoverage:BeginDate": "6101-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1995-01-01T00:00:00Z",
-    "author": [
-        "Pasi Aalto"
-    ],
-    "fulltext": "urn:nbn:fi:csc-kata20160308092917812220;2016-03-08T07:29:17Z;university-of-helsinki-department-of-physics-division-of-atmospheric-sciences;V\u00e4rri\u00f6 SMEAR I meteorology, gases and soil - Global radiation - 1995;Pasi Aalto;http://www.yso.fi/onto/yso/p5394;Title: Global radiation \n\nDescription: Global radiation \n\nVariable: GLOB \n\nUnit: W m\u207b\u00b2 \n\nSource: Middleton SK08 pyranometer \n\nCategory: Radiation \n\n;atm-data@helsinki.fi;2016-03-08;dataset;urn:nbn:fi:csc-ida2014011607359s;urn:nbn:fi:csc-ida2014011607359v;urn:nbn:fi:csc-ida-10x201703282015017315793v;urn:nbn:fi:csc-kata20160308092917812220;http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308092917812220;DCMI-point: name=V\u00e4rri\u00f6; east=29.610137; north=67.755044; elevation=390;;1995-01-01T00:00:00Z/1995-12-31T23:59:59Z;Creative Commons Attribution 4.0",
-    "group": "etsin",
-    "groups": [
-        {
-            "name": "etsin"
-        }
-    ],
-    "name": "0a29e191-dccf-518b-b317-e21ed8f924cc",
-    "notes": [
-        "Title: Global radiation \n\nDescription: Global radiation \n\nVariable: GLOB \n\nUnit: W m\u207b\u00b2 \n\nSource: Middleton SK08 pyranometer \n\nCategory: Radiation \n\n"
-    ],
-    "oai_identifier": [
-        "0a29e191-dccf-518b-b317-e21ed8f924cc"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "http www.yso.fi onto yso p"
-        }
-    ],
-    "title": [
-        "V\u00e4rri\u00f6 SMEAR I meteorology, gases and soil - Global radiation - 1995"
-    ],
-    "url": "http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308092917812220"
-}
\ No newline at end of file
diff --git a/oaitestdata/etsin-oai_dc/SET_1/json/0a3cf0d5-67ad-558d-a34b-bcc39c8a577f.json b/oaitestdata/etsin-oai_dc/SET_1/json/0a3cf0d5-67ad-558d-a34b-bcc39c8a577f.json
deleted file mode 100644
index 185d90ba..00000000
--- a/oaitestdata/etsin-oai_dc/SET_1/json/0a3cf0d5-67ad-558d-a34b-bcc39c8a577f.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "atm-data@helsinki.fi"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://etsin.avointiede.fi/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=0a3cf0d5-67ad-558d-a34b-bcc39c8a577f",
-    "PublicationTimestamp": "2016-03-08T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "atm-data@helsinki.fi"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0"
-    ],
-    "SpatialCoverage": [
-        "DCMI-point: name=Hyyti\u00e4l\u00e4; east=24.294795; north=61.847463 elevation=179",
-        "2013-01-01T00:00:00Z/2013-12-31T23:59:59Z"
-    ],
-    "TempCoverageBegin": 92982427199,
-    "TempCoverageEnd": 63492595200,
-    "TemporalCoverage": " period : ( 2947-07-01T11:59:59Z - 2013-01-01T00:00:00Z ) ",
-    "TemporalCoverage:BeginDate": "2947-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2013-01-01T00:00:00Z",
-    "author": [
-        "Pasi Aalto"
-    ],
-    "fulltext": "urn:nbn:fi:csc-kata20160308105827523554;2016-03-08T08:58:27Z;university-of-helsinki-department-of-physics-division-of-atmospheric-sciences;Hyyti\u00e4l\u00e4 SMEAR II eddy mast 23.3 m - IRGA pressure - 2013;Pasi Aalto;http://www.yso.fi/onto/yso/p26208;Title: IRGA pressure \n\nDescription: Average of IRGA sampling cell pressure, mast / tall tower 23 m height, primary flux measuring setup \n\nVariable: licor_p_av \n\nUnit: kPa \n\nSource: LI-COR LI-6262 gas analyzer \n\nCategory: Flux ancillary data \n\n;atm-data@helsinki.fi;2016-03-08;dataset;urn:nbn:fi:csc-ida-2x201512142015014176178s;urn:nbn:fi:csc-ida-2x201703272015017569149v;urn:nbn:fi:csc-ida-2x201512212015014285204v;urn:nbn:fi:csc-kata20160308105827523554;http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308105827523554;DCMI-point: name=Hyyti\u00e4l\u00e4; east=24.294795; north=61.847463 elevation=179;2013-01-01T00:00:00Z/2013-12-31T23:59:59Z;Creative Commons Attribution 4.0",
-    "group": "etsin",
-    "groups": [
-        {
-            "name": "etsin"
-        }
-    ],
-    "name": "0a3cf0d5-67ad-558d-a34b-bcc39c8a577f",
-    "notes": [
-        "Title: IRGA pressure \n\nDescription: Average of IRGA sampling cell pressure, mast / tall tower 23 m height, primary flux measuring setup \n\nVariable: licor_p_av \n\nUnit: kPa \n\nSource: LI-COR LI-6262 gas analyzer \n\nCategory: Flux ancillary data \n\n"
-    ],
-    "oai_identifier": [
-        "0a3cf0d5-67ad-558d-a34b-bcc39c8a577f"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "http www.yso.fi onto yso p"
-        }
-    ],
-    "title": [
-        "Hyyti\u00e4l\u00e4 SMEAR II eddy mast 23.3 m - IRGA pressure - 2013"
-    ],
-    "url": "http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308105827523554"
-}
\ No newline at end of file
diff --git a/oaitestdata/etsin-oai_dc/SET_1/json/0a4a0dfa-dce0-55fb-b7aa-c3e51855856a.json b/oaitestdata/etsin-oai_dc/SET_1/json/0a4a0dfa-dce0-55fb-b7aa-c3e51855856a.json
deleted file mode 100644
index 27b6dd09..00000000
--- a/oaitestdata/etsin-oai_dc/SET_1/json/0a4a0dfa-dce0-55fb-b7aa-c3e51855856a.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "atm-data@helsinki.fi"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://etsin.avointiede.fi/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=0a4a0dfa-dce0-55fb-b7aa-c3e51855856a",
-    "PublicationTimestamp": "2016-03-08T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "atm-data@helsinki.fi"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0"
-    ],
-    "SpatialCoverage": [
-        "DCMI-point: name=V\u00e4rri\u00f6; east=29.610137; north=67.755044; elevation=390;",
-        "2006-01-01T00:00:00Z/2006-12-31T23:59:59Z"
-    ],
-    "TempCoverageBegin": 192513067199,
-    "TempCoverageEnd": 63271670400,
-    "TemporalCoverage": " period : ( 6101-07-01T11:59:59Z - 2006-01-01T00:00:00Z ) ",
-    "TemporalCoverage:BeginDate": "6101-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2006-01-01T00:00:00Z",
-    "author": [
-        "Pasi Aalto"
-    ],
-    "fulltext": "urn:nbn:fi:csc-kata20160308093442336626;2016-03-08T07:34:42Z;university-of-helsinki-department-of-physics-division-of-atmospheric-sciences;V\u00e4rri\u00f6 SMEAR I meteorology, gases and soil - NO concentration 15 m - 2006;Pasi Aalto;http://www.yso.fi/onto/yso/p26207;Title: NO concentration 15 m \n\nDescription: NO concentration 15 m \n\nVariable: NO_0 \n\nUnit: \u00b5g m\u207b\u00b3 \n\nSource: TEI 42C TL chemiluminescence analyzer \n\nCategory: Gas \n\n;atm-data@helsinki.fi;2016-03-08;dataset;urn:nbn:fi:csc-ida-10x201703282015017316520v;urn:nbn:fi:csc-ida2014011537470v;urn:nbn:fi:csc-ida2014011537470s;urn:nbn:fi:csc-kata20160308093442336626;http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308093442336626;DCMI-point: name=V\u00e4rri\u00f6; east=29.610137; north=67.755044; elevation=390;;2006-01-01T00:00:00Z/2006-12-31T23:59:59Z;Creative Commons Attribution 4.0",
-    "group": "etsin",
-    "groups": [
-        {
-            "name": "etsin"
-        }
-    ],
-    "name": "0a4a0dfa-dce0-55fb-b7aa-c3e51855856a",
-    "notes": [
-        "Title: NO concentration 15 m \n\nDescription: NO concentration 15 m \n\nVariable: NO_0 \n\nUnit: \u00b5g m\u207b\u00b3 \n\nSource: TEI 42C TL chemiluminescence analyzer \n\nCategory: Gas \n\n"
-    ],
-    "oai_identifier": [
-        "0a4a0dfa-dce0-55fb-b7aa-c3e51855856a"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "http www.yso.fi onto yso p"
-        }
-    ],
-    "title": [
-        "V\u00e4rri\u00f6 SMEAR I meteorology, gases and soil - NO concentration 15 m - 2006"
-    ],
-    "url": "http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308093442336626"
-}
\ No newline at end of file
diff --git a/oaitestdata/etsin-oai_dc/SET_1/json/0a4a828d-26f4-55bc-9ac1-17261fdc0df4.json b/oaitestdata/etsin-oai_dc/SET_1/json/0a4a828d-26f4-55bc-9ac1-17261fdc0df4.json
deleted file mode 100644
index 80642954..00000000
--- a/oaitestdata/etsin-oai_dc/SET_1/json/0a4a828d-26f4-55bc-9ac1-17261fdc0df4.json
+++ /dev/null
@@ -1,89 +0,0 @@
-{
-    "Contact": [
-        "Yhteiskuntatieteellinen tietoarkisto"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://etsin.avointiede.fi/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=0a4a828d-26f4-55bc-9ac1-17261fdc0df4",
-    "PublicationTimestamp": "2016-03-10T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Yhteiskuntatieteellinen tietoarkisto"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Other (Not Open)"
-    ],
-    "SpatialCoverage": [
-        "Suomi"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Parviainen, Jaana",
-        "Kinnunen, Taina",
-        "Koivunen, Tuija"
-    ],
-    "fulltext": "urn:nbn:fi:csc-kata20150107040135589587;2016-03-10T09:34:38Z;01905-2571-tampereen-yliopisto-yhteiskuntatieteellinen-tietoarkisto;Henkil\u00f6st\u00f6palveluyritysten ty\u00f6ntekij\u00f6iden haastattelut 2013;Interviews of Recruitment Consultants 2013;Koivunen, Tuija;Kinnunen, Taina;Parviainen, Jaana;etnisyys;henkil\u00f6st\u00f6hankinta;konsultointi;konsulttitoimistot;palkkaty\u00f6;persoonallisuus;rekrytointi;ruumiillisuus;sosiaaliset taidot;tietotekniikka-ala;toimeksianto;ty\u00f6;ty\u00f6el\u00e4m\u00e4;ty\u00f6h\u00f6notto;ty\u00f6llisyys ja ty\u00f6llistyminen;ty\u00f6nantajat;ty\u00f6nhaku;ty\u00f6ntekij\u00e4t;ty\u00f6tt\u00f6myys;ty\u00f6tt\u00f6myys ja ty\u00f6tt\u00f6m\u00e4t;ulkoistaminen;ulkon\u00e4k\u00f6;yhteiskuntatieteet;Aineisto sis\u00e4lt\u00e4\u00e4 henkil\u00f6st\u00f6palveluyrityksiss\u00e4 suorarekrytoinnin parissa ty\u00f6skentelevien henkil\u00f6iden haastatteluja. Haastattelut on tehty kolmen yrityksen eri toimipisteiss\u00e4. Haastateltavien joukossa on yrityksen perustaja, kaksi rekrytointikonsulttia, kaksi henkil\u00f6st\u00f6konsulttia, yksik\u00f6n p\u00e4\u00e4llikk\u00f6, psykologi, aluep\u00e4\u00e4llikk\u00f6 ja tiiminvet\u00e4j\u00e4. Haastatteluissa k\u00e4yd\u00e4\u00e4n l\u00e4pi rekrytointiprosessia erityisesti tietotekniikka-alalla.\r\n\r\nHaastattelujen alussa haastateltavilta kysyt\u00e4\u00e4n heid\u00e4n taustastaan, kuten koulutuksesta, ty\u00f6kokemuksesta ja nykyisest\u00e4 ty\u00f6kuvasta. T\u00e4m\u00e4n j\u00e4lkeen kysyt\u00e4\u00e4n suorarekrytointiprosessiin liittyvi\u00e4 kysymyksi\u00e4 esimerkiksi toimeksiannosta sek\u00e4 rekrytointiprosessin kulusta ja kestosta. Seuraavaksi tiedustellaan rekrytoitaviin henkil\u00f6ihin kohdistuvista emotionaalisista, sosiaalisista ja esteettisist\u00e4 vaatimuksista. Kysyt\u00e4\u00e4n esimerkiksi vaikuttavatko sosiaaliset taidot, ulkon\u00e4k\u00f6, etninen tausta, vaatetus, yleinen olemus tai ik\u00e4 ja sukupuoli ty\u00f6n saantiin. Haastattelun lopuksi kysyt\u00e4\u00e4n viel\u00e4 rekrytointialan tulevaisuuteen liittyvi\u00e4 kysymyksi\u00e4 ja tiedustellaan omaan urakehitykseen vaikuttavia tekij\u00f6it\u00e4.\r\n\r\nTaustatietoina on kerrottu haastattelup\u00e4iv\u00e4m\u00e4\u00e4r\u00e4, haastateltavan sukupuoli ja ammattinimike tai rooli yrityksess\u00e4 sek\u00e4 yrityksen tunniste.\r\n\r\nAineisto on ker\u00e4tty osana Suomen Akatemian rahoittamaa \"Working Body in the Post-Industrial Economy\" (WORKBOD) -tutkimushanketta.;Yhteiskuntatieteellinen tietoarkisto;Yhteiskuntatieteellinen tietoarkisto;2016-03-10;dataset;FSD2851;urn:nbn:fi:fsd:T-FSD2851;urn:nbn:fi:csc-kata20150107040135589587;http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20150107040135589587;Suomi;Other (Not Open)",
-    "group": "etsin",
-    "groups": [
-        {
-            "name": "etsin"
-        }
-    ],
-    "name": "0a4a828d-26f4-55bc-9ac1-17261fdc0df4",
-    "notes": [
-        "Aineisto sis\u00e4lt\u00e4\u00e4 henkil\u00f6st\u00f6palveluyrityksiss\u00e4 suorarekrytoinnin parissa ty\u00f6skentelevien henkil\u00f6iden haastatteluja. Haastattelut on tehty kolmen yrityksen eri toimipisteiss\u00e4. Haastateltavien joukossa on yrityksen perustaja, kaksi rekrytointikonsulttia, kaksi henkil\u00f6st\u00f6konsulttia, yksik\u00f6n p\u00e4\u00e4llikk\u00f6, psykologi, aluep\u00e4\u00e4llikk\u00f6 ja tiiminvet\u00e4j\u00e4. Haastatteluissa k\u00e4yd\u00e4\u00e4n l\u00e4pi rekrytointiprosessia erityisesti tietotekniikka-alalla.\r\n\r\nHaastattelujen alussa haastateltavilta kysyt\u00e4\u00e4n heid\u00e4n taustastaan, kuten koulutuksesta, ty\u00f6kokemuksesta ja nykyisest\u00e4 ty\u00f6kuvasta. T\u00e4m\u00e4n j\u00e4lkeen kysyt\u00e4\u00e4n suorarekrytointiprosessiin liittyvi\u00e4 kysymyksi\u00e4 esimerkiksi toimeksiannosta sek\u00e4 rekrytointiprosessin kulusta ja kestosta. Seuraavaksi tiedustellaan rekrytoitaviin henkil\u00f6ihin kohdistuvista emotionaalisista, sosiaalisista ja esteettisist\u00e4 vaatimuksista. Kysyt\u00e4\u00e4n esimerkiksi vaikuttavatko sosiaaliset taidot, ulkon\u00e4k\u00f6, etninen tausta, vaatetus, yleinen olemus tai ik\u00e4 ja sukupuoli ty\u00f6n saantiin. Haastattelun lopuksi kysyt\u00e4\u00e4n viel\u00e4 rekrytointialan tulevaisuuteen liittyvi\u00e4 kysymyksi\u00e4 ja tiedustellaan omaan urakehitykseen vaikuttavia tekij\u00f6it\u00e4.\r\n\r\nTaustatietoina on kerrottu haastattelup\u00e4iv\u00e4m\u00e4\u00e4r\u00e4, haastateltavan sukupuoli ja ammattinimike tai rooli yrityksess\u00e4 sek\u00e4 yrityksen tunniste.\r\n\r\nAineisto on ker\u00e4tty osana Suomen Akatemian rahoittamaa \"Working Body in the Post-Industrial Economy\" (WORKBOD) -tutkimushanketta."
-    ],
-    "oai_identifier": [
-        "0a4a828d-26f4-55bc-9ac1-17261fdc0df4"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "etnisyys"
-        },
-        {
-            "name": "etnisyys"
-        },
-        {
-            "name": "konsultointi"
-        },
-        {
-            "name": "konsulttitoimistot"
-        },
-        {
-            "name": "konsulttitoimistot"
-        },
-        {
-            "name": "persoonallisuus"
-        },
-        {
-            "name": "rekrytointi"
-        },
-        {
-            "name": "ruumiillisuus"
-        },
-        {
-            "name": "sosiaaliset taidot"
-        },
-        {
-            "name": "tietotekniikka-ala"
-        },
-        {
-            "name": "toimeksianto"
-        },
-        {
-            "name": "toimeksianto"
-        }
-    ],
-    "title": [
-        "Henkil\u00f6st\u00f6palveluyritysten ty\u00f6ntekij\u00f6iden haastattelut 2013",
-        "Interviews of Recruitment Consultants 2013"
-    ],
-    "url": "http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20150107040135589587"
-}
\ No newline at end of file
diff --git a/oaitestdata/etsin-oai_dc/SET_1/json/0a756d03-5428-51a4-a884-7d949ebaf69e.json b/oaitestdata/etsin-oai_dc/SET_1/json/0a756d03-5428-51a4-a884-7d949ebaf69e.json
deleted file mode 100644
index 58d2f8d7..00000000
--- a/oaitestdata/etsin-oai_dc/SET_1/json/0a756d03-5428-51a4-a884-7d949ebaf69e.json
+++ /dev/null
@@ -1,94 +0,0 @@
-{
-    "Contact": [
-        "Yhteiskuntatieteellinen tietoarkisto"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://etsin.avointiede.fi/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=0a756d03-5428-51a4-a884-7d949ebaf69e",
-    "PublicationTimestamp": "2016-03-10T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Yhteiskuntatieteellinen tietoarkisto"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Other (Not Open)"
-    ],
-    "SpatialCoverage": [
-        "Ven\u00e4j\u00e4",
-        "Petroskoi",
-        "2000/2000"
-    ],
-    "TemporalCoverage": [
-        "Ven\u00e4j\u00e4",
-        "Petroskoi",
-        "2000/2000"
-    ],
-    "author": [
-        "Nordenstreng, Kaarle",
-        "Pietil\u00e4inen, Jukka"
-    ],
-    "fulltext": "urn:nbn:fi:csc-kata20141222155652923642;2016-03-10T09:10:53Z;01905-2571-tampereen-yliopisto-yhteiskuntatieteellinen-tietoarkisto;Karjalan mediatutkimus 2000;Karelian Media Survey 2000;Nordenstreng, Kaarle;Pietil\u00e4inen, Jukka;Karjalan tasavalta;Ven\u00e4j\u00e4;asenteet;joukkoviestimet;journalismi;lehdist\u00f6;luotettavuus;luottamus;politiikka;presidentinvaalit;radio;sanomalehdet;sensuuri;televisio;tiedonl\u00e4hteet;uutiset;yhteiskuntatieteet;Karjalan mediatutkimuksessa selvitet\u00e4\u00e4n tiedotusv\u00e4lineiden seuraamista Petroskoissa sek\u00e4 asenteita joukkoviestimi\u00e4 kohtaan. Lis\u00e4ksi tutkimuksessa kartoitetaan, mit\u00e4 kanavia petroskoilaiset k\u00e4ytt\u00e4v\u00e4t eri tietojen hankkimisessa\r\n\r\nEnsin kyselyss\u00e4 selvitettiin sanomalehtien lukemiseen liittyvi\u00e4 asioita. Vastaajilta tiedusteltiin, kuinka usein he lukevat eri sanomalehti\u00e4 ja miten he hankkivat kyseisi\u00e4 lehti\u00e4 luettavakseen. Seuraavaksi kysyttiin, mink\u00e4 mainituista lehdist\u00e4 vastaajat valitsisivat mieluiten, jos olisi mahdollista valita vain yksi. Lis\u00e4ksi pyydettiin arvioimaan, miss\u00e4 sanomalehdess\u00e4 heid\u00e4n mielest\u00e4\u00e4n on useimmiten virheellist\u00e4 ja miss\u00e4 taas virheett\u00f6mint\u00e4 tietoa. Karjalan tasavallassa ilmestyv\u00e4t ja valtakunnalliset sanomalehdet k\u00e4siteltiin omina kysymysryhmin\u00e4\u00e4n.\r\n\r\nLis\u00e4ksi kartoitettiin, mist\u00e4 aiheista tai mit\u00e4 osastoja vastaajat mieluiten lukevat sanomalehdist\u00e4. Arvioitavana olivat esimerkiksi politiikkaan ja talouteen liittyv\u00e4t uutiset, viihde- ja mielipidesivut. Vastaajilta kysyttiin my\u00f6s, kuinka usein he kuuntelevat eri radiokanavia sek\u00e4 katsovat eri televisiokanavia.\r\n\r\nSeuraavaksi tiedusteltiin mielipiteit\u00e4 joukkoviestimist\u00e4 yleens\u00e4. Ensin vastaajilta kysyttiin, mik\u00e4 heid\u00e4n mielest\u00e4\u00e4n on median t\u00e4rkein teht\u00e4v\u00e4. Toimittajista oli esitettyn\u00e4 erilaisia v\u00e4itt\u00e4mi\u00e4, joista vastaajia pyydettiin valitsemaan omaa n\u00e4kemyst\u00e4 parhaiten kuvaava.\r\n\r\nT\u00e4m\u00e4n j\u00e4lkeen kysyttiin, kuinka kiinnostuneita vastaajat ovat poliittisten uutisten seuraamisesta. Vastaajilta kysyttiin my\u00f6s, mit\u00e4 tietol\u00e4hteit\u00e4 he k\u00e4ytt\u00e4v\u00e4t eri uutisten seuraamisessa. Arvioitavina olivat l\u00e4hinn\u00e4 poliittiset ja talouteen liittyv\u00e4t uutiset. Edelleen poliittisiin ja taloudellisiin asioihin liittyen, vastaajilta kysyttiin, kuinka luotettavina he pit\u00e4v\u00e4t joukkotiedotusv\u00e4lineit\u00e4 n\u00e4iden asioiden uutisoinnissa. Vastaajilta tiedusteltiin my\u00f6s, ovatko paikalliset tiedotusv\u00e4lineet heid\u00e4n mielest\u00e4\u00e4n riippuvaisia kaupungin ja tasavallan vallanpit\u00e4jist\u00e4. Lis\u00e4ksi kysyttiin, mink\u00e4lainen vaikutus medialla yleens\u00e4 on ihmisiin ja pit\u00e4isik\u00f6 poliittisten asioiden uutisointia kontrolloida. Lopuksi tiedusteltiin presidentinvaaleihin liittyvi\u00e4 asioita. Vastaajilta kysyttiin, aikovatko he \u00e4\u00e4nest\u00e4\u00e4 tulevissa (2000) vaaleissa ja jos aikovat, niin ket\u00e4.\r\n\r\nTaustatietoina olivat sukupuoli, ik\u00e4, koulutus, kansalaisuus, perheen koko, tiedot ty\u00f6tilanteesta ja alasta, yhden perheenj\u00e4senen yhteenlasketut tulot, perheen taloudellinen tilanne yleens\u00e4 ja kaupunginosa.;Yhteiskuntatieteellinen tietoarkisto;Yhteiskuntatieteellinen tietoarkisto;2016-03-10;dataset;FSD1291;urn:nbn:fi:fsd:T-FSD1291;urn:nbn:fi:csc-kata20141222155652923642;http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20141222155652923642;Ven\u00e4j\u00e4;Petroskoi;2000/2000;Other (Not Open)",
-    "group": "etsin",
-    "groups": [
-        {
-            "name": "etsin"
-        }
-    ],
-    "name": "0a756d03-5428-51a4-a884-7d949ebaf69e",
-    "notes": [
-        "Karjalan mediatutkimuksessa selvitet\u00e4\u00e4n tiedotusv\u00e4lineiden seuraamista Petroskoissa sek\u00e4 asenteita joukkoviestimi\u00e4 kohtaan. Lis\u00e4ksi tutkimuksessa kartoitetaan, mit\u00e4 kanavia petroskoilaiset k\u00e4ytt\u00e4v\u00e4t eri tietojen hankkimisessa\r\n\r\nEnsin kyselyss\u00e4 selvitettiin sanomalehtien lukemiseen liittyvi\u00e4 asioita. Vastaajilta tiedusteltiin, kuinka usein he lukevat eri sanomalehti\u00e4 ja miten he hankkivat kyseisi\u00e4 lehti\u00e4 luettavakseen. Seuraavaksi kysyttiin, mink\u00e4 mainituista lehdist\u00e4 vastaajat valitsisivat mieluiten, jos olisi mahdollista valita vain yksi. Lis\u00e4ksi pyydettiin arvioimaan, miss\u00e4 sanomalehdess\u00e4 heid\u00e4n mielest\u00e4\u00e4n on useimmiten virheellist\u00e4 ja miss\u00e4 taas virheett\u00f6mint\u00e4 tietoa. Karjalan tasavallassa ilmestyv\u00e4t ja valtakunnalliset sanomalehdet k\u00e4siteltiin omina kysymysryhmin\u00e4\u00e4n.\r\n\r\nLis\u00e4ksi kartoitettiin, mist\u00e4 aiheista tai mit\u00e4 osastoja vastaajat mieluiten lukevat sanomalehdist\u00e4. Arvioitavana olivat esimerkiksi politiikkaan ja talouteen liittyv\u00e4t uutiset, viihde- ja mielipidesivut. Vastaajilta kysyttiin my\u00f6s, kuinka usein he kuuntelevat eri radiokanavia sek\u00e4 katsovat eri televisiokanavia.\r\n\r\nSeuraavaksi tiedusteltiin mielipiteit\u00e4 joukkoviestimist\u00e4 yleens\u00e4. Ensin vastaajilta kysyttiin, mik\u00e4 heid\u00e4n mielest\u00e4\u00e4n on median t\u00e4rkein teht\u00e4v\u00e4. Toimittajista oli esitettyn\u00e4 erilaisia v\u00e4itt\u00e4mi\u00e4, joista vastaajia pyydettiin valitsemaan omaa n\u00e4kemyst\u00e4 parhaiten kuvaava.\r\n\r\nT\u00e4m\u00e4n j\u00e4lkeen kysyttiin, kuinka kiinnostuneita vastaajat ovat poliittisten uutisten seuraamisesta. Vastaajilta kysyttiin my\u00f6s, mit\u00e4 tietol\u00e4hteit\u00e4 he k\u00e4ytt\u00e4v\u00e4t eri uutisten seuraamisessa. Arvioitavina olivat l\u00e4hinn\u00e4 poliittiset ja talouteen liittyv\u00e4t uutiset. Edelleen poliittisiin ja taloudellisiin asioihin liittyen, vastaajilta kysyttiin, kuinka luotettavina he pit\u00e4v\u00e4t joukkotiedotusv\u00e4lineit\u00e4 n\u00e4iden asioiden uutisoinnissa. Vastaajilta tiedusteltiin my\u00f6s, ovatko paikalliset tiedotusv\u00e4lineet heid\u00e4n mielest\u00e4\u00e4n riippuvaisia kaupungin ja tasavallan vallanpit\u00e4jist\u00e4. Lis\u00e4ksi kysyttiin, mink\u00e4lainen vaikutus medialla yleens\u00e4 on ihmisiin ja pit\u00e4isik\u00f6 poliittisten asioiden uutisointia kontrolloida. Lopuksi tiedusteltiin presidentinvaaleihin liittyvi\u00e4 asioita. Vastaajilta kysyttiin, aikovatko he \u00e4\u00e4nest\u00e4\u00e4 tulevissa (2000) vaaleissa ja jos aikovat, niin ket\u00e4.\r\n\r\nTaustatietoina olivat sukupuoli, ik\u00e4, koulutus, kansalaisuus, perheen koko, tiedot ty\u00f6tilanteesta ja alasta, yhden perheenj\u00e4senen yhteenlasketut tulot, perheen taloudellinen tilanne yleens\u00e4 ja kaupunginosa."
-    ],
-    "oai_identifier": [
-        "0a756d03-5428-51a4-a884-7d949ebaf69e"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Karjalan tasavalta"
-        },
-        {
-            "name": "Karjalan tasavalta"
-        },
-        {
-            "name": "asenteet"
-        },
-        {
-            "name": "joukkoviestimet"
-        },
-        {
-            "name": "journalismi"
-        },
-        {
-            "name": "journalismi"
-        },
-        {
-            "name": "luotettavuus"
-        },
-        {
-            "name": "luottamus"
-        },
-        {
-            "name": "politiikka"
-        },
-        {
-            "name": "presidentinvaalit"
-        },
-        {
-            "name": "radio"
-        },
-        {
-            "name": "sanomalehdet"
-        }
-    ],
-    "title": [
-        "Karjalan mediatutkimus 2000",
-        "Karelian Media Survey 2000"
-    ],
-    "url": "http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20141222155652923642"
-}
\ No newline at end of file
diff --git a/oaitestdata/etsin-oai_dc/SET_1/json/0a76bc05-f8a2-524a-addc-7148ee84f897.json b/oaitestdata/etsin-oai_dc/SET_1/json/0a76bc05-f8a2-524a-addc-7148ee84f897.json
deleted file mode 100644
index 4842880b..00000000
--- a/oaitestdata/etsin-oai_dc/SET_1/json/0a76bc05-f8a2-524a-addc-7148ee84f897.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "atm-data@helsinki.fi"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://etsin.avointiede.fi/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=0a76bc05-f8a2-524a-addc-7148ee84f897",
-    "PublicationTimestamp": "2016-03-08T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "atm-data@helsinki.fi"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0"
-    ],
-    "SpatialCoverage": [
-        "DCMI-point: name=Torni; east=24.9387; north=60.1678; elevation=15;",
-        "2010-01-01T00:00:00Z/2010-12-31T23:59:59Z"
-    ],
-    "TempCoverageBegin": 296209223999,
-    "TempCoverageEnd": 63397900800,
-    "TemporalCoverage": " period : ( 9387-07-01T11:59:59Z - 2010-01-01T00:00:00Z ) ",
-    "TemporalCoverage:BeginDate": "9387-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2010-01-01T00:00:00Z",
-    "author": [
-        "Pasi Aalto"
-    ],
-    "fulltext": "urn:nbn:fi:csc-kata20160308104406983690;2016-03-08T08:44:07Z;university-of-helsinki-department-of-physics-division-of-atmospheric-sciences;Helsinki Hotel Torni eddy - Air temperature - 2010;Pasi Aalto;http://www.yso.fi/onto/yso/p2100;http://www.yso.fi/onto/yso/p26208;l\u00e4mp\u00f6tila;Title: Air temperature \n\nDescription: 30 min average of air temperature \n\nVariable: av_t \n\nUnit: \u00b0C \n\nSource: Metek USA-1 anemometer/thermometer \n\nCategory: Flux ancillary data \n\n;atm-data@helsinki.fi;2016-03-08;dataset;urn:nbn:fi:csc-ida2014011537120s;urn:nbn:fi:csc-ida-10x201704032015017317926v;urn:nbn:fi:csc-ida2014011537120v;urn:nbn:fi:csc-kata20160308104406983690;http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308104406983690;DCMI-point: name=Torni; east=24.9387; north=60.1678; elevation=15;;2010-01-01T00:00:00Z/2010-12-31T23:59:59Z;Creative Commons Attribution 4.0",
-    "group": "etsin",
-    "groups": [
-        {
-            "name": "etsin"
-        }
-    ],
-    "name": "0a76bc05-f8a2-524a-addc-7148ee84f897",
-    "notes": [
-        "Title: Air temperature \n\nDescription: 30 min average of air temperature \n\nVariable: av_t \n\nUnit: \u00b0C \n\nSource: Metek USA-1 anemometer/thermometer \n\nCategory: Flux ancillary data \n\n"
-    ],
-    "oai_identifier": [
-        "0a76bc05-f8a2-524a-addc-7148ee84f897"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "http www.yso.fi onto yso p"
-        },
-        {
-            "name": "http www.yso.fi onto yso p"
-        },
-        {
-            "name": "http www.yso.fi onto yso p"
-        }
-    ],
-    "title": [
-        "Helsinki Hotel Torni eddy - Air temperature - 2010"
-    ],
-    "url": "http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308104406983690"
-}
\ No newline at end of file
diff --git a/oaitestdata/etsin-oai_dc/SET_1/json/0a784bce-115a-50e0-8e9b-031e0d9a2583.json b/oaitestdata/etsin-oai_dc/SET_1/json/0a784bce-115a-50e0-8e9b-031e0d9a2583.json
deleted file mode 100644
index 9378a9c4..00000000
--- a/oaitestdata/etsin-oai_dc/SET_1/json/0a784bce-115a-50e0-8e9b-031e0d9a2583.json
+++ /dev/null
@@ -1,89 +0,0 @@
-{
-    "Contact": [
-        "Yhteiskuntatieteellinen tietoarkisto"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://etsin.avointiede.fi/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=0a784bce-115a-50e0-8e9b-031e0d9a2583",
-    "PublicationTimestamp": "2016-03-10T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Yhteiskuntatieteellinen tietoarkisto"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Other (Not Open)"
-    ],
-    "SpatialCoverage": [
-        "Suomi"
-    ],
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Himanen, Laura",
-        "Miettinen, Marita",
-        "Puuska, Hanna-Mari"
-    ],
-    "fulltext": "urn:nbn:fi:csc-kata20141222161905627032;2016-03-10T09:32:53Z;01905-2571-tampereen-yliopisto-yhteiskuntatieteellinen-tietoarkisto;Julkaisuk\u00e4yt\u00e4nn\u00f6t eri tieteenaloilla: professorihaastattelut 2007;Disciplinary Differences in Publishing Practices 2007: Professor Interviews;Puuska, Hanna-Mari;Miettinen, Marita;Himanen, Laura;artikkelit;julkaisut;kirjat;muut;oppikirjat;professorit;tiedelehdet;tiedeyhteis\u00f6t;tieteellinen julkaisutoiminta;tieteellinen kirjoittaminen;tieteellinen tieto;tieteellinen yhteisty\u00f6;tieteet;toisen ja korkea-asteen koulutus;tutkimus;vertaisarviointi;yhteisjulkaiseminen;Aineisto k\u00e4sitt\u00e4\u00e4 44 eri tieteenalojen professorien haastattelua, jotka on ker\u00e4tty yhdeks\u00e4st\u00e4 Etel\u00e4- ja Keski-Suomessa sijaitsevasta yliopistosta. N\u00e4ist\u00e4 viisi on monialaista ja kaksi teknillist\u00e4 yliopistoa ja kaksi kauppakorkeakoulua. P\u00e4\u00e4osin jokaiselta tieteenalalta on haastateltu kahta professoria, jotka ovat edustaneet eri yliopistoja.\r\n\r\nHaastattelujen alkuper\u00e4isen\u00e4 tarkoituksena on ollut saada k\u00e4sitys kullakin tieteenalalla vallitsevista julkaisuk\u00e4yt\u00e4nn\u00f6ist\u00e4 ja n\u00e4ihin k\u00e4yt\u00e4nt\u00f6ihin vaikuttavista tekij\u00f6ist\u00e4. N\u00e4iss\u00e4 muodoltaan puolistrukturoiduissa haastatteluissa professoreja pyydettiin kertomaan tieteenalansa ominaispiirteist\u00e4 ja ty\u00f6skentelytavoista. Keskeisimmilt\u00e4 osin kysymykset koskevat julkaisemista. Professoreilta on kysytty muun muassa omasta tutkimusurasta, tieteenalan merkitt\u00e4vimmist\u00e4 julkaisumuodoista, yhteisjulkaisemisesta ja julkaisujen laatuun vaikuttavista tekij\u00f6ist\u00e4. Lis\u00e4ksi professorit ovat p\u00e4\u00e4sseet arvioimaan eri julkaisutyyppien vaatimaa ty\u00f6m\u00e4\u00e4r\u00e4\u00e4 ja pohtimaan alansa julkaisuk\u00e4yt\u00e4nn\u00f6iss\u00e4 tapahtuneita muutoksia.\r\n\r\nTaustatietona mainitaan mm. haastateltavan tieteenala, oppiaine ja sukupuoli.\r\n\r\nAineistosta on tehty html-versio, jonka hakemiston avulla haastatteluja on helppo selata.;Yhteiskuntatieteellinen tietoarkisto;Yhteiskuntatieteellinen tietoarkisto;2016-03-10;dataset;FSD2784;urn:nbn:fi:fsd:T-FSD2784;urn:nbn:fi:csc-kata20141222161905627032;http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20141222161905627032;Suomi;Other (Not Open)",
-    "group": "etsin",
-    "groups": [
-        {
-            "name": "etsin"
-        }
-    ],
-    "name": "0a784bce-115a-50e0-8e9b-031e0d9a2583",
-    "notes": [
-        "Aineisto k\u00e4sitt\u00e4\u00e4 44 eri tieteenalojen professorien haastattelua, jotka on ker\u00e4tty yhdeks\u00e4st\u00e4 Etel\u00e4- ja Keski-Suomessa sijaitsevasta yliopistosta. N\u00e4ist\u00e4 viisi on monialaista ja kaksi teknillist\u00e4 yliopistoa ja kaksi kauppakorkeakoulua. P\u00e4\u00e4osin jokaiselta tieteenalalta on haastateltu kahta professoria, jotka ovat edustaneet eri yliopistoja.\r\n\r\nHaastattelujen alkuper\u00e4isen\u00e4 tarkoituksena on ollut saada k\u00e4sitys kullakin tieteenalalla vallitsevista julkaisuk\u00e4yt\u00e4nn\u00f6ist\u00e4 ja n\u00e4ihin k\u00e4yt\u00e4nt\u00f6ihin vaikuttavista tekij\u00f6ist\u00e4. N\u00e4iss\u00e4 muodoltaan puolistrukturoiduissa haastatteluissa professoreja pyydettiin kertomaan tieteenalansa ominaispiirteist\u00e4 ja ty\u00f6skentelytavoista. Keskeisimmilt\u00e4 osin kysymykset koskevat julkaisemista. Professoreilta on kysytty muun muassa omasta tutkimusurasta, tieteenalan merkitt\u00e4vimmist\u00e4 julkaisumuodoista, yhteisjulkaisemisesta ja julkaisujen laatuun vaikuttavista tekij\u00f6ist\u00e4. Lis\u00e4ksi professorit ovat p\u00e4\u00e4sseet arvioimaan eri julkaisutyyppien vaatimaa ty\u00f6m\u00e4\u00e4r\u00e4\u00e4 ja pohtimaan alansa julkaisuk\u00e4yt\u00e4nn\u00f6iss\u00e4 tapahtuneita muutoksia.\r\n\r\nTaustatietona mainitaan mm. haastateltavan tieteenala, oppiaine ja sukupuoli.\r\n\r\nAineistosta on tehty html-versio, jonka hakemiston avulla haastatteluja on helppo selata."
-    ],
-    "oai_identifier": [
-        "0a784bce-115a-50e0-8e9b-031e0d9a2583"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "artikkelit"
-        },
-        {
-            "name": "julkaisut"
-        },
-        {
-            "name": "kirjat"
-        },
-        {
-            "name": "muut"
-        },
-        {
-            "name": "oppikirjat"
-        },
-        {
-            "name": "professorit"
-        },
-        {
-            "name": "tiedelehdet"
-        },
-        {
-            "name": "tiedelehdet"
-        },
-        {
-            "name": "tieteellinen julkaisutoiminta"
-        },
-        {
-            "name": "tieteellinen kirjoittaminen"
-        },
-        {
-            "name": "tieteellinen tieto"
-        },
-        {
-            "name": "tieteellinen tieto"
-        }
-    ],
-    "title": [
-        "Julkaisuk\u00e4yt\u00e4nn\u00f6t eri tieteenaloilla: professorihaastattelut 2007",
-        "Disciplinary Differences in Publishing Practices 2007: Professor Interviews"
-    ],
-    "url": "http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20141222161905627032"
-}
\ No newline at end of file
diff --git a/oaitestdata/etsin-oai_dc/SET_1/json/0a7856f5-1d9d-587e-a4dc-24dd449a8374.json b/oaitestdata/etsin-oai_dc/SET_1/json/0a7856f5-1d9d-587e-a4dc-24dd449a8374.json
deleted file mode 100644
index cb4cbf74..00000000
--- a/oaitestdata/etsin-oai_dc/SET_1/json/0a7856f5-1d9d-587e-a4dc-24dd449a8374.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "atm-data@helsinki.fi"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://etsin.avointiede.fi/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=0a7856f5-1d9d-587e-a4dc-24dd449a8374",
-    "PublicationTimestamp": "2016-03-08T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "atm-data@helsinki.fi"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0"
-    ],
-    "SpatialCoverage": [
-        "DCMI-point: name=Kumpula; east=24.961227; north=60.202887 elevation=45;",
-        "2006-01-01T00:00:00Z/2006-12-31T23:59:59Z"
-    ],
-    "TempCoverageBegin": 303309575999,
-    "TempCoverageEnd": 63271670400,
-    "TemporalCoverage": " period : ( 9612-07-01T11:59:59Z - 2006-01-01T00:00:00Z ) ",
-    "TemporalCoverage:BeginDate": "9612-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2006-01-01T00:00:00Z",
-    "author": [
-        "Pasi Aalto"
-    ],
-    "fulltext": "urn:nbn:fi:csc-kata20160308103255335202;2016-03-08T08:32:55Z;university-of-helsinki-department-of-physics-division-of-atmospheric-sciences;Helsinki Kumpula SMEAR III eddy - Std of CO2 concentration - 2006;Pasi Aalto;http://www.yso.fi/onto/yso/p26208;Title: Std of CO2 concentration \n\nDescription: Standard deviation of carbon dioxide concentration \n\nVariable: std_c_op \n\nUnit: ppm \n\nSource: LI-COR LI-7500 gas analyzer \n\nCategory: Flux ancillary data \n\n;atm-data@helsinki.fi;2016-03-08;dataset;urn:nbn:fi:csc-ida2014012173551v;urn:nbn:fi:csc-ida-10x201703282015017313476v;urn:nbn:fi:csc-ida2014012173551s;urn:nbn:fi:csc-kata20160308103255335202;http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308103255335202;DCMI-point: name=Kumpula; east=24.961227; north=60.202887 elevation=45;;2006-01-01T00:00:00Z/2006-12-31T23:59:59Z;Creative Commons Attribution 4.0",
-    "group": "etsin",
-    "groups": [
-        {
-            "name": "etsin"
-        }
-    ],
-    "name": "0a7856f5-1d9d-587e-a4dc-24dd449a8374",
-    "notes": [
-        "Title: Std of CO2 concentration \n\nDescription: Standard deviation of carbon dioxide concentration \n\nVariable: std_c_op \n\nUnit: ppm \n\nSource: LI-COR LI-7500 gas analyzer \n\nCategory: Flux ancillary data \n\n"
-    ],
-    "oai_identifier": [
-        "0a7856f5-1d9d-587e-a4dc-24dd449a8374"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "http www.yso.fi onto yso p"
-        }
-    ],
-    "title": [
-        "Helsinki Kumpula SMEAR III eddy - Std of CO2 concentration - 2006"
-    ],
-    "url": "http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308103255335202"
-}
\ No newline at end of file
diff --git a/oaitestdata/etsin-oai_dc/SET_1/json/0a82a6b9-6ab2-5df2-a49c-ba8e6d063976.json b/oaitestdata/etsin-oai_dc/SET_1/json/0a82a6b9-6ab2-5df2-a49c-ba8e6d063976.json
deleted file mode 100644
index d921aaa1..00000000
--- a/oaitestdata/etsin-oai_dc/SET_1/json/0a82a6b9-6ab2-5df2-a49c-ba8e6d063976.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "atm-data@helsinki.fi"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://etsin.avointiede.fi/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=0a82a6b9-6ab2-5df2-a49c-ba8e6d063976",
-    "PublicationTimestamp": "2016-03-08T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "atm-data@helsinki.fi"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0"
-    ],
-    "SpatialCoverage": [
-        "DCMI-point: name=V\u00e4rri\u00f6; east=29.610137; north=67.755044; elevation=390;",
-        "2010-01-01T00:00:00Z/2010-12-31T23:59:59Z"
-    ],
-    "TempCoverageBegin": 192513067199,
-    "TempCoverageEnd": 63397900800,
-    "TemporalCoverage": " period : ( 6101-07-01T11:59:59Z - 2010-01-01T00:00:00Z ) ",
-    "TemporalCoverage:BeginDate": "6101-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2010-01-01T00:00:00Z",
-    "author": [
-        "Pasi Kolari"
-    ],
-    "fulltext": "urn:nbn:fi:csc-kata20160308084414814548;2016-03-08T06:44:14Z;university-of-helsinki-department-of-physics-division-of-atmospheric-sciences;V\u00e4rri\u00f6 SMEAR I tree gas exchange and diameter change - Pine shoot 2 CO2 exchange - 2010;Pasi Kolari;http://www.yso.fi/onto/ysa/Y100405;http://www.yso.fi/onto/ysa/Y95330;http://www.yso.fi/onto/yso/p16571;Title: Pine shoot 2 CO2 exchange \n\nDescription: CO2 exchange of pine shoot 2 per unit all-sided leaf area, positive sign = uptake \n\nVariable: F_CO2_tree2 \n\nUnit: \u00b5g m\u207b\u00b2 s\u207b\u00b9 \n\nSource: Automated chamber & Li-Cor Li-840 gas analyser \n\nCategory: Tree \n\n;atm-data@helsinki.fi;Pasi Kolari;Toivo Pohja;Petri Keronen;2016-03-08;dataset;urn:nbn:fi:csc-ida2014011545561v;urn:nbn:fi:csc-ida-10x201703282015017316494v;urn:nbn:fi:csc-ida2014011545561s;urn:nbn:fi:csc-kata20160308084414814548;http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308084414814548;DCMI-point: name=V\u00e4rri\u00f6; east=29.610137; north=67.755044; elevation=390;;2010-01-01T00:00:00Z/2010-12-31T23:59:59Z;Creative Commons Attribution 4.0",
-    "group": "etsin",
-    "groups": [
-        {
-            "name": "etsin"
-        }
-    ],
-    "name": "0a82a6b9-6ab2-5df2-a49c-ba8e6d063976",
-    "notes": [
-        "Title: Pine shoot 2 CO2 exchange \n\nDescription: CO2 exchange of pine shoot 2 per unit all-sided leaf area, positive sign = uptake \n\nVariable: F_CO2_tree2 \n\nUnit: \u00b5g m\u207b\u00b2 s\u207b\u00b9 \n\nSource: Automated chamber & Li-Cor Li-840 gas analyser \n\nCategory: Tree \n\n"
-    ],
-    "oai_identifier": [
-        "0a82a6b9-6ab2-5df2-a49c-ba8e6d063976"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "http www.yso.fi onto ysa Y"
-        },
-        {
-            "name": "http www.yso.fi onto ysa Y"
-        },
-        {
-            "name": "http www.yso.fi onto yso p"
-        }
-    ],
-    "title": [
-        "V\u00e4rri\u00f6 SMEAR I tree gas exchange and diameter change - Pine shoot 2 CO2 exchange - 2010"
-    ],
-    "url": "http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308084414814548"
-}
\ No newline at end of file
diff --git a/oaitestdata/etsin-oai_dc/SET_1/json/0a8e2865-85c7-58b4-9897-0fa0cc0d8749.json b/oaitestdata/etsin-oai_dc/SET_1/json/0a8e2865-85c7-58b4-9897-0fa0cc0d8749.json
deleted file mode 100644
index ca73a3e3..00000000
--- a/oaitestdata/etsin-oai_dc/SET_1/json/0a8e2865-85c7-58b4-9897-0fa0cc0d8749.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "atm-data@helsinki.fi"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://etsin.avointiede.fi/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=0a8e2865-85c7-58b4-9897-0fa0cc0d8749",
-    "PublicationTimestamp": "2016-03-08T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "atm-data@helsinki.fi"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0"
-    ],
-    "SpatialCoverage": [
-        "DCMI-point: name=V\u00e4rri\u00f6; east=29.610137; north=67.755044; elevation=390;",
-        "1998-01-01T00:00:00Z/1998-12-31T23:59:59Z"
-    ],
-    "TempCoverageBegin": 192513067199,
-    "TempCoverageEnd": 63019209600,
-    "TemporalCoverage": " period : ( 6101-07-01T11:59:59Z - 1998-01-01T00:00:00Z ) ",
-    "TemporalCoverage:BeginDate": "6101-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1998-01-01T00:00:00Z",
-    "author": [
-        "Pasi Aalto"
-    ],
-    "fulltext": "urn:nbn:fi:csc-kata20160308093016850995;2016-03-08T07:30:16Z;university-of-helsinki-department-of-physics-division-of-atmospheric-sciences;V\u00e4rri\u00f6 SMEAR I meteorology, gases and soil - Particle concentration 9 m - 1998;Pasi Aalto;http://www.yso.fi/onto/yso/p26207;Title: Particle concentration 9 m \n\nDescription: Number concentration of particles at 9 m height \n\nVariable: CPC1 \n\nUnit: cm\u207b\u00b3 \n\nSource: Condensation Particle Counter TSI 3022 \n\nCategory: Aerosol \n\n;atm-data@helsinki.fi;2016-03-08;dataset;urn:nbn:fi:csc-ida2014011600870v;urn:nbn:fi:csc-ida-10x201704032015017318048v;urn:nbn:fi:csc-ida2014011600870s;urn:nbn:fi:csc-kata20160308093016850995;http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308093016850995;DCMI-point: name=V\u00e4rri\u00f6; east=29.610137; north=67.755044; elevation=390;;1998-01-01T00:00:00Z/1998-12-31T23:59:59Z;Creative Commons Attribution 4.0",
-    "group": "etsin",
-    "groups": [
-        {
-            "name": "etsin"
-        }
-    ],
-    "name": "0a8e2865-85c7-58b4-9897-0fa0cc0d8749",
-    "notes": [
-        "Title: Particle concentration 9 m \n\nDescription: Number concentration of particles at 9 m height \n\nVariable: CPC1 \n\nUnit: cm\u207b\u00b3 \n\nSource: Condensation Particle Counter TSI 3022 \n\nCategory: Aerosol \n\n"
-    ],
-    "oai_identifier": [
-        "0a8e2865-85c7-58b4-9897-0fa0cc0d8749"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "http www.yso.fi onto yso p"
-        }
-    ],
-    "title": [
-        "V\u00e4rri\u00f6 SMEAR I meteorology, gases and soil - Particle concentration 9 m - 1998"
-    ],
-    "url": "http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308093016850995"
-}
\ No newline at end of file
diff --git a/oaitestdata/etsin-oai_dc/SET_1/json/0aac2f97-5aa3-5dc2-b888-3684cf45893c.json b/oaitestdata/etsin-oai_dc/SET_1/json/0aac2f97-5aa3-5dc2-b888-3684cf45893c.json
deleted file mode 100644
index f25563a5..00000000
--- a/oaitestdata/etsin-oai_dc/SET_1/json/0aac2f97-5aa3-5dc2-b888-3684cf45893c.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "atm-data@helsinki.fi"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://etsin.avointiede.fi/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=0aac2f97-5aa3-5dc2-b888-3684cf45893c",
-    "PublicationTimestamp": "2016-03-08T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "atm-data@helsinki.fi"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0"
-    ],
-    "SpatialCoverage": [
-        "DCMI-point: name=Hyyti\u00e4l\u00e4; east=24.294795; north=61.847463 elevation=179",
-        "1999-01-01T00:00:00Z/1999-12-31T23:59:59Z"
-    ],
-    "TempCoverageBegin": 92982427199,
-    "TempCoverageEnd": 63050745600,
-    "TemporalCoverage": " period : ( 2947-07-01T11:59:59Z - 1999-01-01T00:00:00Z ) ",
-    "TemporalCoverage:BeginDate": "2947-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1999-01-01T00:00:00Z",
-    "author": [
-        "Pasi Aalto"
-    ],
-    "fulltext": "urn:nbn:fi:csc-kata20160308105313295230;2016-03-08T08:53:13Z;university-of-helsinki-department-of-physics-division-of-atmospheric-sciences;Hyyti\u00e4l\u00e4 SMEAR II meteorology, gases and soil - NOx concentration 33.6 m - 1999;Pasi Aalto;http://www.yso.fi/onto/yso/p26207;Title: NOx concentration 33.6 m \n\nDescription: Nitrogen oxide concentration in dry air at 33.6 m height \n\nVariable: NOx336 \n\nUnit: ppb \n\nSource: TEI 42 CTL chemiluminescence analyzer; heated metal (Mb) converter -> 28.02.2007 \n\nCategory: Gas \n\n;atm-data@helsinki.fi;2016-03-08;dataset;urn:nbn:fi:csc-ida2014010801766v;urn:nbn:fi:csc-ida2014010801766s;urn:nbn:fi:csc-ida-10x201703282015017312389v;urn:nbn:fi:csc-kata20160308105313295230;http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308105313295230;DCMI-point: name=Hyyti\u00e4l\u00e4; east=24.294795; north=61.847463 elevation=179;1999-01-01T00:00:00Z/1999-12-31T23:59:59Z;Creative Commons Attribution 4.0",
-    "group": "etsin",
-    "groups": [
-        {
-            "name": "etsin"
-        }
-    ],
-    "name": "0aac2f97-5aa3-5dc2-b888-3684cf45893c",
-    "notes": [
-        "Title: NOx concentration 33.6 m \n\nDescription: Nitrogen oxide concentration in dry air at 33.6 m height \n\nVariable: NOx336 \n\nUnit: ppb \n\nSource: TEI 42 CTL chemiluminescence analyzer; heated metal (Mb) converter -> 28.02.2007 \n\nCategory: Gas \n\n"
-    ],
-    "oai_identifier": [
-        "0aac2f97-5aa3-5dc2-b888-3684cf45893c"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "http www.yso.fi onto yso p"
-        }
-    ],
-    "title": [
-        "Hyyti\u00e4l\u00e4 SMEAR II meteorology, gases and soil - NOx concentration 33.6 m - 1999"
-    ],
-    "url": "http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308105313295230"
-}
\ No newline at end of file
diff --git a/oaitestdata/etsin-oai_dc/SET_1/json/0abaafe8-4971-58af-a155-7aa4bb29e76d.json b/oaitestdata/etsin-oai_dc/SET_1/json/0abaafe8-4971-58af-a155-7aa4bb29e76d.json
deleted file mode 100644
index 75dd7af7..00000000
--- a/oaitestdata/etsin-oai_dc/SET_1/json/0abaafe8-4971-58af-a155-7aa4bb29e76d.json
+++ /dev/null
@@ -1,88 +0,0 @@
-{
-    "Contact": [
-        "Yhteiskuntatieteellinen tietoarkisto"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://etsin.avointiede.fi/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=0abaafe8-4971-58af-a155-7aa4bb29e76d",
-    "PublicationTimestamp": "2016-03-10T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Yhteiskuntatieteellinen tietoarkisto"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Other (Not Open)"
-    ],
-    "SpatialCoverage": [
-        "Suomi",
-        "1996/1996"
-    ],
-    "TemporalCoverage": " period : ( None - 1996-07-01T11:59:59Z ) ",
-    "author": [
-        "Kunnallisalan kehitt\u00e4miss\u00e4\u00e4ti\u00f6"
-    ],
-    "fulltext": "urn:nbn:fi:csc-kata20141222155021700283;2016-03-10T09:05:13Z;01905-2571-tampereen-yliopisto-yhteiskuntatieteellinen-tietoarkisto;Kunnallisalan ilmapuntari 1996: kuntalaiset;Finnish Local Government Barometer 1996: Inhabitants;Kunnallisalan kehitt\u00e4miss\u00e4\u00e4ti\u00f6;julkinen hallinto;julkiset palvelut;kunnallishallinto;kunnallistalous;kunnallisvero;kunnanvaltuutetut;kunnat;poliittinen k\u00e4ytt\u00e4ytyminen;poliittiset asenteet;poliittiset asenteet ja mielipiteet;poliittiset organisaatiot;puolueet;taloudellinen s\u00e4\u00e4ntely;ty\u00f6llist\u00e4minen;vallanjako;valtiovalta;yhteiskuntatieteet;Kuntalaisilta tiedusteltiin kunnallisveron tason ja palvelutason vastaavuutta usean eri kysymyksen avulla. Samoin kysyttiin vastaajan k\u00e4sityst\u00e4 kunnan hallinnon ja palveluiden riitt\u00e4vyydest\u00e4, puutteellisuudesta tai liiallisuudesta. Lis\u00e4ksi kartoitettiin suhtautumista kunnan vastuuseen ty\u00f6llist\u00e4mistoimenpiteiden toteuttamisessa ja rahoittamisessa. Kuntalaisten mielest\u00e4 soveliaita s\u00e4\u00e4st\u00f6kohteita tiedusteltiin my\u00f6s.\r\n\r\nKyselyss\u00e4 selvitettiin my\u00f6s ominaisuuksia, joita kuntalaiset mielell\u00e4\u00e4n n\u00e4kisiv\u00e4t omassa valtuutetussaan. Viel\u00e4 tutkittiin, millainen kuva kuntalaisilla on suomalaisista kunnista ja mm. kunnanhallinnosta, sen merkityksest\u00e4 ja vaikuttavuudesta. Kunnallisalan ilmapuntarin kysymyksi\u00e4 uudistettiin vuoden 1996 kyselyss\u00e4 sarjan edellisiin tutkimuksiin verrattuna tavallista enemm\u00e4n.\r\n\r\nTaustamuuttujia olivat vastaajan sukupuoli, ik\u00e4, peruskoulutus, ammatillinen koulutus, kotitalouden tuloluokka, ik\u00e4rakenne, perheenj\u00e4senten lukum\u00e4\u00e4r\u00e4, vastaajan el\u00e4m\u00e4nvaihe, kotitalouden p\u00e4\u00e4henkil\u00f6n ammattiryhm\u00e4 sek\u00e4 p\u00e4\u00e4henkil\u00f6n entinen ammatti, mik\u00e4li h\u00e4n on el\u00e4kel\u00e4inen, vastaajan ammattiryhm\u00e4, ty\u00f6el\u00e4m\u00e4\u00e4n osallistuminen, paikkakuntatyyppi ja asuinl\u00e4\u00e4ni sek\u00e4 onko vastaaja itse kunnan palveluksessa vai ei.;Yhteiskuntatieteellinen tietoarkisto;Yhteiskuntatieteellinen tietoarkisto;2016-03-10;dataset;FSD1120;urn:nbn:fi:fsd:T-FSD1120;urn:nbn:fi:csc-kata20141222155021700283;http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20141222155021700283;Suomi;1996/1996;Other (Not Open)",
-    "group": "etsin",
-    "groups": [
-        {
-            "name": "etsin"
-        }
-    ],
-    "name": "0abaafe8-4971-58af-a155-7aa4bb29e76d",
-    "notes": [
-        "Kuntalaisilta tiedusteltiin kunnallisveron tason ja palvelutason vastaavuutta usean eri kysymyksen avulla. Samoin kysyttiin vastaajan k\u00e4sityst\u00e4 kunnan hallinnon ja palveluiden riitt\u00e4vyydest\u00e4, puutteellisuudesta tai liiallisuudesta. Lis\u00e4ksi kartoitettiin suhtautumista kunnan vastuuseen ty\u00f6llist\u00e4mistoimenpiteiden toteuttamisessa ja rahoittamisessa. Kuntalaisten mielest\u00e4 soveliaita s\u00e4\u00e4st\u00f6kohteita tiedusteltiin my\u00f6s.\r\n\r\nKyselyss\u00e4 selvitettiin my\u00f6s ominaisuuksia, joita kuntalaiset mielell\u00e4\u00e4n n\u00e4kisiv\u00e4t omassa valtuutetussaan. Viel\u00e4 tutkittiin, millainen kuva kuntalaisilla on suomalaisista kunnista ja mm. kunnanhallinnosta, sen merkityksest\u00e4 ja vaikuttavuudesta. Kunnallisalan ilmapuntarin kysymyksi\u00e4 uudistettiin vuoden 1996 kyselyss\u00e4 sarjan edellisiin tutkimuksiin verrattuna tavallista enemm\u00e4n.\r\n\r\nTaustamuuttujia olivat vastaajan sukupuoli, ik\u00e4, peruskoulutus, ammatillinen koulutus, kotitalouden tuloluokka, ik\u00e4rakenne, perheenj\u00e4senten lukum\u00e4\u00e4r\u00e4, vastaajan el\u00e4m\u00e4nvaihe, kotitalouden p\u00e4\u00e4henkil\u00f6n ammattiryhm\u00e4 sek\u00e4 p\u00e4\u00e4henkil\u00f6n entinen ammatti, mik\u00e4li h\u00e4n on el\u00e4kel\u00e4inen, vastaajan ammattiryhm\u00e4, ty\u00f6el\u00e4m\u00e4\u00e4n osallistuminen, paikkakuntatyyppi ja asuinl\u00e4\u00e4ni sek\u00e4 onko vastaaja itse kunnan palveluksessa vai ei."
-    ],
-    "oai_identifier": [
-        "0abaafe8-4971-58af-a155-7aa4bb29e76d"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "julkinen hallinto"
-        },
-        {
-            "name": "julkiset palvelut"
-        },
-        {
-            "name": "kunnallishallinto"
-        },
-        {
-            "name": "kunnallistalous"
-        },
-        {
-            "name": "kunnallisvero"
-        },
-        {
-            "name": "kunnanvaltuutetut"
-        },
-        {
-            "name": "kunnat"
-        },
-        {
-            "name": "kunnat"
-        },
-        {
-            "name": "poliittiset asenteet"
-        },
-        {
-            "name": "poliittiset asenteet ja mielipiteet"
-        },
-        {
-            "name": "poliittiset organisaatiot"
-        },
-        {
-            "name": "puolueet"
-        }
-    ],
-    "title": [
-        "Kunnallisalan ilmapuntari 1996: kuntalaiset",
-        "Finnish Local Government Barometer 1996: Inhabitants"
-    ],
-    "url": "http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20141222155021700283"
-}
\ No newline at end of file
diff --git a/oaitestdata/etsin-oai_dc/SET_1/json/0ac5863a-3928-5f23-bf4f-1b076667bf3c.json b/oaitestdata/etsin-oai_dc/SET_1/json/0ac5863a-3928-5f23-bf4f-1b076667bf3c.json
deleted file mode 100644
index 1dbe6b86..00000000
--- a/oaitestdata/etsin-oai_dc/SET_1/json/0ac5863a-3928-5f23-bf4f-1b076667bf3c.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "atm-data@helsinki.fi"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://etsin.avointiede.fi/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=0ac5863a-3928-5f23-bf4f-1b076667bf3c",
-    "PublicationTimestamp": "2016-03-08T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "atm-data@helsinki.fi"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0"
-    ],
-    "SpatialCoverage": [
-        "DCMI-point: name=Kumpula; east=24.961227; north=60.202887 elevation=45;",
-        "2002-01-01T00:00:00Z/2002-12-31T23:59:59Z"
-    ],
-    "TempCoverageBegin": 303309575999,
-    "TempCoverageEnd": 63145440000,
-    "TemporalCoverage": " period : ( 9612-07-01T11:59:59Z - 2002-01-01T00:00:00Z ) ",
-    "TemporalCoverage:BeginDate": "9612-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2002-01-01T00:00:00Z",
-    "author": [
-        "Pasi Aalto"
-    ],
-    "fulltext": "urn:nbn:fi:csc-kata20160308094450757789;2016-03-08T07:44:50Z;university-of-helsinki-department-of-physics-division-of-atmospheric-sciences;Helsinki Kumpula SMEAR III meteorology - Relative humidity - 2002;Pasi Aalto;http://www.yso.fi/onto/yso/p5394;http://www.yso.fi/onto/yso/p6452;ilmankosteus;Title: Relative humidity \n\nDescription: Relative humidity, Physicum roof, (%) \n\nVariable: rh \n\nUnit: % \n\nSource: saa \n\nCategory: Meteorology \n\n;atm-data@helsinki.fi;2016-03-08;dataset;urn:nbn:fi:csc-ida20140120122388v;urn:nbn:fi:csc-ida-10x201703282015017313136v;urn:nbn:fi:csc-ida20140120122388s;urn:nbn:fi:csc-kata20160308094450757789;http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308094450757789;DCMI-point: name=Kumpula; east=24.961227; north=60.202887 elevation=45;;2002-01-01T00:00:00Z/2002-12-31T23:59:59Z;Creative Commons Attribution 4.0",
-    "group": "etsin",
-    "groups": [
-        {
-            "name": "etsin"
-        }
-    ],
-    "name": "0ac5863a-3928-5f23-bf4f-1b076667bf3c",
-    "notes": [
-        "Title: Relative humidity \n\nDescription: Relative humidity, Physicum roof, (%) \n\nVariable: rh \n\nUnit: % \n\nSource: saa \n\nCategory: Meteorology \n\n"
-    ],
-    "oai_identifier": [
-        "0ac5863a-3928-5f23-bf4f-1b076667bf3c"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "http www.yso.fi onto yso p"
-        },
-        {
-            "name": "http www.yso.fi onto yso p"
-        },
-        {
-            "name": "ilmankosteus"
-        }
-    ],
-    "title": [
-        "Helsinki Kumpula SMEAR III meteorology - Relative humidity - 2002"
-    ],
-    "url": "http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308094450757789"
-}
\ No newline at end of file
diff --git a/oaitestdata/etsin-oai_dc/SET_1/json/0acdc680-53ad-52ec-aab3-26700b722e27.json b/oaitestdata/etsin-oai_dc/SET_1/json/0acdc680-53ad-52ec-aab3-26700b722e27.json
deleted file mode 100644
index 2e28d635..00000000
--- a/oaitestdata/etsin-oai_dc/SET_1/json/0acdc680-53ad-52ec-aab3-26700b722e27.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "atm-data@helsinki.fi"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://etsin.avointiede.fi/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=0acdc680-53ad-52ec-aab3-26700b722e27",
-    "PublicationTimestamp": "2016-03-08T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "atm-data@helsinki.fi"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0"
-    ],
-    "SpatialCoverage": [
-        "DCMI-point: name=Hyyti\u00e4l\u00e4; east=24.294795; north=61.847463 elevation=179",
-        "2010-01-01T00:00:00Z/2010-12-31T23:59:59Z"
-    ],
-    "TempCoverageBegin": 92982427199,
-    "TempCoverageEnd": 63397900800,
-    "TemporalCoverage": " period : ( 2947-07-01T11:59:59Z - 2010-01-01T00:00:00Z ) ",
-    "TemporalCoverage:BeginDate": "2947-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2010-01-01T00:00:00Z",
-    "author": [
-        "Pasi Aalto"
-    ],
-    "fulltext": "urn:nbn:fi:csc-kata20160308104510304464;2016-03-08T08:45:10Z;university-of-helsinki-department-of-physics-division-of-atmospheric-sciences;Hyyti\u00e4l\u00e4 SMEAR II eddy radiation tower - Std of H2O concentration (2) - 2010;Pasi Aalto;http://www.yso.fi/onto/yso/p26208;Title: Std of H2O concentration (2) \n\nDescription: Standard deviation of water vapour concentration, radiation tower 23 m height, secondary flux measuring setup \n\nVariable: std_h_radtow \n\nUnit: mmol mol\u207b\u00b9 \n\nSource: LI-COR LI-6262 gas analyzer \n\nCategory: Flux ancillary data \n\n;atm-data@helsinki.fi;2016-03-08;dataset;urn:nbn:fi:csc-ida2014010802661v;urn:nbn:fi:csc-ida2014010802661s;urn:nbn:fi:csc-kata20160308104510304464;http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308104510304464;DCMI-point: name=Hyyti\u00e4l\u00e4; east=24.294795; north=61.847463 elevation=179;2010-01-01T00:00:00Z/2010-12-31T23:59:59Z;Creative Commons Attribution 4.0",
-    "group": "etsin",
-    "groups": [
-        {
-            "name": "etsin"
-        }
-    ],
-    "name": "0acdc680-53ad-52ec-aab3-26700b722e27",
-    "notes": [
-        "Title: Std of H2O concentration (2) \n\nDescription: Standard deviation of water vapour concentration, radiation tower 23 m height, secondary flux measuring setup \n\nVariable: std_h_radtow \n\nUnit: mmol mol\u207b\u00b9 \n\nSource: LI-COR LI-6262 gas analyzer \n\nCategory: Flux ancillary data \n\n"
-    ],
-    "oai_identifier": [
-        "0acdc680-53ad-52ec-aab3-26700b722e27"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "http www.yso.fi onto yso p"
-        }
-    ],
-    "title": [
-        "Hyyti\u00e4l\u00e4 SMEAR II eddy radiation tower - Std of H2O concentration (2) - 2010"
-    ],
-    "url": "http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308104510304464"
-}
\ No newline at end of file
diff --git a/oaitestdata/etsin-oai_dc/SET_1/json/0ad1198f-e621-52eb-a76a-e50612998268.json b/oaitestdata/etsin-oai_dc/SET_1/json/0ad1198f-e621-52eb-a76a-e50612998268.json
deleted file mode 100644
index 62ebbf42..00000000
--- a/oaitestdata/etsin-oai_dc/SET_1/json/0ad1198f-e621-52eb-a76a-e50612998268.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "atm-data@helsinki.fi"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://etsin.avointiede.fi/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=0ad1198f-e621-52eb-a76a-e50612998268",
-    "PublicationTimestamp": "2016-03-08T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "atm-data@helsinki.fi"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0"
-    ],
-    "SpatialCoverage": [
-        "DCMI-point: name=V\u00e4rri\u00f6; east=29.610137; north=67.755044; elevation=390;",
-        "1995-01-01T00:00:00Z/1995-12-31T23:59:59Z"
-    ],
-    "TempCoverageBegin": 192513067199,
-    "TempCoverageEnd": 62924515200,
-    "TemporalCoverage": " period : ( 6101-07-01T11:59:59Z - 1995-01-01T00:00:00Z ) ",
-    "TemporalCoverage:BeginDate": "6101-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1995-01-01T00:00:00Z",
-    "author": [
-        "Pasi Aalto"
-    ],
-    "fulltext": "urn:nbn:fi:csc-kata20160308090945812097;2016-03-08T07:09:45Z;university-of-helsinki-department-of-physics-division-of-atmospheric-sciences;V\u00e4rri\u00f6 SMEAR I meteorology, gases and soil - Air temperature 15 m - 1995;Pasi Aalto;http://www.yso.fi/onto/yso/p5394;Title: Air temperature 15 m \n\nDescription: Air temperature 15 m \n\nVariable: TDRY0 \n\nUnit: \u00b0C \n\nSource: Ventilated and shielded Pt100 temperature sensor \n\nCategory: Meteorology \n\n;atm-data@helsinki.fi;2016-03-08;dataset;urn:nbn:fi:csc-ida2014011532168v;urn:nbn:fi:csc-ida2014011532168s;urn:nbn:fi:csc-ida-10x201703282015017315111v;urn:nbn:fi:csc-kata20160308090945812097;http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308090945812097;DCMI-point: name=V\u00e4rri\u00f6; east=29.610137; north=67.755044; elevation=390;;1995-01-01T00:00:00Z/1995-12-31T23:59:59Z;Creative Commons Attribution 4.0",
-    "group": "etsin",
-    "groups": [
-        {
-            "name": "etsin"
-        }
-    ],
-    "name": "0ad1198f-e621-52eb-a76a-e50612998268",
-    "notes": [
-        "Title: Air temperature 15 m \n\nDescription: Air temperature 15 m \n\nVariable: TDRY0 \n\nUnit: \u00b0C \n\nSource: Ventilated and shielded Pt100 temperature sensor \n\nCategory: Meteorology \n\n"
-    ],
-    "oai_identifier": [
-        "0ad1198f-e621-52eb-a76a-e50612998268"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "http www.yso.fi onto yso p"
-        }
-    ],
-    "title": [
-        "V\u00e4rri\u00f6 SMEAR I meteorology, gases and soil - Air temperature 15 m - 1995"
-    ],
-    "url": "http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308090945812097"
-}
\ No newline at end of file
diff --git a/oaitestdata/etsin-oai_dc/SET_1/json/0ada1ea2-bd8e-5de7-bd86-779a9a21f177.json b/oaitestdata/etsin-oai_dc/SET_1/json/0ada1ea2-bd8e-5de7-bd86-779a9a21f177.json
deleted file mode 100644
index 758f2155..00000000
--- a/oaitestdata/etsin-oai_dc/SET_1/json/0ada1ea2-bd8e-5de7-bd86-779a9a21f177.json
+++ /dev/null
@@ -1,155 +0,0 @@
-{
-    "Contact": [
-        "Yhteiskuntatieteellinen tietoarkisto"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://etsin.avointiede.fi/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=0ada1ea2-bd8e-5de7-bd86-779a9a21f177",
-    "PublicationTimestamp": "2016-03-10T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Yhteiskuntatieteellinen tietoarkisto"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Other (Not Open)"
-    ],
-    "SpatialCoverage": [
-        "Suomi",
-        "Alavus",
-        "Anjalankoski",
-        "Espoo",
-        "Helsinki",
-        "Huittinen",
-        "H\u00e4meenlinna",
-        "Imatra",
-        "Joensuu",
-        "J\u00e4ms\u00e4",
-        "J\u00e4rvenp\u00e4\u00e4",
-        "Kemi",
-        "Kerava",
-        "Kokkola",
-        "Kuusankoski",
-        "Lappeenranta",
-        "Lapua",
-        "Loviisa",
-        "Maarianhamina",
-        "Mikkeli",
-        "M\u00e4ntt\u00e4",
-        "Naantali",
-        "Oulainen",
-        "Pieks\u00e4m\u00e4ki",
-        "Porvoo",
-        "Raahe",
-        "Riihim\u00e4ki",
-        "Salo",
-        "Sein\u00e4joki",
-        "Tampere",
-        "Vantaa",
-        "Ylivieska",
-        "1983/1983"
-    ],
-    "TemporalCoverage": [
-        "Suomi",
-        "Alavus",
-        "Anjalankoski",
-        "Espoo",
-        "Helsinki",
-        "Huittinen",
-        "H\u00e4meenlinna",
-        "Imatra",
-        "Joensuu",
-        "J\u00e4ms\u00e4",
-        "J\u00e4rvenp\u00e4\u00e4",
-        "Kemi",
-        "Kerava",
-        "Kokkola",
-        "Kuusankoski",
-        "Lappeenranta",
-        "Lapua",
-        "Loviisa",
-        "Maarianhamina",
-        "Mikkeli",
-        "M\u00e4ntt\u00e4",
-        "Naantali",
-        "Oulainen",
-        "Pieks\u00e4m\u00e4ki",
-        "Porvoo",
-        "Raahe",
-        "Riihim\u00e4ki",
-        "Salo",
-        "Sein\u00e4joki",
-        "Tampere",
-        "Vantaa",
-        "Ylivieska",
-        "1983/1983"
-    ],
-    "author": [
-        "Sneck, Timo",
-        "Outinen, Seppo",
-        "Varhe, Seppo"
-    ],
-    "fulltext": "urn:nbn:fi:csc-kata20141222155318622494;2016-03-10T09:07:47Z;01905-2571-tampereen-yliopisto-yhteiskuntatieteellinen-tietoarkisto;Kaupunkipalvelututkimus 1983;City Service Survey 1983;Outinen, Seppo;Varhe, Seppo;Sneck, Timo;asuminen;julkiset palvelut;kaupungit;kehitt\u00e4minen;koulunk\u00e4ynti;kulttuuripalvelut;kunnat;lastenhoito;osallistuminen;sosiaalipalveluiden k\u00e4ytt\u00f6 ja saatavuus;sosiaalipolitiikka;terveydenhoito;ulkoilu;vaikuttaminen;vanhustenhuolto;vapaa-aika;yhteiskuntatieteet;Kaupunkipalvelututkimus 1983 kartoitti kuntien asukkaiden mielipiteit\u00e4 kaupungin palvelujen ja hallinnon nykytilanteesta ja kehitt\u00e4mistarpeista. Vastaajilta kysyttiin asuinalueesta ja asumisesta, lastenhoidon j\u00e4rjest\u00e4misest\u00e4, neuvolapalveluista, ala- ja yl\u00e4asteesta, terveyspalveluista, vanhustenhuollosta, kulttuuripalveluista, vapaa-ajanviettomahdollisuuksista, suhtautumisesta kunnan hallintoon, kunnan tiedottamisesta sek\u00e4 kunnan kehitt\u00e4misest\u00e4. Taustakysymyksin\u00e4 olivat esimerkiksi syntym\u00e4vuosi, sukupuoli, siviilis\u00e4\u00e4ty, koulutus, lasten lukum\u00e4\u00e4r\u00e4, ammattiasema, kulkuv\u00e4line, jota k\u00e4ytt\u00e4\u00e4 ty\u00f6matkoilla sek\u00e4 ty\u00f6matkan pituus.;Yhteiskuntatieteellinen tietoarkisto;Yhteiskuntatieteellinen tietoarkisto;2016-03-10;dataset;FSD1200;urn:nbn:fi:fsd:T-FSD1200;urn:nbn:fi:csc-kata20141222155318622494;http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20141222155318622494;Suomi;Alavus;Anjalankoski;Espoo;Helsinki;Huittinen;H\u00e4meenlinna;Imatra;Joensuu;J\u00e4ms\u00e4;J\u00e4rvenp\u00e4\u00e4;Kemi;Kerava;Kokkola;Kuusankoski;Lappeenranta;Lapua;Loviisa;Maarianhamina;Mikkeli;M\u00e4ntt\u00e4;Naantali;Oulainen;Pieks\u00e4m\u00e4ki;Porvoo;Raahe;Riihim\u00e4ki;Salo;Sein\u00e4joki;Tampere;Vantaa;Ylivieska;1983/1983;Other (Not Open)",
-    "group": "etsin",
-    "groups": [
-        {
-            "name": "etsin"
-        }
-    ],
-    "name": "0ada1ea2-bd8e-5de7-bd86-779a9a21f177",
-    "notes": [
-        "Kaupunkipalvelututkimus 1983 kartoitti kuntien asukkaiden mielipiteit\u00e4 kaupungin palvelujen ja hallinnon nykytilanteesta ja kehitt\u00e4mistarpeista. Vastaajilta kysyttiin asuinalueesta ja asumisesta, lastenhoidon j\u00e4rjest\u00e4misest\u00e4, neuvolapalveluista, ala- ja yl\u00e4asteesta, terveyspalveluista, vanhustenhuollosta, kulttuuripalveluista, vapaa-ajanviettomahdollisuuksista, suhtautumisesta kunnan hallintoon, kunnan tiedottamisesta sek\u00e4 kunnan kehitt\u00e4misest\u00e4. Taustakysymyksin\u00e4 olivat esimerkiksi syntym\u00e4vuosi, sukupuoli, siviilis\u00e4\u00e4ty, koulutus, lasten lukum\u00e4\u00e4r\u00e4, ammattiasema, kulkuv\u00e4line, jota k\u00e4ytt\u00e4\u00e4 ty\u00f6matkoilla sek\u00e4 ty\u00f6matkan pituus."
-    ],
-    "oai_identifier": [
-        "0ada1ea2-bd8e-5de7-bd86-779a9a21f177"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "asuminen"
-        },
-        {
-            "name": "julkiset palvelut"
-        },
-        {
-            "name": "kaupungit"
-        },
-        {
-            "name": "kaupungit"
-        },
-        {
-            "name": "kaupungit"
-        },
-        {
-            "name": "kulttuuripalvelut"
-        },
-        {
-            "name": "kunnat"
-        },
-        {
-            "name": "lastenhoito"
-        },
-        {
-            "name": "osallistuminen"
-        },
-        {
-            "name": "osallistuminen"
-        },
-        {
-            "name": "sosiaalipolitiikka"
-        },
-        {
-            "name": "terveydenhoito"
-        }
-    ],
-    "title": [
-        "Kaupunkipalvelututkimus 1983",
-        "City Service Survey 1983"
-    ],
-    "url": "http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20141222155318622494"
-}
\ No newline at end of file
diff --git a/oaitestdata/etsin-oai_dc/SET_1/json/0ae1612e-f1de-57e1-8596-5b2e8b26a95a.json b/oaitestdata/etsin-oai_dc/SET_1/json/0ae1612e-f1de-57e1-8596-5b2e8b26a95a.json
deleted file mode 100644
index 000e9ae0..00000000
--- a/oaitestdata/etsin-oai_dc/SET_1/json/0ae1612e-f1de-57e1-8596-5b2e8b26a95a.json
+++ /dev/null
@@ -1,433 +0,0 @@
-{
-    "Contact": [
-        "Yhteiskuntatieteellinen tietoarkisto"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://etsin.avointiede.fi/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=0ae1612e-f1de-57e1-8596-5b2e8b26a95a",
-    "PublicationTimestamp": "2016-03-10T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Yhteiskuntatieteellinen tietoarkisto"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Other (Not Open)"
-    ],
-    "SpatialCoverage": [
-        "Afganistan",
-        "Albania",
-        "Algeria",
-        "Angola",
-        "Argentiina",
-        "Armenia",
-        "Australia",
-        "It\u00e4valta",
-        "Azerbaidzan",
-        "Bahama",
-        "Bahrain",
-        "Bangladesh",
-        "Barbados",
-        "Valko-Ven\u00e4j\u00e4",
-        "Belgia",
-        "Belize",
-        "Benin",
-        "Bhutan",
-        "Bolivia",
-        "Bosnia ja Hertsegovina",
-        "Botswana",
-        "Brasilia",
-        "Brunei",
-        "Bulgaria",
-        "Burkina Faso",
-        "Myanmar (Burma)",
-        "Burundi",
-        "Kambodza",
-        "Kamerun",
-        "Kanada",
-        "Kap Verde",
-        "Keski-Afrikan tasavalta",
-        "Tsad",
-        "Chile",
-        "Kiina",
-        "Kolumbia",
-        "Komorit",
-        "Kongon demokraattinen tasavalta",
-        "Kongon tasavalta",
-        "Costa Rica",
-        "Norsunluurannikko (C\u00f4te d'Ivoire)",
-        "Kroatia",
-        "Kuuba",
-        "Kypros",
-        "Tsekki",
-        "Tanska",
-        "Djibouti",
-        "Dominikaaninen tasavalta",
-        "It\u00e4-Timor",
-        "Ecuador",
-        "Egypti",
-        "El Salvador",
-        "P\u00e4iv\u00e4ntasaajan Guinea",
-        "Eritrea",
-        "Viro",
-        "Etiopia",
-        "Fidzi",
-        "Suomi",
-        "Ranska",
-        "Gabon",
-        "Gambia",
-        "Georgia",
-        "Saksa",
-        "Ghana",
-        "Kreikka",
-        "Guatemala",
-        "Guinea",
-        "Guinea-Bissau",
-        "Guyana",
-        "Haiti",
-        "Honduras",
-        "Unkari",
-        "Islanti",
-        "Intia",
-        "Indonesia",
-        "Iran",
-        "Irak",
-        "Irlanti",
-        "Israel",
-        "Italia",
-        "Jamaika",
-        "Japani",
-        "Jordania",
-        "Kazakstan",
-        "Kenia",
-        "Pohjois-Korea",
-        "Etel\u00e4-Korea",
-        "Kuwait",
-        "Kirgisia",
-        "Laos",
-        "Latvia",
-        "Libanon",
-        "Lesotho",
-        "Liberia",
-        "Libya",
-        "Liettua",
-        "Luxemburg",
-        "Makedonia",
-        "Madagaskar",
-        "Malawi",
-        "Malesia",
-        "Malediivit",
-        "Mali",
-        "Malta",
-        "Mauritania",
-        "Mauritius",
-        "Meksiko",
-        "Moldova",
-        "Mongolia",
-        "Marokko",
-        "Montenegro",
-        "Mosambik",
-        "Namibia",
-        "Nepal",
-        "Alankomaat",
-        "Uusi-Seelanti",
-        "Nicaragua",
-        "Niger",
-        "Nigeria",
-        "Norja",
-        "Oman",
-        "Pakistan",
-        "Panama",
-        "Papua-Uusi-Guinea",
-        "Paraguay",
-        "Peru",
-        "Filippiinit",
-        "Puola",
-        "Portugali",
-        "Qatar",
-        "Romania",
-        "Ven\u00e4j\u00e4",
-        "Ruanda",
-        "Saudi-Arabia",
-        "Senegal",
-        "Serbia",
-        "Sierra Leone",
-        "Singapore",
-        "Slovakia",
-        "Slovenia",
-        "Salomonsaaret",
-        "Somalia",
-        "Etel\u00e4-Afrikka",
-        "Espanja",
-        "Sri Lanka",
-        "Sudan",
-        "Surinam",
-        "Swazimaa",
-        "Ruotsi",
-        "Sveitsi",
-        "Syyria",
-        "Taiwan",
-        "Tadzikistan",
-        "Tansania",
-        "Thaimaa",
-        "Togo",
-        "Trinidad ja Tobago",
-        "Tunisia",
-        "Turkki",
-        "Turkmenistan",
-        "Uganda",
-        "Ukraina",
-        "Arabiemiirikunnat",
-        "Iso-Britannia",
-        "Yhdysvallat",
-        "Uruguay",
-        "Uzbekistan",
-        "Venezuela",
-        "Vietnam",
-        "Jemen",
-        "Sambia",
-        "Zimbabwe",
-        "1980/2006"
-    ],
-    "TemporalCoverage": [
-        "Afganistan",
-        "Albania",
-        "Algeria",
-        "Angola",
-        "Argentiina",
-        "Armenia",
-        "Australia",
-        "It\u00e4valta",
-        "Azerbaidzan",
-        "Bahama",
-        "Bahrain",
-        "Bangladesh",
-        "Barbados",
-        "Valko-Ven\u00e4j\u00e4",
-        "Belgia",
-        "Belize",
-        "Benin",
-        "Bhutan",
-        "Bolivia",
-        "Bosnia ja Hertsegovina",
-        "Botswana",
-        "Brasilia",
-        "Brunei",
-        "Bulgaria",
-        "Burkina Faso",
-        "Myanmar (Burma)",
-        "Burundi",
-        "Kambodza",
-        "Kamerun",
-        "Kanada",
-        "Kap Verde",
-        "Keski-Afrikan tasavalta",
-        "Tsad",
-        "Chile",
-        "Kiina",
-        "Kolumbia",
-        "Komorit",
-        "Kongon demokraattinen tasavalta",
-        "Kongon tasavalta",
-        "Costa Rica",
-        "Norsunluurannikko (C\u00f4te d'Ivoire)",
-        "Kroatia",
-        "Kuuba",
-        "Kypros",
-        "Tsekki",
-        "Tanska",
-        "Djibouti",
-        "Dominikaaninen tasavalta",
-        "It\u00e4-Timor",
-        "Ecuador",
-        "Egypti",
-        "El Salvador",
-        "P\u00e4iv\u00e4ntasaajan Guinea",
-        "Eritrea",
-        "Viro",
-        "Etiopia",
-        "Fidzi",
-        "Suomi",
-        "Ranska",
-        "Gabon",
-        "Gambia",
-        "Georgia",
-        "Saksa",
-        "Ghana",
-        "Kreikka",
-        "Guatemala",
-        "Guinea",
-        "Guinea-Bissau",
-        "Guyana",
-        "Haiti",
-        "Honduras",
-        "Unkari",
-        "Islanti",
-        "Intia",
-        "Indonesia",
-        "Iran",
-        "Irak",
-        "Irlanti",
-        "Israel",
-        "Italia",
-        "Jamaika",
-        "Japani",
-        "Jordania",
-        "Kazakstan",
-        "Kenia",
-        "Pohjois-Korea",
-        "Etel\u00e4-Korea",
-        "Kuwait",
-        "Kirgisia",
-        "Laos",
-        "Latvia",
-        "Libanon",
-        "Lesotho",
-        "Liberia",
-        "Libya",
-        "Liettua",
-        "Luxemburg",
-        "Makedonia",
-        "Madagaskar",
-        "Malawi",
-        "Malesia",
-        "Malediivit",
-        "Mali",
-        "Malta",
-        "Mauritania",
-        "Mauritius",
-        "Meksiko",
-        "Moldova",
-        "Mongolia",
-        "Marokko",
-        "Montenegro",
-        "Mosambik",
-        "Namibia",
-        "Nepal",
-        "Alankomaat",
-        "Uusi-Seelanti",
-        "Nicaragua",
-        "Niger",
-        "Nigeria",
-        "Norja",
-        "Oman",
-        "Pakistan",
-        "Panama",
-        "Papua-Uusi-Guinea",
-        "Paraguay",
-        "Peru",
-        "Filippiinit",
-        "Puola",
-        "Portugali",
-        "Qatar",
-        "Romania",
-        "Ven\u00e4j\u00e4",
-        "Ruanda",
-        "Saudi-Arabia",
-        "Senegal",
-        "Serbia",
-        "Sierra Leone",
-        "Singapore",
-        "Slovakia",
-        "Slovenia",
-        "Salomonsaaret",
-        "Somalia",
-        "Etel\u00e4-Afrikka",
-        "Espanja",
-        "Sri Lanka",
-        "Sudan",
-        "Surinam",
-        "Swazimaa",
-        "Ruotsi",
-        "Sveitsi",
-        "Syyria",
-        "Taiwan",
-        "Tadzikistan",
-        "Tansania",
-        "Thaimaa",
-        "Togo",
-        "Trinidad ja Tobago",
-        "Tunisia",
-        "Turkki",
-        "Turkmenistan",
-        "Uganda",
-        "Ukraina",
-        "Arabiemiirikunnat",
-        "Iso-Britannia",
-        "Yhdysvallat",
-        "Uruguay",
-        "Uzbekistan",
-        "Venezuela",
-        "Vietnam",
-        "Jemen",
-        "Sambia",
-        "Zimbabwe",
-        "1980/2006"
-    ],
-    "author": [
-        "Vanhanen, Tatu"
-    ],
-    "fulltext": "urn:nbn:fi:csc-kata20141222161020777763;2016-03-10T09:23:52Z;01905-2571-tampereen-yliopisto-yhteiskuntatieteellinen-tietoarkisto;Valtaresurssit 2007;Index of Power Resources (IPR) 2007;Vanhanen, Tatu;demokratia;demokratisoituminen;henkinen p\u00e4\u00e4oma;kansainv\u00e4linen politiikka ja j\u00e4rjest\u00f6t;koulutus;lukutaito;maaseutuv\u00e4est\u00f6;maatalousyhteiskunta;resurssit;taloudellinen kehitys;talouden tila ja tunnusluvut;valta;valtio-oppi;yhteiskuntakehitys;yhteiskuntatieteet;Aineisto on jatkoa professori Tatu Vanhasen kokoamalle aineistolle FSD1216 Demokratisoituminen ja valtaresurssit 1850-2000, joka oli tulos pitk\u00e4aikaisesta valtioiden demokratisoitumista ja valtaresursseja koskevasta tutkimusty\u00f6st\u00e4. Erilaisista kirjallisista l\u00e4hteist\u00e4 kootut, p\u00e4ivitetyt tiedot on julkaistu my\u00f6s Vanhasen julkaisussa \"The Limits of Democratization\". Teoksessa julkaistujen numerotietojen alkuper\u00e4iset l\u00e4hteet on koottu erilliseen dokumenttiin, johon on linkki alla kohdassa: muu materiaali: alkuper\u00e4isl\u00e4hteet.\r\n\r\nAineisto sis\u00e4lt\u00e4\u00e4 kahdeksan eri resurssien jakautuneisuutta kuvaavan muuttujan arvot valtioittain. N\u00e4it\u00e4 ovat: 1) Korkeakouluopiskelijoiden osuus (Tertiary Enrollment Ratio %); 2) Lukutaitoisten osuus aikuisv\u00e4est\u00f6st\u00e4 (Adult Literacy Rate %); 3) \u00c4lyllisten valtaresurssien indeksi (Index of Intellectual Power Resources, IR); 4) Perhetilojen osuus (Family Farms, FF %); 5) Agraariv\u00e4est\u00f6n osuus (Agricultural Population, AP %); 6) Arvioitu taloudellisten valtaresurssien jakautuneisuuden aste (Estimated Degree of Decentralization of Economic Power Resources, DD); 7) Taloudellisten valtaresurssien indeksi (Index of Economic Power Resources, ER); ja 8) Valtaresurssi-indeksi (Index of Power Resources, IPR). Muuttujien tiedot on p\u00e4ivitetty edellisest\u00e4 aineistosta, ja n\u00e4iden laskutapaa on joissain tapauksissa tarkennettu tai n\u00e4m\u00e4 on muodostettu kokonaan uudella tavalla.\r\n\r\nKorkeakouluopiskelijoiden osuus (Tertiary Enrollment Ratio %) perustuu korkeakoulutukseen osallistuvien prosenttiosuuteen relevantissa ik\u00e4luokassa. Lukutaitoisten osuus aikuisv\u00e4est\u00f6st\u00e4 (Adult Literacy Rate %) lasketaan prosentteina aikuisv\u00e4est\u00f6st\u00e4. IR on n\u00e4iden kahden keskiarvo.\r\n\r\nPerhetilojen osuus (Family Farms, FF %) tarkoittaa perhetilojen yhteenlaskettua pinta-alaa koko viljelypinta-alasta tai maatilojen kokonaisalasta prosentteina. Agraariv\u00e4est\u00f6n osuus vuosilta 2000-2005 on muuttujassa AP. DD saadaan, kun lasketaan yhteen k\u00f6yhyysrajan alla el\u00e4v\u00e4t (%) ja rikkaimman 10 % osuus koko v\u00e4est\u00f6n tuloista tai kulutuksesta v\u00e4hennettyn\u00e4 10 prosenttiyksikk\u00f6\u00e4, ja v\u00e4hennet\u00e4\u00e4n saatu summa sadasta. Joissain tapauksissa saatua prosenttilukua on v\u00e4hennetty tai kasvatettu syist\u00e4, jotka on esitelty tarkemmin Vanhasen teoksessa The Limits of Democratization. ER lasketaan kaavalla ER=(FF * AP) + (DD * NAP), miss\u00e4 NAP=100-AP. Viimeinen muuttuja, IPR (The Index of Power Resources), saadaan jakamalla IR:n ja ER:n tulo sadalla.;Yhteiskuntatieteellinen tietoarkisto;Yhteiskuntatieteellinen tietoarkisto;2016-03-10;dataset;FSD2420;urn:nbn:fi:fsd:T-FSD2420;urn:nbn:fi:csc-kata20141222161020777763;http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20141222161020777763;Afganistan;Albania;Algeria;Angola;Argentiina;Armenia;Australia;It\u00e4valta;Azerbaidzan;Bahama;Bahrain;Bangladesh;Barbados;Valko-Ven\u00e4j\u00e4;Belgia;Belize;Benin;Bhutan;Bolivia;Bosnia ja Hertsegovina;Botswana;Brasilia;Brunei;Bulgaria;Burkina Faso;Myanmar (Burma);Burundi;Kambodza;Kamerun;Kanada;Kap Verde;Keski-Afrikan tasavalta;Tsad;Chile;Kiina;Kolumbia;Komorit;Kongon demokraattinen tasavalta;Kongon tasavalta;Costa Rica;Norsunluurannikko (C\u00f4te d'Ivoire);Kroatia;Kuuba;Kypros;Tsekki;Tanska;Djibouti;Dominikaaninen tasavalta;It\u00e4-Timor;Ecuador;Egypti;El Salvador;P\u00e4iv\u00e4ntasaajan Guinea;Eritrea;Viro;Etiopia;Fidzi;Suomi;Ranska;Gabon;Gambia;Georgia;Saksa;Ghana;Kreikka;Guatemala;Guinea;Guinea-Bissau;Guyana;Haiti;Honduras;Unkari;Islanti;Intia;Indonesia;Iran;Irak;Irlanti;Israel;Italia;Jamaika;Japani;Jordania;Kazakstan;Kenia;Pohjois-Korea;Etel\u00e4-Korea;Kuwait;Kirgisia;Laos;Latvia;Libanon;Lesotho;Liberia;Libya;Liettua;Luxemburg;Makedonia;Madagaskar;Malawi;Malesia;Malediivit;Mali;Malta;Mauritania;Mauritius;Meksiko;Moldova;Mongolia;Marokko;Montenegro;Mosambik;Namibia;Nepal;Alankomaat;Uusi-Seelanti;Nicaragua;Niger;Nigeria;Norja;Oman;Pakistan;Panama;Papua-Uusi-Guinea;Paraguay;Peru;Filippiinit;Puola;Portugali;Qatar;Romania;Ven\u00e4j\u00e4;Ruanda;Saudi-Arabia;Senegal;Serbia;Sierra Leone;Singapore;Slovakia;Slovenia;Salomonsaaret;Somalia;Etel\u00e4-Afrikka;Espanja;Sri Lanka;Sudan;Surinam;Swazimaa;Ruotsi;Sveitsi;Syyria;Taiwan;Tadzikistan;Tansania;Thaimaa;Togo;Trinidad ja Tobago;Tunisia;Turkki;Turkmenistan;Uganda;Ukraina;Arabiemiirikunnat;Iso-Britannia;Yhdysvallat;Uruguay;Uzbekistan;Venezuela;Vietnam;Jemen;Sambia;Zimbabwe;1980/2006;Other (Not Open)",
-    "group": "etsin",
-    "groups": [
-        {
-            "name": "etsin"
-        }
-    ],
-    "name": "0ae1612e-f1de-57e1-8596-5b2e8b26a95a",
-    "notes": [
-        "Aineisto on jatkoa professori Tatu Vanhasen kokoamalle aineistolle FSD1216 Demokratisoituminen ja valtaresurssit 1850-2000, joka oli tulos pitk\u00e4aikaisesta valtioiden demokratisoitumista ja valtaresursseja koskevasta tutkimusty\u00f6st\u00e4. Erilaisista kirjallisista l\u00e4hteist\u00e4 kootut, p\u00e4ivitetyt tiedot on julkaistu my\u00f6s Vanhasen julkaisussa \"The Limits of Democratization\". Teoksessa julkaistujen numerotietojen alkuper\u00e4iset l\u00e4hteet on koottu erilliseen dokumenttiin, johon on linkki alla kohdassa: muu materiaali: alkuper\u00e4isl\u00e4hteet.\r\n\r\nAineisto sis\u00e4lt\u00e4\u00e4 kahdeksan eri resurssien jakautuneisuutta kuvaavan muuttujan arvot valtioittain. N\u00e4it\u00e4 ovat: 1) Korkeakouluopiskelijoiden osuus (Tertiary Enrollment Ratio %); 2) Lukutaitoisten osuus aikuisv\u00e4est\u00f6st\u00e4 (Adult Literacy Rate %); 3) \u00c4lyllisten valtaresurssien indeksi (Index of Intellectual Power Resources, IR); 4) Perhetilojen osuus (Family Farms, FF %); 5) Agraariv\u00e4est\u00f6n osuus (Agricultural Population, AP %); 6) Arvioitu taloudellisten valtaresurssien jakautuneisuuden aste (Estimated Degree of Decentralization of Economic Power Resources, DD); 7) Taloudellisten valtaresurssien indeksi (Index of Economic Power Resources, ER); ja 8) Valtaresurssi-indeksi (Index of Power Resources, IPR). Muuttujien tiedot on p\u00e4ivitetty edellisest\u00e4 aineistosta, ja n\u00e4iden laskutapaa on joissain tapauksissa tarkennettu tai n\u00e4m\u00e4 on muodostettu kokonaan uudella tavalla.\r\n\r\nKorkeakouluopiskelijoiden osuus (Tertiary Enrollment Ratio %) perustuu korkeakoulutukseen osallistuvien prosenttiosuuteen relevantissa ik\u00e4luokassa. Lukutaitoisten osuus aikuisv\u00e4est\u00f6st\u00e4 (Adult Literacy Rate %) lasketaan prosentteina aikuisv\u00e4est\u00f6st\u00e4. IR on n\u00e4iden kahden keskiarvo.\r\n\r\nPerhetilojen osuus (Family Farms, FF %) tarkoittaa perhetilojen yhteenlaskettua pinta-alaa koko viljelypinta-alasta tai maatilojen kokonaisalasta prosentteina. Agraariv\u00e4est\u00f6n osuus vuosilta 2000-2005 on muuttujassa AP. DD saadaan, kun lasketaan yhteen k\u00f6yhyysrajan alla el\u00e4v\u00e4t (%) ja rikkaimman 10 % osuus koko v\u00e4est\u00f6n tuloista tai kulutuksesta v\u00e4hennettyn\u00e4 10 prosenttiyksikk\u00f6\u00e4, ja v\u00e4hennet\u00e4\u00e4n saatu summa sadasta. Joissain tapauksissa saatua prosenttilukua on v\u00e4hennetty tai kasvatettu syist\u00e4, jotka on esitelty tarkemmin Vanhasen teoksessa The Limits of Democratization. ER lasketaan kaavalla ER=(FF * AP) + (DD * NAP), miss\u00e4 NAP=100-AP. Viimeinen muuttuja, IPR (The Index of Power Resources), saadaan jakamalla IR:n ja ER:n tulo sadalla."
-    ],
-    "oai_identifier": [
-        "0ae1612e-f1de-57e1-8596-5b2e8b26a95a"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "demokratia"
-        },
-        {
-            "name": "demokratisoituminen"
-        },
-        {
-            "name": "demokratisoituminen"
-        },
-        {
-            "name": "demokratisoituminen"
-        },
-        {
-            "name": "koulutus"
-        },
-        {
-            "name": "lukutaito"
-        },
-        {
-            "name": "lukutaito"
-        },
-        {
-            "name": "maatalousyhteiskunta"
-        },
-        {
-            "name": "resurssit"
-        },
-        {
-            "name": "taloudellinen kehitys"
-        },
-        {
-            "name": "talouden tila ja tunnusluvut"
-        },
-        {
-            "name": "valta"
-        }
-    ],
-    "title": [
-        "Valtaresurssit 2007",
-        "Index of Power Resources (IPR) 2007"
-    ],
-    "url": "http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20141222161020777763"
-}
\ No newline at end of file
diff --git a/oaitestdata/etsin-oai_dc/SET_1/json/0af0e594-2ac8-5422-840f-1295ca6cc247.json b/oaitestdata/etsin-oai_dc/SET_1/json/0af0e594-2ac8-5422-840f-1295ca6cc247.json
deleted file mode 100644
index 5abb0d81..00000000
--- a/oaitestdata/etsin-oai_dc/SET_1/json/0af0e594-2ac8-5422-840f-1295ca6cc247.json
+++ /dev/null
@@ -1,88 +0,0 @@
-{
-    "Contact": [
-        "Yhteiskuntatieteellinen tietoarkisto"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://etsin.avointiede.fi/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=0af0e594-2ac8-5422-840f-1295ca6cc247",
-    "PublicationTimestamp": "2016-03-10T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Yhteiskuntatieteellinen tietoarkisto"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Other (Not Open)"
-    ],
-    "SpatialCoverage": [
-        "Suomi",
-        "2005/2005"
-    ],
-    "TemporalCoverage": " period : ( None - 2005-07-01T11:59:59Z ) ",
-    "author": [
-        "Kunnallisalan kehitt\u00e4miss\u00e4\u00e4ti\u00f6"
-    ],
-    "fulltext": "urn:nbn:fi:csc-kata20141222160517169847;2016-03-10T09:18:41Z;01905-2571-tampereen-yliopisto-yhteiskuntatieteellinen-tietoarkisto;Kunnallisalan ilmapuntari 2005: kuntalaiset;Finnish Local Government Barometer 2005: Inhabitants;Kunnallisalan kehitt\u00e4miss\u00e4\u00e4ti\u00f6;julkinen hallinto;julkiset palvelut;kehitys;kunnat;kuntalaiset;kuntaliitokset;poliittiset organisaatiot;puolueet;taloudellinen tila;taloudellinen vastuu;valtiovalta;yhdist\u00e4minen;yhteiskuntatieteet;yksityist\u00e4minen;Vuoden 2005 ilmapuntarin erityisteemana olivat kunta- ja palvelurakenneuudistukset. Vastaajalle esitettiin joukko kuntia koskevia v\u00e4itt\u00e4mi\u00e4 ja h\u00e4nt\u00e4 pyydettiin arvioimaan jokaista v\u00e4itt\u00e4m\u00e4\u00e4 sen mukaan, onko h\u00e4n samaa vai eri mielt\u00e4 v\u00e4itt\u00e4m\u00e4n kanssa. Seuraavaksi vastaajaa pyydettiin arvioimaan kunnallisten palveluiden kehityst\u00e4 omassa kunnassa. Kunta- ja palvelurakenneuudistukseen liittyen tiedusteltiin, mik\u00e4 alueellinen kokonaisuus on vastaajan mielest\u00e4 sopivin tarjoamaan kuntalaisille eri palveluja ja kenen tulisi k\u00e4yt\u00e4nn\u00f6ss\u00e4 tehd\u00e4 ja tuottaa palvelut. Kyselyss\u00e4 kartoitettiin my\u00f6s sit\u00e4, miss\u00e4 kaikissa palveluissa kansalaisten pit\u00e4isi ottaa enemm\u00e4n taloudellista tai toiminnallista vastuuta ja miss\u00e4 palveluissa p\u00e4\u00e4asiallinen toimenpidevastuu tulisi kuntien sijasta olla valtiolla. Vastaajalta tiedusteltiin my\u00f6s, mit\u00e4 keinoja h\u00e4n pit\u00e4\u00e4 hyv\u00e4ksytt\u00e4vin\u00e4 pyritt\u00e4ess\u00e4 parantamaan h\u00e4nen kotikuntansa taloutta. Kysyttiin my\u00f6s, paljonko vastaajan mielest\u00e4 kuntia pit\u00e4isi Suomessa olla. Seuraavaksi tiedusteltiin vastaajan suhtautumista kuntaliitoksiin yleens\u00e4 ja suhtautumista oman kunnan yhdist\u00e4miseen suuremmaksi kokonaisuudeksi naapurikunnan/kuntien kanssa. Vastaajalta kysyttiin viel\u00e4, mitk\u00e4 h\u00e4nen mielest\u00e4\u00e4n ovat hyvi\u00e4 perusteita kuntien lukum\u00e4\u00e4r\u00e4n v\u00e4hent\u00e4miseksi ja mitk\u00e4 hyvi\u00e4 perusteita kuntien lukum\u00e4\u00e4r\u00e4n v\u00e4hent\u00e4mist\u00e4 vastaan. Lopuksi tiedusteltiin, kuka vastaajan mielest\u00e4 tosiasiallisesti johtaa h\u00e4nen kotikuntaansa. Taustamuuttujina olivat muun muassa vastaajan sukupuoli, ik\u00e4, koulutus, ammattiryhm\u00e4, elinvaihe, asuinl\u00e4\u00e4ni ja talouden bruttotulot.;Yhteiskuntatieteellinen tietoarkisto;Yhteiskuntatieteellinen tietoarkisto;2016-03-10;dataset;FSD2236;urn:nbn:fi:fsd:T-FSD2236;urn:nbn:fi:csc-kata20141222160517169847;http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20141222160517169847;Suomi;2005/2005;Other (Not Open)",
-    "group": "etsin",
-    "groups": [
-        {
-            "name": "etsin"
-        }
-    ],
-    "name": "0af0e594-2ac8-5422-840f-1295ca6cc247",
-    "notes": [
-        "Vuoden 2005 ilmapuntarin erityisteemana olivat kunta- ja palvelurakenneuudistukset. Vastaajalle esitettiin joukko kuntia koskevia v\u00e4itt\u00e4mi\u00e4 ja h\u00e4nt\u00e4 pyydettiin arvioimaan jokaista v\u00e4itt\u00e4m\u00e4\u00e4 sen mukaan, onko h\u00e4n samaa vai eri mielt\u00e4 v\u00e4itt\u00e4m\u00e4n kanssa. Seuraavaksi vastaajaa pyydettiin arvioimaan kunnallisten palveluiden kehityst\u00e4 omassa kunnassa. Kunta- ja palvelurakenneuudistukseen liittyen tiedusteltiin, mik\u00e4 alueellinen kokonaisuus on vastaajan mielest\u00e4 sopivin tarjoamaan kuntalaisille eri palveluja ja kenen tulisi k\u00e4yt\u00e4nn\u00f6ss\u00e4 tehd\u00e4 ja tuottaa palvelut. Kyselyss\u00e4 kartoitettiin my\u00f6s sit\u00e4, miss\u00e4 kaikissa palveluissa kansalaisten pit\u00e4isi ottaa enemm\u00e4n taloudellista tai toiminnallista vastuuta ja miss\u00e4 palveluissa p\u00e4\u00e4asiallinen toimenpidevastuu tulisi kuntien sijasta olla valtiolla. Vastaajalta tiedusteltiin my\u00f6s, mit\u00e4 keinoja h\u00e4n pit\u00e4\u00e4 hyv\u00e4ksytt\u00e4vin\u00e4 pyritt\u00e4ess\u00e4 parantamaan h\u00e4nen kotikuntansa taloutta. Kysyttiin my\u00f6s, paljonko vastaajan mielest\u00e4 kuntia pit\u00e4isi Suomessa olla. Seuraavaksi tiedusteltiin vastaajan suhtautumista kuntaliitoksiin yleens\u00e4 ja suhtautumista oman kunnan yhdist\u00e4miseen suuremmaksi kokonaisuudeksi naapurikunnan/kuntien kanssa. Vastaajalta kysyttiin viel\u00e4, mitk\u00e4 h\u00e4nen mielest\u00e4\u00e4n ovat hyvi\u00e4 perusteita kuntien lukum\u00e4\u00e4r\u00e4n v\u00e4hent\u00e4miseksi ja mitk\u00e4 hyvi\u00e4 perusteita kuntien lukum\u00e4\u00e4r\u00e4n v\u00e4hent\u00e4mist\u00e4 vastaan. Lopuksi tiedusteltiin, kuka vastaajan mielest\u00e4 tosiasiallisesti johtaa h\u00e4nen kotikuntaansa. Taustamuuttujina olivat muun muassa vastaajan sukupuoli, ik\u00e4, koulutus, ammattiryhm\u00e4, elinvaihe, asuinl\u00e4\u00e4ni ja talouden bruttotulot."
-    ],
-    "oai_identifier": [
-        "0af0e594-2ac8-5422-840f-1295ca6cc247"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "julkinen hallinto"
-        },
-        {
-            "name": "julkiset palvelut"
-        },
-        {
-            "name": "kehitys"
-        },
-        {
-            "name": "kunnat"
-        },
-        {
-            "name": "kuntalaiset"
-        },
-        {
-            "name": "kuntaliitokset"
-        },
-        {
-            "name": "poliittiset organisaatiot"
-        },
-        {
-            "name": "puolueet"
-        },
-        {
-            "name": "taloudellinen tila"
-        },
-        {
-            "name": "taloudellinen vastuu"
-        },
-        {
-            "name": "valtiovalta"
-        },
-        {
-            "name": "valtiovalta"
-        }
-    ],
-    "title": [
-        "Kunnallisalan ilmapuntari 2005: kuntalaiset",
-        "Finnish Local Government Barometer 2005: Inhabitants"
-    ],
-    "url": "http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20141222160517169847"
-}
\ No newline at end of file
diff --git a/oaitestdata/etsin-oai_dc/SET_1/json/0af81d46-7341-5c9e-a56e-d9df530e3a1c.json b/oaitestdata/etsin-oai_dc/SET_1/json/0af81d46-7341-5c9e-a56e-d9df530e3a1c.json
deleted file mode 100644
index 63469c8e..00000000
--- a/oaitestdata/etsin-oai_dc/SET_1/json/0af81d46-7341-5c9e-a56e-d9df530e3a1c.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "atm-data@helsinki.fi"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://etsin.avointiede.fi/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=0af81d46-7341-5c9e-a56e-d9df530e3a1c",
-    "PublicationTimestamp": "2016-03-08T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "atm-data@helsinki.fi"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0"
-    ],
-    "SpatialCoverage": [
-        "DCMI-point: name=Hyyti\u00e4l\u00e4; east=24.294795; north=61.847463 elevation=179",
-        "2000-01-01T00:00:00Z/2000-12-31T23:59:59Z"
-    ],
-    "TempCoverageBegin": 92982427199,
-    "TempCoverageEnd": 63082281600,
-    "TemporalCoverage": " period : ( 2947-07-01T11:59:59Z - 2000-01-01T00:00:00Z ) ",
-    "TemporalCoverage:BeginDate": "2947-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2000-01-01T00:00:00Z",
-    "author": [
-        "Pasi Aalto"
-    ],
-    "fulltext": "urn:nbn:fi:csc-kata20160308110340318738;2016-03-08T09:03:40Z;university-of-helsinki-department-of-physics-division-of-atmospheric-sciences;Hyyti\u00e4l\u00e4 SMEAR II meteorology, gases and soil - Soil water content B1 - 2000;Pasi Aalto;http://www.yso.fi/onto/yso/p899;Title: Soil water content B1 \n\nDescription: Volumetric soil water content in B1 horizon (14-25 cm depth in the mineral soil), mean of five locations \n\nVariable: wsoil_B1 \n\nUnit: m\u00b3 m\u207b\u00b3 \n\nSource: Campbell TDR100 Time-Domain Reflectometer \n\nCategory: Soil \n\n;atm-data@helsinki.fi;2016-03-08;dataset;urn:nbn:fi:csc-ida-10x201703272015017309341v;urn:nbn:fi:csc-ida2014010803466v;urn:nbn:fi:csc-ida2014010803466s;urn:nbn:fi:csc-kata20160308110340318738;http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308110340318738;DCMI-point: name=Hyyti\u00e4l\u00e4; east=24.294795; north=61.847463 elevation=179;2000-01-01T00:00:00Z/2000-12-31T23:59:59Z;Creative Commons Attribution 4.0",
-    "group": "etsin",
-    "groups": [
-        {
-            "name": "etsin"
-        }
-    ],
-    "name": "0af81d46-7341-5c9e-a56e-d9df530e3a1c",
-    "notes": [
-        "Title: Soil water content B1 \n\nDescription: Volumetric soil water content in B1 horizon (14-25 cm depth in the mineral soil), mean of five locations \n\nVariable: wsoil_B1 \n\nUnit: m\u00b3 m\u207b\u00b3 \n\nSource: Campbell TDR100 Time-Domain Reflectometer \n\nCategory: Soil \n\n"
-    ],
-    "oai_identifier": [
-        "0af81d46-7341-5c9e-a56e-d9df530e3a1c"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "http www.yso.fi onto yso p"
-        }
-    ],
-    "title": [
-        "Hyyti\u00e4l\u00e4 SMEAR II meteorology, gases and soil - Soil water content B1 - 2000"
-    ],
-    "url": "http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20160308110340318738"
-}
\ No newline at end of file
diff --git a/oaitestdata/etsin-oai_dc/SET_1/json/0afd99ea-2d03-595f-be5a-d9b850ff3f81.json b/oaitestdata/etsin-oai_dc/SET_1/json/0afd99ea-2d03-595f-be5a-d9b850ff3f81.json
deleted file mode 100644
index 5b9006d6..00000000
--- a/oaitestdata/etsin-oai_dc/SET_1/json/0afd99ea-2d03-595f-be5a-d9b850ff3f81.json
+++ /dev/null
@@ -1,103 +0,0 @@
-{
-    "Contact": [
-        "Yhteiskuntatieteellinen tietoarkisto"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://etsin.avointiede.fi/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=0afd99ea-2d03-595f-be5a-d9b850ff3f81",
-    "PublicationTimestamp": "2016-03-10T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Yhteiskuntatieteellinen tietoarkisto"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Other (Not Open)"
-    ],
-    "SpatialCoverage": [
-        "Suomi",
-        "Helsinki",
-        "Jyv\u00e4skyl\u00e4",
-        "Tampere",
-        "Turku",
-        "2005/2005"
-    ],
-    "TemporalCoverage": [
-        "Suomi",
-        "Helsinki",
-        "Jyv\u00e4skyl\u00e4",
-        "Tampere",
-        "Turku",
-        "2005/2005"
-    ],
-    "author": [
-        "Jyv\u00e4skyl\u00e4n yliopiston ylioppilaskunta",
-        "Tampereen yliopiston ylioppilaskunta",
-        "Helsingin yliopiston ylioppilaskunta",
-        "Teknillisen Korkeakoulun Ylioppilaskunta",
-        "Turun yliopiston ylioppilaskunta"
-    ],
-    "fulltext": "urn:nbn:fi:csc-kata20141222160201969642;2016-03-10T09:15:27Z;01905-2571-tampereen-yliopisto-yhteiskuntatieteellinen-tietoarkisto;Ulkomaalaiset perustutkinto-opiskelijat 2005: osa-aineisto;Survey of Foreign Students in Five Finnish Universities 2005: Partial Data;Helsingin yliopiston ylioppilaskunta;Jyv\u00e4skyl\u00e4n yliopiston ylioppilaskunta;Tampereen yliopiston ylioppilaskunta;Teknillisen Korkeakoulun Ylioppilaskunta;Turun yliopiston ylioppilaskunta;ansioty\u00f6;asenteet;ennakkoluulot;integraatio;korkeakouluopetus;korkeakouluopiskelu;korkeakoulut;lukukausimaksut;mielipiteet;muukalaisviha;opinto-ohjaus;opintoapurahat;opintotuki;opiskelu ulkomailla;palvelut;sosiaalinen k\u00e4ytt\u00e4ytyminen ja asenteet;suomalaisuus;syrjint\u00e4;toimeentulo;toisen ja korkea-asteen koulutus;ty\u00f6nhaku;ulkomaalaiset;v\u00e4hemmist\u00f6t;yhteiskunta;yhteiskuntatieteet;yliopistot;Aineisto on osa lomakeaineistoa, jossa on kysytty ulkomaalaisten perustutkinto-opiskelijoiden maahanmuuton syit\u00e4, sopeutumista suomalaiseen yhteiskuntaan ja yliopistomaailmaan sek\u00e4 toimeentuloa ja tulevaisuudensuunnitelmia. Aineisto on muodostettu kyselylomakkeen viimeisen kysymyksen avovastauksista, joissa vastaajat kertoivat omin sanoin kokemuksistaan ja k\u00e4sityksist\u00e4\u00e4n, jotka ovat muodostuneet heid\u00e4n opiskellessaan ja asuessaan Suomessa. Kysymysteksti on ollut \"What else do you wish to say as a foreign student?\". Kustakin vastaajasta kerrotaan taustatietona ik\u00e4, sukupuoli, kansallisuus, tiedekunta ja Suomessa olo vuosina.\r\n\r\nAineisto koostuu 288 ulkomaalaisen opiskelijan kommenteista, joissa k\u00e4sitell\u00e4\u00e4n muiden muassa n\u00e4kemyksi\u00e4 Suomesta, suomalaisuudesta ja suomalaisten suhtautumisesta ulkomaalaisiin. Vastaajilla on kokemuksia suomalaisten peloista ja ennakkoluuloista, mutta osa kertoo my\u00f6s vuolaasti kokemastaan avuliaisuudesta ja vieraanvaraisuudesta. Erityisen paljon vastaajat kertovat yliopisto-opiskelun hyvist\u00e4 ja huonoista puolista. Paljon kerrotaan my\u00f6s mielipiteit\u00e4 suunnitelmista kohdentaa lukukausimaksuja erityisesti ulkomaalaisille opiskelijoille. Ty\u00f6nhakua ja suomalaisten ty\u00f6markkinoiden toimintaa kommentoidaan my\u00f6s.\r\n\r\nKirjoitukset vaihtelevat pituudeltaan muutamasta rivist\u00e4 muutamaan kymmeneen riviin. Aineisto soveltuu erityisesti kvalitatiivisten analyysimenetelmien opetuksen englanninkieliseksi harjoitusaineistoksi. Aineisto toimitetaan sek\u00e4 excel- ett\u00e4 teksti (rtf) -tiedostona. Excel-taulukon avulla aineistoa voi jakaa tarkoituksenmukaisiin kokonaisuuksiin k\u00e4ytt\u00e4en apuna vaikkapa vastaajien taustatietoja (ik\u00e4, sukupuoli, kansallisuus, tiedekunta ja Suomessa olo vuosina).;Yhteiskuntatieteellinen tietoarkisto;Yhteiskuntatieteellinen tietoarkisto;K\u00e4rki, Johanna;2016-03-10;dataset;FSD2139;urn:nbn:fi:fsd:T-FSD2139;urn:nbn:fi:csc-kata20141222160201969642;http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20141222160201969642;Suomi;Helsinki;Jyv\u00e4skyl\u00e4;Tampere;Turku;2005/2005;Other (Not Open)",
-    "group": "etsin",
-    "groups": [
-        {
-            "name": "etsin"
-        }
-    ],
-    "name": "0afd99ea-2d03-595f-be5a-d9b850ff3f81",
-    "notes": [
-        "Aineisto on osa lomakeaineistoa, jossa on kysytty ulkomaalaisten perustutkinto-opiskelijoiden maahanmuuton syit\u00e4, sopeutumista suomalaiseen yhteiskuntaan ja yliopistomaailmaan sek\u00e4 toimeentuloa ja tulevaisuudensuunnitelmia. Aineisto on muodostettu kyselylomakkeen viimeisen kysymyksen avovastauksista, joissa vastaajat kertoivat omin sanoin kokemuksistaan ja k\u00e4sityksist\u00e4\u00e4n, jotka ovat muodostuneet heid\u00e4n opiskellessaan ja asuessaan Suomessa. Kysymysteksti on ollut \"What else do you wish to say as a foreign student?\". Kustakin vastaajasta kerrotaan taustatietona ik\u00e4, sukupuoli, kansallisuus, tiedekunta ja Suomessa olo vuosina.\r\n\r\nAineisto koostuu 288 ulkomaalaisen opiskelijan kommenteista, joissa k\u00e4sitell\u00e4\u00e4n muiden muassa n\u00e4kemyksi\u00e4 Suomesta, suomalaisuudesta ja suomalaisten suhtautumisesta ulkomaalaisiin. Vastaajilla on kokemuksia suomalaisten peloista ja ennakkoluuloista, mutta osa kertoo my\u00f6s vuolaasti kokemastaan avuliaisuudesta ja vieraanvaraisuudesta. Erityisen paljon vastaajat kertovat yliopisto-opiskelun hyvist\u00e4 ja huonoista puolista. Paljon kerrotaan my\u00f6s mielipiteit\u00e4 suunnitelmista kohdentaa lukukausimaksuja erityisesti ulkomaalaisille opiskelijoille. Ty\u00f6nhakua ja suomalaisten ty\u00f6markkinoiden toimintaa kommentoidaan my\u00f6s.\r\n\r\nKirjoitukset vaihtelevat pituudeltaan muutamasta rivist\u00e4 muutamaan kymmeneen riviin. Aineisto soveltuu erityisesti kvalitatiivisten analyysimenetelmien opetuksen englanninkieliseksi harjoitusaineistoksi. Aineisto toimitetaan sek\u00e4 excel- ett\u00e4 teksti (rtf) -tiedostona. Excel-taulukon avulla aineistoa voi jakaa tarkoituksenmukaisiin kokonaisuuksiin k\u00e4ytt\u00e4en apuna vaikkapa vastaajien taustatietoja (ik\u00e4, sukupuoli, kansallisuus, tiedekunta ja Suomessa olo vuosina)."
-    ],
-    "oai_identifier": [
-        "0afd99ea-2d03-595f-be5a-d9b850ff3f81"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "asenteet"
-        },
-        {
-            "name": "ennakkoluulot"
-        },
-        {
-            "name": "integraatio"
-        },
-        {
-            "name": "korkeakouluopetus"
-        },
-        {
-            "name": "korkeakouluopiskelu"
-        },
-        {
-            "name": "korkeakoulut"
-        },
-        {
-            "name": "lukukausimaksut"
-        },
-        {
-            "name": "mielipiteet"
-        },
-        {
-            "name": "muukalaisviha"
-        },
-        {
-            "name": "opinto-ohjaus"
-        },
-        {
-            "name": "opintoapurahat"
-        },
-        {
-            "name": "opintotuki"
-        }
-    ],
-    "title": [
-        "Ulkomaalaiset perustutkinto-opiskelijat 2005: osa-aineisto",
-        "Survey of Foreign Students in Five Finnish Universities 2005: Partial Data"
-    ],
-    "url": "http://etsin.avointiede.fi/dataset/urn-nbn-fi-csc-kata20141222160201969642"
-}
\ No newline at end of file
diff --git a/oaitestdata/euroargo-iso19139/euro-argo_1/json/12315a55-94af-5cf2-96a9-95102e7ddee4.json b/oaitestdata/euroargo-iso19139/euro-argo_1/json/12315a55-94af-5cf2-96a9-95102e7ddee4.json
deleted file mode 100644
index 1c7baf0e..00000000
--- a/oaitestdata/euroargo-iso19139/euro-argo_1/json/12315a55-94af-5cf2-96a9-95102e7ddee4.json
+++ /dev/null
@@ -1,92 +0,0 @@
-{
-    "Contact": [
-        "Ifremer"
-    ],
-    "Contributor": "Euro-Argo",
-    "DOI": "http://dx.doi.org/10.17882/42182",
-    "DiscHierarchy": [
-        "4.4.5.2",
-        "Geospheric Science",
-        "Geography"
-    ],
-    "Discipline": "Biogeochemistry;Biology",
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/eng/csw-ATLANTOS?verb=GetRecord&metadataPrefix=iso19139&identifier=12315a55-94af-5cf2-96a9-95102e7ddee4",
-    "OpenAccess": [
-        "No limitations on public access"
-    ],
-    "PublicationTimestamp": "2000-09-12T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "Publisher": [
-        "Seanoe"
-    ],
-    "Rights": [
-        "A user should acknowledge use of Argo data in all publications and products where such data are used, preferably with the following standard sentence:\"These data were collected and made freely available by the international Argo project and the national programs that contribute to it.\""
-    ],
-    "SpatialCoverage": "(90S-90N,180W-180E)",
-    "TempCoverageBegin": 62940193199,
-    "TempCoverageEnd": 62940193199,
-    "TemporalCoverage": " point in time : 1995-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1995-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1995-07-01T11:59:59Z",
-    "fulltext": "3df904de-e47d-4bf9-85a0-7c0942aff8b6;Ifremer;Ifremer;Ifremer;codac@ifremer.fr;codac@ifremer.fr;codac@ifremer.fr;2018-06-06T10:07:28;ISO 19115:2003/19139 - SEXTANT;1.0;1000000000;WGS 84 (EPSG:4326);WGS 84 (EPSG:4326);EPSG;7.9;Argo float data and metadata from Global Data Assembly Centre (Argo GDAC);Argo float data and metadata from Global Data Assembly Centre (Argo GDAC);Argo : Donn\u00e9es et m\u00e9tadonn\u00e9es du Global Data Assembly Centre (Argo GDAC);2000-09-12;1282383d-9b35-4eaa-a9d6-4b0c24c0cfc9;Argo is a global array of 3,000 free-drifting profiling floats that measures the temperature and salinity of the upper 2000 m of the ocean.  This allows, for the first time, continuous monitoring of the temperature, salinity, and velocity of the upper ocean, with all data being relayed and made publicly available within hours after collection.\n\nThe array provides 100,000 temperature/salinity profiles and velocity measurements per year distributed over the global oceans at an average of 3-degree spacing. Some floats provide additional bio-geo parameters such as oxygen or chlorophyll.\n\nAll data collected by Argo floats are publically available in near real-time via the Global Data Assembly Centers (GDACs) in Brest (France) and Monterey (California) after an automated quality control (QC), and in scientifically quality controlled form, delayed mode data, via the GDACs within six months of collection.;Argo is a global array of 3,000 free-drifting profiling floats that measures the temperature and salinity of the upper 2000 m of the ocean.  This allows, for the first time, continuous monitoring of the temperature, salinity, and velocity of the upper ocean, with all data being relayed and made publicly available within hours after collection.\n\nThe array provides 100,000 temperature/salinity profiles and velocity measurements per year distributed over the global oceans at an average of 3-degree spacing. Some floats provide additional bio-geo parameters such as oxygen or chlorophyll.\n\nAll data collected by Argo floats are publically available in near real-time via the Global Data Assembly Centers (GDACs) in Brest (France) and Monterey (California) after an automated quality control (QC), and in scientifically quality controlled form, delayed mode data, via the GDACs within six months of collection.;Argo est un ensemble mondial de 3 000 flotteurs \u00e0 profil d\u00e9rivant libre qui mesurent la temp\u00e9rature et la salinit\u00e9 des 2000 premier m de la colonne d'eau. Cela permet, pour la premi\u00e8re fois, une surveillance continue de la temp\u00e9rature, de la salinit\u00e9 et de la vitesse des eaux sup\u00e9rieures, toutes les donn\u00e9es \u00e9tant relay\u00e9es et rendues publiques dans les heures qui suivent la collecte.\n\nLe tableau fournit 100 000 profils de temp\u00e9rature / salinit\u00e9 et des mesures de vitesse par an r\u00e9parties sur les oc\u00e9ans globaux \u00e0 un espacement moyen de 3 degr\u00e9s. Certains flotteurs fournissent des param\u00e8tres bio-g\u00e9ochimiques suppl\u00e9mentaires tels que l'oxyg\u00e8ne ou la chlorophylle. \n\nToutes les donn\u00e9es recueillies par les flotteurs Argo sont publiquement disponibles en temps quasi r\u00e9el via Global Data Assembly Centers (GDAC) \u00e0 Brest (France) et \u00e0 Monterey (Californie) apr\u00e8s un contr\u00f4le de qualit\u00e9 automatis\u00e9 (QC) et sous une forme scientifiquement de contr\u00f4le qualit\u00e9, temps diff\u00e9r\u00e9e, via les GDAC dans les six mois suivant la collecte.;Ifremer;Ifremer;Ifremer;Argo;Argo;Argo;codac@ifremer.fr;codac@ifremer.fr;codac@ifremer.fr;Ifremer;Ifremer;Ifremer;codac@ifremer.fr;codac@ifremer.fr;codac@ifremer.fr;https://sextant.ifremer.fr/geonetwork/srv/api/records/3df904de-e47d-4bf9-85a0-7c0942aff8b6/attachments/argo-float.jpg;float;float;Argo;Argo;global ocean observing system;global ocean observing system;ocean circulation;ocean circulation;in-situ;in-situ;ocean pressure;ocean pressure;sea water salinity;sea water salinity;sea water temperature;sea water temperature;multi-year;multi-year;weather climate and seasonal observation;weather climate and seasonal observation;global-ocean;global-ocean;Environmental monitoring facilities;Installations de suivi environnemental;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;GEMET - INSPIRE themes, version 1.0;2009-09-22;geonetwork.thesaurus.external.theme.httpinspireeceuropaeutheme-theme;CDS-IS-CORIOLIS;CDS-IS-CORIOLIS;CDS-IS-CORIOLIS;Centre de donn\u00e9es - ODATIS;Centre de donn\u00e9es - ODATIS;2017-10-04;geonetwork.thesaurus.local.theme.odatis_centre_donnees;/Marine Biogeochemistry/Nutrients;/Biog\u00e9ochimie marine/Nutriments (sels nutritifs);/Marine Biogeochemistry/Nutrients;/Marine Biogeochemistry/Dissolved oxygen;/Biog\u00e9ochimie marine/Oxyg\u00e8ne dissous;/Marine Biogeochemistry/Dissolved oxygen;/Marine Biology/Fluorescence - Chlorophyll a;/Biologie marine/Fluorescence - Chlorophylle;/Marine Biology/Fluorescence - Chlorophyll a;/Physical Oceanography/Optical parameters;/Physique de l'Oc\u00e9an/Param\u00e8tres optiques;/Physical Oceanography/Optical parameters;/Physical Oceanography/Salinity;/Physique de l'Oc\u00e9an/Salinit\u00e9;/Physical Oceanography/Salinity;/Marine Biogeochemistry/CDOM;/Biog\u00e9ochimie marine/CDOM;/Marine Biogeochemistry/CDOM;/Physical Oceanography/Temperature;/Physique de l'Oc\u00e9an/Temp\u00e9rature;/Physical Oceanography/Temperature;/Physical Oceanography/Turbidity;/Physique de l'Oc\u00e9an/Turbidit\u00e9;/Physical Oceanography/Turbidity;Variables Odatis;Variables Odatis;2017-10-17;geonetwork.thesaurus.local.theme.odatis_variables;Type de jeux de donn\u00e9e - ODATIS;Type de jeux de donn\u00e9e - ODATIS;2017-09-07;geonetwork.thesaurus.local.theme.type_jeux_donnee;Operational oceanography;Oc\u00e9anographie op\u00e9rationnelle;Operational oceanography;Observation system for research;Dispositifs d\u2019observation pour la recherche;Observation system for research;Th\u00e8matiques - ODATIS;Th\u00e8matiques - ODATIS;2017-10-02;geonetwork.thesaurus.local.theme.odatis_thematiques;Networks;Networks;Networks;AtlantOS Element;AtlantOS Element;2017-11-08;geonetwork.thesaurus.local.theme.atlantos_element;Nutrients;Nutrients;Currents;Currents;Chlorophyll-a and fluorescence;Chlorophyll-a and fluorescence;Salinity;Salinity;Temperature;Temperature;Oxygen;Oxygen;Bottom depth;Bottom depth;AtlantOS Essential Variables;AtlantOS Essential Variables;2017-02-16;geonetwork.thesaurus.external.parameter.NVS.A05;A user should acknowledge use of Argo data in all publications and products where such data are used, preferably with the following standard sentence:\"These data were collected and made freely available by the international Argo project and the national programs that contribute to it.\";A user should acknowledge use of Argo data in all publications and products where such data are used, preferably with the following standard sentence:\"These data were collected and made freely available by the international Argo project and the national programs that contribute to it.\";A user should acknowledge use of Argo data in all publications and products where such data are used, preferably with the following standard sentence:\"These data were collected and made freely available by the international Argo project and the national programs that contribute to it.\";No limitations on public access;No limitations on public access;No limitations on public access;A user of Argo data is expected to read and understand this manual and the documentation about the data contained in the \"attributes\" of the NetCDF data files, as these contain essential information about data quality and accuracy.;A user of Argo data is expected to read and understand this manual and the documentation about the data contained in the \"attributes\" of the NetCDF data files, as these contain essential information about data quality and accuracy.;1000000;oceans;-180;180;-90;90;1995;http://www.coriolis.eu.org/;WWW:LINK;Coriolis Web Site;Coriolis Web Site;http://doi.org/10.17882/42182;WWW:LINK-1.0-http--metadata-URL;Argo GDAC snapshots access;Argo GDAC snapshots access;Argo GDAC snapshots access;Argo GDAC snapshots access;http://www.jcommops.org/board?t=Argo&modules=%5B%7B\"id\":48%7D%5D;WWW:LINK;Web app avec carte interactive Flotteurs Argo op\u00e9rationnels;Web app avec carte interactive Flotteurs Argo op\u00e9rationnels;JCOMMOPS: Web app tous les flotteurs op\u00e9rationnels;JCOMMOPS: Web app tous les flotteurs op\u00e9rationnels;http://www.jcommops.org/board?t=Argo&qparams=%7B\"lastLocOnly\"%3A\"on\"%2C\"allNotGdacs\"%3A\"1\"%2C\"networks\"%3A\"1\"%2C\"status\"%3A\"6\"%7D&modules=%5B%7B\"id\":48%7D%5D;WWW:LINK;Web app avec carte interactive Flotteurs BGC-Argo op\u00e9rationnels;Web app avec carte interactive Flotteurs BGC-Argo op\u00e9rationnels;JCOMMOPS: Web app tous les flotteurs BGC-Argo op\u00e9rationnels;JCOMMOPS: Web app tous les flotteurs BGC-Argo op\u00e9rationnels;http://www.jcommops.org/maps/interactive_new/?theme=Argo;WWW:LINK;JCOMMOPS: Argo Op\u00e9rationnel;JCOMMOPS: Argo Op\u00e9rationnel;http://www.jcommops.org/maps/interactive_new/?theme=Argo&ptfStatuses=%5B6%5D&ptfNetworks=%5B%22Argo%20BioGeoChemical%22%5D;WWW:LINK;Carte interactive seule (tout BGC-Argo op\u00e9rationnel);Carte interactive seule (tout BGC-Argo op\u00e9rationnel);JCOMMOPS: BGC-Argo op\u00e9rationnel;JCOMMOPS: BGC-Argo op\u00e9rationnel;http://map.argo-france.fr/;WWW:LINK;Carte Argo France;Carte Argo France;ftp://ftp.ifremer.fr/ifremer/argo/;WWW:DOWNLOAD-1.0-link--download;FTP ARGO;FTP ARGO;FTP ARGO;FTP ARGO;http://gis.jcommops.org/arcgis/services/Argo/ARGOLocations/MapServer/WFSServer?;OGC:WFS;Argo_ARGOLocations:Latest_Locations;Argo_ARGOLocations:Latest_Locations;Argo Latest Locations;Argo Latest Locations;Inspire specifications;Inspire specifications;2012-01-16;Non \u00e9valu\u00e9;Non \u00e9valu\u00e9;false;http://www.argodatamgt.org/Documentation;http://www.argodatamgt.org/Documentation;http://www.argodatamgt.org/Documentation",
-    "group": "euroargo",
-    "groups": [
-        {
-            "name": "euroargo"
-        }
-    ],
-    "name": "12315a55-94af-5cf2-96a9-95102e7ddee4",
-    "notes": [
-        "Argo is a global array of 3,000 free-drifting profiling floats that measures the temperature and salinity of the upper 2000 m of the ocean.  This allows, for the first time, continuous monitoring of the temperature, salinity, and velocity of the upper ocean, with all data being relayed and made publicly available within hours after collection.\n\nThe array provides 100,000 temperature/salinity profiles and velocity measurements per year distributed over the global oceans at an average of 3-degree spacing. Some floats provide additional bio-geo parameters such as oxygen or chlorophyll.\n\nAll data collected by Argo floats are publically available in near real-time via the Global Data Assembly Centers (GDACs) in Brest (France) and Monterey (California) after an automated quality control (QC), and in scientifically quality controlled form, delayed mode data, via the GDACs within six months of collection."
-    ],
-    "oai_identifier": [
-        "12315a55-94af-5cf2-96a9-95102e7ddee4"
-    ],
-    "oai_set": "euro-argo",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-180,-90],[-180,90],[180,90],[180,-90],[-180,-90]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "float"
-        },
-        {
-            "name": "Argo"
-        },
-        {
-            "name": "global ocean observing system"
-        },
-        {
-            "name": "ocean circulation"
-        },
-        {
-            "name": "in-situ"
-        },
-        {
-            "name": "ocean pressure"
-        },
-        {
-            "name": "sea water salinity"
-        },
-        {
-            "name": "sea water temperature"
-        },
-        {
-            "name": "multi-year"
-        },
-        {
-            "name": "weather climate seasonal observation"
-        },
-        {
-            "name": "global-ocean"
-        },
-        {
-            "name": "Environmental monitoring facilities"
-        }
-    ],
-    "title": [
-        "Argo float data and metadata from Global Data Assembly Centre (Argo GDAC)"
-    ],
-    "url": "http://gis.jcommops.org/arcgis/services/Argo/ARGOLocations/MapServer/WFSServer?"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/0b5abb28-2672-5670-b5c4-fa69aca3cce1.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/0b5abb28-2672-5670-b5c4-fa69aca3cce1.json
deleted file mode 100644
index f6b09445..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/0b5abb28-2672-5670-b5c4-fa69aca3cce1.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6403",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6403"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6403;2018-05-23T09:53:50Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2018.006;Reinhardt-Imjela, Christian;Christian;Reinhardt-Imjela;0000-0002-1951-2503;Freie Universitaet Berlin, Department of Earth Sciences, Applied Geography, Environmental Hydrology and Resource Management, Berlin, Germany;Schulte, Achim;Achim;Schulte;0000-0003-0397-4225;Freie Universitaet Berlin, Department of Earth Sciences, Applied Geography, Environmental Hydrology and Resource Management, Berlin, Germany;Rasche, Daniel;Daniel;Rasche;Freie Universitaet Berlin, Department of Earth Sciences, Applied Geography, Environmental Hydrology and Resource Management, Berlin, Germany;Vormeier, Philipp;Philipp;Vormeier;Freie Universitaet Berlin, Department of Earth Sciences, Applied Geography, Environmental Hydrology and Resource Management, Berlin, Germany;Isau, Oliver;Oliver;Isau;Freie Universitaet Berlin | Department of Earth Sciences | Applied Geography, Environmental Hydrology and Resource Management;A comparative data set of daily precipitation measured with a Davis Vantage Pro tipping bucket and a Hellmann rain collector \u2013 season 2017;GFZ Data Services;2018;Davis Vantage Pro;precipitation;measurement error;Reinhardt-Imjela, Christian;Christian;Reinhardt-Imjela;0000-0002-1951-2503;Freie Universitaet Berlin, Department of Earth Sciences, Applied Geography, Environmental Hydrology and Resource Management, Berlin, Germany;Reinhardt-Imjela, Christian;Christian;Reinhardt-Imjela;0000-0002-1951-2503;Freie Universitaet Berlin, Department of Earth Sciences, Applied Geography, Environmental Hydrology and Resource Management, Berlin, Germany;Reinhardt-Imjela, Christian;Christian;Reinhardt-Imjela;0000-0002-1951-2503;Freie Universitaet Berlin, Department of Earth Sciences, Applied Geography, Environmental Hydrology and Resource Management, Berlin, Germany;Schulte, Achim;Achim;Schulte;0000-0003-0397-4225;Freie Universitaet Berlin, Department of Earth Sciences, Applied Geography, Environmental Hydrology and Resource Management, Berlin, Germany;Rasche, Daniel;Daniel;Rasche;Freie Universitaet Berlin, Department of Earth Sciences, Applied Geography, Environmental Hydrology and Resource Management, Berlin, Germany;Vormeier, Philipp;Philipp;Vormeier;Freie Universitaet Berlin, Department of Earth Sciences, Applied Geography, Environmental Hydrology and Resource Management, Berlin, Germany;Isau, Oliver;Oliver;Isau;Freie Universitaet Berlin | Department of Earth Sciences | Applied Geography, Environmental Hydrology and Resource Management;2018-02-12;2017-01-01/2017-12-31;en;10.1353/lag.2013.0042;3869 Bytes;1 Files;text/plain;1.0;CC BY 4.0;Davis Vantage Pro Rainfall Collectors are used in a wide range of projects worldwide even in remote and inaccessible regions (cf. Krois et al. 2013). However in remote areas or if a large number of collectors is used parallel, measurement errors for each device can hardly be quantified. To provide a dataset that allows an estimation of errors that occur in observations with Davis Vantage Pro collectors, comparative rainfall data were obtained at the hydro-meteorological monitoring station in Berlin-Lankwitz. The station is located at Geo Campus Lankwitz (Freie Universit\u00e4t Berlin, Department of Earth Sciences) at an elevation of 45 m a.s.l. and consists of a 7.5 x 7.5 m wide fenced measuring field covered by short grass which is cut in weekly intervals. The field is equipped with a range of rainfall measuring devices including a Hellmann rain gauge and a Vantage Pro collector. A comparison of both time series allows a general estimation of potential measuring errors of the Davis Vantage Pro data, assuming that the Hellmann data are less affected by random measuring errors. The data are intended to support the interpretation of rainfall records of Davis Vantage Pro stations in studies without control instruments and to enable users to apply their own statistical analysis to the data. However the dataset does not contain a continuous weather record. The detailed time series are published separately.;13.3581;52.4269",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "0b5abb28-2672-5670-b5c4-fa69aca3cce1",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6403"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/0d676849-51fc-5ba5-aa75-c51c18f3fa92.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/0d676849-51fc-5ba5-aa75-c51c18f3fa92.json
deleted file mode 100644
index 032fd193..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/0d676849-51fc-5ba5-aa75-c51c18f3fa92.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6584",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6584"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6584;2018-12-10T15:08:13Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2018.016;Siegert, Susann;Susann;Siegert;0000-0002-4157-863X;Museum f\u00fcr Naturkunde - Leibniz Institute for Evolution and Biodiversity Science, Berlin, Germany;Hecht, Lutz;Lutz;Hecht;0000-0001-8904-0217;Museum f\u00fcr Naturkunde - Leibniz Institute for Evolution and Biodiversity Science, Berlin, Germany;Geochemical data of impactites of the Ries impact structure, Germany;GFZ Data Services;2018;Ries impact crater;geochemistry;melt-brearing impact breccia;suevite;impact melt breccia;impact melt bomb;electron microprobe analysis;laser ablation ICP-MS;X-ray fluorescence;ICP-MS;ICP-AES;Siegert, Susann;Susann;Siegert;0000-0002-4157-863X;Museum f\u00fcr Naturkunde - Leibniz Institute for Evolution and Biodiversity Science, Berlin, Germany;Hecht, Lutz;Lutz;Hecht;0000-0001-8904-0217;Museum f\u00fcr Naturkunde - Leibniz Institute for Evolution and Biodiversity Science, Berlin, Germany;en;10.1111/maps.13210;10.1046/j.1365-2494.1998.53202081.x-i1;10.1111/j.1751-908X.1980.tb00273.x;10.1111/j.1751-908X.2011.00120.x;10.1111/maps.12087;10.1111/maps.12086;6313516 Bytes;3 Files;application/x-zip-compressed;application/pdf;application/vnd.openxmlformats-officedocument.spreadsheetml.sheet;CC BY 4.0;The Ries impact structure in Southern Germany is one of the best-preserved impact structures on Earth. Melt-bearing impact breccia appears in a variety of well accessible exposures around the inner ring up to 10 km beyond the crater rim (so-called outer suevite) overlying a ballistically ejected lithic breccia (so-called \u2018Bunte Breccia\u2019). Occasionally individual melt bombs occur in the \u2018Bunte Breccia\u2019. Coherent impact melt rock outside the inner crater is located in the eastern megablock zone (St\u00f6ffler et al., 2013 and references therein).;10.557469238760063;48.88667960100579",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "0d676849-51fc-5ba5-aa75-c51c18f3fa92",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6584"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/0f0d31cb-e224-57b0-a78e-32fcdd05e1e0.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/0f0d31cb-e224-57b0-a78e-32fcdd05e1e0.json
deleted file mode 100644
index f53c4e73..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/0f0d31cb-e224-57b0-a78e-32fcdd05e1e0.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6592",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6592"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6592;2018-12-05T19:47:39Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2018.024;Wizemann, Hans-Dieter;Hans-Dieter;Wizemann;Institut f\u00fcr Physik und Meteorologie, Universit\u00e4t Hohenheim, 70599 Stuttgart, Germany;University Hohenheim, Stuttgart, Germany;Trebs, Ivonne;Ivonne;Trebs;Department Environmental Research and Innovation, Luxembourg Institute of Science and Technology (LIST), Belvaux, L-4422, Grand-duchy of Luxembourg;Luxembourg Institute of Science and Technology (LIST), Belvaux, Grand-duchy of Luxembourg;Wulfmeyer, Volker;Volker;Wulfmeyer;0000-0003-4882-2524;Institut f\u00fcr Physik und Meteorologie, Universit\u00e4t Hohenheim, 70599 Stuttgart, Germany;University Hohenheim, Stuttgart, Germany;Surface energy balance observations at a grassland site in Luxembourg;GFZ Data Services;2018;Land surface heat fluxes;Eddy covariance;Surface energy balance observations;Catchments As Organized Systems;CAOS;EARTH SCIENCE > BIOSPHERE > TERRESTRIAL ECOSYSTEMS > GRASSLANDS;EARTH SCIENCE > BIOSPHERE > TERRESTRIAL ECOSYSTEMS > GRASSLANDS;EARTH SCIENCE > ATMOSPHERE > ATMOSPHERIC RADIATION > OUTGOING LONGWAVE RADIATION;EARTH SCIENCE > ATMOSPHERE > ATMOSPHERIC RADIATION > INCOMING SOLAR RADIATION;EARTH SCIENCE > ATMOSPHERE > ATMOSPHERIC RADIATION > LONGWAVE RADIATION;EARTH SCIENCE > ATMOSPHERE > ATMOSPHERIC RADIATION > INCOMING SOLAR RADIATION;EARTH SCIENCE > ATMOSPHERE > ATMOSPHERIC WATER VAPOR > EVAPOTRANSPIRATION;EARTH SCIENCE > ATMOSPHERE > ATMOSPHERIC RADIATION > HEAT FLUX;research > scientific research > meteorological research;In Situ/Laboratory Instruments > Current/Wind Meters > EDDY CORRELATION DEVICES;Wizemann, Hans-Dieter;Hans-Dieter;Wizemann;Institut f\u00fcr Physik und Meteorologie, Universit\u00e4t Hohenheim, 70599 Stuttgart, Germany;University Hohenheim, Stuttgart, Germany;Trebs, Ivonne;Ivonne;Trebs;Department Environmental Research and Innovation, Luxembourg Institute of Science and Technology (LIST), Belvaux, L-4422, Grand-duchy of Luxembourg;Luxembourg Institute of Science and Technology (LIST), Belvaux, Grand-duchy of Luxembourg;Wulfmeyer, Volker;Volker;Wulfmeyer;0000-0003-4882-2524;Institut f\u00fcr Physik und Meteorologie, Universit\u00e4t Hohenheim, 70599 Stuttgart, Germany;University Hohenheim, Stuttgart, Germany;2018-09-14;2015-06-11T10:30:00/2015-07-23T06:30:00;en;10.5194/hess-2018-310;10.5880/fidgeo.2018.019;10.1127/metz/2014/0618;371473 Bytes;1 Files;application/x-zip-compressed;CC BY 4.0;This dataset provides half-hourly surface energy balance measurements for a temperate grassland site in Luxembourg. The data were obtained during a field campaign in June and July 2015. The observations comprise multiple variables measurements by an Eddy-Covariance station, a net radiometer, soil moisture, temperature and soil heat flux probes and meteorological standard measurements. For details please see the reference article Renner et al., 2018 HESSD with the general setup described in Wizemann et al., 2015. The data are complemented by half-hourly model output of sensible and latent heat fluxes that are published as individual data publication (Renner et al., 2018).;5.803196525386966;49.77951003393976;Deutsche Forschungsgemeinschaft;http://doi.org/10.13039/501100001659;FOR 1598;From Catchments as Organised Systems to Models based on Dynamic Functional Units \u2013 CAOS;Deutsche Forschungsgemeinschaft;http://doi.org/10.13039/501100001659;KL 2168/2-1;Understanding and characterizing land surface-atmosphere exchange and feedbacks;Fonds National de la Recherche Luxembourg;http://doi.org/10.13039/501100001866;INTER/DFG/14/02;CAOS-2 project grant;Austrian Science Fund;http://doi.org/10.13039/501100002428",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "0f0d31cb-e224-57b0-a78e-32fcdd05e1e0",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6592"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/1b3079de-39e9-5b73-a9e1-f70b0feda6f6.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/1b3079de-39e9-5b73-a9e1-f70b0feda6f6.json
deleted file mode 100644
index ebf2d556..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/1b3079de-39e9-5b73-a9e1-f70b0feda6f6.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Hecht, Lutz",
-        "Siegert, Susann"
-    ],
-    "Contributor": [
-        "Hecht, Lutz",
-        "Siegert, Susann"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.5880/fidgeo.2017.002",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "application/vnd.ms-excel",
-        "application/pdf"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6294",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6294"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "GFZ Data Services"
-    ],
-    "Rights": [
-        "CC BY 4.0"
-    ],
-    "SpatialCoverage": "(49N,11E)",
-    "author": [
-        "Hecht, Lutz",
-        "Schmitt, Ralf-Thomas",
-        "Siegert, Susann"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6294;2017-09-15T09:22:41Z;DOIDB;DOIDB.FID;false;3;DOIDB.FID;10.5880/fidgeo.2017.002;Siegert, Susann;0000-0002-4157-863X;Museum f\u00fcr Naturkunde, Leibniz Institute for Evolution and Biodiversity Science;Hecht, Lutz;Museum f\u00fcr Naturkunde, Leibniz Institute for Evolution and Biodiversity Science;Schmitt, Ralf-Thomas;Museum f\u00fcr Naturkunde, Leibniz Institute for Evolution and Biodiversity Science;Geochemical data of melt-bearing impact breccia (suevite) from the research drill core FBN 73 of the Ries impact crater, Germany;GFZ Data Services;2017;geochemistry;Ries impact crater;melt-bearing impact breccia;suevite ;X-ray fluorescence;Siegert, Susann;0000-0002-4157-863X;Museum f\u00fcr Naturkunde, Leibniz Institute for Evolution and Biodiversity Science;Hecht, Lutz;Museum f\u00fcr Naturkunde, Leibniz Institute for Evolution and Biodiversity Science;en;10.1046/j.1365-2494.1998.53202081.x-i1;10.1111/maps.12087;10.1111/maps.12086;https://www.bestellen.bayern.de/application/applstarter?APPL=eshop&DIR=eshop&ACTIONxSETVAL(artdtl_geo.htm,APGxNODENR:273903,AARTxNR:91072,AARTxNODENR:274870,USERxBODYURL:artdtl.htm,KATALOG:StMUG,AKATxNAME:StMUG,ALLE:x)=X;10.1130/G39198.1;10.5880/fidgeo.2017.001;213251 Bytes;3 Files;application/vnd.ms-excel;application/vnd.ms-excel;application/pdf;CC BY 4.0;This data set comprises XRF (89 samples) and ICP-AES/ICP-MS (12 samples) major and trace element geochemistry of melt-bearing impact breccia (suevite) samples of the research drill core FBN 73 of the Ries impact crater in Southern Germany. The 1,206 m deep drilling in the central part of the Ries impact crater, carried out in 1973 (Bayerisches Geologisches Landesamt 1974), provided insights into the origin and distribution of suevite and into the development of the post-impact Ries lake with redeposited suevitic sediments at its base (St\u00f6ffler et al. 2013). The suevite is divided into five sequences, (1) dike suevite 1186-602 m, (2) melt-rich suevite 602-525 m, (3) melt-rich suevite 525-331 m, (4) graded suevite 331-314 m, and (5) reworked suevite 314-257 m (St\u00f6ffler et al., 2013 and references therein).\n      ;48.88277959345126 10.54962158203125;FBN 73 borehole, Ries Impact Crater, Germany",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "1b3079de-39e9-5b73-a9e1-f70b0feda6f6",
-    "notes": [
-        "This data set comprises XRF (89 samples) and ICP-AES/ICP-MS (12 samples) major and trace element geochemistry of melt-bearing impact breccia (suevite) samples of the research drill core FBN 73 of the Ries impact crater in Southern Germany. The 1,206 m deep drilling in the central part of the Ries impact crater, carried out in 1973 (Bayerisches Geologisches Landesamt 1974), provided insights into the origin and distribution of suevite and into the development of the post-impact Ries lake with redeposited suevitic sediments at its base (St\u00f6ffler et al. 2013). The suevite is divided into five sequences, (1) dike suevite 1186-602 m, (2) melt-rich suevite 602-525 m, (3) melt-rich suevite 525-331 m, (4) graded suevite 331-314 m, and (5) reworked suevite 314-257 m (St\u00f6ffler et al., 2013 and references therein).\n      "
-    ],
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6294"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[10.54962158203125,48.88277959345126],[10.54962158203125,48.88277959345126],[10.54962158203125,48.88277959345126],[10.54962158203125,48.88277959345126],[10.54962158203125,48.88277959345126]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "geochemistry"
-        },
-        {
-            "name": "Ries impact crater"
-        },
-        {
-            "name": "melt-bearing impact breccia"
-        },
-        {
-            "name": "suevite"
-        },
-        {
-            "name": "X-ray fluorescence"
-        }
-    ],
-    "title": [
-        "Geochemical data of melt-bearing impact breccia (suevite) from the research drill core FBN 73 of the Ries impact crater, Germany"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/1bf469fc-9a20-57db-ab6e-e00ac3d99090.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/1bf469fc-9a20-57db-ab6e-e00ac3d99090.json
deleted file mode 100644
index ef62ec40..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/1bf469fc-9a20-57db-ab6e-e00ac3d99090.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6333",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6333"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6333;2018-09-05T10:05:15Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2017.013;Del Bello, Elisabetta;Elisabetta;Del Bello;orcid.org/0000-0001-8043-7410;Istituto Nazionale di Geofisica e Vulcanologia;Taddeucci, Jacopo;Jacopo;Taddeucci;orcid.org/0000-0002-0516-3699;Istituto Nazionale di Geofisica e Vulcanologia;Scarlato, Piergiorgio;Piergiorgio;Scarlato;orcid.org/0000-0003-1933-0192;Giacalone, Emanuele;Emanuele;Giacalone;Particle size distribution analyses of volcanic ash from Campi Flegrei (Italy) and Sakurajima (Japan) volcanoes ;GFZ Data Services;2017;multi-wavelength separation analyser;grain size distribution;phonolite;andesite;EPOS;Multi-scale laboratories;rock and melt physical properties;Del Bello, Elisabetta;Elisabetta;Del Bello;orcid.org/0000-0001-8043-7410;Istituto Nazionale di Geofisica e Vulcanologia;Del Bello, Elisabetta;Elisabetta;Del Bello;orcid.org/0000-0001-8043-7410;Istituto Nazionale di Geofisica e Vulcanologia;Taddeucci, Jacopo;Jacopo;Taddeucci;orcid.org/0000-0002-0516-3699;Istituto Nazionale di Geofisica e Vulcanologia;Taddeucci, Jacopo;Jacopo;Taddeucci;orcid.org/0000-0002-0516-3699;Istituto Nazionale di Geofisica e Vulcanologia;Scarlato, Piergiorgio;Piergiorgio;Scarlato;orcid.org/0000-0003-1933-0192;Scarlato, Piergiorgio;Piergiorgio;Scarlato;orcid.org/0000-0003-1933-0192;Scarlato, Piergiorgio;Piergiorgio;Scarlato;orcid.org/0000-0003-1933-0192;Giacalone, Emanuele;Emanuele;Giacalone;HP-HT Laboratory of Experimental Volcanolgy and Geophysics (INGV, Italy);INGV, Italy;en;10.1002/2014GL062292;10.1002/ppsc.200601028;10.1016/S0377-0273(99)00037-2;19273360 Bytes;3 Files;application/pdf;application/pdf;application/x-zip-compressed;CC BY 4.0;This data publication includes particle size distribution data of natural volcanic ash samples used as starting material for laboratory experiments simulating the aggregation/disaggregation of colliding volcanic ash particles. Full details of the experimental method can be found in Del Bello et. al. (2015) and in the data description file provided here.;130.64838409423828;130.67516326904297;31.568590419282316;31.58964917898045;Sakurajima volcano, Japan;14.034347534179688;14.308319091796875;40.769101775774935;40.9145503626772;Campi Flegrei Volcano, Italy",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "1bf469fc-9a20-57db-ab6e-e00ac3d99090",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6333"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/22eeeb35-8160-5bf1-ab90-1a21dbc6ab14.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/22eeeb35-8160-5bf1-ab90-1a21dbc6ab14.json
deleted file mode 100644
index 2f97ac32..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/22eeeb35-8160-5bf1-ab90-1a21dbc6ab14.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6332",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6332"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6332;2018-10-04T11:10:19Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2017.012;Verberne, Berend Antonie;0000-0002-1208-6193;High Pressure & Temperature Laboratory, Utrecht University;Chen, Jianye;0000-0002-5973-5293;High Pressure & Temperature Laboratory, Utrecht University;Pennock, Gillian;7006507017;Structural Geology & Tectonics, Utrecht University;Mechanical data and microstructures of simulated calcite fault gouge sheared at 550\u00b0C;GFZ Data Services;2017;EPOS;multi-scale laboratories;rock and melt physical properties;European Plate Observing System;Verberne, Berend Antonie;0000-0002-1208-6193;High Pressure & Temperature Laboratory, Utrecht University;Chen, Jianye;0000-0002-5973-5293;High Pressure & Temperature Laboratory, Utrecht University;Pennock, Gillian;7006507017;Structural Geology & Tectonics, Utrecht University;Experimental rock deformation/HPT-Lab (Utrecht University, The Netherlands);Utrecht University, The Netherlands;2017-10-12;en;10.5880/ICDP.5052.002;10.1002/2015JB012292;10.1002/2015jb012593;10.1038/s41467-017-01843-3;364269060 Bytes;2 Files;application/zip;application/pdf;CC BY 4.0;The largest magnitude earthquakes nucleate at depths near the base of the seismogenic zone, near the transition from velocity weakening frictional slip to velocity strengthening ductile flow. However, the mechanisms controlling this transition, and relevant to earthquake nucleation, remain poorly understood. Here we present data from experiments investigating the effect of slip rate on the mechanical properties and microstructure development of simulated calcite fault gouge sheared at ~550\u00b0C, close to the transition from (unstable) velocity weakening to (stable) velocity strengthening behaviour, reported by Verberne et al. (2015).",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "22eeeb35-8160-5bf1-ab90-1a21dbc6ab14",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6332"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/233f6c97-8d8b-5015-8389-2a4e71da187d.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/233f6c97-8d8b-5015-8389-2a4e71da187d.json
deleted file mode 100644
index d5fb12f8..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/233f6c97-8d8b-5015-8389-2a4e71da187d.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Ehlers, Todd",
-        "Starke, Jessica"
-    ],
-    "Contributor": [
-        "Ehlers, Todd",
-        "Starke, Jessica"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.5880/fidgeo.2017.004",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
-        "application/pdf",
-        "application/x-zip-compressed"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6319",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6319"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "GFZ Data Services"
-    ],
-    "Rights": [
-        "CC BY 4.0"
-    ],
-    "SpatialCoverage": "(24S-18S,70W-68W)",
-    "TemporalCoverage": " period : ( 2016-06-01T11:59:59Z - None ) ",
-    "author": [
-        "Ehlers, Todd",
-        "Schaller, Mirjam",
-        "Starke, Jessica"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6319;2017-10-07T16:47:47Z;DOIDB;DOIDB.FID;false;3;DOIDB.FID;10.5880/fidgeo.2017.004;Starke, Jessica;0000-0002-2619-0880;Eberhard Karls University Tuebingen; Germany;Ehlers, Todd;0000-0001-9436-0303;Eberhard Karls University Tuebingen; Germany;Schaller, Mirjam;0000-0003-4638-0873;Eberhard Karls University Tuebingen; Germany; Supplement to: Plate tectonic and climatic controls on the spatial distribution of denudation rates in northern Chile (18\u00b0S to 23\u00b0S) determined from cosmogenic nuclides;GFZ Data Services;2017;Cosmogenic nuclide- derived denudation rates;10Be;factor analysis;Northern Chile;tectonic and climate controls;Starke, Jessica;0000-0002-2619-0880;Eberhard Karls University Tuebingen; Germany;Starke, Jessica;0000-0002-2619-0880;Eberhard Karls University Tuebingen; Germany;Starke, Jessica;0000-0002-2619-0880;Eberhard Karls University Tuebingen; Germany;Starke, Jessica;0000-0002-2619-0880;Eberhard Karls University Tuebingen; Germany;Ehlers, Todd;0000-0001-9436-0303;Eberhard Karls University Tuebingen; Germany;2016-06-01;/2;en;10.1002/2016JF004153;10.1016/j.quageo.2013.02.002;10.1016/j.nimb.2009.09.012;10.1007/BF02289233;10.1016/j.nimb.2009.09.020;10.1016/S0012-821X(02)00951-2;10.1007/BF02291170;10.1007/BF02291170;10.1130/2006.2398(04);243954 Bytes;4 Files;application/vnd.openxmlformats-officedocument.spreadsheetml.sheet;application/pdf;application/x-zip-compressed;application/vnd.openxmlformats-officedocument.wordprocessingml.document;CC BY 4.0;In the arid and largely abiotic region of northern Chile the environmental conditions are favorable for measurement of the tectonic and climate influence on catchment denudation rates. Previous studies of denudation rates from cosmogenic 10Be and 26Al concentrations are limited to single drainages. In this study, we present 34 new 10Be and eight 26Al derived catchment-averaged denudation rates from 33 catchments to analyze variations of denudation rates between 18\u00b0S to 23\u00b0S in the Coastal and Western Cordilleras of northern Chile. Cosmogenic nuclide-derived denudation rates range from 0.4\u00b10.5 to 20.6\u00b11.5 m/Myr in the Coastal Cordillera and from 1.4\u00b10.7 to 168.0\u00b119.8 m/Myr in the Western Cordillera. The controls on the denudation rates are evaluated using a statistical factor analysis of ten selected catchment parameters. Denudation rates indicate a strong linear relationship with channel steepness indices but insignificant correlations and covariation with mean annual precipitation rates, drainage area, stream order, mean elevation, mean local relief, mean basin slope and analyzed grain size. Thus, denudation rates are better correlated with tectonic controls at catchment scale than orogen-scale plate tectonics in the Western Cordillera and Coastal Cordillera. ;-23.885837699861995 -70.48828125 -18.35452552912664 -67.9833984375",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "233f6c97-8d8b-5015-8389-2a4e71da187d",
-    "notes": [
-        "In the arid and largely abiotic region of northern Chile the environmental conditions are favorable for measurement of the tectonic and climate influence on catchment denudation rates. Previous studies of denudation rates from cosmogenic 10Be and 26Al concentrations are limited to single drainages. In this study, we present 34 new 10Be and eight 26Al derived catchment-averaged denudation rates from 33 catchments to analyze variations of denudation rates between 18\u00b0S to 23\u00b0S in the Coastal and Western Cordilleras of northern Chile. Cosmogenic nuclide-derived denudation rates range from 0.4\u00b10.5 to 20.6\u00b11.5 m/Myr in the Coastal Cordillera and from 1.4\u00b10.7 to 168.0\u00b119.8 m/Myr in the Western Cordillera. The controls on the denudation rates are evaluated using a statistical factor analysis of ten selected catchment parameters. Denudation rates indicate a strong linear relationship with channel steepness indices but insignificant correlations and covariation with mean annual precipitation rates, drainage area, stream order, mean elevation, mean local relief, mean basin slope and analyzed grain size. Thus, denudation rates are better correlated with tectonic controls at catchment scale than orogen-scale plate tectonics in the Western Cordillera and Coastal Cordillera. "
-    ],
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6319"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-70.48828125,-23.885837699861995],[-70.48828125,-18.35452552912664],[-67.9833984375,-18.35452552912664],[-67.9833984375,-23.885837699861995],[-70.48828125,-23.885837699861995]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Cosmogenic nuclide- derived denudation rates"
-        },
-        {
-            "name": "factor analysis"
-        },
-        {
-            "name": "Northern Chile"
-        },
-        {
-            "name": "tectonic climate controls"
-        }
-    ],
-    "title": [
-        " Supplement to: Plate tectonic and climatic controls on the spatial distribution of denudation rates in northern Chile (18\u00b0S to 23\u00b0S) determined from cosmogenic nuclides"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/26618647-99c0-5610-a274-724a66ccbe77.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/26618647-99c0-5610-a274-724a66ccbe77.json
deleted file mode 100644
index cc1f8a83..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/26618647-99c0-5610-a274-724a66ccbe77.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6616",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6616"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6616;2019-01-24T07:45:49Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2018.071;Corbi, Fabio;Fabio;Corbi;0000-0003-2662-3065;Universit\u00e0 degli Studi Roma Tre, Rome, Italy;Sandri, Laura;Laura;Sandri;0000-0002-3254-2336;INGV Bologna;Bedford, Jonathan;Jonathan;Bedford;0000-0002-8954-4367;GFZ German Research Centre for Geosciences, Potsdam, Germany;Funiciello, Francesca;Francesca;Funiciello;0000-0001-7900-8272;Universit\u00e0 degli Studi Roma Tre, Rome, Italy;Brizzi, Silvia;Silvia;Brizzi;0000-0002-5258-0495;Universit\u00e0 degli Studi Roma Tre, Rome, Italy;Rosenau, Matthias;Matthias;Rosenau;0000-0003-1134-5381;GFZ German Research Centre for Geosciences, Potsdam, Germany;Lallemand, Serge;Serge;Lallemand;0000-0003-1924-9423;G\u00e9osciences Montpellier, CNRS, Montpellier, France;Montpellier University, Montpellier, France;Supplementary material to \"Machine Learning can predict the timing and size of analog earthquakes\";GFZ Data Services;2018;Machine Learning;Analog models of geologic processes;Subduction megathrust earthquakes;Asperities;multi-scale laboratories;EPOS;Analog modelling results;Software tools;EARTH SCIENCE > SOLID EARTH > TECTONICS > PLATE TECTONICS > FAULT MOVEMENT;EARTH SCIENCE > SOLID EARTH > TECTONICS > EARTHQUAKES;EARTH SCIENCE > SOLID EARTH > TECTONICS > EARTHQUAKES > EARTHQUAKE PREDICTIONS;tectonic setting > plate margin setting;tectonic setting > plate margin setting > subduction zone setting;tectonic process > subduction;tectonic process;geologic process;deformation;thrust fault;tectonic and structural features;Gelatine > Pig skin;Gelatine;Wedge simulator;Earthquake simulator;Digital Image Correlation (DIC) / Particle Image Velocimetry (PIV) > MatPIV;Videocamera;Surface image;Corbi, Fabio;Fabio;Corbi;0000-0003-2662-3065;Universit\u00e0 degli Studi Roma Tre, Rome, Italy;Corbi, Fabio;Fabio;Corbi;0000-0003-2662-3065;Universit\u00e0 degli Studi Roma Tre, Rome, Italy;Laboratory of Experimental Tectonics (University of Roma TRE, Italy);Universit\u00e1 degli studi \"Roma TRE\", Rome, Italy;2016-01;eng;Dataset;10.1029/2018GL081251;10.1002/2017GL074182;http://folk.uio.no/jks/matpiv/html/MatPIVtut.pdf;3 Files;application/octet-stream;application/octet-stream;application/octet-stream;CC BY 4.0;This data set includes the results of digital image correlation of one experiment on subduction megathrust earthquakes with interacting asperities performed at the Laboratory of Experimental Tectonics (LET) Univ. Roma Tre in the framework of AspSync, the Marie Curie project (grant agreement 658034) lead by F. Corbi in 2016-2017. Detailed descriptions of the experiments and monitoring techniques can be found in Corbi et al. (2017 and 2019) to which this data set is supplementary material.;H2020 Marie Sk\u0142odowska-Curie Actions;http://doi.org/10.13039/100010665;658034;AspSync;Deutsche Forschungsgemeinschaft;http://doi.org/10.13039/501100001659;CRC 1114;Scaling Cascades in Complex Systems;Deutsche Forschungsgemeinschaft;http://doi.org/10.13039/501100001659;MO-2310/3;Peascados",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "26618647-99c0-5610-a274-724a66ccbe77",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6616"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/2fd5f485-638a-56ca-8d7e-8f3d981e779d.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/2fd5f485-638a-56ca-8d7e-8f3d981e779d.json
deleted file mode 100644
index 46c9ab4a..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/2fd5f485-638a-56ca-8d7e-8f3d981e779d.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6595",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6595"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6595;2018-12-21T07:38:54Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2018.072;Willingshofer, Ernst;Ernst;Willingshofer;0000-0002-9119-5557;Department of Tectonics, Faculty of Earth Sciences, Utrecht University, Utrecht, The Netherlands;Sokoutis, Dimitrios;Dimitrios;Sokoutis;0000-0003-0523-9785;Department of Tectonics, Faculty of Earth Sciences, Utrecht University, Utrecht, The Netherlands;Beekman, Fred;Fred;Beekman;0000-0002-8455-999X;Department of Tectonics, Faculty of Earth Sciences, Utrecht University, Utrecht, The Netherlands;Sch\u00f6nebeck, Jan-Michael;Jan-Michael;Sch\u00f6nebeck;GFZ German Research Centre for Geosciences, Potsdam, Germany;Warsitzka, Michael;Michael;Warsitzka;0000-0003-1774-5888;GFZ German Research Centre for Geosciences, Potsdam, Germany;Rosenau, Matthias;Matthias;Rosenau;0000-0003-1134-5381;GFZ German Research Centre for Geosciences, Potsdam, Germany;Ring shear test data of feldspar sand and quartz sand used in the Tectonic Laboratory (TecLab) at Utrecht University for experimental Earth Science applications;GFZ Data Services;2018;EPOS;Multi-scale laboratories;analogue models of geologic processes;property data of analogue modelling materials;software tools;EARTH SCIENCE > SOLID EARTH > TECTONICS;EARTH SCIENCE SERVICES > DATA ANALYSIS AND VISUALIZATION > CALIBRATION/VALIDATION;earth interior setting > crust setting > continental-crustal setting > upper continental crustal setting;deformation > fracturing;fault;tectonic and structural features;Sand > Quartz Sand;Iron Powder;Ring-shear tester;Force sensor;Friction coefficient;Cohesion;Willingshofer, Ernst;Ernst;Willingshofer;0000-0002-9119-5557;Department of Tectonics, Faculty of Earth Sciences, Utrecht University, Utrecht, The Netherlands;Sokoutis, Dimitrios;Dimitrios;Sokoutis;0000-0003-0523-9785;Department of Tectonics, Faculty of Earth Sciences, Utrecht University, Utrecht, The Netherlands;Beekman, Fred;Fred;Beekman;0000-0002-8455-999X;Department of Tectonics, Faculty of Earth Sciences, Utrecht University, Utrecht, The Netherlands;Sch\u00f6nebeck, Jan-Michael;Jan-Michael;Sch\u00f6nebeck;GFZ German Research Centre for Geosciences, Potsdam, Germany;Warsitzka, Michael;Michael;Warsitzka;0000-0003-1774-5888;GFZ German Research Centre for Geosciences, Potsdam, Germany;Rosenau, Matthias;Matthias;Rosenau;0000-0003-1134-5381;GFZ German Research Centre for Geosciences, Potsdam, Germany;TecLab - Tectonic Modelling Laboratory (Utrecht University, The Netherlands);University, Utrecht, The Netherlands;HelTec - Helmholtz Laboratory for Tectonic Modelling (GFZ Potsdam, Germany);GFZ German Research Centre for Geosciences, Potsdam, Germany;en;10.1144/GSL.SP.2005.243.01.18;10.1002/2016JB012915;10.1016/j.jsg.2015.03.008;10.1002/ceat.200303112;978-3-540-73767-4;10.1016/j.tecto.2016.01.017;10.1111/j.1365-3091.2009.01120.x;10.3389/feart.2018.00148;10.1002/2016TC004424;10.1016/j.epsl.2015.05.022;10.1002/2014TC003756;10.1029/2010TC002719;10.1029/2012TC003122;10.1144/petgeo2015-029;10.1029/2010TC002823;10.1007/s00531-012-0846-4;10.1016/j.epsl.2014.03.036;10.1016/j.tecto.2013.03.009;10.1111/bre.12129;10.1016/j.epsl.2011.03.028;10.1016/j.epsl.2017.05.012;10.1111/sed.12313;10.1130/G25321A.1;10.1144/GSL.SP.2005.243.01.18;10.1130/G34815.1;3 Files;application/octet-stream;application/octet-stream;application/octet-stream;1;CC BY 4.0;This dataset provides friction data from ring-shear tests (RST) on feldspar sand and quartz sand, which are used to simulate brittle behaviour in crust- and lithosphere-scale analogue experiments at the Tectonic Laboratory (TecLab), Utrecht University (NL) (Willingshofer et al., 2005; Willingshofer & Sokoutis, 2009; Athmer et al., 2010; Luth et al., 2010; Fern\u00e1ndez-Lozano et al., 2011; Leever et al., 2011; Sokoutis & Willingshofer, 2011; Fern\u00e1ndez-Lozano et al., 2012; Luth et al., 2013; Munteanu et al., 2013; Willingshofer et al., 2013; Munteanu et al., 2014; Calignano et al., 2015a, b; Ortner et al., 2015; Gabrielsen et al., 2016; Calignano et al., 2017; van Gelder et al., 2017; Wang et al., 2017; Beniest et al., 2018 ). The materials have been characterized by means of internal friction coefficients \u00b5 and cohesions C as a remote service by the Helmholtz Laboratory for Tectonic Modelling (HelTec) at the GFZ German Research Centre for Geosciences in Potsdam.",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "2fd5f485-638a-56ca-8d7e-8f3d981e779d",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6595"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/45038636-a664-570d-9ec8-918d947a3322.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/45038636-a664-570d-9ec8-918d947a3322.json
deleted file mode 100644
index 9394bf60..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/45038636-a664-570d-9ec8-918d947a3322.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6613",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6613"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6613;2019-01-23T13:57:42Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2019.003;Corbi, Fabio;Fabio;Corbi;0000-0003-2662-3065;Universit\u00e1 degli studi \"Roma TRE\", Rome, Italy;Xu, Wenbin;Wenbin;Xu;0000-0001-7294-8229;King Abdullah University of Science and Technology, , Thuwal, Saudi Arabia;University of California, Berkeley, California, USA;Rivalta, Eleonora;Eleonora;Rivalta;0000-0001-8245-0504;GFZ German Research Centre for Geosciences, Potsdam, Germany;Jonsson, Sigurjon;Sigurjon;Jonsson;0000-0001-5378-7079;King Abdullah University of Science and Technology, , Thuwal, Saudi Arabia;Supplement to: Graben formation and dike arrest during the 2009 Harrat Lunayyir dike intrusion in Saudi Arabia: Insights from InSAR, stress calculations and analog experiments;GFZ Data Services;2019;EPOS;multi-scale laboratories;analogue models of geologic processes;analogue modelling results;software tools;dike;Harrat Lunayyir;graben formation;dike-fault interaction;volcano deformation;EARTH SCIENCE > SOLID EARTH > TECTONICS > VOLCANIC ACTIVITY;graben;magmatic process > intrusion;magmatic process;fault;dike;volcanic features;Sand > Quartz Sand;Sandbox > Sandbox (cm scale);Digital Image Correlation (DIC) / Particle Image Velocimetry (PIV) > MatPIV;SLR camera;Surface image;Corbi, Fabio;Fabio;Corbi;0000-0003-2662-3065;Universit\u00e1 degli studi \"Roma TRE\", Rome, Italy;Laboratory of Experimental Tectonics (University of Roma TRE, Italy);Universit\u00e1 degli studi \"Roma TRE\", Rome, Italy;2015-07-14;eng;10.1002/2015JB012505;2 Files;application/octet-stream;application/octet-stream;CC BY 4.0;This dataset is supplementary material to the article by Xu et al. (2016) \u2018Graben formation and dike arrest during the 2009 Harrat Lunayyir dike intrusion in Saudi Arabia: Insights from InSAR, stress calculations and analog experiments\u2019. The Authors described the spatial and temporal effects of a propagating dike on crustal deformation, including the interaction with faulting, using a multidisciplinary approach. This supplementary material concerns the analog modelling part only. For a detailed description of the experimental procedure, set-up and materials used, please refer to the article of Xu et al. (2016; paragraph 5).;37.43952519700963;38.20307500169713;24.871957649836745;25.394129841584835;European Union;ERC-StG;240583;CCMP-POMPEI",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "45038636-a664-570d-9ec8-918d947a3322",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6613"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/46fc4a70-1b67-5533-a941-9b20867a2771.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/46fc4a70-1b67-5533-a941-9b20867a2771.json
deleted file mode 100644
index 9b93c2f1..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/46fc4a70-1b67-5533-a941-9b20867a2771.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6554",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6554"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6554;2018-10-25T08:10:48Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2018.007;Kelder, Nick A.;Nick A.;Kelder;Utrecht University, The Netherlands;Sant, Karin;Karin;Sant;https://orcid.org/0000-0002-1508-3959;Utrecht University, The Netherlands;van Dijk, Gijs A.;Gijs A.;van Dijk;Utrecht University, The Netherlands;Lathouwers, Ymke Z.;Ymke Z.;Lathouwers;Utrecht University, The Netherlands;Dekkers, Mark J.;Mark J.;Dekkers;http://orcid.org/0000-0002-4156-3841;Utrecht University, The Netherlands;Krijgsman, Wout;Wout;Krijgsman;7003956416;Utrecht University, The Netherlands;Magyar, Imre;Imre;Magyar;7005270225;MTA-MTM-ELTE Research Group for Paleontology, Hungary;Sztan\u00f3, Orsolya;Orsolya;Sztan\u00f3;http://orcid.org/0000-0003-0786-3653;E\u00f6tv\u00f6s Lor\u00e1nd University, Hungary;Supplementary paleomagnetic data to: \u201cPaleomagnetism in the Pannonian; Problems, Pitfalls, and Progress in using iron sulphides for magnetostratigraphy\u201d;GFZ Data Services;2018;magnetostratigraphy;Lake Pannon;Hungary;iron sulfide;greigite;endemic;delta progradation;EPOS;Multi-scale laboratories;Paleomagnetic and magnetic data;paleomagnetic data;Kelder, Nick A.;Nick A.;Kelder;Utrecht University, The Netherlands;Sant, Karin;Karin;Sant;https://orcid.org/0000-0002-1508-3959;Utrecht University, The Netherlands;Sant, Karin;Karin;Sant;https://orcid.org/0000-0002-1508-3959;Utrecht University, The Netherlands;van Dijk, Gijs A.;Gijs A.;van Dijk;Utrecht University, The Netherlands;Lathouwers, Ymke Z.;Ymke Z.;Lathouwers;Utrecht University, The Netherlands;Dekkers, Mark J.;Mark J.;Dekkers;http://orcid.org/0000-0002-4156-3841;Utrecht University, The Netherlands;Krijgsman, Wout;Wout;Krijgsman;7003956416;Utrecht University, The Netherlands;Magyar, Imre;Imre;Magyar;7005270225;MTA-MTM-ELTE Research Group for Paleontology, Hungary;Sztan\u00f3, Orsolya;Orsolya;Sztan\u00f3;http://orcid.org/0000-0003-0786-3653;E\u00f6tv\u00f6s Lor\u00e1nd University, Hungary;Paleomagnetic Laboratory Fort Hoofddijk (Utrecht University, The Netherlands);Utrecht University, Utrecht, The Netherlands;Mecsekerc Ltd.;2018-07-01/2;2018-04-17;eng;10.1029/2018GC007673;10.1016/j.cageo.2016.05.007;1763452 Bytes;2 Files;application/x-zip-compressed;application/pdf;CC BY 4.0;This dataset contains the paleomagnetic supplementary material to the article Kelder et al. (subm.), which presents a magnetostratigraphic correlation of Late Miocene lacustrine sediments based on multi-polarity greigite. The multi-polarity is visible in most thermal paleomagnetic results (Zijderveld diagrams) by antipodal high and medium temperature components, while only one magnetic component was visible in the alternating field demagnetization diagrams. Based on this complex behavior, a tailored demagnetization approach was developed to allow for reliable magnetostratigraphic dating of lacustrine sediments.;18.63555908203125;19.12994384765625;46.47002468938531;46.758679967095574;Data derive from four cores taken in the period 2015-2017;Nederlandse Organisatie voor Wetenschappelijk Onderzoek;http://doi.org/10.13039/501100003246;865.10.011;VICI",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "46fc4a70-1b67-5533-a941-9b20867a2771",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6554"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/60c2d821-0da2-5c83-be3a-1d2ad666cb08.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/60c2d821-0da2-5c83-be3a-1d2ad666cb08.json
deleted file mode 100644
index 9b4de4b2..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/60c2d821-0da2-5c83-be3a-1d2ad666cb08.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Schmitt, Ralf-Thomas"
-    ],
-    "Contributor": [
-        "Schmitt, Ralf-Thomas"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.5880/fidgeo.2017.001",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "application/vnd.ms-excel",
-        "application/pdf"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6295",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6295"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "GFZ Data Services"
-    ],
-    "Rights": [
-        "CC BY 4.0"
-    ],
-    "author": [
-        "Hecht, Lutz",
-        "Schmitt, Ralf-Thomas",
-        "Siegert, Susann",
-        "St\u00f6ffler, Dieter"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6295;2017-09-15T09:22:01Z;DOIDB;DOIDB.FID;false;3;DOIDB.FID;10.5880/fidgeo.2017.001;Schmitt, Ralf-Thomas;Museum f\u00fcr Naturkunde - Leibniz-Institut f\u00fcr Evolutions- und Biodiversit\u00e4tsforschung;Hecht, Lutz;Museum f\u00fcr Naturkunde - Leibniz-Institut f\u00fcr Evolutions- und Biodiversit\u00e4tsforschung;St\u00f6ffler, Dieter;Museum f\u00fcr Naturkunde - Leibniz-Institut f\u00fcr Evolutions- und Biodiversit\u00e4tsforschung;Siegert, Susann;0000-0002-4157-863X;Museum f\u00fcr Naturkunde - Leibniz-Institut f\u00fcr Evolutions- und Biodiversit\u00e4tsforschung;Geochemical data of crystalline target lithologies of the Ries impact crater, Germany;GFZ Data Services;2017;geology;Ries impact crater;target rock geochemistry;X-ray fluorescence;ICP-MS;ICP-AES;Schmitt, Ralf-Thomas;Museum f\u00fcr Naturkunde - Leibniz-Institut f\u00fcr Evolutions- und Biodiversit\u00e4tsforschung;en;10.1130/G39198.1;10.5880/fidgeo.2017.002;240499 Bytes;2 Files;application/vnd.ms-excel;application/pdf;CC BY 4.0;This data set comprises major (XRF) and trace (XRF, ICP-MS, ICP-AES) element geochemistry of 185 samples of crystalline target lithologies of the N\u00f6rdlinger Ries impact crater in Southern Germany. ",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "60c2d821-0da2-5c83-be3a-1d2ad666cb08",
-    "notes": [
-        "This data set comprises major (XRF) and trace (XRF, ICP-MS, ICP-AES) element geochemistry of 185 samples of crystalline target lithologies of the N\u00f6rdlinger Ries impact crater in Southern Germany. "
-    ],
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6295"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "geology"
-        },
-        {
-            "name": "Ries impact crater"
-        },
-        {
-            "name": "target rock geochemistry"
-        },
-        {
-            "name": "X-ray fluorescence"
-        },
-        {
-            "name": "ICP-MS"
-        },
-        {
-            "name": "ICP-AES"
-        }
-    ],
-    "title": [
-        "Geochemical data of crystalline target lithologies of the Ries impact crater, Germany"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/691b68d1-e098-53b3-b1f3-0f77dd1d0c18.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/691b68d1-e098-53b3-b1f3-0f77dd1d0c18.json
deleted file mode 100644
index 89671ce0..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/691b68d1-e098-53b3-b1f3-0f77dd1d0c18.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6428",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6428"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6428;2018-09-05T10:15:34Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2018.005;Pijnenburg, Ronald;Ronald;Pijnenburg;0000-0003-0653-7565;Utrecht University, Utrecht, The Netherlands;Verberne, Berend;Berend;Verberne;0000-0002-1208-6193;Utrecht University, Utrecht, The Netherlands;Hangx, Suzanne;Suzanne;Hangx;0000-0003-2253-3273;Utrecht University, Utrecht, The Netherlands;Spiers, Christopher;Christopher;Spiers;0000-0002-3436-8941;Utrecht University, Utrecht, The Netherlands;Mechanical and microstructural data used in the article Pijnenburg et al., Deformation behaviour of sandstones from the seismogenic Groningen gas field: Role of inelastic versus elastic mechanisms;GFZ Data Services;2018;Groningen gas field;reservoir;sandstone;compressibility;microstructure;strength;crack;creep;EPOS;multi-scale laboratories;rock and melt physical properties;Pijnenburg, Ronald;Ronald;Pijnenburg;0000-0003-0653-7565;Utrecht University, Utrecht, The Netherlands;Pijnenburg, Ronald;Ronald;Pijnenburg;0000-0003-0653-7565;Utrecht University, Utrecht, The Netherlands;Experimental rock deformation/HPT-Lab (Utrecht University, The Netherlands);Utrecht University, The Netherlands;2015-05-01;eng;doi of paper when available;405651 Bytes;2 Files;application/octet-stream;application/pdf;CC BY 4.0;Hydrocarbon or groundwater production from sandstone reservoirs can result in surface subsidence and induced seismicity. Subsidence results from combined elastic and inelastic compaction of the reservoir due to a change in the effective stress state upon fluid extraction. The magnitude of elastic compaction can be accurately described using poroelasticity theory. However inelastic or time-dependent compaction is poorly constrained. We use sandstones recovered by the field operator (NAM) from the Slochteren gas reservoir (Groningen, NE Netherlands) to study the importance of elastic versus inelastic deformation processes upon simulated pore pressure depletion. We conducted conventional triaxial tests under true in-situ conditions of pressure and temperature. To investigate the effect of applied differential stress (\u03c31 \u2013 \u03c33 = 0 - 50 MPa) and initial sample porosity (\u03c6i = 12 \u2013 25%) on instantaneous and time-dependent inelastic deformation, we imposed multiple stages of axial loading and relaxation.;6.6913604736328125;53.32349126597425;Nederlandse Aardolie Maatschappij",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "691b68d1-e098-53b3-b1f3-0f77dd1d0c18",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6428"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/6a28c570-0253-5a3c-8a82-ddd11c13a8dc.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/6a28c570-0253-5a3c-8a82-ddd11c13a8dc.json
deleted file mode 100644
index 110345df..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/6a28c570-0253-5a3c-8a82-ddd11c13a8dc.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6557",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6557"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6557;2018-10-25T08:12:41Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2018.015;Peral, Mireia;Mireia;Peral;0000-0001-8026-2753;Group of Dynamics of the Lithosphere, Institut de Ci\u00e8ncies de la Terra Jaume Almera (ICTJA-CSIC), Barcelona, Spain.;Kir\u00e1ly, \u00c1gnes;\u00c1gnes;Kir\u00e1ly;The Centre for Earth Evolution and Dynamics, University of Oslo, Norway;Zlotnik, Sergio;Sergio;Zlotnik;Department of Civil and Environmental Engineering, Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain.;Funiciello, Francesca;Francesca;Funiciello;0000-0001-7900-8272;Laboratory of Experimental Tectonics, Department of Sciences, Universit\u00e0 degli Studi Roma Tre, Roma, Italy.;Fern\u00e0ndez, Manel;Manel;Fern\u00e0ndez;Group of Dynamics of the Lithosphere, Institut de Ci\u00e8ncies de la Terra Jaume Almera (ICTJA-CSIC), Barcelona, Spain;Faccenna, Claudio;Claudio;Faccenna;Laboratory of Experimental Tectonics, Department of Sciences, Universit\u00e0 degli Studi Roma Tre, Roma, Italy.;Verg\u00e9s, Jaume;Jaume;Verg\u00e9s;Group of Dynamics of the Lithosphere, Institut de Ci\u00e8ncies de la Terra Jaume Almera (ICTJA-CSIC), Barcelona, Spain.;Supplement to \"Opposite subduction polarity in adjacent plate segments\";GFZ Data Services;2018;Subduction analog models;ananlogue models;double subduction system;trench curvature;EPOS;Multi-scale laboratories;analogue models of geologic processes;analogue modelling results;Peral, Mireia;Mireia;Peral;0000-0001-8026-2753;Group of Dynamics of the Lithosphere, Institut de Ci\u00e8ncies de la Terra Jaume Almera (ICTJA-CSIC), Barcelona, Spain.;Laboratory of Experimental Tectonics (Universit\u00e0 di Roma TRE, Italy);Universit\u00e0 di Roma TRE, Italy;eng;10.1029/2017TC004896;949939 Bytes;2 Files;application/pdf;video/mp4;CC BY 4.0;This dataset contains ten movies corresponding to five analog experiments of double subduction systems with opposite polarity in adjacent plate segments. The laboratory model consists of two viscous layers of silicone putty representing the lithospheric plates, on top of a tank of syrup representing the mantle. Different setups have been designed to test the influence of the width of the plates and the initial separation between them on the resulting trench retreat velocities, deformation of plates and mantle flow.",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "6a28c570-0253-5a3c-8a82-ddd11c13a8dc",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6557"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/74b8a1c0-cbca-5615-9198-8eb8397ae025.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/74b8a1c0-cbca-5615-9198-8eb8397ae025.json
deleted file mode 100644
index 59910274..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/74b8a1c0-cbca-5615-9198-8eb8397ae025.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6406",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6406"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6406;2018-10-25T08:11:40Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2018.012;Urbani, Stefano;Stefano;Urbani;0000-0002-0421-022X;University of Roma Tre, Rome, Italy;Acocella, Valerio;Valerio;Acocella;University of Roma Tre, Rome, Italy;Rivalta, Eleonora;Eleonora;Rivalta;0000-0001-8245-0504;GFZ German Research Centre for Geosciences, Potsdam, Germany;Supplementary Material for Analogue Experiments on Lateral versus Vertical Dike Propagation;GFZ Data Services;2018;crustal layering;rigidity;Bardarbunga;EPOS;multi-scale laboratories;analogue models of geologic processes;analogue modelling results;Urbani, Stefano;Stefano;Urbani;0000-0002-0421-022X;University of Roma Tre, Rome, Italy;Urbani, Stefano;Stefano;Urbani;0000-0002-0421-022X;University of Roma Tre, Rome, Italy;Acocella, Valerio;Valerio;Acocella;University of Roma Tre, Rome, Italy;Rivalta, Eleonora;Eleonora;Rivalta;0000-0001-8245-0504;GFZ German Research Centre for Geosciences, Potsdam, Germany;Laboratory of Experimental Tectonics (University of Roma TRE, Italy);University of Roma Tre, Rome, Italy;2018-05-02;eng;10.1029/2017JB015376;97651 Bytes;2 Files;video/x-msvideo;application/pdf;CC BY 4.0;The dataset includes movies of 29 analogue experiments performed to investigate the effects on dike propagation by the following imposed parameters: density ratio between host-rock and magma analogues, rigidity layering and density layering of the host medium, flow rate and topography. The purpose of the experiments is to define a hierarchy of all the parameters considered, by varying systematically each of them, comparing semi-quantitatively the variations on dike geometry and velocity.;-17.77313232421875;-16.556396484375;64.55906111505632;64.9072397186371;Along strike topography along-strike topography of the 2014 Bardarbunga intrusion",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "74b8a1c0-cbca-5615-9198-8eb8397ae025",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6406"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/75010a70-1c9a-5896-8f39-34e088a27dfa.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/75010a70-1c9a-5896-8f39-34e088a27dfa.json
deleted file mode 100644
index e8c7adbf..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/75010a70-1c9a-5896-8f39-34e088a27dfa.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6429",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6429"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6429;2018-09-05T10:16:52Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2018.013;Giacomel, Piercarlo;Piercarlo;Giacomel;0000-0002-1553-7842;Sapienza University of Rome, Rome, Italy;Spagnuolo, Elena;Elena;Spagnuolo;0000-0002-1377-5812;Istituto Nazionale di Geofisica e Vulcanologia (INGV), Rome, Italy;Nazzari, Manuela;Manuela;Nazzari;Istituto Nazionale di Geofisica e Vulcanologia (INGV), Rome, Italy;Marzoli, Andrea;Andrea;Marzoli;University of Padua, Padua, Italy;Passelegue, Fran\u00e7ois;Fran\u00e7ois;Passelegue;\u00c9cole polytechnique f\u00e9d\u00e9rale de Lausanne (EPFL), Lausanne, Switzerland;Youbi, Nasrrddine;Nasrrddine;Youbi;0000-0003-3466-2400;Cadi Ayyad University, Marrakech, Marocco;Di Toro, Giulio;Giulio;Di Toro;0000-0002-6618-3474;University of Padua, Padua, Italy;Frictional and microanalytical data of basalts sheared with pressurized H2O- and CO2- rich fluids;GFZ Data Services;2018;CO2 storage in basalts;Induced seismicity;Role of fluid pressure on fault reactivation;Basalt carbonation;EPOS;Multi-scale laboratories;rock and melt physical properties;Giacomel, Piercarlo;Piercarlo;Giacomel;0000-0002-1553-7842;Sapienza University of Rome, Rome, Italy;Spagnuolo, Elena;Elena;Spagnuolo;0000-0002-1377-5812;Istituto Nazionale di Geofisica e Vulcanologia (INGV), Rome, Italy;Nazzari, Manuela;Manuela;Nazzari;Istituto Nazionale di Geofisica e Vulcanologia (INGV), Rome, Italy;Marzoli, Andrea;Andrea;Marzoli;University of Padua, Padua, Italy;Passelegue, Fran\u00e7ois;Fran\u00e7ois;Passelegue;\u00c9cole polytechnique f\u00e9d\u00e9rale de Lausanne (EPFL), Lausanne, Switzerland;Youbi, Nasrrddine;Nasrrddine;Youbi;0000-0003-3466-2400;Cadi Ayyad University, Marrakech, Marocco;Di Toro, Giulio;Giulio;Di Toro;0000-0002-6618-3474;University of Padua, Padua, Italy;HP-HT Laboratory of Experimental Volcanolgy and Geophysics (INGV, Italy);INGV,  Italy;en;10.1029/2018GL078082;75446831 Bytes;3 Files;text/plain;text/plain;application/octet-stream;CC BY 4.0;Here we report the raw data of the friction experiments performed on basalt-built faults pressurized with de-ionized H2O, pure CO2, pure Ar, and H2O+CO2 mixtures, respectively (Dataset_friction_basalts.zip). The experiments were designed to assess the effects of the fluid chemistry on fault reactivation in faults juxtaposing basalts with different state of hydrothermal alteration. The experiments setup and data are further described in Giacomel et al (2018) to which these data are supplementary material.",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "75010a70-1c9a-5896-8f39-34e088a27dfa",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6429"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/7551b9d4-a063-5255-bf92-56d4f8b0c47b.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/7551b9d4-a063-5255-bf92-56d4f8b0c47b.json
deleted file mode 100644
index 03cc9ee4..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/7551b9d4-a063-5255-bf92-56d4f8b0c47b.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6363",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6363"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6363;2018-10-25T09:08:06Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2018.001;Corti, Giacomo;Giacomo;Corti;Consiglio Nazionale delle Ricerche, Istituto di Geoscienze e Georisorse, Florence, Italy;Sordi, Riccardo;Riccardo;Sordi;Universit\u00e0 degli Studi di Firenze, Dipartimento di Scienze della Terra, Florence, Italy;Cucci, Federica;Federica;Cucci;Universit\u00e0 degli Studi di Firenze, Dipartimento di Scienze della Terra, Florence, Italy;Centrifuge models investigating the influence of transverse pre-existing weaknesses on continental rifting;GFZ Data Services;2018;analogue modelling;continental rifting;pre-existing structures;normal faulting;analogue models of geologic processes;multi-scale laboratories;EPOS;analogue modelling results;Tectonics Modelling Laboratory (IGG-CNR, Italy);IGG-CNR, Florence, Italy;eng;Dataset;10.1130/GES00863.1;10.1016/j.tecto.2011.06.010;10.3390/ma10060635;10.1016/j.tecto.2018.02.011;1511988 Bytes;1 Files;application/x-zip-compressed;CC BY 4.0;We present the results of centrifuge experiments investigating the role of preexisting crustal discontinuity on continental rifting. Specifically, we reproduce inherited weaknesses, orthogonal to the rift trend and parallel to the extension direction, and analyze their influence on the evolution and architecture of extensional deformation in the inner part and at the margins of continental rift valleys. Four different models, with variable width of the pre-existing weakness are illustrated.",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "7551b9d4-a063-5255-bf92-56d4f8b0c47b",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6363"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/7e3f69c6-58d2-5e37-818f-05e88d792513.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/7e3f69c6-58d2-5e37-818f-05e88d792513.json
deleted file mode 100644
index 360a0b69..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/7e3f69c6-58d2-5e37-818f-05e88d792513.json
+++ /dev/null
@@ -1,122 +0,0 @@
-{
-    "Contact": [
-        "Foerster, Saskia",
-        "L\u00f3pez-Taraz\u00f3n, Jos\u00e9 A.",
-        "Helmholtz Centre for Environmental Research (UFZ)",
-        "German Research Foundation",
-        "Brosinsky, Arlena",
-        "Elger, Kirsten",
-        "Batalla, Ramon",
-        "Bronstert, Axel",
-        "Ebro Water Authorities",
-        "Marie Curie Intra-European Fellowship",
-        "Economy and Knowledge Department of the Catalan Government",
-        "G\u00fcntner, Andreas",
-        "Francke, Till",
-        "Sommerer, Erik"
-    ],
-    "Contributor": [
-        "Foerster, Saskia",
-        "L\u00f3pez-Taraz\u00f3n, Jos\u00e9 A.",
-        "Helmholtz Centre for Environmental Research (UFZ)",
-        "German Research Foundation",
-        "Brosinsky, Arlena",
-        "Elger, Kirsten",
-        "Batalla, Ramon",
-        "Bronstert, Axel",
-        "Ebro Water Authorities",
-        "Marie Curie Intra-European Fellowship",
-        "Economy and Knowledge Department of the Catalan Government",
-        "G\u00fcntner, Andreas",
-        "Francke, Till",
-        "Sommerer, Erik"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.5880/fidgeo.2017.003",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "application/x-zip-compressed",
-        "application/pdf",
-        "application/octet-stream"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6287",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6287"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "GFZ Data Services"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "CC BY 4.0"
-    ],
-    "SpatialCoverage": "(42N-43N,0 E-1 E)",
-    "TempCoverageBegin": 63632948399,
-    "TempCoverageEnd": 63413578799,
-    "TemporalCoverage": " period : ( 2017-06-13T11:59:59Z - 2010-07-01T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2017-06-13T11:59:59Z",
-    "TemporalCoverage:EndDate": "2010-07-01T11:59:59Z",
-    "author": [
-        "Foerster, Saskia",
-        "L\u00f3pez-Taraz\u00f3n, Jos\u00e9 A.",
-        "Brosinsky, Arlena",
-        "Batalla, Ramon",
-        "Bronstert, Axel",
-        "G\u00fcntner, Andreas",
-        "Francke, Till",
-        "Sommerer, Erik"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6287;2017-10-04T14:21:34Z;DOIDB;DOIDB.FID;false;3;DOIDB.FID;10.5880/fidgeo.2017.003;Francke, Till;University of Potsdam, Institute of Earth and Environmental Science, Potsdam, Germany;Foerster, Saskia;GFZ German Research Centre for Geosciences, Section 1.4 Remote Sensing, Potsdam, Germany;Brosinsky, Arlena; University of Potsdam, Institute of Earth and Environmental Science, Potsdam, Germany; GFZ German Research Centre for Geosciences, Section 1.4 Remote Sensing, Potsdam, Germany;Sommerer, Erik;GFZ German Research Centre for Geosciences, Section 5.4 Hydrology, Potsdam, Germany;L\u00f3pez-Taraz\u00f3n, Jos\u00e9 A.;University of Potsdam, Institute of Earth and Environmental Science, Potsdam, Germany; Liverpool John Moores University, School of Natural Sciences and Psychology, Liverpool, UK; University of Lleida, Department of Environment and Soil Sciences, Fluvial Dynamics Research Group, Lleida, Spain; University of the Balearic Islands, Department of Geography, Palma, Spain;G\u00fcntner, Andreas;GFZ German Research Centre for Geosciences, Section 5.4 Hydrology; Potsdam, Germany; University of Potsdam; Institute of Earth and Environmental Science, Potsdam, Germany;Batalla, Ramon;University of Lleida, Department of Environment and Soil Sciences, Fluvial Dynamics Research Group, Lleida, Spain;Bronstert, Axel;University of Potsdam, Institute of Earth and Environmental Science, Potsdam, Germany;Hydro-sedimentological dataset for the mesoscale      mountainous Is\u00e1bena catchment, NE Spain;GFZ Data Services;2017;rainfall;discharge;suspended sediment concentration;soil spectroscopy;fingerprint properties;meso-scale;Francke, Till;University of Potsdam, Institute of Earth and Environmental Science, Potsdam, Germany;Francke, Till;University of Potsdam, Institute of Earth and Environmental Science, Potsdam, Germany;Francke, Till;University of Potsdam, Institute of Earth and Environmental Science, Potsdam, Germany;Foerster, Saskia;GFZ German Research Centre for Geosciences, Section 1.4 Remote Sensing, Potsdam, Germany;Foerster, Saskia;GFZ German Research Centre for Geosciences, Section 1.4 Remote Sensing, Potsdam, Germany;Brosinsky, Arlena; University of Potsdam, Institute of Earth and Environmental Science, Potsdam, Germany; GFZ German Research Centre for Geosciences, Section 1.4 Remote Sensing, Potsdam, Germany;Sommerer, Erik;GFZ German Research Centre for Geosciences, Section 5.4 Hydrology, Potsdam, Germany;L\u00f3pez-Taraz\u00f3n, Jos\u00e9 A.;University of Potsdam, Institute of Earth and Environmental Science, Potsdam, Germany; Liverpool John Moores University, School of Natural Sciences and Psychology, Liverpool, UK; University of Lleida, Department of Environment and Soil Sciences, Fluvial Dynamics Research Group, Lleida, Spain; University of the Balearic Islands, Department of Geography, Palma, Spain;G\u00fcntner, Andreas;GFZ German Research Centre for Geosciences, Section 5.4 Hydrology; Potsdam, Germany; University of Potsdam; Institute of Earth and Environmental Science, Potsdam, Germany;Batalla, Ramon;University of Lleida, Department of Environment and Soil Sciences, Fluvial Dynamics Research Group, Lleida, Spain;Batalla, Ramon;University of Lleida, Department of Environment and Soil Sciences, Fluvial Dynamics Research Group, Lleida, Spain;Bronstert, Axel;University of Potsdam, Institute of Earth and Environmental Science, Potsdam, Germany;Elger, Kirsten;0000-0001-5140-8602;GFZ German Research Center for Geosciences;German Research Foundation;German Research Foundation;Helmholtz Centre for Environmental Research (UFZ);Marie Curie Intra-European Fellowship;Economy and Knowledge Department of the Catalan Government;Ebro Water Authorities;Ebro Water Authorities;2017-06-13;2010/2016;eng;Dataset;DOI of ESSD Paper;10.1007/s11368-014-0927-z;10.1007/s11368-014-0925-1;10.1007/s11368-014-0992-3;10.1007/s11368-014-0990-5;10.1007/s11368-014-0961-x;10.1016/j.geomorph.2011.08.020;http://his.cuahsi.org/documents/ODM1.1DesignSpecifications.pdf;190270085 Bytes;7 Files;application/octet-stream;application/pdf;application/octet-stream;application/octet-stream;application/octet-stream;application/octet-stream;application/x-zip-compressed;CC BY 4.0;A comprehensive hydro-sedimentological dataset for the Is\u00e1bena catchment, NE Spain, for the period 2010-2016 is presented to analyse water and sediment fluxes in a Mediterranean meso-scale catchment. The dataset includes rainfall data from twelve rain gauges distributed within the study area complemented by meteorological data of twelve official meteo-stations. It comprises discharge data derived from water stage measurements as well as suspended sediment concentrations (SSC) at six gauging stations of the Is\u00e1bena river and its sub-catchments. ;42.1256 0.237 42.5807 0.6581;Is\u00e1bena catchment",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "7e3f69c6-58d2-5e37-818f-05e88d792513",
-    "notes": [
-        "A comprehensive hydro-sedimentological dataset for the Is\u00e1bena catchment, NE Spain, for the period 2010-2016 is presented to analyse water and sediment fluxes in a Mediterranean meso-scale catchment. The dataset includes rainfall data from twelve rain gauges distributed within the study area complemented by meteorological data of twelve official meteo-stations. It comprises discharge data derived from water stage measurements as well as suspended sediment concentrations (SSC) at six gauging stations of the Is\u00e1bena river and its sub-catchments. "
-    ],
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6287"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[0.237,42.1256],[0.237,42.5807],[0.6581,42.5807],[0.6581,42.1256],[0.237,42.1256]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "rainfall"
-        },
-        {
-            "name": "discharge"
-        },
-        {
-            "name": "suspended sediment concentration"
-        },
-        {
-            "name": "soil spectroscopy"
-        },
-        {
-            "name": "fingerprint properties"
-        },
-        {
-            "name": "meso-scale"
-        }
-    ],
-    "title": [
-        "Hydro-sedimentological dataset for the mesoscale      mountainous Is\u00e1bena catchment, NE Spain"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/7f8f889a-8323-5220-be54-0365ed6b1f47.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/7f8f889a-8323-5220-be54-0365ed6b1f47.json
deleted file mode 100644
index 2c662323..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/7f8f889a-8323-5220-be54-0365ed6b1f47.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6400",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6400"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6400;2018-05-15T10:57:50Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2018.011;Francke, Till;Till;Francke;University of Potsdam, Institute of Earth and Environmental Science, Potsdam, Germany;Foerster, Saskia;Saskia;Foerster;GFZ German Research Centre for Geosciences, Section 1.4 Remote Sensing, Potsdam, Germany;Brosinsky, Arlena;Arlena;Brosinsky; University of Potsdam, Institute of Earth and Environmental Science, Potsdam, Germany; GFZ German Research Centre for Geosciences, Section 1.4 Remote Sensing, Potsdam, Germany;Sommerer, Erik;Erik;Sommerer;GFZ German Research Centre for Geosciences, Section 5.4 Hydrology, Potsdam, Germany;L\u00f3pez-Taraz\u00f3n, Jos\u00e9 A.;Jos\u00e9 A.;L\u00f3pez-Taraz\u00f3n;University of Potsdam, Institute of Earth and Environmental Science, Potsdam, Germany; Liverpool John Moores University, School of Natural Sciences and Psychology, Liverpool, UK; University of Lleida, Department of Environment and Soil Sciences, Fluvial Dynamics Research Group, Lleida, Spain; University of the Balearic Islands, Department of Geography, Palma, Spain;G\u00fcntner, Andreas;Andreas;G\u00fcntner;GFZ German Research Centre for Geosciences, Section 5.4 Hydrology; Potsdam, Germany; University of Potsdam; Institute of Earth and Environmental Science, Potsdam, Germany;Batalla, Ramon;Ramon;Batalla;University of Lleida, Department of Environment and Soil Sciences, Fluvial Dynamics Research Group, Lleida, Spain;Bronstert, Axel;Axel;Bronstert;University of Potsdam, Institute of Earth and Environmental Science, Potsdam, Germany;Hydro-sedimentological dataset for the mesoscale      mountainous Is\u00e1bena catchment, NE Spain;GFZ Data Services;2018;rainfall;discharge;suspended sediment concentration;soil spectroscopy;fingerprint properties;meso-scale;Francke, Till;Till;Francke;University of Potsdam, Institute of Earth and Environmental Science, Potsdam, Germany;Francke, Till;Till;Francke;University of Potsdam, Institute of Earth and Environmental Science, Potsdam, Germany;Francke, Till;Till;Francke;University of Potsdam, Institute of Earth and Environmental Science, Potsdam, Germany;Foerster, Saskia;Saskia;Foerster;GFZ German Research Centre for Geosciences, Section 1.4 Remote Sensing, Potsdam, Germany;Foerster, Saskia;Saskia;Foerster;GFZ German Research Centre for Geosciences, Section 1.4 Remote Sensing, Potsdam, Germany;Brosinsky, Arlena;Arlena;Brosinsky; University of Potsdam, Institute of Earth and Environmental Science, Potsdam, Germany; GFZ German Research Centre for Geosciences, Section 1.4 Remote Sensing, Potsdam, Germany;Sommerer, Erik;Erik;Sommerer;GFZ German Research Centre for Geosciences, Section 5.4 Hydrology, Potsdam, Germany;L\u00f3pez-Taraz\u00f3n, Jos\u00e9 A.;Jos\u00e9 A.;L\u00f3pez-Taraz\u00f3n;University of Potsdam, Institute of Earth and Environmental Science, Potsdam, Germany; Liverpool John Moores University, School of Natural Sciences and Psychology, Liverpool, UK; University of Lleida, Department of Environment and Soil Sciences, Fluvial Dynamics Research Group, Lleida, Spain; University of the Balearic Islands, Department of Geography, Palma, Spain;G\u00fcntner, Andreas;Andreas;G\u00fcntner;GFZ German Research Centre for Geosciences, Section 5.4 Hydrology; Potsdam, Germany; University of Potsdam; Institute of Earth and Environmental Science, Potsdam, Germany;Batalla, Ramon;Ramon;Batalla;University of Lleida, Department of Environment and Soil Sciences, Fluvial Dynamics Research Group, Lleida, Spain;Batalla, Ramon;Ramon;Batalla;University of Lleida, Department of Environment and Soil Sciences, Fluvial Dynamics Research Group, Lleida, Spain;Bronstert, Axel;Axel;Bronstert;University of Potsdam, Institute of Earth and Environmental Science, Potsdam, Germany;Elger, Kirsten;Kirsten;Elger;0000-0001-5140-8602;GFZ German Research Center for Geosciences;Ebro Water Authorities;German Research Foundation;Helmholtz Centre for Environmental Research (UFZ);Marie Curie Intra-European Fellowship;Economy and Knowledge Department of the Catalan Government;2017-06-13;2010/2016;eng;Dataset;10.5194/essd-2017-72;10.1007/s11368-014-0927-z;10.1007/s11368-014-0925-1;10.1007/s11368-014-0992-3;10.1007/s11368-014-0990-5;10.1007/s11368-014-0961-x;10.1016/j.geomorph.2011.08.020;http://his.cuahsi.org/documents/ODM1.1DesignSpecifications.pdf;10.5880/fidgeo.2017.003;183324730 Bytes;10 Files;application/x-zip-compressed;application/x-zip-compressed;application/x-zip-compressed;application/x-zip-compressed;application/x-zip-compressed;application/x-zip-compressed;application/octet-stream;application/octet-stream;application/pdf;application/x-zip-compressed;2.0;CC BY 4.0;Version history: \nThis datased is an updated version of Francke et al. (2017; http://doi.org/10.5880/fidgeo.2017.003) for a revised version of\nthis discussion paper. It contains further data collected, some of which also resulted in the revision of previous data (e.g. updated rating curves).;0.237;0.6581;42.1256;42.5807;Is\u00e1bena catchment",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "7f8f889a-8323-5220-be54-0365ed6b1f47",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6400"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/8b7ec02f-1c01-5375-8d9d-d77caec46041.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/8b7ec02f-1c01-5375-8d9d-d77caec46041.json
deleted file mode 100644
index 6163b1fc..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/8b7ec02f-1c01-5375-8d9d-d77caec46041.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6565",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6565"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6565;2018-10-25T08:20:28Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2018.022;Willingshofer, Ernst;Ernst;Willingshofer;0000-0002-9119-5557;Department of Tectonics, Faculty of Earth Sciences, Utrecht University, 3584 CD Utrecht, The Netherlands;Sokoutis, Dimitrios;Dimitrios;Sokoutis;0000-0003-0523-9785;Department of Tectonics, Faculty of Earth Sciences, Utrecht University, 3584 CD Utrecht, The Netherlands;Kleinhans, Maarten;Maarten;Kleinhans;0000-0002-9484-1673;Department of Tectonics, Faculty of Earth Sciences, Utrecht University, 3584 CD Utrecht, The Netherlands;Beekmann, Fred;Fred;Beekmann;Department of Tectonics, Faculty of Earth Sciences, Utrecht University, 3584 CD Utrecht, The Netherlands;Sch\u00f6nebeck, Jan-Michael;Jan-Michael;Sch\u00f6nebeck;GFZ German Research Centre for Geosciences, Potsdam, Germany;Warsitzka, Michael;Michael;Warsitzka;0000-0003-1774-5888;GFZ German Research Centre for Geosciences, Potsdam, Germany;Rosenau, Matthias;Matthias;Rosenau;0000-0003-1134-5381;GFZ German Research Centre for Geosciences, Potsdam, Germany;Ring-shear test data of plastic sand, a new rock analogue material used for experimental Earth Science applications at Utrecht University, The Netherlands;GFZ Data Services;2018;EPOS;Multi-scale laboratories;analogue models of geologic processes;property data of analogue modelling materials;software tools;Willingshofer, Ernst;Ernst;Willingshofer;0000-0002-9119-5557;Department of Tectonics, Faculty of Earth Sciences, Utrecht University, 3584 CD Utrecht, The Netherlands;Sokoutis, Dimitrios;Dimitrios;Sokoutis;0000-0003-0523-9785;Department of Tectonics, Faculty of Earth Sciences, Utrecht University, 3584 CD Utrecht, The Netherlands;Kleinhans, Maarten;Maarten;Kleinhans;0000-0002-9484-1673;Department of Tectonics, Faculty of Earth Sciences, Utrecht University, 3584 CD Utrecht, The Netherlands;Beekmann, Fred;Fred;Beekmann;Department of Tectonics, Faculty of Earth Sciences, Utrecht University, 3584 CD Utrecht, The Netherlands;Sch\u00f6nebeck, Jan-Michael;Jan-Michael;Sch\u00f6nebeck;GFZ German Research Centre for Geosciences, Potsdam, Germany;Warsitzka, Michael;Michael;Warsitzka;0000-0003-1774-5888;GFZ German Research Centre for Geosciences, Potsdam, Germany;Rosenau, Matthias;Matthias;Rosenau;0000-0003-1134-5381;GFZ German Research Centre for Geosciences, Potsdam, Germany;TecLab - Tectonic Modelling Laboratory (Utrecht University, The Netherlands);Utrecht University, Utrecht, The Netherlands;HelTec - Helmholtz Laboratory for Tectonic Modelling (GFZ Potsdam, Germany);GFZ German Research Centre for Geosciences, Potsdam, Germany;en;10.1016/j.icarus.2013.12.026;10.1111/sed.12358;10.1016/j.tecto.2016.01.017;10.1002/2016JB012915;10.1016/j.jsg.2015.03.008;10.1002/ceat.200303112;https://www.springer.com/de/book/9783540737674;10341089 Bytes;3 Files;application/pdf;application/x-zip-compressed;application/pdf;1;CC BY 4.0;This dataset provides friction data from ring-shear test (RST) on a plastic (polyester) sand material that has been used in flume experiments (Marra et al., 2014; Kleinhans et al., 2017) and is now used in the Tectonic Laboratory (TecLab) at Utrecht University (NL) as an analogue for brittle layers in the crust or lithosphere. Detailed information about the data, methodology and a list of files and formats is given in the data description and list of files that are included in the zip folder and also available via the DOI landing page.",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "8b7ec02f-1c01-5375-8d9d-d77caec46041",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6565"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/8eefde9f-e2fd-5eeb-8747-1cfff9a569f7.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/8eefde9f-e2fd-5eeb-8747-1cfff9a569f7.json
deleted file mode 100644
index 76a7357b..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/8eefde9f-e2fd-5eeb-8747-1cfff9a569f7.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6341",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6341"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6341;2018-09-05T10:38:51Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2017.019;Trippetta, Fabio;Fabio;Trippetta;0000-0001-8336-2194;Dipartimento di Scienze della Terra, Sapienza Universit\u00e0 di Roma;Carpenter, Brett M;Brett M;Carpenter;0000-0002-3451-2528;School of Geology and Geophysics, University of Oklahoma, Norman, OK, USA;Mollo, Silvio;Silvio;Mollo;0000-0002-1448-0282;Istituto Nazionale di Geofisica e Vulcanologia, Roma, Italy;Scuderi, Marco M.;Marco M.;Scuderi;0000-0001-5232-0792;Dipartimento di Scienze della Terra, Sapienza Universit\u00e0 di Roma;Scarlato, Piergiorgio;Piergiorgio;Scarlato;0000-0003-1933-0192;Istituto Nazionale di Geofisica e Vulcanologia, Roma, Italy;Collettini, Cristiano;Cristiano;Collettini;0000-0002-4828-2516;Dipartimento di Scienze della Terra, Sapienza Universit\u00e0 di Roma;Dataset of Physical and Transport Property Variations Within the Carbonate-Bearing Fault Zones of the Monte Maggio Fault (Central Italy);GFZ Data Services;2017;Sesmic Waves;Carbonates;Permeability;Physical properties;Elastic properties;Borehole sonic logs;Vp;Vs;Vp/Vs Ratio;Critical Rupture Length;EPOS;Multi-scale laboratories;rock and melt physical properties;Trippetta, Fabio;Fabio;Trippetta;0000-0001-8336-2194;Dipartimento di Scienze della Terra, Sapienza Universit\u00e0 di Roma;Trippetta, Fabio;Fabio;Trippetta;0000-0001-8336-2194;Dipartimento di Scienze della Terra, Sapienza Universit\u00e0 di Roma;Trippetta, Fabio;Fabio;Trippetta;0000-0001-8336-2194;Dipartimento di Scienze della Terra, Sapienza Universit\u00e0 di Roma;Trippetta, Fabio;Fabio;Trippetta;0000-0001-8336-2194;Dipartimento di Scienze della Terra, Sapienza Universit\u00e0 di Roma;HP-HT Laboratory of Experimental Volcanolgy and Geophysics (INGV, Italy);INGV, Italy;2017-11-03;en;10.1002/2017GC007097;10.1029/2011JB008352;19556 Bytes;1 Files;application/x-zip-compressed;CC BY 4.0;Here we report the raw data of the physical properties of carbonate samples collected along the Monte Maggio normal Fault (MMF), a regional structure (length ~10 km and displacement ~500 m) located within the active system of the Apennines (Italy). In particular, we report results coming from large cores (100 mm in diameter and up to 20 cm long) drilled perpendicular to the fault plane made of Calcare Massiccio (massive limestone) and Bugarone fm (limestone with 8.3 % of clay). ;12.927989959716797;12.952194213867188;42.75823057701311;42.781543233362996;Sapienza Universit\u00e0 di Roma;http://doi.org/10.13039/501100004271;From small to large, to very large: a multiscale study of the influence of fractures on physical properties of carbonate rocks",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "8eefde9f-e2fd-5eeb-8747-1cfff9a569f7",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6341"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/8f43244b-3d33-59ac-9684-f5b4a90e5c31.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/8f43244b-3d33-59ac-9684-f5b4a90e5c31.json
deleted file mode 100644
index 58b16df1..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/8f43244b-3d33-59ac-9684-f5b4a90e5c31.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6320",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6320"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6320;2018-10-25T08:06:20Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2017.005;Souloumiac, Pauline;D\u00e9partement G\u00e9osciences et Environnement Universit\u00e9 de Cergy-Pontoise, Cergy-Pontoise, France;Maillot, Bertrand;0000-0002-0495-8799;D\u00e9partement G\u00e9osciences et Environnement Universit\u00e9 de Cergy-Pontoise, Cergy-Pontoise, France;Herbert, Justin W.;Department of Geosciences University of Massachusetts Amherst Amherst, MA, United States;McBeck, Jessica A.;0000-0002-4465-5522;Physics of Geological Processes Department of Geosciences University of Oslo, Oslo, Norway;Cooke, Michele L.;0000-0002-4407-9676;Department of Geosciences University of Massachusetts Amherst Amherst, MA, United States;Supplement to \"Work optimization predicts accretionary faulting: An integration of physical and numerical experiments\";GFZ Data Services;2017;analogue modeling;accretionary wedge;digital image correlation;EPOS;multi-scale laboratories;analogue models of geologic processes;analogue modelling results;software tools;Physical Modeling Laboratory (GEC) at the Universit\u00e9 de Cergy-Pontoise;CNRS-Cergy-Pontoise University, Cergy-Pontoise, France;GECmodel - Laboratoire de mod\u00e9lisation analogique G\u00e9osciences et Environnement (CNRS-Cergy-Pontoise University, France);CNRS-Cergy-Pontoise University, Cergy-Pontoise, France;eng;Dataset;10.1002/2017JB013931;10.1016/j.jsg.2004.08.008;10.2312/GFZ.b103-06069;10.1016/j.tecto.2013.02.028;10.1016/j.jsg.2011.11.002;445003605 Bytes;2 Files;application/x-zip-compressed;application/pdf;CC BY 4.0;The data set includes photos, force measurements, and incremental displacement fields captured in experiment E240 run at the physical modeling laboratory (GEC) at the Universit\u00e9 de Cergy-Pontoise. We built the accretionary wedge using a novel sedimentation device [Maillot, 2013] that distributes sand in planar layers and creates homogeneous sandpacks. We include photos of the side of the accretionary wedge in a zipped folder (E240_sideviews). Throughout the experiment, we took a photo every 5 seconds.",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "8f43244b-3d33-59ac-9684-f5b4a90e5c31",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6320"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/8febc722-3708-58d3-843f-400dc168f1ae.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/8febc722-3708-58d3-843f-400dc168f1ae.json
deleted file mode 100644
index d73913df..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/8febc722-3708-58d3-843f-400dc168f1ae.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6593",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6593"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6593;2018-12-05T19:48:58Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2018.019;Renner, Maik;Maik;Renner;0000-0002-2992-8414;Max-Planck Institute for Biogeochemistry, Jena, Germany;Wizemann, Hans-Dieter;Hans-Dieter;Wizemann;Institut f\u00fcr Physik und Meteorologie, University Hohenheim, Stuttgart, Germany;University Hohenheim, Stuttgart, Germany;Brenner, Claire;Claire;Brenner;0000-0001-6825-7687;Institut f\u00fcr Wasserwirtschaft, Hydrologie und konstruktiven Wasserbau, Universit\u00e4t f\u00fcr Bodenkultur (BOKU), Vienna, Austria;Universit\u00e4t f\u00fcr Bodenkultur (BOKU), Vienna, Austria;Mallick, Kaniska;Kaniska;Mallick;0000-0002-2735-930X;Department Environmental Research and Innovation, Luxembourg Institute of Science and Technology (LIST), Belvaux, Grand-duchy of Luxembourg;Luxembourg Institute of Science and Technology (LIST), Belvaux, Grand-duchy of Luxembourg;Trebs, Ivonne;Ivonne;Trebs;Department Environmental Research and Innovation, Luxembourg Institute of Science and Technology (LIST), Belvaux, L-4422, Grand-duchy of Luxembourg;Luxembourg Institute of Science and Technology (LIST), Belvaux, Grand-duchy of Luxembourg;Wulfmeyer, Volker;Volker;Wulfmeyer;0000-0003-4882-2524;Institut f\u00fcr Physik und Meteorologie, Universit\u00e4t Hohenheim, 70599 Stuttgart, Germany;University Hohenheim, Stuttgart, Germany;Schulz, Karsten;Karsten;Schulz;0000-0002-6616-2876;Institut f\u00fcr Wasserwirtschaft, Hydrologie und konstruktiven Wasserbau, Universit\u00e4t f\u00fcr Bodenkultur (BOKU), Wien, 1190, Austria;Universit\u00e4t f\u00fcr Bodenkultur (BOKU), Vienna, Austria;Kleidon, Axel;Axel;Kleidon;0000-0002-3798-0730;Max-Planck Institute for Biogeochemistry, Jena, Germany;Surface energy balance at a grassland site in Luxembourg modelled by three structurally different evapotranspiration schemes;GFZ Data Services;2018;Diurnal cycle of surface heat fluxes;Surface energy balance;evapotranspiration;land-surface model;CAOS;Catchments as Organized Systems;EARTH SCIENCE > BIOSPHERE > TERRESTRIAL ECOSYSTEMS > GRASSLANDS;EARTH SCIENCE > BIOSPHERE > TERRESTRIAL ECOSYSTEMS > GRASSLANDS;EARTH SCIENCE > ATMOSPHERE > ATMOSPHERIC WATER VAPOR > EVAPOTRANSPIRATION;EARTH SCIENCE > ATMOSPHERE > ATMOSPHERIC RADIATION > HEAT FLUX;research > scientific research > meteorological research;EARTH SCIENCE > BIOSPHERE > TERRESTRIAL ECOSYSTEMS > GRASSLANDS;EARTH SCIENCE > BIOSPHERE > TERRESTRIAL ECOSYSTEMS > GRASSLANDS;EARTH SCIENCE > ATMOSPHERE > ATMOSPHERIC WATER VAPOR > EVAPOTRANSPIRATION;EARTH SCIENCE > ATMOSPHERE > ATMOSPHERIC RADIATION > HEAT FLUX;research > scientific research > meteorological research;Renner, Maik;Maik;Renner;0000-0002-2992-8414;Max-Planck Institute for Biogeochemistry, Jena, Germany;Wizemann, Hans-Dieter;Hans-Dieter;Wizemann;Institut f\u00fcr Physik und Meteorologie, University Hohenheim, Stuttgart, Germany;University Hohenheim, Stuttgart, Germany;Brenner, Claire;Claire;Brenner;0000-0001-6825-7687;Institut f\u00fcr Wasserwirtschaft, Hydrologie und konstruktiven Wasserbau, Universit\u00e4t f\u00fcr Bodenkultur (BOKU), Vienna, Austria;Universit\u00e4t f\u00fcr Bodenkultur (BOKU), Vienna, Austria;Mallick, Kaniska;Kaniska;Mallick;0000-0002-2735-930X;Department Environmental Research and Innovation, Luxembourg Institute of Science and Technology (LIST), Belvaux, Grand-duchy of Luxembourg;Luxembourg Institute of Science and Technology (LIST), Belvaux, Grand-duchy of Luxembourg;Trebs, Ivonne;Ivonne;Trebs;Department Environmental Research and Innovation, Luxembourg Institute of Science and Technology (LIST), Belvaux, L-4422, Grand-duchy of Luxembourg;Luxembourg Institute of Science and Technology (LIST), Belvaux, Grand-duchy of Luxembourg;Wulfmeyer, Volker;Volker;Wulfmeyer;0000-0003-4882-2524;Institut f\u00fcr Physik und Meteorologie, Universit\u00e4t Hohenheim, 70599 Stuttgart, Germany;University Hohenheim, Stuttgart, Germany;Schulz, Karsten;Karsten;Schulz;0000-0002-6616-2876;Institut f\u00fcr Wasserwirtschaft, Hydrologie und konstruktiven Wasserbau, Universit\u00e4t f\u00fcr Bodenkultur (BOKU), Wien, 1190, Austria;Universit\u00e4t f\u00fcr Bodenkultur (BOKU), Vienna, Austria;Kleidon, Axel;Axel;Kleidon;0000-0002-3798-0730;Max-Planck Institute for Biogeochemistry, Jena, Germany;2018-08-27;2015-06-11T10:30:00/2015-07-23T06:30:00;en;10.5194/hess-2018-310;10.5880/fidgeo.2018.024;10.1080/01431161.2017.1280202;10.5194/hess-20-4237-2016;386156 Bytes;1 Files;application/x-zip-compressed;CC BY 4.0;This dataset provides half-hourly model output of sensible and latent heat fluxes simulated by three structurally different evapotranspiration schemes for a temperate grassland site in Luxembourg. All models use surface energy and meteorological observations as input. The observational data were collected during a field campaign in June and July 2015 and are distributed as complementary dataset by Wizemann et al., 2018. Two models are based on a parameterization of the sensible heat flux (OSEB, TSEB; see Brenner et al., 2017) and one model (STIC 1.2, Mallick et al., 2016) is a modification of the Penman-Monteith formulation using skin temperature as additional input variable. For details please see the reference article Renner et al., 2018 HESSD. The data is provided as comma-separated-values (csv) format in a long table format. Columns represent Date, Time, variable, value, source. The column \u201cvariable\u201d sets the name of the variable (following CEOP standards, https://www.eol.ucar.edu/field_projects/ceop). Column \u201csource\u201d describes the data source with an acronym representing the models (OSEB, TSEB, STIC).;5.803196525386966;49.77951003393976;Deutsche Forschungsgemeinschaft;http://doi.org/10.13039/501100001659;FOR 1598;From Catchments as Organised Systems to Models based on Dynamic Functional Units \u2013 CAOS;Deutsche Forschungsgemeinschaft;http://doi.org/10.13039/501100001659;KL 2168/2-1;Understanding and characterizing land surface-atmosphere exchange and feedbacks;Fonds National de la Recherche Luxembourg;http://doi.org/10.13039/501100001866;INTER/DFG/14/02;CAOS-2 project grant;Austrian Science Fund;http://doi.org/10.13039/501100002428",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "8febc722-3708-58d3-843f-400dc168f1ae",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6593"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/90029ec9-dd10-5e6a-b067-7583054a77e6.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/90029ec9-dd10-5e6a-b067-7583054a77e6.json
deleted file mode 100644
index 35af22f9..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/90029ec9-dd10-5e6a-b067-7583054a77e6.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "Smith, Taylor",
-        "Bodo Bookhagen"
-    ],
-    "Contributor": [
-        "Smith, Taylor",
-        "Bodo Bookhagen"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.5880/fidgeo.2017.006",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "application/x-zip-compressed"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6322",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6322"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "GFZ German Research Center for Geosciences"
-    ],
-    "Rights": [
-        "CC BY 4.0"
-    ],
-    "SpatialCoverage": "(25N-45N,68E-95E)",
-    "TemporalCoverage": [
-        "/2",
-        "2017-06-29",
-        "1987-10-01/2016-10-01"
-    ],
-    "author": [
-        "Smith, Taylor",
-        "Bodo Bookhagen"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6322;2017-10-15T08:53:35Z;DOIDB;DOIDB.FID;false;3;DOIDB.FID;10.5880/fidgeo.2017.006;Smith, Taylor;0000-0002-6763-7204;Universitat Potsdam;Bodo Bookhagen;0000-0003-1323-6453;Universitat Potsdam;Snowmelt Paramaters, 1987-2016, High Mountain Asia;GFZ German Research Center for Geosciences;2017;Snow;SWE;Snowmelt;Cryosphere;High Mountain Asia;Smith, Taylor;0000-0002-6763-7204;Universitat Potsdam;Bodo Bookhagen;0000-0003-1323-6453;Universitat Potsdam;/2;2017-06-29;1987-10-01/2016-10-01;en;10.5194/tc-11-2329-2017;794638 Bytes;1 Files;application/x-zip-compressed;1.0;CC BY 4.0;This data resource contains 9 files, created as part of the work \"Spatio-temporal Patterns of High Mountain Asia's Snowmelt Season Identified with an Automated Snowmelt Detection Algorithm, 1987-2016\" by T. Smith, B. Bookhagen, and A. Rheinwalt (http://doi.org/10.5194/tc-2017-67). Full description of the methods can be found in the published paper. Data tracks the onset, end, and length of the snowmelt period in High Mountain Asia over the period 1987-2016. ;25 67.5 45 95;High Mountain Asia, 1987-2016",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "90029ec9-dd10-5e6a-b067-7583054a77e6",
-    "notes": [
-        "This data resource contains 9 files, created as part of the work \"Spatio-temporal Patterns of High Mountain Asia's Snowmelt Season Identified with an Automated Snowmelt Detection Algorithm, 1987-2016\" by T. Smith, B. Bookhagen, and A. Rheinwalt (http://doi.org/10.5194/tc-2017-67). Full description of the methods can be found in the published paper. Data tracks the onset, end, and length of the snowmelt period in High Mountain Asia over the period 1987-2016. "
-    ],
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6322"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[67.5,25],[67.5,45],[95,45],[95,25],[67.5,25]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Snow"
-        },
-        {
-            "name": "SWE"
-        },
-        {
-            "name": "Snowmelt"
-        },
-        {
-            "name": "Cryosphere"
-        },
-        {
-            "name": "High Mountain Asia"
-        }
-    ],
-    "title": [
-        "Snowmelt Paramaters, 1987-2016, High Mountain Asia"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/9083bd9f-75e3-5773-b763-277a8b8022fe.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/9083bd9f-75e3-5773-b763-277a8b8022fe.json
deleted file mode 100644
index e9f23bd3..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/9083bd9f-75e3-5773-b763-277a8b8022fe.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6540",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6540"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6540;2018-10-25T08:09:54Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2018.004;De Matteo, Ada;Ada;De Matteo;Universit\u00e0 degli Studi del Sannio, Dipartimento di Scienze e Tecnologie, Benevento, Italy;Corti, Giacomo;Giacomo;Corti;0000-0001-7399-4438;Consiglio Nazionale delle Ricerche (CNR), Istituto di Geoscienze e Georisorse (IGG), Sede Secondaria di Firenze, Italy;Istituto Nazionale di Geofisica e Vulcanologia, Sezione di Pisa, Italy;van Wyk de Vries, Benjamin;Benjamin;van Wyk de Vries;0000-0001-7232-0693;Universit\u00e9 Clermont Auvergne, Observatoire du Physique du Globe de Clermont, Laboratoire Magmas et Volcans, UMR6524-CNRS, Clermont-Ferrand, France;Massa, Bruno;Bruno;Massa;0000-0002-7358-1841;Universit\u00e0 degli Studi del Sannio, Dipartimento di Scienze e Tecnologie, Benevento, Italy;Istituto Nazionale di Geofisica e Vulcanologia, sezione di Napoli Osservatorio Vesuviano, Napoli, Italy;Mussetti, Giulio;Giulio;Mussetti;Dipartimento di Scienze della terra, Universit\u00e0 degli Studi di Firenze, Italy;Brittle models of fault-volcano interactions during extension;GFZ Data Services;2018;analogue modelling;extensional tectonics;normal fault pattern;volcano deformation;EPOS;multi-scale laboratories;analogue models of geologic processes;analogue modelling results;Tectonics Modelling Laboratory (IGG-CNR, Italy);IGG-CNR, University of Florence, Florence Italy;2018-02-19;en;10.1016/j.jvolgeores.2018.08.008;10.1016/j.jsg.2005.05.011;3164166 Bytes;3 Files;application/pdf;application/pdf;application/x-zip-compressed;CC BY 4.0;This dataset contains 11 top view photographs of fault pattern in sand surfaces from a series of analogue tectonic experiments run to investigate the interaction between faults and volcanic features in areas characterized by pure extension, such as in rift areas (de-Matteo_2018-004_datasets.zip: Fig 02 \u2013 Fig 12). Additionally, a figure with a sketch of the experimental setup is provided (Fig 01), a file describing experimental settings for analogue experiments (Table 1.pdf) and a file with figure captions (Figure captions.pdf). This dataset is supplementary to De Matteo et al. (2018), discussing if and how the presence of a volcanic edifice and/or of an intrusive body (i.e. a magmatic chamber) perturbs the local stress field, influencing the magnitude and the attitude of a fault pattern, in a rift zone.",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "9083bd9f-75e3-5773-b763-277a8b8022fe",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6540"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/9d5b911d-1d6e-5bd1-8716-a358fc2c9098.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/9d5b911d-1d6e-5bd1-8716-a358fc2c9098.json
deleted file mode 100644
index 13486d17..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/9d5b911d-1d6e-5bd1-8716-a358fc2c9098.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6573",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6573"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6573;2018-12-10T14:54:15Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2018.028;Zwaan, Frank;Frank;Zwaan;0000-0001-8226-2132;Institute of Geological Sciences, University of Bern;Schreurs, Guido;Guido;Schreurs;0000-0002-4544-7514;Institute of Geological Sciences, University of Bern;Gentzmann, Robert;Robert;Gentzmann;GFZ German Research Centre for Geosciences, Potsdam, Germany;Warsitzka, Michael;Michael;Warsitzka;0000-0003-1774-5888;GFZ German Research Centre for Geosciences, Potsdam, Germany;Rosenau, Matthias;Matthias;Rosenau;0000-0003-1134-5381;GFZ German Research Centre for Geosciences, Potsdam, Germany;Ring-shear test data of quartz sand from the Tectonic Modelling Lab of the University of Bern (CH);GFZ Data Services;2018;analogue models of geologic processes;EPOS;Multi-scale Laboratories;property data of analogue modelling materials;software tools;Zwaan, Frank;Frank;Zwaan;0000-0001-8226-2132;Institute of Geological Sciences, University of Bern;Schreurs, Guido;Guido;Schreurs;0000-0002-4544-7514;Institute of Geological Sciences, University of Bern;Gentzmann, Robert;Robert;Gentzmann;GFZ German Research Centre for Geosciences, Potsdam, Germany;Warsitzka, Michael;Michael;Warsitzka;0000-0003-1774-5888;GFZ German Research Centre for Geosciences, Potsdam, Germany;Rosenau, Matthias;Matthias;Rosenau;0000-0003-1134-5381;GFZ German Research Centre for Geosciences, Potsdam, Germany;Tectonic Modelling Laboratory at the Institute for Geological Sciences (TecLab Bern, Switzerland);Institute of Geological Sciences of the University of Bern, Switzerland;HelTec - Helmholtz Laboratory for Tectonic Modelling (GFZ German Research Centre for Geosciences, Germany);GFZ German Research Centre for Geosciences, Potsdam, Germany;en;10.1016/j.tecto.2016.02.036;10.1190/INT-2016-0063.1;10.1016/j.gloplacha.2017.11.002;10.1016/j.tecto.2016.01.017;10.1002/2016JB012915;10.1016/j.jsg.2015.03.008;10.1002/ceat.200303112;https://www.springer.com/de/book/9783540737674;2237044 Bytes;3 Files;application/octet-stream;application/pdf;application/pdf;1;CC BY 4.0;This dataset provides internal and basal (wall) friction data from ring-shear tests (RST) on a quartz sand material that has been used in tectonic experiments in Zwaan et al. (2016, 2017), Zwaan and Scheurs (2017) and in the Tectonic Modelling Lab of the University of Bern (CH) as an analogue for brittle layers in the crust or lithosphere. The material has been characterized by means of internal and basal friction coefficients \u03bc and cohesions C as a remote service by the Helmholtz Laboratory for Tectonic Modelling (HelTec) at the GFZ German Research Centre for Geosciences in Potsdam for the Tectonic Modelling Lab of the University of Bern (UB).",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "9d5b911d-1d6e-5bd1-8716-a358fc2c9098",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6573"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/9d8002d7-eaa0-5347-980b-036e7976441a.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/9d8002d7-eaa0-5347-980b-036e7976441a.json
deleted file mode 100644
index ff61ff07..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/9d8002d7-eaa0-5347-980b-036e7976441a.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6574",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6574"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6574;2019-01-22T07:08:21Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2017.009;Sembroni, Andrea;0000-0003-4672-6125;Department of Science, Roma Tre University, Rome, Italy;Universit\u00e1 degli studi \"Roma TRE, Rome, Italy;Kiraly, Agnes;0000-0002-8407-1038;Department of Science, Roma Tre University, Rome, Italy;Universit\u00e1 degli studi \"Roma TRE, Rome, Italy;Faccenna, Claudio;0000-0003-0765-4165;Department of Science, Roma Tre University, Rome, Italy;Universit\u00e1 degli studi \"Roma TRE, Rome, Italy;Funiciello, Francesca;0000-0001-7900-8272;Department of Science, Roma Tre University, Rome, Italy;Universit\u00e1 degli studi \"Roma TRE, Rome, Italy;Becker, Thorsten W.;0000-0002-5656-4564;Institute for Geophysics, Jackson School of Geosciences, University Texas at Austin, Austin, Texas, USA;University Texas at Austin, Austin, Texas, USA;Globig, Jan;0000-0002-9312-8980;Institute of Earth Sciences Jaume Almera (ICTJA-CSIC), Barcelona, Spain;Fernandez, Manuel;0000-0002-4487-2359;Institute of Earth Sciences Jaume Almera (ICTJA-CSIC), Barcelona, Spain;Supplementary material for analogue experiments on the impact of the lithosphere on dynamic topography;GFZ Data Services;2017;Mantle Plume;EPOS;Multi-scale laboratories;analogue models of geologic processes;analogue modelling results;Sembroni, Andrea;0000-0003-4672-6125;Department of Science, Roma Tre University, Rome, Italy;Universit\u00e1 degli studi \"Roma TRE, Rome, Italy;Sembroni, Andrea;0000-0003-4672-6125;Department of Science, Roma Tre University, Rome, Italy;Universit\u00e1 degli studi \"Roma TRE, Rome, Italy;Kiraly, Agnes;0000-0002-8407-1038;Department of Science, Roma Tre University, Rome, Italy;Universit\u00e1 degli studi \"Roma TRE, Rome, Italy;Faccenna, Claudio;0000-0003-0765-4165;Department of Science, Roma Tre University, Rome, Italy;Universit\u00e1 degli studi \"Roma TRE, Rome, Italy;Faccenna, Claudio;0000-0003-0765-4165;Department of Science, Roma Tre University, Rome, Italy;Universit\u00e1 degli studi \"Roma TRE, Rome, Italy;Funiciello, Francesca;0000-0001-7900-8272;Department of Science, Roma Tre University, Rome, Italy;Universit\u00e1 degli studi \"Roma TRE, Rome, Italy;Becker, Thorsten W.;0000-0002-5656-4564;Institute for Geophysics, Jackson School of Geosciences, University Texas at Austin, Austin, Texas, USA;University Texas at Austin, Austin, Texas, USA;Globig, Jan;0000-0002-9312-8980;Institute of Earth Sciences Jaume Almera (ICTJA-CSIC), Barcelona, Spain;Fernandez, Manuel;0000-0002-4487-2359;Institute of Earth Sciences Jaume Almera (ICTJA-CSIC), Barcelona, Spain;Laboratory of Experimental Tectonics (University of Roma TRE,  Italy);Universit\u00e1 degli studi \"Roma TRE, Rome, Italy;en;10.1002/2017GL072668;1594259 Bytes;3 Files;application/octet-stream;application/pdf;application/pdf;CC BY 4.0;We present videos and figures from 22 scaled analogue models used to investigate the interactions between a density anomaly rising in the mantle and the lithosphere in a Newtonian system.",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "9d8002d7-eaa0-5347-980b-036e7976441a",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6574"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/a6f75629-198f-5f46-9b18-0f2d910b5a4d.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/a6f75629-198f-5f46-9b18-0f2d910b5a4d.json
deleted file mode 100644
index 0b4a048a..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/a6f75629-198f-5f46-9b18-0f2d910b5a4d.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6369",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6369"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6369;2018-09-13T13:09:41Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2018.002;Natho, Stephanie;Stephanie;Natho;University of Potsdam, Potsdam, Germany;Thieken, Annegret;Annegret;Thieken;0000-0001-7068-2615;University of Potsdam, Potsdam, Germany;M. DELENAH Modelling Direct Economic LossEs caused by Natural Hazards;GFZ Data Services;2018;flash floods;hail storms;wind storms;national scale;Sendai Framework;direct economic loss;floods;macro scale;UNISDR;Natho, Stephanie;Stephanie;Natho;University of Potsdam, Potsdam, Germany;Thieken, Annegret;Annegret;Thieken;0000-0001-7068-2615;University of Potsdam, Potsdam, Germany;2017;1984-01-01/2017-12-31;en;https://www.unisdr.org/we/inform/publications/54970;https://www.preventionweb.net/documents/framework/Concept%20Paper%20-%20Direct%20Economic%20Loss%20Indicator%20methodology%2011%20November%202015.pdf;10.1016/j.ijdrr.2018.03.008;http://daten.ktbl.de/sdb/source.do;jsessionid=04E49F6CF7BF2B8D286D1CE42CBFC9FE;10.5880/fidgeo.2018.020;994880 Bytes;2 Files;application/pdf;application/vnd.ms-excel.sheet.macroEnabled.12;CC BY 4.0;Version history:;5.4931640625;15.29296875;47.15984001304432;55.02802211299252;Deutsche Forschungsgemeinschaft;http://doi.org/10.13039/501100001659;GRK 2043/1;Research Training Group \"Natural Hazards and Risks in a Changing World\"",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "a6f75629-198f-5f46-9b18-0f2d910b5a4d",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6369"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/a6f90995-4d60-5bbd-a3a9-f100ff6fb5f2.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/a6f90995-4d60-5bbd-a3a9-f100ff6fb5f2.json
deleted file mode 100644
index 7619e29e..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/a6f90995-4d60-5bbd-a3a9-f100ff6fb5f2.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6604",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6604"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6604;2018-12-21T07:38:25Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2018.029;Broerse, Taco;Taco;Broerse;0000-0002-3235-0844;Utrecht University.Utrecht, The Netherlands;Norder, Ben;Ben;Norder;0000-0003-2960-0053;Delft University of Technology.Delft, The Netherlands;Picken, Stephen;Stephen;Picken;0000-0002-6003-518X;Delft University of Technology.Delft, The Netherlands;Govers, Rob;Rob;Govers;0000-0001-7148-8857;Utrecht University.Utrecht, The Netherlands;Willingshofer, Ernst;Ernst;Willingshofer;0000-0002-9119-5557;Utrecht University.Utrecht, The Netherlands;Sokoutis, Dimitrios;Dimitrios;Sokoutis;0000-0003-0523-9785;Utrecht University.Utrecht, The Netherlands;Data supplement to: New analogue materials for nonlinear lithosphere rheology, with an application to slab break-off;GFZ Data Services;2018;analogue models of geologic processes;EPOS;Multi-scale laboratories;power-law rheology;on-linear rheology;anelasticity;plasticine;silicone polymer;rheology;PDMS;EARTH SCIENCE > SOLID EARTH > TECTONICS > PLATE TECTONICS > STRAIN;Plasticine;Silicon/Silly putty/PDMS;Iron Powder;Rheometer;Viscosity;Shear modulus;Broerse, Taco;Taco;Broerse;0000-0002-3235-0844;Utrecht University.Utrecht, The Netherlands;TecLab - Tectonic Modelling Laboratory (Utrecht University, The Netherlands);Utrecht University, Utrecht, The Netherlands;eng;Dataset;10.1016/j.tecto.2018.12.007;10.1016/j.jsg.2007.10.009;10.1016/0191-8141(87)90028-9;10.1016/0040-1951(86)90208-8;10.1016/j.jsg.2003.07.005;2 Files;application/octet-stream;application/octet-stream;CC BY 4.0;This dataset provides strain and strain rate data on mixtures of plasticine, silicone oils and iron powder that has been used in slab break-of analogue experiments in the Tectonic Laboratory (TecLab) at Utrecht University (NL) as an analogue for viscously deforming lithosphere. The materials have been analyzed in a creep and recovery test, applying a parallel plate setup using an AR-G2 rheometer (by TA Instruments).",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "a6f90995-4d60-5bbd-a3a9-f100ff6fb5f2",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6604"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/ac68a44d-652a-59cc-a1fb-e33f453a5970.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/ac68a44d-652a-59cc-a1fb-e33f453a5970.json
deleted file mode 100644
index 2a28a346..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/ac68a44d-652a-59cc-a1fb-e33f453a5970.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6603",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6603"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6603;2018-12-21T07:37:57Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2018.021;McBeck, Jessica;Jessica;McBeck;0000-0002-4465-5522;University of Oslo;Cooke, Michele;Michele;Cooke;0000-0002-4407-9676;University of Massachusetts, Amherst;Souloumiac, Pauline;Pauline;Souloumiac;Universit\u00e9 de Cergy-Pontoise;Maillot, Bertrand;Bertrand;Maillot;Universit\u00e9 de Cergy-Pontoise;Mary, Baptiste;Baptiste;Mary;Universit\u00e9 de Cergy-Pontoise;Supplement to: The influence of detachment strength on the evolving deformational energy budget of physical accretionary prisms;GFZ Data Services;2018;work budget;detachment strength;frictional work;off-fault deformation;EPOS;multi-scale laboratories;analogue models of geologic processes;analogue modelling results;EARTH SCIENCE > SOLID EARTH > TECTONICS > PLATE TECTONICS > FAULT MOVEMENT;EARTH SCIENCE > SOLID EARTH > GEOMORPHIC LANDFORMS/PROCESSES > TECTONIC PROCESSES;tectonic setting > plate margin setting > subduction zone setting;tectonic process > subduction;tectonic process > accretion;fault > reverse fault;detachment fault;Sand;Sandbox > Sandbox (meter scale);Force sensor;High frame rate camera;Young modulus;McBeck, Jessica;Jessica;McBeck;0000-0002-4465-5522;University of Oslo;Cooke, Michele;Michele;Cooke;0000-0002-4407-9676;University of Massachusetts, Amherst;Souloumiac, Pauline;Pauline;Souloumiac;Universit\u00e9 de Cergy-Pontoise;Maillot, Bertrand;Bertrand;Maillot;Universit\u00e9 de Cergy-Pontoise;Mary, Baptiste;Baptiste;Mary;Universit\u00e9 de Cergy-Pontoise;GECmodel - Laboratoire de mod\u00e9lisation analogique G\u00e9osciences et Environnement (CNRS-Cergy-Pontoise University, France );CNRS-Cergy-Pontoise University, Cergy-Pontoise, France ;2018-10;2016-10;en;10.5194/se-9-1421-2018;2 Files;application/octet-stream;application/octet-stream;1;CC BY 4.0;Tracking the evolution of the deformational energy budget within accretionary systems provides insight into the driving mechanisms that control fault development. To quantify the impact of these mechanisms on overall system efficiency, we estimate energy budget components as the first thrust fault pair develops in dry-sand accretion analogue experiments.;National Science Foundation;http://doi.org/10.13039/501100008982;American Association of Petroleum Geologists;http://doi.org/10.13039/100009301",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "ac68a44d-652a-59cc-a1fb-e33f453a5970",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6603"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/bbbc1858-4efe-5dba-a85d-168f0db3badb.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/bbbc1858-4efe-5dba-a85d-168f0db3badb.json
deleted file mode 100644
index 9b8025bc..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/bbbc1858-4efe-5dba-a85d-168f0db3badb.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6384",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6384"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6384;2018-10-04T11:10:50Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fid.2018.006;Niemeijer, Andre;Andre;Niemeijer;0000-0003-3983-9308;Utrecht University - Department of Earth Sciences;Velocity-dependent slip weakening by the combined operation of pressure solution and foliation development;GFZ Data Services;2018;Friction;Hydrotherrmal;Foliation;Pressure solution;Quartz-muscovite;EPOS;European Plate Observing System;multi-scale laboratories;rock and melt physical properties;Niemeijer, Andre;Andre;Niemeijer;0000-0003-3983-9308;Utrecht University - Department of Earth Sciences;Niemeijer, Andre;Andre;Niemeijer;0000-0003-3983-9308;Utrecht University - Department of Earth Sciences;Niemeijer, Andre;Andre;Niemeijer;0000-0003-3983-9308;Utrecht University - Department of Earth Sciences;Experimental rock deformation/HPT-Lab (Utrecht University, The Netherlands);Utrecht University, The Netherlands;2018-03-01;eng;10.1038/s41598-018-22889-3;1 Files;application/zip;CC BY 4.0;Phyllosilicate-bearing faults are characterized by an anastomosing foliation with intervening hard clasts and are believed to be long-term weak structures. Here, I present results of sliding experiments on gouges of 80 wt% quartz and 20 wt% muscovite, sheared under hydrothermal conditions at constant velocity. The results show that significant strengthening occurs over a narrow range of sliding velocities (0.03-1* m-6/s). At the lowest velocity investigated, weakness is achieved after a considerable sliding distance of over 20 mm with friction reaching a value of 0.3. Microstructural observations and the application of existing models point to the operation of frictional-viscous flow (FVF), through the serial operation of frictional sliding over a weak foliation and pressure solution of intervening clasts, resulting in low frictional strength and pronounced velocity-strengthening. At higher velocities, grain size reduction becomes dominant in a localized zone, which results in disruption of the foliation and the cessation of the FVF mechanism. In natural settings, earthquakes originating elsewhere on the fault would be rapidly arrested when encountering a foliated part of the fault deforming via FVF. Furthermore, pulses of elevated slip velocity would lead to grain size reduction which would destroy the foliation and cause a long-term strengthening of the fault.;FP7 Ideas: European Research Council;http://doi.org/10.13039/100011199;335915;Seismic;Netherlands Organization for Scientific Research;854.12.011;Vidi",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "bbbc1858-4efe-5dba-a85d-168f0db3badb",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6384"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/c096a9e8-0eb8-5a8b-a886-6fcac8ab35ce.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/c096a9e8-0eb8-5a8b-a886-6fcac8ab35ce.json
deleted file mode 100644
index 2cfe4165..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/c096a9e8-0eb8-5a8b-a886-6fcac8ab35ce.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6570",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6570"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6570;2018-12-10T14:29:04Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2018.023;Zwaan, Frank;Frank;Zwaan;0000-0001-8226-2132;Institut f\u00fcr Geologie, Universit\u00e4t Bern, Switzerland;Schreurs, Guido;Guido;Schreurs;0000-0003-1212-4978;Institut f\u00fcr Geologie, Universit\u00e4t Bern, Switzerland;Ritter, Malte;Malte;Ritter;0000-0003-1212-4978;GFZ German Research Centre for Geosciences, Potsdam, Germany;Santimano, Tasca;Tasca;Santimano;0000-0002-8080-9154;GFZ German Research Centre for Geosciences, Potsdam, Germany;Rosenau, Matthias;Matthias;Rosenau;0000-0003-1134-5381;GFZ German Research Centre for Geosciences, Potsdam, Germany;Rheology of PDMS-corundum sand mixtures from the Tectonic Modelling Lab of the University of Bern (CH);GFZ Data Services;2018;analogue models of geologic processes;EPOS;Multi-scale Laboratories;property data of analogue modelling materials;software tools;Tectonic Modelling Laboratory at the Institute for Geological Sciences (TecLab Bern, Switzerland);Institute of Geological Sciences of the University of Bern, Switzerland;HelTec - Helmholtz Laboratory for Tectonic Modelling (GFZ Potsdam, Germany);GFZ German Research Centre for Geosciences, Potsdam, Germany;en;10.1016/j.tecto.2016.02.036;10.1190/INT-2016-0063.1;10.1016/j.gloplacha.2017.11.002;http://www.mate.tue.nl/~wyss/softwiki/doku.php?id=equipment:antonpaar501-rheometer;10.1016/j.jsg.2006.05.004;10.1016/j.tecto.2015.11.028;10.5880/GFZ.4.1.2016.001;1316271 Bytes;3 Files;application/pdf;application/octet-stream;application/pdf;1;CC BY 4.0;This dataset provides rheometric data of silicone (Polydimethylsiloxane, PDMS SGM36)-corundum sand mixtures used for analogue modelling in Zwaan et al. (2016, 2017), Zwaan and Schreurs (2017) and in the Tectonic Modelling Lab of the Institute of Geological Sciences at the University of Bern (CH). The PDMS is produced by Dow Corning and its characteristics have been described by e.g. Rudolf et al. (2016a,b). The corundum sand (Normalkorund Braun 95.5% F120 by Carlo Bernasconi AG: https://www.carloag.ch/shop/catalog/product/view/id/643), has a grainsize of 0.088-0.125 mm and a specific density of 3.96 g cm^-3. Further rheological characteristics are described by Panien et al. (2006). The density of the tested materials ranges between 1 (pure PDMS) and 1.6 g cm^-3 (increasing corundum sand content in mixture). The material samples have been analysed in the Helmholtz Laboratory for Tectonic Modelling (HelTec) at GFZ German Research Centre for Geosciences in Potsdam using an Anton Paar Physica MCR 301 rheometer in a plate-plate configuration at room temperature. Rotational (controlled shear rate) tests with shear rates varying from 10^-4 to 10^-1 s^-1 were performed.",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "c096a9e8-0eb8-5a8b-a886-6fcac8ab35ce",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6570"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/c110292b-f98b-5578-a193-4c236fef7e4f.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/c110292b-f98b-5578-a193-4c236fef7e4f.json
deleted file mode 100644
index 6e71d7a9..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/c110292b-f98b-5578-a193-4c236fef7e4f.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6564",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6564"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6564;2018-09-13T15:40:48Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2018.020;Natho, Stephanie;Stephanie;Natho;University of Potsdam, Potsdam, Germany;Thieken, Annegret;Annegret;Thieken;0000-0001-7068-2615;University of Potsdam, Potsdam, Germany;M. DELENAH Modelling Direct Economic LossEs caused by Natural Hazards;GFZ Data Services;2018;flash floods;hail storms;wind storms;national scale;Sendai Framework;direct economic loss;floods;macro scale;UNISDR;2017;1984-01-01/2017-12-31;1984-01-01/2017-12-31;en;http://daten.ktbl.de/sdb/source.do;jsessionid=04E49F6CF7BF2B8D286D1CE42CBFC9FE;https://www.ifrc.org/docs/IDRL/Sendai_Framework_for_Disaster_Risk_Reduction_2015-2030.pdf;https://www.unisdr.org/we/inform/publications/54970;https://www.preventionweb.net/documents/framework/Concept%20Paper%20-%20Direct%20Economic%20Loss%20Indicator%20methodology%2011%20November%202015.pdf;10.1016/j.ijdrr.2018.03.008;10.5880/fidgeo.2018.002;1719662 Bytes;2 Files;application/pdf;application/vnd.ms-excel.sheet.macroEnabled.12;1.1;CC BY 4.0;Version history:;5.4931640625;15.29296875;47.15984001304432;55.02802211299252;Deutsche Forschungsgemeinschaft;http://doi.org/10.13039/501100001659;GRK 2043/1;Research Training Group \"Natural Hazards and Risks in a Changing World\"",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "c110292b-f98b-5578-a193-4c236fef7e4f",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6564"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/c5298e18-1dd7-501f-83c6-f52f9176ae3d.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/c5298e18-1dd7-501f-83c6-f52f9176ae3d.json
deleted file mode 100644
index 9e5ba6c5..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/c5298e18-1dd7-501f-83c6-f52f9176ae3d.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6343",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6343"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6343;2017-12-07T17:29:11Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2017.015;Vogel, Kristin;Kristin;Vogel;0000-0002-3692-6492;University of Potsdam;Laudan, Jonas;Jonas;Laudan;0000-0003-2899-461X;University of Potsdam;Sieg, Tobias;Tobias;Sieg;0000-0003-3859-9082;University of Potsdam, GFZ German Research Centre for Geosciences;R\u00f6zer, Viktor;Viktor;R\u00f6zer;0000-0002-2883-5347;GFZ German Research Centre for Geosciences;Winter, Benjamin;Benjamin;Winter;0000-0001-9859-7105;University of Innsbruck, alps GmbH Innsbruck;Thieken, Annegret H.;Annegret H.;Thieken;0000-0001-7068-2615;University of Potsdam;Data collection for a damage assessment after the flash flood in Braunsbach (Germany) in May 2016;GFZ Data Services;2017;Flash Flood;Braunsbach;Vogel, Kristin;Kristin;Vogel;0000-0002-3692-6492;University of Potsdam;Vogel, Kristin;Kristin;Vogel;0000-0002-3692-6492;University of Potsdam;Vogel, Kristin;Kristin;Vogel;0000-0002-3692-6492;University of Potsdam;Laudan, Jonas;Jonas;Laudan;0000-0003-2899-461X;University of Potsdam;Laudan, Jonas;Jonas;Laudan;0000-0003-2899-461X;University of Potsdam;Laudan, Jonas;Jonas;Laudan;0000-0003-2899-461X;University of Potsdam;Sieg, Tobias;Tobias;Sieg;0000-0003-3859-9082;University of Potsdam, GFZ German Research Centre for Geosciences;Sieg, Tobias;Tobias;Sieg;0000-0003-3859-9082;University of Potsdam, GFZ German Research Centre for Geosciences;Sieg, Tobias;Tobias;Sieg;0000-0003-3859-9082;University of Potsdam, GFZ German Research Centre for Geosciences;R\u00f6zer, Viktor;Viktor;R\u00f6zer;0000-0002-2883-5347;GFZ German Research Centre for Geosciences;R\u00f6zer, Viktor;Viktor;R\u00f6zer;0000-0002-2883-5347;GFZ German Research Centre for Geosciences;R\u00f6zer, Viktor;Viktor;R\u00f6zer;0000-0002-2883-5347;GFZ German Research Centre for Geosciences;Winter, Benjamin;Benjamin;Winter;0000-0001-9859-7105;University of Innsbruck, alps GmbH Innsbruck;Thieken, Annegret H.;Annegret H.;Thieken;0000-0001-7068-2615;University of Potsdam;Eckle, Melanie;Melanie;Eckle;University of Heidelberg;Herfort, Benjamin;Benjamin;Herfort;University of Heidelberg;Klonner, Carolin;Carolin;Klonner;University of Heidelberg;Kuo, Chiao-Ling;Chiao-Ling;Kuo;University of Heidelberg;2016-06-07T14:00:00/2016-06-08T18:00:00;en;10.5194/nhess-17-2163-2017;10.5675/HyWa_2017,3_2;nbn:de:kobv:517-opus4-394881;10.5194/nhess-14-901-2014;10.1002/bate.200710039;10.1029/2005WR004177;266005 Bytes;2 Files;application/vnd.ms-excel;application/pdf;CC BY-SA 4.0;A severe flash flood event hit the town of Braunsbach (Baden-W\u00fcrttemberg, Germany) on the evening of May 29, 2016, heavily damaging and destroying several dozens of buildings. It was only one of several disastrous events in Central Europe caused by the low-pressure system \u201cElvira\u201d. The DFG Research Training Group \u201cNatural hazards and risks in a changing world\u201d (NatRiskChange, GRK 2043/1) at the University of Potsdam investigated the Braunsbach flash flood. In this context damage data for 94 affected buildings, describing building characteristics, the degree of impact and the caused damage, were collected ten days after the flood event and provide the basis for damage assessment studies (Agarwal et al., 2017; Laudan et al., 2017, Vogel et al., 2017).;9.788351655006409;9.79606568813324;49.19718925349636;49.201283415152794;Deutsche Forschungsgemeinschaft;http://doi.org/10.13039/501100001659;GRK 2043/1",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "c5298e18-1dd7-501f-83c6-f52f9176ae3d",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6343"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/e8833c01-8e8d-55ab-9440-1c4ce983db35.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/e8833c01-8e8d-55ab-9440-1c4ce983db35.json
deleted file mode 100644
index a57c6476..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/e8833c01-8e8d-55ab-9440-1c4ce983db35.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6342",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6342"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6342;2018-09-05T10:07:06Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2017.018;van den Ende, Martijn;Martijn;van den Ende;0000-0002-0634-7078;Utrecht University;Experimental and model data of aggregate compaction by pressure solution;GFZ Data Services;2017;Compaction;Pressure solution;Discrete Element Method;Halite;Granular mechanics;EPOS;multi-scale laboratories;rock and melt physical properties;van den Ende, Martijn;Martijn;van den Ende;0000-0002-0634-7078;Utrecht University;Experimental rock deformation/HPT-Lab (Utrecht University, The Netherlands);Utrecht University, The Netherlands;2017-11-24;eng;10.1002/2017JB014440;370524799 Bytes;2 Files;application/pdf;application/zip;CC BY 4.0;Intergranular pressure solution creep is an important deformation mechanism in the Earth\u2019s crust. The phenomenon has been frequently studied and several analytical models have been proposed that describe its constitutive behavior. These models require assumptions regarding the geometry of the aggregate and the grain size distribution in order to solve for the contact stresses, and often neglect shear tractions. Furthermore, analytical models tend to overestimate experimental compaction rates at low porosities, an observation for which the underlying mechanisms remain to be elucidated. ;Nederlandse Organisatie voor Wetenschappelijk Onderzoek;http://doi.org/10.13039/501100003246;854.12.001",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "e8833c01-8e8d-55ab-9440-1c4ce983db35",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6342"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/e9d05dc7-9f05-56b5-87f2-796161acd189.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/e9d05dc7-9f05-56b5-87f2-796161acd189.json
deleted file mode 100644
index 0d8255e4..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/e9d05dc7-9f05-56b5-87f2-796161acd189.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6335",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6335"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6335;2018-09-05T10:39:14Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2017.014;Hunfeld, Luuk;Luuk;Hunfeld;0000-0001-9250-414X;HPT Laboratory, Department of Earth Sciences, Utrecht University, The Netherlands.;Niemeijer, Andr\u00e9;Andr\u00e9;Niemeijer;0000-0003-3983-9308;HPT Laboratory, Department of Earth Sciences, Utrecht University, The Netherlands.;Spiers, Christopher;Christopher;Spiers;0000-0002-3436-8941;HPT Laboratory, Department of Earth Sciences, Utrecht University, The Netherlands.;Friction data of simulated fault gouges derived from the Groningen gas field;GFZ Data Services;2017;Frictional properties;Simulated fault gouge;Groningen gas field;EPOS;Multi-scale laboratories;rock and melt physical properties;Hunfeld, Luuk;Luuk;Hunfeld;0000-0001-9250-414X;HPT Laboratory, Department of Earth Sciences, Utrecht University, The Netherlands.;Experimental rock deformation/HPT-Lab (Utrecht University, The Netherlands);Utrecht University, The Netherlands;eng;10.1002/2017JB014876;69191878 Bytes;2 Files;application/x-zip-compressed;application/pdf;CC BY 4.0;We investigated the frictional properties of simulated fault gouges derived from the main lithologies present in the seismogenic Groningen gas field (NE Netherlands), employing in-situ P-T conditions and varying pore fluid salinity. Direct shear experiments were performed on gouges prepared from the Carboniferous Shale/Siltstone underburden, the Upper Rotliegend Slochteren Sandstone reservoir, the overlying Ten Boer Claystone, and the Basal Zechstein anhydrite-carbonate caprock, at 100 \u00baC, 40 MPa effective normal stress, and sliding velocities of 0.1-10 \u00b5m/s. As pore fluids, we used pure water, 0.5-6.2 M NaCl solutions, and a 6.9 M mixed chloride brine mimicking the formation water. Our results show a mechanical stratigraphy, with a maximum friction coefficient (\u00b5) of ~0.65 for the Basal Zechstein, a minimum of ~0.37 for the Ten Boer claystone, ~0.6 for the reservoir sandstone, ~0.5 for the Carboniferous, and \u00b5-values between the end-members for mixed gouges. Pore fluid salinity had no effect on frictional strength. Most gouges showed velocity-strengthening behavior, with little effect of pore fluid salinity on (a-b). However, Basal Zechstein gouge showed velocity-weakening at low salinities and/or sliding velocities, as did 50:50 mixtures with sandstone gouges, tested with the 6.9 M reservoir brine. From a Rate-and-State-Friction viewpoint, our results imply that faults incorporating Basal Zechstein anhydrite-carbonate material at the top of the reservoir are the most prone to accelerating slip, i.e. have the highest seismogenic potential. The results are equally relevant to other Dutch Rotliegend fields and to similar sequences globally. ;Nederlandse Aardolie Maatschappij B.V. ",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "e9d05dc7-9f05-56b5-87f2-796161acd189",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6335"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/f037643f-caf7-5f5f-8eec-7e6dc6a5de2f.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/f037643f-caf7-5f5f-8eec-7e6dc6a5de2f.json
deleted file mode 100644
index 0a232252..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/f037643f-caf7-5f5f-8eec-7e6dc6a5de2f.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6314",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6314"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6314;2018-10-25T08:07:33Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2017.007;Brizzi, Silvia;0000-0002-5258-0495;University of Roma Tre, Rome, Italy;Funiciello, Francesca;0000-0001-7900-8272;University of Roma Tre, Rome, Italy;Corbi, Fabio;0000-0003-2662-3065;University of Roma Tre, Rome, Italy;Di Giuseppe, Erika;MINES ParisTech, Paris, France;Mojoli, Giorgio;0000-0002-9370-5952;Penati Strumenti srl, Cetara (SA), Italy;Rheometric measurements of salted type A gelatins;GFZ Data Services;2017;EPOS;multi-scale laboratories;analogue models of geologic processes;property data of analogue modelling materials;Brizzi, Silvia;0000-0002-5258-0495;University of Roma Tre, Rome, Italy;Brizzi, Silvia;0000-0002-5258-0495;University of Roma Tre, Rome, Italy;Funiciello, Francesca;0000-0001-7900-8272;University of Roma Tre, Rome, Italy;Funiciello, Francesca;0000-0001-7900-8272;University of Roma Tre, Rome, Italy;Corbi, Fabio;0000-0003-2662-3065;University of Roma Tre, Rome, Italy;Corbi, Fabio;0000-0003-2662-3065;University of Roma Tre, Rome, Italy;Di Giuseppe, Erika;MINES ParisTech, Paris, France;Di Giuseppe, Erika;MINES ParisTech, Paris, France;Mojoli, Giorgio;0000-0002-9370-5952;Penati Strumenti srl, Cetara (SA), Italy;Mojoli, Giorgio;0000-0002-9370-5952;Penati Strumenti srl, Cetara (SA), Italy;Laboratory of Experimental Tectonics (University of Roma TRE, Italy);University of Roma TRE, Rome, Italy;2017-06-12;en;10.1016/j.tecto.2016.04.021;10.1016/j.tecto.2009.03.012;10.1007/s00397-011-0611-9;10.1016/j.tecto.2014.12.005;366772 Bytes;12 Files;application/vnd.openxmlformats-officedocument.spreadsheetml.sheet;application/vnd.ms-excel;application/pdf;application/vnd.openxmlformats-officedocument.spreadsheetml.sheet;application/vnd.ms-excel;application/vnd.openxmlformats-officedocument.spreadsheetml.sheet;application/vnd.ms-excel;application/pdf;application/vnd.openxmlformats-officedocument.spreadsheetml.sheet;application/vnd.ms-excel;application/vnd.openxmlformats-officedocument.spreadsheetml.sheet;application/vnd.ms-excel;CC BY 4.0;Gelatin is a versatile material commonly used in analogue modelling because of its complex rheology, which allows simulating a wide range of tectonic processes requiring either elastic (e.g., dyke intrusions models) and viscoelastic behavior (e.g., analog earthquakes models). Salt (NaCl) is generally added to gelatin to improve the scaling of the models by increasing the density of the material. The addition of salt results also in a weakening of the gelatin structure, which in turn can dramatically affect its rheological properties. Here, we provide raw data of rheometric measurements performed to test the rheological properties of type A (pig-skin) 2.5 wt% gelatin at T=10\u00b0C as a function of salt concentration and ageing time. Each sample was analyzed using dynamical oscillation tests (i.e., amplitude, frequency and time sweep tests) in shear strain controlled mode. All details about sample preparation procedure, measuring protocol, as well as results and data interpretation can be found in Brizzi et al. (2016).",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "f037643f-caf7-5f5f-8eec-7e6dc6a5de2f",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6314"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/f3b7cc68-c5d0-5d89-b25f-4cc5a0005c00.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/f3b7cc68-c5d0-5d89-b25f-4cc5a0005c00.json
deleted file mode 100644
index 9cd93a1d..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/f3b7cc68-c5d0-5d89-b25f-4cc5a0005c00.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6582",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6582"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6582;2018-12-21T07:37:25Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2018.014;Sant, Karin;Karin;Sant;0000-0002-1508-3959;Utrecht University, Utrecht, The Netherlands;Mandic, Oleg;Oleg;Mandic;6602229581;Natural History Museum Vienna, Vienna, Austria;de Leeuw, Arjan;Arjan;de Leeuw;0000-0002-8878-2785;Universit\u00e9 Grenoble Alpes, Grenoble, France;Krijgsman, Wout;Wout;Krijgsman;7003956416;Utrecht University, Utrecht, The Netherlands;Paleomagnetic dataset of the marine Badenian reference section Ugljevik in Bosnia-Herzegovina (Middle Miocene, Pannonian basin, Central Paratethys);GFZ Data Services;2018;Badenian;Sarmatian;magnetostratigraphy;integrated stratigraphy;Central Paratethys;Pannonian Basin;EPOS;Multi-scale laboratories;paleomagnetic and magnetic data;paleomagnetic data;Sant, Karin;Karin;Sant;0000-0002-1508-3959;Utrecht University, Utrecht, The Netherlands;Sant, Karin;Karin;Sant;0000-0002-1508-3959;Utrecht University, Utrecht, The Netherlands;Sant, Karin;Karin;Sant;0000-0002-1508-3959;Utrecht University, Utrecht, The Netherlands;Mandic, Oleg;Oleg;Mandic;6602229581;Natural History Museum Vienna, Vienna, Austria;Mandic, Oleg;Oleg;Mandic;6602229581;Natural History Museum Vienna, Vienna, Austria;de Leeuw, Arjan;Arjan;de Leeuw;0000-0002-8878-2785;Universit\u00e9 Grenoble Alpes, Grenoble, France;Krijgsman, Wout;Wout;Krijgsman;7003956416;Utrecht University, Utrecht, The Netherlands;Renovica, Svetlana;Svetlana;Renovica;RiTE Ugljevik (Rudnik i Termoelektrana Ugljevik\"; mining company), Ugljevik RS, Bosnia-Herzegovina;Paleomagnetic Laboratory Fort Hoofddijk (Utrecht University, The Netherlands);Utrecht University, The Netherlands;/2;2018-05-31;en;10.2478/geoca-2013-0006;10.1016/j.cageo.2016.05.007;10.1016/j.gloplacha.2018.10.010;570848 Bytes;2 Files;application/octet-stream;application/pdf;CC BY 4.0;This dataset contains paleomagnetic data used to create the magnetostratigraphy of the Ugljevik section in Bosnia and Herzegovina (thesis by Karin Sant, 2018). It is the only outcrop known with the early, middle and upper Badenian sediments exposed in a continuous section.;18.982309498631707;44.667445151876294;Location of open pit mine;Nederlandse Organisatie voor Wetenschappelijk Onderzoek;http://doi.org/10.13039/501100003246;865.10.011",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "f3b7cc68-c5d0-5d89-b25f-4cc5a0005c00",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6582"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/fd0818cb-0dbf-576f-8d20-59c5c101f97d.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/fd0818cb-0dbf-576f-8d20-59c5c101f97d.json
deleted file mode 100644
index 6ebf50e1..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/fd0818cb-0dbf-576f-8d20-59c5c101f97d.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6431",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6431"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6431;2018-10-04T12:51:58Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2018.008;van den Ende, Martijn;Martijn;van den Ende;0000-0002-0634-7078;Utrecht University;Discrete Element Method model data of biaxial shear deformation;GFZ Data Services;2018;Discrete Element Method;Biaxial shear deformation;Stick-slip mechanics;EPOS;European Plate Observing System;multi-scale laboratories;rock and melt physical properties;van den Ende, Martijn;Martijn;van den Ende;0000-0002-0634-7078;Utrecht University;van den Ende, Martijn;Martijn;van den Ende;0000-0002-0634-7078;Utrecht University;van den Ende, Martijn;Martijn;van den Ende;0000-0002-0634-7078;Utrecht University;Experimental rock deformation/HPT-Lab (Utrecht University, The Netherlands);Utrecht University, The Netherlands;2018-02;eng;Dataset;10.1029/2018GL078103;84040 Bytes;2 Files;application/octet-stream;application/pdf;CC BY 4.0;Owing to their destructive potential, earthquakes receive considerable attention from laboratory studies. In friction experiments, stick-slips are studied as the laboratory equivalent of natural earthquakes, and numerous attempts have been made to simulate stick-slips numerically using the Discrete Element Method (DEM). However, while laboratory stick-slips commonly exhibit regular stress drops and recurrence times, stick-slips generated in DEM simulations are highly irregular. This discrepancy highlights a gap in our understanding of stick-slip mechanics, which propagates into our understanding of earthquakes. In this work, we show that regular stick-slips emerge in DEM when time-dependent compaction by pressure solution is considered. We further show that the stress drop and recurrence time of stick-slips is directly controlled by the kinetics of pressure solution. Since compaction is known to operate in faults, this mechanism for frictional instabilities directly relates to natural seismicity.;Nederlandse Organisatie voor Wetenschappelijk Onderzoek;http://doi.org/10.13039/501100003246;854.12.001;NWO Vidi;H2020 European Research Council;http://doi.org/10.13039/100010663;335915;ERC Starter",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "fd0818cb-0dbf-576f-8d20-59c5c101f97d",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6431"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/ff35d3de-2298-59da-b169-fb8f5658d373.json b/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/ff35d3de-2298-59da-b169-fb8f5658d373.json
deleted file mode 100644
index 823ce948..00000000
--- a/oaitestdata/fidgeo-oai_datacite/DOIDB.FID_1/json/ff35d3de-2298-59da-b169-fb8f5658d373.json
+++ /dev/null
@@ -1,25 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6378",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:6378"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:6378;2018-03-26T12:23:07Z;DOIDB;DOIDB.FID;false;4;DOIDB.FID;10.5880/fidgeo.2017.017;Rufin, Philippe;Philippe;Rufin;0000-0001-8919-1058;Geography Department, Humboldt-Universit\u00e4t zu Berlin, Germany;Levers, Christian;Christian;Levers;Geography Department, Humboldt-Universit\u00e4t zu Berlin, Germany;Baumann, Matthias;Matthias;Baumann;0000-0003-2375-3622;Geography Department, Humboldt-Universit\u00e4t zu Berlin, Germany;J\u00e4germeyr, Jonas;Jonas;J\u00e4germeyr;0000-0002-8368-0018;PIK Potsdam Institute for Climate Impact Research, Potsdam, Germany;Krueger, Tobias;Tobias;Krueger;Geography Department, Humboldt-Universit\u00e4t zu Berlin, Germany;Kuemmerle, Tobias;Tobias;Kuemmerle;0000-0002-9775-142X;Geography Department, Humboldt-Universit\u00e4t zu Berlin, Germany;Hostert, Patrick;Patrick;Hostert;0000-0002-5730-5484;Geography Department, Humboldt-Universit\u00e4t zu Berlin, Germany;CA1985: A global approximation of irrigation dam command areas commissioned since 1985;GFZ Data Services;2017;LAND USE INTENSITY;IRRIGATION DAM;COMMAND AREA;Rufin, Philippe;Philippe;Rufin;0000-0001-8919-1058;Geography Department, Humboldt-Universit\u00e4t zu Berlin, Germany;2017-11;1985/2015;eng;10.1002/hyp.9740;10.1016/j.rse.2009.08.016;10.1016/j.jag.2015.01.014;10.1890/100125;http://www.fao.org/nr/water/aquastat/main/index.stm;http://icold-cigb.net/GB/world_register/world_register_of_dams.asp;10.13140/2.1.2660.6728;http://www.gadm.org/;http://srtm.csi.cgiar.org;https://www.ancold.org.au/?page_id=24;http://www.india-wris.nrsc.gov.in/wrpinfo/;10.1016/j.gloenvcha.2018.02.011;3409662 Bytes;2 Files;application/x-zip-compressed;application/pdf;CC BY 4.0;The spatial distribution of irrigation dam benefits is poorly understood at the global scale due to a scarcity of spatial information on irrigation dam command areas. Several studies aimed at mapping irrigated lands globally, but the spatially explicit attribution of irrigated lands to dams has rarely been undertaken. First approaches attributing changes in agricultural production to dams were based on aggregated areal units, such as administrative districts (Duflo and Pande, 2007), or watershed boundaries (Strobl and Strobl, 2011). These approaches represent only indirect approximations of command areas, and may be improved by considering spatially explicit dam- and location-specific parameters (e.g. reservoir storage capacity or topography). Such a refined dataset is required for better understanding the spatial distribution and properties of irrigation dam command areas.;The CA1985 dataset includes two raster datasets in geographic coordinates (WGS1984, EPSG: 4326) in GeoTiff format: ;-180;180;-90;90",
-    "group": "fidgeo",
-    "groups": [
-        {
-            "name": "fidgeo"
-        }
-    ],
-    "name": "ff35d3de-2298-59da-b169-fb8f5658d373",
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:6378"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.FID"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/gfz-oai_datacite/DOIDB_1/json/0a2a02c7-fa17-55a6-809c-73704cc49d54.json b/oaitestdata/gfz-oai_datacite/DOIDB_1/json/0a2a02c7-fa17-55a6-809c-73704cc49d54.json
deleted file mode 100644
index 0ff5693b..00000000
--- a/oaitestdata/gfz-oai_datacite/DOIDB_1/json/0a2a02c7-fa17-55a6-809c-73704cc49d54.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Deutsches GeoForschungsZentrum GFZ"
-    ],
-    "Contributor": [
-        "Deutsches GeoForschungsZentrum GFZ"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.5880/GEOFON.gfz2010eujm",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:3676",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:3676"
-    ],
-    "PublicationTimestamp": "2012-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Deutsches GeoForschungsZentrum GFZ"
-    ],
-    "TemporalCoverage": [
-        "2010-10-27",
-        "2010-03-10",
-        "2010-10-27"
-    ],
-    "author": [
-        "geofon operator"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:3676;2013-09-18T14:41:08Z;DOIDB;DOIDB.GEOFON;false;2.2;DOIDB.GEOFON;10.5880/GEOFON.gfz2010eujm;geofon operator;GEOFON event gfz2010eujm (Near Coast of Central Chile; Magnitude 5.3);Deutsches GeoForschungsZentrum GFZ;2012;Deutsches GeoForschungsZentrum GFZ;2010-10-27;2010-03-10;2010-10-27;eng;text/tab-separated-values;Earthquake, 2010-03-10 02:41:47, Near Coast of Central Chile",
-    "group": "gfz",
-    "groups": [
-        {
-            "name": "gfz"
-        }
-    ],
-    "name": "0a2a02c7-fa17-55a6-809c-73704cc49d54",
-    "notes": [
-        "Earthquake, 2010-03-10 02:41:47, Near Coast of Central Chile"
-    ],
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:3676"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.GEOFON"
-    ],
-    "state": "active",
-    "title": [
-        "GEOFON event gfz2010eujm (Near Coast of Central Chile; Magnitude 5.3)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/gfz-oai_datacite/DOIDB_1/json/0a33a44b-c47d-5f0e-89d0-f48d42ad2428.json b/oaitestdata/gfz-oai_datacite/DOIDB_1/json/0a33a44b-c47d-5f0e-89d0-f48d42ad2428.json
deleted file mode 100644
index a966f34c..00000000
--- a/oaitestdata/gfz-oai_datacite/DOIDB_1/json/0a33a44b-c47d-5f0e-89d0-f48d42ad2428.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Deutsches GeoForschungsZentrum GFZ"
-    ],
-    "Contributor": [
-        "Deutsches GeoForschungsZentrum GFZ"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.5880/GEOFON.gfz2013wxfd",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:4851",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:4851"
-    ],
-    "PublicationTimestamp": "2012-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Deutsches GeoForschungsZentrum GFZ"
-    ],
-    "TemporalCoverage": [
-        "2013-11-23",
-        "2013-11-22",
-        "2013-11-23"
-    ],
-    "author": [
-        "geofon operator"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:4851;2014-04-02T14:59:04Z;DOIDB;DOIDB.GEOFON;false;2.2;DOIDB.GEOFON;10.5880/GEOFON.gfz2013wxfd;geofon operator;GEOFON event gfz2013wxfd (Iran-Iraq Border Region; Magnitude 5.8);Deutsches GeoForschungsZentrum GFZ;2012;Deutsches GeoForschungsZentrum GFZ;2013-11-23;2013-11-22;2013-11-23;eng;text/tab-separated-values;Earthquake, 2013-11-22 18:30:58, Iran-Iraq Border Region",
-    "group": "gfz",
-    "groups": [
-        {
-            "name": "gfz"
-        }
-    ],
-    "name": "0a33a44b-c47d-5f0e-89d0-f48d42ad2428",
-    "notes": [
-        "Earthquake, 2013-11-22 18:30:58, Iran-Iraq Border Region"
-    ],
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:4851"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.GEOFON"
-    ],
-    "state": "active",
-    "title": [
-        "GEOFON event gfz2013wxfd (Iran-Iraq Border Region; Magnitude 5.8)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/gfz-oai_datacite/DOIDB_1/json/0aae5bba-a9c0-5898-8504-7d990f710d14.json b/oaitestdata/gfz-oai_datacite/DOIDB_1/json/0aae5bba-a9c0-5898-8504-7d990f710d14.json
deleted file mode 100644
index 94610f6f..00000000
--- a/oaitestdata/gfz-oai_datacite/DOIDB_1/json/0aae5bba-a9c0-5898-8504-7d990f710d14.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Deutsches GeoForschungsZentrum GFZ"
-    ],
-    "Contributor": [
-        "Deutsches GeoForschungsZentrum GFZ"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.5880/GEOFON.gfz2014bcyf",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:4964",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:4964"
-    ],
-    "PublicationTimestamp": "2012-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Deutsches GeoForschungsZentrum GFZ"
-    ],
-    "TemporalCoverage": [
-        "2014-01-16",
-        "2014-01-16",
-        "2014-01-16"
-    ],
-    "author": [
-        "geofon operator"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:4964;2014-04-02T15:01:53Z;DOIDB;DOIDB.GEOFON;false;2.2;DOIDB.GEOFON;10.5880/GEOFON.gfz2014bcyf;geofon operator;GEOFON event gfz2014bcyf (Bouvet Island Region; Magnitude 5.3);Deutsches GeoForschungsZentrum GFZ;2012;Deutsches GeoForschungsZentrum GFZ;2014-01-16;2014-01-16;2014-01-16;eng;text/tab-separated-values;Earthquake, 2014-01-16 20:02:46, Bouvet Island Region",
-    "group": "gfz",
-    "groups": [
-        {
-            "name": "gfz"
-        }
-    ],
-    "name": "0aae5bba-a9c0-5898-8504-7d990f710d14",
-    "notes": [
-        "Earthquake, 2014-01-16 20:02:46, Bouvet Island Region"
-    ],
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:4964"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.GEOFON"
-    ],
-    "state": "active",
-    "title": [
-        "GEOFON event gfz2014bcyf (Bouvet Island Region; Magnitude 5.3)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/gfz-oai_datacite/DOIDB_1/json/5505f787-f1d7-566e-9a40-8bb505002e2c.json b/oaitestdata/gfz-oai_datacite/DOIDB_1/json/5505f787-f1d7-566e-9a40-8bb505002e2c.json
deleted file mode 100644
index 72c432e8..00000000
--- a/oaitestdata/gfz-oai_datacite/DOIDB_1/json/5505f787-f1d7-566e-9a40-8bb505002e2c.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Deutsches GeoForschungsZentrum GFZ"
-    ],
-    "Contributor": [
-        "Deutsches GeoForschungsZentrum GFZ"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.5880/GEOFON.gfz2011jcos",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:4013",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:4013"
-    ],
-    "PublicationTimestamp": "2012-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Deutsches GeoForschungsZentrum GFZ"
-    ],
-    "TemporalCoverage": [
-        "2011-05-10",
-        "2011-05-10",
-        "2011-05-10"
-    ],
-    "author": [
-        "geofon operator"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:4013;2013-09-18T14:49:43Z;DOIDB;DOIDB.GEOFON;false;2.2;DOIDB.GEOFON;10.5880/GEOFON.gfz2011jcos;geofon operator;GEOFON event gfz2011jcos (Loyalty Islands; Magnitude 5.3);Deutsches GeoForschungsZentrum GFZ;2012;Deutsches GeoForschungsZentrum GFZ;2011-05-10;2011-05-10;2011-05-10;eng;text/tab-separated-values;Earthquake, 2011-05-10 11:31:51, Loyalty Islands",
-    "group": "gfz",
-    "groups": [
-        {
-            "name": "gfz"
-        }
-    ],
-    "name": "5505f787-f1d7-566e-9a40-8bb505002e2c",
-    "notes": [
-        "Earthquake, 2011-05-10 11:31:51, Loyalty Islands"
-    ],
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:4013"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.GEOFON"
-    ],
-    "state": "active",
-    "title": [
-        "GEOFON event gfz2011jcos (Loyalty Islands; Magnitude 5.3)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/gfz-oai_datacite/DOIDB_1/json/558123e9-8da6-5f0c-b162-7877c1a39895.json b/oaitestdata/gfz-oai_datacite/DOIDB_1/json/558123e9-8da6-5f0c-b162-7877c1a39895.json
deleted file mode 100644
index f9176b10..00000000
--- a/oaitestdata/gfz-oai_datacite/DOIDB_1/json/558123e9-8da6-5f0c-b162-7877c1a39895.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "Deutsches GeoForschungsZentrum GFZ"
-    ],
-    "Contributor": [
-        "Deutsches GeoForschungsZentrum GFZ"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.5880/GEOFON.gfz2008jjvh",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:2709",
-    "MetadataAccess": [
-        "oai:doidb.wdc-terra.org:2709"
-    ],
-    "PublicationTimestamp": "2012-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Deutsches GeoForschungsZentrum GFZ"
-    ],
-    "TemporalCoverage": [
-        "2008-05-13",
-        "2008-05-13",
-        "2008-05-13"
-    ],
-    "author": [
-        "geofon operator"
-    ],
-    "fulltext": "oai:doidb.wdc-terra.org:2709;2013-09-18T10:33:53Z;DOIDB;DOIDB.GEOFON;false;2.2;DOIDB.GEOFON;10.5880/GEOFON.gfz2008jjvh;geofon operator;GEOFON event gfz2008jjvh (Sichuan, China; Magnitude 5.5);Deutsches GeoForschungsZentrum GFZ;2012;Deutsches GeoForschungsZentrum GFZ;2008-05-13;2008-05-13;2008-05-13;eng;text/tab-separated-values;Earthquake, 2008-05-13 12:51:39, Sichuan, China",
-    "group": "gfz",
-    "groups": [
-        {
-            "name": "gfz"
-        }
-    ],
-    "name": "558123e9-8da6-5f0c-b162-7877c1a39895",
-    "notes": [
-        "Earthquake, 2008-05-13 12:51:39, Sichuan, China"
-    ],
-    "oai_identifier": [
-        "oai:doidb.wdc-terra.org:2709"
-    ],
-    "oai_set": [
-        "DOIDB",
-        "DOIDB.GEOFON"
-    ],
-    "state": "active",
-    "title": [
-        "GEOFON event gfz2008jjvh (Sichuan, China; Magnitude 5.5)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/hbp-oai_dc/SET_1/json/01ea8d08-ecad-5202-8bd2-22e3180cbbdb.json b/oaitestdata/hbp-oai_dc/SET_1/json/01ea8d08-ecad-5202-8bd2-22e3180cbbdb.json
deleted file mode 100644
index 309c6cb7..00000000
--- a/oaitestdata/hbp-oai_dc/SET_1/json/01ea8d08-ecad-5202-8bd2-22e3180cbbdb.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "https://www.humanbrainproject.eu/"
-    ],
-    "Contributor": [
-        "Poupon, Cyril",
-        "Mangin, Jean-Fran\u00e7ois",
-        "Duclap, Delphine",
-        "Rom\u00e1n, Claudio",
-        "Guevara, Pamela",
-        "Guevara, Miguel",
-        "Houenou, Josselin"
-    ],
-    "DOI": "http://dx.doi.org/10.25493/GFT3-W4M",
-    "DiscHierarchy": [
-        "3.2.1.5",
-        "Microbiology, Virology and Immunology",
-        "Immunology"
-    ],
-    "Discipline": "Neuroscience",
-    "Format": [
-        "NIFTI"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://148.187.98.42:8443/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.25493_GFT3-W4M",
-    "MetadataAccess": [
-        "10.25493_GFT3-W4M"
-    ],
-    "PublicationTimestamp": "2019-05-23T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Human Brain Project"
-    ],
-    "RelatedIdentifier": [
-        "https://doi.org/10.1016/j.neuroimage.2016.11.066"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International"
-    ],
-    "author": [
-        "Mangin, Jean-Fran\u00e7ois"
-    ],
-    "fulltext": "10.25493_GFT3-W4M;2019-12-10T12:41:56Z;https://doi.org/10.25493/GFT3-W4M;Probability map of bundle lh_PoCi-PrCu_0 (atlas of superficial white matter fibre bundles, version 2018);2019-05-23T14:01:08.131Z;This data contains the probability map of a short fibre bundle connecting the left hemisphere Posterior Cingulate and Precuneus regions of the Desikan-Killiany atlas, in the MNI ICBM152 reference brain. This bundle was identified using a hybrid approach, incorporating anatomical information (from cortical regions of interest) and fibre shape (fibre clustering), from the tractography datasets of 78 subjects in the Neurospin\u2019s ARCHI database. The map shows the probability of finding a fibre belonging to the bundle in each voxel of the reference brain. The maximum probability corresponds to the voxels with the highest number of putative fibres going through.;neuroscience;brain mapping;imaging;english;dataset;The Human Brain Project;Guevara, Miguel;Rom\u00e1n, Claudio;Houenou, Josselin;Duclap, Delphine;Poupon, Cyril;Mangin, Jean-Fran\u00e7ois;Guevara, Pamela;Mangin, Jean-Fran\u00e7ois;NIFTI;Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International;https://doi.org/10.1016/j.neuroimage.2016.11.066",
-    "group": "hbp",
-    "groups": [
-        {
-            "name": "hbp"
-        }
-    ],
-    "name": "01ea8d08-ecad-5202-8bd2-22e3180cbbdb",
-    "notes": [
-        "This data contains the probability map of a short fibre bundle connecting the left hemisphere Posterior Cingulate and Precuneus regions of the Desikan-Killiany atlas, in the MNI ICBM152 reference brain. This bundle was identified using a hybrid approach, incorporating anatomical information (from cortical regions of interest) and fibre shape (fibre clustering), from the tractography datasets of 78 subjects in the Neurospin\u2019s ARCHI database. The map shows the probability of finding a fibre belonging to the bundle in each voxel of the reference brain. The maximum probability corresponds to the voxels with the highest number of putative fibres going through."
-    ],
-    "oai_identifier": [
-        "10.25493_GFT3-W4M"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "neuroscience"
-        },
-        {
-            "name": "brain mapping"
-        },
-        {
-            "name": "imaging"
-        }
-    ],
-    "title": [
-        "Probability map of bundle lh_PoCi-PrCu_0 (atlas of superficial white matter fibre bundles, version 2018)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/hbp-oai_dc/SET_1/json/02cd3648-a242-51bb-8c94-1df35c3970fb.json b/oaitestdata/hbp-oai_dc/SET_1/json/02cd3648-a242-51bb-8c94-1df35c3970fb.json
deleted file mode 100644
index 6767023b..00000000
--- a/oaitestdata/hbp-oai_dc/SET_1/json/02cd3648-a242-51bb-8c94-1df35c3970fb.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "https://www.humanbrainproject.eu/"
-    ],
-    "Contributor": [
-        "Poupon, Cyril",
-        "Mangin, Jean-Fran\u00e7ois",
-        "Duclap, Delphine",
-        "Rom\u00e1n, Claudio",
-        "Guevara, Pamela",
-        "Guevara, Miguel",
-        "Houenou, Josselin"
-    ],
-    "DOI": "http://dx.doi.org/10.25493/6FWA-99Y",
-    "DiscHierarchy": [
-        "3.2.1.5",
-        "Microbiology, Virology and Immunology",
-        "Immunology"
-    ],
-    "Discipline": "Neuroscience",
-    "Format": [
-        "NIFTI"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://148.187.98.42:8443/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.25493_6FWA-99Y",
-    "MetadataAccess": [
-        "10.25493_6FWA-99Y"
-    ],
-    "PublicationTimestamp": "2019-05-23T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Human Brain Project"
-    ],
-    "RelatedIdentifier": [
-        "https://doi.org/10.1016/j.neuroimage.2016.11.066"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International"
-    ],
-    "author": [
-        "Mangin, Jean-Fran\u00e7ois"
-    ],
-    "fulltext": "10.25493_6FWA-99Y;2019-12-10T12:41:55Z;https://doi.org/10.25493/6FWA-99Y;Probability map of bundle lh_ST-Ins_0 (atlas of superficial white matter fibre bundles, version 2018);2019-05-23T14:11:52.997Z;This data contains the probability map of a short fibre bundle connecting the left hemisphere Superior Temporal and Insula regions of the Desikan-Killiany atlas, in the MNI ICBM152 reference brain. This bundle was identified using a hybrid approach, incorporating anatomical information (from cortical regions of interest) and fibre shape (fibre clustering), from the tractography datasets of 78 subjects in the Neurospin\u2019s ARCHI database. The map shows the probability of finding a fibre belonging to the bundle in each voxel of the reference brain. The maximum probability corresponds to the voxels with the highest number of putative fibres going through.;neuroscience;brain mapping;imaging;english;dataset;The Human Brain Project;Guevara, Miguel;Rom\u00e1n, Claudio;Houenou, Josselin;Duclap, Delphine;Poupon, Cyril;Mangin, Jean-Fran\u00e7ois;Guevara, Pamela;Mangin, Jean-Fran\u00e7ois;NIFTI;Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International;https://doi.org/10.1016/j.neuroimage.2016.11.066",
-    "group": "hbp",
-    "groups": [
-        {
-            "name": "hbp"
-        }
-    ],
-    "name": "02cd3648-a242-51bb-8c94-1df35c3970fb",
-    "notes": [
-        "This data contains the probability map of a short fibre bundle connecting the left hemisphere Superior Temporal and Insula regions of the Desikan-Killiany atlas, in the MNI ICBM152 reference brain. This bundle was identified using a hybrid approach, incorporating anatomical information (from cortical regions of interest) and fibre shape (fibre clustering), from the tractography datasets of 78 subjects in the Neurospin\u2019s ARCHI database. The map shows the probability of finding a fibre belonging to the bundle in each voxel of the reference brain. The maximum probability corresponds to the voxels with the highest number of putative fibres going through."
-    ],
-    "oai_identifier": [
-        "10.25493_6FWA-99Y"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "neuroscience"
-        },
-        {
-            "name": "brain mapping"
-        },
-        {
-            "name": "imaging"
-        }
-    ],
-    "title": [
-        "Probability map of bundle lh_ST-Ins_0 (atlas of superficial white matter fibre bundles, version 2018)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/hbp-oai_dc/SET_1/json/0a54baa3-0085-5b0a-a6c4-770f89be9860.json b/oaitestdata/hbp-oai_dc/SET_1/json/0a54baa3-0085-5b0a-a6c4-770f89be9860.json
deleted file mode 100644
index ebe68ddd..00000000
--- a/oaitestdata/hbp-oai_dc/SET_1/json/0a54baa3-0085-5b0a-a6c4-770f89be9860.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "https://www.humanbrainproject.eu/"
-    ],
-    "Contributor": [
-        "Nyl\u00e9n, Johanna Frost",
-        "Dorst, Matthijs"
-    ],
-    "DOI": "http://dx.doi.org/10.25493/VW70-659",
-    "DiscHierarchy": [
-        "3.2.3",
-        "Medicine",
-        "Neurosciences"
-    ],
-    "Discipline": "Neuroscience",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://148.187.98.42:8443/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.25493_VW70-659",
-    "MetadataAccess": [
-        "10.25493_VW70-659"
-    ],
-    "PublicationTimestamp": "2019-05-13T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Human Brain Project"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International"
-    ],
-    "author": [
-        "Grillner, Sten"
-    ],
-    "fulltext": "10.25493_VW70-659;2019-12-10T12:41:54Z;https://doi.org/10.25493/VW70-659;Cholinergic interneurons in the striatum - Single cell patch clamp recordings;2019-05-13T13:35:49.022Z;The study entails the collection of single cell patch-clamp recordings, done in conjunction with morphological reconstructions, from cholinergic interneurons in the striatum.   \n\n**Embargo status:**   \n*This dataset is temporarily under embargo. The data will become available for download after the embargo period.*;neuroscience;DAB;Reconstruction;NEUROLUCIDA;english;dataset;The Human Brain Project;Dorst, Matthijs;Nyl\u00e9n, Johanna Frost;Grillner, Sten;Creative Commons Attribution 4.0 International",
-    "group": "hbp",
-    "groups": [
-        {
-            "name": "hbp"
-        }
-    ],
-    "name": "0a54baa3-0085-5b0a-a6c4-770f89be9860",
-    "notes": [
-        "The study entails the collection of single cell patch-clamp recordings, done in conjunction with morphological reconstructions, from cholinergic interneurons in the striatum.   \n\n**Embargo status:**   \n*This dataset is temporarily under embargo. The data will become available for download after the embargo period.*"
-    ],
-    "oai_identifier": [
-        "10.25493_VW70-659"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "neuroscience"
-        },
-        {
-            "name": "DAB"
-        },
-        {
-            "name": "Reconstruction"
-        },
-        {
-            "name": "NEUROLUCIDA"
-        }
-    ],
-    "title": [
-        "Cholinergic interneurons in the striatum - Single cell patch clamp recordings"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/hbp-oai_dc/SET_1/json/0a56258f-fefd-5724-87bf-21ef340d2938.json b/oaitestdata/hbp-oai_dc/SET_1/json/0a56258f-fefd-5724-87bf-21ef340d2938.json
deleted file mode 100644
index 1c9f9307..00000000
--- a/oaitestdata/hbp-oai_dc/SET_1/json/0a56258f-fefd-5724-87bf-21ef340d2938.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "https://www.humanbrainproject.eu/"
-    ],
-    "Contributor": [
-        "Poupon, Cyril",
-        "Mangin, Jean-Fran\u00e7ois",
-        "Duclap, Delphine",
-        "Rom\u00e1n, Claudio",
-        "Guevara, Pamela",
-        "Guevara, Miguel",
-        "Houenou, Josselin"
-    ],
-    "DOI": "http://dx.doi.org/10.25493/S1HG-N64",
-    "DiscHierarchy": [
-        "3.2.1.5",
-        "Microbiology, Virology and Immunology",
-        "Immunology"
-    ],
-    "Discipline": "Neuroscience",
-    "Format": [
-        "NIFTI"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://148.187.98.42:8443/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.25493_S1HG-N64",
-    "MetadataAccess": [
-        "10.25493_S1HG-N64"
-    ],
-    "PublicationTimestamp": "2019-05-23T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Human Brain Project"
-    ],
-    "RelatedIdentifier": [
-        "https://doi.org/10.1016/j.neuroimage.2016.11.066"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International"
-    ],
-    "author": [
-        "Mangin, Jean-Fran\u00e7ois"
-    ],
-    "fulltext": "10.25493_S1HG-N64;2019-12-10T12:41:56Z;https://doi.org/10.25493/S1HG-N64;Probability map of bundle rh_CMF-PrC_0 (atlas of superficial white matter fibre bundles, version 2018);2019-05-23T14:27:26.934Z;This data contains the probability map of a short fibre bundle connecting the right hemisphere Caudal Middle Frontal and Precentral regions of the Desikan-Killiany atlas, in the MNI ICBM152 reference brain. This bundle was identified using a hybrid approach, incorporating anatomical information (from cortical regions of interest) and fibre shape (fibre clustering), from the tractography datasets of 78 subjects in the Neurospin\u2019s ARCHI database. The map shows the probability of finding a fibre belonging to the bundle in each voxel of the reference brain. The maximum probability corresponds to the voxels with the highest number of putative fibres going through.;neuroscience;brain mapping;imaging;english;dataset;The Human Brain Project;Guevara, Miguel;Rom\u00e1n, Claudio;Houenou, Josselin;Duclap, Delphine;Poupon, Cyril;Mangin, Jean-Fran\u00e7ois;Guevara, Pamela;Mangin, Jean-Fran\u00e7ois;NIFTI;Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International;https://doi.org/10.1016/j.neuroimage.2016.11.066",
-    "group": "hbp",
-    "groups": [
-        {
-            "name": "hbp"
-        }
-    ],
-    "name": "0a56258f-fefd-5724-87bf-21ef340d2938",
-    "notes": [
-        "This data contains the probability map of a short fibre bundle connecting the right hemisphere Caudal Middle Frontal and Precentral regions of the Desikan-Killiany atlas, in the MNI ICBM152 reference brain. This bundle was identified using a hybrid approach, incorporating anatomical information (from cortical regions of interest) and fibre shape (fibre clustering), from the tractography datasets of 78 subjects in the Neurospin\u2019s ARCHI database. The map shows the probability of finding a fibre belonging to the bundle in each voxel of the reference brain. The maximum probability corresponds to the voxels with the highest number of putative fibres going through."
-    ],
-    "oai_identifier": [
-        "10.25493_S1HG-N64"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "neuroscience"
-        },
-        {
-            "name": "brain mapping"
-        },
-        {
-            "name": "imaging"
-        }
-    ],
-    "title": [
-        "Probability map of bundle rh_CMF-PrC_0 (atlas of superficial white matter fibre bundles, version 2018)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/hbp-oai_dc/SET_1/json/0c4c065b-0cba-5da0-8d02-5ba15f617539.json b/oaitestdata/hbp-oai_dc/SET_1/json/0c4c065b-0cba-5da0-8d02-5ba15f617539.json
deleted file mode 100644
index de0fb23e..00000000
--- a/oaitestdata/hbp-oai_dc/SET_1/json/0c4c065b-0cba-5da0-8d02-5ba15f617539.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "Contact": [
-        "https://www.humanbrainproject.eu/"
-    ],
-    "Contributor": [
-        "Turegano, Marta",
-        "DeFelipe, Javier",
-        "Merchan-Perez, Angel",
-        "Rodriguez, Rodrigo"
-    ],
-    "DOI": "http://dx.doi.org/10.25493/T3VH-K6P",
-    "DiscHierarchy": [
-        "3.2.3",
-        "Medicine",
-        "Neurosciences"
-    ],
-    "Discipline": "Neuroscience",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://148.187.98.42:8443/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.25493_T3VH-K6P",
-    "MetadataAccess": [
-        "10.25493_T3VH-K6P"
-    ],
-    "PublicationTimestamp": "2019-05-23T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Human Brain Project"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution-NonCommercial 4.0 International"
-    ],
-    "author": [
-        "Merchan-Perez, Angel"
-    ],
-    "fulltext": "10.25493_T3VH-K6P;2019-12-10T12:41:57Z;https://doi.org/10.25493/T3VH-K6P;Densities and 3D distributions of synapses using FIB/SEM imaging in the mouse neocortex (somatosensory cortex);2019-05-23T08:07:34.108Z;Synapses have been identified, segmented and quantified in the adult mouse somatosensory cortex with 3D electron microscopy (FIB-SEM). Three animals have been used (ID5, ID24 and ID25). The six layers of the somatosensory cortex have been studied. Data obtained include the number of asymmetric and symmetric synapses, their sizes and their spatial distribution. \n\n\n**Embargo status:**   \n*This dataset is temporarily under embargo. The data will become available for download after the embargo period.*;neuroscience;english;dataset;The Human Brain Project;Turegano, Marta;Rodriguez, Rodrigo;DeFelipe, Javier;Merchan-Perez, Angel;Merchan-Perez, Angel;Creative Commons Attribution-NonCommercial 4.0 International",
-    "group": "hbp",
-    "groups": [
-        {
-            "name": "hbp"
-        }
-    ],
-    "name": "0c4c065b-0cba-5da0-8d02-5ba15f617539",
-    "notes": [
-        "Synapses have been identified, segmented and quantified in the adult mouse somatosensory cortex with 3D electron microscopy (FIB-SEM). Three animals have been used (ID5, ID24 and ID25). The six layers of the somatosensory cortex have been studied. Data obtained include the number of asymmetric and symmetric synapses, their sizes and their spatial distribution. \n\n\n**Embargo status:**   \n*This dataset is temporarily under embargo. The data will become available for download after the embargo period.*"
-    ],
-    "oai_identifier": [
-        "10.25493_T3VH-K6P"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "neuroscience"
-        }
-    ],
-    "title": [
-        "Densities and 3D distributions of synapses using FIB/SEM imaging in the mouse neocortex (somatosensory cortex)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/hbp-oai_dc/SET_1/json/0c7f1d4a-3cce-5734-a5ba-6d4276439885.json b/oaitestdata/hbp-oai_dc/SET_1/json/0c7f1d4a-3cce-5734-a5ba-6d4276439885.json
deleted file mode 100644
index 0994586b..00000000
--- a/oaitestdata/hbp-oai_dc/SET_1/json/0c7f1d4a-3cce-5734-a5ba-6d4276439885.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "https://www.humanbrainproject.eu/"
-    ],
-    "Contributor": [
-        "Mohlberg, Hartmut",
-        "Caspers, Svenja",
-        "Saal, Martin",
-        "Bludau, Sebastian",
-        "Amunts, Katrin"
-    ],
-    "DOI": "http://dx.doi.org/10.25493/1NGE-YH3",
-    "DiscHierarchy": [
-        "3.2",
-        "Life Sciences",
-        "Medicine"
-    ],
-    "Discipline": "Neuroscience",
-    "Format": [
-        "NIFTI"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://148.187.98.42:8443/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.25493_1NGE-YH3",
-    "MetadataAccess": [
-        "10.25493_1NGE-YH3"
-    ],
-    "PublicationTimestamp": "2019-06-06T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Human Brain Project"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International"
-    ],
-    "author": [
-        "Amunts, Katrin"
-    ],
-    "fulltext": "10.25493_1NGE-YH3;2019-12-10T12:41:57Z;https://doi.org/10.25493/1NGE-YH3;Probabilistic cytoarchitectonic map of Area OP8 (Frontal Operculum) (v5.0);2019-06-06T08:20:32.092Z;This dataset contains the distinct probabilistic cytoarchitectonic map of Area OP8 (Frontal Operculum) in the individual, single subject template of the MNI Colin 27 reference space. As part of the JuBrain cytoarchitectonic atlas, the area was identified using cytoarchitectonic analysis on cell-body-stained histological sections of 10 human postmortem brains obtained from the body donor program of the University of D\u00fcsseldorf. The results of the cytoarchitectonic analysis were then mapped to the reference space, where each voxel was assigned the probability to belong to Area OP8 (Frontal Operculum). The probability map of Area OP8 (Frontal Operculum) is provided in NifTi format for each hemisphere in the reference space. The JuBrain atlas relies on a modular, flexible and adaptive framework containing workflows to create the probabilistic brain maps for these structures. Note that methodological improvements and updated probability estimates for new brain structures may in some cases lead to measurable but negligible deviations of existing probability maps, as compared to earlier released datasets.\n\nOther available data versions of Area OP8 (Frontal Operculum):\nSaal et al. (2019) [Data set, v5.1] [DOI: 10.25493/NGF8-TA4](https://doi.org/10.25493%2FNGF8-TA4)\n\nThe most probable delineation of Area OP8 (Frontal Operculum) derived from the calculation of a maximum probability map of all currently released JuBrain brain structures can be found here:\nAmunts et al. (2019) [Data set, v18] [DOI: 10.25493/8EGG-ZAR](https://doi.org/10.25493%2F8EGG-ZAR)\n;neuroscience;histology;imaging;brain mapping;english;dataset;The Human Brain Project;Saal, Martin;Bludau, Sebastian;Mohlberg, Hartmut;Caspers, Svenja;Amunts, Katrin;Amunts, Katrin;NIFTI;Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International",
-    "group": "hbp",
-    "groups": [
-        {
-            "name": "hbp"
-        }
-    ],
-    "name": "0c7f1d4a-3cce-5734-a5ba-6d4276439885",
-    "notes": [
-        "This dataset contains the distinct probabilistic cytoarchitectonic map of Area OP8 (Frontal Operculum) in the individual, single subject template of the MNI Colin 27 reference space. As part of the JuBrain cytoarchitectonic atlas, the area was identified using cytoarchitectonic analysis on cell-body-stained histological sections of 10 human postmortem brains obtained from the body donor program of the University of D\u00fcsseldorf. The results of the cytoarchitectonic analysis were then mapped to the reference space, where each voxel was assigned the probability to belong to Area OP8 (Frontal Operculum). The probability map of Area OP8 (Frontal Operculum) is provided in NifTi format for each hemisphere in the reference space. The JuBrain atlas relies on a modular, flexible and adaptive framework containing workflows to create the probabilistic brain maps for these structures. Note that methodological improvements and updated probability estimates for new brain structures may in some cases lead to measurable but negligible deviations of existing probability maps, as compared to earlier released datasets.\n\nOther available data versions of Area OP8 (Frontal Operculum):\nSaal et al. (2019) [Data set, v5.1] [DOI: 10.25493/NGF8-TA4](https://doi.org/10.25493%2FNGF8-TA4)\n\nThe most probable delineation of Area OP8 (Frontal Operculum) derived from the calculation of a maximum probability map of all currently released JuBrain brain structures can be found here:\nAmunts et al. (2019) [Data set, v18] [DOI: 10.25493/8EGG-ZAR](https://doi.org/10.25493%2F8EGG-ZAR)\n"
-    ],
-    "oai_identifier": [
-        "10.25493_1NGE-YH3"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "neuroscience"
-        },
-        {
-            "name": "histology"
-        },
-        {
-            "name": "imaging"
-        },
-        {
-            "name": "brain mapping"
-        }
-    ],
-    "title": [
-        "Probabilistic cytoarchitectonic map of Area OP8 (Frontal Operculum) (v5.0)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/hbp-oai_dc/SET_1/json/0ded9e4b-9cb7-5308-8ab5-fcf5c9519db6.json b/oaitestdata/hbp-oai_dc/SET_1/json/0ded9e4b-9cb7-5308-8ab5-fcf5c9519db6.json
deleted file mode 100644
index bd856dcc..00000000
--- a/oaitestdata/hbp-oai_dc/SET_1/json/0ded9e4b-9cb7-5308-8ab5-fcf5c9519db6.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "https://www.humanbrainproject.eu/"
-    ],
-    "Contributor": [
-        "Bludau, Sebastian",
-        "Eickhoff, Simon B.",
-        "Caspers, Svenja",
-        "Amunts, Katrin",
-        "Seitz, R\u00fcdiger J.  ",
-        "Mohlberg, Hartmut",
-        "Ruan, Jianghai",
-        "Palomero-Gallagher, Nicola"
-    ],
-    "DOI": "http://dx.doi.org/10.25493/WVNR-SPT",
-    "DiscHierarchy": [
-        "3.2",
-        "Life Sciences",
-        "Medicine"
-    ],
-    "Discipline": "Neuroscience",
-    "Format": [
-        "NIFTI"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://148.187.98.42:8443/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.25493_WVNR-SPT",
-    "MetadataAccess": [
-        "10.25493_WVNR-SPT"
-    ],
-    "PublicationTimestamp": "2019-06-04T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Human Brain Project"
-    ],
-    "RelatedIdentifier": [
-        "https://doi.org/10.1007/s00429-018-1738-6"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International"
-    ],
-    "author": [
-        "Amunts, Katrin"
-    ],
-    "fulltext": "10.25493_WVNR-SPT;2019-12-10T12:41:56Z;https://doi.org/10.25493/WVNR-SPT;Probabilistic cytoarchitectonic map of Area 6ma (preSMA, mesial SFG) (v9.1);2019-06-04T16:38:35.773Z;This dataset contains the distinct architectonic Area 6ma (preSMA, mesial SFG) in the MNI Colin 27 and MNI ICBM 152 reference spaces. As part of the JuBrain cytoarchitectonic atlas, the area was identified using cytoarchitectonic analysis on cell-body-stained histological sections of 10 human postmortem brains obtained from the body donor program of the University of D\u00fcsseldorf. Subsequently, the results of the cytoarchitectonic analysis are mapped to the MNI Colin 27 and MNI ICBM 152 reference spaces where each voxel is assigned with the probability to belong to Area 6ma (preSMA, mesial SFG). The probability map of Area 6ma (preSMA, mesial SFG) is provided in the NifTi format for each brain reference space and hemisphere. The JuBrain atlas relies on a modular, flexible and adaptive framework containing workflows to create the probabilistic brain maps for these structures. Note that methodological improvements and integration of new brain structures may lead to small deviations in earlier released datasets.;neuroscience;histology;imaging;brain mapping;english;dataset;The Human Brain Project;Ruan, Jianghai;Bludau, Sebastian;Palomero-Gallagher, Nicola;Caspers, Svenja;Mohlberg, Hartmut;Eickhoff, Simon B.;Seitz, R\u00fcdiger J.  ;Amunts, Katrin;Amunts, Katrin;NIFTI;Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International;https://doi.org/10.1007/s00429-018-1738-6",
-    "group": "hbp",
-    "groups": [
-        {
-            "name": "hbp"
-        }
-    ],
-    "name": "0ded9e4b-9cb7-5308-8ab5-fcf5c9519db6",
-    "notes": [
-        "This dataset contains the distinct architectonic Area 6ma (preSMA, mesial SFG) in the MNI Colin 27 and MNI ICBM 152 reference spaces. As part of the JuBrain cytoarchitectonic atlas, the area was identified using cytoarchitectonic analysis on cell-body-stained histological sections of 10 human postmortem brains obtained from the body donor program of the University of D\u00fcsseldorf. Subsequently, the results of the cytoarchitectonic analysis are mapped to the MNI Colin 27 and MNI ICBM 152 reference spaces where each voxel is assigned with the probability to belong to Area 6ma (preSMA, mesial SFG). The probability map of Area 6ma (preSMA, mesial SFG) is provided in the NifTi format for each brain reference space and hemisphere. The JuBrain atlas relies on a modular, flexible and adaptive framework containing workflows to create the probabilistic brain maps for these structures. Note that methodological improvements and integration of new brain structures may lead to small deviations in earlier released datasets."
-    ],
-    "oai_identifier": [
-        "10.25493_WVNR-SPT"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "neuroscience"
-        },
-        {
-            "name": "histology"
-        },
-        {
-            "name": "imaging"
-        },
-        {
-            "name": "brain mapping"
-        }
-    ],
-    "title": [
-        "Probabilistic cytoarchitectonic map of Area 6ma (preSMA, mesial SFG) (v9.1)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/hbp-oai_dc/SET_1/json/0e7dd3b0-3a8d-593a-97d0-344eb2674468.json b/oaitestdata/hbp-oai_dc/SET_1/json/0e7dd3b0-3a8d-593a-97d0-344eb2674468.json
deleted file mode 100644
index d870fc47..00000000
--- a/oaitestdata/hbp-oai_dc/SET_1/json/0e7dd3b0-3a8d-593a-97d0-344eb2674468.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "https://www.humanbrainproject.eu/"
-    ],
-    "Contributor": [
-        "Poupon, Cyril",
-        "Mangin, Jean-Fran\u00e7ois",
-        "Duclap, Delphine",
-        "Rom\u00e1n, Claudio",
-        "Guevara, Pamela",
-        "Guevara, Miguel",
-        "Houenou, Josselin"
-    ],
-    "DOI": "http://dx.doi.org/10.25493/MEF4-C1V",
-    "DiscHierarchy": [
-        "3.2.1.5",
-        "Microbiology, Virology and Immunology",
-        "Immunology"
-    ],
-    "Discipline": "Neuroscience",
-    "Format": [
-        "NIFTI"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://148.187.98.42:8443/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.25493_MEF4-C1V",
-    "MetadataAccess": [
-        "10.25493_MEF4-C1V"
-    ],
-    "PublicationTimestamp": "2019-05-23T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Human Brain Project"
-    ],
-    "RelatedIdentifier": [
-        "https://doi.org/10.1016/j.neuroimage.2016.11.066"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International"
-    ],
-    "author": [
-        "Mangin, Jean-Fran\u00e7ois"
-    ],
-    "fulltext": "10.25493_MEF4-C1V;2019-12-10T12:41:56Z;https://doi.org/10.25493/MEF4-C1V;Probability map of bundle rh_IT-MT_1 (atlas of superficial white matter fibre bundles, version 2018);2019-05-23T14:35:50.095Z;This data contains the probability map of a short fibre bundle connecting the right hemisphere Inferior Temporal and Middle Temporal regions of the Desikan-Killiany atlas, in the MNI ICBM152 reference brain. This bundle was identified using a hybrid approach, incorporating anatomical information (from cortical regions of interest) and fibre shape (fibre clustering), from the tractography datasets of 78 subjects in the Neurospin\u2019s ARCHI database. The map shows the probability of finding a fibre belonging to the bundle in each voxel of the reference brain. The maximum probability corresponds to the voxels with the highest number of putative fibres going through.;neuroscience;brain mapping;imaging;english;dataset;The Human Brain Project;Guevara, Miguel;Rom\u00e1n, Claudio;Houenou, Josselin;Duclap, Delphine;Poupon, Cyril;Mangin, Jean-Fran\u00e7ois;Guevara, Pamela;Mangin, Jean-Fran\u00e7ois;NIFTI;Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International;https://doi.org/10.1016/j.neuroimage.2016.11.066",
-    "group": "hbp",
-    "groups": [
-        {
-            "name": "hbp"
-        }
-    ],
-    "name": "0e7dd3b0-3a8d-593a-97d0-344eb2674468",
-    "notes": [
-        "This data contains the probability map of a short fibre bundle connecting the right hemisphere Inferior Temporal and Middle Temporal regions of the Desikan-Killiany atlas, in the MNI ICBM152 reference brain. This bundle was identified using a hybrid approach, incorporating anatomical information (from cortical regions of interest) and fibre shape (fibre clustering), from the tractography datasets of 78 subjects in the Neurospin\u2019s ARCHI database. The map shows the probability of finding a fibre belonging to the bundle in each voxel of the reference brain. The maximum probability corresponds to the voxels with the highest number of putative fibres going through."
-    ],
-    "oai_identifier": [
-        "10.25493_MEF4-C1V"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "neuroscience"
-        },
-        {
-            "name": "brain mapping"
-        },
-        {
-            "name": "imaging"
-        }
-    ],
-    "title": [
-        "Probability map of bundle rh_IT-MT_1 (atlas of superficial white matter fibre bundles, version 2018)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/hbp-oai_dc/SET_1/json/0ec6787b-02c0-57fb-9690-24d062aff47b.json b/oaitestdata/hbp-oai_dc/SET_1/json/0ec6787b-02c0-57fb-9690-24d062aff47b.json
deleted file mode 100644
index e60f6306..00000000
--- a/oaitestdata/hbp-oai_dc/SET_1/json/0ec6787b-02c0-57fb-9690-24d062aff47b.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "https://www.humanbrainproject.eu/"
-    ],
-    "Contributor": [
-        "Zilles, Karl",
-        "Bludau, Sebastian",
-        "Eickhoff, Simon B.",
-        "Caspers, Svenja",
-        "Richter, Monika",
-        "Mohlberg, Hartmut",
-        "Amunts, Katrin"
-    ],
-    "DOI": "http://dx.doi.org/10.25493/WZNZ-DPQ",
-    "DiscHierarchy": [
-        "3.2",
-        "Life Sciences",
-        "Medicine"
-    ],
-    "Discipline": "Neuroscience",
-    "Format": [
-        "NIFTI"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://148.187.98.42:8443/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.25493_WZNZ-DPQ",
-    "MetadataAccess": [
-        "10.25493_WZNZ-DPQ"
-    ],
-    "PublicationTimestamp": "2019-06-04T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Human Brain Project"
-    ],
-    "RelatedIdentifier": [
-        "https://doi.org/10.1093/cercor/bhy245 "
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International"
-    ],
-    "author": [
-        "Amunts, Katrin"
-    ],
-    "fulltext": "10.25493_WZNZ-DPQ;2019-12-10T12:41:52Z;https://doi.org/10.25493/WZNZ-DPQ;Probabilistic cytoarchitectonic map of Area hIP5 (IPS) (v7.0);2019-06-04T11:26:53.067Z;This dataset contains the distinct probabilistic cytoarchitectonic map of Area hIP5 (IPS) in the individual, single subject template of the MNI Colin 27 reference space. As part of the JuBrain cytoarchitectonic atlas, the area was identified using cytoarchitectonic analysis on cell-body-stained histological sections of 10 human postmortem brains obtained from the body donor program of the University of D\u00fcsseldorf. The results of the cytoarchitectonic analysis were then mapped to the reference space, where each voxel was assigned the probability to belong to Area hIP5 (IPS). The probability map of Area hIP5 (IPS) is provided in NifTi format for each hemisphere in the reference space. The JuBrain atlas relies on a modular, flexible and adaptive framework containing workflows to create the probabilistic brain maps for these structures. Note that methodological improvements and updated probability estimates for new brain structures may in some cases lead to measurable but negligible deviations of existing probability maps, as compared to earlier released datasets.  .\n\nOther available data versions of Area hIP5 (IPS):\nRichter et al. (2019) [Data set, v7.1] [DOI: 10.25493/RNSM-Y4Y](https://doi.org/10.25493%2FRNSM-Y4Y)\n\nThe most probable delineation of Area hIP5 (IPS) derived from the calculation of a maximum probability map of all currently released JuBrain brain structures can be found here:\nAmunts et al. (2019) [Data set, v18] [DOI: 10.25493/8EGG-ZAR](https://doi.org/10.25493%2F8EGG-ZAR)\n;neuroscience;histology;imaging;brain mapping;english;dataset;The Human Brain Project;Richter, Monika;Amunts, Katrin;Mohlberg, Hartmut;Bludau, Sebastian;Eickhoff, Simon B.;Zilles, Karl;Caspers, Svenja;Amunts, Katrin;NIFTI;Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International;https://doi.org/10.1093/cercor/bhy245 ",
-    "group": "hbp",
-    "groups": [
-        {
-            "name": "hbp"
-        }
-    ],
-    "name": "0ec6787b-02c0-57fb-9690-24d062aff47b",
-    "notes": [
-        "This dataset contains the distinct probabilistic cytoarchitectonic map of Area hIP5 (IPS) in the individual, single subject template of the MNI Colin 27 reference space. As part of the JuBrain cytoarchitectonic atlas, the area was identified using cytoarchitectonic analysis on cell-body-stained histological sections of 10 human postmortem brains obtained from the body donor program of the University of D\u00fcsseldorf. The results of the cytoarchitectonic analysis were then mapped to the reference space, where each voxel was assigned the probability to belong to Area hIP5 (IPS). The probability map of Area hIP5 (IPS) is provided in NifTi format for each hemisphere in the reference space. The JuBrain atlas relies on a modular, flexible and adaptive framework containing workflows to create the probabilistic brain maps for these structures. Note that methodological improvements and updated probability estimates for new brain structures may in some cases lead to measurable but negligible deviations of existing probability maps, as compared to earlier released datasets.  .\n\nOther available data versions of Area hIP5 (IPS):\nRichter et al. (2019) [Data set, v7.1] [DOI: 10.25493/RNSM-Y4Y](https://doi.org/10.25493%2FRNSM-Y4Y)\n\nThe most probable delineation of Area hIP5 (IPS) derived from the calculation of a maximum probability map of all currently released JuBrain brain structures can be found here:\nAmunts et al. (2019) [Data set, v18] [DOI: 10.25493/8EGG-ZAR](https://doi.org/10.25493%2F8EGG-ZAR)\n"
-    ],
-    "oai_identifier": [
-        "10.25493_WZNZ-DPQ"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "neuroscience"
-        },
-        {
-            "name": "histology"
-        },
-        {
-            "name": "imaging"
-        },
-        {
-            "name": "brain mapping"
-        }
-    ],
-    "title": [
-        "Probabilistic cytoarchitectonic map of Area hIP5 (IPS) (v7.0)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/hbp-oai_dc/SET_1/json/0ed9dd69-526a-5bd5-b784-82332cfc4c44.json b/oaitestdata/hbp-oai_dc/SET_1/json/0ed9dd69-526a-5bd5-b784-82332cfc4c44.json
deleted file mode 100644
index aca8b7d3..00000000
--- a/oaitestdata/hbp-oai_dc/SET_1/json/0ed9dd69-526a-5bd5-b784-82332cfc4c44.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "https://www.humanbrainproject.eu/"
-    ],
-    "Contributor": [
-        "Poupon, Cyril",
-        "Mangin, Jean-Fran\u00e7ois",
-        "Duclap, Delphine",
-        "Rom\u00e1n, Claudio",
-        "Guevara, Pamela",
-        "Guevara, Miguel",
-        "Houenou, Josselin"
-    ],
-    "DOI": "http://dx.doi.org/10.25493/66PB-17W",
-    "DiscHierarchy": [
-        "3.2.1.5",
-        "Microbiology, Virology and Immunology",
-        "Immunology"
-    ],
-    "Discipline": "Neuroscience",
-    "Format": [
-        "NIFTI"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://148.187.98.42:8443/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.25493_66PB-17W",
-    "MetadataAccess": [
-        "10.25493_66PB-17W"
-    ],
-    "PublicationTimestamp": "2019-05-23T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Human Brain Project"
-    ],
-    "RelatedIdentifier": [
-        "https://doi.org/10.1016/j.neuroimage.2016.11.066"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International"
-    ],
-    "author": [
-        "Mangin, Jean-Fran\u00e7ois"
-    ],
-    "fulltext": "10.25493_66PB-17W;2019-12-10T12:41:50Z;https://doi.org/10.25493/66PB-17W;Probability map of bundle lh_PoC-SM_0 (atlas of superficial white matter fibre bundles, version 2018);2019-05-23T14:05:20.724Z;This data contains the probability map of a short fibre bundle connecting the left hemisphere Postcentral and Supramarginal regions of the Desikan-Killiany atlas, in the MNI ICBM152 reference brain. This bundle was identified using a hybrid approach, incorporating anatomical information (from cortical regions of interest) and fibre shape (fibre clustering), from the tractography datasets of 78 subjects in the Neurospin\u2019s ARCHI database. The map shows the probability of finding a fibre belonging to the bundle in each voxel of the reference brain. The maximum probability corresponds to the voxels with the highest number of putative fibres going through.;neuroscience;brain mapping;imaging;english;dataset;The Human Brain Project;Guevara, Miguel;Rom\u00e1n, Claudio;Houenou, Josselin;Duclap, Delphine;Poupon, Cyril;Mangin, Jean-Fran\u00e7ois;Guevara, Pamela;Mangin, Jean-Fran\u00e7ois;NIFTI;Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International;https://doi.org/10.1016/j.neuroimage.2016.11.066",
-    "group": "hbp",
-    "groups": [
-        {
-            "name": "hbp"
-        }
-    ],
-    "name": "0ed9dd69-526a-5bd5-b784-82332cfc4c44",
-    "notes": [
-        "This data contains the probability map of a short fibre bundle connecting the left hemisphere Postcentral and Supramarginal regions of the Desikan-Killiany atlas, in the MNI ICBM152 reference brain. This bundle was identified using a hybrid approach, incorporating anatomical information (from cortical regions of interest) and fibre shape (fibre clustering), from the tractography datasets of 78 subjects in the Neurospin\u2019s ARCHI database. The map shows the probability of finding a fibre belonging to the bundle in each voxel of the reference brain. The maximum probability corresponds to the voxels with the highest number of putative fibres going through."
-    ],
-    "oai_identifier": [
-        "10.25493_66PB-17W"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "neuroscience"
-        },
-        {
-            "name": "brain mapping"
-        },
-        {
-            "name": "imaging"
-        }
-    ],
-    "title": [
-        "Probability map of bundle lh_PoC-SM_0 (atlas of superficial white matter fibre bundles, version 2018)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/hbp-oai_dc/SET_1/json/0faeb379-dcf8-5ab7-b7b3-e78d0bffe2c0.json b/oaitestdata/hbp-oai_dc/SET_1/json/0faeb379-dcf8-5ab7-b7b3-e78d0bffe2c0.json
deleted file mode 100644
index 5696bd01..00000000
--- a/oaitestdata/hbp-oai_dc/SET_1/json/0faeb379-dcf8-5ab7-b7b3-e78d0bffe2c0.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "https://www.humanbrainproject.eu/"
-    ],
-    "Contributor": [
-        "Poupon, Cyril",
-        "Mangin, Jean-Fran\u00e7ois",
-        "Duclap, Delphine",
-        "Rom\u00e1n, Claudio",
-        "Guevara, Pamela",
-        "Guevara, Miguel",
-        "Houenou, Josselin"
-    ],
-    "DOI": "http://dx.doi.org/10.25493/A4QS-825",
-    "DiscHierarchy": [
-        "3.2.1.5",
-        "Microbiology, Virology and Immunology",
-        "Immunology"
-    ],
-    "Discipline": "Neuroscience",
-    "Format": [
-        "NIFTI"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://148.187.98.42:8443/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.25493_A4QS-825",
-    "MetadataAccess": [
-        "10.25493_A4QS-825"
-    ],
-    "PublicationTimestamp": "2019-05-23T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Human Brain Project"
-    ],
-    "RelatedIdentifier": [
-        "https://doi.org/10.1016/j.neuroimage.2016.11.066"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International"
-    ],
-    "author": [
-        "Mangin, Jean-Fran\u00e7ois"
-    ],
-    "fulltext": "10.25493_A4QS-825;2019-12-10T12:41:51Z;https://doi.org/10.25493/A4QS-825;Probability map of bundle rh_IP-MT_0 (atlas of superficial white matter fibre bundles, version 2018);2019-05-23T14:34:48.295Z;This data contains the probability map of a short fibre bundle connecting the right hemisphere Inferior Parietal and Middle Temporal regions of the Desikan-Killiany atlas, in the MNI ICBM152 reference brain. This bundle was identified using a hybrid approach, incorporating anatomical information (from cortical regions of interest) and fibre shape (fibre clustering), from the tractography datasets of 78 subjects in the Neurospin\u2019s ARCHI database. The map shows the probability of finding a fibre belonging to the bundle in each voxel of the reference brain. The maximum probability corresponds to the voxels with the highest number of putative fibres going through.;neuroscience;brain mapping;imaging;english;dataset;The Human Brain Project;Guevara, Miguel;Rom\u00e1n, Claudio;Houenou, Josselin;Duclap, Delphine;Poupon, Cyril;Mangin, Jean-Fran\u00e7ois;Guevara, Pamela;Mangin, Jean-Fran\u00e7ois;NIFTI;Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International;https://doi.org/10.1016/j.neuroimage.2016.11.066",
-    "group": "hbp",
-    "groups": [
-        {
-            "name": "hbp"
-        }
-    ],
-    "name": "0faeb379-dcf8-5ab7-b7b3-e78d0bffe2c0",
-    "notes": [
-        "This data contains the probability map of a short fibre bundle connecting the right hemisphere Inferior Parietal and Middle Temporal regions of the Desikan-Killiany atlas, in the MNI ICBM152 reference brain. This bundle was identified using a hybrid approach, incorporating anatomical information (from cortical regions of interest) and fibre shape (fibre clustering), from the tractography datasets of 78 subjects in the Neurospin\u2019s ARCHI database. The map shows the probability of finding a fibre belonging to the bundle in each voxel of the reference brain. The maximum probability corresponds to the voxels with the highest number of putative fibres going through."
-    ],
-    "oai_identifier": [
-        "10.25493_A4QS-825"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "neuroscience"
-        },
-        {
-            "name": "brain mapping"
-        },
-        {
-            "name": "imaging"
-        }
-    ],
-    "title": [
-        "Probability map of bundle rh_IP-MT_0 (atlas of superficial white matter fibre bundles, version 2018)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/hbp-oai_dc/SET_1/json/0fee7686-dd4f-5913-9a8b-bbf520e58ac1.json b/oaitestdata/hbp-oai_dc/SET_1/json/0fee7686-dd4f-5913-9a8b-bbf520e58ac1.json
deleted file mode 100644
index ed775a9c..00000000
--- a/oaitestdata/hbp-oai_dc/SET_1/json/0fee7686-dd4f-5913-9a8b-bbf520e58ac1.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "https://www.humanbrainproject.eu/"
-    ],
-    "Contributor": [
-        "Poupon, Cyril",
-        "Mangin, Jean-Fran\u00e7ois",
-        "Duclap, Delphine",
-        "Rom\u00e1n, Claudio",
-        "Guevara, Pamela",
-        "Guevara, Miguel",
-        "Houenou, Josselin"
-    ],
-    "DOI": "http://dx.doi.org/10.25493/C07S-0A0",
-    "DiscHierarchy": [
-        "3.2.1.5",
-        "Microbiology, Virology and Immunology",
-        "Immunology"
-    ],
-    "Discipline": "Neuroscience",
-    "Format": [
-        "NIFTI"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://148.187.98.42:8443/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.25493_C07S-0A0",
-    "MetadataAccess": [
-        "10.25493_C07S-0A0"
-    ],
-    "PublicationTimestamp": "2019-05-23T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Human Brain Project"
-    ],
-    "RelatedIdentifier": [
-        "https://doi.org/10.1016/j.neuroimage.2016.11.066"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International"
-    ],
-    "author": [
-        "Mangin, Jean-Fran\u00e7ois"
-    ],
-    "fulltext": "10.25493_C07S-0A0;2019-12-10T12:41:56Z;https://doi.org/10.25493/C07S-0A0;Probability map of bundle lh_IP-MT_0 (atlas of superficial white matter fibre bundles, version 2018);2019-05-23T13:53:01.054Z;This data contains the probability map of a short fibre bundle connecting the left hemisphere Inferior Parietal and Middle Temporal regions of the Desikan-Killiany atlas, in the MNI ICBM152 reference brain. This bundle was identified using a hybrid approach, incorporating anatomical information (from cortical regions of interest) and fibre shape (fibre clustering), from the tractography datasets of 78 subjects in the Neurospin\u2019s ARCHI database. The map shows the probability of finding a fibre belonging to the bundle in each voxel of the reference brain. The maximum probability corresponds to the voxels with the highest number of putative fibres going through.;neuroscience;brain mapping;imaging;english;dataset;The Human Brain Project;Guevara, Miguel;Rom\u00e1n, Claudio;Houenou, Josselin;Duclap, Delphine;Poupon, Cyril;Mangin, Jean-Fran\u00e7ois;Guevara, Pamela;Mangin, Jean-Fran\u00e7ois;NIFTI;Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International;https://doi.org/10.1016/j.neuroimage.2016.11.066",
-    "group": "hbp",
-    "groups": [
-        {
-            "name": "hbp"
-        }
-    ],
-    "name": "0fee7686-dd4f-5913-9a8b-bbf520e58ac1",
-    "notes": [
-        "This data contains the probability map of a short fibre bundle connecting the left hemisphere Inferior Parietal and Middle Temporal regions of the Desikan-Killiany atlas, in the MNI ICBM152 reference brain. This bundle was identified using a hybrid approach, incorporating anatomical information (from cortical regions of interest) and fibre shape (fibre clustering), from the tractography datasets of 78 subjects in the Neurospin\u2019s ARCHI database. The map shows the probability of finding a fibre belonging to the bundle in each voxel of the reference brain. The maximum probability corresponds to the voxels with the highest number of putative fibres going through."
-    ],
-    "oai_identifier": [
-        "10.25493_C07S-0A0"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "neuroscience"
-        },
-        {
-            "name": "brain mapping"
-        },
-        {
-            "name": "imaging"
-        }
-    ],
-    "title": [
-        "Probability map of bundle lh_IP-MT_0 (atlas of superficial white matter fibre bundles, version 2018)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/hbp-oai_dc/SET_1/json/1ae4430c-4f24-55a1-9e06-c9ad84fbbb22.json b/oaitestdata/hbp-oai_dc/SET_1/json/1ae4430c-4f24-55a1-9e06-c9ad84fbbb22.json
deleted file mode 100644
index fd5b3af4..00000000
--- a/oaitestdata/hbp-oai_dc/SET_1/json/1ae4430c-4f24-55a1-9e06-c9ad84fbbb22.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "https://www.humanbrainproject.eu/"
-    ],
-    "Contributor": [
-        "Zilles, Karl",
-        "Kedo, O.",
-        "Palomero-Gallagher, Nicola",
-        "Bludau, Sebastian",
-        "Amunts, Katrin"
-    ],
-    "DOI": "http://dx.doi.org/10.25493/DW5A-YMD",
-    "DiscHierarchy": [
-        "3.2",
-        "Life Sciences",
-        "Medicine"
-    ],
-    "Discipline": "Neuroscience",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://148.187.98.42:8443/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.25493_DW5A-YMD",
-    "MetadataAccess": [
-        "10.25493_DW5A-YMD"
-    ],
-    "PublicationTimestamp": "2019-08-28T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Human Brain Project"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International"
-    ],
-    "author": [
-        "Amunts, Katrin"
-    ],
-    "fulltext": "10.25493_DW5A-YMD;2019-12-10T12:41:50Z;https://doi.org/10.25493/DW5A-YMD;Reference delineations of area HATA (Hippocampus) in individual sections of the BigBrain;2019-08-28T10:41:13.497Z;This dataset contains cytoarchitectonic delineations of area HATA (Hippocampus) in the BigBrain dataset [Amunts et al. 2013]. The delineations were created after identification of the area in the histological, cell-stained sections based on the cytoarchitectonic criteria. Mappings are available on every 15th to 60th section of the HATA in both hemispheres. They were then transformed to the sections of the 3D reconstructed BigBrain space using the transformations used in Amunts et al. 2013, which were provided by Claude Lepage (McGill).;neuroscience;imaging;histology;brain mapping;english;dataset;The Human Brain Project;Kedo, O.;Zilles, Karl;Palomero-Gallagher, Nicola;Bludau, Sebastian;Amunts, Katrin;Amunts, Katrin;Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International",
-    "group": "hbp",
-    "groups": [
-        {
-            "name": "hbp"
-        }
-    ],
-    "name": "1ae4430c-4f24-55a1-9e06-c9ad84fbbb22",
-    "notes": [
-        "This dataset contains cytoarchitectonic delineations of area HATA (Hippocampus) in the BigBrain dataset [Amunts et al. 2013]. The delineations were created after identification of the area in the histological, cell-stained sections based on the cytoarchitectonic criteria. Mappings are available on every 15th to 60th section of the HATA in both hemispheres. They were then transformed to the sections of the 3D reconstructed BigBrain space using the transformations used in Amunts et al. 2013, which were provided by Claude Lepage (McGill)."
-    ],
-    "oai_identifier": [
-        "10.25493_DW5A-YMD"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "neuroscience"
-        },
-        {
-            "name": "imaging"
-        },
-        {
-            "name": "histology"
-        },
-        {
-            "name": "brain mapping"
-        }
-    ],
-    "title": [
-        "Reference delineations of area HATA (Hippocampus) in individual sections of the BigBrain"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/hbp-oai_dc/SET_1/json/1b8133ff-8284-5ccb-841f-93d7e99f7347.json b/oaitestdata/hbp-oai_dc/SET_1/json/1b8133ff-8284-5ccb-841f-93d7e99f7347.json
deleted file mode 100644
index fc73d4ed..00000000
--- a/oaitestdata/hbp-oai_dc/SET_1/json/1b8133ff-8284-5ccb-841f-93d7e99f7347.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "https://www.humanbrainproject.eu/"
-    ],
-    "Contributor": [
-        "Zilles, Karl",
-        "Hoemke, L.",
-        "Eickhoff, Simon B.",
-        "Schleicher, Axel",
-        "Hermann, K.",
-        "Scheperjans, Filip",
-        "Mohlberg, Hartmut",
-        "Amunts, Katrin"
-    ],
-    "DOI": "http://dx.doi.org/10.25493/SQVP-GK1",
-    "DiscHierarchy": [
-        "3.2",
-        "Life Sciences",
-        "Medicine"
-    ],
-    "Discipline": "Neuroscience",
-    "Format": [
-        "NIFTI"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://148.187.98.42:8443/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.25493_SQVP-GK1",
-    "MetadataAccess": [
-        "10.25493_SQVP-GK1"
-    ],
-    "PublicationTimestamp": "2019-06-04T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Human Brain Project"
-    ],
-    "RelatedIdentifier": [
-        "https://doi.org/10.1093/cercor/bhm241",
-        "https://doi.org/10.1093/cercor/bhm116"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International"
-    ],
-    "author": [
-        "Amunts, Katrin"
-    ],
-    "fulltext": "10.25493_SQVP-GK1;2019-12-10T12:41:55Z;https://doi.org/10.25493/SQVP-GK1;Probabilistic cytoarchitectonic map of Area 5Ci (SPL) (v8.4);2019-06-04T16:33:20.657Z;This dataset contains the distinct architectonic Area 5Ci (SPL) in the individual, single subject template of the MNI Colin 27 as well as the MNI ICBM 152 2009c nonlinear asymmetric reference space. As part of the JuBrain cytoarchitectonic atlas, the area was identified using cytoarchitectonic analysis on cell-body-stained histological sections of 10 human postmortem brains obtained from the body donor program of the University of D\u00fcsseldorf. The results of the cytoarchitectonic analysis were then mapped to both reference spaces, where each voxel was assigned the probability to belong to Area 5Ci (SPL). The probability map of Area 5Ci (SPL) are provided in the NifTi format for each brain reference space and hemisphere. The JuBrain atlas relies on a modular, flexible and adaptive framework containing workflows to create the probabilistic brain maps for these structures. Note that methodological improvements and integration of new brain structures may lead to small deviations in earlier released datasets.;neuroscience;histology;imaging;brain mapping;english;dataset;The Human Brain Project;Scheperjans, Filip;Hermann, K.;Eickhoff, Simon B.;Amunts, Katrin;Schleicher, Axel;Hoemke, L.;Mohlberg, Hartmut;Zilles, Karl;Amunts, Katrin;NIFTI;Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International;https://doi.org/10.1093/cercor/bhm241;https://doi.org/10.1093/cercor/bhm116",
-    "group": "hbp",
-    "groups": [
-        {
-            "name": "hbp"
-        }
-    ],
-    "name": "1b8133ff-8284-5ccb-841f-93d7e99f7347",
-    "notes": [
-        "This dataset contains the distinct architectonic Area 5Ci (SPL) in the individual, single subject template of the MNI Colin 27 as well as the MNI ICBM 152 2009c nonlinear asymmetric reference space. As part of the JuBrain cytoarchitectonic atlas, the area was identified using cytoarchitectonic analysis on cell-body-stained histological sections of 10 human postmortem brains obtained from the body donor program of the University of D\u00fcsseldorf. The results of the cytoarchitectonic analysis were then mapped to both reference spaces, where each voxel was assigned the probability to belong to Area 5Ci (SPL). The probability map of Area 5Ci (SPL) are provided in the NifTi format for each brain reference space and hemisphere. The JuBrain atlas relies on a modular, flexible and adaptive framework containing workflows to create the probabilistic brain maps for these structures. Note that methodological improvements and integration of new brain structures may lead to small deviations in earlier released datasets."
-    ],
-    "oai_identifier": [
-        "10.25493_SQVP-GK1"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "neuroscience"
-        },
-        {
-            "name": "histology"
-        },
-        {
-            "name": "imaging"
-        },
-        {
-            "name": "brain mapping"
-        }
-    ],
-    "title": [
-        "Probabilistic cytoarchitectonic map of Area 5Ci (SPL) (v8.4)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/hbp-oai_dc/SET_1/json/1cc32ec2-2d15-53db-959f-d5d78ede5234.json b/oaitestdata/hbp-oai_dc/SET_1/json/1cc32ec2-2d15-53db-959f-d5d78ede5234.json
deleted file mode 100644
index aa1fcf26..00000000
--- a/oaitestdata/hbp-oai_dc/SET_1/json/1cc32ec2-2d15-53db-959f-d5d78ede5234.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "https://www.humanbrainproject.eu/"
-    ],
-    "Contributor": [
-        "Zilles, Karl",
-        "Hoemke, L.",
-        "Eickhoff, Simon B.",
-        "Schleicher, Axel",
-        "Hermann, K.",
-        "Scheperjans, Filip",
-        "Mohlberg, Hartmut",
-        "Amunts, Katrin"
-    ],
-    "DOI": "http://dx.doi.org/10.25493/Y12F-YMU",
-    "DiscHierarchy": [
-        "3.2",
-        "Life Sciences",
-        "Medicine"
-    ],
-    "Discipline": "Neuroscience",
-    "Format": [
-        "NIFTI"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://148.187.98.42:8443/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.25493_Y12F-YMU",
-    "MetadataAccess": [
-        "10.25493_Y12F-YMU"
-    ],
-    "PublicationTimestamp": "2019-06-04T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Human Brain Project"
-    ],
-    "RelatedIdentifier": [
-        "https://doi.org/10.1093/cercor/bhm241",
-        "https://doi.org/10.1093/cercor/bhm116"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International"
-    ],
-    "author": [
-        "Amunts, Katrin"
-    ],
-    "fulltext": "10.25493_Y12F-YMU;2019-12-10T12:41:53Z;https://doi.org/10.25493/Y12F-YMU;Probabilistic cytoarchitectonic map of Area 5M (SPL) (v8.4);2019-06-04T16:42:00.620Z;This dataset contains the distinct architectonic Area 5M (SPL) in the individual, single subject template of the MNI Colin 27 as well as the MNI ICBM 152 2009c nonlinear asymmetric reference space. As part of the JuBrain cytoarchitectonic atlas, the area was identified using cytoarchitectonic analysis on cell-body-stained histological sections of 10 human postmortem brains obtained from the body donor program of the University of D\u00fcsseldorf. The results of the cytoarchitectonic analysis were then mapped to both reference spaces, where each voxel was assigned the probability to belong to Area 5M (SPL). The probability map of Area 5M (SPL) are provided in the NifTi format for each brain reference space and hemisphere. The JuBrain atlas relies on a modular, flexible and adaptive framework containing workflows to create the probabilistic brain maps for these structures. Note that methodological improvements and integration of new brain structures may lead to small deviations in earlier released datasets.;neuroscience;histology;imaging;brain mapping;english;dataset;The Human Brain Project;Scheperjans, Filip;Hermann, K.;Eickhoff, Simon B.;Amunts, Katrin;Schleicher, Axel;Hoemke, L.;Mohlberg, Hartmut;Zilles, Karl;Amunts, Katrin;NIFTI;Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International;https://doi.org/10.1093/cercor/bhm241;https://doi.org/10.1093/cercor/bhm116",
-    "group": "hbp",
-    "groups": [
-        {
-            "name": "hbp"
-        }
-    ],
-    "name": "1cc32ec2-2d15-53db-959f-d5d78ede5234",
-    "notes": [
-        "This dataset contains the distinct architectonic Area 5M (SPL) in the individual, single subject template of the MNI Colin 27 as well as the MNI ICBM 152 2009c nonlinear asymmetric reference space. As part of the JuBrain cytoarchitectonic atlas, the area was identified using cytoarchitectonic analysis on cell-body-stained histological sections of 10 human postmortem brains obtained from the body donor program of the University of D\u00fcsseldorf. The results of the cytoarchitectonic analysis were then mapped to both reference spaces, where each voxel was assigned the probability to belong to Area 5M (SPL). The probability map of Area 5M (SPL) are provided in the NifTi format for each brain reference space and hemisphere. The JuBrain atlas relies on a modular, flexible and adaptive framework containing workflows to create the probabilistic brain maps for these structures. Note that methodological improvements and integration of new brain structures may lead to small deviations in earlier released datasets."
-    ],
-    "oai_identifier": [
-        "10.25493_Y12F-YMU"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "neuroscience"
-        },
-        {
-            "name": "histology"
-        },
-        {
-            "name": "imaging"
-        },
-        {
-            "name": "brain mapping"
-        }
-    ],
-    "title": [
-        "Probabilistic cytoarchitectonic map of Area 5M (SPL) (v8.4)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/hbp-oai_dc/SET_1/json/1d0f507b-440a-5ed6-a9ba-73215ce7e972.json b/oaitestdata/hbp-oai_dc/SET_1/json/1d0f507b-440a-5ed6-a9ba-73215ce7e972.json
deleted file mode 100644
index fad381d8..00000000
--- a/oaitestdata/hbp-oai_dc/SET_1/json/1d0f507b-440a-5ed6-a9ba-73215ce7e972.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "https://www.humanbrainproject.eu/"
-    ],
-    "Contributor": [
-        "Amunts, Katrin",
-        "Kiwitz, Kai",
-        "Schiffer, Christian ",
-        "Dickscheid, Timo"
-    ],
-    "DOI": "http://dx.doi.org/10.25493/DGEZ-Q93",
-    "DiscHierarchy": [
-        "5.1.2.2",
-        "Mechanics and Constructive Mechanical Engineering",
-        "Mechanicsy"
-    ],
-    "Discipline": "Neuroscience",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://148.187.98.42:8443/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.25493_DGEZ-Q93",
-    "MetadataAccess": [
-        "10.25493_DGEZ-Q93"
-    ],
-    "PublicationTimestamp": "2019-05-23T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Human Brain Project"
-    ],
-    "RelatedIdentifier": [
-        "https://doi.org/10.1006/nimg.1998.0385",
-        "https://doi.org/10.1007/978-3-030-00931-1_76",
-        "https://doi.org/10.1109/ISBI.2017.7950666",
-        "https://doi.org/10.1126/science.1235381"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International"
-    ],
-    "author": [
-        "Amunts, Katrin"
-    ],
-    "fulltext": "10.25493_DGEZ-Q93;2019-12-10T12:41:53Z;https://doi.org/10.25493/DGEZ-Q93;Ultrahigh resolution 3D cytoarchitectonic map of Area hOc1 (V1, 17, CalcS) created by a Deep-Learning assisted workflow;2019-05-23T12:53:24.494Z;This dataset contains automatically created cytoarchitectonic maps of Area hOc1 (V1, 17, CalcS) in the BigBrain dataset [Amunts et al. 2013]. The mappings were created using Deep Convolutional Neural networks based on the idea presented in Spitzer et al. 2017 and Spitzer et al. 2018, which were trained on delineations on every 120th section created using the semi-automatic method presented in Schleicher et al. 1999. Mappings are available on every section. Their quality was observed by a trained neuroscientist to exclude sections with low quality results from further processing. Automatic mappings were then transformed to the 3D reconstructed BigBrain space using transformations used in Amunts et al. 2013, which were provided by Claude Lepage (McGill). Individual sections were used to assemble a 3D volume of the area, low quality results were replaced by interpolations between nearest neighboring sections. The volume was then smoothed using an 11\u00b3 median filter and largest connected components were identified to remove false positive results of the classification algorithm.\nThe dataset consists of a single HDF5 file containing the volume in RAS dimension ordering and 20 micron isotropic resolution in the dataset \u201cvolume\u201d and affine transformation matrix in the dataset \u201caffine\u201d. An additional dataset \u201cinterpolation_info\u201d contains a vector with an integer value for each section which indicates if a section was interpolated due to low quality results (value 2) or not (value 1).\nDue to the large size of the volume, it\u2019s recommended to view the data online using the provided viewer link.\n;neuroscience;imaging;histology;brain mapping;analysis technique;english;dataset;The Human Brain Project;Schiffer, Christian ;Kiwitz, Kai;Amunts, Katrin;Dickscheid, Timo;Amunts, Katrin;Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International;https://doi.org/10.1006/nimg.1998.0385;https://doi.org/10.1007/978-3-030-00931-1_76;https://doi.org/10.1109/ISBI.2017.7950666;https://doi.org/10.1126/science.1235381",
-    "group": "hbp",
-    "groups": [
-        {
-            "name": "hbp"
-        }
-    ],
-    "name": "1d0f507b-440a-5ed6-a9ba-73215ce7e972",
-    "notes": [
-        "This dataset contains automatically created cytoarchitectonic maps of Area hOc1 (V1, 17, CalcS) in the BigBrain dataset [Amunts et al. 2013]. The mappings were created using Deep Convolutional Neural networks based on the idea presented in Spitzer et al. 2017 and Spitzer et al. 2018, which were trained on delineations on every 120th section created using the semi-automatic method presented in Schleicher et al. 1999. Mappings are available on every section. Their quality was observed by a trained neuroscientist to exclude sections with low quality results from further processing. Automatic mappings were then transformed to the 3D reconstructed BigBrain space using transformations used in Amunts et al. 2013, which were provided by Claude Lepage (McGill). Individual sections were used to assemble a 3D volume of the area, low quality results were replaced by interpolations between nearest neighboring sections. The volume was then smoothed using an 11\u00b3 median filter and largest connected components were identified to remove false positive results of the classification algorithm.\nThe dataset consists of a single HDF5 file containing the volume in RAS dimension ordering and 20 micron isotropic resolution in the dataset \u201cvolume\u201d and affine transformation matrix in the dataset \u201caffine\u201d. An additional dataset \u201cinterpolation_info\u201d contains a vector with an integer value for each section which indicates if a section was interpolated due to low quality results (value 2) or not (value 1).\nDue to the large size of the volume, it\u2019s recommended to view the data online using the provided viewer link.\n"
-    ],
-    "oai_identifier": [
-        "10.25493_DGEZ-Q93"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "neuroscience"
-        },
-        {
-            "name": "imaging"
-        },
-        {
-            "name": "histology"
-        },
-        {
-            "name": "brain mapping"
-        },
-        {
-            "name": "analysis technique"
-        }
-    ],
-    "title": [
-        "Ultrahigh resolution 3D cytoarchitectonic map of Area hOc1 (V1, 17, CalcS) created by a Deep-Learning assisted workflow"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/hbp-oai_dc/SET_1/json/1d73177a-0026-5e1b-8853-cef6c46e1b61.json b/oaitestdata/hbp-oai_dc/SET_1/json/1d73177a-0026-5e1b-8853-cef6c46e1b61.json
deleted file mode 100644
index ed5c50db..00000000
--- a/oaitestdata/hbp-oai_dc/SET_1/json/1d73177a-0026-5e1b-8853-cef6c46e1b61.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "https://www.humanbrainproject.eu/"
-    ],
-    "Contributor": [
-        "Poupon, Cyril",
-        "Mangin, Jean-Fran\u00e7ois",
-        "Duclap, Delphine",
-        "Leboyer, Marion ",
-        "Fillard, Pierre",
-        "Houenou, Josselin",
-        "Guevara, Pamela",
-        "Le Bihan, Denis J.",
-        "Marrakchi-Kacem, Linda "
-    ],
-    "DOI": "http://dx.doi.org/10.25493/D5CG-SX6",
-    "DiscHierarchy": [
-        "3.2.1.5",
-        "Microbiology, Virology and Immunology",
-        "Immunology"
-    ],
-    "Discipline": "Neuroscience",
-    "Format": [
-        "NIFTI"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://148.187.98.42:8443/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.25493_D5CG-SX6",
-    "MetadataAccess": [
-        "10.25493_D5CG-SX6"
-    ],
-    "PublicationTimestamp": "2019-06-14T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Human Brain Project"
-    ],
-    "RelatedIdentifier": [
-        "https://doi.org/10.1016/j.neuroimage.2012.02.071"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International"
-    ],
-    "author": [
-        "Mangin, Jean-Fran\u00e7ois"
-    ],
-    "fulltext": "10.25493_D5CG-SX6;2019-12-10T12:41:56Z;https://doi.org/10.25493/D5CG-SX6;Probabilistic map of the left inferior longitudinal fasciculus (atlas of deep white matter fibre bundles, version 2018);2019-06-14T13:24:39.671Z;This data contains the probability map of the left inferior longitudinal fasciculus (atlas of deep white matter fibre bundles, version 2018), in the MNI ICBM152 reference brain. This bundle was identified by fibre clustering, from the tractography datasets of 78 subjects in Neurospin\u2019s ARCHI database. The map shows the probability of finding a fibre belonging to the bundle in each voxel of the reference brain. The maximum probability corresponds to the voxels with the highest number of putative fibres going through.;neuroscience;brain mapping;imaging;english;dataset;The Human Brain Project;Guevara, Pamela;Duclap, Delphine;Poupon, Cyril;Marrakchi-Kacem, Linda ;Fillard, Pierre;Le Bihan, Denis J.;Leboyer, Marion ;Houenou, Josselin;Mangin, Jean-Fran\u00e7ois;Mangin, Jean-Fran\u00e7ois;NIFTI;Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International;https://doi.org/10.1016/j.neuroimage.2012.02.071",
-    "group": "hbp",
-    "groups": [
-        {
-            "name": "hbp"
-        }
-    ],
-    "name": "1d73177a-0026-5e1b-8853-cef6c46e1b61",
-    "notes": [
-        "This data contains the probability map of the left inferior longitudinal fasciculus (atlas of deep white matter fibre bundles, version 2018), in the MNI ICBM152 reference brain. This bundle was identified by fibre clustering, from the tractography datasets of 78 subjects in Neurospin\u2019s ARCHI database. The map shows the probability of finding a fibre belonging to the bundle in each voxel of the reference brain. The maximum probability corresponds to the voxels with the highest number of putative fibres going through."
-    ],
-    "oai_identifier": [
-        "10.25493_D5CG-SX6"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "neuroscience"
-        },
-        {
-            "name": "brain mapping"
-        },
-        {
-            "name": "imaging"
-        }
-    ],
-    "title": [
-        "Probabilistic map of the left inferior longitudinal fasciculus (atlas of deep white matter fibre bundles, version 2018)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/hbp-oai_dc/SET_1/json/1e3a71fb-a446-55d6-847e-0aeeeed53388.json b/oaitestdata/hbp-oai_dc/SET_1/json/1e3a71fb-a446-55d6-847e-0aeeeed53388.json
deleted file mode 100644
index 53b91eec..00000000
--- a/oaitestdata/hbp-oai_dc/SET_1/json/1e3a71fb-a446-55d6-847e-0aeeeed53388.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "https://www.humanbrainproject.eu/"
-    ],
-    "Contributor": [
-        "Zilles, Karl",
-        "Schleicher, Axel",
-        "Bacha-Trams, Maraike",
-        "Amunts, Katrin",
-        "Friederici, Angela D.",
-        "Palomero-Gallagher, Nicola",
-        "Caspers, S."
-    ],
-    "DOI": "http://dx.doi.org/10.25493/VSFY-EYF",
-    "DiscHierarchy": [
-        "1.2",
-        "Humanities",
-        "History"
-    ],
-    "Discipline": "Neuroscience",
-    "Format": [
-        "xlsx, tif, txt"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://148.187.98.42:8443/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.25493_VSFY-EYF",
-    "MetadataAccess": [
-        "10.25493_VSFY-EYF"
-    ],
-    "PublicationTimestamp": "2019-06-12T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Human Brain Project"
-    ],
-    "RelatedIdentifier": [
-        "https://doi.org/10.1093/cercor/bhs048",
-        "https://doi.org/10.1016/j.cortex.2014.07.007"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International"
-    ],
-    "author": [
-        "Zilles, Karl",
-        "Palomero-Gallagher, Nicola"
-    ],
-    "fulltext": "10.25493_VSFY-EYF;2019-12-10T12:41:57Z;https://doi.org/10.25493/VSFY-EYF;Density measurements of different receptors for Area PF;2019-06-12T08:46:18.120Z;This dataset contains the densities (in fmol/mg protein) of 16 receptors for classical neurotransmitters in Area PF using quantitative in vitro autoradiography. The receptor density measurements can be provided in three ways: (fp) as density fingerprints (average across samples; mean density and standard deviation for each of the 16 receptors), (pr) as laminar density profiles (exemplary data from one sample; average course of the density from the pial surface to the border between layer VI and the white matter for each receptor), and (ar) as color-coded autoradiographs (exemplary data from one sample; laminar density distribution patterns for each receptor labeling). \nThis dataset contains the following receptor density measurements based on the labeling of these receptor binding sites: \n\nAMPA (glutamate; labelled with [\u00b3H]AMPA): fp\n\nkainate (glutamate; [\u00b3H]kainate): fp\n\nNMDA (glutamate; [\u00b3H]MK-801): fp\n\nmGluR2/3 (glutamate; [\u00b3H] LY 341 495): fp\n\nGABA<sub>A</sub> (GABA; [\u00b3H]muscimol): fp\n\nGABA<sub>B</sub> (GABA; [\u00b3H] CGP54626): fp\n\nGABA<sub>A</sub> associated benzodiazepine binding sites (BZ; [\u00b3H]flumazenil): fp\n\nmuscarinic M\u2081 (acetylcholine; [\u00b3H]pirenzepine): fp\n\nmuscarinic M\u2082 (acetylcholine; [\u00b3H]oxotremorine-M): fp\n\nmuscarinic M\u2083 (acetylcholine; [\u00b3H]4-DAMP): fp\n\nnicotinic \u03b1\u2084\u03b2\u2082 (acetylcholine; [\u00b3H]epibatidine): fp\n\n\u03b1\u2081 (noradrenalin; [\u00b3H]prazosin): fp\n\n\u03b1\u2082 (noradrenalin; [\u00b3H]UK-14,304): fp\n\n5-HT\u2081<sub>A</sub> (serotonin; [\u00b3H]8-OH-DPAT): fp\n\n5-HT\u2082 (serotonin; [\u00b3H]ketanserin): fp\n\nD\u2081 (dopamine; [\u00b3H]SCH23390): fp\n\nWhich sample was used for which receptor density measurement is stated in metadata files accompanying the main data repository. For methodological details, see Zilles et al. (2002), and in Palomero-Gallagher and Zilles (2018).\n\nZilles, K. et al. (2002). Quantitative analysis of cyto- and receptorarchitecture of the human brain, pp. 573-602. In: Brain Mapping: The Methods, 2nd edition (A.W. Toga and J.C. Mazziotta, eds.). San Diego, Academic Press.\n\nPalomero-Gallagher N, Zilles K. (2018) Cyto- and receptorarchitectonic mapping of the human brain. In: Handbook of Clinical Neurology 150: 355-387;neuroscience;brain mapping;histology;english;dataset;The Human Brain Project;Zilles, Karl;Bacha-Trams, Maraike;Palomero-Gallagher, Nicola;Amunts, Katrin;Friederici, Angela D.;Caspers, S.;Schleicher, Axel;Palomero-Gallagher, Nicola;Zilles, Karl;xlsx, tif, txt;Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International;https://doi.org/10.1093/cercor/bhs048;https://doi.org/10.1016/j.cortex.2014.07.007",
-    "group": "hbp",
-    "groups": [
-        {
-            "name": "hbp"
-        }
-    ],
-    "name": "1e3a71fb-a446-55d6-847e-0aeeeed53388",
-    "notes": [
-        "This dataset contains the densities (in fmol/mg protein) of 16 receptors for classical neurotransmitters in Area PF using quantitative in vitro autoradiography. The receptor density measurements can be provided in three ways: (fp) as density fingerprints (average across samples; mean density and standard deviation for each of the 16 receptors), (pr) as laminar density profiles (exemplary data from one sample; average course of the density from the pial surface to the border between layer VI and the white matter for each receptor), and (ar) as color-coded autoradiographs (exemplary data from one sample; laminar density distribution patterns for each receptor labeling). \nThis dataset contains the following receptor density measurements based on the labeling of these receptor binding sites: \n\nAMPA (glutamate; labelled with [\u00b3H]AMPA): fp\n\nkainate (glutamate; [\u00b3H]kainate): fp\n\nNMDA (glutamate; [\u00b3H]MK-801): fp\n\nmGluR2/3 (glutamate; [\u00b3H] LY 341 495): fp\n\nGABA<sub>A</sub> (GABA; [\u00b3H]muscimol): fp\n\nGABA<sub>B</sub> (GABA; [\u00b3H] CGP54626): fp\n\nGABA<sub>A</sub> associated benzodiazepine binding sites (BZ; [\u00b3H]flumazenil): fp\n\nmuscarinic M\u2081 (acetylcholine; [\u00b3H]pirenzepine): fp\n\nmuscarinic M\u2082 (acetylcholine; [\u00b3H]oxotremorine-M): fp\n\nmuscarinic M\u2083 (acetylcholine; [\u00b3H]4-DAMP): fp\n\nnicotinic \u03b1\u2084\u03b2\u2082 (acetylcholine; [\u00b3H]epibatidine): fp\n\n\u03b1\u2081 (noradrenalin; [\u00b3H]prazosin): fp\n\n\u03b1\u2082 (noradrenalin; [\u00b3H]UK-14,304): fp\n\n5-HT\u2081<sub>A</sub> (serotonin; [\u00b3H]8-OH-DPAT): fp\n\n5-HT\u2082 (serotonin; [\u00b3H]ketanserin): fp\n\nD\u2081 (dopamine; [\u00b3H]SCH23390): fp\n\nWhich sample was used for which receptor density measurement is stated in metadata files accompanying the main data repository. For methodological details, see Zilles et al. (2002), and in Palomero-Gallagher and Zilles (2018).\n\nZilles, K. et al. (2002). Quantitative analysis of cyto- and receptorarchitecture of the human brain, pp. 573-602. In: Brain Mapping: The Methods, 2nd edition (A.W. Toga and J.C. Mazziotta, eds.). San Diego, Academic Press.\n\nPalomero-Gallagher N, Zilles K. (2018) Cyto- and receptorarchitectonic mapping of the human brain. In: Handbook of Clinical Neurology 150: 355-387"
-    ],
-    "oai_identifier": [
-        "10.25493_VSFY-EYF"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "neuroscience"
-        },
-        {
-            "name": "brain mapping"
-        },
-        {
-            "name": "histology"
-        }
-    ],
-    "title": [
-        "Density measurements of different receptors for Area PF"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/hbp-oai_dc/SET_1/json/1e76ab57-07f5-53ca-992e-1e87f99a3055.json b/oaitestdata/hbp-oai_dc/SET_1/json/1e76ab57-07f5-53ca-992e-1e87f99a3055.json
deleted file mode 100644
index 8fdb1597..00000000
--- a/oaitestdata/hbp-oai_dc/SET_1/json/1e76ab57-07f5-53ca-992e-1e87f99a3055.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "https://www.humanbrainproject.eu/"
-    ],
-    "Contributor": [
-        "Zilles, Karl",
-        "Palomero-Gallagher, Nicola"
-    ],
-    "DOI": "http://dx.doi.org/10.25493/6YHV-3BT",
-    "DiscHierarchy": [
-        "1.2",
-        "Humanities",
-        "History"
-    ],
-    "Discipline": "Neuroscience",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://148.187.98.42:8443/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.25493_6YHV-3BT",
-    "MetadataAccess": [
-        "10.25493_6YHV-3BT"
-    ],
-    "PublicationTimestamp": "2019-09-20T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Human Brain Project"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International"
-    ],
-    "author": [
-        "Zilles, Karl",
-        "Palomero-Gallagher, Nicola"
-    ],
-    "fulltext": "10.25493_6YHV-3BT;2019-12-10T12:41:50Z;https://doi.org/10.25493/6YHV-3BT;Density measurements of different receptors for Hippocampus, CA1 (human);2019-09-20T13:50:02.388Z;This dataset contains the densities (in fmol/mg protein) of 5 receptors for classical neurotransmitters in hippocampal subfield Cornu Ammonis 1 (CA1) using quantitative in vitro autoradiography. The receptor density measurements are provided as density fingerprints (average across samples; mean density and standard deviation for each of the 5 receptors) for the following receptors:\n\nAMPA (glutamate; labelled with [\u00b3H]AMPA)\n\nkainate (glutamate; [\u00b3H]kainate)\n\nNMDA (glutamate; [\u00b3H]MK-801)\n\nGABA<sub>A</sub> (GABA; [\u00b3H]muscimol)\n\nGABA<sub>B</sub> (GABA; [\u00b3H] CGP54626)\n\n\nWhich sample was used for which receptor density measurement is stated in metadata files accompanying the main data repository.  For methodological details, see Zilles et al. (2002), and in Palomero-Gallagher and Zilles (2018).\n\nZilles, K. et al. (2002). Quantitative analysis of cyto- and receptorarchitecture of the human brain, pp. 573-602. In: Brain Mapping: The Methods, 2nd edition (A.W. Toga and J.C. Mazziotta, eds.). San Diego, Academic Press.\n\nPalomero-Gallagher N, Zilles K. (2018) Cyto- and receptorarchitectonic mapping of the human brain. In: Handbook of Clinical Neurology 150: 355-387;neuroscience;brain mapping;histology;english;dataset;The Human Brain Project;Palomero-Gallagher, Nicola;Zilles, Karl;Palomero-Gallagher, Nicola;Zilles, Karl;Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International",
-    "group": "hbp",
-    "groups": [
-        {
-            "name": "hbp"
-        }
-    ],
-    "name": "1e76ab57-07f5-53ca-992e-1e87f99a3055",
-    "notes": [
-        "This dataset contains the densities (in fmol/mg protein) of 5 receptors for classical neurotransmitters in hippocampal subfield Cornu Ammonis 1 (CA1) using quantitative in vitro autoradiography. The receptor density measurements are provided as density fingerprints (average across samples; mean density and standard deviation for each of the 5 receptors) for the following receptors:\n\nAMPA (glutamate; labelled with [\u00b3H]AMPA)\n\nkainate (glutamate; [\u00b3H]kainate)\n\nNMDA (glutamate; [\u00b3H]MK-801)\n\nGABA<sub>A</sub> (GABA; [\u00b3H]muscimol)\n\nGABA<sub>B</sub> (GABA; [\u00b3H] CGP54626)\n\n\nWhich sample was used for which receptor density measurement is stated in metadata files accompanying the main data repository.  For methodological details, see Zilles et al. (2002), and in Palomero-Gallagher and Zilles (2018).\n\nZilles, K. et al. (2002). Quantitative analysis of cyto- and receptorarchitecture of the human brain, pp. 573-602. In: Brain Mapping: The Methods, 2nd edition (A.W. Toga and J.C. Mazziotta, eds.). San Diego, Academic Press.\n\nPalomero-Gallagher N, Zilles K. (2018) Cyto- and receptorarchitectonic mapping of the human brain. In: Handbook of Clinical Neurology 150: 355-387"
-    ],
-    "oai_identifier": [
-        "10.25493_6YHV-3BT"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "neuroscience"
-        },
-        {
-            "name": "brain mapping"
-        },
-        {
-            "name": "histology"
-        }
-    ],
-    "title": [
-        "Density measurements of different receptors for Hippocampus, CA1 (human)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/hbp-oai_dc/SET_1/json/1ed15215-c9bc-5b89-9b9b-28cf63f76628.json b/oaitestdata/hbp-oai_dc/SET_1/json/1ed15215-c9bc-5b89-9b9b-28cf63f76628.json
deleted file mode 100644
index 55dfcab9..00000000
--- a/oaitestdata/hbp-oai_dc/SET_1/json/1ed15215-c9bc-5b89-9b9b-28cf63f76628.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "https://www.humanbrainproject.eu/"
-    ],
-    "Contributor": [
-        "Poupon, Cyril",
-        "Mangin, Jean-Fran\u00e7ois",
-        "Duclap, Delphine",
-        "Leboyer, Marion ",
-        "Fillard, Pierre",
-        "Houenou, Josselin",
-        "Guevara, Pamela",
-        "Le Bihan, Denis J.",
-        "Marrakchi-Kacem, Linda "
-    ],
-    "DOI": "http://dx.doi.org/10.25493/7HFQ-98Y",
-    "DiscHierarchy": [
-        "3.2.1.5",
-        "Microbiology, Virology and Immunology",
-        "Immunology"
-    ],
-    "Discipline": "Neuroscience",
-    "Format": [
-        "NIFTI"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://148.187.98.42:8443/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.25493_7HFQ-98Y",
-    "MetadataAccess": [
-        "10.25493_7HFQ-98Y"
-    ],
-    "PublicationTimestamp": "2019-06-14T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Human Brain Project"
-    ],
-    "RelatedIdentifier": [
-        "https://doi.org/10.1016/j.neuroimage.2012.02.071"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International"
-    ],
-    "author": [
-        "Mangin, Jean-Fran\u00e7ois"
-    ],
-    "fulltext": "10.25493_7HFQ-98Y;2019-12-10T12:41:55Z;https://doi.org/10.25493/7HFQ-98Y;Probabilistic map of the left temporal cingulate fibres (atlas of deep white matter fibre bundles, version 2018);2019-06-14T13:27:00.491Z;This data contains the probability map of the left temporal cingulate fibres (atlas of deep white matter fibre bundles, version 2018), in the MNI ICBM152 reference brain. This bundle was identified by fibre clustering, from the tractography datasets of 78 subjects in Neurospin\u2019s ARCHI database. The map shows the probability of finding a fibre belonging to the bundle in each voxel of the reference brain. The maximum probability corresponds to the voxels with the highest number of putative fibres going through.;neuroscience;brain mapping;imaging;english;dataset;The Human Brain Project;Guevara, Pamela;Duclap, Delphine;Poupon, Cyril;Marrakchi-Kacem, Linda ;Fillard, Pierre;Le Bihan, Denis J.;Leboyer, Marion ;Houenou, Josselin;Mangin, Jean-Fran\u00e7ois;Mangin, Jean-Fran\u00e7ois;NIFTI;Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International;https://doi.org/10.1016/j.neuroimage.2012.02.071",
-    "group": "hbp",
-    "groups": [
-        {
-            "name": "hbp"
-        }
-    ],
-    "name": "1ed15215-c9bc-5b89-9b9b-28cf63f76628",
-    "notes": [
-        "This data contains the probability map of the left temporal cingulate fibres (atlas of deep white matter fibre bundles, version 2018), in the MNI ICBM152 reference brain. This bundle was identified by fibre clustering, from the tractography datasets of 78 subjects in Neurospin\u2019s ARCHI database. The map shows the probability of finding a fibre belonging to the bundle in each voxel of the reference brain. The maximum probability corresponds to the voxels with the highest number of putative fibres going through."
-    ],
-    "oai_identifier": [
-        "10.25493_7HFQ-98Y"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "neuroscience"
-        },
-        {
-            "name": "brain mapping"
-        },
-        {
-            "name": "imaging"
-        }
-    ],
-    "title": [
-        "Probabilistic map of the left temporal cingulate fibres (atlas of deep white matter fibre bundles, version 2018)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/hbp-oai_dc/SET_1/json/1f7180d9-eae8-5db2-bae3-e689b005ff35.json b/oaitestdata/hbp-oai_dc/SET_1/json/1f7180d9-eae8-5db2-bae3-e689b005ff35.json
deleted file mode 100644
index 722e4654..00000000
--- a/oaitestdata/hbp-oai_dc/SET_1/json/1f7180d9-eae8-5db2-bae3-e689b005ff35.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "https://www.humanbrainproject.eu/"
-    ],
-    "Contributor": [
-        "Bludau, Sebastian",
-        "Eickhoff, Simon B.",
-        "Caspers, Svenja",
-        "Sigl, Benjamin",
-        "Mohlberg, Hartmut",
-        "Amunts, Katrin"
-    ],
-    "DOI": "http://dx.doi.org/10.25493/KXHS-N90",
-    "DiscHierarchy": [
-        "3.2",
-        "Life Sciences",
-        "Medicine"
-    ],
-    "Discipline": "Neuroscience",
-    "Format": [
-        "NIFTI"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://148.187.98.42:8443/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.25493_KXHS-N90",
-    "MetadataAccess": [
-        "10.25493_KXHS-N90"
-    ],
-    "PublicationTimestamp": "2019-06-04T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Human Brain Project"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International"
-    ],
-    "author": [
-        "Amunts, Katrin"
-    ],
-    "fulltext": "10.25493_KXHS-N90;2019-12-10T12:41:55Z;https://doi.org/10.25493/KXHS-N90;Probabilistic cytoarchitectonic map of Area 6d2 (PreCG) (v4.1);2019-06-04T16:32:05.574Z;This dataset contains the distinct architectonic Area 6d2 (PreG) in the individual, single subject template of the MNI Colin 27 as well as the MNI ICBM 152 2009c nonlinear asymmetric reference space. As part of the JuBrain cytoarchitectonic atlas, the area was identified using cytoarchitectonic analysis on cell-body-stained histological sections of 10 human postmortem brains obtained from the body donor program of the University of D\u00fcsseldorf. The results of the cytoarchitectonic analysis were then mapped to both reference spaces, where each voxel was assigned the probability to belong to Area 6d2 (PreG). The probability map of Area 6d2 (PreG) are provided in the NifTi format for each brain reference space and hemisphere. The JuBrain atlas relies on a modular, flexible and adaptive framework containing workflows to create the probabilistic brain maps for these structures. Note that methodological improvements and integration of new brain structures may lead to small deviations in earlier released datasets.;neuroscience;histology;imaging;brain mapping;english;dataset;The Human Brain Project;Sigl, Benjamin;Caspers, Svenja;Bludau, Sebastian;Mohlberg, Hartmut;Eickhoff, Simon B.;Amunts, Katrin;Amunts, Katrin;NIFTI;Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International",
-    "group": "hbp",
-    "groups": [
-        {
-            "name": "hbp"
-        }
-    ],
-    "name": "1f7180d9-eae8-5db2-bae3-e689b005ff35",
-    "notes": [
-        "This dataset contains the distinct architectonic Area 6d2 (PreG) in the individual, single subject template of the MNI Colin 27 as well as the MNI ICBM 152 2009c nonlinear asymmetric reference space. As part of the JuBrain cytoarchitectonic atlas, the area was identified using cytoarchitectonic analysis on cell-body-stained histological sections of 10 human postmortem brains obtained from the body donor program of the University of D\u00fcsseldorf. The results of the cytoarchitectonic analysis were then mapped to both reference spaces, where each voxel was assigned the probability to belong to Area 6d2 (PreG). The probability map of Area 6d2 (PreG) are provided in the NifTi format for each brain reference space and hemisphere. The JuBrain atlas relies on a modular, flexible and adaptive framework containing workflows to create the probabilistic brain maps for these structures. Note that methodological improvements and integration of new brain structures may lead to small deviations in earlier released datasets."
-    ],
-    "oai_identifier": [
-        "10.25493_KXHS-N90"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "neuroscience"
-        },
-        {
-            "name": "histology"
-        },
-        {
-            "name": "imaging"
-        },
-        {
-            "name": "brain mapping"
-        }
-    ],
-    "title": [
-        "Probabilistic cytoarchitectonic map of Area 6d2 (PreCG) (v4.1)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/hbp-oai_dc/SET_1/json/1fceacde-ae61-5dea-9a97-584b770e598e.json b/oaitestdata/hbp-oai_dc/SET_1/json/1fceacde-ae61-5dea-9a97-584b770e598e.json
deleted file mode 100644
index 3cc52cc8..00000000
--- a/oaitestdata/hbp-oai_dc/SET_1/json/1fceacde-ae61-5dea-9a97-584b770e598e.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "https://www.humanbrainproject.eu/"
-    ],
-    "Contributor": [
-        "Poupon, Cyril",
-        "Mangin, Jean-Fran\u00e7ois",
-        "Duclap, Delphine",
-        "Rom\u00e1n, Claudio",
-        "Guevara, Pamela",
-        "Guevara, Miguel",
-        "Houenou, Josselin"
-    ],
-    "DOI": "http://dx.doi.org/10.25493/ENJ7-ZKM",
-    "DiscHierarchy": [
-        "3.2.1.5",
-        "Microbiology, Virology and Immunology",
-        "Immunology"
-    ],
-    "Discipline": "Neuroscience",
-    "Format": [
-        "NIFTI"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://148.187.98.42:8443/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.25493_ENJ7-ZKM",
-    "MetadataAccess": [
-        "10.25493_ENJ7-ZKM"
-    ],
-    "PublicationTimestamp": "2019-05-23T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Human Brain Project"
-    ],
-    "RelatedIdentifier": [
-        "https://doi.org/10.1016/j.neuroimage.2016.11.066"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International"
-    ],
-    "author": [
-        "Mangin, Jean-Fran\u00e7ois"
-    ],
-    "fulltext": "10.25493_ENJ7-ZKM;2019-12-10T12:41:54Z;https://doi.org/10.25493/ENJ7-ZKM;Maximum probability map of superficial white matter fibre bundles;2019-05-23T14:48:46.328Z;This data contains the maximum probability map of superficial white matter fibre bundles, in the MNI ICBM152 reference brain. These bundles were identified using a hybrid approach, incorporating anatomical information (from cortical regions of interest) and fibre shape (fibre clustering), from the tractography datasets of 78 subjects in the Neurospin\u2019s ARCHI database. The maximum probability corresponds to the voxels with the highest number of putative fibres going through.;neuroscience;brain mapping;imaging;english;dataset;The Human Brain Project;Guevara, Miguel;Rom\u00e1n, Claudio;Houenou, Josselin;Duclap, Delphine;Poupon, Cyril;Mangin, Jean-Fran\u00e7ois;Guevara, Pamela;Mangin, Jean-Fran\u00e7ois;NIFTI;Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International;https://doi.org/10.1016/j.neuroimage.2016.11.066",
-    "group": "hbp",
-    "groups": [
-        {
-            "name": "hbp"
-        }
-    ],
-    "name": "1fceacde-ae61-5dea-9a97-584b770e598e",
-    "notes": [
-        "This data contains the maximum probability map of superficial white matter fibre bundles, in the MNI ICBM152 reference brain. These bundles were identified using a hybrid approach, incorporating anatomical information (from cortical regions of interest) and fibre shape (fibre clustering), from the tractography datasets of 78 subjects in the Neurospin\u2019s ARCHI database. The maximum probability corresponds to the voxels with the highest number of putative fibres going through."
-    ],
-    "oai_identifier": [
-        "10.25493_ENJ7-ZKM"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "neuroscience"
-        },
-        {
-            "name": "brain mapping"
-        },
-        {
-            "name": "imaging"
-        }
-    ],
-    "title": [
-        "Maximum probability map of superficial white matter fibre bundles"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/hbp-oai_dc/SET_1/json/2abd1419-f3eb-5dfc-887b-24d539ebad3c.json b/oaitestdata/hbp-oai_dc/SET_1/json/2abd1419-f3eb-5dfc-887b-24d539ebad3c.json
deleted file mode 100644
index fcb95d2d..00000000
--- a/oaitestdata/hbp-oai_dc/SET_1/json/2abd1419-f3eb-5dfc-887b-24d539ebad3c.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "https://www.humanbrainproject.eu/"
-    ],
-    "Contributor": [
-        "Zilles, Karl",
-        "Hoemke, L.",
-        "Eickhoff, Simon B.",
-        "Schleicher, Axel",
-        "Hermann, K.",
-        "Scheperjans, Filip",
-        "Mohlberg, Hartmut",
-        "Amunts, Katrin"
-    ],
-    "DOI": "http://dx.doi.org/10.25493/7HX2-AJH",
-    "DiscHierarchy": [
-        "3.2",
-        "Life Sciences",
-        "Medicine"
-    ],
-    "Discipline": "Neuroscience",
-    "Format": [
-        "NIFTI"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://148.187.98.42:8443/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.25493_7HX2-AJH",
-    "MetadataAccess": [
-        "10.25493_7HX2-AJH"
-    ],
-    "PublicationTimestamp": "2019-06-04T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Human Brain Project"
-    ],
-    "RelatedIdentifier": [
-        "https://doi.org/10.1093/cercor/bhm241",
-        "https://doi.org/10.1093/cercor/bhm116"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International"
-    ],
-    "author": [
-        "Amunts, Katrin"
-    ],
-    "fulltext": "10.25493_7HX2-AJH;2019-12-10T12:41:53Z;https://doi.org/10.25493/7HX2-AJH;Probabilistic cytoarchitectonic map of Area 7A (SPL) (v8.4);2019-06-04T16:34:57.543Z;This dataset contains the distinct architectonic Area 7A (SPL) in the individual, single subject template of the MNI Colin 27 as well as the MNI ICBM 152 2009c nonlinear asymmetric reference space. As part of the JuBrain cytoarchitectonic atlas, the area was identified using cytoarchitectonic analysis on cell-body-stained histological sections of 10 human postmortem brains obtained from the body donor program of the University of D\u00fcsseldorf. The results of the cytoarchitectonic analysis were then mapped to both reference spaces, where each voxel was assigned the probability to belong to Area 7A (SPL). The probability map of Area 7A (SPL) are provided in the NifTi format for each brain reference space and hemisphere. The JuBrain atlas relies on a modular, flexible and adaptive framework containing workflows to create the probabilistic brain maps for these structures. Note that methodological improvements and integration of new brain structures may lead to small deviations in earlier released datasets.;neuroscience;histology;imaging;brain mapping;english;dataset;The Human Brain Project;Scheperjans, Filip;Hermann, K.;Eickhoff, Simon B.;Amunts, Katrin;Schleicher, Axel;Hoemke, L.;Mohlberg, Hartmut;Zilles, Karl;Amunts, Katrin;NIFTI;Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International;https://doi.org/10.1093/cercor/bhm241;https://doi.org/10.1093/cercor/bhm116",
-    "group": "hbp",
-    "groups": [
-        {
-            "name": "hbp"
-        }
-    ],
-    "name": "2abd1419-f3eb-5dfc-887b-24d539ebad3c",
-    "notes": [
-        "This dataset contains the distinct architectonic Area 7A (SPL) in the individual, single subject template of the MNI Colin 27 as well as the MNI ICBM 152 2009c nonlinear asymmetric reference space. As part of the JuBrain cytoarchitectonic atlas, the area was identified using cytoarchitectonic analysis on cell-body-stained histological sections of 10 human postmortem brains obtained from the body donor program of the University of D\u00fcsseldorf. The results of the cytoarchitectonic analysis were then mapped to both reference spaces, where each voxel was assigned the probability to belong to Area 7A (SPL). The probability map of Area 7A (SPL) are provided in the NifTi format for each brain reference space and hemisphere. The JuBrain atlas relies on a modular, flexible and adaptive framework containing workflows to create the probabilistic brain maps for these structures. Note that methodological improvements and integration of new brain structures may lead to small deviations in earlier released datasets."
-    ],
-    "oai_identifier": [
-        "10.25493_7HX2-AJH"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "neuroscience"
-        },
-        {
-            "name": "histology"
-        },
-        {
-            "name": "imaging"
-        },
-        {
-            "name": "brain mapping"
-        }
-    ],
-    "title": [
-        "Probabilistic cytoarchitectonic map of Area 7A (SPL) (v8.4)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/hbp-oai_dc/SET_1/json/2b5e1177-b2a6-59b6-9cb0-036006ec458a.json b/oaitestdata/hbp-oai_dc/SET_1/json/2b5e1177-b2a6-59b6-9cb0-036006ec458a.json
deleted file mode 100644
index 6facf95e..00000000
--- a/oaitestdata/hbp-oai_dc/SET_1/json/2b5e1177-b2a6-59b6-9cb0-036006ec458a.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "https://www.humanbrainproject.eu/"
-    ],
-    "Contributor": [
-        "Poupon, Cyril",
-        "Mangin, Jean-Fran\u00e7ois",
-        "Duclap, Delphine",
-        "Rom\u00e1n, Claudio",
-        "Guevara, Pamela",
-        "Guevara, Miguel",
-        "Houenou, Josselin"
-    ],
-    "DOI": "http://dx.doi.org/10.25493/1QKP-BGS",
-    "DiscHierarchy": [
-        "3.2.1.5",
-        "Microbiology, Virology and Immunology",
-        "Immunology"
-    ],
-    "Discipline": "Neuroscience",
-    "Format": [
-        "NIFTI"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://148.187.98.42:8443/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.25493_1QKP-BGS",
-    "MetadataAccess": [
-        "10.25493_1QKP-BGS"
-    ],
-    "PublicationTimestamp": "2019-05-23T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Human Brain Project"
-    ],
-    "RelatedIdentifier": [
-        "https://doi.org/10.1016/j.neuroimage.2016.11.066"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International"
-    ],
-    "author": [
-        "Mangin, Jean-Fran\u00e7ois"
-    ],
-    "fulltext": "10.25493_1QKP-BGS;2019-12-10T12:41:52Z;https://doi.org/10.25493/1QKP-BGS;Probability map of bundle rh_SM-Ins_0 (atlas of superficial white matter fibre bundles, version 2018);2019-05-23T14:46:48.841Z;This data contains the probability map of a short fibre bundle connecting the right hemisphere Supramarginal and Insula regions of the Desikan-Killiany atlas, in the MNI ICBM152 reference brain. This bundle was identified using a hybrid approach, incorporating anatomical information (from cortical regions of interest) and fibre shape (fibre clustering), from the tractography datasets of 78 subjects in the Neurospin\u2019s ARCHI database. The map shows the probability of finding a fibre belonging to the bundle in each voxel of the reference brain. The maximum probability corresponds to the voxels with the highest number of putative fibres going through.;neuroscience;brain mapping;imaging;english;dataset;The Human Brain Project;Guevara, Miguel;Rom\u00e1n, Claudio;Houenou, Josselin;Duclap, Delphine;Poupon, Cyril;Mangin, Jean-Fran\u00e7ois;Guevara, Pamela;Mangin, Jean-Fran\u00e7ois;NIFTI;Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International;https://doi.org/10.1016/j.neuroimage.2016.11.066",
-    "group": "hbp",
-    "groups": [
-        {
-            "name": "hbp"
-        }
-    ],
-    "name": "2b5e1177-b2a6-59b6-9cb0-036006ec458a",
-    "notes": [
-        "This data contains the probability map of a short fibre bundle connecting the right hemisphere Supramarginal and Insula regions of the Desikan-Killiany atlas, in the MNI ICBM152 reference brain. This bundle was identified using a hybrid approach, incorporating anatomical information (from cortical regions of interest) and fibre shape (fibre clustering), from the tractography datasets of 78 subjects in the Neurospin\u2019s ARCHI database. The map shows the probability of finding a fibre belonging to the bundle in each voxel of the reference brain. The maximum probability corresponds to the voxels with the highest number of putative fibres going through."
-    ],
-    "oai_identifier": [
-        "10.25493_1QKP-BGS"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "neuroscience"
-        },
-        {
-            "name": "brain mapping"
-        },
-        {
-            "name": "imaging"
-        }
-    ],
-    "title": [
-        "Probability map of bundle rh_SM-Ins_0 (atlas of superficial white matter fibre bundles, version 2018)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/hbp-oai_dc/SET_1/json/2bbb0937-60cd-57ef-b0fa-978c9db59e2e.json b/oaitestdata/hbp-oai_dc/SET_1/json/2bbb0937-60cd-57ef-b0fa-978c9db59e2e.json
deleted file mode 100644
index 707a5de6..00000000
--- a/oaitestdata/hbp-oai_dc/SET_1/json/2bbb0937-60cd-57ef-b0fa-978c9db59e2e.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "https://www.humanbrainproject.eu/"
-    ],
-    "Contributor": [
-        "Huysegoms, Marcel",
-        "Schubert, Nicole",
-        "Schober, Martin",
-        "Zilles, Karl",
-        "Axer, Markus",
-        "Kirlangic, Mehmet E",
-        "Bjaalie, Jan G.",
-        "Amunts, Katrin",
-        "Leergaard, Trygve B.",
-        "Huynh, Anh-Minh",
-        "Palomero-Gallagher, Nicola"
-    ],
-    "DOI": "http://dx.doi.org/10.25493/F9RX-65U",
-    "DiscHierarchy": [
-        "3.2.3",
-        "Medicine",
-        "Neurosciences"
-    ],
-    "Discipline": "Neuroscience",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://148.187.98.42:8443/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.25493_F9RX-65U",
-    "MetadataAccess": [
-        "10.25493_F9RX-65U"
-    ],
-    "PublicationTimestamp": "2019-10-14T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Human Brain Project"
-    ],
-    "RelatedIdentifier": [
-        "https://doi.org/10.3389/fnana.2016.00051"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution-ShareAlike 4.0 International"
-    ],
-    "author": [
-        "Axer, Markus"
-    ],
-    "fulltext": "10.25493_F9RX-65U;2019-12-10T12:41:49Z;https://doi.org/10.25493/F9RX-65U;Wistar rat brain fibre orientation model;2019-10-14T08:05:21.247Z;The 3D fibre orientation model of a male Wistar rat brain was derived from 3D-PLI as described in Axer et al. 2011a [1].  \nThe brain was immersion fixed in 4% paraformaldehyde. After cryoprotection (10% glycerin for 3 days, followed by 20% glycerin for 14 days at +4\u00b0C), the brain was deep frozen at -50\u00b0C and stored till further processing. The brain was serially sectioned in the coronal plane (section thickness 60 \u03bcm) using a large-scale cryostat microtome (Polycut CM 3500, Leica, Germany) and coverslipped with glycerin. Immediately after coverslipping, the sections were measured using the large-area polarimeter (LAP, pixel size: 64 \u03bcm x 64 \u03bcm, cf. [1]). \nDuring sectioning, each blockface was digitized using a CCD camera mounted above the brain in order to obtain an undistorted reference image of each section. Spatial resolution in the z-direction was 60 \u03bcm. No staining was applied. This procedure resulted in an uninterrupted series of 446 sections through the entire brain, which ultimately enabled the 3D reconstruction. \n\nThe application of the Jones calculus [2] describes the light transmittance through the LAP and enables the calculation of the individual spatial fiber orientation in each voxel (defined by pixel size and section thickness). The fiber orientation is defined by the pair of angles (\u03b1, \u03c6) = (inclination, direction) indicating the fiber axis orientation out of and within the section plane, respectively. Inclination and direction angles are encoded in RGB or HSV color space to provide one fiber orientation map (FOM) per section. The entire data set of aligned FOMs (i.e. the fibre orientation model) is assembled in a single NIfTI file (http://nifti.nimh.nih.gov). FOMs are the fundamental data structure provided by 3D-PLI and have an in-plane resolution of 64 \u03bcm\u00d764 \u03bcm, and, since each section was 60 \u03bcm thick, a spatial resolution in the z-direction of 60 \u03bcm. They contain a single 3D fiber orientation vector per voxel that is interpreted as the spatial orientation of the fibers in this voxel.\n\nNon-linear deformations introduced by brain sectioning and mounting were corrected using blockface images as undistorted references for the spatial alignment of 3D-PLI FOMs. Hence, in a first step the blockface images had to be 3D reconstructed. The reconstruction method consisted of a two-phase registration: a marker-based alignment of the blockface images and a refinement of the pre-reconstructed volume using 3D information [3].\nThe 3D reconstruction of the FOMs was done in two steps: (i) a 3D affine registration ensured the correct spatial alignment of the brains and (ii) a subsequent 3D non-linear registration compensated non-linear distortions of the brain sections. Using segmented images the centers of gravity of the corresponding brain masks were calculated and aligned. Based on this initial transformation, an intensity based rigid registration was performed using mutual information as metric. The second step, the refinement, was done by means of a slice-by-slice B-Spline registration with sum of squared differences as metric and a grid size of 5 \u00d7 6 [4].\nAfterwards the fibre orientation model was transferred into the common rodent reference space, the Waxholm Space atlas [5]. The transformation of the brains into the same space was also done in the two step strategy described above.\n\n \n\n**References** \n  \n[1] Axer, M., Amunts, K., Gr\u00e4\u00dfel, D., Palm, C., Dammers, J., Axer, H., et al. (2011a). A novel approach to the human connectome: ultra-high resolution mapping of fiber tracts in the brain. NeuroImage 54, 1091\u20131101. doi: 10.1016/j.neuroimage.2010.08.075\n\n[2] Jones, RC. (1941) A new calculus for the treatment of optical systems. J. Opt. Soc. Am. 31, 488\u2013503. doi:10.1364/JOSA.31.000488\n\n[3] Schober, M., Schl\u00f6mer, P., Cremer, M., Mohlberg, H., Huynh, A.-M., Schubert, N., et al. (2015). \u201cReference volume generation for subsequent 3D reconstruction of histological sections,\u201d in Proceedings of Bildverarbeitung f\u00fcr die Medizin, (L\u00fcbeck), 143\u2013148.\n\n[4] Schubert, N., Kirlangic, M. E., Schober, M., Huynh, A.-M., Amunts, K., Zilles, K., et al. (2016). 3D Reconstructed Cyto-, Muscarinic M2 Receptor, and Fiber Architecture of the Rat Brain Registered to the Waxholm Space Atlas. Frontiers Neuroanatomy 10, 1-13. doi: 10.3389/fnana.2016.00051\n\n[5] Papp, E. A., Leergaard, T. B., Calabrese, E., Johnson, G. A., and Bjaalie, J. G. (2014). Waxholm space atlas of the Spraque Dawley rat brain. NeuroImage 97, 374\u2013386. doi: 10.1016/j.neuroimage.2014.04.001;neuroscience;english;dataset;The Human Brain Project;Schubert, Nicole;Axer, Markus;Schober, Martin;Huynh, Anh-Minh;Huysegoms, Marcel;Palomero-Gallagher, Nicola;Bjaalie, Jan G.;Leergaard, Trygve B.;Kirlangic, Mehmet E;Amunts, Katrin;Zilles, Karl;Axer, Markus;Creative Commons Attribution-ShareAlike 4.0 International;https://doi.org/10.3389/fnana.2016.00051",
-    "group": "hbp",
-    "groups": [
-        {
-            "name": "hbp"
-        }
-    ],
-    "name": "2bbb0937-60cd-57ef-b0fa-978c9db59e2e",
-    "notes": [
-        "The 3D fibre orientation model of a male Wistar rat brain was derived from 3D-PLI as described in Axer et al. 2011a [1].  \nThe brain was immersion fixed in 4% paraformaldehyde. After cryoprotection (10% glycerin for 3 days, followed by 20% glycerin for 14 days at +4\u00b0C), the brain was deep frozen at -50\u00b0C and stored till further processing. The brain was serially sectioned in the coronal plane (section thickness 60 \u03bcm) using a large-scale cryostat microtome (Polycut CM 3500, Leica, Germany) and coverslipped with glycerin. Immediately after coverslipping, the sections were measured using the large-area polarimeter (LAP, pixel size: 64 \u03bcm x 64 \u03bcm, cf. [1]). \nDuring sectioning, each blockface was digitized using a CCD camera mounted above the brain in order to obtain an undistorted reference image of each section. Spatial resolution in the z-direction was 60 \u03bcm. No staining was applied. This procedure resulted in an uninterrupted series of 446 sections through the entire brain, which ultimately enabled the 3D reconstruction. \n\nThe application of the Jones calculus [2] describes the light transmittance through the LAP and enables the calculation of the individual spatial fiber orientation in each voxel (defined by pixel size and section thickness). The fiber orientation is defined by the pair of angles (\u03b1, \u03c6) = (inclination, direction) indicating the fiber axis orientation out of and within the section plane, respectively. Inclination and direction angles are encoded in RGB or HSV color space to provide one fiber orientation map (FOM) per section. The entire data set of aligned FOMs (i.e. the fibre orientation model) is assembled in a single NIfTI file (http://nifti.nimh.nih.gov). FOMs are the fundamental data structure provided by 3D-PLI and have an in-plane resolution of 64 \u03bcm\u00d764 \u03bcm, and, since each section was 60 \u03bcm thick, a spatial resolution in the z-direction of 60 \u03bcm. They contain a single 3D fiber orientation vector per voxel that is interpreted as the spatial orientation of the fibers in this voxel.\n\nNon-linear deformations introduced by brain sectioning and mounting were corrected using blockface images as undistorted references for the spatial alignment of 3D-PLI FOMs. Hence, in a first step the blockface images had to be 3D reconstructed. The reconstruction method consisted of a two-phase registration: a marker-based alignment of the blockface images and a refinement of the pre-reconstructed volume using 3D information [3].\nThe 3D reconstruction of the FOMs was done in two steps: (i) a 3D affine registration ensured the correct spatial alignment of the brains and (ii) a subsequent 3D non-linear registration compensated non-linear distortions of the brain sections. Using segmented images the centers of gravity of the corresponding brain masks were calculated and aligned. Based on this initial transformation, an intensity based rigid registration was performed using mutual information as metric. The second step, the refinement, was done by means of a slice-by-slice B-Spline registration with sum of squared differences as metric and a grid size of 5 \u00d7 6 [4].\nAfterwards the fibre orientation model was transferred into the common rodent reference space, the Waxholm Space atlas [5]. The transformation of the brains into the same space was also done in the two step strategy described above.\n\n \n\n**References** \n  \n[1] Axer, M., Amunts, K., Gr\u00e4\u00dfel, D., Palm, C., Dammers, J., Axer, H., et al. (2011a). A novel approach to the human connectome: ultra-high resolution mapping of fiber tracts in the brain. NeuroImage 54, 1091\u20131101. doi: 10.1016/j.neuroimage.2010.08.075\n\n[2] Jones, RC. (1941) A new calculus for the treatment of optical systems. J. Opt. Soc. Am. 31, 488\u2013503. doi:10.1364/JOSA.31.000488\n\n[3] Schober, M., Schl\u00f6mer, P., Cremer, M., Mohlberg, H., Huynh, A.-M., Schubert, N., et al. (2015). \u201cReference volume generation for subsequent 3D reconstruction of histological sections,\u201d in Proceedings of Bildverarbeitung f\u00fcr die Medizin, (L\u00fcbeck), 143\u2013148.\n\n[4] Schubert, N., Kirlangic, M. E., Schober, M., Huynh, A.-M., Amunts, K., Zilles, K., et al. (2016). 3D Reconstructed Cyto-, Muscarinic M2 Receptor, and Fiber Architecture of the Rat Brain Registered to the Waxholm Space Atlas. Frontiers Neuroanatomy 10, 1-13. doi: 10.3389/fnana.2016.00051\n\n[5] Papp, E. A., Leergaard, T. B., Calabrese, E., Johnson, G. A., and Bjaalie, J. G. (2014). Waxholm space atlas of the Spraque Dawley rat brain. NeuroImage 97, 374\u2013386. doi: 10.1016/j.neuroimage.2014.04.001"
-    ],
-    "oai_identifier": [
-        "10.25493_F9RX-65U"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "neuroscience"
-        }
-    ],
-    "title": [
-        "Wistar rat brain fibre orientation model"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/hbp-oai_dc/SET_1/json/2c1c28aa-9116-5c3e-81a1-9de48194f815.json b/oaitestdata/hbp-oai_dc/SET_1/json/2c1c28aa-9116-5c3e-81a1-9de48194f815.json
deleted file mode 100644
index e5b3700b..00000000
--- a/oaitestdata/hbp-oai_dc/SET_1/json/2c1c28aa-9116-5c3e-81a1-9de48194f815.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "https://www.humanbrainproject.eu/"
-    ],
-    "Contributor": [
-        "Calabrese, Evan",
-        "Leergaard, Trygve B.",
-        "Johnson, G. Allan",
-        "Papp, Eszter A.",
-        "Bjaalie, Jan G."
-    ],
-    "DOI": "http://dx.doi.org/10.25493/DTSG-ZBS",
-    "DiscHierarchy": [
-        "3.2.1.5",
-        "Microbiology, Virology and Immunology",
-        "Immunology"
-    ],
-    "Discipline": "Neuroscience",
-    "Format": [
-        "NIFTI"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://148.187.98.42:8443/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.25493_DTSG-ZBS",
-    "MetadataAccess": [
-        "10.25493_DTSG-ZBS"
-    ],
-    "PublicationTimestamp": "2019-09-20T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Human Brain Project"
-    ],
-    "RelatedIdentifier": [
-        "https://doi.org/10.1016/j.neuroimage.2014.10.017",
-        "https://doi.org/10.1016/j.neuroimage.2014.04.001"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International"
-    ],
-    "author": [
-        "Johnson, G. Allan"
-    ],
-    "fulltext": "10.25493_DTSG-ZBS;2019-12-10T12:41:57Z;https://doi.org/10.25493/DTSG-ZBS;Microscopic resolution diffusion magnetic resonance images of a normal adult Sprague Dawley rat brain;2019-09-20T08:19:41.837Z;Anatomical reference volume of a normal adult male Sprague Dawley rat brain, consisting of high resolution, contrast enhanced, structural magnetic resonance images (sMRI; 39 \u03bcm isotropic voxels) and diffusion tensor images (DTI, 78 \u03bcm isotropic voxels). Version 1.01 features a standardized orientation of the volumetric datasets according to NIfTI-1 format defaults, allowing users to read Waxholm Space coordinates directly from the data volume using publicly available software (e.g. ITK-SNAP and MBAT). For details, see \u201cRelease notes v1.01\u201d.\n\nThe dataset is hosted on [NITRC.org](https://www.nitrc.org/frs/?group_id=1081) and includes: \n* [ T<sub>2</sub><sup>*</sup>-weighted gradient echo image](https://www.nitrc.org/frs/download.php/9423/WHS_SD_rat_T2star_v1.01.nii.gz \"Download T2*-weighted gradient echo image from NITRC\") at 39 \u03bcm original resolution (1024x512x512 voxels)\n* [Apparent Diffusion Coefficient (ADC) map](https://www.nitrc.org/frs/download.php/9430/WHS_SD_rat_ADC_v1.01.nii.gz \"Download Apparent Diffusion Coefficient (ADC) map from NITRC\") resampled to 39 \u03bcm resolution (1024x512x512 voxels)\n* [DTI b0 image](https://www.nitrc.org/frs/download.php/9431/WHS_SD_rat_DTI_512_v1.01.zip \"Download DTI b0 image from NITRC\") resampled to 39 \u03bcm resolution (1024x512x512 voxels)\n* [Diffusion weighted image map](https://www.nitrc.org/frs/download.php/9429/WHS_SD_rat_DWI_v1.01.nii.gz \"Download Diffusion weighted image map from NITRC\") resampled to 39 \u03bcm resolution (1024x512x512 voxels)\n* [Fractional Anisotropy (FA) map](https://www.nitrc.org/frs/download.php/9428/WHS_SD_rat_FA_v1.01.nii.gz \"Download Fractional Anisotropy (FA) map from NITRC\") resampled to 39 \u03bcm resolution (1024x512x512 voxels)\n* [Color FA map](https://www.nitrc.org/frs/download.php/9424/WHS_SD_rat_FA_color_v1.01.nii.gz \"Download Color FA map from NITRC\") resampled to 39 \u03bcm resolution (1024x512x512 voxels), combining the FA and primary eigenvector to 24-bit color RGB where intensity is given by relative FA value and color is assigned to directions (RGB to xyz respectively)\n;neuroscience;Structural brain imaging;english;dataset;The Human Brain Project;Papp, Eszter A.;Leergaard, Trygve B.;Calabrese, Evan;Johnson, G. Allan;Bjaalie, Jan G.;Johnson, G. Allan;NIFTI;Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International;https://doi.org/10.1016/j.neuroimage.2014.10.017;https://doi.org/10.1016/j.neuroimage.2014.04.001",
-    "group": "hbp",
-    "groups": [
-        {
-            "name": "hbp"
-        }
-    ],
-    "name": "2c1c28aa-9116-5c3e-81a1-9de48194f815",
-    "notes": [
-        "Anatomical reference volume of a normal adult male Sprague Dawley rat brain, consisting of high resolution, contrast enhanced, structural magnetic resonance images (sMRI; 39 \u03bcm isotropic voxels) and diffusion tensor images (DTI, 78 \u03bcm isotropic voxels). Version 1.01 features a standardized orientation of the volumetric datasets according to NIfTI-1 format defaults, allowing users to read Waxholm Space coordinates directly from the data volume using publicly available software (e.g. ITK-SNAP and MBAT). For details, see \u201cRelease notes v1.01\u201d.\n\nThe dataset is hosted on [NITRC.org](https://www.nitrc.org/frs/?group_id=1081) and includes: \n* [ T<sub>2</sub><sup>*</sup>-weighted gradient echo image](https://www.nitrc.org/frs/download.php/9423/WHS_SD_rat_T2star_v1.01.nii.gz \"Download T2*-weighted gradient echo image from NITRC\") at 39 \u03bcm original resolution (1024x512x512 voxels)\n* [Apparent Diffusion Coefficient (ADC) map](https://www.nitrc.org/frs/download.php/9430/WHS_SD_rat_ADC_v1.01.nii.gz \"Download Apparent Diffusion Coefficient (ADC) map from NITRC\") resampled to 39 \u03bcm resolution (1024x512x512 voxels)\n* [DTI b0 image](https://www.nitrc.org/frs/download.php/9431/WHS_SD_rat_DTI_512_v1.01.zip \"Download DTI b0 image from NITRC\") resampled to 39 \u03bcm resolution (1024x512x512 voxels)\n* [Diffusion weighted image map](https://www.nitrc.org/frs/download.php/9429/WHS_SD_rat_DWI_v1.01.nii.gz \"Download Diffusion weighted image map from NITRC\") resampled to 39 \u03bcm resolution (1024x512x512 voxels)\n* [Fractional Anisotropy (FA) map](https://www.nitrc.org/frs/download.php/9428/WHS_SD_rat_FA_v1.01.nii.gz \"Download Fractional Anisotropy (FA) map from NITRC\") resampled to 39 \u03bcm resolution (1024x512x512 voxels)\n* [Color FA map](https://www.nitrc.org/frs/download.php/9424/WHS_SD_rat_FA_color_v1.01.nii.gz \"Download Color FA map from NITRC\") resampled to 39 \u03bcm resolution (1024x512x512 voxels), combining the FA and primary eigenvector to 24-bit color RGB where intensity is given by relative FA value and color is assigned to directions (RGB to xyz respectively)\n"
-    ],
-    "oai_identifier": [
-        "10.25493_DTSG-ZBS"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "neuroscience"
-        },
-        {
-            "name": "Structural brain imaging"
-        }
-    ],
-    "title": [
-        "Microscopic resolution diffusion magnetic resonance images of a normal adult Sprague Dawley rat brain"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/hbp-oai_dc/SET_1/json/2c27eae4-2956-5c62-8c61-78ac0b75d1a1.json b/oaitestdata/hbp-oai_dc/SET_1/json/2c27eae4-2956-5c62-8c61-78ac0b75d1a1.json
deleted file mode 100644
index 7d86d7d9..00000000
--- a/oaitestdata/hbp-oai_dc/SET_1/json/2c27eae4-2956-5c62-8c61-78ac0b75d1a1.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "https://www.humanbrainproject.eu/"
-    ],
-    "Contributor": [
-        "Kastanauskaite, Asta",
-        "Cano, Deborah",
-        "Fernaud, Isabel",
-        "Regalado, Mamen",
-        "Rojo, Concepcion.",
-        "Benavides-Piccione, Ruth",
-        "Leon, Gonzalo",
-        "Gonzalez-Tapia, Silvia",
-        "DeFelipe, Javier"
-    ],
-    "DOI": "http://dx.doi.org/10.25493/J3XM-1F8",
-    "DiscHierarchy": [
-        "1.3.3",
-        "Fine Arts, Music, Theatre and Media Studies",
-        "Dance"
-    ],
-    "Discipline": "Neuroscience",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://148.187.98.42:8443/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.25493_J3XM-1F8",
-    "MetadataAccess": [
-        "10.25493_J3XM-1F8"
-    ],
-    "PublicationTimestamp": "2019-05-24T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Human Brain Project"
-    ],
-    "RelatedIdentifier": [
-        "https://doi.org/10.1093/cercor/bhj041"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution-NonCommercial 4.0 International"
-    ],
-    "author": [
-        "Benavides-Piccione, Ruth"
-    ],
-    "fulltext": "10.25493_J3XM-1F8;2019-12-10T12:41:50Z;https://doi.org/10.25493/J3XM-1F8;3D reconstructions of pyramidal neurons from the mouse cortex ;2019-05-24T09:53:13.447Z;We have produced 3D reconstructions of pyramidal neurons from the mouse somatosensory cortex across layers II-VI using Neurolucida software from 3D confocal stack of images. Data from 3D reconstructions will be useful to modeling and integration of anatomical data with functional studies in mouse brain. \n\n**Embargo status:** *This dataset is temporarily under embargo. The data will become available for download after the embargo period.*;neuroscience;3D cell morphological reconstruction data;english;dataset;The Human Brain Project;DeFelipe, Javier;Benavides-Piccione, Ruth;Fernaud, Isabel;Kastanauskaite, Asta;Regalado, Mamen;Gonzalez-Tapia, Silvia;Leon, Gonzalo;Cano, Deborah;Rojo, Concepcion.;Benavides-Piccione, Ruth;Creative Commons Attribution-NonCommercial 4.0 International;https://doi.org/10.1093/cercor/bhj041",
-    "group": "hbp",
-    "groups": [
-        {
-            "name": "hbp"
-        }
-    ],
-    "name": "2c27eae4-2956-5c62-8c61-78ac0b75d1a1",
-    "notes": [
-        "We have produced 3D reconstructions of pyramidal neurons from the mouse somatosensory cortex across layers II-VI using Neurolucida software from 3D confocal stack of images. Data from 3D reconstructions will be useful to modeling and integration of anatomical data with functional studies in mouse brain. \n\n**Embargo status:** *This dataset is temporarily under embargo. The data will become available for download after the embargo period.*"
-    ],
-    "oai_identifier": [
-        "10.25493_J3XM-1F8"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "neuroscience"
-        },
-        {
-            "name": "D cell morphological reconstruction data"
-        }
-    ],
-    "title": [
-        "3D reconstructions of pyramidal neurons from the mouse cortex "
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/hbp-oai_dc/SET_1/json/2cbafa21-9b6c-5218-afa8-e61fe6e7164e.json b/oaitestdata/hbp-oai_dc/SET_1/json/2cbafa21-9b6c-5218-afa8-e61fe6e7164e.json
deleted file mode 100644
index 6608b75c..00000000
--- a/oaitestdata/hbp-oai_dc/SET_1/json/2cbafa21-9b6c-5218-afa8-e61fe6e7164e.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "https://www.humanbrainproject.eu/"
-    ],
-    "Contributor": [
-        "Poupon, Cyril",
-        "Mangin, Jean-Fran\u00e7ois",
-        "Duclap, Delphine",
-        "Leboyer, Marion ",
-        "Fillard, Pierre",
-        "Houenou, Josselin",
-        "Guevara, Pamela",
-        "Le Bihan, Denis J.",
-        "Marrakchi-Kacem, Linda "
-    ],
-    "DOI": "http://dx.doi.org/10.25493/C2AD-H32",
-    "DiscHierarchy": [
-        "3.2.1.5",
-        "Microbiology, Virology and Immunology",
-        "Immunology"
-    ],
-    "Discipline": "Neuroscience",
-    "Format": [
-        "NIFTI"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://148.187.98.42:8443/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.25493_C2AD-H32",
-    "MetadataAccess": [
-        "10.25493_C2AD-H32"
-    ],
-    "PublicationTimestamp": "2019-06-14T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Human Brain Project"
-    ],
-    "RelatedIdentifier": [
-        "https://doi.org/10.1016/j.neuroimage.2012.02.071"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International"
-    ],
-    "author": [
-        "Mangin, Jean-Fran\u00e7ois"
-    ],
-    "fulltext": "10.25493_C2AD-H32;2019-12-10T12:41:51Z;https://doi.org/10.25493/C2AD-H32;Probabilistic map of the anterior segment of the right arcuate fasciculus (atlas of deep white matter fibre bundles, version 2018);2019-06-14T13:19:30.546Z;This data contains the probability map of the anterior segment of the right arcuate fasciculus (atlas of deep white matter fibre bundles, version 2018), in the MNI ICBM152 reference brain. This bundle was identified by fibre clustering, from the tractography datasets of 78 subjects in Neurospin\u2019s ARCHI database. The map shows the probability of finding a fibre belonging to the bundle in each voxel of the reference brain. The maximum probability corresponds to the voxels with the highest number of putative fibres going through.;neuroscience;brain mapping;imaging;english;dataset;The Human Brain Project;Guevara, Pamela;Duclap, Delphine;Poupon, Cyril;Marrakchi-Kacem, Linda ;Fillard, Pierre;Le Bihan, Denis J.;Leboyer, Marion ;Houenou, Josselin;Mangin, Jean-Fran\u00e7ois;Mangin, Jean-Fran\u00e7ois;NIFTI;Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International;https://doi.org/10.1016/j.neuroimage.2012.02.071",
-    "group": "hbp",
-    "groups": [
-        {
-            "name": "hbp"
-        }
-    ],
-    "name": "2cbafa21-9b6c-5218-afa8-e61fe6e7164e",
-    "notes": [
-        "This data contains the probability map of the anterior segment of the right arcuate fasciculus (atlas of deep white matter fibre bundles, version 2018), in the MNI ICBM152 reference brain. This bundle was identified by fibre clustering, from the tractography datasets of 78 subjects in Neurospin\u2019s ARCHI database. The map shows the probability of finding a fibre belonging to the bundle in each voxel of the reference brain. The maximum probability corresponds to the voxels with the highest number of putative fibres going through."
-    ],
-    "oai_identifier": [
-        "10.25493_C2AD-H32"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "neuroscience"
-        },
-        {
-            "name": "brain mapping"
-        },
-        {
-            "name": "imaging"
-        }
-    ],
-    "title": [
-        "Probabilistic map of the anterior segment of the right arcuate fasciculus (atlas of deep white matter fibre bundles, version 2018)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/hbp-oai_dc/SET_1/json/2d208f28-7ac3-5983-9d3c-d1ddd274f9da.json b/oaitestdata/hbp-oai_dc/SET_1/json/2d208f28-7ac3-5983-9d3c-d1ddd274f9da.json
deleted file mode 100644
index 60865b54..00000000
--- a/oaitestdata/hbp-oai_dc/SET_1/json/2d208f28-7ac3-5983-9d3c-d1ddd274f9da.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "https://www.humanbrainproject.eu/"
-    ],
-    "Contributor": [
-        "Schleicher, Axel",
-        "Mohlberg, Hartmut",
-        "Geyer, Stefan",
-        "Zilles, Karl",
-        "Schormann, Thorsten"
-    ],
-    "DOI": "http://dx.doi.org/10.25493/THB5-B64",
-    "DiscHierarchy": [
-        "3.2",
-        "Life Sciences",
-        "Medicine"
-    ],
-    "Discipline": "Neuroscience",
-    "Format": [
-        "NIFTI"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://148.187.98.42:8443/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.25493_THB5-B64",
-    "MetadataAccess": [
-        "10.25493_THB5-B64"
-    ],
-    "PublicationTimestamp": "2019-06-04T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Human Brain Project"
-    ],
-    "RelatedIdentifier": [
-        "https://doi.org/10.1006/nimg.2000.0548",
-        "https://doi.org/10.1006/nimg.1999.0440"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International"
-    ],
-    "author": [
-        "Amunts, Katrin"
-    ],
-    "fulltext": "10.25493_THB5-B64;2019-12-10T12:41:53Z;https://doi.org/10.25493/THB5-B64;Probabilistic cytoarchitectonic map of Area 1 (PostCG) (v8.4);2019-06-04T16:28:25.516Z;This dataset contains the distinct architectonic Area 1 (PostCG) in the individual, single subject template of the MNI Colin 27 as well as the MNI ICBM 152 2009c nonlinear asymmetric reference space. As part of the JuBrain cytoarchitectonic atlas, the area was identified using cytoarchitectonic analysis on cell-body-stained histological sections of 10 human postmortem brains obtained from the body donor program of the University of D\u00fcsseldorf. The results of the cytoarchitectonic analysis were then mapped to both reference spaces, where each voxel was assigned the probability to belong to Area 1 (PostCG). The probability map of Area 1 (PostCG) is provided in the NifTi format for each brain reference space and hemisphere. The JuBrain atlas relies on a modular, flexible and adaptive framework containing workflows to create the probabilistic brain maps for these structures. Note that methodological improvements and integration of new brain structures may lead to small deviations in earlier released datasets.;neuroscience;histology;imaging;brain mapping;english;dataset;The Human Brain Project;Geyer, Stefan;Schleicher, Axel;Schormann, Thorsten;Mohlberg, Hartmut;Zilles, Karl;Amunts, Katrin;NIFTI;Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International;https://doi.org/10.1006/nimg.2000.0548;https://doi.org/10.1006/nimg.1999.0440",
-    "group": "hbp",
-    "groups": [
-        {
-            "name": "hbp"
-        }
-    ],
-    "name": "2d208f28-7ac3-5983-9d3c-d1ddd274f9da",
-    "notes": [
-        "This dataset contains the distinct architectonic Area 1 (PostCG) in the individual, single subject template of the MNI Colin 27 as well as the MNI ICBM 152 2009c nonlinear asymmetric reference space. As part of the JuBrain cytoarchitectonic atlas, the area was identified using cytoarchitectonic analysis on cell-body-stained histological sections of 10 human postmortem brains obtained from the body donor program of the University of D\u00fcsseldorf. The results of the cytoarchitectonic analysis were then mapped to both reference spaces, where each voxel was assigned the probability to belong to Area 1 (PostCG). The probability map of Area 1 (PostCG) is provided in the NifTi format for each brain reference space and hemisphere. The JuBrain atlas relies on a modular, flexible and adaptive framework containing workflows to create the probabilistic brain maps for these structures. Note that methodological improvements and integration of new brain structures may lead to small deviations in earlier released datasets."
-    ],
-    "oai_identifier": [
-        "10.25493_THB5-B64"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "neuroscience"
-        },
-        {
-            "name": "histology"
-        },
-        {
-            "name": "imaging"
-        },
-        {
-            "name": "brain mapping"
-        }
-    ],
-    "title": [
-        "Probabilistic cytoarchitectonic map of Area 1 (PostCG) (v8.4)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/hbp-oai_dc/SET_1/json/2d740789-5a56-5ec4-b0a3-17249f387116.json b/oaitestdata/hbp-oai_dc/SET_1/json/2d740789-5a56-5ec4-b0a3-17249f387116.json
deleted file mode 100644
index f048a9d1..00000000
--- a/oaitestdata/hbp-oai_dc/SET_1/json/2d740789-5a56-5ec4-b0a3-17249f387116.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "https://www.humanbrainproject.eu/"
-    ],
-    "Contributor": [
-        "Bludau, Sebastian",
-        "Eickhoff, Simon B.",
-        "Caspers, Svenja",
-        "Sigl, Benjamin",
-        "Mohlberg, Hartmut",
-        "Amunts, Katrin"
-    ],
-    "DOI": "http://dx.doi.org/10.25493/40J8-TAK",
-    "DiscHierarchy": [
-        "3.2",
-        "Life Sciences",
-        "Medicine"
-    ],
-    "Discipline": "Neuroscience",
-    "Format": [
-        "NIFTI"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://148.187.98.42:8443/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.25493_40J8-TAK",
-    "MetadataAccess": [
-        "10.25493_40J8-TAK"
-    ],
-    "PublicationTimestamp": "2019-06-04T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Human Brain Project"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International"
-    ],
-    "author": [
-        "Amunts, Katrin"
-    ],
-    "fulltext": "10.25493_40J8-TAK;2019-12-10T12:41:55Z;https://doi.org/10.25493/40J8-TAK;Probabilistic cytoarchitectonic map of Area 6d3 (SFS) (v4.0);2019-06-04T09:38:06.258Z;This dataset contains the distinct probabilistic cytoarchitectonic map of Area 6d3 (SFS) in the individual, single subject template of the MNI Colin 27 reference space. As part of the JuBrain cytoarchitectonic atlas, the area was identified using cytoarchitectonic analysis on cell-body-stained histological sections of 10 human postmortem brains obtained from the body donor program of the University of D\u00fcsseldorf. The results of the cytoarchitectonic analysis were then mapped to the reference space, where each voxel was assigned the probability to belong to Area 6d3 (SFS). The probability map of Area 6d3 (SFS) is provided in NifTi format for each hemisphere in the reference space. The JuBrain atlas relies on a modular, flexible and adaptive framework containing workflows to create the probabilistic brain maps for these structures. Note that methodological improvements and updated probability estimates for new brain structures may in some cases lead to measurable but negligible deviations of existing probability maps, as compared to earlier released datasets.  \n\nOther available data versions of Area 6d3 (SFS):\nSigl et al. (2019) [Data set, v4.1] [DOI: 10.25493/NVJ5-JJ](https://doi.org/10.25493%2FNVJ5-JJ)\n\nThe most probable delineation of Area 6d3 (SFS) derived from the calculation of a maximum probability map of all currently released JuBrain brain structures can be found here:\nAmunts et al. (2019) [Data set, v18] [DOI: 10.25493/8EGG-ZAR](https://doi.org/10.25493%2F8EGG-ZAR)\n;neuroscience;histology;imaging;brain mapping;english;dataset;The Human Brain Project;Sigl, Benjamin;Caspers, Svenja;Bludau, Sebastian;Mohlberg, Hartmut;Eickhoff, Simon B.;Amunts, Katrin;Amunts, Katrin;NIFTI;Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International",
-    "group": "hbp",
-    "groups": [
-        {
-            "name": "hbp"
-        }
-    ],
-    "name": "2d740789-5a56-5ec4-b0a3-17249f387116",
-    "notes": [
-        "This dataset contains the distinct probabilistic cytoarchitectonic map of Area 6d3 (SFS) in the individual, single subject template of the MNI Colin 27 reference space. As part of the JuBrain cytoarchitectonic atlas, the area was identified using cytoarchitectonic analysis on cell-body-stained histological sections of 10 human postmortem brains obtained from the body donor program of the University of D\u00fcsseldorf. The results of the cytoarchitectonic analysis were then mapped to the reference space, where each voxel was assigned the probability to belong to Area 6d3 (SFS). The probability map of Area 6d3 (SFS) is provided in NifTi format for each hemisphere in the reference space. The JuBrain atlas relies on a modular, flexible and adaptive framework containing workflows to create the probabilistic brain maps for these structures. Note that methodological improvements and updated probability estimates for new brain structures may in some cases lead to measurable but negligible deviations of existing probability maps, as compared to earlier released datasets.  \n\nOther available data versions of Area 6d3 (SFS):\nSigl et al. (2019) [Data set, v4.1] [DOI: 10.25493/NVJ5-JJ](https://doi.org/10.25493%2FNVJ5-JJ)\n\nThe most probable delineation of Area 6d3 (SFS) derived from the calculation of a maximum probability map of all currently released JuBrain brain structures can be found here:\nAmunts et al. (2019) [Data set, v18] [DOI: 10.25493/8EGG-ZAR](https://doi.org/10.25493%2F8EGG-ZAR)\n"
-    ],
-    "oai_identifier": [
-        "10.25493_40J8-TAK"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "neuroscience"
-        },
-        {
-            "name": "histology"
-        },
-        {
-            "name": "imaging"
-        },
-        {
-            "name": "brain mapping"
-        }
-    ],
-    "title": [
-        "Probabilistic cytoarchitectonic map of Area 6d3 (SFS) (v4.0)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/hbp-oai_dc/SET_1/json/2e59364c-a582-5ef8-b2d1-01f2fe836da3.json b/oaitestdata/hbp-oai_dc/SET_1/json/2e59364c-a582-5ef8-b2d1-01f2fe836da3.json
deleted file mode 100644
index 7c7c70d8..00000000
--- a/oaitestdata/hbp-oai_dc/SET_1/json/2e59364c-a582-5ef8-b2d1-01f2fe836da3.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "https://www.humanbrainproject.eu/"
-    ],
-    "Contributor": [
-        "Bludau, Sebastian",
-        "Eickhoff, Simon B.",
-        "Tellmann, Stefanie",
-        "Mohlberg, Hartmut",
-        "Amunts, Katrin",
-        "Minnerop, Martina"
-    ],
-    "DOI": "http://dx.doi.org/10.25493/8PTB-JDH",
-    "DiscHierarchy": [
-        "3.2",
-        "Life Sciences",
-        "Medicine"
-    ],
-    "Discipline": "Neuroscience",
-    "Format": [
-        "NIFTI"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://148.187.98.42:8443/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.25493_8PTB-JDH",
-    "MetadataAccess": [
-        "10.25493_8PTB-JDH"
-    ],
-    "PublicationTimestamp": "2019-06-05T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Human Brain Project"
-    ],
-    "RelatedIdentifier": [
-        "https://doi.org/10.3389/fnana.2015.00054"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International"
-    ],
-    "author": [
-        "Amunts, Katrin"
-    ],
-    "fulltext": "10.25493_8PTB-JDH;2019-12-10T12:41:52Z;https://doi.org/10.25493/8PTB-JDH;Probabilistic cytoarchitectonic map of Interposed Nucleus (Cerebellum) (v6.2);2019-06-05T12:42:04.021Z;This dataset contains the distinct architectonic Interposed Nucleus (Cerebellum) in the individual, single subject template of the MNI Colin 27 as well as the MNI ICBM 152 2009c nonlinear asymmetric reference space. As part of the JuBrain cytoarchitectonic atlas, the area was identified using cytoarchitectonic analysis on cell-body-stained histological sections of 10 human postmortem brains obtained from the body donor program of the University of D\u00fcsseldorf. The results of the cytoarchitectonic analysis were then mapped to both reference spaces, where each voxel was assigned the probability to belong to Interposed Nucleus (Cerebellum). The probability map of Interposed Nucleus (Cerebellum) is provided in the NifTi format for each brain reference space and hemisphere. The JuBrain atlas relies on a modular, flexible and adaptive framework containing workflows to create the probabilistic brain maps for these structures. Note that methodological improvements and integration of new brain structures may lead to small deviations in earlier released datasets.;neuroscience;histology;imaging;brain mapping;english;dataset;The Human Brain Project;Tellmann, Stefanie;Bludau, Sebastian;Eickhoff, Simon B.;Mohlberg, Hartmut;Minnerop, Martina;Amunts, Katrin;Amunts, Katrin;NIFTI;Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International;https://doi.org/10.3389/fnana.2015.00054",
-    "group": "hbp",
-    "groups": [
-        {
-            "name": "hbp"
-        }
-    ],
-    "name": "2e59364c-a582-5ef8-b2d1-01f2fe836da3",
-    "notes": [
-        "This dataset contains the distinct architectonic Interposed Nucleus (Cerebellum) in the individual, single subject template of the MNI Colin 27 as well as the MNI ICBM 152 2009c nonlinear asymmetric reference space. As part of the JuBrain cytoarchitectonic atlas, the area was identified using cytoarchitectonic analysis on cell-body-stained histological sections of 10 human postmortem brains obtained from the body donor program of the University of D\u00fcsseldorf. The results of the cytoarchitectonic analysis were then mapped to both reference spaces, where each voxel was assigned the probability to belong to Interposed Nucleus (Cerebellum). The probability map of Interposed Nucleus (Cerebellum) is provided in the NifTi format for each brain reference space and hemisphere. The JuBrain atlas relies on a modular, flexible and adaptive framework containing workflows to create the probabilistic brain maps for these structures. Note that methodological improvements and integration of new brain structures may lead to small deviations in earlier released datasets."
-    ],
-    "oai_identifier": [
-        "10.25493_8PTB-JDH"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "neuroscience"
-        },
-        {
-            "name": "histology"
-        },
-        {
-            "name": "imaging"
-        },
-        {
-            "name": "brain mapping"
-        }
-    ],
-    "title": [
-        "Probabilistic cytoarchitectonic map of Interposed Nucleus (Cerebellum) (v6.2)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/hbp-oai_dc/SET_1/json/2fefb752-8956-50bc-8aa2-37b1ffdc4c88.json b/oaitestdata/hbp-oai_dc/SET_1/json/2fefb752-8956-50bc-8aa2-37b1ffdc4c88.json
deleted file mode 100644
index bbd5a5ae..00000000
--- a/oaitestdata/hbp-oai_dc/SET_1/json/2fefb752-8956-50bc-8aa2-37b1ffdc4c88.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "https://www.humanbrainproject.eu/"
-    ],
-    "Contributor": [
-        "Poupon, Cyril",
-        "Mangin, Jean-Fran\u00e7ois",
-        "Duclap, Delphine",
-        "Leboyer, Marion ",
-        "Fillard, Pierre",
-        "Houenou, Josselin",
-        "Guevara, Pamela",
-        "Le Bihan, Denis J.",
-        "Marrakchi-Kacem, Linda "
-    ],
-    "DOI": "http://dx.doi.org/10.25493/TD88-5AQ",
-    "DiscHierarchy": [
-        "3.2.1.5",
-        "Microbiology, Virology and Immunology",
-        "Immunology"
-    ],
-    "Discipline": "Neuroscience",
-    "Format": [
-        "NIFTI"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://148.187.98.42:8443/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.25493_TD88-5AQ",
-    "MetadataAccess": [
-        "10.25493_TD88-5AQ"
-    ],
-    "PublicationTimestamp": "2019-06-14T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Human Brain Project"
-    ],
-    "RelatedIdentifier": [
-        "https://doi.org/10.1016/j.neuroimage.2012.02.071"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International"
-    ],
-    "author": [
-        "Mangin, Jean-Fran\u00e7ois"
-    ],
-    "fulltext": "10.25493_TD88-5AQ;2019-12-10T12:41:54Z;https://doi.org/10.25493/TD88-5AQ;Probabilistic map of the posterior segment of the left arcuate fasciculus (atlas of deep white matter fibre bundles, version 2018);2019-06-14T13:29:32.297Z;This data contains the probability map of the posterior segment of the left arcuate fasciculus (atlas of deep white matter fibre bundles, version 2018), in the MNI ICBM152 reference brain. This bundle was identified by fibre clustering, from the tractography datasets of 78 subjects in Neurospin\u2019s ARCHI database. The map shows the probability of finding a fibre belonging to the bundle in each voxel of the reference brain. The maximum probability corresponds to the voxels with the highest number of putative fibres going through.;neuroscience;brain mapping;imaging;english;dataset;The Human Brain Project;Guevara, Pamela;Duclap, Delphine;Poupon, Cyril;Marrakchi-Kacem, Linda ;Fillard, Pierre;Le Bihan, Denis J.;Leboyer, Marion ;Houenou, Josselin;Mangin, Jean-Fran\u00e7ois;Mangin, Jean-Fran\u00e7ois;NIFTI;Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International;https://doi.org/10.1016/j.neuroimage.2012.02.071",
-    "group": "hbp",
-    "groups": [
-        {
-            "name": "hbp"
-        }
-    ],
-    "name": "2fefb752-8956-50bc-8aa2-37b1ffdc4c88",
-    "notes": [
-        "This data contains the probability map of the posterior segment of the left arcuate fasciculus (atlas of deep white matter fibre bundles, version 2018), in the MNI ICBM152 reference brain. This bundle was identified by fibre clustering, from the tractography datasets of 78 subjects in Neurospin\u2019s ARCHI database. The map shows the probability of finding a fibre belonging to the bundle in each voxel of the reference brain. The maximum probability corresponds to the voxels with the highest number of putative fibres going through."
-    ],
-    "oai_identifier": [
-        "10.25493_TD88-5AQ"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "neuroscience"
-        },
-        {
-            "name": "brain mapping"
-        },
-        {
-            "name": "imaging"
-        }
-    ],
-    "title": [
-        "Probabilistic map of the posterior segment of the left arcuate fasciculus (atlas of deep white matter fibre bundles, version 2018)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/herbadrop-json/SET_1/json/01a6d742-786b-5e3d-829b-ed514a15c75e.json b/oaitestdata/herbadrop-json/SET_1/json/01a6d742-786b-5e3d-829b-ed514a15c75e.json
deleted file mode 100644
index ad19d3a2..00000000
--- a/oaitestdata/herbadrop-json/SET_1/json/01a6d742-786b-5e3d-829b-ed514a15c75e.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contributor": [
-        "CINES"
-    ],
-    "DiscHierarchy": [
-        "3.1.2",
-        "Live Sciences",
-        "Plant Sciences "
-    ],
-    "Discipline": "Plant_Sciences",
-    "Format": [
-        "unavailable"
-    ],
-    "MetaDataAccess": "https://opendata.cines.fr/herbadrop-api/rest/data/search/dataset/01a6d742-786b-5e3d-829b-ed514a15c75e",
-    "MetaDataAcess": [
-        "P04121281"
-    ],
-    "OpenAccess": [
-        "true"
-    ],
-    "PublicationTimestamp": "2019-01-25T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "MNHN"
-    ],
-    "ResourceType": [
-        "PRESERVED_SPECIMEN"
-    ],
-    "Rights": [
-        "unavailable"
-    ],
-    "author": [
-        "unavailable"
-    ],
-    "group": "herbadrop",
-    "groups": [
-        {
-            "name": "herbadrop"
-        }
-    ],
-    "name": "01a6d742-786b-5e3d-829b-ed514a15c75e",
-    "namespaces": [
-        ":"
-    ],
-    "notes": [
-        "Digitized_herbarium_sheet",
-        "unavailable"
-    ],
-    "oai_identifier": [
-        "01a6d742-786b-5e3d-829b-ed514a15c75e"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Asteraceae"
-        }
-    ],
-    "title": [
-        "Taraxacum fagerstroemii Saltin"
-    ],
-    "url": "http://coldb.mnhn.fr/catalognumber/mnhn/p/p04121281"
-}
\ No newline at end of file
diff --git a/oaitestdata/herbadrop-json/SET_1/json/01a980e7-bc01-5068-a83f-f4444ef234e3.json b/oaitestdata/herbadrop-json/SET_1/json/01a980e7-bc01-5068-a83f-f4444ef234e3.json
deleted file mode 100644
index 8c5a58be..00000000
--- a/oaitestdata/herbadrop-json/SET_1/json/01a980e7-bc01-5068-a83f-f4444ef234e3.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contributor": [
-        "CINES"
-    ],
-    "DiscHierarchy": [
-        "3.1.2",
-        "Live Sciences",
-        "Plant Sciences "
-    ],
-    "Discipline": "Plant_Sciences",
-    "Format": [
-        "image/jpeg"
-    ],
-    "MetaDataAccess": "https://opendata.cines.fr/herbadrop-api/rest/data/search/dataset/01a980e7-bc01-5068-a83f-f4444ef234e3",
-    "MetaDataAcess": [
-        "P05293617"
-    ],
-    "OpenAccess": [
-        "true"
-    ],
-    "PublicationTimestamp": "2019-02-25T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "MNHN"
-    ],
-    "ResourceType": [
-        "StillImage|PRESERVED_SPECIMEN"
-    ],
-    "Rights": [
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "unavailable"
-    ],
-    "group": "herbadrop",
-    "groups": [
-        {
-            "name": "herbadrop"
-        }
-    ],
-    "name": "01a980e7-bc01-5068-a83f-f4444ef234e3",
-    "namespaces": [
-        ":"
-    ],
-    "notes": [
-        "Digitized_herbarium_sheet",
-        "unavailable"
-    ],
-    "oai_identifier": [
-        "01a980e7-bc01-5068-a83f-f4444ef234e3"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Amaranthaceae"
-        }
-    ],
-    "title": [
-        "Guilleminea densa Moq."
-    ],
-    "url": "http://coldb.mnhn.fr/catalognumber/mnhn/p/p05293617"
-}
\ No newline at end of file
diff --git a/oaitestdata/herbadrop-json/SET_1/json/01bbfdaf-57d4-5e09-9846-9f58df3d7513.json b/oaitestdata/herbadrop-json/SET_1/json/01bbfdaf-57d4-5e09-9846-9f58df3d7513.json
deleted file mode 100644
index 9ee1f849..00000000
--- a/oaitestdata/herbadrop-json/SET_1/json/01bbfdaf-57d4-5e09-9846-9f58df3d7513.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contributor": [
-        "CINES"
-    ],
-    "DiscHierarchy": [
-        "3.1.2",
-        "Live Sciences",
-        "Plant Sciences "
-    ],
-    "Discipline": "Plant_Sciences",
-    "Format": [
-        "image/jpeg"
-    ],
-    "MetaDataAccess": "https://opendata.cines.fr/herbadrop-api/rest/data/search/dataset/01bbfdaf-57d4-5e09-9846-9f58df3d7513",
-    "MetaDataAcess": [
-        "P03335837"
-    ],
-    "OpenAccess": [
-        "true"
-    ],
-    "PublicationTimestamp": "2019-05-28T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "MNHN"
-    ],
-    "ResourceType": [
-        "StillImage|PRESERVED_SPECIMEN"
-    ],
-    "Rights": [
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "unavailable"
-    ],
-    "group": "herbadrop",
-    "groups": [
-        {
-            "name": "herbadrop"
-        }
-    ],
-    "name": "01bbfdaf-57d4-5e09-9846-9f58df3d7513",
-    "namespaces": [
-        ":"
-    ],
-    "notes": [
-        "Digitized_herbarium_sheet",
-        "unavailable"
-    ],
-    "oai_identifier": [
-        "01bbfdaf-57d4-5e09-9846-9f58df3d7513"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Fabaceae"
-        }
-    ],
-    "title": [
-        "Indigofera melanadenia Benth. ex Harv. & Sond."
-    ],
-    "url": "http://coldb.mnhn.fr/catalognumber/mnhn/p/p03335837"
-}
\ No newline at end of file
diff --git a/oaitestdata/herbadrop-json/SET_1/json/0a8a3ae1-0b1f-54ce-9b5a-962e197d0b9b.json b/oaitestdata/herbadrop-json/SET_1/json/0a8a3ae1-0b1f-54ce-9b5a-962e197d0b9b.json
deleted file mode 100644
index 1b76a951..00000000
--- a/oaitestdata/herbadrop-json/SET_1/json/0a8a3ae1-0b1f-54ce-9b5a-962e197d0b9b.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contributor": [
-        "CINES"
-    ],
-    "DiscHierarchy": [
-        "3.1.2",
-        "Live Sciences",
-        "Plant Sciences "
-    ],
-    "Discipline": "Plant_Sciences",
-    "Format": [
-        "image/jpeg"
-    ],
-    "MetaDataAccess": "https://opendata.cines.fr/herbadrop-api/rest/data/search/dataset/0a8a3ae1-0b1f-54ce-9b5a-962e197d0b9b",
-    "MetaDataAcess": [
-        "P02662526"
-    ],
-    "OpenAccess": [
-        "true"
-    ],
-    "PublicationTimestamp": "2019-05-26T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "MNHN"
-    ],
-    "ResourceType": [
-        "StillImage|PRESERVED_SPECIMEN"
-    ],
-    "Rights": [
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "unavailable"
-    ],
-    "group": "herbadrop",
-    "groups": [
-        {
-            "name": "herbadrop"
-        }
-    ],
-    "name": "0a8a3ae1-0b1f-54ce-9b5a-962e197d0b9b",
-    "namespaces": [
-        ":"
-    ],
-    "notes": [
-        "Digitized_herbarium_sheet",
-        "unavailable"
-    ],
-    "oai_identifier": [
-        "0a8a3ae1-0b1f-54ce-9b5a-962e197d0b9b"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Poaceae"
-        }
-    ],
-    "title": [
-        "Aristida rhiniochloa Hochst."
-    ],
-    "url": "http://coldb.mnhn.fr/catalognumber/mnhn/p/p02662526"
-}
\ No newline at end of file
diff --git a/oaitestdata/herbadrop-json/SET_1/json/0ae70038-4090-5c7e-b487-6b7b17b5bd31.json b/oaitestdata/herbadrop-json/SET_1/json/0ae70038-4090-5c7e-b487-6b7b17b5bd31.json
deleted file mode 100644
index 0dec9d68..00000000
--- a/oaitestdata/herbadrop-json/SET_1/json/0ae70038-4090-5c7e-b487-6b7b17b5bd31.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contributor": [
-        "CINES"
-    ],
-    "DiscHierarchy": [
-        "3.1.2",
-        "Live Sciences",
-        "Plant Sciences "
-    ],
-    "Discipline": "Plant_Sciences",
-    "Format": [
-        "image/jpeg"
-    ],
-    "MetaDataAccess": "https://opendata.cines.fr/herbadrop-api/rest/data/search/dataset/0ae70038-4090-5c7e-b487-6b7b17b5bd31",
-    "MetaDataAcess": [
-        "P04370949"
-    ],
-    "OpenAccess": [
-        "true"
-    ],
-    "PublicationTimestamp": "2019-02-06T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "MNHN"
-    ],
-    "ResourceType": [
-        "StillImage|PRESERVED_SPECIMEN"
-    ],
-    "Rights": [
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "unavailable"
-    ],
-    "group": "herbadrop",
-    "groups": [
-        {
-            "name": "herbadrop"
-        }
-    ],
-    "name": "0ae70038-4090-5c7e-b487-6b7b17b5bd31",
-    "namespaces": [
-        ":"
-    ],
-    "notes": [
-        "Digitized_herbarium_sheet",
-        "unavailable"
-    ],
-    "oai_identifier": [
-        "0ae70038-4090-5c7e-b487-6b7b17b5bd31"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Asteraceae"
-        }
-    ],
-    "title": [
-        "Senecio Herbarium Practice & Following Welman."
-    ],
-    "url": "http://coldb.mnhn.fr/catalognumber/mnhn/p/p04370949"
-}
\ No newline at end of file
diff --git a/oaitestdata/herbadrop-json/SET_1/json/0b1f621c-3569-5d9d-9cbf-411c5b73c926.json b/oaitestdata/herbadrop-json/SET_1/json/0b1f621c-3569-5d9d-9cbf-411c5b73c926.json
deleted file mode 100644
index 06915e33..00000000
--- a/oaitestdata/herbadrop-json/SET_1/json/0b1f621c-3569-5d9d-9cbf-411c5b73c926.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contributor": [
-        "CINES"
-    ],
-    "DiscHierarchy": [
-        "3.1.2",
-        "Live Sciences",
-        "Plant Sciences "
-    ],
-    "Discipline": "Plant_Sciences",
-    "Format": [
-        "image/jpeg"
-    ],
-    "MetaDataAccess": "https://opendata.cines.fr/herbadrop-api/rest/data/search/dataset/0b1f621c-3569-5d9d-9cbf-411c5b73c926",
-    "MetaDataAcess": [
-        "P03056153"
-    ],
-    "OpenAccess": [
-        "true"
-    ],
-    "PublicationTimestamp": "2019-04-27T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "MNHN"
-    ],
-    "ResourceType": [
-        "StillImage|PRESERVED_SPECIMEN"
-    ],
-    "Rights": [
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "unavailable"
-    ],
-    "group": "herbadrop",
-    "groups": [
-        {
-            "name": "herbadrop"
-        }
-    ],
-    "name": "0b1f621c-3569-5d9d-9cbf-411c5b73c926",
-    "namespaces": [
-        ":"
-    ],
-    "notes": [
-        "Digitized_herbarium_sheet",
-        "unavailable"
-    ],
-    "oai_identifier": [
-        "0b1f621c-3569-5d9d-9cbf-411c5b73c926"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Fabaceae"
-        }
-    ],
-    "title": [
-        "Trifolium ochroleucon Huds."
-    ],
-    "url": "http://coldb.mnhn.fr/catalognumber/mnhn/p/p03056153"
-}
\ No newline at end of file
diff --git a/oaitestdata/herbadrop-json/SET_1/json/0b3a53c5-37bd-5d0c-963d-d92e4d245ef6.json b/oaitestdata/herbadrop-json/SET_1/json/0b3a53c5-37bd-5d0c-963d-d92e4d245ef6.json
deleted file mode 100644
index 664e8680..00000000
--- a/oaitestdata/herbadrop-json/SET_1/json/0b3a53c5-37bd-5d0c-963d-d92e4d245ef6.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contributor": [
-        "CINES"
-    ],
-    "DiscHierarchy": [
-        "3.1.2",
-        "Live Sciences",
-        "Plant Sciences "
-    ],
-    "Discipline": "Plant_Sciences",
-    "Format": [
-        "image/jpeg"
-    ],
-    "MetaDataAccess": "https://opendata.cines.fr/herbadrop-api/rest/data/search/dataset/0b3a53c5-37bd-5d0c-963d-d92e4d245ef6",
-    "MetaDataAcess": [
-        "P03078664"
-    ],
-    "OpenAccess": [
-        "true"
-    ],
-    "PublicationTimestamp": "2019-04-11T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "MNHN"
-    ],
-    "ResourceType": [
-        "StillImage|PRESERVED_SPECIMEN"
-    ],
-    "Rights": [
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "unavailable"
-    ],
-    "group": "herbadrop",
-    "groups": [
-        {
-            "name": "herbadrop"
-        }
-    ],
-    "name": "0b3a53c5-37bd-5d0c-963d-d92e4d245ef6",
-    "namespaces": [
-        ":"
-    ],
-    "notes": [
-        "Digitized_herbarium_sheet",
-        "unavailable"
-    ],
-    "oai_identifier": [
-        "0b3a53c5-37bd-5d0c-963d-d92e4d245ef6"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Fabaceae"
-        }
-    ],
-    "title": [
-        "Hippocrepis multisiliquosa L."
-    ],
-    "url": "http://coldb.mnhn.fr/catalognumber/mnhn/p/p03078664"
-}
\ No newline at end of file
diff --git a/oaitestdata/herbadrop-json/SET_1/json/0b770a14-af85-55e2-ae60-3128d9721851.json b/oaitestdata/herbadrop-json/SET_1/json/0b770a14-af85-55e2-ae60-3128d9721851.json
deleted file mode 100644
index f8d92fa8..00000000
--- a/oaitestdata/herbadrop-json/SET_1/json/0b770a14-af85-55e2-ae60-3128d9721851.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contributor": [
-        "CINES"
-    ],
-    "DiscHierarchy": [
-        "3.1.2",
-        "Live Sciences",
-        "Plant Sciences "
-    ],
-    "Discipline": "Plant_Sciences",
-    "Format": [
-        "image/jpeg"
-    ],
-    "MetaDataAccess": "https://opendata.cines.fr/herbadrop-api/rest/data/search/dataset/0b770a14-af85-55e2-ae60-3128d9721851",
-    "MetaDataAcess": [
-        "P02657174"
-    ],
-    "OpenAccess": [
-        "true"
-    ],
-    "PublicationTimestamp": "2019-05-25T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "MNHN"
-    ],
-    "ResourceType": [
-        "StillImage|PRESERVED_SPECIMEN"
-    ],
-    "Rights": [
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "unavailable"
-    ],
-    "group": "herbadrop",
-    "groups": [
-        {
-            "name": "herbadrop"
-        }
-    ],
-    "name": "0b770a14-af85-55e2-ae60-3128d9721851",
-    "namespaces": [
-        ":"
-    ],
-    "notes": [
-        "Digitized_herbarium_sheet",
-        "unavailable"
-    ],
-    "oai_identifier": [
-        "0b770a14-af85-55e2-ae60-3128d9721851"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Poaceae"
-        }
-    ],
-    "title": [
-        "Catapodium rigidum (L.) C.E.Hubb."
-    ],
-    "url": "http://coldb.mnhn.fr/catalognumber/mnhn/p/p02657174"
-}
\ No newline at end of file
diff --git a/oaitestdata/herbadrop-json/SET_1/json/0bbd5df2-4c8c-566b-84c4-b5d02f15c7ff.json b/oaitestdata/herbadrop-json/SET_1/json/0bbd5df2-4c8c-566b-84c4-b5d02f15c7ff.json
deleted file mode 100644
index f9c0c924..00000000
--- a/oaitestdata/herbadrop-json/SET_1/json/0bbd5df2-4c8c-566b-84c4-b5d02f15c7ff.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contributor": [
-        "CINES"
-    ],
-    "DiscHierarchy": [
-        "3.1.2",
-        "Live Sciences",
-        "Plant Sciences "
-    ],
-    "Discipline": "Plant_Sciences",
-    "Format": [
-        "image/jpeg"
-    ],
-    "MetaDataAccess": "https://opendata.cines.fr/herbadrop-api/rest/data/search/dataset/0bbd5df2-4c8c-566b-84c4-b5d02f15c7ff",
-    "MetaDataAcess": [
-        "P04842616"
-    ],
-    "OpenAccess": [
-        "true"
-    ],
-    "PublicationTimestamp": "2019-02-15T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "MNHN"
-    ],
-    "ResourceType": [
-        "StillImage|PRESERVED_SPECIMEN"
-    ],
-    "Rights": [
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "unavailable"
-    ],
-    "group": "herbadrop",
-    "groups": [
-        {
-            "name": "herbadrop"
-        }
-    ],
-    "name": "0bbd5df2-4c8c-566b-84c4-b5d02f15c7ff",
-    "namespaces": [
-        ":"
-    ],
-    "notes": [
-        "Digitized_herbarium_sheet",
-        "unavailable"
-    ],
-    "oai_identifier": [
-        "0bbd5df2-4c8c-566b-84c4-b5d02f15c7ff"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Geraniaceae"
-        }
-    ],
-    "title": [
-        "Geranium pratense L."
-    ],
-    "url": "http://coldb.mnhn.fr/catalognumber/mnhn/p/p04842616"
-}
\ No newline at end of file
diff --git a/oaitestdata/herbadrop-json/SET_1/json/0c74b742-e3c5-51de-9ef3-8d89b9309ef5.json b/oaitestdata/herbadrop-json/SET_1/json/0c74b742-e3c5-51de-9ef3-8d89b9309ef5.json
deleted file mode 100644
index e2175dc8..00000000
--- a/oaitestdata/herbadrop-json/SET_1/json/0c74b742-e3c5-51de-9ef3-8d89b9309ef5.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contributor": [
-        "CINES"
-    ],
-    "DiscHierarchy": [
-        "3.1.2",
-        "Live Sciences",
-        "Plant Sciences "
-    ],
-    "Discipline": "Plant_Sciences",
-    "Format": [
-        "image/jpeg"
-    ],
-    "MetaDataAccess": "https://opendata.cines.fr/herbadrop-api/rest/data/search/dataset/0c74b742-e3c5-51de-9ef3-8d89b9309ef5",
-    "MetaDataAcess": [
-        "P04318966"
-    ],
-    "OpenAccess": [
-        "true"
-    ],
-    "PublicationTimestamp": "2019-01-30T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "MNHN"
-    ],
-    "ResourceType": [
-        "StillImage|PRESERVED_SPECIMEN"
-    ],
-    "Rights": [
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "unavailable"
-    ],
-    "group": "herbadrop",
-    "groups": [
-        {
-            "name": "herbadrop"
-        }
-    ],
-    "name": "0c74b742-e3c5-51de-9ef3-8d89b9309ef5",
-    "namespaces": [
-        ":"
-    ],
-    "notes": [
-        "Digitized_herbarium_sheet",
-        "unavailable"
-    ],
-    "oai_identifier": [
-        "0c74b742-e3c5-51de-9ef3-8d89b9309ef5"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Asteraceae"
-        }
-    ],
-    "title": [
-        "Senecio Herbarium Practice & Following Welman."
-    ],
-    "url": "http://coldb.mnhn.fr/catalognumber/mnhn/p/p04318966"
-}
\ No newline at end of file
diff --git a/oaitestdata/herbadrop-json/SET_1/json/0cb3a2f7-1ec4-5efc-b8c2-31139913e119.json b/oaitestdata/herbadrop-json/SET_1/json/0cb3a2f7-1ec4-5efc-b8c2-31139913e119.json
deleted file mode 100644
index 64ea8af8..00000000
--- a/oaitestdata/herbadrop-json/SET_1/json/0cb3a2f7-1ec4-5efc-b8c2-31139913e119.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contributor": [
-        "CINES"
-    ],
-    "DiscHierarchy": [
-        "3.1.2",
-        "Live Sciences",
-        "Plant Sciences "
-    ],
-    "Discipline": "Plant_Sciences",
-    "Format": [
-        "image/jpeg"
-    ],
-    "MetaDataAccess": "https://opendata.cines.fr/herbadrop-api/rest/data/search/dataset/0cb3a2f7-1ec4-5efc-b8c2-31139913e119",
-    "MetaDataAcess": [
-        "P04215733"
-    ],
-    "OpenAccess": [
-        "true"
-    ],
-    "PublicationTimestamp": "2019-01-27T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "MNHN"
-    ],
-    "ResourceType": [
-        "StillImage|PRESERVED_SPECIMEN"
-    ],
-    "Rights": [
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "unavailable"
-    ],
-    "group": "herbadrop",
-    "groups": [
-        {
-            "name": "herbadrop"
-        }
-    ],
-    "name": "0cb3a2f7-1ec4-5efc-b8c2-31139913e119",
-    "namespaces": [
-        ":"
-    ],
-    "notes": [
-        "Digitized_herbarium_sheet",
-        "unavailable"
-    ],
-    "oai_identifier": [
-        "0cb3a2f7-1ec4-5efc-b8c2-31139913e119"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Asteraceae"
-        }
-    ],
-    "title": [
-        "Senecio Herbarium Practice & Following Welman."
-    ],
-    "url": "http://coldb.mnhn.fr/catalognumber/mnhn/p/p04215733"
-}
\ No newline at end of file
diff --git a/oaitestdata/herbadrop-json/SET_1/json/0d137e90-73c4-50d0-b23f-5b0cb589a8fe.json b/oaitestdata/herbadrop-json/SET_1/json/0d137e90-73c4-50d0-b23f-5b0cb589a8fe.json
deleted file mode 100644
index db81fd29..00000000
--- a/oaitestdata/herbadrop-json/SET_1/json/0d137e90-73c4-50d0-b23f-5b0cb589a8fe.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contributor": [
-        "CINES"
-    ],
-    "DiscHierarchy": [
-        "3.1.2",
-        "Live Sciences",
-        "Plant Sciences "
-    ],
-    "Discipline": "Plant_Sciences",
-    "Format": [
-        "unavailable"
-    ],
-    "MetaDataAccess": "https://opendata.cines.fr/herbadrop-api/rest/data/search/dataset/0d137e90-73c4-50d0-b23f-5b0cb589a8fe",
-    "MetaDataAcess": [
-        "P04111227"
-    ],
-    "OpenAccess": [
-        "true"
-    ],
-    "PublicationTimestamp": "2019-01-22T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "MNHN"
-    ],
-    "ResourceType": [
-        "PRESERVED_SPECIMEN"
-    ],
-    "Rights": [
-        "unavailable"
-    ],
-    "author": [
-        "unavailable"
-    ],
-    "group": "herbadrop",
-    "groups": [
-        {
-            "name": "herbadrop"
-        }
-    ],
-    "name": "0d137e90-73c4-50d0-b23f-5b0cb589a8fe",
-    "namespaces": [
-        ":"
-    ],
-    "notes": [
-        "Digitized_herbarium_sheet",
-        "unavailable"
-    ],
-    "oai_identifier": [
-        "0d137e90-73c4-50d0-b23f-5b0cb589a8fe"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Asteraceae"
-        }
-    ],
-    "title": [
-        "Carduus defloratus L."
-    ],
-    "url": "http://coldb.mnhn.fr/catalognumber/mnhn/p/p04111227"
-}
\ No newline at end of file
diff --git a/oaitestdata/herbadrop-json/SET_1/json/0d38f0d2-37f5-54a0-8e09-f3e0fd382c18.json b/oaitestdata/herbadrop-json/SET_1/json/0d38f0d2-37f5-54a0-8e09-f3e0fd382c18.json
deleted file mode 100644
index 3b15fad1..00000000
--- a/oaitestdata/herbadrop-json/SET_1/json/0d38f0d2-37f5-54a0-8e09-f3e0fd382c18.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contributor": [
-        "CINES"
-    ],
-    "DiscHierarchy": [
-        "3.1.2",
-        "Live Sciences",
-        "Plant Sciences "
-    ],
-    "Discipline": "Plant_Sciences",
-    "Format": [
-        "image/jpeg"
-    ],
-    "MetaDataAccess": "https://opendata.cines.fr/herbadrop-api/rest/data/search/dataset/0d38f0d2-37f5-54a0-8e09-f3e0fd382c18",
-    "MetaDataAcess": [
-        "P04034961"
-    ],
-    "OpenAccess": [
-        "true"
-    ],
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "MNHN"
-    ],
-    "ResourceType": [
-        "StillImage|PRESERVED_SPECIMEN"
-    ],
-    "Rights": [
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "unavailable"
-    ],
-    "group": "herbadrop",
-    "groups": [
-        {
-            "name": "herbadrop"
-        }
-    ],
-    "name": "0d38f0d2-37f5-54a0-8e09-f3e0fd382c18",
-    "namespaces": [
-        ":"
-    ],
-    "notes": [
-        "Digitized_herbarium_sheet",
-        "unavailable"
-    ],
-    "oai_identifier": [
-        "0d38f0d2-37f5-54a0-8e09-f3e0fd382c18"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Asteraceae"
-        }
-    ],
-    "title": [
-        "Phagnalon saxatile Cass."
-    ],
-    "url": "http://coldb.mnhn.fr/catalognumber/mnhn/p/p04034961"
-}
\ No newline at end of file
diff --git a/oaitestdata/herbadrop-json/SET_1/json/0d58e235-0498-5c9c-83d5-636cfd36ab8b.json b/oaitestdata/herbadrop-json/SET_1/json/0d58e235-0498-5c9c-83d5-636cfd36ab8b.json
deleted file mode 100644
index 23114db9..00000000
--- a/oaitestdata/herbadrop-json/SET_1/json/0d58e235-0498-5c9c-83d5-636cfd36ab8b.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contributor": [
-        "CINES"
-    ],
-    "DiscHierarchy": [
-        "3.1.2",
-        "Live Sciences",
-        "Plant Sciences "
-    ],
-    "Discipline": "Plant_Sciences",
-    "Format": [
-        "image/jpeg"
-    ],
-    "MetaDataAccess": "https://opendata.cines.fr/herbadrop-api/rest/data/search/dataset/0d58e235-0498-5c9c-83d5-636cfd36ab8b",
-    "MetaDataAcess": [
-        "P04337750"
-    ],
-    "OpenAccess": [
-        "true"
-    ],
-    "PublicationTimestamp": "2019-01-31T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "MNHN"
-    ],
-    "ResourceType": [
-        "StillImage|PRESERVED_SPECIMEN"
-    ],
-    "Rights": [
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "unavailable"
-    ],
-    "group": "herbadrop",
-    "groups": [
-        {
-            "name": "herbadrop"
-        }
-    ],
-    "name": "0d58e235-0498-5c9c-83d5-636cfd36ab8b",
-    "namespaces": [
-        ":"
-    ],
-    "notes": [
-        "Digitized_herbarium_sheet",
-        "unavailable"
-    ],
-    "oai_identifier": [
-        "0d58e235-0498-5c9c-83d5-636cfd36ab8b"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Asteraceae"
-        }
-    ],
-    "title": [
-        "Senecio Herbarium Practice & Following Welman."
-    ],
-    "url": "http://coldb.mnhn.fr/catalognumber/mnhn/p/p04337750"
-}
\ No newline at end of file
diff --git a/oaitestdata/herbadrop-json/SET_1/json/0d87b4de-8281-5042-aaed-ba322247ca21.json b/oaitestdata/herbadrop-json/SET_1/json/0d87b4de-8281-5042-aaed-ba322247ca21.json
deleted file mode 100644
index 21e7230b..00000000
--- a/oaitestdata/herbadrop-json/SET_1/json/0d87b4de-8281-5042-aaed-ba322247ca21.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contributor": [
-        "CINES"
-    ],
-    "DiscHierarchy": [
-        "3.1.2",
-        "Live Sciences",
-        "Plant Sciences "
-    ],
-    "Discipline": "Plant_Sciences",
-    "Format": [
-        "image/jpeg"
-    ],
-    "MetaDataAccess": "https://opendata.cines.fr/herbadrop-api/rest/data/search/dataset/0d87b4de-8281-5042-aaed-ba322247ca21",
-    "MetaDataAcess": [
-        "P02478444"
-    ],
-    "OpenAccess": [
-        "true"
-    ],
-    "PublicationTimestamp": "2018-11-03T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "MNHN"
-    ],
-    "ResourceType": [
-        "StillImage|PRESERVED_SPECIMEN"
-    ],
-    "Rights": [
-        "cc-by"
-    ],
-    "author": [
-        "unavailable"
-    ],
-    "group": "herbadrop",
-    "groups": [
-        {
-            "name": "herbadrop"
-        }
-    ],
-    "name": "0d87b4de-8281-5042-aaed-ba322247ca21",
-    "namespaces": [
-        ":"
-    ],
-    "notes": [
-        "Digitized_herbarium_sheet",
-        "unavailable"
-    ],
-    "oai_identifier": [
-        "0d87b4de-8281-5042-aaed-ba322247ca21"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Asteraceae"
-        }
-    ],
-    "title": [
-        "Senecio Herbarium Practice & Following Welman."
-    ],
-    "url": "http://coldb.mnhn.fr/catalognumber/mnhn/p/p02478444"
-}
\ No newline at end of file
diff --git a/oaitestdata/herbadrop-json/SET_1/json/0d9e8478-3d92-5a5f-92cb-eb678e8e48dd.json b/oaitestdata/herbadrop-json/SET_1/json/0d9e8478-3d92-5a5f-92cb-eb678e8e48dd.json
deleted file mode 100644
index d96da406..00000000
--- a/oaitestdata/herbadrop-json/SET_1/json/0d9e8478-3d92-5a5f-92cb-eb678e8e48dd.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contributor": [
-        "CINES"
-    ],
-    "DiscHierarchy": [
-        "3.1.2",
-        "Live Sciences",
-        "Plant Sciences "
-    ],
-    "Discipline": "Plant_Sciences",
-    "Format": [
-        "image/jpeg"
-    ],
-    "MetaDataAccess": "https://opendata.cines.fr/herbadrop-api/rest/data/search/dataset/0d9e8478-3d92-5a5f-92cb-eb678e8e48dd",
-    "MetaDataAcess": [
-        "P03945291"
-    ],
-    "OpenAccess": [
-        "true"
-    ],
-    "PublicationTimestamp": "2019-06-18T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "MNHN"
-    ],
-    "ResourceType": [
-        "StillImage|PRESERVED_SPECIMEN"
-    ],
-    "Rights": [
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "TempCoverageBegin": 62089588799,
-    "TempCoverageEnd": 62089588799,
-    "TemporalCoverage": " period : ( 1968-07-17T11:59:59Z - 1968-07-17T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1968-07-17T11:59:59Z",
-    "TemporalCoverage:EndDate": "1968-07-17T11:59:59Z",
-    "author": [
-        "Raynal, J."
-    ],
-    "group": "herbadrop",
-    "groups": [
-        {
-            "name": "herbadrop"
-        }
-    ],
-    "name": "0d9e8478-3d92-5a5f-92cb-eb678e8e48dd",
-    "namespaces": [
-        ":"
-    ],
-    "notes": [
-        "Digitized_herbarium_sheet",
-        "unavailable"
-    ],
-    "oai_identifier": [
-        "0d9e8478-3d92-5a5f-92cb-eb678e8e48dd"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Gentianaceae"
-        }
-    ],
-    "title": [
-        "Gentiana \u00d7marcailhouana Rouy"
-    ],
-    "url": "http://coldb.mnhn.fr/catalognumber/mnhn/p/p03945291"
-}
\ No newline at end of file
diff --git a/oaitestdata/herbadrop-json/SET_1/json/0e0482d0-6856-5ca5-83b7-c784af4990fc.json b/oaitestdata/herbadrop-json/SET_1/json/0e0482d0-6856-5ca5-83b7-c784af4990fc.json
deleted file mode 100644
index a1cf9571..00000000
--- a/oaitestdata/herbadrop-json/SET_1/json/0e0482d0-6856-5ca5-83b7-c784af4990fc.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contributor": [
-        "CINES"
-    ],
-    "DiscHierarchy": [
-        "3.1.2",
-        "Live Sciences",
-        "Plant Sciences "
-    ],
-    "Discipline": "Plant_Sciences",
-    "Format": [
-        "image/jpeg"
-    ],
-    "MetaDataAccess": "https://opendata.cines.fr/herbadrop-api/rest/data/search/dataset/0e0482d0-6856-5ca5-83b7-c784af4990fc",
-    "MetaDataAcess": [
-        "P03056723"
-    ],
-    "OpenAccess": [
-        "true"
-    ],
-    "PublicationTimestamp": "2019-04-27T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "MNHN"
-    ],
-    "ResourceType": [
-        "StillImage|PRESERVED_SPECIMEN"
-    ],
-    "Rights": [
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "unavailable"
-    ],
-    "group": "herbadrop",
-    "groups": [
-        {
-            "name": "herbadrop"
-        }
-    ],
-    "name": "0e0482d0-6856-5ca5-83b7-c784af4990fc",
-    "namespaces": [
-        ":"
-    ],
-    "notes": [
-        "Digitized_herbarium_sheet",
-        "unavailable"
-    ],
-    "oai_identifier": [
-        "0e0482d0-6856-5ca5-83b7-c784af4990fc"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Fabaceae"
-        }
-    ],
-    "title": [
-        "Trifolium rubens L."
-    ],
-    "url": "http://coldb.mnhn.fr/catalognumber/mnhn/p/p03056723"
-}
\ No newline at end of file
diff --git a/oaitestdata/herbadrop-json/SET_1/json/0eabfdf6-190c-5a3d-a954-07abec2870bb.json b/oaitestdata/herbadrop-json/SET_1/json/0eabfdf6-190c-5a3d-a954-07abec2870bb.json
deleted file mode 100644
index 111a0da7..00000000
--- a/oaitestdata/herbadrop-json/SET_1/json/0eabfdf6-190c-5a3d-a954-07abec2870bb.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contributor": [
-        "CINES"
-    ],
-    "DiscHierarchy": [
-        "3.1.2",
-        "Live Sciences",
-        "Plant Sciences "
-    ],
-    "Discipline": "Plant_Sciences",
-    "Format": [
-        "image/jpeg"
-    ],
-    "MetaDataAccess": "https://opendata.cines.fr/herbadrop-api/rest/data/search/dataset/0eabfdf6-190c-5a3d-a954-07abec2870bb",
-    "MetaDataAcess": [
-        "P04093000"
-    ],
-    "OpenAccess": [
-        "true"
-    ],
-    "PublicationTimestamp": "2019-01-11T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "MNHN"
-    ],
-    "ResourceType": [
-        "StillImage|PRESERVED_SPECIMEN"
-    ],
-    "Rights": [
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "unavailable"
-    ],
-    "group": "herbadrop",
-    "groups": [
-        {
-            "name": "herbadrop"
-        }
-    ],
-    "name": "0eabfdf6-190c-5a3d-a954-07abec2870bb",
-    "namespaces": [
-        ":"
-    ],
-    "notes": [
-        "Digitized_herbarium_sheet",
-        "unavailable"
-    ],
-    "oai_identifier": [
-        "0eabfdf6-190c-5a3d-a954-07abec2870bb"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Asteraceae"
-        }
-    ],
-    "title": [
-        "Bellis sylvestris Cirillo"
-    ],
-    "url": "http://coldb.mnhn.fr/catalognumber/mnhn/p/p04093000"
-}
\ No newline at end of file
diff --git a/oaitestdata/herbadrop-json/SET_1/json/0f4ab1f3-06eb-5873-9f75-85547f041eb0.json b/oaitestdata/herbadrop-json/SET_1/json/0f4ab1f3-06eb-5873-9f75-85547f041eb0.json
deleted file mode 100644
index 3fb37b9c..00000000
--- a/oaitestdata/herbadrop-json/SET_1/json/0f4ab1f3-06eb-5873-9f75-85547f041eb0.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contributor": [
-        "CINES"
-    ],
-    "DiscHierarchy": [
-        "3.1.2",
-        "Live Sciences",
-        "Plant Sciences "
-    ],
-    "Discipline": "Plant_Sciences",
-    "Format": [
-        "image/jpeg"
-    ],
-    "MetaDataAccess": "https://opendata.cines.fr/herbadrop-api/rest/data/search/dataset/0f4ab1f3-06eb-5873-9f75-85547f041eb0",
-    "MetaDataAcess": [
-        "P05595212"
-    ],
-    "OpenAccess": [
-        "true"
-    ],
-    "PublicationTimestamp": "2019-03-12T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "MNHN"
-    ],
-    "ResourceType": [
-        "StillImage|PRESERVED_SPECIMEN"
-    ],
-    "Rights": [
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "unavailable"
-    ],
-    "group": "herbadrop",
-    "groups": [
-        {
-            "name": "herbadrop"
-        }
-    ],
-    "name": "0f4ab1f3-06eb-5873-9f75-85547f041eb0",
-    "namespaces": [
-        ":"
-    ],
-    "notes": [
-        "Digitized_herbarium_sheet",
-        "unavailable"
-    ],
-    "oai_identifier": [
-        "0f4ab1f3-06eb-5873-9f75-85547f041eb0"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Onagraceae"
-        }
-    ],
-    "title": [
-        "Clarkia viminea (Dougl.) A.Nels. & J.F.Macbr."
-    ],
-    "url": "http://coldb.mnhn.fr/catalognumber/mnhn/p/p05595212"
-}
\ No newline at end of file
diff --git a/oaitestdata/herbadrop-json/SET_1/json/1a9c30fd-255d-5cea-adbc-0223c8f8d567.json b/oaitestdata/herbadrop-json/SET_1/json/1a9c30fd-255d-5cea-adbc-0223c8f8d567.json
deleted file mode 100644
index 456c32ed..00000000
--- a/oaitestdata/herbadrop-json/SET_1/json/1a9c30fd-255d-5cea-adbc-0223c8f8d567.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "Contributor": [
-        "CINES"
-    ],
-    "DiscHierarchy": [
-        "3.1.2",
-        "Live Sciences",
-        "Plant Sciences "
-    ],
-    "Discipline": "Plant_Sciences",
-    "Format": [
-        "image/jpeg"
-    ],
-    "MetaDataAccess": "https://opendata.cines.fr/herbadrop-api/rest/data/search/dataset/1a9c30fd-255d-5cea-adbc-0223c8f8d567",
-    "MetaDataAcess": [
-        "P02190581"
-    ],
-    "OpenAccess": [
-        "true"
-    ],
-    "PublicationTimestamp": "2018-10-12T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "MNHN"
-    ],
-    "ResourceType": [
-        "StillImage|PRESERVED_SPECIMEN"
-    ],
-    "Rights": [
-        "cc-by"
-    ],
-    "TempCoverageBegin": 57543998399,
-    "TempCoverageEnd": 57543998399,
-    "TemporalCoverage": " period : ( 1824-07-01T11:59:59Z - 1824-07-01T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1824-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1824-07-01T11:59:59Z",
-    "author": [
-        "Gravier"
-    ],
-    "group": "herbadrop",
-    "groups": [
-        {
-            "name": "herbadrop"
-        }
-    ],
-    "name": "1a9c30fd-255d-5cea-adbc-0223c8f8d567",
-    "namespaces": [
-        ":"
-    ],
-    "notes": [
-        "Digitized_herbarium_sheet",
-        "unavailable"
-    ],
-    "oai_identifier": [
-        "1a9c30fd-255d-5cea-adbc-0223c8f8d567"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Asparagaceae"
-        }
-    ],
-    "title": [
-        "Anthericum ramosum L."
-    ],
-    "url": "http://coldb.mnhn.fr/catalognumber/mnhn/p/p02190581"
-}
\ No newline at end of file
diff --git a/oaitestdata/herbadrop-json/SET_1/json/1acf10a1-30eb-5cfa-a946-bb29554ed086.json b/oaitestdata/herbadrop-json/SET_1/json/1acf10a1-30eb-5cfa-a946-bb29554ed086.json
deleted file mode 100644
index ffd451c8..00000000
--- a/oaitestdata/herbadrop-json/SET_1/json/1acf10a1-30eb-5cfa-a946-bb29554ed086.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contributor": [
-        "CINES"
-    ],
-    "DiscHierarchy": [
-        "3.1.2",
-        "Live Sciences",
-        "Plant Sciences "
-    ],
-    "Discipline": "Plant_Sciences",
-    "Format": [
-        "image/jpeg"
-    ],
-    "MetaDataAccess": "https://opendata.cines.fr/herbadrop-api/rest/data/search/dataset/1acf10a1-30eb-5cfa-a946-bb29554ed086",
-    "MetaDataAcess": [
-        "P03623750"
-    ],
-    "OpenAccess": [
-        "true"
-    ],
-    "PublicationTimestamp": "2018-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "MNHN"
-    ],
-    "ResourceType": [
-        "StillImage|PRESERVED_SPECIMEN"
-    ],
-    "Rights": [
-        "cc-by"
-    ],
-    "author": [
-        "unavailable"
-    ],
-    "group": "herbadrop",
-    "groups": [
-        {
-            "name": "herbadrop"
-        }
-    ],
-    "name": "1acf10a1-30eb-5cfa-a946-bb29554ed086",
-    "namespaces": [
-        ":"
-    ],
-    "notes": [
-        "Digitized_herbarium_sheet",
-        "unavailable"
-    ],
-    "oai_identifier": [
-        "1acf10a1-30eb-5cfa-a946-bb29554ed086"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Fabaceae"
-        }
-    ],
-    "title": [
-        "Onobrychis supina DC."
-    ],
-    "url": "http://coldb.mnhn.fr/catalognumber/mnhn/p/p03623750"
-}
\ No newline at end of file
diff --git a/oaitestdata/herbadrop-json/SET_1/json/1b4e01c9-a1c7-5be6-8da6-f53b328b3cc1.json b/oaitestdata/herbadrop-json/SET_1/json/1b4e01c9-a1c7-5be6-8da6-f53b328b3cc1.json
deleted file mode 100644
index b735149c..00000000
--- a/oaitestdata/herbadrop-json/SET_1/json/1b4e01c9-a1c7-5be6-8da6-f53b328b3cc1.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contributor": [
-        "CINES"
-    ],
-    "DiscHierarchy": [
-        "3.1.2",
-        "Live Sciences",
-        "Plant Sciences "
-    ],
-    "Discipline": "Plant_Sciences",
-    "Format": [
-        "image/jpeg"
-    ],
-    "MetaDataAccess": "https://opendata.cines.fr/herbadrop-api/rest/data/search/dataset/1b4e01c9-a1c7-5be6-8da6-f53b328b3cc1",
-    "MetaDataAcess": [
-        "P03612066"
-    ],
-    "OpenAccess": [
-        "true"
-    ],
-    "PublicationTimestamp": "2018-12-08T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "MNHN"
-    ],
-    "ResourceType": [
-        "StillImage|PRESERVED_SPECIMEN"
-    ],
-    "Rights": [
-        "cc-by"
-    ],
-    "author": [
-        "unavailable"
-    ],
-    "group": "herbadrop",
-    "groups": [
-        {
-            "name": "herbadrop"
-        }
-    ],
-    "name": "1b4e01c9-a1c7-5be6-8da6-f53b328b3cc1",
-    "namespaces": [
-        ":"
-    ],
-    "notes": [
-        "Digitized_herbarium_sheet",
-        "unavailable"
-    ],
-    "oai_identifier": [
-        "1b4e01c9-a1c7-5be6-8da6-f53b328b3cc1"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Fabaceae"
-        }
-    ],
-    "title": [
-        "Vicia peregrina L."
-    ],
-    "url": "http://coldb.mnhn.fr/catalognumber/mnhn/p/p03612066"
-}
\ No newline at end of file
diff --git a/oaitestdata/herbadrop-json/SET_1/json/1ba111a9-57d4-5f56-b276-34248a0c709a.json b/oaitestdata/herbadrop-json/SET_1/json/1ba111a9-57d4-5f56-b276-34248a0c709a.json
deleted file mode 100644
index 9cfb0b22..00000000
--- a/oaitestdata/herbadrop-json/SET_1/json/1ba111a9-57d4-5f56-b276-34248a0c709a.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contributor": [
-        "CINES"
-    ],
-    "DiscHierarchy": [
-        "3.1.2",
-        "Live Sciences",
-        "Plant Sciences "
-    ],
-    "Discipline": "Plant_Sciences",
-    "Format": [
-        "image/jpeg"
-    ],
-    "MetaDataAccess": "https://opendata.cines.fr/herbadrop-api/rest/data/search/dataset/1ba111a9-57d4-5f56-b276-34248a0c709a",
-    "MetaDataAcess": [
-        "P06804503"
-    ],
-    "OpenAccess": [
-        "true"
-    ],
-    "PublicationTimestamp": "2019-03-13T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "MNHN"
-    ],
-    "ResourceType": [
-        "StillImage|PRESERVED_SPECIMEN"
-    ],
-    "Rights": [
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "unavailable"
-    ],
-    "group": "herbadrop",
-    "groups": [
-        {
-            "name": "herbadrop"
-        }
-    ],
-    "name": "1ba111a9-57d4-5f56-b276-34248a0c709a",
-    "namespaces": [
-        ":"
-    ],
-    "notes": [
-        "Digitized_herbarium_sheet",
-        "unavailable"
-    ],
-    "oai_identifier": [
-        "1ba111a9-57d4-5f56-b276-34248a0c709a"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Poaceae"
-        }
-    ],
-    "title": [
-        "Muhlenbergia mexicana Trin."
-    ],
-    "url": "http://coldb.mnhn.fr/catalognumber/mnhn/p/p06804503"
-}
\ No newline at end of file
diff --git a/oaitestdata/herbadrop-json/SET_1/json/1c647c2c-5e41-53fc-9af7-5ff7bc609479.json b/oaitestdata/herbadrop-json/SET_1/json/1c647c2c-5e41-53fc-9af7-5ff7bc609479.json
deleted file mode 100644
index 1543016f..00000000
--- a/oaitestdata/herbadrop-json/SET_1/json/1c647c2c-5e41-53fc-9af7-5ff7bc609479.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contributor": [
-        "CINES"
-    ],
-    "DiscHierarchy": [
-        "3.1.2",
-        "Live Sciences",
-        "Plant Sciences "
-    ],
-    "Discipline": "Plant_Sciences",
-    "Format": [
-        "image/jpeg"
-    ],
-    "MetaDataAccess": "https://opendata.cines.fr/herbadrop-api/rest/data/search/dataset/1c647c2c-5e41-53fc-9af7-5ff7bc609479",
-    "MetaDataAcess": [
-        "P05470382"
-    ],
-    "OpenAccess": [
-        "true"
-    ],
-    "PublicationTimestamp": "2019-03-06T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "MNHN"
-    ],
-    "ResourceType": [
-        "StillImage|PRESERVED_SPECIMEN"
-    ],
-    "Rights": [
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "unavailable"
-    ],
-    "group": "herbadrop",
-    "groups": [
-        {
-            "name": "herbadrop"
-        }
-    ],
-    "name": "1c647c2c-5e41-53fc-9af7-5ff7bc609479",
-    "namespaces": [
-        ":"
-    ],
-    "notes": [
-        "Digitized_herbarium_sheet",
-        "unavailable"
-    ],
-    "oai_identifier": [
-        "1c647c2c-5e41-53fc-9af7-5ff7bc609479"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Salicaceae"
-        }
-    ],
-    "title": [
-        "Salix cinerea L."
-    ],
-    "url": "http://coldb.mnhn.fr/catalognumber/mnhn/p/p05470382"
-}
\ No newline at end of file
diff --git a/oaitestdata/herbadrop-json/SET_1/json/1c8c4f5d-09b9-56cd-9cf3-f1e3058f973d.json b/oaitestdata/herbadrop-json/SET_1/json/1c8c4f5d-09b9-56cd-9cf3-f1e3058f973d.json
deleted file mode 100644
index 95085f06..00000000
--- a/oaitestdata/herbadrop-json/SET_1/json/1c8c4f5d-09b9-56cd-9cf3-f1e3058f973d.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contributor": [
-        "CINES"
-    ],
-    "DiscHierarchy": [
-        "3.1.2",
-        "Live Sciences",
-        "Plant Sciences "
-    ],
-    "Discipline": "Plant_Sciences",
-    "Format": [
-        "image/jpeg"
-    ],
-    "MetaDataAccess": "https://opendata.cines.fr/herbadrop-api/rest/data/search/dataset/1c8c4f5d-09b9-56cd-9cf3-f1e3058f973d",
-    "MetaDataAcess": [
-        "P03094617"
-    ],
-    "OpenAccess": [
-        "true"
-    ],
-    "PublicationTimestamp": "2019-04-12T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "MNHN"
-    ],
-    "ResourceType": [
-        "StillImage|PRESERVED_SPECIMEN"
-    ],
-    "Rights": [
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "unavailable"
-    ],
-    "group": "herbadrop",
-    "groups": [
-        {
-            "name": "herbadrop"
-        }
-    ],
-    "name": "1c8c4f5d-09b9-56cd-9cf3-f1e3058f973d",
-    "namespaces": [
-        ":"
-    ],
-    "notes": [
-        "Digitized_herbarium_sheet",
-        "unavailable"
-    ],
-    "oai_identifier": [
-        "1c8c4f5d-09b9-56cd-9cf3-f1e3058f973d"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Fabaceae"
-        }
-    ],
-    "title": [
-        "Argyrolobium candicans Eckl. & Zeyh."
-    ],
-    "url": "http://coldb.mnhn.fr/catalognumber/mnhn/p/p03094617"
-}
\ No newline at end of file
diff --git a/oaitestdata/herbadrop-json/SET_1/json/1ca14c88-e670-5c86-8ec5-7616cb82829b.json b/oaitestdata/herbadrop-json/SET_1/json/1ca14c88-e670-5c86-8ec5-7616cb82829b.json
deleted file mode 100644
index 4788d1c2..00000000
--- a/oaitestdata/herbadrop-json/SET_1/json/1ca14c88-e670-5c86-8ec5-7616cb82829b.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contributor": [
-        "CINES"
-    ],
-    "DiscHierarchy": [
-        "3.1.2",
-        "Live Sciences",
-        "Plant Sciences "
-    ],
-    "Discipline": "Plant_Sciences",
-    "Format": [
-        "image/jpeg"
-    ],
-    "MetaDataAccess": "https://opendata.cines.fr/herbadrop-api/rest/data/search/dataset/1ca14c88-e670-5c86-8ec5-7616cb82829b",
-    "MetaDataAcess": [
-        "P05545912"
-    ],
-    "OpenAccess": [
-        "true"
-    ],
-    "PublicationTimestamp": "2019-03-06T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "MNHN"
-    ],
-    "ResourceType": [
-        "StillImage|PRESERVED_SPECIMEN"
-    ],
-    "Rights": [
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "unavailable"
-    ],
-    "group": "herbadrop",
-    "groups": [
-        {
-            "name": "herbadrop"
-        }
-    ],
-    "name": "1ca14c88-e670-5c86-8ec5-7616cb82829b",
-    "namespaces": [
-        ":"
-    ],
-    "notes": [
-        "Digitized_herbarium_sheet",
-        "unavailable"
-    ],
-    "oai_identifier": [
-        "1ca14c88-e670-5c86-8ec5-7616cb82829b"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "unavailable"
-        }
-    ],
-    "title": [
-        "incertae sedis"
-    ],
-    "url": "http://coldb.mnhn.fr/catalognumber/mnhn/p/p05545912"
-}
\ No newline at end of file
diff --git a/oaitestdata/herbadrop-json/SET_1/json/1d55a277-8348-5ad9-96a7-ad1f9f0060f9.json b/oaitestdata/herbadrop-json/SET_1/json/1d55a277-8348-5ad9-96a7-ad1f9f0060f9.json
deleted file mode 100644
index fb13ab35..00000000
--- a/oaitestdata/herbadrop-json/SET_1/json/1d55a277-8348-5ad9-96a7-ad1f9f0060f9.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contributor": [
-        "CINES"
-    ],
-    "DiscHierarchy": [
-        "3.1.2",
-        "Live Sciences",
-        "Plant Sciences "
-    ],
-    "Discipline": "Plant_Sciences",
-    "Format": [
-        "image/jpeg"
-    ],
-    "MetaDataAccess": "https://opendata.cines.fr/herbadrop-api/rest/data/search/dataset/1d55a277-8348-5ad9-96a7-ad1f9f0060f9",
-    "MetaDataAcess": [
-        "P03441751"
-    ],
-    "OpenAccess": [
-        "true"
-    ],
-    "PublicationTimestamp": "2019-06-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "MNHN"
-    ],
-    "ResourceType": [
-        "StillImage|PRESERVED_SPECIMEN"
-    ],
-    "Rights": [
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "unavailable"
-    ],
-    "group": "herbadrop",
-    "groups": [
-        {
-            "name": "herbadrop"
-        }
-    ],
-    "name": "1d55a277-8348-5ad9-96a7-ad1f9f0060f9",
-    "namespaces": [
-        ":"
-    ],
-    "notes": [
-        "Digitized_herbarium_sheet",
-        "unavailable"
-    ],
-    "oai_identifier": [
-        "1d55a277-8348-5ad9-96a7-ad1f9f0060f9"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Asteraceae"
-        }
-    ],
-    "title": [
-        "Senecio Herbarium Practice & Following Welman."
-    ],
-    "url": "http://coldb.mnhn.fr/catalognumber/mnhn/p/p03441751"
-}
\ No newline at end of file
diff --git a/oaitestdata/herbadrop-json/SET_1/json/1d68744f-ffee-59f7-af53-b3c4e6e3eee7.json b/oaitestdata/herbadrop-json/SET_1/json/1d68744f-ffee-59f7-af53-b3c4e6e3eee7.json
deleted file mode 100644
index e6c1d0c0..00000000
--- a/oaitestdata/herbadrop-json/SET_1/json/1d68744f-ffee-59f7-af53-b3c4e6e3eee7.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contributor": [
-        "CINES"
-    ],
-    "DiscHierarchy": [
-        "3.1.2",
-        "Live Sciences",
-        "Plant Sciences "
-    ],
-    "Discipline": "Plant_Sciences",
-    "Format": [
-        "image/jpeg"
-    ],
-    "MetaDataAccess": "https://opendata.cines.fr/herbadrop-api/rest/data/search/dataset/1d68744f-ffee-59f7-af53-b3c4e6e3eee7",
-    "MetaDataAcess": [
-        "P03053691"
-    ],
-    "OpenAccess": [
-        "true"
-    ],
-    "PublicationTimestamp": "2019-04-27T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "MNHN"
-    ],
-    "ResourceType": [
-        "StillImage|PRESERVED_SPECIMEN"
-    ],
-    "Rights": [
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "unavailable"
-    ],
-    "group": "herbadrop",
-    "groups": [
-        {
-            "name": "herbadrop"
-        }
-    ],
-    "name": "1d68744f-ffee-59f7-af53-b3c4e6e3eee7",
-    "namespaces": [
-        ":"
-    ],
-    "notes": [
-        "Digitized_herbarium_sheet",
-        "unavailable"
-    ],
-    "oai_identifier": [
-        "1d68744f-ffee-59f7-af53-b3c4e6e3eee7"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Fabaceae"
-        }
-    ],
-    "title": [
-        "Oxytropis pilosa DC."
-    ],
-    "url": "http://coldb.mnhn.fr/catalognumber/mnhn/p/p03053691"
-}
\ No newline at end of file
diff --git a/oaitestdata/herbadrop-json/SET_1/json/1dd2ae95-7b32-5d69-b75d-305a76f98226.json b/oaitestdata/herbadrop-json/SET_1/json/1dd2ae95-7b32-5d69-b75d-305a76f98226.json
deleted file mode 100644
index b0cb5397..00000000
--- a/oaitestdata/herbadrop-json/SET_1/json/1dd2ae95-7b32-5d69-b75d-305a76f98226.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contributor": [
-        "CINES"
-    ],
-    "DiscHierarchy": [
-        "3.1.2",
-        "Live Sciences",
-        "Plant Sciences "
-    ],
-    "Discipline": "Plant_Sciences",
-    "Format": [
-        "image/jpeg"
-    ],
-    "MetaDataAccess": "https://opendata.cines.fr/herbadrop-api/rest/data/search/dataset/1dd2ae95-7b32-5d69-b75d-305a76f98226",
-    "MetaDataAcess": [
-        "P05513957"
-    ],
-    "OpenAccess": [
-        "true"
-    ],
-    "PublicationTimestamp": "2019-03-06T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "MNHN"
-    ],
-    "ResourceType": [
-        "StillImage|PRESERVED_SPECIMEN"
-    ],
-    "Rights": [
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "unavailable"
-    ],
-    "group": "herbadrop",
-    "groups": [
-        {
-            "name": "herbadrop"
-        }
-    ],
-    "name": "1dd2ae95-7b32-5d69-b75d-305a76f98226",
-    "namespaces": [
-        ":"
-    ],
-    "notes": [
-        "Digitized_herbarium_sheet",
-        "unavailable"
-    ],
-    "oai_identifier": [
-        "1dd2ae95-7b32-5d69-b75d-305a76f98226"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Euphorbiaceae"
-        }
-    ],
-    "title": [
-        "Euphorbia ruscinonensis Boiss."
-    ],
-    "url": "http://coldb.mnhn.fr/catalognumber/mnhn/p/p05513957"
-}
\ No newline at end of file
diff --git a/oaitestdata/herbadrop-json/SET_1/json/1dd7b141-e18e-5880-a967-2aad6f59a95b.json b/oaitestdata/herbadrop-json/SET_1/json/1dd7b141-e18e-5880-a967-2aad6f59a95b.json
deleted file mode 100644
index 29ef37c0..00000000
--- a/oaitestdata/herbadrop-json/SET_1/json/1dd7b141-e18e-5880-a967-2aad6f59a95b.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contributor": [
-        "CINES"
-    ],
-    "DiscHierarchy": [
-        "3.1.2",
-        "Live Sciences",
-        "Plant Sciences "
-    ],
-    "Discipline": "Plant_Sciences",
-    "Format": [
-        "unavailable"
-    ],
-    "MetaDataAccess": "https://opendata.cines.fr/herbadrop-api/rest/data/search/dataset/1dd7b141-e18e-5880-a967-2aad6f59a95b",
-    "MetaDataAcess": [
-        "P04113361"
-    ],
-    "OpenAccess": [
-        "true"
-    ],
-    "PublicationTimestamp": "2019-01-24T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "MNHN"
-    ],
-    "ResourceType": [
-        "PRESERVED_SPECIMEN"
-    ],
-    "Rights": [
-        "unavailable"
-    ],
-    "author": [
-        "unavailable"
-    ],
-    "group": "herbadrop",
-    "groups": [
-        {
-            "name": "herbadrop"
-        }
-    ],
-    "name": "1dd7b141-e18e-5880-a967-2aad6f59a95b",
-    "namespaces": [
-        ":"
-    ],
-    "notes": [
-        "Digitized_herbarium_sheet",
-        "unavailable"
-    ],
-    "oai_identifier": [
-        "1dd7b141-e18e-5880-a967-2aad6f59a95b"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Asteraceae"
-        }
-    ],
-    "title": [
-        "Senecio Herbarium Practice & Following Welman."
-    ],
-    "url": "http://coldb.mnhn.fr/catalognumber/mnhn/p/p04113361"
-}
\ No newline at end of file
diff --git a/oaitestdata/herbadrop-json/SET_1/json/1ea2c5a9-632c-573e-bbf1-79c60b4e7621.json b/oaitestdata/herbadrop-json/SET_1/json/1ea2c5a9-632c-573e-bbf1-79c60b4e7621.json
deleted file mode 100644
index 275f4f18..00000000
--- a/oaitestdata/herbadrop-json/SET_1/json/1ea2c5a9-632c-573e-bbf1-79c60b4e7621.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contributor": [
-        "CINES"
-    ],
-    "DiscHierarchy": [
-        "3.1.2",
-        "Live Sciences",
-        "Plant Sciences "
-    ],
-    "Discipline": "Plant_Sciences",
-    "Format": [
-        "image/jpeg"
-    ],
-    "MetaDataAccess": "https://opendata.cines.fr/herbadrop-api/rest/data/search/dataset/1ea2c5a9-632c-573e-bbf1-79c60b4e7621",
-    "MetaDataAcess": [
-        "P04328277"
-    ],
-    "OpenAccess": [
-        "true"
-    ],
-    "PublicationTimestamp": "2019-01-30T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "MNHN"
-    ],
-    "ResourceType": [
-        "StillImage|PRESERVED_SPECIMEN"
-    ],
-    "Rights": [
-        "http://creativecommons.org/licenses/by/4.0/"
-    ],
-    "author": [
-        "unavailable"
-    ],
-    "group": "herbadrop",
-    "groups": [
-        {
-            "name": "herbadrop"
-        }
-    ],
-    "name": "1ea2c5a9-632c-573e-bbf1-79c60b4e7621",
-    "namespaces": [
-        ":"
-    ],
-    "notes": [
-        "Digitized_herbarium_sheet",
-        "unavailable"
-    ],
-    "oai_identifier": [
-        "1ea2c5a9-632c-573e-bbf1-79c60b4e7621"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Apiaceae"
-        }
-    ],
-    "title": [
-        "Apium graveolens L."
-    ],
-    "url": "http://coldb.mnhn.fr/catalognumber/mnhn/p/p04328277"
-}
\ No newline at end of file
diff --git a/oaitestdata/herbadrop-json/SET_1/json/1eb0978d-4221-58b6-af65-0b5853050056.json b/oaitestdata/herbadrop-json/SET_1/json/1eb0978d-4221-58b6-af65-0b5853050056.json
deleted file mode 100644
index e20d1032..00000000
--- a/oaitestdata/herbadrop-json/SET_1/json/1eb0978d-4221-58b6-af65-0b5853050056.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contributor": [
-        "CINES"
-    ],
-    "DiscHierarchy": [
-        "3.1.2",
-        "Live Sciences",
-        "Plant Sciences "
-    ],
-    "Discipline": "Plant_Sciences",
-    "Format": [
-        "image/jpeg"
-    ],
-    "MetaDataAccess": "https://opendata.cines.fr/herbadrop-api/rest/data/search/dataset/1eb0978d-4221-58b6-af65-0b5853050056",
-    "MetaDataAcess": [
-        "P02473412"
-    ],
-    "OpenAccess": [
-        "true"
-    ],
-    "PublicationTimestamp": "2018-11-05T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "MNHN"
-    ],
-    "ResourceType": [
-        "StillImage|PRESERVED_SPECIMEN"
-    ],
-    "Rights": [
-        "cc-by"
-    ],
-    "author": [
-        "unavailable"
-    ],
-    "group": "herbadrop",
-    "groups": [
-        {
-            "name": "herbadrop"
-        }
-    ],
-    "name": "1eb0978d-4221-58b6-af65-0b5853050056",
-    "namespaces": [
-        ":"
-    ],
-    "notes": [
-        "Digitized_herbarium_sheet",
-        "unavailable"
-    ],
-    "oai_identifier": [
-        "1eb0978d-4221-58b6-af65-0b5853050056"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Asteraceae"
-        }
-    ],
-    "title": [
-        "Senecio Herbarium Practice & Following Welman."
-    ],
-    "url": "http://coldb.mnhn.fr/catalognumber/mnhn/p/p02473412"
-}
\ No newline at end of file
diff --git a/oaitestdata/iagos-iso19139/SET_1/json/15ff6b9d-93ab-5ead-89b0-13d4b10a6190.json b/oaitestdata/iagos-iso19139/SET_1/json/15ff6b9d-93ab-5ead-89b0-13d4b10a6190.json
deleted file mode 100644
index adec267c..00000000
--- a/oaitestdata/iagos-iso19139/SET_1/json/15ff6b9d-93ab-5ead-89b0-13d4b10a6190.json
+++ /dev/null
@@ -1,98 +0,0 @@
-{
-    "Contact": [
-        "contact@aeris-data.fr"
-    ],
-    "Contributor": [
-        "IAGOS"
-    ],
-    "DOI": "http://dx.doi.org/10.25326/07",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "http://catalogue2.sedoo.fr/geonetwork/srv/eng/csw-iagos?verb=GetRecord&metadataPrefix=iso19139&identifier=15ff6b9d-93ab-5ead-89b0-13d4b10a6190",
-    "PublicationTimestamp": "1994-08-01T11:59:59Z",
-    "PublicationYear": [
-        "1994"
-    ],
-    "Publisher": [
-        "AERIS"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "http://iagos-data.fr/#CMSConsultPlace:DATA_POLICY"
-    ],
-    "SpatialCoverage": "(90S-90N,180W-180E)",
-    "TempCoverageBegin": 62911335599,
-    "TempCoverageEnd": 62911335599,
-    "TemporalCoverage": " point in time : 1994-08-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-08-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-08-01T11:59:59Z",
-    "fulltext": "61e54760-86ba-4b69-804b-06a7793f9104;English;Dataset;AERIS;France;contact@aeris-data.fr;Publisher;2018-09-06T18:17:35.974+02:00;EPSG:4326;IAGOS vertical profiles;1994-08-01;Creation;2018-09-06T18:17:35.975+02:00;Publication;10.25326/07;This dataset provides all vertical profiles over the airports visited by the IAGOS fleet. The profiles match the take-off and landing phases of the flights. The dataset includes values of all species measured by IAGOS instrumentation with a time acquisition resolution of 4 seconds as well as meteorological fields provided by the aircraft or the ECMWF.;SEDOO;14 avenue Edouard Belin;Toulouse;31400;France;aeris@sedoo.fr;Distributor;Ulrich Bundke;Forschungszentrum Julich;u.bundke@fz-juelich.de;Aerosols;Principal investigator;Herman Smit;Forschungszentrum Julich;h.smit@fz-juelich.de;Water vapor;Principal investigator;Bastien Sauvage;Laboratoire d'Aerologie;bastien.sauvage@aero.obs-mip.fr;Ancillary data;Principal investigator;Christoph Gerbig;Max-Planck-Institute for Biogeochemistry Jena;cgerbig@bgc-jena.mpg.de;Greenhouse gases (CH4, CO2);Principal investigator;Markus Hermann;Leibniz Institute for Tropospheric Research;hermann@tropos.de;Aerosols;Principal investigator;Florian Berkes;Forschungszentrum Julich;f.berkes@fz-juelich.de;NOx, NOy;Principal investigator;Philippe Nedelec;Laboratoire d'Aerologie;nedp@aero.obs-mip.fr;Ozone, Carbon monoxyde;Principal investigator;Martin Gallagher;University of Manchester;martin.gallagher@manchester.ac.uk;Clouds particules;Principal investigator;Helmut Ziereis;DLR;helmut.ziereis@dlr.de;NOx, NOy;Principal investigator;Damien Boulanger;Observatoire Midi-Pyrenees;damien.boulanger@obs-mip.fr;Database manager;Originator;Valerie Thouret;Laboratoire d'Aerologie;thov@aero.obs-mip.fr;Coordinator IAGOS-France;Point of contact;Andreas Petzold;Forschungszentrum Julich;a.petzold@fz-juelich.de;Coordinator IAGOS-Germany;Point of contact;http://iagos-data.fr/images/logo_blue.png;Logo;http://iagos-data.fr/portal/rest/images/map:global:thumb;Map of flights;Atmospheric chemistry > Nitrogen compounds > Nitrogen oxides;Atmospheric chemistry > Oxygen compounds > Ozone;Atmospheric winds;Atmospheric temperature;Atmospheric chemistry > Carbon and hydrocarbon compounds > Carbon dioxide;Atmospheric winds > Wind dynamics > Vorticity > Potential vorticity;Altitude > Planetary boundary layer height;Atmospheric temperature;Atmospheric chemistry > Nitrogen compounds > Nitrogen oxides;Atmospheric winds;Altitude > Barometric altitude;Atmospheric winds;Atmospheric temperature;Atmospheric chemistry > Nitrogen compounds > Nitrogen oxides;Atmospheric water vapor > Water vapor indicators > Humidity > Relative humidity;Atmospheric chemistry > Nitrogen compounds > Nitrogen oxides;Altitude > Geopotential height;Atmospheric winds > Wind dynamics > Vorticity > Potential vorticity;Atmospheric pressure > Static pressure;Platform characteristics > Airspeed/ground speed;Altitude > Planetary boundary layer height;Atmospheric water vapor > Water vapor indicators > Water vapor;Atmospheric temperature > Surface temperature > Potential temperature;Atmospheric chemistry > Carbon and hydrocarbon compounds > Carbon monoxide;Atmospheric chemistry > Carbon and hydrocarbon compounds > Methane;Atmospheric winds;Atmospheric winds > Wind dynamics > Vertical wind velocity/speed;Atmospheric pressure > Surface pressure;Atmospheric temperature;Platform characteristics > Airspeed/ground speed;AERIS parameters - GCMD;2018-09-06T18:17:35.975+02:00;Creation;Atmospheric conditions;Theme;GEMET - INSPIRE themes, version 1.0;2008-06-01;Publication;IAGOS;SEDOO;AERIS;http://iagos-data.fr/#CMSConsultPlace:DATA_POLICY;Restricted;NA;English;climatologyMeteorologyAtmosphere;true;-180.0;180.0;-90.0;90.0;1994-08-01;2100-12-31;Nasa Ames;1001;NetCDF;3;http://www.iagos.org;WWW:LINK-1.0-http--link;IAGOS central website;http://iagos-data.fr/#TimeseriesPlace:;WWW:DOWNLOAD-1.0-http--download;IAGOS Data Portal;http://dx.doi.org/10.25326/07;WWW:LINK-1.0-http--link;DOI of the dataset;Dataset;Commission Regulation (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;Publication;NA;true;Data produced by the European Research Infrastructure IAGOS.;Aircraft;Backscatter Cloud Probe;GHG - IAGOS-P2d;CO - IAGOS-P1;O3 - IAGOS-P1;H2O - IAGOS-P1;CPC - IAGOS-P1;OPC - IAGOS-P1;NOy/NOx - IAGOS-P2",
-    "group": "iagos",
-    "groups": [
-        {
-            "name": "iagos"
-        }
-    ],
-    "name": "15ff6b9d-93ab-5ead-89b0-13d4b10a6190",
-    "notes": [
-        "This dataset provides all vertical profiles over the airports visited by the IAGOS fleet. The profiles match the take-off and landing phases of the flights. The dataset includes values of all species measured by IAGOS instrumentation with a time acquisition resolution of 4 seconds as well as meteorological fields provided by the aircraft or the ECMWF."
-    ],
-    "oai_identifier": [
-        "15ff6b9d-93ab-5ead-89b0-13d4b10a6190"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-180.0,-90.0],[-180.0,90.0],[180.0,90.0],[180.0,-90.0],[-180.0,-90.0]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Atmospheric chemistry Nitrogen compounds Nitrogen oxides"
-        },
-        {
-            "name": "Atmospheric chemistry Oxygen compounds Ozone"
-        },
-        {
-            "name": "Atmospheric winds"
-        },
-        {
-            "name": "Atmospheric temperature"
-        },
-        {
-            "name": "Altitude Planetary boundary layer height"
-        },
-        {
-            "name": "Atmospheric temperature"
-        },
-        {
-            "name": "Atmospheric chemistry Nitrogen compounds Nitrogen oxides"
-        },
-        {
-            "name": "Atmospheric winds"
-        },
-        {
-            "name": "Altitude Barometric altitude"
-        },
-        {
-            "name": "Atmospheric winds"
-        },
-        {
-            "name": "Atmospheric temperature"
-        },
-        {
-            "name": "Atmospheric chemistry Nitrogen compounds Nitrogen oxides"
-        }
-    ],
-    "title": [
-        "IAGOS vertical profiles"
-    ],
-    "url": "http://iagos-data.fr/#TimeseriesPlace:"
-}
\ No newline at end of file
diff --git a/oaitestdata/iagos-iso19139/SET_1/json/22c3ef58-9355-5825-8950-765b050e7018.json b/oaitestdata/iagos-iso19139/SET_1/json/22c3ef58-9355-5825-8950-765b050e7018.json
deleted file mode 100644
index 3c3b7a81..00000000
--- a/oaitestdata/iagos-iso19139/SET_1/json/22c3ef58-9355-5825-8950-765b050e7018.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "contact@aeris-data.fr"
-    ],
-    "Contributor": [
-        "IAGOS"
-    ],
-    "DOI": "http://dx.doi.org/10.25326/08",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "http://catalogue2.sedoo.fr/geonetwork/srv/eng/csw-iagos?verb=GetRecord&metadataPrefix=iso19139&identifier=22c3ef58-9355-5825-8950-765b050e7018",
-    "PublicationTimestamp": "1994-08-01T11:59:59Z",
-    "PublicationYear": [
-        "1994"
-    ],
-    "Publisher": [
-        "AERIS"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "http://iagos-data.fr/#CMSConsultPlace:DATA_POLICY"
-    ],
-    "SpatialCoverage": "(44S-83N,180W-180E)",
-    "TempCoverageBegin": 62911335599,
-    "TempCoverageEnd": 63113947199,
-    "TemporalCoverage": " period : ( 1994-08-01T11:59:59Z - 2001-01-01T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1994-08-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2001-01-01T11:59:59Z",
-    "fulltext": "95941ca3-7251-4bed-877a-d2a99fb719cc;English;Dataset;AERIS;France;contact@aeris-data.fr;Publisher;2018-09-06T18:17:37.253+02:00;EPSG:4326;IAGOS Climatologies;1994-08-01;Creation;2018-09-06T18:17:37.254+02:00;Publication;10.25326/08;This dataset provides climatologies for ozone and carbon monoxyde over a decade (2001-2010). Two types of climatologies are available: with 10 fixed pressure levels (from 288 hPa to 186 hPa) or with 4 dynamic pressure levels (lower stratosphere, upper statisphere, tropopause, upper troposphere).;SEDOO;14 avenue Edouard Belin;Toulouse;31400;France;aeris@sedoo.fr;Distributor;Philippe Nedelec;Laboratoire d'Aerologie;nedp@aero.obs-mip.fr;Ozone, Carbon monoxyde;Principal investigator;Damien Boulanger;Observatoire Midi-Pyrenees;damien.boulanger@obs-mip.fr;Database manager;Originator;http://iagos-data.fr/images/logo_blue.png;Logo;http://iagos-data.fr/portal/rest/images/map:global:thumb;Map of flights;Atmospheric chemistry > Oxygen compounds > Ozone;Atmospheric chemistry > Carbon and hydrocarbon compounds > Carbon monoxide;AERIS parameters - GCMD;2018-09-06T18:17:37.254+02:00;Creation;Atmospheric conditions;Theme;GEMET - INSPIRE themes, version 1.0;2008-06-01;Publication;IAGOS;SEDOO;AERIS;http://iagos-data.fr/#CMSConsultPlace:DATA_POLICY;Restricted;NA;English;climatologyMeteorologyAtmosphere;true;-180.0;180.0;-44.0;83.0;1994-08-01;2100-12-31;2001-01-01;2010-12-31;NetCDF;3;http://www.iagos.org;WWW:LINK-1.0-http--link;IAGOS central website;http://www.iagos-data.fr;WWW:LINK-1.0-http--link;IAGOS Data Portal;http://dx.doi.org/10.25326/08;WWW:LINK-1.0-http--link;DOI of the dataset;Dataset;Commission Regulation (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;Publication;NA;true;Data produced by the European Research Infrastructure IAGOS.",
-    "group": "iagos",
-    "groups": [
-        {
-            "name": "iagos"
-        }
-    ],
-    "name": "22c3ef58-9355-5825-8950-765b050e7018",
-    "notes": [
-        "This dataset provides climatologies for ozone and carbon monoxyde over a decade (2001-2010). Two types of climatologies are available: with 10 fixed pressure levels (from 288 hPa to 186 hPa) or with 4 dynamic pressure levels (lower stratosphere, upper statisphere, tropopause, upper troposphere)."
-    ],
-    "oai_identifier": [
-        "22c3ef58-9355-5825-8950-765b050e7018"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-180.0,-44.0],[-180.0,83.0],[180.0,83.0],[180.0,-44.0],[-180.0,-44.0]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Atmospheric chemistry Oxygen compounds Ozone"
-        },
-        {
-            "name": "IAGOS"
-        },
-        {
-            "name": "SEDOO"
-        },
-        {
-            "name": "AERIS"
-        }
-    ],
-    "title": [
-        "IAGOS Climatologies"
-    ],
-    "url": "http://www.iagos-data.fr"
-}
\ No newline at end of file
diff --git a/oaitestdata/iagos-iso19139/SET_1/json/4b383073-20a8-5b74-8dfd-0af5a57415f4.json b/oaitestdata/iagos-iso19139/SET_1/json/4b383073-20a8-5b74-8dfd-0af5a57415f4.json
deleted file mode 100644
index 9fb87e00..00000000
--- a/oaitestdata/iagos-iso19139/SET_1/json/4b383073-20a8-5b74-8dfd-0af5a57415f4.json
+++ /dev/null
@@ -1,98 +0,0 @@
-{
-    "Contact": [
-        "contact@aeris-data.fr"
-    ],
-    "Contributor": [
-        "IAGOS"
-    ],
-    "DOI": "http://dx.doi.org/10.25326/06",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "http://catalogue2.sedoo.fr/geonetwork/srv/eng/csw-iagos?verb=GetRecord&metadataPrefix=iso19139&identifier=4b383073-20a8-5b74-8dfd-0af5a57415f4",
-    "PublicationTimestamp": "1994-08-01T11:59:59Z",
-    "PublicationYear": [
-        "1994"
-    ],
-    "Publisher": [
-        "AERIS"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "http://iagos-data.fr/#CMSConsultPlace:DATA_POLICY"
-    ],
-    "SpatialCoverage": "(44S-83N,180W-180E)",
-    "TempCoverageBegin": 62911335599,
-    "TempCoverageEnd": 62911335599,
-    "TemporalCoverage": " point in time : 1994-08-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-08-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-08-01T11:59:59Z",
-    "fulltext": "575882c0-64ce-4648-bb19-00030d5d63af;English;Dataset;AERIS;France;contact@aeris-data.fr;Publisher;2018-09-06T18:17:33.758+02:00;EPSG:4326;IAGOS Time series;1994-08-01;Creation;2018-09-06T18:17:33.866+02:00;Publication;10.25326/06;This dataset provides all time series, each one matching a IAGOS flight. The dataset includes values of all species measured by IAGOS instrumentation with a time acquisition resolution of 4 seconds as well as meteorological fields provided by the aircraft or the ECMWF.;SEDOO;14 avenue Edouard Belin;Toulouse;31400;France;aeris@sedoo.fr;Distributor;Ulrich Bundke;Forschungszentrum Julich;u.bundke@fz-juelich.de;Aerosols;Principal investigator;Herman Smit;Forschungszentrum Julich;h.smit@fz-juelich.de;Water vapor;Principal investigator;Bastien Sauvage;Laboratoire d'Aerologie;bastien.sauvage@aero.obs-mip.fr;Ancillary data;Principal investigator;Christoph Gerbig;Max-Planck-Institute for Biogeochemistry Jena;cgerbig@bgc-jena.mpg.de;Greenhouse gases (CH4, CO2);Principal investigator;Markus Hermann;Leibniz Institute for Tropospheric Research;hermann@tropos.de;Aerosols;Principal investigator;Florian Berkes;Forschungszentrum Julich;f.berkes@fz-juelich.de;NOx, NOy;Principal investigator;Philippe Nedelec;Laboratoire d'Aerologie;nedp@aero.obs-mip.fr;Ozone, Carbon monoxyde;Principal investigator;Martin Gallagher;University of Manchester;martin.gallagher@manchester.ac.uk;Clouds particules;Principal investigator;Helmut Ziereis;DLR;helmut.ziereis@dlr.de;NOx, NOy;Principal investigator;Damien Boulanger;Observatoire Midi-Pyrenees;damien.boulanger@obs-mip.fr;Database manager;Originator;Valerie Thouret;Laboratoire d'Aerologie;thov@aero.obs-mip.fr;Coordinator IAGOS-France;Point of contact;Andreas Petzold;Forschungszentrum Julich;a.petzold@fz-juelich.de;Coordinator IAGOS-Germany;Point of contact;http://iagos-data.fr/images/logo_blue.png;Logo;http://iagos-data.fr/portal/rest/images/map:global:thumb;Map of flights;Atmospheric chemistry > Nitrogen compounds > Nitrogen oxides;Atmospheric chemistry > Oxygen compounds > Ozone;Atmospheric winds;Atmospheric temperature;Atmospheric chemistry > Carbon and hydrocarbon compounds > Carbon dioxide;Atmospheric winds > Wind dynamics > Vorticity > Potential vorticity;Altitude > Planetary boundary layer height;Atmospheric temperature;Atmospheric chemistry > Nitrogen compounds > Nitrogen oxides;Atmospheric winds;Altitude > Barometric altitude;Atmospheric winds;Atmospheric temperature;Atmospheric chemistry > Nitrogen compounds > Nitrogen oxides;Atmospheric water vapor > Water vapor indicators > Humidity > Relative humidity;Atmospheric chemistry > Nitrogen compounds > Nitrogen oxides;Altitude > Geopotential height;Atmospheric winds > Wind dynamics > Vorticity > Potential vorticity;Atmospheric pressure > Static pressure;Platform characteristics > Airspeed/ground speed;Altitude > Planetary boundary layer height;Atmospheric water vapor > Water vapor indicators > Water vapor;Atmospheric temperature > Surface temperature > Potential temperature;Atmospheric chemistry > Carbon and hydrocarbon compounds > Carbon monoxide;Atmospheric chemistry > Carbon and hydrocarbon compounds > Methane;Atmospheric winds;Atmospheric winds > Wind dynamics > Vertical wind velocity/speed;Atmospheric pressure > Surface pressure;Atmospheric temperature;Platform characteristics > Airspeed/ground speed;AERIS parameters - GCMD;2018-09-06T18:17:33.836+02:00;Creation;Atmospheric conditions;Theme;GEMET - INSPIRE themes, version 1.0;2008-06-01;Publication;IAGOS;SEDOO;AERIS;http://iagos-data.fr/#CMSConsultPlace:DATA_POLICY;Restricted;NA;English;climatologyMeteorologyAtmosphere;true;-180.0;180.0;-44.0;83.0;1994-08-01;2100-12-31;Nasa Ames;1001;NetCDF;3;http://www.iagos.org;WWW:LINK-1.0-http--link;IAGOS central website;http://iagos-data.fr/#TimeseriesPlace:;WWW:DOWNLOAD-1.0-http--download;IAGOS Data Portal;http://dx.doi.org/10.25326/06;WWW:LINK-1.0-http--link;DOI of the dataset;Dataset;Commission Regulation (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;Publication;NA;true;Data produced by the European Research Infrastructure IAGOS.;Aircraft;Backscatter Cloud Probe;GHG - IAGOS-P2d;CO - IAGOS-P1;O3 - IAGOS-P1;H2O - IAGOS-P1;CPC - IAGOS-P1;OPC - IAGOS-P1;NOy/NOx - IAGOS-P2",
-    "group": "iagos",
-    "groups": [
-        {
-            "name": "iagos"
-        }
-    ],
-    "name": "4b383073-20a8-5b74-8dfd-0af5a57415f4",
-    "notes": [
-        "This dataset provides all time series, each one matching a IAGOS flight. The dataset includes values of all species measured by IAGOS instrumentation with a time acquisition resolution of 4 seconds as well as meteorological fields provided by the aircraft or the ECMWF."
-    ],
-    "oai_identifier": [
-        "4b383073-20a8-5b74-8dfd-0af5a57415f4"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-180.0,-44.0],[-180.0,83.0],[180.0,83.0],[180.0,-44.0],[-180.0,-44.0]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Atmospheric chemistry Nitrogen compounds Nitrogen oxides"
-        },
-        {
-            "name": "Atmospheric chemistry Oxygen compounds Ozone"
-        },
-        {
-            "name": "Atmospheric winds"
-        },
-        {
-            "name": "Atmospheric temperature"
-        },
-        {
-            "name": "Altitude Planetary boundary layer height"
-        },
-        {
-            "name": "Atmospheric temperature"
-        },
-        {
-            "name": "Atmospheric chemistry Nitrogen compounds Nitrogen oxides"
-        },
-        {
-            "name": "Atmospheric winds"
-        },
-        {
-            "name": "Altitude Barometric altitude"
-        },
-        {
-            "name": "Atmospheric winds"
-        },
-        {
-            "name": "Atmospheric temperature"
-        },
-        {
-            "name": "Atmospheric chemistry Nitrogen compounds Nitrogen oxides"
-        }
-    ],
-    "title": [
-        "IAGOS Time series"
-    ],
-    "url": "http://iagos-data.fr/#TimeseriesPlace:"
-}
\ No newline at end of file
diff --git a/oaitestdata/iagos-iso19139/SET_1/json/7148e61c-9127-560c-930e-925b6f13ced0.json b/oaitestdata/iagos-iso19139/SET_1/json/7148e61c-9127-560c-930e-925b6f13ced0.json
deleted file mode 100644
index c3f10ecd..00000000
--- a/oaitestdata/iagos-iso19139/SET_1/json/7148e61c-9127-560c-930e-925b6f13ced0.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "contact@aeris-data.fr"
-    ],
-    "Contributor": [
-        "IAGOS"
-    ],
-    "DOI": "http://dx.doi.org/10.25326/4",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "http://catalogue2.sedoo.fr/geonetwork/srv/eng/csw-iagos?verb=GetRecord&metadataPrefix=iso19139&identifier=7148e61c-9127-560c-930e-925b6f13ced0",
-    "PublicationTimestamp": "1994-08-01T11:59:59Z",
-    "PublicationYear": [
-        "1994"
-    ],
-    "Publisher": [
-        "AERIS"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "http://iagos-data.fr/#CMSConsultPlace:DATA_POLICY"
-    ],
-    "SpatialCoverage": "(90S-90N,180W-180E)",
-    "TempCoverageBegin": 62911335599,
-    "TempCoverageEnd": 62911335599,
-    "TemporalCoverage": " point in time : 1994-08-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-08-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-08-01T11:59:59Z",
-    "fulltext": "a9b2506a-c606-49c7-b387-1d722c69fa03;English;Dataset;AERIS;France;contact@aeris-data.fr;Publisher;2018-09-06T18:17:39.700+02:00;EPSG:4326;IAGOS PBL-referenced profiles of O3 and CO;1994-08-01;Creation;2018-09-06T18:17:39.700+02:00;Publication;10.25326/4;The climatological vertical stratification of ozone (O3) and carbon monoxide (CO) within the planetary boundary layer (PBL) and at the interface with free troposphere (FT) was derived using all IAGOS (In-service Aircraft for a Global Observing System) and WOUDC (World Ozone and Ultraviolet Radiation Data Centre) vertical profiles available at northern mid-latitudes (25\u00b0N-60\u00b0N) between August 1994 and December 2016 (Petetin et al., 2018).\n\nThe methodology is the following :\n1) All profiles with a surface-based temperature inversion (i.e. increase of temperature with altitude starting from the surface) are discarded. \n2) All remaining profiles are then interpolated on a fixed vertical grid of 50 m vertical resolution between 0 and 4 km above ground level (i.e. 80 altitude levels). For each of these profiles, the PBL height is estimated as the base altitude of the first elevated temperature inversion (i.e. the altitude level above which temperature starts to increase with altitude). An upper limit of 4 km is fixed for the PBL height. In order to reduce uncertainties associated with data gaps, we discarded (i) all profiles with more than 25% of missing temperature data between 0 and 4 km (i.e. cumulated data gaps larger than 0.25x4000=2000 m), and/or (ii) all profiles with more than 4 missing data between the surface and the estimated PBL height (i.e. cumulated data gaps larger than 4x50=200 m). \n3) The profiles are expressed in the z/h vertical coordinate system where z is the altitude and h the PBL height estimate. O3 and CO mixing ratios are interpolated along z/h values ranging between 0 (the surface) and 2 (two times the PBL height) with a vertical resolution of of 0.05 (i.e. 40 altitude levels). All profiles with missing O3 or CO data are discarded. Then all the remaining profiles are averaged, which gives the so-called PBL-referenced profiles. This is done for the different seasons (DJF : December-January-February, MAM : March-April-May, JJA : June-July-August, SON : September-October-November, ANN : annual) and times of day (night\u00a0: sunset to sunrise, morning\u00a0: sunrise to solar noon, midday\u00a0: solar noon to 3 h past solar noon, afternoon\u00a0: 3 h past solar noon to sunset, daytime\u00a0: sunrise to sunset, all\u00a0: the whole day).\n\nA more complete description of the methodology as well as an analysis of the results is available in the reference paper of Petetin et al. (2018).\n\nL4 IAGOS PBL-referenced profiles are available on the IAGOS data portal (http://iagos-data.fr) and are part of the IAGOS ancillary data. They are subject to the IAGOS data protocol.;SEDOO;14 avenue Edouard Belin;Toulouse;31400;France;aeris@sedoo.fr;Distributor;Herve Petetin;Laboratoire d'Aerologie;herve.petetin@aero.obs-mip.fr;Principal Investigator of IAGOS PBL Profiles;Point of contact;Bastien Sauvage;Laboratoire d'Aerologie;bastien.sauvage@aero.obs-mip.fr;Principal Investigator of IAGOS Ancillary data; Principal Investigator of SOFT-IO;Principal investigator;Philippe Nedelec;Laboratoire d'Aerologie;nedp@aero.obs-mip.fr;Ozone, Carbon monoxyde;Principal investigator;Damien Boulanger;Observatoire Midi-Pyrenees;damien.boulanger@obs-mip.fr;Database manager;Originator;http://iagos-data.fr/images/logo_blue.png;Logo;http://iagos-data.fr/portal/rest/images/map:global:thumb;Map of flights;http://iagos-data.fr/portal/rest/image/storedById/6990116025497246148;Figure 1 : Vertical profiles of O3 mixing ratio (in ppbv; left panels), normalized by the O3 mixing ratio at z/h=1 (middle panels), and vertical gradient (in ppbv hm-1; right panels), for different times of the day (from top to bottom : all day along, daytime, night, morning, midday, afternoon). The shaded area represents the uncertainties (at a 95% confidence level) on the mean. For each season and time of the day, we indicate the number (N) of profiles used for calculating the PBL-referenced profile (i.e. profiles without any missing data), the mean PBL height calculated based on this subset of profiles, and the mean PBL height considering all profiles (in brackets).;http://iagos-data.fr/portal/rest/image/storedById/4641718511330911523;Figure 2 : Vertical profiles of CO mixing ratio (in ppbv; left panels), normalized by the CO mixing ratio at z/h=1 (middle panels), and vertical gradient (in ppbv hm-1; right panels), for different times of the day (from top to bottom : all day along, daytime, night, morning, midday, afternoon). The shaded area represents the uncertainties (at a 95% confidence level) on the mean. For each season and time of the day, we indicate the number (N) of profiles used for calculating the PBL-referenced profile (i.e. profiles without any missing data), the mean PBL height calculated based on this subset of profiles, and the mean PBL height considering all profiles (in brackets).;Atmospheric conditions;Theme;GEMET - INSPIRE themes, version 1.0;2008-06-01;Publication;IAGOS;SEDOO;AERIS;http://iagos-data.fr/#CMSConsultPlace:DATA_POLICY;Restricted;NA;English;climatologyMeteorologyAtmosphere;true;-180.0;180.0;-90.0;90.0;1994-08-01;2016-12-31;CSV;http://www.iagos.org;WWW:LINK-1.0-http--link;IAGOS central website;http://iagos-data.fr/#CMSConsultPlace:PBL_PROFILES;WWW:DOWNLOAD-1.0-http--download;IAGOS PBL Profiles;http://dx.doi.org/10.25326/4;WWW:LINK-1.0-http--link;DOI of the dataset;Dataset;Commission Regulation (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;Publication;NA;true;Data produced by the European Research Infrastructure IAGOS.;Models/Analyses",
-    "group": "iagos",
-    "groups": [
-        {
-            "name": "iagos"
-        }
-    ],
-    "name": "7148e61c-9127-560c-930e-925b6f13ced0",
-    "notes": [
-        "The climatological vertical stratification of ozone (O3) and carbon monoxide (CO) within the planetary boundary layer (PBL) and at the interface with free troposphere (FT) was derived using all IAGOS (In-service Aircraft for a Global Observing System) and WOUDC (World Ozone and Ultraviolet Radiation Data Centre) vertical profiles available at northern mid-latitudes (25\u00b0N-60\u00b0N) between August 1994 and December 2016 (Petetin et al., 2018).\n\nThe methodology is the following :\n1) All profiles with a surface-based temperature inversion (i.e. increase of temperature with altitude starting from the surface) are discarded. \n2) All remaining profiles are then interpolated on a fixed vertical grid of 50 m vertical resolution between 0 and 4 km above ground level (i.e. 80 altitude levels). For each of these profiles, the PBL height is estimated as the base altitude of the first elevated temperature inversion (i.e. the altitude level above which temperature starts to increase with altitude). An upper limit of 4 km is fixed for the PBL height. In order to reduce uncertainties associated with data gaps, we discarded (i) all profiles with more than 25% of missing temperature data between 0 and 4 km (i.e. cumulated data gaps larger than 0.25x4000=2000 m), and/or (ii) all profiles with more than 4 missing data between the surface and the estimated PBL height (i.e. cumulated data gaps larger than 4x50=200 m). \n3) The profiles are expressed in the z/h vertical coordinate system where z is the altitude and h the PBL height estimate. O3 and CO mixing ratios are interpolated along z/h values ranging between 0 (the surface) and 2 (two times the PBL height) with a vertical resolution of of 0.05 (i.e. 40 altitude levels). All profiles with missing O3 or CO data are discarded. Then all the remaining profiles are averaged, which gives the so-called PBL-referenced profiles. This is done for the different seasons (DJF : December-January-February, MAM : March-April-May, JJA : June-July-August, SON : September-October-November, ANN : annual) and times of day (night\u00a0: sunset to sunrise, morning\u00a0: sunrise to solar noon, midday\u00a0: solar noon to 3 h past solar noon, afternoon\u00a0: 3 h past solar noon to sunset, daytime\u00a0: sunrise to sunset, all\u00a0: the whole day).\n\nA more complete description of the methodology as well as an analysis of the results is available in the reference paper of Petetin et al. (2018).\n\nL4 IAGOS PBL-referenced profiles are available on the IAGOS data portal (http://iagos-data.fr) and are part of the IAGOS ancillary data. They are subject to the IAGOS data protocol."
-    ],
-    "oai_identifier": [
-        "7148e61c-9127-560c-930e-925b6f13ced0"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-180.0,-90.0],[-180.0,90.0],[180.0,90.0],[180.0,-90.0],[-180.0,-90.0]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "IAGOS"
-        },
-        {
-            "name": "SEDOO"
-        },
-        {
-            "name": "AERIS"
-        }
-    ],
-    "title": [
-        "IAGOS PBL-referenced profiles of O3 and CO"
-    ],
-    "url": "http://iagos-data.fr/#CMSConsultPlace:PBL_PROFILES"
-}
\ No newline at end of file
diff --git a/oaitestdata/iagos-iso19139/SET_1/json/9b3ef7e7-a7f2-555f-9fe6-8536a15d438d.json b/oaitestdata/iagos-iso19139/SET_1/json/9b3ef7e7-a7f2-555f-9fe6-8536a15d438d.json
deleted file mode 100644
index f7067984..00000000
--- a/oaitestdata/iagos-iso19139/SET_1/json/9b3ef7e7-a7f2-555f-9fe6-8536a15d438d.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "contact@aeris-data.fr"
-    ],
-    "Contributor": [
-        "IAGOS"
-    ],
-    "DOI": "http://dx.doi.org/10.25326/3",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "http://catalogue2.sedoo.fr/geonetwork/srv/eng/csw-iagos?verb=GetRecord&metadataPrefix=iso19139&identifier=9b3ef7e7-a7f2-555f-9fe6-8536a15d438d",
-    "PublicationTimestamp": "1994-08-01T11:59:59Z",
-    "PublicationYear": [
-        "1994"
-    ],
-    "Publisher": [
-        "AERIS"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "http://iagos-data.fr/#CMSConsultPlace:DATA_POLICY"
-    ],
-    "SpatialCoverage": "(90S-90N,180W-180E)",
-    "TempCoverageBegin": 63144359999,
-    "TempCoverageEnd": 63144359999,
-    "TemporalCoverage": " point in time : 2001-12-19T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2001-12-19T11:59:59Z",
-    "TemporalCoverage:EndDate": "2001-12-19T11:59:59Z",
-    "fulltext": "4d3be8dd-c41a-4f35-8ba6-722cf12e2de3;English;Dataset;AERIS;France;contact@aeris-data.fr;Publisher;2018-09-06T18:17:38.497+02:00;EPSG:4326;IAGOS ancillary data (L4) - CO contributions to the aircraft measurements;1994-08-01;Creation;2018-09-06T18:17:38.497+02:00;Publication;10.25326/3;In order to help analyzing the IAGOS carbon monoxide (CO) observations and understanding the processes driving their evolutions, we provide ancillary parameters calculated with SOFT-IO (Sauvage et al., 2017; http://dx.doi.org/10.25326/2) along aircraft observations.\n\nCO contribution is defined as follow. CO mixing ratio is calculated for each IAGOS observations (every 0.5\u00b0 in latitude or longitude at cruising altitude; every 10hPa during ascent or descent of the plane) and sorted by source origin (biomass burning and anthropogenic origin, and for 14 geographical origins, see Fig.1). CO total contribution is then the sum of each CO source origin or the sum of each CO geographical origin and can be used to interpret IAGOS CO measurements. Some examples are highlighted in Sauvage et al., 2017 for individual flights (their Fig.5 to Fig.8).\n\nCO is calculated so far for different up-to-date emissions inventories (ECCAD and MACCity for anthropogenic emissions; GFED4 and GFAS v1.2 for biomass burning emissions) available in the ECCAD project (http://eccad.aeris-data.fr/) and since the beginning of CO measurements in IAGOS (end of 2001) up to now.\n\nL4 IAGOS CO contributions are available on the IAGOS data portal (http://iagos-data.fr) and are part of the IAGOS ancillary data (http://iagos-data.fr/#L4Place:).They are subject to the IAGOS data protocol (http://iagos-data.fr/#RegisterPlace:);SEDOO;14 avenue Edouard Belin;Toulouse;31400;France;aeris@sedoo.fr;Distributor;Bastien Sauvage;Laboratoire d'Aerologie;bastien.sauvage@aero.obs-mip.fr;Ancillary data;Principal investigator;Philippe Nedelec;Laboratoire d'Aerologie;nedp@aero.obs-mip.fr;Ozone, Carbon monoxyde;Principal investigator;Damien Boulanger;Observatoire Midi-Pyrenees;damien.boulanger@obs-mip.fr;Database manager;Originator;http://iagos-data.fr/images/logo_blue.png;Logo;http://iagos-data.fr/portal/rest/images/map:global:thumb;Map of flights;http://iagos-data.fr/portal/rest/image/storedById/6871350981954295755;Figure 1: Geographical regions used to quantify CO origin (Figure from\u00a0: http://www.globalfiredata.org/data.html);Atmospheric conditions;Theme;GEMET - INSPIRE themes, version 1.0;2008-06-01;Publication;IAGOS;SEDOO;AERIS;http://iagos-data.fr/#CMSConsultPlace:DATA_POLICY;Restricted;NA;English;climatologyMeteorologyAtmosphere;true;-180.0;180.0;-90.0;90.0;2001-12-19;2100-12-31;NetCDF;3;http://www.iagos.org;WWW:LINK-1.0-http--link;IAGOS central website;http://iagos-data.fr/#CMSConsultPlace:ANCILLARY_DATA;WWW:DOWNLOAD-1.0-http--download;IAGOS Ancillary Data;http://dx.doi.org/10.25326/3;WWW:LINK-1.0-http--link;DOI of the dataset;Dataset;Commission Regulation (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;Publication;NA;true;Data produced by the European Research Infrastructure IAGOS.;Models/Analyses",
-    "group": "iagos",
-    "groups": [
-        {
-            "name": "iagos"
-        }
-    ],
-    "name": "9b3ef7e7-a7f2-555f-9fe6-8536a15d438d",
-    "notes": [
-        "In order to help analyzing the IAGOS carbon monoxide (CO) observations and understanding the processes driving their evolutions, we provide ancillary parameters calculated with SOFT-IO (Sauvage et al., 2017; http://dx.doi.org/10.25326/2) along aircraft observations.\n\nCO contribution is defined as follow. CO mixing ratio is calculated for each IAGOS observations (every 0.5\u00b0 in latitude or longitude at cruising altitude; every 10hPa during ascent or descent of the plane) and sorted by source origin (biomass burning and anthropogenic origin, and for 14 geographical origins, see Fig.1). CO total contribution is then the sum of each CO source origin or the sum of each CO geographical origin and can be used to interpret IAGOS CO measurements. Some examples are highlighted in Sauvage et al., 2017 for individual flights (their Fig.5 to Fig.8).\n\nCO is calculated so far for different up-to-date emissions inventories (ECCAD and MACCity for anthropogenic emissions; GFED4 and GFAS v1.2 for biomass burning emissions) available in the ECCAD project (http://eccad.aeris-data.fr/) and since the beginning of CO measurements in IAGOS (end of 2001) up to now.\n\nL4 IAGOS CO contributions are available on the IAGOS data portal (http://iagos-data.fr) and are part of the IAGOS ancillary data (http://iagos-data.fr/#L4Place:).They are subject to the IAGOS data protocol (http://iagos-data.fr/#RegisterPlace:)"
-    ],
-    "oai_identifier": [
-        "9b3ef7e7-a7f2-555f-9fe6-8536a15d438d"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-180.0,-90.0],[-180.0,90.0],[180.0,90.0],[180.0,-90.0],[-180.0,-90.0]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "IAGOS"
-        },
-        {
-            "name": "SEDOO"
-        },
-        {
-            "name": "AERIS"
-        }
-    ],
-    "title": [
-        "IAGOS ancillary data (L4) - CO contributions to the aircraft measurements"
-    ],
-    "url": "http://iagos-data.fr/#CMSConsultPlace:ANCILLARY_DATA"
-}
\ No newline at end of file
diff --git a/oaitestdata/iagos-iso19139/SET_1/json/b73648f1-2f43-52c8-b4e4-f071f16f4e61.json b/oaitestdata/iagos-iso19139/SET_1/json/b73648f1-2f43-52c8-b4e4-f071f16f4e61.json
deleted file mode 100644
index 6030f6b9..00000000
--- a/oaitestdata/iagos-iso19139/SET_1/json/b73648f1-2f43-52c8-b4e4-f071f16f4e61.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "contact@aeris-data.fr"
-    ],
-    "Contributor": [
-        "IAGOS"
-    ],
-    "DOI": "http://dx.doi.org/null",
-    "DiscHierarchy": [
-        "4.4.7.1",
-        "Environmental Research",
-        "Environmental Monitoring"
-    ],
-    "Discipline": "Environmental Monitoring",
-    "Language": [
-        "English",
-        "English"
-    ],
-    "MetaDataAccess": "http://catalogue2.sedoo.fr/geonetwork/srv/eng/csw-iagos?verb=GetRecord&metadataPrefix=iso19139&identifier=b73648f1-2f43-52c8-b4e4-f071f16f4e61",
-    "PublicationTimestamp": "1994-08-01T11:59:59Z",
-    "PublicationYear": [
-        "1994"
-    ],
-    "Publisher": [
-        "AERIS"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "http://iagos-data.fr/#CMSConsultPlace:DATA_POLICY"
-    ],
-    "SpatialCoverage": "(90S-90N,180W-180E)",
-    "TempCoverageBegin": 62911335599,
-    "TempCoverageEnd": 62911335599,
-    "TemporalCoverage": " point in time : 1994-08-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-08-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-08-01T11:59:59Z",
-    "fulltext": "c570d452-0f05-4227-bed4-c1905c2951eb;English;Dataset;AERIS;France;contact@aeris-data.fr;Publisher;2018-09-06T18:17:40.891+02:00;EPSG:4326;IAGOS footprints;1994-08-01;Creation;2018-09-06T18:17:40.891+02:00;Publication;This dataset provides footprints for all the vertical profiles of carbon monoxyde over the airports visited by the IAGOS fleet. The footprints are based on model simulations of the up-stream influences on the observation location. Theses footprints are coupled to surface flux maps in order to derive tracer concentration changes at the airport.;SEDOO;14 avenue Edouard Belin;Toulouse;31400;France;aeris@sedoo.fr;Distributor;Bastien Sauvage;Laboratoire d'Aerologie;bastien.sauvage@aero.obs-mip.fr;Ancillary data;Principal investigator;Philippe Nedelec;Laboratoire d'Aerologie;nedp@aero.obs-mip.fr;Ozone, Carbon monoxyde;Principal investigator;Damien Boulanger;Observatoire Midi-Pyrenees;damien.boulanger@obs-mip.fr;Database manager;Originator;http://iagos-data.fr/images/logo_blue.png;Logo;http://iagos-data.fr/portal/rest/images/map:global:thumb;Map of flights;Atmospheric conditions;Theme;GEMET - INSPIRE themes, version 1.0;2008-06-01;Publication;IAGOS;SEDOO;AERIS;http://iagos-data.fr/#CMSConsultPlace:DATA_POLICY;Restricted;NA;English;climatologyMeteorologyAtmosphere;true;-180.0;180.0;-90.0;90.0;1994-08-01;2100-12-31;NetCDF;3;http://www.iagos.org;WWW:LINK-1.0-http--link;IAGOS central website;http://iagos-data.fr/#CMSConsultPlace:ANCILLARY_DATA;WWW:DOWNLOAD-1.0-http--download;IAGOS Ancillary Data;http://dx.doi.org/null;WWW:LINK-1.0-http--link;DOI of the dataset;Dataset;Commission Regulation (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;Publication;NA;true;Data produced by the European Research Infrastructure IAGOS.;Models/Analyses",
-    "group": "iagos",
-    "groups": [
-        {
-            "name": "iagos"
-        }
-    ],
-    "name": "b73648f1-2f43-52c8-b4e4-f071f16f4e61",
-    "notes": [
-        "This dataset provides footprints for all the vertical profiles of carbon monoxyde over the airports visited by the IAGOS fleet. The footprints are based on model simulations of the up-stream influences on the observation location. Theses footprints are coupled to surface flux maps in order to derive tracer concentration changes at the airport."
-    ],
-    "oai_identifier": [
-        "b73648f1-2f43-52c8-b4e4-f071f16f4e61"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-180.0,-90.0],[-180.0,90.0],[180.0,90.0],[180.0,-90.0],[-180.0,-90.0]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "IAGOS"
-        },
-        {
-            "name": "SEDOO"
-        },
-        {
-            "name": "AERIS"
-        }
-    ],
-    "title": [
-        "IAGOS footprints"
-    ],
-    "url": "http://iagos-data.fr/#CMSConsultPlace:ANCILLARY_DATA"
-}
\ No newline at end of file
diff --git a/oaitestdata/iagos-oai_dc/SET_1/json/15ff6b9d-93ab-5ead-89b0-13d4b10a6190.json b/oaitestdata/iagos-oai_dc/SET_1/json/15ff6b9d-93ab-5ead-89b0-13d4b10a6190.json
deleted file mode 100644
index 4c364ce9..00000000
--- a/oaitestdata/iagos-oai_dc/SET_1/json/15ff6b9d-93ab-5ead-89b0-13d4b10a6190.json
+++ /dev/null
@@ -1,95 +0,0 @@
-{
-    "Contact": [
-        "http://www.iagos.org"
-    ],
-    "DOI": "http://dx.doi.org/10.25326/07",
-    "DiscHierarchy": [
-        "4.4.1",
-        "Geosciences",
-        "Atmospheric Sciences"
-    ],
-    "Discipline": "Atmospheric Sciences",
-    "Format": [
-        "Nasa Ames",
-        "NetCDF"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://catalogue2.sedoo.fr/geonetwork/srv/eng/csw-iagos?verb=GetRecord&metadataPrefix=oai_dc&identifier=15ff6b9d-93ab-5ead-89b0-13d4b10a6190",
-    "PublicationTimestamp": "2018-09-06T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "IAGOS"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "restricted"
-    ],
-    "SpatialCoverage": [
-        "180.0 -90.0",
-        "-180.0 90.0"
-    ],
-    "fulltext": "61e54760-86ba-4b69-804b-06a7793f9104;2018-09-06T18:17:35.974+02:00;IAGOS vertical profiles;dataset;Atmospheric chemistry > Nitrogen compounds > Nitrogen oxides;Atmospheric chemistry > Oxygen compounds > Ozone;Atmospheric winds;Atmospheric temperature;Atmospheric chemistry > Carbon and hydrocarbon compounds > Carbon dioxide;Atmospheric winds > Wind dynamics > Vorticity > Potential vorticity;Altitude > Planetary boundary layer height;Atmospheric temperature;Atmospheric chemistry > Nitrogen compounds > Nitrogen oxides;Atmospheric winds;Altitude > Barometric altitude;Atmospheric winds;Atmospheric temperature;Atmospheric chemistry > Nitrogen compounds > Nitrogen oxides;Atmospheric water vapor > Water vapor indicators > Humidity > Relative humidity;Atmospheric chemistry > Nitrogen compounds > Nitrogen oxides;Altitude > Geopotential height;Atmospheric winds > Wind dynamics > Vorticity > Potential vorticity;Atmospheric pressure > Static pressure;Platform characteristics > Airspeed/ground speed;Altitude > Planetary boundary layer height;Atmospheric water vapor > Water vapor indicators > Water vapor;Atmospheric temperature > Surface temperature > Potential temperature;Atmospheric chemistry > Carbon and hydrocarbon compounds > Carbon monoxide;Atmospheric chemistry > Carbon and hydrocarbon compounds > Methane;Atmospheric winds;Atmospheric winds > Wind dynamics > Vertical wind velocity/speed;Atmospheric pressure > Surface pressure;Atmospheric temperature;Platform characteristics > Airspeed/ground speed;Atmospheric conditions;IAGOS;SEDOO;AERIS;climatologyMeteorologyAtmosphere;Nasa Ames;NetCDF;This dataset provides all vertical profiles over the airports visited by the IAGOS fleet. The profiles match the take-off and landing phases of the flights. The dataset includes values of all species measured by IAGOS instrumentation with a time acquisition resolution of 4 seconds as well as meteorological fields provided by the aircraft or the ECMWF.;This dataset provides all vertical profiles over the airports visited by the IAGOS fleet. The profiles match the take-off and landing phases of the flights. The dataset includes values of all species measured by IAGOS instrumentation with a time acquisition resolution of 4 seconds as well as meteorological fields provided by the aircraft or the ECMWF.;restricted;eng;Data produced by the European Research Infrastructure IAGOS.;Nasa Ames;NetCDF;180.0 -90.0;-180.0 90.0;http://www.iagos.org;http://iagos-data.fr/#TimeseriesPlace:;http://dx.doi.org/10.25326/07;http://iagos-data.fr/images/logo_blue.png;http://iagos-data.fr/portal/rest/images/map:global:thumb",
-    "group": "iagos",
-    "groups": [
-        {
-            "name": "iagos"
-        }
-    ],
-    "name": "15ff6b9d-93ab-5ead-89b0-13d4b10a6190",
-    "notes": [
-        "This dataset provides all vertical profiles over the airports visited by the IAGOS fleet. The profiles match the take-off and landing phases of the flights. The dataset includes values of all species measured by IAGOS instrumentation with a time acquisition resolution of 4 seconds as well as meteorological fields provided by the aircraft or the ECMWF."
-    ],
-    "oai_identifier": [
-        "15ff6b9d-93ab-5ead-89b0-13d4b10a6190"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Atmospheric"
-        },
-        {
-            "name": "chemistry"
-        },
-        {
-            "name": "Nitrogen"
-        },
-        {
-            "name": "compounds"
-        },
-        {
-            "name": "Nitrogen"
-        },
-        {
-            "name": "oxides"
-        },
-        {
-            "name": "Atmospheric"
-        },
-        {
-            "name": "chemistry"
-        },
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "compounds"
-        },
-        {
-            "name": "Ozone"
-        },
-        {
-            "name": "Atmospheric"
-        }
-    ],
-    "title": [
-        "IAGOS vertical profiles"
-    ],
-    "url": "http://iagos-data.fr/portal/rest/images/map:global:thumb"
-}
\ No newline at end of file
diff --git a/oaitestdata/iagos-oai_dc/SET_1/json/22c3ef58-9355-5825-8950-765b050e7018.json b/oaitestdata/iagos-oai_dc/SET_1/json/22c3ef58-9355-5825-8950-765b050e7018.json
deleted file mode 100644
index f1b63de1..00000000
--- a/oaitestdata/iagos-oai_dc/SET_1/json/22c3ef58-9355-5825-8950-765b050e7018.json
+++ /dev/null
@@ -1,94 +0,0 @@
-{
-    "Contact": [
-        "http://www.iagos.org"
-    ],
-    "DOI": "http://dx.doi.org/10.25326/08",
-    "DiscHierarchy": [
-        "4.4.1",
-        "Geosciences",
-        "Atmospheric Sciences"
-    ],
-    "Discipline": "Atmospheric Sciences",
-    "Format": [
-        "NetCDF"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://catalogue2.sedoo.fr/geonetwork/srv/eng/csw-iagos?verb=GetRecord&metadataPrefix=oai_dc&identifier=22c3ef58-9355-5825-8950-765b050e7018",
-    "PublicationTimestamp": "2018-09-06T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "IAGOS"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "restricted"
-    ],
-    "SpatialCoverage": [
-        "180.0 -44.0",
-        "-180.0 83.0"
-    ],
-    "fulltext": "95941ca3-7251-4bed-877a-d2a99fb719cc;2018-09-06T18:17:37.253+02:00;IAGOS Climatologies;dataset;Atmospheric chemistry > Oxygen compounds > Ozone;Atmospheric chemistry > Carbon and hydrocarbon compounds > Carbon monoxide;Atmospheric conditions;IAGOS;SEDOO;AERIS;climatologyMeteorologyAtmosphere;NetCDF;This dataset provides climatologies for ozone and carbon monoxyde over a decade (2001-2010). Two types of climatologies are available: with 10 fixed pressure levels (from 288 hPa to 186 hPa) or with 4 dynamic pressure levels (lower stratosphere, upper statisphere, tropopause, upper troposphere).;This dataset provides climatologies for ozone and carbon monoxyde over a decade (2001-2010). Two types of climatologies are available: with 10 fixed pressure levels (from 288 hPa to 186 hPa) or with 4 dynamic pressure levels (lower stratosphere, upper statisphere, tropopause, upper troposphere).;restricted;eng;Data produced by the European Research Infrastructure IAGOS.;NetCDF;180.0 -44.0;-180.0 83.0;http://www.iagos.org;http://www.iagos-data.fr;http://dx.doi.org/10.25326/08;http://iagos-data.fr/images/logo_blue.png;http://iagos-data.fr/portal/rest/images/map:global:thumb",
-    "group": "iagos",
-    "groups": [
-        {
-            "name": "iagos"
-        }
-    ],
-    "name": "22c3ef58-9355-5825-8950-765b050e7018",
-    "notes": [
-        "This dataset provides climatologies for ozone and carbon monoxyde over a decade (2001-2010). Two types of climatologies are available: with 10 fixed pressure levels (from 288 hPa to 186 hPa) or with 4 dynamic pressure levels (lower stratosphere, upper statisphere, tropopause, upper troposphere)."
-    ],
-    "oai_identifier": [
-        "22c3ef58-9355-5825-8950-765b050e7018"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Atmospheric"
-        },
-        {
-            "name": "chemistry"
-        },
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "compounds"
-        },
-        {
-            "name": "Ozone"
-        },
-        {
-            "name": "Atmospheric"
-        },
-        {
-            "name": "chemistry"
-        },
-        {
-            "name": "Carbon"
-        },
-        {
-            "name": "hydrocarbon"
-        },
-        {
-            "name": "compounds"
-        },
-        {
-            "name": "Carbon"
-        },
-        {
-            "name": "monoxide"
-        }
-    ],
-    "title": [
-        "IAGOS Climatologies"
-    ],
-    "url": "http://iagos-data.fr/portal/rest/images/map:global:thumb"
-}
\ No newline at end of file
diff --git a/oaitestdata/iagos-oai_dc/SET_1/json/4b383073-20a8-5b74-8dfd-0af5a57415f4.json b/oaitestdata/iagos-oai_dc/SET_1/json/4b383073-20a8-5b74-8dfd-0af5a57415f4.json
deleted file mode 100644
index 4a124149..00000000
--- a/oaitestdata/iagos-oai_dc/SET_1/json/4b383073-20a8-5b74-8dfd-0af5a57415f4.json
+++ /dev/null
@@ -1,95 +0,0 @@
-{
-    "Contact": [
-        "http://www.iagos.org"
-    ],
-    "DOI": "http://dx.doi.org/10.25326/06",
-    "DiscHierarchy": [
-        "4.4.1",
-        "Geosciences",
-        "Atmospheric Sciences"
-    ],
-    "Discipline": "Atmospheric Sciences",
-    "Format": [
-        "Nasa Ames",
-        "NetCDF"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://catalogue2.sedoo.fr/geonetwork/srv/eng/csw-iagos?verb=GetRecord&metadataPrefix=oai_dc&identifier=4b383073-20a8-5b74-8dfd-0af5a57415f4",
-    "PublicationTimestamp": "2018-09-06T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "IAGOS"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "restricted"
-    ],
-    "SpatialCoverage": [
-        "180.0 -44.0",
-        "-180.0 83.0"
-    ],
-    "fulltext": "575882c0-64ce-4648-bb19-00030d5d63af;2018-09-06T18:17:33.758+02:00;IAGOS Time series;dataset;Atmospheric chemistry > Nitrogen compounds > Nitrogen oxides;Atmospheric chemistry > Oxygen compounds > Ozone;Atmospheric winds;Atmospheric temperature;Atmospheric chemistry > Carbon and hydrocarbon compounds > Carbon dioxide;Atmospheric winds > Wind dynamics > Vorticity > Potential vorticity;Altitude > Planetary boundary layer height;Atmospheric temperature;Atmospheric chemistry > Nitrogen compounds > Nitrogen oxides;Atmospheric winds;Altitude > Barometric altitude;Atmospheric winds;Atmospheric temperature;Atmospheric chemistry > Nitrogen compounds > Nitrogen oxides;Atmospheric water vapor > Water vapor indicators > Humidity > Relative humidity;Atmospheric chemistry > Nitrogen compounds > Nitrogen oxides;Altitude > Geopotential height;Atmospheric winds > Wind dynamics > Vorticity > Potential vorticity;Atmospheric pressure > Static pressure;Platform characteristics > Airspeed/ground speed;Altitude > Planetary boundary layer height;Atmospheric water vapor > Water vapor indicators > Water vapor;Atmospheric temperature > Surface temperature > Potential temperature;Atmospheric chemistry > Carbon and hydrocarbon compounds > Carbon monoxide;Atmospheric chemistry > Carbon and hydrocarbon compounds > Methane;Atmospheric winds;Atmospheric winds > Wind dynamics > Vertical wind velocity/speed;Atmospheric pressure > Surface pressure;Atmospheric temperature;Platform characteristics > Airspeed/ground speed;Atmospheric conditions;IAGOS;SEDOO;AERIS;climatologyMeteorologyAtmosphere;Nasa Ames;NetCDF;This dataset provides all time series, each one matching a IAGOS flight. The dataset includes values of all species measured by IAGOS instrumentation with a time acquisition resolution of 4 seconds as well as meteorological fields provided by the aircraft or the ECMWF.;This dataset provides all time series, each one matching a IAGOS flight. The dataset includes values of all species measured by IAGOS instrumentation with a time acquisition resolution of 4 seconds as well as meteorological fields provided by the aircraft or the ECMWF.;restricted;eng;Data produced by the European Research Infrastructure IAGOS.;Nasa Ames;NetCDF;180.0 -44.0;-180.0 83.0;http://www.iagos.org;http://iagos-data.fr/#TimeseriesPlace:;http://dx.doi.org/10.25326/06;http://iagos-data.fr/images/logo_blue.png;http://iagos-data.fr/portal/rest/images/map:global:thumb",
-    "group": "iagos",
-    "groups": [
-        {
-            "name": "iagos"
-        }
-    ],
-    "name": "4b383073-20a8-5b74-8dfd-0af5a57415f4",
-    "notes": [
-        "This dataset provides all time series, each one matching a IAGOS flight. The dataset includes values of all species measured by IAGOS instrumentation with a time acquisition resolution of 4 seconds as well as meteorological fields provided by the aircraft or the ECMWF."
-    ],
-    "oai_identifier": [
-        "4b383073-20a8-5b74-8dfd-0af5a57415f4"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Atmospheric"
-        },
-        {
-            "name": "chemistry"
-        },
-        {
-            "name": "Nitrogen"
-        },
-        {
-            "name": "compounds"
-        },
-        {
-            "name": "Nitrogen"
-        },
-        {
-            "name": "oxides"
-        },
-        {
-            "name": "Atmospheric"
-        },
-        {
-            "name": "chemistry"
-        },
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "compounds"
-        },
-        {
-            "name": "Ozone"
-        },
-        {
-            "name": "Atmospheric"
-        }
-    ],
-    "title": [
-        "IAGOS Time series"
-    ],
-    "url": "http://iagos-data.fr/portal/rest/images/map:global:thumb"
-}
\ No newline at end of file
diff --git a/oaitestdata/iagos-oai_dc/SET_1/json/7148e61c-9127-560c-930e-925b6f13ced0.json b/oaitestdata/iagos-oai_dc/SET_1/json/7148e61c-9127-560c-930e-925b6f13ced0.json
deleted file mode 100644
index 60dc2ed7..00000000
--- a/oaitestdata/iagos-oai_dc/SET_1/json/7148e61c-9127-560c-930e-925b6f13ced0.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "http://www.iagos.org"
-    ],
-    "DOI": "http://dx.doi.org/10.25326/4",
-    "DiscHierarchy": [
-        "4.4.1",
-        "Geosciences",
-        "Atmospheric Sciences"
-    ],
-    "Discipline": "Atmospheric Sciences",
-    "Format": [
-        "CSV"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://catalogue2.sedoo.fr/geonetwork/srv/eng/csw-iagos?verb=GetRecord&metadataPrefix=oai_dc&identifier=7148e61c-9127-560c-930e-925b6f13ced0",
-    "PublicationTimestamp": "2018-09-06T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "IAGOS"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "restricted"
-    ],
-    "SpatialCoverage": [
-        "180.0 -90.0",
-        "-180.0 90.0"
-    ],
-    "fulltext": "a9b2506a-c606-49c7-b387-1d722c69fa03;2018-09-06T18:17:39.700+02:00;IAGOS PBL-referenced profiles of O3 and CO;dataset;Atmospheric conditions;IAGOS;SEDOO;AERIS;climatologyMeteorologyAtmosphere;CSV;The climatological vertical stratification of ozone (O3) and carbon monoxide (CO) within the planetary boundary layer (PBL) and at the interface with free troposphere (FT) was derived using all IAGOS (In-service Aircraft for a Global Observing System) and WOUDC (World Ozone and Ultraviolet Radiation Data Centre) vertical profiles available at northern mid-latitudes (25\u00b0N-60\u00b0N) between August 1994 and December 2016 (Petetin et al., 2018).\n\nThe methodology is the following :\n1) All profiles with a surface-based temperature inversion (i.e. increase of temperature with altitude starting from the surface) are discarded. \n2) All remaining profiles are then interpolated on a fixed vertical grid of 50 m vertical resolution between 0 and 4 km above ground level (i.e. 80 altitude levels). For each of these profiles, the PBL height is estimated as the base altitude of the first elevated temperature inversion (i.e. the altitude level above which temperature starts to increase with altitude). An upper limit of 4 km is fixed for the PBL height. In order to reduce uncertainties associated with data gaps, we discarded (i) all profiles with more than 25% of missing temperature data between 0 and 4 km (i.e. cumulated data gaps larger than 0.25x4000=2000 m), and/or (ii) all profiles with more than 4 missing data between the surface and the estimated PBL height (i.e. cumulated data gaps larger than 4x50=200 m). \n3) The profiles are expressed in the z/h vertical coordinate system where z is the altitude and h the PBL height estimate. O3 and CO mixing ratios are interpolated along z/h values ranging between 0 (the surface) and 2 (two times the PBL height) with a vertical resolution of of 0.05 (i.e. 40 altitude levels). All profiles with missing O3 or CO data are discarded. Then all the remaining profiles are averaged, which gives the so-called PBL-referenced profiles. This is done for the different seasons (DJF : December-January-February, MAM : March-April-May, JJA : June-July-August, SON : September-October-November, ANN : annual) and times of day (night\u00a0: sunset to sunrise, morning\u00a0: sunrise to solar noon, midday\u00a0: solar noon to 3 h past solar noon, afternoon\u00a0: 3 h past solar noon to sunset, daytime\u00a0: sunrise to sunset, all\u00a0: the whole day).\n\nA more complete description of the methodology as well as an analysis of the results is available in the reference paper of Petetin et al. (2018).\n\nL4 IAGOS PBL-referenced profiles are available on the IAGOS data portal (http://iagos-data.fr) and are part of the IAGOS ancillary data. They are subject to the IAGOS data protocol.;The climatological vertical stratification of ozone (O3) and carbon monoxide (CO) within the planetary boundary layer (PBL) and at the interface with free troposphere (FT) was derived using all IAGOS (In-service Aircraft for a Global Observing System) and WOUDC (World Ozone and Ultraviolet Radiation Data Centre) vertical profiles available at northern mid-latitudes (25\u00b0N-60\u00b0N) between August 1994 and December 2016 (Petetin et al., 2018).\n\nThe methodology is the following :\n1) All profiles with a surface-based temperature inversion (i.e. increase of temperature with altitude starting from the surface) are discarded. \n2) All remaining profiles are then interpolated on a fixed vertical grid of 50 m vertical resolution between 0 and 4 km above ground level (i.e. 80 altitude levels). For each of these profiles, the PBL height is estimated as the base altitude of the first elevated temperature inversion (i.e. the altitude level above which temperature starts to increase with altitude). An upper limit of 4 km is fixed for the PBL height. In order to reduce uncertainties associated with data gaps, we discarded (i) all profiles with more than 25% of missing temperature data between 0 and 4 km (i.e. cumulated data gaps larger than 0.25x4000=2000 m), and/or (ii) all profiles with more than 4 missing data between the surface and the estimated PBL height (i.e. cumulated data gaps larger than 4x50=200 m). \n3) The profiles are expressed in the z/h vertical coordinate system where z is the altitude and h the PBL height estimate. O3 and CO mixing ratios are interpolated along z/h values ranging between 0 (the surface) and 2 (two times the PBL height) with a vertical resolution of of 0.05 (i.e. 40 altitude levels). All profiles with missing O3 or CO data are discarded. Then all the remaining profiles are averaged, which gives the so-called PBL-referenced profiles. This is done for the different seasons (DJF : December-January-February, MAM : March-April-May, JJA : June-July-August, SON : September-October-November, ANN : annual) and times of day (night\u00a0: sunset to sunrise, morning\u00a0: sunrise to solar noon, midday\u00a0: solar noon to 3 h past solar noon, afternoon\u00a0: 3 h past solar noon to sunset, daytime\u00a0: sunrise to sunset, all\u00a0: the whole day).\n\nA more complete description of the methodology as well as an analysis of the results is available in the reference paper of Petetin et al. (2018).\n\nL4 IAGOS PBL-referenced profiles are available on the IAGOS data portal (http://iagos-data.fr) and are part of the IAGOS ancillary data. They are subject to the IAGOS data protocol.;restricted;eng;Data produced by the European Research Infrastructure IAGOS.;CSV;180.0 -90.0;-180.0 90.0;http://www.iagos.org;http://iagos-data.fr/#CMSConsultPlace:PBL_PROFILES;http://dx.doi.org/10.25326/4;http://iagos-data.fr/images/logo_blue.png;http://iagos-data.fr/portal/rest/images/map:global:thumb;http://iagos-data.fr/portal/rest/image/storedById/6990116025497246148;http://iagos-data.fr/portal/rest/image/storedById/4641718511330911523",
-    "group": "iagos",
-    "groups": [
-        {
-            "name": "iagos"
-        }
-    ],
-    "name": "7148e61c-9127-560c-930e-925b6f13ced0",
-    "notes": [
-        "The climatological vertical stratification of ozone (O3) and carbon monoxide (CO) within the planetary boundary layer (PBL) and at the interface with free troposphere (FT) was derived using all IAGOS (In-service Aircraft for a Global Observing System) and WOUDC (World Ozone and Ultraviolet Radiation Data Centre) vertical profiles available at northern mid-latitudes (25\u00b0N-60\u00b0N) between August 1994 and December 2016 (Petetin et al., 2018).\n\nThe methodology is the following :\n1) All profiles with a surface-based temperature inversion (i.e. increase of temperature with altitude starting from the surface) are discarded. \n2) All remaining profiles are then interpolated on a fixed vertical grid of 50 m vertical resolution between 0 and 4 km above ground level (i.e. 80 altitude levels). For each of these profiles, the PBL height is estimated as the base altitude of the first elevated temperature inversion (i.e. the altitude level above which temperature starts to increase with altitude). An upper limit of 4 km is fixed for the PBL height. In order to reduce uncertainties associated with data gaps, we discarded (i) all profiles with more than 25% of missing temperature data between 0 and 4 km (i.e. cumulated data gaps larger than 0.25x4000=2000 m), and/or (ii) all profiles with more than 4 missing data between the surface and the estimated PBL height (i.e. cumulated data gaps larger than 4x50=200 m). \n3) The profiles are expressed in the z/h vertical coordinate system where z is the altitude and h the PBL height estimate. O3 and CO mixing ratios are interpolated along z/h values ranging between 0 (the surface) and 2 (two times the PBL height) with a vertical resolution of of 0.05 (i.e. 40 altitude levels). All profiles with missing O3 or CO data are discarded. Then all the remaining profiles are averaged, which gives the so-called PBL-referenced profiles. This is done for the different seasons (DJF : December-January-February, MAM : March-April-May, JJA : June-July-August, SON : September-October-November, ANN : annual) and times of day (night\u00a0: sunset to sunrise, morning\u00a0: sunrise to solar noon, midday\u00a0: solar noon to 3 h past solar noon, afternoon\u00a0: 3 h past solar noon to sunset, daytime\u00a0: sunrise to sunset, all\u00a0: the whole day).\n\nA more complete description of the methodology as well as an analysis of the results is available in the reference paper of Petetin et al. (2018).\n\nL4 IAGOS PBL-referenced profiles are available on the IAGOS data portal (http://iagos-data.fr) and are part of the IAGOS ancillary data. They are subject to the IAGOS data protocol."
-    ],
-    "oai_identifier": [
-        "7148e61c-9127-560c-930e-925b6f13ced0"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Atmospheric"
-        },
-        {
-            "name": "conditions"
-        },
-        {
-            "name": "IAGOS"
-        },
-        {
-            "name": "SEDOO"
-        },
-        {
-            "name": "AERIS"
-        },
-        {
-            "name": "climatologyMeteorologyAtmosphere"
-        }
-    ],
-    "title": [
-        "IAGOS PBL-referenced profiles of O3 and CO"
-    ],
-    "url": "http://iagos-data.fr/portal/rest/image/storedById/4641718511330911523"
-}
\ No newline at end of file
diff --git a/oaitestdata/iagos-oai_dc/SET_1/json/9b3ef7e7-a7f2-555f-9fe6-8536a15d438d.json b/oaitestdata/iagos-oai_dc/SET_1/json/9b3ef7e7-a7f2-555f-9fe6-8536a15d438d.json
deleted file mode 100644
index 628b937b..00000000
--- a/oaitestdata/iagos-oai_dc/SET_1/json/9b3ef7e7-a7f2-555f-9fe6-8536a15d438d.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "http://www.iagos.org"
-    ],
-    "DOI": "http://dx.doi.org/10.25326/3",
-    "DiscHierarchy": [
-        "4.4.1",
-        "Geosciences",
-        "Atmospheric Sciences"
-    ],
-    "Discipline": "Atmospheric Sciences",
-    "Format": [
-        "NetCDF"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://catalogue2.sedoo.fr/geonetwork/srv/eng/csw-iagos?verb=GetRecord&metadataPrefix=oai_dc&identifier=9b3ef7e7-a7f2-555f-9fe6-8536a15d438d",
-    "PublicationTimestamp": "2018-09-06T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "IAGOS"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "restricted"
-    ],
-    "SpatialCoverage": [
-        "180.0 -90.0",
-        "-180.0 90.0"
-    ],
-    "fulltext": "4d3be8dd-c41a-4f35-8ba6-722cf12e2de3;2018-09-06T18:17:38.497+02:00;IAGOS ancillary data (L4) - CO contributions to the aircraft measurements;dataset;Atmospheric conditions;IAGOS;SEDOO;AERIS;climatologyMeteorologyAtmosphere;NetCDF;In order to help analyzing the IAGOS carbon monoxide (CO) observations and understanding the processes driving their evolutions, we provide ancillary parameters calculated with SOFT-IO (Sauvage et al., 2017; http://dx.doi.org/10.25326/2) along aircraft observations.\n\nCO contribution is defined as follow. CO mixing ratio is calculated for each IAGOS observations (every 0.5\u00b0 in latitude or longitude at cruising altitude; every 10hPa during ascent or descent of the plane) and sorted by source origin (biomass burning and anthropogenic origin, and for 14 geographical origins, see Fig.1). CO total contribution is then the sum of each CO source origin or the sum of each CO geographical origin and can be used to interpret IAGOS CO measurements. Some examples are highlighted in Sauvage et al., 2017 for individual flights (their Fig.5 to Fig.8).\n\nCO is calculated so far for different up-to-date emissions inventories (ECCAD and MACCity for anthropogenic emissions; GFED4 and GFAS v1.2 for biomass burning emissions) available in the ECCAD project (http://eccad.aeris-data.fr/) and since the beginning of CO measurements in IAGOS (end of 2001) up to now.\n\nL4 IAGOS CO contributions are available on the IAGOS data portal (http://iagos-data.fr) and are part of the IAGOS ancillary data (http://iagos-data.fr/#L4Place:).They are subject to the IAGOS data protocol (http://iagos-data.fr/#RegisterPlace:);In order to help analyzing the IAGOS carbon monoxide (CO) observations and understanding the processes driving their evolutions, we provide ancillary parameters calculated with SOFT-IO (Sauvage et al., 2017; http://dx.doi.org/10.25326/2) along aircraft observations.\n\nCO contribution is defined as follow. CO mixing ratio is calculated for each IAGOS observations (every 0.5\u00b0 in latitude or longitude at cruising altitude; every 10hPa during ascent or descent of the plane) and sorted by source origin (biomass burning and anthropogenic origin, and for 14 geographical origins, see Fig.1). CO total contribution is then the sum of each CO source origin or the sum of each CO geographical origin and can be used to interpret IAGOS CO measurements. Some examples are highlighted in Sauvage et al., 2017 for individual flights (their Fig.5 to Fig.8).\n\nCO is calculated so far for different up-to-date emissions inventories (ECCAD and MACCity for anthropogenic emissions; GFED4 and GFAS v1.2 for biomass burning emissions) available in the ECCAD project (http://eccad.aeris-data.fr/) and since the beginning of CO measurements in IAGOS (end of 2001) up to now.\n\nL4 IAGOS CO contributions are available on the IAGOS data portal (http://iagos-data.fr) and are part of the IAGOS ancillary data (http://iagos-data.fr/#L4Place:).They are subject to the IAGOS data protocol (http://iagos-data.fr/#RegisterPlace:);restricted;eng;Data produced by the European Research Infrastructure IAGOS.;NetCDF;180.0 -90.0;-180.0 90.0;http://www.iagos.org;http://iagos-data.fr/#CMSConsultPlace:ANCILLARY_DATA;http://dx.doi.org/10.25326/3;http://iagos-data.fr/images/logo_blue.png;http://iagos-data.fr/portal/rest/images/map:global:thumb;http://iagos-data.fr/portal/rest/image/storedById/6871350981954295755",
-    "group": "iagos",
-    "groups": [
-        {
-            "name": "iagos"
-        }
-    ],
-    "name": "9b3ef7e7-a7f2-555f-9fe6-8536a15d438d",
-    "notes": [
-        "In order to help analyzing the IAGOS carbon monoxide (CO) observations and understanding the processes driving their evolutions, we provide ancillary parameters calculated with SOFT-IO (Sauvage et al., 2017; http://dx.doi.org/10.25326/2) along aircraft observations.\n\nCO contribution is defined as follow. CO mixing ratio is calculated for each IAGOS observations (every 0.5\u00b0 in latitude or longitude at cruising altitude; every 10hPa during ascent or descent of the plane) and sorted by source origin (biomass burning and anthropogenic origin, and for 14 geographical origins, see Fig.1). CO total contribution is then the sum of each CO source origin or the sum of each CO geographical origin and can be used to interpret IAGOS CO measurements. Some examples are highlighted in Sauvage et al., 2017 for individual flights (their Fig.5 to Fig.8).\n\nCO is calculated so far for different up-to-date emissions inventories (ECCAD and MACCity for anthropogenic emissions; GFED4 and GFAS v1.2 for biomass burning emissions) available in the ECCAD project (http://eccad.aeris-data.fr/) and since the beginning of CO measurements in IAGOS (end of 2001) up to now.\n\nL4 IAGOS CO contributions are available on the IAGOS data portal (http://iagos-data.fr) and are part of the IAGOS ancillary data (http://iagos-data.fr/#L4Place:).They are subject to the IAGOS data protocol (http://iagos-data.fr/#RegisterPlace:)"
-    ],
-    "oai_identifier": [
-        "9b3ef7e7-a7f2-555f-9fe6-8536a15d438d"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Atmospheric"
-        },
-        {
-            "name": "conditions"
-        },
-        {
-            "name": "IAGOS"
-        },
-        {
-            "name": "SEDOO"
-        },
-        {
-            "name": "AERIS"
-        },
-        {
-            "name": "climatologyMeteorologyAtmosphere"
-        }
-    ],
-    "title": [
-        "IAGOS ancillary data (L4) - CO contributions to the aircraft measurements"
-    ],
-    "url": "http://iagos-data.fr/portal/rest/image/storedById/6871350981954295755"
-}
\ No newline at end of file
diff --git a/oaitestdata/iagos-oai_dc/SET_1/json/b73648f1-2f43-52c8-b4e4-f071f16f4e61.json b/oaitestdata/iagos-oai_dc/SET_1/json/b73648f1-2f43-52c8-b4e4-f071f16f4e61.json
deleted file mode 100644
index e7329d1e..00000000
--- a/oaitestdata/iagos-oai_dc/SET_1/json/b73648f1-2f43-52c8-b4e4-f071f16f4e61.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "http://www.iagos.org"
-    ],
-    "DOI": "http://dx.doi.org/null",
-    "DiscHierarchy": [
-        "4.4.1",
-        "Geosciences",
-        "Atmospheric Sciences"
-    ],
-    "Discipline": "Atmospheric Sciences",
-    "Format": [
-        "NetCDF"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://catalogue2.sedoo.fr/geonetwork/srv/eng/csw-iagos?verb=GetRecord&metadataPrefix=oai_dc&identifier=b73648f1-2f43-52c8-b4e4-f071f16f4e61",
-    "PublicationTimestamp": "2018-09-06T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "IAGOS"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "restricted"
-    ],
-    "SpatialCoverage": [
-        "180.0 -90.0",
-        "-180.0 90.0"
-    ],
-    "fulltext": "c570d452-0f05-4227-bed4-c1905c2951eb;2018-09-06T18:17:40.891+02:00;IAGOS footprints;dataset;Atmospheric conditions;IAGOS;SEDOO;AERIS;climatologyMeteorologyAtmosphere;NetCDF;This dataset provides footprints for all the vertical profiles of carbon monoxyde over the airports visited by the IAGOS fleet. The footprints are based on model simulations of the up-stream influences on the observation location. Theses footprints are coupled to surface flux maps in order to derive tracer concentration changes at the airport.;This dataset provides footprints for all the vertical profiles of carbon monoxyde over the airports visited by the IAGOS fleet. The footprints are based on model simulations of the up-stream influences on the observation location. Theses footprints are coupled to surface flux maps in order to derive tracer concentration changes at the airport.;restricted;eng;Data produced by the European Research Infrastructure IAGOS.;NetCDF;180.0 -90.0;-180.0 90.0;http://www.iagos.org;http://iagos-data.fr/#CMSConsultPlace:ANCILLARY_DATA;http://dx.doi.org/null;http://iagos-data.fr/images/logo_blue.png;http://iagos-data.fr/portal/rest/images/map:global:thumb",
-    "group": "iagos",
-    "groups": [
-        {
-            "name": "iagos"
-        }
-    ],
-    "name": "b73648f1-2f43-52c8-b4e4-f071f16f4e61",
-    "notes": [
-        "This dataset provides footprints for all the vertical profiles of carbon monoxyde over the airports visited by the IAGOS fleet. The footprints are based on model simulations of the up-stream influences on the observation location. Theses footprints are coupled to surface flux maps in order to derive tracer concentration changes at the airport."
-    ],
-    "oai_identifier": [
-        "b73648f1-2f43-52c8-b4e4-f071f16f4e61"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Atmospheric"
-        },
-        {
-            "name": "conditions"
-        },
-        {
-            "name": "IAGOS"
-        },
-        {
-            "name": "SEDOO"
-        },
-        {
-            "name": "AERIS"
-        },
-        {
-            "name": "climatologyMeteorologyAtmosphere"
-        }
-    ],
-    "title": [
-        "IAGOS footprints"
-    ],
-    "url": "http://iagos-data.fr/portal/rest/images/map:global:thumb"
-}
\ No newline at end of file
diff --git a/oaitestdata/icos-json/SET_1/json/0a1f4750-27e3-51db-93eb-a76522cf2e43.json b/oaitestdata/icos-json/SET_1/json/0a1f4750-27e3-51db-93eb-a76522cf2e43.json
deleted file mode 100644
index 6024040d..00000000
--- a/oaitestdata/icos-json/SET_1/json/0a1f4750-27e3-51db-93eb-a76522cf2e43.json
+++ /dev/null
@@ -1,30 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Atmospheric_Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://meta.icos-cp.eu/sparqlclient//dataset/0a1f4750-27e3-51db-93eb-a76522cf2e43",
-    "Publisher": [
-        "Atmosphere thematic center"
-    ],
-    "ResourceType": [
-        "http://www.w3.org/2001/XMLSchema#integer"
-    ],
-    "group": "icos",
-    "groups": [
-        {
-            "name": "icos"
-        }
-    ],
-    "name": "0a1f4750-27e3-51db-93eb-a76522cf2e43",
-    "oai_identifier": [
-        "0a1f4750-27e3-51db-93eb-a76522cf2e43"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/icos-json/SET_1/json/0a3936f2-78b5-5090-884b-7fe1bd01a829.json b/oaitestdata/icos-json/SET_1/json/0a3936f2-78b5-5090-884b-7fe1bd01a829.json
deleted file mode 100644
index 5153d968..00000000
--- a/oaitestdata/icos-json/SET_1/json/0a3936f2-78b5-5090-884b-7fe1bd01a829.json
+++ /dev/null
@@ -1,30 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Atmospheric_Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://meta.icos-cp.eu/sparqlclient//dataset/0a3936f2-78b5-5090-884b-7fe1bd01a829",
-    "Publisher": [
-        "Atmosphere thematic center"
-    ],
-    "ResourceType": [
-        "http://www.w3.org/2001/XMLSchema#integer"
-    ],
-    "group": "icos",
-    "groups": [
-        {
-            "name": "icos"
-        }
-    ],
-    "name": "0a3936f2-78b5-5090-884b-7fe1bd01a829",
-    "oai_identifier": [
-        "0a3936f2-78b5-5090-884b-7fe1bd01a829"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/icos-json/SET_1/json/0aba8ddc-ba48-5ab2-96c4-14a594e5732d.json b/oaitestdata/icos-json/SET_1/json/0aba8ddc-ba48-5ab2-96c4-14a594e5732d.json
deleted file mode 100644
index c5dc0abd..00000000
--- a/oaitestdata/icos-json/SET_1/json/0aba8ddc-ba48-5ab2-96c4-14a594e5732d.json
+++ /dev/null
@@ -1,30 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Atmospheric_Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://meta.icos-cp.eu/sparqlclient//dataset/0aba8ddc-ba48-5ab2-96c4-14a594e5732d",
-    "Publisher": [
-        "Atmosphere thematic center"
-    ],
-    "ResourceType": [
-        "http://www.w3.org/2001/XMLSchema#integer"
-    ],
-    "group": "icos",
-    "groups": [
-        {
-            "name": "icos"
-        }
-    ],
-    "name": "0aba8ddc-ba48-5ab2-96c4-14a594e5732d",
-    "oai_identifier": [
-        "0aba8ddc-ba48-5ab2-96c4-14a594e5732d"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/icos-json/SET_1/json/0b286d53-1c99-5d99-8b4b-df500e699857.json b/oaitestdata/icos-json/SET_1/json/0b286d53-1c99-5d99-8b4b-df500e699857.json
deleted file mode 100644
index 69382364..00000000
--- a/oaitestdata/icos-json/SET_1/json/0b286d53-1c99-5d99-8b4b-df500e699857.json
+++ /dev/null
@@ -1,30 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Atmospheric_Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://meta.icos-cp.eu/sparqlclient//dataset/0b286d53-1c99-5d99-8b4b-df500e699857",
-    "Publisher": [
-        "Atmosphere thematic center"
-    ],
-    "ResourceType": [
-        "http://www.w3.org/2001/XMLSchema#integer"
-    ],
-    "group": "icos",
-    "groups": [
-        {
-            "name": "icos"
-        }
-    ],
-    "name": "0b286d53-1c99-5d99-8b4b-df500e699857",
-    "oai_identifier": [
-        "0b286d53-1c99-5d99-8b4b-df500e699857"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/icos-json/SET_1/json/0b53d2b7-f6da-51a2-8f06-81a157784b72.json b/oaitestdata/icos-json/SET_1/json/0b53d2b7-f6da-51a2-8f06-81a157784b72.json
deleted file mode 100644
index 6eda6437..00000000
--- a/oaitestdata/icos-json/SET_1/json/0b53d2b7-f6da-51a2-8f06-81a157784b72.json
+++ /dev/null
@@ -1,30 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Atmospheric_Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://meta.icos-cp.eu/sparqlclient//dataset/0b53d2b7-f6da-51a2-8f06-81a157784b72",
-    "Publisher": [
-        "Hyytiala"
-    ],
-    "ResourceType": [
-        "http://www.w3.org/2001/XMLSchema#integer"
-    ],
-    "group": "icos",
-    "groups": [
-        {
-            "name": "icos"
-        }
-    ],
-    "name": "0b53d2b7-f6da-51a2-8f06-81a157784b72",
-    "oai_identifier": [
-        "0b53d2b7-f6da-51a2-8f06-81a157784b72"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/icos-json/SET_1/json/0b7f2b88-58de-5af9-b9af-f26cbd75ac20.json b/oaitestdata/icos-json/SET_1/json/0b7f2b88-58de-5af9-b9af-f26cbd75ac20.json
deleted file mode 100644
index 54d62a20..00000000
--- a/oaitestdata/icos-json/SET_1/json/0b7f2b88-58de-5af9-b9af-f26cbd75ac20.json
+++ /dev/null
@@ -1,30 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Atmospheric_Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://meta.icos-cp.eu/sparqlclient//dataset/0b7f2b88-58de-5af9-b9af-f26cbd75ac20",
-    "Publisher": [
-        "San Rossore 2"
-    ],
-    "ResourceType": [
-        "http://www.w3.org/2001/XMLSchema#integer"
-    ],
-    "group": "icos",
-    "groups": [
-        {
-            "name": "icos"
-        }
-    ],
-    "name": "0b7f2b88-58de-5af9-b9af-f26cbd75ac20",
-    "oai_identifier": [
-        "0b7f2b88-58de-5af9-b9af-f26cbd75ac20"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/icos-json/SET_1/json/0b96bbe4-8cb4-5b3d-8002-07ebd7ee202d.json b/oaitestdata/icos-json/SET_1/json/0b96bbe4-8cb4-5b3d-8002-07ebd7ee202d.json
deleted file mode 100644
index f770d254..00000000
--- a/oaitestdata/icos-json/SET_1/json/0b96bbe4-8cb4-5b3d-8002-07ebd7ee202d.json
+++ /dev/null
@@ -1,30 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Atmospheric_Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://meta.icos-cp.eu/sparqlclient//dataset/0b96bbe4-8cb4-5b3d-8002-07ebd7ee202d",
-    "Publisher": [
-        "San Rossore 2"
-    ],
-    "ResourceType": [
-        "http://www.w3.org/2001/XMLSchema#integer"
-    ],
-    "group": "icos",
-    "groups": [
-        {
-            "name": "icos"
-        }
-    ],
-    "name": "0b96bbe4-8cb4-5b3d-8002-07ebd7ee202d",
-    "oai_identifier": [
-        "0b96bbe4-8cb4-5b3d-8002-07ebd7ee202d"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/icos-json/SET_1/json/0c00007a-a7ff-549f-baa6-1228b8866e95.json b/oaitestdata/icos-json/SET_1/json/0c00007a-a7ff-549f-baa6-1228b8866e95.json
deleted file mode 100644
index 15b7f561..00000000
--- a/oaitestdata/icos-json/SET_1/json/0c00007a-a7ff-549f-baa6-1228b8866e95.json
+++ /dev/null
@@ -1,30 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Atmospheric_Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://meta.icos-cp.eu/sparqlclient//dataset/0c00007a-a7ff-549f-baa6-1228b8866e95",
-    "Publisher": [
-        "Atmosphere thematic center"
-    ],
-    "ResourceType": [
-        "http://www.w3.org/2001/XMLSchema#integer"
-    ],
-    "group": "icos",
-    "groups": [
-        {
-            "name": "icos"
-        }
-    ],
-    "name": "0c00007a-a7ff-549f-baa6-1228b8866e95",
-    "oai_identifier": [
-        "0c00007a-a7ff-549f-baa6-1228b8866e95"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/icos-json/SET_1/json/0cbf6979-f892-53b6-baaa-5a2d23035fe4.json b/oaitestdata/icos-json/SET_1/json/0cbf6979-f892-53b6-baaa-5a2d23035fe4.json
deleted file mode 100644
index 4f9b3e57..00000000
--- a/oaitestdata/icos-json/SET_1/json/0cbf6979-f892-53b6-baaa-5a2d23035fe4.json
+++ /dev/null
@@ -1,30 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Atmospheric_Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://meta.icos-cp.eu/sparqlclient//dataset/0cbf6979-f892-53b6-baaa-5a2d23035fe4",
-    "Publisher": [
-        "Atmosphere thematic center"
-    ],
-    "ResourceType": [
-        "http://www.w3.org/2001/XMLSchema#integer"
-    ],
-    "group": "icos",
-    "groups": [
-        {
-            "name": "icos"
-        }
-    ],
-    "name": "0cbf6979-f892-53b6-baaa-5a2d23035fe4",
-    "oai_identifier": [
-        "0cbf6979-f892-53b6-baaa-5a2d23035fe4"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/icos-json/SET_1/json/0d1e27af-ba99-58d6-a704-9ee2a1366cfe.json b/oaitestdata/icos-json/SET_1/json/0d1e27af-ba99-58d6-a704-9ee2a1366cfe.json
deleted file mode 100644
index 5d5b7b43..00000000
--- a/oaitestdata/icos-json/SET_1/json/0d1e27af-ba99-58d6-a704-9ee2a1366cfe.json
+++ /dev/null
@@ -1,30 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Atmospheric_Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://meta.icos-cp.eu/sparqlclient//dataset/0d1e27af-ba99-58d6-a704-9ee2a1366cfe",
-    "Publisher": [
-        "Atmosphere thematic center"
-    ],
-    "ResourceType": [
-        "http://www.w3.org/2001/XMLSchema#integer"
-    ],
-    "group": "icos",
-    "groups": [
-        {
-            "name": "icos"
-        }
-    ],
-    "name": "0d1e27af-ba99-58d6-a704-9ee2a1366cfe",
-    "oai_identifier": [
-        "0d1e27af-ba99-58d6-a704-9ee2a1366cfe"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/icos-json/SET_1/json/0d3e0ec8-bfb5-5c95-9be8-f97dfa8e10e1.json b/oaitestdata/icos-json/SET_1/json/0d3e0ec8-bfb5-5c95-9be8-f97dfa8e10e1.json
deleted file mode 100644
index e9af73d4..00000000
--- a/oaitestdata/icos-json/SET_1/json/0d3e0ec8-bfb5-5c95-9be8-f97dfa8e10e1.json
+++ /dev/null
@@ -1,30 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Atmospheric_Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://meta.icos-cp.eu/sparqlclient//dataset/0d3e0ec8-bfb5-5c95-9be8-f97dfa8e10e1",
-    "Publisher": [
-        "Atmosphere thematic center"
-    ],
-    "ResourceType": [
-        "http://www.w3.org/2001/XMLSchema#integer"
-    ],
-    "group": "icos",
-    "groups": [
-        {
-            "name": "icos"
-        }
-    ],
-    "name": "0d3e0ec8-bfb5-5c95-9be8-f97dfa8e10e1",
-    "oai_identifier": [
-        "0d3e0ec8-bfb5-5c95-9be8-f97dfa8e10e1"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/icos-json/SET_1/json/0d5ac3ee-1336-509b-aead-1f7bd8b07600.json b/oaitestdata/icos-json/SET_1/json/0d5ac3ee-1336-509b-aead-1f7bd8b07600.json
deleted file mode 100644
index 45962173..00000000
--- a/oaitestdata/icos-json/SET_1/json/0d5ac3ee-1336-509b-aead-1f7bd8b07600.json
+++ /dev/null
@@ -1,30 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Atmospheric_Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://meta.icos-cp.eu/sparqlclient//dataset/0d5ac3ee-1336-509b-aead-1f7bd8b07600",
-    "Publisher": [
-        "Atmosphere thematic center"
-    ],
-    "ResourceType": [
-        "http://www.w3.org/2001/XMLSchema#integer"
-    ],
-    "group": "icos",
-    "groups": [
-        {
-            "name": "icos"
-        }
-    ],
-    "name": "0d5ac3ee-1336-509b-aead-1f7bd8b07600",
-    "oai_identifier": [
-        "0d5ac3ee-1336-509b-aead-1f7bd8b07600"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/icos-json/SET_1/json/0d7fe556-e52d-56b4-bd6f-9be991445e2a.json b/oaitestdata/icos-json/SET_1/json/0d7fe556-e52d-56b4-bd6f-9be991445e2a.json
deleted file mode 100644
index ab439440..00000000
--- a/oaitestdata/icos-json/SET_1/json/0d7fe556-e52d-56b4-bd6f-9be991445e2a.json
+++ /dev/null
@@ -1,30 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Atmospheric_Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://meta.icos-cp.eu/sparqlclient//dataset/0d7fe556-e52d-56b4-bd6f-9be991445e2a",
-    "Publisher": [
-        "Siikaneva"
-    ],
-    "ResourceType": [
-        "http://www.w3.org/2001/XMLSchema#integer"
-    ],
-    "group": "icos",
-    "groups": [
-        {
-            "name": "icos"
-        }
-    ],
-    "name": "0d7fe556-e52d-56b4-bd6f-9be991445e2a",
-    "oai_identifier": [
-        "0d7fe556-e52d-56b4-bd6f-9be991445e2a"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/icos-json/SET_1/json/0db0883d-ab57-5989-97b0-a7fb106f6091.json b/oaitestdata/icos-json/SET_1/json/0db0883d-ab57-5989-97b0-a7fb106f6091.json
deleted file mode 100644
index 402dfe24..00000000
--- a/oaitestdata/icos-json/SET_1/json/0db0883d-ab57-5989-97b0-a7fb106f6091.json
+++ /dev/null
@@ -1,30 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Atmospheric_Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://meta.icos-cp.eu/sparqlclient//dataset/0db0883d-ab57-5989-97b0-a7fb106f6091",
-    "Publisher": [
-        "Atmosphere thematic center"
-    ],
-    "ResourceType": [
-        "http://www.w3.org/2001/XMLSchema#integer"
-    ],
-    "group": "icos",
-    "groups": [
-        {
-            "name": "icos"
-        }
-    ],
-    "name": "0db0883d-ab57-5989-97b0-a7fb106f6091",
-    "oai_identifier": [
-        "0db0883d-ab57-5989-97b0-a7fb106f6091"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/icos-json/SET_1/json/0db59c2b-d6ea-5728-b673-ab70cb039d0a.json b/oaitestdata/icos-json/SET_1/json/0db59c2b-d6ea-5728-b673-ab70cb039d0a.json
deleted file mode 100644
index f9840fae..00000000
--- a/oaitestdata/icos-json/SET_1/json/0db59c2b-d6ea-5728-b673-ab70cb039d0a.json
+++ /dev/null
@@ -1,30 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Atmospheric_Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://meta.icos-cp.eu/sparqlclient//dataset/0db59c2b-d6ea-5728-b673-ab70cb039d0a",
-    "Publisher": [
-        "Atmosphere thematic center"
-    ],
-    "ResourceType": [
-        "http://www.w3.org/2001/XMLSchema#integer"
-    ],
-    "group": "icos",
-    "groups": [
-        {
-            "name": "icos"
-        }
-    ],
-    "name": "0db59c2b-d6ea-5728-b673-ab70cb039d0a",
-    "oai_identifier": [
-        "0db59c2b-d6ea-5728-b673-ab70cb039d0a"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/icos-json/SET_1/json/0ddf0017-b331-576f-83b9-413e2205ec0a.json b/oaitestdata/icos-json/SET_1/json/0ddf0017-b331-576f-83b9-413e2205ec0a.json
deleted file mode 100644
index 0413a2e4..00000000
--- a/oaitestdata/icos-json/SET_1/json/0ddf0017-b331-576f-83b9-413e2205ec0a.json
+++ /dev/null
@@ -1,30 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Atmospheric_Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://meta.icos-cp.eu/sparqlclient//dataset/0ddf0017-b331-576f-83b9-413e2205ec0a",
-    "Publisher": [
-        "Atmosphere thematic center"
-    ],
-    "ResourceType": [
-        "http://www.w3.org/2001/XMLSchema#integer"
-    ],
-    "group": "icos",
-    "groups": [
-        {
-            "name": "icos"
-        }
-    ],
-    "name": "0ddf0017-b331-576f-83b9-413e2205ec0a",
-    "oai_identifier": [
-        "0ddf0017-b331-576f-83b9-413e2205ec0a"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/icos-json/SET_1/json/0e05f9b6-ec4f-58bd-89d5-8a26a9dbf221.json b/oaitestdata/icos-json/SET_1/json/0e05f9b6-ec4f-58bd-89d5-8a26a9dbf221.json
deleted file mode 100644
index 6c5d677b..00000000
--- a/oaitestdata/icos-json/SET_1/json/0e05f9b6-ec4f-58bd-89d5-8a26a9dbf221.json
+++ /dev/null
@@ -1,30 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Atmospheric_Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://meta.icos-cp.eu/sparqlclient//dataset/0e05f9b6-ec4f-58bd-89d5-8a26a9dbf221",
-    "Publisher": [
-        "San Rossore 2"
-    ],
-    "ResourceType": [
-        "http://www.w3.org/2001/XMLSchema#integer"
-    ],
-    "group": "icos",
-    "groups": [
-        {
-            "name": "icos"
-        }
-    ],
-    "name": "0e05f9b6-ec4f-58bd-89d5-8a26a9dbf221",
-    "oai_identifier": [
-        "0e05f9b6-ec4f-58bd-89d5-8a26a9dbf221"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/icos-json/SET_1/json/0e2f5d96-8c95-5866-843e-cc594fcb3c08.json b/oaitestdata/icos-json/SET_1/json/0e2f5d96-8c95-5866-843e-cc594fcb3c08.json
deleted file mode 100644
index bcea5da7..00000000
--- a/oaitestdata/icos-json/SET_1/json/0e2f5d96-8c95-5866-843e-cc594fcb3c08.json
+++ /dev/null
@@ -1,30 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Atmospheric_Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://meta.icos-cp.eu/sparqlclient//dataset/0e2f5d96-8c95-5866-843e-cc594fcb3c08",
-    "Publisher": [
-        "Atmosphere thematic center"
-    ],
-    "ResourceType": [
-        "http://www.w3.org/2001/XMLSchema#integer"
-    ],
-    "group": "icos",
-    "groups": [
-        {
-            "name": "icos"
-        }
-    ],
-    "name": "0e2f5d96-8c95-5866-843e-cc594fcb3c08",
-    "oai_identifier": [
-        "0e2f5d96-8c95-5866-843e-cc594fcb3c08"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/icos-json/SET_1/json/0e572e2c-acc1-5fdb-b86e-a86219806813.json b/oaitestdata/icos-json/SET_1/json/0e572e2c-acc1-5fdb-b86e-a86219806813.json
deleted file mode 100644
index 060b8891..00000000
--- a/oaitestdata/icos-json/SET_1/json/0e572e2c-acc1-5fdb-b86e-a86219806813.json
+++ /dev/null
@@ -1,30 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Atmospheric_Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://meta.icos-cp.eu/sparqlclient//dataset/0e572e2c-acc1-5fdb-b86e-a86219806813",
-    "Publisher": [
-        "Atmosphere thematic center"
-    ],
-    "ResourceType": [
-        "http://www.w3.org/2001/XMLSchema#integer"
-    ],
-    "group": "icos",
-    "groups": [
-        {
-            "name": "icos"
-        }
-    ],
-    "name": "0e572e2c-acc1-5fdb-b86e-a86219806813",
-    "oai_identifier": [
-        "0e572e2c-acc1-5fdb-b86e-a86219806813"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/icos-json/SET_1/json/0ebaf970-555f-59d3-ae1b-217d2694c3c6.json b/oaitestdata/icos-json/SET_1/json/0ebaf970-555f-59d3-ae1b-217d2694c3c6.json
deleted file mode 100644
index 1c72da6c..00000000
--- a/oaitestdata/icos-json/SET_1/json/0ebaf970-555f-59d3-ae1b-217d2694c3c6.json
+++ /dev/null
@@ -1,30 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Atmospheric_Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://meta.icos-cp.eu/sparqlclient//dataset/0ebaf970-555f-59d3-ae1b-217d2694c3c6",
-    "Publisher": [
-        "Hyltemossa"
-    ],
-    "ResourceType": [
-        "http://www.w3.org/2001/XMLSchema#integer"
-    ],
-    "group": "icos",
-    "groups": [
-        {
-            "name": "icos"
-        }
-    ],
-    "name": "0ebaf970-555f-59d3-ae1b-217d2694c3c6",
-    "oai_identifier": [
-        "0ebaf970-555f-59d3-ae1b-217d2694c3c6"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/icos-json/SET_1/json/0ed1eadb-3896-5e5d-95b2-350cb51ae90b.json b/oaitestdata/icos-json/SET_1/json/0ed1eadb-3896-5e5d-95b2-350cb51ae90b.json
deleted file mode 100644
index 36cb3e46..00000000
--- a/oaitestdata/icos-json/SET_1/json/0ed1eadb-3896-5e5d-95b2-350cb51ae90b.json
+++ /dev/null
@@ -1,30 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Atmospheric_Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://meta.icos-cp.eu/sparqlclient//dataset/0ed1eadb-3896-5e5d-95b2-350cb51ae90b",
-    "Publisher": [
-        "Siikaneva"
-    ],
-    "ResourceType": [
-        "http://www.w3.org/2001/XMLSchema#integer"
-    ],
-    "group": "icos",
-    "groups": [
-        {
-            "name": "icos"
-        }
-    ],
-    "name": "0ed1eadb-3896-5e5d-95b2-350cb51ae90b",
-    "oai_identifier": [
-        "0ed1eadb-3896-5e5d-95b2-350cb51ae90b"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/icos-json/SET_1/json/0eebd29a-46a6-5079-ad51-2724eade1227.json b/oaitestdata/icos-json/SET_1/json/0eebd29a-46a6-5079-ad51-2724eade1227.json
deleted file mode 100644
index b1ca8f5c..00000000
--- a/oaitestdata/icos-json/SET_1/json/0eebd29a-46a6-5079-ad51-2724eade1227.json
+++ /dev/null
@@ -1,30 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Atmospheric_Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://meta.icos-cp.eu/sparqlclient//dataset/0eebd29a-46a6-5079-ad51-2724eade1227",
-    "Publisher": [
-        "Atmosphere thematic center"
-    ],
-    "ResourceType": [
-        "http://www.w3.org/2001/XMLSchema#integer"
-    ],
-    "group": "icos",
-    "groups": [
-        {
-            "name": "icos"
-        }
-    ],
-    "name": "0eebd29a-46a6-5079-ad51-2724eade1227",
-    "oai_identifier": [
-        "0eebd29a-46a6-5079-ad51-2724eade1227"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/icos-json/SET_1/json/0ef2a980-5973-597c-a85d-33b4350ebb9b.json b/oaitestdata/icos-json/SET_1/json/0ef2a980-5973-597c-a85d-33b4350ebb9b.json
deleted file mode 100644
index 956a9494..00000000
--- a/oaitestdata/icos-json/SET_1/json/0ef2a980-5973-597c-a85d-33b4350ebb9b.json
+++ /dev/null
@@ -1,30 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Atmospheric_Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://meta.icos-cp.eu/sparqlclient//dataset/0ef2a980-5973-597c-a85d-33b4350ebb9b",
-    "Publisher": [
-        "San Rossore 2"
-    ],
-    "ResourceType": [
-        "http://www.w3.org/2001/XMLSchema#integer"
-    ],
-    "group": "icos",
-    "groups": [
-        {
-            "name": "icos"
-        }
-    ],
-    "name": "0ef2a980-5973-597c-a85d-33b4350ebb9b",
-    "oai_identifier": [
-        "0ef2a980-5973-597c-a85d-33b4350ebb9b"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/icos-json/SET_1/json/0fa4ff76-090d-5426-95d9-9715d8e5566b.json b/oaitestdata/icos-json/SET_1/json/0fa4ff76-090d-5426-95d9-9715d8e5566b.json
deleted file mode 100644
index 975c9f5e..00000000
--- a/oaitestdata/icos-json/SET_1/json/0fa4ff76-090d-5426-95d9-9715d8e5566b.json
+++ /dev/null
@@ -1,30 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Atmospheric_Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://meta.icos-cp.eu/sparqlclient//dataset/0fa4ff76-090d-5426-95d9-9715d8e5566b",
-    "Publisher": [
-        "Atmosphere thematic center"
-    ],
-    "ResourceType": [
-        "http://www.w3.org/2001/XMLSchema#integer"
-    ],
-    "group": "icos",
-    "groups": [
-        {
-            "name": "icos"
-        }
-    ],
-    "name": "0fa4ff76-090d-5426-95d9-9715d8e5566b",
-    "oai_identifier": [
-        "0fa4ff76-090d-5426-95d9-9715d8e5566b"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/icos-json/SET_1/json/0fb4a829-f3a6-59b3-bce6-c26ab4a5c0fe.json b/oaitestdata/icos-json/SET_1/json/0fb4a829-f3a6-59b3-bce6-c26ab4a5c0fe.json
deleted file mode 100644
index a1a0bab8..00000000
--- a/oaitestdata/icos-json/SET_1/json/0fb4a829-f3a6-59b3-bce6-c26ab4a5c0fe.json
+++ /dev/null
@@ -1,30 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Atmospheric_Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://meta.icos-cp.eu/sparqlclient//dataset/0fb4a829-f3a6-59b3-bce6-c26ab4a5c0fe",
-    "Publisher": [
-        "Atmosphere thematic center"
-    ],
-    "ResourceType": [
-        "http://www.w3.org/2001/XMLSchema#integer"
-    ],
-    "group": "icos",
-    "groups": [
-        {
-            "name": "icos"
-        }
-    ],
-    "name": "0fb4a829-f3a6-59b3-bce6-c26ab4a5c0fe",
-    "oai_identifier": [
-        "0fb4a829-f3a6-59b3-bce6-c26ab4a5c0fe"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/icos-json/SET_1/json/0ffe5b0d-2945-5b2e-9089-c58969a9b6a5.json b/oaitestdata/icos-json/SET_1/json/0ffe5b0d-2945-5b2e-9089-c58969a9b6a5.json
deleted file mode 100644
index f7c00cc7..00000000
--- a/oaitestdata/icos-json/SET_1/json/0ffe5b0d-2945-5b2e-9089-c58969a9b6a5.json
+++ /dev/null
@@ -1,30 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Atmospheric_Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://meta.icos-cp.eu/sparqlclient//dataset/0ffe5b0d-2945-5b2e-9089-c58969a9b6a5",
-    "Publisher": [
-        "Atmosphere thematic center"
-    ],
-    "ResourceType": [
-        "http://www.w3.org/2001/XMLSchema#integer"
-    ],
-    "group": "icos",
-    "groups": [
-        {
-            "name": "icos"
-        }
-    ],
-    "name": "0ffe5b0d-2945-5b2e-9089-c58969a9b6a5",
-    "oai_identifier": [
-        "0ffe5b0d-2945-5b2e-9089-c58969a9b6a5"
-    ],
-    "state": "active",
-    "title": "Not stated"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/00afc6ee-df51-5f89-b3d7-ad07745aad90.json b/oaitestdata/ist-oai_dc/SET_1/json/00afc6ee-df51-5f89-b3d7-ad07745aad90.json
deleted file mode 100644
index 02f8fe55..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/00afc6ee-df51-5f89-b3d7-ad07745aad90.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:57",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "archive"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:57",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/57/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Jug, Florian",
-        "Kainmueller, Dagmar",
-        "Rother, Carsten",
-        "Meyers, Gene"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:57;2017-02-24T11:56:57Z;Graph matching problems for annotating C. Elegans;Kainmueller, Dagmar;Jug, Florian;Rother, Carsten;Meyers, Gene;000 Computer science, knowledge & systems;Graph matching problems as described in \"Active Graph Matching for Automatic Joint Segmentation and Annotation of C. Elegans.\" by Kainmueller, Dagmar and Jug, Florian and Rother, Carsten and Myers, Gene, MICCAI 2014. Problems are in OpenGM2 hdf5 format (see http://hciweb2.iwr.uni-heidelberg.de/opengm/) and a custom text format used by the feature matching solver described in \"Feature Correspondence via Graph Matching: Models and Global Optimization.\" by Lorenzo Torresani, Vladimir Kolmogorov and Carsten Rother, ECCV 2008, code at http://pub.ist.ac.at/~vnk/software/GraphMatching-v1.02.src.zip. ;Data Collection;NonPeerReviewed;archive;https://datarep.app.ist.ac.at/57/;https://datarep.app.ist.ac.at/57/1/wormMatchingProblems.zip;  Kainmueller, Dagmar and Jug, Florian and Rother, Carsten and Meyers, Gene   Graph matching problems for annotating C. Elegans.  [Data Collection]     ;10.15479/AT:ISTA:57",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "00afc6ee-df51-5f89-b3d7-ad07745aad90",
-    "notes": [
-        "Graph matching problems as described in \"Active Graph Matching for Automatic Joint Segmentation and Annotation of C. Elegans.\" by Kainmueller, Dagmar and Jug, Florian and Rother, Carsten and Myers, Gene, MICCAI 2014. Problems are in OpenGM2 hdf5 format (see http://hciweb2.iwr.uni-heidelberg.de/opengm/) and a custom text format used by the feature matching solver described in \"Feature Correspondence via Graph Matching: Models and Global Optimization.\" by Lorenzo Torresani, Vladimir Kolmogorov and Carsten Rother, ECCV 2008, code at http://pub.ist.ac.at/~vnk/software/GraphMatching-v1.02.src.zip. "
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:57"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Computer science"
-        },
-        {
-            "name": "knowledge"
-        },
-        {
-            "name": "systems"
-        }
-    ],
-    "title": [
-        "Graph matching problems for annotating C. Elegans"
-    ],
-    "url": "https://datarep.app.ist.ac.at/57/1/wormMatchingProblems.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/027c6c25-78cc-56e8-a3e5-85bf0d4109a5.json b/oaitestdata/ist-oai_dc/SET_1/json/027c6c25-78cc-56e8-a3e5-85bf0d4109a5.json
deleted file mode 100644
index 5ccbbd82..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/027c6c25-78cc-56e8-a3e5-85bf0d4109a5.json
+++ /dev/null
@@ -1,43 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:43",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "archive"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:43",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/43/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Tugrul, Murat"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:43;2017-03-30T14:30:20Z;Experimental Data for Binding Site Evolution of Bacterial RNA Polymerase;Tugrul, Murat;576 Genetics and evolution;The data stored here is used in Murat Tugrul's PhD thesis (Chapter 3), which is related to the evolution of bacterial RNA polymerase binding.\r\nMagdalena Steinrueck (PhD Student in Calin Guet's group at IST Austria) performed the experiments and created the data on de novo promoter evolution. Fabienne Jesse (PhD Student in Jon Bollback's group at IST Austria) performed the experiments and created the data on lac promoter evolution.;Data Collection;NonPeerReviewed;archive;https://datarep.app.ist.ac.at/43/;https://datarep.app.ist.ac.at/43/1/DATA_MTugrul_PhDThesis_Chapter3.zip;  Tugrul, Murat   Experimental Data for Binding Site Evolution of Bacterial RNA Polymerase.  [Data Collection]     ;10.15479/AT:ISTA:43",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "027c6c25-78cc-56e8-a3e5-85bf0d4109a5",
-    "notes": [
-        "The data stored here is used in Murat Tugrul's PhD thesis (Chapter 3), which is related to the evolution of bacterial RNA polymerase binding.\r\nMagdalena Steinrueck (PhD Student in Calin Guet's group at IST Austria) performed the experiments and created the data on de novo promoter evolution. Fabienne Jesse (PhD Student in Jon Bollback's group at IST Austria) performed the experiments and created the data on lac promoter evolution."
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:43"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Genetics evolution"
-        }
-    ],
-    "title": [
-        "Experimental Data for Binding Site Evolution of Bacterial RNA Polymerase"
-    ],
-    "url": "https://datarep.app.ist.ac.at/43/1/DATA_MTugrul_PhDThesis_Chapter3.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/06b929b3-6923-5dae-857b-b63c5fd83297.json b/oaitestdata/ist-oai_dc/SET_1/json/06b929b3-6923-5dae-857b-b63c5fd83297.json
deleted file mode 100644
index 6c9767d7..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/06b929b3-6923-5dae-857b-b63c5fd83297.json
+++ /dev/null
@@ -1,43 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:94",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "archive"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:94",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/94/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Villanyi, Marton"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:94;2018-01-16T14:32:04Z;Taylor&Francis Austrian Publications 2013-2017;Villanyi, Marton;020 Library and information sciences;Data on Austrian open access publication output at Taylor&Francis from 2013-2017 including data analysis.;Data Collection;NonPeerReviewed;archive;https://datarep.app.ist.ac.at/94/;https://datarep.app.ist.ac.at/94/1/Taylor%26Francis_Austrian_Publications_2013-2017.zip;  Villanyi, Marton   Taylor&Francis Austrian Publications 2013-2017.  [Data Collection]    (Submitted)  ;10.15479/AT:ISTA:94",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "06b929b3-6923-5dae-857b-b63c5fd83297",
-    "notes": [
-        "Data on Austrian open access publication output at Taylor&Francis from 2013-2017 including data analysis."
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:94"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Library information sciences"
-        }
-    ],
-    "title": [
-        "Taylor&Francis Austrian Publications 2013-2017"
-    ],
-    "url": "https://datarep.app.ist.ac.at/94/1/Taylor%26Francis_Austrian_Publications_2013-2017.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/0b4731e3-399b-54c7-90c1-4d710519e696.json b/oaitestdata/ist-oai_dc/SET_1/json/0b4731e3-399b-54c7-90c1-4d710519e696.json
deleted file mode 100644
index 701824e3..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/0b4731e3-399b-54c7-90c1-4d710519e696.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:98",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "text",
-        "image",
-        "other"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:98",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/98/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Deny, Stephane",
-        "Martius, Georg",
-        "Marre, Olivier",
-        "Tkacik, Gasper",
-        "Botella-Soler, Vicente"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:98;2018-08-09T07:30:27Z;Nonlinear decoding of a complex movie from the mammalian retina;Deny, Stephane;Marre, Olivier;Botella-Soler, Vicente;Martius, Georg;Tkacik, Gasper;570 Life sciences; biology;This package contains data for the publication \"Nonlinear decoding of a complex movie from the mammalian retina\" by Deny S. et al, PLOS Comput Biol (2018). \r\n\r\nThe data consists of\r\n(i) 91 spike sorted, isolated rat retinal ganglion cells that pass stability and quality criteria, recorded on the multi-electrode array, in response to the presentation of the complex movie with many randomly moving dark discs. The responses are represented as 648000 x 91 binary matrix, where the first index indicates the timebin of duration 12.5 ms, and the second index the neural identity. The matrix entry is 0/1 if the neuron didn't/did spike in the particular time bin.\r\n(ii) README file and a graphical illustration of the structure of the experiment, specifying how the 648000 timebins are split into epochs where 1, 2, 4, or 10 discs  were displayed, and which stimulus segments are exact repeats or unique ball trajectories.\r\n(iii) a 648000 x 400 matrix of luminance traces for each of the 20 x 20 positions (\"sites\") in the movie frame, with time that is locked to the recorded raster. The luminance traces are produced as described in the manuscript by filtering the raw disc movie with a small gaussian spatial kernel. ;Data Collection;NonPeerReviewed;other;image;other;text;https://datarep.app.ist.ac.at/98/;https://datarep.app.ist.ac.at/98/1/BBalls_area2_tile2_20x20.mat;https://datarep.app.ist.ac.at/98/2/ExperimentStructure.pdf;https://datarep.app.ist.ac.at/98/3/GoodLocations_area2_20x20.mat;https://datarep.app.ist.ac.at/98/4/README.txt;  Deny, Stephane and Marre, Olivier and Botella-Soler, Vicente and Martius, Georg and Tkacik, Gasper   Nonlinear decoding of a complex movie from the mammalian retina.  [Data Collection]     ;10.15479/AT:ISTA:98;10.15479/AT:ISTA:98;10.15479/AT:ISTA:98;10.15479/AT:ISTA:98",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "0b4731e3-399b-54c7-90c1-4d710519e696",
-    "notes": [
-        "This package contains data for the publication \"Nonlinear decoding of a complex movie from the mammalian retina\" by Deny S. et al, PLOS Comput Biol (2018). \r\n\r\nThe data consists of\r\n(i) 91 spike sorted, isolated rat retinal ganglion cells that pass stability and quality criteria, recorded on the multi-electrode array, in response to the presentation of the complex movie with many randomly moving dark discs. The responses are represented as 648000 x 91 binary matrix, where the first index indicates the timebin of duration 12.5 ms, and the second index the neural identity. The matrix entry is 0/1 if the neuron didn't/did spike in the particular time bin.\r\n(ii) README file and a graphical illustration of the structure of the experiment, specifying how the 648000 timebins are split into epochs where 1, 2, 4, or 10 discs  were displayed, and which stimulus segments are exact repeats or unique ball trajectories.\r\n(iii) a 648000 x 400 matrix of luminance traces for each of the 20 x 20 positions (\"sites\") in the movie frame, with time that is locked to the recorded raster. The luminance traces are produced as described in the manuscript by filtering the raw disc movie with a small gaussian spatial kernel. "
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:98"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Life sciences"
-        },
-        {
-            "name": "biology"
-        }
-    ],
-    "title": [
-        "Nonlinear decoding of a complex movie from the mammalian retina"
-    ],
-    "url": "https://datarep.app.ist.ac.at/98/4/README.txt"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/15c67c7b-cca1-59ae-966f-7d3ddfcc5956.json b/oaitestdata/ist-oai_dc/SET_1/json/15c67c7b-cca1-59ae-966f-7d3ddfcc5956.json
deleted file mode 100644
index bdd5620c..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/15c67c7b-cca1-59ae-966f-7d3ddfcc5956.json
+++ /dev/null
@@ -1,43 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:93",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "archive"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:93",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/93/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Villanyi, Marton"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:93;2018-01-16T14:31:56Z;Springer Austrian Publications 2013-2016;Villanyi, Marton;020 Library and information sciences;Data on Austrian open access publication output at Springer from 2013-2016 including data analysis.;Data Collection;NonPeerReviewed;archive;https://datarep.app.ist.ac.at/93/;https://datarep.app.ist.ac.at/93/1/Springer_Austrian_Publications_2013-2016.zip;  Villanyi, Marton   Springer Austrian Publications 2013-2016.  [Data Collection]    (Submitted)  ;10.15479/AT:ISTA:93",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "15c67c7b-cca1-59ae-966f-7d3ddfcc5956",
-    "notes": [
-        "Data on Austrian open access publication output at Springer from 2013-2016 including data analysis."
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:93"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Library information sciences"
-        }
-    ],
-    "title": [
-        "Springer Austrian Publications 2013-2016"
-    ],
-    "url": "https://datarep.app.ist.ac.at/93/1/Springer_Austrian_Publications_2013-2016.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/1d6cc71b-82e0-57b4-adf3-8be1fd26bb37.json b/oaitestdata/ist-oai_dc/SET_1/json/1d6cc71b-82e0-57b4-adf3-8be1fd26bb37.json
deleted file mode 100644
index 5891a6fc..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/1d6cc71b-82e0-57b4-adf3-8be1fd26bb37.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:28",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "archive"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:28",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/28/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Fellner, Andreas"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:28;2016-02-19T08:57:23Z;Experimental part of CAV 2015 publication: Counterexample Explanation by Learning Small Strategies in Markov Decision Processes;Fellner, Andreas;004 Data processing & computer science;005 Computer programming, programs & data;This repository contains the experimental part of the CAV 2015 publication Counterexample Explanation by Learning Small Strategies in Markov Decision Processes.\r\nWe extended the probabilistic model checker PRISM to represent strategies of Markov Decision Processes as Decision Trees.\r\nThe archive contains a java executable version of the extended tool (prism_dectree.jar) together with a few examples of the PRISM benchmark library.\r\nTo execute the program, please have a look at the README.txt, which provides instructions and further information on the archive.\r\nThe archive contains scripts that (if run often enough) reproduces the data presented in the publication.;Data Collection;NonPeerReviewed;archive;https://datarep.app.ist.ac.at/28/;https://datarep.app.ist.ac.at/28/2/Fellner_DataRep.zip;  Fellner, Andreas   Experimental part of CAV 2015 publication: Counterexample Explanation by Learning Small Strategies in Markov Decision Processes.  [Data Collection]     ;10.15479/AT:ISTA:28",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "1d6cc71b-82e0-57b4-adf3-8be1fd26bb37",
-    "notes": [
-        "This repository contains the experimental part of the CAV 2015 publication Counterexample Explanation by Learning Small Strategies in Markov Decision Processes.\r\nWe extended the probabilistic model checker PRISM to represent strategies of Markov Decision Processes as Decision Trees.\r\nThe archive contains a java executable version of the extended tool (prism_dectree.jar) together with a few examples of the PRISM benchmark library.\r\nTo execute the program, please have a look at the README.txt, which provides instructions and further information on the archive.\r\nThe archive contains scripts that (if run often enough) reproduces the data presented in the publication."
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:28"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Data processing"
-        },
-        {
-            "name": "computer science"
-        },
-        {
-            "name": "Computer programming"
-        },
-        {
-            "name": "programs"
-        },
-        {
-            "name": "data"
-        }
-    ],
-    "title": [
-        "Experimental part of CAV 2015 publication: Counterexample Explanation by Learning Small Strategies in Markov Decision Processes"
-    ],
-    "url": "https://datarep.app.ist.ac.at/28/2/Fellner_DataRep.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/200f3daf-652b-52b2-90c9-61d397055a62.json b/oaitestdata/ist-oai_dc/SET_1/json/200f3daf-652b-52b2-90c9-61d397055a62.json
deleted file mode 100644
index 2a962677..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/200f3daf-652b-52b2-90c9-61d397055a62.json
+++ /dev/null
@@ -1,43 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:78",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "archive"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:78",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/78/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Vicoso, Beatriz"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:78;2017-11-06T08:51:47Z;Data for \"The genomic characterization of the t-haplotype, a mouse meiotic driver, highlights its complex history and specialized biology\";Vicoso, Beatriz;576 Genetics and evolution;This folder contains all the data used in each of the main figures of \"The genomic characterization of the t-haplotype, a mouse meiotic driver, highlights its complex history and specialized biology\" (Kelemen, R., Vicoso, B.), as well as in the supplementary figures. \r\n;Data Collection;NonPeerReviewed;archive;https://datarep.app.ist.ac.at/78/;https://datarep.app.ist.ac.at/78/1/Data.zip;  Vicoso, Beatriz   Data for \"The genomic characterization of the t-haplotype, a mouse meiotic driver, highlights its complex history and specialized biology\".  [Data Collection]    (Submitted)  ;10.15479/AT:ISTA:78",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "200f3daf-652b-52b2-90c9-61d397055a62",
-    "notes": [
-        "This folder contains all the data used in each of the main figures of \"The genomic characterization of the t-haplotype, a mouse meiotic driver, highlights its complex history and specialized biology\" (Kelemen, R., Vicoso, B.), as well as in the supplementary figures. \r\n"
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:78"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Genetics evolution"
-        }
-    ],
-    "title": [
-        "Data for \"The genomic characterization of the t-haplotype, a mouse meiotic driver, highlights its complex history and specialized biology\""
-    ],
-    "url": "https://datarep.app.ist.ac.at/78/1/Data.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/25b0e4c5-1cbf-5d2c-8d30-5247f2e226d4.json b/oaitestdata/ist-oai_dc/SET_1/json/25b0e4c5-1cbf-5d2c-8d30-5247f2e226d4.json
deleted file mode 100644
index ac7f7a3d..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/25b0e4c5-1cbf-5d2c-8d30-5247f2e226d4.json
+++ /dev/null
@@ -1,45 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "archive"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:69",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/69/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Hauschild, Robert"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:69;2017-07-21T08:44:54Z;Live tracking of moving samples in confocal microscopy for vertically grown roots;Hauschild, Robert;570 Life sciences; biology;Current minimal version of TipTracker;Data Collection;NonPeerReviewed;archive;https://datarep.app.ist.ac.at/69/;https://datarep.app.ist.ac.at/69/2/TipTrackerZeissLSM700.zip;  Hauschild, Robert   Live tracking of moving samples in confocal microscopy for vertically grown roots.  [Data Collection]     ; 10.15479/AT:ISTA:69",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "25b0e4c5-1cbf-5d2c-8d30-5247f2e226d4",
-    "notes": [
-        "Current minimal version of TipTracker"
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:69"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Life sciences"
-        },
-        {
-            "name": "biology"
-        }
-    ],
-    "title": [
-        "Live tracking of moving samples in confocal microscopy for vertically grown roots"
-    ],
-    "url": "https://datarep.app.ist.ac.at/69/2/TipTrackerZeissLSM700.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/2b61e7c6-0a83-567b-b8ac-880bfe7ef013.json b/oaitestdata/ist-oai_dc/SET_1/json/2b61e7c6-0a83-567b-b8ac-880bfe7ef013.json
deleted file mode 100644
index 3c858624..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/2b61e7c6-0a83-567b-b8ac-880bfe7ef013.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:36 ",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "archive"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:36",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/36/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Ellis, Thomas"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:36;2017-03-30T14:27:36Z;Pollinator visitation data for wild Antirrhinum majus plants, with phenotypic and frequency data.;Ellis, Thomas;576 Genetics and evolution;577 Ecology;Data on pollinator visitation to wild snapdragons in a natural hybrid zone, collected as part of Tom Ellis' PhD thesis (submitted February 2016).\r\n\r\nSnapdragon flowers have a mouth-like structure which pollinators must open to access nectar. We placed 5mm cellophane tags in these mouths, which are held in place by the pressure of the flower until a pollinator visits. When she opens the flower, the tag drops out, and one can infer a visit. We surveyed plants over multiple days in 2010, 2011 and 2012.\r\n\r\nAlso included are data on phenotypic and demographic variables which may be explanatory variables for pollinator visitation.;Data Collection;NonPeerReviewed;archive;https://datarep.app.ist.ac.at/36/;https://datarep.app.ist.ac.at/36/1/tag_assay_archive.zip;  Ellis, Thomas   Pollinator visitation data for wild Antirrhinum majus plants, with phenotypic and frequency data.  [Data Collection]     ;10.15479/AT:ISTA:36 ",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "2b61e7c6-0a83-567b-b8ac-880bfe7ef013",
-    "notes": [
-        "Data on pollinator visitation to wild snapdragons in a natural hybrid zone, collected as part of Tom Ellis' PhD thesis (submitted February 2016).\r\n\r\nSnapdragon flowers have a mouth-like structure which pollinators must open to access nectar. We placed 5mm cellophane tags in these mouths, which are held in place by the pressure of the flower until a pollinator visits. When she opens the flower, the tag drops out, and one can infer a visit. We surveyed plants over multiple days in 2010, 2011 and 2012.\r\n\r\nAlso included are data on phenotypic and demographic variables which may be explanatory variables for pollinator visitation."
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:36"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Genetics evolution"
-        },
-        {
-            "name": "Ecology"
-        }
-    ],
-    "title": [
-        "Pollinator visitation data for wild Antirrhinum majus plants, with phenotypic and frequency data."
-    ],
-    "url": "https://datarep.app.ist.ac.at/36/1/tag_assay_archive.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/2d7354ad-eba1-5966-81b2-a6b34fbb207e.json b/oaitestdata/ist-oai_dc/SET_1/json/2d7354ad-eba1-5966-81b2-a6b34fbb207e.json
deleted file mode 100644
index 32e11c1d..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/2d7354ad-eba1-5966-81b2-a6b34fbb207e.json
+++ /dev/null
@@ -1,43 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:92",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "archive"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:92",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/92/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Villanyi, Marton"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:92;2018-01-16T14:31:47Z;SAGE Austrian Publications 2013-2017;Villanyi, Marton;020 Library and information sciences;Data on Austrian open access publication output at SAGE from 2013-2017 including data analysis.;Data Collection;NonPeerReviewed;archive;https://datarep.app.ist.ac.at/92/;https://datarep.app.ist.ac.at/92/1/SAGE_Austrian_Publications_2013-2017.zip;  Villanyi, Marton   SAGE Austrian Publications 2013-2017.  [Data Collection]    (Submitted)  ;10.15479/AT:ISTA:92",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "2d7354ad-eba1-5966-81b2-a6b34fbb207e",
-    "notes": [
-        "Data on Austrian open access publication output at SAGE from 2013-2017 including data analysis."
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:92"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Library information sciences"
-        }
-    ],
-    "title": [
-        "SAGE Austrian Publications 2013-2017"
-    ],
-    "url": "https://datarep.app.ist.ac.at/92/1/SAGE_Austrian_Publications_2013-2017.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/3f20d0da-21d1-5487-81a9-d8679ecb7ce8.json b/oaitestdata/ist-oai_dc/SET_1/json/3f20d0da-21d1-5487-81a9-d8679ecb7ce8.json
deleted file mode 100644
index e48977c0..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/3f20d0da-21d1-5487-81a9-d8679ecb7ce8.json
+++ /dev/null
@@ -1,43 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:79 ",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "archive"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:79",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/79/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Vicoso, Beatriz"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:79;2017-11-06T08:52:10Z;Code for \"The genomic characterization of the t-haplotype, a mouse meiotic driver, highlights its complex history and specialized biology\";Vicoso, Beatriz;576 Genetics and evolution;Code described in the Supplementary Methods of \"The genomic characterization of the t-haplotype, a mouse meiotic driver, highlights its complex history and specialized biology\" (Kelemen, R., Vicoso, B.);Data Collection;NonPeerReviewed;archive;https://datarep.app.ist.ac.at/79/;https://datarep.app.ist.ac.at/79/1/Code.zip;  Vicoso, Beatriz   Code for \"The genomic characterization of the t-haplotype, a mouse meiotic driver, highlights its complex history and specialized biology\".  [Data Collection]    (Submitted)  ;10.15479/AT:ISTA:79 ",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "3f20d0da-21d1-5487-81a9-d8679ecb7ce8",
-    "notes": [
-        "Code described in the Supplementary Methods of \"The genomic characterization of the t-haplotype, a mouse meiotic driver, highlights its complex history and specialized biology\" (Kelemen, R., Vicoso, B.)"
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:79"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Genetics evolution"
-        }
-    ],
-    "title": [
-        "Code for \"The genomic characterization of the t-haplotype, a mouse meiotic driver, highlights its complex history and specialized biology\""
-    ],
-    "url": "https://datarep.app.ist.ac.at/79/1/Code.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/426c836c-f451-5da3-9a66-26d075fcd221.json b/oaitestdata/ist-oai_dc/SET_1/json/426c836c-f451-5da3-9a66-26d075fcd221.json
deleted file mode 100644
index a0f1b40e..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/426c836c-f451-5da3-9a66-26d075fcd221.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:53",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "archive"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:53",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/53/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Balleza, Enrique",
-        "Guet, Calin C",
-        "Tomasek, Kathrin",
-        "Hauschild, Robert",
-        "Andersson, Anna MC",
-        "Tkacik, Gasper",
-        "Kiviet, Daniel J",
-        "Bergmiller, Tobias"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:53;2017-04-12T08:05:52Z;Biased partitioning of the multi-drug efflux pump AcrAB-TolC underlies long-lived phenotypic heterogeneity;Bergmiller, Tobias;Andersson, Anna MC;Tomasek, Kathrin;Balleza, Enrique;Kiviet, Daniel J;Hauschild, Robert;Tkacik, Gasper;Guet, Calin C;571 Physiology;579 Microorganisms, fungi, algae;This repository contains the data collected for the manuscript \"Biased partitioning of the multi-drug efflux pump AcrAB-TolC underlies long-lived phenotypic heterogeneity\".\r\nThe data is compressed into a single archive. Within the archive, different folders correspond to figures of the main text and the SI of the related publication.\r\nData is saved as plain text, with each folder containing a separate readme file describing the format. Typically, the data is from fluorescence microscopy measurements of single cells growing in a microfluidic \"mother machine\" device, and consists of relevant values (primarily arbitrary unit or normalized fluorescence measurements, and division times / growth rates) after raw microscopy images have been processed, segmented, and their features extracted, as described in the methods section of the related publication.;Data Collection;NonPeerReviewed;archive;https://datarep.app.ist.ac.at/53/;https://datarep.app.ist.ac.at/53/1/Data_MDE.zip;  Bergmiller, Tobias and Andersson, Anna MC and Tomasek, Kathrin and Balleza, Enrique and Kiviet, Daniel J and Hauschild, Robert and Tkacik, Gasper and Guet, Calin C   Biased partitioning of the multi-drug efflux pump AcrAB-TolC underlies long-lived phenotypic heterogeneity.  [Data Collection]    (In Press)  ;doi:10.15479/AT:ISTA:53",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "426c836c-f451-5da3-9a66-26d075fcd221",
-    "notes": [
-        "This repository contains the data collected for the manuscript \"Biased partitioning of the multi-drug efflux pump AcrAB-TolC underlies long-lived phenotypic heterogeneity\".\r\nThe data is compressed into a single archive. Within the archive, different folders correspond to figures of the main text and the SI of the related publication.\r\nData is saved as plain text, with each folder containing a separate readme file describing the format. Typically, the data is from fluorescence microscopy measurements of single cells growing in a microfluidic \"mother machine\" device, and consists of relevant values (primarily arbitrary unit or normalized fluorescence measurements, and division times / growth rates) after raw microscopy images have been processed, segmented, and their features extracted, as described in the methods section of the related publication."
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:53"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Physiology"
-        },
-        {
-            "name": "Microorganisms"
-        },
-        {
-            "name": "fungi"
-        },
-        {
-            "name": "algae"
-        }
-    ],
-    "title": [
-        "Biased partitioning of the multi-drug efflux pump AcrAB-TolC underlies long-lived phenotypic heterogeneity"
-    ],
-    "url": "https://datarep.app.ist.ac.at/53/1/Data_MDE.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/4778faa2-6620-59c9-b9fa-ba52a532ee64.json b/oaitestdata/ist-oai_dc/SET_1/json/4778faa2-6620-59c9-b9fa-ba52a532ee64.json
deleted file mode 100644
index 7e474402..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/4778faa2-6620-59c9-b9fa-ba52a532ee64.json
+++ /dev/null
@@ -1,43 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:89",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "archive"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:89",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/89/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Villanyi, Marton"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:89;2018-01-16T14:31:29Z;Emerald Austrian Publications 2013-2017;Villanyi, Marton;020 Library and information sciences;Data on Austrian open access publication output at Emerald from 2013-2017 including data analysis.;Data Collection;NonPeerReviewed;archive;https://datarep.app.ist.ac.at/89/;https://datarep.app.ist.ac.at/89/1/Emerald_Austrian_Publications_2013-2017.zip;  Villanyi, Marton   Emerald Austrian Publications 2013-2017.  [Data Collection]    (Submitted)  ;10.15479/AT:ISTA:89",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "4778faa2-6620-59c9-b9fa-ba52a532ee64",
-    "notes": [
-        "Data on Austrian open access publication output at Emerald from 2013-2017 including data analysis."
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:89"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Library information sciences"
-        }
-    ],
-    "title": [
-        "Emerald Austrian Publications 2013-2017"
-    ],
-    "url": "https://datarep.app.ist.ac.at/89/1/Emerald_Austrian_Publications_2013-2017.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/497bf10a-472a-5a2b-8017-8973ed703298.json b/oaitestdata/ist-oai_dc/SET_1/json/497bf10a-472a-5a2b-8017-8973ed703298.json
deleted file mode 100644
index ddf33da8..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/497bf10a-472a-5a2b-8017-8973ed703298.json
+++ /dev/null
@@ -1,45 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:66",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "video"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:66",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/66/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Friml, Ji\u0159\u00ed ",
-        "Hauschild, Robert",
-        "von Wangenheim, Daniel"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:66;2017-04-12T08:05:45Z;Light Sheet Fluorescence microscopy of plant roots growing on the surface of a gel;von Wangenheim, Daniel;Hauschild, Robert;Friml, Ji\u0159\u00ed ;580 Plants;One of the key questions in understanding plant development is how single cells behave in a larger context of the tissue. Therefore, it requires the observation of the whole organ with a high spatial- as well as temporal resolution over prolonged periods of time, which may cause photo-toxic effects. This protocol shows a plant sample preparation method for light-sheet microscopy, which is characterized by mounting the plant vertically on the surface of a gel. The plant is mounted in such a way that the roots are submerged in a liquid medium while the leaves remain in the air. In order to ensure photosynthetic activity of the plant, a custom-made lighting system illuminates the leaves. To keep the roots in darkness the water surface is covered with sheets of black plastic foil. This method allows long-term imaging of plant organ development in standardized conditions. \r\nThe Video is licensed under a CC BY NC ND license. ;Data Collection;NonPeerReviewed;video;https://datarep.app.ist.ac.at/66/;https://datarep.app.ist.ac.at/66/1/WangenheimHighResolution55044-NEW_1.mp4;  von Wangenheim, Daniel and Hauschild, Robert and Friml, Ji\u0159\u00ed    Light Sheet Fluorescence microscopy of plant roots growing on the surface of a gel.  [Data Collection]     ;10.15479/AT:ISTA:66",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "497bf10a-472a-5a2b-8017-8973ed703298",
-    "notes": [
-        "One of the key questions in understanding plant development is how single cells behave in a larger context of the tissue. Therefore, it requires the observation of the whole organ with a high spatial- as well as temporal resolution over prolonged periods of time, which may cause photo-toxic effects. This protocol shows a plant sample preparation method for light-sheet microscopy, which is characterized by mounting the plant vertically on the surface of a gel. The plant is mounted in such a way that the roots are submerged in a liquid medium while the leaves remain in the air. In order to ensure photosynthetic activity of the plant, a custom-made lighting system illuminates the leaves. To keep the roots in darkness the water surface is covered with sheets of black plastic foil. This method allows long-term imaging of plant organ development in standardized conditions. \r\nThe Video is licensed under a CC BY NC ND license. "
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:66"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Plants"
-        }
-    ],
-    "title": [
-        "Light Sheet Fluorescence microscopy of plant roots growing on the surface of a gel"
-    ],
-    "url": "https://datarep.app.ist.ac.at/66/1/WangenheimHighResolution55044-NEW_1.mp4"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/51283476-a491-5dd8-a246-b87b5d89901d.json b/oaitestdata/ist-oai_dc/SET_1/json/51283476-a491-5dd8-a246-b87b5d89901d.json
deleted file mode 100644
index 57fe7cde..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/51283476-a491-5dd8-a246-b87b5d89901d.json
+++ /dev/null
@@ -1,43 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:88",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "archive"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:88",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/88/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Villanyi, Marton"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:88;2018-01-16T14:30:49Z;Data Check T&F Scopus vs. FWF;Villanyi, Marton;020 Library and information sciences;Comparison of Scopus' and FWF's data on Austrian publication output at T&F.;Data Collection;NonPeerReviewed;archive;https://datarep.app.ist.ac.at/88/;https://datarep.app.ist.ac.at/88/1/Data_Check_T%26F_Scopus_vs._FWF.zip;  Villanyi, Marton   Data Check T&F Scopus vs. FWF.  [Data Collection]    (Submitted)  ;10.15479/AT:ISTA:88",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "51283476-a491-5dd8-a246-b87b5d89901d",
-    "notes": [
-        "Comparison of Scopus' and FWF's data on Austrian publication output at T&F."
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:88"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Library information sciences"
-        }
-    ],
-    "title": [
-        "Data Check T&F Scopus vs. FWF"
-    ],
-    "url": "https://datarep.app.ist.ac.at/88/1/Data_Check_T%26F_Scopus_vs._FWF.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/56fab68b-5168-546b-9818-3a0443f06376.json b/oaitestdata/ist-oai_dc/SET_1/json/56fab68b-5168-546b-9818-3a0443f06376.json
deleted file mode 100644
index 72671d6b..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/56fab68b-5168-546b-9818-3a0443f06376.json
+++ /dev/null
@@ -1,44 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:34 ",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "dataset"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:34",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/34/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Ellis, Thomas",
-        "Field, David"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:34;2017-03-31T07:55:18Z;Flower colour data and phylogeny (NEXUS) files;Ellis, Thomas;Field, David;576 Genetics and evolution;We collected flower colour information on species in the tribe Antirrhineae from taxonomic literature. We also retreived molecular data from GenBank for as many of these species as possible to estimate phylogenetic relationships among these taxa. We then used the R package 'diversitree' to examine patterns of evolutionary transitions between anthocyanin and yellow pigmentation across the phylogeny.\r\n\r\nFor full details of the methods see:\r\nEllis TJ and Field DL \"Repeated gains in yellow and anthocyanin pigmentation in flower colour transitions in the Antirrhineae\u201d, Annals of Botany (in press);Data Collection;NonPeerReviewed;dataset;https://datarep.app.ist.ac.at/34/;https://datarep.app.ist.ac.at/34/1/tellis_flower_colour_data.zip;  Ellis, Thomas and Field, David   Flower colour data and phylogeny (NEXUS) files.  [Data Collection]     ;10.15479/AT:ISTA:34 ",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "56fab68b-5168-546b-9818-3a0443f06376",
-    "notes": [
-        "We collected flower colour information on species in the tribe Antirrhineae from taxonomic literature. We also retreived molecular data from GenBank for as many of these species as possible to estimate phylogenetic relationships among these taxa. We then used the R package 'diversitree' to examine patterns of evolutionary transitions between anthocyanin and yellow pigmentation across the phylogeny.\r\n\r\nFor full details of the methods see:\r\nEllis TJ and Field DL \"Repeated gains in yellow and anthocyanin pigmentation in flower colour transitions in the Antirrhineae\u201d, Annals of Botany (in press)"
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:34"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Genetics evolution"
-        }
-    ],
-    "title": [
-        "Flower colour data and phylogeny (NEXUS) files"
-    ],
-    "url": "https://datarep.app.ist.ac.at/34/1/tellis_flower_colour_data.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/617af245-f3cf-53e0-a147-1c354f705e9d.json b/oaitestdata/ist-oai_dc/SET_1/json/617af245-f3cf-53e0-a147-1c354f705e9d.json
deleted file mode 100644
index 11b5f0d6..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/617af245-f3cf-53e0-a147-1c354f705e9d.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:73",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "archive"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:73",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/73/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Hahn, David"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:73;2018-01-25T12:25:06Z;Source codes: Brittle fracture simulation with boundary elements for computer graphics;Hahn, David;004 Data processing & computer science;005 Computer programming, programs & data;006 Special computer methods;518 Numerical analysis;531 Classical mechanics; Solid mechanics;Includes source codes, test cases, and example data used in the thesis Brittle Fracture Simulation with Boundary Elements for Computer Graphics. Also includes pre-built binaries of the HyENA library, but not sources - please contact the HyENA authors to obtain these sources if required (https://mech.tugraz.at/hyena);Data Collection;NonPeerReviewed;archive;https://datarep.app.ist.ac.at/73/;https://datarep.app.ist.ac.at/73/1/FractureRB_v1.1_2017_07_20_final_public.zip;  Hahn, David   Source codes: Brittle fracture simulation with boundary elements for computer graphics.  [Data Collection]     ;10.15479/AT:ISTA:73",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "617af245-f3cf-53e0-a147-1c354f705e9d",
-    "notes": [
-        "Includes source codes, test cases, and example data used in the thesis Brittle Fracture Simulation with Boundary Elements for Computer Graphics. Also includes pre-built binaries of the HyENA library, but not sources - please contact the HyENA authors to obtain these sources if required (https://mech.tugraz.at/hyena)"
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:73"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Data processing"
-        },
-        {
-            "name": "computer science"
-        },
-        {
-            "name": "Computer programming"
-        },
-        {
-            "name": "programs"
-        },
-        {
-            "name": "data"
-        },
-        {
-            "name": "Special computer methods"
-        },
-        {
-            "name": "Numerical analysis"
-        },
-        {
-            "name": "Classical mechanics"
-        },
-        {
-            "name": "Solid mechanics"
-        }
-    ],
-    "title": [
-        "Source codes: Brittle fracture simulation with boundary elements for computer graphics"
-    ],
-    "url": "https://datarep.app.ist.ac.at/73/1/FractureRB_v1.1_2017_07_20_final_public.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/65dcf01d-433f-5b83-b4c9-34d57f4f4722.json b/oaitestdata/ist-oai_dc/SET_1/json/65dcf01d-433f-5b83-b4c9-34d57f4f4722.json
deleted file mode 100644
index 6d015e94..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/65dcf01d-433f-5b83-b4c9-34d57f4f4722.json
+++ /dev/null
@@ -1,43 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:46",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "dataset"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:46",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/46/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Swoboda, Paul"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:46;2017-01-16T16:01:26Z;Synthetic discrete tomography problems;Swoboda, Paul;006 Special computer methods;Small synthetic discrete tomography problems.\r\nSizes are 32x32, 64z64 and 256x256.\r\nProjection angles are 2, 4, and 6.\r\nNumber of labels are 3 and 5.;Data Collection;NonPeerReviewed;dataset;https://datarep.app.ist.ac.at/46/;https://datarep.app.ist.ac.at/46/1/discrete_tomography_synthetic.zip;  Swoboda, Paul   Synthetic discrete tomography problems.  [Data Collection]    (Unpublished)  ;10.15479/AT:ISTA:46",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "65dcf01d-433f-5b83-b4c9-34d57f4f4722",
-    "notes": [
-        "Small synthetic discrete tomography problems.\r\nSizes are 32x32, 64z64 and 256x256.\r\nProjection angles are 2, 4, and 6.\r\nNumber of labels are 3 and 5."
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:46"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Special computer methods"
-        }
-    ],
-    "title": [
-        "Synthetic discrete tomography problems"
-    ],
-    "url": "https://datarep.app.ist.ac.at/46/1/discrete_tomography_synthetic.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/6a68830e-28eb-5c2d-a869-8f901ccc7b81.json b/oaitestdata/ist-oai_dc/SET_1/json/6a68830e-28eb-5c2d-a869-8f901ccc7b81.json
deleted file mode 100644
index 4512c936..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/6a68830e-28eb-5c2d-a869-8f901ccc7b81.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:71",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "video"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:71",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/71/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Leithner, Alexander"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:71;2017-08-09T11:38:28Z;Immunological synapse DC-Tcells;Leithner, Alexander;570 Life sciences; biology;Immunological synapse DC-Tcells;Data Collection;NonPeerReviewed;video;video;https://datarep.app.ist.ac.at/71/;https://datarep.app.ist.ac.at/71/1/Synapse_1.avi;https://datarep.app.ist.ac.at/71/2/Synapse_2.avi;  Leithner, Alexander   Immunological synapse DC-Tcells.  [Data Collection]    (Unpublished)  ;10.15479/AT:ISTA:71;10.15479/AT:ISTA:71",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "6a68830e-28eb-5c2d-a869-8f901ccc7b81",
-    "notes": [
-        "Immunological synapse DC-Tcells"
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:71"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Life sciences"
-        },
-        {
-            "name": "biology"
-        }
-    ],
-    "title": [
-        "Immunological synapse DC-Tcells"
-    ],
-    "url": "https://datarep.app.ist.ac.at/71/2/Synapse_2.avi"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/6bf9ea73-02e9-54e8-91ce-a465ef8a1659.json b/oaitestdata/ist-oai_dc/SET_1/json/6bf9ea73-02e9-54e8-91ce-a465ef8a1659.json
deleted file mode 100644
index 3be72abe..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/6bf9ea73-02e9-54e8-91ce-a465ef8a1659.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:48",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "archive"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:48",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/48/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Bojsen-Hansen, Morten"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:48;2017-03-30T14:43:50Z;Tracking, Correcting and Absorbing Water Surface Waves;Bojsen-Hansen, Morten;004 Data processing & computer science;005 Computer programming, programs & data;006 Special computer methods;532 Fluid mechanics; Liquid mechanics;621 Applied physics;PhD thesis LaTeX source code;Data Collection;NonPeerReviewed;archive;https://datarep.app.ist.ac.at/48/;https://datarep.app.ist.ac.at/48/1/2016_Bojsen-Hansen_TCaAWSW.tar.bz2;  Bojsen-Hansen, Morten   Tracking, Correcting and Absorbing Water Surface Waves.  [Data Collection]     ;10.15479/AT:ISTA:48",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "6bf9ea73-02e9-54e8-91ce-a465ef8a1659",
-    "notes": [
-        "PhD thesis LaTeX source code"
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:48"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Data processing"
-        },
-        {
-            "name": "computer science"
-        },
-        {
-            "name": "Computer programming"
-        },
-        {
-            "name": "programs"
-        },
-        {
-            "name": "data"
-        },
-        {
-            "name": "Special computer methods"
-        },
-        {
-            "name": "Fluid mechanics"
-        },
-        {
-            "name": "Liquid mechanics"
-        },
-        {
-            "name": "Applied physics"
-        }
-    ],
-    "title": [
-        "Tracking, Correcting and Absorbing Water Surface Waves"
-    ],
-    "url": "https://datarep.app.ist.ac.at/48/1/2016_Bojsen-Hansen_TCaAWSW.tar.bz2"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/6cac1636-dc33-5b7d-a4ba-e28edb7ab8fb.json b/oaitestdata/ist-oai_dc/SET_1/json/6cac1636-dc33-5b7d-a4ba-e28edb7ab8fb.json
deleted file mode 100644
index 9173ad67..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/6cac1636-dc33-5b7d-a4ba-e28edb7ab8fb.json
+++ /dev/null
@@ -1,47 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:37 ",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "archive"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:37",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/37/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Ellis, Thomas",
-        "Field, David"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:37;2017-03-30T14:27:55Z;\tInference of mating patterns among wild snapdragons in a natural hybrid zone in 2012.;Field, David;Ellis, Thomas;576 Genetics and evolution;577 Ecology;Genotypic, phenotypic and demographic data for 2128 wild snapdragons and 1127 open-pollinated progeny from a natural hybrid zone, collected as part of Tom Ellis' PhD thesis (submitted) February 2016).\r\n\r\nTissue samples were sent to LGC Genomics in Berlin for DNA extraction, and genotyping at 70 SNP markers by KASPR genotyping. 29 of these SNPs failed to amplify reliably, and have been removed from this dataset.\r\n\r\nOther data were retreived from an online database of this population at www.antspec.org.;Data Collection;NonPeerReviewed;archive;https://datarep.app.ist.ac.at/37/;https://datarep.app.ist.ac.at/37/1/paternity_archive.zip;  Field, David and Ellis, Thomas    Inference of mating patterns among wild snapdragons in a natural hybrid zone in 2012.  [Data Collection]     ;10.15479/AT:ISTA:37 ",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "6cac1636-dc33-5b7d-a4ba-e28edb7ab8fb",
-    "notes": [
-        "Genotypic, phenotypic and demographic data for 2128 wild snapdragons and 1127 open-pollinated progeny from a natural hybrid zone, collected as part of Tom Ellis' PhD thesis (submitted) February 2016).\r\n\r\nTissue samples were sent to LGC Genomics in Berlin for DNA extraction, and genotyping at 70 SNP markers by KASPR genotyping. 29 of these SNPs failed to amplify reliably, and have been removed from this dataset.\r\n\r\nOther data were retreived from an online database of this population at www.antspec.org."
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:37"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Genetics evolution"
-        },
-        {
-            "name": "Ecology"
-        }
-    ],
-    "title": [
-        "\tInference of mating patterns among wild snapdragons in a natural hybrid zone in 2012."
-    ],
-    "url": "https://datarep.app.ist.ac.at/37/1/paternity_archive.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/7e0e5a32-e63b-51a4-9c99-2c811b1df7a2.json b/oaitestdata/ist-oai_dc/SET_1/json/7e0e5a32-e63b-51a4-9c99-2c811b1df7a2.json
deleted file mode 100644
index a7697adc..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/7e0e5a32-e63b-51a4-9c99-2c811b1df7a2.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:75",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "text"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:75",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/75/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Hauschild, Robert"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:75;2017-10-04T15:32:49Z;Forward migration indexes;Hauschild, Robert;570 Life sciences; biology;Matlab script to calculate the forward migration indexes (<d_y>/<L>) from TrackMate spot-statistics files.;Data Collection;NonPeerReviewed;text;https://datarep.app.ist.ac.at/75/;https://datarep.app.ist.ac.at/75/1/FMI.m;  Hauschild, Robert   Forward migration indexes.  [Data Collection]    (Unpublished)  ;10.15479/AT:ISTA:75",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "7e0e5a32-e63b-51a4-9c99-2c811b1df7a2",
-    "notes": [
-        "Matlab script to calculate the forward migration indexes (<d_y>/<L>) from TrackMate spot-statistics files."
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:75"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Life sciences"
-        },
-        {
-            "name": "biology"
-        }
-    ],
-    "title": [
-        "Forward migration indexes"
-    ],
-    "url": "https://datarep.app.ist.ac.at/75/1/FMI.m"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/90168a14-9bde-5002-9a16-9b88681bd82a.json b/oaitestdata/ist-oai_dc/SET_1/json/90168a14-9bde-5002-9a16-9b88681bd82a.json
deleted file mode 100644
index 66075b58..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/90168a14-9bde-5002-9a16-9b88681bd82a.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:64",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "archive"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:64",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/64/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Lukacisin, Martin"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:64;2017-03-20T08:07:13Z;MATLAB analysis code for 'Sequence-Specific Thermodynamic Properties of Nucleic Acids Influence Both Transcriptional Pausing and Backtracking in Yeast';Lukacisin, Martin;571 Physiology;579 Microorganisms, fungi, algae;MATLAB code and processed datasets available for reproducing the results in: \r\nLuka\u010di\u0161in, M.*, Landon, M.*, Jajoo, R*. (2016) Sequence-Specific Thermodynamic Properties of Nucleic Acids Influence Both Transcriptional Pausing and Backtracking in Yeast.\r\n*equal contributions;Data Collection;NonPeerReviewed;archive;https://datarep.app.ist.ac.at/64/;https://datarep.app.ist.ac.at/64/1/PaperCode.zip;  Lukacisin, Martin   MATLAB analysis code for 'Sequence-Specific Thermodynamic Properties of Nucleic Acids Influence Both Transcriptional Pausing and Backtracking in Yeast'.  [Data Collection]     ;10.15479/AT:ISTA:64",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "90168a14-9bde-5002-9a16-9b88681bd82a",
-    "notes": [
-        "MATLAB code and processed datasets available for reproducing the results in: \r\nLuka\u010di\u0161in, M.*, Landon, M.*, Jajoo, R*. (2016) Sequence-Specific Thermodynamic Properties of Nucleic Acids Influence Both Transcriptional Pausing and Backtracking in Yeast.\r\n*equal contributions"
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:64"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Physiology"
-        },
-        {
-            "name": "Microorganisms"
-        },
-        {
-            "name": "fungi"
-        },
-        {
-            "name": "algae"
-        }
-    ],
-    "title": [
-        "MATLAB analysis code for 'Sequence-Specific Thermodynamic Properties of Nucleic Acids Influence Both Transcriptional Pausing and Backtracking in Yeast'"
-    ],
-    "url": "https://datarep.app.ist.ac.at/64/1/PaperCode.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/9083b50e-6fea-528a-9931-54ad36d88a4d.json b/oaitestdata/ist-oai_dc/SET_1/json/9083b50e-6fea-528a-9931-54ad36d88a4d.json
deleted file mode 100644
index 5e5da584..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/9083b50e-6fea-528a-9931-54ad36d88a4d.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:62",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "archive"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:111",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/111/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Tkacik, Gasper",
-        "De Martino, Daniele"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:111;2018-09-21T14:11:04Z;Supporting materials \"STATISTICAL MECHANICS FOR METABOLIC NETWORKS IN STEADY-STATE GROWTH\";De Martino, Daniele;Tkacik, Gasper;530 Physics;570 Life sciences; biology;Supporting material to the article \r\nSTATISTICAL MECHANICS FOR METABOLIC NETWORKS IN STEADY-STATE GROWTH\r\n\r\n\r\nboundscoli.dat\r\nFlux Bounds of the E. coli catabolic core model iAF1260 in a glucose limited minimal medium. \r\n\r\n\r\npolcoli.dat\r\nMatrix enconding the polytope of the E. coli catabolic core model iAF1260 in a glucose limited minimal medium, \r\nobtained from the soichiometric matrix by standard linear algebra  (reduced row echelon form).\r\n\r\nellis.dat\r\nApproximate Lowner-John ellipsoid rounding the polytope of the E. coli catabolic core model iAF1260 in a glucose limited minimal medium\r\nobtained with the Lovasz method.\r\n\r\npoint0.dat\r\nCenter of the approximate Lowner-John ellipsoid rounding the polytope of the E. coli catabolic core model iAF1260 in a glucose limited minimal medium\r\nobtained with the Lovasz method.\r\n\r\n\r\n\r\nlovasz.cpp  \r\nThis c++ code file receives in input the polytope of the feasible steady states of a metabolic network, \r\n(matrix and bounds), and it gives in output an approximate Lowner-John ellipsoid rounding the polytope\r\nwith the Lovasz method \r\nNB inputs are referred by defaults to the catabolic core of the E.Coli network iAF1260. \r\nFor further details we refer to  PLoS ONE 10.4 e0122670 (2015).\r\n\r\nsampleHRnew.cpp  \r\nThis c++ code file receives in input the polytope of the feasible steady states of a metabolic network, \r\n(matrix and bounds), the ellipsoid rounding the polytope, a point inside and  \r\nit gives in output a max entropy sampling at fixed average growth rate \r\nof the steady states by performing an Hit-and-Run Monte Carlo Markov chain.\r\nNB inputs are referred by defaults to the catabolic core of the E.Coli network iAF1260. \r\nFor further details we refer to  PLoS ONE 10.4 e0122670 (2015).;Data Collection;NonPeerReviewed;archive;https://datarep.app.ist.ac.at/111/;https://datarep.app.ist.ac.at/111/1/CODES.zip;  De Martino, Daniele and Tkacik, Gasper   Supporting materials \"STATISTICAL MECHANICS FOR METABOLIC NETWORKS IN STEADY-STATE GROWTH\".  [Data Collection]     ;10.15479/AT:ISTA:62",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "9083b50e-6fea-528a-9931-54ad36d88a4d",
-    "notes": [
-        "Supporting material to the article \r\nSTATISTICAL MECHANICS FOR METABOLIC NETWORKS IN STEADY-STATE GROWTH\r\n\r\n\r\nboundscoli.dat\r\nFlux Bounds of the E. coli catabolic core model iAF1260 in a glucose limited minimal medium. \r\n\r\n\r\npolcoli.dat\r\nMatrix enconding the polytope of the E. coli catabolic core model iAF1260 in a glucose limited minimal medium, \r\nobtained from the soichiometric matrix by standard linear algebra  (reduced row echelon form).\r\n\r\nellis.dat\r\nApproximate Lowner-John ellipsoid rounding the polytope of the E. coli catabolic core model iAF1260 in a glucose limited minimal medium\r\nobtained with the Lovasz method.\r\n\r\npoint0.dat\r\nCenter of the approximate Lowner-John ellipsoid rounding the polytope of the E. coli catabolic core model iAF1260 in a glucose limited minimal medium\r\nobtained with the Lovasz method.\r\n\r\n\r\n\r\nlovasz.cpp  \r\nThis c++ code file receives in input the polytope of the feasible steady states of a metabolic network, \r\n(matrix and bounds), and it gives in output an approximate Lowner-John ellipsoid rounding the polytope\r\nwith the Lovasz method \r\nNB inputs are referred by defaults to the catabolic core of the E.Coli network iAF1260. \r\nFor further details we refer to  PLoS ONE 10.4 e0122670 (2015).\r\n\r\nsampleHRnew.cpp  \r\nThis c++ code file receives in input the polytope of the feasible steady states of a metabolic network, \r\n(matrix and bounds), the ellipsoid rounding the polytope, a point inside and  \r\nit gives in output a max entropy sampling at fixed average growth rate \r\nof the steady states by performing an Hit-and-Run Monte Carlo Markov chain.\r\nNB inputs are referred by defaults to the catabolic core of the E.Coli network iAF1260. \r\nFor further details we refer to  PLoS ONE 10.4 e0122670 (2015)."
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:111"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Physics"
-        },
-        {
-            "name": "Life sciences"
-        },
-        {
-            "name": "biology"
-        }
-    ],
-    "title": [
-        "Supporting materials \"STATISTICAL MECHANICS FOR METABOLIC NETWORKS IN STEADY-STATE GROWTH\""
-    ],
-    "url": "https://datarep.app.ist.ac.at/111/1/CODES.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/b5e95dfd-9785-59a4-8bd2-92c90877327b.json b/oaitestdata/ist-oai_dc/SET_1/json/b5e95dfd-9785-59a4-8bd2-92c90877327b.json
deleted file mode 100644
index d9c41761..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/b5e95dfd-9785-59a4-8bd2-92c90877327b.json
+++ /dev/null
@@ -1,49 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:51",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "video"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:51",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/51/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Pavlogiannis, Andreas",
-        "Chatterjee, Krishnendu",
-        "Tkadlec, Josef",
-        "Nowak , Martin A"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:51;2017-04-12T07:58:40Z;Strong amplifiers of natural selection;Pavlogiannis, Andreas;Tkadlec, Josef;Chatterjee, Krishnendu;Nowak , Martin A;519 Probabilities & applied mathematics;Strong amplifiers of natural selection;Data Collection;NonPeerReviewed;video;https://datarep.app.ist.ac.at/51/;https://datarep.app.ist.ac.at/51/2/illustration.mp4;  Pavlogiannis, Andreas and Tkadlec, Josef and Chatterjee, Krishnendu and Nowak , Martin A   Strong amplifiers of natural selection.  [Data Collection]     ;10.15479/AT:ISTA:51",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "b5e95dfd-9785-59a4-8bd2-92c90877327b",
-    "notes": [
-        "Strong amplifiers of natural selection"
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:51"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Probabilities"
-        },
-        {
-            "name": "applied mathematics"
-        }
-    ],
-    "title": [
-        "Strong amplifiers of natural selection"
-    ],
-    "url": "https://datarep.app.ist.ac.at/51/2/illustration.mp4"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/b651dc62-e0a5-5048-8829-1fc9c9592210.json b/oaitestdata/ist-oai_dc/SET_1/json/b651dc62-e0a5-5048-8829-1fc9c9592210.json
deleted file mode 100644
index 2beeba09..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/b651dc62-e0a5-5048-8829-1fc9c9592210.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:44",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "archive"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:44",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/44/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Hauschild, Robert"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:44;2017-01-16T16:01:27Z;Fiji  script to determine average speed and direction of migration of cells;Hauschild, Robert;570 Life sciences; biology;This FIJI script calculates the population average of the migration speed as a function of time of all cells from wide field microscopy movies.;Data Collection;NonPeerReviewed;archive;https://datarep.app.ist.ac.at/44/;https://datarep.app.ist.ac.at/44/1/migrationAnalyzer.zip;  Hauschild, Robert   Fiji script to determine average speed and direction of migration of cells.  [Data Collection]    (Submitted)  ;10.15479/AT:ISTA:44",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "b651dc62-e0a5-5048-8829-1fc9c9592210",
-    "notes": [
-        "This FIJI script calculates the population average of the migration speed as a function of time of all cells from wide field microscopy movies."
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:44"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Life sciences"
-        },
-        {
-            "name": "biology"
-        }
-    ],
-    "title": [
-        "Fiji  script to determine average speed and direction of migration of cells"
-    ],
-    "url": "https://datarep.app.ist.ac.at/44/1/migrationAnalyzer.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/ba09c4e2-d8c3-5a48-a9e4-8c8199e115c5.json b/oaitestdata/ist-oai_dc/SET_1/json/ba09c4e2-d8c3-5a48-a9e4-8c8199e115c5.json
deleted file mode 100644
index 884250bc..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/ba09c4e2-d8c3-5a48-a9e4-8c8199e115c5.json
+++ /dev/null
@@ -1,47 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:108",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "dataset"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:108",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/108/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Tkacik, Gasper",
-        "Igler, Claudia",
-        "Lagator , Mato",
-        "Guet, Calin C",
-        "Bollback, Jonathan P"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:108;2018-07-20T10:51:58Z;Data for the paper Evolutionary potential of transcription factors for gene regulatory rewiring;Igler, Claudia;Lagator , Mato;Tkacik, Gasper;Bollback, Jonathan P;Guet, Calin C;576 Genetics and evolution;Mean repression values and standard error of the mean are given for all operator mutant libraries.;Data Collection;NonPeerReviewed;dataset;https://datarep.app.ist.ac.at/108/;https://datarep.app.ist.ac.at/108/1/data_figures.xlsx;  Igler, Claudia and Lagator , Mato and Tkacik, Gasper and Bollback, Jonathan P and Guet, Calin C   Data for the paper Evolutionary potential of transcription factors for gene regulatory rewiring.  [Data Collection]    (In Press)  ;10.15479/AT:ISTA:108",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "ba09c4e2-d8c3-5a48-a9e4-8c8199e115c5",
-    "notes": [
-        "Mean repression values and standard error of the mean are given for all operator mutant libraries."
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:108"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Genetics evolution"
-        }
-    ],
-    "title": [
-        "Data for the paper Evolutionary potential of transcription factors for gene regulatory rewiring"
-    ],
-    "url": "https://datarep.app.ist.ac.at/108/1/data_figures.xlsx"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/ca797dcd-f0a2-5d2c-aacc-f1e356b984b2.json b/oaitestdata/ist-oai_dc/SET_1/json/ca797dcd-f0a2-5d2c-aacc-f1e356b984b2.json
deleted file mode 100644
index cbe30f93..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/ca797dcd-f0a2-5d2c-aacc-f1e356b984b2.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:95",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "archive",
-        "dataset"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:95",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/95/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Ellis, Thomas"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:95;2018-04-04T12:25:19Z;Data and Python scripts supporting Python package FAPS;Ellis, Thomas;519 Probabilities & applied mathematics;576 Genetics and evolution;Data and scripts are provided in support of the manuscript \"Efficient inference of paternity and sibship inference given known maternity via hierarchical clustering\", and the associated Python package FAPS, available from www.github.com/ellisztamas/faps.\r\n\r\nSimulation scripts cover:\r\n1. Performance under different mating scenarios.\r\n2. Comparison with Colony2.\r\n3. Effect of changing the number of Monte Carlo draws\r\n\r\nThe final script covers the analysis of half-sib arrays from wild-pollinated seed in an Antirrhinum majus hybrid zone.;Data Collection;NonPeerReviewed;dataset;dataset;dataset;archive;https://datarep.app.ist.ac.at/95/;https://datarep.app.ist.ac.at/95/1/amajus_GPS_2012.csv;https://datarep.app.ist.ac.at/95/2/offspring_SNPs_2012.csv;https://datarep.app.ist.ac.at/95/3/parents_SNPs_2012.csv;https://datarep.app.ist.ac.at/95/4/faps_scripts.zip;  Ellis, Thomas   Data and Python scripts supporting Python package FAPS.  [Data Collection]    (Submitted)  ;10.15479/AT:ISTA:95;10.15479/AT:ISTA:95;10.15479/AT:ISTA:95;10.15479/AT:ISTA:95",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "ca797dcd-f0a2-5d2c-aacc-f1e356b984b2",
-    "notes": [
-        "Data and scripts are provided in support of the manuscript \"Efficient inference of paternity and sibship inference given known maternity via hierarchical clustering\", and the associated Python package FAPS, available from www.github.com/ellisztamas/faps.\r\n\r\nSimulation scripts cover:\r\n1. Performance under different mating scenarios.\r\n2. Comparison with Colony2.\r\n3. Effect of changing the number of Monte Carlo draws\r\n\r\nThe final script covers the analysis of half-sib arrays from wild-pollinated seed in an Antirrhinum majus hybrid zone."
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:95"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Probabilities"
-        },
-        {
-            "name": "applied mathematics"
-        },
-        {
-            "name": "Genetics evolution"
-        }
-    ],
-    "title": [
-        "Data and Python scripts supporting Python package FAPS"
-    ],
-    "url": "https://datarep.app.ist.ac.at/95/4/faps_scripts.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/cac8ad58-f498-5748-af28-0d7a1a116e08.json b/oaitestdata/ist-oai_dc/SET_1/json/cac8ad58-f498-5748-af28-0d7a1a116e08.json
deleted file mode 100644
index dfc69b77..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/cac8ad58-f498-5748-af28-0d7a1a116e08.json
+++ /dev/null
@@ -1,53 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:65",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "archive"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:65",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/65/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Guet, Calin C",
-        "Steinrueck, Magdalena"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:65;2017-04-12T08:05:41Z;Fastq files for \"Complex chromosomal neighborhood effects determine the adaptive potential of a gene under selection\";Steinrueck, Magdalena;Guet, Calin C;576 Genetics and evolution;579 Microorganisms, fungi, algae;Compressed Fastq files with whole-genome sequencing data of IS-wt strain D and clones from four evolved populations (A11, C08, C10, D08). Information on this data collection is available in the Methods Section of the primary publication.;Data Collection;NonPeerReviewed;archive;archive;archive;archive;archive;archive;archive;archive;archive;https://datarep.app.ist.ac.at/65/;https://datarep.app.ist.ac.at/65/2/D_anc_1.fastq.zip;https://datarep.app.ist.ac.at/65/1/D_anc_2.fastq.zip;https://datarep.app.ist.ac.at/65/3/D_A11_1.fastq.zip;https://datarep.app.ist.ac.at/65/4/D_A11_2.fastq.zip;https://datarep.app.ist.ac.at/65/5/D_C10_1.fastq.zip;https://datarep.app.ist.ac.at/65/7/D_C08_2.fastq.zip;https://datarep.app.ist.ac.at/65/6/D_C10_2.fastq.zip;https://datarep.app.ist.ac.at/65/8/D_C08_1.fastq.zip;https://datarep.app.ist.ac.at/65/9/D_D08_1.fastq.zip;  Steinrueck, Magdalena and Guet, Calin C   Fastq files for \"Complex chromosomal neighborhood effects determine the adaptive potential of a gene under selection\".  [Data Collection]    (Submitted)  ;10.15479/AT:ISTA:65;10.15479/AT:ISTA:65;10.15479/AT:ISTA:65;10.15479/AT:ISTA:65;10.15479/AT:ISTA:65;10.15479/AT:ISTA:65;10.15479/AT:ISTA:65;10.15479/AT:ISTA:65;10.15479/AT:ISTA:65",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "cac8ad58-f498-5748-af28-0d7a1a116e08",
-    "notes": [
-        "Compressed Fastq files with whole-genome sequencing data of IS-wt strain D and clones from four evolved populations (A11, C08, C10, D08). Information on this data collection is available in the Methods Section of the primary publication."
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:65"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Genetics evolution"
-        },
-        {
-            "name": "Microorganisms"
-        },
-        {
-            "name": "fungi"
-        },
-        {
-            "name": "algae"
-        }
-    ],
-    "title": [
-        "Fastq files for \"Complex chromosomal neighborhood effects determine the adaptive potential of a gene under selection\""
-    ],
-    "url": "https://datarep.app.ist.ac.at/65/9/D_D08_1.fastq.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/cc6d5ded-2cda-5944-81fc-326efff93dbd.json b/oaitestdata/ist-oai_dc/SET_1/json/cc6d5ded-2cda-5944-81fc-326efff93dbd.json
deleted file mode 100644
index 07bc917d..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/cc6d5ded-2cda-5944-81fc-326efff93dbd.json
+++ /dev/null
@@ -1,43 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:90",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "archive"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:90",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/90/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Villanyi, Marton"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:90;2018-01-16T14:31:36Z;IOP Austrian Publications 2012-2015;Villanyi, Marton;020 Library and information sciences;Data on Austrian open access publication output at IOP from 2012-2015 including data analysis.;Data Collection;NonPeerReviewed;archive;https://datarep.app.ist.ac.at/90/;https://datarep.app.ist.ac.at/90/1/IOP_Austrian_Publications_2012-2015.zip;  Villanyi, Marton   IOP Austrian Publications 2012-2015.  [Data Collection]    (Submitted)  ;10.15479/AT:ISTA:90",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "cc6d5ded-2cda-5944-81fc-326efff93dbd",
-    "notes": [
-        "Data on Austrian open access publication output at IOP from 2012-2015 including data analysis."
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:90"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Library information sciences"
-        }
-    ],
-    "title": [
-        "IOP Austrian Publications 2012-2015"
-    ],
-    "url": "https://datarep.app.ist.ac.at/90/1/IOP_Austrian_Publications_2012-2015.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/d068f316-9efc-5ce3-b4db-1454fc9faa18.json b/oaitestdata/ist-oai_dc/SET_1/json/d068f316-9efc-5ce3-b4db-1454fc9faa18.json
deleted file mode 100644
index e5f87b8e..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/d068f316-9efc-5ce3-b4db-1454fc9faa18.json
+++ /dev/null
@@ -1,43 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:91",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "archive"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:91",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/91/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Villanyi, Marton"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:91;2018-01-16T14:31:41Z;RSC Austrian Publications 2013-2017;Villanyi, Marton;020 Library and information sciences;Data on Austrian open access publication output at RSC from 2013-2017 including data analysis.;Data Collection;NonPeerReviewed;archive;https://datarep.app.ist.ac.at/91/;https://datarep.app.ist.ac.at/91/1/RSC_Austrian%20_Publications_2013-2017.zip;  Villanyi, Marton   RSC Austrian Publications 2013-2017.  [Data Collection]    (Submitted)  ;10.15479/AT:ISTA:91",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "d068f316-9efc-5ce3-b4db-1454fc9faa18",
-    "notes": [
-        "Data on Austrian open access publication output at RSC from 2013-2017 including data analysis."
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:91"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Library information sciences"
-        }
-    ],
-    "title": [
-        "RSC Austrian Publications 2013-2017"
-    ],
-    "url": "https://datarep.app.ist.ac.at/91/1/RSC_Austrian%20_Publications_2013-2017.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/da929850-9fe3-5c3c-85e2-85ab2a56194b.json b/oaitestdata/ist-oai_dc/SET_1/json/da929850-9fe3-5c3c-85e2-85ab2a56194b.json
deleted file mode 100644
index 171af195..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/da929850-9fe3-5c3c-85e2-85ab2a56194b.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:74",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "image",
-        "video"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:74",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/74/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Nikolic, Nela",
-        "Bergmiller, Tobias"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:74;2018-02-07T07:56:24Z;Time-lapse microscopy data;Bergmiller, Tobias;Nikolic, Nela;579 Microorganisms, fungi, algae;Nela Nikolic, Tobias Bergmiller, Alexandra Vandervelde, Tanino G. Albanese, Lendert Gelens, and Isabella Moll (2018)\r\n\u201cAutoregulation of mazEF expression underlies growth heterogeneity in bacterial populations\u201d Nucleic Acids Research, doi: 10.1093/nar/gky079;\r\nmicroscopy experiments by Tobias Bergmiller; image and data analysis by Nela Nikolic.;Data Collection;NonPeerReviewed;video;video;image;https://datarep.app.ist.ac.at/74/;https://datarep.app.ist.ac.at/74/2/15-11-05.zip;https://datarep.app.ist.ac.at/74/3/15-07-31.zip;https://datarep.app.ist.ac.at/74/4/Images_for_analysis.zip;  Bergmiller, Tobias and Nikolic, Nela   Time-lapse microscopy data.  [Data Collection]    (In Press)  ;10.15479/AT:ISTA:74;10.15479/AT:ISTA:74;10.15479/AT:ISTA:74",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "da929850-9fe3-5c3c-85e2-85ab2a56194b",
-    "notes": [
-        "Nela Nikolic, Tobias Bergmiller, Alexandra Vandervelde, Tanino G. Albanese, Lendert Gelens, and Isabella Moll (2018)\r\n\u201cAutoregulation of mazEF expression underlies growth heterogeneity in bacterial populations\u201d Nucleic Acids Research, doi: 10.1093/nar/gky079;\r\nmicroscopy experiments by Tobias Bergmiller; image and data analysis by Nela Nikolic."
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:74"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Microorganisms"
-        },
-        {
-            "name": "fungi"
-        },
-        {
-            "name": "algae"
-        }
-    ],
-    "title": [
-        "Time-lapse microscopy data"
-    ],
-    "url": "https://datarep.app.ist.ac.at/74/4/Images_for_analysis.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/dcb08ece-b86d-56ac-9b8e-70711b9fe2e4.json b/oaitestdata/ist-oai_dc/SET_1/json/dcb08ece-b86d-56ac-9b8e-70711b9fe2e4.json
deleted file mode 100644
index f9676771..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/dcb08ece-b86d-56ac-9b8e-70711b9fe2e4.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:45",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "archive"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:45",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/45/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Landon, Matthieu",
-        "Jajoo, Rishi",
-        "Luka\u010di\u0161in, Martin"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:45;2017-03-30T14:34:05Z;MATLAB analysis code for 'Sequence-Specific Thermodynamic Properties of Nucleic Acids Influence Both Transcriptional Pausing and Backtracking in Yeast';Luka\u010di\u0161in, Martin;Landon, Matthieu;Jajoo, Rishi;571 Physiology;579 Microorganisms, fungi, algae;MATLAB code and processed datasets available for reproducing the results in: \r\nLuka\u010di\u0161in, M.*, Landon, M.*, Jajoo, R*. (2016) Sequence-Specific Thermodynamic Properties of Nucleic Acids Influence Both Transcriptional Pausing and Backtracking in Yeast.\r\n*equal contributions;Data Collection;NonPeerReviewed;archive;https://datarep.app.ist.ac.at/45/;https://datarep.app.ist.ac.at/45/1/PaperCode.zip;  Luka\u010di\u0161in, Martin and Landon, Matthieu and Jajoo, Rishi   MATLAB analysis code for 'Sequence-Specific Thermodynamic Properties of Nucleic Acids Influence Both Transcriptional Pausing and Backtracking in Yeast'.  [Data Collection]     ;10.15479/AT:ISTA:45",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "dcb08ece-b86d-56ac-9b8e-70711b9fe2e4",
-    "notes": [
-        "MATLAB code and processed datasets available for reproducing the results in: \r\nLuka\u010di\u0161in, M.*, Landon, M.*, Jajoo, R*. (2016) Sequence-Specific Thermodynamic Properties of Nucleic Acids Influence Both Transcriptional Pausing and Backtracking in Yeast.\r\n*equal contributions"
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:45"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Physiology"
-        },
-        {
-            "name": "Microorganisms"
-        },
-        {
-            "name": "fungi"
-        },
-        {
-            "name": "algae"
-        }
-    ],
-    "title": [
-        "MATLAB analysis code for 'Sequence-Specific Thermodynamic Properties of Nucleic Acids Influence Both Transcriptional Pausing and Backtracking in Yeast'"
-    ],
-    "url": "https://datarep.app.ist.ac.at/45/1/PaperCode.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/dd2e1e45-7158-5987-b96c-9adbdba6124d.json b/oaitestdata/ist-oai_dc/SET_1/json/dd2e1e45-7158-5987-b96c-9adbdba6124d.json
deleted file mode 100644
index b21b00e7..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/dd2e1e45-7158-5987-b96c-9adbdba6124d.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:82 ",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "archive"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:82",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/82/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Kondermann, Daniel",
-        "Sellent, Anita",
-        "Rother, Carsten",
-        "Alhaija, Hassan Abu"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:82;2018-01-04T07:53:31Z;Graph matching problems for GraphFlow \u2013 6D Large Displacement Scene Flow;Alhaija, Hassan Abu;Sellent, Anita;Kondermann, Daniel;Rother, Carsten;000 Computer science, knowledge & systems;001 Knowledge;Graph matching problems for large displacement optical flow of RGB-D images.;Data Collection;NonPeerReviewed;archive;https://datarep.app.ist.ac.at/82/;https://datarep.app.ist.ac.at/82/1/GraphFlowMatchingProblems.zip;  Alhaija, Hassan Abu and Sellent, Anita and Kondermann, Daniel and Rother, Carsten   Graph matching problems for GraphFlow \u2013 6D Large Displacement Scene Flow.  [Data Collection]     ;10.15479/AT:ISTA:82 ",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "dd2e1e45-7158-5987-b96c-9adbdba6124d",
-    "notes": [
-        "Graph matching problems for large displacement optical flow of RGB-D images."
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:82"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Computer science"
-        },
-        {
-            "name": "knowledge"
-        },
-        {
-            "name": "systems"
-        },
-        {
-            "name": "Knowledge"
-        }
-    ],
-    "title": [
-        "Graph matching problems for GraphFlow \u2013 6D Large Displacement Scene Flow"
-    ],
-    "url": "https://datarep.app.ist.ac.at/82/1/GraphFlowMatchingProblems.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/e29fe838-ea0a-534c-b9a7-7dd2972ba57e.json b/oaitestdata/ist-oai_dc/SET_1/json/e29fe838-ea0a-534c-b9a7-7dd2972ba57e.json
deleted file mode 100644
index 5d001818..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/e29fe838-ea0a-534c-b9a7-7dd2972ba57e.json
+++ /dev/null
@@ -1,49 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:109",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "archive"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:109",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/109/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Vicoso, Beatriz"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:109;2018-07-24T11:51:46Z;Input files and scripts from \"Evolution of gene dosage on the Z-chromosome of schistosome parasites\" by Picard M.A.L., et al (2018);Vicoso, Beatriz;570 Life sciences; biology;576 Genetics and evolution;Input files and scripts from \"Evolution of gene dosage on the Z-chromosome of schistosome parasites\" by Picard M.A.L., et al (2018).;Data Collection;NonPeerReviewed;archive;https://datarep.app.ist.ac.at/109/;https://datarep.app.ist.ac.at/109/1/SupplementaryMethods.zip;  Vicoso, Beatriz   Input files and scripts from \"Evolution of gene dosage on the Z-chromosome of schistosome parasites\" by Picard M.A.L., et al (2018).  [Data Collection]    (In Press)  ;10.15479/AT:ISTA:109",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "e29fe838-ea0a-534c-b9a7-7dd2972ba57e",
-    "notes": [
-        "Input files and scripts from \"Evolution of gene dosage on the Z-chromosome of schistosome parasites\" by Picard M.A.L., et al (2018)."
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:109"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Life sciences"
-        },
-        {
-            "name": "biology"
-        },
-        {
-            "name": "Genetics evolution"
-        }
-    ],
-    "title": [
-        "Input files and scripts from \"Evolution of gene dosage on the Z-chromosome of schistosome parasites\" by Picard M.A.L., et al (2018)"
-    ],
-    "url": "https://datarep.app.ist.ac.at/109/1/SupplementaryMethods.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/e7a6e3d7-6d4f-5510-b138-de5661848bb0.json b/oaitestdata/ist-oai_dc/SET_1/json/e7a6e3d7-6d4f-5510-b138-de5661848bb0.json
deleted file mode 100644
index fbcfe6ea..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/e7a6e3d7-6d4f-5510-b138-de5661848bb0.json
+++ /dev/null
@@ -1,43 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:86",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "archive"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:86",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/86/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Villanyi, Marton"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:86;2018-01-16T14:30:18Z;Data Check IOP Scopus vs. Publisher;Villanyi, Marton;020 Library and information sciences;Comparison of Scopus' and publisher's data on Austrian publication output at IOP. ;Data Collection;NonPeerReviewed;archive;https://datarep.app.ist.ac.at/86/;https://datarep.app.ist.ac.at/86/1/Data_Check_IOP_Scopus_vs._Publisher.zip;  Villanyi, Marton   Data Check IOP Scopus vs. Publisher.  [Data Collection]    (Submitted)  ;10.15479/AT:ISTA:86",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "e7a6e3d7-6d4f-5510-b138-de5661848bb0",
-    "notes": [
-        "Comparison of Scopus' and publisher's data on Austrian publication output at IOP. "
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:86"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Library information sciences"
-        }
-    ],
-    "title": [
-        "Data Check IOP Scopus vs. Publisher"
-    ],
-    "url": "https://datarep.app.ist.ac.at/86/1/Data_Check_IOP_Scopus_vs._Publisher.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/e8725ed3-2627-5d88-924d-a588907d5558.json b/oaitestdata/ist-oai_dc/SET_1/json/e8725ed3-2627-5d88-924d-a588907d5558.json
deleted file mode 100644
index aee139fa..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/e8725ed3-2627-5d88-924d-a588907d5558.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:61",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "archive",
-        "dataset"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:61",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/61/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Berry, Michael J, II",
-        "Schneidman, Elad",
-        "Amodei, Dario",
-        "Bialek, William",
-        "Tkacik, Gasper",
-        "Marre, Olivier"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:61;2017-04-12T08:05:53Z;Multi-electrode array recording from salamander retinal ganglion cells;Marre, Olivier;Tkacik, Gasper;Amodei, Dario;Schneidman, Elad;Bialek, William;Berry, Michael J, II;570 Life sciences; biology;This data was collected as part of the study [1]. It consists of preprocessed multi-electrode array recording from 160 salamander retinal ganglion cells responding to 297 repeats of a 19 s natural movie. The data is available in two formats: (1) a .mat file containing an array with dimensions \u201cnumber of repeats\u201d x \u201cnumber of neurons\u201d x \u201ctime in a repeat\u201d; (2) a zipped .txt file containing the same data represented as an array with dimensions \u201cnumber of neurons\u201d x \u201cnumber of samples\u201d, where the number of samples is equal to the product of the number of repeats and timebins within a repeat. The time dimension is divided into 20 ms time windows, and the array is binary indicating whether a given cell elicited at least one spike in a given time window during a particular repeat. See the reference below for details regarding collection and preprocessing:\r\n\r\n[1] Tka\u010dik G, Marre O, Amodei D, Schneidman E, Bialek W, Berry MJ II. Searching for Collective Behavior in a Large Network of Sensory Neurons. PLoS Comput Biol. 2014;10(1):e1003408.;Data Collection;NonPeerReviewed;dataset;archive;https://datarep.app.ist.ac.at/61/;https://datarep.app.ist.ac.at/61/1/bint_fishmovie32_100.mat;https://datarep.app.ist.ac.at/61/2/bint_fishmovie32_100.zip;  Marre, Olivier and Tkacik, Gasper and Amodei, Dario and Schneidman, Elad and Bialek, William and Berry, Michael J, II   Multi-electrode array recording from salamander retinal ganglion cells.  [Data Collection]     ;10.15479/AT:ISTA:61;10.15479/AT:ISTA:61",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "e8725ed3-2627-5d88-924d-a588907d5558",
-    "notes": [
-        "This data was collected as part of the study [1]. It consists of preprocessed multi-electrode array recording from 160 salamander retinal ganglion cells responding to 297 repeats of a 19 s natural movie. The data is available in two formats: (1) a .mat file containing an array with dimensions \u201cnumber of repeats\u201d x \u201cnumber of neurons\u201d x \u201ctime in a repeat\u201d; (2) a zipped .txt file containing the same data represented as an array with dimensions \u201cnumber of neurons\u201d x \u201cnumber of samples\u201d, where the number of samples is equal to the product of the number of repeats and timebins within a repeat. The time dimension is divided into 20 ms time windows, and the array is binary indicating whether a given cell elicited at least one spike in a given time window during a particular repeat. See the reference below for details regarding collection and preprocessing:\r\n\r\n[1] Tka\u010dik G, Marre O, Amodei D, Schneidman E, Bialek W, Berry MJ II. Searching for Collective Behavior in a Large Network of Sensory Neurons. PLoS Comput Biol. 2014;10(1):e1003408."
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:61"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Life sciences"
-        },
-        {
-            "name": "biology"
-        }
-    ],
-    "title": [
-        "Multi-electrode array recording from salamander retinal ganglion cells"
-    ],
-    "url": "https://datarep.app.ist.ac.at/61/2/bint_fishmovie32_100.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/e8b54b4e-72fe-5abf-99da-b274861f86ff.json b/oaitestdata/ist-oai_dc/SET_1/json/e8b54b4e-72fe-5abf-99da-b274861f86ff.json
deleted file mode 100644
index 2c80897d..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/e8b54b4e-72fe-5abf-99da-b274861f86ff.json
+++ /dev/null
@@ -1,43 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:87",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "archive"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:87",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/87/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Villanyi, Marton"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:87;2018-01-16T14:30:42Z;Data Check RSC Scopus vs. FWF;Villanyi, Marton;020 Library and information sciences;Comparison of Scopus' and FWF's data on Austrian publication output at RSC. ;Data Collection;NonPeerReviewed;archive;https://datarep.app.ist.ac.at/87/;https://datarep.app.ist.ac.at/87/1/Data_Check_RSC_Scopus_vs._FWF.zip;  Villanyi, Marton   Data Check RSC Scopus vs. FWF.  [Data Collection]    (Submitted)  ;10.15479/AT:ISTA:87",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "e8b54b4e-72fe-5abf-99da-b274861f86ff",
-    "notes": [
-        "Comparison of Scopus' and FWF's data on Austrian publication output at RSC. "
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:87"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Library information sciences"
-        }
-    ],
-    "title": [
-        "Data Check RSC Scopus vs. FWF"
-    ],
-    "url": "https://datarep.app.ist.ac.at/87/1/Data_Check_RSC_Scopus_vs._FWF.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/ist-oai_dc/SET_1/json/fa1bb827-bd71-569c-8db8-070bc8b64ddd.json b/oaitestdata/ist-oai_dc/SET_1/json/fa1bb827-bd71-569c-8db8-070bc8b64ddd.json
deleted file mode 100644
index 0f0030d4..00000000
--- a/oaitestdata/ist-oai_dc/SET_1/json/fa1bb827-bd71-569c-8db8-070bc8b64ddd.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.15479/AT:ISTA:35 ",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "archive"
-    ],
-    "MetaDataAccess": "http://datarep.app.ist.ac.at/cgi/oai2?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:datarep.app.ist.ac.at:35",
-    "RelatedIdentifier": [
-        "https://datarep.app.ist.ac.at/35/"
-    ],
-    "ResourceType": [
-        "Data Collection"
-    ],
-    "author": [
-        "Ellis, Thomas"
-    ],
-    "fulltext": "oai:datarep.app.ist.ac.at:35;2017-03-30T14:27:13Z;Data on pollinator observations and offpsring phenotypes;Ellis, Thomas;576 Genetics and evolution;577 Ecology;Data from array experiments investigating pollinator behaviour on snapdragons in controlled conditions, and their effect on plant mating. Data were collected as part of Tom Ellis' PhD thesis , submitted February 2016.\r\n\r\nWe placed a total of 36 plants in a grid inside a closed organza tent, with a single hive of commercially bred bumblebees (Bombus hortorum). We used only the yellow-flowered Antirrhinum majus striatum and the magenta-flowered Antirrhinum majus pseudomajus, at ratios of 6:36, 12:24, 18:18, 24:12 and 30:6.\r\n\r\nAfter 24 hours to learn how to deal with snapdragons, I observed pollinators foraging on plants, and recorded the transitions between plants. Thereafter seeds on plants were allowed to develops. A sample of these were grown to maturity when their flower colour could be determined, and they were scored as yellow, magenta, or hybrid.;Data Collection;NonPeerReviewed;archive;https://datarep.app.ist.ac.at/35/;https://datarep.app.ist.ac.at/35/1/array_data.zip;  Ellis, Thomas   Data on pollinator observations and offpsring phenotypes.  [Data Collection]     ;10.15479/AT:ISTA:35 ",
-    "group": "ist",
-    "groups": [
-        {
-            "name": "ist"
-        }
-    ],
-    "name": "fa1bb827-bd71-569c-8db8-070bc8b64ddd",
-    "notes": [
-        "Data from array experiments investigating pollinator behaviour on snapdragons in controlled conditions, and their effect on plant mating. Data were collected as part of Tom Ellis' PhD thesis , submitted February 2016.\r\n\r\nWe placed a total of 36 plants in a grid inside a closed organza tent, with a single hive of commercially bred bumblebees (Bombus hortorum). We used only the yellow-flowered Antirrhinum majus striatum and the magenta-flowered Antirrhinum majus pseudomajus, at ratios of 6:36, 12:24, 18:18, 24:12 and 30:6.\r\n\r\nAfter 24 hours to learn how to deal with snapdragons, I observed pollinators foraging on plants, and recorded the transitions between plants. Thereafter seeds on plants were allowed to develops. A sample of these were grown to maturity when their flower colour could be determined, and they were scored as yellow, magenta, or hybrid."
-    ],
-    "oai_identifier": [
-        "oai:datarep.app.ist.ac.at:35"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Genetics evolution"
-        },
-        {
-            "name": "Ecology"
-        }
-    ],
-    "title": [
-        "Data on pollinator observations and offpsring phenotypes"
-    ],
-    "url": "https://datarep.app.ist.ac.at/35/1/array_data.zip"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/01d2b474-a13f-5e8c-aa66-e0ed7d09253b.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/01d2b474-a13f-5e8c-aa66-e0ed7d09253b.json
deleted file mode 100644
index 98750b44..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/01d2b474-a13f-5e8c-aa66-e0ed7d09253b.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/ApJS/199/3",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/ApJS/199/3"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2012ApJS..199....3R"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Ross N.P., Myers A.D., Sheldon E.S., et al."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/ApJS/199/3;2018-04-05T10:00:00Z;J.ApJS;ivo_managed;Ross N.P., Myers A.D., Sheldon E.S., et al.;The quasars MMT-BOSS pilot survey (Ross+, 2012);CDS;2017;Photometry:wide-band;QSOs;Redshifts;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/ApJS/199/3;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/ApJS/199/3;2012ApJS..199....3R;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "01d2b474-a13f-5e8c-aa66-e0ed7d09253b",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/ApJS/199/3"
-    ],
-    "oai_set": [
-        "J.ApJS",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Photometry wide-band"
-        },
-        {
-            "name": "QSOs"
-        },
-        {
-            "name": "Redshifts"
-        }
-    ],
-    "title": [
-        "The quasars MMT-BOSS pilot survey (Ross+, 2012)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/ApJS/199/3"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/01d67619-d482-5343-881f-507d4d98aa22.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/01d67619-d482-5343-881f-507d4d98aa22.json
deleted file mode 100644
index 487ae777..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/01d67619-d482-5343-881f-507d4d98aa22.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/MNRAS/421/2342",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/MNRAS/421/2342"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2012MNRAS.421.2342S"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Steffen J.H., Fabrycky D.C., Ford E.B., et al."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/MNRAS/421/2342;2018-04-05T10:00:00Z;J.MNRAS;ivo_managed;Steffen J.H., Fabrycky D.C., Ford E.B., et al.;4 Kepler systems transit timing observations (Steffen+, 2012);CDS;2018;Multiple_Stars;Planets+Asteroids;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/MNRAS/421/2342;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/MNRAS/421/2342;2012MNRAS.421.2342S;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "01d67619-d482-5343-881f-507d4d98aa22",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/MNRAS/421/2342"
-    ],
-    "oai_set": [
-        "J.MNRAS",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Multiple_Stars"
-        },
-        {
-            "name": "Planets"
-        },
-        {
-            "name": "Asteroids"
-        }
-    ],
-    "title": [
-        "4 Kepler systems transit timing observations (Steffen+, 2012)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/MNRAS/421/2342"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/021576ca-d65e-551e-b6c4-6b58b793ced7.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/021576ca-d65e-551e-b6c4-6b58b793ced7.json
deleted file mode 100644
index a9958846..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/021576ca-d65e-551e-b6c4-6b58b793ced7.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/A+A/623/L11",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/A+A/623/L11"
-    ],
-    "PublicationTimestamp": "2019-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2019A&A...623L..11L"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Lacour S., Nowak M., Wang J., et al."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/A+A/623/L11;2019-03-27T07:28:00Z;J.A_A;ivo_managed;Lacour S., Nowak M., Wang J., et al.;HR8799e K-band spectrum (Lacour+, 2019);CDS;2019;Multiple_Stars;Spectroscopy;Exoplanets;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/A+A/623/L11;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/623/L11;2019A&A...623L..11L;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "021576ca-d65e-551e-b6c4-6b58b793ced7",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/A+A/623/L11"
-    ],
-    "oai_set": [
-        "J.A_A",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Multiple_Stars"
-        },
-        {
-            "name": "Spectroscopy"
-        },
-        {
-            "name": "Exoplanets"
-        }
-    ],
-    "title": [
-        "HR8799e K-band spectrum (Lacour+, 2019)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/623/L11"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/022707ea-f783-535b-bc89-2fa72877f71b.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/022707ea-f783-535b-bc89-2fa72877f71b.json
deleted file mode 100644
index 65248a44..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/022707ea-f783-535b-bc89-2fa72877f71b.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/VI/155",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/VI/155"
-    ],
-    "PublicationTimestamp": "2019-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2019yCat.6155....0E"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Eglitis I., Eglite M., Kazantseva L.V., Shatokhina S.V., Protsyuk Yu.I., Kovylianskaya O.E., Andruk V.M."
-    ],
-    "fulltext": "ivo://CDS.VizieR/VI/155;2019-04-08T14:55:09Z;VI;ivo_managed;Eglitis I., Eglite M., Kazantseva L.V., Shatokhina S.V., Protsyuk Yu.I., Kovylianskaya O.E., Andruk V.M.;Topocentric positions of Pluto (Eglitis+, 2018);CDS;2019;Positional_Data;Planets+Asteroids;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/VI/155;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?VI/155;2019yCat.6155....0E;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "022707ea-f783-535b-bc89-2fa72877f71b",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/VI/155"
-    ],
-    "oai_set": [
-        "VI",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Positional_Data"
-        },
-        {
-            "name": "Planets"
-        },
-        {
-            "name": "Asteroids"
-        }
-    ],
-    "title": [
-        "Topocentric positions of Pluto (Eglitis+, 2018)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?VI/155"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/04f45076-bf24-589d-9e76-b70e4c356e69.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/04f45076-bf24-589d-9e76-b70e4c356e69.json
deleted file mode 100644
index 72781625..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/04f45076-bf24-589d-9e76-b70e4c356e69.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Michael Preciado <Michael.E.Preciado@nasa.gov>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://nasa.heasarc/atlasspecz",
-    "MetadataAccess": [
-        "ivo://nasa.heasarc/atlasspecz"
-    ],
-    "PublicationTimestamp": "2019-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "NASA/GSFC HEASARC"
-    ],
-    "ResourceType": [
-        "AstroObjects"
-    ],
-    "author": [
-        "Mao et al."
-    ],
-    "fulltext": "ivo://nasa.heasarc/atlasspecz;2019-06-17T07:00:59Z;Mao et al.;ATLargeAreaSurvey(ATLAS)SpectroscopicClasses&RedshiftsCatalog;NASA/GSFC HEASARC;2019;Survey Source;Michael Preciado <Michael.E.Preciado@nasa.gov>;AstroObjects;ivo://nasa.heasarc/atlasspecz;https://heasarc.gsfc.nasa.gov/W3Browse/all/atlasspecz.html;\n        https://heasarc.gsfc.nasa.gov/cgi-bin/W3Browse/w3query.pl?tablehead=name=heasarc_atlasspecz&Action=More+Options&Action=Parameter+Search&ConeAdd=1\n      ;text/xml;text/xml;\n      The Australia Telescope Large Area Survey (ATLAS) has surveyed 7 square degrees of sky around the Chandra Deep Field South (CDF-S) and the European Large Area ISO Survey-South 1 (ELAIS-S1) fields at 1.4 GHz. ATLAS aims to reach a uniform sensitivity of 10 &micro;Jy (&micro;Jy) beam&lt;sup&gt;-1&lt;/sup&gt; rms over the entire region with first data release currently reaching ~ 30 uJy beam&lt;sup&gt;-1&lt;/sup&gt; rms. Here the authors present 466 new spectroscopic redshifts for radio sources in ATLAS as part of their optical follow-up program. Of the 466 radio sources with new spectroscopic redshifts, 142 have star-forming optical spectra, 282 show evidence for active galactic nuclei (AGN) in their optical spectra, 10 have stellar spectra and 32 have spectra revealing redshifts, but with insufficient features to classify. The authors compare their spectroscopic classifications with two mid-infrared diagnostics and find them to be in broad agreement. ATLAS is a pathfinder for the forthcoming Evolution Map of the Universe (EMU) survey and the data presented in this paper will be used to guide EMU's survey design and early science papers. This paper uses H&lt;sub&gt;0&lt;/sub&gt; = 70 km s&lt;sup&gt;-1&lt;/sup&gt; Mpc&lt;sup&gt;-1&lt;/sup&gt;, Omega&lt;sub&gt;M&lt;/sub&gt; = 0.3 and Omega&lt;sub&gt;Lambda&lt;/sub&gt; = 0.7, and the web-based calculator of Wright (2006, PASP, 118, 1711) to estimate the distance-dependent physical parameters.\n    ",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "04f45076-bf24-589d-9e76-b70e4c356e69",
-    "notes": [
-        "\n      The Australia Telescope Large Area Survey (ATLAS) has surveyed 7 square degrees of sky around the Chandra Deep Field South (CDF-S) and the European Large Area ISO Survey-South 1 (ELAIS-S1) fields at 1.4 GHz. ATLAS aims to reach a uniform sensitivity of 10 &micro;Jy (&micro;Jy) beam&lt;sup&gt;-1&lt;/sup&gt; rms over the entire region with first data release currently reaching ~ 30 uJy beam&lt;sup&gt;-1&lt;/sup&gt; rms. Here the authors present 466 new spectroscopic redshifts for radio sources in ATLAS as part of their optical follow-up program. Of the 466 radio sources with new spectroscopic redshifts, 142 have star-forming optical spectra, 282 show evidence for active galactic nuclei (AGN) in their optical spectra, 10 have stellar spectra and 32 have spectra revealing redshifts, but with insufficient features to classify. The authors compare their spectroscopic classifications with two mid-infrared diagnostics and find them to be in broad agreement. ATLAS is a pathfinder for the forthcoming Evolution Map of the Universe (EMU) survey and the data presented in this paper will be used to guide EMU's survey design and early science papers. This paper uses H&lt;sub&gt;0&lt;/sub&gt; = 70 km s&lt;sup&gt;-1&lt;/sup&gt; Mpc&lt;sup&gt;-1&lt;/sup&gt;, Omega&lt;sub&gt;M&lt;/sub&gt; = 0.3 and Omega&lt;sub&gt;Lambda&lt;/sub&gt; = 0.7, and the web-based calculator of Wright (2006, PASP, 118, 1711) to estimate the distance-dependent physical parameters.\n    "
-    ],
-    "oai_identifier": [
-        "ivo://nasa.heasarc/atlasspecz"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Survey Source"
-        }
-    ],
-    "title": [
-        "ATLargeAreaSurvey(ATLAS)SpectroscopicClasses&RedshiftsCatalog"
-    ],
-    "url": "https://heasarc.gsfc.nasa.gov/W3Browse/all/atlasspecz.html"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/0a26e96c-9e54-5cc8-8d5f-d9ba2ab6ef25.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/0a26e96c-9e54-5cc8-8d5f-d9ba2ab6ef25.json
deleted file mode 100644
index 0690e99b..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/0a26e96c-9e54-5cc8-8d5f-d9ba2ab6ef25.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/A+A/463/175",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/A+A/463/175"
-    ],
-    "PublicationTimestamp": "2007-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2007"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2007A&A...463..175V"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Vig S., Ghosh S.K., Ojha D.K., Verma R.P."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/A+A/463/175;2018-04-05T10:00:00Z;J.A_A;ivo_managed;Vig S., Ghosh S.K., Ojha D.K., Verma R.P.;Infrared study of IRAS 14416-5937 region (Vig+, 2007);CDS;2007;Stars;YSOs;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/A+A/463/175;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/463/175;2007A&A...463..175V;text/xml+votable;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0a26e96c-9e54-5cc8-8d5f-d9ba2ab6ef25",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/A+A/463/175"
-    ],
-    "oai_set": [
-        "J.A_A",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Stars"
-        },
-        {
-            "name": "YSOs"
-        }
-    ],
-    "title": [
-        "Infrared study of IRAS 14416-5937 region (Vig+, 2007)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/463/175"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/0a2f66f9-c788-538d-a5a1-eddb9a91c5dc.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/0a2f66f9-c788-538d-a5a1-eddb9a91c5dc.json
deleted file mode 100644
index 87186814..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/0a2f66f9-c788-538d-a5a1-eddb9a91c5dc.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/A+A/558/A149",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/A+A/558/A149"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2013A&A...558A.149B"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Burtscher L., Meisenheimer K., Tristram K.R.W., Jaffe W., Honig S.F., Davies R.I., Kishimoto M., Pott J.-U., Rottgering H., Schartmann M., Weigelt G., Wolf S."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/A+A/558/A149;2018-04-05T10:00:00Z;J.A_A;ivo_managed;Burtscher L., Meisenheimer K., Tristram K.R.W., Jaffe W., Honig S.F., Davies R.I., Kishimoto M., Pott J.-U., Rottgering H., Schartmann M., Weigelt G., Wolf S.;VLTI/MIDI AGN Large Program observations (Burtscher+, 2013);CDS;2017;AGN;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/A+A/558/A149;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/558/A149;2013A&A...558A.149B;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0a2f66f9-c788-538d-a5a1-eddb9a91c5dc",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/A+A/558/A149"
-    ],
-    "oai_set": [
-        "J.A_A",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "AGN"
-        }
-    ],
-    "title": [
-        "VLTI/MIDI AGN Large Program observations (Burtscher+, 2013)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/558/A149"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/0a3aab25-d8bf-523c-8811-feb5ec2b962c.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/0a3aab25-d8bf-523c-8811-feb5ec2b962c.json
deleted file mode 100644
index 07f887aa..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/0a3aab25-d8bf-523c-8811-feb5ec2b962c.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "IVOA Data Models WG <dm@ivoa.net>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://ivoa.net/std/ivoadm",
-    "MetadataAccess": [
-        "ivo://ivoa.net/std/ivoadm"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "IVOA"
-    ],
-    "author": [
-        "Donaldson, T.",
-        "Laurino, O.",
-        "Bourges, L.",
-        "Salgado, J.",
-        "Lemson, G.",
-        "Demleitner, M.",
-        "Dowler, P.",
-        "Graham, M.",
-        "Gray, N.",
-        "Cresitello-Dittmar, M.",
-        "Michel, L."
-    ],
-    "fulltext": "ivo://ivoa.net/std/ivoadm;2018-05-19T09:00:00Z;Standard;ivo_managed;Lemson, G.;Laurino, O.;Bourges, L.;Cresitello-Dittmar, M.;Demleitner, M.;Donaldson, T.;Dowler, P.;Graham, M.;Gray, N.;Michel, L.;Salgado, J.;The ivoa data model;IVOA;2017;Virtual observatory;IVOA Data Models WG <dm@ivoa.net>;ivo://ivoa.net/std/ivoadm;http://ivoa.net/documents/VODML/;1.0;\n\t\t\tUltimately all types in a VO-DML model are defined as hierarchies \n\t\t\tof primitive types. This Model defines a special, predefined model \n\t\t\tthat contains a set of the most common of such types: integer, \n\t\t\treal, string etc. This\n    ",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0a3aab25-d8bf-523c-8811-feb5ec2b962c",
-    "notes": [
-        "\n\t\t\tUltimately all types in a VO-DML model are defined as hierarchies \n\t\t\tof primitive types. This Model defines a special, predefined model \n\t\t\tthat contains a set of the most common of such types: integer, \n\t\t\treal, string etc. This\n    "
-    ],
-    "oai_identifier": [
-        "ivo://ivoa.net/std/ivoadm"
-    ],
-    "oai_set": [
-        "Standard",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Virtual observatory"
-        }
-    ],
-    "title": [
-        "The ivoa data model"
-    ],
-    "url": "http://ivoa.net/documents/VODML/"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/0a3c084f-3f66-549d-8677-8de5fdb09946.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/0a3c084f-3f66-549d-8677-8de5fdb09946.json
deleted file mode 100644
index 8d220ca4..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/0a3c084f-3f66-549d-8677-8de5fdb09946.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Michael Preciado <Michael.E.Preciado@nasa.gov>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://nasa.heasarc/orionffcxo",
-    "MetadataAccess": [
-        "ivo://nasa.heasarc/orionffcxo"
-    ],
-    "PublicationTimestamp": "2019-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "NASA/GSFC HEASARC"
-    ],
-    "ResourceType": [
-        "AstroObjects"
-    ],
-    "author": [
-        "Ramirez et al."
-    ],
-    "fulltext": "ivo://nasa.heasarc/orionffcxo;2019-06-17T07:06:37Z;Ramirez et al.;Orion Flanking Fields Chandra X-Ray Point Source Catalog;NASA/GSFC HEASARC;2019;Survey Source;Michael Preciado <Michael.E.Preciado@nasa.gov>;AstroObjects;ivo://nasa.heasarc/orionffcxo;https://heasarc.gsfc.nasa.gov/W3Browse/all/orionffcxo.html;\n        https://heasarc.gsfc.nasa.gov/cgi-bin/W3Browse/w3query.pl?tablehead=name=heasarc_orionffcxo&Action=More+Options&Action=Parameter+Search&ConeAdd=1\n      ;text/xml;text/xml;\n      This table contains the results of Chandra observations of two flanking fields (FFs) in Orion outside the Orion Nebula Cluster (ONC), in the form of a catalog of 417 sources, which includes X-ray luminosity, optical and infrared photometry, and X-ray variability information. 91 variable sources were found, 33 of which have flarelike light curves, and 11 of which have a pattern of a steady increase or decrease over a 10 hour period. The optical and infrared photometry for the stars identified as X-ray sources are consistent with most of these objects being pre-main-sequence stars with ages younger than 10 Myr. The two flanking fields in Orion were observed with the Advanced CCD Imaging Spectrometer (ACIS) detector on board the Chandra X-Ray Observatory. The north Orion flanking field (NOFF) is centered at a J2000 RA and Declination of 05:35:19, -04:48:15, which is about 36' (~5 pc, at a distance of 470 pc) north of the Trapezium cluster and was observed on 2002 August 26 with a total exposure time of 48.8 ks. The south Orion flanking field (SOFF), centered at a J2000 RA and Declination of 05:35:06, -05:40:48, which is about 17' (~ 2.5pc, at a distance of 470 pc) south of the Trapezium cluster, was observed on 2002 September 6 with a total exposure time of 47.9 ks. The data analysis for these observations was performed in the same manner as described in Ramirez et al. (2004, AJ, 127, 2659) for a similar observation of a field in NGC 2264, which should be consulted for the full details. (See also the help file for the HEASARC version of the catalog from the latter reference available at /W3Browse/chandra/ngc2264cxo.html ).\n    ",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0a3c084f-3f66-549d-8677-8de5fdb09946",
-    "notes": [
-        "\n      This table contains the results of Chandra observations of two flanking fields (FFs) in Orion outside the Orion Nebula Cluster (ONC), in the form of a catalog of 417 sources, which includes X-ray luminosity, optical and infrared photometry, and X-ray variability information. 91 variable sources were found, 33 of which have flarelike light curves, and 11 of which have a pattern of a steady increase or decrease over a 10 hour period. The optical and infrared photometry for the stars identified as X-ray sources are consistent with most of these objects being pre-main-sequence stars with ages younger than 10 Myr. The two flanking fields in Orion were observed with the Advanced CCD Imaging Spectrometer (ACIS) detector on board the Chandra X-Ray Observatory. The north Orion flanking field (NOFF) is centered at a J2000 RA and Declination of 05:35:19, -04:48:15, which is about 36' (~5 pc, at a distance of 470 pc) north of the Trapezium cluster and was observed on 2002 August 26 with a total exposure time of 48.8 ks. The south Orion flanking field (SOFF), centered at a J2000 RA and Declination of 05:35:06, -05:40:48, which is about 17' (~ 2.5pc, at a distance of 470 pc) south of the Trapezium cluster, was observed on 2002 September 6 with a total exposure time of 47.9 ks. The data analysis for these observations was performed in the same manner as described in Ramirez et al. (2004, AJ, 127, 2659) for a similar observation of a field in NGC 2264, which should be consulted for the full details. (See also the help file for the HEASARC version of the catalog from the latter reference available at /W3Browse/chandra/ngc2264cxo.html ).\n    "
-    ],
-    "oai_identifier": [
-        "ivo://nasa.heasarc/orionffcxo"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Survey Source"
-        }
-    ],
-    "title": [
-        "Orion Flanking Fields Chandra X-Ray Point Source Catalog"
-    ],
-    "url": "https://heasarc.gsfc.nasa.gov/W3Browse/all/orionffcxo.html"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/0a6d3a79-a6d1-581c-be11-17348f38c710.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/0a6d3a79-a6d1-581c-be11-17348f38c710.json
deleted file mode 100644
index 3195f4ee..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/0a6d3a79-a6d1-581c-be11-17348f38c710.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/PASJ/59/S529",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/PASJ/59/S529"
-    ],
-    "PublicationTimestamp": "2012-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2007PASJ...59S.529L"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Lee H.M., Im M., Wada T., et al."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/PASJ/59/S529;2018-04-05T10:00:00Z;J.PASJ;ivo_managed;Lee H.M., Im M., Wada T., et al.;NEP deep survey at 11um (Lee+, 2007);CDS;2012;Photometry;Galaxies;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/PASJ/59/S529;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/PASJ/59/S529;2007PASJ...59S.529L;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0a6d3a79-a6d1-581c-be11-17348f38c710",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/PASJ/59/S529"
-    ],
-    "oai_set": [
-        "J.PASJ",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Photometry"
-        },
-        {
-            "name": "Galaxies"
-        }
-    ],
-    "title": [
-        "NEP deep survey at 11um (Lee+, 2007)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/PASJ/59/S529"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/0a8c3ec3-4857-538e-bc4c-e91ee3b7c342.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/0a8c3ec3-4857-538e-bc4c-e91ee3b7c342.json
deleted file mode 100644
index 6e686fc4..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/0a8c3ec3-4857-538e-bc4c-e91ee3b7c342.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Michael Preciado <Michael.E.Preciado@nasa.gov>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://nasa.heasarc/ipcultsoft",
-    "MetadataAccess": [
-        "ivo://nasa.heasarc/ipcultsoft"
-    ],
-    "PublicationTimestamp": "2019-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "NASA/GSFC HEASARC"
-    ],
-    "ResourceType": [
-        "AstroObjects"
-    ],
-    "author": [
-        "Thompson, Shelton, Arning"
-    ],
-    "fulltext": "ivo://nasa.heasarc/ipcultsoft;2019-06-17T07:04:24Z;Thompson, Shelton, Arning;Einstein IPC Ultrasoft Sources Catalog;NASA/GSFC HEASARC;2019;Survey Source;Michael Preciado <Michael.E.Preciado@nasa.gov>;AstroObjects;ivo://nasa.heasarc/ipcultsoft;https://heasarc.gsfc.nasa.gov/W3Browse/all/ipcultsoft.html;\n        https://heasarc.gsfc.nasa.gov/cgi-bin/W3Browse/w3query.pl?tablehead=name=heasarc_ipcultsoft&Action=More+Options&Action=Parameter+Search&ConeAdd=1\n      ;text/xml;text/xml;\n      A survey of the entire Einstein IPC database (a total of 5934 sources) has been carried out in order to select objects with strong components of ultrasoft X-ray emission (i.e., emission below 0.5 keV). The selection criteria were based on ratios of counts within three broad energy bands (i.e., X-ray &quot;colors&quot;). A total of 516 objects have been selected, with 202 (39%) having been identified through correlations with other databases. Of the currently identified objects, 45% are active galactic nuclei, 28% are stellar objects, 6% are &quot;normal&quot; galaxies and galaxy clusters, and the remaining 21% are &quot;nonstellar&quot; Galactic objects such as cataclysmic variables, pulsars, and white dwarfs. The selection of sources for this survey was based on the analysis of counts in three broad energy bands defined as C1=0.16-0.56 keV, C2=0.56-1.08 keV, and C3= 1.08-3.5 keV. Ratios of these three bands constituted X-ray 'colors' which in turn were used to estimate the shape of the spectrum over the IPC bandpass. Based on models of X-ray spectra folded through the IPC response function, the following criteria were determined for the selection of ultrasoft sources: C1&gt;0 and R1=C2/C1&lt;0.36. These criteria guarantee an intrinsically soft X-ray spectrum that can be modeled by blackbody temperatures kT&lt;50 keV, power-law spectral indices of &gt;=2, or thermal plasma temperatures T&lt;1 MK (million K). Details of the data analysis can be found in the Thompson et al. (1998) reference.\n    ",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0a8c3ec3-4857-538e-bc4c-e91ee3b7c342",
-    "notes": [
-        "\n      A survey of the entire Einstein IPC database (a total of 5934 sources) has been carried out in order to select objects with strong components of ultrasoft X-ray emission (i.e., emission below 0.5 keV). The selection criteria were based on ratios of counts within three broad energy bands (i.e., X-ray &quot;colors&quot;). A total of 516 objects have been selected, with 202 (39%) having been identified through correlations with other databases. Of the currently identified objects, 45% are active galactic nuclei, 28% are stellar objects, 6% are &quot;normal&quot; galaxies and galaxy clusters, and the remaining 21% are &quot;nonstellar&quot; Galactic objects such as cataclysmic variables, pulsars, and white dwarfs. The selection of sources for this survey was based on the analysis of counts in three broad energy bands defined as C1=0.16-0.56 keV, C2=0.56-1.08 keV, and C3= 1.08-3.5 keV. Ratios of these three bands constituted X-ray 'colors' which in turn were used to estimate the shape of the spectrum over the IPC bandpass. Based on models of X-ray spectra folded through the IPC response function, the following criteria were determined for the selection of ultrasoft sources: C1&gt;0 and R1=C2/C1&lt;0.36. These criteria guarantee an intrinsically soft X-ray spectrum that can be modeled by blackbody temperatures kT&lt;50 keV, power-law spectral indices of &gt;=2, or thermal plasma temperatures T&lt;1 MK (million K). Details of the data analysis can be found in the Thompson et al. (1998) reference.\n    "
-    ],
-    "oai_identifier": [
-        "ivo://nasa.heasarc/ipcultsoft"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Survey Source"
-        }
-    ],
-    "title": [
-        "Einstein IPC Ultrasoft Sources Catalog"
-    ],
-    "url": "https://heasarc.gsfc.nasa.gov/W3Browse/all/ipcultsoft.html"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/11139a9e-d285-5e74-847c-e832dc640d10.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/11139a9e-d285-5e74-847c-e832dc640d10.json
deleted file mode 100644
index 518d7463..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/11139a9e-d285-5e74-847c-e832dc640d10.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/A+A/568/A51",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/A+A/568/A51"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2014A&A...568A..51S"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Schmeja S., Kharchenko N.V., Piskunov A.E., Roeser S., Schilbach E., Froebrich D., Scholz R.-D."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/A+A/568/A51;2018-10-19T10:28:24Z;J.A_A;ivo_managed;Schmeja S., Kharchenko N.V., Piskunov A.E., Roeser S., Schilbach E., Froebrich D., Scholz R.-D.;Milky Way global survey of star clusters. III. (Schmeja+, 2014);CDS;2018;Open_Clusters;Proper_Motions;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/A+A/568/A51;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/568/A51;2014A&A...568A..51S;text/xml+votable;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "11139a9e-d285-5e74-847c-e832dc640d10",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/A+A/568/A51"
-    ],
-    "oai_set": [
-        "J.A_A",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Open_Clusters"
-        },
-        {
-            "name": "Proper_Motions"
-        }
-    ],
-    "title": [
-        "Milky Way global survey of star clusters. III. (Schmeja+, 2014)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/568/A51"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/13755a36-73f9-5c81-8550-a94cd7bc29e9.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/13755a36-73f9-5c81-8550-a94cd7bc29e9.json
deleted file mode 100644
index f4bbed5e..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/13755a36-73f9-5c81-8550-a94cd7bc29e9.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/A+A/616/A175",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/A+A/616/A175"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2018A&A...616A.175Y"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Yang M., Bonanos A.Z., Jiang B.W., Gao J., Xue M.Y., Wang S., Lam M.I., Spetsieri Z.T., Ren Y., Gavras P."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/A+A/616/A175;2018-10-25T11:44:41Z;J.A_A;ivo_managed;Yang M., Bonanos A.Z., Jiang B.W., Gao J., Xue M.Y., Wang S., Lam M.I., Spetsieri Z.T., Ren Y., Gavras P.;Red supergiant stars in the LMC. II. (Yang+, 2018);CDS;2018;Stars;Stars:late-type;Stars:variable;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/A+A/616/A175;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/616/A175;2018A&A...616A.175Y;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "13755a36-73f9-5c81-8550-a94cd7bc29e9",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/A+A/616/A175"
-    ],
-    "oai_set": [
-        "J.A_A",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Stars"
-        },
-        {
-            "name": "Stars late-type"
-        },
-        {
-            "name": "Stars variable"
-        }
-    ],
-    "title": [
-        "Red supergiant stars in the LMC. II. (Yang+, 2018)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/616/A175"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/14678e5b-d9e4-51e2-b5e5-4f270b38bcda.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/14678e5b-d9e4-51e2-b5e5-4f270b38bcda.json
deleted file mode 100644
index 15c135f4..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/14678e5b-d9e4-51e2-b5e5-4f270b38bcda.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/MNRAS/459/140",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/MNRAS/459/140"
-    ],
-    "PublicationTimestamp": "2019-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2016MNRAS.459..140M"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Mereminskiy I.A., Krivonos R.A., Lutovinov A.A., Sazonov S.Y., Revnivtsev M.G., Sunyaev R.A."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/MNRAS/459/140;2019-05-02T11:55:06Z;J.MNRAS;ivo_managed;Mereminskiy I.A., Krivonos R.A., Lutovinov A.A., Sazonov S.Y., Revnivtsev M.G., Sunyaev R.A.;M81, LMC and 3C 273/Coma 17-60keV obs. (Mereminskiy+, 2016);CDS;2019;Galaxies;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/MNRAS/459/140;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/MNRAS/459/140;2016MNRAS.459..140M;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "14678e5b-d9e4-51e2-b5e5-4f270b38bcda",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/MNRAS/459/140"
-    ],
-    "oai_set": [
-        "J.MNRAS",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Galaxies"
-        }
-    ],
-    "title": [
-        "M81, LMC and 3C 273/Coma 17-60keV obs. (Mereminskiy+, 2016)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/MNRAS/459/140"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/15423d91-02b5-572a-a0e2-a2b9a829ee41.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/15423d91-02b5-572a-a0e2-a2b9a829ee41.json
deleted file mode 100644
index 01227504..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/15423d91-02b5-572a-a0e2-a2b9a829ee41.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/A+A/624/A38",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/A+A/624/A38"
-    ],
-    "PublicationTimestamp": "2019-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2019A&A...624A..38D"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Damasso M., Zeng L., Malavolta L., et al."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/A+A/624/A38;2019-04-08T14:51:55Z;J.A_A;ivo_managed;Damasso M., Zeng L., Malavolta L., et al.;Radial velocities of K2-36 (Damasso+, 2019);CDS;2019;Multiple_Stars;Velocities;Exoplanets;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/A+A/624/A38;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/624/A38;2019A&A...624A..38D;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "15423d91-02b5-572a-a0e2-a2b9a829ee41",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/A+A/624/A38"
-    ],
-    "oai_set": [
-        "J.A_A",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Multiple_Stars"
-        },
-        {
-            "name": "Velocities"
-        },
-        {
-            "name": "Exoplanets"
-        }
-    ],
-    "title": [
-        "Radial velocities of K2-36 (Damasso+, 2019)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/624/A38"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/15862d12-1f4a-5df3-bd44-0e8929774bc1.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/15862d12-1f4a-5df3-bd44-0e8929774bc1.json
deleted file mode 100644
index 15bb1d00..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/15862d12-1f4a-5df3-bd44-0e8929774bc1.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/A+AS/117/93",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/A+AS/117/93"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "1996A&AS..117...93S"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Serote Roos M., Boisson C., Joly M."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/A+AS/117/93;2018-10-01T07:46:05Z;J.A_AS;ivo_managed;Serote Roos M., Boisson C., Joly M.;Spectra of 21 late-type stars (Serote Roos+, 1996);CDS;2018;Spectroscopy;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/A+AS/117/93;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+AS/117/93;1996A&AS..117...93S;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "15862d12-1f4a-5df3-bd44-0e8929774bc1",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/A+AS/117/93"
-    ],
-    "oai_set": [
-        "J.A_AS",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Spectroscopy"
-        }
-    ],
-    "title": [
-        "Spectra of 21 late-type stars (Serote Roos+, 1996)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+AS/117/93"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/17016c18-f1d4-5d3e-85a6-9cd23ae4d8cf.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/17016c18-f1d4-5d3e-85a6-9cd23ae4d8cf.json
deleted file mode 100644
index 8ec9e423..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/17016c18-f1d4-5d3e-85a6-9cd23ae4d8cf.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/ApJS/161/154",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/ApJS/161/154"
-    ],
-    "PublicationTimestamp": "2019-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2005ApJS..161..154H"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Hanson M.M., Kudritzki R.-P., Kenworthy M.A., Puls J., Tokunaga A.T."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/ApJS/161/154;2019-02-20T13:53:55Z;J.ApJS;ivo_managed;Hanson M.M., Kudritzki R.-P., Kenworthy M.A., Puls J., Tokunaga A.T.;Near-IR spectral atlas of OB stars (Hanson+, 2005);CDS;2019;Spectroscopy;Stars:early-type;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/ApJS/161/154;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/ApJS/161/154;2005ApJS..161..154H;text/xml+votable;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "17016c18-f1d4-5d3e-85a6-9cd23ae4d8cf",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/ApJS/161/154"
-    ],
-    "oai_set": [
-        "J.ApJS",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Spectroscopy"
-        },
-        {
-            "name": "Stars early-type"
-        }
-    ],
-    "title": [
-        "Near-IR spectral atlas of OB stars (Hanson+, 2005)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/ApJS/161/154"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/1d010f20-291a-59bf-a91c-a56f75ed4c24.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/1d010f20-291a-59bf-a91c-a56f75ed4c24.json
deleted file mode 100644
index cd2d0889..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/1d010f20-291a-59bf-a91c-a56f75ed4c24.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/A+A/510/A89",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/A+A/510/A89"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2010A&A...510A..89M"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Mottram J.C., Hoare M.G., Lumsden S.L., Oudmaijer R.D., Urquhart J.S., Meade M.R., Moore T.J.T, Stead J.J."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/A+A/510/A89;2018-04-05T10:00:00Z;J.A_A;ivo_managed;Mottram J.C., Hoare M.G., Lumsden S.L., Oudmaijer R.D., Urquhart J.S., Meade M.R., Moore T.J.T, Stead J.J.;RMS survey of young massive stars in far-IR (Mottram+, 2010);CDS;2018;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/A+A/510/A89;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/510/A89;2010A&A...510A..89M;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "1d010f20-291a-59bf-a91c-a56f75ed4c24",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/A+A/510/A89"
-    ],
-    "oai_set": [
-        "J.A_A",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [],
-    "title": [
-        "RMS survey of young massive stars in far-IR (Mottram+, 2010)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/510/A89"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/1d05f9f0-e8d1-5a1e-9a2d-d3d4d23ceda7.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/1d05f9f0-e8d1-5a1e-9a2d-d3d4d23ceda7.json
deleted file mode 100644
index 5f0f596b..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/1d05f9f0-e8d1-5a1e-9a2d-d3d4d23ceda7.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/ApJ/833/170",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/ApJ/833/170"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2016ApJ...833..170L"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Lee J.W."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/ApJ/833/170;2018-04-05T10:00:00Z;J.ApJ;ivo_managed;Lee J.W.;Spots parameters for LCs of the EB star KIC 6048106 (Lee, 2016);CDS;2017;Binaries:eclipsing;Photometry;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/ApJ/833/170;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/ApJ/833/170;2016ApJ...833..170L;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "1d05f9f0-e8d1-5a1e-9a2d-d3d4d23ceda7",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/ApJ/833/170"
-    ],
-    "oai_set": [
-        "J.ApJ",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Binaries eclipsing"
-        },
-        {
-            "name": "Photometry"
-        }
-    ],
-    "title": [
-        "Spots parameters for LCs of the EB star KIC 6048106 (Lee, 2016)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/ApJ/833/170"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/1d3ac650-a4ea-50e7-9f9c-378d0221defb.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/1d3ac650-a4ea-50e7-9f9c-378d0221defb.json
deleted file mode 100644
index fbbace9e..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/1d3ac650-a4ea-50e7-9f9c-378d0221defb.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/A+A/541/A143",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/A+A/541/A143"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2012A&A...541A.143S"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Spite M., Andrievsky S.M., Spite F., Caffau E., Korotin S.A., Bonifacio P., Ludwig H.-G., Francois P., Cayrel R."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/A+A/541/A143;2018-04-05T10:00:00Z;J.A_A;ivo_managed;Spite M., Andrievsky S.M., Spite F., Caffau E., Korotin S.A., Bonifacio P., Ludwig H.-G., Francois P., Cayrel R.;NLTE Corrections of the Ca lines (Spite+, 2012);CDS;2017;Abundances;Spectroscopy;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/A+A/541/A143;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/541/A143;2012A&A...541A.143S;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "1d3ac650-a4ea-50e7-9f9c-378d0221defb",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/A+A/541/A143"
-    ],
-    "oai_set": [
-        "J.A_A",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Abundances"
-        },
-        {
-            "name": "Spectroscopy"
-        }
-    ],
-    "title": [
-        "NLTE Corrections of the Ca lines (Spite+, 2012)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/541/A143"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/1d3e47fa-2936-5e0a-90f2-d12708230298.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/1d3e47fa-2936-5e0a-90f2-d12708230298.json
deleted file mode 100644
index 20057ad2..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/1d3e47fa-2936-5e0a-90f2-d12708230298.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/PASJ/57/13",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/PASJ/57/13"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2005PASJ...57...13T"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Takeda Y., Sato B., Kambe E., Masuda S., Izumiura H., Watanabe E., Ohkubo M., Yanagisawa K., Yasaka Y., Honda S., Kawanomoto S., Aoki W., Ando H., Sadakane K., Takada-hidai M., Miyama S.M."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/PASJ/57/13;2018-04-05T10:00:00Z;J.PASJ;ivo_managed;Takeda Y., Sato B., Kambe E., Masuda S., Izumiura H., Watanabe E., Ohkubo M., Yanagisawa K., Yasaka Y., Honda S., Kawanomoto S., Aoki W., Ando H., Sadakane K., Takada-hidai M., Miyama S.M.;High-dispersion spectra of nearby F-K stars (Takeda+, 2005);CDS;2017;Stars;Spectroscopy;Stars:late-type;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/PASJ/57/13;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/PASJ/57/13;2005PASJ...57...13T;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "1d3e47fa-2936-5e0a-90f2-d12708230298",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/PASJ/57/13"
-    ],
-    "oai_set": [
-        "J.PASJ",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Stars"
-        },
-        {
-            "name": "Spectroscopy"
-        },
-        {
-            "name": "Stars late-type"
-        }
-    ],
-    "title": [
-        "High-dispersion spectra of nearby F-K stars (Takeda+, 2005)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/PASJ/57/13"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/1d409225-fcb1-5e23-ae2c-a9d3d00ba90b.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/1d409225-fcb1-5e23-ae2c-a9d3d00ba90b.json
deleted file mode 100644
index 66d6b2a4..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/1d409225-fcb1-5e23-ae2c-a9d3d00ba90b.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/ApJ/759/139",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/ApJ/759/139"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2012ApJ...759..139K"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Kirkpatrick A., Pope A., Alexander D.M., et al."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/ApJ/759/139;2018-04-05T10:00:00Z;J.ApJ;ivo_managed;Kirkpatrick A., Pope A., Alexander D.M., et al.;Herschel + MIPS photometry of GOODS sources (Kirkpatrick+, 2012);CDS;2017;AGN;Galaxies;Redshifts;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/ApJ/759/139;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/ApJ/759/139;2012ApJ...759..139K;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "1d409225-fcb1-5e23-ae2c-a9d3d00ba90b",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/ApJ/759/139"
-    ],
-    "oai_set": [
-        "J.ApJ",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "AGN"
-        },
-        {
-            "name": "Galaxies"
-        },
-        {
-            "name": "Redshifts"
-        }
-    ],
-    "title": [
-        "Herschel + MIPS photometry of GOODS sources (Kirkpatrick+, 2012)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/ApJ/759/139"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/1d619c75-13d4-579c-bfca-68cf55015721.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/1d619c75-13d4-579c-bfca-68cf55015721.json
deleted file mode 100644
index ab4d69ca..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/1d619c75-13d4-579c-bfca-68cf55015721.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/AJ/134/1707",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/AJ/134/1707"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2007AJ....134.1707W"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Winn J.N., Holman M.J., Bakos G.A., Pal A., Johnson J.A., Williams P.K.G., Shporer A., Mazeh T., Fernandez J., Latham D.W., Gillon M."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/AJ/134/1707;2018-04-05T10:00:00Z;J.AJ;ivo_managed;Winn J.N., Holman M.J., Bakos G.A., Pal A., Johnson J.A., Williams P.K.G., Shporer A., Mazeh T., Fernandez J., Latham D.W., Gillon M.;Six transits of exoplanet HAT-P-1b (Winn+, 2007);CDS;2017;Photometry;Planets+Asteroids;Stars:variable;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/AJ/134/1707;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/AJ/134/1707;2007AJ....134.1707W;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "1d619c75-13d4-579c-bfca-68cf55015721",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/AJ/134/1707"
-    ],
-    "oai_set": [
-        "J.AJ",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Photometry"
-        },
-        {
-            "name": "Planets"
-        },
-        {
-            "name": "Asteroids"
-        },
-        {
-            "name": "Stars variable"
-        }
-    ],
-    "title": [
-        "Six transits of exoplanet HAT-P-1b (Winn+, 2007)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/AJ/134/1707"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/1d644251-89fe-5e62-a30c-5b87e4f5da5e.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/1d644251-89fe-5e62-a30c-5b87e4f5da5e.json
deleted file mode 100644
index 0ce44a7c..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/1d644251-89fe-5e62-a30c-5b87e4f5da5e.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/MNRAS/392/19",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/MNRAS/392/19"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2009MNRAS.392...19C"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Croom S.M., Richards G.T., Shanks T., et al."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/MNRAS/392/19;2018-04-05T10:00:00Z;J.MNRAS;ivo_managed;Croom S.M., Richards G.T., Shanks T., et al.;The 2dF-SDSS QSO survey (Croom+, 2009);CDS;2017;Photometry:wide-band;QSOs;Redshifts;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/MNRAS/392/19;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/MNRAS/392/19;2009MNRAS.392...19C;text/xml+votable;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "1d644251-89fe-5e62-a30c-5b87e4f5da5e",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/MNRAS/392/19"
-    ],
-    "oai_set": [
-        "J.MNRAS",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Photometry wide-band"
-        },
-        {
-            "name": "QSOs"
-        },
-        {
-            "name": "Redshifts"
-        }
-    ],
-    "title": [
-        "The 2dF-SDSS QSO survey (Croom+, 2009)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/MNRAS/392/19"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/1d7536d2-56f9-5663-80e6-5e98f657de44.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/1d7536d2-56f9-5663-80e6-5e98f657de44.json
deleted file mode 100644
index 1c3f33ba..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/1d7536d2-56f9-5663-80e6-5e98f657de44.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/A+A/283/759",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/A+A/283/759"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "1994A&A...283..759P"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Petitjean P., Bergeron J."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/A+A/283/759;2018-04-05T10:00:00Z;J.A_A;ivo_managed;Petitjean P., Bergeron J.;CIV QSO absorption systems (Petitjean+ 1994);CDS;2018;Spectroscopy;QSOs;Redshifts;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/A+A/283/759;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/283/759;1994A&A...283..759P;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "1d7536d2-56f9-5663-80e6-5e98f657de44",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/A+A/283/759"
-    ],
-    "oai_set": [
-        "J.A_A",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Spectroscopy"
-        },
-        {
-            "name": "QSOs"
-        },
-        {
-            "name": "Redshifts"
-        }
-    ],
-    "title": [
-        "CIV QSO absorption systems (Petitjean+ 1994)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/283/759"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/1d8ce0ba-3079-54a7-9343-918b9b50400d.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/1d8ce0ba-3079-54a7-9343-918b9b50400d.json
deleted file mode 100644
index b2af297f..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/1d8ce0ba-3079-54a7-9343-918b9b50400d.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/A+A/605/A74",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/A+A/605/A74"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2017A&A...605A..74K"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Kokusho T., Kaneda H., Bureau M., Suzuki T., Murata K., Kondo A., Yamagishi M."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/A+A/605/A74;2018-04-05T10:00:00Z;J.A_A;ivo_managed;Kokusho T., Kaneda H., Bureau M., Suzuki T., Murata K., Kondo A., Yamagishi M.;AKARI fluxes of ATLAS3D early-type galaxies (Kokusho+, 2017);CDS;2018;Galaxies;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/A+A/605/A74;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/605/A74;2017A&A...605A..74K;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "1d8ce0ba-3079-54a7-9343-918b9b50400d",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/A+A/605/A74"
-    ],
-    "oai_set": [
-        "J.A_A",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Galaxies"
-        }
-    ],
-    "title": [
-        "AKARI fluxes of ATLAS3D early-type galaxies (Kokusho+, 2017)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/605/A74"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/1d917ed6-2053-5f24-8cf5-48069111c008.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/1d917ed6-2053-5f24-8cf5-48069111c008.json
deleted file mode 100644
index beed3f85..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/1d917ed6-2053-5f24-8cf5-48069111c008.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/A+A/455/259",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/A+A/455/259"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2006A&A...455..259A"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Ausseloos M., Aerts C., Lefever K., Davis J., Harmanec P."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/A+A/455/259;2018-04-05T10:00:00Z;J.A_A;ivo_managed;Ausseloos M., Aerts C., Lefever K., Davis J., Harmanec P.;Radial velocities of beta Cep (Ausseloos+, 2006);CDS;2017;Binaries:spectroscopic;Velocities;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/A+A/455/259;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/455/259;2006A&A...455..259A;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "1d917ed6-2053-5f24-8cf5-48069111c008",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/A+A/455/259"
-    ],
-    "oai_set": [
-        "J.A_A",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Binaries spectroscopic"
-        },
-        {
-            "name": "Velocities"
-        }
-    ],
-    "title": [
-        "Radial velocities of beta Cep (Ausseloos+, 2006)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/455/259"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/1dab038b-216b-5cf9-9ef4-4d5ec4447025.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/1dab038b-216b-5cf9-9ef4-4d5ec4447025.json
deleted file mode 100644
index 971c8e29..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/1dab038b-216b-5cf9-9ef4-4d5ec4447025.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/A+A/527/A88",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/A+A/527/A88"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2011A&A...527A..88V"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Vasyunina T., Linz H., Henning T., Zinchenko, I., Beuther, H., Voronkov M."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/A+A/527/A88;2018-04-05T10:00:00Z;J.A_A;ivo_managed;Vasyunina T., Linz H., Henning T., Zinchenko, I., Beuther, H., Voronkov M.;Chemistry in infrared dark clouds (Vasyunina+, 2011);CDS;2018;Nebulae;Interstellar_Medium;Spectroscopy;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/A+A/527/A88;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/527/A88;2011A&A...527A..88V;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "1dab038b-216b-5cf9-9ef4-4d5ec4447025",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/A+A/527/A88"
-    ],
-    "oai_set": [
-        "J.A_A",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Nebulae"
-        },
-        {
-            "name": "Interstellar_Medium"
-        },
-        {
-            "name": "Spectroscopy"
-        }
-    ],
-    "title": [
-        "Chemistry in infrared dark clouds (Vasyunina+, 2011)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/527/A88"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/20831aa1-afd2-571e-8bb0-4ded99ee5053.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/20831aa1-afd2-571e-8bb0-4ded99ee5053.json
deleted file mode 100644
index 7335245a..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/20831aa1-afd2-571e-8bb0-4ded99ee5053.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/MNRAS/465/L39",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/MNRAS/465/L39"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2017MNRAS.465L..39H"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Hollyhead K., Kacharov N., Lardo C., Bastian N., Hilker M., Rejkuba M., Koch A., Grebel E.K., Georgiev I."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/MNRAS/465/L39;2018-10-22T12:58:55Z;J.MNRAS;ivo_managed;Hollyhead K., Kacharov N., Lardo C., Bastian N., Hilker M., Rejkuba M., Koch A., Grebel E.K., Georgiev I.;Lindsay 1 spectroscopy for 34 targets (Hollyhead+, 2017);CDS;2018;Associations;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/MNRAS/465/L39;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/MNRAS/465/L39;2017MNRAS.465L..39H;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "20831aa1-afd2-571e-8bb0-4ded99ee5053",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/MNRAS/465/L39"
-    ],
-    "oai_set": [
-        "J.MNRAS",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Associations"
-        }
-    ],
-    "title": [
-        "Lindsay 1 spectroscopy for 34 targets (Hollyhead+, 2017)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/MNRAS/465/L39"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/20863de6-27d9-565d-b35b-3ed31a74a544.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/20863de6-27d9-565d-b35b-3ed31a74a544.json
deleted file mode 100644
index 98c0d036..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/20863de6-27d9-565d-b35b-3ed31a74a544.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/A+A/621/A25",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/A+A/621/A25"
-    ],
-    "PublicationTimestamp": "2019-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2019A&A...621A..25F"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Fuentes-Carrera I., Rosado M., Amram P., Laurikainen E., Salo H., Gomez-Lopez J.A., Castaneda H.O., Bernal A., Balkowski C."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/A+A/621/A25;2019-01-09T09:29:41Z;J.A_A;ivo_managed;Fuentes-Carrera I., Rosado M., Amram P., Laurikainen E., Salo H., Gomez-Lopez J.A., Castaneda H.O., Bernal A., Balkowski C.;Arp 240 Fabry-Perot interferometry (Fuentes-Carrera+, 2019);CDS;2019;Galaxies;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/A+A/621/A25;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/621/A25;2019A&A...621A..25F;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "20863de6-27d9-565d-b35b-3ed31a74a544",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/A+A/621/A25"
-    ],
-    "oai_set": [
-        "J.A_A",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Galaxies"
-        }
-    ],
-    "title": [
-        "Arp 240 Fabry-Perot interferometry (Fuentes-Carrera+, 2019)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/621/A25"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/22086a88-0401-59e9-aba3-8ea6bb81845c.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/22086a88-0401-59e9-aba3-8ea6bb81845c.json
deleted file mode 100644
index 511d2432..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/22086a88-0401-59e9-aba3-8ea6bb81845c.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/AJ/156/98",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/AJ/156/98"
-    ],
-    "PublicationTimestamp": "2019-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2018AJ....156...98P"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Platais I., Lennon D.J., van der Marel R.P., Bellini A., Sabbi E., Watkins L.L., Sohn S.T., Walborn N.R., Bedin L.R., Evans C.J., de Mink S.E., Sana H., Herrero A., Langer N., Crowther P."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/AJ/156/98;2019-03-08T08:16:57Z;J.AJ;ivo_managed;Platais I., Lennon D.J., van der Marel R.P., Bellini A., Sabbi E., Watkins L.L., Sohn S.T., Walborn N.R., Bedin L.R., Evans C.J., de Mink S.E., Sana H., Herrero A., Langer N., Crowther P.;Runaway stars in the 30 Doradus region of the LMC (Platais+, 2018);CDS;2019;Positional_Data;Spectral_Classification;Proper_Motions;Rotational_Velocities;Stars:early-type;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/AJ/156/98;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/AJ/156/98;2018AJ....156...98P;text/xml+votable;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "22086a88-0401-59e9-aba3-8ea6bb81845c",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/AJ/156/98"
-    ],
-    "oai_set": [
-        "J.AJ",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Positional_Data"
-        },
-        {
-            "name": "Spectral_Classification"
-        },
-        {
-            "name": "Proper_Motions"
-        },
-        {
-            "name": "Rotational_Velocities"
-        },
-        {
-            "name": "Stars early-type"
-        }
-    ],
-    "title": [
-        "Runaway stars in the 30 Doradus region of the LMC (Platais+, 2018)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/AJ/156/98"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/22507efc-6f3e-5966-a0c1-3281d138c64e.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/22507efc-6f3e-5966-a0c1-3281d138c64e.json
deleted file mode 100644
index 616a2956..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/22507efc-6f3e-5966-a0c1-3281d138c64e.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/AJ/155/104",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/AJ/155/104"
-    ],
-    "PublicationTimestamp": "2019-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2018AJ....155..104R"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Rigby J.R., Bayliss M.B., Sharon K., Gladders M.D., Chisholm J., Dahle H., Johnson T., Paterno-Mahler R., Wuyts E., Kelson D.D."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/AJ/155/104;2019-01-31T12:45:45Z;J.AJ;ivo_managed;Rigby J.R., Bayliss M.B., Sharon K., Gladders M.D., Chisholm J., Dahle H., Johnson T., Paterno-Mahler R., Wuyts E., Kelson D.D.;MEGaSaURA. I. The sample and the spectra (Rigby+, 2018);CDS;2019;Galaxies;Gravitational_lensing;Spectroscopy;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/AJ/155/104;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/AJ/155/104;2018AJ....155..104R;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "22507efc-6f3e-5966-a0c1-3281d138c64e",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/AJ/155/104"
-    ],
-    "oai_set": [
-        "J.AJ",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Galaxies"
-        },
-        {
-            "name": "Gravitational_lensing"
-        },
-        {
-            "name": "Spectroscopy"
-        }
-    ],
-    "title": [
-        "MEGaSaURA. I. The sample and the spectra (Rigby+, 2018)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/AJ/155/104"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/23066ccc-b2f0-547c-9303-35f4ff4111b1.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/23066ccc-b2f0-547c-9303-35f4ff4111b1.json
deleted file mode 100644
index f8c4fcbc..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/23066ccc-b2f0-547c-9303-35f4ff4111b1.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/A+A/617/A57",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/A+A/617/A57"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2018A&A...617A..57D"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Durech J., Hanus J, Ali-Lagoa V."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/A+A/617/A57;2018-09-28T14:09:11Z;J.A_A;ivo_managed;Durech J., Hanus J, Ali-Lagoa V.;Lowell Photometric Database asteroid models. II. (Durech+, 2018);CDS;2018;Photometry;Planets+Asteroids;Models;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/A+A/617/A57;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/617/A57;2018A&A...617A..57D;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "23066ccc-b2f0-547c-9303-35f4ff4111b1",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/A+A/617/A57"
-    ],
-    "oai_set": [
-        "J.A_A",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Photometry"
-        },
-        {
-            "name": "Planets"
-        },
-        {
-            "name": "Asteroids"
-        },
-        {
-            "name": "Models"
-        }
-    ],
-    "title": [
-        "Lowell Photometric Database asteroid models. II. (Durech+, 2018)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/617/A57"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/27107c16-f161-53f5-bd5f-ade03d52dd56.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/27107c16-f161-53f5-bd5f-ade03d52dd56.json
deleted file mode 100644
index 85317ae1..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/27107c16-f161-53f5-bd5f-ade03d52dd56.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/AJ/154/237",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/AJ/154/237"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2017AJ....154..237V"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Vanderburg A., Becker J.C., Buchhave L.A., et al."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/AJ/154/237;2018-10-01T13:26:34Z;J.AJ;ivo_managed;Vanderburg A., Becker J.C., Buchhave L.A., et al.;HARPS-N radial velocities of WASP-47 (Vanderburg+, 2017);CDS;2018;Binaries:eclipsing;Spectroscopy;Velocities;Exoplanets;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/AJ/154/237;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/AJ/154/237;2017AJ....154..237V;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "27107c16-f161-53f5-bd5f-ade03d52dd56",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/AJ/154/237"
-    ],
-    "oai_set": [
-        "J.AJ",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Binaries eclipsing"
-        },
-        {
-            "name": "Spectroscopy"
-        },
-        {
-            "name": "Velocities"
-        },
-        {
-            "name": "Exoplanets"
-        }
-    ],
-    "title": [
-        "HARPS-N radial velocities of WASP-47 (Vanderburg+, 2017)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/AJ/154/237"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/27893f27-245e-5508-bb54-799a37ffd972.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/27893f27-245e-5508-bb54-799a37ffd972.json
deleted file mode 100644
index dd9c84ae..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/27893f27-245e-5508-bb54-799a37ffd972.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/AJ/154/199",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/AJ/154/199"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2017AJ....154..199N"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Nidever D.L., Olsen K., Walker A.R., et al."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/AJ/154/199;2018-09-28T08:38:02Z;J.AJ;ivo_managed;Nidever D.L., Olsen K., Walker A.R., et al.;SMASH: Survey of the MAgellanic Stellar History (Nidever+, 2017);CDS;2018;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/AJ/154/199;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/AJ/154/199;2017AJ....154..199N;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "27893f27-245e-5508-bb54-799a37ffd972",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/AJ/154/199"
-    ],
-    "oai_set": [
-        "J.AJ",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [],
-    "title": [
-        "SMASH: Survey of the MAgellanic Stellar History (Nidever+, 2017)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/AJ/154/199"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/31086ba5-a93b-5fa1-abea-53edb0811a77.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/31086ba5-a93b-5fa1-abea-53edb0811a77.json
deleted file mode 100644
index baafb3e3..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/31086ba5-a93b-5fa1-abea-53edb0811a77.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/ApJ/848/18",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/ApJ/848/18"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2017ApJ...848...18A"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Aarnio A.N., Monnier J.D., Harries T.J., Kraus S., Calvet N., Acreman D., Che X."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/ApJ/848/18;2018-09-25T13:19:51Z;J.ApJ;ivo_managed;Aarnio A.N., Monnier J.D., Harries T.J., Kraus S., Calvet N., Acreman D., Che X.;High-res. spectroscopic obs. of 2 Herbig stars (Aarnio+, 2017);CDS;2018;Spectroscopy;Stars:variable;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/ApJ/848/18;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/ApJ/848/18;2017ApJ...848...18A;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "31086ba5-a93b-5fa1-abea-53edb0811a77",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/ApJ/848/18"
-    ],
-    "oai_set": [
-        "J.ApJ",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Spectroscopy"
-        },
-        {
-            "name": "Stars variable"
-        }
-    ],
-    "title": [
-        "High-res. spectroscopic obs. of 2 Herbig stars (Aarnio+, 2017)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/ApJ/848/18"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/31399de0-234d-5b24-b1f0-5ba21f51f2e2.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/31399de0-234d-5b24-b1f0-5ba21f51f2e2.json
deleted file mode 100644
index ddd57fa5..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/31399de0-234d-5b24-b1f0-5ba21f51f2e2.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/ApJS/235/8",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/ApJS/235/8"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2018ApJS..235....8B"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Bittner D.M., Bernath P.F."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/ApJS/235/8;2018-10-22T07:49:58Z;J.ApJS;ivo_managed;Bittner D.M., Bernath P.F.;Line lists for X^1^{Sigma}^+^ LiF and LiCl (Bittner+, 2018);CDS;2018;Atomic_Data;Molecular_Data;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/ApJS/235/8;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/ApJS/235/8;2018ApJS..235....8B;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "31399de0-234d-5b24-b1f0-5ba21f51f2e2",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/ApJS/235/8"
-    ],
-    "oai_set": [
-        "J.ApJS",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Atomic_Data"
-        },
-        {
-            "name": "Molecular_Data"
-        }
-    ],
-    "title": [
-        "Line lists for X^1^{Sigma}^+^ LiF and LiCl (Bittner+, 2018)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/ApJS/235/8"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/3ca61b1a-f2e7-5020-a9b8-5f9aa04119d2.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/3ca61b1a-f2e7-5020-a9b8-5f9aa04119d2.json
deleted file mode 100644
index 3cb878e4..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/3ca61b1a-f2e7-5020-a9b8-5f9aa04119d2.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/ApJS/168/128",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/ApJS/168/128"
-    ],
-    "PublicationTimestamp": "2009-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2009"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2007ApJS..168..128B"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Beers T.C., Flynn C., Rossi S., et al."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/ApJS/168/128;2018-04-05T10:00:00Z;J.ApJS;ivo_managed;Beers T.C., Flynn C., Rossi S., et al.;UBVRcIc photometry of FHB and metal-poor stars (Beers+, 2007);CDS;2009;Stars;Photometry:wide-band;Stars:peculiar;Stars:early-type;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/ApJS/168/128;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/ApJS/168/128;2007ApJS..168..128B;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "3ca61b1a-f2e7-5020-a9b8-5f9aa04119d2",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/ApJS/168/128"
-    ],
-    "oai_set": [
-        "J.ApJS",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Stars"
-        },
-        {
-            "name": "Photometry wide-band"
-        },
-        {
-            "name": "Stars peculiar"
-        },
-        {
-            "name": "Stars early-type"
-        }
-    ],
-    "title": [
-        "UBVRcIc photometry of FHB and metal-poor stars (Beers+, 2007)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/ApJS/168/128"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/3ca9c61a-c547-5fd1-8aa5-79b2a6368c7d.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/3ca9c61a-c547-5fd1-8aa5-79b2a6368c7d.json
deleted file mode 100644
index 64c91064..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/3ca9c61a-c547-5fd1-8aa5-79b2a6368c7d.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/A+A/431/793",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/A+A/431/793"
-    ],
-    "PublicationTimestamp": "2005-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2005"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2005A&A...431..793V"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Venemans B.P., Rottgering H.J.A., Miley G.K., Kurk J.D., De Breuck C., Overzier R.A., van Breugel W.J.M., Carilli C.L., Ford H., Heckman T., Pentericci L., McCarthy P."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/A+A/431/793;2018-04-05T10:00:00Z;J.A_A;ivo_managed;Venemans B.P., Rottgering H.J.A., Miley G.K., Kurk J.D., De Breuck C., Overzier R.A., van Breugel W.J.M., Carilli C.L., Ford H., Heckman T., Pentericci L., McCarthy P.;Ly-alpha emitters around MRC 0316-257 (Venemans+, 2005);CDS;2005;Photometry;Galaxies;Redshifts;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/A+A/431/793;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/431/793;2005A&A...431..793V;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "3ca9c61a-c547-5fd1-8aa5-79b2a6368c7d",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/A+A/431/793"
-    ],
-    "oai_set": [
-        "J.A_A",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Photometry"
-        },
-        {
-            "name": "Galaxies"
-        },
-        {
-            "name": "Redshifts"
-        }
-    ],
-    "title": [
-        "Ly-alpha emitters around MRC 0316-257 (Venemans+, 2005)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/431/793"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/3cbd0f83-339f-540b-9340-8c5fad3c0ff0.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/3cbd0f83-339f-540b-9340-8c5fad3c0ff0.json
deleted file mode 100644
index 5e89238b..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/3cbd0f83-339f-540b-9340-8c5fad3c0ff0.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Michael Preciado <Michael.E.Preciado@nasa.gov>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://nasa.heasarc/vlaecdfs1p4",
-    "MetadataAccess": [
-        "ivo://nasa.heasarc/vlaecdfs1p4"
-    ],
-    "PublicationTimestamp": "2019-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "NASA/GSFC HEASARC"
-    ],
-    "ResourceType": [
-        "AstroObjects"
-    ],
-    "author": [
-        "Miller et al."
-    ],
-    "fulltext": "ivo://nasa.heasarc/vlaecdfs1p4;2019-06-17T07:09:34Z;Miller et al.;VLA Extended-Chandra Deep Field-South 1.4-GHz Source Catalog;NASA/GSFC HEASARC;2019;Survey Source;Michael Preciado <Michael.E.Preciado@nasa.gov>;AstroObjects;ivo://nasa.heasarc/vlaecdfs1p4;https://heasarc.gsfc.nasa.gov/W3Browse/all/vlaecdfs1p4.html;\n        https://heasarc.gsfc.nasa.gov/cgi-bin/W3Browse/w3query.pl?tablehead=name=heasarc_vlaecdfs1p4&Action=More+Options&Action=Parameter+Search&ConeAdd=1\n      ;text/xml;text/xml;\n      Deep radio observations at 1.4 GHz for the Extended Chandra Deep Field South were performed in 2007 June through September and presented in a first data release (Miller et al. 2008, ApJS, 179, 114). The survey was made using six separate pointings of the Very Large Array with over 40 hr of observation per pointing. In the current study, the authors improve on the data reduction to produce a second data release (DR2) mosaic image. This DR2 image covers an area of about a third of a square degree, reaches a best rms sensitivity of 6 microJy (uJy), and has a typical sensitivity of 7.4 uJy per 2.8&quot; by 1.6&quot; beam. The authors also present a more comprehensive catalog, including sources down to peak flux densities of five or more times the local rms noise, along with information on source sizes and relevant pointing data. In their paper, they discuss in some detail the consideration of whether sources are resolved under the complication of a radio image created as a mosaic of separate pointings, each suffering some degree of bandwidth smearing, and the accurate evaluation of the flux densities of such sources. Finally, the radio morphologies and optical/near-IR counterpart identifications are used to identify 17 likely multiple-component sources so as to arrive at a catalog of 883 radio sources (and also 49 individual components of the 17 multi-component sources), which is roughly double the number of sources contained in the first data release. In order to cover the full E-CDF-S area at near-uniform sensitivity, the authors pointed the VLA at six separate coordinate locations arranged in a hexagonal grid around the adopted center of the CDF-S, viz. RA, Dec (J2000) 03&lt;sup&gt;h&lt;/sup&gt; 32&lt;sup&gt;m&lt;/sup&gt; 28.00&lt;sup&gt;s&lt;/sup&gt;, -27&lt;sup&gt;o&lt;/sup&gt; 48' 30.0&quot;. The observations were spread over many days on account of the low declination of the field and typically amounted to 5 hr of time per calendar date. The details of the individual pointings are: &lt;pre&gt; Pointing ID R.A. (J2000) DE. (J2000) rms sensitivity for final image ECDFS 1 03:33:22.25 -27:48:30.0 10.5 uJy ECDFS 2 03:32:55.12 -27:38:03.0 9.4 uJy ECDFS 3 03:32:00.88 -27:38:03.0 9.7 uJy ECDFS 4 03:31:33.75 -27:48:30.0 9.5 uJy ECDFS 5 03:32:00.88 -27:58:57.0 10.0 uJy ECDFS 6 03:32:55.12 -27:58:57.0 9.3 uJy &lt;/pre&gt; The images corresponding to the six individual pointings were combined to form the final mosaic image (shown in Figure 1 of the reference paper). This HEASARC table contains the catalog of 883 radio sources (Table 3 in the reference paper) and also the catalog of 49 individual components of the 17 multi-component sources (Table 4 in the reference paper), so that there are a total of 932 entries in the present table. To allow users to easily distinguish these types of entry, the HEASARC created a parameter type_flag which is set to 'S' for the 883 source entries and to 'C' for the 49 component entries. The HEASARC created names for the sources following the standard CDS and IAU recommendations for position-based names and using the prefix of '[MBF2013]' for Miller, Bonzini, Fomalont (2013), the first 3 authors and the date of publication of the reference paper. For the components, we have used the names based on the positions of the parent sources and the suffixes 'A', 'B', etc, in order of increasing J2000.0 RA. Thus, for the multi-component source [MBF2013] J033115.0-275518 which has 3 components, there are 4 entries in this table, one for the entire source, and one for each component, e.g.: &lt;pre&gt; Name | type_flag | RA (J2000.0) Dec (J2000.0) [MBF2013] J033115.0-275518 | S | 03 31 15.04 | -27 55 18.8 [MBF2013] J033115.0-275518 A| C | 03 31 13.99 | -27 55 19.9 [MBF2013] J033115.0-275518 B| C | 03 31 15.06 | -27 55 18.9 [MBF2013] J033115.0-275518 C| C | 03 31 17.05 | -27 55 15.2 &lt;/pre&gt; The 17 sources thought to consist of multiple components associated with a single host object are each listed with a single aggregate integrated flux density. Gaussian fits to the individual components associated with these sources are separately listed for their components\n    ",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "3cbd0f83-339f-540b-9340-8c5fad3c0ff0",
-    "notes": [
-        "\n      Deep radio observations at 1.4 GHz for the Extended Chandra Deep Field South were performed in 2007 June through September and presented in a first data release (Miller et al. 2008, ApJS, 179, 114). The survey was made using six separate pointings of the Very Large Array with over 40 hr of observation per pointing. In the current study, the authors improve on the data reduction to produce a second data release (DR2) mosaic image. This DR2 image covers an area of about a third of a square degree, reaches a best rms sensitivity of 6 microJy (uJy), and has a typical sensitivity of 7.4 uJy per 2.8&quot; by 1.6&quot; beam. The authors also present a more comprehensive catalog, including sources down to peak flux densities of five or more times the local rms noise, along with information on source sizes and relevant pointing data. In their paper, they discuss in some detail the consideration of whether sources are resolved under the complication of a radio image created as a mosaic of separate pointings, each suffering some degree of bandwidth smearing, and the accurate evaluation of the flux densities of such sources. Finally, the radio morphologies and optical/near-IR counterpart identifications are used to identify 17 likely multiple-component sources so as to arrive at a catalog of 883 radio sources (and also 49 individual components of the 17 multi-component sources), which is roughly double the number of sources contained in the first data release. In order to cover the full E-CDF-S area at near-uniform sensitivity, the authors pointed the VLA at six separate coordinate locations arranged in a hexagonal grid around the adopted center of the CDF-S, viz. RA, Dec (J2000) 03&lt;sup&gt;h&lt;/sup&gt; 32&lt;sup&gt;m&lt;/sup&gt; 28.00&lt;sup&gt;s&lt;/sup&gt;, -27&lt;sup&gt;o&lt;/sup&gt; 48' 30.0&quot;. The observations were spread over many days on account of the low declination of the field and typically amounted to 5 hr of time per calendar date. The details of the individual pointings are: &lt;pre&gt; Pointing ID R.A. (J2000) DE. (J2000) rms sensitivity for final image ECDFS 1 03:33:22.25 -27:48:30.0 10.5 uJy ECDFS 2 03:32:55.12 -27:38:03.0 9.4 uJy ECDFS 3 03:32:00.88 -27:38:03.0 9.7 uJy ECDFS 4 03:31:33.75 -27:48:30.0 9.5 uJy ECDFS 5 03:32:00.88 -27:58:57.0 10.0 uJy ECDFS 6 03:32:55.12 -27:58:57.0 9.3 uJy &lt;/pre&gt; The images corresponding to the six individual pointings were combined to form the final mosaic image (shown in Figure 1 of the reference paper). This HEASARC table contains the catalog of 883 radio sources (Table 3 in the reference paper) and also the catalog of 49 individual components of the 17 multi-component sources (Table 4 in the reference paper), so that there are a total of 932 entries in the present table. To allow users to easily distinguish these types of entry, the HEASARC created a parameter type_flag which is set to 'S' for the 883 source entries and to 'C' for the 49 component entries. The HEASARC created names for the sources following the standard CDS and IAU recommendations for position-based names and using the prefix of '[MBF2013]' for Miller, Bonzini, Fomalont (2013), the first 3 authors and the date of publication of the reference paper. For the components, we have used the names based on the positions of the parent sources and the suffixes 'A', 'B', etc, in order of increasing J2000.0 RA. Thus, for the multi-component source [MBF2013] J033115.0-275518 which has 3 components, there are 4 entries in this table, one for the entire source, and one for each component, e.g.: &lt;pre&gt; Name | type_flag | RA (J2000.0) Dec (J2000.0) [MBF2013] J033115.0-275518 | S | 03 31 15.04 | -27 55 18.8 [MBF2013] J033115.0-275518 A| C | 03 31 13.99 | -27 55 19.9 [MBF2013] J033115.0-275518 B| C | 03 31 15.06 | -27 55 18.9 [MBF2013] J033115.0-275518 C| C | 03 31 17.05 | -27 55 15.2 &lt;/pre&gt; The 17 sources thought to consist of multiple components associated with a single host object are each listed with a single aggregate integrated flux density. Gaussian fits to the individual components associated with these sources are separately listed for their components\n    "
-    ],
-    "oai_identifier": [
-        "ivo://nasa.heasarc/vlaecdfs1p4"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Survey Source"
-        }
-    ],
-    "title": [
-        "VLA Extended-Chandra Deep Field-South 1.4-GHz Source Catalog"
-    ],
-    "url": "https://heasarc.gsfc.nasa.gov/W3Browse/all/vlaecdfs1p4.html"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/3cbf2767-3dce-532f-bf7e-e31f25686cb2.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/3cbf2767-3dce-532f-bf7e-e31f25686cb2.json
deleted file mode 100644
index 6c0cc096..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/3cbf2767-3dce-532f-bf7e-e31f25686cb2.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Michael Preciado <Michael.E.Preciado@nasa.gov>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://nasa.heasarc/sax2to10",
-    "MetadataAccess": [
-        "ivo://nasa.heasarc/sax2to10"
-    ],
-    "PublicationTimestamp": "2019-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "NASA/GSFC HEASARC"
-    ],
-    "ResourceType": [
-        "AstroObjects"
-    ],
-    "author": [
-        "Giommi, Perri, Fiore"
-    ],
-    "fulltext": "ivo://nasa.heasarc/sax2to10;2019-06-17T07:08:09Z;Giommi, Perri, Fiore;BeppoSAX 2-10 keV Survey;NASA/GSFC HEASARC;2019;Survey Source;Michael Preciado <Michael.E.Preciado@nasa.gov>;AstroObjects;ivo://nasa.heasarc/sax2to10;https://heasarc.gsfc.nasa.gov/W3Browse/all/sax2to10.html;\n        https://heasarc.gsfc.nasa.gov/cgi-bin/W3Browse/w3query.pl?tablehead=name=heasarc_sax2to10&Action=More+Options&Action=Parameter+Search&ConeAdd=1\n      ;text/xml;text/xml;\n      This catalog presents the results of a 2 - 10 keV BeppoSAX survey based on 140 high galactic latitude Medium Energy Concentrator Spectrometers (MECS) fields, 12 of which are deep exposures of ``blank'' parts of the sky. The limiting sensitivity is 5 x 10^-14 erg/cm^2/s (or mW/m^2) where about 25% of the Cosmic X-ray Background (CXB) is resolved into discrete sources. The log N - log S function, built with a statistically complete sample of 177 sources, is steep and in good agreement with the counts derived from ASCA surveys.\n    ",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "3cbf2767-3dce-532f-bf7e-e31f25686cb2",
-    "notes": [
-        "\n      This catalog presents the results of a 2 - 10 keV BeppoSAX survey based on 140 high galactic latitude Medium Energy Concentrator Spectrometers (MECS) fields, 12 of which are deep exposures of ``blank'' parts of the sky. The limiting sensitivity is 5 x 10^-14 erg/cm^2/s (or mW/m^2) where about 25% of the Cosmic X-ray Background (CXB) is resolved into discrete sources. The log N - log S function, built with a statistically complete sample of 177 sources, is steep and in good agreement with the counts derived from ASCA surveys.\n    "
-    ],
-    "oai_identifier": [
-        "ivo://nasa.heasarc/sax2to10"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Survey Source"
-        }
-    ],
-    "title": [
-        "BeppoSAX 2-10 keV Survey"
-    ],
-    "url": "https://heasarc.gsfc.nasa.gov/W3Browse/all/sax2to10.html"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/479419f2-5642-56d2-8a94-506efee3a698.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/479419f2-5642-56d2-8a94-506efee3a698.json
deleted file mode 100644
index a0ce3330..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/479419f2-5642-56d2-8a94-506efee3a698.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/ApJ/708/1366",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/ApJ/708/1366"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2010ApJ...708.1366V"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Vogt S.S., Wittenmyer R.A., Butler R.P., O'Toole S., Henry G.W., Rivera E.J., Meschiari S., Laughlin G., Tinney C.G., Jones H.R.A., Bailey J., Carter B.D., Batygin K."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/ApJ/708/1366;2018-04-05T10:00:00Z;J.ApJ;ivo_managed;Vogt S.S., Wittenmyer R.A., Butler R.P., O'Toole S., Henry G.W., Rivera E.J., Meschiari S., Laughlin G., Tinney C.G., Jones H.R.A., Bailey J., Carter B.D., Batygin K.;Radial velocities for 61 Vir (Vogt+, 2010);CDS;2017;Multiple_Stars;Planets+Asteroids;Stars;Velocities;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/ApJ/708/1366;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/ApJ/708/1366;2010ApJ...708.1366V;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "479419f2-5642-56d2-8a94-506efee3a698",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/ApJ/708/1366"
-    ],
-    "oai_set": [
-        "J.ApJ",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Multiple_Stars"
-        },
-        {
-            "name": "Planets"
-        },
-        {
-            "name": "Asteroids"
-        },
-        {
-            "name": "Stars"
-        },
-        {
-            "name": "Velocities"
-        }
-    ],
-    "title": [
-        "Radial velocities for 61 Vir (Vogt+, 2010)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/ApJ/708/1366"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/483898b5-fc57-5325-bd0d-3d4b8521092d.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/483898b5-fc57-5325-bd0d-3d4b8521092d.json
deleted file mode 100644
index 654306cb..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/483898b5-fc57-5325-bd0d-3d4b8521092d.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/AJ/145/139",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/AJ/145/139"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2013AJ....145..139M"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Mack C.E III, Ge J., Deshpande R., et al."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/AJ/145/139;2018-04-05T10:00:00Z;J.AJ;ivo_managed;Mack C.E III, Ge J., Deshpande R., et al.;Radial velocities of TYC 3010-1494-1 (Mack+, 2013);CDS;2017;Binaries:spectroscopic;Velocities;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/AJ/145/139;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/AJ/145/139;2013AJ....145..139M;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "483898b5-fc57-5325-bd0d-3d4b8521092d",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/AJ/145/139"
-    ],
-    "oai_set": [
-        "J.AJ",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Binaries spectroscopic"
-        },
-        {
-            "name": "Velocities"
-        }
-    ],
-    "title": [
-        "Radial velocities of TYC 3010-1494-1 (Mack+, 2013)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/AJ/145/139"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/491801cd-c4de-554e-ad4a-e860f21aff78.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/491801cd-c4de-554e-ad4a-e860f21aff78.json
deleted file mode 100644
index 15351a42..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/491801cd-c4de-554e-ad4a-e860f21aff78.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/ApJ/685/436",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/ApJ/685/436"
-    ],
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2008ApJ...685..436A"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Altamirano D., van der Klis M., Mendez M., Jonker P.G., Klein-Wolt M., Lewin W.H.G."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/ApJ/685/436;2018-04-05T10:00:00Z;J.ApJ;ivo_managed;Altamirano D., van der Klis M., Mendez M., Jonker P.G., Klein-Wolt M., Lewin W.H.G.;X-ray variability in 4U 1636-53 (Altamirano+, 2008);CDS;2011;Binaries:cataclysmic;Stars:variable;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/ApJ/685/436;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/ApJ/685/436;2008ApJ...685..436A;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "491801cd-c4de-554e-ad4a-e860f21aff78",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/ApJ/685/436"
-    ],
-    "oai_set": [
-        "J.ApJ",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Binaries cataclysmic"
-        },
-        {
-            "name": "Stars variable"
-        }
-    ],
-    "title": [
-        "X-ray variability in 4U 1636-53 (Altamirano+, 2008)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/ApJ/685/436"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/497515de-d678-58a7-b8cb-437c7dc51b01.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/497515de-d678-58a7-b8cb-437c7dc51b01.json
deleted file mode 100644
index 154a4c8d..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/497515de-d678-58a7-b8cb-437c7dc51b01.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/VI/25",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/VI/25"
-    ],
-    "PublicationTimestamp": "2012-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        " "
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Palomar Observatory"
-    ],
-    "fulltext": "ivo://CDS.VizieR/VI/25;2018-04-05T10:00:00Z;VI;ivo_managed;Palomar Observatory;POSS Plate Data (Palomar Obs. 1960);CDS;2012;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/VI/25;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?VI/25;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "497515de-d678-58a7-b8cb-437c7dc51b01",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/VI/25"
-    ],
-    "oai_set": [
-        "VI",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [],
-    "title": [
-        "POSS Plate Data (Palomar Obs. 1960)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?VI/25"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/4f3846bb-a4cf-5c7c-9791-5b2f2fc1fc0a.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/4f3846bb-a4cf-5c7c-9791-5b2f2fc1fc0a.json
deleted file mode 100644
index 11b77ff3..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/4f3846bb-a4cf-5c7c-9791-5b2f2fc1fc0a.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/A+A/300/751",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/A+A/300/751"
-    ],
-    "PublicationTimestamp": "1999-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1999"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "1995A&A...300..751A"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "AXER M., FUHRMANN K., GEHREN T."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/A+A/300/751;2018-04-05T10:00:00Z;J.A_A;ivo_managed;AXER M., FUHRMANN K., GEHREN T.;Metal-poor stars spectroscopy. II (Axer+, 1995);CDS;1999;Stars;Stars:peculiar;Masses;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/A+A/300/751;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/300/751;1995A&A...300..751A;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "4f3846bb-a4cf-5c7c-9791-5b2f2fc1fc0a",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/A+A/300/751"
-    ],
-    "oai_set": [
-        "J.A_A",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Stars"
-        },
-        {
-            "name": "Stars peculiar"
-        },
-        {
-            "name": "Masses"
-        }
-    ],
-    "title": [
-        "Metal-poor stars spectroscopy. II (Axer+, 1995)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/300/751"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/4f5084a6-bfb1-59b6-9149-b558fb12bab8.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/4f5084a6-bfb1-59b6-9149-b558fb12bab8.json
deleted file mode 100644
index 58253a86..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/4f5084a6-bfb1-59b6-9149-b558fb12bab8.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/ApJ/681/1017",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/ApJ/681/1017"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2008ApJ...681.1017F"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Fassnacht C.D., Kocevski D.D., Auger M.W., Lubin L.M., Neureuther J.L., Jeltema T.E., Mulchaey J.S., McKean J.P."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/ApJ/681/1017;2018-04-05T10:00:00Z;J.ApJ;ivo_managed;Fassnacht C.D., Kocevski D.D., Auger M.W., Lubin L.M., Neureuther J.L., Jeltema T.E., Mulchaey J.S., McKean J.P.;Chandra observations of lens groups (Fassnacht+, 2008);CDS;2017;Clusters_of_galaxies;Redshifts;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/ApJ/681/1017;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/ApJ/681/1017;2008ApJ...681.1017F;text/xml+votable;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "4f5084a6-bfb1-59b6-9149-b558fb12bab8",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/ApJ/681/1017"
-    ],
-    "oai_set": [
-        "J.ApJ",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Clusters_of_galaxies"
-        },
-        {
-            "name": "Redshifts"
-        }
-    ],
-    "title": [
-        "Chandra observations of lens groups (Fassnacht+, 2008)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/ApJ/681/1017"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/4f68449f-a89b-5ffe-9135-fed5a67f90cc.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/4f68449f-a89b-5ffe-9135-fed5a67f90cc.json
deleted file mode 100644
index deceaba3..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/4f68449f-a89b-5ffe-9135-fed5a67f90cc.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/ApJS/93/161",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/ApJS/93/161"
-    ],
-    "PublicationTimestamp": "1999-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1999"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "1994ApJS...93..161S"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Sarajedini A., Norris J.E."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/ApJS/93/161;2018-04-05T10:00:00Z;J.ApJS;ivo_managed;Sarajedini A., Norris J.E.;CCD photometry of 6 globular clusters (Sarajedini+ 1994);CDS;1999;Globular_Clusters;Photometry;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/ApJS/93/161;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/ApJS/93/161;1994ApJS...93..161S;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "4f68449f-a89b-5ffe-9135-fed5a67f90cc",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/ApJS/93/161"
-    ],
-    "oai_set": [
-        "J.ApJS",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Globular_Clusters"
-        },
-        {
-            "name": "Photometry"
-        }
-    ],
-    "title": [
-        "CCD photometry of 6 globular clusters (Sarajedini+ 1994)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/ApJS/93/161"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/4f8692ae-31fd-5a6e-8957-94ae0debb1b4.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/4f8692ae-31fd-5a6e-8957-94ae0debb1b4.json
deleted file mode 100644
index 6ba68e23..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/4f8692ae-31fd-5a6e-8957-94ae0debb1b4.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/A+A/426/119",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/A+A/426/119"
-    ],
-    "PublicationTimestamp": "2007-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2007"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2004A&A...426..119M"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Mookerjea B., Kramer C., Nielbock M., Nyman L.-A."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/A+A/426/119;2018-04-05T10:00:00Z;J.A_A;ivo_managed;Mookerjea B., Kramer C., Nielbock M., Nyman L.-A.;1.2mm mapping of RCW 106 Giant Molecular Cloud (Mookerjea+, 2004);CDS;2007;Nebulae;HII_regions;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/A+A/426/119;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/426/119;2004A&A...426..119M;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "4f8692ae-31fd-5a6e-8957-94ae0debb1b4",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/A+A/426/119"
-    ],
-    "oai_set": [
-        "J.A_A",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Nebulae"
-        },
-        {
-            "name": "HII_regions"
-        }
-    ],
-    "title": [
-        "1.2mm mapping of RCW 106 Giant Molecular Cloud (Mookerjea+, 2004)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/426/119"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/4f86eab2-c7e6-5db5-8670-18bb550657a5.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/4f86eab2-c7e6-5db5-8670-18bb550657a5.json
deleted file mode 100644
index 725a4637..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/4f86eab2-c7e6-5db5-8670-18bb550657a5.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/A+A/299/39",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/A+A/299/39"
-    ],
-    "PublicationTimestamp": "2000-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "1995A&A...299...39G"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Geier S., Wendker H.J., Wisotzki L."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/A+A/299/39;2018-04-05T10:00:00Z;J.A_A;ivo_managed;Geier S., Wendker H.J., Wisotzki L.;Orion Trapezium area ROSAT PSPC obs. I. (Geier+, 1995);CDS;2000;Open_Clusters;Stars:variable;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/A+A/299/39;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/299/39;1995A&A...299...39G;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "4f86eab2-c7e6-5db5-8670-18bb550657a5",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/A+A/299/39"
-    ],
-    "oai_set": [
-        "J.A_A",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Open_Clusters"
-        },
-        {
-            "name": "Stars variable"
-        }
-    ],
-    "title": [
-        "Orion Trapezium area ROSAT PSPC obs. I. (Geier+, 1995)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/299/39"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/4f9995db-73db-57aa-8675-3be605fe7685.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/4f9995db-73db-57aa-8675-3be605fe7685.json
deleted file mode 100644
index 0effcafe..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/4f9995db-73db-57aa-8675-3be605fe7685.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "Michael Preciado <Michael.E.Preciado@nasa.gov>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://nasa.heasarc/acceptcat",
-    "MetadataAccess": [
-        "ivo://nasa.heasarc/acceptcat"
-    ],
-    "PublicationTimestamp": "2019-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "NASA/GSFC HEASARC"
-    ],
-    "ResourceType": [
-        "AstroObjects"
-    ],
-    "author": [
-        "Cavagnolo et al."
-    ],
-    "fulltext": "ivo://nasa.heasarc/acceptcat;2019-06-17T07:00:23Z;Cavagnolo et al.;Archive of Chandra Cluster Entropy Profile Tables (ACCEPT) Catalog;NASA/GSFC HEASARC;2019;Survey Source;Michael Preciado <Michael.E.Preciado@nasa.gov>;AstroObjects;ivo://nasa.heasarc/acceptcat;https://heasarc.gsfc.nasa.gov/W3Browse/all/acceptcat.html;\n        https://heasarc.gsfc.nasa.gov/cgi-bin/W3Browse/w3query.pl?tablehead=name=heasarc_acceptcat&Action=More+Options&Action=Parameter+Search&ConeAdd=1\n      ;text/xml;text/xml;\n      This table, the Archive of Chandra Cluster Entropy Profile Tables (ACCEPT) Catalog, contains the radial entropy profiles of the intracluster medium (ICM) for a collection of 239 clusters taken from the Chandra X-ray Observatory's Data Archive. Entropy is of great interest because it controls ICM global properties and records the thermal history of a cluster. The authors find that most ICM entropy profiles are well fitted by a model which is a power law at large radii and approaches a constant value at small radii: K(r) = K&lt;sub&gt;0&lt;/sub&gt; + K&lt;sub&gt;100&lt;/sub&gt; (r/100 kpc)&lt;sup&gt;alpha&lt;/sup&gt;, where K&lt;sub&gt;0&lt;/sub&gt; quantifies the typical excess of core entropy above the best-fitting power law found at larger radii. The authors also show that the K&lt;sub&gt;0&lt;/sub&gt; distributions of both the full archival sample and the primary Highest X-Ray Flux Galaxy Cluster Sample of Reiprich (2001, Ph.D. thesis) are bimodal with a distinct gap between K&lt;sub&gt;0&lt;/sub&gt; ~ 30 - 50 keV cm&lt;sup&gt;2&lt;/sup&gt; and population peaks at K&lt;sub&gt;0&lt;/sub&gt; ~ 15 keV cm&lt;sup&gt;2&lt;/sup&gt; and K&lt;sub&gt;0&lt;/sub&gt; ~ 150 keV cm&lt;sup&gt;2&lt;/sup&gt;. The effects of point-spread function smearing and angular resolution on best-fit K&lt;sub&gt;0&lt;/sub&gt; values are investigated using mock Chandra observations and degraded entropy profiles, respectively. The authors find that neither of these effects is sufficient to explain the entropy-profile flattening they measure at small radii. The influence of profile curvature and the number of radial bins on the best-fit K&lt;sub&gt;0&lt;/sub&gt; is also considered, and they find no indication that K&lt;sub&gt;0&lt;/sub&gt; is significantly impacted by either. All data and results associated with this work are publicly available via the project web site &lt;a href=\"http://www.pa.msu.edu/astro/MC2/accept/\"&gt;http://www.pa.msu.edu/astro/MC2/accept/&lt;/a&gt;. The sample is collected from observations taken with the Chandra X-ray Observatory and which were publicly available in the CDA (Chandra Data Archive) as of 2008 August.\n    ",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "4f9995db-73db-57aa-8675-3be605fe7685",
-    "notes": [
-        "\n      This table, the Archive of Chandra Cluster Entropy Profile Tables (ACCEPT) Catalog, contains the radial entropy profiles of the intracluster medium (ICM) for a collection of 239 clusters taken from the Chandra X-ray Observatory's Data Archive. Entropy is of great interest because it controls ICM global properties and records the thermal history of a cluster. The authors find that most ICM entropy profiles are well fitted by a model which is a power law at large radii and approaches a constant value at small radii: K(r) = K&lt;sub&gt;0&lt;/sub&gt; + K&lt;sub&gt;100&lt;/sub&gt; (r/100 kpc)&lt;sup&gt;alpha&lt;/sup&gt;, where K&lt;sub&gt;0&lt;/sub&gt; quantifies the typical excess of core entropy above the best-fitting power law found at larger radii. The authors also show that the K&lt;sub&gt;0&lt;/sub&gt; distributions of both the full archival sample and the primary Highest X-Ray Flux Galaxy Cluster Sample of Reiprich (2001, Ph.D. thesis) are bimodal with a distinct gap between K&lt;sub&gt;0&lt;/sub&gt; ~ 30 - 50 keV cm&lt;sup&gt;2&lt;/sup&gt; and population peaks at K&lt;sub&gt;0&lt;/sub&gt; ~ 15 keV cm&lt;sup&gt;2&lt;/sup&gt; and K&lt;sub&gt;0&lt;/sub&gt; ~ 150 keV cm&lt;sup&gt;2&lt;/sup&gt;. The effects of point-spread function smearing and angular resolution on best-fit K&lt;sub&gt;0&lt;/sub&gt; values are investigated using mock Chandra observations and degraded entropy profiles, respectively. The authors find that neither of these effects is sufficient to explain the entropy-profile flattening they measure at small radii. The influence of profile curvature and the number of radial bins on the best-fit K&lt;sub&gt;0&lt;/sub&gt; is also considered, and they find no indication that K&lt;sub&gt;0&lt;/sub&gt; is significantly impacted by either. All data and results associated with this work are publicly available via the project web site &lt;a href=\"http://www.pa.msu.edu/astro/MC2/accept/\"&gt;http://www.pa.msu.edu/astro/MC2/accept/&lt;/a&gt;. The sample is collected from observations taken with the Chandra X-ray Observatory and which were publicly available in the CDA (Chandra Data Archive) as of 2008 August.\n    "
-    ],
-    "oai_identifier": [
-        "ivo://nasa.heasarc/acceptcat"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Survey Source"
-        }
-    ],
-    "title": [
-        "Archive of Chandra Cluster Entropy Profile Tables (ACCEPT) Catalog"
-    ],
-    "url": "https://heasarc.gsfc.nasa.gov/W3Browse/all/acceptcat.html"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/504158ba-d3d4-5fba-9798-6b9f2d2097f4.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/504158ba-d3d4-5fba-9798-6b9f2d2097f4.json
deleted file mode 100644
index ac2928e4..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/504158ba-d3d4-5fba-9798-6b9f2d2097f4.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/MNRAS/396/2011",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/MNRAS/396/2011"
-    ],
-    "PublicationTimestamp": "2010-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2009MNRAS.396.2011E"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "El Bouchefry K."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/MNRAS/396/2011;2018-04-05T10:00:00Z;J.MNRAS;ivo_managed;El Bouchefry K.;X-ray+Radio sources in XBootes (El Bouchefry, 2009);CDS;2010;Photometry;Galaxies;Redshifts;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/MNRAS/396/2011;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/MNRAS/396/2011;2009MNRAS.396.2011E;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "504158ba-d3d4-5fba-9798-6b9f2d2097f4",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/MNRAS/396/2011"
-    ],
-    "oai_set": [
-        "J.MNRAS",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Photometry"
-        },
-        {
-            "name": "Galaxies"
-        },
-        {
-            "name": "Redshifts"
-        }
-    ],
-    "title": [
-        "X-ray+Radio sources in XBootes (El Bouchefry, 2009)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/MNRAS/396/2011"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/9575a105-d39d-58c3-aa3c-8028c0a09e5b.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/9575a105-d39d-58c3-aa3c-8028c0a09e5b.json
deleted file mode 100644
index 27205a45..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/9575a105-d39d-58c3-aa3c-8028c0a09e5b.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/MNRAS/464/2730",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/MNRAS/464/2730"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2017MNRAS.464.2730V"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Villanova S., Moni Bidin C., Mauro F., Munoz C., Monaco L."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/MNRAS/464/2730;2018-10-08T13:12:19Z;J.MNRAS;ivo_managed;Villanova S., Moni Bidin C., Mauro F., Munoz C., Monaco L.;M28 red giant branch stars abundances (Villanova+, 2017);CDS;2018;Abundances;Globular_Clusters;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/MNRAS/464/2730;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/MNRAS/464/2730;2017MNRAS.464.2730V;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "9575a105-d39d-58c3-aa3c-8028c0a09e5b",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/MNRAS/464/2730"
-    ],
-    "oai_set": [
-        "J.MNRAS",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Abundances"
-        },
-        {
-            "name": "Globular_Clusters"
-        }
-    ],
-    "title": [
-        "M28 red giant branch stars abundances (Villanova+, 2017)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/MNRAS/464/2730"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/9904b53e-7ce7-5db4-a6c1-97375722b835.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/9904b53e-7ce7-5db4-a6c1-97375722b835.json
deleted file mode 100644
index ba461c32..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/9904b53e-7ce7-5db4-a6c1-97375722b835.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/ApJ/854/107",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/ApJ/854/107"
-    ],
-    "PublicationTimestamp": "2019-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2018ApJ...854..107F"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Fausnaugh M.M., Starkey D.A., Horne K., et al."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/ApJ/854/107;2019-01-09T09:33:37Z;J.ApJ;ivo_managed;Fausnaugh M.M., Starkey D.A., Horne K., et al.;Light curves of 2 Seyfert 1 galaxies (Fausnaugh+, 2018);CDS;2019;AGN;Photometry;Photometry:wide-band;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/ApJ/854/107;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/ApJ/854/107;2018ApJ...854..107F;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "9904b53e-7ce7-5db4-a6c1-97375722b835",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/ApJ/854/107"
-    ],
-    "oai_set": [
-        "J.ApJ",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "AGN"
-        },
-        {
-            "name": "Photometry"
-        },
-        {
-            "name": "Photometry wide-band"
-        }
-    ],
-    "title": [
-        "Light curves of 2 Seyfert 1 galaxies (Fausnaugh+, 2018)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/ApJ/854/107"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/9926ec67-65d2-565a-b834-eefc8417c271.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/9926ec67-65d2-565a-b834-eefc8417c271.json
deleted file mode 100644
index 0092d6ca..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/9926ec67-65d2-565a-b834-eefc8417c271.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/A+A/623/A146",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/A+A/623/A146"
-    ],
-    "PublicationTimestamp": "2019-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2019A&A...623A.146A"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Anderson R.I."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/A+A/623/A146;2019-03-27T07:01:30Z;J.A_A;ivo_managed;Anderson R.I.;Radial Velocity and BIS measurements of Polaris (Anderson, 2019);CDS;2019;Orbits;Binaries:spectroscopic;Multiple_Stars;Stars;Spectroscopy;Velocities;Stars:variable;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/A+A/623/A146;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/623/A146;2019A&A...623A.146A;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "9926ec67-65d2-565a-b834-eefc8417c271",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/A+A/623/A146"
-    ],
-    "oai_set": [
-        "J.A_A",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Orbits"
-        },
-        {
-            "name": "Binaries spectroscopic"
-        },
-        {
-            "name": "Multiple_Stars"
-        },
-        {
-            "name": "Stars"
-        },
-        {
-            "name": "Spectroscopy"
-        },
-        {
-            "name": "Velocities"
-        },
-        {
-            "name": "Stars variable"
-        }
-    ],
-    "title": [
-        "Radial Velocity and BIS measurements of Polaris (Anderson, 2019)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/623/A146"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/9971c101-a24d-58e2-86e0-bd42d96d82c3.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/9971c101-a24d-58e2-86e0-bd42d96d82c3.json
deleted file mode 100644
index a53235ee..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/9971c101-a24d-58e2-86e0-bd42d96d82c3.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/A+A/624/A107",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/A+A/624/A107"
-    ],
-    "PublicationTimestamp": "2019-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2019A&A...624A.107V"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Verbena J.L., Bujarrabal V., Alcolea J., Gomez-Garrido M., Castro-Carrizo A."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/A+A/624/A107;2019-05-06T15:29:13Z;J.A_A;ivo_managed;Verbena J.L., Bujarrabal V., Alcolea J., Gomez-Garrido M., Castro-Carrizo A.;IK Tau & IRC+10011 interferometric observations (Verbena+, 2019);CDS;2019;Stars;Stars:late-type;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/A+A/624/A107;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/624/A107;2019A&A...624A.107V;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "9971c101-a24d-58e2-86e0-bd42d96d82c3",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/A+A/624/A107"
-    ],
-    "oai_set": [
-        "J.A_A",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Stars"
-        },
-        {
-            "name": "Stars late-type"
-        }
-    ],
-    "title": [
-        "IK Tau & IRC+10011 interferometric observations (Verbena+, 2019)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/624/A107"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/b03cdcbb-6a7a-5ded-bdb6-786e6e13473d.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/b03cdcbb-6a7a-5ded-bdb6-786e6e13473d.json
deleted file mode 100644
index 026f6a7e..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/b03cdcbb-6a7a-5ded-bdb6-786e6e13473d.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/A+A/589/A110",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/A+A/589/A110"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2016A&A...589A.110A"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Anderson J.P., Gutierrez C.P., Dessart L., Hamuy M., Galbany L., Morrell N.I., Stritzinger M.D., Phillips M.M., Folatelli G., Boffin H.M.J., De Jaeger T., Kuncarayakti H., Prieto J.L."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/A+A/589/A110;2018-04-05T10:00:00Z;J.A_A;ivo_managed;Anderson J.P., Gutierrez C.P., Dessart L., Hamuy M., Galbany L., Morrell N.I., Stritzinger M.D., Phillips M.M., Folatelli G., Boffin H.M.J., De Jaeger T., Kuncarayakti H., Prieto J.L.;SN II in host HII regions (Anderson+, 2016);CDS;2018;HII_regions;SuperNovae;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/A+A/589/A110;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/589/A110;2016A&A...589A.110A;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "b03cdcbb-6a7a-5ded-bdb6-786e6e13473d",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/A+A/589/A110"
-    ],
-    "oai_set": [
-        "J.A_A",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "HII_regions"
-        },
-        {
-            "name": "SuperNovae"
-        }
-    ],
-    "title": [
-        "SN II in host HII regions (Anderson+, 2016)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/589/A110"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/b3eb53cc-69ce-5ff8-a7aa-2f1a0b8a20e9.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/b3eb53cc-69ce-5ff8-a7aa-2f1a0b8a20e9.json
deleted file mode 100644
index d6fd0362..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/b3eb53cc-69ce-5ff8-a7aa-2f1a0b8a20e9.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/ApJ/700/209",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/ApJ/700/209"
-    ],
-    "PublicationTimestamp": "2011-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2009ApJ...700..209M"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Miroshnichenko A.S., Chentsov E.L., Klochkova V.G., et al."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/ApJ/700/209;2018-04-05T10:00:00Z;J.ApJ;ivo_managed;Miroshnichenko A.S., Chentsov E.L., Klochkova V.G., et al.;Spectroscopy of the B[e] star VES 695 (Miroshnichenko+, 2009);CDS;2011;Spectroscopy;Velocities;Stars:early-type;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/ApJ/700/209;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/ApJ/700/209;2009ApJ...700..209M;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "b3eb53cc-69ce-5ff8-a7aa-2f1a0b8a20e9",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/ApJ/700/209"
-    ],
-    "oai_set": [
-        "J.ApJ",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Spectroscopy"
-        },
-        {
-            "name": "Velocities"
-        },
-        {
-            "name": "Stars early-type"
-        }
-    ],
-    "title": [
-        "Spectroscopy of the B[e] star VES 695 (Miroshnichenko+, 2009)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/ApJ/700/209"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/b3ef7fb1-a91b-5739-b0e9-83fe9762e247.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/b3ef7fb1-a91b-5739-b0e9-83fe9762e247.json
deleted file mode 100644
index 2324929a..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/b3ef7fb1-a91b-5739-b0e9-83fe9762e247.json
+++ /dev/null
@@ -1,59 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/MNRAS/445/3512",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/MNRAS/445/3512"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2014MNRAS.445.3512S"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Saburova A., del Popolo A."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/MNRAS/445/3512;2018-04-05T10:00:00Z;J.MNRAS;ivo_managed;Saburova A., del Popolo A.;Surface density of dark matter haloes (Saburova+, 2014);CDS;2018;Galaxies;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/MNRAS/445/3512;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/MNRAS/445/3512;2014MNRAS.445.3512S;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "b3ef7fb1-a91b-5739-b0e9-83fe9762e247",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/MNRAS/445/3512"
-    ],
-    "oai_set": [
-        "J.MNRAS",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Galaxies"
-        }
-    ],
-    "title": [
-        "Surface density of dark matter haloes (Saburova+, 2014)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/MNRAS/445/3512"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/b3ff0b66-d41d-53f9-8ca0-3297c8503aab.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/b3ff0b66-d41d-53f9-8ca0-3297c8503aab.json
deleted file mode 100644
index c93b40ce..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/b3ff0b66-d41d-53f9-8ca0-3297c8503aab.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/ApJ/663/1149",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/ApJ/663/1149"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2007ApJ...663.1149H"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Harvey P., Merin B., Huard T.L., Rebull L.M., Chapman N., Evans II N.J., Myers P.C."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/ApJ/663/1149;2018-04-05T10:00:00Z;J.ApJ;ivo_managed;Harvey P., Merin B., Huard T.L., Rebull L.M., Chapman N., Evans II N.J., Myers P.C.;Spitzer survey of Serpens YSO population (Harvey+, 2007);CDS;2017;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/ApJ/663/1149;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/ApJ/663/1149;2007ApJ...663.1149H;text/xml+votable;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "b3ff0b66-d41d-53f9-8ca0-3297c8503aab",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/ApJ/663/1149"
-    ],
-    "oai_set": [
-        "J.ApJ",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [],
-    "title": [
-        "Spitzer survey of Serpens YSO population (Harvey+, 2007)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/ApJ/663/1149"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/b4a170b1-210e-5d0b-aea7-25eafa629687.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/b4a170b1-210e-5d0b-aea7-25eafa629687.json
deleted file mode 100644
index 3bc4b9c6..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/b4a170b1-210e-5d0b-aea7-25eafa629687.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/AJ/134/1963",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/AJ/134/1963"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2007AJ....134.1963F"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Faccioli L., Alcock C., Cook K., Prochter G.E., Protopapas P., Syphers D."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/AJ/134/1963;2018-04-05T10:00:00Z;J.AJ;ivo_managed;Faccioli L., Alcock C., Cook K., Prochter G.E., Protopapas P., Syphers D.;MACHO r,b light curves of MC eclipsing binaries (Faccioli+, 2007);CDS;2017;Binaries:eclipsing;Photometry:wide-band;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/AJ/134/1963;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/AJ/134/1963;2007AJ....134.1963F;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "b4a170b1-210e-5d0b-aea7-25eafa629687",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/AJ/134/1963"
-    ],
-    "oai_set": [
-        "J.AJ",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Binaries eclipsing"
-        },
-        {
-            "name": "Photometry wide-band"
-        }
-    ],
-    "title": [
-        "MACHO r,b light curves of MC eclipsing binaries (Faccioli+, 2007)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/AJ/134/1963"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/feef440a-b5f5-53d1-8042-d88b664f8389.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/feef440a-b5f5-53d1-8042-d88b664f8389.json
deleted file mode 100644
index 6a1caf08..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/feef440a-b5f5-53d1-8042-d88b664f8389.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/ApJ/838/122",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/ApJ/838/122"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2017ApJ...838..122J"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Jetsu L., Henry G.W., Lehtinen J."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/ApJ/838/122;2018-04-05T10:00:00Z;J.ApJ;ivo_managed;Jetsu L., Henry G.W., Lehtinen J.;Light curve analysis of 13 active stars (Jetsu+, 2017);CDS;2017;Photometry;Ephemerides;Stars:variable;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/ApJ/838/122;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/ApJ/838/122;2017ApJ...838..122J;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "feef440a-b5f5-53d1-8042-d88b664f8389",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/ApJ/838/122"
-    ],
-    "oai_set": [
-        "J.ApJ",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Photometry"
-        },
-        {
-            "name": "Ephemerides"
-        },
-        {
-            "name": "Stars variable"
-        }
-    ],
-    "title": [
-        "Light curve analysis of 13 active stars (Jetsu+, 2017)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/ApJ/838/122"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/ff199eb1-69b9-52f5-9222-011a0eb939e1.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/ff199eb1-69b9-52f5-9222-011a0eb939e1.json
deleted file mode 100644
index d2a7012e..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/ff199eb1-69b9-52f5-9222-011a0eb939e1.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/A+A/486/855",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/A+A/486/855"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2008A&A...486..855A"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Andronov I.L., Chinarova L.L., Han W., Kim Y., Yoon J.-N."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/A+A/486/855;2018-04-05T10:00:00Z;J.A_A;ivo_managed;Andronov I.L., Chinarova L.L., Han W., Kim Y., Yoon J.-N.;R light curve of DO Dra (Andronov+, 2008);CDS;2017;Binaries:cataclysmic;Photometry;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/A+A/486/855;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/486/855;2008A&A...486..855A;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "ff199eb1-69b9-52f5-9222-011a0eb939e1",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/A+A/486/855"
-    ],
-    "oai_set": [
-        "J.A_A",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Binaries cataclysmic"
-        },
-        {
-            "name": "Photometry"
-        }
-    ],
-    "title": [
-        "R light curve of DO Dra (Andronov+, 2008)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/486/855"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/ff68dcb2-5c2b-5bde-9480-ed2b4aa04d94.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/ff68dcb2-5c2b-5bde-9480-ed2b4aa04d94.json
deleted file mode 100644
index 64d1b8a9..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/ff68dcb2-5c2b-5bde-9480-ed2b4aa04d94.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/A+A/527/A85",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/A+A/527/A85"
-    ],
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2011A&A...527A..85N"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Nascimbeni V., Piotto G., Bedin L.R., Damasso M."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/A+A/527/A85;2018-04-05T10:00:00Z;J.A_A;ivo_managed;Nascimbeni V., Piotto G., Bedin L.R., Damasso M.;Light curves of HAT-P-3b and HAT-P-14b (Nascimbeni+, 2011);CDS;2017;Multiple_Stars;Photometry;Planets+Asteroids;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/A+A/527/A85;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/527/A85;2011A&A...527A..85N;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "ff68dcb2-5c2b-5bde-9480-ed2b4aa04d94",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/A+A/527/A85"
-    ],
-    "oai_set": [
-        "J.A_A",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Multiple_Stars"
-        },
-        {
-            "name": "Photometry"
-        },
-        {
-            "name": "Planets"
-        },
-        {
-            "name": "Asteroids"
-        }
-    ],
-    "title": [
-        "Light curves of HAT-P-3b and HAT-P-14b (Nascimbeni+, 2011)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/A+A/527/A85"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_datacite/SET_1/json/ff7d3ab6-64b3-5f82-aae9-1022fca6b4af.json b/oaitestdata/ivoa-oai_datacite/SET_1/json/ff7d3ab6-64b3-5f82-aae9-1022fca6b4af.json
deleted file mode 100644
index 49309777..00000000
--- a/oaitestdata/ivoa-oai_datacite/SET_1/json/ff7d3ab6-64b3-5f82-aae9-1022fca6b4af.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "CDS support team <cds-question@unistra.fr>"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "Format": [
-        "text/xml+votable"
-    ],
-    "MetaDataAccess": "http://dc.g-vo.org/rr/q/pmh/pubreg.xml?verb=GetRecord&metadataPrefix=oai_datacite&identifier=ivo://CDS.VizieR/J/ApJ/663/277",
-    "MetadataAccess": [
-        "ivo://CDS.VizieR/J/ApJ/663/277"
-    ],
-    "PublicationTimestamp": "2009-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2009"
-    ],
-    "Publisher": [
-        "CDS"
-    ],
-    "RelatedIdentifier": [
-        "2007ApJ...663..277F"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Fekadu N., Sandquist E.L., Bolte M."
-    ],
-    "fulltext": "ivo://CDS.VizieR/J/ApJ/663/277;2018-04-05T10:00:00Z;J.ApJ;ivo_managed;Fekadu N., Sandquist E.L., Bolte M.;BVI of NGC 5466 red giants and blue stragglers (Fekadu+, 2007);CDS;2009;Globular_Clusters;Stars;Photometry:wide-band;CDS support team <cds-question@unistra.fr>;ivo://CDS.VizieR/J/ApJ/663/277;http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/ApJ/663/277;2007ApJ...663..277F;text/xml+votable;text/xml+votable;public",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "ff7d3ab6-64b3-5f82-aae9-1022fca6b4af",
-    "oai_identifier": [
-        "ivo://CDS.VizieR/J/ApJ/663/277"
-    ],
-    "oai_set": [
-        "J.ApJ",
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Globular_Clusters"
-        },
-        {
-            "name": "Stars"
-        },
-        {
-            "name": "Photometry wide-band"
-        }
-    ],
-    "title": [
-        "BVI of NGC 5466 red giants and blue stragglers (Fekadu+, 2007)"
-    ],
-    "url": "http://cdsarc.u-strasbg.fr/cgi-bin/Cat?J/ApJ/663/277"
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_dc/SET_1/json/00baeb04-a931-5f0a-a070-f31b48ed9ac2.json b/oaitestdata/ivoa-oai_dc/SET_1/json/00baeb04-a931-5f0a-a070-f31b48ed9ac2.json
deleted file mode 100644
index 8620455a..00000000
--- a/oaitestdata/ivoa-oai_dc/SET_1/json/00baeb04-a931-5f0a-a070-f31b48ed9ac2.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Contact": [
-        "MAGIC Collaboration"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "MetaDataAccess": "http://registry.euro-vo.org/oai.jsp?verb=GetRecord&metadataPrefix=oai_dc&identifier=ivo://magic",
-    "PublicationTimestamp": "2016-02-05T14:51:05Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "MAGIC Collaboration"
-    ],
-    "RelatedIdentifier": [
-        "ivo://magic"
-    ],
-    "author": [
-        "MAGIC Collaboration"
-    ],
-    "fulltext": "ivo://magic;2016-02-05T14:51:05Z;ivo_managed;MAGIC Authority Resource;MAGIC Collaboration;MAGIC Public Data;MAGIC (Major Atmospheric Gamma-ray Imaging Cherenkov) experiment is a two-telescope ground-based array that detects and studies very high energy (VHE, E>100 GeV) gamma-rays. Located in the Canary island of La Palma, at altitude of more than 2200 m above the sea level, these instruments benefit from more than 1000 h of dark observational time per year (with additional 300h available for observations under moderate moonlight). With their 17 m diameter mirrors, the MAGIC Telescopes are today the largest instruments of their kind. MAGIC I has been operational since 2004 and it already achieved the lowest energy threshold (~25 GeV) among the current generation of IACTs. In 2009 it was joined by MAGIC-II, and together, in the stereoscopic mode, they allow for the observations of significantly improved sensitivity, lower energy threshold and better energy and angular resolution. The very energetic photons MAGIC detects can only be produced in violent processes, like in the neighbourhood of black holes, or in the aftermath of explosions of stars. As a result, MAGIC Telescopes contribute substantially to the current knowledge about Supernova Remnants, Active Galactic Nuclei, Microquasars, Pulsars, X-ray binaries, Gamma-ray bursts, search for Dark Matter, etc.;MAGIC Collaboration;ivo://magic",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "00baeb04-a931-5f0a-a070-f31b48ed9ac2",
-    "notes": [
-        "MAGIC (Major Atmospheric Gamma-ray Imaging Cherenkov) experiment is a two-telescope ground-based array that detects and studies very high energy (VHE, E>100 GeV) gamma-rays. Located in the Canary island of La Palma, at altitude of more than 2200 m above the sea level, these instruments benefit from more than 1000 h of dark observational time per year (with additional 300h available for observations under moderate moonlight). With their 17 m diameter mirrors, the MAGIC Telescopes are today the largest instruments of their kind. MAGIC I has been operational since 2004 and it already achieved the lowest energy threshold (~25 GeV) among the current generation of IACTs. In 2009 it was joined by MAGIC-II, and together, in the stereoscopic mode, they allow for the observations of significantly improved sensitivity, lower energy threshold and better energy and angular resolution. The very energetic photons MAGIC detects can only be produced in violent processes, like in the neighbourhood of black holes, or in the aftermath of explosions of stars. As a result, MAGIC Telescopes contribute substantially to the current knowledge about Supernova Remnants, Active Galactic Nuclei, Microquasars, Pulsars, X-ray binaries, Gamma-ray bursts, search for Dark Matter, etc."
-    ],
-    "oai_identifier": [
-        "ivo://magic"
-    ],
-    "oai_set": [
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "MAGIC Public Data"
-        }
-    ],
-    "title": [
-        "MAGIC (Major Atmospheric Gamma-ray Imaging Cherenkov) experiment is a two-telescope ground-based array that detects and studies very high energy (VHE, E>100 GeV) gamma-rays. Located in the Canary island of La Palma, at altitude of more than 2200 m above the sea level, these instruments benefit from more than 1000 h of dark observational time per year (with additional 300h available for observations under moderate moonlight). With their 17 m diameter mirrors, the MAGIC Telescopes are today the largest instruments of their kind. MAGIC I has been operational since 2004 and it already achieved the lowest energy threshold (~25 GeV) among the current generation of IACTs. In 2009 it was joined by MAGIC-II, and together, in the stereoscopic mode, they allow for the observations of significantly improved sensitivity, lower energy threshold and better energy and angular resolution. The very energetic photons MAGIC detects can only be produced in violent processes, like in the neighbourhood of black holes, or in the aftermath of explosions of stars. As a result, MAGIC Telescopes contribute substantially to the current knowledge about Supernova Remnants, Active Galactic Nuclei, Microquasars, Pulsars, X-ray binaries, Gamma-ray bursts, search for Dark Matter, etc."
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_dc/SET_1/json/0a013946-d5dd-5806-935a-ee9266254cd0.json b/oaitestdata/ivoa-oai_dc/SET_1/json/0a013946-d5dd-5806-935a-ee9266254cd0.json
deleted file mode 100644
index 8458ffeb..00000000
--- a/oaitestdata/ivoa-oai_dc/SET_1/json/0a013946-d5dd-5806-935a-ee9266254cd0.json
+++ /dev/null
@@ -1,44 +0,0 @@
-{
-    "Contact": [
-        "The GAVO DC team"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "MetaDataAccess": "http://registry.euro-vo.org/oai.jsp?verb=GetRecord&metadataPrefix=oai_dc&identifier=ivo://org.gavo.dc/hppunion/q/im",
-    "PublicationTimestamp": "2018-12-21T17:01:27Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "The GAVO DC team"
-    ],
-    "RelatedIdentifier": [
-        "ivo://org.gavo.dc/hppunion/q/im"
-    ],
-    "author": [
-        "GAVO Data Center"
-    ],
-    "fulltext": "ivo://org.gavo.dc/hppunion/q/im;2018-12-21T17:01:27Z;Historical Photographic Plate Image Archive;ivo://org.gavo.dc/hppunion/q/im;GAVO Data Center;\n        GAVO's historical photographic plate archive (GHHPA) is a\n        collection of various digitized historical photographic\n        plates.  It currently exposes:\n\n        * the scans of plates of selected Kapteyn special fields obtained\n          at Potsdam\n        * the Palomar-Leiden Trojan surveys, 1960-1977,\n        * a collection of plates obtained at Boyden Station, South Africa, \n          kept at various German observatories.\n\n        Other plate collections kept by GAVO include the Heidelberg\n        Digitized Astronomical Plates HDAP,\n        ivo://org.gavo.dc/lswscans/res/positions/siap, and the APPLAUSE\n        database from Potsdam.;The GAVO DC team",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0a013946-d5dd-5806-935a-ee9266254cd0",
-    "notes": [
-        "\n        GAVO's historical photographic plate archive (GHHPA) is a\n        collection of various digitized historical photographic\n        plates.  It currently exposes:\n\n        * the scans of plates of selected Kapteyn special fields obtained\n          at Potsdam\n        * the Palomar-Leiden Trojan surveys, 1960-1977,\n        * a collection of plates obtained at Boyden Station, South Africa, \n          kept at various German observatories.\n\n        Other plate collections kept by GAVO include the Heidelberg\n        Digitized Astronomical Plates HDAP,\n        ivo://org.gavo.dc/lswscans/res/positions/siap, and the APPLAUSE\n        database from Potsdam."
-    ],
-    "oai_identifier": [
-        "ivo://org.gavo.dc/hppunion/q/im"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "title": [
-        "\n        GAVO's historical photographic plate archive (GHHPA) is a\n        collection of various digitized historical photographic\n        plates.  It currently exposes:\n\n        * the scans of plates of selected Kapteyn special fields obtained\n          at Potsdam\n        * the Palomar-Leiden Trojan surveys, 1960-1977,\n        * a collection of plates obtained at Boyden Station, South Africa, \n          kept at various German observatories.\n\n        Other plate collections kept by GAVO include the Heidelberg\n        Digitized Astronomical Plates HDAP,\n        ivo://org.gavo.dc/lswscans/res/positions/siap, and the APPLAUSE\n        database from Potsdam."
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_dc/SET_1/json/0a039405-b85b-574a-b5e1-4290da95bb21.json b/oaitestdata/ivoa-oai_dc/SET_1/json/0a039405-b85b-574a-b5e1-4290da95bb21.json
deleted file mode 100644
index fe3e572e..00000000
--- a/oaitestdata/ivoa-oai_dc/SET_1/json/0a039405-b85b-574a-b5e1-4290da95bb21.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "The GAVO DC team"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "MetaDataAccess": "http://registry.euro-vo.org/oai.jsp?verb=GetRecord&metadataPrefix=oai_dc&identifier=ivo://org.gavo.dc/cars/q/cutout",
-    "PublicationTimestamp": "2018-12-21T17:01:27Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "The GAVO DC team"
-    ],
-    "RelatedIdentifier": [
-        "ivo://org.gavo.dc/cars/q/cutout"
-    ],
-    "author": [
-        "Dietrich, J. P.",
-        "Schirmer, M.",
-        "Brimioulle, F.",
-        "Lerchster, M.",
-        "Hildebrandt, H.",
-        "Erben, T.",
-        "Hudelot, P.",
-        "Schneider, P.",
-        "van Waerbeke, L.",
-        "Benjamin, J.",
-        "Holhjem, K.",
-        "Schrabback, T.",
-        "Cordes, O."
-    ],
-    "fulltext": "ivo://org.gavo.dc/cars/q/cutout;2018-12-21T17:01:27Z;CARS image cutouts;ivo://org.gavo.dc/cars/q/cutout;Erben, T.;Hildebrandt, H.;Lerchster, M.;Hudelot, P.;Benjamin, J.;van Waerbeke, L.;Schrabback, T.;Brimioulle, F.;Cordes, O.;Dietrich, J. P.;Holhjem, K.;Schirmer, M.;Schneider, P.;Images and data from from the CFHTLS archive research survey, a\n        multi-band dataset spanning 37 square degrees of sky in high galactic\n        latitudes.;The GAVO DC team",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0a039405-b85b-574a-b5e1-4290da95bb21",
-    "notes": [
-        "Images and data from from the CFHTLS archive research survey, a\n        multi-band dataset spanning 37 square degrees of sky in high galactic\n        latitudes."
-    ],
-    "oai_identifier": [
-        "ivo://org.gavo.dc/cars/q/cutout"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "title": [
-        "Images and data from from the CFHTLS archive research survey, a\n        multi-band dataset spanning 37 square degrees of sky in high galactic\n        latitudes."
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_dc/SET_1/json/0a0d9543-8055-59bf-98e9-c877f211115b.json b/oaitestdata/ivoa-oai_dc/SET_1/json/0a0d9543-8055-59bf-98e9-c877f211115b.json
deleted file mode 100644
index 58b961c4..00000000
--- a/oaitestdata/ivoa-oai_dc/SET_1/json/0a0d9543-8055-59bf-98e9-c877f211115b.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "NASA/IPAC Infrared Science Archive"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "MetaDataAccess": "http://registry.euro-vo.org/oai.jsp?verb=GetRecord&metadataPrefix=oai_dc&identifier=ivo://irsa.ipac/Spitzer/Catalog/SWIRE/SWIRE-LHISOSha",
-    "PublicationTimestamp": "2016-07-23T23:21:26Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "NASA/IPAC Infrared Science Archive"
-    ],
-    "RelatedIdentifier": [
-        "ivo://irsa.ipac/Spitzer/Catalog/SWIRE/SWIRE-LHISOSha"
-    ],
-    "ResourceType": [
-        "Catalog"
-    ],
-    "author": [
-        "SWIRE team"
-    ],
-    "fulltext": "ivo://irsa.ipac/Spitzer/Catalog/SWIRE/SWIRE-LHISOSha;2016-07-23T23:21:26Z;Spitzer Wide-area InfraRed Extragalactic Survey Lockman Hole ISOCAM Shallow Field MIPS 24 micron Catalog;ivo://irsa.ipac/Spitzer/Catalog/SWIRE/SWIRE-LHISOSha;NASA/IPAC Infrared Science Archive;SWIRE team;extragalactic survey;The Spitzer Wide-area InfraRed Extragalactic survey (SWIRE), the largest Spitzer Legacy program, is a wide-area, imaging survey to trace the evolution of dusty, star-forming galaxies, evolved stellar populations, and AGN as a function of environment, from redshifts z~3 to the current epoch. SWIRE surveys 6 high-latitude fields, totaling ~50 sq. deg. in all 7 Spitzer bands: 3.6, 4.5, 5.8, and 8 microns with IRAC and 24, 70, and 160 microns with MIPS (Lonsdale et al. 2003). The SWIRE Legacy Extragalactic Source Catalogs will eventually contain in excess of 2 million IR-selected galaxies, from those dominated by the light of stellar populations detected primarily by IRAC, to starbursts, ultra-luminous infrared galaxies and AGN detected also by MIPS.\n\n        The SWIRE Lockman Hole ISOCAM Deep Field Catalog presents MIPS 24 micron measurements of the sources detected at 14.3 micron in the Lockman Hole Shallow Survey by ISO. For more details on the Lockman Hole ISOCAM Shallow Survey, see Fadda et al. (2004).;Catalog",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0a0d9543-8055-59bf-98e9-c877f211115b",
-    "notes": [
-        "The Spitzer Wide-area InfraRed Extragalactic survey (SWIRE), the largest Spitzer Legacy program, is a wide-area, imaging survey to trace the evolution of dusty, star-forming galaxies, evolved stellar populations, and AGN as a function of environment, from redshifts z~3 to the current epoch. SWIRE surveys 6 high-latitude fields, totaling ~50 sq. deg. in all 7 Spitzer bands: 3.6, 4.5, 5.8, and 8 microns with IRAC and 24, 70, and 160 microns with MIPS (Lonsdale et al. 2003). The SWIRE Legacy Extragalactic Source Catalogs will eventually contain in excess of 2 million IR-selected galaxies, from those dominated by the light of stellar populations detected primarily by IRAC, to starbursts, ultra-luminous infrared galaxies and AGN detected also by MIPS.\n\n        The SWIRE Lockman Hole ISOCAM Deep Field Catalog presents MIPS 24 micron measurements of the sources detected at 14.3 micron in the Lockman Hole Shallow Survey by ISO. For more details on the Lockman Hole ISOCAM Shallow Survey, see Fadda et al. (2004)."
-    ],
-    "oai_identifier": [
-        "ivo://irsa.ipac/Spitzer/Catalog/SWIRE/SWIRE-LHISOSha"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "extragalactic survey"
-        }
-    ],
-    "title": [
-        "The Spitzer Wide-area InfraRed Extragalactic survey (SWIRE), the largest Spitzer Legacy program, is a wide-area, imaging survey to trace the evolution of dusty, star-forming galaxies, evolved stellar populations, and AGN as a function of environment, from redshifts z~3 to the current epoch. SWIRE surveys 6 high-latitude fields, totaling ~50 sq. deg. in all 7 Spitzer bands: 3.6, 4.5, 5.8, and 8 microns with IRAC and 24, 70, and 160 microns with MIPS (Lonsdale et al. 2003). The SWIRE Legacy Extragalactic Source Catalogs will eventually contain in excess of 2 million IR-selected galaxies, from those dominated by the light of stellar populations detected primarily by IRAC, to starbursts, ultra-luminous infrared galaxies and AGN detected also by MIPS.\n\n        The SWIRE Lockman Hole ISOCAM Deep Field Catalog presents MIPS 24 micron measurements of the sources detected at 14.3 micron in the Lockman Hole Shallow Survey by ISO. For more details on the Lockman Hole ISOCAM Shallow Survey, see Fadda et al. (2004)."
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_dc/SET_1/json/0a3aab25-d8bf-523c-8811-feb5ec2b962c.json b/oaitestdata/ivoa-oai_dc/SET_1/json/0a3aab25-d8bf-523c-8811-feb5ec2b962c.json
deleted file mode 100644
index 70549f9c..00000000
--- a/oaitestdata/ivoa-oai_dc/SET_1/json/0a3aab25-d8bf-523c-8811-feb5ec2b962c.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "Contact": [
-        "IVOA"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "MetaDataAccess": "http://registry.euro-vo.org/oai.jsp?verb=GetRecord&metadataPrefix=oai_dc&identifier=ivo://ivoa.net/std/ivoadm",
-    "PublicationTimestamp": "2018-12-21T16:18:28Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "IVOA"
-    ],
-    "RelatedIdentifier": [
-        "ivo://ivoa.net/std/ivoadm"
-    ],
-    "ResourceType": [
-        "Other"
-    ],
-    "author": [
-        "Donaldson, T.",
-        "Laurino, O.",
-        "Bourges, L.",
-        "Salgado, J.",
-        "Lemson, G.",
-        "Demleitner, M.",
-        "Dowler, P.",
-        "Graham, M.",
-        "Gray, N.",
-        "Cresitello-Dittmar, M.",
-        "Michel, L."
-    ],
-    "fulltext": "ivo://ivoa.net/std/ivoadm;2018-12-21T16:18:28Z;The ivoa data model;ivo://ivoa.net/std/ivoadm;IVOA;Lemson, G.;Laurino, O.;Bourges, L.;Cresitello-Dittmar, M.;Demleitner, M.;Donaldson, T.;Dowler, P.;Graham, M.;Gray, N.;Michel, L.;Salgado, J.;Virtual observatory;\n        \t\t\tUltimately all types in a VO-DML model are defined as hierarchies \n        \t\t\tof primitive types. This Model defines a special, predefined model \n        \t\t\tthat contains a set of the most common of such types: integer, \n        \t\t\treal, string etc. This\n            ;Other",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0a3aab25-d8bf-523c-8811-feb5ec2b962c",
-    "notes": [
-        "\n        \t\t\tUltimately all types in a VO-DML model are defined as hierarchies \n        \t\t\tof primitive types. This Model defines a special, predefined model \n        \t\t\tthat contains a set of the most common of such types: integer, \n        \t\t\treal, string etc. This\n            "
-    ],
-    "oai_identifier": [
-        "ivo://ivoa.net/std/ivoadm"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Virtual observatory"
-        }
-    ],
-    "title": [
-        "\n        \t\t\tUltimately all types in a VO-DML model are defined as hierarchies \n        \t\t\tof primitive types. This Model defines a special, predefined model \n        \t\t\tthat contains a set of the most common of such types: integer, \n        \t\t\treal, string etc. This\n            "
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_dc/SET_1/json/0a61d58c-197b-5ec2-ad9a-fc7c63bc9d68.json b/oaitestdata/ivoa-oai_dc/SET_1/json/0a61d58c-197b-5ec2-ad9a-fc7c63bc9d68.json
deleted file mode 100644
index 1593770e..00000000
--- a/oaitestdata/ivoa-oai_dc/SET_1/json/0a61d58c-197b-5ec2-ad9a-fc7c63bc9d68.json
+++ /dev/null
@@ -1,43 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "MetaDataAccess": "http://registry.euro-vo.org/oai.jsp?verb=GetRecord&metadataPrefix=oai_dc&identifier=ivo://au.csiro/atoavo/TAP",
-    "PublicationTimestamp": "2018-12-21T20:10:25Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "RelatedIdentifier": [
-        "ivo://au.csiro/atoavo/TAP"
-    ],
-    "author": [
-        "CSIRO"
-    ],
-    "fulltext": "ivo://au.csiro/atoavo/TAP;2018-12-21T20:10:25Z;CSIRO Australia Telescope Online Archive TAP Service;CSIRO;CSIRO;Table Access Protocol service for accessing Australia Telescope Online Archive;ATNF Observations;2016-08-24T12:39:30;ivo://au.csiro/atoavo/TAP",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0a61d58c-197b-5ec2-ad9a-fc7c63bc9d68",
-    "notes": [
-        "Table Access Protocol service for accessing Australia Telescope Online Archive"
-    ],
-    "oai_identifier": [
-        "ivo://au.csiro/atoavo/TAP"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "ATNF Observations"
-        }
-    ],
-    "title": [
-        "Table Access Protocol service for accessing Australia Telescope Online Archive"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_dc/SET_1/json/0a87b87f-a18b-5568-8254-ba8d2566b622.json b/oaitestdata/ivoa-oai_dc/SET_1/json/0a87b87f-a18b-5568-8254-ba8d2566b622.json
deleted file mode 100644
index eff28ca5..00000000
--- a/oaitestdata/ivoa-oai_dc/SET_1/json/0a87b87f-a18b-5568-8254-ba8d2566b622.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Chandra X-ray Observatory"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "MetaDataAccess": "http://registry.euro-vo.org/oai.jsp?verb=GetRecord&metadataPrefix=oai_dc&identifier=ivo://cxc.harvard.edu/cda",
-    "PublicationTimestamp": "2018-12-21T17:37:19Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Chandra X-ray Observatory"
-    ],
-    "RelatedIdentifier": [
-        "ivo://cxc.harvard.edu/cda"
-    ],
-    "ResourceType": [
-        "Archive"
-    ],
-    "author": [
-        "Chandra X-ray Center"
-    ],
-    "fulltext": "ivo://cxc.harvard.edu/cda;2018-12-21T17:37:19Z;Chandra X-ray Observatory Data Archive;ivo://cxc.harvard.edu/cda;Chandra X-ray Observatory;Chandra X-ray Center;X-ray astronomy;galaxies;quasars;stars;X-ray;photometry;spectroscopy;variability;\n        The Chandra X-ray Observatory is the U.S. follow-on to the Einstein\n        Observatory. Chandra was formerly known as AXAF, the Advanced X-ray\n        Astrophysics Facility, but renamed by NASA in December, 1998.\n        Originally three instruments and a high-resolution mirror carried in\n        one spacecraft, the project was reworked in 1992 and 1993. The Chandra\n        spacecraft carries a high resolution mirror, two imaging detectors,\n        and two sets of transmission gratings. Important Chandra features are:\n        an order of magnitude improvement in spatial resolution, good\n        sensitivity from 0.1 to 10 keV, and the capability for high spectral\n        resolution observations over most of this range.\n        ;Archive",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0a87b87f-a18b-5568-8254-ba8d2566b622",
-    "notes": [
-        "\n        The Chandra X-ray Observatory is the U.S. follow-on to the Einstein\n        Observatory. Chandra was formerly known as AXAF, the Advanced X-ray\n        Astrophysics Facility, but renamed by NASA in December, 1998.\n        Originally three instruments and a high-resolution mirror carried in\n        one spacecraft, the project was reworked in 1992 and 1993. The Chandra\n        spacecraft carries a high resolution mirror, two imaging detectors,\n        and two sets of transmission gratings. Important Chandra features are:\n        an order of magnitude improvement in spatial resolution, good\n        sensitivity from 0.1 to 10 keV, and the capability for high spectral\n        resolution observations over most of this range.\n        "
-    ],
-    "oai_identifier": [
-        "ivo://cxc.harvard.edu/cda"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "X-ray astronomy"
-        },
-        {
-            "name": "galaxies"
-        },
-        {
-            "name": "quasars"
-        },
-        {
-            "name": "stars"
-        },
-        {
-            "name": "X-ray"
-        },
-        {
-            "name": "photometry"
-        },
-        {
-            "name": "spectroscopy"
-        },
-        {
-            "name": "variability"
-        }
-    ],
-    "title": [
-        "\n        The Chandra X-ray Observatory is the U.S. follow-on to the Einstein\n        Observatory. Chandra was formerly known as AXAF, the Advanced X-ray\n        Astrophysics Facility, but renamed by NASA in December, 1998.\n        Originally three instruments and a high-resolution mirror carried in\n        one spacecraft, the project was reworked in 1992 and 1993. The Chandra\n        spacecraft carries a high resolution mirror, two imaging detectors,\n        and two sets of transmission gratings. Important Chandra features are:\n        an order of magnitude improvement in spatial resolution, good\n        sensitivity from 0.1 to 10 keV, and the capability for high spectral\n        resolution observations over most of this range.\n        "
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_dc/SET_1/json/0acbe0cf-205e-5838-a05a-8ec32631eafa.json b/oaitestdata/ivoa-oai_dc/SET_1/json/0acbe0cf-205e-5838-a05a-8ec32631eafa.json
deleted file mode 100644
index aa97edc3..00000000
--- a/oaitestdata/ivoa-oai_dc/SET_1/json/0acbe0cf-205e-5838-a05a-8ec32631eafa.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "NASA/IPAC Infrared Science Archive"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "MetaDataAccess": "http://registry.euro-vo.org/oai.jsp?verb=GetRecord&metadataPrefix=oai_dc&identifier=ivo://irsa.ipac/Spitzer/Catalog/GLIMPSE/GLM3DEp1Archive",
-    "PublicationTimestamp": "2016-02-05T15:15:06Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "NASA/IPAC Infrared Science Archive"
-    ],
-    "RelatedIdentifier": [
-        "ivo://irsa.ipac/Spitzer/Catalog/GLIMPSE/GLM3DEp1Archive"
-    ],
-    "ResourceType": [
-        "Catalog"
-    ],
-    "author": [
-        "GLIMPSE team"
-    ],
-    "fulltext": "ivo://irsa.ipac/Spitzer/Catalog/GLIMPSE/GLM3DEp1Archive;2016-02-05T15:15:06Z;GLIMPSE 3D Epoch 1 Archive;ivo://irsa.ipac/Spitzer/Catalog/GLIMPSE/GLM3DEp1Archive;NASA/IPAC Infrared Science Archive;GLIMPSE team;Milky Way disk;GLIMPSE3D is the third in a series of large area projects to map selected regions of the Galactic plane using the Spitzer Space Telescope Infrared Array Camera (IRAC). GLIMPSEI1 covered the Galactic plane from |l| = 10\u00e2\u0097\u00a6 to 65\u00e2\u0097\u00a6 and |b| < 1\u00e2\u0097\u00a6; GLIMPSEII filled in the inner 20 degrees of the Galactic plane, |l| < 10\u00e2\u0097\u00a6, with vertical extensions up to \u00c2\u00b11.5\u00e2\u0097\u00a6 for |l| =5\u00e2\u0097\u00a6to 2\u00e2\u0097\u00a6, and up to \u00c2\u00b12\u00e2\u0097\u00a6 from |l| =2\u00e2\u0097\u00a6to 0\u00e2\u0097\u00a6. GLIMPSE3D adds vertical extensions, generally up to |b| < 3\u00e2\u0097\u00a6, but up to |b| < 4.2\u00e2\u0097\u00a6 in the center of the Galaxy. The goal of this coverage is to provide data to study the vertical stellar and interstellar\n\n        The GLIMPSE3D Archive (GLM3DA or the \u00e2\u0080\u009cArchive\u00e2\u0080\u009d) consists of point sources with a signal- to-noise > 5 in at least one band and less stringent selection critera than the Catalog. The photometric uncertainty is typically < 0.3 mag. The GLIMPSE3D Catalog is a subset of the Archive, but note that the entries for a particular source might not be the same due to additional nulling of magnitudes in the Catalog because of the more stringent requirements.;Catalog",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0acbe0cf-205e-5838-a05a-8ec32631eafa",
-    "notes": [
-        "GLIMPSE3D is the third in a series of large area projects to map selected regions of the Galactic plane using the Spitzer Space Telescope Infrared Array Camera (IRAC). GLIMPSEI1 covered the Galactic plane from |l| = 10\u00e2\u0097\u00a6 to 65\u00e2\u0097\u00a6 and |b| < 1\u00e2\u0097\u00a6; GLIMPSEII filled in the inner 20 degrees of the Galactic plane, |l| < 10\u00e2\u0097\u00a6, with vertical extensions up to \u00c2\u00b11.5\u00e2\u0097\u00a6 for |l| =5\u00e2\u0097\u00a6to 2\u00e2\u0097\u00a6, and up to \u00c2\u00b12\u00e2\u0097\u00a6 from |l| =2\u00e2\u0097\u00a6to 0\u00e2\u0097\u00a6. GLIMPSE3D adds vertical extensions, generally up to |b| < 3\u00e2\u0097\u00a6, but up to |b| < 4.2\u00e2\u0097\u00a6 in the center of the Galaxy. The goal of this coverage is to provide data to study the vertical stellar and interstellar\n\n        The GLIMPSE3D Archive (GLM3DA or the \u00e2\u0080\u009cArchive\u00e2\u0080\u009d) consists of point sources with a signal- to-noise > 5 in at least one band and less stringent selection critera than the Catalog. The photometric uncertainty is typically < 0.3 mag. The GLIMPSE3D Catalog is a subset of the Archive, but note that the entries for a particular source might not be the same due to additional nulling of magnitudes in the Catalog because of the more stringent requirements."
-    ],
-    "oai_identifier": [
-        "ivo://irsa.ipac/Spitzer/Catalog/GLIMPSE/GLM3DEp1Archive"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Milky Way disk"
-        }
-    ],
-    "title": [
-        "GLIMPSE3D is the third in a series of large area projects to map selected regions of the Galactic plane using the Spitzer Space Telescope Infrared Array Camera (IRAC). GLIMPSEI1 covered the Galactic plane from |l| = 10\u00e2\u0097\u00a6 to 65\u00e2\u0097\u00a6 and |b| < 1\u00e2\u0097\u00a6; GLIMPSEII filled in the inner 20 degrees of the Galactic plane, |l| < 10\u00e2\u0097\u00a6, with vertical extensions up to \u00c2\u00b11.5\u00e2\u0097\u00a6 for |l| =5\u00e2\u0097\u00a6to 2\u00e2\u0097\u00a6, and up to \u00c2\u00b12\u00e2\u0097\u00a6 from |l| =2\u00e2\u0097\u00a6to 0\u00e2\u0097\u00a6. GLIMPSE3D adds vertical extensions, generally up to |b| < 3\u00e2\u0097\u00a6, but up to |b| < 4.2\u00e2\u0097\u00a6 in the center of the Galaxy. The goal of this coverage is to provide data to study the vertical stellar and interstellar\n\n        The GLIMPSE3D Archive (GLM3DA or the \u00e2\u0080\u009cArchive\u00e2\u0080\u009d) consists of point sources with a signal- to-noise > 5 in at least one band and less stringent selection critera than the Catalog. The photometric uncertainty is typically < 0.3 mag. The GLIMPSE3D Catalog is a subset of the Archive, but note that the entries for a particular source might not be the same due to additional nulling of magnitudes in the Catalog because of the more stringent requirements."
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_dc/SET_1/json/0af98d4e-15e8-502d-a4e3-0af227aec285.json b/oaitestdata/ivoa-oai_dc/SET_1/json/0af98d4e-15e8-502d-a4e3-0af227aec285.json
deleted file mode 100644
index 628f7adc..00000000
--- a/oaitestdata/ivoa-oai_dc/SET_1/json/0af98d4e-15e8-502d-a4e3-0af227aec285.json
+++ /dev/null
@@ -1,47 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "MetaDataAccess": "http://registry.euro-vo.org/oai.jsp?verb=GetRecord&metadataPrefix=oai_dc&identifier=ivo://uk.ac.le.star.tmpledas/ledas/ledas/crabtime",
-    "PublicationTimestamp": "2018-12-21T17:23:27Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "RelatedIdentifier": [
-        "ivo://uk.ac.le.star.tmpledas/ledas/ledas/crabtime"
-    ],
-    "author": [
-        "LEDAS",
-        "LEDAS, University of Leicester"
-    ],
-    "fulltext": "ivo://uk.ac.le.star.tmpledas/ledas/ledas/crabtime;2018-12-21T17:23:27Z;CRABTIME: Crab Pulsar Timing (LEDAS);LEDAS, University of Leicester;LEDAS;Cone Search service for \n                    CRABTIME: Crab Pulsar Timing (LEDAS)\n                . \n          \t\t\t\t\t\t\n          \t\t\t\t\t\tPart of Catalogues hosted at Leicester Database and Archive Service;LEDAS;crabtime;2011-02-10T22:15:35;ivo://uk.ac.le.star.tmpledas/ledas/ledas/crabtime",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0af98d4e-15e8-502d-a4e3-0af227aec285",
-    "notes": [
-        "Cone Search service for \n                    CRABTIME: Crab Pulsar Timing (LEDAS)\n                . \n          \t\t\t\t\t\t\n          \t\t\t\t\t\tPart of Catalogues hosted at Leicester Database and Archive Service"
-    ],
-    "oai_identifier": [
-        "ivo://uk.ac.le.star.tmpledas/ledas/ledas/crabtime"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "LEDAS"
-        },
-        {
-            "name": "crabtime"
-        }
-    ],
-    "title": [
-        "Cone Search service for \n                    CRABTIME: Crab Pulsar Timing (LEDAS)\n                . \n          \t\t\t\t\t\t\n          \t\t\t\t\t\tPart of Catalogues hosted at Leicester Database and Archive Service"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_dc/SET_1/json/0b10d3a0-1cfe-5e67-8a5c-0949db9d19cb.json b/oaitestdata/ivoa-oai_dc/SET_1/json/0b10d3a0-1cfe-5e67-8a5c-0949db9d19cb.json
deleted file mode 100644
index 8032108d..00000000
--- a/oaitestdata/ivoa-oai_dc/SET_1/json/0b10d3a0-1cfe-5e67-8a5c-0949db9d19cb.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "MetaDataAccess": "http://registry.euro-vo.org/oai.jsp?verb=GetRecord&metadataPrefix=oai_dc&identifier=ivo://wfau.roe.ac.uk/vhsDR6-dsa/ceaApplication",
-    "PublicationTimestamp": "2019-03-23T04:08:10Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "RelatedIdentifier": [
-        "ivo://wfau.roe.ac.uk/vhsDR6-dsa/ceaApplication"
-    ],
-    "author": [
-        "WFAU, Institute for Astronomy, University of Edinburgh"
-    ],
-    "fulltext": "ivo://wfau.roe.ac.uk/vhsDR6-dsa/ceaApplication;2019-03-23T04:08:10Z;VHS DR6 - VISTA Hemisphere Survey Data Release 6;WFAU, Institute for Astronomy, University of Edinburgh;WFAU, Institute for Astronomy, University of Edinburgh;The VHS will image the entire ~20 000 square degrees of the Southern Sky, with the exception of the areas already covered by the VIKING and VVV surveys, in J and Ks. The resulting data will be about 4 magnitudes deeper than 2MASS and DENIS. The 5000 square degrees covered by the Dark Energy Survey (DES), another imaging survey scheduled to begin in 2010 at the CTIO 4 metre Blanco telescope, will also be observed in H-band. The area around both of the Galactic Caps will be observed in Y- and H- band as well to be combined with the data from the VST ATLAS survey. The main science drivers of the VHS include: examining low mass and nearby stars, studying the merger history of the Galaxy, measuring the properties of Dark Energy through the examination of large-scale structure to a redshift of ~1, and searches for high redshift quasars.;Stars,Survey,Galaxy, low mass stars, dark energy;2019-03-20T15:27:39;ivo://wfau.roe.ac.uk/vhsDR6-dsa/ceaApplication",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0b10d3a0-1cfe-5e67-8a5c-0949db9d19cb",
-    "notes": [
-        "The VHS will image the entire ~20 000 square degrees of the Southern Sky, with the exception of the areas already covered by the VIKING and VVV surveys, in J and Ks. The resulting data will be about 4 magnitudes deeper than 2MASS and DENIS. The 5000 square degrees covered by the Dark Energy Survey (DES), another imaging survey scheduled to begin in 2010 at the CTIO 4 metre Blanco telescope, will also be observed in H-band. The area around both of the Galactic Caps will be observed in Y- and H- band as well to be combined with the data from the VST ATLAS survey. The main science drivers of the VHS include: examining low mass and nearby stars, studying the merger history of the Galaxy, measuring the properties of Dark Energy through the examination of large-scale structure to a redshift of ~1, and searches for high redshift quasars."
-    ],
-    "oai_identifier": [
-        "ivo://wfau.roe.ac.uk/vhsDR6-dsa/ceaApplication"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Stars"
-        },
-        {
-            "name": "Survey"
-        },
-        {
-            "name": "Galaxy"
-        },
-        {
-            "name": "low mass stars"
-        },
-        {
-            "name": "dark energy"
-        }
-    ],
-    "title": [
-        "The VHS will image the entire ~20 000 square degrees of the Southern Sky, with the exception of the areas already covered by the VIKING and VVV surveys, in J and Ks. The resulting data will be about 4 magnitudes deeper than 2MASS and DENIS. The 5000 square degrees covered by the Dark Energy Survey (DES), another imaging survey scheduled to begin in 2010 at the CTIO 4 metre Blanco telescope, will also be observed in H-band. The area around both of the Galactic Caps will be observed in Y- and H- band as well to be combined with the data from the VST ATLAS survey. The main science drivers of the VHS include: examining low mass and nearby stars, studying the merger history of the Galaxy, measuring the properties of Dark Energy through the examination of large-scale structure to a redshift of ~1, and searches for high redshift quasars."
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_dc/SET_1/json/0b1473bd-6819-5cb9-9a92-9c1596477d5d.json b/oaitestdata/ivoa-oai_dc/SET_1/json/0b1473bd-6819-5cb9-9a92-9c1596477d5d.json
deleted file mode 100644
index 4e824a29..00000000
--- a/oaitestdata/ivoa-oai_dc/SET_1/json/0b1473bd-6819-5cb9-9a92-9c1596477d5d.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "Space Telescope Science Institute Archive"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "MetaDataAccess": "http://registry.euro-vo.org/oai.jsp?verb=GetRecord&metadataPrefix=oai_dc&identifier=ivo://archive.stsci.edu/hst/acs",
-    "PublicationTimestamp": "2019-05-25T09:52:41Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Space Telescope Science Institute Archive"
-    ],
-    "RelatedIdentifier": [
-        "ivo://archive.stsci.edu/hst/acs"
-    ],
-    "fulltext": "ivo://archive.stsci.edu/hst/acs;2019-05-25T09:52:41Z;Advanced Camera for Surveys;HST Advanced Camera for Surveys (ACS) - Images: CCD images between 3,700 - 11;ivo://archive.stsci.edu/hst/acs;Space Telescope Science Institute Archive;Cosmology,Galaxies,Stars,Nebulae,Planets;2018-12-05T16:25:51Z",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0b1473bd-6819-5cb9-9a92-9c1596477d5d",
-    "notes": [
-        "HST Advanced Camera for Surveys (ACS) - Images: CCD images between 3,700 - 11"
-    ],
-    "oai_identifier": [
-        "ivo://archive.stsci.edu/hst/acs"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Cosmology"
-        },
-        {
-            "name": "Galaxies"
-        },
-        {
-            "name": "Stars"
-        },
-        {
-            "name": "Nebulae"
-        },
-        {
-            "name": "Planets"
-        }
-    ],
-    "title": [
-        "HST Advanced Camera for Surveys (ACS) - Images: CCD images between 3,700 - 11"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_dc/SET_1/json/0b2f91b5-8ae5-55e7-8060-22dc04fad17a.json b/oaitestdata/ivoa-oai_dc/SET_1/json/0b2f91b5-8ae5-55e7-8060-22dc04fad17a.json
deleted file mode 100644
index 14ac62be..00000000
--- a/oaitestdata/ivoa-oai_dc/SET_1/json/0b2f91b5-8ae5-55e7-8060-22dc04fad17a.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "MetaDataAccess": "http://registry.euro-vo.org/oai.jsp?verb=GetRecord&metadataPrefix=oai_dc&identifier=ivo://wfau.roe.ac.uk/vista-siap",
-    "PublicationTimestamp": "2019-07-09T21:21:07Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "RelatedIdentifier": [
-        "ivo://wfau.roe.ac.uk/vista-siap"
-    ],
-    "author": [
-        "WFAU, Institute for Astronomy, University of Edinburgh"
-    ],
-    "fulltext": "ivo://wfau.roe.ac.uk/vista-siap;2019-07-09T21:21:07Z;VISTA SIAP Service;WFAU, Institute for Astronomy, University of Edinburgh;WFAU, Institute for Astronomy, University of Edinburgh;Simple image access to all images from the latest releases of the VISTA public surveys (VHS, VMC, VVV, VIDEO, VIKING).;VISTA, SIAP, Images, VHS, VMC, VVV, VIDEO, VIKING;2019-07-09T15:59:27;ivo://wfau.roe.ac.uk/vista-siap",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0b2f91b5-8ae5-55e7-8060-22dc04fad17a",
-    "notes": [
-        "Simple image access to all images from the latest releases of the VISTA public surveys (VHS, VMC, VVV, VIDEO, VIKING)."
-    ],
-    "oai_identifier": [
-        "ivo://wfau.roe.ac.uk/vista-siap"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "VISTA"
-        },
-        {
-            "name": "SIAP"
-        },
-        {
-            "name": "Images"
-        },
-        {
-            "name": "VHS"
-        },
-        {
-            "name": "VMC"
-        },
-        {
-            "name": "VVV"
-        },
-        {
-            "name": "VIDEO"
-        },
-        {
-            "name": "VIKING"
-        }
-    ],
-    "title": [
-        "Simple image access to all images from the latest releases of the VISTA public surveys (VHS, VMC, VVV, VIDEO, VIKING)."
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_dc/SET_1/json/0b62257c-b7cb-5fdb-9fd3-7100d9f86fb5.json b/oaitestdata/ivoa-oai_dc/SET_1/json/0b62257c-b7cb-5fdb-9fd3-7100d9f86fb5.json
deleted file mode 100644
index 4a2f3776..00000000
--- a/oaitestdata/ivoa-oai_dc/SET_1/json/0b62257c-b7cb-5fdb-9fd3-7100d9f86fb5.json
+++ /dev/null
@@ -1,44 +0,0 @@
-{
-    "Contact": [
-        "The GAVO DC team"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "MetaDataAccess": "http://registry.euro-vo.org/oai.jsp?verb=GetRecord&metadataPrefix=oai_dc&identifier=ivo://edu.euro-vo.org/extern/asterics_herbigstars",
-    "PublicationTimestamp": "2018-12-21T17:01:26Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "The GAVO DC team"
-    ],
-    "RelatedIdentifier": [
-        "ivo://edu.euro-vo.org/extern/asterics_herbigstars"
-    ],
-    "author": [
-        "Baines, D."
-    ],
-    "fulltext": "ivo://edu.euro-vo.org/extern/asterics_herbigstars;2018-12-21T17:01:26Z;Classifying the SEDs of Herbig Ae/Be stars;ivo://edu.euro-vo.org/extern/asterics_herbigstars;Baines, D.; The overall goal of this tutorial is to become familiar with VOSpec.\n        For that, we are going to build the Spectral Energy Distribution (SED)\n        of two Herbig Ae/Be stars, compare them and categorise them as group 1\n        or group 2 Herbig Ae/Be stars.;The GAVO DC team",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0b62257c-b7cb-5fdb-9fd3-7100d9f86fb5",
-    "notes": [
-        " The overall goal of this tutorial is to become familiar with VOSpec.\n        For that, we are going to build the Spectral Energy Distribution (SED)\n        of two Herbig Ae/Be stars, compare them and categorise them as group 1\n        or group 2 Herbig Ae/Be stars."
-    ],
-    "oai_identifier": [
-        "ivo://edu.euro-vo.org/extern/asterics_herbigstars"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "title": [
-        " The overall goal of this tutorial is to become familiar with VOSpec.\n        For that, we are going to build the Spectral Energy Distribution (SED)\n        of two Herbig Ae/Be stars, compare them and categorise them as group 1\n        or group 2 Herbig Ae/Be stars."
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_dc/SET_1/json/0b73bf55-92c2-563e-8929-e9098a5da80b.json b/oaitestdata/ivoa-oai_dc/SET_1/json/0b73bf55-92c2-563e-8929-e9098a5da80b.json
deleted file mode 100644
index 87d57e0b..00000000
--- a/oaitestdata/ivoa-oai_dc/SET_1/json/0b73bf55-92c2-563e-8929-e9098a5da80b.json
+++ /dev/null
@@ -1,41 +0,0 @@
-{
-    "Contact": [
-        "Paris Astronomical Data Centre - LESIA"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "MetaDataAccess": "http://registry.euro-vo.org/oai.jsp?verb=GetRecord&metadataPrefix=oai_dc&identifier=ivo://vopdc.obspm/lesia/hfc1ar/epn",
-    "PublicationTimestamp": "2018-12-21T19:59:55Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Paris Astronomical Data Centre - LESIA"
-    ],
-    "RelatedIdentifier": [
-        "ivo://vopdc.obspm/lesia/hfc1ar/epn"
-    ],
-    "fulltext": "ivo://vopdc.obspm/lesia/hfc1ar/epn;2018-12-21T19:59:55Z;Heliophysics Feature Catalog active regions;ivo://vopdc.obspm/lesia/hfc1ar/epn;2017-01-10T00:00:00Z;Paris Astronomical Data Centre - LESIA;Solar active regions extracted from Heliophysics Feature Catalog.",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0b73bf55-92c2-563e-8929-e9098a5da80b",
-    "notes": [
-        "Solar active regions extracted from Heliophysics Feature Catalog."
-    ],
-    "oai_identifier": [
-        "ivo://vopdc.obspm/lesia/hfc1ar/epn"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "title": [
-        "Solar active regions extracted from Heliophysics Feature Catalog."
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_dc/SET_1/json/0b81f76e-22ce-594b-8777-6d1decd16e9c.json b/oaitestdata/ivoa-oai_dc/SET_1/json/0b81f76e-22ce-594b-8777-6d1decd16e9c.json
deleted file mode 100644
index b5f9bc5f..00000000
--- a/oaitestdata/ivoa-oai_dc/SET_1/json/0b81f76e-22ce-594b-8777-6d1decd16e9c.json
+++ /dev/null
@@ -1,47 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "MetaDataAccess": "http://registry.euro-vo.org/oai.jsp?verb=GetRecord&metadataPrefix=oai_dc&identifier=ivo://uk.ac.le.star.tmpledas/ledas/ledas/sdssquasar",
-    "PublicationTimestamp": "2018-12-21T17:23:33Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "RelatedIdentifier": [
-        "ivo://uk.ac.le.star.tmpledas/ledas/ledas/sdssquasar"
-    ],
-    "author": [
-        "LEDAS",
-        "LEDAS, University of Leicester"
-    ],
-    "fulltext": "ivo://uk.ac.le.star.tmpledas/ledas/ledas/sdssquasar;2018-12-21T17:23:33Z;SDSSQUASAR: Sloan Digital Sky Survey Quasar Catalog (5th Data Release) (LEDAS);LEDAS, University of Leicester;LEDAS;Cone Search service for \n                    SDSSQUASAR: Sloan Digital Sky Survey Quasar Catalog (5th Data Release) (LEDAS)\n                . \n          \t\t\t\t\t\t\n          \t\t\t\t\t\tPart of Catalogues hosted at Leicester Database and Archive Service;LEDAS;sdssquasar;2011-02-10T22:17:03;ivo://uk.ac.le.star.tmpledas/ledas/ledas/sdssquasar",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0b81f76e-22ce-594b-8777-6d1decd16e9c",
-    "notes": [
-        "Cone Search service for \n                    SDSSQUASAR: Sloan Digital Sky Survey Quasar Catalog (5th Data Release) (LEDAS)\n                . \n          \t\t\t\t\t\t\n          \t\t\t\t\t\tPart of Catalogues hosted at Leicester Database and Archive Service"
-    ],
-    "oai_identifier": [
-        "ivo://uk.ac.le.star.tmpledas/ledas/ledas/sdssquasar"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "LEDAS"
-        },
-        {
-            "name": "sdssquasar"
-        }
-    ],
-    "title": [
-        "Cone Search service for \n                    SDSSQUASAR: Sloan Digital Sky Survey Quasar Catalog (5th Data Release) (LEDAS)\n                . \n          \t\t\t\t\t\t\n          \t\t\t\t\t\tPart of Catalogues hosted at Leicester Database and Archive Service"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_dc/SET_1/json/0ba165dd-bca1-5182-a71b-53ac3dad831b.json b/oaitestdata/ivoa-oai_dc/SET_1/json/0ba165dd-bca1-5182-a71b-53ac3dad831b.json
deleted file mode 100644
index c688d65c..00000000
--- a/oaitestdata/ivoa-oai_dc/SET_1/json/0ba165dd-bca1-5182-a71b-53ac3dad831b.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "MetaDataAccess": "http://registry.euro-vo.org/oai.jsp?verb=GetRecord&metadataPrefix=oai_dc&identifier=ivo://cadc.nrc.ca/siap/jcmt",
-    "PublicationTimestamp": "2016-02-05T16:34:28Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "RelatedIdentifier": [
-        "ivo://cadc.nrc.ca/siap/jcmt"
-    ],
-    "author": [
-        "                     Canadian Astronomy Data Centre            "
-    ],
-    "fulltext": "ivo://cadc.nrc.ca/siap/jcmt;2016-02-05T16:34:28Z;CADC/JCMT Image Search;                     Canadian Astronomy Data Centre            ;Image search and retrieval of JCMT images. The collection e currently       contains SCUBA products at 450 and 850um.;2014-02-04T15:57:45;ivo://cadc.nrc.ca/siap/jcmt",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0ba165dd-bca1-5182-a71b-53ac3dad831b",
-    "notes": [
-        "Image search and retrieval of JCMT images. The collection e currently       contains SCUBA products at 450 and 850um."
-    ],
-    "oai_identifier": [
-        "ivo://cadc.nrc.ca/siap/jcmt"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "title": [
-        "Image search and retrieval of JCMT images. The collection e currently       contains SCUBA products at 450 and 850um."
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_dc/SET_1/json/0bbcb053-4f3b-5a8d-8c99-9fd937262da1.json b/oaitestdata/ivoa-oai_dc/SET_1/json/0bbcb053-4f3b-5a8d-8c99-9fd937262da1.json
deleted file mode 100644
index fae2b3ab..00000000
--- a/oaitestdata/ivoa-oai_dc/SET_1/json/0bbcb053-4f3b-5a8d-8c99-9fd937262da1.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "NASA/IPAC Infrared Science Archive"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "MetaDataAccess": "http://registry.euro-vo.org/oai.jsp?verb=GetRecord&metadataPrefix=oai_dc&identifier=ivo://irsa.ipac/Spitzer/Catalog/FLS/XFLS-Hectospec",
-    "PublicationTimestamp": "2016-02-05T15:15:05Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "NASA/IPAC Infrared Science Archive"
-    ],
-    "RelatedIdentifier": [
-        "ivo://irsa.ipac/Spitzer/Catalog/FLS/XFLS-Hectospec"
-    ],
-    "ResourceType": [
-        "Catalog"
-    ],
-    "author": [
-        "FLS team"
-    ],
-    "fulltext": "ivo://irsa.ipac/Spitzer/Catalog/FLS/XFLS-Hectospec;2016-02-05T15:15:05Z;Spitzer Extragalactic First Look Survey MMT/Hectospec Spectroscopic Catalog;ivo://irsa.ipac/Spitzer/Catalog/FLS/XFLS-Hectospec;NASA/IPAC Infrared Science Archive;FLS team;extragalactic survey;The Extragalactic First Look Survey is composed of 4 square degrees of imaging with MIPS and IRAC centered at J1718+5930, with extensive ancillary data from ground-based optical and radio telescopes. As one of the first observations made with Spitzer after the completion of Science Verification at the end of 2003 November, the aim of this 67 hr survey was to characterize the extragalactic source populations observed with Spitzer down to sub-millijansky levels in the mid-infrared. \n\n        This catalog allows advanced queries of the MMT/Hectospec ancillary spectra described in Papovich et al. (2006).;Catalog",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0bbcb053-4f3b-5a8d-8c99-9fd937262da1",
-    "notes": [
-        "The Extragalactic First Look Survey is composed of 4 square degrees of imaging with MIPS and IRAC centered at J1718+5930, with extensive ancillary data from ground-based optical and radio telescopes. As one of the first observations made with Spitzer after the completion of Science Verification at the end of 2003 November, the aim of this 67 hr survey was to characterize the extragalactic source populations observed with Spitzer down to sub-millijansky levels in the mid-infrared. \n\n        This catalog allows advanced queries of the MMT/Hectospec ancillary spectra described in Papovich et al. (2006)."
-    ],
-    "oai_identifier": [
-        "ivo://irsa.ipac/Spitzer/Catalog/FLS/XFLS-Hectospec"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "extragalactic survey"
-        }
-    ],
-    "title": [
-        "The Extragalactic First Look Survey is composed of 4 square degrees of imaging with MIPS and IRAC centered at J1718+5930, with extensive ancillary data from ground-based optical and radio telescopes. As one of the first observations made with Spitzer after the completion of Science Verification at the end of 2003 November, the aim of this 67 hr survey was to characterize the extragalactic source populations observed with Spitzer down to sub-millijansky levels in the mid-infrared. \n\n        This catalog allows advanced queries of the MMT/Hectospec ancillary spectra described in Papovich et al. (2006)."
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_dc/SET_1/json/0bd28dee-50e3-5fd2-9001-024f160d7799.json b/oaitestdata/ivoa-oai_dc/SET_1/json/0bd28dee-50e3-5fd2-9001-024f160d7799.json
deleted file mode 100644
index 54423a49..00000000
--- a/oaitestdata/ivoa-oai_dc/SET_1/json/0bd28dee-50e3-5fd2-9001-024f160d7799.json
+++ /dev/null
@@ -1,47 +0,0 @@
-{
-    "Contact": [
-        "The GAVO DC team"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "MetaDataAccess": "http://registry.euro-vo.org/oai.jsp?verb=GetRecord&metadataPrefix=oai_dc&identifier=ivo://org.gavo.dc/bgds/q/sia",
-    "PublicationTimestamp": "2018-12-21T17:01:29Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "The GAVO DC team"
-    ],
-    "RelatedIdentifier": [
-        "ivo://org.gavo.dc/bgds/q/sia"
-    ],
-    "author": [
-        "Chini, R.",
-        "Hackstein, M.",
-        "Haas, M.",
-        "Fein, C."
-    ],
-    "fulltext": "ivo://org.gavo.dc/bgds/q/sia;2018-12-21T17:01:29Z;Bochum Galactic Disk Survey (BGDS) SIAP service;ivo://org.gavo.dc/bgds/q/sia;Hackstein, M.;Haas, M.;Fein, C.;Chini, R.; The Bochum Galactic Disk Survey is an ongoing project to monitor the\n        stellar content of the Galactic disk in a 6 degree wide stripe\n        centered on the Galactic plane. The data has been recorded since\n        mid-2010 in Sloan r and i simultaneously with the RoBoTT Telecsope at\n        the Universitaetssternwarte Bochum near Cerro Armazones in the Chilean\n        Atacama desert. It contains measurements of about 2x10^7 stars over\n        more than seven years. Additionally, intermittent measurements in\n        Johnson UVB and Sloan z have been recorded as well.;The GAVO DC team",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0bd28dee-50e3-5fd2-9001-024f160d7799",
-    "notes": [
-        " The Bochum Galactic Disk Survey is an ongoing project to monitor the\n        stellar content of the Galactic disk in a 6 degree wide stripe\n        centered on the Galactic plane. The data has been recorded since\n        mid-2010 in Sloan r and i simultaneously with the RoBoTT Telecsope at\n        the Universitaetssternwarte Bochum near Cerro Armazones in the Chilean\n        Atacama desert. It contains measurements of about 2x10^7 stars over\n        more than seven years. Additionally, intermittent measurements in\n        Johnson UVB and Sloan z have been recorded as well."
-    ],
-    "oai_identifier": [
-        "ivo://org.gavo.dc/bgds/q/sia"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "title": [
-        " The Bochum Galactic Disk Survey is an ongoing project to monitor the\n        stellar content of the Galactic disk in a 6 degree wide stripe\n        centered on the Galactic plane. The data has been recorded since\n        mid-2010 in Sloan r and i simultaneously with the RoBoTT Telecsope at\n        the Universitaetssternwarte Bochum near Cerro Armazones in the Chilean\n        Atacama desert. It contains measurements of about 2x10^7 stars over\n        more than seven years. Additionally, intermittent measurements in\n        Johnson UVB and Sloan z have been recorded as well."
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_dc/SET_1/json/0bd30323-e611-5635-8e47-96b37a9017f9.json b/oaitestdata/ivoa-oai_dc/SET_1/json/0bd30323-e611-5635-8e47-96b37a9017f9.json
deleted file mode 100644
index e5f96937..00000000
--- a/oaitestdata/ivoa-oai_dc/SET_1/json/0bd30323-e611-5635-8e47-96b37a9017f9.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Contact": [
-        "Space Telescope Science Institute Archive"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "MetaDataAccess": "http://registry.euro-vo.org/oai.jsp?verb=GetRecord&metadataPrefix=oai_dc&identifier=ivo://mast.stsci/siap/uit",
-    "PublicationTimestamp": "2019-05-25T09:52:42Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Space Telescope Science Institute Archive"
-    ],
-    "RelatedIdentifier": [
-        "ivo://mast.stsci/siap/uit"
-    ],
-    "fulltext": "ivo://mast.stsci/siap/uit;2019-05-25T09:52:42Z;Ultraviolet Imaging Telescope (UIT);The Ultraviolet Imaging Telescope UIT was one of three ultraviolet telescopes on the ASTRO-1 mission flown on the space shuttle Columbia during 2-10 December 1990. The same three instruments were later flown on the space shuttle Endeavour from 3-17 March 1995, as part of the ASTRO-2 mission. Exposures were obtained on 70-mm photographic film in the 1200-3300 \u00c3\u0085 range using broadband filters and later digitized using a Perkin-Elmer microdensitometer. Image resolution was 3\" over a 40' field of view. Overall, UIT-1 obtained 821 exposures of 66 targets, and UIT-2 obtained 758 images of 193 targets.;ivo://mast.stsci/siap/uit;Space Telescope Science Institute Archive;UV Astronomy;2017-04-17T15:27:52Z",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0bd30323-e611-5635-8e47-96b37a9017f9",
-    "notes": [
-        "The Ultraviolet Imaging Telescope UIT was one of three ultraviolet telescopes on the ASTRO-1 mission flown on the space shuttle Columbia during 2-10 December 1990. The same three instruments were later flown on the space shuttle Endeavour from 3-17 March 1995, as part of the ASTRO-2 mission. Exposures were obtained on 70-mm photographic film in the 1200-3300 \u00c3\u0085 range using broadband filters and later digitized using a Perkin-Elmer microdensitometer. Image resolution was 3\" over a 40' field of view. Overall, UIT-1 obtained 821 exposures of 66 targets, and UIT-2 obtained 758 images of 193 targets."
-    ],
-    "oai_identifier": [
-        "ivo://mast.stsci/siap/uit"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "UV Astronomy"
-        }
-    ],
-    "title": [
-        "The Ultraviolet Imaging Telescope UIT was one of three ultraviolet telescopes on the ASTRO-1 mission flown on the space shuttle Columbia during 2-10 December 1990. The same three instruments were later flown on the space shuttle Endeavour from 3-17 March 1995, as part of the ASTRO-2 mission. Exposures were obtained on 70-mm photographic film in the 1200-3300 \u00c3\u0085 range using broadband filters and later digitized using a Perkin-Elmer microdensitometer. Image resolution was 3\" over a 40' field of view. Overall, UIT-1 obtained 821 exposures of 66 targets, and UIT-2 obtained 758 images of 193 targets."
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_dc/SET_1/json/0bdc9ea1-e701-5f6d-908b-2113cd9fa6bd.json b/oaitestdata/ivoa-oai_dc/SET_1/json/0bdc9ea1-e701-5f6d-908b-2113cd9fa6bd.json
deleted file mode 100644
index b9cfa541..00000000
--- a/oaitestdata/ivoa-oai_dc/SET_1/json/0bdc9ea1-e701-5f6d-908b-2113cd9fa6bd.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "NASA/IPAC Infrared Science Archive"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "MetaDataAccess": "http://registry.euro-vo.org/oai.jsp?verb=GetRecord&metadataPrefix=oai_dc&identifier=ivo://irsa.ipac/Bolocam_GPS/Catalog/BGPSv2.1",
-    "PublicationTimestamp": "2016-07-23T23:21:14Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "NASA/IPAC Infrared Science Archive"
-    ],
-    "RelatedIdentifier": [
-        "ivo://irsa.ipac/Bolocam_GPS/Catalog/BGPSv2.1"
-    ],
-    "ResourceType": [
-        "Catalog"
-    ],
-    "author": [
-        "Bolocam GPS team"
-    ],
-    "fulltext": "ivo://irsa.ipac/Bolocam_GPS/Catalog/BGPSv2.1;2016-07-23T23:21:14Z;Bolocam Galactic Plane Survey Catalog v2.1;ivo://irsa.ipac/Bolocam_GPS/Catalog/BGPSv2.1;NASA/IPAC Infrared Science Archive;Bolocam GPS team;galactic plane survey;The Version 2 release (hereafter v2) of the BGPS data includes images and a catalog. It is described in Ginsburg et al (2013).\n\n        The new images have improved fidelity and more uniform noise. The fields include all those in the original v1 release and some new data. There are new fields included in the BGPS v2 release, primarily in the outer galaxy but including some expansions in the inner galaxy. These include M17, IRAS 22172, a significant expansion in l and b around the l=110 region, Mon R2, NGC 2264, parts of the Orion A and B clouds, Sharpless 235, and scattered IRAS+CO selected fields at longitude 119, 123, 126, 129, 154, 169, 181, 182, 195, 201, and 217. IRSA provides a coverage map.\n\n        There is a new catalog associated with the v2 images. The sources were extracted using Bolocat with parameters set in the same way as for the v1 catalog. There are many sources in v1 that are not in v2 and vice-versa. These discrepancies occur primarily for faint sources with low signal-to-noise. Objects in both catalogs are likely to be real since catalog parameters were selected to minimize false positives. Changing the quality of the images and the structure of the noise highlights some new objects and obscures others. The v2 catalog has about a 75% overlap with the v1 catalog. The differences are explored in more detail in the Ginsburg et al (2013).\n\n        The flux calibration offset identified in the version 1 data is now understood. The version 2 data are brighter, on average, by approximately a factor 1.5, but the factor varies from source to source. The v2 catalog should be used instead of the v1 catalog. The source of the error was the incorrect application of a flux calibration solution.\n\n        Contreras et al (2013) noted a 4.7 arcsecond offset between the BGPS v1 catalog and the ATLASGAL catalog. We believe this is caused by an offset of that magnitude (~3-4 arcseconds) in a few fields that have an inordinate number of sources extracted; the pointing accuracy in the vast majority of the BGPS fields, based on a comparison to Herschel Hi-Gal images, is better than 4 arcseconds, but the mean offset is within 2 arcseconds of zero.;Catalog",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0bdc9ea1-e701-5f6d-908b-2113cd9fa6bd",
-    "notes": [
-        "The Version 2 release (hereafter v2) of the BGPS data includes images and a catalog. It is described in Ginsburg et al (2013).\n\n        The new images have improved fidelity and more uniform noise. The fields include all those in the original v1 release and some new data. There are new fields included in the BGPS v2 release, primarily in the outer galaxy but including some expansions in the inner galaxy. These include M17, IRAS 22172, a significant expansion in l and b around the l=110 region, Mon R2, NGC 2264, parts of the Orion A and B clouds, Sharpless 235, and scattered IRAS+CO selected fields at longitude 119, 123, 126, 129, 154, 169, 181, 182, 195, 201, and 217. IRSA provides a coverage map.\n\n        There is a new catalog associated with the v2 images. The sources were extracted using Bolocat with parameters set in the same way as for the v1 catalog. There are many sources in v1 that are not in v2 and vice-versa. These discrepancies occur primarily for faint sources with low signal-to-noise. Objects in both catalogs are likely to be real since catalog parameters were selected to minimize false positives. Changing the quality of the images and the structure of the noise highlights some new objects and obscures others. The v2 catalog has about a 75% overlap with the v1 catalog. The differences are explored in more detail in the Ginsburg et al (2013).\n\n        The flux calibration offset identified in the version 1 data is now understood. The version 2 data are brighter, on average, by approximately a factor 1.5, but the factor varies from source to source. The v2 catalog should be used instead of the v1 catalog. The source of the error was the incorrect application of a flux calibration solution.\n\n        Contreras et al (2013) noted a 4.7 arcsecond offset between the BGPS v1 catalog and the ATLASGAL catalog. We believe this is caused by an offset of that magnitude (~3-4 arcseconds) in a few fields that have an inordinate number of sources extracted; the pointing accuracy in the vast majority of the BGPS fields, based on a comparison to Herschel Hi-Gal images, is better than 4 arcseconds, but the mean offset is within 2 arcseconds of zero."
-    ],
-    "oai_identifier": [
-        "ivo://irsa.ipac/Bolocam_GPS/Catalog/BGPSv2.1"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "galactic plane survey"
-        }
-    ],
-    "title": [
-        "The Version 2 release (hereafter v2) of the BGPS data includes images and a catalog. It is described in Ginsburg et al (2013).\n\n        The new images have improved fidelity and more uniform noise. The fields include all those in the original v1 release and some new data. There are new fields included in the BGPS v2 release, primarily in the outer galaxy but including some expansions in the inner galaxy. These include M17, IRAS 22172, a significant expansion in l and b around the l=110 region, Mon R2, NGC 2264, parts of the Orion A and B clouds, Sharpless 235, and scattered IRAS+CO selected fields at longitude 119, 123, 126, 129, 154, 169, 181, 182, 195, 201, and 217. IRSA provides a coverage map.\n\n        There is a new catalog associated with the v2 images. The sources were extracted using Bolocat with parameters set in the same way as for the v1 catalog. There are many sources in v1 that are not in v2 and vice-versa. These discrepancies occur primarily for faint sources with low signal-to-noise. Objects in both catalogs are likely to be real since catalog parameters were selected to minimize false positives. Changing the quality of the images and the structure of the noise highlights some new objects and obscures others. The v2 catalog has about a 75% overlap with the v1 catalog. The differences are explored in more detail in the Ginsburg et al (2013).\n\n        The flux calibration offset identified in the version 1 data is now understood. The version 2 data are brighter, on average, by approximately a factor 1.5, but the factor varies from source to source. The v2 catalog should be used instead of the v1 catalog. The source of the error was the incorrect application of a flux calibration solution.\n\n        Contreras et al (2013) noted a 4.7 arcsecond offset between the BGPS v1 catalog and the ATLASGAL catalog. We believe this is caused by an offset of that magnitude (~3-4 arcseconds) in a few fields that have an inordinate number of sources extracted; the pointing accuracy in the vast majority of the BGPS fields, based on a comparison to Herschel Hi-Gal images, is better than 4 arcseconds, but the mean offset is within 2 arcseconds of zero."
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_dc/SET_1/json/0be6e979-7f9b-5b81-8ef9-1eee2e601c28.json b/oaitestdata/ivoa-oai_dc/SET_1/json/0be6e979-7f9b-5b81-8ef9-1eee2e601c28.json
deleted file mode 100644
index 3f34c581..00000000
--- a/oaitestdata/ivoa-oai_dc/SET_1/json/0be6e979-7f9b-5b81-8ef9-1eee2e601c28.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "The NASA/IPAC Extragalactic Database"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "MetaDataAccess": "http://registry.euro-vo.org/oai.jsp?verb=GetRecord&metadataPrefix=oai_dc&identifier=ivo://ned.ipac/SIA",
-    "PublicationTimestamp": "2019-09-11T23:12:17Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The NASA/IPAC Extragalactic Database"
-    ],
-    "RelatedIdentifier": [
-        "ivo://ned.ipac/SIA"
-    ],
-    "fulltext": "ivo://ned.ipac/SIA;2019-09-11T23:12:17Z;The NASA/IPAC Extragalactic Database Image Data Atlas;NED service to search for Images by Object Name or by position and radius, or refcode: The NASA/IPAC Extragalactic Database (NED) provides a comprehensive fusion of multi-wavelength data for hundreds of millions of objects located beyond the Milky Way galaxy. This service retrieves images for a named object. FITS images across the electromagnetic spectrum have been collected from large surveys, compilations, and the literature. Many original images are contributed by authors of journal articles. FITS images archived in NED are queried by celestial coordinates and areal coverage or refcode.;ivo://ned.ipac/SIA;The NASA/IPAC Extragalactic Database;EXTRAGALACTIC OBJECTS,EXTRAGALACTIC RADIO SOURCES,GALAXIES,QUASARS;2019-09-11T19:35:43Z",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0be6e979-7f9b-5b81-8ef9-1eee2e601c28",
-    "notes": [
-        "NED service to search for Images by Object Name or by position and radius, or refcode: The NASA/IPAC Extragalactic Database (NED) provides a comprehensive fusion of multi-wavelength data for hundreds of millions of objects located beyond the Milky Way galaxy. This service retrieves images for a named object. FITS images across the electromagnetic spectrum have been collected from large surveys, compilations, and the literature. Many original images are contributed by authors of journal articles. FITS images archived in NED are queried by celestial coordinates and areal coverage or refcode."
-    ],
-    "oai_identifier": [
-        "ivo://ned.ipac/SIA"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "EXTRAGALACTIC OBJECTS"
-        },
-        {
-            "name": "EXTRAGALACTIC RADIO SOURCES"
-        },
-        {
-            "name": "GALAXIES"
-        },
-        {
-            "name": "QUASARS"
-        }
-    ],
-    "title": [
-        "NED service to search for Images by Object Name or by position and radius, or refcode: The NASA/IPAC Extragalactic Database (NED) provides a comprehensive fusion of multi-wavelength data for hundreds of millions of objects located beyond the Milky Way galaxy. This service retrieves images for a named object. FITS images across the electromagnetic spectrum have been collected from large surveys, compilations, and the literature. Many original images are contributed by authors of journal articles. FITS images archived in NED are queried by celestial coordinates and areal coverage or refcode."
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_dc/SET_1/json/0c4d3887-8ae3-5d87-b6ee-04cd644210f1.json b/oaitestdata/ivoa-oai_dc/SET_1/json/0c4d3887-8ae3-5d87-b6ee-04cd644210f1.json
deleted file mode 100644
index d29696a6..00000000
--- a/oaitestdata/ivoa-oai_dc/SET_1/json/0c4d3887-8ae3-5d87-b6ee-04cd644210f1.json
+++ /dev/null
@@ -1,47 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "MetaDataAccess": "http://registry.euro-vo.org/oai.jsp?verb=GetRecord&metadataPrefix=oai_dc&identifier=ivo://uk.ac.le.star.tmpledas/ledas/ledas/smmgrs",
-    "PublicationTimestamp": "2018-12-21T17:23:34Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "RelatedIdentifier": [
-        "ivo://uk.ac.le.star.tmpledas/ledas/ledas/smmgrs"
-    ],
-    "author": [
-        "LEDAS",
-        "LEDAS, University of Leicester"
-    ],
-    "fulltext": "ivo://uk.ac.le.star.tmpledas/ledas/ledas/smmgrs;2018-12-21T17:23:34Z;SMMGRS: GRS Gamma-Ray Bursts (LEDAS);LEDAS, University of Leicester;LEDAS;Cone Search service for \n                    SMMGRS: GRS Gamma-Ray Bursts (LEDAS)\n                . \n          \t\t\t\t\t\t\n          \t\t\t\t\t\tPart of Catalogues hosted at Leicester Database and Archive Service;LEDAS;smmgrs;2011-02-10T22:17:06;ivo://uk.ac.le.star.tmpledas/ledas/ledas/smmgrs",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0c4d3887-8ae3-5d87-b6ee-04cd644210f1",
-    "notes": [
-        "Cone Search service for \n                    SMMGRS: GRS Gamma-Ray Bursts (LEDAS)\n                . \n          \t\t\t\t\t\t\n          \t\t\t\t\t\tPart of Catalogues hosted at Leicester Database and Archive Service"
-    ],
-    "oai_identifier": [
-        "ivo://uk.ac.le.star.tmpledas/ledas/ledas/smmgrs"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "LEDAS"
-        },
-        {
-            "name": "smmgrs"
-        }
-    ],
-    "title": [
-        "Cone Search service for \n                    SMMGRS: GRS Gamma-Ray Bursts (LEDAS)\n                . \n          \t\t\t\t\t\t\n          \t\t\t\t\t\tPart of Catalogues hosted at Leicester Database and Archive Service"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_dc/SET_1/json/0c73947a-d056-5b13-bf15-91c5509feb1e.json b/oaitestdata/ivoa-oai_dc/SET_1/json/0c73947a-d056-5b13-bf15-91c5509feb1e.json
deleted file mode 100644
index d422f95a..00000000
--- a/oaitestdata/ivoa-oai_dc/SET_1/json/0c73947a-d056-5b13-bf15-91c5509feb1e.json
+++ /dev/null
@@ -1,47 +0,0 @@
-{
-    "Contact": [
-        "The staff at the VO HPSL datacenter"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "MetaDataAccess": "http://registry.euro-vo.org/oai.jsp?verb=GetRecord&metadataPrefix=oai_dc&identifier=ivo://src.pas/__system__/services/registry",
-    "PublicationTimestamp": "2018-12-21T17:32:50Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "The staff at the VO HPSL datacenter"
-    ],
-    "RelatedIdentifier": [
-        "ivo://src.pas/__system__/services/registry"
-    ],
-    "Rights": [
-        "public"
-    ],
-    "author": [
-        "Lukasz Tomasik"
-    ],
-    "fulltext": "ivo://src.pas/__system__/services/registry;2018-12-21T17:32:50Z;VO HPSL datacenter Registry;ivo://src.pas/__system__/services/registry;Lukasz Tomasik; The publishing registry for the VO HPSL datacenter.;public;The staff at the VO HPSL datacenter",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0c73947a-d056-5b13-bf15-91c5509feb1e",
-    "notes": [
-        " The publishing registry for the VO HPSL datacenter."
-    ],
-    "oai_identifier": [
-        "ivo://src.pas/__system__/services/registry"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "title": [
-        " The publishing registry for the VO HPSL datacenter."
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_dc/SET_1/json/0c75feee-4a27-5040-92c6-e718f8513ff8.json b/oaitestdata/ivoa-oai_dc/SET_1/json/0c75feee-4a27-5040-92c6-e718f8513ff8.json
deleted file mode 100644
index 2690cec7..00000000
--- a/oaitestdata/ivoa-oai_dc/SET_1/json/0c75feee-4a27-5040-92c6-e718f8513ff8.json
+++ /dev/null
@@ -1,54 +0,0 @@
-{
-    "Contact": [
-        "IA2"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "MetaDataAccess": "http://registry.euro-vo.org/oai.jsp?verb=GetRecord&metadataPrefix=oai_dc&identifier=ivo://ia2.inaf.it/edu/inaf_oats/svas/C14/siap",
-    "PublicationTimestamp": "2016-02-05T14:51:01Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "IA2"
-    ],
-    "RelatedIdentifier": [
-        "ivo://ia2.inaf.it/edu/inaf_oats/svas/C14/siap"
-    ],
-    "ResourceType": [
-        "Education"
-    ],
-    "author": [
-        "IA2"
-    ],
-    "fulltext": "ivo://ia2.inaf.it/edu/inaf_oats/svas/C14/siap;2016-02-05T14:51:01Z;ivo_managed;INAF-OATs SVAS Educational Images SIAP service;IA2;educational galaxies stars planets;INAF-OATs SVAS Educational Images SIAP service. Le Stelle Vanno A Scuola (SVAS) proposes a modern tool to support teaching of astronomy, through the study and experimentation of its observation methods. SVAS offers to schools and teachers a remote laboratory with which carry out real observation sessions, managed in real time by the students under the supervision of the teacher, in the classroom, and of an astronomer, at the OATs, thanks to the telematic link between the school and the observatory. Students and teachers experience real astronomical observations, through the interactive participation to the different steps of planning, observing and acquiring the data. The project is addressed to 13-18 yr students. Every observation is previously planned together with the teachers, according to age and curriculum of the students, with the aim to maximize the results. The observing activity, lasting about 90 minutes and led by an astronomer of the OATs, can be done during the morning (observation of the Sun) or in the evening (observation of stars, nebulae, clusters and galaxies). SVAS involves the Astronomical Observatory of Trieste (OATs), the school (of every level) and the University of Trieste. SVAS is supported by the Consorzio per l\u00e2\u0080\u0099Incremento degli Studi e delle Ricerche dei Dipartimenti di Fisica e Astronomia dell\u00e2\u0080\u0099Universit\u00c3\u00a0 di Trieste and by the Ministero dell'Istruzione, dell'Universit\u00c3\u00a0 e della Ricerca.;IA2;Education;ivo://ia2.inaf.it/edu/inaf_oats/svas/C14/siap",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0c75feee-4a27-5040-92c6-e718f8513ff8",
-    "notes": [
-        "INAF-OATs SVAS Educational Images SIAP service. Le Stelle Vanno A Scuola (SVAS) proposes a modern tool to support teaching of astronomy, through the study and experimentation of its observation methods. SVAS offers to schools and teachers a remote laboratory with which carry out real observation sessions, managed in real time by the students under the supervision of the teacher, in the classroom, and of an astronomer, at the OATs, thanks to the telematic link between the school and the observatory. Students and teachers experience real astronomical observations, through the interactive participation to the different steps of planning, observing and acquiring the data. The project is addressed to 13-18 yr students. Every observation is previously planned together with the teachers, according to age and curriculum of the students, with the aim to maximize the results. The observing activity, lasting about 90 minutes and led by an astronomer of the OATs, can be done during the morning (observation of the Sun) or in the evening (observation of stars, nebulae, clusters and galaxies). SVAS involves the Astronomical Observatory of Trieste (OATs), the school (of every level) and the University of Trieste. SVAS is supported by the Consorzio per l\u00e2\u0080\u0099Incremento degli Studi e delle Ricerche dei Dipartimenti di Fisica e Astronomia dell\u00e2\u0080\u0099Universit\u00c3\u00a0 di Trieste and by the Ministero dell'Istruzione, dell'Universit\u00c3\u00a0 e della Ricerca."
-    ],
-    "oai_identifier": [
-        "ivo://ia2.inaf.it/edu/inaf_oats/svas/C14/siap"
-    ],
-    "oai_set": [
-        "ivo_managed"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "educational galaxies stars planets"
-        }
-    ],
-    "title": [
-        "INAF-OATs SVAS Educational Images SIAP service. Le Stelle Vanno A Scuola (SVAS) proposes a modern tool to support teaching of astronomy, through the study and experimentation of its observation methods. SVAS offers to schools and teachers a remote laboratory with which carry out real observation sessions, managed in real time by the students under the supervision of the teacher, in the classroom, and of an astronomer, at the OATs, thanks to the telematic link between the school and the observatory. Students and teachers experience real astronomical observations, through the interactive participation to the different steps of planning, observing and acquiring the data. The project is addressed to 13-18 yr students. Every observation is previously planned together with the teachers, according to age and curriculum of the students, with the aim to maximize the results. The observing activity, lasting about 90 minutes and led by an astronomer of the OATs, can be done during the morning (observation of the Sun) or in the evening (observation of stars, nebulae, clusters and galaxies). SVAS involves the Astronomical Observatory of Trieste (OATs), the school (of every level) and the University of Trieste. SVAS is supported by the Consorzio per l\u00e2\u0080\u0099Incremento degli Studi e delle Ricerche dei Dipartimenti di Fisica e Astronomia dell\u00e2\u0080\u0099Universit\u00c3\u00a0 di Trieste and by the Ministero dell'Istruzione, dell'Universit\u00c3\u00a0 e della Ricerca."
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_dc/SET_1/json/0cb60b22-ad1f-5951-a0a7-0e3a736b3b72.json b/oaitestdata/ivoa-oai_dc/SET_1/json/0cb60b22-ad1f-5951-a0a7-0e3a736b3b72.json
deleted file mode 100644
index b364c9a0..00000000
--- a/oaitestdata/ivoa-oai_dc/SET_1/json/0cb60b22-ad1f-5951-a0a7-0e3a736b3b72.json
+++ /dev/null
@@ -1,47 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "MetaDataAccess": "http://registry.euro-vo.org/oai.jsp?verb=GetRecord&metadataPrefix=oai_dc&identifier=ivo://uk.ac.le.star.tmpledas/ledas/ledas/vlss",
-    "PublicationTimestamp": "2018-12-21T17:23:34Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "RelatedIdentifier": [
-        "ivo://uk.ac.le.star.tmpledas/ledas/ledas/vlss"
-    ],
-    "author": [
-        "LEDAS",
-        "LEDAS, University of Leicester"
-    ],
-    "fulltext": "ivo://uk.ac.le.star.tmpledas/ledas/ledas/vlss;2018-12-21T17:23:34Z;VLSS: VLA Low-Frequency Sky Survey Discrete Source Catalog (LEDAS);LEDAS, University of Leicester;LEDAS;Cone Search service for \n                    VLSS: VLA Low-Frequency Sky Survey Discrete Source Catalog (LEDAS)\n                . \n          \t\t\t\t\t\t\n          \t\t\t\t\t\tPart of Catalogues hosted at Leicester Database and Archive Service;LEDAS;vlss;2011-02-10T22:17:18;ivo://uk.ac.le.star.tmpledas/ledas/ledas/vlss",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0cb60b22-ad1f-5951-a0a7-0e3a736b3b72",
-    "notes": [
-        "Cone Search service for \n                    VLSS: VLA Low-Frequency Sky Survey Discrete Source Catalog (LEDAS)\n                . \n          \t\t\t\t\t\t\n          \t\t\t\t\t\tPart of Catalogues hosted at Leicester Database and Archive Service"
-    ],
-    "oai_identifier": [
-        "ivo://uk.ac.le.star.tmpledas/ledas/ledas/vlss"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "LEDAS"
-        },
-        {
-            "name": "vlss"
-        }
-    ],
-    "title": [
-        "Cone Search service for \n                    VLSS: VLA Low-Frequency Sky Survey Discrete Source Catalog (LEDAS)\n                . \n          \t\t\t\t\t\t\n          \t\t\t\t\t\tPart of Catalogues hosted at Leicester Database and Archive Service"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_dc/SET_1/json/0ccfe146-6bf7-56bf-b7ca-51796627d5e1.json b/oaitestdata/ivoa-oai_dc/SET_1/json/0ccfe146-6bf7-56bf-b7ca-51796627d5e1.json
deleted file mode 100644
index 657fc2fa..00000000
--- a/oaitestdata/ivoa-oai_dc/SET_1/json/0ccfe146-6bf7-56bf-b7ca-51796627d5e1.json
+++ /dev/null
@@ -1,47 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "MetaDataAccess": "http://registry.euro-vo.org/oai.jsp?verb=GetRecord&metadataPrefix=oai_dc&identifier=ivo://uk.ac.le.star.tmpledas/ledas/ledas/ipc",
-    "PublicationTimestamp": "2018-12-21T17:23:29Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "RelatedIdentifier": [
-        "ivo://uk.ac.le.star.tmpledas/ledas/ledas/ipc"
-    ],
-    "author": [
-        "LEDAS",
-        "LEDAS, University of Leicester"
-    ],
-    "fulltext": "ivo://uk.ac.le.star.tmpledas/ledas/ledas/ipc;2018-12-21T17:23:29Z;IPC: Einstein IPC Sources Catalog (LEDAS);LEDAS, University of Leicester;LEDAS;Cone Search service for \n                    IPC: Einstein IPC Sources Catalog (LEDAS)\n                . \n          \t\t\t\t\t\t\n          \t\t\t\t\t\tPart of Catalogues hosted at Leicester Database and Archive Service;LEDAS;ipc;2011-02-10T22:16:04;ivo://uk.ac.le.star.tmpledas/ledas/ledas/ipc",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0ccfe146-6bf7-56bf-b7ca-51796627d5e1",
-    "notes": [
-        "Cone Search service for \n                    IPC: Einstein IPC Sources Catalog (LEDAS)\n                . \n          \t\t\t\t\t\t\n          \t\t\t\t\t\tPart of Catalogues hosted at Leicester Database and Archive Service"
-    ],
-    "oai_identifier": [
-        "ivo://uk.ac.le.star.tmpledas/ledas/ledas/ipc"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "LEDAS"
-        },
-        {
-            "name": "ipc"
-        }
-    ],
-    "title": [
-        "Cone Search service for \n                    IPC: Einstein IPC Sources Catalog (LEDAS)\n                . \n          \t\t\t\t\t\t\n          \t\t\t\t\t\tPart of Catalogues hosted at Leicester Database and Archive Service"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_dc/SET_1/json/0cdd65dd-8c1d-5dab-b6bc-03e3ce1ad2f3.json b/oaitestdata/ivoa-oai_dc/SET_1/json/0cdd65dd-8c1d-5dab-b6bc-03e3ce1ad2f3.json
deleted file mode 100644
index a6e9f5d6..00000000
--- a/oaitestdata/ivoa-oai_dc/SET_1/json/0cdd65dd-8c1d-5dab-b6bc-03e3ce1ad2f3.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "NASA/IPAC Infrared Science Archive"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "MetaDataAccess": "http://registry.euro-vo.org/oai.jsp?verb=GetRecord&metadataPrefix=oai_dc&identifier=ivo://irsa.ipac/Spitzer/Catalog/SWIRE/SWIRE-EN2M70",
-    "PublicationTimestamp": "2016-02-05T15:15:05Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "NASA/IPAC Infrared Science Archive"
-    ],
-    "RelatedIdentifier": [
-        "ivo://irsa.ipac/Spitzer/Catalog/SWIRE/SWIRE-EN2M70"
-    ],
-    "ResourceType": [
-        "Catalog"
-    ],
-    "author": [
-        "SWIRE team"
-    ],
-    "fulltext": "ivo://irsa.ipac/Spitzer/Catalog/SWIRE/SWIRE-EN2M70;2016-02-05T15:15:05Z;Spitzer Wide-area InfraRed Extragalactic Survey ELAIS-N2 MIPS 70 micron Catalog;ivo://irsa.ipac/Spitzer/Catalog/SWIRE/SWIRE-EN2M70;NASA/IPAC Infrared Science Archive;SWIRE team;extragalactic survey;The Spitzer Wide-area InfraRed Extragalactic survey (SWIRE), the largest Spitzer Legacy program, is a wide-area, imaging survey to trace the evolution of dusty, star-forming galaxies, evolved stellar populations, and AGN as a function of environment, from redshifts z~3 to the current epoch. SWIRE surveys 6 high-latitude fields, totaling ~50 sq. deg. in all 7 Spitzer bands: 3.6, 4.5, 5.8, and 8 microns with IRAC and 24, 70, and 160 microns with MIPS (Lonsdale et al. 2003). The SWIRE Legacy Extragalactic Source Catalogs will eventually contain in excess of 2 million IR-selected galaxies, from those dominated by the light of stellar populations detected primarily by IRAC, to starbursts, ultra-luminous infrared galaxies and AGN detected also by MIPS.;Catalog",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0cdd65dd-8c1d-5dab-b6bc-03e3ce1ad2f3",
-    "notes": [
-        "The Spitzer Wide-area InfraRed Extragalactic survey (SWIRE), the largest Spitzer Legacy program, is a wide-area, imaging survey to trace the evolution of dusty, star-forming galaxies, evolved stellar populations, and AGN as a function of environment, from redshifts z~3 to the current epoch. SWIRE surveys 6 high-latitude fields, totaling ~50 sq. deg. in all 7 Spitzer bands: 3.6, 4.5, 5.8, and 8 microns with IRAC and 24, 70, and 160 microns with MIPS (Lonsdale et al. 2003). The SWIRE Legacy Extragalactic Source Catalogs will eventually contain in excess of 2 million IR-selected galaxies, from those dominated by the light of stellar populations detected primarily by IRAC, to starbursts, ultra-luminous infrared galaxies and AGN detected also by MIPS."
-    ],
-    "oai_identifier": [
-        "ivo://irsa.ipac/Spitzer/Catalog/SWIRE/SWIRE-EN2M70"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "extragalactic survey"
-        }
-    ],
-    "title": [
-        "The Spitzer Wide-area InfraRed Extragalactic survey (SWIRE), the largest Spitzer Legacy program, is a wide-area, imaging survey to trace the evolution of dusty, star-forming galaxies, evolved stellar populations, and AGN as a function of environment, from redshifts z~3 to the current epoch. SWIRE surveys 6 high-latitude fields, totaling ~50 sq. deg. in all 7 Spitzer bands: 3.6, 4.5, 5.8, and 8 microns with IRAC and 24, 70, and 160 microns with MIPS (Lonsdale et al. 2003). The SWIRE Legacy Extragalactic Source Catalogs will eventually contain in excess of 2 million IR-selected galaxies, from those dominated by the light of stellar populations detected primarily by IRAC, to starbursts, ultra-luminous infrared galaxies and AGN detected also by MIPS."
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_dc/SET_1/json/0ce5b927-3d5d-5ec0-a643-6e8df0a1788a.json b/oaitestdata/ivoa-oai_dc/SET_1/json/0ce5b927-3d5d-5ec0-a643-6e8df0a1788a.json
deleted file mode 100644
index cb0ccba9..00000000
--- a/oaitestdata/ivoa-oai_dc/SET_1/json/0ce5b927-3d5d-5ec0-a643-6e8df0a1788a.json
+++ /dev/null
@@ -1,47 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "MetaDataAccess": "http://registry.euro-vo.org/oai.jsp?verb=GetRecord&metadataPrefix=oai_dc&identifier=ivo://uk.ac.le.star.tmpledas/ledas/ledas/baxgalclus",
-    "PublicationTimestamp": "2018-12-21T17:23:26Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "RelatedIdentifier": [
-        "ivo://uk.ac.le.star.tmpledas/ledas/ledas/baxgalclus"
-    ],
-    "author": [
-        "LEDAS",
-        "LEDAS, University of Leicester"
-    ],
-    "fulltext": "ivo://uk.ac.le.star.tmpledas/ledas/ledas/baxgalclus;2018-12-21T17:23:26Z;BAXGALCLUS: BAX X-Ray Galaxy Clusters and Groups Catalog (LEDAS);LEDAS, University of Leicester;LEDAS;Cone Search service for \n                    BAXGALCLUS: BAX X-Ray Galaxy Clusters and Groups Catalog (LEDAS)\n                . \n          \t\t\t\t\t\t\n          \t\t\t\t\t\tPart of Catalogues hosted at Leicester Database and Archive Service;LEDAS;baxgalclus;2012-07-06T13:15:55;ivo://uk.ac.le.star.tmpledas/ledas/ledas/baxgalclus",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0ce5b927-3d5d-5ec0-a643-6e8df0a1788a",
-    "notes": [
-        "Cone Search service for \n                    BAXGALCLUS: BAX X-Ray Galaxy Clusters and Groups Catalog (LEDAS)\n                . \n          \t\t\t\t\t\t\n          \t\t\t\t\t\tPart of Catalogues hosted at Leicester Database and Archive Service"
-    ],
-    "oai_identifier": [
-        "ivo://uk.ac.le.star.tmpledas/ledas/ledas/baxgalclus"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "LEDAS"
-        },
-        {
-            "name": "baxgalclus"
-        }
-    ],
-    "title": [
-        "Cone Search service for \n                    BAXGALCLUS: BAX X-Ray Galaxy Clusters and Groups Catalog (LEDAS)\n                . \n          \t\t\t\t\t\t\n          \t\t\t\t\t\tPart of Catalogues hosted at Leicester Database and Archive Service"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_dc/SET_1/json/0ceaf7ab-a4ad-5439-8c28-8eec940c1cb3.json b/oaitestdata/ivoa-oai_dc/SET_1/json/0ceaf7ab-a4ad-5439-8c28-8eec940c1cb3.json
deleted file mode 100644
index dbefdfe1..00000000
--- a/oaitestdata/ivoa-oai_dc/SET_1/json/0ceaf7ab-a4ad-5439-8c28-8eec940c1cb3.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "MetaDataAccess": "http://registry.euro-vo.org/oai.jsp?verb=GetRecord&metadataPrefix=oai_dc&identifier=ivo://wfau.roe.ac.uk/ukidssDR5-v1/wsa/ceaApplication",
-    "PublicationTimestamp": "2018-12-27T13:17:00Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "RelatedIdentifier": [
-        "ivo://wfau.roe.ac.uk/ukidssDR5-v1/wsa/ceaApplication"
-    ],
-    "author": [
-        "WFAU"
-    ],
-    "fulltext": "ivo://wfau.roe.ac.uk/ukidssDR5-v1/wsa/ceaApplication;2018-12-27T13:17:00Z;UKIDSS DR5 (Secure Access);WFAU;WFAU;This DSA hosts data release 5 of the UKIRT Infrared Deep Sky Survey housed at the Wide Field Astronomy Unit at the Univeristy of Edinburgh. In order to access this data you need to contact Mark Holliman at msh@roe.ac.uk to be added to the authorized users list (unless you are already logged on with a valid WFAU community account). This catalog contains WFCAM data primarily originating from the five UKIDSS surveys: Large Area Survey, Galactic Plane Survey, Galactic Clusters Survey, Deep Extragalactic Survey and the Ultra Deep Survey (see the www.ukidss.org for survey descriptions);infrared, galaxies, stars, survey;2010-10-06T14:32:12;ivo://wfau.roe.ac.uk/ukidssDR5-v1/wsa/ceaApplication",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0ceaf7ab-a4ad-5439-8c28-8eec940c1cb3",
-    "notes": [
-        "This DSA hosts data release 5 of the UKIRT Infrared Deep Sky Survey housed at the Wide Field Astronomy Unit at the Univeristy of Edinburgh. In order to access this data you need to contact Mark Holliman at msh@roe.ac.uk to be added to the authorized users list (unless you are already logged on with a valid WFAU community account). This catalog contains WFCAM data primarily originating from the five UKIDSS surveys: Large Area Survey, Galactic Plane Survey, Galactic Clusters Survey, Deep Extragalactic Survey and the Ultra Deep Survey (see the www.ukidss.org for survey descriptions)"
-    ],
-    "oai_identifier": [
-        "ivo://wfau.roe.ac.uk/ukidssDR5-v1/wsa/ceaApplication"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "infrared"
-        },
-        {
-            "name": "galaxies"
-        },
-        {
-            "name": "stars"
-        },
-        {
-            "name": "survey"
-        }
-    ],
-    "title": [
-        "This DSA hosts data release 5 of the UKIRT Infrared Deep Sky Survey housed at the Wide Field Astronomy Unit at the Univeristy of Edinburgh. In order to access this data you need to contact Mark Holliman at msh@roe.ac.uk to be added to the authorized users list (unless you are already logged on with a valid WFAU community account). This catalog contains WFCAM data primarily originating from the five UKIDSS surveys: Large Area Survey, Galactic Plane Survey, Galactic Clusters Survey, Deep Extragalactic Survey and the Ultra Deep Survey (see the www.ukidss.org for survey descriptions)"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/ivoa-oai_dc/SET_1/json/0d77e39a-0b8c-58c1-9d6f-625139bb9a4f.json b/oaitestdata/ivoa-oai_dc/SET_1/json/0d77e39a-0b8c-58c1-9d6f-625139bb9a4f.json
deleted file mode 100644
index cbaa551c..00000000
--- a/oaitestdata/ivoa-oai_dc/SET_1/json/0d77e39a-0b8c-58c1-9d6f-625139bb9a4f.json
+++ /dev/null
@@ -1,52 +0,0 @@
-{
-    "Contact": [
-        "NASA/IPAC Infrared Science Archive"
-    ],
-    "DiscHierarchy": [
-        "4.2.5",
-        "Physics",
-        "Astrophysics and Astronomy"
-    ],
-    "Discipline": "Astrophysics And Astronomy",
-    "MetaDataAccess": "http://registry.euro-vo.org/oai.jsp?verb=GetRecord&metadataPrefix=oai_dc&identifier=ivo://irsa.ipac/Spitzer/Catalog/SDWFS/SDWFSI3Ep2",
-    "PublicationTimestamp": "2016-07-23T23:21:27Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "NASA/IPAC Infrared Science Archive"
-    ],
-    "RelatedIdentifier": [
-        "ivo://irsa.ipac/Spitzer/Catalog/SDWFS/SDWFSI3Ep2"
-    ],
-    "ResourceType": [
-        "Catalog"
-    ],
-    "author": [
-        "SDWFS team"
-    ],
-    "fulltext": "ivo://irsa.ipac/Spitzer/Catalog/SDWFS/SDWFSI3Ep2;2016-07-23T23:21:27Z;Spitzer Deep Wide-Field Survey 5.8 micron Epoch 2 Catalog;ivo://irsa.ipac/Spitzer/Catalog/SDWFS/SDWFSI3Ep2;NASA/IPAC Infrared Science Archive;SDWFS team;extragalactic survey;The Spitzer Deep, Wide-Field Survey (SDWFS) is a four-epoch infrared survey of 10 square degrees in the Bo\u00c3\u00b6tes field of the NOAO Deep Wide-Field Survey using the IRAC instrument on the Spitzer Space Telescope. SDWFS, a Spitzer Cycle 4 Legacy project, occupies a unique position in the area-depth survey space defined by other Spitzer surveys. The four epochs that make up SDWFS permit - for the first time - the selection of infrared-variable and high proper motion objects over a wide field on timescales of years. Because of its large survey volume, SDWFS is sensitive to galaxies out to z ~ 3 with relatively little impact from cosmic variance for all but the richest systems. The SDWFS data sets will thus be especially useful for characterizing galaxy evolution beyond z ~ 1.5.\n\n        The delivery consists of four band-matched catalogs for each of the four epochs and for the total SDWFS coadd data, a total of 20 catalogs. Vega magnitudes are reported for each IRAC band: 3.6, 4.5, 5.8, and 8 microns. Each source was measured three ways: 4 arcsec diameter aperture, 6 arcsec diameter aperture, and Kron radius aperture (MAG_AUTO in SExtractor). Source coordinates correspond to 2MASS catalog positions to within 0.2 arcsec. The tabulated uncertainties are twice the SExtractor (statistical only) uncertainties as an attempt to account for systematic uncertainties.;Catalog",
-    "group": "ivoa",
-    "groups": [
-        {
-            "name": "ivoa"
-        }
-    ],
-    "name": "0d77e39a-0b8c-58c1-9d6f-625139bb9a4f",
-    "notes": [
-        "The Spitzer Deep, Wide-Field Survey (SDWFS) is a four-epoch infrared survey of 10 square degrees in the Bo\u00c3\u00b6tes field of the NOAO Deep Wide-Field Survey using the IRAC instrument on the Spitzer Space Telescope. SDWFS, a Spitzer Cycle 4 Legacy project, occupies a unique position in the area-depth survey space defined by other Spitzer surveys. The four epochs that make up SDWFS permit - for the first time - the selection of infrared-variable and high proper motion objects over a wide field on timescales of years. Because of its large survey volume, SDWFS is sensitive to galaxies out to z ~ 3 with relatively little impact from cosmic variance for all but the richest systems. The SDWFS data sets will thus be especially useful for characterizing galaxy evolution beyond z ~ 1.5.\n\n        The delivery consists of four band-matched catalogs for each of the four epochs and for the total SDWFS coadd data, a total of 20 catalogs. Vega magnitudes are reported for each IRAC band: 3.6, 4.5, 5.8, and 8 microns. Each source was measured three ways: 4 arcsec diameter aperture, 6 arcsec diameter aperture, and Kron radius aperture (MAG_AUTO in SExtractor). Source coordinates correspond to 2MASS catalog positions to within 0.2 arcsec. The tabulated uncertainties are twice the SExtractor (statistical only) uncertainties as an attempt to account for systematic uncertainties."
-    ],
-    "oai_identifier": [
-        "ivo://irsa.ipac/Spitzer/Catalog/SDWFS/SDWFSI3Ep2"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "extragalactic survey"
-        }
-    ],
-    "title": [
-        "The Spitzer Deep, Wide-Field Survey (SDWFS) is a four-epoch infrared survey of 10 square degrees in the Bo\u00c3\u00b6tes field of the NOAO Deep Wide-Field Survey using the IRAC instrument on the Spitzer Space Telescope. SDWFS, a Spitzer Cycle 4 Legacy project, occupies a unique position in the area-depth survey space defined by other Spitzer surveys. The four epochs that make up SDWFS permit - for the first time - the selection of infrared-variable and high proper motion objects over a wide field on timescales of years. Because of its large survey volume, SDWFS is sensitive to galaxies out to z ~ 3 with relatively little impact from cosmic variance for all but the richest systems. The SDWFS data sets will thus be especially useful for characterizing galaxy evolution beyond z ~ 1.5.\n\n        The delivery consists of four band-matched catalogs for each of the four epochs and for the total SDWFS coadd data, a total of 20 catalogs. Vega magnitudes are reported for each IRAC band: 3.6, 4.5, 5.8, and 8 microns. Each source was measured three ways: 4 arcsec diameter aperture, 6 arcsec diameter aperture, and Kron radius aperture (MAG_AUTO in SExtractor). Source coordinates correspond to 2MASS catalog positions to within 0.2 arcsec. The tabulated uncertainties are twice the SExtractor (statistical only) uncertainties as an attempt to account for systematic uncertainties."
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/047f47f5-8beb-5c56-91a9-f91a12ac2de6.json b/oaitestdata/lter-oai_dc/LTER_1/json/047f47f5-8beb-5c56-91a9-f91a12ac2de6.json
deleted file mode 100644
index 3096cbd3..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/047f47f5-8beb-5c56-91a9-f91a12ac2de6.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/4b2ec444-c0d0-4482-852e-c59c7e33d373",
-    "PublicationTimestamp": "2017-03-28T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/closedAccess"
-    ],
-    "author": [
-        "Dirnboeck, Thomas"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/039b24e440f443a5be9e8f0229f850ea",
-        "2018-01-17T07:57:09Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        "Dirnboeck, Thomas",
-        "2017-03-28T15:15:14.303177+00:00",
-        "Deprecated",
-        "http://hdl.handle.net/11097/4b2ec444-c0d0-4482-852e-c59c7e33d373",
-        "https://b2share.fz-juelich.de/api/records/039b24e440f443a5be9e8f0229f850ea",
-        "oai:b2share.fz-juelich.de:b2rec/039b24e440f443a5be9e8f0229f850ea",
-        "info:eu-repo/semantics/closedAccess",
-        "LTER Z\u00f6belboden, Austria, Litterfall chemistry, 2012 - Deprecated"
-    ],
-    "notes": [
-        "Deprecated"
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/4b2ec444-c0d0-4482-852e-c59c7e33d373"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "title": [
-        "LTER Z\u00f6belboden, Austria, Litterfall chemistry, 2012 - Deprecated"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/039b24e440f443a5be9e8f0229f850ea"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/0697a3f4-d9c6-5bca-aed6-b459cea98c86.json b/oaitestdata/lter-oai_dc/LTER_1/json/0697a3f4-d9c6-5bca-aed6-b459cea98c86.json
deleted file mode 100644
index db56e07b..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/0697a3f4-d9c6-5bca-aed6-b459cea98c86.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/a5b949a9-fd23-4075-b537-b33f0b24fdd7",
-    "PublicationTimestamp": "2017-04-12T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/closedAccess"
-    ],
-    "author": [
-        ", "
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/f49f24d2c425476d915ab15267fe1d3c",
-        "2018-01-17T07:57:09Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        ", ",
-        "2017-04-12T14:22:27.230963+00:00",
-        "Deprecated",
-        "http://hdl.handle.net/11097/a5b949a9-fd23-4075-b537-b33f0b24fdd7",
-        "https://b2share.fz-juelich.de/api/records/f49f24d2c425476d915ab15267fe1d3c",
-        "oai:b2share.fz-juelich.de:b2rec/f49f24d2c425476d915ab15267fe1d3c",
-        "info:eu-repo/semantics/closedAccess",
-        "Wind throw monitoring valleys - Deprecated"
-    ],
-    "notes": [
-        "Deprecated"
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/a5b949a9-fd23-4075-b537-b33f0b24fdd7"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "title": [
-        "Wind throw monitoring valleys - Deprecated"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/f49f24d2c425476d915ab15267fe1d3c"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/071c8b99-7559-5184-aa6a-ef6464cf0214.json b/oaitestdata/lter-oai_dc/LTER_1/json/071c8b99-7559-5184-aa6a-ef6464cf0214.json
deleted file mode 100644
index 2a781fa9..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/071c8b99-7559-5184-aa6a-ef6464cf0214.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/6692cf92-e70f-4c67-be06-afc603bf068f",
-    "PublicationTimestamp": "2017-04-14T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/closedAccess"
-    ],
-    "author": [
-        "Kobler, Johannes"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/42abfa024f5c48e486da12396397a29f",
-        "2018-01-17T07:57:10Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        "Kobler, Johannes",
-        "2017-04-14T17:55:10.764339+00:00",
-        "Deprecated",
-        "http://hdl.handle.net/11097/6692cf92-e70f-4c67-be06-afc603bf068f",
-        "https://b2share.fz-juelich.de/api/records/42abfa024f5c48e486da12396397a29f",
-        "oai:b2share.fz-juelich.de:b2rec/42abfa024f5c48e486da12396397a29f",
-        "info:eu-repo/semantics/closedAccess",
-        "LTER Z\u00f6belboden, Austria, Precipitation chemistry, 2014 - Deprecated"
-    ],
-    "notes": [
-        "Deprecated"
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/6692cf92-e70f-4c67-be06-afc603bf068f"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "title": [
-        "LTER Z\u00f6belboden, Austria, Precipitation chemistry, 2014 - Deprecated"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/42abfa024f5c48e486da12396397a29f"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/087115e5-fcf8-56c7-bd56-9ebfa5093294.json b/oaitestdata/lter-oai_dc/LTER_1/json/087115e5-fcf8-56c7-bd56-9ebfa5093294.json
deleted file mode 100644
index 05d3cef5..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/087115e5-fcf8-56c7-bd56-9ebfa5093294.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/d00673b7-0786-45ab-9b85-5378e562325e",
-    "PublicationTimestamp": "2018-04-19T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/734c1d034cd9438481f755ecc4d314bf",
-        "2018-04-19T13:46:50Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        "2018-04-19T13:46:50.570202+00:00",
-        "Air temperature and precipitation data from SMEAR II",
-        "http://hdl.handle.net/11097/d00673b7-0786-45ab-9b85-5378e562325e",
-        "https://b2share.fz-juelich.de/api/records/734c1d034cd9438481f755ecc4d314bf",
-        "oai:b2share.fz-juelich.de:b2rec/734c1d034cd9438481f755ecc4d314bf",
-        "info:eu-repo/semantics/openAccess",
-        "eLTER VA, meteorology, air temperature, precipitation",
-        "meteo_LTER_EU_FI_007_v1"
-    ],
-    "notes": [
-        "Air temperature and precipitation data from SMEAR II"
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/d00673b7-0786-45ab-9b85-5378e562325e"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "tags": [
-        {
-            "name": "eLTER VA"
-        },
-        {
-            "name": "meteorology"
-        },
-        {
-            "name": "air temperature"
-        },
-        {
-            "name": "precipitation"
-        }
-    ],
-    "title": [
-        "meteo_LTER_EU_FI_007_v1"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/734c1d034cd9438481f755ecc4d314bf"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/12a3d4a8-8d23-557e-bded-bebafd430633.json b/oaitestdata/lter-oai_dc/LTER_1/json/12a3d4a8-8d23-557e-bded-bebafd430633.json
deleted file mode 100644
index 27be7f38..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/12a3d4a8-8d23-557e-bded-bebafd430633.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/b78768c2-a0b8-4adf-8917-a92f5575fcde",
-    "PublicationTimestamp": "2017-08-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        ", "
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/3168eccaaf5c4608a1c038a0b0daa492",
-        "2018-01-17T07:57:11Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        ", ",
-        "2017-08-01T13:53:03.092610+00:00",
-        "Vegetation relieves from the the monitoring of wind throws.",
-        "http://hdl.handle.net/11097/b78768c2-a0b8-4adf-8917-a92f5575fcde",
-        "https://b2share.fz-juelich.de/api/records/3168eccaaf5c4608a1c038a0b0daa492",
-        "oai:b2share.fz-juelich.de:b2rec/3168eccaaf5c4608a1c038a0b0daa492",
-        "info:eu-repo/semantics/openAccess",
-        "Wind throw monitoring uplands"
-    ],
-    "notes": [
-        "Vegetation relieves from the the monitoring of wind throws."
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/b78768c2-a0b8-4adf-8917-a92f5575fcde"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "title": [
-        "Wind throw monitoring uplands"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/3168eccaaf5c4608a1c038a0b0daa492"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/219a1f73-6579-547c-a6ad-107b1166746f.json b/oaitestdata/lter-oai_dc/LTER_1/json/219a1f73-6579-547c-a6ad-107b1166746f.json
deleted file mode 100644
index 0a0c8758..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/219a1f73-6579-547c-a6ad-107b1166746f.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/a80e0153-8ea5-4b6b-9801-5a6652410c08",
-    "PublicationTimestamp": "2017-04-14T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/closedAccess"
-    ],
-    "author": [
-        ", "
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/2a1845008ffa46669150c32bc53dc8dc",
-        "2018-01-17T07:57:09Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        ", ",
-        "2017-04-14T07:51:19.627100+00:00",
-        "Deprecated",
-        "http://hdl.handle.net/11097/a80e0153-8ea5-4b6b-9801-5a6652410c08",
-        "https://b2share.fz-juelich.de/api/records/2a1845008ffa46669150c32bc53dc8dc",
-        "oai:b2share.fz-juelich.de:b2rec/2a1845008ffa46669150c32bc53dc8dc",
-        "info:eu-repo/semantics/closedAccess",
-        "LTER Z\u00f6belboden, Austria, Reference documentation - Deprecated"
-    ],
-    "notes": [
-        "Deprecated"
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/a80e0153-8ea5-4b6b-9801-5a6652410c08"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "title": [
-        "LTER Z\u00f6belboden, Austria, Reference documentation - Deprecated"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/2a1845008ffa46669150c32bc53dc8dc"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/29204797-6b5e-539f-bedb-69da8cf505d3.json b/oaitestdata/lter-oai_dc/LTER_1/json/29204797-6b5e-539f-bedb-69da8cf505d3.json
deleted file mode 100644
index badfd00e..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/29204797-6b5e-539f-bedb-69da8cf505d3.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/ff76a8dd-61a2-42c7-bc9f-617d45ffbdad",
-    "PublicationTimestamp": "2018-04-20T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/be5c4f9dd8514fac970576fc6c609934",
-        "2018-04-20T11:48:59Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        "2018-04-20T11:48:59.041533+00:00",
-        "Air temperature and precipitation data from V\u00e4rri\u00f6",
-        "http://hdl.handle.net/11097/ff76a8dd-61a2-42c7-bc9f-617d45ffbdad",
-        "https://b2share.fz-juelich.de/api/records/be5c4f9dd8514fac970576fc6c609934",
-        "oai:b2share.fz-juelich.de:b2rec/be5c4f9dd8514fac970576fc6c609934",
-        "info:eu-repo/semantics/openAccess",
-        "eLTER VA, meteorology, air temperature, precipitation",
-        "meteorology_LTER_EU_FI_020_v1"
-    ],
-    "notes": [
-        "Air temperature and precipitation data from V\u00e4rri\u00f6"
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/ff76a8dd-61a2-42c7-bc9f-617d45ffbdad"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "tags": [
-        {
-            "name": "eLTER VA"
-        },
-        {
-            "name": "meteorology"
-        },
-        {
-            "name": "air temperature"
-        },
-        {
-            "name": "precipitation"
-        }
-    ],
-    "title": [
-        "meteorology_LTER_EU_FI_020_v1"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/be5c4f9dd8514fac970576fc6c609934"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/2f245499-9d2e-5cca-90ca-85ff13367241.json b/oaitestdata/lter-oai_dc/LTER_1/json/2f245499-9d2e-5cca-90ca-85ff13367241.json
deleted file mode 100644
index c9da5f7f..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/2f245499-9d2e-5cca-90ca-85ff13367241.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/6d82b5e1-7d48-4302-8487-8d99f815b2e1",
-    "PublicationTimestamp": "2017-04-12T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        ", "
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/fd1bd844e0ef49aeb828445f2247a100",
-        "2018-01-17T07:57:09Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        ", ",
-        "2017-04-12T14:28:07.410069+00:00",
-        "Vegetation relieves from the the monitoring of wind throws.",
-        "http://hdl.handle.net/11097/6d82b5e1-7d48-4302-8487-8d99f815b2e1",
-        "https://b2share.fz-juelich.de/api/records/fd1bd844e0ef49aeb828445f2247a100",
-        "oai:b2share.fz-juelich.de:b2rec/fd1bd844e0ef49aeb828445f2247a100",
-        "info:eu-repo/semantics/openAccess",
-        "Wind throw monitoring uplands"
-    ],
-    "notes": [
-        "Vegetation relieves from the the monitoring of wind throws."
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/6d82b5e1-7d48-4302-8487-8d99f815b2e1"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "title": [
-        "Wind throw monitoring uplands"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/fd1bd844e0ef49aeb828445f2247a100"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/32ce3e2b-a654-5558-a377-940e1ea356a5.json b/oaitestdata/lter-oai_dc/LTER_1/json/32ce3e2b-a654-5558-a377-940e1ea356a5.json
deleted file mode 100644
index 7fd3c548..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/32ce3e2b-a654-5558-a377-940e1ea356a5.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/ae6fe6f8-215f-48bb-a0a1-52bac0e0248c",
-    "PublicationTimestamp": "2017-08-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        ", "
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/dee5712f99864ee4bdb98473d2c4219c",
-        "2018-01-17T07:57:11Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        ", ",
-        "2017-08-01T13:51:53.674433+00:00",
-        "Vegetation relieves from the the monitoring of wind throws.",
-        "http://hdl.handle.net/11097/ae6fe6f8-215f-48bb-a0a1-52bac0e0248c",
-        "https://b2share.fz-juelich.de/api/records/dee5712f99864ee4bdb98473d2c4219c",
-        "oai:b2share.fz-juelich.de:b2rec/dee5712f99864ee4bdb98473d2c4219c",
-        "info:eu-repo/semantics/openAccess",
-        "Wind throw monitoring slopes"
-    ],
-    "notes": [
-        "Vegetation relieves from the the monitoring of wind throws."
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/ae6fe6f8-215f-48bb-a0a1-52bac0e0248c"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "title": [
-        "Wind throw monitoring slopes"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/dee5712f99864ee4bdb98473d2c4219c"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/332f673d-9b2c-5d69-8cf8-d354ab14c358.json b/oaitestdata/lter-oai_dc/LTER_1/json/332f673d-9b2c-5d69-8cf8-d354ab14c358.json
deleted file mode 100644
index 8d694aeb..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/332f673d-9b2c-5d69-8cf8-d354ab14c358.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/32cf8c66-081b-44d9-902f-a4a4913c3d7e",
-    "PublicationTimestamp": "2018-04-25T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "European Regional Centre for Ecohydrology"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/3dec3a7098144f09b11a65d0ff47e095",
-        "2018-05-08T09:57:46Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        "European Regional Centre for Ecohydrology",
-        "2018-04-25T13:52:00.335614+00:00",
-        "Meteorological date for \u0141\u00f3d\u017a",
-        "http://hdl.handle.net/11097/32cf8c66-081b-44d9-902f-a4a4913c3d7e",
-        "https://b2share.fz-juelich.de/api/records/3dec3a7098144f09b11a65d0ff47e095",
-        "oai:b2share.fz-juelich.de:b2rec/3dec3a7098144f09b11a65d0ff47e095",
-        "info:eu-repo/semantics/openAccess",
-        "The City of Lodz, Meteorological data, 2013 - 2017"
-    ],
-    "notes": [
-        "Meteorological date for \u0141\u00f3d\u017a"
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/32cf8c66-081b-44d9-902f-a4a4913c3d7e"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "title": [
-        "The City of Lodz, Meteorological data, 2013 - 2017"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/3dec3a7098144f09b11a65d0ff47e095"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/3a40ca8e-fbac-50d2-ac43-e30713025b38.json b/oaitestdata/lter-oai_dc/LTER_1/json/3a40ca8e-fbac-50d2-ac43-e30713025b38.json
deleted file mode 100644
index 0b205ded..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/3a40ca8e-fbac-50d2-ac43-e30713025b38.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/e9b0f8d3-b507-4504-8370-ea04c1dbd0ce",
-    "PublicationTimestamp": "2017-08-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Kobler, Johannes"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/0545a5e30eec4de494b2d41936fdf69e",
-        "2018-01-17T07:57:11Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        "Kobler, Johannes",
-        "2017-08-01T13:01:47.719914+00:00",
-        "Precipitation Chemistry of a Karst Watershed (Z\u00f6belboden) from the year 2015",
-        "http://hdl.handle.net/11097/e9b0f8d3-b507-4504-8370-ea04c1dbd0ce",
-        "https://b2share.fz-juelich.de/api/records/0545a5e30eec4de494b2d41936fdf69e",
-        "oai:b2share.fz-juelich.de:b2rec/0545a5e30eec4de494b2d41936fdf69e",
-        "info:eu-repo/semantics/openAccess",
-        "LTER Z\u00f6belboden, Austria, Precipitation chemistry, 2015"
-    ],
-    "notes": [
-        "Precipitation Chemistry of a Karst Watershed (Z\u00f6belboden) from the year 2015"
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/e9b0f8d3-b507-4504-8370-ea04c1dbd0ce"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "title": [
-        "LTER Z\u00f6belboden, Austria, Precipitation chemistry, 2015"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/0545a5e30eec4de494b2d41936fdf69e"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/420e937b-b532-5282-bdb8-855f76d927e3.json b/oaitestdata/lter-oai_dc/LTER_1/json/420e937b-b532-5282-bdb8-855f76d927e3.json
deleted file mode 100644
index b21ee552..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/420e937b-b532-5282-bdb8-855f76d927e3.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/5fe08cc0-e5b4-4e5e-9c05-aa0e93250d56",
-    "PublicationTimestamp": "2017-04-14T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Kobler, Johannes"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/f790570d69794e598fb837cbd35cc70b",
-        "2018-01-17T07:57:09Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        "Kobler, Johannes",
-        "2017-04-14T17:44:24.558133+00:00",
-        "Throughfall Chemistry of Two Forest Ecosystems in a Karst Watershed (Z\u00f6belboden) from the year 2014",
-        "http://hdl.handle.net/11097/5fe08cc0-e5b4-4e5e-9c05-aa0e93250d56",
-        "https://b2share.fz-juelich.de/api/records/f790570d69794e598fb837cbd35cc70b",
-        "oai:b2share.fz-juelich.de:b2rec/f790570d69794e598fb837cbd35cc70b",
-        "info:eu-repo/semantics/openAccess",
-        "LTER Z\u00f6belboden, Austria, Throughfall chemistry, 2014"
-    ],
-    "notes": [
-        "Throughfall Chemistry of Two Forest Ecosystems in a Karst Watershed (Z\u00f6belboden) from the year 2014"
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/5fe08cc0-e5b4-4e5e-9c05-aa0e93250d56"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "title": [
-        "LTER Z\u00f6belboden, Austria, Throughfall chemistry, 2014"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/f790570d69794e598fb837cbd35cc70b"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/4d53551a-bd8d-5e2e-a754-e5fe5ee79c51.json b/oaitestdata/lter-oai_dc/LTER_1/json/4d53551a-bd8d-5e2e-a754-e5fe5ee79c51.json
deleted file mode 100644
index 9e79a272..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/4d53551a-bd8d-5e2e-a754-e5fe5ee79c51.json
+++ /dev/null
@@ -1,48 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/64269d4d-463d-4369-be0d-84e30d0ad02b",
-    "PublicationTimestamp": "2018-04-10T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Rodriguez, Carlos",
-        "Diaz-Delgado, Ricardo"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/ccf40b110df74aa88ffc3c4d600bc98a",
-        "2018-04-10T16:39:48Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        "Diaz-Delgado, Ricardo",
-        "Rodriguez, Carlos",
-        "2018-04-10T16:39:48.229827+00:00",
-        "Basic climate at Do\u00f1ana LTSER platform: annual mean temperature, annual precipitation, monthly average temperature, monthly minimum and maximum temperature and precipitation from permanent meteorological station sited at Palacio de Do\u00f1ana.",
-        "http://hdl.handle.net/11097/64269d4d-463d-4369-be0d-84e30d0ad02b",
-        "https://b2share.fz-juelich.de/api/records/ccf40b110df74aa88ffc3c4d600bc98a",
-        "oai:b2share.fz-juelich.de:b2rec/ccf40b110df74aa88ffc3c4d600bc98a",
-        "info:eu-repo/semantics/openAccess",
-        "Basic climate at Do\u00f1ana LTSER Platform (2014-2016)"
-    ],
-    "notes": [
-        "Basic climate at Do\u00f1ana LTSER platform: annual mean temperature, annual precipitation, monthly average temperature, monthly minimum and maximum temperature and precipitation from permanent meteorological station sited at Palacio de Do\u00f1ana."
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/64269d4d-463d-4369-be0d-84e30d0ad02b"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "title": [
-        "Basic climate at Do\u00f1ana LTSER Platform (2014-2016)"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/ccf40b110df74aa88ffc3c4d600bc98a"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/5946d90c-e781-5d91-bd1e-4dd73d7ce7a9.json b/oaitestdata/lter-oai_dc/LTER_1/json/5946d90c-e781-5d91-bd1e-4dd73d7ce7a9.json
deleted file mode 100644
index 8d9b597d..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/5946d90c-e781-5d91-bd1e-4dd73d7ce7a9.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/423640c1-c07c-4e6e-9fe8-bb198eb5ff9f",
-    "PublicationTimestamp": "2017-05-14T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Rusina, Solvita"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/a5d2fb4923ba4463a82e113cd26b8477",
-        "2018-01-17T07:57:10Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        "Rusina, Solvita",
-        "2017-05-14T18:34:35.888030+00:00",
-        "Precipitation data for Engure LTSER 1995-2008",
-        "http://hdl.handle.net/11097/423640c1-c07c-4e6e-9fe8-bb198eb5ff9f",
-        "https://b2share.fz-juelich.de/api/records/a5d2fb4923ba4463a82e113cd26b8477",
-        "oai:b2share.fz-juelich.de:b2rec/a5d2fb4923ba4463a82e113cd26b8477",
-        "info:eu-repo/semantics/openAccess",
-        "precipitation, climate change",
-        "Precipitation data Engure LTSER 1995-2008"
-    ],
-    "notes": [
-        "Precipitation data for Engure LTSER 1995-2008"
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/423640c1-c07c-4e6e-9fe8-bb198eb5ff9f"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "tags": [
-        {
-            "name": "precipitation"
-        },
-        {
-            "name": "climate change"
-        }
-    ],
-    "title": [
-        "Precipitation data Engure LTSER 1995-2008"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/a5d2fb4923ba4463a82e113cd26b8477"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/6117f8df-65ce-57bc-8df9-3da3e0f4958a.json b/oaitestdata/lter-oai_dc/LTER_1/json/6117f8df-65ce-57bc-8df9-3da3e0f4958a.json
deleted file mode 100644
index 98972cfb..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/6117f8df-65ce-57bc-8df9-3da3e0f4958a.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/28aac0c8-0956-4c51-8844-b023779aa35d",
-    "PublicationTimestamp": "2017-04-12T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/closedAccess"
-    ],
-    "author": [
-        ", "
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/a4fd1e17c86c46f4b3f57e263bc7d84a",
-        "2018-01-17T07:57:09Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        ", ",
-        "2017-04-12T14:08:10.670024+00:00",
-        "Deprecated",
-        "http://hdl.handle.net/11097/28aac0c8-0956-4c51-8844-b023779aa35d",
-        "https://b2share.fz-juelich.de/api/records/a4fd1e17c86c46f4b3f57e263bc7d84a",
-        "oai:b2share.fz-juelich.de:b2rec/a4fd1e17c86c46f4b3f57e263bc7d84a",
-        "info:eu-repo/semantics/closedAccess",
-        "BIOHOLZ dead wood experiment - Deprecated"
-    ],
-    "notes": [
-        "Deprecated"
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/28aac0c8-0956-4c51-8844-b023779aa35d"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "title": [
-        "BIOHOLZ dead wood experiment - Deprecated"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/a4fd1e17c86c46f4b3f57e263bc7d84a"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/69802bfa-3ede-5d08-a6ca-b3a84dbb144e.json b/oaitestdata/lter-oai_dc/LTER_1/json/69802bfa-3ede-5d08-a6ca-b3a84dbb144e.json
deleted file mode 100644
index ccb08b27..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/69802bfa-3ede-5d08-a6ca-b3a84dbb144e.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/9157fbcd-bf2d-4628-8f1e-4977ce54b327",
-    "PublicationTimestamp": "2017-08-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        ", "
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/1fc5226e99884175ae4d551737fbce46",
-        "2018-01-17T07:57:12Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        ", ",
-        "2017-08-01T13:55:13.094067+00:00",
-        "Vegetation relieves from the the monitoring of wind throws.",
-        "http://hdl.handle.net/11097/9157fbcd-bf2d-4628-8f1e-4977ce54b327",
-        "https://b2share.fz-juelich.de/api/records/1fc5226e99884175ae4d551737fbce46",
-        "oai:b2share.fz-juelich.de:b2rec/1fc5226e99884175ae4d551737fbce46",
-        "info:eu-repo/semantics/openAccess",
-        "Wind throw monitoring valleys"
-    ],
-    "notes": [
-        "Vegetation relieves from the the monitoring of wind throws."
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/9157fbcd-bf2d-4628-8f1e-4977ce54b327"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "title": [
-        "Wind throw monitoring valleys"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/1fc5226e99884175ae4d551737fbce46"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/78263984-69d1-5c50-a497-9884a7e0e081.json b/oaitestdata/lter-oai_dc/LTER_1/json/78263984-69d1-5c50-a497-9884a7e0e081.json
deleted file mode 100644
index c7bd0e00..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/78263984-69d1-5c50-a497-9884a7e0e081.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/7e369573-fa07-4cd3-9cec-d02c7badfbfc",
-    "PublicationTimestamp": "2017-06-02T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Dirnboeck, Thomas"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/439000eee13f41fab2b08715d26b1d99",
-        "2018-01-17T07:57:10Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        "Dirnboeck, Thomas",
-        "2017-06-02T09:30:16.739097+00:00",
-        "Deprecated",
-        "http://hdl.handle.net/11097/7e369573-fa07-4cd3-9cec-d02c7badfbfc",
-        "https://b2share.fz-juelich.de/api/records/439000eee13f41fab2b08715d26b1d99",
-        "oai:b2share.fz-juelich.de:b2rec/439000eee13f41fab2b08715d26b1d99",
-        "info:eu-repo/semantics/openAccess",
-        "LTER Z\u00f6belboden, Austria, Epiphytic Lichens, 1993-2010 - Deprecated"
-    ],
-    "notes": [
-        "Deprecated"
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/7e369573-fa07-4cd3-9cec-d02c7badfbfc"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "title": [
-        "LTER Z\u00f6belboden, Austria, Epiphytic Lichens, 1993-2010 - Deprecated"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/439000eee13f41fab2b08715d26b1d99"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/7c34c89f-8450-59ee-947e-cd41492fe072.json b/oaitestdata/lter-oai_dc/LTER_1/json/7c34c89f-8450-59ee-947e-cd41492fe072.json
deleted file mode 100644
index 9062df56..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/7c34c89f-8450-59ee-947e-cd41492fe072.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/dfeb4f73-b689-42f9-949c-108a9e1b52d1",
-    "PublicationTimestamp": "2017-08-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Kobler, Johannes"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/5b3d9799904e4a71bbe5df93e8fbfa3c",
-        "2018-01-17T07:57:11Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        "Kobler, Johannes",
-        "2017-08-01T12:56:33.855245+00:00",
-        "Precipitation Chemistry of a Karst Watershed (Z\u00f6belboden) from the year 2014",
-        "http://hdl.handle.net/11097/dfeb4f73-b689-42f9-949c-108a9e1b52d1",
-        "https://b2share.fz-juelich.de/api/records/5b3d9799904e4a71bbe5df93e8fbfa3c",
-        "oai:b2share.fz-juelich.de:b2rec/5b3d9799904e4a71bbe5df93e8fbfa3c",
-        "info:eu-repo/semantics/openAccess",
-        "LTER Z\u00f6belboden, Austria, Precipitation chemistry, 2014"
-    ],
-    "notes": [
-        "Precipitation Chemistry of a Karst Watershed (Z\u00f6belboden) from the year 2014"
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/dfeb4f73-b689-42f9-949c-108a9e1b52d1"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "title": [
-        "LTER Z\u00f6belboden, Austria, Precipitation chemistry, 2014"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/5b3d9799904e4a71bbe5df93e8fbfa3c"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/88f6c3cc-b628-5b42-be39-68ef48ed49af.json b/oaitestdata/lter-oai_dc/LTER_1/json/88f6c3cc-b628-5b42-be39-68ef48ed49af.json
deleted file mode 100644
index a3891ba0..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/88f6c3cc-b628-5b42-be39-68ef48ed49af.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/830ab14f-4f47-462c-9a69-edf910695a53",
-    "PublicationTimestamp": "2017-04-14T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/closedAccess"
-    ],
-    "author": [
-        ", "
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/58e99af044974ea2bf44113884096ec1",
-        "2018-01-17T07:57:09Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        ", ",
-        "2017-04-14T07:56:52.785219+00:00",
-        "Deprecated",
-        "http://hdl.handle.net/11097/830ab14f-4f47-462c-9a69-edf910695a53",
-        "https://b2share.fz-juelich.de/api/records/58e99af044974ea2bf44113884096ec1",
-        "oai:b2share.fz-juelich.de:b2rec/58e99af044974ea2bf44113884096ec1",
-        "info:eu-repo/semantics/closedAccess",
-        "LTER Z\u00f6belboden, Austria, Station Codes - Deprecated"
-    ],
-    "notes": [
-        "Deprecated"
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/830ab14f-4f47-462c-9a69-edf910695a53"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "title": [
-        "LTER Z\u00f6belboden, Austria, Station Codes - Deprecated"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/58e99af044974ea2bf44113884096ec1"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/8dc6d9aa-8910-52e8-887f-6c29b47df9a4.json b/oaitestdata/lter-oai_dc/LTER_1/json/8dc6d9aa-8910-52e8-887f-6c29b47df9a4.json
deleted file mode 100644
index d8c58890..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/8dc6d9aa-8910-52e8-887f-6c29b47df9a4.json
+++ /dev/null
@@ -1,42 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/76e84cf2-5c1d-45cd-b963-4aed180be77b",
-    "PublicationTimestamp": "2018-01-26T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/4c8dbb87ec1c42749593f528284ee263",
-        "2018-01-26T10:49:30Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        "2018-01-26T10:49:30.824055+00:00",
-        "The aim of the project, was to assess fish biomass and their spatial-temporal distribution patterns in the Sulej\u00f3w Reservoir in relation to cyanobacterial blooms. Additionally the spatial and temporal dynamics of physical variables, inorganic nutrients, zooplankton and phytoplankton chlorophyll a were collected to help understanding which factors are controlling the development of the bloom and determine fish behavior. ",
-        "http://hdl.handle.net/11097/76e84cf2-5c1d-45cd-b963-4aed180be77b",
-        "https://b2share.fz-juelich.de/api/records/4c8dbb87ec1c42749593f528284ee263",
-        "oai:b2share.fz-juelich.de:b2rec/4c8dbb87ec1c42749593f528284ee263",
-        "info:eu-repo/semantics/openAccess",
-        "zooplankton"
-    ],
-    "notes": [
-        "The aim of the project, was to assess fish biomass and their spatial-temporal distribution patterns in the Sulej\u00f3w Reservoir in relation to cyanobacterial blooms. Additionally the spatial and temporal dynamics of physical variables, inorganic nutrients, zooplankton and phytoplankton chlorophyll a were collected to help understanding which factors are controlling the development of the bloom and determine fish behavior. "
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/76e84cf2-5c1d-45cd-b963-4aed180be77b"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "title": [
-        "zooplankton"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/4c8dbb87ec1c42749593f528284ee263"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/92fa02d2-86f7-5ba9-bb34-dbaa94afb8ac.json b/oaitestdata/lter-oai_dc/LTER_1/json/92fa02d2-86f7-5ba9-bb34-dbaa94afb8ac.json
deleted file mode 100644
index 1d33af42..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/92fa02d2-86f7-5ba9-bb34-dbaa94afb8ac.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/7bb7b76e-c295-4b43-a14f-aed36121d668",
-    "PublicationTimestamp": "2017-08-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Environment Agency Austria"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/45e0d33b77f5406db83429cf82cbb82d",
-        "2018-01-17T07:57:11Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        "Environment Agency Austria",
-        "2017-08-01T13:06:09.923666+00:00",
-        "Description of terms used in the columns SUBPROG, MEDIUM, TLEVEL, SUBST, UNIT, FLAGQUA and FLAGSTA in the respective data set",
-        "http://hdl.handle.net/11097/7bb7b76e-c295-4b43-a14f-aed36121d668",
-        "https://b2share.fz-juelich.de/api/records/45e0d33b77f5406db83429cf82cbb82d",
-        "oai:b2share.fz-juelich.de:b2rec/45e0d33b77f5406db83429cf82cbb82d",
-        "info:eu-repo/semantics/openAccess",
-        "LTER Z\u00f6belboden, Austria, Reference documentation"
-    ],
-    "notes": [
-        "Description of terms used in the columns SUBPROG, MEDIUM, TLEVEL, SUBST, UNIT, FLAGQUA and FLAGSTA in the respective data set"
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/7bb7b76e-c295-4b43-a14f-aed36121d668"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "title": [
-        "LTER Z\u00f6belboden, Austria, Reference documentation"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/45e0d33b77f5406db83429cf82cbb82d"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/939af77f-01ef-5926-a26e-5af0dc11f36b.json b/oaitestdata/lter-oai_dc/LTER_1/json/939af77f-01ef-5926-a26e-5af0dc11f36b.json
deleted file mode 100644
index 936e1b1d..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/939af77f-01ef-5926-a26e-5af0dc11f36b.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/4a86d9b8-3a91-4eb9-8259-0c8f3a902284",
-    "PublicationTimestamp": "2017-08-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Kobler, Johannes"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/597e774a6dde424cab134de19722aa95",
-        "2018-01-17T07:57:11Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        "Kobler, Johannes",
-        "2017-08-01T13:40:44.163227+00:00",
-        "Throughfall Chemistry of Two Forest Ecosystems in a Karst Watershed (Z\u00f6belboden) from the year 2014",
-        "http://hdl.handle.net/11097/4a86d9b8-3a91-4eb9-8259-0c8f3a902284",
-        "https://b2share.fz-juelich.de/api/records/597e774a6dde424cab134de19722aa95",
-        "oai:b2share.fz-juelich.de:b2rec/597e774a6dde424cab134de19722aa95",
-        "info:eu-repo/semantics/openAccess",
-        "LTER Z\u00f6belboden, Austria, Throughfall chemistry, 2014"
-    ],
-    "notes": [
-        "Throughfall Chemistry of Two Forest Ecosystems in a Karst Watershed (Z\u00f6belboden) from the year 2014"
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/4a86d9b8-3a91-4eb9-8259-0c8f3a902284"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "title": [
-        "LTER Z\u00f6belboden, Austria, Throughfall chemistry, 2014"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/597e774a6dde424cab134de19722aa95"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/aeeafae7-c41d-56f8-bdec-25449f84e12d.json b/oaitestdata/lter-oai_dc/LTER_1/json/aeeafae7-c41d-56f8-bdec-25449f84e12d.json
deleted file mode 100644
index df76f085..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/aeeafae7-c41d-56f8-bdec-25449f84e12d.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/817ecf38-d4fe-46a0-91e3-11c7bd06a03e",
-    "PublicationTimestamp": "2017-12-13T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Ilaria Baneschi",
-        "Luisa Poto",
-        "Carlo Barbante"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/0b328e18d9f44cc7b6c0ab74923360a1",
-        "2018-01-17T07:57:12Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        "Luisa Poto",
-        "Ilaria Baneschi",
-        "Carlo Barbante",
-        "2017-12-13T13:45:24.051618+00:00",
-        "Changes in the hydrologic aspects of climate are of optimum importance. However, the details of past changes in the hydrologic cycle are difficult to reconstruct. In this report we show the firs results of the analyses of paleohydrological proxies (n-alkanes) that allow the reconstruction of multiple terms of the hydrologic budget in the GPNP. We analyzed a core from Lake Trebecchi (GPNP), and after the definition of the age-dating chronology, we measured the concentrations of n-alkanes and their major indexes (ACL, Paq, C27/C31) usually selected to infer information about hydrological evolution of the ecosystems.",
-        "http://hdl.handle.net/11097/817ecf38-d4fe-46a0-91e3-11c7bd06a03e",
-        "https://b2share.fz-juelich.de/api/records/0b328e18d9f44cc7b6c0ab74923360a1",
-        "oai:b2share.fz-juelich.de:b2rec/0b328e18d9f44cc7b6c0ab74923360a1",
-        "info:eu-repo/semantics/openAccess",
-        "DATA SETS ON THE HISTORIC EVOLUTION OF THE ECOSYSTEMS"
-    ],
-    "notes": [
-        "Changes in the hydrologic aspects of climate are of optimum importance. However, the details of past changes in the hydrologic cycle are difficult to reconstruct. In this report we show the firs results of the analyses of paleohydrological proxies (n-alkanes) that allow the reconstruction of multiple terms of the hydrologic budget in the GPNP. We analyzed a core from Lake Trebecchi (GPNP), and after the definition of the age-dating chronology, we measured the concentrations of n-alkanes and their major indexes (ACL, Paq, C27/C31) usually selected to infer information about hydrological evolution of the ecosystems."
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/817ecf38-d4fe-46a0-91e3-11c7bd06a03e"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "title": [
-        "DATA SETS ON THE HISTORIC EVOLUTION OF THE ECOSYSTEMS"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/0b328e18d9f44cc7b6c0ab74923360a1"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/b5084c89-35dc-597e-82d2-498d14cc0777.json b/oaitestdata/lter-oai_dc/LTER_1/json/b5084c89-35dc-597e-82d2-498d14cc0777.json
deleted file mode 100644
index f81910ec..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/b5084c89-35dc-597e-82d2-498d14cc0777.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/d282b354-99d3-4549-9620-3f0d20c7a3dc",
-    "PublicationTimestamp": "2017-08-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Kobler, Johannes"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/8c2c790c6d694ce2baa3a3dfeded630f",
-        "2018-01-17T07:57:11Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        "Kobler, Johannes",
-        "2017-08-01T13:43:37.555237+00:00",
-        "Throughfall Chemistry of Two Forest Ecosystems in a Karst Watershed (Z\u00f6belboden) from the year 2015",
-        "http://hdl.handle.net/11097/d282b354-99d3-4549-9620-3f0d20c7a3dc",
-        "https://b2share.fz-juelich.de/api/records/8c2c790c6d694ce2baa3a3dfeded630f",
-        "oai:b2share.fz-juelich.de:b2rec/8c2c790c6d694ce2baa3a3dfeded630f",
-        "info:eu-repo/semantics/openAccess",
-        "LTER Z\u00f6belboden, Austria, Throughfall chemistry, 2015"
-    ],
-    "notes": [
-        "Throughfall Chemistry of Two Forest Ecosystems in a Karst Watershed (Z\u00f6belboden) from the year 2015"
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/d282b354-99d3-4549-9620-3f0d20c7a3dc"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "title": [
-        "LTER Z\u00f6belboden, Austria, Throughfall chemistry, 2015"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/8c2c790c6d694ce2baa3a3dfeded630f"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/bb7e6842-0f5d-5bc2-893b-92199302c3d1.json b/oaitestdata/lter-oai_dc/LTER_1/json/bb7e6842-0f5d-5bc2-893b-92199302c3d1.json
deleted file mode 100644
index fa74a8e1..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/bb7e6842-0f5d-5bc2-893b-92199302c3d1.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/ae451b6f-a870-4bc4-a4bb-a2d03ea08282",
-    "PublicationTimestamp": "2017-04-12T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/closedAccess"
-    ],
-    "author": [
-        ", "
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/fb6446dbaf464043b12b56890584079e",
-        "2018-01-17T07:57:09Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        ", ",
-        "2017-04-12T14:24:36.117303+00:00",
-        "Deprecated",
-        "http://hdl.handle.net/11097/ae451b6f-a870-4bc4-a4bb-a2d03ea08282",
-        "https://b2share.fz-juelich.de/api/records/fb6446dbaf464043b12b56890584079e",
-        "oai:b2share.fz-juelich.de:b2rec/fb6446dbaf464043b12b56890584079e",
-        "info:eu-repo/semantics/closedAccess",
-        "Wind throw monitoring slopes - Deprecated"
-    ],
-    "notes": [
-        "Deprecated"
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/ae451b6f-a870-4bc4-a4bb-a2d03ea08282"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "title": [
-        "Wind throw monitoring slopes - Deprecated"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/fb6446dbaf464043b12b56890584079e"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/bf7e83f0-a661-5724-8d0a-079a9fe615c6.json b/oaitestdata/lter-oai_dc/LTER_1/json/bf7e83f0-a661-5724-8d0a-079a9fe615c6.json
deleted file mode 100644
index f81bbc61..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/bf7e83f0-a661-5724-8d0a-079a9fe615c6.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/8dd4e53b-78d8-4680-992c-d26f8a3dbc63",
-    "PublicationTimestamp": "2017-08-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        ", "
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/4ff98a62f26f4bc68d3d21a73e2cc0ce",
-        "2018-01-17T07:57:10Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        ", ",
-        "2017-08-01T12:51:33.678556+00:00",
-        "Method documentation for throughfall chemistry data of the LTER Station Z\u00f6belboden",
-        "http://hdl.handle.net/11097/8dd4e53b-78d8-4680-992c-d26f8a3dbc63",
-        "https://b2share.fz-juelich.de/api/records/4ff98a62f26f4bc68d3d21a73e2cc0ce",
-        "oai:b2share.fz-juelich.de:b2rec/4ff98a62f26f4bc68d3d21a73e2cc0ce",
-        "info:eu-repo/semantics/openAccess",
-        "LTER Z\u00f6belboden, Austria, Method documentation - Throughfall chemistry"
-    ],
-    "notes": [
-        "Method documentation for throughfall chemistry data of the LTER Station Z\u00f6belboden"
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/8dd4e53b-78d8-4680-992c-d26f8a3dbc63"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "title": [
-        "LTER Z\u00f6belboden, Austria, Method documentation - Throughfall chemistry"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/4ff98a62f26f4bc68d3d21a73e2cc0ce"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/c5df17f7-3215-5be1-bfba-6ec75f0cdcc0.json b/oaitestdata/lter-oai_dc/LTER_1/json/c5df17f7-3215-5be1-bfba-6ec75f0cdcc0.json
deleted file mode 100644
index 97fea1e8..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/c5df17f7-3215-5be1-bfba-6ec75f0cdcc0.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/68db076b-651e-4889-a004-c2682c3aa1c0",
-    "PublicationTimestamp": "2017-08-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Kobler, Johannes"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/a64e58d8127d478b93cef92ef2a60155",
-        "2018-01-17T07:57:11Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        "Kobler, Johannes",
-        "2017-08-01T13:37:32.283927+00:00",
-        "Throughfall Chemistry of Two Forest Ecosystems in a Karst Watershed (Z\u00f6belboden) from the year 2013",
-        "http://hdl.handle.net/11097/68db076b-651e-4889-a004-c2682c3aa1c0",
-        "https://b2share.fz-juelich.de/api/records/a64e58d8127d478b93cef92ef2a60155",
-        "oai:b2share.fz-juelich.de:b2rec/a64e58d8127d478b93cef92ef2a60155",
-        "info:eu-repo/semantics/openAccess",
-        "LTER Z\u00f6belboden, Austria, Throughfall chemistry, 2013"
-    ],
-    "notes": [
-        "Throughfall Chemistry of Two Forest Ecosystems in a Karst Watershed (Z\u00f6belboden) from the year 2013"
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/68db076b-651e-4889-a004-c2682c3aa1c0"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "title": [
-        "LTER Z\u00f6belboden, Austria, Throughfall chemistry, 2013"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/a64e58d8127d478b93cef92ef2a60155"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/c69e0148-6f88-5053-a578-f39088578b1b.json b/oaitestdata/lter-oai_dc/LTER_1/json/c69e0148-6f88-5053-a578-f39088578b1b.json
deleted file mode 100644
index b736ad65..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/c69e0148-6f88-5053-a578-f39088578b1b.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/a56aa3f5-f56f-49c6-9910-30c7581e2eef",
-    "PublicationTimestamp": "2017-05-12T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Melecis, Viesturs"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/9159b7c3a7c3466480d8d3221ed080fb",
-        "2018-01-17T07:57:10Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        "Melecis, Viesturs",
-        "2017-05-12T12:27:33.949959+00:00",
-        "Presipitation data for coastal grassland reserve Randu Meadows 1996-2012",
-        "http://hdl.handle.net/11097/a56aa3f5-f56f-49c6-9910-30c7581e2eef",
-        "https://b2share.fz-juelich.de/api/records/9159b7c3a7c3466480d8d3221ed080fb",
-        "oai:b2share.fz-juelich.de:b2rec/9159b7c3a7c3466480d8d3221ed080fb",
-        "info:eu-repo/semantics/openAccess",
-        "bulk precipitation, climate change, coastal grasslands",
-        "Precipitation data Randu Meadows 1996-2012"
-    ],
-    "notes": [
-        "Presipitation data for coastal grassland reserve Randu Meadows 1996-2012"
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/a56aa3f5-f56f-49c6-9910-30c7581e2eef"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "tags": [
-        {
-            "name": "bulk precipitation"
-        },
-        {
-            "name": "climate change"
-        },
-        {
-            "name": "coastal grasslands"
-        }
-    ],
-    "title": [
-        "Precipitation data Randu Meadows 1996-2012"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/9159b7c3a7c3466480d8d3221ed080fb"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/d4002207-e271-5d11-8493-91892f70708c.json b/oaitestdata/lter-oai_dc/LTER_1/json/d4002207-e271-5d11-8493-91892f70708c.json
deleted file mode 100644
index bf54b69b..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/d4002207-e271-5d11-8493-91892f70708c.json
+++ /dev/null
@@ -1,51 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/f00a403b-4966-44e3-a01e-a2680637a130",
-    "PublicationTimestamp": "2018-04-19T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/0bdaa9168d5041e3ab4d8d893c9daf67",
-        "2018-04-19T12:28:52Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        "2018-04-19T12:28:52.043134+00:00",
-        "Tree data from SMEAR II",
-        "http://hdl.handle.net/11097/f00a403b-4966-44e3-a01e-a2680637a130",
-        "https://b2share.fz-juelich.de/api/records/0bdaa9168d5041e3ab4d8d893c9daf67",
-        "oai:b2share.fz-juelich.de:b2rec/0bdaa9168d5041e3ab4d8d893c9daf67",
-        "info:eu-repo/semantics/openAccess",
-        "eLTER VA, vegetation",
-        "vegetation_LTER_EU_FI_007_v1"
-    ],
-    "notes": [
-        "Tree data from SMEAR II"
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/f00a403b-4966-44e3-a01e-a2680637a130"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "tags": [
-        {
-            "name": "eLTER VA"
-        },
-        {
-            "name": "vegetation"
-        }
-    ],
-    "title": [
-        "vegetation_LTER_EU_FI_007_v1"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/0bdaa9168d5041e3ab4d8d893c9daf67"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/e9d08e69-e7c6-5664-acac-b4af15ec5d38.json b/oaitestdata/lter-oai_dc/LTER_1/json/e9d08e69-e7c6-5664-acac-b4af15ec5d38.json
deleted file mode 100644
index c2aa7f23..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/e9d08e69-e7c6-5664-acac-b4af15ec5d38.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/08e4874c-854d-4044-a3d5-816b9cc86aa4",
-    "PublicationTimestamp": "2017-04-14T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        ", "
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/f91ac21e742747b1b7572fe72c7d6af4",
-        "2018-01-17T07:57:09Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        ", ",
-        "2017-04-14T07:54:53.492038+00:00",
-        " Deprecated",
-        "http://hdl.handle.net/11097/08e4874c-854d-4044-a3d5-816b9cc86aa4",
-        "https://b2share.fz-juelich.de/api/records/f91ac21e742747b1b7572fe72c7d6af4",
-        "oai:b2share.fz-juelich.de:b2rec/f91ac21e742747b1b7572fe72c7d6af4",
-        "info:eu-repo/semantics/openAccess",
-        "LTER Z\u00f6belboden, Austria, Method documentation - Throughfall chemistry - Deprecated"
-    ],
-    "notes": [
-        " Deprecated"
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/08e4874c-854d-4044-a3d5-816b9cc86aa4"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "title": [
-        "LTER Z\u00f6belboden, Austria, Method documentation - Throughfall chemistry - Deprecated"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/f91ac21e742747b1b7572fe72c7d6af4"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/ed8806c3-df15-5160-9550-872cbe3919c7.json b/oaitestdata/lter-oai_dc/LTER_1/json/ed8806c3-df15-5160-9550-872cbe3919c7.json
deleted file mode 100644
index 36b85d17..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/ed8806c3-df15-5160-9550-872cbe3919c7.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/cc58a2d1-471f-49db-9443-d5cdc081fc28",
-    "PublicationTimestamp": "2017-08-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Dirnboeck, Thomas"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/0015d00076dc4de49050e74235148128",
-        "2018-01-17T07:57:10Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        "Dirnboeck, Thomas",
-        "2017-08-01T12:48:57.176792+00:00",
-        "Long-term (1993-2010) monitoring data of epiphytic lichens of the LTER station Z\u00f6belboden, Austria",
-        "http://hdl.handle.net/11097/cc58a2d1-471f-49db-9443-d5cdc081fc28",
-        "https://b2share.fz-juelich.de/api/records/0015d00076dc4de49050e74235148128",
-        "oai:b2share.fz-juelich.de:b2rec/0015d00076dc4de49050e74235148128",
-        "info:eu-repo/semantics/openAccess",
-        "LTER Z\u00f6belboden, Austria, Epiphytic Lichens, 1993-2010"
-    ],
-    "notes": [
-        "Long-term (1993-2010) monitoring data of epiphytic lichens of the LTER station Z\u00f6belboden, Austria"
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/cc58a2d1-471f-49db-9443-d5cdc081fc28"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "title": [
-        "LTER Z\u00f6belboden, Austria, Epiphytic Lichens, 1993-2010"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/0015d00076dc4de49050e74235148128"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/f22076c5-1dc4-55a4-8baf-b51df7f06083.json b/oaitestdata/lter-oai_dc/LTER_1/json/f22076c5-1dc4-55a4-8baf-b51df7f06083.json
deleted file mode 100644
index ced706b9..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/f22076c5-1dc4-55a4-8baf-b51df7f06083.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/3c8c86c7-cf1b-4944-9353-6fc6b9b5827c",
-    "PublicationTimestamp": "2017-05-14T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Rusina, Solvita"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/b34bf0efbf574e53bb94034e8e037564",
-        "2018-01-17T07:57:10Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        "Rusina, Solvita",
-        "2017-05-14T16:58:37.343092+00:00",
-        "Air temperature data for Engure LTSER 1995-2008",
-        "http://hdl.handle.net/11097/3c8c86c7-cf1b-4944-9353-6fc6b9b5827c",
-        "https://b2share.fz-juelich.de/api/records/b34bf0efbf574e53bb94034e8e037564",
-        "oai:b2share.fz-juelich.de:b2rec/b34bf0efbf574e53bb94034e8e037564",
-        "info:eu-repo/semantics/openAccess",
-        "air temperature, climate change",
-        "Air temperature data for Engure LTSER 1995-2008"
-    ],
-    "notes": [
-        "Air temperature data for Engure LTSER 1995-2008"
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/3c8c86c7-cf1b-4944-9353-6fc6b9b5827c"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "tags": [
-        {
-            "name": "air temperature"
-        },
-        {
-            "name": "climate change"
-        }
-    ],
-    "title": [
-        "Air temperature data for Engure LTSER 1995-2008"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/b34bf0efbf574e53bb94034e8e037564"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/fb5d18a8-b017-565e-8ca9-765472c3b64b.json b/oaitestdata/lter-oai_dc/LTER_1/json/fb5d18a8-b017-565e-8ca9-765472c3b64b.json
deleted file mode 100644
index aa76d796..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/fb5d18a8-b017-565e-8ca9-765472c3b64b.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/46d34cce-2929-48d3-a697-64d58483a1a2",
-    "PublicationTimestamp": "2017-08-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        ", "
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/70f1edc0abe84d2b80c5961bc2da53fc",
-        "2018-01-17T07:57:11Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        ", ",
-        "2017-08-01T13:49:50.453116+00:00",
-        "Vegetation relieves from the plots of the BIOHOLZ dead wood experiment.",
-        "http://hdl.handle.net/11097/46d34cce-2929-48d3-a697-64d58483a1a2",
-        "https://b2share.fz-juelich.de/api/records/70f1edc0abe84d2b80c5961bc2da53fc",
-        "oai:b2share.fz-juelich.de:b2rec/70f1edc0abe84d2b80c5961bc2da53fc",
-        "info:eu-repo/semantics/openAccess",
-        "BIOHOLZ dead wood experiment"
-    ],
-    "notes": [
-        "Vegetation relieves from the plots of the BIOHOLZ dead wood experiment."
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/46d34cce-2929-48d3-a697-64d58483a1a2"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "title": [
-        "BIOHOLZ dead wood experiment"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/70f1edc0abe84d2b80c5961bc2da53fc"
-}
\ No newline at end of file
diff --git a/oaitestdata/lter-oai_dc/LTER_1/json/fc0c2c9c-efa8-5a6a-9449-0e04e85d44b2.json b/oaitestdata/lter-oai_dc/LTER_1/json/fc0c2c9c-efa8-5a6a-9449-0e04e85d44b2.json
deleted file mode 100644
index 5215f21c..00000000
--- a/oaitestdata/lter-oai_dc/LTER_1/json/fc0c2c9c-efa8-5a6a-9449-0e04e85d44b2.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Discipline": "Environmentalmonitoring",
-    "PID": "http://hdl.handle.net/11097/ecad5e6a-313d-4d23-88e7-914ac0a2cd30",
-    "PublicationTimestamp": "2017-05-12T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "//LTER"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Melecis, Viesturs"
-    ],
-    "fulltext": [
-        "\n    ",
-        "oai:b2share.fz-juelich.de:b2rec/45e36fba641940eaa59814f90a37a179",
-        "2018-01-17T07:57:10Z",
-        "d952913c-451e-4b5c-817e-d578dc8a4469",
-        "\n    ",
-        "\n      ",
-        "Melecis, Viesturs",
-        "2017-05-12T12:52:16.820531+00:00",
-        "Coastal grassland vegetation data from 18 relevees (2x2 m) 1996-2012",
-        "http://hdl.handle.net/11097/ecad5e6a-313d-4d23-88e7-914ac0a2cd30",
-        "https://b2share.fz-juelich.de/api/records/45e36fba641940eaa59814f90a37a179",
-        "oai:b2share.fz-juelich.de:b2rec/45e36fba641940eaa59814f90a37a179",
-        "info:eu-repo/semantics/openAccess",
-        "vegetation, coastal grasslands, climate change",
-        "Vegetation_LTER_EU_LV_003_Randu_meadows_vegetation"
-    ],
-    "notes": [
-        "Coastal grassland vegetation data from 18 relevees (2x2 m) 1996-2012"
-    ],
-    "oai_identifier": [
-        "http://hdl.handle.net/11097/ecad5e6a-313d-4d23-88e7-914ac0a2cd30"
-    ],
-    "oai_set": [
-        "d952913c-451e-4b5c-817e-d578dc8a4469"
-    ],
-    "tags": [
-        {
-            "name": "vegetation"
-        },
-        {
-            "name": "coastal grasslands"
-        },
-        {
-            "name": "climate change"
-        }
-    ],
-    "title": [
-        "Vegetation_LTER_EU_LV_003_Randu_meadows_vegetation"
-    ],
-    "url": "https://b2share.fz-juelich.de/api/records/45e36fba641940eaa59814f90a37a179"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/00f06222-1144-52e1-8b8d-a2745eaf95f3.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/00f06222-1144-52e1-8b8d-a2745eaf95f3.json
deleted file mode 100644
index c6d07afb..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/00f06222-1144-52e1-8b8d-a2745eaf95f3.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0017/v2",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0017/v2",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0017/v2"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-11-29T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Ongari, Daniele",
-        "Keskin, Seda",
-        "Kadioglu, Ozge",
-        "Smit, Berend",
-        "Boyd, Peter G.",
-        "Mace, Amber K."
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0017/v2;2019-06-12Z;DOI;Dataset;Ongari, Daniele;Boyd, Peter G.;Mace, Amber K.;Smit, Berend;Kadioglu, Ozge;Keskin, Seda;Evaluating charge equilibration methods to generate electrostatic fields in nanoporous materials;Materials Cloud;2018-11-29;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;partial charges;Qeq;charge equilibration methods;MARVEL;doi:10.24435/materialscloud:2018.0017/v2;https://archive.materialscloud.org/2018.0017/v2;en;Charge equilibration (Qeq) methods can estimate the electrostatic potential of molecules and periodic frameworks by assigning point charges to each atom, using only a small fraction of the resources needed to compute density functional (DFT)-derived charges. This makes possible, for example, the computational screening of thousands of microporous structures to assess their performance for the adsorption of polar molecules. Recently, different variants of the original Qeq scheme were proposed to improve the quality of the computed point charges. One focus of this research was to improve the gas adsorption predictions in Metal Organic Frameworks (MOFs), for which many different structures are available. In this work, we review the evolution of the method from the original Qeq scheme, understanding the role of the different modifications on the final output. We evaluated the result of combining different protocols and set of parameters, by comparing the Qeq charges with high quality DFT-derived DDEC charges for 2338 MOF structures. We focused on the systematic errors that are attributable to specific atom types to quantify the final precision that one can expect from Qeq methods in the context of gas adsorption where the electrostatic potential plays a significant role, namely CO2 and H2S adsorption. In conclusion, both the type of algorithm and the input parameters have a large impact on the resulting charges and we draw some guidelines to help the user to choose the proper combination of the two for obtaining a meaningful set of charges. We show that, considering this set of MOFs, the accuracy of the original Qeq scheme is often still comparable with the most recent variants, even if it clearly fails in the presence of certain atom types, such as alkali metals.<br/>\n<br/>\nVersion 2 of the record adds the data underlying the figures in CSV format.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "00f06222-1144-52e1-8b8d-a2745eaf95f3",
-    "notes": [
-        "Charge equilibration (Qeq) methods can estimate the electrostatic potential of molecules and periodic frameworks by assigning point charges to each atom, using only a small fraction of the resources needed to compute density functional (DFT)-derived charges. This makes possible, for example, the computational screening of thousands of microporous structures to assess their performance for the adsorption of polar molecules. Recently, different variants of the original Qeq scheme were proposed to improve the quality of the computed point charges. One focus of this research was to improve the gas adsorption predictions in Metal Organic Frameworks (MOFs), for which many different structures are available. In this work, we review the evolution of the method from the original Qeq scheme, understanding the role of the different modifications on the final output. We evaluated the result of combining different protocols and set of parameters, by comparing the Qeq charges with high quality DFT-derived DDEC charges for 2338 MOF structures. We focused on the systematic errors that are attributable to specific atom types to quantify the final precision that one can expect from Qeq methods in the context of gas adsorption where the electrostatic potential plays a significant role, namely CO2 and H2S adsorption. In conclusion, both the type of algorithm and the input parameters have a large impact on the resulting charges and we draw some guidelines to help the user to choose the proper combination of the two for obtaining a meaningful set of charges. We show that, considering this set of MOFs, the accuracy of the original Qeq scheme is often still comparable with the most recent variants, even if it clearly fails in the presence of certain atom types, such as alkali metals.<br/>\n<br/>\nVersion 2 of the record adds the data underlying the figures in CSV format."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0017/v2"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "partial charges"
-        },
-        {
-            "name": "Qeq"
-        },
-        {
-            "name": "charge equilibration methods"
-        },
-        {
-            "name": "MARVEL"
-        }
-    ],
-    "title": [
-        "Evaluating charge equilibration methods to generate electrostatic fields in nanoporous materials"
-    ],
-    "url": "https://archive.materialscloud.org/2018.0017/v2"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/011f4e59-80c9-5e58-9ee6-ee1523f8f837.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/011f4e59-80c9-5e58-9ee6-ee1523f8f837.json
deleted file mode 100644
index 01a05a62..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/011f4e59-80c9-5e58-9ee6-ee1523f8f837.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0013/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0013/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0013/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-04-17T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "\u0160u\u0107ur, Zoran",
-        "Spiwok, Vojtech",
-        "K\u0159\u00ed\u017e, Pavel"
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0013/v1;2019-06-12Z;DOI;Dataset;Spiwok, Vojtech;\u0160u\u0107ur, Zoran;K\u0159\u00ed\u017e, Pavel;Free-Energy Surface Prediction by Flying Gaussian Method: Numerical Proof;Materials Cloud;2019-04-17;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;metadynamics;flying Gaussian method;molecular dynamics simulation;sampling;doi:10.24435/materialscloud:2019.0013/v1;https://archive.materialscloud.org/2019.0013/v1;en;Biomolecular simulations have a great potential in protein engineering, drug discovery and many other fields. Unfortunately, this method is computationally expensive, so many interesting processes cannot be routinely studied. In order to address this problem we developed Flying Gaussian method [Journal of Chemical Theory and Computation 12, 4644-4650 (2016)]. This method simultaneously simulates multiple replicas of the studied system and disfavor replicas with similar structures by artificial bias potential. The question arises how to calculate an unbiased free energy surface from a biased simulation. This dataset demonstrates together with mathematical arguments supports application of Umbrella Sampling reweighing method, despite the fact that this method is designed for methods with a time-independent bias potential.\n<br/>\n",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "011f4e59-80c9-5e58-9ee6-ee1523f8f837",
-    "notes": [
-        "Biomolecular simulations have a great potential in protein engineering, drug discovery and many other fields. Unfortunately, this method is computationally expensive, so many interesting processes cannot be routinely studied. In order to address this problem we developed Flying Gaussian method [Journal of Chemical Theory and Computation 12, 4644-4650 (2016)]. This method simultaneously simulates multiple replicas of the studied system and disfavor replicas with similar structures by artificial bias potential. The question arises how to calculate an unbiased free energy surface from a biased simulation. This dataset demonstrates together with mathematical arguments supports application of Umbrella Sampling reweighing method, despite the fact that this method is designed for methods with a time-independent bias potential.\n<br/>\n"
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0013/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "metadynamics"
-        },
-        {
-            "name": "flying Gaussian method"
-        },
-        {
-            "name": "molecular dynamics simulation"
-        },
-        {
-            "name": "sampling"
-        }
-    ],
-    "title": [
-        "Free-Energy Surface Prediction by Flying Gaussian Method: Numerical Proof"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0013/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/01407b86-305a-558d-a6ae-89e4310b7cc5.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/01407b86-305a-558d-a6ae-89e4310b7cc5.json
deleted file mode 100644
index d16cd88d..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/01407b86-305a-558d-a6ae-89e4310b7cc5.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0022/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0022/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0022/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-12-10T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Chen, Wei",
-        "Pasquarello, Alfredo"
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0022/v1;2019-06-12Z;DOI;Dataset;Chen, Wei;Pasquarello, Alfredo;Atomic structures of semiconductor surfaces;Materials Cloud;2018-12-10;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;semiconductor;surface;ionization potential;doi:10.24435/materialscloud:2018.0022/v1;https://archive.materialscloud.org/2018.0022/v1;en;This entry includes the surface structures of some prototypical semiconductors obtained via structural optimizations using the PBE density functional. The structures were initially used for benchmarking ionization potentials calculated with hybrid density functionals and GW approximation.\n<br/>\n\n<br/>\nSeven semiconductor surfaces are provided in the form of Quantum ESPRESSO input: Si(111), C(111),  GaAs(110), GaP(110), ZnSe(110), ZnO(10-10), and TiO2(110). ",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "01407b86-305a-558d-a6ae-89e4310b7cc5",
-    "notes": [
-        "This entry includes the surface structures of some prototypical semiconductors obtained via structural optimizations using the PBE density functional. The structures were initially used for benchmarking ionization potentials calculated with hybrid density functionals and GW approximation.\n<br/>\n\n<br/>\nSeven semiconductor surfaces are provided in the form of Quantum ESPRESSO input: Si(111), C(111),  GaAs(110), GaP(110), ZnSe(110), ZnO(10-10), and TiO2(110). "
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0022/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "semiconductor"
-        },
-        {
-            "name": "surface"
-        },
-        {
-            "name": "ionization potential"
-        }
-    ],
-    "title": [
-        "Atomic structures of semiconductor surfaces"
-    ],
-    "url": "https://archive.materialscloud.org/2018.0022/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/0180b5cb-bc62-5021-bff4-59e62ca18efb.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/0180b5cb-bc62-5021-bff4-59e62ca18efb.json
deleted file mode 100644
index 43d77386..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/0180b5cb-bc62-5021-bff4-59e62ca18efb.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2017.0001/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2017.0001/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2017.0001/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2017-03-14T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Barthel, Senja D.",
-        "Smit, Berend",
-        "Lee, Yongjin",
-        "Moosavi, S. Mohamad",
-        "D\u0142otko, Pawe\u0142",
-        "Hess, Kathryn"
-    ],
-    "fulltext": "oai:materialscloud.org:2017.0001/v1;2019-06-12Z;DOI;Dataset;Lee, Yongjin;Barthel, Senja D.;D\u0142otko, Pawe\u0142;Moosavi, S. Mohamad;Hess, Kathryn;Smit, Berend;Barcodes for nanoporous materials;Materials Cloud;2017-03-14;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;zeolites;metal organic frameworks;nanoporous materials;topological data analysis;persistence homology;MARVEL;doi:10.24435/materialscloud:2017.0001/v1;https://archive.materialscloud.org/2017.0001/v1;en;In most applications of nanoporous materials the pore structure is as important as the chemical composition as a determinant of performance. For example, one can alter performance in applications like carbon capture or methane storage by orders of magnitude by only modifying the pore structure. For these applications it is therefore important to identify the optimal pore geometry and use this information to find similar materials. However, the mathematical language and tools to identify materials with similar pore structures, but different composition, has been lacking. Recently, we developed a pore recognition approach to quantify similarity of pore structures using topological data analysis. Barcodes generated with using this approach allow us to identify materials with similar pore geometries, and to screen for materials that are similar to given top-performing structures. This database has barcodes for zeolites, metal organic frameworks, and zeolitic imidazolate frameworks.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "0180b5cb-bc62-5021-bff4-59e62ca18efb",
-    "notes": [
-        "In most applications of nanoporous materials the pore structure is as important as the chemical composition as a determinant of performance. For example, one can alter performance in applications like carbon capture or methane storage by orders of magnitude by only modifying the pore structure. For these applications it is therefore important to identify the optimal pore geometry and use this information to find similar materials. However, the mathematical language and tools to identify materials with similar pore structures, but different composition, has been lacking. Recently, we developed a pore recognition approach to quantify similarity of pore structures using topological data analysis. Barcodes generated with using this approach allow us to identify materials with similar pore geometries, and to screen for materials that are similar to given top-performing structures. This database has barcodes for zeolites, metal organic frameworks, and zeolitic imidazolate frameworks."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2017.0001/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "zeolites"
-        },
-        {
-            "name": "metal organic frameworks"
-        },
-        {
-            "name": "nanoporous materials"
-        },
-        {
-            "name": "topological data analysis"
-        },
-        {
-            "name": "persistence homology"
-        },
-        {
-            "name": "MARVEL"
-        }
-    ],
-    "title": [
-        "Barcodes for nanoporous materials"
-    ],
-    "url": "https://archive.materialscloud.org/2017.0001/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/0471393a-2dce-562b-bd77-c45fb015e298.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/0471393a-2dce-562b-bd77-c45fb015e298.json
deleted file mode 100644
index 06ca39d9..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/0471393a-2dce-562b-bd77-c45fb015e298.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0021/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0021/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0021/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-05-17T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Hozzova, Jana",
-        "Krenek, Ales",
-        "Spiwok, Vojtech",
-        "Simkova, Maria"
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0021/v1;2019-06-12Z;DOI;Dataset;Hozzova, Jana;Krenek, Ales;Simkova, Maria;Spiwok, Vojtech;Reducing the Number of Mean-Square Deviation Calculations with Floating Close Structure in Metadynamics;Materials Cloud;2019-05-17;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;metadynamics;collective variable;mean square deviation;doi:10.24435/materialscloud:2019.0021/v1;https://archive.materialscloud.org/2019.0021/v1;en;Biomolecular simulations are computationally expensive. This limits their application in protein folding simulations, protein engineering, drug design and related fields. Enhanced sampling techniques such as metadynamics accelerates slow events in molecular simulation. This and other method apply artificial forces in directions of collective degrees of freedom (aka collective variables). Path collective variables and Property Map collective variables are defined using a series of reference structures of the studied molecular system. They require a huge number of mean square deviation calculations along the simulation. Close Structure algorithm reduces the number of these operations.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "0471393a-2dce-562b-bd77-c45fb015e298",
-    "notes": [
-        "Biomolecular simulations are computationally expensive. This limits their application in protein folding simulations, protein engineering, drug design and related fields. Enhanced sampling techniques such as metadynamics accelerates slow events in molecular simulation. This and other method apply artificial forces in directions of collective degrees of freedom (aka collective variables). Path collective variables and Property Map collective variables are defined using a series of reference structures of the studied molecular system. They require a huge number of mean square deviation calculations along the simulation. Close Structure algorithm reduces the number of these operations."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0021/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "metadynamics"
-        },
-        {
-            "name": "collective variable"
-        },
-        {
-            "name": "mean square deviation"
-        }
-    ],
-    "title": [
-        "Reducing the Number of Mean-Square Deviation Calculations with Floating Close Structure in Metadynamics"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0021/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/071a071b-5346-59f2-9720-46dbeadf6bb3.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/071a071b-5346-59f2-9720-46dbeadf6bb3.json
deleted file mode 100644
index 66318af0..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/071a071b-5346-59f2-9720-46dbeadf6bb3.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0012/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0012/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0012/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-04-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Pignedoli, Carlo Antonio",
-        "Fasel, Roman",
-        "Mishra, Shantanu"
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0012/v1;2019-06-12Z;DOI;Dataset;Fasel, Roman;Pignedoli, Carlo Antonio;Mishra, Shantanu;Tailoring Bond Topologies in Open-Shell Graphene Nanostructures;Materials Cloud;2019-04-07;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;density functional theory;MARVEL;scanning tunneling microscopy;scanning tunneling spectroscopy;open-shell polycyclic aromatic hydrocarbons;nonalternant polycyclic aromatic hydrocarbons;atom manipulation;doi:10.24435/materialscloud:2019.0012/v1;https://archive.materialscloud.org/2019.0012/v1;en;The data contained in this record, raw data of images and input files to reproduce calculations, support our recent report for the on-surface synthesis and characterization of two ultralow-gap open-shell molecules, namely peri-tetracene, a benzenoid graphene fragment with zigzag edge topology, and dibenzo[a,m]dicyclohepta[bcde,nopq]rubicene, a nonbenzenoid nonalternant structural isomer of peri-tetracene with two embedded azulene units. Our results provide an understanding of the ramifications of altered bond topologies at the single-molecule scale, with the prospect of designing functionalities in carbon-based nanostructures via engineering of bond topology ",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "071a071b-5346-59f2-9720-46dbeadf6bb3",
-    "notes": [
-        "The data contained in this record, raw data of images and input files to reproduce calculations, support our recent report for the on-surface synthesis and characterization of two ultralow-gap open-shell molecules, namely peri-tetracene, a benzenoid graphene fragment with zigzag edge topology, and dibenzo[a,m]dicyclohepta[bcde,nopq]rubicene, a nonbenzenoid nonalternant structural isomer of peri-tetracene with two embedded azulene units. Our results provide an understanding of the ramifications of altered bond topologies at the single-molecule scale, with the prospect of designing functionalities in carbon-based nanostructures via engineering of bond topology "
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0012/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "density functional theory"
-        },
-        {
-            "name": "MARVEL"
-        },
-        {
-            "name": "scanning tunneling microscopy"
-        },
-        {
-            "name": "scanning tunneling spectroscopy"
-        },
-        {
-            "name": "open-shell polycyclic aromatic hydrocarbons"
-        },
-        {
-            "name": "nonalternant polycyclic aromatic hydrocarbons"
-        },
-        {
-            "name": "atom manipulation"
-        }
-    ],
-    "title": [
-        "Tailoring Bond Topologies in Open-Shell Graphene Nanostructures"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0012/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/07ce9e2d-6096-5916-9112-47a0430c6dcd.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/07ce9e2d-6096-5916-9112-47a0430c6dcd.json
deleted file mode 100644
index 2f96a0dc..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/07ce9e2d-6096-5916-9112-47a0430c6dcd.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2017.0007/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2017.0007/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2017.0007/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2017-11-28T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Del Ben, Mauro",
-        "Hutter, Juerg",
-        "VandeVondele, Joost"
-    ],
-    "fulltext": "oai:materialscloud.org:2017.0007/v1;2019-06-12Z;DOI;Dataset;Del Ben, Mauro;VandeVondele, Joost;Hutter, Juerg;Isobaric-Isothermal Monte Carlo Simulations of Bulk Liquid Water from MP2 and RPA Theory (MC Trajectories Data Download);Materials Cloud;2017-11-28;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;MP2;RPA;Monte Carlo Simulations;Bulk Liquid Water;Isobaric-Isothermal (NpT);MARVEL;doi:10.24435/materialscloud:2017.0007/v1;https://archive.materialscloud.org/2017.0007/v1;en;Methods based on the second order M\u00f8ller\u2013Plesset perturbation theory (MP2) and the Random Phase Approximation (RPA) have emerged as practicable and reliable approaches to improve the accuracy of density functional approximations for first principle atomistic simulations. Such approaches are in fact capable to account ab-initio for non-local dynamical electron correlation effects, which play a fundamental role, for example, in the description of non-bonded interactions. To assess the performance of MP2 and RPA for real applications, isobaric-isothermal Monte Carlo simulations have been performed to study the structural properties of bulk liquid water under ambient conditions. The choice of bulk liquid water as benchmark system is motivated by the complicated nature of the intermolecular interactions, where repulsion, polarization, hydrogen bonding and van der Waals forces play an important role and are particularly difficult to reproduce accurately in atomistic models. The results demonstrate the feasibility of such approaches which open the way for further applications.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "07ce9e2d-6096-5916-9112-47a0430c6dcd",
-    "notes": [
-        "Methods based on the second order M\u00f8ller\u2013Plesset perturbation theory (MP2) and the Random Phase Approximation (RPA) have emerged as practicable and reliable approaches to improve the accuracy of density functional approximations for first principle atomistic simulations. Such approaches are in fact capable to account ab-initio for non-local dynamical electron correlation effects, which play a fundamental role, for example, in the description of non-bonded interactions. To assess the performance of MP2 and RPA for real applications, isobaric-isothermal Monte Carlo simulations have been performed to study the structural properties of bulk liquid water under ambient conditions. The choice of bulk liquid water as benchmark system is motivated by the complicated nature of the intermolecular interactions, where repulsion, polarization, hydrogen bonding and van der Waals forces play an important role and are particularly difficult to reproduce accurately in atomistic models. The results demonstrate the feasibility of such approaches which open the way for further applications."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2017.0007/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "MP"
-        },
-        {
-            "name": "RPA"
-        },
-        {
-            "name": "Monte Carlo Simulations"
-        },
-        {
-            "name": "Bulk Liquid Water"
-        },
-        {
-            "name": "Isobaric-Isothermal NpT"
-        },
-        {
-            "name": "MARVEL"
-        }
-    ],
-    "title": [
-        "Isobaric-Isothermal Monte Carlo Simulations of Bulk Liquid Water from MP2 and RPA Theory (MC Trajectories Data Download)"
-    ],
-    "url": "https://archive.materialscloud.org/2017.0007/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/0916e202-dba7-51ff-bdf4-313236feec32.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/0916e202-dba7-51ff-bdf4-313236feec32.json
deleted file mode 100644
index c846f0ee..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/0916e202-dba7-51ff-bdf4-313236feec32.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0015/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0015/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0015/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-05-01T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Mamun, Osman",
-        "Winther, Kirsten",
-        "Boes, Jacob",
-        "Bligaard, Thomas"
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0015/v1;2019-06-12Z;DOI;Dataset;Mamun, Osman;Winther, Kirsten;Boes, Jacob;Bligaard, Thomas;High-throughput calculations of catalytic properties of bimetallic alloy surfaces;Materials Cloud;2019-05-01;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;DFT;Heterogeneous catalysis;Chemisorption;surfaces;doi:10.24435/materialscloud:2019.0015/v1;https://archive.materialscloud.org/2019.0015/v1;en;We present a large dataset of adsorption of H, C, N, O and S onto more than 2,000 metallic and bimetallic alloy surfaces, consisting of approximately 90,000 DFT calculations performed in Quantum Espresso. The alloys are constructed from all possible combinations of 37 metals into AB and A3B stoichiometries, in the L1_0 and L1_2 structures respectively, where the 37 metals in the A1 structure are included as well. Slabs are cleaved along the 111 facet for A1 and L1_2 and along the 101 facet for L1_0, and all possible adsorption sites are sampled. In addition to the monoatomic adsorbates, adsorption of CH, CH2, CH3, NH, NH2, OH, H2O and SH  is sampled for a smaller subset of alloys.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "0916e202-dba7-51ff-bdf4-313236feec32",
-    "notes": [
-        "We present a large dataset of adsorption of H, C, N, O and S onto more than 2,000 metallic and bimetallic alloy surfaces, consisting of approximately 90,000 DFT calculations performed in Quantum Espresso. The alloys are constructed from all possible combinations of 37 metals into AB and A3B stoichiometries, in the L1_0 and L1_2 structures respectively, where the 37 metals in the A1 structure are included as well. Slabs are cleaved along the 111 facet for A1 and L1_2 and along the 101 facet for L1_0, and all possible adsorption sites are sampled. In addition to the monoatomic adsorbates, adsorption of CH, CH2, CH3, NH, NH2, OH, H2O and SH  is sampled for a smaller subset of alloys."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0015/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "DFT"
-        },
-        {
-            "name": "Heterogeneous catalysis"
-        },
-        {
-            "name": "Chemisorption"
-        },
-        {
-            "name": "surfaces"
-        }
-    ],
-    "title": [
-        "High-throughput calculations of catalytic properties of bimetallic alloy surfaces"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0015/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/0ee31339-f267-5fcf-8f02-c64eb8f5260e.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/0ee31339-f267-5fcf-8f02-c64eb8f5260e.json
deleted file mode 100644
index a7913259..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/0ee31339-f267-5fcf-8f02-c64eb8f5260e.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0011/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0011/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0011/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-07-14T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Talirz, Leopold",
-        "Chidambaram, Arunraj",
-        "Smit, Berend",
-        "Haranczyk, Maciej",
-        "Stylianou, Kyriakos C.",
-        "Moosavi, Seyed Mohamad"
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0011/v1;2019-06-12Z;DOI;Dataset;Moosavi, Seyed Mohamad;Chidambaram, Arunraj;Talirz, Leopold;Haranczyk, Maciej;Stylianou, Kyriakos C.;Smit, Berend;Synthesis of Metal-Organic Frameworks: capturing chemical intuition;Materials Cloud;2018-07-14;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;Machine learning;Synthesis;Optimisation;Metal-Organic frameworks;MARVEL;doi:10.24435/materialscloud:2018.0011/v1;https://archive.materialscloud.org/2018.0011/v1;en;We report a methodology using machine learning to capture chemical intuition from a set of (partially) failed attempts to synthesize a metal organic framework. We define chemical intuition as the collection of unwritten guidelines used by synthetic chemists to find the right synthesis conditions. As (partially) failed experiments usually remain unreported, we have reconstructed a typical track of failed experiments in a successful search for finding the optimal synthesis conditions that yields HKUST-1 with the highest surface area reported to date. We illustrate the importance of quantifying this chemical intuition for the synthesis of novel materials.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "0ee31339-f267-5fcf-8f02-c64eb8f5260e",
-    "notes": [
-        "We report a methodology using machine learning to capture chemical intuition from a set of (partially) failed attempts to synthesize a metal organic framework. We define chemical intuition as the collection of unwritten guidelines used by synthetic chemists to find the right synthesis conditions. As (partially) failed experiments usually remain unreported, we have reconstructed a typical track of failed experiments in a successful search for finding the optimal synthesis conditions that yields HKUST-1 with the highest surface area reported to date. We illustrate the importance of quantifying this chemical intuition for the synthesis of novel materials."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0011/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Machine learning"
-        },
-        {
-            "name": "Synthesis"
-        },
-        {
-            "name": "Optimisation"
-        },
-        {
-            "name": "Metal-Organic frameworks"
-        },
-        {
-            "name": "MARVEL"
-        }
-    ],
-    "title": [
-        "Synthesis of Metal-Organic Frameworks: capturing chemical intuition"
-    ],
-    "url": "https://archive.materialscloud.org/2018.0011/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/1474c571-14f5-51bf-84da-d3137b3a4e30.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/1474c571-14f5-51bf-84da-d3137b3a4e30.json
deleted file mode 100644
index 201bb4a7..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/1474c571-14f5-51bf-84da-d3137b3a4e30.json
+++ /dev/null
@@ -1,92 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0015/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0015/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0015/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-09-28T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Pignedoli, Carlo Antonio",
-        "Golze,  Dorothea",
-        "Talirz, Leopold",
-        "Hutter,  J\u00fcrg",
-        "Wilhelm, Jan"
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0015/v1;2019-06-12Z;DOI;Dataset;Wilhelm, Jan;Golze,  Dorothea;Talirz, Leopold;Hutter,  J\u00fcrg;Pignedoli, Carlo Antonio;Toward GW Calculations on Thousands of Atoms;Materials Cloud;2018-09-28;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;DFT;MARVEL;GW;abinitio;graphene;nanoribbon;scaling;high performance computing;CP2K;doi:10.24435/materialscloud:2018.0015/v1;https://archive.materialscloud.org/2018.0015/v1;en;We provide the input files needed to reproduce the results of the article\n<br/>\n\n<br/>\nToward GW Calculations on Thousands of Atoms\n<br/>\nJ. Wilhelm, D. Golze, L. Talirz, J. Hutter, C. A. Pignedoli\n<br/>\nJ. Phys. Chem. Lett.  9, 306\u2013312 (2018) DOI:10.1021/acs.jpclett.7b02740\n<br/>\n\n<br/>\nThe GW approximation of many-body perturbation theory is an accurate method\n<br/>\nfor computing electron addition and removal energies of molecules and solids.\n<br/>\nIn a canonical implementation, however, its computational cost is  in the\n<br/>\nsystem size N, which prohibits its application to many systems of interest.\n<br/>\nWe present a full-frequency GW algorithm in a Gaussian-type basis,\n<br/>\nwhose computational cost scales with N2 to N3.\n<br/>\nThe implementation is optimized for massively parallel execution on\n<br/>\nstate-of-the-art supercomputers and is suitable for nanostructures and molecules in the gas,\n<br/>\nliquid or condensed phase, using either pseudopotentials or all electrons.\n<br/>\nWe validate the accuracy of the algorithm on the GW100 molecular test set,\n<br/>\nfinding mean absolute deviations of 35 meV for ionization potentials and 27 meV\n<br/>\nfor electron affinities. Furthermore, we study the length-dependence of quasiparticle\n<br/>\nenergies in armchair graphene nanoribbons of up to 1734 atoms in size, and compute the\n<br/>\nlocal density of states across a nanoscale heterojunction.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "1474c571-14f5-51bf-84da-d3137b3a4e30",
-    "notes": [
-        "We provide the input files needed to reproduce the results of the article\n<br/>\n\n<br/>\nToward GW Calculations on Thousands of Atoms\n<br/>\nJ. Wilhelm, D. Golze, L. Talirz, J. Hutter, C. A. Pignedoli\n<br/>\nJ. Phys. Chem. Lett.  9, 306\u2013312 (2018) DOI:10.1021/acs.jpclett.7b02740\n<br/>\n\n<br/>\nThe GW approximation of many-body perturbation theory is an accurate method\n<br/>\nfor computing electron addition and removal energies of molecules and solids.\n<br/>\nIn a canonical implementation, however, its computational cost is  in the\n<br/>\nsystem size N, which prohibits its application to many systems of interest.\n<br/>\nWe present a full-frequency GW algorithm in a Gaussian-type basis,\n<br/>\nwhose computational cost scales with N2 to N3.\n<br/>\nThe implementation is optimized for massively parallel execution on\n<br/>\nstate-of-the-art supercomputers and is suitable for nanostructures and molecules in the gas,\n<br/>\nliquid or condensed phase, using either pseudopotentials or all electrons.\n<br/>\nWe validate the accuracy of the algorithm on the GW100 molecular test set,\n<br/>\nfinding mean absolute deviations of 35 meV for ionization potentials and 27 meV\n<br/>\nfor electron affinities. Furthermore, we study the length-dependence of quasiparticle\n<br/>\nenergies in armchair graphene nanoribbons of up to 1734 atoms in size, and compute the\n<br/>\nlocal density of states across a nanoscale heterojunction."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0015/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "DFT"
-        },
-        {
-            "name": "MARVEL"
-        },
-        {
-            "name": "GW"
-        },
-        {
-            "name": "abinitio"
-        },
-        {
-            "name": "graphene"
-        },
-        {
-            "name": "nanoribbon"
-        },
-        {
-            "name": "scaling"
-        },
-        {
-            "name": "high performance computing"
-        },
-        {
-            "name": "CPK"
-        }
-    ],
-    "title": [
-        "Toward GW Calculations on Thousands of Atoms"
-    ],
-    "url": "https://archive.materialscloud.org/2018.0015/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/1517d617-6ccc-5aaf-a494-3b21b33729d4.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/1517d617-6ccc-5aaf-a494-3b21b33729d4.json
deleted file mode 100644
index b6264700..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/1517d617-6ccc-5aaf-a494-3b21b33729d4.json
+++ /dev/null
@@ -1,108 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2017.0008/v2",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2017.0008/v2",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2017.0008/v2"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-03-21T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "RelatedIdentifier": [
-        "https://www.materialscloud.org/discover/2dstructures",
-        "https://www.materialscloud.org/explore/2dstructures"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Marzari, Nicola",
-        "Campi, Davide",
-        "Cepellotti, Andrea",
-        "Schwaller, Philippe",
-        "Gibertini, Marco",
-        "Castelli, Ivano E.",
-        "Marrazzo, Antimo",
-        "Sohier, Thibault",
-        "Mounet, Nicolas",
-        "Pizzi, Giovanni",
-        "Merkys, Andrius"
-    ],
-    "fulltext": "oai:materialscloud.org:2017.0008/v2;2019-06-12Z;DOI;Dataset;Mounet, Nicolas;Gibertini, Marco;Schwaller, Philippe;Campi, Davide;Merkys, Andrius;Marrazzo, Antimo;Sohier, Thibault;Castelli, Ivano E.;Cepellotti, Andrea;Pizzi, Giovanni;Marzari, Nicola;Two-dimensional materials from high-throughput computational exfoliation of  experimentally known compounds;Materials Cloud;2018-03-21;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;2D;two-dimensional;monolayer;database;high-throughput;DFT;vibrational properties;phonons;electronic properties;electronic bands;magnetic properties;MARVEL;doi:10.24435/materialscloud:2017.0008/v2;https://archive.materialscloud.org/2017.0008/v2;en;https://www.materialscloud.org/discover/2dstructures;https://www.materialscloud.org/explore/2dstructures;Two-dimensional (2D) materials have emerged as promising candidates for next-generation electronic and optoelectronic applications. Yet, only a few dozens of 2D materials have been successfully synthesized or exfoliated. Here, we search for novel 2D materials that can be easily exfoliated from their parent compounds. Starting from 108423 unique, experimentally known three-dimensional compounds we identify a subset of 5619 that appear layered according to robust geometric and bonding criteria. High-throughput calculations using van-der-Waals density-functional theory, validated against experimental structural data and calculated random-phase-approximation binding energies, allow to identify 1825 compounds that are either easily or potentially exfoliable. In particular, the subset of 1036 easily exfoliable cases provides novel structural prototypes and simple ternary compounds as well as a large portfolio of materials to search from for optimal properties. For a subset of 258 compounds we explore vibrational, electronic, magnetic, and topological properties, identifying 56 ferromagnetic and antiferromagnetic systems, including half-metals and half-semiconductors. This archive entry contains the database of 2D materials (structural parameters, band structures, binding energies, etc.) together with the provenance of all data and calculations as stored by AiiDA.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "1517d617-6ccc-5aaf-a494-3b21b33729d4",
-    "notes": [
-        "Two-dimensional (2D) materials have emerged as promising candidates for next-generation electronic and optoelectronic applications. Yet, only a few dozens of 2D materials have been successfully synthesized or exfoliated. Here, we search for novel 2D materials that can be easily exfoliated from their parent compounds. Starting from 108423 unique, experimentally known three-dimensional compounds we identify a subset of 5619 that appear layered according to robust geometric and bonding criteria. High-throughput calculations using van-der-Waals density-functional theory, validated against experimental structural data and calculated random-phase-approximation binding energies, allow to identify 1825 compounds that are either easily or potentially exfoliable. In particular, the subset of 1036 easily exfoliable cases provides novel structural prototypes and simple ternary compounds as well as a large portfolio of materials to search from for optimal properties. For a subset of 258 compounds we explore vibrational, electronic, magnetic, and topological properties, identifying 56 ferromagnetic and antiferromagnetic systems, including half-metals and half-semiconductors. This archive entry contains the database of 2D materials (structural parameters, band structures, binding energies, etc.) together with the provenance of all data and calculations as stored by AiiDA."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2017.0008/v2"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "two-dimensional"
-        },
-        {
-            "name": "monolayer"
-        },
-        {
-            "name": "database"
-        },
-        {
-            "name": "high-throughput"
-        },
-        {
-            "name": "DFT"
-        },
-        {
-            "name": "vibrational properties"
-        },
-        {
-            "name": "phonons"
-        },
-        {
-            "name": "electronic properties"
-        },
-        {
-            "name": "electronic bands"
-        },
-        {
-            "name": "magnetic properties"
-        },
-        {
-            "name": "MARVEL"
-        }
-    ],
-    "title": [
-        "Two-dimensional materials from high-throughput computational exfoliation of  experimentally known compounds"
-    ],
-    "url": "https://archive.materialscloud.org/2017.0008/v2"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/16c2ed27-2be7-5ece-a593-45f8a60176a2.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/16c2ed27-2be7-5ece-a593-45f8a60176a2.json
deleted file mode 100644
index 42339016..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/16c2ed27-2be7-5ece-a593-45f8a60176a2.json
+++ /dev/null
@@ -1,100 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0019/v2",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0019/v2",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0019/v2"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-05-21T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "RelatedIdentifier": [
-        "https://www.materialscloud.org/discover/topomat"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution Non Commercial 4.0 International https://creativecommons.org/licenses/by-nc/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Mounet, Nicolas",
-        "Wu, QuanSheng",
-        "Yazyev, Oleg V.",
-        "Autes, Gabriel"
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0019/v2;2019-06-12Z;DOI;Dataset;Autes, Gabriel;Wu, QuanSheng;Mounet, Nicolas;Yazyev, Oleg V.;TopoMat: a database of high-throughput first-principles calculations of topological materials;Materials Cloud;2019-05-21;Creative Commons Attribution Non Commercial 4.0 International https://creativecommons.org/licenses/by-nc/4.0/legalcode;info:eu-repo/semantics/openAccess;MARVEL;MARVEL/DD6;Topological materials;Database;TopoMat;QUANTUM ESPRESSO;Z2 topological number;spin-orbit coupling;topological insulators;topological semimetals;high-throughput screening;doi:10.24435/materialscloud:2019.0019/v2;https://archive.materialscloud.org/2019.0019/v2;en;https://www.materialscloud.org/discover/topomat;We present a database of topological materials predicted from high-throughput first-principles calculations. The database contains electronic band structures and topological indices of 13628 materials calculated on experimental crystal structures taken from the Inorganic Crystal Structure Database (ICSD) and the Crystallography Open Database (COD). The calculations have been performed on non-magnetic phases taking into account the spin-orbit interactions using the Quantum ESPRESSO package. The Fu-Kane method and the Wannier charge center method implemented in the Z2pack code have been utilized to calculate the Z2 topological numbers of centrosymmetric and non-centrosymmetric materials, respectively. Over 4000 topologically non-trivial materials have been identified.\n<br/>\n",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "16c2ed27-2be7-5ece-a593-45f8a60176a2",
-    "notes": [
-        "We present a database of topological materials predicted from high-throughput first-principles calculations. The database contains electronic band structures and topological indices of 13628 materials calculated on experimental crystal structures taken from the Inorganic Crystal Structure Database (ICSD) and the Crystallography Open Database (COD). The calculations have been performed on non-magnetic phases taking into account the spin-orbit interactions using the Quantum ESPRESSO package. The Fu-Kane method and the Wannier charge center method implemented in the Z2pack code have been utilized to calculate the Z2 topological numbers of centrosymmetric and non-centrosymmetric materials, respectively. Over 4000 topologically non-trivial materials have been identified.\n<br/>\n"
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0019/v2"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "MARVEL"
-        },
-        {
-            "name": "MARVEL DD"
-        },
-        {
-            "name": "Topological materials"
-        },
-        {
-            "name": "Database"
-        },
-        {
-            "name": "TopoMat"
-        },
-        {
-            "name": "QUANTUM ESPRESSO"
-        },
-        {
-            "name": "Z topological number"
-        },
-        {
-            "name": "spin-orbit coupling"
-        },
-        {
-            "name": "topological insulators"
-        },
-        {
-            "name": "topological semimetals"
-        },
-        {
-            "name": "high-throughput screening"
-        }
-    ],
-    "title": [
-        "TopoMat: a database of high-throughput first-principles calculations of topological materials"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0019/v2"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/18131c19-f2f1-5cc4-980b-033fb0d02d98.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/18131c19-f2f1-5cc4-980b-033fb0d02d98.json
deleted file mode 100644
index 2f1d83b0..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/18131c19-f2f1-5cc4-980b-033fb0d02d98.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0022/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0022/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0022/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-05-27T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Rybkin, Vladimir"
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0022/v1;2019-06-12Z;DOI;Dataset;Rybkin, Vladimir;Dynamics of the Bulk Hydrated Electron from Many\u2010Body Wave\u2010Function Theory;Materials Cloud;2019-05-27;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;MARVEL;molecular dynamics;spin density;hydrated electron;solvated electron;many-body methods;electronic structure;doi:10.24435/materialscloud:2019.0022/v1;https://archive.materialscloud.org/2019.0022/v1;en;Trajectories and spin densities for the bulk hydrated electron at the MP2 level of theory.  The data represent the first ab initio molecular dynamics study of the hydrated electron in the bulk using many-body wave function theory.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "18131c19-f2f1-5cc4-980b-033fb0d02d98",
-    "notes": [
-        "Trajectories and spin densities for the bulk hydrated electron at the MP2 level of theory.  The data represent the first ab initio molecular dynamics study of the hydrated electron in the bulk using many-body wave function theory."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0022/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "MARVEL"
-        },
-        {
-            "name": "molecular dynamics"
-        },
-        {
-            "name": "spin density"
-        },
-        {
-            "name": "hydrated electron"
-        },
-        {
-            "name": "solvated electron"
-        },
-        {
-            "name": "many-body methods"
-        },
-        {
-            "name": "electronic structure"
-        }
-    ],
-    "title": [
-        "Dynamics of the Bulk Hydrated Electron from Many\u2010Body Wave\u2010Function Theory"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0022/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/1ac0cd23-1880-550e-bbbc-3509d163b9b2.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/1ac0cd23-1880-550e-bbbc-3509d163b9b2.json
deleted file mode 100644
index 7bbbb0bf..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/1ac0cd23-1880-550e-bbbc-3509d163b9b2.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0016/v2",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0016/v2",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0016/v2"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-05-07T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Piaggi, Pablo M.",
-        "Parrinello, Michele"
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0016/v2;2019-06-12Z;DOI;Dataset;Piaggi, Pablo M.;Parrinello, Michele;Multithermal-multibaric molecular simulations from a variational principle;Materials Cloud;2019-05-07;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;enhanced sampling;multithermal-multibaric; water;density anomaly;Wang Landau;multicanonical;doi:10.24435/materialscloud:2019.0016/v2;https://archive.materialscloud.org/2019.0016/v2;en;We present a method for performing multithermal-multibaric molecular dynamics simulations that sample entire regions of the temperature-pressure (TP) phase diagram. The method uses a variational principle [Valsson and Parrinello, Phys. Rev. Lett. 113, 090601 (2014)] in order to construct a bias that leads to a uniform sampling in energy and volume. The intervals of temperature and pressure are taken as inputs and the relevant energy and volume regions are determined on the fly. In this way the method guarantees adequate statistics for the chosen TP region. We show that our multithermal-multibaric simulations can be used to calculate all static physical quantities for all temperatures and pressures in the targeted region of the TP plane. We illustrate our approach by studying the density anomaly of TIP4P/Ice water.\n<br/>\n\n<br/>\nThis record includes input and output files, and Jupyter Notebooks describing the analysis of the simulations and the creation of the figures for the paper.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "1ac0cd23-1880-550e-bbbc-3509d163b9b2",
-    "notes": [
-        "We present a method for performing multithermal-multibaric molecular dynamics simulations that sample entire regions of the temperature-pressure (TP) phase diagram. The method uses a variational principle [Valsson and Parrinello, Phys. Rev. Lett. 113, 090601 (2014)] in order to construct a bias that leads to a uniform sampling in energy and volume. The intervals of temperature and pressure are taken as inputs and the relevant energy and volume regions are determined on the fly. In this way the method guarantees adequate statistics for the chosen TP region. We show that our multithermal-multibaric simulations can be used to calculate all static physical quantities for all temperatures and pressures in the targeted region of the TP plane. We illustrate our approach by studying the density anomaly of TIP4P/Ice water.\n<br/>\n\n<br/>\nThis record includes input and output files, and Jupyter Notebooks describing the analysis of the simulations and the creation of the figures for the paper."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0016/v2"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "enhanced sampling"
-        },
-        {
-            "name": "multithermal-multibaric"
-        },
-        {
-            "name": "water"
-        },
-        {
-            "name": "density anomaly"
-        },
-        {
-            "name": "Wang Landau"
-        },
-        {
-            "name": "multicanonical"
-        }
-    ],
-    "title": [
-        "Multithermal-multibaric molecular simulations from a variational principle"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0016/v2"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/1dc5ad3c-da7d-509b-aebd-ed7b6e9178f4.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/1dc5ad3c-da7d-509b-aebd-ed7b6e9178f4.json
deleted file mode 100644
index dc24626a..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/1dc5ad3c-da7d-509b-aebd-ed7b6e9178f4.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0023/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0023/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0023/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-05-27T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Paruzzo, Federico",
-        "Emsley, Lyndon",
-        "Musil, F\u00e9lix",
-        "De, Sandip",
-        "Ceriotti, Michele",
-        "Hofstetter, Albert"
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0023/v1;2019-06-12Z;DOI;Dataset;Paruzzo, Federico;Hofstetter, Albert;Musil, F\u00e9lix;Ceriotti, Michele;Emsley, Lyndon;De, Sandip;Chemical Shifts in Molecular Solids by Machine Learning Datasets;Materials Cloud;2019-05-27;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;MARVEL;NMR;Quantum Espresso;GIPAW;Energy Calculations; Organic Solids;Chemical Shifts;doi:10.24435/materialscloud:2019.0023/v1;https://archive.materialscloud.org/2019.0023/v1;en;We present a database of energy and NMR chemical shifts DFT calculations of 2500 crystal organic solids. The structures contain only H/C/N/O atoms and were subject to all-atoms geometry optimisation. Calculations were carried out using Quantum Espresso and GIPAW.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "1dc5ad3c-da7d-509b-aebd-ed7b6e9178f4",
-    "notes": [
-        "We present a database of energy and NMR chemical shifts DFT calculations of 2500 crystal organic solids. The structures contain only H/C/N/O atoms and were subject to all-atoms geometry optimisation. Calculations were carried out using Quantum Espresso and GIPAW."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0023/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "MARVEL"
-        },
-        {
-            "name": "NMR"
-        },
-        {
-            "name": "Quantum Espresso"
-        },
-        {
-            "name": "GIPAW"
-        },
-        {
-            "name": "Energy Calculations"
-        },
-        {
-            "name": "Organic Solids"
-        },
-        {
-            "name": "Chemical Shifts"
-        }
-    ],
-    "title": [
-        "Chemical Shifts in Molecular Solids by Machine Learning Datasets"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0023/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/1e033182-b94e-5537-9870-9e18266bd70f.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/1e033182-b94e-5537-9870-9e18266bd70f.json
deleted file mode 100644
index 50aff09f..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/1e033182-b94e-5537-9870-9e18266bd70f.json
+++ /dev/null
@@ -1,91 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0009/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0009/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0009/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-05-19T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Grisafi, Andrea",
-        "Cs\u00e1nyi, Gabor",
-        "Ceriotti, Michele",
-        "Wilkins, David M."
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0009/v1;2019-06-12Z;DOI;Dataset;Grisafi, Andrea;Wilkins, David M.;Cs\u00e1nyi, Gabor;Ceriotti, Michele;Symmetry-Adapted Machine Learning for Tensorial Properties of Atomistic Systems;Materials Cloud;2018-05-19;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;water;molecular;bulk;dipole moment;polarizability;hyperpolarizability;dielectric tensor;symmetry-adapted gaussian process regression;machine learning;doi:10.24435/materialscloud:2018.0009/v1;https://archive.materialscloud.org/2018.0009/v1;en;Here we present 1,000 structures each of a water monomer, water dimer, Zundel cation and bulk water used to train tensorial machine-learning models in Phys. Rev. Lett. 120, 036002 (2018). The archive entry contains files in extended-XYZ format including the structures and several tensorial properties: for the monomer, dimer and Zundel cation, the dipole moment, polarizability and first hyperpolarizability are included, and for bulk water the dipole moment, polarizability and dielectric tensor are given.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "1e033182-b94e-5537-9870-9e18266bd70f",
-    "notes": [
-        "Here we present 1,000 structures each of a water monomer, water dimer, Zundel cation and bulk water used to train tensorial machine-learning models in Phys. Rev. Lett. 120, 036002 (2018). The archive entry contains files in extended-XYZ format including the structures and several tensorial properties: for the monomer, dimer and Zundel cation, the dipole moment, polarizability and first hyperpolarizability are included, and for bulk water the dipole moment, polarizability and dielectric tensor are given."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0009/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "water"
-        },
-        {
-            "name": "molecular"
-        },
-        {
-            "name": "bulk"
-        },
-        {
-            "name": "dipole moment"
-        },
-        {
-            "name": "polarizability"
-        },
-        {
-            "name": "hyperpolarizability"
-        },
-        {
-            "name": "dielectric tensor"
-        },
-        {
-            "name": "symmetry-adapted gaussian process regression"
-        },
-        {
-            "name": "machine learning"
-        }
-    ],
-    "title": [
-        "Symmetry-Adapted Machine Learning for Tensorial Properties of Atomistic Systems"
-    ],
-    "url": "https://archive.materialscloud.org/2018.0009/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/1eabe491-6a73-5a9a-8523-d5be104fc74f.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/1eabe491-6a73-5a9a-8523-d5be104fc74f.json
deleted file mode 100644
index b717636c..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/1eabe491-6a73-5a9a-8523-d5be104fc74f.json
+++ /dev/null
@@ -1,105 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0001/v3",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0001/v3",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0001/v3"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-11-08T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "RelatedIdentifier": [
-        "https://www.materialscloud.org/discover/sssp",
-        "https://www.materialscloud.org/explore/sssp"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Castelli, Ivano E.",
-        "Mounet, Nicolas",
-        "Marzari, Nicola",
-        "Marrazzo, Antimo",
-        "Prandini, Gianluca"
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0001/v3;2019-06-12Z;DOI;Dataset;Prandini, Gianluca;Marrazzo, Antimo;Castelli, Ivano E.;Mounet, Nicolas;Marzari, Nicola;A Standard Solid State Pseudopotentials (SSSP) library optimized for precision and efficiency (Version 1.1, data download);Materials Cloud;2018-11-08;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;SSSP;pseudopotentials;database;high-throughput;library;standard;DFT;calculations;vibrational properties;phonons;electronic properties;electronic bands;cohesive energy;chessboards;elemental solids;verification;precision;efficiency;MARVEL;doi:10.24435/materialscloud:2018.0001/v3;https://archive.materialscloud.org/2018.0001/v3;en;https://www.materialscloud.org/discover/sssp;https://www.materialscloud.org/explore/sssp;Despite the enormous success and popularity of density functional theory, systematic verification and validation studies are still very limited both in number and scope. Here, we propose a universal standard protocol to verify publicly available pseudopotential libraries, based on several independent criteria including verification against all-electron equations of state and plane-wave convergence tests for phonon frequencies, band structure, cohesive energy and pressure. Adopting these criteria we obtain two optimal pseudopotential sets, namely the Standard Solid State Pseudopotential (SSSP) efficiency and precision libraries, tailored for high-throughput materials screening and high-precision materials modelling. As of today, the SSSP precision library is the most accurate open-source pseudopotential library available. This archive entry contains the database of calculations (phonons, cohesive energy, equation of state, band structure, pressure, etc.) together with the provenance of all data and calculations as stored by AiiDA.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "1eabe491-6a73-5a9a-8523-d5be104fc74f",
-    "notes": [
-        "Despite the enormous success and popularity of density functional theory, systematic verification and validation studies are still very limited both in number and scope. Here, we propose a universal standard protocol to verify publicly available pseudopotential libraries, based on several independent criteria including verification against all-electron equations of state and plane-wave convergence tests for phonon frequencies, band structure, cohesive energy and pressure. Adopting these criteria we obtain two optimal pseudopotential sets, namely the Standard Solid State Pseudopotential (SSSP) efficiency and precision libraries, tailored for high-throughput materials screening and high-precision materials modelling. As of today, the SSSP precision library is the most accurate open-source pseudopotential library available. This archive entry contains the database of calculations (phonons, cohesive energy, equation of state, band structure, pressure, etc.) together with the provenance of all data and calculations as stored by AiiDA."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0001/v3"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "SSSP"
-        },
-        {
-            "name": "pseudopotentials"
-        },
-        {
-            "name": "database"
-        },
-        {
-            "name": "high-throughput"
-        },
-        {
-            "name": "library"
-        },
-        {
-            "name": "standard"
-        },
-        {
-            "name": "DFT"
-        },
-        {
-            "name": "calculations"
-        },
-        {
-            "name": "vibrational properties"
-        },
-        {
-            "name": "phonons"
-        },
-        {
-            "name": "electronic properties"
-        },
-        {
-            "name": "electronic bands"
-        }
-    ],
-    "title": [
-        "A Standard Solid State Pseudopotentials (SSSP) library optimized for precision and efficiency (Version 1.1, data download)"
-    ],
-    "url": "https://archive.materialscloud.org/2018.0001/v3"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/2756811f-15cb-58d3-8a75-2687b8c68c64.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/2756811f-15cb-58d3-8a75-2687b8c68c64.json
deleted file mode 100644
index 58986d2a..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/2756811f-15cb-58d3-8a75-2687b8c68c64.json
+++ /dev/null
@@ -1,95 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0007/v2",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0007/v2",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0007/v2"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-11-14T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Jariwala, Kuldeep",
-        "Haranczyk, Maciej",
-        "Lin, Li-Chiang",
-        "Martin, Richard L.",
-        "Smit, Berend"
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0007/v2;2019-06-12Z;DOI;Dataset;Martin, Richard L.;Lin, Li-Chiang;Jariwala, Kuldeep;Smit, Berend;Haranczyk, Maciej;Mail-order metal-organic frameworks (MOFs): designing isoreticular MOF-5 analogues comprising commercially available organic molecules;Materials Cloud;2018-11-14;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;3D;three-dimensional;database;high-throughput;MOF-5;nanoporous;methane storage;deliverable capacities;DC;grand canonical Monte Carlo;GCMC;doi:10.24435/materialscloud:2018.0007/v2;https://archive.materialscloud.org/2018.0007/v2;en;Metal\u2013organic frameworks (MOFs), a class of porous materials, are of particular interest in gas storage and separation applications due largely to their high internal surface areas and tunable structures. MOF-5 is perhaps the archetypal MOF; in particular, many isoreticular analogues of MOF-5 have been synthesized, comprising alternative dicarboxylic acid ligands. In this contribution we introduce a new set of hypothesized MOF-5 analogues, constructed from commercially available organic molecules. We describe our automated procedure for hypothetical MOF design, comprising selection of appropriate ligands, construction of 3D structure models, and structure relaxation methods. 116 MOF-5 analogues were designed and characterized in terms of geometric properties and simulated methane uptake at conditions relevant to vehicular storage applications. A strength of the presented approach is that all of the hypothesized MOFs are designed to be synthesizable utilizing ligands purchasable online.<br/>\n<br/>\nVersion 2 includes the structures in CIF format.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "2756811f-15cb-58d3-8a75-2687b8c68c64",
-    "notes": [
-        "Metal\u2013organic frameworks (MOFs), a class of porous materials, are of particular interest in gas storage and separation applications due largely to their high internal surface areas and tunable structures. MOF-5 is perhaps the archetypal MOF; in particular, many isoreticular analogues of MOF-5 have been synthesized, comprising alternative dicarboxylic acid ligands. In this contribution we introduce a new set of hypothesized MOF-5 analogues, constructed from commercially available organic molecules. We describe our automated procedure for hypothetical MOF design, comprising selection of appropriate ligands, construction of 3D structure models, and structure relaxation methods. 116 MOF-5 analogues were designed and characterized in terms of geometric properties and simulated methane uptake at conditions relevant to vehicular storage applications. A strength of the presented approach is that all of the hypothesized MOFs are designed to be synthesizable utilizing ligands purchasable online.<br/>\n<br/>\nVersion 2 includes the structures in CIF format."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0007/v2"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "three-dimensional"
-        },
-        {
-            "name": "database"
-        },
-        {
-            "name": "high-throughput"
-        },
-        {
-            "name": "MOF-"
-        },
-        {
-            "name": "nanoporous"
-        },
-        {
-            "name": "methane storage"
-        },
-        {
-            "name": "deliverable capacities"
-        },
-        {
-            "name": "DC"
-        },
-        {
-            "name": "grand canonical Monte Carlo"
-        },
-        {
-            "name": "GCMC"
-        }
-    ],
-    "title": [
-        "Mail-order metal-organic frameworks (MOFs): designing isoreticular MOF-5 analogues comprising commercially available organic molecules"
-    ],
-    "url": "https://archive.materialscloud.org/2018.0007/v2"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/2e1dccb6-3da1-5b7f-98e9-30f5b2de6ae4.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/2e1dccb6-3da1-5b7f-98e9-30f5b2de6ae4.json
deleted file mode 100644
index 1dd43351..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/2e1dccb6-3da1-5b7f-98e9-30f5b2de6ae4.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2017.0005/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2017.0005/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2017.0005/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2017-05-18T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Ongari, Daniele",
-        "Barthel, Senja",
-        "Smit, Berend",
-        "Witman, Matthew",
-        "Boyd, Peter G.",
-        "Haranczyk, Maciej"
-    ],
-    "fulltext": "oai:materialscloud.org:2017.0005/v1;2019-06-12Z;DOI;Dataset;Ongari, Daniele;Boyd, Peter G.;Barthel, Senja;Witman, Matthew;Haranczyk, Maciej;Smit, Berend;Accurate Characterization of the Pore Volume in Microporous Crystalline Materials (Data Download);Materials Cloud;2017-05-18;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;Nanoporous materials;Pore volume;Void fraction;MARVEL;doi:10.24435/materialscloud:2017.0005/v1;https://archive.materialscloud.org/2017.0005/v1;en;Project Abstract: Pore volume is one of the main properties for the characterization of microporous crystals. It is experimentally measurable and it can also be obtained from the refined unit cell by a number of computational techniques. In this work we assess the accuracy and the discrepancies between the different computational methods which are commonly used for this purpose, i.e, geometric, helium and probe center pore volume, by studying a database of more than 5000 frameworks. We developed a new technique to fully characterize the internal void of a microporous material and to compute the probe accessible and occupiable pore volume. We show that unlike the other definitions of pore volume, the occupiable pore volume can be directly related to the experimentally measured pore volumes from nitrogen isotherms.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "2e1dccb6-3da1-5b7f-98e9-30f5b2de6ae4",
-    "notes": [
-        "Project Abstract: Pore volume is one of the main properties for the characterization of microporous crystals. It is experimentally measurable and it can also be obtained from the refined unit cell by a number of computational techniques. In this work we assess the accuracy and the discrepancies between the different computational methods which are commonly used for this purpose, i.e, geometric, helium and probe center pore volume, by studying a database of more than 5000 frameworks. We developed a new technique to fully characterize the internal void of a microporous material and to compute the probe accessible and occupiable pore volume. We show that unlike the other definitions of pore volume, the occupiable pore volume can be directly related to the experimentally measured pore volumes from nitrogen isotherms."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2017.0005/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Nanoporous materials"
-        },
-        {
-            "name": "Pore volume"
-        },
-        {
-            "name": "Void fraction"
-        },
-        {
-            "name": "MARVEL"
-        }
-    ],
-    "title": [
-        "Accurate Characterization of the Pore Volume in Microporous Crystalline Materials (Data Download)"
-    ],
-    "url": "https://archive.materialscloud.org/2017.0005/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/2fe235af-34fc-5285-993f-5d6ffda2f3bd.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/2fe235af-34fc-5285-993f-5d6ffda2f3bd.json
deleted file mode 100644
index 0d437ade..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/2fe235af-34fc-5285-993f-5d6ffda2f3bd.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0016/v2",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0016/v2",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0016/v2"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-11-25T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Daff, Thomas D.",
-        "G\u0142adysiak, Andrzej",
-        "Chidambaram, Arunraj",
-        "Navarro, Jorge A. R.",
-        "Bounds, Richard",
-        "Smit, Berend",
-        "Woo, Tom K.",
-        "Boyd, Peter George",
-        "Schouwink, Pascal",
-        "Reimer, Jeffrey A.",
-        "Stylianou, Kyriakos C.",
-        "Moosavi, Seyed Mohamad"
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0016/v2;2019-06-12Z;DOI;Dataset;Boyd, Peter George;Chidambaram, Arunraj;Daff, Thomas D.;Bounds, Richard;G\u0142adysiak, Andrzej;Schouwink, Pascal;Moosavi, Seyed Mohamad;Reimer, Jeffrey A.;Navarro, Jorge A. R.;Woo, Tom K.;Smit, Berend;Stylianou, Kyriakos C.;Data-driven design and synthesis of metal-organic frameworks for wet flue gas CO2 capture;Materials Cloud;2018-11-25;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;nanoporous materials;high throughput screening;gas adsorption;co2 capture;adsorbaphore;doi:10.24435/materialscloud:2018.0016/v2;https://archive.materialscloud.org/2018.0016/v2;en;In this entry is a database of 324,426 hypothetical Metal-Organic Frameworks (MOFs) that were used in a study to screen potential carbon dioxide scrubbers.  Using a method to assemble these materials with topological blueprints, we only selected materials that could be accurately represented with the MEPO-QEq charge generation method. By ensuring that the electrostatic potential is accurately represented in these materials, screening for CO2 adsorption properties would result very few false positives/negatives. The atom-centered charges reported in the CIF file for each MOF were derived from the MEPO-QEq method, which can be found under the &#39;_atom_type_partial_charge&#39; column in each CIF file.\n<br/>\n\n<br/>\nThe relevant data for each MOF is reported in accompanying .csv files. Post-combustion flue gas was simulated at a temperature of both 298K and 0.15 bar CO2, and 313K and 0.15 bar CO2. Mixture adsorption was simulated with the conditions 298K and 0.15:0.85 CO2/N2 with a total pressure of 1 bar. The data file reports working capacities, which is the difference of adsorption of CO2 between two thermodynamic state points. The adsorption state point(s) are mentioned above, and two desorption values were simulated; 0.1 bar CO2 at 363K (vacuum swing adsorption) and 0.7 bar CO2 at 413K (temperature swing adsorption). The data presented in the main manuscript correspond to vacuum swing conditions.\n<br/>\n\n<br/>\nOver 8,000 materials were selected for more refined simulations, including re-defining partial atomic charges with the REPEAT method, and more detailed simulations to obtain common chemical patterns surrounding CO2 binding sites (adsorbaphores). There is an additional .csv file with these refined calculations that accompany this entry titled &#39;top_MOFs_screening_data.csv&#39;.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "2fe235af-34fc-5285-993f-5d6ffda2f3bd",
-    "notes": [
-        "In this entry is a database of 324,426 hypothetical Metal-Organic Frameworks (MOFs) that were used in a study to screen potential carbon dioxide scrubbers.  Using a method to assemble these materials with topological blueprints, we only selected materials that could be accurately represented with the MEPO-QEq charge generation method. By ensuring that the electrostatic potential is accurately represented in these materials, screening for CO2 adsorption properties would result very few false positives/negatives. The atom-centered charges reported in the CIF file for each MOF were derived from the MEPO-QEq method, which can be found under the &#39;_atom_type_partial_charge&#39; column in each CIF file.\n<br/>\n\n<br/>\nThe relevant data for each MOF is reported in accompanying .csv files. Post-combustion flue gas was simulated at a temperature of both 298K and 0.15 bar CO2, and 313K and 0.15 bar CO2. Mixture adsorption was simulated with the conditions 298K and 0.15:0.85 CO2/N2 with a total pressure of 1 bar. The data file reports working capacities, which is the difference of adsorption of CO2 between two thermodynamic state points. The adsorption state point(s) are mentioned above, and two desorption values were simulated; 0.1 bar CO2 at 363K (vacuum swing adsorption) and 0.7 bar CO2 at 413K (temperature swing adsorption). The data presented in the main manuscript correspond to vacuum swing conditions.\n<br/>\n\n<br/>\nOver 8,000 materials were selected for more refined simulations, including re-defining partial atomic charges with the REPEAT method, and more detailed simulations to obtain common chemical patterns surrounding CO2 binding sites (adsorbaphores). There is an additional .csv file with these refined calculations that accompany this entry titled &#39;top_MOFs_screening_data.csv&#39;."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0016/v2"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "nanoporous materials"
-        },
-        {
-            "name": "high throughput screening"
-        },
-        {
-            "name": "gas adsorption"
-        },
-        {
-            "name": "co capture"
-        },
-        {
-            "name": "adsorbaphore"
-        }
-    ],
-    "title": [
-        "Data-driven design and synthesis of metal-organic frameworks for wet flue gas CO2 capture"
-    ],
-    "url": "https://archive.materialscloud.org/2018.0016/v2"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/3b853531-4456-5ed2-ae02-55032a1229d2.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/3b853531-4456-5ed2-ae02-55032a1229d2.json
deleted file mode 100644
index 209702e2..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/3b853531-4456-5ed2-ae02-55032a1229d2.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0011/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0011/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0011/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-03-11T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Mace, Amber",
-        "Smit, Berend",
-        "Barthel, Senja"
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0011/v1;2019-06-12Z;DOI;Dataset;Mace, Amber;Barthel, Senja;Smit, Berend;TuTraST data for methane diffusion in IZA structures;Materials Cloud;2019-03-11;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;MARVEL;TuTraST;diffusion;methane;zeolite;transition state theory;kinetic monte carlo;doi:10.24435/materialscloud:2019.0011/v1;https://archive.materialscloud.org/2019.0011/v1;en;Data for the case study of TuTraSt on methane diffusion in zeolites, using a standard kinetic Monte Carlo simulation based on the output of our grid analysis. We find that it is accurate, fast, and rigorous without limitations to the geometries of the diffusion tunnels or transition states. ",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "3b853531-4456-5ed2-ae02-55032a1229d2",
-    "notes": [
-        "Data for the case study of TuTraSt on methane diffusion in zeolites, using a standard kinetic Monte Carlo simulation based on the output of our grid analysis. We find that it is accurate, fast, and rigorous without limitations to the geometries of the diffusion tunnels or transition states. "
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0011/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "MARVEL"
-        },
-        {
-            "name": "TuTraST"
-        },
-        {
-            "name": "diffusion"
-        },
-        {
-            "name": "methane"
-        },
-        {
-            "name": "zeolite"
-        },
-        {
-            "name": "transition state theory"
-        },
-        {
-            "name": "kinetic monte carlo"
-        }
-    ],
-    "title": [
-        "TuTraST data for methane diffusion in IZA structures"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0011/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/3fa09c06-f7a4-52f8-a0e5-1f1b2f84b435.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/3fa09c06-f7a4-52f8-a0e5-1f1b2f84b435.json
deleted file mode 100644
index 0843c51a..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/3fa09c06-f7a4-52f8-a0e5-1f1b2f84b435.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0026/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0026/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0026/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Pasquarello, Alfredo",
-        "Guo, Zhendong",
-        "Ambrosio, Francesco"
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0026/v1;2019-06-12Z;DOI;Dataset;Guo, Zhendong;Ambrosio, Francesco;Pasquarello, Alfredo;Oxygen defects in amorphous Al2O3;Materials Cloud;2019-05-30;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;amorphous Al2O3;oxygen vacancy;oxygen interstitial;peroxy linkage;holes;doi:10.24435/materialscloud:2019.0026/v1;https://archive.materialscloud.org/2019.0026/v1;en;The electronic properties of the oxygen vacancy and interstitial in amorphous Al2O3 are studied via ab initio molecular dynamics simulations and hybrid functional calculations. Our results indicate that these defects do not occur in amorphous Al2O3, due to structural rearrangements which assimilate the defect structure and cause a delocalization of the associated defect levels. The imbalance of oxygen leads to a nonstoichiometric compound in which the oxygen occurs in the form of O2\u2013 ions. Intrinsic oxygen defects are found to be unable to trap excess electrons. For low Fermi energies, the formation of peroxy linkages is found to be favored leading to the capture of holes. The relative +2/0 defect levels occur at 2.5 eV from the valence band.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "3fa09c06-f7a4-52f8-a0e5-1f1b2f84b435",
-    "notes": [
-        "The electronic properties of the oxygen vacancy and interstitial in amorphous Al2O3 are studied via ab initio molecular dynamics simulations and hybrid functional calculations. Our results indicate that these defects do not occur in amorphous Al2O3, due to structural rearrangements which assimilate the defect structure and cause a delocalization of the associated defect levels. The imbalance of oxygen leads to a nonstoichiometric compound in which the oxygen occurs in the form of O2\u2013 ions. Intrinsic oxygen defects are found to be unable to trap excess electrons. For low Fermi energies, the formation of peroxy linkages is found to be favored leading to the capture of holes. The relative +2/0 defect levels occur at 2.5 eV from the valence band."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0026/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "amorphous AlO"
-        },
-        {
-            "name": "oxygen vacancy"
-        },
-        {
-            "name": "oxygen interstitial"
-        },
-        {
-            "name": "peroxy linkage"
-        },
-        {
-            "name": "holes"
-        }
-    ],
-    "title": [
-        "Oxygen defects in amorphous Al2O3"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0026/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/40002087-fa2f-55c8-93c3-c270402c4920.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/40002087-fa2f-55c8-93c3-c270402c4920.json
deleted file mode 100644
index 5db6c0eb..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/40002087-fa2f-55c8-93c3-c270402c4920.json
+++ /dev/null
@@ -1,104 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0005/v2",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0005/v2",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0005/v2"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-11-14T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Lin, Li-Chiang",
-        "Braun, Efrem",
-        "Schnell, Sondre",
-        "Kim, Jihan",
-        "Smit, Berend",
-        "Thijssen, Wouter",
-        "Zurhelle, Alexander F.",
-        "Thompson, Joshua A."
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0005/v2;2019-06-12Z;DOI;Dataset;Braun, Efrem;Zurhelle, Alexander F.;Thijssen, Wouter;Schnell, Sondre;Lin, Li-Chiang;Kim, Jihan;Thompson, Joshua A.;Smit, Berend;High-throughput computational screening of nanoporous adsorbents for CO 2 capture from natural gas;Materials Cloud;2018-11-14;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;3D;three-dimensional;database;high-throughput;porous polymer networks;IZA;nanoporous;methane storage;deliverable capacities;DC;zeolites;grand canonical Monte Carlo;GCMC;doi:10.24435/materialscloud:2018.0005/v2;https://archive.materialscloud.org/2018.0005/v2;en;With the growth of natural gas as an energy source, upgrading CO2-contaminated supplies has become increasingly important. Here we develop a single metric that captures how well an adsorbent performs the separation of CH4 and CO2, and we then use this metric to computationally screen tens of thousands of all-silica zeolites. We show that the most important predictors of separation performance are the CO2 heat of adsorption (Qst, CO2) and the CO2 saturation loading capacity. We find that a higher-performing material results when the absolute value of the CH4 heat of adsorption (Qst, CH4) is decreased independently of Qst, CO2, but a correlation that exists between Qst, CH4 and Qst, CO2 in all-silica zeolites leads to incongruity between the objectives of optimizing Qst, CO2 and minimizing Qst, CH4, rendering Qst, CH4 nonpredictive of separation performance. We also conduct a large-scale analysis of ideal adsorbed solution theory (IAST) by comparing results obtained using directly-generated mixture isotherms to those obtained using IAST; IAST appears adequate for the purposes of establishing performance trends and structure\u2013property relationships in a high-throughput manner, but it must be tested for validity when analyzing individual adsorbents in detail since it can produce significant errors for materials in which there is site segregation of the adsorbate species.<br/>\n<br/>\nVersion 2 provides the structures in CIF format.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "40002087-fa2f-55c8-93c3-c270402c4920",
-    "notes": [
-        "With the growth of natural gas as an energy source, upgrading CO2-contaminated supplies has become increasingly important. Here we develop a single metric that captures how well an adsorbent performs the separation of CH4 and CO2, and we then use this metric to computationally screen tens of thousands of all-silica zeolites. We show that the most important predictors of separation performance are the CO2 heat of adsorption (Qst, CO2) and the CO2 saturation loading capacity. We find that a higher-performing material results when the absolute value of the CH4 heat of adsorption (Qst, CH4) is decreased independently of Qst, CO2, but a correlation that exists between Qst, CH4 and Qst, CO2 in all-silica zeolites leads to incongruity between the objectives of optimizing Qst, CO2 and minimizing Qst, CH4, rendering Qst, CH4 nonpredictive of separation performance. We also conduct a large-scale analysis of ideal adsorbed solution theory (IAST) by comparing results obtained using directly-generated mixture isotherms to those obtained using IAST; IAST appears adequate for the purposes of establishing performance trends and structure\u2013property relationships in a high-throughput manner, but it must be tested for validity when analyzing individual adsorbents in detail since it can produce significant errors for materials in which there is site segregation of the adsorbate species.<br/>\n<br/>\nVersion 2 provides the structures in CIF format."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0005/v2"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "three-dimensional"
-        },
-        {
-            "name": "database"
-        },
-        {
-            "name": "high-throughput"
-        },
-        {
-            "name": "porous polymer networks"
-        },
-        {
-            "name": "IZA"
-        },
-        {
-            "name": "nanoporous"
-        },
-        {
-            "name": "methane storage"
-        },
-        {
-            "name": "deliverable capacities"
-        },
-        {
-            "name": "DC"
-        },
-        {
-            "name": "zeolites"
-        },
-        {
-            "name": "grand canonical Monte Carlo"
-        },
-        {
-            "name": "GCMC"
-        }
-    ],
-    "title": [
-        "High-throughput computational screening of nanoporous adsorbents for CO 2 capture from natural gas"
-    ],
-    "url": "https://archive.materialscloud.org/2018.0005/v2"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/4415a748-9a50-569e-b815-60b75044646f.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/4415a748-9a50-569e-b815-60b75044646f.json
deleted file mode 100644
index cc93f641..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/4415a748-9a50-569e-b815-60b75044646f.json
+++ /dev/null
@@ -1,102 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0003/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0003/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0003/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-03-27T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Talirz, Leopold",
-        "Smit, Berend",
-        "Fu, Rueih-Sheng",
-        "Mercado, Rocio",
-        "Haranczyk, Maciej",
-        "Yakutovich, Aliaksandr V."
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0003/v1;2019-06-12Z;DOI;Dataset;Mercado, Rocio;Fu, Rueih-Sheng;Yakutovich, Aliaksandr V.;Talirz, Leopold;Haranczyk, Maciej;Smit, Berend;In Silico Design of 2D and 3D Covalent Organic Frameworks for Methane Storage Applications;Materials Cloud;2018-03-27;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;2D;two-dimensional;layered;3D;three-dimensional;database;high-throughput;covalent organic frameworks;COF;nanoporous;methane storage;deliverable capacities;DC;grand canonical Monte Carlo;GCMC;MARVEL;doi:10.24435/materialscloud:2018.0003/v1;https://archive.materialscloud.org/2018.0003/v1;en;Here we present 69,840 covalent organic frameworks (COFs) assembled in silico from a set of 666 distinct organic linkers into 2D-layered and 3D configurations. We investigate the feasibility of using these frameworks for methane storage by using grand-canonical Monte Carlo (GCMC) simulations to calculate their deliverable capacities (DCs). From these calculations, we predict that the best structure in the database is linker91_C_linker91_C_tbd, a structure composed of carbon-carbon bonded triazine linkers in the tbd topology. This structure has a predicted 65-bar DC of 216 v STP/v, greater than that of the best current methane storage material. We also predict other top performing materials, with 305 structures having DCs of over 190 v STP/v, and 34 of these having DCs of over 200 v STP/v. This archive entry contains the database of assembled COF structures (in CIF file format) together with all of their properties. Among the calculated properties for each structure are the framework density, the methane heats of desorption at the storage and depletion pressures, the methane uptakes at the storage and deplation pressures, the supercell volume, and the geometric surface area. Structures are also labeled according to their bond types (amide, amine, imine, carbon-carbon, or mixed) and their dimensionalities (2D or 3D).",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "4415a748-9a50-569e-b815-60b75044646f",
-    "notes": [
-        "Here we present 69,840 covalent organic frameworks (COFs) assembled in silico from a set of 666 distinct organic linkers into 2D-layered and 3D configurations. We investigate the feasibility of using these frameworks for methane storage by using grand-canonical Monte Carlo (GCMC) simulations to calculate their deliverable capacities (DCs). From these calculations, we predict that the best structure in the database is linker91_C_linker91_C_tbd, a structure composed of carbon-carbon bonded triazine linkers in the tbd topology. This structure has a predicted 65-bar DC of 216 v STP/v, greater than that of the best current methane storage material. We also predict other top performing materials, with 305 structures having DCs of over 190 v STP/v, and 34 of these having DCs of over 200 v STP/v. This archive entry contains the database of assembled COF structures (in CIF file format) together with all of their properties. Among the calculated properties for each structure are the framework density, the methane heats of desorption at the storage and depletion pressures, the methane uptakes at the storage and deplation pressures, the supercell volume, and the geometric surface area. Structures are also labeled according to their bond types (amide, amine, imine, carbon-carbon, or mixed) and their dimensionalities (2D or 3D)."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0003/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "two-dimensional"
-        },
-        {
-            "name": "layered"
-        },
-        {
-            "name": "three-dimensional"
-        },
-        {
-            "name": "database"
-        },
-        {
-            "name": "high-throughput"
-        },
-        {
-            "name": "covalent organic frameworks"
-        },
-        {
-            "name": "COF"
-        },
-        {
-            "name": "nanoporous"
-        },
-        {
-            "name": "methane storage"
-        },
-        {
-            "name": "deliverable capacities"
-        },
-        {
-            "name": "DC"
-        },
-        {
-            "name": "grand canonical Monte Carlo"
-        }
-    ],
-    "title": [
-        "In Silico Design of 2D and 3D Covalent Organic Frameworks for Methane Storage Applications"
-    ],
-    "url": "https://archive.materialscloud.org/2018.0003/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/4980755c-f9c3-551d-9e5c-a808b5398b7e.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/4980755c-f9c3-551d-9e5c-a808b5398b7e.json
deleted file mode 100644
index 7c13a663..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/4980755c-f9c3-551d-9e5c-a808b5398b7e.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0023/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0023/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0023/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-12-10T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Chen, Wei",
-        "Miceli, Giacomo",
-        "Pasquarello, Alfredo",
-        "Ambrosio, Francesco"
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0023/v1;2019-06-12Z;DOI;Dataset;Chen, Wei;Ambrosio, Francesco;Miceli, Giacomo;Pasquarello, Alfredo;Ab initio electronic structure of liquid water: Molecular dynamics snapshots;Materials Cloud;2018-12-10;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;liquid water;nuclear quantum effect;doi:10.24435/materialscloud:2018.0023/v1;https://archive.materialscloud.org/2018.0023/v1;en;This entry provides the snapshots of liquid water generated with ab initio molecular dynamics using rVV10 density functional at room temperature. Nuclear quantum effects are taken into account through path-integral molecular dynamics simulations. ",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "4980755c-f9c3-551d-9e5c-a808b5398b7e",
-    "notes": [
-        "This entry provides the snapshots of liquid water generated with ab initio molecular dynamics using rVV10 density functional at room temperature. Nuclear quantum effects are taken into account through path-integral molecular dynamics simulations. "
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0023/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "liquid water"
-        },
-        {
-            "name": "nuclear quantum effect"
-        }
-    ],
-    "title": [
-        "Ab initio electronic structure of liquid water: Molecular dynamics snapshots"
-    ],
-    "url": "https://archive.materialscloud.org/2018.0023/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/4baa23c3-bbe7-5729-a122-90fa121edebc.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/4baa23c3-bbe7-5729-a122-90fa121edebc.json
deleted file mode 100644
index f9bf69ce..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/4baa23c3-bbe7-5729-a122-90fa121edebc.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2017.0003/v2",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2017.0003/v2",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2017.0003/v2"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-11-10T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Boyd, Peter G.",
-        "Jawahery, Sudi",
-        "Smit, Berend",
-        "Witman, Matthew",
-        "Ling, Sanliang",
-        "Slater, Ben",
-        "Haranczyk, Maciej"
-    ],
-    "fulltext": "oai:materialscloud.org:2017.0003/v2;2019-06-12Z;DOI;Dataset;Witman, Matthew;Ling, Sanliang;Jawahery, Sudi;Boyd, Peter G.;Haranczyk, Maciej;Slater, Ben;Smit, Berend;The Influence of Intrinsic Framework Flexibility on Adsorption in Nanoporous Materials (Data Download);Materials Cloud;2018-11-10;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;Nanoporous materials;Flexibility;Xe/Kr separations;doi:10.24435/materialscloud:2017.0003/v2;https://archive.materialscloud.org/2017.0003/v2;en;Project Abstract: For applications of metal-organic frameworks (MOFs) such as gas storage and separation, flexibility is often seen as a parameter that can tune material performance. In this work we aim to determine the optimal flexibility for the shape selective separation of similarly sized molecules (e.g., Xe/Kr mixtures). To obtain systematic insight into how the flexibility impacts this type of separation we develop a simple analytical model that predicts a material&#39;s Henry regime adsorption and selectivity as a function of flexibility. We elucidate the complex dependence of selectivity on a framework&#39;s intrinsic flexibility whereby performance is either improved or reduced with increasing flexibility, depending on the material&#39;s pore size characteristics. However, the selectivity of a material with the pore size and chemistry that already maximizes selectivity in the rigid approximation is continuously diminished with increasing flexibility, demonstrating that the globally optimal separation exists within an entirely rigid pore. Molecular simulations show that our simple model predicts performance trends that are observed when screening the adsorption behavior of flexible MOFs. These flexible simulations provide better agreement with experimental adsorption data in a high performance material that is not captured when modeling this framework as rigid, an approximation typically made in high-throughput screening studies. We conclude that, for shape selective adsorption applications, the globally optimal material will have the optimal pore size/chemistry and minimal intrinsic flexibility even though other non-optimal materials&#39; selectivity can actually be improved by flexibility. Equally important, we find that flexible simulations can be critical for correctly modeling adsorption in these types of systems.<br/>\n<br/>\nAbout this entry: You can find the Xe/Kr Henry coefficients and the infinite dilution selectivity of more than 2000 CoRE MOF structures obtained via computational screening when materials are simulated as both flexible and rigid.  For details about the methods used to obtain these results, please see the corresponding paper (DOI: 10.1021/jacs.7b01688).  The data provided here was used to create the scatter plots presented in the original paper and can be used to find the adsorption properties for any material in the CoRE MOF screening.<br/>\n<br/>\nVersion 2 includes a minor formatting correction to make the CIF files compliant with the CIF standard.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "4baa23c3-bbe7-5729-a122-90fa121edebc",
-    "notes": [
-        "Project Abstract: For applications of metal-organic frameworks (MOFs) such as gas storage and separation, flexibility is often seen as a parameter that can tune material performance. In this work we aim to determine the optimal flexibility for the shape selective separation of similarly sized molecules (e.g., Xe/Kr mixtures). To obtain systematic insight into how the flexibility impacts this type of separation we develop a simple analytical model that predicts a material&#39;s Henry regime adsorption and selectivity as a function of flexibility. We elucidate the complex dependence of selectivity on a framework&#39;s intrinsic flexibility whereby performance is either improved or reduced with increasing flexibility, depending on the material&#39;s pore size characteristics. However, the selectivity of a material with the pore size and chemistry that already maximizes selectivity in the rigid approximation is continuously diminished with increasing flexibility, demonstrating that the globally optimal separation exists within an entirely rigid pore. Molecular simulations show that our simple model predicts performance trends that are observed when screening the adsorption behavior of flexible MOFs. These flexible simulations provide better agreement with experimental adsorption data in a high performance material that is not captured when modeling this framework as rigid, an approximation typically made in high-throughput screening studies. We conclude that, for shape selective adsorption applications, the globally optimal material will have the optimal pore size/chemistry and minimal intrinsic flexibility even though other non-optimal materials&#39; selectivity can actually be improved by flexibility. Equally important, we find that flexible simulations can be critical for correctly modeling adsorption in these types of systems.<br/>\n<br/>\nAbout this entry: You can find the Xe/Kr Henry coefficients and the infinite dilution selectivity of more than 2000 CoRE MOF structures obtained via computational screening when materials are simulated as both flexible and rigid.  For details about the methods used to obtain these results, please see the corresponding paper (DOI: 10.1021/jacs.7b01688).  The data provided here was used to create the scatter plots presented in the original paper and can be used to find the adsorption properties for any material in the CoRE MOF screening.<br/>\n<br/>\nVersion 2 includes a minor formatting correction to make the CIF files compliant with the CIF standard."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2017.0003/v2"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Nanoporous materials"
-        },
-        {
-            "name": "Flexibility"
-        },
-        {
-            "name": "Xe Kr separations"
-        }
-    ],
-    "title": [
-        "The Influence of Intrinsic Framework Flexibility on Adsorption in Nanoporous Materials (Data Download)"
-    ],
-    "url": "https://archive.materialscloud.org/2017.0003/v2"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/509d4f47-ddeb-5980-898a-680ac17e3668.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/509d4f47-ddeb-5980-898a-680ac17e3668.json
deleted file mode 100644
index df31aec7..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/509d4f47-ddeb-5980-898a-680ac17e3668.json
+++ /dev/null
@@ -1,89 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0021/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0021/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0021/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-12-11T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Steinr\u00fcck, Hans-Peter ",
-        "Hirsch, Andreas ",
-        "Wild, Stefan ",
-        "Vidal\u2013Moya, Jos\u00e9 Alejandro ",
-        "Hauke, Frank ",
-        " Maier, Florian",
-        "Dom\u00e9nech\u2013Carb\u00f3, Antonio ",
-        "Abell\u00e1n, Gonzalo ",
-        "Shin, Sunghwan ",
-        "Leyva\u2013P\u00e9rez, Antonio ",
-        "Varela, Maria ",
-        "J. Heller, Bettina S.",
-        "Lloret, Vicent ",
-        "Rivero\u2013Crespo, Miguel \u00c1ngel "
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0021/v1;2019-06-12Z;DOI;Dataset;Lloret, Vicent ;Rivero\u2013Crespo, Miguel \u00c1ngel ;Vidal\u2013Moya, Jos\u00e9 Alejandro ;Wild, Stefan ;Dom\u00e9nech\u2013Carb\u00f3, Antonio ;J. Heller, Bettina S.;Shin, Sunghwan ;Steinr\u00fcck, Hans-Peter ; Maier, Florian;Hauke, Frank ;Varela, Maria ;Hirsch, Andreas ;Leyva\u2013P\u00e9rez, Antonio ;Abell\u00e1n, Gonzalo ;Few layer 2D pnictogens catalyze the alkylation of soft nucleophiles with esters.   ;Materials Cloud;2018-12-11;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;antimonene;Black phosphorous;alkylation;esters;ionic liquids;doi:10.24435/materialscloud:2018.0021/v1;https://archive.materialscloud.org/2018.0021/v1;en;Group 15 elements in zero oxidation state (P, As, Sb and Bi), also called pnictogens, are rarely used in catalysis due to the difficulties associated in preparing well\u2013structured and stable materials. Here, we report on the synthesis of highly exfoliated, few layer 2D phosphorene and antimonene in zero oxidation state, suspended in an ionic liquid, with the native atoms ready to interact with external reagents while avoiding aerobic or aqueous decomposition pathways, and on their use as efficient catalysts for the alkylation of nucleophiles with esters. The few layer pnictogen material circumvents the extremely harsh reaction conditions associated to previous superacid\u2013catalyzed alkylations, by enabling an alternative mechanism on surface, protected from the water and air by the ionic liquid. These 2D catalysts allow the alkylation of a variety of acid\u2013sensitive organic molecules and giving synthetic relevancy to the use of simple esters as alkylating agents. ",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "509d4f47-ddeb-5980-898a-680ac17e3668",
-    "notes": [
-        "Group 15 elements in zero oxidation state (P, As, Sb and Bi), also called pnictogens, are rarely used in catalysis due to the difficulties associated in preparing well\u2013structured and stable materials. Here, we report on the synthesis of highly exfoliated, few layer 2D phosphorene and antimonene in zero oxidation state, suspended in an ionic liquid, with the native atoms ready to interact with external reagents while avoiding aerobic or aqueous decomposition pathways, and on their use as efficient catalysts for the alkylation of nucleophiles with esters. The few layer pnictogen material circumvents the extremely harsh reaction conditions associated to previous superacid\u2013catalyzed alkylations, by enabling an alternative mechanism on surface, protected from the water and air by the ionic liquid. These 2D catalysts allow the alkylation of a variety of acid\u2013sensitive organic molecules and giving synthetic relevancy to the use of simple esters as alkylating agents. "
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0021/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "antimonene"
-        },
-        {
-            "name": "Black phosphorous"
-        },
-        {
-            "name": "alkylation"
-        },
-        {
-            "name": "esters"
-        },
-        {
-            "name": "ionic liquids"
-        }
-    ],
-    "title": [
-        "Few layer 2D pnictogens catalyze the alkylation of soft nucleophiles with esters.   "
-    ],
-    "url": "https://archive.materialscloud.org/2018.0021/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/555a906d-16f7-51c1-ae65-02642bc48e50.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/555a906d-16f7-51c1-ae65-02642bc48e50.json
deleted file mode 100644
index 85d1fc14..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/555a906d-16f7-51c1-ae65-02642bc48e50.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0012/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0012/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0012/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-09-03T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Giustino, Feliciano",
-        "Filip, Marina R."
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0012/v1;2019-06-12Z;DOI;Dataset;Filip, Marina R.;Giustino, Feliciano;The geometric blueprint of perovskites;Materials Cloud;2018-09-03;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;Perovskites;Structure predictions;Goldschmidt;Data mining;doi:10.24435/materialscloud:2018.0012/v1;https://archive.materialscloud.org/2018.0012/v1;en;Perovskite minerals form an essential component of the Earth\u2019s mantle, and synthetic crystals are ubiquitous in electronics, photonics, and energy technology. The extraordinary chemical diversity of these crystals raises the question of how many and which perovskites are yet to be discovered. Here we show that the \u201cno-rattling\u201d principle postulated by Goldschmidt in 1926, describing the geometric conditions under which a perovskite can form, is much more effective than previously thought and allows us to predict perovskites with a fidelity of 80%. By supplementing this principle with inferential statistics and internet data mining we establish that currently known perovskites are only the tip of the iceberg, and we enumerate 90,000 hitherto-unknown compounds awaiting to be studied. Our results suggest that geometric blueprints may enable the systematic screening of millions of compounds and offer untapped opportunities in structure prediction and materials design.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "555a906d-16f7-51c1-ae65-02642bc48e50",
-    "notes": [
-        "Perovskite minerals form an essential component of the Earth\u2019s mantle, and synthetic crystals are ubiquitous in electronics, photonics, and energy technology. The extraordinary chemical diversity of these crystals raises the question of how many and which perovskites are yet to be discovered. Here we show that the \u201cno-rattling\u201d principle postulated by Goldschmidt in 1926, describing the geometric conditions under which a perovskite can form, is much more effective than previously thought and allows us to predict perovskites with a fidelity of 80%. By supplementing this principle with inferential statistics and internet data mining we establish that currently known perovskites are only the tip of the iceberg, and we enumerate 90,000 hitherto-unknown compounds awaiting to be studied. Our results suggest that geometric blueprints may enable the systematic screening of millions of compounds and offer untapped opportunities in structure prediction and materials design."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0012/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Perovskites"
-        },
-        {
-            "name": "Structure predictions"
-        },
-        {
-            "name": "Goldschmidt"
-        },
-        {
-            "name": "Data mining"
-        }
-    ],
-    "title": [
-        "The geometric blueprint of perovskites"
-    ],
-    "url": "https://archive.materialscloud.org/2018.0012/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/5b5c7afd-7fd9-510b-81f0-369e983c9577.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/5b5c7afd-7fd9-510b-81f0-369e983c9577.json
deleted file mode 100644
index 092f1ceb..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/5b5c7afd-7fd9-510b-81f0-369e983c9577.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0030/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0030/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0030/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-06-01T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Pasquarello, Alfredo",
-        "Guo, Zhendong",
-        "Ambrosio, Francesco"
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0030/v1;2019-06-12Z;DOI;Dataset;Guo, Zhendong;Ambrosio, Francesco;Pasquarello, Alfredo;MD trajectories of bulk water and of the water-vacuum interface;Materials Cloud;2019-06-01;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;MD trajectory;rVV10 functional;H2O;water-vacuum interface;doi:10.24435/materialscloud:2019.0030/v1;https://archive.materialscloud.org/2019.0030/v1;en;This entry provides MD trajectories for bulk water and the water-vacuum interface generated with ab initio molecular dynamics using rVV10 density functional at the temperature of 350 K. In the rVV10 functional, the parameter b is set to 9.3.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "5b5c7afd-7fd9-510b-81f0-369e983c9577",
-    "notes": [
-        "This entry provides MD trajectories for bulk water and the water-vacuum interface generated with ab initio molecular dynamics using rVV10 density functional at the temperature of 350 K. In the rVV10 functional, the parameter b is set to 9.3."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0030/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "MD trajectory"
-        },
-        {
-            "name": "rVV functional"
-        },
-        {
-            "name": "HO"
-        },
-        {
-            "name": "water-vacuum interface"
-        }
-    ],
-    "title": [
-        "MD trajectories of bulk water and of the water-vacuum interface"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0030/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/5ba55a46-5f44-57ec-af8b-972078541974.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/5ba55a46-5f44-57ec-af8b-972078541974.json
deleted file mode 100644
index 01bf2d51..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/5ba55a46-5f44-57ec-af8b-972078541974.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0020/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0020/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0020/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-05-20T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Chen, Wei ",
-        "Desai, Shaan ",
-        "Rhone, Trevor David",
-        "Yacoby, Amir",
-        "Kaxiras, Efthimios"
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0020/v1;2019-06-12Z;DOI;Dataset;Rhone, Trevor David;Chen, Wei ;Desai, Shaan ;Yacoby, Amir;Kaxiras, Efthimios;Data-driven studies of magnetic two-dimensional materials;Materials Cloud;2019-05-20;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;machine learning;two-dimensional materials;magnetic materials;doi:10.24435/materialscloud:2019.0020/v1;https://archive.materialscloud.org/2019.0020/v1;en;We use a data-driven approach to study the magnetic and thermodynamic properties of van der Waals (vdW) layered materials. We investigate monolayers of the form A2B2X6, based on the known material Cr2Ge2Te6, using density functional theory (DFT) calculations and determine their magnetic properties, such as magnetic order and magnetic moment. We also examine formation energies and use them as a proxy for chemical stability. ",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "5ba55a46-5f44-57ec-af8b-972078541974",
-    "notes": [
-        "We use a data-driven approach to study the magnetic and thermodynamic properties of van der Waals (vdW) layered materials. We investigate monolayers of the form A2B2X6, based on the known material Cr2Ge2Te6, using density functional theory (DFT) calculations and determine their magnetic properties, such as magnetic order and magnetic moment. We also examine formation energies and use them as a proxy for chemical stability. "
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0020/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine learning"
-        },
-        {
-            "name": "two-dimensional materials"
-        },
-        {
-            "name": "magnetic materials"
-        }
-    ],
-    "title": [
-        "Data-driven studies of magnetic two-dimensional materials"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0020/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/5c6166fa-769f-51fe-8094-96d7fea13d5a.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/5c6166fa-769f-51fe-8094-96d7fea13d5a.json
deleted file mode 100644
index a17f235b..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/5c6166fa-769f-51fe-8094-96d7fea13d5a.json
+++ /dev/null
@@ -1,88 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0018/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0018/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0018/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-05-13T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Song, Zhida",
-        "Wu, QuanSheng",
-        "Yazyev, Oleg V.",
-        "Piveteau, Christophe"
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0018/v1;2019-06-12Z;DOI;Dataset;Wu, QuanSheng;Piveteau, Christophe;Song, Zhida;Yazyev, Oleg V.;MgTa2N3: A reference Dirac semimetal;Materials Cloud;2019-05-13;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;MARVEL;MgTa2N3; Dirac semimetal;VASP;WannierTools;MARVEL/DD6;Topological materials;Topological semimetal;doi:10.24435/materialscloud:2019.0018/v1;https://archive.materialscloud.org/2019.0018/v1;en;MgTa2N3 is predicted to host the topological Dirac semimetal phase. This archive includes input data necessary for reproducing first-principles calculation described in the publication.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "5c6166fa-769f-51fe-8094-96d7fea13d5a",
-    "notes": [
-        "MgTa2N3 is predicted to host the topological Dirac semimetal phase. This archive includes input data necessary for reproducing first-principles calculation described in the publication."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0018/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "MARVEL"
-        },
-        {
-            "name": "MgTaN"
-        },
-        {
-            "name": "Dirac semimetal"
-        },
-        {
-            "name": "VASP"
-        },
-        {
-            "name": "WannierTools"
-        },
-        {
-            "name": "MARVEL DD"
-        },
-        {
-            "name": "Topological materials"
-        },
-        {
-            "name": "Topological semimetal"
-        }
-    ],
-    "title": [
-        "MgTa2N3: A reference Dirac semimetal"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0018/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/6324effa-6e7d-5d16-918c-385262474bda.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/6324effa-6e7d-5d16-918c-385262474bda.json
deleted file mode 100644
index 3ddbd271..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/6324effa-6e7d-5d16-918c-385262474bda.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0007/v3",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0007/v3",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0007/v3"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-02-23T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "RelatedIdentifier": [
-        "https://www.materialscloud.org/discover/ccg"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Corminboeuf, Cl\u00e9mence",
-        "Sawatlon, Boodsarin",
-        "Wodrich, Matthew D.",
-        "Fabrizio, Alberto",
-        "Meyer, Benjamin"
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0007/v3;2019-06-12Z;DOI;Dataset;Sawatlon, Boodsarin;Fabrizio, Alberto;Meyer, Benjamin;Wodrich, Matthew D.;Corminboeuf, Cl\u00e9mence;Mining the C-C Cross-Coupling Genome using Machine Learning;Materials Cloud;2019-02-23;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;machine learning;homogeneous catalysis;volcano plot;transition metal complexes;sketch-map;doi:10.24435/materialscloud:2019.0007/v3;https://archive.materialscloud.org/2019.0007/v3;en;https://www.materialscloud.org/discover/ccg;Applications of machine-learning (ML) techniques to the study of catalytic processes have begun to appear in the literature with increasing frequency. The computational speed up provided by ML allows the properties and energetics of thousands of prospective catalysts to be rapidly assessed. These results, once compiled into a database containing different properties, can be mined with the goal of establishing relationships between the intrinsic chemical properties of different catalysts and their overall catalytic performance. Previously, we applied ML models to predict the performance of 18,000 prospective catalysts for a Suzuki coupling reaction using molecular volcano plots. Here, we expand on our earlier work by examining a larger section of the C-C cross-coupling genome by using a dimensionality-reducing data-clustering algorithms (i.e., sketch-map) to, first, identify the compatibility of each catalyst with different C-C cross-coupling variants (e.g., Suzuki, Kumada, Negishi, Stille, and/or Hiyama) and, second, to uncover links between the chemical property of a catalyst and its catalytic activity. Our findings, based on the analysis of 18,000 catalysts, reveal strong correlations between a catalyst\u2019s HOMO energy and the suitability of its thermodynamic profile. These values can, subsequently, be tuned in order to maximize the thermodynamics of the catalytic cycle through the judicious choice of metal centers and the \u03c0-accepting/\u03c3-donating nature of the flanking ligands. Overall, group 10 metals (Ni, Pd, Pt) are best coupled with the strong \u03c0-acceptor ligands and group 11 metals (Cu, Ag, Au) with weak \u03c0-acceptors, which maximize the thermodynamic drive of the catalytic cycle.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "6324effa-6e7d-5d16-918c-385262474bda",
-    "notes": [
-        "Applications of machine-learning (ML) techniques to the study of catalytic processes have begun to appear in the literature with increasing frequency. The computational speed up provided by ML allows the properties and energetics of thousands of prospective catalysts to be rapidly assessed. These results, once compiled into a database containing different properties, can be mined with the goal of establishing relationships between the intrinsic chemical properties of different catalysts and their overall catalytic performance. Previously, we applied ML models to predict the performance of 18,000 prospective catalysts for a Suzuki coupling reaction using molecular volcano plots. Here, we expand on our earlier work by examining a larger section of the C-C cross-coupling genome by using a dimensionality-reducing data-clustering algorithms (i.e., sketch-map) to, first, identify the compatibility of each catalyst with different C-C cross-coupling variants (e.g., Suzuki, Kumada, Negishi, Stille, and/or Hiyama) and, second, to uncover links between the chemical property of a catalyst and its catalytic activity. Our findings, based on the analysis of 18,000 catalysts, reveal strong correlations between a catalyst\u2019s HOMO energy and the suitability of its thermodynamic profile. These values can, subsequently, be tuned in order to maximize the thermodynamics of the catalytic cycle through the judicious choice of metal centers and the \u03c0-accepting/\u03c3-donating nature of the flanking ligands. Overall, group 10 metals (Ni, Pd, Pt) are best coupled with the strong \u03c0-acceptor ligands and group 11 metals (Cu, Ag, Au) with weak \u03c0-acceptors, which maximize the thermodynamic drive of the catalytic cycle."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0007/v3"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine learning"
-        },
-        {
-            "name": "homogeneous catalysis"
-        },
-        {
-            "name": "volcano plot"
-        },
-        {
-            "name": "transition metal complexes"
-        },
-        {
-            "name": "sketch-map"
-        }
-    ],
-    "title": [
-        "Mining the C-C Cross-Coupling Genome using Machine Learning"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0007/v3"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/70d53dd6-c1b8-57a6-a14b-f9d32c2333fa.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/70d53dd6-c1b8-57a6-a14b-f9d32c2333fa.json
deleted file mode 100644
index c67a64f7..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/70d53dd6-c1b8-57a6-a14b-f9d32c2333fa.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2017.0006/v2",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2017.0006/v2",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2017.0006/v2"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2017-11-06T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Dragoni, Daniele",
-        "Daff, Tom",
-        "Csanyi, Gabor",
-        "Marzari, Nicola"
-    ],
-    "fulltext": "oai:materialscloud.org:2017.0006/v2;2019-06-12Z;DOI;Dataset;Dragoni, Daniele;Daff, Tom;Csanyi, Gabor;Marzari, Nicola;Gaussian Approximation Potentials for iron from extended first-principles database (Data Download);Materials Cloud;2017-11-06;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;Machine-learning;iron;Gaussian approximation potentials;Artificial neural networks;Interatomic potentials;MARVEL;doi:10.24435/materialscloud:2017.0006/v2;https://archive.materialscloud.org/2017.0006/v2;en;Interatomic potentials are often necessary to describe complex realistic systems that would be too costly to study from first-principles. Commonly, interatomic potentials are designed using functional forms driven by physical intuition and fitted to experimental or computational data. The moderate flexibility of these functional forms limits their ability to be systematically improved by increasing the fitting datasets; on the other hand, their qualitative description of the essential physical interactions ensures a modicum degree of transferability. Recently, a novel trend has emerged where potential-energy surfaces are represented by neural networks fitted on large numbers of first-principles calculations, thus maximizing flexibility but requiring extensive datasets to ensure transferability. Gaussian Approximation Potentials in particular are a novel class of potentials based on non-linear, non-parametric Gaussian-process regression. Here we generate a Gaussian Approximation model for the \u03b1-phase of iron training on energies, stresses and forces taken from first-principles molecular dynamics simulations of pristine and defected bulk systems, of surfaces and \u03b3-surfaces with different crystallographic orientations.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "70d53dd6-c1b8-57a6-a14b-f9d32c2333fa",
-    "notes": [
-        "Interatomic potentials are often necessary to describe complex realistic systems that would be too costly to study from first-principles. Commonly, interatomic potentials are designed using functional forms driven by physical intuition and fitted to experimental or computational data. The moderate flexibility of these functional forms limits their ability to be systematically improved by increasing the fitting datasets; on the other hand, their qualitative description of the essential physical interactions ensures a modicum degree of transferability. Recently, a novel trend has emerged where potential-energy surfaces are represented by neural networks fitted on large numbers of first-principles calculations, thus maximizing flexibility but requiring extensive datasets to ensure transferability. Gaussian Approximation Potentials in particular are a novel class of potentials based on non-linear, non-parametric Gaussian-process regression. Here we generate a Gaussian Approximation model for the \u03b1-phase of iron training on energies, stresses and forces taken from first-principles molecular dynamics simulations of pristine and defected bulk systems, of surfaces and \u03b3-surfaces with different crystallographic orientations."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2017.0006/v2"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Machine-learning"
-        },
-        {
-            "name": "iron"
-        },
-        {
-            "name": "Gaussian approximation potentials"
-        },
-        {
-            "name": "Artificial neural networks"
-        },
-        {
-            "name": "Interatomic potentials"
-        },
-        {
-            "name": "MARVEL"
-        }
-    ],
-    "title": [
-        "Gaussian Approximation Potentials for iron from extended first-principles database (Data Download)"
-    ],
-    "url": "https://archive.materialscloud.org/2017.0006/v2"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/72a373ad-ca20-5fbb-96b7-fd31947d9974.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/72a373ad-ca20-5fbb-96b7-fd31947d9974.json
deleted file mode 100644
index de5f0a71..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/72a373ad-ca20-5fbb-96b7-fd31947d9974.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0004/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0004/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0004/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-01-22T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Parrinello, Michele",
-        "Invernizzi, Michele "
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0004/v1;2019-06-12Z;DOI;Dataset;Invernizzi, Michele ;Parrinello, Michele;Making the best of a bad situation: a multiscale approach to free energy calculation;Materials Cloud;2019-01-22;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;enhanced sampling;free energy;metadynamics;doi:10.24435/materialscloud:2019.0004/v1;https://archive.materialscloud.org/2019.0004/v1;en;Many enhanced sampling techniques rely on the identification of a number of collective variables that describe all the slow modes of the system. By constructing a bias potential in this reduced space one is then able to sample efficiently and reconstruct the free energy landscape. In methods like metadynamics, the quality of these collective variables plays a key role in convergence efficiency. Unfortunately in many systems of interest it is not possible to identify an optimal collective variable, and one must deal with the non-ideal situation of a system in which some slow modes are not accelerated. \n<br/>\nWe propose a two-step approach in which, by taking into account the residual multiscale nature of the problem, one is able to significantly speed up convergence. To do so, we combine an exploratory metadynamics run with an optimization of the free energy difference between metastable states, based on the recently proposed variationally enhanced sampling method. This new method is well parallelizable and is especially suited for complex systems, because of its simplicity and clear underlying physical picture.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "72a373ad-ca20-5fbb-96b7-fd31947d9974",
-    "notes": [
-        "Many enhanced sampling techniques rely on the identification of a number of collective variables that describe all the slow modes of the system. By constructing a bias potential in this reduced space one is then able to sample efficiently and reconstruct the free energy landscape. In methods like metadynamics, the quality of these collective variables plays a key role in convergence efficiency. Unfortunately in many systems of interest it is not possible to identify an optimal collective variable, and one must deal with the non-ideal situation of a system in which some slow modes are not accelerated. \n<br/>\nWe propose a two-step approach in which, by taking into account the residual multiscale nature of the problem, one is able to significantly speed up convergence. To do so, we combine an exploratory metadynamics run with an optimization of the free energy difference between metastable states, based on the recently proposed variationally enhanced sampling method. This new method is well parallelizable and is especially suited for complex systems, because of its simplicity and clear underlying physical picture."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0004/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "enhanced sampling"
-        },
-        {
-            "name": "free energy"
-        },
-        {
-            "name": "metadynamics"
-        }
-    ],
-    "title": [
-        "Making the best of a bad situation: a multiscale approach to free energy calculation"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0004/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/75cde2be-6997-5732-bd67-c2401d07d05e.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/75cde2be-6997-5732-bd67-c2401d07d05e.json
deleted file mode 100644
index 28356d5e..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/75cde2be-6997-5732-bd67-c2401d07d05e.json
+++ /dev/null
@@ -1,108 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2017.0008/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2017.0008/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2017.0008/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2017-12-21T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "RelatedIdentifier": [
-        "https://www.materialscloud.org/discover/2dstructures",
-        "https://www.materialscloud.org/explore/2dstructures"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Marzari, Nicola",
-        "Campi, Davide",
-        "Cepellotti, Andrea",
-        "Schwaller, Philippe",
-        "Gibertini, Marco",
-        "Castelli, Ivano E.",
-        "Marrazzo, Antimo",
-        "Sohier, Thibault",
-        "Mounet, Nicolas",
-        "Pizzi, Giovanni",
-        "Merkys, Andrius"
-    ],
-    "fulltext": "oai:materialscloud.org:2017.0008/v1;2019-06-12Z;DOI;Dataset;Mounet, Nicolas;Gibertini, Marco;Schwaller, Philippe;Campi, Davide;Merkys, Andrius;Marrazzo, Antimo;Sohier, Thibault;Castelli, Ivano E.;Cepellotti, Andrea;Pizzi, Giovanni;Marzari, Nicola;Two-dimensional materials from high-throughput computational exfoliation of  experimentally known compounds (Data download);Materials Cloud;2017-12-21;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;2D;two-dimensional;monolayer;database;high-throughput;DFT;vibrational properties;phonons;electronic properties;electronic bands;magnetic properties;MARVEL;doi:10.24435/materialscloud:2017.0008/v1;https://archive.materialscloud.org/2017.0008/v1;en;https://www.materialscloud.org/discover/2dstructures;https://www.materialscloud.org/explore/2dstructures;Two-dimensional (2D) materials have emerged as promising candidates for next-generation electronic and optoelectronic applications. Yet, only a few dozens of 2D materials have been successfully synthesized or exfoliated. Here, we search for novel 2D materials that can be easily exfoliated from their parent compounds. Starting from 108423 unique, experimentally known three-dimensional compounds we identify a subset of 5619 that appear layered according to robust geometric and bonding criteria. High-throughput calculations using van-der-Waals density-functional theory, validated against experimental structural data and calculated random-phase-approximation binding energies, allow to identify 1825 compounds that are either easily or potentially exfoliable. In particular, the subset of 1036 easily exfoliable cases provides novel structural prototypes and simple ternary compounds as well as a large portfolio of materials to search from for optimal properties. For a subset of 258 compounds we explore vibrational, electronic, magnetic, and topological properties, identifying 56 ferromagnetic and antiferromagnetic systems, including half-metals and half-semiconductors. This archive entry contains the database of 2D materials (structural parameters, band structures, binding energies, etc.) together with the provenance of all data and calculations as stored by AiiDA.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "75cde2be-6997-5732-bd67-c2401d07d05e",
-    "notes": [
-        "Two-dimensional (2D) materials have emerged as promising candidates for next-generation electronic and optoelectronic applications. Yet, only a few dozens of 2D materials have been successfully synthesized or exfoliated. Here, we search for novel 2D materials that can be easily exfoliated from their parent compounds. Starting from 108423 unique, experimentally known three-dimensional compounds we identify a subset of 5619 that appear layered according to robust geometric and bonding criteria. High-throughput calculations using van-der-Waals density-functional theory, validated against experimental structural data and calculated random-phase-approximation binding energies, allow to identify 1825 compounds that are either easily or potentially exfoliable. In particular, the subset of 1036 easily exfoliable cases provides novel structural prototypes and simple ternary compounds as well as a large portfolio of materials to search from for optimal properties. For a subset of 258 compounds we explore vibrational, electronic, magnetic, and topological properties, identifying 56 ferromagnetic and antiferromagnetic systems, including half-metals and half-semiconductors. This archive entry contains the database of 2D materials (structural parameters, band structures, binding energies, etc.) together with the provenance of all data and calculations as stored by AiiDA."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2017.0008/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "two-dimensional"
-        },
-        {
-            "name": "monolayer"
-        },
-        {
-            "name": "database"
-        },
-        {
-            "name": "high-throughput"
-        },
-        {
-            "name": "DFT"
-        },
-        {
-            "name": "vibrational properties"
-        },
-        {
-            "name": "phonons"
-        },
-        {
-            "name": "electronic properties"
-        },
-        {
-            "name": "electronic bands"
-        },
-        {
-            "name": "magnetic properties"
-        },
-        {
-            "name": "MARVEL"
-        }
-    ],
-    "title": [
-        "Two-dimensional materials from high-throughput computational exfoliation of  experimentally known compounds (Data download)"
-    ],
-    "url": "https://archive.materialscloud.org/2017.0008/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/7697a59c-a9aa-5928-b6ee-ac4a88c09145.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/7697a59c-a9aa-5928-b6ee-ac4a88c09145.json
deleted file mode 100644
index 078a61e3..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/7697a59c-a9aa-5928-b6ee-ac4a88c09145.json
+++ /dev/null
@@ -1,105 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0003/v3",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0003/v3",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0003/v3"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-10-05T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "RelatedIdentifier": [
-        "https://www.materialscloud.org/discover/cofs"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Talirz, Leopold",
-        "Smit, Berend",
-        "Fu, Rueih-Sheng",
-        "Mercado, Rocio",
-        "Haranczyk, Maciej",
-        "Yakutovich, Aliaksandr V."
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0003/v3;2019-06-12Z;DOI;Dataset;Mercado, Rocio;Fu, Rueih-Sheng;Yakutovich, Aliaksandr V.;Talirz, Leopold;Haranczyk, Maciej;Smit, Berend;In Silico Design of 2D and 3D Covalent Organic Frameworks for Methane Storage Applications;Materials Cloud;2018-10-05;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;2D;two-dimensional;layered;3D;three-dimensional;database;high-throughput;covalent organic frameworks;COF;nanoporous;methane storage;deliverable capacities;DC;grand canonical Monte Carlo;GCMC;MARVEL;doi:10.24435/materialscloud:2018.0003/v3;https://archive.materialscloud.org/2018.0003/v3;en;https://www.materialscloud.org/discover/cofs;Here we present 69,840 covalent organic frameworks (COFs) assembled in silico from a set of 666 distinct organic linkers into 2D-layered and 3D configurations. We investigate the feasibility of using these frameworks for methane storage by using grand-canonical Monte Carlo (GCMC) simulations to calculate their deliverable capacities (DCs). From these calculations, we predict that the best structure in the database is linker91_C_linker91_C_tbd, a structure composed of carbon-carbon bonded triazine linkers in the tbd topology. This structure has a predicted 65-bar DC of 216 v STP/v, greater than that of the best current methane storage material. We also predict other top performing materials, with 305 structures having DCs of over 190 v STP/v, and 34 of these having DCs of over 200 v STP/v. <br/>\nThis archive entry contains the database of assembled COF structures (in CIF file format) together with all of their properties, which can be explored using interactive figures. Among the calculated properties for each structure are the framework density, the methane heats of desorption at the storage and depletion pressures, the methane uptakes at the storage and deplation pressures, the supercell volume, and the geometric surface area. Structures are also labeled according to their bond types (amide, amine, imine, carbon-carbon, or mixed) and their dimensionalities (2D or 3D).",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "7697a59c-a9aa-5928-b6ee-ac4a88c09145",
-    "notes": [
-        "Here we present 69,840 covalent organic frameworks (COFs) assembled in silico from a set of 666 distinct organic linkers into 2D-layered and 3D configurations. We investigate the feasibility of using these frameworks for methane storage by using grand-canonical Monte Carlo (GCMC) simulations to calculate their deliverable capacities (DCs). From these calculations, we predict that the best structure in the database is linker91_C_linker91_C_tbd, a structure composed of carbon-carbon bonded triazine linkers in the tbd topology. This structure has a predicted 65-bar DC of 216 v STP/v, greater than that of the best current methane storage material. We also predict other top performing materials, with 305 structures having DCs of over 190 v STP/v, and 34 of these having DCs of over 200 v STP/v. <br/>\nThis archive entry contains the database of assembled COF structures (in CIF file format) together with all of their properties, which can be explored using interactive figures. Among the calculated properties for each structure are the framework density, the methane heats of desorption at the storage and depletion pressures, the methane uptakes at the storage and deplation pressures, the supercell volume, and the geometric surface area. Structures are also labeled according to their bond types (amide, amine, imine, carbon-carbon, or mixed) and their dimensionalities (2D or 3D)."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0003/v3"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "two-dimensional"
-        },
-        {
-            "name": "layered"
-        },
-        {
-            "name": "three-dimensional"
-        },
-        {
-            "name": "database"
-        },
-        {
-            "name": "high-throughput"
-        },
-        {
-            "name": "covalent organic frameworks"
-        },
-        {
-            "name": "COF"
-        },
-        {
-            "name": "nanoporous"
-        },
-        {
-            "name": "methane storage"
-        },
-        {
-            "name": "deliverable capacities"
-        },
-        {
-            "name": "DC"
-        },
-        {
-            "name": "grand canonical Monte Carlo"
-        }
-    ],
-    "title": [
-        "In Silico Design of 2D and 3D Covalent Organic Frameworks for Methane Storage Applications"
-    ],
-    "url": "https://archive.materialscloud.org/2018.0003/v3"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/77a4d9dd-9dd1-50fb-9d2b-303782c05b7e.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/77a4d9dd-9dd1-50fb-9d2b-303782c05b7e.json
deleted file mode 100644
index dd49ef88..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/77a4d9dd-9dd1-50fb-9d2b-303782c05b7e.json
+++ /dev/null
@@ -1,104 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0005/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0005/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0005/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-05-15T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Lin, Li-Chiang",
-        "Braun, Efrem",
-        "Schnell, Sondre",
-        "Kim, Jihan",
-        "Smit, Berend",
-        "Thijssen, Wouter",
-        "Zurhelle, Alexander F.",
-        "Thompson, Joshua A."
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0005/v1;2019-06-12Z;DOI;Dataset;Braun, Efrem;Zurhelle, Alexander F.;Thijssen, Wouter;Schnell, Sondre;Lin, Li-Chiang;Kim, Jihan;Thompson, Joshua A.;Smit, Berend;High-throughput computational screening of nanoporous adsorbents for CO 2 capture from natural gas;Materials Cloud;2018-05-15;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;3D;three-dimensional;database;high-throughput;porous polymer networks;IZA;nanoporous;methane storage;deliverable capacities;DC;zeolites;grand canonical Monte Carlo;GCMC;doi:10.24435/materialscloud:2018.0005/v1;https://archive.materialscloud.org/2018.0005/v1;en;With the growth of natural gas as an energy source, upgrading CO2-contaminated supplies has become increasingly important. Here we develop a single metric that captures how well an adsorbent performs the separation of CH4 and CO2, and we then use this metric to computationally screen tens of thousands of all-silica zeolites. We show that the most important predictors of separation performance are the CO2 heat of adsorption (Qst, CO2) and the CO2 saturation loading capacity. We find that a higher-performing material results when the absolute value of the CH4 heat of adsorption (Qst, CH4) is decreased independently of Qst, CO2, but a correlation that exists between Qst, CH4 and Qst, CO2 in all-silica zeolites leads to incongruity between the objectives of optimizing Qst, CO2 and minimizing Qst, CH4, rendering Qst, CH4 nonpredictive of separation performance. We also conduct a large-scale analysis of ideal adsorbed solution theory (IAST) by comparing results obtained using directly-generated mixture isotherms to those obtained using IAST; IAST appears adequate for the purposes of establishing performance trends and structure\u2013property relationships in a high-throughput manner, but it must be tested for validity when analyzing individual adsorbents in detail since it can produce significant errors for materials in which there is site segregation of the adsorbate species.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "77a4d9dd-9dd1-50fb-9d2b-303782c05b7e",
-    "notes": [
-        "With the growth of natural gas as an energy source, upgrading CO2-contaminated supplies has become increasingly important. Here we develop a single metric that captures how well an adsorbent performs the separation of CH4 and CO2, and we then use this metric to computationally screen tens of thousands of all-silica zeolites. We show that the most important predictors of separation performance are the CO2 heat of adsorption (Qst, CO2) and the CO2 saturation loading capacity. We find that a higher-performing material results when the absolute value of the CH4 heat of adsorption (Qst, CH4) is decreased independently of Qst, CO2, but a correlation that exists between Qst, CH4 and Qst, CO2 in all-silica zeolites leads to incongruity between the objectives of optimizing Qst, CO2 and minimizing Qst, CH4, rendering Qst, CH4 nonpredictive of separation performance. We also conduct a large-scale analysis of ideal adsorbed solution theory (IAST) by comparing results obtained using directly-generated mixture isotherms to those obtained using IAST; IAST appears adequate for the purposes of establishing performance trends and structure\u2013property relationships in a high-throughput manner, but it must be tested for validity when analyzing individual adsorbents in detail since it can produce significant errors for materials in which there is site segregation of the adsorbate species."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0005/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "three-dimensional"
-        },
-        {
-            "name": "database"
-        },
-        {
-            "name": "high-throughput"
-        },
-        {
-            "name": "porous polymer networks"
-        },
-        {
-            "name": "IZA"
-        },
-        {
-            "name": "nanoporous"
-        },
-        {
-            "name": "methane storage"
-        },
-        {
-            "name": "deliverable capacities"
-        },
-        {
-            "name": "DC"
-        },
-        {
-            "name": "zeolites"
-        },
-        {
-            "name": "grand canonical Monte Carlo"
-        },
-        {
-            "name": "GCMC"
-        }
-    ],
-    "title": [
-        "High-throughput computational screening of nanoporous adsorbents for CO 2 capture from natural gas"
-    ],
-    "url": "https://archive.materialscloud.org/2018.0005/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/77fb4b6b-5d71-50db-8f7e-5858df2d61fb.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/77fb4b6b-5d71-50db-8f7e-5858df2d61fb.json
deleted file mode 100644
index bd1a6c41..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/77fb4b6b-5d71-50db-8f7e-5858df2d61fb.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0002/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0002/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0002/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-01-19T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Yang, Yang",
-        "Lao, Ka Un",
-        "Grisafi, Andrea",
-        "DiStasio Jr., Robert A.",
-        "Ceriotti, Michele",
-        "Wilkins, David M."
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0002/v1;2019-06-12Z;DOI;Dataset;Yang, Yang;Lao, Ka Un;Wilkins, David M.;Grisafi, Andrea;Ceriotti, Michele;DiStasio Jr., Robert A.;Coupled-Cluster Polarizabilities in the QM7b and a Showcase Database;Materials Cloud;2019-01-19;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;dipole polarizability;linear response coupled cluster;density functional theory;doi:10.24435/materialscloud:2019.0002/v1;https://archive.materialscloud.org/2019.0002/v1;en;Dipole polarizabilities, computed using linear response coupled cluster theory and density functional theory (using d-aug-cc-pVDZ basis set), for 7211 molecules from the QM7b dataset of small molecules and for 52 molecules from a showcase dataset.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "77fb4b6b-5d71-50db-8f7e-5858df2d61fb",
-    "notes": [
-        "Dipole polarizabilities, computed using linear response coupled cluster theory and density functional theory (using d-aug-cc-pVDZ basis set), for 7211 molecules from the QM7b dataset of small molecules and for 52 molecules from a showcase dataset."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0002/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "dipole polarizability"
-        },
-        {
-            "name": "linear response coupled cluster"
-        },
-        {
-            "name": "density functional theory"
-        }
-    ],
-    "title": [
-        "Coupled-Cluster Polarizabilities in the QM7b and a Showcase Database"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0002/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/8219014e-8922-5de6-81fc-d5e15a71e340.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/8219014e-8922-5de6-81fc-d5e15a71e340.json
deleted file mode 100644
index 156dd6db..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/8219014e-8922-5de6-81fc-d5e15a71e340.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0010/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0010/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0010/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-02-28T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Invernizzi, Michele",
-        "Debnath, Jayashrita ",
-        "Parrinello, Michele "
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0010/v1;2019-06-12Z;DOI;Dataset;Debnath, Jayashrita ;Parrinello, Michele ;Invernizzi, Michele;Enhanced sampling of transition states;Materials Cloud;2019-02-28;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;Transition States;Nucleation;Critical Clusters;Enhanced Sampling;Molecular Modelling;doi:10.24435/materialscloud:2019.0010/v1;https://archive.materialscloud.org/2019.0010/v1;en;The free energy landscapes of several fundamental processes are characterized by high barriers separating long-lived metastable states. In order to explore these type of landscapes enhanced sampling methods are used. While many such methods are able to obtain sufficient sampling in order to draw the free energy, the transition states are often sparsely sampled. We propose an approach based on the Variationally Enhanced Sampling Method to enhance sampling in the transition region. To this effect, we introduce a dynamic target distribution which uses the derivative of the instantaneous free energy surface to locate the transition regions on the fly and modulate the probability of sampling different regions. Finally, we exemplify  the effectiveness of this approach in enriching the number of configurations in the transition state region in the cases of a chemical reaction and of a nucleation process.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "8219014e-8922-5de6-81fc-d5e15a71e340",
-    "notes": [
-        "The free energy landscapes of several fundamental processes are characterized by high barriers separating long-lived metastable states. In order to explore these type of landscapes enhanced sampling methods are used. While many such methods are able to obtain sufficient sampling in order to draw the free energy, the transition states are often sparsely sampled. We propose an approach based on the Variationally Enhanced Sampling Method to enhance sampling in the transition region. To this effect, we introduce a dynamic target distribution which uses the derivative of the instantaneous free energy surface to locate the transition regions on the fly and modulate the probability of sampling different regions. Finally, we exemplify  the effectiveness of this approach in enriching the number of configurations in the transition state region in the cases of a chemical reaction and of a nucleation process."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0010/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Transition States"
-        },
-        {
-            "name": "Nucleation"
-        },
-        {
-            "name": "Critical Clusters"
-        },
-        {
-            "name": "Enhanced Sampling"
-        },
-        {
-            "name": "Molecular Modelling"
-        }
-    ],
-    "title": [
-        "Enhanced sampling of transition states"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0010/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/888879ef-62e9-57ea-8d90-e5909ca2f0e5.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/888879ef-62e9-57ea-8d90-e5909ca2f0e5.json
deleted file mode 100644
index 57559c05..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/888879ef-62e9-57ea-8d90-e5909ca2f0e5.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0003/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0003/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0003/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-01-23T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Goedecker, Stefan",
-        "Tomerini, Daniele ",
-        "Rothlisberger, Ursula",
-        "Boziki, Ariadni",
-        "Amsler, Maximilian ",
-        "Flores-Livas, Jos\u00e9 A."
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0003/v1;2019-06-12Z;DOI;Dataset;Flores-Livas, Jos\u00e9 A.;Tomerini, Daniele ;Amsler, Maximilian ;Boziki, Ariadni;Rothlisberger, Ursula;Goedecker, Stefan;Emergence of hidden phases of methylammonium lead-iodide (CH3NH3PbI) upon compression;Materials Cloud;2019-01-23;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;MAPI Perovskites;Structure prediction;VASP SCAN  functional;Minima hopping method;Force field GULP;doi:10.24435/materialscloud:2019.0003/v1;https://archive.materialscloud.org/2019.0003/v1;en;We perform a thorough structural search with the minima hopping method (MHM) to explore low-energy structures of methylammonium lead iodide. By combining the MHM with a forcefield, we efficiently screen vast portions of the configurational space with large simulation cells containing up to 96 atoms. Our search reveals two structures of methylammonium iodide perovskite (MAPI) that are substantially lower in energy than the well-studied experimentally observed low-temperature orthorhombic phase. The data set containing approximately ~180,000 crystal structures is provided. ",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "888879ef-62e9-57ea-8d90-e5909ca2f0e5",
-    "notes": [
-        "We perform a thorough structural search with the minima hopping method (MHM) to explore low-energy structures of methylammonium lead iodide. By combining the MHM with a forcefield, we efficiently screen vast portions of the configurational space with large simulation cells containing up to 96 atoms. Our search reveals two structures of methylammonium iodide perovskite (MAPI) that are substantially lower in energy than the well-studied experimentally observed low-temperature orthorhombic phase. The data set containing approximately ~180,000 crystal structures is provided. "
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0003/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "MAPI Perovskites"
-        },
-        {
-            "name": "Structure prediction"
-        },
-        {
-            "name": "VASP SCAN functional"
-        },
-        {
-            "name": "Minima hopping method"
-        },
-        {
-            "name": "Force field GULP"
-        }
-    ],
-    "title": [
-        "Emergence of hidden phases of methylammonium lead-iodide (CH3NH3PbI) upon compression"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0003/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/8b1c9e43-811d-5bdd-8607-d3f9128593d4.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/8b1c9e43-811d-5bdd-8607-d3f9128593d4.json
deleted file mode 100644
index d14e6ddc..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/8b1c9e43-811d-5bdd-8607-d3f9128593d4.json
+++ /dev/null
@@ -1,90 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0011/v3",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0011/v3",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0011/v3"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-01-04T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "RelatedIdentifier": [
-        "https://www.materialscloud.org/work/tools/sycofinder"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Talirz, Leopold",
-        "Chidambaram, Arunraj",
-        "Smit, Berend",
-        "Haranczyk, Maciej",
-        "Stylianou, Kyriakos C.",
-        "Moosavi, Seyed Mohamad"
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0011/v3;2019-06-12Z;DOI;Dataset;Moosavi, Seyed Mohamad;Chidambaram, Arunraj;Talirz, Leopold;Haranczyk, Maciej;Stylianou, Kyriakos C.;Smit, Berend;Capturing chemical intuition in synthesis of metal-organic frameworks;Materials Cloud;2019-01-04;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;Machine learning;Synthesis;Optimisation;Genetic algorithms;Metal-Organic frameworks;Robotic synthesi;MARVEL;doi:10.24435/materialscloud:2018.0011/v3;https://archive.materialscloud.org/2018.0011/v3;en;https://www.materialscloud.org/work/tools/sycofinder;We report a methodology using machine learning to capture chemical intuition from a set of (partially) failed attempts to synthesize a metal organic framework. We define chemical intuition as the collection of unwritten guidelines used by synthetic chemists to find the right synthesis conditions. As (partially) failed experiments usually remain unreported, we have reconstructed a typical track of failed experiments in a successful search for finding the optimal synthesis conditions that yields HKUST-1 with the highest surface area reported to date. We illustrate the importance of quantifying this chemical intuition for the synthesis of novel materials.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "8b1c9e43-811d-5bdd-8607-d3f9128593d4",
-    "notes": [
-        "We report a methodology using machine learning to capture chemical intuition from a set of (partially) failed attempts to synthesize a metal organic framework. We define chemical intuition as the collection of unwritten guidelines used by synthetic chemists to find the right synthesis conditions. As (partially) failed experiments usually remain unreported, we have reconstructed a typical track of failed experiments in a successful search for finding the optimal synthesis conditions that yields HKUST-1 with the highest surface area reported to date. We illustrate the importance of quantifying this chemical intuition for the synthesis of novel materials."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0011/v3"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Machine learning"
-        },
-        {
-            "name": "Synthesis"
-        },
-        {
-            "name": "Optimisation"
-        },
-        {
-            "name": "Genetic algorithms"
-        },
-        {
-            "name": "Metal-Organic frameworks"
-        },
-        {
-            "name": "Robotic synthesi"
-        },
-        {
-            "name": "MARVEL"
-        }
-    ],
-    "title": [
-        "Capturing chemical intuition in synthesis of metal-organic frameworks"
-    ],
-    "url": "https://archive.materialscloud.org/2018.0011/v3"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/8c320f3d-cd5a-5bbb-85c7-fb8117a1b80f.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/8c320f3d-cd5a-5bbb-85c7-fb8117a1b80f.json
deleted file mode 100644
index edfcd777..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/8c320f3d-cd5a-5bbb-85c7-fb8117a1b80f.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0008/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0008/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0008/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-02-12T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Kozinsky, Boris",
-        "Marzari, Nicola",
-        "Musaelian, Albert",
-        "Kahle, Leonid"
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0008/v1;2019-06-12Z;DOI;Dataset;Kahle, Leonid;Musaelian, Albert;Marzari, Nicola;Kozinsky, Boris;Unsupervised landmark analysis for jump detection in molecular dynamics simulations;Materials Cloud;2019-02-12;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;molecular dynamics;site analysis;tracer diffusion;doi:10.24435/materialscloud:2019.0008/v1;https://archive.materialscloud.org/2019.0008/v1;en;Molecular dynamics is a versatile and powerful method to study diffusion in solid-state ionic conductors, requiring minimal prior knowledge of equilibrium or transition states of the system&#39;s free energy surface. However, the analysis of trajectories for relevant but rare events, such as a jump of the diffusing mobile ion, is still rather cumbersome, requiring prior knowledge of the diffusive process in order to get meaningful results. In this work we present a novel approach to detect the relevant events in a diffusive system without assuming prior information regarding the underlying process. We start from a projection of the atomic coordinates into a landmark basis to identify the dominant features in a mobile ion&#39;s environment. Subsequent clustering in landmark space enables a discretization of any trajectory into a sequence of distinct states. As a final step, the use of the Smooth Overlap of Atomic Positions descriptor allows distinguishing between different environments in a straightforward way. We apply this algorithm to ten Li-ionic systems and conduct in-depth analyses of cubic Li7La3Zr2O12, tetragonal Li10GeP2S12, and the \u03b2-eucryptite LiAlSiO4. We compare our results to existing methods, underscoring strong points, weaknesses, and insights into the diffusive behavior of the ionic conduction in the materials investigated. ",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "8c320f3d-cd5a-5bbb-85c7-fb8117a1b80f",
-    "notes": [
-        "Molecular dynamics is a versatile and powerful method to study diffusion in solid-state ionic conductors, requiring minimal prior knowledge of equilibrium or transition states of the system&#39;s free energy surface. However, the analysis of trajectories for relevant but rare events, such as a jump of the diffusing mobile ion, is still rather cumbersome, requiring prior knowledge of the diffusive process in order to get meaningful results. In this work we present a novel approach to detect the relevant events in a diffusive system without assuming prior information regarding the underlying process. We start from a projection of the atomic coordinates into a landmark basis to identify the dominant features in a mobile ion&#39;s environment. Subsequent clustering in landmark space enables a discretization of any trajectory into a sequence of distinct states. As a final step, the use of the Smooth Overlap of Atomic Positions descriptor allows distinguishing between different environments in a straightforward way. We apply this algorithm to ten Li-ionic systems and conduct in-depth analyses of cubic Li7La3Zr2O12, tetragonal Li10GeP2S12, and the \u03b2-eucryptite LiAlSiO4. We compare our results to existing methods, underscoring strong points, weaknesses, and insights into the diffusive behavior of the ionic conduction in the materials investigated. "
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0008/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "molecular dynamics"
-        },
-        {
-            "name": "site analysis"
-        },
-        {
-            "name": "tracer diffusion"
-        }
-    ],
-    "title": [
-        "Unsupervised landmark analysis for jump detection in molecular dynamics simulations"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0008/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/8e879687-71f1-544f-a1e8-a43ec8a51ef3.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/8e879687-71f1-544f-a1e8-a43ec8a51ef3.json
deleted file mode 100644
index 61724ae3..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/8e879687-71f1-544f-a1e8-a43ec8a51ef3.json
+++ /dev/null
@@ -1,92 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0005/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0005/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0005/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-02-03T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Zanelotti, Curt",
-        "Madsen, Louis ",
-        "Fahs, Gregory",
-        "Dingemans, Theo",
-        "Ensing, Bernd ",
-        "Wang, Ying",
-        "Brinck, Stephanie",
-        "He, Yadong",
-        "Yu, Zhou",
-        "Gao, Jianwei",
-        "Hegde, Maruti",
-        "Qiao, Rui",
-        "Slebodnick, Carla",
-        "Moore, Robert"
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0005/v1;2019-06-12Z;DOI;Dataset;Madsen, Louis ;Wang, Ying;He, Yadong;Yu, Zhou;Gao, Jianwei;Brinck, Stephanie;Slebodnick, Carla;Fahs, Gregory;Zanelotti, Curt;Hegde, Maruti;Moore, Robert;Ensing, Bernd ;Dingemans, Theo;Qiao, Rui;Double helix PBDT polymer - Submitted manuscript, simulations and other source data;Materials Cloud;2019-02-03;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;ionic;polymer;nematic;X-ray;simulations;NMR;doi:10.24435/materialscloud:2019.0005/v1;https://archive.materialscloud.org/2019.0005/v1;en;We describe a double helical conformation in the densely charged aromatic polyamide poly(2,2\u2019- disulfonyl-4,4\u2019-benzidine terephthalamide) or PBDT. This double helix macromolecule represents one of the most rigid simple molecular structures known, exhibiting an extremely high axial persistence length (~ 1 micrometer). ",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "8e879687-71f1-544f-a1e8-a43ec8a51ef3",
-    "notes": [
-        "We describe a double helical conformation in the densely charged aromatic polyamide poly(2,2\u2019- disulfonyl-4,4\u2019-benzidine terephthalamide) or PBDT. This double helix macromolecule represents one of the most rigid simple molecular structures known, exhibiting an extremely high axial persistence length (~ 1 micrometer). "
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0005/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "ionic"
-        },
-        {
-            "name": "polymer"
-        },
-        {
-            "name": "nematic"
-        },
-        {
-            "name": "X-ray"
-        },
-        {
-            "name": "simulations"
-        },
-        {
-            "name": "NMR"
-        }
-    ],
-    "title": [
-        "Double helix PBDT polymer - Submitted manuscript, simulations and other source data"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0005/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/91157d00-df8c-51cf-b5f9-479192169677.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/91157d00-df8c-51cf-b5f9-479192169677.json
deleted file mode 100644
index 0187fd78..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/91157d00-df8c-51cf-b5f9-479192169677.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0028/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0028/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0028/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Pasquarello, Alfredo",
-        "Guo, Zhendong",
-        "Ambrosio, Francesco"
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0028/v1;2019-06-12Z;DOI;Dataset;Guo, Zhendong;Ambrosio, Francesco;Pasquarello, Alfredo;Intrinsic defects in amorphous TiO2;Materials Cloud;2019-05-30;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;peroxy linkage;holes;amorphous TiO2;bulk model;doi:10.24435/materialscloud:2019.0028/v1;https://archive.materialscloud.org/2019.0028/v1;en;This entry provides the atomic structures of three bulk amorphous TiO2 models generated through the melt-and-quench method with different cooling rates and of ten O-O peroxy linkages obtained by adding two holes to the bulk model constructed with the lowest cooling rate.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "91157d00-df8c-51cf-b5f9-479192169677",
-    "notes": [
-        "This entry provides the atomic structures of three bulk amorphous TiO2 models generated through the melt-and-quench method with different cooling rates and of ten O-O peroxy linkages obtained by adding two holes to the bulk model constructed with the lowest cooling rate."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0028/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "peroxy linkage"
-        },
-        {
-            "name": "holes"
-        },
-        {
-            "name": "amorphous TiO"
-        },
-        {
-            "name": "bulk model"
-        }
-    ],
-    "title": [
-        "Intrinsic defects in amorphous TiO2"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0028/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/9143ee55-7d34-5ffc-b47f-5677ecf87df4.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/9143ee55-7d34-5ffc-b47f-5677ecf87df4.json
deleted file mode 100644
index 3d05432f..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/9143ee55-7d34-5ffc-b47f-5677ecf87df4.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0010/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0010/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0010/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-05-19T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Anelli, Andrea",
-        "Pickard, Chris J.",
-        "Engel, Edgar A.",
-        "Ceriotti, Michele",
-        "Needs, Richard J."
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0010/v1;2019-06-12Z;DOI;Dataset;Engel, Edgar A.;Anelli, Andrea;Ceriotti, Michele;Pickard, Chris J.;Needs, Richard J.;Mapping uncharted territory in ice from zeolite networks to ice structures;Materials Cloud;2018-05-19;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;3D;three-dimensional;database;high-throughput;water;ice;DFT;first-principles;doi:10.24435/materialscloud:2018.0010/v1;https://archive.materialscloud.org/2018.0010/v1;en;We report a large-scale density-functional-theory study of the configuration space of water ice. We geometry optimise 74,963 ice structures, which are selected and constructed from over five million tetrahedral networks listed in the databases of Treacy and Deem, and the International Zeolite Association database. All prior knowledge of ice is set aside and we introduce generalised convex hulls to identify configurations stabilised by appropriate thermodynamic constraints. We thereby rediscover all known phases (I to XVII, i, 0 and the quartz phase) except the metastable ice IV. Crucially, we also find promising candidates for ices XVIII through LI. Using the sketch-map dimensionality-reduction algorithm we construct an a priori, navigable map of configuration space, which reproduces similarity relations between structures and highlights the novel candidates. By relating the known phases to the tractably small, yet structurally diverse set of synthesisable candidate structures, we provide an excellent starting point for identifying formation pathways.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "9143ee55-7d34-5ffc-b47f-5677ecf87df4",
-    "notes": [
-        "We report a large-scale density-functional-theory study of the configuration space of water ice. We geometry optimise 74,963 ice structures, which are selected and constructed from over five million tetrahedral networks listed in the databases of Treacy and Deem, and the International Zeolite Association database. All prior knowledge of ice is set aside and we introduce generalised convex hulls to identify configurations stabilised by appropriate thermodynamic constraints. We thereby rediscover all known phases (I to XVII, i, 0 and the quartz phase) except the metastable ice IV. Crucially, we also find promising candidates for ices XVIII through LI. Using the sketch-map dimensionality-reduction algorithm we construct an a priori, navigable map of configuration space, which reproduces similarity relations between structures and highlights the novel candidates. By relating the known phases to the tractably small, yet structurally diverse set of synthesisable candidate structures, we provide an excellent starting point for identifying formation pathways."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0010/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "three-dimensional"
-        },
-        {
-            "name": "database"
-        },
-        {
-            "name": "high-throughput"
-        },
-        {
-            "name": "water"
-        },
-        {
-            "name": "ice"
-        },
-        {
-            "name": "DFT"
-        },
-        {
-            "name": "first-principles"
-        }
-    ],
-    "title": [
-        "Mapping uncharted territory in ice from zeolite networks to ice structures"
-    ],
-    "url": "https://archive.materialscloud.org/2018.0010/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/983c7895-2ca8-5986-85e2-7317ac602eb5.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/983c7895-2ca8-5986-85e2-7317ac602eb5.json
deleted file mode 100644
index e3300dd9..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/983c7895-2ca8-5986-85e2-7317ac602eb5.json
+++ /dev/null
@@ -1,90 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0016/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0016/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0016/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-10-10T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "RelatedIdentifier": [
-        "https://www.materialscloud.org/discover/mofs"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Daff, Thomas D.",
-        "G\u0142adysiak, Andrzej",
-        "Chidambaram, Arunraj",
-        "Navarro, Jorge A. R.",
-        "Bounds, Richard",
-        "Smit, Berend",
-        "Woo, Tom K.",
-        "Boyd, Peter George",
-        "Schouwink, Pascal",
-        "Reimer, Jeffrey A.",
-        "Stylianou, Kyriakos C.",
-        "Moosavi, Seyed Mohamad"
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0016/v1;2019-06-12Z;DOI;Dataset;Boyd, Peter George;Chidambaram, Arunraj;Daff, Thomas D.;Bounds, Richard;G\u0142adysiak, Andrzej;Schouwink, Pascal;Moosavi, Seyed Mohamad;Reimer, Jeffrey A.;Navarro, Jorge A. R.;Woo, Tom K.;Smit, Berend;Stylianou, Kyriakos C.;Rational design and synthesis of metal-organic frameworks for carbon capture using adsorbaphore identification;Materials Cloud;2018-10-10;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;nanoporous materials;high throughput screening;gas adsorption;co2 capture;adsorbaphore;doi:10.24435/materialscloud:2018.0016/v1;https://archive.materialscloud.org/2018.0016/v1;en;https://www.materialscloud.org/discover/mofs;In this entry is a database of 324,426 hypothetical Metal-Organic Frameworks (MOFs) that were used in a study to screen potential carbon dioxide scrubbers.  Using a method to assemble these materials with topological blueprints, we only selected materials that could be accurately represented with the MEPO-QEq charge generation method. By ensuring that the electrostatic potential is accurately represented in these materials, screening for CO2 adsorption properties would result very few false positives/negatives. The atom-centered charges reported in the CIF file for each MOF were derived from the MEPO-QEq method, which can be found under the &#39;_atom_type_partial_charge&#39; column in each CIF file.\n<br/>\n\n<br/>\nThe relevant data for each MOF is reported in accompanying .csv files. Post-combustion flue gas was simulated at a temperature of both 298K and 0.15 bar CO2, and 313K and 0.15 bar CO2. Mixture adsorption was simulated with the conditions 298K and 0.15:0.85 CO2/N2 with a total pressure of 1 bar. The data file reports working capacities, which is the difference of adsorption of CO2 between two thermodynamic state points. The adsorption state point(s) are mentioned above, and two desorption values were simulated; 0.1 bar CO2 at 363K (vacuum swing adsorption) and 0.7 bar CO2 at 413K (temperature swing adsorption). The data presented in the main manuscript correspond to vacuum swing conditions.\n<br/>\n\n<br/>\nOver 8,000 materials were selected for more refined simulations, including re-defining partial atomic charges with the REPEAT method, and more detailed simulations to obtain common chemical patterns surrounding CO2 binding sites (adsorbaphores). There is an additional .csv file with these refined calculations that accompany this entry titled &#39;top_MOFs_screening_data.csv&#39;.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "983c7895-2ca8-5986-85e2-7317ac602eb5",
-    "notes": [
-        "In this entry is a database of 324,426 hypothetical Metal-Organic Frameworks (MOFs) that were used in a study to screen potential carbon dioxide scrubbers.  Using a method to assemble these materials with topological blueprints, we only selected materials that could be accurately represented with the MEPO-QEq charge generation method. By ensuring that the electrostatic potential is accurately represented in these materials, screening for CO2 adsorption properties would result very few false positives/negatives. The atom-centered charges reported in the CIF file for each MOF were derived from the MEPO-QEq method, which can be found under the &#39;_atom_type_partial_charge&#39; column in each CIF file.\n<br/>\n\n<br/>\nThe relevant data for each MOF is reported in accompanying .csv files. Post-combustion flue gas was simulated at a temperature of both 298K and 0.15 bar CO2, and 313K and 0.15 bar CO2. Mixture adsorption was simulated with the conditions 298K and 0.15:0.85 CO2/N2 with a total pressure of 1 bar. The data file reports working capacities, which is the difference of adsorption of CO2 between two thermodynamic state points. The adsorption state point(s) are mentioned above, and two desorption values were simulated; 0.1 bar CO2 at 363K (vacuum swing adsorption) and 0.7 bar CO2 at 413K (temperature swing adsorption). The data presented in the main manuscript correspond to vacuum swing conditions.\n<br/>\n\n<br/>\nOver 8,000 materials were selected for more refined simulations, including re-defining partial atomic charges with the REPEAT method, and more detailed simulations to obtain common chemical patterns surrounding CO2 binding sites (adsorbaphores). There is an additional .csv file with these refined calculations that accompany this entry titled &#39;top_MOFs_screening_data.csv&#39;."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0016/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "nanoporous materials"
-        },
-        {
-            "name": "high throughput screening"
-        },
-        {
-            "name": "gas adsorption"
-        },
-        {
-            "name": "co capture"
-        },
-        {
-            "name": "adsorbaphore"
-        }
-    ],
-    "title": [
-        "Rational design and synthesis of metal-organic frameworks for carbon capture using adsorbaphore identification"
-    ],
-    "url": "https://archive.materialscloud.org/2018.0016/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/9a1d9938-0957-5554-a8f9-a089de3f9f0b.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/9a1d9938-0957-5554-a8f9-a089de3f9f0b.json
deleted file mode 100644
index 4f5fe66a..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/9a1d9938-0957-5554-a8f9-a089de3f9f0b.json
+++ /dev/null
@@ -1,90 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0011/v4",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0011/v4",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0011/v4"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-03-03T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "RelatedIdentifier": [
-        "https://www.materialscloud.org/work/tools/sycofinder"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Talirz, Leopold",
-        "Chidambaram, Arunraj",
-        "Smit, Berend",
-        "Haranczyk, Maciej",
-        "Stylianou, Kyriakos C.",
-        "Moosavi, Seyed Mohamad"
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0011/v4;2019-06-12Z;DOI;Dataset;Moosavi, Seyed Mohamad;Chidambaram, Arunraj;Talirz, Leopold;Haranczyk, Maciej;Stylianou, Kyriakos C.;Smit, Berend;Capturing chemical intuition in synthesis of metal-organic frameworks;Materials Cloud;2019-03-03;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;Machine learning;Synthesis;Optimisation;Genetic algorithms;Metal-Organic frameworks;Robotic synthesi;MARVEL;doi:10.24435/materialscloud:2018.0011/v4;https://archive.materialscloud.org/2018.0011/v4;en;https://www.materialscloud.org/work/tools/sycofinder;We report a methodology using machine learning to capture chemical intuition from a set of (partially) failed attempts to synthesize a metal organic framework. We define chemical intuition as the collection of unwritten guidelines used by synthetic chemists to find the right synthesis conditions. As (partially) failed experiments usually remain unreported, we have reconstructed a typical track of failed experiments in a successful search for finding the optimal synthesis conditions that yields HKUST-1 with the highest surface area reported to date. We illustrate the importance of quantifying this chemical intuition for the synthesis of novel materials.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "9a1d9938-0957-5554-a8f9-a089de3f9f0b",
-    "notes": [
-        "We report a methodology using machine learning to capture chemical intuition from a set of (partially) failed attempts to synthesize a metal organic framework. We define chemical intuition as the collection of unwritten guidelines used by synthetic chemists to find the right synthesis conditions. As (partially) failed experiments usually remain unreported, we have reconstructed a typical track of failed experiments in a successful search for finding the optimal synthesis conditions that yields HKUST-1 with the highest surface area reported to date. We illustrate the importance of quantifying this chemical intuition for the synthesis of novel materials."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0011/v4"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Machine learning"
-        },
-        {
-            "name": "Synthesis"
-        },
-        {
-            "name": "Optimisation"
-        },
-        {
-            "name": "Genetic algorithms"
-        },
-        {
-            "name": "Metal-Organic frameworks"
-        },
-        {
-            "name": "Robotic synthesi"
-        },
-        {
-            "name": "MARVEL"
-        }
-    ],
-    "title": [
-        "Capturing chemical intuition in synthesis of metal-organic frameworks"
-    ],
-    "url": "https://archive.materialscloud.org/2018.0011/v4"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/9eae16ba-e28c-5530-a5c8-f274cf983619.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/9eae16ba-e28c-5530-a5c8-f274cf983619.json
deleted file mode 100644
index 74f515ef..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/9eae16ba-e28c-5530-a5c8-f274cf983619.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0004/v3",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0004/v3",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0004/v3"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-05-21T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Parrinello, Michele",
-        "Invernizzi, Michele "
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0004/v3;2019-06-12Z;DOI;Dataset;Invernizzi, Michele ;Parrinello, Michele;Making the best of a bad situation: a multiscale approach to free energy calculation;Materials Cloud;2019-05-21;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;enhanced sampling;free energy;metadynamics;doi:10.24435/materialscloud:2019.0004/v3;https://archive.materialscloud.org/2019.0004/v3;en;Many enhanced sampling techniques rely on the identification of a number of collective variables that describe all the slow modes of the system. By constructing a bias potential in this reduced space one is then able to sample efficiently and reconstruct the free energy landscape. In methods like metadynamics, the quality of these collective variables plays a key role in convergence efficiency. Unfortunately in many systems of interest it is not possible to identify an optimal collective variable, and one must deal with the non-ideal situation of a system in which some slow modes are not accelerated. \n<br/>\nWe propose a two-step approach in which, by taking into account the residual multiscale nature of the problem, one is able to significantly speed up convergence. To do so, we combine an exploratory metadynamics run with an optimization of the free energy difference between metastable states, based on the recently proposed variationally enhanced sampling method. This new method is well parallelizable and is especially suited for complex systems, because of its simplicity and clear underlying physical picture.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "9eae16ba-e28c-5530-a5c8-f274cf983619",
-    "notes": [
-        "Many enhanced sampling techniques rely on the identification of a number of collective variables that describe all the slow modes of the system. By constructing a bias potential in this reduced space one is then able to sample efficiently and reconstruct the free energy landscape. In methods like metadynamics, the quality of these collective variables plays a key role in convergence efficiency. Unfortunately in many systems of interest it is not possible to identify an optimal collective variable, and one must deal with the non-ideal situation of a system in which some slow modes are not accelerated. \n<br/>\nWe propose a two-step approach in which, by taking into account the residual multiscale nature of the problem, one is able to significantly speed up convergence. To do so, we combine an exploratory metadynamics run with an optimization of the free energy difference between metastable states, based on the recently proposed variationally enhanced sampling method. This new method is well parallelizable and is especially suited for complex systems, because of its simplicity and clear underlying physical picture."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0004/v3"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "enhanced sampling"
-        },
-        {
-            "name": "free energy"
-        },
-        {
-            "name": "metadynamics"
-        }
-    ],
-    "title": [
-        "Making the best of a bad situation: a multiscale approach to free energy calculation"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0004/v3"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/9f499a9b-75b6-58bd-a29a-e3977eb596dd.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/9f499a9b-75b6-58bd-a29a-e3977eb596dd.json
deleted file mode 100644
index acf2ade3..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/9f499a9b-75b6-58bd-a29a-e3977eb596dd.json
+++ /dev/null
@@ -1,95 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0007/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0007/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0007/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-05-15T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Jariwala, Kuldeep",
-        "Haranczyk, Maciej",
-        "Lin, Li-Chiang",
-        "Martin, Richard L.",
-        "Smit, Berend"
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0007/v1;2019-06-12Z;DOI;Dataset;Martin, Richard L.;Lin, Li-Chiang;Jariwala, Kuldeep;Smit, Berend;Haranczyk, Maciej;Mail-order metal-organic frameworks (MOFs): designing isoreticular MOF-5 analogues comprising commercially available organic molecules;Materials Cloud;2018-05-15;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;3D;three-dimensional;database;high-throughput;MOF-5;nanoporous;methane storage;deliverable capacities;DC;grand canonical Monte Carlo;GCMC;doi:10.24435/materialscloud:2018.0007/v1;https://archive.materialscloud.org/2018.0007/v1;en;Metal\u2013organic frameworks (MOFs), a class of porous materials, are of particular interest in gas storage and separation applications due largely to their high internal surface areas and tunable structures. MOF-5 is perhaps the archetypal MOF; in particular, many isoreticular analogues of MOF-5 have been synthesized, comprising alternative dicarboxylic acid ligands. In this contribution we introduce a new set of hypothesized MOF-5 analogues, constructed from commercially available organic molecules. We describe our automated procedure for hypothetical MOF design, comprising selection of appropriate ligands, construction of 3D structure models, and structure relaxation methods. 116 MOF-5 analogues were designed and characterized in terms of geometric properties and simulated methane uptake at conditions relevant to vehicular storage applications. A strength of the presented approach is that all of the hypothesized MOFs are designed to be synthesizable utilizing ligands purchasable online.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "9f499a9b-75b6-58bd-a29a-e3977eb596dd",
-    "notes": [
-        "Metal\u2013organic frameworks (MOFs), a class of porous materials, are of particular interest in gas storage and separation applications due largely to their high internal surface areas and tunable structures. MOF-5 is perhaps the archetypal MOF; in particular, many isoreticular analogues of MOF-5 have been synthesized, comprising alternative dicarboxylic acid ligands. In this contribution we introduce a new set of hypothesized MOF-5 analogues, constructed from commercially available organic molecules. We describe our automated procedure for hypothetical MOF design, comprising selection of appropriate ligands, construction of 3D structure models, and structure relaxation methods. 116 MOF-5 analogues were designed and characterized in terms of geometric properties and simulated methane uptake at conditions relevant to vehicular storage applications. A strength of the presented approach is that all of the hypothesized MOFs are designed to be synthesizable utilizing ligands purchasable online."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0007/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "three-dimensional"
-        },
-        {
-            "name": "database"
-        },
-        {
-            "name": "high-throughput"
-        },
-        {
-            "name": "MOF-"
-        },
-        {
-            "name": "nanoporous"
-        },
-        {
-            "name": "methane storage"
-        },
-        {
-            "name": "deliverable capacities"
-        },
-        {
-            "name": "DC"
-        },
-        {
-            "name": "grand canonical Monte Carlo"
-        },
-        {
-            "name": "GCMC"
-        }
-    ],
-    "title": [
-        "Mail-order metal-organic frameworks (MOFs): designing isoreticular MOF-5 analogues comprising commercially available organic molecules"
-    ],
-    "url": "https://archive.materialscloud.org/2018.0007/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/9ff3264a-208a-519a-833a-482cfd076d22.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/9ff3264a-208a-519a-833a-482cfd076d22.json
deleted file mode 100644
index 8f99b951..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/9ff3264a-208a-519a-833a-482cfd076d22.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0002/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0002/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0002/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-02-11T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Nguyen, Ngoc Linh",
-        "Marzari, Nicola",
-        "Baletto, Francesca"
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0002/v1;2019-06-12Z;DOI;Dataset;Nguyen, Ngoc Linh;Baletto, Francesca;Marzari, Nicola;Adatom-Induced Local Melting;Materials Cloud;2018-02-11;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;First-principles molecular dynamics;Aluminum;Surface melting;Defects;MARVEL;doi:10.24435/materialscloud:2018.0002/v1;https://archive.materialscloud.org/2018.0002/v1;en;We introduce and discuss the phenomenon of adatom-induced surface local melting, using extensive first-principles molecular dynamics simulations of Al(100) taken as a paradigmatic case of a non-premelting surface that nevertheless displays facile adatom diffusion with single and multiple exchange pathways. Here, a single adatom deposited on the surface is sufficient to nucleate a localized and diffusing liquid-like region that remains confined to the surface layer, but with an area that increases with temperature; in the absence of the adatom, the surface instead remains crystalline until reaching the bulk melting temperature.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "9ff3264a-208a-519a-833a-482cfd076d22",
-    "notes": [
-        "We introduce and discuss the phenomenon of adatom-induced surface local melting, using extensive first-principles molecular dynamics simulations of Al(100) taken as a paradigmatic case of a non-premelting surface that nevertheless displays facile adatom diffusion with single and multiple exchange pathways. Here, a single adatom deposited on the surface is sufficient to nucleate a localized and diffusing liquid-like region that remains confined to the surface layer, but with an area that increases with temperature; in the absence of the adatom, the surface instead remains crystalline until reaching the bulk melting temperature."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0002/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "First-principles molecular dynamics"
-        },
-        {
-            "name": "Aluminum"
-        },
-        {
-            "name": "Surface melting"
-        },
-        {
-            "name": "Defects"
-        },
-        {
-            "name": "MARVEL"
-        }
-    ],
-    "title": [
-        "Adatom-Induced Local Melting"
-    ],
-    "url": "https://archive.materialscloud.org/2018.0002/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/a9674ce4-ae19-5a12-b7e0-f4be007d2364.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/a9674ce4-ae19-5a12-b7e0-f4be007d2364.json
deleted file mode 100644
index d07b4899..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/a9674ce4-ae19-5a12-b7e0-f4be007d2364.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2017.0004/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2017.0004/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2017.0004/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2017-05-05T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Smit, Berend",
-        "Liu, Yifei Michelle"
-    ],
-    "fulltext": "oai:materialscloud.org:2017.0004/v1;2019-06-12Z;DOI;Dataset;Liu, Yifei Michelle;Smit, Berend;Predicting Product Distribution of Propene Dimerization in Nanoporous Materials (Data Download);Materials Cloud;2017-05-05;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;propene dimerization;metal\u2212organic frameworks;zeolites;product distribution;Monte Carlo;molecular simulation;doi:10.24435/materialscloud:2017.0004/v1;https://archive.materialscloud.org/2017.0004/v1;en;Project abstract: In this work, a theoretical framework is developed to explain and predict changes in the product distribution of the propene dimerization reaction, which yields a mixture of C<sub>6</sub> olefin isomers, resulting from the use of different porous materials as catalysts. The MOF-74 class of materials has shown promise in catalyzing the dimerization of propene with high selectivity for valuable linear olefin products. We show that experimentally observed changes in the product distribution can be explained in terms of the contribution of the pores to the free energy of formation, which are directly computed using molecular simulation. Our model is used to screen a library of 118 existing and hypothetical MOF and zeolite structures to study how product distribution can be tuned by changing pore size, shape, and composition of porous materials. Using these molecular descriptors, catalyst properties are identified that increase the selective reaction of linear olefin isomers, which are valued as industrial feedstocks. A pore size commensurate with the size of the desired linear products enhances linear conversion by sterically hindering the branched isomers. Another promising feature is the presence of open metal sites, which interact with the olefin \u03c0-bond to provide favorable binding sites for the linear isomers.<br/>\n<br/>\nAbout this entry: We provide the geometrical framework descriptors, linear conversions, and thermodynamic data for the 118 frameworks screened in this study, as well as thermodynamics of adsorption properties computed for 12 C<sub>6</sub> olefin isomers in each framework. For details about the methods used to obtain these data, please see the corresponding paper (DOI: 10.1021/acscatal.7b00712). The data provided here was used to create the scatter plots in the original paper and can be used to find the product distribution and adsorption properties for all of the materials considered in the study.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "a9674ce4-ae19-5a12-b7e0-f4be007d2364",
-    "notes": [
-        "Project abstract: In this work, a theoretical framework is developed to explain and predict changes in the product distribution of the propene dimerization reaction, which yields a mixture of C<sub>6</sub> olefin isomers, resulting from the use of different porous materials as catalysts. The MOF-74 class of materials has shown promise in catalyzing the dimerization of propene with high selectivity for valuable linear olefin products. We show that experimentally observed changes in the product distribution can be explained in terms of the contribution of the pores to the free energy of formation, which are directly computed using molecular simulation. Our model is used to screen a library of 118 existing and hypothetical MOF and zeolite structures to study how product distribution can be tuned by changing pore size, shape, and composition of porous materials. Using these molecular descriptors, catalyst properties are identified that increase the selective reaction of linear olefin isomers, which are valued as industrial feedstocks. A pore size commensurate with the size of the desired linear products enhances linear conversion by sterically hindering the branched isomers. Another promising feature is the presence of open metal sites, which interact with the olefin \u03c0-bond to provide favorable binding sites for the linear isomers.<br/>\n<br/>\nAbout this entry: We provide the geometrical framework descriptors, linear conversions, and thermodynamic data for the 118 frameworks screened in this study, as well as thermodynamics of adsorption properties computed for 12 C<sub>6</sub> olefin isomers in each framework. For details about the methods used to obtain these data, please see the corresponding paper (DOI: 10.1021/acscatal.7b00712). The data provided here was used to create the scatter plots in the original paper and can be used to find the product distribution and adsorption properties for all of the materials considered in the study."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2017.0004/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "propene dimerization"
-        },
-        {
-            "name": "propene dimerization"
-        },
-        {
-            "name": "zeolites"
-        },
-        {
-            "name": "product distribution"
-        },
-        {
-            "name": "Monte Carlo"
-        },
-        {
-            "name": "molecular simulation"
-        }
-    ],
-    "title": [
-        "Predicting Product Distribution of Propene Dimerization in Nanoporous Materials (Data Download)"
-    ],
-    "url": "https://archive.materialscloud.org/2017.0004/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/a99a1d8e-aee5-5be9-b002-bacd163e6b26.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/a99a1d8e-aee5-5be9-b002-bacd163e6b26.json
deleted file mode 100644
index 57eb91c7..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/a99a1d8e-aee5-5be9-b002-bacd163e6b26.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2017.0003/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2017.0003/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2017.0003/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2017-04-05T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Boyd, Peter G.",
-        "Jawahery, Sudi",
-        "Smit, Berend",
-        "Witman, Matthew",
-        "Ling, Sanliang",
-        "Slater, Ben",
-        "Haranczyk, Maciej"
-    ],
-    "fulltext": "oai:materialscloud.org:2017.0003/v1;2019-06-12Z;DOI;Dataset;Witman, Matthew;Ling, Sanliang;Jawahery, Sudi;Boyd, Peter G.;Haranczyk, Maciej;Slater, Ben;Smit, Berend;The Influence of Intrinsic Framework Flexibility on Adsorption in Nanoporous Materials (Data Download);Materials Cloud;2017-04-05;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;Nanoporous materials;Flexibility;Xe/Kr separations;doi:10.24435/materialscloud:2017.0003/v1;https://archive.materialscloud.org/2017.0003/v1;en;Project Abstract: For applications of metal-organic frameworks (MOFs) such as gas storage and separation, flexibility is often seen as a parameter that can tune material performance. In this work we aim to determine the optimal flexibility for the shape selective separation of similarly sized molecules (e.g., Xe/Kr mixtures). To obtain systematic insight into how the flexibility impacts this type of separation we develop a simple analytical model that predicts a material&#39;s Henry regime adsorption and selectivity as a function of flexibility. We elucidate the complex dependence of selectivity on a framework&#39;s intrinsic flexibility whereby performance is either improved or reduced with increasing flexibility, depending on the material&#39;s pore size characteristics. However, the selectivity of a material with the pore size and chemistry that already maximizes selectivity in the rigid approximation is continuously diminished with increasing flexibility, demonstrating that the globally optimal separation exists within an entirely rigid pore. Molecular simulations show that our simple model predicts performance trends that are observed when screening the adsorption behavior of flexible MOFs. These flexible simulations provide better agreement with experimental adsorption data in a high performance material that is not captured when modeling this framework as rigid, an approximation typically made in high-throughput screening studies. We conclude that, for shape selective adsorption applications, the globally optimal material will have the optimal pore size/chemistry and minimal intrinsic flexibility even though other non-optimal materials&#39; selectivity can actually be improved by flexibility. Equally important, we find that flexible simulations can be critical for correctly modeling adsorption in these types of systems.<br/>\n<br/>\nAbout this entry: You can find the Xe/Kr Henry coefficients and the infinite dilution selectivity of more than 2000 CoRE MOF structures obtained via computational screening when materials are simulated as both flexible and rigid.  For details about the methods used to obtain these results, please see the corresponding paper (DOI: 10.1021/jacs.7b01688).  The data provided here was used to create the scatter plots presented in the original paper and can be used to find the adsorption properties for any material in the CoRE MOF screening.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "a99a1d8e-aee5-5be9-b002-bacd163e6b26",
-    "notes": [
-        "Project Abstract: For applications of metal-organic frameworks (MOFs) such as gas storage and separation, flexibility is often seen as a parameter that can tune material performance. In this work we aim to determine the optimal flexibility for the shape selective separation of similarly sized molecules (e.g., Xe/Kr mixtures). To obtain systematic insight into how the flexibility impacts this type of separation we develop a simple analytical model that predicts a material&#39;s Henry regime adsorption and selectivity as a function of flexibility. We elucidate the complex dependence of selectivity on a framework&#39;s intrinsic flexibility whereby performance is either improved or reduced with increasing flexibility, depending on the material&#39;s pore size characteristics. However, the selectivity of a material with the pore size and chemistry that already maximizes selectivity in the rigid approximation is continuously diminished with increasing flexibility, demonstrating that the globally optimal separation exists within an entirely rigid pore. Molecular simulations show that our simple model predicts performance trends that are observed when screening the adsorption behavior of flexible MOFs. These flexible simulations provide better agreement with experimental adsorption data in a high performance material that is not captured when modeling this framework as rigid, an approximation typically made in high-throughput screening studies. We conclude that, for shape selective adsorption applications, the globally optimal material will have the optimal pore size/chemistry and minimal intrinsic flexibility even though other non-optimal materials&#39; selectivity can actually be improved by flexibility. Equally important, we find that flexible simulations can be critical for correctly modeling adsorption in these types of systems.<br/>\n<br/>\nAbout this entry: You can find the Xe/Kr Henry coefficients and the infinite dilution selectivity of more than 2000 CoRE MOF structures obtained via computational screening when materials are simulated as both flexible and rigid.  For details about the methods used to obtain these results, please see the corresponding paper (DOI: 10.1021/jacs.7b01688).  The data provided here was used to create the scatter plots presented in the original paper and can be used to find the adsorption properties for any material in the CoRE MOF screening."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2017.0003/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Nanoporous materials"
-        },
-        {
-            "name": "Flexibility"
-        },
-        {
-            "name": "Xe Kr separations"
-        }
-    ],
-    "title": [
-        "The Influence of Intrinsic Framework Flexibility on Adsorption in Nanoporous Materials (Data Download)"
-    ],
-    "url": "https://archive.materialscloud.org/2017.0003/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/ac7c95f3-1e34-5222-9cd3-c5287999a84d.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/ac7c95f3-1e34-5222-9cd3-c5287999a84d.json
deleted file mode 100644
index fb7a3957..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/ac7c95f3-1e34-5222-9cd3-c5287999a84d.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0017/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0017/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0017/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-11-08T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Ongari, Daniele",
-        "Keskin, Seda",
-        "Kadioglu, Ozge",
-        "Smit, Berend",
-        "Boyd, Peter G.",
-        "Mace, Amber K."
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0017/v1;2019-06-12Z;DOI;Dataset;Ongari, Daniele;Boyd, Peter G.;Mace, Amber K.;Smit, Berend;Kadioglu, Ozge;Keskin, Seda;Evaluating charge equilibration methods to generate electrostatic fields in nanoporous materials;Materials Cloud;2018-11-08;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;partial charges;Qeq;charge equilibration methods;MARVEL;doi:10.24435/materialscloud:2018.0017/v1;https://archive.materialscloud.org/2018.0017/v1;en;Charge equilibration (Qeq) methods can estimate the electrostatic potential of molecules and periodic frameworks by assigning point charges to each atom, using only a small fraction of the resources needed to compute density functional (DFT)-derived charges. This makes possible, for example, the computational screening of thousands of microporous structures to assess their performance for the adsorption of polar molecules. Recently, different variants of the original Qeq scheme were proposed to improve the quality of the computed point charges. One focus of this research was to improve the gas adsorption predictions in Metal Organic Frameworks (MOFs), for which many different structures are available. In this work, we review the evolution of the method from the original Qeq scheme, understanding the role of the different modifications on the final output. We evaluated the result of combining different protocols and set of parameters, by comparing the Qeq charges with high quality DFT-derived DDEC charges for 2338 MOF structures. We focused on the systematic errors that are attributable to specific atom types to quantify the final precision that one can expect from Qeq methods in the context of gas adsorption where the electrostatic potential plays a significant role, namely CO2 and H2S adsorption. In conclusion, both the type of algorithm and the input parameters have a large impact on the resulting charges and we draw some guidelines to help the user to choose the proper combination of the two for obtaining a meaningful set of charges. We show that, considering this set of MOFs, the accuracy of the original Qeq scheme is often still comparable with the most recent variants, even if it clearly fails in the presence of certain atom types, such as alkali metals. ",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "ac7c95f3-1e34-5222-9cd3-c5287999a84d",
-    "notes": [
-        "Charge equilibration (Qeq) methods can estimate the electrostatic potential of molecules and periodic frameworks by assigning point charges to each atom, using only a small fraction of the resources needed to compute density functional (DFT)-derived charges. This makes possible, for example, the computational screening of thousands of microporous structures to assess their performance for the adsorption of polar molecules. Recently, different variants of the original Qeq scheme were proposed to improve the quality of the computed point charges. One focus of this research was to improve the gas adsorption predictions in Metal Organic Frameworks (MOFs), for which many different structures are available. In this work, we review the evolution of the method from the original Qeq scheme, understanding the role of the different modifications on the final output. We evaluated the result of combining different protocols and set of parameters, by comparing the Qeq charges with high quality DFT-derived DDEC charges for 2338 MOF structures. We focused on the systematic errors that are attributable to specific atom types to quantify the final precision that one can expect from Qeq methods in the context of gas adsorption where the electrostatic potential plays a significant role, namely CO2 and H2S adsorption. In conclusion, both the type of algorithm and the input parameters have a large impact on the resulting charges and we draw some guidelines to help the user to choose the proper combination of the two for obtaining a meaningful set of charges. We show that, considering this set of MOFs, the accuracy of the original Qeq scheme is often still comparable with the most recent variants, even if it clearly fails in the presence of certain atom types, such as alkali metals. "
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0017/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "partial charges"
-        },
-        {
-            "name": "Qeq"
-        },
-        {
-            "name": "charge equilibration methods"
-        },
-        {
-            "name": "MARVEL"
-        }
-    ],
-    "title": [
-        "Evaluating charge equilibration methods to generate electrostatic fields in nanoporous materials"
-    ],
-    "url": "https://archive.materialscloud.org/2018.0017/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/aca1c73a-1d80-5d8f-9704-913cb40d7d4b.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/aca1c73a-1d80-5d8f-9704-913cb40d7d4b.json
deleted file mode 100644
index 4d832917..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/aca1c73a-1d80-5d8f-9704-913cb40d7d4b.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0029/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0029/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0029/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-06-02T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Chen, Wei",
-        "Gono, Patrick",
-        "Guo, Zhendong",
-        "Ambrosio, Francesco",
-        "Pasquarello, Alfredo"
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0029/v1;2019-06-12Z;DOI;Dataset;Guo, Zhendong;Ambrosio, Francesco;Chen, Wei;Gono, Patrick;Pasquarello, Alfredo;MD trajectories of semiconductor-water interfaces and relaxed atomic structures of semiconductor surfaces;Materials Cloud;2019-06-02;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;MD trajectory;semiconductor-water interface;rVV10 functional;doi:10.24435/materialscloud:2019.0029/v1;https://archive.materialscloud.org/2019.0029/v1;en;This entry includes the MD trajectories of several semiconductor-water interfaces generated with ab initio molecular dynamics using the rVV10 density functional at the temperature of 350 K. Eight semiconductor surfaces are considered, namely GaAs(110), GaP(110), GaN(10-10), CdS(10-10), ZnO(10-10), SnO2(110), rutile TiO2(110) and anatase TiO2(101). For GaAs, GaP and anatase TiO2, the trajectories for the interfaces with both the molecular and the dissociative adsorption mode of water are provided. In addition, the relaxed atomic structures of the semiconductor surfaces used to calculate the ionization potential (IP) reported in [Chem. Mater. 2018, 30, 94\u2212111] are added.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "aca1c73a-1d80-5d8f-9704-913cb40d7d4b",
-    "notes": [
-        "This entry includes the MD trajectories of several semiconductor-water interfaces generated with ab initio molecular dynamics using the rVV10 density functional at the temperature of 350 K. Eight semiconductor surfaces are considered, namely GaAs(110), GaP(110), GaN(10-10), CdS(10-10), ZnO(10-10), SnO2(110), rutile TiO2(110) and anatase TiO2(101). For GaAs, GaP and anatase TiO2, the trajectories for the interfaces with both the molecular and the dissociative adsorption mode of water are provided. In addition, the relaxed atomic structures of the semiconductor surfaces used to calculate the ionization potential (IP) reported in [Chem. Mater. 2018, 30, 94\u2212111] are added."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0029/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "MD trajectory"
-        },
-        {
-            "name": "semiconductor-water interface"
-        },
-        {
-            "name": "rVV functional"
-        }
-    ],
-    "title": [
-        "MD trajectories of semiconductor-water interfaces and relaxed atomic structures of semiconductor surfaces"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0029/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/ad2fb810-7a23-5af4-b221-0e0ed558782c.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/ad2fb810-7a23-5af4-b221-0e0ed558782c.json
deleted file mode 100644
index 6663abdf..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/ad2fb810-7a23-5af4-b221-0e0ed558782c.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0018/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0018/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0018/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-11-23T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Pignedoli, Carlo A.",
-        "Tkatchenko, Alexandre",
-        "Yakutovich, Aliaksandr V.",
-        "Passerone, Daniele",
-        "Hoja, Johannes"
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0018/v1;2019-06-12Z;DOI;Dataset;Yakutovich, Aliaksandr V.;Hoja, Johannes;Passerone, Daniele;Tkatchenko, Alexandre;Pignedoli, Carlo A.;Hidden Beneath the Surface: Origin of the Observed Enantioselective Adsorption on PdGa(111);Materials Cloud;2018-11-23;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;DFT;MARVEL  ; van der Waals interactions   many-body dispersion ;PdGa;chirality;many-body dispersion;doi:10.24435/materialscloud:2018.0018/v1;https://archive.materialscloud.org/2018.0018/v1;en;We provide the input files to reproduce the data presented in the work:\n<br/>\nHidden Beneath the Surface: Origin of the Observed Enantioselective Adsorption on PdGa(111)\n<br/>\nThe files are subdivided in directories named after the figures/table of the manuscript\n<br/>\nA. V. Yakutovich, J. Hoja, D. Passerone, Alexandre Tkatchenko, C. A. Pignedoli\n<br/>\nJ. Am. Chem. Soc., 140, 1401-1408 (2018) DOI: 10.1021/jacs.7b10980\n<br/>\nIn the work, we unravel the origin of the recently observed striking enantioselectivity of the PdGa(111) surface with respect to the adsorption of a small organic molecule, 9-ethynylphenanthrene, using first-principles calculations. It turns out that the key ingredient to understand the experimental evidence is the appropriate description of van der Waals interactions beyond the widely employed atomic pairwise approximation. A recently developed van der Waals-inclusive density functional method, which encompasses dielectric screening effects, reveals the origin of the experimentally observed enantioselectivity and provides conclusive evidence of chiral recognition on a bimetallic surface driven by dispersion interactions. ",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "ad2fb810-7a23-5af4-b221-0e0ed558782c",
-    "notes": [
-        "We provide the input files to reproduce the data presented in the work:\n<br/>\nHidden Beneath the Surface: Origin of the Observed Enantioselective Adsorption on PdGa(111)\n<br/>\nThe files are subdivided in directories named after the figures/table of the manuscript\n<br/>\nA. V. Yakutovich, J. Hoja, D. Passerone, Alexandre Tkatchenko, C. A. Pignedoli\n<br/>\nJ. Am. Chem. Soc., 140, 1401-1408 (2018) DOI: 10.1021/jacs.7b10980\n<br/>\nIn the work, we unravel the origin of the recently observed striking enantioselectivity of the PdGa(111) surface with respect to the adsorption of a small organic molecule, 9-ethynylphenanthrene, using first-principles calculations. It turns out that the key ingredient to understand the experimental evidence is the appropriate description of van der Waals interactions beyond the widely employed atomic pairwise approximation. A recently developed van der Waals-inclusive density functional method, which encompasses dielectric screening effects, reveals the origin of the experimentally observed enantioselectivity and provides conclusive evidence of chiral recognition on a bimetallic surface driven by dispersion interactions. "
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0018/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "DFT"
-        },
-        {
-            "name": "MARVEL"
-        },
-        {
-            "name": "van der Waals interactions many-body dispersion"
-        },
-        {
-            "name": "PdGa"
-        },
-        {
-            "name": "chirality"
-        },
-        {
-            "name": "many-body dispersion"
-        }
-    ],
-    "title": [
-        "Hidden Beneath the Surface: Origin of the Observed Enantioselective Adsorption on PdGa(111)"
-    ],
-    "url": "https://archive.materialscloud.org/2018.0018/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/ad6cb17a-2c08-5f26-b33c-1eb6be0ec637.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/ad6cb17a-2c08-5f26-b33c-1eb6be0ec637.json
deleted file mode 100644
index 6dbbebcb..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/ad6cb17a-2c08-5f26-b33c-1eb6be0ec637.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0001/v2",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0001/v2",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0001/v2"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-04-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution Non Commercial 4.0 International https://creativecommons.org/licenses/by-nc/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Marzari, Nicola",
-        "Mauri, Francesco",
-        "Simoncelli, Michele"
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0001/v2;2019-06-12Z;DOI;Dataset;Simoncelli, Michele;Marzari, Nicola;Mauri, Francesco;Unified theory of thermal transport in crystals and disordered solids;Materials Cloud;2019-04-08;Creative Commons Attribution Non Commercial 4.0 International https://creativecommons.org/licenses/by-nc/4.0/legalcode;info:eu-repo/semantics/openAccess;Thermal conductivity;CsPbBr3;Phonon linewidths;doi:10.24435/materialscloud:2019.0001/v2;https://archive.materialscloud.org/2019.0001/v2;en;Crystals and glasses exhibit fundamentally different heat conduction mechanisms: the periodicity of crystals allows for the excitation of propagating vibrational waves that carry heat, as first discussed by Peierls; in glasses, the lack of periodicity breaks Peierls&#39; picture and heat is mainly carried by the coupling of vibrational modes, often described by a harmonic theory introduced by Allen and Feldman. Anharmonicity or disorder are thus the limiting factors for thermal conductivity in crystals or glasses; hitherto, no transport equation has been able to account for both. In the paper https://arxiv.org/abs/1901.01964, we derive such equation, resulting in a thermal conductivity that reduces to the Peierls and Allen-Feldman limits, respectively, in anharmonic-and-ordered or harmonic-and-disordered solids, while also covering the intermediate regimes where both effects are relevant. This approach also solves the long-standing problem of accurately predicting the thermal properties of crystals with ultralow or glass-like thermal conductivity, as we show with an application to a thermoelectric material representative of this class. This database contains the raw data related to the images reported in the paper  https://arxiv.org/abs/1901.01964.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "ad6cb17a-2c08-5f26-b33c-1eb6be0ec637",
-    "notes": [
-        "Crystals and glasses exhibit fundamentally different heat conduction mechanisms: the periodicity of crystals allows for the excitation of propagating vibrational waves that carry heat, as first discussed by Peierls; in glasses, the lack of periodicity breaks Peierls&#39; picture and heat is mainly carried by the coupling of vibrational modes, often described by a harmonic theory introduced by Allen and Feldman. Anharmonicity or disorder are thus the limiting factors for thermal conductivity in crystals or glasses; hitherto, no transport equation has been able to account for both. In the paper https://arxiv.org/abs/1901.01964, we derive such equation, resulting in a thermal conductivity that reduces to the Peierls and Allen-Feldman limits, respectively, in anharmonic-and-ordered or harmonic-and-disordered solids, while also covering the intermediate regimes where both effects are relevant. This approach also solves the long-standing problem of accurately predicting the thermal properties of crystals with ultralow or glass-like thermal conductivity, as we show with an application to a thermoelectric material representative of this class. This database contains the raw data related to the images reported in the paper  https://arxiv.org/abs/1901.01964."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0001/v2"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Thermal conductivity"
-        },
-        {
-            "name": "CsPbBr"
-        },
-        {
-            "name": "Phonon linewidths"
-        }
-    ],
-    "title": [
-        "Unified theory of thermal transport in crystals and disordered solids"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0001/v2"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/aecd23e4-af20-5bd7-a35a-ab6c1a3e1818.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/aecd23e4-af20-5bd7-a35a-ab6c1a3e1818.json
deleted file mode 100644
index eccc1087..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/aecd23e4-af20-5bd7-a35a-ab6c1a3e1818.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0009/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0009/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0009/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-02-21T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Hampel, Alexander",
-        "Franchini, Cesare",
-        "Liu, Peitao",
-        "Ederer, Claude"
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0009/v1;2019-06-12Z;DOI;Dataset;Hampel, Alexander;Ederer, Claude;Liu, Peitao;Franchini, Cesare;Energetics of the coupled electronic\u2013structural transition in the rare-earth nickelates;Materials Cloud;2019-02-21;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;MARVEL;Electronic properties and materials;Quantum Materials;Dynamical Mean Field Theory;correlated systems structural prediction ;doi:10.24435/materialscloud:2019.0009/v1;https://archive.materialscloud.org/2019.0009/v1;en;Rare-earth nickelates exhibit a metal\u2013insulator transition accompanied by a structural distortion that breaks the symmetry between formerly equivalent Ni sites. The quantitative theoretical description of this coupled electronic\u2013structural instability is extremely challenging. Here, we address this issue by simultaneously taking into account both structural and electronic degrees of freedom using a charge self-consistent combination of density functional theory and dynamical mean-field theory, together with screened interaction parameters obtained from the constrained random phase approximation. Our total energy calculations show that the coupling to an electronic instability toward a charge disproportionated insulating state is crucial to stabilize the structural distortion, leading to a clear first order character of the coupled transition. The decreasing octahedral rotations across the series suppress this electronic instability and simultaneously increase the screening of the effective Coulomb interaction, thus weakening the correlation effects responsible for the metal\u2013insulator transition. Our approach allows to obtain accurate values for the structural distortion and thus facilitates a comprehensive understanding, both qualitatively and quantitatively, of the complex interplay between structural properties and electronic correlation effects across the nickelate series.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "aecd23e4-af20-5bd7-a35a-ab6c1a3e1818",
-    "notes": [
-        "Rare-earth nickelates exhibit a metal\u2013insulator transition accompanied by a structural distortion that breaks the symmetry between formerly equivalent Ni sites. The quantitative theoretical description of this coupled electronic\u2013structural instability is extremely challenging. Here, we address this issue by simultaneously taking into account both structural and electronic degrees of freedom using a charge self-consistent combination of density functional theory and dynamical mean-field theory, together with screened interaction parameters obtained from the constrained random phase approximation. Our total energy calculations show that the coupling to an electronic instability toward a charge disproportionated insulating state is crucial to stabilize the structural distortion, leading to a clear first order character of the coupled transition. The decreasing octahedral rotations across the series suppress this electronic instability and simultaneously increase the screening of the effective Coulomb interaction, thus weakening the correlation effects responsible for the metal\u2013insulator transition. Our approach allows to obtain accurate values for the structural distortion and thus facilitates a comprehensive understanding, both qualitatively and quantitatively, of the complex interplay between structural properties and electronic correlation effects across the nickelate series."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0009/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "MARVEL"
-        },
-        {
-            "name": "Electronic properties materials"
-        },
-        {
-            "name": "Quantum Materials"
-        },
-        {
-            "name": "Dynamical Mean Field Theory"
-        },
-        {
-            "name": "correlated systems structural prediction"
-        }
-    ],
-    "title": [
-        "Energetics of the coupled electronic\u2013structural transition in the rare-earth nickelates"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0009/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/b2041c2e-e90b-5432-8fb2-73335806fa3a.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/b2041c2e-e90b-5432-8fb2-73335806fa3a.json
deleted file mode 100644
index 3966da07..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/b2041c2e-e90b-5432-8fb2-73335806fa3a.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0019/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0019/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0019/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-12-03T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Curtin, William",
-        "Yin, Binglun"
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0019/v1;2019-06-12Z;DOI;Dataset;Yin, Binglun;Curtin, William;Special quasi-random structures for the 6-component high entropy alloys;Materials Cloud;2018-12-03;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;special quasi-random structures (SQSs);high entropy alloys;random alloys;misfit volumes;doi:10.24435/materialscloud:2018.0019/v1;https://archive.materialscloud.org/2018.0019/v1;en;We propose a general method to calculate the average misfit volumes of atoms in any random alloy via DFT calculations. The method is validated with an example of a 6-component equi-composition high entropy alloy. The special quasi-random structures (SQSs) used in our work are reported here.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "b2041c2e-e90b-5432-8fb2-73335806fa3a",
-    "notes": [
-        "We propose a general method to calculate the average misfit volumes of atoms in any random alloy via DFT calculations. The method is validated with an example of a 6-component equi-composition high entropy alloy. The special quasi-random structures (SQSs) used in our work are reported here."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0019/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "special quasi-random structures SQSs"
-        },
-        {
-            "name": "high entropy alloys"
-        },
-        {
-            "name": "random alloys"
-        },
-        {
-            "name": "misfit volumes"
-        }
-    ],
-    "title": [
-        "Special quasi-random structures for the 6-component high entropy alloys"
-    ],
-    "url": "https://archive.materialscloud.org/2018.0019/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/b2951f5c-54ab-5045-99ee-bebb5e4b09ef.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/b2951f5c-54ab-5045-99ee-bebb5e4b09ef.json
deleted file mode 100644
index a950132f..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/b2951f5c-54ab-5045-99ee-bebb5e4b09ef.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0027/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0027/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0027/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-05-30T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Pasquarello, Alfredo",
-        "Guo, Zhendong",
-        "Ambrosio, Francesco"
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0027/v1;2019-06-12Z;DOI;Dataset;Guo, Zhendong;Ambrosio, Francesco;Pasquarello, Alfredo;Extrinsic Defects in Amorphous Oxides: Hydrogen, Carbon, and Nitrogen Impurities in Alumina;Materials Cloud;2019-05-30;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;extrinsic defects;Carbon;total charge;alumina;hydrogen;carbon;nitrogen;doi:10.24435/materialscloud:2019.0027/v1;https://archive.materialscloud.org/2019.0027/v1;en;This entry provides the most stable defect configurations of hydrogen, carbon, and nitrogen impurities in alumina, which are identified through ab initio molecular dynamics in various charge states and structural relaxations with the PBE functional. The structural configurations related to carbon and nitrogen impurities are found to depend on the total charge set in the simulation cell.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "b2951f5c-54ab-5045-99ee-bebb5e4b09ef",
-    "notes": [
-        "This entry provides the most stable defect configurations of hydrogen, carbon, and nitrogen impurities in alumina, which are identified through ab initio molecular dynamics in various charge states and structural relaxations with the PBE functional. The structural configurations related to carbon and nitrogen impurities are found to depend on the total charge set in the simulation cell."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0027/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "extrinsic defects"
-        },
-        {
-            "name": "Carbon"
-        },
-        {
-            "name": "total charge"
-        },
-        {
-            "name": "alumina"
-        },
-        {
-            "name": "hydrogen"
-        },
-        {
-            "name": "carbon"
-        },
-        {
-            "name": "nitrogen"
-        }
-    ],
-    "title": [
-        "Extrinsic Defects in Amorphous Oxides: Hydrogen, Carbon, and Nitrogen Impurities in Alumina"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0027/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/b2c72591-4587-5bef-998e-30c14be9337f.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/b2c72591-4587-5bef-998e-30c14be9337f.json
deleted file mode 100644
index 8b1e8743..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/b2c72591-4587-5bef-998e-30c14be9337f.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0024/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0024/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0024/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-05-29T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Jablonka, Kevin Maik",
-        "Ongari, Daniele ",
-        "Smit, Berend"
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0024/v1;2019-06-12Z;DOI;Dataset;Smit, Berend;Jablonka, Kevin Maik;Ongari, Daniele ;Applicability of tail-corrections in the molecular simulations of porous materials;Materials Cloud;2019-05-29;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;MARVEL;zeolites;GCMC;Metal-Organic frameworks;tail-corrections;Covalent-Organic frameworks;doi:10.24435/materialscloud:2019.0024/v1;https://archive.materialscloud.org/2019.0024/v1;en;Molecular simulations with periodic boundary conditions require to define a certain cutoff distance   beyond which pairwise dispersion interactions are neglected. For the simulation of homogeneous phases it is well-established to use tail-corrections, that can remedy this truncation of the potential. These corrections are built under the assumption that beyond  the cutoff the radial distribution function is equal to one. In this work we shed some light on the discussion whether or not tail corrections should be used in the  modelling of heterogeneous systems. We show that for the adsorption of gasses in a diverse set  nanoporous crystalline materials (zeolites, Covalent Organic Frameworks (COFs), and Metal Organic Frameworks (MOFs)), tail-corrections are an appropriate choice with which the results are much less sensitive to the details of the truncation. ",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "b2c72591-4587-5bef-998e-30c14be9337f",
-    "notes": [
-        "Molecular simulations with periodic boundary conditions require to define a certain cutoff distance   beyond which pairwise dispersion interactions are neglected. For the simulation of homogeneous phases it is well-established to use tail-corrections, that can remedy this truncation of the potential. These corrections are built under the assumption that beyond  the cutoff the radial distribution function is equal to one. In this work we shed some light on the discussion whether or not tail corrections should be used in the  modelling of heterogeneous systems. We show that for the adsorption of gasses in a diverse set  nanoporous crystalline materials (zeolites, Covalent Organic Frameworks (COFs), and Metal Organic Frameworks (MOFs)), tail-corrections are an appropriate choice with which the results are much less sensitive to the details of the truncation. "
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0024/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "MARVEL"
-        },
-        {
-            "name": "zeolites"
-        },
-        {
-            "name": "GCMC"
-        },
-        {
-            "name": "Metal-Organic frameworks"
-        },
-        {
-            "name": "tail-corrections"
-        },
-        {
-            "name": "Covalent-Organic frameworks"
-        }
-    ],
-    "title": [
-        "Applicability of tail-corrections in the molecular simulations of porous materials"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0024/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/b92f55d1-b0ea-5113-9b35-0a5a1cbb51ba.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/b92f55d1-b0ea-5113-9b35-0a5a1cbb51ba.json
deleted file mode 100644
index c779412b..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/b92f55d1-b0ea-5113-9b35-0a5a1cbb51ba.json
+++ /dev/null
@@ -1,97 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0008/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0008/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0008/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-05-15T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Haranczyk, Maciej",
-        "Simon, Cory M.",
-        "Martin, Richard L.",
-        "Smit, Berend"
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0008/v1;2019-06-12Z;DOI;Dataset;Martin, Richard L.;Simon, Cory M.;Smit, Berend;Haranczyk, Maciej;In Silico Design of Porous Polymer Networks: High Throughput Screening for Methane Storage Materials;Materials Cloud;2018-05-15;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;3D;three-dimensional;database;high-throughput;porous polymer networks;PPN;nanoporous;methane storage;deliverable capacities;DC;grand canonical Monte Carlo;GCMC;doi:10.24435/materialscloud:2018.0008/v1;https://archive.materialscloud.org/2018.0008/v1;en;Porous polymer networks (PPNs) are a class of advanced porous materials that combine the advantages of cheap and stable polymers with the high surface areas and tunable chemistry of metal\u2013organic frameworks. They are of particular interest for gas separation or storage applications, for instance, as methane adsorbents for a vehicular natural gas tank or other portable applications. PPNs are self-assembled from distinct building units; here, we utilize commercially available chemical fragments and two experimentally known synthetic routes to design in silico a large database of synthetically realistic PPN materials. All structures from our database of 18,000 materials have been relaxed with semiempirical electronic structure methods and characterized with Grand-canonical Monte Carlo simulations for methane uptake and deliverable (working) capacity. A number of novel structure\u2013property relationships that govern methane storage performance were identified. The relationships are translated into experimental guidelines to realize the ideal PPN structure. We found that cooperative methane\u2013methane attractions were present in all of the best-performing materials, highlighting the importance of guest interaction in the design of optimal materials for methane storage.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "b92f55d1-b0ea-5113-9b35-0a5a1cbb51ba",
-    "notes": [
-        "Porous polymer networks (PPNs) are a class of advanced porous materials that combine the advantages of cheap and stable polymers with the high surface areas and tunable chemistry of metal\u2013organic frameworks. They are of particular interest for gas separation or storage applications, for instance, as methane adsorbents for a vehicular natural gas tank or other portable applications. PPNs are self-assembled from distinct building units; here, we utilize commercially available chemical fragments and two experimentally known synthetic routes to design in silico a large database of synthetically realistic PPN materials. All structures from our database of 18,000 materials have been relaxed with semiempirical electronic structure methods and characterized with Grand-canonical Monte Carlo simulations for methane uptake and deliverable (working) capacity. A number of novel structure\u2013property relationships that govern methane storage performance were identified. The relationships are translated into experimental guidelines to realize the ideal PPN structure. We found that cooperative methane\u2013methane attractions were present in all of the best-performing materials, highlighting the importance of guest interaction in the design of optimal materials for methane storage."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0008/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "three-dimensional"
-        },
-        {
-            "name": "database"
-        },
-        {
-            "name": "high-throughput"
-        },
-        {
-            "name": "porous polymer networks"
-        },
-        {
-            "name": "PPN"
-        },
-        {
-            "name": "nanoporous"
-        },
-        {
-            "name": "methane storage"
-        },
-        {
-            "name": "deliverable capacities"
-        },
-        {
-            "name": "DC"
-        },
-        {
-            "name": "grand canonical Monte Carlo"
-        },
-        {
-            "name": "GCMC"
-        }
-    ],
-    "title": [
-        "In Silico Design of Porous Polymer Networks: High Throughput Screening for Methane Storage Materials"
-    ],
-    "url": "https://archive.materialscloud.org/2018.0008/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/b9647ee4-c0fc-5031-9a09-aba633c04332.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/b9647ee4-c0fc-5031-9a09-aba633c04332.json
deleted file mode 100644
index 85cdc7a4..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/b9647ee4-c0fc-5031-9a09-aba633c04332.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0007/v2",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0007/v2",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0007/v2"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-02-19T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "RelatedIdentifier": [
-        "https://www.materialscloud.org/discover/ccg"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Heinen, Stefan N.",
-        "Corminboeuf, Cl\u00e9mence",
-        "Wodrich, Matthew D.",
-        "Meyer, Benjamin",
-        "Fabrizio, Alberto",
-        "Sawatlon, Boodsarin",
-        "von Lilienfeld, O. Anatole"
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0007/v2;2019-06-12Z;DOI;Dataset;Sawatlon, Boodsarin;Fabrizio, Alberto;Meyer, Benjamin;Heinen, Stefan N.;Wodrich, Matthew D.;von Lilienfeld, O. Anatole;Corminboeuf, Cl\u00e9mence;Mining the C-C Cross-Coupling Genome using Machine Learning;Materials Cloud;2019-02-19;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;machine learning;homogeneous catalysis;volcano plot;transition metal complexes;sketch-map;doi:10.24435/materialscloud:2019.0007/v2;https://archive.materialscloud.org/2019.0007/v2;en;https://www.materialscloud.org/discover/ccg;Applications of machine-learning (ML) techniques to the study of catalytic processes have begun to appear in the literature with increasing frequency. The computational speed up provided by ML allows the properties and energetics of thousands of prospective catalysts to be rapidly assessed. These results, once compiled into a database containing different properties, can be mined with the goal of establishing relationships between the intrinsic chemical properties of different catalysts and their overall catalytic performance. Previously, we applied ML models to predict the performance of 18,000 prospective catalysts for a Suzuki coupling reaction using molecular volcano plots. Here, we expand on our earlier work by examining a larger section of the C-C cross-coupling genome by using a dimensionality-reducing data-clustering algorithms (i.e., sketch-map) to, first, identify the compatibility of each catalyst with different C-C cross-coupling variants (e.g., Suzuki, Kumada, Negishi, Stille, and/or Hiyama) and, second, to uncover links between the chemical property of a catalyst and its catalytic activity. Our findings, based on the analysis of 18,000 catalysts, reveal strong correlations between a catalyst\u2019s HOMO energy and the suitability of its thermodynamic profile. These values can, subsequently, be tuned in order to maximize the thermodynamics of the catalytic cycle through the judicious choice of metal centers and the \u03c0-accepting/\u03c3-donating nature of the flanking ligands. Overall, group 10 metals (Ni, Pd, Pt) are best coupled with the strong \u03c0-acceptor ligands and group 11 metals (Cu, Ag, Au) with weak \u03c0-acceptors, which maximize the thermodynamic drive of the catalytic cycle.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "b9647ee4-c0fc-5031-9a09-aba633c04332",
-    "notes": [
-        "Applications of machine-learning (ML) techniques to the study of catalytic processes have begun to appear in the literature with increasing frequency. The computational speed up provided by ML allows the properties and energetics of thousands of prospective catalysts to be rapidly assessed. These results, once compiled into a database containing different properties, can be mined with the goal of establishing relationships between the intrinsic chemical properties of different catalysts and their overall catalytic performance. Previously, we applied ML models to predict the performance of 18,000 prospective catalysts for a Suzuki coupling reaction using molecular volcano plots. Here, we expand on our earlier work by examining a larger section of the C-C cross-coupling genome by using a dimensionality-reducing data-clustering algorithms (i.e., sketch-map) to, first, identify the compatibility of each catalyst with different C-C cross-coupling variants (e.g., Suzuki, Kumada, Negishi, Stille, and/or Hiyama) and, second, to uncover links between the chemical property of a catalyst and its catalytic activity. Our findings, based on the analysis of 18,000 catalysts, reveal strong correlations between a catalyst\u2019s HOMO energy and the suitability of its thermodynamic profile. These values can, subsequently, be tuned in order to maximize the thermodynamics of the catalytic cycle through the judicious choice of metal centers and the \u03c0-accepting/\u03c3-donating nature of the flanking ligands. Overall, group 10 metals (Ni, Pd, Pt) are best coupled with the strong \u03c0-acceptor ligands and group 11 metals (Cu, Ag, Au) with weak \u03c0-acceptors, which maximize the thermodynamic drive of the catalytic cycle."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0007/v2"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine learning"
-        },
-        {
-            "name": "homogeneous catalysis"
-        },
-        {
-            "name": "volcano plot"
-        },
-        {
-            "name": "transition metal complexes"
-        },
-        {
-            "name": "sketch-map"
-        }
-    ],
-    "title": [
-        "Mining the C-C Cross-Coupling Genome using Machine Learning"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0007/v2"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/bad462b1-417f-5b04-b6c9-ba16ccd597bc.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/bad462b1-417f-5b04-b6c9-ba16ccd597bc.json
deleted file mode 100644
index 3d5ec229..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/bad462b1-417f-5b04-b6c9-ba16ccd597bc.json
+++ /dev/null
@@ -1,105 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0001/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0001/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0001/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-01-26T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "RelatedIdentifier": [
-        "https://www.materialscloud.org/discover/sssp",
-        "https://www.materialscloud.org/explore/sssp"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Castelli, Ivano E.",
-        "Mounet, Nicolas",
-        "Marzari, Nicola",
-        "Marrazzo, Antimo",
-        "Prandini, Gianluca"
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0001/v1;2019-06-12Z;DOI;Dataset;Prandini, Gianluca;Marrazzo, Antimo;Castelli, Ivano E.;Mounet, Nicolas;Marzari, Nicola;A Standard Solid State Pseudopotentials (SSSP) library optimized for accuracy and efficiency (Version 1.0, data download);Materials Cloud;2018-01-26;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;SSSP;pseudopotentials;database;high-throughput;library;standard;DFT;calculations;vibrational properties;phonons;electronic properties;electronic bands;cohesive energy;chessboards;elemental solids;verification;accuracy;efficiency;MARVEL;doi:10.24435/materialscloud:2018.0001/v1;https://archive.materialscloud.org/2018.0001/v1;en;https://www.materialscloud.org/discover/sssp;https://www.materialscloud.org/explore/sssp;Despite the enormous success and popularity of density functional theory, systematic verification and validation studies are still very limited both in number and scope. Here, we propose a universal standard protocol to verify publicly available pseudopotential libraries, based on several independent criteria including verification against all-electron equations of state and plane-wave convergence tests for phonon frequencies, band structure, cohesive energy and pressure. Adopting these criteria we obtain two optimal pseudopotential sets, namely the Standard Solid State Pseudopotential (SSSP) efficiency and accuracy libraries, tailored for high-throughput materials screening and high-precision materials modelling. As of today, the SSSP accuracy library is the most accurate open-source pseudopotential library available. This archive entry contains the database of calculations (phonons, cohesive energy, equation of state, band structure, pressure, etc.) together with the provenance of all data and calculations as stored by AiiDA.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "bad462b1-417f-5b04-b6c9-ba16ccd597bc",
-    "notes": [
-        "Despite the enormous success and popularity of density functional theory, systematic verification and validation studies are still very limited both in number and scope. Here, we propose a universal standard protocol to verify publicly available pseudopotential libraries, based on several independent criteria including verification against all-electron equations of state and plane-wave convergence tests for phonon frequencies, band structure, cohesive energy and pressure. Adopting these criteria we obtain two optimal pseudopotential sets, namely the Standard Solid State Pseudopotential (SSSP) efficiency and accuracy libraries, tailored for high-throughput materials screening and high-precision materials modelling. As of today, the SSSP accuracy library is the most accurate open-source pseudopotential library available. This archive entry contains the database of calculations (phonons, cohesive energy, equation of state, band structure, pressure, etc.) together with the provenance of all data and calculations as stored by AiiDA."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0001/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "SSSP"
-        },
-        {
-            "name": "pseudopotentials"
-        },
-        {
-            "name": "database"
-        },
-        {
-            "name": "high-throughput"
-        },
-        {
-            "name": "library"
-        },
-        {
-            "name": "standard"
-        },
-        {
-            "name": "DFT"
-        },
-        {
-            "name": "calculations"
-        },
-        {
-            "name": "vibrational properties"
-        },
-        {
-            "name": "phonons"
-        },
-        {
-            "name": "electronic properties"
-        },
-        {
-            "name": "electronic bands"
-        }
-    ],
-    "title": [
-        "A Standard Solid State Pseudopotentials (SSSP) library optimized for accuracy and efficiency (Version 1.0, data download)"
-    ],
-    "url": "https://archive.materialscloud.org/2018.0001/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/bbdd0d8f-f77a-5e47-ae0d-ce3840e5f5cc.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/bbdd0d8f-f77a-5e47-ae0d-ce3840e5f5cc.json
deleted file mode 100644
index 1cd2b931..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/bbdd0d8f-f77a-5e47-ae0d-ce3840e5f5cc.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0013/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0013/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0013/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-07-31T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Barthel, Senja",
-        "Braun, Efrem",
-        "Smit, Berend",
-        "Lee, Yongjin",
-        "Proserpio, Davide M.",
-        "Baburin, Igor A.",
-        "Mercado, Rocio",
-        "Moosavi, Seyed Mohamad"
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0013/v1;2019-06-12Z;DOI;Dataset;Braun, Efrem;Lee, Yongjin;Moosavi, Seyed Mohamad;Barthel, Senja;Mercado, Rocio;Baburin, Igor A.;Proserpio, Davide M.;Smit, Berend;Generating carbon schwarzites via zeolite-templating;Materials Cloud;2018-07-31;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;schwarzites;carbon materials;ZTC;TPMS;MARVEL;doi:10.24435/materialscloud:2018.0013/v1;https://archive.materialscloud.org/2018.0013/v1;en;Zeolite-templated carbons (ZTCs) comprise a relatively recent material class synthesized via the chemical vapor deposition of a carbon-containing precursor on a zeolite template, followed by the removal of the template. We have developed a theoretical framework to generate a ZTC model from any given zeolite structure, which we show can successfully predict the structure of known ZTCs. We use our method to generate a library of ZTCs from all known zeolites, to establish criteria for which zeolites can produce experimentally accessible ZTCs, and to identify over 10 ZTCs that have never before been synthesized. We show that ZTCs partition space into two disjoint labyrinths that can be described by a pair of interpenetrating nets. Since such a pair of nets also describes a triply periodic minimal surface (TPMS), our results establish the relationship between ZTCs and schwarzites\u2014carbon materials with negative Gaussian curvature that resemble TPMSs\u2014linking the research topics and demonstrating that schwarzites should no longer be thought of as purely hypothetical materials.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "bbdd0d8f-f77a-5e47-ae0d-ce3840e5f5cc",
-    "notes": [
-        "Zeolite-templated carbons (ZTCs) comprise a relatively recent material class synthesized via the chemical vapor deposition of a carbon-containing precursor on a zeolite template, followed by the removal of the template. We have developed a theoretical framework to generate a ZTC model from any given zeolite structure, which we show can successfully predict the structure of known ZTCs. We use our method to generate a library of ZTCs from all known zeolites, to establish criteria for which zeolites can produce experimentally accessible ZTCs, and to identify over 10 ZTCs that have never before been synthesized. We show that ZTCs partition space into two disjoint labyrinths that can be described by a pair of interpenetrating nets. Since such a pair of nets also describes a triply periodic minimal surface (TPMS), our results establish the relationship between ZTCs and schwarzites\u2014carbon materials with negative Gaussian curvature that resemble TPMSs\u2014linking the research topics and demonstrating that schwarzites should no longer be thought of as purely hypothetical materials."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0013/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "schwarzites"
-        },
-        {
-            "name": "carbon materials"
-        },
-        {
-            "name": "ZTC"
-        },
-        {
-            "name": "TPMS"
-        },
-        {
-            "name": "MARVEL"
-        }
-    ],
-    "title": [
-        "Generating carbon schwarzites via zeolite-templating"
-    ],
-    "url": "https://archive.materialscloud.org/2018.0013/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/bfc9e0d6-bb0d-52e7-8074-332a2521cb0a.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/bfc9e0d6-bb0d-52e7-8074-332a2521cb0a.json
deleted file mode 100644
index 7663227a..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/bfc9e0d6-bb0d-52e7-8074-332a2521cb0a.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0001/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0001/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0001/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-01-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution Non Commercial 4.0 International https://creativecommons.org/licenses/by-nc/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Marzari, Nicola",
-        "Mauri, Francesco",
-        "Simoncelli, Michele"
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0001/v1;2019-06-12Z;DOI;Dataset;Simoncelli, Michele;Marzari, Nicola;Mauri, Francesco;Unified theory of thermal transport in crystals and disordered solids;Materials Cloud;2019-01-08;Creative Commons Attribution Non Commercial 4.0 International https://creativecommons.org/licenses/by-nc/4.0/legalcode;info:eu-repo/semantics/openAccess;Thermal conductivity;CsPbBr3;Phonon linewidths;doi:10.24435/materialscloud:2019.0001/v1;https://archive.materialscloud.org/2019.0001/v1;en;Crystals and glasses exhibit fundamentally different heat conduction mechanisms: the periodicity of crystals allows for the excitation of propagating vibrational waves that carry heat, as first discussed by Peierls; in glasses, the lack of periodicity breaks Peierls&#39; picture and heat is mainly carried by the coupling of vibrational modes, often described by a harmonic theory introduced by Allen and Feldman. Anharmonicity or disorder are thus the limiting factors for thermal conductivity in crystals or glasses; hitherto, no transport equation has been able to account for both. In the paper https://arxiv.org/abs/1901.01964, we derive such equation, resulting in a thermal conductivity that reduces to the Peierls and Allen-Feldman limits, respectively, in anharmonic-and-ordered or harmonic-and-disordered solids, while also covering the intermediate regimes where both effects are relevant. This approach also solves the long-standing problem of accurately predicting the thermal properties of crystals with ultralow or glass-like thermal conductivity, as we show with an application to a thermoelectric material representative of this class. This database contains the raw data related to the images reported in the paper  https://arxiv.org/abs/1901.01964.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "bfc9e0d6-bb0d-52e7-8074-332a2521cb0a",
-    "notes": [
-        "Crystals and glasses exhibit fundamentally different heat conduction mechanisms: the periodicity of crystals allows for the excitation of propagating vibrational waves that carry heat, as first discussed by Peierls; in glasses, the lack of periodicity breaks Peierls&#39; picture and heat is mainly carried by the coupling of vibrational modes, often described by a harmonic theory introduced by Allen and Feldman. Anharmonicity or disorder are thus the limiting factors for thermal conductivity in crystals or glasses; hitherto, no transport equation has been able to account for both. In the paper https://arxiv.org/abs/1901.01964, we derive such equation, resulting in a thermal conductivity that reduces to the Peierls and Allen-Feldman limits, respectively, in anharmonic-and-ordered or harmonic-and-disordered solids, while also covering the intermediate regimes where both effects are relevant. This approach also solves the long-standing problem of accurately predicting the thermal properties of crystals with ultralow or glass-like thermal conductivity, as we show with an application to a thermoelectric material representative of this class. This database contains the raw data related to the images reported in the paper  https://arxiv.org/abs/1901.01964."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0001/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Thermal conductivity"
-        },
-        {
-            "name": "CsPbBr"
-        },
-        {
-            "name": "Phonon linewidths"
-        }
-    ],
-    "title": [
-        "Unified theory of thermal transport in crystals and disordered solids"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0001/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/c1acd268-0cba-5b7d-bb23-2f41bc04c893.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/c1acd268-0cba-5b7d-bb23-2f41bc04c893.json
deleted file mode 100644
index b5184bfc..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/c1acd268-0cba-5b7d-bb23-2f41bc04c893.json
+++ /dev/null
@@ -1,92 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0017/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0017/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0017/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-05-09T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution Non Commercial 4.0 International https://creativecommons.org/licenses/by-nc/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Grossman, Jeffrey",
-        "Shao-Horn, Yang",
-        "Xie, Tian",
-        "France-Lanord, Arthur",
-        "Wang, Yanming"
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0017/v1;2019-06-12Z;DOI;Dataset;Xie, Tian;France-Lanord, Arthur;Wang, Yanming;Shao-Horn, Yang;Grossman, Jeffrey;Graph Dynamical Networks for Unsupervised Learning of Atomic Scale Dynamics in Materials;Materials Cloud;2019-05-09;Creative Commons Attribution Non Commercial 4.0 International https://creativecommons.org/licenses/by-nc/4.0/legalcode;info:eu-repo/semantics/openAccess;machine learning;molecular dynamics;polymer;deep learning;graph;neural networks;amorphous;interface;trajectory;doi:10.24435/materialscloud:2019.0017/v1;https://archive.materialscloud.org/2019.0017/v1;en;Understanding the dynamical processes that govern the performance of functional materials is essential for the design of next generation materials to tackle global energy and environmental challenges. Many of these processes involve the dynamics of individual atoms or small molecules in condensed phases, e.g. lithium ions in electrolytes, water molecules in membranes, molten atoms at interfaces, etc., which are difficult to understand due to the complexity of local environments. We develop graph dynamical networks, an unsupervised learning approach for understanding atomic scale dynamics in arbitrary phases and environments from molecular dynamics simulations. We show that important dynamical information can be learned for various multi-component amorphous material systems, which is difficult to obtain otherwise. We develop a software package &#34;gdynet&#34; at https://github.com/txie-93/gdynet which implements the graph dynamical networks algorithm. This record contains the MD trajectories of a Li-S toy system, a Si-Au binary system, and a polymer battery electrolyte system in a format designed for the &#34;gdynet&#34; package.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "c1acd268-0cba-5b7d-bb23-2f41bc04c893",
-    "notes": [
-        "Understanding the dynamical processes that govern the performance of functional materials is essential for the design of next generation materials to tackle global energy and environmental challenges. Many of these processes involve the dynamics of individual atoms or small molecules in condensed phases, e.g. lithium ions in electrolytes, water molecules in membranes, molten atoms at interfaces, etc., which are difficult to understand due to the complexity of local environments. We develop graph dynamical networks, an unsupervised learning approach for understanding atomic scale dynamics in arbitrary phases and environments from molecular dynamics simulations. We show that important dynamical information can be learned for various multi-component amorphous material systems, which is difficult to obtain otherwise. We develop a software package &#34;gdynet&#34; at https://github.com/txie-93/gdynet which implements the graph dynamical networks algorithm. This record contains the MD trajectories of a Li-S toy system, a Si-Au binary system, and a polymer battery electrolyte system in a format designed for the &#34;gdynet&#34; package."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0017/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine learning"
-        },
-        {
-            "name": "molecular dynamics"
-        },
-        {
-            "name": "polymer"
-        },
-        {
-            "name": "deep learning"
-        },
-        {
-            "name": "graph"
-        },
-        {
-            "name": "neural networks"
-        },
-        {
-            "name": "amorphous"
-        },
-        {
-            "name": "interface"
-        },
-        {
-            "name": "trajectory"
-        }
-    ],
-    "title": [
-        "Graph Dynamical Networks for Unsupervised Learning of Atomic Scale Dynamics in Materials"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0017/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/c64df3f8-cb0b-5094-a76e-8b06499e547a.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/c64df3f8-cb0b-5094-a76e-8b06499e547a.json
deleted file mode 100644
index a09a3004..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/c64df3f8-cb0b-5094-a76e-8b06499e547a.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0004/v2",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0004/v2",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0004/v2"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-04-16T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Parrinello, Michele",
-        "Invernizzi, Michele "
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0004/v2;2019-06-12Z;DOI;Dataset;Invernizzi, Michele ;Parrinello, Michele;Making the best of a bad situation: a multiscale approach to free energy calculation;Materials Cloud;2019-04-16;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;enhanced sampling;free energy;metadynamics;doi:10.24435/materialscloud:2019.0004/v2;https://archive.materialscloud.org/2019.0004/v2;en;Many enhanced sampling techniques rely on the identification of a number of collective variables that describe all the slow modes of the system. By constructing a bias potential in this reduced space one is then able to sample efficiently and reconstruct the free energy landscape. In methods like metadynamics, the quality of these collective variables plays a key role in convergence efficiency. Unfortunately in many systems of interest it is not possible to identify an optimal collective variable, and one must deal with the non-ideal situation of a system in which some slow modes are not accelerated. \n<br/>\nWe propose a two-step approach in which, by taking into account the residual multiscale nature of the problem, one is able to significantly speed up convergence. To do so, we combine an exploratory metadynamics run with an optimization of the free energy difference between metastable states, based on the recently proposed variationally enhanced sampling method. This new method is well parallelizable and is especially suited for complex systems, because of its simplicity and clear underlying physical picture.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "c64df3f8-cb0b-5094-a76e-8b06499e547a",
-    "notes": [
-        "Many enhanced sampling techniques rely on the identification of a number of collective variables that describe all the slow modes of the system. By constructing a bias potential in this reduced space one is then able to sample efficiently and reconstruct the free energy landscape. In methods like metadynamics, the quality of these collective variables plays a key role in convergence efficiency. Unfortunately in many systems of interest it is not possible to identify an optimal collective variable, and one must deal with the non-ideal situation of a system in which some slow modes are not accelerated. \n<br/>\nWe propose a two-step approach in which, by taking into account the residual multiscale nature of the problem, one is able to significantly speed up convergence. To do so, we combine an exploratory metadynamics run with an optimization of the free energy difference between metastable states, based on the recently proposed variationally enhanced sampling method. This new method is well parallelizable and is especially suited for complex systems, because of its simplicity and clear underlying physical picture."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0004/v2"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "enhanced sampling"
-        },
-        {
-            "name": "free energy"
-        },
-        {
-            "name": "metadynamics"
-        }
-    ],
-    "title": [
-        "Making the best of a bad situation: a multiscale approach to free energy calculation"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0004/v2"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/c7807157-1b11-5bb6-9b26-7c31b3716cf6.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/c7807157-1b11-5bb6-9b26-7c31b3716cf6.json
deleted file mode 100644
index 10e151ec..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/c7807157-1b11-5bb6-9b26-7c31b3716cf6.json
+++ /dev/null
@@ -1,108 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2017.0008/v3",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2017.0008/v3",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2017.0008/v3"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-04-03T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "RelatedIdentifier": [
-        "https://www.materialscloud.org/discover/2dstructures",
-        "https://www.materialscloud.org/explore/2dstructures"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Marzari, Nicola",
-        "Campi, Davide",
-        "Cepellotti, Andrea",
-        "Schwaller, Philippe",
-        "Gibertini, Marco",
-        "Castelli, Ivano E.",
-        "Marrazzo, Antimo",
-        "Sohier, Thibault",
-        "Mounet, Nicolas",
-        "Pizzi, Giovanni",
-        "Merkys, Andrius"
-    ],
-    "fulltext": "oai:materialscloud.org:2017.0008/v3;2019-06-12Z;DOI;Dataset;Mounet, Nicolas;Gibertini, Marco;Schwaller, Philippe;Campi, Davide;Merkys, Andrius;Marrazzo, Antimo;Sohier, Thibault;Castelli, Ivano E.;Cepellotti, Andrea;Pizzi, Giovanni;Marzari, Nicola;Two-dimensional materials from high-throughput computational exfoliation of  experimentally known compounds;Materials Cloud;2019-04-03;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;2D;two-dimensional;monolayer;database;high-throughput;DFT;vibrational properties;phonons;electronic properties;electronic bands;magnetic properties;MARVEL;doi:10.24435/materialscloud:2017.0008/v3;https://archive.materialscloud.org/2017.0008/v3;en;https://www.materialscloud.org/discover/2dstructures;https://www.materialscloud.org/explore/2dstructures;Two-dimensional (2D) materials have emerged as promising candidates for next-generation electronic and optoelectronic applications. Yet, only a few dozens of 2D materials have been successfully synthesized or exfoliated. Here, we search for novel 2D materials that can be easily exfoliated from their parent compounds. Starting from 108423 unique, experimentally known three-dimensional compounds we identify a subset of 5619 that appear layered according to robust geometric and bonding criteria. High-throughput calculations using van-der-Waals density-functional theory, validated against experimental structural data and calculated random-phase-approximation binding energies, allow to identify 1825 compounds that are either easily or potentially exfoliable. In particular, the subset of 1036 easily exfoliable cases provides novel structural prototypes and simple ternary compounds as well as a large portfolio of materials to search from for optimal properties. For a subset of 258 compounds we explore vibrational, electronic, magnetic, and topological properties, identifying 56 ferromagnetic and antiferromagnetic systems, including half-metals and half-semiconductors. This archive entry contains the database of 2D materials (structural parameters, band structures, binding energies, phonons for the subset of the 258 easily exfoliable materials with less than 6 atoms, structures and binding energies for the remaining 1567 materials) together with the provenance of all data and calculations as stored by AiiDA.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "c7807157-1b11-5bb6-9b26-7c31b3716cf6",
-    "notes": [
-        "Two-dimensional (2D) materials have emerged as promising candidates for next-generation electronic and optoelectronic applications. Yet, only a few dozens of 2D materials have been successfully synthesized or exfoliated. Here, we search for novel 2D materials that can be easily exfoliated from their parent compounds. Starting from 108423 unique, experimentally known three-dimensional compounds we identify a subset of 5619 that appear layered according to robust geometric and bonding criteria. High-throughput calculations using van-der-Waals density-functional theory, validated against experimental structural data and calculated random-phase-approximation binding energies, allow to identify 1825 compounds that are either easily or potentially exfoliable. In particular, the subset of 1036 easily exfoliable cases provides novel structural prototypes and simple ternary compounds as well as a large portfolio of materials to search from for optimal properties. For a subset of 258 compounds we explore vibrational, electronic, magnetic, and topological properties, identifying 56 ferromagnetic and antiferromagnetic systems, including half-metals and half-semiconductors. This archive entry contains the database of 2D materials (structural parameters, band structures, binding energies, phonons for the subset of the 258 easily exfoliable materials with less than 6 atoms, structures and binding energies for the remaining 1567 materials) together with the provenance of all data and calculations as stored by AiiDA."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2017.0008/v3"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "two-dimensional"
-        },
-        {
-            "name": "monolayer"
-        },
-        {
-            "name": "database"
-        },
-        {
-            "name": "high-throughput"
-        },
-        {
-            "name": "DFT"
-        },
-        {
-            "name": "vibrational properties"
-        },
-        {
-            "name": "phonons"
-        },
-        {
-            "name": "electronic properties"
-        },
-        {
-            "name": "electronic bands"
-        },
-        {
-            "name": "magnetic properties"
-        },
-        {
-            "name": "MARVEL"
-        }
-    ],
-    "title": [
-        "Two-dimensional materials from high-throughput computational exfoliation of  experimentally known compounds"
-    ],
-    "url": "https://archive.materialscloud.org/2017.0008/v3"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/c8e3acf8-85be-591b-a8d7-d77598684367.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/c8e3acf8-85be-591b-a8d7-d77598684367.json
deleted file mode 100644
index 39e8af5c..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/c8e3acf8-85be-591b-a8d7-d77598684367.json
+++ /dev/null
@@ -1,102 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0003/v2",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0003/v2",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0003/v2"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-05-23T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Talirz, Leopold",
-        "Smit, Berend",
-        "Fu, Rueih-Sheng",
-        "Mercado, Rocio",
-        "Haranczyk, Maciej",
-        "Yakutovich, Aliaksandr V."
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0003/v2;2019-06-12Z;DOI;Dataset;Mercado, Rocio;Fu, Rueih-Sheng;Yakutovich, Aliaksandr V.;Talirz, Leopold;Haranczyk, Maciej;Smit, Berend;In Silico Design of 2D and 3D Covalent Organic Frameworks for Methane Storage Applications;Materials Cloud;2018-05-23;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;2D;two-dimensional;layered;3D;three-dimensional;database;high-throughput;covalent organic frameworks;COF;nanoporous;methane storage;deliverable capacities;DC;grand canonical Monte Carlo;GCMC;MARVEL;doi:10.24435/materialscloud:2018.0003/v2;https://archive.materialscloud.org/2018.0003/v2;en;Here we present 69,840 covalent organic frameworks (COFs) assembled in silico from a set of 666 distinct organic linkers into 2D-layered and 3D configurations. We investigate the feasibility of using these frameworks for methane storage by using grand-canonical Monte Carlo (GCMC) simulations to calculate their deliverable capacities (DCs). From these calculations, we predict that the best structure in the database is linker91_C_linker91_C_tbd, a structure composed of carbon-carbon bonded triazine linkers in the tbd topology. This structure has a predicted 65-bar DC of 216 v STP/v, greater than that of the best current methane storage material. We also predict other top performing materials, with 305 structures having DCs of over 190 v STP/v, and 34 of these having DCs of over 200 v STP/v. This archive entry contains the database of assembled COF structures (in CIF file format) together with all of their properties. Among the calculated properties for each structure are the framework density, the methane heats of desorption at the storage and depletion pressures, the methane uptakes at the storage and deplation pressures, the supercell volume, and the geometric surface area. Structures are also labeled according to their bond types (amide, amine, imine, carbon-carbon, or mixed) and their dimensionalities (2D or 3D).",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "c8e3acf8-85be-591b-a8d7-d77598684367",
-    "notes": [
-        "Here we present 69,840 covalent organic frameworks (COFs) assembled in silico from a set of 666 distinct organic linkers into 2D-layered and 3D configurations. We investigate the feasibility of using these frameworks for methane storage by using grand-canonical Monte Carlo (GCMC) simulations to calculate their deliverable capacities (DCs). From these calculations, we predict that the best structure in the database is linker91_C_linker91_C_tbd, a structure composed of carbon-carbon bonded triazine linkers in the tbd topology. This structure has a predicted 65-bar DC of 216 v STP/v, greater than that of the best current methane storage material. We also predict other top performing materials, with 305 structures having DCs of over 190 v STP/v, and 34 of these having DCs of over 200 v STP/v. This archive entry contains the database of assembled COF structures (in CIF file format) together with all of their properties. Among the calculated properties for each structure are the framework density, the methane heats of desorption at the storage and depletion pressures, the methane uptakes at the storage and deplation pressures, the supercell volume, and the geometric surface area. Structures are also labeled according to their bond types (amide, amine, imine, carbon-carbon, or mixed) and their dimensionalities (2D or 3D)."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0003/v2"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "two-dimensional"
-        },
-        {
-            "name": "layered"
-        },
-        {
-            "name": "three-dimensional"
-        },
-        {
-            "name": "database"
-        },
-        {
-            "name": "high-throughput"
-        },
-        {
-            "name": "covalent organic frameworks"
-        },
-        {
-            "name": "COF"
-        },
-        {
-            "name": "nanoporous"
-        },
-        {
-            "name": "methane storage"
-        },
-        {
-            "name": "deliverable capacities"
-        },
-        {
-            "name": "DC"
-        },
-        {
-            "name": "grand canonical Monte Carlo"
-        }
-    ],
-    "title": [
-        "In Silico Design of 2D and 3D Covalent Organic Frameworks for Methane Storage Applications"
-    ],
-    "url": "https://archive.materialscloud.org/2018.0003/v2"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/cb4dcfd8-c687-5b96-8742-f6bdf6c32c53.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/cb4dcfd8-c687-5b96-8742-f6bdf6c32c53.json
deleted file mode 100644
index 62cce584..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/cb4dcfd8-c687-5b96-8742-f6bdf6c32c53.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0020/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0020/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0020/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-12-04T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Cheng, Bingqing",
-        "Engel, Edgar",
-        "Behler, J\u00f6rg",
-        "Dellago, Christoph",
-        "Ceriotti, Michele"
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0020/v1;2019-06-12Z;DOI;Dataset;Cheng, Bingqing;Engel, Edgar;Behler, J\u00f6rg;Dellago, Christoph;Ceriotti, Michele;Ab initio thermodynamics of liquid and solid water: supplemental materials;Materials Cloud;2018-12-04;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;Machine learning potential;Machine learning potential training set;Free energy calculation input files;doi:10.24435/materialscloud:2018.0020/v1;https://archive.materialscloud.org/2018.0020/v1;en;Thermodynamic properties of liquid water as well as hexagonal (Ih) and cubic (Ic) ice are predicted based on density functional theory at the hybrid-functional level, rigorously taking into account quantum nuclear motion, anharmonic fluctuations and proton disorder. This is made possible by combining advanced free energy methods and state-of-the-art machine learning techniques. The ab initio description leads to structural properties in excellent agreement with experiments, and reliable estimates of the melting points of light and heavy water. We observe that nuclear quantum effects contribute a crucial 0.2 meV/H2O to the stability of ice Ih, making it more stable than ice Ic. Our computational approach is general and transferable, providing a comprehensive framework for quantitative predictions of ab initio thermodynamic properties using machine learning potentials as an intermediate step.\n<br/>\n\n<br/>\nIn this set of supplemental materials, we have included the neural network potential for bulk water, including its training set in two different formats. We have also included the input files for running free energy calculations.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "cb4dcfd8-c687-5b96-8742-f6bdf6c32c53",
-    "notes": [
-        "Thermodynamic properties of liquid water as well as hexagonal (Ih) and cubic (Ic) ice are predicted based on density functional theory at the hybrid-functional level, rigorously taking into account quantum nuclear motion, anharmonic fluctuations and proton disorder. This is made possible by combining advanced free energy methods and state-of-the-art machine learning techniques. The ab initio description leads to structural properties in excellent agreement with experiments, and reliable estimates of the melting points of light and heavy water. We observe that nuclear quantum effects contribute a crucial 0.2 meV/H2O to the stability of ice Ih, making it more stable than ice Ic. Our computational approach is general and transferable, providing a comprehensive framework for quantitative predictions of ab initio thermodynamic properties using machine learning potentials as an intermediate step.\n<br/>\n\n<br/>\nIn this set of supplemental materials, we have included the neural network potential for bulk water, including its training set in two different formats. We have also included the input files for running free energy calculations."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0020/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Machine learning potential"
-        },
-        {
-            "name": "Machine learning potential training set"
-        },
-        {
-            "name": "Free energy calculation input files"
-        }
-    ],
-    "title": [
-        "Ab initio thermodynamics of liquid and solid water: supplemental materials"
-    ],
-    "url": "https://archive.materialscloud.org/2018.0020/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/cbfd2df0-36d7-5615-b7c6-32f8c72831a7.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/cbfd2df0-36d7-5615-b7c6-32f8c72831a7.json
deleted file mode 100644
index 5ff1b8eb..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/cbfd2df0-36d7-5615-b7c6-32f8c72831a7.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0014/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0014/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0014/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-04-23T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Unal, Gozde",
-        "Horvacanin,  Izabela",
-        "Ozcelik,  Furkan",
-        "Mareska,  Vaclav",
-        "Spiwok, Vojtech",
-        "Trapl, Dalibor"
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0014/v1;2019-06-12Z;DOI;Dataset;Trapl, Dalibor;Horvacanin,  Izabela;Mareska,  Vaclav;Ozcelik,  Furkan;Unal, Gozde;Spiwok, Vojtech;Approximation of Collective Variables by anncolvar;Materials Cloud;2019-04-23;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;metadynamics;artificial neural networks;collective variable;doi:10.24435/materialscloud:2019.0014/v1;https://archive.materialscloud.org/2019.0014/v1;en;Biomolecular simulations are computationally expensive. This limits their application in drug or protein design and related fields. Several methods have been developed to address this problem. These methods often use an artificial force or potential acting on selected degrees of freedom known as collective variables. This requires explicit calculation of a collective variable (and its derivatives) from molecular structure. For collective variables that cannot be calculated explicitly or such calculations is slow we developed anncolvar package (https://github.com/spiwokv/anncolvar). This package approximates collective variables using artificial neural networks. It was tested on Isomap low dimensional representation of cyclooctane derivative or solvent-accessible surface area of Trp-cage miniprotein.\n<br/>\n",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "cbfd2df0-36d7-5615-b7c6-32f8c72831a7",
-    "notes": [
-        "Biomolecular simulations are computationally expensive. This limits their application in drug or protein design and related fields. Several methods have been developed to address this problem. These methods often use an artificial force or potential acting on selected degrees of freedom known as collective variables. This requires explicit calculation of a collective variable (and its derivatives) from molecular structure. For collective variables that cannot be calculated explicitly or such calculations is slow we developed anncolvar package (https://github.com/spiwokv/anncolvar). This package approximates collective variables using artificial neural networks. It was tested on Isomap low dimensional representation of cyclooctane derivative or solvent-accessible surface area of Trp-cage miniprotein.\n<br/>\n"
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0014/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "metadynamics"
-        },
-        {
-            "name": "artificial neural networks"
-        },
-        {
-            "name": "collective variable"
-        }
-    ],
-    "title": [
-        "Approximation of Collective Variables by anncolvar"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0014/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/ce33cf79-ff88-5994-95ce-e32c723daa67.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/ce33cf79-ff88-5994-95ce-e32c723daa67.json
deleted file mode 100644
index dc1d529f..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/ce33cf79-ff88-5994-95ce-e32c723daa67.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0016/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0016/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0016/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-05-03T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Piaggi, Pablo M.",
-        "Parrinello, Michele"
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0016/v1;2019-06-12Z;DOI;Dataset;Piaggi, Pablo M.;Parrinello, Michele;Multithermal-multibaric molecular simulations from a variational principle;Materials Cloud;2019-05-03;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;enhanced sampling;multithermal-multibaric; water;density anomaly;Wang Landau;multicanonical;doi:10.24435/materialscloud:2019.0016/v1;https://archive.materialscloud.org/2019.0016/v1;en;We present a method for performing multithermal-multibaric molecular dynamics simulations that sample entire regions of the temperature-pressure (TP) phase diagram. The method uses a variational principle [Valsson and Parrinello, Phys. Rev. Lett. 113, 090601 (2014)] in order to construct a bias that leads to a uniform sampling in energy and volume. The intervals of temperature and pressure are taken as inputs and the relevant energy and volume regions are determined on the fly. In this way the method guarantees adequate statistics for the chosen TP region. We show that our multithermal-multibaric simulations can be used to calculate all static physical quantities for all temperatures and pressures in the targeted region of the TP plane. We illustrate our approach by studying the density anomaly of TIP4P/Ice water.\n<br/>\n\n<br/>\nThis record includes input and output files, and Jupyter Notebooks describing the analysis of the simulations and the creation of the figures for the paper.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "ce33cf79-ff88-5994-95ce-e32c723daa67",
-    "notes": [
-        "We present a method for performing multithermal-multibaric molecular dynamics simulations that sample entire regions of the temperature-pressure (TP) phase diagram. The method uses a variational principle [Valsson and Parrinello, Phys. Rev. Lett. 113, 090601 (2014)] in order to construct a bias that leads to a uniform sampling in energy and volume. The intervals of temperature and pressure are taken as inputs and the relevant energy and volume regions are determined on the fly. In this way the method guarantees adequate statistics for the chosen TP region. We show that our multithermal-multibaric simulations can be used to calculate all static physical quantities for all temperatures and pressures in the targeted region of the TP plane. We illustrate our approach by studying the density anomaly of TIP4P/Ice water.\n<br/>\n\n<br/>\nThis record includes input and output files, and Jupyter Notebooks describing the analysis of the simulations and the creation of the figures for the paper."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0016/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "enhanced sampling"
-        },
-        {
-            "name": "multithermal-multibaric"
-        },
-        {
-            "name": "water"
-        },
-        {
-            "name": "density anomaly"
-        },
-        {
-            "name": "Wang Landau"
-        },
-        {
-            "name": "multicanonical"
-        }
-    ],
-    "title": [
-        "Multithermal-multibaric molecular simulations from a variational principle"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0016/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/d298732a-71fe-575c-bf8d-783f75a12b89.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/d298732a-71fe-575c-bf8d-783f75a12b89.json
deleted file mode 100644
index 47c7855a..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/d298732a-71fe-575c-bf8d-783f75a12b89.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0025/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0025/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0025/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-05-31T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "MacManus-Driscoll, Judith L.",
-        "Lu, Ping",
-        "Zhu, Bonan",
-        "Schusteritsch, Georg",
-        "Pickard, Chris J."
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0025/v1;2019-06-12Z;DOI;Dataset;Zhu, Bonan;Schusteritsch, Georg;Lu, Ping;MacManus-Driscoll, Judith L.;Pickard, Chris J.;Determining interface structures in vertically aligned nanocomposite films;Materials Cloud;2019-05-31;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;density functional theory;structure prediction;solid-solid interface;doi:10.24435/materialscloud:2019.0025/v1;https://archive.materialscloud.org/2019.0025/v1;en;Vertically aligned nanocomposites (VANs) films have self-assembled pillar-matrix nanostructures. Owing to their large area-to-volume ratios,  interfaces in VAN films are expected to play key roles in inducing functional properties, but our understanding is hindered by limited knowledge about their structures. Motivated by the lack of definitive explanation for the experimentally-found enhanced ionic conductivity in Sm-doped-CeO2/SrTiO3 VAN films, we determine the structure at vertical interfaces using random structure searching and explore how it can affect ionic conduction. This record contains the candidate structures and provenance of the DFT validation calculations. Previously unknown interface structures are found, with lower energy than that of an optimized hand-built model. We find a strongly distorted oxygen sub-lattice which gives a complex landscape of vacancy energies. The cation lattice remains similar to the bulk phase but has a localized strain field. The excess energy of the interface is similar to that of high angle grain boundaries in SrTiO3.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "d298732a-71fe-575c-bf8d-783f75a12b89",
-    "notes": [
-        "Vertically aligned nanocomposites (VANs) films have self-assembled pillar-matrix nanostructures. Owing to their large area-to-volume ratios,  interfaces in VAN films are expected to play key roles in inducing functional properties, but our understanding is hindered by limited knowledge about their structures. Motivated by the lack of definitive explanation for the experimentally-found enhanced ionic conductivity in Sm-doped-CeO2/SrTiO3 VAN films, we determine the structure at vertical interfaces using random structure searching and explore how it can affect ionic conduction. This record contains the candidate structures and provenance of the DFT validation calculations. Previously unknown interface structures are found, with lower energy than that of an optimized hand-built model. We find a strongly distorted oxygen sub-lattice which gives a complex landscape of vacancy energies. The cation lattice remains similar to the bulk phase but has a localized strain field. The excess energy of the interface is similar to that of high angle grain boundaries in SrTiO3."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0025/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "density functional theory"
-        },
-        {
-            "name": "structure prediction"
-        },
-        {
-            "name": "solid-solid interface"
-        }
-    ],
-    "title": [
-        "Determining interface structures in vertically aligned nanocomposite films"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0025/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/e073b9a8-6d35-5a93-897d-ca7327bfb51d.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/e073b9a8-6d35-5a93-897d-ca7327bfb51d.json
deleted file mode 100644
index 35804fbe..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/e073b9a8-6d35-5a93-897d-ca7327bfb51d.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2017.0006/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2017.0006/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2017.0006/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2017-06-21T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Dragoni, Daniele",
-        "Daff, Tom",
-        "Csanyi, Gabor",
-        "Marzari, Nicola"
-    ],
-    "fulltext": "oai:materialscloud.org:2017.0006/v1;2019-06-12Z;DOI;Dataset;Dragoni, Daniele;Daff, Tom;Csanyi, Gabor;Marzari, Nicola;Gaussian Approximation Potentials for iron from extended first-principles database (Data Download);Materials Cloud;2017-06-21;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;Machine-learning;\u03b1-iron;Gaussian approximation potentials;artificial neural networks;interatomic potentials;MARVEL;doi:10.24435/materialscloud:2017.0006/v1;https://archive.materialscloud.org/2017.0006/v1;en;Interatomic potentials are often necessary to describe complex realistic systems that would be too costly to study from first-principles. Commonly, interatomic potentials are designed using functional forms driven by physical intuition and fitted to experimental or computational data. The moderate flexibility of these functional forms limits their ability to be systematically improved by increasing the fitting datasets; on the other hand, their qualitative description of the essential physical interactions ensures a modicum degree of transferability. Recently, a novel trend has emerged where potential-energy surfaces are represented by neural networks fitted on large numbers of first-principles calculations, thus maximizing flexibility but requiring extensive datasets to ensure transferability. Gaussian Approximation Potentials in particular are a novel class of potentials based on non-linear, non-parametric Gaussian-process regression. Here we generate a Gaussian Approximation model for the \u03b1-phase of iron training on energies, stresses and forces taken from first-principles molecular dynamics simulations of pristine and defected bulk systems, of surfaces and \u03b3-surfaces with different crystallographic orientations.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "e073b9a8-6d35-5a93-897d-ca7327bfb51d",
-    "notes": [
-        "Interatomic potentials are often necessary to describe complex realistic systems that would be too costly to study from first-principles. Commonly, interatomic potentials are designed using functional forms driven by physical intuition and fitted to experimental or computational data. The moderate flexibility of these functional forms limits their ability to be systematically improved by increasing the fitting datasets; on the other hand, their qualitative description of the essential physical interactions ensures a modicum degree of transferability. Recently, a novel trend has emerged where potential-energy surfaces are represented by neural networks fitted on large numbers of first-principles calculations, thus maximizing flexibility but requiring extensive datasets to ensure transferability. Gaussian Approximation Potentials in particular are a novel class of potentials based on non-linear, non-parametric Gaussian-process regression. Here we generate a Gaussian Approximation model for the \u03b1-phase of iron training on energies, stresses and forces taken from first-principles molecular dynamics simulations of pristine and defected bulk systems, of surfaces and \u03b3-surfaces with different crystallographic orientations."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2017.0006/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Machine-learning"
-        },
-        {
-            "name": "Machine-learning"
-        },
-        {
-            "name": "Gaussian approximation potentials"
-        },
-        {
-            "name": "artificial neural networks"
-        },
-        {
-            "name": "interatomic potentials"
-        },
-        {
-            "name": "MARVEL"
-        }
-    ],
-    "title": [
-        "Gaussian Approximation Potentials for iron from extended first-principles database (Data Download)"
-    ],
-    "url": "https://archive.materialscloud.org/2017.0006/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/e2f5df18-9621-50d7-85f8-01d0ed9a4057.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/e2f5df18-9621-50d7-85f8-01d0ed9a4057.json
deleted file mode 100644
index 7f97f454..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/e2f5df18-9621-50d7-85f8-01d0ed9a4057.json
+++ /dev/null
@@ -1,100 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0019/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0019/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0019/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-05-15T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "RelatedIdentifier": [
-        "https://www.materialscloud.org/discover/topomat"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution Non Commercial 4.0 International https://creativecommons.org/licenses/by-nc/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Mounet, Nicolas",
-        "Wu, QuanSheng",
-        "Yazyev, Oleg V.",
-        "Aut\u00e8s, Gabriel"
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0019/v1;2019-06-12Z;DOI;Dataset;Wu, QuanSheng;Aut\u00e8s, Gabriel;Mounet, Nicolas;Yazyev, Oleg V.;TopoMat: a database of high-throughput first-principles calculations of topological materials;Materials Cloud;2019-05-15;Creative Commons Attribution Non Commercial 4.0 International https://creativecommons.org/licenses/by-nc/4.0/legalcode;info:eu-repo/semantics/openAccess;MARVEL;MARVEL/DD6;Topological materials;Database;TopoMat;QUANTUM ESPRESSO;Z2 topological number;spin-orbit coupling;topological insulators;topological semimetals;high-throughput screening;doi:10.24435/materialscloud:2019.0019/v1;https://archive.materialscloud.org/2019.0019/v1;en;https://www.materialscloud.org/discover/topomat;We present a database of topological materials predicted from high-throughput first-principles calculations. The database contains electronic band structures and topological indices of 13628 materials calculated on experimental crystal structures taken from the Inorganic Crystal Structure Database (ICSD) and the Crystallography Open Database (COD). The calculations have been performed on non-magnetic phases taking into account the spin-orbit interactions using the Quantum ESPRESSO package. The Fu-Kane method and the Wannier charge center method implemented in the Z2pack code have been utilized to calculate the Z2 topological numbers of centrosymmetric and non-centrosymmetric materials, respectively. Over 4000 topologically non-trivial materials have been identified.\n<br/>\n",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "e2f5df18-9621-50d7-85f8-01d0ed9a4057",
-    "notes": [
-        "We present a database of topological materials predicted from high-throughput first-principles calculations. The database contains electronic band structures and topological indices of 13628 materials calculated on experimental crystal structures taken from the Inorganic Crystal Structure Database (ICSD) and the Crystallography Open Database (COD). The calculations have been performed on non-magnetic phases taking into account the spin-orbit interactions using the Quantum ESPRESSO package. The Fu-Kane method and the Wannier charge center method implemented in the Z2pack code have been utilized to calculate the Z2 topological numbers of centrosymmetric and non-centrosymmetric materials, respectively. Over 4000 topologically non-trivial materials have been identified.\n<br/>\n"
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0019/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "MARVEL"
-        },
-        {
-            "name": "MARVEL DD"
-        },
-        {
-            "name": "Topological materials"
-        },
-        {
-            "name": "Database"
-        },
-        {
-            "name": "TopoMat"
-        },
-        {
-            "name": "QUANTUM ESPRESSO"
-        },
-        {
-            "name": "Z topological number"
-        },
-        {
-            "name": "spin-orbit coupling"
-        },
-        {
-            "name": "topological insulators"
-        },
-        {
-            "name": "topological semimetals"
-        },
-        {
-            "name": "high-throughput screening"
-        }
-    ],
-    "title": [
-        "TopoMat: a database of high-throughput first-principles calculations of topological materials"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0019/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/e52252a1-3d2d-5af3-8b10-f27ad4871b48.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/e52252a1-3d2d-5af3-8b10-f27ad4871b48.json
deleted file mode 100644
index 49cdeabe..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/e52252a1-3d2d-5af3-8b10-f27ad4871b48.json
+++ /dev/null
@@ -1,105 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0001/v2",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0001/v2",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0001/v2"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-07-23T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "RelatedIdentifier": [
-        "https://www.materialscloud.org/discover/sssp",
-        "https://www.materialscloud.org/explore/sssp"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Castelli, Ivano E.",
-        "Mounet, Nicolas",
-        "Marzari, Nicola",
-        "Marrazzo, Antimo",
-        "Prandini, Gianluca"
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0001/v2;2019-06-12Z;DOI;Dataset;Prandini, Gianluca;Marrazzo, Antimo;Castelli, Ivano E.;Mounet, Nicolas;Marzari, Nicola;A Standard Solid State Pseudopotentials (SSSP) library optimized for precision and efficiency (Version 1.0, data download);Materials Cloud;2018-07-23;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;SSSP;pseudopotentials;database;high-throughput;library;standard;DFT;calculations;vibrational properties;phonons;electronic properties;electronic bands;cohesive energy;chessboards;elemental solids;verification;precision;efficiency;MARVEL;doi:10.24435/materialscloud:2018.0001/v2;https://archive.materialscloud.org/2018.0001/v2;en;https://www.materialscloud.org/discover/sssp;https://www.materialscloud.org/explore/sssp;Despite the enormous success and popularity of density functional theory, systematic verification and validation studies are still very limited both in number and scope. Here, we propose a universal standard protocol to verify publicly available pseudopotential libraries, based on several independent criteria including verification against all-electron equations of state and plane-wave convergence tests for phonon frequencies, band structure, cohesive energy and pressure. Adopting these criteria we obtain two optimal pseudopotential sets, namely the Standard Solid State Pseudopotential (SSSP) efficiency and precision libraries, tailored for high-throughput materials screening and high-precision materials modelling. As of today, the SSSP precision library is the most accurate open-source pseudopotential library available. This archive entry contains the database of calculations (phonons, cohesive energy, equation of state, band structure, pressure, etc.) together with the provenance of all data and calculations as stored by AiiDA.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "e52252a1-3d2d-5af3-8b10-f27ad4871b48",
-    "notes": [
-        "Despite the enormous success and popularity of density functional theory, systematic verification and validation studies are still very limited both in number and scope. Here, we propose a universal standard protocol to verify publicly available pseudopotential libraries, based on several independent criteria including verification against all-electron equations of state and plane-wave convergence tests for phonon frequencies, band structure, cohesive energy and pressure. Adopting these criteria we obtain two optimal pseudopotential sets, namely the Standard Solid State Pseudopotential (SSSP) efficiency and precision libraries, tailored for high-throughput materials screening and high-precision materials modelling. As of today, the SSSP precision library is the most accurate open-source pseudopotential library available. This archive entry contains the database of calculations (phonons, cohesive energy, equation of state, band structure, pressure, etc.) together with the provenance of all data and calculations as stored by AiiDA."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0001/v2"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "SSSP"
-        },
-        {
-            "name": "pseudopotentials"
-        },
-        {
-            "name": "database"
-        },
-        {
-            "name": "high-throughput"
-        },
-        {
-            "name": "library"
-        },
-        {
-            "name": "standard"
-        },
-        {
-            "name": "DFT"
-        },
-        {
-            "name": "calculations"
-        },
-        {
-            "name": "vibrational properties"
-        },
-        {
-            "name": "phonons"
-        },
-        {
-            "name": "electronic properties"
-        },
-        {
-            "name": "electronic bands"
-        }
-    ],
-    "title": [
-        "A Standard Solid State Pseudopotentials (SSSP) library optimized for precision and efficiency (Version 1.0, data download)"
-    ],
-    "url": "https://archive.materialscloud.org/2018.0001/v2"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/e5e51d77-b5b5-570a-b32c-7b048612251b.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/e5e51d77-b5b5-570a-b32c-7b048612251b.json
deleted file mode 100644
index dc502636..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/e5e51d77-b5b5-570a-b32c-7b048612251b.json
+++ /dev/null
@@ -1,76 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0004/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0004/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0004/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-04-17T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Boyd, Peter G.",
-        "Moosavi, Seyed Mohamad",
-        "Sarkisov, Lev",
-        "Smit, Berend"
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0004/v1;2019-06-12Z;DOI;Dataset;Moosavi, Seyed Mohamad;Boyd, Peter G.;Sarkisov, Lev;Smit, Berend;Improving the Mechanical Stability of Metal-Organic Frameworks Using Chemical Caryatids;Materials Cloud;2018-04-17;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;Nanoporous materials;Mechanical properties;Stability;MARVEL;doi:10.24435/materialscloud:2018.0004/v1;https://archive.materialscloud.org/2018.0004/v1;en;Metal-organic frameworks (MOFs) have emerged as versatile materials for applications ranging from gas separation and storage, catalysis, and sensing. The attractive feature of MOFs is that by changing the ligand and/or metal, they can be chemically tuned to perform optimally for a given application. In most, if not all, of these applications one also needs a material that has a sufficient mechanical stability, but our understanding of how changes in the chemical structure influence mechanical stability is limited. In this work, we rationalize how the mechanical properties of MOFs are related to framework bonding topology and ligand structure. We illustrate that the functional groups on the organic ligands can either enhance the mechanical stability through formation of a secondary network of non-bonded interactions, or soften the material by destabilizing the bonded network of a MOF. In addition, we show that synergistic effect of the bonding network of the material and the secondary network is required to achieve optimal mechanical stability of a MOF. The developed molecular insights in this work can be used for systematic improvement of the mechanical stability of the materials by careful selection of the functional groups.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "e5e51d77-b5b5-570a-b32c-7b048612251b",
-    "notes": [
-        "Metal-organic frameworks (MOFs) have emerged as versatile materials for applications ranging from gas separation and storage, catalysis, and sensing. The attractive feature of MOFs is that by changing the ligand and/or metal, they can be chemically tuned to perform optimally for a given application. In most, if not all, of these applications one also needs a material that has a sufficient mechanical stability, but our understanding of how changes in the chemical structure influence mechanical stability is limited. In this work, we rationalize how the mechanical properties of MOFs are related to framework bonding topology and ligand structure. We illustrate that the functional groups on the organic ligands can either enhance the mechanical stability through formation of a secondary network of non-bonded interactions, or soften the material by destabilizing the bonded network of a MOF. In addition, we show that synergistic effect of the bonding network of the material and the secondary network is required to achieve optimal mechanical stability of a MOF. The developed molecular insights in this work can be used for systematic improvement of the mechanical stability of the materials by careful selection of the functional groups."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0004/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Nanoporous materials"
-        },
-        {
-            "name": "Mechanical properties"
-        },
-        {
-            "name": "Stability"
-        },
-        {
-            "name": "MARVEL"
-        }
-    ],
-    "title": [
-        "Improving the Mechanical Stability of Metal-Organic Frameworks Using Chemical Caryatids"
-    ],
-    "url": "https://archive.materialscloud.org/2018.0004/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/eb613b6c-8492-5125-b341-bdd201b75f8c.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/eb613b6c-8492-5125-b341-bdd201b75f8c.json
deleted file mode 100644
index 3e14bd4c..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/eb613b6c-8492-5125-b341-bdd201b75f8c.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0007/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0007/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0007/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-02-06T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Heinen, Stefan N.",
-        "Corminboeuf, Cl\u00e9mence",
-        "Wodrich, Matthew D.",
-        "Meyer, Benjamin",
-        "Fabrizio, Alberto",
-        "Sawatlon, Boodsarin",
-        "von Lilienfeld, O. Anatole"
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0007/v1;2019-06-12Z;DOI;Dataset;Sawatlon, Boodsarin;Fabrizio, Alberto;Meyer, Benjamin;Heinen, Stefan N.;Wodrich, Matthew D.;von Lilienfeld, O. Anatole;Corminboeuf, Cl\u00e9mence;Mining the C-C Cross-Coupling Genome using Machine Learning;Materials Cloud;2019-02-06;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;machine learning;homogeneous catalysis;volcano plot;transition metal complexes;sketch-map;doi:10.24435/materialscloud:2019.0007/v1;https://archive.materialscloud.org/2019.0007/v1;en;Applications of machine-learning (ML) techniques to the study of catalytic processes have begun to appear in the literature with increasing frequency. The computational speed up provided by ML allows the properties and energetics of thousands of prospective catalysts to be rapidly assessed. These results, once compiled into a database containing different properties, can be mined with the goal of establishing relationships between the intrinsic chemical properties of different catalysts and their overall catalytic performance. Previously, we applied ML models to predict the performance of 18,000 prospective catalysts for a Suzuki coupling reaction using molecular volcano plots. Here, we expand on our earlier work by examining a larger section of the C-C cross-coupling genome by using a dimensionality-reducing data-clustering algorithms (i.e., sketch-map) to, first, identify the compatibility of each catalyst with different C-C cross-coupling variants (e.g., Suzuki, Kumada, Negishi, Stille, and/or Hiyama) and, second, to uncover links between the chemical property of a catalyst and its catalytic activity. Our findings, based on the analysis of 18,000 catalysts, reveal strong correlations between a catalyst\u2019s HOMO energy and the suitability of its thermodynamic profile. These values can, subsequently, be tuned in order to maximize the thermodynamics of the catalytic cycle through the judicious choice of metal centers and the \u03c0-accepting/\u03c3-donating nature of the flanking ligands. Overall, group 10 metals (Ni, Pd, Pt) are best coupled with the strong \u03c0-acceptor ligands and group 11 metals (Cu, Ag, Au) with weak \u03c0-acceptors, which maximize the thermodynamic drive of the catalytic cycle.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "eb613b6c-8492-5125-b341-bdd201b75f8c",
-    "notes": [
-        "Applications of machine-learning (ML) techniques to the study of catalytic processes have begun to appear in the literature with increasing frequency. The computational speed up provided by ML allows the properties and energetics of thousands of prospective catalysts to be rapidly assessed. These results, once compiled into a database containing different properties, can be mined with the goal of establishing relationships between the intrinsic chemical properties of different catalysts and their overall catalytic performance. Previously, we applied ML models to predict the performance of 18,000 prospective catalysts for a Suzuki coupling reaction using molecular volcano plots. Here, we expand on our earlier work by examining a larger section of the C-C cross-coupling genome by using a dimensionality-reducing data-clustering algorithms (i.e., sketch-map) to, first, identify the compatibility of each catalyst with different C-C cross-coupling variants (e.g., Suzuki, Kumada, Negishi, Stille, and/or Hiyama) and, second, to uncover links between the chemical property of a catalyst and its catalytic activity. Our findings, based on the analysis of 18,000 catalysts, reveal strong correlations between a catalyst\u2019s HOMO energy and the suitability of its thermodynamic profile. These values can, subsequently, be tuned in order to maximize the thermodynamics of the catalytic cycle through the judicious choice of metal centers and the \u03c0-accepting/\u03c3-donating nature of the flanking ligands. Overall, group 10 metals (Ni, Pd, Pt) are best coupled with the strong \u03c0-acceptor ligands and group 11 metals (Cu, Ag, Au) with weak \u03c0-acceptors, which maximize the thermodynamic drive of the catalytic cycle."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0007/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine learning"
-        },
-        {
-            "name": "homogeneous catalysis"
-        },
-        {
-            "name": "volcano plot"
-        },
-        {
-            "name": "transition metal complexes"
-        },
-        {
-            "name": "sketch-map"
-        }
-    ],
-    "title": [
-        "Mining the C-C Cross-Coupling Genome using Machine Learning"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0007/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/ed7ee35c-7c00-5cfd-894e-b229e6442ac9.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/ed7ee35c-7c00-5cfd-894e-b229e6442ac9.json
deleted file mode 100644
index a6cb50c1..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/ed7ee35c-7c00-5cfd-894e-b229e6442ac9.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0014/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0014/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0014/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-08-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Corminboeuf, Cl\u00e9mence",
-        "Meyer, Benjamin",
-        "von Lilienfeld, O. Anatole",
-        "Heinen, Stefan Niklaus",
-        "Sawatlon, Boodsarin"
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0014/v1;2019-06-12Z;DOI;Dataset;Meyer, Benjamin;Sawatlon, Boodsarin;Heinen, Stefan Niklaus;von Lilienfeld, O. Anatole;Corminboeuf, Cl\u00e9mence;Machine learning meets volcano plots: Computational discovery of cross-coupling catalysts;Materials Cloud;2018-08-01;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;machine learning;homogeneous catalysis;volcano plot;transition metal complexes;doi:10.24435/materialscloud:2018.0014/v1;https://archive.materialscloud.org/2018.0014/v1;en;The application of modern machine learning to challenges in atomistic simulation is gaining attraction. We present new machine learning models that can predict the energy of the oxidative addition process between a transition metal complex and a substrate for C-C cross-coupling reaction. In turn, this quantity can be used as a descriptor to estimate the activity of homogeneous catalysts using molecular volcano plots. The versatility of this approach is illustrated for vast libraries of organometallic catalysts based on Pt, Pd, Ni, Cu, Ag, and Au combined with 91 ligands. Out-of-sample machine learning predictions were made on a total of 18,062 compounds leading to 557 catalyst candidates falling into the ideal thermodynamic window. This number was further refined by searching for candidates with an estimated price lower than 10 US$/mmol. The 37 catalyst finalists are dominated by palladium phosphine ligand combinations but also include earth abundant (Cu) transition metal with less common ligands. Our results indicate that modern statistical learning techniques can be applied to the computational discovery of readily available and promising catalyst candidates.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "ed7ee35c-7c00-5cfd-894e-b229e6442ac9",
-    "notes": [
-        "The application of modern machine learning to challenges in atomistic simulation is gaining attraction. We present new machine learning models that can predict the energy of the oxidative addition process between a transition metal complex and a substrate for C-C cross-coupling reaction. In turn, this quantity can be used as a descriptor to estimate the activity of homogeneous catalysts using molecular volcano plots. The versatility of this approach is illustrated for vast libraries of organometallic catalysts based on Pt, Pd, Ni, Cu, Ag, and Au combined with 91 ligands. Out-of-sample machine learning predictions were made on a total of 18,062 compounds leading to 557 catalyst candidates falling into the ideal thermodynamic window. This number was further refined by searching for candidates with an estimated price lower than 10 US$/mmol. The 37 catalyst finalists are dominated by palladium phosphine ligand combinations but also include earth abundant (Cu) transition metal with less common ligands. Our results indicate that modern statistical learning techniques can be applied to the computational discovery of readily available and promising catalyst candidates."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0014/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "machine learning"
-        },
-        {
-            "name": "homogeneous catalysis"
-        },
-        {
-            "name": "volcano plot"
-        },
-        {
-            "name": "transition metal complexes"
-        }
-    ],
-    "title": [
-        "Machine learning meets volcano plots: Computational discovery of cross-coupling catalysts"
-    ],
-    "url": "https://archive.materialscloud.org/2018.0014/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/f482a7fe-d3bf-5201-b7bf-53f618f8bd8d.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/f482a7fe-d3bf-5201-b7bf-53f618f8bd8d.json
deleted file mode 100644
index fe6f1ce9..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/f482a7fe-d3bf-5201-b7bf-53f618f8bd8d.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0006/v1",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0006/v1",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0006/v1"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-02-06T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Mace, Amber",
-        "Barthel, Senja",
-        "Corminboeuf, Cl\u00e9mence",
-        "Smit, Berend",
-        "Meyer, Benjamin",
-        "Guillot, Benoit ",
-        "Vannay, Laurent"
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0006/v1;2019-06-12Z;DOI;Dataset;Meyer, Benjamin;Barthel, Senja;Mace, Amber;Vannay, Laurent;Guillot, Benoit ;Smit, Berend;Corminboeuf, Cl\u00e9mence;DORI reveals the influence of non-covalent interactions on covalent bonding patterns in molecular crystals under pressure;Materials Cloud;2019-02-06;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;Molecular scalar fields;Organic crystals;Topology;High pressure;doi:10.24435/materialscloud:2019.0006/v1;https://archive.materialscloud.org/2019.0006/v1;en;The study of organic molecular crystals under high pressure provides fundamental insight into crystal packing distortions and reveals mechanisms of phase transitions and the crystallization of polymorphs. These solid state transformations can be monitored directly by analyzing electron charge densities that are experimentally obtained at high pressure. However, restricting the analysis to the featureless electron density does not reveal the chemical bonding nature and the existence of intermolecular interactions. This shortcoming can be resolved by the use of the DORI (Density Overlap Region Indicator) descriptor, which is capable of detecting simultaneously both covalent patterns and non-covalent interactions from electron density and its derivatives. Using the biscarbonyl[14]annulene crystal under pressure as an example, we demonstrate how DORI can be exploited on experimental electron densities to reveal and monitor changes in electronic structure patterns resulting from molecular compression. A novel approach based on a flood fill type algorithm is proposed for analyzing the topology of the DORI isosurface. This approach avoids the arbitrarily selection of DORI isovalues and provides an intuitive way to assess how compression packing affects covalent bonding in organic solids.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "f482a7fe-d3bf-5201-b7bf-53f618f8bd8d",
-    "notes": [
-        "The study of organic molecular crystals under high pressure provides fundamental insight into crystal packing distortions and reveals mechanisms of phase transitions and the crystallization of polymorphs. These solid state transformations can be monitored directly by analyzing electron charge densities that are experimentally obtained at high pressure. However, restricting the analysis to the featureless electron density does not reveal the chemical bonding nature and the existence of intermolecular interactions. This shortcoming can be resolved by the use of the DORI (Density Overlap Region Indicator) descriptor, which is capable of detecting simultaneously both covalent patterns and non-covalent interactions from electron density and its derivatives. Using the biscarbonyl[14]annulene crystal under pressure as an example, we demonstrate how DORI can be exploited on experimental electron densities to reveal and monitor changes in electronic structure patterns resulting from molecular compression. A novel approach based on a flood fill type algorithm is proposed for analyzing the topology of the DORI isosurface. This approach avoids the arbitrarily selection of DORI isovalues and provides an intuitive way to assess how compression packing affects covalent bonding in organic solids."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0006/v1"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Molecular scalar fields"
-        },
-        {
-            "name": "Organic crystals"
-        },
-        {
-            "name": "Topology"
-        },
-        {
-            "name": "High pressure"
-        }
-    ],
-    "title": [
-        "DORI reveals the influence of non-covalent interactions on covalent bonding patterns in molecular crystals under pressure"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0006/v1"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/f533c56a-914d-5462-bf98-18235c7ba97d.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/f533c56a-914d-5462-bf98-18235c7ba97d.json
deleted file mode 100644
index 2187e2e1..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/f533c56a-914d-5462-bf98-18235c7ba97d.json
+++ /dev/null
@@ -1,89 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0021/v2",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0021/v2",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0021/v2"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-01-14T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Steinr\u00fcck, Hans-Peter ",
-        "Hirsch, Andreas ",
-        "Wild, Stefan ",
-        "Vidal\u2013Moya, Jos\u00e9 Alejandro ",
-        "Hauke, Frank ",
-        " Maier, Florian",
-        "Dom\u00e9nech\u2013Carb\u00f3, Antonio ",
-        "Abell\u00e1n, Gonzalo ",
-        "Shin, Sunghwan ",
-        "Leyva\u2013P\u00e9rez, Antonio ",
-        "Varela, Maria ",
-        "J. Heller, Bettina S.",
-        "Lloret, Vicent ",
-        "Rivero\u2013Crespo, Miguel \u00c1ngel "
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0021/v2;2019-06-12Z;DOI;Dataset;Lloret, Vicent ;Rivero\u2013Crespo, Miguel \u00c1ngel ;Vidal\u2013Moya, Jos\u00e9 Alejandro ;Wild, Stefan ;Dom\u00e9nech\u2013Carb\u00f3, Antonio ;J. Heller, Bettina S.;Shin, Sunghwan ;Steinr\u00fcck, Hans-Peter ; Maier, Florian;Hauke, Frank ;Varela, Maria ;Hirsch, Andreas ;Leyva\u2013P\u00e9rez, Antonio ;Abell\u00e1n, Gonzalo ;Few layer 2D pnictogens catalyze the alkylation of soft nucleophiles with esters.   ;Materials Cloud;2019-01-14;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;antimonene;Black phosphorous;alkylation;esters;ionic liquids;doi:10.24435/materialscloud:2018.0021/v2;https://archive.materialscloud.org/2018.0021/v2;en;Group 15 elements in zero oxidation state (P, As, Sb and Bi), also called pnictogens, are rarely used in catalysis due to the difficulties associated in preparing well\u2013structured and stable materials. Here, we report on the synthesis of highly exfoliated, few layer 2D phosphorene and antimonene in zero oxidation state, suspended in an ionic liquid, with the native atoms ready to interact with external reagents while avoiding aerobic or aqueous decomposition pathways, and on their use as efficient catalysts for the alkylation of nucleophiles with esters. The few layer pnictogen material circumvents the extremely harsh reaction conditions associated to previous superacid\u2013catalyzed alkylations, by enabling an alternative mechanism on surface, protected from the water and air by the ionic liquid. These 2D catalysts allow the alkylation of a variety of acid\u2013sensitive organic molecules and giving synthetic relevancy to the use of simple esters as alkylating agents. ",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "f533c56a-914d-5462-bf98-18235c7ba97d",
-    "notes": [
-        "Group 15 elements in zero oxidation state (P, As, Sb and Bi), also called pnictogens, are rarely used in catalysis due to the difficulties associated in preparing well\u2013structured and stable materials. Here, we report on the synthesis of highly exfoliated, few layer 2D phosphorene and antimonene in zero oxidation state, suspended in an ionic liquid, with the native atoms ready to interact with external reagents while avoiding aerobic or aqueous decomposition pathways, and on their use as efficient catalysts for the alkylation of nucleophiles with esters. The few layer pnictogen material circumvents the extremely harsh reaction conditions associated to previous superacid\u2013catalyzed alkylations, by enabling an alternative mechanism on surface, protected from the water and air by the ionic liquid. These 2D catalysts allow the alkylation of a variety of acid\u2013sensitive organic molecules and giving synthetic relevancy to the use of simple esters as alkylating agents. "
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0021/v2"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "antimonene"
-        },
-        {
-            "name": "Black phosphorous"
-        },
-        {
-            "name": "alkylation"
-        },
-        {
-            "name": "esters"
-        },
-        {
-            "name": "ionic liquids"
-        }
-    ],
-    "title": [
-        "Few layer 2D pnictogens catalyze the alkylation of soft nucleophiles with esters.   "
-    ],
-    "url": "https://archive.materialscloud.org/2018.0021/v2"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/f5b03381-daf2-5a71-b690-6f0389c1885a.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/f5b03381-daf2-5a71-b690-6f0389c1885a.json
deleted file mode 100644
index 377f826b..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/f5b03381-daf2-5a71-b690-6f0389c1885a.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2018.0011/v2",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2018.0011/v2",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2018.0011/v2"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2018-12-10T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Talirz, Leopold",
-        "Chidambaram, Arunraj",
-        "Smit, Berend",
-        "Haranczyk, Maciej",
-        "Stylianou, Kyriakos C.",
-        "Moosavi, Seyed Mohamad"
-    ],
-    "fulltext": "oai:materialscloud.org:2018.0011/v2;2019-06-12Z;DOI;Dataset;Moosavi, Seyed Mohamad;Chidambaram, Arunraj;Talirz, Leopold;Haranczyk, Maciej;Stylianou, Kyriakos C.;Smit, Berend;Capturing chemical intuition in synthesis of metal-organic frameworks;Materials Cloud;2018-12-10;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;Machine learning;Synthesis;Optimisation;Genetic algorithms;Metal-Organic frameworks;Robotic synthesi;MARVEL;doi:10.24435/materialscloud:2018.0011/v2;https://archive.materialscloud.org/2018.0011/v2;en;We report a methodology using machine learning to capture chemical intuition from a set of (partially) failed attempts to synthesize a metal organic framework. We define chemical intuition as the collection of unwritten guidelines used by synthetic chemists to find the right synthesis conditions. As (partially) failed experiments usually remain unreported, we have reconstructed a typical track of failed experiments in a successful search for finding the optimal synthesis conditions that yields HKUST-1 with the highest surface area reported to date. We illustrate the importance of quantifying this chemical intuition for the synthesis of novel materials.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "f5b03381-daf2-5a71-b690-6f0389c1885a",
-    "notes": [
-        "We report a methodology using machine learning to capture chemical intuition from a set of (partially) failed attempts to synthesize a metal organic framework. We define chemical intuition as the collection of unwritten guidelines used by synthetic chemists to find the right synthesis conditions. As (partially) failed experiments usually remain unreported, we have reconstructed a typical track of failed experiments in a successful search for finding the optimal synthesis conditions that yields HKUST-1 with the highest surface area reported to date. We illustrate the importance of quantifying this chemical intuition for the synthesis of novel materials."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2018.0011/v2"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Machine learning"
-        },
-        {
-            "name": "Synthesis"
-        },
-        {
-            "name": "Optimisation"
-        },
-        {
-            "name": "Genetic algorithms"
-        },
-        {
-            "name": "Metal-Organic frameworks"
-        },
-        {
-            "name": "Robotic synthesi"
-        },
-        {
-            "name": "MARVEL"
-        }
-    ],
-    "title": [
-        "Capturing chemical intuition in synthesis of metal-organic frameworks"
-    ],
-    "url": "https://archive.materialscloud.org/2018.0011/v2"
-}
\ No newline at end of file
diff --git a/oaitestdata/materialscloud-oai_dc/SET_1/json/f8c087a1-96fe-5f16-b390-3ace8d750ee9.json b/oaitestdata/materialscloud-oai_dc/SET_1/json/f8c087a1-96fe-5f16-b390-3ace8d750ee9.json
deleted file mode 100644
index a55c1320..00000000
--- a/oaitestdata/materialscloud-oai_dc/SET_1/json/f8c087a1-96fe-5f16-b390-3ace8d750ee9.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Materials Cloud"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.24435/materialscloud:2019.0002/v2",
-    "DiscHierarchy": [
-        "5.3",
-        "Engineering Sciences",
-        "Materials Science and Engineeringy"
-    ],
-    "Discipline": "Materials Science And Engineering",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:2019.0002/v2",
-    "MetadataAccess": [
-        "oai:materialscloud.org:2019.0002/v2"
-    ],
-    "OpenAccess": "true",
-    "PublicationTimestamp": "2019-05-04T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "Materials Cloud"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode",
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "author": [
-        "Yang, Yang",
-        "Lao, Ka Un",
-        "Grisafi, Andrea",
-        "DiStasio Jr., Robert A.",
-        "Ceriotti, Michele",
-        "Wilkins, David M."
-    ],
-    "fulltext": "oai:materialscloud.org:2019.0002/v2;2019-06-12Z;DOI;Dataset;Yang, Yang;Lao, Ka Un;Wilkins, David M.;Grisafi, Andrea;Ceriotti, Michele;DiStasio Jr., Robert A.;Coupled-Cluster Polarizabilities in the QM7b and a Showcase Database;Materials Cloud;2019-05-04;Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode;info:eu-repo/semantics/openAccess;dipole polarizability;linear response coupled cluster;density functional theory;doi:10.24435/materialscloud:2019.0002/v2;https://archive.materialscloud.org/2019.0002/v2;en;Dipole polarizabilities, computed using linear response coupled cluster theory and density functional theory (using d-aug-cc-pVDZ basis set), for 7211 molecules from the QM7b dataset of small molecules and for 52 molecules from a showcase dataset.",
-    "group": "materialscloud",
-    "groups": [
-        {
-            "name": "materialscloud"
-        }
-    ],
-    "name": "f8c087a1-96fe-5f16-b390-3ace8d750ee9",
-    "notes": [
-        "Dipole polarizabilities, computed using linear response coupled cluster theory and density functional theory (using d-aug-cc-pVDZ basis set), for 7211 molecules from the QM7b dataset of small molecules and for 52 molecules from a showcase dataset."
-    ],
-    "oai_identifier": [
-        "oai:materialscloud.org:2019.0002/v2"
-    ],
-    "oai_set": [
-        "DOI"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "dipole polarizability"
-        },
-        {
-            "name": "linear response coupled cluster"
-        },
-        {
-            "name": "density functional theory"
-        }
-    ],
-    "title": [
-        "Coupled-Cluster Polarizabilities in the QM7b and a Showcase Database"
-    ],
-    "url": "https://archive.materialscloud.org/2019.0002/v2"
-}
\ No newline at end of file
diff --git a/oaitestdata/pandata-oai_dc/SET_1/json/fc178d6f-7b17-5608-8fd9-c7409adc0462.json b/oaitestdata/pandata-oai_dc/SET_1/json/fc178d6f-7b17-5608-8fd9-c7409adc0462.json
deleted file mode 100644
index 4e45fe9c..00000000
--- a/oaitestdata/pandata-oai_dc/SET_1/json/fc178d6f-7b17-5608-8fd9-c7409adc0462.json
+++ /dev/null
@@ -1,95 +0,0 @@
-{
-    "Contact": [
-        "Science and Technology Facilities Council, ISIS"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.5286/ISIS.E.24088567",
-    "Discipline": "Not stated",
-    "Format": [
-        "isis neutron raw;binary;2;None"
-    ],
-    "Language": [
-        "English"
-    ],
-    "PublicationTimestamp": "2015-03-13T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Rights": [
-        "ISIS Data Management Policy http://www.isis.stfc.ac.uk/user-office/data-policy11204.html"
-    ],
-    "TempCoverageBegin": 63465595199,
-    "TempCoverageEnd": 63465595199,
-    "TemporalCoverage": " point in time : 2012-02-23T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2012-02-23T11:59:59Z",
-    "TemporalCoverage:EndDate": "2012-02-23T11:59:59Z",
-    "author": [
-        "Miss Chiara Pasquini",
-        "Professor Carla Andreani",
-        "Dr Giovanni Romanelli",
-        "Professor Chun Loong",
-        "Professor Roberto Senesi",
-        "Mr Jie Chen",
-        "Professor Kan Wang",
-        "Dr Alexander Kolesnikov",
-        "Professor Roberto Car"
-    ],
-    "fulltext": [
-        "\n    ",
-        "isis_24088567",
-        "2016-04-08T15:23:24Z",
-        "\n    ",
-        "\n      ",
-        "10.5286/ISIS.E.24088567",
-        "DINS scattering in supercritical water",
-        "The proposed experiment aims to explore in detail these two effects in a thermodynamic range at ~25 MPa over a temperature range of 280\u00b0 to 600\u00b0C, never investigated before, where the system undergoes different degrees of hydrogen bonding.  This proposal is part of a series of experiments (DINS and INS) and Monte Carlo simulation aiming to characterize the molecular dynamics of supercritical water across the pseudo-critical temperature in an extended thermodynamic region never investigated before, under the conditions pertinent to the proposed operation of supercritical water-cooled reactors (SCWRs). DINS results will be also a challenge to theoretical models that attempt to describe this phase. For supercritical water unique thermodynamic properties SCWR is considered a promising candidate of advanced power reactors that belong to the so-called the Generation-IV reactor technology.",
-        "[VESUVIO];RB1120203;run_number_range",
-        "http://dx.doi.org/10.5286/ISIS.E.24088567",
-        "Dr Giovanni Romanelli",
-        "Professor Chun Loong",
-        "Professor Roberto Senesi",
-        "Dr Alexander Kolesnikov",
-        "Professor Kan Wang",
-        "Professor Roberto Car",
-        "Miss Chiara Pasquini",
-        "Mr Jie Chen",
-        "Professor Carla Andreani",
-        "Science and Technology Facilities Council, ISIS",
-        "Clean energy and the environment, pharmaceuticals and health care, nanotechnology and materials engineering, catalysis and polymers, fundamental studies of materials",
-        "2015-03-13 02:59:31",
-        "en",
-        "ISIS;ISIS Pulsed Neutron & Muon Source;http://www.isis.stfc.ac.uk;[VESUVIO]",
-        "isis neutron raw;binary;2;None",
-        "ISIS, Harwell, United Kingdom",
-        "ISIS Data Management Policy http://www.isis.stfc.ac.uk/user-office/data-policy11204.html",
-        "GB",
-        "2012-02-23 11:21:34;2012-03-12 02:59:31"
-    ],
-    "notes": [
-        "The proposed experiment aims to explore in detail these two effects in a thermodynamic range at ~25 MPa over a temperature range of 280\u00b0 to 600\u00b0C, never investigated before, where the system undergoes different degrees of hydrogen bonding.  This proposal is part of a series of experiments (DINS and INS) and Monte Carlo simulation aiming to characterize the molecular dynamics of supercritical water across the pseudo-critical temperature in an extended thermodynamic region never investigated before, under the conditions pertinent to the proposed operation of supercritical water-cooled reactors (SCWRs). DINS results will be also a challenge to theoretical models that attempt to describe this phase. For supercritical water unique thermodynamic properties SCWR is considered a promising candidate of advanced power reactors that belong to the so-called the Generation-IV reactor technology."
-    ],
-    "oai_identifier": [
-        "isis_24088567"
-    ],
-    "oai_set": null,
-    "tags": [
-        {
-            "name": "Clean energy environment"
-        },
-        {
-            "name": "pharmaceuticals health care"
-        },
-        {
-            "name": "nanotechnology materials engineering"
-        },
-        {
-            "name": "catalysis polymers"
-        },
-        {
-            "name": "fundamental studies materials"
-        }
-    ],
-    "title": [
-        "DINS scattering in supercritical water"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pandata-oai_dc/SET_1/json/fc19e25b-d99b-56fc-b41c-ff5009707b81.json b/oaitestdata/pandata-oai_dc/SET_1/json/fc19e25b-d99b-56fc-b41c-ff5009707b81.json
deleted file mode 100644
index a1a495b5..00000000
--- a/oaitestdata/pandata-oai_dc/SET_1/json/fc19e25b-d99b-56fc-b41c-ff5009707b81.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Science and Technology Facilities Council, ISIS"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.5286/ISIS.E.24079418",
-    "Discipline": "Not stated",
-    "Format": [
-        "isis neutron raw;binary;2;None"
-    ],
-    "Language": [
-        "English"
-    ],
-    "PublicationTimestamp": "2013-07-21T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Rights": [
-        "ISIS Data Management Policy http://www.isis.stfc.ac.uk/user-office/data-policy11204.html"
-    ],
-    "TempCoverageBegin": 63415220399,
-    "TempCoverageEnd": 63415220399,
-    "TemporalCoverage": " point in time : 2010-07-20T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2010-07-20T11:59:59Z",
-    "TemporalCoverage:EndDate": "2010-07-20T11:59:59Z",
-    "author": [
-        "Mr Paul Brown",
-        "Mr Azmi Mohamed",
-        "Mr Stephen Cummings",
-        "Professor Julian Eastoe",
-        "Mr Marios Hopkins Hatzopoulos"
-    ],
-    "fulltext": [
-        "\n    ",
-        "isis_24079418",
-        "2016-04-08T15:23:11Z",
-        "\n    ",
-        "\n      ",
-        "10.5286/ISIS.E.24079418",
-        "Structural evolution - hydrotrope to surfactant",
-        "The aim is to improve understanding about combinations of normal surfactants and hydrotropes in aqueous systems. This is to support our recent work with but in non-aqueous solvents (RB920037, scheduling awaited, test data in Figure 2). A hydrotrope family will be investigated following an evolution of molecular structure (Figure 1), starting with a true hydrotrope (NaSAL), moving to an alkyl hydrotrope (C1, C4, C6-SAL), and ending with a chemically related true surfactant (C12-SAL). Although they are interesting colloidal systems in their own right, there is only limited scientific literature to consult on hydrotrope association structures. Such additives are of great industrial interest, exhibiting detergency efficiencies in both aqueous and oily phases. This new proposal is part of a joint Infineum-Bristol collaboration: the PhD (MH) has recently attended the ISIS training course. ",
-        "[LOQ];RB1010284;run_number_range",
-        "http://dx.doi.org/10.5286/ISIS.E.24079418",
-        "Mr Azmi Mohamed",
-        "Professor Julian Eastoe",
-        "Mr Marios Hopkins Hatzopoulos",
-        "Mr Stephen Cummings",
-        "Mr Paul Brown",
-        "Science and Technology Facilities Council, ISIS",
-        "Clean energy and the environment, pharmaceuticals and health care, nanotechnology and materials engineering, catalysis and polymers, fundamental studies of materials",
-        "2013-07-21 09:25:25",
-        "en",
-        "ISIS;ISIS Pulsed Neutron & Muon Source;http://www.isis.stfc.ac.uk;[LOQ]",
-        "isis neutron raw;binary;2;None",
-        "ISIS, Harwell, United Kingdom",
-        "ISIS Data Management Policy http://www.isis.stfc.ac.uk/user-office/data-policy11204.html",
-        "GB",
-        "2010-07-20 09:50:53;2010-07-21 09:25:25"
-    ],
-    "notes": [
-        "The aim is to improve understanding about combinations of normal surfactants and hydrotropes in aqueous systems. This is to support our recent work with but in non-aqueous solvents (RB920037, scheduling awaited, test data in Figure 2). A hydrotrope family will be investigated following an evolution of molecular structure (Figure 1), starting with a true hydrotrope (NaSAL), moving to an alkyl hydrotrope (C1, C4, C6-SAL), and ending with a chemically related true surfactant (C12-SAL). Although they are interesting colloidal systems in their own right, there is only limited scientific literature to consult on hydrotrope association structures. Such additives are of great industrial interest, exhibiting detergency efficiencies in both aqueous and oily phases. This new proposal is part of a joint Infineum-Bristol collaboration: the PhD (MH) has recently attended the ISIS training course. "
-    ],
-    "oai_identifier": [
-        "isis_24079418"
-    ],
-    "oai_set": null,
-    "tags": [
-        {
-            "name": "Clean energy environment"
-        },
-        {
-            "name": "pharmaceuticals health care"
-        },
-        {
-            "name": "nanotechnology materials engineering"
-        },
-        {
-            "name": "catalysis polymers"
-        },
-        {
-            "name": "fundamental studies materials"
-        }
-    ],
-    "title": [
-        "Structural evolution - hydrotrope to surfactant"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pandata-oai_dc/SET_1/json/fc55f300-2350-5b16-aa48-8d74d08ee355.json b/oaitestdata/pandata-oai_dc/SET_1/json/fc55f300-2350-5b16-aa48-8d74d08ee355.json
deleted file mode 100644
index 59c12e9a..00000000
--- a/oaitestdata/pandata-oai_dc/SET_1/json/fc55f300-2350-5b16-aa48-8d74d08ee355.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Science and Technology Facilities Council, ISIS"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.5286/ISIS.E.24079768",
-    "Discipline": "Not stated",
-    "Format": [
-        "isis neutron raw;binary;2;None"
-    ],
-    "Language": [
-        "English"
-    ],
-    "PublicationTimestamp": "2013-05-04T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Rights": [
-        "ISIS Data Management Policy http://www.isis.stfc.ac.uk/user-office/data-policy11204.html"
-    ],
-    "TempCoverageBegin": 63408308399,
-    "TempCoverageEnd": 63408308399,
-    "TemporalCoverage": " point in time : 2010-05-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2010-05-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2010-05-01T11:59:59Z",
-    "author": [
-        "Dr Jeroen Plomp",
-        "Dr Ad van Well"
-    ],
-    "fulltext": [
-        "\n    ",
-        "isis_24079768",
-        "2016-04-08T15:23:24Z",
-        "\n    ",
-        "\n      ",
-        "10.5286/ISIS.E.24079768",
-        "Structure of phospholipid monolayers containing lipid-PEG-ligand",
-        "The incorporation of lipid-PEG-ligand molecules into liposome membrane imparts targeting ability and specificity to liposomes. Crucial for the targeting ability is the accessibility of the ligand for the cell receptors. However, the surface of the liposome membrane is covered by PEG (polyethylene glycol) layer that shields the ligands and inhibits targeting. Modifying the liposome membrane with bidisperse PEG layer results in distribution of the ligands in the periphery of the liposome and thus enhanced targeting.  Here we would like to examine the structure of model liposome membranes with bidisperse PEG layer regarding the distribution of the ligands.",
-        "[SURF];RB1010369;run_number_range",
-        "http://dx.doi.org/10.5286/ISIS.E.24079768",
-        "Dr Jeroen Plomp",
-        "Dr Ad van Well",
-        "Science and Technology Facilities Council, ISIS",
-        "Clean energy and the environment, pharmaceuticals and health care, nanotechnology and materials engineering, catalysis and polymers, fundamental studies of materials",
-        "2013-05-04 08:43:02",
-        "en",
-        "ISIS;ISIS Pulsed Neutron & Muon Source;http://www.isis.stfc.ac.uk;[SURF]",
-        "isis neutron raw;binary;2;None",
-        "ISIS, Harwell, United Kingdom",
-        "ISIS Data Management Policy http://www.isis.stfc.ac.uk/user-office/data-policy11204.html",
-        "GB",
-        "2010-05-01 08:28:36;2010-05-04 08:43:02"
-    ],
-    "notes": [
-        "The incorporation of lipid-PEG-ligand molecules into liposome membrane imparts targeting ability and specificity to liposomes. Crucial for the targeting ability is the accessibility of the ligand for the cell receptors. However, the surface of the liposome membrane is covered by PEG (polyethylene glycol) layer that shields the ligands and inhibits targeting. Modifying the liposome membrane with bidisperse PEG layer results in distribution of the ligands in the periphery of the liposome and thus enhanced targeting.  Here we would like to examine the structure of model liposome membranes with bidisperse PEG layer regarding the distribution of the ligands."
-    ],
-    "oai_identifier": [
-        "isis_24079768"
-    ],
-    "oai_set": null,
-    "tags": [
-        {
-            "name": "Clean energy environment"
-        },
-        {
-            "name": "pharmaceuticals health care"
-        },
-        {
-            "name": "nanotechnology materials engineering"
-        },
-        {
-            "name": "catalysis polymers"
-        },
-        {
-            "name": "fundamental studies materials"
-        }
-    ],
-    "title": [
-        "Structure of phospholipid monolayers containing lipid-PEG-ligand"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pandata-oai_dc/SET_1/json/fc8fe91a-aa66-55b7-9c16-d6afdadc27ce.json b/oaitestdata/pandata-oai_dc/SET_1/json/fc8fe91a-aa66-55b7-9c16-d6afdadc27ce.json
deleted file mode 100644
index f0c2e449..00000000
--- a/oaitestdata/pandata-oai_dc/SET_1/json/fc8fe91a-aa66-55b7-9c16-d6afdadc27ce.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "Science and Technology Facilities Council, ISIS"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.5286/ISIS.E.24088944",
-    "Discipline": "Not stated",
-    "Format": [
-        "isis neutron raw;binary;2;None"
-    ],
-    "Language": [
-        "English"
-    ],
-    "PublicationTimestamp": "2015-05-26T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Rights": [
-        "ISIS Data Management Policy http://www.isis.stfc.ac.uk/user-office/data-policy11204.html"
-    ],
-    "TempCoverageBegin": 63468615599,
-    "TempCoverageEnd": 63468615599,
-    "TemporalCoverage": " point in time : 2012-03-29T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2012-03-29T11:59:59Z",
-    "TemporalCoverage:EndDate": "2012-03-29T11:59:59Z",
-    "author": [
-        "Dr Martin Rotter",
-        "Professor Andrew Boothroyd",
-        "Mr Stephen Gaw"
-    ],
-    "fulltext": [
-        "\n    ",
-        "isis_24088944",
-        "2016-04-08T15:22:28Z",
-        "\n    ",
-        "\n      ",
-        "10.5286/ISIS.E.24088944",
-        "Electronic state of Co3+ in LaCoO3",
-        "We will search for spin-orbit transitions of the Co3+ ions in LaCoO3. The ground state is a non-magnetic singlet, but there continues to be a debate about the nature of the lowest excited levels, which could either be from the intermediate spin (S=1) or high spin (S=2) terms. We have calculated the neutron cross section based on a recently-published model and obtained predictions of electronic transitions which should be present in the neutron spectrum. We will measure the spectrum up to 500 meV at base temperature and room temperature. If we can measure these excitations then it will provide a direct and unambiguous resolution to a 50-year old problem.",
-        "[MAPS];RB1210197;run_number_range",
-        "http://dx.doi.org/10.5286/ISIS.E.24088944",
-        "Dr Martin Rotter",
-        "Mr Stephen Gaw",
-        "Professor Andrew Boothroyd",
-        "Science and Technology Facilities Council, ISIS",
-        "Clean energy and the environment, pharmaceuticals and health care, nanotechnology and materials engineering, catalysis and polymers, fundamental studies of materials",
-        "2015-05-26 23:15:31",
-        "en",
-        "ISIS;ISIS Pulsed Neutron & Muon Source;http://www.isis.stfc.ac.uk;[MAPS]",
-        "isis neutron raw;binary;2;None",
-        "ISIS, Harwell, United Kingdom",
-        "ISIS Data Management Policy http://www.isis.stfc.ac.uk/user-office/data-policy11204.html",
-        "GB",
-        "2012-03-29 14:33:10;2012-05-25 23:15:31"
-    ],
-    "notes": [
-        "We will search for spin-orbit transitions of the Co3+ ions in LaCoO3. The ground state is a non-magnetic singlet, but there continues to be a debate about the nature of the lowest excited levels, which could either be from the intermediate spin (S=1) or high spin (S=2) terms. We have calculated the neutron cross section based on a recently-published model and obtained predictions of electronic transitions which should be present in the neutron spectrum. We will measure the spectrum up to 500 meV at base temperature and room temperature. If we can measure these excitations then it will provide a direct and unambiguous resolution to a 50-year old problem."
-    ],
-    "oai_identifier": [
-        "isis_24088944"
-    ],
-    "oai_set": null,
-    "tags": [
-        {
-            "name": "Clean energy environment"
-        },
-        {
-            "name": "pharmaceuticals health care"
-        },
-        {
-            "name": "nanotechnology materials engineering"
-        },
-        {
-            "name": "catalysis polymers"
-        },
-        {
-            "name": "fundamental studies materials"
-        }
-    ],
-    "title": [
-        "Electronic state of Co3+ in LaCoO3"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pandata-oai_dc/SET_1/json/fca3ffa6-dfaa-517f-9dca-70f1b66ce104.json b/oaitestdata/pandata-oai_dc/SET_1/json/fca3ffa6-dfaa-517f-9dca-70f1b66ce104.json
deleted file mode 100644
index b8dced46..00000000
--- a/oaitestdata/pandata-oai_dc/SET_1/json/fca3ffa6-dfaa-517f-9dca-70f1b66ce104.json
+++ /dev/null
@@ -1,79 +0,0 @@
-{
-    "Contact": [
-        "Science and Technology Facilities Council, ISIS"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.5286/ISIS.E.24090014",
-    "Discipline": "Not stated",
-    "Format": [
-        "isis neutron raw;binary;2;None"
-    ],
-    "Language": [
-        "English"
-    ],
-    "PublicationTimestamp": "2015-12-07T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Rights": [
-        "ISIS Data Management Policy http://www.isis.stfc.ac.uk/user-office/data-policy11204.html"
-    ],
-    "TempCoverageBegin": 63490391999,
-    "TempCoverageEnd": 63490391999,
-    "TemporalCoverage": " point in time : 2012-12-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2012-12-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "2012-12-06T11:59:59Z",
-    "author": [
-        "Dr Dirk Visser"
-    ],
-    "fulltext": [
-        "\n    ",
-        "isis_24090014",
-        "2016-04-08T15:22:47Z",
-        "\n    ",
-        "\n      ",
-        "10.5286/ISIS.E.24090014",
-        "CaCO3-FeO(x) Tell-Bazi 4 1103 (no spacer)",
-        "None",
-        "[GEM];RB1290066;run_number_range;bcat_inv_str",
-        "http://dx.doi.org/10.5286/ISIS.E.24090014",
-        "Dr Dirk Visser",
-        "Science and Technology Facilities Council, ISIS",
-        "Clean energy and the environment, pharmaceuticals and health care, nanotechnology and materials engineering, catalysis and polymers, fundamental studies of materials",
-        "2015-12-07 03:39:13",
-        "en",
-        "ISIS;ISIS Pulsed Neutron & Muon Source;http://www.isis.stfc.ac.uk;[GEM]",
-        "isis neutron raw;binary;2;None",
-        "ISIS, Harwell, United Kingdom",
-        "ISIS Data Management Policy http://www.isis.stfc.ac.uk/user-office/data-policy11204.html",
-        "GB",
-        "2012-12-06 02:32:46;2012-12-06 03:39:13"
-    ],
-    "notes": [
-        "None"
-    ],
-    "oai_identifier": [
-        "isis_24090014"
-    ],
-    "oai_set": null,
-    "tags": [
-        {
-            "name": "Clean energy environment"
-        },
-        {
-            "name": "pharmaceuticals health care"
-        },
-        {
-            "name": "nanotechnology materials engineering"
-        },
-        {
-            "name": "catalysis polymers"
-        },
-        {
-            "name": "fundamental studies materials"
-        }
-    ],
-    "title": [
-        "CaCO3-FeO(x) Tell-Bazi 4 1103 (no spacer)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pandata-oai_dc/SET_1/json/fcaf32bb-f31e-56ba-974a-1da970cb7d65.json b/oaitestdata/pandata-oai_dc/SET_1/json/fcaf32bb-f31e-56ba-974a-1da970cb7d65.json
deleted file mode 100644
index 5f5bb8f3..00000000
--- a/oaitestdata/pandata-oai_dc/SET_1/json/fcaf32bb-f31e-56ba-974a-1da970cb7d65.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "Science and Technology Facilities Council, ISIS"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.5286/ISIS.E.24089950",
-    "Discipline": "Not stated",
-    "Format": [
-        "isis neutron raw;binary;2;None"
-    ],
-    "Language": [
-        "English"
-    ],
-    "PublicationTimestamp": "2015-12-19T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Rights": [
-        "ISIS Data Management Policy http://www.isis.stfc.ac.uk/user-office/data-policy11204.html"
-    ],
-    "TempCoverageBegin": 63490823999,
-    "TempCoverageEnd": 63490823999,
-    "TemporalCoverage": " point in time : 2012-12-11T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2012-12-11T11:59:59Z",
-    "TemporalCoverage:EndDate": "2012-12-11T11:59:59Z",
-    "author": [
-        "Dr Anita Zeidler",
-        "Professor Phil Salmon",
-        "Mr Keiron Pizzey",
-        "Miss Ruth Rowlands"
-    ],
-    "fulltext": [
-        "\n    ",
-        "isis_24089950",
-        "2016-04-08T15:23:11Z",
-        "\n    ",
-        "\n      ",
-        "10.5286/ISIS.E.24089950",
-        "The partial vibrational density of states for As2Se3 glass",
-        "The method of Se isotope substitution with inelastic neutron scattering will be used to measure the partial VDOS for As2Se3 glass. This is a prototypical network forming material, part of a family that provide the basis of glasses with important infrared transmitting and other optical properties. The predominant structural motif in this glass is the pyramidal AsSe3 unit, in contrast with many other network forming materials (e.g. GeSe2, GeO2, SiO2) which are constructed from corner and/or edge sharing tetrahedra. The results will therefore provide insight into the dynamics of networks with contrasting connectivities. They will also be used in the development of realistic first principles molecular dynamics models for As2Se3 glass. The experiments will make full use of the attributes of the MERLIN spectrometer.",
-        "[MERLIN];RB1220171;run_number_range",
-        "http://dx.doi.org/10.5286/ISIS.E.24089950",
-        "Professor Phil Salmon",
-        "Dr Anita Zeidler",
-        "Mr Keiron Pizzey",
-        "Miss Ruth Rowlands",
-        "Science and Technology Facilities Council, ISIS",
-        "Clean energy and the environment, pharmaceuticals and health care, nanotechnology and materials engineering, catalysis and polymers, fundamental studies of materials",
-        "2015-12-19 15:36:26",
-        "en",
-        "ISIS;ISIS Pulsed Neutron & Muon Source;http://www.isis.stfc.ac.uk;[MERLIN]",
-        "isis neutron raw;binary;2;None",
-        "ISIS, Harwell, United Kingdom",
-        "ISIS Data Management Policy http://www.isis.stfc.ac.uk/user-office/data-policy11204.html",
-        "GB",
-        "2012-12-11 10:33:37;2012-12-18 15:36:26"
-    ],
-    "notes": [
-        "The method of Se isotope substitution with inelastic neutron scattering will be used to measure the partial VDOS for As2Se3 glass. This is a prototypical network forming material, part of a family that provide the basis of glasses with important infrared transmitting and other optical properties. The predominant structural motif in this glass is the pyramidal AsSe3 unit, in contrast with many other network forming materials (e.g. GeSe2, GeO2, SiO2) which are constructed from corner and/or edge sharing tetrahedra. The results will therefore provide insight into the dynamics of networks with contrasting connectivities. They will also be used in the development of realistic first principles molecular dynamics models for As2Se3 glass. The experiments will make full use of the attributes of the MERLIN spectrometer."
-    ],
-    "oai_identifier": [
-        "isis_24089950"
-    ],
-    "oai_set": null,
-    "tags": [
-        {
-            "name": "Clean energy environment"
-        },
-        {
-            "name": "pharmaceuticals health care"
-        },
-        {
-            "name": "nanotechnology materials engineering"
-        },
-        {
-            "name": "catalysis polymers"
-        },
-        {
-            "name": "fundamental studies materials"
-        }
-    ],
-    "title": [
-        "The partial vibrational density of states for As2Se3 glass"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pandata-oai_dc/SET_1/json/fccfd865-b9bf-5a29-9f01-1e9cdc66d371.json b/oaitestdata/pandata-oai_dc/SET_1/json/fccfd865-b9bf-5a29-9f01-1e9cdc66d371.json
deleted file mode 100644
index 96337827..00000000
--- a/oaitestdata/pandata-oai_dc/SET_1/json/fccfd865-b9bf-5a29-9f01-1e9cdc66d371.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "Science and Technology Facilities Council, ISIS"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.5286/ISIS.E.24086022",
-    "Discipline": "Not stated",
-    "Format": [
-        "isis neutron raw;binary;2;None"
-    ],
-    "Language": [
-        "English"
-    ],
-    "PublicationTimestamp": "2014-05-25T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Rights": [
-        "ISIS Data Management Policy http://www.isis.stfc.ac.uk/user-office/data-policy11204.html"
-    ],
-    "TempCoverageBegin": 63441140399,
-    "TempCoverageEnd": 63441140399,
-    "TemporalCoverage": " point in time : 2011-05-16T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2011-05-16T11:59:59Z",
-    "TemporalCoverage:EndDate": "2011-05-16T11:59:59Z",
-    "author": [
-        "Dr Anita Zeidler",
-        "Professor Phil Salmon",
-        "Professor Steve Bennington",
-        "Mr Dean Whittaker"
-    ],
-    "fulltext": [
-        "\n    ",
-        "isis_24086022",
-        "2016-04-08T15:23:22Z",
-        "\n    ",
-        "\n      ",
-        "10.5286/ISIS.E.24086022",
-        "The partial dynamical structure factors and vibrational density of states in network glasses",
-        "We wish to measure the partial dynamical structure factors and the partial vibrational density of states (VDOS) for the archetypal network forming glass GeSe2 by using the method of isotope substitution in neutron scattering and the MERLIN spectrometer. Essentially, by averaging the separated Ge-Ge and Se-Se partial dynamical structure factors over Q, it is possible to obtain the exact VDOS for Ge and Se, respectively. The work builds on an initial test experiment using MERLIN (RB920266) where there was a substantial background scattering problem associated with use of an Al cryostat tail. Instead, in the new experiment, a \u00bfcold finger\u00bf will be used to remove this background scattering problem while still giving access to low temperatures. This is important to ensure that the harmonic approximation is valid and to minimise the multi-phonon contribution to the sample scattering.",
-        "[MERLIN];RB1110412;run_number_range",
-        "http://dx.doi.org/10.5286/ISIS.E.24086022",
-        "Professor Steve Bennington",
-        "Professor Phil Salmon",
-        "Mr Dean Whittaker",
-        "Dr Anita Zeidler",
-        "Science and Technology Facilities Council, ISIS",
-        "Clean energy and the environment, pharmaceuticals and health care, nanotechnology and materials engineering, catalysis and polymers, fundamental studies of materials",
-        "2014-05-25 05:04:25",
-        "en",
-        "ISIS;ISIS Pulsed Neutron & Muon Source;http://www.isis.stfc.ac.uk;[MERLIN]",
-        "isis neutron raw;binary;2;None",
-        "ISIS, Harwell, United Kingdom",
-        "ISIS Data Management Policy http://www.isis.stfc.ac.uk/user-office/data-policy11204.html",
-        "GB",
-        "2011-05-16 09:52:16;2011-05-25 05:04:25"
-    ],
-    "notes": [
-        "We wish to measure the partial dynamical structure factors and the partial vibrational density of states (VDOS) for the archetypal network forming glass GeSe2 by using the method of isotope substitution in neutron scattering and the MERLIN spectrometer. Essentially, by averaging the separated Ge-Ge and Se-Se partial dynamical structure factors over Q, it is possible to obtain the exact VDOS for Ge and Se, respectively. The work builds on an initial test experiment using MERLIN (RB920266) where there was a substantial background scattering problem associated with use of an Al cryostat tail. Instead, in the new experiment, a \u00bfcold finger\u00bf will be used to remove this background scattering problem while still giving access to low temperatures. This is important to ensure that the harmonic approximation is valid and to minimise the multi-phonon contribution to the sample scattering."
-    ],
-    "oai_identifier": [
-        "isis_24086022"
-    ],
-    "oai_set": null,
-    "tags": [
-        {
-            "name": "Clean energy environment"
-        },
-        {
-            "name": "pharmaceuticals health care"
-        },
-        {
-            "name": "nanotechnology materials engineering"
-        },
-        {
-            "name": "catalysis polymers"
-        },
-        {
-            "name": "fundamental studies materials"
-        }
-    ],
-    "title": [
-        "The partial dynamical structure factors and vibrational density of states in network glasses"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pandata-oai_dc/SET_1/json/fcd00056-e275-55eb-b658-b17ffb398bb0.json b/oaitestdata/pandata-oai_dc/SET_1/json/fcd00056-e275-55eb-b658-b17ffb398bb0.json
deleted file mode 100644
index 3acf1f58..00000000
--- a/oaitestdata/pandata-oai_dc/SET_1/json/fcd00056-e275-55eb-b658-b17ffb398bb0.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Science and Technology Facilities Council, ISIS"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.5286/ISIS.E.24079624",
-    "Discipline": "Not stated",
-    "Format": [
-        "isis neutron raw;binary;2;None"
-    ],
-    "Language": [
-        "English"
-    ],
-    "PublicationTimestamp": "2013-07-19T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Rights": [
-        "ISIS Data Management Policy http://www.isis.stfc.ac.uk/user-office/data-policy11204.html"
-    ],
-    "TempCoverageBegin": 63404510399,
-    "TempCoverageEnd": 63404510399,
-    "TemporalCoverage": " point in time : 2010-03-18T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2010-03-18T11:59:59Z",
-    "TemporalCoverage:EndDate": "2010-03-18T11:59:59Z",
-    "author": [
-        "Professor Christopher Marrows",
-        "Dr Steve Lister"
-    ],
-    "fulltext": [
-        "\n    ",
-        "isis_24079624",
-        "2016-04-08T15:22:30Z",
-        "\n    ",
-        "\n      ",
-        "10.5286/ISIS.E.24079624",
-        "Interaction between superconductivity and magnetism in iron-lead thin films",
-        "A previous CRISP measurement allows us to show for the first time using PNR a change in the response due to superconductivity in an Fe/Pb/Fe tri-layer sample. This type of system is of particular interest owing to the possibility of novel forms of superconductivity appearing on mesoscopic length scales. One manifestation of this could be a so-called \u00bfinverse-proximity\u00bf effect, in which a magnetisation is induced in the superconducting layer by coupling to the ferromagnetic layers. With more detailed measurements, particularly of the field dependence, we hope to distinguish this effect from Meisner screening. In addition, a low-energy muon study found evidence for a spin-density wave state, with a particular modification of the magnetisation in the Pb layer near the interfaces below TC. Observing this with PNR would contribute significantly to a fuller understanding of the effect.",
-        "[CRISP];RB920463;run_number_range",
-        "http://dx.doi.org/10.5286/ISIS.E.24079624",
-        "Dr Steve Lister",
-        "Professor Christopher Marrows",
-        "Science and Technology Facilities Council, ISIS",
-        "Clean energy and the environment, pharmaceuticals and health care, nanotechnology and materials engineering, catalysis and polymers, fundamental studies of materials",
-        "2013-07-19 08:31:29",
-        "en",
-        "ISIS;ISIS Pulsed Neutron & Muon Source;http://www.isis.stfc.ac.uk;[CRISP]",
-        "isis neutron raw;binary;2;None",
-        "ISIS, Harwell, United Kingdom",
-        "ISIS Data Management Policy http://www.isis.stfc.ac.uk/user-office/data-policy11204.html",
-        "GB",
-        "2010-03-18 08:53:37;2010-07-19 08:31:29"
-    ],
-    "notes": [
-        "A previous CRISP measurement allows us to show for the first time using PNR a change in the response due to superconductivity in an Fe/Pb/Fe tri-layer sample. This type of system is of particular interest owing to the possibility of novel forms of superconductivity appearing on mesoscopic length scales. One manifestation of this could be a so-called \u00bfinverse-proximity\u00bf effect, in which a magnetisation is induced in the superconducting layer by coupling to the ferromagnetic layers. With more detailed measurements, particularly of the field dependence, we hope to distinguish this effect from Meisner screening. In addition, a low-energy muon study found evidence for a spin-density wave state, with a particular modification of the magnetisation in the Pb layer near the interfaces below TC. Observing this with PNR would contribute significantly to a fuller understanding of the effect."
-    ],
-    "oai_identifier": [
-        "isis_24079624"
-    ],
-    "oai_set": null,
-    "tags": [
-        {
-            "name": "Clean energy environment"
-        },
-        {
-            "name": "pharmaceuticals health care"
-        },
-        {
-            "name": "nanotechnology materials engineering"
-        },
-        {
-            "name": "catalysis polymers"
-        },
-        {
-            "name": "fundamental studies materials"
-        }
-    ],
-    "title": [
-        "Interaction between superconductivity and magnetism in iron-lead thin films"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pandata-oai_dc/SET_1/json/fcd6881b-c038-5f89-83d1-49d87a2d7710.json b/oaitestdata/pandata-oai_dc/SET_1/json/fcd6881b-c038-5f89-83d1-49d87a2d7710.json
deleted file mode 100644
index 7e435025..00000000
--- a/oaitestdata/pandata-oai_dc/SET_1/json/fcd6881b-c038-5f89-83d1-49d87a2d7710.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "Science and Technology Facilities Council, ISIS"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.5286/ISIS.E.24090603",
-    "Discipline": "Not stated",
-    "Format": [
-        "isis neutron raw;binary;2;None"
-    ],
-    "Language": [
-        "English"
-    ],
-    "PublicationTimestamp": "2016-05-17T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Rights": [
-        "ISIS Data Management Policy http://www.isis.stfc.ac.uk/user-office/data-policy11204.html"
-    ],
-    "TempCoverageBegin": 63504212399,
-    "TempCoverageEnd": 63504212399,
-    "TemporalCoverage": " point in time : 2013-05-15T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2013-05-15T11:59:59Z",
-    "TemporalCoverage:EndDate": "2013-05-15T11:59:59Z",
-    "author": [
-        "Mr Abdullah al Mamun",
-        "Dr Hedieh Jazaeri",
-        "Professor Mike Hutchings",
-        "Professor John Bouchard"
-    ],
-    "fulltext": [
-        "\n    ",
-        "isis_24090603",
-        "2016-05-17T15:36:21Z",
-        "\n    ",
-        "\n      ",
-        "10.5286/ISIS.E.24090603",
-        "Development of Creep Cavitation in Stainless Steel",
-        "Reheat cracking is a creep failure mode that has been observed in welded structures operating at high temperatures in the power generation industry. The failure results from the initiation and growth of voids mainly at grain boundaries. A trial experiment has been performed using the D11 instrument and the size distribution of creep cavities size of 1-600 nm characterised. The present experiment will use the SANS2d to measure cavities in interrupted uniaxial creep test specimens which allow us to characterise the cavity size distribution development as a function of life fraction and uniaxial accumulated creep strain. Also it will be used to measure the distribution of creep cavitation damage along the length of a ruptured creep test specimen and a cross weld test specimen to capture the expected rapid spatial variation in creep damage approaching the weld line.  ",
-        "[SANS2D];RB1310349;run_number_range",
-        "http://dx.doi.org/10.5286/ISIS.E.24090603",
-        "Professor Mike Hutchings",
-        "Professor John Bouchard",
-        "Mr Abdullah al Mamun",
-        "Dr Hedieh Jazaeri",
-        "Science and Technology Facilities Council, ISIS",
-        "Clean energy and the environment, pharmaceuticals and health care, nanotechnology and materials engineering, catalysis and polymers, fundamental studies of materials",
-        "2016-05-17 09:18:17",
-        "en",
-        "ISIS;ISIS Pulsed Neutron & Muon Source;http://www.isis.stfc.ac.uk;[SANS2D]",
-        "isis neutron raw;binary;2;None",
-        "ISIS, Harwell, United Kingdom",
-        "ISIS Data Management Policy http://www.isis.stfc.ac.uk/user-office/data-policy11204.html",
-        "GB",
-        "2013-05-15 10:27:43;2013-05-17 09:18:17"
-    ],
-    "notes": [
-        "Reheat cracking is a creep failure mode that has been observed in welded structures operating at high temperatures in the power generation industry. The failure results from the initiation and growth of voids mainly at grain boundaries. A trial experiment has been performed using the D11 instrument and the size distribution of creep cavities size of 1-600 nm characterised. The present experiment will use the SANS2d to measure cavities in interrupted uniaxial creep test specimens which allow us to characterise the cavity size distribution development as a function of life fraction and uniaxial accumulated creep strain. Also it will be used to measure the distribution of creep cavitation damage along the length of a ruptured creep test specimen and a cross weld test specimen to capture the expected rapid spatial variation in creep damage approaching the weld line.  "
-    ],
-    "oai_identifier": [
-        "isis_24090603"
-    ],
-    "oai_set": null,
-    "tags": [
-        {
-            "name": "Clean energy environment"
-        },
-        {
-            "name": "pharmaceuticals health care"
-        },
-        {
-            "name": "nanotechnology materials engineering"
-        },
-        {
-            "name": "catalysis polymers"
-        },
-        {
-            "name": "fundamental studies materials"
-        }
-    ],
-    "title": [
-        "Development of Creep Cavitation in Stainless Steel"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pandata-oai_dc/SET_1/json/fcd6ebc9-cc3e-5599-8c44-a863721f373e.json b/oaitestdata/pandata-oai_dc/SET_1/json/fcd6ebc9-cc3e-5599-8c44-a863721f373e.json
deleted file mode 100644
index 113f4e9a..00000000
--- a/oaitestdata/pandata-oai_dc/SET_1/json/fcd6ebc9-cc3e-5599-8c44-a863721f373e.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "Science and Technology Facilities Council, ISIS"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.5286/ISIS.E.24078918",
-    "Discipline": "Not stated",
-    "Format": [
-        "isis neutron raw;binary;2;None"
-    ],
-    "Language": [
-        "English"
-    ],
-    "PublicationTimestamp": "2013-07-08T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Rights": [
-        "ISIS Data Management Policy http://www.isis.stfc.ac.uk/user-office/data-policy11204.html"
-    ],
-    "TempCoverageBegin": 63395438399,
-    "TempCoverageEnd": 63395438399,
-    "TemporalCoverage": " point in time : 2009-12-03T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2009-12-03T11:59:59Z",
-    "TemporalCoverage:EndDate": "2009-12-03T11:59:59Z",
-    "author": [
-        "Dr Howard Stone",
-        "Ms Jestine Ang"
-    ],
-    "fulltext": [
-        "\n    ",
-        "isis_24078918",
-        "2016-04-08T15:22:56Z",
-        "\n    ",
-        "\n      ",
-        "10.5286/ISIS.E.24078918",
-        "Inter-phase load partitioning in a directionally-solidified Cr-Cr3Si eutectic",
-        "In situ composite materials based upon refractory metal - silicide eutectics are being considered for high temperature structural applications.  These materials derive their high temperature strength from a creep-resistant silicide phase and toughening from a metallic matrix.  Directional solidification under planar growth front conditions can give rise to microstructures of aligned lamellae of these phase leading to considerable strength along the growth direction.  In this experiment it is proposed that the interphase stresses in a Cr-Cr3Si lamellar eutectic composite be investigated to determine its load partitioning behaviour during heating, elastic deformation at intermediate and high temperatures and how these interphase stresses evolve during creep deformation.",
-        "[ENGINX];RB820421;bcat_inv_str;run_number_range",
-        "http://dx.doi.org/10.5286/ISIS.E.24078918",
-        "Ms Jestine Ang",
-        "Dr Howard Stone",
-        "Science and Technology Facilities Council, ISIS",
-        "Clean energy and the environment, pharmaceuticals and health care, nanotechnology and materials engineering, catalysis and polymers, fundamental studies of materials",
-        "2013-07-08 08:22:55",
-        "en",
-        "ISIS;ISIS Pulsed Neutron & Muon Source;http://www.isis.stfc.ac.uk;[ENGINX]",
-        "isis neutron raw;binary;2;None",
-        "ISIS, Harwell, United Kingdom",
-        "ISIS Data Management Policy http://www.isis.stfc.ac.uk/user-office/data-policy11204.html",
-        "GB",
-        "2009-12-03 10:55:51;2010-07-08 08:22:55"
-    ],
-    "notes": [
-        "In situ composite materials based upon refractory metal - silicide eutectics are being considered for high temperature structural applications.  These materials derive their high temperature strength from a creep-resistant silicide phase and toughening from a metallic matrix.  Directional solidification under planar growth front conditions can give rise to microstructures of aligned lamellae of these phase leading to considerable strength along the growth direction.  In this experiment it is proposed that the interphase stresses in a Cr-Cr3Si lamellar eutectic composite be investigated to determine its load partitioning behaviour during heating, elastic deformation at intermediate and high temperatures and how these interphase stresses evolve during creep deformation."
-    ],
-    "oai_identifier": [
-        "isis_24078918"
-    ],
-    "oai_set": null,
-    "tags": [
-        {
-            "name": "Clean energy environment"
-        },
-        {
-            "name": "pharmaceuticals health care"
-        },
-        {
-            "name": "nanotechnology materials engineering"
-        },
-        {
-            "name": "catalysis polymers"
-        },
-        {
-            "name": "fundamental studies materials"
-        }
-    ],
-    "title": [
-        "Inter-phase load partitioning in a directionally-solidified Cr-Cr3Si eutectic"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pandata-oai_dc/SET_1/json/fcff3bab-717e-5970-bb4b-8800937770ff.json b/oaitestdata/pandata-oai_dc/SET_1/json/fcff3bab-717e-5970-bb4b-8800937770ff.json
deleted file mode 100644
index 9974fe19..00000000
--- a/oaitestdata/pandata-oai_dc/SET_1/json/fcff3bab-717e-5970-bb4b-8800937770ff.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "Science and Technology Facilities Council, ISIS"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.5286/ISIS.E.24088312",
-    "Discipline": "Not stated",
-    "Format": [
-        "isis neutron raw;binary;2;None"
-    ],
-    "Language": [
-        "English"
-    ],
-    "PublicationTimestamp": "2014-11-29T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Rights": [
-        "ISIS Data Management Policy http://www.isis.stfc.ac.uk/user-office/data-policy11204.html"
-    ],
-    "TempCoverageBegin": 63457127999,
-    "TempCoverageEnd": 63457127999,
-    "TemporalCoverage": " point in time : 2011-11-17T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2011-11-17T11:59:59Z",
-    "TemporalCoverage:EndDate": "2011-11-17T11:59:59Z",
-    "author": [
-        "Dr Peter Dunne",
-        "Dr Emma Barney",
-        "Professor Richard Walton",
-        "Dr Alex Hannon",
-        "Dr Helen Playford"
-    ],
-    "fulltext": [
-        "\n    ",
-        "isis_24088312",
-        "2016-04-08T15:22:38Z",
-        "\n    ",
-        "\n      ",
-        "10.5286/ISIS.E.24088312",
-        "Structures of Gel Precursors of Nanoporous Materials",
-        "Our aim is to examine the structures of disordered gel precursors to nanoporous zeolites that are formed in the early stages of hydrothermal reactions. They are considered to be intermediates in the synthesis of zeolites materials, although their structures have not yet been described in any detail: indeed previous work has studied samples quneched from reactions mixtures. We will study gel phases in situ, in the presence of their mother liquor. This is a continuation of RB1010291, where we have results that show the total scattering from the gel in situ differs considerably from the material recovered and dried, and also that we can see atomic correlations due to the gel in the presence of the liquid. Now we wish to study how the gel structure evolves with time prior to crystallisation. The project forms part of a larger effort aimed at understanding the formation of complex solids. ",
-        "[SANDALS];RB1120187;run_number_range",
-        "http://dx.doi.org/10.5286/ISIS.E.24088312",
-        "Dr Peter Dunne",
-        "Dr Alex Hannon",
-        "Dr Emma Barney",
-        "Professor Richard Walton",
-        "Dr Helen Playford",
-        "Science and Technology Facilities Council, ISIS",
-        "Clean energy and the environment, pharmaceuticals and health care, nanotechnology and materials engineering, catalysis and polymers, fundamental studies of materials",
-        "2014-11-29 10:53:47",
-        "en",
-        "ISIS;ISIS Pulsed Neutron & Muon Source;http://www.isis.stfc.ac.uk;[SANDALS]",
-        "isis neutron raw;binary;2;None",
-        "ISIS, Harwell, United Kingdom",
-        "ISIS Data Management Policy http://www.isis.stfc.ac.uk/user-office/data-policy11204.html",
-        "GB",
-        "2011-11-17 13:16:24;2011-11-29 10:53:47"
-    ],
-    "notes": [
-        "Our aim is to examine the structures of disordered gel precursors to nanoporous zeolites that are formed in the early stages of hydrothermal reactions. They are considered to be intermediates in the synthesis of zeolites materials, although their structures have not yet been described in any detail: indeed previous work has studied samples quneched from reactions mixtures. We will study gel phases in situ, in the presence of their mother liquor. This is a continuation of RB1010291, where we have results that show the total scattering from the gel in situ differs considerably from the material recovered and dried, and also that we can see atomic correlations due to the gel in the presence of the liquid. Now we wish to study how the gel structure evolves with time prior to crystallisation. The project forms part of a larger effort aimed at understanding the formation of complex solids. "
-    ],
-    "oai_identifier": [
-        "isis_24088312"
-    ],
-    "oai_set": null,
-    "tags": [
-        {
-            "name": "Clean energy environment"
-        },
-        {
-            "name": "pharmaceuticals health care"
-        },
-        {
-            "name": "nanotechnology materials engineering"
-        },
-        {
-            "name": "catalysis polymers"
-        },
-        {
-            "name": "fundamental studies materials"
-        }
-    ],
-    "title": [
-        "Structures of Gel Precursors of Nanoporous Materials"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ACD_1/json/95c0721b-0ad0-5199-b53b-58c8840e3110.json b/oaitestdata/pangaea-datacite3/ACD_1/json/95c0721b-0ad0-5199-b53b-58c8840e3110.json
deleted file mode 100644
index 55a845b6..00000000
--- a/oaitestdata/pangaea-datacite3/ACD_1/json/95c0721b-0ad0-5199-b53b-58c8840e3110.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.76966",
-    "Discipline": "Geosciences",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "PublicationTimestamp": "2002-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2002"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": [
-        "70.77607607 110.1977526 76.20273068 141.161218"
-    ],
-    "author": [
-        "Rachold, Volker",
-        "Grigoriev, Mikhail N"
-    ],
-    "fulltext": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.76966",
-        "2017-08-04T13:23:21Z",
-        "ACD",
-        "ORFOIS",
-        "10.1594/PANGAEA.76966",
-        "Grigoriev, Mikhail N",
-        "Rachold, Volker",
-        "Data of 71 coastal sections from the arctic ocean",
-        "PANGAEA - Data Publisher for Earth & Environmental Science",
-        "2002",
-        "Event label",
-        "Latitude of event",
-        "Longitude of event",
-        "Latitude of event 2",
-        "Longitude of event 2",
-        "ELEVATION",
-        "Cliff height",
-        "Density, dry bulk",
-        "Coastal retreat rate",
-        "Ground-ice",
-        "Carbon, organic, total",
-        "Comment",
-        "Visual observation",
-        "Calculated from weight/volume",
-        "Calculated",
-        "Element analyser CHN, LECO",
-        "Laptev_Sea_2002",
-        "Sampling on land",
-        "Arctic Coastal Dynamics (ACD)",
-        "eng",
-        "Dataset",
-        "10.2312/BzP_0354_1_2000",
-        "10.2312/BzPM_0388_2001",
-        "379 data points",
-        "text/tab-separated-values",
-        "Creative Commons Attribution 3.0 Unported (CC-BY)",
-        "70.77607607 110.1977526 76.20273068 141.161218"
-    ],
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.76966"
-    ],
-    "oai_set": [
-        "ACD",
-        "ORFOIS"
-    ],
-    "tags": [
-        {
-            "name": "Arctic Coastal Dynamics ACD"
-        }
-    ],
-    "title": [
-        "Data of 71 coastal sections from the arctic ocean"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ACD_1/json/aa2a1b44-42b2-52ff-98d1-20ab4dae8a18.json b/oaitestdata/pangaea-datacite3/ACD_1/json/aa2a1b44-42b2-52ff-98d1-20ab4dae8a18.json
deleted file mode 100644
index 64114409..00000000
--- a/oaitestdata/pangaea-datacite3/ACD_1/json/aa2a1b44-42b2-52ff-98d1-20ab4dae8a18.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.58197",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.58197"
-    ],
-    "PublicationTimestamp": "2000-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Supplementary Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(72N,129E)",
-    "TempCoverageBegin": 62514331199,
-    "TempCoverageEnd": 62514331199,
-    "TemporalCoverage": " point in time : 1982-01-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1982-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1982-01-01T11:59:59Z",
-    "author": [
-        "Rachold, Volker"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.58197;2017-08-04T12:57:52Z;ACD;citable;citableWithChilds;supplement;10.1594/PANGAEA.58197;Rachold, Volker;Discription of coastal shape at Bykovsky Peninsula, supplement to: Rachold, Volker; Grigoriev, Mikhail N; Are, Felix; Solomon, Steven; Reimnitz, Erk; Kassens, Heidemarie; Antonow, A (2000): Coastal erosion vs. riverine sediment discharge in the Arctic Shelf Seas. International Journal of Earth Sciences, 89(3), 450-460;PANGAEA - Data Publisher for Earth & Environmental Science;2000;GetInfo;Date/Time of event;Date/Time of event 2;Elevation of event;Elevation of event 2;Onshore FORM-code;Distance to 10 m contour;Distance to 100 m contour;Distance to 500 m contour;Description;Backshore FORM-code;Shorezone complexity;Frontshore FORM-code;Offshore FORM-code;Distance to 2 m isobath;Distance to 10 m isobath;Distance to 20 m isobath;Distance to 100 m isobath;Unlithified-code;Ground-ice;Lithified-code;Ice-code;Man-made structures;Visual observation;ACD_Key_sites;Sampling on land;Arctic Coastal Dynamics (ACD);1982-01-01T00:00:00/2000-12-31T00:00:00;eng;Supplementary Dataset;10.1007/s005310000113;10.2312/BzP_0354_1_2000;18 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);This article presents a comparison of sediment input by rivers and by coastal erosion into both the Laptev Sea and the Canadian Beaufort Sea (CBS). New data on coastal erosion in the Laptev Sea, which are based on field measurements and remote sensing information, and existing data on coastal erosion in the CBS as well as riverine sediment discharge into both the Laptev Sea and the CBS are included. Strong regional differences in the percentages of coastal erosion and riverine sediment supply are observed. The CBS is dominated by the riverine sediment discharge (64.45210**6 t/a) mainly of the Mackenzie River, which is the largest single source of sediments in the Arctic. Riverine sediment discharge into the Laptev Sea amounts to 24.10210**6 t/a, more than 70% of which are related to the Lena River. In comparison with the CBS, the Laptev Sea coast on average delivers approximately twice as much sediment mass per kilometer, a result of higher erosion rates due to higher cliffs and seasonal ice melting. In the Laptev Sea sediment input by coastal erosion (58.4210**6 t/a) is therefore more important than in the CBS and the ratio between riverine and coastal sediment input amounts to 0.4. Coastal erosion supplying 5.6210**6 t/a is less significant for the sediment budget of the CBS where riverine sediment discharge exceeds coastal sediment input by a factor of ca. 10.;71.78612 129.41697",
-    "notes": [
-        "This article presents a comparison of sediment input by rivers and by coastal erosion into both the Laptev Sea and the Canadian Beaufort Sea (CBS). New data on coastal erosion in the Laptev Sea, which are based on field measurements and remote sensing information, and existing data on coastal erosion in the CBS as well as riverine sediment discharge into both the Laptev Sea and the CBS are included. Strong regional differences in the percentages of coastal erosion and riverine sediment supply are observed. The CBS is dominated by the riverine sediment discharge (64.45210**6 t/a) mainly of the Mackenzie River, which is the largest single source of sediments in the Arctic. Riverine sediment discharge into the Laptev Sea amounts to 24.10210**6 t/a, more than 70% of which are related to the Lena River. In comparison with the CBS, the Laptev Sea coast on average delivers approximately twice as much sediment mass per kilometer, a result of higher erosion rates due to higher cliffs and seasonal ice melting. In the Laptev Sea sediment input by coastal erosion (58.4210**6 t/a) is therefore more important than in the CBS and the ratio between riverine and coastal sediment input amounts to 0.4. Coastal erosion supplying 5.6210**6 t/a is less significant for the sediment budget of the CBS where riverine sediment discharge exceeds coastal sediment input by a factor of ca. 10."
-    ],
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.58197"
-    ],
-    "oai_set": [
-        "ACD",
-        "citable",
-        "citableWithChilds",
-        "supplement"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[129.41697,71.78612],[129.41697,71.78612],[129.41697,71.78612],[129.41697,71.78612],[129.41697,71.78612]]]}",
-    "tags": [
-        {
-            "name": "Visual observation"
-        },
-        {
-            "name": "ACD_Key_sites"
-        },
-        {
-            "name": "Sampling land"
-        },
-        {
-            "name": "Arctic Coastal Dynamics ACD"
-        }
-    ],
-    "title": [
-        "Discription of coastal shape at Bykovsky Peninsula, supplement to: Rachold, Volker; Grigoriev, Mikhail N; Are, Felix; Solomon, Steven; Reimnitz, Erk; Kassens, Heidemarie; Antonow, A (2000): Coastal erosion vs. riverine sediment discharge in the Arctic Shelf Seas. International Journal of Earth Sciences, 89(3), 450-460"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/06ffe73c-21ff-5b07-9b30-36f01b0adec3.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/06ffe73c-21ff-5b07-9b30-36f01b0adec3.json
deleted file mode 100644
index 5c564dcc..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/06ffe73c-21ff-5b07-9b30-36f01b0adec3.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.822364",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.822364"
-    ],
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(4 N-8 N,59E-78E)",
-    "TempCoverageBegin": 62933626799,
-    "TempCoverageEnd": 62933626799,
-    "TemporalCoverage": " point in time : 1995-04-16T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1995-04-16T11:59:59Z",
-    "TemporalCoverage:EndDate": "1995-04-16T11:59:59Z",
-    "author": [
-        "GTSPP"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.822364;2017-08-05T09:31:55Z;ASPS;JGOFSCountryUnknown;10.1594/PANGAEA.822364;GTSPP;Physical oceanography during RESEARCHER cruise WT95;PANGAEA - Data Publisher for Earth & Environmental Science;2013;Event label;Date/Time of event;Latitude of event;Longitude of event;DEPTH, water;Pressure, water;Temperature, water;Salinity;Temperature, water, potential;Density, sigma-theta (0);WT95;Researcher;Global Temperature-Salinity Profile Program (GTSPP);Joint Global Ocean Flux Study (JGOFS);1995-04-16T02:51:00/1995-06-18T03:45:00;eng;Dataset;10013/epic.40681.d001;1835 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);4.18 59.33 7.6 78.06",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.822364"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSCountryUnknown"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[59.33,4.18],[59.33,7.6],[78.06,7.6],[78.06,4.18],[59.33,4.18]]]}",
-    "tags": [
-        {
-            "name": "WT"
-        },
-        {
-            "name": "Researcher"
-        },
-        {
-            "name": "Global Temperature-Salinity Profile Program GTSPP"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography during RESEARCHER cruise WT95"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/096aa615-738d-5f65-be64-3138c16d1618.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/096aa615-738d-5f65-be64-3138c16d1618.json
deleted file mode 100644
index 87d72ae7..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/096aa615-738d-5f65-be64-3138c16d1618.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112971",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112971"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(19N,67E)",
-    "TempCoverageBegin": 62916609599,
-    "TempCoverageEnd": 62916609599,
-    "TemporalCoverage": " point in time : 1994-10-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-10-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-10-01T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112971;2017-12-21T11:55:40Z;ASPS;JGOFSUS;10.1594/PANGAEA.112971;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_18-3;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-10-01T23:07:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;52 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);18.999 66.9982",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112971"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[66.9982,18.999],[66.9982,18.999],[66.9982,18.999],[66.9982,18.999],[66.9982,18.999]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_18-3"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/0b272585-e03e-5c4d-8eca-3552df37bad0.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/0b272585-e03e-5c4d-8eca-3552df37bad0.json
deleted file mode 100644
index 773d519c..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/0b272585-e03e-5c4d-8eca-3552df37bad0.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112976",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112976"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(19N,67E)",
-    "TempCoverageBegin": 62916695999,
-    "TempCoverageEnd": 62916695999,
-    "TemporalCoverage": " point in time : 1994-10-02T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-10-02T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-10-02T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112976;2017-12-21T11:55:42Z;ASPS;JGOFSUS;10.1594/PANGAEA.112976;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_18-9;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-10-02T14:57:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;58 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);19.0037 66.995",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112976"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[66.995,19.0037],[66.995,19.0037],[66.995,19.0037],[66.995,19.0037],[66.995,19.0037]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_18-9"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/0ddc8c52-78b1-5a22-8102-3fbd181db098.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/0ddc8c52-78b1-5a22-8102-3fbd181db098.json
deleted file mode 100644
index e22e2e04..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/0ddc8c52-78b1-5a22-8102-3fbd181db098.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112967",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112967"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(16N,68E)",
-    "TempCoverageBegin": 62916523199,
-    "TempCoverageEnd": 62916523199,
-    "TemporalCoverage": " point in time : 1994-09-30T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-09-30T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-09-30T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112967;2017-12-21T11:55:26Z;ASPS;JGOFSUS;10.1594/PANGAEA.112967;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_15-1;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-09-30T16:38:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;239 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);16.4497 68.35",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112967"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[68.35,16.4497],[68.35,16.4497],[68.35,16.4497],[68.35,16.4497],[68.35,16.4497]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_15-1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/0fc8dab8-e28b-53a7-b8e8-8409456b42b5.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/0fc8dab8-e28b-53a7-b8e8-8409456b42b5.json
deleted file mode 100644
index 5f4fcac3..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/0fc8dab8-e28b-53a7-b8e8-8409456b42b5.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112972",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112972"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(19N,67E)",
-    "TempCoverageBegin": 62916695999,
-    "TempCoverageEnd": 62916695999,
-    "TemporalCoverage": " point in time : 1994-10-02T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-10-02T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-10-02T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112972;2017-12-21T11:55:41Z;ASPS;JGOFSUS;10.1594/PANGAEA.112972;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_18-5;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-10-02T03:38:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;52 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);18.9962 67.0035",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112972"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[67.0035,18.9962],[67.0035,18.9962],[67.0035,18.9962],[67.0035,18.9962],[67.0035,18.9962]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_18-5"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/10949c1a-9364-579d-99dc-47cdd37ae7eb.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/10949c1a-9364-579d-99dc-47cdd37ae7eb.json
deleted file mode 100644
index 3bc88169..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/10949c1a-9364-579d-99dc-47cdd37ae7eb.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.826272",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.826272"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(6 N-22N,60E-88E)",
-    "TempCoverageBegin": 62915741999,
-    "TempCoverageEnd": 62915741999,
-    "TemporalCoverage": " point in time : 1994-09-21T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-09-21T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-09-21T11:59:59Z",
-    "author": [
-        "Morrison, John M"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.826272;2017-08-05T09:39:23Z;ASPS;JGOFSUS;10.1594/PANGAEA.826272;Morrison, John M;Physical oceanography during Thomas G. Thompson cruise TT039;PANGAEA - Data Publisher for Earth & Environmental Science;2014;Event label;Date/Time of event;Latitude of event;Longitude of event;DEPTH, water;Pressure, water;Temperature, water;Salinity;Conductivity;Temperature, water, potential;Density, sigma-theta (0);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-09-21T10:32:00/1994-10-06T06:04:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Morrison-tt039.htm;329837 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);5.6776 59.8507 22.4827 87.9673",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.826272"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[59.8507,5.6776],[59.8507,22.4827],[87.9673,22.4827],[87.9673,5.6776],[59.8507,5.6776]]]}",
-    "tags": [
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography during Thomas G. Thompson cruise TT039"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/11c54ac2-3cd8-5757-a4a2-ed6b401c7972.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/11c54ac2-3cd8-5757-a4a2-ed6b401c7972.json
deleted file mode 100644
index 0ce66376..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/11c54ac2-3cd8-5757-a4a2-ed6b401c7972.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112982",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112982"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(22N,62E)",
-    "TempCoverageBegin": 62916868799,
-    "TempCoverageEnd": 62916868799,
-    "TemporalCoverage": " point in time : 1994-10-04T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-10-04T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-10-04T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112982;2017-12-21T11:41:59Z;ASPS;JGOFSUS;10.1594/PANGAEA.112982;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_22-1;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-10-04T18:04:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;220 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);21.8317 62.4037",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112982"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[62.4037,21.8317],[62.4037,21.8317],[62.4037,21.8317],[62.4037,21.8317],[62.4037,21.8317]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_22-1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/14cd187e-e1e7-5ac0-9822-f60841486578.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/14cd187e-e1e7-5ac0-9822-f60841486578.json
deleted file mode 100644
index b3afec86..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/14cd187e-e1e7-5ac0-9822-f60841486578.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112965",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112965"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(15N,67E)",
-    "TempCoverageBegin": 62916436799,
-    "TempCoverageEnd": 62916436799,
-    "TemporalCoverage": " point in time : 1994-09-29T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-09-29T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-09-29T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112965;2017-12-21T11:55:26Z;ASPS;JGOFSUS;10.1594/PANGAEA.112965;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_13-1;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-09-29T19:03:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;240 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);14.9155 66.8825",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112965"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[66.8825,14.9155],[66.8825,14.9155],[66.8825,14.9155],[66.8825,14.9155],[66.8825,14.9155]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_13-1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/18759f64-160e-505c-81fd-85f7ad06c277.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/18759f64-160e-505c-81fd-85f7ad06c277.json
deleted file mode 100644
index ba5049fb..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/18759f64-160e-505c-81fd-85f7ad06c277.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112990",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112990"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(8 N,65E)",
-    "TempCoverageBegin": 62916177599,
-    "TempCoverageEnd": 62916177599,
-    "TemporalCoverage": " point in time : 1994-09-26T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-09-26T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-09-26T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112990;2017-08-04T14:15:04Z;ASPS;JGOFSUS;10.1594/PANGAEA.112990;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_6-1;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-09-26T16:43:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;50 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);8.0 64.997",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112990"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[64.997,8.0],[64.997,8.0],[64.997,8.0],[64.997,8.0],[64.997,8.0]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_6-1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/1941d5d7-163c-59a3-9aeb-82568607bb92.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/1941d5d7-163c-59a3-9aeb-82568607bb92.json
deleted file mode 100644
index a41196ca..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/1941d5d7-163c-59a3-9aeb-82568607bb92.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.822361",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.822361"
-    ],
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(24N-25N,58E-59E)",
-    "TempCoverageBegin": 62964385199,
-    "TempCoverageEnd": 62964385199,
-    "TemporalCoverage": " point in time : 1996-04-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1996-04-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "1996-04-06T11:59:59Z",
-    "author": [
-        "GTSPP"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.822361;2017-08-05T09:31:55Z;ASPS;JGOFSCountryUnknown;10.1594/PANGAEA.822361;GTSPP;Physical oceanography during cruise NV96;PANGAEA - Data Publisher for Earth & Environmental Science;2013;Event label;Date/Time of event;Latitude of event;Longitude of event;DEPTH, water;Pressure, water;Temperature, water;Salinity;Temperature, water, potential;Density, sigma-theta (0);NV96;Global Temperature-Salinity Profile Program (GTSPP);Joint Global Ocean Flux Study (JGOFS);1996-04-06T02:58:00/1996-04-10T06:56:00;eng;Dataset;10013/epic.40681.d001;435 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);24.5 57.5167 24.8667 58.67",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.822361"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSCountryUnknown"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[57.5167,24.5],[57.5167,24.8667],[58.67,24.8667],[58.67,24.5],[57.5167,24.5]]]}",
-    "tags": [
-        {
-            "name": "NV"
-        },
-        {
-            "name": "Global Temperature-Salinity Profile Program GTSPP"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography during cruise NV96"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/1e5dd54a-f86c-51b8-8979-1fc26acf437b.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/1e5dd54a-f86c-51b8-8979-1fc26acf437b.json
deleted file mode 100644
index 587b9ad8..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/1e5dd54a-f86c-51b8-8979-1fc26acf437b.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112970",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112970"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(19N,67E)",
-    "TempCoverageBegin": 62916609599,
-    "TempCoverageEnd": 62916609599,
-    "TemporalCoverage": " point in time : 1994-10-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-10-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-10-01T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112970;2017-12-21T11:55:27Z;ASPS;JGOFSUS;10.1594/PANGAEA.112970;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_18-1;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-10-01T15:36:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;48 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);19.0013 66.9993",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112970"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[66.9993,19.0013],[66.9993,19.0013],[66.9993,19.0013],[66.9993,19.0013],[66.9993,19.0013]]]}",
-    "tags": [
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_18-1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/28d4798e-9601-5663-a43e-389b97a319bb.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/28d4798e-9601-5663-a43e-389b97a319bb.json
deleted file mode 100644
index 01dae0bc..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/28d4798e-9601-5663-a43e-389b97a319bb.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.817140",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.817140"
-    ],
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(8 N-22N,54E-62E)",
-    "author": [
-        "van Bennekom, Johan A",
-        "van der Linden, W J M",
-        "van der Weijden, Cornelis H"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.817140;2017-08-05T09:10:02Z;ASPS;JGOFSNetherlands;10.1594/PANGAEA.817140;van der Weijden, Cornelis H;van der Linden, W J M;van Bennekom, Johan A;Physical oceanography during TYRO cruise NIOP-D3;PANGAEA - Data Publisher for Earth & Environmental Science;2013;Event label;Latitude of event;Longitude of event;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Temperature, water, potential;Density, sigma-theta (0);Fluorescence;Transmission of light;Calculated;Fluorometer, Chelsea Instruments;NIOP-D3;Tyro;Joint Global Ocean Flux Study (JGOFS);Netherlands Indian Ocean Programme (NIOP);eng;Dataset;http://store.pangaea.de/Projects/JGOFS/Netherlands/NIOP-D3_CTD.pdf;165072 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);7.8617 53.655 22.1283 61.795",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.817140"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSNetherlands"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[53.655,7.8617],[53.655,22.1283],[61.795,22.1283],[61.795,7.8617],[53.655,7.8617]]]}",
-    "tags": [
-        {
-            "name": "Calculated"
-        },
-        {
-            "name": "Fluorometer"
-        },
-        {
-            "name": "Chelsea Instruments"
-        },
-        {
-            "name": "NIOP-D"
-        },
-        {
-            "name": "Tyro"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        },
-        {
-            "name": "Netherlands Indian Ocean Programme NIOP"
-        }
-    ],
-    "title": [
-        "Physical oceanography during TYRO cruise NIOP-D3"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/2afc7935-72bf-5c83-8424-9ea743a5e869.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/2afc7935-72bf-5c83-8424-9ea743a5e869.json
deleted file mode 100644
index e32606f0..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/2afc7935-72bf-5c83-8424-9ea743a5e869.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112984",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112984"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(22N,61E)",
-    "TempCoverageBegin": 62916955199,
-    "TempCoverageEnd": 62916955199,
-    "TemporalCoverage": " point in time : 1994-10-05T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-10-05T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-10-05T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112984;2017-12-21T11:42:00Z;ASPS;JGOFSUS;10.1594/PANGAEA.112984;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_23-2;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-10-05T04:52:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;230 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);22.4827 61.1833",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112984"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[61.1833,22.4827],[61.1833,22.4827],[61.1833,22.4827],[61.1833,22.4827],[61.1833,22.4827]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_23-2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/2cf59b57-c6bd-5270-bdb3-cfc951ae4246.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/2cf59b57-c6bd-5270-bdb3-cfc951ae4246.json
deleted file mode 100644
index 9cb409d4..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/2cf59b57-c6bd-5270-bdb3-cfc951ae4246.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112987",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112987"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(22N,61E)",
-    "TempCoverageBegin": 62916955199,
-    "TempCoverageEnd": 62916955199,
-    "TemporalCoverage": " point in time : 1994-10-05T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-10-05T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-10-05T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112987;2017-12-21T11:42:01Z;ASPS;JGOFSUS;10.1594/PANGAEA.112987;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_23-6;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-10-05T17:14:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;51 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);22.4765 61.1905",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112987"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[61.1905,22.4765],[61.1905,22.4765],[61.1905,22.4765],[61.1905,22.4765],[61.1905,22.4765]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_23-6"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/3d08658c-a8dc-5f9b-9c22-ecb0ceeaefa3.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/3d08658c-a8dc-5f9b-9c22-ecb0ceeaefa3.json
deleted file mode 100644
index e86b2d4f..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/3d08658c-a8dc-5f9b-9c22-ecb0ceeaefa3.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.817123",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.817123"
-    ],
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(3 S-24N,37E-54E)",
-    "TempCoverageBegin": 62842215599,
-    "TempCoverageEnd": 62842215599,
-    "TemporalCoverage": " point in time : 1992-05-23T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1992-05-23T11:59:59Z",
-    "TemporalCoverage:EndDate": "1992-05-23T11:59:59Z",
-    "author": [
-        "van der Spoel, Siebrecht",
-        "Baars, Martien A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.817123;2017-08-05T09:10:00Z;ASPS;JGOFSNetherlands;10.1594/PANGAEA.817123;Baars, Martien A;van der Spoel, Siebrecht;Physical oceanography during TYRO cruise NIOP-B0/C0;PANGAEA - Data Publisher for Earth & Environmental Science;2013;Event label;Date/Time of event;Latitude of event;Longitude of event;Elevation of event;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Temperature, water, potential;Density, sigma-theta (0);Fluorescence;Transmission of light;Calculated;Fluorometer, Chelsea Instruments;NIOP-B0/C0;Tyro;Joint Global Ocean Flux Study (JGOFS);Netherlands Indian Ocean Programme (NIOP);1992-05-23T13:51:00/1992-06-11T11:00:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/Netherlands/NIOP-B0C0_CTD.pdf;99248 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);-2.79 36.7667 23.6383 53.5383",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.817123"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSNetherlands"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[36.7667,-2.79],[36.7667,23.6383],[53.5383,23.6383],[53.5383,-2.79],[36.7667,-2.79]]]}",
-    "tags": [
-        {
-            "name": "Calculated"
-        },
-        {
-            "name": "Fluorometer"
-        },
-        {
-            "name": "Chelsea Instruments"
-        },
-        {
-            "name": "NIOP-B C"
-        },
-        {
-            "name": "Tyro"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        },
-        {
-            "name": "Netherlands Indian Ocean Programme NIOP"
-        }
-    ],
-    "title": [
-        "Physical oceanography during TYRO cruise NIOP-B0/C0"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/3f4435c8-c6b5-5628-9e2b-ed86670844f6.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/3f4435c8-c6b5-5628-9e2b-ed86670844f6.json
deleted file mode 100644
index 68f9be9f..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/3f4435c8-c6b5-5628-9e2b-ed86670844f6.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.817135",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.817135"
-    ],
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(1 S-16N,42E-55E)",
-    "TempCoverageBegin": 62830900799,
-    "TempCoverageEnd": 62830900799,
-    "TemporalCoverage": " point in time : 1992-01-13T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1992-01-13T11:59:59Z",
-    "TemporalCoverage:EndDate": "1992-01-13T11:59:59Z",
-    "author": [
-        "van der Spoel, Siebrecht",
-        "Baars, Martien A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.817135;2017-08-05T09:10:01Z;ASPS;JGOFSNetherlands;10.1594/PANGAEA.817135;Baars, Martien A;van der Spoel, Siebrecht;Physical oceanography during TYRO cruise NIOP-B2;PANGAEA - Data Publisher for Earth & Environmental Science;2013;Event label;Date/Time of event;Latitude of event;Longitude of event;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Temperature, water, potential;Density, sigma-theta (0);Fluorescence;Calculated;Fluorometer, Chelsea Instruments;NIOP-B2;Tyro;Joint Global Ocean Flux Study (JGOFS);Netherlands Indian Ocean Programme (NIOP);1992-01-13T00:00:00/1993-02-04T06:47:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/Netherlands/NIOP-B2_CTD.pdf;316792 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);-1.0817 41.5267 16.0233 54.9983",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.817135"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSNetherlands"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[41.5267,-1.0817],[41.5267,16.0233],[54.9983,16.0233],[54.9983,-1.0817],[41.5267,-1.0817]]]}",
-    "tags": [
-        {
-            "name": "Calculated"
-        },
-        {
-            "name": "Fluorometer"
-        },
-        {
-            "name": "Chelsea Instruments"
-        },
-        {
-            "name": "NIOP-B"
-        },
-        {
-            "name": "Tyro"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        },
-        {
-            "name": "Netherlands Indian Ocean Programme NIOP"
-        }
-    ],
-    "title": [
-        "Physical oceanography during TYRO cruise NIOP-B2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/44dec8b8-bf2f-5cae-af42-ec90284fc073.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/44dec8b8-bf2f-5cae-af42-ec90284fc073.json
deleted file mode 100644
index c4f25d4f..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/44dec8b8-bf2f-5cae-af42-ec90284fc073.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.826134",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.826134"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(10N-24N,56E-67E)",
-    "TempCoverageBegin": 62950564799,
-    "TempCoverageEnd": 62950564799,
-    "TemporalCoverage": " point in time : 1995-10-29T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1995-10-29T11:59:59Z",
-    "TemporalCoverage:EndDate": "1995-10-29T11:59:59Z",
-    "author": [
-        "Morrison, John M"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.826134;2017-08-05T09:39:04Z;ASPS;JGOFSUS;10.1594/PANGAEA.826134;Morrison, John M;Physical oceanography during Thomas G. Thompson cruise TT053;PANGAEA - Data Publisher for Earth & Environmental Science;2014;Event label;Date/Time of event;Latitude of event;Longitude of event;DEPTH, water;Pressure, water;Temperature, water;Salinity;Conductivity;Temperature, water, potential;Density, sigma-theta (0);TT053;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1995-10-29T10:00:00/1995-11-25T09:13:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Morrison-tt053.htm;271140 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);10.0823 56.4858 24.3329 67.1784",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.826134"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[56.4858,10.0823],[56.4858,24.3329],[67.1784,24.3329],[67.1784,10.0823],[56.4858,10.0823]]]}",
-    "tags": [
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography during Thomas G. Thompson cruise TT053"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/49f06cb9-a3eb-5e54-9e5b-7ec327b4577d.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/49f06cb9-a3eb-5e54-9e5b-7ec327b4577d.json
deleted file mode 100644
index 5d992ade..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/49f06cb9-a3eb-5e54-9e5b-7ec327b4577d.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112980",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112980"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(21N,64E)",
-    "TempCoverageBegin": 62916782399,
-    "TempCoverageEnd": 62916782399,
-    "TemporalCoverage": " point in time : 1994-10-03T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-10-03T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-10-03T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112980;2017-12-21T11:41:59Z;ASPS;JGOFSUS;10.1594/PANGAEA.112980;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_21-2;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-10-03T22:33:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;77 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);21.1758 63.5492",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112980"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[63.5492,21.1758],[63.5492,21.1758],[63.5492,21.1758],[63.5492,21.1758],[63.5492,21.1758]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_21-2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/4afe020c-4e05-5317-b442-dda1386f4345.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/4afe020c-4e05-5317-b442-dda1386f4345.json
deleted file mode 100644
index 854c9aee..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/4afe020c-4e05-5317-b442-dda1386f4345.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112989",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112989"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(8 N,68E)",
-    "TempCoverageBegin": 62916177599,
-    "TempCoverageEnd": 62916177599,
-    "TemporalCoverage": " point in time : 1994-09-26T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-09-26T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-09-26T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112989;2017-12-21T11:42:20Z;ASPS;JGOFSUS;10.1594/PANGAEA.112989;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_5-1;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-09-26T01:27:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;90 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);7.7481 68.0538",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112989"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[68.0538,7.7481],[68.0538,7.7481],[68.0538,7.7481],[68.0538,7.7481],[68.0538,7.7481]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_5-1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/4b6fb671-a54e-5bba-adc7-78757e87045d.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/4b6fb671-a54e-5bba-adc7-78757e87045d.json
deleted file mode 100644
index 9507086b..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/4b6fb671-a54e-5bba-adc7-78757e87045d.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112961",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112961"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(6 N,88E)",
-    "TempCoverageBegin": 62915741999,
-    "TempCoverageEnd": 62915741999,
-    "TemporalCoverage": " point in time : 1994-09-21T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-09-21T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-09-21T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112961;2017-12-21T11:55:11Z;ASPS;JGOFSUS;10.1594/PANGAEA.112961;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_1-1;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-09-21T10:32:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;240 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);5.6776 87.9673",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112961"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[87.9673,5.6776],[87.9673,5.6776],[87.9673,5.6776],[87.9673,5.6776],[87.9673,5.6776]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_1-1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/4dfec559-690b-5c6f-a78d-742b4f15b3e8.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/4dfec559-690b-5c6f-a78d-742b4f15b3e8.json
deleted file mode 100644
index de25906c..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/4dfec559-690b-5c6f-a78d-742b4f15b3e8.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112992",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112992"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(8 N,65E)",
-    "TempCoverageBegin": 62916177599,
-    "TempCoverageEnd": 62916177599,
-    "TemporalCoverage": " point in time : 1994-09-26T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-09-26T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-09-26T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112992;2017-12-21T11:42:21Z;ASPS;JGOFSUS;10.1594/PANGAEA.112992;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_6-3;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-09-26T20:43:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;82 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);7.9988 64.9948",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112992"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[64.9948,7.9988],[64.9948,7.9988],[64.9948,7.9988],[64.9948,7.9988],[64.9948,7.9988]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_6-3"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/4eff6d93-ab60-5ab5-bd75-a5bd3204f3f3.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/4eff6d93-ab60-5ab5-bd75-a5bd3204f3f3.json
deleted file mode 100644
index 694811cf..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/4eff6d93-ab60-5ab5-bd75-a5bd3204f3f3.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112979",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112979"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(21N,64E)",
-    "TempCoverageBegin": 62916782399,
-    "TempCoverageEnd": 62916782399,
-    "TemporalCoverage": " point in time : 1994-10-03T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-10-03T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-10-03T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112979;2017-12-21T11:41:59Z;ASPS;JGOFSUS;10.1594/PANGAEA.112979;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_21-1;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-10-03T19:52:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;239 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);21.1825 63.55",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112979"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[63.55,21.1825],[63.55,21.1825],[63.55,21.1825],[63.55,21.1825],[63.55,21.1825]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_21-1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/5237c7cf-742c-5ca8-b3a1-b31d44eecca0.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/5237c7cf-742c-5ca8-b3a1-b31d44eecca0.json
deleted file mode 100644
index 73c7b40a..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/5237c7cf-742c-5ca8-b3a1-b31d44eecca0.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112994",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112994"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(9 N,65E)",
-    "TempCoverageBegin": 62916263999,
-    "TempCoverageEnd": 62916263999,
-    "TemporalCoverage": " point in time : 1994-09-27T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-09-27T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-09-27T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112994;2017-12-21T11:42:21Z;ASPS;JGOFSUS;10.1594/PANGAEA.112994;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_7-1;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-09-27T06:43:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;232 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);9.0 65.0003",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112994"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[65.0003,9.0],[65.0003,9.0],[65.0003,9.0],[65.0003,9.0],[65.0003,9.0]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_7-1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/527d1115-9de5-5a20-b56c-d935359c4242.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/527d1115-9de5-5a20-b56c-d935359c4242.json
deleted file mode 100644
index 0c7cf2fd..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/527d1115-9de5-5a20-b56c-d935359c4242.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112993",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112993"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(8 N,65E)",
-    "TempCoverageBegin": 62916263999,
-    "TempCoverageEnd": 62916263999,
-    "TemporalCoverage": " point in time : 1994-09-27T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-09-27T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-09-27T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112993;2017-12-21T11:42:21Z;ASPS;JGOFSUS;10.1594/PANGAEA.112993;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_6-4;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-09-27T01:15:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;52 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);8.116 64.973",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112993"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[64.973,8.116],[64.973,8.116],[64.973,8.116],[64.973,8.116],[64.973,8.116]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_6-4"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/5352b699-85d7-5c98-a807-c16403401a52.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/5352b699-85d7-5c98-a807-c16403401a52.json
deleted file mode 100644
index ab7640ee..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/5352b699-85d7-5c98-a807-c16403401a52.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.826997",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.826997"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(10N-22N,57E-69E)",
-    "TempCoverageBegin": 62930779199,
-    "TempCoverageEnd": 62930779199,
-    "TemporalCoverage": " point in time : 1995-03-14T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1995-03-14T11:59:59Z",
-    "TemporalCoverage:EndDate": "1995-03-14T11:59:59Z",
-    "author": [
-        "Gardner, Wilford",
-        "Morrison, John M"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.826997;2017-08-05T09:40:09Z;ASPS;JGOFSUS;10.1594/PANGAEA.826997;Morrison, John M;Gardner, Wilford;Physical oceanography during Thomas G. Thompson cruise TT045;PANGAEA - Data Publisher for Earth & Environmental Science;2014;Event label;Date/Time of event;Latitude of event;Longitude of event;DEPTH, water;Pressure, water;Temperature, water;Salinity;Conductivity;Temperature, water, potential;Density, sigma-theta (0);Optical beam attenuation coefficient, particle in water column;Fluorescence, chlorophyll;PAR lightmeter voltage from downward irradiance;TT045;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1995-03-14T22:14:00/1995-04-08T07:03:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Morrison-tt045.htm;435660 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);9.9993 57.3007 22.4858 68.7532",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.826997"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[57.3007,9.9993],[57.3007,22.4858],[68.7532,22.4858],[68.7532,9.9993],[57.3007,9.9993]]]}",
-    "tags": [
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography during Thomas G. Thompson cruise TT045"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/5b8affdf-e9a6-52a8-89cd-7eed8c97dae3.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/5b8affdf-e9a6-52a8-89cd-7eed8c97dae3.json
deleted file mode 100644
index ed8642cc..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/5b8affdf-e9a6-52a8-89cd-7eed8c97dae3.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112986",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112986"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(22N,61E)",
-    "TempCoverageBegin": 62916955199,
-    "TempCoverageEnd": 62916955199,
-    "TemporalCoverage": " point in time : 1994-10-05T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-10-05T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-10-05T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112986;2017-12-21T11:42:00Z;ASPS;JGOFSUS;10.1594/PANGAEA.112986;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_23-4;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-10-05T13:43:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;64 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);22.4812 61.1833",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112986"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[61.1833,22.4812],[61.1833,22.4812],[61.1833,22.4812],[61.1833,22.4812],[61.1833,22.4812]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_23-4"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/678c9af1-1828-5121-8ca6-38129710128c.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/678c9af1-1828-5121-8ca6-38129710128c.json
deleted file mode 100644
index 6f4065ea..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/678c9af1-1828-5121-8ca6-38129710128c.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112997",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112997"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(11N,65E)",
-    "TempCoverageBegin": 62916350399,
-    "TempCoverageEnd": 62916350399,
-    "TemporalCoverage": " point in time : 1994-09-28T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-09-28T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-09-28T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112997;2017-12-21T11:42:39Z;ASPS;JGOFSUS;10.1594/PANGAEA.112997;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_9-1;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-09-28T00:24:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;240 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);10.8162 64.9977",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112997"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[64.9977,10.8162],[64.9977,10.8162],[64.9977,10.8162],[64.9977,10.8162],[64.9977,10.8162]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_9-1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/6d690bf1-f135-57b1-b3a3-a0a6bee19fc2.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/6d690bf1-f135-57b1-b3a3-a0a6bee19fc2.json
deleted file mode 100644
index 3147fe07..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/6d690bf1-f135-57b1-b3a3-a0a6bee19fc2.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112969",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112969"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(18N,68E)",
-    "TempCoverageBegin": 62916609599,
-    "TempCoverageEnd": 62916609599,
-    "TemporalCoverage": " point in time : 1994-10-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-10-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-10-01T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112969;2017-12-21T11:55:27Z;ASPS;JGOFSUS;10.1594/PANGAEA.112969;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_17-1;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-10-01T09:08:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;240 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);18.2658 67.5665",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112969"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[67.5665,18.2658],[67.5665,18.2658],[67.5665,18.2658],[67.5665,18.2658],[67.5665,18.2658]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_17-1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/7198bdf3-ff85-50fd-9e56-b631b9b0876d.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/7198bdf3-ff85-50fd-9e56-b631b9b0876d.json
deleted file mode 100644
index 7a6952de..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/7198bdf3-ff85-50fd-9e56-b631b9b0876d.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.817137",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.817137"
-    ],
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(11N-16N,49E-54E)",
-    "TempCoverageBegin": 62865028799,
-    "TempCoverageEnd": 62865028799,
-    "TemporalCoverage": " point in time : 1993-02-11T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1993-02-11T11:59:59Z",
-    "TemporalCoverage:EndDate": "1993-02-11T11:59:59Z",
-    "author": [
-        "van Bennekom, Johan A",
-        "van Weering, Tjeerd C E"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.817137;2017-08-05T09:10:01Z;ASPS;JGOFSNetherlands;10.1594/PANGAEA.817137;van Weering, Tjeerd C E;van Bennekom, Johan A;Physical oceanography during TYRO cruise NIOP-C2;PANGAEA - Data Publisher for Earth & Environmental Science;2013;Event label;Date/Time of event;Latitude of event;Longitude of event;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Temperature, water, potential;Density, sigma-theta (0);Fluorescence;Transmission of light;Calculated;Fluorometer, Chelsea Instruments;NIOP-C2;Tyro;Joint Global Ocean Flux Study (JGOFS);Netherlands Indian Ocean Programme (NIOP);1993-02-11T00:00:00/1993-03-03T00:00:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/Netherlands/NIOP-C2_CTD.pdf;324823 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);10.685 49.1583 16.18 54.13",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.817137"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSNetherlands"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[49.1583,10.685],[49.1583,16.18],[54.13,16.18],[54.13,10.685],[49.1583,10.685]]]}",
-    "tags": [
-        {
-            "name": "Calculated"
-        },
-        {
-            "name": "Fluorometer"
-        },
-        {
-            "name": "Chelsea Instruments"
-        },
-        {
-            "name": "NIOP-C"
-        },
-        {
-            "name": "Tyro"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        },
-        {
-            "name": "Netherlands Indian Ocean Programme NIOP"
-        }
-    ],
-    "title": [
-        "Physical oceanography during TYRO cruise NIOP-C2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/7ba597d3-3527-56bc-8f6f-63a79ab8acc7.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/7ba597d3-3527-56bc-8f6f-63a79ab8acc7.json
deleted file mode 100644
index e7542f54..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/7ba597d3-3527-56bc-8f6f-63a79ab8acc7.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.826025",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.826025"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(10N-23N,57E-69E)",
-    "TempCoverageBegin": 62953329599,
-    "TempCoverageEnd": 62953329599,
-    "TemporalCoverage": " point in time : 1995-11-30T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1995-11-30T11:59:59Z",
-    "TemporalCoverage:EndDate": "1995-11-30T11:59:59Z",
-    "author": [
-        "Gardner, Wilford",
-        "Morrison, John M"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.826025;2017-08-05T09:38:50Z;ASPS;JGOFSUS;10.1594/PANGAEA.826025;Morrison, John M;Gardner, Wilford;Physical oceanography during Thomas G. Thompson cruise TT054;PANGAEA - Data Publisher for Earth & Environmental Science;2014;Event label;Date/Time of event;Latitude of event;Longitude of event;DEPTH, water;Pressure, water;Temperature, water;Salinity;Conductivity;Temperature, water, potential;Density, sigma-theta (0);Optical beam attenuation coefficient, particle in water column;PAR lightmeter voltage from downward irradiance;Fluorescence, chlorophyll;TT054;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1995-11-30T14:18:00/1995-12-26T13:55:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Morrison-tt054.htm;591945 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);9.9673 57.2992 22.5171 68.7849",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.826025"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[57.2992,9.9673],[57.2992,22.5171],[68.7849,22.5171],[68.7849,9.9673],[57.2992,9.9673]]]}",
-    "tags": [
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography during Thomas G. Thompson cruise TT054"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/7c77f1d9-761e-507f-bff1-1365ff658d10.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/7c77f1d9-761e-507f-bff1-1365ff658d10.json
deleted file mode 100644
index 069ba5a8..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/7c77f1d9-761e-507f-bff1-1365ff658d10.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.826369",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.826369"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(10N-22N,57E-69E)",
-    "TempCoverageBegin": 62944340399,
-    "TempCoverageEnd": 62944340399,
-    "TemporalCoverage": " point in time : 1995-08-18T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1995-08-18T11:59:59Z",
-    "TemporalCoverage:EndDate": "1995-08-18T11:59:59Z",
-    "author": [
-        "Gardner, Wilford",
-        "Morrison, John M"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.826369;2017-08-05T09:39:38Z;ASPS;JGOFSUS;10.1594/PANGAEA.826369;Morrison, John M;Gardner, Wilford;Physical oceanography during Thomas G. Thompson cruise TT050;PANGAEA - Data Publisher for Earth & Environmental Science;2014;Event label;Latitude of event;Longitude of event;DEPTH, water;Pressure, water;Temperature, water;Salinity;Conductivity;Temperature, water, potential;Density, sigma-theta (0);Optical beam attenuation coefficient, particle in water column;PAR lightmeter voltage from downward irradiance;Fluorescence, chlorophyll;TT050;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1995-08-18T14:20:00/1995-09-13T17:22:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Morrison-tt050.htm;437711 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);9.9125 57.3004 22.4998 68.7527",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.826369"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[57.3004,9.9125],[57.3004,22.4998],[68.7527,22.4998],[68.7527,9.9125],[57.3004,9.9125]]]}",
-    "tags": [
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography during Thomas G. Thompson cruise TT050"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/7d6d5c67-0cf4-512e-b31d-62116d590541.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/7d6d5c67-0cf4-512e-b31d-62116d590541.json
deleted file mode 100644
index 19a23c22..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/7d6d5c67-0cf4-512e-b31d-62116d590541.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.822360",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.822360"
-    ],
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(1 N-14N,52E-62E)",
-    "TempCoverageBegin": 62775860399,
-    "TempCoverageEnd": 62775860399,
-    "TemporalCoverage": " point in time : 1990-04-16T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1990-04-16T11:59:59Z",
-    "TemporalCoverage:EndDate": "1990-04-16T11:59:59Z",
-    "author": [
-        "GTSPP"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.822360;2017-08-05T09:31:55Z;ASPS;JGOFSCountryUnknown;10.1594/PANGAEA.822360;GTSPP;Physical oceanography during PRIBOY cruise ER90;PANGAEA - Data Publisher for Earth & Environmental Science;2013;Event label;Date/Time of event;Latitude of event;Longitude of event;DEPTH, water;Pressure, water;Temperature, water;Salinity;Temperature, water, potential;Density, sigma-theta (0);ER90;Priboy;Global Temperature-Salinity Profile Program (GTSPP);Joint Global Ocean Flux Study (JGOFS);1990-04-16T12:20:00/1990-05-10T02:09:00;eng;Dataset;10013/epic.40681.d001;715 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);1.2 51.9667 13.7167 62.2667",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.822360"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSCountryUnknown"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[51.9667,1.2],[51.9667,13.7167],[62.2667,13.7167],[62.2667,1.2],[51.9667,1.2]]]}",
-    "tags": [
-        {
-            "name": "ER"
-        },
-        {
-            "name": "Priboy"
-        },
-        {
-            "name": "Global Temperature-Salinity Profile Program GTSPP"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography during PRIBOY cruise ER90"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/7dbc7a7f-7ad2-5003-864f-d77204b79233.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/7dbc7a7f-7ad2-5003-864f-d77204b79233.json
deleted file mode 100644
index 883adc42..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/7dbc7a7f-7ad2-5003-864f-d77204b79233.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112975",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112975"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(19N,67E)",
-    "TempCoverageBegin": 62916695999,
-    "TempCoverageEnd": 62916695999,
-    "TemporalCoverage": " point in time : 1994-10-02T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-10-02T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-10-02T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112975;2017-12-21T11:55:42Z;ASPS;JGOFSUS;10.1594/PANGAEA.112975;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_18-8;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-10-02T13:38:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;119 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);19.0023 66.9968",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112975"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[66.9968,19.0023],[66.9968,19.0023],[66.9968,19.0023],[66.9968,19.0023],[66.9968,19.0023]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_18-8"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/82b31312-4ac9-54dc-8cf1-5e3069b6a2f5.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/82b31312-4ac9-54dc-8cf1-5e3069b6a2f5.json
deleted file mode 100644
index 821079dc..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/82b31312-4ac9-54dc-8cf1-5e3069b6a2f5.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112996",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112996"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(10N,65E)",
-    "TempCoverageBegin": 62916263999,
-    "TempCoverageEnd": 62916263999,
-    "TemporalCoverage": " point in time : 1994-09-27T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-09-27T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-09-27T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112996;2017-12-21T11:42:22Z;ASPS;JGOFSUS;10.1594/PANGAEA.112996;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_8-4;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-09-27T20:31:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;50 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);10.12 65.048",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112996"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[65.048,10.12],[65.048,10.12],[65.048,10.12],[65.048,10.12],[65.048,10.12]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_8-4"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/87e7f46f-9597-5b6b-8041-45024c995f2b.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/87e7f46f-9597-5b6b-8041-45024c995f2b.json
deleted file mode 100644
index cdd7f4af..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/87e7f46f-9597-5b6b-8041-45024c995f2b.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.817136",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.817136"
-    ],
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(0 S-16N,46E-54E)",
-    "TempCoverageBegin": 62849300399,
-    "TempCoverageEnd": 62849300399,
-    "TemporalCoverage": " point in time : 1992-08-13T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1992-08-13T11:59:59Z",
-    "TemporalCoverage:EndDate": "1992-08-13T11:59:59Z",
-    "author": [
-        "van Bennekom, Johan A",
-        "van Weering, Tjeerd C E"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.817136;2017-08-05T09:10:01Z;ASPS;JGOFSNetherlands;10.1594/PANGAEA.817136;van Weering, Tjeerd C E;van Bennekom, Johan A;Physical oceanography during TYRO cruise NIOP-C1;PANGAEA - Data Publisher for Earth & Environmental Science;2013;Event label;Date/Time of event;Latitude of event;Longitude of event;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Temperature, water, potential;Density, sigma-theta (0);Fluorescence;Transmission of light;Calculated;Fluorometer, Chelsea Instruments;NIOP-C1;Tyro;Joint Global Ocean Flux Study (JGOFS);Netherlands Indian Ocean Programme (NIOP);1992-08-13T00:00:00/1992-09-02T00:00:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/Netherlands/NIOP-C1_CTD.pdf;271088 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);-0.3817 46.2717 16.1867 54.5",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.817136"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSNetherlands"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[46.2717,-0.3817],[46.2717,16.1867],[54.5,16.1867],[54.5,-0.3817],[46.2717,-0.3817]]]}",
-    "tags": [
-        {
-            "name": "Calculated"
-        },
-        {
-            "name": "Fluorometer"
-        },
-        {
-            "name": "Chelsea Instruments"
-        },
-        {
-            "name": "NIOP-C"
-        },
-        {
-            "name": "Tyro"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        },
-        {
-            "name": "Netherlands Indian Ocean Programme NIOP"
-        }
-    ],
-    "title": [
-        "Physical oceanography during TYRO cruise NIOP-C1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/899d1207-7760-5ea1-89b6-5a9d090b4207.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/899d1207-7760-5ea1-89b6-5a9d090b4207.json
deleted file mode 100644
index 448e2117..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/899d1207-7760-5ea1-89b6-5a9d090b4207.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112968",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112968"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(17N,68E)",
-    "TempCoverageBegin": 62916523199,
-    "TempCoverageEnd": 62916523199,
-    "TemporalCoverage": " point in time : 1994-09-30T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-09-30T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-09-30T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112968;2017-12-21T11:55:26Z;ASPS;JGOFSUS;10.1594/PANGAEA.112968;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_16-1;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-09-30T23:11:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;240 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);17.3002 67.9313",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112968"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[67.9313,17.3002],[67.9313,17.3002],[67.9313,17.3002],[67.9313,17.3002],[67.9313,17.3002]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_16-1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/8c78beaf-83bd-5c67-9037-fb086b65a16e.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/8c78beaf-83bd-5c67-9037-fb086b65a16e.json
deleted file mode 100644
index 39ffe4bf..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/8c78beaf-83bd-5c67-9037-fb086b65a16e.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112988",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112988"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(22N,60E)",
-    "TempCoverageBegin": 62917041599,
-    "TempCoverageEnd": 62917041599,
-    "TemporalCoverage": " point in time : 1994-10-06T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-10-06T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-10-06T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112988;2017-12-21T11:42:20Z;ASPS;JGOFSUS;10.1594/PANGAEA.112988;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_24-1;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-10-06T06:04:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;120 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);22.0998 59.8507",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112988"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[59.8507,22.0998],[59.8507,22.0998],[59.8507,22.0998],[59.8507,22.0998],[59.8507,22.0998]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_24-1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/94721d29-b054-5ea7-aaab-3874c0cb5577.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/94721d29-b054-5ea7-aaab-3874c0cb5577.json
deleted file mode 100644
index da213b70..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/94721d29-b054-5ea7-aaab-3874c0cb5577.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112963",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112963"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(13N,65E)",
-    "TempCoverageBegin": 62916350399,
-    "TempCoverageEnd": 62916350399,
-    "TemporalCoverage": " point in time : 1994-09-28T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-09-28T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-09-28T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112963;2017-12-21T11:55:25Z;ASPS;JGOFSUS;10.1594/PANGAEA.112963;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_11-1;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-09-28T18:57:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;239 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);13.2502 64.9998",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112963"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[64.9998,13.2502],[64.9998,13.2502],[64.9998,13.2502],[64.9998,13.2502],[64.9998,13.2502]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_11-1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/9f5e4a05-71c7-57c5-84b1-a0c1dabe210e.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/9f5e4a05-71c7-57c5-84b1-a0c1dabe210e.json
deleted file mode 100644
index 961bf018..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/9f5e4a05-71c7-57c5-84b1-a0c1dabe210e.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112977",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112977"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(20N,66E)",
-    "TempCoverageBegin": 62916695999,
-    "TempCoverageEnd": 62916695999,
-    "TemporalCoverage": " point in time : 1994-10-02T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-10-02T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-10-02T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112977;2017-12-21T11:55:42Z;ASPS;JGOFSUS;10.1594/PANGAEA.112977;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_19-1;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-10-02T23:36:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;240 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);19.89 65.875",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112977"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[65.875,19.89],[65.875,19.89],[65.875,19.89],[65.875,19.89],[65.875,19.89]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_19-1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/a18787a2-08ec-5e88-8f2c-c6da2d65d2cd.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/a18787a2-08ec-5e88-8f2c-c6da2d65d2cd.json
deleted file mode 100644
index f16624f3..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/a18787a2-08ec-5e88-8f2c-c6da2d65d2cd.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112978",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112978"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(21N,65E)",
-    "TempCoverageBegin": 62916782399,
-    "TempCoverageEnd": 62916782399,
-    "TemporalCoverage": " point in time : 1994-10-03T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-10-03T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-10-03T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112978;2017-12-21T11:55:42Z;ASPS;JGOFSUS;10.1594/PANGAEA.112978;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_20-1;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-10-03T09:37:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;240 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);20.5563 64.676",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112978"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[64.676,20.5563],[64.676,20.5563],[64.676,20.5563],[64.676,20.5563],[64.676,20.5563]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_20-1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/a7cacdbe-4b5d-5324-9f87-e9c518e8e1ed.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/a7cacdbe-4b5d-5324-9f87-e9c518e8e1ed.json
deleted file mode 100644
index 0727cecd..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/a7cacdbe-4b5d-5324-9f87-e9c518e8e1ed.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112962",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112962"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(12N,65E)",
-    "TempCoverageBegin": 62916350399,
-    "TempCoverageEnd": 62916350399,
-    "TemporalCoverage": " point in time : 1994-09-28T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-09-28T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-09-28T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112962;2017-12-21T11:55:25Z;ASPS;JGOFSUS;10.1594/PANGAEA.112962;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_10-1;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-09-28T08:15:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;229 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);12.0678 65.0",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112962"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[65.0,12.0678],[65.0,12.0678],[65.0,12.0678],[65.0,12.0678],[65.0,12.0678]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_10-1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/b0113118-b7e4-5586-878f-a6bcb08904ab.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/b0113118-b7e4-5586-878f-a6bcb08904ab.json
deleted file mode 100644
index 22282aa5..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/b0113118-b7e4-5586-878f-a6bcb08904ab.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.817139",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.817139"
-    ],
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(22N-25N,62E-65E)",
-    "author": [
-        "van Bennekom, Johan A",
-        "van der Linden, W J M",
-        "van der Weijden, Cornelis H"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.817139;2017-08-05T09:10:02Z;ASPS;JGOFSNetherlands;10.1594/PANGAEA.817139;van der Weijden, Cornelis H;van der Linden, W J M;van Bennekom, Johan A;Physical oceanography during TYRO cruise NIOP-D2;PANGAEA - Data Publisher for Earth & Environmental Science;2013;Event label;Latitude of event;Longitude of event;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Temperature, water, potential;Density, sigma-theta (0);Fluorescence;Transmission of light;Calculated;Fluorometer, Chelsea Instruments;NIOP-D2;Tyro;Joint Global Ocean Flux Study (JGOFS);Netherlands Indian Ocean Programme (NIOP);eng;Dataset;http://store.pangaea.de/Projects/JGOFS/Netherlands/NIOP-D2_CTD.pdf;172832 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);21.7067 62.3483 24.8567 65.0033",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.817139"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSNetherlands"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[62.3483,21.7067],[62.3483,24.8567],[65.0033,24.8567],[65.0033,21.7067],[62.3483,21.7067]]]}",
-    "tags": [
-        {
-            "name": "Calculated"
-        },
-        {
-            "name": "Fluorometer"
-        },
-        {
-            "name": "Chelsea Instruments"
-        },
-        {
-            "name": "NIOP-D"
-        },
-        {
-            "name": "Tyro"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        },
-        {
-            "name": "Netherlands Indian Ocean Programme NIOP"
-        }
-    ],
-    "title": [
-        "Physical oceanography during TYRO cruise NIOP-D2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/b2d6d1bf-5da0-559c-921a-936e0476edee.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/b2d6d1bf-5da0-559c-921a-936e0476edee.json
deleted file mode 100644
index 7134cdd4..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/b2d6d1bf-5da0-559c-921a-936e0476edee.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112973",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112973"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(19N,67E)",
-    "TempCoverageBegin": 62916695999,
-    "TempCoverageEnd": 62916695999,
-    "TemporalCoverage": " point in time : 1994-10-02T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-10-02T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-10-02T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112973;2017-12-21T11:55:41Z;ASPS;JGOFSUS;10.1594/PANGAEA.112973;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_18-6;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-10-02T08:19:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;61 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);18.9997 66.9988",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112973"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[66.9988,18.9997],[66.9988,18.9997],[66.9988,18.9997],[66.9988,18.9997],[66.9988,18.9997]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_18-6"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/b637f6cd-2ebd-5758-8624-99e1060cd581.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/b637f6cd-2ebd-5758-8624-99e1060cd581.json
deleted file mode 100644
index 83ff9f14..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/b637f6cd-2ebd-5758-8624-99e1060cd581.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.822363",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.822363"
-    ],
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(1 N-17N,60E-67E)",
-    "TempCoverageBegin": 62769211199,
-    "TempCoverageEnd": 62769211199,
-    "TemporalCoverage": " point in time : 1990-01-29T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1990-01-29T11:59:59Z",
-    "TemporalCoverage:EndDate": "1990-01-29T11:59:59Z",
-    "author": [
-        "GTSPP"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.822363;2017-08-05T09:31:55Z;ASPS;JGOFSCountryUnknown;10.1594/PANGAEA.822363;GTSPP;Physical oceanography during Akademik Shirshov cruise UM90;PANGAEA - Data Publisher for Earth & Environmental Science;2013;Event label;Date/Time of event;Latitude of event;Longitude of event;DEPTH, water;Pressure, water;Temperature, water;Salinity;Temperature, water, potential;Density, sigma-theta (0);UM90;Akademik Shirshov;Global Temperature-Salinity Profile Program (GTSPP);Joint Global Ocean Flux Study (JGOFS);1990-01-29T00:01:00/1990-02-20T00:12:00;eng;Dataset;10013/epic.40681.d001;2910 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);0.85 60.0 17.05 67.0",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.822363"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSCountryUnknown"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[60.0,0.85],[60.0,17.05],[67.0,17.05],[67.0,0.85],[60.0,0.85]]]}",
-    "tags": [
-        {
-            "name": "UM"
-        },
-        {
-            "name": "Akademik Shirshov"
-        },
-        {
-            "name": "Global Temperature-Salinity Profile Program GTSPP"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography during Akademik Shirshov cruise UM90"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/ba387cc6-a33d-5527-b44e-f76b8e542085.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/ba387cc6-a33d-5527-b44e-f76b8e542085.json
deleted file mode 100644
index 980065cb..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/ba387cc6-a33d-5527-b44e-f76b8e542085.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112991",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112991"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(8 N,65E)",
-    "TempCoverageBegin": 62916177599,
-    "TempCoverageEnd": 62916177599,
-    "TemporalCoverage": " point in time : 1994-09-26T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-09-26T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-09-26T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112991;2017-12-21T11:42:20Z;ASPS;JGOFSUS;10.1594/PANGAEA.112991;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_6-2;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-09-26T20:13:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;240 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);8.0 64.995",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112991"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[64.995,8.0],[64.995,8.0],[64.995,8.0],[64.995,8.0],[64.995,8.0]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_6-2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/baa9db3e-9fe0-5edc-a9e5-5ecb5e054c2c.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/baa9db3e-9fe0-5edc-a9e5-5ecb5e054c2c.json
deleted file mode 100644
index a6812b64..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/baa9db3e-9fe0-5edc-a9e5-5ecb5e054c2c.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112964",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112964"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(14N,65E)",
-    "TempCoverageBegin": 62916436799,
-    "TempCoverageEnd": 62916436799,
-    "TemporalCoverage": " point in time : 1994-09-29T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-09-29T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-09-29T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112964;2017-12-21T11:55:26Z;ASPS;JGOFSUS;10.1594/PANGAEA.112964;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_12-1;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-09-29T02:38:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;240 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);14.4482 65.0012",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112964"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[65.0012,14.4482],[65.0012,14.4482],[65.0012,14.4482],[65.0012,14.4482],[65.0012,14.4482]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_12-1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/cc4b514e-f137-5510-9c80-d20b9df47968.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/cc4b514e-f137-5510-9c80-d20b9df47968.json
deleted file mode 100644
index 41dbc7e9..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/cc4b514e-f137-5510-9c80-d20b9df47968.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.817124",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.817124"
-    ],
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(2 S-13N,43E-56E)",
-    "TempCoverageBegin": 62846708399,
-    "TempCoverageEnd": 62846708399,
-    "TemporalCoverage": " point in time : 1992-07-14T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1992-07-14T11:59:59Z",
-    "TemporalCoverage:EndDate": "1992-07-14T11:59:59Z",
-    "author": [
-        "van der Spoel, Siebrecht",
-        "Baars, Martien A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.817124;2017-08-05T09:10:01Z;ASPS;JGOFSNetherlands;10.1594/PANGAEA.817124;Baars, Martien A;van der Spoel, Siebrecht;Physical oceanography during TYRO cruise NIOP-B1;PANGAEA - Data Publisher for Earth & Environmental Science;2013;Event label;Date/Time of event;Latitude of event;Longitude of event;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Temperature, water, potential;Density, sigma-theta (0);Fluorescence;Transmission of light;Calculated;Fluorometer, Chelsea Instruments;NIOP-B1;Tyro;Joint Global Ocean Flux Study (JGOFS);Netherlands Indian Ocean Programme (NIOP);1992-07-14T13:10:00/1992-08-07T19:46:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/Netherlands/NIOP-B1_CTD.pdf;264997 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);-2.305 42.8983 13.36 56.3233",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.817124"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSNetherlands"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[42.8983,-2.305],[42.8983,13.36],[56.3233,13.36],[56.3233,-2.305],[42.8983,-2.305]]]}",
-    "tags": [
-        {
-            "name": "Calculated"
-        },
-        {
-            "name": "Fluorometer"
-        },
-        {
-            "name": "Chelsea Instruments"
-        },
-        {
-            "name": "NIOP-B"
-        },
-        {
-            "name": "Tyro"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        },
-        {
-            "name": "Netherlands Indian Ocean Programme NIOP"
-        }
-    ],
-    "title": [
-        "Physical oceanography during TYRO cruise NIOP-B1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/cf91e41e-e96f-594d-ba98-489724b61378.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/cf91e41e-e96f-594d-ba98-489724b61378.json
deleted file mode 100644
index 440a57a2..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/cf91e41e-e96f-594d-ba98-489724b61378.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.826996",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.826996"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(10N-22N,57E-69E)",
-    "TempCoverageBegin": 62925163199,
-    "TempCoverageEnd": 62925163199,
-    "TemporalCoverage": " point in time : 1995-01-08T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1995-01-08T11:59:59Z",
-    "TemporalCoverage:EndDate": "1995-01-08T11:59:59Z",
-    "author": [
-        "Gardner, Wilford",
-        "Morrison, John M"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.826996;2017-08-05T09:40:09Z;ASPS;JGOFSUS;10.1594/PANGAEA.826996;Morrison, John M;Gardner, Wilford;Physical oceanography during Thomas G. Thompson cruise TT043;PANGAEA - Data Publisher for Earth & Environmental Science;2014;Event label;Date/Time of event;Latitude of event;Longitude of event;DEPTH, water;Pressure, water;Temperature, water;Salinity;Conductivity;Temperature, water, potential;Density, sigma-theta (0);Optical beam attenuation coefficient, particle in water column;PAR lightmeter voltage from downward irradiance;Fluorescence, chlorophyll;TT043;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1995-01-08T15:34:00/1995-02-01T14:35:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Morrison-tt043.htm;400902 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);9.9826 57.2999 22.483 68.75",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.826996"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[57.2999,9.9826],[57.2999,22.483],[68.75,22.483],[68.75,9.9826],[57.2999,9.9826]]]}",
-    "tags": [
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography during Thomas G. Thompson cruise TT043"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/d04bf9e3-6860-5d9e-959a-151295debee5.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/d04bf9e3-6860-5d9e-959a-151295debee5.json
deleted file mode 100644
index d364412e..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/d04bf9e3-6860-5d9e-959a-151295debee5.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.826998",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.826998"
-    ],
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(10N-23N,57E-69E)",
-    "TempCoverageBegin": 62941661999,
-    "TempCoverageEnd": 62941661999,
-    "TemporalCoverage": " point in time : 1995-07-18T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1995-07-18T11:59:59Z",
-    "TemporalCoverage:EndDate": "1995-07-18T11:59:59Z",
-    "author": [
-        "Gardner, Wilford",
-        "Morrison, John M"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.826998;2017-08-05T09:40:10Z;ASPS;JGOFSUS;10.1594/PANGAEA.826998;Morrison, John M;Gardner, Wilford;Physical oceanography during Thomas G. Thompson cruise TT049;PANGAEA - Data Publisher for Earth & Environmental Science;2014;Event label;Date/Time of event;Latitude of event;Longitude of event;DEPTH, water;Pressure, water;Temperature, water;Salinity;Conductivity;Temperature, water, potential;Density, sigma-theta (0);Optical beam attenuation coefficient, particle in water column;PAR lightmeter voltage from downward irradiance;Fluorescence, chlorophyll;TT049;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1995-07-18T02:45:00/1995-08-13T02:48:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Morrison-tt049.htm;396768 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);9.911 57.2997 22.5268 68.7507",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.826998"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[57.2997,9.911],[57.2997,22.5268],[68.7507,22.5268],[68.7507,9.911],[57.2997,9.911]]]}",
-    "tags": [
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography during Thomas G. Thompson cruise TT049"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/d3551a9b-9e4f-52cd-b4c1-62912579f946.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/d3551a9b-9e4f-52cd-b4c1-62912579f946.json
deleted file mode 100644
index d4d488cd..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/d3551a9b-9e4f-52cd-b4c1-62912579f946.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.822362",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.822362"
-    ],
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(23N-26N,57E-61E)",
-    "TempCoverageBegin": 62963697599,
-    "TempCoverageEnd": 62963697599,
-    "TemporalCoverage": " point in time : 1996-03-29T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1996-03-29T11:59:59Z",
-    "TemporalCoverage:EndDate": "1996-03-29T11:59:59Z",
-    "author": [
-        "GTSPP"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.822362;2017-08-05T09:31:55Z;ASPS;JGOFSCountryUnknown;10.1594/PANGAEA.822362;GTSPP;Physical oceanography during KANE cruise NZ96;PANGAEA - Data Publisher for Earth & Environmental Science;2013;Event label;Date/Time of event;Latitude of event;Longitude of event;DEPTH, water;Pressure, water;Temperature, water;Salinity;Temperature, water, potential;Density, sigma-theta (0);NZ96;Kane;Global Temperature-Salinity Profile Program (GTSPP);Joint Global Ocean Flux Study (JGOFS);1996-03-29T18:17:00/1996-04-13T11:50:00;eng;Dataset;10013/epic.40681.d001;6655 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);23.2 56.71 25.58 60.8",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.822362"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSCountryUnknown"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[56.71,23.2],[56.71,25.58],[60.8,25.58],[60.8,23.2],[56.71,23.2]]]}",
-    "tags": [
-        {
-            "name": "NZ"
-        },
-        {
-            "name": "Kane"
-        },
-        {
-            "name": "Global Temperature-Salinity Profile Program GTSPP"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography during KANE cruise NZ96"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/d674527c-3c20-5260-95d9-3b7243563513.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/d674527c-3c20-5260-95d9-3b7243563513.json
deleted file mode 100644
index 7a878fda..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/d674527c-3c20-5260-95d9-3b7243563513.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112966",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112966"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(15N,69E)",
-    "TempCoverageBegin": 62916523199,
-    "TempCoverageEnd": 62916523199,
-    "TemporalCoverage": " point in time : 1994-09-30T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-09-30T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-09-30T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112966;2017-12-21T11:55:26Z;ASPS;JGOFSUS;10.1594/PANGAEA.112966;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_14-1;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-09-30T06:12:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;238 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);15.3827 68.7495",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112966"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[68.7495,15.3827],[68.7495,15.3827],[68.7495,15.3827],[68.7495,15.3827],[68.7495,15.3827]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_14-1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/d6bf4640-3b8e-5153-9f0e-7e229de93011.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/d6bf4640-3b8e-5153-9f0e-7e229de93011.json
deleted file mode 100644
index 557eab96..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/d6bf4640-3b8e-5153-9f0e-7e229de93011.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.817138",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.817138"
-    ],
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(3 N-23N,54E-65E)",
-    "author": [
-        "van Bennekom, Johan A",
-        "van der Linden, W J M",
-        "van der Weijden, Cornelis H"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.817138;2017-08-05T09:10:02Z;ASPS;JGOFSNetherlands;10.1594/PANGAEA.817138;van der Weijden, Cornelis H;van der Linden, W J M;van Bennekom, Johan A;Physical oceanography during TYRO cruise NIOP-D1;PANGAEA - Data Publisher for Earth & Environmental Science;2013;Event label;Latitude of event;Longitude of event;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Temperature, water, potential;Density, sigma-theta (0);Fluorescence;Transmission of light;Calculated;Fluorometer, Chelsea Instruments;NIOP-D1;Tyro;Joint Global Ocean Flux Study (JGOFS);Netherlands Indian Ocean Programme (NIOP);eng;Dataset;http://store.pangaea.de/Projects/JGOFS/Netherlands/NIOP-D1_CTD.pdf;323832 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);2.98 53.9867 22.93 65.0483",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.817138"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSNetherlands"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[53.9867,2.98],[53.9867,22.93],[65.0483,22.93],[65.0483,2.98],[53.9867,2.98]]]}",
-    "tags": [
-        {
-            "name": "Calculated"
-        },
-        {
-            "name": "Fluorometer"
-        },
-        {
-            "name": "Chelsea Instruments"
-        },
-        {
-            "name": "NIOP-D"
-        },
-        {
-            "name": "Tyro"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        },
-        {
-            "name": "Netherlands Indian Ocean Programme NIOP"
-        }
-    ],
-    "title": [
-        "Physical oceanography during TYRO cruise NIOP-D1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/d7c3f083-3c20-56b2-93cd-f6216c6419bc.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/d7c3f083-3c20-56b2-93cd-f6216c6419bc.json
deleted file mode 100644
index 1aa8be83..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/d7c3f083-3c20-56b2-93cd-f6216c6419bc.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.817122",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.817122"
-    ],
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(4 S-2 S,40E-42E)",
-    "TempCoverageBegin": 62857857599,
-    "TempCoverageEnd": 62857857599,
-    "TemporalCoverage": " point in time : 1992-11-20T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1992-11-20T11:59:59Z",
-    "TemporalCoverage:EndDate": "1992-11-20T11:59:59Z",
-    "author": [
-        "Heip, Carlo H R",
-        "Nguli, Michael Mutua",
-        "Hemminga, M A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.817122;2017-08-05T09:10:00Z;ASPS;JGOFSNetherlands;10.1594/PANGAEA.817122;Heip, Carlo H R;Hemminga, M A;Nguli, Michael Mutua;Physical oceanography during TYRO cruise NIOP-A2;PANGAEA - Data Publisher for Earth & Environmental Science;2013;Event label;Date/Time of event;Latitude of event;Longitude of event;Elevation of event;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Temperature, water, potential;Density, sigma-theta (0);Fluorescence;Calculated;Fluorometer, Chelsea Instruments;NIOP-A2;Tyro;Joint Global Ocean Flux Study (JGOFS);Netherlands Indian Ocean Programme (NIOP);1992-11-20T08:10:00/1992-12-04T10:23:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/Netherlands/NIOP-A2_CTD.pdf;88823 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);-4.4222 39.5925 -1.935 41.7973",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.817122"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSNetherlands"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[39.5925,-4.4222],[39.5925,-1.935],[41.7973,-1.935],[41.7973,-4.4222],[39.5925,-4.4222]]]}",
-    "tags": [
-        {
-            "name": "Calculated"
-        },
-        {
-            "name": "Fluorometer"
-        },
-        {
-            "name": "Chelsea Instruments"
-        },
-        {
-            "name": "NIOP-A"
-        },
-        {
-            "name": "Tyro"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        },
-        {
-            "name": "Netherlands Indian Ocean Programme NIOP"
-        }
-    ],
-    "title": [
-        "Physical oceanography during TYRO cruise NIOP-A2"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/deebf162-f5b5-524e-868b-b7d46e9510b9.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/deebf162-f5b5-524e-868b-b7d46e9510b9.json
deleted file mode 100644
index 3bf421e1..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/deebf162-f5b5-524e-868b-b7d46e9510b9.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112983",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112983"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(22N,61E)",
-    "TempCoverageBegin": 62916955199,
-    "TempCoverageEnd": 62916955199,
-    "TemporalCoverage": " point in time : 1994-10-05T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-10-05T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-10-05T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112983;2017-12-21T11:42:00Z;ASPS;JGOFSUS;10.1594/PANGAEA.112983;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_23-1;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-10-05T04:04:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;75 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);22.4825 61.1832",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112983"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[61.1832,22.4825],[61.1832,22.4825],[61.1832,22.4825],[61.1832,22.4825],[61.1832,22.4825]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_23-1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/eb3ad3ca-783e-52b9-b29b-e116fff5a345.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/eb3ad3ca-783e-52b9-b29b-e116fff5a345.json
deleted file mode 100644
index c26f0ccb..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/eb3ad3ca-783e-52b9-b29b-e116fff5a345.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.817121",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.817121"
-    ],
-    "PublicationTimestamp": "2013-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(4 S-2 S,40E-46E)",
-    "TempCoverageBegin": 62844634799,
-    "TempCoverageEnd": 62844634799,
-    "TemporalCoverage": " point in time : 1992-06-20T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1992-06-20T11:59:59Z",
-    "TemporalCoverage:EndDate": "1992-06-20T11:59:59Z",
-    "author": [
-        "Heip, Carlo H R",
-        "Nguli, Michael Mutua",
-        "Hemminga, M A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.817121;2017-08-05T09:10:00Z;ASPS;JGOFSNetherlands;10.1594/PANGAEA.817121;Heip, Carlo H R;Hemminga, M A;Nguli, Michael Mutua;Physical oceanography during TYRO cruise NIOP-A1;PANGAEA - Data Publisher for Earth & Environmental Science;2013;Event label;Date/Time of event;Latitude of event;Longitude of event;Elevation of event;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Temperature, water, potential;Density, sigma-theta (0);Fluorescence;Calculated;Fluorometer, Chelsea Instruments;NIOP-A1;Tyro;Joint Global Ocean Flux Study (JGOFS);Netherlands Indian Ocean Programme (NIOP);1992-06-20T06:24:00/1992-07-07T17:42:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/Netherlands/NIOP-A1_CTD.pdf;138747 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);-4.4467 39.5533 -1.9522 45.7833",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.817121"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSNetherlands"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[39.5533,-4.4467],[39.5533,-1.9522],[45.7833,-1.9522],[45.7833,-4.4467],[39.5533,-4.4467]]]}",
-    "tags": [
-        {
-            "name": "Calculated"
-        },
-        {
-            "name": "Fluorometer"
-        },
-        {
-            "name": "Chelsea Instruments"
-        },
-        {
-            "name": "NIOP-A"
-        },
-        {
-            "name": "Tyro"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        },
-        {
-            "name": "Netherlands Indian Ocean Programme NIOP"
-        }
-    ],
-    "title": [
-        "Physical oceanography during TYRO cruise NIOP-A1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/ee142025-cfd5-5eef-9c45-01c2d33a43e0.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/ee142025-cfd5-5eef-9c45-01c2d33a43e0.json
deleted file mode 100644
index 84b440c8..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/ee142025-cfd5-5eef-9c45-01c2d33a43e0.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112985",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112985"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(22N,61E)",
-    "TempCoverageBegin": 62916955199,
-    "TempCoverageEnd": 62916955199,
-    "TemporalCoverage": " point in time : 1994-10-05T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-10-05T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-10-05T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112985;2017-12-21T11:42:00Z;ASPS;JGOFSUS;10.1594/PANGAEA.112985;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_23-3;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-10-05T07:27:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;75 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);22.4823 61.1835",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112985"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[61.1835,22.4823],[61.1835,22.4823],[61.1835,22.4823],[61.1835,22.4823],[61.1835,22.4823]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_23-3"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/f3d83728-d6bb-5ec7-af77-24b9f756c060.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/f3d83728-d6bb-5ec7-af77-24b9f756c060.json
deleted file mode 100644
index 494cffdb..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/f3d83728-d6bb-5ec7-af77-24b9f756c060.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112995",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112995"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(10N,65E)",
-    "TempCoverageBegin": 62916263999,
-    "TempCoverageEnd": 62916263999,
-    "TemporalCoverage": " point in time : 1994-09-27T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-09-27T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-09-27T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112995;2017-12-21T11:42:21Z;ASPS;JGOFSUS;10.1594/PANGAEA.112995;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_8-1;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-09-27T12:49:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;240 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);9.9995 65.0003",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112995"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[65.0003,9.9995],[65.0003,9.9995],[65.0003,9.9995],[65.0003,9.9995],[65.0003,9.9995]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_8-1"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/fb5b2960-6453-5ab0-bf53-8e71f1631bc4.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/fb5b2960-6453-5ab0-bf53-8e71f1631bc4.json
deleted file mode 100644
index b4b8f0b8..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/fb5b2960-6453-5ab0-bf53-8e71f1631bc4.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112981",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112981"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(21N,64E)",
-    "TempCoverageBegin": 62916868799,
-    "TempCoverageEnd": 62916868799,
-    "TemporalCoverage": " point in time : 1994-10-04T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-10-04T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-10-04T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112981;2017-12-21T11:41:59Z;ASPS;JGOFSUS;10.1594/PANGAEA.112981;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_21-4;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-10-04T08:00:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;48 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);21.1807 63.5528",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112981"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[63.5528,21.1807],[63.5528,21.1807],[63.5528,21.1807],[63.5528,21.1807],[63.5528,21.1807]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_21-4"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/ASPS_1/json/fc074b84-462c-547c-be20-427017f97b7e.json b/oaitestdata/pangaea-datacite3/ASPS_1/json/fc074b84-462c-547c-be20-427017f97b7e.json
deleted file mode 100644
index 1d79c5dc..00000000
--- a/oaitestdata/pangaea-datacite3/ASPS_1/json/fc074b84-462c-547c-be20-427017f97b7e.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.112974",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112974"
-    ],
-    "PublicationTimestamp": "2003-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2003"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(19N,67E)",
-    "TempCoverageBegin": 62916695999,
-    "TempCoverageEnd": 62916695999,
-    "TemporalCoverage": " point in time : 1994-10-02T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1994-10-02T11:59:59Z",
-    "TemporalCoverage:EndDate": "1994-10-02T11:59:59Z",
-    "author": [
-        "Codispoti, Louis A"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.112974;2017-12-21T11:55:41Z;ASPS;JGOFSUS;10.1594/PANGAEA.112974;Codispoti, Louis A;Physical oceanography and nutrients measured on water bottle samples at station TT039_18-7;PANGAEA - Data Publisher for Earth & Environmental Science;2003;DEPTH, water;Pressure, water;Temperature, water;Salinity;Oxygen;Nitrate;Phosphate;Silicate;Nitrite;Ammonium;Bottle number;Oxygen, Winkler (Culberson, 1991, WOCE Report 68/91);TT039;Thomas G. Thompson;Joint Global Ocean Flux Study (JGOFS);1994-10-02T09:32:00;eng;Dataset;http://store.pangaea.de/Projects/JGOFS/US/ArabianSea/Codispoti-tt039.htm;238 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);19.0093 66.9902",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.112974"
-    ],
-    "oai_set": [
-        "ASPS",
-        "JGOFSUS"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[66.9902,19.0093],[66.9902,19.0093],[66.9902,19.0093],[66.9902,19.0093],[66.9902,19.0093]]]}",
-    "tags": [
-        {
-            "name": "Oxygen"
-        },
-        {
-            "name": "Winkler Culberson"
-        },
-        {
-            "name": "WOCE Report"
-        },
-        {
-            "name": "TT"
-        },
-        {
-            "name": "Thomas G. Thompson"
-        },
-        {
-            "name": "Joint Global Ocean Flux Study JGOFS"
-        }
-    ],
-    "title": [
-        "Physical oceanography and nutrients measured on water bottle samples at station TT039_18-7"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/BAH1962_1/json/046a0852-5365-58f4-af6e-e03ba1ff0e9e.json b/oaitestdata/pangaea-datacite3/BAH1962_1/json/046a0852-5365-58f4-af6e-e03ba1ff0e9e.json
deleted file mode 100644
index d3f962bd..00000000
--- a/oaitestdata/pangaea-datacite3/BAH1962_1/json/046a0852-5365-58f4-af6e-e03ba1ff0e9e.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.56713"
-    ],
-    "PublicationTimestamp": "2000-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "SpatialCoverage": "(54N-54N,8 E-8 E)",
-    "TempCoverageBegin": 61889313599,
-    "TempCoverageEnd": 61889313599,
-    "TemporalCoverage": " point in time : 1962-03-13T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1962-03-13T11:59:59Z",
-    "TemporalCoverage:EndDate": "1962-03-13T11:59:59Z",
-    "author": [
-        "Gillbricht, Max"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.56713;2018-04-19T08:41:44Z;BAH1962;https://doi.pangaea.de/10.1594/PANGAEA.56713;Gillbricht, Max;Helgoland transects 1962;PANGAEA - Data Publisher for Earth & Environmental Science;2000;DATE/TIME;LATITUDE;LONGITUDE;DEPTH, water;Temperature, water;Salinity;Phosphate;Nitrate;Nitrite;Ammonium;Nitrogen, inorganic, dissolved;Reversing thermometer;Titration, chloride (Grasshoff et al., 1983, Verlag Chemie GmbH Weinheim);Photometer, molybdene blue, reduct SnCl;Reduction by hydrazin;Photometer, azo-dye (Bendschneider & Robinson, 1952, J Mar Res, 11:87-96);Bordeaux red, improved by Gillbricht, 1961;Calculated (sum of Nitrate, Nitrite, Ammonium);HelgolandTransects;Uth\u00f6rn;Shelf Seas Systems Ecology @ AWI (former Biologische Anstalt Helgoland) (BAH);Long-term Ecological Research at AWI (LTER);Alfred Wegener Institute - Biological Institute Helgoland;1962-03-13T12:00:00/1962-12-13T12:00:00;eng;Dataset;2093 data points;text/tab-separated-values;53.5667 7.8 54.25 8.4833",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.56713"
-    ],
-    "oai_set": [
-        "BAH1962"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[7.8,53.5667],[7.8,54.25],[8.4833,54.25],[8.4833,53.5667],[7.8,53.5667]]]}",
-    "tags": [
-        {
-            "name": "Reversing thermometer"
-        },
-        {
-            "name": "Titration"
-        },
-        {
-            "name": "chloride Grasshoff et al."
-        },
-        {
-            "name": "Verlag Chemie GmbH Weinheim"
-        },
-        {
-            "name": "Photometer"
-        },
-        {
-            "name": "molybdene blue"
-        },
-        {
-            "name": "reduct SnCl"
-        },
-        {
-            "name": "Reduction hydrazin"
-        },
-        {
-            "name": "Photometer"
-        },
-        {
-            "name": "azo-dye Bendschneider"
-        },
-        {
-            "name": "Robinson"
-        },
-        {
-            "name": "J Mar Res"
-        }
-    ],
-    "title": [
-        "Helgoland transects 1962"
-    ],
-    "url": "https://doi.pangaea.de/10.1594/PANGAEA.56713"
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/BAH1962_1/json/068ee4ed-b97b-59e9-afcd-e1e255874609.json b/oaitestdata/pangaea-datacite3/BAH1962_1/json/068ee4ed-b97b-59e9-afcd-e1e255874609.json
deleted file mode 100644
index 7d22dae4..00000000
--- a/oaitestdata/pangaea-datacite3/BAH1962_1/json/068ee4ed-b97b-59e9-afcd-e1e255874609.json
+++ /dev/null
@@ -1,90 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.55682",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.55682"
-    ],
-    "PublicationTimestamp": "1999-07-01T11:59:59Z",
-    "PublicationYear": [
-        "1999"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(54N,8 E)",
-    "TempCoverageBegin": 61883265599,
-    "TempCoverageEnd": 61883265599,
-    "TemporalCoverage": " point in time : 1962-01-02T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1962-01-02T11:59:59Z",
-    "TemporalCoverage:EndDate": "1962-01-02T11:59:59Z",
-    "author": [
-        "Gillbricht, Max"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.55682;2018-04-19T08:43:01Z;BAH1962;10.1594/PANGAEA.55682;Gillbricht, Max;Hydrochemistry and phytoplankton abundance at time series station Helgoland Roads, North Sea, in 1962;PANGAEA - Data Publisher for Earth & Environmental Science;1999;DATE/TIME;Temperature, water;Salinity;Nitrate;Nitrite;Ammonium;Nitrogen, inorganic, dissolved;Phosphate;Phytoplankton;Diatoms;Flagellates;Phytoplankton, biomass as carbon;Diatoms, biomass as carbon;Flagellates, biomass as carbon;Analyst;Mercury thermometer, in situ;Titration, chloride (Grasshoff et al., 1983, Verlag Chemie GmbH Weinheim);Reduction by hydrazin;Photometer, azo-dye (Bendschneider & Robinson, 1952, J Mar Res, 11:87-96);Bordeaux red, improved by Gillbricht, 1961;Calculated (sum of Nitrate, Nitrite, Ammonium);Photometer, molybdene blue, reduct SnCl;Quantitative phytoplankton method (Uterm\u00f6hl, 1958);HelgolandRoadsTimeseries;Meeresstation Helgoland;Shelf Seas Systems Ecology @ AWI (former Biologische Anstalt Helgoland) (BAH);Long-term Ecological Research at AWI (LTER);1962-01-02T09:00:00/1962-12-28T09:40:00;eng;Dataset;1887 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);54.18833 7.9",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.55682"
-    ],
-    "oai_set": [
-        "BAH1962"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[7.9,54.18833],[7.9,54.18833],[7.9,54.18833],[7.9,54.18833],[7.9,54.18833]]]}",
-    "tags": [
-        {
-            "name": "Mercury thermometer"
-        },
-        {
-            "name": "situ"
-        },
-        {
-            "name": "Titration"
-        },
-        {
-            "name": "chloride Grasshoff et al."
-        },
-        {
-            "name": "Verlag Chemie GmbH Weinheim"
-        },
-        {
-            "name": "Reduction hydrazin"
-        },
-        {
-            "name": "Photometer"
-        },
-        {
-            "name": "azo-dye Bendschneider"
-        },
-        {
-            "name": "Robinson"
-        },
-        {
-            "name": "J Mar Res"
-        },
-        {
-            "name": "Bordeaux red"
-        },
-        {
-            "name": "improved Gillbricht"
-        }
-    ],
-    "title": [
-        "Hydrochemistry and phytoplankton abundance at time series station Helgoland Roads, North Sea, in 1962"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/BAH1962_1/json/1533bf16-fc93-5079-8c5e-a9e2c1307f12.json b/oaitestdata/pangaea-datacite3/BAH1962_1/json/1533bf16-fc93-5079-8c5e-a9e2c1307f12.json
deleted file mode 100644
index 8d7090a7..00000000
--- a/oaitestdata/pangaea-datacite3/BAH1962_1/json/1533bf16-fc93-5079-8c5e-a9e2c1307f12.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.56309",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.56309"
-    ],
-    "PublicationTimestamp": "2007-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2007"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "SpatialCoverage": "(54N,8 E)",
-    "TempCoverageBegin": 61884388799,
-    "TempCoverageEnd": 61884388799,
-    "TemporalCoverage": " point in time : 1962-01-15T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1962-01-15T11:59:59Z",
-    "TemporalCoverage:EndDate": "1962-01-15T11:59:59Z",
-    "author": [
-        "Wiltshire, Karen Helen"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.56309;2018-04-03T09:01:56Z;BAH1962;10.1594/PANGAEA.56309;Wiltshire, Karen Helen;0000-0002-7148-0529;Abundance of bacillariophyceae at time series station Helgoland Roads, North Sea, in 1962;PANGAEA - Data Publisher for Earth & Environmental Science;2007;DATE/TIME;DEPTH, water;Asterionellopsis glacialis, fractionated;Asteroplanus karianus;Bacillaria paxillifera, fractionated;Cylindrotheca closterium, fractionated;Fragilaria sp.;Gyrosigma sp., fractionated;Gyrosigma sp.;Meuniera membranacea;Navicula sp., fractionated;Navicula sp.;Nitzschia longissima;Pleurosigma sp.;Pseudo-nitzschia delicatissima;Pseudo-nitzschia seriata, fractionated;Pseudo-nitzschia seriata;Rhaphoneis amphiceros;Thalassionema nitzschioides;Bacillariales indeterminata, fractionated;Bacillariales indeterminata;Actinoptychus senarius;Bacteriastrum hyalinum, fractionated;Bellerochea malleus, fractionated;Brockmanniella brockmannii;Cerataulina pelagica, fractionated;Cerataulina pelagica;Chaetoceros debilis;Chaetoceros decipiens, fractionated;Chaetoceros decipiens;Chaetoceros densus;Chaetoceros didymus;Chaetoceros socialis;Chaetoceros sp., fractionated;Chaetoceros sp.;Coscinodiscus concinnus, fractionated;Coscinodiscus concinnus;Coscinodiscus granii, fractionated;Coscinodiscus granii;Coscinodiscus radiatus;Coscinodiscus sp., fractionated;Coscinodiscus sp.;Dactyliosolen fragilissimus;Detonula confervacea;Detonula pumila, fractionated;Ditylum brightwellii, fractionated;Ditylum brightwellii;Eucampia zodiacus;Guinardia delicatula;Guinardia flaccida, fractionated;Guinardia flaccida;Guinardia striata, fractionated;Guinardia striata;Helicotheca tamesis, fractionated;Lauderia annulata;Leptocylindrus danicus;Leptocylindrus minimus, fractionated;Lithodesmium undulatum, fractionated;Melosira sp.;Odontella aurita, fractionated;Odontella aurita;Odontella mobiliensis;Odontella regia, fractionated;Odontella regia;Odontella rhombus, fractionated;Odontella sinensis, fractionated;Odontella sinensis;Paralia sulcata;Podosira stelliger;Porosira glacialis;Proboscia alata;Rhizosolenia hebetata;Rhizosolenia imbricata, fractionated;Rhizosolenia imbricata;Rhizosolenia pungens;Rhizosolenia robusta;Rhizosolenia setigera, fractionated;Rhizosolenia setigera;Rhizosolenia styliformis;Skeletonema costatum, fractionated;Skeletonema costatum;Stephanopyxis turris, fractionated;Thalassiosira minima;Thalassiosira nordenskioeldii;Thalassiosira punctigera;Thalassiosira rotula;Thalassiosira sp., fractionated;Thalassiosira sp.;Triceratium favus;Trigonium alternans;Biddulphiales indeterminata, fractionated;Biddulphiales indeterminata;Quantitative phytoplankton method (Uterm\u00f6hl, 1958);HelgolandRoadsTimeseries;Meeresstation Helgoland;Shelf Seas Systems Ecology @ AWI (former Biologische Anstalt Helgoland) (BAH);Long-term Ecological Research at AWI (LTER);Alfred Wegener Institute, Helmholtz Center for Polar and Marine Research, Bremerhaven;1962-01-15T10:30:00/1962-12-28T09:40:00;eng;Dataset;10013/epic.28563.d001;15500 data points;text/tab-separated-values;54.18833 7.9",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.56309"
-    ],
-    "oai_set": [
-        "BAH1962"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[7.9,54.18833],[7.9,54.18833],[7.9,54.18833],[7.9,54.18833],[7.9,54.18833]]]}",
-    "tags": [
-        {
-            "name": "Quantitative phytoplankton method Utermhl"
-        },
-        {
-            "name": "HelgolandRoadsTimeseries"
-        },
-        {
-            "name": "Meeresstation Helgoland"
-        },
-        {
-            "name": "Long-term Ecological Research AWI LTER"
-        }
-    ],
-    "title": [
-        "Abundance of bacillariophyceae at time series station Helgoland Roads, North Sea, in 1962"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/BAH1962_1/json/37b0802d-b857-52fe-be8a-08728a6a22ee.json b/oaitestdata/pangaea-datacite3/BAH1962_1/json/37b0802d-b857-52fe-be8a-08728a6a22ee.json
deleted file mode 100644
index 2e1c2e3c..00000000
--- a/oaitestdata/pangaea-datacite3/BAH1962_1/json/37b0802d-b857-52fe-be8a-08728a6a22ee.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.56380",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.56380"
-    ],
-    "PublicationTimestamp": "2000-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "SpatialCoverage": "(54N,8 E)",
-    "TempCoverageBegin": 61884388799,
-    "TempCoverageEnd": 61884388799,
-    "TemporalCoverage": " point in time : 1962-01-15T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1962-01-15T11:59:59Z",
-    "TemporalCoverage:EndDate": "1962-01-15T11:59:59Z",
-    "author": [
-        "Wiltshire, Karen Helen"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.56380;2018-04-03T09:02:53Z;BAH1962;10.1594/PANGAEA.56380;Wiltshire, Karen Helen;0000-0002-7148-0529;Abundance of dinoflagellates, dictyochophyceae, and prymnesiophyceae at time series station Helgoland Roads, North Sea, in 1962;PANGAEA - Data Publisher for Earth & Environmental Science;2000;DATE/TIME;DEPTH, water;Amphidinium sp., fractionated;Amphidinium sp.;Ceratium furca, fractionated;Ceratium fusus, fractionated;Ceratium horridum, fractionated;Ceratium lineatum, fractionated;Ceratium longipes, fractionated;Ceratium macroceros, fractionated;Ceratium tripos, fractionated;Dinophysis acuminata, fractionated;Dinophysis acuta, fractionated;Dinophysis norvegica, fractionated;Dinophysis sp., fractionated;Gonyaulax sp.;Gymnodinium mikimotoi;Gymnodinium sp., fractionated;Gymnodinium sp.;Gyrodinium sp., fractionated;Gyrodinium sp.;Noctiluca scintillans, fractionated;Phalacroma rotundatum, fractionated;Polykrikos sp., fractionated;Prorocentrum balticum, fractionated;Prorocentrum micans, fractionated;Prorocentrum micans;Protoperidinium brevipes;Protoperidinium claudicans;Protoperidinium conicum;Protoperidinium depressum, fractionated;Protoperidinium divergens, fractionated;Protoperidinium ovatum, fractionated;Protoperidinium pellucidum, fractionated;Protoperidinium punctulatum;Protoperidinium sp., fractionated;Protoperidinium sp.;Pyrocystis noctiluca, fractionated;Pyrophacus sp.;Scrippsiella trochoidea;Torodinium robustum, fractionated;Dinophyceae indeterminata round, fractionated;Dinophyceae indeterminata round;Dinophyceae indeterminata flat, fractionated;Dinophyceae indeterminata flat;Dinophyceae indeterminata;Dictyocha speculum, fractionated;Coccolithophoridae indeterminata, fractionated;Coccolithophoridae indeterminata;Phaeocystis sp., fractionated;Flagellates indeterminata, fractionated;Flagellates indeterminata;Quantitative phytoplankton method (Uterm\u00f6hl, 1958);HelgolandRoadsTimeseries;Meeresstation Helgoland;Shelf Seas Systems Ecology @ AWI (former Biologische Anstalt Helgoland) (BAH);Long-term Ecological Research at AWI (LTER);Alfred Wegener Institute, Helmholtz Center for Polar and Marine Research, Bremerhaven;1962-01-15T10:30:00/1962-12-28T09:40:00;eng;Dataset;10013/epic.28563.d001;10416 data points;text/tab-separated-values;54.18833 7.9",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.56380"
-    ],
-    "oai_set": [
-        "BAH1962"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[7.9,54.18833],[7.9,54.18833],[7.9,54.18833],[7.9,54.18833],[7.9,54.18833]]]}",
-    "tags": [
-        {
-            "name": "Quantitative phytoplankton method Utermhl"
-        },
-        {
-            "name": "HelgolandRoadsTimeseries"
-        },
-        {
-            "name": "Meeresstation Helgoland"
-        },
-        {
-            "name": "Long-term Ecological Research AWI LTER"
-        }
-    ],
-    "title": [
-        "Abundance of dinoflagellates, dictyochophyceae, and prymnesiophyceae at time series station Helgoland Roads, North Sea, in 1962"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/BAH1962_1/json/5194f888-7144-50f3-b300-27ba145b4fb4.json b/oaitestdata/pangaea-datacite3/BAH1962_1/json/5194f888-7144-50f3-b300-27ba145b4fb4.json
deleted file mode 100644
index ababdc7a..00000000
--- a/oaitestdata/pangaea-datacite3/BAH1962_1/json/5194f888-7144-50f3-b300-27ba145b4fb4.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.80767",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.80767"
-    ],
-    "PublicationTimestamp": "2002-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2002"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(54N,8 E)",
-    "TempCoverageBegin": 61883265599,
-    "TempCoverageEnd": 61883265599,
-    "TemporalCoverage": " point in time : 1962-01-02T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1962-01-02T11:59:59Z",
-    "TemporalCoverage:EndDate": "1962-01-02T11:59:59Z",
-    "author": [
-        "DWD"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.80767;2017-08-04T13:28:53Z;BAH1962;10.1594/PANGAEA.80767;DWD;Daily mean weather data of Helgoland in 1962;PANGAEA - Data Publisher for Earth & Environmental Science;2002;DATE/TIME;ALTITUDE;Precipitation integrated;Wind speed;Pressure, atmospheric;Temperature, air;Sunshine duration, daily;Meteorological station;Visual observation;HelgolandRoadsTimeseries;Meeresstation Helgoland;1962-01-02T00:00:00/1962-03-19T00:00:00;eng;Dataset;385 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);54.18833 7.9",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.80767"
-    ],
-    "oai_set": [
-        "BAH1962"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[7.9,54.18833],[7.9,54.18833],[7.9,54.18833],[7.9,54.18833],[7.9,54.18833]]]}",
-    "tags": [
-        {
-            "name": "Meteorological station"
-        },
-        {
-            "name": "Visual observation"
-        },
-        {
-            "name": "HelgolandRoadsTimeseries"
-        },
-        {
-            "name": "Meeresstation Helgoland"
-        }
-    ],
-    "title": [
-        "Daily mean weather data of Helgoland in 1962"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/BAH1962_1/json/70d4eb0a-aba7-5f37-a515-908f2838f417.json b/oaitestdata/pangaea-datacite3/BAH1962_1/json/70d4eb0a-aba7-5f37-a515-908f2838f417.json
deleted file mode 100644
index 75191996..00000000
--- a/oaitestdata/pangaea-datacite3/BAH1962_1/json/70d4eb0a-aba7-5f37-a515-908f2838f417.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.87372",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.87372"
-    ],
-    "PublicationTimestamp": "2002-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2002"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(53N,11E)",
-    "TempCoverageBegin": 61883179199,
-    "TempCoverageEnd": 61883179199,
-    "TemporalCoverage": " point in time : 1962-01-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1962-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1962-01-01T11:59:59Z",
-    "author": [
-        "Engel, Heinz"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.87372;2017-08-04T13:37:24Z;BAH1962;10.1594/PANGAEA.87372;Engel, Heinz;Daily discharge of the river Elbe at km 537 in 1962;PANGAEA - Data Publisher for Earth & Environmental Science;2002;DATE/TIME;River discharge, daily mean;Stream Gauging;HelgolandRoadsTimeseries;Meeresstation Helgoland;Shelf Seas Systems Ecology @ AWI (former Biologische Anstalt Helgoland) (BAH);Long-term Ecological Research at AWI (LTER);1962-01-01T00:00:00/1962-12-31T00:00:00;eng;Dataset;http://www.dgj.de/servlet/IbMenu;365 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);53.23 10.87",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.87372"
-    ],
-    "oai_set": [
-        "BAH1962"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[10.87,53.23],[10.87,53.23],[10.87,53.23],[10.87,53.23],[10.87,53.23]]]}",
-    "tags": [
-        {
-            "name": "Stream Gauging"
-        },
-        {
-            "name": "HelgolandRoadsTimeseries"
-        },
-        {
-            "name": "Meeresstation Helgoland"
-        },
-        {
-            "name": "Long-term Ecological Research AWI LTER"
-        }
-    ],
-    "title": [
-        "Daily discharge of the river Elbe at km 537 in 1962"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/BAH1962_1/json/f2382b6a-6350-5a83-9e2f-f5e829b9f8eb.json b/oaitestdata/pangaea-datacite3/BAH1962_1/json/f2382b6a-6350-5a83-9e2f-f5e829b9f8eb.json
deleted file mode 100644
index 7e31eb39..00000000
--- a/oaitestdata/pangaea-datacite3/BAH1962_1/json/f2382b6a-6350-5a83-9e2f-f5e829b9f8eb.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.1594/PANGAEA.56251",
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.56251"
-    ],
-    "PublicationTimestamp": "2000-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2000"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "SpatialCoverage": "(54N,8 E)",
-    "TempCoverageBegin": 63019339199,
-    "TempCoverageEnd": 63019339199,
-    "TemporalCoverage": " point in time : 1998-01-02T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1998-01-02T11:59:59Z",
-    "TemporalCoverage:EndDate": "1998-01-02T11:59:59Z",
-    "author": [
-        "Wiltshire, Karen Helen"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.56251;2017-09-02T05:35:26Z;BAH1962;10.1594/PANGAEA.56251;Wiltshire, Karen Helen;0000-0002-7148-0529;Abundance of protozoa at time series station Helgoland Roads, North Sea, in 1998;PANGAEA - Data Publisher for Earth & Environmental Science;2000;DATE/TIME;DEPTH, water;Laboea sp.;Myrionecta rubra, fractionated;Myrionecta rubra;Ciliata indeterminata, fractionated;Ciliata indeterminata;Foraminifera, planktic indeterminata;Quantitative phytoplankton method (Uterm\u00f6hl, 1958);HelgolandRoadsTimeseries;Meeresstation Helgoland;Shelf Seas Systems Ecology @ AWI (former Biologische Anstalt Helgoland) (BAH);Long-term Ecological Research at AWI (LTER);Alfred Wegener Institute - Biological Institute Helgoland;1998-01-02T08:35:00/1998-12-30T08:10:00;eng;Dataset;10013/epic.28563.d001;3390 data points;text/tab-separated-values;54.18833 7.9",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.56251"
-    ],
-    "oai_set": [
-        "BAH1962"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[7.9,54.18833],[7.9,54.18833],[7.9,54.18833],[7.9,54.18833],[7.9,54.18833]]]}",
-    "tags": [
-        {
-            "name": "Quantitative phytoplankton method Utermhl"
-        },
-        {
-            "name": "HelgolandRoadsTimeseries"
-        },
-        {
-            "name": "Meeresstation Helgoland"
-        },
-        {
-            "name": "Long-term Ecological Research AWI LTER"
-        }
-    ],
-    "title": [
-        "Abundance of protozoa at time series station Helgoland Roads, North Sea, in 1998"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/FRAM_1/json/102a3e6d-10f0-577a-9ee1-e8d701160158.json b/oaitestdata/pangaea-datacite3/FRAM_1/json/102a3e6d-10f0-577a-9ee1-e8d701160158.json
deleted file mode 100644
index b68daa5d..00000000
--- a/oaitestdata/pangaea-datacite3/FRAM_1/json/102a3e6d-10f0-577a-9ee1-e8d701160158.json
+++ /dev/null
@@ -1,69 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "application/zip"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.887882"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Collection of Datasets"
-    ],
-    "SpatialCoverage": "(71N-89N,117W-89E)",
-    "TempCoverageBegin": 63507754799,
-    "TempCoverageEnd": 63507754799,
-    "TemporalCoverage": " point in time : 2013-06-25T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2013-06-25T11:59:59Z",
-    "TemporalCoverage:EndDate": "2013-06-25T11:59:59Z",
-    "author": [
-        "Petersen, Imke",
-        "Lalande, Catherine",
-        "Lorenzen, Christiane",
-        "Kn\u00fcppel, Nadine",
-        "Winkler, Maria",
-        "Strache, Anique",
-        "Bauerfeind, Eduard",
-        "N\u00f6thig, Eva-Maria",
-        "Bonk, Elizabeth",
-        "Schr\u00f6ter, Franz",
-        "Jacobs, Mirta"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.887882;2018-04-24T14:07:23Z;FRAM;https://doi.pangaea.de/10.1594/PANGAEA.887882;N\u00f6thig, Eva-Maria;0000-0002-7527-7827;Bauerfeind, Eduard;Lorenzen, Christiane;Lalande, Catherine;Kn\u00fcppel, Nadine;Winkler, Maria;Bonk, Elizabeth;Strache, Anique;Jacobs, Mirta;Petersen, Imke;Schr\u00f6ter, Franz;Chlorophyll a in Arctic Ocean, Fram Strait, and Greenland Sea 2013 - 2016;PANGAEA - Data Publisher for Earth & Environmental Science;2018;Hausgarten;Biological Oceanography @ AWI (AWI_BioOce);FRontiers in Arctic marine Monitoring (FRAM);Long-term Investigation at AWI-Hausgarten off Svalbard (Hausgarten);Alfred Wegener Institute, Helmholtz Center for Polar and Marine Research, Bremerhaven;2013-06-25T10:58:00/2016-10-18T15:40:00;eng;Collection of Datasets;10.3389/fmars.2017.00166;10.1038/s41598-017-04106-9;10.1594/PANGAEA.855814;7 datasets;application/zip;70.99967 -116.83033 89.16667 88.50694200000001",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.887882"
-    ],
-    "oai_set": [
-        "FRAM"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-116.83033,70.99967],[-116.83033,89.16667],[88.50694200000001,89.16667],[88.50694200000001,70.99967],[-116.83033,70.99967]]]}",
-    "tags": [
-        {
-            "name": "Biological Oceanography AWI AWI_BioOce"
-        },
-        {
-            "name": "FRontiers Arctic marine Monitoring FRAM"
-        },
-        {
-            "name": "Long-term Investigation AWI-Hausgarten Svalbard Hausgarten"
-        }
-    ],
-    "title": [
-        "Chlorophyll a in Arctic Ocean, Fram Strait, and Greenland Sea 2013 - 2016"
-    ],
-    "url": "https://doi.pangaea.de/10.1594/PANGAEA.887882"
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/FRAM_1/json/471fb3c4-4e37-589d-8c70-c9e2dcbe984e.json b/oaitestdata/pangaea-datacite3/FRAM_1/json/471fb3c4-4e37-589d-8c70-c9e2dcbe984e.json
deleted file mode 100644
index 279aa0c1..00000000
--- a/oaitestdata/pangaea-datacite3/FRAM_1/json/471fb3c4-4e37-589d-8c70-c9e2dcbe984e.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.887846"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(79N-80N,3 W-11E)",
-    "TempCoverageBegin": 63573332399,
-    "TempCoverageEnd": 63573332399,
-    "TemporalCoverage": " point in time : 2015-07-24T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2015-07-24T11:59:59Z",
-    "TemporalCoverage:EndDate": "2015-07-24T11:59:59Z",
-    "author": [
-        "N\u00f6thig, Eva-Maria",
-        "Bonk, Elizabeth",
-        "Kn\u00fcppel, Nadine"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.887846;2018-05-31T15:09:53Z;FRAM;https://doi.pangaea.de/10.1594/PANGAEA.887846;N\u00f6thig, Eva-Maria;0000-0002-7527-7827;Kn\u00fcppel, Nadine;Bonk, Elizabeth;Chlorophyll a measured on water bottle samples during POLARSTERN cruise PS93.2 (ARK-XXIX/2.2);PANGAEA - Data Publisher for Earth & Environmental Science;2018;Hausgarten;Event label;Optional event label;Date/Time of event;Latitude of event;Longitude of event;Elevation of event;DEPTH, water;Chlorophyll a;PS93.2;Polarstern;Biological Oceanography @ AWI (AWI_BioOce);FRontiers in Arctic marine Monitoring (FRAM);Long-term Investigation at AWI-Hausgarten off Svalbard (Hausgarten);Alfred Wegener Institute, Helmholtz Center for Polar and Marine Research, Bremerhaven;2015-07-24T15:59:00/2015-08-12T05:08:00;eng;Dataset;https://doi.pangaea.de/10.1594/PANGAEA.887882;10.3389/fmars.2017.00166;10.1594/PANGAEA.883759;10.1594/PANGAEA.884130;10.2312/BzPM_0693_2015;10.1594/PANGAEA.863807;10.1594/PANGAEA.863808;102 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);78.599 -2.70933 79.93833 11.08783",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.887846"
-    ],
-    "oai_set": [
-        "FRAM"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-2.70933,78.599],[-2.70933,79.93833],[11.08783,79.93833],[11.08783,78.599],[-2.70933,78.599]]]}",
-    "tags": [
-        {
-            "name": "PS."
-        },
-        {
-            "name": "Polarstern"
-        },
-        {
-            "name": "Biological Oceanography AWI AWI_BioOce"
-        },
-        {
-            "name": "FRontiers Arctic marine Monitoring FRAM"
-        },
-        {
-            "name": "Long-term Investigation AWI-Hausgarten Svalbard Hausgarten"
-        }
-    ],
-    "title": [
-        "Chlorophyll a measured on water bottle samples during POLARSTERN cruise PS93.2 (ARK-XXIX/2.2)"
-    ],
-    "url": "https://doi.pangaea.de/10.1594/PANGAEA.887846"
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/FRAM_1/json/670a1540-2f5c-56a6-81cb-44639c3faff2.json b/oaitestdata/pangaea-datacite3/FRAM_1/json/670a1540-2f5c-56a6-81cb-44639c3faff2.json
deleted file mode 100644
index 2d8f2382..00000000
--- a/oaitestdata/pangaea-datacite3/FRAM_1/json/670a1540-2f5c-56a6-81cb-44639c3faff2.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.887840"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(77N-80N,16W-6 E)",
-    "TempCoverageBegin": 63538340399,
-    "TempCoverageEnd": 63538340399,
-    "TemporalCoverage": " point in time : 2014-06-14T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2014-06-14T11:59:59Z",
-    "TemporalCoverage:EndDate": "2014-06-14T11:59:59Z",
-    "author": [
-        "N\u00f6thig, Eva-Maria",
-        "Bonk, Elizabeth",
-        "Winkler, Maria"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.887840;2018-05-31T13:45:21Z;FRAM;https://doi.pangaea.de/10.1594/PANGAEA.887840;N\u00f6thig, Eva-Maria;0000-0002-7527-7827;Winkler, Maria;Bonk, Elizabeth;Chlorophyll a measured on water bottle samples during POLARSTERN cruise PS85 (ARK-XXVIII/2);PANGAEA - Data Publisher for Earth & Environmental Science;2018;Hausgarten;Event label;Optional event label;Date/Time of event;Latitude of event;Longitude of event;Elevation of event;DEPTH, water;Chlorophyll a;PS85;Polarstern;Biological Oceanography @ AWI (AWI_BioOce);FRontiers in Arctic marine Monitoring (FRAM);Long-term Investigation at AWI-Hausgarten off Svalbard (Hausgarten);Alfred Wegener Institute, Helmholtz Center for Polar and Marine Research, Bremerhaven;2014-06-14T14:00:00/2014-06-29T01:53:00;eng;Dataset;https://doi.pangaea.de/10.1594/PANGAEA.887882;10.1038/s41598-017-04106-9;10.1594/PANGAEA.882217;10.1594/PANGAEA.837425;10.1594/PANGAEA.837427;10.2312/BzPM_0687_2015;88 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);77.38833 -16.30467 79.76033 6.0895",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.887840"
-    ],
-    "oai_set": [
-        "FRAM"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-16.30467,77.38833],[-16.30467,79.76033],[6.0895,79.76033],[6.0895,77.38833],[-16.30467,77.38833]]]}",
-    "tags": [
-        {
-            "name": "PS"
-        },
-        {
-            "name": "Polarstern"
-        },
-        {
-            "name": "Biological Oceanography AWI AWI_BioOce"
-        },
-        {
-            "name": "FRontiers Arctic marine Monitoring FRAM"
-        },
-        {
-            "name": "Long-term Investigation AWI-Hausgarten Svalbard Hausgarten"
-        }
-    ],
-    "title": [
-        "Chlorophyll a measured on water bottle samples during POLARSTERN cruise PS85 (ARK-XXVIII/2)"
-    ],
-    "url": "https://doi.pangaea.de/10.1594/PANGAEA.887840"
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/FRAM_1/json/848c7939-ebe7-5dc2-908d-f0a4f69d5244.json b/oaitestdata/pangaea-datacite3/FRAM_1/json/848c7939-ebe7-5dc2-908d-f0a4f69d5244.json
deleted file mode 100644
index 288511f5..00000000
--- a/oaitestdata/pangaea-datacite3/FRAM_1/json/848c7939-ebe7-5dc2-908d-f0a4f69d5244.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.887855"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(79N-80N,5 W-11E)",
-    "TempCoverageBegin": 63602449199,
-    "TempCoverageEnd": 63602449199,
-    "TemporalCoverage": " point in time : 2016-06-25T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2016-06-25T11:59:59Z",
-    "TemporalCoverage:EndDate": "2016-06-25T11:59:59Z",
-    "author": [
-        "N\u00f6thig, Eva-Maria",
-        "Lorenzen, Christiane",
-        "Kn\u00fcppel, Nadine"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.887855;2018-05-31T14:09:53Z;FRAM;https://doi.pangaea.de/10.1594/PANGAEA.887855;N\u00f6thig, Eva-Maria;0000-0002-7527-7827;Kn\u00fcppel, Nadine;Lorenzen, Christiane;Chlorophyll a measured on water bottle samples during POLARSTERN cruise PS99.2 (ARK-XXX/1.2);PANGAEA - Data Publisher for Earth & Environmental Science;2018;Hausgarten;Event label;Optional event label;Date/Time of event;Latitude of event;Longitude of event;Elevation of event;DEPTH, water;Chlorophyll a;PS99.2;Polarstern;Biological Oceanography @ AWI (AWI_BioOce);FRontiers in Arctic marine Monitoring (FRAM);Long-term Investigation at AWI-Hausgarten off Svalbard (Hausgarten);Alfred Wegener Institute, Helmholtz Center for Polar and Marine Research, Bremerhaven;2016-06-25T12:34:00/2016-07-10T20:45:00;eng;Dataset;https://doi.pangaea.de/10.1594/PANGAEA.887882;10.2312/BzPM_0704_2016;10.1594/PANGAEA.871949;10.1594/PANGAEA.871952;107 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);78.60783 -5.40933 79.92117 11.0925",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.887855"
-    ],
-    "oai_set": [
-        "FRAM"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-5.40933,78.60783],[-5.40933,79.92117],[11.0925,79.92117],[11.0925,78.60783],[-5.40933,78.60783]]]}",
-    "tags": [
-        {
-            "name": "PS."
-        },
-        {
-            "name": "Polarstern"
-        },
-        {
-            "name": "Biological Oceanography AWI AWI_BioOce"
-        },
-        {
-            "name": "FRontiers Arctic marine Monitoring FRAM"
-        },
-        {
-            "name": "Long-term Investigation AWI-Hausgarten Svalbard Hausgarten"
-        }
-    ],
-    "title": [
-        "Chlorophyll a measured on water bottle samples during POLARSTERN cruise PS99.2 (ARK-XXX/1.2)"
-    ],
-    "url": "https://doi.pangaea.de/10.1594/PANGAEA.887855"
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/FRAM_1/json/99eacce5-2984-588e-9ba3-f94c03978983.json b/oaitestdata/pangaea-datacite3/FRAM_1/json/99eacce5-2984-588e-9ba3-f94c03978983.json
deleted file mode 100644
index 17bbcdcf..00000000
--- a/oaitestdata/pangaea-datacite3/FRAM_1/json/99eacce5-2984-588e-9ba3-f94c03978983.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.887837"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "SpatialCoverage": "(79N-80N,4 E-11E)",
-    "TempCoverageBegin": 63507754799,
-    "TempCoverageEnd": 63507754799,
-    "TemporalCoverage": " point in time : 2013-06-25T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2013-06-25T11:59:59Z",
-    "TemporalCoverage:EndDate": "2013-06-25T11:59:59Z",
-    "author": [
-        "Bauerfeind, Eduard",
-        "N\u00f6thig, Eva-Maria",
-        "Lalande, Catherine"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.887837;2018-05-31T15:37:19Z;FRAM;https://doi.pangaea.de/10.1594/PANGAEA.887837;N\u00f6thig, Eva-Maria;0000-0002-7527-7827;Bauerfeind, Eduard;Lalande, Catherine;Chlorophyll a measured on water bottle samples during Maria S. Merian cruise MSM29;PANGAEA - Data Publisher for Earth & Environmental Science;2018;Hausgarten;Event label;Optional event label;Date/Time of event;Latitude of event;Longitude of event;Elevation of event;DEPTH, water;Chlorophyll a;MSM29;Maria S. Merian;Biological Oceanography @ AWI (AWI_BioOce);FRontiers in Arctic marine Monitoring (FRAM);Long-term Investigation at AWI-Hausgarten off Svalbard (Hausgarten);Alfred Wegener Institute, Helmholtz Center for Polar and Marine Research, Bremerhaven;2013-06-25T10:58:00/2013-07-09T01:25:00;eng;Dataset;https://doi.pangaea.de/10.1594/PANGAEA.887882;10.1594/PANGAEA.834685;10.2312/cr_msm29;10.1594/PANGAEA.819391;66 data points;text/tab-separated-values;78.62 4.33983 79.71617 11.0885",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.887837"
-    ],
-    "oai_set": [
-        "FRAM"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[4.33983,78.62],[4.33983,79.71617],[11.0885,79.71617],[11.0885,78.62],[4.33983,78.62]]]}",
-    "tags": [
-        {
-            "name": "MSM"
-        },
-        {
-            "name": "Maria S. Merian"
-        },
-        {
-            "name": "Biological Oceanography AWI AWI_BioOce"
-        },
-        {
-            "name": "FRontiers Arctic marine Monitoring FRAM"
-        },
-        {
-            "name": "Long-term Investigation AWI-Hausgarten Svalbard Hausgarten"
-        }
-    ],
-    "title": [
-        "Chlorophyll a measured on water bottle samples during Maria S. Merian cruise MSM29"
-    ],
-    "url": "https://doi.pangaea.de/10.1594/PANGAEA.887837"
-}
\ No newline at end of file
diff --git a/oaitestdata/pangaea-datacite3/FRAM_1/json/ade71e88-1b4e-5b6a-adc9-68bb934ed7d2.json b/oaitestdata/pangaea-datacite3/FRAM_1/json/ade71e88-1b4e-5b6a-adc9-68bb934ed7d2.json
deleted file mode 100644
index 5ad3568f..00000000
--- a/oaitestdata/pangaea-datacite3/FRAM_1/json/ade71e88-1b4e-5b6a-adc9-68bb934ed7d2.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.6",
-        "Geosciences",
-        "Earth System Research"
-    ],
-    "Discipline": "Earth System Research",
-    "Format": [
-        "text/tab-separated-values"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetadataAccess": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.887859"
-    ],
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "PANGAEA - Data Publisher for Earth & Environmental Science"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Creative Commons Attribution 3.0 Unported (CC-BY)"
-    ],
-    "SpatialCoverage": "(83N-87N,13E-62E)",
-    "TempCoverageBegin": 63609533999,
-    "TempCoverageEnd": 63609533999,
-    "TemporalCoverage": " point in time : 2016-09-15T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2016-09-15T11:59:59Z",
-    "TemporalCoverage:EndDate": "2016-09-15T11:59:59Z",
-    "author": [
-        "Jacobs, Mirta",
-        "N\u00f6thig, Eva-Maria",
-        "Lorenzen, Christiane",
-        "Strache, Anique"
-    ],
-    "fulltext": "oai:pangaea.de:doi:10.1594/PANGAEA.887859;2018-05-31T14:49:19Z;FRAM;https://doi.pangaea.de/10.1594/PANGAEA.887859;N\u00f6thig, Eva-Maria;0000-0002-7527-7827;Strache, Anique;Jacobs, Mirta;Lorenzen, Christiane;Chlorophyll a measured on water bottle samples during POLARSTERN cruise PS101 (ARK-XXX/3);PANGAEA - Data Publisher for Earth & Environmental Science;2018;Event label;Date/Time of event;Latitude of event;Longitude of event;Elevation of event;DEPTH, water;Chlorophyll a;PS101;Polarstern;Biological Oceanography @ AWI (AWI_BioOce);FRontiers in Arctic marine Monitoring (FRAM);Alfred Wegener Institute, Helmholtz Center for Polar and Marine Research, Bremerhaven;2016-09-15T10:07:00/2016-10-15T07:16:00;eng;Dataset;https://doi.pangaea.de/10.1594/PANGAEA.887882;10.2312/BzPM_0706_2017;10.1594/PANGAEA.871926;10.1594/PANGAEA.871927;60 data points;text/tab-separated-values;Creative Commons Attribution 3.0 Unported (CC-BY);82.88467 13.03183 87.10467 61.83767",
-    "oai_identifier": [
-        "oai:pangaea.de:doi:10.1594/PANGAEA.887859"
-    ],
-    "oai_set": [
-        "FRAM"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[13.03183,82.88467],[13.03183,87.10467],[61.83767,87.10467],[61.83767,82.88467],[13.03183,82.88467]]]}",
-    "tags": [
-        {
-            "name": "PS"
-        },
-        {
-            "name": "Polarstern"
-        },
-        {
-            "name": "Biological Oceanography AWI AWI_BioOce"
-        },
-        {
-            "name": "FRontiers Arctic marine Monitoring FRAM"
-        }
-    ],
-    "title": [
-        "Chlorophyll a measured on water bottle samples during POLARSTERN cruise PS101 (ARK-XXX/3)"
-    ],
-    "url": "https://doi.pangaea.de/10.1594/PANGAEA.887859"
-}
\ No newline at end of file
diff --git a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/00b55923-23ef-53df-b910-50d911ff6b97.json b/oaitestdata/pdc-fgdc/PDCMetadata_1/json/00b55923-23ef-53df-b910-50d911ff6b97.json
deleted file mode 100644
index 313eebc8..00000000
--- a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/00b55923-23ef-53df-b910-50d911ff6b97.json
+++ /dev/null
@@ -1,91 +0,0 @@
-{
-    "Contact": [
-        "dbarber@cc.umanitoba.ca"
-    ],
-    "Contributor": [
-        "University of Manitoba"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MapperVersion": [
-        "Balloon launches carrying the rawinsonde instrumentation were made at least once per day to provide continuous physical sampling of the troposphere.  Balloon launches were also used to profile low-pressure systems, cyclones, and periods of significant warm or cold-air advection aloft.  Radiosonde data provides a high-frequency sample of atmospheric temperature, humidity, wind speed and direction, and geopotential height.  These data are also used to validate the performance of our ship-based MicroWave atmospheric Radiometer Profiler (MWRP)."
-    ],
-    "MetaDataAccess": "http://www.polardata.ca/oai/provider?verb=GetRecord&metadataPrefix=fgdc&identifier=10527_fgdc",
-    "PublicationTimestamp": "2013-04-15T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "Rights": [
-        "Limited"
-    ],
-    "SpatialCoverage": "(70N-74N,135W-120W)",
-    "TempCoverageBegin": 63332107199,
-    "TempCoverageEnd": 63353789999,
-    "TemporalCoverage": " period : ( 2007-12-01T11:59:59Z - 2008-08-08T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2007-12-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2008-08-08T11:59:59Z",
-    "author": [
-        "Lauren Candlish",
-        "David Barber",
-        "Matthew Asplin"
-    ],
-    "fulltext": "10527_fgdc;2017-04-09T22:02:17Z;PDCMetadata;David Barber;David Barber;Lauren Candlish;Matthew Asplin;20130415;Rawinsonde atmospheric profiles in the southern Beaufort Sea during the IPY Circumpolar Flaw Lead (CFL) study 2007-2008;Computer file;unknown;D. Barber et al., Unpublished data;unavailable;https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=10527;Data are transmitted at a rate of one message per second via VHF radio (~400.00MHz).  Each data message reports a value for pressure, temperature and humidity data (raw PTU data).  GPS strings are also transmitted and are used to calculate upper-level wind speed and direction.  All radiosonde data files are exported as a raw time series which will require quality assurance and post-processing.  Furthermore, an ongoing problem with the paired humidity sensors will need to be checked and rectified if necessary.    &#x0d;\nBefore launch, the radiosonde's temperature, pressure and humidity sensors are calibrated using the Vaisala ground station calibration unit.  Surface meteorological observations are also noted and recorded for each launch.  Starting meteorological conditions are input into the sounding including: sea level pressure, air temperature, relative humidity, and wind speed and direction.  If a large closed low pressure system is affecting the region, the sampling interval is increased to 6-hourly, otherwise launches are typically limited to one per day, or less.;Balloon launches carrying the rawinsonde instrumentation were made at least once per day to provide continuous physical sampling of the troposphere.  Balloon launches were also used to profile low-pressure systems, cyclones, and periods of significant warm or cold-air advection aloft.  Radiosonde data provides a high-frequency sample of atmospheric temperature, humidity, wind speed and direction, and geopotential height.  These data are also used to validate the performance of our ship-based MicroWave atmospheric Radiometer Profiler (MWRP).;Summary: Not Applicable Research Program(s): IPY. For further information: dbarber@cc.umanitoba.ca;20071201;20080808;NULL;Complete;As needed;-135;-120;74;70;NULL;Atmosphere;Beaufort Sea;Humidity;Pressure;Radio telemetry;Temperature;Weather;Wind speed;Southern Beaufort Sea, Canadian Arctic;NULL;Limited;NULL;University of Manitoba;David  Barber;NULL;mailing;476 Wallace Building, University of Manitoba;Winnipeg;MB;R3T2N2;Canada;204-474-6981;204-272-1532;dbarber@cc.umanitoba.ca;NULL;Polar Data Catalogue;Canadian Cryospheric Information Network;Director;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;10527;Research programs, CCIN, or ArcticNet take no liability for the use or transmission of this data;20130415;20130415;David  Barber;University of Manitoba;mailing;476 Wallace Building, University of Manitoba;Winnipeg;MB;R3T2N2;Canada;204-474-6981;204-272-1532;dbarber@cc.umanitoba.ca;FGDC Content Standards for Digital Geospatial Metadata;FGDC-STD-001-1998",
-    "group": "pdc",
-    "groups": [
-        {
-            "name": "pdc"
-        }
-    ],
-    "name": "00b55923-23ef-53df-b910-50d911ff6b97",
-    "notes": [
-        "Data are transmitted at a rate of one message per second via VHF radio (~400.00MHz).  Each data message reports a value for pressure, temperature and humidity data (raw PTU data).  GPS strings are also transmitted and are used to calculate upper-level wind speed and direction.  All radiosonde data files are exported as a raw time series which will require quality assurance and post-processing.  Furthermore, an ongoing problem with the paired humidity sensors will need to be checked and rectified if necessary.    &#x0d;\nBefore launch, the radiosonde's temperature, pressure and humidity sensors are calibrated using the Vaisala ground station calibration unit.  Surface meteorological observations are also noted and recorded for each launch.  Starting meteorological conditions are input into the sounding including: sea level pressure, air temperature, relative humidity, and wind speed and direction.  If a large closed low pressure system is affecting the region, the sampling interval is increased to 6-hourly, otherwise launches are typically limited to one per day, or less."
-    ],
-    "oai_identifier": [
-        "10527_fgdc"
-    ],
-    "oai_set": [
-        "PDCMetadata"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-135,70],[-135,74],[-120,74],[-120,70],[-135,70]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Atmosphere"
-        },
-        {
-            "name": "Beaufort Sea"
-        },
-        {
-            "name": "Humidity"
-        },
-        {
-            "name": "Pressure"
-        },
-        {
-            "name": "Radio telemetry"
-        },
-        {
-            "name": "Temperature"
-        },
-        {
-            "name": "Weather"
-        },
-        {
-            "name": "Wind speed"
-        }
-    ],
-    "title": [
-        "Rawinsonde atmospheric profiles in the southern Beaufort Sea during the IPY Circumpolar Flaw Lead (CFL) study 2007-2008"
-    ],
-    "url": "https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=10527"
-}
\ No newline at end of file
diff --git a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/00c0e8de-ddce-56d0-bdf3-0eb5f687bb49.json b/oaitestdata/pdc-fgdc/PDCMetadata_1/json/00c0e8de-ddce-56d0-bdf3-0eb5f687bb49.json
deleted file mode 100644
index 4c0446ac..00000000
--- a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/00c0e8de-ddce-56d0-bdf3-0eb5f687bb49.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "adaptation@aadnc-aandc.gc.ca"
-    ],
-    "Contributor": [
-        "Aboriginal Affairs and Northern Development Canada"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MapperVersion": [
-        "The goal of this multi-year project was to provide Yukon-decision makers with essential information regarding climate change impacts and projected changes in a central and accessible manner to enable informed decisions regarding adaptation in Yukon. The overall objectives for this project were: (1) to gather historical and current climatic data to determine gaps in knowledge and monitoring; (2) to determine the key indicators of climate change in Yukon; (3) to support the development of regional climate change scenarios in Yukon; and (4) to communicate results and scenario information to decision makers, communities, and other stakeholders. Focus was placed on building capacity in Yukon in the first year and was directed at the inventory of knowledge and analysis components of the project in the second year. As for the third year, this project aimed to aid in climate change research and adaptation planning by providing an information database essential to the future development of Yukon climate change scenarios"
-    ],
-    "MetaDataAccess": "http://www.polardata.ca/oai/provider?verb=GetRecord&metadataPrefix=fgdc&identifier=11482_fgdc",
-    "PublicationTimestamp": "2015-03-03T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "Rights": [
-        "Public"
-    ],
-    "SpatialCoverage": "(60N-70N,141W-124W)",
-    "TempCoverageBegin": 63342644399,
-    "TempCoverageEnd": 63437165999,
-    "TemporalCoverage": " period : ( 2008-04-01T11:59:59Z - 2011-03-31T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2008-04-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2011-03-31T11:59:59Z",
-    "author": [
-        "Government of Yukon"
-    ],
-    "fulltext": "11482_fgdc;2017-04-09T22:02:25Z;PDCMetadata;FGDC_Yukon;Government of Yukon;Government of Yukon;20150303;Supporting the Development of Climate Change Scenarios;Computer file;unknown;Government of Yukon, Council of Yukon First Nations, and Yukon College. (2010). Gap Analysis: Monthly Weather Measurements from Environment Canada's National Climate Data and Information Archive. Climate Change Scenarios Network.;unavailable;https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=11482;To improve capacity, a technical analyst worked with an expert scenario agency, drawing from the agency's expertise and training on the subject of climate change scenario development and on the scenario server from the Canadian Climate Change Scenarios Network (CCCSN). An inventory of knowledge was started (to be built upon in upcoming years) on scientific, weather, climate and meteorological data, creating a baseline to be assessed for scenario development. A database was created, collating temperature, precipitation, extreme weather, ice and snow cover, sea level rise, etc. data. &#x0d;\n&#x0d;\nFurthermore, to collate historical and current climatic data, records from industry, governments, academia, agencies, and public were examined for information concerning average temperature, precipitation, extreme precipitation events, total snowfall, days with snow, lake and river ice, growing season and sea level rise. A gap analysis was performed and adaptation needs were identified through the synthesis of previous work on community priorities and potential scenario users. In the second year of this project specifically, a project coordinator and a technical analyst worked in collaboration, bringing the science of climate change scenarios together with the needs of the communities and stakeholders. A workplan and a communication strategy focused on supplying decision-makers with scenario information were created. The inventory of climatic data was completed by a technical analyst, producing a final report, including gaps in knowledge and monitoring and an analysis of available data. &#x0d;\n&#x0d;\nFinally, the inventory of climate data was made available on the internet as the Collated Yukon Climatic Database. This information was synthesized to determine appropriate climate change indicators in Yukon to develop regional climate change scenarios. Workshops were held to communicate climate scenarios, adaptation strategies, and decision making benefits to stakeholders.;The goal of this multi-year project was to provide Yukon-decision makers with essential information regarding climate change impacts and projected changes in a central and accessible manner to enable informed decisions regarding adaptation in Yukon. The overall objectives for this project were: (1) to gather historical and current climatic data to determine gaps in knowledge and monitoring; (2) to determine the key indicators of climate change in Yukon; (3) to support the development of regional climate change scenarios in Yukon; and (4) to communicate results and scenario information to decision makers, communities, and other stakeholders. Focus was placed on building capacity in Yukon in the first year and was directed at the inventory of knowledge and analysis components of the project in the second year. As for the third year, this project aimed to aid in climate change research and adaptation planning by providing an information database essential to the future development of Yukon climate change scenarios;Summary: Not Applicable Research Program(s): APAN-AANDC - Adaptation Program for Aboriginals and Northerners. For further information: rebecca.world@gov.yk.ca;20080401;20110331;NULL;Complete;As needed;-141;-124;70;60;NULL;Adaptation;Climate change;Database;Scenarios;Yukon;Yukon Territory, Canada;NULL;Public;NULL;Aboriginal Affairs and Northern Development Canada;Martin Tremblay - PDC;NULL;mailing;25, Eddy;Gatineau;QC;K1A 0H4;Canada;(819) 934-9210;(819) 953-2590;adaptation@aadnc-aandc.gc.ca;NULL;Polar Data Catalogue;Canadian Cryospheric Information Network;Director;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;11482;Research programs, CCIN, or ArcticNet take no liability for the use or transmission of this data;20150303;20150303;Martin Tremblay - PDC;Aboriginal Affairs and Northern Development Canada;mailing;25, Eddy;Gatineau;QC;K1A 0H4;Canada;(819) 934-9210;(819) 953-2590;adaptation@aadnc-aandc.gc.ca;FGDC Content Standards for Digital Geospatial Metadata;FGDC-STD-001-1998",
-    "group": "pdc",
-    "groups": [
-        {
-            "name": "pdc"
-        }
-    ],
-    "name": "00c0e8de-ddce-56d0-bdf3-0eb5f687bb49",
-    "notes": [
-        "To improve capacity, a technical analyst worked with an expert scenario agency, drawing from the agency's expertise and training on the subject of climate change scenario development and on the scenario server from the Canadian Climate Change Scenarios Network (CCCSN). An inventory of knowledge was started (to be built upon in upcoming years) on scientific, weather, climate and meteorological data, creating a baseline to be assessed for scenario development. A database was created, collating temperature, precipitation, extreme weather, ice and snow cover, sea level rise, etc. data. &#x0d;\n&#x0d;\nFurthermore, to collate historical and current climatic data, records from industry, governments, academia, agencies, and public were examined for information concerning average temperature, precipitation, extreme precipitation events, total snowfall, days with snow, lake and river ice, growing season and sea level rise. A gap analysis was performed and adaptation needs were identified through the synthesis of previous work on community priorities and potential scenario users. In the second year of this project specifically, a project coordinator and a technical analyst worked in collaboration, bringing the science of climate change scenarios together with the needs of the communities and stakeholders. A workplan and a communication strategy focused on supplying decision-makers with scenario information were created. The inventory of climatic data was completed by a technical analyst, producing a final report, including gaps in knowledge and monitoring and an analysis of available data. &#x0d;\n&#x0d;\nFinally, the inventory of climate data was made available on the internet as the Collated Yukon Climatic Database. This information was synthesized to determine appropriate climate change indicators in Yukon to develop regional climate change scenarios. Workshops were held to communicate climate scenarios, adaptation strategies, and decision making benefits to stakeholders."
-    ],
-    "oai_identifier": [
-        "11482_fgdc"
-    ],
-    "oai_set": [
-        "PDCMetadata",
-        "FGDC_Yukon"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-141,60],[-141,70],[-124,70],[-124,60],[-141,60]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Adaptation"
-        },
-        {
-            "name": "Climate change"
-        },
-        {
-            "name": "Database"
-        },
-        {
-            "name": "Scenarios"
-        },
-        {
-            "name": "Yukon"
-        }
-    ],
-    "title": [
-        "Supporting the Development of Climate Change Scenarios"
-    ],
-    "url": "https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=11482"
-}
\ No newline at end of file
diff --git a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/00c17456-f4cd-5aed-bd97-d8b420f14009.json b/oaitestdata/pdc-fgdc/PDCMetadata_1/json/00c17456-f4cd-5aed-bd97-d8b420f14009.json
deleted file mode 100644
index 94bfbe3c..00000000
--- a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/00c17456-f4cd-5aed-bd97-d8b420f14009.json
+++ /dev/null
@@ -1,90 +0,0 @@
-{
-    "Contact": [
-        "daniel.fortier@umontreal.ca"
-    ],
-    "Contributor": [
-        "University of Montreal"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MapperVersion": [
-        "A detailed observation of a thermo-erosion gully was initiated on Bylot Island (Fortier, Allard et al. 2007) in 1999. Gully monitoring is a joint project with biologists (Gilles Gauthier - Laval University, Esther L\u00e9vesque - UQTR) working on arctic ecosystems where effects of gullying on the permafrost, available water, and the landscape were required to be known. Mapping of the gullies and the geomorphological forms found in these gullies contributed to the understanding of how thermo-erosion affect the permafrost, the speed of gullying growth and the distribution of thermo-erosion gullies.&#x0d;\n&#x0d;\nFor more information: Fortier, D., M. Allard, et al. (2007). \"Observation of rapid drainage system development by thermal erosion of ice wedges on Bylot island, Canadian Arctic Archipelago.\" Permafrost and Periglacial Processes 18(3): 229-243."
-    ],
-    "MetaDataAccess": "http://www.polardata.ca/oai/provider?verb=GetRecord&metadataPrefix=fgdc&identifier=10483_fgdc",
-    "PublicationTimestamp": "2014-10-08T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "Rights": [
-        "Public"
-    ],
-    "SpatialCoverage": "(73N-73N,80W-80W)",
-    "TempCoverageBegin": 63063831599,
-    "TempCoverageEnd": 63511124399,
-    "TemporalCoverage": " period : ( 1999-06-01T11:59:59Z - 2013-08-03T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1999-06-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2013-08-03T11:59:59Z",
-    "author": [
-        "Audrey Veillette",
-        "Na\u00efm Perreault",
-        "Alexandre Guertin Pasquier",
-        "Gabrielle L\u00e9tourneau",
-        "St\u00e9phanie Coulombe",
-        "Michel Allard",
-        "Etienne Godin",
-        "Daniel Fortier"
-    ],
-    "fulltext": "10483_fgdc;2017-04-09T22:02:17Z;PDCMetadata;Daniel Fortier;Etienne Godin;Alexandre Guertin Pasquier;Audrey Veillette;Gabrielle L\u00e9tourneau;Michel Allard;Na\u00efm Perreault;St\u00e9phanie Coulombe;20141008;Thermo-erosion gully GIS in Valley of glacier C-79 on Bylot Island, Nunavut;Computer file;unknown;Godin Etienne and Fortier Daniel, 2014. Thermo-erosion gully GIS in Valley of glacier C-79 on Bylot Island, NU, Canada. Geocryolab, Department of Geography, Universit\u00e9 de Montr\u00e9al, Qu\u00e9bec, Canada.;unavailable;https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=10483;Digitalisation of the thermo-erosion gullies was accomplished using a Trimble differential GPS (model Pathfinder Pro XRS with a TSC1 data collector). Differential correction was applied on surveyed data using GPS Pathfinder Office v3.10 against Thule (Greenland) base station with 99% of data with an error less than 1 m. A Trimble R8 GNSS system replaced the DGPS in 2013. Geomorphological and erosion forms found in the gullies as well as the gullies contours were mapped and entered into the DGPS spatial database during 2009 and 2010 surveys. Overall, 44 gullies were mapped. Data was exported to ESRI's ArcGIS v10. Superposition of the spatial data with historical air photos (1958. 1961, 1972, 1982) and an IKONOS 2007, GeoEYE 2010 high resolution satellite imagery provide background layers to quantify the surveyed geodata. Visual representation of the gullies GIS provides quantitative and qualitative data about permafrost erosion resulting in thermo-erosion at large and small scale.;A detailed observation of a thermo-erosion gully was initiated on Bylot Island (Fortier, Allard et al. 2007) in 1999. Gully monitoring is a joint project with biologists (Gilles Gauthier - Laval University, Esther L\u00e9vesque - UQTR) working on arctic ecosystems where effects of gullying on the permafrost, available water, and the landscape were required to be known. Mapping of the gullies and the geomorphological forms found in these gullies contributed to the understanding of how thermo-erosion affect the permafrost, the speed of gullying growth and the distribution of thermo-erosion gullies.&#x0d;\n&#x0d;\nFor more information: Fortier, D., M. Allard, et al. (2007). \"Observation of rapid drainage system development by thermal erosion of ice wedges on Bylot island, Canadian Arctic Archipelago.\" Permafrost and Periglacial Processes 18(3): 229-243.;Summary: Le projet d'observer \u00e0 fine \u00e9chelle les ravins de thermo-\u00e9rosion sur l'Ile Bylot (Nunavut) a commenc\u00e9 en 1999, conjointement avec une \u00e9quipe de de biologistes (Gilles Gauthier - Laval University, Esther L\u00e9vesque - UQTR). Un ravin observ\u00e9 depuis son initiation en 1999 \u00e9volue sur son axe principal \u00e0 une vitesse moyenne de 60 m par ann\u00e9e. 44 ravins semblables ont \u00e9t\u00e9 cartographi\u00e9s \u00e0 l'aide d'un GPS diff\u00e9rentiel dans la vall\u00e9e du glacier C-79 durant des visites sur le terrain en 2009 et 2010. La g\u00e9omorphologie et les contours des ravins ont ainsi \u00e9t\u00e9 num\u00e9ris\u00e9s. L'utilisation d'images a\u00e9riennes et satellitaires permettent de localiser les ravins \u00e0 visiter sur le terrain; ces images permettent de plus \u00e0 estimer le taux d'\u00e9volution de plusieurs ravins. L'ensemble des donn\u00e9es spatiales qui ont \u00e9t\u00e9 accumul\u00e9es durant les travaux de terrain fournissent des donn\u00e9es quantitatives et qualitatives sur la distribution des ravins de thermo-\u00e9rosion, \u00e0 petite et grande \u00e9chelle. Research Program(s): ArcticNet,IPY,CEN,ADAPT. For further information: daniel.fortier@umontreal.ca;19990601;20130803;NULL;In work;Annually;-80.15;-79.75;73.2;73.1;NULL;Bylot Island;Canadian High Arctic;Geomorphology;Geospatial data;Permafrost;Thermo-erosion gullies;Bylot Island, Nunavut, Canada;NULL;Public;NULL;University of Montreal;Daniel Fortier;NULL;mailing;520, ch. C\u00f4te-Ste-Catherine;Montreal;Quebec;H2V 2B8;Canada;514-343-6111 #26872;514-343-8008;daniel.fortier@umontreal.ca;NULL;Polar Data Catalogue;Canadian Cryospheric Information Network;Director;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;10483;Research programs, CCIN, or ArcticNet take no liability for the use or transmission of this data;20141008;20141008;Daniel Fortier;University of Montreal;mailing;520, ch. C\u00f4te-Ste-Catherine;Montreal;Quebec;H2V 2B8;Canada;514-343-6111 #26872;514-343-8008;daniel.fortier@umontreal.ca;FGDC Content Standards for Digital Geospatial Metadata;FGDC-STD-001-1998",
-    "group": "pdc",
-    "groups": [
-        {
-            "name": "pdc"
-        }
-    ],
-    "name": "00c17456-f4cd-5aed-bd97-d8b420f14009",
-    "notes": [
-        "Digitalisation of the thermo-erosion gullies was accomplished using a Trimble differential GPS (model Pathfinder Pro XRS with a TSC1 data collector). Differential correction was applied on surveyed data using GPS Pathfinder Office v3.10 against Thule (Greenland) base station with 99% of data with an error less than 1 m. A Trimble R8 GNSS system replaced the DGPS in 2013. Geomorphological and erosion forms found in the gullies as well as the gullies contours were mapped and entered into the DGPS spatial database during 2009 and 2010 surveys. Overall, 44 gullies were mapped. Data was exported to ESRI's ArcGIS v10. Superposition of the spatial data with historical air photos (1958. 1961, 1972, 1982) and an IKONOS 2007, GeoEYE 2010 high resolution satellite imagery provide background layers to quantify the surveyed geodata. Visual representation of the gullies GIS provides quantitative and qualitative data about permafrost erosion resulting in thermo-erosion at large and small scale."
-    ],
-    "oai_identifier": [
-        "10483_fgdc"
-    ],
-    "oai_set": [
-        "PDCMetadata"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-80.15,73.1],[-80.15,73.2],[-79.75,73.2],[-79.75,73.1],[-80.15,73.1]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Bylot Island"
-        },
-        {
-            "name": "Canadian High Arctic"
-        },
-        {
-            "name": "Geomorphology"
-        },
-        {
-            "name": "Geospatial data"
-        },
-        {
-            "name": "Permafrost"
-        },
-        {
-            "name": "Thermo-erosion gullies"
-        }
-    ],
-    "title": [
-        "Thermo-erosion gully GIS in Valley of glacier C-79 on Bylot Island, Nunavut"
-    ],
-    "url": "https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=10483"
-}
\ No newline at end of file
diff --git a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/00c9b61c-9acc-5ad2-876e-01bda7d3a51f.json b/oaitestdata/pdc-fgdc/PDCMetadata_1/json/00c9b61c-9acc-5ad2-876e-01bda7d3a51f.json
deleted file mode 100644
index f1ffb2f1..00000000
--- a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/00c9b61c-9acc-5ad2-876e-01bda7d3a51f.json
+++ /dev/null
@@ -1,99 +0,0 @@
-{
-    "Contact": [
-        "polardata@polar.gc.ca"
-    ],
-    "Contributor": [
-        "Polar Knowledge Canada (POLAR)"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MapperVersion": [
-        "The dataset focuses on vascular plants collected in support of an Ecology and Biodiversity of Cambridge Bay, Victoria Island, Nunavut project.The field work was confined to southeast Victoria Island, mostly within walking distance of the road network along the southeast island. Most field sessions were brief with the objective of gaining some initial observations. Collections were made for verification and in support of a core vascular plant reference collection for the Canadian High Arctic Research Station (CHARS) at Cambridge Bay, Nunavut."
-    ],
-    "MetaDataAccess": "http://www.polardata.ca/oai/provider?verb=GetRecord&metadataPrefix=fgdc&identifier=12438_fgdc",
-    "PublicationTimestamp": "2015-04-10T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "Rights": [
-        "Public"
-    ],
-    "SpatialCoverage": "(69N-69N,105W-104W)",
-    "TempCoverageBegin": 63509223599,
-    "TempCoverageEnd": 63509914799,
-    "TemporalCoverage": " period : ( 2013-07-12T11:59:59Z - 2013-07-20T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2013-07-12T11:59:59Z",
-    "TemporalCoverage:EndDate": "2013-07-20T11:59:59Z",
-    "author": [
-        "Wagner, Ioan",
-        "Meidinger, Del",
-        "Sullivan, Josh",
-        "Bennett, Bruce A.",
-        "MacKenzie, Will",
-        "Turner, Derek",
-        "McLennen, Donald",
-        "Kutz, Susan"
-    ],
-    "fulltext": "12438_fgdc;2017-04-09T22:02:43Z;PDCMetadata;Bennett, Bruce A.;McLennen, Donald;Kutz, Susan;MacKenzie, Will;Meidinger, Del;Sullivan, Josh;Turner, Derek;Wagner, Ioan;20150410;Ecology and Biodiversity of Cambridge Bay, Victoria Island, Nunavut - Results of Field Studies, Summer 2013;Computer file;unknown;Bennett, B.A. 2013. Vascular Plant Collections, B.A. Bennett Herbarium (BABY). unpublished.;unavailable;https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=12438;The dataset identifies vascular plant collections to subspecies or variety. Collection information includes collectors, location of collection, coordinates, collection date, associated species and habitat, herbaria where collections are house, identification and confirmation information, and additional notes.;The dataset focuses on vascular plants collected in support of an Ecology and Biodiversity of Cambridge Bay, Victoria Island, Nunavut project.The field work was confined to southeast Victoria Island, mostly within walking distance of the road network along the southeast island. Most field sessions were brief with the objective of gaining some initial observations. Collections were made for verification and in support of a core vascular plant reference collection for the Canadian High Arctic Research Station (CHARS) at Cambridge Bay, Nunavut.;Summary: Not applicable Research Program(s): POLAR/CHARS. For further information: brbennett@klondiker.com;20130712;20130720;NULL;In work;As needed;-105;-104;69;69;NULL;Abundance;Cambridge Bay;Conservation;Flora;Flowering plants;Taxonomy;Terrestrial ecosystem;Vascular plants;Victoria Island;Cambridge Bay and vicinity, se Victoria Island, Nunavut, Canada;NULL;Public;NULL;Polar Knowledge Canada (POLAR);Polar Knowledge Canada;NULL;mailing;360 Albert St., Suite 1710;Ottawa;Ontario;K1R 7X7;Canada;1-800-622-6232;polardata@polar.gc.ca;NULL;Polar Data Catalogue;Canadian Cryospheric Information Network;Director;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;12438;Research programs, CCIN, or ArcticNet take no liability for the use or transmission of this data;20150410;20150410;Polar Knowledge Canada;Polar Knowledge Canada (POLAR);mailing;360 Albert St., Suite 1710;Ottawa;Ontario;K1R 7X7;Canada;1-800-622-6232;polardata@polar.gc.ca;FGDC Content Standards for Digital Geospatial Metadata;FGDC-STD-001-1998",
-    "group": "pdc",
-    "groups": [
-        {
-            "name": "pdc"
-        }
-    ],
-    "name": "00c9b61c-9acc-5ad2-876e-01bda7d3a51f",
-    "notes": [
-        "The dataset identifies vascular plant collections to subspecies or variety. Collection information includes collectors, location of collection, coordinates, collection date, associated species and habitat, herbaria where collections are house, identification and confirmation information, and additional notes."
-    ],
-    "oai_identifier": [
-        "12438_fgdc"
-    ],
-    "oai_set": [
-        "PDCMetadata"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-105,69],[-105,69],[-104,69],[-104,69],[-105,69]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Abundance"
-        },
-        {
-            "name": "Cambridge Bay"
-        },
-        {
-            "name": "Conservation"
-        },
-        {
-            "name": "Flora"
-        },
-        {
-            "name": "Flowering plants"
-        },
-        {
-            "name": "Taxonomy"
-        },
-        {
-            "name": "Terrestrial ecosystem"
-        },
-        {
-            "name": "Vascular plants"
-        },
-        {
-            "name": "Victoria Island"
-        }
-    ],
-    "title": [
-        "Ecology and Biodiversity of Cambridge Bay, Victoria Island, Nunavut - Results of Field Studies, Summer 2013"
-    ],
-    "url": "https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=12438"
-}
\ No newline at end of file
diff --git a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0a047ed4-9e84-5802-8fd4-3ee59546ea7a.json b/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0a047ed4-9e84-5802-8fd4-3ee59546ea7a.json
deleted file mode 100644
index 19abdf14..00000000
--- a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0a047ed4-9e84-5802-8fd4-3ee59546ea7a.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "chris.derksen@ec.gc.ca"
-    ],
-    "Contributor": [
-        "Environment Canada"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.1002/2015JC011464.",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MapperVersion": [
-        "Monthly ice motion fields for the Beaufort Sea are derived from the existing operational image archive of RADARSAT imagery combined with a new ice tracking algorithm. These motion estimates will be used to quantify sea ice dynamics within the Beaufort Sea region, in order to provide meaningful baseline information as well as identify the observed variability, trends, and extreme events. This high resolution, satellite-derived ice motion information will also serve to evaluate a new regional sea ice forecasting system in preparation for operational implementation at Environment Canada."
-    ],
-    "MetaDataAccess": "http://www.polardata.ca/oai/provider?verb=GetRecord&metadataPrefix=fgdc&identifier=11796_fgdc",
-    "PublicationTimestamp": "2017-02-03T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "Rights": [
-        "Public"
-    ],
-    "SpatialCoverage": "(68N-80N,164W-117W)",
-    "TempCoverageBegin": 62987716799,
-    "TempCoverageEnd": 63550353599,
-    "TemporalCoverage": " period : ( 1997-01-01T11:59:59Z - 2014-10-31T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1997-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2014-10-31T11:59:59Z",
-    "author": [
-        "Howell, Stephen",
-        "Derksen, Chris",
-        "Brady, Mike"
-    ],
-    "fulltext": "11796_fgdc;2017-04-09T22:02:32Z;PDCMetadata;Derksen, Chris;Howell, Stephen;Brady, Mike;20170203;RADARSAT derived monthly ice motion estimates for the Beaufort Sea, 1997-2014;Computer file;unknown;Howell, S. E. L., M. Brady, C. Derksen, and R. E. J. Kelly (2016), Recent changes in sea ice area flux through the Beaufort Sea during the summer, J. Geophys. Res. Oceans, 121, 2659\u20132672, doi:10.1002/2015JC011464.;unavailable;https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=11796;Ice motion estimates were derived from RADARSAT-1 and RADARSAT-2 ScanSAR imagery using the Canadian Ice Service Automated Sea Ice Tracking System (CIS-ASITS). The system applies a combination of cross-correlation and phase-correlation methods of feature tracking to sequential SAR-image pairs. Ice drift vectors of varying confidence levels are produced from examining the image pairs at multiple resolution levels. Estimates were gridded at 200 m pixel resolution and organized by month. Using outputs produced by the CIS-ASITS process, bearing and speed were calculated to produce velocity data. Ice velocity map products were generated by bi-linearly interpolating the monthly estimates to 5km and 25km grids.;Monthly ice motion fields for the Beaufort Sea are derived from the existing operational image archive of RADARSAT imagery combined with a new ice tracking algorithm. These motion estimates will be used to quantify sea ice dynamics within the Beaufort Sea region, in order to provide meaningful baseline information as well as identify the observed variability, trends, and extreme events. This high resolution, satellite-derived ice motion information will also serve to evaluate a new regional sea ice forecasting system in preparation for operational implementation at Environment Canada.;Summary: Sea ice within the Beaufort Sea region circulates according to the pre-dominantly anti-cyclonic Beaufort Gyre, but very little quantitative information about sea ice motion exists. Sea ice motion products were derived for the Beaufort Sea region using the Canadian Ice Service's (CIS) operational archive of RADARSAT-1 and RADARSAT-2 imagery and Environment Canada's new sea ice motion tracking algorithm. This analysis fills a considerable knowledge gap with respect to sea ice dynamics in the Beaufort Sea region. The results of this analysis will establish a baseline sea ice motion dataset which can be used for sea ice and climate model validation, and to plan and support future offshore operations. Research Program(s): BREA. For further information: Chris.Derksen@ec.gc.ca;19970101;20141031;NULL;In work;As needed;-164;-117;80;68;NULL;Beaufort Sea;Motion;RADARSAT;SAR;Sea ice;Beaufort Sea / Mer de Beaufort / CGNDB: LACKU;NULL;Public;NULL;Environment Canada;Chris Derksen;NULL;mailing;4905 Dufferin Street;Toronto;ON;M3H5T4;Canada;416-739-5804;416-739-5700;chris.derksen@ec.gc.ca;NULL;Polar Data Catalogue;Canadian Cryospheric Information Network;Director;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;11796;Research programs, CCIN, or ArcticNet take no liability for the use or transmission of this data;20131007;20170203;Chris Derksen;Environment Canada;mailing;4905 Dufferin Street;Toronto;ON;M3H5T4;Canada;416-739-5804;416-739-5700;chris.derksen@ec.gc.ca;FGDC Content Standards for Digital Geospatial Metadata;FGDC-STD-001-1998",
-    "group": "pdc",
-    "groups": [
-        {
-            "name": "pdc"
-        }
-    ],
-    "name": "0a047ed4-9e84-5802-8fd4-3ee59546ea7a",
-    "notes": [
-        "Ice motion estimates were derived from RADARSAT-1 and RADARSAT-2 ScanSAR imagery using the Canadian Ice Service Automated Sea Ice Tracking System (CIS-ASITS). The system applies a combination of cross-correlation and phase-correlation methods of feature tracking to sequential SAR-image pairs. Ice drift vectors of varying confidence levels are produced from examining the image pairs at multiple resolution levels. Estimates were gridded at 200 m pixel resolution and organized by month. Using outputs produced by the CIS-ASITS process, bearing and speed were calculated to produce velocity data. Ice velocity map products were generated by bi-linearly interpolating the monthly estimates to 5km and 25km grids."
-    ],
-    "oai_identifier": [
-        "11796_fgdc"
-    ],
-    "oai_set": [
-        "PDCMetadata"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-164,68],[-164,80],[-117,80],[-117,68],[-164,68]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Beaufort Sea"
-        },
-        {
-            "name": "Motion"
-        },
-        {
-            "name": "RADARSAT"
-        },
-        {
-            "name": "SAR"
-        },
-        {
-            "name": "Sea ice"
-        }
-    ],
-    "title": [
-        "RADARSAT derived monthly ice motion estimates for the Beaufort Sea, 1997-2014"
-    ],
-    "url": "https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=11796"
-}
\ No newline at end of file
diff --git a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0a1fe09a-30fe-5f0f-af38-fbc4611c6249.json b/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0a1fe09a-30fe-5f0f-af38-fbc4611c6249.json
deleted file mode 100644
index 6cd93955..00000000
--- a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0a1fe09a-30fe-5f0f-af38-fbc4611c6249.json
+++ /dev/null
@@ -1,89 +0,0 @@
-{
-    "Contact": [
-        "john.huck@ualberta.ca"
-    ],
-    "Contributor": [
-        "University of Alberta Libraries"
-    ],
-    "DOI": "http://dx.doi.org/10.5443/11278",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MapperVersion": [
-        "Trace elements are chemicals that occur at very low concentrations, but play a role in the carbon cycle, marine ecosystems, and contaminant and climate processes of the oceans. This project is looking at the distribution and processes relating to trace elements in the Arctic Ocean. Specifically, how trace elements interact with changes in temperature, sea-ice cover, fresh water discharge, marine ecosystem structure and carbon sequestration capacity of the Arctic Ocean are being studied."
-    ],
-    "MetaDataAccess": "http://www.polardata.ca/oai/provider?verb=GetRecord&metadataPrefix=fgdc&identifier=11278_fgdc",
-    "PublicationTimestamp": "2012-10-11T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "Rights": [
-        "Public"
-    ],
-    "SpatialCoverage": "(69N-76N,144W-132W)",
-    "TempCoverageBegin": 63386967599,
-    "TempCoverageEnd": 63388349999,
-    "TemporalCoverage": " period : ( 2009-08-27T11:59:59Z - 2009-09-12T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2009-08-27T11:59:59Z",
-    "TemporalCoverage:EndDate": "2009-09-12T11:59:59Z",
-    "author": [
-        "Jean-Eric Tremblay",
-        "Jonathan Gagnon",
-        "Roger Francois"
-    ],
-    "fulltext": "11278_fgdc;2017-04-09T22:02:23Z;PDCMetadata;Roger Francois;Jean-Eric Tremblay;Jonathan Gagnon;Roger Francois;20121011;Nitrate, nitrite, phosphate, dissolved silica concentrations (micromol/L) measured in the Beaufort Sea  on multiple casts at 8 stations in 2009;Computer file;unknown;Tremblay, Jean-Eric, Roger Francois, and Jonathan Gagnon, 2012, Nitrate, nitrite, phosphate, dissolved silica concentrations (micromol/L) measured in the Beaufort Sea  on multiple casts at 8 stations in 2009. Canadian Cryospheric Information Network / International Polar Year Data Assembly Centre Network. http://dx.doi.org/10.5443/11278;unavailable;https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=11278;The concentrations of dissolved nutrients (nitrate, nitrate, phosphate, and dissolved silica) were measured on board ship with a nutrient autoanalyzer to complement the hydrographic data. They were measured on samples collected with the Trace Metal Clean Rosette at Station L1 (71\u00b006'N, 139\u00b010'W), L1.5 (73\u00b019'N, 139\u00b023'W), L2 (74\u00b030'N, 137\u00b000'W, L3 (75\u00b017'N, 137\u00b030'W), L1.1 (72\u00b031'N, 136\u00b041'), and S4 (71\u00b011'N, 132\u00b057'W) and on samples collected with the regular ArcticNet rosette at station S1 (69\u00b030'N, 137\u00b059'W), S2 (70\u00b000'N, 138\u00b030'W), L1, L2, L3, and L1.1;Trace elements are chemicals that occur at very low concentrations, but play a role in the carbon cycle, marine ecosystems, and contaminant and climate processes of the oceans. This project is looking at the distribution and processes relating to trace elements in the Arctic Ocean. Specifically, how trace elements interact with changes in temperature, sea-ice cover, fresh water discharge, marine ecosystem structure and carbon sequestration capacity of the Arctic Ocean are being studied.;Summary: Not Applicable Research Program(s): IPY. For further information: rfrancoi@eos.ubc.ca;20090827;20090912;NULL;In work;Unknown;-144;-132;76;69;NULL;Arctic Ocean;Beaufort Sea;Nitrates;Nutrients;Phosphorus;Silica;Water column;Beaufort Sea;NULL;Public;NULL;University of Alberta Libraries;Metadata Librarian;NULL;mailing;Cameron Library;Edmonton;Alberta;T6G 2J8;Canada;(780) 248-1337;john.huck@ualberta.ca;NULL;Polar Data Catalogue;Canadian Cryospheric Information Network;Director;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;11278;Research programs, CCIN, or ArcticNet take no liability for the use or transmission of this data;20121011;20121011;Metadata Librarian;University of Alberta Libraries;mailing;Cameron Library;Edmonton;Alberta;T6G 2J8;Canada;(780) 248-1337;john.huck@ualberta.ca;FGDC Content Standards for Digital Geospatial Metadata;FGDC-STD-001-1998",
-    "group": "pdc",
-    "groups": [
-        {
-            "name": "pdc"
-        }
-    ],
-    "name": "0a1fe09a-30fe-5f0f-af38-fbc4611c6249",
-    "notes": [
-        "The concentrations of dissolved nutrients (nitrate, nitrate, phosphate, and dissolved silica) were measured on board ship with a nutrient autoanalyzer to complement the hydrographic data. They were measured on samples collected with the Trace Metal Clean Rosette at Station L1 (71\u00b006'N, 139\u00b010'W), L1.5 (73\u00b019'N, 139\u00b023'W), L2 (74\u00b030'N, 137\u00b000'W, L3 (75\u00b017'N, 137\u00b030'W), L1.1 (72\u00b031'N, 136\u00b041'), and S4 (71\u00b011'N, 132\u00b057'W) and on samples collected with the regular ArcticNet rosette at station S1 (69\u00b030'N, 137\u00b059'W), S2 (70\u00b000'N, 138\u00b030'W), L1, L2, L3, and L1.1"
-    ],
-    "oai_identifier": [
-        "11278_fgdc"
-    ],
-    "oai_set": [
-        "PDCMetadata"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-144,69],[-144,76],[-132,76],[-132,69],[-144,69]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Arctic Ocean"
-        },
-        {
-            "name": "Beaufort Sea"
-        },
-        {
-            "name": "Nitrates"
-        },
-        {
-            "name": "Nutrients"
-        },
-        {
-            "name": "Phosphorus"
-        },
-        {
-            "name": "Silica"
-        },
-        {
-            "name": "Water column"
-        }
-    ],
-    "title": [
-        "Nitrate, nitrite, phosphate, dissolved silica concentrations (micromol/L) measured in the Beaufort Sea  on multiple casts at 8 stations in 2009"
-    ],
-    "url": "https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=11278"
-}
\ No newline at end of file
diff --git a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0a2921f7-3325-5e32-9cf6-346412167e64.json b/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0a2921f7-3325-5e32-9cf6-346412167e64.json
deleted file mode 100644
index 44fafd6f..00000000
--- a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0a2921f7-3325-5e32-9cf6-346412167e64.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "cbmp_terrestrial@caff.is"
-    ],
-    "Contributor": [
-        "Circumpolar Biodiversity Monitoring Program - CAFF"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MapperVersion": [
-        "To monitor the distribution and population change of moths in Iceland."
-    ],
-    "MetaDataAccess": "http://www.polardata.ca/oai/provider?verb=GetRecord&metadataPrefix=fgdc&identifier=12247_fgdc",
-    "PublicationTimestamp": "2015-04-30T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "Rights": [
-        "Limited"
-    ],
-    "SpatialCoverage": "(64N-66N,19W-14W)",
-    "TempCoverageBegin": 63379450799,
-    "TempCoverageEnd": 315537854399,
-    "TemporalCoverage": " period : ( 2009-06-01T11:59:59Z - 9999-12-31T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2009-06-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "9999-12-31T11:59:59Z",
-    "author": [
-        "Kolbeinsson, Yann",
-        "\u00de\u00f3rarinsson, \u00deorkell Lindberg",
-        "Sn\u00e6\u00fe\u00f3rsson, A\u00f0alsteinn \u00d6rn"
-    ],
-    "fulltext": "12247_fgdc;2017-04-09T22:02:40Z;PDCMetadata;Kolbeinsson, Yann;Kolbeinsson, Yann;Sn\u00e6\u00fe\u00f3rsson, A\u00f0alsteinn \u00d6rn;\u00de\u00f3rarinsson, \u00deorkell Lindberg;20150430;Moth monitoring in Northeastern Iceland;Computer file;unknown;Unpublished data;unavailable;https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=12247;The goal is to monitor the distribution and population dynamics of moths in Iceland in relation with abiotic environmental factors. Moths are collected in light-trap annually from week 16 to week 40. Abiotic factors are monitored at fixed weather stations in the area by the Icelandic Meteorological Office.;To monitor the distribution and population change of moths in Iceland.;Summary: Not Applicable Research Program(s): CBMP/CAFF - Terrestrial. For further information: www.nna.is;20090601;99991231;NULL;In work;Annually;-19;-13.5;66.5;64.5;NULL;Biodiversity;Environment surveillance;Iceland;Lepidoptera;Monitoring;\u00deingeyjars\u00fdslur, NE Iceland;NULL;Limited;NULL;Circumpolar Biodiversity Monitoring Program - CAFF;CBMP Terrestrial - CAFF;NULL;mailing;Borgir, Nordurslod;Akureyri;N/A;600;Iceland;+ 354 462 3350;cbmp_terrestrial@caff.is;NULL;Polar Data Catalogue;Canadian Cryospheric Information Network;Director;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;12247;Research programs, CCIN, or ArcticNet take no liability for the use or transmission of this data;20150430;20150430;CBMP Terrestrial - CAFF;Circumpolar Biodiversity Monitoring Program - CAFF;mailing;Borgir, Nordurslod;Akureyri;N/A;600;Iceland;+ 354 462 3350;cbmp_terrestrial@caff.is;FGDC Content Standards for Digital Geospatial Metadata;FGDC-STD-001-1998",
-    "group": "pdc",
-    "groups": [
-        {
-            "name": "pdc"
-        }
-    ],
-    "name": "0a2921f7-3325-5e32-9cf6-346412167e64",
-    "notes": [
-        "The goal is to monitor the distribution and population dynamics of moths in Iceland in relation with abiotic environmental factors. Moths are collected in light-trap annually from week 16 to week 40. Abiotic factors are monitored at fixed weather stations in the area by the Icelandic Meteorological Office."
-    ],
-    "oai_identifier": [
-        "12247_fgdc"
-    ],
-    "oai_set": [
-        "PDCMetadata"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-19,64.5],[-19,66.5],[-13.5,66.5],[-13.5,64.5],[-19,64.5]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Biodiversity"
-        },
-        {
-            "name": "Environment surveillance"
-        },
-        {
-            "name": "Iceland"
-        },
-        {
-            "name": "Lepidoptera"
-        },
-        {
-            "name": "Monitoring"
-        }
-    ],
-    "title": [
-        "Moth monitoring in Northeastern Iceland"
-    ],
-    "url": "https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=12247"
-}
\ No newline at end of file
diff --git a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0a31c691-d54f-5ff6-9066-5566dddc4cee.json b/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0a31c691-d54f-5ff6-9066-5566dddc4cee.json
deleted file mode 100644
index 243f6717..00000000
--- a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0a31c691-d54f-5ff6-9066-5566dddc4cee.json
+++ /dev/null
@@ -1,98 +0,0 @@
-{
-    "Contact": [
-        "steve.ferguson@dfo-mpo.gc.ca"
-    ],
-    "Contributor": [
-        "Fisheries and Oceans Canada"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MapperVersion": [
-        "The primary emphasis of the GWAMM research is the development of a Community-Based Monitoring (CBM) network within the greater Hudson Bay region of the Canadian Arctic. This network operates by working with northerners to collect marine mammal tissue samples from subsistence hunts and ecosystem prey and components from dedicated monitors. Biological samples and information are being gathered to develop a long-term data set of marine mammal health and ecology in the region to determine how climate warming may affect marine mammals and Nunavummiut communities that depend on them in the future. We are quantifying changes in diet, reproductive success, condition, survival, and ultimately model how endemic species will respond to new marine mammal species invading their traditional environment."
-    ],
-    "MetaDataAccess": "http://www.polardata.ca/oai/provider?verb=GetRecord&metadataPrefix=fgdc&identifier=9953_fgdc",
-    "PublicationTimestamp": "2011-10-17T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "Rights": [
-        "Limited"
-    ],
-    "SpatialCoverage": "(61N,94W)",
-    "TempCoverageBegin": 63389991599,
-    "TempCoverageEnd": 63392500799,
-    "TemporalCoverage": " period : ( 2009-10-01T11:59:59Z - 2009-10-30T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2009-10-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2009-10-30T11:59:59Z",
-    "author": [
-        "Dave Yurkowski",
-        "Steven H. Ferguson",
-        "Frank Nutarasungnik",
-        "Tara Bortoluzzi"
-    ],
-    "fulltext": "9953_fgdc;2017-04-09T22:02:15Z;PDCMetadata;Steven H. Ferguson;Steven H. Ferguson;Dave Yurkowski;Frank Nutarasungnik;Tara Bortoluzzi;20111017;Global Warming and Arctic Marine Mammals (GWAMM) -  Community-based montoring of seals in Arviat, Nunavut, 2009/10 annual subsistence harvest.;Computer file;unknown;Please contact Dr. Steven Ferguson for information on how to cite this data.;unavailable;https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=9953;Biological samples and information were gathered from ringed and bearded seals by local hunters during annual community subsistance harvests in the community. Biological samples gathered by hunters include: blubber (fist size), liver, muscle (fist size), kidney, lower jaw, reproductive tract, stomach, intestine, blood (5 ml), and a small muscle sample in DMFO (for genetic analysis). Other sample information collected includes: species, sex, date and time of harvest, location, GPS coordinates, habitat, total length, axillary girth, hips girth, fat depth, body weight, and sculp weight. These samples were collected from 53 ringed seals and 5 bearded seals in October 2009. Research scientists also collected further biological samples from a smaller sub-set of 15 ringed seals: whiskers, claw, hair, heart, lung, trachea, adrenal glands, inguinal lymph nodes,  and tyroid glands all frozen at -25C. Small samples (2ml) of liver, muscle, blood, and skin/blubber biopsies were also collected and frozen crygenically at -70C.;The primary emphasis of the GWAMM research is the development of a Community-Based Monitoring (CBM) network within the greater Hudson Bay region of the Canadian Arctic. This network operates by working with northerners to collect marine mammal tissue samples from subsistence hunts and ecosystem prey and components from dedicated monitors. Biological samples and information are being gathered to develop a long-term data set of marine mammal health and ecology in the region to determine how climate warming may affect marine mammals and Nunavummiut communities that depend on them in the future. We are quantifying changes in diet, reproductive success, condition, survival, and ultimately model how endemic species will respond to new marine mammal species invading their traditional environment.;Summary: Not Applicable Research Program(s): CBMP/CAFF - Marine,IPY. For further information: Steve.Ferguson@dfo-mpo.gc.ca;20091001;20091030;NULL;In work;As needed;-94;-94;61;61;NULL;Arviat;Body condition;Climate change;Community-based monitoring;Disease;Genetic analysis;Hudson Bay;Ringed seal;Seals;Trophic dynamics;Arviat, Nunavut, Canada;NULL;Limited;NULL;Fisheries and Oceans Canada;Steven Ferguson;NULL;mailing;501 University Crescent;Winnipeg;MB;R3T2N6;Canada;204-983-5057;204-984-2403;steve.ferguson@dfo-mpo.gc.ca;NULL;Polar Data Catalogue;Canadian Cryospheric Information Network;Director;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;9953;Research programs, CCIN, or ArcticNet take no liability for the use or transmission of this data;20111017;20111017;Steven Ferguson;Fisheries and Oceans Canada;mailing;501 University Crescent;Winnipeg;MB;R3T2N6;Canada;204-983-5057;204-984-2403;steve.ferguson@dfo-mpo.gc.ca;FGDC Content Standards for Digital Geospatial Metadata;FGDC-STD-001-1998",
-    "group": "pdc",
-    "groups": [
-        {
-            "name": "pdc"
-        }
-    ],
-    "name": "0a31c691-d54f-5ff6-9066-5566dddc4cee",
-    "notes": [
-        "Biological samples and information were gathered from ringed and bearded seals by local hunters during annual community subsistance harvests in the community. Biological samples gathered by hunters include: blubber (fist size), liver, muscle (fist size), kidney, lower jaw, reproductive tract, stomach, intestine, blood (5 ml), and a small muscle sample in DMFO (for genetic analysis). Other sample information collected includes: species, sex, date and time of harvest, location, GPS coordinates, habitat, total length, axillary girth, hips girth, fat depth, body weight, and sculp weight. These samples were collected from 53 ringed seals and 5 bearded seals in October 2009. Research scientists also collected further biological samples from a smaller sub-set of 15 ringed seals: whiskers, claw, hair, heart, lung, trachea, adrenal glands, inguinal lymph nodes,  and tyroid glands all frozen at -25C. Small samples (2ml) of liver, muscle, blood, and skin/blubber biopsies were also collected and frozen crygenically at -70C."
-    ],
-    "oai_identifier": [
-        "9953_fgdc"
-    ],
-    "oai_set": [
-        "PDCMetadata"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-94,61],[-94,61],[-94,61],[-94,61],[-94,61]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Arviat"
-        },
-        {
-            "name": "Body condition"
-        },
-        {
-            "name": "Climate change"
-        },
-        {
-            "name": "Community-based monitoring"
-        },
-        {
-            "name": "Disease"
-        },
-        {
-            "name": "Genetic analysis"
-        },
-        {
-            "name": "Hudson Bay"
-        },
-        {
-            "name": "Ringed seal"
-        },
-        {
-            "name": "Seals"
-        },
-        {
-            "name": "Trophic dynamics"
-        }
-    ],
-    "title": [
-        "Global Warming and Arctic Marine Mammals (GWAMM) -  Community-based montoring of seals in Arviat, Nunavut, 2009/10 annual subsistence harvest."
-    ],
-    "url": "https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=9953"
-}
\ No newline at end of file
diff --git a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0a377e9a-2f1b-55fd-958c-2571c5e52637.json b/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0a377e9a-2f1b-55fd-958c-2571c5e52637.json
deleted file mode 100644
index 9c06fc70..00000000
--- a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0a377e9a-2f1b-55fd-958c-2571c5e52637.json
+++ /dev/null
@@ -1,92 +0,0 @@
-{
-    "Contact": [
-        "stoyka.netcheva@canada.ca"
-    ],
-    "Contributor": [
-        "Environment Canada"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MapperVersion": [
-        "O-buoys enable remote and long-term chemical measurements in hostile polar environments, generating important knowledge and understanding for decision makers and Northerners who are adapting to their changing environment. The O-buoy network will provide the long-term observations required not only to improve understanding of the fundamental chemical and physical processes but to better understand how atmosphere-surface interactive processes respond to the changes across the Arctic. The overall project goal is to advance knowledge of the present state of the global atmospheric CO2 level and future behaviour of the global carbon cycle."
-    ],
-    "MetaDataAccess": "http://www.polardata.ca/oai/provider?verb=GetRecord&metadataPrefix=fgdc&identifier=1842_fgdc",
-    "PublicationTimestamp": "2013-04-04T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "Rights": [
-        "Limited"
-    ],
-    "SpatialCoverage": "(59N-90N,172W-52W)",
-    "TempCoverageBegin": 63369259199,
-    "TempCoverageEnd": 315537854399,
-    "TemporalCoverage": " period : ( 2009-02-03T11:59:59Z - 9999-12-31T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2009-02-03T11:59:59Z",
-    "TemporalCoverage:EndDate": "9999-12-31T11:59:59Z",
-    "author": [
-        "Francisco Chavez",
-        "Patricia Matrai",
-        "Stoyka Netcheva",
-        "Jan Bottenheim",
-        "Don Perovich",
-        "Paul Shepson",
-        "William Simpson"
-    ],
-    "fulltext": "1842_fgdc;2017-04-09T22:02:12Z;PDCMetadata;Patricia Matrai;Stoyka Netcheva;Don Perovich;Francisco Chavez;Jan Bottenheim;Paul Shepson;William Simpson;20130404;OASIS-CANADA-O-buoys: Development of an autonomous ice tethered platform (buoy) to determine the surface atmospheric composition year round over selected locations of the Arctic Ocean;Computer file;unknown;T. N. Knepp, J. Bottenheim, M. Carlsen, D. Carlson, D. Donohoue, G. Friederich, P.M. Matrai, S. Netcheva, D.K. Perovich, R. Santini, P.B. Shepson, W. Simpson, T. Valentic, C. Williams, and P.J. Wyss, Development of an Autonomous Sea Ice Tethered Buoy for the Study of Ocean- Atmosphere-Sea Ice-Snow Pack Interactions: the O-buoy, Atmospheric Measurement Techniques, 3, 249-261, 2010.;unavailable;https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=1842;A buoy based instrument platform (the O-buoy) was designed, constructed, and field tested for year-round measurement of ozone (O3), bromine monoxide (BrO), carbon dioxide (CO2), and meteorological variables over Arctic sea ice. The O-buoy operated in an autonomous manner with daily, bi-directional data transmissions using Iridium satellite communication. The O-buoy was equipped with three power sources: primary lithium-ion battery packs, rechargeable lead acid packs, and solar panels that recharge the lead acid packs, and can fully power the O-buoy during summer operation. This system was designed to operate under the harsh conditions present in the Arctic, with minimal direct human interaction, to aid in our understanding of the atmospheric chemistry that occurs in this remote region of the world. The current design requires approximately yearly maintenance limited by the lifetime of the primary power supply. The O-buoy system was field tested in Elson Lagoon, Barrow, Alaska from February to May 2009 and deployed in the Beaufort Sea in October 2009, 2010, 2011; in the Arctic Ocean near Borden Island in April 2010; in the North Pole area September 2011; and in Hudson Bay February 2010 and February 2011. Ozone: one-minute averaged were collected by a modified 2B-technology ozone monitor for periods of time dependant on available power. Hourly measurements of CO2 were collected with specially-constructed instrument based on Licor technology. BrO data were collected employing the MAXDOAS technique developed by the University of Alaska Fairbanks during hours of available daylight. Meteorological variables: temperature, atmospheric pressure, humidity, and wind speed and direction were obtained with Campbell Scientific instrumentation at five-minute intervals. Position and heading came from Hemisphere differential GPS. Data transfer was accomplished by daily upload via Iridium satellite to SRI and open to the public on display. All chemical sensors include the capability for zero and span checks.&#x0d;\nData usage requires permission of P. Matrai at pmatrai@bigelow.org.;O-buoys enable remote and long-term chemical measurements in hostile polar environments, generating important knowledge and understanding for decision makers and Northerners who are adapting to their changing environment. The O-buoy network will provide the long-term observations required not only to improve understanding of the fundamental chemical and physical processes but to better understand how atmosphere-surface interactive processes respond to the changes across the Arctic. The overall project goal is to advance knowledge of the present state of the global atmospheric CO2 level and future behaviour of the global carbon cycle.;Summary: O-buoys were deployed in the frozen Arctic Ocean to obtain long term concentration data for O3, CO2 and BrO.  A prototype O-buoy was operating in the Elson Lagoon near Barrow Alaska to determine performance characteristics.  The prototype was deployed in the frozen Beaufort Sea in 2009 and 2 more units in 2010 and 2011. One unit under name O-buoy 3 collected information over the ice of the Hudson Bay (near Churchill, MB) in February and March 2010 and 2011. O-buoy 4 recorded data over the ice of the Arctic Ocean south of Borden Island in April 2010 and was redeployed in the North Pole area in 2011. More units will be deployed in the future in various parts of the Arctic and sub-Arctic. Research Program(s): IPY. For further information: http://transport.sri.com/obuoy/monitor; http://www.aoncadis.org/dataset/o-buoy3_deployment.html; http://www.aoncadis.org/dataset/o-buoy4_deployment.html; www.o-buoy.org/.;20090203;99991231;NULL;In work;As needed;-171.71;-52.01;89.52;58.76;NULL;Alaska;Arctic;Atmospheric composition;Bromine oxide;Carbon dioxide;Ice;Ozone;Elson lagoon near Barrow, Alaska; Beaufort Gyre; Arctic Ocean south of Borden Island, Canada; Hudson Bay; Arctic Ocean around the North Pole;NULL;Limited;NULL;Environment Canada;Stoyka Netcheva;NULL;mailing;4905 Dufferin Street;Toronto;ON;M3H5T4;Canada;417 7394856;stoyka.netcheva@canada.ca;NULL;Polar Data Catalogue;Canadian Cryospheric Information Network;Director;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;1842;Research programs, CCIN, or ArcticNet take no liability for the use or transmission of this data;20130404;20130404;Stoyka Netcheva;Environment Canada;mailing;4905 Dufferin Street;Toronto;ON;M3H5T4;Canada;417 7394856;stoyka.netcheva@canada.ca;FGDC Content Standards for Digital Geospatial Metadata;FGDC-STD-001-1998",
-    "group": "pdc",
-    "groups": [
-        {
-            "name": "pdc"
-        }
-    ],
-    "name": "0a377e9a-2f1b-55fd-958c-2571c5e52637",
-    "notes": [
-        "A buoy based instrument platform (the O-buoy) was designed, constructed, and field tested for year-round measurement of ozone (O3), bromine monoxide (BrO), carbon dioxide (CO2), and meteorological variables over Arctic sea ice. The O-buoy operated in an autonomous manner with daily, bi-directional data transmissions using Iridium satellite communication. The O-buoy was equipped with three power sources: primary lithium-ion battery packs, rechargeable lead acid packs, and solar panels that recharge the lead acid packs, and can fully power the O-buoy during summer operation. This system was designed to operate under the harsh conditions present in the Arctic, with minimal direct human interaction, to aid in our understanding of the atmospheric chemistry that occurs in this remote region of the world. The current design requires approximately yearly maintenance limited by the lifetime of the primary power supply. The O-buoy system was field tested in Elson Lagoon, Barrow, Alaska from February to May 2009 and deployed in the Beaufort Sea in October 2009, 2010, 2011; in the Arctic Ocean near Borden Island in April 2010; in the North Pole area September 2011; and in Hudson Bay February 2010 and February 2011. Ozone: one-minute averaged were collected by a modified 2B-technology ozone monitor for periods of time dependant on available power. Hourly measurements of CO2 were collected with specially-constructed instrument based on Licor technology. BrO data were collected employing the MAXDOAS technique developed by the University of Alaska Fairbanks during hours of available daylight. Meteorological variables: temperature, atmospheric pressure, humidity, and wind speed and direction were obtained with Campbell Scientific instrumentation at five-minute intervals. Position and heading came from Hemisphere differential GPS. Data transfer was accomplished by daily upload via Iridium satellite to SRI and open to the public on display. All chemical sensors include the capability for zero and span checks.&#x0d;\nData usage requires permission of P. Matrai at pmatrai@bigelow.org."
-    ],
-    "oai_identifier": [
-        "1842_fgdc"
-    ],
-    "oai_set": [
-        "PDCMetadata"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-171.71,58.76],[-171.71,89.52],[-52.01,89.52],[-52.01,58.76],[-171.71,58.76]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Alaska"
-        },
-        {
-            "name": "Arctic"
-        },
-        {
-            "name": "Atmospheric composition"
-        },
-        {
-            "name": "Bromine oxide"
-        },
-        {
-            "name": "Carbon dioxide"
-        },
-        {
-            "name": "Ice"
-        },
-        {
-            "name": "Ozone"
-        }
-    ],
-    "title": [
-        "OASIS-CANADA-O-buoys: Development of an autonomous ice tethered platform (buoy) to determine the surface atmospheric composition year round over selected locations of the Arctic Ocean"
-    ],
-    "url": "https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=1842"
-}
\ No newline at end of file
diff --git a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0a616f49-633d-50bc-9d9c-f6278e4f9827.json b/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0a616f49-633d-50bc-9d9c-f6278e4f9827.json
deleted file mode 100644
index e316bd45..00000000
--- a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0a616f49-633d-50bc-9d9c-f6278e4f9827.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "adaptation@aadnc-aandc.gc.ca"
-    ],
-    "Contributor": [
-        "Aboriginal Affairs and Northern Development Canada"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MapperVersion": [
-        "Communities in coastal Labrador are now and will continue to be affected by climate variability and change. The effects of the changing climate compound other pressures and stresses that communities in which they will need to adapt. The purpose of the project was to: (1) examine what roles and values and cultural identity play in shaping responses to climate change in Labrador and; (2) provide in-depth knowledge of how values and culture are likely elements that will impact adaptation measures in Labrador communities."
-    ],
-    "MetaDataAccess": "http://www.polardata.ca/oai/provider?verb=GetRecord&metadataPrefix=fgdc&identifier=12005_fgdc",
-    "PublicationTimestamp": "2015-03-17T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "Rights": [
-        "Public"
-    ],
-    "SpatialCoverage": "(57N-57N,62W-62W)",
-    "TempCoverageBegin": 63405716399,
-    "TempCoverageEnd": 63437165999,
-    "TemporalCoverage": " period : ( 2010-04-01T11:59:59Z - 2011-03-31T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2010-04-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2011-03-31T11:59:59Z",
-    "author": [
-        "Nunatsiavut Government, Department of Lands and Natural Resources"
-    ],
-    "fulltext": "12005_fgdc;2017-04-09T22:02:34Z;PDCMetadata;Nunatsiavut Government, Department of Lands and Natural Resources;Nunatsiavut Government, Department of Lands and Natural Resources;20150317;Assessing the Roles of Community Values and Cultural Identity in Shaping Responses to Climate Change in Labrador;Computer file;unknown;Unpublished; TBD;unavailable;https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=12005;Firstly, semi-structured interviews were conducted with key stakeholders and decision makers to explore what values underpin ideas to which best adapt to climate change. A preliminary list of participants was drawn up based on a preliminary consultation with communities. Interview questions were developed following the consultation visit, and the questionnaire guide used a semi-structured format with open ended questions that explore people`s culture, identity, and values they hold. Analysis of the interviews was completed by qualitative coding of text passages in order to identify overarching themes. Finally, focus group workshops were also held to facilitate discussions on how values and cultural identity shape adaptation and visions of the future.;Communities in coastal Labrador are now and will continue to be affected by climate variability and change. The effects of the changing climate compound other pressures and stresses that communities in which they will need to adapt. The purpose of the project was to: (1) examine what roles and values and cultural identity play in shaping responses to climate change in Labrador and; (2) provide in-depth knowledge of how values and culture are likely elements that will impact adaptation measures in Labrador communities.;Summary: N/A Research Program(s): APAN-AANDC - Adaptation Program for Aboriginals and Northerners. For further information: tom_sheldon@nunatsiavut.com;20100401;20110331;NULL;Complete;As needed;-61.78;-61.72;56.55;56.53;NULL;Adaptation;Climate change;Community vulnerability;Cultural values;Labrador;Labrador, Canada;NULL;Public;NULL;Aboriginal Affairs and Northern Development Canada;Martin Tremblay - PDC;NULL;mailing;25, Eddy;Gatineau;QC;K1A 0H4;Canada;(819) 934-9210;(819) 953-2590;adaptation@aadnc-aandc.gc.ca;NULL;Polar Data Catalogue;Canadian Cryospheric Information Network;Director;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;12005;Research programs, CCIN, or ArcticNet take no liability for the use or transmission of this data;20150317;20150317;Martin Tremblay - PDC;Aboriginal Affairs and Northern Development Canada;mailing;25, Eddy;Gatineau;QC;K1A 0H4;Canada;(819) 934-9210;(819) 953-2590;adaptation@aadnc-aandc.gc.ca;FGDC Content Standards for Digital Geospatial Metadata;FGDC-STD-001-1998",
-    "group": "pdc",
-    "groups": [
-        {
-            "name": "pdc"
-        }
-    ],
-    "name": "0a616f49-633d-50bc-9d9c-f6278e4f9827",
-    "notes": [
-        "Firstly, semi-structured interviews were conducted with key stakeholders and decision makers to explore what values underpin ideas to which best adapt to climate change. A preliminary list of participants was drawn up based on a preliminary consultation with communities. Interview questions were developed following the consultation visit, and the questionnaire guide used a semi-structured format with open ended questions that explore people`s culture, identity, and values they hold. Analysis of the interviews was completed by qualitative coding of text passages in order to identify overarching themes. Finally, focus group workshops were also held to facilitate discussions on how values and cultural identity shape adaptation and visions of the future."
-    ],
-    "oai_identifier": [
-        "12005_fgdc"
-    ],
-    "oai_set": [
-        "PDCMetadata"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-61.78,56.53],[-61.78,56.55],[-61.72,56.55],[-61.72,56.53],[-61.78,56.53]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Adaptation"
-        },
-        {
-            "name": "Climate change"
-        },
-        {
-            "name": "Community vulnerability"
-        },
-        {
-            "name": "Cultural values"
-        },
-        {
-            "name": "Labrador"
-        }
-    ],
-    "title": [
-        "Assessing the Roles of Community Values and Cultural Identity in Shaping Responses to Climate Change in Labrador"
-    ],
-    "url": "https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=12005"
-}
\ No newline at end of file
diff --git a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0a69f8bf-de95-5c7a-9723-9d7fbfa57708.json b/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0a69f8bf-de95-5c7a-9723-9d7fbfa57708.json
deleted file mode 100644
index 2b5a092c..00000000
--- a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0a69f8bf-de95-5c7a-9723-9d7fbfa57708.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "colin.laroque@usask.ca"
-    ],
-    "Contributor": [
-        "Mistik Askiwin Dendrochronology Laboratory"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MapperVersion": [
-        "Research objectives:  Dendrochronological analysis to isolate climatic factor(s) influencing each tree species' growth.  Tree ring analysis to determine the species' suitability as a proxy for establishing an historical record of insect outbreak in the region."
-    ],
-    "MetaDataAccess": "http://www.polardata.ca/oai/provider?verb=GetRecord&metadataPrefix=fgdc&identifier=1530_fgdc",
-    "PublicationTimestamp": "2012-10-09T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "Rights": [
-        "Limited"
-    ],
-    "SpatialCoverage": "(55N,60W)",
-    "TempCoverageBegin": 63322426799,
-    "TempCoverageEnd": 63322426799,
-    "TemporalCoverage": " period : ( 2007-08-11T11:59:59Z - 2007-08-11T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2007-08-11T11:59:59Z",
-    "TemporalCoverage:EndDate": "2007-08-11T11:59:59Z",
-    "author": [
-        "Colin Laroque",
-        "Karen Harper"
-    ],
-    "fulltext": "1530_fgdc;2017-04-09T22:02:04Z;PDCMetadata;Karen Harper;Colin Laroque;20121009;Dendrochronological analysis at Bush Pond, Central Labrador, Canada;Computer file;unknown;Unpublished data;unavailable;https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=1530;Using increment boring tools, the two most dominant tree species were sampled for subsequent dendrochronological analysis.  Twenty trees of each species were sampled, with two cores extracted from each tree (80 cores total from each site).  Samples will be measured and cross-dated in the lab, and master chronologies will be created for each species using standard dendrochronological procedures.  Statistical procedures will isolate the climatic factor(s) influencing each tree-species growth, and this information will be used to evaluate each species and its individual radial growth-climate relationship.  Dataset variables, with brief description of each variable:  Sample #: Black spruce: 07CJL101 to 07CJL120. Balsam fir: 07CJL301 to 07CJL320.  Grid zone: 21 U.  GPS UTM: Easting 0312218, Northing 6096595.  Elevation (m asl): 28 m.  Notes: Two dominant species were black spruce (Picea mariana) and balsam fir (Abies balsamea).  A set was bored for these two species on a flat mossy floor. The black spruce chronology dates from 2007 to 1666 and the fir from 2007 to 1807.;Research objectives:  Dendrochronological analysis to isolate climatic factor(s) influencing each tree species' growth.  Tree ring analysis to determine the species' suitability as a proxy for establishing an historical record of insect outbreak in the region.;Summary: Not Applicable Research Program(s): IPY. For further information: claroque@mta.ca;20070811;20070811;NULL;Complete;As needed;-59.9;-59.9;54.8;54.8;NULL;Climate;Dendrochronology;Forest-tundra;Growth rate;Spatial data;Bush Pond, Central Labrador, Canada;NULL;Limited;NULL;Mistik Askiwin Dendrochronology Laboratory;Colin Laroque;NULL;mailing;51 Campus Drive;Saskatoon;SK;S7N 5A8;Canada;(306) 966-2493;(306) 966-6881;colin.laroque@usask.ca;NULL;Polar Data Catalogue;Canadian Cryospheric Information Network;Director;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;1530;Research programs, CCIN, or ArcticNet take no liability for the use or transmission of this data;20121009;20121009;Colin Laroque;Mistik Askiwin Dendrochronology Laboratory;mailing;51 Campus Drive;Saskatoon;SK;S7N 5A8;Canada;(306) 966-2493;(306) 966-6881;colin.laroque@usask.ca;FGDC Content Standards for Digital Geospatial Metadata;FGDC-STD-001-1998",
-    "group": "pdc",
-    "groups": [
-        {
-            "name": "pdc"
-        }
-    ],
-    "name": "0a69f8bf-de95-5c7a-9723-9d7fbfa57708",
-    "notes": [
-        "Using increment boring tools, the two most dominant tree species were sampled for subsequent dendrochronological analysis.  Twenty trees of each species were sampled, with two cores extracted from each tree (80 cores total from each site).  Samples will be measured and cross-dated in the lab, and master chronologies will be created for each species using standard dendrochronological procedures.  Statistical procedures will isolate the climatic factor(s) influencing each tree-species growth, and this information will be used to evaluate each species and its individual radial growth-climate relationship.  Dataset variables, with brief description of each variable:  Sample #: Black spruce: 07CJL101 to 07CJL120. Balsam fir: 07CJL301 to 07CJL320.  Grid zone: 21 U.  GPS UTM: Easting 0312218, Northing 6096595.  Elevation (m asl): 28 m.  Notes: Two dominant species were black spruce (Picea mariana) and balsam fir (Abies balsamea).  A set was bored for these two species on a flat mossy floor. The black spruce chronology dates from 2007 to 1666 and the fir from 2007 to 1807."
-    ],
-    "oai_identifier": [
-        "1530_fgdc"
-    ],
-    "oai_set": [
-        "PDCMetadata"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-59.9,54.8],[-59.9,54.8],[-59.9,54.8],[-59.9,54.8],[-59.9,54.8]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Climate"
-        },
-        {
-            "name": "Dendrochronology"
-        },
-        {
-            "name": "Forest-tundra"
-        },
-        {
-            "name": "Growth rate"
-        },
-        {
-            "name": "Spatial data"
-        }
-    ],
-    "title": [
-        "Dendrochronological analysis at Bush Pond, Central Labrador, Canada"
-    ],
-    "url": "https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=1530"
-}
\ No newline at end of file
diff --git a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0a9c28ac-458b-5604-8475-1a54d9496b32.json b/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0a9c28ac-458b-5604-8475-1a54d9496b32.json
deleted file mode 100644
index fd8f58c4..00000000
--- a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0a9c28ac-458b-5604-8475-1a54d9496b32.json
+++ /dev/null
@@ -1,98 +0,0 @@
-{
-    "Contact": [
-        "steve.ferguson@dfo-mpo.gc.ca"
-    ],
-    "Contributor": [
-        "Fisheries and Oceans Canada"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MapperVersion": [
-        "Concerns have arisen over possible declines in ringed seal numbers in nearby western Hudson Bay as indicated by reduced pregnancy rate, pup survival and abundance, and older age structure. Ringed seals are numerically, nutritionally, and economically one of the most important marine mammal species to Inuit communities of Hudson Bay, so knowledge of where and how seals use the bay is needed. As part of a larger project to assess ringed seal population dynamics and diet with climate change, this study focuses on ringed seal movements and haul-out behaviour, assess critical habitat, and investigate characteristics of foraging behaviour. We will further examine how similar metrics of behavior and habitat use for polar bears in the same region overlap. This project describes the collection and analysis of these data for ringed seals."
-    ],
-    "MetaDataAccess": "http://www.polardata.ca/oai/provider?verb=GetRecord&metadataPrefix=fgdc&identifier=9951_fgdc",
-    "PublicationTimestamp": "2011-10-17T11:59:59Z",
-    "PublicationYear": [
-        "2011"
-    ],
-    "Publisher": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "Rights": [
-        "Limited"
-    ],
-    "SpatialCoverage": "(57N-69N,82W-79W)",
-    "TempCoverageBegin": 63383079599,
-    "TempCoverageEnd": 63385585199,
-    "TemporalCoverage": " period : ( 2009-07-13T11:59:59Z - 2009-08-11T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2009-07-13T11:59:59Z",
-    "TemporalCoverage:EndDate": "2009-08-11T11:59:59Z",
-    "author": [
-        "Brent Young",
-        "Elizabeth Peacock",
-        "Steven H. Ferguson",
-        "Tara Bortoluzzi"
-    ],
-    "fulltext": "9951_fgdc;2017-04-09T22:02:15Z;PDCMetadata;Steven H. Ferguson;Steven H. Ferguson;Brent Young;Elizabeth Peacock;Tara Bortoluzzi;20111017;Polar Bears and Seals : Movement of ringed seals in the greater Hudson Bay region, Nunavut, 2009;Computer file;unknown;Please contact Dr. Steven Ferguson for information on how to cite this data.;unavailable;https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=9951;The aim of the project is to provide management information and advice for the Hudson Bay ringed seal stock by: (1) delineating movements that may bring juveniles and possibly adults into areas hunted by other communities; (2) assessing sex- and age-specific site fidelity of individual seals during the breeding season; (3) defining critical foraging habitat, movement and diving behaviour; (4) defining spatio-temporal variation in these aspects of ringed seal foraging ecology to complement ongoing diet studies to address a purported shift in prey of top predators associated with climate change. In total satellite telemetry project has deployed satellite tags (Wildlife Computers Splash instruments relaying location and diving behaviour data via the ARGOS satellite system) on a total of 34 live ringed seals (10 in September 2006, 8 in September 2007, 9 in September 2008, and 8 in August 2009); 2 bearded seals (2 in September 2008) captured at the Belcher Islands, Nunavut, from 2006 to 2008; and 7 ringed seals captured near Igloolik, Nunavut in July 2009. Community-based monitoring and fieldwork for the satellite telemetry project took place in Foxe Basin, near the community of Igloolik 13 to 24 July, 2009; and in south-eastern Hudson Bay, near the community of Sanikiluaq 27 July to 11 August, 2009.;Concerns have arisen over possible declines in ringed seal numbers in nearby western Hudson Bay as indicated by reduced pregnancy rate, pup survival and abundance, and older age structure. Ringed seals are numerically, nutritionally, and economically one of the most important marine mammal species to Inuit communities of Hudson Bay, so knowledge of where and how seals use the bay is needed. As part of a larger project to assess ringed seal population dynamics and diet with climate change, this study focuses on ringed seal movements and haul-out behaviour, assess critical habitat, and investigate characteristics of foraging behaviour. We will further examine how similar metrics of behavior and habitat use for polar bears in the same region overlap. This project describes the collection and analysis of these data for ringed seals.;Summary: Not Applicable Research Program(s): CBMP/CAFF - Marine,IPY. For further information: Steve.Ferguson@dfo-mpo.gc.ca;20090713;20090811;NULL;In work;As needed;-82.3;-79.3;69.4;56.6;NULL;Climate change;Community-based monitoring;Fitness;Genetic analysis;Hudson Bay;Igloolik;Monitoring;Ringed seal;Sanikiluaq;Seals;Foxe Basin (Iglooik, NU) & Hudson Bay (near Sanikiluaq);NULL;Limited;NULL;Fisheries and Oceans Canada;Steven Ferguson;NULL;mailing;501 University Crescent;Winnipeg;MB;R3T2N6;Canada;204-983-5057;204-984-2403;steve.ferguson@dfo-mpo.gc.ca;NULL;Polar Data Catalogue;Canadian Cryospheric Information Network;Director;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;9951;Research programs, CCIN, or ArcticNet take no liability for the use or transmission of this data;20111017;20111017;Steven Ferguson;Fisheries and Oceans Canada;mailing;501 University Crescent;Winnipeg;MB;R3T2N6;Canada;204-983-5057;204-984-2403;steve.ferguson@dfo-mpo.gc.ca;FGDC Content Standards for Digital Geospatial Metadata;FGDC-STD-001-1998",
-    "group": "pdc",
-    "groups": [
-        {
-            "name": "pdc"
-        }
-    ],
-    "name": "0a9c28ac-458b-5604-8475-1a54d9496b32",
-    "notes": [
-        "The aim of the project is to provide management information and advice for the Hudson Bay ringed seal stock by: (1) delineating movements that may bring juveniles and possibly adults into areas hunted by other communities; (2) assessing sex- and age-specific site fidelity of individual seals during the breeding season; (3) defining critical foraging habitat, movement and diving behaviour; (4) defining spatio-temporal variation in these aspects of ringed seal foraging ecology to complement ongoing diet studies to address a purported shift in prey of top predators associated with climate change. In total satellite telemetry project has deployed satellite tags (Wildlife Computers Splash instruments relaying location and diving behaviour data via the ARGOS satellite system) on a total of 34 live ringed seals (10 in September 2006, 8 in September 2007, 9 in September 2008, and 8 in August 2009); 2 bearded seals (2 in September 2008) captured at the Belcher Islands, Nunavut, from 2006 to 2008; and 7 ringed seals captured near Igloolik, Nunavut in July 2009. Community-based monitoring and fieldwork for the satellite telemetry project took place in Foxe Basin, near the community of Igloolik 13 to 24 July, 2009; and in south-eastern Hudson Bay, near the community of Sanikiluaq 27 July to 11 August, 2009."
-    ],
-    "oai_identifier": [
-        "9951_fgdc"
-    ],
-    "oai_set": [
-        "PDCMetadata"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-82.3,56.6],[-82.3,69.4],[-79.3,69.4],[-79.3,56.6],[-82.3,56.6]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Climate change"
-        },
-        {
-            "name": "Community-based monitoring"
-        },
-        {
-            "name": "Fitness"
-        },
-        {
-            "name": "Genetic analysis"
-        },
-        {
-            "name": "Hudson Bay"
-        },
-        {
-            "name": "Igloolik"
-        },
-        {
-            "name": "Monitoring"
-        },
-        {
-            "name": "Ringed seal"
-        },
-        {
-            "name": "Sanikiluaq"
-        },
-        {
-            "name": "Seals"
-        }
-    ],
-    "title": [
-        "Polar Bears and Seals : Movement of ringed seals in the greater Hudson Bay region, Nunavut, 2009"
-    ],
-    "url": "https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=9951"
-}
\ No newline at end of file
diff --git a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0ab07f02-34fa-500e-a4e7-8e9f7fd94e72.json b/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0ab07f02-34fa-500e-a4e7-8e9f7fd94e72.json
deleted file mode 100644
index 8edddfcb..00000000
--- a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0ab07f02-34fa-500e-a4e7-8e9f7fd94e72.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "colin.laroque@usask.ca"
-    ],
-    "Contributor": [
-        "Mistik Askiwin Dendrochronology Laboratory"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MapperVersion": [
-        "Research objectives:  Dendrochronological analysis to isolate climatic factor(s) influencing each tree species' growth.  Tree ring analysis to determine the species' suitability as a proxy for establishing an historical record of insect outbreak in the region."
-    ],
-    "MetaDataAccess": "http://www.polardata.ca/oai/provider?verb=GetRecord&metadataPrefix=fgdc&identifier=1524_fgdc",
-    "PublicationTimestamp": "2012-10-09T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "Rights": [
-        "Limited"
-    ],
-    "SpatialCoverage": "(53N,66W)",
-    "TempCoverageBegin": 63351889199,
-    "TempCoverageEnd": 63351889199,
-    "TemporalCoverage": " period : ( 2008-07-17T11:59:59Z - 2008-07-17T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2008-07-17T11:59:59Z",
-    "TemporalCoverage:EndDate": "2008-07-17T11:59:59Z",
-    "author": [
-        "Colin Laroque",
-        "Karen Harper"
-    ],
-    "fulltext": "1524_fgdc;2017-04-09T22:02:04Z;PDCMetadata;Karen Harper;Colin Laroque;20121009;Dendrochronological analysis at Ritchie Lake, Western Labrador, Canada;Computer file;unknown;Unpublished data;unavailable;https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=1524;Using increment boring tools, the two most dominant tree species were sampled for subsequent dendrochronological analysis.  Twenty trees of each species were sampled, with two cores extracted from each tree (80 cores total from each site).  Samples will be measured and cross-dated in the lab, and master chronologies will be created for each species using standard dendrochronological procedures.  Statistical procedures will isolate the climatic factor(s) influencing each tree-species growth, and this information will be used to evaluate each species and its individual radial growth-climate relationship.  Dataset variables, with brief description of each variable:  Sample #: Black Spruce: 08ABL101 to 08ABL120. Eastern Larch: 08ABL701 to 08ABL720.  Grid zone: 20 U.  GPS UTM: Easting 298779\t, Northing 5877148.  Elevation (m asl): 566m.  Notes: Two dominant species were black spruce (Picea mariana) and eastern larch (Larix laricina).;Research objectives:  Dendrochronological analysis to isolate climatic factor(s) influencing each tree species' growth.  Tree ring analysis to determine the species' suitability as a proxy for establishing an historical record of insect outbreak in the region.;Summary: Not Applicable Research Program(s): IPY. For further information: claroque@mta.ca;20080717;20080717;NULL;Complete;As needed;-66;-66;53;53;NULL;Climate;Dendrochronology;Forest-tundra;Growth rate;Spatial data;Ritchie Lake, Western Labrador, Canada;NULL;Limited;NULL;Mistik Askiwin Dendrochronology Laboratory;Colin Laroque;NULL;mailing;51 Campus Drive;Saskatoon;SK;S7N 5A8;Canada;(306) 966-2493;(306) 966-6881;colin.laroque@usask.ca;NULL;Polar Data Catalogue;Canadian Cryospheric Information Network;Director;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;1524;Research programs, CCIN, or ArcticNet take no liability for the use or transmission of this data;20121009;20121009;Colin Laroque;Mistik Askiwin Dendrochronology Laboratory;mailing;51 Campus Drive;Saskatoon;SK;S7N 5A8;Canada;(306) 966-2493;(306) 966-6881;colin.laroque@usask.ca;FGDC Content Standards for Digital Geospatial Metadata;FGDC-STD-001-1998",
-    "group": "pdc",
-    "groups": [
-        {
-            "name": "pdc"
-        }
-    ],
-    "name": "0ab07f02-34fa-500e-a4e7-8e9f7fd94e72",
-    "notes": [
-        "Using increment boring tools, the two most dominant tree species were sampled for subsequent dendrochronological analysis.  Twenty trees of each species were sampled, with two cores extracted from each tree (80 cores total from each site).  Samples will be measured and cross-dated in the lab, and master chronologies will be created for each species using standard dendrochronological procedures.  Statistical procedures will isolate the climatic factor(s) influencing each tree-species growth, and this information will be used to evaluate each species and its individual radial growth-climate relationship.  Dataset variables, with brief description of each variable:  Sample #: Black Spruce: 08ABL101 to 08ABL120. Eastern Larch: 08ABL701 to 08ABL720.  Grid zone: 20 U.  GPS UTM: Easting 298779\t, Northing 5877148.  Elevation (m asl): 566m.  Notes: Two dominant species were black spruce (Picea mariana) and eastern larch (Larix laricina)."
-    ],
-    "oai_identifier": [
-        "1524_fgdc"
-    ],
-    "oai_set": [
-        "PDCMetadata"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-66,53],[-66,53],[-66,53],[-66,53],[-66,53]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Climate"
-        },
-        {
-            "name": "Dendrochronology"
-        },
-        {
-            "name": "Forest-tundra"
-        },
-        {
-            "name": "Growth rate"
-        },
-        {
-            "name": "Spatial data"
-        }
-    ],
-    "title": [
-        "Dendrochronological analysis at Ritchie Lake, Western Labrador, Canada"
-    ],
-    "url": "https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=1524"
-}
\ No newline at end of file
diff --git a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0adae04e-2a7d-58f9-9c49-e081c949963a.json b/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0adae04e-2a7d-58f9-9c49-e081c949963a.json
deleted file mode 100644
index 329df3e6..00000000
--- a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0adae04e-2a7d-58f9-9c49-e081c949963a.json
+++ /dev/null
@@ -1,93 +0,0 @@
-{
-    "Contact": [
-        "pdc@uwaterloo.ca"
-    ],
-    "Contributor": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MapperVersion": [
-        "The RADARSAT satellite image collections in the Polar Data Catalogue include imagery from both RADARSAT-1 and RADARSAT-2.   &gt;&gt;During its operation (1995-2013), the RADARSAT-1 satellite and sensors collected Synthetic Aperture Radar (SAR) imagery, including a significant portion which is attributable to the systematic data collection effort of the Background Mission. The archive of imagery developed during the Background Mission has emphasized, among other things, the RADARSAT imaging capabilities during times of inclement weather and low illumination conditions.  Practical experience by operational users has demonstrated that RADARSAT imagery is an excellent and reliable source for mapping and monitoring sea ice and other cryospheric features in northern latitudes during different times of the year. RADARSAT-1 has collected an incredible wealth of SAR imagery over polar regions, including northern Canada. A large portion of this archive is available on the Polar Data Catalogue as the RADARSAT Polar Science Dataset.     &gt;&gt;The RADARSAT-2 Antarctic Mapping Initiative was undertaken to produce a continental mosaic consistent with the 1997 RADARSAT-1 Antarctic Mapping Mission. The resulting mosaics and individual tiles, produced in collaboration with the Byrd Polar Research Center, cover all the way to the South Pole, permitted by the left-looking capabilities of the RADARSAT-2. This is only the second time pole-to-coast mosaic SAR (Synthetic Aperture Radar) coverage has been achieved, the first time having been the RADARSAT-1 Antarctic Mapping Mission in 1997. In addition to enhancing the achievements of previous RADARSAT-1 Antarctic missions, the intent of this mission was to facilitate change analysis through space-borne observation of ice sheets. Such data are important for generation of global climate products, including models. The mission was the result of international collaboration associated with the International Polar Year (IPY), incorporating input from the scientific community, with the goal of making science products available for free. This dataset is a Canadian Space Agency contribution to IPY."
-    ],
-    "MetaDataAccess": "http://www.polardata.ca/oai/provider?verb=GetRecord&metadataPrefix=fgdc&identifier=11532_fgdc",
-    "PublicationTimestamp": "2016-04-26T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "Rights": [
-        "Public"
-    ],
-    "SpatialCoverage": "(90S-84N,180W-180E)",
-    "TempCoverageBegin": 62956094399,
-    "TempCoverageEnd": 63366321599,
-    "TemporalCoverage": " period : ( 1996-01-01T11:59:59Z - 2008-12-31T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1996-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2008-12-31T11:59:59Z",
-    "author": [
-        "CCIN/PDC Director",
-        "Canadian Space Agency",
-        "PDC Data Manager",
-        "Canadian Ice Service, Environment and Climate Change Canada",
-        "MacDonald, Dettwiler and Associates Ltd."
-    ],
-    "fulltext": "11532_fgdc;2017-04-09T22:02:26Z;PDCMetadata;MacDonald, Dettwiler and Associates Ltd.;MacDonald, Dettwiler and Associates Ltd.;Canadian Ice Service, Environment and Climate Change Canada;Canadian Space Agency;CCIN/PDC Director;PDC Data Manager;20160426;RADARSAT Satellite Imagery in the Polar Data Catalogue;Computer file;unknown;For Arctic RADARSAT-1 images:  RADARSAT-1 Polar Science Dataset - Canadian Space Agency Arctic Imagery 1996-2007/Canadian Ice Service Image Archive 1997-2006. Waterloo, Canada: Canadian Cryospheric Information Network (CCIN).  >>For Antarctic RADARSAT-2 images:  MacDonald, Dettwiler and Associates Ltd., 2014. RADARSAT-2 Antarctica Mosaics and Tiles, 2008. Waterloo, Canada: Canadian Cryospheric Information Network (CCIN).;unavailable;https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=11532;The RADARSAT-1 imagery collection of northern Canada (the RADARSAT Polar Science Dataset), containing over 27,000 images, is composed of the following elements:  &gt;Blanket coverage in Fine Beam Mode of the Canadian polar region and the Arctic Archipelago (collected during the Canadian Interferometric Mission, 2000-2001).  &gt;Maximum and minimum ice extent Arctic snapshots from 2003 to 2006 - the ScanSAR Seasonal Circum-Polar snapshots.  &gt;Thematically-relevant imagery acquired over specific areas of interest (Supersites) identified by the cryospheric and remote sensing research communities.  &gt;The Canadian Ice Service imagery dataset acquired since 1996.  &gt;Canadian Arctic land mass mosaics - summer and winter 1998-1999.  &gt;&gt;The 2008 RADARSAT-2 full continental mosaics of Antarctica are available in 8-bit, 16-bit, and 32-bit modes; 100 m, 200 m, 400 m, and 800 m resolutions;  and in HH and HV polarizations.  Eighty-nine individual tile products covering a grid of the entire continent at higher resolution (25 m) are available in 16-bit and HH or HV polarizations.;The RADARSAT satellite image collections in the Polar Data Catalogue include imagery from both RADARSAT-1 and RADARSAT-2.   &gt;&gt;During its operation (1995-2013), the RADARSAT-1 satellite and sensors collected Synthetic Aperture Radar (SAR) imagery, including a significant portion which is attributable to the systematic data collection effort of the Background Mission. The archive of imagery developed during the Background Mission has emphasized, among other things, the RADARSAT imaging capabilities during times of inclement weather and low illumination conditions.  Practical experience by operational users has demonstrated that RADARSAT imagery is an excellent and reliable source for mapping and monitoring sea ice and other cryospheric features in northern latitudes during different times of the year. RADARSAT-1 has collected an incredible wealth of SAR imagery over polar regions, including northern Canada. A large portion of this archive is available on the Polar Data Catalogue as the RADARSAT Polar Science Dataset.     &gt;&gt;The RADARSAT-2 Antarctic Mapping Initiative was undertaken to produce a continental mosaic consistent with the 1997 RADARSAT-1 Antarctic Mapping Mission. The resulting mosaics and individual tiles, produced in collaboration with the Byrd Polar Research Center, cover all the way to the South Pole, permitted by the left-looking capabilities of the RADARSAT-2. This is only the second time pole-to-coast mosaic SAR (Synthetic Aperture Radar) coverage has been achieved, the first time having been the RADARSAT-1 Antarctic Mapping Mission in 1997. In addition to enhancing the achievements of previous RADARSAT-1 Antarctic missions, the intent of this mission was to facilitate change analysis through space-borne observation of ice sheets. Such data are important for generation of global climate products, including models. The mission was the result of international collaboration associated with the International Polar Year (IPY), incorporating input from the scientific community, with the goal of making science products available for free. This dataset is a Canadian Space Agency contribution to IPY.;Summary: Not Applicable Research Program(s): CCIN. For further information: www.polardata.ca/pdcsearch;19960101;20081231;NULL;In work;Irregular;-180;180;84;-90;NULL;Antarctic;Archive;Arctic;Glaciers;Ice shelf;RADARSAT;Satellite imagery;Sea ice;North and South polar regions;NULL;Public;NULL;Canadian Cryospheric Information Network;Polar Data Catalogue;NULL;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;NULL;Polar Data Catalogue;Canadian Cryospheric Information Network;Director;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;11532;Research programs, CCIN, or ArcticNet take no liability for the use or transmission of this data;20160426;20160426;Polar Data Catalogue;Canadian Cryospheric Information Network;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;FGDC Content Standards for Digital Geospatial Metadata;FGDC-STD-001-1998",
-    "group": "pdc",
-    "groups": [
-        {
-            "name": "pdc"
-        }
-    ],
-    "name": "0adae04e-2a7d-58f9-9c49-e081c949963a",
-    "notes": [
-        "The RADARSAT-1 imagery collection of northern Canada (the RADARSAT Polar Science Dataset), containing over 27,000 images, is composed of the following elements:  &gt;Blanket coverage in Fine Beam Mode of the Canadian polar region and the Arctic Archipelago (collected during the Canadian Interferometric Mission, 2000-2001).  &gt;Maximum and minimum ice extent Arctic snapshots from 2003 to 2006 - the ScanSAR Seasonal Circum-Polar snapshots.  &gt;Thematically-relevant imagery acquired over specific areas of interest (Supersites) identified by the cryospheric and remote sensing research communities.  &gt;The Canadian Ice Service imagery dataset acquired since 1996.  &gt;Canadian Arctic land mass mosaics - summer and winter 1998-1999.  &gt;&gt;The 2008 RADARSAT-2 full continental mosaics of Antarctica are available in 8-bit, 16-bit, and 32-bit modes; 100 m, 200 m, 400 m, and 800 m resolutions;  and in HH and HV polarizations.  Eighty-nine individual tile products covering a grid of the entire continent at higher resolution (25 m) are available in 16-bit and HH or HV polarizations."
-    ],
-    "oai_identifier": [
-        "11532_fgdc"
-    ],
-    "oai_set": [
-        "PDCMetadata"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-180,-90],[-180,84],[180,84],[180,-90],[-180,-90]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Antarctic"
-        },
-        {
-            "name": "Archive"
-        },
-        {
-            "name": "Arctic"
-        },
-        {
-            "name": "Glaciers"
-        },
-        {
-            "name": "Ice shelf"
-        },
-        {
-            "name": "RADARSAT"
-        },
-        {
-            "name": "Satellite imagery"
-        },
-        {
-            "name": "Sea ice"
-        }
-    ],
-    "title": [
-        "RADARSAT Satellite Imagery in the Polar Data Catalogue"
-    ],
-    "url": "https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=11532"
-}
\ No newline at end of file
diff --git a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0afca2c8-d699-557b-8846-6431b0235963.json b/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0afca2c8-d699-557b-8846-6431b0235963.json
deleted file mode 100644
index 79b86c93..00000000
--- a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0afca2c8-d699-557b-8846-6431b0235963.json
+++ /dev/null
@@ -1,101 +0,0 @@
-{
-    "Contact": [
-        "bscott@qia.ca"
-    ],
-    "Contributor": [
-        "Qikiqtani Inuit Association"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MapperVersion": [
-        "1) Aim: &#x0d;\nTo collect baseline data of community-identified socio-economic areas of concern (hunting and food sharing practices, family and community relationships, and civic and volunteer participation) in four communities affected by resource development.&#x0d;\n&#x0d;\n2) Objectives:&#x0d;\ni) Administer a face-to-face survey to randomly selected adults currently living in Pond Inlet, Clyde River, Igloolik, and Cape Dorset.&#x0d;\nii) To establish baseline data to enable future research of experiences and perceptions of change in communities newly impacted by resource development projects.&#x0d;\niii) To create an opportunity for the community voice to be represented in the collection of socio-economic data, specifically in areas of concern identified and validated by community members. &#x0d;\niv) To build social sciences research capacity with a team of community researchers. &#x0d;\nv) To provide results which: communities can use to advocate for resources; Inuit organizations can use when negotiating Inuit Impact Benefit Agreements; and Stakeholders can use to further understanding of the experience of change in communities impacted by resource development.&#x0d;\n&#x0d;\n3) Rationale:&#x0d;\nIn the mid-20th century, Inuit faced massive social change brought about by the arrival of southern institutional organizations and the establishment of settled communities. Currently, several communities in the Qikiqtani region are experiencing a new wave of social change as resource development intensifies. Many community members are concerned that their way of life will change dramatically once again. &#x0d;\nInuusuip Asijjiqpallianinganik Ujjiqsurniq (IAU) is a community-based socio-economic research project which aims to capture baseline data of current aspects of community life, including hunting and food sharing practices, family and community relationships, and community civic and volunteer participation in order to provide communities with data that they can use to advocate for resources to mitigate the perceived social impacts of mining."
-    ],
-    "MetaDataAccess": "http://www.polardata.ca/oai/provider?verb=GetRecord&metadataPrefix=fgdc&identifier=12666_fgdc",
-    "PublicationTimestamp": "2017-09-11T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "Rights": [
-        "Limited"
-    ],
-    "SpatialCoverage": "(63N-72N,77W-68W)",
-    "TempCoverageBegin": 63505681199,
-    "TempCoverageEnd": 63626554799,
-    "TemporalCoverage": " period : ( 2013-06-01T11:59:59Z - 2017-03-31T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2013-06-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2017-03-31T11:59:59Z",
-    "author": [
-        "Milton, Michael",
-        "Qikiqtani Inuit Association",
-        "Amarualik, Tommy",
-        "Scott, Bethany",
-        "Mucktar, Ena",
-        "Iqalukjuak, Niore",
-        "Pootoogook, Evie",
-        "Saila, Joe",
-        "Arnatsiaq, Sara",
-        "Kalluk, Josh"
-    ],
-    "fulltext": "12666_fgdc;2017-09-11T18:58:33Z;PDCMetadata;Scott, Bethany;Qikiqtani Inuit Association;Amarualik, Tommy;Arnatsiaq, Sara;Iqalukjuak, Niore;Kalluk, Josh;Milton, Michael;Mucktar, Ena;Pootoogook, Evie;Saila, Joe;20170911;Inuusiup Asijjiqpallianinganik Ujjiqsurniq: Understanding Community Change in Qikiqtaaluk (NGMP ID SE06);Computer file;unknown;Data Citation: Qikiqtani Inuit Association, Scott, B., Saila, J., Pootoogook, E., Arnatsiaq, S., Iqalukjuak, N., Mucktar, E., Kalluk, J., Amarualik, T. and Milton, M. (2017) Inuusiup Asijjiqpallianinganik Ujjiqsurniq: Understanding Community Change in Qikiqtaaluk (NGMP ID SE06). Waterloo, Canada: Canadian Cryospheric Information Network (CCIN). Unpublished Data\nAdditional Publication- can be accessed: Arnatsiaq S., Iqalukjuak N., Mucktar E., Pootoogook E., Amarualik T., Kalluk J., Milton M., Saila J., Scott, B. (2016). Inuusiup asijjiqpallianinganik Ujjiqsurniq: Understanding Community Change in the Qikiqtaaluuk. Qikiqtani Inuit Association. Iqaluit. \n(unpublished data);unavailable;https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=12666;1) Background:\nIn the mid-20th century, Inuit faced massive social change brought about by the arrival of southern institutional organizations and the establishment of settled communities. Currently, Inuit communities in the Qikiqtani region are experiencing a new wave of social change as the resource development intensifies. Many community members are concerned that their way of life will change dramatically once again. The research will capture data at repeated three year intervals on the important aspects of community life, as defined by the communities themselves, in four communities newly affected by extractive industries. \n2) Methodology:\nA team of community researchers was established from each of the four target communities in the Qikiqtani Region of Nunavut, affected by the development of mining activities. The community researchers ran focus groups and workshops in their communities to identify key areas of concern to the local community. A list of key indicators was developed by the community researchers from the areas of concern, and a questionnaire developed to gather data on these indicators. A questionnaire was designed to carry out a household survey to report on the indicators. A simple random sample of 96 respondents was selected in each community. Eligible respondents were community members 16 years or older whose principle place of residence was the target community. \n3) Results:\nThe workshops and focus groups identified three main areas of concern: Hunting and food sharing practices; family and community relationships; and civic and volunteer participation. From this, 53 indicators were developed. Baseline data was collected March/April 2016, with repeated applications of the survey every three years. The simple random sample of 96 individuals will mean that the 95% CI will not exceed +/-10%. \n4) Conclusions:\nA report will be generated from the results and circulated to all stakeholders.;1) Aim: &#x0d;\nTo collect baseline data of community-identified socio-economic areas of concern (hunting and food sharing practices, family and community relationships, and civic and volunteer participation) in four communities affected by resource development.&#x0d;\n&#x0d;\n2) Objectives:&#x0d;\ni) Administer a face-to-face survey to randomly selected adults currently living in Pond Inlet, Clyde River, Igloolik, and Cape Dorset.&#x0d;\nii) To establish baseline data to enable future research of experiences and perceptions of change in communities newly impacted by resource development projects.&#x0d;\niii) To create an opportunity for the community voice to be represented in the collection of socio-economic data, specifically in areas of concern identified and validated by community members. &#x0d;\niv) To build social sciences research capacity with a team of community researchers. &#x0d;\nv) To provide results which: communities can use to advocate for resources; Inuit organizations can use when negotiating Inuit Impact Benefit Agreements; and Stakeholders can use to further understanding of the experience of change in communities impacted by resource development.&#x0d;\n&#x0d;\n3) Rationale:&#x0d;\nIn the mid-20th century, Inuit faced massive social change brought about by the arrival of southern institutional organizations and the establishment of settled communities. Currently, several communities in the Qikiqtani region are experiencing a new wave of social change as resource development intensifies. Many community members are concerned that their way of life will change dramatically once again. &#x0d;\nInuusuip Asijjiqpallianinganik Ujjiqsurniq (IAU) is a community-based socio-economic research project which aims to capture baseline data of current aspects of community life, including hunting and food sharing practices, family and community relationships, and community civic and volunteer participation in order to provide communities with data that they can use to advocate for resources to mitigate the perceived social impacts of mining.;Summary: Not Applicable Research Program(s): NGMP. For further information: bscott@qia.ca;20130601;20170331;NULL;Complete;Irregular;-77;-68;72;63;NULL;Baffin Island;Capacity building;Cape Dorset;Clyde River;Community mobilization;Igloolik;Pond Inlet;Resource development;Social change;Pond Inlet, Igloolik, Clyde River, Cape Dorset, Qikiqtani region, Nunavut, Canada;NULL;Limited;NULL;Qikiqtani Inuit Association;Bethany Scott;NULL;mailing;Box 1340;Iqaluit;Nunavut;X0A0H0;Canada;897.975.8400;bscott@qia.ca;NULL;Polar Data Catalogue;Canadian Cryospheric Information Network;Director;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;12666;Research programs, CCIN, or ArcticNet take no liability for the use or transmission of this data;20160328;20170911;Bethany Scott;Qikiqtani Inuit Association;mailing;Box 1340;Iqaluit;Nunavut;X0A0H0;Canada;897.975.8400;bscott@qia.ca;FGDC Content Standards for Digital Geospatial Metadata;FGDC-STD-001-1998",
-    "group": "pdc",
-    "groups": [
-        {
-            "name": "pdc"
-        }
-    ],
-    "name": "0afca2c8-d699-557b-8846-6431b0235963",
-    "notes": [
-        "1) Background:\nIn the mid-20th century, Inuit faced massive social change brought about by the arrival of southern institutional organizations and the establishment of settled communities. Currently, Inuit communities in the Qikiqtani region are experiencing a new wave of social change as the resource development intensifies. Many community members are concerned that their way of life will change dramatically once again. The research will capture data at repeated three year intervals on the important aspects of community life, as defined by the communities themselves, in four communities newly affected by extractive industries. \n2) Methodology:\nA team of community researchers was established from each of the four target communities in the Qikiqtani Region of Nunavut, affected by the development of mining activities. The community researchers ran focus groups and workshops in their communities to identify key areas of concern to the local community. A list of key indicators was developed by the community researchers from the areas of concern, and a questionnaire developed to gather data on these indicators. A questionnaire was designed to carry out a household survey to report on the indicators. A simple random sample of 96 respondents was selected in each community. Eligible respondents were community members 16 years or older whose principle place of residence was the target community. \n3) Results:\nThe workshops and focus groups identified three main areas of concern: Hunting and food sharing practices; family and community relationships; and civic and volunteer participation. From this, 53 indicators were developed. Baseline data was collected March/April 2016, with repeated applications of the survey every three years. The simple random sample of 96 individuals will mean that the 95% CI will not exceed +/-10%. \n4) Conclusions:\nA report will be generated from the results and circulated to all stakeholders."
-    ],
-    "oai_identifier": [
-        "12666_fgdc"
-    ],
-    "oai_set": [
-        "PDCMetadata"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-77,63],[-77,72],[-68,72],[-68,63],[-77,63]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Baffin Island"
-        },
-        {
-            "name": "Capacity building"
-        },
-        {
-            "name": "Cape Dorset"
-        },
-        {
-            "name": "Clyde River"
-        },
-        {
-            "name": "Community mobilization"
-        },
-        {
-            "name": "Igloolik"
-        },
-        {
-            "name": "Pond Inlet"
-        },
-        {
-            "name": "Resource development"
-        },
-        {
-            "name": "Social change"
-        }
-    ],
-    "title": [
-        "Inuusiup Asijjiqpallianinganik Ujjiqsurniq: Understanding Community Change in Qikiqtaaluk (NGMP ID SE06)"
-    ],
-    "url": "https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=12666"
-}
\ No newline at end of file
diff --git a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0b223c0c-e861-5dff-8898-de289b2cbad7.json b/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0b223c0c-e861-5dff-8898-de289b2cbad7.json
deleted file mode 100644
index f4e9664c..00000000
--- a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0b223c0c-e861-5dff-8898-de289b2cbad7.json
+++ /dev/null
@@ -1,104 +0,0 @@
-{
-    "Contact": [
-        "ipy_dacn@scholarsportal.info"
-    ],
-    "Contributor": [
-        "IPY Data Assembly Centre Network"
-    ],
-    "DOI": "http://dx.doi.org/10.5443/11395",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MapperVersion": [
-        "The Circumpolar Flaw Lead (CFL) system study is a Canadian-led International Polar Year (IPY) initiative with over 350 participants from 27 countries. The study is multidisciplinary in nature, integrating the physical sciences, biological sciences, and Inuvialuit traditional knowledge.&#x0d;\n&#x0d;\nThe research of CFL expands upon previous multidisciplinary projects such as the North Water Polynya Study (NOW), the Surface Heat Budget of the Arctic (SHEBA), the Collaborative Interdisciplinary Cryospheric Experiment (C-ICE), and the Canadian Arctic Shelf Exchange Study (CASES) project.&#x0d;\n&#x0d;\nThe study is designed to examine the importance of climate processes in the changing nature of a flaw lead system in the northern Hemisphere, and the effect these changes will have on the marine ecosystem, contaminant transport, carbon flux and greenhouse gases.&#x0d;\n&#x0d;\nThe circumpolar flaw lead is a perennial characteristic of the Arctic Ocean, which forms when the central pack ice (which is mobile) moves away from coastal fast ice, opening a flaw lead which occurs throughout the winter season. The flaw lead is circumpolar in nature, with recurrent and interconnected polynyas occurring in the Norwegian, Icelandic, North American and Siberian sectors of the circumpolar arctic. &#x0d;\n&#x0d;\nDue to a reduced ice cover, these regions are exceedingly sensitive to physical forcing from both the atmosphere and ocean and provide a unique laboratory from which we can gain insights into the changing polar marine ecosystem. The CFL study was 293 days in duration and involved the overwintering of the CCGS Amundsen icebreaker in the Cape Bathurst flaw lead throughout the winter of 2007-2008, representing the first time a research icebreaker has remained mobile in a flaw lead throughout the winter.&#x0d;\n&#x0d;\nAside from ship-based research, background research has been ongoing for a traditional knowledge study that researched many of the topics studied by scientists on board the Amundsen. This was done via interviews with local community members in the coastal communities within the Inuvialuit Settlement Region and was in collaboration with Inuit Circumpolar Council and Inuit Tapiriit Kanatami."
-    ],
-    "MetaDataAccess": "http://www.polardata.ca/oai/provider?verb=GetRecord&metadataPrefix=fgdc&identifier=11395_fgdc",
-    "PublicationTimestamp": "2012-07-09T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "Rights": [
-        "Public"
-    ],
-    "SpatialCoverage": "(66N-76N,141W-113W)",
-    "TempCoverageBegin": 63311021999,
-    "TempCoverageEnd": 63437165999,
-    "TemporalCoverage": " period : ( 2007-04-01T11:59:59Z - 2011-03-31T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2007-04-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2011-03-31T11:59:59Z",
-    "author": [
-        "Steve Ferguson",
-        "Jacques Gagn\u00e9",
-        "Daniel Bourgault",
-        "Philippe Archambault",
-        "Peter Galbraith",
-        "David Barber",
-        "Jessica Beaubier",
-        "Louis Fortier",
-        "Michel Gosselin"
-    ],
-    "fulltext": "11395_fgdc;2017-04-09T22:02:24Z;PDCMetadata;David Barber;David Barber;Daniel Bourgault;Jacques Gagn\u00e9;Jessica Beaubier;Louis Fortier;Michel Gosselin;Peter Galbraith;Philippe Archambault;Steve Ferguson;20120709;The Circumpolar Flaw Lead (CFL) system study;Computer file;unknown;Barber, D., P. Archambault, J. Beaubier, D. Bourgault, S. Ferguson, L. Fortier, J. Gagn\u00e9, P. Galbraith, M. Gosselin, Y. Gratton, J. Hanesiak, L. Harwood, P. Larouche, C. Lovejoy, R. Macdonald, R. Maranger, R. Marsden, C. Michel, C. Nozais, M. Poulin, L. Prieur, S. Raverty, P. Richard, S. Roy, Y. Simard, G. Stern, J.-\u00c9. Tremblay, and F. Wang, 2007. Circumpolar Flaw Lead (CFL) system study. Waterloo, Ontario, Canada: Canadian Cryospheric Information Network (CCIN). http://dx.doi.org/10.5443/11395;unavailable;https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=11395;The CFL project consisted of ten sub-project teams:  Physical oceanography; Sea ice; Light, nutrients, and primary production; Food webs; Marine mammals and birds; Gas fluxes; Carbon and nutrient fluxes; Contaminants; Modeling; and Traditional Knowledge.&#x0d;\n&#x0d;\nIn the fall of 2007, 74 open water sites were sampled throughout the Amundsen Gulf and southern Beaufort Sea. During the winter months, 44 drift sites were sampled, ranging in duration from 1-22 days. Due to thin sea ice and high ice mobility, the fast ice bridge between Cape Parry and Banks Island did not form. For this reason, we were unable to establish a semi-permanent ice camp as originally planned. Instead, a series of ice camps were set up at the fast ice edge at the mouths of Franklin and Darnley Bays in May and June. &#x0d;\n&#x0d;\nEarly results suggest that with decreasing ice cover we can expect powerful feedbacks into the climate system thereby exacerbating the reduction in multiyear sea ice, with commensurate changes in the ecosystem, biogeochemical cycling and human use of the flaw lead region.  Nutrients may become more available to the food web through a higher occurrence of ice edge upwelling as well as eddies carrying Pacific water into the Amundsen Gulf.  Frost flowers, which are produced on young first year ice, have been found to have an important role in atmospheric chemistry around flaw leads and may be important for contaminant transport. Marine mammal use of the flaw lead occurs much earlier and more extensively than previously known.&#x0d;\n&#x0d;\nTraditional Knowledge research efforts included the development, coordination and completion of community interviews in Sachs Harbour, Paulatuk and Ulukhaktok. This comprised of community-based field programs involving semi-directed interviews, a mapping component, and database development and input. The data gathered from 49 experts in 3 communities represents the first and most comprehensive documentation of Inuvialuit knowledge of the circumpolar flaw lead in the Beaufort Sea.&#x0d;\n&#x0d;\nThe Traditional Knowledge study showed that Inuvialuit have extensive knowledge of changes taking place in seasonal patterns, marine and freshwater systems, fish and wildlife of the Beaufort Sea and their uses of these resources, as well as the implications of these changes for human travel and Inuvialuit subsistence and traditional activities.;The Circumpolar Flaw Lead (CFL) system study is a Canadian-led International Polar Year (IPY) initiative with over 350 participants from 27 countries. The study is multidisciplinary in nature, integrating the physical sciences, biological sciences, and Inuvialuit traditional knowledge.&#x0d;\n&#x0d;\nThe research of CFL expands upon previous multidisciplinary projects such as the North Water Polynya Study (NOW), the Surface Heat Budget of the Arctic (SHEBA), the Collaborative Interdisciplinary Cryospheric Experiment (C-ICE), and the Canadian Arctic Shelf Exchange Study (CASES) project.&#x0d;\n&#x0d;\nThe study is designed to examine the importance of climate processes in the changing nature of a flaw lead system in the northern Hemisphere, and the effect these changes will have on the marine ecosystem, contaminant transport, carbon flux and greenhouse gases.&#x0d;\n&#x0d;\nThe circumpolar flaw lead is a perennial characteristic of the Arctic Ocean, which forms when the central pack ice (which is mobile) moves away from coastal fast ice, opening a flaw lead which occurs throughout the winter season. The flaw lead is circumpolar in nature, with recurrent and interconnected polynyas occurring in the Norwegian, Icelandic, North American and Siberian sectors of the circumpolar arctic. &#x0d;\n&#x0d;\nDue to a reduced ice cover, these regions are exceedingly sensitive to physical forcing from both the atmosphere and ocean and provide a unique laboratory from which we can gain insights into the changing polar marine ecosystem. The CFL study was 293 days in duration and involved the overwintering of the CCGS Amundsen icebreaker in the Cape Bathurst flaw lead throughout the winter of 2007-2008, representing the first time a research icebreaker has remained mobile in a flaw lead throughout the winter.&#x0d;\n&#x0d;\nAside from ship-based research, background research has been ongoing for a traditional knowledge study that researched many of the topics studied by scientists on board the Amundsen. This was done via interviews with local community members in the coastal communities within the Inuvialuit Settlement Region and was in collaboration with Inuit Circumpolar Council and Inuit Tapiriit Kanatami.;Summary: A flaw lead is a natural opening in the sea ice that forms and persists throughout the winter, providing an exceptional opportunity to study the Arctic Ocean. This project is looking at ocean dynamics, climate, marine ecosystems, contaminants, greenhouse gases and carbon and nutrient cycles. The data was collected during the first ever overwintering of an icebreaker, the CCGS Amundsen, in a flaw lead system in the Canadian Arctic. Results are helping explain and predict how climate change will affect a flaw lead system. In addition, traditional knowledge is providing further perspective of how the Arctic Ocean has changed over time. Research Program(s): IPY. For further information: 476 Wallace Building, University of Manitoba, Winnipeg, Manitoba, R3T 2N2, Canada, dbarber@cc.umanitoba.ca;20070401;20110331;NULL;In work;None planned;-141;-113;76;66;NULL;Beaufort Sea;Canadian Arctic Archipelago;Carbon dioxide;Marine birds;Marine mammals;Modeling;Nutrient cycling;Primary production;Sea ice;Traditional Knowledge;Amundsen Gulf and southern Beaufort Sea, Arctic Ocean; Inuvik (NT, Canada); Paulatuk (NT, Canada); Sachs Harbour (NT, Canada); Tuktoyaktuk (NT, Canada); Ulukhaktok (NT, Canada);NULL;Public;NULL;IPY Data Assembly Centre Network;International Polar Year;NULL;mailing;Government of Canada IPY Programme;Ottawa;ON;K1A0H4;Canada;N/A;ipy_dacn@scholarsportal.info;NULL;Polar Data Catalogue;Canadian Cryospheric Information Network;Director;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;11395;Research programs, CCIN, or ArcticNet take no liability for the use or transmission of this data;20120709;20120709;International Polar Year;IPY Data Assembly Centre Network;mailing;Government of Canada IPY Programme;Ottawa;ON;K1A0H4;Canada;N/A;ipy_dacn@scholarsportal.info;FGDC Content Standards for Digital Geospatial Metadata;FGDC-STD-001-1998",
-    "group": "pdc",
-    "groups": [
-        {
-            "name": "pdc"
-        }
-    ],
-    "name": "0b223c0c-e861-5dff-8898-de289b2cbad7",
-    "notes": [
-        "The CFL project consisted of ten sub-project teams:  Physical oceanography; Sea ice; Light, nutrients, and primary production; Food webs; Marine mammals and birds; Gas fluxes; Carbon and nutrient fluxes; Contaminants; Modeling; and Traditional Knowledge.&#x0d;\n&#x0d;\nIn the fall of 2007, 74 open water sites were sampled throughout the Amundsen Gulf and southern Beaufort Sea. During the winter months, 44 drift sites were sampled, ranging in duration from 1-22 days. Due to thin sea ice and high ice mobility, the fast ice bridge between Cape Parry and Banks Island did not form. For this reason, we were unable to establish a semi-permanent ice camp as originally planned. Instead, a series of ice camps were set up at the fast ice edge at the mouths of Franklin and Darnley Bays in May and June. &#x0d;\n&#x0d;\nEarly results suggest that with decreasing ice cover we can expect powerful feedbacks into the climate system thereby exacerbating the reduction in multiyear sea ice, with commensurate changes in the ecosystem, biogeochemical cycling and human use of the flaw lead region.  Nutrients may become more available to the food web through a higher occurrence of ice edge upwelling as well as eddies carrying Pacific water into the Amundsen Gulf.  Frost flowers, which are produced on young first year ice, have been found to have an important role in atmospheric chemistry around flaw leads and may be important for contaminant transport. Marine mammal use of the flaw lead occurs much earlier and more extensively than previously known.&#x0d;\n&#x0d;\nTraditional Knowledge research efforts included the development, coordination and completion of community interviews in Sachs Harbour, Paulatuk and Ulukhaktok. This comprised of community-based field programs involving semi-directed interviews, a mapping component, and database development and input. The data gathered from 49 experts in 3 communities represents the first and most comprehensive documentation of Inuvialuit knowledge of the circumpolar flaw lead in the Beaufort Sea.&#x0d;\n&#x0d;\nThe Traditional Knowledge study showed that Inuvialuit have extensive knowledge of changes taking place in seasonal patterns, marine and freshwater systems, fish and wildlife of the Beaufort Sea and their uses of these resources, as well as the implications of these changes for human travel and Inuvialuit subsistence and traditional activities."
-    ],
-    "oai_identifier": [
-        "11395_fgdc"
-    ],
-    "oai_set": [
-        "PDCMetadata"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-141,66],[-141,76],[-113,76],[-113,66],[-141,66]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Beaufort Sea"
-        },
-        {
-            "name": "Canadian Arctic Archipelago"
-        },
-        {
-            "name": "Carbon dioxide"
-        },
-        {
-            "name": "Marine birds"
-        },
-        {
-            "name": "Marine mammals"
-        },
-        {
-            "name": "Modeling"
-        },
-        {
-            "name": "Nutrient cycling"
-        },
-        {
-            "name": "Primary production"
-        },
-        {
-            "name": "Sea ice"
-        },
-        {
-            "name": "Traditional Knowledge"
-        }
-    ],
-    "title": [
-        "The Circumpolar Flaw Lead (CFL) system study"
-    ],
-    "url": "https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=11395"
-}
\ No newline at end of file
diff --git a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0b337416-6927-58ff-ab1d-780122ca47db.json b/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0b337416-6927-58ff-ab1d-780122ca47db.json
deleted file mode 100644
index 296c3c91..00000000
--- a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0b337416-6927-58ff-ab1d-780122ca47db.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "scott.lamoureux@queensu.ca"
-    ],
-    "Contributor": [
-        "Queen's University"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MapperVersion": [
-        "To characterize plant nutrient availability during two 2-week time periods (early and late season) at 12 plots representing three different vegetation communities and within four experimental watersheds."
-    ],
-    "MetaDataAccess": "http://www.polardata.ca/oai/provider?verb=GetRecord&metadataPrefix=fgdc&identifier=9857_fgdc",
-    "PublicationTimestamp": "2013-03-28T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "Rights": [
-        "Limited"
-    ],
-    "SpatialCoverage": "(75N,110W)",
-    "TempCoverageBegin": 63350074799,
-    "TempCoverageEnd": 63353789999,
-    "TemporalCoverage": " period : ( 2008-06-26T11:59:59Z - 2008-08-08T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2008-06-26T11:59:59Z",
-    "TemporalCoverage:EndDate": "2008-08-08T11:59:59Z",
-    "author": [
-        "Neal Scott",
-        "Fiona Gregory"
-    ],
-    "fulltext": "9857_fgdc;2017-04-09T22:02:14Z;PDCMetadata;Neal Scott;Fiona Gregory;20130328;2008 Soil Nutrient Availability, Cape Bounty;Computer file;unknown;Scott, N., and F. Gregory, unpublished data;unavailable;https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=9857;The PRS probes, manufactured by Western Ag Innovations Inc, are cation- or anion-exchange membranes encased in a plastic holding device. 4 cation probes  and 4 anion probes were inserted into the soil along a transect across each plot. In polar desert sites an extra set of probes was deployed in a vegetated area. Each pair of probes was 10 cm apart. The twelve plots represent four examples each of wet sedge meadow, mesic heath, and polar desert vegetation communities. The first burial was made on the 26th to 27th of June and the probes retrieved on the 17th to 18th of July. The second burial took place on the 17th and 18th of July and these probes were retrieved on the 7th to 8th of August. After retrieval the probes were rinsed and sent to Western Ag Innovations for analysis. The nutrients measured are Total N, NO3-N, NH4-N, Ca, Mg, K, P, Fe, Mn, Cu, Zn, B, S, Pb, Al, and Cd. Most of the Cape Bounty sites were below the detection limit for Cd and Pb.;To characterize plant nutrient availability during two 2-week time periods (early and late season) at 12 plots representing three different vegetation communities and within four experimental watersheds.;Summary: Not Applicable Research Program(s): ArcticNet,IPY. For further information: neal.scott@queensu.ca;20080626;20080808;NULL;Complete;As needed;-109.5;-109.5;74.9;74.9;NULL;Cape Bounty;Melville Island;Nutrients;Plants;Soil chemistry;Soils;Cape Bounty, Melville Island, Nunavut;NULL;Limited;NULL;Queen's University;Scott Lamoureux;NULL;mailing;Department of Geography;Kingston;ON;K7L3N6;Canada;613-533-6033;scott.lamoureux@queensu.ca;NULL;Polar Data Catalogue;Canadian Cryospheric Information Network;Director;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;9857;Research programs, CCIN, or ArcticNet take no liability for the use or transmission of this data;20130328;20130328;Scott Lamoureux;Queen's University;mailing;Department of Geography;Kingston;ON;K7L3N6;Canada;613-533-6033;scott.lamoureux@queensu.ca;FGDC Content Standards for Digital Geospatial Metadata;FGDC-STD-001-1998",
-    "group": "pdc",
-    "groups": [
-        {
-            "name": "pdc"
-        }
-    ],
-    "name": "0b337416-6927-58ff-ab1d-780122ca47db",
-    "notes": [
-        "The PRS probes, manufactured by Western Ag Innovations Inc, are cation- or anion-exchange membranes encased in a plastic holding device. 4 cation probes  and 4 anion probes were inserted into the soil along a transect across each plot. In polar desert sites an extra set of probes was deployed in a vegetated area. Each pair of probes was 10 cm apart. The twelve plots represent four examples each of wet sedge meadow, mesic heath, and polar desert vegetation communities. The first burial was made on the 26th to 27th of June and the probes retrieved on the 17th to 18th of July. The second burial took place on the 17th and 18th of July and these probes were retrieved on the 7th to 8th of August. After retrieval the probes were rinsed and sent to Western Ag Innovations for analysis. The nutrients measured are Total N, NO3-N, NH4-N, Ca, Mg, K, P, Fe, Mn, Cu, Zn, B, S, Pb, Al, and Cd. Most of the Cape Bounty sites were below the detection limit for Cd and Pb."
-    ],
-    "oai_identifier": [
-        "9857_fgdc"
-    ],
-    "oai_set": [
-        "PDCMetadata"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-109.5,74.9],[-109.5,74.9],[-109.5,74.9],[-109.5,74.9],[-109.5,74.9]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Cape Bounty"
-        },
-        {
-            "name": "Melville Island"
-        },
-        {
-            "name": "Nutrients"
-        },
-        {
-            "name": "Plants"
-        },
-        {
-            "name": "Soil chemistry"
-        },
-        {
-            "name": "Soils"
-        }
-    ],
-    "title": [
-        "2008 Soil Nutrient Availability, Cape Bounty"
-    ],
-    "url": "https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=9857"
-}
\ No newline at end of file
diff --git a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0b4f0678-610e-5918-96cb-e73c13ac1700.json b/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0b4f0678-610e-5918-96cb-e73c13ac1700.json
deleted file mode 100644
index 761dfc11..00000000
--- a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0b4f0678-610e-5918-96cb-e73c13ac1700.json
+++ /dev/null
@@ -1,86 +0,0 @@
-{
-    "Contact": [
-        "josee.lefebvre@ec.gc.ca"
-    ],
-    "Contributor": [
-        "Service canadien de la faune"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MapperVersion": [
-        "Monitoring the occurence of all tundra species encountered daily"
-    ],
-    "MetaDataAccess": "http://www.polardata.ca/oai/provider?verb=GetRecord&metadataPrefix=fgdc&identifier=1734_fgdc",
-    "PublicationTimestamp": "2015-07-24T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "Rights": [
-        "Public"
-    ],
-    "SpatialCoverage": "(80N-80N,86W-83W)",
-    "TempCoverageBegin": 63317933999,
-    "TempCoverageEnd": 63385153199,
-    "TemporalCoverage": " period : ( 2007-06-20T11:59:59Z - 2009-08-06T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2007-06-20T11:59:59Z",
-    "TemporalCoverage:EndDate": "2009-08-06T11:59:59Z",
-    "author": [
-        "Jos\u00e9e Lefebvre, Canadian Wildlife Service, Quebec Region"
-    ],
-    "fulltext": "1734_fgdc;2017-04-09T22:02:12Z;PDCMetadata;Jos\u00e9e Lefebvre, Canadian Wildlife Service, Quebec Region;Jos\u00e9e Lefebvre, Canadian Wildlife Service, Quebec Region;Jos\u00e9e Lefebvre, Canadian Wildlife Service, Quebec Region;20150724;Monitoring the relative abundance of bird and mammal species at Fosheim Peninsula,  Ellesmere Island;Computer file;unknown;J. Lefebvre, unpublished data;unavailable;https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=1734;The relative abundance of species is recorded as the number of individuals seen per hour spent in the field per observer. Each observer record daily the animal species encountered in the field and the number of individuals observed. To correct for any potential biases the activities and mode of transportation of observers is also taken into account.&#x0d;\n&#x0d;\nWe also monitor the nests of bird species that are not part of our long-term monitoring and are found opportunistically, such as King Eider, Long-tailed Duck and Red-throated Loon.;Monitoring the occurence of all tundra species encountered daily;Summary: Not Applicable Research Program(s): IPY. For further information: josee.lefebvre@ec.gc.ca;20070620;20090806;NULL;Complete;Annually;-86.5;-82.6;80.3;79.9;NULL;Abundance;Birds;Ellesmere Island;Eureka;Fosheim Peninsula;Mammals;Tundra;Fosheim Peninsula, Ellesmere Island, Nunavut;NULL;Public;NULL;Service canadien de la faune;Jos\u00e9e Lefebvre;NULL;mailing;1141, route de l'\u00c9glise;Sainte-Foy;Qc;G1V4H5;Canada;418-648-3915;418-648-5511;josee.lefebvre@ec.gc.ca;NULL;Polar Data Catalogue;Canadian Cryospheric Information Network;Director;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;1734;Research programs, CCIN, or ArcticNet take no liability for the use or transmission of this data;20150724;20150724;Jos\u00e9e Lefebvre;Service canadien de la faune;mailing;1141, route de l'\u00c9glise;Sainte-Foy;Qc;G1V4H5;Canada;418-648-3915;418-648-5511;josee.lefebvre@ec.gc.ca;FGDC Content Standards for Digital Geospatial Metadata;FGDC-STD-001-1998",
-    "group": "pdc",
-    "groups": [
-        {
-            "name": "pdc"
-        }
-    ],
-    "name": "0b4f0678-610e-5918-96cb-e73c13ac1700",
-    "notes": [
-        "The relative abundance of species is recorded as the number of individuals seen per hour spent in the field per observer. Each observer record daily the animal species encountered in the field and the number of individuals observed. To correct for any potential biases the activities and mode of transportation of observers is also taken into account.&#x0d;\n&#x0d;\nWe also monitor the nests of bird species that are not part of our long-term monitoring and are found opportunistically, such as King Eider, Long-tailed Duck and Red-throated Loon."
-    ],
-    "oai_identifier": [
-        "1734_fgdc"
-    ],
-    "oai_set": [
-        "PDCMetadata"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-86.5,79.9],[-86.5,80.3],[-82.6,80.3],[-82.6,79.9],[-86.5,79.9]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Abundance"
-        },
-        {
-            "name": "Birds"
-        },
-        {
-            "name": "Ellesmere Island"
-        },
-        {
-            "name": "Eureka"
-        },
-        {
-            "name": "Fosheim Peninsula"
-        },
-        {
-            "name": "Mammals"
-        },
-        {
-            "name": "Tundra"
-        }
-    ],
-    "title": [
-        "Monitoring the relative abundance of bird and mammal species at Fosheim Peninsula,  Ellesmere Island"
-    ],
-    "url": "https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=1734"
-}
\ No newline at end of file
diff --git a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0b76db9a-d6f9-57ea-8300-9c24005dccf8.json b/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0b76db9a-d6f9-57ea-8300-9c24005dccf8.json
deleted file mode 100644
index 2c65eade..00000000
--- a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0b76db9a-d6f9-57ea-8300-9c24005dccf8.json
+++ /dev/null
@@ -1,88 +0,0 @@
-{
-    "Contact": [
-        "james.ford@mcgill.ca"
-    ],
-    "Contributor": [
-        "McGill University"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MapperVersion": [
-        "Community food programs (CFPs) provide an important safety-net for highly food insecure community members in the larger settlements of the Canadian Arctic. This study identifies who is using CFPs and why, drawing upon a case study from Inuvik, Northwest Territories. This work is compared with a similar study from Iqaluit, Nunavut, allowing the development of an Arctic-wide understanding of CFPs use : a neglected topic in the northern food security literature."
-    ],
-    "MetaDataAccess": "http://www.polardata.ca/oai/provider?verb=GetRecord&metadataPrefix=fgdc&identifier=11955_fgdc",
-    "PublicationTimestamp": "2015-03-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "Rights": [
-        "Limited"
-    ],
-    "SpatialCoverage": "(68N-68N,133W-43W)",
-    "TempCoverageBegin": 63454273199,
-    "TempCoverageEnd": 63459979199,
-    "TemporalCoverage": " period : ( 2011-10-15T11:59:59Z - 2011-12-20T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2011-10-15T11:59:59Z",
-    "TemporalCoverage:EndDate": "2011-12-20T11:59:59Z",
-    "author": [
-        "Ford, James",
-        "Chatwood, Susan",
-        "Lardeau, Marie-Pierre"
-    ],
-    "fulltext": "11955_fgdc;2017-04-09T22:02:34Z;PDCMetadata;Ford, James;Lardeau, Marie-Pierre;Chatwood, Susan;20150316;Community food programs (CFPs) in Inuvik, Northwest Territories;Computer file;unknown;Ford, J., Lardeau, M., Blackett, H., Chatwood, D., and Kurzewski, D. (2013). Community food program use in Inuvik, Northwest Territories. BMC Public Health 13:970.;unavailable;https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=11955;The method used for this study were Photovoice workshops (n=7), a modified USDA food security survey and open ended interviews with CFP users (n=54) in Inuvik. The results show that users of CFPs in Inuvik are more likely to be housing insecure, female, middle aged (35-64), unemployed, Aboriginal, and lack a high school education. Participants are primarily chronic users, and depend on CFPs for regular food access. In conclusion, this work indicates the presence of chronically food insecure groups who have not benefited from the economic development and job opportunities offered in larger regional centers of the Canadian Arctic, and for whom traditional kinship-based food sharing networks have been unable to fully meet their dietary needs. While CFPs do not address the underlying causes of food insecurity, they provide an important service for communities undergoing rapid change, and need greater focus in food policy herein.;Community food programs (CFPs) provide an important safety-net for highly food insecure community members in the larger settlements of the Canadian Arctic. This study identifies who is using CFPs and why, drawing upon a case study from Inuvik, Northwest Territories. This work is compared with a similar study from Iqaluit, Nunavut, allowing the development of an Arctic-wide understanding of CFPs use : a neglected topic in the northern food security literature.;Summary: Not Applicable Research Program(s): ArcticNet. For further information: james.ford@mcgill.ca;20111015;20111220;NULL;Complete;None planned;-133;-43;68;68;NULL;Community vulnerability;Food security;Homelessness;Inuvik;Northwest Territories;Poverty;Social change;Inuvik, Northwest Territories, Canada;NULL;Limited;NULL;McGill University;James Ford;NULL;mailing;805 Sherbrooke St;Montreal;QC;H3A0B9;Canada;514-398-4960;james.ford@mcgill.ca;NULL;Polar Data Catalogue;Canadian Cryospheric Information Network;Director;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;11955;Research programs, CCIN, or ArcticNet take no liability for the use or transmission of this data;20150316;20150316;James Ford;McGill University;mailing;805 Sherbrooke St;Montreal;QC;H3A0B9;Canada;514-398-4960;james.ford@mcgill.ca;FGDC Content Standards for Digital Geospatial Metadata;FGDC-STD-001-1998",
-    "group": "pdc",
-    "groups": [
-        {
-            "name": "pdc"
-        }
-    ],
-    "name": "0b76db9a-d6f9-57ea-8300-9c24005dccf8",
-    "notes": [
-        "The method used for this study were Photovoice workshops (n=7), a modified USDA food security survey and open ended interviews with CFP users (n=54) in Inuvik. The results show that users of CFPs in Inuvik are more likely to be housing insecure, female, middle aged (35-64), unemployed, Aboriginal, and lack a high school education. Participants are primarily chronic users, and depend on CFPs for regular food access. In conclusion, this work indicates the presence of chronically food insecure groups who have not benefited from the economic development and job opportunities offered in larger regional centers of the Canadian Arctic, and for whom traditional kinship-based food sharing networks have been unable to fully meet their dietary needs. While CFPs do not address the underlying causes of food insecurity, they provide an important service for communities undergoing rapid change, and need greater focus in food policy herein."
-    ],
-    "oai_identifier": [
-        "11955_fgdc"
-    ],
-    "oai_set": [
-        "PDCMetadata"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-133,68],[-133,68],[-43,68],[-43,68],[-133,68]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Community vulnerability"
-        },
-        {
-            "name": "Food security"
-        },
-        {
-            "name": "Homelessness"
-        },
-        {
-            "name": "Inuvik"
-        },
-        {
-            "name": "Northwest Territories"
-        },
-        {
-            "name": "Poverty"
-        },
-        {
-            "name": "Social change"
-        }
-    ],
-    "title": [
-        "Community food programs (CFPs) in Inuvik, Northwest Territories"
-    ],
-    "url": "https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=11955"
-}
\ No newline at end of file
diff --git a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0ba6fc8a-ca4c-5942-9fb4-47fdcf105ad8.json b/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0ba6fc8a-ca4c-5942-9fb4-47fdcf105ad8.json
deleted file mode 100644
index 9bd81db7..00000000
--- a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0ba6fc8a-ca4c-5942-9fb4-47fdcf105ad8.json
+++ /dev/null
@@ -1,93 +0,0 @@
-{
-    "Contact": [
-        "dbarber@cc.umanitoba.ca"
-    ],
-    "Contributor": [
-        "University of Manitoba"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MapperVersion": [
-        "To monitor the surface meteorological variables and motion of first and multi-year ice floes in the Southern Beaufort Sea from August 2015 onward."
-    ],
-    "MetaDataAccess": "http://www.polardata.ca/oai/provider?verb=GetRecord&metadataPrefix=fgdc&identifier=12581_fgdc",
-    "PublicationTimestamp": "2016-01-25T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "Rights": [
-        "Limited"
-    ],
-    "SpatialCoverage": "(70N-75N,180W-120W)",
-    "TempCoverageBegin": 63577393199,
-    "TempCoverageEnd": 63618782399,
-    "TemporalCoverage": " period : ( 2015-09-09T11:59:59Z - 2016-12-31T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2015-09-09T11:59:59Z",
-    "TemporalCoverage:EndDate": "2016-12-31T11:59:59Z",
-    "author": [
-        "Barber, David G.",
-        "Candlish, Lauren"
-    ],
-    "fulltext": "12581_fgdc;2017-04-09T22:02:44Z;PDCMetadata;Barber, David G.;Candlish, Lauren;20160125;Surface Meteorological Stations deployed on sea ice, Beaufort Sea - ArcticNet 2015;Computer file;unknown;Unpublished,\r\nArcticNet 2015,\r\nCentre for Earth Observation Science,\r\nUniversity of Manitoba.;unavailable;https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=12581;Surface meteorological stations for temperature, humidity, wind speed and wind direction were deployed on different types of sea ice. Hourly location, and meteorological data was transmitted using Iridium data burst modems. The data were received at the University of Manitoba. The towers were left on the ice, and assumed to have sunk when data transmission ceased. Ice floes sampled included thick first-year, and some large multi-year ice floes.;To monitor the surface meteorological variables and motion of first and multi-year ice floes in the Southern Beaufort Sea from August 2015 onward.;Summary: Not Applicable Research Program(s): ArcticNet. For further information: david.barber@umanitoba.ca;20150909;20161231;NULL;Complete;As needed;-180;-120;75;70;NULL;Beaufort Sea;Buoys;GPS;Motion;Relative humidity;Sea ice;Temperature;Wind direction;Wind speed;Beaufort Sea, Canadian Arctic;NULL;Limited;NULL;University of Manitoba;David  Barber;NULL;mailing;476 Wallace Building, University of Manitoba;Winnipeg;MB;R3T2N2;Canada;204-474-6981;204-272-1532;dbarber@cc.umanitoba.ca;NULL;Polar Data Catalogue;Canadian Cryospheric Information Network;Director;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;12581;Research programs, CCIN, or ArcticNet take no liability for the use or transmission of this data;20160125;20160125;David  Barber;University of Manitoba;mailing;476 Wallace Building, University of Manitoba;Winnipeg;MB;R3T2N2;Canada;204-474-6981;204-272-1532;dbarber@cc.umanitoba.ca;FGDC Content Standards for Digital Geospatial Metadata;FGDC-STD-001-1998",
-    "group": "pdc",
-    "groups": [
-        {
-            "name": "pdc"
-        }
-    ],
-    "name": "0ba6fc8a-ca4c-5942-9fb4-47fdcf105ad8",
-    "notes": [
-        "Surface meteorological stations for temperature, humidity, wind speed and wind direction were deployed on different types of sea ice. Hourly location, and meteorological data was transmitted using Iridium data burst modems. The data were received at the University of Manitoba. The towers were left on the ice, and assumed to have sunk when data transmission ceased. Ice floes sampled included thick first-year, and some large multi-year ice floes."
-    ],
-    "oai_identifier": [
-        "12581_fgdc"
-    ],
-    "oai_set": [
-        "PDCMetadata"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-180,70],[-180,75],[-120,75],[-120,70],[-180,70]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Beaufort Sea"
-        },
-        {
-            "name": "Buoys"
-        },
-        {
-            "name": "GPS"
-        },
-        {
-            "name": "Motion"
-        },
-        {
-            "name": "Relative humidity"
-        },
-        {
-            "name": "Sea ice"
-        },
-        {
-            "name": "Temperature"
-        },
-        {
-            "name": "Wind direction"
-        },
-        {
-            "name": "Wind speed"
-        }
-    ],
-    "title": [
-        "Surface Meteorological Stations deployed on sea ice, Beaufort Sea - ArcticNet 2015"
-    ],
-    "url": "https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=12581"
-}
\ No newline at end of file
diff --git a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0bc5b668-31cb-56e7-971a-94cf0d976260.json b/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0bc5b668-31cb-56e7-971a-94cf0d976260.json
deleted file mode 100644
index 3720ed03..00000000
--- a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0bc5b668-31cb-56e7-971a-94cf0d976260.json
+++ /dev/null
@@ -1,96 +0,0 @@
-{
-    "Contact": [
-        "nfliuqueens@gmail.com"
-    ],
-    "Contributor": [
-        "Queen's University"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MapperVersion": [
-        "Data was collected in order to characterize the spatio-temporal variations in fraction of Photosynthetically Active Radiation (fPAR) values of different vegetation types, for the purpose of correlating fPAR values with the vegetation indices derived from satellite data. fPAR values were determined in 70 plots situated along 14 transects used to characterize the spatial variation in fPAR, as well as in 5 plots used to characterize the temporal variation in fPAR."
-    ],
-    "MetaDataAccess": "http://www.polardata.ca/oai/provider?verb=GetRecord&metadataPrefix=fgdc&identifier=12630_fgdc",
-    "PublicationTimestamp": "2016-02-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "Rights": [
-        "Limited"
-    ],
-    "SpatialCoverage": "(64N-64N,69W-68W)",
-    "TempCoverageBegin": 63571345199,
-    "TempCoverageEnd": 63574196399,
-    "TemporalCoverage": " period : ( 2015-07-01T11:59:59Z - 2015-08-03T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2015-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2015-08-03T11:59:59Z",
-    "author": [
-        "Treitz, Paul",
-        "Liu, Nanfeng"
-    ],
-    "fulltext": "12630_fgdc;2017-04-09T22:02:45Z;PDCMetadata;Treitz, Paul;Liu, Nanfeng;20160201;2015 Assessment of Vegetation fPAR, Apex River Watershed, Iqaluit, Nunavut;Computer file;unknown;Nanfeng Liu, Rebecca Edwards and Paul Treitz, Unpublished data;unavailable;https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=12630;fPAR was measured in 70 plots distributed along 14 transects used to characterize the spatial variation in fPAR, as well as in 5 permanent plots used to characterize the seasonal changes in fPAR. fPAR measurements were performed from July 6 to August 3. Each 6 m x 6 m transect plot was divided into four quadrants (3 m x 3 m), a 0.6 m x 0.6 m quadrat was placed at the center of each quadrant. A line quantum PAR sensor (Apogee Inc.) was handheld horizontally above the quadrats at a height of 0.5 m to take the down-welling (i.e., incident solar PAR) and up-welling PAR (i.e., reflected PAR from the canopy). In order to ensure the fPAR variation within each quadrat was characterized, the up-welling PAR was measured at five different places within each quadrat. For each permanent plot, quantum sensors were installed on brackets: one looking upward to record the down-welling/incident PAR measurements and one looking downward to record the up-welling/reflected PAR measurements at a time interval of 5 minutes. The fPAR was calculated as 1 - the ratio of up-welling PAR to down-welling PAR.;Data was collected in order to characterize the spatio-temporal variations in fraction of Photosynthetically Active Radiation (fPAR) values of different vegetation types, for the purpose of correlating fPAR values with the vegetation indices derived from satellite data. fPAR values were determined in 70 plots situated along 14 transects used to characterize the spatial variation in fPAR, as well as in 5 plots used to characterize the temporal variation in fPAR.;Summary: Not Applicable Research Program(s): ArcticNet,IPY. For further information: 11nl21@queensu.ca;20150701;20150803;NULL;In work;As needed;-68.7;-68.4;63.89;63.71;NULL;Apex River;Baffin Bay;Carbon fluxes;Climate change;Iqaluit;Nunavut;Photosynthesis;Photosynthetically available radiation (PAR);Plants;Vegetation;Iqaluit, Nunavut, Canada, CGNDB identifier: OATRP;NULL;Limited;NULL;Queen's University;Nanfeng Liu;NULL;mailing;Mackintosh-Corry Hall, Room D201;Kingston;Ontario;K7L 3N6;Canada;(613) 533-6030;(613) 533-6122;nfliuqueens@gmail.com;NULL;Polar Data Catalogue;Canadian Cryospheric Information Network;Director;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;12630;Research programs, CCIN, or ArcticNet take no liability for the use or transmission of this data;20160201;20160201;Nanfeng Liu;Queen's University;mailing;Mackintosh-Corry Hall, Room D201;Kingston;Ontario;K7L 3N6;Canada;(613) 533-6030;(613) 533-6122;nfliuqueens@gmail.com;FGDC Content Standards for Digital Geospatial Metadata;FGDC-STD-001-1998",
-    "group": "pdc",
-    "groups": [
-        {
-            "name": "pdc"
-        }
-    ],
-    "name": "0bc5b668-31cb-56e7-971a-94cf0d976260",
-    "notes": [
-        "fPAR was measured in 70 plots distributed along 14 transects used to characterize the spatial variation in fPAR, as well as in 5 permanent plots used to characterize the seasonal changes in fPAR. fPAR measurements were performed from July 6 to August 3. Each 6 m x 6 m transect plot was divided into four quadrants (3 m x 3 m), a 0.6 m x 0.6 m quadrat was placed at the center of each quadrant. A line quantum PAR sensor (Apogee Inc.) was handheld horizontally above the quadrats at a height of 0.5 m to take the down-welling (i.e., incident solar PAR) and up-welling PAR (i.e., reflected PAR from the canopy). In order to ensure the fPAR variation within each quadrat was characterized, the up-welling PAR was measured at five different places within each quadrat. For each permanent plot, quantum sensors were installed on brackets: one looking upward to record the down-welling/incident PAR measurements and one looking downward to record the up-welling/reflected PAR measurements at a time interval of 5 minutes. The fPAR was calculated as 1 - the ratio of up-welling PAR to down-welling PAR."
-    ],
-    "oai_identifier": [
-        "12630_fgdc"
-    ],
-    "oai_set": [
-        "PDCMetadata"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-68.7,63.71],[-68.7,63.89],[-68.4,63.89],[-68.4,63.71],[-68.7,63.71]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Apex River"
-        },
-        {
-            "name": "Baffin Bay"
-        },
-        {
-            "name": "Carbon fluxes"
-        },
-        {
-            "name": "Climate change"
-        },
-        {
-            "name": "Iqaluit"
-        },
-        {
-            "name": "Nunavut"
-        },
-        {
-            "name": "Photosynthesis"
-        },
-        {
-            "name": "Photosynthetically available radiation PAR"
-        },
-        {
-            "name": "Plants"
-        },
-        {
-            "name": "Vegetation"
-        }
-    ],
-    "title": [
-        "2015 Assessment of Vegetation fPAR, Apex River Watershed, Iqaluit, Nunavut"
-    ],
-    "url": "https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=12630"
-}
\ No newline at end of file
diff --git a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0bfe79f5-1e5a-57b8-9179-f920834afdbe.json b/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0bfe79f5-1e5a-57b8-9179-f920834afdbe.json
deleted file mode 100644
index a3ef54f2..00000000
--- a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0bfe79f5-1e5a-57b8-9179-f920834afdbe.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "michelle.johnston@nrc-cnrc.gc.ca"
-    ],
-    "Contributor": [
-        "National Research Council"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MapperVersion": [
-        "Multi-year ice represents one of the most significant design and operational concerns for exploration, development, and shipping systems in the Beaufort Sea. The purpose of this project is to provide information about hummocked multi-year ice, including its thickness, salinity, temperature, and strength. Through collaborative efforts, detailed thickness measurements from on-ice drilling will be compared to data gathered by University of Manitoba and to thickness measurements from helicopter-based electromagnetic induction (EMI) soundings championed by University of Alberta. The National Research Council's (NRC) fine-scale thickness data will be used to validate satellite imagery (University of Manitoba). Information about the thickness and strength of deformed multi-year ice will also provide the National Energy Board (NEB) with the information needed to address questions about whether icebreakers can be used to manage the ice to safely extend the offshore operating season, and which features should be avoided. Ice temperature, salinity, and strength data will provide important information for identifying the most hazardous extreme sea ice features, since satellite imagery that has not been validated can be deceptive."
-    ],
-    "MetaDataAccess": "http://www.polardata.ca/oai/provider?verb=GetRecord&metadataPrefix=fgdc&identifier=11802_fgdc",
-    "PublicationTimestamp": "2016-04-05T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "Rights": [
-        "Public"
-    ],
-    "SpatialCoverage": "(72N-75N,130W-127W)",
-    "TempCoverageBegin": 63471812399,
-    "TempCoverageEnd": 63500068799,
-    "TemporalCoverage": " period : ( 2012-05-05T11:59:59Z - 2013-03-28T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2012-05-05T11:59:59Z",
-    "TemporalCoverage:EndDate": "2013-03-28T11:59:59Z",
-    "author": [
-        "Johnston, Michelle"
-    ],
-    "fulltext": "11802_fgdc;2017-04-09T22:02:32Z;PDCMetadata;Johnston, Michelle;Johnston, Michelle;20160405;Thickness, Salinity, Temperature and Strength of Multi-Year Sea Ice, Beaufort Sea;Computer file;unknown;Michelle Johnston, unpublished data;unavailable;https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=11802;The viability of newly developed equipment to measure the strength of multi-year ice at depths where no information presently exists was demonstrated during the first field program in May 2012 in Resolute, Nunavut. It was tested on hummocked multi-year ice from 3 to 20 May. Measurements were constrained to one hummocked multi-year ice floe for the purposes of testing the equipment. Ice cores were extracted from two boreholes to document the temperature and salinity of the ice to a maximum depth of 12 m. In situ strength tests were conducted in both boreholes at depth intervals of 30 cm to document changes in strength vs. depth, and to relate this information to the ice temperature and salinity. Ice thicknesses were measured at a total of 20 holes using drill hole and steam hole techniques. Measurements from the 2012 field program are unique because they provide the only available information about the keel strength of thick, hummocked multi-year ice below a depth of 10 m. &#x0d;\n&#x0d;\nFour offshore trips took place during the second field program the following year, from 16 March to 10 April, 2013 in Sachs Harbour, Northwest Territories. A total of 6 floes were visited, 4 tracking beacons were deployed on individual floes, and 37 drill-hole/steam-hole measurements were made to document the ice thickness. Strength measurements on multi-year ice were not obtained, as the 2013 field program was cut short due to funding constraints. The viability of a third field program for spring 2014 is currently under consideration.&#x0d;\n&#x0d;\nSea ice thickness, salinity and temperature data are available in .xls and .csv formats. Sea ice strength data is not presented, please contact the Principal Investigator for further information.;Multi-year ice represents one of the most significant design and operational concerns for exploration, development, and shipping systems in the Beaufort Sea. The purpose of this project is to provide information about hummocked multi-year ice, including its thickness, salinity, temperature, and strength. Through collaborative efforts, detailed thickness measurements from on-ice drilling will be compared to data gathered by University of Manitoba and to thickness measurements from helicopter-based electromagnetic induction (EMI) soundings championed by University of Alberta. The National Research Council's (NRC) fine-scale thickness data will be used to validate satellite imagery (University of Manitoba). Information about the thickness and strength of deformed multi-year ice will also provide the National Energy Board (NEB) with the information needed to address questions about whether icebreakers can be used to manage the ice to safely extend the offshore operating season, and which features should be avoided. Ice temperature, salinity, and strength data will provide important information for identifying the most hazardous extreme sea ice features, since satellite imagery that has not been validated can be deceptive.;Summary: Not applicable Research Program(s): BREA. For further information: michelle.johnston@nrc-cnrc.gc.ca;20120505;20130328;NULL;In work;As needed;-130;-127;75;72;NULL;Beaufort Sea;Ice thickness;Salinity;Sea ice;Temperature;Beaufort Sea Region;NULL;Public;NULL;National Research Council;Michelle Johnston;NULL;mailing;Building M-32, Montreal Road;Ottawa;Ontario;K1A 0R6;Canada;1-613-990-5141;1-613-952-7679;michelle.johnston@nrc-cnrc.gc.ca;NULL;Polar Data Catalogue;Canadian Cryospheric Information Network;Director;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;11802;Research programs, CCIN, or ArcticNet take no liability for the use or transmission of this data;20160405;20160405;Michelle Johnston;National Research Council;mailing;Building M-32, Montreal Road;Ottawa;Ontario;K1A 0R6;Canada;1-613-990-5141;1-613-952-7679;michelle.johnston@nrc-cnrc.gc.ca;FGDC Content Standards for Digital Geospatial Metadata;FGDC-STD-001-1998",
-    "group": "pdc",
-    "groups": [
-        {
-            "name": "pdc"
-        }
-    ],
-    "name": "0bfe79f5-1e5a-57b8-9179-f920834afdbe",
-    "notes": [
-        "The viability of newly developed equipment to measure the strength of multi-year ice at depths where no information presently exists was demonstrated during the first field program in May 2012 in Resolute, Nunavut. It was tested on hummocked multi-year ice from 3 to 20 May. Measurements were constrained to one hummocked multi-year ice floe for the purposes of testing the equipment. Ice cores were extracted from two boreholes to document the temperature and salinity of the ice to a maximum depth of 12 m. In situ strength tests were conducted in both boreholes at depth intervals of 30 cm to document changes in strength vs. depth, and to relate this information to the ice temperature and salinity. Ice thicknesses were measured at a total of 20 holes using drill hole and steam hole techniques. Measurements from the 2012 field program are unique because they provide the only available information about the keel strength of thick, hummocked multi-year ice below a depth of 10 m. &#x0d;\n&#x0d;\nFour offshore trips took place during the second field program the following year, from 16 March to 10 April, 2013 in Sachs Harbour, Northwest Territories. A total of 6 floes were visited, 4 tracking beacons were deployed on individual floes, and 37 drill-hole/steam-hole measurements were made to document the ice thickness. Strength measurements on multi-year ice were not obtained, as the 2013 field program was cut short due to funding constraints. The viability of a third field program for spring 2014 is currently under consideration.&#x0d;\n&#x0d;\nSea ice thickness, salinity and temperature data are available in .xls and .csv formats. Sea ice strength data is not presented, please contact the Principal Investigator for further information."
-    ],
-    "oai_identifier": [
-        "11802_fgdc"
-    ],
-    "oai_set": [
-        "PDCMetadata"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-130,72],[-130,75],[-127,75],[-127,72],[-130,72]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Beaufort Sea"
-        },
-        {
-            "name": "Ice thickness"
-        },
-        {
-            "name": "Salinity"
-        },
-        {
-            "name": "Sea ice"
-        },
-        {
-            "name": "Temperature"
-        }
-    ],
-    "title": [
-        "Thickness, Salinity, Temperature and Strength of Multi-Year Sea Ice, Beaufort Sea"
-    ],
-    "url": "https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=11802"
-}
\ No newline at end of file
diff --git a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0c008841-11a6-5d5b-8b62-e0a43bb42dd3.json b/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0c008841-11a6-5d5b-8b62-e0a43bb42dd3.json
deleted file mode 100644
index 138eab1f..00000000
--- a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0c008841-11a6-5d5b-8b62-e0a43bb42dd3.json
+++ /dev/null
@@ -1,100 +0,0 @@
-{
-    "Contact": [
-        "gs.arcticnet.md@hotmail.com"
-    ],
-    "Contributor": [
-        "University of Manitoba"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MapperVersion": [
-        "Samples collected to understand the impact of permafrost degradation and riverine export on the organic carbon cycle of the Hudson Bay using lignin biomarkers and 14C of carbon as source identifiers."
-    ],
-    "MetaDataAccess": "http://www.polardata.ca/oai/provider?verb=GetRecord&metadataPrefix=fgdc&identifier=11688_fgdc",
-    "PublicationTimestamp": "2015-01-23T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "Rights": [
-        "Public"
-    ],
-    "SpatialCoverage": "(55N-63N,95W-76W)",
-    "TempCoverageBegin": 63414356399,
-    "TempCoverageEnd": 63415911599,
-    "TemporalCoverage": " period : ( 2010-07-10T11:59:59Z - 2010-07-28T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2010-07-10T11:59:59Z",
-    "TemporalCoverage:EndDate": "2010-07-28T11:59:59Z",
-    "author": [
-        "Robie Macdonald",
-        "Zou Zou Kuzyk",
-        "Miguel Goni",
-        "Gary Stern",
-        "Joanne DeLaronde",
-        "Pamela Godin",
-        "Joscelyn Bailey",
-        "Peter Outridge",
-        "Allison MacHutchon"
-    ],
-    "fulltext": "11688_fgdc;2017-04-09T22:02:27Z;PDCMetadata;Gary Stern;Pamela Godin;Allison MacHutchon;Joanne DeLaronde;Joscelyn Bailey;Miguel Goni;Peter Outridge;Robie Macdonald;Zou Zou Kuzyk;20150123;Using lignin biomarkers and 14C, of both river DOC and POC, and permafrost soils, to characterize the impacts of climate warming and permafrost degradation on the organic carbon budget of the Hudson Bay, Canada;Computer file;unknown;Unpublished;unavailable;https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=11688;This study looks at characterizing the terrigenous OC sources, like permafrost degradation, of POC and DOC through 17 rivers and six soils of the Hudson Bay (HB) using lignin biomarkers, and &amp;#916;14C. Our findings show the dominance of the OC flux (89%) from the southwest Hudson Bay Rivers, especially from DOC (93%), shedding light on the sources and fate of OC in HB sediments. With warming, organic cryosols, with high OC content in the Cz horizon, have the potential to release as much as 1.5 gOC/m2 for every cm increase in active layer depth. The [Ad/Al] ratios, when combined with 14C ages of DOM, show that older SOC is being released in some rivers and is fresher than expected due to its preservation within permafrost. S/V and C/V ratios, are well correlated to latitude in DOM, reflecting the vegetation in their drainage basins and can be used to indicate OC sources.;Samples collected to understand the impact of permafrost degradation and riverine export on the organic carbon cycle of the Hudson Bay using lignin biomarkers and 14C of carbon as source identifiers.;Summary: Not Applicable Research Program(s): ArcticNet. For further information: gary.stern@dfo-mpo.gc.ca;20100710;20100728;NULL;Complete;As needed;-95;-76;63;55;NULL;Biomarkers;Dissolved organic carbon (DOC);Hudson Bay;Lignin;Organic carbon;Particulate organic carbon;Permafrost;Rivers;Soils;Hudson Bay & Watershed, Canada;NULL;Public;NULL;University of Manitoba;Ashley Gaden;NULL;mailing;586 Wallace Building;Winnipeg;MB;R3T2N6;Canada;204.474.9084;gs.arcticnet.md@hotmail.com;NULL;Polar Data Catalogue;Canadian Cryospheric Information Network;Director;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;11688;Research programs, CCIN, or ArcticNet take no liability for the use or transmission of this data;20150123;20150123;Ashley Gaden;University of Manitoba;mailing;586 Wallace Building;Winnipeg;MB;R3T2N6;Canada;204.474.9084;gs.arcticnet.md@hotmail.com;FGDC Content Standards for Digital Geospatial Metadata;FGDC-STD-001-1998",
-    "group": "pdc",
-    "groups": [
-        {
-            "name": "pdc"
-        }
-    ],
-    "name": "0c008841-11a6-5d5b-8b62-e0a43bb42dd3",
-    "notes": [
-        "This study looks at characterizing the terrigenous OC sources, like permafrost degradation, of POC and DOC through 17 rivers and six soils of the Hudson Bay (HB) using lignin biomarkers, and &amp;#916;14C. Our findings show the dominance of the OC flux (89%) from the southwest Hudson Bay Rivers, especially from DOC (93%), shedding light on the sources and fate of OC in HB sediments. With warming, organic cryosols, with high OC content in the Cz horizon, have the potential to release as much as 1.5 gOC/m2 for every cm increase in active layer depth. The [Ad/Al] ratios, when combined with 14C ages of DOM, show that older SOC is being released in some rivers and is fresher than expected due to its preservation within permafrost. S/V and C/V ratios, are well correlated to latitude in DOM, reflecting the vegetation in their drainage basins and can be used to indicate OC sources."
-    ],
-    "oai_identifier": [
-        "11688_fgdc"
-    ],
-    "oai_set": [
-        "PDCMetadata"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-95,55],[-95,63],[-76,63],[-76,55],[-95,55]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Biomarkers"
-        },
-        {
-            "name": "Dissolved organic carbon DOC"
-        },
-        {
-            "name": "Hudson Bay"
-        },
-        {
-            "name": "Lignin"
-        },
-        {
-            "name": "Organic carbon"
-        },
-        {
-            "name": "Particulate organic carbon"
-        },
-        {
-            "name": "Permafrost"
-        },
-        {
-            "name": "Rivers"
-        },
-        {
-            "name": "Soils"
-        }
-    ],
-    "title": [
-        "Using lignin biomarkers and 14C, of both river DOC and POC, and permafrost soils, to characterize the impacts of climate warming and permafrost degradation on the organic carbon budget of the Hudson Bay, Canada"
-    ],
-    "url": "https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=11688"
-}
\ No newline at end of file
diff --git a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0c0719ae-de3d-551b-a07f-ddec52eec611.json b/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0c0719ae-de3d-551b-a07f-ddec52eec611.json
deleted file mode 100644
index 7886c7e3..00000000
--- a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0c0719ae-de3d-551b-a07f-ddec52eec611.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "aknudby@uottawa.ca"
-    ],
-    "Contributor": [
-        "University of Ottawa"
-    ],
-    "DOI": "http://dx.doi.org/10.21963/12847",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MapperVersion": [
-        "The main goal of this project is to collect and provide data that can be used for the calibration and validation of satellite-derived bathymetry in Cambridge Bay, Nunavut, Canada."
-    ],
-    "MetaDataAccess": "http://www.polardata.ca/oai/provider?verb=GetRecord&metadataPrefix=fgdc&identifier=12847_fgdc",
-    "PublicationTimestamp": "2017-10-27T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "Rights": [
-        "Public"
-    ],
-    "SpatialCoverage": "(69N-69N,105W-105W)",
-    "TempCoverageBegin": 63637354799,
-    "TempCoverageEnd": 63637959599,
-    "TemporalCoverage": " period : ( 2017-08-03T11:59:59Z - 2017-08-10T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2017-08-03T11:59:59Z",
-    "TemporalCoverage:EndDate": "2017-08-10T11:59:59Z",
-    "author": [
-        "Holman, Kiyomi",
-        "Knudby, Anders"
-    ],
-    "fulltext": "12847_fgdc;2017-10-28T03:27:25Z;PDCMetadata;Knudby, Anders;Knudby, Anders;Holman, Kiyomi;20171027;Seafloor spectral reflectance factors and georeferenced water depths from Cambridge Bay, NU (NGMP ID  EC37);Computer file;unknown;Knudby, A. and Holman, K. (2017) Seafloor spectral reflectance factors and georeferenced water depths from Cambridge Bay, NU (NGMP ID  EC37). Waterloo, Canada: Canadian Cryospheric Information Network (CCIN). http://dx.doi.org/10.21963/12847;unavailable;https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=12847;Spectral reflectance measurements were taken using the panel substitution method with a dual-channel Ocean Optics Jaz in an underwater housing, while SCUBA diving. A standard polytetrafluoroethylene (PTFE) panel was used as reference. The second channel was pointing up, to adjust for differences in illumination conditions between panel and seafloor measurements. Water depths were measured with a SonarMite single-beam echosounder, not adjusted for pitch and roll, nor for salinity and density. The transducer was placed approximately 20 centimetres below the water surface. Georeference was provided by a Trimble R1 Global Navigation Satellite System (GNSS) receiver using satellite based augmentation systems (SBAS) corrections. The two data streams were integrated using the Seafloor Systems SonarMite software.;The main goal of this project is to collect and provide data that can be used for the calibration and validation of satellite-derived bathymetry in Cambridge Bay, Nunavut, Canada.;Summary: Not applicable. Research Program(s): NGMP. For further information: http://dx.doi.org/10.21963/12847;20170803;20170810;NULL;Complete;None planned;-105.25;-105;69.15;69.05;NULL;Bathymetry;Benthos;Canada;Optical;Remote sensing data;Water level;Cambridge Bay, Nunavut;NULL;Public;NULL;University of Ottawa;Anders Knudby;NULL;mailing;60 University Private;Ottawa;Ontario;K1N6N5;Canada;6136683998;aknudby@uottawa.ca;NULL;Polar Data Catalogue;Canadian Cryospheric Information Network;Director;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;12847;Research programs, CCIN, or ArcticNet take no liability for the use or transmission of this data;20170929;20171027;Anders Knudby;University of Ottawa;mailing;60 University Private;Ottawa;Ontario;K1N6N5;Canada;6136683998;aknudby@uottawa.ca;FGDC Content Standards for Digital Geospatial Metadata;FGDC-STD-001-1998",
-    "group": "pdc",
-    "groups": [
-        {
-            "name": "pdc"
-        }
-    ],
-    "name": "0c0719ae-de3d-551b-a07f-ddec52eec611",
-    "notes": [
-        "Spectral reflectance measurements were taken using the panel substitution method with a dual-channel Ocean Optics Jaz in an underwater housing, while SCUBA diving. A standard polytetrafluoroethylene (PTFE) panel was used as reference. The second channel was pointing up, to adjust for differences in illumination conditions between panel and seafloor measurements. Water depths were measured with a SonarMite single-beam echosounder, not adjusted for pitch and roll, nor for salinity and density. The transducer was placed approximately 20 centimetres below the water surface. Georeference was provided by a Trimble R1 Global Navigation Satellite System (GNSS) receiver using satellite based augmentation systems (SBAS) corrections. The two data streams were integrated using the Seafloor Systems SonarMite software."
-    ],
-    "oai_identifier": [
-        "12847_fgdc"
-    ],
-    "oai_set": [
-        "PDCMetadata"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-105.25,69.05],[-105.25,69.15],[-105,69.15],[-105,69.05],[-105.25,69.05]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Bathymetry"
-        },
-        {
-            "name": "Benthos"
-        },
-        {
-            "name": "Canada"
-        },
-        {
-            "name": "Optical"
-        },
-        {
-            "name": "Remote sensing data"
-        },
-        {
-            "name": "Water level"
-        }
-    ],
-    "title": [
-        "Seafloor spectral reflectance factors and georeferenced water depths from Cambridge Bay, NU (NGMP ID  EC37)"
-    ],
-    "url": "https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=12847"
-}
\ No newline at end of file
diff --git a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0c0e0156-f102-51f4-909b-46e04034081b.json b/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0c0e0156-f102-51f4-909b-46e04034081b.json
deleted file mode 100644
index 240490f9..00000000
--- a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0c0e0156-f102-51f4-909b-46e04034081b.json
+++ /dev/null
@@ -1,89 +0,0 @@
-{
-    "Contact": [
-        "yu.zhang@canada.ca"
-    ],
-    "Contributor": [
-        "Natural Resources Canada"
-    ],
-    "DOI": "http://dx.doi.org/doi: 10.4141/S06-029",
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MapperVersion": [
-        "Arctic and Sub-Arctic soils contain a large amount of organic carbon in their topsoil horizons and in the upper layers of permafrost. There is concern that climate warming could release this soil organic carbon (SOC) to the atmosphere as greenhouse gases. However, information about the profile features of the soil (SOC concentrations based on horizons and depths) and spatial distribution of SOC in northern ecosystems are far less than for other regions. This study compiled available field measurements of SOC in northern Canada. This project is funded by 1) a joint program between Environment Canada and Natural Resources Canada for estimation of greenhouse gases emissions and removals from land use changes over Canada\u2019s arctic and sub-arctic; 2) Climate Change Geoscience Program (CCGP), Natural Resources Canada; 3) Canadian Space Agency\u2019s Government Related Initiatives Program (GRIP); and 4) Polar Knowledge Canada Science and Technology (POLAR S&amp;T) program."
-    ],
-    "MetaDataAccess": "http://www.polardata.ca/oai/provider?verb=GetRecord&metadataPrefix=fgdc&identifier=12832_fgdc",
-    "PublicationTimestamp": "2017-09-13T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "Rights": [
-        "Public"
-    ],
-    "SpatialCoverage": "(60N-82N,141W-61W)",
-    "TempCoverageBegin": 61599182399,
-    "TempCoverageEnd": 315537854399,
-    "TemporalCoverage": " period : ( 1953-01-01T11:59:59Z - 9999-12-31T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1953-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "9999-12-31T11:59:59Z",
-    "author": [
-        "Hossain, M. Faruque",
-        "Chen, Wenjun",
-        "Zhang, Yu"
-    ],
-    "fulltext": "12832_fgdc;2017-09-14T02:58:33Z;PDCMetadata;Chen, Wenjun;Hossain, M. Faruque;Zhang, Yu;20170913;A database for soil organic carbon in northern Canada;Computer file;unknown;Data Citation: Hossain, F. M., Chen, W. and Zhang, Y. (2017) A database for soil organic carbon in northern Canada. Waterloo, Canada: Canadian Cryospheric Information Network (CCIN). Unpublished Data\nAdditional Publication- can be accessed: Hossain, M. F., Zhang, Y., Chen, W., Wang, J. and Pavlic, G. 2007. Soil organic carbon content in northern Canada: A database of field measurements and its analysis. Can. J. Soil Sci. 87: 259\u2013268. doi: 10.4141/S06-029;unavailable;https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=12832;Available field measurements of soil organic carbon (SOC) in northern Canada were compiled and a database was developed by checking related papers and reports as well as through personal contacts. Additionally, to provide more information on areas where data was missing, studies were conducted in Yellowknife, Northwest Territories and in the Lupin gold mining area, Nunavut in 2005. Including our recent measurements, the database contains 438 profiles with 1473 soil horizons. Preliminary analysis shows that the SOC content of subsurface soils is relatively high in northern regions. In the top 100 cm of soils, 40% of the SOC is located in the 50 to 100 cm layer. The SOC content is lower in northern Arctic and in mountainous regions. The average upland SOC content in northern Canada is higher than in other world biomes (i.e. croplands, temperate forest, tropical savannahs, and tropical forest) except temperate grasslands and boreal forest.;Arctic and Sub-Arctic soils contain a large amount of organic carbon in their topsoil horizons and in the upper layers of permafrost. There is concern that climate warming could release this soil organic carbon (SOC) to the atmosphere as greenhouse gases. However, information about the profile features of the soil (SOC concentrations based on horizons and depths) and spatial distribution of SOC in northern ecosystems are far less than for other regions. This study compiled available field measurements of SOC in northern Canada. This project is funded by 1) a joint program between Environment Canada and Natural Resources Canada for estimation of greenhouse gases emissions and removals from land use changes over Canada\u2019s arctic and sub-arctic; 2) Climate Change Geoscience Program (CCGP), Natural Resources Canada; 3) Canadian Space Agency\u2019s Government Related Initiatives Program (GRIP); and 4) Polar Knowledge Canada Science and Technology (POLAR S&amp;T) program.;Summary: Not Applicable Research Program(s): Other,POLAR/CHARS. For further information: yu.zhang@canada.ca;19530101;99991231;NULL;In work;Irregular;-141;-61;82;60;NULL;Arctic;Database;Greenhouse gas;Northern Canada;Organic carbon;Permafrost;Subarctic;Northern Canada\u2002(above 60 degrees north);NULL;Public;NULL;Natural Resources Canada;Yu Zhang;NULL;mailing;560 Rochester Street;Ottawa;Ontario;K1A 0E4;Canada;(613)759-6024;(613)759-6344;yu.zhang@canada.ca;NULL;Polar Data Catalogue;Canadian Cryospheric Information Network;Director;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;12832;Research programs, CCIN, or ArcticNet take no liability for the use or transmission of this data;20170615;20170913;Yu Zhang;Natural Resources Canada;mailing;560 Rochester Street;Ottawa;Ontario;K1A 0E4;Canada;(613)759-6024;(613)759-6344;yu.zhang@canada.ca;FGDC Content Standards for Digital Geospatial Metadata;FGDC-STD-001-1998",
-    "group": "pdc",
-    "groups": [
-        {
-            "name": "pdc"
-        }
-    ],
-    "name": "0c0e0156-f102-51f4-909b-46e04034081b",
-    "notes": [
-        "Available field measurements of soil organic carbon (SOC) in northern Canada were compiled and a database was developed by checking related papers and reports as well as through personal contacts. Additionally, to provide more information on areas where data was missing, studies were conducted in Yellowknife, Northwest Territories and in the Lupin gold mining area, Nunavut in 2005. Including our recent measurements, the database contains 438 profiles with 1473 soil horizons. Preliminary analysis shows that the SOC content of subsurface soils is relatively high in northern regions. In the top 100 cm of soils, 40% of the SOC is located in the 50 to 100 cm layer. The SOC content is lower in northern Arctic and in mountainous regions. The average upland SOC content in northern Canada is higher than in other world biomes (i.e. croplands, temperate forest, tropical savannahs, and tropical forest) except temperate grasslands and boreal forest."
-    ],
-    "oai_identifier": [
-        "12832_fgdc"
-    ],
-    "oai_set": [
-        "PDCMetadata"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-141,60],[-141,82],[-61,82],[-61,60],[-141,60]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Arctic"
-        },
-        {
-            "name": "Database"
-        },
-        {
-            "name": "Greenhouse gas"
-        },
-        {
-            "name": "Northern Canada"
-        },
-        {
-            "name": "Organic carbon"
-        },
-        {
-            "name": "Permafrost"
-        },
-        {
-            "name": "Subarctic"
-        }
-    ],
-    "title": [
-        "A database for soil organic carbon in northern Canada"
-    ],
-    "url": "https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=12832"
-}
\ No newline at end of file
diff --git a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0c21af55-6821-5332-9256-d881381a8284.json b/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0c21af55-6821-5332-9256-d881381a8284.json
deleted file mode 100644
index e422fd08..00000000
--- a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0c21af55-6821-5332-9256-d881381a8284.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "melissa.lafreniere@queensu.ca"
-    ],
-    "Contributor": [
-        "Queens University"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MapperVersion": [
-        "Data was collected in order to determine seasonal and diurnal variations in DOC and TN in stream waters from the watersheds at Cape Bounty."
-    ],
-    "MetaDataAccess": "http://www.polardata.ca/oai/provider?verb=GetRecord&metadataPrefix=fgdc&identifier=11589_fgdc",
-    "PublicationTimestamp": "2013-01-23T11:59:59Z",
-    "PublicationYear": [
-        "2013"
-    ],
-    "Publisher": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "Rights": [
-        "Limited"
-    ],
-    "SpatialCoverage": "(75N,110W)",
-    "TempCoverageBegin": 63474663599,
-    "TempCoverageEnd": 63478551599,
-    "TemporalCoverage": " period : ( 2012-06-07T11:59:59Z - 2012-07-22T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2012-06-07T11:59:59Z",
-    "TemporalCoverage:EndDate": "2012-07-22T11:59:59Z",
-    "author": [
-        "Melissa Lafreniere"
-    ],
-    "fulltext": "11589_fgdc;2017-04-09T22:02:26Z;PDCMetadata;Melissa Lafreniere;Melissa Lafreniere;20130123;2012 River Dissolved organic carbon (DOC) and total dissolved nitrogen (TDN) concentrations, Cape Bounty;Computer file;unknown;Lafreni\u00e8re, MJ Unpublished data;unavailable;https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=11589;Sites NAD 27 UTM 12x:&#x0d;\nWest River (WR): 0540627, 8313002&#x0d;\nEast River (WR): 0543077, 8312306&#x0d;\nPtarmigan (PT): 0540596, 8314704&#x0d;\nGoose (G):\t0540900, 8314197&#x0d;\nALD05(AD05): 0540679,8134265&#x0d;\nCariboo (CR): 0540280, 8315140&#x0d;\n&#x0d;\n&#x0d;\nSamples named by site abreviation, date (MMDD) and time: PT0714 1300 = Ptarmigan July 14th at 1 pm. &#x0d;\n&#x0d;\nSamples were vaccum filtered using a glass filtration apparatus and precombusted 0.7 &amp;#956;m GF/F glass fibre filters.  The filtration apparatus was soaked overnight with 30% hydrogen peroxide, and triple rinsed with deionised water and sample for each use.  The samples were stored cool in the dark (refrigerated) in amber glass EPA vials, and acidified to a pH of 2 upon return to the laboratory. DOC concentrations were measured as non-purgeable organic carbon via high temperature combustion (720\u00b0C) with a Shimadzu TOC-VCPH analyser using a high sensitivity platinum catalyst in line with a total nitrogen module (TNM-1 unit).  TDN concentrations were measured as nitrogen monoxide via thermal decomposition;Data was collected in order to determine seasonal and diurnal variations in DOC and TN in stream waters from the watersheds at Cape Bounty.;Summary: Not Applicable Research Program(s): ArcticNet. For further information: melissa.lafreniere@queensu.ca;20120607;20120722;NULL;In work;As needed;-109.5;-109.5;74.9;74.9;NULL;Canadian High Arctic;Cape Bounty;Dissolved organic carbon (DOC);Hydrochemistry;Nitrogen;Nutrients;Cape Bounty, Melville Island, Nunavut;NULL;Limited;NULL;Queens University;Melissa Lafreniere;NULL;mailing;Department of Geography, Mackintosh-Corry Hall Rm;Kingston;ON;K7P 3N6;Canada;(613) 533-6000 x78720;(613) 533-6000 x78720;melissa.lafreniere@queensu.ca;NULL;Polar Data Catalogue;Canadian Cryospheric Information Network;Director;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;11589;Research programs, CCIN, or ArcticNet take no liability for the use or transmission of this data;20130123;20130123;Melissa Lafreniere;Queens University;mailing;Department of Geography, Mackintosh-Corry Hall Rm;Kingston;ON;K7P 3N6;Canada;(613) 533-6000 x78720;(613) 533-6000 x78720;melissa.lafreniere@queensu.ca;FGDC Content Standards for Digital Geospatial Metadata;FGDC-STD-001-1998",
-    "group": "pdc",
-    "groups": [
-        {
-            "name": "pdc"
-        }
-    ],
-    "name": "0c21af55-6821-5332-9256-d881381a8284",
-    "notes": [
-        "Sites NAD 27 UTM 12x:&#x0d;\nWest River (WR): 0540627, 8313002&#x0d;\nEast River (WR): 0543077, 8312306&#x0d;\nPtarmigan (PT): 0540596, 8314704&#x0d;\nGoose (G):\t0540900, 8314197&#x0d;\nALD05(AD05): 0540679,8134265&#x0d;\nCariboo (CR): 0540280, 8315140&#x0d;\n&#x0d;\n&#x0d;\nSamples named by site abreviation, date (MMDD) and time: PT0714 1300 = Ptarmigan July 14th at 1 pm. &#x0d;\n&#x0d;\nSamples were vaccum filtered using a glass filtration apparatus and precombusted 0.7 &amp;#956;m GF/F glass fibre filters.  The filtration apparatus was soaked overnight with 30% hydrogen peroxide, and triple rinsed with deionised water and sample for each use.  The samples were stored cool in the dark (refrigerated) in amber glass EPA vials, and acidified to a pH of 2 upon return to the laboratory. DOC concentrations were measured as non-purgeable organic carbon via high temperature combustion (720\u00b0C) with a Shimadzu TOC-VCPH analyser using a high sensitivity platinum catalyst in line with a total nitrogen module (TNM-1 unit).  TDN concentrations were measured as nitrogen monoxide via thermal decomposition"
-    ],
-    "oai_identifier": [
-        "11589_fgdc"
-    ],
-    "oai_set": [
-        "PDCMetadata"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-109.5,74.9],[-109.5,74.9],[-109.5,74.9],[-109.5,74.9],[-109.5,74.9]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Canadian High Arctic"
-        },
-        {
-            "name": "Cape Bounty"
-        },
-        {
-            "name": "Dissolved organic carbon DOC"
-        },
-        {
-            "name": "Hydrochemistry"
-        },
-        {
-            "name": "Nitrogen"
-        },
-        {
-            "name": "Nutrients"
-        }
-    ],
-    "title": [
-        "2012 River Dissolved organic carbon (DOC) and total dissolved nitrogen (TDN) concentrations, Cape Bounty"
-    ],
-    "url": "https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=11589"
-}
\ No newline at end of file
diff --git a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0c3e9cb4-c96a-5bce-a8b2-8183b5cf5a1a.json b/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0c3e9cb4-c96a-5bce-a8b2-8183b5cf5a1a.json
deleted file mode 100644
index 1be64f75..00000000
--- a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0c3e9cb4-c96a-5bce-a8b2-8183b5cf5a1a.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "cbmp_terrestrial@caff.is"
-    ],
-    "Contributor": [
-        "Circumpolar Biodiversity Monitoring Program - CAFF"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MapperVersion": [
-        "1) Characterize changes in ungulate habitat quality and quantity over time, particularly reindeer and caribou winter range condition (e.g., sensitive lichen communities measured both by plots and with exclosures, biomass of forage species or groups of interest); 2) Determine changes to lichen and bryophyte communities associated with increasing inputs of sulfur, nitrogen or metals in active mining areas; 3) Determine the effects of fire and burn severity on the species composition (species diversity and % cover), vegetation structure (tree diameters and heights), and ground cover (% cover and depth) of varying vegetation types; 4) Determine vegetation change over time associated with contaminants (e.g., changes to lichen and bryophyte communities associated with increasing inputs of sulfur, nitrogen or metals in active mining areas); 5) Monitor long-term changes in lichen abundance and diversity; 6) Monitor long-term changes in plant structure - the height and density of plants - using ground plots that can be tied to remotely sensed imagery, such as aerial photographs and satellite images, for extrapolation over large areas."
-    ],
-    "MetaDataAccess": "http://www.polardata.ca/oai/provider?verb=GetRecord&metadataPrefix=fgdc&identifier=12391_fgdc",
-    "PublicationTimestamp": "2015-04-30T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "Rights": [
-        "Limited"
-    ],
-    "SpatialCoverage": "(53N-71N,169W-141W)",
-    "TempCoverageBegin": 63334785599,
-    "TempCoverageEnd": 315537854399,
-    "TemporalCoverage": " period : ( 2008-01-01T11:59:59Z - 9999-12-31T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2008-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "9999-12-31T11:59:59Z",
-    "author": [
-        "Swanson, David",
-        "Wesser, Sara"
-    ],
-    "fulltext": "12391_fgdc;2017-04-09T22:02:42Z;PDCMetadata;Swanson, David;Wesser, Sara;20150430;Terrestrial Vegetation and Soils: National Park Service Alaska Region Inventory &amp; Monitoring Program;Computer file;unknown;Swanson, David; Unpublished data;unavailable;https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=12391;All monitoring occurs within the ARCN (Arctic Inventory and Monitoring Network) using a \"vegetation node\" framework of clustered sampling plots.  As of 2013, the project had sampled 23 \"nodes.\"  Each vegetation node consists of a set of approximately 20 plots accessed from a central campsite. The node locations are chosen to be readily accessible and representative of major ARCN ecosystems. All nodes to date are accessible by fixed-wing aircraft landing on lakes or undeveloped gravel airstrips. The vicinity of each node is stratified into landform-based physiographic units, and proposed transect locations are placed within the strata. Transect starting points and azimuths are randomized, and plots are located systematically thereafter. A few plots locations were deliberately chosen to target features of special interest. Plots locations are recorded with a sub-meter resolution GPS and marked with a buried magnet for future re-sampling. At each plot, plant cover and height by species (or species group for many non-vascular plants) are measured by point intercept using a laser at 100 points spaced 25 cm apart (Fig. 3). Tree and sapling diameters, and seedling counts by species are made on an 8-m radius fixed-area plot (no trees were recorded in 2013). Comprehensive site and soil descriptions are made at each plot, and the intensity of herbivore effects on vegetation are assessed.;1) Characterize changes in ungulate habitat quality and quantity over time, particularly reindeer and caribou winter range condition (e.g., sensitive lichen communities measured both by plots and with exclosures, biomass of forage species or groups of interest); 2) Determine changes to lichen and bryophyte communities associated with increasing inputs of sulfur, nitrogen or metals in active mining areas; 3) Determine the effects of fire and burn severity on the species composition (species diversity and % cover), vegetation structure (tree diameters and heights), and ground cover (% cover and depth) of varying vegetation types; 4) Determine vegetation change over time associated with contaminants (e.g., changes to lichen and bryophyte communities associated with increasing inputs of sulfur, nitrogen or metals in active mining areas); 5) Monitor long-term changes in lichen abundance and diversity; 6) Monitor long-term changes in plant structure - the height and density of plants - using ground plots that can be tied to remotely sensed imagery, such as aerial photographs and satellite images, for extrapolation over large areas.;Summary: Not Applicable Research Program(s): CBMP/CAFF - Terrestrial. For further information: http://catalog.northslope.org/catalogs/646;20080101;99991231;NULL;In work;As needed;-169;-141;71.25;53;NULL;Alaska;Climate;Landscape;Soils;Species composition;Vegetation;Wetland;Alaska, USA;NULL;Limited;NULL;Circumpolar Biodiversity Monitoring Program - CAFF;CBMP Terrestrial - CAFF;NULL;mailing;Borgir, Nordurslod;Akureyri;N/A;600;Iceland;+ 354 462 3350;cbmp_terrestrial@caff.is;NULL;Polar Data Catalogue;Canadian Cryospheric Information Network;Director;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;12391;Research programs, CCIN, or ArcticNet take no liability for the use or transmission of this data;20150430;20150430;CBMP Terrestrial - CAFF;Circumpolar Biodiversity Monitoring Program - CAFF;mailing;Borgir, Nordurslod;Akureyri;N/A;600;Iceland;+ 354 462 3350;cbmp_terrestrial@caff.is;FGDC Content Standards for Digital Geospatial Metadata;FGDC-STD-001-1998",
-    "group": "pdc",
-    "groups": [
-        {
-            "name": "pdc"
-        }
-    ],
-    "name": "0c3e9cb4-c96a-5bce-a8b2-8183b5cf5a1a",
-    "notes": [
-        "All monitoring occurs within the ARCN (Arctic Inventory and Monitoring Network) using a \"vegetation node\" framework of clustered sampling plots.  As of 2013, the project had sampled 23 \"nodes.\"  Each vegetation node consists of a set of approximately 20 plots accessed from a central campsite. The node locations are chosen to be readily accessible and representative of major ARCN ecosystems. All nodes to date are accessible by fixed-wing aircraft landing on lakes or undeveloped gravel airstrips. The vicinity of each node is stratified into landform-based physiographic units, and proposed transect locations are placed within the strata. Transect starting points and azimuths are randomized, and plots are located systematically thereafter. A few plots locations were deliberately chosen to target features of special interest. Plots locations are recorded with a sub-meter resolution GPS and marked with a buried magnet for future re-sampling. At each plot, plant cover and height by species (or species group for many non-vascular plants) are measured by point intercept using a laser at 100 points spaced 25 cm apart (Fig. 3). Tree and sapling diameters, and seedling counts by species are made on an 8-m radius fixed-area plot (no trees were recorded in 2013). Comprehensive site and soil descriptions are made at each plot, and the intensity of herbivore effects on vegetation are assessed."
-    ],
-    "oai_identifier": [
-        "12391_fgdc"
-    ],
-    "oai_set": [
-        "PDCMetadata"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-169,53],[-169,71.25],[-141,71.25],[-141,53],[-169,53]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Alaska"
-        },
-        {
-            "name": "Climate"
-        },
-        {
-            "name": "Landscape"
-        },
-        {
-            "name": "Soils"
-        },
-        {
-            "name": "Species composition"
-        },
-        {
-            "name": "Vegetation"
-        },
-        {
-            "name": "Wetland"
-        }
-    ],
-    "title": [
-        "Terrestrial Vegetation and Soils: National Park Service Alaska Region Inventory &amp; Monitoring Program"
-    ],
-    "url": "https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=12391"
-}
\ No newline at end of file
diff --git a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0c45c2d5-1f67-5778-91d2-1dc81e20cf7c.json b/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0c45c2d5-1f67-5778-91d2-1dc81e20cf7c.json
deleted file mode 100644
index 9ee94210..00000000
--- a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0c45c2d5-1f67-5778-91d2-1dc81e20cf7c.json
+++ /dev/null
@@ -1,104 +0,0 @@
-{
-    "Contact": [
-        "beaufort@aandc.gc.ca"
-    ],
-    "Contributor": [
-        "Aboriginal Affairs and Northern Development Canada"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MapperVersion": [
-        "Canada has the world's longest coastline and largest area of sea ice. Sea ice exerts important seasonal effects on weather, climate, and marine ecosystems with major implications for the safety of marine transportation, northern communities, tourism, and offshore resource development and exploitation. Whether preparing policy or regulations, assessing the impacts of activities on ecosystems, designing sustainable infrastructure, or planning and conducting safe and secure shipping, it is vital to have the best information possible about the variable ice conditions of the Arctic marine environment. Large collections of such data are acquired, compiled, produced, and maintained by national and international agencies such as the Canadian Ice Service (CIS). However, such data collections have not been made readily accessible other than for operational use. The purpose of this project is to develop a Canadian sea ice information infrastructure that manages historical, ongoing, and in-situ sea ice data for research and decision-making, with a particular focus on meeting the needs of Beaufort environmental assessments. CanICE aims to put all current and historical CIS sea ice information from the Beaufort Sea online for northern organizations, northern residents, industry, regulators, researchers, forecasters, modellers, and the general public."
-    ],
-    "MetaDataAccess": "http://www.polardata.ca/oai/provider?verb=GetRecord&metadataPrefix=fgdc&identifier=11929_fgdc",
-    "PublicationTimestamp": "2014-05-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "Rights": [
-        "Public"
-    ],
-    "SpatialCoverage": "(61N-80N,164W-86W)",
-    "TempCoverageBegin": 61472951999,
-    "TempCoverageEnd": 315537854399,
-    "TemporalCoverage": " period : ( 1949-01-01T11:59:59Z - 9999-12-31T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1949-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "9999-12-31T11:59:59Z",
-    "author": [
-        "Ziqiang Ou",
-        "Lina Assad",
-        "Julie Friddell",
-        "Leah Braithwaite",
-        "Yvan B\u00e9dard",
-        "Darlene Langois",
-        "Ellsworth LeDrew",
-        "Songnian Li",
-        "Eveline Bernier",
-        "Stephane Charlebois"
-    ],
-    "fulltext": "11929_fgdc;2017-04-09T22:02:34Z;PDCMetadata;Lina Assad;Leah Braithwaite;Darlene Langois;Ellsworth LeDrew;Eveline Bernier;Julie Friddell;Songnian Li;Stephane Charlebois;Yvan B\u00e9dard;Ziqiang Ou;20140501;CanICE - A Sea Ice Information Database and Web-based Portal;Computer file;unknown;Braithwaite, Leah, Lina Assad, Darlene Langois, Stephane Charlebois, Ziqiang Ou, Songnian Li, Ellsworth LeDrew, Julie Friddell, Yvan Bedard, and Eveline Bernier. 2013. CanICE - A Sea Ice Information Database and Web-based Portal. Waterloo, Canada: Canadian Cryospheric Information Network (CCIN).;unavailable;https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=11929;This project will create a publicly-accessible database with geographic and time-related reference points of sea ice features, including coverage, concentration, type, characteristics, and extreme ice hazards. The database will contain detailed information important to offshore activities and environmental assessments in the Beaufort Sea region. Access to the database will be through the Polar Data Catalogue (PDC). The database will be produced in a standard format to allow for integration with various information sources. New tools will be available for users to easily find information and to study a variety of sea ice properties, including changes over time, differences between locations, and the impacts of climate. The database will be created through the development of a quality-controlled, interoperable geo-database including appropriate data management strategies and database models of sea ice indices. It will enable online, web-based open access to historical and current sea ice information via the PDC, and it will maximize data usability through powerful state-of-the-art tools for knowledge discovery, statistical and climatological analyses and information visualization.;Canada has the world's longest coastline and largest area of sea ice. Sea ice exerts important seasonal effects on weather, climate, and marine ecosystems with major implications for the safety of marine transportation, northern communities, tourism, and offshore resource development and exploitation. Whether preparing policy or regulations, assessing the impacts of activities on ecosystems, designing sustainable infrastructure, or planning and conducting safe and secure shipping, it is vital to have the best information possible about the variable ice conditions of the Arctic marine environment. Large collections of such data are acquired, compiled, produced, and maintained by national and international agencies such as the Canadian Ice Service (CIS). However, such data collections have not been made readily accessible other than for operational use. The purpose of this project is to develop a Canadian sea ice information infrastructure that manages historical, ongoing, and in-situ sea ice data for research and decision-making, with a particular focus on meeting the needs of Beaufort environmental assessments. CanICE aims to put all current and historical CIS sea ice information from the Beaufort Sea online for northern organizations, northern residents, industry, regulators, researchers, forecasters, modellers, and the general public.;Summary: Not Applicable Research Program(s): BREA. For further information: https://www.polardata.ca/pdcsearch/;19490101;99991231;NULL;In work;Weekly;-164;-86;80;61;NULL;Beaufort Sea;Climate;Database;Environmental impacts;Governmental policies;Ice chart;Inuvialuit;Petroleum industry;Sea ice;Shipping;Beaufort Sea (CGNDB ID: LACKU);NULL;Public;NULL;Aboriginal Affairs and Northern Development Canada;Beaufort Regional Environmental Assessment;NULL;mailing;15 Eddy St.;Gatineau;Quebec;K1A0H4;Canada;819-953-0031;beaufort@aandc.gc.ca;NULL;Polar Data Catalogue;Canadian Cryospheric Information Network;Director;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;11929;Research programs, CCIN, or ArcticNet take no liability for the use or transmission of this data;20140501;20140501;Beaufort Regional Environmental Assessment;Aboriginal Affairs and Northern Development Canada;mailing;15 Eddy St.;Gatineau;Quebec;K1A0H4;Canada;819-953-0031;beaufort@aandc.gc.ca;FGDC Content Standards for Digital Geospatial Metadata;FGDC-STD-001-1998",
-    "group": "pdc",
-    "groups": [
-        {
-            "name": "pdc"
-        }
-    ],
-    "name": "0c45c2d5-1f67-5778-91d2-1dc81e20cf7c",
-    "notes": [
-        "This project will create a publicly-accessible database with geographic and time-related reference points of sea ice features, including coverage, concentration, type, characteristics, and extreme ice hazards. The database will contain detailed information important to offshore activities and environmental assessments in the Beaufort Sea region. Access to the database will be through the Polar Data Catalogue (PDC). The database will be produced in a standard format to allow for integration with various information sources. New tools will be available for users to easily find information and to study a variety of sea ice properties, including changes over time, differences between locations, and the impacts of climate. The database will be created through the development of a quality-controlled, interoperable geo-database including appropriate data management strategies and database models of sea ice indices. It will enable online, web-based open access to historical and current sea ice information via the PDC, and it will maximize data usability through powerful state-of-the-art tools for knowledge discovery, statistical and climatological analyses and information visualization."
-    ],
-    "oai_identifier": [
-        "11929_fgdc"
-    ],
-    "oai_set": [
-        "PDCMetadata"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-164,61],[-164,80],[-86,80],[-86,61],[-164,61]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Beaufort Sea"
-        },
-        {
-            "name": "Climate"
-        },
-        {
-            "name": "Database"
-        },
-        {
-            "name": "Environmental impacts"
-        },
-        {
-            "name": "Governmental policies"
-        },
-        {
-            "name": "Ice chart"
-        },
-        {
-            "name": "Inuvialuit"
-        },
-        {
-            "name": "Petroleum industry"
-        },
-        {
-            "name": "Sea ice"
-        },
-        {
-            "name": "Shipping"
-        }
-    ],
-    "title": [
-        "CanICE - A Sea Ice Information Database and Web-based Portal"
-    ],
-    "url": "https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=11929"
-}
\ No newline at end of file
diff --git a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0c57aff3-8b9e-5ef2-8d55-ae2f876da5f2.json b/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0c57aff3-8b9e-5ef2-8d55-ae2f876da5f2.json
deleted file mode 100644
index ff2bca12..00000000
--- a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0c57aff3-8b9e-5ef2-8d55-ae2f876da5f2.json
+++ /dev/null
@@ -1,81 +0,0 @@
-{
-    "Contact": [
-        "cbmp_marine@caff.is"
-    ],
-    "Contributor": [
-        "Circumpolar Biodiversity Monitoring Program - CAFF"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MapperVersion": [
-        "To monitor the abundance of polar bears along the east coast of Greenland."
-    ],
-    "MetaDataAccess": "http://www.polardata.ca/oai/provider?verb=GetRecord&metadataPrefix=fgdc&identifier=10061_fgdc",
-    "PublicationTimestamp": "2010-09-07T11:59:59Z",
-    "PublicationYear": [
-        "2010"
-    ],
-    "Publisher": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "Rights": [
-        "Limited"
-    ],
-    "SpatialCoverage": "(59N-84N,43W-20W)",
-    "TempCoverageBegin": 63303249599,
-    "TempCoverageEnd": 63424123199,
-    "TemporalCoverage": " period : ( 2007-01-01T11:59:59Z - 2010-10-31T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2007-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2010-10-31T11:59:59Z",
-    "author": [
-        "National Environmental Research Institute (NERI)",
-        "Greenland Institute of Natural Resources (GINR)"
-    ],
-    "fulltext": "10061_fgdc;2017-04-09T22:02:15Z;PDCMetadata;Greenland Institute of Natural Resources (GINR);National Environmental Research Institute (NERI);20100907;Monitoring of polar bears in east Greenland;Computer file;unknown;Unpublished data;unavailable;https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=10061;Telemetry and satellite images are used to estimate the abundance of polar bears in eastern Greenland. Tagging of bears occurred in 2007 and 2008. The hypothesis to be tested is that sea ice reduction reduces reproduction and survival of polar bears. A report will be published in 2011. The project is funded in connection with oil impact assessment, the Kalaallit Nunaat Marine Seismic (KANUMAS) project.;To monitor the abundance of polar bears along the east coast of Greenland.;Summary: Not Applicable Research Program(s): CBMP/CAFF - Marine. For further information: feug@natur.gl;20070101;20101031;NULL;In work;As needed;-43;-20;84;59;NULL;Abundance;Biodiversity;Greenland;Polar bear;Satellite imagery;Greenland;NULL;Limited;NULL;Circumpolar Biodiversity Monitoring Program - CAFF;CBMP Marine - CAFF;NULL;mailing;Borgir, Nordurslod;Akureyri;N/A;600;Iceland;+ 354 462 3350;cbmp_marine@caff.is;NULL;Polar Data Catalogue;Canadian Cryospheric Information Network;Director;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;10061;Research programs, CCIN, or ArcticNet take no liability for the use or transmission of this data;20100907;20100907;CBMP Marine - CAFF;Circumpolar Biodiversity Monitoring Program - CAFF;mailing;Borgir, Nordurslod;Akureyri;N/A;600;Iceland;+ 354 462 3350;cbmp_marine@caff.is;FGDC Content Standards for Digital Geospatial Metadata;FGDC-STD-001-1998",
-    "group": "pdc",
-    "groups": [
-        {
-            "name": "pdc"
-        }
-    ],
-    "name": "0c57aff3-8b9e-5ef2-8d55-ae2f876da5f2",
-    "notes": [
-        "Telemetry and satellite images are used to estimate the abundance of polar bears in eastern Greenland. Tagging of bears occurred in 2007 and 2008. The hypothesis to be tested is that sea ice reduction reduces reproduction and survival of polar bears. A report will be published in 2011. The project is funded in connection with oil impact assessment, the Kalaallit Nunaat Marine Seismic (KANUMAS) project."
-    ],
-    "oai_identifier": [
-        "10061_fgdc"
-    ],
-    "oai_set": [
-        "PDCMetadata"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-43,59],[-43,84],[-20,84],[-20,59],[-43,59]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Abundance"
-        },
-        {
-            "name": "Biodiversity"
-        },
-        {
-            "name": "Greenland"
-        },
-        {
-            "name": "Polar bear"
-        },
-        {
-            "name": "Satellite imagery"
-        }
-    ],
-    "title": [
-        "Monitoring of polar bears in east Greenland"
-    ],
-    "url": "https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=10061"
-}
\ No newline at end of file
diff --git a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0c771d98-f93f-53f4-9a53-0f66b137b362.json b/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0c771d98-f93f-53f4-9a53-0f66b137b362.json
deleted file mode 100644
index f12b18d2..00000000
--- a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0c771d98-f93f-53f4-9a53-0f66b137b362.json
+++ /dev/null
@@ -1,89 +0,0 @@
-{
-    "Contact": [
-        "cbmp_terrestrial@caff.is"
-    ],
-    "Contributor": [
-        "Circumpolar Biodiversity Monitoring Program - CAFF"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MapperVersion": [
-        "The Lesser Snow Goose (Chen caerulescens caerulescens) colony on Howe Island, near Prudhoe Bay, Alaska, is the only established nesting colony of this species in the United States. A study was initiated to follow the dynamics of this small population in 1980 when it became clear that oil development would proceed near the nesting colony and in nearby brood-rearing areas."
-    ],
-    "MetaDataAccess": "http://www.polardata.ca/oai/provider?verb=GetRecord&metadataPrefix=fgdc&identifier=12378_fgdc",
-    "PublicationTimestamp": "2015-04-30T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "Rights": [
-        "Limited"
-    ],
-    "SpatialCoverage": "(70N,148W)",
-    "TempCoverageBegin": 62482795199,
-    "TempCoverageEnd": 63366321599,
-    "TemporalCoverage": " period : ( 1981-01-01T11:59:59Z - 2008-12-31T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1981-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2008-12-31T11:59:59Z",
-    "author": [
-        "Sanzone, Diane"
-    ],
-    "fulltext": "12378_fgdc;2017-04-09T22:02:42Z;PDCMetadata;Sanzone, Diane;Sanzone, Diane;20150430;Post Nesting Snow Goose Survey on Howe Island, Alaska;Computer file;unknown;Unpublished data;unavailable;https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=12378;Conduct a post-hatching nest census on Howe island: a complete search of the island and examination of nests for fate determination.;The Lesser Snow Goose (Chen caerulescens caerulescens) colony on Howe Island, near Prudhoe Bay, Alaska, is the only established nesting colony of this species in the United States. A study was initiated to follow the dynamics of this small population in 1980 when it became clear that oil development would proceed near the nesting colony and in nearby brood-rearing areas.;Summary: Not Applicable Research Program(s): CBMP/CAFF - Terrestrial. For further information: http://catalog.northslope.org/catalogs/518;19810101;20081231;NULL;Complete;As needed;-147.99;-147.99;70.32;70.32;NULL;Abundance;Alaska;Birds;Distribution;Geese;Population dynamics;Reproductive success;Snow geese;Howe Island, Prudhoe Bay, Alaska, USA;NULL;Limited;NULL;Circumpolar Biodiversity Monitoring Program - CAFF;CBMP Terrestrial - CAFF;NULL;mailing;Borgir, Nordurslod;Akureyri;N/A;600;Iceland;+ 354 462 3350;cbmp_terrestrial@caff.is;NULL;Polar Data Catalogue;Canadian Cryospheric Information Network;Director;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;12378;Research programs, CCIN, or ArcticNet take no liability for the use or transmission of this data;20150430;20150430;CBMP Terrestrial - CAFF;Circumpolar Biodiversity Monitoring Program - CAFF;mailing;Borgir, Nordurslod;Akureyri;N/A;600;Iceland;+ 354 462 3350;cbmp_terrestrial@caff.is;FGDC Content Standards for Digital Geospatial Metadata;FGDC-STD-001-1998",
-    "group": "pdc",
-    "groups": [
-        {
-            "name": "pdc"
-        }
-    ],
-    "name": "0c771d98-f93f-53f4-9a53-0f66b137b362",
-    "notes": [
-        "Conduct a post-hatching nest census on Howe island: a complete search of the island and examination of nests for fate determination."
-    ],
-    "oai_identifier": [
-        "12378_fgdc"
-    ],
-    "oai_set": [
-        "PDCMetadata"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-147.99,70.32],[-147.99,70.32],[-147.99,70.32],[-147.99,70.32],[-147.99,70.32]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Abundance"
-        },
-        {
-            "name": "Alaska"
-        },
-        {
-            "name": "Birds"
-        },
-        {
-            "name": "Distribution"
-        },
-        {
-            "name": "Geese"
-        },
-        {
-            "name": "Population dynamics"
-        },
-        {
-            "name": "Reproductive success"
-        },
-        {
-            "name": "Snow geese"
-        }
-    ],
-    "title": [
-        "Post Nesting Snow Goose Survey on Howe Island, Alaska"
-    ],
-    "url": "https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=12378"
-}
\ No newline at end of file
diff --git a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0c8b06b4-9d35-52c7-b01f-a35e06da7fba.json b/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0c8b06b4-9d35-52c7-b01f-a35e06da7fba.json
deleted file mode 100644
index af6f559f..00000000
--- a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0c8b06b4-9d35-52c7-b01f-a35e06da7fba.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "e.kahlmeyer@gmail.com"
-    ],
-    "Contributor": [
-        "Memorial University of Newfoundland"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MapperVersion": [
-        "The purpose was to determine the amount of Pb-210 coming from the atmosphere."
-    ],
-    "MetaDataAccess": "http://www.polardata.ca/oai/provider?verb=GetRecord&metadataPrefix=fgdc&identifier=1457_fgdc",
-    "PublicationTimestamp": "2014-10-27T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "Rights": [
-        "Public"
-    ],
-    "SpatialCoverage": "(59N,63W)",
-    "TempCoverageBegin": 63353357999,
-    "TempCoverageEnd": 63353357999,
-    "TemporalCoverage": " period : ( 2008-08-03T11:59:59Z - 2008-08-03T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2008-08-03T11:59:59Z",
-    "TemporalCoverage:EndDate": "2008-08-03T11:59:59Z",
-    "author": [
-        "Elisabeth Kahlmeyer",
-        "Sam Bentley"
-    ],
-    "fulltext": "1457_fgdc;2017-04-09T22:02:03Z;PDCMetadata;Sam Bentley;Elisabeth Kahlmeyer;20141027;Soil sample analysis of Pb-210 in the McCornick River area, Nunatsiavut;Computer file;unknown;Corename: WH0808-2; unpublished data;unavailable;https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=1457;The soil samples were studied for Pb-210 produced in the atmosphere and stored in the soil through radioisotope analysis.;The purpose was to determine the amount of Pb-210 coming from the atmosphere.;Summary: Not Applicable Research Program(s): ArcticNet. For further information: e.kahlmeyer@gmail.com;20080803;20080803;NULL;In work;Annually;-63.45;-63.45;59.01;59.01;NULL;210-Pb;Atmosphere;Earth Sciences;Nachvak Fiord;Soil chemistry;Soils;Close to McCornick River, Nunatsiavut, Canada;NULL;Public;NULL;Memorial University of Newfoundland;Elisabeth Kahlmeyer;NULL;mailing;240 Prince Phillip Drive;St. John's;NL;A1B3X5;Canada;7096992755;e.kahlmeyer@gmail.com;NULL;Polar Data Catalogue;Canadian Cryospheric Information Network;Director;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;1457;Research programs, CCIN, or ArcticNet take no liability for the use or transmission of this data;20141027;20141027;Elisabeth Kahlmeyer;Memorial University of Newfoundland;mailing;240 Prince Phillip Drive;St. John's;NL;A1B3X5;Canada;7096992755;e.kahlmeyer@gmail.com;FGDC Content Standards for Digital Geospatial Metadata;FGDC-STD-001-1998",
-    "group": "pdc",
-    "groups": [
-        {
-            "name": "pdc"
-        }
-    ],
-    "name": "0c8b06b4-9d35-52c7-b01f-a35e06da7fba",
-    "notes": [
-        "The soil samples were studied for Pb-210 produced in the atmosphere and stored in the soil through radioisotope analysis."
-    ],
-    "oai_identifier": [
-        "1457_fgdc"
-    ],
-    "oai_set": [
-        "PDCMetadata"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-63.45,59.01],[-63.45,59.01],[-63.45,59.01],[-63.45,59.01],[-63.45,59.01]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "-Pb"
-        },
-        {
-            "name": "Atmosphere"
-        },
-        {
-            "name": "Earth Sciences"
-        },
-        {
-            "name": "Nachvak Fiord"
-        },
-        {
-            "name": "Soil chemistry"
-        },
-        {
-            "name": "Soils"
-        }
-    ],
-    "title": [
-        "Soil sample analysis of Pb-210 in the McCornick River area, Nunatsiavut"
-    ],
-    "url": "https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=1457"
-}
\ No newline at end of file
diff --git a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0c968163-083a-5d05-a581-bc24a13d3d86.json b/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0c968163-083a-5d05-a581-bc24a13d3d86.json
deleted file mode 100644
index 9628860c..00000000
--- a/oaitestdata/pdc-fgdc/PDCMetadata_1/json/0c968163-083a-5d05-a581-bc24a13d3d86.json
+++ /dev/null
@@ -1,96 +0,0 @@
-{
-    "Contact": [
-        "nigel.roulet@mcgill.ca"
-    ],
-    "Contributor": [
-        "Geography, McGill University"
-    ],
-    "DiscHierarchy": [
-        "4.4.7",
-        "Geosciences",
-        "Environmental Research"
-    ],
-    "Discipline": "Environmental Research",
-    "Language": [
-        "English"
-    ],
-    "MapperVersion": [
-        "Ample evidence shows that dissolved organic carbon (DOC) would be the major or even the only direct contributor to the respired carbon fluxes in temperate forest, peatland, even permafrost peatland. And DOC pool is composed by different DOC fractions with a continuum of biodegradability ranging from labile fractions to recalcitrant fractions. The goal of this research was to provide the litter continuous-recalcitrance (decomposition status) DOC production/mineralization functions for each litter type in permafrost peatland for my model to simulate DOC production /mineralization along peat profile. This study will also provide a constant anaerobic moisture modifier for DOC production/mineralization, test and modify the unsaturated moisture modifier that is used in the Holocene Peat Model (HPM), and modify decomposition temperature dependency that is used in the McGill Wetland Model."
-    ],
-    "MetaDataAccess": "http://www.polardata.ca/oai/provider?verb=GetRecord&metadataPrefix=fgdc&identifier=11687_fgdc",
-    "PublicationTimestamp": "2015-03-17T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Canadian Cryospheric Information Network"
-    ],
-    "Rights": [
-        "Public"
-    ],
-    "SpatialCoverage": "(55N-55N,77W-77W)",
-    "TempCoverageBegin": 63449866799,
-    "TempCoverageEnd": 315537854399,
-    "TemporalCoverage": " period : ( 2011-08-25T11:59:59Z - 9999-12-31T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "2011-08-25T11:59:59Z",
-    "TemporalCoverage:EndDate": "9999-12-31T11:59:59Z",
-    "author": [
-        "Roulet, Nigel",
-        "Wang, Zheng"
-    ],
-    "fulltext": "11687_fgdc;2017-04-09T22:02:27Z;PDCMetadata;Roulet, Nigel;Wang, Zheng;20150317;Decomposition of peat and plant material from a thawing palsa;Computer file;unknown;Zheng Wang and Nigel Roulet, Department of Geography, McGill University, Montreal, QC Canada, Unpublished data;unavailable;https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=11687;Vegetation samples of shrub, sedges and moss were collected from permafrost peatland in the eastern shore of Hudson Bay, near the hamlet of Kuujjuarapik-Whapmagoostui in subarctic Quebec in summer 2012. Each litter type was incubated under two moist conditions (Anoxic and oxic treatments), and adjusted to 2 different temperatures (~4\u00baC and ~22\u00baC). I have set several time interval (caused different mass remaining, i.e. different decomposition degrees) to repeat this measurement three to five times along the incubation for each peatland litter type. At each time interval, the samples were drained, rewashed with distilled water, and the water was replaced in order to remove the DOC produced by previous degradation status organic matter. DOC concentration plus CO2 and CH4 concentrations at each time interval were measured, as well as DOC biodegradability (determined by its spectroscopic properties by UV radiation absorbance). The DOC, CH4 and CO2 concentration were expressed as g-1 oven-dry plant tissue.;Ample evidence shows that dissolved organic carbon (DOC) would be the major or even the only direct contributor to the respired carbon fluxes in temperate forest, peatland, even permafrost peatland. And DOC pool is composed by different DOC fractions with a continuum of biodegradability ranging from labile fractions to recalcitrant fractions. The goal of this research was to provide the litter continuous-recalcitrance (decomposition status) DOC production/mineralization functions for each litter type in permafrost peatland for my model to simulate DOC production /mineralization along peat profile. This study will also provide a constant anaerobic moisture modifier for DOC production/mineralization, test and modify the unsaturated moisture modifier that is used in the Holocene Peat Model (HPM), and modify decomposition temperature dependency that is used in the McGill Wetland Model.;Summary: Not Applicable Research Program(s): ADAPT. For further information: nigel.roulet@mcgill.ca;20110825;99991231;NULL;In work;Annually;-77.31;-77.3;55.21;55.2;NULL;Active layer;Biogeochemistry;Biological productivity;Carbon fluxes;Dissolved organic carbon (DOC);Flora;Kuujjuaraapik;Palsa;Peat;Plants;Kuujjuarapik-Whapmagoostui, Quebec, Canada;NULL;Public;NULL;Geography, McGill University;Nigel Roulet;NULL;mailing;805 Sherbrooke St. O.;Montereal;QC;H3A 0B9;Canada;1-514-398-4945;nigel.roulet@mcgill.ca;NULL;Polar Data Catalogue;Canadian Cryospheric Information Network;Director;mailing;200 University Avenue West, University of Waterloo;Waterloo;Ontario;N2L 3G1;Canada;(519) 888-4567 x32689;(519) 888-6768;pdc@uwaterloo.ca;11687;Research programs, CCIN, or ArcticNet take no liability for the use or transmission of this data;20150317;20150317;Nigel Roulet;Geography, McGill University;mailing;805 Sherbrooke St. O.;Montereal;QC;H3A 0B9;Canada;1-514-398-4945;nigel.roulet@mcgill.ca;FGDC Content Standards for Digital Geospatial Metadata;FGDC-STD-001-1998",
-    "group": "pdc",
-    "groups": [
-        {
-            "name": "pdc"
-        }
-    ],
-    "name": "0c968163-083a-5d05-a581-bc24a13d3d86",
-    "notes": [
-        "Vegetation samples of shrub, sedges and moss were collected from permafrost peatland in the eastern shore of Hudson Bay, near the hamlet of Kuujjuarapik-Whapmagoostui in subarctic Quebec in summer 2012. Each litter type was incubated under two moist conditions (Anoxic and oxic treatments), and adjusted to 2 different temperatures (~4\u00baC and ~22\u00baC). I have set several time interval (caused different mass remaining, i.e. different decomposition degrees) to repeat this measurement three to five times along the incubation for each peatland litter type. At each time interval, the samples were drained, rewashed with distilled water, and the water was replaced in order to remove the DOC produced by previous degradation status organic matter. DOC concentration plus CO2 and CH4 concentrations at each time interval were measured, as well as DOC biodegradability (determined by its spectroscopic properties by UV radiation absorbance). The DOC, CH4 and CO2 concentration were expressed as g-1 oven-dry plant tissue."
-    ],
-    "oai_identifier": [
-        "11687_fgdc"
-    ],
-    "oai_set": [
-        "PDCMetadata"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-77.31,55.2],[-77.31,55.21],[-77.3,55.21],[-77.3,55.2],[-77.31,55.2]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Active layer"
-        },
-        {
-            "name": "Biogeochemistry"
-        },
-        {
-            "name": "Biological productivity"
-        },
-        {
-            "name": "Carbon fluxes"
-        },
-        {
-            "name": "Dissolved organic carbon DOC"
-        },
-        {
-            "name": "Flora"
-        },
-        {
-            "name": "Kuujjuaraapik"
-        },
-        {
-            "name": "Palsa"
-        },
-        {
-            "name": "Peat"
-        },
-        {
-            "name": "Plants"
-        }
-    ],
-    "title": [
-        "Decomposition of peat and plant material from a thawing palsa"
-    ],
-    "url": "https://www.polardata.ca/pdcsearch/PDCSearchDOI.jsp?doi_id=11687"
-}
\ No newline at end of file
diff --git a/oaitestdata/radar-oai_dc/SET_1/json/1cedb20a-dfd9-5ccf-82be-e497d0d47eb5.json b/oaitestdata/radar-oai_dc/SET_1/json/1cedb20a-dfd9-5ccf-82be-e497d0d47eb5.json
deleted file mode 100644
index 9e5ca898..00000000
--- a/oaitestdata/radar-oai_dc/SET_1/json/1cedb20a-dfd9-5ccf-82be-e497d0d47eb5.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-    "Contact": [
-        "Leibniz Institute for Farm Animal Biology (FBN)"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.1002/bimj.201700219",
-    "DiscHierarchy": [
-        "3.",
-        "Live Sciences",
-        "Life Sciences"
-    ],
-    "Discipline": "Biology",
-    "Format": [
-        "application/zip"
-    ],
-    "MetaDataAccess": "https://www.radar-service.eu/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=1cedb20a-dfd9-5ccf-82be-e497d0d47eb5",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Leibniz Institute for Farm Animal Biology (FBN)"
-    ],
-    "ResourceType": [
-        "phenotypic and genetic data",
-        "Dataset"
-    ],
-    "Rights": [
-        "CC BY 4.0 Attribution",
-        "Leibniz Institute for Farm Animal Biology (FBN)"
-    ],
-    "author": [
-        "Melzer, Nina",
-        "Wittenburg, D\u00f6rte"
-    ],
-    "fulltext": "10.22000-80;2018-05-25T08:59:00Z;10.22000/80;DOI;Melzer, Nina;0000-0002-9586-1588;Wittenburg, D\u00f6rte;0000-0002-3639-2574;Supplementary data to publication \u201cAn approximate Bayesian significance test for genomic evaluations\u201d (Biom J);Leibniz Institute for Farm Animal Biology (FBN);2018;Agriculture;Biology;Other;Genetics;Life Science;phenotypic and genetic data;Dataset;CC BY 4.0 Attribution;Leibniz Institute for Farm Animal Biology (FBN);A simulation study has been conducted to analyse the association between genetic and phenotypic variation in livestock.  Following the density and distribution of single nucleotide polymorphisms (SNPs) on the Illumina BovineSNP50 chip, 52,773 SNPs were simulated on the cattle genome of 30 Morgan length. Several generations of random mating were executed in which random recombination events according to the genetic distance between SNPs and random mutation of SNP alleles were considered. In the most recent generations, 50 sires were mated to 20 dams in order to generate multiple half-sib families. The data were split into training (n=2,000) and validation/testing set (n=2,000). Twenty-three SNPs were randomly preselected to be the causative variants, and additive, dominance and epistatic effects were simulated. Two different traits were achieved by adding different residual error terms to the sum of genetic effects, such that the total genetic variation contributed either 30% or 50% to the phenotypic variation. Then, 5,227 SNPs (every 10-th SNP including the causative variants) were selected. The simulation was repeated 100 times. More details can be found in Wittenburg et al. (2011) Including non-additive genetic effects in Bayesian methods for the prediction of genetic values based on genome-wide markers. BMC Genetics 12:74, https://doi.org/10.1186/1471-2156-12-74;SNP, dominance, epistasis, recombination, genetic variation;10.1002/bimj.201700219;10.1002/bimj.201700219;DOI;DOI;grid.5586.e;application/zip",
-    "group": "radar",
-    "groups": [
-        {
-            "name": "radar"
-        }
-    ],
-    "name": "1cedb20a-dfd9-5ccf-82be-e497d0d47eb5",
-    "notes": [
-        "A simulation study has been conducted to analyse the association between genetic and phenotypic variation in livestock.  Following the density and distribution of single nucleotide polymorphisms (SNPs) on the Illumina BovineSNP50 chip, 52,773 SNPs were simulated on the cattle genome of 30 Morgan length. Several generations of random mating were executed in which random recombination events according to the genetic distance between SNPs and random mutation of SNP alleles were considered. In the most recent generations, 50 sires were mated to 20 dams in order to generate multiple half-sib families. The data were split into training (n=2,000) and validation/testing set (n=2,000). Twenty-three SNPs were randomly preselected to be the causative variants, and additive, dominance and epistatic effects were simulated. Two different traits were achieved by adding different residual error terms to the sum of genetic effects, such that the total genetic variation contributed either 30% or 50% to the phenotypic variation. Then, 5,227 SNPs (every 10-th SNP including the causative variants) were selected. The simulation was repeated 100 times. More details can be found in Wittenburg et al. (2011) Including non-additive genetic effects in Bayesian methods for the prediction of genetic values based on genome-wide markers. BMC Genetics 12:74, https://doi.org/10.1186/1471-2156-12-74",
-        "SNP, dominance, epistasis, recombination, genetic variation"
-    ],
-    "oai_identifier": [
-        "1cedb20a-dfd9-5ccf-82be-e497d0d47eb5"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Agriculture"
-        },
-        {
-            "name": "Biology"
-        },
-        {
-            "name": "Genetics"
-        },
-        {
-            "name": "Life"
-        },
-        {
-            "name": "Science"
-        }
-    ],
-    "title": [
-        "Supplementary data to publication \u201cAn approximate Bayesian significance test for genomic evaluations\u201d (Biom J)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/radar-oai_dc/SET_1/json/3c9408c0-6086-5370-9a73-d6ff8c619b05.json b/oaitestdata/radar-oai_dc/SET_1/json/3c9408c0-6086-5370-9a73-d6ff8c619b05.json
deleted file mode 100644
index 35dabdcb..00000000
--- a/oaitestdata/radar-oai_dc/SET_1/json/3c9408c0-6086-5370-9a73-d6ff8c619b05.json
+++ /dev/null
@@ -1,91 +0,0 @@
-{
-    "Contact": [
-        "M\u00fcller, Eric"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.22000/44",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "application/zip"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.radar-service.eu/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=3c9408c0-6086-5370-9a73-d6ff8c619b05",
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "M\u00fcller, Eric"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "CC BY 4.0 Attribution",
-        "M\u00fcller, Eric",
-        "Springstein, Matthias",
-        "Ewerth, Ralph"
-    ],
-    "author": [
-        "Ewerth, Ralph",
-        "Springstein, Matthias",
-        "M\u00fcller, Eric"
-    ],
-    "fulltext": "10.22000-43;2017-06-06T12:25:05Z;10.22000/43;DOI;M\u00fcller, Eric;0000-0002-6802-1241;Springstein, Matthias;0000-0002-6509-8534;Ewerth, Ralph;0000-0003-0918-6297;Date Estimation in the Wild Dataset;M\u00fcller, Eric;2017;Computer Science;Other;Machine Learning;Other;Deep Learning;Other;Information Retrieval;Other;Image Retrieval;Other;Date Estimation;Dataset;CC BY 4.0 Attribution;M\u00fcller, Eric;Springstein, Matthias;Ewerth, Ralph;eng;10.22000/44;10.22000/44;DOI;DOI;application/zip",
-    "group": "radar",
-    "groups": [
-        {
-            "name": "radar"
-        }
-    ],
-    "name": "3c9408c0-6086-5370-9a73-d6ff8c619b05",
-    "oai_identifier": [
-        "3c9408c0-6086-5370-9a73-d6ff8c619b05"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Computer"
-        },
-        {
-            "name": "Science"
-        },
-        {
-            "name": "Machine"
-        },
-        {
-            "name": "Learning"
-        },
-        {
-            "name": "Deep"
-        },
-        {
-            "name": "Learning"
-        },
-        {
-            "name": "Information"
-        },
-        {
-            "name": "Retrieval"
-        },
-        {
-            "name": "Image"
-        },
-        {
-            "name": "Retrieval"
-        },
-        {
-            "name": "Date"
-        },
-        {
-            "name": "Estimation"
-        }
-    ],
-    "title": [
-        "Date Estimation in the Wild Dataset"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/radar-oai_dc/SET_1/json/41d810e3-35fb-5afa-a136-c9034b7025bd.json b/oaitestdata/radar-oai_dc/SET_1/json/41d810e3-35fb-5afa-a136-c9034b7025bd.json
deleted file mode 100644
index 6e612a9f..00000000
--- a/oaitestdata/radar-oai_dc/SET_1/json/41d810e3-35fb-5afa-a136-c9034b7025bd.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "Technische Informationsbibliothek (TIB)"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.22000/64",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "application/zip"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://www.radar-service.eu/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=41d810e3-35fb-5afa-a136-c9034b7025bd",
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Technische Informationsbibliothek (TIB)"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "CC BY 4.0 Attribution",
-        "Technische Informationsbibliothek (TIB)"
-    ],
-    "author": [
-        "Technische Informationsbibliothek (TIB)"
-    ],
-    "fulltext": "10.22000-64;2017-12-21T17:57:18Z;10.22000/64;DOI;Technische Informationsbibliothek (TIB);Questionnaire and Dataset of the TIB Survey 2017 on Conference Recordings;Technische Informationsbibliothek (TIB);2017;Other;Bibliothekswissenschaft;Dataset;CC BY 4.0 Attribution;Technische Informationsbibliothek (TIB);Drees, Bastian;http://orcid.org/0000-0003-3508-602X;Einbock, Joanna;Bernhofer, Carolin;H\u00e4fner, Peter;Aufbauend auf einer gro\u00df angelegten Studie der TIB zum Informationsbeschaffungs- und Publikationsverhalten in Wissenschaft und Technik  (DOI:10.22000/54) wurde eine Analyse der Bed\u00fcrfnisse und Anforderungen von Konferenzorganisatoren, -veranstaltern und Dienstleistern f\u00fcr audiovisuelle Aufzeichnungen durchgef\u00fchrt. Zu diesem Zweck wurde ein Interviewleitfaden erstellt, der in den Interviews verwendet wurde. Erfragt wurde der Status quo bei Produktion und Ver\u00f6ffentlichung von Konferenzaufnahmen sowie Probleme und Anforderungen. In qualitativen Interviews mit 36 Befragten wurde ermittelt, wie weit verbreitet Konferenzaufnahmen in den Ingenieur- und Naturwissenschaften sind. Die 36 Befragten lassen sich in drei verschiedene Gruppen unterteilen, n\u00e4mlich Konferenzorganisatoren, Konferenzveranstalter und Dienstleister f\u00fcr audiovisuelle Aufzeichnungen, d.h. gemeinn\u00fctzige oder kommerzielle Videoproduktionsdienste. Unter den Befragten geh\u00f6rten 20 zur ersten Gruppe (Organisatoren), zehn zur zweiten Gruppe (Veranstalter) und sechs zur dritten Gruppe (AV-Dienstleister).;Umfrage, wissenschaftliche Konferenz, Videoaufzeichnung, Marktanalyse;Drees, Bastian;Einbock, Joanna;Bernhofer, Carolin;H\u00e4fner, Peter;deu;501100002347;application/zip",
-    "group": "radar",
-    "groups": [
-        {
-            "name": "radar"
-        }
-    ],
-    "name": "41d810e3-35fb-5afa-a136-c9034b7025bd",
-    "notes": [
-        "Aufbauend auf einer gro\u00df angelegten Studie der TIB zum Informationsbeschaffungs- und Publikationsverhalten in Wissenschaft und Technik  (DOI:10.22000/54) wurde eine Analyse der Bed\u00fcrfnisse und Anforderungen von Konferenzorganisatoren, -veranstaltern und Dienstleistern f\u00fcr audiovisuelle Aufzeichnungen durchgef\u00fchrt. Zu diesem Zweck wurde ein Interviewleitfaden erstellt, der in den Interviews verwendet wurde. Erfragt wurde der Status quo bei Produktion und Ver\u00f6ffentlichung von Konferenzaufnahmen sowie Probleme und Anforderungen. In qualitativen Interviews mit 36 Befragten wurde ermittelt, wie weit verbreitet Konferenzaufnahmen in den Ingenieur- und Naturwissenschaften sind. Die 36 Befragten lassen sich in drei verschiedene Gruppen unterteilen, n\u00e4mlich Konferenzorganisatoren, Konferenzveranstalter und Dienstleister f\u00fcr audiovisuelle Aufzeichnungen, d.h. gemeinn\u00fctzige oder kommerzielle Videoproduktionsdienste. Unter den Befragten geh\u00f6rten 20 zur ersten Gruppe (Organisatoren), zehn zur zweiten Gruppe (Veranstalter) und sechs zur dritten Gruppe (AV-Dienstleister).",
-        "Umfrage, wissenschaftliche Konferenz, Videoaufzeichnung, Marktanalyse"
-    ],
-    "oai_identifier": [
-        "41d810e3-35fb-5afa-a136-c9034b7025bd"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Bibliothekswissenschaft"
-        }
-    ],
-    "title": [
-        "Questionnaire and Dataset of the TIB Survey 2017 on Conference Recordings"
-    ],
-    "url": "http://orcid.org/0000-0003-3508-602X"
-}
\ No newline at end of file
diff --git a/oaitestdata/radar-oai_dc/SET_1/json/5a9e06d7-6c03-52b5-9644-c04c836e08fd.json b/oaitestdata/radar-oai_dc/SET_1/json/5a9e06d7-6c03-52b5-9644-c04c836e08fd.json
deleted file mode 100644
index 32a900fe..00000000
--- a/oaitestdata/radar-oai_dc/SET_1/json/5a9e06d7-6c03-52b5-9644-c04c836e08fd.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        " Technische Informationsbibliothek (TIB) "
-    ],
-    "DOI": "http://dx.doi.org/doi:10.22000/76",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "application/zip"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://www.radar-service.eu/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=5a9e06d7-6c03-52b5-9644-c04c836e08fd",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        " Technische Informationsbibliothek (TIB) "
-    ],
-    "ResourceType": [
-        "Umfrage / Survey",
-        "Dataset"
-    ],
-    "Rights": [
-        "CC BY 4.0 Attribution",
-        "Technische Informationsbibliothek (TIB) "
-    ],
-    "author": [
-        "Technische Informationsbibliothek (TIB)"
-    ],
-    "fulltext": "10.22000-76;2018-05-24T16:59:00Z;10.22000/76;DOI;Technische Informationsbibliothek (TIB);Datensatz zur Umfrage: Nutzung von Forschungsinformationssystemen in Forschungseinrichtungen; Technische Informationsbibliothek (TIB) ;2018;Other; Bibliothekswissenschaft / library science;Umfrage / Survey;Dataset;CC BY 4.0 Attribution;Technische Informationsbibliothek (TIB) ;Bl\u00fcmel, Ina;0000-0002-3075-7640;Heller, Lambert;0000-0003-0232-7085;Einbock, Joanna;H\u00e4fner, Peter;Melin, Louise;Die qualitative Studie wurde von September bis November 2016 in Form von leitfadengest\u00fctzter Interviews mit administrativen Ansprechpersonen aus 20 deutschen Forschungseinrichtungen (9 aus Hochschulen und 11 aus au\u00dferuniversit\u00e4ren Forschungseinrichtungen) sowie mit 30 Wissenschaftlerinnen und Wissenschaftlern (17 aus Hochschulen und 13 aus au\u00dferuniversit\u00e4ren Forschungseinrichtungen) durchgef\u00fchrt. Das Tabellenblatt \"Leitfaden Administration\" beinhaltet den f\u00fcr die Interviews mit den administrativen Ansprechpersonen verwendeten Interview-Leitfaden. Die Ergebnisse dieser Interviews sind im Tabellenblatt \"Auswertung Administration\" zu finden. Das Tabellenblatt \"Leitfaden Forschende\" beinhaltet den f\u00fcr die Interviews mit den Wissenschaftlerinnen und Wissenschaftlern verwendeten Interview-Leitfaden. Die Ergebnisse dieser Interviews sind im Tabellenblatt \"Auswertung Forschende\" zu finden.;Forschungsinformationssysteme, FIS;Bl\u00fcmel, Ina;Heller, Lambert;Einbock, Joanna;H\u00e4fner, Peter;Melin, Louise;deu;BMBF;application/zip",
-    "group": "radar",
-    "groups": [
-        {
-            "name": "radar"
-        }
-    ],
-    "name": "5a9e06d7-6c03-52b5-9644-c04c836e08fd",
-    "notes": [
-        "Die qualitative Studie wurde von September bis November 2016 in Form von leitfadengest\u00fctzter Interviews mit administrativen Ansprechpersonen aus 20 deutschen Forschungseinrichtungen (9 aus Hochschulen und 11 aus au\u00dferuniversit\u00e4ren Forschungseinrichtungen) sowie mit 30 Wissenschaftlerinnen und Wissenschaftlern (17 aus Hochschulen und 13 aus au\u00dferuniversit\u00e4ren Forschungseinrichtungen) durchgef\u00fchrt. Das Tabellenblatt \"Leitfaden Administration\" beinhaltet den f\u00fcr die Interviews mit den administrativen Ansprechpersonen verwendeten Interview-Leitfaden. Die Ergebnisse dieser Interviews sind im Tabellenblatt \"Auswertung Administration\" zu finden. Das Tabellenblatt \"Leitfaden Forschende\" beinhaltet den f\u00fcr die Interviews mit den Wissenschaftlerinnen und Wissenschaftlern verwendeten Interview-Leitfaden. Die Ergebnisse dieser Interviews sind im Tabellenblatt \"Auswertung Forschende\" zu finden.",
-        "Forschungsinformationssysteme, FIS"
-    ],
-    "oai_identifier": [
-        "5a9e06d7-6c03-52b5-9644-c04c836e08fd"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Bibliothekswissenschaft"
-        },
-        {
-            "name": "library"
-        },
-        {
-            "name": "science"
-        }
-    ],
-    "title": [
-        "Datensatz zur Umfrage: Nutzung von Forschungsinformationssystemen in Forschungseinrichtungen"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/radar-oai_dc/SET_1/json/8836369f-85c6-504b-ba07-f842627328c4.json b/oaitestdata/radar-oai_dc/SET_1/json/8836369f-85c6-504b-ba07-f842627328c4.json
deleted file mode 100644
index e9ff84ba..00000000
--- a/oaitestdata/radar-oai_dc/SET_1/json/8836369f-85c6-504b-ba07-f842627328c4.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "Technische Informationsbibliothek (TIB)"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.22000/72",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "application/zip"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://www.radar-service.eu/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=8836369f-85c6-504b-ba07-f842627328c4",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Technische Informationsbibliothek (TIB)"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "CC BY 4.0 Attribution",
-        "Technische Informationsbibliothek (TIB)"
-    ],
-    "author": [
-        "Drees, Bastian"
-    ],
-    "fulltext": "10.22000-72;2018-04-20T15:52:37Z;10.22000/72;DOI;Drees, Bastian;0000-0003-3508-602X;Survey on Conference Recording Service among the Institutions of the Leibniz Association;Technische Informationsbibliothek (TIB);2018;Other;Bibliothekswissenschaft;Dataset;CC BY 4.0 Attribution;Technische Informationsbibliothek (TIB);In order to determine the demand for a conference recording service within the Leibniz Association, a survey was conducted (using the LimeSurvey software) among all Leibniz institutions (except TIB) from 12 to 24 March 2018. Of the 92 institutions surveyed, 68 took part in the survey (73%), of which 43 completed the survey in full (47%). Only the latter results were taken into account for the evaluation. The participants of the survey come from all 5 sections, with the most participants from section A (35%) and the least from section E (9%). All respondents stated that they organize or host at least 1-2 events per year, while 35% organize or host 3-5 events and a relative majority of 42% organizes or hosts more than 5 events a year. There are talks at all events and a vast majority of 86% stated that there are on average up to 30 talks at each of their events.  42% of the respondents stated that they already recorded events in the past, while 54% did not. However, the comments showed that most institutes had only very occasionally produced recordings and in some cases only audio recordings. Therefore, an enormous majority of 77% stated that they were interested in a Leibniz conference recording service with only 14% stating that they were not interested. The remaining 9% did not answer the question or commented that their interest would depend on the exact conditions of the service.  We conclude from this survey that there is a very great potential and an enormous demand for LeiCord within the Leibniz Association. We estimate from the results that all Leibniz institutes together host and organize about 350-500 events annually with a total of about seven to ten thousand talks. With more than three quarters of the respondents being interested in a conference recording service this represents an enormous treasure trove of scientific communication that can be opened to a larger audience. ;Umfrage, wissenschaftliche Konferenz, Videoaufzeichnung, Marktanalyse, Survey, Scientific Conference, Video Recordings, Needs Assessment;deu;application/zip",
-    "group": "radar",
-    "groups": [
-        {
-            "name": "radar"
-        }
-    ],
-    "name": "8836369f-85c6-504b-ba07-f842627328c4",
-    "notes": [
-        "In order to determine the demand for a conference recording service within the Leibniz Association, a survey was conducted (using the LimeSurvey software) among all Leibniz institutions (except TIB) from 12 to 24 March 2018. Of the 92 institutions surveyed, 68 took part in the survey (73%), of which 43 completed the survey in full (47%). Only the latter results were taken into account for the evaluation. The participants of the survey come from all 5 sections, with the most participants from section A (35%) and the least from section E (9%). All respondents stated that they organize or host at least 1-2 events per year, while 35% organize or host 3-5 events and a relative majority of 42% organizes or hosts more than 5 events a year. There are talks at all events and a vast majority of 86% stated that there are on average up to 30 talks at each of their events.  42% of the respondents stated that they already recorded events in the past, while 54% did not. However, the comments showed that most institutes had only very occasionally produced recordings and in some cases only audio recordings. Therefore, an enormous majority of 77% stated that they were interested in a Leibniz conference recording service with only 14% stating that they were not interested. The remaining 9% did not answer the question or commented that their interest would depend on the exact conditions of the service.  We conclude from this survey that there is a very great potential and an enormous demand for LeiCord within the Leibniz Association. We estimate from the results that all Leibniz institutes together host and organize about 350-500 events annually with a total of about seven to ten thousand talks. With more than three quarters of the respondents being interested in a conference recording service this represents an enormous treasure trove of scientific communication that can be opened to a larger audience. ",
-        "Umfrage, wissenschaftliche Konferenz, Videoaufzeichnung, Marktanalyse, Survey, Scientific Conference, Video Recordings, Needs Assessment"
-    ],
-    "oai_identifier": [
-        "8836369f-85c6-504b-ba07-f842627328c4"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Bibliothekswissenschaft"
-        }
-    ],
-    "title": [
-        "Survey on Conference Recording Service among the Institutions of the Leibniz Association"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/radar-oai_dc/SET_1/json/b8f13f39-102c-5f9e-a598-2d68ae45d64c.json b/oaitestdata/radar-oai_dc/SET_1/json/b8f13f39-102c-5f9e-a598-2d68ae45d64c.json
deleted file mode 100644
index 6b83227b..00000000
--- a/oaitestdata/radar-oai_dc/SET_1/json/b8f13f39-102c-5f9e-a598-2d68ae45d64c.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "Technische Informationsbibliothek (TIB)"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.22000/54",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "application/zip"
-    ],
-    "Language": [
-        "German"
-    ],
-    "MetaDataAccess": "https://www.radar-service.eu/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=b8f13f39-102c-5f9e-a598-2d68ae45d64c",
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Technische Informationsbibliothek (TIB)"
-    ],
-    "ResourceType": [
-        "Umfrage / Survey",
-        "Dataset"
-    ],
-    "Rights": [
-        "CC BY 4.0 Attribution",
-        "Technische Informationsbibliothek (TIB)"
-    ],
-    "author": [
-        "Technische Informationsbibliothek (TIB) (conducted by engage AG)"
-    ],
-    "fulltext": "10.22000-54;2017-09-25T11:56:48Z;10.22000/54;DOI;Technische Informationsbibliothek (TIB) (conducted by engage AG);Questionnaire and Dataset of the TIB Survey 2017 on information procurment and pubishing behaviour of researchers in the natural sciences and engineering;Technische Informationsbibliothek (TIB);2017;Social Sciences;Other;Bibliothekswesen;Other;Library Science;Umfrage / Survey;Dataset;CC BY 4.0 Attribution;Technische Informationsbibliothek (TIB);Dreyer, Britta;0000-0002-0687-5460;Einbock, Joanna;Heller, Lambert;0000-0003-0232-7085;Kraft, Angelina;0000-0002-6454-335X;Plank, Margret;0000-0001-8941-7563;Schrenk, Philip;Sens, Irina;0000-0001-9190-8628;Tullney, Marco;0000-0002-5111-2788;Bernhofer, Carolin;H\u00e4fner, Peter;This data set contains the questionnaire and anonymized excerpts from the raw data of the quantitative online survey carried out from the end of 2016 till the beginning of 2017 among the researchers in the natural sciences and engineering on the subject of their information procurment and publishing behavior. Researchers from German universities and non-university research institutes were questioned. For the statistical evaluation 1,464 questionnaires were included.  The survey was carried out by engage - Key Technology Ventures AG, Karlsruhe, on behalf of the Technische Informationsbibliothek (TIB), and was funded by the Federal Ministry of Education and Research (BMBF) within the project \"Professionalisation and continuation of the concept for exploitation of research results at the German National Library of Science and Technology, Hannover (TIB)\" (funding ID: 03IO1441) dealing with the knowledge and technology transfer at the TIB. Please note, that the data set is available only in German.;survey, information procurment, publishing, scientific publications, repositories, Open Access;Dreyer, Britta;Einbock, Joanna;Heller, Lambert;Kraft, Angelina;Plank, Margret;Schrenk, Philip;Sens, Irina;Tullney, Marco;Bernhofer, Carolin;H\u00e4fner, Peter;deu;501100002347;application/zip",
-    "group": "radar",
-    "groups": [
-        {
-            "name": "radar"
-        }
-    ],
-    "name": "b8f13f39-102c-5f9e-a598-2d68ae45d64c",
-    "notes": [
-        "This data set contains the questionnaire and anonymized excerpts from the raw data of the quantitative online survey carried out from the end of 2016 till the beginning of 2017 among the researchers in the natural sciences and engineering on the subject of their information procurment and publishing behavior. Researchers from German universities and non-university research institutes were questioned. For the statistical evaluation 1,464 questionnaires were included.  The survey was carried out by engage - Key Technology Ventures AG, Karlsruhe, on behalf of the Technische Informationsbibliothek (TIB), and was funded by the Federal Ministry of Education and Research (BMBF) within the project \"Professionalisation and continuation of the concept for exploitation of research results at the German National Library of Science and Technology, Hannover (TIB)\" (funding ID: 03IO1441) dealing with the knowledge and technology transfer at the TIB. Please note, that the data set is available only in German.",
-        "survey, information procurment, publishing, scientific publications, repositories, Open Access"
-    ],
-    "oai_identifier": [
-        "b8f13f39-102c-5f9e-a598-2d68ae45d64c"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Social"
-        },
-        {
-            "name": "Sciences"
-        },
-        {
-            "name": "Bibliothekswesen"
-        },
-        {
-            "name": "Library"
-        },
-        {
-            "name": "Science"
-        }
-    ],
-    "title": [
-        "Questionnaire and Dataset of the TIB Survey 2017 on information procurment and pubishing behaviour of researchers in the natural sciences and engineering"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/radar-oai_dc/SET_1/json/e5000edd-afa6-5eae-8999-fec6acac0422.json b/oaitestdata/radar-oai_dc/SET_1/json/e5000edd-afa6-5eae-8999-fec6acac0422.json
deleted file mode 100644
index fe6c6bfd..00000000
--- a/oaitestdata/radar-oai_dc/SET_1/json/e5000edd-afa6-5eae-8999-fec6acac0422.json
+++ /dev/null
@@ -1,90 +0,0 @@
-{
-    "Contact": [
-        "M\u00fcller, Eric"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.22000/43",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "application/zip"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.radar-service.eu/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=e5000edd-afa6-5eae-8999-fec6acac0422",
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "M\u00fcller, Eric"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Other",
-        "Licenses of the images according to image_licenses.csv",
-        "Rights holders of the images according to image_licenses.csv"
-    ],
-    "author": [
-        "Ewerth, Ralph",
-        "Springstein, Matthias",
-        "M\u00fcller, Eric"
-    ],
-    "fulltext": "10.22000-44;2017-07-12T20:25:05Z;10.22000/44;DOI;M\u00fcller, Eric;0000-0002-6802-1241;Springstein, Matthias;0000-0002-6509-8534;Ewerth, Ralph;0000-0003-0918-6297;Date Estimation in the Wild Images;M\u00fcller, Eric;2017;Computer Science;Other;Machine Learning;Other;Deep Learning;Other;Information Retrieval;Other;Image Retrieval;Other;Date Estimation;Dataset;Other;Licenses of the images according to image_licenses.csv;Rights holders of the images according to image_licenses.csv;eng;10.22000/43;10.22000/43;DOI;DOI;application/zip",
-    "group": "radar",
-    "groups": [
-        {
-            "name": "radar"
-        }
-    ],
-    "name": "e5000edd-afa6-5eae-8999-fec6acac0422",
-    "oai_identifier": [
-        "e5000edd-afa6-5eae-8999-fec6acac0422"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Computer"
-        },
-        {
-            "name": "Science"
-        },
-        {
-            "name": "Machine"
-        },
-        {
-            "name": "Learning"
-        },
-        {
-            "name": "Deep"
-        },
-        {
-            "name": "Learning"
-        },
-        {
-            "name": "Information"
-        },
-        {
-            "name": "Retrieval"
-        },
-        {
-            "name": "Image"
-        },
-        {
-            "name": "Retrieval"
-        },
-        {
-            "name": "Date"
-        },
-        {
-            "name": "Estimation"
-        }
-    ],
-    "title": [
-        "Date Estimation in the Wild Images"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/radar-oai_dc/SET_1/json/f98d075f-69da-57c0-991b-f86f8a1547bf.json b/oaitestdata/radar-oai_dc/SET_1/json/f98d075f-69da-57c0-991b-f86f8a1547bf.json
deleted file mode 100644
index c3e990a1..00000000
--- a/oaitestdata/radar-oai_dc/SET_1/json/f98d075f-69da-57c0-991b-f86f8a1547bf.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "Michelle Lindlar, Yvonne Tunnat"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.22000/53",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Format": [
-        "application/zip"
-    ],
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://www.radar-service.eu/oai/provider?verb=GetRecord&metadataPrefix=oai_dc&identifier=f98d075f-69da-57c0-991b-f86f8a1547bf",
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "Michelle Lindlar, Yvonne Tunnat"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "CC BY-SA 4.0 Attribution-ShareAlike",
-        "Michelle Lindlar"
-    ],
-    "author": [
-        "Lindlar, Michelle",
-        "Tunnat, Yvonne",
-        "Carl, Wilson"
-    ],
-    "fulltext": "10.22000-53;2017-11-05T19:56:48Z;10.22000/53;DOI;Lindlar, Michelle;0000-0003-3709-5608 ;Tunnat, Yvonne;Carl, Wilson;Synthetic PDF Testset for File Format Validation;Michelle Lindlar, Yvonne Tunnat;2017;Software Technology;Text;CC BY-SA 4.0 Attribution-ShareAlike;Michelle Lindlar;This data set presents a corpus of light-weight files designed to test the validation criteria of JHOVE's PDF module against \"well-formedness\". Test cases are based on structural requirements for PDF files as per ISO 32000-1:2008 standard. The basis for all test files is a single page, one line document with no special features such as linearization. While such a light-weight document only allows to check against a fragment of standard requirements, the focus was put on basic structure violations at the header, trailer, document catalog, page tree node and cross-reference levels. The test set also checks for basic violations at the page node, page resource and stream object level.   The accompanying spreadsheet briefly categorizes and describes the test set and includes the outcome when running the test set against JHOVE 1.16, PDF-hul 1.8 as well as Adobe Acrobat Professional XI Pro (11.0.15). The spreadsheet also includes a codecov coverage statistic for the test set in relation to the JHOVE 1.16, PDF-hul 1.8 module. Further information can be found in the paper \"A PDF Test-Set for Well-Formedness Validation in JHOVE - The Good, the Bad and the Ugly\", published in the proceedings of the 14th International Conference on Digital Preservation (Kyoto, Japan, September 25-29 2017). While the spreadsheet only contains results of running the test set against JHOVE, it can be used as a ground truth for any file format validation process.;PDF, file format validation, digital preservation, ISO 32000-1:2008;eng;application/zip",
-    "group": "radar",
-    "groups": [
-        {
-            "name": "radar"
-        }
-    ],
-    "name": "f98d075f-69da-57c0-991b-f86f8a1547bf",
-    "notes": [
-        "This data set presents a corpus of light-weight files designed to test the validation criteria of JHOVE's PDF module against \"well-formedness\". Test cases are based on structural requirements for PDF files as per ISO 32000-1:2008 standard. The basis for all test files is a single page, one line document with no special features such as linearization. While such a light-weight document only allows to check against a fragment of standard requirements, the focus was put on basic structure violations at the header, trailer, document catalog, page tree node and cross-reference levels. The test set also checks for basic violations at the page node, page resource and stream object level.   The accompanying spreadsheet briefly categorizes and describes the test set and includes the outcome when running the test set against JHOVE 1.16, PDF-hul 1.8 as well as Adobe Acrobat Professional XI Pro (11.0.15). The spreadsheet also includes a codecov coverage statistic for the test set in relation to the JHOVE 1.16, PDF-hul 1.8 module. Further information can be found in the paper \"A PDF Test-Set for Well-Formedness Validation in JHOVE - The Good, the Bad and the Ugly\", published in the proceedings of the 14th International Conference on Digital Preservation (Kyoto, Japan, September 25-29 2017). While the spreadsheet only contains results of running the test set against JHOVE, it can be used as a ground truth for any file format validation process.",
-        "PDF, file format validation, digital preservation, ISO 32000-1:2008"
-    ],
-    "oai_identifier": [
-        "f98d075f-69da-57c0-991b-f86f8a1547bf"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Software"
-        },
-        {
-            "name": "Technology"
-        }
-    ],
-    "title": [
-        "Synthetic PDF Testset for File Format Validation"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/076e08f6-371f-5f8e-b7e5-1e3bdfec36d6.json b/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/076e08f6-371f-5f8e-b7e5-1e3bdfec36d6.json
deleted file mode 100644
index f1855dc7..00000000
--- a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/076e08f6-371f-5f8e-b7e5-1e3bdfec36d6.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "sdn-userdesk@seadatanet.org"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=iso19139&identifier=076e08f6-371f-5f8e-b7e5-1e3bdfec36d6",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Royal Belgian Institute of Natural Sciences, Operational Directorate Natural Environment, Belgian Marine Data Centre",
-        "IFREMER / IDM/SISMER",
-        "SEADATANET"
-    ],
-    "ResourceType": "dataset",
-    "Rights": [
-        "No limitations on public access.  For data access please register at http://www.marine-id.org"
-    ],
-    "SpatialCoverage": "(49N-62N,4 W-10E)",
-    "TempCoverageBegin": 59926737599,
-    "TempCoverageEnd": 63506113199,
-    "TemporalCoverage": " period : ( 1900-01-02T11:59:59Z - 2013-06-06T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1900-01-02T11:59:59Z",
-    "TemporalCoverage:EndDate": "2013-06-06T11:59:59Z",
-    "fulltext": "6aeb76a1-cc67-4071-a3a0-3be3b050fe21;SEADATANET;sdn-userdesk@seadatanet.org;http://www.seadatanet.org/;2018-07-24T09:47:48;ISO 19115:2003/19139 - EMODNET - SDN;0.1;4;0;0;false;WGS 84 (EPSG 4326);EPSG;North Sea - Temperature and salinity observation collection V1.1;seadatanet-north_sea-temperature_salinity_aggregated_public-v1_1;2015-07-01;1.1;2015-07-01;6aeb76a1-cc67-4071-a3a0-3be3b050fe21;The North Sea historical dataset includes all open access temperature and salinity in situ data from the North Sea for the period 1900 \u2013 2013. The data were retrieved from the SeaDataNet infrastructure at the beginning of 2014. Data quality has been analysed and checked using ODV software. Quality Flags of anomalous data have been revised using different QC procedures in conjunction with the visual expert check. Duplicates have been identified and excluded from the dataset.\n\nFor data access please register at http://www.marine-id.org;SeaDataNet;Royal Belgian Institute of Natural Sciences, Operational Directorate Natural Environment, Belgian Marine Data Centre;+32 (0)2 773 2111;+32 (0)2 770 6972;Gulledelle 100;Brussels;1200;Belgium;bmdc@mumm.ac.be;http://www.mumm.ac.be/datacentre/;web site;Royal Belgian Institute of Natural Sciences, Operational Directorate Natural Environment, Belgian Marine Data Centre;+32 (0)2 773 2111;+32 (0)2 770 6972;Gulledelle 100;Brussels;1200;Belgium;bmdc@mumm.ac.be;http://www.mumm.ac.be/datacentre/;web site;Royal Belgian Institute of Natural Sciences, Operational Directorate Natural Environment, Belgian Marine Data Centre;+32 (0)2 773 2111;+32 (0)2 770 6972;Gulledelle 100;Brussels;1200;Belgium;bmdc@mumm.ac.be;http://www.mumm.ac.be/datacentre/;web site;IFREMER / IDM/SISMER;+33 (0)2 98.22.49.16;+33 (0)2 98.22.46.44;Centre IFREMER de BrestBP 70;PLOUZANE;29280;France;sismer@ifremer.fr;http://www.ifremer.fr/sismer/;web site;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=6aeb76a1-cc67-4071-a3a0-3be3b050fe21&fname=NorthSeaTransp.png;Oceanographic geographical features;GEMET - INSPIRE themes, version 1.0;2009-09-22T07:57:15;Temperature of the water column;Salinity of the water column;Parameter Discovery Vocabulary (P02);2014-12-11;geonetwork.thesaurus.external.parameter.NVS.P02;ITS-90 water temperature;Water body salinity;EMODNET chemistry lot aggregated parameter names;2014-12-11;geonetwork.thesaurus.external.parameter.NVS.P35;North Sea;SeaVoX salt and fresh water body gazetteer;2014-12-11;geonetwork.thesaurus.external.reference-geographical-area.NVS.C19;Th\u00e8mes Sextant;2017-01-23;geonetwork.thesaurus.local.theme.sextant-theme;SeaDataNet licence;SeaDataNet Usage Agreement: If you use SeaDataNet data in your publications please include the following in the Acknowledgements: Data were provided through SeaDataNet Pan-European infrastructure for ocean and marine data management (https://www.seadatanet.org);No limitations on public access.  For data access please register at http://www.marine-id.org;oceans;bounding box;-4.25;9.96;48.6;62;1900-01-02;2013-06-06;-1575.0;0.0;http://dx.doi.org/10.12770/6aeb76a1-cc67-4071-a3a0-3be3b050fe21;WWW:LINK-1.0-http--metadata-URL;DOI of the product;ftp://ftp2.ifremer.fr/public/seadatanet-north_sea-temperaturesalinity_aggregated/SDN_2014-03_TS_North_Sea_QC_done_v1.1.zip;WWW:DOWNLOAD-1.0-link--download;full collection dataset;zipped ODV binary collection;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_North_Sea_QC_done_v1.1;OGC:WMS:getCapabilities;full collection dataset;full collection dataset;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_North_Sea_QC_done_v1.1;OGC:WMS;SDN_2014-03_TS_North_Sea_QC_done_v1.1/Salinity;Salinity;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_North_Sea_QC_done_v1.1;OGC:WMS;SDN_2014-03_TS_North_Sea_QC_done_v1.1/Temperature;Temperature;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_North_Sea_QC_done_v1.1;OGC:WMS;SDN_2014-03_TS_North_Sea_QC_done_v1.1/*;Observation locations;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;See the referenced specification;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "076e08f6-371f-5f8e-b7e5-1e3bdfec36d6",
-    "notes": [
-        "The North Sea historical dataset includes all open access temperature and salinity in situ data from the North Sea for the period 1900 \u2013 2013. The data were retrieved from the SeaDataNet infrastructure at the beginning of 2014. Data quality has been analysed and checked using ODV software. Quality Flags of anomalous data have been revised using different QC procedures in conjunction with the visual expert check. Duplicates have been identified and excluded from the dataset.\n\nFor data access please register at http://www.marine-id.org"
-    ],
-    "oai_identifier": [
-        "076e08f6-371f-5f8e-b7e5-1e3bdfec36d6"
-    ],
-    "oai_set": "cams1_ps",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-4.25,48.6],[-4.25,62],[9.96,62],[9.96,48.6],[-4.25,48.6]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "North Sea"
-        }
-    ],
-    "title": [
-        "North Sea - Temperature and salinity observation collection V1.1"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/0c10d441-0c39-542a-86cb-4a2d49fd0ffe.json b/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/0c10d441-0c39-542a-86cb-4a2d49fd0ffe.json
deleted file mode 100644
index 3b21efe8..00000000
--- a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/0c10d441-0c39-542a-86cb-4a2d49fd0ffe.json
+++ /dev/null
@@ -1,109 +0,0 @@
-{
-    "Contact": [
-        "sdn-userdesk@seadatanet.org"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=iso19139&identifier=0c10d441-0c39-542a-86cb-4a2d49fd0ffe",
-    "PublicationTimestamp": "2018-02-20T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "SEADATANET",
-        "IFREMER / IDM / SISMER - Scientific Information Systems for the SEA",
-        "Marine Hydrophysical Institute",
-        "Department of Navigation and Hydrography and Oceanography, Turkish Navy",
-        "National Institute for Marine Research and Development \"Grigore Antipa\"",
-        "Ukrainian scientific center of Ecology of Sea (UkrSCES)",
-        "Odessa branch of IBSS (Institute of Biology of Southern Seas)",
-        "OGS (Istituto Nazionale di Oceanografia e di Geofisica Sperimentale), Division of Oceanography",
-        "Nothern Regional Administration of Hydrometeorology of Roshydromet",
-        "Sinop University, Fisheries Faculty",
-        "Kuban offing station, North-Caucasus HMS",
-        "Iv.Javakhishvili Tbilisi State University, Centre of Relations with UNESCO Oceanological Research Centre and GeoDNA (UNESCO)",
-        "Southern Scientific Research Institute of Marine Fisheries and Oceanography",
-        "Shom",
-        "IFREMER",
-        "Odessa Branch of SOI (State Oceanographic Institute)",
-        "Institute of Fishery Resources (IFR)",
-        "Institute of Biology of the Southern Seas, NAS of Ukraine",
-        "Institute of Marine Sciences, Middle East Technical University",
-        "Donskaya offing station North-Caucasus HMS",
-        "Zoological Institute of the Russian Academy of Sciences",
-        "Mariupol Marine Hydrometeorological Station, Ukrainian HMS",
-        "Karadeniz Technical University, Faculty of Marine Sciences",
-        "North-Caucasus Regional Administration of Hydrometeorology of Roshydromet",
-        "National Institute of Meteorology and Hydrology, Bulgarian Academy of Sciences",
-        "ERIC Euro-Argo",
-        "Georgian Institute of Water Management of Georgian Technical University",
-        "Tuapse Hydrometeorological Bureau, North-Caucasus Centre",
-        "P.P.Shirshov Institute of Oceanology, RAS",
-        "Hellenic Centre for Marine Research, Institute of Oceanography (HCMR/IO)",
-        "IFREMER / GM-MARINE GEOSCIENCES",
-        "State Oceanographic Institute, Sebastopol Branch (SB SOI)",
-        "All-Russia Research Institute of Hydrometeorological Information - World Data Centre",
-        "Scientific - Research Firm \"GAMMA\"",
-        "Georgian Institute of Hydrometeorology of Georgian Technical University",
-        "Istanbul University, Institute of Marine Science and Management",
-        "Bulgarian National Oceanographic Data Centre(BGODC), Institute of Oceanology",
-        "Ankara University",
-        "Far Eastern Regional Hydrometeorological Research Institute",
-        "Ukrainian Hydrometeorological Institute - Marine Branch",
-        "Navy Main Administration of Navigation and Oceanography, Ministry of Defence",
-        "National Environmental Agency of the Ministry of Environment Protection and Natural Resources"
-    ],
-    "ResourceType": "dataset",
-    "Rights": [
-        "No limitations on public access.  For data access please register at http://www.marine-id.org"
-    ],
-    "SpatialCoverage": "(40N-48N,28E-42E)",
-    "TempCoverageBegin": 58931323199,
-    "TempCoverageEnd": 63640119599,
-    "TemporalCoverage": " period : ( 1868-06-17T11:59:59Z - 2017-09-04T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1868-06-17T11:59:59Z",
-    "TemporalCoverage:EndDate": "2017-09-04T11:59:59Z",
-    "fulltext": "2287615d-1977-479f-8d5b-439960bcb21a;SEADATANET;sdn-userdesk@seadatanet.org;http://www.seadatanet.org/;2018-09-27T07:47:25;ISO 19115:2003/19139 - EMODNET - SDN;0.1;WGS 84 (EPSG 4326);EPSG;Black Sea - Temperature and salinity Historical Data Collection SeaDataCloud V1;SDC_BLS_DATA_TS_V1;2018-02-20;1;2018-02-20;2287615d-1977-479f-8d5b-439960bcb21a;The SeaDataCloud Temperature and Salinity Historical Data Collection for the Black Sea includes open access in situ data on temperature and salinity of water column in the Black Sea (and a little in the Sea of Azov) for period 1868 \u2013 2017. The data were retrieved from the SeaDataNet infrastructure at the end of 2017. The dataset format is Ocean Data View (ODV - http://odv.awi.de/) binary collection. The quality control of the data has been performed with the help of ODV software. Data Quality Flags have been revised and set up using the elaborated by SeaDataNet2 project QC procedures in conjunction with the visual expert check. Data duplicates have been identified and excluded from the dataset. The final number of the Temperature and Salinity profiles (stations) in the collection is 137723.\n\nFor data access please register at http://www.marine-id.org/.;SeaDataNet;Institute of Marine Sciences, Middle East Technical University;+90 (324) 5212406;+90 (324) 5212327;P.O.Box 28;Erdemli;33731;Turkey;volodymyr@ims.metu.edu.tr; devrim@ims.metu.edu.tr;http://www.ims.metu.edu.tr;web site;Institute of Marine Sciences, Middle East Technical University;+90 (324) 5212406;+90 (324) 5212327;P.O.Box 28;Erdemli;33731;Turkey;volodymyr@ims.metu.edu.tr; devrim@ims.metu.edu.tr;http://www.ims.metu.edu.tr;web site;IFREMER / IDM / SISMER - Scientific Information Systems for the SEA;+33 (0)2 98.22.49.16;+33 (0)2 98.22.46.44;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;sismer@ifremer.fr;http://www.ifremer.fr/sismer/;web site;All-Russia Research Institute of Hydrometeorological Information - World Data Centre;Russian Federation;nodc@meteo.ru;Ankara University;0312 596 10 00;0312 317 67 24;Ankara;06110;Turkey;agricul@agri.ankara.edu.tr;http://www.agri.ankara.edu.tr/;web site;Bulgarian National Oceanographic Data Centre(BGODC), Institute of Oceanology;+359 52 370 486;+359 52 370 483;40 Parvi may str. PO BOX 152;Varna;9000;Bulgaria;bgodc@io-bas.bg;http://www.bgodc.io-bas.bg;web site;Department of Navigation and Hydrography and Oceanography, Turkish Navy;\u00c7ubuklu;Istanbul;81647;Turkey;inapplicable;web site;Donskaya offing station North-Caucasus HMS;33, Leningradskaya St.;Azov;346740;Russian Federation;inapplicable;web site;ERIC Euro-Argo;+33(0)2 98 22 44 83;Z.I. Techonop\u00f4le Brest Iroise 1625 route de Sainte Anne;Plouzane;29280;France;euroargo@ifremer.fr;http://www.euro-argo.eu/;web site;Far Eastern Regional Hydrometeorological Research Institute;+7 (4232) 26-97-88;+7 (4232) 22-77-54;Fontannaya St., 24;Vladivostok;690600;Russian Federation;hydromet@online.ru;http://www.hydromet.com;web site;Georgian Institute of Hydrometeorology of Georgian Technical University;00995 32 951 047;00995 32 951 160;150A, Agmashenebeli ave;Tbilisi;0012;Georgia;begalishvili@gmail.com;web site;Georgian Institute of Water Management of Georgian Technical University;00995 32 224 094;00995 32 227 300;60, I.Chavchavadze Ave.;Tbilisi;0162;Georgia;gwmi@mail.ru;web site;Hellenic Centre for Marine Research, Institute of Oceanography (HCMR/IO);+30-22910-76452. -76460;+30-22910-76347;46.7 km Athinon-Souniou Av. P.O.Box 712;Anavyssos;19013;Greece;iosecretariat@hcmr.gr;http://www.hcmr.gr;web site;IFREMER;France;communication@ifremer.fr;IFREMER / GM-MARINE GEOSCIENCES;+33(0)2 98.22.42.70;+33(0)2 98.22.45.70;IFREMER Centre de Bretagne ZI Pointe du diable CS 10070;PLOUZANE;29280;France;geosciences.marines@ifremer.fr;http://www.ifremer.fr/drogm/;web site;IFREMER / IDM / SISMER - Scientific Information Systems for the SEA;+33 (0)2 98.22.49.16;+33 (0)2 98.22.46.44;IFREMER Centre de Bretagne ZI Pointe du diable CS 10070;PLOUZANE;29280;France;sismer@ifremer.fr;http://www.ifremer.fr/sismer/;web site;Institute of Biology of the Southern Seas, NAS of Ukraine;+380 692 544110;+380 692 557813;2, Nakhimov ave.;Sevastopol;99011;Ukraine;director@ibss.iuf.net;http://ibss.nas.gov.ua;web site;Institute of Fishery Resources (IFR);+359 52 632066;+359 52 632066;4 Primorski Blvd P.O. Box 72;Varna;9000;Bulgaria;vvmihneva@yahoo.com;http://www.ifrvarna.com;web site;Institute of Marine Sciences, Middle East Technical University;+90 (324) 5212406;+90 (324) 5212327;P.O.Box 28;Erdemli;33731;Turkey;devrim@ims.metu.edu.tr;http://www.ims.metu.edu.tr;web site;Istanbul University, Institute of Marine Science and Management;M\u00fcsk\u00fcle Sok. No. 1 Vefa;Istanbul;34470;Turkey;inapplicable;http://www.istanbul.edu.tr/enstituler/denizbilimleri/denizbilimleri.htm;web site;Iv.Javakhishvili Tbilisi State University, Centre of Relations with UNESCO Oceanological Research Centre and GeoDNA (UNESCO);+995 32 253222; +99532 222372;+99532 253222;1 I. Chavchavadze Ave., 0128,Tbilisi, Georgia Iv.Javakhishvili Tbilisi State University;Tbilisi;Georgia;wocean@telenet.ge;http://www.oceandna.ge;web site;Karadeniz Technical University, Faculty of Marine Sciences;+90 462 7522805;+90 462 752 2158;\u00c7amburnu, Trabzon;Turkey;61530;Turkey;www.ktu.edu.tr;web site;Kuban offing station, North-Caucasus HMS;60, R.Luxemburg St.;Temryuk;353520;Russian Federation;inapplicable;web site;Marine Hydrophysical Institute;+380 692 54 02 52;+380 692 55 42 53;2, Kapitanskaya str.;Sevastopol;99011;Ukraine;khaliulin.alexey@nodc.org.ua;http://WWW.MHI.IUF.NET;web site;Mariupol Marine Hydrometeorological Station, Ukrainian HMS;Mariupol;341010;Russian Federation;inapplicable;web site;National Environmental Agency of the Ministry of Environment Protection and Natural Resources;(+995 32) 439502 / 439550;(+995 32) 439503 / 439550;150 David Agmashenebeli ave.;Tbilisi;0112;Georgia;info@environment.ge;http://www.nea.gov.ge;web site;National Institute for Marine Research and Development \"Grigore Antipa\";40 241 543288;40 241 831274;300 Mamaia Blvd.;Constanta;900581;Romania;rmri@rmri.ro;http://www.rmri.ro;web site;National Institute of Meteorology and Hydrology, Bulgarian Academy of Sciences;+359 2 9753986;+359 2 9880380;66 Tsarigradsko schausse;Sofia;1784;Bulgaria;office@meteo.bg;http://www.weather.bg;web site;Navy Main Administration of Navigation and Oceanography, Ministry of Defence;+7 (812) 717 5900;2 Atamanskaya Ul.;St. Petersburg;193167;Russian Federation;suvvlad@mail.ru;http://okeany.com/vk/gunio.htm;web site;North-Caucasus Regional Administration of Hydrometeorology of Roshydromet;1/7, Erevanskaya St.;Rostov-on-Don;344025;Russian Federation;sk-ugms@yugmeteo.donpac.ru;http://www.yugmeteo.donpac.ru/coords.jsp;web site;Nothern Regional Administration of Hydrometeorology of Roshydromet;Russian Federation;norgimet@arh.ru;Odessa branch of IBSS (Institute of Biology of Southern Seas);+380 482 25 13 13;+380 482 25 09 18;37, Pushkinskaya str., Odessa, 65011, UKRAINE;Odessa;65011;Ukraine;Alexandrov@paco.net;http://obibss.narod.ru;web site;Odessa Branch of SOI (State Oceanographic Institute);Odessa;Ukraine;accem@te.net.ua;web site;OGS (Istituto Nazionale di Oceanografia e di Geofisica Sperimentale), Division of Oceanography;Borgo Grotta Gigante 42/c;Sgonico (Trieste);34010;Italy;nodc@ogs.trieste.it;http://www.ogs.trieste.it/;web site;P.P.Shirshov Institute of Oceanology, RAS;+7(499)124-59-96;+7(499)124-59-83;36 Nakhimovsky prospect;Moscow;117997;Russian Federation;office@ocean.ru;http://www.ocean.ru;web site;Scientific - Research Firm \"GAMMA\";+995 32 260 10 24;+995 32 260 44 33;17A , Guramishvili av. 0192, Tbilisi, Georgia;Tbilisi;0192;Georgia;v.gvakharia@gamma.ge;http://gamma.ge/;web site;Shom;+33 (0)2 56.31.23.12;+33 (0)2 56.31.25.80;13, rue du Chatellier CS92803;BREST CEDEX 2;29228;France;seadatanet-admin@shom.fr;http://www.shom.fr/;web site;Sinop University, Fisheries Faculty;Sinop;57000;Turkey;inapplicable;web site;Southern Scientific Research Institute of Marine Fisheries and Oceanography;+380 6561 21012;+380 6561 61627;YugNIRO, 2 Sverdlova str.;Kerch;98300;Ukraine;fish@kerch.com.ua, yugniro@kerch.com.ua;http://yugniro.crimea.com/;web site;State Oceanographic Institute, Sebastopol Branch (SB SOI);U.S.S.R. (deprecated);inapplicable;web site;Tuapse Hydrometeorological Bureau, North-Caucasus Centre;7, Morskaya St.;Tuapse;352800;Russian Federation;inapplicable;web site;Ukrainian Hydrometeorological Institute - Marine Branch;+38044 525 12 50;+38044 525 53 63;37, Prospekt Nauki;Kiev;03028;Ukraine;uhmi@uhmi.org.ua;web site;Ukrainian scientific center of Ecology of Sea (UkrSCES);+38 0482 636622;+380 482 636873;89 Frantsuzsky Blvd.;Odessa;65009;Ukraine;accem@te.net.ua;http://www.sea.gov.ua;web site;Zoological Institute of the Russian Academy of Sciences;+7 812 3280711;+7\u00a0(812)\u00a0328-29-41;Universitetskaya emb., 1;St. Petersburg;199034;Russian Federation;office@zin.ru;http://www.zin.ru;web site;https://sextant.ifremer.fr/geonetwork/srv/fre//resources.get?uuid=2287615d-1977-479f-8d5b-439960bcb21a&fname=BLACK_SDC_V1.png;Oceanographic geographical features;GEMET - INSPIRE themes, version 1.0;2018-07-27;geonetwork.thesaurus.external.theme.httpinspireeceuropaeutheme-theme;Salinity of the water column;Temperature of the water column;Parameter Discovery Vocabulary (P02);2017-11-17;geonetwork.thesaurus.external.parameter.NVS.P02;Water body salinity;ITS-90 water temperature;EMODNET chemistry lot aggregated parameter names;2016-09-20;geonetwork.thesaurus.external.parameter.NVS.P35;Sea of Azov;Black Sea;SeaVoX salt and fresh water body gazetteer;2016-09-20;geonetwork.thesaurus.external.reference-geographical-area.NVS.C19;Th\u00e8mes Sextant;2018-05-24;geonetwork.thesaurus.local.theme.sextant-theme;SeaDataNet licence;SeaDataNet Usage Agreement: If you use SeaDataNet data in your publications please include the following in the Acknowledgements: Data were provided through SeaDataNet Pan-European infrastructure for ocean and marine data management (https://www.seadatanet.org);No limitations on public access.  For data access please register at http://www.marine-id.org;oceans;bounding box;27.5;42;40.5;47.5;1868-06-17;2017-09-04;-2200.0;0.0;ODV binary collection;5;http://dx.doi.org/10.12770/2287615d-1977-479f-8d5b-439960bcb21a;WWW:LINK-1.0-http--metadata-URL;DOI of the product;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;See the referenced specification;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "0c10d441-0c39-542a-86cb-4a2d49fd0ffe",
-    "notes": [
-        "The SeaDataCloud Temperature and Salinity Historical Data Collection for the Black Sea includes open access in situ data on temperature and salinity of water column in the Black Sea (and a little in the Sea of Azov) for period 1868 \u2013 2017. The data were retrieved from the SeaDataNet infrastructure at the end of 2017. The dataset format is Ocean Data View (ODV - http://odv.awi.de/) binary collection. The quality control of the data has been performed with the help of ODV software. Data Quality Flags have been revised and set up using the elaborated by SeaDataNet2 project QC procedures in conjunction with the visual expert check. Data duplicates have been identified and excluded from the dataset. The final number of the Temperature and Salinity profiles (stations) in the collection is 137723.\n\nFor data access please register at http://www.marine-id.org/."
-    ],
-    "oai_identifier": [
-        "0c10d441-0c39-542a-86cb-4a2d49fd0ffe"
-    ],
-    "oai_set": "cams1_ps",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[27.5,40.5],[27.5,47.5],[42,47.5],[42,40.5],[27.5,40.5]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Sea Azov"
-        },
-        {
-            "name": "Black Sea"
-        }
-    ],
-    "title": [
-        "Black Sea - Temperature and salinity Historical Data Collection SeaDataCloud V1"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/0f378d06-d191-5130-94d6-b2507aa9234a.json b/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/0f378d06-d191-5130-94d6-b2507aa9234a.json
deleted file mode 100644
index 2ad2ecd3..00000000
--- a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/0f378d06-d191-5130-94d6-b2507aa9234a.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "sdn-userdesk@seadatanet.org"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=iso19139&identifier=0f378d06-d191-5130-94d6-b2507aa9234a",
-    "PublicationTimestamp": "2014-11-24T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "IFREMER / IDM/SISMER",
-        "SEADATANET",
-        "Istituto Nazionale di Geofisica e Vulcanologia \u2013 INGV, Sede di Bologna"
-    ],
-    "ResourceType": "dataset",
-    "Rights": [
-        "No limitations on public access.  For data access please register at http://www.marine-id.org"
-    ],
-    "SpatialCoverage": "(30N-46N,9 W-37E)",
-    "TempCoverageBegin": 59926651199,
-    "TempCoverageEnd": 63492551999,
-    "TemporalCoverage": " period : ( 1900-01-01T11:59:59Z - 2012-12-31T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1900-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2012-12-31T11:59:59Z",
-    "fulltext": "cd552057-b604-4004-b838-a4f73cc98fcf;SEADATANET;sdn-userdesk@seadatanet.org;http://www.seadatanet.org/;2018-07-24T09:47:24;ISO 19115:2003/19139 - EMODNET - SDN;0.1;4;12;1;false;WGS 84 (EPSG 4326);EPSG;Mediterranean Sea - Temperature and salinity observation collection V1.1;seadatanet-med_sea-temperature_salinity_aggregated_public-v1_1;2014-11-24;1.1;2012-12-17;cd552057-b604-4004-b838-a4f73cc98fcf;SeaDataNet Temperature and Salinity historical data collection contains all open access temperature and salinity in situ data retrieved from SeaDataNet infrastructure at the end of 2013. The data span between -9.25 and 37 degrees of longitude, thus including an Atlantic box and Marmara Sea, and cover the time period 1900-2012.\nData have been quality checked using ODV software. Quality Flags of anomalous data have been revised using basic QC procedures.\n\nFor data access please register at http://www.marine-id.org\n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/;SeaDataNet;Istituto Nazionale di Geofisica e Vulcanologia \u2013 INGV, Sede di Bologna;+39 051 4151412;+39 0514151499;Via Donato Creti n\u00b012;Bologna;40128;Italy;n.pinardi@sincem.unibo.it;http://www.ingv.it;web site;IFREMER / IDM/SISMER;+33 (0)2 98.22.49.16;+33 (0)2 98.22.46.44;Centre IFREMER de BrestBP 70;PLOUZANE;29280;France;sismer@ifremer.fr;http://www.ifremer.fr/sismer/;web site;Istituto Nazionale di Geofisica e Vulcanologia \u2013 INGV, Sede di Bologna;+39 051 4151412;+39 0514151499;Via Donato Creti n\u00b012;Bologna;40128;Italy;simona.simoncelli@ingv.it;http://www.ingv.it;web site;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=cd552057-b604-4004-b838-a4f73cc98fcf&fname=MedSeaTransp.png;Oceanographic geographical features;GEMET - INSPIRE themes, version 1.0;2009-09-22T07:57:15;Temperature of the water column;Temperature variation in the water column;Salinity of the water column;Parameter Discovery Vocabulary (P02);2014-12-11;geonetwork.thesaurus.external.parameter.NVS.P02;ITS-90 water temperature;Water body salinity;EMODNET chemistry lot aggregated parameter names;2014-12-11;geonetwork.thesaurus.external.parameter.NVS.P35;Adriatic Sea;Ligurian Sea;Mediterranean Sea, Eastern Basin;Mediterranean Sea, Western Basin;Ionian Sea;Tyrrhenian Sea;Balearic Sea;Mediterranean Region;Mediterranean Sea;Aegean Sea;Sea of Marmara;external.reference-geographical-area.NVS.C19;2014-11-12T15:05:00;Th\u00e8mes Sextant;2017-01-23;geonetwork.thesaurus.local.theme.sextant-theme;SeaDataNet licence;SeaDataNet Usage Agreement: If you use SeaDataNet data in your publications please include the following in the Acknowledgements: Data were provided through SeaDataNet Pan-European infrastructure for ocean and marine data management (https://www.seadatanet.org);No limitations on public access.  For data access please register at http://www.marine-id.org;1;oceans;bounding box;-9.250;36.625;30.000;46.125;1900-01-01;2012-12-31;-5500.0;0.0;http://dx.doi.org/10.12770/cd552057-b604-4004-b838-a4f73cc98fcf;WWW:LINK-1.0-http--metadata-URL;DOI of the product;ftp://vftp2.ifremer.fr/public/seadatanet-med_sea-temperaturesalinity_aggregated/SDN_2014-03_TS_MedSea_QC_done_v1.1.zip;WWW:DOWNLOAD-1.0-link--download;full collection dataset;zipped ODV binary collection;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_MedSea_QC_done_v1.1;OGC:WMS:getCapabilities;full collection dataset;full collection dataset;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_MedSea_QC_done_v1.1;OGC:WMS;SDN_2014-03_TS_MedSea_QC_done_v1.1/Salinity;Salinity;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_MedSea_QC_done_v1.1;OGC:WMS;SDN_2014-03_TS_MedSea_QC_done_v1.1/Temperature;Temperature;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_MedSea_QC_done_v1.1;OGC:WMS;SDN_2014-03_TS_MedSea_QC_done_v1.1/*;Observation locations;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;See the referenced specification;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "0f378d06-d191-5130-94d6-b2507aa9234a",
-    "notes": [
-        "SeaDataNet Temperature and Salinity historical data collection contains all open access temperature and salinity in situ data retrieved from SeaDataNet infrastructure at the end of 2013. The data span between -9.25 and 37 degrees of longitude, thus including an Atlantic box and Marmara Sea, and cover the time period 1900-2012.\nData have been quality checked using ODV software. Quality Flags of anomalous data have been revised using basic QC procedures.\n\nFor data access please register at http://www.marine-id.org\n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/"
-    ],
-    "oai_identifier": [
-        "0f378d06-d191-5130-94d6-b2507aa9234a"
-    ],
-    "oai_set": "cams1_ps",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-9.250,30.000],[-9.250,46.125],[36.625,46.125],[36.625,30.000],[-9.250,30.000]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Temperature variation water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "Adriatic Sea"
-        },
-        {
-            "name": "Ligurian Sea"
-        },
-        {
-            "name": "Mediterranean Sea"
-        },
-        {
-            "name": "Eastern Basin"
-        },
-        {
-            "name": "Mediterranean Sea"
-        },
-        {
-            "name": "Western Basin"
-        }
-    ],
-    "title": [
-        "Mediterranean Sea - Temperature and salinity observation collection V1.1"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/27c4e287-a115-5da6-9ee2-b8d35e156af3.json b/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/27c4e287-a115-5da6-9ee2-b8d35e156af3.json
deleted file mode 100644
index 2ec72538..00000000
--- a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/27c4e287-a115-5da6-9ee2-b8d35e156af3.json
+++ /dev/null
@@ -1,103 +0,0 @@
-{
-    "Contact": [
-        "sdn-userdesk@seadatanet.org"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=iso19139&identifier=27c4e287-a115-5da6-9ee2-b8d35e156af3",
-    "PublicationTimestamp": "2012-08-26T11:59:59Z",
-    "PublicationYear": [
-        "2012"
-    ],
-    "Publisher": [
-        "Marine Systems Institute at Tallinn University of Technology",
-        "Alfred-Wegener-Institute for Polar- and Marine Research",
-        "SEADATANET",
-        "GEOMAR Helmholtz Centre for Ocean Research Kiel",
-        "Aarhus University, Department of Bioscience, Marine Ecology Roskilde",
-        "Institute of Meteorology and Water Management National Research Institute, Maritime Branch in Gdynia (IMWM MB)",
-        "IFREMER / IDM/SISMER",
-        "NIOZ Royal Netherlands Institute for Sea Research",
-        "Odessa Branch of SOI (State Oceanographic Institute)",
-        "Department of Marine Research of the Environmental Protection Agency",
-        "Russian State Hydrometeorological University, St-Petersburg",
-        "Swedish Meteorological and Hydrological Institute",
-        "National Oceanography Centre, Liverpool",
-        "Institute of Marine Research",
-        "Finnish Institute of Marine Research (FIMR)",
-        "P.P.Shirshov Institute of Oceanology, RAS",
-        "Institute of Oceanology, Polish Academy of Sciences (IO PAS)",
-        "Umea Marine Sciences Centre, UMF",
-        "Shom",
-        "Environmental Protection Agency (EPA)",
-        "Stockholm Marine Research Centre, SMF"
-    ],
-    "ResourceType": "dataset",
-    "Rights": [
-        "No limitations on public access.  For data access please register at http://www.marine-id.org"
-    ],
-    "SpatialCoverage": "(53N-66N,9 E-30E)",
-    "TempCoverageBegin": 59926651199,
-    "TempCoverageEnd": 63524087999,
-    "TemporalCoverage": " period : ( 1900-01-01T11:59:59Z - 2013-12-31T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1900-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2013-12-31T11:59:59Z",
-    "fulltext": "993571fa-cdaf-4b5f-be7e-db9a88ca6d8c;SEADATANET;sdn-userdesk@seadatanet.org;http://www.seadatanet.org/;2018-07-24T09:47:33;ISO 19115:2003/19139 - EMODNET - SDN;0.1;4;23;false;WGS 84 (EPSG 4326);EPSG;Baltic Sea - Temperature and salinity observation collection V1.1;seadatanet-baltic_sea-temperature_salinity_aggregated_public-v1_1;2012-08-26;1.1;2012-08-28;993571fa-cdaf-4b5f-be7e-db9a88ca6d8c;Seadatanet temperature and salinity historical data collection, including revised quality flags after quality control.\n\nFor data access please register at http://www.marine-id.org\n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/;SeaDataNet;Swedish Meteorological and Hydrological Institute;+46-(0)11-495 80 00;+46-(0)11-495 80 01;Folkborgsvagen 1;Norrkoping;SE-601 76;Sweden;shark@smhi.se;http://www.smhi.se;web site;Swedish Meteorological and Hydrological Institute;+46-(0)11-495 80 00;+46-(0)11-495 80 01;Folkborgsvagen 1;Norrkoping;SE-601 76;Sweden;shark@smhi.se;http://www.smhi.se;web site;IFREMER / IDM/SISMER;+33 (0)2 98.22.49.16;+33 (0)2 98.22.46.44;Centre IFREMER de BrestBP 70;PLOUZANE;29280;France;sismer@ifremer.fr;http://www.ifremer.fr/sismer/;web site;Institute of Marine Research;+47 55 23 85 00;+47 55 23 85 31;Nordnesgaten 50\nPostboks 1870 Nordnes;Bergen;N-5817;Norway;post@imr.no;http://www.imr.no;web site;Alfred-Wegener-Institute for Polar- and Marine Research;None;None;Am Handelshafen 12;Bremerhaven;D-27570;Germany;folke.mehrtens@awi.de;http://www.awi.de;web site;Institute of Meteorology and Water Management National Research Institute, Maritime Branch in Gdynia (IMWM MB);+48-58-62-88-100;+48-58-62-88-163;Waszyngtona 42;Gdynia;81-342;Poland;None;http://www.baltyk.pogodynka.pl/;web site;Institute of Oceanology, Polish Academy of Sciences (IO PAS);+48 58 551 72 81;+48 58 551 21 30;Powstancow Warszawy 55;Sopot;81-712;Poland;smas@iopan.gda.pl;http://www.iopan.gda.pl/;web site;Environmental Protection Agency (EPA);None;None;Juozapaviciaus st. 9;Vilnius;LT-09311;Lithuania;aaa@aaa.am.lt;http://www.gamta.lt;web site;National Oceanography Centre, Liverpool;+44 (0)151 795 4800;+44 (0)151 795 4801;Joseph Proudman Building, 6 Brownlow Street;Liverpool;L3 5DA;United Kingdom;enquiries@noc.ac.uk;http://noc.ac.uk;web site;GEOMAR Helmholtz Centre for Ocean Research Kiel;+49 431 600-0;+49 431 600-2805;D\u00fcsternbrooker Weg 20;Kiel;24105;Germany;info@geomar.de;http://www.geomar.de/en/;web site;Shom;+33 (0)2 56.31.23.12;+33 (0)2 56.31.25.80;13, rue du Chatellier\nCS92803;BREST CEDEX 2;29228;France;seadatanet-admin@shom.fr;http://www.shom.fr/;web site;Swedish Meteorological and Hydrological Institute;+46-(0)11-495 80 00;+46-(0)11-495 80 01;Folkborgsvagen 1;Norrkoping;SE-601 76;Sweden;shark@smhi.se;http://www.smhi.se;web site;Stockholm Marine Research Centre, SMF;+46 (0)8-16 37 18;None;Svante Arrhenius V\u00e4g 21B\nFrescati Backe;Stockholm;SE-114 18;Sweden;smf@smf.su.se;http://www.smf.su.se;web site;Umea Marine Sciences Centre, UMF;+46 (0)90-786 79 74;+46 (0)90-786 99 75;Norrbyn;H\u00f6rnefors;SE-910 20;Sweden;info@umf.umu.se;http://www.umf.umu.se/;web site;Finnish Institute of Marine Research (FIMR);+358 9 613 941;+358 9 323 2970;Erik Palm\u00e9nin aukio 1\nP.O.Box 2;Helsinki;00561;Finland;None;http://www.fimr.fi/en/en_GB/en/;web site;NIOZ Royal Netherlands Institute for Sea Research;+31 222 369300;+31 222 319674;Landsdiep 4\nP.O. Box 59;Den Burg/Texel;1790 AB;Netherlands;dmg@nioz.nl;https://www.nioz.nl;web site;Department of Marine Research of the Environmental Protection Agency;+370 46 41 04 50;+370 46 41 04 60;Taikos Av. 26;Klaipeda;LT-91149;Lithuania;jtd@aaa.am.lt;http://www.gamta.lt/;web site;P.P.Shirshov Institute of Oceanology, RAS;+7(499)124-59-96;+7(499)124-59-83;36 Nakhimovsky prospect;Moscow;117997;Russian Federation;office@ocean.ru;http://www.ocean.ru;web site;Marine Systems Institute at Tallinn University of Technology;+372 6204300;None;MSI, Akadeemia tee 15a;Tallinn;12618;Estonia;msi@msi.ttu.ee;http://www.msi.ttu.ee;web site;Aarhus University, Department of Bioscience, Marine Ecology Roskilde;+45 8715000;+45 87154326;399 Frederiksborgvej\nP.O. Box 358;Roskilde;DK-4000;Denmark;None;http://bios.au.dk/en/;web site;Russian State Hydrometeorological University, St-Petersburg;None;None;98, Maloohtinsky Pr.;St.-Petersburg;195196;Russian Federation;rector@rshu.ru;http://www.rshi.nw.ru/win/home-ru.htm;web site;Odessa Branch of SOI (State Oceanographic Institute);None;None;None;Odessa;None;Ukraine;None;None;web site;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=993571fa-cdaf-4b5f-be7e-db9a88ca6d8c&fname=BalticSeaTransp.png;Oceanographic geographical features;GEMET - INSPIRE themes, version 1.0;2009-09-22T07:57:15;Temperature of the water column;Salinity of the water column;external.parameter.NVS.P02;2014-11-12T15:04:00;ITS-90 water temperature;Water body salinity;EMODNET chemistry lot aggregated parameter names;2014-12-11;geonetwork.thesaurus.external.parameter.NVS.P35;Baltic Sea;Bay of Bothnia;Central Baltic Sea;Gulf of Bothnia;Gulf of Finland;Kattegat;Lillebaelt;Skagerrak;Storebaelt;external.reference-geographical-area.NVS.C19;2014-11-12T15:05:00;Th\u00e8mes Sextant;2017-01-23;geonetwork.thesaurus.local.theme.sextant-theme;SeaDataNet licence;SeaDataNet Usage Agreement: If you use SeaDataNet data in your publications please include the following in the Acknowledgements: Data were provided through SeaDataNet Pan-European infrastructure for ocean and marine data management (https://www.seadatanet.org);No limitations on public access.  For data access please register at http://www.marine-id.org;oceans;bounding box;9;30;53;66;1900-01-01;2013-12-31;-500.0;0.0;http://dx.doi.org/10.12770/993571fa-cdaf-4b5f-be7e-db9a88ca6d8c;WWW:LINK-1.0-http--metadata-URL;DOI of the product;ftp://vftp2.ifremer.fr/public/seadatanet-baltic_sea-temperaturesalinity_aggregated/SDN_2014-03_TS_BalticSea_QC_done_v1.1.zip;WWW:DOWNLOAD-1.0-link--download;full collection dataset;zipped ODV binary collection;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_BalticSea_QC_done_v1.1;OGC:WMS:getCapabilities;full collection dataset;full collection dataset;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_BalticSea_QC_done_v1.1;OGC:WMS;SDN_2014-03_TS_BalticSea_QC_done_v1.1/Salinity;Salinity;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_BalticSea_QC_done_v1.1;OGC:WMS;SDN_2014-03_TS_BalticSea_QC_done_v1.1/Temperature;Temperature;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_BalticSea_QC_done_v1.1;OGC:WMS;SDN_2014-03_TS_BalticSea_QC_done_v1.1/*;Observation locations;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;See the referenced specification;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "27c4e287-a115-5da6-9ee2-b8d35e156af3",
-    "notes": [
-        "Seadatanet temperature and salinity historical data collection, including revised quality flags after quality control.\n\nFor data access please register at http://www.marine-id.org\n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/"
-    ],
-    "oai_identifier": [
-        "27c4e287-a115-5da6-9ee2-b8d35e156af3"
-    ],
-    "oai_set": "cams1_ps",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[9,53],[9,66],[30,66],[30,53],[9,53]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "Baltic Sea"
-        },
-        {
-            "name": "Bay Bothnia"
-        },
-        {
-            "name": "Central Baltic Sea"
-        },
-        {
-            "name": "Gulf Bothnia"
-        },
-        {
-            "name": "Gulf Finland"
-        },
-        {
-            "name": "Kattegat"
-        },
-        {
-            "name": "Lillebaelt"
-        }
-    ],
-    "title": [
-        "Baltic Sea - Temperature and salinity observation collection V1.1"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/390e5b25-ee73-5b8a-bc37-7f339bb8221d.json b/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/390e5b25-ee73-5b8a-bc37-7f339bb8221d.json
deleted file mode 100644
index 43cb7bdd..00000000
--- a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/390e5b25-ee73-5b8a-bc37-7f339bb8221d.json
+++ /dev/null
@@ -1,185 +0,0 @@
-{
-    "Contact": [
-        "sdn-userdesk@seadatanet.org"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=iso19139&identifier=390e5b25-ee73-5b8a-bc37-7f339bb8221d",
-    "PublicationTimestamp": "2018-02-23T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "SEADATANET",
-        "IFREMER / STATION DE LA TRINITE",
-        "IRD / CENTRE DE LA MARTINIQUE",
-        "IFREMER / DYNECO/PELAGOS-LABORATOIRE D'ECOLOGIE PELAGIQUE",
-        "Proudman Oceanographic Laboratory",
-        "IEO/ La Coruna Oceanographic Centre",
-        "Scottish Office Agriculture Environment and Fisheries Department - Aberdeen Marine Laboratory",
-        "IFREMER / IDM/SISMER",
-        "Marine Biological Association of the United Kingdom",
-        "Institute of Oceanographic Sciences, Bidston Laboratory",
-        "Institute of Marine Research (IIM-CSIC)",
-        "IHPT, Hydrographic Institute",
-        "ENEA Centro Ricerche Ambiente Marino - La Spezia",
-        "Ifremer / Crela",
-        "IRD / CENTRE OF HANN",
-        "British Oceanographic Data Centre",
-        "University of Plymouth, Institute of Marine Studies",
-        "Isle of Man Government Laboratory",
-        "IFREMER / RBE Department / Biogeochimical end Ecotoxicological Resarch Unit (Nantes)",
-        "Ministry of Agriculture, Fisheries and Food, Lowestoft Fisheries Laboratory",
-        "Swedish Meteorological and Hydrological Institute",
-        "National Oceanography Centre, Liverpool",
-        "CEREGE",
-        "P.P.Shirshov Institute of Oceanology, RAS",
-        "IFREMER / GM-MARINE GEOSCIENCES",
-        "University of Southampton School of Ocean and Earth Science",
-        "LABO ATMOSPHEREs, MILIEUX, OBSERVATIONS SPATIALES (LATMOS)",
-        "University of Rostock, Institute of Biosciences",
-        "Shom",
-        "UTM-CSIC/Marine Technology Unit",
-        "Centre for Environment, Fisheries and Aquaculture Science, Lowestoft Laboratory",
-        "Polar Scientific Research Institute of Fishery and Oceanography",
-        "Laboratory of Physical Oceanography/ UNIVERSITE DE BRETAGNE OCCIDENTALE (UBO)",
-        "Universite de Pau / IPREM multidisciplinary research institute for the environment and materials",
-        "IRD / CENTRE OF ABIDJAN",
-        "IFREMER / STH/LBH-LABORATOIRE BIOLOGIE HALIEUTIQUE",
-        "Roscoff Marine Station, Sorbonne Universit\u00e9s, UPMC Univ Paris 06 and CNRS",
-        "Southampton Oceanography Centre",
-        "LABORATORY OF OCEANOGRAPHY of VILLEFRANCHE (LOV) / OOV",
-        "IEO/ Cadiz Oceanographic Centre",
-        "IRD / CENTRE DE PAPEETE",
-        "IFREMER",
-        "University of Liverpool, Port Erin Marine Laboratory",
-        "IRD CENTRE DE NOUMEA",
-        "IEO/ Malaga Oceanographic Centre",
-        "Institute of Earth Physics of Paris",
-        "Institute of Marine Research",
-        "Atlantic Scientific Research Institute for Marine Fishery and Oceanography",
-        "Universite D'Angers / Laboratoire Des Bio-Indicateurs Actuels Et Fossiles (Biaf)",
-        "CNEVA / LAB. PATHOLOGIE ANIMAUX AQUATIQUES",
-        "NIOZ Royal Netherlands Institute for Sea Research",
-        "University of East Anglia, School of Environmental Sciences",
-        "LABORATORY of PHYSICAL OCEANOGRAPHY (LPO) UMR 6523 CNRS-IFREMER-IRD-UBO",
-        "Institute of Oceanographic Sciences Wormley Laboratory",
-        "IFREMER / DYNECO- Coastal Environment Dynamics department",
-        "University of Southampton Department of Oceanography",
-        "Far Eastern Regional Hydrometeorological Research Institute",
-        "IFREMER / CENTRE DE BRETAGNE",
-        "UNIVERSITE DE BRETAGNE OCCIDENTALE (UBO) / LAB. D'OCEANO. CHIMIQUE LOC - IUEM",
-        "UNKNOWN",
-        "Ukrainian scientific center of Ecology of Sea (UkrSCES)",
-        "Dunstaffnage Marine Laboratory",
-        "Malaga University (UMA). Applied Physics departament II",
-        "IEO/ Gijon Oceanographic Centre",
-        "University of Liverpool Department of Oceanography",
-        "IFREMER STATION DE LA ROCHELLE-L'HOUMEAU",
-        "IFREMER / STATION DE LA TREMBLADE",
-        "CEA / INSTITUT DE RADIOPROTECTION ET DE SURETE NUCLEAIRE",
-        "Odessa Branch of SOI (State Oceanographic Institute)",
-        "Marine Hydrophysical Institute",
-        "IEO/ Santander Oceanographic Centre",
-        "Canary Institute of Marine Sciences",
-        "IFREMER / STATION DE LORIENT",
-        "Laboratory of Oceanography and Climate : Experiments and numerical Approaches - UMR 7159",
-        "IRD ANTENNE INSTITUT OCEANOGRAPHIQUE (IRD)",
-        "Fisheries Research Services, Aberdeen Marine Laboratory",
-        "German Hydrographic Institute",
-        "Oceanologic Observatory of Banyuls (University of Paris VI) / OSU",
-        "Institute of Oceanographic Sciences Deacon Laboratory",
-        "IEO/ Oceanographic Centre of Canary Island",
-        "MUSEUM NATIONAL D'HISTOIRE NATURELLE / LABORATOIRE D'OCEANOGRAPHIE PHYSIQUE",
-        "University of Bordeaux I / Marine Biology Institut",
-        "Scottish Office Agriculture and Fisheries Department - Aberdeen Marine Laboratory",
-        "COM - Physical and Biogeochemical Oceanography Laboratory (LUMINY)",
-        "Department of Agriculture and Fisheries for Scotland - Aberdeen Marine Laboratory",
-        "Scottish Association for Marine Science",
-        "IFREMER / EMH-DEPARTEMENT ECOLOGIE ET MODELES POUR L'HALIEUTIQUE",
-        "IEO/ Vigo Oeanographic Centre",
-        "CEA / Laboratory of climatolocical and environmental Sciences(LSCE)",
-        "University of Cambridge Department of Earth Sciences",
-        "Marine Research Institute",
-        "CNRS / Microbiology, Geochemistry and Marine Ecology Laboratory",
-        "EPOC - Geology and Oceanography Department",
-        "National Oceanography Centre, Southampton",
-        "OGS (Istituto Nazionale di Oceanografia e di Geofisica Sperimentale), Division of Oceanography",
-        "ISTPM (IFREMER NANTES)",
-        "Marine Scotland Science",
-        "IFREMER / STATION DE SETE",
-        "Las Palmas University. Sciences of the Sea Faculty",
-        "GEOMAR Helmholtz Centre for Ocean Research Kiel",
-        "Universite de la Rochelle / Litoral Environnement et Societe (LIENSS) - UMR 7266",
-        "Scottish Marine Biological Association",
-        "Marine Institute",
-        "Aquitaine Observatory of Sciences of the Universe \u2013 University of Bordeaux (OASU)",
-        "University of Bordeaux I / IGBA Talence",
-        "IFREMER / STH-DEPARTEMENT SCIENCES ET TECHNOLOGIES HALIEUTIQUES",
-        "University of Bordeaux I / Laboratory for Physical and Toxico Chemistry (ISM)",
-        "Alfred-Wegener-Institute for Polar- and Marine Research",
-        "IRD /CENTRE DE BRETAGNE",
-        "IFREMER / Dpt Technologicals Research and Development",
-        "IFREMER / DYNECO / PHYSED -LABO PHYSIQUE HYDRODYNAMIQUE ET SEDIMENTAIRE",
-        "Defence Evaluation Research Agency",
-        "Federal Maritime and Hydrographic Agency",
-        "UNIVERSITE DE PAU / LAB.CHIMIE BIO INORGANIQUE & ENVIRONNEMENT",
-        "IFREMER / STATION D'ARCACHON",
-        "IRD / CENTRE DE MONTPELLIER",
-        "IFREMER / HMMN-DEPARTEMENT HALIEUTIQUE DE MANCHE-MER DU NORD",
-        "University of Wales, School of Ocean Sciences",
-        "Plymouth Marine Laboratory",
-        "IEO/Spanish Oceanographic Institute",
-        "IFREMER / EEP / LEP-DEEP ENVIRONMENT LABORATORY"
-    ],
-    "ResourceType": "dataset",
-    "Rights": [
-        "No limitations on public access.  For data access please register at http://www.marine-id.org"
-    ],
-    "SpatialCoverage": "(10N-62N,90W-10E)",
-    "TempCoverageBegin": 59926651199,
-    "TempCoverageEnd": 63645134399,
-    "TemporalCoverage": " period : ( 1900-01-01T11:59:59Z - 2017-11-01T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1900-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2017-11-01T11:59:59Z",
-    "fulltext": "970bb3ba-aaf6-4066-9656-87c85da41dbb;SEADATANET;sdn-userdesk@seadatanet.org;http://www.seadatanet.org/;2018-09-27T10:27:14;ISO 19115:2003/19139 - EMODNET - SDN;0.1;WGS 84 (EPSG 4326);EPSG;North Atlantic Ocean - Temperature and Salinity Historical Data Collection SeaDataCloud V1;SDC_NAT_DATA_TS_V1;2018-02-23;1;970bb3ba-aaf6-4066-9656-87c85da41dbb;The SeaDataCloud TS historical data collection v1 for the North Atlantic Ocean, includes open access in situ data on temperature and salinity of water column in the North Atlantic Ocean from 10\u00b0N  to 62\u00b0N, including the Labrador Sea, The data were retrieved from the SeaDataNet infrastructure at the end of November 2017. The dataset format is Ocean Data View (ODV - http://odv.awi.de/) binary collection. The quality control of the data has been performed with the help of ODV software. Data Quality Flags have been revised and set up using the elaborated by SeaDataNet2 project QC procedures in conjunction with the visual expert check. The final number of the Temperature and Salinity profiles (stations) in the collection is 9091773.\n\nFor data access please register at http://www.marine-id.org/.;SeaDataNet;IFREMER / IDM/SISMER;+33 (0)2 98.22.49.16;+33 (0)2 98.22.46.44;Centre IFREMER de Brest BP 70;PLOUZANE;29280;France;sismer@ifremer.fr;http://www.ifremer.fr/sismer/;web site;IFREMER / IDM/SISMER;+33 (0)2 98.22.49.16;+33 (0)2 98.22.46.44;Centre IFREMER de Brest BP 70;PLOUZANE;29280;France;sismer@ifremer.fr;http://www.ifremer.fr/sismer/;web site;IFREMER / STATION D'ARCACHON;05 56.83.85.60;05 56.83.89.80;IFREMER Station d'Arcachon, Quai du Commandant Silhouette;Arcachon;33120;France;None;http://www.ifremer.fr/delar;web site;Aquitaine Observatory of Sciences of the Universe \u2013 University of Bordeaux (OASU);+33 (0)5 40 00 83 50;+33(0)5 57 77 56 88;O.A.S.U. B\u00e2timent B18N All\u00e9e Geoffroy Saint Hilaire CS 50023;PESSAC Cedex;33615;France;None;http://www.oasu.u-bordeaux.fr/;web site;Oceanologic Observatory of Banyuls (University of Paris VI) / OSU;+33 4 68 88 73 15;+33 4 68 88 16 99;Laboratoire Arago BP 44;BANYULS-SUR-MER;66651;France;None;http://www.obs-banyuls.fr/;web site;IFREMER / DYNECO- Coastal Environment Dynamics department;+33 (0)2 98.22.43.51;+33 (0)2 98 22 45.48;IFREMER Centre de Bretagne ZI Pointe du diable CS 10070;PLOUZANE;29280;France;None;http://www.ifremer.fr/anglais/org/del.htm;web site;CEA / INSTITUT DE RADIOPROTECTION ET DE SURETE NUCLEAIRE;+33(0)2 33.01.41.00;None;LABORATOIRE DE RADIOECOLOGIE MARINE,RUE MAX POL FOUCHET,BP 10;OCTEVILLE;50130;France;None;http://www.irsn.org/en/;web site;CNEVA / LAB. PATHOLOGIE ANIMAUX AQUATIQUES;+33(0)2 98.22.44.61;None;IFREMER Centre de Bretagne ZI Pointe du diable CS 10070;PLOUZANE;29280;France;None;None;web site;UNKNOWN;None;None;UNKNOWN;UNKNOWN;None;Unknown;None;None;web site;IFREMER;+33(0)1 46.48.21.00;+33(0)1 46.48.22.24;Technopolis 40,155 rue J.J. Rousseau;ISSY-LES-MOULINEAUX;92138;France;communication@ifremer.fr;http://wwz.ifremer.fr;web site;IFREMER / STATION DE LA TREMBLADE;+33(0)5 46.36.18.41;+33(0)5 46.36.18.47;Mus du Loup,BP 133;LA TREMBLADE;17390;France;None;http://www.ifremer.fr/latremblade/accueilen.htm;web site;IRD / CENTRE DE LA MARTINIQUE;+33 (0)596 39 77 39;+33 (0)596 50 32 61;BP 8006;FORT DE FRANCE cedex;97259;France;representant@ird-mq.fr;http://www.mq.ird.fr/;web site;IRD / CENTRE DE MONTPELLIER;+33 (0)4 67 41 61 00;+33 (0)4 67 41 63 30;BP 64501;MONTPELLIER CEDEX 5;34394;France;montpellier@ird.fr;http://www.france-sud.ird.fr/;web site;IRD / CENTRE DE PAPEETE;(689) 50 62 00;(689) 42 95 55;Chemin de l'ahari PK 3800 - Arue,BP 529;PAPEETE (Tahiti);98713;France;dirpapet@ird.pf;http://www.polynesie.ird.fr/;web site;ISTPM (IFREMER NANTES);+33(0)2 40.37.40.00;None;rue de l'Ile d'Yeu,BP 1105;NANTES CEDEX 03;44311;France;None;None;web site;University of Bordeaux I / IGBA Talence;+33(0)5 56 80 68 00;None;351, Cours de la Liberation;TALENCE CEDEX;33405;France;None;None;web site;University of Bordeaux I / Marine Biology Institut;+33(0)4 69 82 35 36;None;351, Cours de la Liberation;TALENCE CEDEX;33405;France;None;None;web site;UNIVERSITE DE PAU / LAB.CHIMIE BIO INORGANIQUE & ENVIRONNEMENT;+33(0)5 59 40 77 50;+33(0)5 59 40 77 81;2 Avenue du President ANGOT,HELIOPARC;PAU Cedex 09;64053;France;None;None;web site;IRD / CENTRE OF ABIDJAN;(225) 24 37 79;(225) 24 65 04;Rue du Chevalier de Clieu15 15 BP 917;Abidjan;15;C\u00f4te d'Ivoire;rep@ird.ci;None;web site;IRD / CENTRE OF HANN;+221 849 35 35;+221 832 43 07;Route des Peres Maristes BP 1386;DAKAR - HANN;None;Senegal;infos@ird.sn;http://www.ird.sn/centre/index.htm;web site;Ukrainian scientific center of Ecology of Sea (UkrSCES);+38 0482 636622;+380 482 636873;89 Frantsuzsky Blvd.;Odessa;65009;Ukraine;accem@te.net.ua;http://www.sea.gov.ua;web site;OGS (Istituto Nazionale di Oceanografia e di Geofisica Sperimentale), Division of Oceanography;None;None;Borgo Grotta Gigante 42/c;Sgonico (Trieste);34010;Italy;nodc@ogs.trieste.it;http://www.ogs.trieste.it/;web site;University of Plymouth, Institute of Marine Studies;None;None;Drake Circus;Plymouth;PL4 8AA;United Kingdom;inapplicable;http://www.plymouth.ac.uk/plymouth/main.htm;web site;Institute of Marine Research;+47 55 23 85 00;+47 55 23 85 31;Nordnesgaten 50 Postboks 1870 Nordnes;Bergen;N-5817;Norway;post@imr.no;http://www.imr.no;web site;ENEA Centro Ricerche Ambiente Marino - La Spezia;+39 0187 978258;+39 0187 978213;Forte S. Teresa Via S.Teresa 1;Lerici;19036;Italy;roberta.delfanti@enea.it;http://www.santateresa.enea.it;web site;Alfred-Wegener-Institute for Polar- and Marine Research;None;None;Am Handelshafen 12;Bremerhaven;D-27570;Germany;folke.mehrtens@awi.de;http://www.awi.de;web site;Isle of Man Government Laboratory;+44 (0)1624 642250;+44 (0)1624 642222;Ballakermeen Road;Douglas;IM1 4BR;United Kingdom;analyst@lab.gov.im;http://www.gov.im/dlge/enviro/govlabs/;web site;Malaga University (UMA). Applied Physics departament II;+34 952 132413/27 78;+34 952 13 24 16;Escuela Tecnica Superior de Ingenieros de Telecomunicaciones. Departamento de Fisica Aplicada II Complejo Tecnol\u00f3gico-Campus Teatinos;Malaga;29071;Spain;secteleco@uma.es;web site;Las Palmas University. Sciences of the Sea Faculty;+34 928 452900;+34 928 452922;Edificio Ciencias B\u00e1sicas CAMPUS UNIVERSITARIO DE TAFIRA Apdo. 550;Las Palmas de Gran Canaria (Islas Canarias);35017;Spain;None;http://www.fcm.ulpgc.es;web site;University of Liverpool, Port Erin Marine Laboratory;None;None;None;Port Erin;IM9 6JA;United Kingdom;inapplicable;http://www.liv.ac.uk/www/peml/;web site;IEO/ Gijon Oceanographic Centre;+34 985 30 86 72;+34 985 32 62 77;Camino de Arbeyal, s/n;Gijon (Asturias);33212;Spain;ieogijon@gi.ieo.es;http://www.ieo.es/CoGijon/index.htm;web site;IEO/ Santander Oceanographic Centre;+34 942 291060;+34 942 275072;Promontorio San Martin, s/n Apdo. 240;Santander;39004;Spain;ieosantander@st.ieo.es;http://www.ieo-santander.net/;web site;IEO/ La Coruna Oceanographic Centre;+34 981 205362;+34 981 229077;Muelle de las Animas, s/n Apdo.130;A Coruna;15001;Spain;ieo.coruna@co.ieo.es;http://www.ieo.es;web site;IEO/ Vigo Oeanographic Centre;+34 986 492 111;+34 986 498 626;Cabo Estay \u2013 Canido;Vigo;36200;Spain;ieo.vigo@vi.ieo.es;http://www.vi.ieo.es/;web site;IEO/ Malaga Oceanographic Centre;+34 952 476 955;+34 952 463 808;Puerto Pesquero, s/n Apdo. 285;Fuengirola (Malaga);29640;Spain;ieomalaga@ma.ieo.es;http://www.ieo.es;web site;IEO/ Cadiz Oceanographic Centre;+34 956 294 189;+34 956 263 556;Muelle de Levante (Puerto Pesquero) Apdo. 2609;Puerto Real (Cadiz);11106;Spain;ignacio.sobrino@cd.ieo.es;http://www.ieo.es;web site;IFREMER / STATION DE LORIENT;+33 (0)2 97 87 38 00;+33 (0)2 97 87 38 01;8 rue Fran\u00e7ois Toullec;LORIENT;56100;France;secretariat@ifremer.fr;http://www.ifremer.fr/sth/station_lorient.htm;web site;National Oceanography Centre, Southampton;None;None;University of Southampton Waterfront Campus European Way;Southampton;SO14 3ZH;United Kingdom;enquiries@noc.ac.uk;http://noc.ac.uk;web site;University of Rostock, Institute of Biosciences;+49 (0)381 498 6041;+49 (0)381 498 6042;Wismarsche Strasse 8;Rostock;18057;Germany;institut.biowissenschaften@uni-rostock.de;http://www.bio.uni-rostock.de;web site;University of Liverpool Department of Oceanography;None;None;Brownlow Hill;Liverpool;None;United Kingdom;inapplicable;None;web site;University of Southampton School of Ocean and Earth Science;+44 (0)23 8059 2011;+44 (0)23 8059 3059;National Oceanography Centre, European Way;Southampton;SO14 3ZH;United Kingdom;soes@noc.soton.ac.uk;http://www.soes.soton.ac.uk/;web site;University of Southampton School of Ocean and Earth Science;None;None;Southampton Oceanography Centre, European Way;Southampton;SO14 3ZH;United Kingdom;inapplicable;None;web site;University of Southampton Department of Oceanography;None;None;University of Southampton Waterfront Campus, European Way;Southampton;SO14 3ZH;United Kingdom;inapplicable;None;web site;University of Southampton Department of Oceanography;None;None;Highfield Campus;Southampton;SO9 5NH;United Kingdom;inapplicable;None;web site;German Hydrographic Institute;494031903420;494031905000;Bernhard-Nocht-Str. 78;Hamburg;20359;Germany;friedrich.nast;http://www.bsh.de/en/Marine_data/Hydrographic_surveys_and_wreck_search/Hydrographic_surveys/e_geschichte_sv.jsp;web site;Federal Maritime and Hydrographic Agency;+49 40 3190 0;+49 40 3190 5000;Bernhard-Nocht-Str. 78;Hamburg;20359;Germany;webmaster@bsh.de;http://www.bsh.de;web site;Universite de la Rochelle / Litoral Environnement et Societe (LIENSS) - UMR 7266;05.46.45.72.61;None;Av, Michel Cr\u00e9peau LAB. DE BIOLOGIE ET ENVIRONNEMENT MARIN - LBEM;LA ROCHELLE;17042;France;None;http://www.univ-lr.fr/labo/lbem/;web site;LABO ATMOSPHEREs, MILIEUX, OBSERVATIONS SPATIALES (LATMOS);+33 (0)1 39 25 49 06;+33 (0)1 39 25 49 22;Centre Universitaire de V\u00e9lizy 10-12 Avenue de l'Europe;VELIZY;78140;France;direction@latmos.ipsl.fr;http://www.latmos.ipsl.fr/;web site;Ifremer / Crela;+33(0)5 46.50.94.40;+33(0)5 46.50.06.60;Centre de Recherche sur Ecosyst\u00e8mes Littoraux Anthropis\u00e9s Place du S\u00e9minaire BP 7;L'HOUMEAU;17137;France;None;None;web site;University of Bordeaux I / Laboratory for Physical and Toxico Chemistry (ISM);None;None;LPTC - ESA 5472 CNRS Universite Bordeaux 1l'\u00e9tu 351 Cours de la Lib\u00e9ration;TALENCE CEDEX;33405;France;None;http://www.ism.u-bordeaux1.fr/-Physico-et-Toxicochimie-de-l-.html;web site;Universite D'Angers / Laboratoire Des Bio-Indicateurs Actuels Et Fossiles (Biaf);02.41.73.53.91;02.41.73.53.52;UFR Sciences - UPRES EA 2644 2, Bd Lavoisier;ANGERS cedex 01;49045;France;frans.jorissen@univ-angers.fr;None;web site;Universite de Pau / IPREM multidisciplinary research institute for the environment and materials;05 59 40 77 51;05 59 40 77 81;IPREM UMR 5254 H\u00e9lioparc Pau Pyr\u00e9n\u00e9es 2, av. Pierre Angot;PAU CEDEX 9;64053;France;olivier.donard@univ-pau.fr;http://www.iprem.org/;web site;University of Cambridge Department of Earth Sciences;None;None;Downing Street;Cambridge;CB2 3EQ;United Kingdom;jaj2@cam.ac.uk;http://www.esc.cam.ac.uk;web site;University of Wales, School of Ocean Sciences;None;None;School of Ocean Sciences, University of Wales Bangor, Menai Bridge, Anglesey,;Menai Bridge;LL59 5AB;United Kingdom;inapplicable;http://www.sos.bangor.ac.uk/;web site;Southampton Oceanography Centre;None;None;University of Southampton Waterfront Campus European Way;Southampton;SO14 3ZH;United Kingdom;inapplicable;None;web site;Scottish Office Agriculture Environment and Fisheries Department - Aberdeen Marine Laboratory;None;None;PO Box 101 375 Victoria Road;Aberdeen;AB11 9DB;United Kingdom;inapplicable;None;web site;Scottish Office Agriculture and Fisheries Department - Aberdeen Marine Laboratory;None;None;PO Box 101 375 Victoria Road;Aberdeen;AB11 9DB;United Kingdom;inapplicable;None;web site;Department of Agriculture and Fisheries for Scotland - Aberdeen Marine Laboratory;None;None;PO Box 101 375 Victoria Road;Aberdeen;AB11 9DB;United Kingdom;inapplicable;None;web site;Ministry of Agriculture, Fisheries and Food, Lowestoft Fisheries Laboratory;None;None;Pakefield Road;Lowestoft;NR33 0HT;United Kingdom;inapplicable;None;web site;Institute of Oceanographic Sciences Deacon Laboratory;None;None;Brook Road Wormley;Godalming;GU8 5UB;United Kingdom;inapplicable;None;web site;Institute of Oceanographic Sciences Wormley Laboratory;None;None;Brook Road Wormley;Godalming;GU8 5UB;United Kingdom;inapplicable;None;web site;Proudman Oceanographic Laboratory;+44 (0)151 653 8633;+44 (0)151 653 6269;Bidston Observatory Bidston Hill;Prenton;CH43 7RA;United Kingdom;inapplicable;http://www.pol.ac.uk;web site;Institute of Oceanographic Sciences, Bidston Laboratory;None;None;Bidston Observatory Bidston Hill;Prenton;L43 7RA;United Kingdom;inapplicable;None;web site;Marine Scotland Science;+44 (0)1224 876544;+44 (0)1224 295511;Marine Laboratory, PO Box 101;Aberdeen;AB11 9DB;United Kingdom;inapplicable;None;web site;Defence Evaluation Research Agency;None;None;Winfrith Technology Centre;Winfrith;DT2 8XJ;United Kingdom;inapplicable;http://www.dera.gov.uk/newsite/home_2.htm;web site;National Oceanography Centre, Liverpool;+44 (0)151 795 4800;+44 (0)151 795 4801;Joseph Proudman Building, 6 Brownlow Street;Liverpool;L3 5DA;United Kingdom;enquiries@noc.ac.uk;http://noc.ac.uk;web site;UTM-CSIC/Marine Technology Unit;+34 932 309500;+34 932 309555;Paseo Maritimo de la Barceloneta, 37-49;Barcelona;08003;Spain;info@utm.csic.es;http://www.utm.csic.es/;web site;Dunstaffnage Marine Laboratory;None;None;Dunbeg;Oban;PA37 1QA;United Kingdom;inapplicable;None;web site;Scottish Marine Biological Association;None;None;Dunbeg;Oban;PA37 1QA;United Kingdom;inapplicable;None;web site;Institute of Marine Research (IIM-CSIC);+34 986231930;+34 986292762;Eduardo Cabello, 6;Vigo (Pontevedra);36208;Spain;webmaster@iim.csic.es;http://www.iim.csic.es;web site;Centre for Environment, Fisheries and Aquaculture Science, Lowestoft Laboratory;+44 (0)1502 562244;+44 (0)1502 513865;Pakefield Road;Lowestoft;NR33 OHT;United Kingdom;sarah.turner@cefas.co.uk;http://www.cefas.co.uk/;web site;GEOMAR Helmholtz Centre for Ocean Research Kiel;+49 431 600-0;+49 431 600-2805;D\u00fcsternbrooker Weg 20;Kiel;24105;Germany;info@geomar.de;http://www.geomar.de/en/;web site;IEO/ Oceanographic Centre of Canary Island;+34 922 549400;+34 922 549554;Carretera San Andr\u00e9s Km 7 Apdo. 1373;S. C. Tenerife;38180;Spain;coc@ca.ieo.es;http://www.ieo.es;web site;Canary Institute of Marine Sciences;+34 928 132900;+34 928 132908;Carretera de Taliarte, s/n.;Telde (Las Palmas de Gran Canaria);35200;Spain;None;http://www.iccm.rcanaria.es;web site;IEO/Spanish Oceanographic Institute;+34 915 107513;+34 914 135597;Corazon de Maria, 8;MADRID;28002;Spain;cedo@ieo.es;http://www.ieo.es;web site;Fisheries Research Services, Aberdeen Marine Laboratory;+44 (0)1224 876544;+44 (0)1224 295511;PO Box 101 Victoria Road;Aberdeen;AB11 9DB;United Kingdom;inapplicable;http://www.marlab.ac.uk;web site;Marine Institute;+353-91-387200;+353-91-387201;Rinville;Oranmore;H91 R673;Ireland;datarequests@marine.ie;http://www.marine.ie;web site;British Oceanographic Data Centre;None;None;Joseph Proudman Building 6 Brownlow Street;Liverpool;L3 5DA;United Kingdom;enquiries@bodc.ac.uk;http://www.bodc.ac.uk/;web site;Scottish Association for Marine Science;None;None;None;Argyll;PA37 1QA;United Kingdom;laurence.mee@sams.ac.uk;http://www.sams.ac.uk;web site;IRD /CENTRE DE BRETAGNE;+33 (0)2 98.22.45.01;+33(0)2 98.22.45.14;IFREMER Centre de Bretagne ZI Pointe du diable CS 10070;PLOUZANE;29280;France;None;http://www.brest.ird.fr/;web site;IFREMER / DYNECO/PELAGOS-LABORATOIRE D'ECOLOGIE PELAGIQUE;+33(0)2 98 22 43 34;+33(0)2 98 22 45 98;IFREMER Centre de Brest BP70;PLOUZANE;29280;France;None;http://www.ifremer.fr/delec/;web site;Marine Biological Association of the United Kingdom;None;None;Citadel Hill;Plymouth;PL1 2PB;United Kingdom;sec@mba.ac.uk;http://www.mba.ac.uk/;web site;Plymouth Marine Laboratory;+44 (0)1752 633 100;+44 (0)1752 633101;Prospect Place The Hoe;Plymouth;PL1 3DH;United Kingdom;forinfo@pml.ac.uk;http://www.pml.ac.uk;web site;Proudman Oceanographic Laboratory;None;None;Joseph Proudman Building 6 Brownlow Street;Liverpool;L3 5DA;United Kingdom;inapplicable;http://www.pol.ac.uk;web site;IFREMER / EEP / LEP-DEEP ENVIRONMENT LABORATORY;+33 (0)2 98.22.43.04;+33 (0)2 98.22.47.57;IFREMER Centre de Bretagne ZI Pointe du diable CS 10070;PLOUZANE;29280;France;None;http://www.ifremer.fr/droep/index.html;web site;IFREMER / GM-MARINE GEOSCIENCES;+33(0)2 98.22.42.70;+33(0)2 98.22.45.70;IFREMER Centre de Bretagne ZI Pointe du diable CS 10070;PLOUZANE;29280;France;geosciences.marines@ifremer.fr;http://www.ifremer.fr/drogm/;web site;LABORATORY of PHYSICAL OCEANOGRAPHY (LPO) UMR 6523 CNRS-IFREMER-IRD-UBO;+33 (0)2 98.22.42.76;+33(0)2 98.22.44.96;IFREMER Centre de Bretagne ZI Pointe du diable CS 10070;PLOUZANE;29280;France;None;http://www.ifremer.fr/lpo/;web site;LABORATORY OF OCEANOGRAPHY of VILLEFRANCHE (LOV) / OOV;+33 (0)4 93 76 38 13;+33 (0)4.93.76.38.34;UPMC/UMR 7093 181, chemin du Lazaret;Villefranche-sur-Mer;06230;France;lov@obs-vlfr.fr;http://www.obs-vlfr.fr;web site;Laboratory of Oceanography and Climate : Experiments and numerical Approaches - UMR 7159;+33 (1) 44 27 32 48;+33(0)1 44 27 38 05;UMR 7159 CNRS / IRD / Universit\u00e9 Pierre et Marie Curie/MNHN Institut Pierre Simon Laplace - Bo\u00eete 100 4 Place Jussieu;Paris;75252;France;nelly.lecquyer@locean-ipsl.upmc.fr;http://www.locean-ipsl.upmc.fr/;web site;MUSEUM NATIONAL D'HISTOIRE NATURELLE / LABORATOIRE D'OCEANOGRAPHIE PHYSIQUE;+33 (0)1 40.79.31 58;+33 (0)1 40 79 31 63;43-45 rue Cuvier;PARIS CEDEX 05;75231;France;None;http://www.mnhn.fr;web site;IFREMER / DYNECO / PHYSED -LABO PHYSIQUE HYDRODYNAMIQUE ET SEDIMENTAIRE;33 (0)2 98 22 47 60;33 (0)2 98 22 45 55;IFREMER Centre de Bretagne ZI Pointe du diable CS 10070;PLOUZANE;29280;France;None;http://wwz.ifremer.fr/dyneco/Equipes/Physed;web site;COM - Physical and Biogeochemical Oceanography Laboratory (LUMINY);+33(0)4 91 82 91 15;+33(0)4 91.82.65.48;UFR Centre Oceanologique de Marseille UMR 6535 Campus de Luminy Case 901;Marseille cedex 9;13288;France;queguiner@com.univ-mrs.fr;http://www.com.univ-mrs.fr/LOB/;web site;IFREMER STATION DE LA ROCHELLE-L'HOUMEAU;+33 (0)5 46.50.94.40;+33 (0)5 46.50.06.50;Place du Seminaire, BP 7;L'HOUMEAU;17137;France;None;http://w3.ifremer.fr/francais/implant/larochel.htm;web site;Institute of Earth Physics of Paris;+33 (0)1 83 95 74 00;+33 (0)1 83 95 77 14;1, place Jussieu;PARIS CEDEX 5;75252;France;None;http://www.ipgp.jussieu.fr/;web site;IRD CENTRE DE NOUMEA;+33 (0)1 44 27 34 67;+33 (0)1 44 27 24 01;BP A5;NOUMEA CEDEX5;98848;New Caledonia;nouvelle-caledonie@ird.fr;http://www.ird.nc/;web site;Roscoff Marine Station, Sorbonne Universit\u00e9s, UPMC Univ Paris 06 and CNRS;+33(0)2 98.29.23.23;+33 (0)2 98.29.23.24;Place Georges Teissier;ROSCOFF;29680;France;None;http://www.sb-roscoff.fr/;web site;IFREMER / RBE Department / Biogeochimical end Ecotoxicological Resarch Unit (Nantes);+33 (0)2 40 37 41 93;33(0)2 40.37.40.75;IFREMER Centre de Nantes Rue de l'Ile d'Yeu BP 1105;NANTES CEDEX 03;44311;France;None;http://www.ifremer.fr/delpc/;web site;CNRS / Microbiology, Geochemistry and Marine Ecology Laboratory;+33 (0)4 91 82 92 12;+33 (0)4 91 82 96 41;Centre d'Oc\u00e9anologie de Marseille (COM) UMR 6117 Campus de Luminy, Case 901;MARSEILLE CEDEX 9;13288;France;micromar@com.univ-mrs.fr;http://www.com.univ-mrs.fr/LMGEM/spip.php?rubrique1;web site;IFREMER / STATION DE LA TRINITE;+33 (0)2 97 30 19 19;+33 (0)2 97 30 19 00;12, rue des Resistants BP 86;LA TRINITE-SUR-MER;56470;France;None;http://www.ifremer.fr/anglais/implant/latrinit.htm;web site;IFREMER / STH/LBH-LABORATOIRE BIOLOGIE HALIEUTIQUE;+33 (0)2.97.87.38.00;+33 (0)2.97.87.38.01;IFREMER Station de Lorient 8, rue Francois Toullec;LORIENT;56100;France;mlegall@ifremer.fr;http://wwz.ifremer.fr/lorient;web site;Shom;+33 (0)2 56.31.23.12;+33 (0)2 56.31.25.80;13, rue du Chatellier CS92803;BREST CEDEX 2;29228;France;seadatanet-admin@shom.fr;http://www.shom.fr/;web site;IFREMER / EMH-DEPARTEMENT ECOLOGIE ET MODELES POUR L'HALIEUTIQUE;+33(0)2 40.37.41. 67;+33(0)2 40.37.40.75;IFREMER - Centre de Nantes rue de l'Ile d'Yeu BP 21105;NANTES CEDEX 03;44311;France;None;http://www.ifremer.fr/drvecohal;web site;IFREMER / HMMN-DEPARTEMENT HALIEUTIQUE DE MANCHE-MER DU NORD;+33 (0)3 21.99.56.00;+33 (0)3 21.99.56.01;IFREMER Centre de Boulogne sur Mer 150 quai Gambetta BP 70;BOULOGNE-SUR-MER CEDEX;62321;France;None;http://www.ifremer.fr/boulogne/;web site;Swedish Meteorological and Hydrological Institute;+46-(0)11-495 80 00;+46-(0)11-495 80 01;Folkborgsvagen 1;Norrkoping;SE-601 76;Sweden;shark@smhi.se;http://www.smhi.se;web site;CEA / Laboratory of climatolocical and environmental Sciences(LSCE);+33(0)1 69.82 35 23;+33(0)1 69.82.35.68;CNRS LSCE-Vallee, Bat.12, Avenue de la Terrasse;GIF-SUR-YVETTE CEDEX;91198;France;None;http://www.lsce.cnrs-gif.fr/;web site;UNIVERSITE DE BRETAGNE OCCIDENTALE (UBO) / LAB. D'OCEANO. CHIMIQUE LOC - IUEM;None;None;Place Nicolas Copernic;Plouzane;29280;France;None;None;web site;CEREGE;+33(0)4 42 97 15 00;+33 (0)4 42 97 15 05;Europole Mediterraneen de l'Arbois BP 80;Aix en Provence;13545;France;None;http://www.cerege.fr/;web site;Marine Research Institute;+354 575 2000;+354 575 2001;Skulagata 4 P.O.Box 1390;Reykjavik;IS-121;Iceland;hafro@hafro.is;http://www.hafro.is/index_eng.php;web site;IHPT, Hydrographic Institute;+351 210943000;+351 210943299;Rua das Trinas, 49;Lisboa;1249-093;Portugal;mail@hidrografico.pt;http://www.hidrografico.pt;web site;University of East Anglia, School of Environmental Sciences;None;None;University Plain;Norwich;NR4 7TJ;United Kingdom;env.enquiries@uea.ac.uk;http://www.uea.ac.uk/env/;web site;NIOZ Royal Netherlands Institute for Sea Research;+31 222 369300;+31 222 319674;Landsdiep 4 P.O. Box 59;Den Burg/Texel;1790 AB;Netherlands;dmg@nioz.nl;https://www.nioz.nl;web site;Atlantic Scientific Research Institute for Marine Fishery and Oceanography;8 (0112) 21-56-45;8 (0112) 21-99-97;5, Dm. Donskoi St.;Kaliningrad reg;236000;Russian Federation;atlant@baltnet.ru;http://www.atlantniro.ru/;web site;P.P.Shirshov Institute of Oceanology, RAS;+7(499)124-59-96;+7(499)124-59-83;36 Nakhimovsky prospect;Moscow;117997;Russian Federation;office@ocean.ru;http://www.ocean.ru;web site;IFREMER / STATION DE SETE;+33(0)4 99 57 32 00;+33 (0)4 99 57 32 94;Bd Jean Monnet BP 171;SETE CEDEX;34203;France;None;http://wwz.ifremer.fr/mediterranee/implantations/Sete;web site;Marine Hydrophysical Institute;+380 692 54 02 52;+380 692 55 42 53;2, Kapitanskaya str.;Sevastopol;99011;Ukraine;khaliulin.alexey@nodc.org.ua;http://WWW.MHI.IUF.NET;web site;Far Eastern Regional Hydrometeorological Research Institute;+7 (4232) 26-97-88;+7 (4232) 22-77-54;Fontannaya St., 24;Vladivostok;690600;Russian Federation;hydromet@online.ru;http://www.hydromet.com;web site;IFREMER / STH-DEPARTEMENT SCIENCES ET TECHNOLOGIES HALIEUTIQUES;+33 (0)2 98.22.43.66;+33 (0)2 98 22 45.47;IFREMER Centre de Bretagne ZI Pointe du diable CS 10070;PLOUZANE;29280;France;None;http://www.ifremer.fr/anglais/org/drv.htm;web site;IFREMER / Dpt Technologicals Research and Development;+33(0) 2 98 22 41 41;+33(0) 2 98 22 45 35;IFREMER Centre de Bretagne ZI Pointe du diable CS 10070;PLOUZANE;29280;France;Pierre.Chauchot@ifremer.fr;http://wwz.ifremer.fr/rd_technologiques;web site;IRD ANTENNE INSTITUT OCEANOGRAPHIQUE (IRD);+33 (0)1 44.32.10.70;+33 (0)1 40.51.73.16;INSTITUT OCEANOGRAPHIQUE 195 Rue Saint Jacques;PARIS;75005;France;None;None;web site;Laboratory of Physical Oceanography/ UNIVERSITE DE BRETAGNE OCCIDENTALE (UBO);+33 (0)2 98.01.61.21;+33 (0)2 98 01 64 68;6 avenue Victor-Le-Gorgeu BP 809;BREST CEDEX;29285;France;None;http://www.univ-brest.fr/lpo/site/;web site;EPOC - Geology and Oceanography Department;+33 (0)5 40.00.88.67;+33 (0)5 56.84.08.48;351, Cours de la Liberation Avenue des Facultes;TALENCE;33405;France;inapplicable;http://www.epoc.u-bordeaux.fr;web site;IFREMER / CENTRE DE BRETAGNE;+33 (0)2 98.22.40.40;+33 (0)2 98.22.45.45;ZI Pointe du diable CS 10070;PLOUZANE;29280;France;None;http://www.ifremer.fr/brest/;web site;Polar Scientific Research Institute of Fishery and Oceanography;None;None;6, Knipovich St.;Murmansk;183763;Russian Federation;persey@pinro.ru;http://www.pinro.ru/;web site;Odessa Branch of SOI (State Oceanographic Institute);None;None;None;Odessa;None;Ukraine;None;None;web site;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=970bb3ba-aaf6-4066-9656-87c85da41dbb&fname=Map_Final_NAT_WITHOUTONLAND.png;Oceanographic geographical features;GEMET - INSPIRE themes, version 1.0;2018-07-27;geonetwork.thesaurus.external.theme.httpinspireeceuropaeutheme-theme;Temperature of the water column;Salinity of the water column;Parameter Discovery Vocabulary (P02);2017-11-17;geonetwork.thesaurus.external.parameter.NVS.P02;Water body salinity;ITS-90 water temperature;EMODNET chemistry lot aggregated parameter names;2016-09-20;geonetwork.thesaurus.external.parameter.NVS.P35;Atlantic Ocean;SeaVoX salt and fresh water body gazetteer;2016-09-20;geonetwork.thesaurus.external.reference-geographical-area.NVS.C19;Th\u00e8mes Sextant;2018-05-24;geonetwork.thesaurus.local.theme.sextant-theme;SeaDataNet licence;SeaDataNet Usage Agreement: If you use SeaDataNet data in your publications please include the following in the Acknowledgements: Data were provided through SeaDataNet Pan-European infrastructure for ocean and marine data management (https://www.seadatanet.org);No limitations on public access.  For data access please register at http://www.marine-id.org;oceans;bounding box;-90;10;10;62;1900-01-01;2017-11-01;-5500.0;0.0;ODV binary collection;5;http://dx.doi.org/10.12770/970bb3ba-aaf6-4066-9656-87c85da41dbb;WWW:LINK-1.0-http--metadata-URL;DOI of the product;ftp://vftp2.ifremer.fr/public/seadatanet-north_atlantic_ocean-temperaturesalinity_aggregated/SDC_NAT_DATA_TS_V1/;WWW:DOWNLOAD-1.0-link--download;full collection dataset;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;See the referenced specification;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "390e5b25-ee73-5b8a-bc37-7f339bb8221d",
-    "notes": [
-        "The SeaDataCloud TS historical data collection v1 for the North Atlantic Ocean, includes open access in situ data on temperature and salinity of water column in the North Atlantic Ocean from 10\u00b0N  to 62\u00b0N, including the Labrador Sea, The data were retrieved from the SeaDataNet infrastructure at the end of November 2017. The dataset format is Ocean Data View (ODV - http://odv.awi.de/) binary collection. The quality control of the data has been performed with the help of ODV software. Data Quality Flags have been revised and set up using the elaborated by SeaDataNet2 project QC procedures in conjunction with the visual expert check. The final number of the Temperature and Salinity profiles (stations) in the collection is 9091773.\n\nFor data access please register at http://www.marine-id.org/."
-    ],
-    "oai_identifier": [
-        "390e5b25-ee73-5b8a-bc37-7f339bb8221d"
-    ],
-    "oai_set": "cams1_ps",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-90,10],[-90,62],[10,62],[10,10],[-90,10]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Atlantic Ocean"
-        }
-    ],
-    "title": [
-        "North Atlantic Ocean - Temperature and Salinity Historical Data Collection SeaDataCloud V1"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/47a5fc9c-f244-59d5-83a8-87d938b2074c.json b/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/47a5fc9c-f244-59d5-83a8-87d938b2074c.json
deleted file mode 100644
index f93257c7..00000000
--- a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/47a5fc9c-f244-59d5-83a8-87d938b2074c.json
+++ /dev/null
@@ -1,103 +0,0 @@
-{
-    "Contact": [
-        "sdn-userdesk@seadatanet.org"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=iso19139&identifier=47a5fc9c-f244-59d5-83a8-87d938b2074c",
-    "PublicationTimestamp": "2015-10-12T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Marine Systems Institute at Tallinn University of Technology",
-        "Alfred-Wegener-Institute for Polar- and Marine Research",
-        "SEADATANET",
-        "GEOMAR Helmholtz Centre for Ocean Research Kiel",
-        "IFREMER / IDM / SISMER - Scientific Information Systems for the SEA",
-        "Institute of Meteorology and Water Management National Research Institute, Maritime Branch in Gdynia (IMWM MB)",
-        "Russian State Hydrometeorological University, St-Petersburg",
-        "NIOZ Royal Netherlands Institute for Sea Research",
-        "Odessa Branch of SOI (State Oceanographic Institute)",
-        "Department of Marine Research of the Environmental Protection Agency",
-        "Aarhus University, Department of Bioscience, Marine Ecology Roskilde",
-        "Swedish Meteorological and Hydrological Institute",
-        "National Oceanography Centre, Liverpool",
-        "Institute of Marine Research",
-        "Finnish Institute of Marine Research (FIMR)",
-        "P.P.Shirshov Institute of Oceanology, RAS",
-        "Institute of Oceanology, Polish Academy of Sciences (IO PAS)",
-        "Umea Marine Sciences Centre, UMF",
-        "Shom",
-        "Environmental Protection Agency (EPA)",
-        "Stockholm Marine Research Centre, SMF"
-    ],
-    "ResourceType": "dataset",
-    "Rights": [
-        "No limitations on public access.  For data access please register at http://www.marine-id.org"
-    ],
-    "SpatialCoverage": "(53N-66N,9 E-31E)",
-    "TempCoverageBegin": 59926651199,
-    "TempCoverageEnd": 63492551999,
-    "TemporalCoverage": " period : ( 1900-01-01T11:59:59Z - 2012-12-31T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1900-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2012-12-31T11:59:59Z",
-    "fulltext": "bf35a7c5-c843-4a23-8040-07ddcf3d8e71;SEADATANET;sdn-userdesk@seadatanet.org;http://www.seadatanet.org/;2018-07-24T09:47:26;ISO 19115:2003/19139 - EMODNET - SDN;1.0;4;21;1;false;WGS 84 (EPSG 4326);EPSG;Baltic Sea - Temperature and Salinity Climatology V1.1;2015-10-12;1.1;2015-11-30;bf35a7c5-c843-4a23-8040-07ddcf3d8e71;Seadatanet temperature and salinity monthly climatologies 1900-2012 by DIVA software v4.6.10. Based on Seadatanet historical dataset v1.1.\n\nFor data access please register at http://www.marine-id.org \n\nDIVA settings:\nSeasonal background fields, months 12-02, 03-05, 06-08, 09-11.\nWeighting have been used with length of weighting 0.5\u00b0 and time of weighting 2 days.;SeaDataNet;Swedish Meteorological and Hydrological Institute;+46-(0)11-495 80 00;+46-(0)11-495 80 01;Folkborgsvagen 1;Norrkoping;SE-601 76;Sweden;shark@smhi.se;http://www.smhi.se;web site;IFREMER / IDM / SISMER - Scientific Information Systems for the SEA;+33 (0)2 98.22.49.16;+33 (0)2 98.22.46.44;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;sismer@ifremer.fr;http://www.ifremer.fr/sismer/;web site;Institute of Marine Research;+47 55 23 85 00;+47 55 23 85 31;Nordnesgaten 50\nPostboks 1870 Nordnes;Bergen;N-5817;Norway;post@imr.no;http://www.imr.no;web site;Alfred-Wegener-Institute for Polar- and Marine Research;None;None;Am Handelshafen 12;Bremerhaven;D-27570;Germany;folke.mehrtens@awi.de;http://www.awi.de;web site;Institute of Meteorology and Water Management National Research Institute, Maritime Branch in Gdynia (IMWM MB);+48-58-62-88-100;+48-58-62-88-163;Waszyngtona 42;Gdynia;81-342;Poland;None;http://www.baltyk.pogodynka.pl/;web site;Institute of Oceanology, Polish Academy of Sciences (IO PAS);+48 58 551 72 81;+48 58 551 21 30;Powstancow Warszawy 55;Sopot;81-712;Poland;smas@iopan.gda.pl;http://www.iopan.gda.pl/;web site;Environmental Protection Agency (EPA);None;None;Juozapaviciaus st. 9;Vilnius;LT-09311;Lithuania;aaa@aaa.am.lt;http://www.gamta.lt;web site;National Oceanography Centre, Liverpool;+44 (0)151 795 4800;+44 (0)151 795 4801;Joseph Proudman Building, 6 Brownlow Street;Liverpool;L3 5DA;United Kingdom;enquiries@noc.ac.uk;http://noc.ac.uk;web site;GEOMAR Helmholtz Centre for Ocean Research Kiel;+49 431 600-0;+49 431 600-2805;D\u00fcsternbrooker Weg 20;Kiel;24105;Germany;info@geomar.de;http://www.geomar.de/en/;web site;Shom;+33 (0)2 56.31.23.12;+33 (0)2 56.31.25.80;13, rue du Chatellier\nCS92803;BREST CEDEX 2;29228;France;seadatanet-admin@shom.fr;http://www.shom.fr/;web site;Swedish Meteorological and Hydrological Institute;+46-(0)11-495 80 00;+46-(0)11-495 80 01;Folkborgsvagen 1;Norrkoping;SE-601 76;Sweden;shark@smhi.se;http://www.smhi.se;web site;Stockholm Marine Research Centre, SMF;+46 (0)8-16 37 18;None;Svante Arrhenius V\u00e4g 21B\nFrescati Backe;Stockholm;SE-114 18;Sweden;smf@smf.su.se;http://www.smf.su.se;web site;Umea Marine Sciences Centre, UMF;+46 (0)90-786 79 74;+46 (0)90-786 99 75;Norrbyn;H\u00f6rnefors;SE-910 20;Sweden;info@umf.umu.se;http://www.umf.umu.se/;web site;Finnish Institute of Marine Research (FIMR);+358 9 613 941;+358 9 323 2970;Erik Palm\u00e9nin aukio 1\nP.O.Box 2;Helsinki;00561;Finland;None;http://www.fimr.fi/en/en_GB/en/;web site;NIOZ Royal Netherlands Institute for Sea Research;+31 222 369300;+31 222 319674;Landsdiep 4\nP.O. Box 59;Den Burg/Texel;1790 AB;Netherlands;dmg@nioz.nl;https://www.nioz.nl;web site;Department of Marine Research of the Environmental Protection Agency;+370 46 41 04 50;+370 46 41 04 60;Taikos Av. 26;Klaipeda;LT-91149;Lithuania;jtd@aaa.am.lt;http://www.gamta.lt/;web site;P.P.Shirshov Institute of Oceanology, RAS;+7(499)124-59-96;+7(499)124-59-83;36 Nakhimovsky prospect;Moscow;117997;Russian Federation;office@ocean.ru;http://www.ocean.ru;web site;Marine Systems Institute at Tallinn University of Technology;+372 6204300;None;MSI, Akadeemia tee 15a;Tallinn;12618;Estonia;msi@msi.ttu.ee;http://www.msi.ttu.ee;web site;Aarhus University, Department of Bioscience, Marine Ecology Roskilde;+45 8715000;+45 87154326;399 Frederiksborgvej\nP.O. Box 358;Roskilde;DK-4000;Denmark;None;http://bios.au.dk/en/;web site;Russian State Hydrometeorological University, St-Petersburg;None;None;98, Maloohtinsky Pr.;St.-Petersburg;195196;Russian Federation;rector@rshu.ru;http://www.rshi.nw.ru/win/home-ru.htm;web site;Odessa Branch of SOI (State Oceanographic Institute);None;None;None;Odessa;None;Ukraine;None;None;web site;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=bf35a7c5-c843-4a23-8040-07ddcf3d8e71&fname=baltic_clim.png;Oceanographic geographical features;GEMET - INSPIRE themes, version 1.0;2009-09-22T07:57:15;Temperature of the water column;Salinity of the water column;Parameter Discovery Vocabulary (P02);2014-12-11;geonetwork.thesaurus.external.parameter.NVS.P02;ITS-90 water temperature;Water body salinity;EMODNET chemistry lot aggregated parameter names;2014-12-11;geonetwork.thesaurus.external.parameter.NVS.P35;Baltic Sea;Central Baltic Sea;Bay of Bothnia;Bothnian Sea;Gulf of Finland;Gulf of Bothnia;Lillebaelt;Kattegat;Skagerrak;Storebaelt;SeaVoX salt and fresh water body gazetteer;2014-12-11;geonetwork.thesaurus.external.reference-geographical-area.NVS.C19;Th\u00e8mes Sextant;2017-01-23;geonetwork.thesaurus.local.theme.sextant-theme;SeaDataNet licence;SeaDataNet Usage Agreement: If you use SeaDataNet data in your publications please include the following in the Acknowledgements: Data were provided through SeaDataNet Pan-European infrastructure for ocean and marine data management (https://www.seadatanet.org);No limitations on public access.  For data access please register at http://www.marine-id.org;12.2;oceans;bounding box;9;31;53;66;1900-01-01;2012-12-31;0.0;300.0;http://dx.doi.org/10.12770/bf35a7c5-c843-4a23-8040-07ddcf3d8e71;WWW:LINK-1.0-http--metadata-URL;DOI of the product;http://gher-diva.phys.ulg.ac.be:8080/SeaDataNet-domains/Baltic/Salinity.19002012.4Danl.nc.html;WWW:DOWNLOAD-1.0-link--download;opendap sea watyer salinity;opendap access, sea water salinity;http://gher-diva.phys.ulg.ac.be:8080/SeaDataNet-domains/Baltic/Temperature.19002012.4Danl.nc.html;WWW:DOWNLOAD-1.0-link--download;opendap sea water temperature;opendap access, sea water temperature;ftp://ftp2.ifremer.fr/public/seadatanet-baltic_sea-temperaturesalinity_climatologie/SDN_2015-11_TS_Baltic_Sea_Climatology_v1.1.zip;WWW:DOWNLOAD-1.0-link--download;full dataset, netcdf format;full dataset, netcdf format;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0;OGC:WMS:getCapabilities;sea water salinity;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0;OGC:WMS;Baltic/Salinity.19002012.4Danl.nc*Salinity_L1;Salinity masked using relative error threshold 0.3;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0;OGC:WMS;Baltic/Salinity.19002012.4Danl.nc*Salinity_L2;Salinity masked using relative error threshold 0.5;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0;OGC:WMS:getCapabilities;sea water temperature;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0;OGC:WMS;Baltic/Temperature.19002012.4Danl.nc*Temperature_L1;Temperature masked using relative error threshold 0.3;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0;OGC:WMS;Baltic/Temperature.19002012.4Danl.nc*Temperature_L2;Temperature masked using relative error threshold 0.5;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;See the referenced specification;The data used as input for this product have been extracted from the SeaDataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "47a5fc9c-f244-59d5-83a8-87d938b2074c",
-    "notes": [
-        "Seadatanet temperature and salinity monthly climatologies 1900-2012 by DIVA software v4.6.10. Based on Seadatanet historical dataset v1.1.\n\nFor data access please register at http://www.marine-id.org \n\nDIVA settings:\nSeasonal background fields, months 12-02, 03-05, 06-08, 09-11.\nWeighting have been used with length of weighting 0.5\u00b0 and time of weighting 2 days."
-    ],
-    "oai_identifier": [
-        "47a5fc9c-f244-59d5-83a8-87d938b2074c"
-    ],
-    "oai_set": "cams1_ps",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[9,53],[9,66],[31,66],[31,53],[9,53]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "Baltic Sea"
-        },
-        {
-            "name": "Central Baltic Sea"
-        },
-        {
-            "name": "Bay Bothnia"
-        },
-        {
-            "name": "Bothnian Sea"
-        },
-        {
-            "name": "Gulf Finland"
-        },
-        {
-            "name": "Gulf Bothnia"
-        },
-        {
-            "name": "Lillebaelt"
-        }
-    ],
-    "title": [
-        "Baltic Sea - Temperature and Salinity Climatology V1.1"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/5a896000-4049-5c86-ae45-461fc186ff5c.json b/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/5a896000-4049-5c86-ae45-461fc186ff5c.json
deleted file mode 100644
index 6011ad09..00000000
--- a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/5a896000-4049-5c86-ae45-461fc186ff5c.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "sdn-userdesk@seadatanet.org"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=iso19139&identifier=5a896000-4049-5c86-ae45-461fc186ff5c",
-    "PublicationTimestamp": "2015-09-30T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Alfred-Wegener-Institute for Polar- and Marine Research",
-        "Marine Institute",
-        "SEADATANET",
-        "GEOMAR Helmholtz Centre for Ocean Research Kiel",
-        "IFREMER",
-        "IFREMER / IDM/SISMER",
-        "NIOZ Royal Netherlands Institute for Sea Research",
-        "University of East Anglia, School of Environmental Sciences",
-        "Proudman Oceanographic Laboratory",
-        "Odessa Branch of SOI (State Oceanographic Institute)",
-        "Scott Polar Research Institute",
-        "Swedish Meteorological and Hydrological Institute",
-        "Laboratory of Oceanography and Climate  : Experiments and numerical Approaches - UMR 7159",
-        "National Oceanography Centre, Liverpool",
-        "Institute of Marine Research",
-        "Marine Research Institute",
-        "Baltic Sea Research Institute Warnemuende (IOW)",
-        "Institute of Oceanographic Sciences Wormley Laboratory",
-        "Fisheries Research Services, Aberdeen Marine Laboratory",
-        "Shom"
-    ],
-    "ResourceType": "dataset",
-    "Rights": [
-        "No limitations on public access.  For data access please register at http://www.marine-id.org"
-    ],
-    "SpatialCoverage": "(62N-83N,43W-93E)",
-    "TempCoverageBegin": 60920510399,
-    "TempCoverageEnd": 63560721599,
-    "TemporalCoverage": " period : ( 1931-07-01T11:59:59Z - 2015-02-28T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1931-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2015-02-28T11:59:59Z",
-    "fulltext": "f080166b-0632-4de2-85df-97829d56eabf;SEADATANET;sdn-userdesk@seadatanet.org;http://www.seadatanet.org/;2018-07-24T09:47:25;ISO 19115:2003/19139 - EMODNET - SDN;0.1;4;29;1;false;WGS 84 (EPSG 4326);EPSG;Arctic Ocean - Temperature and salinity observation collection V2;seadatanet-arctic_sea-temperature_salinity_aggregated_public-v2;2015-09-30;2.1;2015-09-30;f080166b-0632-4de2-85df-97829d56eabf;SeaDataNet Temperature and Salinity historical data collection for the North Arctic Ocean, including revised quality flags after quality control with ODV. For data access please register at http://www.marine-id.org The dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/;SeaDataNet;Institute of Marine Research;+47 55 23 85 00;+47 55 23 85 31;Nordnesgaten 50\nPostboks 1870 Nordnes;Bergen;N-5817;Norway;post@imr.no;http://www.imr.no;web site;Institute of Marine Research;+47 55 23 85 00;+47 55 23 85 31;Nordnesgaten 50\nPostboks 1870 Nordnes;Bergen;N-5817;Norway;post@imr.no;http://www.imr.no;web site;IFREMER / IDM/SISMER;+33 (0)2 98.22.49.16;+33 (0)2 98.22.46.44;Centre IFREMER de Brest\nBP 70;PLOUZANE;29280;France;sismer@ifremer.fr;http://www.ifremer.fr/sismer/;web site;Baltic Sea Research Institute Warnemuende (IOW);+49 381 5197-0;+49 381 5197 440;Seestrasse 15;Warnemuende;18119;Germany;iowinfo@io-warnemuende.de;http://www.io-warnemuende.de/;web site;IFREMER;+33(0)1 46.48.21.00;+33(0)1 46.48.22.24;Technopolis 40,155 rue J.J. Rousseau;ISSY-LES-MOULINEAUX;92138;France;communication@ifremer.fr;http://wwz.ifremer.fr;web site;Institute of Marine Research;+47 55 23 85 00;+47 55 23 85 31;Nordnesgaten 50\nPostboks 1870 Nordnes;Bergen;N-5817;Norway;post@imr.no;http://www.imr.no;web site;Alfred-Wegener-Institute for Polar- and Marine Research;None;None;Am Handelshafen 12;Bremerhaven;D-27570;Germany;folke.mehrtens@awi.de;http://www.awi.de;web site;Scott Polar Research Institute;None;None;University of Cambridge\nLensfield Road;Cambridge;CB2 1ER;United Kingdom;None;http://www.spri.cam.ac.uk/;web site;Institute of Oceanographic Sciences Wormley Laboratory;None;None;Brook Road\nWormley;Godalming;GU8 5UB;United Kingdom;inapplicable;None;web site;Proudman Oceanographic Laboratory;+44 (0)151 653 8633;+44 (0)151 653 6269;Bidston Observatory\nBidston Hill;Prenton;CH43 7RA;United Kingdom;inapplicable;http://www.pol.ac.uk;web site;National Oceanography Centre, Liverpool;+44 (0)151 795 4800;+44 (0)151 795 4801;Joseph Proudman Building, 6 Brownlow Street;Liverpool;L3 5DA;United Kingdom;enquiries@noc.ac.uk;http://noc.ac.uk;web site;GEOMAR Helmholtz Centre for Ocean Research Kiel;+49 431 600-0;+49 431 600-2805;D\u00fcsternbrooker Weg 20;Kiel;24105;Germany;info@geomar.de;http://www.geomar.de/en/;web site;Fisheries Research Services, Aberdeen Marine Laboratory;+44 (0)1224 876544;+44 (0)1224 295511;PO Box 101\nVictoria Road;Aberdeen;AB11 9DB;United Kingdom;inapplicable;http://www.marlab.ac.uk;web site;Marine Institute;+353-91-387200;+353-91-387201;Rinville;Oranmore;H91 R673;Ireland;datarequests@marine.ie;http://www.marine.ie;web site;Laboratory of Oceanography and Climate  : Experiments and numerical Approaches - UMR 7159;+33 (1) 44 27 32 48;+33(0)1 44 27 38 05;UMR 7159 CNRS / IRD / Universit\u00e9 Pierre et Marie Curie/MNHN\nInstitut Pierre Simon Laplace - Bo\u00eete 100\n4 Place Jussieu;Paris;75252;France;nelly.lecquyer@locean-ipsl.upmc.fr;http://www.locean-ipsl.upmc.fr/;web site;Shom;+33 (0)2 56.31.23.12;+33 (0)2 56.31.25.80;13, rue du Chatellier\nCS92803;BREST CEDEX 2;29228;France;seadatanet-admin@shom.fr;http://www.shom.fr/;web site;Swedish Meteorological and Hydrological Institute;+46-(0)11-495 80 00;+46-(0)11-495 80 01;Folkborgsvagen 1;Norrkoping;SE-601 76;Sweden;shark@smhi.se;http://www.smhi.se;web site;Marine Research Institute;+354 575 2000;+354 575 2001;Skulagata 4\nP.O.Box 1390;Reykjavik;IS-121;Iceland;hafro@hafro.is;http://www.hafro.is/index_eng.php;web site;University of East Anglia, School of Environmental Sciences;None;None;University Plain;Norwich;NR4 7TJ;United Kingdom;env.enquiries@uea.ac.uk;http://www.uea.ac.uk/env/;web site;NIOZ Royal Netherlands Institute for Sea Research;+31 222 369300;+31 222 319674;Landsdiep 4\nP.O. Box 59;Den Burg/Texel;1790 AB;Netherlands;dmg@nioz.nl;https://www.nioz.nl;web site;Odessa Branch of SOI (State Oceanographic Institute);None;None;None;Odessa;None;Ukraine;None;None;web site;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=f080166b-0632-4de2-85df-97829d56eabf&fname=DefaultView_0.png;Oceanographic geographical features;GEMET - INSPIRE themes, version 1.0;2009-09-22T07:57:15;Temperature of the water column;Salinity of the water column;Parameter Discovery Vocabulary (P02);2014-12-11;geonetwork.thesaurus.external.parameter.NVS.P02;ITS-90 water temperature;Water body salinity;EMODNET chemistry lot aggregated parameter names;2014-12-11;geonetwork.thesaurus.external.parameter.NVS.P35;Arctic Ocean;SeaVoX salt and fresh water body gazetteer;2014-12-11;geonetwork.thesaurus.external.reference-geographical-area.NVS.C19;Th\u00e8mes Sextant;2017-01-23;geonetwork.thesaurus.local.theme.sextant-theme;SeaDataNet licence;SeaDataNet Usage Agreement: If you use SeaDataNet data in your publications please include the following in the Acknowledgements: Data were provided through SeaDataNet Pan-European infrastructure for ocean and marine data management (https://www.seadatanet.org);No limitations on public access.  For data access please register at http://www.marine-id.org;1;oceans;bounding box;-43;93;61.9;83;1931-07-01;2015-02-28;-4000.0;0.0;http://dx.doi.org/10.12770/f080166b-0632-4de2-85df-97829d56eabf;WWW:LINK-1.0-http--metadata-URL;DOI of the product;ftp://ftp2.ifremer.fr/public/seadatanet-arctic_ocean-temperaturesalinity_aggregated/SDN_2015-09_TS_Arctic_QC_done_v2.zip;WWW:DOWNLOAD-1.0-link--download;full collection dataset;full collection dataset;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_Arctic_QC_done_v2;OGC:WMS:getCapabilities;full collection dataset;full collection dataset;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_Arctic_QC_done_v2;OGC:WMS;SDN_2015-09_TS_Arctic_QC_done_v2/ITS-90_water_temperature;Temperature;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_Arctic_QC_done_v2;OGC:WMS;SDN_2015-09_TS_Arctic_QC_done_v2/Water_body_salinity;Salinity;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_Arctic_QC_done_v2;OGC:WMS;SDN_2015-09_TS_Arctic_QC_done_v2/*;Observation locations;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;See the referenced specification;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "5a896000-4049-5c86-ae45-461fc186ff5c",
-    "notes": [
-        "SeaDataNet Temperature and Salinity historical data collection for the North Arctic Ocean, including revised quality flags after quality control with ODV. For data access please register at http://www.marine-id.org The dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/"
-    ],
-    "oai_identifier": [
-        "5a896000-4049-5c86-ae45-461fc186ff5c"
-    ],
-    "oai_set": "cams1_ps",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-43,61.9],[-43,83],[93,83],[93,61.9],[-43,61.9]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "Arctic Ocean"
-        }
-    ],
-    "title": [
-        "Arctic Ocean - Temperature and salinity observation collection V2"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/65d3b4df-ef43-566c-a161-530aac1ad33d.json b/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/65d3b4df-ef43-566c-a161-530aac1ad33d.json
deleted file mode 100644
index 8b7b2cc7..00000000
--- a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/65d3b4df-ef43-566c-a161-530aac1ad33d.json
+++ /dev/null
@@ -1,185 +0,0 @@
-{
-    "Contact": [
-        "sdn-userdesk@seadatanet.org"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=iso19139&identifier=65d3b4df-ef43-566c-a161-530aac1ad33d",
-    "PublicationTimestamp": "2015-07-23T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "SEADATANET",
-        "IFREMER / STATION DE LA TRINITE",
-        "IRD / CENTRE DE LA MARTINIQUE",
-        "IFREMER / DYNECO/PELAGOS-LABORATOIRE D'ECOLOGIE PELAGIQUE",
-        "Proudman Oceanographic Laboratory",
-        "IEO/ La Coruna Oceanographic Centre",
-        "Scottish Office Agriculture Environment and Fisheries Department - Aberdeen Marine Laboratory",
-        "IFREMER / IDM/SISMER",
-        "Marine Biological Association of the United Kingdom",
-        "Institute of Oceanographic Sciences, Bidston Laboratory",
-        "Institute of Marine Research (IIM-CSIC)",
-        "IHPT, Hydrographic Institute",
-        "ENEA Centro Ricerche Ambiente Marino - La Spezia",
-        "Ifremer / Crela",
-        "IRD / CENTRE OF HANN",
-        "British Oceanographic Data Centre",
-        "University of Plymouth, Institute of Marine Studies",
-        "Isle of Man Government Laboratory",
-        "IFREMER / RBE Department / Biogeochimical end Ecotoxicological Resarch Unit (Nantes)",
-        "Ministry of Agriculture, Fisheries and Food, Lowestoft Fisheries Laboratory",
-        "Swedish Meteorological and Hydrological Institute",
-        "National Oceanography Centre, Liverpool",
-        "CEREGE",
-        "P.P.Shirshov Institute of Oceanology, RAS",
-        "IFREMER / GM-MARINE GEOSCIENCES",
-        "University of Southampton School of Ocean and Earth Science",
-        "LABO ATMOSPHEREs, MILIEUX, OBSERVATIONS SPATIALES (LATMOS)",
-        "University of Rostock, Institute of Biosciences",
-        "Shom",
-        "UTM-CSIC/Marine Technology Unit",
-        "Centre for Environment, Fisheries and Aquaculture Science, Lowestoft Laboratory",
-        "Polar Scientific Research Institute of Fishery and Oceanography",
-        "Laboratory of Physical Oceanography/ UNIVERSITE DE BRETAGNE OCCIDENTALE (UBO)",
-        "Universite de Pau / IPREM multidisciplinary research institute for the environment and materials",
-        "University of Bordeaux I / Marine Biology Institut",
-        "IFREMER / STH/LBH-LABORATOIRE BIOLOGIE HALIEUTIQUE",
-        "Roscoff Marine Station, Sorbonne Universit\u00e9s, UPMC Univ Paris 06 and CNRS",
-        "Southampton Oceanography Centre",
-        "LABORATORY OF OCEANOGRAPHY of VILLEFRANCHE (LOV) / OOV",
-        "IEO/ Cadiz Oceanographic Centre",
-        "CNEVA / LAB. PATHOLOGIE ANIMAUX AQUATIQUES",
-        "IFREMER",
-        "University of Liverpool, Port Erin Marine Laboratory",
-        "IEO/ Malaga Oceanographic Centre",
-        "Institute of Earth Physics of Paris",
-        "Institute of Marine Research",
-        "Atlantic Scientific Research Institute for Marine Fishery and Oceanography",
-        "Universite D'Angers / Laboratoire Des Bio-Indicateurs Actuels Et Fossiles (Biaf)",
-        "IRD / CENTRE DE PAPEETE",
-        "IRD CENTRE DE  NOUMEA",
-        "NIOZ Royal Netherlands Institute for Sea Research",
-        "University of East Anglia, School of Environmental Sciences",
-        "LABORATORY of PHYSICAL OCEANOGRAPHY (LPO) UMR 6523 CNRS-IFREMER-IRD-UBO",
-        "Institute of Oceanographic Sciences Wormley Laboratory",
-        "IFREMER / DYNECO- Coastal Environment Dynamics department",
-        "University of Southampton Department of Oceanography",
-        "Far Eastern Regional Hydrometeorological Research Institute",
-        "IFREMER / CENTRE DE BRETAGNE",
-        "UNIVERSITE DE BRETAGNE OCCIDENTALE (UBO) / LAB. D'OCEANO. CHIMIQUE LOC - IUEM",
-        "CEA / INSTITUT DE  RADIOPROTECTION ET DE SURETE NUCLEAIRE",
-        "UNKNOWN",
-        "Ukrainian scientific center of Ecology of Sea (UkrSCES)",
-        "Dunstaffnage Marine Laboratory",
-        "Malaga University (UMA). Applied Physics departament II",
-        "IEO/ Gijon Oceanographic Centre",
-        "University of Liverpool Department of Oceanography",
-        "IFREMER STATION DE LA ROCHELLE-L'HOUMEAU",
-        "IFREMER / STATION DE LA TREMBLADE",
-        "Odessa Branch of SOI (State Oceanographic Institute)",
-        "IRD ANTENNE INSTITUT OCEANOGRAPHIQUE (IRD)",
-        "Marine Hydrophysical Institute",
-        "IEO/ Santander Oceanographic Centre",
-        "Canary Institute of Marine Sciences",
-        "IFREMER / STATION DE LORIENT",
-        "IFREMER / STATION D'ARCACHON",
-        "Fisheries Research Services, Aberdeen Marine Laboratory",
-        "German Hydrographic Institute",
-        "Oceanologic Observatory of Banyuls (University of Paris VI) / OSU",
-        "Institute of Oceanographic Sciences Deacon Laboratory",
-        "IEO/ Oceanographic Centre of Canary Island",
-        "MUSEUM NATIONAL D'HISTOIRE NATURELLE / LABORATOIRE D'OCEANOGRAPHIE PHYSIQUE",
-        "IRD / CENTRE OF ABIDJAN",
-        "Scottish Office Agriculture and Fisheries Department - Aberdeen Marine Laboratory",
-        "COM - Physical and Biogeochemical Oceanography Laboratory (LUMINY)",
-        "Department of Agriculture and Fisheries for Scotland - Aberdeen Marine Laboratory",
-        "Scottish Association for Marine Science",
-        "IFREMER / EMH-DEPARTEMENT ECOLOGIE ET MODELES POUR L'HALIEUTIQUE",
-        "IEO/ Vigo Oeanographic Centre",
-        "CEA / Laboratory of climatolocical and environmental Sciences(LSCE)",
-        "University of Cambridge Department of Earth Sciences",
-        "Marine Research Institute",
-        "CNRS / Microbiology, Geochemistry and Marine Ecology Laboratory",
-        "EPOC - Geology and Oceanography Department",
-        "National Oceanography Centre, Southampton",
-        "OGS (Istituto Nazionale di Oceanografia e di Geofisica Sperimentale), Division of Oceanography",
-        "ISTPM (IFREMER NANTES)",
-        "Marine Scotland Science",
-        "IFREMER / STATION DE SETE",
-        "Las Palmas University. Sciences of the Sea Faculty",
-        "GEOMAR Helmholtz Centre for Ocean Research Kiel",
-        "Universite de la Rochelle / Litoral Environnement et Societe (LIENSS) - UMR 7266",
-        "Scottish Marine Biological Association",
-        "Marine Institute",
-        "Aquitaine Observatory of Sciences of the Universe \u2013 University of Bordeaux (OASU)",
-        "University of Bordeaux I / IGBA Talence",
-        "IFREMER / STH-DEPARTEMENT SCIENCES ET TECHNOLOGIES HALIEUTIQUES",
-        "University of Bordeaux I / Laboratory for Physical and Toxico Chemistry (ISM)",
-        "Alfred-Wegener-Institute for Polar- and Marine Research",
-        "IRD /CENTRE DE BRETAGNE",
-        "IFREMER / Dpt Technologicals Research and Development",
-        "IFREMER / DYNECO / PHYSED -LABO PHYSIQUE HYDRODYNAMIQUE ET SEDIMENTAIRE",
-        "Defence Evaluation Research Agency",
-        "Federal Maritime and Hydrographic Agency",
-        "UNIVERSITE DE PAU / LAB.CHIMIE BIO INORGANIQUE & ENVIRONNEMENT",
-        "Laboratory of Oceanography and Climate  : Experiments and numerical Approaches - UMR 7159",
-        "IRD / CENTRE DE MONTPELLIER",
-        "IFREMER / HMMN-DEPARTEMENT HALIEUTIQUE DE MANCHE-MER DU NORD",
-        "University of Wales, School of Ocean Sciences",
-        "Plymouth Marine Laboratory",
-        "IEO/Spanish Oceanographic Institute",
-        "IFREMER / EEP / LEP-DEEP ENVIRONMENT LABORATORY"
-    ],
-    "ResourceType": "dataset",
-    "Rights": [
-        "No limitations on public access.  For data access please register at http://www.marine-id.org"
-    ],
-    "SpatialCoverage": "(10N-65N,90W-10E)",
-    "TempCoverageBegin": 59926651199,
-    "TempCoverageEnd": 63524087999,
-    "TemporalCoverage": " period : ( 1900-01-01T11:59:59Z - 2013-12-31T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1900-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2013-12-31T11:59:59Z",
-    "fulltext": "103b40c0-c07b-46ba-b0e3-f4d5293edd13;SEADATANET;sdn-userdesk@seadatanet.org;http://www.seadatanet.org/;2018-07-24T09:47:25;ISO 19115:2003/19139 - EMODNET - SDN;0.1;4;33;1;false;WGS 84 (EPSG 4326);EPSG;North Atlantic Ocean - Temperature and Salinity Climatology V1.1;seadatanet-north_atlantic_ocean-climatology_public;2015-07-23;1.1;2015-07-23;103b40c0-c07b-46ba-b0e3-f4d5293edd13;Climatology done from the SeaDataNet aggregated dataset v1.1 for the North Atlantic Ocean.\nThe version used for the DIVA software is the 4.6.9.\nThe period covers 1900-2013.\n\n For data access please register at http://www.marine-id.org;SeaDataNet;IFREMER / IDM/SISMER;+33 (0)2 98.22.49.16;+33 (0)2 98.22.46.44;Centre IFREMER de Brest\nBP 70;PLOUZANE;29280;France;sismer@ifremer.fr;http://www.ifremer.fr/sismer/;web site;IFREMER / IDM/SISMER;+33 (0)2 98.22.49.16;+33 (0)2 98.22.46.44;Centre IFREMER de Brest\nBP 70;PLOUZANE;29280;France;sismer@ifremer.fr;http://www.ifremer.fr/sismer/;web site;IFREMER / STATION D'ARCACHON;05 56.83.85.60;05 56.83.89.80;IFREMER Station d'Arcachon, Quai du Commandant Silhouette;Arcachon;33120;France;None;http://www.ifremer.fr/delar;web site;Aquitaine Observatory of Sciences of the Universe \u2013 University of Bordeaux (OASU);+33 (0)5 40 00 83 50;+33(0)5 57 77 56 88;O.A.S.U. \nB\u00e2timent B18N\nAll\u00e9e Geoffroy Saint Hilaire\nCS 50023;PESSAC Cedex;33615;France;None;http://www.oasu.u-bordeaux.fr/;web site;Oceanologic Observatory of Banyuls (University of Paris VI) / OSU;+33 4 68 88 73 15;+33 4 68 88 16 99;Laboratoire Arago\nBP 44;BANYULS-SUR-MER;66651;France;None;http://www.obs-banyuls.fr/;web site;IFREMER / DYNECO- Coastal Environment Dynamics department;+33 (0)2 98.22.43.51;+33 (0)2 98 22 45.48;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;None;http://www.ifremer.fr/anglais/org/del.htm;web site;CEA / INSTITUT DE  RADIOPROTECTION ET DE SURETE NUCLEAIRE;+33(0)2 33.01.41.00;None;LABORATOIRE DE RADIOECOLOGIE MARINE,RUE MAX POL FOUCHET,BP 10;OCTEVILLE;50130;France;None;http://www.irsn.org/en/;web site;CNEVA / LAB. PATHOLOGIE ANIMAUX AQUATIQUES;+33(0)2 98.22.44.61;None;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;None;None;web site;UNKNOWN;None;None;UNKNOWN;UNKNOWN;None;Unknown;None;None;web site;IFREMER;+33(0)1 46.48.21.00;+33(0)1 46.48.22.24;Technopolis 40,155 rue J.J. Rousseau;ISSY-LES-MOULINEAUX;92138;France;communication@ifremer.fr;http://wwz.ifremer.fr;web site;IFREMER / STATION DE LA TREMBLADE;+33(0)5 46.36.18.41;+33(0)5 46.36.18.47;Mus du Loup,BP 133;LA TREMBLADE;17390;France;None;http://www.ifremer.fr/latremblade/accueilen.htm;web site;IRD / CENTRE DE LA MARTINIQUE;+33 (0)596 39 77 39;+33 (0)596 50 32 61;BP 8006;FORT DE FRANCE cedex;97259;France;representant@ird-mq.fr;http://www.mq.ird.fr/;web site;IRD / CENTRE DE MONTPELLIER;+33 (0)4 67 41 61 00;+33 (0)4 67 41 63 30;BP 64501;MONTPELLIER CEDEX 5;34394;France;montpellier@ird.fr;http://www.france-sud.ird.fr/;web site;IRD / CENTRE DE PAPEETE;(689) 50 62 00;(689) 42 95 55;Chemin de l'ahari PK 3800 - Arue,BP 529;PAPEETE (Tahiti);98713;France;dirpapet@ird.pf;http://www.polynesie.ird.fr/;web site;ISTPM (IFREMER NANTES);+33(0)2 40.37.40.00;None;rue de l'Ile d'Yeu,BP 1105;NANTES CEDEX 03;44311;France;None;None;web site;University of Bordeaux I / IGBA Talence;+33(0)5 56 80 68 00;None;351, Cours de la Liberation;TALENCE CEDEX;33405;France;None;None;web site;University of Bordeaux I / Marine Biology Institut;+33(0)4 69 82 35 36;None;351, Cours de la Liberation;TALENCE CEDEX;33405;France;None;None;web site;UNIVERSITE DE PAU / LAB.CHIMIE BIO INORGANIQUE & ENVIRONNEMENT;+33(0)5 59 40 77 50;+33(0)5 59 40 77 81;2 Avenue du President ANGOT,HELIOPARC;PAU Cedex 09;64053;France;None;None;web site;IRD / CENTRE OF ABIDJAN;(225) 24 37 79;(225) 24 65 04;Rue du Chevalier de Clieu15 \n15 BP 917;Abidjan;15;C\u00f4te d'Ivoire;rep@ird.ci;None;web site;IRD / CENTRE OF HANN;+221 849 35 35;+221 832 43 07;Route des Peres Maristes\nBP 1386;DAKAR - HANN;None;Senegal;infos@ird.sn;http://www.ird.sn/centre/index.htm;web site;Ukrainian scientific center of Ecology of Sea (UkrSCES);+38 0482 636622;+380 482  636873;89 Frantsuzsky Blvd.;Odessa;65009;Ukraine;accem@te.net.ua;http://www.sea.gov.ua;web site;OGS (Istituto Nazionale di Oceanografia e di Geofisica Sperimentale), Division of Oceanography;None;None;Borgo Grotta Gigante 42/c;Sgonico (Trieste);34010;Italy;nodc@ogs.trieste.it;http://www.ogs.trieste.it/;web site;University of Plymouth, Institute of Marine Studies;None;None;Drake Circus;Plymouth;PL4 8AA;United Kingdom;inapplicable;http://www.plymouth.ac.uk/plymouth/main.htm;web site;Institute of Marine Research;+47 55 23 85 00;+47 55 23 85 31;Nordnesgaten 50\nPostboks 1870 Nordnes;Bergen;N-5817;Norway;post@imr.no;http://www.imr.no;web site;ENEA Centro Ricerche Ambiente Marino - La Spezia;+39 0187 978258;+39 0187 978213;Forte S. Teresa\nVia S.Teresa 1;Lerici;19036;Italy;roberta.delfanti@enea.it;http://www.santateresa.enea.it;web site;Alfred-Wegener-Institute for Polar- and Marine Research;None;None;Am Handelshafen 12;Bremerhaven;D-27570;Germany;folke.mehrtens@awi.de;http://www.awi.de;web site;Isle of Man Government Laboratory;+44 (0)1624 642250;+44 (0)1624 642222;Ballakermeen Road;Douglas;IM1 4BR;United Kingdom;analyst@lab.gov.im;http://www.gov.im/dlge/enviro/govlabs/;web site;Malaga University (UMA). Applied Physics departament II;+34 952 132413/27 78;+34 952 13 24 16;Escuela Tecnica Superior de Ingenieros de Telecomunicaciones. Departamento de Fisica Aplicada II\nComplejo Tecnol\u00f3gico-Campus Teatinos;Malaga;29071;Spain;secteleco@uma.es;http://150.214.57.159/fa2.php;web site;Las Palmas University. Sciences of the Sea Faculty;+34 928 452900;+34 928 452922;Edificio Ciencias B\u00e1sicas\nCAMPUS UNIVERSITARIO DE TAFIRA\nApdo. 550;Las Palmas de Gran Canaria (Islas Canarias);35017;Spain;None;http://www.fcm.ulpgc.es;web site;University of Liverpool, Port Erin Marine Laboratory;None;None;None;Port Erin;IM9 6JA;United Kingdom;inapplicable;http://www.liv.ac.uk/www/peml/;web site;IEO/ Gijon Oceanographic Centre;+34 985 30 86 72;+34 985 32 62 77;Camino de Arbeyal, s/n;Gijon (Asturias);33212;Spain;ieogijon@gi.ieo.es;http://www.ieo.es/CoGijon/index.htm;web site;IEO/ Santander Oceanographic Centre;+34 942 291060;+34 942 275072;Promontorio San Martin, s/n\nApdo. 240;Santander;39004;Spain;ieosantander@st.ieo.es;http://www.ieo-santander.net/;web site;IEO/ La Coruna Oceanographic Centre;+34 981 205362;+34 981 229077;Muelle de las Animas, s/n\nApdo.130;A Coruna;15001;Spain;ieo.coruna@co.ieo.es;http://www.ieo.es;web site;IEO/ Vigo Oeanographic Centre;+34 986 492 111;+34 986 498 626;Cabo Estay \u2013 Canido;Vigo;36200;Spain;ieo.vigo@vi.ieo.es;http://www.vi.ieo.es/;web site;IEO/ Malaga Oceanographic Centre;+34 952 476 955;+34 952 463 808;Puerto Pesquero, s/n\nApdo. 285;Fuengirola (Malaga);29640;Spain;ieomalaga@ma.ieo.es;http://www.ieo.es;web site;IEO/ Cadiz Oceanographic Centre;+34 956 294 189;+34 956 263 556;Muelle de Levante (Puerto Pesquero)\nApdo. 2609;Puerto Real (Cadiz);11106;Spain;ignacio.sobrino@cd.ieo.es;http://www.ieo.es;web site;IFREMER / STATION DE LORIENT;+33 (0)2 97 87 38 00;+33 (0)2 97 87 38 01;8 rue Fran\u00e7ois Toullec;LORIENT;56100;France;secretariat@ifremer.fr;http://www.ifremer.fr/sth/station_lorient.htm;web site;National Oceanography Centre, Southampton;None;None;University of Southampton \nWaterfront Campus \nEuropean Way;Southampton;SO14 3ZH;United Kingdom;enquiries@noc.ac.uk;http://noc.ac.uk;web site;University of Rostock, Institute of Biosciences;+49 (0)381 498 6041;+49 (0)381 498 6042;Wismarsche Strasse 8;Rostock;18057;Germany;institut.biowissenschaften@uni-rostock.de;http://www.bio.uni-rostock.de;web site;University of Liverpool Department of Oceanography;None;None;Brownlow Hill;Liverpool;None;United Kingdom;inapplicable;None;web site;University of Southampton School of Ocean and Earth Science;+44 (0)23 8059 2011;+44 (0)23 8059 3059;National Oceanography Centre, European Way;Southampton;SO14 3ZH;United Kingdom;soes@noc.soton.ac.uk;http://www.soes.soton.ac.uk/;web site;University of Southampton School of Ocean and Earth Science;None;None;Southampton Oceanography Centre, European Way;Southampton;SO14 3ZH;United Kingdom;inapplicable;None;web site;University of Southampton Department of Oceanography;None;None;University of Southampton Waterfront Campus, European Way;Southampton;SO14 3ZH;United Kingdom;inapplicable;None;web site;University of Southampton Department of Oceanography;None;None;Highfield Campus;Southampton;SO9 5NH;United Kingdom;inapplicable;None;web site;German Hydrographic Institute;494031903420;494031905000;Bernhard-Nocht-Str. 78;Hamburg;20359;Germany;friedrich.nast;http://www.bsh.de/en/Marine_data/Hydrographic_surveys_and_wreck_search/Hydrographic_surveys/e_geschichte_sv.jsp;web site;Federal Maritime and Hydrographic Agency;+49 40 3190 0;+49 40 3190 5000;Bernhard-Nocht-Str. 78;Hamburg;20359;Germany;webmaster@bsh.de;http://www.bsh.de;web site;Universite de la Rochelle / Litoral Environnement et Societe (LIENSS) - UMR 7266;05.46.45.72.61;None;Av, Michel Cr\u00e9peau\nLAB. DE BIOLOGIE ET ENVIRONNEMENT MARIN - LBEM;LA ROCHELLE;17042;France;None;http://www.univ-lr.fr/labo/lbem/;web site;LABO ATMOSPHEREs, MILIEUX, OBSERVATIONS SPATIALES (LATMOS);+33 (0)1 39 25 49 06;+33 (0)1 39 25 49 22;Centre Universitaire de V\u00e9lizy\n10-12 Avenue de l'Europe;VELIZY;78140;France;direction@latmos.ipsl.fr;http://www.latmos.ipsl.fr/;web site;Ifremer / Crela;+33(0)5 46.50.94.40;+33(0)5 46.50.06.60;Centre de Recherche sur Ecosyst\u00e8mes Littoraux Anthropis\u00e9s\n Place du S\u00e9minaire\nBP 7;L'HOUMEAU;17137;France;None;None;web site;University of Bordeaux I / Laboratory for Physical and Toxico Chemistry (ISM);None;None;LPTC - ESA 5472 CNRS\nUniversite Bordeaux 1l'\u00e9tu\n351 Cours de la Lib\u00e9ration;TALENCE CEDEX;33405;France;None;http://www.ism.u-bordeaux1.fr/-Physico-et-Toxicochimie-de-l-.html;web site;Universite D'Angers / Laboratoire Des Bio-Indicateurs Actuels Et Fossiles (Biaf);02.41.73.53.91;02.41.73.53.52;UFR Sciences - UPRES EA 2644\n2, Bd Lavoisier;ANGERS cedex 01;49045;France;frans.jorissen@univ-angers.fr;None;web site;Universite de Pau / IPREM multidisciplinary research institute for the environment and materials;05 59 40 77 51;05 59 40 77 81;IPREM UMR 5254\nH\u00e9lioparc Pau Pyr\u00e9n\u00e9es\n2, av. Pierre Angot;PAU CEDEX 9;64053;France;olivier.donard@univ-pau.fr;http://www.iprem.org/;web site;University of Cambridge Department of Earth Sciences;None;None;Downing Street;Cambridge;CB2 3EQ;United Kingdom;jaj2@cam.ac.uk;http://www.esc.cam.ac.uk;web site;University of Wales, School of Ocean Sciences;None;None;School of Ocean Sciences,\nUniversity of Wales Bangor, \nMenai Bridge, \nAnglesey,;Menai Bridge;LL59 5AB;United Kingdom;inapplicable;http://www.sos.bangor.ac.uk/;web site;Southampton Oceanography Centre;None;None;University of Southampton \nWaterfront Campus \nEuropean Way;Southampton;SO14 3ZH;United Kingdom;inapplicable;None;web site;Scottish Office Agriculture Environment and Fisheries Department - Aberdeen Marine Laboratory;None;None;PO Box 101\n375 Victoria Road;Aberdeen;AB11 9DB;United Kingdom;inapplicable;None;web site;Scottish Office Agriculture and Fisheries Department - Aberdeen Marine Laboratory;None;None;PO Box 101\n375 Victoria Road;Aberdeen;AB11 9DB;United Kingdom;inapplicable;None;web site;Department of Agriculture and Fisheries for Scotland - Aberdeen Marine Laboratory;None;None;PO Box 101\n375 Victoria Road;Aberdeen;AB11 9DB;United Kingdom;inapplicable;None;web site;Ministry of Agriculture, Fisheries and Food, Lowestoft Fisheries Laboratory;None;None;Pakefield Road;Lowestoft;NR33 0HT;United Kingdom;inapplicable;None;web site;Institute of Oceanographic Sciences Deacon Laboratory;None;None;Brook Road\nWormley;Godalming;GU8 5UB;United Kingdom;inapplicable;None;web site;Institute of Oceanographic Sciences Wormley Laboratory;None;None;Brook Road\nWormley;Godalming;GU8 5UB;United Kingdom;inapplicable;None;web site;Proudman Oceanographic Laboratory;+44 (0)151 653 8633;+44 (0)151 653 6269;Bidston Observatory\nBidston Hill;Prenton;CH43 7RA;United Kingdom;inapplicable;http://www.pol.ac.uk;web site;Institute of Oceanographic Sciences, Bidston Laboratory;None;None;Bidston Observatory\nBidston Hill;Prenton;L43 7RA;United Kingdom;inapplicable;None;web site;Marine Scotland Science;+44 (0)1224 876544;+44 (0)1224 295511;Marine Laboratory, PO Box 101;Aberdeen;AB11 9DB;United Kingdom;inapplicable;None;web site;Defence Evaluation Research Agency;None;None;Winfrith Technology Centre;Winfrith;DT2 8XJ;United Kingdom;inapplicable;http://www.dera.gov.uk/newsite/home_2.htm;web site;National Oceanography Centre, Liverpool;+44 (0)151 795 4800;+44 (0)151 795 4801;Joseph Proudman Building, 6 Brownlow Street;Liverpool;L3 5DA;United Kingdom;enquiries@noc.ac.uk;http://noc.ac.uk;web site;UTM-CSIC/Marine Technology Unit;+34 932 309500;+34 932 309555;Paseo Maritimo de la Barceloneta, 37-49;Barcelona;08003;Spain;info@utm.csic.es;http://www.utm.csic.es/;web site;Dunstaffnage Marine Laboratory;None;None;Dunbeg;Oban;PA37 1QA;United Kingdom;inapplicable;None;web site;Scottish Marine Biological Association;None;None;Dunbeg;Oban;PA37 1QA;United Kingdom;inapplicable;None;web site;Institute of Marine Research (IIM-CSIC);+34 986231930;+34 986292762;Eduardo Cabello, 6;Vigo (Pontevedra);36208;Spain;webmaster@iim.csic.es;http://www.iim.csic.es;web site;Centre for Environment, Fisheries and Aquaculture Science, Lowestoft Laboratory;+44 (0)1502 562244;+44 (0)1502 513865;Pakefield Road;Lowestoft;NR33 OHT;United Kingdom;sarah.turner@cefas.co.uk;http://www.cefas.co.uk/;web site;GEOMAR Helmholtz Centre for Ocean Research Kiel;+49 431 600-0;+49 431 600-2805;D\u00fcsternbrooker Weg 20;Kiel;24105;Germany;info@geomar.de;http://www.geomar.de/en/;web site;IEO/ Oceanographic Centre of Canary Island;+34 922 549400;+34 922 549554;Carretera San Andr\u00e9s Km 7\nApdo. 1373;S. C. Tenerife;38180;Spain;coc@ca.ieo.es;http://www.ieo.es;web site;Canary Institute of Marine Sciences;+34 928 132900;+34 928 132908;Carretera de Taliarte, s/n.;Telde (Las Palmas de Gran Canaria);35200;Spain;None;http://www.iccm.rcanaria.es;web site;IEO/Spanish Oceanographic Institute;+34 915 107513;+34 914 135597;Corazon de Maria, 8;MADRID;28002;Spain;cedo@ieo.es;http://www.ieo.es;web site;Fisheries Research Services, Aberdeen Marine Laboratory;+44 (0)1224 876544;+44 (0)1224 295511;PO Box 101\nVictoria Road;Aberdeen;AB11 9DB;United Kingdom;inapplicable;http://www.marlab.ac.uk;web site;Marine Institute;+353-91-387200;+353-91-387201;Rinville;Oranmore;H91 R673;Ireland;datarequests@marine.ie;http://www.marine.ie;web site;British Oceanographic Data Centre;None;None;Joseph Proudman Building\n6 Brownlow Street;Liverpool;L3 5DA;United Kingdom;enquiries@bodc.ac.uk;http://www.bodc.ac.uk/;web site;Scottish Association for Marine Science;None;None;None;Argyll;PA37 1QA;United Kingdom;laurence.mee@sams.ac.uk;http://www.sams.ac.uk;web site;IRD /CENTRE DE BRETAGNE;+33 (0)2 98.22.45.01;+33(0)2 98.22.45.14;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;None;http://www.brest.ird.fr/;web site;IFREMER / DYNECO/PELAGOS-LABORATOIRE D'ECOLOGIE PELAGIQUE;+33(0)2 98 22 43 34;+33(0)2 98 22  45 98;IFREMER Centre de Brest\nBP70;PLOUZANE;29280;France;None;http://www.ifremer.fr/delec/;web site;Marine Biological Association of the United Kingdom;None;None;Citadel Hill;Plymouth;PL1 2PB;United Kingdom;sec@mba.ac.uk;http://www.mba.ac.uk/;web site;Plymouth Marine Laboratory;+44 (0)1752 633 100;+44 (0)1752 633101;Prospect Place\nThe Hoe;Plymouth;PL1 3DH;United Kingdom;forinfo@pml.ac.uk;http://www.pml.ac.uk;web site;Proudman Oceanographic Laboratory;None;None;Joseph Proudman Building\n6 Brownlow Street;Liverpool;L3 5DA;United Kingdom;inapplicable;http://www.pol.ac.uk;web site;IFREMER / EEP / LEP-DEEP ENVIRONMENT LABORATORY;+33 (0)2 98.22.43.04;+33 (0)2 98.22.47.57;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;None;http://www.ifremer.fr/droep/index.html;web site;IFREMER / GM-MARINE GEOSCIENCES;+33(0)2 98.22.42.70;+33(0)2 98.22.45.70;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;geosciences.marines@ifremer.fr;http://www.ifremer.fr/drogm/;web site;LABORATORY of PHYSICAL OCEANOGRAPHY (LPO) UMR 6523 CNRS-IFREMER-IRD-UBO;+33 (0)2 98.22.42.76;+33(0)2 98.22.44.96;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;None;http://www.ifremer.fr/lpo/;web site;LABORATORY OF OCEANOGRAPHY of VILLEFRANCHE (LOV) / OOV;+33 (0)4 93 76 38 13;+33 (0)4.93.76.38.34;UPMC/UMR 7093 \n181, chemin du Lazaret;Villefranche-sur-Mer;06230;France;lov@obs-vlfr.fr;http://www.obs-vlfr.fr;web site;Laboratory of Oceanography and Climate  : Experiments and numerical Approaches - UMR 7159;+33 (1) 44 27 32 48;+33(0)1 44 27 38 05;UMR 7159 CNRS / IRD / Universit\u00e9 Pierre et Marie Curie/MNHN\nInstitut Pierre Simon Laplace - Bo\u00eete 100\n4 Place Jussieu;Paris;75252;France;nelly.lecquyer@locean-ipsl.upmc.fr;http://www.locean-ipsl.upmc.fr/;web site;MUSEUM NATIONAL D'HISTOIRE NATURELLE / LABORATOIRE D'OCEANOGRAPHIE PHYSIQUE;+33 (0)1 40.79.31 58;+33 (0)1 40 79 31 63;43-45 rue Cuvier;PARIS CEDEX 05;75231;France;None;http://www.mnhn.fr;web site;IFREMER / DYNECO / PHYSED -LABO PHYSIQUE HYDRODYNAMIQUE ET SEDIMENTAIRE;33 (0)2 98 22 47 60;33 (0)2 98 22 45 55;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;None;http://wwz.ifremer.fr/dyneco/Equipes/Physed;web site;COM - Physical and Biogeochemical Oceanography Laboratory (LUMINY);+33(0)4 91 82 91 15;+33(0)4 91.82.65.48;UFR Centre Oceanologique de Marseille\nUMR 6535\nCampus de Luminy Case 901;Marseille cedex 9;13288;France;queguiner@com.univ-mrs.fr;http://www.com.univ-mrs.fr/LOB/;web site;IFREMER STATION DE LA ROCHELLE-L'HOUMEAU;+33 (0)5 46.50.94.40;+33 (0)5 46.50.06.50;Place du Seminaire, \nBP 7;L'HOUMEAU;17137;France;None;http://w3.ifremer.fr/francais/implant/larochel.htm;web site;Institute of Earth Physics of Paris;+33 (0)1 83 95 74 00;+33 (0)1 83 95 77 14;1, place Jussieu;PARIS CEDEX 5;75252;France;None;http://www.ipgp.jussieu.fr/;web site;IRD CENTRE DE  NOUMEA;+33 (0)1 44 27 34 67;+33 (0)1 44 27 24 01;BP A5;NOUMEA CEDEX5;98848;New Caledonia;nouvelle-caledonie@ird.fr;http://www.ird.nc/;web site;Roscoff Marine Station, Sorbonne Universit\u00e9s, UPMC Univ Paris 06 and CNRS;+33(0)2 98.29.23.23;+33 (0)2 98.29.23.24;Place Georges Teissier;ROSCOFF;29680;France;None;http://www.sb-roscoff.fr/;web site;IFREMER / RBE Department / Biogeochimical end Ecotoxicological Resarch Unit (Nantes);+33 (0)2 40 37 41 93;33(0)2 40.37.40.75;IFREMER Centre de Nantes\nRue de l'Ile d'Yeu\nBP 1105;NANTES CEDEX 03;44311;France;None;http://www.ifremer.fr/delpc/;web site;CNRS / Microbiology, Geochemistry and Marine Ecology Laboratory;+33 (0)4 91 82 92 12;+33 (0)4 91 82 96 41;Centre d'Oc\u00e9anologie de Marseille (COM)\nUMR 6117\nCampus de Luminy, Case 901;MARSEILLE CEDEX 9;13288;France;micromar@com.univ-mrs.fr;http://www.com.univ-mrs.fr/LMGEM/spip.php?rubrique1;web site;IFREMER / STATION DE LA TRINITE;+33 (0)2 97 30 19 19;+33 (0)2 97 30 19 00;12, rue des Resistants\nBP 86;LA TRINITE-SUR-MER;56470;France;None;http://www.ifremer.fr/anglais/implant/latrinit.htm;web site;IFREMER / STH/LBH-LABORATOIRE BIOLOGIE HALIEUTIQUE;+33 (0)2.97.87.38.00;+33 (0)2.97.87.38.01;IFREMER Station de Lorient\n8, rue Francois Toullec;LORIENT;56100;France;mlegall@ifremer.fr;http://wwz.ifremer.fr/lorient;web site;Shom;+33 (0)2 56.31.23.12;+33 (0)2 56.31.25.80;13, rue du Chatellier\nCS92803;BREST CEDEX 2;29228;France;seadatanet-admin@shom.fr;http://www.shom.fr/;web site;IFREMER / EMH-DEPARTEMENT ECOLOGIE ET MODELES POUR L'HALIEUTIQUE;+33(0)2 40.37.41. 67;+33(0)2 40.37.40.75;IFREMER - Centre de Nantes\nrue de l'Ile d'Yeu\nBP 21105;NANTES CEDEX 03;44311;France;None;http://www.ifremer.fr/drvecohal;web site;IFREMER / HMMN-DEPARTEMENT HALIEUTIQUE DE MANCHE-MER DU NORD;+33 (0)3 21.99.56.00;+33 (0)3 21.99.56.01;IFREMER Centre de Boulogne sur Mer\n150 quai Gambetta \nBP 70;BOULOGNE-SUR-MER CEDEX;62321;France;None;http://www.ifremer.fr/boulogne/;web site;Swedish Meteorological and Hydrological Institute;+46-(0)11-495 80 00;+46-(0)11-495 80 01;Folkborgsvagen 1;Norrkoping;SE-601 76;Sweden;shark@smhi.se;http://www.smhi.se;web site;CEA / Laboratory of climatolocical and environmental Sciences(LSCE);+33(0)1 69.82 35 23;+33(0)1 69.82.35.68;CNRS\nLSCE-Vallee, Bat.12, Avenue de la Terrasse;GIF-SUR-YVETTE CEDEX;91198;France;None;http://www.lsce.cnrs-gif.fr/;web site;UNIVERSITE DE BRETAGNE OCCIDENTALE (UBO) / LAB. D'OCEANO. CHIMIQUE LOC - IUEM;None;None;Place Nicolas Copernic;Plouzane;29280;France;None;None;web site;CEREGE;+33(0)4 42 97 15 00;+33 (0)4 42 97 15 05;Europole Mediterraneen de l'Arbois \nBP 80;Aix en Provence;13545;France;None;http://www.cerege.fr/;web site;Marine Research Institute;+354 575 2000;+354 575 2001;Skulagata 4\nP.O.Box 1390;Reykjavik;IS-121;Iceland;hafro@hafro.is;http://www.hafro.is/index_eng.php;web site;IHPT, Hydrographic Institute;+351 210943000;+351 210943299;Rua das Trinas, 49;Lisboa;1249-093;Portugal;mail@hidrografico.pt;http://www.hidrografico.pt;web site;University of East Anglia, School of Environmental Sciences;None;None;University Plain;Norwich;NR4 7TJ;United Kingdom;env.enquiries@uea.ac.uk;http://www.uea.ac.uk/env/;web site;NIOZ Royal Netherlands Institute for Sea Research;+31 222 369300;+31 222 319674;Landsdiep 4\nP.O. Box 59;Den Burg/Texel;1790 AB;Netherlands;dmg@nioz.nl;https://www.nioz.nl;web site;Atlantic Scientific Research Institute for Marine Fishery and Oceanography;8 (0112) 21-56-45;8 (0112) 21-99-97;5, Dm. Donskoi St.;Kaliningrad reg;236000;Russian Federation;atlant@baltnet.ru;http://www.atlantniro.ru/;web site;P.P.Shirshov Institute of Oceanology, RAS;+7(499)124-59-96;+7(499)124-59-83;36 Nakhimovsky prospect;Moscow;117997;Russian Federation;office@ocean.ru;http://www.ocean.ru;web site;IFREMER / STATION DE SETE;+33(0)4 99 57 32 00;+33 (0)4 99 57 32 94;Bd Jean Monnet \nBP 171;SETE CEDEX;34203;France;None;http://wwz.ifremer.fr/mediterranee/implantations/Sete;web site;Marine Hydrophysical Institute;+380 692 54 02 52;+380 692 55 42 53;2, Kapitanskaya str.;Sevastopol;99011;Ukraine;khaliulin.alexey@nodc.org.ua;http://WWW.MHI.IUF.NET;web site;Far Eastern Regional Hydrometeorological Research Institute;+7 (4232) 26-97-88;+7 (4232) 22-77-54;Fontannaya St., 24;Vladivostok;690600;Russian Federation;hydromet@online.ru;http://www.hydromet.com;web site;IFREMER / STH-DEPARTEMENT SCIENCES ET TECHNOLOGIES HALIEUTIQUES;+33 (0)2 98.22.43.66;+33 (0)2 98 22 45.47;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;None;http://www.ifremer.fr/anglais/org/drv.htm;web site;IFREMER / Dpt Technologicals Research and Development;+33(0) 2 98 22 41 41;+33(0) 2 98 22 45 35;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;Pierre.Chauchot@ifremer.fr;http://wwz.ifremer.fr/rd_technologiques;web site;IRD ANTENNE INSTITUT OCEANOGRAPHIQUE (IRD);+33 (0)1 44.32.10.70;+33 (0)1 40.51.73.16;INSTITUT OCEANOGRAPHIQUE \n195 Rue Saint Jacques;PARIS;75005;France;None;None;web site;Laboratory of Physical Oceanography/ UNIVERSITE DE BRETAGNE OCCIDENTALE (UBO);+33 (0)2 98.01.61.21;+33 (0)2 98 01 64 68;6 avenue Victor-Le-Gorgeu BP 809;BREST CEDEX;29285;France;None;http://www.univ-brest.fr/lpo/site/;web site;EPOC - Geology and Oceanography Department;+33 (0)5 40.00.88.67;+33 (0)5 56.84.08.48;351, Cours de la Liberation \nAvenue des Facultes;TALENCE;33405;France;inapplicable;http://www.epoc.u-bordeaux.fr;web site;IFREMER / CENTRE DE BRETAGNE;+33 (0)2 98.22.40.40;+33 (0)2 98.22.45.45;ZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;None;http://www.ifremer.fr/brest/;web site;Polar Scientific Research Institute of Fishery and Oceanography;None;None;6, Knipovich St.;Murmansk;183763;Russian Federation;persey@pinro.ru;http://www.pinro.ru/;web site;Odessa Branch of SOI (State Oceanographic Institute);None;None;None;Odessa;None;Ukraine;None;None;web site;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=103b40c0-c07b-46ba-b0e3-f4d5293edd13&fname=Icone_catalogue_sextant_runB.png;Oceanographic geographical features;GEMET - INSPIRE themes, version 1.0;2009-09-22T07:57:15;Temperature of the water column;Salinity of the water column;Parameter Discovery Vocabulary (P02);2014-12-11;geonetwork.thesaurus.external.parameter.NVS.P02;ITS-90 water temperature;Water body salinity;EMODNET chemistry lot aggregated parameter names;2014-12-11;geonetwork.thesaurus.external.parameter.NVS.P35;Atlantic Ocean;SeaVoX salt and fresh water body gazetteer;2014-12-11;geonetwork.thesaurus.external.reference-geographical-area.NVS.C19;Th\u00e8mes Sextant;2017-01-23;geonetwork.thesaurus.local.theme.sextant-theme;SeaDataNet licence;SeaDataNet Usage Agreement: If you use SeaDataNet data in your publications please include the following in the Acknowledgements: Data were provided through SeaDataNet Pan-European infrastructure for ocean and marine data management (https://www.seadatanet.org);No limitations on public access.  For data access please register at http://www.marine-id.org;8;oceans;bounding box;-90;10;10;65;1900-01-01;2013-12-31;-5500.0;0.0;http://dx.doi.org/10.12770/103b40c0-c07b-46ba-b0e3-f4d5293edd13;WWW:LINK-1.0-http--metadata-URL;DOI of the product;http://oceanbrowser.net/web-vis/Python/web/wms;OGC:WMS:getCapabilities;T and S layers;wms from oceanbrowser;http://oceanbrowser.net/web-vis/Python/web/wms;OGC:WMS;Atlantic/Temperature.19002013.4Danl.nc*Temperature_L1;Temperature masked using relative error threshold 0.3;http://oceanbrowser.net/web-vis/Python/web/wms;OGC:WMS;Atlantic/Temperature.19002013.4Danl.nc*Temperature_L2;Temperature masked using relative error threshold 0.5;http://oceanbrowser.net/web-vis/Python/web/wms;OGC:WMS;Atlantic/Salinity.19002013.4Danl.nc*Salinity_L1;Salinity masked using relative error threshold 0.3;http://oceanbrowser.net/web-vis/Python/web/wms;OGC:WMS;Atlantic/Salinity.19002013.4Danl.nc*Salinity_L2;Salinity masked using relative error threshold 0.5;ftp://ftp2.ifremer.fr/public/seadatanet-north_atlantic_ocean-temperaturesalinity_climatologie/SDN_2015-08_TS_Atlantic_Climatology_v1.1.zip;WWW:DOWNLOAD-1.0-link--download;full collection dataset;full collection dataset (odv binary format);COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;See the referenced specification;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "65d3b4df-ef43-566c-a161-530aac1ad33d",
-    "notes": [
-        "Climatology done from the SeaDataNet aggregated dataset v1.1 for the North Atlantic Ocean.\nThe version used for the DIVA software is the 4.6.9.\nThe period covers 1900-2013.\n\n For data access please register at http://www.marine-id.org"
-    ],
-    "oai_identifier": [
-        "65d3b4df-ef43-566c-a161-530aac1ad33d"
-    ],
-    "oai_set": "cams1_ps",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-90,10],[-90,65],[10,65],[10,10],[-90,10]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "Atlantic Ocean"
-        }
-    ],
-    "title": [
-        "North Atlantic Ocean - Temperature and Salinity Climatology V1.1"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/6d5b80c0-f9ea-5594-922c-b580bf5cae07.json b/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/6d5b80c0-f9ea-5594-922c-b580bf5cae07.json
deleted file mode 100644
index 2fd32050..00000000
--- a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/6d5b80c0-f9ea-5594-922c-b580bf5cae07.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "sdn-userdesk@seadatanet.org"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=iso19139&identifier=6d5b80c0-f9ea-5594-922c-b580bf5cae07",
-    "PublicationTimestamp": "2015-07-31T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Royal Belgian Institute of Natural Sciences, Operational Directorate Natural Environment, Belgian Marine Data Centre",
-        "IFREMER / IDM/SISMER",
-        "SEADATANET"
-    ],
-    "ResourceType": "dataset",
-    "Rights": [
-        "No limitations on public access.  For data access please register at http://www.marine-id.org"
-    ],
-    "SpatialCoverage": "(49N-62N,4 W-10E)",
-    "TempCoverageBegin": 59926651199,
-    "TempCoverageEnd": 63555623999,
-    "TemporalCoverage": " period : ( 1900-01-01T11:59:59Z - 2014-12-31T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1900-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2014-12-31T11:59:59Z",
-    "fulltext": "8a51f275-6a8a-4ac2-ba7e-fe491e63a17d;SEADATANET;sdn-userdesk@seadatanet.org;http://www.seadatanet.org/;2018-07-24T09:47:44;ISO 19115:2003/19139 - EMODNET - SDN;0.1;4;999;1;false;WGS 84 (EPSG 4326);EPSG;North Sea - Temperature and salinity observation collection V2;seadatanet-north_sea-temperature_salinity_aggregated_public-v2;2015-07-31;2;2015-07-31;8a51f275-6a8a-4ac2-ba7e-fe491e63a17d;SeaDataNet Temperature and Salinity historical data collection for the North Sea contains all open access temperature and salinity in situ data retrieved from SeaDataNet infrastructure at the end of 2014. The data span between -4\u00b0W and 10\u00b0E in longitude, and from 49\u00b0N to 62\u00b0N in latitude. It covers the time period 1900-2014. Data have been quality checked using ODV software. Quality Flags of anomalous data have been revised using basic QC procedures.\n\nThe dataset is available on authenticated FTP as zip files. You can get access codes from : http://www.marine-id.org. The dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/;SeaDataNet;Royal Belgian Institute of Natural Sciences, Operational Directorate Natural Environment, Belgian Marine Data Centre;+32 (0)2 773 2111;+32 (0)2 770 6972;Gulledelle 100;Brussels;1200;Belgium;bmdc@mumm.ac.be;http://www.mumm.ac.be/datacentre/;web site;Royal Belgian Institute of Natural Sciences, Operational Directorate Natural Environment, Belgian Marine Data Centre;+32 (0)2 773 2111;+32 (0)2 770 6972;Gulledelle 100;Brussels;1200;Belgium;bmdc@mumm.ac.be;http://www.mumm.ac.be/datacentre/;web site;Royal Belgian Institute of Natural Sciences, Operational Directorate Natural Environment, Belgian Marine Data Centre;+32 (0)2 773 2111;+32 (0)2 770 6972;Gulledelle 100;Brussels;1200;Belgium;bmdc@mumm.ac.be;http://www.mumm.ac.be/datacentre/;web site;IFREMER / IDM/SISMER;+33 (0)2 98.22.49.16;+33 (0)2 98.22.46.44;Centre IFREMER de BrestBP 70;PLOUZANE;29280;France;sismer@ifremer.fr;http://www.mumm.ac.be/datacentre/;web site;Royal Belgian Institute of Natural Sciences, Operational Directorate Natural Environment, Belgian Marine Data Centre;+32 (0)2 773 2111;+32 (0)2 770 6972;Gulledelle 100;Brussels;1200;Belgium;bmdc@mumm.ac.be;http://www.mumm.ac.be/datacentre/;web site;Royal Belgian Institute of Natural Sciences, Operational Directorate Natural Environment, Belgian Marine Data Centre;+32 (0)2 773 2111;+32 (0)2 770 6972;Gulledelle 100;Brussels;1200;Belgium;bmdc@mumm.ac.be;http://www.mumm.ac.be/datacentre/;web site;IFREMER / IDM/SISMER;+33 (0)2 98.22.49.16;+33 (0)2 98.22.46.44;Centre IFREMER de Brest\nBP 70;PLOUZANE;29280;France;sismer@ifremer.fr;http://www.ifremer.fr/sismer/;web site;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=8a51f275-6a8a-4ac2-ba7e-fe491e63a17d&fname=DefaultView_0.png;Oceanographic geographical features;GEMET - INSPIRE themes, version 1.0;2009-09-22T07:57:15;Temperature of the water column;Salinity of the water column;Parameter Discovery Vocabulary (P02);2014-12-11;geonetwork.thesaurus.external.parameter.NVS.P02;ITS-90 water temperature;Water body salinity;EMODNET chemistry lot aggregated parameter names;2014-12-11;geonetwork.thesaurus.external.parameter.NVS.P35;North Sea;SeaVoX salt and fresh water body gazetteer;2014-12-11;geonetwork.thesaurus.external.reference-geographical-area.NVS.C19;Th\u00e8mes Sextant;2017-01-23;geonetwork.thesaurus.local.theme.sextant-theme;SeaDataNet licence;SeaDataNet Usage Agreement: If you use SeaDataNet data in your publications please include the following in the Acknowledgements: Data were provided through SeaDataNet Pan-European infrastructure for ocean and marine data management (https://www.seadatanet.org);No limitations on public access.  For data access please register at http://www.marine-id.org;oceans;bounding box;-4;10;49;62;1900-01-01;2014-12-31;-1200;0.0;http://dx.doi.org/10.12770/8a51f275-6a8a-4ac2-ba7e-fe491e63a17d;WWW:LINK-1.0-http--metadata-URL;DOI of the product;ftp://ftp2.ifremer.fr/public/seadatanet-north_sea-temperaturesalinity_aggregated/SDN_2015-09_TS_North_Sea_QC_done_v2.zip;WWW:DOWNLOAD-1.0-link--download;full collection dataset;zipped ODV binary collection;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_North_Sea_QC_done_v2;OGC:WMS:getCapabilities;full collection dataset;full collection dataset;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;See the referenced specification;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "6d5b80c0-f9ea-5594-922c-b580bf5cae07",
-    "notes": [
-        "SeaDataNet Temperature and Salinity historical data collection for the North Sea contains all open access temperature and salinity in situ data retrieved from SeaDataNet infrastructure at the end of 2014. The data span between -4\u00b0W and 10\u00b0E in longitude, and from 49\u00b0N to 62\u00b0N in latitude. It covers the time period 1900-2014. Data have been quality checked using ODV software. Quality Flags of anomalous data have been revised using basic QC procedures.\n\nThe dataset is available on authenticated FTP as zip files. You can get access codes from : http://www.marine-id.org. The dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/"
-    ],
-    "oai_identifier": [
-        "6d5b80c0-f9ea-5594-922c-b580bf5cae07"
-    ],
-    "oai_set": "cams1_ps",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-4,49],[-4,62],[10,62],[10,49],[-4,49]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "North Sea"
-        }
-    ],
-    "title": [
-        "North Sea - Temperature and salinity observation collection V2"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/720fc240-bde4-5a64-a104-094059168e89.json b/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/720fc240-bde4-5a64-a104-094059168e89.json
deleted file mode 100644
index eaa763ca..00000000
--- a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/720fc240-bde4-5a64-a104-094059168e89.json
+++ /dev/null
@@ -1,185 +0,0 @@
-{
-    "Contact": [
-        "sdn-userdesk@seadatanet.org"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=iso19139&identifier=720fc240-bde4-5a64-a104-094059168e89",
-    "PublicationTimestamp": "2014-12-02T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "SEADATANET",
-        "IFREMER / STATION DE LA TRINITE",
-        "IRD / CENTRE DE LA MARTINIQUE",
-        "IFREMER / DYNECO/PELAGOS-LABORATOIRE D'ECOLOGIE PELAGIQUE",
-        "Proudman Oceanographic Laboratory",
-        "IEO/ La Coruna Oceanographic Centre",
-        "Scottish Office Agriculture Environment and Fisheries Department - Aberdeen Marine Laboratory",
-        "IFREMER / IDM/SISMER",
-        "Marine Biological Association of the United Kingdom",
-        "Institute of Oceanographic Sciences, Bidston Laboratory",
-        "Institute of Marine Research (IIM-CSIC)",
-        "IHPT, Hydrographic Institute",
-        "ENEA Centro Ricerche Ambiente Marino - La Spezia",
-        "Ifremer / Crela",
-        "IRD / CENTRE OF HANN",
-        "British Oceanographic Data Centre",
-        "University of Plymouth, Institute of Marine Studies",
-        "Isle of Man Government Laboratory",
-        "IFREMER / RBE Department / Biogeochimical end Ecotoxicological Resarch Unit (Nantes)",
-        "Ministry of Agriculture, Fisheries and Food, Lowestoft Fisheries Laboratory",
-        "Swedish Meteorological and Hydrological Institute",
-        "National Oceanography Centre, Liverpool",
-        "CEREGE",
-        "P.P.Shirshov Institute of Oceanology, RAS",
-        "IFREMER / GM-MARINE GEOSCIENCES",
-        "University of Southampton School of Ocean and Earth Science",
-        "LABO ATMOSPHEREs, MILIEUX, OBSERVATIONS SPATIALES (LATMOS)",
-        "University of Rostock, Institute of Biosciences",
-        "Shom",
-        "UTM-CSIC/Marine Technology Unit",
-        "Centre for Environment, Fisheries and Aquaculture Science, Lowestoft Laboratory",
-        "Polar Scientific Research Institute of Fishery and Oceanography",
-        "Laboratory of Physical Oceanography/ UNIVERSITE DE BRETAGNE OCCIDENTALE (UBO)",
-        "Universite de Pau / IPREM multidisciplinary research institute for the environment and materials",
-        "University of Bordeaux I / Marine Biology Institut",
-        "IFREMER / STH/LBH-LABORATOIRE BIOLOGIE HALIEUTIQUE",
-        "Roscoff Marine Station, Sorbonne Universit\u00e9s, UPMC Univ Paris 06 and CNRS",
-        "Southampton Oceanography Centre",
-        "LABORATORY OF OCEANOGRAPHY of VILLEFRANCHE (LOV) / OOV",
-        "IEO/ Cadiz Oceanographic Centre",
-        "CNEVA / LAB. PATHOLOGIE ANIMAUX AQUATIQUES",
-        "IFREMER",
-        "University of Liverpool, Port Erin Marine Laboratory",
-        "IEO/ Malaga Oceanographic Centre",
-        "Institute of Earth Physics of Paris",
-        "Institute of Marine Research",
-        "Atlantic Scientific Research Institute for Marine Fishery and Oceanography",
-        "Universite D'Angers / Laboratoire Des Bio-Indicateurs Actuels Et Fossiles (Biaf)",
-        "IRD / CENTRE DE PAPEETE",
-        "IRD CENTRE DE  NOUMEA",
-        "NIOZ Royal Netherlands Institute for Sea Research",
-        "University of East Anglia, School of Environmental Sciences",
-        "LABORATORY of PHYSICAL OCEANOGRAPHY (LPO) UMR 6523 CNRS-IFREMER-IRD-UBO",
-        "Institute of Oceanographic Sciences Wormley Laboratory",
-        "IFREMER / DYNECO- Coastal Environment Dynamics department",
-        "University of Southampton Department of Oceanography",
-        "Far Eastern Regional Hydrometeorological Research Institute",
-        "IFREMER / CENTRE DE BRETAGNE",
-        "UNIVERSITE DE BRETAGNE OCCIDENTALE (UBO) / LAB. D'OCEANO. CHIMIQUE LOC - IUEM",
-        "CEA / INSTITUT DE  RADIOPROTECTION ET DE SURETE NUCLEAIRE",
-        "UNKNOWN",
-        "Ukrainian scientific center of Ecology of Sea (UkrSCES)",
-        "Dunstaffnage Marine Laboratory",
-        "Malaga University (UMA). Applied Physics departament II",
-        "IEO/ Gijon Oceanographic Centre",
-        "University of Liverpool Department of Oceanography",
-        "IFREMER STATION DE LA ROCHELLE-L'HOUMEAU",
-        "IFREMER / STATION DE LA TREMBLADE",
-        "Odessa Branch of SOI (State Oceanographic Institute)",
-        "IRD ANTENNE INSTITUT OCEANOGRAPHIQUE (IRD)",
-        "Marine Hydrophysical Institute",
-        "IEO/ Santander Oceanographic Centre",
-        "Canary Institute of Marine Sciences",
-        "IFREMER / STATION DE LORIENT",
-        "IFREMER / STATION D'ARCACHON",
-        "Fisheries Research Services, Aberdeen Marine Laboratory",
-        "German Hydrographic Institute",
-        "Oceanologic Observatory of Banyuls (University of Paris VI) / OSU",
-        "Institute of Oceanographic Sciences Deacon Laboratory",
-        "IEO/ Oceanographic Centre of Canary Island",
-        "MUSEUM NATIONAL D'HISTOIRE NATURELLE / LABORATOIRE D'OCEANOGRAPHIE PHYSIQUE",
-        "IRD / CENTRE OF ABIDJAN",
-        "Scottish Office Agriculture and Fisheries Department - Aberdeen Marine Laboratory",
-        "COM - Physical and Biogeochemical Oceanography Laboratory (LUMINY)",
-        "Department of Agriculture and Fisheries for Scotland - Aberdeen Marine Laboratory",
-        "Scottish Association for Marine Science",
-        "IFREMER / EMH-DEPARTEMENT ECOLOGIE ET MODELES POUR L'HALIEUTIQUE",
-        "IEO/ Vigo Oeanographic Centre",
-        "CEA / Laboratory of climatolocical and environmental Sciences(LSCE)",
-        "University of Cambridge Department of Earth Sciences",
-        "Marine Research Institute",
-        "CNRS / Microbiology, Geochemistry and Marine Ecology Laboratory",
-        "EPOC - Geology and Oceanography Department",
-        "National Oceanography Centre, Southampton",
-        "OGS (Istituto Nazionale di Oceanografia e di Geofisica Sperimentale), Division of Oceanography",
-        "ISTPM (IFREMER NANTES)",
-        "Marine Scotland Science",
-        "IFREMER / STATION DE SETE",
-        "Las Palmas University. Sciences of the Sea Faculty",
-        "GEOMAR Helmholtz Centre for Ocean Research Kiel",
-        "Universite de la Rochelle / Litoral Environnement et Societe (LIENSS) - UMR 7266",
-        "Scottish Marine Biological Association",
-        "Marine Institute",
-        "Aquitaine Observatory of Sciences of the Universe \u2013 University of Bordeaux (OASU)",
-        "University of Bordeaux I / IGBA Talence",
-        "IFREMER / STH-DEPARTEMENT SCIENCES ET TECHNOLOGIES HALIEUTIQUES",
-        "University of Bordeaux I / Laboratory for Physical and Toxico Chemistry (ISM)",
-        "Alfred-Wegener-Institute for Polar- and Marine Research",
-        "IRD /CENTRE DE BRETAGNE",
-        "IFREMER / Dpt Technologicals Research and Development",
-        "IFREMER / DYNECO / PHYSED -LABO PHYSIQUE HYDRODYNAMIQUE ET SEDIMENTAIRE",
-        "Defence Evaluation Research Agency",
-        "Federal Maritime and Hydrographic Agency",
-        "UNIVERSITE DE PAU / LAB.CHIMIE BIO INORGANIQUE & ENVIRONNEMENT",
-        "Laboratory of Oceanography and Climate  : Experiments and numerical Approaches - UMR 7159",
-        "IRD / CENTRE DE MONTPELLIER",
-        "IFREMER / HMMN-DEPARTEMENT HALIEUTIQUE DE MANCHE-MER DU NORD",
-        "University of Wales, School of Ocean Sciences",
-        "Plymouth Marine Laboratory",
-        "IEO/Spanish Oceanographic Institute",
-        "IFREMER / EEP / LEP-DEEP ENVIRONMENT LABORATORY"
-    ],
-    "ResourceType": "dataset",
-    "Rights": [
-        "No limitations on public access.  For data access please register at http://www.marine-id.org"
-    ],
-    "SpatialCoverage": "(10N-65N,90W-10E)",
-    "TempCoverageBegin": 59926651199,
-    "TempCoverageEnd": 63524087999,
-    "TemporalCoverage": " period : ( 1900-01-01T11:59:59Z - 2013-12-31T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1900-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2013-12-31T11:59:59Z",
-    "fulltext": "2a5c1396-f832-4500-8faa-8cfeeded1ebb;SEADATANET;sdn-userdesk@seadatanet.org;http://www.seadatanet.org/;2018-07-24T09:47:30;ISO 19115:2003/19139 - EMODNET - SDN;0.1;4;25;false;WGS 84 (EPSG 4326);EPSG;North Atlantic Ocean - Temperature and salinity observation collection V1.1;seadatanet-north_atlantic_ocean-temperature_salinity_aggregated_public-v1_1;2014-12-02;1.1;2014-12-02;2a5c1396-f832-4500-8faa-8cfeeded1ebb;SeaDataNet Temperature and Salinity historical data collection, including revised quality flags after quality control with ODV.\n\nFor data access please register at http://www.marine-id.org\n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/;SeaDataNet;IFREMER / IDM/SISMER;+33 (0)2 98.22.49.16;+33 (0)2 98.22.46.44;Centre IFREMER de BrestBP 70;PLOUZANE;29280;France;sismer@ifremer.fr;http://www.ifremer.fr/sismer/;web site;IFREMER / IDM/SISMER;+33 (0)2 98.22.49.16;+33 (0)2 98.22.46.44;Centre IFREMER de BrestBP 70;PLOUZANE;29280;France;sismer@ifremer.fr;http://www.ifremer.fr/sismer/;web site;IFREMER / STATION D'ARCACHON;05 56.83.85.60;05 56.83.89.80;IFREMER Station d'Arcachon, Quai du Commandant Silhouette;Arcachon;33120;France;None;http://www.ifremer.fr/delar;web site;Aquitaine Observatory of Sciences of the Universe \u2013 University of Bordeaux (OASU);+33 (0)5 40 00 83 50;+33(0)5 57 77 56 88;O.A.S.U. \nB\u00e2timent B18N\nAll\u00e9e Geoffroy Saint Hilaire\nCS 50023;PESSAC Cedex;33615;France;None;http://www.oasu.u-bordeaux.fr/;web site;Oceanologic Observatory of Banyuls (University of Paris VI) / OSU;+33 4 68 88 73 15;+33 4 68 88 16 99;Laboratoire Arago\nBP 44;BANYULS-SUR-MER;66651;France;None;http://www.obs-banyuls.fr/;web site;IFREMER / DYNECO- Coastal Environment Dynamics department;+33 (0)2 98.22.43.51;+33 (0)2 98 22 45.48;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;None;http://www.ifremer.fr/anglais/org/del.htm;web site;CEA / INSTITUT DE  RADIOPROTECTION ET DE SURETE NUCLEAIRE;+33(0)2 33.01.41.00;None;LABORATOIRE DE RADIOECOLOGIE MARINE,RUE MAX POL FOUCHET,BP 10;OCTEVILLE;50130;France;None;http://www.irsn.org/en/;web site;CNEVA / LAB. PATHOLOGIE ANIMAUX AQUATIQUES;+33(0)2 98.22.44.61;None;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;None;None;web site;UNKNOWN;None;None;UNKNOWN;UNKNOWN;None;Unknown;None;None;web site;IFREMER;+33(0)1 46.48.21.00;+33(0)1 46.48.22.24;Technopolis 40,155 rue J.J. Rousseau;ISSY-LES-MOULINEAUX;92138;France;communication@ifremer.fr;http://wwz.ifremer.fr;web site;IFREMER / STATION DE LA TREMBLADE;+33(0)5 46.36.18.41;+33(0)5 46.36.18.47;Mus du Loup,BP 133;LA TREMBLADE;17390;France;None;http://www.ifremer.fr/latremblade/accueilen.htm;web site;IRD / CENTRE DE LA MARTINIQUE;+33 (0)596 39 77 39;+33 (0)596 50 32 61;BP 8006;FORT DE FRANCE cedex;97259;France;representant@ird-mq.fr;http://www.mq.ird.fr/;web site;IRD / CENTRE DE MONTPELLIER;+33 (0)4 67 41 61 00;+33 (0)4 67 41 63 30;BP 64501;MONTPELLIER CEDEX 5;34394;France;montpellier@ird.fr;http://www.france-sud.ird.fr/;web site;IRD / CENTRE DE PAPEETE;(689) 50 62 00;(689) 42 95 55;Chemin de l'ahari PK 3800 - Arue,BP 529;PAPEETE (Tahiti);98713;France;dirpapet@ird.pf;http://www.polynesie.ird.fr/;web site;ISTPM (IFREMER NANTES);+33(0)2 40.37.40.00;None;rue de l'Ile d'Yeu,BP 1105;NANTES CEDEX 03;44311;France;None;None;web site;University of Bordeaux I / IGBA Talence;+33(0)5 56 80 68 00;None;351, Cours de la Liberation;TALENCE CEDEX;33405;France;None;None;web site;University of Bordeaux I / Marine Biology Institut;+33(0)4 69 82 35 36;None;351, Cours de la Liberation;TALENCE CEDEX;33405;France;None;None;web site;UNIVERSITE DE PAU / LAB.CHIMIE BIO INORGANIQUE & ENVIRONNEMENT;+33(0)5 59 40 77 50;+33(0)5 59 40 77 81;2 Avenue du President ANGOT,HELIOPARC;PAU Cedex 09;64053;France;None;None;web site;IRD / CENTRE OF ABIDJAN;(225) 24 37 79;(225) 24 65 04;Rue du Chevalier de Clieu15 \n15 BP 917;Abidjan;15;C\u00f4te d'Ivoire;rep@ird.ci;None;web site;IRD / CENTRE OF HANN;+221 849 35 35;+221 832 43 07;Route des Peres Maristes\nBP 1386;DAKAR - HANN;None;Senegal;infos@ird.sn;http://www.ird.sn/centre/index.htm;web site;Ukrainian scientific center of Ecology of Sea (UkrSCES);+38 0482 636622;+380 482  636873;89 Frantsuzsky Blvd.;Odessa;65009;Ukraine;accem@te.net.ua;http://www.sea.gov.ua;web site;OGS (Istituto Nazionale di Oceanografia e di Geofisica Sperimentale), Division of Oceanography;None;None;Borgo Grotta Gigante 42/c;Sgonico (Trieste);34010;Italy;nodc@ogs.trieste.it;http://www.ogs.trieste.it/;web site;University of Plymouth, Institute of Marine Studies;None;None;Drake Circus;Plymouth;PL4 8AA;United Kingdom;inapplicable;http://www.plymouth.ac.uk/plymouth/main.htm;web site;Institute of Marine Research;+47 55 23 85 00;+47 55 23 85 31;Nordnesgaten 50\nPostboks 1870 Nordnes;Bergen;N-5817;Norway;post@imr.no;http://www.imr.no;web site;ENEA Centro Ricerche Ambiente Marino - La Spezia;+39 0187 978258;+39 0187 978213;Forte S. Teresa\nVia S.Teresa 1;Lerici;19036;Italy;roberta.delfanti@enea.it;http://www.santateresa.enea.it;web site;Alfred-Wegener-Institute for Polar- and Marine Research;None;None;Am Handelshafen 12;Bremerhaven;D-27570;Germany;folke.mehrtens@awi.de;http://www.awi.de;web site;Isle of Man Government Laboratory;+44 (0)1624 642250;+44 (0)1624 642222;Ballakermeen Road;Douglas;IM1 4BR;United Kingdom;analyst@lab.gov.im;http://www.gov.im/dlge/enviro/govlabs/;web site;Malaga University (UMA). Applied Physics departament II;+34 952 132413/27 78;+34 952 13 24 16;Escuela Tecnica Superior de Ingenieros de Telecomunicaciones. Departamento de Fisica Aplicada II\nComplejo Tecnol\u00f3gico-Campus Teatinos;Malaga;29071;Spain;secteleco@uma.es;http://150.214.57.159/fa2.php;web site;Las Palmas University. Sciences of the Sea Faculty;+34 928 452900;+34 928 452922;Edificio Ciencias B\u00e1sicas\nCAMPUS UNIVERSITARIO DE TAFIRA\nApdo. 550;Las Palmas de Gran Canaria (Islas Canarias);35017;Spain;None;http://www.fcm.ulpgc.es;web site;University of Liverpool, Port Erin Marine Laboratory;None;None;None;Port Erin;IM9 6JA;United Kingdom;inapplicable;http://www.liv.ac.uk/www/peml/;web site;IEO/ Gijon Oceanographic Centre;+34 985 30 86 72;+34 985 32 62 77;Camino de Arbeyal, s/n;Gijon (Asturias);33212;Spain;ieogijon@gi.ieo.es;http://www.ieo.es/CoGijon/index.htm;web site;IEO/ Santander Oceanographic Centre;+34 942 291060;+34 942 275072;Promontorio San Martin, s/n\nApdo. 240;Santander;39004;Spain;ieosantander@st.ieo.es;http://www.ieo-santander.net/;web site;IEO/ La Coruna Oceanographic Centre;+34 981 205362;+34 981 229077;Muelle de las Animas, s/n\nApdo.130;A Coruna;15001;Spain;ieo.coruna@co.ieo.es;http://www.ieo.es;web site;IEO/ Vigo Oeanographic Centre;+34 986 492 111;+34 986 498 626;Cabo Estay \u2013 Canido;Vigo;36200;Spain;ieo.vigo@vi.ieo.es;http://www.vi.ieo.es/;web site;IEO/ Malaga Oceanographic Centre;+34 952 476 955;+34 952 463 808;Puerto Pesquero, s/n\nApdo. 285;Fuengirola (Malaga);29640;Spain;ieomalaga@ma.ieo.es;http://www.ieo.es;web site;IEO/ Cadiz Oceanographic Centre;+34 956 294 189;+34 956 263 556;Muelle de Levante (Puerto Pesquero)\nApdo. 2609;Puerto Real (Cadiz);11106;Spain;ignacio.sobrino@cd.ieo.es;http://www.ieo.es;web site;IFREMER / STATION DE LORIENT;+33 (0)2 97 87 38 00;+33 (0)2 97 87 38 01;8 rue Fran\u00e7ois Toullec;LORIENT;56100;France;secretariat@ifremer.fr;http://www.ifremer.fr/sth/station_lorient.htm;web site;National Oceanography Centre, Southampton;None;None;University of Southampton \nWaterfront Campus \nEuropean Way;Southampton;SO14 3ZH;United Kingdom;enquiries@noc.ac.uk;http://noc.ac.uk;web site;University of Rostock, Institute of Biosciences;+49 (0)381 498 6041;+49 (0)381 498 6042;Wismarsche Strasse 8;Rostock;18057;Germany;institut.biowissenschaften@uni-rostock.de;http://www.bio.uni-rostock.de;web site;University of Liverpool Department of Oceanography;None;None;Brownlow Hill;Liverpool;None;United Kingdom;inapplicable;None;web site;University of Southampton School of Ocean and Earth Science;+44 (0)23 8059 2011;+44 (0)23 8059 3059;National Oceanography Centre, European Way;Southampton;SO14 3ZH;United Kingdom;soes@noc.soton.ac.uk;http://www.soes.soton.ac.uk/;web site;University of Southampton School of Ocean and Earth Science;None;None;Southampton Oceanography Centre, European Way;Southampton;SO14 3ZH;United Kingdom;inapplicable;None;web site;University of Southampton Department of Oceanography;None;None;University of Southampton Waterfront Campus, European Way;Southampton;SO14 3ZH;United Kingdom;inapplicable;None;web site;University of Southampton Department of Oceanography;None;None;Highfield Campus;Southampton;SO9 5NH;United Kingdom;inapplicable;None;web site;German Hydrographic Institute;494031903420;494031905000;Bernhard-Nocht-Str. 78;Hamburg;20359;Germany;friedrich.nast;http://www.bsh.de/en/Marine_data/Hydrographic_surveys_and_wreck_search/Hydrographic_surveys/e_geschichte_sv.jsp;web site;Federal Maritime and Hydrographic Agency;+49 40 3190 0;+49 40 3190 5000;Bernhard-Nocht-Str. 78;Hamburg;20359;Germany;webmaster@bsh.de;http://www.bsh.de;web site;Universite de la Rochelle / Litoral Environnement et Societe (LIENSS) - UMR 7266;05.46.45.72.61;None;Av, Michel Cr\u00e9peau\nLAB. DE BIOLOGIE ET ENVIRONNEMENT MARIN - LBEM;LA ROCHELLE;17042;France;None;http://www.univ-lr.fr/labo/lbem/;web site;LABO ATMOSPHEREs, MILIEUX, OBSERVATIONS SPATIALES (LATMOS);+33 (0)1 39 25 49 06;+33 (0)1 39 25 49 22;Centre Universitaire de V\u00e9lizy\n10-12 Avenue de l'Europe;VELIZY;78140;France;direction@latmos.ipsl.fr;http://www.latmos.ipsl.fr/;web site;Ifremer / Crela;+33(0)5 46.50.94.40;+33(0)5 46.50.06.60;Centre de Recherche sur Ecosyst\u00e8mes Littoraux Anthropis\u00e9s\n Place du S\u00e9minaire\nBP 7;L'HOUMEAU;17137;France;None;None;web site;University of Bordeaux I / Laboratory for Physical and Toxico Chemistry (ISM);None;None;LPTC - ESA 5472 CNRS\nUniversite Bordeaux 1l'\u00e9tu\n351 Cours de la Lib\u00e9ration;TALENCE CEDEX;33405;France;None;http://www.ism.u-bordeaux1.fr/-Physico-et-Toxicochimie-de-l-.html;web site;Universite D'Angers / Laboratoire Des Bio-Indicateurs Actuels Et Fossiles (Biaf);02.41.73.53.91;02.41.73.53.52;UFR Sciences - UPRES EA 2644\n2, Bd Lavoisier;ANGERS cedex 01;49045;France;frans.jorissen@univ-angers.fr;None;web site;Universite de Pau / IPREM multidisciplinary research institute for the environment and materials;05 59 40 77 51;05 59 40 77 81;IPREM UMR 5254\nH\u00e9lioparc Pau Pyr\u00e9n\u00e9es\n2, av. Pierre Angot;PAU CEDEX 9;64053;France;olivier.donard@univ-pau.fr;http://www.iprem.org/;web site;University of Cambridge Department of Earth Sciences;None;None;Downing Street;Cambridge;CB2 3EQ;United Kingdom;jaj2@cam.ac.uk;http://www.esc.cam.ac.uk;web site;University of Wales, School of Ocean Sciences;None;None;School of Ocean Sciences,\nUniversity of Wales Bangor, \nMenai Bridge, \nAnglesey,;Menai Bridge;LL59 5AB;United Kingdom;inapplicable;http://www.sos.bangor.ac.uk/;web site;Southampton Oceanography Centre;None;None;University of Southampton \nWaterfront Campus \nEuropean Way;Southampton;SO14 3ZH;United Kingdom;inapplicable;None;web site;Scottish Office Agriculture Environment and Fisheries Department - Aberdeen Marine Laboratory;None;None;PO Box 101\n375 Victoria Road;Aberdeen;AB11 9DB;United Kingdom;inapplicable;None;web site;Scottish Office Agriculture and Fisheries Department - Aberdeen Marine Laboratory;None;None;PO Box 101\n375 Victoria Road;Aberdeen;AB11 9DB;United Kingdom;inapplicable;None;web site;Department of Agriculture and Fisheries for Scotland - Aberdeen Marine Laboratory;None;None;PO Box 101\n375 Victoria Road;Aberdeen;AB11 9DB;United Kingdom;inapplicable;None;web site;Ministry of Agriculture, Fisheries and Food, Lowestoft Fisheries Laboratory;None;None;Pakefield Road;Lowestoft;NR33 0HT;United Kingdom;inapplicable;None;web site;Institute of Oceanographic Sciences Deacon Laboratory;None;None;Brook Road\nWormley;Godalming;GU8 5UB;United Kingdom;inapplicable;None;web site;Institute of Oceanographic Sciences Wormley Laboratory;None;None;Brook Road\nWormley;Godalming;GU8 5UB;United Kingdom;inapplicable;None;web site;Proudman Oceanographic Laboratory;+44 (0)151 653 8633;+44 (0)151 653 6269;Bidston Observatory\nBidston Hill;Prenton;CH43 7RA;United Kingdom;inapplicable;http://www.pol.ac.uk;web site;Institute of Oceanographic Sciences, Bidston Laboratory;None;None;Bidston Observatory\nBidston Hill;Prenton;L43 7RA;United Kingdom;inapplicable;None;web site;Marine Scotland Science;+44 (0)1224 876544;+44 (0)1224 295511;Marine Laboratory, PO Box 101;Aberdeen;AB11 9DB;United Kingdom;inapplicable;None;web site;Defence Evaluation Research Agency;None;None;Winfrith Technology Centre;Winfrith;DT2 8XJ;United Kingdom;inapplicable;http://www.dera.gov.uk/newsite/home_2.htm;web site;National Oceanography Centre, Liverpool;+44 (0)151 795 4800;+44 (0)151 795 4801;Joseph Proudman Building, 6 Brownlow Street;Liverpool;L3 5DA;United Kingdom;enquiries@noc.ac.uk;http://noc.ac.uk;web site;UTM-CSIC/Marine Technology Unit;+34 932 309500;+34 932 309555;Paseo Maritimo de la Barceloneta, 37-49;Barcelona;08003;Spain;info@utm.csic.es;http://www.utm.csic.es/;web site;Dunstaffnage Marine Laboratory;None;None;Dunbeg;Oban;PA37 1QA;United Kingdom;inapplicable;None;web site;Scottish Marine Biological Association;None;None;Dunbeg;Oban;PA37 1QA;United Kingdom;inapplicable;None;web site;Institute of Marine Research (IIM-CSIC);+34 986231930;+34 986292762;Eduardo Cabello, 6;Vigo (Pontevedra);36208;Spain;webmaster@iim.csic.es;http://www.iim.csic.es;web site;Centre for Environment, Fisheries and Aquaculture Science, Lowestoft Laboratory;+44 (0)1502 562244;+44 (0)1502 513865;Pakefield Road;Lowestoft;NR33 OHT;United Kingdom;sarah.turner@cefas.co.uk;http://www.cefas.co.uk/;web site;GEOMAR Helmholtz Centre for Ocean Research Kiel;+49 431 600-0;+49 431 600-2805;D\u00fcsternbrooker Weg 20;Kiel;24105;Germany;info@geomar.de;http://www.geomar.de/en/;web site;IEO/ Oceanographic Centre of Canary Island;+34 922 549400;+34 922 549554;Carretera San Andr\u00e9s Km 7\nApdo. 1373;S. C. Tenerife;38180;Spain;coc@ca.ieo.es;http://www.ieo.es;web site;Canary Institute of Marine Sciences;+34 928 132900;+34 928 132908;Carretera de Taliarte, s/n.;Telde (Las Palmas de Gran Canaria);35200;Spain;None;http://www.iccm.rcanaria.es;web site;IEO/Spanish Oceanographic Institute;+34 915 107513;+34 914 135597;Corazon de Maria, 8;MADRID;28002;Spain;cedo@ieo.es;http://www.ieo.es;web site;Fisheries Research Services, Aberdeen Marine Laboratory;+44 (0)1224 876544;+44 (0)1224 295511;PO Box 101\nVictoria Road;Aberdeen;AB11 9DB;United Kingdom;inapplicable;http://www.marlab.ac.uk;web site;Marine Institute;+353-91-387200;+353-91-387201;Rinville;Oranmore;H91 R673;Ireland;datarequests@marine.ie;http://www.marine.ie;web site;British Oceanographic Data Centre;None;None;Joseph Proudman Building\n6 Brownlow Street;Liverpool;L3 5DA;United Kingdom;enquiries@bodc.ac.uk;http://www.bodc.ac.uk/;web site;Scottish Association for Marine Science;None;None;None;Argyll;PA37 1QA;United Kingdom;laurence.mee@sams.ac.uk;http://www.sams.ac.uk;web site;IRD /CENTRE DE BRETAGNE;+33 (0)2 98.22.45.01;+33(0)2 98.22.45.14;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;None;http://www.brest.ird.fr/;web site;IFREMER / DYNECO/PELAGOS-LABORATOIRE D'ECOLOGIE PELAGIQUE;+33(0)2 98 22 43 34;+33(0)2 98 22  45 98;IFREMER Centre de Brest\nBP70;PLOUZANE;29280;France;None;http://www.ifremer.fr/delec/;web site;Marine Biological Association of the United Kingdom;None;None;Citadel Hill;Plymouth;PL1 2PB;United Kingdom;sec@mba.ac.uk;http://www.mba.ac.uk/;web site;Plymouth Marine Laboratory;+44 (0)1752 633 100;+44 (0)1752 633101;Prospect Place\nThe Hoe;Plymouth;PL1 3DH;United Kingdom;forinfo@pml.ac.uk;http://www.pml.ac.uk;web site;Proudman Oceanographic Laboratory;None;None;Joseph Proudman Building\n6 Brownlow Street;Liverpool;L3 5DA;United Kingdom;inapplicable;http://www.pol.ac.uk;web site;IFREMER / EEP / LEP-DEEP ENVIRONMENT LABORATORY;+33 (0)2 98.22.43.04;+33 (0)2 98.22.47.57;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;None;http://www.ifremer.fr/droep/index.html;web site;IFREMER / GM-MARINE GEOSCIENCES;+33(0)2 98.22.42.70;+33(0)2 98.22.45.70;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;geosciences.marines@ifremer.fr;http://www.ifremer.fr/drogm/;web site;LABORATORY of PHYSICAL OCEANOGRAPHY (LPO) UMR 6523 CNRS-IFREMER-IRD-UBO;+33 (0)2 98.22.42.76;+33(0)2 98.22.44.96;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;None;http://www.ifremer.fr/lpo/;web site;LABORATORY OF OCEANOGRAPHY of VILLEFRANCHE (LOV) / OOV;+33 (0)4 93 76 38 13;+33 (0)4.93.76.38.34;UPMC/UMR 7093 \n181, chemin du Lazaret;Villefranche-sur-Mer;06230;France;lov@obs-vlfr.fr;http://www.obs-vlfr.fr;web site;Laboratory of Oceanography and Climate  : Experiments and numerical Approaches - UMR 7159;+33 (1) 44 27 32 48;+33(0)1 44 27 38 05;UMR 7159 CNRS / IRD / Universit\u00e9 Pierre et Marie Curie/MNHN\nInstitut Pierre Simon Laplace - Bo\u00eete 100\n4 Place Jussieu;Paris;75252;France;nelly.lecquyer@locean-ipsl.upmc.fr;http://www.locean-ipsl.upmc.fr/;web site;MUSEUM NATIONAL D'HISTOIRE NATURELLE / LABORATOIRE D'OCEANOGRAPHIE PHYSIQUE;+33 (0)1 40.79.31 58;+33 (0)1 40 79 31 63;43-45 rue Cuvier;PARIS CEDEX 05;75231;France;None;http://www.mnhn.fr;web site;IFREMER / DYNECO / PHYSED -LABO PHYSIQUE HYDRODYNAMIQUE ET SEDIMENTAIRE;33 (0)2 98 22 47 60;33 (0)2 98 22 45 55;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;None;http://wwz.ifremer.fr/dyneco/Equipes/Physed;web site;COM - Physical and Biogeochemical Oceanography Laboratory (LUMINY);+33(0)4 91 82 91 15;+33(0)4 91.82.65.48;UFR Centre Oceanologique de Marseille\nUMR 6535\nCampus de Luminy Case 901;Marseille cedex 9;13288;France;queguiner@com.univ-mrs.fr;http://www.com.univ-mrs.fr/LOB/;web site;IFREMER STATION DE LA ROCHELLE-L'HOUMEAU;+33 (0)5 46.50.94.40;+33 (0)5 46.50.06.50;Place du Seminaire, \nBP 7;L'HOUMEAU;17137;France;None;http://w3.ifremer.fr/francais/implant/larochel.htm;web site;Institute of Earth Physics of Paris;+33 (0)1 83 95 74 00;+33 (0)1 83 95 77 14;1, place Jussieu;PARIS CEDEX 5;75252;France;None;http://www.ipgp.jussieu.fr/;web site;IRD CENTRE DE  NOUMEA;+33 (0)1 44 27 34 67;+33 (0)1 44 27 24 01;BP A5;NOUMEA CEDEX5;98848;New Caledonia;nouvelle-caledonie@ird.fr;http://www.ird.nc/;web site;Roscoff Marine Station, Sorbonne Universit\u00e9s, UPMC Univ Paris 06 and CNRS;+33(0)2 98.29.23.23;+33 (0)2 98.29.23.24;Place Georges Teissier;ROSCOFF;29680;France;None;http://www.sb-roscoff.fr/;web site;IFREMER / RBE Department / Biogeochimical end Ecotoxicological Resarch Unit (Nantes);+33 (0)2 40 37 41 93;33(0)2 40.37.40.75;IFREMER Centre de Nantes\nRue de l'Ile d'Yeu\nBP 1105;NANTES CEDEX 03;44311;France;None;http://www.ifremer.fr/delpc/;web site;CNRS / Microbiology, Geochemistry and Marine Ecology Laboratory;+33 (0)4 91 82 92 12;+33 (0)4 91 82 96 41;Centre d'Oc\u00e9anologie de Marseille (COM)\nUMR 6117\nCampus de Luminy, Case 901;MARSEILLE CEDEX 9;13288;France;micromar@com.univ-mrs.fr;http://www.com.univ-mrs.fr/LMGEM/spip.php?rubrique1;web site;IFREMER / STATION DE LA TRINITE;+33 (0)2 97 30 19 19;+33 (0)2 97 30 19 00;12, rue des Resistants\nBP 86;LA TRINITE-SUR-MER;56470;France;None;http://www.ifremer.fr/anglais/implant/latrinit.htm;web site;IFREMER / STH/LBH-LABORATOIRE BIOLOGIE HALIEUTIQUE;+33 (0)2.97.87.38.00;+33 (0)2.97.87.38.01;IFREMER Station de Lorient\n8, rue Francois Toullec;LORIENT;56100;France;mlegall@ifremer.fr;http://wwz.ifremer.fr/lorient;web site;Shom;+33 (0)2 56.31.23.12;+33 (0)2 56.31.25.80;13, rue du Chatellier\nCS92803;BREST CEDEX 2;29228;France;seadatanet-admin@shom.fr;http://www.shom.fr/;web site;IFREMER / EMH-DEPARTEMENT ECOLOGIE ET MODELES POUR L'HALIEUTIQUE;+33(0)2 40.37.41. 67;+33(0)2 40.37.40.75;IFREMER - Centre de Nantes\nrue de l'Ile d'Yeu\nBP 21105;NANTES CEDEX 03;44311;France;None;http://www.ifremer.fr/drvecohal;web site;IFREMER / HMMN-DEPARTEMENT HALIEUTIQUE DE MANCHE-MER DU NORD;+33 (0)3 21.99.56.00;+33 (0)3 21.99.56.01;IFREMER Centre de Boulogne sur Mer\n150 quai Gambetta \nBP 70;BOULOGNE-SUR-MER CEDEX;62321;France;None;http://www.ifremer.fr/boulogne/;web site;Swedish Meteorological and Hydrological Institute;+46-(0)11-495 80 00;+46-(0)11-495 80 01;Folkborgsvagen 1;Norrkoping;SE-601 76;Sweden;shark@smhi.se;http://www.smhi.se;web site;CEA / Laboratory of climatolocical and environmental Sciences(LSCE);+33(0)1 69.82 35 23;+33(0)1 69.82.35.68;CNRS\nLSCE-Vallee, Bat.12, Avenue de la Terrasse;GIF-SUR-YVETTE CEDEX;91198;France;None;http://www.lsce.cnrs-gif.fr/;web site;UNIVERSITE DE BRETAGNE OCCIDENTALE (UBO) / LAB. D'OCEANO. CHIMIQUE LOC - IUEM;None;None;Place Nicolas Copernic;Plouzane;29280;France;None;None;web site;CEREGE;+33(0)4 42 97 15 00;+33 (0)4 42 97 15 05;Europole Mediterraneen de l'Arbois \nBP 80;Aix en Provence;13545;France;None;http://www.cerege.fr/;web site;Marine Research Institute;+354 575 2000;+354 575 2001;Skulagata 4\nP.O.Box 1390;Reykjavik;IS-121;Iceland;hafro@hafro.is;http://www.hafro.is/index_eng.php;web site;IHPT, Hydrographic Institute;+351 210943000;+351 210943299;Rua das Trinas, 49;Lisboa;1249-093;Portugal;mail@hidrografico.pt;http://www.hidrografico.pt;web site;University of East Anglia, School of Environmental Sciences;None;None;University Plain;Norwich;NR4 7TJ;United Kingdom;env.enquiries@uea.ac.uk;http://www.uea.ac.uk/env/;web site;NIOZ Royal Netherlands Institute for Sea Research;+31 222 369300;+31 222 319674;Landsdiep 4\nP.O. Box 59;Den Burg/Texel;1790 AB;Netherlands;dmg@nioz.nl;https://www.nioz.nl;web site;Atlantic Scientific Research Institute for Marine Fishery and Oceanography;8 (0112) 21-56-45;8 (0112) 21-99-97;5, Dm. Donskoi St.;Kaliningrad reg;236000;Russian Federation;atlant@baltnet.ru;http://www.atlantniro.ru/;web site;P.P.Shirshov Institute of Oceanology, RAS;+7(499)124-59-96;+7(499)124-59-83;36 Nakhimovsky prospect;Moscow;117997;Russian Federation;office@ocean.ru;http://www.ocean.ru;web site;IFREMER / STATION DE SETE;+33(0)4 99 57 32 00;+33 (0)4 99 57 32 94;Bd Jean Monnet \nBP 171;SETE CEDEX;34203;France;None;http://wwz.ifremer.fr/mediterranee/implantations/Sete;web site;Marine Hydrophysical Institute;+380 692 54 02 52;+380 692 55 42 53;2, Kapitanskaya str.;Sevastopol;99011;Ukraine;khaliulin.alexey@nodc.org.ua;http://WWW.MHI.IUF.NET;web site;Far Eastern Regional Hydrometeorological Research Institute;+7 (4232) 26-97-88;+7 (4232) 22-77-54;Fontannaya St., 24;Vladivostok;690600;Russian Federation;hydromet@online.ru;http://www.hydromet.com;web site;IFREMER / STH-DEPARTEMENT SCIENCES ET TECHNOLOGIES HALIEUTIQUES;+33 (0)2 98.22.43.66;+33 (0)2 98 22 45.47;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;None;http://www.ifremer.fr/anglais/org/drv.htm;web site;IFREMER / Dpt Technologicals Research and Development;+33(0) 2 98 22 41 41;+33(0) 2 98 22 45 35;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;Pierre.Chauchot@ifremer.fr;http://wwz.ifremer.fr/rd_technologiques;web site;IRD ANTENNE INSTITUT OCEANOGRAPHIQUE (IRD);+33 (0)1 44.32.10.70;+33 (0)1 40.51.73.16;INSTITUT OCEANOGRAPHIQUE \n195 Rue Saint Jacques;PARIS;75005;France;None;None;web site;Laboratory of Physical Oceanography/ UNIVERSITE DE BRETAGNE OCCIDENTALE (UBO);+33 (0)2 98.01.61.21;+33 (0)2 98 01 64 68;6 avenue Victor-Le-Gorgeu BP 809;BREST CEDEX;29285;France;None;http://www.univ-brest.fr/lpo/site/;web site;EPOC - Geology and Oceanography Department;+33 (0)5 40.00.88.67;+33 (0)5 56.84.08.48;351, Cours de la Liberation \nAvenue des Facultes;TALENCE;33405;France;inapplicable;http://www.epoc.u-bordeaux.fr;web site;IFREMER / CENTRE DE BRETAGNE;+33 (0)2 98.22.40.40;+33 (0)2 98.22.45.45;ZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;None;http://www.ifremer.fr/brest/;web site;Polar Scientific Research Institute of Fishery and Oceanography;None;None;6, Knipovich St.;Murmansk;183763;Russian Federation;persey@pinro.ru;http://www.pinro.ru/;web site;Odessa Branch of SOI (State Oceanographic Institute);None;None;None;Odessa;None;Ukraine;None;None;web site;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=2a5c1396-f832-4500-8faa-8cfeeded1ebb&fname=NorthAtlanticTransp.png;Oceanographic geographical features;GEMET - INSPIRE themes, version 1.0;2009-09-22T07:57:15;Temperature of the water column;Salinity of the water column;Parameter Discovery Vocabulary (P02);2014-12-11T09:56:54;ITS-90 water temperature;Water body salinity;EMODNET chemistry lot aggregated parameter names;2014-12-11;geonetwork.thesaurus.external.parameter.NVS.P35;North Atlantic Ocean;SeaVoX salt and fresh water body gazetteer;2014-12-11T09:57:21;Th\u00e8mes Sextant;2017-01-23;geonetwork.thesaurus.local.theme.sextant-theme;SeaDataNet licence;SeaDataNet Usage Agreement: If you use SeaDataNet data in your publications please include the following in the Acknowledgements: Data were provided through SeaDataNet Pan-European infrastructure for ocean and marine data management (https://www.seadatanet.org);No limitations on public access.  For data access please register at http://www.marine-id.org;oceans;bounding box;-90;10;10;65;1900-01-01;2013-12-31;-6000;0.0;http://dx.doi.org/10.12770/2a5c1396-f832-4500-8faa-8cfeeded1ebb;WWW:LINK-1.0-http--metadata-URL;DOI of the product;ftp://vftp2.ifremer.fr/public/seadatanet-north_atlantic_ocean-temperaturesalinity_aggregated/SDN_2014-03_TS_Atlantic_QC_done_v1.1.zip;WWW:DOWNLOAD-1.0-link--download;full collection dataset;zipped ODV binary collection;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_Atlantic_QC_done_v1.1;OGC:WMS:getCapabilities;full collection dataset;full collection dataset;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_Atlantic_QC_done_v1.1;OGC:WMS;SDN_2014-03_TS_Atlantic_QC_done_v1.1/Salinity;Salinity;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_Atlantic_QC_done_v1.1;OGC:WMS;SDN_2014-03_TS_Atlantic_QC_done_v1.1/Temperature;Temperature;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_Atlantic_QC_done_v1.1;OGC:WMS;SDN_2014-03_TS_Atlantic_QC_done_v1.1/Pressure;Pressure;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;See the referenced specification;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "720fc240-bde4-5a64-a104-094059168e89",
-    "notes": [
-        "SeaDataNet Temperature and Salinity historical data collection, including revised quality flags after quality control with ODV.\n\nFor data access please register at http://www.marine-id.org\n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/"
-    ],
-    "oai_identifier": [
-        "720fc240-bde4-5a64-a104-094059168e89"
-    ],
-    "oai_set": "cams1_ps",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-90,10],[-90,65],[10,65],[10,10],[-90,10]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "North Atlantic Ocean"
-        }
-    ],
-    "title": [
-        "North Atlantic Ocean - Temperature and salinity observation collection V1.1"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/8e3ec4a6-e46d-5f1e-b6a8-7d6b5c540f58.json b/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/8e3ec4a6-e46d-5f1e-b6a8-7d6b5c540f58.json
deleted file mode 100644
index 40a1966c..00000000
--- a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/8e3ec4a6-e46d-5f1e-b6a8-7d6b5c540f58.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "sdn-userdesk@seadatanet.org"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=iso19139&identifier=8e3ec4a6-e46d-5f1e-b6a8-7d6b5c540f58",
-    "PublicationTimestamp": "2018-04-23T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Alfred-Wegener-Institute for Polar- and Marine Research",
-        "Marine Institute",
-        "SEADATANET",
-        "GEOMAR Helmholtz Centre for Ocean Research Kiel",
-        "IFREMER",
-        "NIOZ Royal Netherlands Institute for Sea Research",
-        "IFREMER / IDM/SISMER",
-        "Laboratory of Oceanography and Climate : Experiments and numerical Approaches - UMR 7159",
-        "University of East Anglia, School of Environmental Sciences",
-        "Proudman Oceanographic Laboratory",
-        "Odessa Branch of SOI (State Oceanographic Institute)",
-        "Scott Polar Research Institute",
-        "Swedish Meteorological and Hydrological Institute",
-        "National Oceanography Centre, Liverpool",
-        "Institute of Marine Research",
-        "Marine Research Institute",
-        "Baltic Sea Research Institute Warnemuende (IOW)",
-        "Institute of Oceanographic Sciences Wormley Laboratory",
-        "Fisheries Research Services, Aberdeen Marine Laboratory",
-        "Shom"
-    ],
-    "ResourceType": "dataset",
-    "Rights": [
-        "No limitations on public access.  For data access please register at http://www.marine-id.org"
-    ],
-    "SpatialCoverage": "(62N-83N,43W-93E)",
-    "TempCoverageBegin": 60041131199,
-    "TempCoverageEnd": 63640119599,
-    "TemporalCoverage": " period : ( 1903-08-19T11:59:59Z - 2017-09-04T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1903-08-19T11:59:59Z",
-    "TemporalCoverage:EndDate": "2017-09-04T11:59:59Z",
-    "fulltext": "5a9df55d-0cb7-4354-acd0-221b3d5f02fe;SEADATANET;sdn-userdesk@seadatanet.org;http://www.seadatanet.org/;2018-09-26T15:48:40;ISO 19115:2003/19139 - EMODNET - SDN;0.1;WGS 84 (EPSG 4326);EPSG;Arctic Ocean - Temperature and salinity Historical Data Collection SeaDataCloud V1;SDC_ARC_DATA_TS_V1;2018-04-23;1;2018-04-23;5a9df55d-0cb7-4354-acd0-221b3d5f02fe;SeaDataCloud  Temperature  and Salinity historical data collection for the Arctic Ocean, including revised quality flags after quality control with ODV. The dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/.\n\nFor data access please register at http://www.marine-id.org/.;SeaDataNet;Institute of Marine Research;+47 55 23 85 00;+47 55 23 85 31;Nordnesgaten 50 Postboks 1870 Nordnes;Bergen;N-5817;Norway;post@imr.no;http://www.imr.no;web site;Institute of Marine Research;+47 55 23 85 00;+47 55 23 85 31;Nordnesgaten 50 Postboks 1870 Nordnes;Bergen;N-5817;Norway;post@imr.no;http://www.imr.no;web site;IFREMER / IDM/SISMER;+33 (0)2 98.22.49.16;+33 (0)2 98.22.46.44;Centre IFREMER de Brest BP 70;PLOUZANE;29280;France;sismer@ifremer.fr;http://www.ifremer.fr/sismer/;web site;Baltic Sea Research Institute Warnemuende (IOW);+49 381 5197-0;+49 381 5197 440;Seestrasse 15;Warnemuende;18119;Germany;iowinfo@io-warnemuende.de;http://www.io-warnemuende.de/;web site;IFREMER;+33(0)1 46.48.21.00;+33(0)1 46.48.22.24;Technopolis 40,155 rue J.J. Rousseau;ISSY-LES-MOULINEAUX;92138;France;communication@ifremer.fr;http://wwz.ifremer.fr;web site;Institute of Marine Research;+47 55 23 85 00;+47 55 23 85 31;Nordnesgaten 50 Postboks 1870 Nordnes;Bergen;N-5817;Norway;post@imr.no;http://www.imr.no;web site;Alfred-Wegener-Institute for Polar- and Marine Research;None;None;Am Handelshafen 12;Bremerhaven;D-27570;Germany;folke.mehrtens@awi.de;http://www.awi.de;web site;Scott Polar Research Institute;None;None;University of Cambridge Lensfield Road;Cambridge;CB2 1ER;United Kingdom;None;http://www.spri.cam.ac.uk/;web site;Institute of Oceanographic Sciences Wormley Laboratory;None;None;Brook Road Wormley;Godalming;GU8 5UB;United Kingdom;inapplicable;None;web site;Proudman Oceanographic Laboratory;+44 (0)151 653 8633;+44 (0)151 653 6269;Bidston Observatory Bidston Hill;Prenton;CH43 7RA;United Kingdom;inapplicable;http://www.pol.ac.uk;web site;National Oceanography Centre, Liverpool;+44 (0)151 795 4800;+44 (0)151 795 4801;Joseph Proudman Building, 6 Brownlow Street;Liverpool;L3 5DA;United Kingdom;enquiries@noc.ac.uk;http://noc.ac.uk;web site;GEOMAR Helmholtz Centre for Ocean Research Kiel;+49 431 600-0;+49 431 600-2805;D\u00fcsternbrooker Weg 20;Kiel;24105;Germany;info@geomar.de;http://www.geomar.de/en/;web site;Fisheries Research Services, Aberdeen Marine Laboratory;+44 (0)1224 876544;+44 (0)1224 295511;PO Box 101 Victoria Road;Aberdeen;AB11 9DB;United Kingdom;inapplicable;http://www.marlab.ac.uk;web site;Marine Institute;+353-91-387200;+353-91-387201;Rinville;Oranmore;H91 R673;Ireland;datarequests@marine.ie;http://www.marine.ie;web site;Laboratory of Oceanography and Climate : Experiments and numerical Approaches - UMR 7159;+33 (1) 44 27 32 48;+33(0)1 44 27 38 05;UMR 7159 CNRS / IRD / Universit\u00e9 Pierre et Marie Curie/MNHN Institut Pierre Simon Laplace - Bo\u00eete 100 4 Place Jussieu;Paris;75252;France;nelly.lecquyer@locean-ipsl.upmc.fr;http://www.locean-ipsl.upmc.fr/;web site;Shom;+33 (0)2 56.31.23.12;+33 (0)2 56.31.25.80;13, rue du Chatellier CS92803;BREST CEDEX 2;29228;France;seadatanet-admin@shom.fr;http://www.shom.fr/;web site;Swedish Meteorological and Hydrological Institute;+46-(0)11-495 80 00;+46-(0)11-495 80 01;Folkborgsvagen 1;Norrkoping;SE-601 76;Sweden;shark@smhi.se;http://www.smhi.se;web site;Marine Research Institute;+354 575 2000;+354 575 2001;Skulagata 4 P.O.Box 1390;Reykjavik;IS-121;Iceland;hafro@hafro.is;http://www.hafro.is/index_eng.php;web site;University of East Anglia, School of Environmental Sciences;None;None;University Plain;Norwich;NR4 7TJ;United Kingdom;env.enquiries@uea.ac.uk;http://www.uea.ac.uk/env/;web site;NIOZ Royal Netherlands Institute for Sea Research;+31 222 369300;+31 222 319674;Landsdiep 4 P.O. Box 59;Den Burg/Texel;1790 AB;Netherlands;dmg@nioz.nl;https://www.nioz.nl;web site;Odessa Branch of SOI (State Oceanographic Institute);None;None;None;Odessa;None;Ukraine;None;None;web site;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=5a9df55d-0cb7-4354-acd0-221b3d5f02fe&fname=ARCTIC_SDC_V1.png;Oceanographic geographical features;GEMET - INSPIRE themes, version 1.0;2018-07-27;geonetwork.thesaurus.external.theme.httpinspireeceuropaeutheme-theme;Temperature of the water column;Salinity of the water column;Parameter Discovery Vocabulary (P02);2017-11-17;geonetwork.thesaurus.external.parameter.NVS.P02;ITS-90 water temperature;Water body salinity;EMODNET chemistry lot aggregated parameter names;2016-09-20;geonetwork.thesaurus.external.parameter.NVS.P35;Arctic Ocean;SeaVoX salt and fresh water body gazetteer;2016-09-20;geonetwork.thesaurus.external.reference-geographical-area.NVS.C19;Th\u00e8mes Sextant;2018-05-24;geonetwork.thesaurus.local.theme.sextant-theme;SeaDataNet licence;SeaDataNet Usage Agreement: If you use SeaDataNet data in your publications please include the following in the Acknowledgements: Data were provided through SeaDataNet Pan-European infrastructure for ocean and marine data management (https://www.seadatanet.org);No limitations on public access.  For data access please register at http://www.marine-id.org;oceans;bounding box;-43;93;61.9;83;1903-08-19;2017-09-04;-4000.0;0.0;ODV binary collection;5;http://dx.doi.org/10.12770/5a9df55d-0cb7-4354-acd0-221b3d5f02fe;WWW:LINK-1.0-http--metadata-URL;DOI of the product;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;See the referenced specification;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "8e3ec4a6-e46d-5f1e-b6a8-7d6b5c540f58",
-    "notes": [
-        "SeaDataCloud  Temperature  and Salinity historical data collection for the Arctic Ocean, including revised quality flags after quality control with ODV. The dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/.\n\nFor data access please register at http://www.marine-id.org/."
-    ],
-    "oai_identifier": [
-        "8e3ec4a6-e46d-5f1e-b6a8-7d6b5c540f58"
-    ],
-    "oai_set": "cams1_ps",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-43,61.9],[-43,83],[93,83],[93,61.9],[-43,61.9]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "Arctic Ocean"
-        }
-    ],
-    "title": [
-        "Arctic Ocean - Temperature and salinity Historical Data Collection SeaDataCloud V1"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/92b9b5ab-d73b-5cca-83af-b9d9b04d5eb4.json b/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/92b9b5ab-d73b-5cca-83af-b9d9b04d5eb4.json
deleted file mode 100644
index 36bc033c..00000000
--- a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/92b9b5ab-d73b-5cca-83af-b9d9b04d5eb4.json
+++ /dev/null
@@ -1,103 +0,0 @@
-{
-    "Contact": [
-        "sdn-userdesk@seadatanet.org"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=iso19139&identifier=92b9b5ab-d73b-5cca-83af-b9d9b04d5eb4",
-    "PublicationTimestamp": "2015-07-03T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Marine Systems Institute at Tallinn University of Technology",
-        "Alfred-Wegener-Institute for Polar- and Marine Research",
-        "SEADATANET",
-        "GEOMAR Helmholtz Centre for Ocean Research Kiel",
-        "Aarhus University, Department of Bioscience, Marine Ecology Roskilde",
-        "Institute of Meteorology and Water Management National Research Institute, Maritime Branch in Gdynia (IMWM MB)",
-        "IFREMER / IDM/SISMER",
-        "NIOZ Royal Netherlands Institute for Sea Research",
-        "Odessa Branch of SOI (State Oceanographic Institute)",
-        "Department of Marine Research of the Environmental Protection Agency",
-        "Russian State Hydrometeorological University, St-Petersburg",
-        "Swedish Meteorological and Hydrological Institute",
-        "National Oceanography Centre, Liverpool",
-        "Institute of Marine Research",
-        "Finnish Institute of Marine Research (FIMR)",
-        "P.P.Shirshov Institute of Oceanology, RAS",
-        "Institute of Oceanology, Polish Academy of Sciences (IO PAS)",
-        "Umea Marine Sciences Centre, UMF",
-        "Shom",
-        "Environmental Protection Agency (EPA)",
-        "Stockholm Marine Research Centre, SMF"
-    ],
-    "ResourceType": "dataset",
-    "Rights": [
-        "No limitations on public access.  For data access please register at http://www.marine-id.org"
-    ],
-    "SpatialCoverage": "(53N-66N,10E-30E)",
-    "TempCoverageBegin": 59926651199,
-    "TempCoverageEnd": 63555623999,
-    "TemporalCoverage": " period : ( 1900-01-01T11:59:59Z - 2014-12-31T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1900-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2014-12-31T11:59:59Z",
-    "fulltext": "1610aa44-0436-4b53-b220-98e10f17a2d4;SEADATANET;sdn-userdesk@seadatanet.org;http://www.seadatanet.org/;2018-07-24T09:47:28;ISO 19115:2003/19139 - EMODNET - SDN;0.1;4;23;false;WGS 84 (EPSG 4326);EPSG;Baltic Sea  - Temperature and salinity observation collection V2;seadatanet-baltic_sea-temperature_salinity_aggregated_public-v2;2015-07-03;2.0;2015-07-03;1610aa44-0436-4b53-b220-98e10f17a2d4;SeaDataNet Temperature and Salinity historical data collection for the Baltic Sea contains all open access temperature and salinity in situ data retrieved from SeaDataNet infrastructure at the end of 2014.\nData have been quality checked using ODV software. Quality Flags of anomalous data have been revised using basic QC procedures.\nThe dataset is available on authenticated FTP as zip files. You can get access codes from: http://www.marine-id.org. The dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/\n\nFor data access please register at http://www.marine-id.org;SeaDataNet;Swedish Meteorological and Hydrological Institute;+46-(0)11-495 80 00;+46-(0)11-495 80 01;Folkborgsvagen 1;Norrkoping;SE-601 76;Sweden;shark@smhi.se;http://www.smhi.se;web site;Swedish Meteorological and Hydrological Institute;+46-(0)11-495 80 00;+46-(0)11-495 80 01;Folkborgsvagen 1;Norrkoping;SE-601 76;Sweden;shark@smhi.se;http://www.smhi.se;web site;IFREMER / IDM/SISMER;+33 (0)2 98.22.49.16;+33 (0)2 98.22.46.44;Centre IFREMER de Brest\nBP 70;PLOUZANE;29280;France;sismer@ifremer.fr;http://www.ifremer.fr/sismer/;web site;Institute of Marine Research;+47 55 23 85 00;+47 55 23 85 31;Nordnesgaten 50\nPostboks 1870 Nordnes;Bergen;N-5817;Norway;post@imr.no;http://www.imr.no;web site;Alfred-Wegener-Institute for Polar- and Marine Research;None;None;Am Handelshafen 12;Bremerhaven;D-27570;Germany;folke.mehrtens@awi.de;http://www.awi.de;web site;Institute of Meteorology and Water Management National Research Institute, Maritime Branch in Gdynia (IMWM MB);+48-58-62-88-100;+48-58-62-88-163;Waszyngtona 42;Gdynia;81-342;Poland;None;http://www.baltyk.pogodynka.pl/;web site;Institute of Oceanology, Polish Academy of Sciences (IO PAS);+48 58 551 72 81;+48 58 551 21 30;Powstancow Warszawy 55;Sopot;81-712;Poland;smas@iopan.gda.pl;http://www.iopan.gda.pl/;web site;Environmental Protection Agency (EPA);None;None;Juozapaviciaus st. 9;Vilnius;LT-09311;Lithuania;aaa@aaa.am.lt;http://www.gamta.lt;web site;National Oceanography Centre, Liverpool;+44 (0)151 795 4800;+44 (0)151 795 4801;Joseph Proudman Building, 6 Brownlow Street;Liverpool;L3 5DA;United Kingdom;enquiries@noc.ac.uk;http://noc.ac.uk;web site;GEOMAR Helmholtz Centre for Ocean Research Kiel;+49 431 600-0;+49 431 600-2805;D\u00fcsternbrooker Weg 20;Kiel;24105;Germany;info@geomar.de;http://www.geomar.de/en/;web site;Shom;+33 (0)2 56.31.23.12;+33 (0)2 56.31.25.80;13, rue du Chatellier\nCS92803;BREST CEDEX 2;29228;France;seadatanet-admin@shom.fr;http://www.shom.fr/;web site;Swedish Meteorological and Hydrological Institute;+46-(0)11-495 80 00;+46-(0)11-495 80 01;Folkborgsvagen 1;Norrkoping;SE-601 76;Sweden;shark@smhi.se;http://www.smhi.se;web site;Stockholm Marine Research Centre, SMF;+46 (0)8-16 37 18;None;Svante Arrhenius V\u00e4g 21B\nFrescati Backe;Stockholm;SE-114 18;Sweden;smf@smf.su.se;http://www.smf.su.se;web site;Umea Marine Sciences Centre, UMF;+46 (0)90-786 79 74;+46 (0)90-786 99 75;Norrbyn;H\u00f6rnefors;SE-910 20;Sweden;info@umf.umu.se;http://www.umf.umu.se/;web site;Finnish Institute of Marine Research (FIMR);+358 9 613 941;+358 9 323 2970;Erik Palm\u00e9nin aukio 1\nP.O.Box 2;Helsinki;00561;Finland;None;http://www.fimr.fi/en/en_GB/en/;web site;NIOZ Royal Netherlands Institute for Sea Research;+31 222 369300;+31 222 319674;Landsdiep 4\nP.O. Box 59;Den Burg/Texel;1790 AB;Netherlands;dmg@nioz.nl;https://www.nioz.nl;web site;Department of Marine Research of the Environmental Protection Agency;+370 46 41 04 50;+370 46 41 04 60;Taikos Av. 26;Klaipeda;LT-91149;Lithuania;jtd@aaa.am.lt;http://www.gamta.lt/;web site;P.P.Shirshov Institute of Oceanology, RAS;+7(499)124-59-96;+7(499)124-59-83;36 Nakhimovsky prospect;Moscow;117997;Russian Federation;office@ocean.ru;http://www.ocean.ru;web site;Marine Systems Institute at Tallinn University of Technology;+372 6204300;None;MSI, Akadeemia tee 15a;Tallinn;12618;Estonia;msi@msi.ttu.ee;http://www.msi.ttu.ee;web site;Aarhus University, Department of Bioscience, Marine Ecology Roskilde;+45 8715000;+45 87154326;399 Frederiksborgvej\nP.O. Box 358;Roskilde;DK-4000;Denmark;None;http://bios.au.dk/en/;web site;Russian State Hydrometeorological University, St-Petersburg;None;None;98, Maloohtinsky Pr.;St.-Petersburg;195196;Russian Federation;rector@rshu.ru;http://www.rshi.nw.ru/win/home-ru.htm;web site;Odessa Branch of SOI (State Oceanographic Institute);None;None;None;Odessa;None;Ukraine;None;None;web site;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=1610aa44-0436-4b53-b220-98e10f17a2d4&fname=map2.png;Oceanographic geographical features;GEMET - INSPIRE themes, version 1.0;2009-09-22T07:57:15;Temperature of the water column;Salinity of the water column;external.parameter.NVS.P02;2014-11-12T15:04:00;ITS-90 water temperature;Water body salinity;EMODNET chemistry lot aggregated parameter names;2014-12-11;geonetwork.thesaurus.external.parameter.NVS.P35;Baltic Sea;Bay of Bothnia;Central Baltic Sea;Gulf of Bothnia;Gulf of Finland;Kattegat;Lillebaelt;Skagerrak;Storebaelt;external.reference-geographical-area.NVS.C19;2014-11-12T15:05:00;Th\u00e8mes Sextant;2017-01-23;geonetwork.thesaurus.local.theme.sextant-theme;SeaDataNet licence;SeaDataNet Usage Agreement: If you use SeaDataNet data in your publications please include the following in the Acknowledgements: Data were provided through SeaDataNet Pan-European infrastructure for ocean and marine data management (https://www.seadatanet.org);No limitations on public access.  For data access please register at http://www.marine-id.org;oceans;bounding box;10;30;53;66.5;1900-01-01;2014-12-31;-500.0;0.0;http://dx.doi.org/10.12770/1610aa44-0436-4b53-b220-98e10f17a2d4;WWW:LINK-1.0-http--metadata-URL;DOI of the product;ftp://vftp2.ifremer.fr/public/seadatanet-baltic_sea-temperaturesalinity_aggregated/SDN_2015-09_TS_BalticSea_QC_done_v2.zip;WWW:DOWNLOAD-1.0-link--download;full collection dataset;zipped ODV binary collection;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_BalticSea_QC_done_v2;OGC:WMS:getCapabilities;full collection dataset;full collection dataset;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_BalticSea_QC_done_v2;OGC:WMS;SDN_2015-09_TS_BalticSea_QC_done_v2/ITS-90_water_temperature;Temperature;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_BalticSea_QC_done_v2;OGC:WMS;SDN_2015-09_TS_BalticSea_QC_done_v2/Water_body_salinity;Salinity;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_BalticSea_QC_done_v2;OGC:WMS;SDN_2015-09_TS_BalticSea_QC_done_v2/*;Observation collection;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;See the referenced specification;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "92b9b5ab-d73b-5cca-83af-b9d9b04d5eb4",
-    "notes": [
-        "SeaDataNet Temperature and Salinity historical data collection for the Baltic Sea contains all open access temperature and salinity in situ data retrieved from SeaDataNet infrastructure at the end of 2014.\nData have been quality checked using ODV software. Quality Flags of anomalous data have been revised using basic QC procedures.\nThe dataset is available on authenticated FTP as zip files. You can get access codes from: http://www.marine-id.org. The dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/\n\nFor data access please register at http://www.marine-id.org"
-    ],
-    "oai_identifier": [
-        "92b9b5ab-d73b-5cca-83af-b9d9b04d5eb4"
-    ],
-    "oai_set": "cams1_ps",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[10,53],[10,66.5],[30,66.5],[30,53],[10,53]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "Baltic Sea"
-        },
-        {
-            "name": "Bay Bothnia"
-        },
-        {
-            "name": "Central Baltic Sea"
-        },
-        {
-            "name": "Gulf Bothnia"
-        },
-        {
-            "name": "Gulf Finland"
-        },
-        {
-            "name": "Kattegat"
-        },
-        {
-            "name": "Lillebaelt"
-        }
-    ],
-    "title": [
-        "Baltic Sea  - Temperature and salinity observation collection V2"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/a268b804-7fe9-5bc8-9ab7-14a27cf4c435.json b/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/a268b804-7fe9-5bc8-9ab7-14a27cf4c435.json
deleted file mode 100644
index 1b3d0526..00000000
--- a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/a268b804-7fe9-5bc8-9ab7-14a27cf4c435.json
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-    "Contact": [
-        "sdn-userdesk@seadatanet.org"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=iso19139&identifier=a268b804-7fe9-5bc8-9ab7-14a27cf4c435",
-    "PublicationTimestamp": "2015-09-14T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Institute of Marine Sciences, Middle East Technical University",
-        "SEADATANET",
-        "IFREMER / IDM / SISMER - Scientific Information Systems for the SEA"
-    ],
-    "ResourceType": "dataset",
-    "Rights": [
-        "No limitations on public access.  For data access please register at http://www.marine-id.org"
-    ],
-    "SpatialCoverage": "(40N-48N,28E-42E)",
-    "TempCoverageBegin": 58931323199,
-    "TempCoverageEnd": 63550007999,
-    "TemporalCoverage": " period : ( 1868-06-17T11:59:59Z - 2014-10-27T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1868-06-17T11:59:59Z",
-    "TemporalCoverage:EndDate": "2014-10-27T11:59:59Z",
-    "fulltext": "227e9f7b-ddfc-4004-b0e5-f4785d36d43f;SEADATANET;sdn-userdesk@seadatanet.org;http://www.seadatanet.org/;2018-07-24T09:47:49;ISO 19115:2003/19139 - EMODNET - SDN;0.1;4;0;0;false;WGS 84 (EPSG 4326);EPSG;Black Sea - Temperature and salinity observation collection V2;SEADATANET_Black_Sea-temperature_salinity_aggregated_public-v2;2015-09-14;2.0;2015-09-14;227e9f7b-ddfc-4004-b0e5-f4785d36d43f;The Black Sea historical dataset includes all open access temperature and salinity in situ data from the Black Sea and Sea of Azov for period 1868-2014. The data were retrieved from the SeaDataNet infrastructure in the mid of 2015. Data quality has been analysed and checked using ODV software. Quality Flags of anomalous data have been revised using different QC procedures in conjunction with the visual expert check. Duplicates have been identified and excluded from the dataset.\n\nData providers are:\n- Institute of Fishery Resources (IFR)\n- Institute of Biodiversity and Ecosystem Research, Bulgarian Academy of Sciences\n- Hellenic Centre for Marine Research, Hellenic National Oceanographic Data Centre (HCMR/HNODC)\n- IFREMER / IDM / SISMER - Scientific Information Systems for the SEA\n- SHOM (SERVICE HYDROGRAPHIQUE ET OCEANOGRAPHIQUE DE LA MARINE)\n- All-Russia Research Institute of Hydrometeorological Information - World Data Centre (RIHMI-WDC) National Oceanographic Data Centre (NODC)\n- P.P.Shirshov Institute of Oceanology, RAS\n- Bulgarian National Oceanographic Data Centre(BGODC), Institute of Oceanology\n- Iv.Javakhishvili Tbilisi State University, Centre of Relations with UNESCO Oceanological Research Centre and GeoDNA (UNESCO)\n- National Institute for Marine Research and Development \"Grigore Antipa\"\n- Marine Hydrophysical Institute\n- Department of Navigation and Hydrography and Oceanography, Turkish Navy\n- Karadeniz Technical University, Faculty of Marine Sciences\n- Sinop University, Fisheries Faculty\n- Istanbul University, Institute of Marine Science and Management\n- Institute of Biology of the Southern Seas\n- Marine branch of Ukrainian Hydrometeorological Institute\n- Scientific - Research Firm \"GAMMA\"\n- National Environmental Agency of the Ministry of Environment Protection and Natural Resources\n\nFor data access, please regsiter at http://www.marine-id.org\n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/;SeaDataNet;IFREMER / IDM / SISMER - Scientific Information Systems for the SEA;+33 (0)2 98.22.49.16;+33 (0)2 98.22.46.44;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;sismer@ifremer.fr;http://www.ifremer.fr/sismer/;web site;Institute of Marine Sciences, Middle East Technical University;+90 (324) 5212406;+90 (324) 5212327;P.O.Box 28;Erdemli;33731;Turkey;volodymyr@ims.metu.edu.tr; devrim@ims.metu.edu.tr;http://www.ims.metu.edu.tr;web site;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=227e9f7b-ddfc-4004-b0e5-f4785d36d43f&fname=DefaultView_0.png;Oceanographic geographical features;GEMET - INSPIRE themes, version 1.0;2009-09-22T07:57:15;Temperature of the water column;Salinity of the water column;Parameter Discovery Vocabulary (P02);2014-12-11;geonetwork.thesaurus.external.parameter.NVS.P02;ITS-90 water temperature;Water body salinity;EMODNET chemistry lot aggregated parameter names;2014-12-11;geonetwork.thesaurus.external.parameter.NVS.P35;Black Sea;SeaVoX salt and fresh water body gazetteer;2014-12-11;geonetwork.thesaurus.external.reference-geographical-area.NVS.C19;Th\u00e8mes Sextant;2017-01-23;geonetwork.thesaurus.local.theme.sextant-theme;SeaDataNet licence;SeaDataNet Usage Agreement: If you use SeaDataNet data in your publications please include the following in the Acknowledgements: Data were provided through SeaDataNet Pan-European infrastructure for ocean and marine data management (https://www.seadatanet.org);No limitations on public access.  For data access please register at http://www.marine-id.org;oceans;bounding box;27.5;42;40.5;47.5;1868-06-17;2014-10-27;-2200.0;0.0;http://dx.doi.org/10.12770/227e9f7b-ddfc-4004-b0e5-f4785d36d43f;WWW:LINK-1.0-http--metadata-URL;DOI of the product;ftp://vftp2.ifremer.fr/public/seadatanet-black_sea-temperaturesalinity_aggregated/SDN_2015-09_TS_BlackSea_QC_done_v2.zip;WWW:DOWNLOAD-1.0-link--download;SDN_2015-09_TS_BlackSea_QC_done_v2;zipped ODV binary collection;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_Black_Sea_QC_done_v2;OGC:WMS:getCapabilities;full dataset;full datasets;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_Black_Sea_QC_done_v2;OGC:WMS;SDN_2015-09_TS_Black_Sea_QC_done_v2/ITS-90_water_temperature;Temperature;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_Black_Sea_QC_done_v2;OGC:WMS;SDN_2015-09_TS_Black_Sea_QC_done_v2/Water_body_salinity;Salinity;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_Black_Sea_QC_done_v2;OGC:WMS;SDN_2015-09_TS_Black_Sea_QC_done_v2/*;Observation locations;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;See the referenced specification;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "a268b804-7fe9-5bc8-9ab7-14a27cf4c435",
-    "notes": [
-        "The Black Sea historical dataset includes all open access temperature and salinity in situ data from the Black Sea and Sea of Azov for period 1868-2014. The data were retrieved from the SeaDataNet infrastructure in the mid of 2015. Data quality has been analysed and checked using ODV software. Quality Flags of anomalous data have been revised using different QC procedures in conjunction with the visual expert check. Duplicates have been identified and excluded from the dataset.\n\nData providers are:\n- Institute of Fishery Resources (IFR)\n- Institute of Biodiversity and Ecosystem Research, Bulgarian Academy of Sciences\n- Hellenic Centre for Marine Research, Hellenic National Oceanographic Data Centre (HCMR/HNODC)\n- IFREMER / IDM / SISMER - Scientific Information Systems for the SEA\n- SHOM (SERVICE HYDROGRAPHIQUE ET OCEANOGRAPHIQUE DE LA MARINE)\n- All-Russia Research Institute of Hydrometeorological Information - World Data Centre (RIHMI-WDC) National Oceanographic Data Centre (NODC)\n- P.P.Shirshov Institute of Oceanology, RAS\n- Bulgarian National Oceanographic Data Centre(BGODC), Institute of Oceanology\n- Iv.Javakhishvili Tbilisi State University, Centre of Relations with UNESCO Oceanological Research Centre and GeoDNA (UNESCO)\n- National Institute for Marine Research and Development \"Grigore Antipa\"\n- Marine Hydrophysical Institute\n- Department of Navigation and Hydrography and Oceanography, Turkish Navy\n- Karadeniz Technical University, Faculty of Marine Sciences\n- Sinop University, Fisheries Faculty\n- Istanbul University, Institute of Marine Science and Management\n- Institute of Biology of the Southern Seas\n- Marine branch of Ukrainian Hydrometeorological Institute\n- Scientific - Research Firm \"GAMMA\"\n- National Environmental Agency of the Ministry of Environment Protection and Natural Resources\n\nFor data access, please regsiter at http://www.marine-id.org\n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/"
-    ],
-    "oai_identifier": [
-        "a268b804-7fe9-5bc8-9ab7-14a27cf4c435"
-    ],
-    "oai_set": "cams1_ps",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[27.5,40.5],[27.5,47.5],[42,47.5],[42,40.5],[27.5,40.5]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "Black Sea"
-        }
-    ],
-    "title": [
-        "Black Sea - Temperature and salinity observation collection V2"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/a3724d56-b446-523c-beb6-eb0f9df1f8db.json b/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/a3724d56-b446-523c-beb6-eb0f9df1f8db.json
deleted file mode 100644
index 334e3102..00000000
--- a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/a3724d56-b446-523c-beb6-eb0f9df1f8db.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "sdn-userdesk@seadatanet.org"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=iso19139&identifier=a3724d56-b446-523c-beb6-eb0f9df1f8db",
-    "PublicationTimestamp": "2015-09-16T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "Alfred-Wegener-Institute for Polar- and Marine Research",
-        "Marine Institute",
-        "Baltic Sea Research Institute Warnemuende (IOW)",
-        "GEOMAR Helmholtz Centre for Ocean Research Kiel",
-        "University of East Anglia, School of Environmental Sciences",
-        "IFREMER",
-        "NIOZ Royal Netherlands Institute for Sea Research",
-        "IFREMER / IDM / SISMER - Scientific Information Systems for the SEA",
-        "Proudman Oceanographic Laboratory",
-        "Odessa Branch of SOI (State Oceanographic Institute)",
-        "Scott Polar Research Institute",
-        "Swedish Meteorological and Hydrological Institute",
-        "Laboratory of Oceanography and Climate  : Experiments and numerical Approaches - UMR 7159",
-        "National Oceanography Centre, Liverpool",
-        "Institute of Marine Research",
-        "Marine Research Institute",
-        "SEADATANET",
-        "Institute of Oceanographic Sciences Wormley Laboratory",
-        "Fisheries Research Services, Aberdeen Marine Laboratory",
-        "Shom"
-    ],
-    "ResourceType": "dataset",
-    "Rights": [
-        "No limitations on public access.  For data access please register at http://www.marine-id.org"
-    ],
-    "SpatialCoverage": "(65N-82N,40W-65E)",
-    "TempCoverageBegin": 59926651199,
-    "TempCoverageEnd": 63555623999,
-    "TemporalCoverage": " period : ( 1900-01-01T11:59:59Z - 2014-12-31T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1900-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2014-12-31T11:59:59Z",
-    "fulltext": "7d2ed029-4f81-48b3-92f3-0e50ead8e964;SEADATANET;sdn-userdesk@seadatanet.org;http://www.seadatanet.org/;2018-07-24T09:47:31;ISO 19115:2003/19139 - EMODNET - SDN;0.1;4;28;1;false;WGS 84 (EPSG 4326);EPSG;Arctic Ocean - Temperature and Salinity Climatology V1.1;seadatanet-arctic_ocean-climatology_public;2015-09-16;1.1;2015-09-16;7d2ed029-4f81-48b3-92f3-0e50ead8e964;Climatology done from the SeaDataNet aggregated dataset v1.1 for the North Arctic Ocean. The version used for the DIVA software is the 4.6.10 (prerelease 4.6.11). The period covers 1900-2013.\n\nFor data access please register at http://www.marine-id.org;SeaDataNet;Institute of Marine Research;+47 55 23 85 00;+47 55 23 85 31;Nordnesgaten 50\nPostboks 1870 Nordnes;Bergen;N-5817;Norway;post@imr.no;http://www.imr.no;web site;IFREMER / IDM / SISMER - Scientific Information Systems for the SEA;+33 (0)2 98.22.49.16;+33 (0)2 98.22.46.44;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;sismer@ifremer.fr;http://www.ifremer.fr/sismer/;web site;Baltic Sea Research Institute Warnemuende (IOW);+49 381 5197-0;+49 381 5197 440;Seestrasse 15;Warnemuende;18119;Germany;iowinfo@io-warnemuende.de;http://www.io-warnemuende.de/;web site;IFREMER;+33(0)1 46.48.21.00;+33(0)1 46.48.22.24;Technopolis 40,155 rue J.J. Rousseau;ISSY-LES-MOULINEAUX;92138;France;communication@ifremer.fr;http://wwz.ifremer.fr;web site;Institute of Marine Research;+47 55 23 85 00;+47 55 23 85 31;Nordnesgaten 50\nPostboks 1870 Nordnes;Bergen;N-5817;Norway;post@imr.no;http://www.imr.no;web site;Alfred-Wegener-Institute for Polar- and Marine Research;None;None;Am Handelshafen 12;Bremerhaven;D-27570;Germany;folke.mehrtens@awi.de;http://www.awi.de;web site;Scott Polar Research Institute;None;None;University of Cambridge\nLensfield Road;Cambridge;CB2 1ER;United Kingdom;None;http://www.spri.cam.ac.uk/;web site;Institute of Oceanographic Sciences Wormley Laboratory;None;None;Brook Road\nWormley;Godalming;GU8 5UB;United Kingdom;inapplicable;None;web site;Proudman Oceanographic Laboratory;+44 (0)151 653 8633;+44 (0)151 653 6269;Bidston Observatory\nBidston Hill;Prenton;CH43 7RA;United Kingdom;inapplicable;http://www.pol.ac.uk;web site;National Oceanography Centre, Liverpool;+44 (0)151 795 4800;+44 (0)151 795 4801;Joseph Proudman Building, 6 Brownlow Street;Liverpool;L3 5DA;United Kingdom;enquiries@noc.ac.uk;http://noc.ac.uk;web site;GEOMAR Helmholtz Centre for Ocean Research Kiel;+49 431 600-0;+49 431 600-2805;D\u00fcsternbrooker Weg 20;Kiel;24105;Germany;info@geomar.de;http://www.geomar.de/en/;web site;Fisheries Research Services, Aberdeen Marine Laboratory;+44 (0)1224 876544;+44 (0)1224 295511;PO Box 101\nVictoria Road;Aberdeen;AB11 9DB;United Kingdom;inapplicable;http://www.marlab.ac.uk;web site;Marine Institute;+353-91-387200;+353-91-387201;Rinville;Oranmore;H91 R673;Ireland;datarequests@marine.ie;http://www.marine.ie;web site;Laboratory of Oceanography and Climate  : Experiments and numerical Approaches - UMR 7159;+33 (1) 44 27 32 48;+33(0)1 44 27 38 05;UMR 7159 CNRS / IRD / Universit\u00e9 Pierre et Marie Curie/MNHN\nInstitut Pierre Simon Laplace - Bo\u00eete 100\n4 Place Jussieu;Paris;75252;France;nelly.lecquyer@locean-ipsl.upmc.fr;http://www.locean-ipsl.upmc.fr/;web site;Shom;+33 (0)2 56.31.23.12;+33 (0)2 56.31.25.80;13, rue du Chatellier\nCS92803;BREST CEDEX 2;29228;France;seadatanet-admin@shom.fr;http://www.shom.fr/;web site;Swedish Meteorological and Hydrological Institute;+46-(0)11-495 80 00;+46-(0)11-495 80 01;Folkborgsvagen 1;Norrkoping;SE-601 76;Sweden;shark@smhi.se;http://www.smhi.se;web site;Marine Research Institute;+354 575 2000;+354 575 2001;Skulagata 4\nP.O.Box 1390;Reykjavik;IS-121;Iceland;hafro@hafro.is;http://www.hafro.is/index_eng.php;web site;University of East Anglia, School of Environmental Sciences;None;None;University Plain;Norwich;NR4 7TJ;United Kingdom;env.enquiries@uea.ac.uk;http://www.uea.ac.uk/env/;web site;NIOZ Royal Netherlands Institute for Sea Research;+31 222 369300;+31 222 319674;Landsdiep 4\nP.O. Box 59;Den Burg/Texel;1790 AB;Netherlands;dmg@nioz.nl;https://www.nioz.nl;web site;Odessa Branch of SOI (State Oceanographic Institute);None;None;None;Odessa;None;Ukraine;None;None;web site;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=7d2ed029-4f81-48b3-92f3-0e50ead8e964&fname=Screenshot%20from%202015-11-30%2017:44:33.png;Oceanographic geographical features;GEMET - INSPIRE themes, version 1.0;2009-09-22T07:57:15;Temperature of the water column;Salinity of the water column;Parameter Discovery Vocabulary (P02);2014-12-11;geonetwork.thesaurus.external.parameter.NVS.P02;ITS-90 water temperature;Water body salinity;EMODNET chemistry lot aggregated parameter names;2014-12-11;geonetwork.thesaurus.external.parameter.NVS.P35;Arctic Ocean;SeaVoX salt and fresh water body gazetteer;2014-12-11;geonetwork.thesaurus.external.reference-geographical-area.NVS.C19;Th\u00e8mes Sextant;2017-01-23;geonetwork.thesaurus.local.theme.sextant-theme;SeaDataNet licence;SeaDataNet Usage Agreement: If you use SeaDataNet data in your publications please include the following in the Acknowledgements: Data were provided through SeaDataNet Pan-European infrastructure for ocean and marine data management (https://www.seadatanet.org);No limitations on public access.  For data access please register at http://www.marine-id.org;0.2;oceans;bounding box;-40;65;65;82;1900-01-01;2014-12-31;-3000.0;0.0;ftp://ftp2.ifremer.fr/public/seadatanet-arctic_ocean-temperaturesalinity_climatologie/SDN_2015-11_TS_Arctic_Climatology_v1.1.zip;WWW:DOWNLOAD-1.0-link--download;full dataset, netcdf files;full dataset, netcdf files;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms;OGC:WMS:getCapabilities;full dataset;full dataset;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms;OGC:WMS;Arctic/Salinity.19002014.4Danl.nc*Salinity_deepest_L1;Deepest values of Salinity masked using relative error threshold 0.3;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms;OGC:WMS;Arctic/Salinity.19002014.4Danl.nc*Salinity_deepest_L2;Deepest values of Salinity masked using relative error threshold 0.5;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms;OGC:WMS;Arctic/Temperature.19002014.4Danl.nc*Temperature_L1;Temperature masked using relative error threshold 0.3;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms;OGC:WMS;Arctic/Temperature.19002014.4Danl.nc*Temperature_L2;Temperature masked using relative error threshold 0.5;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;See the referenced specification;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "a3724d56-b446-523c-beb6-eb0f9df1f8db",
-    "notes": [
-        "Climatology done from the SeaDataNet aggregated dataset v1.1 for the North Arctic Ocean. The version used for the DIVA software is the 4.6.10 (prerelease 4.6.11). The period covers 1900-2013.\n\nFor data access please register at http://www.marine-id.org"
-    ],
-    "oai_identifier": [
-        "a3724d56-b446-523c-beb6-eb0f9df1f8db"
-    ],
-    "oai_set": "cams1_ps",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-40,65],[-40,82],[65,82],[65,65],[-40,65]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "Arctic Ocean"
-        }
-    ],
-    "title": [
-        "Arctic Ocean - Temperature and Salinity Climatology V1.1"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/aac8799c-93c8-57bf-a5af-41f14fd1dbd3.json b/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/aac8799c-93c8-57bf-a5af-41f14fd1dbd3.json
deleted file mode 100644
index df401412..00000000
--- a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/aac8799c-93c8-57bf-a5af-41f14fd1dbd3.json
+++ /dev/null
@@ -1,185 +0,0 @@
-{
-    "Contact": [
-        "sdn-userdesk@seadatanet.org"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=iso19139&identifier=aac8799c-93c8-57bf-a5af-41f14fd1dbd3",
-    "PublicationTimestamp": "2015-07-23T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "SEADATANET",
-        "IFREMER / STATION DE LA TRINITE",
-        "IRD / CENTRE DE LA MARTINIQUE",
-        "IFREMER / DYNECO/PELAGOS-LABORATOIRE D'ECOLOGIE PELAGIQUE",
-        "Proudman Oceanographic Laboratory",
-        "IEO/ La Coruna Oceanographic Centre",
-        "Scottish Office Agriculture Environment and Fisheries Department - Aberdeen Marine Laboratory",
-        "IFREMER / IDM/SISMER",
-        "Marine Biological Association of the United Kingdom",
-        "Institute of Oceanographic Sciences, Bidston Laboratory",
-        "Institute of Marine Research (IIM-CSIC)",
-        "IHPT, Hydrographic Institute",
-        "ENEA Centro Ricerche Ambiente Marino - La Spezia",
-        "Ifremer / Crela",
-        "IRD / CENTRE OF HANN",
-        "British Oceanographic Data Centre",
-        "University of Plymouth, Institute of Marine Studies",
-        "Isle of Man Government Laboratory",
-        "IFREMER / RBE Department / Biogeochimical end Ecotoxicological Resarch Unit (Nantes)",
-        "Ministry of Agriculture, Fisheries and Food, Lowestoft Fisheries Laboratory",
-        "Swedish Meteorological and Hydrological Institute",
-        "National Oceanography Centre, Liverpool",
-        "CEREGE",
-        "P.P.Shirshov Institute of Oceanology, RAS",
-        "IFREMER / GM-MARINE GEOSCIENCES",
-        "University of Southampton School of Ocean and Earth Science",
-        "LABO ATMOSPHEREs, MILIEUX, OBSERVATIONS SPATIALES (LATMOS)",
-        "University of Rostock, Institute of Biosciences",
-        "Shom",
-        "UTM-CSIC/Marine Technology Unit",
-        "Centre for Environment, Fisheries and Aquaculture Science, Lowestoft Laboratory",
-        "Polar Scientific Research Institute of Fishery and Oceanography",
-        "Laboratory of Physical Oceanography/ UNIVERSITE DE BRETAGNE OCCIDENTALE (UBO)",
-        "Universite de Pau / IPREM multidisciplinary research institute for the environment and materials",
-        "University of Bordeaux I / Marine Biology Institut",
-        "IFREMER / STH/LBH-LABORATOIRE BIOLOGIE HALIEUTIQUE",
-        "Roscoff Marine Station, Sorbonne Universit\u00e9s, UPMC Univ Paris 06 and CNRS",
-        "Southampton Oceanography Centre",
-        "LABORATORY OF OCEANOGRAPHY of VILLEFRANCHE (LOV) / OOV",
-        "IEO/ Cadiz Oceanographic Centre",
-        "CNEVA / LAB. PATHOLOGIE ANIMAUX AQUATIQUES",
-        "IFREMER",
-        "University of Liverpool, Port Erin Marine Laboratory",
-        "IEO/ Malaga Oceanographic Centre",
-        "Institute of Earth Physics of Paris",
-        "Institute of Marine Research",
-        "Atlantic Scientific Research Institute for Marine Fishery and Oceanography",
-        "Universite D'Angers / Laboratoire Des Bio-Indicateurs Actuels Et Fossiles (Biaf)",
-        "IRD / CENTRE DE PAPEETE",
-        "IRD CENTRE DE  NOUMEA",
-        "NIOZ Royal Netherlands Institute for Sea Research",
-        "University of East Anglia, School of Environmental Sciences",
-        "LABORATORY of PHYSICAL OCEANOGRAPHY (LPO) UMR 6523 CNRS-IFREMER-IRD-UBO",
-        "Institute of Oceanographic Sciences Wormley Laboratory",
-        "IFREMER / DYNECO- Coastal Environment Dynamics department",
-        "University of Southampton Department of Oceanography",
-        "Far Eastern Regional Hydrometeorological Research Institute",
-        "IFREMER / CENTRE DE BRETAGNE",
-        "UNIVERSITE DE BRETAGNE OCCIDENTALE (UBO) / LAB. D'OCEANO. CHIMIQUE LOC - IUEM",
-        "CEA / INSTITUT DE  RADIOPROTECTION ET DE SURETE NUCLEAIRE",
-        "UNKNOWN",
-        "Ukrainian scientific center of Ecology of Sea (UkrSCES)",
-        "Dunstaffnage Marine Laboratory",
-        "Malaga University (UMA). Applied Physics departament II",
-        "IEO/ Gijon Oceanographic Centre",
-        "University of Liverpool Department of Oceanography",
-        "IFREMER STATION DE LA ROCHELLE-L'HOUMEAU",
-        "IFREMER / STATION DE LA TREMBLADE",
-        "Odessa Branch of SOI (State Oceanographic Institute)",
-        "IRD ANTENNE INSTITUT OCEANOGRAPHIQUE (IRD)",
-        "Marine Hydrophysical Institute",
-        "IEO/ Santander Oceanographic Centre",
-        "Canary Institute of Marine Sciences",
-        "IFREMER / STATION DE LORIENT",
-        "IFREMER / STATION D'ARCACHON",
-        "Fisheries Research Services, Aberdeen Marine Laboratory",
-        "German Hydrographic Institute",
-        "Oceanologic Observatory of Banyuls (University of Paris VI) / OSU",
-        "Institute of Oceanographic Sciences Deacon Laboratory",
-        "IEO/ Oceanographic Centre of Canary Island",
-        "MUSEUM NATIONAL D'HISTOIRE NATURELLE / LABORATOIRE D'OCEANOGRAPHIE PHYSIQUE",
-        "IRD / CENTRE OF ABIDJAN",
-        "Scottish Office Agriculture and Fisheries Department - Aberdeen Marine Laboratory",
-        "COM - Physical and Biogeochemical Oceanography Laboratory (LUMINY)",
-        "Department of Agriculture and Fisheries for Scotland - Aberdeen Marine Laboratory",
-        "Scottish Association for Marine Science",
-        "IFREMER / EMH-DEPARTEMENT ECOLOGIE ET MODELES POUR L'HALIEUTIQUE",
-        "IEO/ Vigo Oeanographic Centre",
-        "CEA / Laboratory of climatolocical and environmental Sciences(LSCE)",
-        "University of Cambridge Department of Earth Sciences",
-        "Marine Research Institute",
-        "CNRS / Microbiology, Geochemistry and Marine Ecology Laboratory",
-        "EPOC - Geology and Oceanography Department",
-        "National Oceanography Centre, Southampton",
-        "OGS (Istituto Nazionale di Oceanografia e di Geofisica Sperimentale), Division of Oceanography",
-        "ISTPM (IFREMER NANTES)",
-        "Marine Scotland Science",
-        "IFREMER / STATION DE SETE",
-        "Las Palmas University. Sciences of the Sea Faculty",
-        "GEOMAR Helmholtz Centre for Ocean Research Kiel",
-        "Universite de la Rochelle / Litoral Environnement et Societe (LIENSS) - UMR 7266",
-        "Scottish Marine Biological Association",
-        "Marine Institute",
-        "Aquitaine Observatory of Sciences of the Universe \u2013 University of Bordeaux (OASU)",
-        "University of Bordeaux I / IGBA Talence",
-        "IFREMER / STH-DEPARTEMENT SCIENCES ET TECHNOLOGIES HALIEUTIQUES",
-        "University of Bordeaux I / Laboratory for Physical and Toxico Chemistry (ISM)",
-        "Alfred-Wegener-Institute for Polar- and Marine Research",
-        "IRD /CENTRE DE BRETAGNE",
-        "IFREMER / Dpt Technologicals Research and Development",
-        "IFREMER / DYNECO / PHYSED -LABO PHYSIQUE HYDRODYNAMIQUE ET SEDIMENTAIRE",
-        "Defence Evaluation Research Agency",
-        "Federal Maritime and Hydrographic Agency",
-        "UNIVERSITE DE PAU / LAB.CHIMIE BIO INORGANIQUE & ENVIRONNEMENT",
-        "Laboratory of Oceanography and Climate  : Experiments and numerical Approaches - UMR 7159",
-        "IRD / CENTRE DE MONTPELLIER",
-        "IFREMER / HMMN-DEPARTEMENT HALIEUTIQUE DE MANCHE-MER DU NORD",
-        "University of Wales, School of Ocean Sciences",
-        "Plymouth Marine Laboratory",
-        "IEO/Spanish Oceanographic Institute",
-        "IFREMER / EEP / LEP-DEEP ENVIRONMENT LABORATORY"
-    ],
-    "ResourceType": "dataset",
-    "Rights": [
-        "No limitations on public access.  For data access please register at http://www.marine-id.org"
-    ],
-    "SpatialCoverage": "(10N-62N,90W-10E)",
-    "TempCoverageBegin": 59926651199,
-    "TempCoverageEnd": 63555623999,
-    "TemporalCoverage": " period : ( 1900-01-01T11:59:59Z - 2014-12-31T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1900-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2014-12-31T11:59:59Z",
-    "fulltext": "a61129f0-afbc-4bfa-8307-00f37d37d98a;SEADATANET;sdn-userdesk@seadatanet.org;http://www.seadatanet.org/;2018-07-24T09:47:47;ISO 19115:2003/19139 - EMODNET - SDN;0.1;4;33;1;false;WGS 84 (EPSG 4326);EPSG;North Atlantic Ocean - Temperature and salinity observation collection V2;seadatanet-north_atlantic_ocean-temperature_salinity_aggregated_public-v2;2015-07-23;2.1;2015-07-23;a61129f0-afbc-4bfa-8307-00f37d37d98a;SeaDataNet Temperature and Salinity historical data collection v2, including revised quality flags after quality control with ODV.\n\nFor data access please register at http://www.marine-id.org;SeaDataNet;IFREMER / IDM/SISMER;+33 (0)2 98.22.49.16;+33 (0)2 98.22.46.44;Centre IFREMER de Brest\nBP 70;PLOUZANE;29280;France;sismer@ifremer.fr;http://www.ifremer.fr/sismer/;web site;IFREMER / IDM/SISMER;+33 (0)2 98.22.49.16;+33 (0)2 98.22.46.44;Centre IFREMER de Brest\nBP 70;PLOUZANE;29280;France;sismer@ifremer.fr;http://www.ifremer.fr/sismer/;web site;IFREMER / STATION D'ARCACHON;05 56.83.85.60;05 56.83.89.80;IFREMER Station d'Arcachon, Quai du Commandant Silhouette;Arcachon;33120;France;None;http://www.ifremer.fr/delar;web site;Aquitaine Observatory of Sciences of the Universe \u2013 University of Bordeaux (OASU);+33 (0)5 40 00 83 50;+33(0)5 57 77 56 88;O.A.S.U. \nB\u00e2timent B18N\nAll\u00e9e Geoffroy Saint Hilaire\nCS 50023;PESSAC Cedex;33615;France;None;http://www.oasu.u-bordeaux.fr/;web site;Oceanologic Observatory of Banyuls (University of Paris VI) / OSU;+33 4 68 88 73 15;+33 4 68 88 16 99;Laboratoire Arago\nBP 44;BANYULS-SUR-MER;66651;France;None;http://www.obs-banyuls.fr/;web site;IFREMER / DYNECO- Coastal Environment Dynamics department;+33 (0)2 98.22.43.51;+33 (0)2 98 22 45.48;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;None;http://www.ifremer.fr/anglais/org/del.htm;web site;CEA / INSTITUT DE  RADIOPROTECTION ET DE SURETE NUCLEAIRE;+33(0)2 33.01.41.00;None;LABORATOIRE DE RADIOECOLOGIE MARINE,RUE MAX POL FOUCHET,BP 10;OCTEVILLE;50130;France;None;http://www.irsn.org/en/;web site;CNEVA / LAB. PATHOLOGIE ANIMAUX AQUATIQUES;+33(0)2 98.22.44.61;None;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;None;None;web site;UNKNOWN;None;None;UNKNOWN;UNKNOWN;None;Unknown;None;None;web site;IFREMER;+33(0)1 46.48.21.00;+33(0)1 46.48.22.24;Technopolis 40,155 rue J.J. Rousseau;ISSY-LES-MOULINEAUX;92138;France;communication@ifremer.fr;http://wwz.ifremer.fr;web site;IFREMER / STATION DE LA TREMBLADE;+33(0)5 46.36.18.41;+33(0)5 46.36.18.47;Mus du Loup,BP 133;LA TREMBLADE;17390;France;None;http://www.ifremer.fr/latremblade/accueilen.htm;web site;IRD / CENTRE DE LA MARTINIQUE;+33 (0)596 39 77 39;+33 (0)596 50 32 61;BP 8006;FORT DE FRANCE cedex;97259;France;representant@ird-mq.fr;http://www.mq.ird.fr/;web site;IRD / CENTRE DE MONTPELLIER;+33 (0)4 67 41 61 00;+33 (0)4 67 41 63 30;BP 64501;MONTPELLIER CEDEX 5;34394;France;montpellier@ird.fr;http://www.france-sud.ird.fr/;web site;IRD / CENTRE DE PAPEETE;(689) 50 62 00;(689) 42 95 55;Chemin de l'ahari PK 3800 - Arue,BP 529;PAPEETE (Tahiti);98713;France;dirpapet@ird.pf;http://www.polynesie.ird.fr/;web site;ISTPM (IFREMER NANTES);+33(0)2 40.37.40.00;None;rue de l'Ile d'Yeu,BP 1105;NANTES CEDEX 03;44311;France;None;None;web site;University of Bordeaux I / IGBA Talence;+33(0)5 56 80 68 00;None;351, Cours de la Liberation;TALENCE CEDEX;33405;France;None;None;web site;University of Bordeaux I / Marine Biology Institut;+33(0)4 69 82 35 36;None;351, Cours de la Liberation;TALENCE CEDEX;33405;France;None;None;web site;UNIVERSITE DE PAU / LAB.CHIMIE BIO INORGANIQUE & ENVIRONNEMENT;+33(0)5 59 40 77 50;+33(0)5 59 40 77 81;2 Avenue du President ANGOT,HELIOPARC;PAU Cedex 09;64053;France;None;None;web site;IRD / CENTRE OF ABIDJAN;(225) 24 37 79;(225) 24 65 04;Rue du Chevalier de Clieu15 \n15 BP 917;Abidjan;15;C\u00f4te d'Ivoire;rep@ird.ci;None;web site;IRD / CENTRE OF HANN;+221 849 35 35;+221 832 43 07;Route des Peres Maristes\nBP 1386;DAKAR - HANN;None;Senegal;infos@ird.sn;http://www.ird.sn/centre/index.htm;web site;Ukrainian scientific center of Ecology of Sea (UkrSCES);+38 0482 636622;+380 482  636873;89 Frantsuzsky Blvd.;Odessa;65009;Ukraine;accem@te.net.ua;http://www.sea.gov.ua;web site;OGS (Istituto Nazionale di Oceanografia e di Geofisica Sperimentale), Division of Oceanography;None;None;Borgo Grotta Gigante 42/c;Sgonico (Trieste);34010;Italy;nodc@ogs.trieste.it;http://www.ogs.trieste.it/;web site;University of Plymouth, Institute of Marine Studies;None;None;Drake Circus;Plymouth;PL4 8AA;United Kingdom;inapplicable;http://www.plymouth.ac.uk/plymouth/main.htm;web site;Institute of Marine Research;+47 55 23 85 00;+47 55 23 85 31;Nordnesgaten 50\nPostboks 1870 Nordnes;Bergen;N-5817;Norway;post@imr.no;http://www.imr.no;web site;ENEA Centro Ricerche Ambiente Marino - La Spezia;+39 0187 978258;+39 0187 978213;Forte S. Teresa\nVia S.Teresa 1;Lerici;19036;Italy;roberta.delfanti@enea.it;http://www.santateresa.enea.it;web site;Alfred-Wegener-Institute for Polar- and Marine Research;None;None;Am Handelshafen 12;Bremerhaven;D-27570;Germany;folke.mehrtens@awi.de;http://www.awi.de;web site;Isle of Man Government Laboratory;+44 (0)1624 642250;+44 (0)1624 642222;Ballakermeen Road;Douglas;IM1 4BR;United Kingdom;analyst@lab.gov.im;http://www.gov.im/dlge/enviro/govlabs/;web site;Malaga University (UMA). Applied Physics departament II;+34 952 132413/27 78;+34 952 13 24 16;Escuela Tecnica Superior de Ingenieros de Telecomunicaciones. Departamento de Fisica Aplicada II\nComplejo Tecnol\u00f3gico-Campus Teatinos;Malaga;29071;Spain;secteleco@uma.es;http://150.214.57.159/fa2.php;web site;Las Palmas University. Sciences of the Sea Faculty;+34 928 452900;+34 928 452922;Edificio Ciencias B\u00e1sicas\nCAMPUS UNIVERSITARIO DE TAFIRA\nApdo. 550;Las Palmas de Gran Canaria (Islas Canarias);35017;Spain;None;http://www.fcm.ulpgc.es;web site;University of Liverpool, Port Erin Marine Laboratory;None;None;None;Port Erin;IM9 6JA;United Kingdom;inapplicable;http://www.liv.ac.uk/www/peml/;web site;IEO/ Gijon Oceanographic Centre;+34 985 30 86 72;+34 985 32 62 77;Camino de Arbeyal, s/n;Gijon (Asturias);33212;Spain;ieogijon@gi.ieo.es;http://www.ieo.es/CoGijon/index.htm;web site;IEO/ Santander Oceanographic Centre;+34 942 291060;+34 942 275072;Promontorio San Martin, s/n\nApdo. 240;Santander;39004;Spain;ieosantander@st.ieo.es;http://www.ieo-santander.net/;web site;IEO/ La Coruna Oceanographic Centre;+34 981 205362;+34 981 229077;Muelle de las Animas, s/n\nApdo.130;A Coruna;15001;Spain;ieo.coruna@co.ieo.es;http://www.ieo.es;web site;IEO/ Vigo Oeanographic Centre;+34 986 492 111;+34 986 498 626;Cabo Estay \u2013 Canido;Vigo;36200;Spain;ieo.vigo@vi.ieo.es;http://www.vi.ieo.es/;web site;IEO/ Malaga Oceanographic Centre;+34 952 476 955;+34 952 463 808;Puerto Pesquero, s/n\nApdo. 285;Fuengirola (Malaga);29640;Spain;ieomalaga@ma.ieo.es;http://www.ieo.es;web site;IEO/ Cadiz Oceanographic Centre;+34 956 294 189;+34 956 263 556;Muelle de Levante (Puerto Pesquero)\nApdo. 2609;Puerto Real (Cadiz);11106;Spain;ignacio.sobrino@cd.ieo.es;http://www.ieo.es;web site;IFREMER / STATION DE LORIENT;+33 (0)2 97 87 38 00;+33 (0)2 97 87 38 01;8 rue Fran\u00e7ois Toullec;LORIENT;56100;France;secretariat@ifremer.fr;http://www.ifremer.fr/sth/station_lorient.htm;web site;National Oceanography Centre, Southampton;None;None;University of Southampton \nWaterfront Campus \nEuropean Way;Southampton;SO14 3ZH;United Kingdom;enquiries@noc.ac.uk;http://noc.ac.uk;web site;University of Rostock, Institute of Biosciences;+49 (0)381 498 6041;+49 (0)381 498 6042;Wismarsche Strasse 8;Rostock;18057;Germany;institut.biowissenschaften@uni-rostock.de;http://www.bio.uni-rostock.de;web site;University of Liverpool Department of Oceanography;None;None;Brownlow Hill;Liverpool;None;United Kingdom;inapplicable;None;web site;University of Southampton School of Ocean and Earth Science;+44 (0)23 8059 2011;+44 (0)23 8059 3059;National Oceanography Centre, European Way;Southampton;SO14 3ZH;United Kingdom;soes@noc.soton.ac.uk;http://www.soes.soton.ac.uk/;web site;University of Southampton School of Ocean and Earth Science;None;None;Southampton Oceanography Centre, European Way;Southampton;SO14 3ZH;United Kingdom;inapplicable;None;web site;University of Southampton Department of Oceanography;None;None;University of Southampton Waterfront Campus, European Way;Southampton;SO14 3ZH;United Kingdom;inapplicable;None;web site;University of Southampton Department of Oceanography;None;None;Highfield Campus;Southampton;SO9 5NH;United Kingdom;inapplicable;None;web site;German Hydrographic Institute;494031903420;494031905000;Bernhard-Nocht-Str. 78;Hamburg;20359;Germany;friedrich.nast;http://www.bsh.de/en/Marine_data/Hydrographic_surveys_and_wreck_search/Hydrographic_surveys/e_geschichte_sv.jsp;web site;Federal Maritime and Hydrographic Agency;+49 40 3190 0;+49 40 3190 5000;Bernhard-Nocht-Str. 78;Hamburg;20359;Germany;webmaster@bsh.de;http://www.bsh.de;web site;Universite de la Rochelle / Litoral Environnement et Societe (LIENSS) - UMR 7266;05.46.45.72.61;None;Av, Michel Cr\u00e9peau\nLAB. DE BIOLOGIE ET ENVIRONNEMENT MARIN - LBEM;LA ROCHELLE;17042;France;None;http://www.univ-lr.fr/labo/lbem/;web site;LABO ATMOSPHEREs, MILIEUX, OBSERVATIONS SPATIALES (LATMOS);+33 (0)1 39 25 49 06;+33 (0)1 39 25 49 22;Centre Universitaire de V\u00e9lizy\n10-12 Avenue de l'Europe;VELIZY;78140;France;direction@latmos.ipsl.fr;http://www.latmos.ipsl.fr/;web site;Ifremer / Crela;+33(0)5 46.50.94.40;+33(0)5 46.50.06.60;Centre de Recherche sur Ecosyst\u00e8mes Littoraux Anthropis\u00e9s\n Place du S\u00e9minaire\nBP 7;L'HOUMEAU;17137;France;None;None;web site;University of Bordeaux I / Laboratory for Physical and Toxico Chemistry (ISM);None;None;LPTC - ESA 5472 CNRS\nUniversite Bordeaux 1l'\u00e9tu\n351 Cours de la Lib\u00e9ration;TALENCE CEDEX;33405;France;None;http://www.ism.u-bordeaux1.fr/-Physico-et-Toxicochimie-de-l-.html;web site;Universite D'Angers / Laboratoire Des Bio-Indicateurs Actuels Et Fossiles (Biaf);02.41.73.53.91;02.41.73.53.52;UFR Sciences - UPRES EA 2644\n2, Bd Lavoisier;ANGERS cedex 01;49045;France;frans.jorissen@univ-angers.fr;None;web site;Universite de Pau / IPREM multidisciplinary research institute for the environment and materials;05 59 40 77 51;05 59 40 77 81;IPREM UMR 5254\nH\u00e9lioparc Pau Pyr\u00e9n\u00e9es\n2, av. Pierre Angot;PAU CEDEX 9;64053;France;olivier.donard@univ-pau.fr;http://www.iprem.org/;web site;University of Cambridge Department of Earth Sciences;None;None;Downing Street;Cambridge;CB2 3EQ;United Kingdom;jaj2@cam.ac.uk;http://www.esc.cam.ac.uk;web site;University of Wales, School of Ocean Sciences;None;None;School of Ocean Sciences,\nUniversity of Wales Bangor, \nMenai Bridge, \nAnglesey,;Menai Bridge;LL59 5AB;United Kingdom;inapplicable;http://www.sos.bangor.ac.uk/;web site;Southampton Oceanography Centre;None;None;University of Southampton \nWaterfront Campus \nEuropean Way;Southampton;SO14 3ZH;United Kingdom;inapplicable;None;web site;Scottish Office Agriculture Environment and Fisheries Department - Aberdeen Marine Laboratory;None;None;PO Box 101\n375 Victoria Road;Aberdeen;AB11 9DB;United Kingdom;inapplicable;None;web site;Scottish Office Agriculture and Fisheries Department - Aberdeen Marine Laboratory;None;None;PO Box 101\n375 Victoria Road;Aberdeen;AB11 9DB;United Kingdom;inapplicable;None;web site;Department of Agriculture and Fisheries for Scotland - Aberdeen Marine Laboratory;None;None;PO Box 101\n375 Victoria Road;Aberdeen;AB11 9DB;United Kingdom;inapplicable;None;web site;Ministry of Agriculture, Fisheries and Food, Lowestoft Fisheries Laboratory;None;None;Pakefield Road;Lowestoft;NR33 0HT;United Kingdom;inapplicable;None;web site;Institute of Oceanographic Sciences Deacon Laboratory;None;None;Brook Road\nWormley;Godalming;GU8 5UB;United Kingdom;inapplicable;None;web site;Institute of Oceanographic Sciences Wormley Laboratory;None;None;Brook Road\nWormley;Godalming;GU8 5UB;United Kingdom;inapplicable;None;web site;Proudman Oceanographic Laboratory;+44 (0)151 653 8633;+44 (0)151 653 6269;Bidston Observatory\nBidston Hill;Prenton;CH43 7RA;United Kingdom;inapplicable;http://www.pol.ac.uk;web site;Institute of Oceanographic Sciences, Bidston Laboratory;None;None;Bidston Observatory\nBidston Hill;Prenton;L43 7RA;United Kingdom;inapplicable;None;web site;Marine Scotland Science;+44 (0)1224 876544;+44 (0)1224 295511;Marine Laboratory, PO Box 101;Aberdeen;AB11 9DB;United Kingdom;inapplicable;None;web site;Defence Evaluation Research Agency;None;None;Winfrith Technology Centre;Winfrith;DT2 8XJ;United Kingdom;inapplicable;http://www.dera.gov.uk/newsite/home_2.htm;web site;National Oceanography Centre, Liverpool;+44 (0)151 795 4800;+44 (0)151 795 4801;Joseph Proudman Building, 6 Brownlow Street;Liverpool;L3 5DA;United Kingdom;enquiries@noc.ac.uk;http://noc.ac.uk;web site;UTM-CSIC/Marine Technology Unit;+34 932 309500;+34 932 309555;Paseo Maritimo de la Barceloneta, 37-49;Barcelona;08003;Spain;info@utm.csic.es;http://www.utm.csic.es/;web site;Dunstaffnage Marine Laboratory;None;None;Dunbeg;Oban;PA37 1QA;United Kingdom;inapplicable;None;web site;Scottish Marine Biological Association;None;None;Dunbeg;Oban;PA37 1QA;United Kingdom;inapplicable;None;web site;Institute of Marine Research (IIM-CSIC);+34 986231930;+34 986292762;Eduardo Cabello, 6;Vigo (Pontevedra);36208;Spain;webmaster@iim.csic.es;http://www.iim.csic.es;web site;Centre for Environment, Fisheries and Aquaculture Science, Lowestoft Laboratory;+44 (0)1502 562244;+44 (0)1502 513865;Pakefield Road;Lowestoft;NR33 OHT;United Kingdom;sarah.turner@cefas.co.uk;http://www.cefas.co.uk/;web site;GEOMAR Helmholtz Centre for Ocean Research Kiel;+49 431 600-0;+49 431 600-2805;D\u00fcsternbrooker Weg 20;Kiel;24105;Germany;info@geomar.de;http://www.geomar.de/en/;web site;IEO/ Oceanographic Centre of Canary Island;+34 922 549400;+34 922 549554;Carretera San Andr\u00e9s Km 7\nApdo. 1373;S. C. Tenerife;38180;Spain;coc@ca.ieo.es;http://www.ieo.es;web site;Canary Institute of Marine Sciences;+34 928 132900;+34 928 132908;Carretera de Taliarte, s/n.;Telde (Las Palmas de Gran Canaria);35200;Spain;None;http://www.iccm.rcanaria.es;web site;IEO/Spanish Oceanographic Institute;+34 915 107513;+34 914 135597;Corazon de Maria, 8;MADRID;28002;Spain;cedo@ieo.es;http://www.ieo.es;web site;Fisheries Research Services, Aberdeen Marine Laboratory;+44 (0)1224 876544;+44 (0)1224 295511;PO Box 101\nVictoria Road;Aberdeen;AB11 9DB;United Kingdom;inapplicable;http://www.marlab.ac.uk;web site;Marine Institute;+353-91-387200;+353-91-387201;Rinville;Oranmore;H91 R673;Ireland;datarequests@marine.ie;http://www.marine.ie;web site;British Oceanographic Data Centre;None;None;Joseph Proudman Building\n6 Brownlow Street;Liverpool;L3 5DA;United Kingdom;enquiries@bodc.ac.uk;http://www.bodc.ac.uk/;web site;Scottish Association for Marine Science;None;None;None;Argyll;PA37 1QA;United Kingdom;laurence.mee@sams.ac.uk;http://www.sams.ac.uk;web site;IRD /CENTRE DE BRETAGNE;+33 (0)2 98.22.45.01;+33(0)2 98.22.45.14;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;None;http://www.brest.ird.fr/;web site;IFREMER / DYNECO/PELAGOS-LABORATOIRE D'ECOLOGIE PELAGIQUE;+33(0)2 98 22 43 34;+33(0)2 98 22  45 98;IFREMER Centre de Brest\nBP70;PLOUZANE;29280;France;None;http://www.ifremer.fr/delec/;web site;Marine Biological Association of the United Kingdom;None;None;Citadel Hill;Plymouth;PL1 2PB;United Kingdom;sec@mba.ac.uk;http://www.mba.ac.uk/;web site;Plymouth Marine Laboratory;+44 (0)1752 633 100;+44 (0)1752 633101;Prospect Place\nThe Hoe;Plymouth;PL1 3DH;United Kingdom;forinfo@pml.ac.uk;http://www.pml.ac.uk;web site;Proudman Oceanographic Laboratory;None;None;Joseph Proudman Building\n6 Brownlow Street;Liverpool;L3 5DA;United Kingdom;inapplicable;http://www.pol.ac.uk;web site;IFREMER / EEP / LEP-DEEP ENVIRONMENT LABORATORY;+33 (0)2 98.22.43.04;+33 (0)2 98.22.47.57;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;None;http://www.ifremer.fr/droep/index.html;web site;IFREMER / GM-MARINE GEOSCIENCES;+33(0)2 98.22.42.70;+33(0)2 98.22.45.70;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;geosciences.marines@ifremer.fr;http://www.ifremer.fr/drogm/;web site;LABORATORY of PHYSICAL OCEANOGRAPHY (LPO) UMR 6523 CNRS-IFREMER-IRD-UBO;+33 (0)2 98.22.42.76;+33(0)2 98.22.44.96;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;None;http://www.ifremer.fr/lpo/;web site;LABORATORY OF OCEANOGRAPHY of VILLEFRANCHE (LOV) / OOV;+33 (0)4 93 76 38 13;+33 (0)4.93.76.38.34;UPMC/UMR 7093 \n181, chemin du Lazaret;Villefranche-sur-Mer;06230;France;lov@obs-vlfr.fr;http://www.obs-vlfr.fr;web site;Laboratory of Oceanography and Climate  : Experiments and numerical Approaches - UMR 7159;+33 (1) 44 27 32 48;+33(0)1 44 27 38 05;UMR 7159 CNRS / IRD / Universit\u00e9 Pierre et Marie Curie/MNHN\nInstitut Pierre Simon Laplace - Bo\u00eete 100\n4 Place Jussieu;Paris;75252;France;nelly.lecquyer@locean-ipsl.upmc.fr;http://www.locean-ipsl.upmc.fr/;web site;MUSEUM NATIONAL D'HISTOIRE NATURELLE / LABORATOIRE D'OCEANOGRAPHIE PHYSIQUE;+33 (0)1 40.79.31 58;+33 (0)1 40 79 31 63;43-45 rue Cuvier;PARIS CEDEX 05;75231;France;None;http://www.mnhn.fr;web site;IFREMER / DYNECO / PHYSED -LABO PHYSIQUE HYDRODYNAMIQUE ET SEDIMENTAIRE;33 (0)2 98 22 47 60;33 (0)2 98 22 45 55;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;None;http://wwz.ifremer.fr/dyneco/Equipes/Physed;web site;COM - Physical and Biogeochemical Oceanography Laboratory (LUMINY);+33(0)4 91 82 91 15;+33(0)4 91.82.65.48;UFR Centre Oceanologique de Marseille\nUMR 6535\nCampus de Luminy Case 901;Marseille cedex 9;13288;France;queguiner@com.univ-mrs.fr;http://www.com.univ-mrs.fr/LOB/;web site;IFREMER STATION DE LA ROCHELLE-L'HOUMEAU;+33 (0)5 46.50.94.40;+33 (0)5 46.50.06.50;Place du Seminaire, \nBP 7;L'HOUMEAU;17137;France;None;http://w3.ifremer.fr/francais/implant/larochel.htm;web site;Institute of Earth Physics of Paris;+33 (0)1 83 95 74 00;+33 (0)1 83 95 77 14;1, place Jussieu;PARIS CEDEX 5;75252;France;None;http://www.ipgp.jussieu.fr/;web site;IRD CENTRE DE  NOUMEA;+33 (0)1 44 27 34 67;+33 (0)1 44 27 24 01;BP A5;NOUMEA CEDEX5;98848;New Caledonia;nouvelle-caledonie@ird.fr;http://www.ird.nc/;web site;Roscoff Marine Station, Sorbonne Universit\u00e9s, UPMC Univ Paris 06 and CNRS;+33(0)2 98.29.23.23;+33 (0)2 98.29.23.24;Place Georges Teissier;ROSCOFF;29680;France;None;http://www.sb-roscoff.fr/;web site;IFREMER / RBE Department / Biogeochimical end Ecotoxicological Resarch Unit (Nantes);+33 (0)2 40 37 41 93;33(0)2 40.37.40.75;IFREMER Centre de Nantes\nRue de l'Ile d'Yeu\nBP 1105;NANTES CEDEX 03;44311;France;None;http://www.ifremer.fr/delpc/;web site;CNRS / Microbiology, Geochemistry and Marine Ecology Laboratory;+33 (0)4 91 82 92 12;+33 (0)4 91 82 96 41;Centre d'Oc\u00e9anologie de Marseille (COM)\nUMR 6117\nCampus de Luminy, Case 901;MARSEILLE CEDEX 9;13288;France;micromar@com.univ-mrs.fr;http://www.com.univ-mrs.fr/LMGEM/spip.php?rubrique1;web site;IFREMER / STATION DE LA TRINITE;+33 (0)2 97 30 19 19;+33 (0)2 97 30 19 00;12, rue des Resistants\nBP 86;LA TRINITE-SUR-MER;56470;France;None;http://www.ifremer.fr/anglais/implant/latrinit.htm;web site;IFREMER / STH/LBH-LABORATOIRE BIOLOGIE HALIEUTIQUE;+33 (0)2.97.87.38.00;+33 (0)2.97.87.38.01;IFREMER Station de Lorient\n8, rue Francois Toullec;LORIENT;56100;France;mlegall@ifremer.fr;http://wwz.ifremer.fr/lorient;web site;Shom;+33 (0)2 56.31.23.12;+33 (0)2 56.31.25.80;13, rue du Chatellier\nCS92803;BREST CEDEX 2;29228;France;seadatanet-admin@shom.fr;http://www.shom.fr/;web site;IFREMER / EMH-DEPARTEMENT ECOLOGIE ET MODELES POUR L'HALIEUTIQUE;+33(0)2 40.37.41. 67;+33(0)2 40.37.40.75;IFREMER - Centre de Nantes\nrue de l'Ile d'Yeu\nBP 21105;NANTES CEDEX 03;44311;France;None;http://www.ifremer.fr/drvecohal;web site;IFREMER / HMMN-DEPARTEMENT HALIEUTIQUE DE MANCHE-MER DU NORD;+33 (0)3 21.99.56.00;+33 (0)3 21.99.56.01;IFREMER Centre de Boulogne sur Mer\n150 quai Gambetta \nBP 70;BOULOGNE-SUR-MER CEDEX;62321;France;None;http://www.ifremer.fr/boulogne/;web site;Swedish Meteorological and Hydrological Institute;+46-(0)11-495 80 00;+46-(0)11-495 80 01;Folkborgsvagen 1;Norrkoping;SE-601 76;Sweden;shark@smhi.se;http://www.smhi.se;web site;CEA / Laboratory of climatolocical and environmental Sciences(LSCE);+33(0)1 69.82 35 23;+33(0)1 69.82.35.68;CNRS\nLSCE-Vallee, Bat.12, Avenue de la Terrasse;GIF-SUR-YVETTE CEDEX;91198;France;None;http://www.lsce.cnrs-gif.fr/;web site;UNIVERSITE DE BRETAGNE OCCIDENTALE (UBO) / LAB. D'OCEANO. CHIMIQUE LOC - IUEM;None;None;Place Nicolas Copernic;Plouzane;29280;France;None;None;web site;CEREGE;+33(0)4 42 97 15 00;+33 (0)4 42 97 15 05;Europole Mediterraneen de l'Arbois \nBP 80;Aix en Provence;13545;France;None;http://www.cerege.fr/;web site;Marine Research Institute;+354 575 2000;+354 575 2001;Skulagata 4\nP.O.Box 1390;Reykjavik;IS-121;Iceland;hafro@hafro.is;http://www.hafro.is/index_eng.php;web site;IHPT, Hydrographic Institute;+351 210943000;+351 210943299;Rua das Trinas, 49;Lisboa;1249-093;Portugal;mail@hidrografico.pt;http://www.hidrografico.pt;web site;University of East Anglia, School of Environmental Sciences;None;None;University Plain;Norwich;NR4 7TJ;United Kingdom;env.enquiries@uea.ac.uk;http://www.uea.ac.uk/env/;web site;NIOZ Royal Netherlands Institute for Sea Research;+31 222 369300;+31 222 319674;Landsdiep 4\nP.O. Box 59;Den Burg/Texel;1790 AB;Netherlands;dmg@nioz.nl;https://www.nioz.nl;web site;Atlantic Scientific Research Institute for Marine Fishery and Oceanography;8 (0112) 21-56-45;8 (0112) 21-99-97;5, Dm. Donskoi St.;Kaliningrad reg;236000;Russian Federation;atlant@baltnet.ru;http://www.atlantniro.ru/;web site;P.P.Shirshov Institute of Oceanology, RAS;+7(499)124-59-96;+7(499)124-59-83;36 Nakhimovsky prospect;Moscow;117997;Russian Federation;office@ocean.ru;http://www.ocean.ru;web site;IFREMER / STATION DE SETE;+33(0)4 99 57 32 00;+33 (0)4 99 57 32 94;Bd Jean Monnet \nBP 171;SETE CEDEX;34203;France;None;http://wwz.ifremer.fr/mediterranee/implantations/Sete;web site;Marine Hydrophysical Institute;+380 692 54 02 52;+380 692 55 42 53;2, Kapitanskaya str.;Sevastopol;99011;Ukraine;khaliulin.alexey@nodc.org.ua;http://WWW.MHI.IUF.NET;web site;Far Eastern Regional Hydrometeorological Research Institute;+7 (4232) 26-97-88;+7 (4232) 22-77-54;Fontannaya St., 24;Vladivostok;690600;Russian Federation;hydromet@online.ru;http://www.hydromet.com;web site;IFREMER / STH-DEPARTEMENT SCIENCES ET TECHNOLOGIES HALIEUTIQUES;+33 (0)2 98.22.43.66;+33 (0)2 98 22 45.47;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;None;http://www.ifremer.fr/anglais/org/drv.htm;web site;IFREMER / Dpt Technologicals Research and Development;+33(0) 2 98 22 41 41;+33(0) 2 98 22 45 35;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;Pierre.Chauchot@ifremer.fr;http://wwz.ifremer.fr/rd_technologiques;web site;IRD ANTENNE INSTITUT OCEANOGRAPHIQUE (IRD);+33 (0)1 44.32.10.70;+33 (0)1 40.51.73.16;INSTITUT OCEANOGRAPHIQUE \n195 Rue Saint Jacques;PARIS;75005;France;None;None;web site;Laboratory of Physical Oceanography/ UNIVERSITE DE BRETAGNE OCCIDENTALE (UBO);+33 (0)2 98.01.61.21;+33 (0)2 98 01 64 68;6 avenue Victor-Le-Gorgeu BP 809;BREST CEDEX;29285;France;None;http://www.univ-brest.fr/lpo/site/;web site;EPOC - Geology and Oceanography Department;+33 (0)5 40.00.88.67;+33 (0)5 56.84.08.48;351, Cours de la Liberation \nAvenue des Facultes;TALENCE;33405;France;inapplicable;http://www.epoc.u-bordeaux.fr;web site;IFREMER / CENTRE DE BRETAGNE;+33 (0)2 98.22.40.40;+33 (0)2 98.22.45.45;ZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;None;http://www.ifremer.fr/brest/;web site;Polar Scientific Research Institute of Fishery and Oceanography;None;None;6, Knipovich St.;Murmansk;183763;Russian Federation;persey@pinro.ru;http://www.pinro.ru/;web site;Odessa Branch of SOI (State Oceanographic Institute);None;None;None;Odessa;None;Ukraine;None;None;web site;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=a61129f0-afbc-4bfa-8307-00f37d37d98a&fname=North_Atlantic_SDN_v2_QC472_Map_s.png;Oceanographic geographical features;GEMET - INSPIRE themes, version 1.0;2009-09-22T07:57:15;Temperature of the water column;Salinity of the water column;Parameter Discovery Vocabulary (P02);2014-12-11;geonetwork.thesaurus.external.parameter.NVS.P02;ITS-90 water temperature;Water body salinity;EMODNET chemistry lot aggregated parameter names;2014-12-11;geonetwork.thesaurus.external.parameter.NVS.P35;Atlantic Ocean;SeaVoX salt and fresh water body gazetteer;2014-12-11;geonetwork.thesaurus.external.reference-geographical-area.NVS.C19;Th\u00e8mes Sextant;2017-01-23;geonetwork.thesaurus.local.theme.sextant-theme;SeaDataNet licence;SeaDataNet Usage Agreement: If you use SeaDataNet data in your publications please include the following in the Acknowledgements: Data were provided through SeaDataNet Pan-European infrastructure for ocean and marine data management (https://www.seadatanet.org);No limitations on public access.  For data access please register at http://www.marine-id.org;1;oceans;bounding box;-90;10;10;62;1900-01-01;2014-12-31;-5500.0;0.0;http://dx.doi.org/10.12770/a61129f0-afbc-4bfa-8307-00f37d37d98a;WWW:LINK-1.0-http--metadata-URL;DOI of the product;ftp://vftp2.ifremer.fr/public/seadatanet-north_atlantic_ocean-temperaturesalinity_aggregated/SDN_2015-09_TS_Atlantic_QC_done_v2.zip;WWW:DOWNLOAD-1.0-link--download;full collection dataset;zipped ODV binary collection;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_Atlantic_QC_done_v2;OGC:WMS:getCapabilities;full collection dataset;full collection dataset;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_Atlantic_QC_done_v2;OGC:WMS;SDN_2015-09_TS_Atlantic_QC_done_v2/ITS-90_water_temperature;Temperature;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_Atlantic_QC_done_v2;OGC:WMS;SDN_2015-09_TS_Atlantic_QC_done_v2/Water_body_salinity;Salinity;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_Atlantic_QC_done_v2;OGC:WMS;SDN_2015-09_TS_Atlantic_QC_done_v2/*;Observation locations;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;See the referenced specification;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "aac8799c-93c8-57bf-a5af-41f14fd1dbd3",
-    "notes": [
-        "SeaDataNet Temperature and Salinity historical data collection v2, including revised quality flags after quality control with ODV.\n\nFor data access please register at http://www.marine-id.org"
-    ],
-    "oai_identifier": [
-        "aac8799c-93c8-57bf-a5af-41f14fd1dbd3"
-    ],
-    "oai_set": "cams1_ps",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-90,10],[-90,62],[10,62],[10,10],[-90,10]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "Atlantic Ocean"
-        }
-    ],
-    "title": [
-        "North Atlantic Ocean - Temperature and salinity observation collection V2"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/ba3150c9-d93b-5e24-8aa6-7f956a8910d0.json b/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/ba3150c9-d93b-5e24-8aa6-7f956a8910d0.json
deleted file mode 100644
index 9c45d09a..00000000
--- a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/ba3150c9-d93b-5e24-8aa6-7f956a8910d0.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "sdn-userdesk@seadatanet.org"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=iso19139&identifier=ba3150c9-d93b-5e24-8aa6-7f956a8910d0",
-    "PublicationTimestamp": "2015-07-31T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "IFREMER / IDM/SISMER",
-        "SEADATANET",
-        "Istituto Nazionale di Geofisica e Vulcanologia \u2013 INGV, Sede di Bologna"
-    ],
-    "ResourceType": "dataset",
-    "Rights": [
-        "No limitations on public access.  For data access please register at http://www.marine-id.org"
-    ],
-    "SpatialCoverage": "(30N-46N,9 W-37E)",
-    "TempCoverageBegin": 59926651199,
-    "TempCoverageEnd": 63563396399,
-    "TemporalCoverage": " period : ( 1900-01-01T11:59:59Z - 2015-03-31T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1900-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2015-03-31T11:59:59Z",
-    "fulltext": "8c3bd19b-9687-429c-a232-48b10478581c;SEADATANET;sdn-userdesk@seadatanet.org;http://www.seadatanet.org/;2018-07-24T09:47:42;ISO 19115:2003/19139 - EMODNET - SDN;0.1;4;12;1;false;WGS 84 (EPSG 4326);EPSG;Mediterranean Sea - Temperature and salinity observation collection V2;seadatanet-med_sea-temperature_salinity_aggregated_public-v2;2015-07-31;2;2015-07-31;8c3bd19b-9687-429c-a232-48b10478581c;SeaDataNet Temperature and Salinity historical data collection for the Mediterranean Sea contains all open access temperature and salinity in situ data retrieved from SeaDataNet infrastructure. The data span between -9.25 and 37 degrees of longitude, thus including an Atlantic box and Marmara Sea. It covers the time period 1900-2015. Data have been quality checked using ODV software. Quality Flags of anomalous data have been revised using basic QC procedures.\n\nFor data access please register at http://www.marine-id.org\n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/;SeaDataNet;Istituto Nazionale di Geofisica e Vulcanologia \u2013 INGV, Sede di Bologna;+39 051 4151412;+39 0514151499;Via Donato Creti n\u00b012;Bologna;40128;Italy;simona.simoncelli@ingv.it;http://www.ingv.it;web site;IFREMER / IDM/SISMER;+33 (0)2 98.22.49.16;+33 (0)2 98.22.46.44;Centre IFREMER de Brest\nBP 70;PLOUZANE;29280;France;sismer@ifremer.fr;http://www.ifremer.fr/sismer/;web site;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=8c3bd19b-9687-429c-a232-48b10478581c&fname=DefaultView_0.png;Oceanographic geographical features;GEMET - INSPIRE themes, version 1.0;2009-09-22T07:57:15;Temperature of the water column;Salinity of the water column;Parameter Discovery Vocabulary (P02);2014-12-11;geonetwork.thesaurus.external.parameter.NVS.P02;ITS-90 water temperature;Water body salinity;EMODNET chemistry lot aggregated parameter names;2014-12-11;geonetwork.thesaurus.external.parameter.NVS.P35;Adriatic Sea;Mediterranean Sea;Mediterranean Sea, Eastern Basin;Mediterranean Sea, Western Basin;Ionian Sea;Mediterranean Region;Tyrrhenian Sea;Ligurian Sea;Alboran Sea;Strait of Sicily;Aegean Sea;Sea of Marmara;SeaVoX salt and fresh water body gazetteer;2014-12-11;geonetwork.thesaurus.external.reference-geographical-area.NVS.C19;Th\u00e8mes Sextant;2017-01-23;geonetwork.thesaurus.local.theme.sextant-theme;SeaDataNet licence;SeaDataNet Usage Agreement: If you use SeaDataNet data in your publications please include the following in the Acknowledgements: Data were provided through SeaDataNet Pan-European infrastructure for ocean and marine data management (https://www.seadatanet.org);No limitations on public access.  For data access please register at http://www.marine-id.org;1;oceans;bounding box;-9.250;36.625;30.000;46.125;1900-01-01;2015-03-31;-5500.0;0.0;http://dx.doi.org/10.12770/8c3bd19b-9687-429c-a232-48b10478581c;WWW:LINK-1.0-http--metadata-URL;DOI of the product;ftp://vftp2.ifremer.fr/public/seadatanet-med_sea-temperaturesalinity_aggregated/SDN_2015-09_TS_MedSea_QC_done_v2.zip;WWW:DOWNLOAD-1.0-link--download;full collection dataset;zipped ODV binary collection;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_MedSea_QC_done_v2;OGC:WMS:getCapabilities;full collection dataset;full collection dataset;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_MedSea_QC_done_v2;OGC:WMS;SDN_2015-09_TS_MedSea_QC_done_v2/ITS-90_water_temperature;Temperature;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_MedSea_QC_done_v2;OGC:WMS;SDN_2015-09_TS_MedSea_QC_done_v2/Water_body_salinity;Salinity;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_MedSea_QC_done_v2;OGC:WMS;SDN_2015-09_TS_MedSea_QC_done_v2/*;Observation locations;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;See the referenced specification;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "ba3150c9-d93b-5e24-8aa6-7f956a8910d0",
-    "notes": [
-        "SeaDataNet Temperature and Salinity historical data collection for the Mediterranean Sea contains all open access temperature and salinity in situ data retrieved from SeaDataNet infrastructure. The data span between -9.25 and 37 degrees of longitude, thus including an Atlantic box and Marmara Sea. It covers the time period 1900-2015. Data have been quality checked using ODV software. Quality Flags of anomalous data have been revised using basic QC procedures.\n\nFor data access please register at http://www.marine-id.org\n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/"
-    ],
-    "oai_identifier": [
-        "ba3150c9-d93b-5e24-8aa6-7f956a8910d0"
-    ],
-    "oai_set": "cams1_ps",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-9.250,30.000],[-9.250,46.125],[36.625,46.125],[36.625,30.000],[-9.250,30.000]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "Adriatic Sea"
-        },
-        {
-            "name": "Mediterranean Sea"
-        },
-        {
-            "name": "Mediterranean Sea"
-        },
-        {
-            "name": "Eastern Basin"
-        },
-        {
-            "name": "Mediterranean Sea"
-        },
-        {
-            "name": "Western Basin"
-        },
-        {
-            "name": "Ionian Sea"
-        }
-    ],
-    "title": [
-        "Mediterranean Sea - Temperature and salinity observation collection V2"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/baa48a28-7b33-5fd6-978b-c2ec21717280.json b/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/baa48a28-7b33-5fd6-978b-c2ec21717280.json
deleted file mode 100644
index 50f5854c..00000000
--- a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/baa48a28-7b33-5fd6-978b-c2ec21717280.json
+++ /dev/null
@@ -1,95 +0,0 @@
-{
-    "Contact": [
-        "sdn-userdesk@seadatanet.org"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=iso19139&identifier=baa48a28-7b33-5fd6-978b-c2ec21717280",
-    "PublicationTimestamp": "2015-11-19T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "SEADATANET",
-        "IFREMER / IDM / SISMER - Scientific Information Systems for the SEA",
-        "Marine Hydrophysical Institute",
-        "Department of Navigation and Hydrography and Oceanography, Turkish Navy",
-        "National Institute for Marine Research and Development \"Grigore Antipa\"",
-        "Ukrainian scientific center of Ecology of Sea (UkrSCES)",
-        "Sinop University, Fisheries Faculty",
-        "Southern Scientific Research Institute of Marine Fisheries and Oceanography",
-        "Iv.Javakhishvili Tbilisi State University, Centre of Relations with UNESCO Oceanological Research Centre and GeoDNA (UNESCO)",
-        "IFREMER",
-        "Danube Hydro-meteorological Observatory",
-        "State Oceanographic Institute (SOI)",
-        "Odessa Branch of SOI (State Oceanographic Institute)",
-        "Institute of Fishery Resources (IFR)",
-        "Institute of Biology of the Southern Seas, NAS of Ukraine",
-        "Institute of Marine Sciences, Middle East Technical University",
-        "Zoological Institute of the Russian Academy of Sciences",
-        "Taurida V.I. Vernadsky National University",
-        "Karadeniz Technical University, Faculty of Marine Sciences",
-        "P.P.Shirshov Institute of Oceanology, RAS",
-        "Odessa branch of IBSS (Institute of Biology of Southern Seas)",
-        "IFREMER / GM-MARINE GEOSCIENCES",
-        "Scientific - Research Firm \"GAMMA\"",
-        "Bulgarian National Oceanographic Data Centre(BGODC), Institute of Oceanology",
-        "Ankara University",
-        "Far Eastern Regional Hydrometeorological Research Institute",
-        "Ukrainian Hydrometeorological Institute - Marine Branch",
-        "Shom"
-    ],
-    "ResourceType": "dataset",
-    "Rights": [
-        "No limitations on public access.  For data access please register at http://www.marine-id.org"
-    ],
-    "SpatialCoverage": "(40N-48N,27E-42E)",
-    "TempCoverageBegin": 59926651199,
-    "TempCoverageEnd": 63524087999,
-    "TemporalCoverage": " period : ( 1900-01-01T11:59:59Z - 2013-12-31T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1900-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2013-12-31T11:59:59Z",
-    "fulltext": "87052ef6-30bd-48e9-ab07-ff5598cdd336;SEADATANET;sdn-userdesk@seadatanet.org;http://www.seadatanet.org/;2018-07-24T09:47:48;ISO 19115:2003/19139 - EMODNET - SDN;0.1;4;19;1;false;WGS 84 (EPSG 4326);EPSG;Black Sea Temperature and Salinity Climatology V1.1;2015-11-19;1.1;2015-11-19;87052ef6-30bd-48e9-ab07-ff5598cdd336;Monthly temperature and salinity climatology done from the SeaDataNet aggregated dataset v1.1 by DIVA software v4.6.10. The period covers 1900-2013.\n\nFor data access please register at http://www.marine-id.org;SeaDataNet;Institute of Marine Sciences, Middle East Technical University;+90 (324) 5212406;+90 (324) 5212327;P.O.Box 28;Erdemli;33731;Turkey;http://www.ims.metu.edu.tr;web site;Institute of Marine Sciences, Middle East Technical University;+90 (324) 5212406;+90 (324) 5212327;P.O.Box 28;Erdemli;33731;Turkey;http://www.ims.metu.edu.tr;web site;IFREMER / IDM / SISMER - Scientific Information Systems for the SEA;+33 (0)2 98.22.49.16;+33 (0)2 98.22.46.44;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;sismer@ifremer.fr;http://www.ifremer.fr/sismer/;web site;Institute of Marine Sciences, Middle East Technical University;+90 (324) 5212406;+90 (324) 5212327;P.O.Box 28;Erdemli;33731;Turkey;volodymyr@ims.metu.edu.tr;http://www.ims.metu.edu.tr;web site;IFREMER;+33(0)1 46.48.21.00;+33(0)1 46.48.22.24;Technopolis 40,155 rue J.J. Rousseau;ISSY-LES-MOULINEAUX;92138;France;communication@ifremer.fr;http://wwz.ifremer.fr;web site;Ukrainian scientific center of Ecology of Sea (UkrSCES);+38 0482 636622;+380 482  636873;89 Frantsuzsky Blvd.;Odessa;65009;Ukraine;accem@te.net.ua;http://www.sea.gov.ua;web site;Scientific - Research Firm \"GAMMA\";+995 32 260 10 24;+995 32 260 44 33;17A , Guramishvili av. 0192, Tbilisi, Georgia;Tbilisi;0192;Georgia;v.gvakharia@gamma.ge;http://gamma.ge/;web site;Institute of Fishery Resources (IFR);+359 52 632066;+359 52 632066;4 Primorski Blvd\nP.O. Box 72;Varna;9000;Bulgaria;vvmihneva@yahoo.com;http://www.ifrvarna.com;web site;Ankara University;0312 596 10 00;0312 317 67 24;None;Ankara;06110;Turkey;agricul@agri.ankara.edu.tr;http://www.agri.ankara.edu.tr/;web site;Zoological Institute of the Russian Academy of Sciences;+7 812 3280711;+7\u00a0(812)\u00a0328-29-41;Universitetskaya emb., 1;St. Petersburg;199034;Russian Federation;office@zin.ru;http://www.zin.ru;web site;Taurida V.I. Vernadsky National University;+380 (652) 51 64 98;None;Prospekt Vernadskogo 4;Simferopol;95007;Ukraine;None;http://www.ccssu.crimea.ua/;web site;Danube Hydro-meteorological Observatory;None;None;None;Izmail;None;Ukraine;None;None;web site;IFREMER / GM-MARINE GEOSCIENCES;+33(0)2 98.22.42.70;+33(0)2 98.22.45.70;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;geosciences.marines@ifremer.fr;http://www.ifremer.fr/drogm/;web site;Shom;+33 (0)2 56.31.23.12;+33 (0)2 56.31.25.80;13, rue du Chatellier\nCS92803;BREST CEDEX 2;29228;France;seadatanet-admin@shom.fr;http://www.shom.fr/;web site;P.P.Shirshov Institute of Oceanology, RAS;+7(499)124-59-96;+7(499)124-59-83;36 Nakhimovsky prospect;Moscow;117997;Russian Federation;office@ocean.ru;http://www.ocean.ru;web site;Southern Scientific Research Institute of Marine Fisheries and Oceanography;+380 6561 21012;+380 6561 61627;YugNIRO, 2 Sverdlova str.;Kerch;98300;Ukraine;fish@kerch.com.ua, yugniro@kerch.com.ua;http://yugniro.crimea.com/;web site;Bulgarian National Oceanographic Data Centre(BGODC), Institute of Oceanology;+359 52 370 486;+359 52 370 483;40 Parvi may str.\nPO BOX 152;Varna;9000;Bulgaria;bgodc@io-bas.bg;http://www.bgodc.io-bas.bg;web site;Iv.Javakhishvili Tbilisi State University, Centre of Relations with UNESCO Oceanological Research Centre and GeoDNA (UNESCO);+995 32 253222;  +99532 222372;+99532 253222;1 I. Chavchavadze Ave., 0128,Tbilisi, Georgia\nIv.Javakhishvili Tbilisi State University;Tbilisi;None;Georgia;wocean@telenet.ge;http://www.oceandna.ge;web site;Institute of Marine Sciences, Middle East Technical University;+90 (324) 5212406;+90 (324) 5212327;P.O.Box 28;Erdemli;33731;Turkey;None;http://www.ims.metu.edu.tr;web site;National Institute for Marine Research and Development \"Grigore Antipa\";40 241 543288;40 241 831274;300 Mamaia Blvd.;Constanta;900581;Romania;rmri@rmri.ro;http://www.rmri.ro;web site;State Oceanographic Institute (SOI);+7 (499) 246-7288;+7 (499) 246-72-88;Kropotkinsky Lane 6;Moscow;119034;Russian Federation;adm@oceanography.ru, korshenko@mail.ru;http://www.oceanography.ru;web site;Marine Hydrophysical Institute;+380 692 54 02 52;+380 692 55 42 53;2, Kapitanskaya str.;Sevastopol;99011;Ukraine;khaliulin.alexey@nodc.org.ua;http://WWW.MHI.IUF.NET;web site;Department of Navigation and Hydrography and Oceanography, Turkish Navy;None;None;\u00c7ubuklu;Istanbul;81647;Turkey;None;None;web site;Karadeniz Technical University, Faculty of Marine Sciences;+90 462 7522805;+90 462 752 2158;\u00c7amburnu, Trabzon;Turkey;61530;Turkey;www.ktu.edu.tr;None;web site;Sinop University, Fisheries Faculty;None;None;None;Sinop;57000;Turkey;None;None;web site;Far Eastern Regional Hydrometeorological Research Institute;+7 (4232) 26-97-88;+7 (4232) 22-77-54;Fontannaya St., 24;Vladivostok;690600;Russian Federation;hydromet@online.ru;http://www.hydromet.com;web site;Institute of Biology of the Southern Seas, NAS of Ukraine;+380 692  544110;+380 692  557813;2, Nakhimov ave.;Sevastopol;99011;Ukraine;director@ibss.iuf.net;http://ibss.nas.gov.ua;web site;Ukrainian Hydrometeorological Institute - Marine Branch;+38044 525 12 50;+38044 525 53 63;37, Prospekt Nauki;Kiev;03028;Ukraine;uhmi@uhmi.org.ua;None;web site;Odessa branch of IBSS (Institute of Biology of Southern Seas);+380 482  25 13 13;+380 482  25 09 18;37, Pushkinskaya str., Odessa, 65011, UKRAINE;Odessa;65011;Ukraine;Alexandrov@paco.net;http://obibss.narod.ru;web site;Odessa Branch of SOI (State Oceanographic Institute);None;None;None;Odessa;None;Ukraine;None;None;web site;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=87052ef6-30bd-48e9-ab07-ff5598cdd336&fname=black_sea_clim.png;Oceanographic geographical features;GEMET - INSPIRE themes, version 1.0;2009-09-22T07:57:15;Temperature of the water column;Salinity of the water column;Parameter Discovery Vocabulary (P02);2014-12-11;geonetwork.thesaurus.external.parameter.NVS.P02;ITS-90 water temperature;Water body salinity;EMODNET chemistry lot aggregated parameter names;2014-12-11;geonetwork.thesaurus.external.parameter.NVS.P35;Black Sea;Sea of Azov;SeaVoX salt and fresh water body gazetteer;2014-12-11;geonetwork.thesaurus.external.reference-geographical-area.NVS.C19;Th\u00e8mes Sextant;2017-01-23;geonetwork.thesaurus.local.theme.sextant-theme;SeaDataNet licence;SeaDataNet Usage Agreement: If you use SeaDataNet data in your publications please include the following in the Acknowledgements: Data were provided through SeaDataNet Pan-European infrastructure for ocean and marine data management (https://www.seadatanet.org);No limitations on public access.  For data access please register at http://www.marine-id.org;0.1;oceans;bounding box;27;42;40.5;47.5;1900-01-01;2013-12-31;-2000;0;ftp://ftp2.ifremer.fr/public/seadatanet-black_sea-temperaturesalinity_climatologie/SDN_2015-11_TS_BlackSea_Climatology_v1.1.zip;WWW:DOWNLOAD-1.0-link--download;full dataset, netcdf files;full dataset, netcdf files;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms;OGC:WMS:getCapabilities;full dataset;full dataset;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms;OGC:WMS;Black Sea/Salinity.4Danl.nc*Salinity_L2;Salinity masked using relative error threshold 0.5;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms;OGC:WMS;Black Sea/Temperature.4Danl.nc*Temperature_L2;Temperature masked using relative error threshold 0.5;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms;OGC:WMS;Black Sea/Temperature.4Danl.nc*Temperature_L1;Temperature masked using relative error threshold 0.3;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms;OGC:WMS;Black Sea/Salinity.4Danl.nc*Salinity_L1;Salinity masked using relative error threshold 0.3;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;See the referenced specification;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "baa48a28-7b33-5fd6-978b-c2ec21717280",
-    "notes": [
-        "Monthly temperature and salinity climatology done from the SeaDataNet aggregated dataset v1.1 by DIVA software v4.6.10. The period covers 1900-2013.\n\nFor data access please register at http://www.marine-id.org"
-    ],
-    "oai_identifier": [
-        "baa48a28-7b33-5fd6-978b-c2ec21717280"
-    ],
-    "oai_set": "cams1_ps",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[27,40.5],[27,47.5],[42,47.5],[42,40.5],[27,40.5]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "Black Sea"
-        },
-        {
-            "name": "Sea Azov"
-        }
-    ],
-    "title": [
-        "Black Sea Temperature and Salinity Climatology V1.1"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/c66a1336-d7e1-5401-8748-7f3eb020e2a0.json b/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/c66a1336-d7e1-5401-8748-7f3eb020e2a0.json
deleted file mode 100644
index 1dd35863..00000000
--- a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/c66a1336-d7e1-5401-8748-7f3eb020e2a0.json
+++ /dev/null
@@ -1,95 +0,0 @@
-{
-    "Contact": [
-        "sdn-userdesk@seadatanet.org"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=iso19139&identifier=c66a1336-d7e1-5401-8748-7f3eb020e2a0",
-    "PublicationTimestamp": "2015-05-28T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "SEADATANET",
-        "Marine Hydrophysical Institute",
-        "Department of Navigation and Hydrography and Oceanography, Turkish Navy",
-        "National Institute for Marine Research and Development \"Grigore Antipa\"",
-        "Ukrainian scientific center of Ecology of Sea (UkrSCES)",
-        "Ukrainian Hydrometeorological Institute - Marine Branch",
-        "Sinop University, Fisheries Faculty",
-        "Southern Scientific Research Institute of Marine Fisheries and Oceanography",
-        "Iv.Javakhishvili Tbilisi State University, Centre of Relations with UNESCO Oceanological Research Centre and GeoDNA (UNESCO)",
-        "IFREMER",
-        "Danube Hydro-meteorological Observatory",
-        "State Oceanographic Institute (SOI)",
-        "Odessa Branch of SOI (State Oceanographic Institute)",
-        "IFREMER / IDM/SISMER",
-        "Institute of Biology of the Southern Seas, NAS of Ukraine",
-        "Institute of Marine Sciences, Middle East Technical University",
-        "Zoological Institute of the Russian Academy of Sciences",
-        "Taurida V.I. Vernadsky National University",
-        "Karadeniz Technical University, Faculty of Marine Sciences",
-        "P.P.Shirshov Institute of Oceanology, RAS",
-        "Odessa branch of IBSS (Institute of Biology of Southern Seas)",
-        "IFREMER / GM-MARINE GEOSCIENCES",
-        "Scientific - Research Firm \"GAMMA\"",
-        "Bulgarian National Oceanographic Data Centre(BGODC), Institute of Oceanology",
-        "Ankara University",
-        "Far Eastern Regional Hydrometeorological Research Institute",
-        "Institute of Fishery Resources (IFR)",
-        "Shom"
-    ],
-    "ResourceType": "dataset",
-    "Rights": [
-        "No limitations on public access.  For data access please register at http://www.marine-id.org"
-    ],
-    "SpatialCoverage": "(40N-48N,28E-42E)",
-    "TempCoverageBegin": 58931323199,
-    "TempCoverageEnd": 63518558399,
-    "TemporalCoverage": " period : ( 1868-06-17T11:59:59Z - 2013-10-28T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1868-06-17T11:59:59Z",
-    "TemporalCoverage:EndDate": "2013-10-28T11:59:59Z",
-    "fulltext": "117f66f9-22fc-4609-9be8-b58f9dd6d2b9;SEADATANET;sdn-userdesk@seadatanet.org;http://www.seadatanet.org/;2018-07-24T09:47:24;ISO 19115:2003/19139 - EMODNET - SDN;0.1;4;0;0;false;WGS 84 (EPSG 4326);EPSG;Black Sea - Temperature and salinity observation collection V1.1;seadatanet-black_sea-temperature_salinity_aggregated_public-v1_1;2015-05-28;1.1;2015-05-28;117f66f9-22fc-4609-9be8-b58f9dd6d2b9;The Black Sea historical dataset includes all open access temperature and salinity in situ data from the Black Sea and Sea of Azov for period 1868-2013. The data were retrieved from the SeaDataNet infrastructure at the beginning of 2014. Data quality has been analysed and checked using ODV software. Quality Flags of anomalous data have been revised using different QC procedures in conjunction with the visual expert check. Duplicates have been identified and excluded from the dataset.\n\nData Providers:\n- Institute of Fishery Resources (IFR)\n- Institute of Biodiversity and Ecosystem Research, Bulgarian Academy of Sciences\n- IFREMER / IDM / SISMER - Scientific Information Systems for the SEA\n- SHOM (SERVICE HYDROGRAPHIQUE ET OCEANOGRAPHIQUE DE LA MARINE)\n- All-Russia Research Institute of Hydrometeorological Information - World Data Centre (RIHMI-WDC) National Oceanographic Data Centre (NODC)\n- P.P.Shirshov Institute of Oceanology, RAS\n- Southern Scientific Research Institute of Marine Fisheries and Oceanography\n- Bulgarian National Oceanographic Data Centre(BGODC), Institute of Oceanology\n- Iv.Javakhishvili Tbilisi State University, Centre of Relations with UNESCO Oceanological Research Centre and GeoDNA (UNESCO)\n- Institute of Marine Sciences, Middle East Technical University\n- National Institute for Marine Research and Development \"Grigore Antipa\"\n- Marine Hydrophysical Institute\n- Department of Navigation and Hydrography and Oceanography, Turkish Navy\n- Karadeniz Technical University, Faculty of Marine Sciences\n- Sinop University, Fisheries Faculty\n- Institute of Biology of the Southern Seas\n- Marine branch of Ukrainian Hydrometeorological Institute\n- Ukrainian scientific center of Ecology of Sea (UkrSCES)\n- Scientific - Research Firm \"GAMMA\"\n- Georgian Institute of Hydrometeorology of Georgian Technical University (GIH)\n- Georgian Institute of Water Management of Georgian Technical University (GWMI)\n- Ankara University\n- Danube Hydro-meteorological Observatory\n\nFor data access please register at http://www.marine-id.org\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/;SeaDataNet;Institute of Marine Sciences, Middle East Technical University;+90 (324) 5212406;+90 (324) 5212327;P.O.Box 28;Erdemli;33731;Turkey;volodymyr@ims.metu.edu.tr; devrim@ims.metu.edu.tr;http://www.ims.metu.edu.tr;web site;IFREMER / IDM/SISMER;+33 (0)2 98.22.49.16;+33 (0)2 98.22.46.44;Centre IFREMER de BrestBP 70;PLOUZANE;29280;France;sismer@ifremer.fr;http://www.ifremer.fr/sismer/;web site;IFREMER;+33(0)1 46.48.21.00;+33(0)1 46.48.22.24;Technopolis 40,155 rue J.J. Rousseau;ISSY-LES-MOULINEAUX;92138;France;communication@ifremer.fr;http://wwz.ifremer.fr;web site;Ukrainian scientific center of Ecology of Sea (UkrSCES);+38 0482 636622;+380 482  636873;89 Frantsuzsky Blvd.;Odessa;65009;Ukraine;accem@te.net.ua;http://www.sea.gov.ua;web site;Scientific - Research Firm \"GAMMA\";+995 32 260 10 24;+995 32 260 44 33;17A , Guramishvili av. 0192, Tbilisi, Georgia;Tbilisi;0192;Georgia;v.gvakharia@gamma.ge;http://gamma.ge/;web site;Institute of Fishery Resources (IFR);+359 52 632066;+359 52 632066;4 Primorski Blvd\nP.O. Box 72;Varna;9000;Bulgaria;vvmihneva@yahoo.com;http://www.ifrvarna.com;web site;Ankara University;0312 596 10 00;0312 317 67 24;None;Ankara;06110;Turkey;agricul@agri.ankara.edu.tr;http://www.agri.ankara.edu.tr/;web site;Zoological Institute of the Russian Academy of Sciences;+7 812 3280711;+7\u00a0(812)\u00a0328-29-41;Universitetskaya emb., 1;St. Petersburg;199034;Russian Federation;office@zin.ru;http://www.zin.ru;web site;Taurida V.I. Vernadsky National University;+380 (652) 51 64 98;None;Prospekt Vernadskogo 4;Simferopol;95007;Ukraine;None;http://www.ccssu.crimea.ua/;web site;Danube Hydro-meteorological Observatory;None;None;None;Izmail;None;Ukraine;None;None;web site;IFREMER / GM-MARINE GEOSCIENCES;+33(0)2 98.22.42.70;+33(0)2 98.22.45.70;IFREMER Centre de Bretagne\nZI Pointe du diable\nCS 10070;PLOUZANE;29280;France;geosciences.marines@ifremer.fr;http://www.ifremer.fr/drogm/;web site;Shom;+33 (0)2 56.31.23.12;+33 (0)2 56.31.25.80;13, rue du Chatellier\nCS92803;BREST CEDEX 2;29228;France;seadatanet-admin@shom.fr;http://www.shom.fr/;web site;P.P.Shirshov Institute of Oceanology, RAS;+7(499)124-59-96;+7(499)124-59-83;36 Nakhimovsky prospect;Moscow;117997;Russian Federation;office@ocean.ru;http://www.ocean.ru;web site;Southern Scientific Research Institute of Marine Fisheries and Oceanography;+380 6561 21012;+380 6561 61627;YugNIRO, 2 Sverdlova str.;Kerch;98300;Ukraine;fish@kerch.com.ua, yugniro@kerch.com.ua;http://yugniro.crimea.com/;web site;Bulgarian National Oceanographic Data Centre(BGODC), Institute of Oceanology;+359 52 370 486;+359 52 370 483;40 Parvi may str.\nPO BOX 152;Varna;9000;Bulgaria;bgodc@io-bas.bg;http://www.bgodc.io-bas.bg;web site;Iv.Javakhishvili Tbilisi State University, Centre of Relations with UNESCO Oceanological Research Centre and GeoDNA (UNESCO);+995 32 253222;  +99532 222372;+99532 253222;1 I. Chavchavadze Ave., 0128,Tbilisi, Georgia\nIv.Javakhishvili Tbilisi State University;Tbilisi;None;Georgia;wocean@telenet.ge;http://www.oceandna.ge;web site;Institute of Marine Sciences, Middle East Technical University;+90 (324) 5212406;+90 (324) 5212327;P.O.Box 28;Erdemli;33731;Turkey;None;http://www.ims.metu.edu.tr;web site;National Institute for Marine Research and Development \"Grigore Antipa\";40 241 543288;40 241 831274;300 Mamaia Blvd.;Constanta;900581;Romania;rmri@rmri.ro;http://www.rmri.ro;web site;State Oceanographic Institute (SOI);+7 (499) 246-7288;+7 (499) 246-72-88;Kropotkinsky Lane 6;Moscow;119034;Russian Federation;adm@oceanography.ru, korshenko@mail.ru;http://www.oceanography.ru;web site;Marine Hydrophysical Institute;+380 692 54 02 52;+380 692 55 42 53;2, Kapitanskaya str.;Sevastopol;99011;Ukraine;khaliulin.alexey@nodc.org.ua;http://WWW.MHI.IUF.NET;web site;Department of Navigation and Hydrography and Oceanography, Turkish Navy;None;None;\u00c7ubuklu;Istanbul;81647;Turkey;None;None;web site;Karadeniz Technical University, Faculty of Marine Sciences;+90 462 7522805;+90 462 752 2158;\u00c7amburnu, Trabzon;Turkey;61530;Turkey;www.ktu.edu.tr;None;web site;Sinop University, Fisheries Faculty;None;None;None;Sinop;57000;Turkey;None;None;web site;Far Eastern Regional Hydrometeorological Research Institute;+7 (4232) 26-97-88;+7 (4232) 22-77-54;Fontannaya St., 24;Vladivostok;690600;Russian Federation;hydromet@online.ru;http://www.hydromet.com;web site;Institute of Biology of the Southern Seas, NAS of Ukraine;+380 692  544110;+380 692  557813;2, Nakhimov ave.;Sevastopol;99011;Ukraine;director@ibss.iuf.net;http://ibss.nas.gov.ua;web site;Ukrainian Hydrometeorological Institute - Marine Branch;+38044 525 12 50;+38044 525 53 63;37, Prospekt Nauki;Kiev;03028;Ukraine;uhmi@uhmi.org.ua;None;web site;Odessa branch of IBSS (Institute of Biology of Southern Seas);+380 482  25 13 13;+380 482  25 09 18;37, Pushkinskaya str., Odessa, 65011, UKRAINE;Odessa;65011;Ukraine;Alexandrov@paco.net;http://obibss.narod.ru;web site;Odessa Branch of SOI (State Oceanographic Institute);None;None;None;Odessa;None;Ukraine;None;None;web site;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=117f66f9-22fc-4609-9be8-b58f9dd6d2b9&fname=BlackSeaTransp.png;Oceanographic geographical features;GEMET - INSPIRE themes, version 1.0;2009-09-22T07:57:15;Temperature of the water column;Salinity of the water column;Parameter Discovery Vocabulary (P02);2015-05-12T14:18:27;geonetwork.thesaurus.external.parameter.NVS.P02;ITS-90 water temperature;Water body salinity;EMODNET chemistry lot aggregated parameter names;2014-12-11;geonetwork.thesaurus.external.parameter.NVS.P35;Black Sea;Sea of Azov;SeaVoX salt and fresh water body gazetteer;2015-05-12T14:18:28;geonetwork.thesaurus.external.reference-geographical-area.NVS.C19;Th\u00e8mes Sextant;2017-01-23;geonetwork.thesaurus.local.theme.sextant-theme;SeaDataNet licence;SeaDataNet Usage Agreement: If you use SeaDataNet data in your publications please include the following in the Acknowledgements: Data were provided through SeaDataNet Pan-European infrastructure for ocean and marine data management (https://www.seadatanet.org);No limitations on public access.  For data access please register at http://www.marine-id.org;oceans;bounding box;27.5;42;40.5;47.5;1868-06-17;2013-10-28;-2200.0;0.0;http://dx.doi.org/10.12770/117f66f9-22fc-4609-9be8-b58f9dd6d2b9;WWW:LINK-1.0-http--metadata-URL;DOI of the product;ftp://vftp2.ifremer.fr/public/seadatanet-black_sea-temperaturesalinity_aggregated/SDN_2014-03_TS_Black_Sea_QC_done_v1.1.zip;WWW:DOWNLOAD-1.0-link--download;SDN_2014-03_TS_Black_Sea_QC_done_v1.1;zipped ODV binary collection;http://www.ifremer.fr/oceanotron/wms?DATASET=SDN_2014-03_TS_Black_Sea_QC_done_v1.1;OGC:WMS:getCapabilities;full collection dataset;http://www.ifremer.fr/oceanotron/wms?DATASET=SDN_2014-03_TS_Black_Sea_QC_done_v1.1;OGC:WMS;SDN_2014-03_TS_Black_Sea_QC_done_v1.1/Pressure;Pressure;http://www.ifremer.fr/oceanotron/wms?DATASET=SDN_2014-03_TS_Black_Sea_QC_done_v1.1;OGC:WMS;SDN_2014-03_TS_Black_Sea_QC_done_v1.1/Temperature;Temperature;http://www.ifremer.fr/oceanotron/wms?DATASET=SDN_2014-03_TS_Black_Sea_QC_done_v1.1;OGC:WMS;SDN_2014-03_TS_Black_Sea_QC_done_v1.1/Salinity;Salinity;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;See the referenced specification;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "c66a1336-d7e1-5401-8748-7f3eb020e2a0",
-    "notes": [
-        "The Black Sea historical dataset includes all open access temperature and salinity in situ data from the Black Sea and Sea of Azov for period 1868-2013. The data were retrieved from the SeaDataNet infrastructure at the beginning of 2014. Data quality has been analysed and checked using ODV software. Quality Flags of anomalous data have been revised using different QC procedures in conjunction with the visual expert check. Duplicates have been identified and excluded from the dataset.\n\nData Providers:\n- Institute of Fishery Resources (IFR)\n- Institute of Biodiversity and Ecosystem Research, Bulgarian Academy of Sciences\n- IFREMER / IDM / SISMER - Scientific Information Systems for the SEA\n- SHOM (SERVICE HYDROGRAPHIQUE ET OCEANOGRAPHIQUE DE LA MARINE)\n- All-Russia Research Institute of Hydrometeorological Information - World Data Centre (RIHMI-WDC) National Oceanographic Data Centre (NODC)\n- P.P.Shirshov Institute of Oceanology, RAS\n- Southern Scientific Research Institute of Marine Fisheries and Oceanography\n- Bulgarian National Oceanographic Data Centre(BGODC), Institute of Oceanology\n- Iv.Javakhishvili Tbilisi State University, Centre of Relations with UNESCO Oceanological Research Centre and GeoDNA (UNESCO)\n- Institute of Marine Sciences, Middle East Technical University\n- National Institute for Marine Research and Development \"Grigore Antipa\"\n- Marine Hydrophysical Institute\n- Department of Navigation and Hydrography and Oceanography, Turkish Navy\n- Karadeniz Technical University, Faculty of Marine Sciences\n- Sinop University, Fisheries Faculty\n- Institute of Biology of the Southern Seas\n- Marine branch of Ukrainian Hydrometeorological Institute\n- Ukrainian scientific center of Ecology of Sea (UkrSCES)\n- Scientific - Research Firm \"GAMMA\"\n- Georgian Institute of Hydrometeorology of Georgian Technical University (GIH)\n- Georgian Institute of Water Management of Georgian Technical University (GWMI)\n- Ankara University\n- Danube Hydro-meteorological Observatory\n\nFor data access please register at http://www.marine-id.org\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/"
-    ],
-    "oai_identifier": [
-        "c66a1336-d7e1-5401-8748-7f3eb020e2a0"
-    ],
-    "oai_set": "cams1_ps",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[27.5,40.5],[27.5,47.5],[42,47.5],[42,40.5],[27.5,40.5]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "Black Sea"
-        },
-        {
-            "name": "Sea Azov"
-        }
-    ],
-    "title": [
-        "Black Sea - Temperature and salinity observation collection V1.1"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/cf2c2497-f281-59f8-a706-20ef5c0c301e.json b/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/cf2c2497-f281-59f8-a706-20ef5c0c301e.json
deleted file mode 100644
index 1097aa1a..00000000
--- a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/cf2c2497-f281-59f8-a706-20ef5c0c301e.json
+++ /dev/null
@@ -1,103 +0,0 @@
-{
-    "Contact": [
-        "sdn-userdesk@seadatanet.org"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=iso19139&identifier=cf2c2497-f281-59f8-a706-20ef5c0c301e",
-    "PublicationTimestamp": "2018-04-18T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "Marine Systems Institute at Tallinn University of Technology",
-        "Alfred-Wegener-Institute for Polar- and Marine Research",
-        "SEADATANET",
-        "GEOMAR Helmholtz Centre for Ocean Research Kiel",
-        "Aarhus University, Department of Bioscience, Marine Ecology Roskilde",
-        "Institute of Meteorology and Water Management National Research Institute, Maritime Branch in Gdynia (IMWM MB)",
-        "IFREMER / IDM/SISMER",
-        "NIOZ Royal Netherlands Institute for Sea Research",
-        "Odessa Branch of SOI (State Oceanographic Institute)",
-        "Department of Marine Research of the Environmental Protection Agency",
-        "Russian State Hydrometeorological University, St-Petersburg",
-        "Swedish Meteorological and Hydrological Institute",
-        "National Oceanography Centre, Liverpool",
-        "Institute of Marine Research",
-        "Finnish Institute of Marine Research (FIMR)",
-        "P.P.Shirshov Institute of Oceanology, RAS",
-        "Institute of Oceanology, Polish Academy of Sciences (IO PAS)",
-        "Umea Marine Sciences Centre, UMF",
-        "Shom",
-        "Environmental Protection Agency (EPA)",
-        "Stockholm Marine Research Centre, SMF"
-    ],
-    "ResourceType": "dataset",
-    "Rights": [
-        "No limitations on public access.  For data access please register at http://www.marine-id.org"
-    ],
-    "SpatialCoverage": "(53N-66N,10E-30E)",
-    "TempCoverageBegin": 59926651199,
-    "TempCoverageEnd": 63645134399,
-    "TemporalCoverage": " period : ( 1900-01-01T11:59:59Z - 2017-11-01T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1900-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2017-11-01T11:59:59Z",
-    "fulltext": "afcaabb7-0618-4bf6-9e8c-4cdd3da51fab;SEADATANET;sdn-userdesk@seadatanet.org;http://www.seadatanet.org/;2018-09-26T13:58:36;ISO 19115:2003/19139 - EMODNET - SDN;0.1;WGS 84 (EPSG 4326);EPSG;Baltic Sea - Temperature and salinity Historical Data collection SeaDataCloud V1;SDC_BAL_DATA_TS_V1;2018-04-18;1;2018-04-18;afcaabb7-0618-4bf6-9e8c-4cdd3da51fab;The SeaDataCloud  Temperature  and Salinity historical data collection for the Baltic Sea includes open access in situ data on temperature and salinity of water column. The data were retrieved from the SeaDataNet infrastructure at the end of 2017. Data have been quality controlled according to the SeaDataNet2 project QC procedures in conjunction with the visual expert check using the ODV software. The final number of stations in the collection is 407456, containing around 13.7 million values for both temperature and salinity. The dataset format is ODV binary collection which you can read, analyse and export from with the ODV application provided by the Alfred Wegener institute at http://odv.awi.de/. \n\nFor data access please register at http://www.marine-id.org/.;SeaDataNet;Swedish Meteorological and Hydrological Institute;+46-(0)11-495 80 00;+46-(0)11-495 80 01;Folkborgsvagen 1;Norrkoping;SE-601 76;Sweden;shark@smhi.se;http://www.smhi.se;web site;Swedish Meteorological and Hydrological Institute;+46-(0)11-495 80 00;+46-(0)11-495 80 01;Folkborgsvagen 1;Norrkoping;SE-601 76;Sweden;shark@smhi.se;http://www.smhi.se;web site;IFREMER / IDM/SISMER;+33 (0)2 98.22.49.16;+33 (0)2 98.22.46.44;Centre IFREMER de Brest BP 70;PLOUZANE;29280;France;sismer@ifremer.fr;http://www.ifremer.fr/sismer/;web site;Institute of Marine Research;+47 55 23 85 00;+47 55 23 85 31;Nordnesgaten 50 Postboks 1870 Nordnes;Bergen;N-5817;Norway;post@imr.no;http://www.imr.no;web site;Alfred-Wegener-Institute for Polar- and Marine Research;None;None;Am Handelshafen 12;Bremerhaven;D-27570;Germany;folke.mehrtens@awi.de;http://www.awi.de;web site;Institute of Meteorology and Water Management National Research Institute, Maritime Branch in Gdynia (IMWM MB);+48-58-62-88-100;+48-58-62-88-163;Waszyngtona 42;Gdynia;81-342;Poland;None;http://www.baltyk.pogodynka.pl/;web site;Institute of Oceanology, Polish Academy of Sciences (IO PAS);+48 58 551 72 81;+48 58 551 21 30;Powstancow Warszawy 55;Sopot;81-712;Poland;smas@iopan.gda.pl;http://www.iopan.gda.pl/;web site;Environmental Protection Agency (EPA);None;None;Juozapaviciaus st. 9;Vilnius;LT-09311;Lithuania;aaa@aaa.am.lt;http://www.gamta.lt;web site;National Oceanography Centre, Liverpool;+44 (0)151 795 4800;+44 (0)151 795 4801;Joseph Proudman Building, 6 Brownlow Street;Liverpool;L3 5DA;United Kingdom;enquiries@noc.ac.uk;http://noc.ac.uk;web site;GEOMAR Helmholtz Centre for Ocean Research Kiel;+49 431 600-0;+49 431 600-2805;D\u00fcsternbrooker Weg 20;Kiel;24105;Germany;info@geomar.de;http://www.geomar.de/en/;web site;Shom;+33 (0)2 56.31.23.12;+33 (0)2 56.31.25.80;13, rue du Chatellier CS92803;BREST CEDEX 2;29228;France;seadatanet-admin@shom.fr;http://www.shom.fr/;web site;Swedish Meteorological and Hydrological Institute;+46-(0)11-495 80 00;+46-(0)11-495 80 01;Folkborgsvagen 1;Norrkoping;SE-601 76;Sweden;shark@smhi.se;http://www.smhi.se;web site;Stockholm Marine Research Centre, SMF;+46 (0)8-16 37 18;None;Svante Arrhenius V\u00e4g 21B Frescati Backe;Stockholm;SE-114 18;Sweden;smf@smf.su.se;http://www.smf.su.se;web site;Umea Marine Sciences Centre, UMF;+46 (0)90-786 79 74;+46 (0)90-786 99 75;Norrbyn;H\u00f6rnefors;SE-910 20;Sweden;info@umf.umu.se;http://www.umf.umu.se/;web site;Finnish Institute of Marine Research (FIMR);+358 9 613 941;+358 9 323 2970;Erik Palm\u00e9nin aukio 1 P.O.Box 2;Helsinki;00561;Finland;None;http://www.fimr.fi/en/en_GB/en/;web site;NIOZ Royal Netherlands Institute for Sea Research;+31 222 369300;+31 222 319674;Landsdiep 4 P.O. Box 59;Den Burg/Texel;1790 AB;Netherlands;dmg@nioz.nl;https://www.nioz.nl;web site;Department of Marine Research of the Environmental Protection Agency;+370 46 41 04 50;+370 46 41 04 60;Taikos Av. 26;Klaipeda;LT-91149;Lithuania;jtd@aaa.am.lt;http://www.gamta.lt/;web site;P.P.Shirshov Institute of Oceanology, RAS;+7(499)124-59-96;+7(499)124-59-83;36 Nakhimovsky prospect;Moscow;117997;Russian Federation;office@ocean.ru;http://www.ocean.ru;web site;Marine Systems Institute at Tallinn University of Technology;+372 6204300;None;MSI, Akadeemia tee 15a;Tallinn;12618;Estonia;msi@msi.ttu.ee;http://www.msi.ttu.ee;web site;Aarhus University, Department of Bioscience, Marine Ecology Roskilde;+45 8715000;+45 87154326;399 Frederiksborgvej P.O. Box 358;Roskilde;DK-4000;Denmark;None;http://bios.au.dk/en/;web site;Russian State Hydrometeorological University, St-Petersburg;None;None;98, Maloohtinsky Pr.;St.-Petersburg;195196;Russian Federation;rector@rshu.ru;http://www.rshi.nw.ru/win/home-ru.htm;web site;Odessa Branch of SOI (State Oceanographic Institute);None;None;None;Odessa;None;Ukraine;None;None;web site;https://sextant.ifremer.fr/geonetwork/srv/fre//resources.get?uuid=afcaabb7-0618-4bf6-9e8c-4cdd3da51fab&fname=BALTIC_SDC_V1.png;Oceanographic geographical features;GEMET - INSPIRE themes, version 1.0;2018-07-27;geonetwork.thesaurus.external.theme.httpinspireeceuropaeutheme-theme;Temperature of the water column;Salinity of the water column;Parameter Discovery Vocabulary (P02);2017-11-17;geonetwork.thesaurus.external.parameter.NVS.P02;Water body salinity;ITS-90 water temperature;EMODNET chemistry lot aggregated parameter names;2016-09-20;geonetwork.thesaurus.external.parameter.NVS.P35;Baltic Sea;Bay of Bothnia;Central Baltic Sea;Gulf of Bothnia;Gulf of Finland;Kattegat;Lillebaelt;Storebaelt;Skagerrak;SeaVoX salt and fresh water body gazetteer;2016-09-20;geonetwork.thesaurus.external.reference-geographical-area.NVS.C19;Th\u00e8mes Sextant;2018-05-24;geonetwork.thesaurus.local.theme.sextant-theme;SeaDataNet licence;SeaDataNet Usage Agreement: If you use SeaDataNet data in your publications please include the following in the Acknowledgements: Data were provided through SeaDataNet Pan-European infrastructure for ocean and marine data management (https://www.seadatanet.org);No limitations on public access.  For data access please register at http://www.marine-id.org;oceans;bounding box;10;30;53;66.5;1900-01-01;2017-11-01;-500.0;0.0;ODV binary collection;5;http://dx.doi.org/10.12770/afcaabb7-0618-4bf6-9e8c-4cdd3da51fab;WWW:LINK-1.0-http--metadata-URL;DOI of the product;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;See the referenced specification;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "cf2c2497-f281-59f8-a706-20ef5c0c301e",
-    "notes": [
-        "The SeaDataCloud  Temperature  and Salinity historical data collection for the Baltic Sea includes open access in situ data on temperature and salinity of water column. The data were retrieved from the SeaDataNet infrastructure at the end of 2017. Data have been quality controlled according to the SeaDataNet2 project QC procedures in conjunction with the visual expert check using the ODV software. The final number of stations in the collection is 407456, containing around 13.7 million values for both temperature and salinity. The dataset format is ODV binary collection which you can read, analyse and export from with the ODV application provided by the Alfred Wegener institute at http://odv.awi.de/. \n\nFor data access please register at http://www.marine-id.org/."
-    ],
-    "oai_identifier": [
-        "cf2c2497-f281-59f8-a706-20ef5c0c301e"
-    ],
-    "oai_set": "cams1_ps",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[10,53],[10,66.5],[30,66.5],[30,53],[10,53]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Baltic Sea"
-        },
-        {
-            "name": "Bay Bothnia"
-        },
-        {
-            "name": "Central Baltic Sea"
-        },
-        {
-            "name": "Gulf Bothnia"
-        },
-        {
-            "name": "Gulf Finland"
-        },
-        {
-            "name": "Kattegat"
-        },
-        {
-            "name": "Lillebaelt"
-        }
-    ],
-    "title": [
-        "Baltic Sea - Temperature and salinity Historical Data collection SeaDataCloud V1"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/d3c6327d-c751-5725-81ad-1129aef86f69.json b/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/d3c6327d-c751-5725-81ad-1129aef86f69.json
deleted file mode 100644
index c5080744..00000000
--- a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/d3c6327d-c751-5725-81ad-1129aef86f69.json
+++ /dev/null
@@ -1,150 +0,0 @@
-{
-    "Contact": [
-        "sdn-userdesk@seadatanet.org"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=iso19139&identifier=d3c6327d-c751-5725-81ad-1129aef86f69",
-    "PublicationTimestamp": "2018-04-27T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "SEADATANET",
-        "IFREMER / IDM / SISMER - Scientific Information Systems for the SEA",
-        "Royal Belgian Institute of Natural Sciences, Management Unit of North Sea and Scheldt Estuary Mathematical Models",
-        "Atlantic Scientific Research Institute for Marine Fishery and Oceanography",
-        "Environment Agency Solent and South Downs Area Office",
-        "IFREMER / IDM/SISMER",
-        "Th\u00fcnen-Institute of Fisheries Ecology (TI-FI)",
-        "All-Russia Research Institute of Hydrometeorological Information - World Data Centre (RIHMI-WDC) National Oceanographic Data Centre (NODC)",
-        "Institute of Oceanographic Sciences, Bidston Laboratory",
-        "Lower Saxony Water Management, Coastal Defense and Nature Conservation Agency",
-        "British Oceanographic Data Centre",
-        "University of Plymouth, Institute of Marine Studies",
-        "IFREMER / RBE Department / Biogeochimical end Ecotoxicological Resarch Unit (Nantes)",
-        "Scottish Environment Protection Agency, Edinburgh Office",
-        "Swedish Meteorological and Hydrological Institute",
-        "Institute of Biochemistry and Food Chemistry, University Hamburg",
-        "National Oceanography Centre, Liverpool",
-        "Danish Institute for Fisheries Research, Dept. of Marine Fisheries",
-        "Faroese Fisheries Laboratory",
-        "Environment Agency South East Regional Office",
-        "IFREMER / CENTRE MANCHE - MER DU NORD",
-        "Environment Agency South West Regional Office",
-        "Polytechnic South West Institute of Marine Studies",
-        "Shom",
-        "Environment Agency Head Office",
-        "Polar Scientific Research Institute of Fishery and Oceanography",
-        "Marine Systems Institute at Tallinn University of Technology",
-        "Roscoff Marine Station, Sorbonne Universit\u00e9s, UPMC Univ Paris 06 and CNRS",
-        "IFREMER",
-        "Proudman Oceanographic Laboratory",
-        "Institute of Marine Research",
-        "Wimereux Marine Station (University of Sciences and Technologies of Lille 1)",
-        "Scottish Office Agriculture Environment and Fisheries Department - Aberdeen Marine Laboratory",
-        "Federal Research Institute for Rural Areas, Forestry and Fisheries (VTI)",
-        "Th\u00fcnen-Institute of Sea Fisheries (TI-SF)",
-        "NIOZ Royal Netherlands Institute for Sea Research",
-        "Murmansk Hydrometeorological Administration of Roshydromet",
-        "Royal Belgian Institute of Natural Sciences, Management Unit of North Sea and Scheldt Estuary Mathematical Models, Ostend",
-        "Scottish Association for Marine Science",
-        "IFREMER / DYNECO- Coastal Environment Dynamics department",
-        "University of Southampton Department of Oceanography",
-        "Far Eastern Regional Hydrometeorological Research Institute",
-        "Navy Main Administration of Navigation and Oceanography, Ministry of Defence",
-        "German Oceanographic Datacentre (NODC)",
-        "UNKNOWN",
-        "Universit\u00e9 Libre de Bruxelles, Ecology of Aquatic systems",
-        "Department of Safety and Quality of Milk and Fish Products (Max Rubner)",
-        "Dunstaffnage Marine Laboratory",
-        "DTU Aqua \u2013 National Institute of Aquatic Resources, Technical University of Denmark",
-        "Federal Maritime and Hydrographic Agency",
-        "CEA / INSTITUT DE RADIOPROTECTION ET DE SURETE NUCLEAIRE",
-        "Odessa Branch of SOI (State Oceanographic Institute)",
-        "Universit\u00e9 Libre de Bruxelles, Laboratory of Chemical Oceanography and Water Geochemistry",
-        "Federal Research Centre for Fisheries (Hamburg)",
-        "IHE, Management Unit of North Sea and Scheldt Estuary Mathematical Models, Ostend",
-        "Flanders Marine Institute",
-        "Institute of Marine Research - Norwegian Marine Data Centre (NMD)",
-        "Scottish Environment Protection Agency, Angus Smith Building",
-        "Management Unit of North Sea and Scheldt Estuary Mathematical Models, Belgian Marine Data Centre",
-        "Scottish Office Agriculture and Fisheries Department - Aberdeen Marine Laboratory",
-        "STATION MARINE DE DINARD",
-        "Department of Agriculture and Fisheries for Scotland - Aberdeen Marine Laboratory",
-        "Institute of Oceanographic Sciences Wormley Laboratory",
-        "Newcastle University Department of Marine Science and Coastal Management",
-        "Marine Hydrophysical Institute",
-        "Marine Scotland Science",
-        "Institute of Fisheries Ecology - Cuxhaven (VTI-CUX)",
-        "National Oceanography Centre, Southampton",
-        "Fisheries Research Services, Aberdeen Marine Laboratory",
-        "Federal Research Centre for Fisheries (Cuxhaven)",
-        "Universite du Littoral Cote d'Opale / Oceanology and Geosciences Laboratory - UMR 8187 (LOG)",
-        "GEOMAR Helmholtz Centre for Ocean Research Kiel",
-        "Rijkswaterstaat Water, Traffic and Environment",
-        "Scottish Marine Biological Association",
-        "Royal Belgian Institute of Natural Sciences, Operational Directorate Natural Environment, Belgian Marine Data Centre",
-        "International Council for the Exploration of the Sea (ICES)",
-        "Marine Institute",
-        "Alfred-Wegener-Institute for Polar- and Marine Research",
-        "IFREMER / STATION PORT EN BESSIN",
-        "State Office for Agriculture, Environment and Rural Areas of Schleswig Holstein (LLUR)",
-        "Lithuanian Hydrometeorological Service under the Ministry of Environment",
-        "Aarhus University, Department of Bioscience, Marine Ecology Roskilde",
-        "State Agency for Nature and Environment of Schleswig Holstein (LANU)",
-        "IFREMER / HMMN-DEPARTEMENT HALIEUTIQUE DE MANCHE-MER DU NORD",
-        "University of Wales, School of Ocean Sciences",
-        "Plymouth Marine Laboratory"
-    ],
-    "ResourceType": "dataset",
-    "Rights": [
-        "No limitations on public access.  For data access please register at http://www.marine-id.org."
-    ],
-    "SpatialCoverage": "(49N-62N,4 W-10E)",
-    "TempCoverageBegin": 59705812799,
-    "TempCoverageEnd": 63650318399,
-    "TemporalCoverage": " period : ( 1893-01-01T11:59:59Z - 2017-12-31T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1893-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2017-12-31T11:59:59Z",
-    "fulltext": "d9310aa6-c6b3-4657-a3c9-b0a4dd0f016c;SEADATANET;sdn-userdesk@seadatanet.org;http://www.seadatanet.org/;2018-09-26T16:27:14;ISO 19115:2003/19139 - EMODNET - SDN;0.1;WGS 84 (EPSG 4326);EPSG;North Sea - Temperature and salinity Historical Data Collection SeaDataCloud V1;SDC_NS_DATA_TS_V1;2018-04-27;1;2018-04-27;d9310aa6-c6b3-4657-a3c9-b0a4dd0f016c;The data collection of the North Sea is divided in two datasets : the discrete collection and the trajectories collection.\n\nThe Discrete SeaDataCloud Temperature and Salinity Historical Data Collection for the North Sea includes open access in situ data on temperature and salinity measured with \u201cdiscrete\u201d instruments (CTD, XBT, discrete water samplers\u2026). The data span between 4\u00b0W and 10\u00b0E in longitude, and from 49\u00b0N to 62\u00b0N in latitude. It covers the time period 1893 \u2013 2017. The data were retrieved from the SeaDataNet infrastructure in November 2017. \nThe \u201cTrajectories\u201d SeaDataCloud Temperature and Salinity Historical Data Collection for the North Sea includes open access in situ data on temperature and salinity measured by continuously recording sensors (e.g. Ferryboxes). The data span between 4\u00b0W and 10\u00b0E in longitude, and from 49\u00b0N to 62\u00b0N in latitude. It covers the time period 1989 \u2013 2017. \n\nThe data were retrieved from the SeaDataNet infrastructure in November 2017. The quality control of the data has been performed with the help of ODV software. Data Quality Flags have been revised following common recommended procedures defined under SeaDataNet 2 project in conjunction with visual expert check. \n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/.\n\nFor data access please register at http://www.marine-id.org/.;SeaDataNet;Royal Belgian Institute of Natural Sciences, Operational Directorate Natural Environment, Belgian Marine Data Centre;+32 (0)2 773 2111;+32 (0)2 770 6972;Gulledelle 100;Brussels;1200;Belgium;bmdc@mumm.ac.be;http://www.mumm.ac.be/datacentre/;web site;Royal Belgian Institute of Natural Sciences, Operational Directorate Natural Environment, Belgian Marine Data Centre;+32 (0)2 773 2111;+32 (0)2 770 6972;Gulledelle 100;Brussels;1200;Belgium;bmdc@mumm.ac.be;http://www.mumm.ac.be/datacentre/;web site;Royal Belgian Institute of Natural Sciences, Operational Directorate Natural Environment, Belgian Marine Data Centre;+32 (0)2 773 2111;+32 (0)2 770 6972;Gulledelle 100;Brussels;1200;Belgium;bmdc@mumm.ac.be;http://www.mumm.ac.be/datacentre/;web site;IFREMER / IDM/SISMER;+33 (0)2 98.22.49.16;+33 (0)2 98.22.46.44;Centre IFREMER de BrestBP 70;PLOUZANE;29280;France;sismer@ifremer.fr;http://www.ifremer.fr/sismer/;web site;University of Plymouth, Institute of Marine Studies;Drake Circus;Plymouth;PL4 8AA;United Kingdom;inapplicable;http://www.plymouth.ac.uk/plymouth/main.htm;web site;National Oceanography Centre, Southampton;University of Southampton Waterfront Campus European Way;Southampton;SO14 3ZH;United Kingdom;enquiries@noc.ac.uk;http://noc.ac.uk;web site;University of Wales, School of Ocean Sciences;School of Ocean Sciences, University of Wales Bangor, Menai Bridge, Anglesey,;Menai Bridge;LL59 5AB;United Kingdom;inapplicable;http://www.sos.bangor.ac.uk/;web site;Fisheries Research Services, Aberdeen Marine Laboratory;+44 (0)1224 876544;+44 (0)1224 295511;PO Box 101 Victoria Road;Aberdeen;AB11 9DB;United Kingdom;inapplicable;http://www.marlab.ac.uk;web site;British Oceanographic Data Centre;+44 (0)151 653 8633;+44 (0)151 652 3950;Bidston Observatory;Prenton;CH43 7RA;United Kingdom;bodcmail@ccms.ac.uk;http://www.bodc.ac.uk;web site;Scottish Association for Marine Science;Argyll;PA37 1QA;United Kingdom;laurence.mee@sams.ac.uk;http://www.sams.ac.uk;web site;Plymouth Marine Laboratory;+44 (0)1752 633 100;+44 (0)1752 633101;Prospect Place The Hoe;Plymouth;PL1 3DH;United Kingdom;forinfo@pml.ac.uk;http://www.pml.ac.uk;web site;Environment Agency Head Office;+44 (0)3708 506 506;Horizon House;Bristol;BS1 5AH;United Kingdom;enquiries@environment-agency.gov.uk;https://www.gov.uk/government/organisations/environment-agency;web site;German Oceanographic Datacentre (NODC);+49 40 3190 3410;+49 40 3190 5000;Bernhard-Nocht-Strasse 78;Hamburg;20359;Germany;friedrich.nast@bsh.de;http://www.bsh.de/en/Marine_data/Observations/DOD_Data_Centre/index.jsp;web site;Universit\u00e9 Libre de Bruxelles, Laboratory of Chemical Oceanography and Water Geochemistry;+ 32-2-650.52.37 / 650.52.13;+ 32-2-650.52.28;Boulevard du Triomphe/Triomflaan, CP 208;Brussels;1050;Belgium;lei.chou@ulb.ac.be;http://www.ulb.ac.be/sciences/dste/ocean/;web site;Marine Institute;Ireland;datarequests@marine.ie;Flanders Marine Institute;+32 59 34 21 30;+32 59 34 21 31;Wandelaarkaai 7;Oostende;8400;Belgium;data@vliz.be;http://www.vliz.be/;web site;Royal Belgian Institute of Natural Sciences, Management Unit of North Sea and Scheldt Estuary Mathematical Models, Ostend;+32 59 24 20 50;+32 59 70 49 35;c/o Mijnenbestrijdingsschool;Oostende;8400;Belgium;bmmost@mumm.ac.be;http://www.mumm.ac.be;web site;Royal Belgian Institute of Natural Sciences, Management Unit of North Sea and Scheldt Estuary Mathematical Models;Belgium;inapplicable;Universit\u00e9 Libre de Bruxelles, Ecology of Aquatic systems;+32 2 650 59 89;+32 2 650 59 93;Boulevard du Triomphe/Triomflaan, CP 221;Brussels;1050;Belgium;lancelot@ulb.ac.be;http://esa.ulb.ac.be/;web site;IFREMER / IDM / SISMER - Scientific Information Systems for the SEA;+33 (0)2 98.22.49.16;+33 (0)2 98.22.46.44;IFREMER Centre de Bretagne ZI Pointe du diable CS 10070;PLOUZANE;29280;France;sismer@ifremer.fr;http://www.ifremer.fr/sismer/;web site;IFREMER / STATION PORT EN BESSIN;+33 (0)2 31 51 13 00;+33 (0)2 31 51 13 01;Avenue du General de Gaulle, B.P. 32;PORT EN BESSIN;14520;France;inapplicable;http://wwz.ifremer.fr/manchemerdunord/Implantations/Port-en-Bessin;web site;Roscoff Marine Station, Sorbonne Universit\u00e9s, UPMC Univ Paris 06 and CNRS;+33(0)2 98.29.23.23;+33 (0)2 98.29.23.24;Place Georges Teissier;ROSCOFF;29680;France;inapplicable;http://www.sb-roscoff.fr/;web site;IFREMER / RBE Department / Biogeochimical end Ecotoxicological Resarch Unit (Nantes);+33 (0)2 40 37 41 93;33(0)2 40.37.40.75;IFREMER Centre de Nantes Rue de l'Ile d'Yeu BP 1105;NANTES CEDEX 03;44311;France;inapplicable;http://www.ifremer.fr/delpc/;web site;Shom;+33 (0)2 56.31.23.12;+33 (0)2 56.31.25.80;13, rue du Chatellier CS92803;BREST CEDEX 2;29228;France;seadatanet-admin@shom.fr;http://www.shom.fr/;web site;IFREMER / HMMN-DEPARTEMENT HALIEUTIQUE DE MANCHE-MER DU NORD;+33 (0)3 21.99.56.00;+33 (0)3 21.99.56.01;IFREMER Centre de Boulogne sur Mer 150 quai Gambetta BP 70;BOULOGNE-SUR-MER CEDEX;62321;France;inapplicable;http://www.ifremer.fr/boulogne/;web site;Swedish Meteorological and Hydrological Institute;+46-(0)11-495 80 00;+46-(0)11-495 80 01;Folkborgsvagen 1;Norrkoping;SE-601 76;Sweden;shark@smhi.se;http://www.smhi.se;web site;Institute of Marine Research - Norwegian Marine Data Centre (NMD);+47-55238500;+47-55238584;Nordnesgaten 50 Postboks 1870 Nordnes;Bergen;N-5817;Norway;nmd@imr.no, nod@imr.no;http://www.imr.no;web site;NIOZ Royal Netherlands Institute for Sea Research;+31 222 369300;+31 222 319674;Landsdiep 4 P.O. Box 59;Den Burg/Texel;1790 AB;Netherlands;dmg@nioz.nl;https://www.nioz.nl;web site;All-Russia Research Institute of Hydrometeorological Information - World Data Centre (RIHMI-WDC) National Oceanographic Data Centre (NODC);+74843974907;6 Korolyov St.;Obninsk;249035;Russian Federation;nodc@meteo.ru;http://nodc.meteo.ru;web site;Atlantic Scientific Research Institute for Marine Fishery and Oceanography;8 (0112) 21-56-45;8 (0112) 21-99-97;5, Dm. Donskoi St.;Kaliningrad reg;236000;Russian Federation;atlant@baltnet.ru;http://www.atlantniro.ru/;web site;Marine Systems Institute at Tallinn University of Technology;+372 6204300;MSI, Akadeemia tee 15a;Tallinn;12618;Estonia;msi@msi.ttu.ee;http://www.msi.ttu.ee;web site;Marine Hydrophysical Institute;+380 692 54 02 52;+380 692 55 42 53;2, Kapitanskaya str.;Sevastopol;99011;Ukraine;khaliulin.alexey@nodc.org.ua;http://WWW.MHI.IUF.NET;web site;Aarhus University, Department of Bioscience, Marine Ecology Roskilde;+45 8715000;+45 87154326;399 Frederiksborgvej P.O. Box 358;Roskilde;DK-4000;Denmark;inapplicable;http://bios.au.dk/en/;web site;International Council for the Exploration of the Sea (ICES);+45 3338 6700;+45 3393 4215;H. C. Andersens Boulevard 44-46;Copenhagen V;DK-1553;Denmark;info@ices.dk;http://www.ices.dk;web site;Far Eastern Regional Hydrometeorological Research Institute;+7 (4232) 26-97-88;+7 (4232) 22-77-54;Fontannaya St., 24;Vladivostok;690600;Russian Federation;hydromet@online.ru;http://www.hydromet.com;web site;Lithuanian Hydrometeorological Service under the Ministry of Environment;+370 5 275 1194;+370 5 272 8874;6 Rudnios Str.;Vilnius;LT-09300;Lithuania;lhmt@meteo.lt,;http://www.meteo.lt;web site;Murmansk Hydrometeorological Administration of Roshydromet;23, Shmidt St.;Murmansk;183789;Russian Federation;leader@kolgimet.murman.ru;http://www.kolgimet.ru/;web site;Navy Main Administration of Navigation and Oceanography, Ministry of Defence;+7 (812) 717 5900;2 Atamanskaya Ul.;St. Petersburg;193167;Russian Federation;suvvlad@mail.ru;http://okeany.com/vk/gunio.htm;web site;Polar Scientific Research Institute of Fishery and Oceanography;6, Knipovich St.;Murmansk;183763;Russian Federation;persey@pinro.ru;http://www.pinro.ru/;web site;Odessa Branch of SOI (State Oceanographic Institute);Odessa;Ukraine;accem@te.net.ua;web site;Federal Research Centre for Fisheries (Cuxhaven);04721-38035;BFAFi, Institut fuer Fischereioekologie, Deichstrasse 12;Cuxhaven;27472;Germany;t.lang@t-online.de;http://www.bfa-fisch.de;web site;Federal Research Centre for Fisheries (Hamburg);(+49) 40 38905-0;+49) 40 38905-200;Palmaille 9;Hamburg;22767;Germany;info@ish.bfa-fisch.de;http://www.bfa-fisch.de;web site;IFREMER / DYNECO- Coastal Environment Dynamics department;+33 (0)2 98.22.43.51;+33 (0)2 98 22 45.48;IFREMER Centre de Bretagne ZI Pointe du diable CS 10070;PLOUZANE;29280;France;inapplicable;http://www.ifremer.fr/anglais/org/del.htm;web site;Wimereux Marine Station (University of Sciences and Technologies of Lille 1);+33 (0)3 21.99.29.00;+33 (0)3 21.99.29.01;28, Avenue Foch;WIMEREUX;62930;France;inapplicable;http://sm-wimereux.univ-lille1.fr/accueil/actualites/index.php;web site;IFREMER / CENTRE MANCHE - MER DU NORD;+33 (0)3 21.99.56.00;+33 (0)3 21.99.56.01;IFREMER Centre de Boulogne sur Mer 150 quai Gambetta BP 70;BOULOGNE-SUR-MER CEDEX;62321;France;inapplicable;http://wwz.ifremer.fr/manchemerdunord/Environnement/LER-Boulogne-sur-Mer;web site;CEA / INSTITUT DE RADIOPROTECTION ET DE SURETE NUCLEAIRE;+33(0)2 33.01.41.00;LABORATOIRE DE RADIOECOLOGIE MARINE,RUE MAX POL FOUCHET,BP 10;OCTEVILLE;50130;France;inapplicable;http://www.irsn.org/en/;web site;UNKNOWN;UNKNOWN;UNKNOWN;Unknown;inapplicable;web site;IFREMER;+33(0)5 46.50.94.40;+33(0)5 46.50.06.60;Centre de Recherche sur Ecosyst\u00e8mes Littoraux Anthropis\u00e9s Place du S\u00e9minaire BP 7;L'HOUMEAU;17137;France;communication@ifremer.fr;web site;Danish Institute for Fisheries Research, Dept. of Marine Fisheries;Charlottenlund Slot;Charlottenlund;DK-2920;Denmark;inapplicable;http://www.aqua.dtu.dk/English.aspx;web site;State Agency for Nature and Environment of Schleswig Holstein (LANU);+49 4347 704-0;+49 4347 704 102;Hamburger Chaussee 25;Flintbek;24220;Germany;infonet@lanu.landsh.de;http://www.umwelt.schleswig-holstein.de/servlet/is/1/;web site;Institute of Biochemistry and Food Chemistry, University Hamburg;+49 40 42838 5733;+49 40 42838 4243;Martin-Luther-King-Pl.6;Hamburg;20146;Germany;mon@uni-hamburg.de;http://www.chemie.uni-hamburg.de/lc/index_e.html;web site;Lower Saxony Water Management, Coastal Defense and Nature Conservation Agency;+49 5121 509 207;+49 5121 509 196;An der Scharlake 39;Hildesheim;31135;Germany;Dieter.Steffen@nlwkn-hi.niedersachsen.de;http://www.nlwkn.de;web site;Institute of Marine Research;Norway;post@imr.no;Alfred-Wegener-Institute for Polar- and Marine Research;Columbuscenter B\u00fcrgermeister-Smidt-Stra\u00dfe 20;Bremerhaven;27568;Germany;folke.mehrtens@awi.de;http://www.awi-bremerhaven.de;web site;STATION MARINE DE DINARD;+33 (0)2.99.46.13.90;+33 (0)2 99 88 29 42;Museum National d'Histoire Naturelle 17, avenue Georges V BP 28;DINARD;35801;France;station.marine.mnhn@wanadoo.fr;http://www.mnhn.fr/fr/recherche-expertise/stations-marines/station-biologie-marine-dinard-cresco;web site;Rijkswaterstaat Water, Traffic and Environment;+31 320298411;Zuiderwagenplein 2;Lelystad;8224 AD;Netherlands;inapplicable;http://www.rijkswaterstaat.nl/en/about_us/our_organization/;web site;Th\u00fcnen-Institute of Sea Fisheries (TI-SF);+49-40-389050;+40-40-38905129;Palmaille 9;Hamburg;Germany;sf@ti.bund.de;http://www.ti.bund.de/;web site;Th\u00fcnen-Institute of Fisheries Ecology (TI-FI);+49-40-389050;+49 40 38905 261;Palmaille 9;Hamburg;22767;Germany;foe@vti.bund.de;http://www.vti.bund.de/en/institutes/foe/;web site;Federal Research Institute for Rural Areas, Forestry and Fisheries (VTI);+49-531-596-0;+49-531-596-1099;Bundesallee 50;Braunschweig;38116;Germany;info@vti.bund.de;http://www.vti.bund.de;web site;Institute of Fisheries Ecology - Cuxhaven (VTI-CUX);+49-4721 38034;+49-4721 53583;Deichstr. 12;Cuxhaven;27472;Germany;foe@vti.bund.de;http://www.vti.bund.de/en/institutes/foe/;web site;Management Unit of North Sea and Scheldt Estuary Mathematical Models, Belgian Marine Data Centre;+32 (0)2 773 2111;+32 (0)2 770 6972;Gulledelle 100;Brussels;1200;Belgium;bmdc@mumm.ac.be;http://www.bmdc.be;web site;Faroese Fisheries Laboratory;(+298) 35 39 00;(+298) 35 39 01;PO Box 3051, N\u00f3at\u00fan 1;T\u00f3rshavn;FO-110;Faroe Islands;fishlab@frs.fo;http://www.frs.fo;web site;University of Southampton Department of Oceanography;University of Southampton Waterfront Campus, European Way;Southampton;SO14 3ZH;United Kingdom;inapplicable;web site;University of Southampton Department of Oceanography;Highfield Campus;Southampton;SO9 5NH;United Kingdom;inapplicable;web site;Federal Maritime and Hydrographic Agency;Bernhard-Nocht-Strasse 78;Hamburg;20359;Germany;osteingang@bsh.de;http://www.bsh.de/;web site;Universite du Littoral Cote d'Opale / Oceanology and Geosciences Laboratory - UMR 8187 (LOG);+33(0)3 21 99 29 00;+33(0)3 21 99 29 01;28, avenue Foch BP 80;WIMEREUX;62930;France;francois.schmitt@univ-lille1.fr (directeur de recherche);http://log.univ-littoral.fr/;web site;Scottish Office Agriculture Environment and Fisheries Department - Aberdeen Marine Laboratory;PO Box 101 375 Victoria Road;Aberdeen;AB11 9DB;United Kingdom;inapplicable;web site;Scottish Office Agriculture and Fisheries Department - Aberdeen Marine Laboratory;United Kingdom;inapplicable;Department of Agriculture and Fisheries for Scotland - Aberdeen Marine Laboratory;United Kingdom;inapplicable;Institute of Oceanographic Sciences Wormley Laboratory;Brook Road Wormley;Godalming;GU8 5UB;United Kingdom;inapplicable;web site;Proudman Oceanographic Laboratory;Joseph Proudman Building 6 Brownlow Street;Liverpool;L3 5DA;United Kingdom;inapplicable;http://www.pol.ac.uk;web site;Institute of Oceanographic Sciences, Bidston Laboratory;Bidston Observatory Bidston Hill;Prenton;L43 7RA;United Kingdom;inapplicable;web site;Marine Scotland Science;+44 (0)1224 876544;+44 (0)1224 295511;Marine Laboratory, PO Box 101;Aberdeen;AB11 9DB;United Kingdom;inapplicable;web site;DTU Aqua \u2013 National Institute of Aquatic Resources, Technical University of Denmark;+ 45 33 96 33 00;+ 45 33 96 33 33;Kavalerg\u00e5rden 6;Charlottenlund;2920;Denmark;aqua@aqua.dtu.dk;http://www.aqua.dtu.dk/English;web site;Department of Safety and Quality of Milk and Fish Products (Max Rubner);+49 (0)431 609 1;+49 (0)431 609 2222;Hermann-Weigmann-Stra\u00dfe 1;Kiel;24103;Germany;inapplicable;http://www.mri.bund.de/en/de/institute/department-of-safety-and-quality-of-milk-and-fish-products.html;web site;Polytechnic South West Institute of Marine Studies;Drake Circus;Plymouth;PL4 8AA;United Kingdom;inapplicable;web site;National Oceanography Centre, Liverpool;+44 (0)151 795 4800;+44 (0)151 795 4801;Joseph Proudman Building, 6 Brownlow Street;Liverpool;L3 5DA;United Kingdom;enquiries@noc.ac.uk;http://noc.ac.uk;web site;Newcastle University Department of Marine Science and Coastal Management;Armstrong Building;Newcastle upon Tyne;NE1 7RU;United Kingdom;inapplicable;web site;Dunstaffnage Marine Laboratory;Dunbeg;Oban;PA37 1QA;United Kingdom;inapplicable;web site;Scottish Marine Biological Association;Dunbeg;Oban;PA37 1QA;United Kingdom;inapplicable;web site;State Office for Agriculture, Environment and Rural Areas of Schleswig Holstein (LLUR);+49-4347 704-0;+49-4347 704-102;Hamburger Chaussee 25;Flintbek;24220;Germany;poststelle@llur.landsh.de;http://www.schleswig-holstein.de/LLUR/DE/LLUR_node.html;web site;GEOMAR Helmholtz Centre for Ocean Research Kiel;+49 431 600-0;+49 431 600-2805;D\u00fcsternbrooker Weg 20;Kiel;24105;Germany;info@geomar.de;http://www.geomar.de/en/;web site;Scottish Environment Protection Agency, Edinburgh Office;+44 (0)131 449 7296;+44 (0)131 449 7277;Clearwater House, Heriot Watt Research Park;Edinburgh;EH14 4AP;United Kingdom;inapplicable;http://www.sepa.org.uk/;web site;IHE, Management Unit of North Sea and Scheldt Estuary Mathematical Models, Ostend;3de en 23ste Linieregimentsplein;Oostende;8400;Belgium;inapplicable;web site;Environment Agency South West Regional Office;+44 (0)370 8506506;Manley House;Exeter;EX2 7LQ;United Kingdom;enquiries@environment-agency.gov.uk;https://www.gov.uk/government/organisations/environment-agency;web site;Environment Agency South East Regional Office;+44 (0)3708 506 506;Kings Meadow House;Reading;RG1 8DQ;United Kingdom;enquiries@environment-agency.gov.uk;https://www.gov.uk/government/organisations/environment-agency;web site;Environment Agency Solent and South Downs Area Office;+44 (0)3708 506 506;Guildbourne House;Worthing;BN11 1LD;United Kingdom;enquiries@environment-agency.gov.uk;https://www.gov.uk/government/organisations/environment-agency;web site;Scottish Environment Protection Agency, Angus Smith Building;+44 (0)1698 839000;+44 (0)1698 738155;Angus Smith Building;Holytown;ML1 4WQ;United Kingdom;inapplicable;http://www.sepa.org.uk/;web site;https://sextant.ifremer.fr/geonetwork/srv/fre//resources.get?uuid=d9310aa6-c6b3-4657-a3c9-b0a4dd0f016c&fname=NORTH_SEA_SDC_V1.png;Oceanographic geographical features;GEMET - INSPIRE themes, version 1.0;2018-07-27;geonetwork.thesaurus.external.theme.httpinspireeceuropaeutheme-theme;Salinity of the water column;Temperature of the water column;Parameter Discovery Vocabulary (P02);2017-11-17;geonetwork.thesaurus.external.parameter.NVS.P02;Water body salinity;ITS-90 water temperature;EMODNET chemistry lot aggregated parameter names;2016-09-20;geonetwork.thesaurus.external.parameter.NVS.P35;North Sea;SeaVoX salt and fresh water body gazetteer;2016-09-20;geonetwork.thesaurus.external.reference-geographical-area.NVS.C19;Th\u00e8mes Sextant;2018-05-24;geonetwork.thesaurus.local.theme.sextant-theme;SeaDataNet licence;SeaDataNet Usage Agreement: If you use SeaDataNet data in your publications please include the following in the Acknowledgements: Data were provided through SeaDataNet Pan-European infrastructure for ocean and marine data management (https://www.seadatanet.org);No limitations on public access.  For data access please register at http://www.marine-id.org.;oceans;bounding box;-4.25;9.96;48.6;62;1893-01-01;2017-12-31;-1575.0;0.0;ODV binary collection;5;http://dx.doi.org/10.12770/d9310aa6-c6b3-4657-a3c9-b0a4dd0f016c;WWW:LINK-1.0-http--metadata-URL;DOI of the product;ftp://vftp2.ifremer.fr/public/seadatanet-north_sea-temperaturesalinity_aggregated/SDC_NS_DATA_V1/;WWW:DOWNLOAD-1.0-link--download;full collection dataset;2 datasets : discretes and trajectories;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;See the referenced specification;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "d3c6327d-c751-5725-81ad-1129aef86f69",
-    "notes": [
-        "The data collection of the North Sea is divided in two datasets : the discrete collection and the trajectories collection.\n\nThe Discrete SeaDataCloud Temperature and Salinity Historical Data Collection for the North Sea includes open access in situ data on temperature and salinity measured with \u201cdiscrete\u201d instruments (CTD, XBT, discrete water samplers\u2026). The data span between 4\u00b0W and 10\u00b0E in longitude, and from 49\u00b0N to 62\u00b0N in latitude. It covers the time period 1893 \u2013 2017. The data were retrieved from the SeaDataNet infrastructure in November 2017. \nThe \u201cTrajectories\u201d SeaDataCloud Temperature and Salinity Historical Data Collection for the North Sea includes open access in situ data on temperature and salinity measured by continuously recording sensors (e.g. Ferryboxes). The data span between 4\u00b0W and 10\u00b0E in longitude, and from 49\u00b0N to 62\u00b0N in latitude. It covers the time period 1989 \u2013 2017. \n\nThe data were retrieved from the SeaDataNet infrastructure in November 2017. The quality control of the data has been performed with the help of ODV software. Data Quality Flags have been revised following common recommended procedures defined under SeaDataNet 2 project in conjunction with visual expert check. \n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/.\n\nFor data access please register at http://www.marine-id.org/."
-    ],
-    "oai_identifier": [
-        "d3c6327d-c751-5725-81ad-1129aef86f69"
-    ],
-    "oai_set": "cams1_ps",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-4.25,48.6],[-4.25,62],[9.96,62],[9.96,48.6],[-4.25,48.6]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "North Sea"
-        }
-    ],
-    "title": [
-        "North Sea - Temperature and salinity Historical Data Collection SeaDataCloud V1"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/e389bf78-f0ef-50e7-bf24-1c9b212fce9f.json b/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/e389bf78-f0ef-50e7-bf24-1c9b212fce9f.json
deleted file mode 100644
index 344342c1..00000000
--- a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/e389bf78-f0ef-50e7-bf24-1c9b212fce9f.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "sdn-userdesk@seadatanet.org"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=iso19139&identifier=e389bf78-f0ef-50e7-bf24-1c9b212fce9f",
-    "PublicationTimestamp": "2014-11-12T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "IFREMER",
-        "Marine Institute",
-        "SEADATANET",
-        "GEOMAR Helmholtz Centre for Ocean Research Kiel",
-        "Alfred-Wegener-Institute for Polar- and Marine Research",
-        "IFREMER / IDM/SISMER",
-        "NIOZ Royal Netherlands Institute for Sea Research",
-        "University of East Anglia, School of Environmental Sciences",
-        "Proudman Oceanographic Laboratory",
-        "Odessa Branch of SOI (State Oceanographic Institute)",
-        "Scott Polar Research Institute",
-        "Institute for Marine Science",
-        "Swedish Meteorological and Hydrological Institute",
-        "Laboratory of Oceanography and Climate  : Experiments and numerical Approaches - UMR 7159",
-        "National Oceanography Centre, Liverpool",
-        "Institute of Marine Research",
-        "Marine Research Institute",
-        "Baltic Sea Research Institute Warnemuende (IOW)",
-        "Institute of Oceanographic Sciences Wormley Laboratory",
-        "Fisheries Research Services, Aberdeen Marine Laboratory",
-        "Shom"
-    ],
-    "ResourceType": "dataset",
-    "Rights": [
-        "No limitations on public access.  For data access please register at http://www.marine-id.org"
-    ],
-    "SpatialCoverage": "(65N-82N,40W-65E)",
-    "TempCoverageBegin": 59926651199,
-    "TempCoverageEnd": 63524087999,
-    "TemporalCoverage": " period : ( 1900-01-01T11:59:59Z - 2013-12-31T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1900-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2013-12-31T11:59:59Z",
-    "fulltext": "0d819acd-846c-4e2c-bef1-451762b70578;SEADATANET;sdn-userdesk@seadatanet.org;http://www.seadatanet.org/;2018-07-24T09:47:22;ISO 19115:2003/19139 - EMODNET - SDN;0.1;4;28;1;false;WGS 84 (EPSG 4326);EPSG;Arctic Ocean - Temperature and salinity observation collection V1.1;seadatanet-arctic_sea-temperature_salinity_aggregated_public-v1_1;2014-11-12;1.1;2012-08-28;0d819acd-846c-4e2c-bef1-451762b70578;SeaDataNet Temperature and Salinity historical data collection for the North Arctic Ocean, including revised quality flags after quality control with ODV.\n\nFor data access please register at http://www.marine-id.org\n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/;SeaDataNet;Institute for Marine Science;Seestrasse 15, Warnemuende;Rostock;18119;Germany;nmd@imr.no;web site;IFREMER / IDM/SISMER;+33 (0)2 98.22.49.16;+33 (0)2 98.22.46.44;Centre IFREMER de BrestBP 70;PLOUZANE;29280;France;sismer@ifremer.fr;http://www.ifremer.fr/sismer/;web site;Institute of Marine Research;+47 55 23 85 00;+47 55 23 85 31;Nordnesgaten 50Postboks 1870 Nordnes;Bergen;N-5817;Norway;post@imr.no;http://www.imr.no;web site;Baltic Sea Research Institute Warnemuende (IOW);+49 381 5197-0;+49 381 5197 440;Seestrasse 15;Warnemuende;18119;Germany;iowinfo@io-warnemuende.de;http://www.io-warnemuende.de/;web site;IFREMER;+33(0)1 46.48.21.00;+33(0)1 46.48.22.24;Technopolis 40,155 rue J.J. Rousseau;ISSY-LES-MOULINEAUX;92138;France;communication@ifremer.fr;http://wwz.ifremer.fr;web site;Institute of Marine Research;+47 55 23 85 00;+47 55 23 85 31;Nordnesgaten 50\nPostboks 1870 Nordnes;Bergen;N-5817;Norway;post@imr.no;http://www.imr.no;web site;Alfred-Wegener-Institute for Polar- and Marine Research;None;None;Am Handelshafen 12;Bremerhaven;D-27570;Germany;folke.mehrtens@awi.de;http://www.awi.de;web site;Scott Polar Research Institute;None;None;University of Cambridge\nLensfield Road;Cambridge;CB2 1ER;United Kingdom;None;http://www.spri.cam.ac.uk/;web site;Institute of Oceanographic Sciences Wormley Laboratory;None;None;Brook Road\nWormley;Godalming;GU8 5UB;United Kingdom;inapplicable;None;web site;Proudman Oceanographic Laboratory;+44 (0)151 653 8633;+44 (0)151 653 6269;Bidston Observatory\nBidston Hill;Prenton;CH43 7RA;United Kingdom;inapplicable;http://www.pol.ac.uk;web site;National Oceanography Centre, Liverpool;+44 (0)151 795 4800;+44 (0)151 795 4801;Joseph Proudman Building, 6 Brownlow Street;Liverpool;L3 5DA;United Kingdom;enquiries@noc.ac.uk;http://noc.ac.uk;web site;GEOMAR Helmholtz Centre for Ocean Research Kiel;+49 431 600-0;+49 431 600-2805;D\u00fcsternbrooker Weg 20;Kiel;24105;Germany;info@geomar.de;http://www.geomar.de/en/;web site;Fisheries Research Services, Aberdeen Marine Laboratory;+44 (0)1224 876544;+44 (0)1224 295511;PO Box 101\nVictoria Road;Aberdeen;AB11 9DB;United Kingdom;inapplicable;http://www.marlab.ac.uk;web site;Marine Institute;+353-91-387200;+353-91-387201;Rinville;Oranmore;H91 R673;Ireland;datarequests@marine.ie;http://www.marine.ie;web site;Laboratory of Oceanography and Climate  : Experiments and numerical Approaches - UMR 7159;+33 (1) 44 27 32 48;+33(0)1 44 27 38 05;UMR 7159 CNRS / IRD / Universit\u00e9 Pierre et Marie Curie/MNHN\nInstitut Pierre Simon Laplace - Bo\u00eete 100\n4 Place Jussieu;Paris;75252;France;nelly.lecquyer@locean-ipsl.upmc.fr;http://www.locean-ipsl.upmc.fr/;web site;Shom;+33 (0)2 56.31.23.12;+33 (0)2 56.31.25.80;13, rue du Chatellier\nCS92803;BREST CEDEX 2;29228;France;seadatanet-admin@shom.fr;http://www.shom.fr/;web site;Swedish Meteorological and Hydrological Institute;+46-(0)11-495 80 00;+46-(0)11-495 80 01;Folkborgsvagen 1;Norrkoping;SE-601 76;Sweden;shark@smhi.se;http://www.smhi.se;web site;Marine Research Institute;+354 575 2000;+354 575 2001;Skulagata 4\nP.O.Box 1390;Reykjavik;IS-121;Iceland;hafro@hafro.is;http://www.hafro.is/index_eng.php;web site;University of East Anglia, School of Environmental Sciences;None;None;University Plain;Norwich;NR4 7TJ;United Kingdom;env.enquiries@uea.ac.uk;http://www.uea.ac.uk/env/;web site;NIOZ Royal Netherlands Institute for Sea Research;+31 222 369300;+31 222 319674;Landsdiep 4\nP.O. Box 59;Den Burg/Texel;1790 AB;Netherlands;dmg@nioz.nl;https://www.nioz.nl;web site;Odessa Branch of SOI (State Oceanographic Institute);None;None;None;Odessa;None;Ukraine;None;None;web site;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=0d819acd-846c-4e2c-bef1-451762b70578&fname=ArcticOceanTransp.png;Oceanographic geographical features;GEMET - INSPIRE themes, version 1.0;2009-09-22T07:57:15;Temperature of the water column;Salinity of the water column;Parameter Discovery Vocabulary (P02);2014-12-11;geonetwork.thesaurus.external.parameter.NVS.P02;ITS-90 water temperature;Water body salinity;EMODNET chemistry lot aggregated parameter names;2014-12-11;geonetwork.thesaurus.external.parameter.NVS.P35;Arctic Ocean;SeaVoX salt and fresh water body gazetteer;2014-12-11;geonetwork.thesaurus.external.reference-geographical-area.NVS.C19;Th\u00e8mes Sextant;2017-01-23;geonetwork.thesaurus.local.theme.sextant-theme;SeaDataNet licence;SeaDataNet Usage Agreement: If you use SeaDataNet data in your publications please include the following in the Acknowledgements: Data were provided through SeaDataNet Pan-European infrastructure for ocean and marine data management (https://www.seadatanet.org);No limitations on public access.  For data access please register at http://www.marine-id.org;1;oceans;bounding box;-40;65;65;82;1900-01-01;2013-12-31;-3000.0;0.0;http://dx.doi.org/10.12770/0d819acd-846c-4e2c-bef1-451762b70578;WWW:LINK-1.0-http--metadata-URL;DOI of the product;ftp://vftp2.ifremer.fr/public/seadatanet-arctic_ocean-temperaturesalinity_aggregated/SDN_2014-03_TS_Arctic_QC_done_v1.1.zip;WWW:DOWNLOAD-1.0-link--download;full collection dataset;zipped ODV binary collection;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_Arctic_QC_done_v1.1;OGC:WMS:getCapabilities;full collection dataset;full collection dataset;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_Arctic_QC_done_v1.1;OGC:WMS;SDN_2014-03_TS_Arctic_QC_done_v1.1/Salinity;Salinity;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_Arctic_QC_done_v1.1;OGC:WMS;SDN_2014-03_TS_Arctic_QC_done_v1.1/Temperature;Temperature;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_Arctic_QC_done_v1.1;OGC:WMS;SDN_2014-03_TS_Arctic_QC_done_v1.1/*;Observation locations;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;See the referenced specification;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "e389bf78-f0ef-50e7-bf24-1c9b212fce9f",
-    "notes": [
-        "SeaDataNet Temperature and Salinity historical data collection for the North Arctic Ocean, including revised quality flags after quality control with ODV.\n\nFor data access please register at http://www.marine-id.org\n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/"
-    ],
-    "oai_identifier": [
-        "e389bf78-f0ef-50e7-bf24-1c9b212fce9f"
-    ],
-    "oai_set": "cams1_ps",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-40,65],[-40,82],[65,82],[65,65],[-40,65]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "Arctic Ocean"
-        }
-    ],
-    "title": [
-        "Arctic Ocean - Temperature and salinity observation collection V1.1"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/e895449e-017f-5b4f-a45d-7e2a57f0e337.json b/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/e895449e-017f-5b4f-a45d-7e2a57f0e337.json
deleted file mode 100644
index debe9db7..00000000
--- a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/e895449e-017f-5b4f-a45d-7e2a57f0e337.json
+++ /dev/null
@@ -1,191 +0,0 @@
-{
-    "Contact": [
-        "sdn-userdesk@seadatanet.org"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=iso19139&identifier=e895449e-017f-5b4f-a45d-7e2a57f0e337",
-    "PublicationTimestamp": "2018-05-31T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "SEADATANET",
-        "IFREMER / IDM / SISMER - Scientific Information Systems for the SEA",
-        "Universite de Toulon / Lab. De Sondages Electromagnetiques (Lseet)",
-        "IEO/ Malaga Oceanographic Centre",
-        "IFREMER / GENAVIR BREST",
-        "IEO/ La Coruna Oceanographic Centre",
-        "Atlantic Scientific Research Institute for Marine Fishery and Oceanography",
-        "IFREMER / IDM/SISMER",
-        "Institute of Biology of the Southern Seas, NAS of Ukraine",
-        "Institute of Marine Science S.S. of Lerici (SP)",
-        "ENEA Centro Ricerche Ambiente Marino - La Spezia",
-        "British Oceanographic Data Centre",
-        "COM - Physical and Biogeochemical Oceanography Laboratory (Endoume)",
-        "IFREMER / RBE Department / Biogeochimical end Ecotoxicological Resarch Unit (Nantes)",
-        "CEREGE",
-        "P.P.Shirshov Institute of Oceanology, RAS",
-        "IFREMER / GM-MARINE GEOSCIENCES",
-        "Societe ACRI S.A.",
-        "CNRS / Laboratory of of studies on Spatial Geophysics and Oceanography (LEGOS)",
-        "Cyprus Oceanography Center",
-        "Shom",
-        "UTM-CSIC/Marine Technology Unit",
-        "CNR, Institute of Atmospheric Sciences and Climate (ISAC) (Rome)",
-        "Center for marine research - Rudjer Boskovic Institute",
-        "IRD / CENTRE OF ABIDJAN",
-        "EPOC - Geology and Oceanography Department",
-        "Southampton Oceanography Centre",
-        "LABORATORY OF OCEANOGRAPHY of VILLEFRANCHE (LOV) / OOV",
-        "Moscow State University, Geography Department",
-        "Institute Mediterranean Of Advanced Studies (IMEDEA)",
-        "IFREMER",
-        "Marine Biology Laboratory of Trieste",
-        "Baleares Islands University. Environmental Biology Department. UIB",
-        "Proudman Oceanographic Laboratory",
-        "CNRS / Center of Oceanology of Marseille (COM) La-Seyne-Sur-Mer",
-        "IHPT, Hydrographic Institute",
-        "Istituto Nazionale di Geofisica e Vulcanologia \u2013 INGV, Sede di Bologna",
-        "Universite D'Angers / Laboratoire Des Bio-Indicateurs Actuels Et Fossiles (Biaf)",
-        "University of Rostock, Institute of Biosciences",
-        "NIOZ Royal Netherlands Institute for Sea Research",
-        "IFREMER / LERPAC - Toulon",
-        "Murmansk Hydrometeorological Administration of Roshydromet",
-        "Universit\u00e0 degli Studi di Napoli 'Parthenope' - Istituto di Meteorologia e Oceanografia",
-        "Hellenic Centre for Marine Research, Institute of Oceanography (HCMR/IO)",
-        "Commissione Permanente per lo Studio dell'Adriatico, Venezia",
-        "Institute of Oceanography and Fisheries",
-        "Italian Navy Hydrographic Office",
-        "ICM-CSIC/ Institute of Marine Sciences (ICM-CSIC)",
-        "IFREMER / DYNECO- Coastal Environment Dynamics department",
-        "Far Eastern Regional Hydrometeorological Research Institute",
-        "IFREMER / CENTRE DE BRETAGNE",
-        "UNKNOWN",
-        "Ukrainian scientific center of Ecology of Sea (UkrSCES)",
-        "ARPA Emilia-Romagna - Struttura Oceanografica Daphne",
-        "International Ocean Institute - Malta Operational Centre (University Of Malta) / Physical Oceanography Unit",
-        "Stazione Zoologica Anton Dohrn of Naples",
-        "DTU Aqua \u2013 National Institute of Aquatic Resources, Technical University of Denmark",
-        "Hellenic Centre for Marine Research (HCMR)",
-        "IFREMER / CENTRE DE TOULON",
-        "Odessa Branch of SOI (State Oceanographic Institute)",
-        "National Institute of Fisheries Research (INRH)",
-        "Marine Hydrophysical Institute",
-        "IEO/ Santander Oceanographic Centre",
-        "Institute of Marine Biology (IMBK)",
-        "CNR, Institute of Marine Science (ISMAR) - Bologna",
-        "CNR, Istituto per lo Studio della Dinamica delle Grandi Masse",
-        "Israel Oceanographic and Limnological Research (IOLR)",
-        "CNR, Institute of Marine Science (ISMAR) - Ancona",
-        "SACLANT Undersea Research Centre (SACLANTCEN)",
-        "Oceanologic Observatory of Banyuls (University of Paris VI) / OSU",
-        "Oceanological Observatory of Villefranche sur Mer",
-        "CNRS / COM - Physical and Biogeochemical Oceanography Laboratory (Toulon)",
-        "MUSEUM NATIONAL D'HISTOIRE NATURELLE / LABORATOIRE D'OCEANOGRAPHIE PHYSIQUE",
-        "Centre for Advanced Studies of Blanes (CEAB-CSIC)",
-        "COM - Physical and Biogeochemical Oceanography Laboratory (LUMINY)",
-        "V.I. Il'ichevs Pacific Oceanological Institute, Far Eastern Branch, Russian Academy of Sciences",
-        "Primorsky Territorial Office on Hydrometeorology and Environmental Monitoring of Roshydromet",
-        "CEA / Laboratory of climatolocical and environmental Sciences(LSCE)",
-        "CNRS / Microbiology, Geochemistry and Marine Ecology Laboratory",
-        "Department of Navigation and Hydrography and Oceanography, Turkish Navy",
-        "IFREMER / RBE / Biogeochimical end Ecotoxicological Resarch Unit (Brest)",
-        "National Oceanography Centre, Southampton",
-        "OGS (Istituto Nazionale di Oceanografia e di Geofisica Sperimentale), Division of Oceanography",
-        "ISTPM (IFREMER NANTES)",
-        "Institut National des Sciences et Technologies de la Mer \u2013 INSTM",
-        "Administration Of Fish Searching And Research Fleet for the Western Basin",
-        "University of Genova - Laboratory of Marine Geology and Sedimentology, Dpt for the Study of the Territory and Resources",
-        "IFREMER / STATION DE SETE",
-        "GEOMAR Helmholtz Centre for Ocean Research Kiel",
-        "IEO/ Cadiz Oceanographic Centre",
-        "IEO/ Balearic Islands Oceanographic Centre",
-        "Institute of Marine Sciences, Middle East Technical University",
-        "UNIVERSITY OF PERPIGNAN / CEFREM",
-        "Marine Institute",
-        "CNR, Istituto di Scienze Marine (Sezione di Venezia - ex IBM)",
-        "IRD /CENTRE DE BRETAGNE",
-        "IRDN / LERCM - Toulon",
-        "Hellenic Navy Hydrographic Service (HNHS)",
-        "ERIC Euro-Argo",
-        "CNR, Institute of Marine Science (ISMAR) (Trieste)",
-        "Developmental Biology Research Laboratory",
-        "Federal Maritime and Hydrographic Agency",
-        "IEO/ Murcia Oceanographic Centre",
-        "Istanbul University, Institute of Marine Science and Management",
-        "Malta Centre for Fisheries Sciences",
-        "IFREMER / Dpt Technologicals Research and Development",
-        "Plymouth Marine Laboratory",
-        "IEO/Spanish Oceanographic Institute",
-        "IFREMER / EEP / LEP-DEEP ENVIRONMENT LABORATORY"
-    ],
-    "ResourceType": "dataset",
-    "Rights": [
-        "No limitations on public access.  For data access please register at http://www.marine-id.org"
-    ],
-    "SpatialCoverage": "(30N-46N,9 W-37E)",
-    "TempCoverageBegin": 59926651199,
-    "TempCoverageEnd": 63645047999,
-    "TemporalCoverage": " period : ( 1900-01-01T11:59:59Z - 2017-10-31T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1900-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2017-10-31T11:59:59Z",
-    "fulltext": "2698a37e-c78b-4f78-be0b-ec536c4cb4b3;SEADATANET;sdn-userdesk@seadatanet.org;http://www.seadatanet.org/;2018-09-27T08:18:09;ISO 19115:2003/19139 - EMODNET - SDN;0.1;WGS 84 (EPSG 4326);EPSG;Mediterranean Sea - Temperature and salinity Historical Data Collection SeaDataCloud V1;SDC_MED_DATA_TS_V1;2018-05-31;1;2018-05-31;2698a37e-c78b-4f78-be0b-ec536c4cb4b3;SDC_MED_DATA_TS_V1 SeaDataCloud Temperature  and Salinity data collection for the Mediterranean Sea contains all open access temperature  and salinity in situ data retrieved from SeaDataNet infrastructure at the end of October 2017. The data span between -9.25 and 37 degrees of longitude, thus including an Atlantic box and the Marmara Sea. It covers the time period 1900-2017. Data have been quality checked using ODV 5.0 software. Quality Flags of anomalous data have been revised using basic QC procedures. The dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/.\n\nFor data access please register at http://www.marine-id.org/.;SeaDataNet;Istituto Nazionale di Geofisica e Vulcanologia \u2013 INGV, Sede di Bologna;+39 051 4151412;+39 0514151499;Via Donato Creti n\u00b012;Bologna;40128;Italy;simona.simoncelli@ingv.it;http://www.ingv.it;web site;IFREMER / IDM/SISMER;+33 (0)2 98.22.49.16;+33 (0)2 98.22.46.44;Centre IFREMER de Brest BP 70;PLOUZANE;29280;France;sismer@ifremer.fr;http://www.ifremer.fr/sismer/;web site;National Oceanography Centre, Southampton;University of Southampton Waterfront Campus European Way;Southampton;SO14 3ZH;United Kingdom;enquiries@noc.ac.uk;http://noc.ac.uk;web site;British Oceanographic Data Centre;Joseph Proudman Building 6 Brownlow Street;Liverpool;L3 5DA;United Kingdom;enquiries@bodc.ac.uk;http://www.bodc.ac.uk/;web site;Plymouth Marine Laboratory;+44 (0)1752 633 100;+44 (0)1752 633101;Prospect Place The Hoe;Plymouth;PL1 3DH;United Kingdom;forinfo@pml.ac.uk;http://www.pml.ac.uk;web site;Proudman Oceanographic Laboratory;Joseph Proudman Building 6 Brownlow Street;Liverpool;L3 5DA;United Kingdom;inapplicable;http://www.pol.ac.uk;web site;CNR, Istituto di Scienze Marine (Sezione di Venezia - ex IBM);Riva Sette Martiri 1364/A;Venice;30122;Italy;direttore@ismar.cnr.it;http://www.ismar.cnr.it;web site;OGS (Istituto Nazionale di Oceanografia e di Geofisica Sperimentale), Division of Oceanography;Borgo Grotta Gigante 42/c;Sgonico (Trieste);34010;Italy;nodc@ogs.trieste.it;http://www.ogs.trieste.it/;web site;SACLANT Undersea Research Centre (SACLANTCEN);SACLANTCEN - The Library Viale San Bartolomeo 400;La Spezia;19138;Italy;inapplicable;http://www.saclantc.nato.int/;web site;CNR, Institute of Marine Science (ISMAR) (Trieste);Viale Romolo Gessi, 2;Trieste;34123;Italy;inapplicable;http://www.itt.ts.cnr.it;web site;CNR, Istituto per lo Studio della Dinamica delle Grandi Masse;Palazzo Papadopoli S. Polo 1364;Venezia;30125;Italy;inapplicable;http://www.isdgm.ve.cnr.it;web site;Institute of Marine Science S.S. of Lerici (SP);+39 0187 1788900;+39 0187 970585;Forte Santa Teresa Pozzuolo di Lerici;Lerici (SP);19032;Italy;sdc@sp.ismar.cnr.it;http://www.ismar.cnr.it;web site;ENEA Centro Ricerche Ambiente Marino - La Spezia;+39 0187 978258;+39 0187 978213;Forte S. Teresa Via S.Teresa 1;Lerici;19036;Italy;roberta.delfanti@enea.it;http://www.santateresa.enea.it;web site;University of Genova - Laboratory of Marine Geology and Sedimentology, Dpt for the Study of the Territory and Resources;Corso Europa n. 26;Genova;16432;Italy;inapplicable;http://www.dipteris.unige.it;web site;CNR, Institute of Marine Science (ISMAR) - Ancona;+39 071 2078855;+390071 55313;Largo Fiera della Pesca;Ancona;60125;Italy;p.penna@an.ismar.cnr.it;http://www.ismar.cnr.it/organizzazione/sedi-secondarie/ancona;web site;CNR, Institute of Marine Science (ISMAR) - Bologna;(+39) 051 639 8891;(+39) 051 639 8939;Via Gobetti, 101;Bologna;40129;Italy;responsabile@bo.ismar.cnr.it;http://www.bo.ismar.cnr.it/;web site;CNR, Institute of Atmospheric Sciences and Climate (ISAC) (Rome);+39-06-49934554;+39-06-20660291;Via Fosso del Cavaliere, 100;Rome;00133;Italy;f.bignami@isac.cnr.it;http://www.isac.cnr.it;web site;Hellenic Centre for Marine Research, Institute of Oceanography (HCMR/IO);+30-22910-76452. -76460;+30-22910-76347;46.7 km Athinon-Souniou Av. P.O.Box 712;Anavyssos;19013;Greece;iosecretariat@hcmr.gr;http://www.hcmr.gr;web site;Universit\u00e0 degli Studi di Napoli 'Parthenope' - Istituto di Meteorologia e Oceanografia;Via Ammiraglio Acton 38;Napoli;80133;Italy;inapplicable;http://www.uninav.it;web site;Stazione Zoologica Anton Dohrn of Naples;Villa Comunale;Napoli;80121;Italy;inapplicable;http://www.szn.it;web site;Marine Biology Laboratory of Trieste;Via Auguste Piccard 54 Santa Croce;Trieste;34010;Italy;inapplicable;http://www.univ.trieste.it/~mabiolab;web site;ICM-CSIC/ Institute of Marine Sciences (ICM-CSIC);+34 932 309500;+34 932 309555;Paseo Mar\u00edtimo de la Barceloneta, 37-49;Barcelona;08003;Spain;secredir@icm.csic.es;http://www.icm.csic.es;web site;Baleares Islands University. Environmental Biology Department. UIB;+34 971173000;+34 971173184;Fac. de Ciencias. U. de Baleares Edificio Guillem Colom Carretera de Valldemossa Km 7.5;Palma de Mallorca;07122;Spain;inapplicable;http://www.uib.es/depart/dba/;web site;IEO/Spanish Oceanographic Institute;+34 915 107513;+34 914 135597;Corazon de Maria, 8;MADRID;28002;Spain;cedo@ieo.es;http://www.ieo.es;web site;Marine Institute;Ireland;datarequests@marine.ie;IRD /CENTRE DE BRETAGNE;+33 (0)2 98.22.40.40;+33 (0)2 98.22.45.45;ZI Pointe du diable CS 10070;PLOUZANE;29280;France;inapplicable;http://www.ifremer.fr/brest/;web site;IFREMER / EEP / LEP-DEEP ENVIRONMENT LABORATORY;+33 (0)2 98.22.43.04;+33 (0)2 98.22.47.57;IFREMER Centre de Bretagne ZI Pointe du diable CS 10070;PLOUZANE;29280;France;inapplicable;http://www.ifremer.fr/droep/index.html;web site;IFREMER / GM-MARINE GEOSCIENCES;+33(0)2 98.22.42.70;+33(0)2 98.22.45.70;IFREMER Centre de Bretagne ZI Pointe du diable CS 10070;PLOUZANE;29280;France;geosciences.marines@ifremer.fr;http://www.ifremer.fr/drogm/;web site;IFREMER / IDM / SISMER - Scientific Information Systems for the SEA;+33 (0)2 98.22.49.16;+33 (0)2 98.22.46.44;IFREMER Centre de Bretagne ZI Pointe du diable CS 10070;PLOUZANE;29280;France;sismer@ifremer.fr;http://www.ifremer.fr/sismer/;web site;LABORATORY OF OCEANOGRAPHY of VILLEFRANCHE (LOV) / OOV;+33 (0)4 93 76 38 13;+33 (0)4.93.76.38.34;UPMC/UMR 7093 181, chemin du Lazaret;Villefranche-sur-Mer;06230;France;lov@obs-vlfr.fr;http://www.obs-vlfr.fr;web site;MUSEUM NATIONAL D'HISTOIRE NATURELLE / LABORATOIRE D'OCEANOGRAPHIE PHYSIQUE;+33 (0)1 40.79.31 58;+33 (0)1 40 79 31 63;43-45 rue Cuvier;PARIS CEDEX 05;75231;France;inapplicable;http://www.mnhn.fr;web site;COM - Physical and Biogeochemical Oceanography Laboratory (LUMINY);+33(0)4 91 82 91 15;+33(0)4 91.82.65.48;UFR Centre Oceanologique de Marseille UMR 6535 Campus de Luminy Case 901;Marseille cedex 9;13288;France;queguiner@com.univ-mrs.fr;http://www.com.univ-mrs.fr/LOB/;web site;UNIVERSITY OF PERPIGNAN / CEFREM;+33 (0)4 68.66.20.90;+33 (0)4 68.66.20.96;CNRS - UMR 5110 - Universite de Perpignan 52 avenue Paul Alduy;Perpignan Cedex;66860;France;cefrem@univ-perp.fr;http://cefrem.univ-perp.fr/;web site;IFREMER / RBE Department / Biogeochimical end Ecotoxicological Resarch Unit (Nantes);+33 (0)2 40 37 41 93;33(0)2 40.37.40.75;IFREMER Centre de Nantes Rue de l'Ile d'Yeu BP 1105;NANTES CEDEX 03;44311;France;inapplicable;http://www.ifremer.fr/delpc/;web site;Developmental Biology Research Laboratory;+33 (0)4 93.76.37.70;+33(0)4 93.76.37.92;UMR7009 CNRS/UPMC Observatoire Oc\u00e9anologique Quai de la Darse;Villefranche-sur-Mer Cedex;06234;France;biodev@obs-vlfr.fr;http://biodev.obs-vlfr.fr/;web site;CNRS / Microbiology, Geochemistry and Marine Ecology Laboratory;+33 (0)4 91 82 92 12;+33 (0)4 91 82 96 41;Centre d'Oc\u00e9anologie de Marseille (COM) UMR 6117 Campus de Luminy, Case 901;MARSEILLE CEDEX 9;13288;France;micromar@com.univ-mrs.fr;http://www.com.univ-mrs.fr/LMGEM/spip.php?rubrique1;web site;Shom;+33 (0)2 56.31.23.12;+33 (0)2 56.31.25.80;13, rue du Chatellier CS92803;BREST CEDEX 2;29228;France;seadatanet-admin@shom.fr;http://www.shom.fr/;web site;CEA / Laboratory of climatolocical and environmental Sciences(LSCE);+33(0)1 69.82 35 23;+33(0)1 69.82.35.68;CNRS LSCE-Vallee, Bat.12, Avenue de la Terrasse;GIF-SUR-YVETTE CEDEX;91198;France;inapplicable;http://www.lsce.cnrs-gif.fr/;web site;CNRS / Laboratory of of studies on Spatial Geophysics and Oceanography (LEGOS);+33 (0)5 61 33 29 28;+33 (0)5 61 25 32 05;Observatoire Midi-Pyrenees 14, Avenue Edouard Belin;TOULOUSE CEDEX 4;31401;France;inapplicable;http://www.legos.obs-mip.fr/Presentation-generale?set_language=en&cl=en;web site;CEREGE;+33(0)4 42 97 15 00;+33 (0)4 42 97 15 05;Europole Mediterraneen de l'Arbois BP 80;Aix en Provence;13545;France;inapplicable;http://www.cerege.fr/;web site;IHPT, Hydrographic Institute;+351 210943000;+351 210943299;Rua das Trinas, 49;Lisboa;1249-093;Portugal;mail@hidrografico.pt;http://www.hidrografico.pt;web site;NIOZ Royal Netherlands Institute for Sea Research;+31 222 369300;+31 222 319674;Landsdiep 4 P.O. Box 59;Den Burg/Texel;1790 AB;Netherlands;dmg@nioz.nl;https://www.nioz.nl;web site;Atlantic Scientific Research Institute for Marine Fishery and Oceanography;8 (0112) 21-56-45;8 (0112) 21-99-97;5, Dm. Donskoi St.;Kaliningrad reg;236000;Russian Federation;atlant@baltnet.ru;http://www.atlantniro.ru/;web site;P.P.Shirshov Institute of Oceanology, RAS;+7(499)124-59-96;+7(499)124-59-83;36 Nakhimovsky prospect;Moscow;117997;Russian Federation;office@ocean.ru;http://www.ocean.ru;web site;National Institute of Fisheries Research (INRH);212 22 29 85 34;212 22 26 69 67;2, RUE TIZNIT;CASABLANCA;20000;Morocco;orbi@inrh.org.ma;web site;Institute of Marine Sciences, Middle East Technical University;+90 (324) 5212406;+90 (324) 5212327;P.O.Box 28;Erdemli;33731;Turkey;devrim@ims.metu.edu.tr;http://www.ims.metu.edu.tr;web site;Institute of Oceanography and Fisheries;+385 21 408000/8011;+385 21 358650;Setaliste Ivana Mestrovica 63 P.O.BOX 500;SPLIT;21000;Croatia;office@izor.hr;http://www.izor.hr;web site;Center for marine research - Rudjer Boskovic Institute;+385 52 804 700;+385 52 804 780;G. Paliaga 5;Rovinj;52210;Croatia;predstojnik.cim@irb.hr;http://www.irb.hr/Istrazivanja/Zavodi/Centar-za-istrazivanje-mora;web site;International Ocean Institute - Malta Operational Centre (University Of Malta) / Physical Oceanography Unit;+356 - 2144 0972;+356 - 2144 0972;IOI-MOC, Rooms 314/5/6, Chemistry Building, University of Malta;Msida;MSD 2080;Malta;ioi-moc@um.edu.mt;http://www.capemalta.net;web site;Malta Centre for Fisheries Sciences;(+356) 21655525;(+356) 21659380;Fort San Lucjan;Marsaxlokk;BBG 06;Malta;malta.fisheries@gov.mt;http://maltafisheries.gov.mt;web site;Cyprus Oceanography Center;+357-22893988-82-83;+357-22895051;University of Cyprus P.O. BOX 20537;Nicosia;1678;Cyprus;gzodiac@ucy.ac.cy;http://www.oceanography.ucy.ac.cy;web site;IFREMER / STATION DE SETE;+33(0)4 99 57 32 00;+33 (0)4 99 57 32 94;Bd Jean Monnet BP 171;SETE CEDEX;34203;France;inapplicable;http://wwz.ifremer.fr/mediterranee/implantations/Sete;web site;Marine Hydrophysical Institute;+380 692 54 02 52;+380 692 55 42 53;2, Kapitanskaya str.;Sevastopol;99011;Ukraine;khaliulin.alexey@nodc.org.ua;http://WWW.MHI.IUF.NET;web site;Department of Navigation and Hydrography and Oceanography, Turkish Navy;\u00c7ubuklu;Istanbul;81647;Turkey;inapplicable;web site;Far Eastern Regional Hydrometeorological Research Institute;+7 (4232) 26-97-88;+7 (4232) 22-77-54;Fontannaya St., 24;Vladivostok;690600;Russian Federation;hydromet@online.ru;http://www.hydromet.com;web site;IFREMER / Dpt Technologicals Research and Development;+33(0) 2 98 22 41 41;+33(0) 2 98 22 45 35;IFREMER Centre de Bretagne ZI Pointe du diable CS 10070;PLOUZANE;29280;France;Pierre.Chauchot@ifremer.fr;http://wwz.ifremer.fr/rd_technologiques;web site;Istanbul University, Institute of Marine Science and Management;M\u00fcsk\u00fcle Sok. No. 1 Vefa;Istanbul;34470;Turkey;inapplicable;http://www.istanbul.edu.tr/enstituler/denizbilimleri/denizbilimleri.htm;web site;IFREMER / CENTRE DE TOULON;+33 (0)4 94.30.48.00;+33 (0)4 94.30.13.72;Zone portuaire de Bregaillon BP 330;LA SEYNE CEDEX;83507;France;inapplicable;http://www.ifremer.fr/francais/implant/toulon.htm;web site;EPOC - Geology and Oceanography Department;+33 (0)5 40.00.88.67;+33 (0)5 56.84.08.48;351, Cours de la Liberation Avenue des Facultes;TALENCE;33405;France;inapplicable;http://www.epoc.u-bordeaux.fr;web site;Institute of Biology of the Southern Seas, NAS of Ukraine;+380 692 544110;+380 692 557813;2, Nakhimov ave.;Sevastopol;99011;Ukraine;director@ibss.iuf.net;http://ibss.nas.gov.ua;web site;IFREMER / CENTRE DE BRETAGNE;+33 (0)2 98.22.40.40;+33 (0)2 98.22.45.45;ZI Pointe du diable CS 10070;PLOUZANE;29280;France;inapplicable;http://www.ifremer.fr/brest/;web site;Administration Of Fish Searching And Research Fleet for the Western Basin;5a, Dm.Donskoy St.;Kaliningrad;236000;Russian Federation;inapplicable;web site;Moscow State University, Geography Department;+7 95 9391000;Leninsky Gory;Moscow;119992;Russian Federation;info@geogr.msu.ru;http://www.geogr.msu.ru/GeoSite/depts_ocean.html;web site;Murmansk Hydrometeorological Administration of Roshydromet;23, Shmidt St.;Murmansk;183789;Russian Federation;leader@kolgimet.murman.ru;http://www.kolgimet.ru/;web site;Primorsky Territorial Office on Hydrometeorology and Environmental Monitoring of Roshydromet;3, Mordovtsev St.;Vladivostok;690990;Russian Federation;ps@primpogoda.ru;http://www.primpogoda.ru/;web site;Odessa Branch of SOI (State Oceanographic Institute);Odessa;Ukraine;inapplicable;web site;V.I. Il'ichevs Pacific Oceanological Institute, Far Eastern Branch, Russian Academy of Sciences;43, Baltiyskaya St.;Vladivostok;690041;Russian Federation;rostov@poi.dvo.ru;http://www.poi.dvo.ru;web site;Institute Mediterranean Of Advanced Studies (IMEDEA);+34 971 61 17 14;+34 971 61 17 61;C/ Miquel Marqu\u00e8s, 21;Esporles (Mallorca);07190;Spain;inapplicable;http://www.imedea.uib.es;web site;Israel Oceanographic and Limnological Research (IOLR);972-4-8565256;972-4-8511911;Tel-Shikmona P.O.B. 8030;Haifa;31080;Israel;nurit@ocean.org.il;http://www.ocean.org.il;web site;Hellenic Navy Hydrographic Service (HNHS);+30-210-6442966, ...71;+30-210- 6517811;Department of Oceanography Stratopedo Papagou;Athens;T.G.N 1040;Greece;info@hnhs.gr;http://www.hnhs.gr;web site;Oceanologic Observatory of Banyuls (University of Paris VI) / OSU;+33 4 68 88 73 15;+33 4 68 88 16 99;Laboratoire Arago BP 44;BANYULS-SUR-MER;66651;France;inapplicable;http://www.obs-banyuls.fr/;web site;IFREMER / DYNECO- Coastal Environment Dynamics department;+33 (0)2 98.22.43.51;+33 (0)2 98 22 45.48;IFREMER Centre de Bretagne ZI Pointe du diable CS 10070;PLOUZANE;29280;France;inapplicable;http://www.ifremer.fr/anglais/org/del.htm;web site;Societe ACRI S.A.;+33(0)493958898;260, route du Pin Montard BP 234;SOPHIA ANTIPOLIS;06904;France;inapplicable;http://www.acri.fr/;web site;CNRS / COM - Physical and Biogeochemical Oceanography Laboratory (Toulon);+33(0)4.94.87.93.47.;CNRS-UNIVERSITE MEDITERRANEE Antenne de Toulon, BP 330;LA SEYNE-SUR-MER;83507;France;inapplicable;http://www.com.univ-mrs.fr/LOB/;web site;COM - Physical and Biogeochemical Oceanography Laboratory (Endoume);+33(0)4 91 04 16 41;+33(0)4 91 04 16 35;UFR Centre Oceanologique de Marseille,Station Marine d'Endoume,Rue de la Batterie des Lions;MARSEILLE Cedex 9;13007;France;coste@com.univ-mrs.fr;http://www.com.univ-mrs.fr/LOB/;web site;IFREMER / GENAVIR BREST;+33(0)2 98.22.44.21;+33(0)2 98.05.06.33;Centre IFREMER de Brest,BP 71;PLOUZANE;29280;France;inapplicable;http://www.ifremer.fr/genavir;web site;IFREMER;+33 (0)4 94.30.48.00;+33 (0)4 94.30.13.72;Zone portuaire de Bregaillon BP 330;LA SEYNE CEDEX;83507;France;communication@ifremer.fr;http://www.ifremer.fr/francais/implant/toulon.htm;web site;ISTPM (IFREMER NANTES);+33(0)2 40.37.40.00;rue de l'Ile d'Yeu,BP 1105;NANTES CEDEX 03;44311;France;inapplicable;web site;ARPA Emilia-Romagna - Struttura Oceanografica Daphne;Centro Ricerche Marine Viale Vespucci 2;Cesenatico;47042;Italy;inapplicable;http://www.arpa.emr.it/Daphne/index.asp;web site;IRD / CENTRE OF ABIDJAN;(225) 24 37 79;(225) 24 65 04;Rue du Chevalier de Clieu15 15 BP 917;Abidjan;15;C\u00f4te d'Ivoire;rep@ird.ci;web site;Ukrainian scientific center of Ecology of Sea (UkrSCES);+38 0482 636622;+380 482 636873;89 Frantsuzsky Blvd.;Odessa;65009;Ukraine;accem@te.net.ua;http://www.sea.gov.ua;web site;Institut National des Sciences et Technologies de la Mer \u2013 INSTM;+2 16 71 73 04 20;+2 16 71 73 26 22;Rue 2 mars 1934, 28;Salammbo;2025;Tunisia;cherif.sammari@instm.rnrt.tn;http://www.instm.rnrt.tn;web site;Italian Navy Hydrographic Office;+39 010 24431;+39 010 261400;Passo Osservatorio, 4;Genova;16134;Italy;iim.sre@marina.difesa.it;http://www.marina.difesa.it;web site;Commissione Permanente per lo Studio dell'Adriatico, Venezia;Venice;Italy;inapplicable;web site;Centre for Advanced Studies of Blanes (CEAB-CSIC);+34 972 336101;+34 972 337806;c/ Acc\u00e9s a la Cala St. Francesc, 14;Blanes (Girona);17300;Spain;inapplicable;http://www.ceab.csic.es/;web site;IEO/ Santander Oceanographic Centre;+34 942 291060;+34 942 275072;Promontorio San Martin, s/n Apdo. 240;Santander;39004;Spain;ieosantander@st.ieo.es;http://www.ieo-santander.net/;web site;IEO/ La Coruna Oceanographic Centre;+34 981 205362;+34 981 229077;Muelle de las Animas, s/n Apdo.130;A Coruna;15001;Spain;ieo.coruna@co.ieo.es;http://www.ieo.es;web site;IEO/ Malaga Oceanographic Centre;+34 952 476 955;+34 952 463 808;Puerto Pesquero, s/n Apdo. 285;Fuengirola (Malaga);29640;Spain;ieomalaga@ma.ieo.es;http://www.ieo.es;web site;IEO/ Cadiz Oceanographic Centre;+34 956 294 189;+34 956 263 556;Muelle de Levante (Puerto Pesquero) Apdo. 2609;Puerto Real (Cadiz);11106;Spain;ignacio.sobrino@cd.ieo.es;http://www.ieo.es;web site;IEO/ Murcia Oceanographic Centre;+34 968 180 500;+34 968 184 441;Magallanes, 2 - Apdo. 22;San Pedro del Pinatar (Murcia);30740;Spain;comurcia@mu.ieo.es;http://www.mu.ieo.es/;web site;IEO/ Balearic Islands Oceanographic Centre;+34 971 401 561;+34 971 404 945;Muelle de Poniente, s/n Apdo. 291;Palma de Mallorca (Baleares);07015;Spain;cobieo@ba.ieo.es;http://www.ba.ieo.es/;web site;University of Rostock, Institute of Biosciences;+49 (0)381 498 6041;+49 (0)381 498 6042;Wismarsche Strasse 8;Rostock;18057;Germany;institut.biowissenschaften@uni-rostock.de;http://www.bio.uni-rostock.de;web site;IRDN / LERCM - Toulon;CENTRE IFREMER BP 330;LA SEYNE SUR MER;83507;France;inapplicable;http://www.irsn.org/opera/;web site;Federal Maritime and Hydrographic Agency;+49 40 3190 3200;+49 40 3190 5000;Bernhard-Nocht-Str. 78;Hamburg;20359;Germany;dod@bsh.de;http://www.bsh.de/;web site;IFREMER / RBE / Biogeochimical end Ecotoxicological Resarch Unit (Brest);+33 (0)2 98 22 44 64;+33 (0)2 98 22 45 48;IFREMER Centre de Bretagne ZI Pointe du diable CS 10070;PLOUZANE;29280;France;inapplicable;http://www.ifremer.fr/delpc/index.htm;web site;Universite D'Angers / Laboratoire Des Bio-Indicateurs Actuels Et Fossiles (Biaf);02.41.73.53.91;02.41.73.53.52;UFR Sciences - UPRES EA 2644 2, Bd Lavoisier;ANGERS cedex 01;49045;France;frans.jorissen@univ-angers.fr;web site;CNRS / Center of Oceanology of Marseille (COM) La-Seyne-Sur-Mer;+33(0)4 94 30 48 00;+33(0)4 94 87 93 47;Antenne COM - CNRS BP 330;LA SEYNE SUR MER CEDEX;83507;France;inapplicable;web site;Universite de Toulon / Lab. De Sondages Electromagnetiques (Lseet);+33(0)4 94 14 24 57;+33(0)4 94 14 24 17;Universit\u00e9 de Toulon et du Var Boulevard Des Amaris, 639 BP20132;LA GARDE;83957;France;Firstname.Name@lseet.univ-tln.fr;http://lseet.univ-tln.fr/L7/squel.php?content=accueil;web site;Southampton Oceanography Centre;University of Southampton Waterfront Campus European Way;Southampton;SO14 3ZH;United Kingdom;inapplicable;web site;DTU Aqua \u2013 National Institute of Aquatic Resources, Technical University of Denmark;+ 45 33 96 33 00;+ 45 33 96 33 33;Kavalerg\u00e5rden 6;Charlottenlund;2920;Denmark;aqua@aqua.dtu.dk;http://www.aqua.dtu.dk/English;web site;Institute of Marine Biology (IMBK);+382 32 33 45 70;+382 32 33 45 70;Dobrota bb, P.O. box 69;Kotor;85330;Montenegro;danijela.j@ac.me;http://www.ibmk.ucg.ac.me;web site;UTM-CSIC/Marine Technology Unit;+34 932 309500;+34 932 309555;Paseo Maritimo de la Barceloneta, 37-49;Barcelona;08003;Spain;info@utm.csic.es;http://www.utm.csic.es/;web site;GEOMAR Helmholtz Centre for Ocean Research Kiel;+49 431 600-0;+49 431 600-2805;D\u00fcsternbrooker Weg 20;Kiel;24105;Germany;info@geomar.de;http://www.geomar.de/en/;web site;Hellenic Centre for Marine Research (HCMR);+302291076462,+302291076466;+302291076323;46,7 km Athens Sounio ave.;Anavyssos Attiki;19013;Greece;president_secretary@hcmr.gr;http://www.hcmr.gr;web site;Oceanological Observatory of Villefranche sur Mer;+33 (0)4 93 76 38 90;BP 28 - BP 127;Villefranche sur Mer;06230;France;inapplicable;http://www.obs-vlfr.fr;web site;IFREMER / LERPAC - Toulon;+33 (0)4 94.30.48.00;Centre Ifremer M\u00e9diterran\u00e9e Zone portuaire de Bregaillon CS20330;LA SEYNE SUR MER CEDEX;83507;France;inapplicable;web site;ERIC Euro-Argo;+33(0)2 98 22 44 83;Z.I. Techonop\u00f4le Brest Iroise 1625 route de Sainte Anne;Plouzane;29280;France;euroargo@ifremer.fr;http://www.euro-argo.eu/;web site;UNKNOWN;UNKNOWN;UNKNOWN;Unknown;inapplicable;web site;https://sextant.ifremer.fr/geonetwork/srv/fre//resources.get?uuid=2698a37e-c78b-4f78-be0b-ec536c4cb4b3&fname=MED_SEA_SDC_V1.png;Oceanographic geographical features;GEMET - INSPIRE themes, version 1.0;2018-07-27;geonetwork.thesaurus.external.theme.httpinspireeceuropaeutheme-theme;Temperature of the water column;Salinity of the water column;Parameter Discovery Vocabulary (P02);2017-11-17;geonetwork.thesaurus.external.parameter.NVS.P02;Water body salinity;ITS-90 water temperature;EMODNET chemistry lot aggregated parameter names;2016-09-20;geonetwork.thesaurus.external.parameter.NVS.P35;Mediterranean Sea, Eastern Basin;Mediterranean Sea;Adriatic Sea;Ionian Sea;Mediterranean Region;Alboran Sea;Ligurian Sea;Strait of Sicily;Sea of Marmara;Tyrrhenian Sea;Aegean Sea;Mediterranean Sea, Western Basin;SeaVoX salt and fresh water body gazetteer;2016-09-20;geonetwork.thesaurus.external.reference-geographical-area.NVS.C19;Th\u00e8mes Sextant;2018-05-24;geonetwork.thesaurus.local.theme.sextant-theme;SeaDataNet licence;SeaDataNet Usage Agreement: If you use SeaDataNet data in your publications please include the following in the Acknowledgements: Data were provided through SeaDataNet Pan-European infrastructure for ocean and marine data management (https://www.seadatanet.org);No limitations on public access.  For data access please register at http://www.marine-id.org;oceans;bounding box;-9.25;36.625;30;46.125;1900-01-01;2017-10-31;-5052.3;0.0;ODV binary collection;5;http://dx.doi.org/10.12770/2698a37e-c78b-4f78-be0b-ec536c4cb4b3;WWW:LINK-1.0-http--metadata-URL;DOI of the product;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;See the referenced specification;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "e895449e-017f-5b4f-a45d-7e2a57f0e337",
-    "notes": [
-        "SDC_MED_DATA_TS_V1 SeaDataCloud Temperature  and Salinity data collection for the Mediterranean Sea contains all open access temperature  and salinity in situ data retrieved from SeaDataNet infrastructure at the end of October 2017. The data span between -9.25 and 37 degrees of longitude, thus including an Atlantic box and the Marmara Sea. It covers the time period 1900-2017. Data have been quality checked using ODV 5.0 software. Quality Flags of anomalous data have been revised using basic QC procedures. The dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/.\n\nFor data access please register at http://www.marine-id.org/."
-    ],
-    "oai_identifier": [
-        "e895449e-017f-5b4f-a45d-7e2a57f0e337"
-    ],
-    "oai_set": "cams1_ps",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-9.25,30],[-9.25,46.125],[36.625,46.125],[36.625,30],[-9.25,30]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Mediterranean Sea"
-        },
-        {
-            "name": "Eastern Basin"
-        },
-        {
-            "name": "Mediterranean Sea"
-        },
-        {
-            "name": "Adriatic Sea"
-        },
-        {
-            "name": "Ionian Sea"
-        },
-        {
-            "name": "Mediterranean Region"
-        },
-        {
-            "name": "Alboran Sea"
-        }
-    ],
-    "title": [
-        "Mediterranean Sea - Temperature and salinity Historical Data Collection SeaDataCloud V1"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/ea37a79b-9ffd-53dd-8d9c-893579fa67b4.json b/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/ea37a79b-9ffd-53dd-8d9c-893579fa67b4.json
deleted file mode 100644
index bf0b41be..00000000
--- a/oaitestdata/seadatanet-iso19139/cams1_ps_1/json/ea37a79b-9ffd-53dd-8d9c-893579fa67b4.json
+++ /dev/null
@@ -1,70 +0,0 @@
-{
-    "Contact": [
-        "sdn-userdesk@seadatanet.org"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=iso19139&identifier=ea37a79b-9ffd-53dd-8d9c-893579fa67b4",
-    "PublicationTimestamp": "2015-11-30T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "IFREMER / IDM/SISMER",
-        "SEADATANET",
-        "Istituto Nazionale di Geofisica e Vulcanologia \u2013 INGV, Sede di Bologna"
-    ],
-    "ResourceType": "dataset",
-    "Rights": [
-        "No limitations on public access.  For data access please register at http://www.marine-id.org"
-    ],
-    "SpatialCoverage": "(30N-46N,9 W-37E)",
-    "TempCoverageBegin": 59926651199,
-    "TempCoverageEnd": 63524087999,
-    "TemporalCoverage": " period : ( 1900-01-01T11:59:59Z - 2013-12-31T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1900-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2013-12-31T11:59:59Z",
-    "fulltext": "90ae7a06-8b08-4afe-83dd-ca92bc99f5c0;SEADATANET;sdn-userdesk@seadatanet.org;http://www.seadatanet.org/;2018-07-24T09:47:39;ISO 19115:2003/19139 - EMODNET - SDN;0.1;4;33;1;false;WGS 84 (EPSG 4326);EPSG;Mediterranean Sea - Temperature and Salinity Climatology V1.1;SEADATANET_MedSea_climatology_V1.1_public;2015-11-30;1.1;2015-11-30;90ae7a06-8b08-4afe-83dd-ca92bc99f5c0;Mediterranean Sea Climatology computed from the SeaDataNet V1.1 aggregated dataset . The version used for the DIVA software is the 4.6.9. The period covers 1900-2013.\n\n For data access please register at http://www.marine-id.org;SeaDataNet;Istituto Nazionale di Geofisica e Vulcanologia \u2013 INGV, Sede di Bologna;+39 051 4151412;+39 0514151499;Via Donato Creti n\u00b012;Bologna;40128;Italy;simona.simoncelli@ingv.it;http://www.ingv.it;web site;IFREMER / IDM/SISMER;+33 (0)2 98.22.49.16;+33 (0)2 98.22.46.44;Centre IFREMER de Brest\nBP 70;PLOUZANE;29280;France;sismer@ifremer.fr;http://www.ifremer.fr/sismer/;web site;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=90ae7a06-8b08-4afe-83dd-ca92bc99f5c0&fname=med_sea.png;Oceanographic geographical features;GEMET - INSPIRE themes, version 1.0;2009-09-22T07:57:15;Temperature of the water column;Salinity of the water column;Parameter Discovery Vocabulary (P02);2014-12-11;geonetwork.thesaurus.external.parameter.NVS.P02;ITS-90 water temperature;Water body salinity;EMODNET chemistry lot aggregated parameter names;2014-12-11;geonetwork.thesaurus.external.parameter.NVS.P35;Mediterranean Region;Mediterranean Sea;SeaVoX salt and fresh water body gazetteer;2014-12-11;geonetwork.thesaurus.external.reference-geographical-area.NVS.C19;Th\u00e8mes Sextant;2017-01-23;geonetwork.thesaurus.local.theme.sextant-theme;SeaDataNet licence;SeaDataNet Usage Agreement: If you use SeaDataNet data in your publications please include the following in the Acknowledgements: Data were provided through SeaDataNet Pan-European infrastructure for ocean and marine data management (https://www.seadatanet.org);No limitations on public access.  For data access please register at http://www.marine-id.org;0.125;oceans;bounding box;-9.250;36.625;30.000;46.125;1900-01-01;2013-12-31;-5500.0;0.0;http://dx.doi.org/10.12770/90ae7a06-8b08-4afe-83dd-ca92bc99f5c0;WWW:LINK-1.0-http--metadata-URL;DOI of the product;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms;OGC:WMS:getCapabilities;full dataset;full dataset;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms;OGC:WMS;Mediterranean Sea/Salinity.19002013.4Danl.nc*Salinity_L1;Salinity masked using relative error threshold 0.3;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms;OGC:WMS;Mediterranean Sea/Salinity.19002013.4Danl.nc*Salinity_L2;Salinity masked using relative error threshold 0.5;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms;OGC:WMS;Mediterranean Sea/Temperature.19002013.4Danl.nc*Temperature_L1;Temperature masked using relative error threshold 0.3;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms;OGC:WMS;Mediterranean Sea/Temperature.19002013.4Danl.nc*Temperature_L2;Temperature masked using relative error threshold 0.5;ftp://ftp2.ifremer.fr/public/seadatanet-med_sea-temperaturesalinity_climatologie/SDN_2015-11_TS_Med_Sea_Climatology_v1.1.zip;WWW:DOWNLOAD-1.0-link--download;full dataset;full dataset;COMMISSION REGULATION (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services;2010-12-08;See the referenced specification;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "ea37a79b-9ffd-53dd-8d9c-893579fa67b4",
-    "notes": [
-        "Mediterranean Sea Climatology computed from the SeaDataNet V1.1 aggregated dataset . The version used for the DIVA software is the 4.6.9. The period covers 1900-2013.\n\n For data access please register at http://www.marine-id.org"
-    ],
-    "oai_identifier": [
-        "ea37a79b-9ffd-53dd-8d9c-893579fa67b4"
-    ],
-    "oai_set": "cams1_ps",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-9.250,30.000],[-9.250,46.125],[36.625,46.125],[36.625,30.000],[-9.250,30.000]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "Mediterranean Region"
-        },
-        {
-            "name": "Mediterranean Sea"
-        }
-    ],
-    "title": [
-        "Mediterranean Sea - Temperature and Salinity Climatology V1.1"
-    ]
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-iso19139/seadatanet_1/json/7fb92b79-940c-5297-877a-c2dbf43f688b.json b/oaitestdata/seadatanet-iso19139/seadatanet_1/json/7fb92b79-940c-5297-877a-c2dbf43f688b.json
deleted file mode 100644
index 00456efb..00000000
--- a/oaitestdata/seadatanet-iso19139/seadatanet_1/json/7fb92b79-940c-5297-877a-c2dbf43f688b.json
+++ /dev/null
@@ -1,93 +0,0 @@
-{
-    "Contact": [
-        "sdn-userdesk@seadatanet.org"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/eng/csw-ATLANTOS?verb=GetRecord&metadataPrefix=iso19139&identifier=7fb92b79-940c-5297-877a-c2dbf43f688b",
-    "OpenAccess": [
-        "No limitations on public access"
-    ],
-    "PublicationTimestamp": "2017-05-23T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "SeaDataNet"
-    ],
-    "ResourceType": "dataset",
-    "Rights": [
-        "SeaDataNet Usage Agreement:\nIf you use SeaDataNet data in your publications please include the following in the Acknowledgements:\nData were provided through SeaDataNet Pan-European infrastructure for ocean and marine data management (https://www.seadatanet.org)"
-    ],
-    "SpatialCoverage": "(90S-90N,180W-180E)",
-    "TempCoverageBegin": 56944382399,
-    "TempCoverageEnd": 56944382399,
-    "TemporalCoverage": " point in time : 1805-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1805-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1805-07-01T11:59:59Z",
-    "fulltext": "ec9eb0a6-d6aa-41ae-b3ca-571c348c9cc6;SeaDataNet;sdn-userdesk@seadatanet.org;2018-01-18T13:07:16;ISO 19115:2003/19139 - SEXTANT;1.0;SeaDataNet;2017-05-23;SeaDataNet;SeaDataNet is a standardized infrastructure for managing the large and diverse marine data sets collected at sea by the oceanographic fleets, the ships of opportunity and the automatic observation systems. The SeaDataNet infrastructure network sand enhances the currently existing infrastructures, which are the national oceanographic data centres or data focal points of 34 countries, active in data collection. The networking of these professional data centres, in a unique virtual data management system provides integrated data sets of standardized quality on-line. As a research infrastructure, SeaDataNet contributes to build research excellence in Europe.\nSeaDataNet connects together more than 100 data centres aiming at preserving and making re-useable marine observations ranging from ocean physics to chemistry and biology.\nSeaDataNet infrastructure was implemented during the SeaDataNet project (2006-2011), grant agreement 026212, EU Sixth Framework Programme. The second phase, SeaDataNet 2 project (2011-2015), grant agreement 283607, EU Seventh Framework Programme has upgraded the SeaDataNet infrastructure into an operationally robust and state-of-the-art Pan-European infrastructure for providing up-to-date and high quality access to ocean and marine metadata, data and data products by: setting, adopting and promoting common data management standards, realizing technical and semantic interoperability with other relevant data management systems and initiatives on behalf of science, environmental management, policy making, and economy.\nSeaDataCloud project (2016-2020), grant agreement 730960, EU H2020 programme, aims at considerably advancing SeaDataNet Services and increasing their usage, adopting cloud and High Performance Computing technology for better performance.;SeaDataNet;SeaDataNet;sdn-userdesk@seadatanet.org;SeaDataNet;sdn-userdesk@seadatanet.org;https://sextant.ifremer.fr/geonetwork/srv/api/records/ec9eb0a6-d6aa-41ae-b3ca-571c348c9cc6/attachments/SeaDataNet.png;SeaDataNet.png;/Human Activities/Ocean Observation Network;Th\u00e8mes Sextant;2017-09-22;geonetwork.thesaurus.local.theme.sextant-theme;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;2009-09-22;geonetwork.thesaurus.external.theme.httpinspireeceuropaeutheme-theme;Integrators;AtlantOS Element;2017-11-08;geonetwork.thesaurus.local.theme.atlantos_element;Marine data;Physics;Chemistry;Biology;Bathymetry;Data products;Aggregated datasets;Climatology;Air humidity;Air temperature;Atmospheric pressure;Bottom depth;Carbonate system;Carbon isotope 13C;Chlorophyll-a and fluorescence;Currents;Dissolved organic matter;Nitrous oxide;Nutrients;Oxygen;Salinity;Sea Level;Suspended particulates;Temperature;Transient tracers;Waves;Wind direction;Wind speed;AtlantOS Essential Variables;2017-02-16;geonetwork.thesaurus.external.parameter.NVS.A05;SeaDataNet Usage Agreement:\nIf you use SeaDataNet data in your publications please include the following in the Acknowledgements:\nData were provided through SeaDataNet Pan-European infrastructure for ocean and marine data management (https://www.seadatanet.org);No limitations on public access;oceans;-180;180;-90;90;1805;http://www.seadatanet.org;WWW:LINK;SeaDataNet web site;SeaDataNet web site;http://www.seadatanet.org/Standards;WWW:LINK;SeaDataNet standards;SeaDataNet standards;https://www.seadatanet.org/Data-Access;WWW:LINK;Data access services;Data search, browse and download;The SeaDataNet metadata are transmitted by the connected data centres to the central catalogue while data stays in the data centres and are available through a SeaDataNet connector at standardized formats (ASCII Ocean data View and netCDF). During the SeaDataCloud phase, all unrestricted data will be made available, through a replication software, in the cloud environment provided by EUDAT infrastructure",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "7fb92b79-940c-5297-877a-c2dbf43f688b",
-    "notes": [
-        "SeaDataNet is a standardized infrastructure for managing the large and diverse marine data sets collected at sea by the oceanographic fleets, the ships of opportunity and the automatic observation systems. The SeaDataNet infrastructure network sand enhances the currently existing infrastructures, which are the national oceanographic data centres or data focal points of 34 countries, active in data collection. The networking of these professional data centres, in a unique virtual data management system provides integrated data sets of standardized quality on-line. As a research infrastructure, SeaDataNet contributes to build research excellence in Europe.\nSeaDataNet connects together more than 100 data centres aiming at preserving and making re-useable marine observations ranging from ocean physics to chemistry and biology.\nSeaDataNet infrastructure was implemented during the SeaDataNet project (2006-2011), grant agreement 026212, EU Sixth Framework Programme. The second phase, SeaDataNet 2 project (2011-2015), grant agreement 283607, EU Seventh Framework Programme has upgraded the SeaDataNet infrastructure into an operationally robust and state-of-the-art Pan-European infrastructure for providing up-to-date and high quality access to ocean and marine metadata, data and data products by: setting, adopting and promoting common data management standards, realizing technical and semantic interoperability with other relevant data management systems and initiatives on behalf of science, environmental management, policy making, and economy.\nSeaDataCloud project (2016-2020), grant agreement 730960, EU H2020 programme, aims at considerably advancing SeaDataNet Services and increasing their usage, adopting cloud and High Performance Computing technology for better performance."
-    ],
-    "oai_identifier": [
-        "7fb92b79-940c-5297-877a-c2dbf43f688b"
-    ],
-    "oai_set": "seadatanet",
-    "relatedIdentifier": [
-        "https://sextant.ifremer.fr/geonetwork/srv/api/records/ec9eb0a6-d6aa-41ae-b3ca-571c348c9cc6/attachments/SeaDataNet.png"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-180,-90],[-180,90],[180,90],[180,-90],[-180,-90]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Human Activities Ocean Observation Network"
-        },
-        {
-            "name": "Environmental monitoring facilities"
-        },
-        {
-            "name": "Integrators"
-        },
-        {
-            "name": "Marine data"
-        },
-        {
-            "name": "Physics"
-        },
-        {
-            "name": "Chemistry"
-        },
-        {
-            "name": "Biology"
-        },
-        {
-            "name": "Bathymetry"
-        },
-        {
-            "name": "Data products"
-        },
-        {
-            "name": "Aggregated datasets"
-        },
-        {
-            "name": "Climatology"
-        },
-        {
-            "name": "Air humidity"
-        }
-    ],
-    "title": [
-        "SeaDataNet"
-    ],
-    "url": "https://www.seadatanet.org/Data-Access"
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-iso19139/seadatanet_1/json/88015b01-cda5-5c91-9c45-a88acc8fd771.json b/oaitestdata/seadatanet-iso19139/seadatanet_1/json/88015b01-cda5-5c91-9c45-a88acc8fd771.json
deleted file mode 100644
index 9b73dc67..00000000
--- a/oaitestdata/seadatanet-iso19139/seadatanet_1/json/88015b01-cda5-5c91-9c45-a88acc8fd771.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "sdn-userdesk@seadatanet.org"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/eng/csw-ATLANTOS?verb=GetRecord&metadataPrefix=iso19139&identifier=88015b01-cda5-5c91-9c45-a88acc8fd771",
-    "OpenAccess": [
-        "No limitations on public access.  For data access please register at http://www.marine-id.org"
-    ],
-    "PublicationTimestamp": "2017-07-11T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "SeaDataNet"
-    ],
-    "ResourceType": "dataset",
-    "Rights": [
-        "SeaDataNet Usage Agreement: If you use SeaDataNet data in your publications please include the following in the Acknowledgements: Data were provided through SeaDataNet Pan-European infrastructure for ocean and marine data management (https://www.seadatanet.org)"
-    ],
-    "SpatialCoverage": "(10N-83N,90W-93E)",
-    "TempCoverageBegin": 59926651199,
-    "TempCoverageEnd": 63560721599,
-    "TemporalCoverage": " period : ( 1900-01-01T11:59:59Z - 2015-02-28T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1900-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2015-02-28T11:59:59Z",
-    "fulltext": "ade2c115-0be4-467d-bdde-d98236ed7588;SeaDataNet;sdn-userdesk@seadatanet.org;2018-01-18T13:13:03;ISO 19115:2003/19139 - SEXTANT;1.0;WGS 84 (EPSG:4326);EPSG;8.6;SeaDataNet aggregated datasets over the Atlantic Ocean;2017-07-11;ATLANTOS_SEADATANET_COLLECTIONS;The SeaDataNet aggregated datasets over the Atlantic Ocean are regional ODV historical collections of all temperature and salinity measurements contained within SeaDataNet database and covering 3 European sea basins: North Arctic Ocean, North Sea, North Atlantic Ocean.\nTwo versions have been published during SeaDataNet 2 and they represent a snapshot of the SeaDataNet database content at two different times:\n\u2022\tV1.1 January 2014\n\u2022\tV2   March 2015\nEach of them is the result of the Quality Check Strategy (QCS) implemented during SeaDataNet 2 that contributed to highly improve the quality of temperature and salinity data. The QCS is made by four main phases:\n1.\tdata harvesting from the central CDI\n2.\tfile and parameter aggregation\n3.\tquality check analysis at regional level\n4.\tanalysis and correction of data anomalies.\nThe aggregated datasets have been prepared and quality checked using ODV software.;SeaDataNet;SeaDataNet;sdn-userdesk@seadatanet.org;SeaDataNet;sdn-userdesk@seadatanet.org;https://sextant.ifremer.fr/geonetwork/srv/api/records/ade2c115-0be4-467d-bdde-d98236ed7588/attachments/Atlantic_collection.png;/Human Activities/Ocean Observation Network;Th\u00e8mes Sextant;2017-09-22;geonetwork.thesaurus.local.theme.sextant-theme;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;2009-09-22;geonetwork.thesaurus.external.theme.httpinspireeceuropaeutheme-theme;Products;AtlantOS Element;2017-11-08;geonetwork.thesaurus.local.theme.atlantos_element;temperature;salinity;Temperature;Salinity;AtlantOS Essential Variables;2017-02-16;geonetwork.thesaurus.external.parameter.NVS.A05;SeaDataNet Usage Agreement: If you use SeaDataNet data in your publications please include the following in the Acknowledgements: Data were provided through SeaDataNet Pan-European infrastructure for ocean and marine data management (https://www.seadatanet.org);No limitations on public access.  For data access please register at http://www.marine-id.org;oceans;-90;93;10;83;1900-01-01;2015-02-28;https://sextant.ifremer.fr/en/web/seadatanet#/search?fast=index&_content_type=json&sortBy=popularity&from=1&to=20&any=north%20observation%20collection;WWW:LINK;View and download historical datasets;View and download historical datasets;The agregated datasets includes all open access temperature and salinity in situ data. The data were retrieved from the SeaDataNet infrastructure in January 2014 (v1.1) and march 2015 (v2). Data quality has been analysed and checked using ODV software. Quality Flags of anomalous data have been revised using different QC procedures in conjunction with the visual expert check. Duplicates have been identified and excluded from the dataset.",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "88015b01-cda5-5c91-9c45-a88acc8fd771",
-    "notes": [
-        "The SeaDataNet aggregated datasets over the Atlantic Ocean are regional ODV historical collections of all temperature and salinity measurements contained within SeaDataNet database and covering 3 European sea basins: North Arctic Ocean, North Sea, North Atlantic Ocean.\nTwo versions have been published during SeaDataNet 2 and they represent a snapshot of the SeaDataNet database content at two different times:\n\u2022\tV1.1 January 2014\n\u2022\tV2   March 2015\nEach of them is the result of the Quality Check Strategy (QCS) implemented during SeaDataNet 2 that contributed to highly improve the quality of temperature and salinity data. The QCS is made by four main phases:\n1.\tdata harvesting from the central CDI\n2.\tfile and parameter aggregation\n3.\tquality check analysis at regional level\n4.\tanalysis and correction of data anomalies.\nThe aggregated datasets have been prepared and quality checked using ODV software."
-    ],
-    "oai_identifier": [
-        "88015b01-cda5-5c91-9c45-a88acc8fd771"
-    ],
-    "oai_set": "seadatanet",
-    "relatedIdentifier": [
-        "https://sextant.ifremer.fr/geonetwork/srv/api/records/ade2c115-0be4-467d-bdde-d98236ed7588/attachments/Atlantic_collection.png"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-90,10],[-90,83],[93,83],[93,10],[-90,10]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Human Activities Ocean Observation Network"
-        },
-        {
-            "name": "Environmental monitoring facilities"
-        },
-        {
-            "name": "Products"
-        },
-        {
-            "name": "temperature"
-        },
-        {
-            "name": "salinity"
-        },
-        {
-            "name": "Temperature"
-        },
-        {
-            "name": "Salinity"
-        }
-    ],
-    "title": [
-        "SeaDataNet aggregated datasets over the Atlantic Ocean"
-    ],
-    "url": "https://sextant.ifremer.fr/en/web/seadatanet#/search?fast=index&_content_type=json&sortBy=popularity&from=1&to=20&any=north%20observation%20collection"
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-iso19139/seadatanet_1/json/8be095bf-10a1-5fad-bb95-794857e55a9c.json b/oaitestdata/seadatanet-iso19139/seadatanet_1/json/8be095bf-10a1-5fad-bb95-794857e55a9c.json
deleted file mode 100644
index 457cd53c..00000000
--- a/oaitestdata/seadatanet-iso19139/seadatanet_1/json/8be095bf-10a1-5fad-bb95-794857e55a9c.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "Contact": [
-        "sdn-userdesk@seadatanet.org"
-    ],
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/eng/csw-ATLANTOS?verb=GetRecord&metadataPrefix=iso19139&identifier=8be095bf-10a1-5fad-bb95-794857e55a9c",
-    "OpenAccess": [
-        "No limitations on public access.  For data access please register at http://www.marine-id.org"
-    ],
-    "PublicationTimestamp": "2017-07-11T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "SeaDataNet"
-    ],
-    "ResourceType": "dataset",
-    "Rights": [
-        "SeaDataNet Usage Agreement: If you use SeaDataNet data in your publications please include the following in the Acknowledgements: Data were provided through SeaDataNet Pan-European infrastructure for ocean and marine data management (https://www.seadatanet.org)"
-    ],
-    "SpatialCoverage": "(10N-82N,90W-65E)",
-    "TempCoverageBegin": 59926651199,
-    "TempCoverageEnd": 63560721599,
-    "TemporalCoverage": " period : ( 1900-01-01T11:59:59Z - 2015-02-28T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1900-01-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2015-02-28T11:59:59Z",
-    "fulltext": "639a97f9-b863-41a3-9b5f-604767356415;SeaDataNet;sdn-userdesk@seadatanet.org;2018-01-18T13:26:34;ISO 19115:2003/19139 - SEXTANT;1.0;WGS 84 (EPSG:4326);EPSG;8.6;SeaDataNet climatologies over the Atlantic Ocean;2017-07-11;ATLANTOS_SEADATANET_CLIMATOLOGIES;SeaDataNet gridded climatologies are based on the SeaDataNet Temperature and Salinity historical data collection v1.1. For the Atlantic Ocean there are covering 2 European sea basins: North Arctic Ocean, and North Atlantic Ocean The preparation of the products has also improved the quality, the consistency and the overall coherence of the data made available by SeaDataNet. They have been computed using DIVA software.;SeaDataNet;SeaDataNet;sdn-userdesk@seadatanet.org;SeaDataNet;sdn-userdesk@seadatanet.org;https://sextant.ifremer.fr/geonetwork/srv/api/records/639a97f9-b863-41a3-9b5f-604767356415/attachments/Atlantic_climato.png;/Human Activities/Ocean Observation Network;Th\u00e8mes Sextant;2017-09-22;geonetwork.thesaurus.local.theme.sextant-theme;Environmental monitoring facilities;GEMET - INSPIRE themes, version 1.0;2009-09-22;geonetwork.thesaurus.external.theme.httpinspireeceuropaeutheme-theme;Products;AtlantOS Element;2017-11-08;geonetwork.thesaurus.local.theme.atlantos_element;temperature;salinity;Temperature;Salinity;AtlantOS Essential Variables;2017-02-16;geonetwork.thesaurus.external.parameter.NVS.A05;SeaDataNet Usage Agreement: If you use SeaDataNet data in your publications please include the following in the Acknowledgements: Data were provided through SeaDataNet Pan-European infrastructure for ocean and marine data management (https://www.seadatanet.org);No limitations on public access.  For data access please register at http://www.marine-id.org;oceans;-90;65;10;82;1900-01-01;2015-02-28;https://sextant.ifremer.fr/en/web/seadatanet#/search?fast=index&_content_type=json&sortBy=popularity&from=1&to=20&any=north%20Climatology;WWW:LINK;View and download climatologies;View and download climatologies;SeaDataNet gridded climatologies are based on the aggregated datasets v1.1 issued in January 2014",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "8be095bf-10a1-5fad-bb95-794857e55a9c",
-    "notes": [
-        "SeaDataNet gridded climatologies are based on the SeaDataNet Temperature and Salinity historical data collection v1.1. For the Atlantic Ocean there are covering 2 European sea basins: North Arctic Ocean, and North Atlantic Ocean The preparation of the products has also improved the quality, the consistency and the overall coherence of the data made available by SeaDataNet. They have been computed using DIVA software."
-    ],
-    "oai_identifier": [
-        "8be095bf-10a1-5fad-bb95-794857e55a9c"
-    ],
-    "oai_set": "seadatanet",
-    "relatedIdentifier": [
-        "https://sextant.ifremer.fr/geonetwork/srv/api/records/639a97f9-b863-41a3-9b5f-604767356415/attachments/Atlantic_climato.png"
-    ],
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-90,10],[-90,82],[65,82],[65,10],[-90,10]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Human Activities Ocean Observation Network"
-        },
-        {
-            "name": "Environmental monitoring facilities"
-        },
-        {
-            "name": "Products"
-        },
-        {
-            "name": "temperature"
-        },
-        {
-            "name": "salinity"
-        },
-        {
-            "name": "Temperature"
-        },
-        {
-            "name": "Salinity"
-        }
-    ],
-    "title": [
-        "SeaDataNet climatologies over the Atlantic Ocean"
-    ],
-    "url": "https://sextant.ifremer.fr/en/web/seadatanet#/search?fast=index&_content_type=json&sortBy=popularity&from=1&to=20&any=north%20Climatology"
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/076e08f6-371f-5f8e-b7e5-1e3bdfec36d6.json b/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/076e08f6-371f-5f8e-b7e5-1e3bdfec36d6.json
deleted file mode 100644
index 98b1e700..00000000
--- a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/076e08f6-371f-5f8e-b7e5-1e3bdfec36d6.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.12770/6aeb76a1-cc67-4071-a3a0-3be3b050fe21",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=oai_dc&identifier=076e08f6-371f-5f8e-b7e5-1e3bdfec36d6",
-    "Rights": [
-        "otherRestrictions"
-    ],
-    "SpatialCoverage": [
-        "9.96 48.6",
-        "-4.25 62"
-    ],
-    "fulltext": "6aeb76a1-cc67-4071-a3a0-3be3b050fe21;2018-07-24T09:47:48;North Sea - Temperature and salinity observation collection V1.1;seadatanet-north_sea-temperature_salinity_aggregated_public-v1_1;series;Oceanographic geographical features;Temperature of the water column;Salinity of the water column;ITS-90 water temperature;Water body salinity;North Sea;oceans;The North Sea historical dataset includes all open access temperature and salinity in situ data from the North Sea for the period 1900 \u2013 2013. The data were retrieved from the SeaDataNet infrastructure at the beginning of 2014. Data quality has been analysed and checked using ODV software. Quality Flags of anomalous data have been revised using different QC procedures in conjunction with the visual expert check. Duplicates have been identified and excluded from the dataset.\n\nFor data access please register at http://www.marine-id.org;The North Sea historical dataset includes all open access temperature and salinity in situ data from the North Sea for the period 1900 \u2013 2013. The data were retrieved from the SeaDataNet infrastructure at the beginning of 2014. Data quality has been analysed and checked using ODV software. Quality Flags of anomalous data have been revised using different QC procedures in conjunction with the visual expert check. Duplicates have been identified and excluded from the dataset.\n\nFor data access please register at http://www.marine-id.org;otherRestrictions;eng;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI;9.96 48.6;-4.25 62;http://dx.doi.org/10.12770/6aeb76a1-cc67-4071-a3a0-3be3b050fe21;ftp://ftp2.ifremer.fr/public/seadatanet-north_sea-temperaturesalinity_aggregated/SDN_2014-03_TS_North_Sea_QC_done_v1.1.zip;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_North_Sea_QC_done_v1.1;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_North_Sea_QC_done_v1.1;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_North_Sea_QC_done_v1.1;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_North_Sea_QC_done_v1.1;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=6aeb76a1-cc67-4071-a3a0-3be3b050fe21&fname=NorthSeaTransp.png",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "076e08f6-371f-5f8e-b7e5-1e3bdfec36d6",
-    "notes": [
-        "The North Sea historical dataset includes all open access temperature and salinity in situ data from the North Sea for the period 1900 \u2013 2013. The data were retrieved from the SeaDataNet infrastructure at the beginning of 2014. Data quality has been analysed and checked using ODV software. Quality Flags of anomalous data have been revised using different QC procedures in conjunction with the visual expert check. Duplicates have been identified and excluded from the dataset.\n\nFor data access please register at http://www.marine-id.org"
-    ],
-    "oai_identifier": [
-        "076e08f6-371f-5f8e-b7e5-1e3bdfec36d6"
-    ],
-    "oai_set": "cams1_ps",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "North Sea"
-        },
-        {
-            "name": "oceans"
-        }
-    ],
-    "title": [
-        "North Sea - Temperature and salinity observation collection V1.1"
-    ],
-    "url": "https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=6aeb76a1-cc67-4071-a3a0-3be3b050fe21&fname=NorthSeaTransp.png"
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/0c10d441-0c39-542a-86cb-4a2d49fd0ffe.json b/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/0c10d441-0c39-542a-86cb-4a2d49fd0ffe.json
deleted file mode 100644
index f2904068..00000000
--- a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/0c10d441-0c39-542a-86cb-4a2d49fd0ffe.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.12770/2287615d-1977-479f-8d5b-439960bcb21a",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=oai_dc&identifier=0c10d441-0c39-542a-86cb-4a2d49fd0ffe",
-    "Rights": [
-        "otherRestrictions"
-    ],
-    "SpatialCoverage": [
-        "42 40.5",
-        "27.5 47.5"
-    ],
-    "fulltext": "2287615d-1977-479f-8d5b-439960bcb21a;2018-09-27T07:47:25;Black Sea - Temperature and salinity Historical Data Collection SeaDataCloud V1;SDC_BLS_DATA_TS_V1;dataset;Oceanographic geographical features;Salinity of the water column;Temperature of the water column;Water body salinity;ITS-90 water temperature;Sea of Azov;Black Sea;oceans;ODV binary collection;The SeaDataCloud Temperature and Salinity Historical Data Collection for the Black Sea includes open access in situ data on temperature and salinity of water column in the Black Sea (and a little in the Sea of Azov) for period 1868 \u2013 2017. The data were retrieved from the SeaDataNet infrastructure at the end of 2017. The dataset format is Ocean Data View (ODV - http://odv.awi.de/) binary collection. The quality control of the data has been performed with the help of ODV software. Data Quality Flags have been revised and set up using the elaborated by SeaDataNet2 project QC procedures in conjunction with the visual expert check. Data duplicates have been identified and excluded from the dataset. The final number of the Temperature and Salinity profiles (stations) in the collection is 137723.\n\nFor data access please register at http://www.marine-id.org/.;The SeaDataCloud Temperature and Salinity Historical Data Collection for the Black Sea includes open access in situ data on temperature and salinity of water column in the Black Sea (and a little in the Sea of Azov) for period 1868 \u2013 2017. The data were retrieved from the SeaDataNet infrastructure at the end of 2017. The dataset format is Ocean Data View (ODV - http://odv.awi.de/) binary collection. The quality control of the data has been performed with the help of ODV software. Data Quality Flags have been revised and set up using the elaborated by SeaDataNet2 project QC procedures in conjunction with the visual expert check. Data duplicates have been identified and excluded from the dataset. The final number of the Temperature and Salinity profiles (stations) in the collection is 137723.\n\nFor data access please register at http://www.marine-id.org/.;otherRestrictions;eng;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI;ODV binary collection;42 40.5;27.5 47.5;http://dx.doi.org/10.12770/2287615d-1977-479f-8d5b-439960bcb21a;https://sextant.ifremer.fr/geonetwork/srv/fre//resources.get?uuid=2287615d-1977-479f-8d5b-439960bcb21a&fname=BLACK_SDC_V1.png",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "0c10d441-0c39-542a-86cb-4a2d49fd0ffe",
-    "notes": [
-        "The SeaDataCloud Temperature and Salinity Historical Data Collection for the Black Sea includes open access in situ data on temperature and salinity of water column in the Black Sea (and a little in the Sea of Azov) for period 1868 \u2013 2017. The data were retrieved from the SeaDataNet infrastructure at the end of 2017. The dataset format is Ocean Data View (ODV - http://odv.awi.de/) binary collection. The quality control of the data has been performed with the help of ODV software. Data Quality Flags have been revised and set up using the elaborated by SeaDataNet2 project QC procedures in conjunction with the visual expert check. Data duplicates have been identified and excluded from the dataset. The final number of the Temperature and Salinity profiles (stations) in the collection is 137723.\n\nFor data access please register at http://www.marine-id.org/."
-    ],
-    "oai_identifier": [
-        "0c10d441-0c39-542a-86cb-4a2d49fd0ffe"
-    ],
-    "oai_set": "cams1_ps",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Sea Azov"
-        },
-        {
-            "name": "Black Sea"
-        },
-        {
-            "name": "oceans"
-        }
-    ],
-    "title": [
-        "Black Sea - Temperature and salinity Historical Data Collection SeaDataCloud V1"
-    ],
-    "url": "https://sextant.ifremer.fr/geonetwork/srv/fre//resources.get?uuid=2287615d-1977-479f-8d5b-439960bcb21a&fname=BLACK_SDC_V1.png"
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/0f378d06-d191-5130-94d6-b2507aa9234a.json b/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/0f378d06-d191-5130-94d6-b2507aa9234a.json
deleted file mode 100644
index 6c32f122..00000000
--- a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/0f378d06-d191-5130-94d6-b2507aa9234a.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.12770/cd552057-b604-4004-b838-a4f73cc98fcf",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=oai_dc&identifier=0f378d06-d191-5130-94d6-b2507aa9234a",
-    "Rights": [
-        "otherRestrictions"
-    ],
-    "SpatialCoverage": [
-        "36.625 30.000",
-        "-9.250 46.125"
-    ],
-    "fulltext": "cd552057-b604-4004-b838-a4f73cc98fcf;2018-07-24T09:47:24;Mediterranean Sea - Temperature and salinity observation collection V1.1;seadatanet-med_sea-temperature_salinity_aggregated_public-v1_1;series;Oceanographic geographical features;Temperature of the water column;Temperature variation in the water column;Salinity of the water column;ITS-90 water temperature;Water body salinity;Adriatic Sea;Ligurian Sea;Mediterranean Sea, Eastern Basin;Mediterranean Sea, Western Basin;Ionian Sea;Tyrrhenian Sea;Balearic Sea;Mediterranean Region;Mediterranean Sea;Aegean Sea;Sea of Marmara;oceans;SeaDataNet Temperature and Salinity historical data collection contains all open access temperature and salinity in situ data retrieved from SeaDataNet infrastructure at the end of 2013. The data span between -9.25 and 37 degrees of longitude, thus including an Atlantic box and Marmara Sea, and cover the time period 1900-2012.\nData have been quality checked using ODV software. Quality Flags of anomalous data have been revised using basic QC procedures.\n\nFor data access please register at http://www.marine-id.org\n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/;SeaDataNet Temperature and Salinity historical data collection contains all open access temperature and salinity in situ data retrieved from SeaDataNet infrastructure at the end of 2013. The data span between -9.25 and 37 degrees of longitude, thus including an Atlantic box and Marmara Sea, and cover the time period 1900-2012.\nData have been quality checked using ODV software. Quality Flags of anomalous data have been revised using basic QC procedures.\n\nFor data access please register at http://www.marine-id.org\n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/;otherRestrictions;eng;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI;36.625 30.000;-9.250 46.125;http://dx.doi.org/10.12770/cd552057-b604-4004-b838-a4f73cc98fcf;ftp://vftp2.ifremer.fr/public/seadatanet-med_sea-temperaturesalinity_aggregated/SDN_2014-03_TS_MedSea_QC_done_v1.1.zip;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_MedSea_QC_done_v1.1;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_MedSea_QC_done_v1.1;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_MedSea_QC_done_v1.1;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_MedSea_QC_done_v1.1;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=cd552057-b604-4004-b838-a4f73cc98fcf&fname=MedSeaTransp.png",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "0f378d06-d191-5130-94d6-b2507aa9234a",
-    "notes": [
-        "SeaDataNet Temperature and Salinity historical data collection contains all open access temperature and salinity in situ data retrieved from SeaDataNet infrastructure at the end of 2013. The data span between -9.25 and 37 degrees of longitude, thus including an Atlantic box and Marmara Sea, and cover the time period 1900-2012.\nData have been quality checked using ODV software. Quality Flags of anomalous data have been revised using basic QC procedures.\n\nFor data access please register at http://www.marine-id.org\n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/"
-    ],
-    "oai_identifier": [
-        "0f378d06-d191-5130-94d6-b2507aa9234a"
-    ],
-    "oai_set": "cams1_ps",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Temperature variation water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "Adriatic Sea"
-        },
-        {
-            "name": "Ligurian Sea"
-        },
-        {
-            "name": "Mediterranean Sea"
-        },
-        {
-            "name": "Eastern Basin"
-        },
-        {
-            "name": "Mediterranean Sea"
-        },
-        {
-            "name": "Western Basin"
-        }
-    ],
-    "title": [
-        "Mediterranean Sea - Temperature and salinity observation collection V1.1"
-    ],
-    "url": "https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=cd552057-b604-4004-b838-a4f73cc98fcf&fname=MedSeaTransp.png"
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/27c4e287-a115-5da6-9ee2-b8d35e156af3.json b/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/27c4e287-a115-5da6-9ee2-b8d35e156af3.json
deleted file mode 100644
index 53e1c7d2..00000000
--- a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/27c4e287-a115-5da6-9ee2-b8d35e156af3.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.12770/993571fa-cdaf-4b5f-be7e-db9a88ca6d8c",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=oai_dc&identifier=27c4e287-a115-5da6-9ee2-b8d35e156af3",
-    "Rights": [
-        "otherRestrictions"
-    ],
-    "SpatialCoverage": [
-        "30 53",
-        "9 66"
-    ],
-    "fulltext": "993571fa-cdaf-4b5f-be7e-db9a88ca6d8c;2018-07-24T09:47:33;Baltic Sea - Temperature and salinity observation collection V1.1;seadatanet-baltic_sea-temperature_salinity_aggregated_public-v1_1;series;Oceanographic geographical features;Temperature of the water column;Salinity of the water column;ITS-90 water temperature;Water body salinity;Baltic Sea;Bay of Bothnia;Central Baltic Sea;Gulf of Bothnia;Gulf of Finland;Kattegat;Lillebaelt;Skagerrak;Storebaelt;oceans;Seadatanet temperature and salinity historical data collection, including revised quality flags after quality control.\n\nFor data access please register at http://www.marine-id.org\n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/;Seadatanet temperature and salinity historical data collection, including revised quality flags after quality control.\n\nFor data access please register at http://www.marine-id.org\n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/;otherRestrictions;eng;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI;30 53;9 66;http://dx.doi.org/10.12770/993571fa-cdaf-4b5f-be7e-db9a88ca6d8c;ftp://vftp2.ifremer.fr/public/seadatanet-baltic_sea-temperaturesalinity_aggregated/SDN_2014-03_TS_BalticSea_QC_done_v1.1.zip;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_BalticSea_QC_done_v1.1;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_BalticSea_QC_done_v1.1;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_BalticSea_QC_done_v1.1;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_BalticSea_QC_done_v1.1;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=993571fa-cdaf-4b5f-be7e-db9a88ca6d8c&fname=BalticSeaTransp.png",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "27c4e287-a115-5da6-9ee2-b8d35e156af3",
-    "notes": [
-        "Seadatanet temperature and salinity historical data collection, including revised quality flags after quality control.\n\nFor data access please register at http://www.marine-id.org\n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/"
-    ],
-    "oai_identifier": [
-        "27c4e287-a115-5da6-9ee2-b8d35e156af3"
-    ],
-    "oai_set": "cams1_ps",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "Baltic Sea"
-        },
-        {
-            "name": "Bay Bothnia"
-        },
-        {
-            "name": "Central Baltic Sea"
-        },
-        {
-            "name": "Gulf Bothnia"
-        },
-        {
-            "name": "Gulf Finland"
-        },
-        {
-            "name": "Kattegat"
-        },
-        {
-            "name": "Lillebaelt"
-        }
-    ],
-    "title": [
-        "Baltic Sea - Temperature and salinity observation collection V1.1"
-    ],
-    "url": "https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=993571fa-cdaf-4b5f-be7e-db9a88ca6d8c&fname=BalticSeaTransp.png"
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/390e5b25-ee73-5b8a-bc37-7f339bb8221d.json b/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/390e5b25-ee73-5b8a-bc37-7f339bb8221d.json
deleted file mode 100644
index bd32e207..00000000
--- a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/390e5b25-ee73-5b8a-bc37-7f339bb8221d.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.12770/970bb3ba-aaf6-4066-9656-87c85da41dbb",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=oai_dc&identifier=390e5b25-ee73-5b8a-bc37-7f339bb8221d",
-    "Rights": [
-        "otherRestrictions"
-    ],
-    "SpatialCoverage": [
-        "10 10",
-        "-90 62"
-    ],
-    "fulltext": "970bb3ba-aaf6-4066-9656-87c85da41dbb;2018-09-27T10:27:14;North Atlantic Ocean - Temperature and Salinity Historical Data Collection SeaDataCloud V1;SDC_NAT_DATA_TS_V1;dataset;Oceanographic geographical features;Temperature of the water column;Salinity of the water column;Water body salinity;ITS-90 water temperature;Atlantic Ocean;oceans;ODV binary collection;The SeaDataCloud TS historical data collection v1 for the North Atlantic Ocean, includes open access in situ data on temperature and salinity of water column in the North Atlantic Ocean from 10\u00b0N  to 62\u00b0N, including the Labrador Sea, The data were retrieved from the SeaDataNet infrastructure at the end of November 2017. The dataset format is Ocean Data View (ODV - http://odv.awi.de/) binary collection. The quality control of the data has been performed with the help of ODV software. Data Quality Flags have been revised and set up using the elaborated by SeaDataNet2 project QC procedures in conjunction with the visual expert check. The final number of the Temperature and Salinity profiles (stations) in the collection is 9091773.\n\nFor data access please register at http://www.marine-id.org/.;The SeaDataCloud TS historical data collection v1 for the North Atlantic Ocean, includes open access in situ data on temperature and salinity of water column in the North Atlantic Ocean from 10\u00b0N  to 62\u00b0N, including the Labrador Sea, The data were retrieved from the SeaDataNet infrastructure at the end of November 2017. The dataset format is Ocean Data View (ODV - http://odv.awi.de/) binary collection. The quality control of the data has been performed with the help of ODV software. Data Quality Flags have been revised and set up using the elaborated by SeaDataNet2 project QC procedures in conjunction with the visual expert check. The final number of the Temperature and Salinity profiles (stations) in the collection is 9091773.\n\nFor data access please register at http://www.marine-id.org/.;otherRestrictions;eng;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI;ODV binary collection;10 10;-90 62;http://dx.doi.org/10.12770/970bb3ba-aaf6-4066-9656-87c85da41dbb;ftp://vftp2.ifremer.fr/public/seadatanet-north_atlantic_ocean-temperaturesalinity_aggregated/SDC_NAT_DATA_TS_V1/;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=970bb3ba-aaf6-4066-9656-87c85da41dbb&fname=Map_Final_NAT_WITHOUTONLAND.png",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "390e5b25-ee73-5b8a-bc37-7f339bb8221d",
-    "notes": [
-        "The SeaDataCloud TS historical data collection v1 for the North Atlantic Ocean, includes open access in situ data on temperature and salinity of water column in the North Atlantic Ocean from 10\u00b0N  to 62\u00b0N, including the Labrador Sea, The data were retrieved from the SeaDataNet infrastructure at the end of November 2017. The dataset format is Ocean Data View (ODV - http://odv.awi.de/) binary collection. The quality control of the data has been performed with the help of ODV software. Data Quality Flags have been revised and set up using the elaborated by SeaDataNet2 project QC procedures in conjunction with the visual expert check. The final number of the Temperature and Salinity profiles (stations) in the collection is 9091773.\n\nFor data access please register at http://www.marine-id.org/."
-    ],
-    "oai_identifier": [
-        "390e5b25-ee73-5b8a-bc37-7f339bb8221d"
-    ],
-    "oai_set": "cams1_ps",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Atlantic Ocean"
-        },
-        {
-            "name": "oceans"
-        }
-    ],
-    "title": [
-        "North Atlantic Ocean - Temperature and Salinity Historical Data Collection SeaDataCloud V1"
-    ],
-    "url": "https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=970bb3ba-aaf6-4066-9656-87c85da41dbb&fname=Map_Final_NAT_WITHOUTONLAND.png"
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/47a5fc9c-f244-59d5-83a8-87d938b2074c.json b/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/47a5fc9c-f244-59d5-83a8-87d938b2074c.json
deleted file mode 100644
index 90352adf..00000000
--- a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/47a5fc9c-f244-59d5-83a8-87d938b2074c.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.12770/bf35a7c5-c843-4a23-8040-07ddcf3d8e71",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=oai_dc&identifier=47a5fc9c-f244-59d5-83a8-87d938b2074c",
-    "Rights": [
-        "otherRestrictions"
-    ],
-    "SpatialCoverage": [
-        "31 53",
-        "9 66"
-    ],
-    "fulltext": "bf35a7c5-c843-4a23-8040-07ddcf3d8e71;2018-07-24T09:47:26;Baltic Sea - Temperature and Salinity Climatology V1.1;series;Oceanographic geographical features;Temperature of the water column;Salinity of the water column;ITS-90 water temperature;Water body salinity;Baltic Sea;Central Baltic Sea;Bay of Bothnia;Bothnian Sea;Gulf of Finland;Gulf of Bothnia;Lillebaelt;Kattegat;Skagerrak;Storebaelt;oceans;Seadatanet temperature and salinity monthly climatologies 1900-2012 by DIVA software v4.6.10. Based on Seadatanet historical dataset v1.1.\n\nFor data access please register at http://www.marine-id.org \n\nDIVA settings:\nSeasonal background fields, months 12-02, 03-05, 06-08, 09-11.\nWeighting have been used with length of weighting 0.5\u00b0 and time of weighting 2 days.;Seadatanet temperature and salinity monthly climatologies 1900-2012 by DIVA software v4.6.10. Based on Seadatanet historical dataset v1.1.\n\nFor data access please register at http://www.marine-id.org \n\nDIVA settings:\nSeasonal background fields, months 12-02, 03-05, 06-08, 09-11.\nWeighting have been used with length of weighting 0.5\u00b0 and time of weighting 2 days.;otherRestrictions;eng;The data used as input for this product have been extracted from the SeaDataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI;31 53;9 66;http://dx.doi.org/10.12770/bf35a7c5-c843-4a23-8040-07ddcf3d8e71;http://gher-diva.phys.ulg.ac.be:8080/SeaDataNet-domains/Baltic/Salinity.19002012.4Danl.nc.html;http://gher-diva.phys.ulg.ac.be:8080/SeaDataNet-domains/Baltic/Temperature.19002012.4Danl.nc.html;ftp://ftp2.ifremer.fr/public/seadatanet-baltic_sea-temperaturesalinity_climatologie/SDN_2015-11_TS_Baltic_Sea_Climatology_v1.1.zip;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=bf35a7c5-c843-4a23-8040-07ddcf3d8e71&fname=baltic_clim.png",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "47a5fc9c-f244-59d5-83a8-87d938b2074c",
-    "notes": [
-        "Seadatanet temperature and salinity monthly climatologies 1900-2012 by DIVA software v4.6.10. Based on Seadatanet historical dataset v1.1.\n\nFor data access please register at http://www.marine-id.org \n\nDIVA settings:\nSeasonal background fields, months 12-02, 03-05, 06-08, 09-11.\nWeighting have been used with length of weighting 0.5\u00b0 and time of weighting 2 days."
-    ],
-    "oai_identifier": [
-        "47a5fc9c-f244-59d5-83a8-87d938b2074c"
-    ],
-    "oai_set": "cams1_ps",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "Baltic Sea"
-        },
-        {
-            "name": "Central Baltic Sea"
-        },
-        {
-            "name": "Bay Bothnia"
-        },
-        {
-            "name": "Bothnian Sea"
-        },
-        {
-            "name": "Gulf Finland"
-        },
-        {
-            "name": "Gulf Bothnia"
-        },
-        {
-            "name": "Lillebaelt"
-        }
-    ],
-    "title": [
-        "Baltic Sea - Temperature and Salinity Climatology V1.1"
-    ],
-    "url": "https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=bf35a7c5-c843-4a23-8040-07ddcf3d8e71&fname=baltic_clim.png"
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/5a896000-4049-5c86-ae45-461fc186ff5c.json b/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/5a896000-4049-5c86-ae45-461fc186ff5c.json
deleted file mode 100644
index d3ce6f40..00000000
--- a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/5a896000-4049-5c86-ae45-461fc186ff5c.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.12770/f080166b-0632-4de2-85df-97829d56eabf",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=oai_dc&identifier=5a896000-4049-5c86-ae45-461fc186ff5c",
-    "Rights": [
-        "otherRestrictions"
-    ],
-    "SpatialCoverage": [
-        "93 61.9",
-        "-43 83"
-    ],
-    "fulltext": "f080166b-0632-4de2-85df-97829d56eabf;2018-07-24T09:47:25;Arctic Ocean - Temperature and salinity observation collection V2;seadatanet-arctic_sea-temperature_salinity_aggregated_public-v2;series;Oceanographic geographical features;Temperature of the water column;Salinity of the water column;ITS-90 water temperature;Water body salinity;Arctic Ocean;oceans;SeaDataNet Temperature and Salinity historical data collection for the North Arctic Ocean, including revised quality flags after quality control with ODV. For data access please register at http://www.marine-id.org The dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/;SeaDataNet Temperature and Salinity historical data collection for the North Arctic Ocean, including revised quality flags after quality control with ODV. For data access please register at http://www.marine-id.org The dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/;otherRestrictions;eng;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI;93 61.9;-43 83;http://dx.doi.org/10.12770/f080166b-0632-4de2-85df-97829d56eabf;ftp://ftp2.ifremer.fr/public/seadatanet-arctic_ocean-temperaturesalinity_aggregated/SDN_2015-09_TS_Arctic_QC_done_v2.zip;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_Arctic_QC_done_v2;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_Arctic_QC_done_v2;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_Arctic_QC_done_v2;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_Arctic_QC_done_v2;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=f080166b-0632-4de2-85df-97829d56eabf&fname=DefaultView_0.png",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "5a896000-4049-5c86-ae45-461fc186ff5c",
-    "notes": [
-        "SeaDataNet Temperature and Salinity historical data collection for the North Arctic Ocean, including revised quality flags after quality control with ODV. For data access please register at http://www.marine-id.org The dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/"
-    ],
-    "oai_identifier": [
-        "5a896000-4049-5c86-ae45-461fc186ff5c"
-    ],
-    "oai_set": "cams1_ps",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "Arctic Ocean"
-        },
-        {
-            "name": "oceans"
-        }
-    ],
-    "title": [
-        "Arctic Ocean - Temperature and salinity observation collection V2"
-    ],
-    "url": "https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=f080166b-0632-4de2-85df-97829d56eabf&fname=DefaultView_0.png"
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/65d3b4df-ef43-566c-a161-530aac1ad33d.json b/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/65d3b4df-ef43-566c-a161-530aac1ad33d.json
deleted file mode 100644
index 76a00e36..00000000
--- a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/65d3b4df-ef43-566c-a161-530aac1ad33d.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.12770/103b40c0-c07b-46ba-b0e3-f4d5293edd13",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=oai_dc&identifier=65d3b4df-ef43-566c-a161-530aac1ad33d",
-    "Rights": [
-        "otherRestrictions"
-    ],
-    "SpatialCoverage": [
-        "10 10",
-        "-90 65"
-    ],
-    "fulltext": "103b40c0-c07b-46ba-b0e3-f4d5293edd13;2018-07-24T09:47:25;North Atlantic Ocean - Temperature and Salinity Climatology V1.1;seadatanet-north_atlantic_ocean-climatology_public;series;Oceanographic geographical features;Temperature of the water column;Salinity of the water column;ITS-90 water temperature;Water body salinity;Atlantic Ocean;oceans;Climatology done from the SeaDataNet aggregated dataset v1.1 for the North Atlantic Ocean.\nThe version used for the DIVA software is the 4.6.9.\nThe period covers 1900-2013.\n\n For data access please register at http://www.marine-id.org;Climatology done from the SeaDataNet aggregated dataset v1.1 for the North Atlantic Ocean.\nThe version used for the DIVA software is the 4.6.9.\nThe period covers 1900-2013.\n\n For data access please register at http://www.marine-id.org;otherRestrictions;eng;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI;10 10;-90 65;http://dx.doi.org/10.12770/103b40c0-c07b-46ba-b0e3-f4d5293edd13;http://oceanbrowser.net/web-vis/Python/web/wms;http://oceanbrowser.net/web-vis/Python/web/wms;http://oceanbrowser.net/web-vis/Python/web/wms;http://oceanbrowser.net/web-vis/Python/web/wms;http://oceanbrowser.net/web-vis/Python/web/wms;ftp://ftp2.ifremer.fr/public/seadatanet-north_atlantic_ocean-temperaturesalinity_climatologie/SDN_2015-08_TS_Atlantic_Climatology_v1.1.zip;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=103b40c0-c07b-46ba-b0e3-f4d5293edd13&fname=Icone_catalogue_sextant_runB.png",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "65d3b4df-ef43-566c-a161-530aac1ad33d",
-    "notes": [
-        "Climatology done from the SeaDataNet aggregated dataset v1.1 for the North Atlantic Ocean.\nThe version used for the DIVA software is the 4.6.9.\nThe period covers 1900-2013.\n\n For data access please register at http://www.marine-id.org"
-    ],
-    "oai_identifier": [
-        "65d3b4df-ef43-566c-a161-530aac1ad33d"
-    ],
-    "oai_set": "cams1_ps",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "Atlantic Ocean"
-        },
-        {
-            "name": "oceans"
-        }
-    ],
-    "title": [
-        "North Atlantic Ocean - Temperature and Salinity Climatology V1.1"
-    ],
-    "url": "https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=103b40c0-c07b-46ba-b0e3-f4d5293edd13&fname=Icone_catalogue_sextant_runB.png"
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/6d5b80c0-f9ea-5594-922c-b580bf5cae07.json b/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/6d5b80c0-f9ea-5594-922c-b580bf5cae07.json
deleted file mode 100644
index 453204a8..00000000
--- a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/6d5b80c0-f9ea-5594-922c-b580bf5cae07.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.12770/8a51f275-6a8a-4ac2-ba7e-fe491e63a17d",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=oai_dc&identifier=6d5b80c0-f9ea-5594-922c-b580bf5cae07",
-    "Rights": [
-        "otherRestrictions"
-    ],
-    "SpatialCoverage": [
-        "10 49",
-        "-4 62"
-    ],
-    "fulltext": "8a51f275-6a8a-4ac2-ba7e-fe491e63a17d;2018-07-24T09:47:44;North Sea - Temperature and salinity observation collection V2;seadatanet-north_sea-temperature_salinity_aggregated_public-v2;series;Oceanographic geographical features;Temperature of the water column;Salinity of the water column;ITS-90 water temperature;Water body salinity;North Sea;oceans;SeaDataNet Temperature and Salinity historical data collection for the North Sea contains all open access temperature and salinity in situ data retrieved from SeaDataNet infrastructure at the end of 2014. The data span between -4\u00b0W and 10\u00b0E in longitude, and from 49\u00b0N to 62\u00b0N in latitude. It covers the time period 1900-2014. Data have been quality checked using ODV software. Quality Flags of anomalous data have been revised using basic QC procedures.\n\nThe dataset is available on authenticated FTP as zip files. You can get access codes from : http://www.marine-id.org. The dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/;SeaDataNet Temperature and Salinity historical data collection for the North Sea contains all open access temperature and salinity in situ data retrieved from SeaDataNet infrastructure at the end of 2014. The data span between -4\u00b0W and 10\u00b0E in longitude, and from 49\u00b0N to 62\u00b0N in latitude. It covers the time period 1900-2014. Data have been quality checked using ODV software. Quality Flags of anomalous data have been revised using basic QC procedures.\n\nThe dataset is available on authenticated FTP as zip files. You can get access codes from : http://www.marine-id.org. The dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/;otherRestrictions;eng;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI;10 49;-4 62;http://dx.doi.org/10.12770/8a51f275-6a8a-4ac2-ba7e-fe491e63a17d;ftp://ftp2.ifremer.fr/public/seadatanet-north_sea-temperaturesalinity_aggregated/SDN_2015-09_TS_North_Sea_QC_done_v2.zip;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_North_Sea_QC_done_v2;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=8a51f275-6a8a-4ac2-ba7e-fe491e63a17d&fname=DefaultView_0.png",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "6d5b80c0-f9ea-5594-922c-b580bf5cae07",
-    "notes": [
-        "SeaDataNet Temperature and Salinity historical data collection for the North Sea contains all open access temperature and salinity in situ data retrieved from SeaDataNet infrastructure at the end of 2014. The data span between -4\u00b0W and 10\u00b0E in longitude, and from 49\u00b0N to 62\u00b0N in latitude. It covers the time period 1900-2014. Data have been quality checked using ODV software. Quality Flags of anomalous data have been revised using basic QC procedures.\n\nThe dataset is available on authenticated FTP as zip files. You can get access codes from : http://www.marine-id.org. The dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/"
-    ],
-    "oai_identifier": [
-        "6d5b80c0-f9ea-5594-922c-b580bf5cae07"
-    ],
-    "oai_set": "cams1_ps",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "North Sea"
-        },
-        {
-            "name": "oceans"
-        }
-    ],
-    "title": [
-        "North Sea - Temperature and salinity observation collection V2"
-    ],
-    "url": "https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=8a51f275-6a8a-4ac2-ba7e-fe491e63a17d&fname=DefaultView_0.png"
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/720fc240-bde4-5a64-a104-094059168e89.json b/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/720fc240-bde4-5a64-a104-094059168e89.json
deleted file mode 100644
index 9a296712..00000000
--- a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/720fc240-bde4-5a64-a104-094059168e89.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.12770/2a5c1396-f832-4500-8faa-8cfeeded1ebb",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=oai_dc&identifier=720fc240-bde4-5a64-a104-094059168e89",
-    "Rights": [
-        "otherRestrictions"
-    ],
-    "SpatialCoverage": [
-        "10 10",
-        "-90 65"
-    ],
-    "fulltext": "2a5c1396-f832-4500-8faa-8cfeeded1ebb;2018-07-24T09:47:30;North Atlantic Ocean - Temperature and salinity observation collection V1.1;seadatanet-north_atlantic_ocean-temperature_salinity_aggregated_public-v1_1;series;Oceanographic geographical features;Temperature of the water column;Salinity of the water column;ITS-90 water temperature;Water body salinity;North Atlantic Ocean;oceans;SeaDataNet Temperature and Salinity historical data collection, including revised quality flags after quality control with ODV.\n\nFor data access please register at http://www.marine-id.org\n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/;SeaDataNet Temperature and Salinity historical data collection, including revised quality flags after quality control with ODV.\n\nFor data access please register at http://www.marine-id.org\n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/;otherRestrictions;eng;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI;10 10;-90 65;http://dx.doi.org/10.12770/2a5c1396-f832-4500-8faa-8cfeeded1ebb;ftp://vftp2.ifremer.fr/public/seadatanet-north_atlantic_ocean-temperaturesalinity_aggregated/SDN_2014-03_TS_Atlantic_QC_done_v1.1.zip;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_Atlantic_QC_done_v1.1;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_Atlantic_QC_done_v1.1;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_Atlantic_QC_done_v1.1;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_Atlantic_QC_done_v1.1;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=2a5c1396-f832-4500-8faa-8cfeeded1ebb&fname=NorthAtlanticTransp.png",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "720fc240-bde4-5a64-a104-094059168e89",
-    "notes": [
-        "SeaDataNet Temperature and Salinity historical data collection, including revised quality flags after quality control with ODV.\n\nFor data access please register at http://www.marine-id.org\n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/"
-    ],
-    "oai_identifier": [
-        "720fc240-bde4-5a64-a104-094059168e89"
-    ],
-    "oai_set": "cams1_ps",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "North Atlantic Ocean"
-        },
-        {
-            "name": "oceans"
-        }
-    ],
-    "title": [
-        "North Atlantic Ocean - Temperature and salinity observation collection V1.1"
-    ],
-    "url": "https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=2a5c1396-f832-4500-8faa-8cfeeded1ebb&fname=NorthAtlanticTransp.png"
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/8e3ec4a6-e46d-5f1e-b6a8-7d6b5c540f58.json b/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/8e3ec4a6-e46d-5f1e-b6a8-7d6b5c540f58.json
deleted file mode 100644
index 83099509..00000000
--- a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/8e3ec4a6-e46d-5f1e-b6a8-7d6b5c540f58.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.12770/5a9df55d-0cb7-4354-acd0-221b3d5f02fe",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=oai_dc&identifier=8e3ec4a6-e46d-5f1e-b6a8-7d6b5c540f58",
-    "Rights": [
-        "otherRestrictions"
-    ],
-    "SpatialCoverage": [
-        "93 61.9",
-        "-43 83"
-    ],
-    "fulltext": "5a9df55d-0cb7-4354-acd0-221b3d5f02fe;2018-09-26T15:48:40;Arctic Ocean - Temperature and salinity Historical Data Collection SeaDataCloud V1;SDC_ARC_DATA_TS_V1;dataset;Oceanographic geographical features;Temperature of the water column;Salinity of the water column;ITS-90 water temperature;Water body salinity;Arctic Ocean;oceans;ODV binary collection;SeaDataCloud  Temperature  and Salinity historical data collection for the Arctic Ocean, including revised quality flags after quality control with ODV. The dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/.\n\nFor data access please register at http://www.marine-id.org/.;SeaDataCloud  Temperature  and Salinity historical data collection for the Arctic Ocean, including revised quality flags after quality control with ODV. The dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/.\n\nFor data access please register at http://www.marine-id.org/.;otherRestrictions;eng;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI;ODV binary collection;93 61.9;-43 83;http://dx.doi.org/10.12770/5a9df55d-0cb7-4354-acd0-221b3d5f02fe;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=5a9df55d-0cb7-4354-acd0-221b3d5f02fe&fname=ARCTIC_SDC_V1.png",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "8e3ec4a6-e46d-5f1e-b6a8-7d6b5c540f58",
-    "notes": [
-        "SeaDataCloud  Temperature  and Salinity historical data collection for the Arctic Ocean, including revised quality flags after quality control with ODV. The dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/.\n\nFor data access please register at http://www.marine-id.org/."
-    ],
-    "oai_identifier": [
-        "8e3ec4a6-e46d-5f1e-b6a8-7d6b5c540f58"
-    ],
-    "oai_set": "cams1_ps",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "Arctic Ocean"
-        },
-        {
-            "name": "oceans"
-        }
-    ],
-    "title": [
-        "Arctic Ocean - Temperature and salinity Historical Data Collection SeaDataCloud V1"
-    ],
-    "url": "https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=5a9df55d-0cb7-4354-acd0-221b3d5f02fe&fname=ARCTIC_SDC_V1.png"
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/92b9b5ab-d73b-5cca-83af-b9d9b04d5eb4.json b/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/92b9b5ab-d73b-5cca-83af-b9d9b04d5eb4.json
deleted file mode 100644
index 79e1edd1..00000000
--- a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/92b9b5ab-d73b-5cca-83af-b9d9b04d5eb4.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.12770/1610aa44-0436-4b53-b220-98e10f17a2d4",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=oai_dc&identifier=92b9b5ab-d73b-5cca-83af-b9d9b04d5eb4",
-    "Rights": [
-        "otherRestrictions"
-    ],
-    "SpatialCoverage": [
-        "30 53",
-        "10 66.5"
-    ],
-    "fulltext": "1610aa44-0436-4b53-b220-98e10f17a2d4;2018-07-24T09:47:28;Baltic Sea  - Temperature and salinity observation collection V2;seadatanet-baltic_sea-temperature_salinity_aggregated_public-v2;series;Oceanographic geographical features;Temperature of the water column;Salinity of the water column;ITS-90 water temperature;Water body salinity;Baltic Sea;Bay of Bothnia;Central Baltic Sea;Gulf of Bothnia;Gulf of Finland;Kattegat;Lillebaelt;Skagerrak;Storebaelt;oceans;SeaDataNet Temperature and Salinity historical data collection for the Baltic Sea contains all open access temperature and salinity in situ data retrieved from SeaDataNet infrastructure at the end of 2014.\nData have been quality checked using ODV software. Quality Flags of anomalous data have been revised using basic QC procedures.\nThe dataset is available on authenticated FTP as zip files. You can get access codes from: http://www.marine-id.org. The dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/\n\nFor data access please register at http://www.marine-id.org;SeaDataNet Temperature and Salinity historical data collection for the Baltic Sea contains all open access temperature and salinity in situ data retrieved from SeaDataNet infrastructure at the end of 2014.\nData have been quality checked using ODV software. Quality Flags of anomalous data have been revised using basic QC procedures.\nThe dataset is available on authenticated FTP as zip files. You can get access codes from: http://www.marine-id.org. The dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/\n\nFor data access please register at http://www.marine-id.org;otherRestrictions;eng;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI;30 53;10 66.5;http://dx.doi.org/10.12770/1610aa44-0436-4b53-b220-98e10f17a2d4;ftp://vftp2.ifremer.fr/public/seadatanet-baltic_sea-temperaturesalinity_aggregated/SDN_2015-09_TS_BalticSea_QC_done_v2.zip;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_BalticSea_QC_done_v2;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_BalticSea_QC_done_v2;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_BalticSea_QC_done_v2;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_BalticSea_QC_done_v2;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=1610aa44-0436-4b53-b220-98e10f17a2d4&fname=map2.png",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "92b9b5ab-d73b-5cca-83af-b9d9b04d5eb4",
-    "notes": [
-        "SeaDataNet Temperature and Salinity historical data collection for the Baltic Sea contains all open access temperature and salinity in situ data retrieved from SeaDataNet infrastructure at the end of 2014.\nData have been quality checked using ODV software. Quality Flags of anomalous data have been revised using basic QC procedures.\nThe dataset is available on authenticated FTP as zip files. You can get access codes from: http://www.marine-id.org. The dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/\n\nFor data access please register at http://www.marine-id.org"
-    ],
-    "oai_identifier": [
-        "92b9b5ab-d73b-5cca-83af-b9d9b04d5eb4"
-    ],
-    "oai_set": "cams1_ps",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "Baltic Sea"
-        },
-        {
-            "name": "Bay Bothnia"
-        },
-        {
-            "name": "Central Baltic Sea"
-        },
-        {
-            "name": "Gulf Bothnia"
-        },
-        {
-            "name": "Gulf Finland"
-        },
-        {
-            "name": "Kattegat"
-        },
-        {
-            "name": "Lillebaelt"
-        }
-    ],
-    "title": [
-        "Baltic Sea  - Temperature and salinity observation collection V2"
-    ],
-    "url": "https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=1610aa44-0436-4b53-b220-98e10f17a2d4&fname=map2.png"
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/a268b804-7fe9-5bc8-9ab7-14a27cf4c435.json b/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/a268b804-7fe9-5bc8-9ab7-14a27cf4c435.json
deleted file mode 100644
index 553382b7..00000000
--- a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/a268b804-7fe9-5bc8-9ab7-14a27cf4c435.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.12770/227e9f7b-ddfc-4004-b0e5-f4785d36d43f",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=oai_dc&identifier=a268b804-7fe9-5bc8-9ab7-14a27cf4c435",
-    "Rights": [
-        "otherRestrictions"
-    ],
-    "SpatialCoverage": [
-        "42 40.5",
-        "27.5 47.5"
-    ],
-    "fulltext": "227e9f7b-ddfc-4004-b0e5-f4785d36d43f;2018-07-24T09:47:49;Black Sea - Temperature and salinity observation collection V2;SEADATANET_Black_Sea-temperature_salinity_aggregated_public-v2;series;Oceanographic geographical features;Temperature of the water column;Salinity of the water column;ITS-90 water temperature;Water body salinity;Black Sea;oceans;The Black Sea historical dataset includes all open access temperature and salinity in situ data from the Black Sea and Sea of Azov for period 1868-2014. The data were retrieved from the SeaDataNet infrastructure in the mid of 2015. Data quality has been analysed and checked using ODV software. Quality Flags of anomalous data have been revised using different QC procedures in conjunction with the visual expert check. Duplicates have been identified and excluded from the dataset.\n\nData providers are:\n- Institute of Fishery Resources (IFR)\n- Institute of Biodiversity and Ecosystem Research, Bulgarian Academy of Sciences\n- Hellenic Centre for Marine Research, Hellenic National Oceanographic Data Centre (HCMR/HNODC)\n- IFREMER / IDM / SISMER - Scientific Information Systems for the SEA\n- SHOM (SERVICE HYDROGRAPHIQUE ET OCEANOGRAPHIQUE DE LA MARINE)\n- All-Russia Research Institute of Hydrometeorological Information - World Data Centre (RIHMI-WDC) National Oceanographic Data Centre (NODC)\n- P.P.Shirshov Institute of Oceanology, RAS\n- Bulgarian National Oceanographic Data Centre(BGODC), Institute of Oceanology\n- Iv.Javakhishvili Tbilisi State University, Centre of Relations with UNESCO Oceanological Research Centre and GeoDNA (UNESCO)\n- National Institute for Marine Research and Development \"Grigore Antipa\"\n- Marine Hydrophysical Institute\n- Department of Navigation and Hydrography and Oceanography, Turkish Navy\n- Karadeniz Technical University, Faculty of Marine Sciences\n- Sinop University, Fisheries Faculty\n- Istanbul University, Institute of Marine Science and Management\n- Institute of Biology of the Southern Seas\n- Marine branch of Ukrainian Hydrometeorological Institute\n- Scientific - Research Firm \"GAMMA\"\n- National Environmental Agency of the Ministry of Environment Protection and Natural Resources\n\nFor data access, please regsiter at http://www.marine-id.org\n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/;The Black Sea historical dataset includes all open access temperature and salinity in situ data from the Black Sea and Sea of Azov for period 1868-2014. The data were retrieved from the SeaDataNet infrastructure in the mid of 2015. Data quality has been analysed and checked using ODV software. Quality Flags of anomalous data have been revised using different QC procedures in conjunction with the visual expert check. Duplicates have been identified and excluded from the dataset.\n\nData providers are:\n- Institute of Fishery Resources (IFR)\n- Institute of Biodiversity and Ecosystem Research, Bulgarian Academy of Sciences\n- Hellenic Centre for Marine Research, Hellenic National Oceanographic Data Centre (HCMR/HNODC)\n- IFREMER / IDM / SISMER - Scientific Information Systems for the SEA\n- SHOM (SERVICE HYDROGRAPHIQUE ET OCEANOGRAPHIQUE DE LA MARINE)\n- All-Russia Research Institute of Hydrometeorological Information - World Data Centre (RIHMI-WDC) National Oceanographic Data Centre (NODC)\n- P.P.Shirshov Institute of Oceanology, RAS\n- Bulgarian National Oceanographic Data Centre(BGODC), Institute of Oceanology\n- Iv.Javakhishvili Tbilisi State University, Centre of Relations with UNESCO Oceanological Research Centre and GeoDNA (UNESCO)\n- National Institute for Marine Research and Development \"Grigore Antipa\"\n- Marine Hydrophysical Institute\n- Department of Navigation and Hydrography and Oceanography, Turkish Navy\n- Karadeniz Technical University, Faculty of Marine Sciences\n- Sinop University, Fisheries Faculty\n- Istanbul University, Institute of Marine Science and Management\n- Institute of Biology of the Southern Seas\n- Marine branch of Ukrainian Hydrometeorological Institute\n- Scientific - Research Firm \"GAMMA\"\n- National Environmental Agency of the Ministry of Environment Protection and Natural Resources\n\nFor data access, please regsiter at http://www.marine-id.org\n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/;otherRestrictions;eng;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI;42 40.5;27.5 47.5;http://dx.doi.org/10.12770/227e9f7b-ddfc-4004-b0e5-f4785d36d43f;ftp://vftp2.ifremer.fr/public/seadatanet-black_sea-temperaturesalinity_aggregated/SDN_2015-09_TS_BlackSea_QC_done_v2.zip;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_Black_Sea_QC_done_v2;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_Black_Sea_QC_done_v2;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_Black_Sea_QC_done_v2;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_Black_Sea_QC_done_v2;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=227e9f7b-ddfc-4004-b0e5-f4785d36d43f&fname=DefaultView_0.png",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "a268b804-7fe9-5bc8-9ab7-14a27cf4c435",
-    "notes": [
-        "The Black Sea historical dataset includes all open access temperature and salinity in situ data from the Black Sea and Sea of Azov for period 1868-2014. The data were retrieved from the SeaDataNet infrastructure in the mid of 2015. Data quality has been analysed and checked using ODV software. Quality Flags of anomalous data have been revised using different QC procedures in conjunction with the visual expert check. Duplicates have been identified and excluded from the dataset.\n\nData providers are:\n- Institute of Fishery Resources (IFR)\n- Institute of Biodiversity and Ecosystem Research, Bulgarian Academy of Sciences\n- Hellenic Centre for Marine Research, Hellenic National Oceanographic Data Centre (HCMR/HNODC)\n- IFREMER / IDM / SISMER - Scientific Information Systems for the SEA\n- SHOM (SERVICE HYDROGRAPHIQUE ET OCEANOGRAPHIQUE DE LA MARINE)\n- All-Russia Research Institute of Hydrometeorological Information - World Data Centre (RIHMI-WDC) National Oceanographic Data Centre (NODC)\n- P.P.Shirshov Institute of Oceanology, RAS\n- Bulgarian National Oceanographic Data Centre(BGODC), Institute of Oceanology\n- Iv.Javakhishvili Tbilisi State University, Centre of Relations with UNESCO Oceanological Research Centre and GeoDNA (UNESCO)\n- National Institute for Marine Research and Development \"Grigore Antipa\"\n- Marine Hydrophysical Institute\n- Department of Navigation and Hydrography and Oceanography, Turkish Navy\n- Karadeniz Technical University, Faculty of Marine Sciences\n- Sinop University, Fisheries Faculty\n- Istanbul University, Institute of Marine Science and Management\n- Institute of Biology of the Southern Seas\n- Marine branch of Ukrainian Hydrometeorological Institute\n- Scientific - Research Firm \"GAMMA\"\n- National Environmental Agency of the Ministry of Environment Protection and Natural Resources\n\nFor data access, please regsiter at http://www.marine-id.org\n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/"
-    ],
-    "oai_identifier": [
-        "a268b804-7fe9-5bc8-9ab7-14a27cf4c435"
-    ],
-    "oai_set": "cams1_ps",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "Black Sea"
-        },
-        {
-            "name": "oceans"
-        }
-    ],
-    "title": [
-        "Black Sea - Temperature and salinity observation collection V2"
-    ],
-    "url": "https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=227e9f7b-ddfc-4004-b0e5-f4785d36d43f&fname=DefaultView_0.png"
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/a3724d56-b446-523c-beb6-eb0f9df1f8db.json b/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/a3724d56-b446-523c-beb6-eb0f9df1f8db.json
deleted file mode 100644
index 4521088d..00000000
--- a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/a3724d56-b446-523c-beb6-eb0f9df1f8db.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=oai_dc&identifier=a3724d56-b446-523c-beb6-eb0f9df1f8db",
-    "Rights": [
-        "otherRestrictions"
-    ],
-    "SpatialCoverage": [
-        "65 65",
-        "-40 82"
-    ],
-    "fulltext": "7d2ed029-4f81-48b3-92f3-0e50ead8e964;2018-07-24T09:47:31;Arctic Ocean - Temperature and Salinity Climatology V1.1;seadatanet-arctic_ocean-climatology_public;series;Oceanographic geographical features;Temperature of the water column;Salinity of the water column;ITS-90 water temperature;Water body salinity;Arctic Ocean;oceans;Climatology done from the SeaDataNet aggregated dataset v1.1 for the North Arctic Ocean. The version used for the DIVA software is the 4.6.10 (prerelease 4.6.11). The period covers 1900-2013.\n\nFor data access please register at http://www.marine-id.org;Climatology done from the SeaDataNet aggregated dataset v1.1 for the North Arctic Ocean. The version used for the DIVA software is the 4.6.10 (prerelease 4.6.11). The period covers 1900-2013.\n\nFor data access please register at http://www.marine-id.org;otherRestrictions;eng;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI;65 65;-40 82;ftp://ftp2.ifremer.fr/public/seadatanet-arctic_ocean-temperaturesalinity_climatologie/SDN_2015-11_TS_Arctic_Climatology_v1.1.zip;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=7d2ed029-4f81-48b3-92f3-0e50ead8e964&fname=Screenshot%20from%202015-11-30%2017:44:33.png",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "a3724d56-b446-523c-beb6-eb0f9df1f8db",
-    "notes": [
-        "Climatology done from the SeaDataNet aggregated dataset v1.1 for the North Arctic Ocean. The version used for the DIVA software is the 4.6.10 (prerelease 4.6.11). The period covers 1900-2013.\n\nFor data access please register at http://www.marine-id.org"
-    ],
-    "oai_identifier": [
-        "a3724d56-b446-523c-beb6-eb0f9df1f8db"
-    ],
-    "oai_set": "cams1_ps",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "Arctic Ocean"
-        },
-        {
-            "name": "oceans"
-        }
-    ],
-    "title": [
-        "Arctic Ocean - Temperature and Salinity Climatology V1.1"
-    ],
-    "url": "https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=7d2ed029-4f81-48b3-92f3-0e50ead8e964&fname=Screenshot%20from%202015-11-30%2017:44:33.png"
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/aac8799c-93c8-57bf-a5af-41f14fd1dbd3.json b/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/aac8799c-93c8-57bf-a5af-41f14fd1dbd3.json
deleted file mode 100644
index dccfebcd..00000000
--- a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/aac8799c-93c8-57bf-a5af-41f14fd1dbd3.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.12770/a61129f0-afbc-4bfa-8307-00f37d37d98a",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=oai_dc&identifier=aac8799c-93c8-57bf-a5af-41f14fd1dbd3",
-    "Rights": [
-        "otherRestrictions"
-    ],
-    "SpatialCoverage": [
-        "10 10",
-        "-90 62"
-    ],
-    "fulltext": "a61129f0-afbc-4bfa-8307-00f37d37d98a;2018-07-24T09:47:47;North Atlantic Ocean - Temperature and salinity observation collection V2;seadatanet-north_atlantic_ocean-temperature_salinity_aggregated_public-v2;series;Oceanographic geographical features;Temperature of the water column;Salinity of the water column;ITS-90 water temperature;Water body salinity;Atlantic Ocean;oceans;SeaDataNet Temperature and Salinity historical data collection v2, including revised quality flags after quality control with ODV.\n\nFor data access please register at http://www.marine-id.org;SeaDataNet Temperature and Salinity historical data collection v2, including revised quality flags after quality control with ODV.\n\nFor data access please register at http://www.marine-id.org;otherRestrictions;eng;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI;10 10;-90 62;http://dx.doi.org/10.12770/a61129f0-afbc-4bfa-8307-00f37d37d98a;ftp://vftp2.ifremer.fr/public/seadatanet-north_atlantic_ocean-temperaturesalinity_aggregated/SDN_2015-09_TS_Atlantic_QC_done_v2.zip;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_Atlantic_QC_done_v2;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_Atlantic_QC_done_v2;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_Atlantic_QC_done_v2;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_Atlantic_QC_done_v2;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=a61129f0-afbc-4bfa-8307-00f37d37d98a&fname=North_Atlantic_SDN_v2_QC472_Map_s.png",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "aac8799c-93c8-57bf-a5af-41f14fd1dbd3",
-    "notes": [
-        "SeaDataNet Temperature and Salinity historical data collection v2, including revised quality flags after quality control with ODV.\n\nFor data access please register at http://www.marine-id.org"
-    ],
-    "oai_identifier": [
-        "aac8799c-93c8-57bf-a5af-41f14fd1dbd3"
-    ],
-    "oai_set": "cams1_ps",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "Atlantic Ocean"
-        },
-        {
-            "name": "oceans"
-        }
-    ],
-    "title": [
-        "North Atlantic Ocean - Temperature and salinity observation collection V2"
-    ],
-    "url": "https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=a61129f0-afbc-4bfa-8307-00f37d37d98a&fname=North_Atlantic_SDN_v2_QC472_Map_s.png"
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/ba3150c9-d93b-5e24-8aa6-7f956a8910d0.json b/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/ba3150c9-d93b-5e24-8aa6-7f956a8910d0.json
deleted file mode 100644
index 827dcd59..00000000
--- a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/ba3150c9-d93b-5e24-8aa6-7f956a8910d0.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.12770/8c3bd19b-9687-429c-a232-48b10478581c",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=oai_dc&identifier=ba3150c9-d93b-5e24-8aa6-7f956a8910d0",
-    "Rights": [
-        "otherRestrictions"
-    ],
-    "SpatialCoverage": [
-        "36.625 30.000",
-        "-9.250 46.125"
-    ],
-    "fulltext": "8c3bd19b-9687-429c-a232-48b10478581c;2018-07-24T09:47:42;Mediterranean Sea - Temperature and salinity observation collection V2;seadatanet-med_sea-temperature_salinity_aggregated_public-v2;series;Oceanographic geographical features;Temperature of the water column;Salinity of the water column;ITS-90 water temperature;Water body salinity;Adriatic Sea;Mediterranean Sea;Mediterranean Sea, Eastern Basin;Mediterranean Sea, Western Basin;Ionian Sea;Mediterranean Region;Tyrrhenian Sea;Ligurian Sea;Alboran Sea;Strait of Sicily;Aegean Sea;Sea of Marmara;oceans;SeaDataNet Temperature and Salinity historical data collection for the Mediterranean Sea contains all open access temperature and salinity in situ data retrieved from SeaDataNet infrastructure. The data span between -9.25 and 37 degrees of longitude, thus including an Atlantic box and Marmara Sea. It covers the time period 1900-2015. Data have been quality checked using ODV software. Quality Flags of anomalous data have been revised using basic QC procedures.\n\nFor data access please register at http://www.marine-id.org\n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/;SeaDataNet Temperature and Salinity historical data collection for the Mediterranean Sea contains all open access temperature and salinity in situ data retrieved from SeaDataNet infrastructure. The data span between -9.25 and 37 degrees of longitude, thus including an Atlantic box and Marmara Sea. It covers the time period 1900-2015. Data have been quality checked using ODV software. Quality Flags of anomalous data have been revised using basic QC procedures.\n\nFor data access please register at http://www.marine-id.org\n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/;otherRestrictions;eng;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI;36.625 30.000;-9.250 46.125;http://dx.doi.org/10.12770/8c3bd19b-9687-429c-a232-48b10478581c;ftp://vftp2.ifremer.fr/public/seadatanet-med_sea-temperaturesalinity_aggregated/SDN_2015-09_TS_MedSea_QC_done_v2.zip;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_MedSea_QC_done_v2;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_MedSea_QC_done_v2;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_MedSea_QC_done_v2;http://www.ifremer.fr/oceanotron/WMS/wms?SERVICE=WMS&REQUEST=GetCapabilities&VERSION=1.3.0&DATASET=SDN_2015-09_TS_MedSea_QC_done_v2;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=8c3bd19b-9687-429c-a232-48b10478581c&fname=DefaultView_0.png",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "ba3150c9-d93b-5e24-8aa6-7f956a8910d0",
-    "notes": [
-        "SeaDataNet Temperature and Salinity historical data collection for the Mediterranean Sea contains all open access temperature and salinity in situ data retrieved from SeaDataNet infrastructure. The data span between -9.25 and 37 degrees of longitude, thus including an Atlantic box and Marmara Sea. It covers the time period 1900-2015. Data have been quality checked using ODV software. Quality Flags of anomalous data have been revised using basic QC procedures.\n\nFor data access please register at http://www.marine-id.org\n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/"
-    ],
-    "oai_identifier": [
-        "ba3150c9-d93b-5e24-8aa6-7f956a8910d0"
-    ],
-    "oai_set": "cams1_ps",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "Adriatic Sea"
-        },
-        {
-            "name": "Mediterranean Sea"
-        },
-        {
-            "name": "Mediterranean Sea"
-        },
-        {
-            "name": "Eastern Basin"
-        },
-        {
-            "name": "Mediterranean Sea"
-        },
-        {
-            "name": "Western Basin"
-        },
-        {
-            "name": "Ionian Sea"
-        }
-    ],
-    "title": [
-        "Mediterranean Sea - Temperature and salinity observation collection V2"
-    ],
-    "url": "https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=8c3bd19b-9687-429c-a232-48b10478581c&fname=DefaultView_0.png"
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/baa48a28-7b33-5fd6-978b-c2ec21717280.json b/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/baa48a28-7b33-5fd6-978b-c2ec21717280.json
deleted file mode 100644
index b90b1e1a..00000000
--- a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/baa48a28-7b33-5fd6-978b-c2ec21717280.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=oai_dc&identifier=baa48a28-7b33-5fd6-978b-c2ec21717280",
-    "Rights": [
-        "otherRestrictions"
-    ],
-    "SpatialCoverage": [
-        "42 40.5",
-        "27 47.5"
-    ],
-    "fulltext": "87052ef6-30bd-48e9-ab07-ff5598cdd336;2018-07-24T09:47:48;Black Sea Temperature and Salinity Climatology V1.1;series;Oceanographic geographical features;Temperature of the water column;Salinity of the water column;ITS-90 water temperature;Water body salinity;Black Sea;Sea of Azov;oceans;Monthly temperature and salinity climatology done from the SeaDataNet aggregated dataset v1.1 by DIVA software v4.6.10. The period covers 1900-2013.\n\nFor data access please register at http://www.marine-id.org;Monthly temperature and salinity climatology done from the SeaDataNet aggregated dataset v1.1 by DIVA software v4.6.10. The period covers 1900-2013.\n\nFor data access please register at http://www.marine-id.org;otherRestrictions;eng;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI;42 40.5;27 47.5;ftp://ftp2.ifremer.fr/public/seadatanet-black_sea-temperaturesalinity_climatologie/SDN_2015-11_TS_BlackSea_Climatology_v1.1.zip;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=87052ef6-30bd-48e9-ab07-ff5598cdd336&fname=black_sea_clim.png",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "baa48a28-7b33-5fd6-978b-c2ec21717280",
-    "notes": [
-        "Monthly temperature and salinity climatology done from the SeaDataNet aggregated dataset v1.1 by DIVA software v4.6.10. The period covers 1900-2013.\n\nFor data access please register at http://www.marine-id.org"
-    ],
-    "oai_identifier": [
-        "baa48a28-7b33-5fd6-978b-c2ec21717280"
-    ],
-    "oai_set": "cams1_ps",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "Black Sea"
-        },
-        {
-            "name": "Sea Azov"
-        },
-        {
-            "name": "oceans"
-        }
-    ],
-    "title": [
-        "Black Sea Temperature and Salinity Climatology V1.1"
-    ],
-    "url": "https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=87052ef6-30bd-48e9-ab07-ff5598cdd336&fname=black_sea_clim.png"
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/c66a1336-d7e1-5401-8748-7f3eb020e2a0.json b/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/c66a1336-d7e1-5401-8748-7f3eb020e2a0.json
deleted file mode 100644
index 98903974..00000000
--- a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/c66a1336-d7e1-5401-8748-7f3eb020e2a0.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.12770/117f66f9-22fc-4609-9be8-b58f9dd6d2b9",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=oai_dc&identifier=c66a1336-d7e1-5401-8748-7f3eb020e2a0",
-    "Rights": [
-        "otherRestrictions"
-    ],
-    "SpatialCoverage": [
-        "42 40.5",
-        "27.5 47.5"
-    ],
-    "fulltext": "117f66f9-22fc-4609-9be8-b58f9dd6d2b9;2018-07-24T09:47:24;Black Sea - Temperature and salinity observation collection V1.1;seadatanet-black_sea-temperature_salinity_aggregated_public-v1_1;series;Oceanographic geographical features;Temperature of the water column;Salinity of the water column;ITS-90 water temperature;Water body salinity;Black Sea;Sea of Azov;oceans;The Black Sea historical dataset includes all open access temperature and salinity in situ data from the Black Sea and Sea of Azov for period 1868-2013. The data were retrieved from the SeaDataNet infrastructure at the beginning of 2014. Data quality has been analysed and checked using ODV software. Quality Flags of anomalous data have been revised using different QC procedures in conjunction with the visual expert check. Duplicates have been identified and excluded from the dataset.\n\nData Providers:\n- Institute of Fishery Resources (IFR)\n- Institute of Biodiversity and Ecosystem Research, Bulgarian Academy of Sciences\n- IFREMER / IDM / SISMER - Scientific Information Systems for the SEA\n- SHOM (SERVICE HYDROGRAPHIQUE ET OCEANOGRAPHIQUE DE LA MARINE)\n- All-Russia Research Institute of Hydrometeorological Information - World Data Centre (RIHMI-WDC) National Oceanographic Data Centre (NODC)\n- P.P.Shirshov Institute of Oceanology, RAS\n- Southern Scientific Research Institute of Marine Fisheries and Oceanography\n- Bulgarian National Oceanographic Data Centre(BGODC), Institute of Oceanology\n- Iv.Javakhishvili Tbilisi State University, Centre of Relations with UNESCO Oceanological Research Centre and GeoDNA (UNESCO)\n- Institute of Marine Sciences, Middle East Technical University\n- National Institute for Marine Research and Development \"Grigore Antipa\"\n- Marine Hydrophysical Institute\n- Department of Navigation and Hydrography and Oceanography, Turkish Navy\n- Karadeniz Technical University, Faculty of Marine Sciences\n- Sinop University, Fisheries Faculty\n- Institute of Biology of the Southern Seas\n- Marine branch of Ukrainian Hydrometeorological Institute\n- Ukrainian scientific center of Ecology of Sea (UkrSCES)\n- Scientific - Research Firm \"GAMMA\"\n- Georgian Institute of Hydrometeorology of Georgian Technical University (GIH)\n- Georgian Institute of Water Management of Georgian Technical University (GWMI)\n- Ankara University\n- Danube Hydro-meteorological Observatory\n\nFor data access please register at http://www.marine-id.org\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/;The Black Sea historical dataset includes all open access temperature and salinity in situ data from the Black Sea and Sea of Azov for period 1868-2013. The data were retrieved from the SeaDataNet infrastructure at the beginning of 2014. Data quality has been analysed and checked using ODV software. Quality Flags of anomalous data have been revised using different QC procedures in conjunction with the visual expert check. Duplicates have been identified and excluded from the dataset.\n\nData Providers:\n- Institute of Fishery Resources (IFR)\n- Institute of Biodiversity and Ecosystem Research, Bulgarian Academy of Sciences\n- IFREMER / IDM / SISMER - Scientific Information Systems for the SEA\n- SHOM (SERVICE HYDROGRAPHIQUE ET OCEANOGRAPHIQUE DE LA MARINE)\n- All-Russia Research Institute of Hydrometeorological Information - World Data Centre (RIHMI-WDC) National Oceanographic Data Centre (NODC)\n- P.P.Shirshov Institute of Oceanology, RAS\n- Southern Scientific Research Institute of Marine Fisheries and Oceanography\n- Bulgarian National Oceanographic Data Centre(BGODC), Institute of Oceanology\n- Iv.Javakhishvili Tbilisi State University, Centre of Relations with UNESCO Oceanological Research Centre and GeoDNA (UNESCO)\n- Institute of Marine Sciences, Middle East Technical University\n- National Institute for Marine Research and Development \"Grigore Antipa\"\n- Marine Hydrophysical Institute\n- Department of Navigation and Hydrography and Oceanography, Turkish Navy\n- Karadeniz Technical University, Faculty of Marine Sciences\n- Sinop University, Fisheries Faculty\n- Institute of Biology of the Southern Seas\n- Marine branch of Ukrainian Hydrometeorological Institute\n- Ukrainian scientific center of Ecology of Sea (UkrSCES)\n- Scientific - Research Firm \"GAMMA\"\n- Georgian Institute of Hydrometeorology of Georgian Technical University (GIH)\n- Georgian Institute of Water Management of Georgian Technical University (GWMI)\n- Ankara University\n- Danube Hydro-meteorological Observatory\n\nFor data access please register at http://www.marine-id.org\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/;otherRestrictions;eng;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI;42 40.5;27.5 47.5;http://dx.doi.org/10.12770/117f66f9-22fc-4609-9be8-b58f9dd6d2b9;ftp://vftp2.ifremer.fr/public/seadatanet-black_sea-temperaturesalinity_aggregated/SDN_2014-03_TS_Black_Sea_QC_done_v1.1.zip;http://www.ifremer.fr/oceanotron/wms?DATASET=SDN_2014-03_TS_Black_Sea_QC_done_v1.1;http://www.ifremer.fr/oceanotron/wms?DATASET=SDN_2014-03_TS_Black_Sea_QC_done_v1.1;http://www.ifremer.fr/oceanotron/wms?DATASET=SDN_2014-03_TS_Black_Sea_QC_done_v1.1;http://www.ifremer.fr/oceanotron/wms?DATASET=SDN_2014-03_TS_Black_Sea_QC_done_v1.1;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=117f66f9-22fc-4609-9be8-b58f9dd6d2b9&fname=BlackSeaTransp.png",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "c66a1336-d7e1-5401-8748-7f3eb020e2a0",
-    "notes": [
-        "The Black Sea historical dataset includes all open access temperature and salinity in situ data from the Black Sea and Sea of Azov for period 1868-2013. The data were retrieved from the SeaDataNet infrastructure at the beginning of 2014. Data quality has been analysed and checked using ODV software. Quality Flags of anomalous data have been revised using different QC procedures in conjunction with the visual expert check. Duplicates have been identified and excluded from the dataset.\n\nData Providers:\n- Institute of Fishery Resources (IFR)\n- Institute of Biodiversity and Ecosystem Research, Bulgarian Academy of Sciences\n- IFREMER / IDM / SISMER - Scientific Information Systems for the SEA\n- SHOM (SERVICE HYDROGRAPHIQUE ET OCEANOGRAPHIQUE DE LA MARINE)\n- All-Russia Research Institute of Hydrometeorological Information - World Data Centre (RIHMI-WDC) National Oceanographic Data Centre (NODC)\n- P.P.Shirshov Institute of Oceanology, RAS\n- Southern Scientific Research Institute of Marine Fisheries and Oceanography\n- Bulgarian National Oceanographic Data Centre(BGODC), Institute of Oceanology\n- Iv.Javakhishvili Tbilisi State University, Centre of Relations with UNESCO Oceanological Research Centre and GeoDNA (UNESCO)\n- Institute of Marine Sciences, Middle East Technical University\n- National Institute for Marine Research and Development \"Grigore Antipa\"\n- Marine Hydrophysical Institute\n- Department of Navigation and Hydrography and Oceanography, Turkish Navy\n- Karadeniz Technical University, Faculty of Marine Sciences\n- Sinop University, Fisheries Faculty\n- Institute of Biology of the Southern Seas\n- Marine branch of Ukrainian Hydrometeorological Institute\n- Ukrainian scientific center of Ecology of Sea (UkrSCES)\n- Scientific - Research Firm \"GAMMA\"\n- Georgian Institute of Hydrometeorology of Georgian Technical University (GIH)\n- Georgian Institute of Water Management of Georgian Technical University (GWMI)\n- Ankara University\n- Danube Hydro-meteorological Observatory\n\nFor data access please register at http://www.marine-id.org\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/"
-    ],
-    "oai_identifier": [
-        "c66a1336-d7e1-5401-8748-7f3eb020e2a0"
-    ],
-    "oai_set": "cams1_ps",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "Black Sea"
-        },
-        {
-            "name": "Sea Azov"
-        },
-        {
-            "name": "oceans"
-        }
-    ],
-    "title": [
-        "Black Sea - Temperature and salinity observation collection V1.1"
-    ],
-    "url": "https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=117f66f9-22fc-4609-9be8-b58f9dd6d2b9&fname=BlackSeaTransp.png"
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/cf2c2497-f281-59f8-a706-20ef5c0c301e.json b/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/cf2c2497-f281-59f8-a706-20ef5c0c301e.json
deleted file mode 100644
index 81f73231..00000000
--- a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/cf2c2497-f281-59f8-a706-20ef5c0c301e.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.12770/afcaabb7-0618-4bf6-9e8c-4cdd3da51fab",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=oai_dc&identifier=cf2c2497-f281-59f8-a706-20ef5c0c301e",
-    "Rights": [
-        "otherRestrictions"
-    ],
-    "SpatialCoverage": [
-        "30 53",
-        "10 66.5"
-    ],
-    "fulltext": "afcaabb7-0618-4bf6-9e8c-4cdd3da51fab;2018-09-26T13:58:36;Baltic Sea - Temperature and salinity Historical Data collection SeaDataCloud V1;SDC_BAL_DATA_TS_V1;dataset;Oceanographic geographical features;Temperature of the water column;Salinity of the water column;Water body salinity;ITS-90 water temperature;Baltic Sea;Bay of Bothnia;Central Baltic Sea;Gulf of Bothnia;Gulf of Finland;Kattegat;Lillebaelt;Storebaelt;Skagerrak;oceans;ODV binary collection;The SeaDataCloud  Temperature  and Salinity historical data collection for the Baltic Sea includes open access in situ data on temperature and salinity of water column. The data were retrieved from the SeaDataNet infrastructure at the end of 2017. Data have been quality controlled according to the SeaDataNet2 project QC procedures in conjunction with the visual expert check using the ODV software. The final number of stations in the collection is 407456, containing around 13.7 million values for both temperature and salinity. The dataset format is ODV binary collection which you can read, analyse and export from with the ODV application provided by the Alfred Wegener institute at http://odv.awi.de/. \n\nFor data access please register at http://www.marine-id.org/.;The SeaDataCloud  Temperature  and Salinity historical data collection for the Baltic Sea includes open access in situ data on temperature and salinity of water column. The data were retrieved from the SeaDataNet infrastructure at the end of 2017. Data have been quality controlled according to the SeaDataNet2 project QC procedures in conjunction with the visual expert check using the ODV software. The final number of stations in the collection is 407456, containing around 13.7 million values for both temperature and salinity. The dataset format is ODV binary collection which you can read, analyse and export from with the ODV application provided by the Alfred Wegener institute at http://odv.awi.de/. \n\nFor data access please register at http://www.marine-id.org/.;otherRestrictions;eng;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI;ODV binary collection;30 53;10 66.5;http://dx.doi.org/10.12770/afcaabb7-0618-4bf6-9e8c-4cdd3da51fab;https://sextant.ifremer.fr/geonetwork/srv/fre//resources.get?uuid=afcaabb7-0618-4bf6-9e8c-4cdd3da51fab&fname=BALTIC_SDC_V1.png",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "cf2c2497-f281-59f8-a706-20ef5c0c301e",
-    "notes": [
-        "The SeaDataCloud  Temperature  and Salinity historical data collection for the Baltic Sea includes open access in situ data on temperature and salinity of water column. The data were retrieved from the SeaDataNet infrastructure at the end of 2017. Data have been quality controlled according to the SeaDataNet2 project QC procedures in conjunction with the visual expert check using the ODV software. The final number of stations in the collection is 407456, containing around 13.7 million values for both temperature and salinity. The dataset format is ODV binary collection which you can read, analyse and export from with the ODV application provided by the Alfred Wegener institute at http://odv.awi.de/. \n\nFor data access please register at http://www.marine-id.org/."
-    ],
-    "oai_identifier": [
-        "cf2c2497-f281-59f8-a706-20ef5c0c301e"
-    ],
-    "oai_set": "cams1_ps",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Baltic Sea"
-        },
-        {
-            "name": "Bay Bothnia"
-        },
-        {
-            "name": "Central Baltic Sea"
-        },
-        {
-            "name": "Gulf Bothnia"
-        },
-        {
-            "name": "Gulf Finland"
-        },
-        {
-            "name": "Kattegat"
-        },
-        {
-            "name": "Lillebaelt"
-        }
-    ],
-    "title": [
-        "Baltic Sea - Temperature and salinity Historical Data collection SeaDataCloud V1"
-    ],
-    "url": "https://sextant.ifremer.fr/geonetwork/srv/fre//resources.get?uuid=afcaabb7-0618-4bf6-9e8c-4cdd3da51fab&fname=BALTIC_SDC_V1.png"
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/d3c6327d-c751-5725-81ad-1129aef86f69.json b/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/d3c6327d-c751-5725-81ad-1129aef86f69.json
deleted file mode 100644
index 9f84087f..00000000
--- a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/d3c6327d-c751-5725-81ad-1129aef86f69.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.12770/d9310aa6-c6b3-4657-a3c9-b0a4dd0f016c",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=oai_dc&identifier=d3c6327d-c751-5725-81ad-1129aef86f69",
-    "Rights": [
-        "otherRestrictions"
-    ],
-    "SpatialCoverage": [
-        "9.96 48.6",
-        "-4.25 62"
-    ],
-    "fulltext": "d9310aa6-c6b3-4657-a3c9-b0a4dd0f016c;2018-09-26T16:27:14;North Sea - Temperature and salinity Historical Data Collection SeaDataCloud V1;SDC_NS_DATA_TS_V1;dataset;Oceanographic geographical features;Salinity of the water column;Temperature of the water column;Water body salinity;ITS-90 water temperature;North Sea;oceans;ODV binary collection;The data collection of the North Sea is divided in two datasets : the discrete collection and the trajectories collection.\n\nThe Discrete SeaDataCloud Temperature and Salinity Historical Data Collection for the North Sea includes open access in situ data on temperature and salinity measured with \u201cdiscrete\u201d instruments (CTD, XBT, discrete water samplers\u2026). The data span between 4\u00b0W and 10\u00b0E in longitude, and from 49\u00b0N to 62\u00b0N in latitude. It covers the time period 1893 \u2013 2017. The data were retrieved from the SeaDataNet infrastructure in November 2017. \nThe \u201cTrajectories\u201d SeaDataCloud Temperature and Salinity Historical Data Collection for the North Sea includes open access in situ data on temperature and salinity measured by continuously recording sensors (e.g. Ferryboxes). The data span between 4\u00b0W and 10\u00b0E in longitude, and from 49\u00b0N to 62\u00b0N in latitude. It covers the time period 1989 \u2013 2017. \n\nThe data were retrieved from the SeaDataNet infrastructure in November 2017. The quality control of the data has been performed with the help of ODV software. Data Quality Flags have been revised following common recommended procedures defined under SeaDataNet 2 project in conjunction with visual expert check. \n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/.\n\nFor data access please register at http://www.marine-id.org/.;The data collection of the North Sea is divided in two datasets : the discrete collection and the trajectories collection.\n\nThe Discrete SeaDataCloud Temperature and Salinity Historical Data Collection for the North Sea includes open access in situ data on temperature and salinity measured with \u201cdiscrete\u201d instruments (CTD, XBT, discrete water samplers\u2026). The data span between 4\u00b0W and 10\u00b0E in longitude, and from 49\u00b0N to 62\u00b0N in latitude. It covers the time period 1893 \u2013 2017. The data were retrieved from the SeaDataNet infrastructure in November 2017. \nThe \u201cTrajectories\u201d SeaDataCloud Temperature and Salinity Historical Data Collection for the North Sea includes open access in situ data on temperature and salinity measured by continuously recording sensors (e.g. Ferryboxes). The data span between 4\u00b0W and 10\u00b0E in longitude, and from 49\u00b0N to 62\u00b0N in latitude. It covers the time period 1989 \u2013 2017. \n\nThe data were retrieved from the SeaDataNet infrastructure in November 2017. The quality control of the data has been performed with the help of ODV software. Data Quality Flags have been revised following common recommended procedures defined under SeaDataNet 2 project in conjunction with visual expert check. \n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/.\n\nFor data access please register at http://www.marine-id.org/.;otherRestrictions;eng;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI;ODV binary collection;9.96 48.6;-4.25 62;http://dx.doi.org/10.12770/d9310aa6-c6b3-4657-a3c9-b0a4dd0f016c;ftp://vftp2.ifremer.fr/public/seadatanet-north_sea-temperaturesalinity_aggregated/SDC_NS_DATA_V1/;https://sextant.ifremer.fr/geonetwork/srv/fre//resources.get?uuid=d9310aa6-c6b3-4657-a3c9-b0a4dd0f016c&fname=NORTH_SEA_SDC_V1.png",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "d3c6327d-c751-5725-81ad-1129aef86f69",
-    "notes": [
-        "The data collection of the North Sea is divided in two datasets : the discrete collection and the trajectories collection.\n\nThe Discrete SeaDataCloud Temperature and Salinity Historical Data Collection for the North Sea includes open access in situ data on temperature and salinity measured with \u201cdiscrete\u201d instruments (CTD, XBT, discrete water samplers\u2026). The data span between 4\u00b0W and 10\u00b0E in longitude, and from 49\u00b0N to 62\u00b0N in latitude. It covers the time period 1893 \u2013 2017. The data were retrieved from the SeaDataNet infrastructure in November 2017. \nThe \u201cTrajectories\u201d SeaDataCloud Temperature and Salinity Historical Data Collection for the North Sea includes open access in situ data on temperature and salinity measured by continuously recording sensors (e.g. Ferryboxes). The data span between 4\u00b0W and 10\u00b0E in longitude, and from 49\u00b0N to 62\u00b0N in latitude. It covers the time period 1989 \u2013 2017. \n\nThe data were retrieved from the SeaDataNet infrastructure in November 2017. The quality control of the data has been performed with the help of ODV software. Data Quality Flags have been revised following common recommended procedures defined under SeaDataNet 2 project in conjunction with visual expert check. \n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/.\n\nFor data access please register at http://www.marine-id.org/."
-    ],
-    "oai_identifier": [
-        "d3c6327d-c751-5725-81ad-1129aef86f69"
-    ],
-    "oai_set": "cams1_ps",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "North Sea"
-        },
-        {
-            "name": "oceans"
-        }
-    ],
-    "title": [
-        "North Sea - Temperature and salinity Historical Data Collection SeaDataCloud V1"
-    ],
-    "url": "https://sextant.ifremer.fr/geonetwork/srv/fre//resources.get?uuid=d9310aa6-c6b3-4657-a3c9-b0a4dd0f016c&fname=NORTH_SEA_SDC_V1.png"
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/e389bf78-f0ef-50e7-bf24-1c9b212fce9f.json b/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/e389bf78-f0ef-50e7-bf24-1c9b212fce9f.json
deleted file mode 100644
index 5e6aa0e2..00000000
--- a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/e389bf78-f0ef-50e7-bf24-1c9b212fce9f.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.12770/0d819acd-846c-4e2c-bef1-451762b70578",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=oai_dc&identifier=e389bf78-f0ef-50e7-bf24-1c9b212fce9f",
-    "Rights": [
-        "otherRestrictions"
-    ],
-    "SpatialCoverage": [
-        "65 65",
-        "-40 82"
-    ],
-    "fulltext": "0d819acd-846c-4e2c-bef1-451762b70578;2018-07-24T09:47:22;Arctic Ocean - Temperature and salinity observation collection V1.1;seadatanet-arctic_sea-temperature_salinity_aggregated_public-v1_1;series;Oceanographic geographical features;Temperature of the water column;Salinity of the water column;ITS-90 water temperature;Water body salinity;Arctic Ocean;oceans;SeaDataNet Temperature and Salinity historical data collection for the North Arctic Ocean, including revised quality flags after quality control with ODV.\n\nFor data access please register at http://www.marine-id.org\n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/;SeaDataNet Temperature and Salinity historical data collection for the North Arctic Ocean, including revised quality flags after quality control with ODV.\n\nFor data access please register at http://www.marine-id.org\n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/;otherRestrictions;eng;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI;65 65;-40 82;http://dx.doi.org/10.12770/0d819acd-846c-4e2c-bef1-451762b70578;ftp://vftp2.ifremer.fr/public/seadatanet-arctic_ocean-temperaturesalinity_aggregated/SDN_2014-03_TS_Arctic_QC_done_v1.1.zip;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_Arctic_QC_done_v1.1;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_Arctic_QC_done_v1.1;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_Arctic_QC_done_v1.1;http://www.ifremer.fr/oceanotron/WMS/wms?DATASET=SDN_2014-03_TS_Arctic_QC_done_v1.1;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=0d819acd-846c-4e2c-bef1-451762b70578&fname=ArcticOceanTransp.png",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "e389bf78-f0ef-50e7-bf24-1c9b212fce9f",
-    "notes": [
-        "SeaDataNet Temperature and Salinity historical data collection for the North Arctic Ocean, including revised quality flags after quality control with ODV.\n\nFor data access please register at http://www.marine-id.org\n\nThe dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/"
-    ],
-    "oai_identifier": [
-        "e389bf78-f0ef-50e7-bf24-1c9b212fce9f"
-    ],
-    "oai_set": "cams1_ps",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "Arctic Ocean"
-        },
-        {
-            "name": "oceans"
-        }
-    ],
-    "title": [
-        "Arctic Ocean - Temperature and salinity observation collection V1.1"
-    ],
-    "url": "https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=0d819acd-846c-4e2c-bef1-451762b70578&fname=ArcticOceanTransp.png"
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/e895449e-017f-5b4f-a45d-7e2a57f0e337.json b/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/e895449e-017f-5b4f-a45d-7e2a57f0e337.json
deleted file mode 100644
index c991ce72..00000000
--- a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/e895449e-017f-5b4f-a45d-7e2a57f0e337.json
+++ /dev/null
@@ -1,78 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.12770/2698a37e-c78b-4f78-be0b-ec536c4cb4b3",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=oai_dc&identifier=e895449e-017f-5b4f-a45d-7e2a57f0e337",
-    "Rights": [
-        "otherRestrictions"
-    ],
-    "SpatialCoverage": [
-        "36.625 30",
-        "-9.25 46.125"
-    ],
-    "fulltext": "2698a37e-c78b-4f78-be0b-ec536c4cb4b3;2018-09-27T08:18:09;Mediterranean Sea - Temperature and salinity Historical Data Collection SeaDataCloud V1;SDC_MED_DATA_TS_V1;dataset;Oceanographic geographical features;Temperature of the water column;Salinity of the water column;Water body salinity;ITS-90 water temperature;Mediterranean Sea, Eastern Basin;Mediterranean Sea;Adriatic Sea;Ionian Sea;Mediterranean Region;Alboran Sea;Ligurian Sea;Strait of Sicily;Sea of Marmara;Tyrrhenian Sea;Aegean Sea;Mediterranean Sea, Western Basin;oceans;ODV binary collection;SDC_MED_DATA_TS_V1 SeaDataCloud Temperature  and Salinity data collection for the Mediterranean Sea contains all open access temperature  and salinity in situ data retrieved from SeaDataNet infrastructure at the end of October 2017. The data span between -9.25 and 37 degrees of longitude, thus including an Atlantic box and the Marmara Sea. It covers the time period 1900-2017. Data have been quality checked using ODV 5.0 software. Quality Flags of anomalous data have been revised using basic QC procedures. The dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/.\n\nFor data access please register at http://www.marine-id.org/.;SDC_MED_DATA_TS_V1 SeaDataCloud Temperature  and Salinity data collection for the Mediterranean Sea contains all open access temperature  and salinity in situ data retrieved from SeaDataNet infrastructure at the end of October 2017. The data span between -9.25 and 37 degrees of longitude, thus including an Atlantic box and the Marmara Sea. It covers the time period 1900-2017. Data have been quality checked using ODV 5.0 software. Quality Flags of anomalous data have been revised using basic QC procedures. The dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/.\n\nFor data access please register at http://www.marine-id.org/.;otherRestrictions;eng;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI;ODV binary collection;36.625 30;-9.25 46.125;http://dx.doi.org/10.12770/2698a37e-c78b-4f78-be0b-ec536c4cb4b3;https://sextant.ifremer.fr/geonetwork/srv/fre//resources.get?uuid=2698a37e-c78b-4f78-be0b-ec536c4cb4b3&fname=MED_SEA_SDC_V1.png",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "e895449e-017f-5b4f-a45d-7e2a57f0e337",
-    "notes": [
-        "SDC_MED_DATA_TS_V1 SeaDataCloud Temperature  and Salinity data collection for the Mediterranean Sea contains all open access temperature  and salinity in situ data retrieved from SeaDataNet infrastructure at the end of October 2017. The data span between -9.25 and 37 degrees of longitude, thus including an Atlantic box and the Marmara Sea. It covers the time period 1900-2017. Data have been quality checked using ODV 5.0 software. Quality Flags of anomalous data have been revised using basic QC procedures. The dataset format is ODV binary collections. You can read, analyse and export from the ODV application provided by Alfred Wegener institute at http://odv.awi.de/.\n\nFor data access please register at http://www.marine-id.org/."
-    ],
-    "oai_identifier": [
-        "e895449e-017f-5b4f-a45d-7e2a57f0e337"
-    ],
-    "oai_set": "cams1_ps",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Mediterranean Sea"
-        },
-        {
-            "name": "Eastern Basin"
-        },
-        {
-            "name": "Mediterranean Sea"
-        },
-        {
-            "name": "Adriatic Sea"
-        },
-        {
-            "name": "Ionian Sea"
-        },
-        {
-            "name": "Mediterranean Region"
-        },
-        {
-            "name": "Alboran Sea"
-        }
-    ],
-    "title": [
-        "Mediterranean Sea - Temperature and salinity Historical Data Collection SeaDataCloud V1"
-    ],
-    "url": "https://sextant.ifremer.fr/geonetwork/srv/fre//resources.get?uuid=2698a37e-c78b-4f78-be0b-ec536c4cb4b3&fname=MED_SEA_SDC_V1.png"
-}
\ No newline at end of file
diff --git a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/ea37a79b-9ffd-53dd-8d9c-893579fa67b4.json b/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/ea37a79b-9ffd-53dd-8d9c-893579fa67b4.json
deleted file mode 100644
index 4860a153..00000000
--- a/oaitestdata/seadatanet-oai_dc/cams1_ps_1/json/ea37a79b-9ffd-53dd-8d9c-893579fa67b4.json
+++ /dev/null
@@ -1,66 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/10.12770/90ae7a06-8b08-4afe-83dd-ca92bc99f5c0",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "http://sextant.ifremer.fr/geonetwork/srv/fre/csw-SEADATANET?verb=GetRecord&metadataPrefix=oai_dc&identifier=ea37a79b-9ffd-53dd-8d9c-893579fa67b4",
-    "Rights": [
-        "otherRestrictions"
-    ],
-    "SpatialCoverage": [
-        "36.625 30.000",
-        "-9.250 46.125"
-    ],
-    "fulltext": "90ae7a06-8b08-4afe-83dd-ca92bc99f5c0;2018-07-24T09:47:39;Mediterranean Sea - Temperature and Salinity Climatology V1.1;SEADATANET_MedSea_climatology_V1.1_public;series;Oceanographic geographical features;Temperature of the water column;Salinity of the water column;ITS-90 water temperature;Water body salinity;Mediterranean Region;Mediterranean Sea;oceans;Mediterranean Sea Climatology computed from the SeaDataNet V1.1 aggregated dataset . The version used for the DIVA software is the 4.6.9. The period covers 1900-2013.\n\n For data access please register at http://www.marine-id.org;Mediterranean Sea Climatology computed from the SeaDataNet V1.1 aggregated dataset . The version used for the DIVA software is the 4.6.9. The period covers 1900-2013.\n\n For data access please register at http://www.marine-id.org;otherRestrictions;eng;The data used as input for this product have been extracted from the SeadataNet Download Service: http://www.seadatanet.org/Data-Access/Common-Data-Index-CDI;36.625 30.000;-9.250 46.125;http://dx.doi.org/10.12770/90ae7a06-8b08-4afe-83dd-ca92bc99f5c0;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms;http://gher-diva.phys.ulg.ac.be/web-vis/Python/web/wms;ftp://ftp2.ifremer.fr/public/seadatanet-med_sea-temperaturesalinity_climatologie/SDN_2015-11_TS_Med_Sea_Climatology_v1.1.zip;https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=90ae7a06-8b08-4afe-83dd-ca92bc99f5c0&fname=med_sea.png",
-    "group": "seadatanet",
-    "groups": [
-        {
-            "name": "seadatanet"
-        }
-    ],
-    "name": "ea37a79b-9ffd-53dd-8d9c-893579fa67b4",
-    "notes": [
-        "Mediterranean Sea Climatology computed from the SeaDataNet V1.1 aggregated dataset . The version used for the DIVA software is the 4.6.9. The period covers 1900-2013.\n\n For data access please register at http://www.marine-id.org"
-    ],
-    "oai_identifier": [
-        "ea37a79b-9ffd-53dd-8d9c-893579fa67b4"
-    ],
-    "oai_set": "cams1_ps",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Oceanographic geographical features"
-        },
-        {
-            "name": "Temperature water column"
-        },
-        {
-            "name": "Salinity water column"
-        },
-        {
-            "name": "ITS- water temperature"
-        },
-        {
-            "name": "Water body salinity"
-        },
-        {
-            "name": "Mediterranean Region"
-        },
-        {
-            "name": "Mediterranean Sea"
-        },
-        {
-            "name": "oceans"
-        }
-    ],
-    "title": [
-        "Mediterranean Sea - Temperature and Salinity Climatology V1.1"
-    ],
-    "url": "https://sextant.ifremer.fr/geonetwork/srv/eng//resources.get?uuid=90ae7a06-8b08-4afe-83dd-ca92bc99f5c0&fname=med_sea.png"
-}
\ No newline at end of file
diff --git a/oaitestdata/seanoe-oai_dc/SET_1/json/00fb0b1a-3860-5818-885b-be2758793c30.json b/oaitestdata/seanoe-oai_dc/SET_1/json/00fb0b1a-3860-5818-885b-be2758793c30.json
deleted file mode 100644
index 3d225304..00000000
--- a/oaitestdata/seanoe-oai_dc/SET_1/json/00fb0b1a-3860-5818-885b-be2758793c30.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "SEANOE"
-    ],
-    "DOI": "http://dx.doi.org/10.17882/58406",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "MetaDataAccess": "http://www.seanoe.org/oai/OAIHandler?verb=GetRecord&metadataPrefix=oai_dc&identifier=00fb0b1a-3860-5818-885b-be2758793c30",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "SEANOE"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "CC-BY"
-    ],
-    "SpatialCoverage": "(25S-54N,62W-13W)",
-    "TempCoverageBegin": 28669377599,
-    "TempCoverageEnd": 28669377599,
-    "TemporalCoverage": " point in time : 0909-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "0909-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "0909-07-01T11:59:59Z",
-    "author": [
-        "Lef\u00e8vre, Nathalie"
-    ],
-    "fulltext": "oai:seanoe.org:58406;2019-01-22;Carbon parameters in the Western tropical Atlantic;Lef\u00e8vre, Nathalie;Carbon parameters;Atlantic ocean;Surface alkalinity and total inorganic carbon (in \u00b5mol/kg) were measured by closed-cell potentiometric titration during PIRATA Brazilian cruises.\n;SEANOE;2018;dataset;DOI:10.17882/58406;http://dx.doi.org/10.17882/58406;North 54.090918, South -24.957261, East -13.183594, West -61.699219;http://www.seanoe.org/data/00472/58406/illustration.gif;-24.957261 -61.699219 54.090918 -13.183594;CC-BY",
-    "group": "seanoe",
-    "groups": [
-        {
-            "name": "seanoe"
-        }
-    ],
-    "name": "00fb0b1a-3860-5818-885b-be2758793c30",
-    "notes": [
-        "Surface alkalinity and total inorganic carbon (in \u00b5mol/kg) were measured by closed-cell potentiometric titration during PIRATA Brazilian cruises.\n"
-    ],
-    "oai_identifier": [
-        "00fb0b1a-3860-5818-885b-be2758793c30"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-61.699219,-24.957261],[-61.699219,54.090918],[-13.183594,54.090918],[-13.183594,-24.957261],[-61.699219,-24.957261]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Carbon parameters"
-        },
-        {
-            "name": "Atlantic ocean"
-        }
-    ],
-    "title": [
-        "Carbon parameters in the Western tropical Atlantic"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/seanoe-oai_dc/SET_1/json/0a476c9c-47ab-51ed-aa7b-8607416cdc0c.json b/oaitestdata/seanoe-oai_dc/SET_1/json/0a476c9c-47ab-51ed-aa7b-8607416cdc0c.json
deleted file mode 100644
index bb10fbdd..00000000
--- a/oaitestdata/seanoe-oai_dc/SET_1/json/0a476c9c-47ab-51ed-aa7b-8607416cdc0c.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "SEANOE"
-    ],
-    "DOI": "http://dx.doi.org/10.17882/59517",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "MetaDataAccess": "http://www.seanoe.org/oai/OAIHandler?verb=GetRecord&metadataPrefix=oai_dc&identifier=0a476c9c-47ab-51ed-aa7b-8607416cdc0c",
-    "PublicationTimestamp": "2019-03-05T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "SEANOE"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "CC-BY-ND"
-    ],
-    "SpatialCoverage": "(41N-57N,6 W-11E)",
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Vaz, Sandrine",
-        "Jac, Cyrielle",
-        "Llapasset, Margaux",
-        "Guillerme, Chlo\u00e9",
-        "Foveau, Aurelie",
-        "Desroy, Nicolas"
-    ],
-    "fulltext": "oai:seanoe.org:59517;2019-05-21;Updated biological traits' scoring and protection status to calculate sensitivity to trawling on mega-epibenthic fauna;Foveau, Aurelie;Jac, Cyrielle;Llapasset, Margaux;Guillerme, Chlo\u00e9;Desroy, Nicolas;Vaz, Sandrine;benthic fauna;disturbance;sensitivity;indicator;biological traits;Particularly suited to the purpose of measuring the sensitivity of benthic communities to trawling, a trawl disturbance indicator (de Juan and Demestre, 2012, de Juan et al. 2009) was proposed based on benthic species biological traits to evaluate the sensibility of mega- and epifaunal community to fishing pressure known to have a physical impact on the seafloor (such as dredging and bottom trawling). The selected biological traits were chosen as they determine vulnerability to trawling: mobility, fragility, position on substrata, average size and feeding mode that can easily be related to the fragility, recoverability and vulnerability ecological concepts. The five categories retained are functional traits that were selected based on the knowledge of the response of benthic taxa to trawling disturbance (de Juan et al., 2009). They reflect respectively the possibility to avoid direct gear impact, to benefit from trawling for feeding, to escape gear, to get caught by the net and to resist trawling/dredging action, each of these characteristics being either advantageous or sensitive to trawling. To expand this approach to that proposed by Certain et al. (2015), the protection status of certain species was also indicated.\nTo enable quantitative analysis, a score was assigned to each category: from low sensitivity (0) to high sensitivity (3). Biological traits of species have been defined, from the BIOTIC database (MARLIN, 2014) and from information given by Garcia (2010), Le Pape et al. (2007) and Brind\u2019Amour et al. (2009). For missing traits, additional information from literature has been considered.\nThe protection status of each taxa was also scored: Atlantic species listed in OSPAR List of Threatened and/or Declining Species and Habitats (https://www.ospar.org/work-areas/bdc/species-habitats/list-of-threatened-declining-species-habitats) and Mediterranean species listed in Vulnerable Marine Ecosystems (FAO, 2018 and Oceana, 2017) were scored 3 and other species were scored 1.\nThe scores of 819\u00a0taxa commonly found in bottom trawl by-catch in the southern North Sea, English Channel and north-western Mediterranean were described.\n;SEANOE;2019-03-05;dataset;DOI:10.17882/59517;http://dx.doi.org/10.17882/59517;North 57.0, South 41.0, East 11.0, West -6.0;http://www.seanoe.org/data/00483/59517/illustration.gif;41.0 -6.0 57.0 11.0;CC-BY-ND",
-    "group": "seanoe",
-    "groups": [
-        {
-            "name": "seanoe"
-        }
-    ],
-    "name": "0a476c9c-47ab-51ed-aa7b-8607416cdc0c",
-    "notes": [
-        "Particularly suited to the purpose of measuring the sensitivity of benthic communities to trawling, a trawl disturbance indicator (de Juan and Demestre, 2012, de Juan et al. 2009) was proposed based on benthic species biological traits to evaluate the sensibility of mega- and epifaunal community to fishing pressure known to have a physical impact on the seafloor (such as dredging and bottom trawling). The selected biological traits were chosen as they determine vulnerability to trawling: mobility, fragility, position on substrata, average size and feeding mode that can easily be related to the fragility, recoverability and vulnerability ecological concepts. The five categories retained are functional traits that were selected based on the knowledge of the response of benthic taxa to trawling disturbance (de Juan et al., 2009). They reflect respectively the possibility to avoid direct gear impact, to benefit from trawling for feeding, to escape gear, to get caught by the net and to resist trawling/dredging action, each of these characteristics being either advantageous or sensitive to trawling. To expand this approach to that proposed by Certain et al. (2015), the protection status of certain species was also indicated.\nTo enable quantitative analysis, a score was assigned to each category: from low sensitivity (0) to high sensitivity (3). Biological traits of species have been defined, from the BIOTIC database (MARLIN, 2014) and from information given by Garcia (2010), Le Pape et al. (2007) and Brind\u2019Amour et al. (2009). For missing traits, additional information from literature has been considered.\nThe protection status of each taxa was also scored: Atlantic species listed in OSPAR List of Threatened and/or Declining Species and Habitats (https://www.ospar.org/work-areas/bdc/species-habitats/list-of-threatened-declining-species-habitats) and Mediterranean species listed in Vulnerable Marine Ecosystems (FAO, 2018 and Oceana, 2017) were scored 3 and other species were scored 1.\nThe scores of 819\u00a0taxa commonly found in bottom trawl by-catch in the southern North Sea, English Channel and north-western Mediterranean were described.\n"
-    ],
-    "oai_identifier": [
-        "0a476c9c-47ab-51ed-aa7b-8607416cdc0c"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-6.0,41.0],[-6.0,57.0],[11.0,57.0],[11.0,41.0],[-6.0,41.0]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "benthic fauna"
-        },
-        {
-            "name": "disturbance"
-        },
-        {
-            "name": "sensitivity"
-        },
-        {
-            "name": "indicator"
-        },
-        {
-            "name": "biological traits"
-        }
-    ],
-    "title": [
-        "Updated biological traits' scoring and protection status to calculate sensitivity to trawling on mega-epibenthic fauna"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/seanoe-oai_dc/SET_1/json/0b4eedc5-537f-5b5e-a37e-d904873b83e2.json b/oaitestdata/seanoe-oai_dc/SET_1/json/0b4eedc5-537f-5b5e-a37e-d904873b83e2.json
deleted file mode 100644
index a8b71591..00000000
--- a/oaitestdata/seanoe-oai_dc/SET_1/json/0b4eedc5-537f-5b5e-a37e-d904873b83e2.json
+++ /dev/null
@@ -1,63 +0,0 @@
-{
-    "Contact": [
-        "SEANOE"
-    ],
-    "DOI": "http://dx.doi.org/10.17882/42980",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "MetaDataAccess": "http://www.seanoe.org/oai/OAIHandler?verb=GetRecord&metadataPrefix=oai_dc&identifier=0b4eedc5-537f-5b5e-a37e-d904873b83e2",
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "SEANOE"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/312463/EU//FIXO3"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "CC-BY"
-    ],
-    "SpatialCoverage": "(37N-37N,32W-32W)",
-    "TempCoverageBegin": 95065185599,
-    "TempCoverageEnd": 95065185599,
-    "TemporalCoverage": " point in time : 3013-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "3013-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "3013-07-01T11:59:59Z",
-    "author": [
-        "Godfroy, Anne",
-        "Legrand, Julien",
-        "Cannat, Mathilde",
-        "Sarradin, Pierre-marie",
-        "Rommevaux, C\u00e9line"
-    ],
-    "fulltext": "oai:seanoe.org:42980;2018-11-29;GROUP:EMSO;Temperature data from CISICS coloniser, EMSO-Azores observatory, 2013-2014;Rommevaux, C\u00e9line;Godfroy, Anne;Legrand, Julien;Cannat, Mathilde;Sarradin, Pierre-marie;This dataset contains the controled temperature data in \u00b0C from the two temperature sensor (Bottom and Top) inside the CISICS colonizer deployed between September 2013 and July 2014 (n=49096) inside the Aisics chimney. (data acquired every 5 min.)\n;SEANOE;2016-03;dataset;DOI:10.17882/42980;http://dx.doi.org/10.17882/42980;info:eu-repo/grantAgreement/EC/FP7/312463/EU//FIXO3;North 37.30134, South 37.2888, East -32.275618, West -32.27982;https://www.seanoe.org/data/00319/42980/illustration.gif;37.2888 -32.27982 37.30134 -32.275618;CC-BY",
-    "group": "seanoe",
-    "groups": [
-        {
-            "name": "seanoe"
-        }
-    ],
-    "name": "0b4eedc5-537f-5b5e-a37e-d904873b83e2",
-    "notes": [
-        "This dataset contains the controled temperature data in \u00b0C from the two temperature sensor (Bottom and Top) inside the CISICS colonizer deployed between September 2013 and July 2014 (n=49096) inside the Aisics chimney. (data acquired every 5 min.)\n"
-    ],
-    "oai_identifier": [
-        "0b4eedc5-537f-5b5e-a37e-d904873b83e2"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-32.27982,37.2888],[-32.27982,37.30134],[-32.275618,37.30134],[-32.275618,37.2888],[-32.27982,37.2888]]]}",
-    "state": "active",
-    "title": [
-        "Temperature data from CISICS coloniser, EMSO-Azores observatory, 2013-2014"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/seanoe-oai_dc/SET_1/json/0ba48e12-747d-5739-9d52-8325f3db3e6e.json b/oaitestdata/seanoe-oai_dc/SET_1/json/0ba48e12-747d-5739-9d52-8325f3db3e6e.json
deleted file mode 100644
index 14537736..00000000
--- a/oaitestdata/seanoe-oai_dc/SET_1/json/0ba48e12-747d-5739-9d52-8325f3db3e6e.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "SEANOE"
-    ],
-    "DOI": "http://dx.doi.org/10.17882/47237",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "MetaDataAccess": "http://www.seanoe.org/oai/OAIHandler?verb=GetRecord&metadataPrefix=oai_dc&identifier=0ba48e12-747d-5739-9d52-8325f3db3e6e",
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "SEANOE"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/312463/EU//FIXO3"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "CC-BY"
-    ],
-    "SpatialCoverage": "(37N-37N,32W-32W)",
-    "TempCoverageBegin": 95065185599,
-    "TempCoverageEnd": 95065185599,
-    "TemporalCoverage": " point in time : 3013-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "3013-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "3013-07-01T11:59:59Z",
-    "author": [
-        "Legrand, Julien",
-        "Sarradin, Pierre-marie",
-        "Cannat, Mathilde"
-    ],
-    "fulltext": "oai:seanoe.org:47237;2017-10-09;GROUP:EMSO;Buoy management unit 2 data from the EMSO-Azores observatory, 2016-2017;Legrand, Julien;Sarradin, Pierre-marie;Cannat, Mathilde;Mid-Atlantic Ridge;EMSO;Lucky Strike;buoy;Time-series;Transmission;MoMAR;BOREL;This dataset contains technical parameters (Voltage in V, internal pressure in mbar, water intrusion detection, tilt in \u00b0) acquired since September 2016 by the buoy management unit 2, which is the Electronic core of BOREL, the transmission buoy of the EMSO-Azores observatory (data acquired every 6 hours).\n;SEANOE;2016;dataset;DOI:10.17882/47237;http://dx.doi.org/10.17882/47237;info:eu-repo/grantAgreement/EC/FP7/312463/EU//FIXO3;North 37.30134, South 37.2888, East -32.275618, West -32.27982;https://www.seanoe.org/data/00361/47237/illustration.gif;37.2888 -32.27982 37.30134 -32.275618;CC-BY",
-    "group": "seanoe",
-    "groups": [
-        {
-            "name": "seanoe"
-        }
-    ],
-    "name": "0ba48e12-747d-5739-9d52-8325f3db3e6e",
-    "notes": [
-        "This dataset contains technical parameters (Voltage in V, internal pressure in mbar, water intrusion detection, tilt in \u00b0) acquired since September 2016 by the buoy management unit 2, which is the Electronic core of BOREL, the transmission buoy of the EMSO-Azores observatory (data acquired every 6 hours).\n"
-    ],
-    "oai_identifier": [
-        "0ba48e12-747d-5739-9d52-8325f3db3e6e"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-32.27982,37.2888],[-32.27982,37.30134],[-32.275618,37.30134],[-32.275618,37.2888],[-32.27982,37.2888]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Mid-Atlantic Ridge"
-        },
-        {
-            "name": "EMSO"
-        },
-        {
-            "name": "Lucky Strike"
-        },
-        {
-            "name": "buoy"
-        },
-        {
-            "name": "Time-series"
-        },
-        {
-            "name": "Transmission"
-        },
-        {
-            "name": "MoMAR"
-        },
-        {
-            "name": "BOREL"
-        }
-    ],
-    "title": [
-        "Buoy management unit 2 data from the EMSO-Azores observatory, 2016-2017"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/seanoe-oai_dc/SET_1/json/0bc124fb-6ffa-5c49-8b13-a62924972be0.json b/oaitestdata/seanoe-oai_dc/SET_1/json/0bc124fb-6ffa-5c49-8b13-a62924972be0.json
deleted file mode 100644
index 002a886f..00000000
--- a/oaitestdata/seanoe-oai_dc/SET_1/json/0bc124fb-6ffa-5c49-8b13-a62924972be0.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "SEANOE"
-    ],
-    "DOI": "http://dx.doi.org/10.17882/57249",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "MetaDataAccess": "http://www.seanoe.org/oai/OAIHandler?verb=GetRecord&metadataPrefix=oai_dc&identifier=0bc124fb-6ffa-5c49-8b13-a62924972be0",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "SEANOE"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "CC-BY-NC-SA"
-    ],
-    "SpatialCoverage": "(43N-43N,5 E-5 E)",
-    "TempCoverageBegin": 92414433599,
-    "TempCoverageEnd": 92414433599,
-    "TemporalCoverage": " point in time : 2929-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2929-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2929-07-01T11:59:59Z",
-    "author": [
-        "Lebreton, Benoit",
-        "Guillou, Ga\u00ebl",
-        "Belloni, Bruno",
-        "Harmelin-vivien, Mireille",
-        "Bouchoucha, Marc",
-        "Sartoretto, Stephane",
-        "Ruitton, Sandrine",
-        "Cresson, Pierre"
-    ],
-    "fulltext": "oai:seanoe.org:57249;2018-11-09;Food web structure of a mediterranean coralligenous ecosystem;Belloni, Bruno;Sartoretto, Stephane;Cresson, Pierre;Bouchoucha, Marc;Guillou, Ga\u00ebl;Lebreton, Benoit;Ruitton, Sandrine;Harmelin-vivien, Mireille;food webs;coralligenous ecosystem;stable isotopes;carbon;nitrogen;This dataset gather\u00a0isotope composition\u00a0measured on organisms collected in Cap Caveau (Marseille, France) by SCUBA diving\u00a0between 30 and 40 m depth from October to December 2015. A total of 78 compartments were analysed (76 taxa, POM and SOM). For each compartment or taxon, mean \u03b413C and \u03b415N values were calculated from 3 to 6 replicates.\u00a0Isotope compositions are expressed in parts per thousand (\u2030) according to the equation: \u03b4X = [(Rsample/Rstandard) \u2013 1] x 10^3, where X is 13C or 15N and R is the isotope ratio 13C/12C or 15N/14N, respectively\n;SEANOE;2018;dataset;DOI:10.17882/57249;http://dx.doi.org/10.17882/57249;North 43.292957, South 43.242959, East 5.342102, West 5.259705;http://www.seanoe.org/data/00461/57249/illustration.gif;43.242959 5.259705 43.292957 5.342102;CC-BY-NC-SA",
-    "group": "seanoe",
-    "groups": [
-        {
-            "name": "seanoe"
-        }
-    ],
-    "name": "0bc124fb-6ffa-5c49-8b13-a62924972be0",
-    "notes": [
-        "This dataset gather\u00a0isotope composition\u00a0measured on organisms collected in Cap Caveau (Marseille, France) by SCUBA diving\u00a0between 30 and 40 m depth from October to December 2015. A total of 78 compartments were analysed (76 taxa, POM and SOM). For each compartment or taxon, mean \u03b413C and \u03b415N values were calculated from 3 to 6 replicates.\u00a0Isotope compositions are expressed in parts per thousand (\u2030) according to the equation: \u03b4X = [(Rsample/Rstandard) \u2013 1] x 10^3, where X is 13C or 15N and R is the isotope ratio 13C/12C or 15N/14N, respectively\n"
-    ],
-    "oai_identifier": [
-        "0bc124fb-6ffa-5c49-8b13-a62924972be0"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[5.259705,43.242959],[5.259705,43.292957],[5.342102,43.292957],[5.342102,43.242959],[5.259705,43.242959]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "food webs"
-        },
-        {
-            "name": "coralligenous ecosystem"
-        },
-        {
-            "name": "stable isotopes"
-        },
-        {
-            "name": "carbon"
-        },
-        {
-            "name": "nitrogen"
-        }
-    ],
-    "title": [
-        "Food web structure of a mediterranean coralligenous ecosystem"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/seanoe-oai_dc/SET_1/json/0c7e3673-15a9-58cc-9b3a-a0bf55f5d9c4.json b/oaitestdata/seanoe-oai_dc/SET_1/json/0c7e3673-15a9-58cc-9b3a-a0bf55f5d9c4.json
deleted file mode 100644
index 6b26482c..00000000
--- a/oaitestdata/seanoe-oai_dc/SET_1/json/0c7e3673-15a9-58cc-9b3a-a0bf55f5d9c4.json
+++ /dev/null
@@ -1,77 +0,0 @@
-{
-    "Contact": [
-        "SEANOE"
-    ],
-    "DOI": "http://dx.doi.org/10.17882/41146",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "MetaDataAccess": "http://www.seanoe.org/oai/OAIHandler?verb=GetRecord&metadataPrefix=oai_dc&identifier=0c7e3673-15a9-58cc-9b3a-a0bf55f5d9c4",
-    "PublicationTimestamp": "2015-12-17T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "SEANOE"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "CC-BY-NC-ND"
-    ],
-    "SpatialCoverage": "(46N-46N,1 W-1 W)",
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Seugnet, Jean-luc",
-        "Chabirand, Jean-michel",
-        "Verite, Celine",
-        "Guesdon, Stephane",
-        "Grizon, James",
-        "Bechemin, Christian"
-    ],
-    "fulltext": "oai:seanoe.org:41146;2017-12-20;SAPERCHAIS-HF data and metadata;Guesdon, Stephane;Bechemin, Christian;Chabirand, Jean-michel;Verite, Celine;Seugnet, Jean-luc;Grizon, James;Pertuis Charentais;Terrigenous and marine inputs;Estuary;Temperature;Salinity;High frequency;The SAPERCHAIS program (Suivi des Apports marins et terrig\u00e8nes dans la mer des PERtuis CHarentAIS) was developed to monitor environmental fluctuations in the Pertuis Charentais Sea by an hydrological watchfulness. Seven stations, representatives of terrigenous or marine inputs, have been followed from 2011 to 2014. From north to south, the main four rivers of the Pertuis, Le Lay, La S\u00e8vre, Charente and Seudre, and the three maritime inputs of each strait, Breton, Antioche and Maumusson. At each station, temperature and salinity were recorded in situ, just below the surface, with a high frequency resolution (10 minutes) . This work was supported by grants from R\u00e9gion Poitou-Charentes and European Regional Development Fund to the Ifremer \"Developpement Durable de la P\u00eache et de la Conchyliculture\" project.\n;SEANOE;2015-12-17;dataset;DOI:10.17882/41146;http://dx.doi.org/10.17882/41146;North 46.31, South 45.78, East -1.05, West -1.38;https://www.seanoe.org/data/00300/41146/illustration.gif;45.78 -1.38 46.31 -1.05;CC-BY-NC-ND",
-    "group": "seanoe",
-    "groups": [
-        {
-            "name": "seanoe"
-        }
-    ],
-    "name": "0c7e3673-15a9-58cc-9b3a-a0bf55f5d9c4",
-    "notes": [
-        "The SAPERCHAIS program (Suivi des Apports marins et terrig\u00e8nes dans la mer des PERtuis CHarentAIS) was developed to monitor environmental fluctuations in the Pertuis Charentais Sea by an hydrological watchfulness. Seven stations, representatives of terrigenous or marine inputs, have been followed from 2011 to 2014. From north to south, the main four rivers of the Pertuis, Le Lay, La S\u00e8vre, Charente and Seudre, and the three maritime inputs of each strait, Breton, Antioche and Maumusson. At each station, temperature and salinity were recorded in situ, just below the surface, with a high frequency resolution (10 minutes) . This work was supported by grants from R\u00e9gion Poitou-Charentes and European Regional Development Fund to the Ifremer \"Developpement Durable de la P\u00eache et de la Conchyliculture\" project.\n"
-    ],
-    "oai_identifier": [
-        "0c7e3673-15a9-58cc-9b3a-a0bf55f5d9c4"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-1.38,45.78],[-1.38,46.31],[-1.05,46.31],[-1.05,45.78],[-1.38,45.78]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Pertuis Charentais"
-        },
-        {
-            "name": "Terrigenous marine inputs"
-        },
-        {
-            "name": "Estuary"
-        },
-        {
-            "name": "Temperature"
-        },
-        {
-            "name": "Salinity"
-        },
-        {
-            "name": "High frequency"
-        }
-    ],
-    "title": [
-        "SAPERCHAIS-HF data and metadata"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/seanoe-oai_dc/SET_1/json/0d05b91e-7713-51ea-96a4-99f727c41e06.json b/oaitestdata/seanoe-oai_dc/SET_1/json/0d05b91e-7713-51ea-96a4-99f727c41e06.json
deleted file mode 100644
index 25d17e12..00000000
--- a/oaitestdata/seanoe-oai_dc/SET_1/json/0d05b91e-7713-51ea-96a4-99f727c41e06.json
+++ /dev/null
@@ -1,102 +0,0 @@
-{
-    "Contact": [
-        "SEANOE"
-    ],
-    "DOI": "http://dx.doi.org/10.17882/52149",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "MetaDataAccess": "http://www.seanoe.org/oai/OAIHandler?verb=GetRecord&metadataPrefix=oai_dc&identifier=0d05b91e-7713-51ea-96a4-99f727c41e06",
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "SEANOE"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/312463/EU//FIXO3"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "CC-BY"
-    ],
-    "SpatialCoverage": "(37N-37N,32W-32W)",
-    "TempCoverageBegin": 95065185599,
-    "TempCoverageEnd": 95065185599,
-    "TemporalCoverage": " point in time : 3013-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "3013-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "3013-07-01T11:59:59Z",
-    "author": [
-        "Rodier, Philippe",
-        "Sarrazin, Jozee",
-        "Sarradin, Pierre-marie",
-        "Brulport, Jean-pierre",
-        "Matabos, Marjolaine",
-        "Cannat, Mathilde"
-    ],
-    "fulltext": "oai:seanoe.org:52149;2017-11-22;GROUP:EMSO;Autonomous ibuttons temperature data from the EMSO-Azores observatory, 2015-2016;Matabos, Marjolaine;Brulport, Jean-pierre;Rodier, Philippe;Sarrazin, Jozee;Sarradin, Pierre-marie;Cannat, Mathilde;Mid-Atlantic Ridge;EMSO-A\u00e7ores;Hydrothermal Vents;Lucky Strike;Eiffel Tower;Temperature;TEMPO;Time-series;MoMAR;MoMARSAT2015;Bathymodiolus azoricus assemblage;Environment;This dataset contains temperature data acquired between April 2015 and September 2016 using16 thermocrons i-buttons \u00a9 installed along chains in the field of view of the SMOOVE camera connected the SeaMoN East frame. Data was acquired every 2 hours. The array is not connected to an energy node. They are associated with the SMOOVE camera which is part of the SeaMoN East ecological monitoring node.\n;SEANOE;2017;dataset;DOI:10.17882/52149;http://dx.doi.org/10.17882/52149;info:eu-repo/grantAgreement/EC/FP7/312463/EU//FIXO3;North 37.30134, South 37.2888, East -32.275618, West -32.27982;https://www.seanoe.org/data/00410/52149/illustration.gif;37.2888 -32.27982 37.30134 -32.275618;CC-BY",
-    "group": "seanoe",
-    "groups": [
-        {
-            "name": "seanoe"
-        }
-    ],
-    "name": "0d05b91e-7713-51ea-96a4-99f727c41e06",
-    "notes": [
-        "This dataset contains temperature data acquired between April 2015 and September 2016 using16 thermocrons i-buttons \u00a9 installed along chains in the field of view of the SMOOVE camera connected the SeaMoN East frame. Data was acquired every 2 hours. The array is not connected to an energy node. They are associated with the SMOOVE camera which is part of the SeaMoN East ecological monitoring node.\n"
-    ],
-    "oai_identifier": [
-        "0d05b91e-7713-51ea-96a4-99f727c41e06"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-32.27982,37.2888],[-32.27982,37.30134],[-32.275618,37.30134],[-32.275618,37.2888],[-32.27982,37.2888]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Mid-Atlantic Ridge"
-        },
-        {
-            "name": "Mid-Atlantic Ridge"
-        },
-        {
-            "name": "Hydrothermal Vents"
-        },
-        {
-            "name": "Lucky Strike"
-        },
-        {
-            "name": "Eiffel Tower"
-        },
-        {
-            "name": "Temperature"
-        },
-        {
-            "name": "TEMPO"
-        },
-        {
-            "name": "Time-series"
-        },
-        {
-            "name": "MoMAR"
-        },
-        {
-            "name": "MoMARSAT"
-        },
-        {
-            "name": "Bathymodiolus azoricus assemblage"
-        },
-        {
-            "name": "Environment"
-        }
-    ],
-    "title": [
-        "Autonomous ibuttons temperature data from the EMSO-Azores observatory, 2015-2016"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/seanoe-oai_dc/SET_1/json/0d0a6dc7-da79-509c-ae2c-32ee310f51bd.json b/oaitestdata/seanoe-oai_dc/SET_1/json/0d0a6dc7-da79-509c-ae2c-32ee310f51bd.json
deleted file mode 100644
index 9709108f..00000000
--- a/oaitestdata/seanoe-oai_dc/SET_1/json/0d0a6dc7-da79-509c-ae2c-32ee310f51bd.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "SEANOE"
-    ],
-    "DOI": "http://dx.doi.org/10.17882/47157",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "MetaDataAccess": "http://www.seanoe.org/oai/OAIHandler?verb=GetRecord&metadataPrefix=oai_dc&identifier=0d0a6dc7-da79-509c-ae2c-32ee310f51bd",
-    "PublicationTimestamp": "2019-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "SEANOE"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "CC-BY"
-    ],
-    "SpatialCoverage": [
-        "41.97574 1.855243 44.62949 8.139423",
-        "47.47698 -5.800781 49.286306 -2.460937",
-        "43.185804 -2.636719 47.238826 -0.527344",
-        "48.477155 -2.241211 51.086834 2.592773"
-    ],
-    "TemporalCoverage": [
-        "North 44.62949, South 41.97574, East 8.139423, West 1.855243",
-        "North 49.286306, South 47.47698, East -2.460937, West -5.800781",
-        "North 47.238826, South 43.185804, East -0.527344, West -2.636719",
-        "North 51.086834, South 48.477155, East 2.592773, West -2.241211"
-    ],
-    "author": [
-        "Orsoni, Valerie",
-        "Marzin, Anahita",
-        "Lamort, Laure",
-        "Catherine, Martial",
-        "Meteigner, Claire",
-        "Morin, Dimitri",
-        "Piquet, Jean-come",
-        "Boulben, Sylviane",
-        "Derrien, Annick",
-        "Amouroux, Isabelle",
-        "Verin, Francoise",
-        "Marco-miralles, Francoise",
-        "Treguier, Cathy",
-        "Cheve, Julien",
-        "Miossec, Laurence"
-    ],
-    "fulltext": "oai:seanoe.org:47157;2019-03-29;REMI dataset : the French microbiological monitoring program of mollusc harvesting areas;Piquet, Jean-come;Boulben, Sylviane;Cheve, Julien;Derrien, Annick;Lamort, Laure;Marco-miralles, Francoise;Marzin, Anahita;Meteigner, Claire;Morin, Dimitri;Orsoni, Valerie;Treguier, Cathy;Verin, Francoise;Amouroux, Isabelle;Catherine, Martial;Miossec, Laurence;Long-term time series of coliform bacteria concentration (fecal coliform or Escherichia coli) in shellfish in four submarine areas (North Sea/Channel, Britany, Atlantic, Mediterranean).\n;SEANOE;2019-03;dataset;DOI:10.17882/47157;http://dx.doi.org/10.17882/47157;North 44.62949, South 41.97574, East 8.139423, West 1.855243;North 49.286306, South 47.47698, East -2.460937, West -5.800781;North 47.238826, South 43.185804, East -0.527344, West -2.636719;North 51.086834, South 48.477155, East 2.592773, West -2.241211;https://www.seanoe.org/data/00360/47157/illustration.gif;41.97574 1.855243 44.62949 8.139423;47.47698 -5.800781 49.286306 -2.460937;43.185804 -2.636719 47.238826 -0.527344;48.477155 -2.241211 51.086834 2.592773;CC-BY",
-    "group": "seanoe",
-    "groups": [
-        {
-            "name": "seanoe"
-        }
-    ],
-    "name": "0d0a6dc7-da79-509c-ae2c-32ee310f51bd",
-    "notes": [
-        "Long-term time series of coliform bacteria concentration (fecal coliform or Escherichia coli) in shellfish in four submarine areas (North Sea/Channel, Britany, Atlantic, Mediterranean).\n"
-    ],
-    "oai_identifier": [
-        "0d0a6dc7-da79-509c-ae2c-32ee310f51bd"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "title": [
-        "REMI dataset : the French microbiological monitoring program of mollusc harvesting areas"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/seanoe-oai_dc/SET_1/json/0dfb1443-3871-5820-9633-bb5588cce052.json b/oaitestdata/seanoe-oai_dc/SET_1/json/0dfb1443-3871-5820-9633-bb5588cce052.json
deleted file mode 100644
index 191608e1..00000000
--- a/oaitestdata/seanoe-oai_dc/SET_1/json/0dfb1443-3871-5820-9633-bb5588cce052.json
+++ /dev/null
@@ -1,83 +0,0 @@
-{
-    "Contact": [
-        "SEANOE"
-    ],
-    "DOI": "http://dx.doi.org/10.17882/59777",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "MetaDataAccess": "http://www.seanoe.org/oai/OAIHandler?verb=GetRecord&metadataPrefix=oai_dc&identifier=0dfb1443-3871-5820-9633-bb5588cce052",
-    "PublicationTimestamp": "2019-04-11T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "SEANOE"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "CC-BY-NC-ND"
-    ],
-    "SpatialCoverage": "(37N-43N,9 E-16E)",
-    "TempCoverageBegin": 142021943999,
-    "TempCoverageEnd": 142021943999,
-    "TemporalCoverage": " point in time : 4501-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "4501-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "4501-07-01T11:59:59Z",
-    "author": [
-        "Vetrano, Anna",
-        "Ribotti, Alberto",
-        "Magni, Paolo",
-        "Borghini, Mireno",
-        "Chiappini, Catia"
-    ],
-    "fulltext": "oai:seanoe.org:59777;2019-04-11;GROUP:EMSO;ICHNUSSA 2015;Ribotti, Alberto;Magni, Paolo;Vetrano, Anna;Chiappini, Catia;Borghini, Mireno;Mediterranean;Temperature;Salinity;Dissolved Oxygen;Fluorescence;hydrological data;CTD profiles;The sampling plan of the ICHNUSSA2015 proposes the route already covered in previous cruises since 2000 to acquire data for the activities of Cal/Val of oceanographic ecosystem or for the validation of forecasting numerical models at different spatial scales. Then the aim is also to study the inter-annual variability of biogeochemical and physical properties of the water masses in crucial areas for understanding the circulation and exchange between basins, in particular the transport of heat and salt in the western Mediterranean. In particular, we want to study the exchange between western and eastern Mediterranean and the waters recirculating or formed in the Algerian-Proven\u00e7al basin (like the new deep water in the Gulf of Lions) and along the transect Sardinia-Balearic islands. Then we want to monitor characteristics and distribution of the new western Mediterranean deep water and its possible effects on the general circulation of the Mediterranean. The ICHNUSSA2015 is designed to approximately replicate the stations of previous cruises like those named medgoos, MedCO or MedOc and the most recent ICHNUSSA2012 and 2013.\nCTD Casts\nAt every station, pressure (P), salinity (S), potential temperature (\u03b8) dissolved oxygen concentration (DO) and Fluorescence were measured with a CTD-rosette system consisting of a CTD SBE 911 plus, and a General Oceanics rosette with 24 Niskin Bottles (12 liters each). Temperature measurements were performed with a SBE-3/F thermometer, with a resolution of 0.00015 \u00b0C/bit at -1 \u00b0C or 0.00018\u00b0C/bit at 31 \u00b0C, and conductivity measurements were performed with a SBE-4C sensor, with a resolution of 3 x 10-4 S/m. Dissolved oxygen was measured with a SBE-43 sensor (resolution 4.3\u03bcM). The vertical profiles of all parameters were obtained by sampling the signals at 24 Hz, with the CTD/rosette going down at a speed of 1 m/s. The data were processed on board, and the coarse errors were corrected thanks to the sampling and analyzing on board o f oxygen and salinity of the deepest station. The rosette is equipped with a sonar altimeter which intercept the bottom 70-50 meters before getting to it. The altimeter is used just for safety, to avoid the rosette to touch the bottom, and for more precision in measuring depth.\nOxygen and Salinity Determination\nSalinity samples were collected, stored and analyzed with a Guildline Portasal Salinometer, standardized with IPSO standard 34.999 PSu Water and at controlled temperature. Also dissolved oxygen samples were collected and analyzed with the Winkler method,using a computer controlled potentiometric end-point titration procedure. Samples were taken from the Niskins bottle with the recommendedprecautions and following the Winkler procedure.\nThe dataset is provided as an ODV txt file and has been processed in accordance to the SeaDataNet's Data QC rules; for each station (66 station) the file contains the following parameters: DEPTH, PRESS, TEMP, PSAL, DOXY and FLUOZZ.\n;SEANOE;2019-04-11;dataset;DOI:10.17882/59777;http://dx.doi.org/10.17882/59777;North 43.450166, South 37.226833, East 15.5, West 8.8;http://www.seanoe.org/data/00486/59777/illustration.gif;37.226833 8.8 43.450166 15.5;CC-BY-NC-ND",
-    "group": "seanoe",
-    "groups": [
-        {
-            "name": "seanoe"
-        }
-    ],
-    "name": "0dfb1443-3871-5820-9633-bb5588cce052",
-    "notes": [
-        "The sampling plan of the ICHNUSSA2015 proposes the route already covered in previous cruises since 2000 to acquire data for the activities of Cal/Val of oceanographic ecosystem or for the validation of forecasting numerical models at different spatial scales. Then the aim is also to study the inter-annual variability of biogeochemical and physical properties of the water masses in crucial areas for understanding the circulation and exchange between basins, in particular the transport of heat and salt in the western Mediterranean. In particular, we want to study the exchange between western and eastern Mediterranean and the waters recirculating or formed in the Algerian-Proven\u00e7al basin (like the new deep water in the Gulf of Lions) and along the transect Sardinia-Balearic islands. Then we want to monitor characteristics and distribution of the new western Mediterranean deep water and its possible effects on the general circulation of the Mediterranean. The ICHNUSSA2015 is designed to approximately replicate the stations of previous cruises like those named medgoos, MedCO or MedOc and the most recent ICHNUSSA2012 and 2013.\nCTD Casts\nAt every station, pressure (P), salinity (S), potential temperature (\u03b8) dissolved oxygen concentration (DO) and Fluorescence were measured with a CTD-rosette system consisting of a CTD SBE 911 plus, and a General Oceanics rosette with 24 Niskin Bottles (12 liters each). Temperature measurements were performed with a SBE-3/F thermometer, with a resolution of 0.00015 \u00b0C/bit at -1 \u00b0C or 0.00018\u00b0C/bit at 31 \u00b0C, and conductivity measurements were performed with a SBE-4C sensor, with a resolution of 3 x 10-4 S/m. Dissolved oxygen was measured with a SBE-43 sensor (resolution 4.3\u03bcM). The vertical profiles of all parameters were obtained by sampling the signals at 24 Hz, with the CTD/rosette going down at a speed of 1 m/s. The data were processed on board, and the coarse errors were corrected thanks to the sampling and analyzing on board o f oxygen and salinity of the deepest station. The rosette is equipped with a sonar altimeter which intercept the bottom 70-50 meters before getting to it. The altimeter is used just for safety, to avoid the rosette to touch the bottom, and for more precision in measuring depth.\nOxygen and Salinity Determination\nSalinity samples were collected, stored and analyzed with a Guildline Portasal Salinometer, standardized with IPSO standard 34.999 PSu Water and at controlled temperature. Also dissolved oxygen samples were collected and analyzed with the Winkler method,using a computer controlled potentiometric end-point titration procedure. Samples were taken from the Niskins bottle with the recommendedprecautions and following the Winkler procedure.\nThe dataset is provided as an ODV txt file and has been processed in accordance to the SeaDataNet's Data QC rules; for each station (66 station) the file contains the following parameters: DEPTH, PRESS, TEMP, PSAL, DOXY and FLUOZZ.\n"
-    ],
-    "oai_identifier": [
-        "0dfb1443-3871-5820-9633-bb5588cce052"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[8.8,37.226833],[8.8,43.450166],[15.5,43.450166],[15.5,37.226833],[8.8,37.226833]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Mediterranean"
-        },
-        {
-            "name": "Temperature"
-        },
-        {
-            "name": "Salinity"
-        },
-        {
-            "name": "Dissolved Oxygen"
-        },
-        {
-            "name": "Fluorescence"
-        },
-        {
-            "name": "hydrological data"
-        },
-        {
-            "name": "CTD profiles"
-        }
-    ],
-    "title": [
-        "ICHNUSSA 2015"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/seanoe-oai_dc/SET_1/json/0f11c3ac-c68a-5b91-ab3b-ed09dba38f9c.json b/oaitestdata/seanoe-oai_dc/SET_1/json/0f11c3ac-c68a-5b91-ab3b-ed09dba38f9c.json
deleted file mode 100644
index b19bfd76..00000000
--- a/oaitestdata/seanoe-oai_dc/SET_1/json/0f11c3ac-c68a-5b91-ab3b-ed09dba38f9c.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "SEANOE"
-    ],
-    "DOI": "http://dx.doi.org/10.17882/61186",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "MetaDataAccess": "http://www.seanoe.org/oai/OAIHandler?verb=GetRecord&metadataPrefix=oai_dc&identifier=0f11c3ac-c68a-5b91-ab3b-ed09dba38f9c",
-    "PublicationTimestamp": "2019-06-04T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "SEANOE"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "CC-BY-NC"
-    ],
-    "SpatialCoverage": "(62S-54S,48W-72W)",
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Provost, Christine",
-        "Lee, Jae Hak",
-        "Ferrari, Ramiro",
-        "Artana, Camila",
-        "Durand, Isabelle",
-        "Senn\u00e9chael, Nathalie",
-        "Kartavtseff, Annie",
-        "Koenig, Zo\u00e9",
-        "Lanoisell\u00e9, Jacky"
-    ],
-    "fulltext": "oai:seanoe.org:61186;2019-06-06;Drake current-meter mooring velocity data (2006-2008);Provost, Christine;Kartavtseff, Annie;Lee, Jae Hak;Senn\u00e9chael, Nathalie;Lanoisell\u00e9, Jacky;Ferrari, Ramiro;Koenig, Zo\u00e9;Artana, Camila;Durand, Isabelle;Drake Passage;Current meter moorings;Antarctic Circumpolar Current;Ten current meter moorings (M1 through M10) were deployed in the Drake Passage in January 2006 (DRAKE 2006, ANT-XIII/3) from RV Polarstern on her way south from Punta Arenas to Jubany station (King-George Island) and Bernardo O Higgins Station (Antarctic Peninsula). The moorings were placed along ground track #104 of Jason altimetry satellite. Recovery took place in April 2008 (Drake 2008, ANT-XXIV/3) from RV Polarstern on her way from Bellingshausen station (King George Island) to Punta Arenas. Moorings M2 and M8 could not be recovered (flotation issues). This data set is made of the velocity time series from 8 moorings.\n;SEANOE;2019-06-04;dataset;DOI:10.17882/61186;http://dx.doi.org/10.17882/61186;North -54.0, South -62.0, East -72.0, West -48.0;https://www.seanoe.org/data/00500/61186/illustration.gif;-62.0 -48.0 -54.0 -72.0;CC-BY-NC",
-    "group": "seanoe",
-    "groups": [
-        {
-            "name": "seanoe"
-        }
-    ],
-    "name": "0f11c3ac-c68a-5b91-ab3b-ed09dba38f9c",
-    "notes": [
-        "Ten current meter moorings (M1 through M10) were deployed in the Drake Passage in January 2006 (DRAKE 2006, ANT-XIII/3) from RV Polarstern on her way south from Punta Arenas to Jubany station (King-George Island) and Bernardo O Higgins Station (Antarctic Peninsula). The moorings were placed along ground track #104 of Jason altimetry satellite. Recovery took place in April 2008 (Drake 2008, ANT-XXIV/3) from RV Polarstern on her way from Bellingshausen station (King George Island) to Punta Arenas. Moorings M2 and M8 could not be recovered (flotation issues). This data set is made of the velocity time series from 8 moorings.\n"
-    ],
-    "oai_identifier": [
-        "0f11c3ac-c68a-5b91-ab3b-ed09dba38f9c"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-48.0,-62.0],[-48.0,-54.0],[-72.0,-54.0],[-72.0,-62.0],[-48.0,-62.0]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Drake Passage"
-        },
-        {
-            "name": "Current meter moorings"
-        },
-        {
-            "name": "Antarctic Circumpolar Current"
-        }
-    ],
-    "title": [
-        "Drake current-meter mooring velocity data (2006-2008)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/seanoe-oai_dc/SET_1/json/0fa80f69-7895-574a-96f2-f434438eb931.json b/oaitestdata/seanoe-oai_dc/SET_1/json/0fa80f69-7895-574a-96f2-f434438eb931.json
deleted file mode 100644
index a4666c1a..00000000
--- a/oaitestdata/seanoe-oai_dc/SET_1/json/0fa80f69-7895-574a-96f2-f434438eb931.json
+++ /dev/null
@@ -1,56 +0,0 @@
-{
-    "Contact": [
-        "SEANOE"
-    ],
-    "DOI": "http://dx.doi.org/10.17882/47251",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "MetaDataAccess": "http://www.seanoe.org/oai/OAIHandler?verb=GetRecord&metadataPrefix=oai_dc&identifier=0fa80f69-7895-574a-96f2-f434438eb931",
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "SEANOE"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "CC-BY"
-    ],
-    "SpatialCoverage": "(42N-51N,6 W-8 E)",
-    "TempCoverageBegin": 32045975999,
-    "TempCoverageEnd": 32045975999,
-    "TemporalCoverage": " point in time : 1016-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "1016-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1016-07-01T11:59:59Z",
-    "author": [
-        "REPHYTOX - French Monitoring program for Phycotoxins in marine organisms"
-    ],
-    "fulltext": "oai:seanoe.org:47251;2017-12-07;REPHYTOX dataset. French Monitoring program for Phycotoxins in marine organisms. Data since 1987;REPHYTOX - French Monitoring program for Phycotoxins in marine organisms;REPHYTOX dataset includes long-term time series on phycotoxins in marine bivalve molluscs, since 1987, along the whole French coast. The dataset covers results on lipophilic toxins, PSP toxins, ASP toxins, and palytoxins. REPHYTOX was until 2015 an integral part of the REPHY network. The dataset is available in its entirety.\n;SEANOE;2017;dataset;DOI:10.17882/47251;http://dx.doi.org/10.17882/47251;North 51.10164, South 42.201888, East 7.732407, West -5.583023;https://www.seanoe.org/data/00361/47251/illustration.gif;42.201888 -5.583023 51.10164 7.732407;CC-BY",
-    "group": "seanoe",
-    "groups": [
-        {
-            "name": "seanoe"
-        }
-    ],
-    "name": "0fa80f69-7895-574a-96f2-f434438eb931",
-    "notes": [
-        "REPHYTOX dataset includes long-term time series on phycotoxins in marine bivalve molluscs, since 1987, along the whole French coast. The dataset covers results on lipophilic toxins, PSP toxins, ASP toxins, and palytoxins. REPHYTOX was until 2015 an integral part of the REPHY network. The dataset is available in its entirety.\n"
-    ],
-    "oai_identifier": [
-        "0fa80f69-7895-574a-96f2-f434438eb931"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-5.583023,42.201888],[-5.583023,51.10164],[7.732407,51.10164],[7.732407,42.201888],[-5.583023,42.201888]]]}",
-    "state": "active",
-    "title": [
-        "REPHYTOX dataset. French Monitoring program for Phycotoxins in marine organisms. Data since 1987"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/seanoe-oai_dc/SET_1/json/1a11de6e-43fd-5c09-9b95-ae8242067e0d.json b/oaitestdata/seanoe-oai_dc/SET_1/json/1a11de6e-43fd-5c09-9b95-ae8242067e0d.json
deleted file mode 100644
index 7b77f262..00000000
--- a/oaitestdata/seanoe-oai_dc/SET_1/json/1a11de6e-43fd-5c09-9b95-ae8242067e0d.json
+++ /dev/null
@@ -1,55 +0,0 @@
-{
-    "Contact": [
-        "SEANOE"
-    ],
-    "DOI": "http://dx.doi.org/10.17882/59750",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "MetaDataAccess": "http://www.seanoe.org/oai/OAIHandler?verb=GetRecord&metadataPrefix=oai_dc&identifier=1a11de6e-43fd-5c09-9b95-ae8242067e0d",
-    "PublicationTimestamp": "2019-03-28T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "SEANOE"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "CC-BY-NC"
-    ],
-    "SpatialCoverage": "(40N-42N,26E-30E)",
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Pi\u00e9t\u00e9, Helen",
-        "Ballu, Val\u00e9rie",
-        "Sakic, Pierre",
-        "Royer, Jean-yves"
-    ],
-    "fulltext": "oai:seanoe.org:59750;2019-03-28;Seafloor acoustic ranging data across the North-Anatolian Fault, Marmara Sea, Turkey;Royer, Jean-yves;Pi\u00e9t\u00e9, Helen;Ballu, Val\u00e9rie;Sakic, Pierre;In October 2014, a ranging network of 10 acoustic transponders was installed across an active segment of the North-Anatolian Fault, in the Marmara Sea at a depth of about 800 m, for up to 5 years (Figure 1).\u00a0 This active fault segment is lacking any major seismic activity since the 18th century.\u00a0 The purpose of this acoustic ranging experiment was to determine whether this fault is continuously and aseismically creeping (i.e. slipping) or is locked and thus accumulating stress that could cause a large magnitude earthquake, few ten kilometers away from Istanbul.\nThe acoustic network comprised 4 transponders from the University of Brest, France, and 6 transponders from the Geomar Institute, Germany. The data available through this web site corresponds to the data collected by the 4 French stations only. They include sets of acoustic ranging between pairs of stations (i.e. two-way-travel times), in addition to sound-speed, temperature and pressure measurements at each station. The sampling rate varies with the data type, but is generally hourly (one or several samples every hour). These are the raw, unprocessed data. For instance, distances must be inferred from the two-way-travel times and sound-speeds.\nThe experiment lasted until January 2018.\nData collection:\n\t- In April 2015, the first set of acoustic ranging data, spanning a period of 6 months, was downloaded from the seafloor transponders using a modem from the sea surface (cruise POS484).\n\t- In April 2016, a second set of acoustic ranging data, spanning one more year, was downloaded from the seafloor transponders, but only 3 of the transponders responded (cruise POS497).\n\t- In May 2017, a third set of acoustic ranging data was downloaded from the seafloor transponders, but only 3 of the transponders responded (cruise YUNUS17).\n\t- In January 2018, a last set was downloaded, but only 3 of the transponders responded (cruise YUNUS17). Since the batteries were almost exhausted, two of the French transponders were retrieved from the seafloor (2002 and 2003, for which all the data had already been downloaded from the surface). The last two will be recovered in 2020 (2001 and 2004).\nMore information about the acoustic network can be found in the paper by Sakic et al. (2016; see reference below).\n;SEANOE;2019-03-28;dataset;DOI:10.17882/59750;http://dx.doi.org/10.17882/59750;North 41.5, South 40.0, East 30.0, West 26.5;https://www.seanoe.org/data/00486/59750/illustration.gif;40.0 26.5 41.5 30.0;CC-BY-NC",
-    "group": "seanoe",
-    "groups": [
-        {
-            "name": "seanoe"
-        }
-    ],
-    "name": "1a11de6e-43fd-5c09-9b95-ae8242067e0d",
-    "notes": [
-        "In October 2014, a ranging network of 10 acoustic transponders was installed across an active segment of the North-Anatolian Fault, in the Marmara Sea at a depth of about 800 m, for up to 5 years (Figure 1).\u00a0 This active fault segment is lacking any major seismic activity since the 18th century.\u00a0 The purpose of this acoustic ranging experiment was to determine whether this fault is continuously and aseismically creeping (i.e. slipping) or is locked and thus accumulating stress that could cause a large magnitude earthquake, few ten kilometers away from Istanbul.\nThe acoustic network comprised 4 transponders from the University of Brest, France, and 6 transponders from the Geomar Institute, Germany. The data available through this web site corresponds to the data collected by the 4 French stations only. They include sets of acoustic ranging between pairs of stations (i.e. two-way-travel times), in addition to sound-speed, temperature and pressure measurements at each station. The sampling rate varies with the data type, but is generally hourly (one or several samples every hour). These are the raw, unprocessed data. For instance, distances must be inferred from the two-way-travel times and sound-speeds.\nThe experiment lasted until January 2018.\nData collection:\n\t- In April 2015, the first set of acoustic ranging data, spanning a period of 6 months, was downloaded from the seafloor transponders using a modem from the sea surface (cruise POS484).\n\t- In April 2016, a second set of acoustic ranging data, spanning one more year, was downloaded from the seafloor transponders, but only 3 of the transponders responded (cruise POS497).\n\t- In May 2017, a third set of acoustic ranging data was downloaded from the seafloor transponders, but only 3 of the transponders responded (cruise YUNUS17).\n\t- In January 2018, a last set was downloaded, but only 3 of the transponders responded (cruise YUNUS17). Since the batteries were almost exhausted, two of the French transponders were retrieved from the seafloor (2002 and 2003, for which all the data had already been downloaded from the surface). The last two will be recovered in 2020 (2001 and 2004).\nMore information about the acoustic network can be found in the paper by Sakic et al. (2016; see reference below).\n"
-    ],
-    "oai_identifier": [
-        "1a11de6e-43fd-5c09-9b95-ae8242067e0d"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[26.5,40.0],[26.5,41.5],[30.0,41.5],[30.0,40.0],[26.5,40.0]]]}",
-    "state": "active",
-    "title": [
-        "Seafloor acoustic ranging data across the North-Anatolian Fault, Marmara Sea, Turkey"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/seanoe-oai_dc/SET_1/json/1a939a46-01a2-5cc2-ac90-b27184a4bb10.json b/oaitestdata/seanoe-oai_dc/SET_1/json/1a939a46-01a2-5cc2-ac90-b27184a4bb10.json
deleted file mode 100644
index f4bf862f..00000000
--- a/oaitestdata/seanoe-oai_dc/SET_1/json/1a939a46-01a2-5cc2-ac90-b27184a4bb10.json
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-    "Contact": [
-        "SEANOE"
-    ],
-    "DOI": "http://dx.doi.org/10.17882/47748",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "MetaDataAccess": "http://www.seanoe.org/oai/OAIHandler?verb=GetRecord&metadataPrefix=oai_dc&identifier=1a939a46-01a2-5cc2-ac90-b27184a4bb10",
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "SEANOE"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/312463/EU//FIXO3"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "CC-BY"
-    ],
-    "SpatialCoverage": "(37N-37N,32W-32W)",
-    "TempCoverageBegin": 95065185599,
-    "TempCoverageEnd": 95065185599,
-    "TemporalCoverage": " point in time : 3013-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "3013-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "3013-07-01T11:59:59Z",
-    "author": [
-        "Legrand, Julien",
-        "Sarradin, Pierre-marie",
-        "Cannat, Mathilde"
-    ],
-    "fulltext": "oai:seanoe.org:47748;2019-01-22;GROUP:EMSO;Buoy management unit 1 data from the EMSO-Azores observatory, 2015-2016;Legrand, Julien;Sarradin, Pierre-marie;Cannat, Mathilde;Mid-Atlantic Ridge;EMSO;Lucky Strike;buoy;Time-series;Transmission;MoMAR;BOREL;This dataset contains technical parameters (Voltage in V, internal pressure in mbar, water intrusion detection, tilt in \u00b0) acquired between April 2015 and September 2016\u00a0by the buoy management unit 1, which is the Electronic core of BOREL, the transmission buoy of the EMSO-Azores observatory (data acquired every 6 hours).\n;SEANOE;2016;dataset;DOI:10.17882/47748;http://dx.doi.org/10.17882/47748;info:eu-repo/grantAgreement/EC/FP7/312463/EU//FIXO3;North 37.30134, South 37.2888, East -32.275618, West -32.27982;https://www.seanoe.org/data/00366/47748/illustration.gif;37.2888 -32.27982 37.30134 -32.275618;CC-BY",
-    "group": "seanoe",
-    "groups": [
-        {
-            "name": "seanoe"
-        }
-    ],
-    "name": "1a939a46-01a2-5cc2-ac90-b27184a4bb10",
-    "notes": [
-        "This dataset contains technical parameters (Voltage in V, internal pressure in mbar, water intrusion detection, tilt in \u00b0) acquired between April 2015 and September 2016\u00a0by the buoy management unit 1, which is the Electronic core of BOREL, the transmission buoy of the EMSO-Azores observatory (data acquired every 6 hours).\n"
-    ],
-    "oai_identifier": [
-        "1a939a46-01a2-5cc2-ac90-b27184a4bb10"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-32.27982,37.2888],[-32.27982,37.30134],[-32.275618,37.30134],[-32.275618,37.2888],[-32.27982,37.2888]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Mid-Atlantic Ridge"
-        },
-        {
-            "name": "EMSO"
-        },
-        {
-            "name": "Lucky Strike"
-        },
-        {
-            "name": "buoy"
-        },
-        {
-            "name": "Time-series"
-        },
-        {
-            "name": "Transmission"
-        },
-        {
-            "name": "MoMAR"
-        },
-        {
-            "name": "BOREL"
-        }
-    ],
-    "title": [
-        "Buoy management unit 1 data from the EMSO-Azores observatory, 2015-2016"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/seanoe-oai_dc/SET_1/json/1af3b1e0-e7ef-5a85-b619-b7cdc140f3c4.json b/oaitestdata/seanoe-oai_dc/SET_1/json/1af3b1e0-e7ef-5a85-b619-b7cdc140f3c4.json
deleted file mode 100644
index 04df37bb..00000000
--- a/oaitestdata/seanoe-oai_dc/SET_1/json/1af3b1e0-e7ef-5a85-b619-b7cdc140f3c4.json
+++ /dev/null
@@ -1,82 +0,0 @@
-{
-    "Contact": [
-        "SEANOE"
-    ],
-    "DOI": "http://dx.doi.org/10.17882/52943",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "MetaDataAccess": "http://www.seanoe.org/oai/OAIHandler?verb=GetRecord&metadataPrefix=oai_dc&identifier=1af3b1e0-e7ef-5a85-b619-b7cdc140f3c4",
-    "PublicationTimestamp": "2018-01-10T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "SEANOE"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "CC-BY-NC"
-    ],
-    "SpatialCoverage": "(44N-44N,7 E-7 E)",
-    "TempCoverageBegin": 222870830399,
-    "TempCoverageEnd": 222870830399,
-    "TemporalCoverage": " point in time : 7063-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "7063-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "7063-07-01T11:59:59Z",
-    "author": [
-        "De Li\u00e8ge, Guillaume",
-        "Petit, Franck",
-        "Irisson, Jean-olivier",
-        "Faillettaz, Robin"
-    ],
-    "fulltext": "oai:seanoe.org:52943;2018-01-26;RadeICHTHYO : Abundance of settlement-stage fish larvae (ichthyoplankton) in the bay of Villefranche-sur-mer;Irisson, Jean-olivier;Faillettaz, Robin;Petit, Franck;De Li\u00e8ge, Guillaume;fish;larvae;ichthyoplankton;recruitment;settlement;light-trap;CARE;Most coastal fishes display a bipartite life history, whereby adults live on the coast and are quite sedentery but produce larvae that are pelagic for a few days to a few weeks. The outcome of this pelagic episode influences future stocks of adults as well as the connectity among coastal populations.\nWe monitor the supply of larvae to the bay of Villefranche-sur-Mer (43.69\u00b0N,\u00a07.315\u00b0E) by capturing settling larvae using CARE light-traps. Traps are set in the evening and collected the next morning, usually every week (with some variations: more intense effort during some periods and some missing dates due to weather constraints).\nHere we report:\n\t- the date of collection of the traps (`date`)\n\t- the identification of organisms (`family`, `genus`, `species`; when individuals can only be identified to family or genus, the subsequent fields are left blank)\n\t- the number of individuals\u00a0caught (`n`)\n\t- the number of traps set (`sampling_effort`)\n\t- the Catch Per Unit Effort (`cpue`=`n`/`sampling_effort`)\n\t- the location of sampling (`lat` and `lon` of the bay of Villefranche-sur-Mer).\nAll coastal fish species caught are reported so if a species is not reported on a given date, it can be considered absent (even though it is not explicitely set to 0 in the file). Nights over which no coastal fish larvae were caught are reported with empty identification and 0 for `n` and `cpue`.\nThis dataset can be dynamically explored at http://www.obs-vlfr.fr/data/view/fish/rade/.\n;SEANOE;2018-01-10;dataset;DOI:10.17882/52943;http://dx.doi.org/10.17882/52943;North 43.706359, South 43.679549, East 7.330284, West 7.302818;https://www.seanoe.org/data/00418/52943/illustration.gif;43.679549 7.302818 43.706359 7.330284;CC-BY-NC",
-    "group": "seanoe",
-    "groups": [
-        {
-            "name": "seanoe"
-        }
-    ],
-    "name": "1af3b1e0-e7ef-5a85-b619-b7cdc140f3c4",
-    "notes": [
-        "Most coastal fishes display a bipartite life history, whereby adults live on the coast and are quite sedentery but produce larvae that are pelagic for a few days to a few weeks. The outcome of this pelagic episode influences future stocks of adults as well as the connectity among coastal populations.\nWe monitor the supply of larvae to the bay of Villefranche-sur-Mer (43.69\u00b0N,\u00a07.315\u00b0E) by capturing settling larvae using CARE light-traps. Traps are set in the evening and collected the next morning, usually every week (with some variations: more intense effort during some periods and some missing dates due to weather constraints).\nHere we report:\n\t- the date of collection of the traps (`date`)\n\t- the identification of organisms (`family`, `genus`, `species`; when individuals can only be identified to family or genus, the subsequent fields are left blank)\n\t- the number of individuals\u00a0caught (`n`)\n\t- the number of traps set (`sampling_effort`)\n\t- the Catch Per Unit Effort (`cpue`=`n`/`sampling_effort`)\n\t- the location of sampling (`lat` and `lon` of the bay of Villefranche-sur-Mer).\nAll coastal fish species caught are reported so if a species is not reported on a given date, it can be considered absent (even though it is not explicitely set to 0 in the file). Nights over which no coastal fish larvae were caught are reported with empty identification and 0 for `n` and `cpue`.\nThis dataset can be dynamically explored at http://www.obs-vlfr.fr/data/view/fish/rade/.\n"
-    ],
-    "oai_identifier": [
-        "1af3b1e0-e7ef-5a85-b619-b7cdc140f3c4"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[7.302818,43.679549],[7.302818,43.706359],[7.330284,43.706359],[7.330284,43.679549],[7.302818,43.679549]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "fish"
-        },
-        {
-            "name": "larvae"
-        },
-        {
-            "name": "ichthyoplankton"
-        },
-        {
-            "name": "recruitment"
-        },
-        {
-            "name": "settlement"
-        },
-        {
-            "name": "light-trap"
-        },
-        {
-            "name": "CARE"
-        }
-    ],
-    "title": [
-        "RadeICHTHYO : Abundance of settlement-stage fish larvae (ichthyoplankton) in the bay of Villefranche-sur-mer"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/seanoe-oai_dc/SET_1/json/1b97c088-0967-5f6d-84c9-142c5db309f9.json b/oaitestdata/seanoe-oai_dc/SET_1/json/1b97c088-0967-5f6d-84c9-142c5db309f9.json
deleted file mode 100644
index d8a621f1..00000000
--- a/oaitestdata/seanoe-oai_dc/SET_1/json/1b97c088-0967-5f6d-84c9-142c5db309f9.json
+++ /dev/null
@@ -1,84 +0,0 @@
-{
-    "Contact": [
-        "SEANOE"
-    ],
-    "DOI": "http://dx.doi.org/10.17882/41459",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "MetaDataAccess": "http://www.seanoe.org/oai/OAIHandler?verb=GetRecord&metadataPrefix=oai_dc&identifier=1b97c088-0967-5f6d-84c9-142c5db309f9",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "SEANOE"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/312463/EU//FIXO3"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "CC-BY"
-    ],
-    "SpatialCoverage": "(37N-37N,32W-32W)",
-    "TempCoverageBegin": 95065185599,
-    "TempCoverageEnd": 95065185599,
-    "TemporalCoverage": " point in time : 3013-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "3013-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "3013-07-01T11:59:59Z",
-    "author": [
-        "Legrand, Julien",
-        "Sarradin, Pierre-marie",
-        "Cannat, Mathilde"
-    ],
-    "fulltext": "oai:seanoe.org:41459;2017-05-17;GROUP:EMSO;COSTOF, technical data from SeaMoN East, node of the EMSO-Azores observatory, 2011-2012;Legrand, Julien;Sarradin, Pierre-marie;Cannat, Mathilde;Mid-Atlantic Ridge;EMSO;Lucky Strike;Time-series;Geophysical monitoring node;MoMAR;COSTOF;This dataset contains technical parameters (Voltage in V, current in mA, energy in Ah, internal pressure in mbar, water leak detection) acquired between Jannuary 2011 and December 2011 (n=332) by the COSTOF (COmmunication and STOrage Front-end), which is the Electronic core of SeaMoN East, the bottom station of EMSO-Azores dedicated to geophysical observations (data acquired every 6 hours).;SEANOE;2015-10;dataset;DOI:10.17882/41459;http://dx.doi.org/10.17882/41459;info:eu-repo/grantAgreement/EC/FP7/312463/EU//FIXO3;North 37.30134, South 37.2888, East -32.275618, West -32.27982;https://www.seanoe.org/data/00303/41459/illustration.gif;37.2888 -32.27982 37.30134 -32.275618;CC-BY",
-    "group": "seanoe",
-    "groups": [
-        {
-            "name": "seanoe"
-        }
-    ],
-    "name": "1b97c088-0967-5f6d-84c9-142c5db309f9",
-    "notes": [
-        "This dataset contains technical parameters (Voltage in V, current in mA, energy in Ah, internal pressure in mbar, water leak detection) acquired between Jannuary 2011 and December 2011 (n=332) by the COSTOF (COmmunication and STOrage Front-end), which is the Electronic core of SeaMoN East, the bottom station of EMSO-Azores dedicated to geophysical observations (data acquired every 6 hours)."
-    ],
-    "oai_identifier": [
-        "1b97c088-0967-5f6d-84c9-142c5db309f9"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-32.27982,37.2888],[-32.27982,37.30134],[-32.275618,37.30134],[-32.275618,37.2888],[-32.27982,37.2888]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Mid-Atlantic Ridge"
-        },
-        {
-            "name": "EMSO"
-        },
-        {
-            "name": "Lucky Strike"
-        },
-        {
-            "name": "Time-series"
-        },
-        {
-            "name": "Geophysical monitoring node"
-        },
-        {
-            "name": "MoMAR"
-        },
-        {
-            "name": "COSTOF"
-        }
-    ],
-    "title": [
-        "COSTOF, technical data from SeaMoN East, node of the EMSO-Azores observatory, 2011-2012"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/seanoe-oai_dc/SET_1/json/1bfff9c8-6ba6-5473-bf9f-bddbe19910b2.json b/oaitestdata/seanoe-oai_dc/SET_1/json/1bfff9c8-6ba6-5473-bf9f-bddbe19910b2.json
deleted file mode 100644
index 2b99702e..00000000
--- a/oaitestdata/seanoe-oai_dc/SET_1/json/1bfff9c8-6ba6-5473-bf9f-bddbe19910b2.json
+++ /dev/null
@@ -1,50 +0,0 @@
-{
-    "Contact": [
-        "SEANOE"
-    ],
-    "DOI": "http://dx.doi.org/10.17882/45940",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "MetaDataAccess": "http://www.seanoe.org/oai/OAIHandler?verb=GetRecord&metadataPrefix=oai_dc&identifier=1bfff9c8-6ba6-5473-bf9f-bddbe19910b2",
-    "PublicationTimestamp": "2014-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2014"
-    ],
-    "Publisher": [
-        "SEANOE"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "CC-BY"
-    ],
-    "author": [
-        "Girard, Sophie",
-        "Kalaydjian, Regis"
-    ],
-    "fulltext": "oai:seanoe.org:45940;2017-12-08;Sea and river port services and workforce, maritime and inland shipping business data; benchmark on world largest seaports and EU inland waterway traffic;Kalaydjian, Regis;Girard, Sophie;Maritine transport includes seaport services, maritime and inland shipping and river port activities. Most segments are documented as sectors in INSEE's business database. Complementary data on specific workforce, port throughput and the breakdown of the merchant fleet are sourced from transport satellite accounts and databases developed by the ministry in charge of maritime transport. International data on EU and world largest seaports are sourced from Eurostat and Unctad. Inland shipping data on main European waterways are usually published by Eurostat.\n;SEANOE;2014;dataset;DOI:10.17882/45940;http://dx.doi.org/10.17882/45940;https://www.seanoe.org/data/00348/45940/illustration.gif;CC-BY",
-    "group": "seanoe",
-    "groups": [
-        {
-            "name": "seanoe"
-        }
-    ],
-    "name": "1bfff9c8-6ba6-5473-bf9f-bddbe19910b2",
-    "notes": [
-        "Maritine transport includes seaport services, maritime and inland shipping and river port activities. Most segments are documented as sectors in INSEE's business database. Complementary data on specific workforce, port throughput and the breakdown of the merchant fleet are sourced from transport satellite accounts and databases developed by the ministry in charge of maritime transport. International data on EU and world largest seaports are sourced from Eurostat and Unctad. Inland shipping data on main European waterways are usually published by Eurostat.\n"
-    ],
-    "oai_identifier": [
-        "1bfff9c8-6ba6-5473-bf9f-bddbe19910b2"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "title": [
-        "Sea and river port services and workforce, maritime and inland shipping business data; benchmark on world largest seaports and EU inland waterway traffic"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/seanoe-oai_dc/SET_1/json/1cc66e50-1d82-54f8-9c55-5844ca0236a7.json b/oaitestdata/seanoe-oai_dc/SET_1/json/1cc66e50-1d82-54f8-9c55-5844ca0236a7.json
deleted file mode 100644
index 4f34872f..00000000
--- a/oaitestdata/seanoe-oai_dc/SET_1/json/1cc66e50-1d82-54f8-9c55-5844ca0236a7.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "SEANOE"
-    ],
-    "DOI": "http://dx.doi.org/10.17882/59867",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "MetaDataAccess": "http://www.seanoe.org/oai/OAIHandler?verb=GetRecord&metadataPrefix=oai_dc&identifier=1cc66e50-1d82-54f8-9c55-5844ca0236a7",
-    "PublicationTimestamp": "2019-04-03T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "SEANOE"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "CC-BY-NC-SA"
-    ],
-    "SpatialCoverage": "(37N-42N,7 E-10E)",
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Ribotti, Alberto",
-        "Borghini, Mireno",
-        "Di Bitetto, Massimiliano",
-        "Sorgente, Roberto"
-    ],
-    "fulltext": "oai:seanoe.org:59867;2019-04-25;CTD profiles in western Sardinia (2000 - 2004), western Mediterranean;Ribotti, Alberto;Di Bitetto, Massimiliano;Borghini, Mireno;Sorgente, Roberto;Sardinia;water masses;mesoscale activity;hydrological data;western Mediterranean;CTD profiles;Hydrological data have been collected during 7 oceanographic cruises, named medgoos, organized in the Sardinia Sea and in the Sardinia Channel between May 2000 and January 2004 (table 1) by the Italian Consiglio Nazionale delle Ricerche (CNR).\nTab.1\n\nThe 61,30 meters long R/V Urania of CNR was used during all cruises. Data of conductivity, temperature, dissolved oxygen (DO) and Chlorophyll-a fluorescence (Chl-a) were acquired by a SBE911 plus CTD probe (Sea-Bird Inc.) equipped with a 24 Niskin bottle rosette for water column samples collection. The CTD data were quality checked and processed by Seasoft software. Then salinity was checked against the on-board analyses of water samples by a Guildline-Autosal salinometer. The same for DO data checked against Winkler titration analyses. Chl-a data were not calibrated, so they are reported as Relative Fluorescence Units. During cruises from medgoos4 to medgoos7 acquired temperature data were checked at defined depths against inverted thermometers installed in correspondence of the Niskin bottles number 1, 3, 5, 7 of the rosette sampler. Pre-cruise and post-cruise calibrations of the sensors were performed at the SACLANT Center (now NATO-CMRE) of La Spezia (Italy). Redundant sensors were often used for both temperature and salinity measurements, apart during the medgoos1 and medgoos2 cruises.\nThe vessel was positioned using an integrated navigation system consisting of two DGPS antennas managed by Andrews Hydrographics software installed on HP 386, 33 MHz PCs.\nThe data set is provided per cruise as ODV Spreadsheet files in TXT format:\n\t- Cruise name\n\t- Station number\n\t- Type of acquisition (here C)\n\t- Date in mon/day/yr and Time in hh:mm\n\t- Coordinates in Longitude [degrees_east] and Latitude [degrees_north]\n\t- Bot. Depth [m]\n\t- Ship name\n\t- Pressure, Digiquartz [db]\n\t- Conductivity [mS/cm]\n\t- Fluorescence, Seatech\n\t- Temperature [deg C]; IPTS-68 in medgoos1; ITS-68 in medgoos2, 6; ITS-90 in medgoos3, 4, 5, 7\n\t- Oxygen, Beckman/YSI , WS = 3 [ml/l]\n\t- Depth [salt water, m]\n\t- Practical Salinity from Conductivity [PSS-78]\n;SEANOE;2019-04-03;dataset;DOI:10.17882/59867;http://dx.doi.org/10.17882/59867;North 41.5, South 37.0, East 9.5, West 7.0;http://www.seanoe.org/data/00487/59867/illustration.gif;37.0 7.0 41.5 9.5;CC-BY-NC-SA",
-    "group": "seanoe",
-    "groups": [
-        {
-            "name": "seanoe"
-        }
-    ],
-    "name": "1cc66e50-1d82-54f8-9c55-5844ca0236a7",
-    "notes": [
-        "Hydrological data have been collected during 7 oceanographic cruises, named medgoos, organized in the Sardinia Sea and in the Sardinia Channel between May 2000 and January 2004 (table 1) by the Italian Consiglio Nazionale delle Ricerche (CNR).\nTab.1\n\nThe 61,30 meters long R/V Urania of CNR was used during all cruises. Data of conductivity, temperature, dissolved oxygen (DO) and Chlorophyll-a fluorescence (Chl-a) were acquired by a SBE911 plus CTD probe (Sea-Bird Inc.) equipped with a 24 Niskin bottle rosette for water column samples collection. The CTD data were quality checked and processed by Seasoft software. Then salinity was checked against the on-board analyses of water samples by a Guildline-Autosal salinometer. The same for DO data checked against Winkler titration analyses. Chl-a data were not calibrated, so they are reported as Relative Fluorescence Units. During cruises from medgoos4 to medgoos7 acquired temperature data were checked at defined depths against inverted thermometers installed in correspondence of the Niskin bottles number 1, 3, 5, 7 of the rosette sampler. Pre-cruise and post-cruise calibrations of the sensors were performed at the SACLANT Center (now NATO-CMRE) of La Spezia (Italy). Redundant sensors were often used for both temperature and salinity measurements, apart during the medgoos1 and medgoos2 cruises.\nThe vessel was positioned using an integrated navigation system consisting of two DGPS antennas managed by Andrews Hydrographics software installed on HP 386, 33 MHz PCs.\nThe data set is provided per cruise as ODV Spreadsheet files in TXT format:\n\t- Cruise name\n\t- Station number\n\t- Type of acquisition (here C)\n\t- Date in mon/day/yr and Time in hh:mm\n\t- Coordinates in Longitude [degrees_east] and Latitude [degrees_north]\n\t- Bot. Depth [m]\n\t- Ship name\n\t- Pressure, Digiquartz [db]\n\t- Conductivity [mS/cm]\n\t- Fluorescence, Seatech\n\t- Temperature [deg C]; IPTS-68 in medgoos1; ITS-68 in medgoos2, 6; ITS-90 in medgoos3, 4, 5, 7\n\t- Oxygen, Beckman/YSI , WS = 3 [ml/l]\n\t- Depth [salt water, m]\n\t- Practical Salinity from Conductivity [PSS-78]\n"
-    ],
-    "oai_identifier": [
-        "1cc66e50-1d82-54f8-9c55-5844ca0236a7"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[7.0,37.0],[7.0,41.5],[9.5,41.5],[9.5,37.0],[7.0,37.0]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Sardinia"
-        },
-        {
-            "name": "water masses"
-        },
-        {
-            "name": "mesoscale activity"
-        },
-        {
-            "name": "hydrological data"
-        },
-        {
-            "name": "western Mediterranean"
-        },
-        {
-            "name": "CTD profiles"
-        }
-    ],
-    "title": [
-        "CTD profiles in western Sardinia (2000 - 2004), western Mediterranean"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/seanoe-oai_dc/SET_1/json/1d230b6e-9ed0-5334-9aed-ec1bc3eb57eb.json b/oaitestdata/seanoe-oai_dc/SET_1/json/1d230b6e-9ed0-5334-9aed-ec1bc3eb57eb.json
deleted file mode 100644
index c3faa33c..00000000
--- a/oaitestdata/seanoe-oai_dc/SET_1/json/1d230b6e-9ed0-5334-9aed-ec1bc3eb57eb.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "SEANOE"
-    ],
-    "DOI": "http://dx.doi.org/10.17882/39746",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "MetaDataAccess": "http://www.seanoe.org/oai/OAIHandler?verb=GetRecord&metadataPrefix=oai_dc&identifier=1d230b6e-9ed0-5334-9aed-ec1bc3eb57eb",
-    "PublicationTimestamp": "2015-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2015"
-    ],
-    "Publisher": [
-        "SEANOE"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "CC-BY-NC-SA"
-    ],
-    "SpatialCoverage": [
-        "47.485362 -8.648903 47.485365 -8.648895",
-        "46.293976 -5.077749 46.293977 -5.077748",
-        "46.191084 -4.413131 46.191262 -4.412852"
-    ],
-    "TemporalCoverage": [
-        "North 47.485365, South 47.485362, East -8.648895, West -8.648903",
-        "North 46.293977, South 46.293976, East -5.077748, West -5.077749",
-        "North 46.191262, South 46.191084, East -4.412852, West -4.413131"
-    ],
-    "author": [
-        "Trenkel, Verena",
-        "Rochet, Marie-joelle",
-        "Berthele, Olivier",
-        "Le Piver, David",
-        "Lorance, Pascal",
-        "Ferrant, Anthony"
-    ],
-    "fulltext": "oai:seanoe.org:39746;2016-10-04;Observations for Synaphobranchus kaupii from bait experiments carried out in the Bay of Biscay in 2002 using ROV Victor 6000;Trenkel, Verena;Lorance, Pascal;Berthele, Olivier;Ferrant, Anthony;Le Piver, David;Rochet, Marie-joelle;The data come from bait experiments that were carried out at three study sites (Meriadzek Terrace, terrace located between the canyon of Belle \u00cele and the canyon of St Nazaire referred to as St Nazaire Terrace, and Belle \u00cele Canyon) on the continental slope of the Bay of Biscay during the VITAL cruise in late August and early September 2002 using the ROV Victor 6000. A full description of the experiments and results can be found in Trenkel and Lorance (2011). The depth range 1100 \u2013 1500 m was investigated in all sites by perpendicular strip transects starting from the deepest point and moving up slope (see full description in Trenkel et al 2004). Bait experiments were carried out at all three sites at regular intervals (every 12 hours) along the transects. Two types of bait were used, a standardised aquaculture paste and cod fillets (only on St Nazaire Terrace). The paste was made of fish farming food pellets mixed with sea water (480 g per liter). Sardine oil was added (3 cm3 per liter) to increase the smell of the bait. The bait was filled into identical bottles (~4 cm diameter opening, 15.5 cm high). At the beginning of the experiment the ROV opened the bottle, put it onto the ground and retreated a few meters perpendicular to the current to observe fish arrival. After it was judged that no more individuals were going to arrive, the ROV shook the bottle to create a new plume and continued observations. In one experiment the bottle was shaken a second time. Video tapes were analysed in the laboratory after the cruise for Kaup's arrowtooth eel (Synaphobranchus kaupii). For each individual arriving, the time and direction of arrival, the initial behaviour and the reaction to the bait were noted. Initial behaviour was categorised by the position in the water column: near the bottom (<1 body length) or higher up in the water column (>1 body length) and the locomotion type: drifting or moving with current (\u201cwith current\u201d), swimming against current or swimming perpendicular to the current. Reaction to the bait was categorised as not interested, attracted, touching bait bottle or eating bait. When possible the speed of the first individual arriving swimming against the current was estimated. Using the size of the bait bottle as a yard stick the time taken for swimming a certain distance (1 cm on the video screen) was recorded on two occasions and used to calculate the average arrival speed. At the deepest point sampled at each site (1460-1550m), an autonomous lander equipped with a current meter was deployed for three days. Data from these sensors were recorded every minute to every two minutes. A temperature probe was carried by the ROV.\n;SEANOE;2015-11;dataset;DOI:10.17882/39746;http://dx.doi.org/10.17882/39746;North 47.485365, South 47.485362, East -8.648895, West -8.648903;North 46.293977, South 46.293976, East -5.077748, West -5.077749;North 46.191262, South 46.191084, East -4.412852, West -4.413131;https://www.seanoe.org/data/00286/39746/illustration.gif;47.485362 -8.648903 47.485365 -8.648895;46.293976 -5.077749 46.293977 -5.077748;46.191084 -4.413131 46.191262 -4.412852;CC-BY-NC-SA",
-    "group": "seanoe",
-    "groups": [
-        {
-            "name": "seanoe"
-        }
-    ],
-    "name": "1d230b6e-9ed0-5334-9aed-ec1bc3eb57eb",
-    "notes": [
-        "The data come from bait experiments that were carried out at three study sites (Meriadzek Terrace, terrace located between the canyon of Belle \u00cele and the canyon of St Nazaire referred to as St Nazaire Terrace, and Belle \u00cele Canyon) on the continental slope of the Bay of Biscay during the VITAL cruise in late August and early September 2002 using the ROV Victor 6000. A full description of the experiments and results can be found in Trenkel and Lorance (2011). The depth range 1100 \u2013 1500 m was investigated in all sites by perpendicular strip transects starting from the deepest point and moving up slope (see full description in Trenkel et al 2004). Bait experiments were carried out at all three sites at regular intervals (every 12 hours) along the transects. Two types of bait were used, a standardised aquaculture paste and cod fillets (only on St Nazaire Terrace). The paste was made of fish farming food pellets mixed with sea water (480 g per liter). Sardine oil was added (3 cm3 per liter) to increase the smell of the bait. The bait was filled into identical bottles (~4 cm diameter opening, 15.5 cm high). At the beginning of the experiment the ROV opened the bottle, put it onto the ground and retreated a few meters perpendicular to the current to observe fish arrival. After it was judged that no more individuals were going to arrive, the ROV shook the bottle to create a new plume and continued observations. In one experiment the bottle was shaken a second time. Video tapes were analysed in the laboratory after the cruise for Kaup's arrowtooth eel (Synaphobranchus kaupii). For each individual arriving, the time and direction of arrival, the initial behaviour and the reaction to the bait were noted. Initial behaviour was categorised by the position in the water column: near the bottom (<1 body length) or higher up in the water column (>1 body length) and the locomotion type: drifting or moving with current (\u201cwith current\u201d), swimming against current or swimming perpendicular to the current. Reaction to the bait was categorised as not interested, attracted, touching bait bottle or eating bait. When possible the speed of the first individual arriving swimming against the current was estimated. Using the size of the bait bottle as a yard stick the time taken for swimming a certain distance (1 cm on the video screen) was recorded on two occasions and used to calculate the average arrival speed. At the deepest point sampled at each site (1460-1550m), an autonomous lander equipped with a current meter was deployed for three days. Data from these sensors were recorded every minute to every two minutes. A temperature probe was carried by the ROV.\n"
-    ],
-    "oai_identifier": [
-        "1d230b6e-9ed0-5334-9aed-ec1bc3eb57eb"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "title": [
-        "Observations for Synaphobranchus kaupii from bait experiments carried out in the Bay of Biscay in 2002 using ROV Victor 6000"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/seanoe-oai_dc/SET_1/json/1d44582a-9804-5022-b9de-0bac8e14fa4c.json b/oaitestdata/seanoe-oai_dc/SET_1/json/1d44582a-9804-5022-b9de-0bac8e14fa4c.json
deleted file mode 100644
index 361b8523..00000000
--- a/oaitestdata/seanoe-oai_dc/SET_1/json/1d44582a-9804-5022-b9de-0bac8e14fa4c.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "SEANOE"
-    ],
-    "DOI": "http://dx.doi.org/10.17882/50173",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "MetaDataAccess": "http://www.seanoe.org/oai/OAIHandler?verb=GetRecord&metadataPrefix=oai_dc&identifier=1d44582a-9804-5022-b9de-0bac8e14fa4c",
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "SEANOE"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "CC-BY-NC-SA"
-    ],
-    "SpatialCoverage": "(25N-73N,26W-39E)",
-    "TempCoverageBegin": 180048052799,
-    "TempCoverageEnd": 180048052799,
-    "TemporalCoverage": " point in time : 5706-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "5706-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "5706-07-01T11:59:59Z",
-    "author": [
-        "Bianchini, Marco L.",
-        "Ragauskas, Adomas",
-        "Butkauskas, Dalius"
-    ],
-    "fulltext": "oai:seanoe.org:50173;2017-07-07;European eel Anguilla anguilla mtDNA cyt b sequence data;Ragauskas, Adomas;Butkauskas, Dalius;Bianchini, Marco L.;A total of 394 mtDNA cyt b sequences that were used for the intraspecific genetic analysis of the European eel (doi:10.1051/alr/2017021). Newly obtained sequences of different haplotypes and previously determined sequences are deposited in the GenBank under AB021776, AF006714\u2013AF006715, AF165069, AF368238\u2013AF368254, AP007233, D84302, EF427617\u2013EF427618, EU223996\u2013EU223997, EU492326\u2013EU492327, KJ564218\u2013KJ564270 and KT633956\u2013KT633987 accession numbers.\nThe files are created by the\u00a0created for MEGA6 program (http://www.megasoftware.net/older_versions).\u00a0\n;SEANOE;2017-07;dataset;DOI:10.17882/50173;http://dx.doi.org/10.17882/50173;North 72.570602, South 25.372732, East 39.375, West -26.015625;https://www.seanoe.org/data/00390/50173/illustration.gif;25.372732 -26.015625 72.570602 39.375;CC-BY-NC-SA",
-    "group": "seanoe",
-    "groups": [
-        {
-            "name": "seanoe"
-        }
-    ],
-    "name": "1d44582a-9804-5022-b9de-0bac8e14fa4c",
-    "notes": [
-        "A total of 394 mtDNA cyt b sequences that were used for the intraspecific genetic analysis of the European eel (doi:10.1051/alr/2017021). Newly obtained sequences of different haplotypes and previously determined sequences are deposited in the GenBank under AB021776, AF006714\u2013AF006715, AF165069, AF368238\u2013AF368254, AP007233, D84302, EF427617\u2013EF427618, EU223996\u2013EU223997, EU492326\u2013EU492327, KJ564218\u2013KJ564270 and KT633956\u2013KT633987 accession numbers.\nThe files are created by the\u00a0created for MEGA6 program (http://www.megasoftware.net/older_versions).\u00a0\n"
-    ],
-    "oai_identifier": [
-        "1d44582a-9804-5022-b9de-0bac8e14fa4c"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-26.015625,25.372732],[-26.015625,72.570602],[39.375,72.570602],[39.375,25.372732],[-26.015625,25.372732]]]}",
-    "state": "active",
-    "title": [
-        "European eel Anguilla anguilla mtDNA cyt b sequence data"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/seanoe-oai_dc/SET_1/json/1d69f605-c13f-5d28-a414-eba6df988900.json b/oaitestdata/seanoe-oai_dc/SET_1/json/1d69f605-c13f-5d28-a414-eba6df988900.json
deleted file mode 100644
index d74bc337..00000000
--- a/oaitestdata/seanoe-oai_dc/SET_1/json/1d69f605-c13f-5d28-a414-eba6df988900.json
+++ /dev/null
@@ -1,80 +0,0 @@
-{
-    "Contact": [
-        "SEANOE"
-    ],
-    "DOI": "http://dx.doi.org/10.17882/54979",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "MetaDataAccess": "http://www.seanoe.org/oai/OAIHandler?verb=GetRecord&metadataPrefix=oai_dc&identifier=1d69f605-c13f-5d28-a414-eba6df988900",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "SEANOE"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "CC-BY-NC"
-    ],
-    "SpatialCoverage": "(39N-44N,0 W-10E)",
-    "TempCoverageBegin": 253796673599,
-    "TempCoverageEnd": 253796673599,
-    "TemporalCoverage": " point in time : 8043-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "8043-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "8043-07-01T11:59:59Z",
-    "author": [
-        "Garreau, Pierre",
-        "Pairaud, Ivane"
-    ],
-    "fulltext": "oai:seanoe.org:54979;2018-10-24;imedia deployment (EGO glider : campe) (Mediterranean Sea - Western basin);Garreau, Pierre;Pairaud, Ivane;sea water temperature;sea water electrical conductivity;sea water pressure;mole concentration of dissolved molecular oxygen in sea water;temperature of sensor for oxygen in sea water;uncalibrated phase shift reported by oxygen sensor;calibrated phase shift reported by oxygen sensor;uncalibrated red phase shift reported by oxygen sensor;The observations of campe glider on imedia deployment (Mediterranean Sea - Western basin) are distributed in 4 files:\n\t- EGO NetCDF time-series (data, metadata, derived sea water current)\n\t- NetCDF profiles extracted from the above time-series\n\t- Raw data\n\t- JSON metadata used by the decoder\nThe following parameters are provided :\n\t- Practical salinity\n\t- Sea temperature in-situ ITS-90 scale\n\t- Electrical conductivity\n\t- Sea water pressure, equals 0 at sea-level\n;SEANOE;2018-04;dataset;DOI:10.17882/54979;http://dx.doi.org/10.17882/54979;North 43.804358, South 38.772879, East 9.556747, West -0.26503;https://www.seanoe.org/data/00438/54979/illustration.gif;38.772879 -0.26503 43.804358 9.556747;CC-BY-NC",
-    "group": "seanoe",
-    "groups": [
-        {
-            "name": "seanoe"
-        }
-    ],
-    "name": "1d69f605-c13f-5d28-a414-eba6df988900",
-    "notes": [
-        "The observations of campe glider on imedia deployment (Mediterranean Sea - Western basin) are distributed in 4 files:\n\t- EGO NetCDF time-series (data, metadata, derived sea water current)\n\t- NetCDF profiles extracted from the above time-series\n\t- Raw data\n\t- JSON metadata used by the decoder\nThe following parameters are provided :\n\t- Practical salinity\n\t- Sea temperature in-situ ITS-90 scale\n\t- Electrical conductivity\n\t- Sea water pressure, equals 0 at sea-level\n"
-    ],
-    "oai_identifier": [
-        "1d69f605-c13f-5d28-a414-eba6df988900"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-0.26503,38.772879],[-0.26503,43.804358],[9.556747,43.804358],[9.556747,38.772879],[-0.26503,38.772879]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "sea water temperature"
-        },
-        {
-            "name": "sea water electrical conductivity"
-        },
-        {
-            "name": "sea water pressure"
-        },
-        {
-            "name": "temperature sensor oxygen sea water"
-        },
-        {
-            "name": "uncalibrated phase shift reported oxygen sensor"
-        },
-        {
-            "name": "calibrated phase shift reported oxygen sensor"
-        },
-        {
-            "name": "uncalibrated red phase shift reported oxygen sensor"
-        }
-    ],
-    "title": [
-        "imedia deployment (EGO glider : campe) (Mediterranean Sea - Western basin)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/seanoe-oai_dc/SET_1/json/1e449dcc-2026-5d86-9501-3013d1cc40f4.json b/oaitestdata/seanoe-oai_dc/SET_1/json/1e449dcc-2026-5d86-9501-3013d1cc40f4.json
deleted file mode 100644
index 3c7fc2ba..00000000
--- a/oaitestdata/seanoe-oai_dc/SET_1/json/1e449dcc-2026-5d86-9501-3013d1cc40f4.json
+++ /dev/null
@@ -1,71 +0,0 @@
-{
-    "Contact": [
-        "SEANOE"
-    ],
-    "DOI": "http://dx.doi.org/10.17882/46446",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "MetaDataAccess": "http://www.seanoe.org/oai/OAIHandler?verb=GetRecord&metadataPrefix=oai_dc&identifier=1e449dcc-2026-5d86-9501-3013d1cc40f4",
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "SEANOE"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "CC-BY-NC"
-    ],
-    "SpatialCoverage": "(40N-60N,45W-5 E)",
-    "TemporalCoverage": " point in time : None",
-    "author": [
-        "Daniault, Nathalie",
-        "Lherminier, Pascale",
-        "Mercier, Herle"
-    ],
-    "fulltext": "oai:seanoe.org:46446;2016-10-12;Gridded property and transport data of the biennial Greenland-Portugal A25 OVIDE line;Daniault, Nathalie;Mercier, Herle;Lherminier, Pascale;North Atlantic Ocean;circulation;water mass;transport;OVIDE;This data set contains the gridded hydrographic and transport data for the biennial Go-Ship A25 Greenland\u2013Portugal OVIDE section from 2002 to 2012. The properties and transports are mapped on a 7km x 1m grid. Using a common grid facilitates the comparison between the different occupations of the line and the averaging. This data set was used in Daniault et al. (2016, Progress in Oceanography) to which the reader is referred for a description of the gridding method.\n;SEANOE;2016-10;dataset;DOI:10.17882/46446;http://dx.doi.org/10.17882/46446;North 60.0, South 40.0, East 5.0, West -45.0;https://www.seanoe.org/data/00353/46446/illustration.gif;40.0 -45.0 60.0 5.0;CC-BY-NC",
-    "group": "seanoe",
-    "groups": [
-        {
-            "name": "seanoe"
-        }
-    ],
-    "name": "1e449dcc-2026-5d86-9501-3013d1cc40f4",
-    "notes": [
-        "This data set contains the gridded hydrographic and transport data for the biennial Go-Ship A25 Greenland\u2013Portugal OVIDE section from 2002 to 2012. The properties and transports are mapped on a 7km x 1m grid. Using a common grid facilitates the comparison between the different occupations of the line and the averaging. This data set was used in Daniault et al. (2016, Progress in Oceanography) to which the reader is referred for a description of the gridding method.\n"
-    ],
-    "oai_identifier": [
-        "1e449dcc-2026-5d86-9501-3013d1cc40f4"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-45.0,40.0],[-45.0,60.0],[5.0,60.0],[5.0,40.0],[-45.0,40.0]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "North Atlantic Ocean"
-        },
-        {
-            "name": "circulation"
-        },
-        {
-            "name": "water mass"
-        },
-        {
-            "name": "transport"
-        },
-        {
-            "name": "OVIDE"
-        }
-    ],
-    "title": [
-        "Gridded property and transport data of the biennial Greenland-Portugal A25 OVIDE line"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/seanoe-oai_dc/SET_1/json/1e965a59-f366-5c7a-8ffc-da8d30f7d813.json b/oaitestdata/seanoe-oai_dc/SET_1/json/1e965a59-f366-5c7a-8ffc-da8d30f7d813.json
deleted file mode 100644
index c7b92645..00000000
--- a/oaitestdata/seanoe-oai_dc/SET_1/json/1e965a59-f366-5c7a-8ffc-da8d30f7d813.json
+++ /dev/null
@@ -1,85 +0,0 @@
-{
-    "Contact": [
-        "SEANOE"
-    ],
-    "DOI": "http://dx.doi.org/10.17882/51473",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "MetaDataAccess": "http://www.seanoe.org/oai/OAIHandler?verb=GetRecord&metadataPrefix=oai_dc&identifier=1e965a59-f366-5c7a-8ffc-da8d30f7d813",
-    "PublicationTimestamp": "2017-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2017"
-    ],
-    "Publisher": [
-        "SEANOE"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/727890/EU//INTAROS"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "CC-BY-NC"
-    ],
-    "SpatialCoverage": "(78N-78N,9 E-16E)",
-    "TempCoverageBegin": 71050391999,
-    "TempCoverageEnd": 71050391999,
-    "TemporalCoverage": " point in time : 2252-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "2252-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2252-07-01T11:59:59Z",
-    "author": [
-        "Mortier, Laurent",
-        "Houssais, Marie-noelle",
-        "Testor, Pierre",
-        "Herbaut, Christophe"
-    ],
-    "fulltext": "oai:seanoe.org:51473;2018-12-17;taiga deployment (EGO glider\u00a0: tintin) (Greenland sea);Houssais, Marie-noelle;Herbaut, Christophe;Testor, Pierre;Mortier, Laurent;sea water temperature;sea water electrical conductivity;sea water pressure;mole concentration of dissolved molecular oxygen in sea water;temperature of sensor for oxygen in sea water;uncalibrated phase shift reported by oxygen sensor;calibrated phase shift reported by oxygen sensor;mass concentration of chlorophyll a in sea water;volume absorption coefficient of radiative flux in sea water due to dissolved organic matter;volume scattering function of radiative flux in sea water 700;The observations of tintin glider on taiga (Greenland sea) :\n\t- EGO NetCDF time-series (data, metadata, derived sea water current)\n\t- NetCDF profiles extracted from the above time-series\n\t- Raw data\n\t- JSON metadata used by the decoder\nThe following parameters are provided :\u00a0\n\t- Practical salinity\n\t- Sea temperature in-situ ITS-90 scale\n\t- Electrical conductivity\n\t- Sea water pressure, equals 0 at sea-level\n;SEANOE;2017-09;dataset;DOI:10.17882/51473;http://dx.doi.org/10.17882/51473;info:eu-repo/grantAgreement/EC/FP7/727890/EU//INTAROS;North 78.2252, South 78.029, East 15.6414, West 8.8952;https://www.seanoe.org/data/00403/51473/illustration.gif;78.029 8.8952 78.2252 15.6414;CC-BY-NC",
-    "group": "seanoe",
-    "groups": [
-        {
-            "name": "seanoe"
-        }
-    ],
-    "name": "1e965a59-f366-5c7a-8ffc-da8d30f7d813",
-    "notes": [
-        "The observations of tintin glider on taiga (Greenland sea) :\n\t- EGO NetCDF time-series (data, metadata, derived sea water current)\n\t- NetCDF profiles extracted from the above time-series\n\t- Raw data\n\t- JSON metadata used by the decoder\nThe following parameters are provided :\u00a0\n\t- Practical salinity\n\t- Sea temperature in-situ ITS-90 scale\n\t- Electrical conductivity\n\t- Sea water pressure, equals 0 at sea-level\n"
-    ],
-    "oai_identifier": [
-        "1e965a59-f366-5c7a-8ffc-da8d30f7d813"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[8.8952,78.029],[8.8952,78.2252],[15.6414,78.2252],[15.6414,78.029],[8.8952,78.029]]]}",
-    "state": "active",
-    "tags": [
-        {
-            "name": "sea water temperature"
-        },
-        {
-            "name": "sea water electrical conductivity"
-        },
-        {
-            "name": "sea water pressure"
-        },
-        {
-            "name": "temperature sensor oxygen sea water"
-        },
-        {
-            "name": "uncalibrated phase shift reported oxygen sensor"
-        },
-        {
-            "name": "calibrated phase shift reported oxygen sensor"
-        },
-        {
-            "name": "mass concentration chlorophyll sea water"
-        }
-    ],
-    "title": [
-        "taiga deployment (EGO glider\u00a0: tintin) (Greenland sea)"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/seanoe-oai_dc/SET_1/json/1ebcca16-8156-5371-ba28-fe300be8df16.json b/oaitestdata/seanoe-oai_dc/SET_1/json/1ebcca16-8156-5371-ba28-fe300be8df16.json
deleted file mode 100644
index 8d9b4d09..00000000
--- a/oaitestdata/seanoe-oai_dc/SET_1/json/1ebcca16-8156-5371-ba28-fe300be8df16.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "SEANOE"
-    ],
-    "DOI": "http://dx.doi.org/10.17882/57450",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "MetaDataAccess": "http://www.seanoe.org/oai/OAIHandler?verb=GetRecord&metadataPrefix=oai_dc&identifier=1ebcca16-8156-5371-ba28-fe300be8df16",
-    "PublicationTimestamp": "2018-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2018"
-    ],
-    "Publisher": [
-        "SEANOE"
-    ],
-    "RelatedIdentifier": [
-        "info:eu-repo/grantAgreement/EC/FP7/262552/EU//MARINET"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "CC-BY-NC"
-    ],
-    "SpatialCoverage": [
-        "50.729627 1.597578 50.729627 1.597578",
-        "55.862869 -4.242457 55.862869 -4.242457",
-        "41.818443 12.457076 41.818443 12.457076"
-    ],
-    "TemporalCoverage": [
-        "North 50.729627, South 50.729627, East 1.597578, West 1.597578",
-        "North 55.862869, South 55.862869, East -4.242457, West -4.242457",
-        "North 41.818443, South 41.818443, East 12.457076, West 12.457076"
-    ],
-    "author": [
-        "Germain, Gregory",
-        "Gaurier, Benoit",
-        "Facq, Jean-valery",
-        "Di Felice, Fabio",
-        "Johnstone, Cameron",
-        "Day, Sandy",
-        "Costanzo, Marcello"
-    ],
-    "fulltext": "oai:seanoe.org:57450;2018-11-14;Towing and circulating tanks tidal energy converter test results;Gaurier, Benoit;Germain, Gregory;Facq, Jean-valery;Day, Sandy;Johnstone, Cameron;Di Felice, Fabio;Costanzo, Marcello;A comparative \"Round Robin\" testing program has been conducted as part of the EC FP VII MaRINET program in order to evaluate the impact of different experimental facilities on the test results. The aim of the trials was to test the same model tidal turbine in four different test facilities to explore the sensitivity of the results to the choice of facility. The facilities used in the testing program include two towing tanks, at CNR-INSEAN (Rome, 220 m long) and at Strathclyde University (Glasgow, 76 m long), and two recirculating tanks at CNR-INSEAN (Rome) and at IFREMER (Boulogne sur mer).\nThe model consists of a three-bladed horizontal axis turbine, which is D=0.7m in diameter. The rotor is connected to a motor-gearbox assembly consisting of a gearbox, a DC motor, a ballast load and a motor speed control unit, providing an active rotor speed control. The turbine blades are designed from a NACA 63-418 profile. A torque meter is placed between the rotor and the gearbox for torque measurements.\nThe forces and moments acting on the structure are obtained by means of a six-component load cell, which measures the three force components and the three moment components and the torque by a torque sensor directly fixed between the rotor and the motor. All signals coming from the load-cell, the torque-meter and the motor are recorded synchronously at a sample frequency of 100Hz.\nIn each tank, the turbine depth is kept constant at 1 m under the free surface. The turbine is fixed on a moving carriage in the towing tanks and on a customised mounting in the flume tanks. The flow velocity or carriage velocity is chosen and fixed for each set of tests; the turbine rotation speed is then varied to adjust the tip speed ratio. The rotational speed is measured and controlled for each measurement point, but is adjusted manually.\n;SEANOE;2018-10;dataset;DOI:10.17882/57450;http://dx.doi.org/10.17882/57450;info:eu-repo/grantAgreement/EC/FP7/262552/EU//MARINET;North 50.729627, South 50.729627, East 1.597578, West 1.597578;North 55.862869, South 55.862869, East -4.242457, West -4.242457;North 41.818443, South 41.818443, East 12.457076, West 12.457076;https://www.seanoe.org/data/00463/57450/illustration.gif;50.729627 1.597578 50.729627 1.597578;55.862869 -4.242457 55.862869 -4.242457;41.818443 12.457076 41.818443 12.457076;CC-BY-NC",
-    "group": "seanoe",
-    "groups": [
-        {
-            "name": "seanoe"
-        }
-    ],
-    "name": "1ebcca16-8156-5371-ba28-fe300be8df16",
-    "notes": [
-        "A comparative \"Round Robin\" testing program has been conducted as part of the EC FP VII MaRINET program in order to evaluate the impact of different experimental facilities on the test results. The aim of the trials was to test the same model tidal turbine in four different test facilities to explore the sensitivity of the results to the choice of facility. The facilities used in the testing program include two towing tanks, at CNR-INSEAN (Rome, 220 m long) and at Strathclyde University (Glasgow, 76 m long), and two recirculating tanks at CNR-INSEAN (Rome) and at IFREMER (Boulogne sur mer).\nThe model consists of a three-bladed horizontal axis turbine, which is D=0.7m in diameter. The rotor is connected to a motor-gearbox assembly consisting of a gearbox, a DC motor, a ballast load and a motor speed control unit, providing an active rotor speed control. The turbine blades are designed from a NACA 63-418 profile. A torque meter is placed between the rotor and the gearbox for torque measurements.\nThe forces and moments acting on the structure are obtained by means of a six-component load cell, which measures the three force components and the three moment components and the torque by a torque sensor directly fixed between the rotor and the motor. All signals coming from the load-cell, the torque-meter and the motor are recorded synchronously at a sample frequency of 100Hz.\nIn each tank, the turbine depth is kept constant at 1 m under the free surface. The turbine is fixed on a moving carriage in the towing tanks and on a customised mounting in the flume tanks. The flow velocity or carriage velocity is chosen and fixed for each set of tests; the turbine rotation speed is then varied to adjust the tip speed ratio. The rotational speed is measured and controlled for each measurement point, but is adjusted manually.\n"
-    ],
-    "oai_identifier": [
-        "1ebcca16-8156-5371-ba28-fe300be8df16"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "title": [
-        "Towing and circulating tanks tidal energy converter test results"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/seanoe-oai_dc/SET_1/json/1f0d846a-8796-5a82-9170-6ead85bb9b71.json b/oaitestdata/seanoe-oai_dc/SET_1/json/1f0d846a-8796-5a82-9170-6ead85bb9b71.json
deleted file mode 100644
index 344a6063..00000000
--- a/oaitestdata/seanoe-oai_dc/SET_1/json/1f0d846a-8796-5a82-9170-6ead85bb9b71.json
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-    "Contact": [
-        "SEANOE"
-    ],
-    "DOI": "http://dx.doi.org/10.17882/41825",
-    "DiscHierarchy": [
-        "4.4.4",
-        "Geosciences",
-        "Oceanography/Marine Science"
-    ],
-    "Discipline": "Oceanography/Marine Science",
-    "MetaDataAccess": "http://www.seanoe.org/oai/OAIHandler?verb=GetRecord&metadataPrefix=oai_dc&identifier=1f0d846a-8796-5a82-9170-6ead85bb9b71",
-    "PublicationTimestamp": "2016-07-01T11:59:59Z",
-    "PublicationYear": [
-        "2016"
-    ],
-    "Publisher": [
-        "SEANOE"
-    ],
-    "ResourceType": [
-        "dataset"
-    ],
-    "Rights": [
-        "CC-BY"
-    ],
-    "SpatialCoverage": "(30N-46N,6 W-36E)",
-    "TempCoverageBegin": 109896955199,
-    "TempCoverageEnd": 109896955199,
-    "TemporalCoverage": " point in time : 3483-07-01T11:59:59Z",
-    "TemporalCoverage:BeginDate": "3483-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "3483-07-01T11:59:59Z",
-    "author": [
-        "Jadaud, Angelique",
-        "Follesa, Maria",
-        "Maiorano, Porzia",
-        "Rabiller, Manuella",
-        "Denis, Axelle",
-        "Ordines, Francesc",
-        "Di Santo, Carla",
-        "Theil, Andr\u00e9a",
-        "Cavaill\u00e9, Thomas",
-        "Brind'Amour, Anik",
-        "Spedicato, Maria Teresa",
-        "M\u00e9rigot, Bastien",
-        "Carbonara, Pierluigi"
-    ],
-    "fulltext": "oai:seanoe.org:41825;2016-10-04;Morphological traits measured for 89 fish species sampled in the Mediterranean Sea during MEDITS scientific surveys;Brind'Amour, Anik;M\u00e9rigot, Bastien;Ordines, Francesc;Carbonara, Pierluigi;Follesa, Maria;Jadaud, Angelique;Maiorano, Porzia;Rabiller, Manuella;Denis, Axelle;Di Santo, Carla;Cavaill\u00e9, Thomas;Theil, Andr\u00e9a;Spedicato, Maria Teresa;The data come from organisms and pictures collected during the MEDITS annual bottom trawl surveys conducted between 2011 and 2013 (Bertrand et al. 2002). MEDITS surveys cover the continental shelf (10 m to 200 m depth) and the upper part of the continental slope (200 m to 800 m) on the Mediterranean. A total of 1511 individuals from 85 fish species were collected from seven Mediterranean areas (South Adriatic Sea, Sardinia, Gulf of Lions, around Cyprus, Mallorca, Tyrrhenian Sea, and North West Ionian Sea). A set of 14 morphological traits related to the habitat and the diet of the species were measured in the field and on pictures using the ImageJ software (version 1.47, http://imagej.nih.gov/ij/) (see Granger et al. 2015 and Brind'Amour et al. submitted for details) (Figure 1). Replicats of measures vary between 1 (e.g. Scorpaena loppei) to 53 (e.g. Serranus hepatus) according to fish species. Twelve of the chosen traits consist in continuous biological characteristics measured on each individual (measured in cm). The two remaining traits are categorical and determined at the species level.\n;SEANOE;2016-01;dataset;DOI:10.17882/41825;http://dx.doi.org/10.17882/41825;North 46.3483, South 30.108837, East 36.474609, West -5.888672;https://www.seanoe.org/data/00307/41825/illustration.gif;30.108837 -5.888672 46.3483 36.474609;CC-BY",
-    "group": "seanoe",
-    "groups": [
-        {
-            "name": "seanoe"
-        }
-    ],
-    "name": "1f0d846a-8796-5a82-9170-6ead85bb9b71",
-    "notes": [
-        "The data come from organisms and pictures collected during the MEDITS annual bottom trawl surveys conducted between 2011 and 2013 (Bertrand et al. 2002). MEDITS surveys cover the continental shelf (10 m to 200 m depth) and the upper part of the continental slope (200 m to 800 m) on the Mediterranean. A total of 1511 individuals from 85 fish species were collected from seven Mediterranean areas (South Adriatic Sea, Sardinia, Gulf of Lions, around Cyprus, Mallorca, Tyrrhenian Sea, and North West Ionian Sea). A set of 14 morphological traits related to the habitat and the diet of the species were measured in the field and on pictures using the ImageJ software (version 1.47, http://imagej.nih.gov/ij/) (see Granger et al. 2015 and Brind'Amour et al. submitted for details) (Figure 1). Replicats of measures vary between 1 (e.g. Scorpaena loppei) to 53 (e.g. Serranus hepatus) according to fish species. Twelve of the chosen traits consist in continuous biological characteristics measured on each individual (measured in cm). The two remaining traits are categorical and determined at the species level.\n"
-    ],
-    "oai_identifier": [
-        "1f0d846a-8796-5a82-9170-6ead85bb9b71"
-    ],
-    "oai_set": "",
-    "spatial": "{\"type\":\"Polygon\",\"coordinates\":[[[-5.888672,30.108837],[-5.888672,46.3483],[36.474609,46.3483],[36.474609,30.108837],[-5.888672,30.108837]]]}",
-    "state": "active",
-    "title": [
-        "Morphological traits measured for 89 fish species sampled in the Mediterranean Sea during MEDITS scientific surveys"
-    ],
-    "url": ""
-}
\ No newline at end of file
diff --git a/oaitestdata/slks-ff/SET_1/json/0a31efd1-f722-5f0e-9fc5-7dad67d5028e.json b/oaitestdata/slks-ff/SET_1/json/0a31efd1-f722-5f0e-9fc5-7dad67d5028e.json
deleted file mode 100644
index 216049d4..00000000
--- a/oaitestdata/slks-ff/SET_1/json/0a31efd1-f722-5f0e-9fc5-7dad67d5028e.json
+++ /dev/null
@@ -1,58 +0,0 @@
-{
-    "Contact": [
-        "post@slks.dk"
-    ],
-    "DiscHierarchy": [
-        "1.1.4",
-        "Ancient Cultures",
-        "Classical Archaeology"
-    ],
-    "Discipline": "Classical Archaeology",
-    "Language": [
-        "Danish"
-    ],
-    "MetaDataAccess": "http://www.kulturarv.dk/ffrepox/OAIHandler?verb=GetRecord&metadataPrefix=ff&identifier=0a31efd1-f722-5f0e-9fc5-7dad67d5028e",
-    "PublicationTimestamp": "2020-01-17T11:59:59Z",
-    "PublicationYear": [
-        "2020"
-    ],
-    "Publisher": [
-        "Slots- og Kulturstyrelsen"
-    ],
-    "Rights": [
-        "For scientific use"
-    ],
-    "notes": [
-        "This record describes ancient sites and monuments as well as archaeological excavations undertaken by Danish museums."
-    ],
-    "SpatialCoverage": [
-        "872778;6126327"
-    ],
-    "TemporalCoverage": " period : ( None - 1066-07-01T11:59:59Z ) ",
-    "author": [
-        "Kroppedal Museum,  Ark\u00e6ologi"
-    ],
-    "fulltext": "urn:repox.www.kulturarv.dkSites:http://www.kulturarv.dk/fundogfortidsminder/site/1546;2020-01-18;Sites;http://www.kulturarv.dk/fundogfortidsminder/site/1546;2020-01-17T17:00:01.923696+01:00;1;B;http://www.kulturarv.dk/fundogfortidsminder/skos/parish#060305;Vestermarie;http://www.kulturarv.dk/fundogfortidsminder/skos/plot#50;Digitaliseret 1981;Kantedamsgaaard;1876;http://www.kulturarv.dk/fundogfortidsminder/skos/placename#9;Uspecificeret;1849;0;0;http://www.kulturarv.dk/fundogfortidsminder/skos/surroundings#DMK;Dyrket mark;http://www.kulturarv.dk/fundogfortidsminder/skos/monumentsign#10;Uvis;http://www.kulturarv.dk/fundogfortidsminder/skos/municipality#400;Bornholm;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:institution#)BMR;Bornholms Museum;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:institution#TAK;Kroppedal Museum,  Ark\u00e6ologi;872778;6126327;http://www.kulturarv.dk/fundogfortidsminder/object/2547;375;1066;CXXX;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:period#CYXX;Yngre Jernalder (Germansk jernalder og Vikingetid);Jernalder;http://www.kulturarv.dk/fundogfortidsminder/skos/object#07046;Enkeltfund;Diverse anl\u00e6g og genstande;menneskeskabte objekter;1876;1876;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:event#MBR;Museal berejsning;Museal;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:institution#N01;Nationalmuseet, Danske Afd., Danmarks Oldtid;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:archive#SBT;Sognebeskrivelsen;I Aaret 1849 fandtes ved Sl\u00f8ifning af et \u00e6ldre Markskj\u00e6l en pr\u00e6gtig Halsring af s\u00f8lvblandet Guld af lignende Arbeide som Worsaas Afb N:444. Den er omtalt i V Boyes Fortegnelse Side 66 N:369, og henregnes til den yngre Jernalder (vog 1 Mark 6 7/8 Lod).;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:text#BTE;Berejsertekst;http://www.kulturarv.dk/fundogfortidsminder/skos/person#117046;J.A. J\u00f8rgensen;http://www.kulturarv.dk/fundogfortidsminder/skos/title#1354;Kaptajn;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:role#211;Berejser;http://www.kulturarv.dk/fundogfortidsminder/skos/person#121053;J.A. J\u00f8rgensen;http://www.kulturarv.dk/fundogfortidsminder/skos/title#1354;Kaptajn;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:role#211;Berejser;1849      ;1849      ;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:event#GDF;Danef\u00e6 erkl\u00e6ring ved Nationalmuseet;Genstand;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:institution#N01;Nationalmuseet, Danske Afd., Danmarks Oldtid;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:archive#TOP;Topografisk arkiv;1849;1849;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:event#LSL;Sl\u00f8jfet ved land- og skovbrug;Dyrkning og fiskeri;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:institution#N01;Nationalmuseet, Danske Afd., Danmarks Oldtid;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:archive#TOP;Topografisk arkiv;http://www.kulturarv.dk/fundogfortidsminder/resource/map/1546;Kantedamsgaaard;2020-01-17;Kort og Matrikelstyrelsen;M\u00e5 kun kopieres til personlig brug.;Kortet viser lokalitetens placering i Danmark.;http://www.kulturarv.dk/fundogfortidsminder/resource/map/1546;http://www.kulturarv.dk/fundogfortidsminder/skos/digitaldocumentation#USP;Uspecificeret",
-    "group": "slks",
-    "groups": [
-        {
-            "name": "slks"
-        }
-    ],
-    "name": "0a31efd1-f722-5f0e-9fc5-7dad67d5028e",
-    
-    "oai_identifier": [
-        "0a31efd1-f722-5f0e-9fc5-7dad67d5028e"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Uspecificeret"
-        }
-    ],
-    "title": [
-        "Kantedamsgaaard"
-    ],
-    "url": "http://www.kulturarv.dk/fundogfortidsminder/site/1546"
-}
\ No newline at end of file
diff --git a/oaitestdata/slks-ff/SET_1/json/2d337211-f960-5283-9e5d-eb573e89667f.json b/oaitestdata/slks-ff/SET_1/json/2d337211-f960-5283-9e5d-eb573e89667f.json
deleted file mode 100644
index 4ba5468d..00000000
--- a/oaitestdata/slks-ff/SET_1/json/2d337211-f960-5283-9e5d-eb573e89667f.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "post@slks.dk"
-    ],
-    "DiscHierarchy": [
-        "1.1.4",
-        "Ancient Cultures",
-        "Classical Archaeology"
-    ],
-    "Discipline": "Classical Archaeology",
-    "Language": [
-        "Danish"
-    ],
-    "MetaDataAccess": "http://www.kulturarv.dk/ffrepox/OAIHandler?verb=GetRecord&metadataPrefix=ff&identifier=2d337211-f960-5283-9e5d-eb573e89667f",
-    "PublicationTimestamp": "2020-01-17T11:59:59Z",
-    "PublicationYear": [
-        "2020"
-    ],
-    "Publisher": [
-        "Slots- og Kulturstyrelsen"
-    ],
-    "Rights": [
-        "For scientific use"
-    ],
-    "notes": [
-        "This record describes ancient sites and monuments as well as archaeological excavations undertaken by Danish museums."
-    ],
-    "SpatialCoverage": [
-        "549425;6091293"
-    ],
-    "TemporalCoverage": " period : ( 1700-07-01T11:59:59Z - None ) ",
-    "author": [
-        "Museum S\u00f8nderjylland"
-    ],
-    "fulltext": "urn:repox.www.kulturarv.dkSites:http://www.kulturarv.dk/fundogfortidsminder/site/87457;2020-01-18;Sites;http://www.kulturarv.dk/fundogfortidsminder/site/87457;2020-01-17T17:00:01.923696+01:00;174;http://www.kulturarv.dk/fundogfortidsminder/skos/parish#230210;Ulkeb\u00f8l;http://www.kulturarv.dk/fundogfortidsminder/skos/plot#50;Digitaliseret 1981;Arnkils Fredskov, afd. 273.;1955;http://www.kulturarv.dk/fundogfortidsminder/skos/placename#10;AFD Afdeling i skove o.a.;Arnkils fredskov afd. 273;1955;http://www.kulturarv.dk/fundogfortidsminder/skos/placename#3;Landskab, herunder v\u00e5domr\u00e5de;R 286/ktb. ?;1955;http://www.kulturarv.dk/fundogfortidsminder/skos/id#SPEC;Anden identifikation;421121;Fredet 1937 eller senere;Sk\u00e5lsten. Fl\u00e6kket sten, med 5 sk\u00e5lgruber i \u00d8-lige side, hvor der ogs\u00e5, af nyere dato, er indhugget JDK Lejren 1940. \n\nP\u00e5 N-lige side er endvidere indhugget (mindre dybt) 2/13 B.;FREDNR tildelt p\u00e5 statsejet areal;false;sev\u00e6rdig;false;false;false;false;1955;0;0;http://www.kulturarv.dk/fundogfortidsminder/skos/surroundings#SKO;Skov/plantage;http://www.kulturarv.dk/fundogfortidsminder/skos/monumentsign#10;Uvis;http://www.kulturarv.dk/fundogfortidsminder/skos/municipality#540;S\u00f8nderborg;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:institution#)MSJ;Museum S\u00f8nderjylland;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:institution#MSJ;Museum S\u00f8nderjylland;549425;6091293;http://www.kulturarv.dk/fundogfortidsminder/object/94246;-1700;-501;BXXX;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:period#BXXX;Bronzealder;Bronzealder;http://www.kulturarv.dk/fundogfortidsminder/skos/object#20199;Sk\u00e5ltegn;Tro og tradition;steder og objekter knyttet til tro og tradition;http://www.kulturarv.dk/fundogfortidsminder/object/164817;1946;1949;FXXX;http://www.kulturarv.dk/fundogfortidsminder/skos/object#22155;Mindesm\u00e6rke;Social og samfund;anl\u00e6g og steder til offentlig brug;1984-12-04;1984-12-04;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:event#MNB;Nyberejsning af fredede lokaliteter;Museal;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:institution#SNS;Skov- og Naturstyrelsen, 10. kontor;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:archive#XXX;Uspecificeret arkiv;Som beskrevet. Stensign.;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:text#BTE;Berejsertekst;http://www.kulturarv.dk/fundogfortidsminder/skos/person#117077;N.-C. Clemmesen;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:title#1354;Kaptajn;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:role#211;Berejser;1908;1955;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:event#MBS;Museal besigtigelse;Museal;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:institution#MSS;Museet p\u00e5 S\u00f8nderborg Slot;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:archive#XXX;Uspecificeret arkiv;Ingen beskrivelse.;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:text#DKC;DKC/KUAS-registrator kommentar;http://www.kulturarv.dk/fundogfortidsminder/skos/person#124903;J. Raben;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:role#210;Ansvarlig;1955;1955;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:event#MBR;Museal berejsning;Museal;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:institution#N01;Nationalmuseet, Danske Afd., Danmarks Oldtid;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:archive#SBT;Sognebeskrivelsen;Stor fl\u00e6kket sten med 5 sk\u00e5lgruber i \u00f8stlige side. P\u00e5 stenen er lige ved helleristningerne indhugget JDK LEJREN 1940.;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:text#GUL;Tekst fra Nationalmuseets gule lister 1937-1956;http://www.kulturarv.dk/fundogfortidsminder/skos/person#117080;O. Klindt-Jensen;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:role#211;Berejser;1955      ;1955      ;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:event#FTL;Tinglysning;Fredning;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:institution#N01;Nationalmuseet, Danske Afd., Danmarks Oldtid;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:archive#SBT;Sognebeskrivelsen;1955      ;1985      ;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:event#IRA;Institutionssag uden journaldata;Sagsbehandling og planl\u00e6gning;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:institution#HAM;Haderslev Museum;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:archive#XXX;Uspecificeret arkiv;2009-10-08;2011-06-30;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:event#MPT;Periodisk tilsyn med fredede lokaliteter;Museal;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:institution#MSJ;Museum S\u00f8nderjylland;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:archive#XXX;Uspecificeret arkiv;Blev ikke fundet.;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:text#BLA;Blandet tekst;2017-10-17;2017-11-17;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:event#MPT;Periodisk tilsyn med fredede lokaliteter;Museal;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:institution#MSJ;Museum S\u00f8nderjylland;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:archive#XXX;Uspecificeret arkiv;http://www.kulturarv.dk/fundogfortidsminder/resource/186681;stenen set fra \u00f8st;2017-10-17;msj1tekr_20171117153439.JPG;http://www.kulturarv.dk/fundogfortidsminder/resource/186681;http://www.kulturarv.dk/fundogfortidsminder/Lokalitet/87457;http://www.kulturarv.dk/fundogfortidsminder/skos/digitaldocumentation#TSF;Tilsynsfoto;http://www.kulturarv.dk/fundogfortidsminder/resource/186682;stenen set fra syd;2017-10-17;msj1tekr_20171117153522.JPG;http://www.kulturarv.dk/fundogfortidsminder/resource/186682;http://www.kulturarv.dk/fundogfortidsminder/Lokalitet/87457;http://www.kulturarv.dk/fundogfortidsminder/skos/digitaldocumentation#TSF;Tilsynsfoto;http://www.kulturarv.dk/fundogfortidsminder/resource/186683;stenen set fra nord;2017-10-17;msj1tekr_20171117153603.JPG;http://www.kulturarv.dk/fundogfortidsminder/resource/186683;http://www.kulturarv.dk/fundogfortidsminder/Lokalitet/87457;http://www.kulturarv.dk/fundogfortidsminder/skos/digitaldocumentation#TSF;Tilsynsfoto;http://www.kulturarv.dk/fundogfortidsminder/resource/map/87457;Arnkils Fredskov, afd. 273.;2020-01-17;Kort og Matrikelstyrelsen;M\u00e5 kun kopieres til personlig brug.;Kortet viser lokalitetens placering i Danmark.;http://www.kulturarv.dk/fundogfortidsminder/resource/map/87457;http://www.kulturarv.dk/fundogfortidsminder/skos/digitaldocumentation#USP;Uspecificeret;1984-12-04;9;18;Clemmesen, N.-C.;http://www.kulturarv.dk/fundogfortidsminder/skos/archivaldocumentation#USP;Uspecificeret;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:institution#KAS;Kulturstyrelsen;http://www.kulturarv.dk/fundogfortidsminder/skos/person#117077;N.-C. Clemmesen;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:title#1354;Kaptajn;http://www.kulturarv.dk/fundogfortidsminder/skos/#role210;Ansvarlig",
-    "group": "slks",
-    "groups": [
-        {
-            "name": "slks"
-        }
-    ],
-    "name": "2d337211-f960-5283-9e5d-eb573e89667f",
-    
-    "oai_identifier": [
-        "2d337211-f960-5283-9e5d-eb573e89667f"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "AFD Afdeling skove o.a."
-        },
-        {
-            "name": "Landskab"
-        },
-        {
-            "name": "herunder v\u00e5domr\u00e5de"
-        }
-    ],
-    "title": [
-        "Arnkils Fredskov, afd. 273.",
-        "Arnkils fredskov afd. 273"
-    ],
-    "url": "http://www.kulturarv.dk/fundogfortidsminder/site/87457"
-}
\ No newline at end of file
diff --git a/oaitestdata/slks-ff/SET_1/json/2d631790-3cbb-5a0d-9545-002da28d06bc.json b/oaitestdata/slks-ff/SET_1/json/2d631790-3cbb-5a0d-9545-002da28d06bc.json
deleted file mode 100644
index 282cc4a9..00000000
--- a/oaitestdata/slks-ff/SET_1/json/2d631790-3cbb-5a0d-9545-002da28d06bc.json
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-    "Contact": [
-        "post@slks.dk"
-    ],
-    "DiscHierarchy": [
-        "1.1.4",
-        "Ancient Cultures",
-        "Classical Archaeology"
-    ],
-    "Discipline": "Classical Archaeology",
-    "Language": [
-        "Danish"
-    ],
-    "MetaDataAccess": "http://www.kulturarv.dk/ffrepox/OAIHandler?verb=GetRecord&metadataPrefix=ff&identifier=2d631790-3cbb-5a0d-9545-002da28d06bc",
-    "PublicationTimestamp": "2020-01-17T11:59:59Z",
-    "PublicationYear": [
-        "2020"
-    ],
-    "Publisher": [
-        "Slots- og Kulturstyrelsen"
-    ],
-    "Rights": [
-        "For scientific use"
-    ],
-    "notes": [
-        "This record describes ancient sites and monuments as well as archaeological excavations undertaken by Danish museums."
-    ],
-    "SpatialCoverage": [
-        "538911;6144507"
-    ],
-    "TempCoverageBegin": 40377095999,
-    "TempCoverageEnd": 53662478399,
-    "TemporalCoverage": " period : ( 1280-07-01T11:59:59Z - 1701-07-01T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "1280-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1701-07-01T11:59:59Z",
-    "author": [
-        "Museum S\u00f8nderjylland"
-    ],
-    "fulltext": "urn:repox.www.kulturarv.dkSites:http://www.kulturarv.dk/fundogfortidsminder/site/171708;2020-01-18;Sites;http://www.kulturarv.dk/fundogfortidsminder/site/171708;2020-01-17T17:00:01.923696+01:00;157;http://www.kulturarv.dk/fundogfortidsminder/skos/parish#170704;S\u00f8nder Stenderup;http://www.kulturarv.dk/fundogfortidsminder/skos/plot#49;Afsat af museumsmedarbejder;Agstrup;2005;http://www.kulturarv.dk/fundogfortidsminder/skos/placename#5;Bebyggelse, havne og industrianl\u00e6g;http://www.kulturarv.dk/fundogfortidsminder/skos/municipality#621;Kolding;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:institution#)MKH;Museet p\u00e5 Koldinghus;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:institution#MSJ;Museum S\u00f8nderjylland;538911;6144507;http://www.kulturarv.dk/fundogfortidsminder/object/232162;-12800;-1701;AXXX;http://www.kulturarv.dk/fundogfortidsminder/skos/object#03046;Enkeltfund;Bos\u00e6ttelse;alle former for bos\u00e6ttelse;http://www.kulturarv.dk/fundogfortidsminder/object/287277;-3950;-1701;AXXX;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:period#AYXX;Neolitikum;Bondestenalder;http://www.kulturarv.dk/fundogfortidsminder/skos/object#03046;Enkeltfund;Bos\u00e6ttelse;alle former for bos\u00e6ttelse;2008-05-15;2008-05-15;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:ff:event#IRA;Institutionssag uden journaldata;Sagsbehandling og planl\u00e6gning;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:institution#N01;Nationalmuseet, Danske Afd., Danmarks Oldtid;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:archive#XXX;Uspecificeret arkiv;2005-09;2005-09;4557;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:ff:event#GGM;Genstand givet til museum;Genstand;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:institution#HAM;Haderslev Museum;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:archive#XXX;Uspecificeret arkiv;Genstandene er en del af N. Boysens oldsagssamling, der er overdraget til HAM.;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:text#BLA;Blandet tekst;2005-09;2005-09;4557;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:ff:event#POS;Privat opsamling;Privat;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:institution#HAM;Haderslev Museum;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:archive#XXX;Uspecificeret arkiv;Opsamling af flintredskaber p\u00e5 et lille n\u00e6s, der skyder sig ud i engomr\u00e5det. Ingen kronologiske ledetyper, men skraberne har et neolitisk pr\u00e6g.;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:text#BLA;Blandet tekst;http://www.kulturarv.dk/fundogfortidsminder/skos/person#121231;N. Boysen;http://www.kulturarv.dk/fundogfortidsminder/skos/title#1358;K\u00f8bmand;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:role#216;Finder;http://www.kulturarv.dk/fundogfortidsminder/resource/map/171708;Agstrup;2020-01-17;Kort og Matrikelstyrelsen;M\u00e5 kun kopieres til personlig brug.;Kortet viser lokalitetens placering i Danmark.;http://www.kulturarv.dk/fundogfortidsminder/resource/map/171708;http://www.kulturarv.dk/fundogfortidsminder/skos/digitaldocumentation#USP;Uspecificeret",
-    "group": "slks",
-    "groups": [
-        {
-            "name": "slks"
-        }
-    ],
-    "name": "2d631790-3cbb-5a0d-9545-002da28d06bc",
-    
-    "oai_identifier": [
-        "2d631790-3cbb-5a0d-9545-002da28d06bc"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Bebyggelse"
-        },
-        {
-            "name": "havne og industrianl\u00e6g"
-        }
-    ],
-    "title": [
-        "Agstrup"
-    ],
-    "url": "http://www.kulturarv.dk/fundogfortidsminder/site/171708"
-}
\ No newline at end of file
diff --git a/oaitestdata/slks-ff/SET_1/json/2d885071-cbc8-5aba-a251-1b574fad2762.json b/oaitestdata/slks-ff/SET_1/json/2d885071-cbc8-5aba-a251-1b574fad2762.json
deleted file mode 100644
index bb0c35eb..00000000
--- a/oaitestdata/slks-ff/SET_1/json/2d885071-cbc8-5aba-a251-1b574fad2762.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "post@slks.dk"
-    ],
-    "DiscHierarchy": [
-        "1.1.4",
-        "Ancient Cultures",
-        "Classical Archaeology"
-    ],
-    "Discipline": "Classical Archaeology",
-    "Language": [
-        "Danish"
-    ],
-    "MetaDataAccess": "http://www.kulturarv.dk/ffrepox/OAIHandler?verb=GetRecord&metadataPrefix=ff&identifier=2d885071-cbc8-5aba-a251-1b574fad2762",
-    "PublicationTimestamp": "2020-01-17T11:59:59Z",
-    "PublicationYear": [
-        "2020"
-    ],
-    "Publisher": [
-        "Slots- og Kulturstyrelsen"
-    ],
-    "Rights" : [
-        "For scientific use"
-    ],
-    "notes": [
-        "This record describes ancient sites and monuments as well as archaeological excavations undertaken by Danish museums."
-    ],
-    "SpatialCoverage": [
-        "607816;6253363"
-    ],
-    "TemporalCoverage": " period : ( None - None ) ",
-    "author": [
-        "Moesg\u00e5rd Museum"
-    ],
-    "fulltext": "urn:repox.www.kulturarv.dkSites:http://www.kulturarv.dk/fundogfortidsminder/site/202526;2020-01-18;Sites;http://www.kulturarv.dk/fundogfortidsminder/site/202526;2020-01-17T17:00:01.923696+01:00;181;http://www.kulturarv.dk/fundogfortidsminder/skos/parish#140105;Ginnerup;http://www.kulturarv.dk/fundogfortidsminder/skos/plot#21;Usikker position fra gl. kort /dokument;Ginnerup;2011;http://www.kulturarv.dk/fundogfortidsminder/skos/placename#5;Bebyggelse, havne og industrianl\u00e6g;Ginnerup matr. nr. 2a;1908;http://www.kulturarv.dk/fundogfortidsminder/skos/placename#2;Ejendom, g\u00e5rd, hus;Sunddalvej-Neergaardsvej;2011;http://www.kulturarv.dk/fundogfortidsminder/skos/placename#4;Vej-, gade-, o.lign., evt. nr.+ bynavn;http://www.kulturarv.dk/fundogfortidsminder/skos/municipality#707;Norddjurs;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:institution#)MOE;Museum \u00d8stjylland;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:institution#FHM;Moesg\u00e5rd Museum;607816;6253363;http://www.kulturarv.dk/fundogfortidsminder/object/289229;Lokaliseringen er defineret med areal svarende til den fulde udstr\u00e6kning af matr. nr. 2a f\u00f8r udparcellering, jvf. matr. kort i arkiv hos KMS (funktionstid 1808-1996). Tidspunktet for udparcellering kendes ikke. Opdelingen medf\u00f8rte, at matr. 2a kun omfatter et mindre areal omkring selve g\u00e5rden.;175;374;CXXX;http://www.kulturarv.dk/fundogfortidsminder/skos/period#C\u00c6RY;Yngre Romersk Jernalder;Jernalder;http://www.kulturarv.dk/fundogfortidsminder/skos/object#01103;Jordf\u00e6stegrav;Begravelse;alle begravelsesformer;1930-01-01;1930-01-01;AM7814;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:event#GGM;Genstand givet til museum;Genstand;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:institution#FHM;Moesg\u00e5rd Museum;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:archive#PRO;Accessionsprotokol;Skeletgrav Matr. 2 a. Ginnerup, Ginnerup  Sogn, N\u00f8rre \nDyrs Herred. Yngre Romertid. 1930. 7814-15. \n7814.  meget   lille   vase, 11  h\u00f8j  Diameter  Bund  5. Bug 11, Rand 7, vandrette Riller paa Halsen lodrette paa Oversiden. \n7815. 1 Tand og 2 smaa Brudstykker af Bronce,;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:text#AFS;Kopi af tekst/indskrift;1930-01-01;1930-01-01;AM7815;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:event#GGM;Genstand givet til museum;Genstand;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:institution#FHM;Moesg\u00e5rd Museum;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:archive#PRO;Accessionsprotokol;Skeletgrav Matr. 2 a. Ginnerup, Ginnerup  Sogn, N\u00f8rre \nDyrs Herred. Yngre Romertid. 1930. 7814-15. \n7814.  meget   lille   vase, 11  h\u00f8j  Diameter  Bund  5. Bug 11, Rand 7, vandrette Riller paa Halsen lodrette paa Oversiden. \n7815. 1 Tand og 2 smaa Brudstykker af Bronce,;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:text#AFS;Kopi af tekst/indskrift;2012-06-11;2012-06-11;AM7814, AM7815;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:event#IHD;Registrering via historisk dokumentation;Sagsbehandling og planl\u00e6gning;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:institution#FHM;Moesg\u00e5rd Museum;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:archive#XXX;Uspecificeret arkiv;I museumsprotokollen oplyses det, at fundene er gjort p\u00e5 matr. nr. 2a. Denne matrikel ses p\u00e5 KMS arkivkort Original 2 med gyldighed 1908-1996, se evt. Matrieklkort p\u00e5 Nettet.\nDer foreg\u00e5r en del udparcellering, som ikke kan tidsf\u00e6stes pr\u00e6cist pga. kortets lange l\u00f8betid. Den st\u00f8rst mulige udstr\u00e6kning for 2a er afsat med areal i F&F, lokalitetspunktet er sat vilk\u00e5rligt.\n;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:text#DKC;DKC/KUAS-registrator kommentar;http://www.kulturarv.dk/fundogfortidsminder/skos/person#121080;D.H. Kristiansen;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:role#230;Uspecificeret;http://www.kulturarv.dk/fundogfortidsminder/resource/map/202526;Ginnerup matr. nr. 2a;2020-01-17;Kort og Matrikelstyrelsen;M\u00e5 kun kopieres til personlig brug.;Kortet viser lokalitetens placering i Danmark.;http://www.kulturarv.dk/fundogfortidsminder/resource/map/202526;http://www.kulturarv.dk/fundogfortidsminder/skos/digitaldocumentation#USP;Uspecificeret",
-    "group": "slks",
-    "groups": [
-        {
-            "name": "slks"
-        }
-    ],
-    "name": "2d885071-cbc8-5aba-a251-1b574fad2762",
-    
-    "oai_identifier": [
-        "2d885071-cbc8-5aba-a251-1b574fad2762"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Bebyggelse"
-        },
-        {
-            "name": "havne og industrianl\u00e6g"
-        },
-        {
-            "name": "Ejendom"
-        },
-        {
-            "name": "g\u00e5rd"
-        },
-        {
-            "name": "hus"
-        }
-    ],
-    "title": [
-        "Ginnerup",
-        "Ginnerup matr. nr. 2a",
-        "Sunddalvej-Neergaardsvej"
-    ],
-    "url": "http://www.kulturarv.dk/fundogfortidsminder/site/202526"
-}
\ No newline at end of file
diff --git a/oaitestdata/slks-ff/SET_1/json/7cc2f87f-d6bc-5242-9130-1805bb3147c6.json b/oaitestdata/slks-ff/SET_1/json/7cc2f87f-d6bc-5242-9130-1805bb3147c6.json
deleted file mode 100644
index bfdc3f93..00000000
--- a/oaitestdata/slks-ff/SET_1/json/7cc2f87f-d6bc-5242-9130-1805bb3147c6.json
+++ /dev/null
@@ -1,61 +0,0 @@
-{
-    "Contact": [
-        "post@slks.dk"
-    ],
-    "DiscHierarchy": [
-        "1.1.4",
-        "Ancient Cultures",
-        "Classical Archaeology"
-    ],
-    "Discipline": "Classical Archaeology",
-    "Language": [
-        "Danish"
-    ],
-    "MetaDataAccess": "http://www.kulturarv.dk/ffrepox/OAIHandler?verb=GetRecord&metadataPrefix=ff&identifier=7cc2f87f-d6bc-5242-9130-1805bb3147c6",
-    "PublicationTimestamp": "2020-01-17T11:59:59Z",
-    "PublicationYear": [
-        "2020"
-    ],
-    "Publisher": [
-        "Slots- og Kulturstyrelsen"
-    ]
-    "Rights": [
-        "For scientific use"
-    ],
-    "notes": [
-        "This record describes ancient sites and monuments as well as archaeological excavations undertaken by Danish museums."
-    ],
-    "SpatialCoverage": [
-        "591348;6075988"
-    ],
-    "TempCoverageBegin": 124634030399,
-    "TempCoverageEnd": 88375147199,
-    "TemporalCoverage": " period : ( 3950-07-01T11:59:59Z - 2801-07-01T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "3950-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "2801-07-01T11:59:59Z",
-    "author": [
-        "Odense Bys Museer"
-    ],
-    "fulltext": "urn:repox.www.kulturarv.dkSites:http://www.kulturarv.dk/fundogfortidsminder/site/9886;2020-01-18;Sites;http://www.kulturarv.dk/fundogfortidsminder/site/9886;2020-01-17T17:00:01.923696+01:00;100;http://www.kulturarv.dk/fundogfortidsminder/skos/parish#090704;Rise;http://www.kulturarv.dk/fundogfortidsminder/skos/plot#50;Digitaliseret 1981;Dungkj\u00e6r;1884;http://www.kulturarv.dk/fundogfortidsminder/skos/placename#9;Uspecificeret;29;1936;http://www.kulturarv.dk/fundogfortidsminder/skos/id#GMLL;Gammel/\u00e6ndret identifikation (land);http://www.kulturarv.dk/fundogfortidsminder/skos/parish#090704;Rise;1884;0;0;http://www.kulturarv.dk/fundogfortidsminder/skos/surroundings#DMK;Dyrket mark;http://www.kulturarv.dk/fundogfortidsminder/skos/monumentsign#10;Uvis;http://www.kulturarv.dk/fundogfortidsminder/skos/municipality#492;\u00c6r\u00f8;http://www.kulturarv.dk/fundogfortidsminder/skos/institution#)ASF;Ark\u00e6ologi Sydfyn;http://www.kulturarv.dk/fundogfortidsminder/skos/institution#OBM;Odense Bys Museer;591348;6075988;http://www.kulturarv.dk/fundogfortidsminder/object/12247;-3950;-2801;AXXX;http://www.kulturarv.dk/fundogfortidsminder/skos/period#AYTX;Tragtb\u00e6gerkultur;Bondestenalder;1884;http://www.kulturarv.dk/fundogfortidsminder/skos/preservationstate#6;Synligt men sv\u00e6rt beskadiget;http://www.kulturarv.dk/fundogfortidsminder/skos/object#01092;Rundh\u00f8j;Begravelse;alle begravelsesformer;http://www.kulturarv.dk/fundogfortidsminder/object/182264;-3950;-2801;AXXX;http://www.kulturarv.dk/fundogfortidsminder/skos/period#AYTX;Tragtb\u00e6gerkultur;Bondestenalder;1884;http://www.kulturarv.dk/fundogfortidsminder/skos/preservationstate#7;Antagelig tilintetgjort eller fjernet fra stedet;http://www.kulturarv.dk/fundogfortidsminder/skos/object#01151;Megalitgrav (uspecificeret type);Begravelse;alle begravelsesformer;1884;1884;http://www.kulturarv.dk/fundogfortidsminder/skos/event#GEF;Efterretning om forsvunden genstand;Genstand;http://www.kulturarv.dk/fundogfortidsminder/skos/institution#N01;Nationalmuseet, Danske Afd., Danmarks Oldtid;http://www.kulturarv.dk/fundogfortidsminder/skos/archive#SBT;Sognebeskrivelsen;1930;1936;http://www.kulturarv.dk/fundogfortidsminder/skos/event#LAG;Graveaktivitet/land- og skovbrug;Dyrkning og fiskeri;http://www.kulturarv.dk/fundogfortidsminder/skos/institution#N01;Nationalmuseet, Danske Afd., Danmarks Oldtid;http://www.kulturarv.dk/fundogfortidsminder/skos/archive#SBT;Sognebeskrivelsen;1936;1936;http://www.kulturarv.dk/fundogfortidsminder/skos/event#MBR;Museal berejsning;Museal;http://www.kulturarv.dk/fundogfortidsminder/skos/institution#N01;Nationalmuseet, Danske Afd., Danmarks Oldtid;http://www.kulturarv.dk/fundogfortidsminder/skos/archive#SBT;Sognebeskrivelsen;Svag h\u00f8jning paa det nederste af bakkeflade; meget flintbrok i overfladen. For en del aar siden gravede gdr. Madsen, Holme- gaard, nogle store sten op efter sigende fra et underjordisk kammer; under pl\u00f8jning var jorden faldet sammen under hestene. Der fandtes ingen oldsager. Dyssetomt.;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:text#BTE;Berejsertekst;http://www.kulturarv.dk/fundogfortidsminder/skos/person#117039;J. Jessen;http://www.kulturarv.dk/fundogfortidsminder/skos/role#211;Berejser;http://www.kulturarv.dk/fundogfortidsminder/skos/person#126895;J. Jessen;http://www.kulturarv.dk/fundogfortidsminder/skos/role#211;Berejser;1981;1981;http://www.kulturarv.dk/fundogfortidsminder/skos/event#MRC;Museal rekognoscering;Museal;http://www.kulturarv.dk/fundogfortidsminder/skos/institution#LMR;Langelands Museum;http://www.kulturarv.dk/fundogfortidsminder/skos/archive#XXX;Uspecificeret arkiv;http://www.kulturarv.dk/fundogfortidsminder/skos/person#119011;J. Bech;http://www.kulturarv.dk/fundogfortidsminder/skos/role#210;Ansvarlig;1884;1884;http://www.kulturarv.dk/fundogfortidsminder/skos/event#MBR;Museal berejsning;Museal;http://www.kulturarv.dk/fundogfortidsminder/skos/institution#N01;Nationalmuseet, Danske Afd., Danmarks Oldtid;http://www.kulturarv.dk/fundogfortidsminder/skos/archive#SBT;Sognebeskrivelsen;En anden Dysse er sl\u00f8jfet for c. 40 Aar siden, hvorved der fandtes mange Kiler.;http://www.kulturarv.dk/fundogfortidsminder/skos/ff:text#BTE;Berejsertekst;http://www.kulturarv.dk/fundogfortidsminder/skos/person#120812;H. Petersen;http://www.kulturarv.dk/fundogfortidsminder/skos/title#1341;Grosserer;http://www.kulturarv.dk/fundogfortidsminder/skos/role#211;Berejser;http://www.kulturarv.dk/fundogfortidsminder/skos/person#117030;H. Petersen;http://www.kulturarv.dk/fundogfortidsminder/skos/title#1341;Grosserer;http://www.kulturarv.dk/fundogfortidsminder/skos/role#211;Berejser;1840;1850;http://www.kulturarv.dk/fundogfortidsminder/skos/event#LSL;Sl\u00f8jfet ved land- og skovbrug;Dyrkning og fiskeri;http://www.kulturarv.dk/fundogfortidsminder/skos/institution#N01;Nationalmuseet, Danske Afd., Danmarks Oldtid;http://www.kulturarv.dk/fundogfortidsminder/skos/archive#SBT;Sognebeskrivelsen;http://www.kulturarv.dk/fundogfortidsminder/resource/map/9886;Dungkj\u00e6r;2020-01-17;Kort og Matrikelstyrelsen;M\u00e5 kun kopieres til personlig brug.;Kortet viser lokalitetens placering i Danmark.;http://www.kulturarv.dk/fundogfortidsminder/resource/map/9886;http://www.kulturarv.dk/fundogfortidsminder/skos/digitaldocumentation#USP;Uspecificeret",
-    "group": "slks",
-    "groups": [
-        {
-            "name": "slks"
-        }
-    ],
-    "name": "7cc2f87f-d6bc-5242-9130-1805bb3147c6",
-    "oai_identifier": [
-        "7cc2f87f-d6bc-5242-9130-1805bb3147c6"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Uspecificeret"
-        }
-    ],
-    "title": [
-        "Dungkj\u00e6r"
-    ],
-    "url": "http://www.kulturarv.dk/fundogfortidsminder/site/9886"
-}
\ No newline at end of file
diff --git a/oaitestdata/slks-ff/SET_1/json/7ce9b40b-d75b-5224-83bc-de67ae9d9a46.json b/oaitestdata/slks-ff/SET_1/json/7ce9b40b-d75b-5224-83bc-de67ae9d9a46.json
deleted file mode 100644
index cff6937d..00000000
--- a/oaitestdata/slks-ff/SET_1/json/7ce9b40b-d75b-5224-83bc-de67ae9d9a46.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-    "Contact": [
-        "post@slks.dk"
-    ],
-    "DiscHierarchy": [
-        "1.1.4",
-        "Ancient Cultures",
-        "Classical Archaeology"
-    ],
-    "Discipline": "Classical Archaeology",
-    "Language": [
-        "Danish"
-    ],
-    "MetaDataAccess": "http://www.kulturarv.dk/ffrepox/OAIHandler?verb=GetRecord&metadataPrefix=ff&identifier=7ce9b40b-d75b-5224-83bc-de67ae9d9a46",
-    "PublicationTimestamp": "2020-01-17T11:59:59Z",
-    "PublicationYear": [
-        "2020"
-    ],
-    "Publisher": [
-        "Slots- og Kulturstyrelsen"
-    ],
-    "Rights": [
-        "For scientific use"
-    ],
-    "SpatialCoverage": [
-        "566105;6363138"
-    ],
-    "TempCoverageBegin": 124634030399,
-    "TempCoverageEnd": 53662478399,
-    "TemporalCoverage": " period : ( 3950-07-01T11:59:59Z - 1701-07-01T11:59:59Z ) ",
-    "TemporalCoverage:BeginDate": "3950-07-01T11:59:59Z",
-    "TemporalCoverage:EndDate": "1701-07-01T11:59:59Z",
-    "author": [
-        "Nordjyllands Historiske Museum"
-    ],
-    "fulltext": "urn:repox.www.kulturarv.dkSites:http://www.kulturarv.dk/fundogfortidsminder/site/10751;2020-01-18;Sites;http://www.kulturarv.dk/fundogfortidsminder/site/10751;2020-01-17T17:00:01.923696+01:00;46;http://www.kulturarv.dk/fundogfortidsminder/skos/parish#100114;T\u00e5rs;http://www.kulturarv.dk/fundogfortidsminder/skos/plot#50;Digitaliseret 1981;Agdrup;1908;http://www.kulturarv.dk/fundogfortidsminder/skos/placename#5;Bebyggelse, havne og industrianl\u00e6g;http://www.kulturarv.dk/fundogfortidsminder/skos/municipality#860;Hj\u00f8rring;http://www.kulturarv.dk/fundogfortidsminder/skos/institution#)VHM;Vendsyssel Historiske Museum;http://www.kulturarv.dk/fundogfortidsminder/skos/institution#NJM;Nordjyllands Historiske Museum;566105;6363138;http://www.kulturarv.dk/fundogfortidsminder/object/13118;-3950;-1701;AXXX;http://www.kulturarv.dk/fundogfortidsminder/skos/period#AYXX;Neolitikum;Bondestenalder;http://www.kulturarv.dk/fundogfortidsminder/skos/object#01092;Rundh\u00f8j;Begravelse;alle begravelsesformer;http://www.kulturarv.dk/fundogfortidsminder/object/173050;-3950;-1701;AXXX;http://www.kulturarv.dk/fundogfortidsminder/skos/period#AYXX;Neolitikum;Bondestenalder;http://www.kulturarv.dk/fundogfortidsminder/skos/object#01046;Enkeltfund;Begravelse;alle begravelsesformer;1908;1908;http://www.kulturarv.dk/fundogfortidsminder/skos/event#MBR;Museal berejsning;Museal;http://www.kulturarv.dk/fundogfortidsminder/skos/institution#N01;Nationalmuseet, Danske Afd., Danmarks Oldtid;http://www.kulturarv.dk/fundogfortidsminder/skos/archive#SBT;Sognebeskrivelsen;H\u00f8jtomt, hvori der er fundet en Flint\u00f8xe.;http://www.kulturarv.dk/fundogfortidsminder/skos/text#BTE;Berejsertekst;http://www.kulturarv.dk/fundogfortidsminder/skos/person#117105;T. Thomsen;http://www.kulturarv.dk/fundogfortidsminder/skos/title#1421;gartner;http://www.kulturarv.dk/fundogfortidsminder/skos/role#211;Berejser;http://www.kulturarv.dk/fundogfortidsminder/skos/person#125261;T. Thomsen;http://www.kulturarv.dk/fundogfortidsminder/skos/title#1421;gartner;http://www.kulturarv.dk/fundogfortidsminder/skos/role#211;Berejser;http://www.kulturarv.dk/fundogfortidsminder/resource/map/10751;Agdrup;2020-01-17;Kort og Matrikelstyrelsen;M\u00e5 kun kopieres til personlig brug.;Kortet viser lokalitetens placering i Danmark.;http://www.kulturarv.dk/fundogfortidsminder/resource/map/10751;http://www.kulturarv.dk/fundogfortidsminder/skos/digitaldocumentation#USP;Uspecificeret",
-    "group": "slks",
-    "groups": [
-        {
-            "name": "slks"
-        }
-    ],
-    "name": "7ce9b40b-d75b-5224-83bc-de67ae9d9a46",
-    "notes": [
-        "This record describes ancient sites and monuments as well as archaeological excavations undertaken by Danish museums."
-    ],
-    "oai_identifier": [
-        "7ce9b40b-d75b-5224-83bc-de67ae9d9a46"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Bebyggelse"
-        },
-        {
-            "name": "havne og industrianl\u00e6g"
-        }
-    ],
-    "title": [
-        "Agdrup"
-    ],
-    "url": "http://www.kulturarv.dk/fundogfortidsminder/site/10751"
-}
\ No newline at end of file
diff --git a/oaitestdata/slks-oai_dc/SET_1/json/a937f99e-da2a-5c39-ac8d-37e3b0c7e6bd.json b/oaitestdata/slks-oai_dc/SET_1/json/a937f99e-da2a-5c39-ac8d-37e3b0c7e6bd.json
deleted file mode 100644
index d8d82044..00000000
--- a/oaitestdata/slks-oai_dc/SET_1/json/a937f99e-da2a-5c39-ac8d-37e3b0c7e6bd.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "Aarhus University (www.au.dk)",
-        "Slots- og Kulturstyrelsen (www.slks.dk)"
-    ],
-    "DiscHierarchy": [
-        "1.1.5",
-        "Ancient Cultures",
-        "Archaeology"
-    ],
-    "Discipline": "Archaeology",
-    "Language": [
-        "Danish"
-    ],
-    "MetaDataAccess": "https://www.archaeo.dk/ff/oai-pmh/?verb=GetRecord&metadataPrefix=oai_dc&identifier=a937f99e-da2a-5c39-ac8d-37e3b0c7e6bd",
-    "MetadataAccess": [
-        "http://www.kulturarv.dk/fundogfortidsminder/Lokalitet/34277/"
-    ],
-    "OpenAccess": "true",
-    "Publisher": [
-        "Aarhus University (www.au.dk)",
-        "Slots- og Kulturstyrelsen (www.slks.dk)"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "Public"
-    ],
-    "SpatialCoverage": [
-        "9.811246,56.302585"
-    ],
-    "TemporalCoverage": [
-        "Stenalder",
-        "-2800,-2351",
-        "AYEX"
-    ],
-    "author": [
-        "Moesg\u00e5rd Museum"
-    ],
-    "fulltext": "http://www.kulturarv.dk/fundogfortidsminder/Lokalitet/34277/;2020-03-06T17:00:01.743162+01:00;http://www.kulturarv.dk/fundogfortidsminder/Lokalitet/34277/;130511-10 Thors\u00f8;Moesg\u00e5rd Museum;This record describes ancient sites and monuments as well archaeological excavations undertaken by Danish museums. Excerpt of the Danish description of events:\n1929      : Overpl\u00f8jet rund H\u00f8j paa Top af h\u00f8j, bred Banke; 2 x 18 m. St\u00e6rkt uregelm\u00e6ssig Overflade, neddybet i Midten. Der fandtes i denne H\u00f8j for et Par Aar siden en Sten\u00f8xe med Skafthul og et Flintspyd; nylig er en M\u00e6ngde store Sten opgravet..1892      : I de senere Aar er denne H\u00f8j overpl\u00f8jet, saa det kan nu ikke sees, om den er brudt eller ej. Fodsteen eller andre Steen sees ikke. Den er bygt af Muld og har en meget smuk Form.1929      : Overpl\u00f8jet rund H\u00f8j paa Top af h\u00f8j, bred Banke; 2 x 18 m. St\u00e6rkt uregelm\u00e6ssig Overflade, neddybet i Midten. Der fandtes i denne H\u00f8j for et Par Aar siden en Sten\u00f8xe med Skafthul og et Flintspyd; nylig er en M\u00e6ngde store Sten opgravet..1892      : I de senere Aar er denne H\u00f8j overpl\u00f8jet, saa det kan nu ikke sees, om den er brudt eller ej. Fodsteen eller andre Steen sees ikke. Den er bygt af Muld og har en meget smuk Form.\n;Slots- og Kulturstyrelsen (www.slks.dk);Aarhus University (www.au.dk);Dataset;130511-10;dan;Thors\u00f8;9.811246,56.302585;Rundh\u00f8j;Round barrow, burial mound, Funerary;Stenalder;-2800,-2351;AYEX;Public",
-    "group": "slks",
-    "groups": [
-        {
-            "name": "slks"
-        }
-    ],
-    "name": "a937f99e-da2a-5c39-ac8d-37e3b0c7e6bd",
-    "notes": [
-        "This record describes ancient sites and monuments as well archaeological excavations undertaken by Danish museums. Excerpt of the Danish description of events:\n1929      : Overpl\u00f8jet rund H\u00f8j paa Top af h\u00f8j, bred Banke; 2 x 18 m. St\u00e6rkt uregelm\u00e6ssig Overflade, neddybet i Midten. Der fandtes i denne H\u00f8j for et Par Aar siden en Sten\u00f8xe med Skafthul og et Flintspyd; nylig er en M\u00e6ngde store Sten opgravet..1892      : I de senere Aar er denne H\u00f8j overpl\u00f8jet, saa det kan nu ikke sees, om den er brudt eller ej. Fodsteen eller andre Steen sees ikke. Den er bygt af Muld og har en meget smuk Form.1929      : Overpl\u00f8jet rund H\u00f8j paa Top af h\u00f8j, bred Banke; 2 x 18 m. St\u00e6rkt uregelm\u00e6ssig Overflade, neddybet i Midten. Der fandtes i denne H\u00f8j for et Par Aar siden en Sten\u00f8xe med Skafthul og et Flintspyd; nylig er en M\u00e6ngde store Sten opgravet..1892      : I de senere Aar er denne H\u00f8j overpl\u00f8jet, saa det kan nu ikke sees, om den er brudt eller ej. Fodsteen eller andre Steen sees ikke. Den er bygt af Muld og har en meget smuk Form.\n"
-    ],
-    "oai_identifier": [
-        "a937f99e-da2a-5c39-ac8d-37e3b0c7e6bd"
-    ],
-    "oai_set": "",
-    "state": "active",
-    "tags": [
-        {
-            "name": "Rundh\u00f8j"
-        },
-        {
-            "name": "Round barrow"
-        },
-        {
-            "name": "burial mound"
-        },
-        {
-            "name": "Funerary"
-        }
-    ],
-    "title": [
-        "130511-10 Thors\u00f8"
-    ],
-    "url": "http://www.kulturarv.dk/fundogfortidsminder/Lokalitet/34277/"
-}
\ No newline at end of file
diff --git a/oaitestdata/toar-oai_dc/578593c4-4cac-4890-be16-37e5619ff043_1/json/0426746d-a140-5e75-8d18-3dbb8303bec4.json b/oaitestdata/toar-oai_dc/578593c4-4cac-4890-be16-37e5619ff043_1/json/0426746d-a140-5e75-8d18-3dbb8303bec4.json
deleted file mode 100644
index 1c05c34d..00000000
--- a/oaitestdata/toar-oai_dc/578593c4-4cac-4890-be16-37e5619ff043_1/json/0426746d-a140-5e75-8d18-3dbb8303bec4.json
+++ /dev/null
@@ -1,35 +0,0 @@
-{
-    "DOI": "http://dx.doi.org/doi:10.7970/3985d2e30c1f4163830c18655df67675",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://b2share-testing.fz-juelich.de/api/oai2d?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:b2share.eudat.eu:b2rec/3985d2e30c1f4163830c18655df67675",
-    "MetadataAccess": [
-        "oai:b2share.eudat.eu:b2rec/3985d2e30c1f4163830c18655df67675"
-    ],
-    "PublicationTimestamp": "2019-09-26T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/3985d2e30c1f4163830c18655df67675;2019-09-26T10:29:19Z;578593c4-4cac-4890-be16-37e5619ff043;2019-09-26T10:29:19.169090+00:00;10.7970/3985d2e30c1f4163830c18655df67675;https://b2share-testing.fz-juelich.de/api/records/3985d2e30c1f4163830c18655df67675;oai:b2share.eudat.eu:b2rec/3985d2e30c1f4163830c18655df67675;info:eu-repo/semantics/openAccess;toar test",
-    "group": "toar",
-    "groups": [
-        {
-            "name": "toar"
-        }
-    ],
-    "name": "0426746d-a140-5e75-8d18-3dbb8303bec4",
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/3985d2e30c1f4163830c18655df67675"
-    ],
-    "oai_set": [
-        "578593c4-4cac-4890-be16-37e5619ff043"
-    ],
-    "state": "active",
-    "title": [
-        "toar test"
-    ],
-    "url": "https://b2share-testing.fz-juelich.de/api/records/3985d2e30c1f4163830c18655df67675"
-}
\ No newline at end of file
diff --git a/oaitestdata/toar-oai_dc/578593c4-4cac-4890-be16-37e5619ff043_1/json/b11ea8d2-fc39-562a-a25a-5d8a79ccb306.json b/oaitestdata/toar-oai_dc/578593c4-4cac-4890-be16-37e5619ff043_1/json/b11ea8d2-fc39-562a-a25a-5d8a79ccb306.json
deleted file mode 100644
index bcaa6398..00000000
--- a/oaitestdata/toar-oai_dc/578593c4-4cac-4890-be16-37e5619ff043_1/json/b11ea8d2-fc39-562a-a25a-5d8a79ccb306.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "Contact": [
-        "TOAR"
-    ],
-    "Contributor": [
-        "Aristizabal, Beatriz "
-    ],
-    "DOI": "http://dx.doi.org/doi:10.7970/2c06a8da0a33496cad35aca66f2d2b9e",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://b2share-testing.fz-juelich.de/api/oai2d?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:b2share.eudat.eu:b2rec/2c06a8da0a33496cad35aca66f2d2b9e",
-    "MetadataAccess": [
-        "oai:b2share.eudat.eu:b2rec/2c06a8da0a33496cad35aca66f2d2b9e"
-    ],
-    "PublicationTimestamp": "2019-10-09T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "TOAR"
-    ],
-    "ResourceType": [
-        "Collection"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/closedAccess",
-        "Creative Commons Attribution (CC-BY)"
-    ],
-    "author": [
-        "Schr\u00f6der, Sabine"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/2c06a8da0a33496cad35aca66f2d2b9e;2019-10-08T12:04:17Z;578593c4-4cac-4890-be16-37e5619ff043;Aristizabal, Beatriz ;Schr\u00f6der, Sabine;2019-10-08T12:04:17.925318+00:00;info:eu-repo/date/embargoEnd/2019-10-09T09:50:46.580Z;collection of surface measurements of station Gobernacion (UN_4058943), Colombia, submitted to the TOAR datacenter;10.7970/2c06a8da0a33496cad35aca66f2d2b9e;https://b2share-testing.fz-juelich.de/api/records/2c06a8da0a33496cad35aca66f2d2b9e;oai:b2share.eudat.eu:b2rec/2c06a8da0a33496cad35aca66f2d2b9e;eng;TOAR;info:eu-repo/semantics/closedAccess;Creative Commons Attribution (CC-BY);surface measurements of Gobernacion, Colombia;Collection",
-    "group": "toar",
-    "groups": [
-        {
-            "name": "toar"
-        }
-    ],
-    "name": "b11ea8d2-fc39-562a-a25a-5d8a79ccb306",
-    "notes": [
-        "collection of surface measurements of station Gobernacion (UN_4058943), Colombia, submitted to the TOAR datacenter"
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/2c06a8da0a33496cad35aca66f2d2b9e"
-    ],
-    "oai_set": [
-        "578593c4-4cac-4890-be16-37e5619ff043"
-    ],
-    "state": "active",
-    "title": [
-        "surface measurements of Gobernacion, Colombia"
-    ],
-    "url": "https://b2share-testing.fz-juelich.de/api/records/2c06a8da0a33496cad35aca66f2d2b9e"
-}
\ No newline at end of file
diff --git a/oaitestdata/toar-oai_dc/578593c4-4cac-4890-be16-37e5619ff043_1/json/ee57ccd1-4cb8-56d2-b2d7-9f9ff741cb48.json b/oaitestdata/toar-oai_dc/578593c4-4cac-4890-be16-37e5619ff043_1/json/ee57ccd1-4cb8-56d2-b2d7-9f9ff741cb48.json
deleted file mode 100644
index ba9529b9..00000000
--- a/oaitestdata/toar-oai_dc/578593c4-4cac-4890-be16-37e5619ff043_1/json/ee57ccd1-4cb8-56d2-b2d7-9f9ff741cb48.json
+++ /dev/null
@@ -1,57 +0,0 @@
-{
-    "Contact": [
-        "TOAR"
-    ],
-    "Contributor": [
-        "Aristizabal, Beatriz"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.7970/63b5621948a64019b7ea2a74251abc08",
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://b2share-testing.fz-juelich.de/api/oai2d?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:b2share.eudat.eu:b2rec/63b5621948a64019b7ea2a74251abc08",
-    "MetadataAccess": [
-        "oai:b2share.eudat.eu:b2rec/63b5621948a64019b7ea2a74251abc08"
-    ],
-    "PublicationTimestamp": "2019-10-08T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "TOAR"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess",
-        "Creative Commons Attribution (CC-BY)"
-    ],
-    "author": [
-        "Schr\u00f6der, Sabine"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/63b5621948a64019b7ea2a74251abc08;2019-10-08T12:14:09Z;578593c4-4cac-4890-be16-37e5619ff043;Aristizabal, Beatriz;Schr\u00f6der, Sabine;2019-10-08T12:14:09.637491+00:00;hourly surface ozone data for station Gobernacion (UN_4058943), Colombia, covering 2019-01 to 2019-06;10.7970/63b5621948a64019b7ea2a74251abc08;https://b2share-testing.fz-juelich.de/api/records/63b5621948a64019b7ea2a74251abc08;oai:b2share.eudat.eu:b2rec/63b5621948a64019b7ea2a74251abc08;eng;TOAR;info:eu-repo/semantics/openAccess;Creative Commons Attribution (CC-BY);hourly surface ozone data for station Gobernacion (UN_4058943), Colombia, covering 2019-01 to 2019-06;Dataset",
-    "group": "toar",
-    "groups": [
-        {
-            "name": "toar"
-        }
-    ],
-    "name": "ee57ccd1-4cb8-56d2-b2d7-9f9ff741cb48",
-    "notes": [
-        "hourly surface ozone data for station Gobernacion (UN_4058943), Colombia, covering 2019-01 to 2019-06"
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/63b5621948a64019b7ea2a74251abc08"
-    ],
-    "oai_set": [
-        "578593c4-4cac-4890-be16-37e5619ff043"
-    ],
-    "state": "active",
-    "title": [
-        "hourly surface ozone data for station Gobernacion (UN_4058943), Colombia, covering 2019-01 to 2019-06"
-    ],
-    "url": "https://b2share-testing.fz-juelich.de/api/records/63b5621948a64019b7ea2a74251abc08"
-}
\ No newline at end of file
diff --git a/oaitestdata/toar-oai_dc/8cb65167-71d4-4845-a454-5d56624568d2_1/json/25226e95-8881-52c3-a532-ea65f5d12c88.json b/oaitestdata/toar-oai_dc/8cb65167-71d4-4845-a454-5d56624568d2_1/json/25226e95-8881-52c3-a532-ea65f5d12c88.json
deleted file mode 100644
index 1505fddc..00000000
--- a/oaitestdata/toar-oai_dc/8cb65167-71d4-4845-a454-5d56624568d2_1/json/25226e95-8881-52c3-a532-ea65f5d12c88.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Chemistry;Atmospheric Chemistry",
-    "MetaDataAccess": "https://b2share-testing.fz-juelich.de/api/oai2d?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:b2share.eudat.eu:b2rec/78e8c312175c4af3a80b28cfe407b741",
-    "MetadataAccess": [
-        "oai:b2share.eudat.eu:b2rec/78e8c312175c4af3a80b28cfe407b741"
-    ],
-    "PublicationTimestamp": "2020-01-15T11:59:59Z",
-    "PublicationYear": [
-        "2020"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/78e8c312175c4af3a80b28cfe407b741;2020-01-15T15:49:22Z;8cb65167-71d4-4845-a454-5d56624568d2;2020-01-15T15:49:22.961101+00:00;https://b2share-testing.fz-juelich.de/api/records/78e8c312175c4af3a80b28cfe407b741;oai:b2share.eudat.eu:b2rec/78e8c312175c4af3a80b28cfe407b741;info:eu-repo/semantics/openAccess;This is the version of the TOAR metadata schema",
-    "group": "toar",
-    "groups": [
-        {
-            "name": "toar"
-        }
-    ],
-    "name": "25226e95-8881-52c3-a532-ea65f5d12c88",
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/78e8c312175c4af3a80b28cfe407b741"
-    ],
-    "oai_set": [
-        "8cb65167-71d4-4845-a454-5d56624568d2"
-    ],
-    "state": "active",
-    "title": [
-        "This is the version of the TOAR metadata schema"
-    ],
-    "url": "https://b2share-testing.fz-juelich.de/api/records/78e8c312175c4af3a80b28cfe407b741"
-}
\ No newline at end of file
diff --git a/oaitestdata/toar-oai_dc/8cb65167-71d4-4845-a454-5d56624568d2_1/json/720d438a-f3e9-5255-8c9e-cc663dd1f2e6.json b/oaitestdata/toar-oai_dc/8cb65167-71d4-4845-a454-5d56624568d2_1/json/720d438a-f3e9-5255-8c9e-cc663dd1f2e6.json
deleted file mode 100644
index 117c5d86..00000000
--- a/oaitestdata/toar-oai_dc/8cb65167-71d4-4845-a454-5d56624568d2_1/json/720d438a-f3e9-5255-8c9e-cc663dd1f2e6.json
+++ /dev/null
@@ -1,93 +0,0 @@
-{
-    "Contact": [
-        "The Tropospheric Ozone Assessment Report (TOAR)"
-    ],
-    "Contributor": [
-        "Schr\u00f6der, Sabine"
-    ],
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Chemistry;Atmospheric Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://b2share-testing.fz-juelich.de/api/oai2d?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:b2share.eudat.eu:b2rec/444eca4015574832b7e15802a4574c01",
-    "MetadataAccess": [
-        "oai:b2share.eudat.eu:b2rec/444eca4015574832b7e15802a4574c01"
-    ],
-    "PublicationTimestamp": "2020-01-15T11:59:59Z",
-    "PublicationYear": [
-        "2020"
-    ],
-    "Publisher": [
-        "The Tropospheric Ozone Assessment Report (TOAR)"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess",
-        "Creative Commons Attribution (CC-BY)"
-    ],
-    "author": [
-        "Huarong Zhao",
-        "Gen Zhang",
-        "Wanyun Xu",
-        "Zou Li",
-        "Ying Wang",
-        "Junli Jin",
-        "Xiaobin Xu, Ph.D.",
-        "Dingding Wang",
-        "Xiaochun Zhang",
-        "Dajiang Yu",
-        "Yuanzhen Dong",
-        "Qianli Ma",
-        "Weili Lin",
-        "Zhiqiang Ma"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/444eca4015574832b7e15802a4574c01;2020-01-15T21:10:38Z;8cb65167-71d4-4845-a454-5d56624568d2;Schr\u00f6der, Sabine;Xiaobin Xu, Ph.D.;Weili Lin;Wanyun Xu;Junli Jin;Ying Wang;Gen Zhang;Xiaochun Zhang;Zhiqiang Ma;Yuanzhen Dong;Qianli Ma;Dajiang Yu;Zou Li;Dingding Wang;Huarong Zhao;2020-01-15T16:23:34.180902+00:00;Information about the trends and spatial variations of tropospheric and surface ozone is crucial for assessing the impacts of ozone on human health, ecosystem, and climate. To answer the questions related to spatiotemporal variations of tropospheric ozone, the International Global Atmospheric Chemistry Project developed the Tropospheric Ozone Assessment Report (TOAR). However, few sites in China could be included in TOAR\u2019s assessment of long-term ozone trends. There have been only sporadic reports on long-term ozone measurements from a few individual Chinese sites. Here, we present an integrated analysis of long-term measurements of surface ozone from eight sites in China, including six Global Atmosphere Watch sites, one rural site, and one urban site. The sites are located in the North China Plain (NCP) and Yangtze River Delta (YRD), the underdeveloped region (the Northeast Plain), and the remote regions (Northwest and Southwest). Most of the ozone time-series analyzed have lengths over 11 years, with the longest and shortest dating back to 1994 and 2009, respectively. Seven annual and four seasonal ozone metrics, along with their trends and presentday values, are calculated following the TOAR methodologies. We compare the seasonal and diurnal cycles of ozone concentrations as well as the present-day values of ozone metrics among sites and discuss the long-term trends of the annual and seasonal metrics. We find large and significant increases of ozone metrics at the background site in the NCP, smaller increases at the global baseline site in western China, significant decreases at the site in Northern Xinjiang, and nearly no trend at other sites. Alarming high values of ozone metrics occur in the NCP and YRD, particularly in warmer seasons. Our results fill knowledge gaps in spatiotemporal changes of ozone metrics in China and can be of useful in the assessment of ozone impacts on human health and vegetation.;https://b2share-testing.fz-juelich.de/api/records/444eca4015574832b7e15802a4574c01;oai:b2share.eudat.eu:b2rec/444eca4015574832b7e15802a4574c01;eng;The Tropospheric Ozone Assessment Report (TOAR);info:eu-repo/semantics/openAccess;Creative Commons Attribution (CC-BY);surface ozone; China; exposure metrics; human health; vegetation; long-term trends;Data collection of \"Long-term changes of regional ozone in China: implications for human health and ecosystem impacts\";Text",
-    "group": "toar",
-    "groups": [
-        {
-            "name": "toar"
-        }
-    ],
-    "name": "720d438a-f3e9-5255-8c9e-cc663dd1f2e6",
-    "notes": [
-        "Information about the trends and spatial variations of tropospheric and surface ozone is crucial for assessing the impacts of ozone on human health, ecosystem, and climate. To answer the questions related to spatiotemporal variations of tropospheric ozone, the International Global Atmospheric Chemistry Project developed the Tropospheric Ozone Assessment Report (TOAR). However, few sites in China could be included in TOAR\u2019s assessment of long-term ozone trends. There have been only sporadic reports on long-term ozone measurements from a few individual Chinese sites. Here, we present an integrated analysis of long-term measurements of surface ozone from eight sites in China, including six Global Atmosphere Watch sites, one rural site, and one urban site. The sites are located in the North China Plain (NCP) and Yangtze River Delta (YRD), the underdeveloped region (the Northeast Plain), and the remote regions (Northwest and Southwest). Most of the ozone time-series analyzed have lengths over 11 years, with the longest and shortest dating back to 1994 and 2009, respectively. Seven annual and four seasonal ozone metrics, along with their trends and presentday values, are calculated following the TOAR methodologies. We compare the seasonal and diurnal cycles of ozone concentrations as well as the present-day values of ozone metrics among sites and discuss the long-term trends of the annual and seasonal metrics. We find large and significant increases of ozone metrics at the background site in the NCP, smaller increases at the global baseline site in western China, significant decreases at the site in Northern Xinjiang, and nearly no trend at other sites. Alarming high values of ozone metrics occur in the NCP and YRD, particularly in warmer seasons. Our results fill knowledge gaps in spatiotemporal changes of ozone metrics in China and can be of useful in the assessment of ozone impacts on human health and vegetation."
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/444eca4015574832b7e15802a4574c01"
-    ],
-    "oai_set": [
-        "8cb65167-71d4-4845-a454-5d56624568d2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "surface ozone"
-        },
-        {
-            "name": "China"
-        },
-        {
-            "name": "exposure metrics"
-        },
-        {
-            "name": "human health"
-        },
-        {
-            "name": "vegetation"
-        },
-        {
-            "name": "long-term trends"
-        }
-    ],
-    "title": [
-        "Data collection of \"Long-term changes of regional ozone in China: implications for human health and ecosystem impacts\""
-    ],
-    "url": "https://b2share-testing.fz-juelich.de/api/records/444eca4015574832b7e15802a4574c01"
-}
\ No newline at end of file
diff --git a/oaitestdata/toar-oai_dc/8cb65167-71d4-4845-a454-5d56624568d2_1/json/810fe0e6-6b17-59d3-99e0-62b7251af1b5.json b/oaitestdata/toar-oai_dc/8cb65167-71d4-4845-a454-5d56624568d2_1/json/810fe0e6-6b17-59d3-99e0-62b7251af1b5.json
deleted file mode 100644
index f919ef7e..00000000
--- a/oaitestdata/toar-oai_dc/8cb65167-71d4-4845-a454-5d56624568d2_1/json/810fe0e6-6b17-59d3-99e0-62b7251af1b5.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "TOAR"
-    ],
-    "Contributor": [
-        "Schr\u00f6der, Sabine",
-        "Xu Xiaobin"
-    ],
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Chemistry;Atmospheric Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://b2share-testing.fz-juelich.de/api/oai2d?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:b2share.eudat.eu:b2rec/0f6e65dcd18e4d2a909ffbc14556c236",
-    "MetadataAccess": [
-        "oai:b2share.eudat.eu:b2rec/0f6e65dcd18e4d2a909ffbc14556c236"
-    ],
-    "PublicationTimestamp": "2020-01-15T11:59:59Z",
-    "PublicationYear": [
-        "2020"
-    ],
-    "Publisher": [
-        "TOAR"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess",
-        "Creative Commons Attribution (CC-BY)"
-    ],
-    "author": [
-        "Schr\u00f6der, Sabine"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/0f6e65dcd18e4d2a909ffbc14556c236;2020-01-16T07:35:52Z;8cb65167-71d4-4845-a454-5d56624568d2;Xu Xiaobin;Xu Xiaobin;Xu Xiaobin;Schr\u00f6der, Sabine;Schr\u00f6der, Sabine;Schr\u00f6der, Sabine;2020-01-15T16:18:03.445164+00:00;Timeseries of 1-hourly measurements of ground-level ozone at station GuCheng (GCH), China.\nThese data were provided  by Prof.Dr. Xiaobin Xu of Key Laboratory for Atmospheric Chemistry (KLAC), Chinese Academy of Meteorological Sciences (CAMS), China Meteorological Administration (CMA) in the context of the Tropospheric Ozone Assessment Report (TOAR).\nFor further information about TOAR see http://www.igacproject.org/activities/TOAR.\nAn uptodate record of this data can be found in the TOAR database at https://toar-data.fz-juelich.de/api/getCoverage/?id=48237&sampling_method=hourly (not yet implemented);This timeseries belongs to the collection http://doi.org/10.7970/faa9dd8c58474fa68e187b5b7e4910e3 of TOAR datasets from station GuCheng (GCH), China.;The data are formatted as a csv file with variable header information. Each header line begins with # and contains key: value metadata elements. \nThe data file was generated by the TOAR database query https://toar-data.fz-juelich.de/api/getCoverage/?id=GCH&sampling_method=hourly&version_tag=1.0 (not yet implemented).\nA detailed description of the file format and the metadata elements can be found at: https://toar-data-portal.fz-juelich.de/docs/surfacedata/TOAR_file_format_v2.pdf (not yet implemented).\nSoftware tools for working with these data are available at https://gitlab... (not yet implemented).;https://b2share-testing.fz-juelich.de/api/records/0f6e65dcd18e4d2a909ffbc14556c236;oai:b2share.eudat.eu:b2rec/0f6e65dcd18e4d2a909ffbc14556c236;eng;TOAR;info:eu-repo/semantics/openAccess;Creative Commons Attribution (CC-BY);TOAR, air quality, tropospheric ozone;TOAR timeseries of ground-level ozone at station GuCheng (GCH), China;Dataset",
-    "group": "toar",
-    "groups": [
-        {
-            "name": "toar"
-        }
-    ],
-    "name": "810fe0e6-6b17-59d3-99e0-62b7251af1b5",
-    "notes": [
-        "Timeseries of 1-hourly measurements of ground-level ozone at station GuCheng (GCH), China.\nThese data were provided  by Prof.Dr. Xiaobin Xu of Key Laboratory for Atmospheric Chemistry (KLAC), Chinese Academy of Meteorological Sciences (CAMS), China Meteorological Administration (CMA) in the context of the Tropospheric Ozone Assessment Report (TOAR).\nFor further information about TOAR see http://www.igacproject.org/activities/TOAR.\nAn uptodate record of this data can be found in the TOAR database at https://toar-data.fz-juelich.de/api/getCoverage/?id=48237&sampling_method=hourly (not yet implemented)",
-        "This timeseries belongs to the collection http://doi.org/10.7970/faa9dd8c58474fa68e187b5b7e4910e3 of TOAR datasets from station GuCheng (GCH), China.",
-        "The data are formatted as a csv file with variable header information. Each header line begins with # and contains key: value metadata elements. \nThe data file was generated by the TOAR database query https://toar-data.fz-juelich.de/api/getCoverage/?id=GCH&sampling_method=hourly&version_tag=1.0 (not yet implemented).\nA detailed description of the file format and the metadata elements can be found at: https://toar-data-portal.fz-juelich.de/docs/surfacedata/TOAR_file_format_v2.pdf (not yet implemented).\nSoftware tools for working with these data are available at https://gitlab... (not yet implemented)."
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/0f6e65dcd18e4d2a909ffbc14556c236"
-    ],
-    "oai_set": [
-        "8cb65167-71d4-4845-a454-5d56624568d2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "TOAR"
-        },
-        {
-            "name": "air quality"
-        },
-        {
-            "name": "tropospheric ozone"
-        }
-    ],
-    "title": [
-        "TOAR timeseries of ground-level ozone at station GuCheng (GCH), China"
-    ],
-    "url": "https://b2share-testing.fz-juelich.de/api/records/0f6e65dcd18e4d2a909ffbc14556c236"
-}
\ No newline at end of file
diff --git a/oaitestdata/toar-oai_dc/8cb65167-71d4-4845-a454-5d56624568d2_1/json/983521e8-5ce1-5b2c-aaee-14b090e01263.json b/oaitestdata/toar-oai_dc/8cb65167-71d4-4845-a454-5d56624568d2_1/json/983521e8-5ce1-5b2c-aaee-14b090e01263.json
deleted file mode 100644
index 4d656a2d..00000000
--- a/oaitestdata/toar-oai_dc/8cb65167-71d4-4845-a454-5d56624568d2_1/json/983521e8-5ce1-5b2c-aaee-14b090e01263.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "The Tropospheric Ozone Assessment Report (TOAR)"
-    ],
-    "Contributor": [
-        "Guangsheng Zhou",
-        "Schr\u00f6der, Sabine",
-        "Xu Xiaobin"
-    ],
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Chemistry;Atmospheric Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://b2share-testing.fz-juelich.de/api/oai2d?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:b2share.eudat.eu:b2rec/faa9dd8c58474fa68e187b5b7e4910e3",
-    "MetadataAccess": [
-        "oai:b2share.eudat.eu:b2rec/faa9dd8c58474fa68e187b5b7e4910e3"
-    ],
-    "PublicationTimestamp": "2020-01-15T11:59:59Z",
-    "PublicationYear": [
-        "2020"
-    ],
-    "Publisher": [
-        "The Tropospheric Ozone Assessment Report (TOAR)"
-    ],
-    "ResourceType": [
-        "Collection"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess",
-        "Creative Commons Attribution (CC-BY)"
-    ],
-    "author": [
-        "Schr\u00f6der, Sabine"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/faa9dd8c58474fa68e187b5b7e4910e3;2020-01-15T16:21:38Z;8cb65167-71d4-4845-a454-5d56624568d2;Xu Xiaobin;Guangsheng Zhou;Schr\u00f6der, Sabine;Schr\u00f6der, Sabine;Schr\u00f6der, Sabine;2020-01-15T16:21:38.962951+00:00;Collection of air quality (and meteorological) measurement data at station GuCheng (GCH), China. \nThese data were provided  by Prof.Dr. Xiaobin Xu of Key Laboratory for Atmospheric Chemistry (KLAC), Chinese Academy of Meteorological Sciences (CAMS), China Meteorological Administration (CMA) in the context of the Tropospheric Ozone Assessment Report (TOAR).\nFor further information about TOAR see http://www.igacproject.org/activities/TOAR.\nAn uptodate record of this data collection can be found in the TOAR database at https://toar-data.fz-juelich.de/api/getStationMeta/?id=GCH (not yet implemented);The data contained in this collection are formatted as csv files with variable header information. Each header line begins with # and contains key: value metadata elements. \nThe data files in this collection were generated by TOAR database queries. For details, see technical information provided with each single station series.;Timeseries of 1-hourly ozone measurements at station GuCheng (GCH), China: http://doi.org/10.7970/0f6e65dcd18e4d2a909ffbc14556c236;https://b2share-testing.fz-juelich.de/api/records/faa9dd8c58474fa68e187b5b7e4910e3;oai:b2share.eudat.eu:b2rec/faa9dd8c58474fa68e187b5b7e4910e3;eng;The Tropospheric Ozone Assessment Report (TOAR);info:eu-repo/semantics/openAccess;Creative Commons Attribution (CC-BY);TOAR, air quality, tropospheric ozone;TOAR data collection at station GuCheng (GCH), China;Collection",
-    "group": "toar",
-    "groups": [
-        {
-            "name": "toar"
-        }
-    ],
-    "name": "983521e8-5ce1-5b2c-aaee-14b090e01263",
-    "notes": [
-        "Collection of air quality (and meteorological) measurement data at station GuCheng (GCH), China. \nThese data were provided  by Prof.Dr. Xiaobin Xu of Key Laboratory for Atmospheric Chemistry (KLAC), Chinese Academy of Meteorological Sciences (CAMS), China Meteorological Administration (CMA) in the context of the Tropospheric Ozone Assessment Report (TOAR).\nFor further information about TOAR see http://www.igacproject.org/activities/TOAR.\nAn uptodate record of this data collection can be found in the TOAR database at https://toar-data.fz-juelich.de/api/getStationMeta/?id=GCH (not yet implemented)",
-        "The data contained in this collection are formatted as csv files with variable header information. Each header line begins with # and contains key: value metadata elements. \nThe data files in this collection were generated by TOAR database queries. For details, see technical information provided with each single station series.",
-        "Timeseries of 1-hourly ozone measurements at station GuCheng (GCH), China: http://doi.org/10.7970/0f6e65dcd18e4d2a909ffbc14556c236"
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/faa9dd8c58474fa68e187b5b7e4910e3"
-    ],
-    "oai_set": [
-        "8cb65167-71d4-4845-a454-5d56624568d2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "TOAR"
-        },
-        {
-            "name": "air quality"
-        },
-        {
-            "name": "tropospheric ozone"
-        }
-    ],
-    "title": [
-        "TOAR data collection at station GuCheng (GCH), China"
-    ],
-    "url": "https://b2share-testing.fz-juelich.de/api/records/faa9dd8c58474fa68e187b5b7e4910e3"
-}
\ No newline at end of file
diff --git a/oaitestdata/toar-oai_dc/RDA_1/json/0979dd19-a33b-5fae-b614-bd4e0bbd117f.json b/oaitestdata/toar-oai_dc/RDA_1/json/0979dd19-a33b-5fae-b614-bd4e0bbd117f.json
deleted file mode 100644
index 5b434a58..00000000
--- a/oaitestdata/toar-oai_dc/RDA_1/json/0979dd19-a33b-5fae-b614-bd4e0bbd117f.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://b2share-testing.fz-juelich.de/api/oai2d?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:b2share.eudat.eu:b2rec/56ec7bf5bbe840c38d67f134d1575958",
-    "MetadataAccess": [
-        "oai:b2share.eudat.eu:b2rec/56ec7bf5bbe840c38d67f134d1575958"
-    ],
-    "PublicationTimestamp": "2019-07-25T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess",
-        "Creative Commons Attribution (CC-BY)"
-    ],
-    "author": [
-        "RDA2",
-        "Research Data Alliance Council"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/56ec7bf5bbe840c38d67f134d1575958;2019-07-25T11:01:58Z;8d963a29-5e19-492b-8cfe-97da4f54fad2;Research Data Alliance Council;RDA2;2019-07-25T11:01:58.195429+00:00;A document describing the high-level structures of the Research Data Alliance Foundation. This document is separate from the regular governance document, which describes procedures and processes.;https://b2share-testing.fz-juelich.de/api/records/56ec7bf5bbe840c38d67f134d1575958;oai:b2share.eudat.eu:b2rec/56ec7bf5bbe840c38d67f134d1575958;info:eu-repo/semantics/openAccess;Creative Commons Attribution (CC-BY);Research Data Alliance;RDA;Governance;Foundation;RDA Policy;RDA Foundation Governance Document;Text",
-    "group": "toar",
-    "groups": [
-        {
-            "name": "toar"
-        }
-    ],
-    "name": "0979dd19-a33b-5fae-b614-bd4e0bbd117f",
-    "notes": [
-        "A document describing the high-level structures of the Research Data Alliance Foundation. This document is separate from the regular governance document, which describes procedures and processes."
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/56ec7bf5bbe840c38d67f134d1575958"
-    ],
-    "oai_set": [
-        "8d963a29-5e19-492b-8cfe-97da4f54fad2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Research Data Alliance"
-        },
-        {
-            "name": "RDA"
-        },
-        {
-            "name": "Governance"
-        },
-        {
-            "name": "Foundation"
-        },
-        {
-            "name": "RDA Policy"
-        }
-    ],
-    "title": [
-        "RDA Foundation Governance Document"
-    ],
-    "url": "https://b2share-testing.fz-juelich.de/api/records/56ec7bf5bbe840c38d67f134d1575958"
-}
\ No newline at end of file
diff --git a/oaitestdata/toar-oai_dc/RDA_1/json/5a0061b0-2cea-5a5a-8eaa-12e14747d633.json b/oaitestdata/toar-oai_dc/RDA_1/json/5a0061b0-2cea-5a5a-8eaa-12e14747d633.json
deleted file mode 100644
index 10a71fc0..00000000
--- a/oaitestdata/toar-oai_dc/RDA_1/json/5a0061b0-2cea-5a5a-8eaa-12e14747d633.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://b2share-testing.fz-juelich.de/api/oai2d?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:b2share.eudat.eu:b2rec/47077e3c4b9f4852a40709e338ad4620",
-    "MetadataAccess": [
-        "oai:b2share.eudat.eu:b2rec/47077e3c4b9f4852a40709e338ad4620"
-    ],
-    "PublicationTimestamp": "2019-07-25T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess",
-        "Creative Commons Attribution (CC-BY)"
-    ],
-    "author": [
-        "RDA2",
-        "Research Data Alliance Council"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/47077e3c4b9f4852a40709e338ad4620;2019-07-25T11:01:57Z;8d963a29-5e19-492b-8cfe-97da4f54fad2;Research Data Alliance Council;RDA2;2019-07-25T11:01:57.570704+00:00;A document describing the high-level structures of the Research Data Alliance Foundation. This document is separate from the regular governance document, which describes procedures and processes.;https://b2share-testing.fz-juelich.de/api/records/47077e3c4b9f4852a40709e338ad4620;oai:b2share.eudat.eu:b2rec/47077e3c4b9f4852a40709e338ad4620;info:eu-repo/semantics/openAccess;Creative Commons Attribution (CC-BY);Research Data Alliance;RDA;Governance;Foundation;RDA Policy;RDA Foundation Governance Document;Text",
-    "group": "toar",
-    "groups": [
-        {
-            "name": "toar"
-        }
-    ],
-    "name": "5a0061b0-2cea-5a5a-8eaa-12e14747d633",
-    "notes": [
-        "A document describing the high-level structures of the Research Data Alliance Foundation. This document is separate from the regular governance document, which describes procedures and processes."
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/47077e3c4b9f4852a40709e338ad4620"
-    ],
-    "oai_set": [
-        "8d963a29-5e19-492b-8cfe-97da4f54fad2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Research Data Alliance"
-        },
-        {
-            "name": "RDA"
-        },
-        {
-            "name": "Governance"
-        },
-        {
-            "name": "Foundation"
-        },
-        {
-            "name": "RDA Policy"
-        }
-    ],
-    "title": [
-        "RDA Foundation Governance Document"
-    ],
-    "url": "https://b2share-testing.fz-juelich.de/api/records/47077e3c4b9f4852a40709e338ad4620"
-}
\ No newline at end of file
diff --git a/oaitestdata/toar-oai_dc/RDA_1/json/969e0205-9cf3-59b8-993f-9a3f01df4f19.json b/oaitestdata/toar-oai_dc/RDA_1/json/969e0205-9cf3-59b8-993f-9a3f01df4f19.json
deleted file mode 100644
index e2ff45f0..00000000
--- a/oaitestdata/toar-oai_dc/RDA_1/json/969e0205-9cf3-59b8-993f-9a3f01df4f19.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://b2share-testing.fz-juelich.de/api/oai2d?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:b2share.eudat.eu:b2rec/c7277c54c2b44ee1b42d7bc0ed28b7c6",
-    "MetadataAccess": [
-        "oai:b2share.eudat.eu:b2rec/c7277c54c2b44ee1b42d7bc0ed28b7c6"
-    ],
-    "PublicationTimestamp": "2019-07-25T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess",
-        "Creative Commons Attribution (CC-BY)"
-    ],
-    "author": [
-        "RDA2",
-        "Research Data Alliance Council"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/c7277c54c2b44ee1b42d7bc0ed28b7c6;2019-07-25T11:01:58Z;8d963a29-5e19-492b-8cfe-97da4f54fad2;Research Data Alliance Council;RDA2;2019-07-25T11:01:58.857614+00:00;A document describing the high-level structures of the Research Data Alliance Foundation. This document is separate from the regular governance document, which describes procedures and processes.;https://b2share-testing.fz-juelich.de/api/records/c7277c54c2b44ee1b42d7bc0ed28b7c6;oai:b2share.eudat.eu:b2rec/c7277c54c2b44ee1b42d7bc0ed28b7c6;info:eu-repo/semantics/openAccess;Creative Commons Attribution (CC-BY);Research Data Alliance;RDA;Governance;Foundation;RDA Policy;RDA Foundation Governance Document;Text",
-    "group": "toar",
-    "groups": [
-        {
-            "name": "toar"
-        }
-    ],
-    "name": "969e0205-9cf3-59b8-993f-9a3f01df4f19",
-    "notes": [
-        "A document describing the high-level structures of the Research Data Alliance Foundation. This document is separate from the regular governance document, which describes procedures and processes."
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/c7277c54c2b44ee1b42d7bc0ed28b7c6"
-    ],
-    "oai_set": [
-        "8d963a29-5e19-492b-8cfe-97da4f54fad2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Research Data Alliance"
-        },
-        {
-            "name": "RDA"
-        },
-        {
-            "name": "Governance"
-        },
-        {
-            "name": "Foundation"
-        },
-        {
-            "name": "RDA Policy"
-        }
-    ],
-    "title": [
-        "RDA Foundation Governance Document"
-    ],
-    "url": "https://b2share-testing.fz-juelich.de/api/records/c7277c54c2b44ee1b42d7bc0ed28b7c6"
-}
\ No newline at end of file
diff --git a/oaitestdata/toar-oai_dc/RDA_1/json/9ccc6163-fbad-5975-820e-c9b9b63d6bb4.json b/oaitestdata/toar-oai_dc/RDA_1/json/9ccc6163-fbad-5975-820e-c9b9b63d6bb4.json
deleted file mode 100644
index 8803b8ac..00000000
--- a/oaitestdata/toar-oai_dc/RDA_1/json/9ccc6163-fbad-5975-820e-c9b9b63d6bb4.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://b2share-testing.fz-juelich.de/api/oai2d?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:b2share.eudat.eu:b2rec/d6454861a8bb463382121e28b71ab770",
-    "MetadataAccess": [
-        "oai:b2share.eudat.eu:b2rec/d6454861a8bb463382121e28b71ab770"
-    ],
-    "PublicationTimestamp": "2019-07-25T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess",
-        "Creative Commons Attribution (CC-BY)"
-    ],
-    "author": [
-        "RDA2",
-        "Research Data Alliance Council"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/d6454861a8bb463382121e28b71ab770;2019-07-25T11:01:59Z;8d963a29-5e19-492b-8cfe-97da4f54fad2;Research Data Alliance Council;RDA2;2019-07-25T11:01:59.598779+00:00;A document describing the high-level structures of the Research Data Alliance Foundation. This document is separate from the regular governance document, which describes procedures and processes.;https://b2share-testing.fz-juelich.de/api/records/d6454861a8bb463382121e28b71ab770;oai:b2share.eudat.eu:b2rec/d6454861a8bb463382121e28b71ab770;info:eu-repo/semantics/openAccess;Creative Commons Attribution (CC-BY);Research Data Alliance;RDA;Governance;Foundation;RDA Policy;RDA Foundation Governance Document;Text",
-    "group": "toar",
-    "groups": [
-        {
-            "name": "toar"
-        }
-    ],
-    "name": "9ccc6163-fbad-5975-820e-c9b9b63d6bb4",
-    "notes": [
-        "A document describing the high-level structures of the Research Data Alliance Foundation. This document is separate from the regular governance document, which describes procedures and processes."
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/d6454861a8bb463382121e28b71ab770"
-    ],
-    "oai_set": [
-        "8d963a29-5e19-492b-8cfe-97da4f54fad2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Research Data Alliance"
-        },
-        {
-            "name": "RDA"
-        },
-        {
-            "name": "Governance"
-        },
-        {
-            "name": "Foundation"
-        },
-        {
-            "name": "RDA Policy"
-        }
-    ],
-    "title": [
-        "RDA Foundation Governance Document"
-    ],
-    "url": "https://b2share-testing.fz-juelich.de/api/records/d6454861a8bb463382121e28b71ab770"
-}
\ No newline at end of file
diff --git a/oaitestdata/toar-oai_dc/RDA_1/json/a5087b69-a796-5b1a-9d84-36929dcf734b.json b/oaitestdata/toar-oai_dc/RDA_1/json/a5087b69-a796-5b1a-9d84-36929dcf734b.json
deleted file mode 100644
index d6ea736f..00000000
--- a/oaitestdata/toar-oai_dc/RDA_1/json/a5087b69-a796-5b1a-9d84-36929dcf734b.json
+++ /dev/null
@@ -1,62 +0,0 @@
-{
-    "DiscHierarchy": [],
-    "Discipline": "Not stated",
-    "MetaDataAccess": "https://b2share-testing.fz-juelich.de/api/oai2d?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:b2share.eudat.eu:b2rec/618e6fe1927c4b5297450b8216f15c56",
-    "MetadataAccess": [
-        "oai:b2share.eudat.eu:b2rec/618e6fe1927c4b5297450b8216f15c56"
-    ],
-    "PublicationTimestamp": "2019-07-25T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "ResourceType": [
-        "Text"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess",
-        "Creative Commons Attribution (CC-BY)"
-    ],
-    "author": [
-        "RDA2",
-        "Research Data Alliance Council"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/618e6fe1927c4b5297450b8216f15c56;2019-07-25T11:02:00Z;8d963a29-5e19-492b-8cfe-97da4f54fad2;Research Data Alliance Council;RDA2;2019-07-25T11:02:00.368018+00:00;A document describing the high-level structures of the Research Data Alliance Foundation. This document is separate from the regular governance document, which describes procedures and processes.;https://b2share-testing.fz-juelich.de/api/records/618e6fe1927c4b5297450b8216f15c56;oai:b2share.eudat.eu:b2rec/618e6fe1927c4b5297450b8216f15c56;info:eu-repo/semantics/openAccess;Creative Commons Attribution (CC-BY);Research Data Alliance;RDA;Governance;Foundation;RDA Policy;RDA Foundation Governance Document;Text",
-    "group": "toar",
-    "groups": [
-        {
-            "name": "toar"
-        }
-    ],
-    "name": "a5087b69-a796-5b1a-9d84-36929dcf734b",
-    "notes": [
-        "A document describing the high-level structures of the Research Data Alliance Foundation. This document is separate from the regular governance document, which describes procedures and processes."
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/618e6fe1927c4b5297450b8216f15c56"
-    ],
-    "oai_set": [
-        "8d963a29-5e19-492b-8cfe-97da4f54fad2"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "Research Data Alliance"
-        },
-        {
-            "name": "RDA"
-        },
-        {
-            "name": "Governance"
-        },
-        {
-            "name": "Foundation"
-        },
-        {
-            "name": "RDA Policy"
-        }
-    ],
-    "title": [
-        "RDA Foundation Governance Document"
-    ],
-    "url": "https://b2share-testing.fz-juelich.de/api/records/618e6fe1927c4b5297450b8216f15c56"
-}
\ No newline at end of file
diff --git a/oaitestdata/toar-oai_dc/e153ef6e-20a4-49b2-a307-735f9d587f5c_1/json/12e6c0c2-2a10-5c53-b2e2-4b0a6b19343b.json b/oaitestdata/toar-oai_dc/e153ef6e-20a4-49b2-a307-735f9d587f5c_1/json/12e6c0c2-2a10-5c53-b2e2-4b0a6b19343b.json
deleted file mode 100644
index 9323d00a..00000000
--- a/oaitestdata/toar-oai_dc/e153ef6e-20a4-49b2-a307-735f9d587f5c_1/json/12e6c0c2-2a10-5c53-b2e2-4b0a6b19343b.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "The Tropospheric Ozone Assessment Report (TOAR)"
-    ],
-    "Contributor": [
-        "Aristiz\u00e1bal Zuluaga, Beatriz Helena",
-        "Schr\u00f6der, Sabine"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.7970/51dbbeb85280420d99a8c0115cb680da",
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Chemistry;Atmospheric Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://b2share-testing.fz-juelich.de/api/oai2d?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:b2share.eudat.eu:b2rec/51dbbeb85280420d99a8c0115cb680da",
-    "MetadataAccess": [
-        "oai:b2share.eudat.eu:b2rec/51dbbeb85280420d99a8c0115cb680da"
-    ],
-    "PublicationTimestamp": "2019-11-22T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Tropospheric Ozone Assessment Report (TOAR)"
-    ],
-    "ResourceType": [
-        "Collection"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess",
-        "Creative Commons Attribution (CC-BY)"
-    ],
-    "author": [
-        "Schr\u00f6der, Sabine"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/51dbbeb85280420d99a8c0115cb680da;2019-11-22T14:08:23Z;e153ef6e-20a4-49b2-a307-735f9d587f5c;Aristiz\u00e1bal Zuluaga, Beatriz Helena;Aristiz\u00e1bal Zuluaga, Beatriz Helena;Schr\u00f6der, Sabine;Schr\u00f6der, Sabine;Schr\u00f6der, Sabine;2019-11-22T14:08:23.525151+00:00;Collection of air quality (and meteorological) measurement data at station Gobernaci\u00f3n (UN_4058943), Colombia. \nThese data were provided by Beatriz Helena Aristiz\u00e1bal Zuluaga of Universidad Nacional de Colombia Sede Manizales (see contributors:data producer) in the context of the Tropospheric Ozone Assessment Report (TOAR).\nFor further information about TOAR see http://www.igacproject.org/activities/TOAR.\nAn uptodate record of this data collection can be found in the TOAR database at https://join.fz-juelich.de/services/rest/surfacedata/search/?station_id=UN_4058943&columns=station_id,station_name,station_country,station_lon,station_lat,station_alt,parameter_name,parameter_contributor&as_dict=True;The data contained in this collection are formatted as csv files with variable header information. Each header line begins with # and contains key: value metadata elements. \nThe data files in this collection were generated by TOAR database queries. For details, see technical information provided with each single station series.;Timeseries of 1-hourly ozone measurements at station Gobernaci\u00f3n (UN_4058943), Colombia: http://doi.org/10.7970/6663d3f5ff994d29a7a23a6b870990b4 \nTimeseries of 1-hourly carbon monoxide measurements at station Gobernaci\u00f3n (UN_4058943), Colombia: http://doi.org/10.7970/89668ee1d194406cb55bd716cb0ac1ce;10.7970/51dbbeb85280420d99a8c0115cb680da;https://b2share-testing.fz-juelich.de/api/records/51dbbeb85280420d99a8c0115cb680da;oai:b2share.eudat.eu:b2rec/51dbbeb85280420d99a8c0115cb680da;eng;The Tropospheric Ozone Assessment Report (TOAR);info:eu-repo/semantics/openAccess;Creative Commons Attribution (CC-BY);TOAR, air quality, tropospheric ozone;TOAR data collection at station Gobernaci\u00f3n (UN_4058943), Colombia;Collection",
-    "group": "toar",
-    "groups": [
-        {
-            "name": "toar"
-        }
-    ],
-    "name": "12e6c0c2-2a10-5c53-b2e2-4b0a6b19343b",
-    "notes": [
-        "Collection of air quality (and meteorological) measurement data at station Gobernaci\u00f3n (UN_4058943), Colombia. \nThese data were provided by Beatriz Helena Aristiz\u00e1bal Zuluaga of Universidad Nacional de Colombia Sede Manizales (see contributors:data producer) in the context of the Tropospheric Ozone Assessment Report (TOAR).\nFor further information about TOAR see http://www.igacproject.org/activities/TOAR.\nAn uptodate record of this data collection can be found in the TOAR database at https://join.fz-juelich.de/services/rest/surfacedata/search/?station_id=UN_4058943&columns=station_id,station_name,station_country,station_lon,station_lat,station_alt,parameter_name,parameter_contributor&as_dict=True",
-        "The data contained in this collection are formatted as csv files with variable header information. Each header line begins with # and contains key: value metadata elements. \nThe data files in this collection were generated by TOAR database queries. For details, see technical information provided with each single station series.",
-        "Timeseries of 1-hourly ozone measurements at station Gobernaci\u00f3n (UN_4058943), Colombia: http://doi.org/10.7970/6663d3f5ff994d29a7a23a6b870990b4 \nTimeseries of 1-hourly carbon monoxide measurements at station Gobernaci\u00f3n (UN_4058943), Colombia: http://doi.org/10.7970/89668ee1d194406cb55bd716cb0ac1ce"
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/51dbbeb85280420d99a8c0115cb680da"
-    ],
-    "oai_set": [
-        "e153ef6e-20a4-49b2-a307-735f9d587f5c"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "TOAR"
-        },
-        {
-            "name": "air quality"
-        },
-        {
-            "name": "tropospheric ozone"
-        }
-    ],
-    "title": [
-        "TOAR data collection at station Gobernaci\u00f3n (UN_4058943), Colombia"
-    ],
-    "url": "https://b2share-testing.fz-juelich.de/api/records/51dbbeb85280420d99a8c0115cb680da"
-}
\ No newline at end of file
diff --git a/oaitestdata/toar-oai_dc/e153ef6e-20a4-49b2-a307-735f9d587f5c_1/json/191468d5-8796-5eff-a23f-ca74712adad9.json b/oaitestdata/toar-oai_dc/e153ef6e-20a4-49b2-a307-735f9d587f5c_1/json/191468d5-8796-5eff-a23f-ca74712adad9.json
deleted file mode 100644
index 051dd2f2..00000000
--- a/oaitestdata/toar-oai_dc/e153ef6e-20a4-49b2-a307-735f9d587f5c_1/json/191468d5-8796-5eff-a23f-ca74712adad9.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "The Tropospheric Ozone Assessment Report (TOAR)"
-    ],
-    "Contributor": [
-        "Aristiz\u00e1bal Zuluaga, Beatriz Helena",
-        "Schr\u00f6der, Sabine"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.7970/ae517992a58f42b8978cd4c01e63b64c",
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Chemistry;Atmospheric Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://b2share-testing.fz-juelich.de/api/oai2d?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:b2share.eudat.eu:b2rec/ae517992a58f42b8978cd4c01e63b64c",
-    "MetadataAccess": [
-        "oai:b2share.eudat.eu:b2rec/ae517992a58f42b8978cd4c01e63b64c"
-    ],
-    "PublicationTimestamp": "2019-11-22T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Tropospheric Ozone Assessment Report (TOAR)"
-    ],
-    "ResourceType": [
-        "Collection"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess",
-        "Creative Commons Attribution (CC-BY)"
-    ],
-    "author": [
-        "Schr\u00f6der, Sabine"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/ae517992a58f42b8978cd4c01e63b64c;2019-11-22T14:04:36Z;e153ef6e-20a4-49b2-a307-735f9d587f5c;Aristiz\u00e1bal Zuluaga, Beatriz Helena;Aristiz\u00e1bal Zuluaga, Beatriz Helena;Schr\u00f6der, Sabine;Schr\u00f6der, Sabine;Schr\u00f6der, Sabine;2019-11-22T14:04:36.012874+00:00;Collection of air quality (and meteorological) measurement data at station Gobernaci\u00f3n (UN_4058943), Colombia. \nThese data were provided by Beatriz Helena Aristiz\u00e1bal Zuluaga of Universidad Nacional de Colombia Sede Manizales (see contributors:data producer) in the context of the Tropospheric Ozone Assessment Report (TOAR).\nFor further information about TOAR see http://www.igacproject.org/activities/TOAR.\nAn uptodate record of this data collection can be found in the TOAR database at https://join.fz-juelich.de/services/rest/surfacedata/search/?station_id=UN_4058943&columns=station_id,station_name,station_country,station_lon,station_lat,station_alt,parameter_name,parameter_contributor&as_dict=True;The data contained in this collection are formatted as csv files with variable header information. Each header line begins with # and contains key: value metadata elements. \nThe data files in this collection were generated by TOAR database queries. For details, see technical information provided with each single station series.;Timeseries of 1-hourly ozone measurements at station Gobernaci\u00f3n (UN_4058943), Colombia: http://doi.org/10.7970/6663d3f5ff994d29a7a23a6b870990b4 \nTimeseries of 1-hourly carbon monoxide measurements at station Gobernaci\u00f3n (UN_4058943), Colombia: http://doi.org/10.7970/89668ee1d194406cb55bd716cb0ac1ce;10.7970/ae517992a58f42b8978cd4c01e63b64c;https://b2share-testing.fz-juelich.de/api/records/ae517992a58f42b8978cd4c01e63b64c;oai:b2share.eudat.eu:b2rec/ae517992a58f42b8978cd4c01e63b64c;eng;The Tropospheric Ozone Assessment Report (TOAR);info:eu-repo/semantics/openAccess;Creative Commons Attribution (CC-BY);TOAR, air quality, tropospheric ozone;TOAR data collection at station Gobernaci\u00f3n (UN_4058943), Colombia;Collection",
-    "group": "toar",
-    "groups": [
-        {
-            "name": "toar"
-        }
-    ],
-    "name": "191468d5-8796-5eff-a23f-ca74712adad9",
-    "notes": [
-        "Collection of air quality (and meteorological) measurement data at station Gobernaci\u00f3n (UN_4058943), Colombia. \nThese data were provided by Beatriz Helena Aristiz\u00e1bal Zuluaga of Universidad Nacional de Colombia Sede Manizales (see contributors:data producer) in the context of the Tropospheric Ozone Assessment Report (TOAR).\nFor further information about TOAR see http://www.igacproject.org/activities/TOAR.\nAn uptodate record of this data collection can be found in the TOAR database at https://join.fz-juelich.de/services/rest/surfacedata/search/?station_id=UN_4058943&columns=station_id,station_name,station_country,station_lon,station_lat,station_alt,parameter_name,parameter_contributor&as_dict=True",
-        "The data contained in this collection are formatted as csv files with variable header information. Each header line begins with # and contains key: value metadata elements. \nThe data files in this collection were generated by TOAR database queries. For details, see technical information provided with each single station series.",
-        "Timeseries of 1-hourly ozone measurements at station Gobernaci\u00f3n (UN_4058943), Colombia: http://doi.org/10.7970/6663d3f5ff994d29a7a23a6b870990b4 \nTimeseries of 1-hourly carbon monoxide measurements at station Gobernaci\u00f3n (UN_4058943), Colombia: http://doi.org/10.7970/89668ee1d194406cb55bd716cb0ac1ce"
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/ae517992a58f42b8978cd4c01e63b64c"
-    ],
-    "oai_set": [
-        "e153ef6e-20a4-49b2-a307-735f9d587f5c"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "TOAR"
-        },
-        {
-            "name": "air quality"
-        },
-        {
-            "name": "tropospheric ozone"
-        }
-    ],
-    "title": [
-        "TOAR data collection at station Gobernaci\u00f3n (UN_4058943), Colombia"
-    ],
-    "url": "https://b2share-testing.fz-juelich.de/api/records/ae517992a58f42b8978cd4c01e63b64c"
-}
\ No newline at end of file
diff --git a/oaitestdata/toar-oai_dc/e153ef6e-20a4-49b2-a307-735f9d587f5c_1/json/4e279b9a-9c2d-5802-b66f-7a707bd9ad52.json b/oaitestdata/toar-oai_dc/e153ef6e-20a4-49b2-a307-735f9d587f5c_1/json/4e279b9a-9c2d-5802-b66f-7a707bd9ad52.json
deleted file mode 100644
index 6f289d71..00000000
--- a/oaitestdata/toar-oai_dc/e153ef6e-20a4-49b2-a307-735f9d587f5c_1/json/4e279b9a-9c2d-5802-b66f-7a707bd9ad52.json
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "Contact": [
-        "TOAR"
-    ],
-    "Contributor": [
-        "Aristiz\u00e1bal Zuluaga, Beatriz Helena"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.7970/e9e2e9a61c574d8f8edb6e438bf7f8ff",
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Chemistry;Atmospheric Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://b2share-testing.fz-juelich.de/api/oai2d?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:b2share.eudat.eu:b2rec/e9e2e9a61c574d8f8edb6e438bf7f8ff",
-    "MetadataAccess": [
-        "oai:b2share.eudat.eu:b2rec/e9e2e9a61c574d8f8edb6e438bf7f8ff"
-    ],
-    "PublicationTimestamp": "2019-11-19T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "TOAR"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess",
-        "Creative Commons Attribution (CC-BY)"
-    ],
-    "author": [
-        "Schr\u00f6der, Sabine"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/e9e2e9a61c574d8f8edb6e438bf7f8ff;2019-11-19T09:16:56Z;e153ef6e-20a4-49b2-a307-735f9d587f5c;Aristiz\u00e1bal Zuluaga, Beatriz Helena;Schr\u00f6der, Sabine;2019-11-19T09:16:56.961499+00:00;Timeseries of 1-hourly surface carbon monoxide measurements at station Gobernaci\u00f3n (UN_4058943), Colombia;10.7970/e9e2e9a61c574d8f8edb6e438bf7f8ff;https://b2share-testing.fz-juelich.de/api/records/e9e2e9a61c574d8f8edb6e438bf7f8ff;oai:b2share.eudat.eu:b2rec/e9e2e9a61c574d8f8edb6e438bf7f8ff;eng;TOAR;info:eu-repo/semantics/openAccess;Creative Commons Attribution (CC-BY);TOAR, air quality, global tropospheric ozone;Timeseries of surface carbon monoxide at station Gobernaci\u00f3n (UN_4058943), Colombia;Dataset",
-    "group": "toar",
-    "groups": [
-        {
-            "name": "toar"
-        }
-    ],
-    "name": "4e279b9a-9c2d-5802-b66f-7a707bd9ad52",
-    "notes": [
-        "Timeseries of 1-hourly surface carbon monoxide measurements at station Gobernaci\u00f3n (UN_4058943), Colombia"
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/e9e2e9a61c574d8f8edb6e438bf7f8ff"
-    ],
-    "oai_set": [
-        "e153ef6e-20a4-49b2-a307-735f9d587f5c"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "TOAR"
-        },
-        {
-            "name": "air quality"
-        },
-        {
-            "name": "global tropospheric ozone"
-        }
-    ],
-    "title": [
-        "Timeseries of surface carbon monoxide at station Gobernaci\u00f3n (UN_4058943), Colombia"
-    ],
-    "url": "https://b2share-testing.fz-juelich.de/api/records/e9e2e9a61c574d8f8edb6e438bf7f8ff"
-}
\ No newline at end of file
diff --git a/oaitestdata/toar-oai_dc/e153ef6e-20a4-49b2-a307-735f9d587f5c_1/json/7aa4227b-248a-5e4e-b9d5-3b4b16da2ac1.json b/oaitestdata/toar-oai_dc/e153ef6e-20a4-49b2-a307-735f9d587f5c_1/json/7aa4227b-248a-5e4e-b9d5-3b4b16da2ac1.json
deleted file mode 100644
index 9ce57a1a..00000000
--- a/oaitestdata/toar-oai_dc/e153ef6e-20a4-49b2-a307-735f9d587f5c_1/json/7aa4227b-248a-5e4e-b9d5-3b4b16da2ac1.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "TOAR"
-    ],
-    "Contributor": [
-        "Aristiz\u00e1bal Zuluaga, Beatriz Helena"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.7970/6663d3f5ff994d29a7a23a6b870990b4",
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Chemistry;Atmospheric Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://b2share-testing.fz-juelich.de/api/oai2d?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:b2share.eudat.eu:b2rec/6663d3f5ff994d29a7a23a6b870990b4",
-    "MetadataAccess": [
-        "oai:b2share.eudat.eu:b2rec/6663d3f5ff994d29a7a23a6b870990b4"
-    ],
-    "PublicationTimestamp": "2019-11-19T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "TOAR"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess",
-        "Creative Commons Attribution (CC-BY)"
-    ],
-    "author": [
-        "Schr\u00f6der, Sabine"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/6663d3f5ff994d29a7a23a6b870990b4;2019-11-26T13:45:57Z;e153ef6e-20a4-49b2-a307-735f9d587f5c;Aristiz\u00e1bal Zuluaga, Beatriz Helena;Schr\u00f6der, Sabine;2019-11-19T08:59:06.138905+00:00;Timeseries of 1-hourly measurements of ground-level ozone at station Gobernaci\u00f3n (UN_4058943), Colombia.\nThese data were provided by Beatriz Helena Aristiz\u00e1bal Zuluaga of Universidad Nacional de Colombia Sede Manizales (see contributors:data producer) in the context of the Tropospheric Ozone Assessment Report (TOAR).\nFor further information about TOAR see http://www.igacproject.org/activities/TOAR.\nAn uptodate record of this data can be found in the TOAR database at https://toar-data.fz-juelich.de/api/getCoverage/?id=99999&sampling_method=hourly;This timeseries belongs to the collection http://doi.org/10.7970/d6921f19f9f04c84b40017967adff8ee of TOAR datasets from station Gobernaci\u00f3n (UN_4058943), Colombia.;The data are formatted as a csv file with variable header information. Each header line begins with # and contains key: value metadata elements. \nThe data file was generated by the TOAR database query https://toar-data.fz-juelich.de/api/getCoverage/?id=99999&sampling_method=hourly&version_tag=...\nA detailed description of the file format and the metadata elements can be found at: https://toar-data-portal.fz-juelich.de/docs/surfacedata/TOAR_file_format_v2.pdf.\nSoftware tools for working with these data are available at https://gitlab...;10.7970/6663d3f5ff994d29a7a23a6b870990b4;https://b2share-testing.fz-juelich.de/api/records/6663d3f5ff994d29a7a23a6b870990b4;oai:b2share.eudat.eu:b2rec/6663d3f5ff994d29a7a23a6b870990b4;eng;TOAR;info:eu-repo/semantics/openAccess;Creative Commons Attribution (CC-BY);TOAR, air quality, tropospheric ozone;TOAR timeseries of ground-level ozone at station Gobernaci\u00f3n (UN_4058943), Colombia;Dataset",
-    "group": "toar",
-    "groups": [
-        {
-            "name": "toar"
-        }
-    ],
-    "name": "7aa4227b-248a-5e4e-b9d5-3b4b16da2ac1",
-    "notes": [
-        "Timeseries of 1-hourly measurements of ground-level ozone at station Gobernaci\u00f3n (UN_4058943), Colombia.\nThese data were provided by Beatriz Helena Aristiz\u00e1bal Zuluaga of Universidad Nacional de Colombia Sede Manizales (see contributors:data producer) in the context of the Tropospheric Ozone Assessment Report (TOAR).\nFor further information about TOAR see http://www.igacproject.org/activities/TOAR.\nAn uptodate record of this data can be found in the TOAR database at https://toar-data.fz-juelich.de/api/getCoverage/?id=99999&sampling_method=hourly",
-        "This timeseries belongs to the collection http://doi.org/10.7970/d6921f19f9f04c84b40017967adff8ee of TOAR datasets from station Gobernaci\u00f3n (UN_4058943), Colombia.",
-        "The data are formatted as a csv file with variable header information. Each header line begins with # and contains key: value metadata elements. \nThe data file was generated by the TOAR database query https://toar-data.fz-juelich.de/api/getCoverage/?id=99999&sampling_method=hourly&version_tag=...\nA detailed description of the file format and the metadata elements can be found at: https://toar-data-portal.fz-juelich.de/docs/surfacedata/TOAR_file_format_v2.pdf.\nSoftware tools for working with these data are available at https://gitlab..."
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/6663d3f5ff994d29a7a23a6b870990b4"
-    ],
-    "oai_set": [
-        "e153ef6e-20a4-49b2-a307-735f9d587f5c"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "TOAR"
-        },
-        {
-            "name": "air quality"
-        },
-        {
-            "name": "tropospheric ozone"
-        }
-    ],
-    "title": [
-        "TOAR timeseries of ground-level ozone at station Gobernaci\u00f3n (UN_4058943), Colombia"
-    ],
-    "url": "https://b2share-testing.fz-juelich.de/api/records/6663d3f5ff994d29a7a23a6b870990b4"
-}
\ No newline at end of file
diff --git a/oaitestdata/toar-oai_dc/e153ef6e-20a4-49b2-a307-735f9d587f5c_1/json/801951f3-3233-593b-80f5-2362a7812e71.json b/oaitestdata/toar-oai_dc/e153ef6e-20a4-49b2-a307-735f9d587f5c_1/json/801951f3-3233-593b-80f5-2362a7812e71.json
deleted file mode 100644
index 45e00f0e..00000000
--- a/oaitestdata/toar-oai_dc/e153ef6e-20a4-49b2-a307-735f9d587f5c_1/json/801951f3-3233-593b-80f5-2362a7812e71.json
+++ /dev/null
@@ -1,74 +0,0 @@
-{
-    "Contact": [
-        "TOAR"
-    ],
-    "Contributor": [
-        "Aristiz\u00e1bal Zuluaga, Beatriz Helena"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.7970/89668ee1d194406cb55bd716cb0ac1ce",
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Chemistry;Atmospheric Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://b2share-testing.fz-juelich.de/api/oai2d?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:b2share.eudat.eu:b2rec/89668ee1d194406cb55bd716cb0ac1ce",
-    "MetadataAccess": [
-        "oai:b2share.eudat.eu:b2rec/89668ee1d194406cb55bd716cb0ac1ce"
-    ],
-    "PublicationTimestamp": "2019-11-19T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "TOAR"
-    ],
-    "ResourceType": [
-        "Dataset"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess",
-        "Creative Commons Attribution (CC-BY)"
-    ],
-    "author": [
-        "Schr\u00f6der, Sabine"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/89668ee1d194406cb55bd716cb0ac1ce;2019-11-26T13:48:08Z;e153ef6e-20a4-49b2-a307-735f9d587f5c;Aristiz\u00e1bal Zuluaga, Beatriz Helena;Schr\u00f6der, Sabine;2019-11-19T09:38:43.603686+00:00;Timeseries of 1-hourly measurements of ground-level carbon monoxide at station Gobernaci\u00f3n (UN_4058943), Colombia.\nThese data were provided by Beatriz Helena Aristiz\u00e1bal Zuluaga of Universidad Nacional de Colombia Sede Manizales (see contributors:data producer) in the context of the Tropospheric Ozone Assessment Report (TOAR).\nFor further information about TOAR see http://www.igacproject.org/activities/TOAR.\nAn uptodate record of this data can be found in the TOAR database at https://toar-data.fz-juelich.de/api/getCoverage/?id=99999&sampling_method=hourly;This timeseries belongs to the collection http://doi.org/10.7970/d6921f19f9f04c84b40017967adff8ee of TOAR datasets from station Gobernaci\u00f3n (UN_4058943), Colombia.;The data are formatted as a csv file with variable header information. Each header line begins with # and contains key: value metadata elements. \nThe data file was generated by the TOAR database query https://toar-data.fz-juelich.de/api/getCoverage/?id=99999&sampling_method=hourly&version_tag=...\nA detailed description of the file format and the metadata elements can be found at: https://toar-data-portal.fz-juelich.de/docs/surfacedata/TOAR_file_format_v2.pdf.\nSoftware tools for working with these data are available at https://gitlab...;10.7970/89668ee1d194406cb55bd716cb0ac1ce;https://b2share-testing.fz-juelich.de/api/records/89668ee1d194406cb55bd716cb0ac1ce;oai:b2share.eudat.eu:b2rec/89668ee1d194406cb55bd716cb0ac1ce;eng;TOAR;info:eu-repo/semantics/openAccess;Creative Commons Attribution (CC-BY);TOAR, air quality, tropospheric ozone;TOAR timeseries of ground-level carbon monoxide at station Gobernaci\u00f3n (UN_4058943), Colombia;Dataset",
-    "group": "toar",
-    "groups": [
-        {
-            "name": "toar"
-        }
-    ],
-    "name": "801951f3-3233-593b-80f5-2362a7812e71",
-    "notes": [
-        "Timeseries of 1-hourly measurements of ground-level carbon monoxide at station Gobernaci\u00f3n (UN_4058943), Colombia.\nThese data were provided by Beatriz Helena Aristiz\u00e1bal Zuluaga of Universidad Nacional de Colombia Sede Manizales (see contributors:data producer) in the context of the Tropospheric Ozone Assessment Report (TOAR).\nFor further information about TOAR see http://www.igacproject.org/activities/TOAR.\nAn uptodate record of this data can be found in the TOAR database at https://toar-data.fz-juelich.de/api/getCoverage/?id=99999&sampling_method=hourly",
-        "This timeseries belongs to the collection http://doi.org/10.7970/d6921f19f9f04c84b40017967adff8ee of TOAR datasets from station Gobernaci\u00f3n (UN_4058943), Colombia.",
-        "The data are formatted as a csv file with variable header information. Each header line begins with # and contains key: value metadata elements. \nThe data file was generated by the TOAR database query https://toar-data.fz-juelich.de/api/getCoverage/?id=99999&sampling_method=hourly&version_tag=...\nA detailed description of the file format and the metadata elements can be found at: https://toar-data-portal.fz-juelich.de/docs/surfacedata/TOAR_file_format_v2.pdf.\nSoftware tools for working with these data are available at https://gitlab..."
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/89668ee1d194406cb55bd716cb0ac1ce"
-    ],
-    "oai_set": [
-        "e153ef6e-20a4-49b2-a307-735f9d587f5c"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "TOAR"
-        },
-        {
-            "name": "air quality"
-        },
-        {
-            "name": "tropospheric ozone"
-        }
-    ],
-    "title": [
-        "TOAR timeseries of ground-level carbon monoxide at station Gobernaci\u00f3n (UN_4058943), Colombia"
-    ],
-    "url": "https://b2share-testing.fz-juelich.de/api/records/89668ee1d194406cb55bd716cb0ac1ce"
-}
\ No newline at end of file
diff --git a/oaitestdata/toar-oai_dc/e153ef6e-20a4-49b2-a307-735f9d587f5c_1/json/908494ef-1b68-54a0-8df2-a5de9d9b557b.json b/oaitestdata/toar-oai_dc/e153ef6e-20a4-49b2-a307-735f9d587f5c_1/json/908494ef-1b68-54a0-8df2-a5de9d9b557b.json
deleted file mode 100644
index f9d3172e..00000000
--- a/oaitestdata/toar-oai_dc/e153ef6e-20a4-49b2-a307-735f9d587f5c_1/json/908494ef-1b68-54a0-8df2-a5de9d9b557b.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "The Tropospheric Ozone Assessment Report (TOAR)"
-    ],
-    "Contributor": [
-        "Aristiz\u00e1bal Zuluaga, Beatriz Helena",
-        "Schr\u00f6der, Sabine"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.7970/d6921f19f9f04c84b40017967adff8ee",
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Chemistry;Atmospheric Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://b2share-testing.fz-juelich.de/api/oai2d?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:b2share.eudat.eu:b2rec/d6921f19f9f04c84b40017967adff8ee",
-    "MetadataAccess": [
-        "oai:b2share.eudat.eu:b2rec/d6921f19f9f04c84b40017967adff8ee"
-    ],
-    "PublicationTimestamp": "2019-11-19T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Tropospheric Ozone Assessment Report (TOAR)"
-    ],
-    "ResourceType": [
-        "Collection"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess",
-        "Creative Commons Attribution (CC-BY)"
-    ],
-    "author": [
-        "Schr\u00f6der, Sabine"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/d6921f19f9f04c84b40017967adff8ee;2019-11-22T13:38:06Z;e153ef6e-20a4-49b2-a307-735f9d587f5c;Aristiz\u00e1bal Zuluaga, Beatriz Helena;Aristiz\u00e1bal Zuluaga, Beatriz Helena;Schr\u00f6der, Sabine;Schr\u00f6der, Sabine;Schr\u00f6der, Sabine;2019-11-19T09:00:05.192075+00:00;Collection of air quality (and meteorological) measurement data at station Gobernaci\u00f3n (UN_4058943), Colombia. \nThese data were provided by Beatriz Helena Aristiz\u00e1bal Zuluaga of Universidad Nacional de Colombia Sede Manizales (see contributors:data producer) in the context of the Tropospheric Ozone Assessment Report (TOAR).\nFor further information about TOAR see http://www.igacproject.org/activities/TOAR.\nAn uptodate record of this data collection can be found in the TOAR database at https://join.fz-juelich.de/services/rest/surfacedata/search/?station_id=UN_4058943&columns=station_id,station_name,station_country,station_lon,station_lat,station_alt,parameter_name,parameter_contributor&as_dict=True;The data contained in this collection are formatted as csv files with variable header information. Each header line begins with # and contains key: value metadata elements. \nThe data files in this collection were generated by TOAR database queries. For details, see technical information provided with each single station series.;Timeseries of 1-hourly ozone measurements at station Gobernaci\u00f3n (UN_4058943), Colombia: http://doi.org/10.7970/6663d3f5ff994d29a7a23a6b870990b4 \nTimeseries of 1-hourly carbon monoxide measurements at station Gobernaci\u00f3n (UN_4058943), Colombia: http://doi.org/10.7970/89668ee1d194406cb55bd716cb0ac1ce;10.7970/d6921f19f9f04c84b40017967adff8ee;https://b2share-testing.fz-juelich.de/api/records/d6921f19f9f04c84b40017967adff8ee;oai:b2share.eudat.eu:b2rec/d6921f19f9f04c84b40017967adff8ee;eng;The Tropospheric Ozone Assessment Report (TOAR);info:eu-repo/semantics/openAccess;Creative Commons Attribution (CC-BY);TOAR, air quality, tropospheric ozone;TOAR data collection at station Gobernaci\u00f3n (UN_4058943), Colombia;Collection",
-    "group": "toar",
-    "groups": [
-        {
-            "name": "toar"
-        }
-    ],
-    "name": "908494ef-1b68-54a0-8df2-a5de9d9b557b",
-    "notes": [
-        "Collection of air quality (and meteorological) measurement data at station Gobernaci\u00f3n (UN_4058943), Colombia. \nThese data were provided by Beatriz Helena Aristiz\u00e1bal Zuluaga of Universidad Nacional de Colombia Sede Manizales (see contributors:data producer) in the context of the Tropospheric Ozone Assessment Report (TOAR).\nFor further information about TOAR see http://www.igacproject.org/activities/TOAR.\nAn uptodate record of this data collection can be found in the TOAR database at https://join.fz-juelich.de/services/rest/surfacedata/search/?station_id=UN_4058943&columns=station_id,station_name,station_country,station_lon,station_lat,station_alt,parameter_name,parameter_contributor&as_dict=True",
-        "The data contained in this collection are formatted as csv files with variable header information. Each header line begins with # and contains key: value metadata elements. \nThe data files in this collection were generated by TOAR database queries. For details, see technical information provided with each single station series.",
-        "Timeseries of 1-hourly ozone measurements at station Gobernaci\u00f3n (UN_4058943), Colombia: http://doi.org/10.7970/6663d3f5ff994d29a7a23a6b870990b4 \nTimeseries of 1-hourly carbon monoxide measurements at station Gobernaci\u00f3n (UN_4058943), Colombia: http://doi.org/10.7970/89668ee1d194406cb55bd716cb0ac1ce"
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/d6921f19f9f04c84b40017967adff8ee"
-    ],
-    "oai_set": [
-        "e153ef6e-20a4-49b2-a307-735f9d587f5c"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "TOAR"
-        },
-        {
-            "name": "air quality"
-        },
-        {
-            "name": "tropospheric ozone"
-        }
-    ],
-    "title": [
-        "TOAR data collection at station Gobernaci\u00f3n (UN_4058943), Colombia"
-    ],
-    "url": "https://b2share-testing.fz-juelich.de/api/records/d6921f19f9f04c84b40017967adff8ee"
-}
\ No newline at end of file
diff --git a/oaitestdata/toar-oai_dc/e153ef6e-20a4-49b2-a307-735f9d587f5c_1/json/b54926fe-ec2c-598f-bc9d-e586276a6238.json b/oaitestdata/toar-oai_dc/e153ef6e-20a4-49b2-a307-735f9d587f5c_1/json/b54926fe-ec2c-598f-bc9d-e586276a6238.json
deleted file mode 100644
index a15a3273..00000000
--- a/oaitestdata/toar-oai_dc/e153ef6e-20a4-49b2-a307-735f9d587f5c_1/json/b54926fe-ec2c-598f-bc9d-e586276a6238.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "The Tropospheric Ozone Assessment Report (TOAR)"
-    ],
-    "Contributor": [
-        "Aristiz\u00e1bal Zuluaga, Beatriz Helena",
-        "Schr\u00f6der, Sabine"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.7970/40678354841e4f18b1b494f02384f9d2",
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Chemistry;Atmospheric Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://b2share-testing.fz-juelich.de/api/oai2d?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:b2share.eudat.eu:b2rec/40678354841e4f18b1b494f02384f9d2",
-    "MetadataAccess": [
-        "oai:b2share.eudat.eu:b2rec/40678354841e4f18b1b494f02384f9d2"
-    ],
-    "PublicationTimestamp": "2019-11-22T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Tropospheric Ozone Assessment Report (TOAR)"
-    ],
-    "ResourceType": [
-        "Collection"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess",
-        "Creative Commons Attribution (CC-BY)"
-    ],
-    "author": [
-        "Schr\u00f6der, Sabine"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/40678354841e4f18b1b494f02384f9d2;2019-11-22T14:07:22Z;e153ef6e-20a4-49b2-a307-735f9d587f5c;Aristiz\u00e1bal Zuluaga, Beatriz Helena;Aristiz\u00e1bal Zuluaga, Beatriz Helena;Schr\u00f6der, Sabine;Schr\u00f6der, Sabine;Schr\u00f6der, Sabine;2019-11-22T14:07:22.738499+00:00;Collection of air quality (and meteorological) measurement data at station Gobernaci\u00f3n (UN_4058943), Colombia. \nThese data were provided by Beatriz Helena Aristiz\u00e1bal Zuluaga of Universidad Nacional de Colombia Sede Manizales (see contributors:data producer) in the context of the Tropospheric Ozone Assessment Report (TOAR).\nFor further information about TOAR see http://www.igacproject.org/activities/TOAR.\nAn uptodate record of this data collection can be found in the TOAR database at https://join.fz-juelich.de/services/rest/surfacedata/search/?station_id=UN_4058943&columns=station_id,station_name,station_country,station_lon,station_lat,station_alt,parameter_name,parameter_contributor&as_dict=True;The data contained in this collection are formatted as csv files with variable header information. Each header line begins with # and contains key: value metadata elements. \nThe data files in this collection were generated by TOAR database queries. For details, see technical information provided with each single station series.;Timeseries of 1-hourly ozone measurements at station Gobernaci\u00f3n (UN_4058943), Colombia: http://doi.org/10.7970/6663d3f5ff994d29a7a23a6b870990b4 \nTimeseries of 1-hourly carbon monoxide measurements at station Gobernaci\u00f3n (UN_4058943), Colombia: http://doi.org/10.7970/89668ee1d194406cb55bd716cb0ac1ce;10.7970/40678354841e4f18b1b494f02384f9d2;https://b2share-testing.fz-juelich.de/api/records/40678354841e4f18b1b494f02384f9d2;oai:b2share.eudat.eu:b2rec/40678354841e4f18b1b494f02384f9d2;eng;The Tropospheric Ozone Assessment Report (TOAR);info:eu-repo/semantics/openAccess;Creative Commons Attribution (CC-BY);TOAR, air quality, tropospheric ozone;TOAR data collection at station Gobernaci\u00f3n (UN_4058943), Colombia;Collection",
-    "group": "toar",
-    "groups": [
-        {
-            "name": "toar"
-        }
-    ],
-    "name": "b54926fe-ec2c-598f-bc9d-e586276a6238",
-    "notes": [
-        "Collection of air quality (and meteorological) measurement data at station Gobernaci\u00f3n (UN_4058943), Colombia. \nThese data were provided by Beatriz Helena Aristiz\u00e1bal Zuluaga of Universidad Nacional de Colombia Sede Manizales (see contributors:data producer) in the context of the Tropospheric Ozone Assessment Report (TOAR).\nFor further information about TOAR see http://www.igacproject.org/activities/TOAR.\nAn uptodate record of this data collection can be found in the TOAR database at https://join.fz-juelich.de/services/rest/surfacedata/search/?station_id=UN_4058943&columns=station_id,station_name,station_country,station_lon,station_lat,station_alt,parameter_name,parameter_contributor&as_dict=True",
-        "The data contained in this collection are formatted as csv files with variable header information. Each header line begins with # and contains key: value metadata elements. \nThe data files in this collection were generated by TOAR database queries. For details, see technical information provided with each single station series.",
-        "Timeseries of 1-hourly ozone measurements at station Gobernaci\u00f3n (UN_4058943), Colombia: http://doi.org/10.7970/6663d3f5ff994d29a7a23a6b870990b4 \nTimeseries of 1-hourly carbon monoxide measurements at station Gobernaci\u00f3n (UN_4058943), Colombia: http://doi.org/10.7970/89668ee1d194406cb55bd716cb0ac1ce"
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/40678354841e4f18b1b494f02384f9d2"
-    ],
-    "oai_set": [
-        "e153ef6e-20a4-49b2-a307-735f9d587f5c"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "TOAR"
-        },
-        {
-            "name": "air quality"
-        },
-        {
-            "name": "tropospheric ozone"
-        }
-    ],
-    "title": [
-        "TOAR data collection at station Gobernaci\u00f3n (UN_4058943), Colombia"
-    ],
-    "url": "https://b2share-testing.fz-juelich.de/api/records/40678354841e4f18b1b494f02384f9d2"
-}
\ No newline at end of file
diff --git a/oaitestdata/toar-oai_dc/e153ef6e-20a4-49b2-a307-735f9d587f5c_1/json/e9edf5a9-3121-5128-98d9-62c3b788d886.json b/oaitestdata/toar-oai_dc/e153ef6e-20a4-49b2-a307-735f9d587f5c_1/json/e9edf5a9-3121-5128-98d9-62c3b788d886.json
deleted file mode 100644
index 552e0624..00000000
--- a/oaitestdata/toar-oai_dc/e153ef6e-20a4-49b2-a307-735f9d587f5c_1/json/e9edf5a9-3121-5128-98d9-62c3b788d886.json
+++ /dev/null
@@ -1,75 +0,0 @@
-{
-    "Contact": [
-        "The Tropospheric Ozone Assessment Report (TOAR)"
-    ],
-    "Contributor": [
-        "Aristiz\u00e1bal Zuluaga, Beatriz Helena",
-        "Schr\u00f6der, Sabine"
-    ],
-    "DOI": "http://dx.doi.org/doi:10.7970/8ed52eb8e01c4704ae2f1142520e72be",
-    "DiscHierarchy": [
-        "4.4.1.3",
-        "Atmospheric Sciences",
-        "Atmospheric chemistry"
-    ],
-    "Discipline": "Chemistry;Atmospheric Chemistry",
-    "Language": [
-        "English"
-    ],
-    "MetaDataAccess": "https://b2share-testing.fz-juelich.de/api/oai2d?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:b2share.eudat.eu:b2rec/8ed52eb8e01c4704ae2f1142520e72be",
-    "MetadataAccess": [
-        "oai:b2share.eudat.eu:b2rec/8ed52eb8e01c4704ae2f1142520e72be"
-    ],
-    "PublicationTimestamp": "2019-11-22T11:59:59Z",
-    "PublicationYear": [
-        "2019"
-    ],
-    "Publisher": [
-        "The Tropospheric Ozone Assessment Report (TOAR)"
-    ],
-    "ResourceType": [
-        "Collection"
-    ],
-    "Rights": [
-        "info:eu-repo/semantics/openAccess",
-        "Creative Commons Attribution (CC-BY)"
-    ],
-    "author": [
-        "Schr\u00f6der, Sabine"
-    ],
-    "fulltext": "oai:b2share.eudat.eu:b2rec/8ed52eb8e01c4704ae2f1142520e72be;2019-11-22T14:02:12Z;e153ef6e-20a4-49b2-a307-735f9d587f5c;Aristiz\u00e1bal Zuluaga, Beatriz Helena;Aristiz\u00e1bal Zuluaga, Beatriz Helena;Schr\u00f6der, Sabine;Schr\u00f6der, Sabine;Schr\u00f6der, Sabine;2019-11-22T14:02:12.117579+00:00;Collection of air quality (and meteorological) measurement data at station Gobernaci\u00f3n (UN_4058943), Colombia. \nThese data were provided by Beatriz Helena Aristiz\u00e1bal Zuluaga of Universidad Nacional de Colombia Sede Manizales (see contributors:data producer) in the context of the Tropospheric Ozone Assessment Report (TOAR).\nFor further information about TOAR see http://www.igacproject.org/activities/TOAR.\nAn uptodate record of this data collection can be found in the TOAR database at https://join.fz-juelich.de/services/rest/surfacedata/search/?station_id=UN_4058943&columns=station_id,station_name,station_country,station_lon,station_lat,station_alt,parameter_name,parameter_contributor&as_dict=True;The data contained in this collection are formatted as csv files with variable header information. Each header line begins with # and contains key: value metadata elements. \nThe data files in this collection were generated by TOAR database queries. For details, see technical information provided with each single station series.;Timeseries of 1-hourly ozone measurements at station Gobernaci\u00f3n (UN_4058943), Colombia: http://doi.org/10.7970/6663d3f5ff994d29a7a23a6b870990b4 \nTimeseries of 1-hourly carbon monoxide measurements at station Gobernaci\u00f3n (UN_4058943), Colombia: http://doi.org/10.7970/89668ee1d194406cb55bd716cb0ac1ce;10.7970/8ed52eb8e01c4704ae2f1142520e72be;https://b2share-testing.fz-juelich.de/api/records/8ed52eb8e01c4704ae2f1142520e72be;oai:b2share.eudat.eu:b2rec/8ed52eb8e01c4704ae2f1142520e72be;eng;The Tropospheric Ozone Assessment Report (TOAR);info:eu-repo/semantics/openAccess;Creative Commons Attribution (CC-BY);TOAR, air quality, tropospheric ozone;TOAR data collection at station Gobernaci\u00f3n (UN_4058943), Colombia;Collection",
-    "group": "toar",
-    "groups": [
-        {
-            "name": "toar"
-        }
-    ],
-    "name": "e9edf5a9-3121-5128-98d9-62c3b788d886",
-    "notes": [
-        "Collection of air quality (and meteorological) measurement data at station Gobernaci\u00f3n (UN_4058943), Colombia. \nThese data were provided by Beatriz Helena Aristiz\u00e1bal Zuluaga of Universidad Nacional de Colombia Sede Manizales (see contributors:data producer) in the context of the Tropospheric Ozone Assessment Report (TOAR).\nFor further information about TOAR see http://www.igacproject.org/activities/TOAR.\nAn uptodate record of this data collection can be found in the TOAR database at https://join.fz-juelich.de/services/rest/surfacedata/search/?station_id=UN_4058943&columns=station_id,station_name,station_country,station_lon,station_lat,station_alt,parameter_name,parameter_contributor&as_dict=True",
-        "The data contained in this collection are formatted as csv files with variable header information. Each header line begins with # and contains key: value metadata elements. \nThe data files in this collection were generated by TOAR database queries. For details, see technical information provided with each single station series.",
-        "Timeseries of 1-hourly ozone measurements at station Gobernaci\u00f3n (UN_4058943), Colombia: http://doi.org/10.7970/6663d3f5ff994d29a7a23a6b870990b4 \nTimeseries of 1-hourly carbon monoxide measurements at station Gobernaci\u00f3n (UN_4058943), Colombia: http://doi.org/10.7970/89668ee1d194406cb55bd716cb0ac1ce"
-    ],
-    "oai_identifier": [
-        "oai:b2share.eudat.eu:b2rec/8ed52eb8e01c4704ae2f1142520e72be"
-    ],
-    "oai_set": [
-        "e153ef6e-20a4-49b2-a307-735f9d587f5c"
-    ],
-    "state": "active",
-    "tags": [
-        {
-            "name": "TOAR"
-        },
-        {
-            "name": "air quality"
-        },
-        {
-            "name": "tropospheric ozone"
-        }
-    ],
-    "title": [
-        "TOAR data collection at station Gobernaci\u00f3n (UN_4058943), Colombia"
-    ],
-    "url": "https://b2share-testing.fz-juelich.de/api/records/8ed52eb8e01c4704ae2f1142520e72be"
-}
\ No newline at end of file